Merge tag 'dmaengine-fix-5.10-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine
Pull dmaengine fixes from Vinod Koul:
"A solitary core fix and a few driver fixes:
Core:
- channel_register error handling
Driver fixes:
- idxd: wq config registers programming and mapping of portal size
- ioatdma: unused fn removal
- pl330: fix burst size
- ti: pm fix on busy and -Wenum-conversion warns
- xilinx: SG capability check, usage of xilinx_aximcdma_tx_segment,
readl_poll_timeout_atomic variant"
* tag 'dmaengine-fix-5.10-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine:
dmaengine: fix error codes in channel_register()
dmaengine: pl330: _prep_dma_memcpy: Fix wrong burst size
dmaengine: ioatdma: remove unused function missed during dma_v2 removal
dmaengine: idxd: fix mapping of portal size
dmaengine: ti: omap-dma: Block PM if SDMA is busy to fix audio
dmaengine: xilinx_dma: Fix SG capability check for MCDMA
dmaengine: xilinx_dma: Fix usage of xilinx_aximcdma_tx_segment
dmaengine: xilinx_dma: use readl_poll_timeout_atomic variant
dmaengine: ti: k3-udma: fix -Wenum-conversion warning
dmaengine: idxd: fix wq config registers offset programming
diff --git a/.mailmap b/.mailmap
index 1e14566..505b3d7 100644
--- a/.mailmap
+++ b/.mailmap
@@ -82,7 +82,10 @@
Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com>
Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com>
<dev.kurt@vandijck-laurijssen.be> <kurt.van.dijck@eia.be>
-Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
+Dmitry Baryshkov <dbaryshkov@gmail.com>
+Dmitry Baryshkov <dbaryshkov@gmail.com> <[dbaryshkov@gmail.com]>
+Dmitry Baryshkov <dbaryshkov@gmail.com> <dmitry_baryshkov@mentor.com>
+Dmitry Baryshkov <dbaryshkov@gmail.com> <dmitry_eremin@mentor.com>
Dmitry Safonov <0x7f454c46@gmail.com> <dima@arista.com>
Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com>
Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com>
diff --git a/CREDITS b/CREDITS
index cb02b99..7483019 100644
--- a/CREDITS
+++ b/CREDITS
@@ -98,7 +98,7 @@
E: andersen@codepoet.org
W: https://www.codepoet.org/
P: 1024D/30D39057 1BC4 2742 E885 E4DE 9301 0C82 5F9B 643E 30D3 9057
-D: Maintainer of ide-cd and Uniform CD-ROM driver,
+D: Maintainer of ide-cd and Uniform CD-ROM driver,
D: ATAPI CD-Changer support, Major 2.1.x CD-ROM update.
S: 352 North 525 East
S: Springville, Utah 84663
@@ -263,7 +263,7 @@
E: pbd@op.net
D: Driver for WaveFront soundcards (Turtle Beach Maui, Tropez, Tropez+)
D: Various bugfixes and changes to sound drivers
-S: USA
+S: USA
N: Carlos Henrique Bauer
E: chbauer@acm.org
@@ -849,6 +849,12 @@
D: AX25-HOWTO, HAM-HOWTO, IPX-HOWTO, NET-2-HOWTO
D: ax25-utils maintainer.
+N: Kamil Debski
+E: kamil@wypas.org
+D: Samsung S5P 2D graphics acceleration and Multi Format Codec drivers
+D: Samsung USB2 phy drivers
+D: PWM fan driver
+
N: Helge Deller
E: deller@gmx.de
W: http://www.parisc-linux.org/
@@ -1199,7 +1205,7 @@
E: dfrasnel@alphalinux.org
W: http://www.alphalinux.org/
P: 1024/3EF87611 B9 F1 44 50 D3 E8 C2 80 DA E5 55 AA 56 7C 42 DA
-D: DEC Alpha hacker
+D: DEC Alpha hacker
D: Miscellaneous bug squisher
N: Jim Freeman
@@ -1299,7 +1305,7 @@
S: New South Wales, 2121
S: Australia
-N: Carlos E. Gorges
+N: Carlos E. Gorges
E: carlos@techlinux.com.br
D: fix smp support on cmpci driver
P: 2048G/EA3C4B19 FF31 33A6 0362 4915 B7EB E541 17D0 0379 EA3C 4B19
@@ -1340,7 +1346,7 @@
E: wgreathouse@myfavoritei.com
D: Current Belkin USB Serial Adapter F5U103 hacker
D: Kernel hacker, embedded systems
-S: 7802 Fitzwater Road
+S: 7802 Fitzwater Road
S: Brecksville, OH 44141-1334
S: USA
@@ -1381,7 +1387,7 @@
E: grant@torque.net
W: http://www.torque.net/linux-pp.html
D: original author of ppa driver for parallel port ZIP drive
-D: original architect of the parallel-port sharing scheme
+D: original architect of the parallel-port sharing scheme
D: PARIDE subsystem: drivers for parallel port IDE & ATAPI devices
S: 44 St. Joseph Street, Suite 506
S: Toronto, Ontario, M4Y 2W4
@@ -1523,7 +1529,7 @@
E: benh@kernel.crashing.org
D: Various parts of PPC/PPC64 & PowerMac
S: 312/107 Canberra Avenue
-S: Griffith, ACT 2603
+S: Griffith, ACT 2603
S: Australia
N: Andreas Herrmann
@@ -1825,7 +1831,7 @@
N: Bernhard Kaindl
E: bkaindl@netway.at
E: edv@bartelt.via.at
-D: Author of a menu based configuration tool, kmenu, which
+D: Author of a menu based configuration tool, kmenu, which
D: is the predecessor of 'make menuconfig' and 'make xconfig'.
D: digiboard driver update(modularisation work and 2.1.x upd)
S: Tallak 95
@@ -1910,6 +1916,15 @@
S: Santa Clara, CA 95051
S: USA
+N: Kukjin Kim
+E: kgene@kernel.org
+D: Samsung S3C, S5P and Exynos ARM architectures
+
+N: Sangbeom Kim
+E: sbkim73@samsung.com
+D: Samsung SoC Audio (ASoC) drivers
+D: Samsung PMIC (RTC, regulators, MFD) drivers
+
N: Russell King
E: rmk@arm.linux.org.uk
D: Linux/arm integrator, maintainer & hacker
@@ -2007,7 +2022,7 @@
D: IP transparent proxy support
S: X/OS Experts in Open Systems BV
S: Kruislaan 419
-S: 1098 VA Amsterdam
+S: 1098 VA Amsterdam
S: The Netherlands
N: Goran Koruga
@@ -2079,7 +2094,7 @@
N: Andrzej M. Krzysztofowicz
E: ankry@mif.pg.gda.pl
-D: Some 8-bit XT disk driver and devfs hacking
+D: Some 8-bit XT disk driver and devfs hacking
D: Aladdin 1533/1543(C) chipset IDE
D: PIIX chipset IDE
S: ul. Matemblewska 1B/10
@@ -2454,7 +2469,7 @@
D: Logical Volume Manager
S: Bartningstr. 12
S: 64289 Darmstadt
-S: Germany
+S: Germany
N: Mark W. McClelland
E: mmcclell@bigfoot.com
@@ -2538,7 +2553,7 @@
P: 1024/04B6E8F5 6C 77 33 CA CC D6 22 03 AB AB 15 A3 AE AD 39 7D
D: Kernel hacker. PostgreSQL hacker. Software watchdog daemon.
D: Maintainer of several Debian packages
-S: Th.-Heuss-Str. 61
+S: Th.-Heuss-Str. 61
S: D-41812 Erkelenz
S: Germany
@@ -2776,7 +2791,7 @@
W: http://www.i-Connect.Net/~mike/
D: Developer and maintainer of the EATA-DMA SCSI driver
D: Co-developer EATA-PIO SCSI driver
-D: /proc/scsi and assorted other snippets
+D: /proc/scsi and assorted other snippets
S: Zum Schiersteiner Grund 2
S: 55127 Mainz
S: Germany
@@ -2843,6 +2858,10 @@
N: Venkatesh Pallipadi (Venki)
D: x86/HPET
+N: Kyungmin Park
+E: kyungmin.park@samsung.com
+D: Samsung S5Pv210 and Exynos4210 mobile platforms
+
N: David Parsons
E: orc@pell.chi.il.us
D: improved memory detection code.
@@ -3010,7 +3029,7 @@
S: Chandler, Arizona 85249
S: USA
-N: Frederic Potter
+N: Frederic Potter
E: fpotter@cirpack.com
D: Some PCI kernel support
@@ -3443,21 +3462,21 @@
S: 76131 Karlsruhe
S: Germany
-N: James Simmons
+N: James Simmons
E: jsimmons@infradead.org
-E: jsimmons@users.sf.net
+E: jsimmons@users.sf.net
D: Frame buffer device maintainer
D: input layer development
D: tty/console layer
-D: various mipsel devices
-S: 115 Carmel Avenue
+D: various mipsel devices
+S: 115 Carmel Avenue
S: El Cerrito CA 94530
-S: USA
+S: USA
N: Jaspreet Singh
E: jaspreet@sangoma.com
W: www.sangoma.com
-D: WANPIPE drivers & API Support for Sangoma S508/FT1 cards
+D: WANPIPE drivers & API Support for Sangoma S508/FT1 cards
S: Sangoma Technologies Inc.,
S: 1001 Denison Street
S: Suite 101
@@ -3481,7 +3500,7 @@
E: csmall@triode.apana.org.au
E: vk2xlz@gonzo.vk2xlz.ampr.org (packet radio)
D: Gracilis PackeTwin device driver
-D: RSPF daemon
+D: RSPF daemon
S: 10 Stockalls Place
S: Minto, NSW, 2566
S: Australia
@@ -3691,7 +3710,7 @@
E: tsusheng@scf.usc.edu
D: IGMP(Internet Group Management Protocol) version 2
S: 2F 14 ALY 31 LN 166 SEC 1 SHIH-PEI RD
-S: Taipei
+S: Taipei
S: Taiwan 112
S: Republic of China
S: 24335 Delta Drive
@@ -3852,7 +3871,7 @@
D: patches for ghostscript, worked on color 'ls', etc.
S: 301 15th Street S.
S: Moorhead, Minnesota 56560
-S: USA
+S: USA
N: Jos Vos
E: jos@xos.nl
@@ -3860,7 +3879,7 @@
D: Various IP firewall updates, ipfwadm
S: X/OS Experts in Open Systems BV
S: Kruislaan 419
-S: 1098 VA Amsterdam
+S: 1098 VA Amsterdam
S: The Netherlands
N: Jeroen Vreeken
@@ -4098,7 +4117,7 @@
N: Victor Yodaiken
E: yodaiken@fsmlabs.com
D: RTLinux (RealTime Linux)
-S: POB 1822
+S: POB 1822
S: Socorro NM, 87801
S: USA
@@ -4196,7 +4215,7 @@
S: France
# Don't add your name here, unless you really _are_ after Marc
-# alphabetically. Leonard used to be very proud of being the
+# alphabetically. Leonard used to be very proud of being the
# last entry, and he'll get positively pissed if he can't even
# be second-to-last. (and this file really _is_ supposed to be
# in alphabetic order)
diff --git a/Documentation/ABI/README b/Documentation/ABI/README
index 3121029..8bac9cb 100644
--- a/Documentation/ABI/README
+++ b/Documentation/ABI/README
@@ -32,7 +32,7 @@
layout of the files below for details on how to do this.)
obsolete/
- This directory documents interfaces that are still remaining in
+ This directory documents interfaces that are still remaining in
the kernel, but are marked to be removed at some later point in
time. The description of the interface will document the reason
why it is obsolete and when it can be expected to be removed.
@@ -58,6 +58,14 @@
be changed further.
+Note:
+ The fields should be use a simple notation, compatible with ReST markup.
+ Also, the file **should not** have a top-level index, like::
+
+ ===
+ foo
+ ===
+
How things move between levels:
Interfaces in stable may move to obsolete, as long as the proper
diff --git a/Documentation/ABI/obsolete/sysfs-class-dax b/Documentation/ABI/obsolete/sysfs-class-dax
index 2cb9fc5..0faf135 100644
--- a/Documentation/ABI/obsolete/sysfs-class-dax
+++ b/Documentation/ABI/obsolete/sysfs-class-dax
@@ -8,11 +8,11 @@
system. Device DAX is strict, precise and predictable.
Specifically this interface:
- 1/ Guarantees fault granularity with respect to a given
- page size (pte, pmd, or pud) set at configuration time.
+ 1. Guarantees fault granularity with respect to a given
+ page size (pte, pmd, or pud) set at configuration time.
- 2/ Enforces deterministic behavior by being strict about
- what fault scenarios are supported.
+ 2. Enforces deterministic behavior by being strict about
+ what fault scenarios are supported.
The /sys/class/dax/ interface enumerates all the
device-dax instances in the system. The ABI is
diff --git a/Documentation/ABI/obsolete/sysfs-driver-hid-roccat-pyra b/Documentation/ABI/obsolete/sysfs-driver-hid-roccat-pyra
index 5d41eba..66545c5 100644
--- a/Documentation/ABI/obsolete/sysfs-driver-hid-roccat-pyra
+++ b/Documentation/ABI/obsolete/sysfs-driver-hid-roccat-pyra
@@ -7,10 +7,13 @@
setting reported by the mouse. This number has to be further
processed to receive the real dpi value:
+ ===== ====
VALUE DPI
+ ===== ====
1 400
2 800
4 1600
+ ===== ====
This file is readonly.
Has never been used. If bookkeeping is done, it's done in userland tools.
diff --git a/Documentation/ABI/obsolete/sysfs-gpio b/Documentation/ABI/obsolete/sysfs-gpio
index e0d4e5e..b8b0fd3 100644
--- a/Documentation/ABI/obsolete/sysfs-gpio
+++ b/Documentation/ABI/obsolete/sysfs-gpio
@@ -13,6 +13,8 @@
GPIOs are identified as they are inside the kernel, using integers in
the range 0..INT_MAX. See Documentation/admin-guide/gpio for more information.
+ ::
+
/sys/class/gpio
/export ... asks the kernel to export a GPIO to userspace
/unexport ... to return a GPIO to the kernel
diff --git a/Documentation/ABI/removed/devfs b/Documentation/ABI/removed/devfs
index 0020c49..24fb35a 100644
--- a/Documentation/ABI/removed/devfs
+++ b/Documentation/ABI/removed/devfs
@@ -5,6 +5,7 @@
devfs has been unmaintained for a number of years, has unfixable
races, contains a naming policy within the kernel that is
against the LSB, and can be replaced by using udev.
+
The files fs/devfs/*, include/linux/devfs_fs*.h were removed,
along with the assorted devfs function calls throughout the
kernel tree.
diff --git a/Documentation/ABI/removed/raw1394 b/Documentation/ABI/removed/raw1394
index ec333e6..9ec7ec4 100644
--- a/Documentation/ABI/removed/raw1394
+++ b/Documentation/ABI/removed/raw1394
@@ -7,6 +7,7 @@
to implement sensible device security policies, and its low level
of abstraction that required userspace clients to duplicate much
of the kernel's ieee1394 core functionality.
+
Replaced by /dev/fw*, i.e. the <linux/firewire-cdev.h> ABI of
firewire-core.
diff --git a/Documentation/ABI/removed/sysfs-class-rfkill b/Documentation/ABI/removed/sysfs-class-rfkill
index 9c08c7f..f25174e 100644
--- a/Documentation/ABI/removed/sysfs-class-rfkill
+++ b/Documentation/ABI/removed/sysfs-class-rfkill
@@ -10,4 +10,4 @@
claim just control over a single rfkill instance.
This file was scheduled to be removed in 2012, and was removed
in 2016.
-Values: 0: Kernel handles events
+Values: 0: Kernel handles events
diff --git a/Documentation/ABI/removed/video1394 b/Documentation/ABI/removed/video1394
index c39c25a..1905d35 100644
--- a/Documentation/ABI/removed/video1394
+++ b/Documentation/ABI/removed/video1394
@@ -8,6 +8,7 @@
performance issues in its first generation. Any video1394 user had
to use raw1394 + libraw1394 too because video1394 did not provide
asynchronous I/O for device discovery and configuration.
+
Replaced by /dev/fw*, i.e. the <linux/firewire-cdev.h> ABI of
firewire-core.
diff --git a/Documentation/ABI/stable/firewire-cdev b/Documentation/ABI/stable/firewire-cdev
index f72ed65..261f85b 100644
--- a/Documentation/ABI/stable/firewire-cdev
+++ b/Documentation/ABI/stable/firewire-cdev
@@ -14,13 +14,17 @@
Each /dev/fw* is associated with one IEEE 1394 node, which can
be remote or local nodes. Operations on a /dev/fw* file have
different scope:
+
- The 1394 node which is associated with the file:
+
- Asynchronous request transmission
- Get the Configuration ROM
- Query node ID
- Query maximum speed of the path between this node
and local node
+
- The 1394 bus (i.e. "card") to which the node is attached to:
+
- Isochronous stream transmission and reception
- Asynchronous stream transmission and reception
- Asynchronous broadcast request transmission
@@ -31,7 +35,9 @@
manager
- Query cycle time
- Bus reset initiation, bus reset event reception
+
- All 1394 buses:
+
- Allocation of IEEE 1212 address ranges on the local
link layers, reception of inbound requests to such
an address range, asynchronous response transmission
@@ -43,6 +49,7 @@
userland implement different access permission models, some
operations are restricted to /dev/fw* files that are associated
with a local node:
+
- Addition of descriptors or directories to the local
nodes' Configuration ROM
- PHY packet transmission and reception
@@ -55,50 +62,50 @@
The following file operations are supported:
open(2)
- Currently the only useful flags are O_RDWR.
+ Currently the only useful flags are O_RDWR.
ioctl(2)
- Initiate various actions. Some take immediate effect, others
- are performed asynchronously while or after the ioctl returns.
- See the inline documentation in <linux/firewire-cdev.h> for
- descriptions of all ioctls.
+ Initiate various actions. Some take immediate effect, others
+ are performed asynchronously while or after the ioctl returns.
+ See the inline documentation in <linux/firewire-cdev.h> for
+ descriptions of all ioctls.
poll(2), select(2), epoll_wait(2) etc.
- Watch for events to become available to be read.
+ Watch for events to become available to be read.
read(2)
- Receive various events. There are solicited events like
- outbound asynchronous transaction completion or isochronous
- buffer completion, and unsolicited events such as bus resets,
- request reception, or PHY packet reception. Always use a read
- buffer which is large enough to receive the largest event that
- could ever arrive. See <linux/firewire-cdev.h> for descriptions
- of all event types and for which ioctls affect reception of
- events.
+ Receive various events. There are solicited events like
+ outbound asynchronous transaction completion or isochronous
+ buffer completion, and unsolicited events such as bus resets,
+ request reception, or PHY packet reception. Always use a read
+ buffer which is large enough to receive the largest event that
+ could ever arrive. See <linux/firewire-cdev.h> for descriptions
+ of all event types and for which ioctls affect reception of
+ events.
mmap(2)
- Allocate a DMA buffer for isochronous reception or transmission
- and map it into the process address space. The arguments should
- be used as follows: addr = NULL, length = the desired buffer
- size, i.e. number of packets times size of largest packet,
- prot = at least PROT_READ for reception and at least PROT_WRITE
- for transmission, flags = MAP_SHARED, fd = the handle to the
- /dev/fw*, offset = 0.
+ Allocate a DMA buffer for isochronous reception or transmission
+ and map it into the process address space. The arguments should
+ be used as follows: addr = NULL, length = the desired buffer
+ size, i.e. number of packets times size of largest packet,
+ prot = at least PROT_READ for reception and at least PROT_WRITE
+ for transmission, flags = MAP_SHARED, fd = the handle to the
+ /dev/fw*, offset = 0.
Isochronous reception works in packet-per-buffer fashion except
for multichannel reception which works in buffer-fill mode.
munmap(2)
- Unmap the isochronous I/O buffer from the process address space.
+ Unmap the isochronous I/O buffer from the process address space.
close(2)
- Besides stopping and freeing I/O contexts that were associated
- with the file descriptor, back out any changes to the local
- nodes' Configuration ROM. Deallocate isochronous channels and
- bandwidth at the IRM that were marked for kernel-assisted
- re- and deallocation.
+ Besides stopping and freeing I/O contexts that were associated
+ with the file descriptor, back out any changes to the local
+ nodes' Configuration ROM. Deallocate isochronous channels and
+ bandwidth at the IRM that were marked for kernel-assisted
+ re- and deallocation.
-Users: libraw1394
- libdc1394
- libhinawa
+Users: libraw1394;
+ libdc1394;
+ libhinawa;
tools like linux-firewire-utils, fwhack, ...
diff --git a/Documentation/ABI/stable/sysfs-acpi-pmprofile b/Documentation/ABI/stable/sysfs-acpi-pmprofile
index 964c7a8..2d6314f 100644
--- a/Documentation/ABI/stable/sysfs-acpi-pmprofile
+++ b/Documentation/ABI/stable/sysfs-acpi-pmprofile
@@ -1,22 +1,26 @@
-What: /sys/firmware/acpi/pm_profile
+What: /sys/firmware/acpi/pm_profile
Date: 03-Nov-2011
KernelVersion: v3.2
Contact: linux-acpi@vger.kernel.org
-Description: The ACPI pm_profile sysfs interface exports the platform
+Description: The ACPI pm_profile sysfs interface exports the platform
power management (and performance) requirement expectations
as provided by BIOS. The integer value is directly passed as
retrieved from the FADT ACPI table.
-Values: For possible values see ACPI specification:
+
+Values: For possible values see ACPI specification:
5.2.9 Fixed ACPI Description Table (FADT)
Field: Preferred_PM_Profile
Currently these values are defined by spec:
- 0 Unspecified
- 1 Desktop
- 2 Mobile
- 3 Workstation
- 4 Enterprise Server
- 5 SOHO Server
- 6 Appliance PC
- 7 Performance Server
+
+ == =================
+ 0 Unspecified
+ 1 Desktop
+ 2 Mobile
+ 3 Workstation
+ 4 Enterprise Server
+ 5 SOHO Server
+ 6 Appliance PC
+ 7 Performance Server
>7 Reserved
+ == =================
diff --git a/Documentation/ABI/stable/sysfs-bus-firewire b/Documentation/ABI/stable/sysfs-bus-firewire
index 41e5a0c..9ac9edd 100644
--- a/Documentation/ABI/stable/sysfs-bus-firewire
+++ b/Documentation/ABI/stable/sysfs-bus-firewire
@@ -47,6 +47,7 @@
IEEE 1394 node device attribute.
Read-only and immutable.
Values: 1: The sysfs entry represents a local node (a controller card).
+
0: The sysfs entry represents a remote node.
@@ -125,7 +126,9 @@
Read-only attribute, immutable during the target's lifetime.
Format, as exposed by firewire-sbp2 since 2.6.22, May 2007:
Colon-separated hexadecimal string representations of
+
u64 EUI-64 : u24 directory_ID : u16 LUN
+
without 0x prefixes, without whitespace. The former sbp2 driver
(removed in 2.6.37 after being superseded by firewire-sbp2) used
a somewhat shorter format which was not as close to SAM.
diff --git a/Documentation/ABI/stable/sysfs-bus-nvmem b/Documentation/ABI/stable/sysfs-bus-nvmem
index 9ffba85..c399323 100644
--- a/Documentation/ABI/stable/sysfs-bus-nvmem
+++ b/Documentation/ABI/stable/sysfs-bus-nvmem
@@ -9,13 +9,14 @@
Note: This file is only present if CONFIG_NVMEM_SYSFS
is enabled
- ex:
- hexdump /sys/bus/nvmem/devices/qfprom0/nvmem
+ ex::
- 0000000 0000 0000 0000 0000 0000 0000 0000 0000
- *
- 00000a0 db10 2240 0000 e000 0c00 0c00 0000 0c00
- 0000000 0000 0000 0000 0000 0000 0000 0000 0000
- ...
- *
- 0001000
+ hexdump /sys/bus/nvmem/devices/qfprom0/nvmem
+
+ 0000000 0000 0000 0000 0000 0000 0000 0000 0000
+ *
+ 00000a0 db10 2240 0000 e000 0c00 0c00 0000 0c00
+ 0000000 0000 0000 0000 0000 0000 0000 0000 0000
+ ...
+ *
+ 0001000
diff --git a/Documentation/ABI/stable/sysfs-bus-usb b/Documentation/ABI/stable/sysfs-bus-usb
index b832eef..cad4bc2 100644
--- a/Documentation/ABI/stable/sysfs-bus-usb
+++ b/Documentation/ABI/stable/sysfs-bus-usb
@@ -50,8 +50,10 @@
Tools can use this file and the connected_duration file to
compute the percentage of time that a device has been active.
- For example,
- echo $((100 * `cat active_duration` / `cat connected_duration`))
+ For example::
+
+ echo $((100 * `cat active_duration` / `cat connected_duration`))
+
will give an integer percentage. Note that this does not
account for counter wrap.
Users:
diff --git a/Documentation/ABI/stable/sysfs-bus-vmbus b/Documentation/ABI/stable/sysfs-bus-vmbus
index 8e8d167..c27b7b8 100644
--- a/Documentation/ABI/stable/sysfs-bus-vmbus
+++ b/Documentation/ABI/stable/sysfs-bus-vmbus
@@ -63,13 +63,6 @@
Description: VCPU (sub)channel is affinitized to
Users: tools/hv/lsvmbus and other debugging tools
-What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/cpu
-Date: September. 2017
-KernelVersion: 4.14
-Contact: Stephen Hemminger <sthemmin@microsoft.com>
-Description: VCPU (sub)channel is affinitized to
-Users: tools/hv/lsvmbus and other debugging tools
-
What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/in_mask
Date: September. 2017
KernelVersion: 4.14
diff --git a/Documentation/ABI/stable/sysfs-bus-w1 b/Documentation/ABI/stable/sysfs-bus-w1
index 992dfb1..5cd5e87 100644
--- a/Documentation/ABI/stable/sysfs-bus-w1
+++ b/Documentation/ABI/stable/sysfs-bus-w1
@@ -6,6 +6,7 @@
control systems are attached/generate presence for as short as
100 ms - hence the tens-to-hundreds milliseconds scan intervals
are required.
+
see Documentation/w1/w1-generic.rst for detailed information.
Users: any user space application which wants to know bus scanning
interval
diff --git a/Documentation/ABI/stable/sysfs-class-backlight b/Documentation/ABI/stable/sysfs-class-backlight
index 70302f3..023fb52 100644
--- a/Documentation/ABI/stable/sysfs-class-backlight
+++ b/Documentation/ABI/stable/sysfs-class-backlight
@@ -4,6 +4,7 @@
Contact: Richard Purdie <rpurdie@rpsys.net>
Description:
Control BACKLIGHT power, values are FB_BLANK_* from fb.h
+
- FB_BLANK_UNBLANK (0) : power on.
- FB_BLANK_POWERDOWN (4) : power off
Users: HAL
diff --git a/Documentation/ABI/stable/sysfs-class-infiniband b/Documentation/ABI/stable/sysfs-class-infiniband
index 87b11f9..348c4ac 100644
--- a/Documentation/ABI/stable/sysfs-class-infiniband
+++ b/Documentation/ABI/stable/sysfs-class-infiniband
@@ -8,12 +8,14 @@
KernelVersion: v2.6.12
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ===========================================
node_type: (RO) Node type (CA, RNIC, usNIC, usNIC UDP,
switch or router)
node_guid: (RO) Node GUID
sys_image_guid: (RO) System image GUID
+ =============== ===========================================
What: /sys/class/infiniband/<device>/node_desc
@@ -47,6 +49,7 @@
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ===============================================
lid: (RO) Port LID
rate: (RO) Port data rate (active width * active
@@ -66,8 +69,9 @@
cap_mask: (RO) Port capability mask. 2 bits here are
settable- IsCommunicationManagementSupported
- (set when CM module is loaded) and IsSM (set via
- open of issmN file).
+ (set when CM module is loaded) and IsSM (set
+ via open of issmN file).
+ =============== ===============================================
What: /sys/class/infiniband/<device>/ports/<port-num>/link_layer
@@ -103,8 +107,7 @@
KernelVersion: v2.6.12
Contact: linux-rdma@vger.kernel.org
Description:
- Errors info:
- -----------
+ **Errors info**:
symbol_error: (RO) Total number of minor link errors detected on
one or more physical lanes.
@@ -142,8 +145,7 @@
intervention. It can also indicate hardware issues or extremely
poor link signal integrity
- Data info:
- ---------
+ **Data info**:
port_xmit_data: (RO) Total number of data octets, divided by 4
(lanes), transmitted on all VLs. This is 64 bit counter
@@ -176,8 +178,7 @@
transmitted on all VLs from the port. This may include multicast
packets with errors.
- Misc info:
- ---------
+ **Misc info**:
port_xmit_discards: (RO) Total number of outbound packets
discarded by the port because the port is down or congested.
@@ -244,9 +245,11 @@
two umad devices and two issm devices, while a switch will have
one device of each type (for switch port 0).
+ ======= =====================================
ibdev: (RO) Show Infiniband (IB) device name
port: (RO) Display port number
+ ======= =====================================
What: /sys/class/infiniband_mad/abi_version
@@ -264,10 +267,12 @@
KernelVersion: v2.6.14
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ===========================================
ibdev: (RO) Display Infiniband (IB) device name
abi_version: (RO) Show ABI version of IB device specific
interfaces.
+ =============== ===========================================
What: /sys/class/infiniband_verbs/abi_version
@@ -289,12 +294,14 @@
KernelVersion: v2.6.12
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ================================================
hw_rev: (RO) Hardware revision number
hca_type: (RO) Host Channel Adapter type: MT23108, MT25208
(MT23108 compat mode), MT25208 or MT25204
board_id: (RO) Manufacturing board ID
+ =============== ================================================
sysfs interface for Mellanox ConnectX HCA IB driver (mlx4)
@@ -307,11 +314,13 @@
KernelVersion: v2.6.24
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ===============================
hw_rev: (RO) Hardware revision number
hca_type: (RO) Host channel adapter type
board_id: (RO) Manufacturing board ID
+ =============== ===============================
What: /sys/class/infiniband/mlx4_X/iov/ports/<port-num>/gids/<n>
@@ -337,6 +346,7 @@
example, ports/1/pkeys/10 contains the value at index 10 in port
1's P_Key table.
+ ======================= ==========================================
gids/<n>: (RO) The physical port gids n = 0..127
admin_guids/<n>: (RW) Allows examining or changing the
@@ -365,6 +375,7 @@
guest, whenever it uses its pkey index
1, will actually be using the real pkey
index 10.
+ ======================= ==========================================
What: /sys/class/infiniband/mlx4_X/iov/<pci-slot-num>/ports/<m>/smi_enabled
@@ -376,12 +387,14 @@
Enabling QP0 on VFs for selected VF/port. By default, no VFs are
enabled for QP0 operation.
- smi_enabled: (RO) Indicates whether smi is currently enabled
- for the indicated VF/port
+ ================= ==== ===========================================
+ smi_enabled: (RO) Indicates whether smi is currently enabled
+ for the indicated VF/port
- enable_smi_admin:(RW) Used by the admin to request that smi
- capability be enabled or disabled for the
- indicated VF/port. 0 = disable, 1 = enable.
+ enable_smi_admin: (RW) Used by the admin to request that smi
+ capability be enabled or disabled for the
+ indicated VF/port. 0 = disable, 1 = enable.
+ ================= ==== ===========================================
The requested enablement will occur at the next reset of the VF
(e.g. driver restart on the VM which owns the VF).
@@ -398,6 +411,7 @@
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== =============================================
hw_rev: (RO) Hardware revision number
hca_type: (RO) Driver short name. Should normally match
@@ -406,6 +420,7 @@
board_id: (RO) Manufacturing board id. (Vendor + device
information)
+ =============== =============================================
sysfs interface for Intel IB driver qib
@@ -426,6 +441,7 @@
KernelVersion: v2.6.35
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ======================================================
version: (RO) Display version information of installed software
and drivers.
@@ -452,6 +468,7 @@
chip_reset: (WO) Reset the chip if possible by writing
"reset" to this file. Only allowed if no user
contexts are open that use chip resources.
+ =============== ======================================================
What: /sys/class/infiniband/qibX/ports/N/sl2vl/[0-15]
@@ -471,14 +488,16 @@
Description:
Per-port congestion control. Both are binary attributes.
- cc_table_bin: (RO) Congestion control table size followed by
+ =============== ================================================
+ cc_table_bin (RO) Congestion control table size followed by
table entries.
- cc_settings_bin:(RO) Congestion settings: port control, control
+ cc_settings_bin (RO) Congestion settings: port control, control
map and an array of 16 entries for the
congestion entries - increase, timer, event log
trigger threshold and the minimum injection rate
delay.
+ =============== ================================================
What: /sys/class/infiniband/qibX/ports/N/linkstate/loopback
What: /sys/class/infiniband/qibX/ports/N/linkstate/led_override
@@ -491,6 +510,7 @@
Description:
[to be documented]
+ =============== ===============================================
loopback: (WO)
led_override: (WO)
hrtbt_enable: (RW)
@@ -501,6 +521,7 @@
errors. Possible states are- "Initted",
"Present", "IB_link_up", "IB_configured" or
"Fatal_Hardware_Error".
+ =============== ===============================================
What: /sys/class/infiniband/qibX/ports/N/diag_counters/rc_resends
What: /sys/class/infiniband/qibX/ports/N/diag_counters/seq_naks
@@ -549,6 +570,7 @@
linux-rdma@vger.kernel.org
Description:
+ =============== ===============================================
board_id: (RO) Manufacturing board id
config: (RO) Report the configuration for this PF
@@ -561,6 +583,7 @@
iface: (RO) Shows which network interface this usNIC
entry is associated to (visible with ifconfig).
+ =============== ===============================================
What: /sys/class/infiniband/usnic_X/qpn/summary
What: /sys/class/infiniband/usnic_X/qpn/context
@@ -605,6 +628,7 @@
KernelVersion: v4.6
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== =============================================
hw_rev: (RO) Hardware revision number
board_id: (RO) Manufacturing board id
@@ -623,6 +647,7 @@
available.
tempsense: (RO) Thermal sense information
+ =============== =============================================
What: /sys/class/infiniband/hfi1_X/ports/N/CCMgtA/cc_settings_bin
@@ -634,19 +659,21 @@
Description:
Per-port congestion control.
- cc_table_bin: (RO) CCA tables used by PSM2 Congestion control
+ =============== ================================================
+ cc_table_bin (RO) CCA tables used by PSM2 Congestion control
table size followed by table entries. Binary
attribute.
- cc_settings_bin:(RO) Congestion settings: port control, control
+ cc_settings_bin (RO) Congestion settings: port control, control
map and an array of 16 entries for the
congestion entries - increase, timer, event log
trigger threshold and the minimum injection rate
delay. Binary attribute.
- cc_prescan: (RW) enable prescanning for faster BECN
+ cc_prescan (RW) enable prescanning for faster BECN
response. Write "on" to enable and "off" to
disable.
+ =============== ================================================
What: /sys/class/infiniband/hfi1_X/ports/N/sc2vl/[0-31]
What: /sys/class/infiniband/hfi1_X/ports/N/sl2sc/[0-31]
@@ -655,11 +682,13 @@
KernelVersion: v4.6
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ===================================================
sc2vl/: (RO) 32 files (0 - 31) used to translate sl->vl
sl2sc/: (RO) 32 files (0 - 31) used to translate sl->sc
vl2mtu/: (RO) 16 files (0 - 15) used to determine MTU for vl
+ =============== ===================================================
What: /sys/class/infiniband/hfi1_X/sdma_N/cpu_list
@@ -670,26 +699,28 @@
Description:
sdma<N>/ contains one directory per sdma engine (0 - 15)
+ =============== ==============================================
cpu_list: (RW) List of cpus for user-process to sdma
engine assignment.
vl: (RO) Displays the virtual lane (vl) the sdma
engine maps to.
+ =============== ==============================================
This interface gives the user control on the affinity settings
for the device. As an example, to set an sdma engine irq
affinity and thread affinity of a user processes to use the
sdma engine, which is "near" in terms of NUMA configuration, or
- physical cpu location, the user will do:
+ physical cpu location, the user will do::
- echo "3" > /proc/irq/<N>/smp_affinity_list
- echo "4-7" > /sys/devices/.../sdma3/cpu_list
- cat /sys/devices/.../sdma3/vl
- 0
- echo "8" > /proc/irq/<M>/smp_affinity_list
- echo "9-12" > /sys/devices/.../sdma4/cpu_list
- cat /sys/devices/.../sdma4/vl
- 1
+ echo "3" > /proc/irq/<N>/smp_affinity_list
+ echo "4-7" > /sys/devices/.../sdma3/cpu_list
+ cat /sys/devices/.../sdma3/vl
+ 0
+ echo "8" > /proc/irq/<M>/smp_affinity_list
+ echo "9-12" > /sys/devices/.../sdma4/cpu_list
+ cat /sys/devices/.../sdma4/vl
+ 1
to make sure that when a process runs on cpus 4,5,6, or 7, and
uses vl=0, then sdma engine 3 is selected by the driver, and
@@ -711,11 +742,13 @@
KernelVersion: v4.10
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ==== ========================
hw_rev: (RO) Hardware revision number
hca_type: (RO) Show HCA type (I40IW)
board_id: (RO) I40IW board ID
+ =============== ==== ========================
sysfs interface for QLogic qedr NIC Driver
@@ -728,9 +761,11 @@
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ==== ========================
hw_rev: (RO) Hardware revision number
hca_type: (RO) Display HCA type
+ =============== ==== ========================
sysfs interface for VMware Paravirtual RDMA driver
@@ -744,11 +779,13 @@
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ==== =====================================
hw_rev: (RO) Hardware revision number
hca_type: (RO) Host channel adapter type
board_id: (RO) Display PVRDMA manufacturing board ID
+ =============== ==== =====================================
sysfs interface for Broadcom NetXtreme-E RoCE driver
@@ -760,6 +797,8 @@
KernelVersion: v4.11
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ==== =========================
hw_rev: (RO) Hardware revision number
hca_type: (RO) Host channel adapter type
+ =============== ==== =========================
diff --git a/Documentation/ABI/stable/sysfs-class-rfkill b/Documentation/ABI/stable/sysfs-class-rfkill
index 5b154f9..037979f 100644
--- a/Documentation/ABI/stable/sysfs-class-rfkill
+++ b/Documentation/ABI/stable/sysfs-class-rfkill
@@ -2,7 +2,7 @@
For details to this subsystem look at Documentation/driver-api/rfkill.rst.
-For the deprecated /sys/class/rfkill/*/claim knobs of this interface look in
+For the deprecated ``/sys/class/rfkill/*/claim`` knobs of this interface look in
Documentation/ABI/removed/sysfs-class-rfkill.
What: /sys/class/rfkill
@@ -36,9 +36,10 @@
Contact: linux-wireless@vger.kernel.org
Description: Whether the soft blocked state is initialised from non-volatile
storage at startup.
-Values: A numeric value.
- 0: false
- 1: true
+Values: A numeric value:
+
+ - 0: false
+ - 1: true
What: /sys/class/rfkill/rfkill[0-9]+/state
@@ -54,6 +55,7 @@
through this interface. There will likely be another attempt to
remove it in the future.
Values: A numeric value.
+
0: RFKILL_STATE_SOFT_BLOCKED
transmitter is turned off by software
1: RFKILL_STATE_UNBLOCKED
@@ -69,6 +71,7 @@
Contact: linux-wireless@vger.kernel.org
Description: Current hardblock state. This file is read only.
Values: A numeric value.
+
0: inactive
The transmitter is (potentially) active.
1: active
@@ -82,7 +85,9 @@
Contact: linux-wireless@vger.kernel.org
Description: Current softblock state. This file is read and write.
Values: A numeric value.
+
0: inactive
The transmitter is (potentially) active.
+
1: active
The transmitter is turned off by software.
diff --git a/Documentation/ABI/stable/sysfs-class-tpm b/Documentation/ABI/stable/sysfs-class-tpm
index 58e94e7..91ca63e 100644
--- a/Documentation/ABI/stable/sysfs-class-tpm
+++ b/Documentation/ABI/stable/sysfs-class-tpm
@@ -32,11 +32,11 @@
Contact: linux-integrity@vger.kernel.org
Description: The "caps" property contains TPM manufacturer and version info.
- Example output:
+ Example output::
- Manufacturer: 0x53544d20
- TCG version: 1.2
- Firmware version: 8.16
+ Manufacturer: 0x53544d20
+ TCG version: 1.2
+ Firmware version: 8.16
Manufacturer is a hex dump of the 4 byte manufacturer info
space in a TPM. TCG version shows the TCG TPM spec level that
@@ -54,9 +54,9 @@
any longer than necessary before starting to poll for a
result.
- Example output:
+ Example output::
- 3015000 4508000 180995000 [original]
+ 3015000 4508000 180995000 [original]
Here the short, medium and long durations are displayed in
usecs. "[original]" indicates that the values are displayed
@@ -92,14 +92,14 @@
values may be constantly changing, the output is only valid
for a snapshot in time.
- Example output:
+ Example output::
- PCR-00: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
- PCR-01: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
- PCR-02: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
- PCR-03: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
- PCR-04: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
- ...
+ PCR-00: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
+ PCR-01: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
+ PCR-02: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
+ PCR-03: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
+ PCR-04: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
+ ...
The number of PCRs and hex bytes needed to represent a PCR
value will vary depending on TPM chip version. For TPM 1.1 and
@@ -119,44 +119,44 @@
ated at TPM manufacture time and exists for the life of the
chip.
- Example output:
+ Example output::
- Algorithm: 00 00 00 01
- Encscheme: 00 03
- Sigscheme: 00 01
- Parameters: 00 00 08 00 00 00 00 02 00 00 00 00
- Modulus length: 256
- Modulus:
- B4 76 41 82 C9 20 2C 10 18 40 BC 8B E5 44 4C 6C
- 3A B2 92 0C A4 9B 2A 83 EB 5C 12 85 04 48 A0 B6
- 1E E4 81 84 CE B2 F2 45 1C F0 85 99 61 02 4D EB
- 86 C4 F7 F3 29 60 52 93 6B B2 E5 AB 8B A9 09 E3
- D7 0E 7D CA 41 BF 43 07 65 86 3C 8C 13 7A D0 8B
- 82 5E 96 0B F8 1F 5F 34 06 DA A2 52 C1 A9 D5 26
- 0F F4 04 4B D9 3F 2D F2 AC 2F 74 64 1F 8B CD 3E
- 1E 30 38 6C 70 63 69 AB E2 50 DF 49 05 2E E1 8D
- 6F 78 44 DA 57 43 69 EE 76 6C 38 8A E9 8E A3 F0
- A7 1F 3C A8 D0 12 15 3E CA 0E BD FA 24 CD 33 C6
- 47 AE A4 18 83 8E 22 39 75 93 86 E6 FD 66 48 B6
- 10 AD 94 14 65 F9 6A 17 78 BD 16 53 84 30 BF 70
- E0 DC 65 FD 3C C6 B0 1E BF B9 C1 B5 6C EF B1 3A
- F8 28 05 83 62 26 11 DC B4 6B 5A 97 FF 32 26 B6
- F7 02 71 CF 15 AE 16 DD D1 C1 8E A8 CF 9B 50 7B
- C3 91 FF 44 1E CF 7C 39 FE 17 77 21 20 BD CE 9B
+ Algorithm: 00 00 00 01
+ Encscheme: 00 03
+ Sigscheme: 00 01
+ Parameters: 00 00 08 00 00 00 00 02 00 00 00 00
+ Modulus length: 256
+ Modulus:
+ B4 76 41 82 C9 20 2C 10 18 40 BC 8B E5 44 4C 6C
+ 3A B2 92 0C A4 9B 2A 83 EB 5C 12 85 04 48 A0 B6
+ 1E E4 81 84 CE B2 F2 45 1C F0 85 99 61 02 4D EB
+ 86 C4 F7 F3 29 60 52 93 6B B2 E5 AB 8B A9 09 E3
+ D7 0E 7D CA 41 BF 43 07 65 86 3C 8C 13 7A D0 8B
+ 82 5E 96 0B F8 1F 5F 34 06 DA A2 52 C1 A9 D5 26
+ 0F F4 04 4B D9 3F 2D F2 AC 2F 74 64 1F 8B CD 3E
+ 1E 30 38 6C 70 63 69 AB E2 50 DF 49 05 2E E1 8D
+ 6F 78 44 DA 57 43 69 EE 76 6C 38 8A E9 8E A3 F0
+ A7 1F 3C A8 D0 12 15 3E CA 0E BD FA 24 CD 33 C6
+ 47 AE A4 18 83 8E 22 39 75 93 86 E6 FD 66 48 B6
+ 10 AD 94 14 65 F9 6A 17 78 BD 16 53 84 30 BF 70
+ E0 DC 65 FD 3C C6 B0 1E BF B9 C1 B5 6C EF B1 3A
+ F8 28 05 83 62 26 11 DC B4 6B 5A 97 FF 32 26 B6
+ F7 02 71 CF 15 AE 16 DD D1 C1 8E A8 CF 9B 50 7B
+ C3 91 FF 44 1E CF 7C 39 FE 17 77 21 20 BD CE 9B
- Possible values:
+ Possible values::
- Algorithm: TPM_ALG_RSA (1)
- Encscheme: TPM_ES_RSAESPKCSv15 (2)
+ Algorithm: TPM_ALG_RSA (1)
+ Encscheme: TPM_ES_RSAESPKCSv15 (2)
TPM_ES_RSAESOAEP_SHA1_MGF1 (3)
- Sigscheme: TPM_SS_NONE (1)
- Parameters, a byte string of 3 u32 values:
+ Sigscheme: TPM_SS_NONE (1)
+ Parameters, a byte string of 3 u32 values:
Key Length (bits): 00 00 08 00 (2048)
Num primes: 00 00 00 02 (2)
Exponent Size: 00 00 00 00 (0 means the
default exp)
- Modulus Length: 256 (bytes)
- Modulus: The 256 byte Endorsement Key modulus
+ Modulus Length: 256 (bytes)
+ Modulus: The 256 byte Endorsement Key modulus
What: /sys/class/tpm/tpmX/device/temp_deactivated
Date: April 2006
@@ -176,9 +176,9 @@
timeouts is defined by the TPM interface spec that the chip
conforms to.
- Example output:
+ Example output::
- 750000 750000 750000 750000 [original]
+ 750000 750000 750000 750000 [original]
The four timeout values are shown in usecs, with a trailing
"[original]" or "[adjusted]" depending on whether the values
@@ -191,6 +191,6 @@
Description: The "tpm_version_major" property shows the TCG spec major version
implemented by the TPM device.
- Example output:
+ Example output::
- 2
+ 2
diff --git a/Documentation/ABI/stable/sysfs-devices b/Documentation/ABI/stable/sysfs-devices
index 4404bd9..42bf1ea 100644
--- a/Documentation/ABI/stable/sysfs-devices
+++ b/Documentation/ABI/stable/sysfs-devices
@@ -1,5 +1,6 @@
-# Note: This documents additional properties of any device beyond what
-# is documented in Documentation/admin-guide/sysfs-rules.rst
+Note:
+ This documents additional properties of any device beyond what
+ is documented in Documentation/admin-guide/sysfs-rules.rst
What: /sys/devices/*/of_node
Date: February 2015
diff --git a/Documentation/ABI/stable/sysfs-driver-dma-ioatdma b/Documentation/ABI/stable/sysfs-driver-dma-ioatdma
index 420c1d0..3a4e2cd 100644
--- a/Documentation/ABI/stable/sysfs-driver-dma-ioatdma
+++ b/Documentation/ABI/stable/sysfs-driver-dma-ioatdma
@@ -1,29 +1,29 @@
-What: sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/cap
+What: /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/cap
Date: December 3, 2009
KernelVersion: 2.6.32
Contact: dmaengine@vger.kernel.org
Description: Capabilities the DMA supports.Currently there are DMA_PQ, DMA_PQ_VAL,
DMA_XOR,DMA_XOR_VAL,DMA_INTERRUPT.
-What: sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_active
+What: /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_active
Date: December 3, 2009
KernelVersion: 2.6.32
Contact: dmaengine@vger.kernel.org
Description: The number of descriptors active in the ring.
-What: sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_size
+What: /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_size
Date: December 3, 2009
KernelVersion: 2.6.32
Contact: dmaengine@vger.kernel.org
Description: Descriptor ring size, total number of descriptors available.
-What: sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/version
+What: /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/version
Date: December 3, 2009
KernelVersion: 2.6.32
Contact: dmaengine@vger.kernel.org
Description: Version of ioatdma device.
-What: sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/intr_coalesce
+What: /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/intr_coalesce
Date: August 8, 2017
KernelVersion: 4.14
Contact: dmaengine@vger.kernel.org
diff --git a/Documentation/ABI/stable/sysfs-driver-firmware-zynqmp b/Documentation/ABI/stable/sysfs-driver-firmware-zynqmp
index 00fa04c..f5724bb 100644
--- a/Documentation/ABI/stable/sysfs-driver-firmware-zynqmp
+++ b/Documentation/ABI/stable/sysfs-driver-firmware-zynqmp
@@ -12,13 +12,15 @@
resets. Three registers are used by the FSBL and
other Xilinx software products: GLOBAL_GEN_STORAGE{4:6}.
- Usage:
- # cat /sys/devices/platform/firmware\:zynqmp-firmware/ggs0
- # echo <value> > /sys/devices/platform/firmware\:zynqmp-firmware/ggs0
+ Usage::
- Example:
- # cat /sys/devices/platform/firmware\:zynqmp-firmware/ggs0
- # echo 0x1234ABCD > /sys/devices/platform/firmware\:zynqmp-firmware/ggs0
+ # cat /sys/devices/platform/firmware\:zynqmp-firmware/ggs0
+ # echo <value> > /sys/devices/platform/firmware\:zynqmp-firmware/ggs0
+
+ Example::
+
+ # cat /sys/devices/platform/firmware\:zynqmp-firmware/ggs0
+ # echo 0x1234ABCD > /sys/devices/platform/firmware\:zynqmp-firmware/ggs0
Users: Xilinx
@@ -39,13 +41,15 @@
software products: PERS_GLOB_GEN_STORAGE{4:7}.
Register is reset only by a POR reset.
- Usage:
- # cat /sys/devices/platform/firmware\:zynqmp-firmware/pggs0
- # echo <value> > /sys/devices/platform/firmware\:zynqmp-firmware/pggs0
+ Usage::
- Example:
- # cat /sys/devices/platform/firmware\:zynqmp-firmware/pggs0
- # echo 0x1234ABCD > /sys/devices/platform/firmware\:zynqmp-firmware/pggs0
+ # cat /sys/devices/platform/firmware\:zynqmp-firmware/pggs0
+ # echo <value> > /sys/devices/platform/firmware\:zynqmp-firmware/pggs0
+
+ Example::
+
+ # cat /sys/devices/platform/firmware\:zynqmp-firmware/pggs0
+ # echo 0x1234ABCD > /sys/devices/platform/firmware\:zynqmp-firmware/pggs0
Users: Xilinx
@@ -61,23 +65,28 @@
Following are available shutdown scopes(subtypes):
- subsystem: Only the APU along with all of its peripherals
+ subsystem:
+ Only the APU along with all of its peripherals
not used by other processing units will be
shut down. This may result in the FPD power
domain being shut down provided that no other
processing unit uses FPD peripherals or DRAM.
- ps_only: The complete PS will be shut down, including the
+ ps_only:
+ The complete PS will be shut down, including the
RPU, PMU, etc. Only the PL domain (FPGA)
remains untouched.
- system: The complete system/device is shut down.
+ system:
+ The complete system/device is shut down.
- Usage:
- # cat /sys/devices/platform/firmware\:zynqmp-firmware/shutdown_scope
- # echo <scope> > /sys/devices/platform/firmware\:zynqmp-firmware/shutdown_scope
+ Usage::
- Example:
- # cat /sys/devices/platform/firmware\:zynqmp-firmware/shutdown_scope
- # echo "subsystem" > /sys/devices/platform/firmware\:zynqmp-firmware/shutdown_scope
+ # cat /sys/devices/platform/firmware\:zynqmp-firmware/shutdown_scope
+ # echo <scope> > /sys/devices/platform/firmware\:zynqmp-firmware/shutdown_scope
+
+ Example::
+
+ # cat /sys/devices/platform/firmware\:zynqmp-firmware/shutdown_scope
+ # echo "subsystem" > /sys/devices/platform/firmware\:zynqmp-firmware/shutdown_scope
Users: Xilinx
@@ -94,10 +103,13 @@
system restart.
Usage:
- Set healthy bit
- # echo 1 > /sys/devices/platform/firmware\:zynqmp-firmware/health_status
- Unset healthy bit
- # echo 0 > /sys/devices/platform/firmware\:zynqmp-firmware/health_status
+ Set healthy bit::
+
+ # echo 1 > /sys/devices/platform/firmware\:zynqmp-firmware/health_status
+
+ Unset healthy bit::
+
+ # echo 0 > /sys/devices/platform/firmware\:zynqmp-firmware/health_status
Users: Xilinx
diff --git a/Documentation/ABI/stable/sysfs-driver-ib_srp b/Documentation/ABI/stable/sysfs-driver-ib_srp
index 84972a5..bada15a 100644
--- a/Documentation/ABI/stable/sysfs-driver-ib_srp
+++ b/Documentation/ABI/stable/sysfs-driver-ib_srp
@@ -6,6 +6,7 @@
One can request ib_srp to connect to a new target by writing
a comma-separated list of login parameters to this sysfs
attribute. The supported parameters are:
+
* id_ext, a 16-digit hexadecimal number specifying the eight
byte identifier extension in the 16-byte SRP target port
identifier. The target port identifier is sent by ib_srp
diff --git a/Documentation/ABI/stable/sysfs-driver-speakup b/Documentation/ABI/stable/sysfs-driver-speakup
index c6a32c4..792f58b 100644
--- a/Documentation/ABI/stable/sysfs-driver-speakup
+++ b/Documentation/ABI/stable/sysfs-driver-speakup
@@ -69,6 +69,7 @@
speakup if for example
the say screen command is used before the
entire screen is read.
+
With no_interrupt set to one, if the say
screen command is used, and one then types on the keyboard,
speakup will continue to say the whole screen regardless until
@@ -215,8 +216,10 @@
Again, these are part of the help system. For instance, if you
had pressed speakup + keypad 3, you would hear:
"speakup keypad 3 is go to bottom edge."
+
The speakup key is depressed, so the name of the key state is
speakup.
+
This part of the message comes from the states collection.
What: /sys/accessibility/speakup/i18n/characters
@@ -297,6 +300,7 @@
Contact: speakup@linux-speakup.org
Description: Controls if punctuation is spoken by speakup, or by the
synthesizer.
+
For example, speakup speaks ">" as "greater", while
the espeak synthesizer used by the soft driver speaks "greater
than". Zero lets speakup speak the punctuation. One lets the
diff --git a/Documentation/ABI/stable/sysfs-firmware-efi-vars b/Documentation/ABI/stable/sysfs-firmware-efi-vars
index 5def20b..46ccd23 100644
--- a/Documentation/ABI/stable/sysfs-firmware-efi-vars
+++ b/Documentation/ABI/stable/sysfs-firmware-efi-vars
@@ -17,6 +17,7 @@
directory has a name of the form "<key>-<vendor guid>"
and contains the following files:
+ =============== ========================================
attributes: A read-only text file enumerating the
EFI variable flags. Potential values
include:
@@ -59,12 +60,14 @@
size: As ASCII representation of the size of
the variable's value.
+ =============== ========================================
In addition, two other magic binary files are provided
in the top-level directory and are used for adding and
removing variables:
+ =============== ========================================
new_var: Takes a "struct efi_variable" and
instructs the EFI firmware to create a
new variable.
@@ -73,3 +76,4 @@
instructs the EFI firmware to remove any
variable that has a matching vendor GUID
and variable key name.
+ =============== ========================================
diff --git a/Documentation/ABI/stable/sysfs-firmware-opal-dump b/Documentation/ABI/stable/sysfs-firmware-opal-dump
index 32fe7f5..1f74f45 100644
--- a/Documentation/ABI/stable/sysfs-firmware-opal-dump
+++ b/Documentation/ABI/stable/sysfs-firmware-opal-dump
@@ -7,6 +7,7 @@
This is only for the powerpc/powernv platform.
+ =============== ===============================================
initiate_dump: When '1' is written to it,
we will initiate a dump.
Read this file for supported commands.
@@ -19,8 +20,11 @@
and ID of the dump, use the id and type files.
Do not rely on any particular size of dump
type or dump id.
+ =============== ===============================================
Each dump has the following files:
+
+ =============== ===============================================
id: An ASCII representation of the dump ID
in hex (e.g. '0x01')
type: An ASCII representation of the type of
@@ -39,3 +43,4 @@
inaccessible.
Reading this file will get a list of
supported actions.
+ =============== ===============================================
diff --git a/Documentation/ABI/stable/sysfs-firmware-opal-elog b/Documentation/ABI/stable/sysfs-firmware-opal-elog
index 2536434..7c8a61a 100644
--- a/Documentation/ABI/stable/sysfs-firmware-opal-elog
+++ b/Documentation/ABI/stable/sysfs-firmware-opal-elog
@@ -38,6 +38,7 @@
For each log entry (directory), there are the following
files:
+ ============== ================================================
id: An ASCII representation of the ID of the
error log, in hex - e.g. "0x01".
@@ -58,3 +59,4 @@
entry will be removed from sysfs.
Reading this file will list the supported
operations (currently just acknowledge).
+ ============== ================================================
diff --git a/Documentation/ABI/stable/sysfs-hypervisor-xen b/Documentation/ABI/stable/sysfs-hypervisor-xen
index 3cf5cdf..748593c 100644
--- a/Documentation/ABI/stable/sysfs-hypervisor-xen
+++ b/Documentation/ABI/stable/sysfs-hypervisor-xen
@@ -33,6 +33,8 @@
Space separated list of supported guest system types. Each type
is in the format: <class>-<major>.<minor>-<arch>
With:
+
+ ======== ============================================
<class>: "xen" -- x86: paravirtualized, arm: standard
"hvm" -- x86 only: fully virtualized
<major>: major guest interface version
@@ -43,6 +45,7 @@
"x86_64": 64 bit x86 guest
"armv7l": 32 bit arm guest
"aarch64": 64 bit arm guest
+ ======== ============================================
What: /sys/hypervisor/properties/changeset
Date: March 2009
diff --git a/Documentation/ABI/stable/vdso b/Documentation/ABI/stable/vdso
index 55406ec8..951838d 100644
--- a/Documentation/ABI/stable/vdso
+++ b/Documentation/ABI/stable/vdso
@@ -1,3 +1,9 @@
+What: vDSO
+Date: July 2011
+KernelVersion: 3.0
+Contact: Andy Lutomirski <luto@kernel.org>
+Description:
+
On some architectures, when the kernel loads any userspace program it
maps an ELF DSO into that program's address space. This DSO is called
the vDSO and it often contains useful and highly-optimized alternatives
@@ -23,6 +29,7 @@
ABI of those symbols is considered stable. It may vary across architectures,
though.
-(As of this writing, this ABI documentation as been confirmed for x86_64.
+Note:
+ As of this writing, this ABI documentation as been confirmed for x86_64.
The maintainers of the other vDSO-using architectures should confirm
- that it is correct for their architecture.)
+ that it is correct for their architecture.
diff --git a/Documentation/ABI/testing/configfs-acpi b/Documentation/ABI/testing/configfs-acpi
index 4ab4e99..c09b640c 100644
--- a/Documentation/ABI/testing/configfs-acpi
+++ b/Documentation/ABI/testing/configfs-acpi
@@ -14,7 +14,8 @@
This group contains the configuration for user defined ACPI
tables. The attributes of a user define table are:
- aml - a binary attribute that the user can use to
+ aml
+ - a binary attribute that the user can use to
fill in the ACPI aml definitions. Once the aml
data is written to this file and the file is
closed the table will be loaded and ACPI devices
@@ -26,11 +27,26 @@
The rest of the attributes are read-only and are valid only
after the table has been loaded by filling the aml entry:
- signature - ASCII table signature
- length - length of table in bytes, including the header
- revision - ACPI Specification minor version number
- oem_id - ASCII OEM identification
- oem_table_id - ASCII OEM table identification
- oem_revision - OEM revision number
- asl_compiler_id - ASCII ASL compiler vendor ID
- asl_compiler_revision - ASL compiler version
+ signature
+ - ASCII table signature
+
+ length
+ - length of table in bytes, including the header
+
+ revision
+ - ACPI Specification minor version number
+
+ oem_id
+ - ASCII OEM identification
+
+ oem_table_id
+ - ASCII OEM table identification
+
+ oem_revision
+ - OEM revision number
+
+ asl_compiler_id
+ - ASCII ASL compiler vendor ID
+
+ asl_compiler_revision
+ - ASL compiler version
diff --git a/Documentation/ABI/testing/configfs-most b/Documentation/ABI/testing/configfs-most
index ed67a4d..bc6b8bd 100644
--- a/Documentation/ABI/testing/configfs-most
+++ b/Documentation/ABI/testing/configfs-most
@@ -15,22 +15,28 @@
Description:
The attributes:
- buffer_size configure the buffer size for this channel
+ buffer_size
+ configure the buffer size for this channel
- subbuffer_size configure the sub-buffer size for this channel
+ subbuffer_size
+ configure the sub-buffer size for this channel
(needed for synchronous and isochrnous data)
- num_buffers configure number of buffers used for this
+ num_buffers
+ configure number of buffers used for this
channel
- datatype configure type of data that will travel over
+ datatype
+ configure type of data that will travel over
this channel
- direction configure whether this link will be an input
+ direction
+ configure whether this link will be an input
or output
- dbr_size configure DBR data buffer size (this is used
+ dbr_size
+ configure DBR data buffer size (this is used
for MediaLB communication only)
packets_per_xact
@@ -39,18 +45,23 @@
transmitted via USB (this is used for USB
communication only)
- device name of the device the link is to be attached to
+ device
+ name of the device the link is to be attached to
- channel name of the channel the link is to be attached to
+ channel
+ name of the channel the link is to be attached to
- comp_params pass parameters needed by some components
+ comp_params
+ pass parameters needed by some components
- create_link write '1' to this attribute to trigger the
+ create_link
+ write '1' to this attribute to trigger the
creation of the link. In case of speculative
configuration, the creation is post-poned until
a physical device is being attached to the bus.
- destroy_link write '1' to this attribute to destroy an
+ destroy_link
+ write '1' to this attribute to destroy an
active link
What: /sys/kernel/config/most_video/<link>
@@ -59,22 +70,28 @@
Description:
The attributes:
- buffer_size configure the buffer size for this channel
+ buffer_size
+ configure the buffer size for this channel
- subbuffer_size configure the sub-buffer size for this channel
+ subbuffer_size
+ configure the sub-buffer size for this channel
(needed for synchronous and isochrnous data)
- num_buffers configure number of buffers used for this
+ num_buffers
+ configure number of buffers used for this
channel
- datatype configure type of data that will travel over
+ datatype
+ configure type of data that will travel over
this channel
- direction configure whether this link will be an input
+ direction
+ configure whether this link will be an input
or output
- dbr_size configure DBR data buffer size (this is used
+ dbr_size
+ configure DBR data buffer size (this is used
for MediaLB communication only)
packets_per_xact
@@ -83,18 +100,23 @@
transmitted via USB (this is used for USB
communication only)
- device name of the device the link is to be attached to
+ device
+ name of the device the link is to be attached to
- channel name of the channel the link is to be attached to
+ channel
+ name of the channel the link is to be attached to
- comp_params pass parameters needed by some components
+ comp_params
+ pass parameters needed by some components
- create_link write '1' to this attribute to trigger the
+ create_link
+ write '1' to this attribute to trigger the
creation of the link. In case of speculative
configuration, the creation is post-poned until
a physical device is being attached to the bus.
- destroy_link write '1' to this attribute to destroy an
+ destroy_link
+ write '1' to this attribute to destroy an
active link
What: /sys/kernel/config/most_net/<link>
@@ -103,22 +125,28 @@
Description:
The attributes:
- buffer_size configure the buffer size for this channel
+ buffer_size
+ configure the buffer size for this channel
- subbuffer_size configure the sub-buffer size for this channel
+ subbuffer_size
+ configure the sub-buffer size for this channel
(needed for synchronous and isochrnous data)
- num_buffers configure number of buffers used for this
+ num_buffers
+ configure number of buffers used for this
channel
- datatype configure type of data that will travel over
+ datatype
+ configure type of data that will travel over
this channel
- direction configure whether this link will be an input
+ direction
+ configure whether this link will be an input
or output
- dbr_size configure DBR data buffer size (this is used
+ dbr_size
+ configure DBR data buffer size (this is used
for MediaLB communication only)
packets_per_xact
@@ -127,18 +155,23 @@
transmitted via USB (this is used for USB
communication only)
- device name of the device the link is to be attached to
+ device
+ name of the device the link is to be attached to
- channel name of the channel the link is to be attached to
+ channel
+ name of the channel the link is to be attached to
- comp_params pass parameters needed by some components
+ comp_params
+ pass parameters needed by some components
- create_link write '1' to this attribute to trigger the
+ create_link
+ write '1' to this attribute to trigger the
creation of the link. In case of speculative
configuration, the creation is post-poned until
a physical device is being attached to the bus.
- destroy_link write '1' to this attribute to destroy an
+ destroy_link
+ write '1' to this attribute to destroy an
active link
What: /sys/kernel/config/most_sound/<card>
@@ -147,7 +180,8 @@
Description:
The attributes:
- create_card write '1' to this attribute to trigger the
+ create_card
+ write '1' to this attribute to trigger the
registration of the sound card with the ALSA
subsystem.
@@ -157,22 +191,28 @@
Description:
The attributes:
- buffer_size configure the buffer size for this channel
+ buffer_size
+ configure the buffer size for this channel
- subbuffer_size configure the sub-buffer size for this channel
+ subbuffer_size
+ configure the sub-buffer size for this channel
(needed for synchronous and isochrnous data)
- num_buffers configure number of buffers used for this
+ num_buffers
+ configure number of buffers used for this
channel
- datatype configure type of data that will travel over
+ datatype
+ configure type of data that will travel over
this channel
- direction configure whether this link will be an input
+ direction
+ configure whether this link will be an input
or output
- dbr_size configure DBR data buffer size (this is used
+ dbr_size
+ configure DBR data buffer size (this is used
for MediaLB communication only)
packets_per_xact
@@ -181,16 +221,21 @@
transmitted via USB (this is used for USB
communication only)
- device name of the device the link is to be attached to
+ device
+ name of the device the link is to be attached to
- channel name of the channel the link is to be attached to
+ channel
+ name of the channel the link is to be attached to
- comp_params pass parameters needed by some components
+ comp_params
+ pass parameters needed by some components
- create_link write '1' to this attribute to trigger the
+ create_link
+ write '1' to this attribute to trigger the
creation of the link. In case of speculative
configuration, the creation is post-poned until
a physical device is being attached to the bus.
- destroy_link write '1' to this attribute to destroy an
+ destroy_link
+ write '1' to this attribute to destroy an
active link
diff --git a/Documentation/ABI/testing/configfs-spear-pcie-gadget b/Documentation/ABI/testing/configfs-spear-pcie-gadget
index 840c324..cf877bd 100644
--- a/Documentation/ABI/testing/configfs-spear-pcie-gadget
+++ b/Documentation/ABI/testing/configfs-spear-pcie-gadget
@@ -10,22 +10,24 @@
This interfaces can be used to show spear's PCIe device capability.
Nodes are only visible when configfs is mounted. To mount configfs
- in /config directory use:
- # mount -t configfs none /config/
+ in /config directory use::
- For nth PCIe Device Controller
- /config/pcie-gadget.n/
- link ... used to enable ltssm and read its status.
- int_type ...used to configure and read type of supported
- interrupt
- no_of_msi ... used to configure number of MSI vector needed and
+ # mount -t configfs none /config/
+
+ For nth PCIe Device Controller /config/pcie-gadget.n/:
+
+ =============== ======================================================
+ link used to enable ltssm and read its status.
+ int_type used to configure and read type of supported interrupt
+ no_of_msi used to configure number of MSI vector needed and
to read no of MSI granted.
- inta ... write 1 to assert INTA and 0 to de-assert.
- send_msi ... write MSI vector to be sent.
- vendor_id ... used to write and read vendor id (hex)
- device_id ... used to write and read device id (hex)
- bar0_size ... used to write and read bar0_size
- bar0_address ... used to write and read bar0 mapped area in hex.
- bar0_rw_offset ... used to write and read offset of bar0 where
- bar0_data will be written or read.
- bar0_data ... used to write and read data at bar0_rw_offset.
+ inta write 1 to assert INTA and 0 to de-assert.
+ send_msi write MSI vector to be sent.
+ vendor_id used to write and read vendor id (hex)
+ device_id used to write and read device id (hex)
+ bar0_size used to write and read bar0_size
+ bar0_address used to write and read bar0 mapped area in hex.
+ bar0_rw_offset used to write and read offset of bar0 where bar0_data
+ will be written or read.
+ bar0_data used to write and read data at bar0_rw_offset.
+ =============== ======================================================
diff --git a/Documentation/ABI/testing/configfs-usb-gadget b/Documentation/ABI/testing/configfs-usb-gadget
index 4594cc2..dc351e9 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget
+++ b/Documentation/ABI/testing/configfs-usb-gadget
@@ -12,22 +12,24 @@
The attributes of a gadget:
- UDC - bind a gadget to UDC/unbind a gadget;
- write UDC's name found in /sys/class/udc/*
- to bind a gadget, empty string "" to unbind.
+ ================ ============================================
+ UDC bind a gadget to UDC/unbind a gadget;
+ write UDC's name found in /sys/class/udc/*
+ to bind a gadget, empty string "" to unbind.
- max_speed - maximum speed the driver supports. Valid
- names are super-speed-plus, super-speed,
- high-speed, full-speed, and low-speed.
+ max_speed maximum speed the driver supports. Valid
+ names are super-speed-plus, super-speed,
+ high-speed, full-speed, and low-speed.
- bDeviceClass - USB device class code
- bDeviceSubClass - USB device subclass code
- bDeviceProtocol - USB device protocol code
- bMaxPacketSize0 - maximum endpoint 0 packet size
- bcdDevice - bcd device release number
- bcdUSB - bcd USB specification version number
- idProduct - product ID
- idVendor - vendor ID
+ bDeviceClass USB device class code
+ bDeviceSubClass USB device subclass code
+ bDeviceProtocol USB device protocol code
+ bMaxPacketSize0 maximum endpoint 0 packet size
+ bcdDevice bcd device release number
+ bcdUSB bcd USB specification version number
+ idProduct product ID
+ idVendor vendor ID
+ ================ ============================================
What: /config/usb-gadget/gadget/configs
Date: Jun 2013
@@ -41,8 +43,10 @@
Description:
The attributes of a configuration:
- bmAttributes - configuration characteristics
- MaxPower - maximum power consumption from the bus
+ ================ ======================================
+ bmAttributes configuration characteristics
+ MaxPower maximum power consumption from the bus
+ ================ ======================================
What: /config/usb-gadget/gadget/configs/config/strings
Date: Jun 2013
@@ -57,7 +61,9 @@
Description:
The attributes:
- configuration - configuration description
+ ================ =========================
+ configuration configuration description
+ ================ =========================
What: /config/usb-gadget/gadget/functions
@@ -76,8 +82,10 @@
The attributes:
- compatible_id - 8-byte string for "Compatible ID"
- sub_compatible_id - 8-byte string for "Sub Compatible ID"
+ ================= =====================================
+ compatible_id 8-byte string for "Compatible ID"
+ sub_compatible_id 8-byte string for "Sub Compatible ID"
+ ================= =====================================
What: /config/usb-gadget/gadget/functions/<func>.<inst>/interface.<n>/<property>
Date: May 2014
@@ -89,16 +97,19 @@
The attributes:
- type - value 1..7 for interpreting the data
- 1: unicode string
- 2: unicode string with environment variable
- 3: binary
- 4: little-endian 32-bit
- 5: big-endian 32-bit
- 6: unicode string with a symbolic link
- 7: multiple unicode strings
- data - blob of data to be interpreted depending on
+ ===== ===============================================
+ type value 1..7 for interpreting the data
+
+ - 1: unicode string
+ - 2: unicode string with environment variable
+ - 3: binary
+ - 4: little-endian 32-bit
+ - 5: big-endian 32-bit
+ - 6: unicode string with a symbolic link
+ - 7: multiple unicode strings
+ data blob of data to be interpreted depending on
type
+ ===== ===============================================
What: /config/usb-gadget/gadget/strings
Date: Jun 2013
@@ -113,9 +124,11 @@
Description:
The attributes:
- serialnumber - gadget's serial number (string)
- product - gadget's product description
- manufacturer - gadget's manufacturer description
+ ============ =================================
+ serialnumber gadget's serial number (string)
+ product gadget's product description
+ manufacturer gadget's manufacturer description
+ ============ =================================
What: /config/usb-gadget/gadget/os_desc
Date: May 2014
@@ -123,8 +136,10 @@
Description:
This group contains "OS String" extension handling attributes.
- use - flag turning "OS Desctiptors" support on/off
- b_vendor_code - one-byte value used for custom per-device and
+ ============= ===============================================
+ use flag turning "OS Desctiptors" support on/off
+ b_vendor_code one-byte value used for custom per-device and
per-interface requests
- qw_sign - an identifier to be reported as "OS String"
+ qw_sign an identifier to be reported as "OS String"
proper
+ ============= ===============================================
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-ecm b/Documentation/ABI/testing/configfs-usb-gadget-ecm
index 0addf77..272bc1e 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-ecm
+++ b/Documentation/ABI/testing/configfs-usb-gadget-ecm
@@ -4,13 +4,17 @@
Description:
The attributes:
- ifname - network device interface name associated with
+ ifname
+ - network device interface name associated with
this function instance
- qmult - queue length multiplier for high and
+ qmult
+ - queue length multiplier for high and
super speed
- host_addr - MAC address of host's end of this
+ host_addr
+ - MAC address of host's end of this
Ethernet over USB link
- dev_addr - MAC address of device's end of this
+ dev_addr
+ - MAC address of device's end of this
Ethernet over USB link
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-eem b/Documentation/ABI/testing/configfs-usb-gadget-eem
index a4c5715..178c3d5 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-eem
+++ b/Documentation/ABI/testing/configfs-usb-gadget-eem
@@ -4,11 +4,13 @@
Description:
The attributes:
- ifname - network device interface name associated with
+ ========== =============================================
+ ifname network device interface name associated with
this function instance
- qmult - queue length multiplier for high and
+ qmult queue length multiplier for high and
super speed
- host_addr - MAC address of host's end of this
+ host_addr MAC address of host's end of this
Ethernet over USB link
- dev_addr - MAC address of device's end of this
+ dev_addr MAC address of device's end of this
Ethernet over USB link
+ ========== =============================================
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-hid b/Documentation/ABI/testing/configfs-usb-gadget-hid
index f12e00e..748705c 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-hid
+++ b/Documentation/ABI/testing/configfs-usb-gadget-hid
@@ -4,8 +4,10 @@
Description:
The attributes:
- protocol - HID protocol to use
- report_desc - blob corresponding to HID report descriptors
+ ============= ============================================
+ protocol HID protocol to use
+ report_desc blob corresponding to HID report descriptors
except the data passed through /dev/hidg<N>
- report_length - HID report length
- subclass - HID device subclass to use
+ report_length HID report length
+ subclass HID device subclass to use
+ ============= ============================================
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-loopback b/Documentation/ABI/testing/configfs-usb-gadget-loopback
index 06beefbc..e6c6ba5ac 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-loopback
+++ b/Documentation/ABI/testing/configfs-usb-gadget-loopback
@@ -4,5 +4,7 @@
Description:
The attributes:
- qlen - depth of loopback queue
- buflen - buffer length
+ ======= =======================
+ qlen depth of loopback queue
+ buflen buffer length
+ ======= =======================
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-mass-storage b/Documentation/ABI/testing/configfs-usb-gadget-mass-storage
index 9931fb0..c86b63a 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-mass-storage
+++ b/Documentation/ABI/testing/configfs-usb-gadget-mass-storage
@@ -4,12 +4,14 @@
Description:
The attributes:
- stall - Set to permit function to halt bulk endpoints.
+ =========== ==============================================
+ stall Set to permit function to halt bulk endpoints.
Disabled on some USB devices known not to work
correctly. You should set it to true.
- num_buffers - Number of pipeline buffers. Valid numbers
+ num_buffers Number of pipeline buffers. Valid numbers
are 2..4. Available only if
CONFIG_USB_GADGET_DEBUG_FILES is set.
+ =========== ==============================================
What: /config/usb-gadget/gadget/functions/mass_storage.name/lun.name
Date: Oct 2013
@@ -17,15 +19,17 @@
Description:
The attributes:
- file - The path to the backing file for the LUN.
+ =========== ==============================================
+ file The path to the backing file for the LUN.
Required if LUN is not marked as removable.
- ro - Flag specifying access to the LUN shall be
+ ro Flag specifying access to the LUN shall be
read-only. This is implied if CD-ROM emulation
is enabled as well as when it was impossible
to open "filename" in R/W mode.
- removable - Flag specifying that LUN shall be indicated as
+ removable Flag specifying that LUN shall be indicated as
being removable.
- cdrom - Flag specifying that LUN shall be reported as
+ cdrom Flag specifying that LUN shall be reported as
being a CD-ROM.
- nofua - Flag specifying that FUA flag
+ nofua Flag specifying that FUA flag
in SCSI WRITE(10,12)
+ =========== ==============================================
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-midi b/Documentation/ABI/testing/configfs-usb-gadget-midi
index 6b341df..07389cd 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-midi
+++ b/Documentation/ABI/testing/configfs-usb-gadget-midi
@@ -4,9 +4,11 @@
Description:
The attributes:
- index - index value for the USB MIDI adapter
- id - ID string for the USB MIDI adapter
- buflen - MIDI buffer length
- qlen - USB read request queue length
- in_ports - number of MIDI input ports
- out_ports - number of MIDI output ports
+ ========== ====================================
+ index index value for the USB MIDI adapter
+ id ID string for the USB MIDI adapter
+ buflen MIDI buffer length
+ qlen USB read request queue length
+ in_ports number of MIDI input ports
+ out_ports number of MIDI output ports
+ ========== ====================================
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-printer b/Documentation/ABI/testing/configfs-usb-gadget-printer
index 6b0714e..7aa731b 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-printer
+++ b/Documentation/ABI/testing/configfs-usb-gadget-printer
@@ -4,6 +4,8 @@
Description:
The attributes:
- pnp_string - Data to be passed to the host in pnp string
- q_len - Number of requests per endpoint
+ ========== ===========================================
+ pnp_string Data to be passed to the host in pnp string
+ q_len Number of requests per endpoint
+ ========== ===========================================
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-rndis b/Documentation/ABI/testing/configfs-usb-gadget-rndis
index 1373990..9416eda 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-rndis
+++ b/Documentation/ABI/testing/configfs-usb-gadget-rndis
@@ -4,14 +4,16 @@
Description:
The attributes:
- ifname - network device interface name associated with
+ ========= =============================================
+ ifname network device interface name associated with
this function instance
- qmult - queue length multiplier for high and
+ qmult queue length multiplier for high and
super speed
- host_addr - MAC address of host's end of this
+ host_addr MAC address of host's end of this
Ethernet over USB link
- dev_addr - MAC address of device's end of this
+ dev_addr MAC address of device's end of this
Ethernet over USB link
- class - USB interface class, default is 02 (hex)
- subclass - USB interface subclass, default is 06 (hex)
- protocol - USB interface protocol, default is 00 (hex)
+ class USB interface class, default is 02 (hex)
+ subclass USB interface subclass, default is 06 (hex)
+ protocol USB interface protocol, default is 00 (hex)
+ ========= =============================================
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-sourcesink b/Documentation/ABI/testing/configfs-usb-gadget-sourcesink
index f56335a..1f3d31b 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-sourcesink
+++ b/Documentation/ABI/testing/configfs-usb-gadget-sourcesink
@@ -4,11 +4,13 @@
Description:
The attributes:
- pattern - 0 (all zeros), 1 (mod63), 2 (none)
- isoc_interval - 1..16
- isoc_maxpacket - 0 - 1023 (fs), 0 - 1024 (hs/ss)
- isoc_mult - 0..2 (hs/ss only)
- isoc_maxburst - 0..15 (ss only)
- buflen - buffer length
- bulk_qlen - depth of queue for bulk
- iso_qlen - depth of queue for iso
+ ============== ==================================
+ pattern 0 (all zeros), 1 (mod63), 2 (none)
+ isoc_interval 1..16
+ isoc_maxpacket 0 - 1023 (fs), 0 - 1024 (hs/ss)
+ isoc_mult 0..2 (hs/ss only)
+ isoc_maxburst 0..15 (ss only)
+ buflen buffer length
+ bulk_qlen depth of queue for bulk
+ iso_qlen depth of queue for iso
+ ============== ==================================
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-subset b/Documentation/ABI/testing/configfs-usb-gadget-subset
index 9373e2c5..0061b86 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-subset
+++ b/Documentation/ABI/testing/configfs-usb-gadget-subset
@@ -4,11 +4,13 @@
Description:
The attributes:
- ifname - network device interface name associated with
+ ========== =============================================
+ ifname network device interface name associated with
this function instance
- qmult - queue length multiplier for high and
+ qmult queue length multiplier for high and
super speed
- host_addr - MAC address of host's end of this
+ host_addr MAC address of host's end of this
Ethernet over USB link
- dev_addr - MAC address of device's end of this
+ dev_addr MAC address of device's end of this
Ethernet over USB link
+ ========== =============================================
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-uac1 b/Documentation/ABI/testing/configfs-usb-gadget-uac1
index abfe447..dc23fd7 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-uac1
+++ b/Documentation/ABI/testing/configfs-usb-gadget-uac1
@@ -4,11 +4,13 @@
Description:
The attributes:
- c_chmask - capture channel mask
- c_srate - capture sampling rate
- c_ssize - capture sample size (bytes)
- p_chmask - playback channel mask
- p_srate - playback sampling rate
- p_ssize - playback sample size (bytes)
- req_number - the number of pre-allocated request
- for both capture and playback
+ ========== ===================================
+ c_chmask capture channel mask
+ c_srate capture sampling rate
+ c_ssize capture sample size (bytes)
+ p_chmask playback channel mask
+ p_srate playback sampling rate
+ p_ssize playback sample size (bytes)
+ req_number the number of pre-allocated request
+ for both capture and playback
+ ========== ===================================
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-uac2 b/Documentation/ABI/testing/configfs-usb-gadget-uac2
index 2bfdd4e..d4356c8 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-uac2
+++ b/Documentation/ABI/testing/configfs-usb-gadget-uac2
@@ -4,9 +4,11 @@
Description:
The attributes:
- c_chmask - capture channel mask
- c_srate - capture sampling rate
- c_ssize - capture sample size (bytes)
- p_chmask - playback channel mask
- p_srate - playback sampling rate
- p_ssize - playback sample size (bytes)
+ ========= ============================
+ c_chmask capture channel mask
+ c_srate capture sampling rate
+ c_ssize capture sample size (bytes)
+ p_chmask playback channel mask
+ p_srate playback sampling rate
+ p_ssize playback sample size (bytes)
+ ========= ============================
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-uvc b/Documentation/ABI/testing/configfs-usb-gadget-uvc
index 809765b..ac5e11a 100644
--- a/Documentation/ABI/testing/configfs-usb-gadget-uvc
+++ b/Documentation/ABI/testing/configfs-usb-gadget-uvc
@@ -3,9 +3,11 @@
KernelVersion: 4.0
Description: UVC function directory
- streaming_maxburst - 0..15 (ss only)
- streaming_maxpacket - 1..1023 (fs), 1..3072 (hs/ss)
- streaming_interval - 1..16
+ =================== =============================
+ streaming_maxburst 0..15 (ss only)
+ streaming_maxpacket 1..1023 (fs), 1..3072 (hs/ss)
+ streaming_interval 1..16
+ =================== =============================
What: /config/usb-gadget/gadget/functions/uvc.name/control
Date: Dec 2014
@@ -13,8 +15,11 @@
Description: Control descriptors
All attributes read only:
- bInterfaceNumber - USB interface number for this
- streaming interface
+
+ ================ =============================
+ bInterfaceNumber USB interface number for this
+ streaming interface
+ ================ =============================
What: /config/usb-gadget/gadget/functions/uvc.name/control/class
Date: Dec 2014
@@ -47,13 +52,16 @@
Description: Default output terminal descriptors
All attributes read only:
- iTerminal - index of string descriptor
- bSourceID - id of the terminal to which this terminal
+
+ ============== =============================================
+ iTerminal index of string descriptor
+ bSourceID id of the terminal to which this terminal
is connected
- bAssocTerminal - id of the input terminal to which this output
+ bAssocTerminal id of the input terminal to which this output
terminal is associated
- wTerminalType - terminal type
- bTerminalID - a non-zero id of this terminal
+ wTerminalType terminal type
+ bTerminalID a non-zero id of this terminal
+ ============== =============================================
What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal/camera
Date: Dec 2014
@@ -66,16 +74,19 @@
Description: Default camera terminal descriptors
All attributes read only:
- bmControls - bitmap specifying which controls are
- supported for the video stream
- wOcularFocalLength - the value of Locular
- wObjectiveFocalLengthMax- the value of Lmin
- wObjectiveFocalLengthMin- the value of Lmax
- iTerminal - index of string descriptor
- bAssocTerminal - id of the output terminal to which
- this terminal is connected
- wTerminalType - terminal type
- bTerminalID - a non-zero id of this terminal
+
+ ======================== ====================================
+ bmControls bitmap specifying which controls are
+ supported for the video stream
+ wOcularFocalLength the value of Locular
+ wObjectiveFocalLengthMax the value of Lmin
+ wObjectiveFocalLengthMin the value of Lmax
+ iTerminal index of string descriptor
+ bAssocTerminal id of the output terminal to which
+ this terminal is connected
+ wTerminalType terminal type
+ bTerminalID a non-zero id of this terminal
+ ======================== ====================================
What: /config/usb-gadget/gadget/functions/uvc.name/control/processing
Date: Dec 2014
@@ -88,13 +99,16 @@
Description: Default processing unit descriptors
All attributes read only:
- iProcessing - index of string descriptor
- bmControls - bitmap specifying which controls are
+
+ =============== ========================================
+ iProcessing index of string descriptor
+ bmControls bitmap specifying which controls are
supported for the video stream
- wMaxMultiplier - maximum digital magnification x100
- bSourceID - id of the terminal to which this unit is
+ wMaxMultiplier maximum digital magnification x100
+ bSourceID id of the terminal to which this unit is
connected
- bUnitID - a non-zero id of this unit
+ bUnitID a non-zero id of this unit
+ =============== ========================================
What: /config/usb-gadget/gadget/functions/uvc.name/control/header
Date: Dec 2014
@@ -114,8 +128,11 @@
Description: Streaming descriptors
All attributes read only:
- bInterfaceNumber - USB interface number for this
- streaming interface
+
+ ================ =============================
+ bInterfaceNumber USB interface number for this
+ streaming interface
+ ================ =============================
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/class
Date: Dec 2014
@@ -148,13 +165,16 @@
Description: Default color matching descriptors
All attributes read only:
- bMatrixCoefficients - matrix used to compute luma and
- chroma values from the color primaries
- bTransferCharacteristics- optoelectronic transfer
- characteristic of the source picutre,
- also called the gamma function
- bColorPrimaries - color primaries and the reference
- white
+
+ ======================== ======================================
+ bMatrixCoefficients matrix used to compute luma and
+ chroma values from the color primaries
+ bTransferCharacteristics optoelectronic transfer
+ characteristic of the source picutre,
+ also called the gamma function
+ bColorPrimaries color primaries and the reference
+ white
+ ======================== ======================================
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/mjpeg
Date: Dec 2014
@@ -168,47 +188,52 @@
All attributes read only,
except bmaControls and bDefaultFrameIndex:
- bFormatIndex - unique id for this format descriptor;
+
+ =================== =====================================
+ bFormatIndex unique id for this format descriptor;
only defined after parent header is
linked into the streaming class;
read-only
- bmaControls - this format's data for bmaControls in
+ bmaControls this format's data for bmaControls in
the streaming header
- bmInterfaceFlags - specifies interlace information,
+ bmInterfaceFlags specifies interlace information,
read-only
- bAspectRatioY - the X dimension of the picture aspect
+ bAspectRatioY the X dimension of the picture aspect
ratio, read-only
- bAspectRatioX - the Y dimension of the picture aspect
+ bAspectRatioX the Y dimension of the picture aspect
ratio, read-only
- bmFlags - characteristics of this format,
+ bmFlags characteristics of this format,
read-only
- bDefaultFrameIndex - optimum frame index for this stream
+ bDefaultFrameIndex optimum frame index for this stream
+ =================== =====================================
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/mjpeg/name/name
Date: Dec 2014
KernelVersion: 4.0
Description: Specific MJPEG frame descriptors
- bFrameIndex - unique id for this framedescriptor;
- only defined after parent format is
- linked into the streaming header;
- read-only
- dwFrameInterval - indicates how frame interval can be
- programmed; a number of values
- separated by newline can be specified
- dwDefaultFrameInterval - the frame interval the device would
- like to use as default
- dwMaxVideoFrameBufferSize- the maximum number of bytes the
- compressor will produce for a video
- frame or still image
- dwMaxBitRate - the maximum bit rate at the shortest
- frame interval in bps
- dwMinBitRate - the minimum bit rate at the longest
- frame interval in bps
- wHeight - height of decoded bitmap frame in px
- wWidth - width of decoded bitmam frame in px
- bmCapabilities - still image support, fixed frame-rate
- support
+ ========================= =====================================
+ bFrameIndex unique id for this framedescriptor;
+ only defined after parent format is
+ linked into the streaming header;
+ read-only
+ dwFrameInterval indicates how frame interval can be
+ programmed; a number of values
+ separated by newline can be specified
+ dwDefaultFrameInterval the frame interval the device would
+ like to use as default
+ dwMaxVideoFrameBufferSize the maximum number of bytes the
+ compressor will produce for a video
+ frame or still image
+ dwMaxBitRate the maximum bit rate at the shortest
+ frame interval in bps
+ dwMinBitRate the minimum bit rate at the longest
+ frame interval in bps
+ wHeight height of decoded bitmap frame in px
+ wWidth width of decoded bitmam frame in px
+ bmCapabilities still image support, fixed frame-rate
+ support
+ ========================= =====================================
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/uncompressed
Date: Dec 2014
@@ -220,50 +245,54 @@
KernelVersion: 4.0
Description: Specific uncompressed format descriptors
- bFormatIndex - unique id for this format descriptor;
+ ================== =======================================
+ bFormatIndex unique id for this format descriptor;
only defined after parent header is
linked into the streaming class;
read-only
- bmaControls - this format's data for bmaControls in
+ bmaControls this format's data for bmaControls in
the streaming header
- bmInterfaceFlags - specifies interlace information,
+ bmInterfaceFlags specifies interlace information,
read-only
- bAspectRatioY - the X dimension of the picture aspect
+ bAspectRatioY the X dimension of the picture aspect
ratio, read-only
- bAspectRatioX - the Y dimension of the picture aspect
+ bAspectRatioX the Y dimension of the picture aspect
ratio, read-only
- bDefaultFrameIndex - optimum frame index for this stream
- bBitsPerPixel - number of bits per pixel used to
+ bDefaultFrameIndex optimum frame index for this stream
+ bBitsPerPixel number of bits per pixel used to
specify color in the decoded video
frame
- guidFormat - globally unique id used to identify
+ guidFormat globally unique id used to identify
stream-encoding format
+ ================== =======================================
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/uncompressed/name/name
Date: Dec 2014
KernelVersion: 4.0
Description: Specific uncompressed frame descriptors
- bFrameIndex - unique id for this framedescriptor;
- only defined after parent format is
- linked into the streaming header;
- read-only
- dwFrameInterval - indicates how frame interval can be
- programmed; a number of values
- separated by newline can be specified
- dwDefaultFrameInterval - the frame interval the device would
- like to use as default
- dwMaxVideoFrameBufferSize- the maximum number of bytes the
- compressor will produce for a video
- frame or still image
- dwMaxBitRate - the maximum bit rate at the shortest
- frame interval in bps
- dwMinBitRate - the minimum bit rate at the longest
- frame interval in bps
- wHeight - height of decoded bitmap frame in px
- wWidth - width of decoded bitmam frame in px
- bmCapabilities - still image support, fixed frame-rate
- support
+ ========================= =====================================
+ bFrameIndex unique id for this framedescriptor;
+ only defined after parent format is
+ linked into the streaming header;
+ read-only
+ dwFrameInterval indicates how frame interval can be
+ programmed; a number of values
+ separated by newline can be specified
+ dwDefaultFrameInterval the frame interval the device would
+ like to use as default
+ dwMaxVideoFrameBufferSize the maximum number of bytes the
+ compressor will produce for a video
+ frame or still image
+ dwMaxBitRate the maximum bit rate at the shortest
+ frame interval in bps
+ dwMinBitRate the minimum bit rate at the longest
+ frame interval in bps
+ wHeight height of decoded bitmap frame in px
+ wWidth width of decoded bitmam frame in px
+ bmCapabilities still image support, fixed frame-rate
+ support
+ ========================= =====================================
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/header
Date: Dec 2014
@@ -276,17 +305,20 @@
Description: Specific streaming header descriptors
All attributes read only:
- bTriggerUsage - how the host software will respond to
+
+ ==================== =====================================
+ bTriggerUsage how the host software will respond to
a hardware trigger interrupt event
- bTriggerSupport - flag specifying if hardware
+ bTriggerSupport flag specifying if hardware
triggering is supported
- bStillCaptureMethod - method of still image caputre
+ bStillCaptureMethod method of still image caputre
supported
- bTerminalLink - id of the output terminal to which
+ bTerminalLink id of the output terminal to which
the video endpoint of this interface
is connected
- bmInfo - capabilities of this video streaming
+ bmInfo capabilities of this video streaming
interface
+ ==================== =====================================
What: /sys/class/udc/udc.name/device/gadget/video4linux/video.name/function_name
Date: May 2018
diff --git a/Documentation/ABI/testing/debugfs-cec-error-inj b/Documentation/ABI/testing/debugfs-cec-error-inj
index 5afcd78f..8debcb0 100644
--- a/Documentation/ABI/testing/debugfs-cec-error-inj
+++ b/Documentation/ABI/testing/debugfs-cec-error-inj
@@ -23,7 +23,7 @@
commands.
Note that the output of 'error-inj' shall be valid as input to 'error-inj'.
-So this must work:
+So this must work::
$ cat error-inj >einj.txt
$ cat einj.txt >error-inj
diff --git a/Documentation/ABI/testing/debugfs-driver-habanalabs b/Documentation/ABI/testing/debugfs-driver-habanalabs
index 2e9ae31..c5d678d 100644
--- a/Documentation/ABI/testing/debugfs-driver-habanalabs
+++ b/Documentation/ABI/testing/debugfs-driver-habanalabs
@@ -20,9 +20,13 @@
The user can supply a bitmask value, each bit represents
a different engine to disable/enable its clock gating feature.
The bitmask is composed of 20 bits:
- 0 - 7 : DMA channels
- 8 - 11 : MME engines
- 12 - 19 : TPC engines
+
+ ======= ============
+ 0 - 7 DMA channels
+ 8 - 11 MME engines
+ 12 - 19 TPC engines
+ ======= ============
+
The bit's location of a specific engine can be determined
using (1 << GAUDI_ENGINE_ID_*). GAUDI_ENGINE_ID_* values
are defined in uapi habanalabs.h file in enum gaudi_engine_id
@@ -59,6 +63,7 @@
the generic Linux user-space PCI mapping) because the DDR bar
is very small compared to the DDR memory and only the driver can
move the bar before and after the transaction.
+
If the IOMMU is disabled, it also allows the root user to read
or write from the host a device VA of a host mapped memory
@@ -73,6 +78,7 @@
the generic Linux user-space PCI mapping) because the DDR bar
is very small compared to the DDR memory and only the driver can
move the bar before and after the transaction.
+
If the IOMMU is disabled, it also allows the root user to read
or write from the host a device VA of a host mapped memory
diff --git a/Documentation/ABI/testing/debugfs-ec b/Documentation/ABI/testing/debugfs-ec
index 6546115..ab6099d 100644
--- a/Documentation/ABI/testing/debugfs-ec
+++ b/Documentation/ABI/testing/debugfs-ec
@@ -6,7 +6,7 @@
General information like which GPE is assigned to the EC and whether
the global lock should get used.
Knowing the EC GPE one can watch the amount of HW events related to
-the EC here (XY -> GPE number from /sys/kernel/debug/ec/*/gpe):
+the EC here (XY -> GPE number from `/sys/kernel/debug/ec/*/gpe`):
/sys/firmware/acpi/interrupts/gpeXY
The io file is binary and a userspace tool located here:
@@ -14,7 +14,8 @@
should get used to read out the 256 Embedded Controller registers
or writing to them.
-CAUTION: Do not write to the Embedded Controller if you don't know
-what you are doing! Rebooting afterwards also is a good idea.
-This can influence the way your machine is cooled and fans may
-not get switched on again after you did a wrong write.
+CAUTION:
+ Do not write to the Embedded Controller if you don't know
+ what you are doing! Rebooting afterwards also is a good idea.
+ This can influence the way your machine is cooled and fans may
+ not get switched on again after you did a wrong write.
diff --git a/Documentation/ABI/testing/debugfs-moxtet b/Documentation/ABI/testing/debugfs-moxtet
index 67b1717..6eee10c 100644
--- a/Documentation/ABI/testing/debugfs-moxtet
+++ b/Documentation/ABI/testing/debugfs-moxtet
@@ -2,13 +2,19 @@
Date: March 2019
KernelVersion: 5.3
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) Read input from the shift registers, in hexadecimal.
+Description: (Read) Read input from the shift registers, in hexadecimal.
Returns N+1 bytes, where N is the number of Moxtet connected
modules. The first byte is from the CPU board itself.
- Example: 101214
- 10: CPU board with SD card
- 12: 2 = PCIe module, 1 = IRQ not active
- 14: 4 = Peridot module, 1 = IRQ not active
+
+ Example::
+
+ 101214
+
+ == =======================================
+ 10 CPU board with SD card
+ 12 2 = PCIe module, 1 = IRQ not active
+ 14 4 = Peridot module, 1 = IRQ not active
+ == =======================================
What: /sys/kernel/debug/moxtet/output
Date: March 2019
@@ -17,7 +23,13 @@
Description: (RW) Read last written value to the shift registers, in
hexadecimal, or write values to the shift registers, also
in hexadecimal.
- Example: 0102
- 01: 01 was last written, or is to be written, to the
- first module's shift register
- 02: the same for second module
+
+ Example::
+
+ 0102
+
+ == ================================================
+ 01 01 was last written, or is to be written, to the
+ first module's shift register
+ 02 the same for second module
+ == ================================================
diff --git a/Documentation/ABI/testing/debugfs-pfo-nx-crypto b/Documentation/ABI/testing/debugfs-pfo-nx-crypto
index 685d5a4..f75a655 100644
--- a/Documentation/ABI/testing/debugfs-pfo-nx-crypto
+++ b/Documentation/ABI/testing/debugfs-pfo-nx-crypto
@@ -4,42 +4,42 @@
Contact: Kent Yoder <key@linux.vnet.ibm.com>
Description:
- These debugfs interfaces are built by the nx-crypto driver, built in
+These debugfs interfaces are built by the nx-crypto driver, built in
arch/powerpc/crypto/nx.
Error Detection
===============
errors:
-- A u32 providing a total count of errors since the driver was loaded. The
-only errors counted here are those returned from the hcall, H_COP_OP.
+ A u32 providing a total count of errors since the driver was loaded. The
+ only errors counted here are those returned from the hcall, H_COP_OP.
last_error:
-- The most recent non-zero return code from the H_COP_OP hcall. -EBUSY is not
-recorded here (the hcall will retry until -EBUSY goes away).
+ The most recent non-zero return code from the H_COP_OP hcall. -EBUSY is not
+ recorded here (the hcall will retry until -EBUSY goes away).
last_error_pid:
-- The process ID of the process who received the most recent error from the
-hcall.
+ The process ID of the process who received the most recent error from the
+ hcall.
Device Use
==========
aes_bytes:
-- The total number of bytes encrypted using AES in any of the driver's
-supported modes.
+ The total number of bytes encrypted using AES in any of the driver's
+ supported modes.
aes_ops:
-- The total number of AES operations submitted to the hardware.
+ The total number of AES operations submitted to the hardware.
sha256_bytes:
-- The total number of bytes hashed by the hardware using SHA-256.
+ The total number of bytes hashed by the hardware using SHA-256.
sha256_ops:
-- The total number of SHA-256 operations submitted to the hardware.
+ The total number of SHA-256 operations submitted to the hardware.
sha512_bytes:
-- The total number of bytes hashed by the hardware using SHA-512.
+ The total number of bytes hashed by the hardware using SHA-512.
sha512_ops:
-- The total number of SHA-512 operations submitted to the hardware.
+ The total number of SHA-512 operations submitted to the hardware.
diff --git a/Documentation/ABI/testing/debugfs-pktcdvd b/Documentation/ABI/testing/debugfs-pktcdvd
index cf11736..f6f65a4 100644
--- a/Documentation/ABI/testing/debugfs-pktcdvd
+++ b/Documentation/ABI/testing/debugfs-pktcdvd
@@ -4,16 +4,15 @@
Contact: Thomas Maier <balagi@justmail.de>
Description:
-debugfs interface
------------------
-
The pktcdvd module (packet writing driver) creates
these files in debugfs:
/sys/kernel/debug/pktcdvd/pktcdvd[0-7]/
- info (0444) Lots of driver statistics and infos.
-Example:
--------
+ ==== ====== ====================================
+ info 0444 Lots of driver statistics and infos.
+ ==== ====== ====================================
-cat /sys/kernel/debug/pktcdvd/pktcdvd0/info
+Example::
+
+ cat /sys/kernel/debug/pktcdvd/pktcdvd0/info
diff --git a/Documentation/ABI/testing/debugfs-turris-mox-rwtm b/Documentation/ABI/testing/debugfs-turris-mox-rwtm
index 2b3255e..326df1b 100644
--- a/Documentation/ABI/testing/debugfs-turris-mox-rwtm
+++ b/Documentation/ABI/testing/debugfs-turris-mox-rwtm
@@ -2,8 +2,13 @@
Date: Jun 2020
KernelVersion: 5.8
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (W) Message to sign with the ECDSA private key stored in
- device's OTP. The message must be exactly 64 bytes (since
- this is intended for SHA-512 hashes).
- (R) The resulting signature, 136 bytes. This contains the R and
- S values of the ECDSA signature, both in big-endian format.
+Description:
+
+ ======= ===========================================================
+ (Write) Message to sign with the ECDSA private key stored in
+ device's OTP. The message must be exactly 64 bytes
+ (since this is intended for SHA-512 hashes).
+ (Read) The resulting signature, 136 bytes. This contains the
+ R and S values of the ECDSA signature, both in
+ big-endian format.
+ ======= ===========================================================
diff --git a/Documentation/ABI/testing/debugfs-wilco-ec b/Documentation/ABI/testing/debugfs-wilco-ec
index 9d8d9d2..682e3c0 100644
--- a/Documentation/ABI/testing/debugfs-wilco-ec
+++ b/Documentation/ABI/testing/debugfs-wilco-ec
@@ -27,16 +27,17 @@
for writing, two for the type and at least a single byte of
data.
- Example:
- // Request EC info type 3 (EC firmware build date)
- // Corresponds with sending type 0x00f0 with
- // MBOX = [38, 00, 03, 00]
- $ echo 00 f0 38 00 03 00 > /sys/kernel/debug/wilco_ec/raw
- // View the result. The decoded ASCII result "12/21/18" is
- // included after the raw hex.
- // Corresponds with MBOX = [00, 00, 31, 32, 2f, 32, 31, 38, ...]
- $ cat /sys/kernel/debug/wilco_ec/raw
- 00 00 31 32 2f 32 31 2f 31 38 00 38 00 01 00 2f 00 ..12/21/18.8...
+ Example::
+
+ // Request EC info type 3 (EC firmware build date)
+ // Corresponds with sending type 0x00f0 with
+ // MBOX = [38, 00, 03, 00]
+ $ echo 00 f0 38 00 03 00 > /sys/kernel/debug/wilco_ec/raw
+ // View the result. The decoded ASCII result "12/21/18" is
+ // included after the raw hex.
+ // Corresponds with MBOX = [00, 00, 31, 32, 2f, 32, 31, 38, ...]
+ $ cat /sys/kernel/debug/wilco_ec/raw
+ 00 00 31 32 2f 32 31 2f 31 38 00 38 00 01 00 2f 00 ..12/21/18.8...
Note that the first 16 bytes of the received MBOX[] will be
printed, even if some of the data is junk, and skipping bytes
diff --git a/Documentation/ABI/testing/dell-smbios-wmi b/Documentation/ABI/testing/dell-smbios-wmi
index fc919ce..5f3a0dc 100644
--- a/Documentation/ABI/testing/dell-smbios-wmi
+++ b/Documentation/ABI/testing/dell-smbios-wmi
@@ -10,29 +10,29 @@
<uapi/linux/wmi.h>
1) To perform an SMBIOS call from userspace, you'll need to
- first determine the minimum size of the calling interface
- buffer for your machine.
- Platforms that contain larger buffers can return larger
- objects from the system firmware.
- Commonly this size is either 4k or 32k.
+ first determine the minimum size of the calling interface
+ buffer for your machine.
+ Platforms that contain larger buffers can return larger
+ objects from the system firmware.
+ Commonly this size is either 4k or 32k.
- To determine the size of the buffer read() a u64 dword from
- the WMI character device /dev/wmi/dell-smbios.
+ To determine the size of the buffer read() a u64 dword from
+ the WMI character device /dev/wmi/dell-smbios.
2) After you've determined the minimum size of the calling
- interface buffer, you can allocate a structure that represents
- the structure documented above.
+ interface buffer, you can allocate a structure that represents
+ the structure documented above.
3) In the 'length' object store the size of the buffer you
- determined above and allocated.
+ determined above and allocated.
4) In this buffer object, prepare as necessary for the SMBIOS
- call you're interested in. Typically SMBIOS buffers have
- "class", "select", and "input" defined to values that coincide
- with the data you are interested in.
- Documenting class/select/input values is outside of the scope
- of this documentation. Check with the libsmbios project for
- further documentation on these values.
+ call you're interested in. Typically SMBIOS buffers have
+ "class", "select", and "input" defined to values that coincide
+ with the data you are interested in.
+ Documenting class/select/input values is outside of the scope
+ of this documentation. Check with the libsmbios project for
+ further documentation on these values.
6) Run the call by using ioctl() as described in the header.
diff --git a/Documentation/ABI/testing/dev-kmsg b/Documentation/ABI/testing/dev-kmsg
index 3c0bb76..a377b6c 100644
--- a/Documentation/ABI/testing/dev-kmsg
+++ b/Documentation/ABI/testing/dev-kmsg
@@ -6,6 +6,7 @@
to the kernel's printk buffer.
Injecting messages:
+
Every write() to the opened device node places a log entry in
the kernel's printk buffer.
@@ -21,6 +22,7 @@
the messages can always be reliably determined.
Accessing the buffer:
+
Every read() from the opened device node receives one record
of the kernel's printk buffer.
@@ -48,6 +50,7 @@
if needed, without limiting the interface to a single reader.
The device supports seek with the following parameters:
+
SEEK_SET, 0
seek to the first entry in the buffer
SEEK_END, 0
@@ -87,18 +90,22 @@
readable context of the message, for reliable processing in
userspace.
- Example:
- 7,160,424069,-;pci_root PNP0A03:00: host bridge window [io 0x0000-0x0cf7] (ignored)
- SUBSYSTEM=acpi
- DEVICE=+acpi:PNP0A03:00
- 6,339,5140900,-;NET: Registered protocol family 10
- 30,340,5690716,-;udevd[80]: starting version 181
+ Example::
+
+ 7,160,424069,-;pci_root PNP0A03:00: host bridge window [io 0x0000-0x0cf7] (ignored)
+ SUBSYSTEM=acpi
+ DEVICE=+acpi:PNP0A03:00
+ 6,339,5140900,-;NET: Registered protocol family 10
+ 30,340,5690716,-;udevd[80]: starting version 181
The DEVICE= key uniquely identifies devices the following way:
- b12:8 - block dev_t
- c127:3 - char dev_t
- n8 - netdev ifindex
- +sound:card0 - subsystem:devname
+
+ ============ =================
+ b12:8 block dev_t
+ c127:3 char dev_t
+ n8 netdev ifindex
+ +sound:card0 subsystem:devname
+ ============ =================
The flags field carries '-' by default. A 'c' indicates a
fragment of a line. Note, that these hints about continuation
diff --git a/Documentation/ABI/testing/evm b/Documentation/ABI/testing/evm
index 201d103..3c477ba 100644
--- a/Documentation/ABI/testing/evm
+++ b/Documentation/ABI/testing/evm
@@ -17,26 +17,33 @@
echoing a value to <securityfs>/evm made up of the
following bits:
+ === ==================================================
Bit Effect
+ === ==================================================
0 Enable HMAC validation and creation
1 Enable digital signature validation
2 Permit modification of EVM-protected metadata at
runtime. Not supported if HMAC validation and
creation is enabled.
31 Disable further runtime modification of EVM policy
+ === ==================================================
- For example:
+ For example::
- echo 1 ><securityfs>/evm
+ echo 1 ><securityfs>/evm
will enable HMAC validation and creation
- echo 0x80000003 ><securityfs>/evm
+ ::
+
+ echo 0x80000003 ><securityfs>/evm
will enable HMAC and digital signature validation and
HMAC creation and disable all further modification of policy.
- echo 0x80000006 ><securityfs>/evm
+ ::
+
+ echo 0x80000006 ><securityfs>/evm
will enable digital signature validation, permit
modification of EVM-protected metadata and
@@ -65,7 +72,7 @@
Shows the set of extended attributes used to calculate or
validate the EVM signature, and allows additional attributes
to be added at runtime. Any signatures generated after
- additional attributes are added (and on files posessing those
+ additional attributes are added (and on files possessing those
additional attributes) will only be valid if the same
additional attributes are configured on system boot. Writing
a single period (.) will lock the xattr list from any further
diff --git a/Documentation/ABI/testing/gpio-cdev b/Documentation/ABI/testing/gpio-cdev
index 7b265fbb..66bdcd1 100644
--- a/Documentation/ABI/testing/gpio-cdev
+++ b/Documentation/ABI/testing/gpio-cdev
@@ -12,15 +12,16 @@
The following file operations are supported:
open(2)
- Currently the only useful flags are O_RDWR.
+ Currently the only useful flags are O_RDWR.
ioctl(2)
- Initiate various actions.
- See the inline documentation in [include/uapi]<linux/gpio.h>
- for descriptions of all ioctls.
+ Initiate various actions.
+
+ See the inline documentation in [include/uapi]<linux/gpio.h>
+ for descriptions of all ioctls.
close(2)
- Stops and free up the I/O contexts that was associated
- with the file descriptor.
+ Stops and free up the I/O contexts that was associated
+ with the file descriptor.
Users: TBD
diff --git a/Documentation/ABI/testing/ima_policy b/Documentation/ABI/testing/ima_policy
index cd57291..e35263f 100644
--- a/Documentation/ABI/testing/ima_policy
+++ b/Documentation/ABI/testing/ima_policy
@@ -15,19 +15,22 @@
IMA appraisal, if configured, uses these file measurements
for local measurement appraisal.
- rule format: action [condition ...]
+ ::
- action: measure | dont_measure | appraise | dont_appraise |
- audit | hash | dont_hash
- condition:= base | lsm [option]
+ rule format: action [condition ...]
+
+ action: measure | dont_measure | appraise | dont_appraise |
+ audit | hash | dont_hash
+ condition:= base | lsm [option]
base: [[func=] [mask=] [fsmagic=] [fsuuid=] [uid=]
[euid=] [fowner=] [fsname=]]
lsm: [[subj_user=] [subj_role=] [subj_type=]
[obj_user=] [obj_role=] [obj_type=]]
option: [[appraise_type=]] [template=] [permit_directio]
[appraise_flag=] [keyrings=]
- base: func:= [BPRM_CHECK][MMAP_CHECK][CREDS_CHECK][FILE_CHECK][MODULE_CHECK]
- [FIRMWARE_CHECK]
+ base:
+ func:= [BPRM_CHECK][MMAP_CHECK][CREDS_CHECK][FILE_CHECK]MODULE_CHECK]
+ [FIRMWARE_CHECK]
[KEXEC_KERNEL_CHECK] [KEXEC_INITRAMFS_CHECK]
[KEXEC_CMDLINE] [KEY_CHECK]
mask:= [[^]MAY_READ] [[^]MAY_WRITE] [[^]MAY_APPEND]
@@ -37,8 +40,9 @@
uid:= decimal value
euid:= decimal value
fowner:= decimal value
- lsm: are LSM specific
- option: appraise_type:= [imasig] [imasig|modsig]
+ lsm: are LSM specific
+ option:
+ appraise_type:= [imasig] [imasig|modsig]
appraise_flag:= [check_blacklist]
Currently, blacklist check is only for files signed with appended
signature.
@@ -49,7 +53,7 @@
(eg, ima-ng). Only valid when action is "measure".
pcr:= decimal value
- default policy:
+ default policy:
# PROC_SUPER_MAGIC
dont_measure fsmagic=0x9fa0
dont_appraise fsmagic=0x9fa0
@@ -97,7 +101,8 @@
Examples of LSM specific definitions:
- SELinux:
+ SELinux::
+
dont_measure obj_type=var_log_t
dont_appraise obj_type=var_log_t
dont_measure obj_type=auditd_log_t
@@ -105,10 +110,11 @@
measure subj_user=system_u func=FILE_CHECK mask=MAY_READ
measure subj_role=system_r func=FILE_CHECK mask=MAY_READ
- Smack:
+ Smack::
+
measure subj_user=_ func=FILE_CHECK mask=MAY_READ
- Example of measure rules using alternate PCRs:
+ Example of measure rules using alternate PCRs::
measure func=KEXEC_KERNEL_CHECK pcr=4
measure func=KEXEC_INITRAMFS_CHECK pcr=5
diff --git a/Documentation/ABI/testing/procfs-diskstats b/Documentation/ABI/testing/procfs-diskstats
index 70dcaf2..e58d641 100644
--- a/Documentation/ABI/testing/procfs-diskstats
+++ b/Documentation/ABI/testing/procfs-diskstats
@@ -6,32 +6,38 @@
of block devices. Each line contains the following 14
fields:
- 1 - major number
- 2 - minor mumber
- 3 - device name
- 4 - reads completed successfully
- 5 - reads merged
- 6 - sectors read
- 7 - time spent reading (ms)
- 8 - writes completed
- 9 - writes merged
- 10 - sectors written
- 11 - time spent writing (ms)
- 12 - I/Os currently in progress
- 13 - time spent doing I/Os (ms)
- 14 - weighted time spent doing I/Os (ms)
+ == ===================================
+ 1 major number
+ 2 minor mumber
+ 3 device name
+ 4 reads completed successfully
+ 5 reads merged
+ 6 sectors read
+ 7 time spent reading (ms)
+ 8 writes completed
+ 9 writes merged
+ 10 sectors written
+ 11 time spent writing (ms)
+ 12 I/Os currently in progress
+ 13 time spent doing I/Os (ms)
+ 14 weighted time spent doing I/Os (ms)
+ == ===================================
Kernel 4.18+ appends four more fields for discard
tracking putting the total at 18:
- 15 - discards completed successfully
- 16 - discards merged
- 17 - sectors discarded
- 18 - time spent discarding
+ == ===================================
+ 15 discards completed successfully
+ 16 discards merged
+ 17 sectors discarded
+ 18 time spent discarding
+ == ===================================
Kernel 5.5+ appends two more fields for flush requests:
- 19 - flush requests completed successfully
- 20 - time spent flushing
+ == =====================================
+ 19 flush requests completed successfully
+ 20 time spent flushing
+ == =====================================
For more details refer to Documentation/admin-guide/iostats.rst
diff --git a/Documentation/ABI/testing/procfs-smaps_rollup b/Documentation/ABI/testing/procfs-smaps_rollup
index 0469781..a4e31c4 100644
--- a/Documentation/ABI/testing/procfs-smaps_rollup
+++ b/Documentation/ABI/testing/procfs-smaps_rollup
@@ -14,28 +14,28 @@
For more details, see Documentation/filesystems/proc.rst
and the procfs man page.
- Typical output looks like this:
+ Typical output looks like this::
- 00100000-ff709000 ---p 00000000 00:00 0 [rollup]
- Size: 1192 kB
- KernelPageSize: 4 kB
- MMUPageSize: 4 kB
- Rss: 884 kB
- Pss: 385 kB
- Pss_Anon: 301 kB
- Pss_File: 80 kB
- Pss_Shmem: 4 kB
- Shared_Clean: 696 kB
- Shared_Dirty: 0 kB
- Private_Clean: 120 kB
- Private_Dirty: 68 kB
- Referenced: 884 kB
- Anonymous: 68 kB
- LazyFree: 0 kB
- AnonHugePages: 0 kB
- ShmemPmdMapped: 0 kB
- Shared_Hugetlb: 0 kB
- Private_Hugetlb: 0 kB
- Swap: 0 kB
- SwapPss: 0 kB
- Locked: 385 kB
+ 00100000-ff709000 ---p 00000000 00:00 0 [rollup]
+ Size: 1192 kB
+ KernelPageSize: 4 kB
+ MMUPageSize: 4 kB
+ Rss: 884 kB
+ Pss: 385 kB
+ Pss_Anon: 301 kB
+ Pss_File: 80 kB
+ Pss_Shmem: 4 kB
+ Shared_Clean: 696 kB
+ Shared_Dirty: 0 kB
+ Private_Clean: 120 kB
+ Private_Dirty: 68 kB
+ Referenced: 884 kB
+ Anonymous: 68 kB
+ LazyFree: 0 kB
+ AnonHugePages: 0 kB
+ ShmemPmdMapped: 0 kB
+ Shared_Hugetlb: 0 kB
+ Private_Hugetlb: 0 kB
+ Swap: 0 kB
+ SwapPss: 0 kB
+ Locked: 385 kB
diff --git a/Documentation/ABI/testing/pstore b/Documentation/ABI/testing/pstore
index d45209a..5b02540 100644
--- a/Documentation/ABI/testing/pstore
+++ b/Documentation/ABI/testing/pstore
@@ -9,25 +9,25 @@
provide a generic interface to show records captured in
the dying moments. In the case of a panic the last part
of the console log is captured, but other interesting
- data can also be saved.
+ data can also be saved::
- # mount -t pstore -o kmsg_bytes=8000 - /sys/fs/pstore
+ # mount -t pstore -o kmsg_bytes=8000 - /sys/fs/pstore
- $ ls -l /sys/fs/pstore/
- total 0
- -r--r--r-- 1 root root 7896 Nov 30 15:38 dmesg-erst-1
+ $ ls -l /sys/fs/pstore/
+ total 0
+ -r--r--r-- 1 root root 7896 Nov 30 15:38 dmesg-erst-1
Different users of this interface will result in different
filename prefixes. Currently two are defined:
- "dmesg" - saved console log
- "mce" - architecture dependent data from fatal h/w error
+ - "dmesg" - saved console log
+ - "mce" - architecture dependent data from fatal h/w error
Once the information in a file has been read, removing
the file will signal to the underlying persistent storage
- device that it can reclaim the space for later re-use.
+ device that it can reclaim the space for later re-use::
- $ rm /sys/fs/pstore/dmesg-erst-1
+ $ rm /sys/fs/pstore/dmesg-erst-1
The expectation is that all files in /sys/fs/pstore/
will be saved elsewhere and erased from persistent store
@@ -44,4 +44,3 @@
backends are available, the preferred backend may be
set by passing the pstore.backend= argument to the kernel at
boot time.
-
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index 2322eb7..e34cdee 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -4,23 +4,27 @@
Description:
The /sys/block/<disk>/stat files displays the I/O
statistics of disk <disk>. They contain 11 fields:
- 1 - reads completed successfully
- 2 - reads merged
- 3 - sectors read
- 4 - time spent reading (ms)
- 5 - writes completed
- 6 - writes merged
- 7 - sectors written
- 8 - time spent writing (ms)
- 9 - I/Os currently in progress
- 10 - time spent doing I/Os (ms)
- 11 - weighted time spent doing I/Os (ms)
- 12 - discards completed
- 13 - discards merged
- 14 - sectors discarded
- 15 - time spent discarding (ms)
- 16 - flush requests completed
- 17 - time spent flushing (ms)
+
+ == ==============================================
+ 1 reads completed successfully
+ 2 reads merged
+ 3 sectors read
+ 4 time spent reading (ms)
+ 5 writes completed
+ 6 writes merged
+ 7 sectors written
+ 8 time spent writing (ms)
+ 9 I/Os currently in progress
+ 10 time spent doing I/Os (ms)
+ 11 weighted time spent doing I/Os (ms)
+ 12 discards completed
+ 13 discards merged
+ 14 sectors discarded
+ 15 time spent discarding (ms)
+ 16 flush requests completed
+ 17 time spent flushing (ms)
+ == ==============================================
+
For more details refer Documentation/admin-guide/iostats.rst
diff --git a/Documentation/ABI/testing/sysfs-block-device b/Documentation/ABI/testing/sysfs-block-device
index 17f2bc7..aa0fb50 100644
--- a/Documentation/ABI/testing/sysfs-block-device
+++ b/Documentation/ABI/testing/sysfs-block-device
@@ -8,11 +8,13 @@
It has the following valid values:
+ == ========================================================
0 OFF - the LED is not activated on activity
1 BLINK_ON - the LED blinks on every 10ms when activity is
detected.
2 BLINK_OFF - the LED is on when idle, and blinks off
every 10ms when activity is detected.
+ == ========================================================
Note that the user must turn sw_activity OFF it they wish to
control the activity LED via the em_message file.
diff --git a/Documentation/ABI/testing/sysfs-block-rnbd b/Documentation/ABI/testing/sysfs-block-rnbd
index 8f070b4..14a6fe9 100644
--- a/Documentation/ABI/testing/sysfs-block-rnbd
+++ b/Documentation/ABI/testing/sysfs-block-rnbd
@@ -9,9 +9,9 @@
is using the device. When "force" is used, the device is also unmapped
when device is in use. All I/Os that are in progress will fail.
- Example:
+ Example::
- # echo "normal" > /sys/block/rnbd0/rnbd/unmap_device
+ # echo "normal" > /sys/block/rnbd0/rnbd/unmap_device
What: /sys/block/rnbd<N>/rnbd/state
Date: Feb 2020
diff --git a/Documentation/ABI/testing/sysfs-bus-acpi b/Documentation/ABI/testing/sysfs-bus-acpi
index e7898cf..58abacf 100644
--- a/Documentation/ABI/testing/sysfs-bus-acpi
+++ b/Documentation/ABI/testing/sysfs-bus-acpi
@@ -5,6 +5,7 @@
This attribute indicates the full path of ACPI namespace
object associated with the device object. For example,
\_SB_.PCI0.
+
This file is not present for device objects representing
fixed ACPI hardware features (like power and sleep
buttons).
@@ -67,14 +68,16 @@
The return value is a decimal integer representing the device's
status bitmap:
- Bit [0] – Set if the device is present.
- Bit [1] – Set if the device is enabled and decoding its
- resources.
- Bit [2] – Set if the device should be shown in the UI.
- Bit [3] – Set if the device is functioning properly (cleared if
- device failed its diagnostics).
- Bit [4] – Set if the battery is present.
- Bits [31:5] – Reserved (must be cleared)
+ =========== ==================================================
+ Bit [0] Set if the device is present.
+ Bit [1] Set if the device is enabled and decoding its
+ resources.
+ Bit [2] Set if the device should be shown in the UI.
+ Bit [3] Set if the device is functioning properly (cleared
+ if device failed its diagnostics).
+ Bit [4] Set if the battery is present.
+ Bits [31:5] Reserved (must be cleared)
+ =========== ==================================================
If bit [0] is clear, then bit 1 must also be clear (a device
that is not present cannot be enabled).
diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-cti b/Documentation/ABI/testing/sysfs-bus-coresight-devices-cti
index 9d11502..bf2869c 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-cti
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-cti
@@ -8,50 +8,50 @@
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Indicate if the CTI hardware is powered.
+Description: (Read) Indicate if the CTI hardware is powered.
What: /sys/bus/coresight/devices/<cti-name>/ctmid
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Display the associated CTM ID
+Description: (Read) Display the associated CTM ID
What: /sys/bus/coresight/devices/<cti-name>/nr_trigger_cons
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Number of devices connected to triggers on this CTI
+Description: (Read) Number of devices connected to triggers on this CTI
What: /sys/bus/coresight/devices/<cti-name>/triggers<N>/name
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Name of connected device <N>
+Description: (Read) Name of connected device <N>
What: /sys/bus/coresight/devices/<cti-name>/triggers<N>/in_signals
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Input trigger signals from connected device <N>
+Description: (Read) Input trigger signals from connected device <N>
What: /sys/bus/coresight/devices/<cti-name>/triggers<N>/in_types
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Functional types for the input trigger signals
+Description: (Read) Functional types for the input trigger signals
from connected device <N>
What: /sys/bus/coresight/devices/<cti-name>/triggers<N>/out_signals
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Output trigger signals to connected device <N>
+Description: (Read) Output trigger signals to connected device <N>
What: /sys/bus/coresight/devices/<cti-name>/triggers<N>/out_types
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Functional types for the output trigger signals
+Description: (Read) Functional types for the output trigger signals
to connected device <N>
What: /sys/bus/coresight/devices/<cti-name>/regs/inout_sel
@@ -88,7 +88,7 @@
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Write the INTACK register.
+Description: (Write) Write the INTACK register.
What: /sys/bus/coresight/devices/<cti-name>/regs/appset
Date: March 2020
@@ -101,99 +101,99 @@
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Write APPCLEAR register to deactivate channel.
+Description: (Write) Write APPCLEAR register to deactivate channel.
What: /sys/bus/coresight/devices/<cti-name>/regs/apppulse
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Write APPPULSE to pulse a channel active for one clock
+Description: (Write) Write APPPULSE to pulse a channel active for one clock
cycle.
What: /sys/bus/coresight/devices/<cti-name>/regs/chinstatus
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Read current status of channel inputs.
+Description: (Read) Read current status of channel inputs.
What: /sys/bus/coresight/devices/<cti-name>/regs/choutstatus
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) read current status of channel outputs.
+Description: (Read) read current status of channel outputs.
What: /sys/bus/coresight/devices/<cti-name>/regs/triginstatus
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) read current status of input trigger signals
+Description: (Read) read current status of input trigger signals
What: /sys/bus/coresight/devices/<cti-name>/regs/trigoutstatus
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) read current status of output trigger signals.
+Description: (Read) read current status of output trigger signals.
What: /sys/bus/coresight/devices/<cti-name>/channels/trigin_attach
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Attach a CTI input trigger to a CTM channel.
+Description: (Write) Attach a CTI input trigger to a CTM channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/trigin_detach
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Detach a CTI input trigger from a CTM channel.
+Description: (Write) Detach a CTI input trigger from a CTM channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/trigout_attach
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Attach a CTI output trigger to a CTM channel.
+Description: (Write) Attach a CTI output trigger to a CTM channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/trigout_detach
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Detach a CTI output trigger from a CTM channel.
+Description: (Write) Detach a CTI output trigger from a CTM channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_gate_enable
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (RW) Enable CTIGATE for single channel (W) or list enabled
+Description: (RW) Enable CTIGATE for single channel (Write) or list enabled
channels through the gate (R).
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_gate_disable
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Disable CTIGATE for single channel.
+Description: (Write) Disable CTIGATE for single channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_set
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Activate a single channel.
+Description: (Write) Activate a single channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_clear
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Deactivate a single channel.
+Description: (Write) Deactivate a single channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_pulse
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Pulse a single channel - activate for a single clock cycle.
+Description: (Write) Pulse a single channel - activate for a single clock cycle.
What: /sys/bus/coresight/devices/<cti-name>/channels/trigout_filtered
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) List of output triggers filtered across all connections.
+Description: (Read) List of output triggers filtered across all connections.
What: /sys/bus/coresight/devices/<cti-name>/channels/trig_filter_enable
Date: March 2020
@@ -205,13 +205,13 @@
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) show channels with at least one attached trigger signal.
+Description: (Read) show channels with at least one attached trigger signal.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_free
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) show channels with no attached trigger signals.
+Description: (Read) show channels with no attached trigger signals.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_xtrigs_sel
Date: March 2020
@@ -224,18 +224,18 @@
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Read to see input triggers connected to selected view
+Description: (Read) Read to see input triggers connected to selected view
channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_xtrigs_out
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Read to see output triggers connected to selected view
+Description: (Read) Read to see output triggers connected to selected view
channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_xtrigs_reset
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Clear all channel / trigger programming.
+Description: (Write) Clear all channel / trigger programming.
diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-etb10 b/Documentation/ABI/testing/sysfs-bus-coresight-devices-etb10
index b5f52608..9a383f6 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-etb10
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-etb10
@@ -4,7 +4,10 @@
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
Description: (RW) Add/remove a sink from a trace path. There can be multiple
source for a single sink.
- ex: echo 1 > /sys/bus/coresight/devices/20010000.etb/enable_sink
+
+ ex::
+
+ echo 1 > /sys/bus/coresight/devices/20010000.etb/enable_sink
What: /sys/bus/coresight/devices/<memory_map>.etb/trigger_cntr
Date: November 2014
@@ -20,21 +23,21 @@
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Defines the depth, in words, of the trace RAM in powers of
+Description: (Read) Defines the depth, in words, of the trace RAM in powers of
2. The value is read directly from HW register RDP, 0x004.
What: /sys/bus/coresight/devices/<memory_map>.etb/mgmt/sts
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the ETB status register. The value
+Description: (Read) Shows the value held by the ETB status register. The value
is read directly from HW register STS, 0x00C.
What: /sys/bus/coresight/devices/<memory_map>.etb/mgmt/rrp
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the ETB RAM Read Pointer register
+Description: (Read) Shows the value held by the ETB RAM Read Pointer register
that is used to read entries from the Trace RAM over the APB
interface. The value is read directly from HW register RRP,
0x014.
@@ -43,7 +46,7 @@
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the ETB RAM Write Pointer register
+Description: (Read) Shows the value held by the ETB RAM Write Pointer register
that is used to sets the write pointer to write entries from
the CoreSight bus into the Trace RAM. The value is read directly
from HW register RWP, 0x018.
@@ -52,21 +55,21 @@
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Similar to "trigger_cntr" above except that this value is
+Description: (Read) Similar to "trigger_cntr" above except that this value is
read directly from HW register TRG, 0x01C.
What: /sys/bus/coresight/devices/<memory_map>.etb/mgmt/ctl
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the ETB Control register. The value
+Description: (Read) Shows the value held by the ETB Control register. The value
is read directly from HW register CTL, 0x020.
What: /sys/bus/coresight/devices/<memory_map>.etb/mgmt/ffsr
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the ETB Formatter and Flush Status
+Description: (Read) Shows the value held by the ETB Formatter and Flush Status
register. The value is read directly from HW register FFSR,
0x300.
@@ -74,6 +77,6 @@
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the ETB Formatter and Flush Control
+Description: (Read) Shows the value held by the ETB Formatter and Flush Control
register. The value is read directly from HW register FFCR,
0x304.
diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm3x b/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm3x
index 924265a..651602a 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm3x
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm3x
@@ -146,28 +146,28 @@
Date: November 2014
KernelVersion: 3.19
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Provides the number of address comparators pairs accessible
+Description: (Read) Provides the number of address comparators pairs accessible
on a trace unit, as specified by bit 3:0 of register ETMCCR.
What: /sys/bus/coresight/devices/<memory_map>.[etm|ptm]/nr_cntr
Date: November 2014
KernelVersion: 3.19
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Provides the number of counters accessible on a trace unit,
+Description: (Read) Provides the number of counters accessible on a trace unit,
as specified by bit 15:13 of register ETMCCR.
What: /sys/bus/coresight/devices/<memory_map>.[etm|ptm]/nr_ctxid_cmp
Date: November 2014
KernelVersion: 3.19
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Provides the number of context ID comparator available on a
+Description: (Read) Provides the number of context ID comparator available on a
trace unit, as specified by bit 25:24 of register ETMCCR.
What: /sys/bus/coresight/devices/<memory_map>.[etm|ptm]/reset
Date: November 2014
KernelVersion: 3.19
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (W) Cancels all configuration on a trace unit and set it back
+Description: (Write) Cancels all configuration on a trace unit and set it back
to its boot configuration.
What: /sys/bus/coresight/devices/<memory_map>.[etm|ptm]/seq_12_event
@@ -216,7 +216,7 @@
Date: November 2014
KernelVersion: 3.19
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Holds the current state of the sequencer.
+Description: (Read) Holds the current state of the sequencer.
What: /sys/bus/coresight/devices/<memory_map>.[etm|ptm]/sync_freq
Date: November 2014
diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm4x b/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm4x
index 614874e..881f0cd 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm4x
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm4x
@@ -12,75 +12,75 @@
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) The CPU this tracing entity is associated with.
+Description: (Read) The CPU this tracing entity is associated with.
What: /sys/bus/coresight/devices/etm<N>/nr_pe_cmp
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the number of PE comparator inputs that are
+Description: (Read) Indicates the number of PE comparator inputs that are
available for tracing.
What: /sys/bus/coresight/devices/etm<N>/nr_addr_cmp
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the number of address comparator pairs that are
+Description: (Read) Indicates the number of address comparator pairs that are
available for tracing.
What: /sys/bus/coresight/devices/etm<N>/nr_cntr
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the number of counters that are available for
+Description: (Read) Indicates the number of counters that are available for
tracing.
What: /sys/bus/coresight/devices/etm<N>/nr_ext_inp
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates how many external inputs are implemented.
+Description: (Read) Indicates how many external inputs are implemented.
What: /sys/bus/coresight/devices/etm<N>/numcidc
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the number of Context ID comparators that are
+Description: (Read) Indicates the number of Context ID comparators that are
available for tracing.
What: /sys/bus/coresight/devices/etm<N>/numvmidc
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the number of VMID comparators that are available
+Description: (Read) Indicates the number of VMID comparators that are available
for tracing.
What: /sys/bus/coresight/devices/etm<N>/nrseqstate
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the number of sequencer states that are
+Description: (Read) Indicates the number of sequencer states that are
implemented.
What: /sys/bus/coresight/devices/etm<N>/nr_resource
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the number of resource selection pairs that are
+Description: (Read) Indicates the number of resource selection pairs that are
available for tracing.
What: /sys/bus/coresight/devices/etm<N>/nr_ss_cmp
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the number of single-shot comparator controls that
+Description: (Read) Indicates the number of single-shot comparator controls that
are available for tracing.
What: /sys/bus/coresight/devices/etm<N>/reset
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (W) Cancels all configuration on a trace unit and set it back
+Description: (Write) Cancels all configuration on a trace unit and set it back
to its boot configuration.
What: /sys/bus/coresight/devices/etm<N>/mode
@@ -300,7 +300,7 @@
Date: December 2019
KernelVersion: 5.5
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the current settings for the selected address
+Description: (Read) Print the current settings for the selected address
comparator.
What: /sys/bus/coresight/devices/etm<N>/sshot_idx
@@ -319,7 +319,7 @@
Date: December 2019
KernelVersion: 5.5
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the current value of the selected single shot
+Description: (Read) Print the current value of the selected single shot
status register.
What: /sys/bus/coresight/devices/etm<N>/sshot_pe_ctrl
@@ -333,111 +333,111 @@
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the OS Lock Status Register (0x304).
+Description: (Read) Print the content of the OS Lock Status Register (0x304).
The value it taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcpdcr
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Power Down Control Register
+Description: (Read) Print the content of the Power Down Control Register
(0x310). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcpdsr
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Power Down Status Register
+Description: (Read) Print the content of the Power Down Status Register
(0x314). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trclsr
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the SW Lock Status Register
+Description: (Read) Print the content of the SW Lock Status Register
(0xFB4). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcauthstatus
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Authentication Status Register
+Description: (Read) Print the content of the Authentication Status Register
(0xFB8). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcdevid
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Device ID Register
+Description: (Read) Print the content of the Device ID Register
(0xFC8). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcdevtype
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Device Type Register
+Description: (Read) Print the content of the Device Type Register
(0xFCC). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcpidr0
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Peripheral ID0 Register
+Description: (Read) Print the content of the Peripheral ID0 Register
(0xFE0). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcpidr1
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Peripheral ID1 Register
+Description: (Read) Print the content of the Peripheral ID1 Register
(0xFE4). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcpidr2
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Peripheral ID2 Register
+Description: (Read) Print the content of the Peripheral ID2 Register
(0xFE8). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcpidr3
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Peripheral ID3 Register
+Description: (Read) Print the content of the Peripheral ID3 Register
(0xFEC). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcconfig
Date: February 2016
KernelVersion: 4.07
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the trace configuration register
+Description: (Read) Print the content of the trace configuration register
(0x010) as currently set by SW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trctraceid
Date: February 2016
KernelVersion: 4.07
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the trace ID register (0x040).
+Description: (Read) Print the content of the trace ID register (0x040).
What: /sys/bus/coresight/devices/etm<N>/trcidr/trcidr0
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the tracing capabilities of the trace unit (0x1E0).
+Description: (Read) Returns the tracing capabilities of the trace unit (0x1E0).
The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/trcidr/trcidr1
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the tracing capabilities of the trace unit (0x1E4).
+Description: (Read) Returns the tracing capabilities of the trace unit (0x1E4).
The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/trcidr/trcidr2
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the maximum size of the data value, data address,
+Description: (Read) Returns the maximum size of the data value, data address,
VMID, context ID and instuction address in the trace unit
(0x1E8). The value is taken directly from the HW.
@@ -445,7 +445,7 @@
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the value associated with various resources
+Description: (Read) Returns the value associated with various resources
available to the trace unit. See the Trace Macrocell
architecture specification for more details (0x1E8).
The value is taken directly from the HW.
@@ -454,42 +454,42 @@
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns how many resources the trace unit supports (0x1F0).
+Description: (Read) Returns how many resources the trace unit supports (0x1F0).
The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/trcidr/trcidr5
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns how many resources the trace unit supports (0x1F4).
+Description: (Read) Returns how many resources the trace unit supports (0x1F4).
The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/trcidr/trcidr8
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the maximum speculation depth of the instruction
+Description: (Read) Returns the maximum speculation depth of the instruction
trace stream. (0x180). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/trcidr/trcidr9
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the number of P0 right-hand keys that the trace unit
+Description: (Read) Returns the number of P0 right-hand keys that the trace unit
can use (0x184). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/trcidr/trcidr10
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the number of P1 right-hand keys that the trace unit
+Description: (Read) Returns the number of P1 right-hand keys that the trace unit
can use (0x188). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/trcidr/trcidr11
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the number of special P1 right-hand keys that the
+Description: (Read) Returns the number of special P1 right-hand keys that the
trace unit can use (0x18C). The value is taken directly from
the HW.
@@ -497,7 +497,7 @@
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the number of conditional P1 right-hand keys that
+Description: (Read) Returns the number of conditional P1 right-hand keys that
the trace unit can use (0x190). The value is taken directly
from the HW.
@@ -505,6 +505,6 @@
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the number of special conditional P1 right-hand keys
+Description: (Read) Returns the number of special conditional P1 right-hand keys
that the trace unit can use (0x194). The value is taken
directly from the HW.
diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-stm b/Documentation/ABI/testing/sysfs-bus-coresight-devices-stm
index 1dffabe..53e1f48 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-stm
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-stm
@@ -42,7 +42,7 @@
Date: April 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) List various control and status registers. The specific
+Description: (Read) List various control and status registers. The specific
layout and content is driver specific.
What: /sys/bus/coresight/devices/<memory_map>.stm/traceid
diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc
index ab49b9a..6aa5272 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc
@@ -11,21 +11,21 @@
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Defines the size, in 32-bit words, of the local RAM buffer.
+Description: (Read) Defines the size, in 32-bit words, of the local RAM buffer.
The value is read directly from HW register RSZ, 0x004.
What: /sys/bus/coresight/devices/<memory_map>.tmc/mgmt/sts
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the TMC status register. The value
+Description: (Read) Shows the value held by the TMC status register. The value
is read directly from HW register STS, 0x00C.
What: /sys/bus/coresight/devices/<memory_map>.tmc/mgmt/rrp
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the TMC RAM Read Pointer register
+Description: (Read) Shows the value held by the TMC RAM Read Pointer register
that is used to read entries from the Trace RAM over the APB
interface. The value is read directly from HW register RRP,
0x014.
@@ -34,7 +34,7 @@
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the TMC RAM Write Pointer register
+Description: (Read) Shows the value held by the TMC RAM Write Pointer register
that is used to sets the write pointer to write entries from
the CoreSight bus into the Trace RAM. The value is read directly
from HW register RWP, 0x018.
@@ -43,21 +43,21 @@
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Similar to "trigger_cntr" above except that this value is
+Description: (Read) Similar to "trigger_cntr" above except that this value is
read directly from HW register TRG, 0x01C.
What: /sys/bus/coresight/devices/<memory_map>.tmc/mgmt/ctl
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the TMC Control register. The value
+Description: (Read) Shows the value held by the TMC Control register. The value
is read directly from HW register CTL, 0x020.
What: /sys/bus/coresight/devices/<memory_map>.tmc/mgmt/ffsr
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the TMC Formatter and Flush Status
+Description: (Read) Shows the value held by the TMC Formatter and Flush Status
register. The value is read directly from HW register FFSR,
0x300.
@@ -65,7 +65,7 @@
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the TMC Formatter and Flush Control
+Description: (Read) Shows the value held by the TMC Formatter and Flush Control
register. The value is read directly from HW register FFCR,
0x304.
@@ -73,7 +73,7 @@
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the TMC Mode register, which
+Description: (Read) Shows the value held by the TMC Mode register, which
indicate the mode the device has been configured to enact. The
The value is read directly from the MODE register, 0x028.
@@ -81,7 +81,7 @@
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the capabilities of the Coresight TMC.
+Description: (Read) Indicates the capabilities of the Coresight TMC.
The value is read directly from the DEVID register, 0xFC8,
What: /sys/bus/coresight/devices/<memory_map>.tmc/buffer_size
diff --git a/Documentation/ABI/testing/sysfs-bus-css b/Documentation/ABI/testing/sysfs-bus-css
index 966f850..12a733f 100644
--- a/Documentation/ABI/testing/sysfs-bus-css
+++ b/Documentation/ABI/testing/sysfs-bus-css
@@ -20,6 +20,7 @@
Description: Contains the ids of the channel paths used by this
subchannel, as reported by the channel subsystem
during subchannel recognition.
+
Note: This is an I/O-subchannel specific attribute.
Users: s390-tools, HAL
@@ -31,6 +32,7 @@
channel subsystem when last queried by the common I/O
layer (this implies that this attribute is not necessarily
in sync with the values current in the channel subsystem).
+
Note: This is an I/O-subchannel specific attribute.
Users: s390-tools, HAL
@@ -53,6 +55,7 @@
opt-out of driver binding using a driver_override name such as
"none". Only a single driver may be specified in the override,
there is no support for parsing delimiters.
+
Note that unlike the mechanism of the same name for pci, this
file does not allow to override basic matching rules. I.e.,
the driver must still match the subchannel type of the device.
diff --git a/Documentation/ABI/testing/sysfs-bus-dfl b/Documentation/ABI/testing/sysfs-bus-dfl
index 23543be..b0265ab 100644
--- a/Documentation/ABI/testing/sysfs-bus-dfl
+++ b/Documentation/ABI/testing/sysfs-bus-dfl
@@ -4,6 +4,7 @@
Contact: Xu Yilun <yilun.xu@intel.com>
Description: Read-only. It returns type of DFL FIU of the device. Now DFL
supports 2 FIU types, 0 for FME, 1 for PORT.
+
Format: 0x%x
What: /sys/bus/dfl/devices/dfl_dev.X/feature_id
@@ -12,4 +13,5 @@
Contact: Xu Yilun <yilun.xu@intel.com>
Description: Read-only. It returns feature identifier local to its DFL FIU
type.
+
Format: 0x%x
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-dfl_fme b/Documentation/ABI/testing/sysfs-bus-event_source-devices-dfl_fme
index c9278a3..63a32dd 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-dfl_fme
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-dfl_fme
@@ -8,13 +8,13 @@
Each attribute under this group defines a bit range of the
perf_event_attr.config. All supported attributes are listed
- below.
+ below::
event = "config:0-11" - event ID
evtype = "config:12-15" - event type
portid = "config:16-23" - event source
- For example,
+ For example::
fab_mmio_read = "event=0x06,evtype=0x02,portid=0xff"
@@ -40,11 +40,11 @@
All supported performance monitoring events are listed below.
- Basic events (evtype=0x00)
+ Basic events (evtype=0x00)::
clock = "event=0x00,evtype=0x00,portid=0xff"
- Cache events (evtype=0x01)
+ Cache events (evtype=0x01)::
cache_read_hit = "event=0x00,evtype=0x01,portid=0xff"
cache_read_miss = "event=0x01,evtype=0x01,portid=0xff"
@@ -59,7 +59,7 @@
cache_rx_req_stall = "event=0x09,evtype=0x01,portid=0xff"
cache_eviction = "event=0x0a,evtype=0x01,portid=0xff"
- Fabric events (evtype=0x02)
+ Fabric events (evtype=0x02)::
fab_pcie0_read = "event=0x00,evtype=0x02,portid=0xff"
fab_pcie0_write = "event=0x01,evtype=0x02,portid=0xff"
@@ -78,7 +78,7 @@
fab_port_mmio_read = "event=0x06,evtype=0x02,portid=?"
fab_port_mmio_write = "event=0x07,evtype=0x02,portid=?"
- VTD events (evtype=0x03)
+ VTD events (evtype=0x03)::
vtd_port_read_transaction = "event=0x00,evtype=0x03,portid=?"
vtd_port_write_transaction = "event=0x01,evtype=0x03,portid=?"
@@ -88,7 +88,7 @@
vtd_port_devtlb_2m_fill = "event=0x05,evtype=0x03,portid=?"
vtd_port_devtlb_1g_fill = "event=0x06,evtype=0x03,portid=?"
- VTD SIP events (evtype=0x04)
+ VTD SIP events (evtype=0x04)::
vtd_sip_iotlb_4k_hit = "event=0x00,evtype=0x04,portid=0xff"
vtd_sip_iotlb_2m_hit = "event=0x01,evtype=0x04,portid=0xff"
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-format b/Documentation/ABI/testing/sysfs-bus-event_source-devices-format
index 5bb793e..df7ccc1 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-format
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-format
@@ -10,7 +10,8 @@
name/value pairs.
Userspace must be prepared for the possibility that attributes
- define overlapping bit ranges. For example:
+ define overlapping bit ranges. For example::
+
attr1 = 'config:0-23'
attr2 = 'config:0-7'
attr3 = 'config:12-35'
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
index 2273627..de390a0 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
@@ -7,7 +7,7 @@
Each attribute under this group defines a bit range of the
perf_event_attr.config. All supported attributes are listed
- below.
+ below::
chip = "config:16-31"
core = "config:16-31"
@@ -16,9 +16,9 @@
offset = "config:32-63"
vcpu = "config:16-31"
- For example,
+ For example::
- PM_PB_CYC = "domain=1,offset=0x80,chip=?,lpar=0x0"
+ PM_PB_CYC = "domain=1,offset=0x80,chip=?,lpar=0x0"
In this event, '?' after chip specifies that
this value will be provided by user while running this event.
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci
index 6a023b4..12e2bf9 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci
@@ -7,7 +7,7 @@
Each attribute under this group defines a bit range of the
perf_event_attr.config. All supported attributes are listed
- below.
+ below::
counter_info_version = "config:16-23"
length = "config:24-31"
@@ -20,9 +20,9 @@
secondary_index = "config:0-15"
starting_index = "config:32-63"
- For example,
+ For example::
- processor_core_utilization_instructions_completed = "request=0x94,
+ processor_core_utilization_instructions_completed = "request=0x94,
phys_processor_idx=?,counter_info_version=0x8,
length=8,offset=0x18"
@@ -36,6 +36,7 @@
'0' if the hypervisor is configured to forbid access to event
counters being accumulated by other guests and to physical
domain event counters.
+
'1' if that access is allowed.
What: /sys/bus/event_source/devices/hv_gpci/interface/ga
diff --git a/Documentation/ABI/testing/sysfs-bus-fcoe b/Documentation/ABI/testing/sysfs-bus-fcoe
index 657df13..8fe787c 100644
--- a/Documentation/ABI/testing/sysfs-bus-fcoe
+++ b/Documentation/ABI/testing/sysfs-bus-fcoe
@@ -3,16 +3,19 @@
KernelVersion: TBD
Contact: Robert Love <robert.w.love@intel.com>, devel@open-fcoe.org
Description: The FCoE bus. Attributes in this directory are control interfaces.
+
Attributes:
- ctlr_create: 'FCoE Controller' instance creation interface. Writing an
+ ctlr_create:
+ 'FCoE Controller' instance creation interface. Writing an
<ifname> to this file will allocate and populate sysfs with a
fcoe_ctlr_device (ctlr_X). The user can then configure any
per-port settings and finally write to the fcoe_ctlr_device's
'start' attribute to begin the kernel's discovery and login
process.
- ctlr_destroy: 'FCoE Controller' instance removal interface. Writing a
+ ctlr_destroy:
+ 'FCoE Controller' instance removal interface. Writing a
fcoe_ctlr_device's sysfs name to this file will log the
fcoe_ctlr_device out of the fabric or otherwise connected
FCoE devices. It will also free all kernel memory allocated
@@ -32,11 +35,13 @@
Attributes:
- fcf_dev_loss_tmo: Device loss timeout period (see below). Changing
+ fcf_dev_loss_tmo:
+ Device loss timeout period (see below). Changing
this value will change the dev_loss_tmo for all
FCFs discovered by this controller.
- mode: Display or change the FCoE Controller's mode. Possible
+ mode:
+ Display or change the FCoE Controller's mode. Possible
modes are 'Fabric' and 'VN2VN'. If a FCoE Controller
is started in 'Fabric' mode then FIP FCF discovery is
initiated and ultimately a fabric login is attempted.
@@ -44,23 +49,30 @@
FIP VN2VN discovery and login is performed. A FCoE
Controller only supports one mode at a time.
- enabled: Whether an FCoE controller is enabled or disabled.
+ enabled:
+ Whether an FCoE controller is enabled or disabled.
0 if disabled, 1 if enabled. Writing either 0 or 1
to this file will enable or disable the FCoE controller.
- lesb/link_fail: Link Error Status Block (LESB) link failure count.
+ lesb/link_fail:
+ Link Error Status Block (LESB) link failure count.
- lesb/vlink_fail: Link Error Status Block (LESB) virtual link
+ lesb/vlink_fail:
+ Link Error Status Block (LESB) virtual link
failure count.
- lesb/miss_fka: Link Error Status Block (LESB) missed FCoE
+ lesb/miss_fka:
+ Link Error Status Block (LESB) missed FCoE
Initialization Protocol (FIP) Keep-Alives (FKA).
- lesb/symb_err: Link Error Status Block (LESB) symbolic error count.
+ lesb/symb_err:
+ Link Error Status Block (LESB) symbolic error count.
- lesb/err_block: Link Error Status Block (LESB) block error count.
+ lesb/err_block:
+ Link Error Status Block (LESB) block error count.
- lesb/fcs_error: Link Error Status Block (LESB) Fibre Channel
+ lesb/fcs_error:
+ Link Error Status Block (LESB) Fibre Channel
Services error count.
Notes: ctlr_X (global increment starting at 0)
@@ -75,31 +87,41 @@
Fibre Channel frames into a FC fabric. It can also take
outbound FC frames and pack them in Ethernet packets to
be sent to their destination on the Ethernet segment.
+
Attributes:
- fabric_name: Identifies the fabric that the FCF services.
+ fabric_name:
+ Identifies the fabric that the FCF services.
- switch_name: Identifies the FCF.
+ switch_name:
+ Identifies the FCF.
- priority: The switch's priority amongst other FCFs on the same
+ priority:
+ The switch's priority amongst other FCFs on the same
fabric.
- selected: 1 indicates that the switch has been selected for use;
+ selected:
+ 1 indicates that the switch has been selected for use;
0 indicates that the switch will not be used.
- fc_map: The Fibre Channel MAP
+ fc_map:
+ The Fibre Channel MAP
- vfid: The Virtual Fabric ID
+ vfid:
+ The Virtual Fabric ID
- mac: The FCF's MAC address
+ mac:
+ The FCF's MAC address
- fka_period: The FIP Keep-Alive period
+ fka_period:
+ The FIP Keep-Alive period
fabric_state: The internal kernel state
- "Unknown" - Initialization value
- "Disconnected" - No link to the FCF/fabric
- "Connected" - Host is connected to the FCF
- "Deleted" - FCF is being removed from the system
+
+ - "Unknown" - Initialization value
+ - "Disconnected" - No link to the FCF/fabric
+ - "Connected" - Host is connected to the FCF
+ - "Deleted" - FCF is being removed from the system
dev_loss_tmo: The device loss timeout period for this FCF.
diff --git a/Documentation/ABI/testing/sysfs-bus-fsl-mc b/Documentation/ABI/testing/sysfs-bus-fsl-mc
index 80256b8..bf3c6af6a 100644
--- a/Documentation/ABI/testing/sysfs-bus-fsl-mc
+++ b/Documentation/ABI/testing/sysfs-bus-fsl-mc
@@ -6,8 +6,10 @@
the driver to attempt to bind to the device found at
this location. The format for the location is Object.Id
and is the same as found in /sys/bus/fsl-mc/devices/.
- For example:
- # echo dpni.2 > /sys/bus/fsl-mc/drivers/fsl_dpaa2_eth/bind
+
+ For example::
+
+ # echo dpni.2 > /sys/bus/fsl-mc/drivers/fsl_dpaa2_eth/bind
What: /sys/bus/fsl-mc/drivers/.../unbind
Date: December 2016
@@ -17,5 +19,7 @@
driver to attempt to unbind from the device found at
this location. The format for the location is Object.Id
and is the same as found in /sys/bus/fsl-mc/devices/.
- For example:
- # echo dpni.2 > /sys/bus/fsl-mc/drivers/fsl_dpaa2_eth/unbind
+
+ For example::
+
+ # echo dpni.2 > /sys/bus/fsl-mc/drivers/fsl_dpaa2_eth/unbind
diff --git a/Documentation/ABI/testing/sysfs-bus-i2c-devices-fsa9480 b/Documentation/ABI/testing/sysfs-bus-i2c-devices-fsa9480
index 9de269b..42dfc93 100644
--- a/Documentation/ABI/testing/sysfs-bus-i2c-devices-fsa9480
+++ b/Documentation/ABI/testing/sysfs-bus-i2c-devices-fsa9480
@@ -3,19 +3,25 @@
Contact: Minkyu Kang <mk7.kang@samsung.com>
Description:
show what device is attached
- NONE - no device
- USB - USB device is attached
- UART - UART is attached
- CHARGER - Charger is attaced
- JIG - JIG is attached
+
+ ======= ======================
+ NONE no device
+ USB USB device is attached
+ UART UART is attached
+ CHARGER Charger is attaced
+ JIG JIG is attached
+ ======= ======================
What: /sys/bus/i2c/devices/.../switch
Date: February 2011
Contact: Minkyu Kang <mk7.kang@samsung.com>
Description:
show or set the state of manual switch
- VAUDIO - switch to VAUDIO path
- UART - switch to UART path
- AUDIO - switch to AUDIO path
- DHOST - switch to DHOST path
- AUTO - switch automatically by device
+
+ ======= ==============================
+ VAUDIO switch to VAUDIO path
+ UART switch to UART path
+ AUDIO switch to AUDIO path
+ DHOST switch to DHOST path
+ AUTO switch automatically by device
+ ======= ==============================
diff --git a/Documentation/ABI/testing/sysfs-bus-i2c-devices-pca954x b/Documentation/ABI/testing/sysfs-bus-i2c-devices-pca954x
index 0b0de8c..b6c69eb 100644
--- a/Documentation/ABI/testing/sysfs-bus-i2c-devices-pca954x
+++ b/Documentation/ABI/testing/sysfs-bus-i2c-devices-pca954x
@@ -6,15 +6,18 @@
Value that exists only for mux devices that can be
written to control the behaviour of the multiplexer on
idle. Possible values:
- -2 - disconnect on idle, i.e. deselect the last used
- channel, which is useful when there is a device
- with an address that conflicts with another
- device on another mux on the same parent bus.
- -1 - leave the mux as-is, which is the most optimal
- setting in terms of I2C operations and is the
- default mode.
- 0..<nchans> - set the mux to a predetermined channel,
- which is useful if there is one channel that is
- used almost always, and you want to reduce the
- latency for normal operations after rare
- transactions on other channels
+
+ =========== ===============================================
+ -2 disconnect on idle, i.e. deselect the last used
+ channel, which is useful when there is a device
+ with an address that conflicts with another
+ device on another mux on the same parent bus.
+ -1 leave the mux as-is, which is the most optimal
+ setting in terms of I2C operations and is the
+ default mode.
+ 0..<nchans> set the mux to a predetermined channel,
+ which is useful if there is one channel that is
+ used almost always, and you want to reduce the
+ latency for normal operations after rare
+ transactions on other channels
+ =========== ===============================================
diff --git a/Documentation/ABI/testing/sysfs-bus-i3c b/Documentation/ABI/testing/sysfs-bus-i3c
index 2f332ec..1f4a266 100644
--- a/Documentation/ABI/testing/sysfs-bus-i3c
+++ b/Documentation/ABI/testing/sysfs-bus-i3c
@@ -84,6 +84,7 @@
by space. Modes can be "hdr-ddr", "hdr-tsp" and "hdr-tsl".
See the I3C specification for more details about these HDR
modes.
+
This entry describes the HDRCAP of the master controller
driving the bus.
@@ -135,6 +136,7 @@
Expose the HDR (High Data Rate) capabilities of a device.
Returns a list of supported HDR mode, each element is separated
by space. Modes can be "hdr-ddr", "hdr-tsp" and "hdr-tsl".
+
See the I3C specification for more details about these HDR
modes.
diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index a9d51810..df42bed 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -15,6 +15,7 @@
based on hardware generated events (e.g. data ready) or
provided by a separate driver for other hardware (e.g.
periodic timer, GPIO or high resolution timer).
+
Contains trigger type specific elements. These do not
generalize well and hence are not documented in this file.
X is the IIO index of the trigger.
@@ -65,6 +66,7 @@
Description:
When the internal sampling clock can only take a specific set of
frequencies, we can specify the available values with:
+
- a small discrete set of values like "0 2 4 6 8"
- a range with minimum, step and maximum frequencies like
"[min step max]"
@@ -665,6 +667,7 @@
<type>[Y][_name]_<raw|input>_thresh_falling_value may take
different values, but the device can only enable both thresholds
or neither.
+
Note the driver will assume the last p events requested are
to be enabled where p is how many it supports (which may vary
depending on the exact set requested. So if you want to be
@@ -719,6 +722,7 @@
<type>[Y][_name]_<raw|input>_roc_falling_value may take
different values, but the device can only enable both rate of
change thresholds or neither.
+
Note the driver will assume the last p events requested are
to be enabled where p is however many it supports (which may
vary depending on the exact set requested. So if you want to be
@@ -774,9 +778,11 @@
Specifies the value of threshold that the device is comparing
against for the events enabled by
<type>Y[_name]_thresh[_rising|falling]_en.
+
If separate attributes exist for the two directions, but
direction is not specified for this attribute, then a single
threshold value applies to both directions.
+
The raw or input element of the name indicates whether the
value is in raw device units or in processed units (as _raw
and _input do on sysfs direct channel read attributes).
@@ -859,6 +865,7 @@
If separate attributes exist for the two directions, but
direction is not specified for this attribute, then a single
hysteresis value applies to both directions.
+
For falling events the hysteresis is added to the _value attribute for
this event to get the upper threshold for when the event goes back to
normal, for rising events the hysteresis is subtracted from the _value
@@ -905,6 +912,7 @@
Specifies the value of rate of change threshold that the
device is comparing against for the events enabled by
<type>[Y][_name]_roc[_rising|falling]_en.
+
If separate attributes exist for the two directions,
but direction is not specified for this attribute,
then a single threshold value applies to both directions.
@@ -1304,6 +1312,7 @@
Proximity measurement indicating that some
object is near the sensor, usually by observing
reflectivity of infrared or ultrasound emitted.
+
Often these sensors are unit less and as such conversion
to SI units is not possible. Higher proximity measurements
indicate closer objects, and vice versa. Units after
@@ -1449,9 +1458,12 @@
Description:
A single positive integer specifying the maximum number of scan
elements to wait for.
+
Poll will block until the watermark is reached.
+
Blocking read will wait until the minimum between the requested
read amount or the low water mark is available.
+
Non-blocking read will retrieve the available samples from the
buffer even if there are less samples then watermark level. This
allows the application to block on poll with a timeout and read
@@ -1480,11 +1492,13 @@
device settings allows it (e.g. if a trigger is set that samples
data differently that the hardware fifo does then hardware fifo
will not enabled).
+
If the hardware fifo is enabled and the level of the hardware
fifo reaches the hardware fifo watermark level the device will
flush its hardware fifo to the device buffer. Doing a non
blocking read on the device when no samples are present in the
device buffer will also force a flush.
+
When the hardware fifo is enabled there is no need to use a
trigger to use buffer mode since the watermark settings
guarantees that the hardware fifo is flushed to the device
@@ -1522,6 +1536,7 @@
A single positive integer specifying the minimum watermark level
for the hardware fifo of this device. If the device does not
have a hardware fifo this entry is not present.
+
If the user sets buffer/watermark to a value less than this one,
then the hardware watermark will remain unset.
@@ -1532,6 +1547,7 @@
A single positive integer specifying the maximum watermark level
for the hardware fifo of this device. If the device does not
have a hardware fifo this entry is not present.
+
If the user sets buffer/watermark to a value greater than this
one, then the hardware watermark will be capped at this value.
@@ -1543,6 +1559,7 @@
levels for the hardware fifo. This entry is optional and if it
is not present it means that all the values between
hwfifo_watermark_min and hwfifo_watermark_max are supported.
+
If the user sets buffer/watermark to a value greater than
hwfifo_watermak_min but not equal to any of the values in this
list, the driver will chose an appropriate value for the
@@ -1604,7 +1621,8 @@
Contact: linux-iio@vger.kernel.org
Description:
'1' (enable) or '0' (disable) specifying the enable
- of heater function. Same reading values apply
+ of heater function. Same reading values apply.
+
This ABI is especially applicable for humidity sensors
to heatup the device and get rid of any condensation
in some humidity environment
@@ -1627,17 +1645,21 @@
Mounting matrix for IIO sensors. This is a rotation matrix which
informs userspace about sensor chip's placement relative to the
main hardware it is mounted on.
+
Main hardware placement is defined according to the local
reference frame related to the physical quantity the sensor
measures.
+
Given that the rotation matrix is defined in a board specific
way (platform data and / or device-tree), the main hardware
reference frame definition is left to the implementor's choice
(see below for a magnetometer example).
+
Applications should apply this rotation matrix to samples so
that when main hardware reference frame is aligned onto local
reference frame, then sensor chip reference frame is also
perfectly aligned with it.
+
Matrix is a 3x3 unitary matrix and typically looks like
[0, 1, 0; 1, 0, 0; 0, 0, -1]. Identity matrix
[1, 0, 0; 0, 1, 0; 0, 0, 1] means sensor chip and main hardware
@@ -1646,8 +1668,10 @@
For example, a mounting matrix for a magnetometer sensor informs
userspace about sensor chip's ORIENTATION relative to the main
hardware.
+
More specifically, main hardware orientation is defined with
respect to the LOCAL EARTH GEOMAGNETIC REFERENCE FRAME where :
+
* Y is in the ground plane and positive towards magnetic North ;
* X is in the ground plane, perpendicular to the North axis and
positive towards the East ;
@@ -1656,13 +1680,16 @@
An implementor might consider that for a hand-held device, a
'natural' orientation would be 'front facing camera at the top'.
The main hardware reference frame could then be described as :
+
* Y is in the plane of the screen and is positive towards the
top of the screen ;
* X is in the plane of the screen, perpendicular to Y axis, and
positive towards the right hand side of the screen ;
* Z is perpendicular to the screen plane and positive out of the
screen.
+
Another example for a quadrotor UAV might be :
+
* Y is in the plane of the propellers and positive towards the
front-view camera;
* X is in the plane of the propellers, perpendicular to Y axis,
@@ -1704,6 +1731,7 @@
This interface is deprecated; please use the Counter subsystem.
A list of possible counting directions which are:
+
- "up" : counter device is increasing.
- "down": counter device is decreasing.
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-adc-envelope-detector b/Documentation/ABI/testing/sysfs-bus-iio-adc-envelope-detector
index 2071f9b..1c2a07f7 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-adc-envelope-detector
+++ b/Documentation/ABI/testing/sysfs-bus-iio-adc-envelope-detector
@@ -5,7 +5,8 @@
Description:
The DAC is used to find the peak level of an alternating
voltage input signal by a binary search using the output
- of a comparator wired to an interrupt pin. Like so:
+ of a comparator wired to an interrupt pin. Like so::
+
_
| \
input +------>-------|+ \
@@ -19,10 +20,12 @@
| irq|------<-------'
| |
'-------'
+
The boolean invert attribute (0/1) should be set when the
input signal is centered around the maximum value of the
dac instead of zero. The envelope detector will search
from below in this case and will also invert the result.
+
The edge/level of the interrupt is also switched to its
opposite value.
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-adc-hi8435 b/Documentation/ABI/testing/sysfs-bus-iio-adc-hi8435
index f30b4c4..4b01150 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-adc-hi8435
+++ b/Documentation/ABI/testing/sysfs-bus-iio-adc-hi8435
@@ -19,9 +19,11 @@
is separately set for "GND-Open" and "Supply-Open" modes.
Channels 0..31 have common low threshold values, but could have different
sensing_modes.
+
The low voltage threshold range is between 2..21V.
Hysteresis between low and high thresholds can not be lower then 2 and
can not be odd.
+
If falling threshold results hysteresis to odd value then rising
threshold is automatically subtracted by one.
@@ -34,10 +36,13 @@
this value then the threshold rising event is pushed.
Depending on in_voltageY_sensing_mode the high voltage threshold
is separately set for "GND-Open" and "Supply-Open" modes.
+
Channels 0..31 have common high threshold values, but could have different
sensing_modes.
+
The high voltage threshold range is between 3..22V.
Hysteresis between low and high thresholds can not be lower then 2 and
can not be odd.
+
If rising threshold results hysteresis to odd value then falling
threshold is automatically appended by one.
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-adc-stm32 b/Documentation/ABI/testing/sysfs-bus-iio-adc-stm32
index efe4c85..1975c7a 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-adc-stm32
+++ b/Documentation/ABI/testing/sysfs-bus-iio-adc-stm32
@@ -5,10 +5,13 @@
The STM32 ADC can be configured to use external trigger sources
(e.g. timers, pwm or exti gpio). Then, it can be tuned to start
conversions on external trigger by either:
+
- "rising-edge"
- "falling-edge"
- "both-edges".
+
Reading returns current trigger polarity.
+
Writing value before enabling conversions sets trigger polarity.
What: /sys/bus/iio/devices/triggerX/trigger_polarity_available
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-cros-ec b/Documentation/ABI/testing/sysfs-bus-iio-cros-ec
index 6158f83..adf24c4 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-cros-ec
+++ b/Documentation/ABI/testing/sysfs-bus-iio-cros-ec
@@ -4,7 +4,7 @@
Contact: linux-iio@vger.kernel.org
Description:
Writing '1' will perform a FOC (Fast Online Calibration). The
- corresponding calibration offsets can be read from *_calibbias
+ corresponding calibration offsets can be read from `*_calibbias`
entries.
What: /sys/bus/iio/devices/iio:deviceX/location
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-dfsdm-adc-stm32 b/Documentation/ABI/testing/sysfs-bus-iio-dfsdm-adc-stm32
index 0e66ae9..91439d6d 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-dfsdm-adc-stm32
+++ b/Documentation/ABI/testing/sysfs-bus-iio-dfsdm-adc-stm32
@@ -3,14 +3,20 @@
Contact: arnaud.pouliquen@st.com
Description:
For audio purpose only.
+
Used by audio driver to set/get the spi input frequency.
+
This is mandatory if DFSDM is slave on SPI bus, to
provide information on the SPI clock frequency during runtime
Notice that the SPI frequency should be a multiple of sample
frequency to ensure the precision.
- if DFSDM input is SPI master
+
+ if DFSDM input is SPI master:
+
Reading SPI clkout frequency,
error on writing
+
If DFSDM input is SPI Slave:
+
Reading returns value previously set.
Writing value before starting conversions.
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-distance-srf08 b/Documentation/ABI/testing/sysfs-bus-iio-distance-srf08
index a133fd8..40df5c9 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-distance-srf08
+++ b/Documentation/ABI/testing/sysfs-bus-iio-distance-srf08
@@ -15,8 +15,11 @@
first object echoed in meters. Default value is 6.020.
This setting limits the time the driver is waiting for a
echo.
+
Showing the range of available values is represented as the
minimum value, the step and the maximum value, all enclosed
in square brackets.
- Example:
- [0.043 0.043 11.008]
+
+ Example::
+
+ [0.043 0.043 11.008]
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-frequency-ad9523 b/Documentation/ABI/testing/sysfs-bus-iio-frequency-ad9523
index a91aeab..d065cda 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-frequency-ad9523
+++ b/Documentation/ABI/testing/sysfs-bus-iio-frequency-ad9523
@@ -8,7 +8,9 @@
Contact: linux-iio@vger.kernel.org
Description:
Reading returns either '1' or '0'.
+
'1' means that the clock in question is present.
+
'0' means that the clock is missing.
What: /sys/bus/iio/devices/iio:deviceX/pllY_locked
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-frequency-adf4371 b/Documentation/ABI/testing/sysfs-bus-iio-frequency-adf4371
index 302de64..544548e 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-frequency-adf4371
+++ b/Documentation/ABI/testing/sysfs-bus-iio-frequency-adf4371
@@ -27,12 +27,12 @@
KernelVersion:
Contact: linux-iio@vger.kernel.org
Description:
- Reading returns the datasheet name for channel Y:
+ Reading returns the datasheet name for channel Y::
- out_altvoltage0_name: RF8x
- out_altvoltage1_name: RFAUX8x
- out_altvoltage2_name: RF16x
- out_altvoltage3_name: RF32x
+ out_altvoltage0_name: RF8x
+ out_altvoltage1_name: RFAUX8x
+ out_altvoltage2_name: RF16x
+ out_altvoltage3_name: RF32x
What: /sys/bus/iio/devices/iio:deviceX/out_altvoltageY_powerdown
KernelVersion:
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-health-afe440x b/Documentation/ABI/testing/sysfs-bus-iio-health-afe440x
index 6adba90..66b621f 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-health-afe440x
+++ b/Documentation/ABI/testing/sysfs-bus-iio-health-afe440x
@@ -6,10 +6,14 @@
Get measured values from the ADC for these stages. Y is the
specific stage number corresponding to datasheet stage names
as follows:
- 1 -> LED2
- 2 -> ALED2/LED3
- 3 -> LED1
- 4 -> ALED1/LED4
+
+ == ==========
+ 1 LED2
+ 2 ALED2/LED3
+ 3 LED1
+ 4 ALED1/LED4
+ == ==========
+
Note that channels 5 and 6 represent LED2-ALED2 and LED1-ALED1
respectively which simply helper channels containing the
calculated difference in the value of stage 1 - 2 and 3 - 4.
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-light-isl29018 b/Documentation/ABI/testing/sysfs-bus-iio-light-isl29018
index f0ce0a0..220206a 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-light-isl29018
+++ b/Documentation/ABI/testing/sysfs-bus-iio-light-isl29018
@@ -15,5 +15,7 @@
Scheme 0 has wider dynamic range, Scheme 1 proximity detection
is less affected by the ambient IR noise variation.
- 0 Sensing IR from LED and ambient
- 1 Sensing IR from LED with ambient IR rejection
+ == =============================================
+ 0 Sensing IR from LED and ambient
+ 1 Sensing IR from LED with ambient IR rejection
+ == =============================================
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-lptimer-stm32 b/Documentation/ABI/testing/sysfs-bus-iio-lptimer-stm32
index ad2cc63..73498ff 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-lptimer-stm32
+++ b/Documentation/ABI/testing/sysfs-bus-iio-lptimer-stm32
@@ -17,9 +17,11 @@
Contact: fabrice.gasnier@st.com
Description:
Configure the device counter quadrature modes:
+
- non-quadrature:
Encoder IN1 input servers as the count input (up
direction).
+
- quadrature:
Encoder IN1 and IN2 inputs are mixed to get direction
and count.
@@ -35,23 +37,26 @@
Contact: fabrice.gasnier@st.com
Description:
Configure the device encoder/counter active edge:
+
- rising-edge
- falling-edge
- both-edges
In non-quadrature mode, device counts up on active edge.
+
In quadrature mode, encoder counting scenarios are as follows:
- ----------------------------------------------------------------
+
+ +---------+----------+--------------------+--------------------+
| Active | Level on | IN1 signal | IN2 signal |
- | edge | opposite |------------------------------------------
+ | edge | opposite +----------+---------+----------+---------+
| | signal | Rising | Falling | Rising | Falling |
- ----------------------------------------------------------------
- | Rising | High -> | Down | - | Up | - |
- | edge | Low -> | Up | - | Down | - |
- ----------------------------------------------------------------
- | Falling | High -> | - | Up | - | Down |
- | edge | Low -> | - | Down | - | Up |
- ----------------------------------------------------------------
- | Both | High -> | Down | Up | Up | Down |
- | edges | Low -> | Up | Down | Down | Up |
- ----------------------------------------------------------------
+ +---------+----------+----------+---------+----------+---------+
+ | Rising | High -> | Down | - | Up | - |
+ | edge | Low -> | Up | - | Down | - |
+ +---------+----------+----------+---------+----------+---------+
+ | Falling | High -> | - | Up | - | Down |
+ | edge | Low -> | - | Down | - | Up |
+ +---------+----------+----------+---------+----------+---------+
+ | Both | High -> | Down | Up | Up | Down |
+ | edges | Low -> | Up | Down | Down | Up |
+ +---------+----------+----------+---------+----------+---------+
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-magnetometer-hmc5843 b/Documentation/ABI/testing/sysfs-bus-iio-magnetometer-hmc5843
index 6275e9f..13f099e 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-magnetometer-hmc5843
+++ b/Documentation/ABI/testing/sysfs-bus-iio-magnetometer-hmc5843
@@ -5,11 +5,16 @@
Description:
Current configuration and available configurations
for the bias current.
- normal - Normal measurement configurations (default)
- positivebias - Positive bias configuration
- negativebias - Negative bias configuration
- disabled - Only available on HMC5983. Disables magnetic
+
+ ============ ============================================
+ normal Normal measurement configurations (default)
+ positivebias Positive bias configuration
+ negativebias Negative bias configuration
+ disabled Only available on HMC5983. Disables magnetic
sensor and enables temperature sensor.
- Note: The effect of this configuration may vary
- according to the device. For exact documentation
- check the device's datasheet.
+ ============ ============================================
+
+ Note:
+ The effect of this configuration may vary
+ according to the device. For exact documentation
+ check the device's datasheet.
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-temperature-max31856 b/Documentation/ABI/testing/sysfs-bus-iio-temperature-max31856
index 3b3509a..e5ef6d8 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-temperature-max31856
+++ b/Documentation/ABI/testing/sysfs-bus-iio-temperature-max31856
@@ -5,9 +5,12 @@
Open-circuit fault. The detection of open-circuit faults,
such as those caused by broken thermocouple wires.
Reading returns either '1' or '0'.
- '1' = An open circuit such as broken thermocouple wires
- has been detected.
- '0' = No open circuit or broken thermocouple wires are detected
+
+ === =======================================================
+ '1' An open circuit such as broken thermocouple wires
+ has been detected.
+ '0' No open circuit or broken thermocouple wires are detected
+ === =======================================================
What: /sys/bus/iio/devices/iio:deviceX/fault_ovuv
KernelVersion: 5.1
@@ -18,7 +21,11 @@
cables by integrated MOSFETs at the T+ and T- inputs, and the
BIAS output. These MOSFETs turn off when the input voltage is
negative or greater than VDD.
+
Reading returns either '1' or '0'.
- '1' = The input voltage is negative or greater than VDD.
- '0' = The input voltage is positive and less than VDD (normal
- state).
+
+ === =======================================================
+ '1' The input voltage is negative or greater than VDD.
+ '0' The input voltage is positive and less than VDD (normal
+ state).
+ === =======================================================
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 b/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32
index b725923..a10a4de 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32
+++ b/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32
@@ -3,67 +3,85 @@
Contact: benjamin.gaignard@st.com
Description:
Reading returns the list possible master modes which are:
- - "reset" : The UG bit from the TIMx_EGR register is
+
+
+ - "reset"
+ The UG bit from the TIMx_EGR register is
used as trigger output (TRGO).
- - "enable" : The Counter Enable signal CNT_EN is used
+ - "enable"
+ The Counter Enable signal CNT_EN is used
as trigger output.
- - "update" : The update event is selected as trigger output.
+ - "update"
+ The update event is selected as trigger output.
For instance a master timer can then be used
as a prescaler for a slave timer.
- - "compare_pulse" : The trigger output send a positive pulse
- when the CC1IF flag is to be set.
- - "OC1REF" : OC1REF signal is used as trigger output.
- - "OC2REF" : OC2REF signal is used as trigger output.
- - "OC3REF" : OC3REF signal is used as trigger output.
- - "OC4REF" : OC4REF signal is used as trigger output.
+ - "compare_pulse"
+ The trigger output send a positive pulse
+ when the CC1IF flag is to be set.
+ - "OC1REF"
+ OC1REF signal is used as trigger output.
+ - "OC2REF"
+ OC2REF signal is used as trigger output.
+ - "OC3REF"
+ OC3REF signal is used as trigger output.
+ - "OC4REF"
+ OC4REF signal is used as trigger output.
+
Additional modes (on TRGO2 only):
- - "OC5REF" : OC5REF signal is used as trigger output.
- - "OC6REF" : OC6REF signal is used as trigger output.
+
+ - "OC5REF"
+ OC5REF signal is used as trigger output.
+ - "OC6REF"
+ OC6REF signal is used as trigger output.
- "compare_pulse_OC4REF":
- OC4REF rising or falling edges generate pulses.
+ OC4REF rising or falling edges generate pulses.
- "compare_pulse_OC6REF":
- OC6REF rising or falling edges generate pulses.
+ OC6REF rising or falling edges generate pulses.
- "compare_pulse_OC4REF_r_or_OC6REF_r":
- OC4REF or OC6REF rising edges generate pulses.
+ OC4REF or OC6REF rising edges generate pulses.
- "compare_pulse_OC4REF_r_or_OC6REF_f":
- OC4REF rising or OC6REF falling edges generate pulses.
+ OC4REF rising or OC6REF falling edges generate
+ pulses.
- "compare_pulse_OC5REF_r_or_OC6REF_r":
- OC5REF or OC6REF rising edges generate pulses.
+ OC5REF or OC6REF rising edges generate pulses.
- "compare_pulse_OC5REF_r_or_OC6REF_f":
- OC5REF rising or OC6REF falling edges generate pulses.
+ OC5REF rising or OC6REF falling edges generate
+ pulses.
- +-----------+ +-------------+ +---------+
- | Prescaler +-> | Counter | +-> | Master | TRGO(2)
- +-----------+ +--+--------+-+ |-> | Control +-->
- | | || +---------+
- +--v--------+-+ OCxREF || +---------+
- | Chx compare +----------> | Output | ChX
- +-----------+-+ | | Control +-->
- . | | +---------+
- . | | .
- +-----------v-+ OC6REF | .
- | Ch6 compare +---------+>
- +-------------+
+ ::
- Example with: "compare_pulse_OC4REF_r_or_OC6REF_r":
+ +-----------+ +-------------+ +---------+
+ | Prescaler +-> | Counter | +-> | Master | TRGO(2)
+ +-----------+ +--+--------+-+ |-> | Control +-->
+ | | || +---------+
+ +--v--------+-+ OCxREF || +---------+
+ | Chx compare +----------> | Output | ChX
+ +-----------+-+ | | Control +-->
+ . | | +---------+
+ . | | .
+ +-----------v-+ OC6REF | .
+ | Ch6 compare +---------+>
+ +-------------+
- X
- X X
- X . . X
- X . . X
- X . . X
- count X . . . . X
- . . . .
- . . . .
- +---------------+
- OC4REF | . . |
- +-+ . . +-+
- . +---+ .
- OC6REF . | | .
- +-------+ +-------+
- +-+ +-+
- TRGO2 | | | |
- +-+ +---+ +---------+
+ Example with: "compare_pulse_OC4REF_r_or_OC6REF_r"::
+
+ X
+ X X
+ X . . X
+ X . . X
+ X . . X
+ count X . . . . X
+ . . . .
+ . . . .
+ +---------------+
+ OC4REF | . . |
+ +-+ . . +-+
+ . +---+ .
+ OC6REF . | | .
+ +-------+ +-------+
+ +-+ +-+
+ TRGO2 | | | |
+ +-+ +---+ +---------+
What: /sys/bus/iio/devices/triggerX/master_mode
KernelVersion: 4.11
@@ -91,6 +109,30 @@
When counting down the counter start from preset value
and fire event when reach 0.
+What: /sys/bus/iio/devices/iio:deviceX/in_count_quadrature_mode_available
+KernelVersion: 4.12
+Contact: benjamin.gaignard@st.com
+Description:
+ Reading returns the list possible quadrature modes.
+
+What: /sys/bus/iio/devices/iio:deviceX/in_count0_quadrature_mode
+KernelVersion: 4.12
+Contact: benjamin.gaignard@st.com
+Description:
+ Configure the device counter quadrature modes:
+
+ channel_A:
+ Encoder A input servers as the count input and B as
+ the UP/DOWN direction control input.
+
+ channel_B:
+ Encoder B input serves as the count input and A as
+ the UP/DOWN direction control input.
+
+ quadrature:
+ Encoder A and B inputs are mixed to get direction
+ and count with a scale of 0.25.
+
What: /sys/bus/iio/devices/iio:deviceX/in_count_enable_mode_available
KernelVersion: 4.12
Contact: benjamin.gaignard@st.com
@@ -104,6 +146,7 @@
Configure the device counter enable modes, in all case
counting direction is set by in_count0_count_direction
attribute and the counter is clocked by the internal clock.
+
always:
Counter is always ON.
diff --git a/Documentation/ABI/testing/sysfs-bus-intel_th-devices-gth b/Documentation/ABI/testing/sysfs-bus-intel_th-devices-gth
index 22d0843..b7b2278 100644
--- a/Documentation/ABI/testing/sysfs-bus-intel_th-devices-gth
+++ b/Documentation/ABI/testing/sysfs-bus-intel_th-devices-gth
@@ -10,10 +10,13 @@
KernelVersion: 4.3
Contact: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Description: (RO) Output port type:
- 0: not present,
- 1: MSU (Memory Storage Unit)
- 2: CTP (Common Trace Port)
- 4: PTI (MIPI PTI).
+
+ == =========================
+ 0 not present,
+ 1 MSU (Memory Storage Unit)
+ 2 CTP (Common Trace Port)
+ 4 PTI (MIPI PTI).
+ == =========================
What: /sys/bus/intel_th/devices/<intel_th_id>-gth/outputs/[0-7]_drop
Date: June 2015
diff --git a/Documentation/ABI/testing/sysfs-bus-intel_th-devices-msc b/Documentation/ABI/testing/sysfs-bus-intel_th-devices-msc
index 7fd2601..a74252e 100644
--- a/Documentation/ABI/testing/sysfs-bus-intel_th-devices-msc
+++ b/Documentation/ABI/testing/sysfs-bus-intel_th-devices-msc
@@ -9,11 +9,13 @@
KernelVersion: 4.3
Contact: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Description: (RW) Configure MSC operating mode:
+
- "single", for contiguous buffer mode (high-order alloc);
- "multi", for multiblock mode;
- "ExI", for DCI handler mode;
- "debug", for debug mode;
- any of the currently loaded buffer sinks.
+
If operating mode changes, existing buffer is deallocated,
provided there are no active users and tracing is not enabled,
otherwise the write will fail.
@@ -23,10 +25,12 @@
KernelVersion: 4.3
Contact: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Description: (RW) Configure MSC buffer size for "single" or "multi" modes.
+
In single mode, this is a single number of pages, has to be
power of 2. In multiblock mode, this is a comma-separated list
of numbers of pages for each window to be allocated. Number of
windows is not limited.
+
Writing to this file deallocates existing buffer (provided
there are no active users and tracing is not enabled) and then
allocates a new one.
diff --git a/Documentation/ABI/testing/sysfs-bus-most b/Documentation/ABI/testing/sysfs-bus-most
index ec0a603..38cc03e 100644
--- a/Documentation/ABI/testing/sysfs-bus-most
+++ b/Documentation/ABI/testing/sysfs-bus-most
@@ -235,7 +235,8 @@
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is to read back the configured direction of the channel.
- The following strings will be accepted:
+ The following strings will be accepted::
+
'tx',
'rx'
Users:
@@ -246,7 +247,8 @@
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is to read back the configured data type of the channel.
- The following strings will be accepted:
+ The following strings will be accepted::
+
'control',
'async',
'sync',
diff --git a/Documentation/ABI/testing/sysfs-bus-moxtet-devices b/Documentation/ABI/testing/sysfs-bus-moxtet-devices
index 3559585..4a6d61b 100644
--- a/Documentation/ABI/testing/sysfs-bus-moxtet-devices
+++ b/Documentation/ABI/testing/sysfs-bus-moxtet-devices
@@ -2,16 +2,16 @@
Date: March 2019
KernelVersion: 5.3
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) Moxtet module description. Format: string
+Description: (Read) Moxtet module description. Format: string
What: /sys/bus/moxtet/devices/moxtet-<name>.<addr>/module_id
Date: March 2019
KernelVersion: 5.3
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) Moxtet module ID. Format: %x
+Description: (Read) Moxtet module ID. Format: %x
What: /sys/bus/moxtet/devices/moxtet-<name>.<addr>/module_name
Date: March 2019
KernelVersion: 5.3
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) Moxtet module name. Format: string
+Description: (Read) Moxtet module name. Format: string
diff --git a/Documentation/ABI/testing/sysfs-bus-nfit b/Documentation/ABI/testing/sysfs-bus-nfit
index e4f76e7..63ef0b9 100644
--- a/Documentation/ABI/testing/sysfs-bus-nfit
+++ b/Documentation/ABI/testing/sysfs-bus-nfit
@@ -1,4 +1,4 @@
-For all of the nmem device attributes under nfit/*, see the 'NVDIMM Firmware
+For all of the nmem device attributes under ``nfit/*``, see the 'NVDIMM Firmware
Interface Table (NFIT)' section in the ACPI specification
(http://www.uefi.org/specifications) for more details.
diff --git a/Documentation/ABI/testing/sysfs-bus-nvdimm b/Documentation/ABI/testing/sysfs-bus-nvdimm
index d643802..bff84a1 100644
--- a/Documentation/ABI/testing/sysfs-bus-nvdimm
+++ b/Documentation/ABI/testing/sysfs-bus-nvdimm
@@ -1,2 +1,8 @@
+What: nvdimm
+Date: July 2020
+KernelVersion: 5.8
+Contact: Dan Williams <dan.j.williams@intel.com>
+Description:
+
The libnvdimm sub-system implements a common sysfs interface for
platform nvdimm resources. See Documentation/driver-api/nvdimm/.
diff --git a/Documentation/ABI/testing/sysfs-bus-papr-pmem b/Documentation/ABI/testing/sysfs-bus-papr-pmem
index c1a6727..8316c33 100644
--- a/Documentation/ABI/testing/sysfs-bus-papr-pmem
+++ b/Documentation/ABI/testing/sysfs-bus-papr-pmem
@@ -11,19 +11,26 @@
at 'Documentation/powerpc/papr_hcalls.rst' . Below are
the flags reported in this sysfs file:
- * "not_armed" : Indicates that NVDIMM contents will not
+ * "not_armed"
+ Indicates that NVDIMM contents will not
survive a power cycle.
- * "flush_fail" : Indicates that NVDIMM contents
+ * "flush_fail"
+ Indicates that NVDIMM contents
couldn't be flushed during last
shut-down event.
- * "restore_fail": Indicates that NVDIMM contents
+ * "restore_fail"
+ Indicates that NVDIMM contents
couldn't be restored during NVDIMM
initialization.
- * "encrypted" : NVDIMM contents are encrypted.
- * "smart_notify": There is health event for the NVDIMM.
- * "scrubbed" : Indicating that contents of the
+ * "encrypted"
+ NVDIMM contents are encrypted.
+ * "smart_notify"
+ There is health event for the NVDIMM.
+ * "scrubbed"
+ Indicating that contents of the
NVDIMM have been scrubbed.
- * "locked" : Indicating that NVDIMM contents cant
+ * "locked"
+ Indicating that NVDIMM contents cant
be modified until next power cycle.
What: /sys/bus/nd/devices/nmemX/papr/perf_stats
@@ -51,4 +58,4 @@
* "MedWDur " : Media Write Duration
* "CchRHCnt" : Cache Read Hit Count
* "CchWHCnt" : Cache Write Hit Count
- * "FastWCnt" : Fast Write Count
\ No newline at end of file
+ * "FastWCnt" : Fast Write Count
diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci
index 450296c..77ad9ec 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci
+++ b/Documentation/ABI/testing/sysfs-bus-pci
@@ -7,8 +7,10 @@
this location. This is useful for overriding default
bindings. The format for the location is: DDDD:BB:DD.F.
That is Domain:Bus:Device.Function and is the same as
- found in /sys/bus/pci/devices/. For example:
- # echo 0000:00:19.0 > /sys/bus/pci/drivers/foo/bind
+ found in /sys/bus/pci/devices/. For example::
+
+ # echo 0000:00:19.0 > /sys/bus/pci/drivers/foo/bind
+
(Note: kernels before 2.6.28 may require echo -n).
What: /sys/bus/pci/drivers/.../unbind
@@ -20,8 +22,10 @@
this location. This may be useful when overriding default
bindings. The format for the location is: DDDD:BB:DD.F.
That is Domain:Bus:Device.Function and is the same as
- found in /sys/bus/pci/devices/. For example:
- # echo 0000:00:19.0 > /sys/bus/pci/drivers/foo/unbind
+ found in /sys/bus/pci/devices/. For example::
+
+ # echo 0000:00:19.0 > /sys/bus/pci/drivers/foo/unbind
+
(Note: kernels before 2.6.28 may require echo -n).
What: /sys/bus/pci/drivers/.../new_id
@@ -38,8 +42,9 @@
Class, Class Mask, and Private Driver Data. The Vendor ID
and Device ID fields are required, the rest are optional.
Upon successfully adding an ID, the driver will probe
- for the device and attempt to bind to it. For example:
- # echo "8086 10f5" > /sys/bus/pci/drivers/foo/new_id
+ for the device and attempt to bind to it. For example::
+
+ # echo "8086 10f5" > /sys/bus/pci/drivers/foo/new_id
What: /sys/bus/pci/drivers/.../remove_id
Date: February 2009
@@ -54,8 +59,9 @@
required, the rest are optional. After successfully
removing an ID, the driver will no longer support the
device. This is useful to ensure auto probing won't
- match the driver to the device. For example:
- # echo "8086 10f5" > /sys/bus/pci/drivers/foo/remove_id
+ match the driver to the device. For example::
+
+ # echo "8086 10f5" > /sys/bus/pci/drivers/foo/remove_id
What: /sys/bus/pci/rescan
Date: January 2009
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
index 3c9a8c4..860db53 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
+++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
@@ -1,6 +1,6 @@
-==========================
PCIe Device AER statistics
-==========================
+--------------------------
+
These attributes show up under all the devices that are AER capable. These
statistical counters indicate the errors "as seen/reported by the device".
Note that this may mean that if an endpoint is causing problems, the AER
@@ -17,19 +17,18 @@
PCI device using ERR_COR. Note that since multiple errors may
be reported using a single ERR_COR message, thus
TOTAL_ERR_COR at the end of the file may not match the actual
- total of all the errors in the file. Sample output:
--------------------------------------------------------------------------
-localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_correctable
-Receiver Error 2
-Bad TLP 0
-Bad DLLP 0
-RELAY_NUM Rollover 0
-Replay Timer Timeout 0
-Advisory Non-Fatal 0
-Corrected Internal Error 0
-Header Log Overflow 0
-TOTAL_ERR_COR 2
--------------------------------------------------------------------------
+ total of all the errors in the file. Sample output::
+
+ localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_correctable
+ Receiver Error 2
+ Bad TLP 0
+ Bad DLLP 0
+ RELAY_NUM Rollover 0
+ Replay Timer Timeout 0
+ Advisory Non-Fatal 0
+ Corrected Internal Error 0
+ Header Log Overflow 0
+ TOTAL_ERR_COR 2
What: /sys/bus/pci/devices/<dev>/aer_dev_fatal
Date: July 2018
@@ -39,28 +38,27 @@
PCI device using ERR_FATAL. Note that since multiple errors may
be reported using a single ERR_FATAL message, thus
TOTAL_ERR_FATAL at the end of the file may not match the actual
- total of all the errors in the file. Sample output:
--------------------------------------------------------------------------
-localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_fatal
-Undefined 0
-Data Link Protocol 0
-Surprise Down Error 0
-Poisoned TLP 0
-Flow Control Protocol 0
-Completion Timeout 0
-Completer Abort 0
-Unexpected Completion 0
-Receiver Overflow 0
-Malformed TLP 0
-ECRC 0
-Unsupported Request 0
-ACS Violation 0
-Uncorrectable Internal Error 0
-MC Blocked TLP 0
-AtomicOp Egress Blocked 0
-TLP Prefix Blocked Error 0
-TOTAL_ERR_FATAL 0
--------------------------------------------------------------------------
+ total of all the errors in the file. Sample output::
+
+ localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_fatal
+ Undefined 0
+ Data Link Protocol 0
+ Surprise Down Error 0
+ Poisoned TLP 0
+ Flow Control Protocol 0
+ Completion Timeout 0
+ Completer Abort 0
+ Unexpected Completion 0
+ Receiver Overflow 0
+ Malformed TLP 0
+ ECRC 0
+ Unsupported Request 0
+ ACS Violation 0
+ Uncorrectable Internal Error 0
+ MC Blocked TLP 0
+ AtomicOp Egress Blocked 0
+ TLP Prefix Blocked Error 0
+ TOTAL_ERR_FATAL 0
What: /sys/bus/pci/devices/<dev>/aer_dev_nonfatal
Date: July 2018
@@ -70,32 +68,31 @@
PCI device using ERR_NONFATAL. Note that since multiple errors
may be reported using a single ERR_FATAL message, thus
TOTAL_ERR_NONFATAL at the end of the file may not match the
- actual total of all the errors in the file. Sample output:
--------------------------------------------------------------------------
-localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_nonfatal
-Undefined 0
-Data Link Protocol 0
-Surprise Down Error 0
-Poisoned TLP 0
-Flow Control Protocol 0
-Completion Timeout 0
-Completer Abort 0
-Unexpected Completion 0
-Receiver Overflow 0
-Malformed TLP 0
-ECRC 0
-Unsupported Request 0
-ACS Violation 0
-Uncorrectable Internal Error 0
-MC Blocked TLP 0
-AtomicOp Egress Blocked 0
-TLP Prefix Blocked Error 0
-TOTAL_ERR_NONFATAL 0
--------------------------------------------------------------------------
+ actual total of all the errors in the file. Sample output::
-============================
+ localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_nonfatal
+ Undefined 0
+ Data Link Protocol 0
+ Surprise Down Error 0
+ Poisoned TLP 0
+ Flow Control Protocol 0
+ Completion Timeout 0
+ Completer Abort 0
+ Unexpected Completion 0
+ Receiver Overflow 0
+ Malformed TLP 0
+ ECRC 0
+ Unsupported Request 0
+ ACS Violation 0
+ Uncorrectable Internal Error 0
+ MC Blocked TLP 0
+ AtomicOp Egress Blocked 0
+ TLP Prefix Blocked Error 0
+ TOTAL_ERR_NONFATAL 0
+
PCIe Rootport AER statistics
-============================
+----------------------------
+
These attributes show up under only the rootports (or root complex event
collectors) that are AER capable. These indicate the number of error messages as
"reported to" the rootport. Please note that the rootports also transmit
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-catpt b/Documentation/ABI/testing/sysfs-bus-pci-devices-catpt
index 8a200f4..f85db86 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci-devices-catpt
+++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-catpt
@@ -4,6 +4,7 @@
Description:
Version of AudioDSP firmware ASoC catpt driver is
communicating with.
+
Format: %d.%d.%d.%d, type:major:minor:build.
What: /sys/devices/pci0000:00/<dev>/fw_info
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-drivers-ehci_hcd b/Documentation/ABI/testing/sysfs-bus-pci-drivers-ehci_hcd
index 60c60fa..c90d97a 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci-drivers-ehci_hcd
+++ b/Documentation/ABI/testing/sysfs-bus-pci-drivers-ehci_hcd
@@ -21,11 +21,11 @@
number returns the port to normal operation.
For example: To force the high-speed device attached to
- port 4 on bus 2 to run at full speed:
+ port 4 on bus 2 to run at full speed::
echo 4 >/sys/bus/usb/devices/usb2/../companion
- To return the port to high-speed operation:
+ To return the port to high-speed operation::
echo -4 >/sys/bus/usb/devices/usb2/../companion
diff --git a/Documentation/ABI/testing/sysfs-bus-rapidio b/Documentation/ABI/testing/sysfs-bus-rapidio
index 13208b2..634ea20 100644
--- a/Documentation/ABI/testing/sysfs-bus-rapidio
+++ b/Documentation/ABI/testing/sysfs-bus-rapidio
@@ -4,24 +4,27 @@
an individual subdirectory with the following name format of
device_name "nn:d:iiii", where:
- nn - two-digit hexadecimal ID of RapidIO network where the
+ ==== ========================================================
+ nn two-digit hexadecimal ID of RapidIO network where the
device resides
- d - device type: 'e' - for endpoint or 's' - for switch
- iiii - four-digit device destID for endpoints, or switchID for
+ d device type: 'e' - for endpoint or 's' - for switch
+ iiii four-digit device destID for endpoints, or switchID for
switches
+ ==== ========================================================
For example, below is a list of device directories that
represents a typical RapidIO network with one switch, one host,
and two agent endpoints, as it is seen by the enumerating host
- (with destID = 1):
+ (with destID = 1)::
- /sys/bus/rapidio/devices/00:e:0000
- /sys/bus/rapidio/devices/00:e:0002
- /sys/bus/rapidio/devices/00:s:0001
+ /sys/bus/rapidio/devices/00:e:0000
+ /sys/bus/rapidio/devices/00:e:0002
+ /sys/bus/rapidio/devices/00:s:0001
- NOTE: An enumerating or discovering endpoint does not create a
- sysfs entry for itself, this is why an endpoint with destID=1 is
- not shown in the list.
+ NOTE:
+ An enumerating or discovering endpoint does not create a
+ sysfs entry for itself, this is why an endpoint with destID=1
+ is not shown in the list.
Attributes Common for All RapidIO Devices
-----------------------------------------
diff --git a/Documentation/ABI/testing/sysfs-bus-rbd b/Documentation/ABI/testing/sysfs-bus-rbd
index cc30bee..417a2fe 100644
--- a/Documentation/ABI/testing/sysfs-bus-rbd
+++ b/Documentation/ABI/testing/sysfs-bus-rbd
@@ -7,6 +7,8 @@
Usage: <mon ip addr> <options> <pool name> <rbd image name> [<snap name>]
+ Example::
+
$ echo "192.168.0.1 name=admin rbd foo" > /sys/bus/rbd/add
The snapshot name can be "-" or omitted to map the image
@@ -23,6 +25,8 @@
Usage: <dev-id> [force]
+ Example::
+
$ echo 2 > /sys/bus/rbd/remove
Optional "force" argument which when passed will wait for
@@ -80,26 +84,29 @@
KernelVersion: v2.6.37
Contact: Sage Weil <sage@newdream.net>
Description:
- size: (RO) The size (in bytes) of the mapped block
+
+ ============== ================================================
+ size (RO) The size (in bytes) of the mapped block
device.
- major: (RO) The block device major number.
+ major (RO) The block device major number.
- client_id: (RO) The ceph unique client id that was assigned
+ client_id (RO) The ceph unique client id that was assigned
for this specific session.
- pool: (RO) The name of the storage pool where this rbd
+ pool (RO) The name of the storage pool where this rbd
image resides. An rbd image name is unique
within its pool.
- name: (RO) The name of the rbd image.
+ name (RO) The name of the rbd image.
- refresh: (WO) Writing to this file will reread the image
+ refresh (WO) Writing to this file will reread the image
header data and set all relevant data structures
accordingly.
- current_snap: (RO) The current snapshot for which the device
+ current_snap (RO) The current snapshot for which the device
is mapped.
+ ============== ================================================
What: /sys/bus/rbd/devices/<dev-id>/pool_id
@@ -117,11 +124,13 @@
KernelVersion: v3.7
Contact: Sage Weil <sage@newdream.net>
Description:
- image_id: (RO) The unique id for the rbd image. (For rbd
+ ========= ===============================================
+ image_id (RO) The unique id for the rbd image. (For rbd
image format 1 this is empty.)
- features: (RO) A hexadecimal encoding of the feature bits
+ features (RO) A hexadecimal encoding of the feature bits
for this image.
+ ========= ===============================================
What: /sys/bus/rbd/devices/<dev-id>/parent
@@ -149,14 +158,16 @@
KernelVersion: v4.9
Contact: Sage Weil <sage@newdream.net>
Description:
- snap_id: (RO) The current snapshot's id.
+ ============ ================================================
+ snap_id (RO) The current snapshot's id.
- config_info: (RO) The string written into
+ config_info (RO) The string written into
/sys/bus/rbd/add{,_single_major}.
- cluster_fsid: (RO) The ceph cluster UUID.
+ cluster_fsid (RO) The ceph cluster UUID.
- client_addr: (RO) The ceph unique client
+ client_addr (RO) The ceph unique client
entity_addr_t (address + nonce). The format is
<address>:<port>/<nonce>: '1.2.3.4:1234/5678' or
'[1:2:3:4:5:6:7:8]:1234/5678'.
+ ============ ================================================
diff --git a/Documentation/ABI/testing/sysfs-bus-siox b/Documentation/ABI/testing/sysfs-bus-siox
index c2a403f..50e8023 100644
--- a/Documentation/ABI/testing/sysfs-bus-siox
+++ b/Documentation/ABI/testing/sysfs-bus-siox
@@ -8,6 +8,7 @@
When the file contains a "1" the bus is operated and periodically
does a push-pull cycle to write and read data from the
connected devices.
+
When writing a "0" or "1" the bus moves to the described state.
What: /sys/bus/siox/devices/siox-X/device_add
@@ -21,8 +22,10 @@
to add a new device dynamically. <type> is the name that is used to match
to a driver (similar to the platform bus). <inbytes> and <outbytes> define
the length of the input and output shift register in bytes respectively.
+
<statustype> defines the 4 bit device type that is check to identify connection
problems.
+
The new device is added to the end of the existing chain.
What: /sys/bus/siox/devices/siox-X/device_remove
diff --git a/Documentation/ABI/testing/sysfs-bus-thunderbolt b/Documentation/ABI/testing/sysfs-bus-thunderbolt
index dd565c3..0b4ab9e 100644
--- a/Documentation/ABI/testing/sysfs-bus-thunderbolt
+++ b/Documentation/ABI/testing/sysfs-bus-thunderbolt
@@ -37,16 +37,18 @@
Description: This attribute holds current Thunderbolt security level
set by the system BIOS. Possible values are:
- none: All devices are automatically authorized
- user: Devices are only authorized based on writing
- appropriate value to the authorized attribute
- secure: Require devices that support secure connect at
- minimum. User needs to authorize each device.
- dponly: Automatically tunnel Display port (and USB). No
- PCIe tunnels are created.
- usbonly: Automatically tunnel USB controller of the
+ ======= ==================================================
+ none All devices are automatically authorized
+ user Devices are only authorized based on writing
+ appropriate value to the authorized attribute
+ secure Require devices that support secure connect at
+ minimum. User needs to authorize each device.
+ dponly Automatically tunnel Display port (and USB). No
+ PCIe tunnels are created.
+ usbonly Automatically tunnel USB controller of the
connected Thunderbolt dock (and Display Port). All
PCIe links downstream of the dock are removed.
+ ======= ==================================================
What: /sys/bus/thunderbolt/devices/.../authorized
Date: Sep 2017
@@ -61,17 +63,23 @@
yet authorized.
Possible values are supported:
- 1: The device will be authorized and connected
+
+ == ===========================================
+ 1 The device will be authorized and connected
+ == ===========================================
When key attribute contains 32 byte hex string the possible
values are:
- 1: The 32 byte hex string is added to the device NVM and
- the device is authorized.
- 2: Send a challenge based on the 32 byte hex string. If the
- challenge response from device is valid, the device is
- authorized. In case of failure errno will be ENOKEY if
- the device did not contain a key at all, and
- EKEYREJECTED if the challenge response did not match.
+
+ == ========================================================
+ 1 The 32 byte hex string is added to the device NVM and
+ the device is authorized.
+ 2 Send a challenge based on the 32 byte hex string. If the
+ challenge response from device is valid, the device is
+ authorized. In case of failure errno will be ENOKEY if
+ the device did not contain a key at all, and
+ EKEYREJECTED if the challenge response did not match.
+ == ========================================================
What: /sys/bus/thunderbolt/devices/.../boot
Date: Jun 2018
@@ -185,10 +193,11 @@
verification fails an error code is returned instead.
This file will accept writing values "1" or "2"
+
- Writing "1" will flush the image to the storage
- area and authenticate the image in one action.
+ area and authenticate the image in one action.
- Writing "2" will run some basic validation on the image
- and flush it to the storage area.
+ and flush it to the storage area.
When read holds status of the last authentication
operation if an error occurred during the process. This
@@ -205,9 +214,11 @@
question. Following directories are already reserved by
the Apple XDomain specification:
- network: IP/ethernet over Thunderbolt
- targetdm: Target disk mode protocol over Thunderbolt
- extdisp: External display mode protocol over Thunderbolt
+ ======== ===============================================
+ network IP/ethernet over Thunderbolt
+ targetdm Target disk mode protocol over Thunderbolt
+ extdisp External display mode protocol over Thunderbolt
+ ======== ===============================================
What: /sys/bus/thunderbolt/devices/<xdomain>.<service>/modalias
Date: Jan 2018
@@ -285,7 +296,8 @@
image when the device is disconnected from the host system.
This file will accept writing values "1" or "2"
+
- Writing "1" will flush the image to the storage
- area and prepare the device for authentication on disconnect.
+ area and prepare the device for authentication on disconnect.
- Writing "2" will run some basic validation on the image
- and flush it to the storage area.
+ and flush it to the storage area.
diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb
index 614d216..bf2c1968 100644
--- a/Documentation/ABI/testing/sysfs-bus-usb
+++ b/Documentation/ABI/testing/sysfs-bus-usb
@@ -9,6 +9,7 @@
by writing INTERFACE to /sys/bus/usb/drivers_probe
This allows to avoid side-effects with drivers
that need multiple interfaces.
+
A deauthorized interface cannot be probed or claimed.
What: /sys/bus/usb/devices/usbX/interface_authorized_default
@@ -72,24 +73,27 @@
table at compile time. The format for the device ID is:
idVendor idProduct bInterfaceClass RefIdVendor RefIdProduct
The vendor ID and device ID fields are required, the
- rest is optional. The Ref* tuple can be used to tell the
+ rest is optional. The `Ref*` tuple can be used to tell the
driver to use the same driver_data for the new device as
it is used for the reference device.
Upon successfully adding an ID, the driver will probe
- for the device and attempt to bind to it. For example:
- # echo "8086 10f5" > /sys/bus/usb/drivers/foo/new_id
+ for the device and attempt to bind to it. For example::
+
+ # echo "8086 10f5" > /sys/bus/usb/drivers/foo/new_id
Here add a new device (0458:7045) using driver_data from
- an already supported device (0458:704c):
- # echo "0458 7045 0 0458 704c" > /sys/bus/usb/drivers/foo/new_id
+ an already supported device (0458:704c)::
+
+ # echo "0458 7045 0 0458 704c" > /sys/bus/usb/drivers/foo/new_id
Reading from this file will list all dynamically added
device IDs in the same format, with one entry per
- line. For example:
- # cat /sys/bus/usb/drivers/foo/new_id
- 8086 10f5
- dead beef 06
- f00d cafe
+ line. For example::
+
+ # cat /sys/bus/usb/drivers/foo/new_id
+ 8086 10f5
+ dead beef 06
+ f00d cafe
The list will be truncated at PAGE_SIZE bytes due to
sysfs restrictions.
@@ -209,9 +213,11 @@
advance, and behaves well according to the specification.
This attribute is a bit-field that controls the behavior of
a specific port:
+
- Bit 0 of this field selects the "old" enumeration scheme,
as it is considerably faster (it only causes one USB reset
instead of 2).
+
The old enumeration scheme can also be selected globally
using /sys/module/usbcore/parameters/old_scheme_first, but
it is often not desirable as the new scheme was introduced to
@@ -233,10 +239,10 @@
poll() for monitoring changes to this value in user space.
Any time this value changes the corresponding hub device will send a
- udev event with the following attributes:
+ udev event with the following attributes::
- OVER_CURRENT_PORT=/sys/bus/usb/devices/.../(hub interface)/portX
- OVER_CURRENT_COUNT=[current value of this sysfs attribute]
+ OVER_CURRENT_PORT=/sys/bus/usb/devices/.../(hub interface)/portX
+ OVER_CURRENT_COUNT=[current value of this sysfs attribute]
What: /sys/bus/usb/devices/.../(hub interface)/portX/usb3_lpm_permit
Date: November 2015
diff --git a/Documentation/ABI/testing/sysfs-bus-usb-devices-usbsevseg b/Documentation/ABI/testing/sysfs-bus-usb-devices-usbsevseg
index 9ade80f..2f86e42 100644
--- a/Documentation/ABI/testing/sysfs-bus-usb-devices-usbsevseg
+++ b/Documentation/ABI/testing/sysfs-bus-usb-devices-usbsevseg
@@ -12,8 +12,11 @@
Contact: Harrison Metzger <harrisonmetz@gmail.com>
Description: Controls the devices display mode.
For a 6 character display the values are
+
MSB 0x06; LSB 0x3F, and
+
for an 8 character display the values are
+
MSB 0x08; LSB 0xFF.
What: /sys/bus/usb/.../textmode
@@ -37,7 +40,7 @@
Contact: Harrison Metzger <harrisonmetz@gmail.com>
Description: Controls the decimal places on the device.
To set the nth decimal place, give this field
- the value of 10 ** n. Assume this field has
+ the value of ``10 ** n``. Assume this field has
the value k and has 1 or more decimal places set,
to set the mth place (where m is not already set),
- change this fields value to k + 10 ** m.
+ change this fields value to ``k + 10 ** m``.
diff --git a/Documentation/ABI/testing/sysfs-bus-vfio-mdev b/Documentation/ABI/testing/sysfs-bus-vfio-mdev
index 452dbe3..59fc804 100644
--- a/Documentation/ABI/testing/sysfs-bus-vfio-mdev
+++ b/Documentation/ABI/testing/sysfs-bus-vfio-mdev
@@ -28,8 +28,9 @@
Writing UUID to this file will create mediated device of
type <type-id> for parent device <device>. This is a
write-only file.
- For example:
- # echo "83b8f4f2-509f-382f-3c1e-e6bfe0fa1001" > \
+ For example::
+
+ # echo "83b8f4f2-509f-382f-3c1e-e6bfe0fa1001" > \
/sys/devices/foo/mdev_supported_types/foo-1/create
What: /sys/.../mdev_supported_types/<type-id>/devices/
@@ -107,5 +108,6 @@
Writing '1' to this file destroys the mediated device. The
vendor driver can fail the remove() callback if that device
is active and the vendor driver doesn't support hot unplug.
- Example:
- # echo 1 > /sys/bus/mdev/devices/<UUID>/remove
+ Example::
+
+ # echo 1 > /sys/bus/mdev/devices/<UUID>/remove
diff --git a/Documentation/ABI/testing/sysfs-c2port b/Documentation/ABI/testing/sysfs-c2port
index 716cffc..f7b8cf6 100644
--- a/Documentation/ABI/testing/sysfs-c2port
+++ b/Documentation/ABI/testing/sysfs-c2port
@@ -66,13 +66,6 @@
the "erase" command on the on-board flash of the connected
micro.
-What: /sys/class/c2port/c2portX/flash_erase
-Date: October 2008
-Contact: Rodolfo Giometti <giometti@linux.it>
-Description:
- The /sys/class/c2port/c2portX/flash_erase file show the
- on-board flash size of the connected micro.
-
What: /sys/class/c2port/c2portX/reset
Date: October 2008
Contact: Rodolfo Giometti <giometti@linux.it>
diff --git a/Documentation/ABI/testing/sysfs-class-backlight b/Documentation/ABI/testing/sysfs-class-backlight
index 3ab175a..1fc8640 100644
--- a/Documentation/ABI/testing/sysfs-class-backlight
+++ b/Documentation/ABI/testing/sysfs-class-backlight
@@ -24,3 +24,63 @@
non-linear
The brightness changes non-linearly with each step. Brightness
controls should use a linear mapping for a linear perception.
+
+What: /sys/class/backlight/<backlight>/ambient_light_level
+Date: Apr, 2010
+KernelVersion: v2.6.35
+Contact: Michael Hennerich <michael.hennerich@analog.com>
+Description:
+ (RO) Get conversion value of the light sensor.
+
+ The value is automatically updated every 80 ms when the
+ light sensor is enabled.
+
+ The value range is device-driver specific:
+
+ For ADP8870:
+
+ It returns integer between 0 (dark) and 8000 (max ambient
+ brightness).
+
+ For ADP8860:
+
+ It returns a 13-bits integer.
+
+What: /sys/class/backlight/<backlight>/ambient_light_zone
+Date: Apr, 2010
+KernelVersion: v2.6.35
+Contact: Michael Hennerich <michael.hennerich@analog.com>,
+ device-drivers-devel@blackfin.uclinux.org
+
+Description:
+ (RW) Read or write the specific brightness level at which the
+ backlight operates.
+
+ The value meaning is device-driver specific:
+
+ For ADP8860:
+
+ == ==========================
+ 0 Off: Backlight set to 0 mA
+ 1 Level 1: daylight
+ 2 Level 2: bright
+ 3 Level 3: dark
+ == ==========================
+
+ For ADP8870:
+
+ == ==========================
+ 0 Off: Backlight set to 0 mA
+ 1 Level 1: daylight
+ 2 Level 2: bright
+ 3 Level 3: office
+ 4 Level 4: indoor
+ 5 Level 5: dark
+ == ==========================
+
+ Writing 0 returns to normal/automatic ambient light level
+ operation.
+
+ It can be enabled by writing the value stored in
+ /sys/class/backlight/<backlight>/max_brightness to
+ /sys/class/backlight/<backlight>/brightness.
diff --git a/Documentation/ABI/testing/sysfs-class-backlight-adp8860 b/Documentation/ABI/testing/sysfs-class-backlight-adp8860
index 54d61c7..6610ac7 100644
--- a/Documentation/ABI/testing/sysfs-class-backlight-adp8860
+++ b/Documentation/ABI/testing/sysfs-class-backlight-adp8860
@@ -6,25 +6,8 @@
dark (level 3). By default the brightness operates at the daylight brightness
level.
-What: /sys/class/backlight/<backlight>/ambient_light_level
-Date: Apr, 2010
-KernelVersion: v2.6.35
-Contact: Michael Hennerich <michael.hennerich@analog.com>
-Description:
- (RO) 13-bit conversion value for the first light sensor—high
- byte (Bit 12 to Bit 8). The value is updated every 80 ms (when
- the light sensor is enabled).
-
-
-What: /sys/class/backlight/<backlight>/ambient_light_zone
-Date: Apr, 2010
-KernelVersion: v2.6.35
-Contact: Michael Hennerich <michael.hennerich@analog.com>
-Description:
- (RW) Read or write the specific level at which the backlight
- operates. Value "0" enables automatic ambient light sensing, and
- values "1", "2" or "3" set the control to daylight, office or
- dark respectively.
+See also /sys/class/backlight/<backlight>/ambient_light_level and
+/sys/class/backlight/<backlight>/ambient_light_zone.
What: /sys/class/backlight/<backlight>/l1_daylight_max
diff --git a/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870 b/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870
index 33e6488..b08ca91 100644
--- a/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870
+++ b/Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870
@@ -1,3 +1,6 @@
+See also /sys/class/backlight/<backlight>/ambient_light_level and
+/sys/class/backlight/<backlight>/ambient_light_zone.
+
What: /sys/class/backlight/<backlight>/<ambient light zone>_max
What: /sys/class/backlight/<backlight>/l1_daylight_max
What: /sys/class/backlight/<backlight>/l2_bright_max
@@ -27,30 +30,3 @@
set to 0. Full off when the backlight is disabled.
This file will also show the dim brightness level stored for
this <ambient light zone>.
-
-What: /sys/class/backlight/<backlight>/ambient_light_level
-Date: May 2011
-KernelVersion: 3.0
-Contact: device-drivers-devel@blackfin.uclinux.org
-Description:
- Get conversion value of the light sensor.
- This value is updated every 80 ms (when the light sensor
- is enabled). Returns integer between 0 (dark) and
- 8000 (max ambient brightness)
-
-What: /sys/class/backlight/<backlight>/ambient_light_zone
-Date: May 2011
-KernelVersion: 3.0
-Contact: device-drivers-devel@blackfin.uclinux.org
-Description:
- Get/Set current ambient light zone. Reading returns
- integer between 1..5 (1 = daylight, 2 = bright, ..., 5 = dark).
- Writing a value between 1..5 forces the backlight controller
- to enter the corresponding ambient light zone.
- Writing 0 returns to normal/automatic ambient light level
- operation. The ambient light sensing feature on these devices
- is an extension to the API documented in
- Documentation/ABI/stable/sysfs-class-backlight.
- It can be enabled by writing the value stored in
- /sys/class/backlight/<backlight>/max_brightness to
- /sys/class/backlight/<backlight>/brightness.
diff --git a/Documentation/ABI/testing/sysfs-class-backlight-driver-lm3533 b/Documentation/ABI/testing/sysfs-class-backlight-driver-lm3533
index c0e0a9a..8251e78 100644
--- a/Documentation/ABI/testing/sysfs-class-backlight-driver-lm3533
+++ b/Documentation/ABI/testing/sysfs-class-backlight-driver-lm3533
@@ -6,8 +6,10 @@
Get the ALS output channel used as input in
ALS-current-control mode (0, 1), where:
- 0 - out_current0 (backlight 0)
- 1 - out_current1 (backlight 1)
+ == ==========================
+ 0 out_current0 (backlight 0)
+ 1 out_current1 (backlight 1)
+ == ==========================
What: /sys/class/backlight/<backlight>/als_en
Date: May 2012
@@ -30,8 +32,10 @@
Description:
Set the brightness-mapping mode (0, 1), where:
- 0 - exponential mode
- 1 - linear mode
+ == ================
+ 0 exponential mode
+ 1 linear mode
+ == ================
What: /sys/class/backlight/<backlight>/pwm
Date: April 2012
@@ -40,9 +44,11 @@
Description:
Set the PWM-input control mask (5 bits), where:
- bit 5 - PWM-input enabled in Zone 4
- bit 4 - PWM-input enabled in Zone 3
- bit 3 - PWM-input enabled in Zone 2
- bit 2 - PWM-input enabled in Zone 1
- bit 1 - PWM-input enabled in Zone 0
- bit 0 - PWM-input enabled
+ ===== ===========================
+ bit 5 PWM-input enabled in Zone 4
+ bit 4 PWM-input enabled in Zone 3
+ bit 3 PWM-input enabled in Zone 2
+ bit 2 PWM-input enabled in Zone 1
+ bit 1 PWM-input enabled in Zone 0
+ bit 0 PWM-input enabled
+ ===== ===========================
diff --git a/Documentation/ABI/testing/sysfs-class-bdi b/Documentation/ABI/testing/sysfs-class-bdi
index d773d56..5402bd7 100644
--- a/Documentation/ABI/testing/sysfs-class-bdi
+++ b/Documentation/ABI/testing/sysfs-class-bdi
@@ -24,7 +24,6 @@
filesystems which do not provide their own BDI.
Files under /sys/class/bdi/<bdi>/
----------------------------------
read_ahead_kb (read-write)
diff --git a/Documentation/ABI/testing/sysfs-class-chromeos b/Documentation/ABI/testing/sysfs-class-chromeos
index 5819699..74ece94 100644
--- a/Documentation/ABI/testing/sysfs-class-chromeos
+++ b/Documentation/ABI/testing/sysfs-class-chromeos
@@ -17,13 +17,14 @@
KernelVersion: 4.2
Description:
Tell the EC to reboot in various ways. Options are:
- "cancel": Cancel a pending reboot.
- "ro": Jump to RO without rebooting.
- "rw": Jump to RW without rebooting.
- "cold": Cold reboot.
- "disable-jump": Disable jump until next reboot.
- "hibernate": Hibernate the EC.
- "at-shutdown": Reboot after an AP shutdown.
+
+ - "cancel": Cancel a pending reboot.
+ - "ro": Jump to RO without rebooting.
+ - "rw": Jump to RW without rebooting.
+ - "cold": Cold reboot.
+ - "disable-jump": Disable jump until next reboot.
+ - "hibernate": Hibernate the EC.
+ - "at-shutdown": Reboot after an AP shutdown.
What: /sys/class/chromeos/<ec-device-name>/version
Date: August 2015
diff --git a/Documentation/ABI/testing/sysfs-class-cxl b/Documentation/ABI/testing/sysfs-class-cxl
index 7970e37..818f559 100644
--- a/Documentation/ABI/testing/sysfs-class-cxl
+++ b/Documentation/ABI/testing/sysfs-class-cxl
@@ -72,11 +72,16 @@
when performing the START_WORK ioctl. Only applicable when
running under hashed page table mmu.
Possible values:
- none: No prefaulting (default)
- work_element_descriptor: Treat the work element
- descriptor as an effective address and
- prefault what it points to.
- all: all segments process calling START_WORK maps.
+
+ ======================= ======================================
+ none No prefaulting (default)
+ work_element_descriptor Treat the work element
+ descriptor as an effective address and
+ prefault what it points to.
+ all all segments process calling
+ START_WORK maps.
+ ======================= ======================================
+
Users: https://github.com/ibm-capi/libcxl
What: /sys/class/cxl/<afu>/reset
@@ -212,6 +217,7 @@
card. A power cycle is required to load the image.
"none" could be useful for debugging because the trace arrays
are preserved.
+
"user" and "factory" means PERST will cause either the user or
user or factory image to be loaded.
Default is to reload on PERST whichever image the card has
@@ -235,8 +241,11 @@
Description: read/write
Trust that when an image is reloaded via PERST, it will not
have changed.
- 0 = don't trust, the image may be different (default)
- 1 = trust that the image will not change.
+
+ == =================================================
+ 0 don't trust, the image may be different (default)
+ 1 trust that the image will not change.
+ == =================================================
Users: https://github.com/ibm-capi/libcxl
What: /sys/class/cxl/<card>/psl_timebase_synced
diff --git a/Documentation/ABI/testing/sysfs-class-devfreq b/Documentation/ABI/testing/sysfs-class-devfreq
index deefffb..b8ebff4 100644
--- a/Documentation/ABI/testing/sysfs-class-devfreq
+++ b/Documentation/ABI/testing/sysfs-class-devfreq
@@ -62,7 +62,8 @@
driver should provide the list of available frequencies
with its profile. If need to reset the statistics of devfreq
behavior on a specific device, enter 0(zero) to 'trans_stat'
- as following:
+ as following::
+
echo 0 > /sys/class/devfreq/.../trans_stat
What: /sys/class/devfreq/.../userspace/set_freq
@@ -117,6 +118,7 @@
This work timer is used by devfreq workqueue in order to
monitor the device status such as utilization. The user
can change the work timer on runtime according to their demand
- as following:
+ as following::
+
echo deferrable > /sys/class/devfreq/.../timer
echo delayed > /sys/class/devfreq/.../timer
diff --git a/Documentation/ABI/testing/sysfs-class-devlink b/Documentation/ABI/testing/sysfs-class-devlink
index 64791b6..b662f74 100644
--- a/Documentation/ABI/testing/sysfs-class-devlink
+++ b/Documentation/ABI/testing/sysfs-class-devlink
@@ -18,9 +18,9 @@
This will be one of the following strings:
- 'consumer unbind'
- 'supplier unbind'
- 'never'
+ - 'consumer unbind'
+ - 'supplier unbind'
+ - 'never'
'consumer unbind' means the device link will be removed when
the consumer's driver is unbound from the consumer device.
@@ -49,8 +49,10 @@
This will be one of the following strings:
- '0' - Does not affect runtime power management
- '1' - Affects runtime power management
+ === ========================================
+ '0' Does not affect runtime power management
+ '1' Affects runtime power management
+ === ========================================
What: /sys/class/devlink/.../status
Date: May 2020
@@ -68,13 +70,13 @@
This will be one of the following strings:
- 'not tracked'
- 'dormant'
- 'available'
- 'consumer probing'
- 'active'
- 'supplier unbinding'
- 'unknown'
+ - 'not tracked'
+ - 'dormant'
+ - 'available'
+ - 'consumer probing'
+ - 'active'
+ - 'supplier unbinding'
+ - 'unknown'
'not tracked' means this device link does not track the status
and has no impact on the binding, unbinding and syncing the
@@ -114,8 +116,10 @@
This will be one of the following strings:
+ === ================================
'0'
- '1' - Affects runtime power management
+ '1' Affects runtime power management
+ === ================================
'0' means the device link can affect other device behaviors
like binding/unbinding, suspend/resume, runtime power
diff --git a/Documentation/ABI/testing/sysfs-class-extcon b/Documentation/ABI/testing/sysfs-class-extcon
index 57a7262..fde0fec 100644
--- a/Documentation/ABI/testing/sysfs-class-extcon
+++ b/Documentation/ABI/testing/sysfs-class-extcon
@@ -39,19 +39,22 @@
callback.
If the default callback for showing function is used, the
- format is like this:
- # cat state
- USB_OTG=1
- HDMI=0
- TA=1
- EAR_JACK=0
- #
+ format is like this::
+
+ # cat state
+ USB_OTG=1
+ HDMI=0
+ TA=1
+ EAR_JACK=0
+ #
+
In this example, the extcon device has USB_OTG and TA
cables attached and HDMI and EAR_JACK cables detached.
In order to update the state of an extcon device, enter a hex
- state number starting with 0x:
- # echo 0xHEX > state
+ state number starting with 0x::
+
+ # echo 0xHEX > state
This updates the whole state of the extcon device.
Inputs of all the methods are required to meet the
@@ -84,12 +87,13 @@
Description:
Shows the relations of mutually exclusiveness. For example,
if the mutually_exclusive array of extcon device is
- {0x3, 0x5, 0xC, 0x0}, then the output is:
- # ls mutually_exclusive/
- 0x3
- 0x5
- 0xc
- #
+ {0x3, 0x5, 0xC, 0x0}, then the output is::
+
+ # ls mutually_exclusive/
+ 0x3
+ 0x5
+ 0xc
+ #
Note that mutually_exclusive is a sub-directory of the extcon
device and the file names under the mutually_exclusive
diff --git a/Documentation/ABI/testing/sysfs-class-fpga-manager b/Documentation/ABI/testing/sysfs-class-fpga-manager
index 5284fa3..d78689c 100644
--- a/Documentation/ABI/testing/sysfs-class-fpga-manager
+++ b/Documentation/ABI/testing/sysfs-class-fpga-manager
@@ -28,8 +28,7 @@
* firmware request = firmware class request in progress
* firmware request error = firmware request failed
* write init = preparing FPGA for programming
- * write init error = Error while preparing FPGA for
- programming
+ * write init error = Error while preparing FPGA for programming
* write = FPGA ready to receive image data
* write error = Error while programming
* write complete = Doing post programming steps
@@ -47,7 +46,7 @@
programming errors to userspace. This is a list of strings for
the supported status.
- * reconfig operation error - invalid operations detected by
+ * reconfig operation error - invalid operations detected by
reconfiguration hardware.
e.g. start reconfiguration
with errors not cleared
diff --git a/Documentation/ABI/testing/sysfs-class-gnss b/Documentation/ABI/testing/sysfs-class-gnss
index 2467b69..c8553d9 100644
--- a/Documentation/ABI/testing/sysfs-class-gnss
+++ b/Documentation/ABI/testing/sysfs-class-gnss
@@ -6,9 +6,11 @@
The GNSS receiver type. The currently identified types reflect
the protocol(s) supported by the receiver:
+ ====== ===========
"NMEA" NMEA 0183
"SiRF" SiRF Binary
"UBX" UBX
+ ====== ===========
Note that also non-"NMEA" type receivers typically support a
subset of NMEA 0183 with vendor extensions (e.g. to allow
diff --git a/Documentation/ABI/testing/sysfs-class-led b/Documentation/ABI/testing/sysfs-class-led
index 5f67f7a..2e24ac3 100644
--- a/Documentation/ABI/testing/sysfs-class-led
+++ b/Documentation/ABI/testing/sysfs-class-led
@@ -3,9 +3,26 @@
KernelVersion: 2.6.17
Contact: Richard Purdie <rpurdie@rpsys.net>
Description:
- Set the brightness of the LED. Most LEDs don't
- have hardware brightness support, so will just be turned on for
- non-zero brightness settings. The value is between 0 and
+ Set the brightness of the LED.
+
+ Most LEDs don't have hardware brightness support, so will
+ just be turned on for non-zero brightness settings.
+
+ .. Note::
+
+ For multicolor LEDs, writing to this file will update all
+ LEDs within the group to a calculated percentage of what
+ each color LED intensity is set to.
+
+ The percentage is calculated for each grouped LED via
+ the equation below::
+
+ led_brightness = brightness * multi_intensity/max_brightness
+
+ For additional details please refer to
+ Documentation/leds/leds-class-multicolor.rst.
+
+ The value is between 0 and
/sys/class/leds/<led>/max_brightness.
Writing 0 to this file clears active trigger.
@@ -13,6 +30,8 @@
Writing non-zero to this file while trigger is active changes the
top brightness trigger is going to use.
+
+
What: /sys/class/leds/<led>/max_brightness
Date: March 2006
KernelVersion: 2.6.17
@@ -47,10 +66,11 @@
Description:
Set the trigger for this LED. A trigger is a kernel based source
of LED events.
+
You can change triggers in a similar manner to the way an IO
scheduler is chosen. Trigger specific parameters can appear in
/sys/class/leds/<led> once a given trigger is selected. For
- their documentation see sysfs-class-led-trigger-*.
+ their documentation see `sysfs-class-led-trigger-*`.
What: /sys/class/leds/<led>/inverted
Date: January 2011
diff --git a/Documentation/ABI/testing/sysfs-class-led-driver-el15203000 b/Documentation/ABI/testing/sysfs-class-led-driver-el15203000
index f520ece..04f3ffd 100644
--- a/Documentation/ABI/testing/sysfs-class-led-driver-el15203000
+++ b/Documentation/ABI/testing/sysfs-class-led-driver-el15203000
@@ -1,133 +1,3 @@
-What: /sys/class/leds/<led>/hw_pattern
-Date: September 2019
-KernelVersion: 5.5
-Description:
- Specify a hardware pattern for the EL15203000 LED.
- The LEDs board supports only predefined patterns by firmware
- for specific LEDs.
-
- Breathing mode for Screen frame light tube:
- "0 4000 1 4000"
-
- ^
- |
- Max-| ---
- | / \
- | / \
- | / \ /
- | / \ /
- Min-|- ---
- |
- 0------4------8--> time (sec)
-
- Cascade mode for Pipe LED:
- "1 800 2 800 4 800 8 800 16 800"
-
- ^
- |
- 0 On -|----+ +----+ +---
- | | | | |
- Off-| +-------------------+ +-------------------+
- |
- 1 On -| +----+ +----+
- | | | | |
- Off |----+ +-------------------+ +------------------
- |
- 2 On -| +----+ +----+
- | | | | |
- Off-|---------+ +-------------------+ +-------------
- |
- 3 On -| +----+ +----+
- | | | | |
- Off-|--------------+ +-------------------+ +--------
- |
- 4 On -| +----+ +----+
- | | | | |
- Off-|-------------------+ +-------------------+ +---
- |
- 0---0.8--1.6--2.4--3.2---4---4.8--5.6--6.4--7.2---8--> time (sec)
-
- Inverted cascade mode for Pipe LED:
- "30 800 29 800 27 800 23 800 15 800"
-
- ^
- |
- 0 On -| +-------------------+ +-------------------+
- | | | | |
- Off-|----+ +----+ +---
- |
- 1 On -|----+ +-------------------+ +------------------
- | | | | |
- Off | +----+ +----+
- |
- 2 On -|---------+ +-------------------+ +-------------
- | | | | |
- Off-| +----+ +----+
- |
- 3 On -|--------------+ +-------------------+ +--------
- | | | | |
- Off-| +----+ +----+
- |
- 4 On -|-------------------+ +-------------------+ +---
- | | | | |
- Off-| +----+ +----+
- |
- 0---0.8--1.6--2.4--3.2---4---4.8--5.6--6.4--7.2---8--> time (sec)
-
- Bounce mode for Pipe LED:
- "1 800 2 800 4 800 8 800 16 800 16 800 8 800 4 800 2 800 1 800"
-
- ^
- |
- 0 On -|----+ +--------
- | | |
- Off-| +---------------------------------------+
- |
- 1 On -| +----+ +----+
- | | | | |
- Off |----+ +-----------------------------+ +--------
- |
- 2 On -| +----+ +----+
- | | | | |
- Off-|---------+ +-------------------+ +-------------
- |
- 3 On -| +----+ +----+
- | | | | |
- Off-|--------------+ +---------+ +------------------
- |
- 4 On -| +---------+
- | | |
- Off-|-------------------+ +-----------------------
- |
- 0---0.8--1.6--2.4--3.2---4---4.8--5.6--6.4--7.2---8--> time (sec)
-
- Inverted bounce mode for Pipe LED:
- "30 800 29 800 27 800 23 800 15 800 15 800 23 800 27 800 29 800 30 800"
-
- ^
- |
- 0 On -| +---------------------------------------+
- | | |
- Off-|----+ +--------
- |
- 1 On -|----+ +-----------------------------+ +--------
- | | | | |
- Off | +----+ +----+
- |
- 2 On -|---------+ +-------------------+ +-------------
- | | | | |
- Off-| +----+ +----+
- |
- 3 On -|--------------+ +---------+ +------------------
- | | | | |
- Off-| +----+ +----+
- |
- 4 On -|-------------------+ +-----------------------
- | | |
- Off-| +---------+
- |
- 0---0.8--1.6--2.4--3.2---4---4.8--5.6--6.4--7.2---8--> time (sec)
-
What: /sys/class/leds/<led>/repeat
Date: September 2019
KernelVersion: 5.5
diff --git a/Documentation/ABI/testing/sysfs-class-led-driver-lm3533 b/Documentation/ABI/testing/sysfs-class-led-driver-lm3533
index e4c89b2..e38a835 100644
--- a/Documentation/ABI/testing/sysfs-class-led-driver-lm3533
+++ b/Documentation/ABI/testing/sysfs-class-led-driver-lm3533
@@ -6,8 +6,10 @@
Set the ALS output channel to use as input in
ALS-current-control mode (1, 2), where:
- 1 - out_current1
- 2 - out_current2
+ == ============
+ 1 out_current1
+ 2 out_current2
+ == ============
What: /sys/class/leds/<led>/als_en
Date: May 2012
@@ -24,14 +26,16 @@
Description:
Set the pattern generator fall and rise times (0..7), where:
- 0 - 2048 us
- 1 - 262 ms
- 2 - 524 ms
- 3 - 1.049 s
- 4 - 2.097 s
- 5 - 4.194 s
- 6 - 8.389 s
- 7 - 16.78 s
+ == =======
+ 0 2048 us
+ 1 262 ms
+ 2 524 ms
+ 3 1.049 s
+ 4 2.097 s
+ 5 4.194 s
+ 6 8.389 s
+ 7 16.78 s
+ == =======
What: /sys/class/leds/<led>/id
Date: April 2012
@@ -47,8 +51,10 @@
Description:
Set the brightness-mapping mode (0, 1), where:
- 0 - exponential mode
- 1 - linear mode
+ == ================
+ 0 exponential mode
+ 1 linear mode
+ == ================
What: /sys/class/leds/<led>/pwm
Date: April 2012
@@ -57,9 +63,11 @@
Description:
Set the PWM-input control mask (5 bits), where:
- bit 5 - PWM-input enabled in Zone 4
- bit 4 - PWM-input enabled in Zone 3
- bit 3 - PWM-input enabled in Zone 2
- bit 2 - PWM-input enabled in Zone 1
- bit 1 - PWM-input enabled in Zone 0
- bit 0 - PWM-input enabled
+ ===== ===========================
+ bit 5 PWM-input enabled in Zone 4
+ bit 4 PWM-input enabled in Zone 3
+ bit 3 PWM-input enabled in Zone 2
+ bit 2 PWM-input enabled in Zone 1
+ bit 1 PWM-input enabled in Zone 0
+ bit 0 PWM-input enabled
+ ===== ===========================
diff --git a/Documentation/ABI/testing/sysfs-class-led-driver-sc27xx b/Documentation/ABI/testing/sysfs-class-led-driver-sc27xx
deleted file mode 100644
index 45b1e60..0000000
--- a/Documentation/ABI/testing/sysfs-class-led-driver-sc27xx
+++ /dev/null
@@ -1,22 +0,0 @@
-What: /sys/class/leds/<led>/hw_pattern
-Date: September 2018
-KernelVersion: 4.20
-Description:
- Specify a hardware pattern for the SC27XX LED. For the SC27XX
- LED controller, it only supports 4 stages to make a single
- hardware pattern, which is used to configure the rise time,
- high time, fall time and low time for the breathing mode.
-
- For the breathing mode, the SC27XX LED only expects one brightness
- for the high stage. To be compatible with the hardware pattern
- format, we should set brightness as 0 for rise stage, fall
- stage and low stage.
-
- Min stage duration: 125 ms
- Max stage duration: 31875 ms
-
- Since the stage duration step is 125 ms, the duration should be
- a multiplier of 125, like 125ms, 250ms, 375ms, 500ms ... 31875ms.
-
- Thus the format of the hardware pattern values should be:
- "0 rise_duration brightness high_duration 0 fall_duration 0 low_duration".
diff --git a/Documentation/ABI/testing/sysfs-class-led-flash b/Documentation/ABI/testing/sysfs-class-led-flash
index 220a0270..11e5677 100644
--- a/Documentation/ABI/testing/sysfs-class-led-flash
+++ b/Documentation/ABI/testing/sysfs-class-led-flash
@@ -55,26 +55,35 @@
Flash faults are re-read after strobing the flash. Possible
flash faults:
- * led-over-voltage - flash controller voltage to the flash LED
+ * led-over-voltage
+ flash controller voltage to the flash LED
has exceeded the limit specific to the flash controller
- * flash-timeout-exceeded - the flash strobe was still on when
+ * flash-timeout-exceeded
+ the flash strobe was still on when
the timeout set by the user has expired; not all flash
controllers may set this in all such conditions
- * controller-over-temperature - the flash controller has
+ * controller-over-temperature
+ the flash controller has
overheated
- * controller-short-circuit - the short circuit protection
+ * controller-short-circuit
+ the short circuit protection
of the flash controller has been triggered
- * led-power-supply-over-current - current in the LED power
+ * led-power-supply-over-current
+ current in the LED power
supply has exceeded the limit specific to the flash
controller
- * indicator-led-fault - the flash controller has detected
+ * indicator-led-fault
+ the flash controller has detected
a short or open circuit condition on the indicator LED
- * led-under-voltage - flash controller voltage to the flash
+ * led-under-voltage
+ flash controller voltage to the flash
LED has been below the minimum limit specific to
the flash
- * controller-under-voltage - the input voltage of the flash
+ * controller-under-voltage
+ the input voltage of the flash
controller is below the limit under which strobing the
flash at full current will not be possible;
the condition persists until this flag is no longer set
- * led-over-temperature - the temperature of the LED has exceeded
+ * led-over-temperature
+ the temperature of the LED has exceeded
its allowed upper limit
diff --git a/Documentation/ABI/testing/sysfs-class-led-multicolor b/Documentation/ABI/testing/sysfs-class-led-multicolor
index eeeddcb..16fc827 100644
--- a/Documentation/ABI/testing/sysfs-class-led-multicolor
+++ b/Documentation/ABI/testing/sysfs-class-led-multicolor
@@ -1,20 +1,3 @@
-What: /sys/class/leds/<led>/brightness
-Date: March 2020
-KernelVersion: 5.9
-Contact: Dan Murphy <dmurphy@ti.com>
-Description: read/write
- Writing to this file will update all LEDs within the group to a
- calculated percentage of what each color LED intensity is set
- to. The percentage is calculated for each grouped LED via the
- equation below:
-
- led_brightness = brightness * multi_intensity/max_brightness
-
- For additional details please refer to
- Documentation/leds/leds-class-multicolor.rst.
-
- The value of the LED is from 0 to
- /sys/class/leds/<led>/max_brightness.
What: /sys/class/leds/<led>/multi_index
Date: March 2020
@@ -25,6 +8,9 @@
as an array of strings as they are indexed in the
multi_intensity file.
+ For additional details please refer to
+ Documentation/leds/leds-class-multicolor.rst.
+
What: /sys/class/leds/<led>/multi_intensity
Date: March 2020
KernelVersion: 5.9
@@ -33,3 +19,6 @@
This file contains array of integers. Order of components is
described by the multi_index array. The maximum intensity should
not exceed /sys/class/leds/<led>/max_brightness.
+
+ For additional details please refer to
+ Documentation/leds/leds-class-multicolor.rst.
diff --git a/Documentation/ABI/testing/sysfs-class-led-trigger-netdev b/Documentation/ABI/testing/sysfs-class-led-trigger-netdev
index 451af6d..6465409 100644
--- a/Documentation/ABI/testing/sysfs-class-led-trigger-netdev
+++ b/Documentation/ABI/testing/sysfs-class-led-trigger-netdev
@@ -19,18 +19,23 @@
Contact: linux-leds@vger.kernel.org
Description:
Signal the link state of the named network device.
+
If set to 0 (default), the LED's normal state is off.
+
If set to 1, the LED's normal state reflects the link state
of the named network device.
Setting this value also immediately changes the LED state.
+
What: /sys/class/leds/<led>/tx
Date: Dec 2017
KernelVersion: 4.16
Contact: linux-leds@vger.kernel.org
Description:
Signal transmission of data on the named network device.
+
If set to 0 (default), the LED will not blink on transmission.
+
If set to 1, the LED will blink for the milliseconds specified
in interval to signal transmission.
@@ -40,6 +45,8 @@
Contact: linux-leds@vger.kernel.org
Description:
Signal reception of data on the named network device.
+
If set to 0 (default), the LED will not blink on reception.
+
If set to 1, the LED will blink for the milliseconds specified
in interval to signal reception.
diff --git a/Documentation/ABI/testing/sysfs-class-led-trigger-pattern b/Documentation/ABI/testing/sysfs-class-led-trigger-pattern
index bd92ef9..d91a077 100644
--- a/Documentation/ABI/testing/sysfs-class-led-trigger-pattern
+++ b/Documentation/ABI/testing/sysfs-class-led-trigger-pattern
@@ -23,8 +23,8 @@
Since different LED hardware can have different semantics of
hardware patterns, each driver is expected to provide its own
- description for the hardware patterns in their ABI documentation
- file.
+ description for the hardware patterns in their documentation
+ file at Documentation/leds/.
What: /sys/class/leds/<led>/repeat
Date: September 2018
diff --git a/Documentation/ABI/testing/sysfs-class-led-trigger-usbport b/Documentation/ABI/testing/sysfs-class-led-trigger-usbport
index f440e69..eb81152 100644
--- a/Documentation/ABI/testing/sysfs-class-led-trigger-usbport
+++ b/Documentation/ABI/testing/sysfs-class-led-trigger-usbport
@@ -8,5 +8,6 @@
selected for the USB port trigger. Selecting ports makes trigger
observing them for any connected devices and lighting on LED if
there are any.
+
Echoing "1" value selects USB port. Echoing "0" unselects it.
Current state can be also read.
diff --git a/Documentation/ABI/testing/sysfs-class-leds-gt683r b/Documentation/ABI/testing/sysfs-class-leds-gt683r
index 6adab27..b57ffb2 100644
--- a/Documentation/ABI/testing/sysfs-class-leds-gt683r
+++ b/Documentation/ABI/testing/sysfs-class-leds-gt683r
@@ -7,9 +7,11 @@
of one LED will update the mode of its two sibling devices as
well. Possible values are:
- 0 - normal
- 1 - audio
- 2 - breathing
+ == =========
+ 0 normal
+ 1 audio
+ 2 breathing
+ == =========
Normal: LEDs are fully on when enabled
Audio: LEDs brightness depends on sound level
diff --git a/Documentation/ABI/testing/sysfs-class-mic b/Documentation/ABI/testing/sysfs-class-mic
index 6ef6826..bd0e780 100644
--- a/Documentation/ABI/testing/sysfs-class-mic
+++ b/Documentation/ABI/testing/sysfs-class-mic
@@ -41,24 +41,33 @@
When read, this entry provides the current state of an Intel
MIC device in the context of the card OS. Possible values that
will be read are:
- "ready" - The MIC device is ready to boot the card OS. On
- reading this entry after an OSPM resume, a "boot" has to be
- written to this entry if the card was previously shutdown
- during OSPM suspend.
- "booting" - The MIC device has initiated booting a card OS.
- "online" - The MIC device has completed boot and is online
- "shutting_down" - The card OS is shutting down.
- "resetting" - A reset has been initiated for the MIC device
- "reset_failed" - The MIC device has failed to reset.
+
+
+ =============== ===============================================
+ "ready" The MIC device is ready to boot the card OS.
+ On reading this entry after an OSPM resume,
+ a "boot" has to be written to this entry if
+ the card was previously shutdown during OSPM
+ suspend.
+ "booting" The MIC device has initiated booting a card OS.
+ "online" The MIC device has completed boot and is online
+ "shutting_down" The card OS is shutting down.
+ "resetting" A reset has been initiated for the MIC device
+ "reset_failed" The MIC device has failed to reset.
+ =============== ===============================================
When written, this sysfs entry triggers different state change
operations depending upon the current state of the card OS.
Acceptable values are:
- "boot" - Boot the card OS image specified by the combination
- of firmware, ramdisk, cmdline and bootmode
- sysfs entries.
- "reset" - Initiates device reset.
- "shutdown" - Initiates card OS shutdown.
+
+
+ ========== ===================================================
+ "boot" Boot the card OS image specified by the combination
+ of firmware, ramdisk, cmdline and bootmode
+ sysfs entries.
+ "reset" Initiates device reset.
+ "shutdown" Initiates card OS shutdown.
+ ========== ===================================================
What: /sys/class/mic/mic(x)/shutdown_status
Date: October 2013
@@ -69,12 +78,15 @@
OS can shutdown because of various reasons. When read, this
entry provides the status on why the card OS was shutdown.
Possible values are:
- "nop" - shutdown status is not applicable, when the card OS is
- "online"
- "crashed" - Shutdown because of a HW or SW crash.
- "halted" - Shutdown because of a halt command.
- "poweroff" - Shutdown because of a poweroff command.
- "restart" - Shutdown because of a restart command.
+
+ ========== ===================================================
+ "nop" shutdown status is not applicable, when the card OS
+ is "online"
+ "crashed" Shutdown because of a HW or SW crash.
+ "halted" Shutdown because of a halt command.
+ "poweroff" Shutdown because of a poweroff command.
+ "restart" Shutdown because of a restart command.
+ ========== ===================================================
What: /sys/class/mic/mic(x)/cmdline
Date: October 2013
diff --git a/Documentation/ABI/testing/sysfs-class-net b/Documentation/ABI/testing/sysfs-class-net
index 3b40457..1f2002d 100644
--- a/Documentation/ABI/testing/sysfs-class-net
+++ b/Documentation/ABI/testing/sysfs-class-net
@@ -4,10 +4,13 @@
Contact: netdev@vger.kernel.org
Description:
Indicates the name assignment type. Possible values are:
- 1: enumerated by the kernel, possibly in an unpredictable way
- 2: predictably named by the kernel
- 3: named by userspace
- 4: renamed
+
+ == ==========================================================
+ 1 enumerated by the kernel, possibly in an unpredictable way
+ 2 predictably named by the kernel
+ 3 named by userspace
+ 4 renamed
+ == ==========================================================
What: /sys/class/net/<iface>/addr_assign_type
Date: July 2010
@@ -15,10 +18,13 @@
Contact: netdev@vger.kernel.org
Description:
Indicates the address assignment type. Possible values are:
- 0: permanent address
- 1: randomly generated
- 2: stolen from another device
- 3: set using dev_set_mac_address
+
+ == =============================
+ 0 permanent address
+ 1 randomly generated
+ 2 stolen from another device
+ 3 set using dev_set_mac_address
+ == =============================
What: /sys/class/net/<iface>/addr_len
Date: April 2005
@@ -51,9 +57,12 @@
Default value 0 does not forward any link local frames.
Restricted bits:
- 0: 01-80-C2-00-00-00 Bridge Group Address used for STP
- 1: 01-80-C2-00-00-01 (MAC Control) 802.3 used for MAC PAUSE
- 2: 01-80-C2-00-00-02 (Link Aggregation) 802.3ad
+
+ == ========================================================
+ 0 01-80-C2-00-00-00 Bridge Group Address used for STP
+ 1 01-80-C2-00-00-01 (MAC Control) 802.3 used for MAC PAUSE
+ 2 01-80-C2-00-00-02 (Link Aggregation) 802.3ad
+ == ========================================================
Any values not setting these bits can be used. Take special
care when forwarding control frames e.g. 802.1X-PAE or LLDP.
@@ -74,8 +83,11 @@
Description:
Indicates the current physical link state of the interface.
Posssible values are:
- 0: physical link is down
- 1: physical link is up
+
+ == =====================
+ 0 physical link is down
+ 1 physical link is up
+ == =====================
Note: some special devices, e.g: bonding and team drivers will
allow this attribute to be written to force a link state for
@@ -131,21 +143,27 @@
Description:
Indicates whether the interface is under test. Possible
values are:
- 0: interface is not being tested
- 1: interface is being tested
+
+ == =============================
+ 0 interface is not being tested
+ 1 interface is being tested
+ == =============================
When an interface is under test, it cannot be expected
to pass packets as normal.
-What: /sys/clas/net/<iface>/duplex
+What: /sys/class/net/<iface>/duplex
Date: October 2009
KernelVersion: 2.6.33
Contact: netdev@vger.kernel.org
Description:
Indicates the interface latest or current duplex value. Possible
values are:
- half: half duplex
- full: full duplex
+
+ ==== ===========
+ half half duplex
+ full full duplex
+ ==== ===========
Note: This attribute is only valid for interfaces that implement
the ethtool get_link_ksettings method (mostly Ethernet).
@@ -196,8 +214,11 @@
Indicates the interface link mode, as a decimal number. This
attribute should be used in conjunction with 'dormant' attribute
to determine the interface usability. Possible values:
- 0: default link mode
- 1: dormant link mode
+
+ == =================
+ 0 default link mode
+ 1 dormant link mode
+ == =================
What: /sys/class/net/<iface>/mtu
Date: April 2005
@@ -226,7 +247,9 @@
Contact: netdev@vger.kernel.org
Description:
Indicates the interface RFC2863 operational state as a string.
+
Possible values are:
+
"unknown", "notpresent", "down", "lowerlayerdown", "testing",
"dormant", "up".
diff --git a/Documentation/ABI/testing/sysfs-class-net-cdc_ncm b/Documentation/ABI/testing/sysfs-class-net-cdc_ncm
index f7be0e8..06416d0 100644
--- a/Documentation/ABI/testing/sysfs-class-net-cdc_ncm
+++ b/Documentation/ABI/testing/sysfs-class-net-cdc_ncm
@@ -91,9 +91,9 @@
KernelVersion: 3.16
Contact: Bjørn Mork <bjorn@mork.no>
Description:
- Bit 0: 16-bit NTB supported (set to 1)
- Bit 1: 32-bit NTB supported
- Bits 2 – 15: reserved (reset to zero; must be ignored by host)
+ - Bit 0: 16-bit NTB supported (set to 1)
+ - Bit 1: 32-bit NTB supported
+ - Bits 2 – 15: reserved (reset to zero; must be ignored by host)
What: /sys/class/net/<iface>/cdc_ncm/dwNtbInMaxSize
Date: May 2014
diff --git a/Documentation/ABI/testing/sysfs-class-net-phydev b/Documentation/ABI/testing/sysfs-class-net-phydev
index 206cbf5..40ced0e 100644
--- a/Documentation/ABI/testing/sysfs-class-net-phydev
+++ b/Documentation/ABI/testing/sysfs-class-net-phydev
@@ -35,7 +35,9 @@
Ethernet driver during bus enumeration, encoded in string.
This interface mode is used to configure the Ethernet MAC with the
appropriate mode for its data lines to the PHY hardware.
+
Possible values are:
+
<empty> (not available), mii, gmii, sgmii, tbi, rev-mii,
rmii, rgmii, rgmii-id, rgmii-rxid, rgmii-txid, rtbi, smii
xgmii, moca, qsgmii, trgmii, 1000base-x, 2500base-x, rxaui,
diff --git a/Documentation/ABI/testing/sysfs-class-ocxl b/Documentation/ABI/testing/sysfs-class-ocxl
index ae1276e..847a7ed 100644
--- a/Documentation/ABI/testing/sysfs-class-ocxl
+++ b/Documentation/ABI/testing/sysfs-class-ocxl
@@ -11,8 +11,11 @@
Description: read only
Number of contexts for the AFU, in the format <n>/<max>
where:
- n: number of currently active contexts, for debug
- max: maximum number of contexts supported by the AFU
+
+ ==== ===============================================
+ n number of currently active contexts, for debug
+ max maximum number of contexts supported by the AFU
+ ==== ===============================================
What: /sys/class/ocxl/<afu name>/pp_mmio_size
Date: January 2018
@@ -40,7 +43,9 @@
Description: read/write
Control whether the FPGA is reloaded on a link reset. Enabled
through a vendor-specific logic block on the FPGA.
- 0 Do not reload FPGA image from flash
- 1 Reload FPGA image from flash
- unavailable
- The device does not support this capability
+
+ =========== ===========================================
+ 0 Do not reload FPGA image from flash
+ 1 Reload FPGA image from flash
+ unavailable The device does not support this capability
+ =========== ===========================================
diff --git a/Documentation/ABI/testing/sysfs-class-pktcdvd b/Documentation/ABI/testing/sysfs-class-pktcdvd
index dde4f26..ba1ce62 100644
--- a/Documentation/ABI/testing/sysfs-class-pktcdvd
+++ b/Documentation/ABI/testing/sysfs-class-pktcdvd
@@ -11,15 +11,17 @@
Contact: Thomas Maier <balagi@justmail.de>
Description:
- add: (WO) Write a block device id (major:minor) to
+ ========== ==============================================
+ add (WO) Write a block device id (major:minor) to
create a new pktcdvd device and map it to the
block device.
- remove: (WO) Write the pktcdvd device id (major:minor)
+ remove (WO) Write the pktcdvd device id (major:minor)
to remove the pktcdvd device.
- device_map: (RO) Shows the device mapping in format:
+ device_map (RO) Shows the device mapping in format:
pktcdvd[0-7] <pktdevid> <blkdevid>
+ ========== ==============================================
What: /sys/class/pktcdvd/pktcdvd[0-7]/dev
@@ -65,29 +67,31 @@
KernelVersion: 2.6.20
Contact: Thomas Maier <balagi@justmail.de>
Description:
- size: (RO) Contains the size of the bio write queue.
+ ============== ================================================
+ size (RO) Contains the size of the bio write queue.
- congestion_off: (RW) If bio write queue size is below this mark,
+ congestion_off (RW) If bio write queue size is below this mark,
accept new bio requests from the block layer.
- congestion_on: (RW) If bio write queue size is higher as this
+ congestion_on (RW) If bio write queue size is higher as this
mark, do no longer accept bio write requests
from the block layer and wait till the pktcdvd
device has processed enough bio's so that bio
write queue size is below congestion off mark.
A value of <= 0 disables congestion control.
+ ============== ================================================
Example:
--------
-To use the pktcdvd sysfs interface directly, you can do:
+To use the pktcdvd sysfs interface directly, you can do::
-# create a new pktcdvd device mapped to /dev/hdc
-echo "22:0" >/sys/class/pktcdvd/add
-cat /sys/class/pktcdvd/device_map
-# assuming device pktcdvd0 was created, look at stat's
-cat /sys/class/pktcdvd/pktcdvd0/stat/kb_written
-# print the device id of the mapped block device
-fgrep pktcdvd0 /sys/class/pktcdvd/device_map
-# remove device, using pktcdvd0 device id 253:0
-echo "253:0" >/sys/class/pktcdvd/remove
+ # create a new pktcdvd device mapped to /dev/hdc
+ echo "22:0" >/sys/class/pktcdvd/add
+ cat /sys/class/pktcdvd/device_map
+ # assuming device pktcdvd0 was created, look at stat's
+ cat /sys/class/pktcdvd/pktcdvd0/stat/kb_written
+ # print the device id of the mapped block device
+ fgrep pktcdvd0 /sys/class/pktcdvd/device_map
+ # remove device, using pktcdvd0 device id 253:0
+ echo "253:0" >/sys/class/pktcdvd/remove
diff --git a/Documentation/ABI/testing/sysfs-class-power b/Documentation/ABI/testing/sysfs-class-power
index dbccb2f..ca830c6 100644
--- a/Documentation/ABI/testing/sysfs-class-power
+++ b/Documentation/ABI/testing/sysfs-class-power
@@ -1,4 +1,4 @@
-===== General Properties =====
+**General Properties**
What: /sys/class/power_supply/<supply_name>/manufacturer
Date: May 2007
@@ -36,14 +36,238 @@
Access: Read
Valid values: "Battery", "UPS", "Mains", "USB", "Wireless"
-===== Battery Properties =====
+**Battery and USB properties**
+
+What: /sys/class/power_supply/<supply_name>/current_avg
+Date: May 2007
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Reports an average IBAT current reading for the battery, over
+ a fixed period. Normally devices will provide a fixed interval
+ in which they average readings to smooth out the reported
+ value.
+
+ USB:
+
+ Reports an average IBUS current reading over a fixed period.
+ Normally devices will provide a fixed interval in which they
+ average readings to smooth out the reported value.
+
+ Access: Read
+
+ Valid values: Represented in microamps. Negative values are
+ used for discharging batteries, positive values for charging
+ batteries and for USB IBUS current.
+
+What: /sys/class/power_supply/<supply_name>/current_max
+Date: October 2010
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Reports the maximum IBAT current allowed into the battery.
+
+ USB:
+
+ Reports the maximum IBUS current the supply can support.
+
+ Access: Read
+ Valid values: Represented in microamps
+
+What: /sys/class/power_supply/<supply_name>/current_now
+Date: May 2007
+Contact: linux-pm@vger.kernel.org
+Description:
+
+ Battery:
+
+ Reports an instant, single IBAT current reading for the
+ battery. This value is not averaged/smoothed.
+
+ Access: Read
+
+ USB:
+
+ Reports the IBUS current supplied now. This value is generally
+ read-only reporting, unless the 'online' state of the supply
+ is set to be programmable, in which case this value can be set
+ within the reported min/max range.
+
+ Access: Read, Write
+
+ Valid values: Represented in microamps. Negative values are
+ used for discharging batteries, positive values for charging
+ batteries and for USB IBUS current.
+
+What: /sys/class/power_supply/<supply_name>/temp
+Date: May 2007
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Reports the current TBAT battery temperature reading.
+
+ USB:
+
+ Reports the current supply temperature reading. This would
+ normally be the internal temperature of the device itself
+ (e.g TJUNC temperature of an IC)
+
+ Access: Read
+
+ Valid values: Represented in 1/10 Degrees Celsius
+
+What: /sys/class/power_supply/<supply_name>/temp_alert_max
+Date: July 2012
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Maximum TBAT temperature trip-wire value where the supply will
+ notify user-space of the event.
+
+ USB:
+
+ Maximum supply temperature trip-wire value where the supply
+ will notify user-space of the event.
+
+ This is normally used for the charging scenario where
+ user-space needs to know if the temperature has crossed an
+ upper threshold so it can take appropriate action (e.g. warning
+ user that the temperature is critically high, and charging has
+ stopped).
+
+ Access: Read
+
+ Valid values: Represented in 1/10 Degrees Celsius
+
+What: /sys/class/power_supply/<supply_name>/temp_alert_min
+Date: July 2012
+Contact: linux-pm@vger.kernel.org
+Description:
+
+ Battery:
+
+ Minimum TBAT temperature trip-wire value where the supply will
+ notify user-space of the event.
+
+ USB:
+
+ Minimum supply temperature trip-wire value where the supply
+ will notify user-space of the event.
+
+ This is normally used for the charging scenario where user-space
+ needs to know if the temperature has crossed a lower threshold
+ so it can take appropriate action (e.g. warning user that
+ temperature level is high, and charging current has been
+ reduced accordingly to remedy the situation).
+
+ Access: Read
+
+ Valid values: Represented in 1/10 Degrees Celsius
+
+What: /sys/class/power_supply/<supply_name>/temp_max
+Date: July 2014
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Reports the maximum allowed TBAT battery temperature for
+ charging.
+
+ USB:
+
+ Reports the maximum allowed supply temperature for operation.
+
+ Access: Read
+
+ Valid values: Represented in 1/10 Degrees Celsius
+
+What: /sys/class/power_supply/<supply_name>/temp_min
+Date: July 2014
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Reports the minimum allowed TBAT battery temperature for
+ charging.
+
+ USB:
+
+ Reports the minimum allowed supply temperature for operation.
+
+ Access: Read
+
+ Valid values: Represented in 1/10 Degrees Celsius
+
+What: /sys/class/power_supply/<supply_name>/voltage_max,
+Date: January 2008
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Reports the maximum safe VBAT voltage permitted for the
+ battery, during charging.
+
+ USB:
+
+ Reports the maximum VBUS voltage the supply can support.
+
+ Access: Read
+
+ Valid values: Represented in microvolts
+
+What: /sys/class/power_supply/<supply_name>/voltage_min,
+Date: January 2008
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Reports the minimum safe VBAT voltage permitted for the
+ battery, during discharging.
+
+ USB:
+
+ Reports the minimum VBUS voltage the supply can support.
+
+ Access: Read
+
+ Valid values: Represented in microvolts
+
+What: /sys/class/power_supply/<supply_name>/voltage_now,
+Date: May 2007
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Reports an instant, single VBAT voltage reading for the
+ battery. This value is not averaged/smoothed.
+
+ Access: Read
+
+ USB:
+
+ Reports the VBUS voltage supplied now. This value is generally
+ read-only reporting, unless the 'online' state of the supply
+ is set to be programmable, in which case this value can be set
+ within the reported min/max range.
+
+ Access: Read, Write
+
+ Valid values: Represented in microvolts
+
+**Battery Properties**
What: /sys/class/power_supply/<supply_name>/capacity
Date: May 2007
Contact: linux-pm@vger.kernel.org
Description:
Fine grain representation of battery capacity.
+
Access: Read
+
Valid values: 0 - 100 (percent)
What: /sys/class/power_supply/<supply_name>/capacity_alert_max
@@ -58,6 +282,7 @@
low).
Access: Read, Write
+
Valid values: 0 - 100 (percent)
What: /sys/class/power_supply/<supply_name>/capacity_alert_min
@@ -72,6 +297,7 @@
critically low).
Access: Read, Write
+
Valid values: 0 - 100 (percent)
What: /sys/class/power_supply/<supply_name>/capacity_error_margin
@@ -87,6 +313,7 @@
completely useless.
Access: Read
+
Valid values: 0 - 100 (percent)
What: /sys/class/power_supply/<supply_name>/capacity_level
@@ -96,41 +323,11 @@
Coarse representation of battery capacity.
Access: Read
- Valid values: "Unknown", "Critical", "Low", "Normal", "High",
+
+ Valid values:
+ "Unknown", "Critical", "Low", "Normal", "High",
"Full"
-What: /sys/class/power_supply/<supply_name>/current_avg
-Date: May 2007
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports an average IBAT current reading for the battery, over a
- fixed period. Normally devices will provide a fixed interval in
- which they average readings to smooth out the reported value.
-
- Access: Read
- Valid values: Represented in microamps. Negative values are used
- for discharging batteries, positive values for charging batteries.
-
-What: /sys/class/power_supply/<supply_name>/current_max
-Date: October 2010
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the maximum IBAT current allowed into the battery.
-
- Access: Read
- Valid values: Represented in microamps
-
-What: /sys/class/power_supply/<supply_name>/current_now
-Date: May 2007
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports an instant, single IBAT current reading for the battery.
- This value is not averaged/smoothed.
-
- Access: Read
- Valid values: Represented in microamps. Negative values are used
- for discharging batteries, positive values for charging batteries.
-
What: /sys/class/power_supply/<supply_name>/charge_control_limit
Date: Oct 2012
Contact: linux-pm@vger.kernel.org
@@ -139,6 +336,7 @@
throttling for thermal cooling or improving battery health.
Access: Read, Write
+
Valid values: Represented in microamps
What: /sys/class/power_supply/<supply_name>/charge_control_limit_max
@@ -148,6 +346,7 @@
Maximum legal value for the charge_control_limit property.
Access: Read
+
Valid values: Represented in microamps
What: /sys/class/power_supply/<supply_name>/charge_control_start_threshold
@@ -168,6 +367,7 @@
stop.
Access: Read, Write
+
Valid values: 0 - 100 (percent)
What: /sys/class/power_supply/<supply_name>/charge_type
@@ -183,7 +383,9 @@
different algorithm.
Access: Read, Write
- Valid values: "Unknown", "N/A", "Trickle", "Fast", "Standard",
+
+ Valid values:
+ "Unknown", "N/A", "Trickle", "Fast", "Standard",
"Adaptive", "Custom"
What: /sys/class/power_supply/<supply_name>/charge_term_current
@@ -194,6 +396,7 @@
when the battery is considered full and charging should end.
Access: Read
+
Valid values: Represented in microamps
What: /sys/class/power_supply/<supply_name>/health
@@ -204,7 +407,9 @@
functionality.
Access: Read
- Valid values: "Unknown", "Good", "Overheat", "Dead",
+
+ Valid values:
+ "Unknown", "Good", "Overheat", "Dead",
"Over voltage", "Unspecified failure", "Cold",
"Watchdog timer expire", "Safety timer expire",
"Over current", "Calibration required", "Warm",
@@ -218,6 +423,7 @@
for a battery charge cycle.
Access: Read
+
Valid values: Represented in microamps
What: /sys/class/power_supply/<supply_name>/present
@@ -227,9 +433,13 @@
Reports whether a battery is present or not in the system.
Access: Read
+
Valid values:
+
+ == =======
0: Absent
1: Present
+ == =======
What: /sys/class/power_supply/<supply_name>/status
Date: May 2007
@@ -240,7 +450,9 @@
used to enable/disable charging to the battery.
Access: Read, Write
- Valid values: "Unknown", "Charging", "Discharging",
+
+ Valid values:
+ "Unknown", "Charging", "Discharging",
"Not charging", "Full"
What: /sys/class/power_supply/<supply_name>/technology
@@ -250,66 +462,11 @@
Describes the battery technology supported by the supply.
Access: Read
- Valid values: "Unknown", "NiMH", "Li-ion", "Li-poly", "LiFe",
+
+ Valid values:
+ "Unknown", "NiMH", "Li-ion", "Li-poly", "LiFe",
"NiCd", "LiMn"
-What: /sys/class/power_supply/<supply_name>/temp
-Date: May 2007
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the current TBAT battery temperature reading.
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
-
-What: /sys/class/power_supply/<supply_name>/temp_alert_max
-Date: July 2012
-Contact: linux-pm@vger.kernel.org
-Description:
- Maximum TBAT temperature trip-wire value where the supply will
- notify user-space of the event. This is normally used for the
- battery charging scenario where user-space needs to know the
- battery temperature has crossed an upper threshold so it can
- take appropriate action (e.g. warning user that battery level is
- critically high, and charging has stopped).
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
-
-What: /sys/class/power_supply/<supply_name>/temp_alert_min
-Date: July 2012
-Contact: linux-pm@vger.kernel.org
-Description:
- Minimum TBAT temperature trip-wire value where the supply will
- notify user-space of the event. This is normally used for the
- battery charging scenario where user-space needs to know the
- battery temperature has crossed a lower threshold so it can take
- appropriate action (e.g. warning user that battery level is
- high, and charging current has been reduced accordingly to
- remedy the situation).
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
-
-What: /sys/class/power_supply/<supply_name>/temp_max
-Date: July 2014
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the maximum allowed TBAT battery temperature for
- charging.
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
-
-What: /sys/class/power_supply/<supply_name>/temp_min
-Date: July 2014
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the minimum allowed TBAT battery temperature for
- charging.
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
What: /sys/class/power_supply/<supply_name>/voltage_avg,
Date: May 2007
@@ -320,72 +477,10 @@
which they average readings to smooth out the reported value.
Access: Read
+
Valid values: Represented in microvolts
-What: /sys/class/power_supply/<supply_name>/voltage_max,
-Date: January 2008
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the maximum safe VBAT voltage permitted for the battery,
- during charging.
-
- Access: Read
- Valid values: Represented in microvolts
-
-What: /sys/class/power_supply/<supply_name>/voltage_min,
-Date: January 2008
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the minimum safe VBAT voltage permitted for the battery,
- during discharging.
-
- Access: Read
- Valid values: Represented in microvolts
-
-What: /sys/class/power_supply/<supply_name>/voltage_now,
-Date: May 2007
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports an instant, single VBAT voltage reading for the battery.
- This value is not averaged/smoothed.
-
- Access: Read
- Valid values: Represented in microvolts
-
-===== USB Properties =====
-
-What: /sys/class/power_supply/<supply_name>/current_avg
-Date: May 2007
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports an average IBUS current reading over a fixed period.
- Normally devices will provide a fixed interval in which they
- average readings to smooth out the reported value.
-
- Access: Read
- Valid values: Represented in microamps
-
-
-What: /sys/class/power_supply/<supply_name>/current_max
-Date: October 2010
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the maximum IBUS current the supply can support.
-
- Access: Read
- Valid values: Represented in microamps
-
-What: /sys/class/power_supply/<supply_name>/current_now
-Date: May 2007
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the IBUS current supplied now. This value is generally
- read-only reporting, unless the 'online' state of the supply
- is set to be programmable, in which case this value can be set
- within the reported min/max range.
-
- Access: Read, Write
- Valid values: Represented in microamps
+**USB Properties**
What: /sys/class/power_supply/<supply_name>/input_current_limit
Date: July 2014
@@ -399,6 +494,7 @@
solved using power limit use input_current_limit.
Access: Read, Write
+
Valid values: Represented in microamps
What: /sys/class/power_supply/<supply_name>/input_voltage_limit
@@ -416,6 +512,7 @@
solved using power limit use input_voltage_limit.
Access: Read, Write
+
Valid values: Represented in microvolts
What: /sys/class/power_supply/<supply_name>/input_power_limit
@@ -429,6 +526,7 @@
limit only for problems that can be solved using power limit.
Access: Read, Write
+
Valid values: Represented in microwatts
What: /sys/class/power_supply/<supply_name>/online,
@@ -441,69 +539,14 @@
USB supply so voltage and current can be controlled).
Access: Read, Write
+
Valid values:
+
+ == ==================================================
0: Offline
1: Online Fixed - Fixed Voltage Supply
2: Online Programmable - Programmable Voltage Supply
-
-What: /sys/class/power_supply/<supply_name>/temp
-Date: May 2007
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the current supply temperature reading. This would
- normally be the internal temperature of the device itself (e.g
- TJUNC temperature of an IC)
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
-
-What: /sys/class/power_supply/<supply_name>/temp_alert_max
-Date: July 2012
-Contact: linux-pm@vger.kernel.org
-Description:
- Maximum supply temperature trip-wire value where the supply will
- notify user-space of the event. This is normally used for the
- charging scenario where user-space needs to know the supply
- temperature has crossed an upper threshold so it can take
- appropriate action (e.g. warning user that the supply
- temperature is critically high, and charging has stopped to
- remedy the situation).
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
-
-What: /sys/class/power_supply/<supply_name>/temp_alert_min
-Date: July 2012
-Contact: linux-pm@vger.kernel.org
-Description:
- Minimum supply temperature trip-wire value where the supply will
- notify user-space of the event. This is normally used for the
- charging scenario where user-space needs to know the supply
- temperature has crossed a lower threshold so it can take
- appropriate action (e.g. warning user that the supply
- temperature is high, and charging current has been reduced
- accordingly to remedy the situation).
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
-
-What: /sys/class/power_supply/<supply_name>/temp_max
-Date: July 2014
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the maximum allowed supply temperature for operation.
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
-
-What: /sys/class/power_supply/<supply_name>/temp_min
-Date: July 2014
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the mainimum allowed supply temperature for operation.
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
+ == ==================================================
What: /sys/class/power_supply/<supply_name>/usb_type
Date: March 2018
@@ -514,40 +557,12 @@
is attached.
Access: Read-Only
- Valid values: "Unknown", "SDP", "DCP", "CDP", "ACA", "C", "PD",
+
+ Valid values:
+ "Unknown", "SDP", "DCP", "CDP", "ACA", "C", "PD",
"PD_DRP", "PD_PPS", "BrickID"
-What: /sys/class/power_supply/<supply_name>/voltage_max
-Date: January 2008
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the maximum VBUS voltage the supply can support.
-
- Access: Read
- Valid values: Represented in microvolts
-
-What: /sys/class/power_supply/<supply_name>/voltage_min
-Date: January 2008
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the minimum VBUS voltage the supply can support.
-
- Access: Read
- Valid values: Represented in microvolts
-
-What: /sys/class/power_supply/<supply_name>/voltage_now
-Date: May 2007
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the VBUS voltage supplied now. This value is generally
- read-only reporting, unless the 'online' state of the supply
- is set to be programmable, in which case this value can be set
- within the reported min/max range.
-
- Access: Read, Write
- Valid values: Represented in microvolts
-
-===== Device Specific Properties =====
+**Device Specific Properties**
What: /sys/class/power/ds2760-battery.*/charge_now
Date: May 2010
@@ -581,6 +596,7 @@
will drop to 0 A) and will trigger interrupt.
Valid values:
+
- 5, 6 or 7 (hours),
- 0: disabled.
@@ -595,6 +611,7 @@
will drop to 0 A) and will trigger interrupt.
Valid values:
+
- 4 - 16 (hours), step by 2 (rounded down)
- 0: disabled.
@@ -609,6 +626,7 @@
interrupt and start top-off charging mode.
Valid values:
+
- 100000 - 200000 (microamps), step by 25000 (rounded down)
- 200000 - 350000 (microamps), step by 50000 (rounded down)
- 0: disabled.
@@ -624,6 +642,7 @@
will drop to 0 A) and will trigger interrupt.
Valid values:
+
- 0 - 70 (minutes), step by 10 (rounded down)
What: /sys/class/power_supply/bq24257-charger/ovp_voltage
@@ -637,6 +656,7 @@
device datasheet for details.
Valid values:
+
- 6000000, 6500000, 7000000, 8000000, 9000000, 9500000, 10000000,
10500000 (all uV)
@@ -652,6 +672,7 @@
lower than the set value. See device datasheet for details.
Valid values:
+
- 4200000, 4280000, 4360000, 4440000, 4520000, 4600000, 4680000,
4760000 (all uV)
@@ -666,6 +687,7 @@
the charger operates normally. See device datasheet for details.
Valid values:
+
- 1: enabled
- 0: disabled
@@ -681,6 +703,7 @@
from the system. See device datasheet for details.
Valid values:
+
- 1: enabled
- 0: disabled
@@ -692,6 +715,7 @@
manufactured.
Access: Read
+
Valid values: Reported as integer
What: /sys/class/power_supply/<supply_name>/manufacture_month
@@ -701,6 +725,7 @@
Reports the month when the device has been manufactured.
Access: Read
+
Valid values: 1-12
What: /sys/class/power_supply/<supply_name>/manufacture_day
diff --git a/Documentation/ABI/testing/sysfs-class-power-mp2629 b/Documentation/ABI/testing/sysfs-class-power-mp2629
index 327a07e..914d67c 100644
--- a/Documentation/ABI/testing/sysfs-class-power-mp2629
+++ b/Documentation/ABI/testing/sysfs-class-power-mp2629
@@ -5,4 +5,5 @@
Represents a battery impedance compensation to accelerate charging.
Access: Read, Write
+
Valid values: Represented in milli-ohms. Valid range is [0, 140].
diff --git a/Documentation/ABI/testing/sysfs-class-power-twl4030 b/Documentation/ABI/testing/sysfs-class-power-twl4030
index b4fd32d..b52f702 100644
--- a/Documentation/ABI/testing/sysfs-class-power-twl4030
+++ b/Documentation/ABI/testing/sysfs-class-power-twl4030
@@ -4,18 +4,20 @@
Writing to this can disable charging.
Possible values are:
- "auto" - draw power as appropriate for detected
- power source and battery status.
- "off" - do not draw any power.
- "continuous"
- - activate mode described as "linear" in
- TWL data sheets. This uses whatever
- current is available and doesn't switch off
- when voltage drops.
- This is useful for unstable power sources
- such as bicycle dynamo, but care should
- be taken that battery is not over-charged.
+ ============= ===========================================
+ "auto" draw power as appropriate for detected
+ power source and battery status.
+ "off" do not draw any power.
+ "continuous" activate mode described as "linear" in
+ TWL data sheets. This uses whatever
+ current is available and doesn't switch off
+ when voltage drops.
+
+ This is useful for unstable power sources
+ such as bicycle dynamo, but care should
+ be taken that battery is not over-charged.
+ ============= ===========================================
What: /sys/class/power_supply/twl4030_ac/mode
Description:
@@ -23,6 +25,9 @@
Writing to this can disable charging.
Possible values are:
- "auto" - draw power as appropriate for detected
- power source and battery status.
- "off" - do not draw any power.
+
+ ====== ===========================================
+ "auto" draw power as appropriate for detected
+ power source and battery status.
+ "off" do not draw any power.
+ ====== ===========================================
diff --git a/Documentation/ABI/testing/sysfs-class-power-wilco b/Documentation/ABI/testing/sysfs-class-power-wilco
index 84fde1d..82af180f 100644
--- a/Documentation/ABI/testing/sysfs-class-power-wilco
+++ b/Documentation/ABI/testing/sysfs-class-power-wilco
@@ -4,17 +4,23 @@
Description:
What charging algorithm to use:
- Standard: Fully charges battery at a standard rate.
- Adaptive: Battery settings adaptively optimized based on
+ Standard:
+ Fully charges battery at a standard rate.
+ Adaptive:
+ Battery settings adaptively optimized based on
typical battery usage pattern.
- Fast: Battery charges over a shorter period.
- Trickle: Extends battery lifespan, intended for users who
+ Fast:
+ Battery charges over a shorter period.
+ Trickle:
+ Extends battery lifespan, intended for users who
primarily use their Chromebook while connected to AC.
- Custom: A low and high threshold percentage is specified.
+ Custom:
+ A low and high threshold percentage is specified.
Charging begins when level drops below
charge_control_start_threshold, and ceases when
level is above charge_control_end_threshold.
- Long Life: Customized charge rate for last longer battery life.
+ Long Life:
+ Customized charge rate for last longer battery life.
On Wilco device this mode is pre-configured in the factory
through EC's private PID. Swiching to a different mode will
be denied by Wilco EC when Long Life mode is enabled.
diff --git a/Documentation/ABI/testing/sysfs-class-rapidio b/Documentation/ABI/testing/sysfs-class-rapidio
index 8716bee..19aefb2 100644
--- a/Documentation/ABI/testing/sysfs-class-rapidio
+++ b/Documentation/ABI/testing/sysfs-class-rapidio
@@ -6,6 +6,7 @@
The /sys/class/rapidio_port subdirectory contains individual
subdirectories named as "rapidioN" where N = mport ID registered
with RapidIO subsystem.
+
NOTE: An mport ID is not a RapidIO destination ID assigned to a
given local mport device.
@@ -16,7 +17,9 @@
Alexandre Bounine <alexandre.bounine@idt.com>
Description:
(RO) reports RapidIO common transport system size:
+
0 = small (8-bit destination ID, max. 256 devices),
+
1 = large (16-bit destination ID, max. 65536 devices).
What: /sys/class/rapidio_port/rapidioN/port_destid
@@ -25,31 +28,32 @@
Contact: Matt Porter <mporter@kernel.crashing.org>,
Alexandre Bounine <alexandre.bounine@idt.com>
Description:
- (RO) reports RapidIO destination ID assigned to the given
- RapidIO mport device. If value 0xFFFFFFFF is returned this means
- that no valid destination ID have been assigned to the mport
- (yet). Normally, before enumeration/discovery have been executed
- only fabric enumerating mports have a valid destination ID
- assigned to them using "hdid=..." rapidio module parameter.
+
+(RO) reports RapidIO destination ID assigned to the given
+RapidIO mport device. If value 0xFFFFFFFF is returned this means
+that no valid destination ID have been assigned to the mport
+(yet). Normally, before enumeration/discovery have been executed
+only fabric enumerating mports have a valid destination ID
+assigned to them using "hdid=..." rapidio module parameter.
After enumeration or discovery was performed for a given mport device,
the corresponding subdirectory will also contain subdirectories for each
child RapidIO device connected to the mport.
The example below shows mport device subdirectory with several child RapidIO
-devices attached to it.
+devices attached to it::
-[rio@rapidio ~]$ ls /sys/class/rapidio_port/rapidio0/ -l
-total 0
-drwxr-xr-x 3 root root 0 Feb 11 15:10 00:e:0001
-drwxr-xr-x 3 root root 0 Feb 11 15:10 00:e:0004
-drwxr-xr-x 3 root root 0 Feb 11 15:10 00:e:0007
-drwxr-xr-x 3 root root 0 Feb 11 15:10 00:s:0002
-drwxr-xr-x 3 root root 0 Feb 11 15:10 00:s:0003
-drwxr-xr-x 3 root root 0 Feb 11 15:10 00:s:0005
-lrwxrwxrwx 1 root root 0 Feb 11 15:11 device -> ../../../0000:01:00.0
--r--r--r-- 1 root root 4096 Feb 11 15:11 port_destid
-drwxr-xr-x 2 root root 0 Feb 11 15:11 power
-lrwxrwxrwx 1 root root 0 Feb 11 15:04 subsystem -> ../../../../../../class/rapidio_port
--r--r--r-- 1 root root 4096 Feb 11 15:11 sys_size
--rw-r--r-- 1 root root 4096 Feb 11 15:04 uevent
+ [rio@rapidio ~]$ ls /sys/class/rapidio_port/rapidio0/ -l
+ total 0
+ drwxr-xr-x 3 root root 0 Feb 11 15:10 00:e:0001
+ drwxr-xr-x 3 root root 0 Feb 11 15:10 00:e:0004
+ drwxr-xr-x 3 root root 0 Feb 11 15:10 00:e:0007
+ drwxr-xr-x 3 root root 0 Feb 11 15:10 00:s:0002
+ drwxr-xr-x 3 root root 0 Feb 11 15:10 00:s:0003
+ drwxr-xr-x 3 root root 0 Feb 11 15:10 00:s:0005
+ lrwxrwxrwx 1 root root 0 Feb 11 15:11 device -> ../../../0000:01:00.0
+ -r--r--r-- 1 root root 4096 Feb 11 15:11 port_destid
+ drwxr-xr-x 2 root root 0 Feb 11 15:11 power
+ lrwxrwxrwx 1 root root 0 Feb 11 15:04 subsystem -> ../../../../../../class/rapidio_port
+ -r--r--r-- 1 root root 4096 Feb 11 15:11 sys_size
+ -rw-r--r-- 1 root root 4096 Feb 11 15:04 uevent
diff --git a/Documentation/ABI/testing/sysfs-class-rc b/Documentation/ABI/testing/sysfs-class-rc
index 6c0d6c8..9c8ff79 100644
--- a/Documentation/ABI/testing/sysfs-class-rc
+++ b/Documentation/ABI/testing/sysfs-class-rc
@@ -21,15 +21,22 @@
Contact: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Description:
Reading this file returns a list of available protocols,
- something like:
+ something like::
+
"rc5 [rc6] nec jvc [sony]"
+
Enabled protocols are shown in [] brackets.
+
Writing "+proto" will add a protocol to the list of enabled
protocols.
+
Writing "-proto" will remove a protocol from the list of enabled
protocols.
+
Writing "proto" will enable only "proto".
+
Writing "none" will disable all protocols.
+
Write fails with EINVAL if an invalid protocol combination or
unknown protocol name is used.
@@ -39,11 +46,13 @@
Contact: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Description:
Sets the scancode filter expected value.
+
Use in combination with /sys/class/rc/rcN/filter_mask to set the
expected value of the bits set in the filter mask.
If the hardware supports it then scancodes which do not match
the filter will be ignored. Otherwise the write will fail with
an error.
+
This value may be reset to 0 if the current protocol is altered.
What: /sys/class/rc/rcN/filter_mask
@@ -56,9 +65,11 @@
of the scancode which should be compared against the expected
value. A value of 0 disables the filter to allow all valid
scancodes to be processed.
+
If the hardware supports it then scancodes which do not match
the filter will be ignored. Otherwise the write will fail with
an error.
+
This value may be reset to 0 if the current protocol is altered.
What: /sys/class/rc/rcN/wakeup_protocols
@@ -67,15 +78,22 @@
Contact: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Description:
Reading this file returns a list of available protocols to use
- for the wakeup filter, something like:
+ for the wakeup filter, something like::
+
"rc-5 nec nec-x rc-6-0 rc-6-6a-24 [rc-6-6a-32] rc-6-mce"
+
Note that protocol variants are listed, so "nec", "sony",
"rc-5", "rc-6" have their different bit length encodings
listed if available.
+
The enabled wakeup protocol is shown in [] brackets.
+
Only one protocol can be selected at a time.
+
Writing "proto" will use "proto" for wakeup events.
+
Writing "none" will disable wakeup.
+
Write fails with EINVAL if an invalid protocol combination or
unknown protocol name is used, or if wakeup is not supported by
the hardware.
@@ -86,13 +104,17 @@
Contact: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Description:
Sets the scancode wakeup filter expected value.
+
Use in combination with /sys/class/rc/rcN/wakeup_filter_mask to
set the expected value of the bits set in the wakeup filter mask
to trigger a system wake event.
+
If the hardware supports it and wakeup_filter_mask is not 0 then
scancodes which match the filter will wake the system from e.g.
suspend to RAM or power off.
+
Otherwise the write will fail with an error.
+
This value may be reset to 0 if the wakeup protocol is altered.
What: /sys/class/rc/rcN/wakeup_filter_mask
@@ -101,11 +123,15 @@
Contact: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Description:
Sets the scancode wakeup filter mask of bits to compare.
+
Use in combination with /sys/class/rc/rcN/wakeup_filter to set
the bits of the scancode which should be compared against the
expected value to trigger a system wake event.
+
If the hardware supports it and wakeup_filter_mask is not 0 then
scancodes which match the filter will wake the system from e.g.
suspend to RAM or power off.
+
Otherwise the write will fail with an error.
+
This value may be reset to 0 if the wakeup protocol is altered.
diff --git a/Documentation/ABI/testing/sysfs-class-regulator b/Documentation/ABI/testing/sysfs-class-regulator
index bc578bc..8516f08 100644
--- a/Documentation/ABI/testing/sysfs-class-regulator
+++ b/Documentation/ABI/testing/sysfs-class-regulator
@@ -35,13 +35,13 @@
This will be one of the following strings:
- off
- on
- error
- fast
- normal
- idle
- standby
+ - off
+ - on
+ - error
+ - fast
+ - normal
+ - idle
+ - standby
"off" means the regulator is not supplying power to the
system.
@@ -74,9 +74,9 @@
This will be one of the following strings:
- 'voltage'
- 'current'
- 'unknown'
+ - 'voltage'
+ - 'current'
+ - 'unknown'
'voltage' means the regulator output voltage can be controlled
by software.
@@ -129,11 +129,11 @@
The opmode value can be one of the following strings:
- 'fast'
- 'normal'
- 'idle'
- 'standby'
- 'unknown'
+ - 'fast'
+ - 'normal'
+ - 'idle'
+ - 'standby'
+ - 'unknown'
The modes are described in include/linux/regulator/consumer.h
@@ -360,9 +360,9 @@
This will be one of the following strings:
- 'enabled'
- 'disabled'
- 'unknown'
+ - 'enabled'
+ - 'disabled'
+ - 'unknown'
'enabled' means the regulator is in bypass mode.
diff --git a/Documentation/ABI/testing/sysfs-class-remoteproc b/Documentation/ABI/testing/sysfs-class-remoteproc
index 066b9b6..0c9ee55 100644
--- a/Documentation/ABI/testing/sysfs-class-remoteproc
+++ b/Documentation/ABI/testing/sysfs-class-remoteproc
@@ -16,11 +16,11 @@
Reports the state of the remote processor, which will be one of:
- "offline"
- "suspended"
- "running"
- "crashed"
- "invalid"
+ - "offline"
+ - "suspended"
+ - "running"
+ - "crashed"
+ - "invalid"
"offline" means the remote processor is powered off.
@@ -38,8 +38,8 @@
Writing this file controls the state of the remote processor.
The following states can be written:
- "start"
- "stop"
+ - "start"
+ - "stop"
Writing "start" will attempt to start the processor running the
firmware indicated by, or written to,
diff --git a/Documentation/ABI/testing/sysfs-class-rnbd-client b/Documentation/ABI/testing/sysfs-class-rnbd-client
index c084f20..00c0286 100644
--- a/Documentation/ABI/testing/sysfs-class-rnbd-client
+++ b/Documentation/ABI/testing/sysfs-class-rnbd-client
@@ -5,62 +5,70 @@
Description: Provide information about RNBD-client.
All sysfs files that are not read-only provide the usage information on read:
- Example:
- # cat /sys/class/rnbd-client/ctl/map_device
+ Example::
- > Usage: echo "sessname=<name of the rtrs session> path=<[srcaddr,]dstaddr>
- > [path=<[srcaddr,]dstaddr>] device_path=<full path on remote side>
- > [access_mode=<ro|rw|migration>] > map_device
- >
- > addr ::= [ ip:<ipv4> | ip:<ipv6> | gid:<gid> ]
+ # cat /sys/class/rnbd-client/ctl/map_device
+
+ > Usage: echo "sessname=<name of the rtrs session> path=<[srcaddr,]dstaddr>
+ > [path=<[srcaddr,]dstaddr>] device_path=<full path on remote side>
+ > [access_mode=<ro|rw|migration>] > map_device
+ >
+ > addr ::= [ ip:<ipv4> | ip:<ipv6> | gid:<gid> ]
What: /sys/class/rnbd-client/ctl/map_device
Date: Feb 2020
KernelVersion: 5.7
Contact: Jack Wang <jinpu.wang@cloud.ionos.com> Danil Kipnis <danil.kipnis@cloud.ionos.com>
-Description: Expected format is the following:
+Description: Expected format is the following::
- sessname=<name of the rtrs session>
- path=<[srcaddr,]dstaddr> [path=<[srcaddr,]dstaddr> ...]
- device_path=<full path on remote side>
- [access_mode=<ro|rw|migration>]
+ sessname=<name of the rtrs session>
+ path=<[srcaddr,]dstaddr> [path=<[srcaddr,]dstaddr> ...]
+ device_path=<full path on remote side>
+ [access_mode=<ro|rw|migration>]
Where:
- sessname: accepts a string not bigger than 256 chars, which identifies
- a given session on the client and on the server.
- I.e. "clt_hostname-srv_hostname" could be a natural choice.
+ sessname:
+ accepts a string not bigger than 256 chars, which identifies
+ a given session on the client and on the server.
+ I.e. "clt_hostname-srv_hostname" could be a natural choice.
- path: describes a connection between the client and the server by
- specifying destination and, when required, the source address.
- The addresses are to be provided in the following format:
+ path:
+ describes a connection between the client and the server by
+ specifying destination and, when required, the source address.
+ The addresses are to be provided in the following format::
- ip:<IPv6>
- ip:<IPv4>
- gid:<GID>
+ ip:<IPv6>
+ ip:<IPv4>
+ gid:<GID>
- for example:
+ for example::
- path=ip:10.0.0.66
+ path=ip:10.0.0.66
+
The single addr is treated as the destination.
The connection will be established to this server from any client IP address.
- path=ip:10.0.0.66,ip:10.0.1.66
+ ::
+
+ path=ip:10.0.0.66,ip:10.0.1.66
+
First addr is the source address and the second is the destination.
If multiple "path=" options are specified multiple connection
will be established and data will be sent according to
the selected multipath policy (see RTRS mp_policy sysfs entry description).
- device_path: Path to the block device on the server side. Path is specified
- relative to the directory on server side configured in the
- 'dev_search_path' module parameter of the rnbd_server.
- The rnbd_server prepends the <device_path> received from client
- with <dev_search_path> and tries to open the
- <dev_search_path>/<device_path> block device. On success,
- a /dev/rnbd<N> device file, a /sys/block/rnbd_client/rnbd<N>/
- directory and an entry in /sys/class/rnbd-client/ctl/devices
- will be created.
+ device_path:
+ Path to the block device on the server side. Path is specified
+ relative to the directory on server side configured in the
+ 'dev_search_path' module parameter of the rnbd_server.
+ The rnbd_server prepends the <device_path> received from client
+ with <dev_search_path> and tries to open the
+ <dev_search_path>/<device_path> block device. On success,
+ a /dev/rnbd<N> device file, a /sys/block/rnbd_client/rnbd<N>/
+ directory and an entry in /sys/class/rnbd-client/ctl/devices
+ will be created.
If 'dev_search_path' contains '%SESSNAME%', then each session can
have different devices namespace, e.g. server was configured with
@@ -68,11 +76,12 @@
client has this string "sessname=blya device_path=sda", then server
will try to open: /run/rnbd-devs/blya/sda.
- access_mode: the access_mode parameter specifies if the device is to be
- mapped as "ro" read-only or "rw" read-write. The server allows
- a device to be exported in rw mode only once. The "migration"
- access mode has to be specified if a second mapping in read-write
- mode is desired.
+ access_mode:
+ the access_mode parameter specifies if the device is to be
+ mapped as "ro" read-only or "rw" read-write. The server allows
+ a device to be exported in rw mode only once. The "migration"
+ access mode has to be specified if a second mapping in read-write
+ mode is desired.
By default "rw" is used.
@@ -91,7 +100,7 @@
is the same as the device name. By extracting the last part of the
path the path to the device /dev/<dev-name> can be build.
- o /dev/block/$(cat /sys/class/rnbd-client/ctl/devices/<device_id>/dev)
+ * /dev/block/$(cat /sys/class/rnbd-client/ctl/devices/<device_id>/dev)
How to find the <device_id> of the device is described on the next
section.
@@ -106,6 +115,6 @@
The <device_id> of each device is created as follows:
- If the 'device_path' provided during mapping contains slashes ("/"),
- they are replaced by exclamation mark ("!") and used as as the
- <device_id>. Otherwise, the <device_id> will be the same as the
- "device_path" provided.
+ they are replaced by exclamation mark ("!") and used as as the
+ <device_id>. Otherwise, the <device_id> will be the same as the
+ "device_path" provided.
diff --git a/Documentation/ABI/testing/sysfs-class-rtc-rtc0-device-rtc_calibration b/Documentation/ABI/testing/sysfs-class-rtc-rtc0-device-rtc_calibration
index ec950c9..ee8ed64 100644
--- a/Documentation/ABI/testing/sysfs-class-rtc-rtc0-device-rtc_calibration
+++ b/Documentation/ABI/testing/sysfs-class-rtc-rtc0-device-rtc_calibration
@@ -7,6 +7,7 @@
calibrate the AB8500.s 32KHz Real Time Clock.
Every 60 seconds the AB8500 will correct the RTC's value
by adding to it the value of this attribute.
+
The range of the attribute is -127 to +127 in units of
30.5 micro-seconds (half-parts-per-million of the 32KHz clock)
Users: The /vendor/st-ericsson/base_utilities/core/rtc_calibration
diff --git a/Documentation/ABI/testing/sysfs-class-rtrs-client b/Documentation/ABI/testing/sysfs-class-rtrs-client
index e7e718d..0f7165a 100644
--- a/Documentation/ABI/testing/sysfs-class-rtrs-client
+++ b/Documentation/ABI/testing/sysfs-class-rtrs-client
@@ -10,10 +10,10 @@
KernelVersion: 5.7
Contact: Jack Wang <jinpu.wang@cloud.ionos.com> Danil Kipnis <danil.kipnis@cloud.ionos.com>
Description: RW, adds a new path (connection) to an existing session. Expected format is the
- following:
+ following::
- <[source addr,]destination addr>
- *addr ::= [ ip:<ipv4|ipv6> | gid:<gid> ]
+ <[source addr,]destination addr>
+ *addr ::= [ ip:<ipv4|ipv6> | gid:<gid> ]
What: /sys/class/rtrs-client/<session-name>/max_reconnect_attempts
Date: Feb 2020
@@ -29,10 +29,10 @@
Description: Multipath policy specifies which path should be selected on each IO:
round-robin (0):
- select path in per CPU round-robin manner.
+ select path in per CPU round-robin manner.
min-inflight (1):
- select path with minimum inflights.
+ select path with minimum inflights.
What: /sys/class/rtrs-client/<session-name>/paths/
Date: Feb 2020
@@ -109,8 +109,11 @@
not the case, the processing of an I/O response could be processed on a
different CPU than where it was originally submitted. This file shows
how many interrupts where generated on a non expected CPU.
- "from:" is the CPU on which the IRQ was expected, but not generated.
- "to:" is the CPU on which the IRQ was generated, but not expected.
+
+ "from:"
+ is the CPU on which the IRQ was expected, but not generated.
+ "to:"
+ is the CPU on which the IRQ was generated, but not expected.
What: /sys/class/rtrs-client/<session-name>/paths/<src@dst>/stats/reconnects
Date: Feb 2020
@@ -125,7 +128,7 @@
KernelVersion: 5.7
Contact: Jack Wang <jinpu.wang@cloud.ionos.com> Danil Kipnis <danil.kipnis@cloud.ionos.com>
Description: Contains statistics regarding rdma operations and inflight operations.
- The output consists of 6 values:
+ The output consists of 6 values::
- <read-count> <read-total-size> <write-count> <write-total-size> \
- <inflights> <failovered>
+ <read-count> <read-total-size> <write-count> \
+ <write-total-size> <inflights> <failovered>
diff --git a/Documentation/ABI/testing/sysfs-class-scsi_host b/Documentation/ABI/testing/sysfs-class-scsi_host
index bafc59f..7c98d8f 100644
--- a/Documentation/ABI/testing/sysfs-class-scsi_host
+++ b/Documentation/ABI/testing/sysfs-class-scsi_host
@@ -56,8 +56,9 @@
management) on top, which makes it match the Windows IRST (Intel
Rapid Storage Technology) driver settings. This setting is also
close to min_power, except that:
+
a) It does not use host-initiated slumber mode, but it does
- allow device-initiated slumber
+ allow device-initiated slumber
b) It does not enable low power device sleep mode (DevSlp).
What: /sys/class/scsi_host/hostX/em_message
@@ -70,8 +71,8 @@
protocol, writes and reads correspond to the LED message format
as defined in the AHCI spec.
- The user must turn sw_activity (under /sys/block/*/device/) OFF
- it they wish to control the activity LED via the em_message
+ The user must turn sw_activity (under `/sys/block/*/device/`)
+ OFF it they wish to control the activity LED via the em_message
file.
em_message_type: (RO) Displays the current enclosure management
diff --git a/Documentation/ABI/testing/sysfs-class-typec b/Documentation/ABI/testing/sysfs-class-typec
index b834671..b7794e0 100644
--- a/Documentation/ABI/testing/sysfs-class-typec
+++ b/Documentation/ABI/testing/sysfs-class-typec
@@ -40,10 +40,13 @@
attribute will not return until the operation has finished.
Valid values:
- - source (The port will behave as source only DFP port)
- - sink (The port will behave as sink only UFP port)
- - dual (The port will behave as dual-role-data and
+
+ ====== ==============================================
+ source (The port will behave as source only DFP port)
+ sink (The port will behave as sink only UFP port)
+ dual (The port will behave as dual-role-data and
dual-role-power port)
+ ====== ==============================================
What: /sys/class/typec/<port>/vconn_source
Date: April 2017
@@ -59,6 +62,7 @@
generates uevent KOBJ_CHANGE.
Valid values:
+
- "no" when the port is not the VCONN Source
- "yes" when the port is the VCONN Source
@@ -72,6 +76,7 @@
power operation mode should show "usb_power_delivery".
Valid values:
+
- default
- 1.5A
- 3.0A
@@ -191,6 +196,7 @@
Contact: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Description:
Shows type of the plug on the cable:
+
- type-a - Standard A
- type-b - Standard B
- type-c
diff --git a/Documentation/ABI/testing/sysfs-class-uwb_rc b/Documentation/ABI/testing/sysfs-class-uwb_rc
index a057875..6c5dcad 100644
--- a/Documentation/ABI/testing/sysfs-class-uwb_rc
+++ b/Documentation/ABI/testing/sysfs-class-uwb_rc
@@ -66,11 +66,14 @@
<channel> <type> [<bpst offset>]
to start (or stop) scanning on a channel. <type> is one of:
- 0 - scan
- 1 - scan outside BP
- 2 - scan while inactive
- 3 - scanning disabled
- 4 - scan (with start time of <bpst offset>)
+
+ == =======================================
+ 0 scan
+ 1 scan outside BP
+ 2 scan while inactive
+ 3 scanning disabled
+ 4 scan (with start time of <bpst offset>)
+ == =======================================
What: /sys/class/uwb_rc/uwbN/mac_address
Date: July 2008
diff --git a/Documentation/ABI/testing/sysfs-class-watchdog b/Documentation/ABI/testing/sysfs-class-watchdog
index 9860a8b..585caec 100644
--- a/Documentation/ABI/testing/sysfs-class-watchdog
+++ b/Documentation/ABI/testing/sysfs-class-watchdog
@@ -91,10 +91,13 @@
h/w strapping (for WDT2 only).
At alternate flash the 'access_cs0' sysfs node provides:
- ast2400: a way to get access to the primary SPI flash
+
+ ast2400:
+ a way to get access to the primary SPI flash
chip at CS0 after booting from the alternate
chip at CS1.
- ast2500: a way to restore the normal address mapping
+ ast2500:
+ a way to restore the normal address mapping
from (CS0->CS1, CS1->CS0) to (CS0->CS0,
CS1->CS1).
diff --git a/Documentation/ABI/testing/sysfs-dev b/Documentation/ABI/testing/sysfs-dev
index a9f2b8b..d173906 100644
--- a/Documentation/ABI/testing/sysfs-dev
+++ b/Documentation/ABI/testing/sysfs-dev
@@ -9,9 +9,10 @@
the form "<major>:<minor>". These links point to the
corresponding sysfs path for the given device.
- Example:
- $ readlink /sys/dev/block/8:32
- ../../block/sdc
+ Example::
+
+ $ readlink /sys/dev/block/8:32
+ ../../block/sdc
Entries in /sys/dev/char and /sys/dev/block will be
dynamically created and destroyed as devices enter and
diff --git a/Documentation/ABI/testing/sysfs-devices-mapping b/Documentation/ABI/testing/sysfs-devices-mapping
index 490ccfd..8d202ba 100644
--- a/Documentation/ABI/testing/sysfs-devices-mapping
+++ b/Documentation/ABI/testing/sysfs-devices-mapping
@@ -8,26 +8,27 @@
block.
For example, on 4-die Xeon platform with up to 6 IIO stacks per
die and, therefore, 6 IIO PMON blocks per die, the mapping of
- IIO PMON block 0 exposes as the following:
+ IIO PMON block 0 exposes as the following::
- $ ls /sys/devices/uncore_iio_0/die*
- -r--r--r-- /sys/devices/uncore_iio_0/die0
- -r--r--r-- /sys/devices/uncore_iio_0/die1
- -r--r--r-- /sys/devices/uncore_iio_0/die2
- -r--r--r-- /sys/devices/uncore_iio_0/die3
+ $ ls /sys/devices/uncore_iio_0/die*
+ -r--r--r-- /sys/devices/uncore_iio_0/die0
+ -r--r--r-- /sys/devices/uncore_iio_0/die1
+ -r--r--r-- /sys/devices/uncore_iio_0/die2
+ -r--r--r-- /sys/devices/uncore_iio_0/die3
- $ tail /sys/devices/uncore_iio_0/die*
- ==> /sys/devices/uncore_iio_0/die0 <==
- 0000:00
- ==> /sys/devices/uncore_iio_0/die1 <==
- 0000:40
- ==> /sys/devices/uncore_iio_0/die2 <==
- 0000:80
- ==> /sys/devices/uncore_iio_0/die3 <==
- 0000:c0
+ $ tail /sys/devices/uncore_iio_0/die*
+ ==> /sys/devices/uncore_iio_0/die0 <==
+ 0000:00
+ ==> /sys/devices/uncore_iio_0/die1 <==
+ 0000:40
+ ==> /sys/devices/uncore_iio_0/die2 <==
+ 0000:80
+ ==> /sys/devices/uncore_iio_0/die3 <==
+ 0000:c0
- Which means:
- IIO PMU 0 on die 0 belongs to PCI RP on bus 0x00, domain 0x0000
- IIO PMU 0 on die 1 belongs to PCI RP on bus 0x40, domain 0x0000
- IIO PMU 0 on die 2 belongs to PCI RP on bus 0x80, domain 0x0000
- IIO PMU 0 on die 3 belongs to PCI RP on bus 0xc0, domain 0x0000
+ Which means::
+
+ IIO PMU 0 on die 0 belongs to PCI RP on bus 0x00, domain 0x0000
+ IIO PMU 0 on die 1 belongs to PCI RP on bus 0x40, domain 0x0000
+ IIO PMU 0 on die 2 belongs to PCI RP on bus 0x80, domain 0x0000
+ IIO PMU 0 on die 3 belongs to PCI RP on bus 0xc0, domain 0x0000
diff --git a/Documentation/ABI/testing/sysfs-devices-memory b/Documentation/ABI/testing/sysfs-devices-memory
index deef3b5..2da2b1f 100644
--- a/Documentation/ABI/testing/sysfs-devices-memory
+++ b/Documentation/ABI/testing/sysfs-devices-memory
@@ -47,16 +47,19 @@
online/offline state of the memory section. When written,
root can toggle the the online/offline state of a removable
memory section (see removable file description above)
- using the following commands.
- # echo online > /sys/devices/system/memory/memoryX/state
- # echo offline > /sys/devices/system/memory/memoryX/state
+ using the following commands::
+
+ # echo online > /sys/devices/system/memory/memoryX/state
+ # echo offline > /sys/devices/system/memory/memoryX/state
For example, if /sys/devices/system/memory/memory22/removable
contains a value of 1 and
/sys/devices/system/memory/memory22/state contains the
string "online" the following command can be executed by
- by root to offline that section.
- # echo offline > /sys/devices/system/memory/memory22/state
+ by root to offline that section::
+
+ # echo offline > /sys/devices/system/memory/memory22/state
+
Users: hotplug memory remove tools
http://www.ibm.com/developerworks/wikis/display/LinuxP/powerpc-utils
@@ -78,6 +81,7 @@
For example, the following symbolic link is created for
memory section 9 on node0:
+
/sys/devices/system/memory/memory9/node0 -> ../../node/node0
@@ -90,4 +94,5 @@
points to the corresponding /sys/devices/system/memory/memoryY
memory section directory. For example, the following symbolic
link is created for memory section 9 on node0.
+
/sys/devices/system/node/node0/memory9 -> ../../memory/memory9
diff --git a/Documentation/ABI/testing/sysfs-devices-platform-ACPI-TAD b/Documentation/ABI/testing/sysfs-devices-platform-ACPI-TAD
index 7e43cdc..f7b360a 100644
--- a/Documentation/ABI/testing/sysfs-devices-platform-ACPI-TAD
+++ b/Documentation/ABI/testing/sysfs-devices-platform-ACPI-TAD
@@ -7,6 +7,7 @@
(RO) Hexadecimal bitmask of the TAD attributes are reported by
the platform firmware (see ACPI 6.2, section 9.18.2):
+ ======= ======================================================
BIT(0): AC wakeup implemented if set
BIT(1): DC wakeup implemented if set
BIT(2): Get/set real time features implemented if set
@@ -16,6 +17,7 @@
BIT(6): The AC timer wakes up from S5 if set
BIT(7): The DC timer wakes up from S4 if set
BIT(8): The DC timer wakes up from S5 if set
+ ======= ======================================================
The other bits are reserved.
@@ -62,9 +64,11 @@
timer status with the following meaning of bits (see ACPI 6.2,
Section 9.18.5):
+ ======= ======================================================
Bit(0): The timer has expired if set.
Bit(1): The timer has woken up the system from a sleep state
(S3 or S4/S5 if supported) if set.
+ ======= ======================================================
The other bits are reserved.
diff --git a/Documentation/ABI/testing/sysfs-devices-platform-_UDC_-gadget b/Documentation/ABI/testing/sysfs-devices-platform-_UDC_-gadget
index d548eaa..40f29a0 100644
--- a/Documentation/ABI/testing/sysfs-devices-platform-_UDC_-gadget
+++ b/Documentation/ABI/testing/sysfs-devices-platform-_UDC_-gadget
@@ -3,8 +3,9 @@
Contact: Fabien Chouteau <fabien.chouteau@barco.com>
Description:
Show the suspend state of an USB composite gadget.
- 1 -> suspended
- 0 -> resumed
+
+ - 1 -> suspended
+ - 0 -> resumed
(_UDC_ is the name of the USB Device Controller driver)
@@ -17,5 +18,6 @@
Storage mode.
Possible values are:
- 1 -> ignore the FUA flag
- 0 -> obey the FUA flag
+
+ - 1 -> ignore the FUA flag
+ - 0 -> obey the FUA flag
diff --git a/Documentation/ABI/testing/sysfs-devices-platform-docg3 b/Documentation/ABI/testing/sysfs-devices-platform-docg3
index 8aa3671..378c426 100644
--- a/Documentation/ABI/testing/sysfs-devices-platform-docg3
+++ b/Documentation/ABI/testing/sysfs-devices-platform-docg3
@@ -9,8 +9,10 @@
The protection has information embedded whether it blocks reads,
writes or both.
The result is:
- 0 -> the DPS is not keylocked
- 1 -> the DPS is keylocked
+
+ - 0 -> the DPS is not keylocked
+ - 1 -> the DPS is keylocked
+
Users: None identified so far.
What: /sys/devices/platform/docg3/f[0-3]_dps[01]_protection_key
@@ -27,8 +29,12 @@
Entering the correct value toggle the lock, and can be observed
through f[0-3]_dps[01]_is_keylocked.
Possible values are:
+
- 8 bytes
+
Typical values are:
+
- "00000000"
- "12345678"
+
Users: None identified so far.
diff --git a/Documentation/ABI/testing/sysfs-devices-platform-ipmi b/Documentation/ABI/testing/sysfs-devices-platform-ipmi
index afb5db8..07df0dd 100644
--- a/Documentation/ABI/testing/sysfs-devices-platform-ipmi
+++ b/Documentation/ABI/testing/sysfs-devices-platform-ipmi
@@ -123,38 +123,40 @@
Contact: openipmi-developer@lists.sourceforge.net
Description:
- idles: (RO) Number of times the interface was
+ ====================== ========================================
+ idles (RO) Number of times the interface was
idle while being polled.
- watchdog_pretimeouts: (RO) Number of watchdog pretimeouts.
+ watchdog_pretimeouts (RO) Number of watchdog pretimeouts.
- complete_transactions: (RO) Number of completed messages.
+ complete_transactions (RO) Number of completed messages.
- events: (RO) Number of IPMI events received from
+ events (RO) Number of IPMI events received from
the hardware.
- interrupts: (RO) Number of interrupts the driver
+ interrupts (RO) Number of interrupts the driver
handled.
- hosed_count: (RO) Number of times the hardware didn't
+ hosed_count (RO) Number of times the hardware didn't
follow the state machine.
- long_timeouts: (RO) Number of times the driver
+ long_timeouts (RO) Number of times the driver
requested a timer while nothing was in
progress.
- flag_fetches: (RO) Number of times the driver
+ flag_fetches (RO) Number of times the driver
requested flags from the hardware.
- attentions: (RO) Number of time the driver got an
+ attentions (RO) Number of time the driver got an
ATTN from the hardware.
- incoming_messages: (RO) Number of asynchronous messages
+ incoming_messages (RO) Number of asynchronous messages
received.
- short_timeouts: (RO) Number of times the driver
+ short_timeouts (RO) Number of times the driver
requested a timer while an operation was
in progress.
+ ====================== ========================================
What: /sys/devices/platform/ipmi_si.*/interrupts_enabled
@@ -201,38 +203,40 @@
KernelVersion: v4.15
Contact: openipmi-developer@lists.sourceforge.net
Description:
- hosed: (RO) Number of times the hardware didn't
+ ====================== ========================================
+ hosed (RO) Number of times the hardware didn't
follow the state machine.
- alerts: (RO) Number of alerts received.
+ alerts (RO) Number of alerts received.
- sent_messages: (RO) Number of total messages sent.
+ sent_messages (RO) Number of total messages sent.
- sent_message_parts: (RO) Number of message parts sent.
+ sent_message_parts (RO) Number of message parts sent.
Messages may be broken into parts if
they are long.
- received_messages: (RO) Number of message responses
+ received_messages (RO) Number of message responses
received.
- received_message_parts: (RO) Number of message fragments
+ received_message_parts (RO) Number of message fragments
received.
- events: (RO) Number of received events.
+ events (RO) Number of received events.
- watchdog_pretimeouts: (RO) Number of watchdog pretimeouts.
+ watchdog_pretimeouts (RO) Number of watchdog pretimeouts.
- flag_fetches: (RO) Number of times a flag fetch was
+ flag_fetches (RO) Number of times a flag fetch was
requested.
- send_retries: (RO) Number of time a message was
+ send_retries (RO) Number of time a message was
retried.
- receive_retries: (RO) Number of times the receive of a
+ receive_retries (RO) Number of times the receive of a
message was retried.
- send_errors: (RO) Number of times the send of a
+ send_errors (RO) Number of times the send of a
message failed.
- receive_errors: (RO) Number of errors in receiving
+ receive_errors (RO) Number of errors in receiving
messages.
+ ====================== ========================================
diff --git a/Documentation/ABI/testing/sysfs-devices-platform-sh_mobile_lcdc_fb b/Documentation/ABI/testing/sysfs-devices-platform-sh_mobile_lcdc_fb
index 2107082..e45ac2e 100644
--- a/Documentation/ABI/testing/sysfs-devices-platform-sh_mobile_lcdc_fb
+++ b/Documentation/ABI/testing/sysfs-devices-platform-sh_mobile_lcdc_fb
@@ -17,10 +17,10 @@
to overlay planes.
Selects the composition mode for the overlay. Possible values
- are
+ are:
- 0 - Alpha Blending
- 1 - ROP3
+ - 0 - Alpha Blending
+ - 1 - ROP3
What: /sys/devices/platform/sh_mobile_lcdc_fb.[0-3]/graphics/fb[0-9]/ovl_position
Date: May 2012
@@ -30,7 +30,7 @@
to overlay planes.
Stores the x,y overlay position on the display in pixels. The
- position format is `[0-9]+,[0-9]+'.
+ position format is `[0-9]+,[0-9]+`.
What: /sys/devices/platform/sh_mobile_lcdc_fb.[0-3]/graphics/fb[0-9]/ovl_rop3
Date: May 2012
diff --git a/Documentation/ABI/testing/sysfs-devices-platform-stratix10-rsu b/Documentation/ABI/testing/sysfs-devices-platform-stratix10-rsu
index a8daceb..ee253b0 100644
--- a/Documentation/ABI/testing/sysfs-devices-platform-stratix10-rsu
+++ b/Documentation/ABI/testing/sysfs-devices-platform-stratix10-rsu
@@ -102,6 +102,8 @@
b[15:0]
inform firmware the current software execution
stage.
+
+ == ===========================================
0 the first stage bootloader didn't run or
didn't reach the point of launching second
stage bootloader.
@@ -111,21 +113,29 @@
2 both first and second stage bootloader ran
and the operating system launch was
attempted.
+ == ===========================================
b[16]
+ == ===========================================
1 firmware to reset current image retry
counter.
0 no action.
+ == ===========================================
b[17]
+ == ===========================================
1 firmware to clear RSU log
0 no action.
+ == ===========================================
b[18]
this is negative logic
+
+ == ===========================================
1 no action
0 firmware record the notify code defined
in b[15:0].
+ == ===========================================
What: /sys/devices/platform/stratix10-rsu.0/dcmf0
Date: June 2020
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index b555df8..1a04ca8 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -151,23 +151,28 @@
The processor idle states which are available for use have the
following attributes:
- name: (RO) Name of the idle state (string).
+ ======== ==== =================================================
+ name: (RO) Name of the idle state (string).
latency: (RO) The latency to exit out of this idle state (in
- microseconds).
+ microseconds).
- power: (RO) The power consumed while in this idle state (in
- milliwatts).
+ power: (RO) The power consumed while in this idle state (in
+ milliwatts).
- time: (RO) The total time spent in this idle state (in microseconds).
+ time: (RO) The total time spent in this idle state
+ (in microseconds).
- usage: (RO) Number of times this state was entered (a count).
+ usage: (RO) Number of times this state was entered (a count).
- above: (RO) Number of times this state was entered, but the
- observed CPU idle duration was too short for it (a count).
+ above: (RO) Number of times this state was entered, but the
+ observed CPU idle duration was too short for it
+ (a count).
- below: (RO) Number of times this state was entered, but the
- observed CPU idle duration was too long for it (a count).
+ below: (RO) Number of times this state was entered, but the
+ observed CPU idle duration was too long for it
+ (a count).
+ ======== ==== =================================================
What: /sys/devices/system/cpu/cpuX/cpuidle/stateN/desc
Date: February 2008
@@ -290,6 +295,7 @@
This switch controls the boost setting for the whole system.
Boosting allows the CPU and the firmware to run at a frequency
beyound it's nominal limit.
+
More details can be found in
Documentation/admin-guide/pm/cpufreq.rst
@@ -337,43 +343,57 @@
Description: Parameters for the CPU cache attributes
allocation_policy:
- - WriteAllocate: allocate a memory location to a cache line
- on a cache miss because of a write
- - ReadAllocate: allocate a memory location to a cache line
+ - WriteAllocate:
+ allocate a memory location to a cache line
+ on a cache miss because of a write
+ - ReadAllocate:
+ allocate a memory location to a cache line
on a cache miss because of a read
- - ReadWriteAllocate: both writeallocate and readallocate
+ - ReadWriteAllocate:
+ both writeallocate and readallocate
- attributes: LEGACY used only on IA64 and is same as write_policy
+ attributes:
+ LEGACY used only on IA64 and is same as write_policy
- coherency_line_size: the minimum amount of data in bytes that gets
+ coherency_line_size:
+ the minimum amount of data in bytes that gets
transferred from memory to cache
- level: the cache hierarchy in the multi-level cache configuration
+ level:
+ the cache hierarchy in the multi-level cache configuration
- number_of_sets: total number of sets in the cache, a set is a
+ number_of_sets:
+ total number of sets in the cache, a set is a
collection of cache lines with the same cache index
- physical_line_partition: number of physical cache line per cache tag
+ physical_line_partition:
+ number of physical cache line per cache tag
- shared_cpu_list: the list of logical cpus sharing the cache
+ shared_cpu_list:
+ the list of logical cpus sharing the cache
- shared_cpu_map: logical cpu mask containing the list of cpus sharing
+ shared_cpu_map:
+ logical cpu mask containing the list of cpus sharing
the cache
- size: the total cache size in kB
+ size:
+ the total cache size in kB
type:
- Instruction: cache that only holds instructions
- Data: cache that only caches data
- Unified: cache that holds both data and instructions
- ways_of_associativity: degree of freedom in placing a particular block
- of memory in the cache
+ ways_of_associativity:
+ degree of freedom in placing a particular block
+ of memory in the cache
write_policy:
- - WriteThrough: data is written to both the cache line
+ - WriteThrough:
+ data is written to both the cache line
and to the block in the lower-level memory
- - WriteBack: data is written only to the cache line and
+ - WriteBack:
+ data is written only to the cache line and
the modified cache line is written to main
memory only when it is replaced
@@ -414,30 +434,30 @@
throttle attributes exported in the 'throttle_stats' directory:
- turbo_stat : This file gives the total number of times the max
- frequency is throttled to lower frequency in turbo (at and above
- nominal frequency) range of frequencies.
+ frequency is throttled to lower frequency in turbo (at and above
+ nominal frequency) range of frequencies.
- sub_turbo_stat : This file gives the total number of times the
- max frequency is throttled to lower frequency in sub-turbo(below
- nominal frequency) range of frequencies.
+ max frequency is throttled to lower frequency in sub-turbo(below
+ nominal frequency) range of frequencies.
- unthrottle : This file gives the total number of times the max
- frequency is unthrottled after being throttled.
+ frequency is unthrottled after being throttled.
- powercap : This file gives the total number of times the max
- frequency is throttled due to 'Power Capping'.
+ frequency is throttled due to 'Power Capping'.
- overtemp : This file gives the total number of times the max
- frequency is throttled due to 'CPU Over Temperature'.
+ frequency is throttled due to 'CPU Over Temperature'.
- supply_fault : This file gives the total number of times the
- max frequency is throttled due to 'Power Supply Failure'.
+ max frequency is throttled due to 'Power Supply Failure'.
- overcurrent : This file gives the total number of times the
- max frequency is throttled due to 'Overcurrent'.
+ max frequency is throttled due to 'Overcurrent'.
- occ_reset : This file gives the total number of times the max
- frequency is throttled due to 'OCC Reset'.
+ frequency is throttled due to 'OCC Reset'.
The sysfs attributes representing different throttle reasons like
powercap, overtemp, supply_fault, overcurrent and occ_reset map to
@@ -469,8 +489,9 @@
Date: June 2016
Contact: Linux ARM Kernel Mailing list <linux-arm-kernel@lists.infradead.org>
Description: AArch64 CPU registers
+
'identification' directory exposes the CPU ID registers for
- identifying model and revision of the CPU.
+ identifying model and revision of the CPU.
What: /sys/devices/system/cpu/cpu#/cpu_capacity
Date: December 2016
@@ -497,9 +518,11 @@
vulnerabilities. The output of those files reflects the
state of the CPUs in the system. Possible output values:
+ ================ ==============================================
"Not affected" CPU is not affected by the vulnerability
"Vulnerable" CPU is affected and no mitigation in effect
"Mitigation: $M" CPU is affected and mitigation $M is in effect
+ ================ ==============================================
See also: Documentation/admin-guide/hw-vuln/index.rst
@@ -515,12 +538,14 @@
control: Read/write interface to control SMT. Possible
values:
+ ================ =========================================
"on" SMT is enabled
"off" SMT is disabled
"forceoff" SMT is force disabled. Cannot be changed.
"notsupported" SMT is not supported by the CPU
"notimplemented" SMT runtime toggling is not
implemented for the architecture
+ ================ =========================================
If control status is "forceoff" or "notsupported" writes
are rejected.
@@ -576,7 +601,7 @@
Facility in POWER9 and newer processors. i.e., it is a Secure
Virtual Machine.
-What: /sys/devices/system/cpu/cpuX/purr
+What: /sys/devices/system/cpu/cpuX/purr
Date: Apr 2005
Contact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org>
Description: PURR ticks for this CPU since the system boot.
diff --git a/Documentation/ABI/testing/sysfs-devices-system-ibm-rtl b/Documentation/ABI/testing/sysfs-devices-system-ibm-rtl
index 470def0..1a8ee26 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-ibm-rtl
+++ b/Documentation/ABI/testing/sysfs-devices-system-ibm-rtl
@@ -5,8 +5,10 @@
Description: The state file allows a means by which to change in and
out of Premium Real-Time Mode (PRTM), as well as the
ability to query the current state.
- 0 => PRTM off
- 1 => PRTM enabled
+
+ - 0 => PRTM off
+ - 1 => PRTM enabled
+
Users: The ibm-prtm userspace daemon uses this interface.
diff --git a/Documentation/ABI/testing/sysfs-driver-bd9571mwv-regulator b/Documentation/ABI/testing/sysfs-driver-bd9571mwv-regulator
index 4d63a79..42214b4 100644
--- a/Documentation/ABI/testing/sysfs-driver-bd9571mwv-regulator
+++ b/Documentation/ABI/testing/sysfs-driver-bd9571mwv-regulator
@@ -6,11 +6,13 @@
if DDR power rails will be kept powered during system suspend.
("on"/"1" = enabled, "off"/"0" = disabled).
Two types of power switches (or control signals) can be used:
+
A. With a momentary power switch (or pulse signal), DDR
Backup Mode is enabled by default when available, as the
PMIC will be configured only during system suspend.
B. With a toggle power switch (or level signal), the
following steps must be followed exactly:
+
1. Configure PMIC for backup mode, to change the role of
the accessory power switch from a power switch to a
wake-up switch,
@@ -20,8 +22,10 @@
3. Suspend system,
4. Switch accessory power switch on, to resume the
system.
+
DDR Backup Mode must be explicitly enabled by the user,
to invoke step 1.
+
See also Documentation/devicetree/bindings/mfd/bd9571mwv.txt.
Users: User space applications for embedded boards equipped with a
BD9571MWV PMIC.
diff --git a/Documentation/ABI/testing/sysfs-driver-genwqe b/Documentation/ABI/testing/sysfs-driver-genwqe
index 64ac6d5..69d855dc 100644
--- a/Documentation/ABI/testing/sysfs-driver-genwqe
+++ b/Documentation/ABI/testing/sysfs-driver-genwqe
@@ -29,8 +29,12 @@
Date: May 2014
Contact: klebers@linux.vnet.ibm.com
Description: Interface to trigger a PCIe card reset to reload the bitstream.
+
+ ::
+
sudo sh -c 'echo 1 > \
/sys/class/genwqe/genwqe0_card/reload_bitstream'
+
If successfully, the card will come back with the bitstream set
on 'next_bitstream'.
@@ -64,8 +68,11 @@
What: /sys/class/genwqe/genwqe<n>_card/device/sriov_numvfs
Date: Oct 2013
Contact: haver@linux.vnet.ibm.com
-Description: Enable VFs (1..15):
+Description: Enable VFs (1..15)::
+
sudo sh -c 'echo 15 > \
/sys/bus/pci/devices/0000\:1b\:00.0/sriov_numvfs'
- Disable VFs:
+
+ Disable VFs::
+
Write a 0 into the same sysfs entry.
diff --git a/Documentation/ABI/testing/sysfs-driver-hid-lenovo b/Documentation/ABI/testing/sysfs-driver-hid-lenovo
index 53a0725..aee85ca 100644
--- a/Documentation/ABI/testing/sysfs-driver-hid-lenovo
+++ b/Documentation/ABI/testing/sysfs-driver-hid-lenovo
@@ -3,14 +3,18 @@
Contact: linux-input@vger.kernel.org
Description: This controls if mouse clicks should be generated if the trackpoint is quickly pressed. How fast this press has to be
is being controlled by press_speed.
+
Values are 0 or 1.
+
Applies to Thinkpad USB Keyboard with TrackPoint.
What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/dragging
Date: July 2011
Contact: linux-input@vger.kernel.org
Description: If this setting is enabled, it is possible to do dragging by pressing the trackpoint. This requires press_to_select to be enabled.
+
Values are 0 or 1.
+
Applies to Thinkpad USB Keyboard with TrackPoint.
What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/release_to_select
@@ -25,7 +29,9 @@
Contact: linux-input@vger.kernel.org
Description: This setting controls if the mouse click events generated by pressing the trackpoint (if press_to_select is enabled) generate
a left or right mouse button click.
+
Values are 0 or 1.
+
Applies to Thinkpad USB Keyboard with TrackPoint.
What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/sensitivity
@@ -39,12 +45,16 @@
Date: July 2011
Contact: linux-input@vger.kernel.org
Description: This setting controls how fast the trackpoint needs to be pressed to generate a mouse click if press_to_select is enabled.
+
Values are decimal integers from 1 (slowest) to 255 (fastest).
+
Applies to Thinkpad USB Keyboard with TrackPoint.
What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/fn_lock
Date: July 2014
Contact: linux-input@vger.kernel.org
Description: This setting controls whether Fn Lock is enabled on the keyboard (i.e. if F1 is Mute or F1)
+
Values are 0 or 1
+
Applies to ThinkPad Compact (USB|Bluetooth) Keyboard with TrackPoint.
diff --git a/Documentation/ABI/testing/sysfs-driver-hid-logitech-lg4ff b/Documentation/ABI/testing/sysfs-driver-hid-logitech-lg4ff
index 305dffd..de07be3 100644
--- a/Documentation/ABI/testing/sysfs-driver-hid-logitech-lg4ff
+++ b/Documentation/ABI/testing/sysfs-driver-hid-logitech-lg4ff
@@ -12,7 +12,9 @@
Contact: Michal Malý <madcatxster@devoid-pointer.net>
Description: Displays a set of alternate modes supported by a wheel. Each
mode is listed as follows:
+
Tag: Mode Name
+
Currently active mode is marked with an asterisk. List also
contains an abstract item "native" which always denotes the
native mode of the wheel. Echoing the mode tag switches the
@@ -24,24 +26,30 @@
This entry is not created for devices that have only one mode.
Currently supported mode switches:
- Driving Force Pro:
+
+ Driving Force Pro::
+
DF-EX --> DFP
- G25:
+ G25::
+
DF-EX --> DFP --> G25
- G27:
+ G27::
+
DF-EX <*> DFP <-> G25 <-> G27
DF-EX <*--------> G25 <-> G27
DF-EX <*----------------> G27
- G29:
+ G29::
+
DF-EX <*> DFP <-> G25 <-> G27 <-> G29
DF-EX <*--------> G25 <-> G27 <-> G29
DF-EX <*----------------> G27 <-> G29
DF-EX <*------------------------> G29
- DFGT:
+ DFGT::
+
DF-EX <*> DFP <-> DFGT
DF-EX <*--------> DFGT
diff --git a/Documentation/ABI/testing/sysfs-driver-hid-ntrig b/Documentation/ABI/testing/sysfs-driver-hid-ntrig
index e574a56..0e323a5 100644
--- a/Documentation/ABI/testing/sysfs-driver-hid-ntrig
+++ b/Documentation/ABI/testing/sysfs-driver-hid-ntrig
@@ -29,12 +29,13 @@
Description:
Threholds to override activation slack.
- activation_width: (RW) Width threshold to immediately
+ ================= =====================================
+ activation_width (RW) Width threshold to immediately
start processing touch events.
- activation_height: (RW) Height threshold to immediately
+ activation_height (RW) Height threshold to immediately
start processing touch events.
-
+ ================= =====================================
What: /sys/bus/hid/drivers/ntrig/<dev>/min_width
What: /sys/bus/hid/drivers/ntrig/<dev>/min_height
@@ -44,11 +45,13 @@
Description:
Minimum size contact accepted.
- min_width: (RW) Minimum touch contact width to decide
+ ========== ===========================================
+ min_width (RW) Minimum touch contact width to decide
activation and activity.
- min_height: (RW) Minimum touch contact height to decide
+ min_height (RW) Minimum touch contact height to decide
activation and activity.
+ ========== ===========================================
What: /sys/bus/hid/drivers/ntrig/<dev>/sensor_physical_width
diff --git a/Documentation/ABI/testing/sysfs-driver-hid-roccat-kone b/Documentation/ABI/testing/sysfs-driver-hid-roccat-kone
index 8f7982c..11cd9bf 100644
--- a/Documentation/ABI/testing/sysfs-driver-hid-roccat-kone
+++ b/Documentation/ABI/testing/sysfs-driver-hid-roccat-kone
@@ -3,17 +3,21 @@
Contact: Stefan Achatz <erazor_de@users.sourceforge.net>
Description: It is possible to switch the dpi setting of the mouse with the
press of a button.
+
When read, this file returns the raw number of the actual dpi
setting reported by the mouse. This number has to be further
processed to receive the real dpi value:
+ ===== =====
VALUE DPI
+ ===== =====
1 800
2 1200
3 1600
4 2000
5 2400
6 3200
+ ===== =====
This file is readonly.
Users: http://roccat.sourceforge.net
@@ -22,6 +26,7 @@
Date: March 2010
Contact: Stefan Achatz <erazor_de@users.sourceforge.net>
Description: When read, this file returns the number of the actual profile.
+
This file is readonly.
Users: http://roccat.sourceforge.net
@@ -33,6 +38,7 @@
further usage in other programs. To receive the real version
number the decimal point has to be shifted 2 positions to the
left. E.g. a returned value of 138 means 1.38
+
This file is readonly.
Users: http://roccat.sourceforge.net
@@ -43,10 +49,13 @@
press of a button. A profile holds information like button
mappings, sensitivity, the colors of the 5 leds and light
effects.
+
When read, these files return the respective profile. The
returned data is 975 bytes in size.
+
When written, this file lets one write the respective profile
data back to the mouse. The data has to be 975 bytes long.
+
The mouse will reject invalid data, whereas the profile number
stored in the profile doesn't need to fit the number of the
store.
@@ -58,6 +67,7 @@
Description: When read, this file returns the settings stored in the mouse.
The size of the data is 36 bytes and holds information like the
startup_profile, tcu state and calibration_data.
+
When written, this file lets write settings back to the mouse.
The data has to be 36 bytes long. The mouse will reject invalid
data.
@@ -67,8 +77,10 @@
Date: March 2010
Contact: Stefan Achatz <erazor_de@users.sourceforge.net>
Description: The integer value of this attribute ranges from 1 to 5.
+
When read, this attribute returns the number of the profile
that's active when the mouse is powered on.
+
When written, this file sets the number of the startup profile
and the mouse activates this profile immediately.
Users: http://roccat.sourceforge.net
@@ -80,9 +92,12 @@
calibrate the laser power to fit the mousepad surface.
When read, this file returns the current state of the TCU,
where 0 means off and 1 means on.
+
Writing 0 in this file will switch the TCU off.
+
Writing 1 in this file will start the calibration which takes
around 6 seconds to complete and activates the TCU.
+
Users: http://roccat.sourceforge.net
What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/kone/roccatkone<minor>/weight
@@ -93,14 +108,18 @@
and its value can be read out. When read, this file returns the
raw value returned by the mouse which eases further processing
in other software.
+
The values map to the weights as follows:
+ ===== ======
VALUE WEIGHT
+ ===== ======
0 none
1 5g
2 10g
3 15g
4 20g
+ ===== ======
This file is readonly.
Users: http://roccat.sourceforge.net
diff --git a/Documentation/ABI/testing/sysfs-driver-hid-wiimote b/Documentation/ABI/testing/sysfs-driver-hid-wiimote
index 39dfa5c..3bf43d9 100644
--- a/Documentation/ABI/testing/sysfs-driver-hid-wiimote
+++ b/Documentation/ABI/testing/sysfs-driver-hid-wiimote
@@ -20,6 +20,7 @@
the official Nintendo Nunchuck extension and classic is the
Nintendo Classic Controller extension. The motionp extension can
be combined with the other two.
+
Starting with kernel-version 3.11 Motion Plus hotplugging is
supported and if detected, it's no longer reported as static
extension. You will get uevent notifications for the motion-plus
@@ -39,9 +40,13 @@
Other strings for each device-type are available and may be
added if new device-specific detections are added.
Currently supported are:
- gen10: First Wii Remote generation
- gen20: Second Wii Remote Plus generation (builtin MP)
+
+ ============= =======================================
+ gen10: First Wii Remote generation
+ gen20: Second Wii Remote Plus generation
+ (builtin MP)
balanceboard: Wii Balance Board
+ ============= =======================================
What: /sys/bus/hid/drivers/wiimote/<dev>/bboard_calib
Date: May 2013
@@ -54,6 +59,7 @@
First, 0kg values for all 4 sensors are written, followed by the
17kg values for all 4 sensors and last the 34kg values for all 4
sensors.
+
Calibration data is already applied by the kernel to all input
values but may be used by user-space to perform other
transformations.
@@ -68,9 +74,11 @@
is prefixed with a +/-. Each value is a signed 16bit number.
Data is encoded as decimal numbers and specifies the offsets of
the analog sticks of the pro-controller.
+
Calibration data is already applied by the kernel to all input
values but may be used by user-space to perform other
transformations.
+
Calibration data is detected by the kernel during device setup.
You can write "scan\n" into this file to re-trigger calibration.
You can also write data directly in the form "x1:y1 x2:y2" to
diff --git a/Documentation/ABI/testing/sysfs-driver-input-exc3000 b/Documentation/ABI/testing/sysfs-driver-input-exc3000
index 3d316d5..cd7c578 100644
--- a/Documentation/ABI/testing/sysfs-driver-input-exc3000
+++ b/Documentation/ABI/testing/sysfs-driver-input-exc3000
@@ -4,6 +4,7 @@
Description: Reports the firmware version provided by the touchscreen, for example "00_T6" on a EXC80H60
Access: Read
+
Valid values: Represented as string
What: /sys/bus/i2c/devices/xxx/model
@@ -12,4 +13,5 @@
Description: Reports the model identification provided by the touchscreen, for example "Orion_1320" on a EXC80H60
Access: Read
+
Valid values: Represented as string
diff --git a/Documentation/ABI/testing/sysfs-driver-jz4780-efuse b/Documentation/ABI/testing/sysfs-driver-jz4780-efuse
index bb6f5d6..4cf595d 100644
--- a/Documentation/ABI/testing/sysfs-driver-jz4780-efuse
+++ b/Documentation/ABI/testing/sysfs-driver-jz4780-efuse
@@ -4,7 +4,9 @@
Description: read-only access to the efuse on the Ingenic JZ4780 SoC
The SoC has a one time programmable 8K efuse that is
split into segments. The driver supports read only.
- The segments are
+ The segments are:
+
+ ===== ======== =================
0x000 64 bit Random Number
0x008 128 bit Ingenic Chip ID
0x018 128 bit Customer ID
@@ -12,5 +14,7 @@
0x1E0 8 bit Protect Segment
0x1E1 2296 bit HDMI Key
0x300 2048 bit Security boot key
+ ===== ======== =================
+
Users: any user space application which wants to read the Chip
and Customer ID
diff --git a/Documentation/ABI/testing/sysfs-driver-pciback b/Documentation/ABI/testing/sysfs-driver-pciback
index 73308c2..49f5fd0 100644
--- a/Documentation/ABI/testing/sysfs-driver-pciback
+++ b/Documentation/ABI/testing/sysfs-driver-pciback
@@ -7,8 +7,10 @@
the format of DDDD:BB:DD.F-REG:SIZE:MASK will allow the guest
to write and read from the PCI device. That is Domain:Bus:
Device.Function-Register:Size:Mask (Domain is optional).
- For example:
- #echo 00:19.0-E0:2:FF > /sys/bus/pci/drivers/pciback/quirks
+ For example::
+
+ #echo 00:19.0-E0:2:FF > /sys/bus/pci/drivers/pciback/quirks
+
will allow the guest to read and write to the configuration
register 0x0E.
diff --git a/Documentation/ABI/testing/sysfs-driver-samsung-laptop b/Documentation/ABI/testing/sysfs-driver-samsung-laptop
index 34d3a33..28c9c04 100644
--- a/Documentation/ABI/testing/sysfs-driver-samsung-laptop
+++ b/Documentation/ABI/testing/sysfs-driver-samsung-laptop
@@ -9,10 +9,12 @@
their fans quiet at all costs. Reading from this file
will show the current performance level. Writing to the
file can change this value.
+
Valid options:
- "silent"
- "normal"
- "overclock"
+ - "silent"
+ - "normal"
+ - "overclock"
+
Note that not all laptops support all of these options.
Specifically, not all support the "overclock" option,
and it's still unknown if this value even changes
@@ -25,8 +27,9 @@
Description: Max battery charge level can be modified, battery cycle
life can be extended by reducing the max battery charge
level.
- 0 means normal battery mode (100% charge)
- 1 means battery life extender mode (80% charge)
+
+ - 0 means normal battery mode (100% charge)
+ - 1 means battery life extender mode (80% charge)
What: /sys/devices/platform/samsung/usb_charge
Date: December 1, 2011
diff --git a/Documentation/ABI/testing/sysfs-driver-toshiba_acpi b/Documentation/ABI/testing/sysfs-driver-toshiba_acpi
index f34221b..e5a438d 100644
--- a/Documentation/ABI/testing/sysfs-driver-toshiba_acpi
+++ b/Documentation/ABI/testing/sysfs-driver-toshiba_acpi
@@ -4,10 +4,12 @@
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls the keyboard backlight operation mode, valid
values are:
+
* 0x1 -> FN-Z
* 0x2 -> AUTO (also called TIMER)
* 0x8 -> ON
* 0x10 -> OFF
+
Note that from kernel 3.16 onwards this file accepts all listed
parameters, kernel 3.15 only accepts the first two (FN-Z and
AUTO).
@@ -41,8 +43,10 @@
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This files controls the status of the touchpad and pointing
stick (if available), valid values are:
+
* 0 -> OFF
* 1 -> ON
+
Users: KToshiba
What: /sys/devices/LNXSYSTM:00/LNXSYBUS:00/TOS{1900,620{0,7,8}}:00/available_kbd_modes
@@ -51,10 +55,12 @@
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file shows the supported keyboard backlight modes
the system supports, which can be:
+
* 0x1 -> FN-Z
* 0x2 -> AUTO (also called TIMER)
* 0x8 -> ON
* 0x10 -> OFF
+
Note that not all keyboard types support the listed modes.
See the entry named "available_kbd_modes"
Users: KToshiba
@@ -65,6 +71,7 @@
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file shows the current keyboard backlight type,
which can be:
+
* 1 -> Type 1, supporting modes FN-Z and AUTO
* 2 -> Type 2, supporting modes TIMER, ON and OFF
Users: KToshiba
@@ -75,10 +82,12 @@
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls the USB Sleep & Charge charging mode, which
can be:
+
* 0 -> Disabled (0x00)
* 1 -> Alternate (0x09)
* 2 -> Auto (0x21)
* 3 -> Typical (0x11)
+
Note that from kernel 4.1 onwards this file accepts all listed
values, kernel 4.0 only supports the first three.
Note that this feature only works when connected to power, if
@@ -93,8 +102,10 @@
Description: This file controls the USB Sleep Functions under battery, and
set the level at which point they will be disabled, accepted
values can be:
+
* 0 -> Disabled
* 1-100 -> Battery level to disable sleep functions
+
Currently it prints two values, the first one indicates if the
feature is enabled or disabled, while the second one shows the
current battery level set.
@@ -107,8 +118,10 @@
KernelVersion: 4.0
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls the USB Rapid Charge state, which can be:
+
* 0 -> Disabled
* 1 -> Enabled
+
Note that toggling this value requires a reboot for changes to
take effect.
Users: KToshiba
@@ -118,8 +131,10 @@
KernelVersion: 4.0
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls the Sleep & Music state, which values can be:
+
* 0 -> Disabled
* 1 -> Enabled
+
Note that this feature only works when connected to power, if
you want to use it under battery, see the entry named
"sleep_functions_on_battery"
@@ -138,6 +153,7 @@
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls the state of the internal fan, valid
values are:
+
* 0 -> OFF
* 1 -> ON
@@ -147,8 +163,10 @@
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls the Special Functions (hotkeys) operation
mode, valid values are:
+
* 0 -> Normal Operation
* 1 -> Special Functions
+
In the "Normal Operation" mode, the F{1-12} keys are as usual
and the hotkeys are accessed via FN-F{1-12}.
In the "Special Functions" mode, the F{1-12} keys trigger the
@@ -163,8 +181,10 @@
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls whether the laptop should turn ON whenever
the LID is opened, valid values are:
+
* 0 -> Disabled
* 1 -> Enabled
+
Note that toggling this value requires a reboot for changes to
take effect.
Users: KToshiba
@@ -174,8 +194,10 @@
KernelVersion: 4.0
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls the USB 3 functionality, valid values are:
+
* 0 -> Disabled (Acts as a regular USB 2)
* 1 -> Enabled (Full USB 3 functionality)
+
Note that toggling this value requires a reboot for changes to
take effect.
Users: KToshiba
@@ -188,10 +210,14 @@
Reading this file prints two values, the first is the actual cooling method
and the second is the maximum cooling method supported.
When the maximum cooling method is ONE, valid values are:
+
* 0 -> Maximum Performance
* 1 -> Battery Optimized
+
When the maximum cooling method is TWO, valid values are:
+
* 0 -> Maximum Performance
* 1 -> Performance
* 2 -> Battery Optimized
+
Users: KToshiba
diff --git a/Documentation/ABI/testing/sysfs-driver-toshiba_haps b/Documentation/ABI/testing/sysfs-driver-toshiba_haps
index a662370..c938690 100644
--- a/Documentation/ABI/testing/sysfs-driver-toshiba_haps
+++ b/Documentation/ABI/testing/sysfs-driver-toshiba_haps
@@ -4,10 +4,12 @@
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls the built-in accelerometer protection level,
valid values are:
+
* 0 -> Disabled
* 1 -> Low
* 2 -> Medium
* 3 -> High
+
The default potection value is set to 2 (Medium).
Users: KToshiba
diff --git a/Documentation/ABI/testing/sysfs-driver-ufs b/Documentation/ABI/testing/sysfs-driver-ufs
index d1a3521..adc0d0e 100644
--- a/Documentation/ABI/testing/sysfs-driver-ufs
+++ b/Documentation/ABI/testing/sysfs-driver-ufs
@@ -18,6 +18,7 @@
Description: This file shows the device type. This is one of the UFS
device descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/device_class
@@ -26,6 +27,7 @@
Description: This file shows the device class. This is one of the UFS
device descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/device_sub_class
@@ -34,6 +36,7 @@
Description: This file shows the UFS storage subclass. This is one of
the UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/protocol
@@ -43,6 +46,7 @@
This is one of the UFS device descriptor parameters.
The full information about the descriptor could be found
at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/number_of_luns
@@ -51,6 +55,7 @@
Description: This file shows number of logical units. This is one of
the UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/number_of_wluns
@@ -60,6 +65,7 @@
This is one of the UFS device descriptor parameters.
The full information about the descriptor could be found
at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/boot_enable
@@ -69,6 +75,7 @@
enabled for boot. This is one of the UFS device descriptor
parameters. The full information about the descriptor could
be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/descriptor_access_enable
@@ -79,6 +86,7 @@
of the boot sequence. This is one of the UFS device descriptor
parameters. The full information about the descriptor could
be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/initial_power_mode
@@ -88,6 +96,7 @@
device initialization or hardware reset. This is one of
the UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/high_priority_lun
@@ -96,6 +105,7 @@
Description: This file shows the high priority lun. This is one of
the UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/secure_removal_type
@@ -104,6 +114,7 @@
Description: This file shows the secure removal type. This is one of
the UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/support_security_lun
@@ -113,6 +124,7 @@
This is one of the UFS device descriptor parameters.
The full information about the descriptor could be found
at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/bkops_termination_latency
@@ -122,6 +134,7 @@
latency. This is one of the UFS device descriptor parameters.
The full information about the descriptor could be found
at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/initial_active_icc_level
@@ -130,6 +143,7 @@
Description: This file shows the initial active ICC level. This is one
of the UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/specification_version
@@ -138,6 +152,7 @@
Description: This file shows the specification version. This is one
of the UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/manufacturing_date
@@ -147,6 +162,7 @@
This is one of the UFS device descriptor parameters.
The full information about the descriptor could be found
at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/manufacturer_id
@@ -155,6 +171,7 @@
Description: This file shows the manufacturee ID. This is one of the
UFS device descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/rtt_capability
@@ -164,6 +181,7 @@
supported by the device. This is one of the UFS device
descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/rtc_update
@@ -173,6 +191,7 @@
clock update. This is one of the UFS device descriptor
parameters. The full information about the descriptor
could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/ufs_features
@@ -182,6 +201,7 @@
This is one of the UFS device descriptor parameters.
The full information about the descriptor could be
found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/ffu_timeout
@@ -190,6 +210,7 @@
Description: This file shows the FFU timeout. This is one of the
UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/queue_depth
@@ -198,6 +219,7 @@
Description: This file shows the device queue depth. This is one of the
UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/device_version
@@ -206,6 +228,7 @@
Description: This file shows the device version. This is one of the
UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/number_of_secure_wpa
@@ -215,6 +238,7 @@
supported by the device. This is one of the UFS device
descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/psa_max_data_size
@@ -225,6 +249,7 @@
This is one of the UFS device descriptor parameters.
The full information about the descriptor could be found
at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/psa_state_timeout
@@ -234,6 +259,7 @@
in PSA state. This is one of the UFS device descriptor
parameters. The full information about the descriptor could
be found at UFS specifications 2.1.
+
The file is read only.
@@ -244,6 +270,7 @@
This is one of the UFS interconnect descriptor parameters.
The full information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/interconnect_descriptor/mphy_version
@@ -253,6 +280,7 @@
This is one of the UFS interconnect descriptor parameters.
The full information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
@@ -264,6 +292,7 @@
of the UFS geometry descriptor parameters. The full
information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/max_number_of_luns
@@ -273,6 +302,7 @@
supported by the UFS device. This is one of the UFS
geometry descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/segment_size
@@ -281,6 +311,7 @@
Description: This file shows the segment size. This is one of the UFS
geometry descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/allocation_unit_size
@@ -289,6 +320,7 @@
Description: This file shows the allocation unit size. This is one of
the UFS geometry descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/min_addressable_block_size
@@ -298,6 +330,7 @@
is one of the UFS geometry descriptor parameters. The full
information about the descriptor could be found at UFS
specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/optimal_read_block_size
@@ -307,6 +340,7 @@
of the UFS geometry descriptor parameters. The full
information about the descriptor could be found at UFS
specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/optimal_write_block_size
@@ -316,6 +350,7 @@
of the UFS geometry descriptor parameters. The full
information about the descriptor could be found at UFS
specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/max_in_buffer_size
@@ -325,6 +360,7 @@
is one of the UFS geometry descriptor parameters. The full
information about the descriptor could be found at UFS
specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/max_out_buffer_size
@@ -334,6 +370,7 @@
is one of the UFS geometry descriptor parameters. The full
information about the descriptor could be found at UFS
specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/rpmb_rw_size
@@ -343,6 +380,7 @@
in Security Protocol In/Out. This is one of the UFS geometry
descriptor parameters. The full information about the
descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/dyn_capacity_resource_policy
@@ -352,6 +390,7 @@
is one of the UFS geometry descriptor parameters. The full
information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/data_ordering
@@ -361,6 +400,7 @@
This is one of the UFS geometry descriptor parameters.
The full information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/max_number_of_contexts
@@ -370,6 +410,7 @@
are supported by the device. This is one of the UFS geometry
descriptor parameters. The full information about the
descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/sys_data_tag_unit_size
@@ -378,6 +419,7 @@
Description: This file shows system data tag unit size. This is one of
the UFS geometry descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/sys_data_tag_resource_size
@@ -388,6 +430,7 @@
This is one of the UFS geometry descriptor parameters.
The full information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/secure_removal_types
@@ -397,6 +440,7 @@
one of the UFS geometry descriptor parameters. The full
information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/memory_types
@@ -406,6 +450,7 @@
the UFS geometry descriptor parameters. The full
information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/*_memory_max_alloc_units
@@ -416,6 +461,7 @@
enhanced type 1-4). This is one of the UFS geometry
descriptor parameters. The full information about the
descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/*_memory_capacity_adjustment_factor
@@ -426,6 +472,7 @@
enhanced type 1-4). This is one of the UFS geometry
descriptor parameters. The full information about the
descriptor could be found at UFS specifications 2.1.
+
The file is read only.
@@ -436,6 +483,7 @@
of the UFS health descriptor parameters. The full
information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/health_descriptor/life_time_estimation_a
@@ -445,6 +493,7 @@
(method a). This is one of the UFS health descriptor
parameters. The full information about the descriptor
could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/health_descriptor/life_time_estimation_b
@@ -454,6 +503,7 @@
(method b). This is one of the UFS health descriptor
parameters. The full information about the descriptor
could be found at UFS specifications 2.1.
+
The file is read only.
@@ -464,6 +514,7 @@
active ICC levels from 0 to 15. This is one of the UFS
power descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
@@ -473,6 +524,7 @@
Description: This file contains a device manufactureer name string.
The full information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/string_descriptors/product_name
@@ -480,6 +532,7 @@
Contact: Stanislav Nijnikov <stanislav.nijnikov@wdc.com>
Description: This file contains a product name string. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/string_descriptors/oem_id
@@ -487,6 +540,7 @@
Contact: Stanislav Nijnikov <stanislav.nijnikov@wdc.com>
Description: This file contains a OEM ID string. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/string_descriptors/serial_number
@@ -495,6 +549,7 @@
Description: This file contains a device serial number string. The full
information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/string_descriptors/product_revision
@@ -503,6 +558,7 @@
Description: This file contains a product revision string. The full
information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
@@ -512,6 +568,7 @@
Description: This file shows boot LUN information. This is one of
the UFS unit descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/lun_write_protect
@@ -520,6 +577,7 @@
Description: This file shows LUN write protection status. This is one of
the UFS unit descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/lun_queue_depth
@@ -528,6 +586,7 @@
Description: This file shows LUN queue depth. This is one of the UFS
unit descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/psa_sensitive
@@ -536,6 +595,7 @@
Description: This file shows PSA sensitivity. This is one of the UFS
unit descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/lun_memory_type
@@ -544,6 +604,7 @@
Description: This file shows LUN memory type. This is one of the UFS
unit descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/data_reliability
@@ -553,6 +614,7 @@
occurs during a write operation. This is one of the UFS
unit descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/logical_block_size
@@ -562,6 +624,7 @@
(calculated as an exponent with base 2). This is one of
the UFS unit descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/logical_block_count
@@ -571,6 +634,7 @@
This is one of the UFS unit descriptor parameters. The full
information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/erase_block_size
@@ -579,6 +643,7 @@
Description: This file shows the erase block size. This is one of
the UFS unit descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/provisioning_type
@@ -587,6 +652,7 @@
Description: This file shows the thin provisioning type. This is one of
the UFS unit descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/physical_memory_resourse_count
@@ -595,6 +661,7 @@
Description: This file shows the total physical memory resources. This is
one of the UFS unit descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/context_capabilities
@@ -603,6 +670,7 @@
Description: This file shows the context capabilities. This is one of
the UFS unit descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/large_unit_granularity
@@ -611,6 +679,7 @@
Description: This file shows the granularity of the LUN. This is one of
the UFS unit descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
@@ -619,6 +688,7 @@
Contact: Stanislav Nijnikov <stanislav.nijnikov@wdc.com>
Description: This file shows the device init status. The full information
about the flag could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/permanent_wpe
@@ -627,6 +697,7 @@
Description: This file shows whether permanent write protection is enabled.
The full information about the flag could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/power_on_wpe
@@ -636,6 +707,7 @@
logical units configured as power on write protected. The
full information about the flag could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/bkops_enable
@@ -644,6 +716,7 @@
Description: This file shows whether the device background operations are
enabled. The full information about the flag could be
found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/life_span_mode_enable
@@ -652,6 +725,7 @@
Description: This file shows whether the device life span mode is enabled.
The full information about the flag could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/phy_resource_removal
@@ -660,6 +734,7 @@
Description: This file shows whether physical resource removal is enable.
The full information about the flag could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/busy_rtc
@@ -668,6 +743,7 @@
Description: This file shows whether the device is executing internal
operation related to real time clock. The full information
about the flag could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/disable_fw_update
@@ -676,6 +752,7 @@
Description: This file shows whether the device FW update is permanently
disabled. The full information about the flag could be found
at UFS specifications 2.1.
+
The file is read only.
@@ -685,6 +762,7 @@
Description: This file provides the boot lun enabled UFS device attribute.
The full information about the attribute could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/current_power_mode
@@ -693,6 +771,7 @@
Description: This file provides the current power mode UFS device attribute.
The full information about the attribute could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/active_icc_level
@@ -701,6 +780,7 @@
Description: This file provides the active icc level UFS device attribute.
The full information about the attribute could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/ooo_data_enabled
@@ -709,6 +789,7 @@
Description: This file provides the out of order data transfer enabled UFS
device attribute. The full information about the attribute
could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/bkops_status
@@ -717,6 +798,7 @@
Description: This file provides the background operations status UFS device
attribute. The full information about the attribute could
be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/purge_status
@@ -725,6 +807,7 @@
Description: This file provides the purge operation status UFS device
attribute. The full information about the attribute could
be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/max_data_in_size
@@ -733,6 +816,7 @@
Description: This file shows the maximum data size in a DATA IN
UPIU. The full information about the attribute could
be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/max_data_out_size
@@ -741,6 +825,7 @@
Description: This file shows the maximum number of bytes that can be
requested with a READY TO TRANSFER UPIU. The full information
about the attribute could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/reference_clock_frequency
@@ -749,6 +834,7 @@
Description: This file provides the reference clock frequency UFS device
attribute. The full information about the attribute could
be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/configuration_descriptor_lock
@@ -765,6 +851,7 @@
outstanding RTTs in device that is allowed. The full
information about the attribute could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/exception_event_control
@@ -773,6 +860,7 @@
Description: This file provides the exception event control UFS device
attribute. The full information about the attribute could
be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/exception_event_status
@@ -781,6 +869,7 @@
Description: This file provides the exception event status UFS device
attribute. The full information about the attribute could
be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/ffu_status
@@ -789,6 +878,7 @@
Description: This file provides the ffu status UFS device attribute.
The full information about the attribute could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/psa_state
@@ -796,6 +886,7 @@
Contact: Stanislav Nijnikov <stanislav.nijnikov@wdc.com>
Description: This file show the PSA feature status. The full information
about the attribute could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/psa_data_size
@@ -805,6 +896,7 @@
load to all logical units in pre-soldering state.
The full information about the attribute could be found at
UFS specifications 2.1.
+
The file is read only.
@@ -815,6 +907,7 @@
to be removed from the physical memory resources pool of
the particular logical unit. The full information about
the attribute could be found at UFS specifications 2.1.
+
The file is read only.
@@ -824,24 +917,28 @@
Description: This entry could be used to set or show the UFS device
runtime power management level. The current driver
implementation supports 6 levels with next target states:
- 0 - an UFS device will stay active, an UIC link will
- stay active
- 1 - an UFS device will stay active, an UIC link will
- hibernate
- 2 - an UFS device will moved to sleep, an UIC link will
- stay active
- 3 - an UFS device will moved to sleep, an UIC link will
- hibernate
- 4 - an UFS device will be powered off, an UIC link will
- hibernate
- 5 - an UFS device will be powered off, an UIC link will
- be powered off
+
+ == ====================================================
+ 0 an UFS device will stay active, an UIC link will
+ stay active
+ 1 an UFS device will stay active, an UIC link will
+ hibernate
+ 2 an UFS device will moved to sleep, an UIC link will
+ stay active
+ 3 an UFS device will moved to sleep, an UIC link will
+ hibernate
+ 4 an UFS device will be powered off, an UIC link will
+ hibernate
+ 5 an UFS device will be powered off, an UIC link will
+ be powered off
+ == ====================================================
What: /sys/bus/platform/drivers/ufshcd/*/rpm_target_dev_state
Date: February 2018
Contact: Subhash Jadavani <subhashj@codeaurora.org>
Description: This entry shows the target power mode of an UFS device
for the chosen runtime power management level.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/rpm_target_link_state
@@ -849,6 +946,7 @@
Contact: Subhash Jadavani <subhashj@codeaurora.org>
Description: This entry shows the target state of an UFS UIC link
for the chosen runtime power management level.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/spm_lvl
@@ -857,24 +955,28 @@
Description: This entry could be used to set or show the UFS device
system power management level. The current driver
implementation supports 6 levels with next target states:
- 0 - an UFS device will stay active, an UIC link will
- stay active
- 1 - an UFS device will stay active, an UIC link will
- hibernate
- 2 - an UFS device will moved to sleep, an UIC link will
- stay active
- 3 - an UFS device will moved to sleep, an UIC link will
- hibernate
- 4 - an UFS device will be powered off, an UIC link will
- hibernate
- 5 - an UFS device will be powered off, an UIC link will
- be powered off
+
+ == ====================================================
+ 0 an UFS device will stay active, an UIC link will
+ stay active
+ 1 an UFS device will stay active, an UIC link will
+ hibernate
+ 2 an UFS device will moved to sleep, an UIC link will
+ stay active
+ 3 an UFS device will moved to sleep, an UIC link will
+ hibernate
+ 4 an UFS device will be powered off, an UIC link will
+ hibernate
+ 5 an UFS device will be powered off, an UIC link will
+ be powered off
+ == ====================================================
What: /sys/bus/platform/drivers/ufshcd/*/spm_target_dev_state
Date: February 2018
Contact: Subhash Jadavani <subhashj@codeaurora.org>
Description: This entry shows the target power mode of an UFS device
for the chosen system power management level.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/spm_target_link_state
@@ -882,18 +984,21 @@
Contact: Subhash Jadavani <subhashj@codeaurora.org>
Description: This entry shows the target state of an UFS UIC link
for the chosen system power management level.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/wb_presv_us_en
Date: June 2020
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows if preserve user-space was configured
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/wb_shared_alloc_units
Date: June 2020
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the shared allocated units of WB buffer
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/wb_type
@@ -901,6 +1006,7 @@
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the configured WB type.
0x1 for shared buffer mode. 0x0 for dedicated buffer mode.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/wb_buff_cap_adj
@@ -910,6 +1016,7 @@
buffer mode.
The value of this parameter is 3 for TLC NAND when SLC mode
is used as WriteBooster Buffer. 2 for MLC NAND.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/wb_max_alloc_units
@@ -917,6 +1024,7 @@
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the Maximum total WriteBooster Buffer size
which is supported by the entire device.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/wb_max_wb_luns
@@ -924,6 +1032,7 @@
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the maximum number of luns that can support
WriteBooster.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/wb_sup_red_type
@@ -937,46 +1046,59 @@
preserve user space type.
02h: Device can be configured in either user space
reduction type or preserve user space type.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/wb_sup_wb_type
Date: June 2020
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: The supportability of WriteBooster Buffer type.
- 00h: LU based WriteBooster Buffer configuration
- 01h: Single shared WriteBooster Buffer
- configuration
- 02h: Supporting both LU based WriteBooster
- Buffer and Single shared WriteBooster Buffer
- configuration
+
+ === ==========================================================
+ 00h LU based WriteBooster Buffer configuration
+ 01h Single shared WriteBooster Buffer configuration
+ 02h Supporting both LU based WriteBooster.
+ Buffer and Single shared WriteBooster Buffer configuration
+ === ==========================================================
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/wb_enable
Date: June 2020
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the status of WriteBooster.
- 0: WriteBooster is not enabled.
- 1: WriteBooster is enabled
+
+ == ============================
+ 0 WriteBooster is not enabled.
+ 1 WriteBooster is enabled
+ == ============================
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/wb_flush_en
Date: June 2020
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows if flush is enabled.
- 0: Flush operation is not performed.
- 1: Flush operation is performed.
+
+ == =================================
+ 0 Flush operation is not performed.
+ 1 Flush operation is performed.
+ == =================================
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/wb_flush_during_h8
Date: June 2020
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: Flush WriteBooster Buffer during hibernate state.
- 0: Device is not allowed to flush the
- WriteBooster Buffer during link hibernate
- state.
- 1: Device is allowed to flush the
- WriteBooster Buffer during link hibernate
- state
+
+ == =================================================
+ 0 Device is not allowed to flush the
+ WriteBooster Buffer during link hibernate state.
+ 1 Device is allowed to flush the
+ WriteBooster Buffer during link hibernate state.
+ == =================================================
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/wb_avail_buf
@@ -984,23 +1106,30 @@
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the amount of unused WriteBooster buffer
available.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/wb_cur_buf
Date: June 2020
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the amount of unused current buffer.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/wb_flush_status
Date: June 2020
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the flush operation status.
- 00h: idle
- 01h: Flush operation in progress
- 02h: Flush operation stopped prematurely.
- 03h: Flush operation completed successfully
- 04h: Flush operation general failure
+
+
+ === ======================================
+ 00h idle
+ 01h Flush operation in progress
+ 02h Flush operation stopped prematurely.
+ 03h Flush operation completed successfully
+ 04h Flush operation general failure
+ === ======================================
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/wb_life_time_est
@@ -1008,9 +1137,13 @@
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows an indication of the WriteBooster Buffer
lifetime based on the amount of performed program/erase cycles
- 01h: 0% - 10% WriteBooster Buffer life time used
+
+ === =============================================
+ 01h 0% - 10% WriteBooster Buffer life time used
...
- 0Ah: 90% - 100% WriteBooster Buffer life time used
+ 0Ah 90% - 100% WriteBooster Buffer life time used
+ === =============================================
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/wb_buf_alloc_units
@@ -1018,4 +1151,5 @@
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the configured size of WriteBooster buffer.
0400h corresponds to 4GB.
+
The file is read only.
diff --git a/Documentation/ABI/testing/sysfs-driver-w1_ds28e17 b/Documentation/ABI/testing/sysfs-driver-w1_ds28e17
index d301e70..e92aba4 100644
--- a/Documentation/ABI/testing/sysfs-driver-w1_ds28e17
+++ b/Documentation/ABI/testing/sysfs-driver-w1_ds28e17
@@ -5,7 +5,9 @@
Description: When written, this file sets the I2C speed on the connected
DS28E17 chip. When read, it reads the current setting from
the DS28E17 chip.
+
Valid values: 100, 400, 900 [kBaud].
+
Default 100, can be set by w1_ds28e17.speed= module parameter.
Users: w1_ds28e17 driver
@@ -17,5 +19,6 @@
the busy timeout for I2C operations on the connected DS28E17
chip. When read, returns the current setting.
Valid values: 1 to 9.
+
Default 1, can be set by w1_ds28e17.stretch= module parameter.
Users: w1_ds28e17 driver
diff --git a/Documentation/ABI/testing/sysfs-driver-w1_therm b/Documentation/ABI/testing/sysfs-driver-w1_therm
index 8873bbb..6a37dc3 100644
--- a/Documentation/ABI/testing/sysfs-driver-w1_therm
+++ b/Documentation/ABI/testing/sysfs-driver-w1_therm
@@ -22,8 +22,10 @@
device data to its embedded EEPROM, either restore data
embedded in device EEPROM. Be aware that devices support
limited EEPROM writing cycles (typical 50k)
+
* 'save': save device RAM to EEPROM
* 'restore': restore EEPROM data in device RAM
+
Users: any user space application which wants to communicate with
w1_term device
@@ -33,9 +35,11 @@
Contact: Akira Shimahara <akira215corp@gmail.com>
Description:
(RO) return the power status by asking the device
+
* '0': device parasite powered
* '1': device externally powered
* '-xx': xx is kernel error when reading power status
+
Users: any user space application which wants to communicate with
w1_term device
@@ -49,10 +53,12 @@
will be changed only in device RAM, so it will be cleared when
power is lost. Trigger a 'save' to EEPROM command to keep
values after power-on. Read or write are :
+
* '9..14': device resolution in bit
- or resolution to set in bit
+ or resolution to set in bit
* '-xx': xx is kernel error when reading the resolution
* Anything else: do nothing
+
Some DS18B20 clones are fixed in 12-bit resolution, so the
actual resolution is read back from the chip and verified. Error
is reported if the results differ.
@@ -65,16 +71,18 @@
Contact: Akira Shimahara <akira215corp@gmail.com>
Description:
(RO) return the temperature in 1/1000 degC.
+
* If a bulk read has been triggered, it will directly
- return the temperature computed when the bulk read
- occurred, if available. If not yet available, nothing
- is returned (a debug kernel message is sent), you
- should retry later on.
+ return the temperature computed when the bulk read
+ occurred, if available. If not yet available, nothing
+ is returned (a debug kernel message is sent), you
+ should retry later on.
* If no bulk read has been triggered, it will trigger
- a conversion and send the result. Note that the
- conversion duration depend on the resolution (if
- device support this feature). It takes 94ms in 9bits
- resolution, 750ms for 12bits.
+ a conversion and send the result. Note that the
+ conversion duration depend on the resolution (if
+ device support this feature). It takes 94ms in 9bits
+ resolution, 750ms for 12bits.
+
Users: any user space application which wants to communicate with
w1_term device
@@ -86,12 +94,14 @@
(RW) return the temperature in 1/1000 degC.
*read*: return 2 lines with the hexa output data sent on the
bus, return the CRC check and temperature in 1/1000 degC
- *write* :
+ *write*:
+
* '0' : save the 2 or 3 bytes to the device EEPROM
- (i.e. TH, TL and config register)
+ (i.e. TH, TL and config register)
* '9..14' : set the device resolution in RAM
- (if supported)
+ (if supported)
* Anything else: do nothing
+
refer to Documentation/w1/slaves/w1_therm.rst for detailed
information.
Users: any user space application which wants to communicate with
@@ -103,14 +113,21 @@
Contact: Akira Shimahara <akira215corp@gmail.com>
Description:
(RW) trigger a bulk read conversion. read the status
+
*read*:
- * '-1': conversion in progress on at least 1 sensor
- * '1' : conversion complete but at least one sensor
+ * '-1':
+ conversion in progress on at least 1 sensor
+ * '1' :
+ conversion complete but at least one sensor
value has not been read yet
- * '0' : no bulk operation. Reading temperature will
+ * '0' :
+ no bulk operation. Reading temperature will
trigger a conversion on each device
- *write*: 'trigger': trigger a bulk read on all supporting
+
+ *write*:
+ 'trigger': trigger a bulk read on all supporting
devices on the bus
+
Note that if a bulk read is sent but one sensor is not read
immediately, the next access to temperature on this device
will return the temperature measured at the time of issue
@@ -128,14 +145,19 @@
reset to default (datasheet) conversion time for a new
resolution.
- *read*: Actual conversion time in milliseconds. *write*:
- '0': Set the default conversion time from the datasheet.
- '1': Measure and set the conversion time. Make a single
+ *read*:
+ Actual conversion time in milliseconds.
+
+ *write*:
+ * '0':
+ Set the default conversion time from the datasheet.
+ * '1':
+ Measure and set the conversion time. Make a single
temperature conversion, measure an actual value.
Increase it by 20% for temperature range. A new
conversion time can be obtained by reading this
same attribute.
- other positive value:
+ * other positive value:
Set the conversion time in milliseconds.
Users: An application using the w1_term device
@@ -148,16 +170,21 @@
(RW) Control optional driver settings.
Bit masks to read/write (bitwise OR):
- 1: Enable check for conversion success. If byte 6 of
+ == ============================================================
+ 1 Enable check for conversion success. If byte 6 of
scratchpad memory is 0xC after conversion, and
temperature reads 85.00 (powerup value) or 127.94
(insufficient power) - return a conversion error.
- 2: Enable poll for conversion completion. Generate read cycles
+ 2 Enable poll for conversion completion. Generate read cycles
after the conversion start and wait for 1's. In parasite
power mode this feature is not available.
+ == ============================================================
- *read*: Currently selected features.
- *write*: Select features.
+ *read*:
+ Currently selected features.
+
+ *write*:
+ Select features.
Users: An application using the w1_term device
diff --git a/Documentation/ABI/testing/sysfs-driver-wacom b/Documentation/ABI/testing/sysfs-driver-wacom
index afc48fc..16acaa5 100644
--- a/Documentation/ABI/testing/sysfs-driver-wacom
+++ b/Documentation/ABI/testing/sysfs-driver-wacom
@@ -79,7 +79,9 @@
When the Wacom Intuos 4 is connected over Bluetooth, the
image has to contain 256 bytes (64x32 px 1 bit colour).
The format is also scrambled, like in the USB mode, and it can
- be summarized by converting 76543210 into GECA6420.
+ be summarized by converting::
+
+ 76543210 into GECA6420.
HGFEDCBA HFDB7531
What: /sys/bus/hid/devices/<bus>:<vid>:<pid>.<n>/wacom_remote/unpair_remote
diff --git a/Documentation/ABI/testing/sysfs-firmware-acpi b/Documentation/ABI/testing/sysfs-firmware-acpi
index 613f42a9..b16d30a 100644
--- a/Documentation/ABI/testing/sysfs-firmware-acpi
+++ b/Documentation/ABI/testing/sysfs-firmware-acpi
@@ -12,11 +12,14 @@
image: The image bitmap. Currently a 32-bit BMP.
status: 1 if the image is valid, 0 if firmware invalidated it.
type: 0 indicates image is in BMP format.
+
+ ======== ===================================================
version: The version of the BGRT. Currently 1.
xoffset: The number of pixels between the left of the screen
and the left edge of the image.
yoffset: The number of pixels between the top of the screen
and the top edge of the image.
+ ======== ===================================================
What: /sys/firmware/acpi/hotplug/
Date: February 2013
@@ -33,12 +36,14 @@
The following setting is available to user space for each
hotplug profile:
+ ======== =======================================================
enabled: If set, the ACPI core will handle notifications of
- hotplug events associated with the given class of
- devices and will allow those devices to be ejected with
- the help of the _EJ0 control method. Unsetting it
- effectively disables hotplug for the correspoinding
- class of devices.
+ hotplug events associated with the given class of
+ devices and will allow those devices to be ejected with
+ the help of the _EJ0 control method. Unsetting it
+ effectively disables hotplug for the correspoinding
+ class of devices.
+ ======== =======================================================
The value of the above attribute is an integer number: 1 (set)
or 0 (unset). Attempts to write any other values to it will
@@ -71,86 +76,90 @@
To figure out where all the SCI's are coming from,
/sys/firmware/acpi/interrupts contains a file listing
every possible source, and the count of how many
- times it has triggered.
+ times it has triggered::
- $ cd /sys/firmware/acpi/interrupts
- $ grep . *
- error: 0
- ff_gbl_lock: 0 enable
- ff_pmtimer: 0 invalid
- ff_pwr_btn: 0 enable
- ff_rt_clk: 2 disable
- ff_slp_btn: 0 invalid
- gpe00: 0 invalid
- gpe01: 0 enable
- gpe02: 108 enable
- gpe03: 0 invalid
- gpe04: 0 invalid
- gpe05: 0 invalid
- gpe06: 0 enable
- gpe07: 0 enable
- gpe08: 0 invalid
- gpe09: 0 invalid
- gpe0A: 0 invalid
- gpe0B: 0 invalid
- gpe0C: 0 invalid
- gpe0D: 0 invalid
- gpe0E: 0 invalid
- gpe0F: 0 invalid
- gpe10: 0 invalid
- gpe11: 0 invalid
- gpe12: 0 invalid
- gpe13: 0 invalid
- gpe14: 0 invalid
- gpe15: 0 invalid
- gpe16: 0 invalid
- gpe17: 1084 enable
- gpe18: 0 enable
- gpe19: 0 invalid
- gpe1A: 0 invalid
- gpe1B: 0 invalid
- gpe1C: 0 invalid
- gpe1D: 0 invalid
- gpe1E: 0 invalid
- gpe1F: 0 invalid
- gpe_all: 1192
- sci: 1194
- sci_not: 0
+ $ cd /sys/firmware/acpi/interrupts
+ $ grep . *
+ error: 0
+ ff_gbl_lock: 0 enable
+ ff_pmtimer: 0 invalid
+ ff_pwr_btn: 0 enable
+ ff_rt_clk: 2 disable
+ ff_slp_btn: 0 invalid
+ gpe00: 0 invalid
+ gpe01: 0 enable
+ gpe02: 108 enable
+ gpe03: 0 invalid
+ gpe04: 0 invalid
+ gpe05: 0 invalid
+ gpe06: 0 enable
+ gpe07: 0 enable
+ gpe08: 0 invalid
+ gpe09: 0 invalid
+ gpe0A: 0 invalid
+ gpe0B: 0 invalid
+ gpe0C: 0 invalid
+ gpe0D: 0 invalid
+ gpe0E: 0 invalid
+ gpe0F: 0 invalid
+ gpe10: 0 invalid
+ gpe11: 0 invalid
+ gpe12: 0 invalid
+ gpe13: 0 invalid
+ gpe14: 0 invalid
+ gpe15: 0 invalid
+ gpe16: 0 invalid
+ gpe17: 1084 enable
+ gpe18: 0 enable
+ gpe19: 0 invalid
+ gpe1A: 0 invalid
+ gpe1B: 0 invalid
+ gpe1C: 0 invalid
+ gpe1D: 0 invalid
+ gpe1E: 0 invalid
+ gpe1F: 0 invalid
+ gpe_all: 1192
+ sci: 1194
+ sci_not: 0
- sci - The number of times the ACPI SCI
- has been called and claimed an interrupt.
+ =========== ==================================================
+ sci The number of times the ACPI SCI
+ has been called and claimed an interrupt.
- sci_not - The number of times the ACPI SCI
- has been called and NOT claimed an interrupt.
+ sci_not The number of times the ACPI SCI
+ has been called and NOT claimed an interrupt.
- gpe_all - count of SCI caused by GPEs.
+ gpe_all count of SCI caused by GPEs.
- gpeXX - count for individual GPE source
+ gpeXX count for individual GPE source
- ff_gbl_lock - Global Lock
+ ff_gbl_lock Global Lock
- ff_pmtimer - PM Timer
+ ff_pmtimer PM Timer
- ff_pwr_btn - Power Button
+ ff_pwr_btn Power Button
- ff_rt_clk - Real Time Clock
+ ff_rt_clk Real Time Clock
- ff_slp_btn - Sleep Button
+ ff_slp_btn Sleep Button
- error - an interrupt that can't be accounted for above.
+ error an interrupt that can't be accounted for above.
- invalid: it's either a GPE or a Fixed Event that
- doesn't have an event handler.
+ invalid it's either a GPE or a Fixed Event that
+ doesn't have an event handler.
- disable: the GPE/Fixed Event is valid but disabled.
+ disable the GPE/Fixed Event is valid but disabled.
- enable: the GPE/Fixed Event is valid and enabled.
+ enable the GPE/Fixed Event is valid and enabled.
+ =========== ==================================================
- Root has permission to clear any of these counters. Eg.
- # echo 0 > gpe11
+ Root has permission to clear any of these counters. Eg.::
- All counters can be cleared by clearing the total "sci":
- # echo 0 > sci
+ # echo 0 > gpe11
+
+ All counters can be cleared by clearing the total "sci"::
+
+ # echo 0 > sci
None of these counters has an effect on the function
of the system, they are simply statistics.
@@ -165,32 +174,34 @@
Let's take power button fixed event for example, please kill acpid
and other user space applications so that the machine won't shutdown
- when pressing the power button.
- # cat ff_pwr_btn
- 0 enabled
- # press the power button for 3 times;
- # cat ff_pwr_btn
- 3 enabled
- # echo disable > ff_pwr_btn
- # cat ff_pwr_btn
- 3 disabled
- # press the power button for 3 times;
- # cat ff_pwr_btn
- 3 disabled
- # echo enable > ff_pwr_btn
- # cat ff_pwr_btn
- 4 enabled
- /*
- * this is because the status bit is set even if the enable bit is cleared,
- * and it triggers an ACPI fixed event when the enable bit is set again
- */
- # press the power button for 3 times;
- # cat ff_pwr_btn
- 7 enabled
- # echo disable > ff_pwr_btn
- # press the power button for 3 times;
- # echo clear > ff_pwr_btn /* clear the status bit */
- # echo disable > ff_pwr_btn
- # cat ff_pwr_btn
- 7 enabled
+ when pressing the power button::
+
+ # cat ff_pwr_btn
+ 0 enabled
+ # press the power button for 3 times;
+ # cat ff_pwr_btn
+ 3 enabled
+ # echo disable > ff_pwr_btn
+ # cat ff_pwr_btn
+ 3 disabled
+ # press the power button for 3 times;
+ # cat ff_pwr_btn
+ 3 disabled
+ # echo enable > ff_pwr_btn
+ # cat ff_pwr_btn
+ 4 enabled
+ /*
+ * this is because the status bit is set even if the enable
+ * bit is cleared, and it triggers an ACPI fixed event when
+ * the enable bit is set again
+ */
+ # press the power button for 3 times;
+ # cat ff_pwr_btn
+ 7 enabled
+ # echo disable > ff_pwr_btn
+ # press the power button for 3 times;
+ # echo clear > ff_pwr_btn /* clear the status bit */
+ # echo disable > ff_pwr_btn
+ # cat ff_pwr_btn
+ 7 enabled
diff --git a/Documentation/ABI/testing/sysfs-firmware-dmi-entries b/Documentation/ABI/testing/sysfs-firmware-dmi-entries
index 210ad44..fe0289c 100644
--- a/Documentation/ABI/testing/sysfs-firmware-dmi-entries
+++ b/Documentation/ABI/testing/sysfs-firmware-dmi-entries
@@ -33,7 +33,7 @@
doesn't matter), they will be represented in sysfs as
entries "T-0" through "T-(N-1)":
- Example entry directories:
+ Example entry directories::
/sys/firmware/dmi/entries/17-0
/sys/firmware/dmi/entries/17-1
@@ -50,61 +50,65 @@
Each DMI entry in sysfs has the common header values
exported as attributes:
- handle : The 16bit 'handle' that is assigned to this
+ ======== =================================================
+ handle The 16bit 'handle' that is assigned to this
entry by the firmware. This handle may be
referred to by other entries.
- length : The length of the entry, as presented in the
+ length The length of the entry, as presented in the
entry itself. Note that this is _not the
total count of bytes associated with the
- entry_. This value represents the length of
+ entry. This value represents the length of
the "formatted" portion of the entry. This
"formatted" region is sometimes followed by
the "unformatted" region composed of nul
terminated strings, with termination signalled
by a two nul characters in series.
- raw : The raw bytes of the entry. This includes the
+ raw The raw bytes of the entry. This includes the
"formatted" portion of the entry, the
"unformatted" strings portion of the entry,
and the two terminating nul characters.
- type : The type of the entry. This value is the same
+ type The type of the entry. This value is the same
as found in the directory name. It indicates
how the rest of the entry should be interpreted.
- instance: The instance ordinal of the entry for the
+ instance The instance ordinal of the entry for the
given type. This value is the same as found
in the parent directory name.
- position: The ordinal position (zero-based) of the entry
+ position The ordinal position (zero-based) of the entry
within the entirety of the DMI entry table.
+ ======== =================================================
- === Entry Specialization ===
+ **Entry Specialization**
Some entry types may have other information available in
sysfs. Not all types are specialized.
- --- Type 15 - System Event Log ---
+ **Type 15 - System Event Log**
This entry allows the firmware to export a log of
events the system has taken. This information is
typically backed by nvram, but the implementation
details are abstracted by this table. This entry's data
- is exported in the directory:
+ is exported in the directory::
- /sys/firmware/dmi/entries/15-0/system_event_log
+ /sys/firmware/dmi/entries/15-0/system_event_log
and has the following attributes (documented in the
SMBIOS / DMI specification under "System Event Log (Type 15)":
- area_length
- header_start_offset
- data_start_offset
- access_method
- status
- change_token
- access_method_address
- header_format
- per_log_type_descriptor_length
- type_descriptors_supported_count
+ - area_length
+ - header_start_offset
+ - data_start_offset
+ - access_method
+ - status
+ - change_token
+ - access_method_address
+ - header_format
+ - per_log_type_descriptor_length
+ - type_descriptors_supported_count
As well, the kernel exports the binary attribute:
- raw_event_log : The raw binary bits of the event log
+ ============= ====================================
+ raw_event_log The raw binary bits of the event log
as described by the DMI entry.
+ ============= ====================================
diff --git a/Documentation/ABI/testing/sysfs-firmware-efi-esrt b/Documentation/ABI/testing/sysfs-firmware-efi-esrt
index 6e431d1..31b5767 100644
--- a/Documentation/ABI/testing/sysfs-firmware-efi-esrt
+++ b/Documentation/ABI/testing/sysfs-firmware-efi-esrt
@@ -35,10 +35,13 @@
Date: February 2015
Contact: Peter Jones <pjones@redhat.com>
Description: What kind of firmware entry this is:
- 0 - Unknown
- 1 - System Firmware
- 2 - Device Firmware
- 3 - UEFI Driver
+
+ == ===============
+ 0 Unknown
+ 1 System Firmware
+ 2 Device Firmware
+ 3 UEFI Driver
+ == ===============
What: /sys/firmware/efi/esrt/entries/entry$N/fw_class
Date: February 2015
@@ -71,11 +74,14 @@
Contact: Peter Jones <pjones@redhat.com>
Description: The result of the last firmware update attempt for the
firmware resource entry.
- 0 - Success
- 1 - Insufficient resources
- 2 - Incorrect version
- 3 - Invalid format
- 4 - Authentication error
- 5 - AC power event
- 6 - Battery power event
+
+ == ======================
+ 0 Success
+ 1 Insufficient resources
+ 2 Incorrect version
+ 3 Invalid format
+ 4 Authentication error
+ 5 AC power event
+ 6 Battery power event
+ == ======================
diff --git a/Documentation/ABI/testing/sysfs-firmware-efi-runtime-map b/Documentation/ABI/testing/sysfs-firmware-efi-runtime-map
index c61b9b3..9c4d581 100644
--- a/Documentation/ABI/testing/sysfs-firmware-efi-runtime-map
+++ b/Documentation/ABI/testing/sysfs-firmware-efi-runtime-map
@@ -14,7 +14,7 @@
/sys/firmware/efi/runtime-map/ is the directory the kernel
exports that information in.
- subdirectories are named with the number of the memory range:
+ subdirectories are named with the number of the memory range::
/sys/firmware/efi/runtime-map/0
/sys/firmware/efi/runtime-map/1
@@ -24,11 +24,13 @@
Each subdirectory contains five files:
- attribute : The attributes of the memory range.
- num_pages : The size of the memory range in pages.
- phys_addr : The physical address of the memory range.
- type : The type of the memory range.
- virt_addr : The virtual address of the memory range.
+ ========= =========================================
+ attribute The attributes of the memory range.
+ num_pages The size of the memory range in pages.
+ phys_addr The physical address of the memory range.
+ type The type of the memory range.
+ virt_addr The virtual address of the memory range.
+ ========= =========================================
Above values are all hexadecimal numbers with the '0x' prefix.
Users: Kexec
diff --git a/Documentation/ABI/testing/sysfs-firmware-gsmi b/Documentation/ABI/testing/sysfs-firmware-gsmi
index 0faa0aa..7a55835 100644
--- a/Documentation/ABI/testing/sysfs-firmware-gsmi
+++ b/Documentation/ABI/testing/sysfs-firmware-gsmi
@@ -20,7 +20,7 @@
This directory has the same layout (and
underlying implementation as /sys/firmware/efi/vars.
- See Documentation/ABI/*/sysfs-firmware-efi-vars
+ See `Documentation/ABI/*/sysfs-firmware-efi-vars`
for more information on how to interact with
this structure.
diff --git a/Documentation/ABI/testing/sysfs-firmware-memmap b/Documentation/ABI/testing/sysfs-firmware-memmap
index eca0d65..1f6f4d3 100644
--- a/Documentation/ABI/testing/sysfs-firmware-memmap
+++ b/Documentation/ABI/testing/sysfs-firmware-memmap
@@ -20,7 +20,7 @@
the raw memory map to userspace.
The structure is as follows: Under /sys/firmware/memmap there
- are subdirectories with the number of the entry as their name:
+ are subdirectories with the number of the entry as their name::
/sys/firmware/memmap/0
/sys/firmware/memmap/1
@@ -34,14 +34,16 @@
Each directory contains three files:
- start : The start address (as hexadecimal number with the
+ ======== =====================================================
+ start The start address (as hexadecimal number with the
'0x' prefix).
- end : The end address, inclusive (regardless whether the
+ end The end address, inclusive (regardless whether the
firmware provides inclusive or exclusive ranges).
- type : Type of the entry as string. See below for a list of
+ type Type of the entry as string. See below for a list of
valid types.
+ ======== =====================================================
- So, for example:
+ So, for example::
/sys/firmware/memmap/0/start
/sys/firmware/memmap/0/end
@@ -57,9 +59,8 @@
- reserved
Following shell snippet can be used to display that memory
- map in a human-readable format:
+ map in a human-readable format::
- -------------------- 8< ----------------------------------------
#!/bin/bash
cd /sys/firmware/memmap
for dir in * ; do
@@ -68,4 +69,3 @@
type=$(cat $dir/type)
printf "%016x-%016x (%s)\n" $start $[ $end +1] "$type"
done
- -------------------- >8 ----------------------------------------
diff --git a/Documentation/ABI/testing/sysfs-firmware-qemu_fw_cfg b/Documentation/ABI/testing/sysfs-firmware-qemu_fw_cfg
index 011dda4..ee0d6db 100644
--- a/Documentation/ABI/testing/sysfs-firmware-qemu_fw_cfg
+++ b/Documentation/ABI/testing/sysfs-firmware-qemu_fw_cfg
@@ -15,7 +15,7 @@
to the fw_cfg device can be found in "docs/specs/fw_cfg.txt"
in the QEMU source tree.
- === SysFS fw_cfg Interface ===
+ **SysFS fw_cfg Interface**
The fw_cfg sysfs interface described in this document is only
intended to display discoverable blobs (i.e., those registered
@@ -31,7 +31,7 @@
/sys/firmware/qemu_fw_cfg/rev
- --- Discoverable fw_cfg blobs by selector key ---
+ **Discoverable fw_cfg blobs by selector key**
All discoverable blobs listed in the fw_cfg file directory are
displayed as entries named after their unique selector key
@@ -45,24 +45,26 @@
Each such fw_cfg sysfs entry has the following values exported
as attributes:
- name : The 56-byte nul-terminated ASCII string used as the
+ ==== ====================================================
+ name The 56-byte nul-terminated ASCII string used as the
blob's 'file name' in the fw_cfg directory.
- size : The length of the blob, as given in the fw_cfg
+ size The length of the blob, as given in the fw_cfg
directory.
- key : The value of the blob's selector key as given in the
+ key The value of the blob's selector key as given in the
fw_cfg directory. This value is the same as used in
the parent directory name.
- raw : The raw bytes of the blob, obtained by selecting the
+ raw The raw bytes of the blob, obtained by selecting the
entry via the control register, and reading a number
of bytes equal to the blob size from the data
register.
+ ==== ====================================================
- --- Listing fw_cfg blobs by file name ---
+ **Listing fw_cfg blobs by file name**
While the fw_cfg device does not impose any specific naming
convention on the blobs registered in the file directory,
QEMU developers have traditionally used path name semantics
- to give each blob a descriptive name. For example:
+ to give each blob a descriptive name. For example::
"bootorder"
"genroms/kvmvapic.bin"
@@ -81,7 +83,7 @@
of directories matching the path name components of fw_cfg
blob names, ending in symlinks to the by_key entry for each
"basename", as illustrated below (assume current directory is
- /sys/firmware):
+ /sys/firmware)::
qemu_fw_cfg/by_name/bootorder -> ../by_key/38
qemu_fw_cfg/by_name/etc/e820 -> ../../by_key/35
diff --git a/Documentation/ABI/testing/sysfs-firmware-sfi b/Documentation/ABI/testing/sysfs-firmware-sfi
index 4be7d44..5210e0f 100644
--- a/Documentation/ABI/testing/sysfs-firmware-sfi
+++ b/Documentation/ABI/testing/sysfs-firmware-sfi
@@ -9,7 +9,7 @@
http://simplefirmware.org/documentation
While the tables are used by the kernel, user-space
- can observe them this way:
+ can observe them this way::
- # cd /sys/firmware/sfi/tables
- # cat $TABLENAME > $TABLENAME.bin
+ # cd /sys/firmware/sfi/tables
+ # cat $TABLENAME > $TABLENAME.bin
diff --git a/Documentation/ABI/testing/sysfs-firmware-sgi_uv b/Documentation/ABI/testing/sysfs-firmware-sgi_uv
index 4573fd4..66800baa 100644
--- a/Documentation/ABI/testing/sysfs-firmware-sgi_uv
+++ b/Documentation/ABI/testing/sysfs-firmware-sgi_uv
@@ -5,7 +5,7 @@
The /sys/firmware/sgi_uv directory contains information
about the SGI UV platform.
- Under that directory are a number of files:
+ Under that directory are a number of files::
partition_id
coherence_id
@@ -14,7 +14,7 @@
SGI UV systems can be partitioned into multiple physical
machines, which each partition running a unique copy
of the operating system. Each partition will have a unique
- partition id. To display the partition id, use the command:
+ partition id. To display the partition id, use the command::
cat /sys/firmware/sgi_uv/partition_id
@@ -22,6 +22,6 @@
A partitioned SGI UV system can have one or more coherence
domain. The coherence id indicates which coherence domain
this partition is in. To display the coherence id, use the
- command:
+ command::
cat /sys/firmware/sgi_uv/coherence_id
diff --git a/Documentation/ABI/testing/sysfs-firmware-turris-mox-rwtm b/Documentation/ABI/testing/sysfs-firmware-turris-mox-rwtm
index 15595fa..b8631f5 100644
--- a/Documentation/ABI/testing/sysfs-firmware-turris-mox-rwtm
+++ b/Documentation/ABI/testing/sysfs-firmware-turris-mox-rwtm
@@ -2,21 +2,21 @@
Date: August 2019
KernelVersion: 5.4
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) Board version burned into eFuses of this Turris Mox board.
+Description: (Read) Board version burned into eFuses of this Turris Mox board.
Format: %i
What: /sys/firmware/turris-mox-rwtm/mac_address*
Date: August 2019
KernelVersion: 5.4
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) MAC addresses burned into eFuses of this Turris Mox board.
+Description: (Read) MAC addresses burned into eFuses of this Turris Mox board.
Format: %pM
What: /sys/firmware/turris-mox-rwtm/pubkey
Date: August 2019
KernelVersion: 5.4
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) ECDSA public key (in pubkey hex compressed form) computed
+Description: (Read) ECDSA public key (in pubkey hex compressed form) computed
as pair to the ECDSA private key burned into eFuses of this
Turris Mox Board.
Format: string
@@ -25,7 +25,7 @@
Date: August 2019
KernelVersion: 5.4
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) RAM size in MiB of this Turris Mox board as was detected
+Description: (Read) RAM size in MiB of this Turris Mox board as was detected
during manufacturing and burned into eFuses. Can be 512 or 1024.
Format: %i
@@ -33,5 +33,5 @@
Date: August 2019
KernelVersion: 5.4
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) Serial number burned into eFuses of this Turris Mox device.
+Description: (Read) Serial number burned into eFuses of this Turris Mox device.
Format: %016X
diff --git a/Documentation/ABI/testing/sysfs-fs-ext4 b/Documentation/ABI/testing/sysfs-fs-ext4
index 78604db..99e3d92 100644
--- a/Documentation/ABI/testing/sysfs-fs-ext4
+++ b/Documentation/ABI/testing/sysfs-fs-ext4
@@ -45,8 +45,8 @@
parameter will have their blocks allocated out of a
block group specific preallocation pool, so that small
files are packed closely together. Each large file
- will have its blocks allocated out of its own unique
- preallocation pool.
+ will have its blocks allocated out of its own unique
+ preallocation pool.
What: /sys/fs/ext4/<disk>/inode_readahead_blks
Date: March 2008
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index 834d0be..67b3ed8 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -20,10 +20,13 @@
Date: July 2013
Contact: "Namjae Jeon" <namjae.jeon@samsung.com>
Description: Controls the victim selection policy for garbage collection.
- Setting gc_idle = 0(default) will disable this option. Setting
- gc_idle = 1 will select the Cost Benefit approach & setting
- gc_idle = 2 will select the greedy approach & setting
- gc_idle = 3 will select the age-threshold based approach.
+ Setting gc_idle = 0(default) will disable this option. Setting:
+
+ =========== ===============================================
+ gc_idle = 1 will select the Cost Benefit approach & setting
+ gc_idle = 2 will select the greedy approach & setting
+ gc_idle = 3 will select the age-threshold based approach.
+ =========== ===============================================
What: /sys/fs/f2fs/<disk>/reclaim_segments
Date: October 2013
@@ -46,10 +49,17 @@
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
Description: Controls the in-place-update policy.
updates in f2fs. User can set:
- 0x01: F2FS_IPU_FORCE, 0x02: F2FS_IPU_SSR,
- 0x04: F2FS_IPU_UTIL, 0x08: F2FS_IPU_SSR_UTIL,
- 0x10: F2FS_IPU_FSYNC, 0x20: F2FS_IPU_ASYNC,
- 0x40: F2FS_IPU_NOCACHE.
+
+ ==== =================
+ 0x01 F2FS_IPU_FORCE
+ 0x02 F2FS_IPU_SSR
+ 0x04 F2FS_IPU_UTIL
+ 0x08 F2FS_IPU_SSR_UTIL
+ 0x10 F2FS_IPU_FSYNC
+ 0x20 F2FS_IPU_ASYNC,
+ 0x40 F2FS_IPU_NOCACHE
+ ==== =================
+
Refer segment.h for details.
What: /sys/fs/f2fs/<disk>/min_ipu_util
@@ -332,18 +342,28 @@
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description: Give a way to attach REQ_META|FUA to data writes
given temperature-based bits. Now the bits indicate:
- * REQ_META | REQ_FUA |
- * 5 | 4 | 3 | 2 | 1 | 0 |
- * Cold | Warm | Hot | Cold | Warm | Hot |
+
+ +-------------------+-------------------+
+ | REQ_META | REQ_FUA |
+ +------+------+-----+------+------+-----+
+ | 5 | 4 | 3 | 2 | 1 | 0 |
+ +------+------+-----+------+------+-----+
+ | Cold | Warm | Hot | Cold | Warm | Hot |
+ +------+------+-----+------+------+-----+
What: /sys/fs/f2fs/<disk>/node_io_flag
Date: June 2020
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description: Give a way to attach REQ_META|FUA to node writes
given temperature-based bits. Now the bits indicate:
- * REQ_META | REQ_FUA |
- * 5 | 4 | 3 | 2 | 1 | 0 |
- * Cold | Warm | Hot | Cold | Warm | Hot |
+
+ +-------------------+-------------------+
+ | REQ_META | REQ_FUA |
+ +------+------+-----+------+------+-----+
+ | 5 | 4 | 3 | 2 | 1 | 0 |
+ +------+------+-----+------+------+-----+
+ | Cold | Warm | Hot | Cold | Warm | Hot |
+ +------+------+-----+------+------+-----+
What: /sys/fs/f2fs/<disk>/iostat_period_ms
Date: April 2020
diff --git a/Documentation/ABI/testing/sysfs-hypervisor-xen b/Documentation/ABI/testing/sysfs-hypervisor-xen
index 53b7b2e..4dbe0c4 100644
--- a/Documentation/ABI/testing/sysfs-hypervisor-xen
+++ b/Documentation/ABI/testing/sysfs-hypervisor-xen
@@ -15,14 +15,17 @@
Contact: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Description: If running under Xen:
Describes mode that Xen's performance-monitoring unit (PMU)
- uses. Accepted values are
- "off" -- PMU is disabled
- "self" -- The guest can profile itself
- "hv" -- The guest can profile itself and, if it is
+ uses. Accepted values are:
+
+ ====== ============================================
+ "off" PMU is disabled
+ "self" The guest can profile itself
+ "hv" The guest can profile itself and, if it is
privileged (e.g. dom0), the hypervisor
- "all" -- The guest can profile itself, the hypervisor
+ "all" The guest can profile itself, the hypervisor
and all other guests. Only available to
privileged guests.
+ ====== ============================================
What: /sys/hypervisor/pmu/pmu_features
Date: August 2015
diff --git a/Documentation/ABI/testing/sysfs-kernel-boot_params b/Documentation/ABI/testing/sysfs-kernel-boot_params
index eca38ce..7f9bda4 100644
--- a/Documentation/ABI/testing/sysfs-kernel-boot_params
+++ b/Documentation/ABI/testing/sysfs-kernel-boot_params
@@ -23,16 +23,17 @@
representation of setup_data type. "data" file is the binary
representation of setup_data payload.
- The whole boot_params directory structure is like below:
- /sys/kernel/boot_params
- |__ data
- |__ setup_data
- | |__ 0
- | | |__ data
- | | |__ type
- | |__ 1
- | |__ data
- | |__ type
- |__ version
+ The whole boot_params directory structure is like below::
+
+ /sys/kernel/boot_params
+ |__ data
+ |__ setup_data
+ | |__ 0
+ | | |__ data
+ | | |__ type
+ | |__ 1
+ | |__ data
+ | |__ type
+ |__ version
Users: Kexec
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-hugepages b/Documentation/ABI/testing/sysfs-kernel-mm-hugepages
index fdaa216..294387e 100644
--- a/Documentation/ABI/testing/sysfs-kernel-mm-hugepages
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-hugepages
@@ -7,9 +7,11 @@
of the hugepages supported by the kernel/CPU combination.
Under these directories are a number of files:
- nr_hugepages
- nr_overcommit_hugepages
- free_hugepages
- surplus_hugepages
- resv_hugepages
+
+ - nr_hugepages
+ - nr_overcommit_hugepages
+ - free_hugepages
+ - surplus_hugepages
+ - resv_hugepages
+
See Documentation/admin-guide/mm/hugetlbpage.rst for details.
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-ksm b/Documentation/ABI/testing/sysfs-kernel-mm-ksm
index dfc1324..1c9bed5 100644
--- a/Documentation/ABI/testing/sysfs-kernel-mm-ksm
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-ksm
@@ -34,8 +34,9 @@
in a tree.
run: write 0 to disable ksm, read 0 while ksm is disabled.
- write 1 to run ksm, read 1 while ksm is running.
- write 2 to disable ksm and unmerge all its pages.
+
+ - write 1 to run ksm, read 1 while ksm is running.
+ - write 2 to disable ksm and unmerge all its pages.
sleep_millisecs: how many milliseconds ksm should sleep between
scans.
diff --git a/Documentation/ABI/testing/sysfs-kernel-slab b/Documentation/ABI/testing/sysfs-kernel-slab
index ed35833a..c9f12ba 100644
--- a/Documentation/ABI/testing/sysfs-kernel-slab
+++ b/Documentation/ABI/testing/sysfs-kernel-slab
@@ -346,6 +346,7 @@
number of objects per slab. If a slab cannot be allocated
because of fragmentation, SLUB will retry with the minimum order
possible depending on its characteristics.
+
When debug_guardpage_minorder=N (N > 0) parameter is specified
(see Documentation/admin-guide/kernel-parameters.rst), the minimum possible
order is used and this sysfs entry can not be used to change
@@ -361,6 +362,7 @@
new slab has not been possible at the cache's order and instead
fallen back to its minimum possible order. It can be written to
clear the current count.
+
Available when CONFIG_SLUB_STATS is enabled.
What: /sys/kernel/slab/cache/partial
@@ -410,6 +412,7 @@
slab from a remote node as opposed to allocating a new slab on
the local node. This reduces the amount of wasted memory over
the entire system but can be expensive.
+
Available when CONFIG_NUMA is enabled.
What: /sys/kernel/slab/cache/sanity_checks
diff --git a/Documentation/ABI/testing/sysfs-module b/Documentation/ABI/testing/sysfs-module
index 0aac02e..353c0db5 100644
--- a/Documentation/ABI/testing/sysfs-module
+++ b/Documentation/ABI/testing/sysfs-module
@@ -17,14 +17,15 @@
Contact: Kirill Smelkov <kirr@mns.spb.ru>
Description: Maximum time allowed for periodic transfers per microframe (μs)
- [ USB 2.0 sets maximum allowed time for periodic transfers per
+ Note:
+ USB 2.0 sets maximum allowed time for periodic transfers per
microframe to be 80%, that is 100 microseconds out of 125
microseconds (full microframe).
However there are cases, when 80% max isochronous bandwidth is
too limiting. For example two video streams could require 110
microseconds of isochronous bandwidth per microframe to work
- together. ]
+ together.
Through this setting it is possible to raise the limit so that
the host controller would allow allocating more than 100
@@ -45,8 +46,10 @@
KernelVersion:»·3.3
Contact: Kay Sievers <kay.sievers@vrfy.org>
Description: Module taint flags:
- P - proprietary module
- O - out-of-tree module
- F - force-loaded module
- C - staging driver module
- E - unsigned module
+ == =====================
+ P proprietary module
+ O out-of-tree module
+ F force-loaded module
+ C staging driver module
+ E unsigned module
+ == =====================
diff --git a/Documentation/ABI/testing/sysfs-platform-asus-laptop b/Documentation/ABI/testing/sysfs-platform-asus-laptop
index 8b0e820..c78d358 100644
--- a/Documentation/ABI/testing/sysfs-platform-asus-laptop
+++ b/Documentation/ABI/testing/sysfs-platform-asus-laptop
@@ -4,13 +4,16 @@
Contact: "Corentin Chary" <corentincj@iksaif.net>
Description:
This file allows display switching. The value
- is composed by 4 bits and defined as follow:
- 4321
- |||`- LCD
- ||`-- CRT
- |`--- TV
- `---- DVI
- Ex: - 0 (0000b) means no display
+ is composed by 4 bits and defined as follow::
+
+ 4321
+ |||`- LCD
+ ||`-- CRT
+ |`--- TV
+ `---- DVI
+
+ Ex:
+ - 0 (0000b) means no display
- 3 (0011b) CRT+LCD.
What: /sys/devices/platform/asus_laptop/gps
@@ -28,8 +31,10 @@
Description:
Some models like the W1N have a LED display that can be
used to display several items of information.
- To control the LED display, use the following :
+ To control the LED display, use the following::
+
echo 0x0T000DDD > /sys/devices/platform/asus_laptop/
+
where T control the 3 letters display, and DDD the 3 digits display.
The DDD table can be found in Documentation/admin-guide/laptops/asus-laptop.rst
diff --git a/Documentation/ABI/testing/sysfs-platform-asus-wmi b/Documentation/ABI/testing/sysfs-platform-asus-wmi
index 1efac0d..0488573 100644
--- a/Documentation/ABI/testing/sysfs-platform-asus-wmi
+++ b/Documentation/ABI/testing/sysfs-platform-asus-wmi
@@ -5,6 +5,7 @@
Description:
Change CPU clock configuration (write-only).
There are three available clock configuration:
+
* 0 -> Super Performance Mode
* 1 -> High Performance Mode
* 2 -> Power Saving Mode
diff --git a/Documentation/ABI/testing/sysfs-platform-at91 b/Documentation/ABI/testing/sysfs-platform-at91
index 4cc6a86..b146be7 100644
--- a/Documentation/ABI/testing/sysfs-platform-at91
+++ b/Documentation/ABI/testing/sysfs-platform-at91
@@ -18,8 +18,10 @@
In order to use an extended can_id add the
CAN_EFF_FLAG (0x80000000U) to the can_id. Example:
- - standard id 0x7ff:
- echo 0x7ff > /sys/class/net/can0/mb0_id
+ - standard id 0x7ff::
- - extended id 0x1fffffff:
- echo 0x9fffffff > /sys/class/net/can0/mb0_id
+ echo 0x7ff > /sys/class/net/can0/mb0_id
+
+ - extended id 0x1fffffff::
+
+ echo 0x9fffffff > /sys/class/net/can0/mb0_id
diff --git a/Documentation/ABI/testing/sysfs-platform-dell-laptop b/Documentation/ABI/testing/sysfs-platform-dell-laptop
index 9b917c7..82bcfe9 100644
--- a/Documentation/ABI/testing/sysfs-platform-dell-laptop
+++ b/Documentation/ABI/testing/sysfs-platform-dell-laptop
@@ -34,9 +34,12 @@
this file. To disable a trigger, write its name preceded
by '-' instead.
- For example, to enable the keyboard as trigger run:
+ For example, to enable the keyboard as trigger run::
+
echo +keyboard > /sys/class/leds/dell::kbd_backlight/start_triggers
- To disable it:
+
+ To disable it::
+
echo -keyboard > /sys/class/leds/dell::kbd_backlight/start_triggers
Note that not all the available triggers can be configured.
@@ -57,7 +60,8 @@
with any the above units. If no unit is specified, the value
is assumed to be expressed in seconds.
- For example, to set the timeout to 10 minutes run:
+ For example, to set the timeout to 10 minutes run::
+
echo 10m > /sys/class/leds/dell::kbd_backlight/stop_timeout
Note that when this file is read, the returned value might be
diff --git a/Documentation/ABI/testing/sysfs-platform-dell-smbios b/Documentation/ABI/testing/sysfs-platform-dell-smbios
index 205d3b6..e6e0f7f 100644
--- a/Documentation/ABI/testing/sysfs-platform-dell-smbios
+++ b/Documentation/ABI/testing/sysfs-platform-dell-smbios
@@ -13,8 +13,8 @@
For example the token ID "5" would be available
as the following attributes:
- 0005_location
- 0005_value
+ - 0005_location
+ - 0005_value
Tokens will vary from machine to machine, and
only tokens available on that machine will be
diff --git a/Documentation/ABI/testing/sysfs-platform-dfl-fme b/Documentation/ABI/testing/sysfs-platform-dfl-fme
index 3683cb1c..d6ab34e 100644
--- a/Documentation/ABI/testing/sysfs-platform-dfl-fme
+++ b/Documentation/ABI/testing/sysfs-platform-dfl-fme
@@ -113,8 +113,11 @@
Contact: Wu Hao <hao.wu@intel.com>
Description: Read-Only. Read this file to get the name of hwmon device, it
supports values:
- 'dfl_fme_thermal' - thermal hwmon device name
- 'dfl_fme_power' - power hwmon device name
+
+ ================= =========================
+ 'dfl_fme_thermal' thermal hwmon device name
+ 'dfl_fme_power' power hwmon device name
+ ================= =========================
What: /sys/bus/platform/devices/dfl-fme.0/hwmon/hwmonX/temp1_input
Date: October 2019
@@ -169,8 +172,11 @@
Contact: Wu Hao <hao.wu@intel.com>
Description: Read-Only. Read this file to get the policy of hardware threshold1
(see 'temp1_max'). It only supports two values (policies):
- 0 - AP2 state (90% throttling)
- 1 - AP1 state (50% throttling)
+
+ == ==========================
+ 0 AP2 state (90% throttling)
+ 1 AP1 state (50% throttling)
+ == ==========================
What: /sys/bus/platform/devices/dfl-fme.0/hwmon/hwmonX/power1_input
Date: October 2019
diff --git a/Documentation/ABI/testing/sysfs-platform-dptf b/Documentation/ABI/testing/sysfs-platform-dptf
index 2cbc660..1418343 100644
--- a/Documentation/ABI/testing/sysfs-platform-dptf
+++ b/Documentation/ABI/testing/sysfs-platform-dptf
@@ -27,12 +27,15 @@
Contact: linux-acpi@vger.kernel.org
Description:
(RO) Display the platform power source
+
+ ========= ============================
bits[3:0] Current power source
- 0x00 = DC
- 0x01 = AC
- 0x02 = USB
- 0x03 = Wireless Charger
+ - 0x00 = DC
+ - 0x01 = AC
+ - 0x02 = USB
+ - 0x03 = Wireless Charger
bits[7:4] Power source sequence number
+ ========= ============================
What: /sys/bus/platform/devices/INT3407:00/dptf_power/battery_steady_power
Date: Jul, 2016
diff --git a/Documentation/ABI/testing/sysfs-platform-eeepc-laptop b/Documentation/ABI/testing/sysfs-platform-eeepc-laptop
index 5b026c6..70dbe07 100644
--- a/Documentation/ABI/testing/sysfs-platform-eeepc-laptop
+++ b/Documentation/ABI/testing/sysfs-platform-eeepc-laptop
@@ -4,9 +4,11 @@
Contact: "Corentin Chary" <corentincj@iksaif.net>
Description:
This file allows display switching.
+
- 1 = LCD
- 2 = CRT
- 3 = LCD+CRT
+
If you run X11, you should use xrandr instead.
What: /sys/devices/platform/eeepc/camera
@@ -30,16 +32,20 @@
Description:
Change CPU clock configuration.
On the Eee PC 1000H there are three available clock configuration:
+
* 0 -> Super Performance Mode
* 1 -> High Performance Mode
* 2 -> Power Saving Mode
+
On Eee PC 701 there is only 2 available clock configurations.
Available configuration are listed in available_cpufv file.
Reading this file will show the raw hexadecimal value which
- is defined as follow:
- | 8 bit | 8 bit |
- | `---- Current mode
- `------------ Availables modes
+ is defined as follow::
+
+ | 8 bit | 8 bit |
+ | `---- Current mode
+ `------------ Availables modes
+
For example, 0x301 means: mode 1 selected, 3 available modes.
What: /sys/devices/platform/eeepc/available_cpufv
diff --git a/Documentation/ABI/testing/sysfs-platform-i2c-demux-pinctrl b/Documentation/ABI/testing/sysfs-platform-i2c-demux-pinctrl
index c394b808..b6a138b 100644
--- a/Documentation/ABI/testing/sysfs-platform-i2c-demux-pinctrl
+++ b/Documentation/ABI/testing/sysfs-platform-i2c-demux-pinctrl
@@ -5,9 +5,9 @@
Description:
Reading the file will give you a list of masters which can be
selected for a demultiplexed bus. The format is
- "<index>:<name>". Example from a Renesas Lager board:
+ "<index>:<name>". Example from a Renesas Lager board::
- 0:/i2c@e6500000 1:/i2c@e6508000
+ 0:/i2c@e6500000 1:/i2c@e6508000
What: /sys/devices/platform/<i2c-demux-name>/current_master
Date: January 2016
diff --git a/Documentation/ABI/testing/sysfs-platform-ideapad-laptop b/Documentation/ABI/testing/sysfs-platform-ideapad-laptop
index 1b31be3..fd2ac02 100644
--- a/Documentation/ABI/testing/sysfs-platform-ideapad-laptop
+++ b/Documentation/ABI/testing/sysfs-platform-ideapad-laptop
@@ -12,6 +12,7 @@
Description:
Change fan mode
There are four available modes:
+
* 0 -> Super Silent Mode
* 1 -> Standard Mode
* 2 -> Dust Cleaning
@@ -32,9 +33,11 @@
Contact: "Oleg Keri <ezhi99@gmail.com>"
Description:
Control fn-lock mode.
+
* 1 -> Switched On
* 0 -> Switched Off
- For example:
- # echo "0" > \
- /sys/bus/pci/devices/0000:00:1f.0/PNP0C09:00/VPC2004:00/fn_lock
+ For example::
+
+ # echo "0" > \
+ /sys/bus/pci/devices/0000:00:1f.0/PNP0C09:00/VPC2004:00/fn_lock
diff --git a/Documentation/ABI/testing/sysfs-platform-intel-wmi-sbl-fw-update b/Documentation/ABI/testing/sysfs-platform-intel-wmi-sbl-fw-update
index 5aa6189..02ae1e9 100644
--- a/Documentation/ABI/testing/sysfs-platform-intel-wmi-sbl-fw-update
+++ b/Documentation/ABI/testing/sysfs-platform-intel-wmi-sbl-fw-update
@@ -8,5 +8,6 @@
of 0 and userspace can signal SBL to update firmware,
on next reboot, by writing a value of 1.
There are two available states:
+
* 0 -> Skip firmware update while rebooting
* 1 -> Attempt firmware update on next reboot
diff --git a/Documentation/ABI/testing/sysfs-platform-intel-wmi-thunderbolt b/Documentation/ABI/testing/sysfs-platform-intel-wmi-thunderbolt
index 8af6505..e19144f 100644
--- a/Documentation/ABI/testing/sysfs-platform-intel-wmi-thunderbolt
+++ b/Documentation/ABI/testing/sysfs-platform-intel-wmi-thunderbolt
@@ -7,5 +7,6 @@
Thunderbolt controllers to turn on or off when no
devices are connected (write-only)
There are two available states:
+
* 0 -> Force power disabled
* 1 -> Force power enabled
diff --git a/Documentation/ABI/testing/sysfs-platform-kim b/Documentation/ABI/testing/sysfs-platform-kim
index c165327..a7f81de 100644
--- a/Documentation/ABI/testing/sysfs-platform-kim
+++ b/Documentation/ABI/testing/sysfs-platform-kim
@@ -5,6 +5,7 @@
Description:
Name of the UART device at which the WL128x chip
is connected. example: "/dev/ttyS0".
+
The device name flows down to architecture specific board
initialization file from the SFI/ATAGS bootloader
firmware. The name exposed is read from the user-space
diff --git a/Documentation/ABI/testing/sysfs-platform-mellanox-bootctl b/Documentation/ABI/testing/sysfs-platform-mellanox-bootctl
index 401d202..e79ca22 100644
--- a/Documentation/ABI/testing/sysfs-platform-mellanox-bootctl
+++ b/Documentation/ABI/testing/sysfs-platform-mellanox-bootctl
@@ -5,10 +5,13 @@
Description:
The Life-cycle state of the SoC, which could be one of the
following values.
- Production - Production state and can be updated to secure
- GA Secured - Secure chip and not able to change state
- GA Non-Secured - Non-Secure chip and not able to change state
- RMA - Return Merchandise Authorization
+
+ ============== =============================================
+ Production Production state and can be updated to secure
+ GA Secured Secure chip and not able to change state
+ GA Non-Secured Non-Secure chip and not able to change state
+ RMA Return Merchandise Authorization
+ ============== =============================================
What: /sys/bus/platform/devices/MLNXBF04:00/post_reset_wdog
Date: Oct 2019
@@ -25,10 +28,13 @@
Contact: "Liming Sun <lsun@mellanox.com>"
Description:
The source of the boot stream for the next reset. It could be
- one of the following values.
- external - boot from external source (USB or PCIe)
- emmc - boot from the onchip eMMC
- emmc_legacy - boot from the onchip eMMC in legacy (slow) mode
+ one of the following values:
+
+ =========== ===============================================
+ external boot from external source (USB or PCIe)
+ emmc boot from the onchip eMMC
+ emmc_legacy boot from the onchip eMMC in legacy (slow) mode
+ =========== ===============================================
What: /sys/bus/platform/devices/MLNXBF04:00/second_reset_action
Date: Oct 2019
@@ -38,11 +44,14 @@
Update the source of the boot stream after next reset. It could
be one of the following values and will be applied after next
reset.
- external - boot from external source (USB or PCIe)
- emmc - boot from the onchip eMMC
- emmc_legacy - boot from the onchip eMMC in legacy (slow) mode
- swap_emmc - swap the primary / secondary boot partition
- none - cancel the action
+
+ =========== ===============================================
+ external boot from external source (USB or PCIe)
+ emmc boot from the onchip eMMC
+ emmc_legacy boot from the onchip eMMC in legacy (slow) mode
+ swap_emmc swap the primary / secondary boot partition
+ none cancel the action
+ =========== ===============================================
What: /sys/bus/platform/devices/MLNXBF04:00/secure_boot_fuse_state
Date: Oct 2019
@@ -50,9 +59,12 @@
Contact: "Liming Sun <lsun@mellanox.com>"
Description:
The state of eFuse versions with the following values.
- InUse - burnt, valid and currently in use
- Used - burnt and valid
- Free - not burnt and free to use
- Skipped - not burnt but not free (skipped)
- Wasted - burnt and invalid
- Invalid - not burnt but marked as valid (error state).
+
+ ======= ===============================================
+ InUse burnt, valid and currently in use
+ Used burnt and valid
+ Free not burnt and free to use
+ Skipped not burnt but not free (skipped)
+ Wasted burnt and invalid
+ Invalid not burnt but marked as valid (error state).
+ ======= ===============================================
diff --git a/Documentation/ABI/testing/sysfs-platform-phy-rcar-gen3-usb2 b/Documentation/ABI/testing/sysfs-platform-phy-rcar-gen3-usb2
index 6212697..bc510cc 100644
--- a/Documentation/ABI/testing/sysfs-platform-phy-rcar-gen3-usb2
+++ b/Documentation/ABI/testing/sysfs-platform-phy-rcar-gen3-usb2
@@ -7,9 +7,11 @@
The file can show/change the phy mode for role swap of usb.
Write the following strings to change the mode:
- "host" - switching mode from peripheral to host.
- "peripheral" - switching mode from host to peripheral.
+
+ - "host" - switching mode from peripheral to host.
+ - "peripheral" - switching mode from host to peripheral.
Read the file, then it shows the following strings:
- "host" - The mode is host now.
- "peripheral" - The mode is peripheral now.
+
+ - "host" - The mode is host now.
+ - "peripheral" - The mode is peripheral now.
diff --git a/Documentation/ABI/testing/sysfs-platform-renesas_usb3 b/Documentation/ABI/testing/sysfs-platform-renesas_usb3
index 5621c15..8af5b9c 100644
--- a/Documentation/ABI/testing/sysfs-platform-renesas_usb3
+++ b/Documentation/ABI/testing/sysfs-platform-renesas_usb3
@@ -7,9 +7,11 @@
The file can show/change the drd mode of usb.
Write the following string to change the mode:
- "host" - switching mode from peripheral to host.
- "peripheral" - switching mode from host to peripheral.
+
+ - "host" - switching mode from peripheral to host.
+ - "peripheral" - switching mode from host to peripheral.
Read the file, then it shows the following strings:
- "host" - The mode is host now.
- "peripheral" - The mode is peripheral now.
+
+ - "host" - The mode is host now.
+ - "peripheral" - The mode is peripheral now.
diff --git a/Documentation/ABI/testing/sysfs-platform-sst-atom b/Documentation/ABI/testing/sysfs-platform-sst-atom
index 0d07c03..d5f6e21 100644
--- a/Documentation/ABI/testing/sysfs-platform-sst-atom
+++ b/Documentation/ABI/testing/sysfs-platform-sst-atom
@@ -5,13 +5,22 @@
Description:
LPE Firmware version for SST driver on all atom
plaforms (BYT/CHT/Merrifield/BSW).
- If the FW has never been loaded it will display:
+ If the FW has never been loaded it will display::
+
"FW not yet loaded"
- If FW has been loaded it will display:
+
+ If FW has been loaded it will display::
+
"v01.aa.bb.cc"
+
aa: Major version is reflecting SoC version:
+
+ === =============
0d: BYT FW
0b: BSW FW
07: Merrifield FW
+ === =============
+
bb: Minor version
+
cc: Build version
diff --git a/Documentation/ABI/testing/sysfs-platform-usbip-vudc b/Documentation/ABI/testing/sysfs-platform-usbip-vudc
index 81fcfb4..53622d3 100644
--- a/Documentation/ABI/testing/sysfs-platform-usbip-vudc
+++ b/Documentation/ABI/testing/sysfs-platform-usbip-vudc
@@ -16,10 +16,13 @@
Description:
Current status of the device.
Allowed values:
- 1 - Device is available and can be exported
- 2 - Device is currently exported
- 3 - Fatal error occurred during communication
- with peer
+
+ == ==========================================
+ 1 Device is available and can be exported
+ 2 Device is currently exported
+ 3 Fatal error occurred during communication
+ with peer
+ == ==========================================
What: /sys/devices/platform/usbip-vudc.%d/usbip_sockfd
Date: April 2016
diff --git a/Documentation/ABI/testing/sysfs-platform-wilco-ec b/Documentation/ABI/testing/sysfs-platform-wilco-ec
index 5f60b18..4439d06 100644
--- a/Documentation/ABI/testing/sysfs-platform-wilco-ec
+++ b/Documentation/ABI/testing/sysfs-platform-wilco-ec
@@ -39,6 +39,7 @@
which affects charging via the special USB PowerShare port
(marked with a small lightning bolt or battery icon) when in
low power states:
+
- In S0, the port will always provide power.
- In S0ix, if usb_charge is enabled, then power will be
supplied to the port when on AC or if battery is > 50%.
diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power
index 5e6ead2..51c0f57 100644
--- a/Documentation/ABI/testing/sysfs-power
+++ b/Documentation/ABI/testing/sysfs-power
@@ -47,14 +47,18 @@
suspend-to-disk mechanism. Reading from this file returns
the name of the method by which the system will be put to
sleep on the next suspend. There are four methods supported:
+
'firmware' - means that the memory image will be saved to disk
by some firmware, in which case we also assume that the
firmware will handle the system suspend.
+
'platform' - the memory image will be saved by the kernel and
the system will be put to sleep by the platform driver (e.g.
ACPI or other PM registers).
+
'shutdown' - the memory image will be saved by the kernel and
the system will be powered off.
+
'reboot' - the memory image will be saved by the kernel and
the system will be rebooted.
@@ -74,12 +78,12 @@
The suspend-to-disk method may be chosen by writing to this
file one of the accepted strings:
- 'firmware'
- 'platform'
- 'shutdown'
- 'reboot'
- 'testproc'
- 'test'
+ - 'firmware'
+ - 'platform'
+ - 'shutdown'
+ - 'reboot'
+ - 'testproc'
+ - 'test'
It will only change to 'firmware' or 'platform' if the system
supports that.
@@ -114,9 +118,9 @@
string representing a nonzero integer into it.
To use this debugging feature you should attempt to suspend
- the machine, then reboot it and run
+ the machine, then reboot it and run::
- dmesg -s 1000000 | grep 'hash matches'
+ dmesg -s 1000000 | grep 'hash matches'
If you do not get any matches (or they appear to be false
positives), it is possible that the last PM event point
@@ -244,6 +248,7 @@
wakeup sources created with the help of /sys/power/wake_lock.
When a string is written to /sys/power/wake_unlock, it will be
assumed to represent the name of a wakeup source to deactivate.
+
If a wakeup source object of that name exists and is active at
the moment, it will be deactivated.
diff --git a/Documentation/ABI/testing/sysfs-profiling b/Documentation/ABI/testing/sysfs-profiling
index 8a8e466..e39dd3a 100644
--- a/Documentation/ABI/testing/sysfs-profiling
+++ b/Documentation/ABI/testing/sysfs-profiling
@@ -5,7 +5,7 @@
/sys/kernel/profiling is the runtime equivalent
of the boot-time profile= option.
- You can get the same effect running:
+ You can get the same effect running::
echo 2 > /sys/kernel/profiling
diff --git a/Documentation/ABI/testing/sysfs-ptp b/Documentation/ABI/testing/sysfs-ptp
index a17f817..2363ad8 100644
--- a/Documentation/ABI/testing/sysfs-ptp
+++ b/Documentation/ABI/testing/sysfs-ptp
@@ -69,7 +69,7 @@
pin offered by the PTP hardware clock. The file name
is the hardware dependent pin name. Reading from this
file produces two numbers, the assigned function (see
- the PTP_PF_ enumeration values in linux/ptp_clock.h)
+ the `PTP_PF_` enumeration values in linux/ptp_clock.h)
and the channel number. The function and channel
assignment may be changed by two writing numbers into
the file.
diff --git a/Documentation/ABI/testing/sysfs-uevent b/Documentation/ABI/testing/sysfs-uevent
index aa39f8d..0b62277 100644
--- a/Documentation/ABI/testing/sysfs-uevent
+++ b/Documentation/ABI/testing/sysfs-uevent
@@ -6,42 +6,46 @@
Enable passing additional variables for synthetic uevents that
are generated by writing /sys/.../uevent file.
- Recognized extended format is ACTION [UUID [KEY=VALUE ...].
+ Recognized extended format is::
- The ACTION is compulsory - it is the name of the uevent action
- ("add", "change", "remove"). There is no change compared to
- previous functionality here. The rest of the extended format
- is optional.
+ ACTION [UUID [KEY=VALUE ...]
+
+ The ACTION is compulsory - it is the name of the uevent
+ action (``add``, ``change``, ``remove``). There is no change
+ compared to previous functionality here. The rest of the
+ extended format is optional.
You need to pass UUID first before any KEY=VALUE pairs.
- The UUID must be in "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
+ The UUID must be in ``xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx``
format where 'x' is a hex digit. The UUID is considered to be
a transaction identifier so it's possible to use the same UUID
value for one or more synthetic uevents in which case we
logically group these uevents together for any userspace
listeners. The UUID value appears in uevent as
- "SYNTH_UUID=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" environment
+ ``SYNTH_UUID=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx`` environment
variable.
If UUID is not passed in, the generated synthetic uevent gains
- "SYNTH_UUID=0" environment variable automatically.
+ ``SYNTH_UUID=0`` environment variable automatically.
The KEY=VALUE pairs can contain alphanumeric characters only.
+
It's possible to define zero or more pairs - each pair is then
delimited by a space character ' '. Each pair appears in
- synthetic uevent as "SYNTH_ARG_KEY=VALUE". That means the KEY
- name gains "SYNTH_ARG_" prefix to avoid possible collisions
+ synthetic uevent as ``SYNTH_ARG_KEY=VALUE``. That means the KEY
+ name gains ``SYNTH_ARG_`` prefix to avoid possible collisions
with existing variables.
- Example of valid sequence written to the uevent file:
+ Example of valid sequence written to the uevent file::
add fe4d7c9d-b8c6-4a70-9ef1-3d8a58d18eed A=1 B=abc
- This generates synthetic uevent including these variables:
+ This generates synthetic uevent including these variables::
ACTION=add
SYNTH_ARG_A=1
SYNTH_ARG_B=abc
SYNTH_UUID=fe4d7c9d-b8c6-4a70-9ef1-3d8a58d18eed
+
Users:
udev, userspace tools generating synthetic uevents
diff --git a/Documentation/ABI/testing/sysfs-wusb_cbaf b/Documentation/ABI/testing/sysfs-wusb_cbaf
index a99c5f8..2969d36 100644
--- a/Documentation/ABI/testing/sysfs-wusb_cbaf
+++ b/Documentation/ABI/testing/sysfs-wusb_cbaf
@@ -45,7 +45,8 @@
7. Device is unplugged.
References:
- [WUSB-AM] Association Models Supplement to the
+ [WUSB-AM]
+ Association Models Supplement to the
Certified Wireless Universal Serial Bus
Specification, version 1.0.
diff --git a/Documentation/ABI/testing/usb-charger-uevent b/Documentation/ABI/testing/usb-charger-uevent
index 419a92d..1db89b0 100644
--- a/Documentation/ABI/testing/usb-charger-uevent
+++ b/Documentation/ABI/testing/usb-charger-uevent
@@ -3,44 +3,52 @@
KernelVersion: 5.6
Contact: linux-usb@vger.kernel.org
Description: There are two USB charger states:
- USB_CHARGER_ABSENT
- USB_CHARGER_PRESENT
+
+ - USB_CHARGER_ABSENT
+ - USB_CHARGER_PRESENT
+
There are five USB charger types:
- USB_CHARGER_UNKNOWN_TYPE: Charger type is unknown
- USB_CHARGER_SDP_TYPE: Standard Downstream Port
- USB_CHARGER_CDP_TYPE: Charging Downstream Port
- USB_CHARGER_DCP_TYPE: Dedicated Charging Port
- USB_CHARGER_ACA_TYPE: Accessory Charging Adapter
+
+ ======================== ==========================
+ USB_CHARGER_UNKNOWN_TYPE Charger type is unknown
+ USB_CHARGER_SDP_TYPE Standard Downstream Port
+ USB_CHARGER_CDP_TYPE Charging Downstream Port
+ USB_CHARGER_DCP_TYPE Dedicated Charging Port
+ USB_CHARGER_ACA_TYPE Accessory Charging Adapter
+ ======================== ==========================
+
https://www.usb.org/document-library/battery-charging-v12-spec-and-adopters-agreement
- Here are two examples taken using udevadm monitor -p when
- USB charger is online:
- UDEV change /devices/soc0/usbphynop1 (platform)
- ACTION=change
- DEVPATH=/devices/soc0/usbphynop1
- DRIVER=usb_phy_generic
- MODALIAS=of:Nusbphynop1T(null)Cusb-nop-xceiv
- OF_COMPATIBLE_0=usb-nop-xceiv
- OF_COMPATIBLE_N=1
- OF_FULLNAME=/usbphynop1
- OF_NAME=usbphynop1
- SEQNUM=2493
- SUBSYSTEM=platform
- USB_CHARGER_STATE=USB_CHARGER_PRESENT
- USB_CHARGER_TYPE=USB_CHARGER_SDP_TYPE
- USEC_INITIALIZED=227422826
+ Here are two examples taken using ``udevadm monitor -p`` when
+ USB charger is online::
- USB charger is offline:
- KERNEL change /devices/soc0/usbphynop1 (platform)
- ACTION=change
- DEVPATH=/devices/soc0/usbphynop1
- DRIVER=usb_phy_generic
- MODALIAS=of:Nusbphynop1T(null)Cusb-nop-xceiv
- OF_COMPATIBLE_0=usb-nop-xceiv
- OF_COMPATIBLE_N=1
- OF_FULLNAME=/usbphynop1
- OF_NAME=usbphynop1
- SEQNUM=2494
- SUBSYSTEM=platform
- USB_CHARGER_STATE=USB_CHARGER_ABSENT
- USB_CHARGER_TYPE=USB_CHARGER_UNKNOWN_TYPE
+ UDEV change /devices/soc0/usbphynop1 (platform)
+ ACTION=change
+ DEVPATH=/devices/soc0/usbphynop1
+ DRIVER=usb_phy_generic
+ MODALIAS=of:Nusbphynop1T(null)Cusb-nop-xceiv
+ OF_COMPATIBLE_0=usb-nop-xceiv
+ OF_COMPATIBLE_N=1
+ OF_FULLNAME=/usbphynop1
+ OF_NAME=usbphynop1
+ SEQNUM=2493
+ SUBSYSTEM=platform
+ USB_CHARGER_STATE=USB_CHARGER_PRESENT
+ USB_CHARGER_TYPE=USB_CHARGER_SDP_TYPE
+ USEC_INITIALIZED=227422826
+
+ USB charger is offline::
+
+ KERNEL change /devices/soc0/usbphynop1 (platform)
+ ACTION=change
+ DEVPATH=/devices/soc0/usbphynop1
+ DRIVER=usb_phy_generic
+ MODALIAS=of:Nusbphynop1T(null)Cusb-nop-xceiv
+ OF_COMPATIBLE_0=usb-nop-xceiv
+ OF_COMPATIBLE_N=1
+ OF_FULLNAME=/usbphynop1
+ OF_NAME=usbphynop1
+ SEQNUM=2494
+ SUBSYSTEM=platform
+ USB_CHARGER_STATE=USB_CHARGER_ABSENT
+ USB_CHARGER_TYPE=USB_CHARGER_UNKNOWN_TYPE
diff --git a/Documentation/ABI/testing/usb-uevent b/Documentation/ABI/testing/usb-uevent
index d35c3ca..2b8eca4 100644
--- a/Documentation/ABI/testing/usb-uevent
+++ b/Documentation/ABI/testing/usb-uevent
@@ -6,22 +6,22 @@
longer functional a uevent will be raised. The uevent will
contain ACTION=offline and ERROR=DEAD.
- Here is an example taken using udevadm monitor -p:
+ Here is an example taken using udevadm monitor -p::
- KERNEL[130.428945] offline /devices/pci0000:00/0000:00:10.0/usb2 (usb)
- ACTION=offline
- BUSNUM=002
- DEVNAME=/dev/bus/usb/002/001
- DEVNUM=001
- DEVPATH=/devices/pci0000:00/0000:00:10.0/usb2
- DEVTYPE=usb_device
- DRIVER=usb
- ERROR=DEAD
- MAJOR=189
- MINOR=128
- PRODUCT=1d6b/2/414
- SEQNUM=2168
- SUBSYSTEM=usb
- TYPE=9/0/1
+ KERNEL[130.428945] offline /devices/pci0000:00/0000:00:10.0/usb2 (usb)
+ ACTION=offline
+ BUSNUM=002
+ DEVNAME=/dev/bus/usb/002/001
+ DEVNUM=001
+ DEVPATH=/devices/pci0000:00/0000:00:10.0/usb2
+ DEVTYPE=usb_device
+ DRIVER=usb
+ ERROR=DEAD
+ MAJOR=189
+ MINOR=128
+ PRODUCT=1d6b/2/414
+ SEQNUM=2168
+ SUBSYSTEM=usb
+ TYPE=9/0/1
Users: chromium-os-dev@chromium.org
diff --git a/Documentation/Kconfig b/Documentation/Kconfig
index 66046fa..e549a61 100644
--- a/Documentation/Kconfig
+++ b/Documentation/Kconfig
@@ -10,4 +10,14 @@
If unsure, select 'N'.
+config WARN_ABI_ERRORS
+ bool "Warn if there are errors at ABI files"
+ depends on COMPILE_TEST
+ help
+ The files under Documentation/ABI should follow what's
+ described at Documentation/ABI/README. Yet, as they're manually
+ written, it would be possible that some of those files would
+ have errors that would break them for being parsed by
+ scripts/get_abi.pl. Add a check to verify them.
+ If unsure, select 'N'.
diff --git a/Documentation/Makefile b/Documentation/Makefile
index 6b12dd8..61a7310 100644
--- a/Documentation/Makefile
+++ b/Documentation/Makefile
@@ -10,6 +10,11 @@
$(shell $(srctree)/scripts/documentation-file-ref-check --warn)
endif
+# Check for broken ABI files
+ifeq ($(CONFIG_WARN_ABI_ERRORS),y)
+$(shell $(srctree)/scripts/get_abi.pl validate --dir $(srctree)/Documentation/ABI)
+endif
+
# You can set these variables from the command line.
SPHINXBUILD = sphinx-build
SPHINXOPTS =
@@ -21,6 +26,10 @@
PDFLATEX = xelatex
LATEXOPTS = -interaction=batchmode
+ifeq ($(KBUILD_VERBOSE),0)
+SPHINXOPTS += "-q"
+endif
+
# User-friendly check for sphinx-build
HAVE_SPHINX := $(shell if which $(SPHINXBUILD) >/dev/null 2>&1; then echo 1; else echo 0; fi)
diff --git a/Documentation/admin-guide/LSM/SafeSetID.rst b/Documentation/admin-guide/LSM/SafeSetID.rst
index 17996c9..0ec3486 100644
--- a/Documentation/admin-guide/LSM/SafeSetID.rst
+++ b/Documentation/admin-guide/LSM/SafeSetID.rst
@@ -107,7 +107,7 @@
privileges, such as allowing a user to set up user namespace UID/GID mappings.
Note on GID policies and setgroups()
-==================
+====================================
In v5.9 we are adding support for limiting CAP_SETGID privileges as was done
previously for CAP_SETUID. However, for compatibility with common sandboxing
related code conventions in userspace, we currently allow arbitrary
diff --git a/Documentation/admin-guide/abi-obsolete.rst b/Documentation/admin-guide/abi-obsolete.rst
new file mode 100644
index 0000000..d095867
--- /dev/null
+++ b/Documentation/admin-guide/abi-obsolete.rst
@@ -0,0 +1,11 @@
+ABI obsolete symbols
+====================
+
+Documents interfaces that are still remaining in the kernel, but are
+marked to be removed at some later point in time.
+
+The description of the interface will document the reason why it is
+obsolete and when it can be expected to be removed.
+
+.. kernel-abi:: $srctree/Documentation/ABI/obsolete
+ :rst:
diff --git a/Documentation/admin-guide/abi-removed.rst b/Documentation/admin-guide/abi-removed.rst
new file mode 100644
index 0000000..f7e9e43
--- /dev/null
+++ b/Documentation/admin-guide/abi-removed.rst
@@ -0,0 +1,5 @@
+ABI removed symbols
+===================
+
+.. kernel-abi:: $srctree/Documentation/ABI/removed
+ :rst:
diff --git a/Documentation/admin-guide/abi-stable.rst b/Documentation/admin-guide/abi-stable.rst
new file mode 100644
index 0000000..7049073
--- /dev/null
+++ b/Documentation/admin-guide/abi-stable.rst
@@ -0,0 +1,14 @@
+ABI stable symbols
+==================
+
+Documents the interfaces that the developer has defined to be stable.
+
+Userspace programs are free to use these interfaces with no
+restrictions, and backward compatibility for them will be guaranteed
+for at least 2 years.
+
+Most interfaces (like syscalls) are expected to never change and always
+be available.
+
+.. kernel-abi:: $srctree/Documentation/ABI/stable
+ :rst:
diff --git a/Documentation/admin-guide/abi-testing.rst b/Documentation/admin-guide/abi-testing.rst
new file mode 100644
index 0000000..b205b16
--- /dev/null
+++ b/Documentation/admin-guide/abi-testing.rst
@@ -0,0 +1,20 @@
+ABI testing symbols
+===================
+
+Documents interfaces that are felt to be stable,
+as the main development of this interface has been completed.
+
+The interface can be changed to add new features, but the
+current interface will not break by doing this, unless grave
+errors or security problems are found in them.
+
+Userspace programs can start to rely on these interfaces, but they must
+be aware of changes that can occur before these interfaces move to
+be marked stable.
+
+Programs that use these interfaces are strongly encouraged to add their
+name to the description of these interfaces, so that the kernel
+developers can easily notify them if any changes occur.
+
+.. kernel-abi:: $srctree/Documentation/ABI/testing
+ :rst:
diff --git a/Documentation/admin-guide/abi.rst b/Documentation/admin-guide/abi.rst
new file mode 100644
index 0000000..bcab3ef25
--- /dev/null
+++ b/Documentation/admin-guide/abi.rst
@@ -0,0 +1,11 @@
+=====================
+Linux ABI description
+=====================
+
+.. toctree::
+ :maxdepth: 2
+
+ abi-stable
+ abi-testing
+ abi-obsolete
+ abi-removed
diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst
index ed1cf94..4e0c4ae 100644
--- a/Documentation/admin-guide/index.rst
+++ b/Documentation/admin-guide/index.rst
@@ -18,6 +18,8 @@
devices
sysctl/index
+ abi
+
This section describes CPU vulnerabilities and their mitigations.
.. toctree::
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 526d65d..44fde25 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2858,6 +2858,8 @@
mds=off [X86]
tsx_async_abort=off [X86]
kvm.nx_huge_pages=off [X86]
+ no_entry_flush [PPC]
+ no_uaccess_flush [PPC]
Exceptions:
This does not have any effect on
@@ -3186,6 +3188,8 @@
noefi Disable EFI runtime services support.
+ no_entry_flush [PPC] Don't flush the L1-D cache when entering the kernel.
+
noexec [IA-64]
noexec [X86]
@@ -3235,6 +3239,9 @@
nospec_store_bypass_disable
[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
+ no_uaccess_flush
+ [PPC] Don't flush the L1-D cache after accessing user data.
+
noxsave [BUGS=X86] Disables x86 extended register state save
and restore using xsave. The kernel will fallback to
enabling legacy floating-point and sse state.
diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst
index 37940a0..10fde58 100644
--- a/Documentation/admin-guide/pm/cpuidle.rst
+++ b/Documentation/admin-guide/pm/cpuidle.rst
@@ -478,7 +478,7 @@
statistics of the given idle state. That information is exposed by the kernel
via ``sysfs``.
-For each CPU in the system, there is a :file:`/sys/devices/system/cpu<N>/cpuidle/`
+For each CPU in the system, there is a :file:`/sys/devices/system/cpu/cpu<N>/cpuidle/`
directory in ``sysfs``, where the number ``<N>`` is assigned to the given
CPU at the initialization time. That directory contains a set of subdirectories
called :file:`state0`, :file:`state1` and so on, up to the number of idle state
@@ -494,7 +494,7 @@
residency.
``below``
- Total number of times this idle state had been asked for, but cerainly
+ Total number of times this idle state had been asked for, but certainly
a deeper idle state would have been a better match for the observed idle
duration.
diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst
index 57fd6ce..f2ab8a5 100644
--- a/Documentation/admin-guide/sysctl/net.rst
+++ b/Documentation/admin-guide/sysctl/net.rst
@@ -300,6 +300,7 @@
0: 0 1 2 3 4 5 6 7
RSS hash key:
84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47:25:42:97:74:ca:56:bb:b6:a1:d8:43:e3:c9:0c:fd:17:55:c2:3a:4d:69:ed:f1:42:89
+
netdev_tstamp_prequeue
----------------------
diff --git a/Documentation/arm/sunxi.rst b/Documentation/arm/sunxi.rst
index 62b533d..0c536ae 100644
--- a/Documentation/arm/sunxi.rst
+++ b/Documentation/arm/sunxi.rst
@@ -148,3 +148,13 @@
* User Manual
http://dl.linux-sunxi.org/A64/Allwinner%20A64%20User%20Manual%20v1.0.pdf
+
+ - Allwinner H6
+
+ * Datasheet
+
+ https://linux-sunxi.org/images/5/5c/Allwinner_H6_V200_Datasheet_V1.1.pdf
+
+ * User Manual
+
+ https://linux-sunxi.org/images/4/46/Allwinner_H6_V200_User_Manual_V1.1.pdf
diff --git a/Documentation/arm64/memory-tagging-extension.rst b/Documentation/arm64/memory-tagging-extension.rst
index 034d37c..b540178 100644
--- a/Documentation/arm64/memory-tagging-extension.rst
+++ b/Documentation/arm64/memory-tagging-extension.rst
@@ -102,7 +102,9 @@
system call) are not checked if the user thread tag checking mode is
``PR_MTE_TCF_NONE`` or ``PR_MTE_TCF_ASYNC``. If the tag checking mode is
``PR_MTE_TCF_SYNC``, the kernel makes a best effort to check its user
-address accesses, however it cannot always guarantee it.
+address accesses, however it cannot always guarantee it. Kernel accesses
+to user addresses are always performed with an effective ``PSTATE.TCO``
+value of zero, regardless of the user configuration.
Excluding Tags in the ``IRG``, ``ADDG`` and ``SUBG`` instructions
-----------------------------------------------------------------
diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst
index d358780..7195102 100644
--- a/Documentation/arm64/silicon-errata.rst
+++ b/Documentation/arm64/silicon-errata.rst
@@ -90,6 +90,8 @@
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-A76 | #1463225 | ARM64_ERRATUM_1463225 |
+----------------+-----------------+-----------------+-----------------------------+
+| ARM | Cortex-A77 | #1508412 | ARM64_ERRATUM_1508412 |
++----------------+-----------------+-----------------+-----------------------------+
| ARM | Neoverse-N1 | #1188873,1418040| ARM64_ERRATUM_1418040 |
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Neoverse-N1 | #1349291 | N/A |
diff --git a/Documentation/conf.py b/Documentation/conf.py
index 376dd0d..ed2b43e 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -38,7 +38,8 @@
# ones.
extensions = ['kerneldoc', 'rstFlatTable', 'kernel_include',
'kfigure', 'sphinx.ext.ifconfig', 'automarkup',
- 'maintainers_include', 'sphinx.ext.autosectionlabel' ]
+ 'maintainers_include', 'sphinx.ext.autosectionlabel',
+ 'kernel_abi']
#
# cdomain is badly broken in Sphinx 3+. Leaving it out generates *most*
@@ -50,7 +51,7 @@
support for Sphinx v3.0 and above is brand new. Be prepared for
possible issues in the generated output.
''')
- if minor > 0 or patch >= 2:
+ if (major > 3) or (minor > 0 or patch >= 2):
# Sphinx c function parser is more pedantic with regards to type
# checking. Due to that, having macros at c:function cause problems.
# Those needed to be scaped by using c_id_attributes[] array
diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst
index c09c9ca..2b68add 100644
--- a/Documentation/dev-tools/kasan.rst
+++ b/Documentation/dev-tools/kasan.rst
@@ -295,11 +295,13 @@
pass::
ok 28 - kmalloc_double_kzfree
+
or, if kmalloc failed::
# kmalloc_large_oob_right: ASSERTION FAILED at lib/test_kasan.c:163
Expected ptr is not null, but is
not ok 4 - kmalloc_large_oob_right
+
or, if a KASAN report was expected, but not found::
# kmalloc_double_kzfree: EXPECTATION FAILED at lib/test_kasan.c:629
diff --git a/Documentation/dev-tools/kunit/faq.rst b/Documentation/dev-tools/kunit/faq.rst
index 1628862..8d5029a 100644
--- a/Documentation/dev-tools/kunit/faq.rst
+++ b/Documentation/dev-tools/kunit/faq.rst
@@ -90,7 +90,7 @@
re-run kunit_tool.
5. Try to run ``make ARCH=um defconfig`` before running ``kunit.py run``. This
may help clean up any residual config items which could be causing problems.
-6. Finally, try running KUnit outside UML. KUnit and KUnit tests can run be
+6. Finally, try running KUnit outside UML. KUnit and KUnit tests can be
built into any kernel, or can be built as a module and loaded at runtime.
Doing so should allow you to determine if UML is causing the issue you're
seeing. When tests are built-in, they will execute when the kernel boots, and
diff --git a/Documentation/dev-tools/kunit/start.rst b/Documentation/dev-tools/kunit/start.rst
index d23385e..454f307 100644
--- a/Documentation/dev-tools/kunit/start.rst
+++ b/Documentation/dev-tools/kunit/start.rst
@@ -197,7 +197,7 @@
config MISC_EXAMPLE_TEST
bool "Test for my example"
- depends on MISC_EXAMPLE && KUNIT
+ depends on MISC_EXAMPLE && KUNIT=y
and the following to ``drivers/misc/Makefile``:
diff --git a/Documentation/dev-tools/kunit/style.rst b/Documentation/dev-tools/kunit/style.rst
index da1d6f0..8dbcdc5 100644
--- a/Documentation/dev-tools/kunit/style.rst
+++ b/Documentation/dev-tools/kunit/style.rst
@@ -175,17 +175,17 @@
.. code-block:: none
- config FOO_KUNIT_TEST
- tristate "KUnit test for foo" if !KUNIT_ALL_TESTS
- depends on KUNIT
- default KUNIT_ALL_TESTS
- help
- This builds unit tests for foo.
+ config FOO_KUNIT_TEST
+ tristate "KUnit test for foo" if !KUNIT_ALL_TESTS
+ depends on KUNIT
+ default KUNIT_ALL_TESTS
+ help
+ This builds unit tests for foo.
- For more information on KUnit and unit tests in general, please refer
- to the KUnit documentation in Documentation/dev-tools/kunit
+ For more information on KUnit and unit tests in general, please refer
+ to the KUnit documentation in Documentation/dev-tools/kunit/.
- If unsure, say N
+ If unsure, say N.
Test File and Module Names
diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst
index 961d3ea..9c28c51 100644
--- a/Documentation/dev-tools/kunit/usage.rst
+++ b/Documentation/dev-tools/kunit/usage.rst
@@ -92,7 +92,7 @@
the second parameter, in this case, is what the value is expected to be; the
last value is what the value actually is. If ``add`` passes all of these
expectations, the test case, ``add_test_basic`` will pass; if any one of these
-expectations fail, the test case will fail.
+expectations fails, the test case will fail.
It is important to understand that a test case *fails* when any expectation is
violated; however, the test will continue running, potentially trying other
@@ -202,7 +202,7 @@
kunit_test_suite(example_test_suite);
In the above example the test suite, ``example_test_suite``, would run the test
-cases ``example_test_foo``, ``example_test_bar``, and ``example_test_baz``,
+cases ``example_test_foo``, ``example_test_bar``, and ``example_test_baz``;
each would have ``example_test_init`` called immediately before it and would
have ``example_test_exit`` called immediately after it.
``kunit_test_suite(example_test_suite)`` registers the test suite with the
@@ -229,7 +229,7 @@
such that the definition of that function can be changed without affecting the
rest of the code base. In the kernel this primarily comes from two constructs,
classes, structs that contain function pointers that are provided by the
-implementer, and architecture specific functions which have definitions selected
+implementer, and architecture-specific functions which have definitions selected
at compile time.
Classes
@@ -459,7 +459,7 @@
By default KUnit uses UML as a way to provide dependencies for code under test.
Under most circumstances KUnit's usage of UML should be treated as an
implementation detail of how KUnit works under the hood. Nevertheless, there
-are instances where being able to run architecture specific code or test
+are instances where being able to run architecture-specific code or test
against real hardware is desirable. For these reasons KUnit supports running on
other architectures.
@@ -561,6 +561,11 @@
...will run the tests.
+.. note::
+ Note that you should make sure your test depends on ``KUNIT=y`` in Kconfig
+ if the test does not support module build. Otherwise, it will trigger
+ compile errors if ``CONFIG_KUNIT`` is ``m``.
+
Writing new tests for other architectures
-----------------------------------------
@@ -594,7 +599,7 @@
hardware state in between test cases; if this is not possible, you may only be
able to run one test case per invocation.
-.. TODO(brendanhiggins@google.com): Add an actual example of an architecture
+.. TODO(brendanhiggins@google.com): Add an actual example of an architecture-
dependent KUnit test.
KUnit debugfs representation
diff --git a/Documentation/devicetree/bindings/arm/actions.yaml b/Documentation/devicetree/bindings/arm/actions.yaml
index fe22c66..02dc72c 100644
--- a/Documentation/devicetree/bindings/arm/actions.yaml
+++ b/Documentation/devicetree/bindings/arm/actions.yaml
@@ -49,3 +49,5 @@
- enum:
- ucrobotics,bubblegum-96 # uCRobotics Bubblegum-96
- const: actions,s900
+
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/arm/altera.yaml b/Documentation/devicetree/bindings/arm/altera.yaml
index 0bc5020..c15c92fd 100644
--- a/Documentation/devicetree/bindings/arm/altera.yaml
+++ b/Documentation/devicetree/bindings/arm/altera.yaml
@@ -19,4 +19,7 @@
- altr,socfpga-arria5
- altr,socfpga-arria10
- const: altr,socfpga
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/amazon,al.yaml b/Documentation/devicetree/bindings/arm/amazon,al.yaml
index a3a4d71..0f03135 100644
--- a/Documentation/devicetree/bindings/arm/amazon,al.yaml
+++ b/Documentation/devicetree/bindings/arm/amazon,al.yaml
@@ -30,4 +30,6 @@
- amazon,al-alpine-v3-evp
- const: amazon,al-alpine-v3
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/amlogic.yaml b/Documentation/devicetree/bindings/arm/amlogic.yaml
index 0ee7c5b..3341788 100644
--- a/Documentation/devicetree/bindings/arm/amlogic.yaml
+++ b/Documentation/devicetree/bindings/arm/amlogic.yaml
@@ -173,4 +173,7 @@
- enum:
- amlogic,ad401
- const: amlogic,a1
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/arm,integrator.yaml b/Documentation/devicetree/bindings/arm/arm,integrator.yaml
index f0daf99..528eee6 100644
--- a/Documentation/devicetree/bindings/arm/arm,integrator.yaml
+++ b/Documentation/devicetree/bindings/arm/arm,integrator.yaml
@@ -83,4 +83,6 @@
- compatible
- core-module@10000000
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/arm,realview.yaml b/Documentation/devicetree/bindings/arm/arm,realview.yaml
index 1d0b4e2..4f9b21f 100644
--- a/Documentation/devicetree/bindings/arm/arm,realview.yaml
+++ b/Documentation/devicetree/bindings/arm/arm,realview.yaml
@@ -120,4 +120,6 @@
- compatible
- soc
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/arm,versatile.yaml b/Documentation/devicetree/bindings/arm/arm,versatile.yaml
index 06efd2a..34b437c 100644
--- a/Documentation/devicetree/bindings/arm/arm,versatile.yaml
+++ b/Documentation/devicetree/bindings/arm/arm,versatile.yaml
@@ -68,4 +68,6 @@
- compatible
- core-module@10000000
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/arm,vexpress-juno.yaml b/Documentation/devicetree/bindings/arm/arm,vexpress-juno.yaml
index 26829a80..55ef656 100644
--- a/Documentation/devicetree/bindings/arm/arm,vexpress-juno.yaml
+++ b/Documentation/devicetree/bindings/arm/arm,vexpress-juno.yaml
@@ -216,4 +216,6 @@
required:
- arm,hbi
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/atmel-at91.yaml b/Documentation/devicetree/bindings/arm/atmel-at91.yaml
index 614c919..6fc5a22 100644
--- a/Documentation/devicetree/bindings/arm/atmel-at91.yaml
+++ b/Documentation/devicetree/bindings/arm/atmel-at91.yaml
@@ -184,4 +184,6 @@
- const: atmel,samv71
- const: atmel,samv7
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/axxia.yaml b/Documentation/devicetree/bindings/arm/axxia.yaml
index 3ea5f2f..e0d2bb7 100644
--- a/Documentation/devicetree/bindings/arm/axxia.yaml
+++ b/Documentation/devicetree/bindings/arm/axxia.yaml
@@ -18,4 +18,6 @@
- const: lsi,axm5516-amarillo
- const: lsi,axm5516
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/bcm/bcm2835.yaml b/Documentation/devicetree/bindings/arm/bcm/bcm2835.yaml
index dd52e29..812ae8c 100644
--- a/Documentation/devicetree/bindings/arm/bcm/bcm2835.yaml
+++ b/Documentation/devicetree/bindings/arm/bcm/bcm2835.yaml
@@ -51,4 +51,6 @@
- raspberrypi,3-compute-module-lite
- const: brcm,bcm2837
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm11351.yaml b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm11351.yaml
index 497600a..c603243 100644
--- a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm11351.yaml
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm11351.yaml
@@ -18,4 +18,6 @@
- brcm,bcm28155-ap
- const: brcm,bcm11351
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm21664.yaml b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm21664.yaml
index e0ee931..b302075 100644
--- a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm21664.yaml
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm21664.yaml
@@ -18,4 +18,6 @@
- brcm,bcm21664-garnet
- const: brcm,bcm21664
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm23550.yaml b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm23550.yaml
index 40d12ea..37f3a6f 100644
--- a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm23550.yaml
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm23550.yaml
@@ -18,4 +18,6 @@
- brcm,bcm23550-sparrow
- const: brcm,bcm23550
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm4708.yaml b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm4708.yaml
index 988e0bb..434d3c6 100644
--- a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm4708.yaml
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm4708.yaml
@@ -87,4 +87,7 @@
- const: brcm,brcm53012
- const: brcm,brcm53016
- const: brcm,bcm4708
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,cygnus.yaml b/Documentation/devicetree/bindings/arm/bcm/brcm,cygnus.yaml
index 9ba7b16..432ccf9 100644
--- a/Documentation/devicetree/bindings/arm/bcm/brcm,cygnus.yaml
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,cygnus.yaml
@@ -26,4 +26,6 @@
- brcm,bcm58305
- const: brcm,cygnus
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,hr2.yaml b/Documentation/devicetree/bindings/arm/bcm/brcm,hr2.yaml
index ae614b6..2949483 100644
--- a/Documentation/devicetree/bindings/arm/bcm/brcm,hr2.yaml
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,hr2.yaml
@@ -25,4 +25,6 @@
- const: brcm,bcm53342
- const: brcm,hr2
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,ns2.yaml b/Documentation/devicetree/bindings/arm/bcm/brcm,ns2.yaml
index 0749adf..c4847ab 100644
--- a/Documentation/devicetree/bindings/arm/bcm/brcm,ns2.yaml
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,ns2.yaml
@@ -20,4 +20,6 @@
- brcm,ns2-xmc
- const: brcm,ns2
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,nsp.yaml b/Documentation/devicetree/bindings/arm/bcm/brcm,nsp.yaml
index 8c2cacb..476bc23 100644
--- a/Documentation/devicetree/bindings/arm/bcm/brcm,nsp.yaml
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,nsp.yaml
@@ -33,4 +33,6 @@
- brcm,bcm88312
- const: brcm,nsp
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,stingray.yaml b/Documentation/devicetree/bindings/arm/bcm/brcm,stingray.yaml
index c13cb96..c638e04 100644
--- a/Documentation/devicetree/bindings/arm/bcm/brcm,stingray.yaml
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,stingray.yaml
@@ -21,4 +21,6 @@
- brcm,bcm958802a802x
- const: brcm,stingray
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,vulcan-soc.yaml b/Documentation/devicetree/bindings/arm/bcm/brcm,vulcan-soc.yaml
index ccdf9f9..4eba182 100644
--- a/Documentation/devicetree/bindings/arm/bcm/brcm,vulcan-soc.yaml
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,vulcan-soc.yaml
@@ -19,4 +19,6 @@
- cavium,thunderx2-cn9900
- const: brcm,vulcan-soc
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/bitmain.yaml b/Documentation/devicetree/bindings/arm/bitmain.yaml
index 5880083..90ba02b 100644
--- a/Documentation/devicetree/bindings/arm/bitmain.yaml
+++ b/Documentation/devicetree/bindings/arm/bitmain.yaml
@@ -17,4 +17,7 @@
- enum:
- bitmain,sophon-edge
- const: bitmain,bm1880
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/calxeda.yaml b/Documentation/devicetree/bindings/arm/calxeda.yaml
index aa5571d..46f78ad 100644
--- a/Documentation/devicetree/bindings/arm/calxeda.yaml
+++ b/Documentation/devicetree/bindings/arm/calxeda.yaml
@@ -20,3 +20,5 @@
- enum:
- calxeda,highbank
- calxeda,ecx-2000
+
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/arm/digicolor.yaml b/Documentation/devicetree/bindings/arm/digicolor.yaml
index 849e205..a35de3c 100644
--- a/Documentation/devicetree/bindings/arm/digicolor.yaml
+++ b/Documentation/devicetree/bindings/arm/digicolor.yaml
@@ -15,4 +15,6 @@
compatible:
const: cnxt,cx92755
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/fsl.yaml b/Documentation/devicetree/bindings/arm/fsl.yaml
index 1ca9dfa..9342894 100644
--- a/Documentation/devicetree/bindings/arm/fsl.yaml
+++ b/Documentation/devicetree/bindings/arm/fsl.yaml
@@ -621,4 +621,6 @@
- fsl,s32v234-evb # S32V234-EVB2 Customer Evaluation Board
- const: fsl,s32v234
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/hisilicon/hisilicon.yaml b/Documentation/devicetree/bindings/arm/hisilicon/hisilicon.yaml
index 43b8ce2..b384580 100644
--- a/Documentation/devicetree/bindings/arm/hisilicon/hisilicon.yaml
+++ b/Documentation/devicetree/bindings/arm/hisilicon/hisilicon.yaml
@@ -64,4 +64,7 @@
items:
- const: H836ASDJ
- const: hisilicon,sd5203
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/intel,keembay.yaml b/Documentation/devicetree/bindings/arm/intel,keembay.yaml
index 06a7b05..69cd308 100644
--- a/Documentation/devicetree/bindings/arm/intel,keembay.yaml
+++ b/Documentation/devicetree/bindings/arm/intel,keembay.yaml
@@ -16,4 +16,7 @@
- enum:
- intel,keembay-evm
- const: intel,keembay
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/intel-ixp4xx.yaml b/Documentation/devicetree/bindings/arm/intel-ixp4xx.yaml
index f18302e..d72e92b 100644
--- a/Documentation/devicetree/bindings/arm/intel-ixp4xx.yaml
+++ b/Documentation/devicetree/bindings/arm/intel-ixp4xx.yaml
@@ -22,3 +22,5 @@
- enum:
- gateworks,gw2358
- const: intel,ixp43x
+
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/arm/keystone/ti,k3-sci-common.yaml b/Documentation/devicetree/bindings/arm/keystone/ti,k3-sci-common.yaml
index 7597bc93..5cbcaca 100644
--- a/Documentation/devicetree/bindings/arm/keystone/ti,k3-sci-common.yaml
+++ b/Documentation/devicetree/bindings/arm/keystone/ti,k3-sci-common.yaml
@@ -42,3 +42,5 @@
- description: TI-SCI processor id for the remote processor device
- description: TI-SCI host id to which processor control ownership
should be transferred to
+
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/arm/marvell/armada-7k-8k.yaml b/Documentation/devicetree/bindings/arm/marvell/armada-7k-8k.yaml
index a9828c5..e9bf305 100644
--- a/Documentation/devicetree/bindings/arm/marvell/armada-7k-8k.yaml
+++ b/Documentation/devicetree/bindings/arm/marvell/armada-7k-8k.yaml
@@ -59,3 +59,5 @@
- const: marvell,cn9130
- const: marvell,armada-ap807-quad
- const: marvell,armada-ap807
+
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/arm/mediatek.yaml b/Documentation/devicetree/bindings/arm/mediatek.yaml
index 3090896..f736e8c 100644
--- a/Documentation/devicetree/bindings/arm/mediatek.yaml
+++ b/Documentation/devicetree/bindings/arm/mediatek.yaml
@@ -119,4 +119,7 @@
- const: google,krane-sku176
- const: google,krane
- const: mediatek,mt8183
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/microchip,sparx5.yaml b/Documentation/devicetree/bindings/arm/microchip,sparx5.yaml
index ecf6fa1..6193388 100644
--- a/Documentation/devicetree/bindings/arm/microchip,sparx5.yaml
+++ b/Documentation/devicetree/bindings/arm/microchip,sparx5.yaml
@@ -62,4 +62,6 @@
- compatible
- axi@600000000
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/moxart.yaml b/Documentation/devicetree/bindings/arm/moxart.yaml
index c068df5..670d24c 100644
--- a/Documentation/devicetree/bindings/arm/moxart.yaml
+++ b/Documentation/devicetree/bindings/arm/moxart.yaml
@@ -16,4 +16,5 @@
- const: moxa,moxart-uc-7112-lx
- const: moxa,moxart
+additionalProperties: true
...
diff --git a/Documentation/devicetree/bindings/arm/mrvl/mrvl.yaml b/Documentation/devicetree/bindings/arm/mrvl/mrvl.yaml
index 3235ec9..d581161 100644
--- a/Documentation/devicetree/bindings/arm/mrvl/mrvl.yaml
+++ b/Documentation/devicetree/bindings/arm/mrvl/mrvl.yaml
@@ -35,4 +35,7 @@
- enum:
- dell,wyse-ariel
- const: marvell,mmp3
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/mstar/mstar.yaml b/Documentation/devicetree/bindings/arm/mstar/mstar.yaml
index c2f980b..7c78740 100644
--- a/Documentation/devicetree/bindings/arm/mstar/mstar.yaml
+++ b/Documentation/devicetree/bindings/arm/mstar/mstar.yaml
@@ -31,3 +31,5 @@
- enum:
- 70mai,midrived08 # 70mai midrive d08
- const: mstar,mercury5
+
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/arm/nxp/lpc32xx.yaml b/Documentation/devicetree/bindings/arm/nxp/lpc32xx.yaml
index f7f0249..214c97b 100644
--- a/Documentation/devicetree/bindings/arm/nxp/lpc32xx.yaml
+++ b/Documentation/devicetree/bindings/arm/nxp/lpc32xx.yaml
@@ -21,4 +21,6 @@
- ea,ea3250
- phytec,phy3250
- const: nxp,lpc3250
+
+additionalProperties: true
...
diff --git a/Documentation/devicetree/bindings/arm/qcom.yaml b/Documentation/devicetree/bindings/arm/qcom.yaml
index ad25deb..c97d4a5 100644
--- a/Documentation/devicetree/bindings/arm/qcom.yaml
+++ b/Documentation/devicetree/bindings/arm/qcom.yaml
@@ -178,4 +178,6 @@
- qcom,sm8250-mtp
- const: qcom,sm8250
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/rda.yaml b/Documentation/devicetree/bindings/arm/rda.yaml
index 9672aa0..a5c0444 100644
--- a/Documentation/devicetree/bindings/arm/rda.yaml
+++ b/Documentation/devicetree/bindings/arm/rda.yaml
@@ -19,4 +19,6 @@
- xunlong,orangepi-i96 # Orange Pi i96
- const: rda,8810pl
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/realtek.yaml b/Documentation/devicetree/bindings/arm/realtek.yaml
index 845f9c7..9fb0297 100644
--- a/Documentation/devicetree/bindings/arm/realtek.yaml
+++ b/Documentation/devicetree/bindings/arm/realtek.yaml
@@ -54,4 +54,7 @@
- enum:
- realtek,mjolnir # Realtek Mjolnir EVB
- const: realtek,rtd1619
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/renesas.yaml b/Documentation/devicetree/bindings/arm/renesas.yaml
index 01a6d0c..ff94c45 100644
--- a/Documentation/devicetree/bindings/arm/renesas.yaml
+++ b/Documentation/devicetree/bindings/arm/renesas.yaml
@@ -299,4 +299,6 @@
- renesas,rzn1d400-db # RZN1D-DB (RZ/N1D Demo Board for the RZ/N1D 400 pins package)
- const: renesas,r9a06g032
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/rockchip.yaml b/Documentation/devicetree/bindings/arm/rockchip.yaml
index 65b4cc2..b621752a 100644
--- a/Documentation/devicetree/bindings/arm/rockchip.yaml
+++ b/Documentation/devicetree/bindings/arm/rockchip.yaml
@@ -569,4 +569,7 @@
items:
- const: zkmagic,a95x-z2
- const: rockchip,rk3318
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.yaml b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.yaml
index eb92f9e..2725080 100644
--- a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.yaml
+++ b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.yaml
@@ -180,3 +180,5 @@
required:
- compatible
+
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/arm/sirf.yaml b/Documentation/devicetree/bindings/arm/sirf.yaml
index 0b59703..b25eb35 100644
--- a/Documentation/devicetree/bindings/arm/sirf.yaml
+++ b/Documentation/devicetree/bindings/arm/sirf.yaml
@@ -24,4 +24,7 @@
- items:
- const: sirf,prima2-cb
- const: sirf,prima2
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/socionext/milbeaut.yaml b/Documentation/devicetree/bindings/arm/socionext/milbeaut.yaml
index 2bd519d..aa1d4afb 100644
--- a/Documentation/devicetree/bindings/arm/socionext/milbeaut.yaml
+++ b/Documentation/devicetree/bindings/arm/socionext/milbeaut.yaml
@@ -19,4 +19,7 @@
- enum:
- socionext,milbeaut-m10v-evb
- const: socionext,sc2000a
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/socionext/uniphier.yaml b/Documentation/devicetree/bindings/arm/socionext/uniphier.yaml
index 6caf1f9..8c0e916 100644
--- a/Documentation/devicetree/bindings/arm/socionext/uniphier.yaml
+++ b/Documentation/devicetree/bindings/arm/socionext/uniphier.yaml
@@ -60,3 +60,5 @@
- enum:
- socionext,uniphier-pxs3-ref
- const: socionext,uniphier-pxs3
+
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/arm/spear.yaml b/Documentation/devicetree/bindings/arm/spear.yaml
index f6ec731..605ad3f 100644
--- a/Documentation/devicetree/bindings/arm/spear.yaml
+++ b/Documentation/devicetree/bindings/arm/spear.yaml
@@ -22,4 +22,7 @@
- st,spear320
- st,spear1310
- st,spear1340
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/sprd/sprd.yaml b/Documentation/devicetree/bindings/arm/sprd/sprd.yaml
index 0258a96b..7b6ae30 100644
--- a/Documentation/devicetree/bindings/arm/sprd/sprd.yaml
+++ b/Documentation/devicetree/bindings/arm/sprd/sprd.yaml
@@ -30,4 +30,6 @@
- sprd,sp9863a-1h10
- const: sprd,sc9863a
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/sti.yaml b/Documentation/devicetree/bindings/arm/sti.yaml
index 47f9b8e..b1f28d1 100644
--- a/Documentation/devicetree/bindings/arm/sti.yaml
+++ b/Documentation/devicetree/bindings/arm/sti.yaml
@@ -20,4 +20,7 @@
- st,stih407
- st,stih410
- st,stih418
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/stm32/stm32.yaml b/Documentation/devicetree/bindings/arm/stm32/stm32.yaml
index deacb4e..009b424 100644
--- a/Documentation/devicetree/bindings/arm/stm32/stm32.yaml
+++ b/Documentation/devicetree/bindings/arm/stm32/stm32.yaml
@@ -54,8 +54,11 @@
- const: st,stm32mp157
- description: Odyssey STM32MP1 SoM based Boards
items:
- - enum:
- - seeed,stm32mp157c-odyssey
- - const: seeed,stm32mp157c-odyssey-som
- - const: st,stm32mp157
+ - enum:
+ - seeed,stm32mp157c-odyssey
+ - const: seeed,stm32mp157c-odyssey-som
+ - const: st,stm32mp157
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/sunxi.yaml b/Documentation/devicetree/bindings/arm/sunxi.yaml
index afa0026..cab8e1b 100644
--- a/Documentation/devicetree/bindings/arm/sunxi.yaml
+++ b/Documentation/devicetree/bindings/arm/sunxi.yaml
@@ -893,3 +893,5 @@
items:
- const: xunlong,orangepi-zero-plus2-h3
- const: allwinner,sun8i-h3
+
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/arm/tegra.yaml b/Documentation/devicetree/bindings/arm/tegra.yaml
index 8ae4494..767e863 100644
--- a/Documentation/devicetree/bindings/arm/tegra.yaml
+++ b/Documentation/devicetree/bindings/arm/tegra.yaml
@@ -125,3 +125,5 @@
- enum:
- nvidia,tegra234-vdk
- const: nvidia,tegra234
+
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/arm/ti/k3.yaml b/Documentation/devicetree/bindings/arm/ti/k3.yaml
index 8297512..c6e1c1e 100644
--- a/Documentation/devicetree/bindings/arm/ti/k3.yaml
+++ b/Documentation/devicetree/bindings/arm/ti/k3.yaml
@@ -32,4 +32,7 @@
- description: K3 J7200 SoC
items:
- const: ti,j7200
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/ti/nspire.yaml b/Documentation/devicetree/bindings/arm/ti/nspire.yaml
index e372b43..cc2023b 100644
--- a/Documentation/devicetree/bindings/arm/ti/nspire.yaml
+++ b/Documentation/devicetree/bindings/arm/ti/nspire.yaml
@@ -21,4 +21,7 @@
- ti,nspire-tp
# Clickpad models
- ti,nspire-clp
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/ti/ti,davinci.yaml b/Documentation/devicetree/bindings/arm/ti/ti,davinci.yaml
index a8765ba..c022d32 100644
--- a/Documentation/devicetree/bindings/arm/ti/ti,davinci.yaml
+++ b/Documentation/devicetree/bindings/arm/ti/ti,davinci.yaml
@@ -23,4 +23,7 @@
- enbw,cmc # EnBW AM1808 based CMC board
- lego,ev3 # LEGO MINDSTORMS EV3 (AM1808 based)
- const: ti,da850
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/toshiba.yaml b/Documentation/devicetree/bindings/arm/toshiba.yaml
index 0e06629..001bbbc 100644
--- a/Documentation/devicetree/bindings/arm/toshiba.yaml
+++ b/Documentation/devicetree/bindings/arm/toshiba.yaml
@@ -19,4 +19,7 @@
- enum:
- toshiba,tmpv7708-rm-mbrc # TMPV7708 RM main board
- const: toshiba,tmpv7708
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/ux500.yaml b/Documentation/devicetree/bindings/arm/ux500.yaml
index accaee9..5db7cfb 100644
--- a/Documentation/devicetree/bindings/arm/ux500.yaml
+++ b/Documentation/devicetree/bindings/arm/ux500.yaml
@@ -34,3 +34,5 @@
items:
- const: samsung,golden
- const: st-ericsson,u8500
+
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/arm/vt8500.yaml b/Documentation/devicetree/bindings/arm/vt8500.yaml
index 7b25b6f..29ff399 100644
--- a/Documentation/devicetree/bindings/arm/vt8500.yaml
+++ b/Documentation/devicetree/bindings/arm/vt8500.yaml
@@ -21,3 +21,6 @@
- wm,wm8650
- wm,wm8750
- wm,wm8850
+
+additionalProperties: true
+
diff --git a/Documentation/devicetree/bindings/arm/xilinx.yaml b/Documentation/devicetree/bindings/arm/xilinx.yaml
index c73b1f5..e0c6787 100644
--- a/Documentation/devicetree/bindings/arm/xilinx.yaml
+++ b/Documentation/devicetree/bindings/arm/xilinx.yaml
@@ -111,4 +111,6 @@
- const: xlnx,zynqmp-zcu111
- const: xlnx,zynqmp
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/arm/zte.yaml b/Documentation/devicetree/bindings/arm/zte.yaml
index 2d3fefd..672f812 100644
--- a/Documentation/devicetree/bindings/arm/zte.yaml
+++ b/Documentation/devicetree/bindings/arm/zte.yaml
@@ -23,4 +23,6 @@
- zte,zx296718-evb
- const: zte,zx296718
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/clock/hi6220-clock.txt b/Documentation/devicetree/bindings/clock/hi6220-clock.txt
index ef3deb7..17ac4a3 100644
--- a/Documentation/devicetree/bindings/clock/hi6220-clock.txt
+++ b/Documentation/devicetree/bindings/clock/hi6220-clock.txt
@@ -4,7 +4,7 @@
please refer the following document to know more about the binding rules
for these system controllers:
-Documentation/devicetree/bindings/arm/hisilicon/hisilicon.txt
+Documentation/devicetree/bindings/arm/hisilicon/hisilicon.yaml
Required Properties:
diff --git a/Documentation/devicetree/bindings/clock/imx5-clock.yaml b/Documentation/devicetree/bindings/clock/imx5-clock.yaml
index 4d9e7c7..90775c2 100644
--- a/Documentation/devicetree/bindings/clock/imx5-clock.yaml
+++ b/Documentation/devicetree/bindings/clock/imx5-clock.yaml
@@ -57,7 +57,7 @@
};
can@53fc8000 {
- compatible = "fsl,imx53-flexcan", "fsl,p1010-flexcan";
+ compatible = "fsl,imx53-flexcan", "fsl,imx25-flexcan";
reg = <0x53fc8000 0x4000>;
interrupts = <82>;
clocks = <&clks IMX5_CLK_CAN1_IPG_GATE>, <&clks IMX5_CLK_CAN1_SERIAL_GATE>;
diff --git a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358775.yaml b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358775.yaml
index 31f085d..fd3113a 100644
--- a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358775.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358775.yaml
@@ -7,17 +7,17 @@
title: Toshiba TC358775 DSI to LVDS bridge bindings
maintainers:
- - Vinay Simha BN <simhavcs@gmail.com>
+ - Vinay Simha BN <simhavcs@gmail.com>
description: |
- This binding supports DSI to LVDS bridge TC358775
+ This binding supports DSI to LVDS bridge TC358775
- MIPI DSI-RX Data 4-lane, CLK 1-lane with data rates up to 800 Mbps/lane.
- Video frame size:
- Up to 1600x1200 24-bit/pixel resolution for single-link LVDS display panel
- limited by 135 MHz LVDS speed
- Up to WUXGA (1920x1200 24-bit pixels) resolution for dual-link LVDS display
- panel, limited by 270 MHz LVDS speed.
+ MIPI DSI-RX Data 4-lane, CLK 1-lane with data rates up to 800 Mbps/lane.
+ Video frame size:
+ Up to 1600x1200 24-bit/pixel resolution for single-link LVDS display panel
+ limited by 135 MHz LVDS speed
+ Up to WUXGA (1920x1200 24-bit pixels) resolution for dual-link LVDS display
+ panel, limited by 270 MHz LVDS speed.
properties:
compatible:
@@ -29,7 +29,7 @@
vdd-supply:
maxItems: 1
- description: 1.2V LVDS Power Supply
+ description: 1.2V LVDS Power Supply
vddio-supply:
maxItems: 1
@@ -77,16 +77,18 @@
- port@1
required:
- - compatible
- - reg
- - vdd-supply
- - vddio-supply
- - stby-gpios
- - reset-gpios
- - ports
+ - compatible
+ - reg
+ - vdd-supply
+ - vddio-supply
+ - stby-gpios
+ - reset-gpios
+ - ports
+
+additionalProperties: false
examples:
- - |
+ - |
#include <dt-bindings/gpio/gpio.h>
/* For single-link LVDS display panel */
@@ -147,7 +149,7 @@
};
};
- - |
+ - |
/* For dual-link LVDS display panel */
i2c@78b8000 {
diff --git a/Documentation/devicetree/bindings/display/panel/ilitek,ili9881c.yaml b/Documentation/devicetree/bindings/display/panel/ilitek,ili9881c.yaml
index c60b3bd..b2fcec4 100644
--- a/Documentation/devicetree/bindings/display/panel/ilitek,ili9881c.yaml
+++ b/Documentation/devicetree/bindings/display/panel/ilitek,ili9881c.yaml
@@ -13,9 +13,8 @@
compatible:
items:
- enum:
- - bananapi,lhr050h41
- - feixin,k101-im2byl02
-
+ - bananapi,lhr050h41
+ - feixin,k101-im2byl02
- const: ilitek,ili9881c
backlight: true
diff --git a/Documentation/devicetree/bindings/display/panel/mantix,mlaf057we51-x.yaml b/Documentation/devicetree/bindings/display/panel/mantix,mlaf057we51-x.yaml
index 937323c..51f4232 100644
--- a/Documentation/devicetree/bindings/display/panel/mantix,mlaf057we51-x.yaml
+++ b/Documentation/devicetree/bindings/display/panel/mantix,mlaf057we51-x.yaml
@@ -37,6 +37,9 @@
reset-gpios: true
+ 'mantix,tp-rstn-gpios':
+ description: second reset line that triggers DSI config load
+
backlight: true
required:
@@ -63,6 +66,7 @@
avee-supply = <®_avee>;
vddi-supply = <®_1v8_p>;
reset-gpios = <&gpio1 29 GPIO_ACTIVE_LOW>;
+ mantix,tp-rstn-gpios = <&gpio1 24 GPIO_ACTIVE_LOW>;
backlight = <&backlight>;
};
};
diff --git a/Documentation/devicetree/bindings/edac/amazon,al-mc-edac.yaml b/Documentation/devicetree/bindings/edac/amazon,al-mc-edac.yaml
index a25387d..57e5270a 100644
--- a/Documentation/devicetree/bindings/edac/amazon,al-mc-edac.yaml
+++ b/Documentation/devicetree/bindings/edac/amazon,al-mc-edac.yaml
@@ -48,6 +48,7 @@
- "#address-cells"
- "#size-cells"
+additionalProperties: false
examples:
- |
diff --git a/Documentation/devicetree/bindings/eeprom/at25.yaml b/Documentation/devicetree/bindings/eeprom/at25.yaml
index 9810619..7449736 100644
--- a/Documentation/devicetree/bindings/eeprom/at25.yaml
+++ b/Documentation/devicetree/bindings/eeprom/at25.yaml
@@ -81,14 +81,14 @@
at25,byte-len:
$ref: /schemas/types.yaml#/definitions/uint32
description:
- Total eeprom size in bytes. Deprecated, use "size" property instead.
+ Total eeprom size in bytes. Deprecated, use "size" property instead.
deprecated: true
at25,addr-mode:
$ref: /schemas/types.yaml#/definitions/uint32
description:
- Addr-mode flags, as defined in include/linux/spi/eeprom.h.
- Deprecated, use "address-width" property instead.
+ Addr-mode flags, as defined in include/linux/spi/eeprom.h.
+ Deprecated, use "address-width" property instead.
deprecated: true
at25,page-size:
diff --git a/Documentation/devicetree/bindings/gpio/kontron,sl28cpld-gpio.yaml b/Documentation/devicetree/bindings/gpio/kontron,sl28cpld-gpio.yaml
index e2d2c10..b032471 100644
--- a/Documentation/devicetree/bindings/gpio/kontron,sl28cpld-gpio.yaml
+++ b/Documentation/devicetree/bindings/gpio/kontron,sl28cpld-gpio.yaml
@@ -43,8 +43,8 @@
gpio-controller: true
gpio-line-names:
- minItems: 1
- maxItems: 8
+ minItems: 1
+ maxItems: 8
required:
- compatible
diff --git a/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml b/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml
new file mode 100644
index 0000000..b386e41
--- /dev/null
+++ b/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml
@@ -0,0 +1,66 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+
+$id: http://devicetree.org/schemas/i2c/google,cros-ec-i2c-tunnel.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: I2C bus that tunnels through the ChromeOS EC (cros-ec)
+
+maintainers:
+ - Doug Anderson <dianders@chromium.org>
+ - Benson Leung <bleung@chromium.org>
+ - Enric Balletbo i Serra <enric.balletbo@collabora.com>
+
+description: |
+ On some ChromeOS board designs we've got a connection to the EC
+ (embedded controller) but no direct connection to some devices on the
+ other side of the EC (like a battery and PMIC). To get access to
+ those devices we need to tunnel our i2c commands through the EC.
+
+ The node for this device should be under a cros-ec node like
+ google,cros-ec-spi or google,cros-ec-i2c.
+
+allOf:
+ - $ref: i2c-controller.yaml#
+
+properties:
+ compatible:
+ const: google,cros-ec-i2c-tunnel
+
+ google,remote-bus:
+ description: The EC bus we'd like to talk to.
+ $ref: /schemas/types.yaml#/definitions/uint32
+
+required:
+ - compatible
+ - google,remote-bus
+
+unevaluatedProperties: false
+
+examples:
+ - |
+ spi0 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cros-ec@0 {
+ compatible = "google,cros-ec-spi";
+ reg = <0>;
+ spi-max-frequency = <5000000>;
+
+ i2c-tunnel {
+ compatible = "google,cros-ec-i2c-tunnel";
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ google,remote-bus = <0>;
+
+ battery: sbs-battery@b {
+ compatible = "sbs,sbs-battery";
+ reg = <0xb>;
+ sbs,poll-retry-count = <1>;
+ };
+ };
+ };
+ };
diff --git a/Documentation/devicetree/bindings/i2c/i2c-cros-ec-tunnel.txt b/Documentation/devicetree/bindings/i2c/i2c-cros-ec-tunnel.txt
deleted file mode 100644
index 898f030..0000000
--- a/Documentation/devicetree/bindings/i2c/i2c-cros-ec-tunnel.txt
+++ /dev/null
@@ -1,39 +0,0 @@
-I2C bus that tunnels through the ChromeOS EC (cros-ec)
-======================================================
-On some ChromeOS board designs we've got a connection to the EC (embedded
-controller) but no direct connection to some devices on the other side of
-the EC (like a battery and PMIC). To get access to those devices we need
-to tunnel our i2c commands through the EC.
-
-The node for this device should be under a cros-ec node like google,cros-ec-spi
-or google,cros-ec-i2c.
-
-
-Required properties:
-- compatible: google,cros-ec-i2c-tunnel
-- google,remote-bus: The EC bus we'd like to talk to.
-
-Optional child nodes:
-- One node per I2C device connected to the tunnelled I2C bus.
-
-
-Example:
- cros-ec@0 {
- compatible = "google,cros-ec-spi";
-
- ...
-
- i2c-tunnel {
- compatible = "google,cros-ec-i2c-tunnel";
- #address-cells = <1>;
- #size-cells = <0>;
-
- google,remote-bus = <0>;
-
- battery: sbs-battery@b {
- compatible = "sbs,sbs-battery";
- reg = <0xb>;
- sbs,poll-retry-count = <1>;
- };
- };
- }
diff --git a/Documentation/devicetree/bindings/i2c/ingenic,i2c.yaml b/Documentation/devicetree/bindings/i2c/ingenic,i2c.yaml
index 0e7b4b8..e1e65eb 100644
--- a/Documentation/devicetree/bindings/i2c/ingenic,i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/ingenic,i2c.yaml
@@ -19,11 +19,11 @@
compatible:
oneOf:
- enum:
- - ingenic,jz4770-i2c
- - ingenic,x1000-i2c
+ - ingenic,jz4770-i2c
+ - ingenic,x1000-i2c
- items:
- - const: ingenic,jz4780-i2c
- - const: ingenic,jz4770-i2c
+ - const: ingenic,jz4780-i2c
+ - const: ingenic,jz4770-i2c
reg:
maxItems: 1
diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7291.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7291.yaml
index 6feafb7..930f9e3 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7291.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7291.yaml
@@ -43,4 +43,5 @@
vref-supply = <&adc_vref>;
};
};
-...
\ No newline at end of file
+...
+
diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.yaml
index d3733ad..8f32800 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.yaml
@@ -46,7 +46,8 @@
spi-max-frequency: true
spi-cpol: true
- spi-cpha : true
+
+ spi-cpha: true
"#io-channel-cells":
const: 1
diff --git a/Documentation/devicetree/bindings/iio/adc/cosmic,10001-adc.yaml b/Documentation/devicetree/bindings/iio/adc/cosmic,10001-adc.yaml
index 5d92b47..4e695b9 100644
--- a/Documentation/devicetree/bindings/iio/adc/cosmic,10001-adc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/cosmic,10001-adc.yaml
@@ -22,8 +22,8 @@
adc-reserved-channels:
$ref: /schemas/types.yaml#/definitions/uint32
description:
- Bitmask of reserved channels, i.e. channels that cannot be
- used by the OS.
+ Bitmask of reserved channels, i.e. channels that cannot be
+ used by the OS.
clocks:
maxItems: 1
diff --git a/Documentation/devicetree/bindings/iio/adc/holt,hi8435.yaml b/Documentation/devicetree/bindings/iio/adc/holt,hi8435.yaml
index 9514c33..52490cb 100644
--- a/Documentation/devicetree/bindings/iio/adc/holt,hi8435.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/holt,hi8435.yaml
@@ -21,7 +21,7 @@
gpios:
description:
- GPIO used for controlling the reset pin
+ GPIO used for controlling the reset pin
maxItems: 1
spi-max-frequency: true
diff --git a/Documentation/devicetree/bindings/iio/adc/lltc,ltc2497.yaml b/Documentation/devicetree/bindings/iio/adc/lltc,ltc2497.yaml
index 6a176f5..c1772b5 100644
--- a/Documentation/devicetree/bindings/iio/adc/lltc,ltc2497.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/lltc,ltc2497.yaml
@@ -28,6 +28,8 @@
- reg
- vref-supply
+additionalProperties: false
+
examples:
- |
i2c {
diff --git a/Documentation/devicetree/bindings/iio/humidity/ti,hdc2010.yaml b/Documentation/devicetree/bindings/iio/humidity/ti,hdc2010.yaml
index dc870eb..7037f82 100644
--- a/Documentation/devicetree/bindings/iio/humidity/ti,hdc2010.yaml
+++ b/Documentation/devicetree/bindings/iio/humidity/ti,hdc2010.yaml
@@ -32,6 +32,8 @@
- compatible
- reg
+additionalProperties: false
+
examples:
- |
i2c0 {
diff --git a/Documentation/devicetree/bindings/input/cros-ec-keyb.txt b/Documentation/devicetree/bindings/input/cros-ec-keyb.txt
deleted file mode 100644
index 0f6355c..0000000
--- a/Documentation/devicetree/bindings/input/cros-ec-keyb.txt
+++ /dev/null
@@ -1,72 +0,0 @@
-ChromeOS EC Keyboard
-
-Google's ChromeOS EC Keyboard is a simple matrix keyboard implemented on
-a separate EC (Embedded Controller) device. It provides a message for reading
-key scans from the EC. These are then converted into keycodes for processing
-by the kernel.
-
-This binding is based on matrix-keymap.txt and extends/modifies it as follows:
-
-Required properties:
-- compatible: "google,cros-ec-keyb"
-
-Optional properties:
-- google,needs-ghost-filter: True to enable a ghost filter for the matrix
-keyboard. This is recommended if the EC does not have its own logic or
-hardware for this.
-
-
-Example:
-
-cros-ec-keyb {
- compatible = "google,cros-ec-keyb";
- keypad,num-rows = <8>;
- keypad,num-columns = <13>;
- google,needs-ghost-filter;
- /*
- * Keymap entries take the form of 0xRRCCKKKK where
- * RR=Row CC=Column KKKK=Key Code
- * The values below are for a US keyboard layout and
- * are taken from the Linux driver. Note that the
- * 102ND key is not used for US keyboards.
- */
- linux,keymap = <
- /* CAPSLCK F1 B F10 */
- 0x0001003a 0x0002003b 0x00030030 0x00040044
- /* N = R_ALT ESC */
- 0x00060031 0x0008000d 0x000a0064 0x01010001
- /* F4 G F7 H */
- 0x0102003e 0x01030022 0x01040041 0x01060023
- /* ' F9 BKSPACE L_CTRL */
- 0x01080028 0x01090043 0x010b000e 0x0200001d
- /* TAB F3 T F6 */
- 0x0201000f 0x0202003d 0x02030014 0x02040040
- /* ] Y 102ND [ */
- 0x0205001b 0x02060015 0x02070056 0x0208001a
- /* F8 GRAVE F2 5 */
- 0x02090042 0x03010029 0x0302003c 0x03030006
- /* F5 6 - \ */
- 0x0304003f 0x03060007 0x0308000c 0x030b002b
- /* R_CTRL A D F */
- 0x04000061 0x0401001e 0x04020020 0x04030021
- /* S K J ; */
- 0x0404001f 0x04050025 0x04060024 0x04080027
- /* L ENTER Z C */
- 0x04090026 0x040b001c 0x0501002c 0x0502002e
- /* V X , M */
- 0x0503002f 0x0504002d 0x05050033 0x05060032
- /* L_SHIFT / . SPACE */
- 0x0507002a 0x05080035 0x05090034 0x050B0039
- /* 1 3 4 2 */
- 0x06010002 0x06020004 0x06030005 0x06040003
- /* 8 7 0 9 */
- 0x06050009 0x06060008 0x0608000b 0x0609000a
- /* L_ALT DOWN RIGHT Q */
- 0x060a0038 0x060b006c 0x060c006a 0x07010010
- /* E R W I */
- 0x07020012 0x07030013 0x07040011 0x07050017
- /* U R_SHIFT P O */
- 0x07060016 0x07070036 0x07080019 0x07090018
- /* UP LEFT */
- 0x070b0067 0x070c0069>;
-};
diff --git a/Documentation/devicetree/bindings/input/google,cros-ec-keyb.yaml b/Documentation/devicetree/bindings/input/google,cros-ec-keyb.yaml
new file mode 100644
index 0000000..8e50c14
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/google,cros-ec-keyb.yaml
@@ -0,0 +1,92 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+
+$id: http://devicetree.org/schemas/input/google,cros-ec-keyb.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ChromeOS EC Keyboard
+
+maintainers:
+ - Simon Glass <sjg@chromium.org>
+ - Benson Leung <bleung@chromium.org>
+ - Enric Balletbo i Serra <enric.balletbo@collabora.com>
+
+description: |
+ Google's ChromeOS EC Keyboard is a simple matrix keyboard
+ implemented on a separate EC (Embedded Controller) device. It provides
+ a message for reading key scans from the EC. These are then converted
+ into keycodes for processing by the kernel.
+
+allOf:
+ - $ref: "/schemas/input/matrix-keymap.yaml#"
+
+properties:
+ compatible:
+ const: google,cros-ec-keyb
+
+ google,needs-ghost-filter:
+ description:
+ Enable a ghost filter for the matrix keyboard. This is recommended
+ if the EC does not have its own logic or hardware for this.
+ type: boolean
+
+required:
+ - compatible
+
+unevaluatedProperties: false
+
+examples:
+ - |
+ cros-ec-keyb {
+ compatible = "google,cros-ec-keyb";
+ keypad,num-rows = <8>;
+ keypad,num-columns = <13>;
+ google,needs-ghost-filter;
+ /*
+ * Keymap entries take the form of 0xRRCCKKKK where
+ * RR=Row CC=Column KKKK=Key Code
+ * The values below are for a US keyboard layout and
+ * are taken from the Linux driver. Note that the
+ * 102ND key is not used for US keyboards.
+ */
+ linux,keymap = <
+ /* CAPSLCK F1 B F10 */
+ 0x0001003a 0x0002003b 0x00030030 0x00040044
+ /* N = R_ALT ESC */
+ 0x00060031 0x0008000d 0x000a0064 0x01010001
+ /* F4 G F7 H */
+ 0x0102003e 0x01030022 0x01040041 0x01060023
+ /* ' F9 BKSPACE L_CTRL */
+ 0x01080028 0x01090043 0x010b000e 0x0200001d
+ /* TAB F3 T F6 */
+ 0x0201000f 0x0202003d 0x02030014 0x02040040
+ /* ] Y 102ND [ */
+ 0x0205001b 0x02060015 0x02070056 0x0208001a
+ /* F8 GRAVE F2 5 */
+ 0x02090042 0x03010029 0x0302003c 0x03030006
+ /* F5 6 - \ */
+ 0x0304003f 0x03060007 0x0308000c 0x030b002b
+ /* R_CTRL A D F */
+ 0x04000061 0x0401001e 0x04020020 0x04030021
+ /* S K J ; */
+ 0x0404001f 0x04050025 0x04060024 0x04080027
+ /* L ENTER Z C */
+ 0x04090026 0x040b001c 0x0501002c 0x0502002e
+ /* V X , M */
+ 0x0503002f 0x0504002d 0x05050033 0x05060032
+ /* L_SHIFT / . SPACE */
+ 0x0507002a 0x05080035 0x05090034 0x050B0039
+ /* 1 3 4 2 */
+ 0x06010002 0x06020004 0x06030005 0x06040003
+ /* 8 7 0 9 */
+ 0x06050009 0x06060008 0x0608000b 0x0609000a
+ /* L_ALT DOWN RIGHT Q */
+ 0x060a0038 0x060b006c 0x060c006a 0x07010010
+ /* E R W I */
+ 0x07020012 0x07030013 0x07040011 0x07050017
+ /* U R_SHIFT P O */
+ 0x07060016 0x07070036 0x07080019 0x07090018
+ /* UP LEFT */
+ 0x070b0067 0x070c0069>;
+ };
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,pruss-intc.yaml b/Documentation/devicetree/bindings/interrupt-controller/ti,pruss-intc.yaml
index bbf79d1..1c4c009 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/ti,pruss-intc.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/ti,pruss-intc.yaml
@@ -94,12 +94,12 @@
instances.
required:
- - compatible
- - reg
- - interrupts
- - interrupt-names
- - interrupt-controller
- - "#interrupt-cells"
+ - compatible
+ - reg
+ - interrupts
+ - interrupt-names
+ - interrupt-controller
+ - "#interrupt-cells"
additionalProperties: false
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml
index c7cd056..b5af120 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml
@@ -32,6 +32,11 @@
| | vint | bit | | 0 |.....|63| vintx |
| +--------------+ +------------+ |
| |
+ | Unmap |
+ | +--------------+ |
+ Unmapped events ---->| | umapidx |-------------------------> Globalevents
+ | +--------------+ |
+ | |
+-----------------------------------------+
Configuration of these Intmap registers that maps global events to vint is
@@ -70,6 +75,11 @@
- description: |
"limit" specifies the limit for translation
+ ti,unmapped-event-sources:
+ $ref: /schemas/types.yaml#definitions/phandle-array
+ description:
+ Array of phandles to DMA controllers where the unmapped events originate.
+
required:
- compatible
- reg
@@ -79,6 +89,8 @@
- ti,sci-dev-id
- ti,interrupt-ranges
+unevaluatedProperties: false
+
examples:
- |
bus {
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.yaml b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.yaml
index cff6a95..e12aee4 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-intr.yaml
@@ -88,6 +88,8 @@
- ti,sci-dev-id
- ti,interrupt-ranges
+unevaluatedProperties: false
+
examples:
- |
main_gpio_intr: interrupt-controller0 {
diff --git a/Documentation/devicetree/bindings/leds/backlight/common.yaml b/Documentation/devicetree/bindings/leds/backlight/common.yaml
index 4e7e95e..bc817f7 100644
--- a/Documentation/devicetree/bindings/leds/backlight/common.yaml
+++ b/Documentation/devicetree/bindings/leds/backlight/common.yaml
@@ -32,3 +32,5 @@
that a LED can be made so bright that it gets damaged or causes damage
due to restrictions in a specific system, such as mounting conditions.
$ref: /schemas/types.yaml#definitions/uint32
+
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/leds/common.yaml b/Documentation/devicetree/bindings/leds/common.yaml
index 08b6700..f1211e70 100644
--- a/Documentation/devicetree/bindings/leds/common.yaml
+++ b/Documentation/devicetree/bindings/leds/common.yaml
@@ -43,7 +43,7 @@
LED_COLOR_ID available, add a new one.
$ref: /schemas/types.yaml#definitions/uint32
minimum: 0
- maximum: 8
+ maximum: 9
function-enumerator:
description:
diff --git a/Documentation/devicetree/bindings/leds/leds-class-multicolor.yaml b/Documentation/devicetree/bindings/leds/leds-class-multicolor.yaml
index b1a53f05..37445c6 100644
--- a/Documentation/devicetree/bindings/leds/leds-class-multicolor.yaml
+++ b/Documentation/devicetree/bindings/leds/leds-class-multicolor.yaml
@@ -16,7 +16,7 @@
modules. This is achieved by adding multi-led nodes layer to the
monochrome LED bindings.
The nodes and properties defined in this document are unique to the multicolor
- LED class. Common LED nodes and properties are inherited from the common.txt
+ LED class. Common LED nodes and properties are inherited from the common.yaml
within this documentation directory.
patternProperties:
@@ -25,10 +25,11 @@
description: Represents the LEDs that are to be grouped.
properties:
color:
- const: 8 # LED_COLOR_ID_MULTI
description: |
- For multicolor LED support this property should be defined as
- LED_COLOR_ID_MULTI which can be found in include/linux/leds/common.h.
+ For multicolor LED support this property should be defined as either
+ LED_COLOR_ID_RGB or LED_COLOR_ID_MULTI which can be found in
+ include/linux/leds/common.h.
+ enum: [ 8, 9 ]
$ref: "common.yaml#"
diff --git a/Documentation/devicetree/bindings/leds/leds-lp50xx.yaml b/Documentation/devicetree/bindings/leds/leds-lp50xx.yaml
index 947542a..c192b5f 100644
--- a/Documentation/devicetree/bindings/leds/leds-lp50xx.yaml
+++ b/Documentation/devicetree/bindings/leds/leds-lp50xx.yaml
@@ -46,6 +46,12 @@
vled-supply:
description: LED supply.
+ '#address-cells':
+ const: 1
+
+ '#size-cells':
+ const: 0
+
patternProperties:
'^multi-led@[0-9a-f]$':
type: object
@@ -69,6 +75,8 @@
- compatible
- reg
+additionalProperties: false
+
examples:
- |
#include <dt-bindings/gpio/gpio.h>
diff --git a/Documentation/devicetree/bindings/mailbox/mtk-gce.txt b/Documentation/devicetree/bindings/mailbox/mtk-gce.txt
index cf48cd8..7771eca 100644
--- a/Documentation/devicetree/bindings/mailbox/mtk-gce.txt
+++ b/Documentation/devicetree/bindings/mailbox/mtk-gce.txt
@@ -47,7 +47,7 @@
interrupts = <GIC_SPI 135 IRQ_TYPE_LEVEL_LOW>;
clocks = <&infracfg CLK_INFRA_GCE>;
clock-names = "gce";
- #mbox-cells = <3>;
+ #mbox-cells = <2>;
};
Example for a client device:
diff --git a/Documentation/devicetree/bindings/mfd/ene-kb3930.yaml b/Documentation/devicetree/bindings/mfd/ene-kb3930.yaml
index 074243c..08af356 100644
--- a/Documentation/devicetree/bindings/mfd/ene-kb3930.yaml
+++ b/Documentation/devicetree/bindings/mfd/ene-kb3930.yaml
@@ -17,7 +17,7 @@
compatible:
items:
- enum:
- - dell,wyse-ariel-ec # Dell Wyse Ariel board (3020)
+ - dell,wyse-ariel-ec # Dell Wyse Ariel board (3020)
- const: ene,kb3930
reg:
maxItems: 1
diff --git a/Documentation/devicetree/bindings/mfd/google,cros-ec.yaml b/Documentation/devicetree/bindings/mfd/google,cros-ec.yaml
index f49c0d5..76bf16e 100644
--- a/Documentation/devicetree/bindings/mfd/google,cros-ec.yaml
+++ b/Documentation/devicetree/bindings/mfd/google,cros-ec.yaml
@@ -59,6 +59,14 @@
whether this nvram is present or not.
type: boolean
+ mtk,rpmsg-name:
+ description:
+ Must be defined if the cros-ec is a rpmsg device for a Mediatek
+ ARM Cortex M4 Co-processor. Contains the name pf the rpmsg
+ device. Used to match the subnode to the rpmsg device announced by
+ the SCP.
+ $ref: "/schemas/types.yaml#/definitions/string"
+
spi-max-frequency:
description: Maximum SPI frequency of the device in Hz.
@@ -71,6 +79,54 @@
wakeup-source:
description: Button can wake-up the system.
+ '#address-cells':
+ const: 1
+
+ '#size-cells':
+ const: 0
+
+ typec:
+ $ref: "/schemas/chrome/google,cros-ec-typec.yaml#"
+
+ ec-pwm:
+ $ref: "/schemas/pwm/google,cros-ec-pwm.yaml#"
+
+ keyboard-controller:
+ $ref: "/schemas/input/google,cros-ec-keyb.yaml#"
+
+ codecs:
+ type: object
+ additionalProperties: false
+
+ properties:
+ '#address-cells':
+ const: 2
+
+ '#size-cells':
+ const: 1
+
+ patternProperties:
+ "^ec-codec@[a-f0-9]+$":
+ type: object
+ $ref: "/schemas/sound/google,cros-ec-codec.yaml#"
+
+ required:
+ - "#address-cells"
+ - "#size-cells"
+
+patternProperties:
+ "^i2c-tunnel[0-9]*$":
+ type: object
+ $ref: "/schemas/i2c/google,cros-ec-i2c-tunnel.yaml#"
+
+ "^regulator@[0-9]+$":
+ type: object
+ $ref: "/schemas/regulator/google,cros-ec-regulator.yaml#"
+
+ "^extcon[0-9]*$":
+ type: object
+ $ref: "/schemas/extcon/extcon-usbc-cros-ec.yaml#"
+
required:
- compatible
diff --git a/Documentation/devicetree/bindings/mips/ingenic/devices.yaml b/Documentation/devicetree/bindings/mips/ingenic/devices.yaml
index dc21b46..ee00d41 100644
--- a/Documentation/devicetree/bindings/mips/ingenic/devices.yaml
+++ b/Documentation/devicetree/bindings/mips/ingenic/devices.yaml
@@ -52,4 +52,7 @@
items:
- const: yna,cu2000-neo
- const: ingenic,x2000e
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/mips/loongson/devices.yaml b/Documentation/devicetree/bindings/mips/loongson/devices.yaml
index d25e80a..9fee670 100644
--- a/Documentation/devicetree/bindings/mips/loongson/devices.yaml
+++ b/Documentation/devicetree/bindings/mips/loongson/devices.yaml
@@ -36,4 +36,7 @@
- description: Virtual Loongson64 Quad Core + VirtIO
items:
- const: loongson,loongson64v-4core-virtio
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml b/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml
index 58fe9d0..0753289 100644
--- a/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml
+++ b/Documentation/devicetree/bindings/mmc/arasan,sdhci.yaml
@@ -32,11 +32,11 @@
clock-output-names:
oneOf:
- items:
- - const: clk_out_sd0
- - const: clk_in_sd0
+ - const: clk_out_sd0
+ - const: clk_in_sd0
- items:
- - const: clk_out_sd1
- - const: clk_in_sd1
+ - const: clk_out_sd1
+ - const: clk_in_sd1
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/mmc/microchip,dw-sparx5-sdhci.yaml b/Documentation/devicetree/bindings/mmc/microchip,dw-sparx5-sdhci.yaml
index 5588329..69ff065 100644
--- a/Documentation/devicetree/bindings/mmc/microchip,dw-sparx5-sdhci.yaml
+++ b/Documentation/devicetree/bindings/mmc/microchip,dw-sparx5-sdhci.yaml
@@ -46,6 +46,8 @@
- clocks
- clock-names
+unevaluatedProperties: false
+
examples:
- |
#include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/mmc/sdhci-am654.yaml b/Documentation/devicetree/bindings/mmc/sdhci-am654.yaml
index ac79f3a..1ae9454 100644
--- a/Documentation/devicetree/bindings/mmc/sdhci-am654.yaml
+++ b/Documentation/devicetree/bindings/mmc/sdhci-am654.yaml
@@ -3,7 +3,7 @@
%YAML 1.2
---
$id: "http://devicetree.org/schemas/mmc/sdhci-am654.yaml#"
-$schema : "http://devicetree.org/meta-schemas/core.yaml#"
+$schema: "http://devicetree.org/meta-schemas/core.yaml#"
title: TI AM654 MMC Controller
@@ -163,13 +163,12 @@
ti,driver-strength-ohm:
description: DLL drive strength in ohms
$ref: "/schemas/types.yaml#/definitions/uint32"
- oneOf:
- - enum:
- - 33
- - 40
- - 50
- - 66
- - 100
+ enum:
+ - 33
+ - 40
+ - 50
+ - 66
+ - 100
ti,strobe-sel:
description: strobe select delay for HS400 speed mode.
@@ -187,6 +186,8 @@
- clock-names
- ti,otap-del-sel-legacy
+unevaluatedProperties: false
+
examples:
- |
#include <dt-bindings/interrupt-controller/irq.h>
diff --git a/Documentation/devicetree/bindings/net/can/can-controller.yaml b/Documentation/devicetree/bindings/net/can/can-controller.yaml
new file mode 100644
index 0000000..9cf2ae0
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/can-controller.yaml
@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/can/can-controller.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: CAN Controller Generic Binding
+
+maintainers:
+ - Marc Kleine-Budde <mkl@pengutronix.de>
+
+properties:
+ $nodename:
+ pattern: "^can(@.*)?$"
+
+additionalProperties: true
+
+...
diff --git a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
new file mode 100644
index 0000000..13875ea
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
@@ -0,0 +1,139 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/can/fsl,flexcan.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title:
+ Flexcan CAN controller on Freescale's ARM and PowerPC system-on-a-chip (SOC).
+
+maintainers:
+ - Marc Kleine-Budde <mkl@pengutronix.de>
+
+allOf:
+ - $ref: can-controller.yaml#
+
+properties:
+ compatible:
+ oneOf:
+ - enum:
+ - fsl,imx8qm-flexcan
+ - fsl,imx8mp-flexcan
+ - fsl,imx6q-flexcan
+ - fsl,imx28-flexcan
+ - fsl,imx25-flexcan
+ - fsl,p1010-flexcan
+ - fsl,vf610-flexcan
+ - fsl,ls1021ar2-flexcan
+ - fsl,lx2160ar1-flexcan
+ - items:
+ - enum:
+ - fsl,imx53-flexcan
+ - fsl,imx35-flexcan
+ - const: fsl,imx25-flexcan
+ - items:
+ - enum:
+ - fsl,imx7d-flexcan
+ - fsl,imx6ul-flexcan
+ - fsl,imx6sx-flexcan
+ - const: fsl,imx6q-flexcan
+ - items:
+ - enum:
+ - fsl,ls1028ar1-flexcan
+ - const: fsl,lx2160ar1-flexcan
+
+ reg:
+ maxItems: 1
+
+ interrupts:
+ maxItems: 1
+
+ clocks:
+ maxItems: 2
+
+ clock-names:
+ items:
+ - const: ipg
+ - const: per
+
+ clock-frequency:
+ description: |
+ The oscillator frequency driving the flexcan device, filled in by the
+ boot loader. This property should only be used the used operating system
+ doesn't support the clocks and clock-names property.
+
+ xceiver-supply:
+ description: Regulator that powers the CAN transceiver.
+
+ big-endian:
+ $ref: /schemas/types.yaml#/definitions/flag
+ description: |
+ This means the registers of FlexCAN controller are big endian. This is
+ optional property.i.e. if this property is not present in device tree
+ node then controller is assumed to be little endian. If this property is
+ present then controller is assumed to be big endian.
+
+ fsl,stop-mode:
+ description: |
+ Register bits of stop mode control.
+
+ The format should be as follows:
+ <gpr req_gpr req_bit>
+ gpr is the phandle to general purpose register node.
+ req_gpr is the gpr register offset of CAN stop request.
+ req_bit is the bit offset of CAN stop request.
+ $ref: /schemas/types.yaml#/definitions/phandle-array
+ items:
+ items:
+ - description: The 'gpr' is the phandle to general purpose register node.
+ - description: The 'req_gpr' is the gpr register offset of CAN stop request.
+ maximum: 0xff
+ - description: The 'req_bit' is the bit offset of CAN stop request.
+ maximum: 0x1f
+
+ fsl,clk-source:
+ description: |
+ Select the clock source to the CAN Protocol Engine (PE). It's SoC
+ implementation dependent. Refer to RM for detailed definition. If this
+ property is not set in device tree node then driver selects clock source 1
+ by default.
+ 0: clock source 0 (oscillator clock)
+ 1: clock source 1 (peripheral clock)
+ $ref: /schemas/types.yaml#/definitions/uint32
+ default: 1
+ minimum: 0
+ maximum: 1
+
+ wakeup-source:
+ $ref: /schemas/types.yaml#/definitions/flag
+ description:
+ Enable CAN remote wakeup.
+
+required:
+ - compatible
+ - reg
+ - interrupts
+
+additionalProperties: false
+
+examples:
+ - |
+ can@1c000 {
+ compatible = "fsl,p1010-flexcan";
+ reg = <0x1c000 0x1000>;
+ interrupts = <48 0x2>;
+ interrupt-parent = <&mpic>;
+ clock-frequency = <200000000>;
+ fsl,clk-source = <0>;
+ };
+ - |
+ #include <dt-bindings/interrupt-controller/irq.h>
+
+ can@2090000 {
+ compatible = "fsl,imx6q-flexcan";
+ reg = <0x02090000 0x4000>;
+ interrupts = <0 110 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clks 1>, <&clks 2>;
+ clock-names = "ipg", "per";
+ fsl,stop-mode = <&gpr 0x34 28>;
+ };
diff --git a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt b/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt
deleted file mode 100644
index e10b6eb..0000000
--- a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt
+++ /dev/null
@@ -1,57 +0,0 @@
-Flexcan CAN controller on Freescale's ARM and PowerPC system-on-a-chip (SOC).
-
-Required properties:
-
-- compatible : Should be "fsl,<processor>-flexcan"
-
- where <processor> is imx8qm, imx6q, imx28, imx53, imx35, imx25, p1010,
- vf610, ls1021ar2, lx2160ar1, ls1028ar1.
-
- The ls1028ar1 must be followed by lx2160ar1, e.g.
- - "fsl,ls1028ar1-flexcan", "fsl,lx2160ar1-flexcan"
-
- An implementation should also claim any of the following compatibles
- that it is fully backwards compatible with:
-
- - fsl,p1010-flexcan
-
-- reg : Offset and length of the register set for this device
-- interrupts : Interrupt tuple for this device
-
-Optional properties:
-
-- clock-frequency : The oscillator frequency driving the flexcan device
-
-- xceiver-supply: Regulator that powers the CAN transceiver
-
-- big-endian: This means the registers of FlexCAN controller are big endian.
- This is optional property.i.e. if this property is not present in
- device tree node then controller is assumed to be little endian.
- if this property is present then controller is assumed to be big
- endian.
-
-- fsl,stop-mode: register bits of stop mode control, the format is
- <&gpr req_gpr req_bit>.
- gpr is the phandle to general purpose register node.
- req_gpr is the gpr register offset of CAN stop request.
- req_bit is the bit offset of CAN stop request.
-
-- fsl,clk-source: Select the clock source to the CAN Protocol Engine (PE).
- It's SoC Implementation dependent. Refer to RM for detailed
- definition. If this property is not set in device tree node
- then driver selects clock source 1 by default.
- 0: clock source 0 (oscillator clock)
- 1: clock source 1 (peripheral clock)
-
-- wakeup-source: enable CAN remote wakeup
-
-Example:
-
- can@1c000 {
- compatible = "fsl,p1010-flexcan";
- reg = <0x1c000 0x1000>;
- interrupts = <48 0x2>;
- interrupt-parent = <&mpic>;
- clock-frequency = <200000000>; // filled in by bootloader
- fsl,clk-source = <0>; // select clock source 0 for PE
- };
diff --git a/Documentation/devicetree/bindings/net/intel,dwmac-plat.yaml b/Documentation/devicetree/bindings/net/intel,dwmac-plat.yaml
index fa3ebba..c1948ce 100644
--- a/Documentation/devicetree/bindings/net/intel,dwmac-plat.yaml
+++ b/Documentation/devicetree/bindings/net/intel,dwmac-plat.yaml
@@ -46,6 +46,8 @@
- clocks
- clock-names
+unevaluatedProperties: false
+
examples:
# FIXME: Remove defines and include the correct header file
# once it is available in mainline.
diff --git a/Documentation/devicetree/bindings/net/ti,dp83822.yaml b/Documentation/devicetree/bindings/net/ti,dp83822.yaml
index 5591353..75e8712 100644
--- a/Documentation/devicetree/bindings/net/ti,dp83822.yaml
+++ b/Documentation/devicetree/bindings/net/ti,dp83822.yaml
@@ -65,6 +65,8 @@
required:
- reg
+unevaluatedProperties: false
+
examples:
- |
mdio0 {
diff --git a/Documentation/devicetree/bindings/pci/socionext,uniphier-pcie-ep.yaml b/Documentation/devicetree/bindings/pci/socionext,uniphier-pcie-ep.yaml
index f4292d2..d6cf8a5 100644
--- a/Documentation/devicetree/bindings/pci/socionext,uniphier-pcie-ep.yaml
+++ b/Documentation/devicetree/bindings/pci/socionext,uniphier-pcie-ep.yaml
@@ -29,16 +29,16 @@
reg-names:
oneOf:
- items:
- - const: dbi
- - const: dbi2
- - const: link
- - const: addr_space
+ - const: dbi
+ - const: dbi2
+ - const: link
+ - const: addr_space
- items:
- - const: dbi
- - const: dbi2
- - const: link
- - const: addr_space
- - const: atu
+ - const: dbi
+ - const: dbi2
+ - const: link
+ - const: addr_space
+ - const: atu
clocks:
maxItems: 2
diff --git a/Documentation/devicetree/bindings/phy/socionext,uniphier-ahci-phy.yaml b/Documentation/devicetree/bindings/phy/socionext,uniphier-ahci-phy.yaml
index bab2ff4..3475634 100644
--- a/Documentation/devicetree/bindings/phy/socionext,uniphier-ahci-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/socionext,uniphier-ahci-phy.yaml
@@ -31,10 +31,10 @@
clock-names:
oneOf:
- items: # for PXs2
- - const: link
+ - const: link
- items: # for others
- - const: link
- - const: phy
+ - const: link
+ - const: phy
resets:
maxItems: 2
diff --git a/Documentation/devicetree/bindings/phy/ti,omap-usb2.yaml b/Documentation/devicetree/bindings/phy/ti,omap-usb2.yaml
index 15207ca..83d5d0a 100644
--- a/Documentation/devicetree/bindings/phy/ti,omap-usb2.yaml
+++ b/Documentation/devicetree/bindings/phy/ti,omap-usb2.yaml
@@ -7,23 +7,23 @@
title: OMAP USB2 PHY
maintainers:
- - Kishon Vijay Abraham I <kishon@ti.com>
- - Roger Quadros <rogerq@ti.com>
+ - Kishon Vijay Abraham I <kishon@ti.com>
+ - Roger Quadros <rogerq@ti.com>
properties:
compatible:
oneOf:
- items:
- - enum:
- - ti,dra7x-usb2
- - ti,dra7x-usb2-phy2
- - ti,am654-usb2
- - enum:
- - ti,omap-usb2
+ - enum:
+ - ti,dra7x-usb2
+ - ti,dra7x-usb2-phy2
+ - ti,am654-usb2
+ - enum:
+ - ti,omap-usb2
- items:
- - const: ti,am437x-usb2
+ - const: ti,am437x-usb2
- items:
- - const: ti,omap-usb2
+ - const: ti,omap-usb2
reg:
maxItems: 1
@@ -62,6 +62,8 @@
- clocks
- clock-names
+additionalProperties: false
+
examples:
- |
usb0_phy: phy@4100000 {
diff --git a/Documentation/devicetree/bindings/pinctrl/actions,s500-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/actions,s500-pinctrl.yaml
index 33391d3..ccdd9e3 100644
--- a/Documentation/devicetree/bindings/pinctrl/actions,s500-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/actions,s500-pinctrl.yaml
@@ -76,22 +76,22 @@
items:
oneOf:
- enum: [lcd0_d18_mfp, rmii_crs_dv_mfp, rmii_txd0_mfp,
- rmii_txd1_mfp, rmii_txen_mfp, rmii_rxen_mfp, rmii_rxd1_mfp,
- rmii_rxd0_mfp, rmii_ref_clk_mfp, i2s_d0_mfp, i2s_pcm1_mfp,
- i2s0_pcm0_mfp, i2s1_pcm0_mfp, i2s_d1_mfp, ks_in2_mfp,
- ks_in1_mfp, ks_in0_mfp, ks_in3_mfp, ks_out0_mfp,
- ks_out1_mfp, ks_out2_mfp, lvds_o_pn_mfp, dsi_dn0_mfp,
- dsi_dp2_mfp, lcd0_d17_mfp, dsi_dp3_mfp, dsi_dn3_mfp,
- dsi_dp0_mfp, lvds_ee_pn_mfp, spi0_i2c_pcm_mfp,
- spi0_i2s_pcm_mfp, dsi_dnp1_cp_mfp, lvds_e_pn_mfp,
- dsi_dn2_mfp, uart2_rtsb_mfp, uart2_ctsb_mfp, uart3_rtsb_mfp,
- uart3_ctsb_mfp, sd0_d0_mfp, sd0_d1_mfp, sd0_d2_d3_mfp,
- sd1_d0_d3_mfp, sd0_cmd_mfp, sd0_clk_mfp, sd1_cmd_mfp,
- uart0_rx_mfp, clko_25m_mfp, csi_cn_cp_mfp, sens0_ckout_mfp,
- uart0_tx_mfp, i2c0_mfp, csi_dn_dp_mfp, sen0_pclk_mfp,
- pcm1_in_mfp, pcm1_clk_mfp, pcm1_sync_mfp, pcm1_out_mfp,
- dnand_data_wr_mfp, dnand_acle_ce0_mfp, nand_ceb2_mfp,
- nand_ceb3_mfp]
+ rmii_txd1_mfp, rmii_txen_mfp, rmii_rxen_mfp, rmii_rxd1_mfp,
+ rmii_rxd0_mfp, rmii_ref_clk_mfp, i2s_d0_mfp, i2s_pcm1_mfp,
+ i2s0_pcm0_mfp, i2s1_pcm0_mfp, i2s_d1_mfp, ks_in2_mfp,
+ ks_in1_mfp, ks_in0_mfp, ks_in3_mfp, ks_out0_mfp,
+ ks_out1_mfp, ks_out2_mfp, lvds_o_pn_mfp, dsi_dn0_mfp,
+ dsi_dp2_mfp, lcd0_d17_mfp, dsi_dp3_mfp, dsi_dn3_mfp,
+ dsi_dp0_mfp, lvds_ee_pn_mfp, spi0_i2c_pcm_mfp,
+ spi0_i2s_pcm_mfp, dsi_dnp1_cp_mfp, lvds_e_pn_mfp,
+ dsi_dn2_mfp, uart2_rtsb_mfp, uart2_ctsb_mfp, uart3_rtsb_mfp,
+ uart3_ctsb_mfp, sd0_d0_mfp, sd0_d1_mfp, sd0_d2_d3_mfp,
+ sd1_d0_d3_mfp, sd0_cmd_mfp, sd0_clk_mfp, sd1_cmd_mfp,
+ uart0_rx_mfp, clko_25m_mfp, csi_cn_cp_mfp, sens0_ckout_mfp,
+ uart0_tx_mfp, i2c0_mfp, csi_dn_dp_mfp, sen0_pclk_mfp,
+ pcm1_in_mfp, pcm1_clk_mfp, pcm1_sync_mfp, pcm1_out_mfp,
+ dnand_data_wr_mfp, dnand_acle_ce0_mfp, nand_ceb2_mfp,
+ nand_ceb3_mfp]
minItems: 1
maxItems: 32
@@ -100,10 +100,10 @@
Specify the alternative function to be configured for the
given gpio pin groups.
enum: [nor, eth_rmii, eth_smii, spi0, spi1, spi2, spi3, sens0,
- sens1, uart0, uart1, uart2, uart3, uart4, uart5, uart6, i2s0,
- i2s1, pcm1, pcm0, ks, jtag, pwm0, pwm1, pwm2, pwm3, pwm4, pwm5,
- p0, sd0, sd1, sd2, i2c0, i2c1, i2c3, dsi, lvds, usb30, clko_25m,
- mipi_csi, nand, spdif, ts, lcd0]
+ sens1, uart0, uart1, uart2, uart3, uart4, uart5, uart6, i2s0,
+ i2s1, pcm1, pcm0, ks, jtag, pwm0, pwm1, pwm2, pwm3, pwm4, pwm5,
+ p0, sd0, sd1, sd2, i2c0, i2c1, i2c3, dsi, lvds, usb30, clko_25m,
+ mipi_csi, nand, spdif, ts, lcd0]
required:
- groups
@@ -126,14 +126,14 @@
items:
oneOf:
- enum: [sirq_drv, rmii_txd01_txen_drv, rmii_rxer_drv,
- rmii_crs_drv, rmii_rxd10_drv, rmii_ref_clk_drv,
- smi_mdc_mdio_drv, i2s_d0_drv, i2s_bclk0_drv, i2s3_drv,
- i2s13_drv, pcm1_drv, ks_in_drv, ks_out_drv, lvds_all_drv,
- lcd_dsi_drv, dsi_drv, sd0_d0_d3_drv, sd1_d0_d3_drv,
- sd0_cmd_drv, sd0_clk_drv, sd1_cmd_drv, sd1_clk_drv,
- spi0_all_drv, uart0_rx_drv, uart0_tx_drv, uart2_all_drv,
- i2c0_all_drv, i2c12_all_drv, sens0_pclk_drv,
- sens0_ckout_drv, uart3_all_drv]
+ rmii_crs_drv, rmii_rxd10_drv, rmii_ref_clk_drv,
+ smi_mdc_mdio_drv, i2s_d0_drv, i2s_bclk0_drv, i2s3_drv,
+ i2s13_drv, pcm1_drv, ks_in_drv, ks_out_drv, lvds_all_drv,
+ lcd_dsi_drv, dsi_drv, sd0_d0_d3_drv, sd1_d0_d3_drv,
+ sd0_cmd_drv, sd0_clk_drv, sd1_cmd_drv, sd1_clk_drv,
+ spi0_all_drv, uart0_rx_drv, uart0_tx_drv, uart2_all_drv,
+ i2c0_all_drv, i2c12_all_drv, sens0_pclk_drv,
+ sens0_ckout_drv, uart3_all_drv]
minItems: 1
maxItems: 32
@@ -144,29 +144,29 @@
items:
oneOf:
- enum: [dnand_dqs, dnand_dqsn, eth_txd0, eth_txd1, eth_txen,
- eth_rxer, eth_crs_dv, eth_rxd1, eth_rxd0, eth_ref_clk,
- eth_mdc, eth_mdio, sirq0, sirq1, sirq2, i2s_d0, i2s_bclk0,
- i2s_lrclk0, i2s_mclk0, i2s_d1, i2s_bclk1, i2s_lrclk1,
- i2s_mclk1, ks_in0, ks_in1, ks_in2, ks_in3, ks_out0, ks_out1,
- ks_out2, lvds_oep, lvds_oen, lvds_odp, lvds_odn, lvds_ocp,
- lvds_ocn, lvds_obp, lvds_obn, lvds_oap, lvds_oan, lvds_eep,
- lvds_een, lvds_edp, lvds_edn, lvds_ecp, lvds_ecn, lvds_ebp,
- lvds_ebn, lvds_eap, lvds_ean, lcd0_d18, lcd0_d17, dsi_dp3,
- dsi_dn3, dsi_dp1, dsi_dn1, dsi_cp, dsi_cn, dsi_dp0, dsi_dn0,
- dsi_dp2, dsi_dn2, sd0_d0, sd0_d1, sd0_d2, sd0_d3, sd1_d0,
- sd1_d1, sd1_d2, sd1_d3, sd0_cmd, sd0_clk, sd1_cmd, sd1_clk,
- spi0_sclk, spi0_ss, spi0_miso, spi0_mosi, uart0_rx,
- uart0_tx, i2c0_sclk, i2c0_sdata, sensor0_pclk,
- sensor0_ckout, dnand_ale, dnand_cle, dnand_ceb0, dnand_ceb1,
- dnand_ceb2, dnand_ceb3, uart2_rx, uart2_tx, uart2_rtsb,
- uart2_ctsb, uart3_rx, uart3_tx, uart3_rtsb, uart3_ctsb,
- pcm1_in, pcm1_clk, pcm1_sync, pcm1_out, i2c1_sclk,
- i2c1_sdata, i2c2_sclk, i2c2_sdata, csi_dn0, csi_dp0,
- csi_dn1, csi_dp1, csi_dn2, csi_dp2, csi_dn3, csi_dp3,
- csi_cn, csi_cp, dnand_d0, dnand_d1, dnand_d2, dnand_d3,
- dnand_d4, dnand_d5, dnand_d6, dnand_d7, dnand_rb, dnand_rdb,
- dnand_rdbn, dnand_wrb, porb, clko_25m, bsel, pkg0, pkg1,
- pkg2, pkg3]
+ eth_rxer, eth_crs_dv, eth_rxd1, eth_rxd0, eth_ref_clk,
+ eth_mdc, eth_mdio, sirq0, sirq1, sirq2, i2s_d0, i2s_bclk0,
+ i2s_lrclk0, i2s_mclk0, i2s_d1, i2s_bclk1, i2s_lrclk1,
+ i2s_mclk1, ks_in0, ks_in1, ks_in2, ks_in3, ks_out0, ks_out1,
+ ks_out2, lvds_oep, lvds_oen, lvds_odp, lvds_odn, lvds_ocp,
+ lvds_ocn, lvds_obp, lvds_obn, lvds_oap, lvds_oan, lvds_eep,
+ lvds_een, lvds_edp, lvds_edn, lvds_ecp, lvds_ecn, lvds_ebp,
+ lvds_ebn, lvds_eap, lvds_ean, lcd0_d18, lcd0_d17, dsi_dp3,
+ dsi_dn3, dsi_dp1, dsi_dn1, dsi_cp, dsi_cn, dsi_dp0, dsi_dn0,
+ dsi_dp2, dsi_dn2, sd0_d0, sd0_d1, sd0_d2, sd0_d3, sd1_d0,
+ sd1_d1, sd1_d2, sd1_d3, sd0_cmd, sd0_clk, sd1_cmd, sd1_clk,
+ spi0_sclk, spi0_ss, spi0_miso, spi0_mosi, uart0_rx,
+ uart0_tx, i2c0_sclk, i2c0_sdata, sensor0_pclk,
+ sensor0_ckout, dnand_ale, dnand_cle, dnand_ceb0, dnand_ceb1,
+ dnand_ceb2, dnand_ceb3, uart2_rx, uart2_tx, uart2_rtsb,
+ uart2_ctsb, uart3_rx, uart3_tx, uart3_rtsb, uart3_ctsb,
+ pcm1_in, pcm1_clk, pcm1_sync, pcm1_out, i2c1_sclk,
+ i2c1_sdata, i2c2_sclk, i2c2_sdata, csi_dn0, csi_dp0,
+ csi_dn1, csi_dp1, csi_dn2, csi_dp2, csi_dn3, csi_dp3,
+ csi_cn, csi_cp, dnand_d0, dnand_d1, dnand_d2, dnand_d3,
+ dnand_d4, dnand_d5, dnand_d6, dnand_d7, dnand_rb, dnand_rdb,
+ dnand_rdbn, dnand_wrb, porb, clko_25m, bsel, pkg0, pkg1,
+ pkg2, pkg3]
minItems: 1
maxItems: 64
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt8192.yaml b/Documentation/devicetree/bindings/pinctrl/pinctrl-mt8192.yaml
index 5556def..c4c0712 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt8192.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-mt8192.yaml
@@ -106,7 +106,7 @@
required:
- pinmux
- additionalProperties: false
+ additionalProperties: false
required:
- compatible
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8226-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8226-pinctrl.yaml
index 1f0f575..040d2ad 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8226-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8226-pinctrl.yaml
@@ -71,9 +71,9 @@
Specify the alternative function to be configured for the specified
pins. Functions are only valid for gpio pins.
enum: [ gpio, cci_i2c0, blsp_uim1, blsp_uim2, blsp_uim3, blsp_uim5,
- blsp_i2c1, blsp_i2c2, blsp_i2c3, blsp_i2c5, blsp_spi1,
- blsp_spi2, blsp_spi3, blsp_spi5, blsp_uart1, blsp_uart2,
- blsp_uart3, blsp_uart5, cam_mclk0, cam_mclk1, wlan ]
+ blsp_i2c1, blsp_i2c2, blsp_i2c3, blsp_i2c5, blsp_spi1,
+ blsp_spi2, blsp_spi3, blsp_spi5, blsp_uart1, blsp_uart2,
+ blsp_uart3, blsp_uart5, cam_mclk0, cam_mclk1, wlan ]
drive-strength:
enum: [2, 4, 6, 8, 10, 12, 14, 16]
diff --git a/Documentation/devicetree/bindings/pinctrl/toshiba,visconti-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/toshiba,visconti-pinctrl.yaml
index d0d1a01..9f1dab0 100644
--- a/Documentation/devicetree/bindings/pinctrl/toshiba,visconti-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/toshiba,visconti-pinctrl.yaml
@@ -40,24 +40,24 @@
Function to mux.
$ref: "/schemas/types.yaml#/definitions/string"
enum: [i2c0, i2c1, i2c2, i2c3, i2c4, i2c5, i2c6, i2c7, i2c8,
- spi0, spi1, spi2, spi3, spi4, spi5, spi6,
- uart0, uart1, uart2, uart3, pwm, pcmif_out, pcmif_in]
+ spi0, spi1, spi2, spi3, spi4, spi5, spi6,
+ uart0, uart1, uart2, uart3, pwm, pcmif_out, pcmif_in]
groups:
description:
Name of the pin group to use for the functions.
$ref: "/schemas/types.yaml#/definitions/string"
enum: [i2c0_grp, i2c1_grp, i2c2_grp, i2c3_grp, i2c4_grp,
- i2c5_grp, i2c6_grp, i2c7_grp, i2c8_grp,
- spi0_grp, spi0_cs0_grp, spi0_cs1_grp, spi0_cs2_grp,
- spi1_grp, spi2_grp, spi3_grp, spi4_grp, spi5_grp, spi6_grp,
- uart0_grp, uart1_grp, uart2_grp, uart3_grp,
- pwm0_gpio4_grp, pwm0_gpio8_grp, pwm0_gpio12_grp,
- pwm0_gpio16_grp, pwm1_gpio5_grp, pwm1_gpio9_grp,
- pwm1_gpio13_grp, pwm1_gpio17_grp, pwm2_gpio6_grp,
- pwm2_gpio10_grp, pwm2_gpio14_grp, pwm2_gpio18_grp,
- pwm3_gpio7_grp, pwm3_gpio11_grp, pwm3_gpio15_grp,
- pwm3_gpio19_grp, pcmif_out_grp, pcmif_in_grp]
+ i2c5_grp, i2c6_grp, i2c7_grp, i2c8_grp,
+ spi0_grp, spi0_cs0_grp, spi0_cs1_grp, spi0_cs2_grp,
+ spi1_grp, spi2_grp, spi3_grp, spi4_grp, spi5_grp, spi6_grp,
+ uart0_grp, uart1_grp, uart2_grp, uart3_grp,
+ pwm0_gpio4_grp, pwm0_gpio8_grp, pwm0_gpio12_grp,
+ pwm0_gpio16_grp, pwm1_gpio5_grp, pwm1_gpio9_grp,
+ pwm1_gpio13_grp, pwm1_gpio17_grp, pwm2_gpio6_grp,
+ pwm2_gpio10_grp, pwm2_gpio14_grp, pwm2_gpio18_grp,
+ pwm3_gpio7_grp, pwm3_gpio11_grp, pwm3_gpio15_grp,
+ pwm3_gpio19_grp, pcmif_out_grp, pcmif_in_grp]
drive-strength:
enum: [2, 4, 6, 8, 16, 24, 32]
diff --git a/Documentation/devicetree/bindings/power/reset/reboot-mode.yaml b/Documentation/devicetree/bindings/power/reset/reboot-mode.yaml
index a6c9102..9c6fda6 100644
--- a/Documentation/devicetree/bindings/power/reset/reboot-mode.yaml
+++ b/Documentation/devicetree/bindings/power/reset/reboot-mode.yaml
@@ -28,14 +28,16 @@
properties:
mode-normal:
- $ref: /schemas/types.yaml#/definitions/uint32
- description: |
- Default value to set on a reboot if no command was provided.
+ $ref: /schemas/types.yaml#/definitions/uint32
+ description:
+ Default value to set on a reboot if no command was provided.
patternProperties:
"^mode-.*$":
$ref: /schemas/types.yaml#/definitions/uint32
+additionalProperties: false
+
examples:
- |
reboot-mode {
diff --git a/Documentation/devicetree/bindings/power/supply/ingenic,battery.yaml b/Documentation/devicetree/bindings/power/supply/ingenic,battery.yaml
index 867e3e6..76c227a 100644
--- a/Documentation/devicetree/bindings/power/supply/ingenic,battery.yaml
+++ b/Documentation/devicetree/bindings/power/supply/ingenic,battery.yaml
@@ -15,10 +15,10 @@
oneOf:
- const: ingenic,jz4740-battery
- items:
- - enum:
- - ingenic,jz4725b-battery
- - ingenic,jz4770-battery
- - const: ingenic,jz4740-battery
+ - enum:
+ - ingenic,jz4725b-battery
+ - ingenic,jz4770-battery
+ - const: ingenic,jz4740-battery
io-channels:
maxItems: 1
diff --git a/Documentation/devicetree/bindings/power/supply/summit,smb347-charger.yaml b/Documentation/devicetree/bindings/power/supply/summit,smb347-charger.yaml
index 193a23a..983fc21 100644
--- a/Documentation/devicetree/bindings/power/supply/summit,smb347-charger.yaml
+++ b/Documentation/devicetree/bindings/power/supply/summit,smb347-charger.yaml
@@ -84,12 +84,12 @@
then:
properties:
summit,mains-current-limit-microamp:
- enum: [ 300000, 500000, 700000, 1000000,
- 1500000, 1800000, 2000000]
+ enum: [ 300000, 500000, 700000, 1000000,
+ 1500000, 1800000, 2000000]
summit,usb-current-limit-microamp:
- enum: [ 300000, 500000, 700000, 1000000,
- 1500000, 1800000, 2000000]
+ enum: [ 300000, 500000, 700000, 1000000,
+ 1500000, 1800000, 2000000]
summit,charge-current-compensation-microamp:
enum: [200000, 450000, 600000, 900000]
@@ -97,12 +97,12 @@
else:
properties:
summit,mains-current-limit-microamp:
- enum: [ 300000, 500000, 700000, 900000, 1200000,
- 1500000, 1800000, 2000000, 2200000, 2500000]
+ enum: [ 300000, 500000, 700000, 900000, 1200000,
+ 1500000, 1800000, 2000000, 2200000, 2500000]
summit,usb-current-limit-microamp:
- enum: [ 300000, 500000, 700000, 900000, 1200000,
- 1500000, 1800000, 2000000, 2200000, 2500000]
+ enum: [ 300000, 500000, 700000, 900000, 1200000,
+ 1500000, 1800000, 2000000, 2200000, 2500000]
summit,charge-current-compensation-microamp:
enum: [250000, 700000, 900000, 1200000]
diff --git a/Documentation/devicetree/bindings/regulator/mps,mp886x.yaml b/Documentation/devicetree/bindings/regulator/mps,mp886x.yaml
index ba175b3..9245b71 100644
--- a/Documentation/devicetree/bindings/regulator/mps,mp886x.yaml
+++ b/Documentation/devicetree/bindings/regulator/mps,mp886x.yaml
@@ -41,6 +41,8 @@
- enable-gpios
- mps,fb-voltage-divider
+unevaluatedProperties: false
+
examples:
- |
#include <dt-bindings/gpio/gpio.h>
diff --git a/Documentation/devicetree/bindings/regulator/pfuze100.yaml b/Documentation/devicetree/bindings/regulator/pfuze100.yaml
index c6de496..f578e72 100644
--- a/Documentation/devicetree/bindings/regulator/pfuze100.yaml
+++ b/Documentation/devicetree/bindings/regulator/pfuze100.yaml
@@ -80,6 +80,8 @@
- compatible
- reg
+additionalProperties: false
+
examples:
- |
i2c {
diff --git a/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml b/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml
index 3f4a193..efc0198 100644
--- a/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml
+++ b/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml
@@ -25,8 +25,8 @@
properties:
compatible:
items:
- - enum:
- - sifive,fu540-c000-ccache
+ - enum:
+ - sifive,fu540-c000-ccache
required:
- compatible
diff --git a/Documentation/devicetree/bindings/riscv/sifive.yaml b/Documentation/devicetree/bindings/riscv/sifive.yaml
index 3ab5327..3a8647d 100644
--- a/Documentation/devicetree/bindings/riscv/sifive.yaml
+++ b/Documentation/devicetree/bindings/riscv/sifive.yaml
@@ -22,4 +22,7 @@
- sifive,hifive-unleashed-a00
- const: sifive,fu540-c000
- const: sifive,fu540
+
+additionalProperties: true
+
...
diff --git a/Documentation/devicetree/bindings/rng/imx-rng.yaml b/Documentation/devicetree/bindings/rng/imx-rng.yaml
index 4ad1e45..07f6ff8 100644
--- a/Documentation/devicetree/bindings/rng/imx-rng.yaml
+++ b/Documentation/devicetree/bindings/rng/imx-rng.yaml
@@ -19,9 +19,9 @@
- const: fsl,imx21-rnga
- items:
- enum:
- - fsl,imx6sl-rngb
- - fsl,imx6sll-rngb
- - fsl,imx6ull-rngb
+ - fsl,imx6sl-rngb
+ - fsl,imx6sll-rngb
+ - fsl,imx6ull-rngb
- const: fsl,imx25-rngb
- const: fsl,imx35-rngc
diff --git a/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml b/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml
index 9ff85bc..9702c07 100644
--- a/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml
+++ b/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml
@@ -20,30 +20,30 @@
- const: fsl,imx21-uart
- items:
- enum:
- - fsl,imx25-uart
- - fsl,imx27-uart
- - fsl,imx31-uart
- - fsl,imx35-uart
- - fsl,imx50-uart
- - fsl,imx51-uart
- - fsl,imx53-uart
- - fsl,imx6q-uart
+ - fsl,imx25-uart
+ - fsl,imx27-uart
+ - fsl,imx31-uart
+ - fsl,imx35-uart
+ - fsl,imx50-uart
+ - fsl,imx51-uart
+ - fsl,imx53-uart
+ - fsl,imx6q-uart
- const: fsl,imx21-uart
- items:
- enum:
- - fsl,imx6sl-uart
- - fsl,imx6sll-uart
- - fsl,imx6sx-uart
+ - fsl,imx6sl-uart
+ - fsl,imx6sll-uart
+ - fsl,imx6sx-uart
- const: fsl,imx6q-uart
- const: fsl,imx21-uart
- items:
- enum:
- - fsl,imx6ul-uart
- - fsl,imx7d-uart
- - fsl,imx8mm-uart
- - fsl,imx8mn-uart
- - fsl,imx8mp-uart
- - fsl,imx8mq-uart
+ - fsl,imx6ul-uart
+ - fsl,imx7d-uart
+ - fsl,imx8mm-uart
+ - fsl,imx8mn-uart
+ - fsl,imx8mp-uart
+ - fsl,imx8mq-uart
- const: fsl,imx6q-uart
reg:
diff --git a/Documentation/devicetree/bindings/sound/google,cros-ec-codec.yaml b/Documentation/devicetree/bindings/sound/google,cros-ec-codec.yaml
index 3b9143a..acfb9db 100644
--- a/Documentation/devicetree/bindings/sound/google,cros-ec-codec.yaml
+++ b/Documentation/devicetree/bindings/sound/google,cros-ec-codec.yaml
@@ -11,9 +11,10 @@
description: |
Google's ChromeOS EC codec is a digital mic codec provided by the
- Embedded Controller (EC) and is controlled via a host-command interface.
- An EC codec node should only be found as a sub-node of the EC node (see
- Documentation/devicetree/bindings/mfd/google,cros-ec.yaml).
+ Embedded Controller (EC) and is controlled via a host-command
+ interface. An EC codec node should only be found inside the "codecs"
+ subnode of a cros-ec node.
+ (see Documentation/devicetree/bindings/mfd/google,cros-ec.yaml).
properties:
compatible:
@@ -54,14 +55,19 @@
#size-cells = <0>;
cros-ec@0 {
compatible = "google,cros-ec-spi";
- #address-cells = <2>;
- #size-cells = <1>;
reg = <0>;
- cros_ec_codec: ec-codec@10500000 {
- compatible = "google,cros-ec-codec";
- #sound-dai-cells = <1>;
- reg = <0x0 0x10500000 0x80000>;
- memory-region = <&reserved_mem>;
+
+ codecs {
+ #address-cells = <2>;
+ #size-cells = <1>;
+
+ cros_ec_codec: ec-codec@10500000 {
+ compatible = "google,cros-ec-codec";
+ #sound-dai-cells = <1>;
+ reg = <0x0 0x10500000 0x80000>;
+ memory-region = <&reserved_mem>;
+ };
+
};
};
};
diff --git a/Documentation/devicetree/bindings/sound/mchp,spdifrx.yaml b/Documentation/devicetree/bindings/sound/mchp,spdifrx.yaml
index 7d8bd4e..4a21290 100644
--- a/Documentation/devicetree/bindings/sound/mchp,spdifrx.yaml
+++ b/Documentation/devicetree/bindings/sound/mchp,spdifrx.yaml
@@ -10,8 +10,8 @@
- Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
description:
- The Microchip Sony/Philips Digital Interface Receiver is a
- serial port compliant with the IEC-60958 standard.
+ The Microchip Sony/Philips Digital Interface Receiver is a serial port
+ compliant with the IEC-60958 standard.
properties:
"#sound-dai-cells":
diff --git a/Documentation/devicetree/bindings/sound/mchp,spdiftx.yaml b/Documentation/devicetree/bindings/sound/mchp,spdiftx.yaml
index a03b0b8..bdfb633 100644
--- a/Documentation/devicetree/bindings/sound/mchp,spdiftx.yaml
+++ b/Documentation/devicetree/bindings/sound/mchp,spdiftx.yaml
@@ -10,8 +10,8 @@
- Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
description:
- The Microchip Sony/Philips Digital Interface Transmitter is a
- serial port compliant with the IEC-60958 standard.
+ The Microchip Sony/Philips Digital Interface Transmitter is a serial port
+ compliant with the IEC-60958 standard.
properties:
"#sound-dai-cells":
diff --git a/Documentation/devicetree/bindings/sound/qcom,lpass-cpu.yaml b/Documentation/devicetree/bindings/sound/qcom,lpass-cpu.yaml
index f6f9fb4..1e23c0e 100644
--- a/Documentation/devicetree/bindings/sound/qcom,lpass-cpu.yaml
+++ b/Documentation/devicetree/bindings/sound/qcom,lpass-cpu.yaml
@@ -26,8 +26,10 @@
reg:
maxItems: 2
description: LPAIF core registers
+
reg-names:
- maxItems: 2
+ maxItems: 2
+
clocks:
minItems: 3
maxItems: 6
@@ -39,8 +41,10 @@
interrupts:
maxItems: 2
description: LPAIF DMA buffer interrupt
+
interrupt-names:
maxItems: 2
+
qcom,adsp:
$ref: /schemas/types.yaml#/definitions/phandle
description: Phandle for the audio DSP node
@@ -141,31 +145,31 @@
properties:
clock-names:
oneOf:
- - items: #for I2S
- - const: pcnoc-sway-clk
- - const: audio-core
- - const: mclk0
- - const: pcnoc-mport-clk
- - const: mi2s-bit-clk0
- - const: mi2s-bit-clk1
- - items: #for HDMI
- - const: pcnoc-sway-clk
- - const: audio-core
- - const: pcnoc-mport-clk
+ - items: #for I2S
+ - const: pcnoc-sway-clk
+ - const: audio-core
+ - const: mclk0
+ - const: pcnoc-mport-clk
+ - const: mi2s-bit-clk0
+ - const: mi2s-bit-clk1
+ - items: #for HDMI
+ - const: pcnoc-sway-clk
+ - const: audio-core
+ - const: pcnoc-mport-clk
reg-names:
anyOf:
- items: #for I2S
- - const: lpass-lpaif
+ - const: lpass-lpaif
- items: #for I2S and HDMI
- - const: lpass-hdmiif
- - const: lpass-lpaif
+ - const: lpass-hdmiif
+ - const: lpass-lpaif
interrupt-names:
anyOf:
- items: #for I2S
- - const: lpass-irq-lpaif
+ - const: lpass-irq-lpaif
- items: #for I2S and HDMI
- - const: lpass-irq-lpaif
- - const: lpass-irq-hdmi
+ - const: lpass-irq-lpaif
+ - const: lpass-irq-hdmi
required:
- iommus
- power-domains
diff --git a/Documentation/devicetree/bindings/sound/realtek,rt1015p.yaml b/Documentation/devicetree/bindings/sound/realtek,rt1015p.yaml
index def1db2..644b68e 100644
--- a/Documentation/devicetree/bindings/sound/realtek,rt1015p.yaml
+++ b/Documentation/devicetree/bindings/sound/realtek,rt1015p.yaml
@@ -26,6 +26,8 @@
required:
- compatible
+additionalProperties: false
+
examples:
- |
#include <dt-bindings/gpio/gpio.h>
diff --git a/Documentation/devicetree/bindings/sound/rt1015.txt b/Documentation/devicetree/bindings/sound/rt1015.txt
index fcfd02d..e498966 100644
--- a/Documentation/devicetree/bindings/sound/rt1015.txt
+++ b/Documentation/devicetree/bindings/sound/rt1015.txt
@@ -8,10 +8,16 @@
- reg : The I2C address of the device.
+Optional properties:
+
+- realtek,power-up-delay-ms
+ Set a delay time for flush work to be completed,
+ this value is adjustable depending on platform.
Example:
rt1015: codec@28 {
compatible = "realtek,rt1015";
reg = <0x28>;
+ realtek,power-up-delay-ms = <50>;
};
diff --git a/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml b/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml
index 6ebcbc1..b66a07e 100644
--- a/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml
+++ b/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml
@@ -34,6 +34,9 @@
- const: allwinner,sun8i-a23-system-control
- const: allwinner,sun8i-h3-system-control
- items:
+ - const: allwinner,sun8i-v3s-system-control
+ - const: allwinner,sun8i-h3-system-control
+ - items:
- const: allwinner,sun8i-r40-system-control
- const: allwinner,sun4i-a10-system-control
- const: allwinner,sun50i-a64-sram-controller
diff --git a/Documentation/devicetree/bindings/timer/arm,sp804.yaml b/Documentation/devicetree/bindings/timer/arm,sp804.yaml
index e35d305..960e2bd 100644
--- a/Documentation/devicetree/bindings/timer/arm,sp804.yaml
+++ b/Documentation/devicetree/bindings/timer/arm,sp804.yaml
@@ -33,8 +33,8 @@
compatible:
items:
- enum:
- - arm,sp804
- - hisilicon,sp804
+ - arm,sp804
+ - hisilicon,sp804
- const: arm,primecell
interrupts:
@@ -58,11 +58,11 @@
clock is used for all clock inputs.
oneOf:
- items:
- - description: clock for timer 1
- - description: clock for timer 2
- - description: bus clock
+ - description: clock for timer 1
+ - description: clock for timer 2
+ - description: bus clock
- items:
- - description: unified clock for both timers and the bus
+ - description: unified clock for both timers and the bus
clock-names: true
# The original binding did not specify any clock names, and there is no
diff --git a/Documentation/devicetree/bindings/usb/cdns,usb3.yaml b/Documentation/devicetree/bindings/usb/cdns,usb3.yaml
index ac20b98..d6af279 100644
--- a/Documentation/devicetree/bindings/usb/cdns,usb3.yaml
+++ b/Documentation/devicetree/bindings/usb/cdns,usb3.yaml
@@ -44,8 +44,8 @@
enum: [super-speed, high-speed, full-speed]
phys:
- minItems: 1
- maxItems: 2
+ minItems: 1
+ maxItems: 2
phy-names:
minItems: 1
diff --git a/Documentation/devicetree/bindings/usb/ti,hd3ss3220.yaml b/Documentation/devicetree/bindings/usb/ti,hd3ss3220.yaml
index 5fe9e62..52ceb07 100644
--- a/Documentation/devicetree/bindings/usb/ti,hd3ss3220.yaml
+++ b/Documentation/devicetree/bindings/usb/ti,hd3ss3220.yaml
@@ -17,7 +17,7 @@
properties:
compatible:
- const: ti,hd3ss3220
+ const: ti,hd3ss3220
reg:
maxItems: 1
diff --git a/Documentation/devicetree/bindings/w1/fsl-imx-owire.yaml b/Documentation/devicetree/bindings/w1/fsl-imx-owire.yaml
index 1aaf3e7..55adea8 100644
--- a/Documentation/devicetree/bindings/w1/fsl-imx-owire.yaml
+++ b/Documentation/devicetree/bindings/w1/fsl-imx-owire.yaml
@@ -15,10 +15,10 @@
- const: fsl,imx21-owire
- items:
- enum:
- - fsl,imx27-owire
- - fsl,imx50-owire
- - fsl,imx51-owire
- - fsl,imx53-owire
+ - fsl,imx27-owire
+ - fsl,imx50-owire
+ - fsl,imx51-owire
+ - fsl,imx53-owire
- const: fsl,imx21-owire
reg:
diff --git a/Documentation/filesystems/api-summary.rst b/Documentation/filesystems/api-summary.rst
index bbb0c1c..a94f17d 100644
--- a/Documentation/filesystems/api-summary.rst
+++ b/Documentation/filesystems/api-summary.rst
@@ -86,9 +86,6 @@
.. kernel-doc:: fs/dax.c
:export:
-.. kernel-doc:: fs/direct-io.c
- :export:
-
.. kernel-doc:: fs/libfs.c
:export:
diff --git a/Documentation/filesystems/debugfs.rst b/Documentation/filesystems/debugfs.rst
index 728ab57..0f2292e 100644
--- a/Documentation/filesystems/debugfs.rst
+++ b/Documentation/filesystems/debugfs.rst
@@ -199,7 +199,7 @@
There is a helper function to create device related seq_file::
- struct dentry *debugfs_create_devm_seqfile(struct device *dev,
+ void debugfs_create_devm_seqfile(struct device *dev,
const char *name,
struct dentry *parent,
int (*read_fn)(struct seq_file *s,
diff --git a/Documentation/filesystems/ext4/journal.rst b/Documentation/filesystems/ext4/journal.rst
index 805a1e9..849d5b1 100644
--- a/Documentation/filesystems/ext4/journal.rst
+++ b/Documentation/filesystems/ext4/journal.rst
@@ -256,6 +256,10 @@
- s\_padding2
-
* - 0x54
+ - \_\_be32
+ - s\_num\_fc\_blocks
+ - Number of fast commit blocks in the journal.
+ * - 0x58
- \_\_u32
- s\_padding[42]
-
@@ -310,6 +314,8 @@
- This journal uses v3 of the checksum on-disk format. This is the same as
v2, but the journal block tag size is fixed regardless of the size of
block numbers. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3)
+ * - 0x20
+ - Journal has fast commit blocks. (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT)
.. _jbd2_checksum_type:
diff --git a/Documentation/filesystems/ext4/super.rst b/Documentation/filesystems/ext4/super.rst
index 93e55d7..2eb1ab2 100644
--- a/Documentation/filesystems/ext4/super.rst
+++ b/Documentation/filesystems/ext4/super.rst
@@ -596,6 +596,13 @@
- Sparse Super Block, v2. If this flag is set, the SB field s\_backup\_bgs
points to the two block groups that contain backup superblocks
(COMPAT\_SPARSE\_SUPER2).
+ * - 0x400
+ - Fast commits supported. Although fast commits blocks are
+ backward incompatible, fast commit blocks are not always
+ present in the journal. If fast commit blocks are present in
+ the journal, JBD2 incompat feature
+ (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT) gets
+ set (COMPAT\_FAST\_COMMIT).
.. _super_incompat:
diff --git a/Documentation/filesystems/journalling.rst b/Documentation/filesystems/journalling.rst
index 5a5f70b..e18f90f 100644
--- a/Documentation/filesystems/journalling.rst
+++ b/Documentation/filesystems/journalling.rst
@@ -136,10 +136,8 @@
~~~~~~~~~~~~
JBD2 to also allows you to perform file-system specific delta commits known as
-fast commits. In order to use fast commits, you first need to call
-:c:func:`jbd2_fc_init` and tell how many blocks at the end of journal
-area should be reserved for fast commits. Along with that, you will also need
-to set following callbacks that perform correspodning work:
+fast commits. In order to use fast commits, you will need to set following
+callbacks that perform correspodning work:
`journal->j_fc_cleanup_cb`: Cleanup function called after every full commit and
fast commit.
diff --git a/Documentation/firmware-guide/acpi/acpi-lid.rst b/Documentation/firmware-guide/acpi/acpi-lid.rst
index 874ce0e..71b9af1 100644
--- a/Documentation/firmware-guide/acpi/acpi-lid.rst
+++ b/Documentation/firmware-guide/acpi/acpi-lid.rst
@@ -19,9 +19,9 @@
For most platforms, both the _LID method and the lid notifications are
reliable. However, there are exceptions. In order to work with these
-exceptional buggy platforms, special restrictions and expections should be
+exceptional buggy platforms, special restrictions and exceptions should be
taken into account. This document describes the restrictions and the
-expections of the Linux ACPI lid device driver.
+exceptions of the Linux ACPI lid device driver.
Restrictions of the returning value of the _LID control method
@@ -46,7 +46,7 @@
trigger some system power saving operations on Windows. Since it is fully
tested, it is reliable from all AML tables.
-Expections for the userspace users of the ACPI lid device driver
+Exceptions for the userspace users of the ACPI lid device driver
================================================================
The ACPI button driver exports the lid state to the userspace via the
@@ -100,7 +100,7 @@
C. button.lid_init_state=ignore:
When this option is specified, the ACPI button driver never reports the
initial lid state and there is a compensation mechanism implemented to
- ensure that the reliable "closed" notifications can always be delievered
+ ensure that the reliable "closed" notifications can always be delivered
to the userspace by always pairing "closed" input events with complement
"opened" input events. But there is still no guarantee that the "opened"
notifications can be delivered to the userspace when the lid is actually
diff --git a/Documentation/firmware-guide/acpi/gpio-properties.rst b/Documentation/firmware-guide/acpi/gpio-properties.rst
index bb6d74f..59aad61 100644
--- a/Documentation/firmware-guide/acpi/gpio-properties.rst
+++ b/Documentation/firmware-guide/acpi/gpio-properties.rst
@@ -20,9 +20,9 @@
Name (_CRS, ResourceTemplate ()
{
- GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionInputOnly,
+ GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionOutputOnly,
"\\_SB.GPO0", 0, ResourceConsumer) {15}
- GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionInputOnly,
+ GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionOutputOnly,
"\\_SB.GPO0", 0, ResourceConsumer) {27, 31}
})
@@ -49,15 +49,41 @@
pin
Pin in the GpioIo()/GpioInt() resource. Typically this is zero.
active_low
- If 1 the GPIO is marked as active_low.
+ If 1, the GPIO is marked as active_low.
Since ACPI GpioIo() resource does not have a field saying whether it is
active low or high, the "active_low" argument can be used here. Setting
it to 1 marks the GPIO as active low.
+Note, active_low in _DSD does not make sense for GpioInt() resource and
+must be 0. GpioInt() resource has its own means of defining it.
+
In our Bluetooth example the "reset-gpios" refers to the second GpioIo()
resource, second pin in that resource with the GPIO number of 31.
+The GpioIo() resource unfortunately doesn't explicitly provide an initial
+state of the output pin which driver should use during its initialization.
+
+Linux tries to use common sense here and derives the state from the bias
+and polarity settings. The table below shows the expectations:
+
+========= ============= ==============
+Pull Bias Polarity Requested...
+========= ============= ==============
+Implicit x AS IS (assumed firmware configured for us)
+Explicit x (no _DSD) as Pull Bias (Up == High, Down == Low),
+ assuming non-active (Polarity = !Pull Bias)
+Down Low as low, assuming active
+Down High as low, assuming non-active
+Up Low as high, assuming non-active
+Up High as high, assuming active
+========= ============= ==============
+
+That said, for our above example the both GPIOs, since the bias setting
+is explicit and _DSD is present, will be treated as active with a high
+polarity and Linux will configure the pins in this state until a driver
+reprograms them differently.
+
It is possible to leave holes in the array of GPIOs. This is useful in
cases like with SPI host controllers where some chip selects may be
implemented as GPIOs and some as native signals. For example a SPI host
@@ -112,8 +138,8 @@
Package () {
"gpio-line-names",
Package () {
- "SPI0_CS_N", "EXP2_INT", "MUX6_IO", "UART0_RXD", "MUX7_IO",
- "LVL_C_A1", "MUX0_IO", "SPI1_MISO"
+ "SPI0_CS_N", "EXP2_INT", "MUX6_IO", "UART0_RXD",
+ "MUX7_IO", "LVL_C_A1", "MUX0_IO", "SPI1_MISO",
}
}
@@ -137,7 +163,7 @@
mapping between those names and the ACPI GPIO resources corresponding to them.
To do that, the driver needs to define a mapping table as a NULL-terminated
-array of struct acpi_gpio_mapping objects that each contain a name, a pointer
+array of struct acpi_gpio_mapping objects that each contains a name, a pointer
to an array of line data (struct acpi_gpio_params) objects and the size of that
array. Each struct acpi_gpio_params object consists of three fields,
crs_entry_index, line_index, active_low, representing the index of the target
@@ -154,13 +180,14 @@
static const struct acpi_gpio_mapping bluetooth_acpi_gpios[] = {
{ "reset-gpios", &reset_gpio, 1 },
{ "shutdown-gpios", &shutdown_gpio, 1 },
- { },
+ { }
};
Next, the mapping table needs to be passed as the second argument to
-acpi_dev_add_driver_gpios() that will register it with the ACPI device object
-pointed to by its first argument. That should be done in the driver's .probe()
-routine. On removal, the driver should unregister its GPIO mapping table by
+acpi_dev_add_driver_gpios() or its managed analogue that will
+register it with the ACPI device object pointed to by its first
+argument. That should be done in the driver's .probe() routine.
+On removal, the driver should unregister its GPIO mapping table by
calling acpi_dev_remove_driver_gpios() on the ACPI device object where that
table was previously registered.
@@ -191,12 +218,12 @@
but since there is no way to know the mapping between "reset" and
the GpioIo() in _CRS desc will hold ERR_PTR(-ENOENT).
-The driver author can solve this by passing the mapping explictly
-(the recommended way and documented in the above chapter).
+The driver author can solve this by passing the mapping explicitly
+(this is the recommended way and it's documented in the above chapter).
The ACPI GPIO mapping tables should not contaminate drivers that are not
knowing about which exact device they are servicing on. It implies that
-the ACPI GPIO mapping tables are hardly linked to ACPI ID and certain
+the ACPI GPIO mapping tables are hardly linked to an ACPI ID and certain
objects, as listed in the above chapter, of the device in question.
Getting GPIO descriptor
@@ -229,5 +256,5 @@
Be aware that gpiod_get_index() in cases 1 and 2, assuming that there
are two versions of ACPI device description provided and no mapping is
present in the driver, will return different resources. That's why a
-certain driver has to handle them carefully as explained in previous
+certain driver has to handle them carefully as explained in the previous
chapter.
diff --git a/Documentation/firmware-guide/acpi/method-tracing.rst b/Documentation/firmware-guide/acpi/method-tracing.rst
index 0aa7e2c..6ab6c096 100644
--- a/Documentation/firmware-guide/acpi/method-tracing.rst
+++ b/Documentation/firmware-guide/acpi/method-tracing.rst
@@ -98,7 +98,7 @@
[ 0.188903] exdebug-0398 ex_trace_point : Method End [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution.
Developers can utilize these special log entries to track the AML
-interpretion, thus can aid issue debugging and performance tuning. Note
+interpretation, thus can aid issue debugging and performance tuning. Note
that, as the "AML tracer" logs are implemented via ACPI_DEBUG_PRINT()
macro, CONFIG_ACPI_DEBUG is also required to be enabled for enabling
"AML tracer" logs.
diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index 1f9ea82..2062a60 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -83,10 +83,6 @@
===================
.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
- :doc: AMDGPU XGMI Support
-
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
- :internal:
AMDGPU RAS Support
==================
@@ -124,9 +120,6 @@
.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
:doc: AMDGPU RAS sysfs gpu_vram_bad_pages Interface
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
- :internal:
-
Sample Code
-----------
Sample code for testing error injection can be found here:
diff --git a/Documentation/hwmon/adm1266.rst b/Documentation/hwmon/adm1266.rst
index 9257f8a..2b87701 100644
--- a/Documentation/hwmon/adm1266.rst
+++ b/Documentation/hwmon/adm1266.rst
@@ -20,7 +20,7 @@
integrated 12 bit SAR ADC, accessed using a PMBus interface.
The driver is a client driver to the core PMBus driver. Please see
-Documentation/hwmon/pmbus for details on PMBus client drivers.
+Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
Sysfs entries
diff --git a/Documentation/hwmon/index.rst b/Documentation/hwmon/index.rst
index e6b91ab..b797db7 100644
--- a/Documentation/hwmon/index.rst
+++ b/Documentation/hwmon/index.rst
@@ -132,6 +132,7 @@
mcp3021
menf21bmc
mlxreg-fan
+ mp2975
nct6683
nct6775
nct7802
diff --git a/Documentation/hwmon/mp2975.rst b/Documentation/hwmon/mp2975.rst
index 5b0609c..81d816b 100644
--- a/Documentation/hwmon/mp2975.rst
+++ b/Documentation/hwmon/mp2975.rst
@@ -20,6 +20,7 @@
vendor dual-loop, digital, multi-phase controller MP2975.
This device:
+
- Supports up to two power rail.
- Provides 8 pulse-width modulations (PWMs), and can be configured up
to 8-phase operation for rail 1 and up to 4-phase operation for rail
@@ -32,10 +33,12 @@
10-mV DAC, IMVP9 mode with 5-mV DAC.
Device supports:
+
- SVID interface.
- AVSBus interface.
Device complaint with:
+
- PMBus rev 1.3 interface.
Device supports direct format for reading output current, output voltage,
@@ -45,11 +48,14 @@
The below VID modes are supported: VR12, VR13, IMVP9.
The driver provides the next attributes for the current:
+
- for current in: input, maximum alarm;
- for current out input, maximum alarm and highest values;
- for phase current: input and label.
-attributes.
+ attributes.
+
The driver exports the following attributes via the 'sysfs' files, where
+
- 'n' is number of telemetry pages (from 1 to 2);
- 'k' is number of configured phases (from 1 to 8);
- indexes 1, 1*n for "iin";
@@ -65,11 +71,14 @@
**curr[1-{2n+k}]_label**
The driver provides the next attributes for the voltage:
+
- for voltage in: input, high critical threshold, high critical alarm, all only
from page 0;
- for voltage out: input, low and high critical thresholds, low and high
critical alarms, from pages 0 and 1;
+
The driver exports the following attributes via the 'sysfs' files, where
+
- 'n' is number of telemetry pages (from 1 to 2);
- indexes 1 for "iin";
- indexes n+1, n+2 for "vout";
@@ -87,9 +96,12 @@
**in[2-{n+1}1_lcrit_alarm**
The driver provides the next attributes for the power:
+
- for power in alarm and input.
- for power out: highest and input.
+
The driver exports the following attributes via the 'sysfs' files, where
+
- 'n' is number of telemetry pages (from 1 to 2);
- indexes 1 for "pin";
- indexes n+1, n+2 for "pout";
diff --git a/Documentation/leds/index.rst b/Documentation/leds/index.rst
index bc70c6aa..e5d63b9 100644
--- a/Documentation/leds/index.rst
+++ b/Documentation/leds/index.rst
@@ -17,6 +17,7 @@
uleds
leds-blinkm
+ leds-el15203000
leds-lm3556
leds-lp3944
leds-lp5521
@@ -24,3 +25,4 @@
leds-lp5562
leds-lp55xx
leds-mlxcpld
+ leds-sc27xx
diff --git a/Documentation/leds/leds-el15203000.rst b/Documentation/leds/leds-el15203000.rst
new file mode 100644
index 0000000..12c23d7
--- /dev/null
+++ b/Documentation/leds/leds-el15203000.rst
@@ -0,0 +1,140 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==================================
+Kernel driver for Crane EL15203000
+==================================
+
+/sys/class/leds/<led>/hw_pattern
+--------------------------------
+
+Specify a hardware pattern for the EL15203000 LED.
+
+The LEDs board supports only predefined patterns by firmware
+for specific LEDs.
+
+Breathing mode for Screen frame light tube::
+
+ "0 4000 1 4000"
+
+ ^
+ |
+ Max-| ---
+ | / \
+ | / \
+ | / \ /
+ | / \ /
+ Min-|- ---
+ |
+ 0------4------8--> time (sec)
+
+Cascade mode for Pipe LED::
+
+ "1 800 2 800 4 800 8 800 16 800"
+
+ ^
+ |
+ 0 On -|----+ +----+ +---
+ | | | | |
+ Off-| +-------------------+ +-------------------+
+ |
+ 1 On -| +----+ +----+
+ | | | | |
+ Off |----+ +-------------------+ +------------------
+ |
+ 2 On -| +----+ +----+
+ | | | | |
+ Off-|---------+ +-------------------+ +-------------
+ |
+ 3 On -| +----+ +----+
+ | | | | |
+ Off-|--------------+ +-------------------+ +--------
+ |
+ 4 On -| +----+ +----+
+ | | | | |
+ Off-|-------------------+ +-------------------+ +---
+ |
+ 0---0.8--1.6--2.4--3.2---4---4.8--5.6--6.4--7.2---8--> time (sec)
+
+Inverted cascade mode for Pipe LED::
+
+ "30 800 29 800 27 800 23 800 15 800"
+
+ ^
+ |
+ 0 On -| +-------------------+ +-------------------+
+ | | | | |
+ Off-|----+ +----+ +---
+ |
+ 1 On -|----+ +-------------------+ +------------------
+ | | | | |
+ Off | +----+ +----+
+ |
+ 2 On -|---------+ +-------------------+ +-------------
+ | | | | |
+ Off-| +----+ +----+
+ |
+ 3 On -|--------------+ +-------------------+ +--------
+ | | | | |
+ Off-| +----+ +----+
+ |
+ 4 On -|-------------------+ +-------------------+ +---
+ | | | | |
+ Off-| +----+ +----+
+ |
+ 0---0.8--1.6--2.4--3.2---4---4.8--5.6--6.4--7.2---8--> time (sec)
+
+Bounce mode for Pipe LED::
+
+ "1 800 2 800 4 800 8 800 16 800 16 800 8 800 4 800 2 800 1 800"
+
+ ^
+ |
+ 0 On -|----+ +--------
+ | | |
+ Off-| +---------------------------------------+
+ |
+ 1 On -| +----+ +----+
+ | | | | |
+ Off |----+ +-----------------------------+ +--------
+ |
+ 2 On -| +----+ +----+
+ | | | | |
+ Off-|---------+ +-------------------+ +-------------
+ |
+ 3 On -| +----+ +----+
+ | | | | |
+ Off-|--------------+ +---------+ +------------------
+ |
+ 4 On -| +---------+
+ | | |
+ Off-|-------------------+ +-----------------------
+ |
+ 0---0.8--1.6--2.4--3.2---4---4.8--5.6--6.4--7.2---8--> time (sec)
+
+Inverted bounce mode for Pipe LED::
+
+ "30 800 29 800 27 800 23 800 15 800 15 800 23 800 27 800 29 800 30 800"
+
+ ^
+ |
+ 0 On -| +---------------------------------------+
+ | | |
+ Off-|----+ +--------
+ |
+ 1 On -|----+ +-----------------------------+ +--------
+ | | | | |
+ Off | +----+ +----+
+ |
+ 2 On -|---------+ +-------------------+ +-------------
+ | | | | |
+ Off-| +----+ +----+
+ |
+ 3 On -|--------------+ +---------+ +------------------
+ | | | | |
+ Off-| +----+ +----+
+ |
+ 4 On -|-------------------+ +-----------------------
+ | | |
+ Off-| +---------+
+ |
+ 0---0.8--1.6--2.4--3.2---4---4.8--5.6--6.4--7.2---8--> time (sec)
diff --git a/Documentation/leds/leds-sc27xx.rst b/Documentation/leds/leds-sc27xx.rst
new file mode 100644
index 0000000..6bdf6ba
--- /dev/null
+++ b/Documentation/leds/leds-sc27xx.rst
@@ -0,0 +1,27 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===================================
+Kernel driver for Spreadtrum SC27XX
+===================================
+
+/sys/class/leds/<led>/hw_pattern
+--------------------------------
+
+Specify a hardware pattern for the SC27XX LED. For the SC27XX
+LED controller, it only supports 4 stages to make a single
+hardware pattern, which is used to configure the rise time,
+high time, fall time and low time for the breathing mode.
+
+For the breathing mode, the SC27XX LED only expects one brightness
+for the high stage. To be compatible with the hardware pattern
+format, we should set brightness as 0 for rise stage, fall
+stage and low stage.
+
+- Min stage duration: 125 ms
+- Max stage duration: 31875 ms
+
+Since the stage duration step is 125 ms, the duration should be
+a multiplier of 125, like 125ms, 250ms, 375ms, 500ms ... 31875ms.
+
+Thus the format of the hardware pattern values should be:
+"0 rise_duration brightness high_duration 0 fall_duration 0 low_duration".
diff --git a/Documentation/locking/lockdep-design.rst b/Documentation/locking/lockdep-design.rst
index cec03bd1..9f3cfca 100644
--- a/Documentation/locking/lockdep-design.rst
+++ b/Documentation/locking/lockdep-design.rst
@@ -42,6 +42,7 @@
(4 usages * n STATEs + 1) categories:
where the 4 usages can be:
+
- 'ever held in STATE context'
- 'ever held as readlock in STATE context'
- 'ever held with STATE enabled'
@@ -49,10 +50,12 @@
where the n STATEs are coded in kernel/locking/lockdep_states.h and as of
now they include:
+
- hardirq
- softirq
where the last 1 category is:
+
- 'ever used' [ == !unused ]
When locking rules are violated, these usage bits are presented in the
@@ -96,9 +99,9 @@
+--------------+-------------+--------------+
| | irq enabled | irq disabled |
+--------------+-------------+--------------+
- | ever in irq | ? | - |
+ | ever in irq | '?' | '-' |
+--------------+-------------+--------------+
- | never in irq | + | . |
+ | never in irq | '+' | '.' |
+--------------+-------------+--------------+
The character '-' suggests irq is disabled because if otherwise the
@@ -216,7 +219,7 @@
BD_MUTEX_PARTITION
};
-mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_PARTITION);
+ mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_PARTITION);
In this case the locking is done on a bdev object that is known to be a
partition.
@@ -334,7 +337,7 @@
----------------
The validator tracks a maximum of MAX_LOCKDEP_KEYS number of lock classes.
-Exceeding this number will trigger the following lockdep warning:
+Exceeding this number will trigger the following lockdep warning::
(DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS))
@@ -420,7 +423,8 @@
The difference between recursive readers and non-recursive readers is because:
recursive readers get blocked only by a write lock *holder*, while non-recursive
-readers could get blocked by a write lock *waiter*. Considering the follow example:
+readers could get blocked by a write lock *waiter*. Considering the follow
+example::
TASK A: TASK B:
@@ -448,20 +452,22 @@
Block condition matrix, Y means the row blocks the column, and N means otherwise.
- | E | r | R |
+---+---+---+---+
- E | Y | Y | Y |
+ | | E | r | R |
+---+---+---+---+
- r | Y | Y | N |
+ | E | Y | Y | Y |
+---+---+---+---+
- R | Y | Y | N |
+ | r | Y | Y | N |
+ +---+---+---+---+
+ | R | Y | Y | N |
+ +---+---+---+---+
(W: writers, r: non-recursive readers, R: recursive readers)
acquired recursively. Unlike non-recursive read locks, recursive read locks
only get blocked by current write lock *holders* other than write lock
-*waiters*, for example:
+*waiters*, for example::
TASK A: TASK B:
@@ -491,7 +497,7 @@
even true for two non-recursive read locks). A non-recursive lock can block the
corresponding recursive lock, and vice versa.
-A deadlock case with recursive locks involved is as follow:
+A deadlock case with recursive locks involved is as follow::
TASK A: TASK B:
@@ -510,7 +516,7 @@
dependencies, but we can show that 4 types of lock dependencies are enough for
deadlock detection.
-For each lock dependency:
+For each lock dependency::
L1 -> L2
@@ -525,20 +531,25 @@
With the above combination for simplification, there are 4 types of dependency edges
in the lockdep graph:
-1) -(ER)->: exclusive writer to recursive reader dependency, "X -(ER)-> Y" means
+1) -(ER)->:
+ exclusive writer to recursive reader dependency, "X -(ER)-> Y" means
X -> Y and X is a writer and Y is a recursive reader.
-2) -(EN)->: exclusive writer to non-recursive locker dependency, "X -(EN)-> Y" means
+2) -(EN)->:
+ exclusive writer to non-recursive locker dependency, "X -(EN)-> Y" means
X -> Y and X is a writer and Y is either a writer or non-recursive reader.
-3) -(SR)->: shared reader to recursive reader dependency, "X -(SR)-> Y" means
+3) -(SR)->:
+ shared reader to recursive reader dependency, "X -(SR)-> Y" means
X -> Y and X is a reader (recursive or not) and Y is a recursive reader.
-4) -(SN)->: shared reader to non-recursive locker dependency, "X -(SN)-> Y" means
+4) -(SN)->:
+ shared reader to non-recursive locker dependency, "X -(SN)-> Y" means
X -> Y and X is a reader (recursive or not) and Y is either a writer or
non-recursive reader.
-Note that given two locks, they may have multiple dependencies between them, for example:
+Note that given two locks, they may have multiple dependencies between them,
+for example::
TASK A:
@@ -592,11 +603,11 @@
Proof for sufficiency (Lemma 1):
-Let's say we have a strong circle:
+Let's say we have a strong circle::
L1 -> L2 ... -> Ln -> L1
-, which means we have dependencies:
+, which means we have dependencies::
L1 -> L2
L2 -> L3
@@ -633,7 +644,7 @@
for a lock held by P1. Let's name the lock Px is waiting as Lx, so since P1 is waiting
for L1 and holding Ln, so we will have Ln -> L1 in the dependency graph. Similarly,
we have L1 -> L2, L2 -> L3, ..., Ln-1 -> Ln in the dependency graph, which means we
-have a circle:
+have a circle::
Ln -> L1 -> L2 -> ... -> Ln
diff --git a/Documentation/misc-devices/index.rst b/Documentation/misc-devices/index.rst
index 46072ce..64420b331 100644
--- a/Documentation/misc-devices/index.rst
+++ b/Documentation/misc-devices/index.rst
@@ -24,7 +24,6 @@
isl29003
lis3lv02d
max6875
- mic/index
pci-endpoint-test
spear-pcie-gadget
uacce
diff --git a/Documentation/misc-devices/mic/index.rst b/Documentation/misc-devices/mic/index.rst
deleted file mode 100644
index 3a8d063..0000000
--- a/Documentation/misc-devices/mic/index.rst
+++ /dev/null
@@ -1,16 +0,0 @@
-=============================================
-Intel Many Integrated Core (MIC) architecture
-=============================================
-
-.. toctree::
- :maxdepth: 1
-
- mic_overview
- scif_overview
-
-.. only:: subproject and html
-
- Indices
- =======
-
- * :ref:`genindex`
diff --git a/Documentation/misc-devices/mic/mic_overview.rst b/Documentation/misc-devices/mic/mic_overview.rst
deleted file mode 100644
index 17d956b..0000000
--- a/Documentation/misc-devices/mic/mic_overview.rst
+++ /dev/null
@@ -1,85 +0,0 @@
-======================================================
-Intel Many Integrated Core (MIC) architecture overview
-======================================================
-
-An Intel MIC X100 device is a PCIe form factor add-in coprocessor
-card based on the Intel Many Integrated Core (MIC) architecture
-that runs a Linux OS. It is a PCIe endpoint in a platform and therefore
-implements the three required standard address spaces i.e. configuration,
-memory and I/O. The host OS loads a device driver as is typical for
-PCIe devices. The card itself runs a bootstrap after reset that
-transfers control to the card OS downloaded from the host driver. The
-host driver supports OSPM suspend and resume operations. It shuts down
-the card during suspend and reboots the card OS during resume.
-The card OS as shipped by Intel is a Linux kernel with modifications
-for the X100 devices.
-
-Since it is a PCIe card, it does not have the ability to host hardware
-devices for networking, storage and console. We provide these devices
-on X100 coprocessors thus enabling a self-bootable equivalent
-environment for applications. A key benefit of our solution is that it
-leverages the standard virtio framework for network, disk and console
-devices, though in our case the virtio framework is used across a PCIe
-bus. A Virtio Over PCIe (VOP) driver allows creating user space
-backends or devices on the host which are used to probe virtio drivers
-for these devices on the MIC card. The existing VRINGH infrastructure
-in the kernel is used to access virtio rings from the host. The card
-VOP driver allows card virtio drivers to communicate with their user
-space backends on the host via a device page. Ring 3 apps on the host
-can add, remove and configure virtio devices. A thin MIC specific
-virtio_config_ops is implemented which is borrowed heavily from
-previous similar implementations in lguest and s390.
-
-MIC PCIe card has a dma controller with 8 channels. These channels are
-shared between the host s/w and the card s/w. 0 to 3 are used by host
-and 4 to 7 by card. As the dma device doesn't show up as PCIe device,
-a virtual bus called mic bus is created and virtual dma devices are
-created on it by the host/card drivers. On host the channels are private
-and used only by the host driver to transfer data for the virtio devices.
-
-The Symmetric Communication Interface (SCIF (pronounced as skiff)) is a
-low level communications API across PCIe currently implemented for MIC.
-More details are available at scif_overview.txt.
-
-The Coprocessor State Management (COSM) driver on the host allows for
-boot, shutdown and reset of Intel MIC devices. It communicates with a COSM
-"client" driver on the MIC cards over SCIF to perform these functions.
-
-Here is a block diagram of the various components described above. The
-virtio backends are situated on the host rather than the card given better
-single threaded performance for the host compared to MIC, the ability of
-the host to initiate DMA's to/from the card using the MIC DMA engine and
-the fact that the virtio block storage backend can only be on the host::
-
- +----------+ | +----------+
- | Card OS | | | Host OS |
- +----------+ | +----------+
- |
- +-------+ +--------+ +------+ | +---------+ +--------+ +--------+
- | Virtio| |Virtio | |Virtio| | |Virtio | |Virtio | |Virtio |
- | Net | |Console | |Block | | |Net | |Console | |Block |
- | Driver| |Driver | |Driver| | |backend | |backend | |backend |
- +---+---+ +---+----+ +--+---+ | +---------+ +----+---+ +--------+
- | | | | | | |
- | | | |User | | |
- | | | |------|------------|--+------|-------
- +---------+---------+ |Kernel |
- | | |
- +---------+ +---+----+ +------+ | +------+ +------+ +--+---+ +-------+
- |MIC DMA | | VOP | | SCIF | | | SCIF | | COSM | | VOP | |MIC DMA|
- +---+-----+ +---+----+ +--+---+ | +--+---+ +--+---+ +------+ +----+--+
- | | | | | | |
- +---+-----+ +---+----+ +--+---+ | +--+---+ +--+---+ +------+ +----+--+
- |MIC | | VOP | |SCIF | | |SCIF | | COSM | | VOP | | MIC |
- |HW Bus | | HW Bus| |HW Bus| | |HW Bus| | Bus | |HW Bus| |HW Bus |
- +---------+ +--------+ +--+---+ | +--+---+ +------+ +------+ +-------+
- | | | | | | |
- | +-----------+--+ | | | +---------------+ |
- | |Intel MIC | | | | |Intel MIC | |
- | |Card Driver | | | | |Host Driver | |
- +---+--------------+------+ | +----+---------------+-----+
- | | |
- +-------------------------------------------------------------+
- | |
- | PCIe Bus |
- +-------------------------------------------------------------+
diff --git a/Documentation/misc-devices/mic/scif_overview.rst b/Documentation/misc-devices/mic/scif_overview.rst
deleted file mode 100644
index 4c8ad9e..0000000
--- a/Documentation/misc-devices/mic/scif_overview.rst
+++ /dev/null
@@ -1,108 +0,0 @@
-========================================
-Symmetric Communication Interface (SCIF)
-========================================
-
-The Symmetric Communication Interface (SCIF (pronounced as skiff)) is a low
-level communications API across PCIe currently implemented for MIC. Currently
-SCIF provides inter-node communication within a single host platform, where a
-node is a MIC Coprocessor or Xeon based host. SCIF abstracts the details of
-communicating over the PCIe bus while providing an API that is symmetric
-across all the nodes in the PCIe network. An important design objective for SCIF
-is to deliver the maximum possible performance given the communication
-abilities of the hardware. SCIF has been used to implement an offload compiler
-runtime and OFED support for MPI implementations for MIC coprocessors.
-
-SCIF API Components
-===================
-
-The SCIF API has the following parts:
-
-1. Connection establishment using a client server model
-2. Byte stream messaging intended for short messages
-3. Node enumeration to determine online nodes
-4. Poll semantics for detection of incoming connections and messages
-5. Memory registration to pin down pages
-6. Remote memory mapping for low latency CPU accesses via mmap
-7. Remote DMA (RDMA) for high bandwidth DMA transfers
-8. Fence APIs for RDMA synchronization
-
-SCIF exposes the notion of a connection which can be used by peer processes on
-nodes in a SCIF PCIe "network" to share memory "windows" and to communicate. A
-process in a SCIF node initiates a SCIF connection to a peer process on a
-different node via a SCIF "endpoint". SCIF endpoints support messaging APIs
-which are similar to connection oriented socket APIs. Connected SCIF endpoints
-can also register local memory which is followed by data transfer using either
-DMA, CPU copies or remote memory mapping via mmap. SCIF supports both user and
-kernel mode clients which are functionally equivalent.
-
-SCIF Performance for MIC
-========================
-
-DMA bandwidth comparison between the TCP (over ethernet over PCIe) stack versus
-SCIF shows the performance advantages of SCIF for HPC applications and
-runtimes::
-
- Comparison of TCP and SCIF based BW
-
- Throughput (GB/sec)
- 8 + PCIe Bandwidth ******
- + TCP ######
- 7 + ************************************** SCIF %%%%%%
- | %%%%%%%%%%%%%%%%%%%
- 6 + %%%%
- | %%
- | %%%
- 5 + %%
- | %%
- 4 + %%
- | %%
- 3 + %%
- | %
- 2 + %%
- | %%
- | %
- 1 +
- + ######################################
- 0 +++---+++--+--+-+--+--+-++-+--+-++-+--+-++-+-
- 1 10 100 1000 10000 100000
- Transfer Size (KBytes)
-
-SCIF allows memory sharing via mmap(..) between processes on different PCIe
-nodes and thus provides bare-metal PCIe latency. The round trip SCIF mmap
-latency from the host to an x100 MIC for an 8 byte message is 0.44 usecs.
-
-SCIF has a user space library which is a thin IOCTL wrapper providing a user
-space API similar to the kernel API in scif.h. The SCIF user space library
-is distributed @ https://software.intel.com/en-us/mic-developer
-
-Here is some pseudo code for an example of how two applications on two PCIe
-nodes would typically use the SCIF API::
-
- Process A (on node A) Process B (on node B)
-
- /* get online node information */
- scif_get_node_ids(..) scif_get_node_ids(..)
- scif_open(..) scif_open(..)
- scif_bind(..) scif_bind(..)
- scif_listen(..)
- scif_accept(..) scif_connect(..)
- /* SCIF connection established */
-
- /* Send and receive short messages */
- scif_send(..)/scif_recv(..) scif_send(..)/scif_recv(..)
-
- /* Register memory */
- scif_register(..) scif_register(..)
-
- /* RDMA */
- scif_readfrom(..)/scif_writeto(..) scif_readfrom(..)/scif_writeto(..)
-
- /* Fence DMAs */
- scif_fence_signal(..) scif_fence_signal(..)
-
- mmap(..) mmap(..)
-
- /* Access remote registered memory */
-
- /* Close the endpoints */
- scif_close(..) scif_close(..)
diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst
index b165181..a432dc4 100644
--- a/Documentation/networking/devlink/ice.rst
+++ b/Documentation/networking/devlink/ice.rst
@@ -70,6 +70,7 @@
that both the name (as reported by ``fw.app.name``) and version are
required to uniquely identify the package.
* - ``fw.app.bundle_id``
+ - running
- 0xc0000001
- Unique identifier for the DDP package loaded in the device. Also
referred to as the DDP Track ID. Can be used to uniquely identify
diff --git a/Documentation/networking/j1939.rst b/Documentation/networking/j1939.rst
index f5be243..0a4b73b 100644
--- a/Documentation/networking/j1939.rst
+++ b/Documentation/networking/j1939.rst
@@ -10,9 +10,9 @@
SAE J1939 defines a higher layer protocol on CAN. It implements a more
sophisticated addressing scheme and extends the maximum packet size above 8
bytes. Several derived specifications exist, which differ from the original
-J1939 on the application level, like MilCAN A, NMEA2000 and especially
+J1939 on the application level, like MilCAN A, NMEA2000, and especially
ISO-11783 (ISOBUS). This last one specifies the so-called ETP (Extended
-Transport Protocol) which is has been included in this implementation. This
+Transport Protocol), which has been included in this implementation. This
results in a maximum packet size of ((2 ^ 24) - 1) * 7 bytes == 111 MiB.
Specifications used
@@ -32,15 +32,15 @@
addressing and transport methods used by J1939.
* **Addressing:** when a process on an ECU communicates via J1939, it should
- not necessarily know its source address. Although at least one process per
+ not necessarily know its source address. Although, at least one process per
ECU should know the source address. Other processes should be able to reuse
that address. This way, address parameters for different processes
cooperating for the same ECU, are not duplicated. This way of working is
- closely related to the UNIX concept where programs do just one thing, and do
+ closely related to the UNIX concept, where programs do just one thing and do
it well.
* **Dynamic addressing:** Address Claiming in J1939 is time critical.
- Furthermore data transport should be handled properly during the address
+ Furthermore, data transport should be handled properly during the address
negotiation. Putting this functionality in the kernel eliminates it as a
requirement for _every_ user space process that communicates via J1939. This
results in a consistent J1939 bus with proper addressing.
@@ -58,7 +58,7 @@
The J1939 sockets operate on CAN network devices (see SocketCAN). Any J1939
user space library operating on CAN raw sockets will still operate properly.
-Since such library does not communicate with the in-kernel implementation, care
+Since such a library does not communicate with the in-kernel implementation, care
must be taken that these two do not interfere. In practice, this means they
cannot share ECU addresses. A single ECU (or virtual ECU) address is used by
the library exclusively, or by the in-kernel system exclusively.
@@ -77,13 +77,13 @@
8 bits : PS (PDU Specific)
In J1939-21 distinction is made between PDU1 format (where PF < 240) and PDU2
-format (where PF >= 240). Furthermore, when using PDU2 format, the PS-field
+format (where PF >= 240). Furthermore, when using the PDU2 format, the PS-field
contains a so-called Group Extension, which is part of the PGN. When using PDU2
format, the Group Extension is set in the PS-field.
On the other hand, when using PDU1 format, the PS-field contains a so-called
Destination Address, which is _not_ part of the PGN. When communicating a PGN
-from user space to kernel (or visa versa) and PDU2 format is used, the PS-field
+from user space to kernel (or vice versa) and PDU2 format is used, the PS-field
of the PGN shall be set to zero. The Destination Address shall be set
elsewhere.
@@ -96,15 +96,15 @@
Both static and dynamic addressing methods can be used.
-For static addresses, no extra checks are made by the kernel, and provided
+For static addresses, no extra checks are made by the kernel and provided
addresses are considered right. This responsibility is for the OEM or system
integrator.
For dynamic addressing, so-called Address Claiming, extra support is foreseen
-in the kernel. In J1939 any ECU is known by it's 64-bit NAME. At the moment of
+in the kernel. In J1939 any ECU is known by its 64-bit NAME. At the moment of
a successful address claim, the kernel keeps track of both NAME and source
address being claimed. This serves as a base for filter schemes. By default,
-packets with a destination that is not locally, will be rejected.
+packets with a destination that is not locally will be rejected.
Mixed mode packets (from a static to a dynamic address or vice versa) are
allowed. The BSD sockets define separate API calls for getting/setting the
@@ -131,31 +131,31 @@
---------
On CAN, you first need to open a socket for communicating over a CAN network.
-To use J1939, #include <linux/can/j1939.h>. From there, <linux/can.h> will be
+To use J1939, ``#include <linux/can/j1939.h>``. From there, ``<linux/can.h>`` will be
included too. To open a socket, use:
.. code-block:: C
s = socket(PF_CAN, SOCK_DGRAM, CAN_J1939);
-J1939 does use SOCK_DGRAM sockets. In the J1939 specification, connections are
+J1939 does use ``SOCK_DGRAM`` sockets. In the J1939 specification, connections are
mentioned in the context of transport protocol sessions. These still deliver
-packets to the other end (using several CAN packets). SOCK_STREAM is not
+packets to the other end (using several CAN packets). ``SOCK_STREAM`` is not
supported.
-After the successful creation of the socket, you would normally use the bind(2)
-and/or connect(2) system call to bind the socket to a CAN interface. After
-binding and/or connecting the socket, you can read(2) and write(2) from/to the
-socket or use send(2), sendto(2), sendmsg(2) and the recv*() counterpart
+After the successful creation of the socket, you would normally use the ``bind(2)``
+and/or ``connect(2)`` system call to bind the socket to a CAN interface. After
+binding and/or connecting the socket, you can ``read(2)`` and ``write(2)`` from/to the
+socket or use ``send(2)``, ``sendto(2)``, ``sendmsg(2)`` and the ``recv*()`` counterpart
operations on the socket as usual. There are also J1939 specific socket options
described below.
-In order to send data, a bind(2) must have been successful. bind(2) assigns a
+In order to send data, a ``bind(2)`` must have been successful. ``bind(2)`` assigns a
local address to a socket.
-Different from CAN is that the payload data is just the data that get send,
-without it's header info. The header info is derived from the sockaddr supplied
-to bind(2), connect(2), sendto(2) and recvfrom(2). A write(2) with size 4 will
+Different from CAN is that the payload data is just the data that get sends,
+without its header info. The header info is derived from the sockaddr supplied
+to ``bind(2)``, ``connect(2)``, ``sendto(2)`` and ``recvfrom(2)``. A ``write(2)`` with size 4 will
result in a packet with 4 bytes.
The sockaddr structure has extensions for use with J1939 as specified below:
@@ -180,47 +180,47 @@
} can_addr;
}
-can_family & can_ifindex serve the same purpose as for other SocketCAN sockets.
+``can_family`` & ``can_ifindex`` serve the same purpose as for other SocketCAN sockets.
-can_addr.j1939.pgn specifies the PGN (max 0x3ffff). Individual bits are
+``can_addr.j1939.pgn`` specifies the PGN (max 0x3ffff). Individual bits are
specified above.
-can_addr.j1939.name contains the 64-bit J1939 NAME.
+``can_addr.j1939.name`` contains the 64-bit J1939 NAME.
-can_addr.j1939.addr contains the address.
+``can_addr.j1939.addr`` contains the address.
-The bind(2) system call assigns the local address, i.e. the source address when
-sending packages. If a PGN during bind(2) is set, it's used as a RX filter.
-I.e. only packets with a matching PGN are received. If an ADDR or NAME is set
+The ``bind(2)`` system call assigns the local address, i.e. the source address when
+sending packages. If a PGN during ``bind(2)`` is set, it's used as a RX filter.
+I.e. only packets with a matching PGN are received. If an ADDR or NAME is set
it is used as a receive filter, too. It will match the destination NAME or ADDR
of the incoming packet. The NAME filter will work only if appropriate Address
Claiming for this name was done on the CAN bus and registered/cached by the
kernel.
-On the other hand connect(2) assigns the remote address, i.e. the destination
-address. The PGN from connect(2) is used as the default PGN when sending
+On the other hand ``connect(2)`` assigns the remote address, i.e. the destination
+address. The PGN from ``connect(2)`` is used as the default PGN when sending
packets. If ADDR or NAME is set it will be used as the default destination ADDR
-or NAME. Further a set ADDR or NAME during connect(2) is used as a receive
+or NAME. Further a set ADDR or NAME during ``connect(2)`` is used as a receive
filter. It will match the source NAME or ADDR of the incoming packet.
-Both write(2) and send(2) will send a packet with local address from bind(2) and
-the remote address from connect(2). Use sendto(2) to overwrite the destination
+Both ``write(2)`` and ``send(2)`` will send a packet with local address from ``bind(2)`` and the
+remote address from ``connect(2)``. Use ``sendto(2)`` to overwrite the destination
address.
-If can_addr.j1939.name is set (!= 0) the NAME is looked up by the kernel and
-the corresponding ADDR is used. If can_addr.j1939.name is not set (== 0),
-can_addr.j1939.addr is used.
+If ``can_addr.j1939.name`` is set (!= 0) the NAME is looked up by the kernel and
+the corresponding ADDR is used. If ``can_addr.j1939.name`` is not set (== 0),
+``can_addr.j1939.addr`` is used.
When creating a socket, reasonable defaults are set. Some options can be
-modified with setsockopt(2) & getsockopt(2).
+modified with ``setsockopt(2)`` & ``getsockopt(2)``.
RX path related options:
-- SO_J1939_FILTER - configure array of filters
-- SO_J1939_PROMISC - disable filters set by bind(2) and connect(2)
+- ``SO_J1939_FILTER`` - configure array of filters
+- ``SO_J1939_PROMISC`` - disable filters set by ``bind(2)`` and ``connect(2)``
By default no broadcast packets can be send or received. To enable sending or
-receiving broadcast packets use the socket option SO_BROADCAST:
+receiving broadcast packets use the socket option ``SO_BROADCAST``:
.. code-block:: C
@@ -261,26 +261,26 @@
+---------------------------+
TX path related options:
-SO_J1939_SEND_PRIO - change default send priority for the socket
+``SO_J1939_SEND_PRIO`` - change default send priority for the socket
Message Flags during send() and Related System Calls
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-send(2), sendto(2) and sendmsg(2) take a 'flags' argument. Currently
+``send(2)``, ``sendto(2)`` and ``sendmsg(2)`` take a 'flags' argument. Currently
supported flags are:
-* MSG_DONTWAIT, i.e. non-blocking operation.
+* ``MSG_DONTWAIT``, i.e. non-blocking operation.
recvmsg(2)
^^^^^^^^^^
-In most cases recvmsg(2) is needed if you want to extract more information than
-recvfrom(2) can provide. For example package priority and timestamp. The
+In most cases ``recvmsg(2)`` is needed if you want to extract more information than
+``recvfrom(2)`` can provide. For example package priority and timestamp. The
Destination Address, name and packet priority (if applicable) are attached to
-the msghdr in the recvmsg(2) call. They can be extracted using cmsg(3) macros,
-with cmsg_level == SOL_J1939 && cmsg_type == SCM_J1939_DEST_ADDR,
-SCM_J1939_DEST_NAME or SCM_J1939_PRIO. The returned data is a uint8_t for
-priority and dst_addr, and uint64_t for dst_name.
+the msghdr in the ``recvmsg(2)`` call. They can be extracted using ``cmsg(3)`` macros,
+with ``cmsg_level == SOL_J1939 && cmsg_type == SCM_J1939_DEST_ADDR``,
+``SCM_J1939_DEST_NAME`` or ``SCM_J1939_PRIO``. The returned data is a ``uint8_t`` for
+``priority`` and ``dst_addr``, and ``uint64_t`` for ``dst_name``.
.. code-block:: C
@@ -305,12 +305,12 @@
Distinction has to be made between using the claimed address and doing an
address claim. To use an already claimed address, one has to fill in the
-j1939.name member and provide it to bind(2). If the name had claimed an address
+``j1939.name`` member and provide it to ``bind(2)``. If the name had claimed an address
earlier, all further messages being sent will use that address. And the
-j1939.addr member will be ignored.
+``j1939.addr`` member will be ignored.
An exception on this is PGN 0x0ee00. This is the "Address Claim/Cannot Claim
-Address" message and the kernel will use the j1939.addr member for that PGN if
+Address" message and the kernel will use the ``j1939.addr`` member for that PGN if
necessary.
To claim an address following code example can be used:
@@ -371,12 +371,12 @@
If another ECU claims the address, the kernel will mark the NAME-SA expired.
No socket bound to the NAME can send packets (other than address claims). To
-claim another address, some socket bound to NAME, must bind(2) again, but with
-only j1939.addr changed to the new SA, and must then send a valid address claim
+claim another address, some socket bound to NAME, must ``bind(2)`` again, but with
+only ``j1939.addr`` changed to the new SA, and must then send a valid address claim
packet. This restarts the state machine in the kernel (and any other
participant on the bus) for this NAME.
-can-utils also include the jacd tool, so it can be used as code example or as
+``can-utils`` also include the ``j1939acd`` tool, so it can be used as code example or as
default Address Claiming daemon.
Send Examples
@@ -403,8 +403,8 @@
bind(sock, (struct sockaddr *)&baddr, sizeof(baddr));
-Now, the socket 'sock' is bound to the SA 0x20. Since no connect(2) was called,
-at this point we can use only sendto(2) or sendmsg(2).
+Now, the socket 'sock' is bound to the SA 0x20. Since no ``connect(2)`` was called,
+at this point we can use only ``sendto(2)`` or ``sendmsg(2)``.
Send:
@@ -414,8 +414,8 @@
.can_family = AF_CAN,
.can_addr.j1939 = {
.name = J1939_NO_NAME;
- .pgn = 0x30,
- .addr = 0x12300,
+ .addr = 0x30,
+ .pgn = 0x12300,
},
};
diff --git a/Documentation/networking/netdev-FAQ.rst b/Documentation/networking/netdev-FAQ.rst
index d5c9320..2153776 100644
--- a/Documentation/networking/netdev-FAQ.rst
+++ b/Documentation/networking/netdev-FAQ.rst
@@ -110,7 +110,7 @@
Q: How can I tell whether it got merged?
A: Start by looking at the main patchworks queue for netdev:
- http://patchwork.ozlabs.org/project/netdev/list/
+ https://patchwork.kernel.org/project/netdevbpf/list/
The "State" field will tell you exactly where things are at with your
patch.
@@ -152,7 +152,7 @@
There is a patchworks queue that you can see here:
- http://patchwork.ozlabs.org/bundle/davem/stable/?state=*
+ https://patchwork.kernel.org/bundle/netdev/stable/?state=*
It contains the patches which Dave has selected, but not yet handed off
to Greg. If Greg already has the patch, then it will be here:
diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst
index 2561060..b2f7ec7 100644
--- a/Documentation/networking/phy.rst
+++ b/Documentation/networking/phy.rst
@@ -247,8 +247,8 @@
speeds (see below.)
``PHY_INTERFACE_MODE_2500BASEX``
- This defines a variant of 1000BASE-X which is clocked 2.5 times faster,
- than the 802.3 standard giving a fixed bit rate of 3.125Gbaud.
+ This defines a variant of 1000BASE-X which is clocked 2.5 times as fast
+ as the 802.3 standard, giving a fixed bit rate of 3.125Gbaud.
``PHY_INTERFACE_MODE_SGMII``
This is used for Cisco SGMII, which is a modification of 1000BASE-X
diff --git a/Documentation/networking/statistics.rst b/Documentation/networking/statistics.rst
index 8e15bc9..234abed 100644
--- a/Documentation/networking/statistics.rst
+++ b/Documentation/networking/statistics.rst
@@ -175,5 +175,4 @@
translated to netlink attributes when dumped. Drivers must not overwrite
the statistics they don't report with 0.
-.. kernel-doc:: include/linux/ethtool.h
- :identifiers: ethtool_pause_stats
+- ethtool_pause_stats()
diff --git a/Documentation/process/stable-kernel-rules.rst b/Documentation/process/stable-kernel-rules.rst
index 06f743b..3973556 100644
--- a/Documentation/process/stable-kernel-rules.rst
+++ b/Documentation/process/stable-kernel-rules.rst
@@ -39,7 +39,7 @@
submission guidelines as described in
:ref:`Documentation/networking/netdev-FAQ.rst <netdev-FAQ>`
after first checking the stable networking queue at
- https://patchwork.ozlabs.org/bundle/davem/stable/?series=&submitter=&state=*&q=&archive=
+ https://patchwork.kernel.org/bundle/netdev/stable/?state=*
to ensure the requested patch is not already queued up.
- Security patches should not be handled (solely) by the -stable review
process but should follow the procedures in
diff --git a/Documentation/sphinx/automarkup.py b/Documentation/sphinx/automarkup.py
index 409dbc4..3e81eba 100644
--- a/Documentation/sphinx/automarkup.py
+++ b/Documentation/sphinx/automarkup.py
@@ -16,28 +16,36 @@
from itertools import chain
#
+# Python 2 lacks re.ASCII...
+#
+try:
+ ascii_p3 = re.ASCII
+except AttributeError:
+ ascii_p3 = 0
+
+#
# Regex nastiness. Of course.
# Try to identify "function()" that's not already marked up some
# other way. Sphinx doesn't like a lot of stuff right after a
# :c:func: block (i.e. ":c:func:`mmap()`s" flakes out), so the last
# bit tries to restrict matches to things that won't create trouble.
#
-RE_function = re.compile(r'\b(([a-zA-Z_]\w+)\(\))', flags=re.ASCII)
+RE_function = re.compile(r'\b(([a-zA-Z_]\w+)\(\))', flags=ascii_p3)
#
# Sphinx 2 uses the same :c:type role for struct, union, enum and typedef
#
RE_generic_type = re.compile(r'\b(struct|union|enum|typedef)\s+([a-zA-Z_]\w+)',
- flags=re.ASCII)
+ flags=ascii_p3)
#
# Sphinx 3 uses a different C role for each one of struct, union, enum and
# typedef
#
-RE_struct = re.compile(r'\b(struct)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
-RE_union = re.compile(r'\b(union)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
-RE_enum = re.compile(r'\b(enum)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
-RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
+RE_struct = re.compile(r'\b(struct)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
+RE_union = re.compile(r'\b(union)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
+RE_enum = re.compile(r'\b(enum)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
+RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
#
# Detects a reference to a documentation page of the form Documentation/... with
diff --git a/Documentation/sphinx/kernel_abi.py b/Documentation/sphinx/kernel_abi.py
new file mode 100644
index 0000000..f3da859c
--- /dev/null
+++ b/Documentation/sphinx/kernel_abi.py
@@ -0,0 +1,194 @@
+# -*- coding: utf-8; mode: python -*-
+# coding=utf-8
+# SPDX-License-Identifier: GPL-2.0
+#
+u"""
+ kernel-abi
+ ~~~~~~~~~~
+
+ Implementation of the ``kernel-abi`` reST-directive.
+
+ :copyright: Copyright (C) 2016 Markus Heiser
+ :copyright: Copyright (C) 2016-2020 Mauro Carvalho Chehab
+ :maintained-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
+ :license: GPL Version 2, June 1991 see Linux/COPYING for details.
+
+ The ``kernel-abi`` (:py:class:`KernelCmd`) directive calls the
+ scripts/get_abi.pl script to parse the Kernel ABI files.
+
+ Overview of directive's argument and options.
+
+ .. code-block:: rst
+
+ .. kernel-abi:: <ABI directory location>
+ :debug:
+
+ The argument ``<ABI directory location>`` is required. It contains the
+ location of the ABI files to be parsed.
+
+ ``debug``
+ Inserts a code-block with the *raw* reST. Sometimes it is helpful to see
+ what reST is generated.
+
+"""
+
+import codecs
+import os
+import subprocess
+import sys
+import re
+import kernellog
+
+from os import path
+
+from docutils import nodes, statemachine
+from docutils.statemachine import ViewList
+from docutils.parsers.rst import directives, Directive
+from docutils.utils.error_reporting import ErrorString
+
+#
+# AutodocReporter is only good up to Sphinx 1.7
+#
+import sphinx
+
+Use_SSI = sphinx.__version__[:3] >= '1.7'
+if Use_SSI:
+ from sphinx.util.docutils import switch_source_input
+else:
+ from sphinx.ext.autodoc import AutodocReporter
+
+__version__ = '1.0'
+
+def setup(app):
+
+ app.add_directive("kernel-abi", KernelCmd)
+ return dict(
+ version = __version__
+ , parallel_read_safe = True
+ , parallel_write_safe = True
+ )
+
+class KernelCmd(Directive):
+
+ u"""KernelABI (``kernel-abi``) directive"""
+
+ required_arguments = 1
+ optional_arguments = 2
+ has_content = False
+ final_argument_whitespace = True
+
+ option_spec = {
+ "debug" : directives.flag,
+ "rst" : directives.unchanged
+ }
+
+ def run(self):
+
+ doc = self.state.document
+ if not doc.settings.file_insertion_enabled:
+ raise self.warning("docutils: file insertion disabled")
+
+ env = doc.settings.env
+ cwd = path.dirname(doc.current_source)
+ cmd = "get_abi.pl rest --enable-lineno --dir "
+ cmd += self.arguments[0]
+
+ if 'rst' in self.options:
+ cmd += " --rst-source"
+
+ srctree = path.abspath(os.environ["srctree"])
+
+ fname = cmd
+
+ # extend PATH with $(srctree)/scripts
+ path_env = os.pathsep.join([
+ srctree + os.sep + "scripts",
+ os.environ["PATH"]
+ ])
+ shell_env = os.environ.copy()
+ shell_env["PATH"] = path_env
+ shell_env["srctree"] = srctree
+
+ lines = self.runCmd(cmd, shell=True, cwd=cwd, env=shell_env)
+ nodeList = self.nestedParse(lines, self.arguments[0])
+ return nodeList
+
+ def runCmd(self, cmd, **kwargs):
+ u"""Run command ``cmd`` and return it's stdout as unicode."""
+
+ try:
+ proc = subprocess.Popen(
+ cmd
+ , stdout = subprocess.PIPE
+ , stderr = subprocess.PIPE
+ , **kwargs
+ )
+ out, err = proc.communicate()
+
+ out, err = codecs.decode(out, 'utf-8'), codecs.decode(err, 'utf-8')
+
+ if proc.returncode != 0:
+ raise self.severe(
+ u"command '%s' failed with return code %d"
+ % (cmd, proc.returncode)
+ )
+ except OSError as exc:
+ raise self.severe(u"problems with '%s' directive: %s."
+ % (self.name, ErrorString(exc)))
+ return out
+
+ def nestedParse(self, lines, fname):
+ content = ViewList()
+ node = nodes.section()
+
+ if "debug" in self.options:
+ code_block = "\n\n.. code-block:: rst\n :linenos:\n"
+ for l in lines.split("\n"):
+ code_block += "\n " + l
+ lines = code_block + "\n\n"
+
+ line_regex = re.compile("^#define LINENO (\S+)\#([0-9]+)$")
+ ln = 0
+ n = 0
+ f = fname
+
+ for line in lines.split("\n"):
+ n = n + 1
+ match = line_regex.search(line)
+ if match:
+ new_f = match.group(1)
+
+ # Sphinx parser is lazy: it stops parsing contents in the
+ # middle, if it is too big. So, handle it per input file
+ if new_f != f and content:
+ self.do_parse(content, node)
+ content = ViewList()
+
+ f = new_f
+
+ # sphinx counts lines from 0
+ ln = int(match.group(2)) - 1
+ else:
+ content.append(line, f, ln)
+
+ kernellog.info(self.state.document.settings.env.app, "%s: parsed %i lines" % (fname, n))
+
+ if content:
+ self.do_parse(content, node)
+
+ return node.children
+
+ def do_parse(self, content, node):
+ if Use_SSI:
+ with switch_source_input(self.state, content):
+ self.state.nested_parse(content, 0, node, match_titles=1)
+ else:
+ buf = self.state.memo.title_styles, self.state.memo.section_level, self.state.memo.reporter
+
+ self.state.memo.title_styles = []
+ self.state.memo.section_level = 0
+ self.state.memo.reporter = AutodocReporter(content, self.state.memo.reporter)
+ try:
+ self.state.nested_parse(content, 0, node, match_titles=1)
+ finally:
+ self.state.memo.title_styles, self.state.memo.section_level, self.state.memo.reporter = buf
diff --git a/Documentation/sphinx/kernellog.py b/Documentation/sphinx/kernellog.py
index af924f5..8ac7d27 100644
--- a/Documentation/sphinx/kernellog.py
+++ b/Documentation/sphinx/kernellog.py
@@ -25,4 +25,8 @@
else:
app.verbose(message)
-
+def info(app, message):
+ if UseLogging:
+ logger.info(message)
+ else:
+ app.info(message)
diff --git a/Documentation/translations/it_IT/process/stable-kernel-rules.rst b/Documentation/translations/it_IT/process/stable-kernel-rules.rst
index 4f206ce..283d6254 100644
--- a/Documentation/translations/it_IT/process/stable-kernel-rules.rst
+++ b/Documentation/translations/it_IT/process/stable-kernel-rules.rst
@@ -46,7 +46,7 @@
:ref:`Documentation/translations/it_IT/networking/netdev-FAQ.rst <it_netdev-FAQ>`;
ma solo dopo aver verificato al seguente indirizzo che la patch non sia
già in coda:
- https://patchwork.ozlabs.org/bundle/davem/stable/?series=&submitter=&state=*&q=&archive=
+ https://patchwork.kernel.org/bundle/netdev/stable/?state=*
- Una patch di sicurezza non dovrebbero essere gestite (solamente) dal processo
di revisione -stable, ma dovrebbe seguire le procedure descritte in
:ref:`Documentation/translations/it_IT/admin-guide/security-bugs.rst <it_securitybugs>`.
diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst
index 69fc516..acd2cc2 100644
--- a/Documentation/userspace-api/index.rst
+++ b/Documentation/userspace-api/index.rst
@@ -22,6 +22,7 @@
spec_ctrl
accelerators/ocxl
ioctl/index
+ iommu
media/index
.. only:: subproject and html
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 36d5f1f..e00a66d 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6367,7 +6367,7 @@
instead get bounced to user space through the KVM_EXIT_X86_RDMSR and
KVM_EXIT_X86_WRMSR exit notifications.
-8.25 KVM_X86_SET_MSR_FILTER
+8.27 KVM_X86_SET_MSR_FILTER
---------------------------
:Architectures: x86
@@ -6381,8 +6381,7 @@
trap and emulate MSRs that are outside of the scope of KVM as well as
limit the attack surface on KVM's MSR emulation code.
-
-8.26 KVM_CAP_ENFORCE_PV_CPUID
+8.28 KVM_CAP_ENFORCE_PV_CPUID
-----------------------------
Architectures: x86
diff --git a/Documentation/virt/kvm/cpuid.rst b/Documentation/virt/kvm/cpuid.rst
index 7d81c0a..cf62162 100644
--- a/Documentation/virt/kvm/cpuid.rst
+++ b/Documentation/virt/kvm/cpuid.rst
@@ -92,6 +92,10 @@
async pf acknowledgment msr
0x4b564d07.
+KVM_FEATURE_MSI_EXT_DEST_ID 15 guest checks this feature bit
+ before using extended destination
+ ID bits in MSI address bits 11-5.
+
KVM_FEATURE_CLOCKSOURCE_STABLE_BIT 24 host will warn if no guest-side
per-cpu warps are expected in
kvmclock
diff --git a/Documentation/xtensa/mmu.rst b/Documentation/xtensa/mmu.rst
index e52a129..450573a 100644
--- a/Documentation/xtensa/mmu.rst
+++ b/Documentation/xtensa/mmu.rst
@@ -82,7 +82,8 @@
+------------------+
| VMALLOC area | VMALLOC_START 0xc0000000 128MB - 64KB
+------------------+ VMALLOC_END
- | Cache aliasing | TLBTEMP_BASE_1 0xc7ff0000 DCACHE_WAY_SIZE
+ +------------------+
+ | Cache aliasing | TLBTEMP_BASE_1 0xc8000000 DCACHE_WAY_SIZE
| remap area 1 |
+------------------+
| Cache aliasing | TLBTEMP_BASE_2 DCACHE_WAY_SIZE
@@ -124,7 +125,8 @@
+------------------+
| VMALLOC area | VMALLOC_START 0xa0000000 128MB - 64KB
+------------------+ VMALLOC_END
- | Cache aliasing | TLBTEMP_BASE_1 0xa7ff0000 DCACHE_WAY_SIZE
+ +------------------+
+ | Cache aliasing | TLBTEMP_BASE_1 0xa8000000 DCACHE_WAY_SIZE
| remap area 1 |
+------------------+
| Cache aliasing | TLBTEMP_BASE_2 DCACHE_WAY_SIZE
@@ -167,7 +169,8 @@
+------------------+
| VMALLOC area | VMALLOC_START 0x90000000 128MB - 64KB
+------------------+ VMALLOC_END
- | Cache aliasing | TLBTEMP_BASE_1 0x97ff0000 DCACHE_WAY_SIZE
+ +------------------+
+ | Cache aliasing | TLBTEMP_BASE_1 0x98000000 DCACHE_WAY_SIZE
| remap area 1 |
+------------------+
| Cache aliasing | TLBTEMP_BASE_2 DCACHE_WAY_SIZE
diff --git a/MAINTAINERS b/MAINTAINERS
index e73636b..a008b70 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -934,7 +934,7 @@
L: amd-gfx@lists.freedesktop.org
S: Supported
T: git git://people.freedesktop.org/~agd5f/linux
-F: drivers/gpu/drm/amd/powerplay/
+F: drivers/gpu/drm/amd/pm/powerplay/
AMD SEATTLE DEVICE TREE SUPPORT
M: Brijesh Singh <brijeshkumar.singh@amd.com>
@@ -978,7 +978,7 @@
L: linux-iio@vger.kernel.org
S: Supported
W: http://ez.analog.com/community/linux-device-drivers
-F: Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.txt
+F: Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.yaml
F: drivers/iio/adc/ad7768-1.c
ANALOG DEVICES INC AD7780 DRIVER
@@ -1279,7 +1279,7 @@
L: netdev@vger.kernel.org
S: Supported
W: https://www.marvell.com/
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: Documentation/networking/device_drivers/ethernet/aquantia/atlantic.rst
F: drivers/net/ethernet/aquantia/atlantic/
@@ -1546,6 +1546,7 @@
ARM/Allwinner sunXi SoC support
M: Maxime Ripard <mripard@kernel.org>
M: Chen-Yu Tsai <wens@csie.org>
+R: Jernej Skrabec <jernej.skrabec@siol.net>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git
@@ -2374,8 +2375,7 @@
F: sound/soc/rockchip/
N: rockchip
-ARM/SAMSUNG EXYNOS ARM ARCHITECTURES
-M: Kukjin Kim <kgene@kernel.org>
+ARM/SAMSUNG S3C, S5P AND EXYNOS ARM ARCHITECTURES
M: Krzysztof Kozlowski <krzk@kernel.org>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: linux-samsung-soc@vger.kernel.org
@@ -2404,15 +2404,7 @@
N: s3c64xx
N: s5pv210
-ARM/SAMSUNG MOBILE MACHINE SUPPORT
-M: Kyungmin Park <kyungmin.park@samsung.com>
-L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S: Maintained
-F: arch/arm/mach-s5pv210/
-
ARM/SAMSUNG S5P SERIES 2D GRAPHICS ACCELERATION (G2D) SUPPORT
-M: Kyungmin Park <kyungmin.park@samsung.com>
-M: Kamil Debski <kamil@wypas.org>
M: Andrzej Hajda <a.hajda@samsung.com>
L: linux-arm-kernel@lists.infradead.org
L: linux-media@vger.kernel.org
@@ -2437,9 +2429,6 @@
F: drivers/media/platform/s5p-jpeg/
ARM/SAMSUNG S5P SERIES Multi Format Codec (MFC) SUPPORT
-M: Kyungmin Park <kyungmin.park@samsung.com>
-M: Kamil Debski <kamil@wypas.org>
-M: Jeongtae Park <jtp.park@samsung.com>
M: Andrzej Hajda <a.hajda@samsung.com>
L: linux-arm-kernel@lists.infradead.org
L: linux-media@vger.kernel.org
@@ -2642,10 +2631,8 @@
N: visconti
ARM/UNIPHIER ARCHITECTURE
-M: Masahiro Yamada <yamada.masahiro@socionext.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S: Maintained
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-uniphier.git
+S: Orphan
F: Documentation/devicetree/bindings/arm/socionext/uniphier.yaml
F: Documentation/devicetree/bindings/gpio/socionext,uniphier-gpio.yaml
F: Documentation/devicetree/bindings/pinctrl/socionext,uniphier-pinctrl.yaml
@@ -3246,10 +3233,10 @@
BPF (Safe dynamic programs and tools)
M: Alexei Starovoitov <ast@kernel.org>
M: Daniel Borkmann <daniel@iogearbox.net>
+M: Andrii Nakryiko <andrii@kernel.org>
R: Martin KaFai Lau <kafai@fb.com>
R: Song Liu <songliubraving@fb.com>
R: Yonghong Song <yhs@fb.com>
-R: Andrii Nakryiko <andrii@kernel.org>
R: John Fastabend <john.fastabend@gmail.com>
R: KP Singh <kpsingh@chromium.org>
L: netdev@vger.kernel.org
@@ -3860,7 +3847,7 @@
L: linux-usb@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/peter.chen/usb.git
-F: Documentation/devicetree/bindings/usb/cdns-usb3.txt
+F: Documentation/devicetree/bindings/usb/cdns,usb3.yaml
F: drivers/usb/cdns3/
CADET FM/AM RADIO RECEIVER DRIVER
@@ -4713,7 +4700,7 @@
F: drivers/media/dvb-frontends/cxd2820r*
CXGB3 ETHERNET DRIVER (CXGB3)
-M: Vishal Kulkarni <vishal@chelsio.com>
+M: Raju Rangoju <rajur@chelsio.com>
L: netdev@vger.kernel.org
S: Supported
W: http://www.chelsio.com
@@ -4745,7 +4732,7 @@
F: drivers/net/ethernet/chelsio/inline_crypto/
CXGB4 ETHERNET DRIVER (CXGB4)
-M: Vishal Kulkarni <vishal@chelsio.com>
+M: Raju Rangoju <rajur@chelsio.com>
L: netdev@vger.kernel.org
S: Supported
W: http://www.chelsio.com
@@ -4767,7 +4754,7 @@
F: include/uapi/rdma/cxgb4-abi.h
CXGB4VF ETHERNET DRIVER (CXGB4VF)
-M: Vishal Kulkarni <vishal@gmail.com>
+M: Raju Rangoju <rajur@chelsio.com>
L: netdev@vger.kernel.org
S: Supported
W: http://www.chelsio.com
@@ -5006,9 +4993,8 @@
F: drivers/media/platform/sti/delta
DENALI NAND DRIVER
-M: Masahiro Yamada <yamada.masahiro@socionext.com>
L: linux-mtd@lists.infradead.org
-S: Supported
+S: Orphan
F: drivers/mtd/nand/raw/denali*
DESIGNWARE EDMA CORE IP DRIVER
@@ -6618,6 +6604,7 @@
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4.git
F: Documentation/filesystems/ext4/
F: fs/ext4/
+F: include/trace/events/ext4.h
Extended Verification Module (EVM)
M: Mimi Zohar <zohar@linux.ibm.com>
@@ -7920,7 +7907,7 @@
M: john.garry@huawei.com
S: Maintained
W: http://www.hisilicon.com
-F: Documentation/devicetree/bindings/arm/hisilicon/hisilicon-low-pin-count.txt
+F: Documentation/devicetree/bindings/arm/hisilicon/low-pin-count.yaml
F: drivers/bus/hisi_lpc.c
HISILICON NETWORK SUBSYSTEM 3 DRIVER (HNS3)
@@ -8833,8 +8820,8 @@
W: http://www.intel.com/support/feedback.htm
W: http://e1000.sourceforge.net/
Q: http://patchwork.ozlabs.org/project/intel-wired-lan/list/
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-queue.git
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue.git
F: Documentation/networking/device_drivers/ethernet/intel/
F: drivers/net/ethernet/intel/
F: drivers/net/ethernet/intel/*/
@@ -8976,22 +8963,6 @@
W: https://01.org/linux-acpi
F: drivers/platform/x86/intel_menlow.c
-INTEL MIC DRIVERS (mic)
-M: Sudeep Dutt <sudeep.dutt@intel.com>
-M: Ashutosh Dixit <ashutosh.dixit@intel.com>
-S: Supported
-W: https://github.com/sudeepdutt/mic
-W: http://software.intel.com/en-us/mic-developer
-F: Documentation/misc-devices/mic/
-F: drivers/dma/mic_x100_dma.c
-F: drivers/dma/mic_x100_dma.h
-F: drivers/misc/mic/
-F: include/linux/mic_bus.h
-F: include/linux/scif.h
-F: include/uapi/linux/mic_common.h
-F: include/uapi/linux/mic_ioctl.h
-F: include/uapi/linux/scif_ioctl.h
-
INTEL P-Unit IPC DRIVER
M: Zha Qipeng <qipeng.zha@intel.com>
L: platform-driver-x86@vger.kernel.org
@@ -9191,6 +9162,7 @@
IOMMU DRIVERS
M: Joerg Roedel <joro@8bytes.org>
+M: Will Deacon <will@kernel.org>
L: iommu@lists.linux-foundation.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
@@ -9862,13 +9834,6 @@
F: arch/mips/lantiq
F: drivers/soc/lantiq
-LAPB module
-L: linux-x25@vger.kernel.org
-S: Orphan
-F: Documentation/networking/lapb-module.rst
-F: include/*/lapb.h
-F: net/lapb/
-
LASI 53c700 driver for PARISC
M: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
L: linux-scsi@vger.kernel.org
@@ -11183,7 +11148,7 @@
F: drivers/input/touchscreen/melfas_mip4.c
MELLANOX BLUEFIELD I2C DRIVER
-M: Khalil Blaiech <kblaiech@mellanox.com>
+M: Khalil Blaiech <kblaiech@nvidia.com>
L: linux-i2c@vger.kernel.org
S: Supported
F: drivers/i2c/busses/i2c-mlxbf.c
@@ -11193,7 +11158,7 @@
L: netdev@vger.kernel.org
S: Supported
W: http://www.mellanox.com
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: drivers/net/ethernet/mellanox/mlx4/en_*
MELLANOX ETHERNET DRIVER (mlx5e)
@@ -11201,7 +11166,7 @@
L: netdev@vger.kernel.org
S: Supported
W: http://www.mellanox.com
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: drivers/net/ethernet/mellanox/mlx5/core/en_*
MELLANOX ETHERNET INNOVA DRIVERS
@@ -11209,7 +11174,7 @@
L: netdev@vger.kernel.org
S: Supported
W: http://www.mellanox.com
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: drivers/net/ethernet/mellanox/mlx5/core/accel/*
F: drivers/net/ethernet/mellanox/mlx5/core/en_accel/*
F: drivers/net/ethernet/mellanox/mlx5/core/fpga/*
@@ -11221,7 +11186,7 @@
L: netdev@vger.kernel.org
S: Supported
W: http://www.mellanox.com
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: drivers/net/ethernet/mellanox/mlxsw/
F: tools/testing/selftests/drivers/net/mlxsw/
@@ -11230,7 +11195,7 @@
L: netdev@vger.kernel.org
S: Supported
W: http://www.mellanox.com
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: drivers/net/ethernet/mellanox/mlxfw/
MELLANOX HARDWARE PLATFORM SUPPORT
@@ -11249,7 +11214,7 @@
L: linux-rdma@vger.kernel.org
S: Supported
W: http://www.mellanox.com
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: drivers/net/ethernet/mellanox/mlx4/
F: include/linux/mlx4/
@@ -11270,7 +11235,7 @@
L: linux-rdma@vger.kernel.org
S: Supported
W: http://www.mellanox.com
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: Documentation/networking/device_drivers/ethernet/mellanox/
F: drivers/net/ethernet/mellanox/mlx5/core/
F: include/linux/mlx5/
@@ -12150,7 +12115,7 @@
L: netdev@vger.kernel.org
S: Maintained
W: http://www.linuxfoundation.org/en/Net
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
F: Documentation/devicetree/bindings/net/
@@ -12195,7 +12160,7 @@
L: netdev@vger.kernel.org
S: Maintained
W: http://www.linuxfoundation.org/en/Net
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
B: mailto:netdev@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
@@ -14230,7 +14195,6 @@
F: include/trace/events/pwc.h
PWM FAN DRIVER
-M: Kamil Debski <kamil@wypas.org>
M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
L: linux-hwmon@vger.kernel.org
S: Supported
@@ -14547,6 +14511,14 @@
F: drivers/mailbox/qcom-ipcc.c
F: include/dt-bindings/mailbox/qcom-ipcc.h
+QUALCOMM IPQ4019 VQMMC REGULATOR DRIVER
+M: Robert Marko <robert.marko@sartura.hr>
+M: Luka Perkov <luka.perkov@sartura.hr>
+L: linux-arm-msm@vger.kernel.org
+S: Maintained
+F: Documentation/devicetree/bindings/regulator/vqmmc-ipq4019-regulator.yaml
+F: drivers/regulator/vqmmc-ipq4019-regulator.c
+
QUALCOMM RMNET DRIVER
M: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
M: Sean Tranchetti <stranche@codeaurora.org>
@@ -14902,7 +14874,6 @@
R: Sergei Shtylyov <sergei.shtylyov@gmail.com>
L: netdev@vger.kernel.org
L: linux-renesas-soc@vger.kernel.org
-F: Documentation/devicetree/bindings/net/renesas,*.txt
F: Documentation/devicetree/bindings/net/renesas,*.yaml
F: drivers/net/ethernet/renesas/
F: include/linux/sh_eth.h
@@ -15259,7 +15230,6 @@
S390 IUCV NETWORK LAYER
M: Julian Wiedmann <jwi@linux.ibm.com>
M: Karsten Graul <kgraul@linux.ibm.com>
-M: Ursula Braun <ubraun@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
W: http://www.ibm.com/developerworks/linux/linux390/
@@ -15270,7 +15240,6 @@
S390 NETWORK DRIVERS
M: Julian Wiedmann <jwi@linux.ibm.com>
M: Karsten Graul <kgraul@linux.ibm.com>
-M: Ursula Braun <ubraun@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
W: http://www.ibm.com/developerworks/linux/linux390/
@@ -15372,7 +15341,6 @@
SAMSUNG AUDIO (ASoC) DRIVERS
M: Krzysztof Kozlowski <krzk@kernel.org>
-M: Sangbeom Kim <sbkim73@samsung.com>
M: Sylwester Nawrocki <s.nawrocki@samsung.com>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
S: Supported
@@ -15407,7 +15375,6 @@
F: drivers/platform/x86/samsung-laptop.c
SAMSUNG MULTIFUNCTION PMIC DEVICE DRIVERS
-M: Sangbeom Kim <sbkim73@samsung.com>
M: Krzysztof Kozlowski <krzk@kernel.org>
M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
L: linux-kernel@vger.kernel.org
@@ -15441,14 +15408,12 @@
F: drivers/nfc/s3fwrn5
SAMSUNG S5C73M3 CAMERA DRIVER
-M: Kyungmin Park <kyungmin.park@samsung.com>
M: Andrzej Hajda <a.hajda@samsung.com>
L: linux-media@vger.kernel.org
S: Supported
F: drivers/media/i2c/s5c73m3/*
SAMSUNG S5K5BAF CAMERA DRIVER
-M: Kyungmin Park <kyungmin.park@samsung.com>
M: Andrzej Hajda <a.hajda@samsung.com>
L: linux-media@vger.kernel.org
S: Supported
@@ -15466,7 +15431,6 @@
F: drivers/crypto/s5p-sss.c
SAMSUNG S5P/EXYNOS4 SOC SERIES CAMERA SUBSYSTEM DRIVERS
-M: Kyungmin Park <kyungmin.park@samsung.com>
M: Sylwester Nawrocki <s.nawrocki@samsung.com>
L: linux-media@vger.kernel.org
S: Supported
@@ -15489,7 +15453,6 @@
F: include/linux/platform_data/clk-s3c2410.h
SAMSUNG SPI DRIVERS
-M: Kukjin Kim <kgene@kernel.org>
M: Krzysztof Kozlowski <krzk@kernel.org>
M: Andi Shyti <andi@etezian.org>
L: linux-spi@vger.kernel.org
@@ -15515,7 +15478,6 @@
F: drivers/thermal/samsung/
SAMSUNG USB2 PHY DRIVER
-M: Kamil Debski <kamil@wypas.org>
M: Sylwester Nawrocki <s.nawrocki@samsung.com>
L: linux-kernel@vger.kernel.org
S: Supported
@@ -15844,7 +15806,6 @@
F: drivers/misc/sgi-xp/
SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS
-M: Ursula Braun <ubraun@linux.ibm.com>
M: Karsten Graul <kgraul@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
@@ -18106,7 +18067,7 @@
M: Binghui Wang <wangbinghui@hisilicon.com>
L: linux-usb@vger.kernel.org
S: Maintained
-F: Documentation/devicetree/bindings/phy/phy-hi3660-usb3.txt
+F: Documentation/devicetree/bindings/phy/hisilicon,hi3660-usb3.yaml
F: drivers/phy/hisilicon/phy-hi3660-usb3.c
USB ISP116X DRIVER
@@ -18191,6 +18152,14 @@
S: Supported
F: drivers/usb/class/usblp.c
+USB RAW GADGET DRIVER
+R: Andrey Konovalov <andreyknvl@gmail.com>
+L: linux-usb@vger.kernel.org
+S: Maintained
+F: Documentation/usb/raw-gadget.rst
+F: drivers/usb/gadget/legacy/raw_gadget.c
+F: include/uapi/linux/usb/raw_gadget.h
+
USB QMI WWAN NETWORK DRIVER
M: Bjørn Mork <bjorn@mork.no>
L: netdev@vger.kernel.org
@@ -19016,12 +18985,18 @@
S: Maintained
N: axp[128]
-X.25 NETWORK LAYER
-M: Andrew Hendry <andrew.hendry@gmail.com>
+X.25 STACK
+M: Martin Schiller <ms@dev.tdt.de>
L: linux-x25@vger.kernel.org
-S: Odd Fixes
+S: Maintained
+F: Documentation/networking/lapb-module.rst
F: Documentation/networking/x25*
+F: drivers/net/wan/hdlc_x25.c
+F: drivers/net/wan/lapbether.c
+F: include/*/lapb.h
F: include/net/x25*
+F: include/uapi/linux/x25.h
+F: net/lapb/
F: net/x25/
X86 ARCHITECTURE (32-BIT AND 64-BIT)
diff --git a/Makefile b/Makefile
index ee2284a..e2c3f65 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 5
PATCHLEVEL = 10
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc4
NAME = Kleptomaniac Octopus
# *DOCUMENTATION*
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 17fd1ed..9152782 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -67,7 +67,22 @@
sr r5, [ARC_REG_LPB_CTRL]
1:
#endif /* CONFIG_ARC_LPB_DISABLE */
-#endif
+
+ /* On HSDK, CCMs need to remapped super early */
+#ifdef CONFIG_ARC_SOC_HSDK
+ mov r6, 0x60000000
+ lr r5, [ARC_REG_ICCM_BUILD]
+ breq r5, 0, 1f
+ sr r6, [ARC_REG_AUX_ICCM]
+1:
+ lr r5, [ARC_REG_DCCM_BUILD]
+ breq r5, 0, 2f
+ sr r6, [ARC_REG_AUX_DCCM]
+2:
+#endif /* CONFIG_ARC_SOC_HSDK */
+
+#endif /* CONFIG_ISA_ARCV2 */
+
; Config DSP_CTRL properly, so kernel may use integer multiply,
; multiply-accumulate, and divide operations
DSP_EARLY_INIT
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index feba91c..b23986f 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -112,7 +112,7 @@
int (*consumer_fn) (unsigned int, void *), void *arg)
{
#ifdef CONFIG_ARC_DW2_UNWIND
- int ret = 0;
+ int ret = 0, cnt = 0;
unsigned int address;
struct unwind_frame_info frame_info;
@@ -132,6 +132,11 @@
break;
frame_info.regs.r63 = frame_info.regs.r31;
+
+ if (cnt++ > 128) {
+ printk("unwinder looping too long, aborting !\n");
+ return 0;
+ }
}
return address; /* return the last address it saw */
diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c
index 0b63fc0..b3ea1fa 100644
--- a/arch/arc/plat-hsdk/platform.c
+++ b/arch/arc/plat-hsdk/platform.c
@@ -17,22 +17,6 @@
#define ARC_CCM_UNUSED_ADDR 0x60000000
-static void __init hsdk_init_per_cpu(unsigned int cpu)
-{
- /*
- * By default ICCM is mapped to 0x7z while this area is used for
- * kernel virtual mappings, so move it to currently unused area.
- */
- if (cpuinfo_arc700[cpu].iccm.sz)
- write_aux_reg(ARC_REG_AUX_ICCM, ARC_CCM_UNUSED_ADDR);
-
- /*
- * By default DCCM is mapped to 0x8z while this area is used by kernel,
- * so move it to currently unused area.
- */
- if (cpuinfo_arc700[cpu].dccm.sz)
- write_aux_reg(ARC_REG_AUX_DCCM, ARC_CCM_UNUSED_ADDR);
-}
#define ARC_PERIPHERAL_BASE 0xf0000000
#define CREG_BASE (ARC_PERIPHERAL_BASE + 0x1000)
@@ -339,5 +323,4 @@
MACHINE_START(SIMULATION, "hsdk")
.dt_compat = hsdk_compat,
.init_early = hsdk_init_early,
- .init_per_cpu = hsdk_init_per_cpu,
MACHINE_END
diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
index ab291ce..2983e91 100644
--- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
+++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
@@ -122,7 +122,6 @@
};
&clock {
- clocks = <&clock CLK_XUSBXTI>;
assigned-clocks = <&clock CLK_FOUT_EPLL>;
assigned-clock-rates = <45158401>;
};
diff --git a/arch/arm/boot/dts/imx50-evk.dts b/arch/arm/boot/dts/imx50-evk.dts
index 878e89c..4ea5c23 100644
--- a/arch/arm/boot/dts/imx50-evk.dts
+++ b/arch/arm/boot/dts/imx50-evk.dts
@@ -59,7 +59,7 @@
MX50_PAD_CSPI_MISO__CSPI_MISO 0x00
MX50_PAD_CSPI_MOSI__CSPI_MOSI 0x00
MX50_PAD_CSPI_SS0__GPIO4_11 0xc4
- MX50_PAD_ECSPI1_MOSI__CSPI_SS1 0xf4
+ MX50_PAD_ECSPI1_MOSI__GPIO4_13 0x84
>;
};
diff --git a/arch/arm/boot/dts/imx6q-prti6q.dts b/arch/arm/boot/dts/imx6q-prti6q.dts
index d112b50..b4605ed 100644
--- a/arch/arm/boot/dts/imx6q-prti6q.dts
+++ b/arch/arm/boot/dts/imx6q-prti6q.dts
@@ -213,8 +213,8 @@
#size-cells = <0>;
/* Microchip KSZ9031RNX PHY */
- rgmii_phy: ethernet-phy@4 {
- reg = <4>;
+ rgmii_phy: ethernet-phy@0 {
+ reg = <0>;
interrupts-extended = <&gpio1 28 IRQ_TYPE_LEVEL_LOW>;
reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>;
reset-assert-us = <10000>;
diff --git a/arch/arm/boot/dts/imx6qdl-udoo.dtsi b/arch/arm/boot/dts/imx6qdl-udoo.dtsi
index 828dd20..d07d8f8 100644
--- a/arch/arm/boot/dts/imx6qdl-udoo.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-udoo.dtsi
@@ -98,7 +98,7 @@
&fec {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_enet>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
diff --git a/arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts b/arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts
index f1a4115..adde62d 100644
--- a/arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts
+++ b/arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts
@@ -227,12 +227,12 @@
/delete-property/ #size-cells;
spi-slave;
status = "okay";
- ready-gpio = <&gpio 125 GPIO_ACTIVE_HIGH>;
+ ready-gpios = <&gpio 125 GPIO_ACTIVE_HIGH>;
slave {
compatible = "olpc,xo1.75-ec";
spi-cpha;
- cmd-gpio = <&gpio 155 GPIO_ACTIVE_HIGH>;
+ cmd-gpios = <&gpio 155 GPIO_ACTIVE_HIGH>;
};
};
diff --git a/arch/arm/boot/dts/mmp3.dtsi b/arch/arm/boot/dts/mmp3.dtsi
index cc4efd0..4ae630d 100644
--- a/arch/arm/boot/dts/mmp3.dtsi
+++ b/arch/arm/boot/dts/mmp3.dtsi
@@ -296,6 +296,7 @@
interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&soc_clocks MMP2_CLK_CCIC0>;
clock-names = "axi";
+ power-domains = <&soc_clocks MMP3_POWER_DOMAIN_CAMERA>;
#clock-cells = <0>;
clock-output-names = "mclk";
status = "disabled";
@@ -307,6 +308,7 @@
interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&soc_clocks MMP2_CLK_CCIC1>;
clock-names = "axi";
+ power-domains = <&soc_clocks MMP3_POWER_DOMAIN_CAMERA>;
#clock-cells = <0>;
clock-output-names = "mclk";
status = "disabled";
diff --git a/arch/arm/boot/dts/stm32mp157c-ed1.dts b/arch/arm/boot/dts/stm32mp157c-ed1.dts
index ca109dc..2e77cce 100644
--- a/arch/arm/boot/dts/stm32mp157c-ed1.dts
+++ b/arch/arm/boot/dts/stm32mp157c-ed1.dts
@@ -89,6 +89,14 @@
states = <1800000 0x1>,
<2900000 0x0>;
};
+
+ vin: vin {
+ compatible = "regulator-fixed";
+ regulator-name = "vin";
+ regulator-min-microvolt = <5000000>;
+ regulator-max-microvolt = <5000000>;
+ regulator-always-on;
+ };
};
&adc {
@@ -150,11 +158,18 @@
regulators {
compatible = "st,stpmic1-regulators";
+ buck1-supply = <&vin>;
+ buck2-supply = <&vin>;
+ buck3-supply = <&vin>;
+ buck4-supply = <&vin>;
ldo1-supply = <&v3v3>;
ldo2-supply = <&v3v3>;
ldo3-supply = <&vdd_ddr>;
+ ldo4-supply = <&vin>;
ldo5-supply = <&v3v3>;
ldo6-supply = <&v3v3>;
+ vref_ddr-supply = <&vin>;
+ boost-supply = <&vin>;
pwr_sw1-supply = <&bst_out>;
pwr_sw2-supply = <&bst_out>;
diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi
index 5dff24e..8456f17 100644
--- a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi
+++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi
@@ -46,6 +46,16 @@
linux,code = <KEY_A>;
gpios = <&gpiof 3 GPIO_ACTIVE_LOW>;
};
+
+ /*
+ * The EXTi IRQ line 0 is shared with PMIC,
+ * so mark this as polled GPIO key.
+ */
+ button-2 {
+ label = "TA3-GPIO-C";
+ linux,code = <KEY_C>;
+ gpios = <&gpiog 0 GPIO_ACTIVE_LOW>;
+ };
};
gpio-keys {
@@ -59,13 +69,6 @@
wakeup-source;
};
- button-2 {
- label = "TA3-GPIO-C";
- linux,code = <KEY_C>;
- gpios = <&gpioi 11 GPIO_ACTIVE_LOW>;
- wakeup-source;
- };
-
button-3 {
label = "TA4-GPIO-D";
linux,code = <KEY_D>;
@@ -79,7 +82,7 @@
led-0 {
label = "green:led5";
- gpios = <&gpiog 2 GPIO_ACTIVE_HIGH>;
+ gpios = <&gpioc 6 GPIO_ACTIVE_HIGH>;
default-state = "off";
};
diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi
index b4b52cf..f796a61 100644
--- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi
+++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi
@@ -68,6 +68,7 @@
gpio = <&gpiog 3 GPIO_ACTIVE_LOW>;
regulator-always-on;
regulator-boot-on;
+ vin-supply = <&vdd>;
};
};
@@ -202,6 +203,7 @@
vdda: ldo1 {
regulator-name = "vdda";
+ regulator-always-on;
regulator-min-microvolt = <2900000>;
regulator-max-microvolt = <2900000>;
interrupts = <IT_CURLIM_LDO1 0>;
diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi
index 04fbb32..803eb8b 100644
--- a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi
+++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi
@@ -21,6 +21,10 @@
};
};
+&dts {
+ status = "okay";
+};
+
&i2c4 {
pinctrl-names = "default";
pinctrl-0 = <&i2c4_pins_a>;
diff --git a/arch/arm/boot/dts/stm32mp15xx-dkx.dtsi b/arch/arm/boot/dts/stm32mp15xx-dkx.dtsi
index a530774..93398cf 100644
--- a/arch/arm/boot/dts/stm32mp15xx-dkx.dtsi
+++ b/arch/arm/boot/dts/stm32mp15xx-dkx.dtsi
@@ -80,6 +80,14 @@
dais = <&sai2a_port &sai2b_port &i2s2_port>;
status = "okay";
};
+
+ vin: vin {
+ compatible = "regulator-fixed";
+ regulator-name = "vin";
+ regulator-min-microvolt = <5000000>;
+ regulator-max-microvolt = <5000000>;
+ regulator-always-on;
+ };
};
&adc {
@@ -240,9 +248,18 @@
regulators {
compatible = "st,stpmic1-regulators";
+ buck1-supply = <&vin>;
+ buck2-supply = <&vin>;
+ buck3-supply = <&vin>;
+ buck4-supply = <&vin>;
ldo1-supply = <&v3v3>;
+ ldo2-supply = <&vin>;
ldo3-supply = <&vdd_ddr>;
+ ldo4-supply = <&vin>;
+ ldo5-supply = <&vin>;
ldo6-supply = <&v3v3>;
+ vref_ddr-supply = <&vin>;
+ boost-supply = <&vin>;
pwr_sw1-supply = <&bst_out>;
pwr_sw2-supply = <&bst_out>;
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index 0f95a6e..1c5a666 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -143,7 +143,7 @@
trips {
cpu_alert0: cpu-alert0 {
/* milliCelsius */
- temperature = <850000>;
+ temperature = <85000>;
hysteresis = <2000>;
type = "passive";
};
diff --git a/arch/arm/boot/dts/sun6i-a31-hummingbird.dts b/arch/arm/boot/dts/sun6i-a31-hummingbird.dts
index 049e6ab..73de34a 100644
--- a/arch/arm/boot/dts/sun6i-a31-hummingbird.dts
+++ b/arch/arm/boot/dts/sun6i-a31-hummingbird.dts
@@ -154,7 +154,7 @@
pinctrl-names = "default";
pinctrl-0 = <&gmac_rgmii_pins>;
phy-handle = <&phy1>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
diff --git a/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts b/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts
index 32d5d45..8945dbb 100644
--- a/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts
+++ b/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts
@@ -130,7 +130,7 @@
pinctrl-names = "default";
pinctrl-0 = <&gmac_rgmii_pins>;
phy-handle = <&phy1>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
phy-supply = <®_gmac_3v3>;
status = "okay";
};
diff --git a/arch/arm/boot/dts/sun7i-a20-cubietruck.dts b/arch/arm/boot/dts/sun7i-a20-cubietruck.dts
index 8c8dee6..9109ca0 100644
--- a/arch/arm/boot/dts/sun7i-a20-cubietruck.dts
+++ b/arch/arm/boot/dts/sun7i-a20-cubietruck.dts
@@ -151,7 +151,7 @@
pinctrl-names = "default";
pinctrl-0 = <&gmac_rgmii_pins>;
phy-handle = <&phy1>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
diff --git a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts
index 9d34eab..431f702 100644
--- a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts
+++ b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts
@@ -131,7 +131,7 @@
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <®_sw>;
phy-handle = <&rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
allwinner,rx-delay-ps = <700>;
allwinner,tx-delay-ps = <700>;
status = "okay";
diff --git a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts
index d9be511..d8326a5 100644
--- a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts
+++ b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts
@@ -183,7 +183,7 @@
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <®_dldo4>;
phy-handle = <&rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts
index 71fb732..babf4cf 100644
--- a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts
+++ b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts
@@ -53,11 +53,6 @@
};
};
-&emac {
- /* LEDs changed to active high on the plus */
- /delete-property/ allwinner,leds-active-low;
-};
-
&mmc1 {
vmmc-supply = <®_vcc3v3>;
bus-width = <4>;
diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts
index 6dbf7b2..b6ca45d 100644
--- a/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts
+++ b/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts
@@ -67,7 +67,7 @@
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <®_gmac_3v3>;
phy-handle = <&ext_rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
diff --git a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts
index 2fc62ef..a6a1087 100644
--- a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts
+++ b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts
@@ -129,7 +129,7 @@
pinctrl-names = "default";
pinctrl-0 = <&gmac_rgmii_pins>;
phy-handle = <&phy1>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
phy-supply = <®_dc1sw>;
status = "okay";
};
diff --git a/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts b/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts
index d3b337b..484b93d 100644
--- a/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts
+++ b/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts
@@ -129,7 +129,7 @@
pinctrl-names = "default";
pinctrl-0 = <&gmac_rgmii_pins>;
phy-handle = <&phy1>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
phy-supply = <®_cldo1>;
status = "okay";
};
diff --git a/arch/arm/boot/dts/sun9i-a80-optimus.dts b/arch/arm/boot/dts/sun9i-a80-optimus.dts
index bbc6335..5c3580d 100644
--- a/arch/arm/boot/dts/sun9i-a80-optimus.dts
+++ b/arch/arm/boot/dts/sun9i-a80-optimus.dts
@@ -124,7 +124,7 @@
pinctrl-names = "default";
pinctrl-0 = <&gmac_rgmii_pins>;
phy-handle = <&phy1>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
phy-supply = <®_cldo1>;
status = "okay";
};
diff --git a/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi b/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi
index 39263e7..8e5cb3b 100644
--- a/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi
+++ b/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi
@@ -126,7 +126,7 @@
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <®_gmac_3v3>;
phy-handle = <&ext_rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
index e500911..6f1e0f0 100644
--- a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
+++ b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
@@ -406,6 +406,9 @@
};
};
+&mdio1 {
+ clock-frequency = <5000000>;
+};
&iomuxc {
pinctrl_gpio_e6185_eeprom_sel: pinctrl-gpio-e6185-eeprom-spi0 {
diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig
index aeb1209..bb70acc 100644
--- a/arch/arm/configs/imx_v4_v5_defconfig
+++ b/arch/arm/configs/imx_v4_v5_defconfig
@@ -93,6 +93,7 @@
CONFIG_SPI_IMX=y
CONFIG_SPI_SPIDEV=y
CONFIG_GPIO_SYSFS=y
+CONFIG_GPIO_MXC=y
CONFIG_W1=y
CONFIG_W1_MASTER_MXC=y
CONFIG_W1_SLAVE_THERM=y
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index 0fa79bd..221f5c3 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -217,6 +217,7 @@
CONFIG_GPIO_PCF857X=y
CONFIG_GPIO_STMPE=y
CONFIG_GPIO_74X164=y
+CONFIG_GPIO_MXC=y
CONFIG_POWER_RESET=y
CONFIG_POWER_RESET_SYSCON=y
CONFIG_POWER_RESET_SYSCON_POWEROFF=y
diff --git a/arch/arm/configs/multi_v5_defconfig b/arch/arm/configs/multi_v5_defconfig
index 70b709a..e00be9f 100644
--- a/arch/arm/configs/multi_v5_defconfig
+++ b/arch/arm/configs/multi_v5_defconfig
@@ -166,6 +166,7 @@
CONFIG_SPI_ORION=y
CONFIG_GPIO_ASPEED=m
CONFIG_GPIO_ASPEED_SGPIO=y
+CONFIG_GPIO_MXC=y
CONFIG_POWER_RESET=y
CONFIG_POWER_RESET_GPIO=y
CONFIG_POWER_RESET_QNAP=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index e731cdf..a611b0c 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -465,6 +465,7 @@
CONFIG_GPIO_TPS6586X=y
CONFIG_GPIO_TPS65910=y
CONFIG_GPIO_TWL4030=y
+CONFIG_GPIO_MXC=y
CONFIG_POWER_AVS=y
CONFIG_ROCKCHIP_IODOMAIN=y
CONFIG_POWER_RESET_AS3722=y
diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h
index 213607a..e26a278 100644
--- a/arch/arm/include/asm/kprobes.h
+++ b/arch/arm/include/asm/kprobes.h
@@ -44,20 +44,20 @@
unsigned long val, void *data);
/* optinsn template addresses */
-extern __visible kprobe_opcode_t optprobe_template_entry;
-extern __visible kprobe_opcode_t optprobe_template_val;
-extern __visible kprobe_opcode_t optprobe_template_call;
-extern __visible kprobe_opcode_t optprobe_template_end;
-extern __visible kprobe_opcode_t optprobe_template_sub_sp;
-extern __visible kprobe_opcode_t optprobe_template_add_sp;
-extern __visible kprobe_opcode_t optprobe_template_restore_begin;
-extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn;
-extern __visible kprobe_opcode_t optprobe_template_restore_end;
+extern __visible kprobe_opcode_t optprobe_template_entry[];
+extern __visible kprobe_opcode_t optprobe_template_val[];
+extern __visible kprobe_opcode_t optprobe_template_call[];
+extern __visible kprobe_opcode_t optprobe_template_end[];
+extern __visible kprobe_opcode_t optprobe_template_sub_sp[];
+extern __visible kprobe_opcode_t optprobe_template_add_sp[];
+extern __visible kprobe_opcode_t optprobe_template_restore_begin[];
+extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn[];
+extern __visible kprobe_opcode_t optprobe_template_restore_end[];
#define MAX_OPTIMIZED_LENGTH 4
#define MAX_OPTINSN_SIZE \
- ((unsigned long)&optprobe_template_end - \
- (unsigned long)&optprobe_template_entry)
+ ((unsigned long)optprobe_template_end - \
+ (unsigned long)optprobe_template_entry)
#define RELATIVEJUMP_SIZE 4
struct arch_optimized_insn {
diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c
index 05fe92a..0529f90 100644
--- a/arch/arm/kernel/perf_regs.c
+++ b/arch/arm/kernel/perf_regs.c
@@ -32,8 +32,7 @@
}
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
regs_user->regs = task_pt_regs(current);
regs_user->abi = perf_reg_abi(current);
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 5f4922e..f7f4620 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -41,6 +41,10 @@
#ifndef CONFIG_SMP_ON_UP
*(.alt.smp.init)
#endif
+#ifndef CONFIG_ARM_UNWIND
+ *(.ARM.exidx) *(.ARM.exidx.*)
+ *(.ARM.extab) *(.ARM.extab.*)
+#endif
}
. = PAGE_OFFSET + TEXT_OFFSET;
diff --git a/arch/arm/mach-mvebu/coherency_ll.S b/arch/arm/mach-mvebu/coherency_ll.S
index 2d962fe..a3a64bf 100644
--- a/arch/arm/mach-mvebu/coherency_ll.S
+++ b/arch/arm/mach-mvebu/coherency_ll.S
@@ -35,13 +35,8 @@
/*
* MMU is disabled, use the physical address of the coherency
- * base address. However, if the coherency fabric isn't mapped
- * (i.e its virtual address is zero), it means coherency is
- * not enabled, so we return 0.
+ * base address, (or 0x0 if the coherency fabric is not mapped)
*/
- ldr r1, =coherency_base
- cmp r1, #0
- beq 2f
adr r1, 3f
ldr r3, [r1]
ldr r1, [r1, r3]
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index d57112a..c23dbf8 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -354,8 +354,8 @@
/* set highmem page free */
for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
&range_start, &range_end, NULL) {
- unsigned long start = PHYS_PFN(range_start);
- unsigned long end = PHYS_PFN(range_end);
+ unsigned long start = PFN_UP(range_start);
+ unsigned long end = PFN_DOWN(range_end);
/* Ignore complete lowmem entries */
if (end <= max_low)
diff --git a/arch/arm/probes/kprobes/opt-arm.c b/arch/arm/probes/kprobes/opt-arm.c
index 7a449df..c78180172 100644
--- a/arch/arm/probes/kprobes/opt-arm.c
+++ b/arch/arm/probes/kprobes/opt-arm.c
@@ -85,21 +85,21 @@
"optprobe_template_end:\n");
#define TMPL_VAL_IDX \
- ((unsigned long *)&optprobe_template_val - (unsigned long *)&optprobe_template_entry)
+ ((unsigned long *)optprobe_template_val - (unsigned long *)optprobe_template_entry)
#define TMPL_CALL_IDX \
- ((unsigned long *)&optprobe_template_call - (unsigned long *)&optprobe_template_entry)
+ ((unsigned long *)optprobe_template_call - (unsigned long *)optprobe_template_entry)
#define TMPL_END_IDX \
- ((unsigned long *)&optprobe_template_end - (unsigned long *)&optprobe_template_entry)
+ ((unsigned long *)optprobe_template_end - (unsigned long *)optprobe_template_entry)
#define TMPL_ADD_SP \
- ((unsigned long *)&optprobe_template_add_sp - (unsigned long *)&optprobe_template_entry)
+ ((unsigned long *)optprobe_template_add_sp - (unsigned long *)optprobe_template_entry)
#define TMPL_SUB_SP \
- ((unsigned long *)&optprobe_template_sub_sp - (unsigned long *)&optprobe_template_entry)
+ ((unsigned long *)optprobe_template_sub_sp - (unsigned long *)optprobe_template_entry)
#define TMPL_RESTORE_BEGIN \
- ((unsigned long *)&optprobe_template_restore_begin - (unsigned long *)&optprobe_template_entry)
+ ((unsigned long *)optprobe_template_restore_begin - (unsigned long *)optprobe_template_entry)
#define TMPL_RESTORE_ORIGN_INSN \
- ((unsigned long *)&optprobe_template_restore_orig_insn - (unsigned long *)&optprobe_template_entry)
+ ((unsigned long *)optprobe_template_restore_orig_insn - (unsigned long *)optprobe_template_entry)
#define TMPL_RESTORE_END \
- ((unsigned long *)&optprobe_template_restore_end - (unsigned long *)&optprobe_template_entry)
+ ((unsigned long *)optprobe_template_restore_end - (unsigned long *)optprobe_template_entry)
/*
* ARM can always optimize an instruction when using ARM ISA, except
@@ -234,7 +234,7 @@
}
/* Copy arch-dep-instance from template. */
- memcpy(code, (unsigned long *)&optprobe_template_entry,
+ memcpy(code, (unsigned long *)optprobe_template_entry,
TMPL_END_IDX * sizeof(kprobe_opcode_t));
/* Adjust buffer according to instruction. */
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index f858c35..1515f6f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -636,6 +636,26 @@
If unsure, say Y.
+config ARM64_ERRATUM_1508412
+ bool "Cortex-A77: 1508412: workaround deadlock on sequence of NC/Device load and store exclusive or PAR read"
+ default y
+ help
+ This option adds a workaround for Arm Cortex-A77 erratum 1508412.
+
+ Affected Cortex-A77 cores (r0p0, r1p0) could deadlock on a sequence
+ of a store-exclusive or read of PAR_EL1 and a load with device or
+ non-cacheable memory attributes. The workaround depends on a firmware
+ counterpart.
+
+ KVM guests must also have the workaround implemented or they can
+ deadlock the system.
+
+ Work around the issue by inserting DMB SY barriers around PAR_EL1
+ register reads and warning KVM users. The DMB barrier is sufficient
+ to prevent a speculative PAR_EL1 read.
+
+ If unsure, say Y.
+
config CAVIUM_ERRATUM_22375
bool "Cavium erratum 22375, 24313"
default y
@@ -982,7 +1002,7 @@
config NODES_SHIFT
int "Maximum NUMA Nodes (as a power of 2)"
range 1 10
- default "2"
+ default "4"
depends on NEED_MULTIPLE_NODES
help
Specify the maximum number of NUMA Nodes available on the target
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index 6f2494d..5c4ac1c9 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -54,6 +54,7 @@
config ARCH_BERLIN
bool "Marvell Berlin SoC Family"
select DW_APB_ICTL
+ select DW_APB_TIMER_OF
select GPIOLIB
select PINCTRL
help
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts
index 3ea5182..e5e840b 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts
@@ -105,7 +105,7 @@
&emac {
pinctrl-names = "default";
pinctrl-0 = <&rgmii_pins>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
phy-handle = <&ext_rgmii_phy>;
phy-supply = <®_dc1sw>;
status = "okay";
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts
index d894ec5..70e3174 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts
@@ -120,7 +120,7 @@
&emac {
pinctrl-names = "default";
pinctrl-0 = <&rgmii_pins>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
phy-handle = <&ext_rgmii_phy>;
phy-supply = <®_gmac_3v3>;
status = "okay";
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts
index b26181c..b54099b 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts
@@ -13,7 +13,7 @@
&emac {
pinctrl-names = "default";
pinctrl-0 = <&rgmii_pins>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-txid";
phy-handle = <&ext_rgmii_phy>;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts
index 3ab0f03..0494bfa 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts
@@ -122,9 +122,6 @@
status = "okay";
port {
- #address-cells = <1>;
- #size-cells = <0>;
-
csi_ep: endpoint {
remote-endpoint = <&ov5640_ep>;
bus-width = <8>;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts
index df1b926..6e30a56 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts
@@ -36,7 +36,7 @@
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <®_gmac_3v3>;
phy-handle = <&ext_rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
/delete-property/ allwinner,leds-active-low;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts
index 7d7aad1..8bf2db9 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts
@@ -123,7 +123,7 @@
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <®_gmac_3v3>;
phy-handle = <&ext_rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts
index cb44bfa..33ab440 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts
@@ -124,7 +124,7 @@
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <®_gmac_3v3>;
phy-handle = <&ext_rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
index 3f7ceeb..7c9dbde 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
@@ -97,7 +97,7 @@
&emac {
pinctrl-names = "default";
pinctrl-0 = <&ext_rgmii_pins>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
phy-handle = <&ext_rgmii_phy>;
phy-supply = <®_aldo2>;
status = "okay";
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts
index af85b20..961732c 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts
@@ -100,7 +100,7 @@
&emac {
pinctrl-names = "default";
pinctrl-0 = <&ext_rgmii_pins>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
phy-handle = <&ext_rgmii_phy>;
phy-supply = <®_gmac_3v3>;
allwinner,rx-delay-ps = <200>;
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
index feadd21..46e558a 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
@@ -159,7 +159,7 @@
flash@0 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "n25q00a";
+ compatible = "micron,mt25qu02g", "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <100000000>;
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts
index c079667..f9b4a39 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts
@@ -192,7 +192,7 @@
flash@0 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "n25q00a";
+ compatible = "micron,mt25qu02g", "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <100000000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts b/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts
index cb1360a..7740f97 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts
@@ -584,3 +584,9 @@
pinctrl-0 = <&uart_ao_a_pins>;
pinctrl-names = "default";
};
+
+&usb {
+ status = "okay";
+ dr_mode = "otg";
+ vbus-supply = <&usb_pwr>;
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
index b9efc84..724ee179b 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
@@ -171,6 +171,46 @@
#size-cells = <2>;
ranges;
+ usb: usb@ffe09080 {
+ compatible = "amlogic,meson-axg-usb-ctrl";
+ reg = <0x0 0xffe09080 0x0 0x20>;
+ interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+
+ clocks = <&clkc CLKID_USB>, <&clkc CLKID_USB1_DDR_BRIDGE>;
+ clock-names = "usb_ctrl", "ddr";
+ resets = <&reset RESET_USB_OTG>;
+
+ dr_mode = "otg";
+
+ phys = <&usb2_phy1>;
+ phy-names = "usb2-phy1";
+
+ dwc2: usb@ff400000 {
+ compatible = "amlogic,meson-g12a-usb", "snps,dwc2";
+ reg = <0x0 0xff400000 0x0 0x40000>;
+ interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clkc CLKID_USB1>;
+ clock-names = "otg";
+ phys = <&usb2_phy1>;
+ dr_mode = "peripheral";
+ g-rx-fifo-size = <192>;
+ g-np-tx-fifo-size = <128>;
+ g-tx-fifo-size = <128 128 16 16 16>;
+ };
+
+ dwc3: usb@ff500000 {
+ compatible = "snps,dwc3";
+ reg = <0x0 0xff500000 0x0 0x100000>;
+ interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+ dr_mode = "host";
+ maximum-speed = "high-speed";
+ snps,dis_u2_susphy_quirk;
+ };
+ };
+
ethmac: ethernet@ff3f0000 {
compatible = "amlogic,meson-axg-dwmac",
"snps,dwmac-3.70a",
@@ -187,6 +227,8 @@
"timing-adjustment";
rx-fifo-depth = <4096>;
tx-fifo-depth = <2048>;
+ resets = <&reset RESET_ETHERNET>;
+ reset-names = "stmmaceth";
status = "disabled";
};
@@ -1734,6 +1776,16 @@
clock-names = "core", "clkin0", "clkin1";
resets = <&reset RESET_SD_EMMC_C>;
};
+
+ usb2_phy1: phy@9020 {
+ compatible = "amlogic,meson-gxl-usb2-phy";
+ #phy-cells = <0>;
+ reg = <0x0 0x9020 0x0 0x20>;
+ clocks = <&clkc CLKID_USB>;
+ clock-names = "phy";
+ resets = <&reset RESET_USB_OTG>;
+ reset-names = "phy";
+ };
};
sram: sram@fffc0000 {
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
index 1e83ec5..8514fe6 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
@@ -209,7 +209,7 @@
};
ethmac: ethernet@ff3f0000 {
- compatible = "amlogic,meson-axg-dwmac",
+ compatible = "amlogic,meson-g12a-dwmac",
"snps,dwmac-3.70a",
"snps,dwmac";
reg = <0x0 0xff3f0000 0x0 0x10000>,
@@ -224,6 +224,8 @@
"timing-adjustment";
rx-fifo-depth = <4096>;
tx-fifo-depth = <2048>;
+ resets = <&reset RESET_ETHERNET>;
+ reset-names = "stmmaceth";
status = "disabled";
mdio0: mdio {
@@ -282,6 +284,8 @@
hwrng: rng@218 {
compatible = "amlogic,meson-rng";
reg = <0x0 0x218 0x0 0x4>;
+ clocks = <&clkc CLKID_RNG0>;
+ clock-names = "core";
};
};
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2-plus.dts b/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2-plus.dts
index 5de2815..ce1198a 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2-plus.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2-plus.dts
@@ -19,7 +19,7 @@
regulator-min-microvolt = <680000>;
regulator-max-microvolt = <1040000>;
- pwms = <&pwm_AO_cd 1 1500 0>;
+ pwms = <&pwm_ab 0 1500 0>;
};
&vddcpu_b {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index 0edd137..726b91d 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -13,6 +13,7 @@
#include <dt-bindings/interrupt-controller/irq.h>
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/power/meson-gxbb-power.h>
+#include <dt-bindings/reset/amlogic,meson-gxbb-reset.h>
#include <dt-bindings/thermal/thermal.h>
/ {
@@ -575,6 +576,8 @@
interrupt-names = "macirq";
rx-fifo-depth = <4096>;
tx-fifo-depth = <2048>;
+ resets = <&reset RESET_ETHERNET>;
+ reset-names = "stmmaceth";
power-domains = <&pwrc PWRC_GXBB_ETHERNET_MEM_ID>;
status = "disabled";
};
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts
index f46eb47..8161dd2 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts
@@ -75,6 +75,7 @@
&enetc_port0 {
phy-handle = <&phy0>;
phy-connection-type = "sgmii";
+ managed = "in-band-status";
status = "okay";
mdio {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
index 73e4f94..7a6fb7e 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
@@ -1012,6 +1012,7 @@
compatible = "fsl,ls1028a-rcpm", "fsl,qoriq-rcpm-2.1+";
reg = <0x0 0x1e34040 0x0 0x1c>;
#fsl,rcpm-wakeup-cells = <7>;
+ little-endian;
};
ftm_alarm0: timer@2800000 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
index ff58052..692d8f4 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
@@ -805,6 +805,7 @@
compatible = "fsl,ls1088a-rcpm", "fsl,qoriq-rcpm-2.1+";
reg = <0x0 0x1e34040 0x0 0x18>;
#fsl,rcpm-wakeup-cells = <6>;
+ little-endian;
};
ftm_alarm0: timer@2800000 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
index bf72918..e7abb74 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
@@ -892,6 +892,7 @@
compatible = "fsl,ls208xa-rcpm", "fsl,qoriq-rcpm-2.1+";
reg = <0x0 0x1e34040 0x0 0x18>;
#fsl,rcpm-wakeup-cells = <6>;
+ little-endian;
};
ftm_alarm0: timer@2800000 {
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi
index 6de86a4..b88c3c9 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi
@@ -72,6 +72,7 @@
pmic@4b {
compatible = "rohm,bd71847";
reg = <0x4b>;
+ pinctrl-names = "default";
pinctrl-0 = <&pinctrl_pmic>;
interrupt-parent = <&gpio1>;
interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
@@ -210,6 +211,7 @@
host-wakeup-gpios = <&gpio2 8 GPIO_ACTIVE_HIGH>;
device-wakeup-gpios = <&gpio2 7 GPIO_ACTIVE_HIGH>;
clocks = <&osc_32k>;
+ max-speed = <4000000>;
clock-names = "extclk";
};
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
index f305a53..521eb3a 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
@@ -121,6 +121,7 @@
pmic@4b {
compatible = "rohm,bd71847";
reg = <0x4b>;
+ pinctrl-names = "default";
pinctrl-0 = <&pinctrl_pmic>;
interrupt-parent = <&gpio1>;
interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi
index 4107fe9..4908252 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi
@@ -135,13 +135,10 @@
pmic@4b {
compatible = "rohm,bd71847";
reg = <0x4b>;
+ pinctrl-names = "default";
pinctrl-0 = <&pinctrl_pmic>;
interrupt-parent = <&gpio2>;
- /*
- * The interrupt is not correct. It should be level low,
- * however with internal pull up this causes IRQ storm.
- */
- interrupts = <8 IRQ_TYPE_EDGE_RISING>;
+ interrupts = <8 IRQ_TYPE_LEVEL_LOW>;
rohm,reset-snvs-powered;
#clock-cells = <0>;
@@ -398,7 +395,7 @@
pinctrl_pmic: pmicirqgrp {
fsl,pins = <
- MX8MM_IOMUXC_SD1_DATA6_GPIO2_IO8 0x41
+ MX8MM_IOMUXC_SD1_DATA6_GPIO2_IO8 0x141
>;
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
index b83f400..05ee062 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
@@ -129,7 +129,7 @@
opp-1600000000 {
opp-hz = /bits/ 64 <1600000000>;
- opp-microvolt = <900000>;
+ opp-microvolt = <950000>;
opp-supported-hw = <0xc>, <0x7>;
clock-latency-ns = <150000>;
opp-suspend;
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts
index 46e76cf..7dfee71 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts
@@ -53,6 +53,7 @@
pmic@4b {
compatible = "rohm,bd71847";
reg = <0x4b>;
+ pinctrl-names = "default";
pinctrl-0 = <&pinctrl_pmic>;
interrupt-parent = <&gpio1>;
interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-evk.dts
index 707d848..8311b95 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mn-evk.dts
@@ -18,6 +18,7 @@
pmic: pmic@25 {
compatible = "nxp,pca9450b";
reg = <0x25>;
+ pinctrl-names = "default";
pinctrl-0 = <&pinctrl_pmic>;
interrupt-parent = <&gpio1>;
interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi
index a2d0190..7f356ed 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi
@@ -116,13 +116,10 @@
pmic@4b {
compatible = "rohm,bd71847";
reg = <0x4b>;
+ pinctrl-names = "default";
pinctrl-0 = <&pinctrl_pmic>;
interrupt-parent = <&gpio2>;
- /*
- * The interrupt is not correct. It should be level low,
- * however with internal pull up this causes IRQ storm.
- */
- interrupts = <8 IRQ_TYPE_EDGE_RISING>;
+ interrupts = <8 IRQ_TYPE_LEVEL_LOW>;
rohm,reset-snvs-powered;
regulators {
@@ -388,7 +385,7 @@
pinctrl_pmic: pmicirqgrp {
fsl,pins = <
- MX8MN_IOMUXC_SD1_DATA6_GPIO2_IO8 0x101
+ MX8MN_IOMUXC_SD1_DATA6_GPIO2_IO8 0x141
>;
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
index 746faf1..16c7202 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
@@ -790,28 +790,6 @@
#index-cells = <1>;
reg = <0x32e40200 0x200>;
};
-
- usbotg2: usb@32e50000 {
- compatible = "fsl,imx8mn-usb", "fsl,imx7d-usb";
- reg = <0x32e50000 0x200>;
- interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>;
- clocks = <&clk IMX8MN_CLK_USB1_CTRL_ROOT>;
- clock-names = "usb1_ctrl_root_clk";
- assigned-clocks = <&clk IMX8MN_CLK_USB_BUS>,
- <&clk IMX8MN_CLK_USB_CORE_REF>;
- assigned-clock-parents = <&clk IMX8MN_SYS_PLL2_500M>,
- <&clk IMX8MN_SYS_PLL1_100M>;
- fsl,usbphy = <&usbphynop2>;
- fsl,usbmisc = <&usbmisc2 0>;
- status = "disabled";
- };
-
- usbmisc2: usbmisc@32e50200 {
- compatible = "fsl,imx8mn-usbmisc", "fsl,imx7d-usbmisc";
- #index-cells = <1>;
- reg = <0x32e50200 0x200>;
- };
-
};
dma_apbh: dma-controller@33000000 {
@@ -876,12 +854,4 @@
assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>;
clock-names = "main_clk";
};
-
- usbphynop2: usbphynop2 {
- compatible = "usb-nop-xceiv";
- clocks = <&clk IMX8MN_CLK_USB_PHY_REF>;
- assigned-clocks = <&clk IMX8MN_CLK_USB_PHY_REF>;
- assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>;
- clock-names = "main_clk";
- };
};
diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi
index 8bc6caa..4338db1 100644
--- a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi
+++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi
@@ -19,6 +19,7 @@
clock-names = "fmanclk";
fsl,qman-channel-range = <0x800 0x10>;
ptimer-handle = <&ptp_timer0>;
+ dma-coherent;
muram@0 {
compatible = "fsl,fman-muram";
diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts
index 96c50d4..a7a83f2 100644
--- a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts
+++ b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts
@@ -110,7 +110,7 @@
flash@0 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "mt25qu02g";
+ compatible = "micron,mt25qu02g", "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <100000000>;
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7-emmc.dts b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7-emmc.dts
index 03733fd..215d2f7 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7-emmc.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7-emmc.dts
@@ -20,17 +20,23 @@
compatible = "globalscale,espressobin-v7-emmc", "globalscale,espressobin-v7",
"globalscale,espressobin", "marvell,armada3720",
"marvell,armada3710";
+
+ aliases {
+ /* ethernet1 is wan port */
+ ethernet1 = &switch0port3;
+ ethernet3 = &switch0port1;
+ };
};
&switch0 {
ports {
- port@1 {
+ switch0port1: port@1 {
reg = <1>;
label = "lan1";
phy-handle = <&switch0phy0>;
};
- port@3 {
+ switch0port3: port@3 {
reg = <3>;
label = "wan";
phy-handle = <&switch0phy2>;
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7.dts b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7.dts
index 8570c5f..b6f4af8 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7.dts
@@ -19,17 +19,23 @@
model = "Globalscale Marvell ESPRESSOBin Board V7";
compatible = "globalscale,espressobin-v7", "globalscale,espressobin",
"marvell,armada3720", "marvell,armada3710";
+
+ aliases {
+ /* ethernet1 is wan port */
+ ethernet1 = &switch0port3;
+ ethernet3 = &switch0port1;
+ };
};
&switch0 {
ports {
- port@1 {
+ switch0port1: port@1 {
reg = <1>;
label = "lan1";
phy-handle = <&switch0phy0>;
};
- port@3 {
+ switch0port3: port@3 {
reg = <3>;
label = "wan";
phy-handle = <&switch0phy2>;
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi
index b97218c..0775c16 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi
@@ -13,6 +13,10 @@
/ {
aliases {
ethernet0 = ð0;
+ /* for dsa slave device */
+ ethernet1 = &switch0port1;
+ ethernet2 = &switch0port2;
+ ethernet3 = &switch0port3;
serial0 = &uart0;
serial1 = &uart1;
};
@@ -120,7 +124,7 @@
#address-cells = <1>;
#size-cells = <0>;
- port@0 {
+ switch0port0: port@0 {
reg = <0>;
label = "cpu";
ethernet = <ð0>;
@@ -131,19 +135,19 @@
};
};
- port@1 {
+ switch0port1: port@1 {
reg = <1>;
label = "wan";
phy-handle = <&switch0phy0>;
};
- port@2 {
+ switch0port2: port@2 {
reg = <2>;
label = "lan0";
phy-handle = <&switch0phy1>;
};
- port@3 {
+ switch0port3: port@3 {
reg = <3>;
label = "lan1";
phy-handle = <&switch0phy2>;
diff --git a/arch/arm64/boot/dts/renesas/r8a774e1.dtsi b/arch/arm64/boot/dts/renesas/r8a774e1.dtsi
index 9cbf963..c296434 100644
--- a/arch/arm64/boot/dts/renesas/r8a774e1.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a774e1.dtsi
@@ -28,6 +28,12 @@
clock-frequency = <0>;
};
+ audio_clk_b: audio_clk_b {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <0>;
+ };
+
audio_clk_c: audio_clk_c {
compatible = "fixed-clock";
#clock-cells = <0>;
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 17a2df6..5cfe3cf 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -500,6 +500,7 @@
CONFIG_GPIO_DWAPB=y
CONFIG_GPIO_MB86S7X=y
CONFIG_GPIO_MPC8XXX=y
+CONFIG_GPIO_MXC=y
CONFIG_GPIO_PL061=y
CONFIG_GPIO_RCAR=y
CONFIG_GPIO_UNIPHIER=y
diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h
index e3d47b52..ec7720d 100644
--- a/arch/arm64/include/asm/brk-imm.h
+++ b/arch/arm64/include/asm/brk-imm.h
@@ -10,6 +10,7 @@
* #imm16 values used for BRK instruction generation
* 0x004: for installing kprobes
* 0x005: for installing uprobes
+ * 0x006: for kprobe software single-step
* Allowed values for kgdb are 0x400 - 0x7ff
* 0x100: for triggering a fault on purpose (reserved)
* 0x400: for dynamic BRK instruction
@@ -19,6 +20,7 @@
*/
#define KPROBES_BRK_IMM 0x004
#define UPROBES_BRK_IMM 0x005
+#define KPROBES_BRK_SS_IMM 0x006
#define FAULT_BRK_IMM 0x100
#define KGDB_DYN_DBG_BRK_IMM 0x400
#define KGDB_COMPILED_DBG_BRK_IMM 0x401
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index 0ac3e06..63d43b5 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -24,6 +24,7 @@
#define CTR_L1IP(ctr) (((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
#define ICACHE_POLICY_VPIPT 0
+#define ICACHE_POLICY_RESERVED 1
#define ICACHE_POLICY_VIPT 2
#define ICACHE_POLICY_PIPT 3
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 42868db..e7d9899 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -65,7 +65,8 @@
#define ARM64_HAS_ARMv8_4_TTL 55
#define ARM64_HAS_TLB_RANGE 56
#define ARM64_MTE 57
+#define ARM64_WORKAROUND_1508412 58
-#define ARM64_NCAPS 58
+#define ARM64_NCAPS 59
#endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index f7e7144..da250e4 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -268,6 +268,8 @@
/*
* CPU feature detected at boot time based on feature of one or more CPUs.
* All possible conflicts for a late CPU are ignored.
+ * NOTE: this means that a late CPU with the feature will *not* cause the
+ * capability to be advertised by cpus_have_*cap()!
*/
#define ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE \
(ARM64_CPUCAP_SCOPE_LOCAL_CPU | \
@@ -375,6 +377,23 @@
return false;
}
+static __always_inline bool is_vhe_hyp_code(void)
+{
+ /* Only defined for code run in VHE hyp context */
+ return __is_defined(__KVM_VHE_HYPERVISOR__);
+}
+
+static __always_inline bool is_nvhe_hyp_code(void)
+{
+ /* Only defined for code run in NVHE hyp context */
+ return __is_defined(__KVM_NVHE_HYPERVISOR__);
+}
+
+static __always_inline bool is_hyp_code(void)
+{
+ return is_vhe_hyp_code() || is_nvhe_hyp_code();
+}
+
extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS];
extern struct static_key_false arm64_const_caps_ready;
@@ -428,22 +447,6 @@
}
/*
- * Test for a capability, possibly with a runtime check.
- *
- * Before capabilities are finalized, this behaves as cpus_have_cap().
- * After capabilities are finalized, this is patched to avoid a runtime check.
- *
- * @num must be a compile-time constant.
- */
-static __always_inline bool cpus_have_const_cap(int num)
-{
- if (system_capabilities_finalized())
- return __cpus_have_const_cap(num);
- else
- return cpus_have_cap(num);
-}
-
-/*
* Test for a capability without a runtime check.
*
* Before capabilities are finalized, this will BUG().
@@ -459,6 +462,27 @@
BUG();
}
+/*
+ * Test for a capability, possibly with a runtime check for non-hyp code.
+ *
+ * For hyp code, this behaves the same as cpus_have_final_cap().
+ *
+ * For non-hyp code:
+ * Before capabilities are finalized, this behaves as cpus_have_cap().
+ * After capabilities are finalized, this is patched to avoid a runtime check.
+ *
+ * @num must be a compile-time constant.
+ */
+static __always_inline bool cpus_have_const_cap(int num)
+{
+ if (is_hyp_code())
+ return cpus_have_final_cap(num);
+ else if (system_capabilities_finalized())
+ return __cpus_have_const_cap(num);
+ else
+ return cpus_have_cap(num);
+}
+
static inline void cpus_set_cap(unsigned int num)
{
if (num >= ARM64_NCAPS) {
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 7219cdd..ef5b040 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -71,6 +71,7 @@
#define ARM_CPU_PART_CORTEX_A55 0xD05
#define ARM_CPU_PART_CORTEX_A76 0xD0B
#define ARM_CPU_PART_NEOVERSE_N1 0xD0C
+#define ARM_CPU_PART_CORTEX_A77 0xD0D
#define APM_CPU_PART_POTENZA 0x000
@@ -85,6 +86,8 @@
#define QCOM_CPU_PART_FALKOR_V1 0x800
#define QCOM_CPU_PART_FALKOR 0xC00
#define QCOM_CPU_PART_KRYO 0x200
+#define QCOM_CPU_PART_KRYO_2XX_GOLD 0x800
+#define QCOM_CPU_PART_KRYO_2XX_SILVER 0x801
#define QCOM_CPU_PART_KRYO_3XX_SILVER 0x803
#define QCOM_CPU_PART_KRYO_4XX_GOLD 0x804
#define QCOM_CPU_PART_KRYO_4XX_SILVER 0x805
@@ -105,6 +108,7 @@
#define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55)
#define MIDR_CORTEX_A76 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76)
#define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1)
+#define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77)
#define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
#define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
@@ -114,6 +118,8 @@
#define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
#define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR)
#define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
+#define MIDR_QCOM_KRYO_2XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_GOLD)
+#define MIDR_QCOM_KRYO_2XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_SILVER)
#define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER)
#define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD)
#define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER)
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 0b298f4..657c921 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -53,6 +53,7 @@
/* kprobes BRK opcodes with ESR encoding */
#define BRK64_OPCODE_KPROBES (AARCH64_BREAK_MON | (KPROBES_BRK_IMM << 5))
+#define BRK64_OPCODE_KPROBES_SS (AARCH64_BREAK_MON | (KPROBES_BRK_SS_IMM << 5))
/* uprobes BRK opcodes with ESR encoding */
#define BRK64_OPCODE_UPROBES (AARCH64_BREAK_MON | (UPROBES_BRK_IMM << 5))
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
index 97e511d..8699ce3 100644
--- a/arch/arm64/include/asm/kprobes.h
+++ b/arch/arm64/include/asm/kprobes.h
@@ -16,7 +16,7 @@
#include <linux/percpu.h>
#define __ARCH_WANT_KPROBES_INSN_SLOT
-#define MAX_INSN_SIZE 1
+#define MAX_INSN_SIZE 2
#define flush_insn_slot(p) do { } while (0)
#define kretprobe_blacklist_size 0
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 0aecbab..0cd9f0f 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -118,6 +118,8 @@
*/
unsigned long *pmu_filter;
unsigned int pmuver;
+
+ u8 pfr0_csv2;
};
struct kvm_vcpu_fault_info {
@@ -239,6 +241,7 @@
#define cp14_DBGWCR0 (DBGWCR0_EL1 * 2)
#define cp14_DBGWVR0 (DBGWVR0_EL1 * 2)
#define cp14_DBGDCCINT (MDCCINT_EL1 * 2)
+#define cp14_DBGVCR (DBGVCR32_EL2 * 2)
#define NR_COPRO_REGS (NR_SYS_REGS * 2)
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index d52c1b3..e2ef4c2 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -372,6 +372,8 @@
#define SYS_CONTEXTIDR_EL1 sys_reg(3, 0, 13, 0, 1)
#define SYS_TPIDR_EL1 sys_reg(3, 0, 13, 0, 4)
+#define SYS_SCXTNUM_EL1 sys_reg(3, 0, 13, 0, 7)
+
#define SYS_CNTKCTL_EL1 sys_reg(3, 0, 14, 1, 0)
#define SYS_CCSIDR_EL1 sys_reg(3, 1, 0, 0, 0)
@@ -404,6 +406,8 @@
#define SYS_TPIDR_EL0 sys_reg(3, 3, 13, 0, 2)
#define SYS_TPIDRRO_EL0 sys_reg(3, 3, 13, 0, 3)
+#define SYS_SCXTNUM_EL0 sys_reg(3, 3, 13, 0, 7)
+
/* Definitions for system register interface to AMU for ARMv8.4 onwards */
#define SYS_AM_EL0(crm, op2) sys_reg(3, 3, 13, (crm), (op2))
#define SYS_AMCR_EL0 SYS_AM_EL0(2, 0)
@@ -1007,6 +1011,7 @@
#include <linux/build_bug.h>
#include <linux/types.h>
+#include <asm/alternative.h>
#define __DEFINE_MRS_MSR_S_REGNUM \
" .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n" \
@@ -1095,6 +1100,14 @@
write_sysreg_s(__scs_new, sysreg); \
} while (0)
+#define read_sysreg_par() ({ \
+ u64 par; \
+ asm(ALTERNATIVE("nop", "dmb sy", ARM64_WORKAROUND_1508412)); \
+ par = read_sysreg(par_el1); \
+ asm(ALTERNATIVE("nop", "dmb sy", ARM64_WORKAROUND_1508412)); \
+ par; \
+})
+
#endif
#endif /* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 09977ac..6069be5 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -86,13 +86,12 @@
static __always_inline bool has_vhe(void)
{
/*
- * The following macros are defined for code specic to VHE/nVHE.
- * If has_vhe() is inlined into those compilation units, it can
- * be determined statically. Otherwise fall back to caps.
+ * Code only run in VHE/NVHE hyp context can assume VHE is present or
+ * absent. Otherwise fall back to caps.
*/
- if (__is_defined(__KVM_VHE_HYPERVISOR__))
+ if (is_vhe_hyp_code())
return true;
- else if (__is_defined(__KVM_NVHE_HYPERVISOR__))
+ else if (is_nvhe_hyp_code())
return false;
else
return cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN);
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 24d75af..cafaf0d 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -299,6 +299,8 @@
MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4),
/* Brahma-B53 r0p[0] */
MIDR_REV(MIDR_BRAHMA_B53, 0, 0),
+ /* Kryo2XX Silver rAp4 */
+ MIDR_REV(MIDR_QCOM_KRYO_2XX_SILVER, 0xa, 0x4),
{},
};
#endif
@@ -523,6 +525,16 @@
.cpu_enable = cpu_enable_trap_ctr_access,
},
#endif
+#ifdef CONFIG_ARM64_ERRATUM_1508412
+ {
+ /* we depend on the firmware portion for correctness */
+ .desc = "ARM erratum 1508412 (kernel portion)",
+ .capability = ARM64_WORKAROUND_1508412,
+ ERRATA_MIDR_RANGE(MIDR_CORTEX_A77,
+ 0, 0,
+ 1, 0),
+ },
+#endif
{
}
};
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index dcc165b..6f36c4f 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1337,6 +1337,8 @@
MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
+ MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_GOLD),
+ MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
{ /* sentinel */ }
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 6a7bb372..77605ae 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -34,10 +34,10 @@
static struct cpuinfo_arm64 boot_cpu_data;
static const char *icache_policy_str[] = {
- [0 ... ICACHE_POLICY_PIPT] = "RESERVED/UNKNOWN",
+ [ICACHE_POLICY_VPIPT] = "VPIPT",
+ [ICACHE_POLICY_RESERVED] = "RESERVED/UNKNOWN",
[ICACHE_POLICY_VIPT] = "VIPT",
[ICACHE_POLICY_PIPT] = "PIPT",
- [ICACHE_POLICY_VPIPT] = "VPIPT",
};
unsigned long __icache_flags;
@@ -334,10 +334,11 @@
case ICACHE_POLICY_VPIPT:
set_bit(ICACHEF_VPIPT, &__icache_flags);
break;
- default:
+ case ICACHE_POLICY_RESERVED:
case ICACHE_POLICY_VIPT:
/* Assume aliasing */
set_bit(ICACHEF_ALIASING, &__icache_flags);
+ break;
}
pr_info("Detected %s I-cache on CPU%d\n", icache_policy_str[l1ip], cpu);
diff --git a/arch/arm64/kernel/efi-header.S b/arch/arm64/kernel/efi-header.S
index df67c0f..a71844f 100644
--- a/arch/arm64/kernel/efi-header.S
+++ b/arch/arm64/kernel/efi-header.S
@@ -147,6 +147,6 @@
* correctly at this alignment, we must ensure that .text is
* placed at a 4k boundary in the Image to begin with.
*/
- .align 12
+ .balign SEGMENT_ALIGN
efi_header_end:
.endm
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index f30007d..b295fb9 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -365,6 +365,9 @@
br x30
#endif
.else
+ /* Ensure any device/NC reads complete */
+ alternative_insn nop, "dmb sy", ARM64_WORKAROUND_1508412
+
eret
.endif
sb
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 61684a5..c615b28 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -87,7 +87,6 @@
/* Kernel symbols needed for cpus_have_final/const_caps checks. */
KVM_NVHE_ALIAS(arm64_const_caps_ready);
KVM_NVHE_ALIAS(cpu_hwcap_keys);
-KVM_NVHE_ALIAS(cpu_hwcaps);
/* Static keys which are set if a vGIC trap should be handled in hyp. */
KVM_NVHE_ALIAS(vgic_v2_cpuif_trap);
diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c
index af9987c..9ec3469 100644
--- a/arch/arm64/kernel/kexec_image.c
+++ b/arch/arm64/kernel/kexec_image.c
@@ -43,7 +43,7 @@
u64 flags, value;
bool be_image, be_kernel;
struct kexec_buf kbuf;
- unsigned long text_offset;
+ unsigned long text_offset, kernel_segment_number;
struct kexec_segment *kernel_segment;
int ret;
@@ -88,11 +88,37 @@
/* Adjust kernel segment with TEXT_OFFSET */
kbuf.memsz += text_offset;
- ret = kexec_add_buffer(&kbuf);
- if (ret)
- return ERR_PTR(ret);
+ kernel_segment_number = image->nr_segments;
- kernel_segment = &image->segment[image->nr_segments - 1];
+ /*
+ * The location of the kernel segment may make it impossible to satisfy
+ * the other segment requirements, so we try repeatedly to find a
+ * location that will work.
+ */
+ while ((ret = kexec_add_buffer(&kbuf)) == 0) {
+ /* Try to load additional data */
+ kernel_segment = &image->segment[kernel_segment_number];
+ ret = load_other_segments(image, kernel_segment->mem,
+ kernel_segment->memsz, initrd,
+ initrd_len, cmdline);
+ if (!ret)
+ break;
+
+ /*
+ * We couldn't find space for the other segments; erase the
+ * kernel segment and try the next available hole.
+ */
+ image->nr_segments -= 1;
+ kbuf.buf_min = kernel_segment->mem + kernel_segment->memsz;
+ kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
+ }
+
+ if (ret) {
+ pr_err("Could not find any suitable kernel location!");
+ return ERR_PTR(ret);
+ }
+
+ kernel_segment = &image->segment[kernel_segment_number];
kernel_segment->mem += text_offset;
kernel_segment->memsz -= text_offset;
image->start = kernel_segment->mem;
@@ -101,12 +127,7 @@
kernel_segment->mem, kbuf.bufsz,
kernel_segment->memsz);
- /* Load additional data */
- ret = load_other_segments(image,
- kernel_segment->mem, kernel_segment->memsz,
- initrd, initrd_len, cmdline);
-
- return ERR_PTR(ret);
+ return NULL;
}
#ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index 5b0e67b..03210f6 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -240,6 +240,11 @@
return ret;
}
+/*
+ * Tries to add the initrd and DTB to the image. If it is not possible to find
+ * valid locations, this function will undo changes to the image and return non
+ * zero.
+ */
int load_other_segments(struct kimage *image,
unsigned long kernel_load_addr,
unsigned long kernel_size,
@@ -248,7 +253,8 @@
{
struct kexec_buf kbuf;
void *headers, *dtb = NULL;
- unsigned long headers_sz, initrd_load_addr = 0, dtb_len;
+ unsigned long headers_sz, initrd_load_addr = 0, dtb_len,
+ orig_segments = image->nr_segments;
int ret = 0;
kbuf.image = image;
@@ -334,6 +340,7 @@
return 0;
out_err:
+ image->nr_segments = orig_segments;
vfree(dtb);
return ret;
}
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 94e8718..f6f58e6 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -73,8 +73,7 @@
}
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
regs_user->regs = task_pt_regs(current);
regs_user->abi = perf_reg_abi(current);
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index deba7381..f11a1a1 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -36,25 +36,16 @@
static void __kprobes
post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *);
-static int __kprobes patch_text(kprobe_opcode_t *addr, u32 opcode)
-{
- void *addrs[1];
- u32 insns[1];
-
- addrs[0] = addr;
- insns[0] = opcode;
-
- return aarch64_insn_patch_text(addrs, insns, 1);
-}
-
static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
{
- /* prepare insn slot */
- patch_text(p->ainsn.api.insn, p->opcode);
+ kprobe_opcode_t *addr = p->ainsn.api.insn;
+ void *addrs[] = {addr, addr + 1};
+ u32 insns[] = {p->opcode, BRK64_OPCODE_KPROBES_SS};
- flush_icache_range((uintptr_t) (p->ainsn.api.insn),
- (uintptr_t) (p->ainsn.api.insn) +
- MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+ /* prepare insn slot */
+ aarch64_insn_patch_text(addrs, insns, 2);
+
+ flush_icache_range((uintptr_t)addr, (uintptr_t)(addr + MAX_INSN_SIZE));
/*
* Needs restoring of return address after stepping xol.
@@ -128,13 +119,18 @@
/* arm kprobe: install breakpoint in text */
void __kprobes arch_arm_kprobe(struct kprobe *p)
{
- patch_text(p->addr, BRK64_OPCODE_KPROBES);
+ void *addr = p->addr;
+ u32 insn = BRK64_OPCODE_KPROBES;
+
+ aarch64_insn_patch_text(&addr, &insn, 1);
}
/* disarm kprobe: remove breakpoint from text */
void __kprobes arch_disarm_kprobe(struct kprobe *p)
{
- patch_text(p->addr, p->opcode);
+ void *addr = p->addr;
+
+ aarch64_insn_patch_text(&addr, &p->opcode, 1);
}
void __kprobes arch_remove_kprobe(struct kprobe *p)
@@ -163,20 +159,15 @@
}
/*
- * Interrupts need to be disabled before single-step mode is set, and not
- * reenabled until after single-step mode ends.
- * Without disabling interrupt on local CPU, there is a chance of
- * interrupt occurrence in the period of exception return and start of
- * out-of-line single-step, that result in wrongly single stepping
- * into the interrupt handler.
+ * Mask all of DAIF while executing the instruction out-of-line, to keep things
+ * simple and avoid nesting exceptions. Interrupts do have to be disabled since
+ * the kprobe state is per-CPU and doesn't get migrated.
*/
static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb,
struct pt_regs *regs)
{
kcb->saved_irqflag = regs->pstate & DAIF_MASK;
- regs->pstate |= PSR_I_BIT;
- /* Unmask PSTATE.D for enabling software step exceptions. */
- regs->pstate &= ~PSR_D_BIT;
+ regs->pstate |= DAIF_MASK;
}
static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb,
@@ -219,10 +210,7 @@
slot = (unsigned long)p->ainsn.api.insn;
set_ss_context(kcb, slot); /* mark pending ss */
-
- /* IRQs and single stepping do not mix well. */
kprobes_save_local_irqflag(kcb, regs);
- kernel_enable_single_step(regs);
instruction_pointer_set(regs, slot);
} else {
/* insn simulation */
@@ -273,12 +261,8 @@
}
/* call post handler */
kcb->kprobe_status = KPROBE_HIT_SSDONE;
- if (cur->post_handler) {
- /* post_handler can hit breakpoint and single step
- * again, so we enable D-flag for recursive exception.
- */
+ if (cur->post_handler)
cur->post_handler(cur, regs, 0);
- }
reset_current_kprobe();
}
@@ -302,8 +286,6 @@
if (!instruction_pointer(regs))
BUG();
- kernel_disable_single_step();
-
if (kcb->kprobe_status == KPROBE_REENTER)
restore_previous_kprobe(kcb);
else
@@ -365,10 +347,6 @@
* pre-handler and it returned non-zero, it will
* modify the execution path and no need to single
* stepping. Let's just reset current kprobe and exit.
- *
- * pre_handler can hit a breakpoint and can step thru
- * before return, keep PSTATE D-flag enabled until
- * pre_handler return back.
*/
if (!p->pre_handler || !p->pre_handler(p, regs)) {
setup_singlestep(p, regs, kcb, 0);
@@ -399,7 +377,7 @@
}
static int __kprobes
-kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
+kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned int esr)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
int retval;
@@ -409,16 +387,15 @@
if (retval == DBG_HOOK_HANDLED) {
kprobes_restore_local_irqflag(kcb, regs);
- kernel_disable_single_step();
-
post_kprobe_handler(kcb, regs);
}
return retval;
}
-static struct step_hook kprobes_step_hook = {
- .fn = kprobe_single_step_handler,
+static struct break_hook kprobes_break_ss_hook = {
+ .imm = KPROBES_BRK_SS_IMM,
+ .fn = kprobe_breakpoint_ss_handler,
};
static int __kprobes
@@ -486,7 +463,7 @@
int __init arch_init_kprobes(void)
{
register_kernel_break_hook(&kprobes_break_hook);
- register_kernel_step_hook(&kprobes_step_hook);
+ register_kernel_break_hook(&kprobes_break_ss_hook);
return 0;
}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 4784011..a47a40e 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -522,14 +522,13 @@
bool prev32, next32;
u64 val;
- if (!(IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) &&
- cpus_have_const_cap(ARM64_WORKAROUND_1418040)))
+ if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040))
return;
prev32 = is_compat_thread(task_thread_info(prev));
next32 = is_compat_thread(task_thread_info(next));
- if (prev32 == next32)
+ if (prev32 == next32 || !this_cpu_has_cap(ARM64_WORKAROUND_1418040))
return;
val = read_sysreg(cntkctl_el1);
diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index 25f3c80..f6e4e37 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -118,6 +118,7 @@
MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
+ MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
{ /* sentinel */ }
@@ -135,8 +136,6 @@
return SPECTRE_VULNERABLE;
}
-#define SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED (1)
-
static enum mitigation_state spectre_v2_get_cpu_fw_mitigation_state(void)
{
int ret;
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 43ae4e0..62d2bda 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -66,7 +66,6 @@
static void cpu_psci_cpu_die(unsigned int cpu)
{
- int ret;
/*
* There are no known implementations of PSCI actually using the
* power state field, pass a sensible default for now.
@@ -74,9 +73,7 @@
u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN <<
PSCI_0_2_POWER_STATE_TYPE_SHIFT;
- ret = psci_ops.cpu_off(state);
-
- pr_crit("unable to power off CPU%u (%d)\n", cpu, ret);
+ psci_ops.cpu_off(state);
}
static int cpu_psci_cpu_kill(unsigned int cpu)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 82e75fc..18e9727 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -222,6 +222,7 @@
if (system_uses_irq_prio_masking())
init_gic_priority_masking();
+ rcu_cpu_starting(cpu);
preempt_disable();
trace_hardirqs_off();
@@ -412,6 +413,7 @@
/* Mark this CPU absent */
set_cpu_present(cpu, 0);
+ rcu_report_dead(cpu);
if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
update_cpu_boot_status(CPU_KILL_ME);
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 7f96a1a..79280c5 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -22,16 +22,21 @@
CC_COMPAT ?= $(CC)
CC_COMPAT += $(CC_COMPAT_CLANG_FLAGS)
+
+ifneq ($(LLVM),)
+LD_COMPAT ?= $(LD)
+else
+LD_COMPAT ?= $(CROSS_COMPILE_COMPAT)ld
+endif
else
CC_COMPAT ?= $(CROSS_COMPILE_COMPAT)gcc
+LD_COMPAT ?= $(CROSS_COMPILE_COMPAT)ld
endif
cc32-option = $(call try-run,\
$(CC_COMPAT) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
cc32-disable-warning = $(call try-run,\
$(CC_COMPAT) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
-cc32-ldoption = $(call try-run,\
- $(CC_COMPAT) $(1) -nostdlib -x c /dev/null -o "$$TMP",$(1),$(2))
cc32-as-instr = $(call try-run,\
printf "%b\n" "$(1)" | $(CC_COMPAT) $(VDSO_AFLAGS) -c -x assembler -o "$$TMP" -,$(2),$(3))
@@ -122,14 +127,10 @@
VDSO_CFLAGS += $(dmbinstr)
VDSO_AFLAGS += $(dmbinstr)
-VDSO_LDFLAGS := $(VDSO_CPPFLAGS)
# From arm vDSO Makefile
-VDSO_LDFLAGS += -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1
-VDSO_LDFLAGS += -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
-VDSO_LDFLAGS += -nostdlib -shared -mfloat-abi=soft
-VDSO_LDFLAGS += -Wl,--hash-style=sysv
-VDSO_LDFLAGS += -Wl,--build-id=sha1
-VDSO_LDFLAGS += $(call cc32-ldoption,-fuse-ld=bfd)
+VDSO_LDFLAGS += -Bsymbolic --no-undefined -soname=linux-vdso.so.1
+VDSO_LDFLAGS += -z max-page-size=4096 -z common-page-size=4096
+VDSO_LDFLAGS += -nostdlib -shared --hash-style=sysv --build-id=sha1
# Borrow vdsomunge.c from the arm vDSO
@@ -189,8 +190,8 @@
cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check)
quiet_cmd_vdsold = LD32 $@
- cmd_vdsold = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \
- -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@
+ cmd_vdsold = $(LD_COMPAT) $(VDSO_LDFLAGS) \
+ -T $(filter %.lds,$^) $(filter %.o,$^) -o $@
quiet_cmd_vdsocc = CC32 $@
cmd_vdsocc = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) -c -o $@ $<
quiet_cmd_vdsocc_gettimeofday = CC32 $@
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 6d78c04..1bda604 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -278,7 +278,7 @@
* explicitly check instead of blindly discarding.
*/
.plt : {
- *(.plt) *(.plt.*) *(.iplt) *(.igot)
+ *(.plt) *(.plt.*) *(.iplt) *(.igot .igot.plt)
}
ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!")
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index f56122e..c0ffb01 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -102,6 +102,20 @@
return vgic_present ? kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS;
}
+static void set_default_csv2(struct kvm *kvm)
+{
+ /*
+ * The default is to expose CSV2 == 1 if the HW isn't affected.
+ * Although this is a per-CPU feature, we make it global because
+ * asymmetric systems are just a nuisance.
+ *
+ * Userspace can override this as long as it doesn't promise
+ * the impossible.
+ */
+ if (arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED)
+ kvm->arch.pfr0_csv2 = 1;
+}
+
/**
* kvm_arch_init_vm - initializes a VM data structure
* @kvm: pointer to the KVM struct
@@ -127,6 +141,8 @@
/* The maximum number of VCPUs is limited by the host's GIC model */
kvm->arch.max_vcpus = kvm_arm_default_max_vcpus();
+ set_default_csv2(kvm);
+
return ret;
out_free_stage2_pgd:
kvm_free_stage2_pgd(&kvm->arch.mmu);
@@ -808,6 +824,25 @@
preempt_enable();
+ /*
+ * The ARMv8 architecture doesn't give the hypervisor
+ * a mechanism to prevent a guest from dropping to AArch32 EL0
+ * if implemented by the CPU. If we spot the guest in such
+ * state and that we decided it wasn't supposed to do so (like
+ * with the asymmetric AArch32 case), return to userspace with
+ * a fatal error.
+ */
+ if (!system_supports_32bit_el0() && vcpu_mode_is_32bit(vcpu)) {
+ /*
+ * As we have caught the guest red-handed, decide that
+ * it isn't fit for purpose anymore by making the vcpu
+ * invalid. The VMM can try and fix it by issuing a
+ * KVM_ARM_VCPU_INIT if it really wants to.
+ */
+ vcpu->arch.target = -1;
+ ret = ARM_EXCEPTION_IL;
+ }
+
ret = handle_exit(vcpu, ret);
}
@@ -1719,7 +1754,8 @@
return -ENODEV;
}
- if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE))
+ if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE) ||
+ cpus_have_final_cap(ARM64_WORKAROUND_1508412))
kvm_info("Guests without required CPU erratum workarounds can deadlock system!\n" \
"Only trusted guests should be used on this system.\n");
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 313a8fa3..1f875a8 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -140,9 +140,9 @@
* We do need to save/restore PAR_EL1 though, as we haven't
* saved the guest context yet, and we may return early...
*/
- par = read_sysreg(par_el1);
+ par = read_sysreg_par();
if (!__kvm_at("s1e1r", far))
- tmp = read_sysreg(par_el1);
+ tmp = read_sysreg_par();
else
tmp = SYS_PAR_EL1_F; /* back to the guest */
write_sysreg(par, par_el1);
@@ -421,7 +421,7 @@
if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
handle_tx2_tvm(vcpu))
- return true;
+ goto guest;
/*
* We trap the first access to the FP/SIMD to save the host context
@@ -431,13 +431,13 @@
* Similarly for trapped SVE accesses.
*/
if (__hyp_handle_fpsimd(vcpu))
- return true;
+ goto guest;
if (__hyp_handle_ptrauth(vcpu))
- return true;
+ goto guest;
if (!__populate_fault_info(vcpu))
- return true;
+ goto guest;
if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
bool valid;
@@ -452,7 +452,7 @@
int ret = __vgic_v2_perform_cpuif_access(vcpu);
if (ret == 1)
- return true;
+ goto guest;
/* Promote an illegal access to an SError.*/
if (ret == -1)
@@ -468,12 +468,17 @@
int ret = __vgic_v3_perform_cpuif_access(vcpu);
if (ret == 1)
- return true;
+ goto guest;
}
exit:
/* Return to the host kernel and handle the exit */
return false;
+
+guest:
+ /* Re-enter the guest */
+ asm(ALTERNATIVE("nop", "dmb sy", ARM64_WORKAROUND_1508412));
+ return true;
}
static inline void __kvm_unexpected_el2_exception(void)
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 7a98603..cce43bf 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -43,7 +43,7 @@
ctxt_sys_reg(ctxt, CONTEXTIDR_EL1) = read_sysreg_el1(SYS_CONTEXTIDR);
ctxt_sys_reg(ctxt, AMAIR_EL1) = read_sysreg_el1(SYS_AMAIR);
ctxt_sys_reg(ctxt, CNTKCTL_EL1) = read_sysreg_el1(SYS_CNTKCTL);
- ctxt_sys_reg(ctxt, PAR_EL1) = read_sysreg(par_el1);
+ ctxt_sys_reg(ctxt, PAR_EL1) = read_sysreg_par();
ctxt_sys_reg(ctxt, TPIDR_EL1) = read_sysreg(tpidr_el1);
ctxt_sys_reg(ctxt, SP_EL1) = read_sysreg(sp_el1);
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index ff9a0f5..ed27f06 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -17,8 +17,6 @@
get_host_ctxt x0, x1
- ALTERNATIVE(nop, SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
-
/* Store the host regs x2 and x3 */
stp x2, x3, [x0, #CPU_XREG_OFFSET(2)]
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 47224dc..b11a9d7 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -57,16 +57,25 @@
cmp x0, #HVC_STUB_HCALL_NR
b.lo __kvm_handle_stub_hvc
- /* Set tpidr_el2 for use by HYP to free a register */
- msr tpidr_el2, x2
+ // We only actively check bits [24:31], and everything
+ // else has to be zero, which we check at build time.
+#if (KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) & 0xFFFFFFFF00FFFFFF)
+#error Unexpected __KVM_HOST_SMCCC_FUNC___kvm_hyp_init value
+#endif
- mov x2, #KVM_HOST_SMCCC_FUNC(__kvm_hyp_init)
- cmp x0, x2
- b.eq 1f
+ ror x0, x0, #24
+ eor x0, x0, #((KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) >> 24) & 0xF)
+ ror x0, x0, #4
+ eor x0, x0, #((KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) >> 28) & 0xF)
+ cbz x0, 1f
mov x0, #SMCCC_RET_NOT_SUPPORTED
eret
-1: phys_to_ttbr x0, x1
+1:
+ /* Set tpidr_el2 for use by HYP to free a register */
+ msr tpidr_el2, x2
+
+ phys_to_ttbr x0, x1
alternative_if ARM64_HAS_CNP
orr x0, x0, #TTBR_CNP_BIT
alternative_else_nop_endif
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index a457a03..8ae8160 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -250,7 +250,7 @@
{
u64 spsr = read_sysreg_el2(SYS_SPSR);
u64 elr = read_sysreg_el2(SYS_ELR);
- u64 par = read_sysreg(par_el1);
+ u64 par = read_sysreg_par();
bool restore_host = true;
struct kvm_cpu_context *host_ctxt;
struct kvm_vcpu *vcpu;
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index 39ca71ab..fbde89a 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -128,7 +128,6 @@
struct tlb_inv_context cxt;
/* Switch to requested VMID */
- mmu = kern_hyp_va(mmu);
__tlb_switch_to_guest(mmu, &cxt);
__tlbi(vmalle1);
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 0cdf6e4..0271b4a 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -635,7 +635,7 @@
static bool stage2_pte_cacheable(kvm_pte_t pte)
{
- u64 memattr = FIELD_GET(KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR, pte);
+ u64 memattr = pte & KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR;
return memattr == PAGE_S2_MEMATTR(NORMAL);
}
@@ -846,7 +846,7 @@
u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
pgd_sz = kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE;
- pgt->pgd = alloc_pages_exact(pgd_sz, GFP_KERNEL | __GFP_ZERO);
+ pgt->pgd = alloc_pages_exact(pgd_sz, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
if (!pgt->pgd)
return -ENOMEM;
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index fe69de1..62546e2 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -215,7 +215,7 @@
{
u64 spsr = read_sysreg_el2(SYS_SPSR);
u64 elr = read_sysreg_el2(SYS_ELR);
- u64 par = read_sysreg(par_el1);
+ u64 par = read_sysreg_par();
__hyp_call_panic(spsr, elr, par);
unreachable();
diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c
index 9824025..25ea4ec 100644
--- a/arch/arm64/kvm/hypercalls.c
+++ b/arch/arm64/kvm/hypercalls.c
@@ -31,7 +31,7 @@
val = SMCCC_RET_SUCCESS;
break;
case SPECTRE_UNAFFECTED:
- val = SMCCC_RET_NOT_REQUIRED;
+ val = SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED;
break;
}
break;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 19aacc7..1a01da9 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -787,14 +787,28 @@
vma_shift = PAGE_SHIFT;
}
- if (vma_shift == PUD_SHIFT &&
- !fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE))
- vma_shift = PMD_SHIFT;
-
- if (vma_shift == PMD_SHIFT &&
- !fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) {
- force_pte = true;
+ switch (vma_shift) {
+#ifndef __PAGETABLE_PMD_FOLDED
+ case PUD_SHIFT:
+ if (fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE))
+ break;
+ fallthrough;
+#endif
+ case CONT_PMD_SHIFT:
+ vma_shift = PMD_SHIFT;
+ fallthrough;
+ case PMD_SHIFT:
+ if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE))
+ break;
+ fallthrough;
+ case CONT_PTE_SHIFT:
vma_shift = PAGE_SHIFT;
+ force_pte = true;
+ fallthrough;
+ case PAGE_SHIFT:
+ break;
+ default:
+ WARN_ONCE(1, "Unknown vma_shift %d", vma_shift);
}
vma_pagesize = 1UL << vma_shift;
@@ -839,6 +853,7 @@
if (kvm_is_device_pfn(pfn)) {
device = true;
+ force_pte = true;
} else if (logging_active && !write_fault) {
/*
* Only actually map the page as writable if this was a write
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index d9117bc..c1fac98 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -95,7 +95,7 @@
case AMAIR_EL1: *val = read_sysreg_s(SYS_AMAIR_EL12); break;
case CNTKCTL_EL1: *val = read_sysreg_s(SYS_CNTKCTL_EL12); break;
case ELR_EL1: *val = read_sysreg_s(SYS_ELR_EL12); break;
- case PAR_EL1: *val = read_sysreg_s(SYS_PAR_EL1); break;
+ case PAR_EL1: *val = read_sysreg_par(); break;
case DACR32_EL2: *val = read_sysreg_s(SYS_DACR32_EL2); break;
case IFSR32_EL2: *val = read_sysreg_s(SYS_IFSR32_EL2); break;
case DBGVCR32_EL2: *val = read_sysreg_s(SYS_DBGVCR32_EL2); break;
@@ -1038,8 +1038,8 @@
{ SYS_DESC(SYS_PMEVTYPERn_EL0(n)), \
access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), }
-static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
- const struct sys_reg_desc *r)
+static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
{
kvm_inject_undefined(vcpu);
@@ -1047,33 +1047,25 @@
}
/* Macro to expand the AMU counter and type registers*/
-#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), access_amu }
-#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), access_amu }
-#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), access_amu }
-#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), access_amu }
-
-static bool trap_ptrauth(struct kvm_vcpu *vcpu,
- struct sys_reg_params *p,
- const struct sys_reg_desc *rd)
-{
- /*
- * If we land here, that is because we didn't fixup the access on exit
- * by allowing the PtrAuth sysregs. The only way this happens is when
- * the guest does not have PtrAuth support enabled.
- */
- kvm_inject_undefined(vcpu);
-
- return false;
-}
+#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), undef_access }
+#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), undef_access }
+#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), undef_access }
+#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), undef_access }
static unsigned int ptrauth_visibility(const struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
- return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN_USER | REG_HIDDEN_GUEST;
+ return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN;
}
+/*
+ * If we land here on a PtrAuth access, that is because we didn't
+ * fixup the access on exit by allowing the PtrAuth sysregs. The only
+ * way this happens is when the guest does not have PtrAuth support
+ * enabled.
+ */
#define __PTRAUTH_KEY(k) \
- { SYS_DESC(SYS_## k), trap_ptrauth, reset_unknown, k, \
+ { SYS_DESC(SYS_## k), undef_access, reset_unknown, k, \
.visibility = ptrauth_visibility}
#define PTRAUTH_KEY(k) \
@@ -1128,9 +1120,8 @@
if (!vcpu_has_sve(vcpu))
val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT);
- if (!(val & (0xfUL << ID_AA64PFR0_CSV2_SHIFT)) &&
- arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED)
- val |= (1UL << ID_AA64PFR0_CSV2_SHIFT);
+ val &= ~(0xfUL << ID_AA64PFR0_CSV2_SHIFT);
+ val |= ((u64)vcpu->kvm->arch.pfr0_csv2 << ID_AA64PFR0_CSV2_SHIFT);
} else if (id == SYS_ID_AA64PFR1_EL1) {
val &= ~(0xfUL << ID_AA64PFR1_MTE_SHIFT);
} else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) {
@@ -1153,6 +1144,22 @@
return val;
}
+static unsigned int id_visibility(const struct kvm_vcpu *vcpu,
+ const struct sys_reg_desc *r)
+{
+ u32 id = sys_reg((u32)r->Op0, (u32)r->Op1,
+ (u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
+
+ switch (id) {
+ case SYS_ID_AA64ZFR0_EL1:
+ if (!vcpu_has_sve(vcpu))
+ return REG_RAZ;
+ break;
+ }
+
+ return 0;
+}
+
/* cpufeature ID register access trap handlers */
static bool __access_id_reg(struct kvm_vcpu *vcpu,
@@ -1171,7 +1178,9 @@
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
- return __access_id_reg(vcpu, p, r, false);
+ bool raz = sysreg_visible_as_raz(vcpu, r);
+
+ return __access_id_reg(vcpu, p, r, raz);
}
static bool access_raz_id_reg(struct kvm_vcpu *vcpu,
@@ -1192,71 +1201,40 @@
if (vcpu_has_sve(vcpu))
return 0;
- return REG_HIDDEN_USER | REG_HIDDEN_GUEST;
+ return REG_HIDDEN;
}
-/* Visibility overrides for SVE-specific ID registers */
-static unsigned int sve_id_visibility(const struct kvm_vcpu *vcpu,
- const struct sys_reg_desc *rd)
-{
- if (vcpu_has_sve(vcpu))
- return 0;
-
- return REG_HIDDEN_USER;
-}
-
-/* Generate the emulated ID_AA64ZFR0_EL1 value exposed to the guest */
-static u64 guest_id_aa64zfr0_el1(const struct kvm_vcpu *vcpu)
-{
- if (!vcpu_has_sve(vcpu))
- return 0;
-
- return read_sanitised_ftr_reg(SYS_ID_AA64ZFR0_EL1);
-}
-
-static bool access_id_aa64zfr0_el1(struct kvm_vcpu *vcpu,
- struct sys_reg_params *p,
- const struct sys_reg_desc *rd)
-{
- if (p->is_write)
- return write_to_read_only(vcpu, p, rd);
-
- p->regval = guest_id_aa64zfr0_el1(vcpu);
- return true;
-}
-
-static int get_id_aa64zfr0_el1(struct kvm_vcpu *vcpu,
- const struct sys_reg_desc *rd,
- const struct kvm_one_reg *reg, void __user *uaddr)
-{
- u64 val;
-
- if (WARN_ON(!vcpu_has_sve(vcpu)))
- return -ENOENT;
-
- val = guest_id_aa64zfr0_el1(vcpu);
- return reg_to_user(uaddr, &val, reg->id);
-}
-
-static int set_id_aa64zfr0_el1(struct kvm_vcpu *vcpu,
- const struct sys_reg_desc *rd,
- const struct kvm_one_reg *reg, void __user *uaddr)
+static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu,
+ const struct sys_reg_desc *rd,
+ const struct kvm_one_reg *reg, void __user *uaddr)
{
const u64 id = sys_reg_to_index(rd);
int err;
u64 val;
-
- if (WARN_ON(!vcpu_has_sve(vcpu)))
- return -ENOENT;
+ u8 csv2;
err = reg_from_user(&val, uaddr, id);
if (err)
return err;
- /* This is what we mean by invariant: you can't change it. */
- if (val != guest_id_aa64zfr0_el1(vcpu))
+ /*
+ * Allow AA64PFR0_EL1.CSV2 to be set from userspace as long as
+ * it doesn't promise more than what is actually provided (the
+ * guest could otherwise be covered in ectoplasmic residue).
+ */
+ csv2 = cpuid_feature_extract_unsigned_field(val, ID_AA64PFR0_CSV2_SHIFT);
+ if (csv2 > 1 ||
+ (csv2 && arm64_get_spectre_v2_state() != SPECTRE_UNAFFECTED))
return -EINVAL;
+ /* We can only differ with CSV2, and anything else is an error */
+ val ^= read_id_reg(vcpu, rd, false);
+ val &= ~(0xFUL << ID_AA64PFR0_CSV2_SHIFT);
+ if (val)
+ return -EINVAL;
+
+ vcpu->kvm->arch.pfr0_csv2 = csv2;
+
return 0;
}
@@ -1299,13 +1277,17 @@
static int get_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
const struct kvm_one_reg *reg, void __user *uaddr)
{
- return __get_id_reg(vcpu, rd, uaddr, false);
+ bool raz = sysreg_visible_as_raz(vcpu, rd);
+
+ return __get_id_reg(vcpu, rd, uaddr, raz);
}
static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
const struct kvm_one_reg *reg, void __user *uaddr)
{
- return __set_id_reg(vcpu, rd, uaddr, false);
+ bool raz = sysreg_visible_as_raz(vcpu, rd);
+
+ return __set_id_reg(vcpu, rd, uaddr, raz);
}
static int get_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
@@ -1384,19 +1366,13 @@
return true;
}
-static bool access_mte_regs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
- const struct sys_reg_desc *r)
-{
- kvm_inject_undefined(vcpu);
- return false;
-}
-
/* sys_reg_desc initialiser for known cpufeature ID registers */
#define ID_SANITISED(name) { \
SYS_DESC(SYS_##name), \
.access = access_id_reg, \
.get_user = get_id_reg, \
.set_user = set_id_reg, \
+ .visibility = id_visibility, \
}
/*
@@ -1514,11 +1490,12 @@
/* AArch64 ID registers */
/* CRm=4 */
- ID_SANITISED(ID_AA64PFR0_EL1),
+ { SYS_DESC(SYS_ID_AA64PFR0_EL1), .access = access_id_reg,
+ .get_user = get_id_reg, .set_user = set_id_aa64pfr0_el1, },
ID_SANITISED(ID_AA64PFR1_EL1),
ID_UNALLOCATED(4,2),
ID_UNALLOCATED(4,3),
- { SYS_DESC(SYS_ID_AA64ZFR0_EL1), access_id_aa64zfr0_el1, .get_user = get_id_aa64zfr0_el1, .set_user = set_id_aa64zfr0_el1, .visibility = sve_id_visibility },
+ ID_SANITISED(ID_AA64ZFR0_EL1),
ID_UNALLOCATED(4,5),
ID_UNALLOCATED(4,6),
ID_UNALLOCATED(4,7),
@@ -1557,8 +1534,8 @@
{ SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 },
{ SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 },
- { SYS_DESC(SYS_RGSR_EL1), access_mte_regs },
- { SYS_DESC(SYS_GCR_EL1), access_mte_regs },
+ { SYS_DESC(SYS_RGSR_EL1), undef_access },
+ { SYS_DESC(SYS_GCR_EL1), undef_access },
{ SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility },
{ SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 },
@@ -1584,8 +1561,8 @@
{ SYS_DESC(SYS_ERXMISC0_EL1), trap_raz_wi },
{ SYS_DESC(SYS_ERXMISC1_EL1), trap_raz_wi },
- { SYS_DESC(SYS_TFSR_EL1), access_mte_regs },
- { SYS_DESC(SYS_TFSRE0_EL1), access_mte_regs },
+ { SYS_DESC(SYS_TFSR_EL1), undef_access },
+ { SYS_DESC(SYS_TFSRE0_EL1), undef_access },
{ SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 },
{ SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 },
@@ -1621,6 +1598,8 @@
{ SYS_DESC(SYS_CONTEXTIDR_EL1), access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
{ SYS_DESC(SYS_TPIDR_EL1), NULL, reset_unknown, TPIDR_EL1 },
+ { SYS_DESC(SYS_SCXTNUM_EL1), undef_access },
+
{ SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0},
{ SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr },
@@ -1649,14 +1628,16 @@
{ SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
{ SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 },
- { SYS_DESC(SYS_AMCR_EL0), access_amu },
- { SYS_DESC(SYS_AMCFGR_EL0), access_amu },
- { SYS_DESC(SYS_AMCGCR_EL0), access_amu },
- { SYS_DESC(SYS_AMUSERENR_EL0), access_amu },
- { SYS_DESC(SYS_AMCNTENCLR0_EL0), access_amu },
- { SYS_DESC(SYS_AMCNTENSET0_EL0), access_amu },
- { SYS_DESC(SYS_AMCNTENCLR1_EL0), access_amu },
- { SYS_DESC(SYS_AMCNTENSET1_EL0), access_amu },
+ { SYS_DESC(SYS_SCXTNUM_EL0), undef_access },
+
+ { SYS_DESC(SYS_AMCR_EL0), undef_access },
+ { SYS_DESC(SYS_AMCFGR_EL0), undef_access },
+ { SYS_DESC(SYS_AMCGCR_EL0), undef_access },
+ { SYS_DESC(SYS_AMUSERENR_EL0), undef_access },
+ { SYS_DESC(SYS_AMCNTENCLR0_EL0), undef_access },
+ { SYS_DESC(SYS_AMCNTENSET0_EL0), undef_access },
+ { SYS_DESC(SYS_AMCNTENCLR1_EL0), undef_access },
+ { SYS_DESC(SYS_AMCNTENSET1_EL0), undef_access },
AMU_AMEVCNTR0_EL0(0),
AMU_AMEVCNTR0_EL0(1),
AMU_AMEVCNTR0_EL0(2),
@@ -1897,9 +1878,9 @@
{ Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi },
DBG_BCR_BVR_WCR_WVR(1),
/* DBGDCCINT */
- { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32 },
+ { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32, NULL, cp14_DBGDCCINT },
/* DBGDSCRext */
- { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32 },
+ { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32, NULL, cp14_DBGDSCRext },
DBG_BCR_BVR_WCR_WVR(2),
/* DBGDTR[RT]Xint */
{ Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi },
@@ -1914,7 +1895,7 @@
{ Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi },
DBG_BCR_BVR_WCR_WVR(6),
/* DBGVCR */
- { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32 },
+ { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32, NULL, cp14_DBGVCR },
DBG_BCR_BVR_WCR_WVR(7),
DBG_BCR_BVR_WCR_WVR(8),
DBG_BCR_BVR_WCR_WVR(9),
@@ -2185,7 +2166,7 @@
trace_kvm_sys_access(*vcpu_pc(vcpu), params, r);
/* Check for regs disabled by runtime config */
- if (sysreg_hidden_from_guest(vcpu, r)) {
+ if (sysreg_hidden(vcpu, r)) {
kvm_inject_undefined(vcpu);
return;
}
@@ -2684,7 +2665,7 @@
return get_invariant_sys_reg(reg->id, uaddr);
/* Check for regs disabled by runtime config */
- if (sysreg_hidden_from_user(vcpu, r))
+ if (sysreg_hidden(vcpu, r))
return -ENOENT;
if (r->get_user)
@@ -2709,7 +2690,7 @@
return set_invariant_sys_reg(reg->id, uaddr);
/* Check for regs disabled by runtime config */
- if (sysreg_hidden_from_user(vcpu, r))
+ if (sysreg_hidden(vcpu, r))
return -ENOENT;
if (r->set_user)
@@ -2780,7 +2761,7 @@
if (!(rd->reg || rd->get_user))
return 0;
- if (sysreg_hidden_from_user(vcpu, rd))
+ if (sysreg_hidden(vcpu, rd))
return 0;
if (!copy_reg_to_user(rd, uind))
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index 5a6fc30..0f95964 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -59,8 +59,8 @@
const struct sys_reg_desc *rd);
};
-#define REG_HIDDEN_USER (1 << 0) /* hidden from userspace ioctls */
-#define REG_HIDDEN_GUEST (1 << 1) /* hidden from guest */
+#define REG_HIDDEN (1 << 0) /* hidden from userspace and guest */
+#define REG_RAZ (1 << 1) /* RAZ from userspace and guest */
static __printf(2, 3)
inline void print_sys_reg_msg(const struct sys_reg_params *p,
@@ -111,22 +111,22 @@
__vcpu_sys_reg(vcpu, r->reg) = r->val;
}
-static inline bool sysreg_hidden_from_guest(const struct kvm_vcpu *vcpu,
- const struct sys_reg_desc *r)
+static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu,
+ const struct sys_reg_desc *r)
{
if (likely(!r->visibility))
return false;
- return r->visibility(vcpu, r) & REG_HIDDEN_GUEST;
+ return r->visibility(vcpu, r) & REG_HIDDEN;
}
-static inline bool sysreg_hidden_from_user(const struct kvm_vcpu *vcpu,
- const struct sys_reg_desc *r)
+static inline bool sysreg_visible_as_raz(const struct kvm_vcpu *vcpu,
+ const struct sys_reg_desc *r)
{
if (likely(!r->visibility))
return false;
- return r->visibility(vcpu, r) & REG_HIDDEN_USER;
+ return r->visibility(vcpu, r) & REG_RAZ;
}
static inline int cmp_sys_reg(const struct sys_reg_desc *i1,
diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S
index e0bf83d..dc8d2a2 100644
--- a/arch/arm64/lib/memcpy.S
+++ b/arch/arm64/lib/memcpy.S
@@ -56,9 +56,8 @@
stp \reg1, \reg2, [\ptr], \val
.endm
- .weak memcpy
SYM_FUNC_START_ALIAS(__memcpy)
-SYM_FUNC_START_PI(memcpy)
+SYM_FUNC_START_WEAK_PI(memcpy)
#include "copy_template.S"
ret
SYM_FUNC_END_PI(memcpy)
diff --git a/arch/arm64/lib/memmove.S b/arch/arm64/lib/memmove.S
index 02cda2e..1035dce 100644
--- a/arch/arm64/lib/memmove.S
+++ b/arch/arm64/lib/memmove.S
@@ -45,9 +45,8 @@
D_l .req x13
D_h .req x14
- .weak memmove
SYM_FUNC_START_ALIAS(__memmove)
-SYM_FUNC_START_PI(memmove)
+SYM_FUNC_START_WEAK_PI(memmove)
cmp dstin, src
b.lo __memcpy
add tmp1, src, count
diff --git a/arch/arm64/lib/memset.S b/arch/arm64/lib/memset.S
index 77c3c7b..a9c1c9a 100644
--- a/arch/arm64/lib/memset.S
+++ b/arch/arm64/lib/memset.S
@@ -42,9 +42,8 @@
tmp3w .req w9
tmp3 .req x9
- .weak memset
SYM_FUNC_START_ALIAS(__memset)
-SYM_FUNC_START_PI(memset)
+SYM_FUNC_START_WEAK_PI(memset)
mov dst, dstin /* Preserve return value. */
and A_lw, val, #255
orr A_lw, A_lw, A_lw, lsl #8
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 94c99c1c..1ee9400 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -262,7 +262,7 @@
local_irq_save(flags);
asm volatile("at s1e1r, %0" :: "r" (addr));
isb();
- par = read_sysreg(par_el1);
+ par = read_sysreg_par();
local_irq_restore(flags);
/*
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 1c0f3e0..ca692a8 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1444,11 +1444,28 @@
free_empty_tables(start, end, PAGE_OFFSET, PAGE_END);
}
+static bool inside_linear_region(u64 start, u64 size)
+{
+ /*
+ * Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)]
+ * accommodating both its ends but excluding PAGE_END. Max physical
+ * range which can be mapped inside this linear mapping range, must
+ * also be derived from its end points.
+ */
+ return start >= __pa(_PAGE_OFFSET(vabits_actual)) &&
+ (start + size - 1) <= __pa(PAGE_END - 1);
+}
+
int arch_add_memory(int nid, u64 start, u64 size,
struct mhp_params *params)
{
int ret, flags = 0;
+ if (!inside_linear_region(start, size)) {
+ pr_err("[%llx %llx] is outside linear mapping region\n", start, start + size);
+ return -EINVAL;
+ }
+
if (rodata_full || debug_pagealloc_enabled())
flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
diff --git a/arch/csky/kernel/perf_regs.c b/arch/csky/kernel/perf_regs.c
index eb32838..09b7f88 100644
--- a/arch/csky/kernel/perf_regs.c
+++ b/arch/csky/kernel/perf_regs.c
@@ -32,8 +32,7 @@
}
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
regs_user->regs = task_pt_regs(current);
regs_user->abi = perf_reg_abi(current);
diff --git a/arch/mips/alchemy/common/clock.c b/arch/mips/alchemy/common/clock.c
index a95a894..f0c8303 100644
--- a/arch/mips/alchemy/common/clock.c
+++ b/arch/mips/alchemy/common/clock.c
@@ -152,6 +152,7 @@
{
struct clk_init_data id;
struct clk_hw *h;
+ struct clk *clk;
h = kzalloc(sizeof(*h), GFP_KERNEL);
if (!h)
@@ -164,7 +165,13 @@
id.ops = &alchemy_clkops_cpu;
h->init = &id;
- return clk_register(NULL, h);
+ clk = clk_register(NULL, h);
+ if (IS_ERR(clk)) {
+ pr_err("failed to register clock\n");
+ kfree(h);
+ }
+
+ return clk;
}
/* AUXPLLs ************************************************************/
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 0d42532..ca579de 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -262,8 +262,8 @@
static void __init bootmem_init(void)
{
phys_addr_t ramstart, ramend;
- phys_addr_t start, end;
- u64 i;
+ unsigned long start, end;
+ int i;
ramstart = memblock_start_of_DRAM();
ramend = memblock_end_of_DRAM();
@@ -300,7 +300,7 @@
min_low_pfn = ARCH_PFN_OFFSET;
max_pfn = PFN_DOWN(ramend);
- for_each_mem_range(i, &start, &end) {
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) {
/*
* Skip highmem here so we get an accurate max_low_pfn if low
* memory stops short of high memory.
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index 38e2894..1b939ab 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -438,6 +438,7 @@
}
return mask == PM_HUGE_MASK;
}
+EXPORT_SYMBOL(has_transparent_hugepage);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h
index 3ee1ec6..28716e2 100644
--- a/arch/powerpc/include/asm/book3s/64/kup-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h
@@ -27,6 +27,7 @@
#endif
.endm
+#ifdef CONFIG_PPC_KUAP
.macro kuap_check_amr gpr1, gpr2
#ifdef CONFIG_PPC_KUAP_DEBUG
BEGIN_MMU_FTR_SECTION_NESTED(67)
@@ -38,6 +39,7 @@
END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67)
#endif
.endm
+#endif
.macro kuap_save_amr_and_lock gpr1, gpr2, use_cr, msr_pr_cr
#ifdef CONFIG_PPC_KUAP
@@ -61,6 +63,8 @@
#else /* !__ASSEMBLY__ */
+DECLARE_STATIC_KEY_FALSE(uaccess_flush_key);
+
#ifdef CONFIG_PPC_KUAP
#include <asm/mmu.h>
@@ -103,8 +107,16 @@
static inline unsigned long get_kuap(void)
{
+ /*
+ * We return AMR_KUAP_BLOCKED when we don't support KUAP because
+ * prevent_user_access_return needs to return AMR_KUAP_BLOCKED to
+ * cause restore_user_access to do a flush.
+ *
+ * This has no effect in terms of actually blocking things on hash,
+ * so it doesn't break anything.
+ */
if (!early_mmu_has_feature(MMU_FTR_RADIX_KUAP))
- return 0;
+ return AMR_KUAP_BLOCKED;
return mfspr(SPRN_AMR);
}
@@ -123,6 +135,29 @@
isync();
}
+static inline bool
+bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
+{
+ return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) &&
+ (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)),
+ "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read");
+}
+#else /* CONFIG_PPC_KUAP */
+static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr) { }
+
+static inline unsigned long kuap_get_and_check_amr(void)
+{
+ return 0UL;
+}
+
+static inline unsigned long get_kuap(void)
+{
+ return AMR_KUAP_BLOCKED;
+}
+
+static inline void set_kuap(unsigned long value) { }
+#endif /* !CONFIG_PPC_KUAP */
+
static __always_inline void allow_user_access(void __user *to, const void __user *from,
unsigned long size, unsigned long dir)
{
@@ -142,6 +177,8 @@
unsigned long size, unsigned long dir)
{
set_kuap(AMR_KUAP_BLOCKED);
+ if (static_branch_unlikely(&uaccess_flush_key))
+ do_uaccess_flush();
}
static inline unsigned long prevent_user_access_return(void)
@@ -149,6 +186,8 @@
unsigned long flags = get_kuap();
set_kuap(AMR_KUAP_BLOCKED);
+ if (static_branch_unlikely(&uaccess_flush_key))
+ do_uaccess_flush();
return flags;
}
@@ -156,30 +195,9 @@
static inline void restore_user_access(unsigned long flags)
{
set_kuap(flags);
+ if (static_branch_unlikely(&uaccess_flush_key) && flags == AMR_KUAP_BLOCKED)
+ do_uaccess_flush();
}
-
-static inline bool
-bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
-{
- return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) &&
- (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)),
- "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read");
-}
-#else /* CONFIG_PPC_KUAP */
-static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr)
-{
-}
-
-static inline void kuap_check_amr(void)
-{
-}
-
-static inline unsigned long kuap_get_and_check_amr(void)
-{
- return 0;
-}
-#endif /* CONFIG_PPC_KUAP */
-
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H */
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index ebe95aa..1d32b17 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -57,11 +57,18 @@
nop; \
nop
+#define ENTRY_FLUSH_SLOT \
+ ENTRY_FLUSH_FIXUP_SECTION; \
+ nop; \
+ nop; \
+ nop;
+
/*
* r10 must be free to use, r13 must be paca
*/
#define INTERRUPT_TO_KERNEL \
- STF_ENTRY_BARRIER_SLOT
+ STF_ENTRY_BARRIER_SLOT; \
+ ENTRY_FLUSH_SLOT
/*
* Macros for annotating the expected destination of (h)rfid
@@ -137,6 +144,9 @@
RFSCV; \
b rfscv_flush_fallback
+#else /* __ASSEMBLY__ */
+/* Prototype for function defined in exceptions-64s.S */
+void do_uaccess_flush(void);
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_EXCEPTION_H */
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index b0af97a..fbd406c 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -205,6 +205,22 @@
FTR_ENTRY_OFFSET 955b-956b; \
.popsection;
+#define UACCESS_FLUSH_FIXUP_SECTION \
+959: \
+ .pushsection __uaccess_flush_fixup,"a"; \
+ .align 2; \
+960: \
+ FTR_ENTRY_OFFSET 959b-960b; \
+ .popsection;
+
+#define ENTRY_FLUSH_FIXUP_SECTION \
+957: \
+ .pushsection __entry_flush_fixup,"a"; \
+ .align 2; \
+958: \
+ FTR_ENTRY_OFFSET 957b-958b; \
+ .popsection;
+
#define RFI_FLUSH_FIXUP_SECTION \
951: \
.pushsection __rfi_flush_fixup,"a"; \
@@ -237,8 +253,11 @@
#include <linux/types.h>
extern long stf_barrier_fallback;
+extern long entry_flush_fallback;
extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup;
extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup;
+extern long __start___uaccess_flush_fixup, __stop___uaccess_flush_fixup;
+extern long __start___entry_flush_fixup, __stop___entry_flush_fixup;
extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup;
extern long __start__btb_flush_fixup, __stop__btb_flush_fixup;
diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h
index 1d0f7d8..0d93331 100644
--- a/arch/powerpc/include/asm/kup.h
+++ b/arch/powerpc/include/asm/kup.h
@@ -14,7 +14,7 @@
#define KUAP_CURRENT_WRITE 8
#define KUAP_CURRENT (KUAP_CURRENT_READ | KUAP_CURRENT_WRITE)
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S_64
#include <asm/book3s/64/kup-radix.h>
#endif
#ifdef CONFIG_PPC_8xx
@@ -35,6 +35,9 @@
.macro kuap_check current, gpr
.endm
+.macro kuap_check_amr gpr1, gpr2
+.endm
+
#endif
#else /* !__ASSEMBLY__ */
@@ -53,17 +56,28 @@
void setup_kuap(bool disabled);
#else
static inline void setup_kuap(bool disabled) { }
+
+static inline bool
+bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
+{
+ return false;
+}
+
+static inline void kuap_check_amr(void) { }
+
+/*
+ * book3s/64/kup-radix.h defines these functions for the !KUAP case to flush
+ * the L1D cache after user accesses. Only include the empty stubs for other
+ * platforms.
+ */
+#ifndef CONFIG_PPC_BOOK3S_64
static inline void allow_user_access(void __user *to, const void __user *from,
unsigned long size, unsigned long dir) { }
static inline void prevent_user_access(void __user *to, const void __user *from,
unsigned long size, unsigned long dir) { }
static inline unsigned long prevent_user_access_return(void) { return 0UL; }
static inline void restore_user_access(unsigned long flags) { }
-static inline bool
-bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
-{
- return false;
-}
+#endif /* CONFIG_PPC_BOOK3S_64 */
#endif /* CONFIG_PPC_KUAP */
static inline void allow_read_from_user(const void __user *from, unsigned long size)
diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h
index 85ed239..567cdc5 100644
--- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h
@@ -63,7 +63,7 @@
static inline bool
bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
{
- return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xf0000000),
+ return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xff000000),
"Bug: fault blocked by AP register !");
}
diff --git a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
index 1d9ac0f..0bd1b14 100644
--- a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
@@ -33,19 +33,18 @@
* respectively NA for All or X for Supervisor and no access for User.
* Then we use the APG to say whether accesses are according to Page rules or
* "all Supervisor" rules (Access to all)
- * Therefore, we define 2 APG groups. lsb is _PMD_USER
- * 0 => Kernel => 01 (all accesses performed according to page definition)
- * 1 => User => 00 (all accesses performed as supervisor iaw page definition)
- * 2-15 => Not Used
+ * _PAGE_ACCESSED is also managed via APG. When _PAGE_ACCESSED is not set, say
+ * "all User" rules, that will lead to NA for all.
+ * Therefore, we define 4 APG groups. lsb is _PAGE_ACCESSED
+ * 0 => Kernel => 11 (all accesses performed according as user iaw page definition)
+ * 1 => Kernel+Accessed => 01 (all accesses performed according to page definition)
+ * 2 => User => 11 (all accesses performed according as user iaw page definition)
+ * 3 => User+Accessed => 00 (all accesses performed as supervisor iaw page definition) for INIT
+ * => 10 (all accesses performed according to swaped page definition) for KUEP
+ * 4-15 => Not Used
*/
-#define MI_APG_INIT 0x40000000
-
-/*
- * 0 => Kernel => 01 (all accesses performed according to page definition)
- * 1 => User => 10 (all accesses performed according to swaped page definition)
- * 2-15 => Not Used
- */
-#define MI_APG_KUEP 0x60000000
+#define MI_APG_INIT 0xdc000000
+#define MI_APG_KUEP 0xde000000
/* The effective page number register. When read, contains the information
* about the last instruction TLB miss. When MI_RPN is written, bits in
@@ -106,25 +105,9 @@
#define MD_Ks 0x80000000 /* Should not be set */
#define MD_Kp 0x40000000 /* Should always be set */
-/*
- * All pages' PP data bits are set to either 000 or 011 or 001, which means
- * respectively RW for Supervisor and no access for User, or RO for
- * Supervisor and no access for user and NA for ALL.
- * Then we use the APG to say whether accesses are according to Page rules or
- * "all Supervisor" rules (Access to all)
- * Therefore, we define 2 APG groups. lsb is _PMD_USER
- * 0 => Kernel => 01 (all accesses performed according to page definition)
- * 1 => User => 00 (all accesses performed as supervisor iaw page definition)
- * 2-15 => Not Used
- */
-#define MD_APG_INIT 0x40000000
-
-/*
- * 0 => No user => 01 (all accesses performed according to page definition)
- * 1 => User => 10 (all accesses performed according to swaped page definition)
- * 2-15 => Not Used
- */
-#define MD_APG_KUAP 0x60000000
+/* See explanation above at the definition of MI_APG_INIT */
+#define MD_APG_INIT 0xdc000000
+#define MD_APG_KUAP 0xde000000
/* The effective page number register. When read, contains the information
* about the last instruction TLB miss. When MD_RPN is written, bits in
diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
index 66f403a..1581204 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
@@ -39,9 +39,9 @@
* into the TLB.
*/
#define _PAGE_GUARDED 0x0010 /* Copied to L1 G entry in DTLB */
-#define _PAGE_SPECIAL 0x0020 /* SW entry */
+#define _PAGE_ACCESSED 0x0020 /* Copied to L1 APG 1 entry in I/DTLB */
#define _PAGE_EXEC 0x0040 /* Copied to PP (bit 21) in ITLB */
-#define _PAGE_ACCESSED 0x0080 /* software: page referenced */
+#define _PAGE_SPECIAL 0x0080 /* SW entry */
#define _PAGE_NA 0x0200 /* Supervisor NA, User no access */
#define _PAGE_RO 0x0600 /* Supervisor RO, User no access */
@@ -59,11 +59,12 @@
#define _PMD_PRESENT 0x0001
#define _PMD_PRESENT_MASK _PMD_PRESENT
-#define _PMD_BAD 0x0fd0
+#define _PMD_BAD 0x0f90
#define _PMD_PAGE_MASK 0x000c
#define _PMD_PAGE_8M 0x000c
#define _PMD_PAGE_512K 0x0004
-#define _PMD_USER 0x0020 /* APG 1 */
+#define _PMD_ACCESSED 0x0020 /* APG 1 */
+#define _PMD_USER 0x0040 /* APG 2 */
#define _PTE_NONE_MASK 0
diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h
index fbb8fa3..b774a44 100644
--- a/arch/powerpc/include/asm/security_features.h
+++ b/arch/powerpc/include/asm/security_features.h
@@ -86,12 +86,19 @@
// Software required to flush link stack on context switch
#define SEC_FTR_FLUSH_LINK_STACK 0x0000000000001000ull
+// The L1-D cache should be flushed when entering the kernel
+#define SEC_FTR_L1D_FLUSH_ENTRY 0x0000000000004000ull
+
+// The L1-D cache should be flushed after user accesses from the kernel
+#define SEC_FTR_L1D_FLUSH_UACCESS 0x0000000000008000ull
// Features enabled by default
#define SEC_FTR_DEFAULT \
(SEC_FTR_L1D_FLUSH_HV | \
SEC_FTR_L1D_FLUSH_PR | \
SEC_FTR_BNDS_CHK_SPEC_BAR | \
+ SEC_FTR_L1D_FLUSH_ENTRY | \
+ SEC_FTR_L1D_FLUSH_UACCESS | \
SEC_FTR_FAVOUR_SECURITY)
#endif /* _ASM_POWERPC_SECURITY_FEATURES_H */
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index 9efbdde..a466749 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -52,12 +52,16 @@
};
void setup_rfi_flush(enum l1d_flush_type, bool enable);
+void setup_entry_flush(bool enable);
+void setup_uaccess_flush(bool enable);
void do_rfi_flush_fixups(enum l1d_flush_type types);
#ifdef CONFIG_PPC_BARRIER_NOSPEC
void setup_barrier_nospec(void);
#else
static inline void setup_barrier_nospec(void) { };
#endif
+void do_uaccess_flush_fixups(enum l1d_flush_type types);
+void do_entry_flush_fixups(enum l1d_flush_type types);
void do_barrier_nospec_fixups(bool enable);
extern bool barrier_nospec_enabled;
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 8728590..3beeb03 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -6,6 +6,7 @@
struct device;
struct device_node;
+struct drmem_lmb;
#ifdef CONFIG_NUMA
@@ -61,6 +62,9 @@
*/
return (nid < 0) ? 0 : nid;
}
+
+int of_drconf_to_nid_single(struct drmem_lmb *lmb);
+
#else
static inline int early_cpu_to_node(int cpu) { return 0; }
@@ -84,10 +88,12 @@
return 0;
}
-#endif /* CONFIG_NUMA */
+static inline int of_drconf_to_nid_single(struct drmem_lmb *lmb)
+{
+ return first_online_node;
+}
-struct drmem_lmb;
-int of_drconf_to_nid_single(struct drmem_lmb *lmb);
+#endif /* CONFIG_NUMA */
#if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
extern int find_and_online_cpu_nid(int cpu);
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index ef5bbb70..501c9a7 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -178,7 +178,7 @@
* are no aliasing issues.
*/
#define __put_user_asm_goto(x, addr, label, op) \
- asm volatile goto( \
+ asm_volatile_goto( \
"1: " op "%U1%X1 %0,%1 # put_user\n" \
EX_TABLE(1b, %l2) \
: \
@@ -191,7 +191,7 @@
__put_user_asm_goto(x, ptr, label, "std")
#else /* __powerpc64__ */
#define __put_user_asm2_goto(x, addr, label) \
- asm volatile goto( \
+ asm_volatile_goto( \
"1: stw%X1 %0, %1\n" \
"2: stw%X1 %L0, %L1\n" \
EX_TABLE(1b, %l2) \
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index 6b50bf1..bf32704 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -264,8 +264,9 @@
{
struct pci_io_addr_range *piar;
struct rb_node *n;
+ unsigned long flags;
- spin_lock(&pci_io_addr_cache_root.piar_lock);
+ spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
for (n = rb_first(&pci_io_addr_cache_root.rb_root); n; n = rb_next(n)) {
piar = rb_entry(n, struct pci_io_addr_range, rb_node);
@@ -273,7 +274,7 @@
(piar->flags & IORESOURCE_IO) ? "i/o" : "mem",
&piar->addr_lo, &piar->addr_hi, pci_name(piar->pcidev));
}
- spin_unlock(&pci_io_addr_cache_root.piar_lock);
+ spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
return 0;
}
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index f7d748b..f63a3d3 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -2951,15 +2951,8 @@
.endr
blr
-TRAMP_REAL_BEGIN(rfi_flush_fallback)
- SET_SCRATCH0(r13);
- GET_PACA(r13);
- std r1,PACA_EXRFI+EX_R12(r13)
- ld r1,PACAKSAVE(r13)
- std r9,PACA_EXRFI+EX_R9(r13)
- std r10,PACA_EXRFI+EX_R10(r13)
- std r11,PACA_EXRFI+EX_R11(r13)
- mfctr r9
+/* Clobbers r10, r11, ctr */
+.macro L1D_DISPLACEMENT_FLUSH
ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
ld r11,PACA_L1D_FLUSH_SIZE(r13)
srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
@@ -2970,7 +2963,7 @@
sync
/*
- * The load adresses are at staggered offsets within cachelines,
+ * The load addresses are at staggered offsets within cachelines,
* which suits some pipelines better (on others it should not
* hurt).
*/
@@ -2985,7 +2978,30 @@
ld r11,(0x80 + 8)*7(r10)
addi r10,r10,0x80*8
bdnz 1b
+.endm
+TRAMP_REAL_BEGIN(entry_flush_fallback)
+ std r9,PACA_EXRFI+EX_R9(r13)
+ std r10,PACA_EXRFI+EX_R10(r13)
+ std r11,PACA_EXRFI+EX_R11(r13)
+ mfctr r9
+ L1D_DISPLACEMENT_FLUSH
+ mtctr r9
+ ld r9,PACA_EXRFI+EX_R9(r13)
+ ld r10,PACA_EXRFI+EX_R10(r13)
+ ld r11,PACA_EXRFI+EX_R11(r13)
+ blr
+
+TRAMP_REAL_BEGIN(rfi_flush_fallback)
+ SET_SCRATCH0(r13);
+ GET_PACA(r13);
+ std r1,PACA_EXRFI+EX_R12(r13)
+ ld r1,PACAKSAVE(r13)
+ std r9,PACA_EXRFI+EX_R9(r13)
+ std r10,PACA_EXRFI+EX_R10(r13)
+ std r11,PACA_EXRFI+EX_R11(r13)
+ mfctr r9
+ L1D_DISPLACEMENT_FLUSH
mtctr r9
ld r9,PACA_EXRFI+EX_R9(r13)
ld r10,PACA_EXRFI+EX_R10(r13)
@@ -3003,32 +3019,7 @@
std r10,PACA_EXRFI+EX_R10(r13)
std r11,PACA_EXRFI+EX_R11(r13)
mfctr r9
- ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
- ld r11,PACA_L1D_FLUSH_SIZE(r13)
- srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
- mtctr r11
- DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
-
- /* order ld/st prior to dcbt stop all streams with flushing */
- sync
-
- /*
- * The load adresses are at staggered offsets within cachelines,
- * which suits some pipelines better (on others it should not
- * hurt).
- */
-1:
- ld r11,(0x80 + 8)*0(r10)
- ld r11,(0x80 + 8)*1(r10)
- ld r11,(0x80 + 8)*2(r10)
- ld r11,(0x80 + 8)*3(r10)
- ld r11,(0x80 + 8)*4(r10)
- ld r11,(0x80 + 8)*5(r10)
- ld r11,(0x80 + 8)*6(r10)
- ld r11,(0x80 + 8)*7(r10)
- addi r10,r10,0x80*8
- bdnz 1b
-
+ L1D_DISPLACEMENT_FLUSH
mtctr r9
ld r9,PACA_EXRFI+EX_R9(r13)
ld r10,PACA_EXRFI+EX_R10(r13)
@@ -3079,8 +3070,21 @@
RFSCV
USE_TEXT_SECTION()
- MASKED_INTERRUPT
- MASKED_INTERRUPT hsrr=1
+
+_GLOBAL(do_uaccess_flush)
+ UACCESS_FLUSH_FIXUP_SECTION
+ nop
+ nop
+ nop
+ blr
+ L1D_DISPLACEMENT_FLUSH
+ blr
+_ASM_NOKPROBE_SYMBOL(do_uaccess_flush)
+EXPORT_SYMBOL(do_uaccess_flush)
+
+
+MASKED_INTERRUPT
+MASKED_INTERRUPT hsrr=1
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
kvmppc_skip_interrupt:
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index 44c9018..a1ae006 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -284,11 +284,7 @@
rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */
lwz r11, 0(r11) /* Get Linux PTE */
-#ifdef CONFIG_SWAP
li r9, _PAGE_PRESENT | _PAGE_ACCESSED
-#else
- li r9, _PAGE_PRESENT
-#endif
andc. r9, r9, r11 /* Check permission */
bne 5f
@@ -369,11 +365,7 @@
rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */
lwz r11, 0(r11) /* Get Linux PTE */
-#ifdef CONFIG_SWAP
li r9, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
-#else
- li r9, _PAGE_PRESENT | _PAGE_EXEC
-#endif
andc. r9, r9, r11 /* Check permission */
bne 5f
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 9f359d3..ee0bfeb 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -202,9 +202,7 @@
InstructionTLBMiss:
mtspr SPRN_SPRG_SCRATCH0, r10
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) || defined(CONFIG_HUGETLBFS)
mtspr SPRN_SPRG_SCRATCH1, r11
-#endif
/* If we are faulting a kernel address, we have to use the
* kernel page tables.
@@ -224,25 +222,13 @@
3:
mtcr r11
#endif
-#if defined(CONFIG_HUGETLBFS) || !defined(CONFIG_PIN_TLB_TEXT)
lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */
mtspr SPRN_MD_TWC, r11
-#else
- lwz r10, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */
- mtspr SPRN_MI_TWC, r10 /* Set segment attributes */
- mtspr SPRN_MD_TWC, r10
-#endif
mfspr r10, SPRN_MD_TWC
lwz r10, 0(r10) /* Get the pte */
-#if defined(CONFIG_HUGETLBFS) || !defined(CONFIG_PIN_TLB_TEXT)
+ rlwimi r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED
rlwimi r11, r10, 32 - 9, _PMD_PAGE_512K
mtspr SPRN_MI_TWC, r11
-#endif
-#ifdef CONFIG_SWAP
- rlwinm r11, r10, 32-5, _PAGE_PRESENT
- and r11, r11, r10
- rlwimi r10, r11, 0, _PAGE_PRESENT
-#endif
/* The Linux PTE won't go exactly into the MMU TLB.
* Software indicator bits 20 and 23 must be clear.
* Software indicator bits 22, 24, 25, 26, and 27 must be
@@ -256,9 +242,7 @@
/* Restore registers */
0: mfspr r10, SPRN_SPRG_SCRATCH0
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) || defined(CONFIG_HUGETLBFS)
mfspr r11, SPRN_SPRG_SCRATCH1
-#endif
rfi
patch_site 0b, patch__itlbmiss_exit_1
@@ -268,9 +252,7 @@
addi r10, r10, 1
stw r10, (itlb_miss_counter - PAGE_OFFSET)@l(0)
mfspr r10, SPRN_SPRG_SCRATCH0
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP)
mfspr r11, SPRN_SPRG_SCRATCH1
-#endif
rfi
#endif
@@ -297,30 +279,16 @@
mfspr r10, SPRN_MD_TWC
lwz r10, 0(r10) /* Get the pte */
- /* Insert the Guarded flag into the TWC from the Linux PTE.
+ /* Insert Guarded and Accessed flags into the TWC from the Linux PTE.
* It is bit 27 of both the Linux PTE and the TWC (at least
* I got that right :-). It will be better when we can put
* this into the Linux pgd/pmd and load it in the operation
* above.
*/
- rlwimi r11, r10, 0, _PAGE_GUARDED
+ rlwimi r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED
rlwimi r11, r10, 32 - 9, _PMD_PAGE_512K
mtspr SPRN_MD_TWC, r11
- /* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set.
- * We also need to know if the insn is a load/store, so:
- * Clear _PAGE_PRESENT and load that which will
- * trap into DTLB Error with store bit set accordinly.
- */
- /* PRESENT=0x1, ACCESSED=0x20
- * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5));
- * r10 = (r10 & ~PRESENT) | r11;
- */
-#ifdef CONFIG_SWAP
- rlwinm r11, r10, 32-5, _PAGE_PRESENT
- and r11, r11, r10
- rlwimi r10, r11, 0, _PAGE_PRESENT
-#endif
/* The Linux PTE won't go exactly into the MMU TLB.
* Software indicator bits 24, 25, 26, and 27 must be
* set. All other Linux PTE bits control the behavior
@@ -711,7 +679,7 @@
li r9, 4 /* up to 4 pages of 8M */
mtctr r9
lis r9, KERNELBASE@h /* Create vaddr for TLB */
- li r10, MI_PS8MEG | MI_SVALID /* Set 8M byte page */
+ li r10, MI_PS8MEG | _PMD_ACCESSED | MI_SVALID
li r11, MI_BOOTINIT /* Create RPN for address 0 */
1:
mtspr SPRN_MI_CTR, r8 /* Set instruction MMU control */
@@ -775,7 +743,7 @@
#ifdef CONFIG_PIN_TLB_TEXT
LOAD_REG_IMMEDIATE(r5, 28 << 8)
LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET)
- LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG)
+ LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED)
LOAD_REG_IMMEDIATE(r8, 0xf0 | _PAGE_RO | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT)
LOAD_REG_ADDR(r9, _sinittext)
li r0, 4
@@ -797,7 +765,7 @@
LOAD_REG_IMMEDIATE(r5, 28 << 8 | MD_TWAM)
#ifdef CONFIG_PIN_TLB_DATA
LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET)
- LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG)
+ LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED)
#ifdef CONFIG_PIN_TLB_IMMR
li r0, 3
#else
@@ -834,7 +802,7 @@
#endif
#ifdef CONFIG_PIN_TLB_IMMR
LOAD_REG_IMMEDIATE(r0, VIRT_IMMR_BASE | MD_EVALID)
- LOAD_REG_IMMEDIATE(r7, MD_SVALID | MD_PS512K | MD_GUARDED)
+ LOAD_REG_IMMEDIATE(r7, MD_SVALID | MD_PS512K | MD_GUARDED | _PMD_ACCESSED)
mfspr r8, SPRN_IMMR
rlwinm r8, r8, 0, 0xfff80000
ori r8, r8, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | \
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 5eb9eed..2aa16d5 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -457,11 +457,7 @@
cmplw 0,r1,r3
#endif
mfspr r2, SPRN_SPRG_PGDIR
-#ifdef CONFIG_SWAP
li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
-#else
- li r1,_PAGE_PRESENT | _PAGE_EXEC
-#endif
#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC)
bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
@@ -523,11 +519,7 @@
lis r1, TASK_SIZE@h /* check if kernel address */
cmplw 0,r1,r3
mfspr r2, SPRN_SPRG_PGDIR
-#ifdef CONFIG_SWAP
li r1, _PAGE_PRESENT | _PAGE_ACCESSED
-#else
- li r1, _PAGE_PRESENT
-#endif
bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
@@ -603,11 +595,7 @@
lis r1, TASK_SIZE@h /* check if kernel address */
cmplw 0,r1,r3
mfspr r2, SPRN_SPRG_PGDIR
-#ifdef CONFIG_SWAP
li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
-#else
- li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT
-#endif
bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index bb9cab3..74fd47f 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -945,7 +945,13 @@
static enum l1d_flush_type enabled_flush_types;
static void *l1d_flush_fallback_area;
static bool no_rfi_flush;
+static bool no_entry_flush;
+static bool no_uaccess_flush;
bool rfi_flush;
+bool entry_flush;
+bool uaccess_flush;
+DEFINE_STATIC_KEY_FALSE(uaccess_flush_key);
+EXPORT_SYMBOL(uaccess_flush_key);
static int __init handle_no_rfi_flush(char *p)
{
@@ -955,6 +961,22 @@
}
early_param("no_rfi_flush", handle_no_rfi_flush);
+static int __init handle_no_entry_flush(char *p)
+{
+ pr_info("entry-flush: disabled on command line.");
+ no_entry_flush = true;
+ return 0;
+}
+early_param("no_entry_flush", handle_no_entry_flush);
+
+static int __init handle_no_uaccess_flush(char *p)
+{
+ pr_info("uaccess-flush: disabled on command line.");
+ no_uaccess_flush = true;
+ return 0;
+}
+early_param("no_uaccess_flush", handle_no_uaccess_flush);
+
/*
* The RFI flush is not KPTI, but because users will see doco that says to use
* nopti we hijack that option here to also disable the RFI flush.
@@ -986,6 +1008,32 @@
rfi_flush = enable;
}
+void entry_flush_enable(bool enable)
+{
+ if (enable) {
+ do_entry_flush_fixups(enabled_flush_types);
+ on_each_cpu(do_nothing, NULL, 1);
+ } else {
+ do_entry_flush_fixups(L1D_FLUSH_NONE);
+ }
+
+ entry_flush = enable;
+}
+
+void uaccess_flush_enable(bool enable)
+{
+ if (enable) {
+ do_uaccess_flush_fixups(enabled_flush_types);
+ static_branch_enable(&uaccess_flush_key);
+ on_each_cpu(do_nothing, NULL, 1);
+ } else {
+ static_branch_disable(&uaccess_flush_key);
+ do_uaccess_flush_fixups(L1D_FLUSH_NONE);
+ }
+
+ uaccess_flush = enable;
+}
+
static void __ref init_fallback_flush(void)
{
u64 l1d_size, limit;
@@ -1044,10 +1092,28 @@
enabled_flush_types = types;
- if (!no_rfi_flush && !cpu_mitigations_off())
+ if (!cpu_mitigations_off() && !no_rfi_flush)
rfi_flush_enable(enable);
}
+void setup_entry_flush(bool enable)
+{
+ if (cpu_mitigations_off())
+ return;
+
+ if (!no_entry_flush)
+ entry_flush_enable(enable);
+}
+
+void setup_uaccess_flush(bool enable)
+{
+ if (cpu_mitigations_off())
+ return;
+
+ if (!no_uaccess_flush)
+ uaccess_flush_enable(enable);
+}
+
#ifdef CONFIG_DEBUG_FS
static int rfi_flush_set(void *data, u64 val)
{
@@ -1075,9 +1141,63 @@
DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n");
+static int entry_flush_set(void *data, u64 val)
+{
+ bool enable;
+
+ if (val == 1)
+ enable = true;
+ else if (val == 0)
+ enable = false;
+ else
+ return -EINVAL;
+
+ /* Only do anything if we're changing state */
+ if (enable != entry_flush)
+ entry_flush_enable(enable);
+
+ return 0;
+}
+
+static int entry_flush_get(void *data, u64 *val)
+{
+ *val = entry_flush ? 1 : 0;
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_entry_flush, entry_flush_get, entry_flush_set, "%llu\n");
+
+static int uaccess_flush_set(void *data, u64 val)
+{
+ bool enable;
+
+ if (val == 1)
+ enable = true;
+ else if (val == 0)
+ enable = false;
+ else
+ return -EINVAL;
+
+ /* Only do anything if we're changing state */
+ if (enable != uaccess_flush)
+ uaccess_flush_enable(enable);
+
+ return 0;
+}
+
+static int uaccess_flush_get(void *data, u64 *val)
+{
+ *val = uaccess_flush ? 1 : 0;
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_uaccess_flush, uaccess_flush_get, uaccess_flush_set, "%llu\n");
+
static __init int rfi_flush_debugfs_init(void)
{
debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush);
+ debugfs_create_file("entry_flush", 0600, powerpc_debugfs_root, NULL, &fops_entry_flush);
+ debugfs_create_file("uaccess_flush", 0600, powerpc_debugfs_root, NULL, &fops_uaccess_flush);
return 0;
}
device_initcall(rfi_flush_debugfs_init);
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 3c6b982..8c2857c 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1393,13 +1393,14 @@
/* Activate a secondary processor. */
void start_secondary(void *unused)
{
- unsigned int cpu = smp_processor_id();
+ unsigned int cpu = raw_smp_processor_id();
mmgrab(&init_mm);
current->active_mm = &init_mm;
smp_store_cpu_info(cpu);
set_dec(tb_ticks_per_jiffy);
+ rcu_cpu_starting(cpu);
preempt_disable();
cpu_callin_map[cpu] = 1;
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index 8e50818..310bcd7 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -2,7 +2,7 @@
#include <linux/err.h>
#include <asm/asm-prototypes.h>
-#include <asm/book3s/64/kup-radix.h>
+#include <asm/kup.h>
#include <asm/cputime.h>
#include <asm/hw_irq.h>
#include <asm/kprobes.h>
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index e0548b4..6db90cd 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -132,6 +132,20 @@
}
. = ALIGN(8);
+ __uaccess_flush_fixup : AT(ADDR(__uaccess_flush_fixup) - LOAD_OFFSET) {
+ __start___uaccess_flush_fixup = .;
+ *(__uaccess_flush_fixup)
+ __stop___uaccess_flush_fixup = .;
+ }
+
+ . = ALIGN(8);
+ __entry_flush_fixup : AT(ADDR(__entry_flush_fixup) - LOAD_OFFSET) {
+ __start___entry_flush_fixup = .;
+ *(__entry_flush_fixup)
+ __stop___entry_flush_fixup = .;
+ }
+
+ . = ALIGN(8);
__stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) {
__start___stf_exit_barrier_fixup = .;
*(__stf_exit_barrier_fixup)
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 4c0a7ee..321c12a 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -234,6 +234,110 @@
do_stf_exit_barrier_fixups(types);
}
+void do_uaccess_flush_fixups(enum l1d_flush_type types)
+{
+ unsigned int instrs[4], *dest;
+ long *start, *end;
+ int i;
+
+ start = PTRRELOC(&__start___uaccess_flush_fixup);
+ end = PTRRELOC(&__stop___uaccess_flush_fixup);
+
+ instrs[0] = 0x60000000; /* nop */
+ instrs[1] = 0x60000000; /* nop */
+ instrs[2] = 0x60000000; /* nop */
+ instrs[3] = 0x4e800020; /* blr */
+
+ i = 0;
+ if (types == L1D_FLUSH_FALLBACK) {
+ instrs[3] = 0x60000000; /* nop */
+ /* fallthrough to fallback flush */
+ }
+
+ if (types & L1D_FLUSH_ORI) {
+ instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+ instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+ }
+
+ if (types & L1D_FLUSH_MTTRIG)
+ instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+ for (i = 0; start < end; start++, i++) {
+ dest = (void *)start + *start;
+
+ pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+ patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0]));
+
+ patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1]));
+ patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2]));
+ patch_instruction((struct ppc_inst *)(dest + 3), ppc_inst(instrs[3]));
+ }
+
+ printk(KERN_DEBUG "uaccess-flush: patched %d locations (%s flush)\n", i,
+ (types == L1D_FLUSH_NONE) ? "no" :
+ (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" :
+ (types & L1D_FLUSH_ORI) ? (types & L1D_FLUSH_MTTRIG)
+ ? "ori+mttrig type"
+ : "ori type" :
+ (types & L1D_FLUSH_MTTRIG) ? "mttrig type"
+ : "unknown");
+}
+
+void do_entry_flush_fixups(enum l1d_flush_type types)
+{
+ unsigned int instrs[3], *dest;
+ long *start, *end;
+ int i;
+
+ start = PTRRELOC(&__start___entry_flush_fixup);
+ end = PTRRELOC(&__stop___entry_flush_fixup);
+
+ instrs[0] = 0x60000000; /* nop */
+ instrs[1] = 0x60000000; /* nop */
+ instrs[2] = 0x60000000; /* nop */
+
+ i = 0;
+ if (types == L1D_FLUSH_FALLBACK) {
+ instrs[i++] = 0x7d4802a6; /* mflr r10 */
+ instrs[i++] = 0x60000000; /* branch patched below */
+ instrs[i++] = 0x7d4803a6; /* mtlr r10 */
+ }
+
+ if (types & L1D_FLUSH_ORI) {
+ instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+ instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+ }
+
+ if (types & L1D_FLUSH_MTTRIG)
+ instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+ for (i = 0; start < end; start++, i++) {
+ dest = (void *)start + *start;
+
+ pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+ patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0]));
+
+ if (types == L1D_FLUSH_FALLBACK)
+ patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&entry_flush_fallback,
+ BRANCH_SET_LINK);
+ else
+ patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1]));
+
+ patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2]));
+ }
+
+ printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i,
+ (types == L1D_FLUSH_NONE) ? "no" :
+ (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" :
+ (types & L1D_FLUSH_ORI) ? (types & L1D_FLUSH_MTTRIG)
+ ? "ori+mttrig type"
+ : "ori type" :
+ (types & L1D_FLUSH_MTTRIG) ? "mttrig type"
+ : "unknown");
+}
+
void do_rfi_flush_fixups(enum l1d_flush_type types)
{
unsigned int instrs[3], *dest;
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index 9ed4fcc..7b25548 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -1336,7 +1336,7 @@
/* If this is a valid record, create the sample */
struct perf_output_handle handle;
- if (perf_output_begin(&handle, event, header.size))
+ if (perf_output_begin(&handle, &data, event, header.size))
return;
perf_output_sample(&handle, &header, &data, event);
diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c
index 8e53f2f..6f681b1 100644
--- a/arch/powerpc/perf/perf_regs.c
+++ b/arch/powerpc/perf/perf_regs.c
@@ -144,8 +144,7 @@
}
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
regs_user->regs = task_pt_regs(current);
regs_user->abi = (regs_user->regs) ? perf_reg_abi(current) :
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 9acaa0f..4611523 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -98,7 +98,7 @@
security_ftr_clear(SEC_FTR_BNDS_CHK_SPEC_BAR);
}
-static void pnv_setup_rfi_flush(void)
+static void pnv_setup_security_mitigations(void)
{
struct device_node *np, *fw_features;
enum l1d_flush_type type;
@@ -122,12 +122,31 @@
type = L1D_FLUSH_ORI;
}
+ /*
+ * If we are non-Power9 bare metal, we don't need to flush on kernel
+ * entry or after user access: they fix a P9 specific vulnerability.
+ */
+ if (!pvr_version_is(PVR_POWER9)) {
+ security_ftr_clear(SEC_FTR_L1D_FLUSH_ENTRY);
+ security_ftr_clear(SEC_FTR_L1D_FLUSH_UACCESS);
+ }
+
enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && \
(security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR) || \
security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV));
setup_rfi_flush(type, enable);
setup_count_cache_flush();
+
+ enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY);
+ setup_entry_flush(enable);
+
+ enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS);
+ setup_uaccess_flush(enable);
+
+ setup_stf_barrier();
}
static void __init pnv_check_guarded_cores(void)
@@ -156,8 +175,7 @@
{
set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
- pnv_setup_rfi_flush();
- setup_stf_barrier();
+ pnv_setup_security_mitigations();
/* Initialize SMP */
pnv_smp_init();
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index d6f4162..2f73cb5 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -349,8 +349,8 @@
cpus_read_unlock();
- /* Possibly switch to a new RFI flush type */
- pseries_setup_rfi_flush();
+ /* Possibly switch to a new L1 flush type */
+ pseries_setup_security_mitigations();
/* Reinitialise system information for hv-24x7 */
read_24x7_sys_info();
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 13fa370a..5938408 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -111,7 +111,7 @@
int dlpar_workqueue_init(void);
-void pseries_setup_rfi_flush(void);
+void pseries_setup_security_mitigations(void);
void pseries_lpar_read_hblkrm_characteristics(void);
#endif /* _PSERIES_PSERIES_H */
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 633c45e..090c13f 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -542,7 +542,7 @@
security_ftr_clear(SEC_FTR_BNDS_CHK_SPEC_BAR);
}
-void pseries_setup_rfi_flush(void)
+void pseries_setup_security_mitigations(void)
{
struct h_cpu_char_result result;
enum l1d_flush_type types;
@@ -579,6 +579,16 @@
setup_rfi_flush(types, enable);
setup_count_cache_flush();
+
+ enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY);
+ setup_entry_flush(enable);
+
+ enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS);
+ setup_uaccess_flush(enable);
+
+ setup_stf_barrier();
}
#ifdef CONFIG_PCI_IOV
@@ -768,8 +778,7 @@
fwnmi_init();
- pseries_setup_rfi_flush();
- setup_stf_barrier();
+ pseries_setup_security_mitigations();
pseries_lpar_read_hblkrm_characteristics();
/* By default, only probe PCI (can be overridden by rtas_pci) */
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index c47e6b3..824b2c9 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -476,7 +476,7 @@
do { \
long __kr_err; \
\
- __put_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \
+ __put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \
if (unlikely(__kr_err)) \
goto err_label; \
} while (0)
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 99e12fa..765b624 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2013 Linaro Limited
* Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 11e2a4f..7e84979 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -35,6 +35,10 @@
.word 0
#endif
.balign 8
+#ifdef CONFIG_RISCV_M_MODE
+ /* Image load offset (0MB) from start of RAM for M-mode */
+ .dword 0
+#else
#if __riscv_xlen == 64
/* Image load offset(2MB) from start of RAM */
.dword 0x200000
@@ -42,6 +46,7 @@
/* Image load offset(4MB) from start of RAM */
.dword 0x400000
#endif
+#endif
/* Effective size of kernel image */
.dword _end - _start
.dword __HEAD_FLAGS
diff --git a/arch/riscv/kernel/perf_regs.c b/arch/riscv/kernel/perf_regs.c
index 04a38fb..fd304a2 100644
--- a/arch/riscv/kernel/perf_regs.c
+++ b/arch/riscv/kernel/perf_regs.c
@@ -36,8 +36,7 @@
}
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
regs_user->regs = task_pt_regs(current);
regs_user->abi = perf_reg_abi(current);
diff --git a/arch/riscv/kernel/vdso/.gitignore b/arch/riscv/kernel/vdso/.gitignore
index 11ebee9..3a19def 100644
--- a/arch/riscv/kernel/vdso/.gitignore
+++ b/arch/riscv/kernel/vdso/.gitignore
@@ -1,3 +1,4 @@
# SPDX-License-Identifier: GPL-2.0-only
vdso.lds
*.tmp
+vdso-syms.S
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 7d6a94d..cb8f9e4 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -43,19 +43,14 @@
SYSCFLAGS_vdso.so.dbg = $(c_flags)
$(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE
$(call if_changed,vdsold)
+SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
+ -Wl,--build-id -Wl,--hash-style=both
# We also create a special relocatable object that should mirror the symbol
# table and layout of the linked DSO. With ld --just-symbols we can then
# refer to these symbols in the kernel code rather than hand-coded addresses.
-
-SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
- -Wl,--build-id=sha1 -Wl,--hash-style=both
-$(obj)/vdso-dummy.o: $(src)/vdso.lds $(obj)/rt_sigreturn.o FORCE
- $(call if_changed,vdsold)
-
-LDFLAGS_vdso-syms.o := -r --just-symbols
-$(obj)/vdso-syms.o: $(obj)/vdso-dummy.o FORCE
- $(call if_changed,ld)
+$(obj)/vdso-syms.S: $(obj)/vdso.so FORCE
+ $(call if_changed,so2s)
# strip rule for the .so file
$(obj)/%.so: OBJCOPYFLAGS := -S
@@ -73,6 +68,11 @@
$(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \
rm $@.tmp
+# Extracts symbol offsets from the VDSO, converting them into an assembly file
+# that contains the same symbols at the same offsets.
+quiet_cmd_so2s = SO2S $@
+ cmd_so2s = $(NM) -D $< | $(srctree)/$(src)/so2s.sh > $@
+
# install commands for the unstripped file
quiet_cmd_vdso_install = INSTALL $@
cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
diff --git a/arch/riscv/kernel/vdso/so2s.sh b/arch/riscv/kernel/vdso/so2s.sh
new file mode 100755
index 0000000..e64cb6d
--- /dev/null
+++ b/arch/riscv/kernel/vdso/so2s.sh
@@ -0,0 +1,6 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+# Copyright 2020 Palmer Dabbelt <palmerdabbelt@google.com>
+
+sed 's!\([0-9a-f]*\) T \([a-z0-9_]*\)\(@@LINUX_4.15\)*!.global \2\n.set \2,0x\1!' \
+| grep '^\.'
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 1359e21..3c8b9e4 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -86,6 +86,7 @@
pmd_t *pmd, *pmd_k;
pte_t *pte_k;
int index;
+ unsigned long pfn;
/* User mode accesses just cause a SIGSEGV */
if (user_mode(regs))
@@ -100,7 +101,8 @@
* of a task switch.
*/
index = pgd_index(addr);
- pgd = (pgd_t *)pfn_to_virt(csr_read(CSR_SATP)) + index;
+ pfn = csr_read(CSR_SATP) & SATP_PPN;
+ pgd = (pgd_t *)pfn_to_virt(pfn) + index;
pgd_k = init_mm.pgd + index;
if (!pgd_present(*pgd_k)) {
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index ea933b7..8e577f1 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -154,9 +154,8 @@
void __init setup_bootmem(void)
{
- phys_addr_t mem_size = 0;
- phys_addr_t total_mem = 0;
- phys_addr_t mem_start, start, end = 0;
+ phys_addr_t mem_start = 0;
+ phys_addr_t start, end = 0;
phys_addr_t vmlinux_end = __pa_symbol(&_end);
phys_addr_t vmlinux_start = __pa_symbol(&_start);
u64 i;
@@ -164,21 +163,18 @@
/* Find the memory region containing the kernel */
for_each_mem_range(i, &start, &end) {
phys_addr_t size = end - start;
- if (!total_mem)
+ if (!mem_start)
mem_start = start;
if (start <= vmlinux_start && vmlinux_end <= end)
BUG_ON(size == 0);
- total_mem = total_mem + size;
}
/*
- * Remove memblock from the end of usable area to the
- * end of region
+ * The maximal physical memory size is -PAGE_OFFSET.
+ * Make sure that any memory beyond mem_start + (-PAGE_OFFSET) is removed
+ * as it is unusable by kernel.
*/
- mem_size = min(total_mem, (phys_addr_t)-PAGE_OFFSET);
- if (mem_start + mem_size < end)
- memblock_remove(mem_start + mem_size,
- end - mem_start - mem_size);
+ memblock_enforce_memory_limit(mem_start - PAGE_OFFSET);
/* Reserve from the start of the kernel to the end of the kernel */
memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
@@ -297,6 +293,7 @@
#define NUM_EARLY_PMDS (1UL + MAX_EARLY_MAPPING_SIZE / PGDIR_SIZE)
#endif
pmd_t early_pmd[PTRS_PER_PMD * NUM_EARLY_PMDS] __initdata __aligned(PAGE_SIZE);
+pmd_t early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
static pmd_t *__init get_pmd_virt_early(phys_addr_t pa)
{
@@ -494,6 +491,18 @@
load_pa + (va - PAGE_OFFSET),
map_size, PAGE_KERNEL_EXEC);
+#ifndef __PAGETABLE_PMD_FOLDED
+ /* Setup early PMD for DTB */
+ create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA,
+ (uintptr_t)early_dtb_pmd, PGDIR_SIZE, PAGE_TABLE);
+ /* Create two consecutive PMD mappings for FDT early scan */
+ pa = dtb_pa & ~(PMD_SIZE - 1);
+ create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA,
+ pa, PMD_SIZE, PAGE_KERNEL);
+ create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA + PMD_SIZE,
+ pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL);
+ dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PMD_SIZE - 1));
+#else
/* Create two consecutive PGD mappings for FDT early scan */
pa = dtb_pa & ~(PGDIR_SIZE - 1);
create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA,
@@ -501,6 +510,7 @@
create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA + PGDIR_SIZE,
pa + PGDIR_SIZE, PGDIR_SIZE, PAGE_KERNEL);
dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PGDIR_SIZE - 1));
+#endif
dtb_early_pa = dtb_pa;
/*
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 0784bf3..fe6f529 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -1,3 +1,4 @@
+CONFIG_UAPI_HEADER_TEST=y
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
CONFIG_WATCH_QUEUE=y
@@ -93,9 +94,10 @@
CONFIG_FRONTSWAP=y
CONFIG_CMA_DEBUG=y
CONFIG_CMA_DEBUGFS=y
+CONFIG_CMA_AREAS=7
CONFIG_MEM_SOFT_DIRTY=y
CONFIG_ZSWAP=y
-CONFIG_ZSMALLOC=m
+CONFIG_ZSMALLOC=y
CONFIG_ZSMALLOC_STAT=y
CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
CONFIG_IDLE_PAGE_TRACKING=y
@@ -378,7 +380,6 @@
CONFIG_CGROUP_NET_PRIO=y
CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
-# CONFIG_NET_DROP_MONITOR is not set
CONFIG_PCI=y
# CONFIG_PCIEASPM is not set
CONFIG_PCI_DEBUG=y
@@ -386,7 +387,7 @@
CONFIG_HOTPLUG_PCI_S390=y
CONFIG_DEVTMPFS=y
CONFIG_CONNECTOR=y
-CONFIG_ZRAM=m
+CONFIG_ZRAM=y
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_DRBD=m
@@ -689,6 +690,7 @@
CONFIG_CRYPTO_DH=m
CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_ECRDSA=m
+CONFIG_CRYPTO_SM2=m
CONFIG_CRYPTO_CURVE25519=m
CONFIG_CRYPTO_GCM=y
CONFIG_CRYPTO_CHACHA20POLY1305=m
@@ -709,7 +711,6 @@
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
@@ -753,6 +754,7 @@
CONFIG_CRYPTO_AES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
CONFIG_CRYPTO_CRC32_S390=y
+CONFIG_CRYPTO_DEV_VIRTIO=m
CONFIG_CORDIC=m
CONFIG_CRC32_SELFTEST=y
CONFIG_CRC4=m
@@ -829,6 +831,7 @@
CONFIG_FAULT_INJECTION=y
CONFIG_FAILSLAB=y
CONFIG_FAIL_PAGE_ALLOC=y
+CONFIG_FAULT_INJECTION_USERCOPY=y
CONFIG_FAIL_MAKE_REQUEST=y
CONFIG_FAIL_IO_TIMEOUT=y
CONFIG_FAIL_FUTEX=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 905bc8c..17d5df2c 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -87,9 +87,10 @@
CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_CLEANCACHE=y
CONFIG_FRONTSWAP=y
+CONFIG_CMA_AREAS=7
CONFIG_MEM_SOFT_DIRTY=y
CONFIG_ZSWAP=y
-CONFIG_ZSMALLOC=m
+CONFIG_ZSMALLOC=y
CONFIG_ZSMALLOC_STAT=y
CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
CONFIG_IDLE_PAGE_TRACKING=y
@@ -371,7 +372,6 @@
CONFIG_CGROUP_NET_PRIO=y
CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
-# CONFIG_NET_DROP_MONITOR is not set
CONFIG_PCI=y
# CONFIG_PCIEASPM is not set
CONFIG_HOTPLUG_PCI=y
@@ -379,7 +379,7 @@
CONFIG_UEVENT_HELPER=y
CONFIG_DEVTMPFS=y
CONFIG_CONNECTOR=y
-CONFIG_ZRAM=m
+CONFIG_ZRAM=y
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_DRBD=m
@@ -680,6 +680,7 @@
CONFIG_CRYPTO_DH=m
CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_ECRDSA=m
+CONFIG_CRYPTO_SM2=m
CONFIG_CRYPTO_CURVE25519=m
CONFIG_CRYPTO_GCM=y
CONFIG_CRYPTO_CHACHA20POLY1305=m
@@ -701,7 +702,6 @@
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
@@ -745,6 +745,7 @@
CONFIG_CRYPTO_AES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
CONFIG_CRYPTO_CRC32_S390=y
+CONFIG_CRYPTO_DEV_VIRTIO=m
CONFIG_CORDIC=m
CONFIG_PRIME_NUMBERS=m
CONFIG_CRC4=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 8f67c55..a302630 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -17,11 +17,11 @@
# CONFIG_CHSC_SCH is not set
# CONFIG_SCM_BUS is not set
CONFIG_CRASH_DUMP=y
-# CONFIG_SECCOMP is not set
# CONFIG_PFAULT is not set
# CONFIG_S390_HYPFS_FS is not set
# CONFIG_VIRTUALIZATION is not set
# CONFIG_S390_GUEST is not set
+# CONFIG_SECCOMP is not set
CONFIG_PARTITION_ADVANCED=y
CONFIG_IBM_PARTITION=y
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 6b8d8c6..b5dbae7 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -692,16 +692,6 @@
return !!(pud_val(pud) & _REGION3_ENTRY_LARGE);
}
-static inline unsigned long pud_pfn(pud_t pud)
-{
- unsigned long origin_mask;
-
- origin_mask = _REGION_ENTRY_ORIGIN;
- if (pud_large(pud))
- origin_mask = _REGION3_ENTRY_ORIGIN_LARGE;
- return (pud_val(pud) & origin_mask) >> PAGE_SHIFT;
-}
-
#define pmd_leaf pmd_large
static inline int pmd_large(pmd_t pmd)
{
@@ -747,16 +737,6 @@
return pmd_val(pmd) == _SEGMENT_ENTRY_EMPTY;
}
-static inline unsigned long pmd_pfn(pmd_t pmd)
-{
- unsigned long origin_mask;
-
- origin_mask = _SEGMENT_ENTRY_ORIGIN;
- if (pmd_large(pmd))
- origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE;
- return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT;
-}
-
#define pmd_write pmd_write
static inline int pmd_write(pmd_t pmd)
{
@@ -1238,11 +1218,39 @@
#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
-#define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN)
-#define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN)
#define p4d_deref(pud) (p4d_val(pud) & _REGION_ENTRY_ORIGIN)
#define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN)
+static inline unsigned long pmd_deref(pmd_t pmd)
+{
+ unsigned long origin_mask;
+
+ origin_mask = _SEGMENT_ENTRY_ORIGIN;
+ if (pmd_large(pmd))
+ origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE;
+ return pmd_val(pmd) & origin_mask;
+}
+
+static inline unsigned long pmd_pfn(pmd_t pmd)
+{
+ return pmd_deref(pmd) >> PAGE_SHIFT;
+}
+
+static inline unsigned long pud_deref(pud_t pud)
+{
+ unsigned long origin_mask;
+
+ origin_mask = _REGION_ENTRY_ORIGIN;
+ if (pud_large(pud))
+ origin_mask = _REGION3_ENTRY_ORIGIN_LARGE;
+ return pud_val(pud) & origin_mask;
+}
+
+static inline unsigned long pud_pfn(pud_t pud)
+{
+ return pud_deref(pud) >> PAGE_SHIFT;
+}
+
/*
* The pgd_offset function *always* adds the index for the top-level
* region/segment table. This is done to get a sequence like the
diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h
index a996d39..0c21514 100644
--- a/arch/s390/include/asm/sections.h
+++ b/arch/s390/include/asm/sections.h
@@ -26,14 +26,14 @@
* final .boot.data section, which should be identical in the decompressor and
* the decompressed kernel (that is checked during the build).
*/
-#define __bootdata(var) __section(".boot.data.var") var
+#define __bootdata(var) __section(".boot.data." #var) var
/*
* .boot.preserved.data is similar to .boot.data, but it is not part of the
* .init section and thus will be preserved for later use in the decompressed
* kernel.
*/
-#define __bootdata_preserved(var) __section(".boot.preserved.data.var") var
+#define __bootdata_preserved(var) __section(".boot.preserved.data." #var) var
extern unsigned long __sdma, __edma;
extern unsigned long __stext_dma, __etext_dma;
diff --git a/arch/s390/include/asm/vdso/vdso.h b/arch/s390/include/asm/vdso/vdso.h
deleted file mode 100644
index e69de29..0000000
--- a/arch/s390/include/asm/vdso/vdso.h
+++ /dev/null
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index ece58f2..2012c1c 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -61,14 +61,6 @@
BLANK();
OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val);
BLANK();
- /* constants used by the vdso */
- DEFINE(__CLOCK_REALTIME, CLOCK_REALTIME);
- DEFINE(__CLOCK_MONOTONIC, CLOCK_MONOTONIC);
- DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
- DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
- DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID);
- DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC);
- BLANK();
/* idle data offsets */
OFFSET(__CLOCK_IDLE_ENTER, s390_idle_data, clock_idle_enter);
OFFSET(__CLOCK_IDLE_EXIT, s390_idle_data, clock_idle_exit);
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 8623591..5346545 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -422,6 +422,7 @@
#endif
LOCKDEP_SYS_EXIT
.Lsysc_tif:
+ DISABLE_INTS
TSTMSK __PT_FLAGS(%r11),_PIF_WORK
jnz .Lsysc_work
TSTMSK __TI_flags(%r12),_TIF_WORK
@@ -444,6 +445,7 @@
# One of the work bits is on. Find out which one.
#
.Lsysc_work:
+ ENABLE_INTS
TSTMSK __TI_flags(%r12),_TIF_NEED_RESCHED
jo .Lsysc_reschedule
TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL_RESTART
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 4f9e462..19cd7b9 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -672,7 +672,7 @@
rcu_read_lock();
perf_prepare_sample(&header, data, event, regs);
- if (perf_output_begin(&handle, event, header.size))
+ if (perf_output_begin(&handle, data, event, header.size))
goto out;
/* Update the process ID (see also kernel/events/core.c) */
@@ -2228,4 +2228,4 @@
}
arch_initcall(init_cpum_sampling_pmu);
-core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0640);
+core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0644);
diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c
index 4352a504..6e9e5d5 100644
--- a/arch/s390/kernel/perf_regs.c
+++ b/arch/s390/kernel/perf_regs.c
@@ -53,8 +53,7 @@
}
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
/*
* Use the regs from the first interruption and let
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index ebfe86d..390d97d 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -855,13 +855,14 @@
static void smp_init_secondary(void)
{
- int cpu = smp_processor_id();
+ int cpu = raw_smp_processor_id();
S390_lowcore.last_update_clock = get_tod_clock();
restore_access_regs(S390_lowcore.access_regs_save_area);
set_cpu_flag(CIF_ASCE_PRIMARY);
set_cpu_flag(CIF_ASCE_SECONDARY);
cpu_init();
+ rcu_cpu_starting(cpu);
preempt_disable();
init_cpu_timer();
vtime_init();
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index d33f215..9a6bae5 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -101,6 +101,10 @@
if (ret)
break;
+ /* the PCI function will be scanned once function 0 appears */
+ if (!zdev->zbus->bus)
+ break;
+
pdev = pci_scan_single_device(zdev->zbus->bus, zdev->devfn);
if (!pdev)
break;
diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h
index 5393e13..2bbf28c 100644
--- a/arch/um/include/asm/pgalloc.h
+++ b/arch/um/include/asm/pgalloc.h
@@ -33,7 +33,13 @@
} while (0)
#ifdef CONFIG_3_LEVEL_PGTABLES
-#define __pmd_free_tlb(tlb,x, address) tlb_remove_page((tlb),virt_to_page(x))
+
+#define __pmd_free_tlb(tlb, pmd, address) \
+do { \
+ pgtable_pmd_page_dtor(virt_to_page(pmd)); \
+ tlb_remove_page((tlb),virt_to_page(pmd)); \
+} while (0) \
+
#endif
#endif
diff --git a/arch/um/kernel/skas/clone.c b/arch/um/kernel/skas/clone.c
index 95c3551..bfb70c4 100644
--- a/arch/um/kernel/skas/clone.c
+++ b/arch/um/kernel/skas/clone.c
@@ -21,7 +21,7 @@
* on some systems.
*/
-void __section(".__syscall_stub")
+void __attribute__ ((__section__ (".__syscall_stub")))
stub_clone_handler(void)
{
struct stub_data *data = (struct stub_data *) STUB_DATA;
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
index a5e5db6..39b2ede 100644
--- a/arch/x86/boot/compressed/ident_map_64.c
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -164,6 +164,7 @@
add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE);
/* Load the new page-table. */
+ sev_verify_cbit(top_level_pgt);
write_cr3(top_level_pgt);
}
diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S
index dd07e7b..aa56179 100644
--- a/arch/x86/boot/compressed/mem_encrypt.S
+++ b/arch/x86/boot/compressed/mem_encrypt.S
@@ -68,6 +68,9 @@
SYM_FUNC_END(get_sev_encryption_bit)
.code64
+
+#include "../../kernel/sev_verify_cbit.S"
+
SYM_FUNC_START(set_sev_encryption_mask)
#ifdef CONFIG_AMD_MEM_ENCRYPT
push %rbp
@@ -81,6 +84,19 @@
bts %rax, sme_me_mask(%rip) /* Create the encryption mask */
+ /*
+ * Read MSR_AMD64_SEV again and store it to sev_status. Can't do this in
+ * get_sev_encryption_bit() because this function is 32-bit code and
+ * shared between 64-bit and 32-bit boot path.
+ */
+ movl $MSR_AMD64_SEV, %ecx /* Read the SEV MSR */
+ rdmsr
+
+ /* Store MSR value in sev_status */
+ shlq $32, %rdx
+ orq %rdx, %rax
+ movq %rax, sev_status(%rip)
+
.Lno_sev_mask:
movq %rbp, %rsp /* Restore original stack pointer */
@@ -96,5 +112,7 @@
#ifdef CONFIG_AMD_MEM_ENCRYPT
.balign 8
-SYM_DATA(sme_me_mask, .quad 0)
+SYM_DATA(sme_me_mask, .quad 0)
+SYM_DATA(sev_status, .quad 0)
+SYM_DATA(sev_check_data, .quad 0)
#endif
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 6d31f1b..d9a631c 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -159,4 +159,6 @@
void boot_stage1_vc(void);
void boot_stage2_vc(void);
+unsigned long sev_verify_cbit(unsigned long cr3);
+
#endif /* BOOT_COMPRESSED_MISC_H */
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index e508dbd..c44aba2 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -158,6 +158,7 @@
dctx->s[1] = get_unaligned_le32(&inp[4]);
dctx->s[2] = get_unaligned_le32(&inp[8]);
dctx->s[3] = get_unaligned_le32(&inp[12]);
+ acc += POLY1305_BLOCK_SIZE;
dctx->sset = true;
}
}
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 1f47e24..3798192 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -364,10 +364,10 @@
440 common process_madvise sys_process_madvise
#
-# x32-specific system call numbers start at 512 to avoid cache impact
-# for native 64-bit operation. The __x32_compat_sys stubs are created
-# on-the-fly for compat_sys_*() compatibility system calls if X86_X32
-# is defined.
+# Due to a historical design error, certain syscalls are numbered differently
+# in x32 as compared to native x86_64. These syscalls have numbers 512-547.
+# Do not add new syscalls to this range. Numbers 548 and above are available
+# for non-x32 use.
#
512 x32 rt_sigaction compat_sys_rt_sigaction
513 x32 rt_sigreturn compat_sys_x32_rt_sigreturn
@@ -405,3 +405,5 @@
545 x32 execveat compat_sys_execveat
546 x32 preadv2 compat_sys_preadv64v2
547 x32 pwritev2 compat_sys_pwritev64v2
+# This is the end of the legacy x32 range. Numbers 548 and above are
+# not special and are not to be used for x32-specific syscalls.
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index f1926e9..af457f8c 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2630,7 +2630,7 @@
u64 pebs_enabled = cpuc->pebs_enabled;
handled++;
- x86_pmu.drain_pebs(regs);
+ x86_pmu.drain_pebs(regs, &data);
status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
/*
@@ -4987,6 +4987,12 @@
x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */
+ if (version >= 5) {
+ x86_pmu.intel_cap.anythread_deprecated = edx.split.anythread_deprecated;
+ if (x86_pmu.intel_cap.anythread_deprecated)
+ pr_cont(" AnyThread deprecated, ");
+ }
+
/*
* Install the hw-cache-events table:
*/
@@ -5512,6 +5518,10 @@
x86_pmu.intel_ctrl |=
((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
+ /* AnyThread may be deprecated on arch perfmon v5 or later */
+ if (x86_pmu.intel_cap.anythread_deprecated)
+ x86_pmu.format_attrs = intel_arch_formats_attr;
+
if (x86_pmu.event_constraints) {
/*
* event on fixed counter2 (REF_CYCLES) only works on this
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 404315d..b47cc42 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -642,8 +642,8 @@
rcu_read_lock();
perf_prepare_sample(&header, &data, event, ®s);
- if (perf_output_begin(&handle, event, header.size *
- (top - base - skip)))
+ if (perf_output_begin(&handle, &data, event,
+ header.size * (top - base - skip)))
goto unlock;
for (at = base; at < top; at++) {
@@ -670,7 +670,9 @@
static inline void intel_pmu_drain_pebs_buffer(void)
{
- x86_pmu.drain_pebs(NULL);
+ struct perf_sample_data data;
+
+ x86_pmu.drain_pebs(NULL, &data);
}
/*
@@ -1719,23 +1721,24 @@
return 0;
}
-static void __intel_pmu_pebs_event(struct perf_event *event,
- struct pt_regs *iregs,
- void *base, void *top,
- int bit, int count,
- void (*setup_sample)(struct perf_event *,
- struct pt_regs *,
- void *,
- struct perf_sample_data *,
- struct pt_regs *))
+static __always_inline void
+__intel_pmu_pebs_event(struct perf_event *event,
+ struct pt_regs *iregs,
+ struct perf_sample_data *data,
+ void *base, void *top,
+ int bit, int count,
+ void (*setup_sample)(struct perf_event *,
+ struct pt_regs *,
+ void *,
+ struct perf_sample_data *,
+ struct pt_regs *))
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
- struct perf_sample_data data;
struct x86_perf_regs perf_regs;
struct pt_regs *regs = &perf_regs.regs;
void *at = get_next_pebs_record_by_bit(base, top, bit);
- struct pt_regs dummy_iregs;
+ static struct pt_regs dummy_iregs;
if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
/*
@@ -1752,14 +1755,14 @@
iregs = &dummy_iregs;
while (count > 1) {
- setup_sample(event, iregs, at, &data, regs);
- perf_event_output(event, &data, regs);
+ setup_sample(event, iregs, at, data, regs);
+ perf_event_output(event, data, regs);
at += cpuc->pebs_record_size;
at = get_next_pebs_record_by_bit(at, top, bit);
count--;
}
- setup_sample(event, iregs, at, &data, regs);
+ setup_sample(event, iregs, at, data, regs);
if (iregs == &dummy_iregs) {
/*
* The PEBS records may be drained in the non-overflow context,
@@ -1767,18 +1770,18 @@
* last record the same as other PEBS records, and doesn't
* invoke the generic overflow handler.
*/
- perf_event_output(event, &data, regs);
+ perf_event_output(event, data, regs);
} else {
/*
* All but the last records are processed.
* The last one is left to be able to call the overflow handler.
*/
- if (perf_event_overflow(event, &data, regs))
+ if (perf_event_overflow(event, data, regs))
x86_pmu_stop(event, 0);
}
}
-static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
+static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_data *data)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct debug_store *ds = cpuc->ds;
@@ -1812,7 +1815,7 @@
return;
}
- __intel_pmu_pebs_event(event, iregs, at, top, 0, n,
+ __intel_pmu_pebs_event(event, iregs, data, at, top, 0, n,
setup_pebs_fixed_sample_data);
}
@@ -1835,7 +1838,7 @@
}
}
-static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
+static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_data *data)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct debug_store *ds = cpuc->ds;
@@ -1942,14 +1945,14 @@
}
if (counts[bit]) {
- __intel_pmu_pebs_event(event, iregs, base,
+ __intel_pmu_pebs_event(event, iregs, data, base,
top, bit, counts[bit],
setup_pebs_fixed_sample_data);
}
}
}
-static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs)
+static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_data *data)
{
short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1997,7 +2000,7 @@
if (WARN_ON_ONCE(!event->attr.precise_ip))
continue;
- __intel_pmu_pebs_event(event, iregs, base,
+ __intel_pmu_pebs_event(event, iregs, data, base,
top, bit, counts[bit],
setup_pebs_adaptive_sample_data);
}
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 39e632e..bbd1120 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -475,7 +475,7 @@
static struct freerunning_counters snb_uncore_imc_freerunning[] = {
[SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
0x0, 0x0, 1, 32 },
- [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE,
+ [SNB_PCI_UNCORE_IMC_DATA_WRITES] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE,
0x0, 0x0, 1, 32 },
[SNB_PCI_UNCORE_IMC_GT_REQUESTS] = { SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE,
0x0, 0x0, 1, 32 },
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ee2b9b9..6a8edfe 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -585,6 +585,7 @@
u64 pebs_baseline:1;
u64 perf_metrics:1;
u64 pebs_output_pt_available:1;
+ u64 anythread_deprecated:1;
};
u64 capabilities;
};
@@ -727,7 +728,7 @@
int pebs_record_size;
int pebs_buffer_size;
int max_pebs_events;
- void (*drain_pebs)(struct pt_regs *regs);
+ void (*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data);
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
unsigned long large_pebs_flags;
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 40e0e32..284e736 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -273,11 +273,15 @@
pr_info("Hyper-V: Using enlightened APIC (%s mode)",
x2apic_enabled() ? "x2apic" : "xapic");
/*
- * With x2apic, architectural x2apic MSRs are equivalent to the
- * respective synthetic MSRs, so there's no need to override
- * the apic accessors. The only exception is
- * hv_apic_eoi_write, because it benefits from lazy EOI when
- * available, but it works for both xapic and x2apic modes.
+ * When in x2apic mode, don't use the Hyper-V specific APIC
+ * accessors since the field layout in the ICR register is
+ * different in x2apic mode. Furthermore, the architectural
+ * x2apic MSRs function just as well as the Hyper-V
+ * synthetic APIC MSRs, so there's no benefit in having
+ * separate Hyper-V accessors for x2apic mode. The only
+ * exception is hv_apic_eoi_write, because it benefits from
+ * lazy EOI when available, but the same accessor works for
+ * both xapic and x2apic because the field layout is the same.
*/
apic_set_eoi_write(hv_apic_eoi_write);
if (!x2apic_enabled()) {
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d44858b..324ddd7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -639,6 +639,7 @@
int cpuid_nent;
struct kvm_cpuid_entry2 *cpuid_entries;
+ unsigned long cr3_lm_rsvd_bits;
int maxphyaddr;
int max_tdp_level;
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 6960cd6..b9a7fd0 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -137,7 +137,9 @@
struct {
unsigned int num_counters_fixed:5;
unsigned int bit_width_fixed:8;
- unsigned int reserved:19;
+ unsigned int reserved1:2;
+ unsigned int anythread_deprecated:1;
+ unsigned int reserved2:16;
} split;
unsigned int full;
};
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index 172d3e4a..648eb23f 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -2,14 +2,8 @@
#ifndef _ASM_X86_UV_UV_H
#define _ASM_X86_UV_UV_H
-#include <asm/tlbflush.h>
-
enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC};
-struct cpumask;
-struct mm_struct;
-struct flush_tlb_info;
-
#ifdef CONFIG_X86_UV
#include <linux/efi.h>
@@ -44,10 +38,6 @@
static inline int is_uv_hubbed(int uv) { return 0; }
static inline void uv_cpu_init(void) { }
static inline void uv_system_init(void) { }
-static inline const struct cpumask *
-uv_flush_tlb_others(const struct cpumask *cpumask,
- const struct flush_tlb_info *info)
-{ return cpumask; }
#endif /* X86_UV */
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 812e9b4..950afeb 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -32,6 +32,7 @@
#define KVM_FEATURE_POLL_CONTROL 12
#define KVM_FEATURE_PV_SCHED_YIELD 13
#define KVM_FEATURE_ASYNC_PF_INT 14
+#define KVM_FEATURE_MSI_EXT_DEST_ID 15
#define KVM_HINTS_REALTIME 0
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 4adbe65..2400ad6 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -807,6 +807,15 @@
temp_mm_state_t temp_state;
lockdep_assert_irqs_disabled();
+
+ /*
+ * Make sure not to be in TLB lazy mode, as otherwise we'll end up
+ * with a stale address space WITHOUT being in lazy mode after
+ * restoring the previous mm.
+ */
+ if (this_cpu_read(cpu_tlbstate.is_lazy))
+ leave_mm(smp_processor_id());
+
temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm);
switch_mm_irqs_off(NULL, mm, current);
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 714233c..1b98f8c 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -33,7 +33,7 @@
static int uv_node_id;
/* Unpack AT/OEM/TABLE ID's to be NULL terminated strings */
-static u8 uv_archtype[UV_AT_SIZE];
+static u8 uv_archtype[UV_AT_SIZE + 1];
static u8 oem_id[ACPI_OEM_ID_SIZE + 1];
static u8 oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1];
@@ -290,6 +290,9 @@
{
/* Relies on 'to' being NULL chars so result will be NULL terminated */
strncpy(to, from, len-1);
+
+ /* Trim trailing spaces */
+ (void)strim(to);
}
/* Find UV arch type entry in UVsystab */
@@ -317,7 +320,7 @@
if (n > 0 && n < sizeof(uv_ate->archtype)) {
pr_info("UV: UVarchtype received from BIOS\n");
- uv_stringify(UV_AT_SIZE, uv_archtype, uv_ate->archtype);
+ uv_stringify(sizeof(uv_archtype), uv_archtype, uv_ate->archtype);
return 1;
}
return 0;
@@ -366,7 +369,7 @@
return ret;
}
-static int __init uv_set_system_type(char *_oem_id)
+static int __init uv_set_system_type(char *_oem_id, char *_oem_table_id)
{
/* Save OEM_ID passed from ACPI MADT */
uv_stringify(sizeof(oem_id), oem_id, _oem_id);
@@ -375,7 +378,7 @@
if (!early_get_arch_type())
/* If not use OEM ID for UVarchtype */
- uv_stringify(UV_AT_SIZE, uv_archtype, _oem_id);
+ uv_stringify(sizeof(uv_archtype), uv_archtype, oem_id);
/* Check if not hubbed */
if (strncmp(uv_archtype, "SGI", 3) != 0) {
@@ -386,13 +389,23 @@
/* (Not hubless), not a UV */
return 0;
+ /* Is UV hubless system */
+ uv_hubless_system = 0x01;
+
+ /* UV5 Hubless */
+ if (strncmp(uv_archtype, "NSGI5", 5) == 0)
+ uv_hubless_system |= 0x20;
+
/* UV4 Hubless: CH */
- if (strncmp(uv_archtype, "NSGI4", 5) == 0)
- uv_hubless_system = 0x11;
+ else if (strncmp(uv_archtype, "NSGI4", 5) == 0)
+ uv_hubless_system |= 0x10;
/* UV3 Hubless: UV300/MC990X w/o hub */
else
- uv_hubless_system = 0x9;
+ uv_hubless_system |= 0x8;
+
+ /* Copy APIC type */
+ uv_stringify(sizeof(oem_table_id), oem_table_id, _oem_table_id);
pr_info("UV: OEM IDs %s/%s, SystemType %d, HUBLESS ID %x\n",
oem_id, oem_table_id, uv_system_type, uv_hubless_system);
@@ -456,7 +469,7 @@
uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0;
/* If not UV, return. */
- if (likely(uv_set_system_type(_oem_id) == 0))
+ if (uv_set_system_type(_oem_id, _oem_table_id) == 0)
return 0;
/* Save and Decode OEM Table ID */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d3f0db46..581fb72 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1254,6 +1254,14 @@
return 0;
}
+static bool is_spec_ib_user_controlled(void)
+{
+ return spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL ||
+ spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP ||
+ spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL ||
+ spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP;
+}
+
static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
{
switch (ctrl) {
@@ -1261,16 +1269,26 @@
if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
return 0;
+
/*
- * Indirect branch speculation is always disabled in strict
- * mode. It can neither be enabled if it was force-disabled
- * by a previous prctl call.
+ * With strict mode for both IBPB and STIBP, the instruction
+ * code paths avoid checking this task flag and instead,
+ * unconditionally run the instruction. However, STIBP and IBPB
+ * are independent and either can be set to conditionally
+ * enabled regardless of the mode of the other.
+ *
+ * If either is set to conditional, allow the task flag to be
+ * updated, unless it was force-disabled by a previous prctl
+ * call. Currently, this is possible on an AMD CPU which has the
+ * feature X86_FEATURE_AMD_STIBP_ALWAYS_ON. In this case, if the
+ * kernel is booted with 'spectre_v2_user=seccomp', then
+ * spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP and
+ * spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED.
*/
- if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
- spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
- spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ||
+ if (!is_spec_ib_user_controlled() ||
task_spec_ib_force_disable(task))
return -EPERM;
+
task_clear_spec_ib_disable(task);
task_update_spec_tif(task);
break;
@@ -1283,10 +1301,10 @@
if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
return -EPERM;
- if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
- spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
- spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
+
+ if (!is_spec_ib_user_controlled())
return 0;
+
task_set_spec_ib_disable(task);
if (ctrl == PR_SPEC_FORCE_DISABLE)
task_set_spec_ib_force_disable(task);
@@ -1351,20 +1369,17 @@
if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
return PR_SPEC_ENABLE;
- else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
- spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
- spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
- return PR_SPEC_DISABLE;
- else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL ||
- spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP ||
- spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL ||
- spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) {
+ else if (is_spec_ib_user_controlled()) {
if (task_spec_ib_force_disable(task))
return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
if (task_spec_ib_disable(task))
return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
- } else
+ } else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
+ spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
+ spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
+ return PR_SPEC_DISABLE;
+ else
return PR_SPEC_NOT_AFFECTED;
}
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 7eb2a1c..3c41773 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -161,6 +161,21 @@
/* Setup early boot stage 4-/5-level pagetables. */
addq phys_base(%rip), %rax
+
+ /*
+ * For SEV guests: Verify that the C-bit is correct. A malicious
+ * hypervisor could lie about the C-bit position to perform a ROP
+ * attack on the guest by writing to the unencrypted stack and wait for
+ * the next RET instruction.
+ * %rsi carries pointer to realmode data and is callee-clobbered. Save
+ * and restore it.
+ */
+ pushq %rsi
+ movq %rax, %rdi
+ call sev_verify_cbit
+ popq %rsi
+
+ /* Switch to new page-table */
movq %rax, %cr3
/* Ensure I am executing from virtual addresses */
@@ -279,6 +294,7 @@
SYM_CODE_END(secondary_startup_64)
#include "verify_cpu.S"
+#include "sev_verify_cbit.S"
#ifdef CONFIG_HOTPLUG_CPU
/*
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 57c2ecf..ce831f9 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -200,8 +200,7 @@
params->hdr.hardware_subarch = boot_params.hdr.hardware_subarch;
/* Copying screen_info will do? */
- memcpy(¶ms->screen_info, &boot_params.screen_info,
- sizeof(struct screen_info));
+ memcpy(¶ms->screen_info, &screen_info, sizeof(struct screen_info));
/* Fill in memsize later */
params->screen_info.ext_mem_k = 0;
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index bb7e113..f9e5352 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -101,8 +101,7 @@
}
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
regs_user->regs = task_pt_regs(current);
regs_user->abi = perf_reg_abi(current);
@@ -129,12 +128,20 @@
return PERF_SAMPLE_REGS_ABI_64;
}
+static DEFINE_PER_CPU(struct pt_regs, nmi_user_regs);
+
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
+ struct pt_regs *regs_user_copy = this_cpu_ptr(&nmi_user_regs);
struct pt_regs *user_regs = task_pt_regs(current);
+ if (!in_nmi()) {
+ regs_user->regs = user_regs;
+ regs_user->abi = perf_reg_abi(current);
+ return;
+ }
+
/*
* If we're in an NMI that interrupted task_pt_regs setup, then
* we can't sample user regs at all. This check isn't really
diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c
index 5f83cca..7d04b35 100644
--- a/arch/x86/kernel/sev-es-shared.c
+++ b/arch/x86/kernel/sev-es-shared.c
@@ -178,6 +178,32 @@
goto fail;
regs->dx = val >> 32;
+ /*
+ * This is a VC handler and the #VC is only raised when SEV-ES is
+ * active, which means SEV must be active too. Do sanity checks on the
+ * CPUID results to make sure the hypervisor does not trick the kernel
+ * into the no-sev path. This could map sensitive data unencrypted and
+ * make it accessible to the hypervisor.
+ *
+ * In particular, check for:
+ * - Hypervisor CPUID bit
+ * - Availability of CPUID leaf 0x8000001f
+ * - SEV CPUID bit.
+ *
+ * The hypervisor might still report the wrong C-bit position, but this
+ * can't be checked here.
+ */
+
+ if ((fn == 1 && !(regs->cx & BIT(31))))
+ /* Hypervisor bit */
+ goto fail;
+ else if (fn == 0x80000000 && (regs->ax < 0x8000001f))
+ /* SEV leaf check */
+ goto fail;
+ else if ((fn == 0x8000001f && !(regs->ax & BIT(1))))
+ /* SEV bit */
+ goto fail;
+
/* Skip over the CPUID two-byte opcode */
regs->ip += 2;
diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c
index 4a96726..0bd1a0f 100644
--- a/arch/x86/kernel/sev-es.c
+++ b/arch/x86/kernel/sev-es.c
@@ -374,8 +374,8 @@
return ES_EXCEPTION;
}
-static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
- unsigned long vaddr, phys_addr_t *paddr)
+static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
+ unsigned long vaddr, phys_addr_t *paddr)
{
unsigned long va = (unsigned long)vaddr;
unsigned int level;
@@ -394,15 +394,19 @@
if (user_mode(ctxt->regs))
ctxt->fi.error_code |= X86_PF_USER;
- return false;
+ return ES_EXCEPTION;
}
+ if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC))
+ /* Emulated MMIO to/from encrypted memory not supported */
+ return ES_UNSUPPORTED;
+
pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
pa |= va & ~page_level_mask(level);
*paddr = pa;
- return true;
+ return ES_OK;
}
/* Include code shared with pre-decompression boot stage */
@@ -731,6 +735,7 @@
{
u64 exit_code, exit_info_1, exit_info_2;
unsigned long ghcb_pa = __pa(ghcb);
+ enum es_result res;
phys_addr_t paddr;
void __user *ref;
@@ -740,11 +745,12 @@
exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE;
- if (!vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr)) {
- if (!read)
+ res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr);
+ if (res != ES_OK) {
+ if (res == ES_EXCEPTION && !read)
ctxt->fi.error_code |= X86_PF_WRITE;
- return ES_EXCEPTION;
+ return res;
}
exit_info_1 = paddr;
diff --git a/arch/x86/kernel/sev_verify_cbit.S b/arch/x86/kernel/sev_verify_cbit.S
new file mode 100644
index 0000000..ee04941
--- /dev/null
+++ b/arch/x86/kernel/sev_verify_cbit.S
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * sev_verify_cbit.S - Code for verification of the C-bit position reported
+ * by the Hypervisor when running with SEV enabled.
+ *
+ * Copyright (c) 2020 Joerg Roedel (jroedel@suse.de)
+ *
+ * sev_verify_cbit() is called before switching to a new long-mode page-table
+ * at boot.
+ *
+ * Verify that the C-bit position is correct by writing a random value to
+ * an encrypted memory location while on the current page-table. Then it
+ * switches to the new page-table to verify the memory content is still the
+ * same. After that it switches back to the current page-table and when the
+ * check succeeded it returns. If the check failed the code invalidates the
+ * stack pointer and goes into a hlt loop. The stack-pointer is invalidated to
+ * make sure no interrupt or exception can get the CPU out of the hlt loop.
+ *
+ * New page-table pointer is expected in %rdi (first parameter)
+ *
+ */
+SYM_FUNC_START(sev_verify_cbit)
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+ /* First check if a C-bit was detected */
+ movq sme_me_mask(%rip), %rsi
+ testq %rsi, %rsi
+ jz 3f
+
+ /* sme_me_mask != 0 could mean SME or SEV - Check also for SEV */
+ movq sev_status(%rip), %rsi
+ testq %rsi, %rsi
+ jz 3f
+
+ /* Save CR4 in %rsi */
+ movq %cr4, %rsi
+
+ /* Disable Global Pages */
+ movq %rsi, %rdx
+ andq $(~X86_CR4_PGE), %rdx
+ movq %rdx, %cr4
+
+ /*
+ * Verified that running under SEV - now get a random value using
+ * RDRAND. This instruction is mandatory when running as an SEV guest.
+ *
+ * Don't bail out of the loop if RDRAND returns errors. It is better to
+ * prevent forward progress than to work with a non-random value here.
+ */
+1: rdrand %rdx
+ jnc 1b
+
+ /* Store value to memory and keep it in %rdx */
+ movq %rdx, sev_check_data(%rip)
+
+ /* Backup current %cr3 value to restore it later */
+ movq %cr3, %rcx
+
+ /* Switch to new %cr3 - This might unmap the stack */
+ movq %rdi, %cr3
+
+ /*
+ * Compare value in %rdx with memory location. If C-bit is incorrect
+ * this would read the encrypted data and make the check fail.
+ */
+ cmpq %rdx, sev_check_data(%rip)
+
+ /* Restore old %cr3 */
+ movq %rcx, %cr3
+
+ /* Restore previous CR4 */
+ movq %rsi, %cr4
+
+ /* Check CMPQ result */
+ je 3f
+
+ /*
+ * The check failed, prevent any forward progress to prevent ROP
+ * attacks, invalidate the stack and go into a hlt loop.
+ */
+ xorq %rsp, %rsp
+ subq $0x1000, %rsp
+2: hlt
+ jmp 2b
+3:
+#endif
+ /* Return page-table pointer */
+ movq %rdi, %rax
+ ret
+SYM_FUNC_END(sev_verify_cbit)
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 992fb14..420be87 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -514,9 +514,6 @@
if (!tboot_enabled())
return 0;
- if (intel_iommu_tboot_noforce)
- return 1;
-
if (no_iommu || swiotlb || dmar_disabled)
pr_warn("Forcing Intel-IOMMU to enabled\n");
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 3c70fb3..e19df6c 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -793,19 +793,6 @@
set_debugreg(DR6_RESERVED, 6);
dr6 ^= DR6_RESERVED; /* Flip to positive polarity */
- /*
- * Clear the virtual DR6 value, ptrace routines will set bits here for
- * things we want signals for.
- */
- current->thread.virtual_dr6 = 0;
-
- /*
- * The SDM says "The processor clears the BTF flag when it
- * generates a debug exception." Clear TIF_BLOCKSTEP to keep
- * TIF_BLOCKSTEP in sync with the hardware BTF flag.
- */
- clear_thread_flag(TIF_BLOCKSTEP);
-
return dr6;
}
@@ -873,6 +860,20 @@
*/
WARN_ON_ONCE(user_mode(regs));
+ if (test_thread_flag(TIF_BLOCKSTEP)) {
+ /*
+ * The SDM says "The processor clears the BTF flag when it
+ * generates a debug exception." but PTRACE_BLOCKSTEP requested
+ * it for userspace, but we just took a kernel #DB, so re-set
+ * BTF.
+ */
+ unsigned long debugctl;
+
+ rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+ debugctl |= DEBUGCTLMSR_BTF;
+ wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+ }
+
/*
* Catch SYSENTER with TF set and clear DR_STEP. If this hit a
* watchpoint at the same time then that will still be handled.
@@ -936,6 +937,22 @@
instrumentation_begin();
/*
+ * Start the virtual/ptrace DR6 value with just the DR_STEP mask
+ * of the real DR6. ptrace_triggered() will set the DR_TRAPn bits.
+ *
+ * Userspace expects DR_STEP to be visible in ptrace_get_debugreg(6)
+ * even if it is not the result of PTRACE_SINGLESTEP.
+ */
+ current->thread.virtual_dr6 = (dr6 & DR_STEP);
+
+ /*
+ * The SDM says "The processor clears the BTF flag when it
+ * generates a debug exception." Clear TIF_BLOCKSTEP to keep
+ * TIF_BLOCKSTEP in sync with the hardware BTF flag.
+ */
+ clear_thread_flag(TIF_BLOCKSTEP);
+
+ /*
* If dr6 has no reason to give us about the origin of this trap,
* then it's very likely the result of an icebp/int01 trap.
* User wants a sigtrap for that.
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 6a339ce..73f8001 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -321,19 +321,12 @@
unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
{
- struct task_struct *task = state->task;
-
if (unwind_done(state))
return NULL;
if (state->regs)
return &state->regs->ip;
- if (task != current && state->sp == task->thread.sp) {
- struct inactive_task_frame *frame = (void *)task->thread.sp;
- return &frame->ret_addr;
- }
-
if (state->sp)
return (unsigned long *)state->sp - 1;
@@ -663,7 +656,7 @@
} else {
struct inactive_task_frame *frame = (void *)task->thread.sp;
- state->sp = task->thread.sp;
+ state->sp = task->thread.sp + sizeof(*frame);
state->bp = READ_ONCE_NOCHECK(frame->bp);
state->ip = READ_ONCE_NOCHECK(frame->ret_addr);
state->signal = (void *)state->ip == ret_from_fork;
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 06a278b..83637a2 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -90,6 +90,20 @@
return 0;
}
+void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *best;
+
+ best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0);
+
+ /*
+ * save the feature bitmap to avoid cpuid lookup for every PV
+ * operation
+ */
+ if (best)
+ vcpu->arch.pv_cpuid.features = best->eax;
+}
+
void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
@@ -124,13 +138,6 @@
(best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
- /*
- * save the feature bitmap to avoid cpuid lookup for every PV
- * operation
- */
- if (best)
- vcpu->arch.pv_cpuid.features = best->eax;
-
if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) {
best = kvm_find_cpuid_entry(vcpu, 0x1, 0);
if (best)
@@ -162,6 +169,8 @@
vcpu->arch.guest_supported_xcr0 =
(best->eax | ((u64)best->edx << 32)) & supported_xcr0;
+ kvm_update_pv_runtime(vcpu);
+
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
kvm_mmu_reset_context(vcpu);
@@ -169,6 +178,8 @@
vcpu->arch.cr4_guest_rsvd_bits =
__cr4_reserved_bits(guest_cpuid_has, vcpu);
+ vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63);
+
/* Invoke the vendor callback only after the above state is updated. */
kvm_x86_ops.vcpu_after_set_cpuid(vcpu);
}
@@ -672,7 +683,9 @@
edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS);
edx.split.bit_width_fixed = cap.bit_width_fixed;
- edx.split.reserved = 0;
+ edx.split.anythread_deprecated = 1;
+ edx.split.reserved1 = 0;
+ edx.split.reserved2 = 0;
entry->eax = eax.full;
entry->ebx = cap.events_mask;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index bf85779..f7a6e8f 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -11,6 +11,7 @@
void kvm_set_cpu_caps(void);
void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu);
+void kvm_update_pv_runtime(struct kvm_vcpu *vcpu);
struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
u32 function, u32 index);
int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 0d917eb..56cae1f 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -4046,6 +4046,12 @@
return X86EMUL_CONTINUE;
}
+static int em_clflushopt(struct x86_emulate_ctxt *ctxt)
+{
+ /* emulating clflushopt regardless of cpuid */
+ return X86EMUL_CONTINUE;
+}
+
static int em_movsxd(struct x86_emulate_ctxt *ctxt)
{
ctxt->dst.val = (s32) ctxt->src.val;
@@ -4585,7 +4591,7 @@
};
static const struct gprefix pfx_0f_ae_7 = {
- I(SrcMem | ByteOp, em_clflush), N, N, N,
+ I(SrcMem | ByteOp, em_clflush), I(SrcMem | ByteOp, em_clflushopt), N, N,
};
static const struct group_dual group15 = { {
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 17587f4..5bb1939 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -225,7 +225,7 @@
{
u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask;
- gpa |= (spte >> shadow_nonpresent_or_rsvd_mask_len)
+ gpa |= (spte >> SHADOW_NONPRESENT_OR_RSVD_MASK_LEN)
& shadow_nonpresent_or_rsvd_mask;
return gpa >> PAGE_SHIFT;
@@ -591,15 +591,15 @@
static u64 restore_acc_track_spte(u64 spte)
{
u64 new_spte = spte;
- u64 saved_bits = (spte >> shadow_acc_track_saved_bits_shift)
- & shadow_acc_track_saved_bits_mask;
+ u64 saved_bits = (spte >> SHADOW_ACC_TRACK_SAVED_BITS_SHIFT)
+ & SHADOW_ACC_TRACK_SAVED_BITS_MASK;
WARN_ON_ONCE(spte_ad_enabled(spte));
WARN_ON_ONCE(!is_access_track_spte(spte));
new_spte &= ~shadow_acc_track_mask;
- new_spte &= ~(shadow_acc_track_saved_bits_mask <<
- shadow_acc_track_saved_bits_shift);
+ new_spte &= ~(SHADOW_ACC_TRACK_SAVED_BITS_MASK <<
+ SHADOW_ACC_TRACK_SAVED_BITS_SHIFT);
new_spte |= saved_bits;
return new_spte;
@@ -856,12 +856,14 @@
} else {
rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte);
desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
- while (desc->sptes[PTE_LIST_EXT-1] && desc->more) {
- desc = desc->more;
+ while (desc->sptes[PTE_LIST_EXT-1]) {
count += PTE_LIST_EXT;
- }
- if (desc->sptes[PTE_LIST_EXT-1]) {
- desc->more = mmu_alloc_pte_list_desc(vcpu);
+
+ if (!desc->more) {
+ desc->more = mmu_alloc_pte_list_desc(vcpu);
+ desc = desc->more;
+ break;
+ }
desc = desc->more;
}
for (i = 0; desc->sptes[i]; ++i)
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index d9c5665..fcac2ca 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -55,7 +55,7 @@
mask |= shadow_mmio_value | access;
mask |= gpa | shadow_nonpresent_or_rsvd_mask;
mask |= (gpa & shadow_nonpresent_or_rsvd_mask)
- << shadow_nonpresent_or_rsvd_mask_len;
+ << SHADOW_NONPRESENT_OR_RSVD_MASK_LEN;
return mask;
}
@@ -231,12 +231,12 @@
!spte_can_locklessly_be_made_writable(spte),
"kvm: Writable SPTE is not locklessly dirty-trackable\n");
- WARN_ONCE(spte & (shadow_acc_track_saved_bits_mask <<
- shadow_acc_track_saved_bits_shift),
+ WARN_ONCE(spte & (SHADOW_ACC_TRACK_SAVED_BITS_MASK <<
+ SHADOW_ACC_TRACK_SAVED_BITS_SHIFT),
"kvm: Access Tracking saved bit locations are not zero\n");
- spte |= (spte & shadow_acc_track_saved_bits_mask) <<
- shadow_acc_track_saved_bits_shift;
+ spte |= (spte & SHADOW_ACC_TRACK_SAVED_BITS_MASK) <<
+ SHADOW_ACC_TRACK_SAVED_BITS_SHIFT;
spte &= ~shadow_acc_track_mask;
return spte;
@@ -245,7 +245,7 @@
void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 access_mask)
{
BUG_ON((u64)(unsigned)access_mask != access_mask);
- WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << shadow_nonpresent_or_rsvd_mask_len));
+ WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << SHADOW_NONPRESENT_OR_RSVD_MASK_LEN));
WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask);
shadow_mmio_value = mmio_value | SPTE_MMIO_MASK;
shadow_mmio_access_mask = access_mask;
@@ -306,9 +306,9 @@
low_phys_bits = boot_cpu_data.x86_phys_bits;
if (boot_cpu_has_bug(X86_BUG_L1TF) &&
!WARN_ON_ONCE(boot_cpu_data.x86_cache_bits >=
- 52 - shadow_nonpresent_or_rsvd_mask_len)) {
+ 52 - SHADOW_NONPRESENT_OR_RSVD_MASK_LEN)) {
low_phys_bits = boot_cpu_data.x86_cache_bits
- - shadow_nonpresent_or_rsvd_mask_len;
+ - SHADOW_NONPRESENT_OR_RSVD_MASK_LEN;
shadow_nonpresent_or_rsvd_mask =
rsvd_bits(low_phys_bits, boot_cpu_data.x86_cache_bits - 1);
}
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 4ecf40e..5c75a45 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -105,19 +105,19 @@
extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
/*
+ * The number of high-order 1 bits to use in the mask above.
+ */
+#define SHADOW_NONPRESENT_OR_RSVD_MASK_LEN 5
+
+/*
* The mask/shift to use for saving the original R/X bits when marking the PTE
* as not-present for access tracking purposes. We do not save the W bit as the
* PTEs being access tracked also need to be dirty tracked, so the W bit will be
* restored only when a write is attempted to the page.
*/
-static const u64 shadow_acc_track_saved_bits_mask = PT64_EPT_READABLE_MASK |
- PT64_EPT_EXECUTABLE_MASK;
-static const u64 shadow_acc_track_saved_bits_shift = PT64_SECOND_AVAIL_BITS_SHIFT;
-
-/*
- * The number of high-order 1 bits to use in the mask above.
- */
-static const u64 shadow_nonpresent_or_rsvd_mask_len = 5;
+#define SHADOW_ACC_TRACK_SAVED_BITS_MASK (PT64_EPT_READABLE_MASK | \
+ PT64_EPT_EXECUTABLE_MASK)
+#define SHADOW_ACC_TRACK_SAVED_BITS_SHIFT PT64_SECOND_AVAIL_BITS_SHIFT
/*
* In some cases, we need to preserve the GFN of a non-present or reserved
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 27e381c..ff28a5c 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -49,7 +49,14 @@
{
struct kvm_mmu_page *sp;
+ if (!kvm->arch.tdp_mmu_enabled)
+ return false;
+ if (WARN_ON(!VALID_PAGE(hpa)))
+ return false;
+
sp = to_shadow_page(hpa);
+ if (WARN_ON(!sp))
+ return false;
return sp->tdp_mmu_page && sp->root_count;
}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 2f32fd0..1e81cfe 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3741,6 +3741,7 @@
static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ struct kvm_cpuid_entry2 *best;
vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
boot_cpu_has(X86_FEATURE_XSAVE) &&
@@ -3753,6 +3754,13 @@
/* Check again if INVPCID interception if required */
svm_check_invpcid(svm);
+ /* For sev guests, the memory encryption bit is not reserved in CR3. */
+ if (sev_guest(vcpu->kvm)) {
+ best = kvm_find_cpuid_entry(vcpu, 0x8000001F, 0);
+ if (best)
+ vcpu->arch.cr3_lm_rsvd_bits &= ~(1UL << (best->ebx & 0x3f));
+ }
+
if (!kvm_vcpu_apicv_active(vcpu))
return;
diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c
index e5325bd..f3199bb 100644
--- a/arch/x86/kvm/vmx/evmcs.c
+++ b/arch/x86/kvm/vmx/evmcs.c
@@ -297,14 +297,13 @@
};
const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1);
-void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf)
+__init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf)
{
vmcs_conf->pin_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_PINCTRL;
vmcs_conf->cpu_based_2nd_exec_ctrl &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
vmcs_conf->vmexit_ctrl &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
vmcs_conf->vmentry_ctrl &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
-
}
#endif
diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h
index e5f7a7e..bd41d94 100644
--- a/arch/x86/kvm/vmx/evmcs.h
+++ b/arch/x86/kvm/vmx/evmcs.h
@@ -185,7 +185,7 @@
vp_ap->enlighten_vmentry = 1;
}
-void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf);
+__init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf);
#else /* !IS_ENABLED(CONFIG_HYPERV) */
static inline void evmcs_write64(unsigned long field, u64 value) {}
static inline void evmcs_write32(unsigned long field, u32 value) {}
@@ -194,7 +194,6 @@
static inline u32 evmcs_read32(unsigned long field) { return 0; }
static inline u16 evmcs_read16(unsigned long field) { return 0; }
static inline void evmcs_load(u64 phys_addr) {}
-static inline void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) {}
static inline void evmcs_touch_msr_bitmap(void) {}
#endif /* IS_ENABLED(CONFIG_HYPERV) */
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index d14c94d..47b8357 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2560,8 +2560,10 @@
vmcs_conf->vmexit_ctrl = _vmexit_control;
vmcs_conf->vmentry_ctrl = _vmentry_control;
- if (static_branch_unlikely(&enable_evmcs))
+#if IS_ENABLED(CONFIG_HYPERV)
+ if (enlightened_vmcs)
evmcs_sanitize_exec_ctrls(vmcs_conf);
+#endif
return 0;
}
@@ -6834,7 +6836,6 @@
static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx;
- unsigned long *msr_bitmap;
int i, cpu, err;
BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0);
@@ -6894,7 +6895,6 @@
bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS);
bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS);
- msr_bitmap = vmx->vmcs01.msr_bitmap;
vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R);
vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW);
vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 397f599..078a39d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -255,24 +255,23 @@
/*
* When called, it means the previous get/set msr reached an invalid msr.
- * Return 0 if we want to ignore/silent this failed msr access, or 1 if we want
- * to fail the caller.
+ * Return true if we want to ignore/silent this failed msr access.
*/
-static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
- u64 data, bool write)
+static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
+ u64 data, bool write)
{
const char *op = write ? "wrmsr" : "rdmsr";
if (ignore_msrs) {
if (report_ignored_msrs)
- vcpu_unimpl(vcpu, "ignored %s: 0x%x data 0x%llx\n",
- op, msr, data);
+ kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n",
+ op, msr, data);
/* Mask the error */
- return 0;
+ return true;
} else {
- vcpu_debug_ratelimited(vcpu, "unhandled %s: 0x%x data 0x%llx\n",
- op, msr, data);
- return -ENOENT;
+ kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n",
+ op, msr, data);
+ return false;
}
}
@@ -1042,7 +1041,7 @@
}
if (is_long_mode(vcpu) &&
- (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63)))
+ (cr3 & vcpu->arch.cr3_lm_rsvd_bits))
return 1;
else if (is_pae_paging(vcpu) &&
!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
@@ -1416,7 +1415,8 @@
if (r == KVM_MSR_RET_INVALID) {
/* Unconditionally clear the output for simplicity */
*data = 0;
- r = kvm_msr_ignored_check(vcpu, index, 0, false);
+ if (kvm_msr_ignored_check(vcpu, index, 0, false))
+ r = 0;
}
if (r)
@@ -1540,7 +1540,7 @@
struct msr_data msr;
if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE))
- return -EPERM;
+ return KVM_MSR_RET_FILTERED;
switch (index) {
case MSR_FS_BASE:
@@ -1581,7 +1581,8 @@
int ret = __kvm_set_msr(vcpu, index, data, host_initiated);
if (ret == KVM_MSR_RET_INVALID)
- ret = kvm_msr_ignored_check(vcpu, index, data, true);
+ if (kvm_msr_ignored_check(vcpu, index, data, true))
+ ret = 0;
return ret;
}
@@ -1599,7 +1600,7 @@
int ret;
if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ))
- return -EPERM;
+ return KVM_MSR_RET_FILTERED;
msr.index = index;
msr.host_initiated = host_initiated;
@@ -1618,7 +1619,8 @@
if (ret == KVM_MSR_RET_INVALID) {
/* Unconditionally clear *data for simplicity */
*data = 0;
- ret = kvm_msr_ignored_check(vcpu, index, 0, false);
+ if (kvm_msr_ignored_check(vcpu, index, 0, false))
+ ret = 0;
}
return ret;
@@ -1662,9 +1664,9 @@
static u64 kvm_msr_reason(int r)
{
switch (r) {
- case -ENOENT:
+ case KVM_MSR_RET_INVALID:
return KVM_MSR_EXIT_REASON_UNKNOWN;
- case -EPERM:
+ case KVM_MSR_RET_FILTERED:
return KVM_MSR_EXIT_REASON_FILTER;
default:
return KVM_MSR_EXIT_REASON_INVAL;
@@ -1965,7 +1967,7 @@
struct kvm_arch *ka = &vcpu->kvm->arch;
if (vcpu->vcpu_id == 0 && !host_initiated) {
- if (ka->boot_vcpu_runs_old_kvmclock && old_msr)
+ if (ka->boot_vcpu_runs_old_kvmclock != old_msr)
kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
ka->boot_vcpu_runs_old_kvmclock = old_msr;
@@ -3063,9 +3065,9 @@
/* Values other than LBR and BTF are vendor-specific,
thus reserved and should throw a #GP */
return 1;
- }
- vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
- __func__, data);
+ } else if (report_ignored_msrs)
+ vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
+ __func__, data);
break;
case 0x200 ... 0x2ff:
return kvm_mtrr_set_msr(vcpu, msr, data);
@@ -3463,29 +3465,63 @@
msr_info->data = vcpu->arch.efer;
break;
case MSR_KVM_WALL_CLOCK:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE))
+ return 1;
+
+ msr_info->data = vcpu->kvm->arch.wall_clock;
+ break;
case MSR_KVM_WALL_CLOCK_NEW:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2))
+ return 1;
+
msr_info->data = vcpu->kvm->arch.wall_clock;
break;
case MSR_KVM_SYSTEM_TIME:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE))
+ return 1;
+
+ msr_info->data = vcpu->arch.time;
+ break;
case MSR_KVM_SYSTEM_TIME_NEW:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2))
+ return 1;
+
msr_info->data = vcpu->arch.time;
break;
case MSR_KVM_ASYNC_PF_EN:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+ return 1;
+
msr_info->data = vcpu->arch.apf.msr_en_val;
break;
case MSR_KVM_ASYNC_PF_INT:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
+ return 1;
+
msr_info->data = vcpu->arch.apf.msr_int_val;
break;
case MSR_KVM_ASYNC_PF_ACK:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+ return 1;
+
msr_info->data = 0;
break;
case MSR_KVM_STEAL_TIME:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME))
+ return 1;
+
msr_info->data = vcpu->arch.st.msr_val;
break;
case MSR_KVM_PV_EOI_EN:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI))
+ return 1;
+
msr_info->data = vcpu->arch.pv_eoi.msr_val;
break;
case MSR_KVM_POLL_CONTROL:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL))
+ return 1;
+
msr_info->data = vcpu->arch.msr_kvm_poll_control;
break;
case MSR_IA32_P5_MC_ADDR:
@@ -4575,6 +4611,8 @@
case KVM_CAP_ENFORCE_PV_FEATURE_CPUID:
vcpu->arch.pv_cpuid.enforce = cap->args[0];
+ if (vcpu->arch.pv_cpuid.enforce)
+ kvm_update_pv_runtime(vcpu);
return 0;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 3900ab0..e7ca622 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -376,7 +376,13 @@
int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva);
bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type);
-#define KVM_MSR_RET_INVALID 2
+/*
+ * Internal error codes that are used to indicate that MSR emulation encountered
+ * an error that should result in #GP in the guest, unless userspace
+ * handles it.
+ */
+#define KVM_MSR_RET_INVALID 2 /* in-kernel MSR emulation #GP condition */
+#define KVM_MSR_RET_FILTERED 3 /* #GP due to userspace MSR filter */
#define __cr4_reserved_bits(__cpu_has, __c) \
({ \
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 037faac..1e299ac 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -16,8 +16,6 @@
* to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
*/
-.weak memcpy
-
/*
* memcpy - Copy a memory block.
*
@@ -30,7 +28,7 @@
* rax original destination
*/
SYM_FUNC_START_ALIAS(__memcpy)
-SYM_FUNC_START_LOCAL(memcpy)
+SYM_FUNC_START_WEAK(memcpy)
ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
"jmp memcpy_erms", X86_FEATURE_ERMS
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 7ff00ea..41902fe 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -24,9 +24,7 @@
* Output:
* rax: dest
*/
-.weak memmove
-
-SYM_FUNC_START_ALIAS(memmove)
+SYM_FUNC_START_WEAK(memmove)
SYM_FUNC_START(__memmove)
mov %rdi, %rax
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 9ff15ee..0bfd26e 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -6,8 +6,6 @@
#include <asm/alternative-asm.h>
#include <asm/export.h>
-.weak memset
-
/*
* ISO C memset - set a memory block to a byte value. This function uses fast
* string to get better performance than the original function. The code is
@@ -19,7 +17,7 @@
*
* rax original destination
*/
-SYM_FUNC_START_ALIAS(memset)
+SYM_FUNC_START_WEAK(memset)
SYM_FUNC_START(__memset)
/*
* Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index efbb3de..bc08337 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -39,6 +39,7 @@
*/
u64 sme_me_mask __section(".data") = 0;
u64 sev_status __section(".data") = 0;
+u64 sev_check_data __section(".data") = 0;
EXPORT_SYMBOL(sme_me_mask);
DEFINE_STATIC_KEY_FALSE(sev_enable_key);
EXPORT_SYMBOL_GPL(sev_enable_key);
diff --git a/arch/x86/um/stub_segv.c b/arch/x86/um/stub_segv.c
index fdcd58a..27361cb 100644
--- a/arch/x86/um/stub_segv.c
+++ b/arch/x86/um/stub_segv.c
@@ -8,7 +8,7 @@
#include <sysdep/mcontext.h>
#include <sys/ucontext.h>
-void __section(".__syscall_stub")
+void __attribute__ ((__section__ (".__syscall_stub")))
stub_segv_handler(int sig, siginfo_t *info, void *p)
{
ucontext_t *uc = p;
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index fa054a1..4dc04e6 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -69,7 +69,7 @@
*/
#define VMALLOC_START (XCHAL_KSEG_CACHED_VADDR - 0x10000000)
#define VMALLOC_END (VMALLOC_START + 0x07FEFFFF)
-#define TLBTEMP_BASE_1 (VMALLOC_END + 1)
+#define TLBTEMP_BASE_1 (VMALLOC_START + 0x08000000)
#define TLBTEMP_BASE_2 (TLBTEMP_BASE_1 + DCACHE_WAY_SIZE)
#if 2 * DCACHE_WAY_SIZE > ICACHE_WAY_SIZE
#define TLBTEMP_SIZE (2 * DCACHE_WAY_SIZE)
diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index b975811..5c9fb80 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -302,7 +302,7 @@
return -EFAULT;
}
#else
-long strncpy_from_user(char *dst, const char *src, long count);
+long strncpy_from_user(char *dst, const char __user *src, long count);
#endif
/*
diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c
index 5835406..085b8c7 100644
--- a/arch/xtensa/mm/cache.c
+++ b/arch/xtensa/mm/cache.c
@@ -70,8 +70,10 @@
kvaddr = TLBTEMP_BASE_1 +
(page_to_phys(page) & DCACHE_ALIAS_MASK);
+ preempt_disable();
__invalidate_dcache_page_alias(kvaddr,
page_to_phys(page));
+ preempt_enable();
}
}
}
@@ -156,6 +158,7 @@
if (!alias && !mapping)
return;
+ preempt_disable();
virt = TLBTEMP_BASE_1 + (phys & DCACHE_ALIAS_MASK);
__flush_invalidate_dcache_page_alias(virt, phys);
@@ -166,6 +169,7 @@
if (mapping)
__invalidate_icache_page_alias(virt, phys);
+ preempt_enable();
}
/* There shouldn't be an entry in the cache for this page anymore. */
@@ -199,8 +203,10 @@
unsigned long phys = page_to_phys(pfn_to_page(pfn));
unsigned long virt = TLBTEMP_BASE_1 + (address & DCACHE_ALIAS_MASK);
+ preempt_disable();
__flush_invalidate_dcache_page_alias(virt, phys);
__invalidate_icache_page_alias(virt, phys);
+ preempt_enable();
}
EXPORT_SYMBOL(local_flush_cache_page);
@@ -227,11 +233,13 @@
unsigned long phys = page_to_phys(page);
unsigned long tmp;
+ preempt_disable();
tmp = TLBTEMP_BASE_1 + (phys & DCACHE_ALIAS_MASK);
__flush_invalidate_dcache_page_alias(tmp, phys);
tmp = TLBTEMP_BASE_1 + (addr & DCACHE_ALIAS_MASK);
__flush_invalidate_dcache_page_alias(tmp, phys);
__invalidate_icache_page_alias(tmp, phys);
+ preempt_enable();
clear_bit(PG_arch_1, &page->flags);
}
@@ -265,7 +273,9 @@
if (alias) {
unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK);
+ preempt_disable();
__flush_invalidate_dcache_page_alias(t, phys);
+ preempt_enable();
}
/* Copy data */
@@ -280,9 +290,11 @@
if (alias) {
unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK);
+ preempt_disable();
__flush_invalidate_dcache_range((unsigned long) dst, len);
if ((vma->vm_flags & VM_EXEC) != 0)
__invalidate_icache_page_alias(t, phys);
+ preempt_enable();
} else if ((vma->vm_flags & VM_EXEC) != 0) {
__flush_dcache_range((unsigned long)dst,len);
@@ -304,7 +316,9 @@
if (alias) {
unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK);
+ preempt_disable();
__flush_invalidate_dcache_page_alias(t, phys);
+ preempt_enable();
}
memcpy(dst, src, len);
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index c6fc83e..8731b7a 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -89,8 +89,8 @@
/* set highmem page free */
for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
&range_start, &range_end, NULL) {
- unsigned long start = PHYS_PFN(range_start);
- unsigned long end = PHYS_PFN(range_end);
+ unsigned long start = PFN_UP(range_start);
+ unsigned long end = PFN_DOWN(range_end);
/* Ignore complete lowmem entries */
if (end <= max_low)
diff --git a/block/bio.c b/block/bio.c
index e6e26d7..fa01bef3 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1044,6 +1044,7 @@
ssize_t size, left;
unsigned len, i;
size_t offset;
+ int ret = 0;
if (WARN_ON_ONCE(!max_append_sectors))
return 0;
@@ -1066,15 +1067,17 @@
len = min_t(size_t, PAGE_SIZE - offset, left);
if (bio_add_hw_page(q, bio, page, len, offset,
- max_append_sectors, &same_page) != len)
- return -EINVAL;
+ max_append_sectors, &same_page) != len) {
+ ret = -EINVAL;
+ break;
+ }
if (same_page)
put_page(page);
offset = 0;
}
- iov_iter_advance(iter, size);
- return 0;
+ iov_iter_advance(iter, size - left);
+ return ret;
}
/**
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index f9b5561..c68bdf5 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -657,13 +657,20 @@
goto fail;
}
+ if (radix_tree_preload(GFP_KERNEL)) {
+ blkg_free(new_blkg);
+ ret = -ENOMEM;
+ goto fail;
+ }
+
rcu_read_lock();
spin_lock_irq(&q->queue_lock);
blkg = blkg_lookup_check(pos, pol, q);
if (IS_ERR(blkg)) {
ret = PTR_ERR(blkg);
- goto fail_unlock;
+ blkg_free(new_blkg);
+ goto fail_preloaded;
}
if (blkg) {
@@ -672,10 +679,12 @@
blkg = blkg_create(pos, q, new_blkg);
if (IS_ERR(blkg)) {
ret = PTR_ERR(blkg);
- goto fail_unlock;
+ goto fail_preloaded;
}
}
+ radix_tree_preload_end();
+
if (pos == blkcg)
goto success;
}
@@ -685,6 +694,8 @@
ctx->body = input;
return 0;
+fail_preloaded:
+ radix_tree_preload_end();
fail_unlock:
spin_unlock_irq(&q->queue_lock);
rcu_read_unlock();
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 53abb5c..e32958f 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -225,6 +225,7 @@
/* release the tag's ownership to the req cloned from */
spin_lock_irqsave(&fq->mq_flush_lock, flags);
+ WRITE_ONCE(flush_rq->state, MQ_RQ_IDLE);
if (!refcount_dec_and_test(&flush_rq->ref)) {
fq->rq_status = error;
spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
diff --git a/block/genhd.c b/block/genhd.c
index 0a27321..9387f05 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -49,7 +49,7 @@
* Set disk capacity and notify if the size is not currently
* zero and will not be set to zero
*/
-void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
+bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
bool update_bdev)
{
sector_t capacity = get_capacity(disk);
@@ -62,7 +62,10 @@
char *envp[] = { "RESIZE=1", NULL };
kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp);
+ return true;
}
+
+ return false;
}
EXPORT_SYMBOL_GPL(set_capacity_revalidate_and_notify);
diff --git a/drivers/accessibility/speakup/main.c b/drivers/accessibility/speakup/main.c
index be79b21..4801966 100644
--- a/drivers/accessibility/speakup/main.c
+++ b/drivers/accessibility/speakup/main.c
@@ -357,7 +357,6 @@
mark_cut_flag = 0;
synth_printf("%s\n", spk_msg_get(MSG_CUT));
- speakup_clear_selection();
ret = speakup_set_selection(tty);
switch (ret) {
diff --git a/drivers/accessibility/speakup/selection.c b/drivers/accessibility/speakup/selection.c
index 032f326..7df7afa 100644
--- a/drivers/accessibility/speakup/selection.c
+++ b/drivers/accessibility/speakup/selection.c
@@ -22,13 +22,6 @@
struct tty_struct *tty;
};
-void speakup_clear_selection(void)
-{
- console_lock();
- clear_selection();
- console_unlock();
-}
-
static void __speakup_set_selection(struct work_struct *work)
{
struct speakup_selection_work *ssw =
@@ -51,6 +44,10 @@
goto unref;
}
+ console_lock();
+ clear_selection();
+ console_unlock();
+
set_selection_kernel(&sel, tty);
unref:
diff --git a/drivers/accessibility/speakup/speakup.h b/drivers/accessibility/speakup/speakup.h
index 74fe49c..33594f5 100644
--- a/drivers/accessibility/speakup/speakup.h
+++ b/drivers/accessibility/speakup/speakup.h
@@ -70,7 +70,6 @@
void speakup_start_ttys(void);
void synth_buffer_add(u16 ch);
void synth_buffer_clear(void);
-void speakup_clear_selection(void);
int speakup_set_selection(struct tty_struct *tty);
void speakup_cancel_selection(void);
int speakup_paste_selection(struct tty_struct *tty);
diff --git a/drivers/accessibility/speakup/spk_ttyio.c b/drivers/accessibility/speakup/spk_ttyio.c
index a831ff6..ecc3998 100644
--- a/drivers/accessibility/speakup/spk_ttyio.c
+++ b/drivers/accessibility/speakup/spk_ttyio.c
@@ -298,11 +298,13 @@
struct spk_ldisc_data *ldisc_data = speakup_tty->disc_data;
char rv;
- if (wait_for_completion_timeout(&ldisc_data->completion,
+ if (!timeout) {
+ if (!try_wait_for_completion(&ldisc_data->completion))
+ return 0xff;
+ } else if (wait_for_completion_timeout(&ldisc_data->completion,
usecs_to_jiffies(timeout)) == 0) {
- if (timeout)
- pr_warn("spk_ttyio: timeout (%d) while waiting for input\n",
- timeout);
+ pr_warn("spk_ttyio: timeout (%d) while waiting for input\n",
+ timeout);
return 0xff;
}
diff --git a/drivers/accessibility/speakup/spk_types.h b/drivers/accessibility/speakup/spk_types.h
index 7398f11..91fca303 100644
--- a/drivers/accessibility/speakup/spk_types.h
+++ b/drivers/accessibility/speakup/spk_types.h
@@ -32,6 +32,10 @@
E_NEW_DEFAULT,
};
+/*
+ * Note: add new members at the end, speakupmap.h depends on the values of the
+ * enum starting from SPELL_DELAY (see inc_dec_var)
+ */
enum var_id_t {
VERSION = 0, SYNTH, SILENT, SYNTH_DIRECT,
KEYMAP, CHARS,
@@ -42,9 +46,9 @@
SAY_CONTROL, SAY_WORD_CTL, NO_INTERRUPT, KEY_ECHO,
SPELL_DELAY, PUNC_LEVEL, READING_PUNC,
ATTRIB_BLEEP, BLEEPS,
- RATE, PITCH, INFLECTION, VOL, TONE, PUNCT, VOICE, FREQUENCY, LANG,
+ RATE, PITCH, VOL, TONE, PUNCT, VOICE, FREQUENCY, LANG,
DIRECT, PAUSE,
- CAPS_START, CAPS_STOP, CHARTAB,
+ CAPS_START, CAPS_STOP, CHARTAB, INFLECTION,
MAXVARS
};
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index bc96457..a322a7b 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -578,7 +578,7 @@
ACPI_VIDEO_FIRST_LEVEL - 1 - bqc_value;
level = device->brightness->levels[bqc_value +
- ACPI_VIDEO_FIRST_LEVEL];
+ ACPI_VIDEO_FIRST_LEVEL];
} else {
level = bqc_value;
}
@@ -990,8 +990,8 @@
goto out_free_levels;
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
- "found %d brightness levels\n",
- br->count - ACPI_VIDEO_FIRST_LEVEL));
+ "found %d brightness levels\n",
+ br->count - ACPI_VIDEO_FIRST_LEVEL));
return 0;
out_free_levels:
diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index 552fd9f..3294cc8 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -633,6 +633,10 @@
if (rc)
return rc;
+ /* IO space doesn't need mapping */
+ if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO)
+ return 0;
+
if (!acpi_os_map_generic_address(reg))
return -ENXIO;
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index cab4af5..08ee1c7 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -987,7 +987,7 @@
*/
if ((battery->state & ACPI_BATTERY_STATE_CRITICAL) ||
(test_bit(ACPI_BATTERY_ALARM_PRESENT, &battery->flags) &&
- (battery->capacity_now <= battery->alarm)))
+ (battery->capacity_now <= battery->alarm)))
acpi_pm_wakeup_event(&battery->device->dev);
return result;
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index da4b125..0d93a5e 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -74,19 +74,6 @@
/* Please keep this list sorted alphabetically by vendor and model */
static const struct dmi_system_id dmi_lid_quirks[] = {
{
- /*
- * Acer Switch 10 SW5-012. _LID method messes with home and
- * power button GPIO IRQ settings causing an interrupt storm on
- * both GPIOs. This is unfixable without a DSDT override, so we
- * have to disable the lid-switch functionality altogether :|
- */
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
- DMI_MATCH(DMI_PRODUCT_NAME, "Aspire SW5-012"),
- },
- .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_DISABLED,
- },
- {
/* GP-electronic T701, _LID method points to a floating GPIO */
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Insyde"),
@@ -102,7 +89,18 @@
*/
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "MEDION"),
- DMI_MATCH(DMI_PRODUCT_NAME, "E2215T MD60198"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "E2215T"),
+ },
+ .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN,
+ },
+ {
+ /*
+ * Medion Akoya E2228T, notification of the LID device only
+ * happens on close, not on open and _LID always returns closed.
+ */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "MEDION"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "E2228T"),
},
.driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN,
},
diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c
index 45d4b7b6..24e076f 100644
--- a/drivers/acpi/dock.c
+++ b/drivers/acpi/dock.c
@@ -231,7 +231,8 @@
* between them).
*/
list_for_each_entry_reverse(dd, &ds->dependent_devices, list)
- dock_hotplug_event(dd, ACPI_NOTIFY_EJECT_REQUEST, false);
+ dock_hotplug_event(dd, ACPI_NOTIFY_EJECT_REQUEST,
+ DOCK_CALL_HANDLER);
list_for_each_entry_reverse(dd, &ds->dependent_devices, list)
acpi_bus_trim(dd->adev);
diff --git a/drivers/acpi/dptf/dptf_pch_fivr.c b/drivers/acpi/dptf/dptf_pch_fivr.c
index 4c1992f..5fca182 100644
--- a/drivers/acpi/dptf/dptf_pch_fivr.c
+++ b/drivers/acpi/dptf/dptf_pch_fivr.c
@@ -106,6 +106,7 @@
static const struct acpi_device_id pch_fivr_device_ids[] = {
{"INTC1045", 0},
+ {"INTC1049", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, pch_fivr_device_ids);
diff --git a/drivers/acpi/dptf/dptf_power.c b/drivers/acpi/dptf/dptf_power.c
index 0674130..a24d5d7 100644
--- a/drivers/acpi/dptf/dptf_power.c
+++ b/drivers/acpi/dptf/dptf_power.c
@@ -229,6 +229,8 @@
{"INT3532", 0},
{"INTC1047", 0},
{"INTC1050", 0},
+ {"INTC1060", 0},
+ {"INTC1061", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, int3407_device_ids);
diff --git a/drivers/acpi/dptf/int340x_thermal.c b/drivers/acpi/dptf/int340x_thermal.c
index 8d420c7..d14025a 100644
--- a/drivers/acpi/dptf/int340x_thermal.c
+++ b/drivers/acpi/dptf/int340x_thermal.c
@@ -25,10 +25,16 @@
{"INT340A"},
{"INT340B"},
{"INTC1040"},
+ {"INTC1041"},
{"INTC1043"},
{"INTC1044"},
{"INTC1045"},
+ {"INTC1046"},
{"INTC1047"},
+ {"INTC1048"},
+ {"INTC1049"},
+ {"INTC1060"},
+ {"INTC1061"},
{""},
};
diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c
index 1706439..92e59f4 100644
--- a/drivers/acpi/event.c
+++ b/drivers/acpi/event.c
@@ -31,7 +31,7 @@
event.type = type;
event.data = data;
return (blocking_notifier_call_chain(&acpi_chain_head, 0, (void *)&event)
- == NOTIFY_BAD) ? -EINVAL : 0;
+ == NOTIFY_BAD) ? -EINVAL : 0;
}
EXPORT_SYMBOL(acpi_notifier_call_chain);
diff --git a/drivers/acpi/evged.c b/drivers/acpi/evged.c
index b1a7f8d..fe6b679 100644
--- a/drivers/acpi/evged.c
+++ b/drivers/acpi/evged.c
@@ -101,7 +101,7 @@
switch (gsi) {
case 0 ... 255:
- sprintf(ev_name, "_%c%02hhX",
+ sprintf(ev_name, "_%c%02X",
trigger == ACPI_EDGE_SENSITIVE ? 'E' : 'L', gsi);
if (ACPI_SUCCESS(acpi_get_handle(handle, ev_name, &evt_handle)))
diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c
index 6287338..66c3983 100644
--- a/drivers/acpi/fan.c
+++ b/drivers/acpi/fan.c
@@ -27,6 +27,7 @@
{"PNP0C0B", 0},
{"INT3404", 0},
{"INTC1044", 0},
+ {"INTC1048", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, fan_device_ids);
@@ -351,6 +352,7 @@
struct acpi_fan_fps *fps = &fan->fps[i];
snprintf(fps->name, ACPI_FPS_NAME_LEN, "state%d", i);
+ sysfs_attr_init(&fps->dev_attr.attr);
fps->dev_attr.show = show_state;
fps->dev_attr.store = NULL;
fps->dev_attr.attr.name = fps->name;
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 43411a74..e3638ba 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -134,7 +134,7 @@
void acpi_power_add_remove_device(struct acpi_device *adev, bool add);
int acpi_power_wakeup_list_init(struct list_head *list, int *system_level);
int acpi_device_sleep_wake(struct acpi_device *dev,
- int enable, int sleep_state, int dev_state);
+ int enable, int sleep_state, int dev_state);
int acpi_power_get_inferred_state(struct acpi_device *device, int *state);
int acpi_power_on_resources(struct acpi_device *device, int state);
int acpi_power_transition(struct acpi_device *device, int state);
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 7562278..4426082 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -1564,7 +1564,7 @@
le16_to_cpu(nfit_dcr->dcr->code));
break;
}
- if (rc != ENXIO)
+ if (rc != -ENXIO)
break;
}
mutex_unlock(&acpi_desc->init_mutex);
@@ -2175,10 +2175,10 @@
* these commands.
*/
enum nfit_aux_cmds {
- NFIT_CMD_TRANSLATE_SPA = 5,
- NFIT_CMD_ARS_INJECT_SET = 7,
- NFIT_CMD_ARS_INJECT_CLEAR = 8,
- NFIT_CMD_ARS_INJECT_GET = 9,
+ NFIT_CMD_TRANSLATE_SPA = 5,
+ NFIT_CMD_ARS_INJECT_SET = 7,
+ NFIT_CMD_ARS_INJECT_CLEAR = 8,
+ NFIT_CMD_ARS_INJECT_GET = 9,
};
static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
@@ -2632,7 +2632,7 @@
nfit_blk->bdw_offset = nfit_mem->bdw->offset;
mmio = &nfit_blk->mmio[BDW];
mmio->addr.base = devm_nvdimm_memremap(dev, nfit_mem->spa_bdw->address,
- nfit_mem->spa_bdw->length, nd_blk_memremap_flags(ndbr));
+ nfit_mem->spa_bdw->length, nd_blk_memremap_flags(ndbr));
if (!mmio->addr.base) {
dev_dbg(dev, "%s failed to map bdw\n",
nvdimm_name(nvdimm));
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index dea8a60..14ee631 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -175,7 +175,7 @@
* configure the IRQ assigned to this slot|dev|pin. The 'source_index'
* indicates which resource descriptor in the resource template (of
* the link device) this interrupt is allocated from.
- *
+ *
* NOTE: Don't query the Link Device for IRQ information at this time
* because Link Device enumeration may not have occurred yet
* (e.g. exists somewhere 'below' this _PRT entry in the ACPI
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index 606da5d..fb4c563 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -6,8 +6,8 @@
* Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
* Copyright (C) 2002 Dominik Brodowski <devel@brodo.de>
*
- * TBD:
- * 1. Support more than one IRQ resource entry per link device (index).
+ * TBD:
+ * 1. Support more than one IRQ resource entry per link device (index).
* 2. Implement start/stop mechanism and use ACPI Bus Driver facilities
* for IRQ management (e.g. start()->_SRS).
*/
@@ -249,8 +249,8 @@
}
}
- /*
- * Query and parse _CRS to get the current IRQ assignment.
+ /*
+ * Query and parse _CRS to get the current IRQ assignment.
*/
status = acpi_walk_resources(link->device->handle, METHOD_NAME__CRS,
@@ -396,7 +396,7 @@
/*
* "acpi_irq_balance" (default in APIC mode) enables ACPI to use PIC Interrupt
* Link Devices to move the PIRQs around to minimize sharing.
- *
+ *
* "acpi_irq_nobalance" (default in PIC mode) tells ACPI not to move any PIC IRQs
* that the BIOS has already set to active. This is necessary because
* ACPI has no automatic means of knowing what ISA IRQs are used. Note that
@@ -414,7 +414,7 @@
*
* Note that PCI IRQ routers have a list of possible IRQs,
* which may not include the IRQs this table says are available.
- *
+ *
* Since this heuristic can't tell the difference between a link
* that no device will attach to, vs. a link which may be shared
* by multiple active devices -- it is not optimal.
diff --git a/drivers/acpi/pci_mcfg.c b/drivers/acpi/pci_mcfg.c
index 7ddd57a..95f23ac 100644
--- a/drivers/acpi/pci_mcfg.c
+++ b/drivers/acpi/pci_mcfg.c
@@ -173,7 +173,7 @@
{
if (!memcmp(f->oem_id, mcfg_oem_id, ACPI_OEM_ID_SIZE) &&
!memcmp(f->oem_table_id, mcfg_oem_table_id,
- ACPI_OEM_TABLE_ID_SIZE) &&
+ ACPI_OEM_TABLE_ID_SIZE) &&
f->oem_revision == mcfg_oem_revision &&
f->segment == segment &&
resource_contains(&f->bus_range, bus_range))
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index 837b875..8048da8 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -13,7 +13,7 @@
* 1. via "Device Specific (D-State) Control"
* 2. via "Power Resource Control".
* The code below deals with ACPI Power Resources control.
- *
+ *
* An ACPI "power resource object" represents a software controllable power
* plane, clock plane, or other resource depended on by a device.
*
@@ -645,7 +645,7 @@
* -ENODEV if the execution of either _DSW or _PSW has failed
*/
int acpi_device_sleep_wake(struct acpi_device *dev,
- int enable, int sleep_state, int dev_state)
+ int enable, int sleep_state, int dev_state)
{
union acpi_object in_arg[3];
struct acpi_object_list arg_list = { 3, in_arg };
@@ -690,7 +690,7 @@
/*
* Prepare a wakeup device, two steps (Ref ACPI 2.0:P229):
- * 1. Power on the power resources required for the wakeup device
+ * 1. Power on the power resources required for the wakeup device
* 2. Execute _DSW (Device Sleep Wake) or (deprecated in ACPI 3.0) _PSW (Power
* State Wake) for the device, if present
*/
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 5909e8f..b04a689 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -354,7 +354,7 @@
(u32) px->control, (u32) px->status));
/*
- * Check that ACPI's u64 MHz will be valid as u32 KHz in cpufreq
+ * Check that ACPI's u64 MHz will be valid as u32 KHz in cpufreq
*/
if (!px->core_frequency ||
((u32)(px->core_frequency * 1000) !=
@@ -627,7 +627,7 @@
goto err_ret;
/*
- * Now that we have _PSD data from all CPUs, lets setup P-state
+ * Now that we have _PSD data from all CPUs, lets setup P-state
* domain info.
*/
for_each_possible_cpu(i) {
@@ -693,7 +693,7 @@
if (match_pdomain->domain != pdomain->domain)
continue;
- match_pr->performance->shared_type =
+ match_pr->performance->shared_type =
pr->performance->shared_type;
cpumask_copy(match_pr->performance->shared_cpu_map,
pr->performance->shared_cpu_map);
diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c
index f158b8c..e6d9f4d 100644
--- a/drivers/acpi/sbs.c
+++ b/drivers/acpi/sbs.c
@@ -366,7 +366,7 @@
state_readers[i].mode,
ACPI_SBS_BATTERY,
state_readers[i].command,
- (u8 *)battery +
+ (u8 *)battery +
state_readers[i].offset);
if (result)
goto end;
diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c
index 87b74e9..53c2862 100644
--- a/drivers/acpi/sbshc.c
+++ b/drivers/acpi/sbshc.c
@@ -176,7 +176,7 @@
EXPORT_SYMBOL_GPL(acpi_smbus_write);
int acpi_smbus_register_callback(struct acpi_smb_hc *hc,
- smbus_alarm_callback callback, void *context)
+ smbus_alarm_callback callback, void *context)
{
mutex_lock(&hc->lock);
hc->callback = callback;
diff --git a/drivers/acpi/sbshc.h b/drivers/acpi/sbshc.h
index c3522bb..695c390 100644
--- a/drivers/acpi/sbshc.h
+++ b/drivers/acpi/sbshc.h
@@ -24,9 +24,9 @@
typedef void (*smbus_alarm_callback)(void *context);
extern int acpi_smbus_read(struct acpi_smb_hc *hc, u8 protocol, u8 address,
- u8 command, u8 * data);
+ u8 command, u8 *data);
extern int acpi_smbus_write(struct acpi_smb_hc *hc, u8 protocol, u8 slave_address,
- u8 command, u8 * data, u8 length);
+ u8 command, u8 *data, u8 length);
extern int acpi_smbus_register_callback(struct acpi_smb_hc *hc,
- smbus_alarm_callback callback, void *context);
+ smbus_alarm_callback callback, void *context);
extern int acpi_smbus_unregister_callback(struct acpi_smb_hc *hc);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index a896e5e..bc6a79e 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1453,7 +1453,7 @@
}
/**
- * acpi_dma_configure - Set-up DMA configuration for the device.
+ * acpi_dma_configure_id - Set-up DMA configuration for the device.
* @dev: The pointer to the device
* @attr: device dma attributes
* @input_id: input device id const value pointer
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 3a032af..4f5463b 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -178,14 +178,14 @@
DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201s"),
},
},
- {
- .callback = video_detect_force_video,
- .ident = "ThinkPad X201T",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
- DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201T"),
- },
- },
+ {
+ .callback = video_detect_force_video,
+ .ident = "ThinkPad X201T",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201T"),
+ },
+ },
/* The native backlight controls do not work on some older machines */
{
diff --git a/drivers/acpi/wakeup.c b/drivers/acpi/wakeup.c
index f89dd9a..b02bf77 100644
--- a/drivers/acpi/wakeup.c
+++ b/drivers/acpi/wakeup.c
@@ -44,7 +44,7 @@
if (!dev->wakeup.flags.valid
|| sleep_state > (u32) dev->wakeup.sleep_state
|| !(device_may_wakeup(&dev->dev)
- || dev->wakeup.prepare_count))
+ || dev->wakeup.prepare_count))
continue;
if (device_may_wakeup(&dev->dev))
@@ -69,7 +69,7 @@
if (!dev->wakeup.flags.valid
|| sleep_state > (u32) dev->wakeup.sleep_state
|| !(device_may_wakeup(&dev->dev)
- || dev->wakeup.prepare_count))
+ || dev->wakeup.prepare_count))
continue;
acpi_set_gpe_wake_mask(dev->wakeup.gpe_device, dev->wakeup.gpe_number,
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index eb9dc14e..20190f6 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -2100,7 +2100,7 @@
pp->dhfis_bits &= ~done_mask;
pp->dmafis_bits &= ~done_mask;
pp->sdbfis_bits |= done_mask;
- ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask);
+ ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask);
if (!ap->qc_active) {
DPRINTK("over\n");
diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c
index 7af74fb..09ad73361 100644
--- a/drivers/atm/nicstar.c
+++ b/drivers/atm/nicstar.c
@@ -1706,6 +1706,8 @@
if (push_scqe(card, vc, scq, &scqe, skb) != 0) {
atomic_inc(&vcc->stats->tx_err);
+ dma_unmap_single(&card->pcidev->dev, NS_PRV_DMA(skb), skb->len,
+ DMA_TO_DEVICE);
dev_kfree_skb_any(skb);
return -EIO;
}
diff --git a/drivers/base/core.c b/drivers/base/core.c
index c852f16..d661ada 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -773,8 +773,7 @@
dev_dbg(link->consumer, "Dropping the link to %s\n",
dev_name(link->supplier));
- if (link->flags & DL_FLAG_PM_RUNTIME)
- pm_runtime_drop_link(link->consumer);
+ pm_runtime_drop_link(link);
list_del_rcu(&link->s_node);
list_del_rcu(&link->c_node);
@@ -788,8 +787,7 @@
dev_info(link->consumer, "Dropping the link to %s\n",
dev_name(link->supplier));
- if (link->flags & DL_FLAG_PM_RUNTIME)
- pm_runtime_drop_link(link->consumer);
+ pm_runtime_drop_link(link);
list_del(&link->s_node);
list_del(&link->c_node);
@@ -4264,6 +4262,7 @@
*/
void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode)
{
+ struct device *parent = dev->parent;
struct fwnode_handle *fn = dev->fwnode;
if (fwnode) {
@@ -4278,7 +4277,8 @@
} else {
if (fwnode_is_primary(fn)) {
dev->fwnode = fn->secondary;
- fn->secondary = NULL;
+ if (!(parent && fn == parent->fwnode))
+ fn->secondary = ERR_PTR(-ENODEV);
} else {
dev->fwnode = NULL;
}
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index b42229b..148e819 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -1117,6 +1117,8 @@
drv = dev->driver;
if (drv) {
+ pm_runtime_get_sync(dev);
+
while (device_links_busy(dev)) {
__device_driver_unlock(dev, parent);
@@ -1128,13 +1130,12 @@
* have released the driver successfully while this one
* was waiting, so check for that.
*/
- if (dev->driver != drv)
+ if (dev->driver != drv) {
+ pm_runtime_put(dev);
return;
+ }
}
- pm_runtime_get_sync(dev);
- pm_runtime_clean_up_links(dev);
-
driver_sysfs_remove(dev);
if (dev->bus)
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 6f605f7..bfda153 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1643,42 +1643,6 @@
}
/**
- * pm_runtime_clean_up_links - Prepare links to consumers for driver removal.
- * @dev: Device whose driver is going to be removed.
- *
- * Check links from this device to any consumers and if any of them have active
- * runtime PM references to the device, drop the usage counter of the device
- * (as many times as needed).
- *
- * Links with the DL_FLAG_MANAGED flag unset are ignored.
- *
- * Since the device is guaranteed to be runtime-active at the point this is
- * called, nothing else needs to be done here.
- *
- * Moreover, this is called after device_links_busy() has returned 'false', so
- * the status of each link is guaranteed to be DL_STATE_SUPPLIER_UNBIND and
- * therefore rpm_active can't be manipulated concurrently.
- */
-void pm_runtime_clean_up_links(struct device *dev)
-{
- struct device_link *link;
- int idx;
-
- idx = device_links_read_lock();
-
- list_for_each_entry_rcu(link, &dev->links.consumers, s_node,
- device_links_read_lock_held()) {
- if (!(link->flags & DL_FLAG_MANAGED))
- continue;
-
- while (refcount_dec_not_one(&link->rpm_active))
- pm_runtime_put_noidle(dev);
- }
-
- device_links_read_unlock(idx);
-}
-
-/**
* pm_runtime_get_suppliers - Resume and reference-count supplier devices.
* @dev: Consumer device.
*/
@@ -1729,7 +1693,7 @@
spin_unlock_irq(&dev->power.lock);
}
-void pm_runtime_drop_link(struct device *dev)
+static void pm_runtime_drop_link_count(struct device *dev)
{
spin_lock_irq(&dev->power.lock);
WARN_ON(dev->power.links_count == 0);
@@ -1737,6 +1701,25 @@
spin_unlock_irq(&dev->power.lock);
}
+/**
+ * pm_runtime_drop_link - Prepare for device link removal.
+ * @link: Device link going away.
+ *
+ * Drop the link count of the consumer end of @link and decrement the supplier
+ * device's runtime PM usage counter as many times as needed to drop all of the
+ * PM runtime reference to it from the consumer.
+ */
+void pm_runtime_drop_link(struct device_link *link)
+{
+ if (!(link->flags & DL_FLAG_PM_RUNTIME))
+ return;
+
+ pm_runtime_drop_link_count(link->consumer);
+
+ while (refcount_dec_not_one(&link->rpm_active))
+ pm_runtime_put(link->supplier);
+}
+
static bool pm_runtime_need_not_resume(struct device *dev)
{
return atomic_read(&dev->power.usage_count) <= 1 &&
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index cb1191d..a58084c 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -255,7 +255,8 @@
bd_set_nr_sectors(bdev, size);
- set_capacity_revalidate_and_notify(lo->lo_disk, size, false);
+ if (!set_capacity_revalidate_and_notify(lo->lo_disk, size, false))
+ kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
}
static inline int
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 0bed21c..aaae922 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -296,7 +296,7 @@
}
}
-static void nbd_size_update(struct nbd_device *nbd)
+static void nbd_size_update(struct nbd_device *nbd, bool start)
{
struct nbd_config *config = nbd->config;
struct block_device *bdev = bdget_disk(nbd->disk, 0);
@@ -313,7 +313,8 @@
if (bdev) {
if (bdev->bd_disk) {
bd_set_nr_sectors(bdev, nr_sectors);
- set_blocksize(bdev, config->blksize);
+ if (start)
+ set_blocksize(bdev, config->blksize);
} else
set_bit(GD_NEED_PART_SCAN, &nbd->disk->state);
bdput(bdev);
@@ -328,7 +329,7 @@
config->blksize = blocksize;
config->bytesize = blocksize * nr_blocks;
if (nbd->task_recv != NULL)
- nbd_size_update(nbd);
+ nbd_size_update(nbd, false);
}
static void nbd_complete_rq(struct request *req)
@@ -1308,7 +1309,7 @@
args->index = i;
queue_work(nbd->recv_workq, &args->work);
}
- nbd_size_update(nbd);
+ nbd_size_update(nbd, true);
return error;
}
@@ -1517,6 +1518,7 @@
if (test_bit(NBD_RT_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) &&
bdev->bd_openers == 0)
nbd_disconnect_and_put(nbd);
+ bdput(bdev);
nbd_config_put(nbd);
nbd_put(nbd);
diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h
index d2e7db4..c24d9b5 100644
--- a/drivers/block/null_blk.h
+++ b/drivers/block/null_blk.h
@@ -47,6 +47,8 @@
unsigned int nr_zones_closed;
struct blk_zone *zones;
sector_t zone_size_sects;
+ spinlock_t zone_lock;
+ unsigned long *zone_locks;
unsigned long size; /* device size in MB */
unsigned long completion_nsec; /* time in ns to complete a request */
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
index 7d94f2d..beb34b4 100644
--- a/drivers/block/null_blk_zoned.c
+++ b/drivers/block/null_blk_zoned.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/vmalloc.h>
+#include <linux/bitmap.h>
#include "null_blk.h"
#define CREATE_TRACE_POINTS
@@ -45,6 +46,22 @@
if (!dev->zones)
return -ENOMEM;
+ /*
+ * With memory backing, the zone_lock spinlock needs to be temporarily
+ * released to avoid scheduling in atomic context. To guarantee zone
+ * information protection, use a bitmap to lock zones with
+ * wait_on_bit_lock_io(). Sleeping on the lock is OK as memory backing
+ * implies that the queue is marked with BLK_MQ_F_BLOCKING.
+ */
+ spin_lock_init(&dev->zone_lock);
+ if (dev->memory_backed) {
+ dev->zone_locks = bitmap_zalloc(dev->nr_zones, GFP_KERNEL);
+ if (!dev->zone_locks) {
+ kvfree(dev->zones);
+ return -ENOMEM;
+ }
+ }
+
if (dev->zone_nr_conv >= dev->nr_zones) {
dev->zone_nr_conv = dev->nr_zones - 1;
pr_info("changed the number of conventional zones to %u",
@@ -123,15 +140,31 @@
void null_free_zoned_dev(struct nullb_device *dev)
{
+ bitmap_free(dev->zone_locks);
kvfree(dev->zones);
}
+static inline void null_lock_zone(struct nullb_device *dev, unsigned int zno)
+{
+ if (dev->memory_backed)
+ wait_on_bit_lock_io(dev->zone_locks, zno, TASK_UNINTERRUPTIBLE);
+ spin_lock_irq(&dev->zone_lock);
+}
+
+static inline void null_unlock_zone(struct nullb_device *dev, unsigned int zno)
+{
+ spin_unlock_irq(&dev->zone_lock);
+
+ if (dev->memory_backed)
+ clear_and_wake_up_bit(zno, dev->zone_locks);
+}
+
int null_report_zones(struct gendisk *disk, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data)
{
struct nullb *nullb = disk->private_data;
struct nullb_device *dev = nullb->dev;
- unsigned int first_zone, i;
+ unsigned int first_zone, i, zno;
struct blk_zone zone;
int error;
@@ -142,15 +175,18 @@
nr_zones = min(nr_zones, dev->nr_zones - first_zone);
trace_nullb_report_zones(nullb, nr_zones);
- for (i = 0; i < nr_zones; i++) {
+ zno = first_zone;
+ for (i = 0; i < nr_zones; i++, zno++) {
/*
* Stacked DM target drivers will remap the zone information by
* modifying the zone information passed to the report callback.
* So use a local copy to avoid corruption of the device zone
* array.
*/
- memcpy(&zone, &dev->zones[first_zone + i],
- sizeof(struct blk_zone));
+ null_lock_zone(dev, zno);
+ memcpy(&zone, &dev->zones[zno], sizeof(struct blk_zone));
+ null_unlock_zone(dev, zno);
+
error = cb(&zone, i, data);
if (error)
return error;
@@ -159,6 +195,10 @@
return nr_zones;
}
+/*
+ * This is called in the case of memory backing from null_process_cmd()
+ * with the target zone already locked.
+ */
size_t null_zone_valid_read_len(struct nullb *nullb,
sector_t sector, unsigned int len)
{
@@ -295,22 +335,26 @@
if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
return null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
+ null_lock_zone(dev, zno);
+
switch (zone->cond) {
case BLK_ZONE_COND_FULL:
/* Cannot write to a full zone */
- return BLK_STS_IOERR;
+ ret = BLK_STS_IOERR;
+ goto unlock;
case BLK_ZONE_COND_EMPTY:
case BLK_ZONE_COND_CLOSED:
ret = null_check_zone_resources(dev, zone);
if (ret != BLK_STS_OK)
- return ret;
+ goto unlock;
break;
case BLK_ZONE_COND_IMP_OPEN:
case BLK_ZONE_COND_EXP_OPEN:
break;
default:
/* Invalid zone condition */
- return BLK_STS_IOERR;
+ ret = BLK_STS_IOERR;
+ goto unlock;
}
/*
@@ -326,11 +370,14 @@
else
cmd->rq->__sector = sector;
} else if (sector != zone->wp) {
- return BLK_STS_IOERR;
+ ret = BLK_STS_IOERR;
+ goto unlock;
}
- if (zone->wp + nr_sectors > zone->start + zone->capacity)
- return BLK_STS_IOERR;
+ if (zone->wp + nr_sectors > zone->start + zone->capacity) {
+ ret = BLK_STS_IOERR;
+ goto unlock;
+ }
if (zone->cond == BLK_ZONE_COND_CLOSED) {
dev->nr_zones_closed--;
@@ -341,9 +388,19 @@
if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
zone->cond = BLK_ZONE_COND_IMP_OPEN;
+ /*
+ * Memory backing allocation may sleep: release the zone_lock spinlock
+ * to avoid scheduling in atomic context. Zone operation atomicity is
+ * still guaranteed through the zone_locks bitmap.
+ */
+ if (dev->memory_backed)
+ spin_unlock_irq(&dev->zone_lock);
ret = null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
+ if (dev->memory_backed)
+ spin_lock_irq(&dev->zone_lock);
+
if (ret != BLK_STS_OK)
- return ret;
+ goto unlock;
zone->wp += nr_sectors;
if (zone->wp == zone->start + zone->capacity) {
@@ -353,7 +410,12 @@
dev->nr_zones_imp_open--;
zone->cond = BLK_ZONE_COND_FULL;
}
- return BLK_STS_OK;
+ ret = BLK_STS_OK;
+
+unlock:
+ null_unlock_zone(dev, zno);
+
+ return ret;
}
static blk_status_t null_open_zone(struct nullb_device *dev, struct blk_zone *zone)
@@ -464,16 +526,30 @@
sector_t sector)
{
struct nullb_device *dev = cmd->nq->dev;
- unsigned int zone_no = null_zone_no(dev, sector);
- struct blk_zone *zone = &dev->zones[zone_no];
- blk_status_t ret = BLK_STS_OK;
+ unsigned int zone_no;
+ struct blk_zone *zone;
+ blk_status_t ret;
size_t i;
+ if (op == REQ_OP_ZONE_RESET_ALL) {
+ for (i = dev->zone_nr_conv; i < dev->nr_zones; i++) {
+ null_lock_zone(dev, i);
+ zone = &dev->zones[i];
+ if (zone->cond != BLK_ZONE_COND_EMPTY) {
+ null_reset_zone(dev, zone);
+ trace_nullb_zone_op(cmd, i, zone->cond);
+ }
+ null_unlock_zone(dev, i);
+ }
+ return BLK_STS_OK;
+ }
+
+ zone_no = null_zone_no(dev, sector);
+ zone = &dev->zones[zone_no];
+
+ null_lock_zone(dev, zone_no);
+
switch (op) {
- case REQ_OP_ZONE_RESET_ALL:
- for (i = dev->zone_nr_conv; i < dev->nr_zones; i++)
- null_reset_zone(dev, &dev->zones[i]);
- break;
case REQ_OP_ZONE_RESET:
ret = null_reset_zone(dev, zone);
break;
@@ -487,30 +563,44 @@
ret = null_finish_zone(dev, zone);
break;
default:
- return BLK_STS_NOTSUPP;
+ ret = BLK_STS_NOTSUPP;
+ break;
}
if (ret == BLK_STS_OK)
trace_nullb_zone_op(cmd, zone_no, zone->cond);
+ null_unlock_zone(dev, zone_no);
+
return ret;
}
blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_opf op,
sector_t sector, sector_t nr_sectors)
{
+ struct nullb_device *dev = cmd->nq->dev;
+ unsigned int zno = null_zone_no(dev, sector);
+ blk_status_t sts;
+
switch (op) {
case REQ_OP_WRITE:
- return null_zone_write(cmd, sector, nr_sectors, false);
+ sts = null_zone_write(cmd, sector, nr_sectors, false);
+ break;
case REQ_OP_ZONE_APPEND:
- return null_zone_write(cmd, sector, nr_sectors, true);
+ sts = null_zone_write(cmd, sector, nr_sectors, true);
+ break;
case REQ_OP_ZONE_RESET:
case REQ_OP_ZONE_RESET_ALL:
case REQ_OP_ZONE_OPEN:
case REQ_OP_ZONE_CLOSE:
case REQ_OP_ZONE_FINISH:
- return null_zone_mgmt(cmd, op, sector);
+ sts = null_zone_mgmt(cmd, op, sector);
+ break;
default:
- return null_process_cmd(cmd, op, sector, nr_sectors);
+ null_lock_zone(dev, zno);
+ sts = null_process_cmd(cmd, op, sector, nr_sectors);
+ null_unlock_zone(dev, zno);
}
+
+ return sts;
}
diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c
index 8d581c7..eb8ef65 100644
--- a/drivers/block/xsysace.c
+++ b/drivers/block/xsysace.c
@@ -443,22 +443,27 @@
#define ACE_FSM_NUM_STATES 11
/* Set flag to exit FSM loop and reschedule tasklet */
-static inline void ace_fsm_yield(struct ace_device *ace)
+static inline void ace_fsm_yieldpoll(struct ace_device *ace)
{
- dev_dbg(ace->dev, "ace_fsm_yield()\n");
tasklet_schedule(&ace->fsm_tasklet);
ace->fsm_continue_flag = 0;
}
+static inline void ace_fsm_yield(struct ace_device *ace)
+{
+ dev_dbg(ace->dev, "%s()\n", __func__);
+ ace_fsm_yieldpoll(ace);
+}
+
/* Set flag to exit FSM loop and wait for IRQ to reschedule tasklet */
static inline void ace_fsm_yieldirq(struct ace_device *ace)
{
dev_dbg(ace->dev, "ace_fsm_yieldirq()\n");
- if (!ace->irq)
- /* No IRQ assigned, so need to poll */
- tasklet_schedule(&ace->fsm_tasklet);
- ace->fsm_continue_flag = 0;
+ if (ace->irq > 0)
+ ace->fsm_continue_flag = 0;
+ else
+ ace_fsm_yieldpoll(ace);
}
static bool ace_has_next_request(struct request_queue *q)
@@ -1053,12 +1058,12 @@
ACE_CTRL_DATABUFRDYIRQ | ACE_CTRL_ERRORIRQ);
/* Now we can hook up the irq handler */
- if (ace->irq) {
+ if (ace->irq > 0) {
rc = request_irq(ace->irq, ace_interrupt, 0, "systemace", ace);
if (rc) {
/* Failure - fall back to polled mode */
dev_err(ace->dev, "request_irq failed\n");
- ace->irq = 0;
+ ace->irq = rc;
}
}
@@ -1110,7 +1115,7 @@
tasklet_kill(&ace->fsm_tasklet);
- if (ace->irq)
+ if (ace->irq > 0)
free_irq(ace->irq, ace);
iounmap(ace->baseaddr);
@@ -1123,11 +1128,6 @@
int rc;
dev_dbg(dev, "ace_alloc(%p)\n", dev);
- if (!physaddr) {
- rc = -ENODEV;
- goto err_noreg;
- }
-
/* Allocate and initialize the ace device structure */
ace = kzalloc(sizeof(struct ace_device), GFP_KERNEL);
if (!ace) {
@@ -1153,7 +1153,6 @@
dev_set_drvdata(dev, NULL);
kfree(ace);
err_alloc:
-err_noreg:
dev_err(dev, "could not initialize device, err=%i\n", rc);
return rc;
}
@@ -1176,10 +1175,11 @@
static int ace_probe(struct platform_device *dev)
{
- resource_size_t physaddr = 0;
int bus_width = ACE_BUS_WIDTH_16; /* FIXME: should not be hard coded */
+ resource_size_t physaddr;
+ struct resource *res;
u32 id = dev->id;
- int irq = 0;
+ int irq;
int i;
dev_dbg(&dev->dev, "ace_probe(%p)\n", dev);
@@ -1190,12 +1190,15 @@
if (of_find_property(dev->dev.of_node, "8-bit", NULL))
bus_width = ACE_BUS_WIDTH_8;
- for (i = 0; i < dev->num_resources; i++) {
- if (dev->resource[i].flags & IORESOURCE_MEM)
- physaddr = dev->resource[i].start;
- if (dev->resource[i].flags & IORESOURCE_IRQ)
- irq = dev->resource[i].start;
- }
+ res = platform_get_resource(dev, IORESOURCE_MEM, 0);
+ if (!res)
+ return -EINVAL;
+
+ physaddr = res->start;
+ if (!physaddr)
+ return -ENODEV;
+
+ irq = platform_get_irq_optional(dev, 0);
/* Call the bus-independent setup code */
return ace_alloc(&dev->dev, id, physaddr, irq, bus_width);
diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h
index 09346ae..78cc64b 100644
--- a/drivers/bluetooth/btintel.h
+++ b/drivers/bluetooth/btintel.h
@@ -47,7 +47,7 @@
struct intel_tlv {
u8 type;
u8 len;
- u8 val[0];
+ u8 val[];
} __packed;
struct intel_version_tlv {
diff --git a/drivers/char/tpm/eventlog/efi.c b/drivers/char/tpm/eventlog/efi.c
index 6bb023d..35229e5 100644
--- a/drivers/char/tpm/eventlog/efi.c
+++ b/drivers/char/tpm/eventlog/efi.c
@@ -41,6 +41,11 @@
log_size = log_tbl->size;
memunmap(log_tbl);
+ if (!log_size) {
+ pr_warn("UEFI TPM log area empty\n");
+ return -EIO;
+ }
+
log_tbl = memremap(efi.tpm_log, sizeof(*log_tbl) + log_size,
MEMREMAP_WB);
if (!log_tbl) {
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index 0b21496..4ed6e66 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -27,6 +27,7 @@
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/kernel.h>
+#include <linux/dmi.h>
#include "tpm.h"
#include "tpm_tis_core.h"
@@ -49,8 +50,8 @@
return container_of(data, struct tpm_tis_tcg_phy, priv);
}
-static bool interrupts = true;
-module_param(interrupts, bool, 0444);
+static int interrupts = -1;
+module_param(interrupts, int, 0444);
MODULE_PARM_DESC(interrupts, "Enable interrupts");
static bool itpm;
@@ -63,6 +64,28 @@
MODULE_PARM_DESC(force, "Force device probe rather than using ACPI entry");
#endif
+static int tpm_tis_disable_irq(const struct dmi_system_id *d)
+{
+ if (interrupts == -1) {
+ pr_notice("tpm_tis: %s detected: disabling interrupts.\n", d->ident);
+ interrupts = 0;
+ }
+
+ return 0;
+}
+
+static const struct dmi_system_id tpm_tis_dmi_table[] = {
+ {
+ .callback = tpm_tis_disable_irq,
+ .ident = "ThinkPad T490s",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T490s"),
+ },
+ },
+ {}
+};
+
#if defined(CONFIG_PNP) && defined(CONFIG_ACPI)
static int has_hid(struct acpi_device *dev, const char *hid)
{
@@ -192,6 +215,8 @@
int irq = -1;
int rc;
+ dmi_check_system(tpm_tis_dmi_table);
+
rc = check_acpi_tpm2(dev);
if (rc)
return rc;
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index a2da8f7..1836cc5 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -435,12 +435,12 @@
/*
* Allocate DMA memory from ancestor. When a virtio
* device is created by remoteproc, the DMA memory is
- * associated with the grandparent device:
- * vdev => rproc => platform-dev.
+ * associated with the parent device:
+ * virtioY => remoteprocX#vdevYbuffer.
*/
- if (!vdev->dev.parent || !vdev->dev.parent->parent)
+ buf->dev = vdev->dev.parent;
+ if (!buf->dev)
goto free_buf;
- buf->dev = vdev->dev.parent->parent;
/* Increase device refcnt to avoid freeing it */
get_device(buf->dev);
diff --git a/drivers/clk/imx/clk-imx8mm.c b/drivers/clk/imx/clk-imx8mm.c
index 0de0be0..f358ad9 100644
--- a/drivers/clk/imx/clk-imx8mm.c
+++ b/drivers/clk/imx/clk-imx8mm.c
@@ -443,9 +443,9 @@
hws[IMX8MM_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mm_a53_core_sels, ARRAY_SIZE(imx8mm_a53_core_sels));
/* BUS */
- hws[IMX8MM_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mm_main_axi_sels, base + 0x8800);
+ hws[IMX8MM_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mm_main_axi_sels, base + 0x8800);
hws[IMX8MM_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mm_enet_axi_sels, base + 0x8880);
- hws[IMX8MM_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_critical("nand_usdhc_bus", imx8mm_nand_usdhc_sels, base + 0x8900);
+ hws[IMX8MM_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus_critical("nand_usdhc_bus", imx8mm_nand_usdhc_sels, base + 0x8900);
hws[IMX8MM_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mm_vpu_bus_sels, base + 0x8980);
hws[IMX8MM_CLK_DISP_AXI] = imx8m_clk_hw_composite_bus("disp_axi", imx8mm_disp_axi_sels, base + 0x8a00);
hws[IMX8MM_CLK_DISP_APB] = imx8m_clk_hw_composite_bus("disp_apb", imx8mm_disp_apb_sels, base + 0x8a80);
@@ -453,11 +453,11 @@
hws[IMX8MM_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mm_usb_bus_sels, base + 0x8b80);
hws[IMX8MM_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mm_gpu_axi_sels, base + 0x8c00);
hws[IMX8MM_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mm_gpu_ahb_sels, base + 0x8c80);
- hws[IMX8MM_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mm_noc_sels, base + 0x8d00);
- hws[IMX8MM_CLK_NOC_APB] = imx8m_clk_hw_composite_critical("noc_apb", imx8mm_noc_apb_sels, base + 0x8d80);
+ hws[IMX8MM_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mm_noc_sels, base + 0x8d00);
+ hws[IMX8MM_CLK_NOC_APB] = imx8m_clk_hw_composite_bus_critical("noc_apb", imx8mm_noc_apb_sels, base + 0x8d80);
/* AHB */
- hws[IMX8MM_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mm_ahb_sels, base + 0x9000);
+ hws[IMX8MM_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mm_ahb_sels, base + 0x9000);
hws[IMX8MM_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mm_audio_ahb_sels, base + 0x9100);
/* IPG */
diff --git a/drivers/clk/imx/clk-imx8mn.c b/drivers/clk/imx/clk-imx8mn.c
index e984de5..f3c5e6c 100644
--- a/drivers/clk/imx/clk-imx8mn.c
+++ b/drivers/clk/imx/clk-imx8mn.c
@@ -431,7 +431,7 @@
hws[IMX8MN_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mn_a53_core_sels, ARRAY_SIZE(imx8mn_a53_core_sels));
/* BUS */
- hws[IMX8MN_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mn_main_axi_sels, base + 0x8800);
+ hws[IMX8MN_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mn_main_axi_sels, base + 0x8800);
hws[IMX8MN_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mn_enet_axi_sels, base + 0x8880);
hws[IMX8MN_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus("nand_usdhc_bus", imx8mn_nand_usdhc_sels, base + 0x8900);
hws[IMX8MN_CLK_DISP_AXI] = imx8m_clk_hw_composite_bus("disp_axi", imx8mn_disp_axi_sels, base + 0x8a00);
@@ -439,9 +439,9 @@
hws[IMX8MN_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mn_usb_bus_sels, base + 0x8b80);
hws[IMX8MN_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mn_gpu_axi_sels, base + 0x8c00);
hws[IMX8MN_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mn_gpu_ahb_sels, base + 0x8c80);
- hws[IMX8MN_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mn_noc_sels, base + 0x8d00);
+ hws[IMX8MN_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mn_noc_sels, base + 0x8d00);
- hws[IMX8MN_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mn_ahb_sels, base + 0x9000);
+ hws[IMX8MN_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mn_ahb_sels, base + 0x9000);
hws[IMX8MN_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mn_audio_ahb_sels, base + 0x9100);
hws[IMX8MN_CLK_IPG_ROOT] = imx_clk_hw_divider2("ipg_root", "ahb", base + 0x9080, 0, 1);
hws[IMX8MN_CLK_IPG_AUDIO_ROOT] = imx_clk_hw_divider2("ipg_audio_root", "audio_ahb", base + 0x9180, 0, 1);
diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c
index 12ce477..48e2124 100644
--- a/drivers/clk/imx/clk-imx8mp.c
+++ b/drivers/clk/imx/clk-imx8mp.c
@@ -557,9 +557,9 @@
/* CORE SEL */
hws[IMX8MP_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", ccm_base + 0x9880, 24, 1, imx8mp_a53_core_sels, ARRAY_SIZE(imx8mp_a53_core_sels));
- hws[IMX8MP_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mp_main_axi_sels, ccm_base + 0x8800);
+ hws[IMX8MP_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mp_main_axi_sels, ccm_base + 0x8800);
hws[IMX8MP_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mp_enet_axi_sels, ccm_base + 0x8880);
- hws[IMX8MP_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_critical("nand_usdhc_bus", imx8mp_nand_usdhc_sels, ccm_base + 0x8900);
+ hws[IMX8MP_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus_critical("nand_usdhc_bus", imx8mp_nand_usdhc_sels, ccm_base + 0x8900);
hws[IMX8MP_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mp_vpu_bus_sels, ccm_base + 0x8980);
hws[IMX8MP_CLK_MEDIA_AXI] = imx8m_clk_hw_composite_bus("media_axi", imx8mp_media_axi_sels, ccm_base + 0x8a00);
hws[IMX8MP_CLK_MEDIA_APB] = imx8m_clk_hw_composite_bus("media_apb", imx8mp_media_apb_sels, ccm_base + 0x8a80);
@@ -567,12 +567,12 @@
hws[IMX8MP_CLK_HDMI_AXI] = imx8m_clk_hw_composite_bus("hdmi_axi", imx8mp_media_axi_sels, ccm_base + 0x8b80);
hws[IMX8MP_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mp_gpu_axi_sels, ccm_base + 0x8c00);
hws[IMX8MP_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mp_gpu_ahb_sels, ccm_base + 0x8c80);
- hws[IMX8MP_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mp_noc_sels, ccm_base + 0x8d00);
- hws[IMX8MP_CLK_NOC_IO] = imx8m_clk_hw_composite_critical("noc_io", imx8mp_noc_io_sels, ccm_base + 0x8d80);
+ hws[IMX8MP_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mp_noc_sels, ccm_base + 0x8d00);
+ hws[IMX8MP_CLK_NOC_IO] = imx8m_clk_hw_composite_bus_critical("noc_io", imx8mp_noc_io_sels, ccm_base + 0x8d80);
hws[IMX8MP_CLK_ML_AXI] = imx8m_clk_hw_composite_bus("ml_axi", imx8mp_ml_axi_sels, ccm_base + 0x8e00);
hws[IMX8MP_CLK_ML_AHB] = imx8m_clk_hw_composite_bus("ml_ahb", imx8mp_ml_ahb_sels, ccm_base + 0x8e80);
- hws[IMX8MP_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb_root", imx8mp_ahb_sels, ccm_base + 0x9000);
+ hws[IMX8MP_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb_root", imx8mp_ahb_sels, ccm_base + 0x9000);
hws[IMX8MP_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mp_audio_ahb_sels, ccm_base + 0x9100);
hws[IMX8MP_CLK_MIPI_DSI_ESC_RX] = imx8m_clk_hw_composite_bus("mipi_dsi_esc_rx", imx8mp_mipi_dsi_esc_rx_sels, ccm_base + 0x9200);
diff --git a/drivers/clk/imx/clk-imx8mq.c b/drivers/clk/imx/clk-imx8mq.c
index 8265d1d..06292d4 100644
--- a/drivers/clk/imx/clk-imx8mq.c
+++ b/drivers/clk/imx/clk-imx8mq.c
@@ -431,7 +431,7 @@
hws[IMX8MQ_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mq_a53_core_sels, ARRAY_SIZE(imx8mq_a53_core_sels));
/* BUS */
- hws[IMX8MQ_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mq_main_axi_sels, base + 0x8800);
+ hws[IMX8MQ_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mq_main_axi_sels, base + 0x8800);
hws[IMX8MQ_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mq_enet_axi_sels, base + 0x8880);
hws[IMX8MQ_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus("nand_usdhc_bus", imx8mq_nand_usdhc_sels, base + 0x8900);
hws[IMX8MQ_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mq_vpu_bus_sels, base + 0x8980);
@@ -441,12 +441,12 @@
hws[IMX8MQ_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mq_usb_bus_sels, base + 0x8b80);
hws[IMX8MQ_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mq_gpu_axi_sels, base + 0x8c00);
hws[IMX8MQ_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mq_gpu_ahb_sels, base + 0x8c80);
- hws[IMX8MQ_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mq_noc_sels, base + 0x8d00);
- hws[IMX8MQ_CLK_NOC_APB] = imx8m_clk_hw_composite_critical("noc_apb", imx8mq_noc_apb_sels, base + 0x8d80);
+ hws[IMX8MQ_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mq_noc_sels, base + 0x8d00);
+ hws[IMX8MQ_CLK_NOC_APB] = imx8m_clk_hw_composite_bus_critical("noc_apb", imx8mq_noc_apb_sels, base + 0x8d80);
/* AHB */
/* AHB clock is used by the AHB bus therefore marked as critical */
- hws[IMX8MQ_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mq_ahb_sels, base + 0x9000);
+ hws[IMX8MQ_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mq_ahb_sels, base + 0x9000);
hws[IMX8MQ_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mq_audio_ahb_sels, base + 0x9100);
/* IPG */
diff --git a/drivers/clk/imx/clk.h b/drivers/clk/imx/clk.h
index 3b796b3..1d7be0c 100644
--- a/drivers/clk/imx/clk.h
+++ b/drivers/clk/imx/clk.h
@@ -549,6 +549,11 @@
IMX_COMPOSITE_BUS, \
CLK_SET_RATE_NO_REPARENT | CLK_OPS_PARENT_ENABLE)
+#define imx8m_clk_hw_composite_bus_critical(name, parent_names, reg) \
+ imx8m_clk_hw_composite_flags(name, parent_names, ARRAY_SIZE(parent_names), reg, \
+ IMX_COMPOSITE_BUS, \
+ CLK_SET_RATE_NO_REPARENT | CLK_OPS_PARENT_ENABLE | CLK_IS_CRITICAL)
+
#define imx8m_clk_hw_composite_core(name, parent_names, reg) \
imx8m_clk_hw_composite_flags(name, parent_names, \
ARRAY_SIZE(parent_names), reg, \
diff --git a/drivers/clk/meson/clk-regmap.h b/drivers/clk/meson/clk-regmap.h
index c4a3960..e365312 100644
--- a/drivers/clk/meson/clk-regmap.h
+++ b/drivers/clk/meson/clk-regmap.h
@@ -26,7 +26,10 @@
void *data;
};
-#define to_clk_regmap(_hw) container_of(_hw, struct clk_regmap, hw)
+static inline struct clk_regmap *to_clk_regmap(struct clk_hw *hw)
+{
+ return container_of(hw, struct clk_regmap, hw);
+}
/**
* struct clk_regmap_gate_data - regmap backed gate specific data
diff --git a/drivers/clk/qcom/clk-regmap.h b/drivers/clk/qcom/clk-regmap.h
index 6cfc1bc..14ec659 100644
--- a/drivers/clk/qcom/clk-regmap.h
+++ b/drivers/clk/qcom/clk-regmap.h
@@ -24,7 +24,11 @@
unsigned int enable_mask;
bool enable_is_inverted;
};
-#define to_clk_regmap(_hw) container_of(_hw, struct clk_regmap, hw)
+
+static inline struct clk_regmap *to_clk_regmap(struct clk_hw *hw)
+{
+ return container_of(hw, struct clk_regmap, hw);
+}
int clk_is_enabled_regmap(struct clk_hw *hw);
int clk_enable_regmap(struct clk_hw *hw);
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 2c7171e..85de313 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -71,6 +71,7 @@
config CPU_FREQ_DEFAULT_GOV_ONDEMAND
bool "ondemand"
+ depends on !(X86_INTEL_PSTATE && SMP)
select CPU_FREQ_GOV_ONDEMAND
select CPU_FREQ_GOV_PERFORMANCE
help
@@ -83,6 +84,7 @@
config CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
bool "conservative"
+ depends on !(X86_INTEL_PSTATE && SMP)
select CPU_FREQ_GOV_CONSERVATIVE
select CPU_FREQ_GOV_PERFORMANCE
help
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index f4b6066..1e7e3f2 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1908,6 +1908,18 @@
}
/**
+ * cpufreq_driver_test_flags - Test cpufreq driver's flags against given ones.
+ * @flags: Flags to test against the current cpufreq driver's flags.
+ *
+ * Assumes that the driver is there, so callers must ensure that this is the
+ * case.
+ */
+bool cpufreq_driver_test_flags(u16 flags)
+{
+ return !!(cpufreq_driver->flags & flags);
+}
+
+/**
* cpufreq_get_current_driver - return current driver's name
*
* Return the name string of the currently loaded cpufreq driver
@@ -2187,7 +2199,8 @@
* exactly same freq is called again and so we can save on few function
* calls.
*/
- if (target_freq == policy->cur)
+ if (target_freq == policy->cur &&
+ !(cpufreq_driver->flags & CPUFREQ_NEED_UPDATE_LIMITS))
return 0;
/* Save last value to restore later on errors */
@@ -2241,7 +2254,7 @@
return -EINVAL;
/* Platform doesn't want dynamic frequency switching ? */
- if (policy->governor->dynamic_switching &&
+ if (policy->governor->flags & CPUFREQ_GOV_DYNAMIC_SWITCHING &&
cpufreq_driver->flags & CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING) {
struct cpufreq_governor *gov = cpufreq_fallback_governor();
@@ -2267,6 +2280,8 @@
}
}
+ policy->strict_target = !!(policy->governor->flags & CPUFREQ_GOV_STRICT_TARGET);
+
return 0;
}
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index c56773c..bab8e61 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -156,7 +156,7 @@
#define CPUFREQ_DBS_GOVERNOR_INITIALIZER(_name_) \
{ \
.name = _name_, \
- .dynamic_switching = true, \
+ .flags = CPUFREQ_GOV_DYNAMIC_SWITCHING, \
.owner = THIS_MODULE, \
.init = cpufreq_dbs_governor_init, \
.exit = cpufreq_dbs_governor_exit, \
diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c
index 71c1d9a..addd93f 100644
--- a/drivers/cpufreq/cpufreq_performance.c
+++ b/drivers/cpufreq/cpufreq_performance.c
@@ -20,6 +20,7 @@
static struct cpufreq_governor cpufreq_gov_performance = {
.name = "performance",
.owner = THIS_MODULE,
+ .flags = CPUFREQ_GOV_STRICT_TARGET,
.limits = cpufreq_gov_performance_limits,
};
diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c
index 7749522..8d830d8 100644
--- a/drivers/cpufreq/cpufreq_powersave.c
+++ b/drivers/cpufreq/cpufreq_powersave.c
@@ -21,6 +21,7 @@
.name = "powersave",
.limits = cpufreq_gov_powersave_limits,
.owner = THIS_MODULE,
+ .flags = CPUFREQ_GOV_STRICT_TARGET,
};
MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
diff --git a/drivers/cpufreq/e_powersaver.c b/drivers/cpufreq/e_powersaver.c
index 776a58ba..ab93bce 100644
--- a/drivers/cpufreq/e_powersaver.c
+++ b/drivers/cpufreq/e_powersaver.c
@@ -223,7 +223,6 @@
case EPS_BRAND_C3:
pr_cont("C3\n");
return -ENODEV;
- break;
}
/* Enable Enhanced PowerSaver */
rdmsrl(MSR_IA32_MISC_ENABLE, val);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 3c14555..36a3ccf 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2527,7 +2527,7 @@
}
static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 target_pstate,
- bool fast_switch)
+ bool strict, bool fast_switch)
{
u64 prev = READ_ONCE(cpu->hwp_req_cached), value = prev;
@@ -2539,7 +2539,7 @@
* field in it, so opportunistically update the max too if needed.
*/
value &= ~HWP_MAX_PERF(~0L);
- value |= HWP_MAX_PERF(cpu->max_perf_ratio);
+ value |= HWP_MAX_PERF(strict ? target_pstate : cpu->max_perf_ratio);
if (value == prev)
return;
@@ -2562,20 +2562,20 @@
pstate_funcs.get_val(cpu, target_pstate));
}
-static int intel_cpufreq_update_pstate(struct cpudata *cpu, int target_pstate,
- bool fast_switch)
+static int intel_cpufreq_update_pstate(struct cpufreq_policy *policy,
+ int target_pstate, bool fast_switch)
{
+ struct cpudata *cpu = all_cpu_data[policy->cpu];
int old_pstate = cpu->pstate.current_pstate;
target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
- if (target_pstate != old_pstate) {
+ if (hwp_active) {
+ intel_cpufreq_adjust_hwp(cpu, target_pstate,
+ policy->strict_target, fast_switch);
cpu->pstate.current_pstate = target_pstate;
- if (hwp_active)
- intel_cpufreq_adjust_hwp(cpu, target_pstate,
- fast_switch);
- else
- intel_cpufreq_adjust_perf_ctl(cpu, target_pstate,
- fast_switch);
+ } else if (target_pstate != old_pstate) {
+ intel_cpufreq_adjust_perf_ctl(cpu, target_pstate, fast_switch);
+ cpu->pstate.current_pstate = target_pstate;
}
intel_cpufreq_trace(cpu, fast_switch ? INTEL_PSTATE_TRACE_FAST_SWITCH :
@@ -2611,7 +2611,7 @@
break;
}
- target_pstate = intel_cpufreq_update_pstate(cpu, target_pstate, false);
+ target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, false);
freqs.new = target_pstate * cpu->pstate.scaling;
@@ -2630,7 +2630,7 @@
target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling);
- target_pstate = intel_cpufreq_update_pstate(cpu, target_pstate, true);
+ target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, true);
return target_pstate * cpu->pstate.scaling;
}
@@ -3032,6 +3032,7 @@
hwp_mode_bdw = id->driver_data;
intel_pstate.attr = hwp_cpufreq_attrs;
intel_cpufreq.attr = hwp_cpufreq_attrs;
+ intel_cpufreq.flags |= CPUFREQ_NEED_UPDATE_LIMITS;
if (!default_driver)
default_driver = &intel_pstate;
diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c
index 123fb00..182a4dbc 100644
--- a/drivers/cpufreq/longhaul.c
+++ b/drivers/cpufreq/longhaul.c
@@ -593,7 +593,6 @@
break;
default:
return;
- break;
}
if (min_vid_speed >= highest_speed)
return;
diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index e855e86..7831850 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -8,6 +8,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/clk-provider.h>
#include <linux/cpu.h>
#include <linux/cpufreq.h>
#include <linux/cpumask.h>
@@ -228,12 +229,17 @@
static int scmi_cpufreq_probe(struct scmi_device *sdev)
{
int ret;
+ struct device *dev = &sdev->dev;
handle = sdev->handle;
if (!handle || !handle->perf_ops)
return -ENODEV;
+ /* dummy clock provider as needed by OPP if clocks property is used */
+ if (of_find_property(dev->of_node, "#clock-cells", NULL))
+ devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL);
+
ret = cpufreq_register_driver(&scmi_cpufreq_driver);
if (ret) {
dev_err(&sdev->dev, "%s: registering cpufreq failed, err: %d\n",
diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c
index a13a2d1..0b66df4 100644
--- a/drivers/cpufreq/speedstep-lib.c
+++ b/drivers/cpufreq/speedstep-lib.c
@@ -240,7 +240,7 @@
return pentium3_get_frequency(processor);
default:
return 0;
- };
+ }
return 0;
}
EXPORT_SYMBOL_GPL(speedstep_get_frequency);
diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c
index 4b4079f..7eb2c56 100644
--- a/drivers/cpufreq/tegra186-cpufreq.c
+++ b/drivers/cpufreq/tegra186-cpufreq.c
@@ -42,6 +42,8 @@
struct tegra186_cpufreq_cluster {
const struct tegra186_cpufreq_cluster_info *info;
struct cpufreq_frequency_table *table;
+ u32 ref_clk_khz;
+ u32 div;
};
struct tegra186_cpufreq_data {
@@ -94,7 +96,7 @@
static unsigned int tegra186_cpufreq_get(unsigned int cpu)
{
- struct cpufreq_frequency_table *tbl;
+ struct tegra186_cpufreq_data *data = cpufreq_get_driver_data();
struct cpufreq_policy *policy;
void __iomem *edvd_reg;
unsigned int i, freq = 0;
@@ -104,17 +106,23 @@
if (!policy)
return 0;
- tbl = policy->freq_table;
edvd_reg = policy->driver_data;
ndiv = readl(edvd_reg) & EDVD_CORE_VOLT_FREQ_F_MASK;
- for (i = 0; tbl[i].frequency != CPUFREQ_TABLE_END; i++) {
- if ((tbl[i].driver_data & EDVD_CORE_VOLT_FREQ_F_MASK) == ndiv) {
- freq = tbl[i].frequency;
- break;
+ for (i = 0; i < data->num_clusters; i++) {
+ struct tegra186_cpufreq_cluster *cluster = &data->clusters[i];
+ int core;
+
+ for (core = 0; core < ARRAY_SIZE(cluster->info->cpus); core++) {
+ if (cluster->info->cpus[core] != policy->cpu)
+ continue;
+
+ freq = (cluster->ref_clk_khz * ndiv) / cluster->div;
+ goto out;
}
}
+out:
cpufreq_cpu_put(policy);
return freq;
@@ -133,7 +141,7 @@
static struct cpufreq_frequency_table *init_vhint_table(
struct platform_device *pdev, struct tegra_bpmp *bpmp,
- unsigned int cluster_id)
+ struct tegra186_cpufreq_cluster *cluster)
{
struct cpufreq_frequency_table *table;
struct mrq_cpu_vhint_request req;
@@ -152,7 +160,7 @@
memset(&req, 0, sizeof(req));
req.addr = phys;
- req.cluster_id = cluster_id;
+ req.cluster_id = cluster->info->bpmp_cluster_id;
memset(&msg, 0, sizeof(msg));
msg.mrq = MRQ_CPU_VHINT;
@@ -185,6 +193,9 @@
goto free;
}
+ cluster->ref_clk_khz = data->ref_clk_hz / 1000;
+ cluster->div = data->pdiv * data->mdiv;
+
for (i = data->vfloor, j = 0; i <= data->vceil; i++) {
struct cpufreq_frequency_table *point;
u16 ndiv = data->ndiv[i];
@@ -202,8 +213,7 @@
point = &table[j++];
point->driver_data = edvd_val;
- point->frequency = data->ref_clk_hz * ndiv / data->pdiv /
- data->mdiv / 1000;
+ point->frequency = (cluster->ref_clk_khz * ndiv) / cluster->div;
}
table[j].frequency = CPUFREQ_TABLE_END;
@@ -245,8 +255,7 @@
struct tegra186_cpufreq_cluster *cluster = &data->clusters[i];
cluster->info = &tegra186_clusters[i];
- cluster->table = init_vhint_table(
- pdev, bpmp, cluster->info->bpmp_cluster_id);
+ cluster->table = init_vhint_table(pdev, bpmp, cluster);
if (IS_ERR(cluster->table)) {
err = PTR_ERR(cluster->table);
goto put_bpmp;
diff --git a/drivers/cpuidle/cpuidle-tegra.c b/drivers/cpuidle/cpuidle-tegra.c
index e895670..191966d 100644
--- a/drivers/cpuidle/cpuidle-tegra.c
+++ b/drivers/cpuidle/cpuidle-tegra.c
@@ -189,7 +189,7 @@
}
local_fiq_disable();
- tegra_pm_set_cpu_in_lp2();
+ RCU_NONIDLE(tegra_pm_set_cpu_in_lp2());
cpu_pm_enter();
switch (index) {
@@ -207,7 +207,7 @@
}
cpu_pm_exit();
- tegra_pm_clear_cpu_in_lp2();
+ RCU_NONIDLE(tegra_pm_clear_cpu_in_lp2());
local_fiq_enable();
return err ?: index;
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
index fa2f1b4..a94bf28 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
@@ -7,7 +7,7 @@
*
* This file add support for MD5 and SHA1/SHA224/SHA256/SHA384/SHA512.
*
- * You could find the datasheet in Documentation/arm/sunxi/README
+ * You could find the datasheet in Documentation/arm/sunxi.rst
*/
#include <linux/dma-mapping.h>
#include <linux/pm_runtime.h>
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c
index 78503006..cfde9ee 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c
@@ -7,7 +7,7 @@
*
* This file handle the PRNG
*
- * You could find a link for the datasheet in Documentation/arm/sunxi/README
+ * You could find a link for the datasheet in Documentation/arm/sunxi.rst
*/
#include "sun8i-ce.h"
#include <linux/dma-mapping.h>
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c
index 6543281..5b7af44 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c
@@ -7,7 +7,7 @@
*
* This file handle the TRNG
*
- * You could find a link for the datasheet in Documentation/arm/sunxi/README
+ * You could find a link for the datasheet in Documentation/arm/sunxi.rst
*/
#include "sun8i-ce.h"
#include <linux/dma-mapping.h>
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 518a143..90284ff 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -318,24 +318,6 @@
help
Enable support for the Intel(R) IOP Series RAID engines.
-config INTEL_MIC_X100_DMA
- tristate "Intel MIC X100 DMA Driver"
- depends on 64BIT && X86 && INTEL_MIC_BUS
- select DMA_ENGINE
- help
- This enables DMA support for the Intel Many Integrated Core
- (MIC) family of PCIe form factor coprocessor X100 devices that
- run a 64 bit Linux OS. This driver will be used by both MIC
- host and card drivers.
-
- If you are building host kernel with a MIC device or a card
- kernel for a MIC device, then say M (recommended) or Y, else
- say N. If unsure say N.
-
- More information about the Intel MIC family as well as the Linux
- OS and tools for MIC to use with this driver are available from
- <http://software.intel.com/en-us/mic-developer>.
-
config K3_DMA
tristate "Hisilicon K3 DMA support"
depends on ARCH_HI3xxx || ARCH_HISI || COMPILE_TEST
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index e60f813..948a8da 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -44,7 +44,6 @@
obj-$(CONFIG_INTEL_IOATDMA) += ioat/
obj-$(CONFIG_INTEL_IDXD) += idxd/
obj-$(CONFIG_INTEL_IOP_ADMA) += iop-adma.o
-obj-$(CONFIG_INTEL_MIC_X100_DMA) += mic_x100_dma.o
obj-$(CONFIG_K3_DMA) += k3dma.o
obj-$(CONFIG_LPC18XX_DMAMUX) += lpc18xx-dmamux.o
obj-$(CONFIG_MILBEAUT_HDMAC) += milbeaut-hdmac.o
diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c
deleted file mode 100644
index fea8608..0000000
--- a/drivers/dma/mic_x100_dma.c
+++ /dev/null
@@ -1,770 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel MIC X100 DMA Driver.
- *
- * Adapted from IOAT dma driver.
- */
-#include <linux/module.h>
-#include <linux/io.h>
-#include <linux/seq_file.h>
-#include <linux/vmalloc.h>
-
-#include "mic_x100_dma.h"
-
-#define MIC_DMA_MAX_XFER_SIZE_CARD (1 * 1024 * 1024 -\
- MIC_DMA_ALIGN_BYTES)
-#define MIC_DMA_MAX_XFER_SIZE_HOST (1 * 1024 * 1024 >> 1)
-#define MIC_DMA_DESC_TYPE_SHIFT 60
-#define MIC_DMA_MEMCPY_LEN_SHIFT 46
-#define MIC_DMA_STAT_INTR_SHIFT 59
-
-/* high-water mark for pushing dma descriptors */
-static int mic_dma_pending_level = 4;
-
-/* Status descriptor is used to write a 64 bit value to a memory location */
-enum mic_dma_desc_format_type {
- MIC_DMA_MEMCPY = 1,
- MIC_DMA_STATUS,
-};
-
-static inline u32 mic_dma_hw_ring_inc(u32 val)
-{
- return (val + 1) % MIC_DMA_DESC_RX_SIZE;
-}
-
-static inline u32 mic_dma_hw_ring_dec(u32 val)
-{
- return val ? val - 1 : MIC_DMA_DESC_RX_SIZE - 1;
-}
-
-static inline void mic_dma_hw_ring_inc_head(struct mic_dma_chan *ch)
-{
- ch->head = mic_dma_hw_ring_inc(ch->head);
-}
-
-/* Prepare a memcpy desc */
-static inline void mic_dma_memcpy_desc(struct mic_dma_desc *desc,
- dma_addr_t src_phys, dma_addr_t dst_phys, u64 size)
-{
- u64 qw0, qw1;
-
- qw0 = src_phys;
- qw0 |= (size >> MIC_DMA_ALIGN_SHIFT) << MIC_DMA_MEMCPY_LEN_SHIFT;
- qw1 = MIC_DMA_MEMCPY;
- qw1 <<= MIC_DMA_DESC_TYPE_SHIFT;
- qw1 |= dst_phys;
- desc->qw0 = qw0;
- desc->qw1 = qw1;
-}
-
-/* Prepare a status desc. with @data to be written at @dst_phys */
-static inline void mic_dma_prep_status_desc(struct mic_dma_desc *desc, u64 data,
- dma_addr_t dst_phys, bool generate_intr)
-{
- u64 qw0, qw1;
-
- qw0 = data;
- qw1 = (u64) MIC_DMA_STATUS << MIC_DMA_DESC_TYPE_SHIFT | dst_phys;
- if (generate_intr)
- qw1 |= (1ULL << MIC_DMA_STAT_INTR_SHIFT);
- desc->qw0 = qw0;
- desc->qw1 = qw1;
-}
-
-static void mic_dma_cleanup(struct mic_dma_chan *ch)
-{
- struct dma_async_tx_descriptor *tx;
- u32 tail;
- u32 last_tail;
-
- spin_lock(&ch->cleanup_lock);
- tail = mic_dma_read_cmp_cnt(ch);
- /*
- * This is the barrier pair for smp_wmb() in fn.
- * mic_dma_tx_submit_unlock. It's required so that we read the
- * updated cookie value from tx->cookie.
- */
- smp_rmb();
- for (last_tail = ch->last_tail; tail != last_tail;) {
- tx = &ch->tx_array[last_tail];
- if (tx->cookie) {
- dma_cookie_complete(tx);
- dmaengine_desc_get_callback_invoke(tx, NULL);
- tx->callback = NULL;
- }
- last_tail = mic_dma_hw_ring_inc(last_tail);
- }
- /* finish all completion callbacks before incrementing tail */
- smp_mb();
- ch->last_tail = last_tail;
- spin_unlock(&ch->cleanup_lock);
-}
-
-static u32 mic_dma_ring_count(u32 head, u32 tail)
-{
- u32 count;
-
- if (head >= tail)
- count = (tail - 0) + (MIC_DMA_DESC_RX_SIZE - head);
- else
- count = tail - head;
- return count - 1;
-}
-
-/* Returns the num. of free descriptors on success, -ENOMEM on failure */
-static int mic_dma_avail_desc_ring_space(struct mic_dma_chan *ch, int required)
-{
- struct device *dev = mic_dma_ch_to_device(ch);
- u32 count;
-
- count = mic_dma_ring_count(ch->head, ch->last_tail);
- if (count < required) {
- mic_dma_cleanup(ch);
- count = mic_dma_ring_count(ch->head, ch->last_tail);
- }
-
- if (count < required) {
- dev_dbg(dev, "Not enough desc space");
- dev_dbg(dev, "%s %d required=%u, avail=%u\n",
- __func__, __LINE__, required, count);
- return -ENOMEM;
- } else {
- return count;
- }
-}
-
-/* Program memcpy descriptors into the descriptor ring and update s/w head ptr*/
-static int mic_dma_prog_memcpy_desc(struct mic_dma_chan *ch, dma_addr_t src,
- dma_addr_t dst, size_t len)
-{
- size_t current_transfer_len;
- size_t max_xfer_size = to_mic_dma_dev(ch)->max_xfer_size;
- /* 3 is added to make sure we have enough space for status desc */
- int num_desc = len / max_xfer_size + 3;
- int ret;
-
- if (len % max_xfer_size)
- num_desc++;
-
- ret = mic_dma_avail_desc_ring_space(ch, num_desc);
- if (ret < 0)
- return ret;
- do {
- current_transfer_len = min(len, max_xfer_size);
- mic_dma_memcpy_desc(&ch->desc_ring[ch->head],
- src, dst, current_transfer_len);
- mic_dma_hw_ring_inc_head(ch);
- len -= current_transfer_len;
- dst = dst + current_transfer_len;
- src = src + current_transfer_len;
- } while (len > 0);
- return 0;
-}
-
-/* It's a h/w quirk and h/w needs 2 status descriptors for every status desc */
-static void mic_dma_prog_intr(struct mic_dma_chan *ch)
-{
- mic_dma_prep_status_desc(&ch->desc_ring[ch->head], 0,
- ch->status_dest_micpa, false);
- mic_dma_hw_ring_inc_head(ch);
- mic_dma_prep_status_desc(&ch->desc_ring[ch->head], 0,
- ch->status_dest_micpa, true);
- mic_dma_hw_ring_inc_head(ch);
-}
-
-/* Wrapper function to program memcpy descriptors/status descriptors */
-static int mic_dma_do_dma(struct mic_dma_chan *ch, int flags, dma_addr_t src,
- dma_addr_t dst, size_t len)
-{
- if (len && -ENOMEM == mic_dma_prog_memcpy_desc(ch, src, dst, len)) {
- return -ENOMEM;
- } else {
- /* 3 is the maximum number of status descriptors */
- int ret = mic_dma_avail_desc_ring_space(ch, 3);
-
- if (ret < 0)
- return ret;
- }
-
- /* Above mic_dma_prog_memcpy_desc() makes sure we have enough space */
- if (flags & DMA_PREP_FENCE) {
- mic_dma_prep_status_desc(&ch->desc_ring[ch->head], 0,
- ch->status_dest_micpa, false);
- mic_dma_hw_ring_inc_head(ch);
- }
-
- if (flags & DMA_PREP_INTERRUPT)
- mic_dma_prog_intr(ch);
-
- return 0;
-}
-
-static inline void mic_dma_issue_pending(struct dma_chan *ch)
-{
- struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
-
- spin_lock(&mic_ch->issue_lock);
- /*
- * Write to head triggers h/w to act on the descriptors.
- * On MIC, writing the same head value twice causes
- * a h/w error. On second write, h/w assumes we filled
- * the entire ring & overwrote some of the descriptors.
- */
- if (mic_ch->issued == mic_ch->submitted)
- goto out;
- mic_ch->issued = mic_ch->submitted;
- /*
- * make descriptor updates visible before advancing head,
- * this is purposefully not smp_wmb() since we are also
- * publishing the descriptor updates to a dma device
- */
- wmb();
- mic_dma_write_reg(mic_ch, MIC_DMA_REG_DHPR, mic_ch->issued);
-out:
- spin_unlock(&mic_ch->issue_lock);
-}
-
-static inline void mic_dma_update_pending(struct mic_dma_chan *ch)
-{
- if (mic_dma_ring_count(ch->issued, ch->submitted)
- > mic_dma_pending_level)
- mic_dma_issue_pending(&ch->api_ch);
-}
-
-static dma_cookie_t mic_dma_tx_submit_unlock(struct dma_async_tx_descriptor *tx)
-{
- struct mic_dma_chan *mic_ch = to_mic_dma_chan(tx->chan);
- dma_cookie_t cookie;
-
- dma_cookie_assign(tx);
- cookie = tx->cookie;
- /*
- * We need an smp write barrier here because another CPU might see
- * an update to submitted and update h/w head even before we
- * assigned a cookie to this tx.
- */
- smp_wmb();
- mic_ch->submitted = mic_ch->head;
- spin_unlock(&mic_ch->prep_lock);
- mic_dma_update_pending(mic_ch);
- return cookie;
-}
-
-static inline struct dma_async_tx_descriptor *
-allocate_tx(struct mic_dma_chan *ch)
-{
- u32 idx = mic_dma_hw_ring_dec(ch->head);
- struct dma_async_tx_descriptor *tx = &ch->tx_array[idx];
-
- dma_async_tx_descriptor_init(tx, &ch->api_ch);
- tx->tx_submit = mic_dma_tx_submit_unlock;
- return tx;
-}
-
-/* Program a status descriptor with dst as address and value to be written */
-static struct dma_async_tx_descriptor *
-mic_dma_prep_status_lock(struct dma_chan *ch, dma_addr_t dst, u64 src_val,
- unsigned long flags)
-{
- struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
- int result;
-
- spin_lock(&mic_ch->prep_lock);
- result = mic_dma_avail_desc_ring_space(mic_ch, 4);
- if (result < 0)
- goto error;
- mic_dma_prep_status_desc(&mic_ch->desc_ring[mic_ch->head], src_val, dst,
- false);
- mic_dma_hw_ring_inc_head(mic_ch);
- result = mic_dma_do_dma(mic_ch, flags, 0, 0, 0);
- if (result < 0)
- goto error;
-
- return allocate_tx(mic_ch);
-error:
- dev_err(mic_dma_ch_to_device(mic_ch),
- "Error enqueueing dma status descriptor, error=%d\n", result);
- spin_unlock(&mic_ch->prep_lock);
- return NULL;
-}
-
-/*
- * Prepare a memcpy descriptor to be added to the ring.
- * Note that the temporary descriptor adds an extra overhead of copying the
- * descriptor to ring. So, we copy directly to the descriptor ring
- */
-static struct dma_async_tx_descriptor *
-mic_dma_prep_memcpy_lock(struct dma_chan *ch, dma_addr_t dma_dest,
- dma_addr_t dma_src, size_t len, unsigned long flags)
-{
- struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
- struct device *dev = mic_dma_ch_to_device(mic_ch);
- int result;
-
- if (!len && !flags)
- return NULL;
-
- spin_lock(&mic_ch->prep_lock);
- result = mic_dma_do_dma(mic_ch, flags, dma_src, dma_dest, len);
- if (result >= 0)
- return allocate_tx(mic_ch);
- dev_err(dev, "Error enqueueing dma, error=%d\n", result);
- spin_unlock(&mic_ch->prep_lock);
- return NULL;
-}
-
-static struct dma_async_tx_descriptor *
-mic_dma_prep_interrupt_lock(struct dma_chan *ch, unsigned long flags)
-{
- struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
- int ret;
-
- spin_lock(&mic_ch->prep_lock);
- ret = mic_dma_do_dma(mic_ch, flags, 0, 0, 0);
- if (!ret)
- return allocate_tx(mic_ch);
- spin_unlock(&mic_ch->prep_lock);
- return NULL;
-}
-
-/* Return the status of the transaction */
-static enum dma_status
-mic_dma_tx_status(struct dma_chan *ch, dma_cookie_t cookie,
- struct dma_tx_state *txstate)
-{
- struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
-
- if (DMA_COMPLETE != dma_cookie_status(ch, cookie, txstate))
- mic_dma_cleanup(mic_ch);
-
- return dma_cookie_status(ch, cookie, txstate);
-}
-
-static irqreturn_t mic_dma_thread_fn(int irq, void *data)
-{
- mic_dma_cleanup((struct mic_dma_chan *)data);
- return IRQ_HANDLED;
-}
-
-static irqreturn_t mic_dma_intr_handler(int irq, void *data)
-{
- struct mic_dma_chan *ch = ((struct mic_dma_chan *)data);
-
- mic_dma_ack_interrupt(ch);
- return IRQ_WAKE_THREAD;
-}
-
-static int mic_dma_alloc_desc_ring(struct mic_dma_chan *ch)
-{
- u64 desc_ring_size = MIC_DMA_DESC_RX_SIZE * sizeof(*ch->desc_ring);
- struct device *dev = &to_mbus_device(ch)->dev;
-
- desc_ring_size = ALIGN(desc_ring_size, MIC_DMA_ALIGN_BYTES);
- ch->desc_ring = kzalloc(desc_ring_size, GFP_KERNEL);
-
- if (!ch->desc_ring)
- return -ENOMEM;
-
- ch->desc_ring_micpa = dma_map_single(dev, ch->desc_ring,
- desc_ring_size, DMA_BIDIRECTIONAL);
- if (dma_mapping_error(dev, ch->desc_ring_micpa))
- goto map_error;
-
- ch->tx_array = vzalloc(array_size(MIC_DMA_DESC_RX_SIZE,
- sizeof(*ch->tx_array)));
- if (!ch->tx_array)
- goto tx_error;
- return 0;
-tx_error:
- dma_unmap_single(dev, ch->desc_ring_micpa, desc_ring_size,
- DMA_BIDIRECTIONAL);
-map_error:
- kfree(ch->desc_ring);
- return -ENOMEM;
-}
-
-static void mic_dma_free_desc_ring(struct mic_dma_chan *ch)
-{
- u64 desc_ring_size = MIC_DMA_DESC_RX_SIZE * sizeof(*ch->desc_ring);
-
- vfree(ch->tx_array);
- desc_ring_size = ALIGN(desc_ring_size, MIC_DMA_ALIGN_BYTES);
- dma_unmap_single(&to_mbus_device(ch)->dev, ch->desc_ring_micpa,
- desc_ring_size, DMA_BIDIRECTIONAL);
- kfree(ch->desc_ring);
- ch->desc_ring = NULL;
-}
-
-static void mic_dma_free_status_dest(struct mic_dma_chan *ch)
-{
- dma_unmap_single(&to_mbus_device(ch)->dev, ch->status_dest_micpa,
- L1_CACHE_BYTES, DMA_BIDIRECTIONAL);
- kfree(ch->status_dest);
-}
-
-static int mic_dma_alloc_status_dest(struct mic_dma_chan *ch)
-{
- struct device *dev = &to_mbus_device(ch)->dev;
-
- ch->status_dest = kzalloc(L1_CACHE_BYTES, GFP_KERNEL);
- if (!ch->status_dest)
- return -ENOMEM;
- ch->status_dest_micpa = dma_map_single(dev, ch->status_dest,
- L1_CACHE_BYTES, DMA_BIDIRECTIONAL);
- if (dma_mapping_error(dev, ch->status_dest_micpa)) {
- kfree(ch->status_dest);
- ch->status_dest = NULL;
- return -ENOMEM;
- }
- return 0;
-}
-
-static int mic_dma_check_chan(struct mic_dma_chan *ch)
-{
- if (mic_dma_read_reg(ch, MIC_DMA_REG_DCHERR) ||
- mic_dma_read_reg(ch, MIC_DMA_REG_DSTAT) & MIC_DMA_CHAN_QUIESCE) {
- mic_dma_disable_chan(ch);
- mic_dma_chan_mask_intr(ch);
- dev_err(mic_dma_ch_to_device(ch),
- "%s %d error setting up mic dma chan %d\n",
- __func__, __LINE__, ch->ch_num);
- return -EBUSY;
- }
- return 0;
-}
-
-static int mic_dma_chan_setup(struct mic_dma_chan *ch)
-{
- if (MIC_DMA_CHAN_MIC == ch->owner)
- mic_dma_chan_set_owner(ch);
- mic_dma_disable_chan(ch);
- mic_dma_chan_mask_intr(ch);
- mic_dma_write_reg(ch, MIC_DMA_REG_DCHERRMSK, 0);
- mic_dma_chan_set_desc_ring(ch);
- ch->last_tail = mic_dma_read_reg(ch, MIC_DMA_REG_DTPR);
- ch->head = ch->last_tail;
- ch->issued = 0;
- mic_dma_chan_unmask_intr(ch);
- mic_dma_enable_chan(ch);
- return mic_dma_check_chan(ch);
-}
-
-static void mic_dma_chan_destroy(struct mic_dma_chan *ch)
-{
- mic_dma_disable_chan(ch);
- mic_dma_chan_mask_intr(ch);
-}
-
-static int mic_dma_setup_irq(struct mic_dma_chan *ch)
-{
- ch->cookie =
- to_mbus_hw_ops(ch)->request_threaded_irq(to_mbus_device(ch),
- mic_dma_intr_handler, mic_dma_thread_fn,
- "mic dma_channel", ch, ch->ch_num);
- return PTR_ERR_OR_ZERO(ch->cookie);
-}
-
-static inline void mic_dma_free_irq(struct mic_dma_chan *ch)
-{
- to_mbus_hw_ops(ch)->free_irq(to_mbus_device(ch), ch->cookie, ch);
-}
-
-static int mic_dma_chan_init(struct mic_dma_chan *ch)
-{
- int ret = mic_dma_alloc_desc_ring(ch);
-
- if (ret)
- goto ring_error;
- ret = mic_dma_alloc_status_dest(ch);
- if (ret)
- goto status_error;
- ret = mic_dma_chan_setup(ch);
- if (ret)
- goto chan_error;
- return ret;
-chan_error:
- mic_dma_free_status_dest(ch);
-status_error:
- mic_dma_free_desc_ring(ch);
-ring_error:
- return ret;
-}
-
-static int mic_dma_drain_chan(struct mic_dma_chan *ch)
-{
- struct dma_async_tx_descriptor *tx;
- int err = 0;
- dma_cookie_t cookie;
-
- tx = mic_dma_prep_memcpy_lock(&ch->api_ch, 0, 0, 0, DMA_PREP_FENCE);
- if (!tx) {
- err = -ENOMEM;
- goto error;
- }
-
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie))
- err = -ENOMEM;
- else
- err = dma_sync_wait(&ch->api_ch, cookie);
- if (err) {
- dev_err(mic_dma_ch_to_device(ch), "%s %d TO chan 0x%x\n",
- __func__, __LINE__, ch->ch_num);
- err = -EIO;
- }
-error:
- mic_dma_cleanup(ch);
- return err;
-}
-
-static inline void mic_dma_chan_uninit(struct mic_dma_chan *ch)
-{
- mic_dma_chan_destroy(ch);
- mic_dma_cleanup(ch);
- mic_dma_free_status_dest(ch);
- mic_dma_free_desc_ring(ch);
-}
-
-static int mic_dma_init(struct mic_dma_device *mic_dma_dev,
- enum mic_dma_chan_owner owner)
-{
- int i, first_chan = mic_dma_dev->start_ch;
- struct mic_dma_chan *ch;
- int ret;
-
- for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) {
- ch = &mic_dma_dev->mic_ch[i];
- ch->ch_num = i;
- ch->owner = owner;
- spin_lock_init(&ch->cleanup_lock);
- spin_lock_init(&ch->prep_lock);
- spin_lock_init(&ch->issue_lock);
- ret = mic_dma_setup_irq(ch);
- if (ret)
- goto error;
- }
- return 0;
-error:
- for (i = i - 1; i >= first_chan; i--)
- mic_dma_free_irq(ch);
- return ret;
-}
-
-static void mic_dma_uninit(struct mic_dma_device *mic_dma_dev)
-{
- int i, first_chan = mic_dma_dev->start_ch;
- struct mic_dma_chan *ch;
-
- for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) {
- ch = &mic_dma_dev->mic_ch[i];
- mic_dma_free_irq(ch);
- }
-}
-
-static int mic_dma_alloc_chan_resources(struct dma_chan *ch)
-{
- int ret = mic_dma_chan_init(to_mic_dma_chan(ch));
- if (ret)
- return ret;
- return MIC_DMA_DESC_RX_SIZE;
-}
-
-static void mic_dma_free_chan_resources(struct dma_chan *ch)
-{
- struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
- mic_dma_drain_chan(mic_ch);
- mic_dma_chan_uninit(mic_ch);
-}
-
-/* Set the fn. handlers and register the dma device with dma api */
-static int mic_dma_register_dma_device(struct mic_dma_device *mic_dma_dev,
- enum mic_dma_chan_owner owner)
-{
- int i, first_chan = mic_dma_dev->start_ch;
-
- dma_cap_zero(mic_dma_dev->dma_dev.cap_mask);
- /*
- * This dma engine is not capable of host memory to host memory
- * transfers
- */
- dma_cap_set(DMA_MEMCPY, mic_dma_dev->dma_dev.cap_mask);
-
- if (MIC_DMA_CHAN_HOST == owner)
- dma_cap_set(DMA_PRIVATE, mic_dma_dev->dma_dev.cap_mask);
- mic_dma_dev->dma_dev.device_alloc_chan_resources =
- mic_dma_alloc_chan_resources;
- mic_dma_dev->dma_dev.device_free_chan_resources =
- mic_dma_free_chan_resources;
- mic_dma_dev->dma_dev.device_tx_status = mic_dma_tx_status;
- mic_dma_dev->dma_dev.device_prep_dma_memcpy = mic_dma_prep_memcpy_lock;
- mic_dma_dev->dma_dev.device_prep_dma_imm_data =
- mic_dma_prep_status_lock;
- mic_dma_dev->dma_dev.device_prep_dma_interrupt =
- mic_dma_prep_interrupt_lock;
- mic_dma_dev->dma_dev.device_issue_pending = mic_dma_issue_pending;
- mic_dma_dev->dma_dev.copy_align = MIC_DMA_ALIGN_SHIFT;
- INIT_LIST_HEAD(&mic_dma_dev->dma_dev.channels);
- for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) {
- mic_dma_dev->mic_ch[i].api_ch.device = &mic_dma_dev->dma_dev;
- dma_cookie_init(&mic_dma_dev->mic_ch[i].api_ch);
- list_add_tail(&mic_dma_dev->mic_ch[i].api_ch.device_node,
- &mic_dma_dev->dma_dev.channels);
- }
- return dmaenginem_async_device_register(&mic_dma_dev->dma_dev);
-}
-
-/*
- * Initializes dma channels and registers the dma device with the
- * dma engine api.
- */
-static struct mic_dma_device *mic_dma_dev_reg(struct mbus_device *mbdev,
- enum mic_dma_chan_owner owner)
-{
- struct mic_dma_device *mic_dma_dev;
- int ret;
- struct device *dev = &mbdev->dev;
-
- mic_dma_dev = devm_kzalloc(dev, sizeof(*mic_dma_dev), GFP_KERNEL);
- if (!mic_dma_dev) {
- ret = -ENOMEM;
- goto alloc_error;
- }
- mic_dma_dev->mbdev = mbdev;
- mic_dma_dev->dma_dev.dev = dev;
- mic_dma_dev->mmio = mbdev->mmio_va;
- if (MIC_DMA_CHAN_HOST == owner) {
- mic_dma_dev->start_ch = 0;
- mic_dma_dev->max_xfer_size = MIC_DMA_MAX_XFER_SIZE_HOST;
- } else {
- mic_dma_dev->start_ch = 4;
- mic_dma_dev->max_xfer_size = MIC_DMA_MAX_XFER_SIZE_CARD;
- }
- ret = mic_dma_init(mic_dma_dev, owner);
- if (ret)
- goto init_error;
- ret = mic_dma_register_dma_device(mic_dma_dev, owner);
- if (ret)
- goto reg_error;
- return mic_dma_dev;
-reg_error:
- mic_dma_uninit(mic_dma_dev);
-init_error:
- mic_dma_dev = NULL;
-alloc_error:
- dev_err(dev, "Error at %s %d ret=%d\n", __func__, __LINE__, ret);
- return mic_dma_dev;
-}
-
-static void mic_dma_dev_unreg(struct mic_dma_device *mic_dma_dev)
-{
- mic_dma_uninit(mic_dma_dev);
-}
-
-/* DEBUGFS CODE */
-static int mic_dma_reg_show(struct seq_file *s, void *pos)
-{
- struct mic_dma_device *mic_dma_dev = s->private;
- int i, chan_num, first_chan = mic_dma_dev->start_ch;
- struct mic_dma_chan *ch;
-
- seq_printf(s, "SBOX_DCR: %#x\n",
- mic_dma_mmio_read(&mic_dma_dev->mic_ch[first_chan],
- MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR));
- seq_puts(s, "DMA Channel Registers\n");
- seq_printf(s, "%-10s| %-10s %-10s %-10s %-10s %-10s",
- "Channel", "DCAR", "DTPR", "DHPR", "DRAR_HI", "DRAR_LO");
- seq_printf(s, " %-11s %-14s %-10s\n", "DCHERR", "DCHERRMSK", "DSTAT");
- for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) {
- ch = &mic_dma_dev->mic_ch[i];
- chan_num = ch->ch_num;
- seq_printf(s, "%-10i| %-#10x %-#10x %-#10x %-#10x",
- chan_num,
- mic_dma_read_reg(ch, MIC_DMA_REG_DCAR),
- mic_dma_read_reg(ch, MIC_DMA_REG_DTPR),
- mic_dma_read_reg(ch, MIC_DMA_REG_DHPR),
- mic_dma_read_reg(ch, MIC_DMA_REG_DRAR_HI));
- seq_printf(s, " %-#10x %-#10x %-#14x %-#10x\n",
- mic_dma_read_reg(ch, MIC_DMA_REG_DRAR_LO),
- mic_dma_read_reg(ch, MIC_DMA_REG_DCHERR),
- mic_dma_read_reg(ch, MIC_DMA_REG_DCHERRMSK),
- mic_dma_read_reg(ch, MIC_DMA_REG_DSTAT));
- }
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(mic_dma_reg);
-
-/* Debugfs parent dir */
-static struct dentry *mic_dma_dbg;
-
-static int mic_dma_driver_probe(struct mbus_device *mbdev)
-{
- struct mic_dma_device *mic_dma_dev;
- enum mic_dma_chan_owner owner;
-
- if (MBUS_DEV_DMA_MIC == mbdev->id.device)
- owner = MIC_DMA_CHAN_MIC;
- else
- owner = MIC_DMA_CHAN_HOST;
-
- mic_dma_dev = mic_dma_dev_reg(mbdev, owner);
- dev_set_drvdata(&mbdev->dev, mic_dma_dev);
-
- if (mic_dma_dbg) {
- mic_dma_dev->dbg_dir = debugfs_create_dir(dev_name(&mbdev->dev),
- mic_dma_dbg);
- debugfs_create_file("mic_dma_reg", 0444, mic_dma_dev->dbg_dir,
- mic_dma_dev, &mic_dma_reg_fops);
- }
- return 0;
-}
-
-static void mic_dma_driver_remove(struct mbus_device *mbdev)
-{
- struct mic_dma_device *mic_dma_dev;
-
- mic_dma_dev = dev_get_drvdata(&mbdev->dev);
- debugfs_remove_recursive(mic_dma_dev->dbg_dir);
- mic_dma_dev_unreg(mic_dma_dev);
-}
-
-static struct mbus_device_id id_table[] = {
- {MBUS_DEV_DMA_MIC, MBUS_DEV_ANY_ID},
- {MBUS_DEV_DMA_HOST, MBUS_DEV_ANY_ID},
- {0},
-};
-
-static struct mbus_driver mic_dma_driver = {
- .driver.name = KBUILD_MODNAME,
- .driver.owner = THIS_MODULE,
- .id_table = id_table,
- .probe = mic_dma_driver_probe,
- .remove = mic_dma_driver_remove,
-};
-
-static int __init mic_x100_dma_init(void)
-{
- int rc = mbus_register_driver(&mic_dma_driver);
- if (rc)
- return rc;
- mic_dma_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL);
- return 0;
-}
-
-static void __exit mic_x100_dma_exit(void)
-{
- debugfs_remove_recursive(mic_dma_dbg);
- mbus_unregister_driver(&mic_dma_driver);
-}
-
-module_init(mic_x100_dma_init);
-module_exit(mic_x100_dma_exit);
-
-MODULE_DEVICE_TABLE(mbus, id_table);
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC X100 DMA Driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/mic_x100_dma.h b/drivers/dma/mic_x100_dma.h
deleted file mode 100644
index 68ef43a..0000000
--- a/drivers/dma/mic_x100_dma.h
+++ /dev/null
@@ -1,275 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel MIC X100 DMA Driver.
- *
- * Adapted from IOAT dma driver.
- */
-#ifndef _MIC_X100_DMA_H_
-#define _MIC_X100_DMA_H_
-
-#include <linux/kernel.h>
-#include <linux/delay.h>
-#include <linux/sched.h>
-#include <linux/debugfs.h>
-#include <linux/slab.h>
-#include <linux/interrupt.h>
-#include <linux/mic_bus.h>
-
-#include "dmaengine.h"
-
-/*
- * MIC has a total of 8 dma channels.
- * Four channels are assigned for host SW use & the remaining for MIC SW.
- * MIC DMA transfer size & addresses need to be 64 byte aligned.
- */
-#define MIC_DMA_MAX_NUM_CHAN 8
-#define MIC_DMA_NUM_CHAN 4
-#define MIC_DMA_ALIGN_SHIFT DMAENGINE_ALIGN_64_BYTES
-#define MIC_DMA_ALIGN_BYTES (1 << MIC_DMA_ALIGN_SHIFT)
-#define MIC_DMA_DESC_RX_SIZE (128 * 1024 - 4)
-
-/*
- * Register descriptions
- * All the registers are 32 bit registers.
- * DCR is a global register and all others are per-channel.
- * DCR - bits 0, 2, 4, 6, 8, 10, 12, 14 - enable bits for channels 0 to 7
- * bits 1, 3, 5, 7, 9, 11, 13, 15 - owner bits for channels 0 to 7
- * DCAR - bit 24 & 25 interrupt masks for mic owned & host owned channels
- * DHPR - head of the descriptor ring updated by s/w
- * DTPR - tail of the descriptor ring updated by h/w
- * DRAR_LO - lower 32 bits of descriptor ring's mic address
- * DRAR_HI - 3:0 - remaining 4 bits of descriptor ring's mic address
- * 20:4 descriptor ring size
- * 25:21 mic smpt entry number
- * DSTAT - 16:0 h/w completion count; 31:28 dma engine status
- * DCHERR - this register is non-zero on error
- * DCHERRMSK - interrupt mask register
- */
-#define MIC_DMA_HW_CMP_CNT_MASK 0x1ffff
-#define MIC_DMA_CHAN_QUIESCE 0x20000000
-#define MIC_DMA_SBOX_BASE 0x00010000
-#define MIC_DMA_SBOX_DCR 0x0000A280
-#define MIC_DMA_SBOX_CH_BASE 0x0001A000
-#define MIC_DMA_SBOX_CHAN_OFF 0x40
-#define MIC_DMA_SBOX_DCAR_IM0 (0x1 << 24)
-#define MIC_DMA_SBOX_DCAR_IM1 (0x1 << 25)
-#define MIC_DMA_SBOX_DRARHI_SYS_MASK (0x1 << 26)
-#define MIC_DMA_REG_DCAR 0
-#define MIC_DMA_REG_DHPR 4
-#define MIC_DMA_REG_DTPR 8
-#define MIC_DMA_REG_DRAR_LO 20
-#define MIC_DMA_REG_DRAR_HI 24
-#define MIC_DMA_REG_DSTAT 32
-#define MIC_DMA_REG_DCHERR 44
-#define MIC_DMA_REG_DCHERRMSK 48
-
-/* HW dma desc */
-struct mic_dma_desc {
- u64 qw0;
- u64 qw1;
-};
-
-enum mic_dma_chan_owner {
- MIC_DMA_CHAN_MIC = 0,
- MIC_DMA_CHAN_HOST
-};
-
-/*
- * mic_dma_chan - channel specific information
- * @ch_num: channel number
- * @owner: owner of this channel
- * @last_tail: cached value of descriptor ring tail
- * @head: index of next descriptor in desc_ring
- * @issued: hardware notification point
- * @submitted: index that will be used to submit descriptors to h/w
- * @api_ch: dma engine api channel
- * @desc_ring: dma descriptor ring
- * @desc_ring_micpa: mic physical address of desc_ring
- * @status_dest: destination for status (fence) descriptor
- * @status_dest_micpa: mic address for status_dest,
- * DMA controller uses this address
- * @tx_array: array of async_tx
- * @cleanup_lock: lock held when processing completed tx
- * @prep_lock: lock held in prep_memcpy & released in tx_submit
- * @issue_lock: lock used to synchronize writes to head
- * @cookie: mic_irq cookie used with mic irq request
- */
-struct mic_dma_chan {
- int ch_num;
- enum mic_dma_chan_owner owner;
- u32 last_tail;
- u32 head;
- u32 issued;
- u32 submitted;
- struct dma_chan api_ch;
- struct mic_dma_desc *desc_ring;
- dma_addr_t desc_ring_micpa;
- u64 *status_dest;
- dma_addr_t status_dest_micpa;
- struct dma_async_tx_descriptor *tx_array;
- spinlock_t cleanup_lock;
- spinlock_t prep_lock;
- spinlock_t issue_lock;
- struct mic_irq *cookie;
-};
-
-/*
- * struct mic_dma_device - per mic device
- * @mic_ch: dma channels
- * @dma_dev: underlying dma device
- * @mbdev: mic bus dma device
- * @mmio: virtual address of the mmio space
- * @dbg_dir: debugfs directory
- * @start_ch: first channel number that can be used
- * @max_xfer_size: maximum transfer size per dma descriptor
- */
-struct mic_dma_device {
- struct mic_dma_chan mic_ch[MIC_DMA_MAX_NUM_CHAN];
- struct dma_device dma_dev;
- struct mbus_device *mbdev;
- void __iomem *mmio;
- struct dentry *dbg_dir;
- int start_ch;
- size_t max_xfer_size;
-};
-
-static inline struct mic_dma_chan *to_mic_dma_chan(struct dma_chan *ch)
-{
- return container_of(ch, struct mic_dma_chan, api_ch);
-}
-
-static inline struct mic_dma_device *to_mic_dma_dev(struct mic_dma_chan *ch)
-{
- return
- container_of((const typeof(((struct mic_dma_device *)0)->mic_ch)*)
- (ch - ch->ch_num), struct mic_dma_device, mic_ch);
-}
-
-static inline struct mbus_device *to_mbus_device(struct mic_dma_chan *ch)
-{
- return to_mic_dma_dev(ch)->mbdev;
-}
-
-static inline struct mbus_hw_ops *to_mbus_hw_ops(struct mic_dma_chan *ch)
-{
- return to_mbus_device(ch)->hw_ops;
-}
-
-static inline struct device *mic_dma_ch_to_device(struct mic_dma_chan *ch)
-{
- return to_mic_dma_dev(ch)->dma_dev.dev;
-}
-
-static inline void __iomem *mic_dma_chan_to_mmio(struct mic_dma_chan *ch)
-{
- return to_mic_dma_dev(ch)->mmio;
-}
-
-static inline u32 mic_dma_read_reg(struct mic_dma_chan *ch, u32 reg)
-{
- return ioread32(mic_dma_chan_to_mmio(ch) + MIC_DMA_SBOX_CH_BASE +
- ch->ch_num * MIC_DMA_SBOX_CHAN_OFF + reg);
-}
-
-static inline void mic_dma_write_reg(struct mic_dma_chan *ch, u32 reg, u32 val)
-{
- iowrite32(val, mic_dma_chan_to_mmio(ch) + MIC_DMA_SBOX_CH_BASE +
- ch->ch_num * MIC_DMA_SBOX_CHAN_OFF + reg);
-}
-
-static inline u32 mic_dma_mmio_read(struct mic_dma_chan *ch, u32 offset)
-{
- return ioread32(mic_dma_chan_to_mmio(ch) + offset);
-}
-
-static inline void mic_dma_mmio_write(struct mic_dma_chan *ch, u32 val,
- u32 offset)
-{
- iowrite32(val, mic_dma_chan_to_mmio(ch) + offset);
-}
-
-static inline u32 mic_dma_read_cmp_cnt(struct mic_dma_chan *ch)
-{
- return mic_dma_read_reg(ch, MIC_DMA_REG_DSTAT) &
- MIC_DMA_HW_CMP_CNT_MASK;
-}
-
-static inline void mic_dma_chan_set_owner(struct mic_dma_chan *ch)
-{
- u32 dcr = mic_dma_mmio_read(ch, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
- u32 chan_num = ch->ch_num;
-
- dcr = (dcr & ~(0x1 << (chan_num * 2))) | (ch->owner << (chan_num * 2));
- mic_dma_mmio_write(ch, dcr, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
-}
-
-static inline void mic_dma_enable_chan(struct mic_dma_chan *ch)
-{
- u32 dcr = mic_dma_mmio_read(ch, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
-
- dcr |= 2 << (ch->ch_num << 1);
- mic_dma_mmio_write(ch, dcr, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
-}
-
-static inline void mic_dma_disable_chan(struct mic_dma_chan *ch)
-{
- u32 dcr = mic_dma_mmio_read(ch, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
-
- dcr &= ~(2 << (ch->ch_num << 1));
- mic_dma_mmio_write(ch, dcr, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
-}
-
-static void mic_dma_chan_set_desc_ring(struct mic_dma_chan *ch)
-{
- u32 drar_hi;
- dma_addr_t desc_ring_micpa = ch->desc_ring_micpa;
-
- drar_hi = (MIC_DMA_DESC_RX_SIZE & 0x1ffff) << 4;
- if (MIC_DMA_CHAN_MIC == ch->owner) {
- drar_hi |= (desc_ring_micpa >> 32) & 0xf;
- } else {
- drar_hi |= MIC_DMA_SBOX_DRARHI_SYS_MASK;
- drar_hi |= ((desc_ring_micpa >> 34)
- & 0x1f) << 21;
- drar_hi |= (desc_ring_micpa >> 32) & 0x3;
- }
- mic_dma_write_reg(ch, MIC_DMA_REG_DRAR_LO, (u32) desc_ring_micpa);
- mic_dma_write_reg(ch, MIC_DMA_REG_DRAR_HI, drar_hi);
-}
-
-static inline void mic_dma_chan_mask_intr(struct mic_dma_chan *ch)
-{
- u32 dcar = mic_dma_read_reg(ch, MIC_DMA_REG_DCAR);
-
- if (MIC_DMA_CHAN_MIC == ch->owner)
- dcar |= MIC_DMA_SBOX_DCAR_IM0;
- else
- dcar |= MIC_DMA_SBOX_DCAR_IM1;
- mic_dma_write_reg(ch, MIC_DMA_REG_DCAR, dcar);
-}
-
-static inline void mic_dma_chan_unmask_intr(struct mic_dma_chan *ch)
-{
- u32 dcar = mic_dma_read_reg(ch, MIC_DMA_REG_DCAR);
-
- if (MIC_DMA_CHAN_MIC == ch->owner)
- dcar &= ~MIC_DMA_SBOX_DCAR_IM0;
- else
- dcar &= ~MIC_DMA_SBOX_DCAR_IM1;
- mic_dma_write_reg(ch, MIC_DMA_REG_DCAR, dcar);
-}
-
-static void mic_dma_ack_interrupt(struct mic_dma_chan *ch)
-{
- if (MIC_DMA_CHAN_MIC == ch->owner) {
- /* HW errata */
- mic_dma_chan_mask_intr(ch);
- mic_dma_chan_unmask_intr(ch);
- }
- to_mbus_hw_ops(ch)->ack_interrupt(to_mbus_device(ch), ch->ch_num);
-}
-#endif
diff --git a/drivers/firmware/arm_scmi/base.c b/drivers/firmware/arm_scmi/base.c
index 9853bd3..017e5d8 100644
--- a/drivers/firmware/arm_scmi/base.c
+++ b/drivers/firmware/arm_scmi/base.c
@@ -197,6 +197,8 @@
protocols_imp[tot_num_ret + loop] = *(list + loop);
tot_num_ret += loop_num_ret;
+
+ scmi_reset_rx_to_maxsz(handle, t);
} while (loop_num_ret);
scmi_xfer_put(handle, t);
diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c
index c1cfe3e..4645677 100644
--- a/drivers/firmware/arm_scmi/clock.c
+++ b/drivers/firmware/arm_scmi/clock.c
@@ -192,6 +192,8 @@
}
tot_rate_cnt += num_returned;
+
+ scmi_reset_rx_to_maxsz(handle, t);
/*
* check for both returned and remaining to avoid infinite
* loop due to buggy firmware
diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h
index 37fb583..65063fa 100644
--- a/drivers/firmware/arm_scmi/common.h
+++ b/drivers/firmware/arm_scmi/common.h
@@ -147,6 +147,8 @@
struct scmi_xfer *xfer);
int scmi_xfer_get_init(const struct scmi_handle *h, u8 msg_id, u8 prot_id,
size_t tx_size, size_t rx_size, struct scmi_xfer **p);
+void scmi_reset_rx_to_maxsz(const struct scmi_handle *handle,
+ struct scmi_xfer *xfer);
int scmi_handle_put(const struct scmi_handle *handle);
struct scmi_handle *scmi_handle_get(struct device *dev);
void scmi_set_handle(struct scmi_device *scmi_dev);
diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c
index c5dea87..3dfd8b6 100644
--- a/drivers/firmware/arm_scmi/driver.c
+++ b/drivers/firmware/arm_scmi/driver.c
@@ -402,6 +402,14 @@
return ret;
}
+void scmi_reset_rx_to_maxsz(const struct scmi_handle *handle,
+ struct scmi_xfer *xfer)
+{
+ struct scmi_info *info = handle_to_scmi_info(handle);
+
+ xfer->rx.len = info->desc->max_msg_size;
+}
+
#define SCMI_MAX_RESPONSE_TIMEOUT (2 * MSEC_PER_SEC)
/**
diff --git a/drivers/firmware/arm_scmi/notify.c b/drivers/firmware/arm_scmi/notify.c
index 2754f9d..ce33689 100644
--- a/drivers/firmware/arm_scmi/notify.c
+++ b/drivers/firmware/arm_scmi/notify.c
@@ -1403,15 +1403,21 @@
"finalized PENDING handler - key:%X\n",
hndl->key);
ret = scmi_event_handler_enable_events(hndl);
+ if (ret) {
+ dev_dbg(ni->handle->dev,
+ "purging INVALID handler - key:%X\n",
+ hndl->key);
+ scmi_put_active_handler(ni, hndl);
+ }
} else {
ret = scmi_valid_pending_handler(ni, hndl);
- }
- if (ret) {
- dev_dbg(ni->handle->dev,
- "purging PENDING handler - key:%X\n",
- hndl->key);
- /* this hndl can be only a pending one */
- scmi_put_handler_unlocked(ni, hndl);
+ if (ret) {
+ dev_dbg(ni->handle->dev,
+ "purging PENDING handler - key:%X\n",
+ hndl->key);
+ /* this hndl can be only a pending one */
+ scmi_put_handler_unlocked(ni, hndl);
+ }
}
}
mutex_unlock(&ni->pending_mtx);
@@ -1468,7 +1474,7 @@
ni->gid = gid;
ni->handle = handle;
- ni->notify_wq = alloc_workqueue("scmi_notify",
+ ni->notify_wq = alloc_workqueue(dev_name(handle->dev),
WQ_UNBOUND | WQ_FREEZABLE | WQ_SYSFS,
0);
if (!ni->notify_wq)
diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c
index ed475b40..82fb3ba 100644
--- a/drivers/firmware/arm_scmi/perf.c
+++ b/drivers/firmware/arm_scmi/perf.c
@@ -304,6 +304,8 @@
}
tot_opp_cnt += num_returned;
+
+ scmi_reset_rx_to_maxsz(handle, t);
/*
* check for both returned and remaining to avoid infinite
* loop due to buggy firmware
diff --git a/drivers/firmware/arm_scmi/reset.c b/drivers/firmware/arm_scmi/reset.c
index f063cfe..a981a22 100644
--- a/drivers/firmware/arm_scmi/reset.c
+++ b/drivers/firmware/arm_scmi/reset.c
@@ -36,9 +36,7 @@
#define EXPLICIT_RESET_ASSERT BIT(1)
#define ASYNCHRONOUS_RESET BIT(2)
__le32 reset_state;
-#define ARCH_RESET_TYPE BIT(31)
-#define COLD_RESET_STATE BIT(0)
-#define ARCH_COLD_RESET (ARCH_RESET_TYPE | COLD_RESET_STATE)
+#define ARCH_COLD_RESET 0
};
struct scmi_msg_reset_notify {
diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c
index 9703cf6..b4232d6 100644
--- a/drivers/firmware/arm_scmi/sensors.c
+++ b/drivers/firmware/arm_scmi/sensors.c
@@ -166,6 +166,8 @@
}
desc_index += num_returned;
+
+ scmi_reset_rx_to_maxsz(handle, t);
/*
* check for both returned and remaining to avoid infinite
* loop due to buggy firmware
diff --git a/drivers/firmware/arm_scmi/smc.c b/drivers/firmware/arm_scmi/smc.c
index 1a03c3e..82a82a5 100644
--- a/drivers/firmware/arm_scmi/smc.c
+++ b/drivers/firmware/arm_scmi/smc.c
@@ -149,6 +149,6 @@
const struct scmi_desc scmi_smc_desc = {
.ops = &scmi_smc_ops,
.max_rx_timeout_ms = 30,
- .max_msg = 1,
+ .max_msg = 20,
.max_msg_size = 128,
};
diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 8d1ff24..efb8a66 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -147,6 +147,9 @@
return 0;
/* Return value if feature is already checked */
+ if (api_id > ARRAY_SIZE(zynqmp_pm_features))
+ return PM_FEATURE_INVALID;
+
if (zynqmp_pm_features[api_id] != PM_FEATURE_UNCHECKED)
return zynqmp_pm_features[api_id];
diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c
index e44d5de..b966f5e 100644
--- a/drivers/gpio/gpio-aspeed.c
+++ b/drivers/gpio/gpio-aspeed.c
@@ -1114,6 +1114,7 @@
static const struct aspeed_bank_props ast2600_bank_props[] = {
/* input output */
+ {4, 0xffffffff, 0x00ffffff}, /* Q/R/S/T */
{5, 0xffffffff, 0xffffff00}, /* U/V/W/X */
{6, 0x0000ffff, 0x0000ffff}, /* Y/Z */
{ },
diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c
index a5b3267..2a9046c 100644
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@@ -343,8 +343,8 @@
#ifdef CONFIG_PM_SLEEP
static int dwapb_irq_set_wake(struct irq_data *d, unsigned int enable)
{
- struct irq_chip_generic *igc = irq_data_get_irq_chip_data(d);
- struct dwapb_gpio *gpio = igc->private;
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct dwapb_gpio *gpio = to_dwapb_gpio(gc);
struct dwapb_context *ctx = gpio->ports[0].ctx;
irq_hw_number_t bit = irqd_to_hwirq(d);
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index 6d59e3a..f7ceb2b 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -1114,13 +1114,23 @@
{
struct device *dev = bank->chip.parent;
void __iomem *base = bank->base;
- u32 nowake;
+ u32 mask, nowake;
bank->saved_datain = readl_relaxed(base + bank->regs->datain);
if (!bank->enabled_non_wakeup_gpios)
goto update_gpio_context_count;
+ /* Check for pending EDGE_FALLING, ignore EDGE_BOTH */
+ mask = bank->enabled_non_wakeup_gpios & bank->context.fallingdetect;
+ mask &= ~bank->context.risingdetect;
+ bank->saved_datain |= mask;
+
+ /* Check for pending EDGE_RISING, ignore EDGE_BOTH */
+ mask = bank->enabled_non_wakeup_gpios & bank->context.risingdetect;
+ mask &= ~bank->context.fallingdetect;
+ bank->saved_datain &= ~mask;
+
if (!may_lose_context)
goto update_gpio_context_count;
diff --git a/drivers/gpio/gpio-pcie-idio-24.c b/drivers/gpio/gpio-pcie-idio-24.c
index a68941d..2a07fd9 100644
--- a/drivers/gpio/gpio-pcie-idio-24.c
+++ b/drivers/gpio/gpio-pcie-idio-24.c
@@ -28,6 +28,47 @@
#include <linux/spinlock.h>
#include <linux/types.h>
+/*
+ * PLX PEX8311 PCI LCS_INTCSR Interrupt Control/Status
+ *
+ * Bit: Description
+ * 0: Enable Interrupt Sources (Bit 0)
+ * 1: Enable Interrupt Sources (Bit 1)
+ * 2: Generate Internal PCI Bus Internal SERR# Interrupt
+ * 3: Mailbox Interrupt Enable
+ * 4: Power Management Interrupt Enable
+ * 5: Power Management Interrupt
+ * 6: Slave Read Local Data Parity Check Error Enable
+ * 7: Slave Read Local Data Parity Check Error Status
+ * 8: Internal PCI Wire Interrupt Enable
+ * 9: PCI Express Doorbell Interrupt Enable
+ * 10: PCI Abort Interrupt Enable
+ * 11: Local Interrupt Input Enable
+ * 12: Retry Abort Enable
+ * 13: PCI Express Doorbell Interrupt Active
+ * 14: PCI Abort Interrupt Active
+ * 15: Local Interrupt Input Active
+ * 16: Local Interrupt Output Enable
+ * 17: Local Doorbell Interrupt Enable
+ * 18: DMA Channel 0 Interrupt Enable
+ * 19: DMA Channel 1 Interrupt Enable
+ * 20: Local Doorbell Interrupt Active
+ * 21: DMA Channel 0 Interrupt Active
+ * 22: DMA Channel 1 Interrupt Active
+ * 23: Built-In Self-Test (BIST) Interrupt Active
+ * 24: Direct Master was the Bus Master during a Master or Target Abort
+ * 25: DMA Channel 0 was the Bus Master during a Master or Target Abort
+ * 26: DMA Channel 1 was the Bus Master during a Master or Target Abort
+ * 27: Target Abort after internal 256 consecutive Master Retrys
+ * 28: PCI Bus wrote data to LCS_MBOX0
+ * 29: PCI Bus wrote data to LCS_MBOX1
+ * 30: PCI Bus wrote data to LCS_MBOX2
+ * 31: PCI Bus wrote data to LCS_MBOX3
+ */
+#define PLX_PEX8311_PCI_LCS_INTCSR 0x68
+#define INTCSR_INTERNAL_PCI_WIRE BIT(8)
+#define INTCSR_LOCAL_INPUT BIT(11)
+
/**
* struct idio_24_gpio_reg - GPIO device registers structure
* @out0_7: Read: FET Outputs 0-7
@@ -92,6 +133,7 @@
struct idio_24_gpio {
struct gpio_chip chip;
raw_spinlock_t lock;
+ __u8 __iomem *plx;
struct idio_24_gpio_reg __iomem *reg;
unsigned long irq_mask;
};
@@ -334,13 +376,13 @@
unsigned long flags;
const unsigned long bit_offset = irqd_to_hwirq(data) - 24;
unsigned char new_irq_mask;
- const unsigned long bank_offset = bit_offset/8 * 8;
+ const unsigned long bank_offset = bit_offset / 8;
unsigned char cos_enable_state;
raw_spin_lock_irqsave(&idio24gpio->lock, flags);
- idio24gpio->irq_mask &= BIT(bit_offset);
- new_irq_mask = idio24gpio->irq_mask >> bank_offset;
+ idio24gpio->irq_mask &= ~BIT(bit_offset);
+ new_irq_mask = idio24gpio->irq_mask >> bank_offset * 8;
if (!new_irq_mask) {
cos_enable_state = ioread8(&idio24gpio->reg->cos_enable);
@@ -363,12 +405,12 @@
unsigned long flags;
unsigned char prev_irq_mask;
const unsigned long bit_offset = irqd_to_hwirq(data) - 24;
- const unsigned long bank_offset = bit_offset/8 * 8;
+ const unsigned long bank_offset = bit_offset / 8;
unsigned char cos_enable_state;
raw_spin_lock_irqsave(&idio24gpio->lock, flags);
- prev_irq_mask = idio24gpio->irq_mask >> bank_offset;
+ prev_irq_mask = idio24gpio->irq_mask >> bank_offset * 8;
idio24gpio->irq_mask |= BIT(bit_offset);
if (!prev_irq_mask) {
@@ -455,6 +497,7 @@
struct device *const dev = &pdev->dev;
struct idio_24_gpio *idio24gpio;
int err;
+ const size_t pci_plx_bar_index = 1;
const size_t pci_bar_index = 2;
const char *const name = pci_name(pdev);
struct gpio_irq_chip *girq;
@@ -469,12 +512,13 @@
return err;
}
- err = pcim_iomap_regions(pdev, BIT(pci_bar_index), name);
+ err = pcim_iomap_regions(pdev, BIT(pci_plx_bar_index) | BIT(pci_bar_index), name);
if (err) {
dev_err(dev, "Unable to map PCI I/O addresses (%d)\n", err);
return err;
}
+ idio24gpio->plx = pcim_iomap_table(pdev)[pci_plx_bar_index];
idio24gpio->reg = pcim_iomap_table(pdev)[pci_bar_index];
idio24gpio->chip.label = name;
@@ -504,6 +548,12 @@
/* Software board reset */
iowrite8(0, &idio24gpio->reg->soft_reset);
+ /*
+ * enable PLX PEX8311 internal PCI wire interrupt and local interrupt
+ * input
+ */
+ iowrite8((INTCSR_INTERNAL_PCI_WIRE | INTCSR_LOCAL_INPUT) >> 8,
+ idio24gpio->plx + PLX_PEX8311_PCI_LCS_INTCSR + 1);
err = devm_gpiochip_add_data(dev, &idio24gpio->chip, idio24gpio);
if (err) {
diff --git a/drivers/gpio/gpio-sifive.c b/drivers/gpio/gpio-sifive.c
index c54dd08..d5eb9ca 100644
--- a/drivers/gpio/gpio-sifive.c
+++ b/drivers/gpio/gpio-sifive.c
@@ -183,7 +183,7 @@
return PTR_ERR(chip->regs);
ngpio = of_irq_count(node);
- if (ngpio >= SIFIVE_GPIO_MAX) {
+ if (ngpio > SIFIVE_GPIO_MAX) {
dev_err(dev, "Too many GPIO interrupts (max=%d)\n",
SIFIVE_GPIO_MAX);
return -ENXIO;
diff --git a/drivers/gpio/gpiolib-cdev.h b/drivers/gpio/gpiolib-cdev.h
index cb41dd7..b42644c 100644
--- a/drivers/gpio/gpiolib-cdev.h
+++ b/drivers/gpio/gpiolib-cdev.h
@@ -7,22 +7,7 @@
struct gpio_device;
-#ifdef CONFIG_GPIO_CDEV
-
int gpiolib_cdev_register(struct gpio_device *gdev, dev_t devt);
void gpiolib_cdev_unregister(struct gpio_device *gdev);
-#else
-
-static inline int gpiolib_cdev_register(struct gpio_device *gdev, dev_t devt)
-{
- return 0;
-}
-
-static inline void gpiolib_cdev_unregister(struct gpio_device *gdev)
-{
-}
-
-#endif /* CONFIG_GPIO_CDEV */
-
#endif /* GPIOLIB_CDEV_H */
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 3cdf9ef..089ddca 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -480,11 +480,23 @@
kfree(gdev);
}
+#ifdef CONFIG_GPIO_CDEV
+#define gcdev_register(gdev, devt) gpiolib_cdev_register((gdev), (devt))
+#define gcdev_unregister(gdev) gpiolib_cdev_unregister((gdev))
+#else
+/*
+ * gpiolib_cdev_register() indirectly calls device_add(), which is still
+ * required even when cdev is not selected.
+ */
+#define gcdev_register(gdev, devt) device_add(&(gdev)->dev)
+#define gcdev_unregister(gdev) device_del(&(gdev)->dev)
+#endif
+
static int gpiochip_setup_dev(struct gpio_device *gdev)
{
int ret;
- ret = gpiolib_cdev_register(gdev, gpio_devt);
+ ret = gcdev_register(gdev, gpio_devt);
if (ret)
return ret;
@@ -500,7 +512,7 @@
return 0;
err_remove_device:
- gpiolib_cdev_unregister(gdev);
+ gcdev_unregister(gdev);
return ret;
}
@@ -825,7 +837,7 @@
* be removed, else it will be dangling until the last user is
* gone.
*/
- gpiolib_cdev_unregister(gdev);
+ gcdev_unregister(gdev);
put_device(&gdev->dev);
}
EXPORT_SYMBOL_GPL(gpiochip_remove);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 37da353..e3783f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -80,6 +80,7 @@
MODULE_FIRMWARE("amdgpu/navi10_gpu_info.bin");
MODULE_FIRMWARE("amdgpu/navi14_gpu_info.bin");
MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_gpu_info.bin");
#define AMDGPU_RESUME_MS 2000
@@ -239,9 +240,11 @@
return amdgpu_asic_supports_baco(adev);
}
+/*
+ * VRAM access helper functions
+ */
+
/**
- * VRAM access helper functions.
- *
* amdgpu_device_vram_access - read/write a buffer in vram
*
* @adev: amdgpu_device pointer
@@ -705,7 +708,7 @@
/**
* amdgpu_invalid_rreg - dummy reg read function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @reg: offset of register
*
* Dummy register read function. Used for register blocks
@@ -722,7 +725,7 @@
/**
* amdgpu_invalid_wreg - dummy reg write function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @reg: offset of register
* @v: value to write to the register
*
@@ -739,7 +742,7 @@
/**
* amdgpu_invalid_rreg64 - dummy 64 bit reg read function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @reg: offset of register
*
* Dummy register read function. Used for register blocks
@@ -756,7 +759,7 @@
/**
* amdgpu_invalid_wreg64 - dummy reg write function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @reg: offset of register
* @v: value to write to the register
*
@@ -773,7 +776,7 @@
/**
* amdgpu_block_invalid_rreg - dummy reg read function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @block: offset of instance
* @reg: offset of register
*
@@ -793,7 +796,7 @@
/**
* amdgpu_block_invalid_wreg - dummy reg write function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @block: offset of instance
* @reg: offset of register
* @v: value to write to the register
@@ -813,7 +816,7 @@
/**
* amdgpu_device_asic_init - Wrapper for atom asic_init
*
- * @dev: drm_device pointer
+ * @adev: amdgpu_device pointer
*
* Does any asic specific work and then calls atom asic init.
*/
@@ -827,7 +830,7 @@
/**
* amdgpu_device_vram_scratch_init - allocate the VRAM scratch page
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
*
* Allocates a scratch page of VRAM for use by various things in the
* driver.
@@ -844,7 +847,7 @@
/**
* amdgpu_device_vram_scratch_fini - Free the VRAM scratch page
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
*
* Frees the VRAM scratch page.
*/
@@ -1803,7 +1806,10 @@
chip_name = "arcturus";
break;
case CHIP_RENOIR:
- chip_name = "renoir";
+ if (adev->apu_flags & AMD_APU_IS_RENOIR)
+ chip_name = "renoir";
+ else
+ chip_name = "green_sardine";
break;
case CHIP_NAVI10:
chip_name = "navi10";
@@ -3011,7 +3017,7 @@
/**
* amdgpu_device_has_dc_support - check if dc is supported
*
- * @adev: amdgpu_device_pointer
+ * @adev: amdgpu_device pointer
*
* Returns true for supported, false for not supported
*/
@@ -4045,7 +4051,7 @@
/**
* amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @from_hypervisor: request from hypervisor
*
* do VF FLR and reinitialize Asic
@@ -4100,7 +4106,7 @@
/**
* amdgpu_device_has_job_running - check if there is any job in mirror list
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
*
* check if there is any job in mirror list
*/
@@ -4128,7 +4134,7 @@
/**
* amdgpu_device_should_recover_gpu - check if we should try GPU recovery
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
*
* Check amdgpu_gpu_recovery and SRIOV status to see if we should try to recover
* a hung GPU.
@@ -4477,7 +4483,7 @@
/**
* amdgpu_device_gpu_recover - reset the asic and recover scheduler
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @job: which job trigger hang
*
* Attempt to reset the GPU if it has hung (all asics).
@@ -4497,7 +4503,7 @@
bool need_emergency_restart = false;
bool audio_suspended = false;
- /**
+ /*
* Special case: RAS triggered and full reset isn't supported
*/
need_emergency_restart = amdgpu_ras_need_emergency_restart(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index c241317..8e988f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1055,10 +1055,10 @@
{0x1002, 0x15dd, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU},
{0x1002, 0x15d8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU},
/* Arcturus */
- {0x1002, 0x738C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT},
- {0x1002, 0x7388, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT},
- {0x1002, 0x738E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT},
- {0x1002, 0x7390, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT},
+ {0x1002, 0x738C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS},
+ {0x1002, 0x7388, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS},
+ {0x1002, 0x738E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS},
+ {0x1002, 0x7390, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS},
/* Navi10 */
{0x1002, 0x7310, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
{0x1002, 0x7312, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
@@ -1066,6 +1066,7 @@
{0x1002, 0x7319, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
{0x1002, 0x731A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
{0x1002, 0x731B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
+ {0x1002, 0x731E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
{0x1002, 0x731F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
/* Navi14 */
{0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index aa7f230..7e8265d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -596,6 +596,7 @@
struct ww_acquire_ctx ticket;
struct list_head list, duplicates;
uint64_t va_flags;
+ uint64_t vm_size;
int r = 0;
if (args->va_address < AMDGPU_VA_RESERVED_SIZE) {
@@ -616,6 +617,15 @@
args->va_address &= AMDGPU_GMC_HOLE_MASK;
+ vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE;
+ vm_size -= AMDGPU_VA_RESERVED_SIZE;
+ if (args->va_address + args->map_size > vm_size) {
+ dev_dbg(&dev->pdev->dev,
+ "va_address 0x%llx is in top reserved area 0x%llx\n",
+ args->va_address + args->map_size, vm_size);
+ return -EINVAL;
+ }
+
if ((args->flags & ~valid_flags) && (args->flags & ~prt_flags)) {
dev_dbg(&dev->pdev->dev, "invalid flags combination 0x%08X\n",
args->flags);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index f203e4a..731f3aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -81,8 +81,8 @@
/**
* amdgpu_gtt_mgr_init - init GTT manager and DRM MM
*
- * @man: TTM memory type manager
- * @p_size: maximum size of GTT
+ * @adev: amdgpu_device pointer
+ * @gtt_size: maximum size of GTT
*
* Allocate and initialize the GTT manager.
*/
@@ -123,7 +123,7 @@
/**
* amdgpu_gtt_mgr_fini - free and destroy GTT manager
*
- * @man: TTM memory type manager
+ * @adev: amdgpu_device pointer
*
* Destroy and free the GTT manager, returns -EBUSY if ranges are still
* allocated inside it.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 96a9699..a6dbe4b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -2524,6 +2524,7 @@
psp->asd_feature_version = le32_to_cpu(desc->fw_version);
psp->asd_ucode_size = le32_to_cpu(desc->size_bytes);
psp->asd_start_addr = ucode_start_addr;
+ psp->asd_fw = psp->ta_fw;
break;
case TA_FW_TYPE_PSP_XGMI:
psp->ta_xgmi_ucode_version = le32_to_cpu(desc->fw_version);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index f3b7287..a563328 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -39,6 +39,7 @@
#define FIRMWARE_RAVEN2 "amdgpu/raven2_vcn.bin"
#define FIRMWARE_ARCTURUS "amdgpu/arcturus_vcn.bin"
#define FIRMWARE_RENOIR "amdgpu/renoir_vcn.bin"
+#define FIRMWARE_GREEN_SARDINE "amdgpu/green_sardine_vcn.bin"
#define FIRMWARE_NAVI10 "amdgpu/navi10_vcn.bin"
#define FIRMWARE_NAVI14 "amdgpu/navi14_vcn.bin"
#define FIRMWARE_NAVI12 "amdgpu/navi12_vcn.bin"
@@ -50,6 +51,7 @@
MODULE_FIRMWARE(FIRMWARE_RAVEN2);
MODULE_FIRMWARE(FIRMWARE_ARCTURUS);
MODULE_FIRMWARE(FIRMWARE_RENOIR);
+MODULE_FIRMWARE(FIRMWARE_GREEN_SARDINE);
MODULE_FIRMWARE(FIRMWARE_NAVI10);
MODULE_FIRMWARE(FIRMWARE_NAVI14);
MODULE_FIRMWARE(FIRMWARE_NAVI12);
@@ -89,7 +91,11 @@
adev->vcn.indirect_sram = true;
break;
case CHIP_RENOIR:
- fw_name = FIRMWARE_RENOIR;
+ if (adev->apu_flags & AMD_APU_IS_RENOIR)
+ fw_name = FIRMWARE_RENOIR;
+ else
+ fw_name = FIRMWARE_GREEN_SARDINE;
+
if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
(adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
adev->vcn.indirect_sram = true;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index c6abb16..58c83a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -112,8 +112,8 @@
#define AMDGPU_MMHUB_0 1
#define AMDGPU_MMHUB_1 2
-/* hardcode that limit for now */
-#define AMDGPU_VA_RESERVED_SIZE (1ULL << 20)
+/* Reserve 2MB at top/bottom of address space for kernel use */
+#define AMDGPU_VA_RESERVED_SIZE (2ULL << 20)
/* max vmids dedicated for process */
#define AMDGPU_VM_MAX_RESERVED_VMID 1
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 01c1171..0c6b7c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -168,8 +168,7 @@
/**
* amdgpu_vram_mgr_init - init VRAM manager and DRM MM
*
- * @man: TTM memory type manager
- * @p_size: maximum size of VRAM
+ * @adev: amdgpu_device pointer
*
* Allocate and initialize the VRAM manager.
*/
@@ -199,7 +198,7 @@
/**
* amdgpu_vram_mgr_fini - free and destroy VRAM manager
*
- * @man: TTM memory type manager
+ * @adev: amdgpu_device pointer
*
* Destroy and free the VRAM manager, returns -EBUSY if ranges are still
* allocated inside it.
@@ -229,7 +228,7 @@
/**
* amdgpu_vram_mgr_vis_size - Calculate visible node size
*
- * @adev: amdgpu device structure
+ * @adev: amdgpu_device pointer
* @node: MM node structure
*
* Calculate how many bytes of the MM node are inside visible VRAM
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 03ff8bd..5442df0 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1336,11 +1336,13 @@
switch (adev->asic_type) {
case CHIP_BONAIRE:
- case CHIP_HAWAII:
/* disable baco reset until it works */
/* smu7_asic_get_baco_capability(adev, &baco_reset); */
baco_reset = false;
break;
+ case CHIP_HAWAII:
+ baco_reset = cik_asic_supports_baco(adev);
+ break;
default:
baco_reset = false;
break;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index 20f1088..a3c3fe9 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -1071,22 +1071,19 @@
{
u32 srbm_soft_reset = 0;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- u32 tmp = RREG32(mmSRBM_STATUS2);
+ u32 tmp;
- if (tmp & SRBM_STATUS2__SDMA_BUSY_MASK) {
- /* sdma0 */
- tmp = RREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET);
- tmp |= SDMA0_F32_CNTL__HALT_MASK;
- WREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET, tmp);
- srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA_MASK;
- }
- if (tmp & SRBM_STATUS2__SDMA1_BUSY_MASK) {
- /* sdma1 */
- tmp = RREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET);
- tmp |= SDMA0_F32_CNTL__HALT_MASK;
- WREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET, tmp);
- srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA1_MASK;
- }
+ /* sdma0 */
+ tmp = RREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET);
+ tmp |= SDMA0_F32_CNTL__HALT_MASK;
+ WREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET, tmp);
+ srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA_MASK;
+
+ /* sdma1 */
+ tmp = RREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET);
+ tmp |= SDMA0_F32_CNTL__HALT_MASK;
+ WREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET, tmp);
+ srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA1_MASK;
if (srbm_soft_reset) {
tmp = RREG32(mmSRBM_SOFT_RESET);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 56fdbe6..3579565 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -128,6 +128,9 @@
#define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO__SHIFT 0x3
#define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO_MASK 0x00000008L
+#define mmCGTT_SPI_CS_CLK_CTRL 0x507c
+#define mmCGTT_SPI_CS_CLK_CTRL_BASE_IDX 1
+
MODULE_FIRMWARE("amdgpu/navi10_ce.bin");
MODULE_FIRMWARE("amdgpu/navi10_pfp.bin");
MODULE_FIRMWARE("amdgpu/navi10_me.bin");
@@ -3094,6 +3097,7 @@
static const struct soc15_reg_golden golden_settings_gc_10_3[] =
{
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CS_CLK_CTRL, 0x78000000, 0x78000100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_PS_CLK_CTRL, 0xff7f0fff, 0x78000100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_RA0_CLK_CTRL, 0xff7f0fff, 0x30000100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_RA1_CLK_CTRL, 0xff7f0fff, 0x7e000100),
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 6959aeb..0d8e203 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -117,6 +117,13 @@
MODULE_FIRMWARE("amdgpu/renoir_mec2.bin");
MODULE_FIRMWARE("amdgpu/renoir_rlc.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_ce.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_pfp.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_me.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_mec.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_mec2.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_rlc.bin");
+
#define mmTCP_CHAN_STEER_0_ARCT 0x0b03
#define mmTCP_CHAN_STEER_0_ARCT_BASE_IDX 0
#define mmTCP_CHAN_STEER_1_ARCT 0x0b04
@@ -1630,7 +1637,10 @@
chip_name = "arcturus";
break;
case CHIP_RENOIR:
- chip_name = "renoir";
+ if (adev->apu_flags & AMD_APU_IS_RENOIR)
+ chip_name = "renoir";
+ else
+ chip_name = "green_sardine";
break;
default:
BUG();
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 1ce741a..8eeba80 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -455,6 +455,15 @@
adev->virt.ops = &xgpu_nv_virt_ops;
}
+static bool nv_is_headless_sku(struct pci_dev *pdev)
+{
+ if ((pdev->device == 0x731E &&
+ (pdev->revision == 0xC6 || pdev->revision == 0xC7)) ||
+ (pdev->device == 0x7340 && pdev->revision == 0xC9))
+ return true;
+ return false;
+}
+
int nv_set_ip_blocks(struct amdgpu_device *adev)
{
int r;
@@ -491,7 +500,8 @@
if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT &&
!amdgpu_sriov_vf(adev))
amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
- amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
+ if (!nv_is_headless_sku(adev->pdev))
+ amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
if (adev->enable_mes)
amdgpu_device_ip_block_add(adev, &mes_v10_1_ip_block);
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
index 7548931..c4828bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
@@ -39,6 +39,8 @@
MODULE_FIRMWARE("amdgpu/renoir_asd.bin");
MODULE_FIRMWARE("amdgpu/renoir_ta.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_asd.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_ta.bin");
/* address block */
#define smnMP1_FIRMWARE_FLAGS 0x3010024
@@ -54,7 +56,10 @@
switch (adev->asic_type) {
case CHIP_RENOIR:
- chip_name = "renoir";
+ if (adev->apu_flags & AMD_APU_IS_RENOIR)
+ chip_name = "renoir";
+ else
+ chip_name = "green_sardine";
break;
default:
BUG();
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 86fb1ed..e82f49f 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -69,6 +69,7 @@
MODULE_FIRMWARE("amdgpu/raven2_sdma.bin");
MODULE_FIRMWARE("amdgpu/arcturus_sdma.bin");
MODULE_FIRMWARE("amdgpu/renoir_sdma.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_sdma.bin");
#define SDMA0_POWER_CNTL__ON_OFF_CONDITION_HOLD_TIME_MASK 0x000000F8L
#define SDMA0_POWER_CNTL__ON_OFF_STATUS_DURATION_TIME_MASK 0xFC000000L
@@ -619,7 +620,10 @@
chip_name = "arcturus";
break;
case CHIP_RENOIR:
- chip_name = "renoir";
+ if (adev->apu_flags & AMD_APU_IS_RENOIR)
+ chip_name = "renoir";
+ else
+ chip_name = "green_sardine";
break;
default:
BUG();
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index afcccc6..f57c5f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1195,8 +1195,7 @@
adev->pg_flags = AMD_PG_SUPPORT_SDMA |
AMD_PG_SUPPORT_MMHUB |
- AMD_PG_SUPPORT_VCN |
- AMD_PG_SUPPORT_VCN_DPG;
+ AMD_PG_SUPPORT_VCN;
} else {
adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
AMD_CG_SUPPORT_GFX_MGLS |
@@ -1243,7 +1242,15 @@
break;
case CHIP_RENOIR:
adev->asic_funcs = &soc15_asic_funcs;
- adev->apu_flags |= AMD_APU_IS_RENOIR;
+ if (adev->pdev->device == 0x1636)
+ adev->apu_flags |= AMD_APU_IS_RENOIR;
+ else
+ adev->apu_flags |= AMD_APU_IS_GREEN_SARDINE;
+
+ if (adev->apu_flags & AMD_APU_IS_RENOIR)
+ adev->external_rev_id = adev->rev_id + 0x91;
+ else
+ adev->external_rev_id = adev->rev_id + 0xa1;
adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
AMD_CG_SUPPORT_GFX_MGLS |
AMD_CG_SUPPORT_GFX_3D_CGCG |
@@ -1268,7 +1275,6 @@
AMD_PG_SUPPORT_VCN |
AMD_PG_SUPPORT_JPEG |
AMD_PG_SUPPORT_VCN_DPG;
- adev->external_rev_id = adev->rev_id + 0x91;
break;
default:
/* FIXME: not supported yet */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 5e2254b..3de5e14 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -798,10 +798,10 @@
}
pcrat_image = kvmalloc(crat_table->length, GFP_KERNEL);
- memcpy(pcrat_image, crat_table, crat_table->length);
if (!pcrat_image)
return -ENOMEM;
+ memcpy(pcrat_image, crat_table, crat_table->length);
*crat_image = pcrat_image;
*size = crat_table->length;
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index f24abf4..60dfdd4 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -42,6 +42,7 @@
config DEBUG_KERNEL_DC
bool "Enable kgdb break in DC"
depends on DRM_AMD_DC
+ depends on KGDB
help
Choose this option if you want to hit kdgb_break in assert.
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index e2b23486..0e71180 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -100,6 +100,8 @@
#define FIRMWARE_NAVY_FLOUNDER_DMUB "amdgpu/navy_flounder_dmcub.bin"
MODULE_FIRMWARE(FIRMWARE_NAVY_FLOUNDER_DMUB);
#endif
+#define FIRMWARE_GREEN_SARDINE_DMUB "amdgpu/green_sardine_dmcub.bin"
+MODULE_FIRMWARE(FIRMWARE_GREEN_SARDINE_DMUB);
#define FIRMWARE_RAVEN_DMCU "amdgpu/raven_dmcu.bin"
MODULE_FIRMWARE(FIRMWARE_RAVEN_DMCU);
@@ -583,7 +585,7 @@
{
struct drm_device *dev = connector->dev;
struct amdgpu_device *adev = drm_to_adev(dev);
- struct dm_comressor_info *compressor = &adev->dm.compressor;
+ struct dm_compressor_info *compressor = &adev->dm.compressor;
struct amdgpu_dm_connector *aconn = to_amdgpu_dm_connector(connector);
struct drm_display_mode *mode;
unsigned long max_size = 0;
@@ -973,6 +975,8 @@
case CHIP_RAVEN:
case CHIP_RENOIR:
init_data.flags.gpu_vm_support = true;
+ if (ASICREV_IS_GREEN_SARDINE(adev->external_rev_id))
+ init_data.flags.disable_dmcu = true;
break;
default:
break;
@@ -1267,6 +1271,8 @@
case CHIP_RENOIR:
dmub_asic = DMUB_ASIC_DCN21;
fw_name_dmub = FIRMWARE_RENOIR_DMUB;
+ if (ASICREV_IS_GREEN_SARDINE(adev->external_rev_id))
+ fw_name_dmub = FIRMWARE_GREEN_SARDINE_DMUB;
break;
#if defined(CONFIG_DRM_AMD_DC_DCN3_0)
case CHIP_SIENNA_CICHLID:
@@ -7500,7 +7506,6 @@
bool mode_set_reset_required = false;
drm_atomic_helper_update_legacy_modeset_state(dev, state);
- drm_atomic_helper_calc_timestamping_constants(state);
dm_state = dm_atomic_get_new_state(state);
if (dm_state && dm_state->context) {
@@ -7527,6 +7532,8 @@
}
}
+ drm_atomic_helper_calc_timestamping_constants(state);
+
/* update changed items */
for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 34f6369..a8a0e8c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -86,7 +86,7 @@
* @bo_ptr: Pointer to the buffer object
* @gpu_addr: MMIO gpu addr
*/
-struct dm_comressor_info {
+struct dm_compressor_info {
void *cpu_addr;
struct amdgpu_bo *bo_ptr;
uint64_t gpu_addr;
@@ -148,7 +148,7 @@
* @soc_bounding_box: SOC bounding box values provided by gpu_info FW
* @cached_state: Caches device atomic state for suspend/resume
* @cached_dc_state: Cached state of content streams
- * @compressor: Frame buffer compression buffer. See &struct dm_comressor_info
+ * @compressor: Frame buffer compression buffer. See &struct dm_compressor_info
* @force_timing_sync: set via debugfs. When set, indicates that all connected
* displays will be forced to synchronize.
*/
@@ -324,7 +324,7 @@
struct drm_atomic_state *cached_state;
struct dc_state *cached_dc_state;
- struct dm_comressor_info compressor;
+ struct dm_compressor_info compressor;
const struct firmware *fw_dmcu;
uint32_t dmcu_fw_version;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
index efb909e..857f156 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
@@ -166,6 +166,11 @@
rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
break;
}
+
+ if (ASICREV_IS_GREEN_SARDINE(asic_id.hw_internal_rev)) {
+ rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
+ break;
+ }
if (ASICREV_IS_RAVEN2(asic_id.hw_internal_rev)) {
rv2_clk_mgr_construct(ctx, clk_mgr, pp_smu);
break;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 1eb29c3..45ad05f 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1571,8 +1571,8 @@
struct dc_state *dc_create_state(struct dc *dc)
{
- struct dc_state *context = kzalloc(sizeof(struct dc_state),
- GFP_KERNEL);
+ struct dc_state *context = kvzalloc(sizeof(struct dc_state),
+ GFP_KERNEL);
if (!context)
return NULL;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index e430148..59d48cf 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -120,6 +120,8 @@
dc_version = DCN_VERSION_1_01;
if (ASICREV_IS_RENOIR(asic_id.hw_internal_rev))
dc_version = DCN_VERSION_2_1;
+ if (ASICREV_IS_GREEN_SARDINE(asic_id.hw_internal_rev))
+ dc_version = DCN_VERSION_2_1;
break;
#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index 9cc65dc..49ae5ff 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -1149,7 +1149,8 @@
static const struct clock_source_funcs dcn3_clk_src_funcs = {
.cs_power_down = dce110_clock_source_power_down,
.program_pix_clk = dcn3_program_pix_clk,
- .get_pix_clk_dividers = dcn3_get_pix_clk_dividers
+ .get_pix_clk_dividers = dcn3_get_pix_clk_dividers,
+ .get_pixel_clk_frequency_100hz = get_pixel_clk_frequency_100hz
};
#endif
/*****************************************/
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
index 24fb39a..2455d21 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
@@ -2105,12 +2105,12 @@
if (split[i]) {
if (odm) {
- if (split[i] == 4 && old_pipe->next_odm_pipe->next_odm_pipe)
+ if (split[i] == 4 && old_pipe->next_odm_pipe && old_pipe->next_odm_pipe->next_odm_pipe)
old_index = old_pipe->next_odm_pipe->next_odm_pipe->pipe_idx;
else if (old_pipe->next_odm_pipe)
old_index = old_pipe->next_odm_pipe->pipe_idx;
} else {
- if (split[i] == 4 && old_pipe->bottom_pipe->bottom_pipe &&
+ if (split[i] == 4 && old_pipe->bottom_pipe && old_pipe->bottom_pipe->bottom_pipe &&
old_pipe->bottom_pipe->bottom_pipe->plane_state == old_pipe->plane_state)
old_index = old_pipe->bottom_pipe->bottom_pipe->pipe_idx;
else if (old_pipe->bottom_pipe &&
@@ -2150,10 +2150,12 @@
goto validate_fail;
newly_split[pipe_4to1->pipe_idx] = true;
- if (odm && old_pipe->next_odm_pipe->next_odm_pipe->next_odm_pipe)
+ if (odm && old_pipe->next_odm_pipe && old_pipe->next_odm_pipe->next_odm_pipe
+ && old_pipe->next_odm_pipe->next_odm_pipe->next_odm_pipe)
old_index = old_pipe->next_odm_pipe->next_odm_pipe->next_odm_pipe->pipe_idx;
- else if (!odm && old_pipe->bottom_pipe->bottom_pipe->bottom_pipe &&
- old_pipe->bottom_pipe->bottom_pipe->bottom_pipe->plane_state == old_pipe->plane_state)
+ else if (!odm && old_pipe->bottom_pipe && old_pipe->bottom_pipe->bottom_pipe &&
+ old_pipe->bottom_pipe->bottom_pipe->bottom_pipe &&
+ old_pipe->bottom_pipe->bottom_pipe->bottom_pipe->plane_state == old_pipe->plane_state)
old_index = old_pipe->bottom_pipe->bottom_pipe->bottom_pipe->pipe_idx;
else
old_index = -1;
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn30/hw_factory_dcn30.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn30/hw_factory_dcn30.c
index 3be2c90..2158369 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn30/hw_factory_dcn30.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn30/hw_factory_dcn30.c
@@ -117,6 +117,12 @@
ddc_data_regs_dcn2(4),
ddc_data_regs_dcn2(5),
ddc_data_regs_dcn2(6),
+ {
+ DDC_GPIO_VGA_REG_LIST(DATA),
+ .ddc_setup = 0,
+ .phy_aux_cntl = 0,
+ .dc_gpio_aux_ctrl_5 = 0
+ }
};
static const struct ddc_registers ddc_clk_regs_dcn[] = {
@@ -126,6 +132,12 @@
ddc_clk_regs_dcn2(4),
ddc_clk_regs_dcn2(5),
ddc_clk_regs_dcn2(6),
+ {
+ DDC_GPIO_VGA_REG_LIST(CLK),
+ .ddc_setup = 0,
+ .phy_aux_cntl = 0,
+ .dc_gpio_aux_ctrl_5 = 0
+ }
};
static const struct ddc_sh_mask ddc_shift[] = {
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c b/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c
index f67c183..dac427b 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c
@@ -63,13 +63,13 @@
enum gpio_mode mode)
{
if (gpio->pin) {
- ASSERT_CRITICAL(false);
+ BREAK_TO_DEBUGGER();
return GPIO_RESULT_ALREADY_OPENED;
}
// No action if allocation failed during gpio construct
if (!gpio->hw_container.ddc) {
- ASSERT_CRITICAL(false);
+ BREAK_TO_DEBUGGER();
return GPIO_RESULT_NON_SPECIFIC_ERROR;
}
gpio->mode = mode;
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
index 2a1fea5..3f1e7a1 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
@@ -299,8 +299,8 @@
pflip_int_entry(1),
pflip_int_entry(2),
pflip_int_entry(3),
- [DC_IRQ_SOURCE_PFLIP5] = dummy_irq_entry(),
- [DC_IRQ_SOURCE_PFLIP6] = dummy_irq_entry(),
+ pflip_int_entry(4),
+ pflip_int_entry(5),
[DC_IRQ_SOURCE_PFLIP_UNDERLAY0] = dummy_irq_entry(),
gpio_pad_int_entry(0),
gpio_pad_int_entry(1),
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c b/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c
index 49689f7..0effbb2 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c
@@ -306,8 +306,8 @@
pflip_int_entry(1),
pflip_int_entry(2),
pflip_int_entry(3),
- [DC_IRQ_SOURCE_PFLIP5] = dummy_irq_entry(),
- [DC_IRQ_SOURCE_PFLIP6] = dummy_irq_entry(),
+ pflip_int_entry(4),
+ pflip_int_entry(5),
[DC_IRQ_SOURCE_PFLIP_UNDERLAY0] = dummy_irq_entry(),
gpio_pad_int_entry(0),
gpio_pad_int_entry(1),
diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h
index 330acaa..95cb569 100644
--- a/drivers/gpu/drm/amd/display/dc/os_types.h
+++ b/drivers/gpu/drm/amd/display/dc/os_types.h
@@ -94,36 +94,27 @@
* general debug capabilities
*
*/
-#if defined(CONFIG_HAVE_KGDB) || defined(CONFIG_KGDB)
-#define ASSERT_CRITICAL(expr) do { \
- if (WARN_ON(!(expr))) { \
- kgdb_breakpoint(); \
- } \
-} while (0)
+#ifdef CONFIG_DEBUG_KERNEL_DC
+#define dc_breakpoint() kgdb_breakpoint()
#else
-#define ASSERT_CRITICAL(expr) do { \
- if (WARN_ON(!(expr))) { \
- ; \
- } \
-} while (0)
+#define dc_breakpoint() do {} while (0)
#endif
-#if defined(CONFIG_DEBUG_KERNEL_DC)
-#define ASSERT(expr) ASSERT_CRITICAL(expr)
+#define ASSERT_CRITICAL(expr) do { \
+ if (WARN_ON(!(expr))) \
+ dc_breakpoint(); \
+ } while (0)
-#else
-#define ASSERT(expr) WARN_ON_ONCE(!(expr))
-#endif
+#define ASSERT(expr) do { \
+ if (WARN_ON_ONCE(!(expr))) \
+ dc_breakpoint(); \
+ } while (0)
-#if defined(CONFIG_DEBUG_KERNEL_DC) && (defined(CONFIG_HAVE_KGDB) || defined(CONFIG_KGDB))
#define BREAK_TO_DEBUGGER() \
do { \
DRM_DEBUG_DRIVER("%s():%d\n", __func__, __LINE__); \
- kgdb_breakpoint(); \
+ dc_breakpoint(); \
} while (0)
-#else
-#define BREAK_TO_DEBUGGER() DRM_DEBUG_DRIVER("%s():%d\n", __func__, __LINE__)
-#endif
#define DC_ERR(...) do { \
dm_error(__VA_ARGS__); \
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index b267987..ffcb059 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -205,6 +205,10 @@
#if defined(CONFIG_DRM_AMD_DC_DCN3_0)
#define ASICREV_IS_SIENNA_CICHLID_P(eChipRev) ((eChipRev >= NV_SIENNA_CICHLID_P_A0))
#endif
+#define GREEN_SARDINE_A0 0xA1
+#ifndef ASICREV_IS_GREEN_SARDINE
+#define ASICREV_IS_GREEN_SARDINE(eChipRev) ((eChipRev >= GREEN_SARDINE_A0) && (eChipRev < 0xFF))
+#endif
/*
* ASIC chip ID
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 10dc481..06c1aab 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -45,6 +45,7 @@
AMD_APU_IS_RAVEN2 = 0x00000002UL,
AMD_APU_IS_PICASSO = 0x00000004UL,
AMD_APU_IS_RENOIR = 0x00000008UL,
+ AMD_APU_IS_GREEN_SARDINE = 0x00000010UL,
};
/**
diff --git a/drivers/gpu/drm/amd/pm/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/inc/hwmgr.h
index 3898a95..518796a2 100644
--- a/drivers/gpu/drm/amd/pm/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/inc/hwmgr.h
@@ -229,6 +229,7 @@
bool (*is_hw_avfs_present)(struct pp_hwmgr *hwmgr);
int (*update_dpm_settings)(struct pp_hwmgr *hwmgr, void *profile_setting);
int (*smc_table_manager)(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw); /*rw: true for read, false for write */
+ int (*stop_smc)(struct pp_hwmgr *hwmgr);
};
struct pp_hwmgr_func {
diff --git a/drivers/gpu/drm/amd/pm/inc/smumgr.h b/drivers/gpu/drm/amd/pm/inc/smumgr.h
index ad100b5..5f46f1a 100644
--- a/drivers/gpu/drm/amd/pm/inc/smumgr.h
+++ b/drivers/gpu/drm/amd/pm/inc/smumgr.h
@@ -113,4 +113,6 @@
extern int smum_smc_table_manager(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw);
+extern int smum_stop_smc(struct pp_hwmgr *hwmgr);
+
#endif
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c
index 3be4011..45f6088 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c
@@ -142,12 +142,12 @@
{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK, BACO_CNTL__BACO_BCLK_OFF__SHIFT, 0, 0x00 },
{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK, BACO_CNTL__BACO_POWER_OFF__SHIFT, 0, 0x00 },
{ CMD_DELAY_MS, 0, 0, 0, 20, 0 },
- { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x20 },
+ { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x200 },
{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, BACO_CNTL__BACO_ISO_DIS__SHIFT, 0, 0x01 },
- { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c },
+ { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c00 },
{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, BACO_CNTL__BACO_ANA_ISO_DIS__SHIFT, 0, 0x01 },
{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_RESET_EN_MASK, BACO_CNTL__BACO_RESET_EN__SHIFT, 0, 0x00 },
- { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x10 },
+ { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x100 },
{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_EN_MASK, BACO_CNTL__BACO_EN__SHIFT, 0, 0x00 },
{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_MODE_MASK, 0, 0xffffffff, 0x00 }
};
@@ -155,6 +155,7 @@
static const struct baco_cmd_entry clean_baco_tbl[] =
{
{ CMD_WRITE, mmBIOS_SCRATCH_6, 0, 0, 0, 0 },
+ { CMD_WRITE, mmBIOS_SCRATCH_7, 0, 0, 0, 0 },
{ CMD_WRITE, mmCP_PFP_UCODE_ADDR, 0, 0, 0, 0 }
};
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index 1e8919b..3562914 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -1541,6 +1541,10 @@
PP_ASSERT_WITH_CODE((tmp_result == 0),
"Failed to reset to default!", result = tmp_result);
+ tmp_result = smum_stop_smc(hwmgr);
+ PP_ASSERT_WITH_CODE((tmp_result == 0),
+ "Failed to stop smc!", result = tmp_result);
+
tmp_result = smu7_force_switch_to_arbf0(hwmgr);
PP_ASSERT_WITH_CODE((tmp_result == 0),
"Failed to force to switch arbf0!", result = tmp_result);
@@ -1585,18 +1589,24 @@
data->current_profile_setting.sclk_down_hyst = 100;
data->current_profile_setting.sclk_activity = SMU7_SCLK_TARGETACTIVITY_DFLT;
data->current_profile_setting.bupdate_mclk = 1;
- if (adev->gmc.vram_width == 256) {
- data->current_profile_setting.mclk_up_hyst = 10;
- data->current_profile_setting.mclk_down_hyst = 60;
- data->current_profile_setting.mclk_activity = 25;
- } else if (adev->gmc.vram_width == 128) {
- data->current_profile_setting.mclk_up_hyst = 5;
- data->current_profile_setting.mclk_down_hyst = 16;
- data->current_profile_setting.mclk_activity = 20;
- } else if (adev->gmc.vram_width == 64) {
- data->current_profile_setting.mclk_up_hyst = 3;
- data->current_profile_setting.mclk_down_hyst = 16;
- data->current_profile_setting.mclk_activity = 20;
+ if (hwmgr->chip_id >= CHIP_POLARIS10) {
+ if (adev->gmc.vram_width == 256) {
+ data->current_profile_setting.mclk_up_hyst = 10;
+ data->current_profile_setting.mclk_down_hyst = 60;
+ data->current_profile_setting.mclk_activity = 25;
+ } else if (adev->gmc.vram_width == 128) {
+ data->current_profile_setting.mclk_up_hyst = 5;
+ data->current_profile_setting.mclk_down_hyst = 16;
+ data->current_profile_setting.mclk_activity = 20;
+ } else if (adev->gmc.vram_width == 64) {
+ data->current_profile_setting.mclk_up_hyst = 3;
+ data->current_profile_setting.mclk_down_hyst = 16;
+ data->current_profile_setting.mclk_activity = 20;
+ }
+ } else {
+ data->current_profile_setting.mclk_up_hyst = 0;
+ data->current_profile_setting.mclk_down_hyst = 100;
+ data->current_profile_setting.mclk_activity = SMU7_MCLK_TARGETACTIVITY_DFLT;
}
hwmgr->workload_mask = 1 << hwmgr->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D];
hwmgr->power_profile_mode = PP_SMC_POWER_PROFILE_FULLSCREEN3D;
diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c
index e4d1f3d..329bf4d 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c
@@ -2726,10 +2726,7 @@
static bool ci_is_dpm_running(struct pp_hwmgr *hwmgr)
{
- return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device,
- CGS_IND_REG__SMC, FEATURE_STATUS,
- VOLTAGE_CONTROLLER_ON))
- ? true : false;
+ return ci_is_smc_ram_running(hwmgr);
}
static int ci_smu_init(struct pp_hwmgr *hwmgr)
@@ -2939,6 +2936,29 @@
return 0;
}
+static void ci_reset_smc(struct pp_hwmgr *hwmgr)
+{
+ PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+ SMC_SYSCON_RESET_CNTL,
+ rst_reg, 1);
+}
+
+
+static void ci_stop_smc_clock(struct pp_hwmgr *hwmgr)
+{
+ PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+ SMC_SYSCON_CLOCK_CNTL_0,
+ ck_disable, 1);
+}
+
+static int ci_stop_smc(struct pp_hwmgr *hwmgr)
+{
+ ci_reset_smc(hwmgr);
+ ci_stop_smc_clock(hwmgr);
+
+ return 0;
+}
+
const struct pp_smumgr_func ci_smu_funcs = {
.name = "ci_smu",
.smu_init = ci_smu_init,
@@ -2964,4 +2984,5 @@
.is_dpm_running = ci_is_dpm_running,
.update_dpm_settings = ci_update_dpm_settings,
.update_smc_table = ci_update_smc_table,
+ .stop_smc = ci_stop_smc,
};
diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c
index b6fb480..b6921db 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c
@@ -245,3 +245,11 @@
return -EINVAL;
}
+
+int smum_stop_smc(struct pp_hwmgr *hwmgr)
+{
+ if (hwmgr->smumgr_funcs->stop_smc)
+ return hwmgr->smumgr_funcs->stop_smc(hwmgr);
+
+ return 0;
+}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index fc4f95f..b1e5ec0 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1029,17 +1029,6 @@
return ret;
}
- /*
- * Set initialized values (get from vbios) to dpm tables context such as
- * gfxclk, memclk, dcefclk, and etc. And enable the DPM feature for each
- * type of clks.
- */
- ret = smu_set_default_dpm_table(smu);
- if (ret) {
- dev_err(adev->dev, "Failed to setup default dpm clock tables!\n");
- return ret;
- }
-
ret = smu_notify_display_change(smu);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index 8d8081c6..ef1a62e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -1361,14 +1361,9 @@
if (!speed)
return -EINVAL;
- switch (smu_v11_0_get_fan_control_mode(smu)) {
- case AMD_FAN_CTRL_AUTO:
- return navi10_get_smu_metrics_data(smu,
- METRICS_CURR_FANSPEED,
- speed);
- default:
- return smu_v11_0_get_fan_speed_rpm(smu, speed);
- }
+ return navi10_get_smu_metrics_data(smu,
+ METRICS_CURR_FANSPEED,
+ speed);
}
static int navi10_get_fan_parameters(struct smu_context *smu)
@@ -2534,29 +2529,6 @@
.functionality = navi10_i2c_func,
};
-static int navi10_i2c_control_init(struct smu_context *smu, struct i2c_adapter *control)
-{
- struct amdgpu_device *adev = to_amdgpu_device(control);
- int res;
-
- control->owner = THIS_MODULE;
- control->class = I2C_CLASS_SPD;
- control->dev.parent = &adev->pdev->dev;
- control->algo = &navi10_i2c_algo;
- snprintf(control->name, sizeof(control->name), "AMDGPU SMU");
-
- res = i2c_add_adapter(control);
- if (res)
- DRM_ERROR("Failed to register hw i2c, err: %d\n", res);
-
- return res;
-}
-
-static void navi10_i2c_control_fini(struct smu_context *smu, struct i2c_adapter *control)
-{
- i2c_del_adapter(control);
-}
-
static ssize_t navi10_get_gpu_metrics(struct smu_context *smu,
void **table)
{
@@ -2687,8 +2659,6 @@
.set_default_dpm_table = navi10_set_default_dpm_table,
.dpm_set_vcn_enable = navi10_dpm_set_vcn_enable,
.dpm_set_jpeg_enable = navi10_dpm_set_jpeg_enable,
- .i2c_init = navi10_i2c_control_init,
- .i2c_fini = navi10_i2c_control_fini,
.print_clk_levels = navi10_print_clk_levels,
.force_clk_levels = navi10_force_clk_levels,
.populate_umd_state_clk = navi10_populate_umd_state_clk,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index 685a8a3..895d89b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -1177,14 +1177,9 @@
if (!speed)
return -EINVAL;
- switch (smu_v11_0_get_fan_control_mode(smu)) {
- case AMD_FAN_CTRL_AUTO:
- return sienna_cichlid_get_smu_metrics_data(smu,
- METRICS_CURR_FANSPEED,
- speed);
- default:
- return smu_v11_0_get_fan_speed_rpm(smu, speed);
- }
+ return sienna_cichlid_get_smu_metrics_data(smu,
+ METRICS_CURR_FANSPEED,
+ speed);
}
static int sienna_cichlid_get_fan_parameters(struct smu_context *smu)
diff --git a/drivers/gpu/drm/bridge/cadence/Kconfig b/drivers/gpu/drm/bridge/cadence/Kconfig
index 511d67b..ef8c230 100644
--- a/drivers/gpu/drm/bridge/cadence/Kconfig
+++ b/drivers/gpu/drm/bridge/cadence/Kconfig
@@ -13,7 +13,7 @@
if DRM_CDNS_MHDP8546
config DRM_CDNS_MHDP8546_J721E
- depends on ARCH_K3_J721E_SOC || COMPILE_TEST
+ depends on ARCH_K3 || COMPILE_TEST
bool "J721E Cadence DPI/DP wrapper support"
default y
help
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
index 748df1c..0c79a9b 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
@@ -2327,12 +2327,6 @@
{
enum drm_connector_status result;
- mutex_lock(&hdmi->mutex);
- hdmi->force = DRM_FORCE_UNSPECIFIED;
- dw_hdmi_update_power(hdmi);
- dw_hdmi_update_phy_mask(hdmi);
- mutex_unlock(&hdmi->mutex);
-
result = hdmi->phy.ops->read_hpd(hdmi, hdmi->phy.data);
mutex_lock(&hdmi->mutex);
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 90807a6..deeed73 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -374,6 +374,10 @@
* drm_dp_downstream_is_type() - is the downstream facing port of certain type?
* @dpcd: DisplayPort configuration data
* @port_cap: port capabilities
+ * @type: port type to be checked. Can be:
+ * %DP_DS_PORT_TYPE_DP, %DP_DS_PORT_TYPE_VGA, %DP_DS_PORT_TYPE_DVI,
+ * %DP_DS_PORT_TYPE_HDMI, %DP_DS_PORT_TYPE_NON_EDID,
+ * %DP_DS_PORT_TYPE_DP_DUALMODE or %DP_DS_PORT_TYPE_WIRELESS.
*
* Caveat: Only works with DPCD 1.1+ port caps.
*
@@ -870,6 +874,7 @@
/**
* drm_dp_downstream_mode() - return a mode for downstream facing port
+ * @dev: DRM device
* @dpcd: DisplayPort configuration data
* @port_cap: port capabilities
*
@@ -1028,7 +1033,8 @@
/**
* drm_dp_subconnector_type() - get DP branch device type
- *
+ * @dpcd: DisplayPort configuration data
+ * @port_cap: port capabilities
*/
enum drm_mode_subconnector
drm_dp_subconnector_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
@@ -1079,6 +1085,10 @@
/**
* drm_mode_set_dp_subconnector_property - set subconnector for DP connector
+ * @connector: connector to set property on
+ * @status: connector status
+ * @dpcd: DisplayPort configuration data
+ * @port_cap: port capabilities
*
* Called by a driver on every detect event.
*/
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index a82f37d..631125b 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -3741,7 +3741,7 @@
/**
* drm_display_mode_from_cea_vic() - return a mode for CEA VIC
* @dev: DRM device
- * @vic: CEA VIC of the mode
+ * @video_code: CEA VIC of the mode
*
* Creates a new mode matching the specified CEA VIC.
*
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 19d7386..69c2c07 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -1085,6 +1085,8 @@
*/
drm_gem_object_get(obj);
+ vma->vm_private_data = obj;
+
if (obj->funcs && obj->funcs->mmap) {
ret = obj->funcs->mmap(obj, vma);
if (ret) {
@@ -1107,8 +1109,6 @@
vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
}
- vma->vm_private_data = obj;
-
return 0;
}
EXPORT_SYMBOL(drm_gem_mmap_obj);
diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index d77c9f8..e00616d 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -593,8 +593,13 @@
/* Remove the fake offset */
vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node);
- if (obj->import_attach)
+ if (obj->import_attach) {
+ /* Drop the reference drm_gem_mmap_obj() acquired.*/
+ drm_gem_object_put(obj);
+ vma->vm_private_data = NULL;
+
return dma_buf_mmap(obj->dma_buf, vma, 0);
+ }
shmem = to_drm_gem_shmem_obj(obj);
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index 50cad0e..375c79e 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -140,7 +140,7 @@
unsigned int c = 0;
if (pl_flag & DRM_GEM_VRAM_PL_FLAG_TOPDOWN)
- pl_flag = TTM_PL_FLAG_TOPDOWN;
+ invariant_flags = TTM_PL_FLAG_TOPDOWN;
gbo->placement.placement = gbo->placements;
gbo->placement.busy_placement = gbo->placements;
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index d6808f6..9f955f2 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -794,6 +794,7 @@
/**
* drm_prime_pages_to_sg - converts a page array into an sg list
+ * @dev: DRM device
* @pages: pointer to the array of page pointers to convert
* @nr_pages: length of the page vector
*
diff --git a/drivers/gpu/drm/gma500/psb_irq.c b/drivers/gpu/drm/gma500/psb_irq.c
index 15eb377..361e3a0c 100644
--- a/drivers/gpu/drm/gma500/psb_irq.c
+++ b/drivers/gpu/drm/gma500/psb_irq.c
@@ -347,6 +347,7 @@
{
struct drm_psb_private *dev_priv = dev->dev_private;
unsigned long irqflags;
+ unsigned int i;
spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags);
@@ -359,20 +360,12 @@
PSB_WVDC32(dev_priv->vdc_irq_mask, PSB_INT_ENABLE_R);
PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM);
- if (dev->vblank[0].enabled)
- psb_enable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
- else
- psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
-
- if (dev->vblank[1].enabled)
- psb_enable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
- else
- psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
-
- if (dev->vblank[2].enabled)
- psb_enable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
- else
- psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
+ for (i = 0; i < dev->num_crtcs; ++i) {
+ if (dev->vblank[i].enabled)
+ psb_enable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE);
+ else
+ psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE);
+ }
if (dev_priv->ops->hotplug_enable)
dev_priv->ops->hotplug_enable(dev, true);
@@ -385,6 +378,7 @@
{
struct drm_psb_private *dev_priv = dev->dev_private;
unsigned long irqflags;
+ unsigned int i;
spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags);
@@ -393,14 +387,10 @@
PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM);
- if (dev->vblank[0].enabled)
- psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
-
- if (dev->vblank[1].enabled)
- psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
-
- if (dev->vblank[2].enabled)
- psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
+ for (i = 0; i < dev->num_crtcs; ++i) {
+ if (dev->vblank[i].enabled)
+ psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE);
+ }
dev_priv->vdc_irq_mask &= _PSB_IRQ_SGX_FLAG |
_PSB_IRQ_MSVDX_FLAG |
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 829b2a4..99e6825 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -10636,6 +10636,10 @@
val & PLANE_CTL_FLIP_HORIZONTAL)
plane_config->rotation |= DRM_MODE_REFLECT_X;
+ /* 90/270 degree rotation would require extra work */
+ if (drm_rotation_90_or_270(plane_config->rotation))
+ goto error;
+
base = intel_de_read(dev_priv, PLANE_SURF(pipe, plane_id)) & 0xfffff000;
plane_config->base = base;
@@ -12874,10 +12878,11 @@
case 10 ... 11:
bpp = 10 * 3;
break;
- case 12:
+ case 12 ... 16:
bpp = 12 * 3;
break;
default:
+ MISSING_CASE(conn_state->max_bpc);
return -EINVAL;
}
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 8a9d0bd..40e9cb2 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -1754,7 +1754,7 @@
return;
intel_connector = to_intel_connector(connector);
- dig_port = enc_to_dig_port(intel_attached_encoder(intel_connector));
+ dig_port = enc_to_dig_port(to_intel_encoder(new_state->best_encoder));
if (dev_priv->psr.dp != &dig_port->dp)
return;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index 7c90a63..fcce690 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -509,21 +509,6 @@
return -ENOENT;
/*
- * Already in the desired write domain? Nothing for us to do!
- *
- * We apply a little bit of cunning here to catch a broader set of
- * no-ops. If obj->write_domain is set, we must be in the same
- * obj->read_domains, and only that domain. Therefore, if that
- * obj->write_domain matches the request read_domains, we are
- * already in the same read/write domain and can skip the operation,
- * without having to further check the requested write_domain.
- */
- if (READ_ONCE(obj->write_domain) == read_domains) {
- err = 0;
- goto out;
- }
-
- /*
* Try to flush the object off the GPU without holding the lock.
* We will repeat the flush holding the lock in the normal manner
* to catch cases where we are gazumped.
@@ -560,6 +545,19 @@
if (err)
goto out;
+ /*
+ * Already in the desired write domain? Nothing for us to do!
+ *
+ * We apply a little bit of cunning here to catch a broader set of
+ * no-ops. If obj->write_domain is set, we must be in the same
+ * obj->read_domains, and only that domain. Therefore, if that
+ * obj->write_domain matches the request read_domains, we are
+ * already in the same read/write domain and can skip the operation,
+ * without having to further check the requested write_domain.
+ */
+ if (READ_ONCE(obj->write_domain) == read_domains)
+ goto out_unpin;
+
err = i915_gem_object_lock_interruptible(obj, NULL);
if (err)
goto out_unpin;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index b5c1555..d6711ca 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -56,6 +56,8 @@
void (*truncate)(struct drm_i915_gem_object *obj);
void (*writeback)(struct drm_i915_gem_object *obj);
+ int (*pread)(struct drm_i915_gem_object *obj,
+ const struct drm_i915_gem_pread *arg);
int (*pwrite)(struct drm_i915_gem_object *obj,
const struct drm_i915_gem_pwrite *arg);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
index 28147aa..3a4dfe2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
@@ -134,6 +134,58 @@
vaddr, dma);
}
+static int
+phys_pwrite(struct drm_i915_gem_object *obj,
+ const struct drm_i915_gem_pwrite *args)
+{
+ void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset;
+ char __user *user_data = u64_to_user_ptr(args->data_ptr);
+ int err;
+
+ err = i915_gem_object_wait(obj,
+ I915_WAIT_INTERRUPTIBLE |
+ I915_WAIT_ALL,
+ MAX_SCHEDULE_TIMEOUT);
+ if (err)
+ return err;
+
+ /*
+ * We manually control the domain here and pretend that it
+ * remains coherent i.e. in the GTT domain, like shmem_pwrite.
+ */
+ i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU);
+
+ if (copy_from_user(vaddr, user_data, args->size))
+ return -EFAULT;
+
+ drm_clflush_virt_range(vaddr, args->size);
+ intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt);
+
+ i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU);
+ return 0;
+}
+
+static int
+phys_pread(struct drm_i915_gem_object *obj,
+ const struct drm_i915_gem_pread *args)
+{
+ void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset;
+ char __user *user_data = u64_to_user_ptr(args->data_ptr);
+ int err;
+
+ err = i915_gem_object_wait(obj,
+ I915_WAIT_INTERRUPTIBLE,
+ MAX_SCHEDULE_TIMEOUT);
+ if (err)
+ return err;
+
+ drm_clflush_virt_range(vaddr, args->size);
+ if (copy_to_user(user_data, vaddr, args->size))
+ return -EFAULT;
+
+ return 0;
+}
+
static void phys_release(struct drm_i915_gem_object *obj)
{
fput(obj->base.filp);
@@ -144,6 +196,9 @@
.get_pages = i915_gem_object_get_pages_phys,
.put_pages = i915_gem_object_put_pages_phys,
+ .pread = phys_pread,
+ .pwrite = phys_pwrite,
+
.release = phys_release,
};
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 7c3a101..760fefd 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -245,22 +245,14 @@
}
static inline u32 *
-__gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1)
+__gen8_emit_write_rcs(u32 *cs, u32 value, u32 offset, u32 flags0, u32 flags1)
{
- /* We're using qword write, offset should be aligned to 8 bytes. */
- GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
-
- /* w/a for post sync ops following a GPGPU operation we
- * need a prior CS_STALL, which is emitted by the flush
- * following the batch.
- */
*cs++ = GFX_OP_PIPE_CONTROL(6) | flags0;
- *cs++ = flags1 | PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_GLOBAL_GTT_IVB;
- *cs++ = gtt_offset;
+ *cs++ = flags1 | PIPE_CONTROL_QW_WRITE;
+ *cs++ = offset;
*cs++ = 0;
*cs++ = value;
- /* We're thrashing one dword of HWS. */
- *cs++ = 0;
+ *cs++ = 0; /* We're thrashing one extra dword. */
return cs;
}
@@ -268,13 +260,38 @@
static inline u32*
gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
{
- return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, 0, flags);
+ /* We're using qword write, offset should be aligned to 8 bytes. */
+ GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
+
+ return __gen8_emit_write_rcs(cs,
+ value,
+ gtt_offset,
+ 0,
+ flags | PIPE_CONTROL_GLOBAL_GTT_IVB);
}
static inline u32*
gen12_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1)
{
- return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, flags0, flags1);
+ /* We're using qword write, offset should be aligned to 8 bytes. */
+ GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
+
+ return __gen8_emit_write_rcs(cs,
+ value,
+ gtt_offset,
+ flags0,
+ flags1 | PIPE_CONTROL_GLOBAL_GTT_IVB);
+}
+
+static inline u32 *
+__gen8_emit_flush_dw(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
+{
+ *cs++ = (MI_FLUSH_DW + 1) | flags;
+ *cs++ = gtt_offset;
+ *cs++ = 0;
+ *cs++ = value;
+
+ return cs;
}
static inline u32 *
@@ -285,12 +302,10 @@
/* Offset should be aligned to 8 bytes for both (QW/DW) write types */
GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
- *cs++ = (MI_FLUSH_DW + 1) | MI_FLUSH_DW_OP_STOREDW | flags;
- *cs++ = gtt_offset | MI_FLUSH_DW_USE_GTT;
- *cs++ = 0;
- *cs++ = value;
-
- return cs;
+ return __gen8_emit_flush_dw(cs,
+ value,
+ gtt_offset | MI_FLUSH_DW_USE_GTT,
+ flags | MI_FLUSH_DW_OP_STOREDW);
}
static inline void __intel_engine_reset(struct intel_engine_cs *engine,
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 5bfb5f7..efdeb7b 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -371,7 +371,8 @@
* instances.
*/
if ((INTEL_GEN(i915) >= 11 &&
- engine->gt->info.vdbox_sfc_access & engine->mask) ||
+ (engine->gt->info.vdbox_sfc_access &
+ BIT(engine->instance))) ||
(INTEL_GEN(i915) >= 9 && engine->instance == 0))
engine->uabi_capabilities |=
I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index a32aabc..9bb16bdf9 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -3547,6 +3547,19 @@
.destroy = execlists_context_destroy,
};
+static u32 hwsp_offset(const struct i915_request *rq)
+{
+ const struct intel_timeline_cacheline *cl;
+
+ /* Before the request is executed, the timeline/cachline is fixed */
+
+ cl = rcu_dereference_protected(rq->hwsp_cacheline, 1);
+ if (cl)
+ return cl->ggtt_offset;
+
+ return rcu_dereference_protected(rq->timeline, 1)->hwsp_offset;
+}
+
static int gen8_emit_init_breadcrumb(struct i915_request *rq)
{
u32 *cs;
@@ -3569,7 +3582,7 @@
*cs++ = MI_NOOP;
*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
- *cs++ = i915_request_timeline(rq)->hwsp_offset;
+ *cs++ = hwsp_offset(rq);
*cs++ = 0;
*cs++ = rq->fence.seqno - 1;
@@ -4886,11 +4899,9 @@
return gen8_emit_wa_tail(request, cs);
}
-static u32 *emit_xcs_breadcrumb(struct i915_request *request, u32 *cs)
+static u32 *emit_xcs_breadcrumb(struct i915_request *rq, u32 *cs)
{
- u32 addr = i915_request_active_timeline(request)->hwsp_offset;
-
- return gen8_emit_ggtt_write(cs, request->fence.seqno, addr, 0);
+ return gen8_emit_ggtt_write(cs, rq->fence.seqno, hwsp_offset(rq), 0);
}
static u32 *gen8_emit_fini_breadcrumb(struct i915_request *rq, u32 *cs)
@@ -4909,7 +4920,7 @@
/* XXX flush+write+CS_STALL all in one upsets gem_concurrent_blt:kbl */
cs = gen8_emit_ggtt_write_rcs(cs,
request->fence.seqno,
- i915_request_active_timeline(request)->hwsp_offset,
+ hwsp_offset(request),
PIPE_CONTROL_FLUSH_ENABLE |
PIPE_CONTROL_CS_STALL);
@@ -4921,7 +4932,7 @@
{
cs = gen8_emit_ggtt_write_rcs(cs,
request->fence.seqno,
- i915_request_active_timeline(request)->hwsp_offset,
+ hwsp_offset(request),
PIPE_CONTROL_CS_STALL |
PIPE_CONTROL_TILE_CACHE_FLUSH |
PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
@@ -4983,7 +4994,9 @@
static u32 *gen12_emit_fini_breadcrumb(struct i915_request *rq, u32 *cs)
{
- return gen12_emit_fini_breadcrumb_tail(rq, emit_xcs_breadcrumb(rq, cs));
+ /* XXX Stalling flush before seqno write; post-sync not */
+ cs = emit_xcs_breadcrumb(rq, __gen8_emit_flush_dw(cs, 0, 0, 0));
+ return gen12_emit_fini_breadcrumb_tail(rq, cs);
}
static u32 *
@@ -4991,7 +5004,7 @@
{
cs = gen12_emit_ggtt_write_rcs(cs,
request->fence.seqno,
- i915_request_active_timeline(request)->hwsp_offset,
+ hwsp_offset(request),
PIPE_CONTROL0_HDC_PIPELINE_FLUSH,
PIPE_CONTROL_CS_STALL |
PIPE_CONTROL_TILE_CACHE_FLUSH |
@@ -5444,6 +5457,7 @@
__execlists_context_fini(&ve->context);
intel_context_fini(&ve->context);
+ intel_breadcrumbs_free(ve->base.breadcrumbs);
intel_engine_free_request_pool(&ve->base);
kfree(ve->bonds);
diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c
index b8f56e6..313e51e 100644
--- a/drivers/gpu/drm/i915/gt/intel_mocs.c
+++ b/drivers/gpu/drm/i915/gt/intel_mocs.c
@@ -243,8 +243,9 @@
* only, __init_mocs_table() take care to program unused index with
* this entry.
*/
- MOCS_ENTRY(1, LE_3_WB | LE_TC_1_LLC | LE_LRUM(3),
- L3_3_WB),
+ MOCS_ENTRY(I915_MOCS_PTE,
+ LE_0_PAGETABLE | LE_TC_0_PAGETABLE,
+ L3_1_UC),
GEN11_MOCS_ENTRIES,
/* Implicitly enable L1 - HDC:L1 + L3 + LLC */
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c
index ab675d3..d7b8e445 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6.c
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.c
@@ -56,9 +56,12 @@
static void gen11_rc6_enable(struct intel_rc6 *rc6)
{
- struct intel_uncore *uncore = rc6_to_uncore(rc6);
+ struct intel_gt *gt = rc6_to_gt(rc6);
+ struct intel_uncore *uncore = gt->uncore;
struct intel_engine_cs *engine;
enum intel_engine_id id;
+ u32 pg_enable;
+ int i;
/* 2b: Program RC6 thresholds.*/
set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85);
@@ -102,10 +105,19 @@
GEN6_RC_CTL_RC6_ENABLE |
GEN6_RC_CTL_EI_MODE(1);
- set(uncore, GEN9_PG_ENABLE,
- GEN9_RENDER_PG_ENABLE |
- GEN9_MEDIA_PG_ENABLE |
- GEN11_MEDIA_SAMPLER_PG_ENABLE);
+ pg_enable =
+ GEN9_RENDER_PG_ENABLE |
+ GEN9_MEDIA_PG_ENABLE |
+ GEN11_MEDIA_SAMPLER_PG_ENABLE;
+
+ if (INTEL_GEN(gt->i915) >= 12) {
+ for (i = 0; i < I915_MAX_VCS; i++)
+ if (HAS_ENGINE(gt, _VCS(i)))
+ pg_enable |= (VDN_HCP_POWERGATE_ENABLE(i) |
+ VDN_MFX_POWERGATE_ENABLE(i));
+ }
+
+ set(uncore, GEN9_PG_ENABLE, pg_enable);
}
static void gen9_rc6_enable(struct intel_rc6 *rc6)
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index a2f74ce..7ea94d2 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -188,10 +188,14 @@
return cl;
}
-static void cacheline_acquire(struct intel_timeline_cacheline *cl)
+static void cacheline_acquire(struct intel_timeline_cacheline *cl,
+ u32 ggtt_offset)
{
- if (cl)
- i915_active_acquire(&cl->active);
+ if (!cl)
+ return;
+
+ cl->ggtt_offset = ggtt_offset;
+ i915_active_acquire(&cl->active);
}
static void cacheline_release(struct intel_timeline_cacheline *cl)
@@ -340,7 +344,7 @@
GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n",
tl->fence_context, tl->hwsp_offset);
- cacheline_acquire(tl->hwsp_cacheline);
+ cacheline_acquire(tl->hwsp_cacheline, tl->hwsp_offset);
if (atomic_fetch_inc(&tl->pin_count)) {
cacheline_release(tl->hwsp_cacheline);
__i915_vma_unpin(tl->hwsp_ggtt);
@@ -515,7 +519,7 @@
GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n",
tl->fence_context, tl->hwsp_offset);
- cacheline_acquire(cl);
+ cacheline_acquire(cl, tl->hwsp_offset);
tl->hwsp_cacheline = cl;
*seqno = timeline_advance(tl);
@@ -573,9 +577,7 @@
if (err)
goto out;
- *hwsp = i915_ggtt_offset(cl->hwsp->vma) +
- ptr_unmask_bits(cl->vaddr, CACHELINE_BITS) * CACHELINE_BYTES;
-
+ *hwsp = cl->ggtt_offset;
out:
i915_active_release(&cl->active);
return err;
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline_types.h b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
index 02181c5..4474f48 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
@@ -94,6 +94,8 @@
struct intel_timeline_hwsp *hwsp;
void *vaddr;
+ u32 ggtt_offset;
+
struct rcu_head rcu;
};
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 6c580d0..4a3bde7 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -131,8 +131,10 @@
return;
}
- if (wal->list)
+ if (wal->list) {
memcpy(list, wal->list, sizeof(*wa) * wal->count);
+ kfree(wal->list);
+ }
wal->list = list;
}
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index 7ba16dd..d7898e8 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -164,7 +164,7 @@
/* let the virtual display supports DP1.2 */
static u8 dpcd_fix_data[DPCD_HEADER_SIZE] = {
- 0x12, 0x014, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
+ 0x12, 0x014, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
};
static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 3be37e6..eb342a7 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1489,7 +1489,8 @@
const struct intel_engine_cs *engine =
intel_gvt_render_mmio_to_engine(vgpu->gvt, offset);
- if (!intel_gvt_ggtt_validate_range(vgpu, value, I915_GTT_PAGE_SIZE)) {
+ if (value != 0 &&
+ !intel_gvt_ggtt_validate_range(vgpu, value, I915_GTT_PAGE_SIZE)) {
gvt_vgpu_err("write invalid HWSP address, reg:0x%x, value:0x%x\n",
offset, value);
return -EINVAL;
@@ -1650,6 +1651,34 @@
return 0;
}
+/**
+ * FixMe:
+ * If guest fills non-priv batch buffer on ApolloLake/Broxton as Mesa i965 did:
+ * 717e7539124d (i965: Use a WC map and memcpy for the batch instead of pwrite.)
+ * Due to the missing flush of bb filled by VM vCPU, host GPU hangs on executing
+ * these MI_BATCH_BUFFER.
+ * Temporarily workaround this by setting SNOOP bit for PAT3 used by PPGTT
+ * PML4 PTE: PAT(0) PCD(1) PWT(1).
+ * The performance is still expected to be low, will need further improvement.
+ */
+static int bxt_ppat_low_write(struct intel_vgpu *vgpu, unsigned int offset,
+ void *p_data, unsigned int bytes)
+{
+ u64 pat =
+ GEN8_PPAT(0, CHV_PPAT_SNOOP) |
+ GEN8_PPAT(1, 0) |
+ GEN8_PPAT(2, 0) |
+ GEN8_PPAT(3, CHV_PPAT_SNOOP) |
+ GEN8_PPAT(4, CHV_PPAT_SNOOP) |
+ GEN8_PPAT(5, CHV_PPAT_SNOOP) |
+ GEN8_PPAT(6, CHV_PPAT_SNOOP) |
+ GEN8_PPAT(7, CHV_PPAT_SNOOP);
+
+ vgpu_vreg(vgpu, offset) = lower_32_bits(pat);
+
+ return 0;
+}
+
static int guc_status_read(struct intel_vgpu *vgpu,
unsigned int offset, void *p_data,
unsigned int bytes)
@@ -2812,7 +2841,7 @@
MMIO_DH(GEN6_PCODE_MAILBOX, D_BDW_PLUS, NULL, mailbox_write);
- MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS);
+ MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS & ~D_BXT);
MMIO_D(GEN8_PRIVATE_PAT_HI, D_BDW_PLUS);
MMIO_D(GAMTARBMODE, D_BDW_PLUS);
@@ -3139,7 +3168,7 @@
NULL, NULL);
MMIO_DFH(GAMT_CHKN_BIT_REG, D_KBL | D_CFL, F_CMD_ACCESS, NULL, NULL);
- MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS);
+ MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS & ~D_BXT);
return 0;
}
@@ -3313,9 +3342,21 @@
MMIO_D(GEN8_PUSHBUS_SHIFT, D_BXT);
MMIO_D(GEN6_GFXPAUSE, D_BXT);
MMIO_DFH(GEN8_L3SQCREG1, D_BXT, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(GEN8_L3CNTLREG, D_BXT, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(_MMIO(0x20D8), D_BXT, F_CMD_ACCESS, NULL, NULL);
+ MMIO_F(GEN8_RING_CS_GPR(RENDER_RING_BASE, 0), 0x40, F_CMD_ACCESS,
+ 0, 0, D_BXT, NULL, NULL);
+ MMIO_F(GEN8_RING_CS_GPR(GEN6_BSD_RING_BASE, 0), 0x40, F_CMD_ACCESS,
+ 0, 0, D_BXT, NULL, NULL);
+ MMIO_F(GEN8_RING_CS_GPR(BLT_RING_BASE, 0), 0x40, F_CMD_ACCESS,
+ 0, 0, D_BXT, NULL, NULL);
+ MMIO_F(GEN8_RING_CS_GPR(VEBOX_RING_BASE, 0), 0x40, F_CMD_ACCESS,
+ 0, 0, D_BXT, NULL, NULL);
MMIO_DFH(GEN9_CTX_PREEMPT_REG, D_BXT, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DH(GEN8_PRIVATE_PAT_LO, D_BXT, NULL, bxt_ppat_low_write);
+
return 0;
}
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index ad8a9df..778eb8c 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -829,8 +829,10 @@
/* Take a module reference as mdev core doesn't take
* a reference for vendor driver.
*/
- if (!try_module_get(THIS_MODULE))
+ if (!try_module_get(THIS_MODULE)) {
+ ret = -ENODEV;
goto undo_group;
+ }
ret = kvmgt_guest_init(mdev);
if (ret)
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 1570eb8..aed2ef6 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -1277,7 +1277,7 @@
i915_context_ppgtt_root_restore(s, i915_vm_to_ppgtt(s->shadow[0]->vm));
for_each_engine(engine, vgpu->gvt->gt, id)
- intel_context_unpin(s->shadow[id]);
+ intel_context_put(s->shadow[id]);
kmem_cache_destroy(s->workloads);
}
@@ -1369,11 +1369,6 @@
ce->ring = __intel_context_ring_size(ring_size);
}
- ret = intel_context_pin(ce);
- intel_context_put(ce);
- if (ret)
- goto out_shadow_ctx;
-
s->shadow[i] = ce;
}
@@ -1405,7 +1400,6 @@
if (IS_ERR(s->shadow[i]))
break;
- intel_context_unpin(s->shadow[i]);
intel_context_put(s->shadow[i]);
}
i915_vm_put(&ppgtt->vm);
@@ -1479,6 +1473,7 @@
{
struct intel_vgpu_submission *s = &workload->vgpu->submission;
+ intel_context_unpin(s->shadow[workload->engine->id]);
release_shadow_batch_buffer(workload);
release_shadow_wa_ctx(&workload->wa_ctx);
@@ -1724,6 +1719,12 @@
return ERR_PTR(ret);
}
+ ret = intel_context_pin(s->shadow[engine->id]);
+ if (ret) {
+ intel_vgpu_destroy_workload(workload);
+ return ERR_PTR(ret);
+ }
+
return workload;
}
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index f6d7e33..399582a 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -439,7 +439,8 @@
if (IS_BROADWELL(dev_priv))
ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B);
- else
+ /* FixMe: Re-enable APL/BXT once vfio_edid enabled */
+ else if (!IS_BROXTON(dev_priv))
ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D);
if (ret)
goto out_clean_sched_policy;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index bb0c129..5827669 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -180,30 +180,6 @@
}
static int
-i915_gem_phys_pwrite(struct drm_i915_gem_object *obj,
- struct drm_i915_gem_pwrite *args,
- struct drm_file *file)
-{
- void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset;
- char __user *user_data = u64_to_user_ptr(args->data_ptr);
-
- /*
- * We manually control the domain here and pretend that it
- * remains coherent i.e. in the GTT domain, like shmem_pwrite.
- */
- i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU);
-
- if (copy_from_user(vaddr, user_data, args->size))
- return -EFAULT;
-
- drm_clflush_virt_range(vaddr, args->size);
- intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt);
-
- i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU);
- return 0;
-}
-
-static int
i915_gem_create(struct drm_file *file,
struct intel_memory_region *mr,
u64 *size_p,
@@ -527,6 +503,12 @@
trace_i915_gem_object_pread(obj, args->offset, args->size);
+ ret = -ENODEV;
+ if (obj->ops->pread)
+ ret = obj->ops->pread(obj, args);
+ if (ret != -ENODEV)
+ goto out;
+
ret = i915_gem_object_wait(obj,
I915_WAIT_INTERRUPTIBLE,
MAX_SCHEDULE_TIMEOUT);
@@ -866,8 +848,6 @@
if (ret == -EFAULT || ret == -ENOSPC) {
if (i915_gem_object_has_struct_page(obj))
ret = i915_gem_shmem_pwrite(obj, args);
- else
- ret = i915_gem_phys_pwrite(obj, args, file);
}
i915_gem_object_unpin_pages(obj);
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 366ddfc..fb5e30d 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -389,6 +389,7 @@
GEN5_FEATURES,
PLATFORM(INTEL_IRONLAKE),
.is_mobile = 1,
+ .has_rps = true,
.display.has_fbc = 1,
};
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index d805d4d..664f3bf 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -8971,10 +8971,6 @@
#define GEN9_PWRGT_MEDIA_STATUS_MASK (1 << 0)
#define GEN9_PWRGT_RENDER_STATUS_MASK (1 << 1)
-#define POWERGATE_ENABLE _MMIO(0xa210)
-#define VDN_HCP_POWERGATE_ENABLE(n) BIT(((n) * 2) + 3)
-#define VDN_MFX_POWERGATE_ENABLE(n) BIT(((n) * 2) + 4)
-
#define GTFIFODBG _MMIO(0x120000)
#define GT_FIFO_SBDEDICATE_FREE_ENTRY_CHV (0x1f << 20)
#define GT_FIFO_FREE_ENTRIES_CHV (0x7f << 13)
@@ -9114,9 +9110,11 @@
#define GEN9_MEDIA_PG_IDLE_HYSTERESIS _MMIO(0xA0C4)
#define GEN9_RENDER_PG_IDLE_HYSTERESIS _MMIO(0xA0C8)
#define GEN9_PG_ENABLE _MMIO(0xA210)
-#define GEN9_RENDER_PG_ENABLE REG_BIT(0)
-#define GEN9_MEDIA_PG_ENABLE REG_BIT(1)
-#define GEN11_MEDIA_SAMPLER_PG_ENABLE REG_BIT(2)
+#define GEN9_RENDER_PG_ENABLE REG_BIT(0)
+#define GEN9_MEDIA_PG_ENABLE REG_BIT(1)
+#define GEN11_MEDIA_SAMPLER_PG_ENABLE REG_BIT(2)
+#define VDN_HCP_POWERGATE_ENABLE(n) REG_BIT(3 + 2 * (n))
+#define VDN_MFX_POWERGATE_ENABLE(n) REG_BIT(4 + 2 * (n))
#define GEN8_PUSHBUS_CONTROL _MMIO(0xA248)
#define GEN8_PUSHBUS_ENABLE _MMIO(0xA250)
#define GEN8_PUSHBUS_SHIFT _MMIO(0xA25C)
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index ffb5287..caa9b04 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -314,8 +314,10 @@
{
struct i915_vma_work *vw = container_of(work, typeof(*vw), base);
- if (vw->pinned)
+ if (vw->pinned) {
__i915_gem_object_unpin_pages(vw->pinned);
+ i915_gem_object_put(vw->pinned);
+ }
i915_vm_free_pt_stash(vw->vm, &vw->stash);
i915_vm_put(vw->vm);
@@ -431,7 +433,7 @@
if (vma->obj) {
__i915_gem_object_pin_pages(vma->obj);
- work->pinned = vma->obj;
+ work->pinned = i915_gem_object_get(vma->obj);
}
} else {
vma->ops->bind_vma(vma->vm, NULL, vma, cache_level, bind_flags);
diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
index 6b5e9d8..180e107 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/intel_memory_region.c
@@ -87,7 +87,7 @@
min_order = ilog2(size) - ilog2(mem->mm.chunk_size);
}
- if (size > BIT(mem->mm.max_order) * mem->mm.chunk_size)
+ if (size > mem->mm.size)
return -E2BIG;
n_pages = size >> ilog2(mem->mm.chunk_size);
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 34e0d22..cfb8067 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -7118,23 +7118,10 @@
static void tgl_init_clock_gating(struct drm_i915_private *dev_priv)
{
- u32 vd_pg_enable = 0;
- unsigned int i;
-
/* Wa_1409120013:tgl */
I915_WRITE(ILK_DPFC_CHICKEN,
ILK_DPFC_CHICKEN_COMP_DUMMY_PIXEL);
- /* This is not a WA. Enable VD HCP & MFX_ENC powergate */
- for (i = 0; i < I915_MAX_VCS; i++) {
- if (HAS_ENGINE(&dev_priv->gt, _VCS(i)))
- vd_pg_enable |= VDN_HCP_POWERGATE_ENABLE(i) |
- VDN_MFX_POWERGATE_ENABLE(i);
- }
-
- I915_WRITE(POWERGATE_ENABLE,
- I915_READ(POWERGATE_ENABLE) | vd_pg_enable);
-
/* Wa_1409825376:tgl (pre-prod)*/
if (IS_TGL_DISP_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_B1))
I915_WRITE(GEN9_CLKGATE_DIS_3, I915_READ(GEN9_CLKGATE_DIS_3) |
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 64bbb82..e424a6d 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -2293,8 +2293,10 @@
struct intel_context *ce;
ce = intel_context_create(engine);
- if (IS_ERR(ce))
+ if (IS_ERR(ce)) {
+ err = PTR_ERR(ce);
goto out;
+ }
err = intel_context_pin(ce);
if (err) {
@@ -2467,8 +2469,10 @@
struct intel_context *ce;
ce = intel_context_create(engine);
- if (IS_ERR(ce))
+ if (IS_ERR(ce)) {
+ err = PTR_ERR(ce);
goto out;
+ }
err = intel_context_pin(ce);
if (err) {
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index 334b064..0aeba8e 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -261,6 +261,82 @@
return err;
}
+static int igt_mock_splintered_region(void *arg)
+{
+ struct intel_memory_region *mem = arg;
+ struct drm_i915_private *i915 = mem->i915;
+ struct drm_i915_gem_object *obj;
+ unsigned int expected_order;
+ LIST_HEAD(objects);
+ u64 size;
+ int err = 0;
+
+ /*
+ * Sanity check we can still allocate everything even if the
+ * mm.max_order != mm.size. i.e our starting address space size is not a
+ * power-of-two.
+ */
+
+ size = (SZ_4G - 1) & PAGE_MASK;
+ mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0);
+ if (IS_ERR(mem))
+ return PTR_ERR(mem);
+
+ if (mem->mm.size != size) {
+ pr_err("%s size mismatch(%llu != %llu)\n",
+ __func__, mem->mm.size, size);
+ err = -EINVAL;
+ goto out_put;
+ }
+
+ expected_order = get_order(rounddown_pow_of_two(size));
+ if (mem->mm.max_order != expected_order) {
+ pr_err("%s order mismatch(%u != %u)\n",
+ __func__, mem->mm.max_order, expected_order);
+ err = -EINVAL;
+ goto out_put;
+ }
+
+ obj = igt_object_create(mem, &objects, size, 0);
+ if (IS_ERR(obj)) {
+ err = PTR_ERR(obj);
+ goto out_close;
+ }
+
+ close_objects(mem, &objects);
+
+ /*
+ * While we should be able allocate everything without any flag
+ * restrictions, if we consider I915_BO_ALLOC_CONTIGUOUS then we are
+ * actually limited to the largest power-of-two for the region size i.e
+ * max_order, due to the inner workings of the buddy allocator. So make
+ * sure that does indeed hold true.
+ */
+
+ obj = igt_object_create(mem, &objects, size, I915_BO_ALLOC_CONTIGUOUS);
+ if (!IS_ERR(obj)) {
+ pr_err("%s too large contiguous allocation was not rejected\n",
+ __func__);
+ err = -EINVAL;
+ goto out_close;
+ }
+
+ obj = igt_object_create(mem, &objects, rounddown_pow_of_two(size),
+ I915_BO_ALLOC_CONTIGUOUS);
+ if (IS_ERR(obj)) {
+ pr_err("%s largest possible contiguous allocation failed\n",
+ __func__);
+ err = PTR_ERR(obj);
+ goto out_close;
+ }
+
+out_close:
+ close_objects(mem, &objects);
+out_put:
+ intel_memory_region_put(mem);
+ return err;
+}
+
static int igt_gpu_write_dw(struct intel_context *ce,
struct i915_vma *vma,
u32 dword,
@@ -771,6 +847,7 @@
static const struct i915_subtest tests[] = {
SUBTEST(igt_mock_fill),
SUBTEST(igt_mock_contiguous),
+ SUBTEST(igt_mock_splintered_region),
};
struct intel_memory_region *mem;
struct drm_i915_private *i915;
diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c
index 09660f5..979d96f 100644
--- a/drivers/gpu/drm/i915/selftests/mock_region.c
+++ b/drivers/gpu/drm/i915/selftests/mock_region.c
@@ -24,7 +24,7 @@
struct drm_i915_private *i915 = mem->i915;
struct drm_i915_gem_object *obj;
- if (size > BIT(mem->mm.max_order) * mem->mm.chunk_size)
+ if (size > mem->mm.size)
return ERR_PTR(-E2BIG);
obj = i915_gem_object_alloc();
diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c
index 71d84c7..d07b39b 100644
--- a/drivers/gpu/drm/imx/dw_hdmi-imx.c
+++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c
@@ -111,10 +111,6 @@
return 0;
}
-static void dw_hdmi_imx_encoder_disable(struct drm_encoder *encoder)
-{
-}
-
static void dw_hdmi_imx_encoder_enable(struct drm_encoder *encoder)
{
struct imx_hdmi *hdmi = enc_to_imx_hdmi(encoder);
@@ -140,7 +136,6 @@
static const struct drm_encoder_helper_funcs dw_hdmi_imx_encoder_helper_funcs = {
.enable = dw_hdmi_imx_encoder_enable,
- .disable = dw_hdmi_imx_encoder_disable,
.atomic_check = dw_hdmi_imx_atomic_check,
};
@@ -219,15 +214,9 @@
hdmi->dev = &pdev->dev;
encoder = &hdmi->encoder;
- encoder->possible_crtcs = drm_of_find_possible_crtcs(drm, dev->of_node);
- /*
- * If we failed to find the CRTC(s) which this encoder is
- * supposed to be connected to, it's because the CRTC has
- * not been registered yet. Defer probing, and hope that
- * the required CRTC is added later.
- */
- if (encoder->possible_crtcs == 0)
- return -EPROBE_DEFER;
+ ret = imx_drm_encoder_parse_of(drm, encoder, dev->of_node);
+ if (ret)
+ return ret;
ret = dw_hdmi_imx_parse_dt(hdmi);
if (ret < 0)
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 7d00c49..9bf5ad6 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -20,6 +20,7 @@
#include <drm/drm_fb_helper.h>
#include <drm/drm_gem_cma_helper.h>
#include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_managed.h>
#include <drm/drm_of.h>
#include <drm/drm_plane_helper.h>
#include <drm/drm_probe_helper.h>
@@ -212,7 +213,9 @@
drm->mode_config.allow_fb_modifiers = true;
drm->mode_config.normalize_zpos = true;
- drm_mode_config_init(drm);
+ ret = drmm_mode_config_init(drm);
+ if (ret)
+ return ret;
ret = drm_vblank_init(drm, MAX_CRTC);
if (ret)
@@ -251,7 +254,6 @@
drm_kms_helper_poll_fini(drm);
component_unbind_all(drm->dev, drm);
err_kms:
- drm_mode_config_cleanup(drm);
drm_dev_put(drm);
return ret;
@@ -267,11 +269,9 @@
component_unbind_all(drm->dev, drm);
- drm_mode_config_cleanup(drm);
+ drm_dev_put(drm);
dev_set_drvdata(dev, NULL);
-
- drm_dev_put(drm);
}
static const struct component_master_ops imx_drm_ops = {
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index af757d1..41e2978 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -62,7 +62,6 @@
struct i2c_adapter *ddc;
int chno;
void *edid;
- int edid_len;
struct drm_display_mode mode;
int mode_valid;
u32 bus_format;
@@ -536,15 +535,14 @@
}
if (!channel->ddc) {
+ int edid_len;
+
/* if no DDC available, fallback to hardcoded EDID */
dev_dbg(dev, "no ddc available\n");
- edidp = of_get_property(child, "edid",
- &channel->edid_len);
+ edidp = of_get_property(child, "edid", &edid_len);
if (edidp) {
- channel->edid = kmemdup(edidp,
- channel->edid_len,
- GFP_KERNEL);
+ channel->edid = kmemdup(edidp, edid_len, GFP_KERNEL);
} else if (!channel->panel) {
/* fallback to display-timings node */
ret = of_get_drm_display_mode(child,
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index 813bb61..2a8d2e3 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -13,7 +13,6 @@
#include <linux/platform_device.h>
#include <linux/regmap.h>
#include <linux/regulator/consumer.h>
-#include <linux/spinlock.h>
#include <linux/videodev2.h>
#include <video/imx-ipu-v3.h>
@@ -104,8 +103,6 @@
struct drm_connector connector;
struct drm_encoder encoder;
struct device *dev;
- spinlock_t lock; /* register lock */
- bool enabled;
int mode;
int di_hsync_pin;
int di_vsync_pin;
@@ -129,30 +126,10 @@
return container_of(e, struct imx_tve, encoder);
}
-static void tve_lock(void *__tve)
-__acquires(&tve->lock)
-{
- struct imx_tve *tve = __tve;
-
- spin_lock(&tve->lock);
-}
-
-static void tve_unlock(void *__tve)
-__releases(&tve->lock)
-{
- struct imx_tve *tve = __tve;
-
- spin_unlock(&tve->lock);
-}
-
static void tve_enable(struct imx_tve *tve)
{
- if (!tve->enabled) {
- tve->enabled = true;
- clk_prepare_enable(tve->clk);
- regmap_update_bits(tve->regmap, TVE_COM_CONF_REG,
- TVE_EN, TVE_EN);
- }
+ clk_prepare_enable(tve->clk);
+ regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, TVE_EN);
/* clear interrupt status register */
regmap_write(tve->regmap, TVE_STAT_REG, 0xffffffff);
@@ -169,11 +146,8 @@
static void tve_disable(struct imx_tve *tve)
{
- if (tve->enabled) {
- tve->enabled = false;
- regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, 0);
- clk_disable_unprepare(tve->clk);
- }
+ regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, 0);
+ clk_disable_unprepare(tve->clk);
}
static int tve_setup_tvout(struct imx_tve *tve)
@@ -500,8 +474,7 @@
.readable_reg = imx_tve_readable_reg,
- .lock = tve_lock,
- .unlock = tve_unlock,
+ .fast_io = true,
.max_register = 0xdc,
};
@@ -511,7 +484,7 @@
[TVE_MODE_VGA] = "vga",
};
-static const int of_get_tve_mode(struct device_node *np)
+static int of_get_tve_mode(struct device_node *np)
{
const char *bm;
int ret, i;
@@ -544,7 +517,6 @@
memset(tve, 0, sizeof(*tve));
tve->dev = dev;
- spin_lock_init(&tve->lock);
ddc_node = of_parse_phandle(np, "ddc-i2c-bus", 0);
if (ddc_node) {
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index 8232f51..2eb8df46 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -28,7 +28,6 @@
struct drm_bridge bridge;
struct device *dev;
void *edid;
- int edid_len;
u32 bus_format;
u32 bus_flags;
struct drm_display_mode mode;
@@ -41,11 +40,6 @@
return container_of(c, struct imx_parallel_display, connector);
}
-static inline struct imx_parallel_display *enc_to_imxpd(struct drm_encoder *e)
-{
- return container_of(e, struct imx_parallel_display, encoder);
-}
-
static inline struct imx_parallel_display *bridge_to_imxpd(struct drm_bridge *b)
{
return container_of(b, struct imx_parallel_display, bridge);
@@ -310,6 +304,7 @@
struct device_node *np = dev->of_node;
const u8 *edidp;
struct imx_parallel_display *imxpd;
+ int edid_len;
int ret;
u32 bus_format = 0;
const char *fmt;
@@ -323,9 +318,9 @@
if (ret && ret != -ENODEV)
return ret;
- edidp = of_get_property(np, "edid", &imxpd->edid_len);
+ edidp = of_get_property(np, "edid", &edid_len);
if (edidp)
- imxpd->edid = kmemdup(edidp, imxpd->edid_len, GFP_KERNEL);
+ imxpd->edid = devm_kmemdup(dev, edidp, edid_len, GFP_KERNEL);
ret = of_property_read_string(np, "interface-pix-fmt", &fmt);
if (!ret) {
@@ -349,17 +344,8 @@
return 0;
}
-static void imx_pd_unbind(struct device *dev, struct device *master,
- void *data)
-{
- struct imx_parallel_display *imxpd = dev_get_drvdata(dev);
-
- kfree(imxpd->edid);
-}
-
static const struct component_ops imx_pd_ops = {
.bind = imx_pd_bind,
- .unbind = imx_pd_unbind,
};
static int imx_pd_probe(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c
index c592957..92f8bd9 100644
--- a/drivers/gpu/drm/mcde/mcde_drv.c
+++ b/drivers/gpu/drm/mcde/mcde_drv.c
@@ -413,7 +413,13 @@
match);
if (ret) {
dev_err(dev, "failed to add component master\n");
- goto clk_disable;
+ /*
+ * The EPOD regulator is already disabled at this point so some
+ * special errorpath code is needed
+ */
+ clk_disable_unprepare(mcde->mcde_clk);
+ regulator_disable(mcde->vana);
+ return ret;
}
return 0;
diff --git a/drivers/gpu/drm/nouveau/dispnv50/core.h b/drivers/gpu/drm/nouveau/dispnv50/core.h
index 498622c..f750881 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/core.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/core.h
@@ -44,6 +44,7 @@
struct nv50_core **);
int core507d_init(struct nv50_core *);
void core507d_ntfy_init(struct nouveau_bo *, u32);
+int core507d_read_caps(struct nv50_disp *disp);
int core507d_caps_init(struct nouveau_drm *, struct nv50_disp *);
int core507d_ntfy_wait_done(struct nouveau_bo *, u32, struct nvif_device *);
int core507d_update(struct nv50_core *, u32 *, bool);
@@ -55,6 +56,7 @@
int core827d_new(struct nouveau_drm *, s32, struct nv50_core **);
int core907d_new(struct nouveau_drm *, s32, struct nv50_core **);
+int core907d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp);
extern const struct nv50_outp_func dac907d;
extern const struct nv50_outp_func sor907d;
diff --git a/drivers/gpu/drm/nouveau/dispnv50/core507d.c b/drivers/gpu/drm/nouveau/dispnv50/core507d.c
index 248edf6..e6f16a7 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/core507d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/core507d.c
@@ -78,19 +78,56 @@
}
int
-core507d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp)
+core507d_read_caps(struct nv50_disp *disp)
{
struct nvif_push *push = disp->core->chan.push;
int ret;
- if ((ret = PUSH_WAIT(push, 2)))
+ ret = PUSH_WAIT(push, 6);
+ if (ret)
return ret;
+ PUSH_MTHD(push, NV507D, SET_NOTIFIER_CONTROL,
+ NVDEF(NV507D, SET_NOTIFIER_CONTROL, MODE, WRITE) |
+ NVVAL(NV507D, SET_NOTIFIER_CONTROL, OFFSET, NV50_DISP_CORE_NTFY >> 2) |
+ NVDEF(NV507D, SET_NOTIFIER_CONTROL, NOTIFY, ENABLE));
+
PUSH_MTHD(push, NV507D, GET_CAPABILITIES, 0x00000000);
+
+ PUSH_MTHD(push, NV507D, SET_NOTIFIER_CONTROL,
+ NVDEF(NV507D, SET_NOTIFIER_CONTROL, NOTIFY, DISABLE));
+
return PUSH_KICK(push);
}
int
+core507d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp)
+{
+ struct nv50_core *core = disp->core;
+ struct nouveau_bo *bo = disp->sync;
+ s64 time;
+ int ret;
+
+ NVBO_WR32(bo, NV50_DISP_CORE_NTFY, NV_DISP_CORE_NOTIFIER_1, CAPABILITIES_1,
+ NVDEF(NV_DISP_CORE_NOTIFIER_1, CAPABILITIES_1, DONE, FALSE));
+
+ ret = core507d_read_caps(disp);
+ if (ret < 0)
+ return ret;
+
+ time = nvif_msec(core->chan.base.device, 2000ULL,
+ if (NVBO_TD32(bo, NV50_DISP_CORE_NTFY,
+ NV_DISP_CORE_NOTIFIER_1, CAPABILITIES_1, DONE, ==, TRUE))
+ break;
+ usleep_range(1, 2);
+ );
+ if (time < 0)
+ NV_ERROR(drm, "core caps notifier timeout\n");
+
+ return 0;
+}
+
+int
core507d_init(struct nv50_core *core)
{
struct nvif_push *push = core->chan.push;
diff --git a/drivers/gpu/drm/nouveau/dispnv50/core907d.c b/drivers/gpu/drm/nouveau/dispnv50/core907d.c
index b17c035..8564d4d 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/core907d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/core907d.c
@@ -22,11 +22,45 @@
#include "core.h"
#include "head.h"
+#include <nvif/push507c.h>
+#include <nvif/timer.h>
+
+#include <nvhw/class/cl907d.h>
+
+#include "nouveau_bo.h"
+
+int
+core907d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp)
+{
+ struct nv50_core *core = disp->core;
+ struct nouveau_bo *bo = disp->sync;
+ s64 time;
+ int ret;
+
+ NVBO_WR32(bo, NV50_DISP_CORE_NTFY, NV907D_CORE_NOTIFIER_3, CAPABILITIES_4,
+ NVDEF(NV907D_CORE_NOTIFIER_3, CAPABILITIES_4, DONE, FALSE));
+
+ ret = core507d_read_caps(disp);
+ if (ret < 0)
+ return ret;
+
+ time = nvif_msec(core->chan.base.device, 2000ULL,
+ if (NVBO_TD32(bo, NV50_DISP_CORE_NTFY,
+ NV907D_CORE_NOTIFIER_3, CAPABILITIES_4, DONE, ==, TRUE))
+ break;
+ usleep_range(1, 2);
+ );
+ if (time < 0)
+ NV_ERROR(drm, "core caps notifier timeout\n");
+
+ return 0;
+}
+
static const struct nv50_core_func
core907d = {
.init = core507d_init,
.ntfy_init = core507d_ntfy_init,
- .caps_init = core507d_caps_init,
+ .caps_init = core907d_caps_init,
.ntfy_wait_done = core507d_ntfy_wait_done,
.update = core507d_update,
.head = &head907d,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/core917d.c b/drivers/gpu/drm/nouveau/dispnv50/core917d.c
index 66846f3..1cd3a2a 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/core917d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/core917d.c
@@ -26,7 +26,7 @@
core917d = {
.init = core507d_init,
.ntfy_init = core507d_ntfy_init,
- .caps_init = core507d_caps_init,
+ .caps_init = core907d_caps_init,
.ntfy_wait_done = core507d_ntfy_wait_done,
.update = core507d_update,
.head = &head917d,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index b111fe2..36d6b60 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -455,7 +455,7 @@
* DAC
*****************************************************************************/
static void
-nv50_dac_disable(struct drm_encoder *encoder)
+nv50_dac_disable(struct drm_encoder *encoder, struct drm_atomic_state *state)
{
struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
struct nv50_core *core = nv50_disp(encoder->dev)->core;
@@ -467,7 +467,7 @@
}
static void
-nv50_dac_enable(struct drm_encoder *encoder)
+nv50_dac_enable(struct drm_encoder *encoder, struct drm_atomic_state *state)
{
struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
@@ -525,8 +525,8 @@
static const struct drm_encoder_helper_funcs
nv50_dac_help = {
.atomic_check = nv50_outp_atomic_check,
- .enable = nv50_dac_enable,
- .disable = nv50_dac_disable,
+ .atomic_enable = nv50_dac_enable,
+ .atomic_disable = nv50_dac_disable,
.detect = nv50_dac_detect
};
@@ -1055,7 +1055,7 @@
}
static void
-nv50_msto_enable(struct drm_encoder *encoder)
+nv50_msto_enable(struct drm_encoder *encoder, struct drm_atomic_state *state)
{
struct nv50_head *head = nv50_head(encoder->crtc);
struct nv50_head_atom *armh = nv50_head_atom(head->base.base.state);
@@ -1101,7 +1101,7 @@
}
static void
-nv50_msto_disable(struct drm_encoder *encoder)
+nv50_msto_disable(struct drm_encoder *encoder, struct drm_atomic_state *state)
{
struct nv50_msto *msto = nv50_msto(encoder);
struct nv50_mstc *mstc = msto->mstc;
@@ -1118,8 +1118,8 @@
static const struct drm_encoder_helper_funcs
nv50_msto_help = {
- .disable = nv50_msto_disable,
- .enable = nv50_msto_enable,
+ .atomic_disable = nv50_msto_disable,
+ .atomic_enable = nv50_msto_enable,
.atomic_check = nv50_msto_atomic_check,
};
@@ -1645,8 +1645,7 @@
}
static void
-nv50_sor_enable(struct drm_encoder *encoder,
- struct drm_atomic_state *state)
+nv50_sor_enable(struct drm_encoder *encoder, struct drm_atomic_state *state)
{
struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
@@ -1873,7 +1872,7 @@
}
static void
-nv50_pior_disable(struct drm_encoder *encoder)
+nv50_pior_disable(struct drm_encoder *encoder, struct drm_atomic_state *state)
{
struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
struct nv50_core *core = nv50_disp(encoder->dev)->core;
@@ -1885,7 +1884,7 @@
}
static void
-nv50_pior_enable(struct drm_encoder *encoder)
+nv50_pior_enable(struct drm_encoder *encoder, struct drm_atomic_state *state)
{
struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
@@ -1921,14 +1920,14 @@
}
core->func->pior->ctrl(core, nv_encoder->or, ctrl, asyh);
- nv_encoder->crtc = encoder->crtc;
+ nv_encoder->crtc = &nv_crtc->base;
}
static const struct drm_encoder_helper_funcs
nv50_pior_help = {
.atomic_check = nv50_pior_atomic_check,
- .enable = nv50_pior_enable,
- .disable = nv50_pior_disable,
+ .atomic_enable = nv50_pior_enable,
+ .atomic_disable = nv50_pior_disable,
};
static void
diff --git a/drivers/gpu/drm/nouveau/include/nvhw/class/cl507d.h b/drivers/gpu/drm/nouveau/include/nvhw/class/cl507d.h
index 2e444ba..6a463f3 100644
--- a/drivers/gpu/drm/nouveau/include/nvhw/class/cl507d.h
+++ b/drivers/gpu/drm/nouveau/include/nvhw/class/cl507d.h
@@ -32,7 +32,10 @@
#define NV_DISP_CORE_NOTIFIER_1_COMPLETION_0_DONE_TRUE 0x00000001
#define NV_DISP_CORE_NOTIFIER_1_COMPLETION_0_R0 15:1
#define NV_DISP_CORE_NOTIFIER_1_COMPLETION_0_TIMESTAMP 29:16
-
+#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1 0x00000001
+#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1_DONE 0:0
+#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1_DONE_FALSE 0x00000000
+#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1_DONE_TRUE 0x00000001
// class methods
#define NV507D_UPDATE (0x00000080)
diff --git a/drivers/gpu/drm/nouveau/include/nvhw/class/cl907d.h b/drivers/gpu/drm/nouveau/include/nvhw/class/cl907d.h
index 34bc3ea..79aff6f 100644
--- a/drivers/gpu/drm/nouveau/include/nvhw/class/cl907d.h
+++ b/drivers/gpu/drm/nouveau/include/nvhw/class/cl907d.h
@@ -24,6 +24,10 @@
#ifndef _cl907d_h_
#define _cl907d_h_
+#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4 0x00000004
+#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4_DONE 0:0
+#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4_DONE_FALSE 0x00000000
+#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4_DONE_TRUE 0x00000001
#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_CAP_SOR0_20 0x00000014
#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_CAP_SOR0_20_SINGLE_LVDS18 0:0
#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_CAP_SOR0_20_SINGLE_LVDS18_FALSE 0x00000000
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 2ee7564..56b335a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -350,14 +350,13 @@
if (domain & NOUVEAU_GEM_DOMAIN_VRAM) {
struct nvif_mmu *mmu = &drm->client.mmu;
- const u8 type = mmu->type[drm->ttm.type_vram].type;
pl[*n].mem_type = TTM_PL_VRAM;
pl[*n].flags = flags & ~TTM_PL_FLAG_CACHED;
/* Some BARs do not support being ioremapped WC */
if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA &&
- type & NVIF_MEM_UNCACHED)
+ mmu->type[drm->ttm.type_vram].type & NVIF_MEM_UNCACHED)
pl[*n].flags &= ~TTM_PL_FLAG_WC;
(*n)++;
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 49dd0cbc..8b4b3688 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -532,11 +532,13 @@
nouveau_connector_set_edid(struct nouveau_connector *nv_connector,
struct edid *edid)
{
- struct edid *old_edid = nv_connector->edid;
+ if (nv_connector->edid != edid) {
+ struct edid *old_edid = nv_connector->edid;
- drm_connector_update_edid_property(&nv_connector->base, edid);
- kfree(old_edid);
- nv_connector->edid = edid;
+ drm_connector_update_edid_property(&nv_connector->base, edid);
+ kfree(old_edid);
+ nv_connector->edid = edid;
+ }
}
static enum drm_connector_status
@@ -669,8 +671,10 @@
/* Try retrieving EDID via DDC */
if (!drm->vbios.fp_no_ddc) {
status = nouveau_connector_detect(connector, force);
- if (status == connector_status_connected)
+ if (status == connector_status_connected) {
+ edid = nv_connector->edid;
goto out;
+ }
}
/* On some laptops (Sony, i'm looking at you) there appears to
@@ -1023,29 +1027,6 @@
return 112000 * duallink_scale;
}
-enum drm_mode_status
-nouveau_conn_mode_clock_valid(const struct drm_display_mode *mode,
- const unsigned min_clock,
- const unsigned max_clock,
- unsigned int *clock_out)
-{
- unsigned int clock = mode->clock;
-
- if ((mode->flags & DRM_MODE_FLAG_3D_MASK) ==
- DRM_MODE_FLAG_3D_FRAME_PACKING)
- clock *= 2;
-
- if (clock < min_clock)
- return MODE_CLOCK_LOW;
- if (clock > max_clock)
- return MODE_CLOCK_HIGH;
-
- if (clock_out)
- *clock_out = clock;
-
- return MODE_OK;
-}
-
static enum drm_mode_status
nouveau_connector_mode_valid(struct drm_connector *connector,
struct drm_display_mode *mode)
@@ -1053,7 +1034,7 @@
struct nouveau_connector *nv_connector = nouveau_connector(connector);
struct nouveau_encoder *nv_encoder = nv_connector->detected_encoder;
struct drm_encoder *encoder = to_drm_encoder(nv_encoder);
- unsigned min_clock = 25000, max_clock = min_clock;
+ unsigned int min_clock = 25000, max_clock = min_clock, clock = mode->clock;
switch (nv_encoder->dcb->type) {
case DCB_OUTPUT_LVDS:
@@ -1082,8 +1063,15 @@
return MODE_BAD;
}
- return nouveau_conn_mode_clock_valid(mode, min_clock, max_clock,
- NULL);
+ if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING)
+ clock *= 2;
+
+ if (clock < min_clock)
+ return MODE_CLOCK_LOW;
+ if (clock > max_clock)
+ return MODE_CLOCK_HIGH;
+
+ return MODE_OK;
}
static struct drm_encoder *
diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c
index 7b640e0..040ed88 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dp.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dp.c
@@ -231,23 +231,30 @@
const struct drm_display_mode *mode,
unsigned *out_clock)
{
- const unsigned min_clock = 25000;
- unsigned max_clock, ds_clock, clock;
- enum drm_mode_status ret;
+ const unsigned int min_clock = 25000;
+ unsigned int max_rate, mode_rate, ds_max_dotclock, clock = mode->clock;
+ const u8 bpp = connector->display_info.bpc * 3;
if (mode->flags & DRM_MODE_FLAG_INTERLACE && !outp->caps.dp_interlace)
return MODE_NO_INTERLACE;
- max_clock = outp->dp.link_nr * outp->dp.link_bw;
- ds_clock = drm_dp_downstream_max_dotclock(outp->dp.dpcd,
- outp->dp.downstream_ports);
- if (ds_clock)
- max_clock = min(max_clock, ds_clock);
+ if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING)
+ clock *= 2;
- clock = mode->clock * (connector->display_info.bpc * 3) / 10;
- ret = nouveau_conn_mode_clock_valid(mode, min_clock, max_clock,
- &clock);
+ max_rate = outp->dp.link_nr * outp->dp.link_bw;
+ mode_rate = DIV_ROUND_UP(clock * bpp, 8);
+ if (mode_rate > max_rate)
+ return MODE_CLOCK_HIGH;
+
+ ds_max_dotclock = drm_dp_downstream_max_dotclock(outp->dp.dpcd, outp->dp.downstream_ports);
+ if (ds_max_dotclock && clock > ds_max_dotclock)
+ return MODE_CLOCK_HIGH;
+
+ if (clock < min_clock)
+ return MODE_CLOCK_LOW;
+
if (out_clock)
*out_clock = clock;
- return ret;
+
+ return MODE_OK;
}
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 89adadf..549bc67 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -190,7 +190,8 @@
* to the caller, instead of a normal nouveau_bo ttm reference. */
ret = drm_gem_object_init(drm->dev, &nvbo->bo.base, size);
if (ret) {
- nouveau_bo_ref(NULL, &nvbo);
+ drm_gem_object_release(&nvbo->bo.base);
+ kfree(nvbo);
return ret;
}
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index 2df1c04..4f69e4c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -105,11 +105,11 @@
struct nouveau_cli *cli = nouveau_cli(file_priv);
struct drm_nouveau_svm_bind *args = data;
unsigned target, cmd, priority;
- unsigned long addr, end, size;
+ unsigned long addr, end;
struct mm_struct *mm;
args->va_start &= PAGE_MASK;
- args->va_end &= PAGE_MASK;
+ args->va_end = ALIGN(args->va_end, PAGE_SIZE);
/* Sanity check arguments */
if (args->reserved0 || args->reserved1)
@@ -118,8 +118,6 @@
return -EINVAL;
if (args->va_start >= args->va_end)
return -EINVAL;
- if (!args->npages)
- return -EINVAL;
cmd = args->header >> NOUVEAU_SVM_BIND_COMMAND_SHIFT;
cmd &= NOUVEAU_SVM_BIND_COMMAND_MASK;
@@ -151,12 +149,6 @@
if (args->stride)
return -EINVAL;
- size = ((unsigned long)args->npages) << PAGE_SHIFT;
- if ((args->va_start + size) <= args->va_start)
- return -EINVAL;
- if ((args->va_start + size) > args->va_end)
- return -EINVAL;
-
/*
* Ok we are ask to do something sane, for now we only support migrate
* commands but we will add things like memory policy (what to do on
@@ -171,7 +163,7 @@
return -EINVAL;
}
- for (addr = args->va_start, end = args->va_start + size; addr < end;) {
+ for (addr = args->va_start, end = args->va_end; addr < end;) {
struct vm_area_struct *vma;
unsigned long next;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index dcb7067..7851bec 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -2924,17 +2924,34 @@
}
}
+/* returns true if the GPU is in the CPU native byte order */
static inline bool
nvkm_device_endianness(struct nvkm_device *device)
{
- u32 boot1 = nvkm_rd32(device, 0x000004) & 0x01000001;
#ifdef __BIG_ENDIAN
- if (!boot1)
- return false;
+ const bool big_endian = true;
#else
- if (boot1)
- return false;
+ const bool big_endian = false;
#endif
+
+ /* Read NV_PMC_BOOT_1, and assume non-functional endian switch if it
+ * doesn't contain the expected values.
+ */
+ u32 pmc_boot_1 = nvkm_rd32(device, 0x000004);
+ if (pmc_boot_1 && pmc_boot_1 != 0x01000001)
+ return !big_endian; /* Assume GPU is LE in this case. */
+
+ /* 0 means LE and 0x01000001 means BE GPU. Condition is true when
+ * GPU/CPU endianness don't match.
+ */
+ if (big_endian == !pmc_boot_1) {
+ nvkm_wr32(device, 0x000004, 0x01000001);
+ nvkm_rd32(device, 0x000000);
+ if (nvkm_rd32(device, 0x000004) != (big_endian ? 0x01000001 : 0x00000000))
+ return !big_endian; /* Assume GPU is LE on any unexpected read-back. */
+ }
+
+ /* CPU/GPU endianness should (hopefully) match. */
return true;
}
@@ -2987,14 +3004,10 @@
if (detect) {
/* switch mmio to cpu's native endianness */
if (!nvkm_device_endianness(device)) {
- nvkm_wr32(device, 0x000004, 0x01000001);
- nvkm_rd32(device, 0x000000);
- if (!nvkm_device_endianness(device)) {
- nvdev_error(device,
- "GPU not supported on big-endian\n");
- ret = -ENOSYS;
- goto done;
- }
+ nvdev_error(device,
+ "Couldn't switch GPU to CPUs endianess\n");
+ ret = -ENOSYS;
+ goto done;
}
boot0 = nvkm_rd32(device, 0x000000);
diff --git a/drivers/gpu/drm/panel/panel-mantix-mlaf057we51.c b/drivers/gpu/drm/panel/panel-mantix-mlaf057we51.c
index 3482e28..0c5f22e 100644
--- a/drivers/gpu/drm/panel/panel-mantix-mlaf057we51.c
+++ b/drivers/gpu/drm/panel/panel-mantix-mlaf057we51.c
@@ -26,7 +26,9 @@
struct mantix {
struct device *dev;
struct drm_panel panel;
+
struct gpio_desc *reset_gpio;
+ struct gpio_desc *tp_rstn_gpio;
struct regulator *avdd;
struct regulator *avee;
@@ -124,6 +126,10 @@
{
struct mantix *ctx = panel_to_mantix(panel);
+ gpiod_set_value_cansleep(ctx->tp_rstn_gpio, 1);
+ usleep_range(5000, 6000);
+ gpiod_set_value_cansleep(ctx->reset_gpio, 1);
+
regulator_disable(ctx->avee);
regulator_disable(ctx->avdd);
/* T11 */
@@ -165,13 +171,10 @@
return ret;
}
- /* T3+T5 */
- usleep_range(10000, 12000);
-
- gpiod_set_value_cansleep(ctx->reset_gpio, 1);
- usleep_range(5150, 7000);
-
+ /* T3 + T4 + time for voltage to become stable: */
+ usleep_range(6000, 7000);
gpiod_set_value_cansleep(ctx->reset_gpio, 0);
+ gpiod_set_value_cansleep(ctx->tp_rstn_gpio, 0);
/* T6 */
msleep(50);
@@ -204,7 +207,7 @@
if (!mode) {
dev_err(ctx->dev, "Failed to add mode %ux%u@%u\n",
default_mode.hdisplay, default_mode.vdisplay,
- drm_mode_vrefresh(mode));
+ drm_mode_vrefresh(&default_mode));
return -ENOMEM;
}
@@ -236,12 +239,18 @@
if (!ctx)
return -ENOMEM;
- ctx->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
+ ctx->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
if (IS_ERR(ctx->reset_gpio)) {
dev_err(dev, "cannot get reset gpio\n");
return PTR_ERR(ctx->reset_gpio);
}
+ ctx->tp_rstn_gpio = devm_gpiod_get(dev, "mantix,tp-rstn", GPIOD_OUT_HIGH);
+ if (IS_ERR(ctx->tp_rstn_gpio)) {
+ dev_err(dev, "cannot get tp-rstn gpio\n");
+ return PTR_ERR(ctx->tp_rstn_gpio);
+ }
+
mipi_dsi_set_drvdata(dsi, ctx);
ctx->dev = dev;
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index 37d4cb7..0fc0841 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -626,6 +626,7 @@
err_out1:
pm_runtime_disable(pfdev->dev);
panfrost_device_fini(pfdev);
+ pm_runtime_set_suspended(pfdev->dev);
err_out0:
drm_dev_put(ddev);
return err;
@@ -640,9 +641,9 @@
panfrost_gem_shrinker_cleanup(ddev);
pm_runtime_get_sync(pfdev->dev);
- panfrost_device_fini(pfdev);
- pm_runtime_put_sync_suspend(pfdev->dev);
pm_runtime_disable(pfdev->dev);
+ panfrost_device_fini(pfdev);
+ pm_runtime_set_suspended(pfdev->dev);
drm_dev_put(ddev);
return 0;
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c
index 1a6cea0..62d4d71 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
@@ -105,14 +105,12 @@
kref_put(&mapping->refcount, panfrost_gem_mapping_release);
}
-void panfrost_gem_teardown_mappings(struct panfrost_gem_object *bo)
+void panfrost_gem_teardown_mappings_locked(struct panfrost_gem_object *bo)
{
struct panfrost_gem_mapping *mapping;
- mutex_lock(&bo->mappings.lock);
list_for_each_entry(mapping, &bo->mappings.list, node)
panfrost_gem_teardown_mapping(mapping);
- mutex_unlock(&bo->mappings.lock);
}
int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv)
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h
index b3517ff..8088d5f 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.h
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.h
@@ -82,7 +82,7 @@
panfrost_gem_mapping_get(struct panfrost_gem_object *bo,
struct panfrost_file_priv *priv);
void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping);
-void panfrost_gem_teardown_mappings(struct panfrost_gem_object *bo);
+void panfrost_gem_teardown_mappings_locked(struct panfrost_gem_object *bo);
void panfrost_gem_shrinker_init(struct drm_device *dev);
void panfrost_gem_shrinker_cleanup(struct drm_device *dev);
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
index 288e46c..1b9f68d 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
@@ -40,18 +40,26 @@
{
struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
struct panfrost_gem_object *bo = to_panfrost_bo(obj);
+ bool ret = false;
if (atomic_read(&bo->gpu_usecount))
return false;
- if (!mutex_trylock(&shmem->pages_lock))
+ if (!mutex_trylock(&bo->mappings.lock))
return false;
- panfrost_gem_teardown_mappings(bo);
+ if (!mutex_trylock(&shmem->pages_lock))
+ goto unlock_mappings;
+
+ panfrost_gem_teardown_mappings_locked(bo);
drm_gem_shmem_purge_locked(obj);
+ ret = true;
mutex_unlock(&shmem->pages_lock);
- return true;
+
+unlock_mappings:
+ mutex_unlock(&bo->mappings.lock);
+ return ret;
}
static unsigned long
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index 77497b4..55960cb 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -814,9 +814,15 @@
*
* XXX(hch): this has no business in a driver and needs to move
* to the device tree.
+ *
+ * If we have two subsequent calls to dma_direct_set_offset
+ * returns -EINVAL. Unfortunately, this happens when we have two
+ * backends in the system, and will result in the driver
+ * reporting an error while it has been setup properly before.
+ * Ignore EINVAL, but it should really be removed eventually.
*/
ret = dma_direct_set_offset(drm->dev, PHYS_OFFSET, 0, SZ_4G);
- if (ret)
+ if (ret && ret != -EINVAL)
return ret;
}
diff --git a/drivers/gpu/drm/sun4i/sun4i_frontend.c b/drivers/gpu/drm/sun4i/sun4i_frontend.c
index b51cc68..edb60ae0 100644
--- a/drivers/gpu/drm/sun4i/sun4i_frontend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_frontend.c
@@ -407,6 +407,7 @@
struct drm_framebuffer *fb = state->fb;
const struct drm_format_info *format = fb->format;
uint64_t modifier = fb->modifier;
+ unsigned int ch1_phase_idx;
u32 out_fmt_val;
u32 in_fmt_val, in_mod_val, in_ps_val;
unsigned int i;
@@ -442,18 +443,19 @@
* I have no idea what this does exactly, but it seems to be
* related to the scaler FIR filter phase parameters.
*/
+ ch1_phase_idx = (format->num_planes > 1) ? 1 : 0;
regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_HORZPHASE_REG,
- frontend->data->ch_phase[0].horzphase);
+ frontend->data->ch_phase[0]);
regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_HORZPHASE_REG,
- frontend->data->ch_phase[1].horzphase);
+ frontend->data->ch_phase[ch1_phase_idx]);
regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_VERTPHASE0_REG,
- frontend->data->ch_phase[0].vertphase[0]);
+ frontend->data->ch_phase[0]);
regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_VERTPHASE0_REG,
- frontend->data->ch_phase[1].vertphase[0]);
+ frontend->data->ch_phase[ch1_phase_idx]);
regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_VERTPHASE1_REG,
- frontend->data->ch_phase[0].vertphase[1]);
+ frontend->data->ch_phase[0]);
regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_VERTPHASE1_REG,
- frontend->data->ch_phase[1].vertphase[1]);
+ frontend->data->ch_phase[ch1_phase_idx]);
/*
* Checking the input format is sufficient since we currently only
@@ -687,30 +689,12 @@
};
static const struct sun4i_frontend_data sun4i_a10_frontend = {
- .ch_phase = {
- {
- .horzphase = 0,
- .vertphase = { 0, 0 },
- },
- {
- .horzphase = 0xfc000,
- .vertphase = { 0xfc000, 0xfc000 },
- },
- },
+ .ch_phase = { 0x000, 0xfc000 },
.has_coef_rdy = true,
};
static const struct sun4i_frontend_data sun8i_a33_frontend = {
- .ch_phase = {
- {
- .horzphase = 0x400,
- .vertphase = { 0x400, 0x400 },
- },
- {
- .horzphase = 0x400,
- .vertphase = { 0x400, 0x400 },
- },
- },
+ .ch_phase = { 0x400, 0xfc400 },
.has_coef_access_ctrl = true,
};
diff --git a/drivers/gpu/drm/sun4i/sun4i_frontend.h b/drivers/gpu/drm/sun4i/sun4i_frontend.h
index 0c382c1..2e7b76e 100644
--- a/drivers/gpu/drm/sun4i/sun4i_frontend.h
+++ b/drivers/gpu/drm/sun4i/sun4i_frontend.h
@@ -115,11 +115,7 @@
struct sun4i_frontend_data {
bool has_coef_access_ctrl;
bool has_coef_rdy;
-
- struct {
- u32 horzphase;
- u32 vertphase[2];
- } ch_phase[2];
+ u32 ch_phase[2];
};
struct sun4i_frontend {
diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
index d4c0804..92add2c 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
@@ -208,6 +208,7 @@
phy_node = of_parse_phandle(dev->of_node, "phys", 0);
if (!phy_node) {
dev_err(dev, "Can't found PHY phandle\n");
+ ret = -EINVAL;
goto err_disable_clk_tmds;
}
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index 915f8bfd..182c586 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -568,7 +568,6 @@
ret = v3d_job_init(v3d, file_priv, &bin->base,
v3d_job_free, args->in_sync_bcl);
if (ret) {
- kfree(bin);
v3d_job_put(&render->base);
kfree(bin);
return ret;
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index 74ceebd..cc74a3f 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -449,7 +449,7 @@
}
if (IS_ERR(cma_obj)) {
- struct drm_printer p = drm_info_printer(vc4->dev->dev);
+ struct drm_printer p = drm_info_printer(vc4->base.dev);
DRM_ERROR("Failed to allocate from CMA:\n");
vc4_bo_stats_print(&p, vc4);
return ERR_PTR(-ENOMEM);
@@ -590,7 +590,7 @@
{
struct vc4_dev *vc4 =
container_of(work, struct vc4_dev, bo_cache.time_work);
- struct drm_device *dev = vc4->dev;
+ struct drm_device *dev = &vc4->base;
mutex_lock(&vc4->bo_lock);
vc4_bo_cache_free_old(dev);
@@ -1005,6 +1005,7 @@
return 0;
}
+static void vc4_bo_cache_destroy(struct drm_device *dev, void *unused);
int vc4_bo_cache_init(struct drm_device *dev)
{
struct vc4_dev *vc4 = to_vc4_dev(dev);
@@ -1033,10 +1034,10 @@
INIT_WORK(&vc4->bo_cache.time_work, vc4_bo_cache_time_work);
timer_setup(&vc4->bo_cache.time_timer, vc4_bo_cache_time_timer, 0);
- return 0;
+ return drmm_add_action_or_reset(dev, vc4_bo_cache_destroy, NULL);
}
-void vc4_bo_cache_destroy(struct drm_device *dev)
+static void vc4_bo_cache_destroy(struct drm_device *dev, void *unused)
{
struct vc4_dev *vc4 = to_vc4_dev(dev);
int i;
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index f1a5fd5..839610f 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -257,37 +257,37 @@
dev->coherent_dma_mask = DMA_BIT_MASK(32);
- vc4 = devm_kzalloc(dev, sizeof(*vc4), GFP_KERNEL);
- if (!vc4)
- return -ENOMEM;
-
/* If VC4 V3D is missing, don't advertise render nodes. */
node = of_find_matching_node_and_match(NULL, vc4_v3d_dt_match, NULL);
if (!node || !of_device_is_available(node))
vc4_drm_driver.driver_features &= ~DRIVER_RENDER;
of_node_put(node);
- drm = drm_dev_alloc(&vc4_drm_driver, dev);
- if (IS_ERR(drm))
- return PTR_ERR(drm);
+ vc4 = devm_drm_dev_alloc(dev, &vc4_drm_driver, struct vc4_dev, base);
+ if (IS_ERR(vc4))
+ return PTR_ERR(vc4);
+
+ drm = &vc4->base;
platform_set_drvdata(pdev, drm);
- vc4->dev = drm;
- drm->dev_private = vc4;
INIT_LIST_HEAD(&vc4->debugfs_list);
mutex_init(&vc4->bin_bo_lock);
ret = vc4_bo_cache_init(drm);
if (ret)
- goto dev_put;
+ return ret;
- drm_mode_config_init(drm);
+ ret = drmm_mode_config_init(drm);
+ if (ret)
+ return ret;
- vc4_gem_init(drm);
+ ret = vc4_gem_init(drm);
+ if (ret)
+ return ret;
ret = component_bind_all(dev, drm);
if (ret)
- goto gem_destroy;
+ return ret;
ret = vc4_plane_create_additional_planes(drm);
if (ret)
@@ -312,29 +312,17 @@
unbind_all:
component_unbind_all(dev, drm);
-gem_destroy:
- vc4_gem_destroy(drm);
- vc4_bo_cache_destroy(drm);
-dev_put:
- drm_dev_put(drm);
+
return ret;
}
static void vc4_drm_unbind(struct device *dev)
{
struct drm_device *drm = dev_get_drvdata(dev);
- struct vc4_dev *vc4 = to_vc4_dev(drm);
drm_dev_unregister(drm);
drm_atomic_helper_shutdown(drm);
-
- drm_mode_config_cleanup(drm);
-
- drm_atomic_private_obj_fini(&vc4->load_tracker);
- drm_atomic_private_obj_fini(&vc4->ctm_manager);
-
- drm_dev_put(drm);
}
static const struct component_master_ops vc4_drm_ops = {
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 90b911f..19b75be 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -14,6 +14,7 @@
#include <drm/drm_device.h>
#include <drm/drm_encoder.h>
#include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_managed.h>
#include <drm/drm_mm.h>
#include <drm/drm_modeset_lock.h>
@@ -71,7 +72,7 @@
};
struct vc4_dev {
- struct drm_device *dev;
+ struct drm_device base;
struct vc4_hvs *hvs;
struct vc4_v3d *v3d;
@@ -234,7 +235,7 @@
static inline struct vc4_dev *
to_vc4_dev(struct drm_device *dev)
{
- return (struct vc4_dev *)dev->dev_private;
+ return container_of(dev, struct vc4_dev, base);
}
struct vc4_bo {
@@ -287,7 +288,7 @@
static inline struct vc4_bo *
to_vc4_bo(struct drm_gem_object *bo)
{
- return (struct vc4_bo *)bo;
+ return container_of(to_drm_gem_cma_obj(bo), struct vc4_bo, base);
}
struct vc4_fence {
@@ -300,7 +301,7 @@
static inline struct vc4_fence *
to_vc4_fence(struct dma_fence *fence)
{
- return (struct vc4_fence *)fence;
+ return container_of(fence, struct vc4_fence, base);
}
struct vc4_seqno_cb {
@@ -347,7 +348,7 @@
static inline struct vc4_plane *
to_vc4_plane(struct drm_plane *plane)
{
- return (struct vc4_plane *)plane;
+ return container_of(plane, struct vc4_plane, base);
}
enum vc4_scaling_mode {
@@ -423,7 +424,7 @@
static inline struct vc4_plane_state *
to_vc4_plane_state(struct drm_plane_state *state)
{
- return (struct vc4_plane_state *)state;
+ return container_of(state, struct vc4_plane_state, base);
}
enum vc4_encoder_type {
@@ -499,7 +500,7 @@
static inline struct vc4_crtc *
to_vc4_crtc(struct drm_crtc *crtc)
{
- return (struct vc4_crtc *)crtc;
+ return container_of(crtc, struct vc4_crtc, base);
}
static inline const struct vc4_crtc_data *
@@ -537,7 +538,7 @@
static inline struct vc4_crtc_state *
to_vc4_crtc_state(struct drm_crtc_state *crtc_state)
{
- return (struct vc4_crtc_state *)crtc_state;
+ return container_of(crtc_state, struct vc4_crtc_state, base);
}
#define V3D_READ(offset) readl(vc4->v3d->regs + offset)
@@ -809,7 +810,6 @@
struct sg_table *sgt);
void *vc4_prime_vmap(struct drm_gem_object *obj);
int vc4_bo_cache_init(struct drm_device *dev);
-void vc4_bo_cache_destroy(struct drm_device *dev);
int vc4_bo_inc_usecnt(struct vc4_bo *bo);
void vc4_bo_dec_usecnt(struct vc4_bo *bo);
void vc4_bo_add_to_purgeable_pool(struct vc4_bo *bo);
@@ -874,8 +874,7 @@
extern const struct dma_fence_ops vc4_fence_ops;
/* vc4_gem.c */
-void vc4_gem_init(struct drm_device *dev);
-void vc4_gem_destroy(struct drm_device *dev);
+int vc4_gem_init(struct drm_device *dev);
int vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv);
int vc4_wait_seqno_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 9f01ddd..b641252 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -314,16 +314,16 @@
struct vc4_dev *vc4 =
container_of(work, struct vc4_dev, hangcheck.reset_work);
- vc4_save_hang_state(vc4->dev);
+ vc4_save_hang_state(&vc4->base);
- vc4_reset(vc4->dev);
+ vc4_reset(&vc4->base);
}
static void
vc4_hangcheck_elapsed(struct timer_list *t)
{
struct vc4_dev *vc4 = from_timer(vc4, t, hangcheck.timer);
- struct drm_device *dev = vc4->dev;
+ struct drm_device *dev = &vc4->base;
uint32_t ct0ca, ct1ca;
unsigned long irqflags;
struct vc4_exec_info *bin_exec, *render_exec;
@@ -1000,7 +1000,7 @@
list_del(&exec->head);
spin_unlock_irqrestore(&vc4->job_lock, irqflags);
- vc4_complete_exec(vc4->dev, exec);
+ vc4_complete_exec(&vc4->base, exec);
spin_lock_irqsave(&vc4->job_lock, irqflags);
}
@@ -1258,13 +1258,13 @@
return 0;
fail:
- vc4_complete_exec(vc4->dev, exec);
+ vc4_complete_exec(&vc4->base, exec);
return ret;
}
-void
-vc4_gem_init(struct drm_device *dev)
+static void vc4_gem_destroy(struct drm_device *dev, void *unused);
+int vc4_gem_init(struct drm_device *dev)
{
struct vc4_dev *vc4 = to_vc4_dev(dev);
@@ -1285,10 +1285,11 @@
INIT_LIST_HEAD(&vc4->purgeable.list);
mutex_init(&vc4->purgeable.lock);
+
+ return drmm_add_action_or_reset(dev, vc4_gem_destroy, NULL);
}
-void
-vc4_gem_destroy(struct drm_device *dev)
+static void vc4_gem_destroy(struct drm_device *dev, void *unused)
{
struct vc4_dev *vc4 = to_vc4_dev(dev);
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index e8f99e2..95779d5 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -922,6 +922,7 @@
struct snd_soc_dai *dai)
{
struct vc4_hdmi *vc4_hdmi = dai_to_hdmi(dai);
+ struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base;
struct device *dev = &vc4_hdmi->pdev->dev;
u32 audio_packet_config, channel_mask;
u32 channel_map;
@@ -981,6 +982,8 @@
HDMI_WRITE(HDMI_AUDIO_PACKET_CONFIG, audio_packet_config);
vc4_hdmi_set_n_cts(vc4_hdmi);
+ vc4_hdmi_set_audio_infoframe(encoder);
+
return 0;
}
@@ -988,11 +991,9 @@
struct snd_soc_dai *dai)
{
struct vc4_hdmi *vc4_hdmi = dai_to_hdmi(dai);
- struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base;
switch (cmd) {
case SNDRV_PCM_TRIGGER_START:
- vc4_hdmi_set_audio_infoframe(encoder);
vc4_hdmi->audio.streaming = true;
if (vc4_hdmi->variant->phy_rng_enable)
@@ -1076,6 +1077,7 @@
};
static const struct snd_soc_component_driver vc4_hdmi_audio_component_drv = {
+ .name = "vc4-hdmi-codec-dai-component",
.controls = vc4_hdmi_audio_controls,
.num_controls = ARRAY_SIZE(vc4_hdmi_audio_controls),
.dapm_widgets = vc4_hdmi_audio_widgets,
diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c
index 4d0a833..b72b2bd 100644
--- a/drivers/gpu/drm/vc4/vc4_hvs.c
+++ b/drivers/gpu/drm/vc4/vc4_hvs.c
@@ -560,7 +560,7 @@
{
struct platform_device *pdev = to_platform_device(dev);
struct drm_device *drm = dev_get_drvdata(master);
- struct vc4_dev *vc4 = drm->dev_private;
+ struct vc4_dev *vc4 = to_vc4_dev(drm);
struct vc4_hvs *hvs = NULL;
int ret;
u32 dispctrl;
@@ -679,7 +679,7 @@
void *data)
{
struct drm_device *drm = dev_get_drvdata(master);
- struct vc4_dev *vc4 = drm->dev_private;
+ struct vc4_dev *vc4 = to_vc4_dev(drm);
struct vc4_hvs *hvs = vc4->hvs;
if (drm_mm_node_allocated(&vc4->hvs->mitchell_netravali_filter))
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index 149825f..2b951ca 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -51,7 +51,7 @@
struct drm_private_obj *manager)
{
struct drm_device *dev = state->dev;
- struct vc4_dev *vc4 = dev->dev_private;
+ struct vc4_dev *vc4 = to_vc4_dev(dev);
struct drm_private_state *priv_state;
int ret;
@@ -93,6 +93,29 @@
.atomic_destroy_state = vc4_ctm_destroy_state,
};
+static void vc4_ctm_obj_fini(struct drm_device *dev, void *unused)
+{
+ struct vc4_dev *vc4 = to_vc4_dev(dev);
+
+ drm_atomic_private_obj_fini(&vc4->ctm_manager);
+}
+
+static int vc4_ctm_obj_init(struct vc4_dev *vc4)
+{
+ struct vc4_ctm_state *ctm_state;
+
+ drm_modeset_lock_init(&vc4->ctm_state_lock);
+
+ ctm_state = kzalloc(sizeof(*ctm_state), GFP_KERNEL);
+ if (!ctm_state)
+ return -ENOMEM;
+
+ drm_atomic_private_obj_init(&vc4->base, &vc4->ctm_manager, &ctm_state->base,
+ &vc4_ctm_state_funcs);
+
+ return drmm_add_action(&vc4->base, vc4_ctm_obj_fini, NULL);
+}
+
/* Converts a DRM S31.32 value to the HW S0.9 format. */
static u16 vc4_ctm_s31_32_to_s0_9(u64 in)
{
@@ -609,6 +632,34 @@
.atomic_destroy_state = vc4_load_tracker_destroy_state,
};
+static void vc4_load_tracker_obj_fini(struct drm_device *dev, void *unused)
+{
+ struct vc4_dev *vc4 = to_vc4_dev(dev);
+
+ if (!vc4->load_tracker_available)
+ return;
+
+ drm_atomic_private_obj_fini(&vc4->load_tracker);
+}
+
+static int vc4_load_tracker_obj_init(struct vc4_dev *vc4)
+{
+ struct vc4_load_tracker_state *load_state;
+
+ if (!vc4->load_tracker_available)
+ return 0;
+
+ load_state = kzalloc(sizeof(*load_state), GFP_KERNEL);
+ if (!load_state)
+ return -ENOMEM;
+
+ drm_atomic_private_obj_init(&vc4->base, &vc4->load_tracker,
+ &load_state->base,
+ &vc4_load_tracker_state_funcs);
+
+ return drmm_add_action(&vc4->base, vc4_load_tracker_obj_fini, NULL);
+}
+
#define NUM_OUTPUTS 6
#define NUM_CHANNELS 3
@@ -711,8 +762,6 @@
int vc4_kms_load(struct drm_device *dev)
{
struct vc4_dev *vc4 = to_vc4_dev(dev);
- struct vc4_ctm_state *ctm_state;
- struct vc4_load_tracker_state *load_state;
bool is_vc5 = of_device_is_compatible(dev->dev->of_node,
"brcm,bcm2711-vc5");
int ret;
@@ -751,26 +800,13 @@
dev->mode_config.async_page_flip = true;
dev->mode_config.allow_fb_modifiers = true;
- drm_modeset_lock_init(&vc4->ctm_state_lock);
+ ret = vc4_ctm_obj_init(vc4);
+ if (ret)
+ return ret;
- ctm_state = kzalloc(sizeof(*ctm_state), GFP_KERNEL);
- if (!ctm_state)
- return -ENOMEM;
-
- drm_atomic_private_obj_init(dev, &vc4->ctm_manager, &ctm_state->base,
- &vc4_ctm_state_funcs);
-
- if (vc4->load_tracker_available) {
- load_state = kzalloc(sizeof(*load_state), GFP_KERNEL);
- if (!load_state) {
- drm_atomic_private_obj_fini(&vc4->ctm_manager);
- return -ENOMEM;
- }
-
- drm_atomic_private_obj_init(dev, &vc4->load_tracker,
- &load_state->base,
- &vc4_load_tracker_state_funcs);
- }
+ ret = vc4_load_tracker_obj_init(vc4);
+ if (ret)
+ return ret;
drm_mode_config_reset(dev);
diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c
index f7ab979..65d0dac 100644
--- a/drivers/gpu/drm/vc4/vc4_v3d.c
+++ b/drivers/gpu/drm/vc4/vc4_v3d.c
@@ -168,7 +168,7 @@
int vc4_v3d_get_bin_slot(struct vc4_dev *vc4)
{
- struct drm_device *dev = vc4->dev;
+ struct drm_device *dev = &vc4->base;
unsigned long irqflags;
int slot;
uint64_t seqno = 0;
@@ -246,7 +246,7 @@
INIT_LIST_HEAD(&list);
while (true) {
- struct vc4_bo *bo = vc4_bo_create(vc4->dev, size, true,
+ struct vc4_bo *bo = vc4_bo_create(&vc4->base, size, true,
VC4_BO_TYPE_BIN);
if (IS_ERR(bo)) {
@@ -361,7 +361,7 @@
struct vc4_v3d *v3d = dev_get_drvdata(dev);
struct vc4_dev *vc4 = v3d->vc4;
- vc4_irq_uninstall(vc4->dev);
+ vc4_irq_uninstall(&vc4->base);
clk_disable_unprepare(v3d->clk);
@@ -378,11 +378,11 @@
if (ret != 0)
return ret;
- vc4_v3d_init_hw(vc4->dev);
+ vc4_v3d_init_hw(&vc4->base);
/* We disabled the IRQ as part of vc4_irq_uninstall in suspend. */
- enable_irq(vc4->dev->irq);
- vc4_irq_postinstall(vc4->dev);
+ enable_irq(vc4->base.irq);
+ vc4_irq_postinstall(&vc4->base);
return 0;
}
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index b3dae9e..d166ee2 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -133,73 +133,6 @@
}
EXPORT_SYMBOL_GPL(ipu_pixelformat_to_colorspace);
-bool ipu_pixelformat_is_planar(u32 pixelformat)
-{
- switch (pixelformat) {
- case V4L2_PIX_FMT_YUV420:
- case V4L2_PIX_FMT_YVU420:
- case V4L2_PIX_FMT_YUV422P:
- case V4L2_PIX_FMT_NV12:
- case V4L2_PIX_FMT_NV21:
- case V4L2_PIX_FMT_NV16:
- case V4L2_PIX_FMT_NV61:
- return true;
- }
-
- return false;
-}
-EXPORT_SYMBOL_GPL(ipu_pixelformat_is_planar);
-
-enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code)
-{
- switch (mbus_code & 0xf000) {
- case 0x1000:
- return IPUV3_COLORSPACE_RGB;
- case 0x2000:
- return IPUV3_COLORSPACE_YUV;
- default:
- return IPUV3_COLORSPACE_UNKNOWN;
- }
-}
-EXPORT_SYMBOL_GPL(ipu_mbus_code_to_colorspace);
-
-int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat)
-{
- switch (pixelformat) {
- case V4L2_PIX_FMT_YUV420:
- case V4L2_PIX_FMT_YVU420:
- case V4L2_PIX_FMT_YUV422P:
- case V4L2_PIX_FMT_NV12:
- case V4L2_PIX_FMT_NV21:
- case V4L2_PIX_FMT_NV16:
- case V4L2_PIX_FMT_NV61:
- /*
- * for the planar YUV formats, the stride passed to
- * cpmem must be the stride in bytes of the Y plane.
- * And all the planar YUV formats have an 8-bit
- * Y component.
- */
- return (8 * pixel_stride) >> 3;
- case V4L2_PIX_FMT_RGB565:
- case V4L2_PIX_FMT_YUYV:
- case V4L2_PIX_FMT_UYVY:
- return (16 * pixel_stride) >> 3;
- case V4L2_PIX_FMT_BGR24:
- case V4L2_PIX_FMT_RGB24:
- return (24 * pixel_stride) >> 3;
- case V4L2_PIX_FMT_BGR32:
- case V4L2_PIX_FMT_RGB32:
- case V4L2_PIX_FMT_XBGR32:
- case V4L2_PIX_FMT_XRGB32:
- return (32 * pixel_stride) >> 3;
- default:
- break;
- }
-
- return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(ipu_stride_to_bytes);
-
int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees,
bool hflip, bool vflip)
{
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 0cde10f..f202ac7 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -244,9 +244,13 @@
/*
* Hyper-V does not provide a way to change the connect CPU once
- * it is set; we must prevent the connect CPU from going offline.
+ * it is set; we must prevent the connect CPU from going offline
+ * while the VM is running normally. But in the panic or kexec()
+ * path where the vmbus is already disconnected, the CPU must be
+ * allowed to shut down.
*/
- if (cpu == VMBUS_CONNECT_CPU)
+ if (cpu == VMBUS_CONNECT_CPU &&
+ vmbus_connection.conn_state == CONNECTED)
return -EBUSY;
/*
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index b64d2ef..eb56e09 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -1275,7 +1275,7 @@
/* Refuse to balloon below the floor. */
if (avail_pages < num_pages || avail_pages - num_pages < floor) {
- pr_warn("Balloon request will be partially fulfilled. %s\n",
+ pr_info("Balloon request will be partially fulfilled. %s\n",
avail_pages < num_pages ? "Not enough memory." :
"Balloon floor reached.");
diff --git a/drivers/hwmon/amd_energy.c b/drivers/hwmon/amd_energy.c
index d065973..3197cda 100644
--- a/drivers/hwmon/amd_energy.c
+++ b/drivers/hwmon/amd_energy.c
@@ -171,7 +171,7 @@
enum hwmon_sensor_types type,
u32 attr, int channel)
{
- return 0444;
+ return 0440;
}
static int energy_accumulator(void *p)
diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c
index a188879..79b498f 100644
--- a/drivers/hwmon/applesmc.c
+++ b/drivers/hwmon/applesmc.c
@@ -32,6 +32,7 @@
#include <linux/hwmon.h>
#include <linux/workqueue.h>
#include <linux/err.h>
+#include <linux/bits.h>
/* data port used by Apple SMC */
#define APPLESMC_DATA_PORT 0x300
@@ -42,10 +43,13 @@
#define APPLESMC_MAX_DATA_LENGTH 32
-/* wait up to 128 ms for a status change. */
-#define APPLESMC_MIN_WAIT 0x0010
-#define APPLESMC_RETRY_WAIT 0x0100
-#define APPLESMC_MAX_WAIT 0x20000
+/* Apple SMC status bits */
+#define SMC_STATUS_AWAITING_DATA BIT(0) /* SMC has data waiting to be read */
+#define SMC_STATUS_IB_CLOSED BIT(1) /* Will ignore any input */
+#define SMC_STATUS_BUSY BIT(2) /* Command in progress */
+
+/* Initial wait is 8us */
+#define APPLESMC_MIN_WAIT 0x0008
#define APPLESMC_READ_CMD 0x10
#define APPLESMC_WRITE_CMD 0x11
@@ -151,65 +155,84 @@
static struct workqueue_struct *applesmc_led_wq;
/*
- * wait_read - Wait for a byte to appear on SMC port. Callers must
- * hold applesmc_lock.
+ * Wait for specific status bits with a mask on the SMC.
+ * Used before all transactions.
+ * This does 10 fast loops of 8us then exponentially backs off for a
+ * minimum total wait of 262ms. Depending on usleep_range this could
+ * run out past 500ms.
*/
-static int wait_read(void)
+
+static int wait_status(u8 val, u8 mask)
{
- unsigned long end = jiffies + (APPLESMC_MAX_WAIT * HZ) / USEC_PER_SEC;
u8 status;
int us;
+ int i;
- for (us = APPLESMC_MIN_WAIT; us < APPLESMC_MAX_WAIT; us <<= 1) {
- usleep_range(us, us * 16);
+ us = APPLESMC_MIN_WAIT;
+ for (i = 0; i < 24 ; i++) {
status = inb(APPLESMC_CMD_PORT);
- /* read: wait for smc to settle */
- if (status & 0x01)
+ if ((status & mask) == val)
return 0;
- /* timeout: give up */
- if (time_after(jiffies, end))
- break;
+ usleep_range(us, us * 2);
+ if (i > 9)
+ us <<= 1;
}
-
- pr_warn("wait_read() fail: 0x%02x\n", status);
return -EIO;
}
-/*
- * send_byte - Write to SMC port, retrying when necessary. Callers
- * must hold applesmc_lock.
- */
+/* send_byte - Write to SMC data port. Callers must hold applesmc_lock. */
+
static int send_byte(u8 cmd, u16 port)
{
- u8 status;
- int us;
- unsigned long end = jiffies + (APPLESMC_MAX_WAIT * HZ) / USEC_PER_SEC;
+ int status;
+
+ status = wait_status(0, SMC_STATUS_IB_CLOSED);
+ if (status)
+ return status;
+ /*
+ * This needs to be a separate read looking for bit 0x04
+ * after bit 0x02 falls. If consolidated with the wait above
+ * this extra read may not happen if status returns both
+ * simultaneously and this would appear to be required.
+ */
+ status = wait_status(SMC_STATUS_BUSY, SMC_STATUS_BUSY);
+ if (status)
+ return status;
outb(cmd, port);
- for (us = APPLESMC_MIN_WAIT; us < APPLESMC_MAX_WAIT; us <<= 1) {
- usleep_range(us, us * 16);
- status = inb(APPLESMC_CMD_PORT);
- /* write: wait for smc to settle */
- if (status & 0x02)
- continue;
- /* ready: cmd accepted, return */
- if (status & 0x04)
- return 0;
- /* timeout: give up */
- if (time_after(jiffies, end))
- break;
- /* busy: long wait and resend */
- udelay(APPLESMC_RETRY_WAIT);
- outb(cmd, port);
- }
-
- pr_warn("send_byte(0x%02x, 0x%04x) fail: 0x%02x\n", cmd, port, status);
- return -EIO;
+ return 0;
}
+/* send_command - Write a command to the SMC. Callers must hold applesmc_lock. */
+
static int send_command(u8 cmd)
{
- return send_byte(cmd, APPLESMC_CMD_PORT);
+ int ret;
+
+ ret = wait_status(0, SMC_STATUS_IB_CLOSED);
+ if (ret)
+ return ret;
+ outb(cmd, APPLESMC_CMD_PORT);
+ return 0;
+}
+
+/*
+ * Based on logic from the Apple driver. This is issued before any interaction
+ * If busy is stuck high, issue a read command to reset the SMC state machine.
+ * If busy is stuck high after the command then the SMC is jammed.
+ */
+
+static int smc_sane(void)
+{
+ int ret;
+
+ ret = wait_status(0, SMC_STATUS_BUSY);
+ if (!ret)
+ return ret;
+ ret = send_command(APPLESMC_READ_CMD);
+ if (ret)
+ return ret;
+ return wait_status(0, SMC_STATUS_BUSY);
}
static int send_argument(const char *key)
@@ -226,6 +249,11 @@
{
u8 status, data = 0;
int i;
+ int ret;
+
+ ret = smc_sane();
+ if (ret)
+ return ret;
if (send_command(cmd) || send_argument(key)) {
pr_warn("%.4s: read arg fail\n", key);
@@ -239,7 +267,8 @@
}
for (i = 0; i < len; i++) {
- if (wait_read()) {
+ if (wait_status(SMC_STATUS_AWAITING_DATA | SMC_STATUS_BUSY,
+ SMC_STATUS_AWAITING_DATA | SMC_STATUS_BUSY)) {
pr_warn("%.4s: read data[%d] fail\n", key, i);
return -EIO;
}
@@ -250,19 +279,24 @@
for (i = 0; i < 16; i++) {
udelay(APPLESMC_MIN_WAIT);
status = inb(APPLESMC_CMD_PORT);
- if (!(status & 0x01))
+ if (!(status & SMC_STATUS_AWAITING_DATA))
break;
data = inb(APPLESMC_DATA_PORT);
}
if (i)
pr_warn("flushed %d bytes, last value is: %d\n", i, data);
- return 0;
+ return wait_status(0, SMC_STATUS_BUSY);
}
static int write_smc(u8 cmd, const char *key, const u8 *buffer, u8 len)
{
int i;
+ int ret;
+
+ ret = smc_sane();
+ if (ret)
+ return ret;
if (send_command(cmd) || send_argument(key)) {
pr_warn("%s: write arg fail\n", key);
@@ -281,7 +315,7 @@
}
}
- return 0;
+ return wait_status(0, SMC_STATUS_BUSY);
}
static int read_register_count(unsigned int *count)
diff --git a/drivers/hwmon/pmbus/max20730.c b/drivers/hwmon/pmbus/max20730.c
index 57923d7..be83b98 100644
--- a/drivers/hwmon/pmbus/max20730.c
+++ b/drivers/hwmon/pmbus/max20730.c
@@ -122,8 +122,8 @@
switch (idx) {
case MAX20730_DEBUGFS_VOUT_MIN:
ret = VOLT_FROM_REG(data->mfr_voutmin * 10000);
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d.%d\n",
- ret / 10000, ret % 10000);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d.%d\n",
+ ret / 10000, ret % 10000);
break;
case MAX20730_DEBUGFS_FREQUENCY:
val = (data->mfr_devset1 & MAX20730_MFR_DEVSET1_FSW_MASK)
@@ -141,7 +141,7 @@
ret = 800;
else
ret = 900;
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
break;
case MAX20730_DEBUGFS_PG_DELAY:
val = (data->mfr_devset1 & MAX20730_MFR_DEVSET1_TSTAT_MASK)
@@ -223,7 +223,7 @@
case MAX20730_DEBUGFS_OC_PROTECT_MODE:
ret = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_OCPM_MASK)
>> MAX20730_MFR_DEVSET2_OCPM_BIT_POS;
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
break;
case MAX20730_DEBUGFS_SS_TIMING:
val = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_SS_MASK)
@@ -241,32 +241,32 @@
case MAX20730_DEBUGFS_IMAX:
ret = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_IMAX_MASK)
>> MAX20730_MFR_DEVSET2_IMAX_BIT_POS;
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
break;
case MAX20730_DEBUGFS_OPERATION:
ret = i2c_smbus_read_byte_data(psu->client, PMBUS_OPERATION);
if (ret < 0)
return ret;
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
break;
case MAX20730_DEBUGFS_ON_OFF_CONFIG:
ret = i2c_smbus_read_byte_data(psu->client, PMBUS_ON_OFF_CONFIG);
if (ret < 0)
return ret;
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
break;
case MAX20730_DEBUGFS_SMBALERT_MASK:
ret = i2c_smbus_read_word_data(psu->client,
PMBUS_SMB_ALERT_MASK);
if (ret < 0)
return ret;
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
break;
case MAX20730_DEBUGFS_VOUT_MODE:
ret = i2c_smbus_read_byte_data(psu->client, PMBUS_VOUT_MODE);
if (ret < 0)
return ret;
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
break;
case MAX20730_DEBUGFS_VOUT_COMMAND:
ret = i2c_smbus_read_word_data(psu->client, PMBUS_VOUT_COMMAND);
@@ -274,8 +274,8 @@
return ret;
ret = VOLT_FROM_REG(ret * 10000);
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX,
- "%d.%d\n", ret / 10000, ret % 10000);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX,
+ "%d.%d\n", ret / 10000, ret % 10000);
break;
case MAX20730_DEBUGFS_VOUT_MAX:
ret = i2c_smbus_read_word_data(psu->client, PMBUS_VOUT_MAX);
@@ -283,8 +283,8 @@
return ret;
ret = VOLT_FROM_REG(ret * 10000);
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX,
- "%d.%d\n", ret / 10000, ret % 10000);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX,
+ "%d.%d\n", ret / 10000, ret % 10000);
break;
default:
len = strlcpy(tbuf, "Invalid\n", DEBUG_FS_DATA_MAX);
diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c
index 170a9f8..b0e2820 100644
--- a/drivers/hwmon/pmbus/pmbus_core.c
+++ b/drivers/hwmon/pmbus/pmbus_core.c
@@ -941,12 +941,16 @@
struct i2c_client *client = to_i2c_client(dev->parent);
struct pmbus_sensor *sensor = to_pmbus_sensor(devattr);
struct pmbus_data *data = i2c_get_clientdata(client);
+ ssize_t ret;
+ mutex_lock(&data->update_lock);
pmbus_update_sensor_data(client, sensor);
if (sensor->data < 0)
- return sensor->data;
-
- return snprintf(buf, PAGE_SIZE, "%lld\n", pmbus_reg2data(data, sensor));
+ ret = sensor->data;
+ else
+ ret = snprintf(buf, PAGE_SIZE, "%lld\n", pmbus_reg2data(data, sensor));
+ mutex_unlock(&data->update_lock);
+ return ret;
}
static ssize_t pmbus_set_sensor(struct device *dev,
@@ -2012,8 +2016,11 @@
int val;
struct i2c_client *client = to_i2c_client(dev->parent);
struct pmbus_samples_reg *reg = to_samples_reg(devattr);
+ struct pmbus_data *data = i2c_get_clientdata(client);
+ mutex_lock(&data->update_lock);
val = _pmbus_read_word_data(client, reg->page, 0xff, reg->attr->reg);
+ mutex_unlock(&data->update_lock);
if (val < 0)
return val;
diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c
index bdba214..1f63807 100644
--- a/drivers/hwmon/pwm-fan.c
+++ b/drivers/hwmon/pwm-fan.c
@@ -54,16 +54,18 @@
static void sample_timer(struct timer_list *t)
{
struct pwm_fan_ctx *ctx = from_timer(ctx, t, rpm_timer);
+ unsigned int delta = ktime_ms_delta(ktime_get(), ctx->sample_start);
int pulses;
- u64 tmp;
- pulses = atomic_read(&ctx->pulses);
- atomic_sub(pulses, &ctx->pulses);
- tmp = (u64)pulses * ktime_ms_delta(ktime_get(), ctx->sample_start) * 60;
- do_div(tmp, ctx->pulses_per_revolution * 1000);
- ctx->rpm = tmp;
+ if (delta) {
+ pulses = atomic_read(&ctx->pulses);
+ atomic_sub(pulses, &ctx->pulses);
+ ctx->rpm = (unsigned int)(pulses * 1000 * 60) /
+ (ctx->pulses_per_revolution * delta);
- ctx->sample_start = ktime_get();
+ ctx->sample_start = ktime_get();
+ }
+
mod_timer(&ctx->rpm_timer, jiffies + HZ);
}
diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c
index 6994c13..cc9e802 100644
--- a/drivers/hwtracing/coresight/coresight-core.c
+++ b/drivers/hwtracing/coresight/coresight-core.c
@@ -1689,6 +1689,7 @@
module_init(coresight_init);
module_exit(coresight_exit);
+MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Pratik Patel <pratikp@codeaurora.org>");
MODULE_AUTHOR("Mathieu Poirier <mathieu.poirier@linaro.org>");
MODULE_DESCRIPTION("Arm CoreSight tracer driver");
diff --git a/drivers/hwtracing/coresight/coresight-cti-sysfs.c b/drivers/hwtracing/coresight/coresight-cti-sysfs.c
index 392757f..7ff7e77 100644
--- a/drivers/hwtracing/coresight/coresight-cti-sysfs.c
+++ b/drivers/hwtracing/coresight/coresight-cti-sysfs.c
@@ -1065,6 +1065,13 @@
}
eattr->var = con;
con->con_attrs[attr_idx] = &eattr->attr.attr;
+ /*
+ * Initialize the dynamically allocated attribute
+ * to avoid LOCKDEP splat. See include/linux/sysfs.h
+ * for more details.
+ */
+ sysfs_attr_init(con->con_attrs[attr_idx]);
+
return 0;
}
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index c2c9b12..bdc34ca 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -210,7 +210,7 @@
u32 id;
int cpu = event->cpu;
cpumask_t *mask;
- struct coresight_device *sink;
+ struct coresight_device *sink = NULL;
struct etm_event_data *event_data = NULL;
event_data = alloc_event_data(cpu);
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index a4f473e..a97a9d0 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -733,7 +733,7 @@
config I2C_MLXBF
tristate "Mellanox BlueField I2C controller"
- depends on ARM64
+ depends on MELLANOX_PLATFORM && ARM64
help
Enabling this option will add I2C SMBus support for Mellanox BlueField
system.
diff --git a/drivers/i2c/busses/i2c-designware-slave.c b/drivers/i2c/busses/i2c-designware-slave.c
index 44974b5..0d15f4c 100644
--- a/drivers/i2c/busses/i2c-designware-slave.c
+++ b/drivers/i2c/busses/i2c-designware-slave.c
@@ -159,7 +159,6 @@
u32 raw_stat, stat, enabled, tmp;
u8 val = 0, slave_activity;
- regmap_read(dev->map, DW_IC_INTR_STAT, &stat);
regmap_read(dev->map, DW_IC_ENABLE, &enabled);
regmap_read(dev->map, DW_IC_RAW_INTR_STAT, &raw_stat);
regmap_read(dev->map, DW_IC_STATUS, &tmp);
@@ -168,32 +167,30 @@
if (!enabled || !(raw_stat & ~DW_IC_INTR_ACTIVITY) || !dev->slave)
return 0;
+ stat = i2c_dw_read_clear_intrbits_slave(dev);
dev_dbg(dev->dev,
"%#x STATUS SLAVE_ACTIVITY=%#x : RAW_INTR_STAT=%#x : INTR_STAT=%#x\n",
enabled, slave_activity, raw_stat, stat);
- if ((stat & DW_IC_INTR_RX_FULL) && (stat & DW_IC_INTR_STOP_DET))
- i2c_slave_event(dev->slave, I2C_SLAVE_WRITE_REQUESTED, &val);
+ if (stat & DW_IC_INTR_RX_FULL) {
+ if (dev->status != STATUS_WRITE_IN_PROGRESS) {
+ dev->status = STATUS_WRITE_IN_PROGRESS;
+ i2c_slave_event(dev->slave, I2C_SLAVE_WRITE_REQUESTED,
+ &val);
+ }
+
+ regmap_read(dev->map, DW_IC_DATA_CMD, &tmp);
+ val = tmp;
+ if (!i2c_slave_event(dev->slave, I2C_SLAVE_WRITE_RECEIVED,
+ &val))
+ dev_vdbg(dev->dev, "Byte %X acked!", val);
+ }
if (stat & DW_IC_INTR_RD_REQ) {
if (slave_activity) {
- if (stat & DW_IC_INTR_RX_FULL) {
- regmap_read(dev->map, DW_IC_DATA_CMD, &tmp);
- val = tmp;
+ regmap_read(dev->map, DW_IC_CLR_RD_REQ, &tmp);
- if (!i2c_slave_event(dev->slave,
- I2C_SLAVE_WRITE_RECEIVED,
- &val)) {
- dev_vdbg(dev->dev, "Byte %X acked!",
- val);
- }
- regmap_read(dev->map, DW_IC_CLR_RD_REQ, &tmp);
- stat = i2c_dw_read_clear_intrbits_slave(dev);
- } else {
- regmap_read(dev->map, DW_IC_CLR_RD_REQ, &tmp);
- regmap_read(dev->map, DW_IC_CLR_RX_UNDER, &tmp);
- stat = i2c_dw_read_clear_intrbits_slave(dev);
- }
+ dev->status = STATUS_READ_IN_PROGRESS;
if (!i2c_slave_event(dev->slave,
I2C_SLAVE_READ_REQUESTED,
&val))
@@ -205,21 +202,11 @@
if (!i2c_slave_event(dev->slave, I2C_SLAVE_READ_PROCESSED,
&val))
regmap_read(dev->map, DW_IC_CLR_RX_DONE, &tmp);
-
- i2c_slave_event(dev->slave, I2C_SLAVE_STOP, &val);
- stat = i2c_dw_read_clear_intrbits_slave(dev);
- return 1;
}
- if (stat & DW_IC_INTR_RX_FULL) {
- regmap_read(dev->map, DW_IC_DATA_CMD, &tmp);
- val = tmp;
- if (!i2c_slave_event(dev->slave, I2C_SLAVE_WRITE_RECEIVED,
- &val))
- dev_vdbg(dev->dev, "Byte %X acked!", val);
- } else {
+ if (stat & DW_IC_INTR_STOP_DET) {
+ dev->status = STATUS_IDLE;
i2c_slave_event(dev->slave, I2C_SLAVE_STOP, &val);
- stat = i2c_dw_read_clear_intrbits_slave(dev);
}
return 1;
@@ -230,7 +217,6 @@
struct dw_i2c_dev *dev = dev_id;
int ret;
- i2c_dw_read_clear_intrbits_slave(dev);
ret = i2c_dw_irq_handler_slave(dev);
if (ret > 0)
complete(&dev->cmd_complete);
diff --git a/drivers/i2c/busses/i2c-mlxbf.c b/drivers/i2c/busses/i2c-mlxbf.c
index ee59e0d..33574d4 100644
--- a/drivers/i2c/busses/i2c-mlxbf.c
+++ b/drivers/i2c/busses/i2c-mlxbf.c
@@ -62,10 +62,8 @@
* Master. Default value is set to 400MHz.
*/
#define MLXBF_I2C_TYU_PLL_OUT_FREQ (400 * 1000 * 1000)
-/* Reference clock for Bluefield 1 - 156 MHz. */
-#define MLXBF_I2C_TYU_PLL_IN_FREQ (156 * 1000 * 1000)
-/* Reference clock for BlueField 2 - 200 MHz. */
-#define MLXBF_I2C_YU_PLL_IN_FREQ (200 * 1000 * 1000)
+/* Reference clock for Bluefield - 156 MHz. */
+#define MLXBF_I2C_PLL_IN_FREQ (156 * 1000 * 1000)
/* Constant used to determine the PLL frequency. */
#define MLNXBF_I2C_COREPLL_CONST 16384
@@ -489,44 +487,6 @@
#define MLXBF_I2C_FREQUENCY_1GHZ 1000000000
-static void mlxbf_i2c_write(void __iomem *io, int reg, u32 val)
-{
- writel(val, io + reg);
-}
-
-static u32 mlxbf_i2c_read(void __iomem *io, int reg)
-{
- return readl(io + reg);
-}
-
-/*
- * This function is used to read data from Master GW Data Descriptor.
- * Data bytes in the Master GW Data Descriptor are shifted left so the
- * data starts at the MSB of the descriptor registers as set by the
- * underlying hardware. TYU_READ_DATA enables byte swapping while
- * reading data bytes, and MUST be called by the SMBus read routines
- * to copy data from the 32 * 32-bit HW Data registers a.k.a Master GW
- * Data Descriptor.
- */
-static u32 mlxbf_i2c_read_data(void __iomem *io, int reg)
-{
- return (u32)be32_to_cpu(mlxbf_i2c_read(io, reg));
-}
-
-/*
- * This function is used to write data to the Master GW Data Descriptor.
- * Data copied to the Master GW Data Descriptor MUST be shifted left so
- * the data starts at the MSB of the descriptor registers as required by
- * the underlying hardware. TYU_WRITE_DATA enables byte swapping when
- * writing data bytes, and MUST be called by the SMBus write routines to
- * copy data to the 32 * 32-bit HW Data registers a.k.a Master GW Data
- * Descriptor.
- */
-static void mlxbf_i2c_write_data(void __iomem *io, int reg, u32 val)
-{
- mlxbf_i2c_write(io, reg, (u32)cpu_to_be32(val));
-}
-
/*
* Function to poll a set of bits at a specific address; it checks whether
* the bits are equal to zero when eq_zero is set to 'true', and not equal
@@ -541,7 +501,7 @@
timeout = (timeout / MLXBF_I2C_POLL_FREQ_IN_USEC) + 1;
do {
- bits = mlxbf_i2c_read(io, addr) & mask;
+ bits = readl(io + addr) & mask;
if (eq_zero ? bits == 0 : bits != 0)
return eq_zero ? 1 : bits;
udelay(MLXBF_I2C_POLL_FREQ_IN_USEC);
@@ -609,16 +569,16 @@
MLXBF_I2C_SMBUS_TIMEOUT);
/* Read cause status bits. */
- cause_status_bits = mlxbf_i2c_read(priv->mst_cause->io,
- MLXBF_I2C_CAUSE_ARBITER);
+ cause_status_bits = readl(priv->mst_cause->io +
+ MLXBF_I2C_CAUSE_ARBITER);
cause_status_bits &= MLXBF_I2C_CAUSE_MASTER_ARBITER_BITS_MASK;
/*
* Parse both Cause and Master GW bits, then return transaction status.
*/
- master_status_bits = mlxbf_i2c_read(priv->smbus->io,
- MLXBF_I2C_SMBUS_MASTER_STATUS);
+ master_status_bits = readl(priv->smbus->io +
+ MLXBF_I2C_SMBUS_MASTER_STATUS);
master_status_bits &= MLXBF_I2C_SMBUS_MASTER_STATUS_MASK;
if (mlxbf_i2c_smbus_transaction_success(master_status_bits,
@@ -649,10 +609,17 @@
aligned_length = round_up(length, 4);
- /* Copy data bytes from 4-byte aligned source buffer. */
+ /*
+ * Copy data bytes from 4-byte aligned source buffer.
+ * Data copied to the Master GW Data Descriptor MUST be shifted
+ * left so the data starts at the MSB of the descriptor registers
+ * as required by the underlying hardware. Enable byte swapping
+ * when writing data bytes to the 32 * 32-bit HW Data registers
+ * a.k.a Master GW Data Descriptor.
+ */
for (offset = 0; offset < aligned_length; offset += sizeof(u32)) {
data32 = *((u32 *)(data + offset));
- mlxbf_i2c_write_data(priv->smbus->io, addr + offset, data32);
+ iowrite32be(data32, priv->smbus->io + addr + offset);
}
}
@@ -664,15 +631,23 @@
mask = sizeof(u32) - 1;
+ /*
+ * Data bytes in the Master GW Data Descriptor are shifted left
+ * so the data starts at the MSB of the descriptor registers as
+ * set by the underlying hardware. Enable byte swapping while
+ * reading data bytes from the 32 * 32-bit HW Data registers
+ * a.k.a Master GW Data Descriptor.
+ */
+
for (offset = 0; offset < (length & ~mask); offset += sizeof(u32)) {
- data32 = mlxbf_i2c_read_data(priv->smbus->io, addr + offset);
+ data32 = ioread32be(priv->smbus->io + addr + offset);
*((u32 *)(data + offset)) = data32;
}
if (!(length & mask))
return;
- data32 = mlxbf_i2c_read_data(priv->smbus->io, addr + offset);
+ data32 = ioread32be(priv->smbus->io + addr + offset);
for (byte = 0; byte < (length & mask); byte++) {
data[offset + byte] = data32 & GENMASK(7, 0);
@@ -698,16 +673,16 @@
command |= rol32(pec_en, MLXBF_I2C_MASTER_SEND_PEC_SHIFT);
/* Clear status bits. */
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_STATUS, 0x0);
+ writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_STATUS);
/* Set the cause data. */
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_CAUSE_OR_CLEAR, ~0x0);
+ writel(~0x0, priv->smbus->io + MLXBF_I2C_CAUSE_OR_CLEAR);
/* Zero PEC byte. */
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_PEC, 0x0);
+ writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_PEC);
/* Zero byte count. */
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_RS_BYTES, 0x0);
+ writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_RS_BYTES);
/* GW activation. */
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_GW, command);
+ writel(command, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_GW);
/*
* Poll master status and check status bits. An ACK is sent when
@@ -823,8 +798,8 @@
* needs to be 'manually' reset. This should be removed in
* next tag integration.
*/
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_FSM,
- MLXBF_I2C_SMBUS_MASTER_FSM_PS_STATE_MASK);
+ writel(MLXBF_I2C_SMBUS_MASTER_FSM_PS_STATE_MASK,
+ priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_FSM);
}
return ret;
@@ -1113,8 +1088,8 @@
timer |= mlxbf_i2c_set_timer(priv, timings->scl_low,
false, MLXBF_I2C_MASK_16,
MLXBF_I2C_SHIFT_16);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_TIMER_SCL_LOW_SCL_HIGH,
- timer);
+ writel(timer, priv->smbus->io +
+ MLXBF_I2C_SMBUS_TIMER_SCL_LOW_SCL_HIGH);
timer = mlxbf_i2c_set_timer(priv, timings->sda_rise, false,
MLXBF_I2C_MASK_8, MLXBF_I2C_SHIFT_0);
@@ -1124,37 +1099,34 @@
MLXBF_I2C_MASK_8, MLXBF_I2C_SHIFT_16);
timer |= mlxbf_i2c_set_timer(priv, timings->scl_fall, false,
MLXBF_I2C_MASK_8, MLXBF_I2C_SHIFT_24);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_TIMER_FALL_RISE_SPIKE,
- timer);
+ writel(timer, priv->smbus->io +
+ MLXBF_I2C_SMBUS_TIMER_FALL_RISE_SPIKE);
timer = mlxbf_i2c_set_timer(priv, timings->hold_start, true,
MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_0);
timer |= mlxbf_i2c_set_timer(priv, timings->hold_data, true,
MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_16);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_TIMER_THOLD, timer);
+ writel(timer, priv->smbus->io + MLXBF_I2C_SMBUS_TIMER_THOLD);
timer = mlxbf_i2c_set_timer(priv, timings->setup_start, true,
MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_0);
timer |= mlxbf_i2c_set_timer(priv, timings->setup_stop, true,
MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_16);
- mlxbf_i2c_write(priv->smbus->io,
- MLXBF_I2C_SMBUS_TIMER_TSETUP_START_STOP, timer);
+ writel(timer, priv->smbus->io +
+ MLXBF_I2C_SMBUS_TIMER_TSETUP_START_STOP);
timer = mlxbf_i2c_set_timer(priv, timings->setup_data, true,
MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_0);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_TIMER_TSETUP_DATA,
- timer);
+ writel(timer, priv->smbus->io + MLXBF_I2C_SMBUS_TIMER_TSETUP_DATA);
timer = mlxbf_i2c_set_timer(priv, timings->buf, false,
MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_0);
timer |= mlxbf_i2c_set_timer(priv, timings->thigh_max, false,
MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_16);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_THIGH_MAX_TBUF,
- timer);
+ writel(timer, priv->smbus->io + MLXBF_I2C_SMBUS_THIGH_MAX_TBUF);
timer = timings->timeout;
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SCL_LOW_TIMEOUT,
- timer);
+ writel(timer, priv->smbus->io + MLXBF_I2C_SMBUS_SCL_LOW_TIMEOUT);
}
enum mlxbf_i2c_timings_config {
@@ -1426,19 +1398,15 @@
* platform firmware; disabling the bus might compromise the system
* functionality.
*/
- config_reg = mlxbf_i2c_read(gpio_res->io,
- MLXBF_I2C_GPIO_0_FUNC_EN_0);
+ config_reg = readl(gpio_res->io + MLXBF_I2C_GPIO_0_FUNC_EN_0);
config_reg = MLXBF_I2C_GPIO_SMBUS_GW_ASSERT_PINS(priv->bus,
config_reg);
- mlxbf_i2c_write(gpio_res->io, MLXBF_I2C_GPIO_0_FUNC_EN_0,
- config_reg);
+ writel(config_reg, gpio_res->io + MLXBF_I2C_GPIO_0_FUNC_EN_0);
- config_reg = mlxbf_i2c_read(gpio_res->io,
- MLXBF_I2C_GPIO_0_FORCE_OE_EN);
+ config_reg = readl(gpio_res->io + MLXBF_I2C_GPIO_0_FORCE_OE_EN);
config_reg = MLXBF_I2C_GPIO_SMBUS_GW_RESET_PINS(priv->bus,
config_reg);
- mlxbf_i2c_write(gpio_res->io, MLXBF_I2C_GPIO_0_FORCE_OE_EN,
- config_reg);
+ writel(config_reg, gpio_res->io + MLXBF_I2C_GPIO_0_FORCE_OE_EN);
mutex_unlock(gpio_res->lock);
@@ -1452,10 +1420,9 @@
u32 corepll_val;
u16 core_f;
- pad_frequency = MLXBF_I2C_TYU_PLL_IN_FREQ;
+ pad_frequency = MLXBF_I2C_PLL_IN_FREQ;
- corepll_val = mlxbf_i2c_read(corepll_res->io,
- MLXBF_I2C_CORE_PLL_REG1);
+ corepll_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG1);
/* Get Core PLL configuration bits. */
core_f = rol32(corepll_val, MLXBF_I2C_COREPLL_CORE_F_TYU_SHIFT) &
@@ -1488,12 +1455,10 @@
u8 core_od, core_r;
u32 core_f;
- pad_frequency = MLXBF_I2C_YU_PLL_IN_FREQ;
+ pad_frequency = MLXBF_I2C_PLL_IN_FREQ;
- corepll_reg1_val = mlxbf_i2c_read(corepll_res->io,
- MLXBF_I2C_CORE_PLL_REG1);
- corepll_reg2_val = mlxbf_i2c_read(corepll_res->io,
- MLXBF_I2C_CORE_PLL_REG2);
+ corepll_reg1_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG1);
+ corepll_reg2_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG2);
/* Get Core PLL configuration bits */
core_f = rol32(corepll_reg1_val, MLXBF_I2C_COREPLL_CORE_F_YU_SHIFT) &
@@ -1585,7 +1550,7 @@
* (7-bit address, 1 status bit (1 if enabled, 0 if not)).
*/
for (reg = 0; reg < reg_cnt; reg++) {
- slave_reg = mlxbf_i2c_read(priv->smbus->io,
+ slave_reg = readl(priv->smbus->io +
MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + reg * 0x4);
/*
* Each register holds 4 slave addresses. So, we have to keep
@@ -1643,8 +1608,8 @@
/* Enable the slave address and update the register. */
slave_reg |= (1 << MLXBF_I2C_SMBUS_SLAVE_ADDR_EN_BIT) << (byte * 8);
- mlxbf_i2c_write(priv->smbus->io,
- MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + reg * 0x4, slave_reg);
+ writel(slave_reg, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG +
+ reg * 0x4);
return 0;
}
@@ -1668,7 +1633,7 @@
* (7-bit address, 1 status bit (1 if enabled, 0 if not)).
*/
for (reg = 0; reg < reg_cnt; reg++) {
- slave_reg = mlxbf_i2c_read(priv->smbus->io,
+ slave_reg = readl(priv->smbus->io +
MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + reg * 0x4);
/* Check whether the address slots are empty. */
@@ -1708,8 +1673,8 @@
/* Cleanup the slave address slot. */
slave_reg &= ~(GENMASK(7, 0) << (slave_byte * 8));
- mlxbf_i2c_write(priv->smbus->io,
- MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + reg * 0x4, slave_reg);
+ writel(slave_reg, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG +
+ reg * 0x4);
return 0;
}
@@ -1801,7 +1766,7 @@
int ret;
/* Reset FSM. */
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_FSM, 0);
+ writel(0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_FSM);
/*
* Enable slave cause interrupt bits. Drive
@@ -1810,15 +1775,13 @@
* masters issue a Read and Write, respectively. But, clear all
* interrupts first.
*/
- mlxbf_i2c_write(priv->slv_cause->io,
- MLXBF_I2C_CAUSE_OR_CLEAR, ~0);
+ writel(~0, priv->slv_cause->io + MLXBF_I2C_CAUSE_OR_CLEAR);
int_reg = MLXBF_I2C_CAUSE_READ_WAIT_FW_RESPONSE;
int_reg |= MLXBF_I2C_CAUSE_WRITE_SUCCESS;
- mlxbf_i2c_write(priv->slv_cause->io,
- MLXBF_I2C_CAUSE_OR_EVTEN0, int_reg);
+ writel(int_reg, priv->slv_cause->io + MLXBF_I2C_CAUSE_OR_EVTEN0);
/* Finally, set the 'ready' bit to start handling transactions. */
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_READY, 0x1);
+ writel(0x1, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_READY);
/* Initialize the cause coalesce resource. */
ret = mlxbf_i2c_init_coalesce(pdev, priv);
@@ -1844,23 +1807,21 @@
MLXBF_I2C_CAUSE_YU_SLAVE_BIT :
priv->bus + MLXBF_I2C_CAUSE_TYU_SLAVE_BIT;
- coalesce0_reg = mlxbf_i2c_read(priv->coalesce->io,
- MLXBF_I2C_CAUSE_COALESCE_0);
+ coalesce0_reg = readl(priv->coalesce->io + MLXBF_I2C_CAUSE_COALESCE_0);
is_set = coalesce0_reg & (1 << slave_shift);
if (!is_set)
return false;
/* Check the source of the interrupt, i.e. whether a Read or Write. */
- cause_reg = mlxbf_i2c_read(priv->slv_cause->io,
- MLXBF_I2C_CAUSE_ARBITER);
+ cause_reg = readl(priv->slv_cause->io + MLXBF_I2C_CAUSE_ARBITER);
if (cause_reg & MLXBF_I2C_CAUSE_READ_WAIT_FW_RESPONSE)
*read = true;
else if (cause_reg & MLXBF_I2C_CAUSE_WRITE_SUCCESS)
*write = true;
/* Clear cause bits. */
- mlxbf_i2c_write(priv->slv_cause->io, MLXBF_I2C_CAUSE_OR_CLEAR, ~0x0);
+ writel(~0x0, priv->slv_cause->io + MLXBF_I2C_CAUSE_OR_CLEAR);
return true;
}
@@ -1900,8 +1861,8 @@
* address, if supplied.
*/
if (recv_bytes > 0) {
- data32 = mlxbf_i2c_read_data(priv->smbus->io,
- MLXBF_I2C_SLAVE_DATA_DESC_ADDR);
+ data32 = ioread32be(priv->smbus->io +
+ MLXBF_I2C_SLAVE_DATA_DESC_ADDR);
/* Parse the received bytes. */
switch (recv_bytes) {
@@ -1966,7 +1927,7 @@
control32 |= rol32(write_size, MLXBF_I2C_SLAVE_WRITE_BYTES_SHIFT);
control32 |= rol32(pec_en, MLXBF_I2C_SLAVE_SEND_PEC_SHIFT);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_GW, control32);
+ writel(control32, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_GW);
/*
* Wait until the transfer is completed; the driver will wait
@@ -1975,10 +1936,9 @@
mlxbf_smbus_slave_wait_for_idle(priv, MLXBF_I2C_SMBUS_TIMEOUT);
/* Release the Slave GW. */
- mlxbf_i2c_write(priv->smbus->io,
- MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES, 0x0);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_PEC, 0x0);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_READY, 0x1);
+ writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES);
+ writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_PEC);
+ writel(0x1, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_READY);
return 0;
}
@@ -2023,10 +1983,9 @@
i2c_slave_event(slave, I2C_SLAVE_STOP, &value);
/* Release the Slave GW. */
- mlxbf_i2c_write(priv->smbus->io,
- MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES, 0x0);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_PEC, 0x0);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_READY, 0x1);
+ writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES);
+ writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_PEC);
+ writel(0x1, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_READY);
return ret;
}
@@ -2061,8 +2020,8 @@
* slave, if the higher 8 bits are sent then the slave expect N bytes
* from the master.
*/
- rw_bytes_reg = mlxbf_i2c_read(priv->smbus->io,
- MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES);
+ rw_bytes_reg = readl(priv->smbus->io +
+ MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES);
recv_bytes = (rw_bytes_reg >> 8) & GENMASK(7, 0);
/*
@@ -2264,6 +2223,7 @@
MODULE_DEVICE_TABLE(of, mlxbf_i2c_dt_ids);
+#ifdef CONFIG_ACPI
static const struct acpi_device_id mlxbf_i2c_acpi_ids[] = {
{ "MLNXBF03", (kernel_ulong_t)&mlxbf_i2c_chip[MLXBF_I2C_CHIP_TYPE_1] },
{ "MLNXBF23", (kernel_ulong_t)&mlxbf_i2c_chip[MLXBF_I2C_CHIP_TYPE_2] },
@@ -2305,6 +2265,12 @@
return ret;
}
+#else
+static int mlxbf_i2c_acpi_probe(struct device *dev, struct mlxbf_i2c_priv *priv)
+{
+ return -ENOENT;
+}
+#endif /* CONFIG_ACPI */
static int mlxbf_i2c_of_probe(struct device *dev, struct mlxbf_i2c_priv *priv)
{
@@ -2473,7 +2439,9 @@
.driver = {
.name = "i2c-mlxbf",
.of_match_table = mlxbf_i2c_dt_ids,
+#ifdef CONFIG_ACPI
.acpi_match_table = ACPI_PTR(mlxbf_i2c_acpi_ids),
+#endif /* CONFIG_ACPI */
},
};
@@ -2502,5 +2470,5 @@
module_exit(mlxbf_i2c_exit);
MODULE_DESCRIPTION("Mellanox BlueField I2C bus driver");
-MODULE_AUTHOR("Khalil Blaiech <kblaiech@mellanox.com>");
+MODULE_AUTHOR("Khalil Blaiech <kblaiech@nvidia.com>");
MODULE_LICENSE("GPL v2");
diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c
index 0cbdfbe..33de99b 100644
--- a/drivers/i2c/busses/i2c-mt65xx.c
+++ b/drivers/i2c/busses/i2c-mt65xx.c
@@ -475,6 +475,10 @@
{
u16 control_reg;
+ writel(I2C_DMA_HARD_RST, i2c->pdmabase + OFFSET_RST);
+ udelay(50);
+ writel(I2C_DMA_CLR_FLAG, i2c->pdmabase + OFFSET_RST);
+
mtk_i2c_writew(i2c, I2C_SOFT_RST, OFFSET_SOFTRESET);
/* Set ioconfig */
@@ -529,10 +533,6 @@
mtk_i2c_writew(i2c, control_reg, OFFSET_CONTROL);
mtk_i2c_writew(i2c, I2C_DELAY_LEN, OFFSET_DELAY_LEN);
-
- writel(I2C_DMA_HARD_RST, i2c->pdmabase + OFFSET_RST);
- udelay(50);
- writel(I2C_DMA_CLR_FLAG, i2c->pdmabase + OFFSET_RST);
}
static const struct i2c_spec_values *mtk_i2c_get_spec(unsigned int speed)
diff --git a/drivers/i2c/busses/i2c-sh_mobile.c b/drivers/i2c/busses/i2c-sh_mobile.c
index cab7255..bdd60770 100644
--- a/drivers/i2c/busses/i2c-sh_mobile.c
+++ b/drivers/i2c/busses/i2c-sh_mobile.c
@@ -129,6 +129,7 @@
int sr;
bool send_stop;
bool stop_after_dma;
+ bool atomic_xfer;
struct resource *res;
struct dma_chan *dma_tx;
@@ -330,13 +331,15 @@
ret = iic_rd(pd, ICDR);
break;
case OP_RX_STOP: /* enable DTE interrupt, issue stop */
- iic_wr(pd, ICIC,
- ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE);
+ if (!pd->atomic_xfer)
+ iic_wr(pd, ICIC,
+ ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE);
iic_wr(pd, ICCR, ICCR_ICE | ICCR_RACK);
break;
case OP_RX_STOP_DATA: /* enable DTE interrupt, read data, issue stop */
- iic_wr(pd, ICIC,
- ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE);
+ if (!pd->atomic_xfer)
+ iic_wr(pd, ICIC,
+ ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE);
ret = iic_rd(pd, ICDR);
iic_wr(pd, ICCR, ICCR_ICE | ICCR_RACK);
break;
@@ -429,7 +432,8 @@
if (wakeup) {
pd->sr |= SW_DONE;
- wake_up(&pd->wait);
+ if (!pd->atomic_xfer)
+ wake_up(&pd->wait);
}
/* defeat write posting to avoid spurious WAIT interrupts */
@@ -581,6 +585,9 @@
pd->pos = -1;
pd->sr = 0;
+ if (pd->atomic_xfer)
+ return;
+
pd->dma_buf = i2c_get_dma_safe_msg_buf(pd->msg, 8);
if (pd->dma_buf)
sh_mobile_i2c_xfer_dma(pd);
@@ -637,15 +644,13 @@
return i ? 0 : -ETIMEDOUT;
}
-static int sh_mobile_i2c_xfer(struct i2c_adapter *adapter,
- struct i2c_msg *msgs,
- int num)
+static int sh_mobile_xfer(struct sh_mobile_i2c_data *pd,
+ struct i2c_msg *msgs, int num)
{
- struct sh_mobile_i2c_data *pd = i2c_get_adapdata(adapter);
struct i2c_msg *msg;
int err = 0;
int i;
- long timeout;
+ long time_left;
/* Wake up device and enable clock */
pm_runtime_get_sync(pd->dev);
@@ -662,15 +667,35 @@
if (do_start)
i2c_op(pd, OP_START);
- /* The interrupt handler takes care of the rest... */
- timeout = wait_event_timeout(pd->wait,
- pd->sr & (ICSR_TACK | SW_DONE),
- adapter->timeout);
+ if (pd->atomic_xfer) {
+ unsigned long j = jiffies + pd->adap.timeout;
- /* 'stop_after_dma' tells if DMA transfer was complete */
- i2c_put_dma_safe_msg_buf(pd->dma_buf, pd->msg, pd->stop_after_dma);
+ time_left = time_before_eq(jiffies, j);
+ while (time_left &&
+ !(pd->sr & (ICSR_TACK | SW_DONE))) {
+ unsigned char sr = iic_rd(pd, ICSR);
- if (!timeout) {
+ if (sr & (ICSR_AL | ICSR_TACK |
+ ICSR_WAIT | ICSR_DTE)) {
+ sh_mobile_i2c_isr(0, pd);
+ udelay(150);
+ } else {
+ cpu_relax();
+ }
+ time_left = time_before_eq(jiffies, j);
+ }
+ } else {
+ /* The interrupt handler takes care of the rest... */
+ time_left = wait_event_timeout(pd->wait,
+ pd->sr & (ICSR_TACK | SW_DONE),
+ pd->adap.timeout);
+
+ /* 'stop_after_dma' tells if DMA xfer was complete */
+ i2c_put_dma_safe_msg_buf(pd->dma_buf, pd->msg,
+ pd->stop_after_dma);
+ }
+
+ if (!time_left) {
dev_err(pd->dev, "Transfer request timed out\n");
if (pd->dma_direction != DMA_NONE)
sh_mobile_i2c_cleanup_dma(pd);
@@ -696,14 +721,35 @@
return err ?: num;
}
+static int sh_mobile_i2c_xfer(struct i2c_adapter *adapter,
+ struct i2c_msg *msgs,
+ int num)
+{
+ struct sh_mobile_i2c_data *pd = i2c_get_adapdata(adapter);
+
+ pd->atomic_xfer = false;
+ return sh_mobile_xfer(pd, msgs, num);
+}
+
+static int sh_mobile_i2c_xfer_atomic(struct i2c_adapter *adapter,
+ struct i2c_msg *msgs,
+ int num)
+{
+ struct sh_mobile_i2c_data *pd = i2c_get_adapdata(adapter);
+
+ pd->atomic_xfer = true;
+ return sh_mobile_xfer(pd, msgs, num);
+}
+
static u32 sh_mobile_i2c_func(struct i2c_adapter *adapter)
{
return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_PROTOCOL_MANGLING;
}
static const struct i2c_algorithm sh_mobile_i2c_algorithm = {
- .functionality = sh_mobile_i2c_func,
- .master_xfer = sh_mobile_i2c_xfer,
+ .functionality = sh_mobile_i2c_func,
+ .master_xfer = sh_mobile_i2c_xfer,
+ .master_xfer_atomic = sh_mobile_i2c_xfer_atomic,
};
static const struct i2c_adapter_quirks sh_mobile_i2c_quirks = {
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 56f5b80..01bace4 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -1239,7 +1239,7 @@
struct acpi_processor_cx *cx;
struct cpuidle_state *state;
- if (intel_idle_max_cstate_reached(cstate))
+ if (intel_idle_max_cstate_reached(cstate - 1))
break;
cx = &acpi_state_table.states[cstate];
diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 32a5143..9325e18 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -73,6 +73,9 @@
This allows the user to config the default GID type that the CM
uses for each device, when initiaing new connections.
+config INFINIBAND_VIRT_DMA
+ def_bool !HIGHMEM
+
if INFINIBAND_USER_ACCESS || !INFINIBAND_USER_ACCESS
source "drivers/infiniband/hw/mthca/Kconfig"
source "drivers/infiniband/hw/qib/Kconfig"
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 5740d1b..01215662 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -859,8 +859,8 @@
atomic_set(&cm_id_priv->work_count, -1);
refcount_set(&cm_id_priv->refcount, 1);
- ret = xa_alloc_cyclic_irq(&cm.local_id_table, &id, NULL, xa_limit_32b,
- &cm.local_id_next, GFP_KERNEL);
+ ret = xa_alloc_cyclic(&cm.local_id_table, &id, NULL, xa_limit_32b,
+ &cm.local_id_next, GFP_KERNEL);
if (ret < 0)
goto error;
cm_id_priv->id.local_id = (__force __be32)id ^ cm.random_id_operand;
@@ -878,8 +878,8 @@
*/
static void cm_finalize_id(struct cm_id_private *cm_id_priv)
{
- xa_store_irq(&cm.local_id_table, cm_local_id(cm_id_priv->id.local_id),
- cm_id_priv, GFP_KERNEL);
+ xa_store(&cm.local_id_table, cm_local_id(cm_id_priv->id.local_id),
+ cm_id_priv, GFP_ATOMIC);
}
struct ib_cm_id *ib_create_cm_id(struct ib_device *device,
@@ -1169,7 +1169,7 @@
spin_unlock(&cm.lock);
spin_unlock_irq(&cm_id_priv->lock);
- xa_erase_irq(&cm.local_id_table, cm_local_id(cm_id->local_id));
+ xa_erase(&cm.local_id_table, cm_local_id(cm_id->local_id));
cm_deref_id(cm_id_priv);
wait_for_completion(&cm_id_priv->comp);
while ((work = cm_dequeue_work(cm_id_priv)) != NULL)
@@ -4482,7 +4482,7 @@
cm.remote_id_table = RB_ROOT;
cm.remote_qp_table = RB_ROOT;
cm.remote_sidr_table = RB_ROOT;
- xa_init_flags(&cm.local_id_table, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
+ xa_init_flags(&cm.local_id_table, XA_FLAGS_ALLOC);
get_random_bytes(&cm.random_id_operand, sizeof cm.random_id_operand);
INIT_LIST_HEAD(&cm.timewait_list);
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 7c2ab1f..a77750b 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -405,10 +405,10 @@
/*
* The FSM uses a funny double locking where state is protected by both
* the handler_mutex and the spinlock. State is not allowed to change
- * away from a handler_mutex protected value without also holding
+ * to/from a handler_mutex protected value without also holding
* handler_mutex.
*/
- if (comp == RDMA_CM_CONNECT)
+ if (comp == RDMA_CM_CONNECT || exch == RDMA_CM_CONNECT)
lockdep_assert_held(&id_priv->handler_mutex);
spin_lock_irqsave(&id_priv->lock, flags);
@@ -4038,17 +4038,23 @@
return ret;
}
-int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
+/**
+ * rdma_connect_locked - Initiate an active connection request.
+ * @id: Connection identifier to connect.
+ * @conn_param: Connection information used for connected QPs.
+ *
+ * Same as rdma_connect() but can only be called from the
+ * RDMA_CM_EVENT_ROUTE_RESOLVED handler callback.
+ */
+int rdma_connect_locked(struct rdma_cm_id *id,
+ struct rdma_conn_param *conn_param)
{
struct rdma_id_private *id_priv =
container_of(id, struct rdma_id_private, id);
int ret;
- mutex_lock(&id_priv->handler_mutex);
- if (!cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_CONNECT)) {
- ret = -EINVAL;
- goto err_unlock;
- }
+ if (!cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_CONNECT))
+ return -EINVAL;
if (!id->qp) {
id_priv->qp_num = conn_param->qp_num;
@@ -4066,11 +4072,33 @@
ret = -ENOSYS;
if (ret)
goto err_state;
- mutex_unlock(&id_priv->handler_mutex);
return 0;
err_state:
cma_comp_exch(id_priv, RDMA_CM_CONNECT, RDMA_CM_ROUTE_RESOLVED);
-err_unlock:
+ return ret;
+}
+EXPORT_SYMBOL(rdma_connect_locked);
+
+/**
+ * rdma_connect - Initiate an active connection request.
+ * @id: Connection identifier to connect.
+ * @conn_param: Connection information used for connected QPs.
+ *
+ * Users must have resolved a route for the rdma_cm_id to connect with by having
+ * called rdma_resolve_route before calling this routine.
+ *
+ * This call will either connect to a remote QP or obtain remote QP information
+ * for unconnected rdma_cm_id's. The actual operation is based on the
+ * rdma_cm_id's port space.
+ */
+int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
+{
+ struct rdma_id_private *id_priv =
+ container_of(id, struct rdma_id_private, id);
+ int ret;
+
+ mutex_lock(&id_priv->handler_mutex);
+ ret = rdma_connect_locked(id, conn_param);
mutex_unlock(&id_priv->handler_mutex);
return ret;
}
diff --git a/drivers/infiniband/core/uverbs_std_types_device.c b/drivers/infiniband/core/uverbs_std_types_device.c
index f367d52..302f898 100644
--- a/drivers/infiniband/core/uverbs_std_types_device.c
+++ b/drivers/infiniband/core/uverbs_std_types_device.c
@@ -401,9 +401,6 @@
if (!rdma_is_port_valid(ib_dev, port_num))
return -EINVAL;
- if (!rdma_ib_or_roce(ib_dev, port_num))
- return -EOPNOTSUPP;
-
gid_attr = rdma_get_gid_attr(ib_dev, port_num, gid_index);
if (IS_ERR(gid_attr))
return PTR_ERR(gid_attr);
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 7eaf9953..c87b94e 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -15245,7 +15245,8 @@
& CCE_REVISION_SW_MASK);
/* alloc netdev data */
- if (hfi1_netdev_alloc(dd))
+ ret = hfi1_netdev_alloc(dd);
+ if (ret)
goto bail_cleanup;
ret = set_up_context_variables(dd);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 89e04ca..246e3cb 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3305,7 +3305,8 @@
int err;
dev->port[port_num].roce.nb.notifier_call = mlx5_netdev_event;
- err = register_netdevice_notifier(&dev->port[port_num].roce.nb);
+ err = register_netdevice_notifier_net(mlx5_core_net(dev->mdev),
+ &dev->port[port_num].roce.nb);
if (err) {
dev->port[port_num].roce.nb.notifier_call = NULL;
return err;
@@ -3317,7 +3318,8 @@
static void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
{
if (dev->port[port_num].roce.nb.notifier_call) {
- unregister_netdevice_notifier(&dev->port[port_num].roce.nb);
+ unregister_netdevice_notifier_net(mlx5_core_net(dev->mdev),
+ &dev->port[port_num].roce.nb);
dev->port[port_num].roce.nb.notifier_call = NULL;
}
}
diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c
index c7169d2..c4bc587 100644
--- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c
+++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c
@@ -727,6 +727,7 @@
listener->qed_handle);
cm_id->rem_ref(cm_id);
+ kfree(listener);
return rc;
}
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
index fa2a3fa..6895bac 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
@@ -266,7 +266,7 @@
}
ret = ib_device_set_netdev(&dev->ib_dev, dev->netdev, 1);
if (ret)
- return ret;
+ goto err_srq_free;
spin_lock_init(&dev->srq_tbl_lock);
rdma_set_device_sysfs_group(&dev->ib_dev, &pvrdma_attr_group);
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
index f0e5ffb..97ed8f9 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
@@ -176,7 +176,7 @@
u8 subnet_timeout;
u8 init_type_reply;
u8 active_width;
- u16 active_speed;
+ u8 active_speed;
u8 phys_state;
u8 reserved[2];
};
diff --git a/drivers/infiniband/sw/rdmavt/Kconfig b/drivers/infiniband/sw/rdmavt/Kconfig
index 9ef5f5c..c8e2680 100644
--- a/drivers/infiniband/sw/rdmavt/Kconfig
+++ b/drivers/infiniband/sw/rdmavt/Kconfig
@@ -1,7 +1,8 @@
# SPDX-License-Identifier: GPL-2.0-only
config INFINIBAND_RDMAVT
tristate "RDMA verbs transport library"
- depends on X86_64 && ARCH_DMA_ADDR_T_64BIT
+ depends on INFINIBAND_VIRT_DMA
+ depends on X86_64
depends on PCI
select DMA_VIRT_OPS
help
diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c
index 5221868..670a9623 100644
--- a/drivers/infiniband/sw/rdmavt/vt.c
+++ b/drivers/infiniband/sw/rdmavt/vt.c
@@ -524,6 +524,7 @@
int rvt_register_device(struct rvt_dev_info *rdi)
{
int ret = 0, i;
+ u64 dma_mask;
if (!rdi)
return -EINVAL;
@@ -580,8 +581,10 @@
/* DMA Operations */
rdi->ibdev.dev.dma_parms = rdi->ibdev.dev.parent->dma_parms;
- dma_set_coherent_mask(&rdi->ibdev.dev,
- rdi->ibdev.dev.parent->coherent_dma_mask);
+ dma_mask = IS_ENABLED(CONFIG_64BIT) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32);
+ ret = dma_coerce_mask_and_coherent(&rdi->ibdev.dev, dma_mask);
+ if (ret)
+ goto bail_wss;
/* Protection Domain */
spin_lock_init(&rdi->n_pds_lock);
diff --git a/drivers/infiniband/sw/rxe/Kconfig b/drivers/infiniband/sw/rxe/Kconfig
index a0c6c7df..8810bfa 100644
--- a/drivers/infiniband/sw/rxe/Kconfig
+++ b/drivers/infiniband/sw/rxe/Kconfig
@@ -2,7 +2,7 @@
config RDMA_RXE
tristate "Software RDMA over Ethernet (RoCE) driver"
depends on INET && PCI && INFINIBAND
- depends on !64BIT || ARCH_DMA_ADDR_T_64BIT
+ depends on INFINIBAND_VIRT_DMA
select NET_UDP_TUNNEL
select CRYPTO_CRC32
select DMA_VIRT_OPS
diff --git a/drivers/infiniband/sw/rxe/rxe_av.c b/drivers/infiniband/sw/rxe/rxe_av.c
index 38021e2..df0d173 100644
--- a/drivers/infiniband/sw/rxe/rxe_av.c
+++ b/drivers/infiniband/sw/rxe/rxe_av.c
@@ -16,15 +16,24 @@
int rxe_av_chk_attr(struct rxe_dev *rxe, struct rdma_ah_attr *attr)
{
+ const struct ib_global_route *grh = rdma_ah_read_grh(attr);
struct rxe_port *port;
+ int type;
port = &rxe->port;
if (rdma_ah_get_ah_flags(attr) & IB_AH_GRH) {
- u8 sgid_index = rdma_ah_read_grh(attr)->sgid_index;
+ if (grh->sgid_index > port->attr.gid_tbl_len) {
+ pr_warn("invalid sgid index = %d\n",
+ grh->sgid_index);
+ return -EINVAL;
+ }
- if (sgid_index > port->attr.gid_tbl_len) {
- pr_warn("invalid sgid index = %d\n", sgid_index);
+ type = rdma_gid_attr_network_type(grh->sgid_attr);
+ if (type < RDMA_NETWORK_IPV4 ||
+ type > RDMA_NETWORK_IPV6) {
+ pr_warn("invalid network type for rdma_rxe = %d\n",
+ type);
return -EINVAL;
}
}
@@ -65,11 +74,29 @@
void rxe_av_fill_ip_info(struct rxe_av *av, struct rdma_ah_attr *attr)
{
const struct ib_gid_attr *sgid_attr = attr->grh.sgid_attr;
+ int ibtype;
+ int type;
rdma_gid2ip((struct sockaddr *)&av->sgid_addr, &sgid_attr->gid);
rdma_gid2ip((struct sockaddr *)&av->dgid_addr,
&rdma_ah_read_grh(attr)->dgid);
- av->network_type = rdma_gid_attr_network_type(sgid_attr);
+
+ ibtype = rdma_gid_attr_network_type(sgid_attr);
+
+ switch (ibtype) {
+ case RDMA_NETWORK_IPV4:
+ type = RXE_NETWORK_TYPE_IPV4;
+ break;
+ case RDMA_NETWORK_IPV6:
+ type = RXE_NETWORK_TYPE_IPV4;
+ break;
+ default:
+ /* not reached - checked in rxe_av_chk_attr */
+ type = 0;
+ break;
+ }
+
+ av->network_type = type;
}
struct rxe_av *rxe_get_av(struct rxe_pkt_info *pkt)
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 575e1a4..34bef7d 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -442,7 +442,7 @@
if (IS_ERR(attr))
return NULL;
- if (av->network_type == RXE_NETWORK_TYPE_IPV6)
+ if (av->network_type == RXE_NETWORK_TYPE_IPV4)
hdr_len = ETH_HLEN + sizeof(struct udphdr) +
sizeof(struct iphdr);
else
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 1fc0223..f9c832e 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -1118,6 +1118,7 @@
int err;
struct ib_device *dev = &rxe->ib_dev;
struct crypto_shash *tfm;
+ u64 dma_mask;
strlcpy(dev->node_desc, "rxe", sizeof(dev->node_desc));
@@ -1130,7 +1131,10 @@
rxe->ndev->dev_addr);
dev->dev.dma_parms = &rxe->dma_parms;
dma_set_max_seg_size(&dev->dev, UINT_MAX);
- dma_set_coherent_mask(&dev->dev, dma_get_required_mask(&dev->dev));
+ dma_mask = IS_ENABLED(CONFIG_64BIT) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32);
+ err = dma_coerce_mask_and_coherent(&dev->dev, dma_mask);
+ if (err)
+ return err;
dev->uverbs_cmd_mask = BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT)
| BIT_ULL(IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL)
diff --git a/drivers/infiniband/sw/siw/Kconfig b/drivers/infiniband/sw/siw/Kconfig
index b622fc6..3450ba5 100644
--- a/drivers/infiniband/sw/siw/Kconfig
+++ b/drivers/infiniband/sw/siw/Kconfig
@@ -1,6 +1,7 @@
config RDMA_SIW
tristate "Software RDMA over TCP/IP (iWARP) driver"
depends on INET && INFINIBAND && LIBCRC32C
+ depends on INFINIBAND_VIRT_DMA
select DMA_VIRT_OPS
help
This driver implements the iWARP RDMA transport over
diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c
index ca8bc72..181e06c 100644
--- a/drivers/infiniband/sw/siw/siw_main.c
+++ b/drivers/infiniband/sw/siw/siw_main.c
@@ -306,6 +306,7 @@
struct siw_device *sdev = NULL;
struct ib_device *base_dev;
struct device *parent = netdev->dev.parent;
+ u64 dma_mask;
int rv;
if (!parent) {
@@ -384,8 +385,10 @@
base_dev->dev.parent = parent;
base_dev->dev.dma_parms = &sdev->dma_parms;
dma_set_max_seg_size(&base_dev->dev, UINT_MAX);
- dma_set_coherent_mask(&base_dev->dev,
- dma_get_required_mask(&base_dev->dev));
+ dma_mask = IS_ENABLED(CONFIG_64BIT) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32);
+ if (dma_coerce_mask_and_coherent(&base_dev->dev, dma_mask))
+ goto error;
+
base_dev->num_comp_vectors = num_possible_cpus();
xa_init_flags(&sdev->qp_xa, XA_FLAGS_ALLOC1);
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 2f3ebc0..2bd18b0 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -620,7 +620,7 @@
conn_param.private_data = (void *)&req_hdr;
conn_param.private_data_len = sizeof(struct iser_cm_hdr);
- ret = rdma_connect(cma_id, &conn_param);
+ ret = rdma_connect_locked(cma_id, &conn_param);
if (ret) {
iser_err("failure connecting: %d\n", ret);
goto failure;
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index 776e892..f298adc 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -1674,9 +1674,9 @@
uuid_copy(&msg.sess_uuid, &sess->s.uuid);
uuid_copy(&msg.paths_uuid, &clt->paths_uuid);
- err = rdma_connect(con->c.cm_id, ¶m);
+ err = rdma_connect_locked(con->c.cm_id, ¶m);
if (err)
- rtrs_err(clt, "rdma_connect(): %d\n", err);
+ rtrs_err(clt, "rdma_connect_locked(): %d\n", err);
return err;
}
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 0065eb1..53a8bec 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -622,10 +622,11 @@
/**
* srpt_unregister_mad_agent - unregister MAD callback functions
* @sdev: SRPT HCA pointer.
+ * @port_cnt: number of ports with registered MAD
*
* Note: It is safe to call this function more than once for the same device.
*/
-static void srpt_unregister_mad_agent(struct srpt_device *sdev)
+static void srpt_unregister_mad_agent(struct srpt_device *sdev, int port_cnt)
{
struct ib_port_modify port_modify = {
.clr_port_cap_mask = IB_PORT_DEVICE_MGMT_SUP,
@@ -633,7 +634,7 @@
struct srpt_port *sport;
int i;
- for (i = 1; i <= sdev->device->phys_port_cnt; i++) {
+ for (i = 1; i <= port_cnt; i++) {
sport = &sdev->port[i - 1];
WARN_ON(sport->port != i);
if (sport->mad_agent) {
@@ -3185,7 +3186,8 @@
if (ret) {
pr_err("MAD registration failed for %s-%d.\n",
dev_name(&sdev->device->dev), i);
- goto err_event;
+ i--;
+ goto err_port;
}
}
@@ -3197,7 +3199,8 @@
pr_debug("added %s.\n", dev_name(&device->dev));
return 0;
-err_event:
+err_port:
+ srpt_unregister_mad_agent(sdev, i);
ib_unregister_event_handler(&sdev->event_handler);
err_cm:
if (sdev->cm_id)
@@ -3221,7 +3224,7 @@
struct srpt_device *sdev = client_data;
int i;
- srpt_unregister_mad_agent(sdev);
+ srpt_unregister_mad_agent(sdev, sdev->device->phys_port_cnt);
ib_unregister_event_handler(&sdev->event_handler);
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h
index 41435a6..bdeb010 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.h
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.h
@@ -256,6 +256,7 @@
* @rdma_cm: See below.
* @rdma_cm.cm_id: RDMA CM ID associated with the channel.
* @cq: IB completion queue for this channel.
+ * @cq_size: Number of CQEs in @cq.
* @zw_cqe: Zero-length write CQE.
* @rcu: RCU head.
* @kref: kref for this channel.
diff --git a/drivers/input/keyboard/sunkbd.c b/drivers/input/keyboard/sunkbd.c
index 27126e6..d450f11 100644
--- a/drivers/input/keyboard/sunkbd.c
+++ b/drivers/input/keyboard/sunkbd.c
@@ -99,7 +99,8 @@
switch (data) {
case SUNKBD_RET_RESET:
- schedule_work(&sunkbd->tq);
+ if (sunkbd->enabled)
+ schedule_work(&sunkbd->tq);
sunkbd->reset = -1;
break;
@@ -200,16 +201,12 @@
}
/*
- * sunkbd_reinit() sets leds and beeps to a state the computer remembers they
- * were in.
+ * sunkbd_set_leds_beeps() sets leds and beeps to a state the computer remembers
+ * they were in.
*/
-static void sunkbd_reinit(struct work_struct *work)
+static void sunkbd_set_leds_beeps(struct sunkbd *sunkbd)
{
- struct sunkbd *sunkbd = container_of(work, struct sunkbd, tq);
-
- wait_event_interruptible_timeout(sunkbd->wait, sunkbd->reset >= 0, HZ);
-
serio_write(sunkbd->serio, SUNKBD_CMD_SETLED);
serio_write(sunkbd->serio,
(!!test_bit(LED_CAPSL, sunkbd->dev->led) << 3) |
@@ -222,11 +219,39 @@
SUNKBD_CMD_BELLOFF - !!test_bit(SND_BELL, sunkbd->dev->snd));
}
+
+/*
+ * sunkbd_reinit() wait for the keyboard reset to complete and restores state
+ * of leds and beeps.
+ */
+
+static void sunkbd_reinit(struct work_struct *work)
+{
+ struct sunkbd *sunkbd = container_of(work, struct sunkbd, tq);
+
+ /*
+ * It is OK that we check sunkbd->enabled without pausing serio,
+ * as we only want to catch true->false transition that will
+ * happen once and we will be woken up for it.
+ */
+ wait_event_interruptible_timeout(sunkbd->wait,
+ sunkbd->reset >= 0 || !sunkbd->enabled,
+ HZ);
+
+ if (sunkbd->reset >= 0 && sunkbd->enabled)
+ sunkbd_set_leds_beeps(sunkbd);
+}
+
static void sunkbd_enable(struct sunkbd *sunkbd, bool enable)
{
serio_pause_rx(sunkbd->serio);
sunkbd->enabled = enable;
serio_continue_rx(sunkbd->serio);
+
+ if (!enable) {
+ wake_up_interruptible(&sunkbd->wait);
+ cancel_work_sync(&sunkbd->tq);
+ }
}
/*
diff --git a/drivers/input/misc/adxl34x.c b/drivers/input/misc/adxl34x.c
index 5fe92d4..4cc4e8f 100644
--- a/drivers/input/misc/adxl34x.c
+++ b/drivers/input/misc/adxl34x.c
@@ -696,7 +696,7 @@
struct input_dev *input_dev;
const struct adxl34x_platform_data *pdata;
int err, range, i;
- unsigned char revid;
+ int revid;
if (!irq) {
dev_err(dev, "no IRQ?\n");
diff --git a/drivers/input/mouse/elan_i2c.h b/drivers/input/mouse/elan_i2c.h
index c75b00c..36e3cd9 100644
--- a/drivers/input/mouse/elan_i2c.h
+++ b/drivers/input/mouse/elan_i2c.h
@@ -78,7 +78,7 @@
int (*iap_reset)(struct i2c_client *client);
int (*prepare_fw_update)(struct i2c_client *client, u16 ic_type,
- u8 iap_version);
+ u8 iap_version, u16 fw_page_size);
int (*write_fw_block)(struct i2c_client *client, u16 fw_page_size,
const u8 *page, u16 checksum, int idx);
int (*finish_fw_update)(struct i2c_client *client,
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index c599e21..61ed3f5 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -497,7 +497,8 @@
u16 sw_checksum = 0, fw_checksum = 0;
error = data->ops->prepare_fw_update(client, data->ic_type,
- data->iap_version);
+ data->iap_version,
+ data->fw_page_size);
if (error)
return error;
diff --git a/drivers/input/mouse/elan_i2c_i2c.c b/drivers/input/mouse/elan_i2c_i2c.c
index 5a496d4..13dc097 100644
--- a/drivers/input/mouse/elan_i2c_i2c.c
+++ b/drivers/input/mouse/elan_i2c_i2c.c
@@ -517,7 +517,7 @@
return 0;
}
-static int elan_read_write_iap_type(struct i2c_client *client)
+static int elan_read_write_iap_type(struct i2c_client *client, u16 fw_page_size)
{
int error;
u16 constant;
@@ -526,7 +526,7 @@
do {
error = elan_i2c_write_cmd(client, ETP_I2C_IAP_TYPE_CMD,
- ETP_I2C_IAP_TYPE_REG);
+ fw_page_size / 2);
if (error) {
dev_err(&client->dev,
"cannot write iap type: %d\n", error);
@@ -543,7 +543,7 @@
constant = le16_to_cpup((__le16 *)val);
dev_dbg(&client->dev, "iap type reg: 0x%04x\n", constant);
- if (constant == ETP_I2C_IAP_TYPE_REG)
+ if (constant == fw_page_size / 2)
return 0;
} while (--retry > 0);
@@ -553,7 +553,7 @@
}
static int elan_i2c_prepare_fw_update(struct i2c_client *client, u16 ic_type,
- u8 iap_version)
+ u8 iap_version, u16 fw_page_size)
{
struct device *dev = &client->dev;
int error;
@@ -594,7 +594,7 @@
}
if (ic_type >= 0x0D && iap_version >= 1) {
- error = elan_read_write_iap_type(client);
+ error = elan_read_write_iap_type(client, fw_page_size);
if (error)
return error;
}
diff --git a/drivers/input/mouse/elan_i2c_smbus.c b/drivers/input/mouse/elan_i2c_smbus.c
index 8ff8237..1820f1c 100644
--- a/drivers/input/mouse/elan_i2c_smbus.c
+++ b/drivers/input/mouse/elan_i2c_smbus.c
@@ -340,7 +340,7 @@
}
static int elan_smbus_prepare_fw_update(struct i2c_client *client, u16 ic_type,
- u8 iap_version)
+ u8 iap_version, u16 fw_page_size)
{
struct device *dev = &client->dev;
int len;
diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index d3eda48..944cbb51 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -122,6 +122,7 @@
MODULE_PARM_DESC(unmask_kbd_data, "Unconditional enable (may reveal sensitive data) of normally sanitize-filtered kbd data traffic debug log [pre-condition: i8042.debug=1 enabled]");
#endif
+static bool i8042_present;
static bool i8042_bypass_aux_irq_test;
static char i8042_kbd_firmware_id[128];
static char i8042_aux_firmware_id[128];
@@ -343,6 +344,9 @@
unsigned long flags;
int retval;
+ if (!i8042_present)
+ return -1;
+
spin_lock_irqsave(&i8042_lock, flags);
retval = __i8042_command(param, command);
spin_unlock_irqrestore(&i8042_lock, flags);
@@ -1612,12 +1616,15 @@
err = i8042_platform_init();
if (err)
- return err;
+ return (err == -ENODEV) ? 0 : err;
err = i8042_controller_check();
if (err)
goto err_platform_exit;
+ /* Set this before creating the dev to allow i8042_command to work right away */
+ i8042_present = true;
+
pdev = platform_create_bundle(&i8042_driver, i8042_probe, NULL, 0, NULL, 0);
if (IS_ERR(pdev)) {
err = PTR_ERR(pdev);
@@ -1636,6 +1643,9 @@
static void __exit i8042_exit(void)
{
+ if (!i8042_present)
+ return;
+
platform_device_unregister(i8042_platform_device);
platform_driver_unregister(&i8042_driver);
i8042_platform_exit();
diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index f012fe7..cc18f54 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -96,6 +96,7 @@
config TOUCHSCREEN_ADC
tristate "Generic ADC based resistive touchscreen"
depends on IIO
+ select IIO_BUFFER
select IIO_BUFFER_CB
help
Say Y here if you want to use the generic ADC
diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index eea47b4..974a667 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -971,6 +971,9 @@
}
node->avg_bw = node->init_avg;
node->peak_bw = node->init_peak;
+ if (provider->aggregate)
+ provider->aggregate(node, 0, node->init_avg, node->init_peak,
+ &node->avg_bw, &node->peak_bw);
provider->set(node, node);
node->avg_bw = 0;
node->peak_bw = 0;
diff --git a/drivers/interconnect/qcom/icc-rpmh.c b/drivers/interconnect/qcom/icc-rpmh.c
index cf10a4b..bf01d09 100644
--- a/drivers/interconnect/qcom/icc-rpmh.c
+++ b/drivers/interconnect/qcom/icc-rpmh.c
@@ -79,6 +79,7 @@
int qcom_icc_set(struct icc_node *src, struct icc_node *dst)
{
struct qcom_icc_provider *qp;
+ struct qcom_icc_node *qn;
struct icc_node *node;
if (!src)
@@ -87,6 +88,12 @@
node = src;
qp = to_qcom_provider(node->provider);
+ qn = node->data;
+
+ qn->sum_avg[QCOM_ICC_BUCKET_AMC] = max_t(u64, qn->sum_avg[QCOM_ICC_BUCKET_AMC],
+ node->avg_bw);
+ qn->max_peak[QCOM_ICC_BUCKET_AMC] = max_t(u64, qn->max_peak[QCOM_ICC_BUCKET_AMC],
+ node->peak_bw);
qcom_icc_bcm_voter_commit(qp->voter);
diff --git a/drivers/interconnect/qcom/sc7180.c b/drivers/interconnect/qcom/sc7180.c
index bf11b82..8d9044e 100644
--- a/drivers/interconnect/qcom/sc7180.c
+++ b/drivers/interconnect/qcom/sc7180.c
@@ -553,6 +553,9 @@
return ret;
}
+ for (i = 0; i < qp->num_bcms; i++)
+ qcom_icc_bcm_init(qp->bcms[i], &pdev->dev);
+
for (i = 0; i < num_nodes; i++) {
size_t j;
@@ -576,9 +579,6 @@
}
data->num_nodes = num_nodes;
- for (i = 0; i < qp->num_bcms; i++)
- qcom_icc_bcm_init(qp->bcms[i], &pdev->dev);
-
platform_set_drvdata(pdev, qp);
return 0;
diff --git a/drivers/interconnect/qcom/sdm845.c b/drivers/interconnect/qcom/sdm845.c
index d79e316..5304aea 100644
--- a/drivers/interconnect/qcom/sdm845.c
+++ b/drivers/interconnect/qcom/sdm845.c
@@ -151,7 +151,7 @@
DEFINE_QBCM(bcm_sh0, "SH0", true, &qns_llcc);
DEFINE_QBCM(bcm_mm0, "MM0", false, &qns_mem_noc_hf);
DEFINE_QBCM(bcm_sh1, "SH1", false, &qns_apps_io);
-DEFINE_QBCM(bcm_mm1, "MM1", false, &qxm_camnoc_hf0_uncomp, &qxm_camnoc_hf1_uncomp, &qxm_camnoc_sf_uncomp, &qxm_camnoc_hf0, &qxm_camnoc_hf1, &qxm_mdp0, &qxm_mdp1);
+DEFINE_QBCM(bcm_mm1, "MM1", true, &qxm_camnoc_hf0_uncomp, &qxm_camnoc_hf1_uncomp, &qxm_camnoc_sf_uncomp, &qxm_camnoc_hf0, &qxm_camnoc_hf1, &qxm_mdp0, &qxm_mdp1);
DEFINE_QBCM(bcm_sh2, "SH2", false, &qns_memnoc_snoc);
DEFINE_QBCM(bcm_mm2, "MM2", false, &qns2_mem_noc);
DEFINE_QBCM(bcm_sh3, "SH3", false, &acm_tcu);
@@ -489,6 +489,9 @@
return ret;
}
+ for (i = 0; i < qp->num_bcms; i++)
+ qcom_icc_bcm_init(qp->bcms[i], &pdev->dev);
+
for (i = 0; i < num_nodes; i++) {
size_t j;
@@ -512,9 +515,6 @@
}
data->num_nodes = num_nodes;
- for (i = 0; i < qp->num_bcms; i++)
- qcom_icc_bcm_init(qp->bcms[i], &pdev->dev);
-
platform_set_drvdata(pdev, qp);
return 0;
diff --git a/drivers/interconnect/qcom/sm8150.c b/drivers/interconnect/qcom/sm8150.c
index 9218efe..c76b2c7 100644
--- a/drivers/interconnect/qcom/sm8150.c
+++ b/drivers/interconnect/qcom/sm8150.c
@@ -551,6 +551,9 @@
return ret;
}
+ for (i = 0; i < qp->num_bcms; i++)
+ qcom_icc_bcm_init(qp->bcms[i], &pdev->dev);
+
for (i = 0; i < num_nodes; i++) {
size_t j;
@@ -574,9 +577,6 @@
}
data->num_nodes = num_nodes;
- for (i = 0; i < qp->num_bcms; i++)
- qcom_icc_bcm_init(qp->bcms[i], &pdev->dev);
-
platform_set_drvdata(pdev, qp);
return 0;
@@ -627,6 +627,7 @@
.driver = {
.name = "qnoc-sm8150",
.of_match_table = qnoc_of_match,
+ .sync_state = icc_sync_state,
},
};
module_platform_driver(qnoc_driver);
diff --git a/drivers/interconnect/qcom/sm8250.c b/drivers/interconnect/qcom/sm8250.c
index 9b58946..cc558fe 100644
--- a/drivers/interconnect/qcom/sm8250.c
+++ b/drivers/interconnect/qcom/sm8250.c
@@ -567,6 +567,9 @@
return ret;
}
+ for (i = 0; i < qp->num_bcms; i++)
+ qcom_icc_bcm_init(qp->bcms[i], &pdev->dev);
+
for (i = 0; i < num_nodes; i++) {
size_t j;
@@ -590,9 +593,6 @@
}
data->num_nodes = num_nodes;
- for (i = 0; i < qp->num_bcms; i++)
- qcom_icc_bcm_init(qp->bcms[i], &pdev->dev);
-
platform_set_drvdata(pdev, qp);
return 0;
@@ -643,6 +643,7 @@
.driver = {
.name = "qnoc-sm8250",
.of_match_table = qnoc_of_match,
+ .sync_state = icc_sync_state,
},
};
module_platform_driver(qnoc_driver);
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index f696ac7..8964770 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -409,7 +409,11 @@
/* Only true if all IOMMUs support device IOTLBs */
extern bool amd_iommu_iotlb_sup;
-#define MAX_IRQS_PER_TABLE 256
+/*
+ * AMD IOMMU hardware only support 512 IRTEs despite
+ * the architectural limitation of 2048 entries.
+ */
+#define MAX_IRQS_PER_TABLE 512
#define IRQ_TABLE_ALIGNMENT 128
struct irq_remap_table {
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 404b40a..11319e4 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -333,6 +333,13 @@
dmar_iommu_notify_scope_dev(info);
}
+static inline void vf_inherit_msi_domain(struct pci_dev *pdev)
+{
+ struct pci_dev *physfn = pci_physfn(pdev);
+
+ dev_set_msi_domain(&pdev->dev, dev_get_msi_domain(&physfn->dev));
+}
+
static int dmar_pci_bus_notifier(struct notifier_block *nb,
unsigned long action, void *data)
{
@@ -342,8 +349,20 @@
/* Only care about add/remove events for physical functions.
* For VFs we actually do the lookup based on the corresponding
* PF in device_to_iommu() anyway. */
- if (pdev->is_virtfn)
+ if (pdev->is_virtfn) {
+ /*
+ * Ensure that the VF device inherits the irq domain of the
+ * PF device. Ideally the device would inherit the domain
+ * from the bus, but DMAR can have multiple units per bus
+ * which makes this impossible. The VF 'bus' could inherit
+ * from the PF device, but that's yet another x86'sism to
+ * inflict on everybody else.
+ */
+ if (action == BUS_NOTIFY_ADD_DEVICE)
+ vf_inherit_msi_domain(pdev);
return NOTIFY_DONE;
+ }
+
if (action != BUS_NOTIFY_ADD_DEVICE &&
action != BUS_NOTIFY_REMOVED_DEVICE)
return NOTIFY_DONE;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 8651f6d..c71a9c2 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -179,7 +179,7 @@
* (used when kernel is launched w/ TXT)
*/
static int force_on = 0;
-int intel_iommu_tboot_noforce;
+static int intel_iommu_tboot_noforce;
static int no_platform_optin;
#define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry))
@@ -2525,6 +2525,9 @@
{
struct device_domain_info *info;
+ if (unlikely(!dev || !dev->iommu))
+ return NULL;
+
if (unlikely(attach_deferred(dev)))
return NULL;
@@ -3815,9 +3818,8 @@
* page aligned, we don't need to use a bounce page.
*/
if (!IS_ALIGNED(paddr | size, VTD_PAGE_SIZE)) {
- tlb_addr = swiotlb_tbl_map_single(dev,
- phys_to_dma_unencrypted(dev, io_tlb_start),
- paddr, size, aligned_size, dir, attrs);
+ tlb_addr = swiotlb_tbl_map_single(dev, paddr, size,
+ aligned_size, dir, attrs);
if (tlb_addr == DMA_MAPPING_ERROR) {
goto swiotlb_error;
} else {
@@ -4882,7 +4884,8 @@
* Intel IOMMU is required for a TXT/tboot launch or platform
* opt in, so enforce that.
*/
- force_on = tboot_force_iommu() || platform_optin_force_iommu();
+ force_on = (!intel_iommu_tboot_noforce && tboot_force_iommu()) ||
+ platform_optin_force_iommu();
if (iommu_init_mempool()) {
if (force_on)
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index f1861fa..3242ebd 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -279,6 +279,7 @@
struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
struct intel_svm_dev *sdev = NULL;
struct dmar_domain *dmar_domain;
+ struct device_domain_info *info;
struct intel_svm *svm = NULL;
int ret = 0;
@@ -310,6 +311,10 @@
if (data->hpasid <= 0 || data->hpasid >= PASID_MAX)
return -EINVAL;
+ info = get_domain_info(dev);
+ if (!info)
+ return -EINVAL;
+
dmar_domain = to_dmar_domain(domain);
mutex_lock(&pasid_mutex);
@@ -357,6 +362,7 @@
goto out;
}
sdev->dev = dev;
+ sdev->sid = PCI_DEVID(info->bus, info->devfn);
/* Only count users if device has aux domains */
if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX))
@@ -1029,7 +1035,7 @@
resp.qw0 = QI_PGRP_PASID(req->pasid) |
QI_PGRP_DID(req->rid) |
QI_PGRP_PASID_P(req->pasid_present) |
- QI_PGRP_PDP(req->pasid_present) |
+ QI_PGRP_PDP(req->priv_data_present) |
QI_PGRP_RESP_CODE(result) |
QI_PGRP_RESP_TYPE;
resp.qw1 = QI_PGRP_IDX(req->prg_index) |
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 8c470f4..b53446b 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2071,7 +2071,7 @@
static int iommu_check_bind_data(struct iommu_gpasid_bind_data *data)
{
- u32 mask;
+ u64 mask;
int i;
if (data->version != IOMMU_GPASID_BIND_VERSION_1)
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index c6098ee..2aa79c3 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -180,7 +180,6 @@
select GENERIC_IRQ_CHIP
select GENERIC_IRQ_IPI if SYS_SUPPORTS_MULTITHREADING
select IRQ_DOMAIN
- select IRQ_DOMAIN_HIERARCHY if GENERIC_IRQ_IPI
select GENERIC_IRQ_EFFECTIVE_AFF_MASK
config CLPS711X_IRQCHIP
@@ -315,7 +314,6 @@
config MIPS_GIC
bool
select GENERIC_IRQ_IPI
- select IRQ_DOMAIN_HIERARCHY
select MIPS_CM
config INGENIC_IRQ
@@ -591,6 +589,7 @@
config MST_IRQ
bool "MStar Interrupt Controller"
+ depends on ARCH_MEDIATEK || ARCH_MSTARV7 || COMPILE_TEST
default ARCH_MEDIATEK
select IRQ_DOMAIN
select IRQ_DOMAIN_HIERARCHY
diff --git a/drivers/irqchip/irq-bcm2836.c b/drivers/irqchip/irq-bcm2836.c
index 97838eb..cbc7c74 100644
--- a/drivers/irqchip/irq-bcm2836.c
+++ b/drivers/irqchip/irq-bcm2836.c
@@ -244,7 +244,7 @@
#define BITS_PER_MBOX 32
-static void bcm2836_arm_irqchip_smp_init(void)
+static void __init bcm2836_arm_irqchip_smp_init(void)
{
struct irq_fwspec ipi_fwspec = {
.fwnode = intc.domain->fwnode,
diff --git a/drivers/irqchip/irq-mst-intc.c b/drivers/irqchip/irq-mst-intc.c
index 4be0775..143657b 100644
--- a/drivers/irqchip/irq-mst-intc.c
+++ b/drivers/irqchip/irq-mst-intc.c
@@ -154,8 +154,8 @@
.free = irq_domain_free_irqs_common,
};
-int __init
-mst_intc_of_init(struct device_node *dn, struct device_node *parent)
+static int __init mst_intc_of_init(struct device_node *dn,
+ struct device_node *parent)
{
struct irq_domain *domain, *domain_parent;
struct mst_intc_chip_data *cd;
diff --git a/drivers/irqchip/irq-renesas-intc-irqpin.c b/drivers/irqchip/irq-renesas-intc-irqpin.c
index 3819185b..cb7f60b 100644
--- a/drivers/irqchip/irq-renesas-intc-irqpin.c
+++ b/drivers/irqchip/irq-renesas-intc-irqpin.c
@@ -71,8 +71,7 @@
};
struct intc_irqpin_config {
- unsigned int irlm_bit;
- unsigned needs_irlm:1;
+ int irlm_bit; /* -1 if non-existent */
};
static unsigned long intc_irqpin_read32(void __iomem *iomem)
@@ -349,11 +348,10 @@
static const struct intc_irqpin_config intc_irqpin_irlm_r8a777x = {
.irlm_bit = 23, /* ICR0.IRLM0 */
- .needs_irlm = 1,
};
static const struct intc_irqpin_config intc_irqpin_rmobile = {
- .needs_irlm = 0,
+ .irlm_bit = -1,
};
static const struct of_device_id intc_irqpin_dt_ids[] = {
@@ -470,7 +468,7 @@
}
/* configure "individual IRQ mode" where needed */
- if (config && config->needs_irlm) {
+ if (config && config->irlm_bit >= 0) {
if (io[INTC_IRQPIN_REG_IRLM])
intc_irqpin_read_modify_write(p, INTC_IRQPIN_REG_IRLM,
config->irlm_bit, 1, 1);
diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index eaa3e9f..6f432d2 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -99,7 +99,7 @@
struct irq_data *d, int enable)
{
int cpu;
- struct plic_priv *priv = irq_get_chip_data(d->irq);
+ struct plic_priv *priv = irq_data_get_irq_chip_data(d);
writel(enable, priv->regs + PRIORITY_BASE + d->hwirq * PRIORITY_PER_ID);
for_each_cpu(cpu, mask) {
@@ -115,7 +115,7 @@
{
struct cpumask amask;
unsigned int cpu;
- struct plic_priv *priv = irq_get_chip_data(d->irq);
+ struct plic_priv *priv = irq_data_get_irq_chip_data(d);
cpumask_and(&amask, &priv->lmask, cpu_online_mask);
cpu = cpumask_any_and(irq_data_get_affinity_mask(d),
@@ -127,7 +127,7 @@
static void plic_irq_mask(struct irq_data *d)
{
- struct plic_priv *priv = irq_get_chip_data(d->irq);
+ struct plic_priv *priv = irq_data_get_irq_chip_data(d);
plic_irq_toggle(&priv->lmask, d, 0);
}
@@ -138,7 +138,7 @@
{
unsigned int cpu;
struct cpumask amask;
- struct plic_priv *priv = irq_get_chip_data(d->irq);
+ struct plic_priv *priv = irq_data_get_irq_chip_data(d);
cpumask_and(&amask, &priv->lmask, mask_val);
@@ -151,7 +151,7 @@
return -EINVAL;
plic_irq_toggle(&priv->lmask, d, 0);
- plic_irq_toggle(cpumask_of(cpu), d, 1);
+ plic_irq_toggle(cpumask_of(cpu), d, !irqd_irq_masked(d));
irq_data_update_effective_affinity(d, cpumask_of(cpu));
diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c
index 0c2c61d..8662d7b 100644
--- a/drivers/irqchip/irq-stm32-exti.c
+++ b/drivers/irqchip/irq-stm32-exti.c
@@ -195,6 +195,10 @@
{ .exti = 25, .irq_parent = 107, .chip = &stm32_exti_h_chip_direct },
{ .exti = 30, .irq_parent = 52, .chip = &stm32_exti_h_chip_direct },
{ .exti = 47, .irq_parent = 93, .chip = &stm32_exti_h_chip_direct },
+ { .exti = 48, .irq_parent = 138, .chip = &stm32_exti_h_chip_direct },
+ { .exti = 50, .irq_parent = 139, .chip = &stm32_exti_h_chip_direct },
+ { .exti = 52, .irq_parent = 140, .chip = &stm32_exti_h_chip_direct },
+ { .exti = 53, .irq_parent = 141, .chip = &stm32_exti_h_chip_direct },
{ .exti = 54, .irq_parent = 135, .chip = &stm32_exti_h_chip_direct },
{ .exti = 61, .irq_parent = 100, .chip = &stm32_exti_h_chip_direct },
{ .exti = 65, .irq_parent = 144, .chip = &stm32_exti_h_chip },
diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c
index e0cceb8..b2ab8db4 100644
--- a/drivers/irqchip/irq-ti-sci-inta.c
+++ b/drivers/irqchip/irq-ti-sci-inta.c
@@ -85,6 +85,17 @@
* @base: Base address of the memory mapped IO registers
* @pdev: Pointer to platform device.
* @ti_sci_id: TI-SCI device identifier
+ * @unmapped_cnt: Number of @unmapped_dev_ids entries
+ * @unmapped_dev_ids: Pointer to an array of TI-SCI device identifiers of
+ * unmapped event sources.
+ * Unmapped Events are not part of the Global Event Map and
+ * they are converted to Global event within INTA to be
+ * received by the same INTA to generate an interrupt.
+ * In case an interrupt request comes for a device which is
+ * generating Unmapped Event, we must use the INTA's TI-SCI
+ * device identifier in place of the source device
+ * identifier to let sysfw know where it has to program the
+ * Global Event number.
*/
struct ti_sci_inta_irq_domain {
const struct ti_sci_handle *sci;
@@ -96,11 +107,37 @@
void __iomem *base;
struct platform_device *pdev;
u32 ti_sci_id;
+
+ int unmapped_cnt;
+ u16 *unmapped_dev_ids;
};
#define to_vint_desc(e, i) container_of(e, struct ti_sci_inta_vint_desc, \
events[i])
+static u16 ti_sci_inta_get_dev_id(struct ti_sci_inta_irq_domain *inta, u32 hwirq)
+{
+ u16 dev_id = HWIRQ_TO_DEVID(hwirq);
+ int i;
+
+ if (inta->unmapped_cnt == 0)
+ return dev_id;
+
+ /*
+ * For devices sending Unmapped Events we must use the INTA's TI-SCI
+ * device identifier number to be able to convert it to a Global Event
+ * and map it to an interrupt.
+ */
+ for (i = 0; i < inta->unmapped_cnt; i++) {
+ if (dev_id == inta->unmapped_dev_ids[i]) {
+ dev_id = inta->ti_sci_id;
+ break;
+ }
+ }
+
+ return dev_id;
+}
+
/**
* ti_sci_inta_irq_handler() - Chained IRQ handler for the vint irqs
* @desc: Pointer to irq_desc corresponding to the irq
@@ -251,7 +288,7 @@
u16 dev_id, dev_index;
int err;
- dev_id = HWIRQ_TO_DEVID(hwirq);
+ dev_id = ti_sci_inta_get_dev_id(inta, hwirq);
dev_index = HWIRQ_TO_IRQID(hwirq);
event_desc = &vint_desc->events[free_bit];
@@ -352,14 +389,15 @@
{
struct ti_sci_inta_vint_desc *vint_desc;
struct ti_sci_inta_irq_domain *inta;
+ u16 dev_id;
vint_desc = to_vint_desc(event_desc, event_desc->vint_bit);
inta = vint_desc->domain->host_data;
+ dev_id = ti_sci_inta_get_dev_id(inta, hwirq);
/* free event irq */
mutex_lock(&inta->vint_mutex);
inta->sci->ops.rm_irq_ops.free_event_map(inta->sci,
- HWIRQ_TO_DEVID(hwirq),
- HWIRQ_TO_IRQID(hwirq),
+ dev_id, HWIRQ_TO_IRQID(hwirq),
inta->ti_sci_id,
vint_desc->vint_id,
event_desc->global_event,
@@ -574,6 +612,41 @@
.chip = &ti_sci_inta_msi_irq_chip,
};
+static int ti_sci_inta_get_unmapped_sources(struct ti_sci_inta_irq_domain *inta)
+{
+ struct device *dev = &inta->pdev->dev;
+ struct device_node *node = dev_of_node(dev);
+ struct of_phandle_iterator it;
+ int count, err, ret, i;
+
+ count = of_count_phandle_with_args(node, "ti,unmapped-event-sources", NULL);
+ if (count <= 0)
+ return 0;
+
+ inta->unmapped_dev_ids = devm_kcalloc(dev, count,
+ sizeof(*inta->unmapped_dev_ids),
+ GFP_KERNEL);
+ if (!inta->unmapped_dev_ids)
+ return -ENOMEM;
+
+ i = 0;
+ of_for_each_phandle(&it, err, node, "ti,unmapped-event-sources", NULL, 0) {
+ u32 dev_id;
+
+ ret = of_property_read_u32(it.node, "ti,sci-dev-id", &dev_id);
+ if (ret) {
+ dev_err(dev, "ti,sci-dev-id read failure for %pOFf\n", it.node);
+ of_node_put(it.node);
+ return ret;
+ }
+ inta->unmapped_dev_ids[i++] = dev_id;
+ }
+
+ inta->unmapped_cnt = count;
+
+ return 0;
+}
+
static int ti_sci_inta_irq_domain_probe(struct platform_device *pdev)
{
struct irq_domain *parent_domain, *domain, *msi_domain;
@@ -629,6 +702,10 @@
if (IS_ERR(inta->base))
return PTR_ERR(inta->base);
+ ret = ti_sci_inta_get_unmapped_sources(inta);
+ if (ret)
+ return ret;
+
domain = irq_domain_add_linear(dev_of_node(dev),
ti_sci_get_num_resources(inta->vint),
&ti_sci_inta_irq_domain_ops, inta);
diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c
index a5ef9fa..e7f0d4a 100644
--- a/drivers/message/fusion/mptscsih.c
+++ b/drivers/message/fusion/mptscsih.c
@@ -1176,8 +1176,10 @@
MPT_SCSI_HOST *hd;
int sz1;
- if((hd = shost_priv(host)) == NULL)
- return;
+ if (host == NULL)
+ hd = NULL;
+ else
+ hd = shost_priv(host);
mptscsih_shutdown(pdev);
@@ -1193,14 +1195,15 @@
"Free'd ScsiLookup (%d) memory\n",
ioc->name, sz1));
- kfree(hd->info_kbuf);
+ if (hd)
+ kfree(hd->info_kbuf);
/* NULL the Scsi_Host pointer
*/
ioc->sh = NULL;
- scsi_host_put(host);
-
+ if (host)
+ scsi_host_put(host);
mpt_detach(pdev);
}
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index d5ce808..fafa8b0 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -474,7 +474,6 @@
source "drivers/misc/altera-stapl/Kconfig"
source "drivers/misc/mei/Kconfig"
source "drivers/misc/vmw_vmci/Kconfig"
-source "drivers/misc/mic/Kconfig"
source "drivers/misc/genwqe/Kconfig"
source "drivers/misc/echo/Kconfig"
source "drivers/misc/cxl/Kconfig"
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index 2521359..d23231e 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -46,7 +46,6 @@
obj-$(CONFIG_LATTICE_ECP3_CONFIG) += lattice-ecp3-config.o
obj-$(CONFIG_SRAM) += sram.o
obj-$(CONFIG_SRAM_EXEC) += sram-exec.o
-obj-y += mic/
obj-$(CONFIG_GENWQE) += genwqe/
obj-$(CONFIG_ECHO) += echo/
obj-$(CONFIG_CXL_BASE) += cxl/
diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c
index 901e213..ada570f3 100644
--- a/drivers/misc/habanalabs/common/command_buffer.c
+++ b/drivers/misc/habanalabs/common/command_buffer.c
@@ -142,11 +142,10 @@
{
if (cb->is_internal)
gen_pool_free(hdev->internal_cb_pool,
- cb->kernel_address, cb->size);
+ (uintptr_t)cb->kernel_address, cb->size);
else
hdev->asic_funcs->asic_dma_free_coherent(hdev, cb->size,
- (void *) (uintptr_t) cb->kernel_address,
- cb->bus_address);
+ cb->kernel_address, cb->bus_address);
kfree(cb);
}
@@ -230,7 +229,7 @@
return NULL;
}
- cb->kernel_address = (u64) (uintptr_t) p;
+ cb->kernel_address = p;
cb->size = cb_size;
return cb;
@@ -509,7 +508,7 @@
vma->vm_private_data = cb;
- rc = hdev->asic_funcs->cb_mmap(hdev, vma, (void *) cb->kernel_address,
+ rc = hdev->asic_funcs->cb_mmap(hdev, vma, cb->kernel_address,
cb->bus_address, cb->size);
if (rc) {
spin_lock(&cb->lock);
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 80d4d73..6ed974d 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -452,7 +452,7 @@
struct list_head pool_list;
struct list_head va_block_list;
u64 id;
- u64 kernel_address;
+ void *kernel_address;
dma_addr_t bus_address;
u32 mmap_size;
u32 size;
@@ -515,7 +515,7 @@
struct hl_hw_sob hw_sob[HL_RSVD_SOBS];
struct hl_cs_job **shadow_queue;
enum hl_queue_type queue_type;
- u64 kernel_address;
+ void *kernel_address;
dma_addr_t bus_address;
u32 pi;
atomic_t ci;
@@ -544,7 +544,7 @@
*/
struct hl_cq {
struct hl_device *hdev;
- u64 kernel_address;
+ void *kernel_address;
dma_addr_t bus_address;
u32 cq_idx;
u32 hw_queue_id;
@@ -562,7 +562,7 @@
*/
struct hl_eq {
struct hl_device *hdev;
- u64 kernel_address;
+ void *kernel_address;
dma_addr_t bus_address;
u32 ci;
};
@@ -757,7 +757,7 @@
u32 (*get_dma_desc_list_size)(struct hl_device *hdev,
struct sg_table *sgt);
void (*add_end_of_cb_packets)(struct hl_device *hdev,
- u64 kernel_address, u32 len,
+ void *kernel_address, u32 len,
u64 cq_addr, u32 cq_val, u32 msix_num,
bool eb);
void (*update_eq_ci)(struct hl_device *hdev, u32 val);
@@ -1382,13 +1382,13 @@
for (;;) { \
/* Verify we read updates done by other cores or by device */ \
mb(); \
- (val) = *((u32 *) (uintptr_t) (addr)); \
+ (val) = *((u32 *)(addr)); \
if (mem_written_by_device) \
(val) = le32_to_cpu(*(__le32 *) &(val)); \
if (cond) \
break; \
if (timeout_us && ktime_compare(ktime_get(), __timeout) > 0) { \
- (val) = *((u32 *) (uintptr_t) (addr)); \
+ (val) = *((u32 *)(addr)); \
if (mem_written_by_device) \
(val) = le32_to_cpu(*(__le32 *) &(val)); \
break; \
diff --git a/drivers/misc/habanalabs/common/hw_queue.c b/drivers/misc/habanalabs/common/hw_queue.c
index 5e66c98..250cf9c 100644
--- a/drivers/misc/habanalabs/common/hw_queue.c
+++ b/drivers/misc/habanalabs/common/hw_queue.c
@@ -75,7 +75,7 @@
{
struct hl_bd *bd;
- bd = (struct hl_bd *) (uintptr_t) q->kernel_address;
+ bd = q->kernel_address;
bd += hl_pi_2_offset(q->pi);
bd->ctl = cpu_to_le32(ctl);
bd->len = cpu_to_le32(len);
@@ -335,8 +335,7 @@
bd.len = cpu_to_le32(job->job_cb_size);
bd.ptr = cpu_to_le64((u64) (uintptr_t) job->user_cb);
- pi = (__le64 *) (uintptr_t) (q->kernel_address +
- ((q->pi & (q->int_queue_len - 1)) * sizeof(bd)));
+ pi = q->kernel_address + (q->pi & (q->int_queue_len - 1)) * sizeof(bd);
q->pi++;
q->pi &= ((q->int_queue_len << 1) - 1);
@@ -630,7 +629,7 @@
if (!p)
return -ENOMEM;
- q->kernel_address = (u64) (uintptr_t) p;
+ q->kernel_address = p;
q->shadow_queue = kmalloc_array(HL_QUEUE_LENGTH,
sizeof(*q->shadow_queue),
@@ -653,11 +652,11 @@
if (is_cpu_queue)
hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
HL_QUEUE_SIZE_IN_BYTES,
- (void *) (uintptr_t) q->kernel_address);
+ q->kernel_address);
else
hdev->asic_funcs->asic_dma_free_coherent(hdev,
HL_QUEUE_SIZE_IN_BYTES,
- (void *) (uintptr_t) q->kernel_address,
+ q->kernel_address,
q->bus_address);
return rc;
@@ -676,7 +675,7 @@
return -EFAULT;
}
- q->kernel_address = (u64) (uintptr_t) p;
+ q->kernel_address = p;
q->pi = 0;
atomic_set(&q->ci, 0);
@@ -704,7 +703,7 @@
if (!p)
return -ENOMEM;
- q->kernel_address = (u64) (uintptr_t) p;
+ q->kernel_address = p;
/* Make sure read/write pointers are initialized to start of queue */
atomic_set(&q->ci, 0);
@@ -839,11 +838,11 @@
if (q->queue_type == QUEUE_TYPE_CPU)
hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
HL_QUEUE_SIZE_IN_BYTES,
- (void *) (uintptr_t) q->kernel_address);
+ q->kernel_address);
else
hdev->asic_funcs->asic_dma_free_coherent(hdev,
HL_QUEUE_SIZE_IN_BYTES,
- (void *) (uintptr_t) q->kernel_address,
+ q->kernel_address,
q->bus_address);
}
diff --git a/drivers/misc/habanalabs/common/irq.c b/drivers/misc/habanalabs/common/irq.c
index d20e40a..de53fb5 100644
--- a/drivers/misc/habanalabs/common/irq.c
+++ b/drivers/misc/habanalabs/common/irq.c
@@ -90,7 +90,7 @@
return IRQ_HANDLED;
}
- cq_base = (struct hl_cq_entry *) (uintptr_t) cq->kernel_address;
+ cq_base = cq->kernel_address;
while (1) {
bool entry_ready = ((le32_to_cpu(cq_base[cq->ci].data) &
@@ -152,7 +152,7 @@
struct hl_eq_entry *eq_base;
struct hl_eqe_work *handle_eqe_work;
- eq_base = (struct hl_eq_entry *) (uintptr_t) eq->kernel_address;
+ eq_base = eq->kernel_address;
while (1) {
bool entry_ready =
@@ -221,7 +221,7 @@
return -ENOMEM;
q->hdev = hdev;
- q->kernel_address = (u64) (uintptr_t) p;
+ q->kernel_address = p;
q->hw_queue_id = hw_queue_id;
q->ci = 0;
q->pi = 0;
@@ -242,7 +242,8 @@
void hl_cq_fini(struct hl_device *hdev, struct hl_cq *q)
{
hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_CQ_SIZE_IN_BYTES,
- (void *) (uintptr_t) q->kernel_address, q->bus_address);
+ q->kernel_address,
+ q->bus_address);
}
void hl_cq_reset(struct hl_device *hdev, struct hl_cq *q)
@@ -259,7 +260,7 @@
* when the device is operational again
*/
- memset((void *) (uintptr_t) q->kernel_address, 0, HL_CQ_SIZE_IN_BYTES);
+ memset(q->kernel_address, 0, HL_CQ_SIZE_IN_BYTES);
}
/**
@@ -282,7 +283,7 @@
return -ENOMEM;
q->hdev = hdev;
- q->kernel_address = (u64) (uintptr_t) p;
+ q->kernel_address = p;
q->ci = 0;
return 0;
@@ -302,7 +303,7 @@
hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
HL_EQ_SIZE_IN_BYTES,
- (void *) (uintptr_t) q->kernel_address);
+ q->kernel_address);
}
void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q)
@@ -316,5 +317,5 @@
* when the device is operational again
*/
- memset((void *) (uintptr_t) q->kernel_address, 0, HL_EQ_SIZE_IN_BYTES);
+ memset(q->kernel_address, 0, HL_EQ_SIZE_IN_BYTES);
}
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 5f65a16..2519a34 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -680,8 +680,7 @@
if (!cb)
return -EFAULT;
- init_tpc_mem_pkt = (struct packet_lin_dma *) (uintptr_t)
- cb->kernel_address;
+ init_tpc_mem_pkt = cb->kernel_address;
cb_size = sizeof(*init_tpc_mem_pkt);
memset(init_tpc_mem_pkt, 0, cb_size);
@@ -3811,8 +3810,7 @@
u16 pkt_size;
struct gaudi_packet *user_pkt;
- user_pkt = (struct gaudi_packet *) (uintptr_t)
- (parser->user_cb->kernel_address + cb_parsed_length);
+ user_pkt = parser->user_cb->kernel_address + cb_parsed_length;
pkt_id = (enum packet_id) (
(le64_to_cpu(user_pkt->header) &
@@ -4035,11 +4033,9 @@
u32 new_pkt_size = 0;
struct gaudi_packet *user_pkt, *kernel_pkt;
- user_pkt = (struct gaudi_packet *) (uintptr_t)
- (parser->user_cb->kernel_address + cb_parsed_length);
- kernel_pkt = (struct gaudi_packet *) (uintptr_t)
- (parser->patched_cb->kernel_address +
- cb_patched_cur_length);
+ user_pkt = parser->user_cb->kernel_address + cb_parsed_length;
+ kernel_pkt = parser->patched_cb->kernel_address +
+ cb_patched_cur_length;
pkt_id = (enum packet_id) (
(le64_to_cpu(user_pkt->header) &
@@ -4155,8 +4151,8 @@
* The check that parser->user_cb_size <= parser->user_cb->size was done
* in validate_queue_index().
*/
- memcpy((void *) (uintptr_t) parser->patched_cb->kernel_address,
- (void *) (uintptr_t) parser->user_cb->kernel_address,
+ memcpy(parser->patched_cb->kernel_address,
+ parser->user_cb->kernel_address,
parser->user_cb_size);
patched_cb_size = parser->patched_cb_size;
@@ -4290,7 +4286,7 @@
}
static void gaudi_add_end_of_cb_packets(struct hl_device *hdev,
- u64 kernel_address, u32 len,
+ void *kernel_address, u32 len,
u64 cq_addr, u32 cq_val, u32 msi_vec,
bool eb)
{
@@ -4298,8 +4294,7 @@
struct packet_msg_prot *cq_pkt;
u32 tmp;
- cq_pkt = (struct packet_msg_prot *) (uintptr_t)
- (kernel_address + len - (sizeof(struct packet_msg_prot) * 2));
+ cq_pkt = kernel_address + len - (sizeof(struct packet_msg_prot) * 2);
tmp = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_PROT);
tmp |= FIELD_PREP(GAUDI_PKT_CTL_MB_MASK, 1);
@@ -4342,7 +4337,7 @@
if (!cb)
return -EFAULT;
- lin_dma_pkt = (struct packet_lin_dma *) (uintptr_t) cb->kernel_address;
+ lin_dma_pkt = cb->kernel_address;
memset(lin_dma_pkt, 0, sizeof(*lin_dma_pkt));
cb_size = sizeof(*lin_dma_pkt);
@@ -4747,7 +4742,7 @@
(addr - gaudi->hbm_bar_cur_addr));
}
-static void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid)
+void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid)
{
/* mask to zero the MMBP and ASID bits */
WREG32_AND(reg, ~0x7FF);
@@ -4915,9 +4910,6 @@
gaudi_mmu_prepare_reg(hdev, mmMME2_ACC_WBC, asid);
gaudi_mmu_prepare_reg(hdev, mmMME3_ACC_WBC, asid);
- gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER, asid);
- gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER, asid);
-
hdev->asic_funcs->set_clock_gating(hdev);
mutex_unlock(&gaudi->clk_gate_mutex);
@@ -4954,8 +4946,8 @@
cb = job->patched_cb;
- fence_pkt = (struct packet_msg_prot *) (uintptr_t) (cb->kernel_address +
- job->job_cb_size - sizeof(struct packet_msg_prot));
+ fence_pkt = cb->kernel_address +
+ job->job_cb_size - sizeof(struct packet_msg_prot);
tmp = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_PROT);
tmp |= FIELD_PREP(GAUDI_PKT_CTL_EB_MASK, 1);
@@ -6386,7 +6378,7 @@
struct packet_msg_short *pkt;
u32 value, ctl;
- pkt = (struct packet_msg_short *) (uintptr_t) cb->kernel_address;
+ pkt = cb->kernel_address;
memset(pkt, 0, sizeof(*pkt));
/* Inc by 1, Mode ADD */
@@ -6478,7 +6470,7 @@
u16 sob_val, u16 mon_id, u32 q_idx)
{
struct hl_cb *cb = (struct hl_cb *) data;
- void *buf = (void *) (uintptr_t) cb->kernel_address;
+ void *buf = cb->kernel_address;
u64 monitor_base, fence_addr = 0;
u32 size = 0;
u16 msg_addr_offset;
diff --git a/drivers/misc/habanalabs/gaudi/gaudiP.h b/drivers/misc/habanalabs/gaudi/gaudiP.h
index 83ad2b0..8eb598d 100644
--- a/drivers/misc/habanalabs/gaudi/gaudiP.h
+++ b/drivers/misc/habanalabs/gaudi/gaudiP.h
@@ -271,5 +271,6 @@
int gaudi_debug_coresight(struct hl_device *hdev, void *data);
void gaudi_halt_coresight(struct hl_device *hdev);
int gaudi_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk);
+void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid);
#endif /* GAUDIP_H_ */
diff --git a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
index 881531d..3d2b0f0 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
@@ -623,6 +623,11 @@
return -EINVAL;
}
+ gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER,
+ hdev->compute_ctx->asid);
+ gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER,
+ hdev->compute_ctx->asid);
+
msb = upper_32_bits(input->buffer_address) >> 8;
msb &= PSOC_GLOBAL_CONF_TRACE_ADDR_MSB_MASK;
WREG32(mmPSOC_GLOBAL_CONF_TRACE_ADDR, msb);
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 5db5206..235d47b 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -2882,8 +2882,8 @@
cb = job->patched_cb;
- fence_pkt = (struct packet_msg_prot *) (uintptr_t) (cb->kernel_address +
- job->job_cb_size - sizeof(struct packet_msg_prot));
+ fence_pkt = cb->kernel_address +
+ job->job_cb_size - sizeof(struct packet_msg_prot);
tmp = (PACKET_MSG_PROT << GOYA_PKT_CTL_OPCODE_SHIFT) |
(1 << GOYA_PKT_CTL_EB_SHIFT) |
@@ -3475,8 +3475,7 @@
u16 pkt_size;
struct goya_packet *user_pkt;
- user_pkt = (struct goya_packet *) (uintptr_t)
- (parser->user_cb->kernel_address + cb_parsed_length);
+ user_pkt = parser->user_cb->kernel_address + cb_parsed_length;
pkt_id = (enum packet_id) (
(le64_to_cpu(user_pkt->header) &
@@ -3713,11 +3712,9 @@
u32 new_pkt_size = 0;
struct goya_packet *user_pkt, *kernel_pkt;
- user_pkt = (struct goya_packet *) (uintptr_t)
- (parser->user_cb->kernel_address + cb_parsed_length);
- kernel_pkt = (struct goya_packet *) (uintptr_t)
- (parser->patched_cb->kernel_address +
- cb_patched_cur_length);
+ user_pkt = parser->user_cb->kernel_address + cb_parsed_length;
+ kernel_pkt = parser->patched_cb->kernel_address +
+ cb_patched_cur_length;
pkt_id = (enum packet_id) (
(le64_to_cpu(user_pkt->header) &
@@ -3841,8 +3838,8 @@
* The check that parser->user_cb_size <= parser->user_cb->size was done
* in validate_queue_index().
*/
- memcpy((void *) (uintptr_t) parser->patched_cb->kernel_address,
- (void *) (uintptr_t) parser->user_cb->kernel_address,
+ memcpy(parser->patched_cb->kernel_address,
+ parser->user_cb->kernel_address,
parser->user_cb_size);
patched_cb_size = parser->patched_cb_size;
@@ -3974,15 +3971,14 @@
return goya_parse_cb_no_mmu(hdev, parser);
}
-void goya_add_end_of_cb_packets(struct hl_device *hdev, u64 kernel_address,
+void goya_add_end_of_cb_packets(struct hl_device *hdev, void *kernel_address,
u32 len, u64 cq_addr, u32 cq_val, u32 msix_vec,
bool eb)
{
struct packet_msg_prot *cq_pkt;
u32 tmp;
- cq_pkt = (struct packet_msg_prot *) (uintptr_t)
- (kernel_address + len - (sizeof(struct packet_msg_prot) * 2));
+ cq_pkt = kernel_address + len - (sizeof(struct packet_msg_prot) * 2);
tmp = (PACKET_MSG_PROT << GOYA_PKT_CTL_OPCODE_SHIFT) |
(1 << GOYA_PKT_CTL_EB_SHIFT) |
@@ -4746,7 +4742,7 @@
if (!cb)
return -ENOMEM;
- lin_dma_pkt = (struct packet_lin_dma *) (uintptr_t) cb->kernel_address;
+ lin_dma_pkt = cb->kernel_address;
do {
memset(lin_dma_pkt, 0, sizeof(*lin_dma_pkt));
diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h
index 09b4006..def86c7 100644
--- a/drivers/misc/habanalabs/goya/goyaP.h
+++ b/drivers/misc/habanalabs/goya/goyaP.h
@@ -217,7 +217,7 @@
void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry);
void *goya_get_events_stat(struct hl_device *hdev, bool aggregate, u32 *size);
-void goya_add_end_of_cb_packets(struct hl_device *hdev, u64 kernel_address,
+void goya_add_end_of_cb_packets(struct hl_device *hdev, void *kernel_address,
u32 len, u64 cq_addr, u32 cq_val, u32 msix_vec,
bool eb);
int goya_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser);
diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
index f395721..46aed13 100644
--- a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
+++ b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
@@ -421,7 +421,6 @@
#define QM_ARB_ERR_MSG_EN_MASK (\
QM_ARB_ERR_MSG_EN_CHOISE_OVF_MASK |\
- QM_ARB_ERR_MSG_EN_CHOISE_WDT_MASK |\
QM_ARB_ERR_MSG_EN_AXI_LBW_ERR_MASK)
#define PCIE_AUX_FLR_CTRL_HW_CTRL_MASK 0x1
diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h
index 64143d4..9e08a98 100644
--- a/drivers/misc/mei/client.h
+++ b/drivers/misc/mei/client.h
@@ -182,11 +182,11 @@
*
* @cl: host client
*
- * Return: mtu
+ * Return: mtu or 0 if client is not connected
*/
static inline size_t mei_cl_mtu(const struct mei_cl *cl)
{
- return cl->me_cl->props.max_msg_length;
+ return cl->me_cl ? cl->me_cl->props.max_msg_length : 0;
}
/**
diff --git a/drivers/misc/mei/hw.h b/drivers/misc/mei/hw.h
index 8bac86c..df2fb95 100644
--- a/drivers/misc/mei/hw.h
+++ b/drivers/misc/mei/hw.h
@@ -224,7 +224,7 @@
u8 type;
u8 length;
u8 ext_payload[2];
- u8 hdr[0];
+ u8 hdr[];
};
/**
@@ -238,7 +238,7 @@
u8 count;
u8 size;
u8 reserved[2];
- struct mei_ext_hdr hdrs[0];
+ struct mei_ext_hdr hdrs[];
};
/*
@@ -308,7 +308,7 @@
u32 dma_ring:1;
u32 internal:1;
u32 msg_complete:1;
- u32 extension[0];
+ u32 extension[];
} __packed;
/* The length is up to 9 bits */
diff --git a/drivers/misc/mic/Kconfig b/drivers/misc/mic/Kconfig
deleted file mode 100644
index 8a7c2c5..0000000
--- a/drivers/misc/mic/Kconfig
+++ /dev/null
@@ -1,141 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-menu "Intel MIC & related support"
-
-config INTEL_MIC_BUS
- tristate "Intel MIC Bus Driver"
- depends on 64BIT && PCI && X86
- select DMA_OPS
- help
- This option is selected by any driver which registers a
- device or driver on the MIC Bus, such as CONFIG_INTEL_MIC_HOST,
- CONFIG_INTEL_MIC_CARD, CONFIG_INTEL_MIC_X100_DMA etc.
-
- If you are building a host/card kernel with an Intel MIC device
- then say M (recommended) or Y, else say N. If unsure say N.
-
- More information about the Intel MIC family as well as the Linux
- OS and tools for MIC to use with this driver are available from
- <http://software.intel.com/en-us/mic-developer>.
-
-config SCIF_BUS
- tristate "SCIF Bus Driver"
- depends on 64BIT && PCI && X86
- select DMA_OPS
- help
- This option is selected by any driver which registers a
- device or driver on the SCIF Bus, such as CONFIG_INTEL_MIC_HOST
- and CONFIG_INTEL_MIC_CARD.
-
- If you are building a host/card kernel with an Intel MIC device
- then say M (recommended) or Y, else say N. If unsure say N.
-
- More information about the Intel MIC family as well as the Linux
- OS and tools for MIC to use with this driver are available from
- <http://software.intel.com/en-us/mic-developer>.
-
-config VOP_BUS
- tristate "VOP Bus Driver"
- depends on HAS_DMA
- select DMA_OPS
- help
- This option is selected by any driver which registers a
- device or driver on the VOP Bus, such as CONFIG_INTEL_MIC_HOST
- and CONFIG_INTEL_MIC_CARD.
-
- If you are building a host/card kernel with an Intel MIC device
- then say M (recommended) or Y, else say N. If unsure say N.
-
- More information about the Intel MIC family as well as the Linux
- OS and tools for MIC to use with this driver are available from
- <http://software.intel.com/en-us/mic-developer>.
-
-config INTEL_MIC_HOST
- tristate "Intel MIC Host Driver"
- depends on 64BIT && PCI && X86
- depends on INTEL_MIC_BUS && SCIF_BUS && MIC_COSM && VOP_BUS
- select DMA_OPS
- help
- This enables Host Driver support for the Intel Many Integrated
- Core (MIC) family of PCIe form factor coprocessor devices that
- run a 64 bit Linux OS. The driver manages card OS state and
- enables communication between host and card. Intel MIC X100
- devices are currently supported.
-
- If you are building a host kernel with an Intel MIC device then
- say M (recommended) or Y, else say N. If unsure say N.
-
- More information about the Intel MIC family as well as the Linux
- OS and tools for MIC to use with this driver are available from
- <http://software.intel.com/en-us/mic-developer>.
-
-config INTEL_MIC_CARD
- tristate "Intel MIC Card Driver"
- depends on 64BIT && X86
- depends on INTEL_MIC_BUS && SCIF_BUS && MIC_COSM && VOP_BUS
- select VIRTIO
- help
- This enables card driver support for the Intel Many Integrated
- Core (MIC) device family. The card driver communicates shutdown/
- crash events to the host and allows registration/configuration of
- virtio devices. Intel MIC X100 devices are currently supported.
-
- If you are building a card kernel for an Intel MIC device then
- say M (recommended) or Y, else say N. If unsure say N.
-
- For more information see
- <http://software.intel.com/en-us/mic-developer>.
-
-config SCIF
- tristate "SCIF Driver"
- depends on 64BIT && PCI && X86 && SCIF_BUS && IOMMU_SUPPORT
- select IOMMU_IOVA
- help
- This enables SCIF Driver support for the Intel Many Integrated
- Core (MIC) family of PCIe form factor coprocessor devices that
- run a 64 bit Linux OS. The Symmetric Communication Interface
- (SCIF (pronounced as skiff)) is a low level communications API
- across PCIe currently implemented for MIC.
-
- If you are building a host kernel with an Intel MIC device then
- say M (recommended) or Y, else say N. If unsure say N.
-
- More information about the Intel MIC family as well as the Linux
- OS and tools for MIC to use with this driver are available from
- <http://software.intel.com/en-us/mic-developer>.
-
-config MIC_COSM
- tristate "Intel MIC Coprocessor State Management (COSM) Drivers"
- depends on 64BIT && PCI && X86 && SCIF
- help
- This enables COSM driver support for the Intel Many
- Integrated Core (MIC) family of PCIe form factor coprocessor
- devices. COSM drivers implement functions such as boot,
- shutdown, reset and reboot of MIC devices.
-
- If you are building a host kernel with an Intel MIC device then
- say M (recommended) or Y, else say N. If unsure say N.
-
- More information about the Intel MIC family as well as the Linux
- OS and tools for MIC to use with this driver are available from
- <http://software.intel.com/en-us/mic-developer>.
-
-config VOP
- tristate "VOP Driver"
- depends on VOP_BUS
- select VHOST_RING
- select VIRTIO
- help
- This enables VOP (Virtio over PCIe) Driver support for the Intel
- Many Integrated Core (MIC) family of PCIe form factor coprocessor
- devices. The VOP driver allows virtio drivers, e.g. net, console
- and block drivers, on the card connect to user space virtio
- devices on the host.
-
- If you are building a host kernel with an Intel MIC device then
- say M (recommended) or Y, else say N. If unsure say N.
-
- More information about the Intel MIC family as well as the Linux
- OS and tools for MIC to use with this driver are available from
- <http://software.intel.com/en-us/mic-developer>.
-
-endmenu
diff --git a/drivers/misc/mic/Makefile b/drivers/misc/mic/Makefile
deleted file mode 100644
index 1a43622..0000000
--- a/drivers/misc/mic/Makefile
+++ /dev/null
@@ -1,12 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile - Intel MIC Linux driver.
-# Copyright(c) 2013, Intel Corporation.
-#
-obj-$(CONFIG_INTEL_MIC_HOST) += host/
-obj-$(CONFIG_INTEL_MIC_CARD) += card/
-obj-y += bus/
-obj-$(CONFIG_SCIF) += scif/
-obj-$(CONFIG_MIC_COSM) += cosm/
-obj-$(CONFIG_MIC_COSM) += cosm_client/
-obj-$(CONFIG_VOP) += vop/
diff --git a/drivers/misc/mic/bus/Makefile b/drivers/misc/mic/bus/Makefile
deleted file mode 100644
index 0a6aa21..0000000
--- a/drivers/misc/mic/bus/Makefile
+++ /dev/null
@@ -1,9 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Makefile - Intel MIC Linux driver.
-# Copyright(c) 2014, Intel Corporation.
-#
-obj-$(CONFIG_INTEL_MIC_BUS) += mic_bus.o
-obj-$(CONFIG_SCIF_BUS) += scif_bus.o
-obj-$(CONFIG_MIC_COSM) += cosm_bus.o
-obj-$(CONFIG_VOP_BUS) += vop_bus.o
diff --git a/drivers/misc/mic/bus/cosm_bus.c b/drivers/misc/mic/bus/cosm_bus.c
deleted file mode 100644
index 5f2141c..0000000
--- a/drivers/misc/mic/bus/cosm_bus.c
+++ /dev/null
@@ -1,130 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC COSM Bus Driver
- */
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/idr.h>
-#include "cosm_bus.h"
-
-/* Unique numbering for cosm devices. */
-static DEFINE_IDA(cosm_index_ida);
-
-static int cosm_dev_probe(struct device *d)
-{
- struct cosm_device *dev = dev_to_cosm(d);
- struct cosm_driver *drv = drv_to_cosm(dev->dev.driver);
-
- return drv->probe(dev);
-}
-
-static int cosm_dev_remove(struct device *d)
-{
- struct cosm_device *dev = dev_to_cosm(d);
- struct cosm_driver *drv = drv_to_cosm(dev->dev.driver);
-
- drv->remove(dev);
- return 0;
-}
-
-static struct bus_type cosm_bus = {
- .name = "cosm_bus",
- .probe = cosm_dev_probe,
- .remove = cosm_dev_remove,
-};
-
-int cosm_register_driver(struct cosm_driver *driver)
-{
- driver->driver.bus = &cosm_bus;
- return driver_register(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(cosm_register_driver);
-
-void cosm_unregister_driver(struct cosm_driver *driver)
-{
- driver_unregister(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(cosm_unregister_driver);
-
-static inline void cosm_release_dev(struct device *d)
-{
- struct cosm_device *cdev = dev_to_cosm(d);
-
- kfree(cdev);
-}
-
-struct cosm_device *
-cosm_register_device(struct device *pdev, struct cosm_hw_ops *hw_ops)
-{
- struct cosm_device *cdev;
- int ret;
-
- cdev = kzalloc(sizeof(*cdev), GFP_KERNEL);
- if (!cdev)
- return ERR_PTR(-ENOMEM);
-
- cdev->dev.parent = pdev;
- cdev->dev.release = cosm_release_dev;
- cdev->hw_ops = hw_ops;
- dev_set_drvdata(&cdev->dev, cdev);
- cdev->dev.bus = &cosm_bus;
-
- /* Assign a unique device index and hence name */
- ret = ida_simple_get(&cosm_index_ida, 0, 0, GFP_KERNEL);
- if (ret < 0)
- goto free_cdev;
-
- cdev->index = ret;
- cdev->dev.id = ret;
- dev_set_name(&cdev->dev, "cosm-dev%u", cdev->index);
-
- ret = device_register(&cdev->dev);
- if (ret)
- goto ida_remove;
- return cdev;
-ida_remove:
- ida_simple_remove(&cosm_index_ida, cdev->index);
-free_cdev:
- put_device(&cdev->dev);
- return ERR_PTR(ret);
-}
-EXPORT_SYMBOL_GPL(cosm_register_device);
-
-void cosm_unregister_device(struct cosm_device *dev)
-{
- int index = dev->index; /* save for after device release */
-
- device_unregister(&dev->dev);
- ida_simple_remove(&cosm_index_ida, index);
-}
-EXPORT_SYMBOL_GPL(cosm_unregister_device);
-
-struct cosm_device *cosm_find_cdev_by_id(int id)
-{
- struct device *dev = subsys_find_device_by_id(&cosm_bus, id, NULL);
-
- return dev ? container_of(dev, struct cosm_device, dev) : NULL;
-}
-EXPORT_SYMBOL_GPL(cosm_find_cdev_by_id);
-
-static int __init cosm_init(void)
-{
- return bus_register(&cosm_bus);
-}
-
-static void __exit cosm_exit(void)
-{
- bus_unregister(&cosm_bus);
- ida_destroy(&cosm_index_ida);
-}
-
-core_initcall(cosm_init);
-module_exit(cosm_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC card OS state management bus driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/bus/cosm_bus.h b/drivers/misc/mic/bus/cosm_bus.h
deleted file mode 100644
index d50d7ae..0000000
--- a/drivers/misc/mic/bus/cosm_bus.h
+++ /dev/null
@@ -1,125 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC COSM Bus Driver
- */
-#ifndef _COSM_BUS_H_
-#define _COSM_BUS_H_
-
-#include <linux/scif.h>
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-
-/**
- * cosm_device - representation of a cosm device
- *
- * @attr_group: Pointer to list of sysfs attribute groups.
- * @sdev: Device for sysfs entries.
- * @state: MIC state.
- * @prev_state: MIC state previous to MIC_RESETTING
- * @shutdown_status: MIC status reported by card for shutdown/crashes.
- * @shutdown_status_int: Internal shutdown status maintained by the driver
- * @cosm_mutex: Mutex for synchronizing access to data structures.
- * @reset_trigger_work: Work for triggering reset requests.
- * @scif_work: Work for handling per device SCIF connections
- * @cmdline: Kernel command line.
- * @firmware: Firmware file name.
- * @ramdisk: Ramdisk file name.
- * @bootmode: Boot mode i.e. "linux" or "elf" for flash updates.
- * @log_buf_addr: Log buffer address for MIC.
- * @log_buf_len: Log buffer length address for MIC.
- * @state_sysfs: Sysfs dirent for notifying ring 3 about MIC state changes.
- * @hw_ops: the hardware bus ops for this device.
- * @dev: underlying device.
- * @index: unique position on the cosm bus
- * @dbg_dir: debug fs directory
- * @newepd: new endpoint from scif accept to be assigned to this cdev
- * @epd: SCIF endpoint for this cdev
- * @heartbeat_watchdog_enable: if heartbeat watchdog is enabled for this cdev
- * @sysfs_heartbeat_enable: sysfs setting for disabling heartbeat notification
- */
-struct cosm_device {
- const struct attribute_group **attr_group;
- struct device *sdev;
- u8 state;
- u8 prev_state;
- u8 shutdown_status;
- u8 shutdown_status_int;
- struct mutex cosm_mutex;
- struct work_struct reset_trigger_work;
- struct work_struct scif_work;
- char *cmdline;
- char *firmware;
- char *ramdisk;
- char *bootmode;
- void *log_buf_addr;
- int *log_buf_len;
- struct kernfs_node *state_sysfs;
- struct cosm_hw_ops *hw_ops;
- struct device dev;
- int index;
- struct dentry *dbg_dir;
- scif_epd_t newepd;
- scif_epd_t epd;
- bool heartbeat_watchdog_enable;
- bool sysfs_heartbeat_enable;
-};
-
-/**
- * cosm_driver - operations for a cosm driver
- *
- * @driver: underlying device driver (populate name and owner).
- * @probe: the function to call when a device is found. Returns 0 or -errno.
- * @remove: the function to call when a device is removed.
- */
-struct cosm_driver {
- struct device_driver driver;
- int (*probe)(struct cosm_device *dev);
- void (*remove)(struct cosm_device *dev);
-};
-
-/**
- * cosm_hw_ops - cosm bus ops
- *
- * @reset: trigger MIC reset
- * @force_reset: force MIC reset
- * @post_reset: inform MIC reset is complete
- * @ready: is MIC ready for OS download
- * @start: boot MIC
- * @stop: prepare MIC for reset
- * @family: return MIC HW family string
- * @stepping: return MIC HW stepping string
- * @aper: return MIC PCIe aperture
- */
-struct cosm_hw_ops {
- void (*reset)(struct cosm_device *cdev);
- void (*force_reset)(struct cosm_device *cdev);
- void (*post_reset)(struct cosm_device *cdev, enum mic_states state);
- bool (*ready)(struct cosm_device *cdev);
- int (*start)(struct cosm_device *cdev, int id);
- void (*stop)(struct cosm_device *cdev, bool force);
- ssize_t (*family)(struct cosm_device *cdev, char *buf);
- ssize_t (*stepping)(struct cosm_device *cdev, char *buf);
- struct mic_mw *(*aper)(struct cosm_device *cdev);
-};
-
-struct cosm_device *
-cosm_register_device(struct device *pdev, struct cosm_hw_ops *hw_ops);
-void cosm_unregister_device(struct cosm_device *dev);
-int cosm_register_driver(struct cosm_driver *drv);
-void cosm_unregister_driver(struct cosm_driver *drv);
-struct cosm_device *cosm_find_cdev_by_id(int id);
-
-static inline struct cosm_device *dev_to_cosm(struct device *dev)
-{
- return container_of(dev, struct cosm_device, dev);
-}
-
-static inline struct cosm_driver *drv_to_cosm(struct device_driver *drv)
-{
- return container_of(drv, struct cosm_driver, driver);
-}
-#endif /* _COSM_BUS_H */
diff --git a/drivers/misc/mic/bus/mic_bus.c b/drivers/misc/mic/bus/mic_bus.c
deleted file mode 100644
index a08cb29..0000000
--- a/drivers/misc/mic/bus/mic_bus.c
+++ /dev/null
@@ -1,194 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel MIC Bus driver.
- *
- * This implementation is very similar to the the virtio bus driver
- * implementation @ drivers/virtio/virtio.c
- */
-#include <linux/dma-map-ops.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/idr.h>
-#include <linux/mic_bus.h>
-
-static ssize_t device_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct mbus_device *dev = dev_to_mbus(d);
- return sprintf(buf, "0x%04x\n", dev->id.device);
-}
-static DEVICE_ATTR_RO(device);
-
-static ssize_t vendor_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct mbus_device *dev = dev_to_mbus(d);
- return sprintf(buf, "0x%04x\n", dev->id.vendor);
-}
-static DEVICE_ATTR_RO(vendor);
-
-static ssize_t modalias_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct mbus_device *dev = dev_to_mbus(d);
- return sprintf(buf, "mbus:d%08Xv%08X\n",
- dev->id.device, dev->id.vendor);
-}
-static DEVICE_ATTR_RO(modalias);
-
-static struct attribute *mbus_dev_attrs[] = {
- &dev_attr_device.attr,
- &dev_attr_vendor.attr,
- &dev_attr_modalias.attr,
- NULL,
-};
-ATTRIBUTE_GROUPS(mbus_dev);
-
-static inline int mbus_id_match(const struct mbus_device *dev,
- const struct mbus_device_id *id)
-{
- if (id->device != dev->id.device && id->device != MBUS_DEV_ANY_ID)
- return 0;
-
- return id->vendor == MBUS_DEV_ANY_ID || id->vendor == dev->id.vendor;
-}
-
-/*
- * This looks through all the IDs a driver claims to support. If any of them
- * match, we return 1 and the kernel will call mbus_dev_probe().
- */
-static int mbus_dev_match(struct device *dv, struct device_driver *dr)
-{
- unsigned int i;
- struct mbus_device *dev = dev_to_mbus(dv);
- const struct mbus_device_id *ids;
-
- ids = drv_to_mbus(dr)->id_table;
- for (i = 0; ids[i].device; i++)
- if (mbus_id_match(dev, &ids[i]))
- return 1;
- return 0;
-}
-
-static int mbus_uevent(struct device *dv, struct kobj_uevent_env *env)
-{
- struct mbus_device *dev = dev_to_mbus(dv);
-
- return add_uevent_var(env, "MODALIAS=mbus:d%08Xv%08X",
- dev->id.device, dev->id.vendor);
-}
-
-static int mbus_dev_probe(struct device *d)
-{
- int err;
- struct mbus_device *dev = dev_to_mbus(d);
- struct mbus_driver *drv = drv_to_mbus(dev->dev.driver);
-
- err = drv->probe(dev);
- if (!err)
- if (drv->scan)
- drv->scan(dev);
- return err;
-}
-
-static int mbus_dev_remove(struct device *d)
-{
- struct mbus_device *dev = dev_to_mbus(d);
- struct mbus_driver *drv = drv_to_mbus(dev->dev.driver);
-
- drv->remove(dev);
- return 0;
-}
-
-static struct bus_type mic_bus = {
- .name = "mic_bus",
- .match = mbus_dev_match,
- .dev_groups = mbus_dev_groups,
- .uevent = mbus_uevent,
- .probe = mbus_dev_probe,
- .remove = mbus_dev_remove,
-};
-
-int mbus_register_driver(struct mbus_driver *driver)
-{
- driver->driver.bus = &mic_bus;
- return driver_register(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(mbus_register_driver);
-
-void mbus_unregister_driver(struct mbus_driver *driver)
-{
- driver_unregister(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(mbus_unregister_driver);
-
-static void mbus_release_dev(struct device *d)
-{
- struct mbus_device *mbdev = dev_to_mbus(d);
- kfree(mbdev);
-}
-
-struct mbus_device *
-mbus_register_device(struct device *pdev, int id, const struct dma_map_ops *dma_ops,
- struct mbus_hw_ops *hw_ops, int index,
- void __iomem *mmio_va)
-{
- int ret;
- struct mbus_device *mbdev;
-
- mbdev = kzalloc(sizeof(*mbdev), GFP_KERNEL);
- if (!mbdev)
- return ERR_PTR(-ENOMEM);
-
- mbdev->mmio_va = mmio_va;
- mbdev->dev.parent = pdev;
- mbdev->id.device = id;
- mbdev->id.vendor = MBUS_DEV_ANY_ID;
- mbdev->dev.dma_ops = dma_ops;
- mbdev->dev.dma_mask = &mbdev->dev.coherent_dma_mask;
- dma_set_mask(&mbdev->dev, DMA_BIT_MASK(64));
- mbdev->dev.release = mbus_release_dev;
- mbdev->hw_ops = hw_ops;
- mbdev->dev.bus = &mic_bus;
- mbdev->index = index;
- dev_set_name(&mbdev->dev, "mbus-dev%u", mbdev->index);
- /*
- * device_register() causes the bus infrastructure to look for a
- * matching driver.
- */
- ret = device_register(&mbdev->dev);
- if (ret)
- goto free_mbdev;
- return mbdev;
-free_mbdev:
- put_device(&mbdev->dev);
- return ERR_PTR(ret);
-}
-EXPORT_SYMBOL_GPL(mbus_register_device);
-
-void mbus_unregister_device(struct mbus_device *mbdev)
-{
- device_unregister(&mbdev->dev);
-}
-EXPORT_SYMBOL_GPL(mbus_unregister_device);
-
-static int __init mbus_init(void)
-{
- return bus_register(&mic_bus);
-}
-
-static void __exit mbus_exit(void)
-{
- bus_unregister(&mic_bus);
-}
-
-core_initcall(mbus_init);
-module_exit(mbus_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC Bus driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/bus/scif_bus.c b/drivers/misc/mic/bus/scif_bus.c
deleted file mode 100644
index ad7c360..0000000
--- a/drivers/misc/mic/bus/scif_bus.c
+++ /dev/null
@@ -1,201 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel Symmetric Communications Interface Bus driver.
- */
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/idr.h>
-#include <linux/dma-map-ops.h>
-
-#include "scif_bus.h"
-
-static ssize_t device_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct scif_hw_dev *dev = dev_to_scif(d);
-
- return sprintf(buf, "0x%04x\n", dev->id.device);
-}
-static DEVICE_ATTR_RO(device);
-
-static ssize_t vendor_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct scif_hw_dev *dev = dev_to_scif(d);
-
- return sprintf(buf, "0x%04x\n", dev->id.vendor);
-}
-static DEVICE_ATTR_RO(vendor);
-
-static ssize_t modalias_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct scif_hw_dev *dev = dev_to_scif(d);
-
- return sprintf(buf, "scif:d%08Xv%08X\n",
- dev->id.device, dev->id.vendor);
-}
-static DEVICE_ATTR_RO(modalias);
-
-static struct attribute *scif_dev_attrs[] = {
- &dev_attr_device.attr,
- &dev_attr_vendor.attr,
- &dev_attr_modalias.attr,
- NULL,
-};
-ATTRIBUTE_GROUPS(scif_dev);
-
-static inline int scif_id_match(const struct scif_hw_dev *dev,
- const struct scif_hw_dev_id *id)
-{
- if (id->device != dev->id.device && id->device != SCIF_DEV_ANY_ID)
- return 0;
-
- return id->vendor == SCIF_DEV_ANY_ID || id->vendor == dev->id.vendor;
-}
-
-/*
- * This looks through all the IDs a driver claims to support. If any of them
- * match, we return 1 and the kernel will call scif_dev_probe().
- */
-static int scif_dev_match(struct device *dv, struct device_driver *dr)
-{
- unsigned int i;
- struct scif_hw_dev *dev = dev_to_scif(dv);
- const struct scif_hw_dev_id *ids;
-
- ids = drv_to_scif(dr)->id_table;
- for (i = 0; ids[i].device; i++)
- if (scif_id_match(dev, &ids[i]))
- return 1;
- return 0;
-}
-
-static int scif_uevent(struct device *dv, struct kobj_uevent_env *env)
-{
- struct scif_hw_dev *dev = dev_to_scif(dv);
-
- return add_uevent_var(env, "MODALIAS=scif:d%08Xv%08X",
- dev->id.device, dev->id.vendor);
-}
-
-static int scif_dev_probe(struct device *d)
-{
- struct scif_hw_dev *dev = dev_to_scif(d);
- struct scif_driver *drv = drv_to_scif(dev->dev.driver);
-
- return drv->probe(dev);
-}
-
-static int scif_dev_remove(struct device *d)
-{
- struct scif_hw_dev *dev = dev_to_scif(d);
- struct scif_driver *drv = drv_to_scif(dev->dev.driver);
-
- drv->remove(dev);
- return 0;
-}
-
-static struct bus_type scif_bus = {
- .name = "scif_bus",
- .match = scif_dev_match,
- .dev_groups = scif_dev_groups,
- .uevent = scif_uevent,
- .probe = scif_dev_probe,
- .remove = scif_dev_remove,
-};
-
-int scif_register_driver(struct scif_driver *driver)
-{
- driver->driver.bus = &scif_bus;
- return driver_register(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(scif_register_driver);
-
-void scif_unregister_driver(struct scif_driver *driver)
-{
- driver_unregister(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(scif_unregister_driver);
-
-static void scif_release_dev(struct device *d)
-{
- struct scif_hw_dev *sdev = dev_to_scif(d);
-
- kfree(sdev);
-}
-
-struct scif_hw_dev *
-scif_register_device(struct device *pdev, int id, const struct dma_map_ops *dma_ops,
- struct scif_hw_ops *hw_ops, u8 dnode, u8 snode,
- struct mic_mw *mmio, struct mic_mw *aper, void *dp,
- void __iomem *rdp, struct dma_chan **chan, int num_chan,
- bool card_rel_da)
-{
- int ret;
- struct scif_hw_dev *sdev;
-
- sdev = kzalloc(sizeof(*sdev), GFP_KERNEL);
- if (!sdev)
- return ERR_PTR(-ENOMEM);
-
- sdev->dev.parent = pdev;
- sdev->id.device = id;
- sdev->id.vendor = SCIF_DEV_ANY_ID;
- sdev->dev.dma_ops = dma_ops;
- sdev->dev.release = scif_release_dev;
- sdev->hw_ops = hw_ops;
- sdev->dnode = dnode;
- sdev->snode = snode;
- dev_set_drvdata(&sdev->dev, sdev);
- sdev->dev.bus = &scif_bus;
- sdev->mmio = mmio;
- sdev->aper = aper;
- sdev->dp = dp;
- sdev->rdp = rdp;
- sdev->dev.dma_mask = &sdev->dev.coherent_dma_mask;
- dma_set_mask(&sdev->dev, DMA_BIT_MASK(64));
- sdev->dma_ch = chan;
- sdev->num_dma_ch = num_chan;
- sdev->card_rel_da = card_rel_da;
- dev_set_name(&sdev->dev, "scif-dev%u", sdev->dnode);
- /*
- * device_register() causes the bus infrastructure to look for a
- * matching driver.
- */
- ret = device_register(&sdev->dev);
- if (ret)
- goto free_sdev;
- return sdev;
-free_sdev:
- put_device(&sdev->dev);
- return ERR_PTR(ret);
-}
-EXPORT_SYMBOL_GPL(scif_register_device);
-
-void scif_unregister_device(struct scif_hw_dev *sdev)
-{
- device_unregister(&sdev->dev);
-}
-EXPORT_SYMBOL_GPL(scif_unregister_device);
-
-static int __init scif_init(void)
-{
- return bus_register(&scif_bus);
-}
-
-static void __exit scif_exit(void)
-{
- bus_unregister(&scif_bus);
-}
-
-core_initcall(scif_init);
-module_exit(scif_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) SCIF Bus driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/bus/scif_bus.h b/drivers/misc/mic/bus/scif_bus.h
deleted file mode 100644
index 4981eb5..0000000
--- a/drivers/misc/mic/bus/scif_bus.h
+++ /dev/null
@@ -1,125 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel Symmetric Communications Interface Bus driver.
- */
-#ifndef _SCIF_BUS_H_
-#define _SCIF_BUS_H_
-/*
- * Everything a scif driver needs to work with any particular scif
- * hardware abstraction layer.
- */
-#include <linux/dma-map-ops.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-
-struct scif_hw_dev_id {
- u32 device;
- u32 vendor;
-};
-
-#define MIC_SCIF_DEV 1
-#define SCIF_DEV_ANY_ID 0xffffffff
-
-/**
- * scif_hw_dev - representation of a hardware device abstracted for scif
- * @hw_ops: the hardware ops supported by this device
- * @id: the device type identification (used to match it with a driver)
- * @mmio: MMIO memory window
- * @aper: Aperture memory window
- * @dev: underlying device
- * @dnode - The destination node which this device will communicate with.
- * @snode - The source node for this device.
- * @dp - Self device page
- * @rdp - Remote device page
- * @dma_ch - Array of DMA channels
- * @num_dma_ch - Number of DMA channels available
- * @card_rel_da - Set to true if DMA addresses programmed in the DMA engine
- * are relative to the card point of view
- */
-struct scif_hw_dev {
- struct scif_hw_ops *hw_ops;
- struct scif_hw_dev_id id;
- struct mic_mw *mmio;
- struct mic_mw *aper;
- struct device dev;
- u8 dnode;
- u8 snode;
- void *dp;
- void __iomem *rdp;
- struct dma_chan **dma_ch;
- int num_dma_ch;
- bool card_rel_da;
-};
-
-/**
- * scif_driver - operations for a scif I/O driver
- * @driver: underlying device driver (populate name and owner).
- * @id_table: the ids serviced by this driver.
- * @probe: the function to call when a device is found. Returns 0 or -errno.
- * @remove: the function to call when a device is removed.
- */
-struct scif_driver {
- struct device_driver driver;
- const struct scif_hw_dev_id *id_table;
- int (*probe)(struct scif_hw_dev *dev);
- void (*remove)(struct scif_hw_dev *dev);
-};
-
-/**
- * scif_hw_ops - Hardware operations for accessing a SCIF device on the SCIF bus.
- *
- * @next_db: Obtain the next available doorbell.
- * @request_irq: Request an interrupt on a particular doorbell.
- * @free_irq: Free an interrupt requested previously.
- * @ack_interrupt: acknowledge an interrupt in the ISR.
- * @send_intr: Send an interrupt to the remote node on a specified doorbell.
- * @send_p2p_intr: Send an interrupt to the peer node on a specified doorbell
- * which is specifically targeted for a peer to peer node.
- * @remap: Map a buffer with the specified physical address and length.
- * @unmap: Unmap a buffer previously mapped.
- */
-struct scif_hw_ops {
- int (*next_db)(struct scif_hw_dev *sdev);
- struct mic_irq * (*request_irq)(struct scif_hw_dev *sdev,
- irqreturn_t (*func)(int irq,
- void *data),
- const char *name, void *data,
- int db);
- void (*free_irq)(struct scif_hw_dev *sdev,
- struct mic_irq *cookie, void *data);
- void (*ack_interrupt)(struct scif_hw_dev *sdev, int num);
- void (*send_intr)(struct scif_hw_dev *sdev, int db);
- void (*send_p2p_intr)(struct scif_hw_dev *sdev, int db,
- struct mic_mw *mw);
- void __iomem * (*remap)(struct scif_hw_dev *sdev,
- phys_addr_t pa, size_t len);
- void (*unmap)(struct scif_hw_dev *sdev, void __iomem *va);
-};
-
-int scif_register_driver(struct scif_driver *driver);
-void scif_unregister_driver(struct scif_driver *driver);
-struct scif_hw_dev *
-scif_register_device(struct device *pdev, int id,
- const struct dma_map_ops *dma_ops,
- struct scif_hw_ops *hw_ops, u8 dnode, u8 snode,
- struct mic_mw *mmio, struct mic_mw *aper,
- void *dp, void __iomem *rdp,
- struct dma_chan **chan, int num_chan,
- bool card_rel_da);
-void scif_unregister_device(struct scif_hw_dev *sdev);
-
-static inline struct scif_hw_dev *dev_to_scif(struct device *dev)
-{
- return container_of(dev, struct scif_hw_dev, dev);
-}
-
-static inline struct scif_driver *drv_to_scif(struct device_driver *drv)
-{
- return container_of(drv, struct scif_driver, driver);
-}
-#endif /* _SCIF_BUS_H */
diff --git a/drivers/misc/mic/bus/vop_bus.c b/drivers/misc/mic/bus/vop_bus.c
deleted file mode 100644
index 6935ddc..0000000
--- a/drivers/misc/mic/bus/vop_bus.c
+++ /dev/null
@@ -1,194 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Intel Virtio Over PCIe (VOP) Bus driver.
- */
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/idr.h>
-#include <linux/dma-map-ops.h>
-
-#include "vop_bus.h"
-
-static ssize_t device_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct vop_device *dev = dev_to_vop(d);
-
- return sprintf(buf, "0x%04x\n", dev->id.device);
-}
-static DEVICE_ATTR_RO(device);
-
-static ssize_t vendor_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct vop_device *dev = dev_to_vop(d);
-
- return sprintf(buf, "0x%04x\n", dev->id.vendor);
-}
-static DEVICE_ATTR_RO(vendor);
-
-static ssize_t modalias_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct vop_device *dev = dev_to_vop(d);
-
- return sprintf(buf, "vop:d%08Xv%08X\n",
- dev->id.device, dev->id.vendor);
-}
-static DEVICE_ATTR_RO(modalias);
-
-static struct attribute *vop_dev_attrs[] = {
- &dev_attr_device.attr,
- &dev_attr_vendor.attr,
- &dev_attr_modalias.attr,
- NULL,
-};
-ATTRIBUTE_GROUPS(vop_dev);
-
-static inline int vop_id_match(const struct vop_device *dev,
- const struct vop_device_id *id)
-{
- if (id->device != dev->id.device && id->device != VOP_DEV_ANY_ID)
- return 0;
-
- return id->vendor == VOP_DEV_ANY_ID || id->vendor == dev->id.vendor;
-}
-
-/*
- * This looks through all the IDs a driver claims to support. If any of them
- * match, we return 1 and the kernel will call vop_dev_probe().
- */
-static int vop_dev_match(struct device *dv, struct device_driver *dr)
-{
- unsigned int i;
- struct vop_device *dev = dev_to_vop(dv);
- const struct vop_device_id *ids;
-
- ids = drv_to_vop(dr)->id_table;
- for (i = 0; ids[i].device; i++)
- if (vop_id_match(dev, &ids[i]))
- return 1;
- return 0;
-}
-
-static int vop_uevent(struct device *dv, struct kobj_uevent_env *env)
-{
- struct vop_device *dev = dev_to_vop(dv);
-
- return add_uevent_var(env, "MODALIAS=vop:d%08Xv%08X",
- dev->id.device, dev->id.vendor);
-}
-
-static int vop_dev_probe(struct device *d)
-{
- struct vop_device *dev = dev_to_vop(d);
- struct vop_driver *drv = drv_to_vop(dev->dev.driver);
-
- return drv->probe(dev);
-}
-
-static int vop_dev_remove(struct device *d)
-{
- struct vop_device *dev = dev_to_vop(d);
- struct vop_driver *drv = drv_to_vop(dev->dev.driver);
-
- drv->remove(dev);
- return 0;
-}
-
-static struct bus_type vop_bus = {
- .name = "vop_bus",
- .match = vop_dev_match,
- .dev_groups = vop_dev_groups,
- .uevent = vop_uevent,
- .probe = vop_dev_probe,
- .remove = vop_dev_remove,
-};
-
-int vop_register_driver(struct vop_driver *driver)
-{
- driver->driver.bus = &vop_bus;
- return driver_register(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(vop_register_driver);
-
-void vop_unregister_driver(struct vop_driver *driver)
-{
- driver_unregister(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(vop_unregister_driver);
-
-static void vop_release_dev(struct device *d)
-{
- struct vop_device *dev = dev_to_vop(d);
-
- kfree(dev);
-}
-
-struct vop_device *
-vop_register_device(struct device *pdev, int id,
- const struct dma_map_ops *dma_ops,
- struct vop_hw_ops *hw_ops, u8 dnode, struct mic_mw *aper,
- struct dma_chan *chan)
-{
- int ret;
- struct vop_device *vdev;
-
- vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
- if (!vdev)
- return ERR_PTR(-ENOMEM);
-
- vdev->dev.parent = pdev;
- vdev->id.device = id;
- vdev->id.vendor = VOP_DEV_ANY_ID;
- vdev->dev.dma_ops = dma_ops;
- vdev->dev.dma_mask = &vdev->dev.coherent_dma_mask;
- dma_set_mask(&vdev->dev, DMA_BIT_MASK(64));
- vdev->dev.release = vop_release_dev;
- vdev->hw_ops = hw_ops;
- vdev->dev.bus = &vop_bus;
- vdev->dnode = dnode;
- vdev->aper = aper;
- vdev->dma_ch = chan;
- vdev->index = dnode - 1;
- dev_set_name(&vdev->dev, "vop-dev%u", vdev->index);
- /*
- * device_register() causes the bus infrastructure to look for a
- * matching driver.
- */
- ret = device_register(&vdev->dev);
- if (ret)
- goto free_vdev;
- return vdev;
-free_vdev:
- put_device(&vdev->dev);
- return ERR_PTR(ret);
-}
-EXPORT_SYMBOL_GPL(vop_register_device);
-
-void vop_unregister_device(struct vop_device *dev)
-{
- device_unregister(&dev->dev);
-}
-EXPORT_SYMBOL_GPL(vop_unregister_device);
-
-static int __init vop_init(void)
-{
- return bus_register(&vop_bus);
-}
-
-static void __exit vop_exit(void)
-{
- bus_unregister(&vop_bus);
-}
-
-core_initcall(vop_init);
-module_exit(vop_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) VOP Bus driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/bus/vop_bus.h b/drivers/misc/mic/bus/vop_bus.h
deleted file mode 100644
index 4fa0280..0000000
--- a/drivers/misc/mic/bus/vop_bus.h
+++ /dev/null
@@ -1,129 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Intel Virtio over PCIe Bus driver.
- */
-#ifndef _VOP_BUS_H_
-#define _VOP_BUS_H_
-/*
- * Everything a vop driver needs to work with any particular vop
- * implementation.
- */
-#include <linux/dmaengine.h>
-#include <linux/interrupt.h>
-
-#include "../common/mic_dev.h"
-
-struct vop_device_id {
- u32 device;
- u32 vendor;
-};
-
-#define VOP_DEV_TRNSP 1
-#define VOP_DEV_ANY_ID 0xffffffff
-/*
- * Size of the internal buffer used during DMA's as an intermediate buffer
- * for copy to/from user. Must be an integral number of pages.
- */
-#define VOP_INT_DMA_BUF_SIZE PAGE_ALIGN(64 * 1024ULL)
-
-/**
- * vop_device - representation of a device using vop
- * @hw_ops: the hardware ops supported by this device.
- * @id: the device type identification (used to match it with a driver).
- * @dev: underlying device.
- * @dnode - The destination node which this device will communicate with.
- * @aper: Aperture memory window
- * @dma_ch - DMA channel
- * @index: unique position on the vop bus
- */
-struct vop_device {
- struct vop_hw_ops *hw_ops;
- struct vop_device_id id;
- struct device dev;
- u8 dnode;
- struct mic_mw *aper;
- struct dma_chan *dma_ch;
- int index;
-};
-
-/**
- * vop_driver - operations for a vop I/O driver
- * @driver: underlying device driver (populate name and owner).
- * @id_table: the ids serviced by this driver.
- * @probe: the function to call when a device is found. Returns 0 or -errno.
- * @remove: the function to call when a device is removed.
- */
-struct vop_driver {
- struct device_driver driver;
- const struct vop_device_id *id_table;
- int (*probe)(struct vop_device *dev);
- void (*remove)(struct vop_device *dev);
-};
-
-/**
- * vop_hw_ops - Hardware operations for accessing a VOP device on the VOP bus.
- *
- * @next_db: Obtain the next available doorbell.
- * @request_irq: Request an interrupt on a particular doorbell.
- * @free_irq: Free an interrupt requested previously.
- * @ack_interrupt: acknowledge an interrupt in the ISR.
- * @get_remote_dp: Get access to the virtio device page used by the remote
- * node to add/remove/configure virtio devices.
- * @get_dp: Get access to the virtio device page used by the self
- * node to add/remove/configure virtio devices.
- * @send_intr: Send an interrupt to the peer node on a specified doorbell.
- * @remap: Map a buffer with the specified DMA address and length.
- * @unmap: Unmap a buffer previously mapped.
- * @dma_filter: The DMA filter function to use for obtaining access to
- * a DMA channel on the peer node.
- */
-struct vop_hw_ops {
- int (*next_db)(struct vop_device *vpdev);
- struct mic_irq *(*request_irq)(struct vop_device *vpdev,
- irqreturn_t (*func)(int irq, void *data),
- const char *name, void *data,
- int intr_src);
- void (*free_irq)(struct vop_device *vpdev,
- struct mic_irq *cookie, void *data);
- void (*ack_interrupt)(struct vop_device *vpdev, int num);
- void __iomem * (*get_remote_dp)(struct vop_device *vpdev);
- void * (*get_dp)(struct vop_device *vpdev);
- void (*send_intr)(struct vop_device *vpdev, int db);
- void __iomem * (*remap)(struct vop_device *vpdev,
- dma_addr_t pa, size_t len);
- void (*unmap)(struct vop_device *vpdev, void __iomem *va);
-};
-
-struct vop_device *
-vop_register_device(struct device *pdev, int id,
- const struct dma_map_ops *dma_ops,
- struct vop_hw_ops *hw_ops, u8 dnode, struct mic_mw *aper,
- struct dma_chan *chan);
-void vop_unregister_device(struct vop_device *dev);
-int vop_register_driver(struct vop_driver *drv);
-void vop_unregister_driver(struct vop_driver *drv);
-
-/*
- * module_vop_driver() - Helper macro for drivers that don't do
- * anything special in module init/exit. This eliminates a lot of
- * boilerplate. Each module may only use this macro once, and
- * calling it replaces module_init() and module_exit()
- */
-#define module_vop_driver(__vop_driver) \
- module_driver(__vop_driver, vop_register_driver, \
- vop_unregister_driver)
-
-static inline struct vop_device *dev_to_vop(struct device *dev)
-{
- return container_of(dev, struct vop_device, dev);
-}
-
-static inline struct vop_driver *drv_to_vop(struct device_driver *drv)
-{
- return container_of(drv, struct vop_driver, driver);
-}
-#endif /* _VOP_BUS_H */
diff --git a/drivers/misc/mic/card/Makefile b/drivers/misc/mic/card/Makefile
deleted file mode 100644
index 921a7e7..0000000
--- a/drivers/misc/mic/card/Makefile
+++ /dev/null
@@ -1,11 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile - Intel MIC Linux driver.
-# Copyright(c) 2013, Intel Corporation.
-#
-ccflags-y += -DINTEL_MIC_CARD
-
-obj-$(CONFIG_INTEL_MIC_CARD) += mic_card.o
-mic_card-y += mic_x100.o
-mic_card-y += mic_device.o
-mic_card-y += mic_debugfs.o
diff --git a/drivers/misc/mic/card/mic_debugfs.c b/drivers/misc/mic/card/mic_debugfs.c
deleted file mode 100644
index 4c326e8..0000000
--- a/drivers/misc/mic/card/mic_debugfs.c
+++ /dev/null
@@ -1,85 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Disclaimer: The codes contained in these modules may be specific to
- * the Intel Software Development Platform codenamed: Knights Ferry, and
- * the Intel product codenamed: Knights Corner, and are not backward
- * compatible with other Intel products. Additionally, Intel will NOT
- * support the codes or instruction set in future products.
- *
- * Intel MIC Card driver.
- */
-#include <linux/debugfs.h>
-#include <linux/delay.h>
-#include <linux/seq_file.h>
-#include <linux/interrupt.h>
-#include <linux/device.h>
-
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-
-/* Debugfs parent dir */
-static struct dentry *mic_dbg;
-
-/*
- * mic_intr_show - Send interrupts to host.
- */
-static int mic_intr_show(struct seq_file *s, void *unused)
-{
- struct mic_driver *mdrv = s->private;
- struct mic_device *mdev = &mdrv->mdev;
-
- mic_send_intr(mdev, 0);
- msleep(1000);
- mic_send_intr(mdev, 1);
- msleep(1000);
- mic_send_intr(mdev, 2);
- msleep(1000);
- mic_send_intr(mdev, 3);
- msleep(1000);
-
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(mic_intr);
-
-/*
- * mic_create_card_debug_dir - Initialize MIC debugfs entries.
- */
-void __init mic_create_card_debug_dir(struct mic_driver *mdrv)
-{
- if (!mic_dbg)
- return;
-
- mdrv->dbg_dir = debugfs_create_dir(mdrv->name, mic_dbg);
-
- debugfs_create_file("intr_test", 0444, mdrv->dbg_dir, mdrv,
- &mic_intr_fops);
-}
-
-/*
- * mic_delete_card_debug_dir - Uninitialize MIC debugfs entries.
- */
-void mic_delete_card_debug_dir(struct mic_driver *mdrv)
-{
- debugfs_remove_recursive(mdrv->dbg_dir);
-}
-
-/*
- * mic_init_card_debugfs - Initialize global debugfs entry.
- */
-void __init mic_init_card_debugfs(void)
-{
- mic_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL);
-}
-
-/*
- * mic_exit_card_debugfs - Uninitialize global debugfs entry
- */
-void mic_exit_card_debugfs(void)
-{
- debugfs_remove(mic_dbg);
-}
diff --git a/drivers/misc/mic/card/mic_device.c b/drivers/misc/mic/card/mic_device.c
deleted file mode 100644
index a156062..0000000
--- a/drivers/misc/mic/card/mic_device.c
+++ /dev/null
@@ -1,417 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Disclaimer: The codes contained in these modules may be specific to
- * the Intel Software Development Platform codenamed: Knights Ferry, and
- * the Intel product codenamed: Knights Corner, and are not backward
- * compatible with other Intel products. Additionally, Intel will NOT
- * support the codes or instruction set in future products.
- *
- * Intel MIC Card driver.
- */
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/interrupt.h>
-#include <linux/reboot.h>
-#include <linux/dmaengine.h>
-#include <linux/kmod.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-
-static struct mic_driver *g_drv;
-
-static int __init mic_dp_init(void)
-{
- struct mic_driver *mdrv = g_drv;
- struct mic_device *mdev = &mdrv->mdev;
- struct mic_bootparam __iomem *bootparam;
- u64 lo, hi, dp_dma_addr;
- u32 magic;
-
- lo = mic_read_spad(&mdrv->mdev, MIC_DPLO_SPAD);
- hi = mic_read_spad(&mdrv->mdev, MIC_DPHI_SPAD);
-
- dp_dma_addr = lo | (hi << 32);
- mdrv->dp = mic_card_map(mdev, dp_dma_addr, MIC_DP_SIZE);
- if (!mdrv->dp) {
- dev_err(mdrv->dev, "Cannot remap Aperture BAR\n");
- return -ENOMEM;
- }
- bootparam = mdrv->dp;
- magic = ioread32(&bootparam->magic);
- if (MIC_MAGIC != magic) {
- dev_err(mdrv->dev, "bootparam magic mismatch 0x%x\n", magic);
- return -EIO;
- }
- return 0;
-}
-
-/* Uninitialize the device page */
-static void mic_dp_uninit(void)
-{
- mic_card_unmap(&g_drv->mdev, g_drv->dp);
-}
-
-/**
- * mic_request_card_irq - request an irq.
- *
- * @handler: interrupt handler passed to request_threaded_irq.
- * @thread_fn: thread fn. passed to request_threaded_irq.
- * @name: The ASCII name of the callee requesting the irq.
- * @data: private data that is returned back when calling the
- * function handler.
- * @index: The doorbell index of the requester.
- *
- * returns: The cookie that is transparent to the caller. Passed
- * back when calling mic_free_irq. An appropriate error code
- * is returned on failure. Caller needs to use IS_ERR(return_val)
- * to check for failure and PTR_ERR(return_val) to obtained the
- * error code.
- *
- */
-struct mic_irq *
-mic_request_card_irq(irq_handler_t handler,
- irq_handler_t thread_fn, const char *name,
- void *data, int index)
-{
- int rc = 0;
- unsigned long cookie;
- struct mic_driver *mdrv = g_drv;
-
- rc = request_threaded_irq(mic_db_to_irq(mdrv, index), handler,
- thread_fn, 0, name, data);
- if (rc) {
- dev_err(mdrv->dev, "request_threaded_irq failed rc = %d\n", rc);
- goto err;
- }
- mdrv->irq_info.irq_usage_count[index]++;
- cookie = index;
- return (struct mic_irq *)cookie;
-err:
- return ERR_PTR(rc);
-}
-
-/**
- * mic_free_card_irq - free irq.
- *
- * @cookie: cookie obtained during a successful call to mic_request_threaded_irq
- * @data: private data specified by the calling function during the
- * mic_request_threaded_irq
- *
- * returns: none.
- */
-void mic_free_card_irq(struct mic_irq *cookie, void *data)
-{
- int index;
- struct mic_driver *mdrv = g_drv;
-
- index = (unsigned long)cookie & 0xFFFFU;
- free_irq(mic_db_to_irq(mdrv, index), data);
- mdrv->irq_info.irq_usage_count[index]--;
-}
-
-/**
- * mic_next_card_db - Get the doorbell with minimum usage count.
- *
- * Returns the irq index.
- */
-int mic_next_card_db(void)
-{
- int i;
- int index = 0;
- struct mic_driver *mdrv = g_drv;
-
- for (i = 0; i < mdrv->intr_info.num_intr; i++) {
- if (mdrv->irq_info.irq_usage_count[i] <
- mdrv->irq_info.irq_usage_count[index])
- index = i;
- }
-
- return index;
-}
-
-/**
- * mic_init_irq - Initialize irq information.
- *
- * Returns 0 in success. Appropriate error code on failure.
- */
-static int mic_init_irq(void)
-{
- struct mic_driver *mdrv = g_drv;
-
- mdrv->irq_info.irq_usage_count = kzalloc((sizeof(u32) *
- mdrv->intr_info.num_intr),
- GFP_KERNEL);
- if (!mdrv->irq_info.irq_usage_count)
- return -ENOMEM;
- return 0;
-}
-
-/**
- * mic_uninit_irq - Uninitialize irq information.
- *
- * None.
- */
-static void mic_uninit_irq(void)
-{
- struct mic_driver *mdrv = g_drv;
-
- kfree(mdrv->irq_info.irq_usage_count);
-}
-
-static inline struct mic_driver *scdev_to_mdrv(struct scif_hw_dev *scdev)
-{
- return dev_get_drvdata(scdev->dev.parent);
-}
-
-static struct mic_irq *
-___mic_request_irq(struct scif_hw_dev *scdev,
- irqreturn_t (*func)(int irq, void *data),
- const char *name, void *data,
- int db)
-{
- return mic_request_card_irq(func, NULL, name, data, db);
-}
-
-static void
-___mic_free_irq(struct scif_hw_dev *scdev,
- struct mic_irq *cookie, void *data)
-{
- return mic_free_card_irq(cookie, data);
-}
-
-static void ___mic_ack_interrupt(struct scif_hw_dev *scdev, int num)
-{
- struct mic_driver *mdrv = scdev_to_mdrv(scdev);
-
- mic_ack_interrupt(&mdrv->mdev);
-}
-
-static int ___mic_next_db(struct scif_hw_dev *scdev)
-{
- return mic_next_card_db();
-}
-
-static void ___mic_send_intr(struct scif_hw_dev *scdev, int db)
-{
- struct mic_driver *mdrv = scdev_to_mdrv(scdev);
-
- mic_send_intr(&mdrv->mdev, db);
-}
-
-static void ___mic_send_p2p_intr(struct scif_hw_dev *scdev, int db,
- struct mic_mw *mw)
-{
- mic_send_p2p_intr(db, mw);
-}
-
-static void __iomem *
-___mic_ioremap(struct scif_hw_dev *scdev,
- phys_addr_t pa, size_t len)
-{
- struct mic_driver *mdrv = scdev_to_mdrv(scdev);
-
- return mic_card_map(&mdrv->mdev, pa, len);
-}
-
-static void ___mic_iounmap(struct scif_hw_dev *scdev, void __iomem *va)
-{
- struct mic_driver *mdrv = scdev_to_mdrv(scdev);
-
- mic_card_unmap(&mdrv->mdev, va);
-}
-
-static struct scif_hw_ops scif_hw_ops = {
- .request_irq = ___mic_request_irq,
- .free_irq = ___mic_free_irq,
- .ack_interrupt = ___mic_ack_interrupt,
- .next_db = ___mic_next_db,
- .send_intr = ___mic_send_intr,
- .send_p2p_intr = ___mic_send_p2p_intr,
- .remap = ___mic_ioremap,
- .unmap = ___mic_iounmap,
-};
-
-static inline struct mic_driver *vpdev_to_mdrv(struct vop_device *vpdev)
-{
- return dev_get_drvdata(vpdev->dev.parent);
-}
-
-static struct mic_irq *
-__mic_request_irq(struct vop_device *vpdev,
- irqreturn_t (*func)(int irq, void *data),
- const char *name, void *data, int intr_src)
-{
- return mic_request_card_irq(func, NULL, name, data, intr_src);
-}
-
-static void __mic_free_irq(struct vop_device *vpdev,
- struct mic_irq *cookie, void *data)
-{
- return mic_free_card_irq(cookie, data);
-}
-
-static void __mic_ack_interrupt(struct vop_device *vpdev, int num)
-{
- struct mic_driver *mdrv = vpdev_to_mdrv(vpdev);
-
- mic_ack_interrupt(&mdrv->mdev);
-}
-
-static int __mic_next_db(struct vop_device *vpdev)
-{
- return mic_next_card_db();
-}
-
-static void __iomem *__mic_get_remote_dp(struct vop_device *vpdev)
-{
- struct mic_driver *mdrv = vpdev_to_mdrv(vpdev);
-
- return mdrv->dp;
-}
-
-static void __mic_send_intr(struct vop_device *vpdev, int db)
-{
- struct mic_driver *mdrv = vpdev_to_mdrv(vpdev);
-
- mic_send_intr(&mdrv->mdev, db);
-}
-
-static void __iomem *__mic_ioremap(struct vop_device *vpdev,
- dma_addr_t pa, size_t len)
-{
- struct mic_driver *mdrv = vpdev_to_mdrv(vpdev);
-
- return mic_card_map(&mdrv->mdev, pa, len);
-}
-
-static void __mic_iounmap(struct vop_device *vpdev, void __iomem *va)
-{
- struct mic_driver *mdrv = vpdev_to_mdrv(vpdev);
-
- mic_card_unmap(&mdrv->mdev, va);
-}
-
-static struct vop_hw_ops vop_hw_ops = {
- .request_irq = __mic_request_irq,
- .free_irq = __mic_free_irq,
- .ack_interrupt = __mic_ack_interrupt,
- .next_db = __mic_next_db,
- .get_remote_dp = __mic_get_remote_dp,
- .send_intr = __mic_send_intr,
- .remap = __mic_ioremap,
- .unmap = __mic_iounmap,
-};
-
-static int mic_request_dma_chans(struct mic_driver *mdrv)
-{
- dma_cap_mask_t mask;
- struct dma_chan *chan;
-
- dma_cap_zero(mask);
- dma_cap_set(DMA_MEMCPY, mask);
-
- do {
- chan = dma_request_channel(mask, NULL, NULL);
- if (chan) {
- mdrv->dma_ch[mdrv->num_dma_ch++] = chan;
- if (mdrv->num_dma_ch >= MIC_MAX_DMA_CHAN)
- break;
- }
- } while (chan);
- dev_info(mdrv->dev, "DMA channels # %d\n", mdrv->num_dma_ch);
- return mdrv->num_dma_ch;
-}
-
-static void mic_free_dma_chans(struct mic_driver *mdrv)
-{
- int i = 0;
-
- for (i = 0; i < mdrv->num_dma_ch; i++) {
- dma_release_channel(mdrv->dma_ch[i]);
- mdrv->dma_ch[i] = NULL;
- }
- mdrv->num_dma_ch = 0;
-}
-
-/*
- * mic_driver_init - MIC driver initialization tasks.
- *
- * Returns 0 in success. Appropriate error code on failure.
- */
-int __init mic_driver_init(struct mic_driver *mdrv)
-{
- int rc;
- struct mic_bootparam __iomem *bootparam;
- u8 node_id;
-
- g_drv = mdrv;
- /* Unloading the card module is not supported. */
- if (!try_module_get(mdrv->dev->driver->owner)) {
- rc = -ENODEV;
- goto done;
- }
- rc = mic_dp_init();
- if (rc)
- goto put;
- rc = mic_init_irq();
- if (rc)
- goto dp_uninit;
- if (!mic_request_dma_chans(mdrv)) {
- rc = -ENODEV;
- goto irq_uninit;
- }
- mdrv->vpdev = vop_register_device(mdrv->dev, VOP_DEV_TRNSP,
- NULL, &vop_hw_ops, 0,
- NULL, mdrv->dma_ch[0]);
- if (IS_ERR(mdrv->vpdev)) {
- rc = PTR_ERR(mdrv->vpdev);
- goto dma_free;
- }
- bootparam = mdrv->dp;
- node_id = ioread8(&bootparam->node_id);
- mdrv->scdev = scif_register_device(mdrv->dev, MIC_SCIF_DEV,
- NULL, &scif_hw_ops,
- 0, node_id, &mdrv->mdev.mmio, NULL,
- NULL, mdrv->dp, mdrv->dma_ch,
- mdrv->num_dma_ch, true);
- if (IS_ERR(mdrv->scdev)) {
- rc = PTR_ERR(mdrv->scdev);
- goto vop_remove;
- }
- mic_create_card_debug_dir(mdrv);
-done:
- return rc;
-vop_remove:
- vop_unregister_device(mdrv->vpdev);
-dma_free:
- mic_free_dma_chans(mdrv);
-irq_uninit:
- mic_uninit_irq();
-dp_uninit:
- mic_dp_uninit();
-put:
- module_put(mdrv->dev->driver->owner);
- return rc;
-}
-
-/*
- * mic_driver_uninit - MIC driver uninitialization tasks.
- *
- * Returns None
- */
-void mic_driver_uninit(struct mic_driver *mdrv)
-{
- mic_delete_card_debug_dir(mdrv);
- scif_unregister_device(mdrv->scdev);
- vop_unregister_device(mdrv->vpdev);
- mic_free_dma_chans(mdrv);
- mic_uninit_irq();
- mic_dp_uninit();
- module_put(mdrv->dev->driver->owner);
-}
diff --git a/drivers/misc/mic/card/mic_device.h b/drivers/misc/mic/card/mic_device.h
deleted file mode 100644
index d6cc69a..0000000
--- a/drivers/misc/mic/card/mic_device.h
+++ /dev/null
@@ -1,137 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Disclaimer: The codes contained in these modules may be specific to
- * the Intel Software Development Platform codenamed: Knights Ferry, and
- * the Intel product codenamed: Knights Corner, and are not backward
- * compatible with other Intel products. Additionally, Intel will NOT
- * support the codes or instruction set in future products.
- *
- * Intel MIC Card driver.
- */
-#ifndef _MIC_CARD_DEVICE_H_
-#define _MIC_CARD_DEVICE_H_
-
-#include <linux/workqueue.h>
-#include <linux/io.h>
-#include <linux/interrupt.h>
-#include <linux/mic_bus.h>
-#include "../bus/scif_bus.h"
-#include "../bus/vop_bus.h"
-
-/**
- * struct mic_intr_info - Contains h/w specific interrupt sources info
- *
- * @num_intr: The number of irqs available
- */
-struct mic_intr_info {
- u32 num_intr;
-};
-
-/**
- * struct mic_irq_info - OS specific irq information
- *
- * @irq_usage_count: usage count array tracking the number of sources
- * assigned for each irq.
- */
-struct mic_irq_info {
- int *irq_usage_count;
-};
-
-/**
- * struct mic_device - MIC device information.
- *
- * @mmio: MMIO bar information.
- */
-struct mic_device {
- struct mic_mw mmio;
-};
-
-/**
- * struct mic_driver - MIC card driver information.
- *
- * @name: Name for MIC driver.
- * @dbg_dir: debugfs directory of this MIC device.
- * @dev: The device backing this MIC.
- * @dp: The pointer to the virtio device page.
- * @mdev: MIC device information for the host.
- * @hotplug_work: Hot plug work for adding/removing virtio devices.
- * @irq_info: The OS specific irq information
- * @intr_info: H/W specific interrupt information.
- * @dma_mbdev: dma device on the MIC virtual bus.
- * @dma_ch - Array of DMA channels
- * @num_dma_ch - Number of DMA channels available
- * @scdev: SCIF device on the SCIF virtual bus.
- * @vpdev: Virtio over PCIe device on the VOP virtual bus.
- */
-struct mic_driver {
- char name[20];
- struct dentry *dbg_dir;
- struct device *dev;
- void __iomem *dp;
- struct mic_device mdev;
- struct work_struct hotplug_work;
- struct mic_irq_info irq_info;
- struct mic_intr_info intr_info;
- struct mbus_device *dma_mbdev;
- struct dma_chan *dma_ch[MIC_MAX_DMA_CHAN];
- int num_dma_ch;
- struct scif_hw_dev *scdev;
- struct vop_device *vpdev;
-};
-
-/**
- * struct mic_irq - opaque pointer used as cookie
- */
-struct mic_irq;
-
-/**
- * mic_mmio_read - read from an MMIO register.
- * @mw: MMIO register base virtual address.
- * @offset: register offset.
- *
- * RETURNS: register value.
- */
-static inline u32 mic_mmio_read(struct mic_mw *mw, u32 offset)
-{
- return ioread32(mw->va + offset);
-}
-
-/**
- * mic_mmio_write - write to an MMIO register.
- * @mw: MMIO register base virtual address.
- * @val: the data value to put into the register
- * @offset: register offset.
- *
- * RETURNS: none.
- */
-static inline void
-mic_mmio_write(struct mic_mw *mw, u32 val, u32 offset)
-{
- iowrite32(val, mw->va + offset);
-}
-
-int mic_driver_init(struct mic_driver *mdrv);
-void mic_driver_uninit(struct mic_driver *mdrv);
-int mic_next_card_db(void);
-struct mic_irq *
-mic_request_card_irq(irq_handler_t handler, irq_handler_t thread_fn,
- const char *name, void *data, int db);
-void mic_free_card_irq(struct mic_irq *cookie, void *data);
-u32 mic_read_spad(struct mic_device *mdev, unsigned int idx);
-void mic_send_intr(struct mic_device *mdev, int doorbell);
-void mic_send_p2p_intr(int doorbell, struct mic_mw *mw);
-int mic_db_to_irq(struct mic_driver *mdrv, int db);
-u32 mic_ack_interrupt(struct mic_device *mdev);
-void mic_hw_intr_init(struct mic_driver *mdrv);
-void __iomem *
-mic_card_map(struct mic_device *mdev, dma_addr_t addr, size_t size);
-void mic_card_unmap(struct mic_device *mdev, void __iomem *addr);
-void __init mic_create_card_debug_dir(struct mic_driver *mdrv);
-void mic_delete_card_debug_dir(struct mic_driver *mdrv);
-void __init mic_init_card_debugfs(void);
-void mic_exit_card_debugfs(void);
-#endif
diff --git a/drivers/misc/mic/card/mic_x100.c b/drivers/misc/mic/card/mic_x100.c
deleted file mode 100644
index c8bff291..0000000
--- a/drivers/misc/mic/card/mic_x100.c
+++ /dev/null
@@ -1,347 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Disclaimer: The codes contained in these modules may be specific to
- * the Intel Software Development Platform codenamed: Knights Ferry, and
- * the Intel product codenamed: Knights Corner, and are not backward
- * compatible with other Intel products. Additionally, Intel will NOT
- * support the codes or instruction set in future products.
- *
- * Intel MIC Card driver.
- */
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/platform_device.h>
-
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_x100.h"
-
-static const char mic_driver_name[] = "mic";
-
-static struct mic_driver g_drv;
-
-/**
- * mic_read_spad - read from the scratchpad register
- * @mdev: pointer to mic_device instance
- * @idx: index to scratchpad register, 0 based
- *
- * This function allows reading of the 32bit scratchpad register.
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-u32 mic_read_spad(struct mic_device *mdev, unsigned int idx)
-{
- return mic_mmio_read(&mdev->mmio,
- MIC_X100_SBOX_BASE_ADDRESS +
- MIC_X100_SBOX_SPAD0 + idx * 4);
-}
-
-/**
- * __mic_send_intr - Send interrupt to Host.
- * @mdev: pointer to mic_device instance
- * @doorbell: Doorbell number.
- */
-void mic_send_intr(struct mic_device *mdev, int doorbell)
-{
- struct mic_mw *mw = &mdev->mmio;
-
- if (doorbell > MIC_X100_MAX_DOORBELL_IDX)
- return;
- /* Ensure that the interrupt is ordered w.r.t previous stores. */
- wmb();
- mic_mmio_write(mw, MIC_X100_SBOX_SDBIC0_DBREQ_BIT,
- MIC_X100_SBOX_BASE_ADDRESS +
- (MIC_X100_SBOX_SDBIC0 + (4 * doorbell)));
-}
-
-/*
- * mic_x100_send_sbox_intr - Send an MIC_X100_SBOX interrupt to MIC.
- */
-static void mic_x100_send_sbox_intr(struct mic_mw *mw, int doorbell)
-{
- u64 apic_icr_offset = MIC_X100_SBOX_APICICR0 + doorbell * 8;
- u32 apicicr_low = mic_mmio_read(mw, MIC_X100_SBOX_BASE_ADDRESS +
- apic_icr_offset);
-
- /* for MIC we need to make sure we "hit" the send_icr bit (13) */
- apicicr_low = (apicicr_low | (1 << 13));
- /*
- * Ensure that the interrupt is ordered w.r.t. previous stores
- * to main memory. Fence instructions are not implemented in X100
- * since execution is in order but a compiler barrier is still
- * required.
- */
- wmb();
- mic_mmio_write(mw, apicicr_low,
- MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset);
-}
-
-static void mic_x100_send_rdmasr_intr(struct mic_mw *mw, int doorbell)
-{
- int rdmasr_offset = MIC_X100_SBOX_RDMASR0 + (doorbell << 2);
- /*
- * Ensure that the interrupt is ordered w.r.t. previous stores
- * to main memory. Fence instructions are not implemented in X100
- * since execution is in order but a compiler barrier is still
- * required.
- */
- wmb();
- mic_mmio_write(mw, 0, MIC_X100_SBOX_BASE_ADDRESS + rdmasr_offset);
-}
-
-/**
- * mic_ack_interrupt - Device specific interrupt handling.
- * @mdev: pointer to mic_device instance
- *
- * Returns: bitmask of doorbell events triggered.
- */
-u32 mic_ack_interrupt(struct mic_device *mdev)
-{
- return 0;
-}
-
-static inline int mic_get_sbox_irq(int db)
-{
- return MIC_X100_IRQ_BASE + db;
-}
-
-static inline int mic_get_rdmasr_irq(int index)
-{
- return MIC_X100_RDMASR_IRQ_BASE + index;
-}
-
-void mic_send_p2p_intr(int db, struct mic_mw *mw)
-{
- int rdmasr_index;
-
- if (db < MIC_X100_NUM_SBOX_IRQ) {
- mic_x100_send_sbox_intr(mw, db);
- } else {
- rdmasr_index = db - MIC_X100_NUM_SBOX_IRQ;
- mic_x100_send_rdmasr_intr(mw, rdmasr_index);
- }
-}
-
-/**
- * mic_hw_intr_init - Initialize h/w specific interrupt
- * information.
- * @mdrv: pointer to mic_driver
- */
-void mic_hw_intr_init(struct mic_driver *mdrv)
-{
- mdrv->intr_info.num_intr = MIC_X100_NUM_SBOX_IRQ +
- MIC_X100_NUM_RDMASR_IRQ;
-}
-
-/**
- * mic_db_to_irq - Retrieve irq number corresponding to a doorbell.
- * @mdrv: pointer to mic_driver
- * @db: The doorbell obtained for which the irq is needed. Doorbell
- * may correspond to an sbox doorbell or an rdmasr index.
- *
- * Returns the irq corresponding to the doorbell.
- */
-int mic_db_to_irq(struct mic_driver *mdrv, int db)
-{
- int rdmasr_index;
-
- /*
- * The total number of doorbell interrupts on the card are 16. Indices
- * 0-8 falls in the SBOX category and 8-15 fall in the RDMASR category.
- */
- if (db < MIC_X100_NUM_SBOX_IRQ) {
- return mic_get_sbox_irq(db);
- } else {
- rdmasr_index = db - MIC_X100_NUM_SBOX_IRQ;
- return mic_get_rdmasr_irq(rdmasr_index);
- }
-}
-
-/*
- * mic_card_map - Allocate virtual address for a remote memory region.
- * @mdev: pointer to mic_device instance.
- * @addr: Remote DMA address.
- * @size: Size of the region.
- *
- * Returns: Virtual address backing the remote memory region.
- */
-void __iomem *
-mic_card_map(struct mic_device *mdev, dma_addr_t addr, size_t size)
-{
- return ioremap(addr, size);
-}
-
-/*
- * mic_card_unmap - Unmap the virtual address for a remote memory region.
- * @mdev: pointer to mic_device instance.
- * @addr: Virtual address for remote memory region.
- *
- * Returns: None.
- */
-void mic_card_unmap(struct mic_device *mdev, void __iomem *addr)
-{
- iounmap(addr);
-}
-
-static inline struct mic_driver *mbdev_to_mdrv(struct mbus_device *mbdev)
-{
- return dev_get_drvdata(mbdev->dev.parent);
-}
-
-static struct mic_irq *
-_mic_request_threaded_irq(struct mbus_device *mbdev,
- irq_handler_t handler, irq_handler_t thread_fn,
- const char *name, void *data, int intr_src)
-{
- int rc = 0;
- unsigned int irq = intr_src;
- unsigned long cookie = irq;
-
- rc = request_threaded_irq(irq, handler, thread_fn, 0, name, data);
- if (rc) {
- dev_err(mbdev_to_mdrv(mbdev)->dev,
- "request_threaded_irq failed rc = %d\n", rc);
- return ERR_PTR(rc);
- }
- return (struct mic_irq *)cookie;
-}
-
-static void _mic_free_irq(struct mbus_device *mbdev,
- struct mic_irq *cookie, void *data)
-{
- unsigned long irq = (unsigned long)cookie;
- free_irq(irq, data);
-}
-
-static void _mic_ack_interrupt(struct mbus_device *mbdev, int num)
-{
- mic_ack_interrupt(&mbdev_to_mdrv(mbdev)->mdev);
-}
-
-static struct mbus_hw_ops mbus_hw_ops = {
- .request_threaded_irq = _mic_request_threaded_irq,
- .free_irq = _mic_free_irq,
- .ack_interrupt = _mic_ack_interrupt,
-};
-
-static int __init mic_probe(struct platform_device *pdev)
-{
- struct mic_driver *mdrv = &g_drv;
- struct mic_device *mdev = &mdrv->mdev;
- int rc = 0;
-
- mdrv->dev = &pdev->dev;
- snprintf(mdrv->name, sizeof(mic_driver_name), mic_driver_name);
-
- /* FIXME: use dma_set_mask_and_coherent() and check result */
- dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
-
- mdev->mmio.pa = MIC_X100_MMIO_BASE;
- mdev->mmio.len = MIC_X100_MMIO_LEN;
- mdev->mmio.va = devm_ioremap(&pdev->dev, MIC_X100_MMIO_BASE,
- MIC_X100_MMIO_LEN);
- if (!mdev->mmio.va) {
- dev_err(&pdev->dev, "Cannot remap MMIO BAR\n");
- rc = -EIO;
- goto done;
- }
- mic_hw_intr_init(mdrv);
- platform_set_drvdata(pdev, mdrv);
- mdrv->dma_mbdev = mbus_register_device(mdrv->dev, MBUS_DEV_DMA_MIC,
- NULL, &mbus_hw_ops, 0,
- mdrv->mdev.mmio.va);
- if (IS_ERR(mdrv->dma_mbdev)) {
- rc = PTR_ERR(mdrv->dma_mbdev);
- dev_err(&pdev->dev, "mbus_add_device failed rc %d\n", rc);
- goto done;
- }
- rc = mic_driver_init(mdrv);
- if (rc) {
- dev_err(&pdev->dev, "mic_driver_init failed rc %d\n", rc);
- goto remove_dma;
- }
-done:
- return rc;
-remove_dma:
- mbus_unregister_device(mdrv->dma_mbdev);
- return rc;
-}
-
-static int mic_remove(struct platform_device *pdev)
-{
- struct mic_driver *mdrv = &g_drv;
-
- mic_driver_uninit(mdrv);
- mbus_unregister_device(mdrv->dma_mbdev);
- return 0;
-}
-
-static void mic_platform_shutdown(struct platform_device *pdev)
-{
- mic_remove(pdev);
-}
-
-static struct platform_driver __refdata mic_platform_driver = {
- .probe = mic_probe,
- .remove = mic_remove,
- .shutdown = mic_platform_shutdown,
- .driver = {
- .name = mic_driver_name,
- },
-};
-
-static struct platform_device *mic_platform_dev;
-
-static int __init mic_init(void)
-{
- int ret;
- struct cpuinfo_x86 *c = &cpu_data(0);
-
- if (!(c->x86 == 11 && c->x86_model == 1)) {
- ret = -ENODEV;
- pr_err("%s not running on X100 ret %d\n", __func__, ret);
- goto done;
- }
-
- request_module("mic_x100_dma");
- mic_init_card_debugfs();
-
- mic_platform_dev = platform_device_register_simple(mic_driver_name,
- 0, NULL, 0);
- ret = PTR_ERR_OR_ZERO(mic_platform_dev);
- if (ret) {
- pr_err("platform_device_register_full ret %d\n", ret);
- goto cleanup_debugfs;
- }
- ret = platform_driver_register(&mic_platform_driver);
- if (ret) {
- pr_err("platform_driver_register ret %d\n", ret);
- goto device_unregister;
- }
- return ret;
-
-device_unregister:
- platform_device_unregister(mic_platform_dev);
-cleanup_debugfs:
- mic_exit_card_debugfs();
-done:
- return ret;
-}
-
-static void __exit mic_exit(void)
-{
- platform_driver_unregister(&mic_platform_driver);
- platform_device_unregister(mic_platform_dev);
- mic_exit_card_debugfs();
-}
-
-module_init(mic_init);
-module_exit(mic_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC X100 Card driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/card/mic_x100.h b/drivers/misc/mic/card/mic_x100.h
deleted file mode 100644
index 46644dd..0000000
--- a/drivers/misc/mic/card/mic_x100.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Disclaimer: The codes contained in these modules may be specific to
- * the Intel Software Development Platform codenamed: Knights Ferry, and
- * the Intel product codenamed: Knights Corner, and are not backward
- * compatible with other Intel products. Additionally, Intel will NOT
- * support the codes or instruction set in future products.
- *
- * Intel MIC Card driver.
- */
-#ifndef _MIC_X100_CARD_H_
-#define _MIC_X100_CARD_H_
-
-#define MIC_X100_MMIO_BASE 0x08007C0000ULL
-#define MIC_X100_MMIO_LEN 0x00020000ULL
-#define MIC_X100_SBOX_BASE_ADDRESS 0x00010000ULL
-
-#define MIC_X100_SBOX_SPAD0 0x0000AB20
-#define MIC_X100_SBOX_SDBIC0 0x0000CC90
-#define MIC_X100_SBOX_SDBIC0_DBREQ_BIT 0x80000000
-#define MIC_X100_SBOX_RDMASR0 0x0000B180
-#define MIC_X100_SBOX_APICICR0 0x0000A9D0
-
-#define MIC_X100_MAX_DOORBELL_IDX 8
-
-#define MIC_X100_NUM_SBOX_IRQ 8
-#define MIC_X100_NUM_RDMASR_IRQ 8
-#define MIC_X100_SBOX_IRQ_BASE 0
-#define MIC_X100_RDMASR_IRQ_BASE 17
-
-#define MIC_X100_IRQ_BASE 26
-
-#endif
diff --git a/drivers/misc/mic/common/mic_dev.h b/drivers/misc/mic/common/mic_dev.h
deleted file mode 100644
index f94f08d..0000000
--- a/drivers/misc/mic/common/mic_dev.h
+++ /dev/null
@@ -1,55 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC driver.
- */
-#ifndef __MIC_DEV_H__
-#define __MIC_DEV_H__
-
-/* The maximum number of MIC devices supported in a single host system. */
-#define MIC_MAX_NUM_DEVS 128
-
-/**
- * enum mic_hw_family - The hardware family to which a device belongs.
- */
-enum mic_hw_family {
- MIC_FAMILY_X100 = 0,
- MIC_FAMILY_X200,
- MIC_FAMILY_UNKNOWN,
- MIC_FAMILY_LAST
-};
-
-/**
- * struct mic_mw - MIC memory window
- *
- * @pa: Base physical address.
- * @va: Base ioremap'd virtual address.
- * @len: Size of the memory window.
- */
-struct mic_mw {
- phys_addr_t pa;
- void __iomem *va;
- resource_size_t len;
-};
-
-/*
- * Scratch pad register offsets used by the host to communicate
- * device page DMA address to the card.
- */
-#define MIC_DPLO_SPAD 14
-#define MIC_DPHI_SPAD 15
-
-/*
- * These values are supposed to be in the config_change field of the
- * device page when the host sends a config change interrupt to the card.
- */
-#define MIC_VIRTIO_PARAM_DEV_REMOVE 0x1
-#define MIC_VIRTIO_PARAM_CONFIG_CHANGED 0x2
-
-/* Maximum number of DMA channels */
-#define MIC_MAX_DMA_CHAN 4
-
-#endif
diff --git a/drivers/misc/mic/cosm/Makefile b/drivers/misc/mic/cosm/Makefile
deleted file mode 100644
index 97d74cb..0000000
--- a/drivers/misc/mic/cosm/Makefile
+++ /dev/null
@@ -1,11 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile - Intel MIC Coprocessor State Management (COSM) Driver
-# Copyright(c) 2015, Intel Corporation.
-#
-obj-$(CONFIG_MIC_COSM) += mic_cosm.o
-
-mic_cosm-objs := cosm_main.o
-mic_cosm-objs += cosm_debugfs.o
-mic_cosm-objs += cosm_sysfs.o
-mic_cosm-objs += cosm_scif_server.o
diff --git a/drivers/misc/mic/cosm/cosm_debugfs.c b/drivers/misc/mic/cosm/cosm_debugfs.c
deleted file mode 100644
index cb55653..0000000
--- a/drivers/misc/mic/cosm/cosm_debugfs.c
+++ /dev/null
@@ -1,116 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC Coprocessor State Management (COSM) Driver
- */
-
-#include <linux/debugfs.h>
-#include <linux/slab.h>
-#include <linux/io.h>
-#include "cosm_main.h"
-
-/* Debugfs parent dir */
-static struct dentry *cosm_dbg;
-
-/*
- * log_buf_show - Display MIC kernel log buffer
- *
- * log_buf addr/len is read from System.map by user space
- * and populated in sysfs entries.
- */
-static int log_buf_show(struct seq_file *s, void *unused)
-{
- void __iomem *log_buf_va;
- int __iomem *log_buf_len_va;
- struct cosm_device *cdev = s->private;
- void *kva;
- int size;
- u64 aper_offset;
-
- if (!cdev || !cdev->log_buf_addr || !cdev->log_buf_len)
- goto done;
-
- mutex_lock(&cdev->cosm_mutex);
- switch (cdev->state) {
- case MIC_BOOTING:
- case MIC_ONLINE:
- case MIC_SHUTTING_DOWN:
- break;
- default:
- goto unlock;
- }
-
- /*
- * Card kernel will never be relocated and any kernel text/data mapping
- * can be translated to phys address by subtracting __START_KERNEL_map.
- */
- aper_offset = (u64)cdev->log_buf_len - __START_KERNEL_map;
- log_buf_len_va = cdev->hw_ops->aper(cdev)->va + aper_offset;
- aper_offset = (u64)cdev->log_buf_addr - __START_KERNEL_map;
- log_buf_va = cdev->hw_ops->aper(cdev)->va + aper_offset;
-
- size = ioread32(log_buf_len_va);
- kva = kmalloc(size, GFP_KERNEL);
- if (!kva)
- goto unlock;
-
- memcpy_fromio(kva, log_buf_va, size);
- seq_write(s, kva, size);
- kfree(kva);
-unlock:
- mutex_unlock(&cdev->cosm_mutex);
-done:
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(log_buf);
-
-/*
- * force_reset_show - Force MIC reset
- *
- * Invokes the force_reset COSM bus op instead of the standard reset
- * op in case a force reset of the MIC device is required
- */
-static int force_reset_show(struct seq_file *s, void *pos)
-{
- struct cosm_device *cdev = s->private;
-
- cosm_stop(cdev, true);
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(force_reset);
-
-void cosm_create_debug_dir(struct cosm_device *cdev)
-{
- char name[16];
-
- if (!cosm_dbg)
- return;
-
- scnprintf(name, sizeof(name), "mic%d", cdev->index);
- cdev->dbg_dir = debugfs_create_dir(name, cosm_dbg);
-
- debugfs_create_file("log_buf", 0444, cdev->dbg_dir, cdev,
- &log_buf_fops);
- debugfs_create_file("force_reset", 0444, cdev->dbg_dir, cdev,
- &force_reset_fops);
-}
-
-void cosm_delete_debug_dir(struct cosm_device *cdev)
-{
- debugfs_remove_recursive(cdev->dbg_dir);
-}
-
-void cosm_init_debugfs(void)
-{
- cosm_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL);
-}
-
-void cosm_exit_debugfs(void)
-{
- debugfs_remove(cosm_dbg);
-}
diff --git a/drivers/misc/mic/cosm/cosm_main.c b/drivers/misc/mic/cosm/cosm_main.c
deleted file mode 100644
index ebb0eac..0000000
--- a/drivers/misc/mic/cosm/cosm_main.c
+++ /dev/null
@@ -1,382 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC Coprocessor State Management (COSM) Driver
- */
-
-#include <linux/module.h>
-#include <linux/delay.h>
-#include <linux/idr.h>
-#include <linux/slab.h>
-#include <linux/cred.h>
-#include "cosm_main.h"
-
-static const char cosm_driver_name[] = "mic";
-
-/* COSM ID allocator */
-static struct ida g_cosm_ida;
-/* Class of MIC devices for sysfs accessibility. */
-static struct class *g_cosm_class;
-/* Number of MIC devices */
-static atomic_t g_num_dev;
-
-/**
- * cosm_hw_reset - Issue a HW reset for the MIC device
- * @cdev: pointer to cosm_device instance
- * @force: force a MIC to reset even if it is already reset and ready
- */
-static void cosm_hw_reset(struct cosm_device *cdev, bool force)
-{
- int i;
-
-#define MIC_RESET_TO (45)
- if (force && cdev->hw_ops->force_reset)
- cdev->hw_ops->force_reset(cdev);
- else
- cdev->hw_ops->reset(cdev);
-
- for (i = 0; i < MIC_RESET_TO; i++) {
- if (cdev->hw_ops->ready(cdev)) {
- cosm_set_state(cdev, MIC_READY);
- return;
- }
- /*
- * Resets typically take 10s of seconds to complete.
- * Since an MMIO read is required to check if the
- * firmware is ready or not, a 1 second delay works nicely.
- */
- msleep(1000);
- }
- cosm_set_state(cdev, MIC_RESET_FAILED);
-}
-
-/**
- * cosm_start - Start the MIC
- * @cdev: pointer to cosm_device instance
- *
- * This function prepares an MIC for boot and initiates boot.
- * RETURNS: An appropriate -ERRNO error value on error, or 0 for success.
- */
-int cosm_start(struct cosm_device *cdev)
-{
- const struct cred *orig_cred;
- struct cred *override_cred;
- int rc;
-
- mutex_lock(&cdev->cosm_mutex);
- if (!cdev->bootmode) {
- dev_err(&cdev->dev, "%s %d bootmode not set\n",
- __func__, __LINE__);
- rc = -EINVAL;
- goto unlock_ret;
- }
-retry:
- if (cdev->state != MIC_READY) {
- dev_err(&cdev->dev, "%s %d MIC state not READY\n",
- __func__, __LINE__);
- rc = -EINVAL;
- goto unlock_ret;
- }
- if (!cdev->hw_ops->ready(cdev)) {
- cosm_hw_reset(cdev, false);
- /*
- * The state will either be MIC_READY if the reset succeeded
- * or MIC_RESET_FAILED if the firmware reset failed.
- */
- goto retry;
- }
-
- /*
- * Set credentials to root to allow non-root user to download initramsfs
- * with 600 permissions
- */
- override_cred = prepare_creds();
- if (!override_cred) {
- dev_err(&cdev->dev, "%s %d prepare_creds failed\n",
- __func__, __LINE__);
- rc = -ENOMEM;
- goto unlock_ret;
- }
- override_cred->fsuid = GLOBAL_ROOT_UID;
- orig_cred = override_creds(override_cred);
-
- rc = cdev->hw_ops->start(cdev, cdev->index);
-
- revert_creds(orig_cred);
- put_cred(override_cred);
- if (rc)
- goto unlock_ret;
-
- /*
- * If linux is being booted, card is treated 'online' only
- * when the scif interface in the card is up. If anything else
- * is booted, we set card to 'online' immediately.
- */
- if (!strcmp(cdev->bootmode, "linux"))
- cosm_set_state(cdev, MIC_BOOTING);
- else
- cosm_set_state(cdev, MIC_ONLINE);
-unlock_ret:
- mutex_unlock(&cdev->cosm_mutex);
- if (rc)
- dev_err(&cdev->dev, "cosm_start failed rc %d\n", rc);
- return rc;
-}
-
-/**
- * cosm_stop - Prepare the MIC for reset and trigger reset
- * @cdev: pointer to cosm_device instance
- * @force: force a MIC to reset even if it is already reset and ready.
- *
- * RETURNS: None
- */
-void cosm_stop(struct cosm_device *cdev, bool force)
-{
- mutex_lock(&cdev->cosm_mutex);
- if (cdev->state != MIC_READY || force) {
- /*
- * Don't call hw_ops if they have been called previously.
- * stop(..) calls device_unregister and will crash the system if
- * called multiple times.
- */
- u8 state = cdev->state == MIC_RESETTING ?
- cdev->prev_state : cdev->state;
- bool call_hw_ops = state != MIC_RESET_FAILED &&
- state != MIC_READY;
-
- if (cdev->state != MIC_RESETTING)
- cosm_set_state(cdev, MIC_RESETTING);
- cdev->heartbeat_watchdog_enable = false;
- if (call_hw_ops)
- cdev->hw_ops->stop(cdev, force);
- cosm_hw_reset(cdev, force);
- cosm_set_shutdown_status(cdev, MIC_NOP);
- if (call_hw_ops && cdev->hw_ops->post_reset)
- cdev->hw_ops->post_reset(cdev, cdev->state);
- }
- mutex_unlock(&cdev->cosm_mutex);
- flush_work(&cdev->scif_work);
-}
-
-/**
- * cosm_reset_trigger_work - Trigger MIC reset
- * @work: The work structure
- *
- * This work is scheduled whenever the host wants to reset the MIC.
- */
-static void cosm_reset_trigger_work(struct work_struct *work)
-{
- struct cosm_device *cdev = container_of(work, struct cosm_device,
- reset_trigger_work);
- cosm_stop(cdev, false);
-}
-
-/**
- * cosm_reset - Schedule MIC reset
- * @cdev: pointer to cosm_device instance
- *
- * RETURNS: An -EINVAL if the card is already READY or 0 for success.
- */
-int cosm_reset(struct cosm_device *cdev)
-{
- int rc = 0;
-
- mutex_lock(&cdev->cosm_mutex);
- if (cdev->state != MIC_READY) {
- if (cdev->state != MIC_RESETTING) {
- cdev->prev_state = cdev->state;
- cosm_set_state(cdev, MIC_RESETTING);
- schedule_work(&cdev->reset_trigger_work);
- }
- } else {
- dev_err(&cdev->dev, "%s %d MIC is READY\n", __func__, __LINE__);
- rc = -EINVAL;
- }
- mutex_unlock(&cdev->cosm_mutex);
- return rc;
-}
-
-/**
- * cosm_shutdown - Initiate MIC shutdown.
- * @cdev: pointer to cosm_device instance
- *
- * RETURNS: None
- */
-int cosm_shutdown(struct cosm_device *cdev)
-{
- struct cosm_msg msg = { .id = COSM_MSG_SHUTDOWN };
- int rc = 0;
-
- mutex_lock(&cdev->cosm_mutex);
- if (cdev->state != MIC_ONLINE) {
- rc = -EINVAL;
- dev_err(&cdev->dev, "%s %d skipping shutdown in state: %s\n",
- __func__, __LINE__, cosm_state_string[cdev->state]);
- goto err;
- }
-
- if (!cdev->epd) {
- rc = -ENOTCONN;
- dev_err(&cdev->dev, "%s %d scif endpoint not connected rc %d\n",
- __func__, __LINE__, rc);
- goto err;
- }
-
- rc = scif_send(cdev->epd, &msg, sizeof(msg), SCIF_SEND_BLOCK);
- if (rc < 0) {
- dev_err(&cdev->dev, "%s %d scif_send failed rc %d\n",
- __func__, __LINE__, rc);
- goto err;
- }
- cdev->heartbeat_watchdog_enable = false;
- cosm_set_state(cdev, MIC_SHUTTING_DOWN);
- rc = 0;
-err:
- mutex_unlock(&cdev->cosm_mutex);
- return rc;
-}
-
-static int cosm_driver_probe(struct cosm_device *cdev)
-{
- int rc;
-
- /* Initialize SCIF server at first probe */
- if (atomic_add_return(1, &g_num_dev) == 1) {
- rc = cosm_scif_init();
- if (rc)
- goto scif_exit;
- }
- mutex_init(&cdev->cosm_mutex);
- INIT_WORK(&cdev->reset_trigger_work, cosm_reset_trigger_work);
- INIT_WORK(&cdev->scif_work, cosm_scif_work);
- cdev->sysfs_heartbeat_enable = true;
- cosm_sysfs_init(cdev);
- cdev->sdev = device_create_with_groups(g_cosm_class, cdev->dev.parent,
- MKDEV(0, cdev->index), cdev, cdev->attr_group,
- "mic%d", cdev->index);
- if (IS_ERR(cdev->sdev)) {
- rc = PTR_ERR(cdev->sdev);
- dev_err(&cdev->dev, "device_create_with_groups failed rc %d\n",
- rc);
- goto scif_exit;
- }
-
- cdev->state_sysfs = sysfs_get_dirent(cdev->sdev->kobj.sd,
- "state");
- if (!cdev->state_sysfs) {
- rc = -ENODEV;
- dev_err(&cdev->dev, "sysfs_get_dirent failed rc %d\n", rc);
- goto destroy_device;
- }
- cosm_create_debug_dir(cdev);
- return 0;
-destroy_device:
- device_destroy(g_cosm_class, MKDEV(0, cdev->index));
-scif_exit:
- if (atomic_dec_and_test(&g_num_dev))
- cosm_scif_exit();
- return rc;
-}
-
-static void cosm_driver_remove(struct cosm_device *cdev)
-{
- cosm_delete_debug_dir(cdev);
- sysfs_put(cdev->state_sysfs);
- device_destroy(g_cosm_class, MKDEV(0, cdev->index));
- flush_work(&cdev->reset_trigger_work);
- cosm_stop(cdev, false);
- if (atomic_dec_and_test(&g_num_dev))
- cosm_scif_exit();
-
- /* These sysfs entries might have allocated */
- kfree(cdev->cmdline);
- kfree(cdev->firmware);
- kfree(cdev->ramdisk);
- kfree(cdev->bootmode);
-}
-
-static int cosm_suspend(struct device *dev)
-{
- struct cosm_device *cdev = dev_to_cosm(dev);
-
- mutex_lock(&cdev->cosm_mutex);
- switch (cdev->state) {
- /**
- * Suspend/freeze hooks in userspace have already shutdown the card.
- * Card should be 'ready' in most cases. It is however possible that
- * some userspace application initiated a boot. In those cases, we
- * simply reset the card.
- */
- case MIC_ONLINE:
- case MIC_BOOTING:
- case MIC_SHUTTING_DOWN:
- mutex_unlock(&cdev->cosm_mutex);
- cosm_stop(cdev, false);
- break;
- default:
- mutex_unlock(&cdev->cosm_mutex);
- break;
- }
- return 0;
-}
-
-static const struct dev_pm_ops cosm_pm_ops = {
- .suspend = cosm_suspend,
- .freeze = cosm_suspend
-};
-
-static struct cosm_driver cosm_driver = {
- .driver = {
- .name = KBUILD_MODNAME,
- .owner = THIS_MODULE,
- .pm = &cosm_pm_ops,
- },
- .probe = cosm_driver_probe,
- .remove = cosm_driver_remove
-};
-
-static int __init cosm_init(void)
-{
- int ret;
-
- cosm_init_debugfs();
-
- g_cosm_class = class_create(THIS_MODULE, cosm_driver_name);
- if (IS_ERR(g_cosm_class)) {
- ret = PTR_ERR(g_cosm_class);
- pr_err("class_create failed ret %d\n", ret);
- goto cleanup_debugfs;
- }
-
- ida_init(&g_cosm_ida);
- ret = cosm_register_driver(&cosm_driver);
- if (ret) {
- pr_err("cosm_register_driver failed ret %d\n", ret);
- goto ida_destroy;
- }
- return 0;
-ida_destroy:
- ida_destroy(&g_cosm_ida);
- class_destroy(g_cosm_class);
-cleanup_debugfs:
- cosm_exit_debugfs();
- return ret;
-}
-
-static void __exit cosm_exit(void)
-{
- cosm_unregister_driver(&cosm_driver);
- ida_destroy(&g_cosm_ida);
- class_destroy(g_cosm_class);
- cosm_exit_debugfs();
-}
-
-module_init(cosm_init);
-module_exit(cosm_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC Coprocessor State Management (COSM) Driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/cosm/cosm_main.h b/drivers/misc/mic/cosm/cosm_main.h
deleted file mode 100644
index 5188ad2..0000000
--- a/drivers/misc/mic/cosm/cosm_main.h
+++ /dev/null
@@ -1,61 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC Coprocessor State Management (COSM) Driver
- */
-#ifndef _COSM_COSM_H_
-#define _COSM_COSM_H_
-
-#include <linux/scif.h>
-#include "../bus/cosm_bus.h"
-
-#define COSM_HEARTBEAT_SEND_SEC 30
-#define SCIF_COSM_LISTEN_PORT 201
-
-/**
- * enum COSM msg id's
- * @COSM_MSG_SHUTDOWN: host->card trigger shutdown
- * @COSM_MSG_SYNC_TIME: host->card send host time to card to sync time
- * @COSM_MSG_HEARTBEAT: card->host heartbeat
- * @COSM_MSG_SHUTDOWN_STATUS: card->host with shutdown status as payload
- */
-enum cosm_msg_id {
- COSM_MSG_SHUTDOWN,
- COSM_MSG_SYNC_TIME,
- COSM_MSG_HEARTBEAT,
- COSM_MSG_SHUTDOWN_STATUS,
-};
-
-struct cosm_msg {
- u64 id;
- union {
- u64 shutdown_status;
- struct {
- u64 tv_sec;
- u64 tv_nsec;
- } timespec;
- };
-};
-
-extern const char * const cosm_state_string[];
-extern const char * const cosm_shutdown_status_string[];
-
-void cosm_sysfs_init(struct cosm_device *cdev);
-int cosm_start(struct cosm_device *cdev);
-void cosm_stop(struct cosm_device *cdev, bool force);
-int cosm_reset(struct cosm_device *cdev);
-int cosm_shutdown(struct cosm_device *cdev);
-void cosm_set_state(struct cosm_device *cdev, u8 state);
-void cosm_set_shutdown_status(struct cosm_device *cdev, u8 status);
-void cosm_init_debugfs(void);
-void cosm_exit_debugfs(void);
-void cosm_create_debug_dir(struct cosm_device *cdev);
-void cosm_delete_debug_dir(struct cosm_device *cdev);
-int cosm_scif_init(void);
-void cosm_scif_exit(void);
-void cosm_scif_work(struct work_struct *work);
-
-#endif
diff --git a/drivers/misc/mic/cosm/cosm_scif_server.c b/drivers/misc/mic/cosm/cosm_scif_server.c
deleted file mode 100644
index 7baec9f..0000000
--- a/drivers/misc/mic/cosm/cosm_scif_server.c
+++ /dev/null
@@ -1,399 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC Coprocessor State Management (COSM) Driver
- */
-#include <linux/kthread.h>
-#include <linux/sched/signal.h>
-
-#include "cosm_main.h"
-
-/*
- * The COSM driver uses SCIF to communicate between the management node and the
- * MIC cards. SCIF is used to (a) Send a shutdown command to the card (b)
- * receive a shutdown status back from the card upon completion of shutdown and
- * (c) receive periodic heartbeat messages from the card used to deduce if the
- * card has crashed.
- *
- * A COSM server consisting of a SCIF listening endpoint waits for incoming
- * connections from the card. Upon acceptance of the connection, a separate
- * work-item is scheduled to handle SCIF message processing for that card. The
- * life-time of this work-item is therefore the time from which the connection
- * from a card is accepted to the time at which the connection is closed. A new
- * work-item starts each time the card boots and is alive till the card (a)
- * shuts down (b) is reset (c) crashes (d) cosm_client driver on the card is
- * unloaded.
- *
- * From the point of view of COSM interactions with SCIF during card
- * shutdown, reset and crash are as follows:
- *
- * Card shutdown
- * -------------
- * 1. COSM client on the card invokes orderly_poweroff() in response to SHUTDOWN
- * message from the host.
- * 2. Card driver shutdown callback invokes scif_unregister_device(..) resulting
- * in scif_remove(..) getting called on the card
- * 3. scif_remove -> scif_stop -> scif_handle_remove_node ->
- * scif_peer_unregister_device -> device_unregister for the host peer device
- * 4. During device_unregister remove(..) method of cosm_client is invoked which
- * closes the COSM SCIF endpoint on the card. This results in a SCIF_DISCNCT
- * message being sent to host SCIF. SCIF_DISCNCT message processing on the
- * host SCIF sets the host COSM SCIF endpoint state to DISCONNECTED and wakes
- * up the host COSM thread blocked in scif_poll(..) resulting in
- * scif_poll(..) returning EPOLLHUP.
- * 5. On the card, scif_peer_release_dev is next called which results in an
- * SCIF_EXIT message being sent to the host and after receiving the
- * SCIF_EXIT_ACK from the host the peer device teardown on the card is
- * complete.
- * 6. As part of the SCIF_EXIT message processing on the host, host sends a
- * SCIF_REMOVE_NODE to itself corresponding to the card being removed. This
- * starts a similar SCIF peer device teardown sequence on the host
- * corresponding to the card being shut down.
- *
- * Card reset
- * ----------
- * The case of interest here is when the card has not been previously shut down
- * since most of the steps below are skipped in that case:
-
- * 1. cosm_stop(..) invokes hw_ops->stop(..) method of the base PCIe driver
- * which unregisters the SCIF HW device resulting in scif_remove(..) being
- * called on the host.
- * 2. scif_remove(..) calls scif_disconnect_node(..) which results in a
- * SCIF_EXIT message being sent to the card.
- * 3. The card executes scif_stop() as part of SCIF_EXIT message
- * processing. This results in the COSM endpoint on the card being closed and
- * the SCIF host peer device on the card getting unregistered similar to
- * steps 3, 4 and 5 for the card shutdown case above. scif_poll(..) on the
- * host returns EPOLLHUP as a result.
- * 4. On the host, card peer device unregister and SCIF HW remove(..) also
- * subsequently complete.
- *
- * Card crash
- * ----------
- * If a reset is issued after the card has crashed, there is no SCIF_DISCNT
- * message from the card which would result in scif_poll(..) returning
- * EPOLLHUP. In this case when the host SCIF driver sends a SCIF_REMOVE_NODE
- * message to itself resulting in the card SCIF peer device being unregistered,
- * this results in a scif_peer_release_dev -> scif_cleanup_scifdev->
- * scif_invalidate_ep call sequence which sets the endpoint state to
- * DISCONNECTED and results in scif_poll(..) returning EPOLLHUP.
- */
-
-#define COSM_SCIF_BACKLOG 16
-#define COSM_HEARTBEAT_CHECK_DELTA_SEC 10
-#define COSM_HEARTBEAT_TIMEOUT_SEC \
- (COSM_HEARTBEAT_SEND_SEC + COSM_HEARTBEAT_CHECK_DELTA_SEC)
-#define COSM_HEARTBEAT_TIMEOUT_MSEC (COSM_HEARTBEAT_TIMEOUT_SEC * MSEC_PER_SEC)
-
-static struct task_struct *server_thread;
-static scif_epd_t listen_epd;
-
-/* Publish MIC card's shutdown status to user space MIC daemon */
-static void cosm_update_mic_status(struct cosm_device *cdev)
-{
- if (cdev->shutdown_status_int != MIC_NOP) {
- cosm_set_shutdown_status(cdev, cdev->shutdown_status_int);
- cdev->shutdown_status_int = MIC_NOP;
- }
-}
-
-/* Store MIC card's shutdown status internally when it is received */
-static void cosm_shutdown_status_int(struct cosm_device *cdev,
- enum mic_status shutdown_status)
-{
- switch (shutdown_status) {
- case MIC_HALTED:
- case MIC_POWER_OFF:
- case MIC_RESTART:
- case MIC_CRASHED:
- break;
- default:
- dev_err(&cdev->dev, "%s %d Unexpected shutdown_status %d\n",
- __func__, __LINE__, shutdown_status);
- return;
- };
- cdev->shutdown_status_int = shutdown_status;
- cdev->heartbeat_watchdog_enable = false;
-
- if (cdev->state != MIC_SHUTTING_DOWN)
- cosm_set_state(cdev, MIC_SHUTTING_DOWN);
-}
-
-/* Non-blocking recv. Read and process all available messages */
-static void cosm_scif_recv(struct cosm_device *cdev)
-{
- struct cosm_msg msg;
- int rc;
-
- while (1) {
- rc = scif_recv(cdev->epd, &msg, sizeof(msg), 0);
- if (!rc) {
- break;
- } else if (rc < 0) {
- dev_dbg(&cdev->dev, "%s: %d rc %d\n",
- __func__, __LINE__, rc);
- break;
- }
- dev_dbg(&cdev->dev, "%s: %d rc %d id 0x%llx\n",
- __func__, __LINE__, rc, msg.id);
-
- switch (msg.id) {
- case COSM_MSG_SHUTDOWN_STATUS:
- cosm_shutdown_status_int(cdev, msg.shutdown_status);
- break;
- case COSM_MSG_HEARTBEAT:
- /* Nothing to do, heartbeat only unblocks scif_poll */
- break;
- default:
- dev_err(&cdev->dev, "%s: %d unknown msg.id %lld\n",
- __func__, __LINE__, msg.id);
- break;
- }
- }
-}
-
-/* Publish crashed status for this MIC card */
-static void cosm_set_crashed(struct cosm_device *cdev)
-{
- dev_err(&cdev->dev, "node alive timeout\n");
- cosm_shutdown_status_int(cdev, MIC_CRASHED);
- cosm_update_mic_status(cdev);
-}
-
-/* Send host time to the MIC card to sync system time between host and MIC */
-static void cosm_send_time(struct cosm_device *cdev)
-{
- struct cosm_msg msg = { .id = COSM_MSG_SYNC_TIME };
- struct timespec64 ts;
- int rc;
-
- ktime_get_real_ts64(&ts);
- msg.timespec.tv_sec = ts.tv_sec;
- msg.timespec.tv_nsec = ts.tv_nsec;
-
- rc = scif_send(cdev->epd, &msg, sizeof(msg), SCIF_SEND_BLOCK);
- if (rc < 0)
- dev_err(&cdev->dev, "%s %d scif_send failed rc %d\n",
- __func__, __LINE__, rc);
-}
-
-/*
- * Close this cosm_device's endpoint after its peer endpoint on the card has
- * been closed. In all cases except MIC card crash EPOLLHUP on the host is
- * triggered by the client's endpoint being closed.
- */
-static void cosm_scif_close(struct cosm_device *cdev)
-{
- /*
- * Because SHUTDOWN_STATUS message is sent by the MIC cards in the
- * reboot notifier when shutdown is still not complete, we notify mpssd
- * to reset the card when SCIF endpoint is closed.
- */
- cosm_update_mic_status(cdev);
- scif_close(cdev->epd);
- cdev->epd = NULL;
- dev_dbg(&cdev->dev, "%s %d\n", __func__, __LINE__);
-}
-
-/*
- * Set card state to ONLINE when a new SCIF connection from a MIC card is
- * received. Normally the state is BOOTING when the connection comes in, but can
- * be ONLINE if cosm_client driver on the card was unloaded and then reloaded.
- */
-static int cosm_set_online(struct cosm_device *cdev)
-{
- int rc = 0;
-
- if (MIC_BOOTING == cdev->state || MIC_ONLINE == cdev->state) {
- cdev->heartbeat_watchdog_enable = cdev->sysfs_heartbeat_enable;
- cdev->epd = cdev->newepd;
- if (cdev->state == MIC_BOOTING)
- cosm_set_state(cdev, MIC_ONLINE);
- cosm_send_time(cdev);
- dev_dbg(&cdev->dev, "%s %d\n", __func__, __LINE__);
- } else {
- dev_warn(&cdev->dev, "%s %d not going online in state: %s\n",
- __func__, __LINE__, cosm_state_string[cdev->state]);
- rc = -EINVAL;
- }
- /* Drop reference acquired by bus_find_device in the server thread */
- put_device(&cdev->dev);
- return rc;
-}
-
-/*
- * Work function for handling work for a SCIF connection from a particular MIC
- * card. It first sets the card state to ONLINE and then calls scif_poll to
- * block on activity such as incoming messages on the SCIF endpoint. When the
- * endpoint is closed, the work function exits, completing its life cycle, from
- * MIC card boot to card shutdown/reset/crash.
- */
-void cosm_scif_work(struct work_struct *work)
-{
- struct cosm_device *cdev = container_of(work, struct cosm_device,
- scif_work);
- struct scif_pollepd pollepd;
- int rc;
-
- mutex_lock(&cdev->cosm_mutex);
- if (cosm_set_online(cdev))
- goto exit;
-
- while (1) {
- pollepd.epd = cdev->epd;
- pollepd.events = EPOLLIN;
-
- /* Drop the mutex before blocking in scif_poll(..) */
- mutex_unlock(&cdev->cosm_mutex);
- /* poll(..) with timeout on our endpoint */
- rc = scif_poll(&pollepd, 1, COSM_HEARTBEAT_TIMEOUT_MSEC);
- mutex_lock(&cdev->cosm_mutex);
- if (rc < 0) {
- dev_err(&cdev->dev, "%s %d scif_poll rc %d\n",
- __func__, __LINE__, rc);
- continue;
- }
-
- /* There is a message from the card */
- if (pollepd.revents & EPOLLIN)
- cosm_scif_recv(cdev);
-
- /* The peer endpoint is closed or this endpoint disconnected */
- if (pollepd.revents & EPOLLHUP) {
- cosm_scif_close(cdev);
- break;
- }
-
- /* Did we timeout from poll? */
- if (!rc && cdev->heartbeat_watchdog_enable)
- cosm_set_crashed(cdev);
- }
-exit:
- dev_dbg(&cdev->dev, "%s %d exiting\n", __func__, __LINE__);
- mutex_unlock(&cdev->cosm_mutex);
-}
-
-/*
- * COSM SCIF server thread function. Accepts incoming SCIF connections from MIC
- * cards, finds the correct cosm_device to associate that connection with and
- * schedules individual work items for each MIC card.
- */
-static int cosm_scif_server(void *unused)
-{
- struct cosm_device *cdev;
- scif_epd_t newepd;
- struct scif_port_id port_id;
- int rc;
-
- allow_signal(SIGKILL);
-
- while (!kthread_should_stop()) {
- rc = scif_accept(listen_epd, &port_id, &newepd,
- SCIF_ACCEPT_SYNC);
- if (rc < 0) {
- if (-ERESTARTSYS != rc)
- pr_err("%s %d rc %d\n", __func__, __LINE__, rc);
- continue;
- }
-
- /*
- * Associate the incoming connection with a particular
- * cosm_device, COSM device ID == SCIF node ID - 1
- */
- cdev = cosm_find_cdev_by_id(port_id.node - 1);
- if (!cdev)
- continue;
- cdev->newepd = newepd;
- schedule_work(&cdev->scif_work);
- }
-
- pr_debug("%s %d Server thread stopped\n", __func__, __LINE__);
- return 0;
-}
-
-static int cosm_scif_listen(void)
-{
- int rc;
-
- listen_epd = scif_open();
- if (!listen_epd) {
- pr_err("%s %d scif_open failed\n", __func__, __LINE__);
- return -ENOMEM;
- }
-
- rc = scif_bind(listen_epd, SCIF_COSM_LISTEN_PORT);
- if (rc < 0) {
- pr_err("%s %d scif_bind failed rc %d\n",
- __func__, __LINE__, rc);
- goto err;
- }
-
- rc = scif_listen(listen_epd, COSM_SCIF_BACKLOG);
- if (rc < 0) {
- pr_err("%s %d scif_listen rc %d\n", __func__, __LINE__, rc);
- goto err;
- }
- pr_debug("%s %d listen_epd set up\n", __func__, __LINE__);
- return 0;
-err:
- scif_close(listen_epd);
- listen_epd = NULL;
- return rc;
-}
-
-static void cosm_scif_listen_exit(void)
-{
- pr_debug("%s %d closing listen_epd\n", __func__, __LINE__);
- if (listen_epd) {
- scif_close(listen_epd);
- listen_epd = NULL;
- }
-}
-
-/*
- * Create a listening SCIF endpoint and a server kthread which accepts incoming
- * SCIF connections from MIC cards
- */
-int cosm_scif_init(void)
-{
- int rc = cosm_scif_listen();
-
- if (rc) {
- pr_err("%s %d cosm_scif_listen rc %d\n",
- __func__, __LINE__, rc);
- goto err;
- }
-
- server_thread = kthread_run(cosm_scif_server, NULL, "cosm_server");
- if (IS_ERR(server_thread)) {
- rc = PTR_ERR(server_thread);
- pr_err("%s %d kthread_run rc %d\n", __func__, __LINE__, rc);
- goto listen_exit;
- }
- return 0;
-listen_exit:
- cosm_scif_listen_exit();
-err:
- return rc;
-}
-
-/* Stop the running server thread and close the listening SCIF endpoint */
-void cosm_scif_exit(void)
-{
- int rc;
-
- if (!IS_ERR_OR_NULL(server_thread)) {
- rc = send_sig(SIGKILL, server_thread, 0);
- if (rc) {
- pr_err("%s %d send_sig rc %d\n",
- __func__, __LINE__, rc);
- return;
- }
- kthread_stop(server_thread);
- }
-
- cosm_scif_listen_exit();
-}
diff --git a/drivers/misc/mic/cosm/cosm_sysfs.c b/drivers/misc/mic/cosm/cosm_sysfs.c
deleted file mode 100644
index e6dac96..0000000
--- a/drivers/misc/mic/cosm/cosm_sysfs.c
+++ /dev/null
@@ -1,449 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC Coprocessor State Management (COSM) Driver
- */
-#include <linux/slab.h>
-#include "cosm_main.h"
-
-/*
- * A state-to-string lookup table, for exposing a human readable state
- * via sysfs. Always keep in sync with enum cosm_states
- */
-const char * const cosm_state_string[] = {
- [MIC_READY] = "ready",
- [MIC_BOOTING] = "booting",
- [MIC_ONLINE] = "online",
- [MIC_SHUTTING_DOWN] = "shutting_down",
- [MIC_RESETTING] = "resetting",
- [MIC_RESET_FAILED] = "reset_failed",
-};
-
-/*
- * A shutdown-status-to-string lookup table, for exposing a human
- * readable state via sysfs. Always keep in sync with enum cosm_shutdown_status
- */
-const char * const cosm_shutdown_status_string[] = {
- [MIC_NOP] = "nop",
- [MIC_CRASHED] = "crashed",
- [MIC_HALTED] = "halted",
- [MIC_POWER_OFF] = "poweroff",
- [MIC_RESTART] = "restart",
-};
-
-void cosm_set_shutdown_status(struct cosm_device *cdev, u8 shutdown_status)
-{
- dev_dbg(&cdev->dev, "Shutdown Status %s -> %s\n",
- cosm_shutdown_status_string[cdev->shutdown_status],
- cosm_shutdown_status_string[shutdown_status]);
- cdev->shutdown_status = shutdown_status;
-}
-
-void cosm_set_state(struct cosm_device *cdev, u8 state)
-{
- dev_dbg(&cdev->dev, "State %s -> %s\n",
- cosm_state_string[cdev->state],
- cosm_state_string[state]);
- cdev->state = state;
- sysfs_notify_dirent(cdev->state_sysfs);
-}
-
-static ssize_t
-family_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- return cdev->hw_ops->family(cdev, buf);
-}
-static DEVICE_ATTR_RO(family);
-
-static ssize_t
-stepping_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- return cdev->hw_ops->stepping(cdev, buf);
-}
-static DEVICE_ATTR_RO(stepping);
-
-static ssize_t
-state_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev || cdev->state >= MIC_LAST)
- return -EINVAL;
-
- return scnprintf(buf, PAGE_SIZE, "%s\n",
- cosm_state_string[cdev->state]);
-}
-
-static ssize_t
-state_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
- int rc;
-
- if (!cdev)
- return -EINVAL;
-
- if (sysfs_streq(buf, "boot")) {
- rc = cosm_start(cdev);
- goto done;
- }
- if (sysfs_streq(buf, "reset")) {
- rc = cosm_reset(cdev);
- goto done;
- }
-
- if (sysfs_streq(buf, "shutdown")) {
- rc = cosm_shutdown(cdev);
- goto done;
- }
- rc = -EINVAL;
-done:
- if (rc)
- count = rc;
- return count;
-}
-static DEVICE_ATTR_RW(state);
-
-static ssize_t shutdown_status_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev || cdev->shutdown_status >= MIC_STATUS_LAST)
- return -EINVAL;
-
- return scnprintf(buf, PAGE_SIZE, "%s\n",
- cosm_shutdown_status_string[cdev->shutdown_status]);
-}
-static DEVICE_ATTR_RO(shutdown_status);
-
-static ssize_t
-heartbeat_enable_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- return scnprintf(buf, PAGE_SIZE, "%d\n", cdev->sysfs_heartbeat_enable);
-}
-
-static ssize_t
-heartbeat_enable_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
- int enable;
- int ret;
-
- if (!cdev)
- return -EINVAL;
-
- mutex_lock(&cdev->cosm_mutex);
- ret = kstrtoint(buf, 10, &enable);
- if (ret)
- goto unlock;
-
- cdev->sysfs_heartbeat_enable = enable;
- /* if state is not online, cdev->heartbeat_watchdog_enable is 0 */
- if (cdev->state == MIC_ONLINE)
- cdev->heartbeat_watchdog_enable = enable;
- ret = count;
-unlock:
- mutex_unlock(&cdev->cosm_mutex);
- return ret;
-}
-static DEVICE_ATTR_RW(heartbeat_enable);
-
-static ssize_t
-cmdline_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
- char *cmdline;
-
- if (!cdev)
- return -EINVAL;
-
- cmdline = cdev->cmdline;
-
- if (cmdline)
- return scnprintf(buf, PAGE_SIZE, "%s\n", cmdline);
- return 0;
-}
-
-static ssize_t
-cmdline_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- mutex_lock(&cdev->cosm_mutex);
- kfree(cdev->cmdline);
-
- cdev->cmdline = kmalloc(count + 1, GFP_KERNEL);
- if (!cdev->cmdline) {
- count = -ENOMEM;
- goto unlock;
- }
-
- strncpy(cdev->cmdline, buf, count);
-
- if (cdev->cmdline[count - 1] == '\n')
- cdev->cmdline[count - 1] = '\0';
- else
- cdev->cmdline[count] = '\0';
-unlock:
- mutex_unlock(&cdev->cosm_mutex);
- return count;
-}
-static DEVICE_ATTR_RW(cmdline);
-
-static ssize_t
-firmware_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
- char *firmware;
-
- if (!cdev)
- return -EINVAL;
-
- firmware = cdev->firmware;
-
- if (firmware)
- return scnprintf(buf, PAGE_SIZE, "%s\n", firmware);
- return 0;
-}
-
-static ssize_t
-firmware_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- mutex_lock(&cdev->cosm_mutex);
- kfree(cdev->firmware);
-
- cdev->firmware = kmalloc(count + 1, GFP_KERNEL);
- if (!cdev->firmware) {
- count = -ENOMEM;
- goto unlock;
- }
- strncpy(cdev->firmware, buf, count);
-
- if (cdev->firmware[count - 1] == '\n')
- cdev->firmware[count - 1] = '\0';
- else
- cdev->firmware[count] = '\0';
-unlock:
- mutex_unlock(&cdev->cosm_mutex);
- return count;
-}
-static DEVICE_ATTR_RW(firmware);
-
-static ssize_t
-ramdisk_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
- char *ramdisk;
-
- if (!cdev)
- return -EINVAL;
-
- ramdisk = cdev->ramdisk;
-
- if (ramdisk)
- return scnprintf(buf, PAGE_SIZE, "%s\n", ramdisk);
- return 0;
-}
-
-static ssize_t
-ramdisk_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- mutex_lock(&cdev->cosm_mutex);
- kfree(cdev->ramdisk);
-
- cdev->ramdisk = kmalloc(count + 1, GFP_KERNEL);
- if (!cdev->ramdisk) {
- count = -ENOMEM;
- goto unlock;
- }
-
- strncpy(cdev->ramdisk, buf, count);
-
- if (cdev->ramdisk[count - 1] == '\n')
- cdev->ramdisk[count - 1] = '\0';
- else
- cdev->ramdisk[count] = '\0';
-unlock:
- mutex_unlock(&cdev->cosm_mutex);
- return count;
-}
-static DEVICE_ATTR_RW(ramdisk);
-
-static ssize_t
-bootmode_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
- char *bootmode;
-
- if (!cdev)
- return -EINVAL;
-
- bootmode = cdev->bootmode;
-
- if (bootmode)
- return scnprintf(buf, PAGE_SIZE, "%s\n", bootmode);
- return 0;
-}
-
-static ssize_t
-bootmode_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- if (!sysfs_streq(buf, "linux") && !sysfs_streq(buf, "flash"))
- return -EINVAL;
-
- mutex_lock(&cdev->cosm_mutex);
- kfree(cdev->bootmode);
-
- cdev->bootmode = kmalloc(count + 1, GFP_KERNEL);
- if (!cdev->bootmode) {
- count = -ENOMEM;
- goto unlock;
- }
-
- strncpy(cdev->bootmode, buf, count);
-
- if (cdev->bootmode[count - 1] == '\n')
- cdev->bootmode[count - 1] = '\0';
- else
- cdev->bootmode[count] = '\0';
-unlock:
- mutex_unlock(&cdev->cosm_mutex);
- return count;
-}
-static DEVICE_ATTR_RW(bootmode);
-
-static ssize_t
-log_buf_addr_show(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- return scnprintf(buf, PAGE_SIZE, "%p\n", cdev->log_buf_addr);
-}
-
-static ssize_t
-log_buf_addr_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
- int ret;
- unsigned long addr;
-
- if (!cdev)
- return -EINVAL;
-
- ret = kstrtoul(buf, 16, &addr);
- if (ret)
- goto exit;
-
- cdev->log_buf_addr = (void *)addr;
- ret = count;
-exit:
- return ret;
-}
-static DEVICE_ATTR_RW(log_buf_addr);
-
-static ssize_t
-log_buf_len_show(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- return scnprintf(buf, PAGE_SIZE, "%p\n", cdev->log_buf_len);
-}
-
-static ssize_t
-log_buf_len_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
- int ret;
- unsigned long addr;
-
- if (!cdev)
- return -EINVAL;
-
- ret = kstrtoul(buf, 16, &addr);
- if (ret)
- goto exit;
-
- cdev->log_buf_len = (int *)addr;
- ret = count;
-exit:
- return ret;
-}
-static DEVICE_ATTR_RW(log_buf_len);
-
-static struct attribute *cosm_default_attrs[] = {
- &dev_attr_family.attr,
- &dev_attr_stepping.attr,
- &dev_attr_state.attr,
- &dev_attr_shutdown_status.attr,
- &dev_attr_heartbeat_enable.attr,
- &dev_attr_cmdline.attr,
- &dev_attr_firmware.attr,
- &dev_attr_ramdisk.attr,
- &dev_attr_bootmode.attr,
- &dev_attr_log_buf_addr.attr,
- &dev_attr_log_buf_len.attr,
-
- NULL
-};
-
-ATTRIBUTE_GROUPS(cosm_default);
-
-void cosm_sysfs_init(struct cosm_device *cdev)
-{
- cdev->attr_group = cosm_default_groups;
-}
diff --git a/drivers/misc/mic/cosm_client/Makefile b/drivers/misc/mic/cosm_client/Makefile
deleted file mode 100644
index 5b62270..0000000
--- a/drivers/misc/mic/cosm_client/Makefile
+++ /dev/null
@@ -1,8 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Makefile - Intel MIC COSM Client Driver
-# Copyright(c) 2015, Intel Corporation.
-#
-obj-$(CONFIG_MIC_COSM) += cosm_client.o
-
-cosm_client-objs += cosm_scif_client.o
diff --git a/drivers/misc/mic/cosm_client/cosm_scif_client.c b/drivers/misc/mic/cosm_client/cosm_scif_client.c
deleted file mode 100644
index a03213d..0000000
--- a/drivers/misc/mic/cosm_client/cosm_scif_client.c
+++ /dev/null
@@ -1,269 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC COSM Client Driver
- */
-#include <linux/module.h>
-#include <linux/delay.h>
-#include <linux/reboot.h>
-#include <linux/kthread.h>
-#include <linux/sched/signal.h>
-
-#include "../cosm/cosm_main.h"
-
-#define COSM_SCIF_MAX_RETRIES 10
-#define COSM_HEARTBEAT_SEND_MSEC (COSM_HEARTBEAT_SEND_SEC * MSEC_PER_SEC)
-
-static struct task_struct *client_thread;
-static scif_epd_t client_epd;
-static struct scif_peer_dev *client_spdev;
-
-/*
- * Reboot notifier: receives shutdown status from the OS and communicates it
- * back to the COSM process on the host
- */
-static int cosm_reboot_event(struct notifier_block *this, unsigned long event,
- void *ptr)
-{
- struct cosm_msg msg = { .id = COSM_MSG_SHUTDOWN_STATUS };
- int rc;
-
- event = (event == SYS_RESTART) ? SYSTEM_RESTART : event;
- dev_info(&client_spdev->dev, "%s %d received event %ld\n",
- __func__, __LINE__, event);
-
- msg.shutdown_status = event;
- rc = scif_send(client_epd, &msg, sizeof(msg), SCIF_SEND_BLOCK);
- if (rc < 0)
- dev_err(&client_spdev->dev, "%s %d scif_send rc %d\n",
- __func__, __LINE__, rc);
-
- return NOTIFY_DONE;
-}
-
-static struct notifier_block cosm_reboot = {
- .notifier_call = cosm_reboot_event,
-};
-
-/* Set system time from timespec value received from the host */
-static void cosm_set_time(struct cosm_msg *msg)
-{
- struct timespec64 ts = {
- .tv_sec = msg->timespec.tv_sec,
- .tv_nsec = msg->timespec.tv_nsec,
- };
- int rc = do_settimeofday64(&ts);
-
- if (rc)
- dev_err(&client_spdev->dev, "%s: %d settimeofday rc %d\n",
- __func__, __LINE__, rc);
-}
-
-/* COSM client receive message processing */
-static void cosm_client_recv(void)
-{
- struct cosm_msg msg;
- int rc;
-
- while (1) {
- rc = scif_recv(client_epd, &msg, sizeof(msg), 0);
- if (!rc) {
- return;
- } else if (rc < 0) {
- dev_err(&client_spdev->dev, "%s: %d rc %d\n",
- __func__, __LINE__, rc);
- return;
- }
-
- dev_dbg(&client_spdev->dev, "%s: %d rc %d id 0x%llx\n",
- __func__, __LINE__, rc, msg.id);
-
- switch (msg.id) {
- case COSM_MSG_SYNC_TIME:
- cosm_set_time(&msg);
- break;
- case COSM_MSG_SHUTDOWN:
- orderly_poweroff(true);
- break;
- default:
- dev_err(&client_spdev->dev, "%s: %d unknown id %lld\n",
- __func__, __LINE__, msg.id);
- break;
- }
- }
-}
-
-/* Initiate connection to the COSM server on the host */
-static int cosm_scif_connect(void)
-{
- struct scif_port_id port_id;
- int i, rc;
-
- client_epd = scif_open();
- if (!client_epd) {
- dev_err(&client_spdev->dev, "%s %d scif_open failed\n",
- __func__, __LINE__);
- return -ENOMEM;
- }
-
- port_id.node = 0;
- port_id.port = SCIF_COSM_LISTEN_PORT;
-
- for (i = 0; i < COSM_SCIF_MAX_RETRIES; i++) {
- rc = scif_connect(client_epd, &port_id);
- if (rc < 0)
- msleep(1000);
- else
- break;
- }
-
- if (rc < 0) {
- dev_err(&client_spdev->dev, "%s %d scif_connect rc %d\n",
- __func__, __LINE__, rc);
- scif_close(client_epd);
- client_epd = NULL;
- }
- return rc < 0 ? rc : 0;
-}
-
-/* Close host SCIF connection */
-static void cosm_scif_connect_exit(void)
-{
- if (client_epd) {
- scif_close(client_epd);
- client_epd = NULL;
- }
-}
-
-/*
- * COSM SCIF client thread function: waits for messages from the host and sends
- * a heartbeat to the host
- */
-static int cosm_scif_client(void *unused)
-{
- struct cosm_msg msg = { .id = COSM_MSG_HEARTBEAT };
- struct scif_pollepd pollepd;
- int rc;
-
- allow_signal(SIGKILL);
-
- while (!kthread_should_stop()) {
- pollepd.epd = client_epd;
- pollepd.events = EPOLLIN;
-
- rc = scif_poll(&pollepd, 1, COSM_HEARTBEAT_SEND_MSEC);
- if (rc < 0) {
- if (-EINTR != rc)
- dev_err(&client_spdev->dev,
- "%s %d scif_poll rc %d\n",
- __func__, __LINE__, rc);
- continue;
- }
-
- if (pollepd.revents & EPOLLIN)
- cosm_client_recv();
-
- msg.id = COSM_MSG_HEARTBEAT;
- rc = scif_send(client_epd, &msg, sizeof(msg), SCIF_SEND_BLOCK);
- if (rc < 0)
- dev_err(&client_spdev->dev, "%s %d scif_send rc %d\n",
- __func__, __LINE__, rc);
- }
-
- dev_dbg(&client_spdev->dev, "%s %d Client thread stopped\n",
- __func__, __LINE__);
- return 0;
-}
-
-static void cosm_scif_probe(struct scif_peer_dev *spdev)
-{
- int rc;
-
- dev_dbg(&spdev->dev, "%s %d: dnode %d\n",
- __func__, __LINE__, spdev->dnode);
-
- /* We are only interested in the host with spdev->dnode == 0 */
- if (spdev->dnode)
- return;
-
- client_spdev = spdev;
- rc = cosm_scif_connect();
- if (rc)
- goto exit;
-
- rc = register_reboot_notifier(&cosm_reboot);
- if (rc) {
- dev_err(&spdev->dev,
- "reboot notifier registration failed rc %d\n", rc);
- goto connect_exit;
- }
-
- client_thread = kthread_run(cosm_scif_client, NULL, "cosm_client");
- if (IS_ERR(client_thread)) {
- rc = PTR_ERR(client_thread);
- dev_err(&spdev->dev, "%s %d kthread_run rc %d\n",
- __func__, __LINE__, rc);
- goto unreg_reboot;
- }
- return;
-unreg_reboot:
- unregister_reboot_notifier(&cosm_reboot);
-connect_exit:
- cosm_scif_connect_exit();
-exit:
- client_spdev = NULL;
-}
-
-static void cosm_scif_remove(struct scif_peer_dev *spdev)
-{
- int rc;
-
- dev_dbg(&spdev->dev, "%s %d: dnode %d\n",
- __func__, __LINE__, spdev->dnode);
-
- if (spdev->dnode)
- return;
-
- if (!IS_ERR_OR_NULL(client_thread)) {
- rc = send_sig(SIGKILL, client_thread, 0);
- if (rc) {
- pr_err("%s %d send_sig rc %d\n",
- __func__, __LINE__, rc);
- return;
- }
- kthread_stop(client_thread);
- }
- unregister_reboot_notifier(&cosm_reboot);
- cosm_scif_connect_exit();
- client_spdev = NULL;
-}
-
-static struct scif_client scif_client_cosm = {
- .name = KBUILD_MODNAME,
- .probe = cosm_scif_probe,
- .remove = cosm_scif_remove,
-};
-
-static int __init cosm_client_init(void)
-{
- int rc = scif_client_register(&scif_client_cosm);
-
- if (rc)
- pr_err("scif_client_register failed rc %d\n", rc);
- return rc;
-}
-
-static void __exit cosm_client_exit(void)
-{
- scif_client_unregister(&scif_client_cosm);
-}
-
-module_init(cosm_client_init);
-module_exit(cosm_client_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC card OS state management client driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/host/Makefile b/drivers/misc/mic/host/Makefile
deleted file mode 100644
index 25f1533..0000000
--- a/drivers/misc/mic/host/Makefile
+++ /dev/null
@@ -1,12 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile - Intel MIC Linux driver.
-# Copyright(c) 2013, Intel Corporation.
-#
-obj-$(CONFIG_INTEL_MIC_HOST) += mic_host.o
-mic_host-objs := mic_main.o
-mic_host-objs += mic_x100.o
-mic_host-objs += mic_smpt.o
-mic_host-objs += mic_intr.o
-mic_host-objs += mic_boot.o
-mic_host-objs += mic_debugfs.o
diff --git a/drivers/misc/mic/host/mic_boot.c b/drivers/misc/mic/host/mic_boot.c
deleted file mode 100644
index 8cb85b8..0000000
--- a/drivers/misc/mic/host/mic_boot.c
+++ /dev/null
@@ -1,588 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/delay.h>
-#include <linux/firmware.h>
-#include <linux/pci.h>
-#include <linux/kmod.h>
-#include <linux/dma-map-ops.h>
-#include <linux/mic_common.h>
-#include <linux/mic_bus.h>
-#include "../bus/scif_bus.h"
-#include "../bus/vop_bus.h"
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_smpt.h"
-
-static inline struct mic_device *vpdev_to_mdev(struct device *dev)
-{
- return dev_get_drvdata(dev->parent);
-}
-
-static dma_addr_t
-_mic_dma_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir, unsigned long attrs)
-{
- void *va = phys_to_virt(page_to_phys(page)) + offset;
- struct mic_device *mdev = vpdev_to_mdev(dev);
-
- return mic_map_single(mdev, va, size);
-}
-
-static void _mic_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- struct mic_device *mdev = vpdev_to_mdev(dev);
-
- mic_unmap_single(mdev, dma_addr, size);
-}
-
-static const struct dma_map_ops _mic_dma_ops = {
- .map_page = _mic_dma_map_page,
- .unmap_page = _mic_dma_unmap_page,
-};
-
-static struct mic_irq *
-__mic_request_irq(struct vop_device *vpdev,
- irqreturn_t (*func)(int irq, void *data),
- const char *name, void *data, int intr_src)
-{
- struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
- return mic_request_threaded_irq(mdev, func, NULL, name, data,
- intr_src, MIC_INTR_DB);
-}
-
-static void __mic_free_irq(struct vop_device *vpdev,
- struct mic_irq *cookie, void *data)
-{
- struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
- mic_free_irq(mdev, cookie, data);
-}
-
-static void __mic_ack_interrupt(struct vop_device *vpdev, int num)
-{
- struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
- mdev->ops->intr_workarounds(mdev);
-}
-
-static int __mic_next_db(struct vop_device *vpdev)
-{
- struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
- return mic_next_db(mdev);
-}
-
-static void *__mic_get_dp(struct vop_device *vpdev)
-{
- struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
- return mdev->dp;
-}
-
-static void __iomem *__mic_get_remote_dp(struct vop_device *vpdev)
-{
- return NULL;
-}
-
-static void __mic_send_intr(struct vop_device *vpdev, int db)
-{
- struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
- mdev->ops->send_intr(mdev, db);
-}
-
-static void __iomem *__mic_ioremap(struct vop_device *vpdev,
- dma_addr_t pa, size_t len)
-{
- struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
- return mdev->aper.va + pa;
-}
-
-static void __mic_iounmap(struct vop_device *vpdev, void __iomem *va)
-{
- /* nothing to do */
-}
-
-static struct vop_hw_ops vop_hw_ops = {
- .request_irq = __mic_request_irq,
- .free_irq = __mic_free_irq,
- .ack_interrupt = __mic_ack_interrupt,
- .next_db = __mic_next_db,
- .get_dp = __mic_get_dp,
- .get_remote_dp = __mic_get_remote_dp,
- .send_intr = __mic_send_intr,
- .remap = __mic_ioremap,
- .unmap = __mic_iounmap,
-};
-
-static inline struct mic_device *scdev_to_mdev(struct scif_hw_dev *scdev)
-{
- return dev_get_drvdata(scdev->dev.parent);
-}
-
-static void *__mic_dma_alloc(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp,
- unsigned long attrs)
-{
- struct scif_hw_dev *scdev = dev_get_drvdata(dev);
- struct mic_device *mdev = scdev_to_mdev(scdev);
- dma_addr_t tmp;
- void *va = kzalloc(size, gfp);
-
- if (va) {
- tmp = mic_map_single(mdev, va, size);
- if (dma_mapping_error(dev, tmp)) {
- kfree(va);
- va = NULL;
- } else {
- *dma_handle = tmp;
- }
- }
- return va;
-}
-
-static void __mic_dma_free(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_handle, unsigned long attrs)
-{
- struct scif_hw_dev *scdev = dev_get_drvdata(dev);
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- mic_unmap_single(mdev, dma_handle, size);
- kfree(vaddr);
-}
-
-static dma_addr_t
-__mic_dma_map_page(struct device *dev, struct page *page, unsigned long offset,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- void *va = phys_to_virt(page_to_phys(page)) + offset;
- struct scif_hw_dev *scdev = dev_get_drvdata(dev);
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- return mic_map_single(mdev, va, size);
-}
-
-static void
-__mic_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- struct scif_hw_dev *scdev = dev_get_drvdata(dev);
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- mic_unmap_single(mdev, dma_addr, size);
-}
-
-static int __mic_dma_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction dir,
- unsigned long attrs)
-{
- struct scif_hw_dev *scdev = dev_get_drvdata(dev);
- struct mic_device *mdev = scdev_to_mdev(scdev);
- struct scatterlist *s;
- int i, j, ret;
- dma_addr_t da;
-
- ret = dma_map_sg(&mdev->pdev->dev, sg, nents, dir);
- if (ret <= 0)
- return 0;
-
- for_each_sg(sg, s, nents, i) {
- da = mic_map(mdev, sg_dma_address(s) + s->offset, s->length);
- if (!da)
- goto err;
- sg_dma_address(s) = da;
- }
- return nents;
-err:
- for_each_sg(sg, s, i, j) {
- mic_unmap(mdev, sg_dma_address(s), s->length);
- sg_dma_address(s) = mic_to_dma_addr(mdev, sg_dma_address(s));
- }
- dma_unmap_sg(&mdev->pdev->dev, sg, nents, dir);
- return 0;
-}
-
-static void __mic_dma_unmap_sg(struct device *dev,
- struct scatterlist *sg, int nents,
- enum dma_data_direction dir,
- unsigned long attrs)
-{
- struct scif_hw_dev *scdev = dev_get_drvdata(dev);
- struct mic_device *mdev = scdev_to_mdev(scdev);
- struct scatterlist *s;
- dma_addr_t da;
- int i;
-
- for_each_sg(sg, s, nents, i) {
- da = mic_to_dma_addr(mdev, sg_dma_address(s));
- mic_unmap(mdev, sg_dma_address(s), s->length);
- sg_dma_address(s) = da;
- }
- dma_unmap_sg(&mdev->pdev->dev, sg, nents, dir);
-}
-
-static const struct dma_map_ops __mic_dma_ops = {
- .alloc = __mic_dma_alloc,
- .free = __mic_dma_free,
- .map_page = __mic_dma_map_page,
- .unmap_page = __mic_dma_unmap_page,
- .map_sg = __mic_dma_map_sg,
- .unmap_sg = __mic_dma_unmap_sg,
-};
-
-static struct mic_irq *
-___mic_request_irq(struct scif_hw_dev *scdev,
- irqreturn_t (*func)(int irq, void *data),
- const char *name,
- void *data, int db)
-{
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- return mic_request_threaded_irq(mdev, func, NULL, name, data,
- db, MIC_INTR_DB);
-}
-
-static void
-___mic_free_irq(struct scif_hw_dev *scdev,
- struct mic_irq *cookie, void *data)
-{
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- mic_free_irq(mdev, cookie, data);
-}
-
-static void ___mic_ack_interrupt(struct scif_hw_dev *scdev, int num)
-{
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- mdev->ops->intr_workarounds(mdev);
-}
-
-static int ___mic_next_db(struct scif_hw_dev *scdev)
-{
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- return mic_next_db(mdev);
-}
-
-static void ___mic_send_intr(struct scif_hw_dev *scdev, int db)
-{
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- mdev->ops->send_intr(mdev, db);
-}
-
-static void __iomem *___mic_ioremap(struct scif_hw_dev *scdev,
- phys_addr_t pa, size_t len)
-{
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- return mdev->aper.va + pa;
-}
-
-static void ___mic_iounmap(struct scif_hw_dev *scdev, void __iomem *va)
-{
- /* nothing to do */
-}
-
-static struct scif_hw_ops scif_hw_ops = {
- .request_irq = ___mic_request_irq,
- .free_irq = ___mic_free_irq,
- .ack_interrupt = ___mic_ack_interrupt,
- .next_db = ___mic_next_db,
- .send_intr = ___mic_send_intr,
- .remap = ___mic_ioremap,
- .unmap = ___mic_iounmap,
-};
-
-static inline struct mic_device *mbdev_to_mdev(struct mbus_device *mbdev)
-{
- return dev_get_drvdata(mbdev->dev.parent);
-}
-
-static dma_addr_t
-mic_dma_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- void *va = phys_to_virt(page_to_phys(page)) + offset;
- struct mic_device *mdev = dev_get_drvdata(dev->parent);
-
- return mic_map_single(mdev, va, size);
-}
-
-static void
-mic_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- struct mic_device *mdev = dev_get_drvdata(dev->parent);
- mic_unmap_single(mdev, dma_addr, size);
-}
-
-static const struct dma_map_ops mic_dma_ops = {
- .map_page = mic_dma_map_page,
- .unmap_page = mic_dma_unmap_page,
-};
-
-static struct mic_irq *
-_mic_request_threaded_irq(struct mbus_device *mbdev,
- irq_handler_t handler, irq_handler_t thread_fn,
- const char *name, void *data, int intr_src)
-{
- return mic_request_threaded_irq(mbdev_to_mdev(mbdev), handler,
- thread_fn, name, data,
- intr_src, MIC_INTR_DMA);
-}
-
-static void _mic_free_irq(struct mbus_device *mbdev,
- struct mic_irq *cookie, void *data)
-{
- mic_free_irq(mbdev_to_mdev(mbdev), cookie, data);
-}
-
-static void _mic_ack_interrupt(struct mbus_device *mbdev, int num)
-{
- struct mic_device *mdev = mbdev_to_mdev(mbdev);
- mdev->ops->intr_workarounds(mdev);
-}
-
-static struct mbus_hw_ops mbus_hw_ops = {
- .request_threaded_irq = _mic_request_threaded_irq,
- .free_irq = _mic_free_irq,
- .ack_interrupt = _mic_ack_interrupt,
-};
-
-/* Initialize the MIC bootparams */
-void mic_bootparam_init(struct mic_device *mdev)
-{
- struct mic_bootparam *bootparam = mdev->dp;
-
- bootparam->magic = cpu_to_le32(MIC_MAGIC);
- bootparam->h2c_config_db = -1;
- bootparam->node_id = mdev->id + 1;
- bootparam->scif_host_dma_addr = 0x0;
- bootparam->scif_card_dma_addr = 0x0;
- bootparam->c2h_scif_db = -1;
- bootparam->h2c_scif_db = -1;
-}
-
-static inline struct mic_device *cosmdev_to_mdev(struct cosm_device *cdev)
-{
- return dev_get_drvdata(cdev->dev.parent);
-}
-
-static void _mic_reset(struct cosm_device *cdev)
-{
- struct mic_device *mdev = cosmdev_to_mdev(cdev);
-
- mdev->ops->reset_fw_ready(mdev);
- mdev->ops->reset(mdev);
-}
-
-static bool _mic_ready(struct cosm_device *cdev)
-{
- struct mic_device *mdev = cosmdev_to_mdev(cdev);
-
- return mdev->ops->is_fw_ready(mdev);
-}
-
-/**
- * mic_request_dma_chans - Request DMA channels
- * @mdev: pointer to mic_device instance
- *
- * returns number of DMA channels acquired
- */
-static int mic_request_dma_chans(struct mic_device *mdev)
-{
- dma_cap_mask_t mask;
- struct dma_chan *chan;
-
- dma_cap_zero(mask);
- dma_cap_set(DMA_MEMCPY, mask);
-
- do {
- chan = dma_request_channel(mask, mdev->ops->dma_filter,
- &mdev->pdev->dev);
- if (chan) {
- mdev->dma_ch[mdev->num_dma_ch++] = chan;
- if (mdev->num_dma_ch >= MIC_MAX_DMA_CHAN)
- break;
- }
- } while (chan);
- dev_info(&mdev->pdev->dev, "DMA channels # %d\n", mdev->num_dma_ch);
- return mdev->num_dma_ch;
-}
-
-/**
- * mic_free_dma_chans - release DMA channels
- * @mdev: pointer to mic_device instance
- *
- * returns none
- */
-static void mic_free_dma_chans(struct mic_device *mdev)
-{
- int i = 0;
-
- for (i = 0; i < mdev->num_dma_ch; i++) {
- dma_release_channel(mdev->dma_ch[i]);
- mdev->dma_ch[i] = NULL;
- }
- mdev->num_dma_ch = 0;
-}
-
-/**
- * _mic_start - Start the MIC.
- * @cdev: pointer to cosm_device instance
- * @id: MIC device id/index provided by COSM used in other drivers like SCIF
- *
- * This function prepares an MIC for boot and initiates boot.
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- *
- * For all cosm_hw_ops the caller holds a mutex to ensure serialization.
- */
-static int _mic_start(struct cosm_device *cdev, int id)
-{
- struct mic_device *mdev = cosmdev_to_mdev(cdev);
- int rc;
-
- mic_bootparam_init(mdev);
- mdev->dma_mbdev = mbus_register_device(&mdev->pdev->dev,
- MBUS_DEV_DMA_HOST, &mic_dma_ops,
- &mbus_hw_ops, id, mdev->mmio.va);
- if (IS_ERR(mdev->dma_mbdev)) {
- rc = PTR_ERR(mdev->dma_mbdev);
- goto unlock_ret;
- }
- if (!mic_request_dma_chans(mdev)) {
- rc = -ENODEV;
- goto dma_remove;
- }
- mdev->scdev = scif_register_device(&mdev->pdev->dev, MIC_SCIF_DEV,
- &__mic_dma_ops, &scif_hw_ops,
- id + 1, 0, &mdev->mmio,
- &mdev->aper, mdev->dp, NULL,
- mdev->dma_ch, mdev->num_dma_ch,
- true);
- if (IS_ERR(mdev->scdev)) {
- rc = PTR_ERR(mdev->scdev);
- goto dma_free;
- }
-
- mdev->vpdev = vop_register_device(&mdev->pdev->dev,
- VOP_DEV_TRNSP, &_mic_dma_ops,
- &vop_hw_ops, id + 1, &mdev->aper,
- mdev->dma_ch[0]);
- if (IS_ERR(mdev->vpdev)) {
- rc = PTR_ERR(mdev->vpdev);
- goto scif_remove;
- }
-
- rc = mdev->ops->load_mic_fw(mdev, NULL);
- if (rc)
- goto vop_remove;
- mic_smpt_restore(mdev);
- mic_intr_restore(mdev);
- mdev->intr_ops->enable_interrupts(mdev);
- mdev->ops->write_spad(mdev, MIC_DPLO_SPAD, mdev->dp_dma_addr);
- mdev->ops->write_spad(mdev, MIC_DPHI_SPAD, mdev->dp_dma_addr >> 32);
- mdev->ops->send_firmware_intr(mdev);
- goto unlock_ret;
-vop_remove:
- vop_unregister_device(mdev->vpdev);
-scif_remove:
- scif_unregister_device(mdev->scdev);
-dma_free:
- mic_free_dma_chans(mdev);
-dma_remove:
- mbus_unregister_device(mdev->dma_mbdev);
-unlock_ret:
- return rc;
-}
-
-/**
- * _mic_stop - Prepare the MIC for reset and trigger reset.
- * @cdev: pointer to cosm_device instance
- * @force: force a MIC to reset even if it is already offline.
- *
- * RETURNS: None.
- */
-static void _mic_stop(struct cosm_device *cdev, bool force)
-{
- struct mic_device *mdev = cosmdev_to_mdev(cdev);
-
- /*
- * Since SCIF handles card shutdown and reset (using COSM), it will
- * will be the first to be registered and the last to be
- * unregistered.
- */
- vop_unregister_device(mdev->vpdev);
- scif_unregister_device(mdev->scdev);
- mic_free_dma_chans(mdev);
- mbus_unregister_device(mdev->dma_mbdev);
- mic_bootparam_init(mdev);
-}
-
-static ssize_t _mic_family(struct cosm_device *cdev, char *buf)
-{
- struct mic_device *mdev = cosmdev_to_mdev(cdev);
- static const char *family[MIC_FAMILY_LAST] = { "x100", "Unknown" };
-
- return scnprintf(buf, PAGE_SIZE, "%s\n", family[mdev->family]);
-}
-
-static ssize_t _mic_stepping(struct cosm_device *cdev, char *buf)
-{
- struct mic_device *mdev = cosmdev_to_mdev(cdev);
- const char *string = "??";
-
- switch (mdev->stepping) {
- case MIC_A0_STEP:
- string = "A0";
- break;
- case MIC_B0_STEP:
- string = "B0";
- break;
- case MIC_B1_STEP:
- string = "B1";
- break;
- case MIC_C0_STEP:
- string = "C0";
- break;
- default:
- break;
- }
- return scnprintf(buf, PAGE_SIZE, "%s\n", string);
-}
-
-static struct mic_mw *_mic_aper(struct cosm_device *cdev)
-{
- struct mic_device *mdev = cosmdev_to_mdev(cdev);
-
- return &mdev->aper;
-}
-
-struct cosm_hw_ops cosm_hw_ops = {
- .reset = _mic_reset,
- .force_reset = _mic_reset,
- .post_reset = NULL,
- .ready = _mic_ready,
- .start = _mic_start,
- .stop = _mic_stop,
- .family = _mic_family,
- .stepping = _mic_stepping,
- .aper = _mic_aper,
-};
diff --git a/drivers/misc/mic/host/mic_debugfs.c b/drivers/misc/mic/host/mic_debugfs.c
deleted file mode 100644
index ffda740..0000000
--- a/drivers/misc/mic/host/mic_debugfs.c
+++ /dev/null
@@ -1,149 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/debugfs.h>
-#include <linux/pci.h>
-#include <linux/seq_file.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_smpt.h"
-
-/* Debugfs parent dir */
-static struct dentry *mic_dbg;
-
-static int mic_smpt_show(struct seq_file *s, void *pos)
-{
- int i;
- struct mic_device *mdev = s->private;
- unsigned long flags;
-
- seq_printf(s, "MIC %-2d |%-10s| %-14s %-10s\n",
- mdev->id, "SMPT entry", "SW DMA addr", "RefCount");
- seq_puts(s, "====================================================\n");
-
- if (mdev->smpt) {
- struct mic_smpt_info *smpt_info = mdev->smpt;
- spin_lock_irqsave(&smpt_info->smpt_lock, flags);
- for (i = 0; i < smpt_info->info.num_reg; i++) {
- seq_printf(s, "%9s|%-10d| %-#14llx %-10lld\n",
- " ", i, smpt_info->entry[i].dma_addr,
- smpt_info->entry[i].ref_count);
- }
- spin_unlock_irqrestore(&smpt_info->smpt_lock, flags);
- }
- seq_puts(s, "====================================================\n");
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(mic_smpt);
-
-static int mic_post_code_show(struct seq_file *s, void *pos)
-{
- struct mic_device *mdev = s->private;
- u32 reg = mdev->ops->get_postcode(mdev);
-
- seq_printf(s, "%c%c", reg & 0xff, (reg >> 8) & 0xff);
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(mic_post_code);
-
-static int mic_msi_irq_info_show(struct seq_file *s, void *pos)
-{
- struct mic_device *mdev = s->private;
- int reg;
- int i, j;
- u16 entry;
- u16 vector;
- struct pci_dev *pdev = mdev->pdev;
-
- if (pci_dev_msi_enabled(pdev)) {
- for (i = 0; i < mdev->irq_info.num_vectors; i++) {
- if (pdev->msix_enabled) {
- entry = mdev->irq_info.msix_entries[i].entry;
- vector = mdev->irq_info.msix_entries[i].vector;
- } else {
- entry = 0;
- vector = pdev->irq;
- }
-
- reg = mdev->intr_ops->read_msi_to_src_map(mdev, entry);
-
- seq_printf(s, "%s %-10d %s %-10d MXAR[%d]: %08X\n",
- "IRQ:", vector, "Entry:", entry, i, reg);
-
- seq_printf(s, "%-10s", "offset:");
- for (j = (MIC_NUM_OFFSETS - 1); j >= 0; j--)
- seq_printf(s, "%4d ", j);
- seq_puts(s, "\n");
-
-
- seq_printf(s, "%-10s", "count:");
- for (j = (MIC_NUM_OFFSETS - 1); j >= 0; j--)
- seq_printf(s, "%4d ",
- (mdev->irq_info.mic_msi_map[i] &
- BIT(j)) ? 1 : 0);
- seq_puts(s, "\n\n");
- }
- } else {
- seq_puts(s, "MSI/MSIx interrupts not enabled\n");
- }
-
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(mic_msi_irq_info);
-
-/*
- * mic_create_debug_dir - Initialize MIC debugfs entries.
- */
-void mic_create_debug_dir(struct mic_device *mdev)
-{
- char name[16];
-
- if (!mic_dbg)
- return;
-
- scnprintf(name, sizeof(name), "mic%d", mdev->id);
- mdev->dbg_dir = debugfs_create_dir(name, mic_dbg);
-
- debugfs_create_file("smpt", 0444, mdev->dbg_dir, mdev,
- &mic_smpt_fops);
-
- debugfs_create_file("post_code", 0444, mdev->dbg_dir, mdev,
- &mic_post_code_fops);
-
- debugfs_create_file("msi_irq_info", 0444, mdev->dbg_dir, mdev,
- &mic_msi_irq_info_fops);
-}
-
-/*
- * mic_delete_debug_dir - Uninitialize MIC debugfs entries.
- */
-void mic_delete_debug_dir(struct mic_device *mdev)
-{
- debugfs_remove_recursive(mdev->dbg_dir);
-}
-
-/*
- * mic_init_debugfs - Initialize global debugfs entry.
- */
-void __init mic_init_debugfs(void)
-{
- mic_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL);
-}
-
-/*
- * mic_exit_debugfs - Uninitialize global debugfs entry
- */
-void mic_exit_debugfs(void)
-{
- debugfs_remove(mic_dbg);
-}
diff --git a/drivers/misc/mic/host/mic_device.h b/drivers/misc/mic/host/mic_device.h
deleted file mode 100644
index 41bcd30..0000000
--- a/drivers/misc/mic/host/mic_device.h
+++ /dev/null
@@ -1,157 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#ifndef _MIC_DEVICE_H_
-#define _MIC_DEVICE_H_
-
-#include <linux/cdev.h>
-#include <linux/idr.h>
-#include <linux/notifier.h>
-#include <linux/irqreturn.h>
-#include <linux/dmaengine.h>
-#include <linux/miscdevice.h>
-#include <linux/mic_bus.h>
-#include "../bus/scif_bus.h"
-#include "../bus/vop_bus.h"
-#include "../bus/cosm_bus.h"
-#include "mic_intr.h"
-
-/**
- * enum mic_stepping - MIC stepping ids.
- */
-enum mic_stepping {
- MIC_A0_STEP = 0x0,
- MIC_B0_STEP = 0x10,
- MIC_B1_STEP = 0x11,
- MIC_C0_STEP = 0x20,
-};
-
-extern struct cosm_hw_ops cosm_hw_ops;
-
-/**
- * struct mic_device - MIC device information for each card.
- *
- * @mmio: MMIO bar information.
- * @aper: Aperture bar information.
- * @family: The MIC family to which this device belongs.
- * @ops: MIC HW specific operations.
- * @id: The unique device id for this MIC device.
- * @stepping: Stepping ID.
- * @pdev: Underlying PCI device.
- * @mic_mutex: Mutex for synchronizing access to mic_device.
- * @intr_ops: HW specific interrupt operations.
- * @smpt_ops: Hardware specific SMPT operations.
- * @smpt: MIC SMPT information.
- * @intr_info: H/W specific interrupt information.
- * @irq_info: The OS specific irq information
- * @dbg_dir: debugfs directory of this MIC device.
- * @bootaddr: MIC boot address.
- * @dp: virtio device page
- * @dp_dma_addr: virtio device page DMA address.
- * @dma_mbdev: MIC BUS DMA device.
- * @dma_ch - Array of DMA channels
- * @num_dma_ch - Number of DMA channels available
- * @scdev: SCIF device on the SCIF virtual bus.
- * @vpdev: Virtio over PCIe device on the VOP virtual bus.
- * @cosm_dev: COSM device
- */
-struct mic_device {
- struct mic_mw mmio;
- struct mic_mw aper;
- enum mic_hw_family family;
- struct mic_hw_ops *ops;
- int id;
- enum mic_stepping stepping;
- struct pci_dev *pdev;
- struct mutex mic_mutex;
- struct mic_hw_intr_ops *intr_ops;
- struct mic_smpt_ops *smpt_ops;
- struct mic_smpt_info *smpt;
- struct mic_intr_info *intr_info;
- struct mic_irq_info irq_info;
- struct dentry *dbg_dir;
- u32 bootaddr;
- void *dp;
- dma_addr_t dp_dma_addr;
- struct mbus_device *dma_mbdev;
- struct dma_chan *dma_ch[MIC_MAX_DMA_CHAN];
- int num_dma_ch;
- struct scif_hw_dev *scdev;
- struct vop_device *vpdev;
- struct cosm_device *cosm_dev;
-};
-
-/**
- * struct mic_hw_ops - MIC HW specific operations.
- * @aper_bar: Aperture bar resource number.
- * @mmio_bar: MMIO bar resource number.
- * @read_spad: Read from scratch pad register.
- * @write_spad: Write to scratch pad register.
- * @send_intr: Send an interrupt for a particular doorbell on the card.
- * @ack_interrupt: Hardware specific operations to ack the h/w on
- * receipt of an interrupt.
- * @intr_workarounds: Hardware specific workarounds needed after
- * handling an interrupt.
- * @reset: Reset the remote processor.
- * @reset_fw_ready: Reset firmware ready field.
- * @is_fw_ready: Check if firmware is ready for OS download.
- * @send_firmware_intr: Send an interrupt to the card firmware.
- * @load_mic_fw: Load firmware segments required to boot the card
- * into card memory. This includes the kernel, command line, ramdisk etc.
- * @get_postcode: Get post code status from firmware.
- * @dma_filter: DMA filter function to be used.
- */
-struct mic_hw_ops {
- u8 aper_bar;
- u8 mmio_bar;
- u32 (*read_spad)(struct mic_device *mdev, unsigned int idx);
- void (*write_spad)(struct mic_device *mdev, unsigned int idx, u32 val);
- void (*send_intr)(struct mic_device *mdev, int doorbell);
- u32 (*ack_interrupt)(struct mic_device *mdev);
- void (*intr_workarounds)(struct mic_device *mdev);
- void (*reset)(struct mic_device *mdev);
- void (*reset_fw_ready)(struct mic_device *mdev);
- bool (*is_fw_ready)(struct mic_device *mdev);
- void (*send_firmware_intr)(struct mic_device *mdev);
- int (*load_mic_fw)(struct mic_device *mdev, const char *buf);
- u32 (*get_postcode)(struct mic_device *mdev);
- bool (*dma_filter)(struct dma_chan *chan, void *param);
-};
-
-/**
- * mic_mmio_read - read from an MMIO register.
- * @mw: MMIO register base virtual address.
- * @offset: register offset.
- *
- * RETURNS: register value.
- */
-static inline u32 mic_mmio_read(struct mic_mw *mw, u32 offset)
-{
- return ioread32(mw->va + offset);
-}
-
-/**
- * mic_mmio_write - write to an MMIO register.
- * @mw: MMIO register base virtual address.
- * @val: the data value to put into the register
- * @offset: register offset.
- *
- * RETURNS: none.
- */
-static inline void
-mic_mmio_write(struct mic_mw *mw, u32 val, u32 offset)
-{
- iowrite32(val, mw->va + offset);
-}
-
-void mic_bootparam_init(struct mic_device *mdev);
-void mic_create_debug_dir(struct mic_device *dev);
-void mic_delete_debug_dir(struct mic_device *dev);
-void __init mic_init_debugfs(void);
-void mic_exit_debugfs(void);
-#endif
diff --git a/drivers/misc/mic/host/mic_intr.c b/drivers/misc/mic/host/mic_intr.c
deleted file mode 100644
index 85b3221..0000000
--- a/drivers/misc/mic/host/mic_intr.c
+++ /dev/null
@@ -1,635 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/pci.h>
-#include <linux/interrupt.h>
-
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-
-static irqreturn_t mic_thread_fn(int irq, void *dev)
-{
- struct mic_device *mdev = dev;
- struct mic_intr_info *intr_info = mdev->intr_info;
- struct mic_irq_info *irq_info = &mdev->irq_info;
- struct mic_intr_cb *intr_cb;
- struct pci_dev *pdev = mdev->pdev;
- int i;
-
- spin_lock(&irq_info->mic_thread_lock);
- for (i = intr_info->intr_start_idx[MIC_INTR_DB];
- i < intr_info->intr_len[MIC_INTR_DB]; i++)
- if (test_and_clear_bit(i, &irq_info->mask)) {
- list_for_each_entry(intr_cb, &irq_info->cb_list[i],
- list)
- if (intr_cb->thread_fn)
- intr_cb->thread_fn(pdev->irq,
- intr_cb->data);
- }
- spin_unlock(&irq_info->mic_thread_lock);
- return IRQ_HANDLED;
-}
-/**
- * mic_interrupt - Generic interrupt handler for
- * MSI and INTx based interrupts.
- * @irq: interrupt to handle (unused)
- * @dev: pointer to the mic_device instance
- */
-static irqreturn_t mic_interrupt(int irq, void *dev)
-{
- struct mic_device *mdev = dev;
- struct mic_intr_info *intr_info = mdev->intr_info;
- struct mic_irq_info *irq_info = &mdev->irq_info;
- struct mic_intr_cb *intr_cb;
- struct pci_dev *pdev = mdev->pdev;
- u32 mask;
- int i;
-
- mask = mdev->ops->ack_interrupt(mdev);
- if (!mask)
- return IRQ_NONE;
-
- spin_lock(&irq_info->mic_intr_lock);
- for (i = intr_info->intr_start_idx[MIC_INTR_DB];
- i < intr_info->intr_len[MIC_INTR_DB]; i++)
- if (mask & BIT(i)) {
- list_for_each_entry(intr_cb, &irq_info->cb_list[i],
- list)
- if (intr_cb->handler)
- intr_cb->handler(pdev->irq,
- intr_cb->data);
- set_bit(i, &irq_info->mask);
- }
- spin_unlock(&irq_info->mic_intr_lock);
- return IRQ_WAKE_THREAD;
-}
-
-/* Return the interrupt offset from the index. Index is 0 based. */
-static u16 mic_map_src_to_offset(struct mic_device *mdev,
- int intr_src, enum mic_intr_type type)
-{
- if (type >= MIC_NUM_INTR_TYPES)
- return MIC_NUM_OFFSETS;
- if (intr_src >= mdev->intr_info->intr_len[type])
- return MIC_NUM_OFFSETS;
-
- return mdev->intr_info->intr_start_idx[type] + intr_src;
-}
-
-/* Return next available msix_entry. */
-static struct msix_entry *mic_get_available_vector(struct mic_device *mdev)
-{
- int i;
- struct mic_irq_info *info = &mdev->irq_info;
-
- for (i = 0; i < info->num_vectors; i++)
- if (!info->mic_msi_map[i])
- return &info->msix_entries[i];
- return NULL;
-}
-
-/**
- * mic_register_intr_callback - Register a callback handler for the
- * given source id.
- *
- * @mdev: pointer to the mic_device instance
- * @idx: The source id to be registered.
- * @handler: The function to be called when the source id receives
- * the interrupt.
- * @thread_fn: thread fn. corresponding to the handler
- * @data: Private data of the requester.
- * Return the callback structure that was registered or an
- * appropriate error on failure.
- */
-static struct mic_intr_cb *mic_register_intr_callback(struct mic_device *mdev,
- u8 idx, irq_handler_t handler, irq_handler_t thread_fn,
- void *data)
-{
- struct mic_intr_cb *intr_cb;
- unsigned long flags;
- int rc;
- intr_cb = kmalloc(sizeof(*intr_cb), GFP_KERNEL);
-
- if (!intr_cb)
- return ERR_PTR(-ENOMEM);
-
- intr_cb->handler = handler;
- intr_cb->thread_fn = thread_fn;
- intr_cb->data = data;
- intr_cb->cb_id = ida_simple_get(&mdev->irq_info.cb_ida,
- 0, 0, GFP_KERNEL);
- if (intr_cb->cb_id < 0) {
- rc = intr_cb->cb_id;
- goto ida_fail;
- }
-
- spin_lock(&mdev->irq_info.mic_thread_lock);
- spin_lock_irqsave(&mdev->irq_info.mic_intr_lock, flags);
- list_add_tail(&intr_cb->list, &mdev->irq_info.cb_list[idx]);
- spin_unlock_irqrestore(&mdev->irq_info.mic_intr_lock, flags);
- spin_unlock(&mdev->irq_info.mic_thread_lock);
-
- return intr_cb;
-ida_fail:
- kfree(intr_cb);
- return ERR_PTR(rc);
-}
-
-/**
- * mic_unregister_intr_callback - Unregister the callback handler
- * identified by its callback id.
- *
- * @mdev: pointer to the mic_device instance
- * @idx: The callback structure id to be unregistered.
- * Return the source id that was unregistered or MIC_NUM_OFFSETS if no
- * such callback handler was found.
- */
-static u8 mic_unregister_intr_callback(struct mic_device *mdev, u32 idx)
-{
- struct list_head *pos, *tmp;
- struct mic_intr_cb *intr_cb;
- unsigned long flags;
- int i;
-
- spin_lock(&mdev->irq_info.mic_thread_lock);
- spin_lock_irqsave(&mdev->irq_info.mic_intr_lock, flags);
- for (i = 0; i < MIC_NUM_OFFSETS; i++) {
- list_for_each_safe(pos, tmp, &mdev->irq_info.cb_list[i]) {
- intr_cb = list_entry(pos, struct mic_intr_cb, list);
- if (intr_cb->cb_id == idx) {
- list_del(pos);
- ida_simple_remove(&mdev->irq_info.cb_ida,
- intr_cb->cb_id);
- kfree(intr_cb);
- spin_unlock_irqrestore(
- &mdev->irq_info.mic_intr_lock, flags);
- spin_unlock(&mdev->irq_info.mic_thread_lock);
- return i;
- }
- }
- }
- spin_unlock_irqrestore(&mdev->irq_info.mic_intr_lock, flags);
- spin_unlock(&mdev->irq_info.mic_thread_lock);
- return MIC_NUM_OFFSETS;
-}
-
-/**
- * mic_setup_msix - Initializes MSIx interrupts.
- *
- * @mdev: pointer to mic_device instance
- * @pdev: PCI device structure
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int mic_setup_msix(struct mic_device *mdev, struct pci_dev *pdev)
-{
- int rc, i;
- int entry_size = sizeof(*mdev->irq_info.msix_entries);
-
- mdev->irq_info.msix_entries = kmalloc_array(MIC_MIN_MSIX,
- entry_size, GFP_KERNEL);
- if (!mdev->irq_info.msix_entries) {
- rc = -ENOMEM;
- goto err_nomem1;
- }
-
- for (i = 0; i < MIC_MIN_MSIX; i++)
- mdev->irq_info.msix_entries[i].entry = i;
-
- rc = pci_enable_msix_exact(pdev, mdev->irq_info.msix_entries,
- MIC_MIN_MSIX);
- if (rc) {
- dev_dbg(&pdev->dev, "Error enabling MSIx. rc = %d\n", rc);
- goto err_enable_msix;
- }
-
- mdev->irq_info.num_vectors = MIC_MIN_MSIX;
- mdev->irq_info.mic_msi_map = kzalloc((sizeof(u32) *
- mdev->irq_info.num_vectors), GFP_KERNEL);
-
- if (!mdev->irq_info.mic_msi_map) {
- rc = -ENOMEM;
- goto err_nomem2;
- }
-
- dev_dbg(&mdev->pdev->dev,
- "%d MSIx irqs setup\n", mdev->irq_info.num_vectors);
- return 0;
-err_nomem2:
- pci_disable_msix(pdev);
-err_enable_msix:
- kfree(mdev->irq_info.msix_entries);
-err_nomem1:
- mdev->irq_info.num_vectors = 0;
- return rc;
-}
-
-/**
- * mic_setup_callbacks - Initialize data structures needed
- * to handle callbacks.
- *
- * @mdev: pointer to mic_device instance
- */
-static int mic_setup_callbacks(struct mic_device *mdev)
-{
- int i;
-
- mdev->irq_info.cb_list = kmalloc_array(MIC_NUM_OFFSETS,
- sizeof(*mdev->irq_info.cb_list),
- GFP_KERNEL);
- if (!mdev->irq_info.cb_list)
- return -ENOMEM;
-
- for (i = 0; i < MIC_NUM_OFFSETS; i++)
- INIT_LIST_HEAD(&mdev->irq_info.cb_list[i]);
- ida_init(&mdev->irq_info.cb_ida);
- spin_lock_init(&mdev->irq_info.mic_intr_lock);
- spin_lock_init(&mdev->irq_info.mic_thread_lock);
- return 0;
-}
-
-/**
- * mic_release_callbacks - Uninitialize data structures needed
- * to handle callbacks.
- *
- * @mdev: pointer to mic_device instance
- */
-static void mic_release_callbacks(struct mic_device *mdev)
-{
- unsigned long flags;
- struct list_head *pos, *tmp;
- struct mic_intr_cb *intr_cb;
- int i;
-
- spin_lock(&mdev->irq_info.mic_thread_lock);
- spin_lock_irqsave(&mdev->irq_info.mic_intr_lock, flags);
- for (i = 0; i < MIC_NUM_OFFSETS; i++) {
- if (list_empty(&mdev->irq_info.cb_list[i]))
- break;
-
- list_for_each_safe(pos, tmp, &mdev->irq_info.cb_list[i]) {
- intr_cb = list_entry(pos, struct mic_intr_cb, list);
- list_del(pos);
- ida_simple_remove(&mdev->irq_info.cb_ida,
- intr_cb->cb_id);
- kfree(intr_cb);
- }
- }
- spin_unlock_irqrestore(&mdev->irq_info.mic_intr_lock, flags);
- spin_unlock(&mdev->irq_info.mic_thread_lock);
- ida_destroy(&mdev->irq_info.cb_ida);
- kfree(mdev->irq_info.cb_list);
-}
-
-/**
- * mic_setup_msi - Initializes MSI interrupts.
- *
- * @mdev: pointer to mic_device instance
- * @pdev: PCI device structure
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int mic_setup_msi(struct mic_device *mdev, struct pci_dev *pdev)
-{
- int rc;
-
- rc = pci_enable_msi(pdev);
- if (rc) {
- dev_dbg(&pdev->dev, "Error enabling MSI. rc = %d\n", rc);
- return rc;
- }
-
- mdev->irq_info.num_vectors = 1;
- mdev->irq_info.mic_msi_map = kzalloc((sizeof(u32) *
- mdev->irq_info.num_vectors), GFP_KERNEL);
-
- if (!mdev->irq_info.mic_msi_map) {
- rc = -ENOMEM;
- goto err_nomem1;
- }
-
- rc = mic_setup_callbacks(mdev);
- if (rc) {
- dev_err(&pdev->dev, "Error setting up callbacks\n");
- goto err_nomem2;
- }
-
- rc = request_threaded_irq(pdev->irq, mic_interrupt, mic_thread_fn,
- 0, "mic-msi", mdev);
- if (rc) {
- dev_err(&pdev->dev, "Error allocating MSI interrupt\n");
- goto err_irq_req_fail;
- }
-
- dev_dbg(&pdev->dev, "%d MSI irqs setup\n", mdev->irq_info.num_vectors);
- return 0;
-err_irq_req_fail:
- mic_release_callbacks(mdev);
-err_nomem2:
- kfree(mdev->irq_info.mic_msi_map);
-err_nomem1:
- pci_disable_msi(pdev);
- mdev->irq_info.num_vectors = 0;
- return rc;
-}
-
-/**
- * mic_setup_intx - Initializes legacy interrupts.
- *
- * @mdev: pointer to mic_device instance
- * @pdev: PCI device structure
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int mic_setup_intx(struct mic_device *mdev, struct pci_dev *pdev)
-{
- int rc;
-
- /* Enable intx */
- pci_intx(pdev, 1);
- rc = mic_setup_callbacks(mdev);
- if (rc) {
- dev_err(&pdev->dev, "Error setting up callbacks\n");
- goto err_nomem;
- }
-
- rc = request_threaded_irq(pdev->irq, mic_interrupt, mic_thread_fn,
- IRQF_SHARED, "mic-intx", mdev);
- if (rc)
- goto err;
-
- dev_dbg(&pdev->dev, "intx irq setup\n");
- return 0;
-err:
- mic_release_callbacks(mdev);
-err_nomem:
- return rc;
-}
-
-/**
- * mic_next_db - Retrieve the next doorbell interrupt source id.
- * The id is picked sequentially from the available pool of
- * doorlbell ids.
- *
- * @mdev: pointer to the mic_device instance.
- *
- * Returns the next doorbell interrupt source.
- */
-int mic_next_db(struct mic_device *mdev)
-{
- int next_db;
-
- next_db = mdev->irq_info.next_avail_src %
- mdev->intr_info->intr_len[MIC_INTR_DB];
- mdev->irq_info.next_avail_src++;
- return next_db;
-}
-
-#define COOKIE_ID_SHIFT 16
-#define GET_ENTRY(cookie) ((cookie) & 0xFFFF)
-#define GET_OFFSET(cookie) ((cookie) >> COOKIE_ID_SHIFT)
-#define MK_COOKIE(x, y) ((x) | (y) << COOKIE_ID_SHIFT)
-
-/**
- * mic_request_threaded_irq - request an irq. mic_mutex needs
- * to be held before calling this function.
- *
- * @mdev: pointer to mic_device instance
- * @handler: The callback function that handles the interrupt.
- * The function needs to call ack_interrupts
- * (mdev->ops->ack_interrupt(mdev)) when handling the interrupts.
- * @thread_fn: thread fn required by request_threaded_irq.
- * @name: The ASCII name of the callee requesting the irq.
- * @data: private data that is returned back when calling the
- * function handler.
- * @intr_src: The source id of the requester. Its the doorbell id
- * for Doorbell interrupts and DMA channel id for DMA interrupts.
- * @type: The type of interrupt. Values defined in mic_intr_type
- *
- * returns: The cookie that is transparent to the caller. Passed
- * back when calling mic_free_irq. An appropriate error code
- * is returned on failure. Caller needs to use IS_ERR(return_val)
- * to check for failure and PTR_ERR(return_val) to obtained the
- * error code.
- *
- */
-struct mic_irq *
-mic_request_threaded_irq(struct mic_device *mdev,
- irq_handler_t handler, irq_handler_t thread_fn,
- const char *name, void *data, int intr_src,
- enum mic_intr_type type)
-{
- u16 offset;
- int rc = 0;
- struct msix_entry *msix = NULL;
- unsigned long cookie = 0;
- u16 entry;
- struct mic_intr_cb *intr_cb;
- struct pci_dev *pdev = mdev->pdev;
-
- offset = mic_map_src_to_offset(mdev, intr_src, type);
- if (offset >= MIC_NUM_OFFSETS) {
- dev_err(&mdev->pdev->dev,
- "Error mapping index %d to a valid source id.\n",
- intr_src);
- rc = -EINVAL;
- goto err;
- }
-
- if (mdev->irq_info.num_vectors > 1) {
- msix = mic_get_available_vector(mdev);
- if (!msix) {
- dev_err(&mdev->pdev->dev,
- "No MSIx vectors available for use.\n");
- rc = -ENOSPC;
- goto err;
- }
-
- rc = request_threaded_irq(msix->vector, handler, thread_fn,
- 0, name, data);
- if (rc) {
- dev_dbg(&mdev->pdev->dev,
- "request irq failed rc = %d\n", rc);
- goto err;
- }
- entry = msix->entry;
- mdev->irq_info.mic_msi_map[entry] |= BIT(offset);
- mdev->intr_ops->program_msi_to_src_map(mdev,
- entry, offset, true);
- cookie = MK_COOKIE(entry, offset);
- dev_dbg(&mdev->pdev->dev, "irq: %d assigned for src: %d\n",
- msix->vector, intr_src);
- } else {
- intr_cb = mic_register_intr_callback(mdev, offset, handler,
- thread_fn, data);
- if (IS_ERR(intr_cb)) {
- dev_err(&mdev->pdev->dev,
- "No available callback entries for use\n");
- rc = PTR_ERR(intr_cb);
- goto err;
- }
-
- entry = 0;
- if (pci_dev_msi_enabled(pdev)) {
- mdev->irq_info.mic_msi_map[entry] |= (1 << offset);
- mdev->intr_ops->program_msi_to_src_map(mdev,
- entry, offset, true);
- }
- cookie = MK_COOKIE(entry, intr_cb->cb_id);
- dev_dbg(&mdev->pdev->dev, "callback %d registered for src: %d\n",
- intr_cb->cb_id, intr_src);
- }
- return (struct mic_irq *)cookie;
-err:
- return ERR_PTR(rc);
-}
-
-/**
- * mic_free_irq - free irq. mic_mutex
- * needs to be held before calling this function.
- *
- * @mdev: pointer to mic_device instance
- * @cookie: cookie obtained during a successful call to mic_request_threaded_irq
- * @data: private data specified by the calling function during the
- * mic_request_threaded_irq
- *
- * returns: none.
- */
-void mic_free_irq(struct mic_device *mdev,
- struct mic_irq *cookie, void *data)
-{
- u32 offset;
- u32 entry;
- u8 src_id;
- unsigned int irq;
- struct pci_dev *pdev = mdev->pdev;
-
- entry = GET_ENTRY((unsigned long)cookie);
- offset = GET_OFFSET((unsigned long)cookie);
- if (mdev->irq_info.num_vectors > 1) {
- if (entry >= mdev->irq_info.num_vectors) {
- dev_warn(&mdev->pdev->dev,
- "entry %d should be < num_irq %d\n",
- entry, mdev->irq_info.num_vectors);
- return;
- }
- irq = mdev->irq_info.msix_entries[entry].vector;
- free_irq(irq, data);
- mdev->irq_info.mic_msi_map[entry] &= ~(BIT(offset));
- mdev->intr_ops->program_msi_to_src_map(mdev,
- entry, offset, false);
-
- dev_dbg(&mdev->pdev->dev, "irq: %d freed\n", irq);
- } else {
- irq = pdev->irq;
- src_id = mic_unregister_intr_callback(mdev, offset);
- if (src_id >= MIC_NUM_OFFSETS) {
- dev_warn(&mdev->pdev->dev, "Error unregistering callback\n");
- return;
- }
- if (pci_dev_msi_enabled(pdev)) {
- mdev->irq_info.mic_msi_map[entry] &= ~(BIT(src_id));
- mdev->intr_ops->program_msi_to_src_map(mdev,
- entry, src_id, false);
- }
- dev_dbg(&mdev->pdev->dev, "callback %d unregistered for src: %d\n",
- offset, src_id);
- }
-}
-
-/**
- * mic_setup_interrupts - Initializes interrupts.
- *
- * @mdev: pointer to mic_device instance
- * @pdev: PCI device structure
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-int mic_setup_interrupts(struct mic_device *mdev, struct pci_dev *pdev)
-{
- int rc;
-
- rc = mic_setup_msix(mdev, pdev);
- if (!rc)
- goto done;
-
- rc = mic_setup_msi(mdev, pdev);
- if (!rc)
- goto done;
-
- rc = mic_setup_intx(mdev, pdev);
- if (rc) {
- dev_err(&mdev->pdev->dev, "no usable interrupts\n");
- return rc;
- }
-done:
- mdev->intr_ops->enable_interrupts(mdev);
- return 0;
-}
-
-/**
- * mic_free_interrupts - Frees interrupts setup by mic_setup_interrupts
- *
- * @mdev: pointer to mic_device instance
- * @pdev: PCI device structure
- *
- * returns none.
- */
-void mic_free_interrupts(struct mic_device *mdev, struct pci_dev *pdev)
-{
- int i;
-
- mdev->intr_ops->disable_interrupts(mdev);
- if (mdev->irq_info.num_vectors > 1) {
- for (i = 0; i < mdev->irq_info.num_vectors; i++) {
- if (mdev->irq_info.mic_msi_map[i])
- dev_warn(&pdev->dev, "irq %d may still be in use.\n",
- mdev->irq_info.msix_entries[i].vector);
- }
- kfree(mdev->irq_info.mic_msi_map);
- kfree(mdev->irq_info.msix_entries);
- pci_disable_msix(pdev);
- } else {
- if (pci_dev_msi_enabled(pdev)) {
- free_irq(pdev->irq, mdev);
- kfree(mdev->irq_info.mic_msi_map);
- pci_disable_msi(pdev);
- } else {
- free_irq(pdev->irq, mdev);
- }
- mic_release_callbacks(mdev);
- }
-}
-
-/**
- * mic_intr_restore - Restore MIC interrupt registers.
- *
- * @mdev: pointer to mic_device instance.
- *
- * Restore the interrupt registers to values previously
- * stored in the SW data structures. mic_mutex needs to
- * be held before calling this function.
- *
- * returns None.
- */
-void mic_intr_restore(struct mic_device *mdev)
-{
- int entry, offset;
- struct pci_dev *pdev = mdev->pdev;
-
- if (!pci_dev_msi_enabled(pdev))
- return;
-
- for (entry = 0; entry < mdev->irq_info.num_vectors; entry++) {
- for (offset = 0; offset < MIC_NUM_OFFSETS; offset++) {
- if (mdev->irq_info.mic_msi_map[entry] & BIT(offset))
- mdev->intr_ops->program_msi_to_src_map(mdev,
- entry, offset, true);
- }
- }
-}
diff --git a/drivers/misc/mic/host/mic_intr.h b/drivers/misc/mic/host/mic_intr.h
deleted file mode 100644
index b14ba81..0000000
--- a/drivers/misc/mic/host/mic_intr.h
+++ /dev/null
@@ -1,137 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#ifndef _MIC_INTR_H_
-#define _MIC_INTR_H_
-
-#include <linux/bitops.h>
-#include <linux/interrupt.h>
-/*
- * The minimum number of msix vectors required for normal operation.
- * 3 for virtio network, console and block devices.
- * 1 for card shutdown notifications.
- * 4 for host owned DMA channels.
- * 1 for SCIF
- */
-#define MIC_MIN_MSIX 9
-#define MIC_NUM_OFFSETS 32
-
-/**
- * mic_intr_source - The type of source that will generate
- * the interrupt.The number of types needs to be in sync with
- * MIC_NUM_INTR_TYPES
- *
- * MIC_INTR_DB: The source is a doorbell
- * MIC_INTR_DMA: The source is a DMA channel
- * MIC_INTR_ERR: The source is an error interrupt e.g. SBOX ERR
- * MIC_NUM_INTR_TYPES: Total number of interrupt sources.
- */
-enum mic_intr_type {
- MIC_INTR_DB = 0,
- MIC_INTR_DMA,
- MIC_INTR_ERR,
- MIC_NUM_INTR_TYPES
-};
-
-/**
- * struct mic_intr_info - Contains h/w specific interrupt sources
- * information.
- *
- * @intr_start_idx: Contains the starting indexes of the
- * interrupt types.
- * @intr_len: Contains the length of the interrupt types.
- */
-struct mic_intr_info {
- u16 intr_start_idx[MIC_NUM_INTR_TYPES];
- u16 intr_len[MIC_NUM_INTR_TYPES];
-};
-
-/**
- * struct mic_irq_info - OS specific irq information
- *
- * @next_avail_src: next available doorbell that can be assigned.
- * @msix_entries: msix entries allocated while setting up MSI-x
- * @mic_msi_map: The MSI/MSI-x mapping information.
- * @num_vectors: The number of MSI/MSI-x vectors that have been allocated.
- * @cb_ida: callback ID allocator to track the callbacks registered.
- * @mic_intr_lock: spinlock to protect the interrupt callback list.
- * @mic_thread_lock: spinlock to protect the thread callback list.
- * This lock is used to protect against thread_fn while
- * mic_intr_lock is used to protect against interrupt handler.
- * @cb_list: Array of callback lists one for each source.
- * @mask: Mask used by the main thread fn to call the underlying thread fns.
- */
-struct mic_irq_info {
- int next_avail_src;
- struct msix_entry *msix_entries;
- u32 *mic_msi_map;
- u16 num_vectors;
- struct ida cb_ida;
- spinlock_t mic_intr_lock;
- spinlock_t mic_thread_lock;
- struct list_head *cb_list;
- unsigned long mask;
-};
-
-/**
- * struct mic_intr_cb - Interrupt callback structure.
- *
- * @handler: The callback function
- * @thread_fn: The thread_fn.
- * @data: Private data of the requester.
- * @cb_id: The callback id. Identifies this callback.
- * @list: list head pointing to the next callback structure.
- */
-struct mic_intr_cb {
- irq_handler_t handler;
- irq_handler_t thread_fn;
- void *data;
- int cb_id;
- struct list_head list;
-};
-
-/**
- * struct mic_irq - opaque pointer used as cookie
- */
-struct mic_irq;
-
-/* Forward declaration */
-struct mic_device;
-
-/**
- * struct mic_hw_intr_ops: MIC HW specific interrupt operations
- * @intr_init: Initialize H/W specific interrupt information.
- * @enable_interrupts: Enable interrupts from the hardware.
- * @disable_interrupts: Disable interrupts from the hardware.
- * @program_msi_to_src_map: Update MSI mapping registers with
- * irq information.
- * @read_msi_to_src_map: Read MSI mapping registers containing
- * irq information.
- */
-struct mic_hw_intr_ops {
- void (*intr_init)(struct mic_device *mdev);
- void (*enable_interrupts)(struct mic_device *mdev);
- void (*disable_interrupts)(struct mic_device *mdev);
- void (*program_msi_to_src_map) (struct mic_device *mdev,
- int idx, int intr_src, bool set);
- u32 (*read_msi_to_src_map) (struct mic_device *mdev,
- int idx);
-};
-
-int mic_next_db(struct mic_device *mdev);
-struct mic_irq *
-mic_request_threaded_irq(struct mic_device *mdev,
- irq_handler_t handler, irq_handler_t thread_fn,
- const char *name, void *data, int intr_src,
- enum mic_intr_type type);
-void mic_free_irq(struct mic_device *mdev,
- struct mic_irq *cookie, void *data);
-int mic_setup_interrupts(struct mic_device *mdev, struct pci_dev *pdev);
-void mic_free_interrupts(struct mic_device *mdev, struct pci_dev *pdev);
-void mic_intr_restore(struct mic_device *mdev);
-#endif
diff --git a/drivers/misc/mic/host/mic_main.c b/drivers/misc/mic/host/mic_main.c
deleted file mode 100644
index ea46085..0000000
--- a/drivers/misc/mic/host/mic_main.c
+++ /dev/null
@@ -1,335 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/fs.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/poll.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_x100.h"
-#include "mic_smpt.h"
-
-static const char mic_driver_name[] = "mic";
-
-static const struct pci_device_id mic_pci_tbl[] = {
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2250)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2251)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2252)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2253)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2254)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2255)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2256)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2257)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2258)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2259)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225a)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225b)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225c)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225d)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225e)},
-
- /* required last entry */
- { 0, }
-};
-
-MODULE_DEVICE_TABLE(pci, mic_pci_tbl);
-
-/* ID allocator for MIC devices */
-static struct ida g_mic_ida;
-
-/* Initialize the device page */
-static int mic_dp_init(struct mic_device *mdev)
-{
- mdev->dp = kzalloc(MIC_DP_SIZE, GFP_KERNEL);
- if (!mdev->dp)
- return -ENOMEM;
-
- mdev->dp_dma_addr = mic_map_single(mdev,
- mdev->dp, MIC_DP_SIZE);
- if (mic_map_error(mdev->dp_dma_addr)) {
- kfree(mdev->dp);
- dev_err(&mdev->pdev->dev, "%s %d err %d\n",
- __func__, __LINE__, -ENOMEM);
- return -ENOMEM;
- }
- mdev->ops->write_spad(mdev, MIC_DPLO_SPAD, mdev->dp_dma_addr);
- mdev->ops->write_spad(mdev, MIC_DPHI_SPAD, mdev->dp_dma_addr >> 32);
- return 0;
-}
-
-/* Uninitialize the device page */
-static void mic_dp_uninit(struct mic_device *mdev)
-{
- mic_unmap_single(mdev, mdev->dp_dma_addr, MIC_DP_SIZE);
- kfree(mdev->dp);
-}
-
-/**
- * mic_ops_init: Initialize HW specific operation tables.
- *
- * @mdev: pointer to mic_device instance
- *
- * returns none.
- */
-static void mic_ops_init(struct mic_device *mdev)
-{
- switch (mdev->family) {
- case MIC_FAMILY_X100:
- mdev->ops = &mic_x100_ops;
- mdev->intr_ops = &mic_x100_intr_ops;
- mdev->smpt_ops = &mic_x100_smpt_ops;
- break;
- default:
- break;
- }
-}
-
-/**
- * mic_get_family - Determine hardware family to which this MIC belongs.
- *
- * @pdev: The pci device structure
- *
- * returns family.
- */
-static enum mic_hw_family mic_get_family(struct pci_dev *pdev)
-{
- enum mic_hw_family family;
-
- switch (pdev->device) {
- case MIC_X100_PCI_DEVICE_2250:
- case MIC_X100_PCI_DEVICE_2251:
- case MIC_X100_PCI_DEVICE_2252:
- case MIC_X100_PCI_DEVICE_2253:
- case MIC_X100_PCI_DEVICE_2254:
- case MIC_X100_PCI_DEVICE_2255:
- case MIC_X100_PCI_DEVICE_2256:
- case MIC_X100_PCI_DEVICE_2257:
- case MIC_X100_PCI_DEVICE_2258:
- case MIC_X100_PCI_DEVICE_2259:
- case MIC_X100_PCI_DEVICE_225a:
- case MIC_X100_PCI_DEVICE_225b:
- case MIC_X100_PCI_DEVICE_225c:
- case MIC_X100_PCI_DEVICE_225d:
- case MIC_X100_PCI_DEVICE_225e:
- family = MIC_FAMILY_X100;
- break;
- default:
- family = MIC_FAMILY_UNKNOWN;
- break;
- }
- return family;
-}
-
-/**
- * mic_device_init - Allocates and initializes the MIC device structure
- *
- * @mdev: pointer to mic_device instance
- * @pdev: The pci device structure
- *
- * returns none.
- */
-static void
-mic_device_init(struct mic_device *mdev, struct pci_dev *pdev)
-{
- mdev->pdev = pdev;
- mdev->family = mic_get_family(pdev);
- mdev->stepping = pdev->revision;
- mic_ops_init(mdev);
- mutex_init(&mdev->mic_mutex);
- mdev->irq_info.next_avail_src = 0;
-}
-
-/**
- * mic_probe - Device Initialization Routine
- *
- * @pdev: PCI device structure
- * @ent: entry in mic_pci_tbl
- *
- * returns 0 on success, < 0 on failure.
- */
-static int mic_probe(struct pci_dev *pdev,
- const struct pci_device_id *ent)
-{
- int rc;
- struct mic_device *mdev;
-
- mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
- if (!mdev) {
- rc = -ENOMEM;
- goto mdev_alloc_fail;
- }
- mdev->id = ida_simple_get(&g_mic_ida, 0, MIC_MAX_NUM_DEVS, GFP_KERNEL);
- if (mdev->id < 0) {
- rc = mdev->id;
- dev_err(&pdev->dev, "ida_simple_get failed rc %d\n", rc);
- goto ida_fail;
- }
-
- mic_device_init(mdev, pdev);
-
- rc = pci_enable_device(pdev);
- if (rc) {
- dev_err(&pdev->dev, "failed to enable pci device.\n");
- goto ida_remove;
- }
-
- pci_set_master(pdev);
-
- rc = pci_request_regions(pdev, mic_driver_name);
- if (rc) {
- dev_err(&pdev->dev, "failed to get pci regions.\n");
- goto disable_device;
- }
-
- rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
- if (rc) {
- dev_err(&pdev->dev, "Cannot set DMA mask\n");
- goto release_regions;
- }
-
- mdev->mmio.pa = pci_resource_start(pdev, mdev->ops->mmio_bar);
- mdev->mmio.len = pci_resource_len(pdev, mdev->ops->mmio_bar);
- mdev->mmio.va = pci_ioremap_bar(pdev, mdev->ops->mmio_bar);
- if (!mdev->mmio.va) {
- dev_err(&pdev->dev, "Cannot remap MMIO BAR\n");
- rc = -EIO;
- goto release_regions;
- }
-
- mdev->aper.pa = pci_resource_start(pdev, mdev->ops->aper_bar);
- mdev->aper.len = pci_resource_len(pdev, mdev->ops->aper_bar);
- mdev->aper.va = ioremap_wc(mdev->aper.pa, mdev->aper.len);
- if (!mdev->aper.va) {
- dev_err(&pdev->dev, "Cannot remap Aperture BAR\n");
- rc = -EIO;
- goto unmap_mmio;
- }
-
- mdev->intr_ops->intr_init(mdev);
- rc = mic_setup_interrupts(mdev, pdev);
- if (rc) {
- dev_err(&pdev->dev, "mic_setup_interrupts failed %d\n", rc);
- goto unmap_aper;
- }
- rc = mic_smpt_init(mdev);
- if (rc) {
- dev_err(&pdev->dev, "smpt_init failed %d\n", rc);
- goto free_interrupts;
- }
-
- pci_set_drvdata(pdev, mdev);
-
- rc = mic_dp_init(mdev);
- if (rc) {
- dev_err(&pdev->dev, "mic_dp_init failed rc %d\n", rc);
- goto smpt_uninit;
- }
- mic_bootparam_init(mdev);
- mic_create_debug_dir(mdev);
-
- mdev->cosm_dev = cosm_register_device(&mdev->pdev->dev, &cosm_hw_ops);
- if (IS_ERR(mdev->cosm_dev)) {
- rc = PTR_ERR(mdev->cosm_dev);
- dev_err(&pdev->dev, "cosm_add_device failed rc %d\n", rc);
- goto cleanup_debug_dir;
- }
- return 0;
-cleanup_debug_dir:
- mic_delete_debug_dir(mdev);
- mic_dp_uninit(mdev);
-smpt_uninit:
- mic_smpt_uninit(mdev);
-free_interrupts:
- mic_free_interrupts(mdev, pdev);
-unmap_aper:
- iounmap(mdev->aper.va);
-unmap_mmio:
- iounmap(mdev->mmio.va);
-release_regions:
- pci_release_regions(pdev);
-disable_device:
- pci_disable_device(pdev);
-ida_remove:
- ida_simple_remove(&g_mic_ida, mdev->id);
-ida_fail:
- kfree(mdev);
-mdev_alloc_fail:
- dev_err(&pdev->dev, "Probe failed rc %d\n", rc);
- return rc;
-}
-
-/**
- * mic_remove - Device Removal Routine
- * mic_remove is called by the PCI subsystem to alert the driver
- * that it should release a PCI device.
- *
- * @pdev: PCI device structure
- */
-static void mic_remove(struct pci_dev *pdev)
-{
- struct mic_device *mdev;
-
- mdev = pci_get_drvdata(pdev);
- if (!mdev)
- return;
-
- cosm_unregister_device(mdev->cosm_dev);
- mic_delete_debug_dir(mdev);
- mic_dp_uninit(mdev);
- mic_smpt_uninit(mdev);
- mic_free_interrupts(mdev, pdev);
- iounmap(mdev->aper.va);
- iounmap(mdev->mmio.va);
- pci_release_regions(pdev);
- pci_disable_device(pdev);
- ida_simple_remove(&g_mic_ida, mdev->id);
- kfree(mdev);
-}
-
-static struct pci_driver mic_driver = {
- .name = mic_driver_name,
- .id_table = mic_pci_tbl,
- .probe = mic_probe,
- .remove = mic_remove
-};
-
-static int __init mic_init(void)
-{
- int ret;
-
- request_module("mic_x100_dma");
- mic_init_debugfs();
- ida_init(&g_mic_ida);
- ret = pci_register_driver(&mic_driver);
- if (ret) {
- pr_err("pci_register_driver failed ret %d\n", ret);
- goto cleanup_debugfs;
- }
- return 0;
-cleanup_debugfs:
- ida_destroy(&g_mic_ida);
- mic_exit_debugfs();
- return ret;
-}
-
-static void __exit mic_exit(void)
-{
- pci_unregister_driver(&mic_driver);
- ida_destroy(&g_mic_ida);
- mic_exit_debugfs();
-}
-
-module_init(mic_init);
-module_exit(mic_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC X100 Host driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/host/mic_smpt.c b/drivers/misc/mic/host/mic_smpt.c
deleted file mode 100644
index 50d1beb..0000000
--- a/drivers/misc/mic/host/mic_smpt.c
+++ /dev/null
@@ -1,427 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/pci.h>
-
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_smpt.h"
-
-static inline u64 mic_system_page_mask(struct mic_device *mdev)
-{
- return (1ULL << mdev->smpt->info.page_shift) - 1ULL;
-}
-
-static inline u8 mic_sys_addr_to_smpt(struct mic_device *mdev, dma_addr_t pa)
-{
- return (pa - mdev->smpt->info.base) >> mdev->smpt->info.page_shift;
-}
-
-static inline u64 mic_smpt_to_pa(struct mic_device *mdev, u8 index)
-{
- return mdev->smpt->info.base + (index * mdev->smpt->info.page_size);
-}
-
-static inline u64 mic_smpt_offset(struct mic_device *mdev, dma_addr_t pa)
-{
- return pa & mic_system_page_mask(mdev);
-}
-
-static inline u64 mic_smpt_align_low(struct mic_device *mdev, dma_addr_t pa)
-{
- return ALIGN(pa - mic_system_page_mask(mdev),
- mdev->smpt->info.page_size);
-}
-
-static inline u64 mic_smpt_align_high(struct mic_device *mdev, dma_addr_t pa)
-{
- return ALIGN(pa, mdev->smpt->info.page_size);
-}
-
-/* Total Cumulative system memory accessible by MIC across all SMPT entries */
-static inline u64 mic_max_system_memory(struct mic_device *mdev)
-{
- return mdev->smpt->info.num_reg * mdev->smpt->info.page_size;
-}
-
-/* Maximum system memory address accessible by MIC */
-static inline u64 mic_max_system_addr(struct mic_device *mdev)
-{
- return mdev->smpt->info.base + mic_max_system_memory(mdev) - 1ULL;
-}
-
-/* Check if the DMA address is a MIC system memory address */
-static inline bool
-mic_is_system_addr(struct mic_device *mdev, dma_addr_t pa)
-{
- return pa >= mdev->smpt->info.base && pa <= mic_max_system_addr(mdev);
-}
-
-/* Populate an SMPT entry and update the reference counts. */
-static void mic_add_smpt_entry(int spt, s64 *ref, u64 addr,
- int entries, struct mic_device *mdev)
-{
- struct mic_smpt_info *smpt_info = mdev->smpt;
- int i;
-
- for (i = spt; i < spt + entries; i++,
- addr += smpt_info->info.page_size) {
- if (!smpt_info->entry[i].ref_count &&
- (smpt_info->entry[i].dma_addr != addr)) {
- mdev->smpt_ops->set(mdev, addr, i);
- smpt_info->entry[i].dma_addr = addr;
- }
- smpt_info->entry[i].ref_count += ref[i - spt];
- }
-}
-
-/*
- * Find an available MIC address in MIC SMPT address space
- * for a given DMA address and size.
- */
-static dma_addr_t mic_smpt_op(struct mic_device *mdev, u64 dma_addr,
- int entries, s64 *ref, size_t size)
-{
- int spt;
- int ae = 0;
- int i;
- unsigned long flags;
- dma_addr_t mic_addr = 0;
- dma_addr_t addr = dma_addr;
- struct mic_smpt_info *smpt_info = mdev->smpt;
-
- spin_lock_irqsave(&smpt_info->smpt_lock, flags);
-
- /* find existing entries */
- for (i = 0; i < smpt_info->info.num_reg; i++) {
- if (smpt_info->entry[i].dma_addr == addr) {
- ae++;
- addr += smpt_info->info.page_size;
- } else if (ae) /* cannot find contiguous entries */
- goto not_found;
-
- if (ae == entries)
- goto found;
- }
-
- /* find free entry */
- for (ae = 0, i = 0; i < smpt_info->info.num_reg; i++) {
- ae = (smpt_info->entry[i].ref_count == 0) ? ae + 1 : 0;
- if (ae == entries)
- goto found;
- }
-
-not_found:
- spin_unlock_irqrestore(&smpt_info->smpt_lock, flags);
- return mic_addr;
-
-found:
- spt = i - entries + 1;
- mic_addr = mic_smpt_to_pa(mdev, spt);
- mic_add_smpt_entry(spt, ref, dma_addr, entries, mdev);
- smpt_info->map_count++;
- smpt_info->ref_count += (s64)size;
- spin_unlock_irqrestore(&smpt_info->smpt_lock, flags);
- return mic_addr;
-}
-
-/*
- * Returns number of smpt entries needed for dma_addr to dma_addr + size
- * also returns the reference count array for each of those entries
- * and the starting smpt address
- */
-static int mic_get_smpt_ref_count(struct mic_device *mdev, dma_addr_t dma_addr,
- size_t size, s64 *ref, u64 *smpt_start)
-{
- u64 start = dma_addr;
- u64 end = dma_addr + size;
- int i = 0;
-
- while (start < end) {
- ref[i++] = min(mic_smpt_align_high(mdev, start + 1),
- end) - start;
- start = mic_smpt_align_high(mdev, start + 1);
- }
-
- if (smpt_start)
- *smpt_start = mic_smpt_align_low(mdev, dma_addr);
-
- return i;
-}
-
-/*
- * mic_to_dma_addr - Converts a MIC address to a DMA address.
- *
- * @mdev: pointer to mic_device instance.
- * @mic_addr: MIC address.
- *
- * returns a DMA address.
- */
-dma_addr_t mic_to_dma_addr(struct mic_device *mdev, dma_addr_t mic_addr)
-{
- struct mic_smpt_info *smpt_info = mdev->smpt;
- int spt;
- dma_addr_t dma_addr;
-
- if (!mic_is_system_addr(mdev, mic_addr)) {
- dev_err(&mdev->pdev->dev,
- "mic_addr is invalid. mic_addr = 0x%llx\n", mic_addr);
- return -EINVAL;
- }
- spt = mic_sys_addr_to_smpt(mdev, mic_addr);
- dma_addr = smpt_info->entry[spt].dma_addr +
- mic_smpt_offset(mdev, mic_addr);
- return dma_addr;
-}
-
-/**
- * mic_map - Maps a DMA address to a MIC physical address.
- *
- * @mdev: pointer to mic_device instance.
- * @dma_addr: DMA address.
- * @size: Size of the region to be mapped.
- *
- * This API converts the DMA address provided to a DMA address understood
- * by MIC. Caller should check for errors by calling mic_map_error(..).
- *
- * returns DMA address as required by MIC.
- */
-dma_addr_t mic_map(struct mic_device *mdev, dma_addr_t dma_addr, size_t size)
-{
- dma_addr_t mic_addr = 0;
- int num_entries;
- s64 *ref;
- u64 smpt_start;
-
- if (!size || size > mic_max_system_memory(mdev))
- return mic_addr;
-
- ref = kmalloc_array(mdev->smpt->info.num_reg, sizeof(s64), GFP_ATOMIC);
- if (!ref)
- return mic_addr;
-
- num_entries = mic_get_smpt_ref_count(mdev, dma_addr, size,
- ref, &smpt_start);
-
- /* Set the smpt table appropriately and get 16G aligned mic address */
- mic_addr = mic_smpt_op(mdev, smpt_start, num_entries, ref, size);
-
- kfree(ref);
-
- /*
- * If mic_addr is zero then its an error case
- * since mic_addr can never be zero.
- * else generate mic_addr by adding the 16G offset in dma_addr
- */
- if (!mic_addr && MIC_FAMILY_X100 == mdev->family) {
- dev_err(&mdev->pdev->dev,
- "mic_map failed dma_addr 0x%llx size 0x%lx\n",
- dma_addr, size);
- return mic_addr;
- } else {
- return mic_addr + mic_smpt_offset(mdev, dma_addr);
- }
-}
-
-/**
- * mic_unmap - Unmaps a MIC physical address.
- *
- * @mdev: pointer to mic_device instance.
- * @mic_addr: MIC physical address.
- * @size: Size of the region to be unmapped.
- *
- * This API unmaps the mappings created by mic_map(..).
- *
- * returns None.
- */
-void mic_unmap(struct mic_device *mdev, dma_addr_t mic_addr, size_t size)
-{
- struct mic_smpt_info *smpt_info = mdev->smpt;
- s64 *ref;
- int num_smpt;
- int spt;
- int i;
- unsigned long flags;
-
- if (!size)
- return;
-
- if (!mic_is_system_addr(mdev, mic_addr)) {
- dev_err(&mdev->pdev->dev,
- "invalid address: 0x%llx\n", mic_addr);
- return;
- }
-
- spt = mic_sys_addr_to_smpt(mdev, mic_addr);
- ref = kmalloc_array(mdev->smpt->info.num_reg, sizeof(s64), GFP_ATOMIC);
- if (!ref)
- return;
-
- /* Get number of smpt entries to be mapped, ref count array */
- num_smpt = mic_get_smpt_ref_count(mdev, mic_addr, size, ref, NULL);
-
- spin_lock_irqsave(&smpt_info->smpt_lock, flags);
- smpt_info->unmap_count++;
- smpt_info->ref_count -= (s64)size;
-
- for (i = spt; i < spt + num_smpt; i++) {
- smpt_info->entry[i].ref_count -= ref[i - spt];
- if (smpt_info->entry[i].ref_count < 0)
- dev_warn(&mdev->pdev->dev,
- "ref count for entry %d is negative\n", i);
- }
- spin_unlock_irqrestore(&smpt_info->smpt_lock, flags);
- kfree(ref);
-}
-
-/**
- * mic_map_single - Maps a virtual address to a MIC physical address.
- *
- * @mdev: pointer to mic_device instance.
- * @va: Kernel direct mapped virtual address.
- * @size: Size of the region to be mapped.
- *
- * This API calls pci_map_single(..) for the direct mapped virtual address
- * and then converts the DMA address provided to a DMA address understood
- * by MIC. Caller should check for errors by calling mic_map_error(..).
- *
- * returns DMA address as required by MIC.
- */
-dma_addr_t mic_map_single(struct mic_device *mdev, void *va, size_t size)
-{
- dma_addr_t mic_addr = 0;
- struct pci_dev *pdev = mdev->pdev;
- dma_addr_t dma_addr =
- pci_map_single(pdev, va, size, PCI_DMA_BIDIRECTIONAL);
-
- if (!pci_dma_mapping_error(pdev, dma_addr)) {
- mic_addr = mic_map(mdev, dma_addr, size);
- if (!mic_addr) {
- dev_err(&mdev->pdev->dev,
- "mic_map failed dma_addr 0x%llx size 0x%lx\n",
- dma_addr, size);
- pci_unmap_single(pdev, dma_addr,
- size, PCI_DMA_BIDIRECTIONAL);
- }
- }
- return mic_addr;
-}
-
-/**
- * mic_unmap_single - Unmaps a MIC physical address.
- *
- * @mdev: pointer to mic_device instance.
- * @mic_addr: MIC physical address.
- * @size: Size of the region to be unmapped.
- *
- * This API unmaps the mappings created by mic_map_single(..).
- *
- * returns None.
- */
-void
-mic_unmap_single(struct mic_device *mdev, dma_addr_t mic_addr, size_t size)
-{
- struct pci_dev *pdev = mdev->pdev;
- dma_addr_t dma_addr = mic_to_dma_addr(mdev, mic_addr);
- mic_unmap(mdev, mic_addr, size);
- pci_unmap_single(pdev, dma_addr, size, PCI_DMA_BIDIRECTIONAL);
-}
-
-/**
- * mic_smpt_init - Initialize MIC System Memory Page Tables.
- *
- * @mdev: pointer to mic_device instance.
- *
- * returns 0 for success and -errno for error.
- */
-int mic_smpt_init(struct mic_device *mdev)
-{
- int i, err = 0;
- dma_addr_t dma_addr;
- struct mic_smpt_info *smpt_info;
-
- mdev->smpt = kmalloc(sizeof(*mdev->smpt), GFP_KERNEL);
- if (!mdev->smpt)
- return -ENOMEM;
-
- smpt_info = mdev->smpt;
- mdev->smpt_ops->init(mdev);
- smpt_info->entry = kmalloc_array(smpt_info->info.num_reg,
- sizeof(*smpt_info->entry), GFP_KERNEL);
- if (!smpt_info->entry) {
- err = -ENOMEM;
- goto free_smpt;
- }
- spin_lock_init(&smpt_info->smpt_lock);
- for (i = 0; i < smpt_info->info.num_reg; i++) {
- dma_addr = i * smpt_info->info.page_size;
- smpt_info->entry[i].dma_addr = dma_addr;
- smpt_info->entry[i].ref_count = 0;
- mdev->smpt_ops->set(mdev, dma_addr, i);
- }
- smpt_info->ref_count = 0;
- smpt_info->map_count = 0;
- smpt_info->unmap_count = 0;
- return 0;
-free_smpt:
- kfree(smpt_info);
- return err;
-}
-
-/**
- * mic_smpt_uninit - UnInitialize MIC System Memory Page Tables.
- *
- * @mdev: pointer to mic_device instance.
- *
- * returns None.
- */
-void mic_smpt_uninit(struct mic_device *mdev)
-{
- struct mic_smpt_info *smpt_info = mdev->smpt;
- int i;
-
- dev_dbg(&mdev->pdev->dev,
- "nodeid %d SMPT ref count %lld map %lld unmap %lld\n",
- mdev->id, smpt_info->ref_count,
- smpt_info->map_count, smpt_info->unmap_count);
-
- for (i = 0; i < smpt_info->info.num_reg; i++) {
- dev_dbg(&mdev->pdev->dev,
- "SMPT entry[%d] dma_addr = 0x%llx ref_count = %lld\n",
- i, smpt_info->entry[i].dma_addr,
- smpt_info->entry[i].ref_count);
- if (smpt_info->entry[i].ref_count)
- dev_warn(&mdev->pdev->dev,
- "ref count for entry %d is not zero\n", i);
- }
- kfree(smpt_info->entry);
- kfree(smpt_info);
-}
-
-/**
- * mic_smpt_restore - Restore MIC System Memory Page Tables.
- *
- * @mdev: pointer to mic_device instance.
- *
- * Restore the SMPT registers to values previously stored in the
- * SW data structures. Some MIC steppings lose register state
- * across resets and this API should be called for performing
- * a restore operation if required.
- *
- * returns None.
- */
-void mic_smpt_restore(struct mic_device *mdev)
-{
- int i;
- dma_addr_t dma_addr;
-
- for (i = 0; i < mdev->smpt->info.num_reg; i++) {
- dma_addr = mdev->smpt->entry[i].dma_addr;
- mdev->smpt_ops->set(mdev, dma_addr, i);
- }
-}
diff --git a/drivers/misc/mic/host/mic_smpt.h b/drivers/misc/mic/host/mic_smpt.h
deleted file mode 100644
index 3b1ec14..0000000
--- a/drivers/misc/mic/host/mic_smpt.h
+++ /dev/null
@@ -1,87 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#ifndef MIC_SMPT_H
-#define MIC_SMPT_H
-/**
- * struct mic_smpt_ops - MIC HW specific SMPT operations.
- * @init: Initialize hardware specific SMPT information in mic_smpt_hw_info.
- * @set: Set the value for a particular SMPT entry.
- */
-struct mic_smpt_ops {
- void (*init)(struct mic_device *mdev);
- void (*set)(struct mic_device *mdev, dma_addr_t dma_addr, u8 index);
-};
-
-/**
- * struct mic_smpt - MIC SMPT entry information.
- * @dma_addr: Base DMA address for this SMPT entry.
- * @ref_count: Number of active mappings for this SMPT entry in bytes.
- */
-struct mic_smpt {
- dma_addr_t dma_addr;
- s64 ref_count;
-};
-
-/**
- * struct mic_smpt_hw_info - MIC SMPT hardware specific information.
- * @num_reg: Number of SMPT registers.
- * @page_shift: System memory page shift.
- * @page_size: System memory page size.
- * @base: System address base.
- */
-struct mic_smpt_hw_info {
- u8 num_reg;
- u8 page_shift;
- u64 page_size;
- u64 base;
-};
-
-/**
- * struct mic_smpt_info - MIC SMPT information.
- * @entry: Array of SMPT entries.
- * @smpt_lock: Spin lock protecting access to SMPT data structures.
- * @info: Hardware specific SMPT information.
- * @ref_count: Number of active SMPT mappings (for debug).
- * @map_count: Number of SMPT mappings created (for debug).
- * @unmap_count: Number of SMPT mappings destroyed (for debug).
- */
-struct mic_smpt_info {
- struct mic_smpt *entry;
- spinlock_t smpt_lock;
- struct mic_smpt_hw_info info;
- s64 ref_count;
- s64 map_count;
- s64 unmap_count;
-};
-
-dma_addr_t mic_map_single(struct mic_device *mdev, void *va, size_t size);
-void mic_unmap_single(struct mic_device *mdev,
- dma_addr_t mic_addr, size_t size);
-dma_addr_t mic_map(struct mic_device *mdev,
- dma_addr_t dma_addr, size_t size);
-void mic_unmap(struct mic_device *mdev, dma_addr_t mic_addr, size_t size);
-dma_addr_t mic_to_dma_addr(struct mic_device *mdev, dma_addr_t mic_addr);
-
-/**
- * mic_map_error - Check a MIC address for errors.
- *
- * @mdev: pointer to mic_device instance.
- *
- * returns Whether there was an error during mic_map..(..) APIs.
- */
-static inline bool mic_map_error(dma_addr_t mic_addr)
-{
- return !mic_addr;
-}
-
-int mic_smpt_init(struct mic_device *mdev);
-void mic_smpt_uninit(struct mic_device *mdev);
-void mic_smpt_restore(struct mic_device *mdev);
-
-#endif
diff --git a/drivers/misc/mic/host/mic_x100.c b/drivers/misc/mic/host/mic_x100.c
deleted file mode 100644
index f5536c1..0000000
--- a/drivers/misc/mic/host/mic_x100.c
+++ /dev/null
@@ -1,585 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/fs.h>
-#include <linux/pci.h>
-#include <linux/sched.h>
-#include <linux/firmware.h>
-#include <linux/delay.h>
-
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_x100.h"
-#include "mic_smpt.h"
-
-static const u16 mic_x100_intr_init[] = {
- MIC_X100_DOORBELL_IDX_START,
- MIC_X100_DMA_IDX_START,
- MIC_X100_ERR_IDX_START,
- MIC_X100_NUM_DOORBELL,
- MIC_X100_NUM_DMA,
- MIC_X100_NUM_ERR,
-};
-
-/**
- * mic_x100_write_spad - write to the scratchpad register
- * @mdev: pointer to mic_device instance
- * @idx: index to the scratchpad register, 0 based
- * @val: the data value to put into the register
- *
- * This function allows writing of a 32bit value to the indexed scratchpad
- * register.
- *
- * RETURNS: none.
- */
-static void
-mic_x100_write_spad(struct mic_device *mdev, unsigned int idx, u32 val)
-{
- dev_dbg(&mdev->pdev->dev, "Writing 0x%x to scratch pad index %d\n",
- val, idx);
- mic_mmio_write(&mdev->mmio, val,
- MIC_X100_SBOX_BASE_ADDRESS +
- MIC_X100_SBOX_SPAD0 + idx * 4);
-}
-
-/**
- * mic_x100_read_spad - read from the scratchpad register
- * @mdev: pointer to mic_device instance
- * @idx: index to scratchpad register, 0 based
- *
- * This function allows reading of the 32bit scratchpad register.
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static u32
-mic_x100_read_spad(struct mic_device *mdev, unsigned int idx)
-{
- u32 val = mic_mmio_read(&mdev->mmio,
- MIC_X100_SBOX_BASE_ADDRESS +
- MIC_X100_SBOX_SPAD0 + idx * 4);
-
- dev_dbg(&mdev->pdev->dev,
- "Reading 0x%x from scratch pad index %d\n", val, idx);
- return val;
-}
-
-/**
- * mic_x100_enable_interrupts - Enable interrupts.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_enable_interrupts(struct mic_device *mdev)
-{
- u32 reg;
- struct mic_mw *mw = &mdev->mmio;
- u32 sice0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SICE0;
- u32 siac0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SIAC0;
-
- reg = mic_mmio_read(mw, sice0);
- reg |= MIC_X100_SBOX_DBR_BITS(0xf) | MIC_X100_SBOX_DMA_BITS(0xff);
- mic_mmio_write(mw, reg, sice0);
-
- /*
- * Enable auto-clear when enabling interrupts. Applicable only for
- * MSI-x. Legacy and MSI mode cannot have auto-clear enabled.
- */
- if (mdev->irq_info.num_vectors > 1) {
- reg = mic_mmio_read(mw, siac0);
- reg |= MIC_X100_SBOX_DBR_BITS(0xf) |
- MIC_X100_SBOX_DMA_BITS(0xff);
- mic_mmio_write(mw, reg, siac0);
- }
-}
-
-/**
- * mic_x100_disable_interrupts - Disable interrupts.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_disable_interrupts(struct mic_device *mdev)
-{
- u32 reg;
- struct mic_mw *mw = &mdev->mmio;
- u32 sice0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SICE0;
- u32 siac0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SIAC0;
- u32 sicc0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SICC0;
-
- reg = mic_mmio_read(mw, sice0);
- mic_mmio_write(mw, reg, sicc0);
-
- if (mdev->irq_info.num_vectors > 1) {
- reg = mic_mmio_read(mw, siac0);
- reg &= ~(MIC_X100_SBOX_DBR_BITS(0xf) |
- MIC_X100_SBOX_DMA_BITS(0xff));
- mic_mmio_write(mw, reg, siac0);
- }
-}
-
-/**
- * mic_x100_send_sbox_intr - Send an MIC_X100_SBOX interrupt to MIC.
- * @mdev: pointer to mic_device instance
- * @doorbell: doorbell number
- */
-static void mic_x100_send_sbox_intr(struct mic_device *mdev,
- int doorbell)
-{
- struct mic_mw *mw = &mdev->mmio;
- u64 apic_icr_offset = MIC_X100_SBOX_APICICR0 + doorbell * 8;
- u32 apicicr_low = mic_mmio_read(mw, MIC_X100_SBOX_BASE_ADDRESS +
- apic_icr_offset);
-
- /* for MIC we need to make sure we "hit" the send_icr bit (13) */
- apicicr_low = (apicicr_low | (1 << 13));
-
- /* Ensure that the interrupt is ordered w.r.t. previous stores. */
- wmb();
- mic_mmio_write(mw, apicicr_low,
- MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset);
-}
-
-/**
- * mic_x100_send_rdmasr_intr - Send an RDMASR interrupt to MIC.
- * @mdev: pointer to mic_device instance
- * @doorbell: doorbell number
- */
-static void mic_x100_send_rdmasr_intr(struct mic_device *mdev,
- int doorbell)
-{
- int rdmasr_offset = MIC_X100_SBOX_RDMASR0 + (doorbell << 2);
- /* Ensure that the interrupt is ordered w.r.t. previous stores. */
- wmb();
- mic_mmio_write(&mdev->mmio, 0,
- MIC_X100_SBOX_BASE_ADDRESS + rdmasr_offset);
-}
-
-/**
- * __mic_x100_send_intr - Send interrupt to MIC.
- * @mdev: pointer to mic_device instance
- * @doorbell: doorbell number.
- */
-static void mic_x100_send_intr(struct mic_device *mdev, int doorbell)
-{
- int rdmasr_db;
- if (doorbell < MIC_X100_NUM_SBOX_IRQ) {
- mic_x100_send_sbox_intr(mdev, doorbell);
- } else {
- rdmasr_db = doorbell - MIC_X100_NUM_SBOX_IRQ;
- mic_x100_send_rdmasr_intr(mdev, rdmasr_db);
- }
-}
-
-/**
- * mic_x100_ack_interrupt - Read the interrupt sources register and
- * clear it. This function will be called in the MSI/INTx case.
- * @mdev: Pointer to mic_device instance.
- *
- * Returns: bitmask of interrupt sources triggered.
- */
-static u32 mic_x100_ack_interrupt(struct mic_device *mdev)
-{
- u32 sicr0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SICR0;
- u32 reg = mic_mmio_read(&mdev->mmio, sicr0);
- mic_mmio_write(&mdev->mmio, reg, sicr0);
- return reg;
-}
-
-/**
- * mic_x100_intr_workarounds - These hardware specific workarounds are
- * to be invoked everytime an interrupt is handled.
- * @mdev: Pointer to mic_device instance.
- *
- * Returns: none
- */
-static void mic_x100_intr_workarounds(struct mic_device *mdev)
-{
- struct mic_mw *mw = &mdev->mmio;
-
- /* Clear pending bit array. */
- if (MIC_A0_STEP == mdev->stepping)
- mic_mmio_write(mw, 1, MIC_X100_SBOX_BASE_ADDRESS +
- MIC_X100_SBOX_MSIXPBACR);
-
- if (mdev->stepping >= MIC_B0_STEP)
- mdev->intr_ops->enable_interrupts(mdev);
-}
-
-/**
- * mic_x100_hw_intr_init - Initialize h/w specific interrupt
- * information.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_hw_intr_init(struct mic_device *mdev)
-{
- mdev->intr_info = (struct mic_intr_info *)mic_x100_intr_init;
-}
-
-/**
- * mic_x100_read_msi_to_src_map - read from the MSI mapping registers
- * @mdev: pointer to mic_device instance
- * @idx: index to the mapping register, 0 based
- *
- * This function allows reading of the 32bit MSI mapping register.
- *
- * RETURNS: The value in the register.
- */
-static u32
-mic_x100_read_msi_to_src_map(struct mic_device *mdev, int idx)
-{
- return mic_mmio_read(&mdev->mmio,
- MIC_X100_SBOX_BASE_ADDRESS +
- MIC_X100_SBOX_MXAR0 + idx * 4);
-}
-
-/**
- * mic_x100_program_msi_to_src_map - program the MSI mapping registers
- * @mdev: pointer to mic_device instance
- * @idx: index to the mapping register, 0 based
- * @offset: The bit offset in the register that needs to be updated.
- * @set: boolean specifying if the bit in the specified offset needs
- * to be set or cleared.
- *
- * RETURNS: None.
- */
-static void
-mic_x100_program_msi_to_src_map(struct mic_device *mdev,
- int idx, int offset, bool set)
-{
- unsigned long reg;
- struct mic_mw *mw = &mdev->mmio;
- u32 mxar = MIC_X100_SBOX_BASE_ADDRESS +
- MIC_X100_SBOX_MXAR0 + idx * 4;
-
- reg = mic_mmio_read(mw, mxar);
- if (set)
- __set_bit(offset, ®);
- else
- __clear_bit(offset, ®);
- mic_mmio_write(mw, reg, mxar);
-}
-
-/*
- * mic_x100_reset_fw_ready - Reset Firmware ready status field.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_reset_fw_ready(struct mic_device *mdev)
-{
- mdev->ops->write_spad(mdev, MIC_X100_DOWNLOAD_INFO, 0);
-}
-
-/*
- * mic_x100_is_fw_ready - Check if firmware is ready.
- * @mdev: pointer to mic_device instance
- */
-static bool mic_x100_is_fw_ready(struct mic_device *mdev)
-{
- u32 scratch2 = mdev->ops->read_spad(mdev, MIC_X100_DOWNLOAD_INFO);
- return MIC_X100_SPAD2_DOWNLOAD_STATUS(scratch2) ? true : false;
-}
-
-/**
- * mic_x100_get_apic_id - Get bootstrap APIC ID.
- * @mdev: pointer to mic_device instance
- */
-static u32 mic_x100_get_apic_id(struct mic_device *mdev)
-{
- u32 scratch2 = 0;
-
- scratch2 = mdev->ops->read_spad(mdev, MIC_X100_DOWNLOAD_INFO);
- return MIC_X100_SPAD2_APIC_ID(scratch2);
-}
-
-/**
- * mic_x100_send_firmware_intr - Send an interrupt to the firmware on MIC.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_send_firmware_intr(struct mic_device *mdev)
-{
- u32 apicicr_low;
- u64 apic_icr_offset = MIC_X100_SBOX_APICICR7;
- int vector = MIC_X100_BSP_INTERRUPT_VECTOR;
- struct mic_mw *mw = &mdev->mmio;
-
- /*
- * For MIC we need to make sure we "hit"
- * the send_icr bit (13).
- */
- apicicr_low = (vector | (1 << 13));
-
- mic_mmio_write(mw, mic_x100_get_apic_id(mdev),
- MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset + 4);
-
- /* Ensure that the interrupt is ordered w.r.t. previous stores. */
- wmb();
- mic_mmio_write(mw, apicicr_low,
- MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset);
-}
-
-/**
- * mic_x100_hw_reset - Reset the MIC device.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_hw_reset(struct mic_device *mdev)
-{
- u32 reset_reg;
- u32 rgcr = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_RGCR;
- struct mic_mw *mw = &mdev->mmio;
-
- /* Ensure that the reset is ordered w.r.t. previous loads and stores */
- mb();
- /* Trigger reset */
- reset_reg = mic_mmio_read(mw, rgcr);
- reset_reg |= 0x1;
- mic_mmio_write(mw, reset_reg, rgcr);
- /*
- * It seems we really want to delay at least 1 second
- * after touching reset to prevent a lot of problems.
- */
- msleep(1000);
-}
-
-/**
- * mic_x100_load_command_line - Load command line to MIC.
- * @mdev: pointer to mic_device instance
- * @fw: the firmware image
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int
-mic_x100_load_command_line(struct mic_device *mdev, const struct firmware *fw)
-{
- u32 len = 0;
- u32 boot_mem;
- char *buf;
- void __iomem *cmd_line_va = mdev->aper.va + mdev->bootaddr + fw->size;
-#define CMDLINE_SIZE 2048
-
- boot_mem = mdev->aper.len >> 20;
- buf = kzalloc(CMDLINE_SIZE, GFP_KERNEL);
- if (!buf)
- return -ENOMEM;
-
- len += scnprintf(buf, CMDLINE_SIZE - len,
- " mem=%dM", boot_mem);
- if (mdev->cosm_dev->cmdline)
- scnprintf(buf + len, CMDLINE_SIZE - len, " %s",
- mdev->cosm_dev->cmdline);
- memcpy_toio(cmd_line_va, buf, strlen(buf) + 1);
- kfree(buf);
- return 0;
-}
-
-/**
- * mic_x100_load_ramdisk - Load ramdisk to MIC.
- * @mdev: pointer to mic_device instance
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int
-mic_x100_load_ramdisk(struct mic_device *mdev)
-{
- const struct firmware *fw;
- int rc;
- struct boot_params __iomem *bp = mdev->aper.va + mdev->bootaddr;
-
- rc = request_firmware(&fw, mdev->cosm_dev->ramdisk, &mdev->pdev->dev);
- if (rc < 0) {
- dev_err(&mdev->pdev->dev,
- "ramdisk request_firmware failed: %d %s\n",
- rc, mdev->cosm_dev->ramdisk);
- goto error;
- }
- /*
- * Typically the bootaddr for card OS is 64M
- * so copy over the ramdisk @ 128M.
- */
- memcpy_toio(mdev->aper.va + (mdev->bootaddr << 1), fw->data, fw->size);
- iowrite32(mdev->bootaddr << 1, &bp->hdr.ramdisk_image);
- iowrite32(fw->size, &bp->hdr.ramdisk_size);
- release_firmware(fw);
-error:
- return rc;
-}
-
-/**
- * mic_x100_get_boot_addr - Get MIC boot address.
- * @mdev: pointer to mic_device instance
- *
- * This function is called during firmware load to determine
- * the address at which the OS should be downloaded in card
- * memory i.e. GDDR.
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int
-mic_x100_get_boot_addr(struct mic_device *mdev)
-{
- u32 scratch2, boot_addr;
- int rc = 0;
-
- scratch2 = mdev->ops->read_spad(mdev, MIC_X100_DOWNLOAD_INFO);
- boot_addr = MIC_X100_SPAD2_DOWNLOAD_ADDR(scratch2);
- dev_dbg(&mdev->pdev->dev, "%s %d boot_addr 0x%x\n",
- __func__, __LINE__, boot_addr);
- if (boot_addr > (1 << 31)) {
- dev_err(&mdev->pdev->dev,
- "incorrect bootaddr 0x%x\n",
- boot_addr);
- rc = -EINVAL;
- goto error;
- }
- mdev->bootaddr = boot_addr;
-error:
- return rc;
-}
-
-/**
- * mic_x100_load_firmware - Load firmware to MIC.
- * @mdev: pointer to mic_device instance
- * @buf: buffer containing boot string including firmware/ramdisk path.
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int
-mic_x100_load_firmware(struct mic_device *mdev, const char *buf)
-{
- int rc;
- const struct firmware *fw;
-
- rc = mic_x100_get_boot_addr(mdev);
- if (rc)
- return rc;
- /* load OS */
- rc = request_firmware(&fw, mdev->cosm_dev->firmware, &mdev->pdev->dev);
- if (rc < 0) {
- dev_err(&mdev->pdev->dev,
- "ramdisk request_firmware failed: %d %s\n",
- rc, mdev->cosm_dev->firmware);
- return rc;
- }
- if (mdev->bootaddr > mdev->aper.len - fw->size) {
- rc = -EINVAL;
- dev_err(&mdev->pdev->dev, "%s %d rc %d bootaddr 0x%x\n",
- __func__, __LINE__, rc, mdev->bootaddr);
- goto error;
- }
- memcpy_toio(mdev->aper.va + mdev->bootaddr, fw->data, fw->size);
- mdev->ops->write_spad(mdev, MIC_X100_FW_SIZE, fw->size);
- if (!strcmp(mdev->cosm_dev->bootmode, "flash")) {
- rc = -EINVAL;
- dev_err(&mdev->pdev->dev, "%s %d rc %d\n",
- __func__, __LINE__, rc);
- goto error;
- }
- /* load command line */
- rc = mic_x100_load_command_line(mdev, fw);
- if (rc) {
- dev_err(&mdev->pdev->dev, "%s %d rc %d\n",
- __func__, __LINE__, rc);
- goto error;
- }
- release_firmware(fw);
- /* load ramdisk */
- if (mdev->cosm_dev->ramdisk)
- rc = mic_x100_load_ramdisk(mdev);
-
- return rc;
-
-error:
- release_firmware(fw);
- return rc;
-}
-
-/**
- * mic_x100_get_postcode - Get postcode status from firmware.
- * @mdev: pointer to mic_device instance
- *
- * RETURNS: postcode.
- */
-static u32 mic_x100_get_postcode(struct mic_device *mdev)
-{
- return mic_mmio_read(&mdev->mmio, MIC_X100_POSTCODE);
-}
-
-/**
- * mic_x100_smpt_set - Update an SMPT entry with a DMA address.
- * @mdev: pointer to mic_device instance
- * @dma_addr: DMA address to use
- * @index: entry to write to
- *
- * RETURNS: none.
- */
-static void
-mic_x100_smpt_set(struct mic_device *mdev, dma_addr_t dma_addr, u8 index)
-{
-#define SNOOP_ON (0 << 0)
-#define SNOOP_OFF (1 << 0)
-/*
- * Sbox Smpt Reg Bits:
- * Bits 31:2 Host address
- * Bits 1 RSVD
- * Bits 0 No snoop
- */
-#define BUILD_SMPT(NO_SNOOP, HOST_ADDR) \
- (u32)(((HOST_ADDR) << 2) | ((NO_SNOOP) & 0x01))
-
- uint32_t smpt_reg_val = BUILD_SMPT(SNOOP_ON,
- dma_addr >> mdev->smpt->info.page_shift);
- mic_mmio_write(&mdev->mmio, smpt_reg_val,
- MIC_X100_SBOX_BASE_ADDRESS +
- MIC_X100_SBOX_SMPT00 + (4 * index));
-}
-
-/**
- * mic_x100_smpt_hw_init - Initialize SMPT X100 specific fields.
- * @mdev: pointer to mic_device instance
- *
- * RETURNS: none.
- */
-static void mic_x100_smpt_hw_init(struct mic_device *mdev)
-{
- struct mic_smpt_hw_info *info = &mdev->smpt->info;
-
- info->num_reg = 32;
- info->page_shift = 34;
- info->page_size = (1ULL << info->page_shift);
- info->base = 0x8000000000ULL;
-}
-
-struct mic_smpt_ops mic_x100_smpt_ops = {
- .init = mic_x100_smpt_hw_init,
- .set = mic_x100_smpt_set,
-};
-
-static bool mic_x100_dma_filter(struct dma_chan *chan, void *param)
-{
- if (chan->device->dev->parent == (struct device *)param)
- return true;
- return false;
-}
-
-struct mic_hw_ops mic_x100_ops = {
- .aper_bar = MIC_X100_APER_BAR,
- .mmio_bar = MIC_X100_MMIO_BAR,
- .read_spad = mic_x100_read_spad,
- .write_spad = mic_x100_write_spad,
- .send_intr = mic_x100_send_intr,
- .ack_interrupt = mic_x100_ack_interrupt,
- .intr_workarounds = mic_x100_intr_workarounds,
- .reset = mic_x100_hw_reset,
- .reset_fw_ready = mic_x100_reset_fw_ready,
- .is_fw_ready = mic_x100_is_fw_ready,
- .send_firmware_intr = mic_x100_send_firmware_intr,
- .load_mic_fw = mic_x100_load_firmware,
- .get_postcode = mic_x100_get_postcode,
- .dma_filter = mic_x100_dma_filter,
-};
-
-struct mic_hw_intr_ops mic_x100_intr_ops = {
- .intr_init = mic_x100_hw_intr_init,
- .enable_interrupts = mic_x100_enable_interrupts,
- .disable_interrupts = mic_x100_disable_interrupts,
- .program_msi_to_src_map = mic_x100_program_msi_to_src_map,
- .read_msi_to_src_map = mic_x100_read_msi_to_src_map,
-};
diff --git a/drivers/misc/mic/host/mic_x100.h b/drivers/misc/mic/host/mic_x100.h
deleted file mode 100644
index aebcaed..0000000
--- a/drivers/misc/mic/host/mic_x100.h
+++ /dev/null
@@ -1,77 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#ifndef _MIC_X100_HW_H_
-#define _MIC_X100_HW_H_
-
-#define MIC_X100_PCI_DEVICE_2250 0x2250
-#define MIC_X100_PCI_DEVICE_2251 0x2251
-#define MIC_X100_PCI_DEVICE_2252 0x2252
-#define MIC_X100_PCI_DEVICE_2253 0x2253
-#define MIC_X100_PCI_DEVICE_2254 0x2254
-#define MIC_X100_PCI_DEVICE_2255 0x2255
-#define MIC_X100_PCI_DEVICE_2256 0x2256
-#define MIC_X100_PCI_DEVICE_2257 0x2257
-#define MIC_X100_PCI_DEVICE_2258 0x2258
-#define MIC_X100_PCI_DEVICE_2259 0x2259
-#define MIC_X100_PCI_DEVICE_225a 0x225a
-#define MIC_X100_PCI_DEVICE_225b 0x225b
-#define MIC_X100_PCI_DEVICE_225c 0x225c
-#define MIC_X100_PCI_DEVICE_225d 0x225d
-#define MIC_X100_PCI_DEVICE_225e 0x225e
-
-#define MIC_X100_APER_BAR 0
-#define MIC_X100_MMIO_BAR 4
-
-#define MIC_X100_SBOX_BASE_ADDRESS 0x00010000
-#define MIC_X100_SBOX_SPAD0 0x0000AB20
-#define MIC_X100_SBOX_SICR0_DBR(x) ((x) & 0xf)
-#define MIC_X100_SBOX_SICR0_DMA(x) (((x) >> 8) & 0xff)
-#define MIC_X100_SBOX_SICE0_DBR(x) ((x) & 0xf)
-#define MIC_X100_SBOX_DBR_BITS(x) ((x) & 0xf)
-#define MIC_X100_SBOX_SICE0_DMA(x) (((x) >> 8) & 0xff)
-#define MIC_X100_SBOX_DMA_BITS(x) (((x) & 0xff) << 8)
-
-#define MIC_X100_SBOX_APICICR0 0x0000A9D0
-#define MIC_X100_SBOX_SICR0 0x00009004
-#define MIC_X100_SBOX_SICE0 0x0000900C
-#define MIC_X100_SBOX_SICC0 0x00009010
-#define MIC_X100_SBOX_SIAC0 0x00009014
-#define MIC_X100_SBOX_MSIXPBACR 0x00009084
-#define MIC_X100_SBOX_MXAR0 0x00009044
-#define MIC_X100_SBOX_SMPT00 0x00003100
-#define MIC_X100_SBOX_RDMASR0 0x0000B180
-
-#define MIC_X100_DOORBELL_IDX_START 0
-#define MIC_X100_NUM_DOORBELL 4
-#define MIC_X100_DMA_IDX_START 8
-#define MIC_X100_NUM_DMA 8
-#define MIC_X100_ERR_IDX_START 30
-#define MIC_X100_NUM_ERR 1
-
-#define MIC_X100_NUM_SBOX_IRQ 8
-#define MIC_X100_NUM_RDMASR_IRQ 8
-#define MIC_X100_RDMASR_IRQ_BASE 17
-#define MIC_X100_SPAD2_DOWNLOAD_STATUS(x) ((x) & 0x1)
-#define MIC_X100_SPAD2_APIC_ID(x) (((x) >> 1) & 0x1ff)
-#define MIC_X100_SPAD2_DOWNLOAD_ADDR(x) ((x) & 0xfffff000)
-#define MIC_X100_SBOX_APICICR7 0x0000AA08
-#define MIC_X100_SBOX_RGCR 0x00004010
-#define MIC_X100_SBOX_SDBIC0 0x0000CC90
-#define MIC_X100_DOWNLOAD_INFO 2
-#define MIC_X100_FW_SIZE 5
-#define MIC_X100_POSTCODE 0x242c
-
-/* Host->Card(bootstrap) Interrupt Vector */
-#define MIC_X100_BSP_INTERRUPT_VECTOR 229
-
-extern struct mic_hw_ops mic_x100_ops;
-extern struct mic_smpt_ops mic_x100_smpt_ops;
-extern struct mic_hw_intr_ops mic_x100_intr_ops;
-
-#endif
diff --git a/drivers/misc/mic/scif/Makefile b/drivers/misc/mic/scif/Makefile
deleted file mode 100644
index ff37255..0000000
--- a/drivers/misc/mic/scif/Makefile
+++ /dev/null
@@ -1,21 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile - SCIF driver.
-# Copyright(c) 2014, Intel Corporation.
-#
-obj-$(CONFIG_SCIF) += scif.o
-scif-objs := scif_main.o
-scif-objs += scif_peer_bus.o
-scif-objs += scif_ports.o
-scif-objs += scif_debugfs.o
-scif-objs += scif_fd.o
-scif-objs += scif_api.o
-scif-objs += scif_epd.o
-scif-objs += scif_rb.o
-scif-objs += scif_nodeqp.o
-scif-objs += scif_nm.o
-scif-objs += scif_dma.o
-scif-objs += scif_fence.o
-scif-objs += scif_mmap.o
-scif-objs += scif_rma.o
-scif-objs += scif_rma_list.o
diff --git a/drivers/misc/mic/scif/scif_api.c b/drivers/misc/mic/scif/scif_api.c
deleted file mode 100644
index 304d6c8..0000000
--- a/drivers/misc/mic/scif/scif_api.c
+++ /dev/null
@@ -1,1485 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/scif.h>
-#include "scif_main.h"
-#include "scif_map.h"
-
-static const char * const scif_ep_states[] = {
- "Unbound",
- "Bound",
- "Listening",
- "Connected",
- "Connecting",
- "Mapping",
- "Closing",
- "Close Listening",
- "Disconnected",
- "Zombie"};
-
-enum conn_async_state {
- ASYNC_CONN_IDLE = 1, /* ep setup for async connect */
- ASYNC_CONN_INPROGRESS, /* async connect in progress */
- ASYNC_CONN_FLUSH_WORK /* async work flush in progress */
-};
-
-/*
- * File operations for anonymous inode file associated with a SCIF endpoint,
- * used in kernel mode SCIF poll. Kernel mode SCIF poll calls portions of the
- * poll API in the kernel and these take in a struct file *. Since a struct
- * file is not available to kernel mode SCIF, it uses an anonymous file for
- * this purpose.
- */
-const struct file_operations scif_anon_fops = {
- .owner = THIS_MODULE,
-};
-
-scif_epd_t scif_open(void)
-{
- struct scif_endpt *ep;
- int err;
-
- might_sleep();
- ep = kzalloc(sizeof(*ep), GFP_KERNEL);
- if (!ep)
- goto err_ep_alloc;
-
- ep->qp_info.qp = kzalloc(sizeof(*ep->qp_info.qp), GFP_KERNEL);
- if (!ep->qp_info.qp)
- goto err_qp_alloc;
-
- err = scif_anon_inode_getfile(ep);
- if (err)
- goto err_anon_inode;
-
- spin_lock_init(&ep->lock);
- mutex_init(&ep->sendlock);
- mutex_init(&ep->recvlock);
-
- scif_rma_ep_init(ep);
- ep->state = SCIFEP_UNBOUND;
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI open: ep %p success\n", ep);
- return ep;
-
-err_anon_inode:
- kfree(ep->qp_info.qp);
-err_qp_alloc:
- kfree(ep);
-err_ep_alloc:
- return NULL;
-}
-EXPORT_SYMBOL_GPL(scif_open);
-
-/*
- * scif_disconnect_ep - Disconnects the endpoint if found
- * @epd: The end point returned from scif_open()
- */
-static struct scif_endpt *scif_disconnect_ep(struct scif_endpt *ep)
-{
- struct scifmsg msg;
- struct scif_endpt *fep = NULL;
- struct scif_endpt *tmpep;
- struct list_head *pos, *tmpq;
- int err;
-
- /*
- * Wake up any threads blocked in send()/recv() before closing
- * out the connection. Grabbing and releasing the send/recv lock
- * will ensure that any blocked senders/receivers have exited for
- * Ring 0 endpoints. It is a Ring 0 bug to call send/recv after
- * close. Ring 3 endpoints are not affected since close will not
- * be called while there are IOCTLs executing.
- */
- wake_up_interruptible(&ep->sendwq);
- wake_up_interruptible(&ep->recvwq);
- mutex_lock(&ep->sendlock);
- mutex_unlock(&ep->sendlock);
- mutex_lock(&ep->recvlock);
- mutex_unlock(&ep->recvlock);
-
- /* Remove from the connected list */
- mutex_lock(&scif_info.connlock);
- list_for_each_safe(pos, tmpq, &scif_info.connected) {
- tmpep = list_entry(pos, struct scif_endpt, list);
- if (tmpep == ep) {
- list_del(pos);
- fep = tmpep;
- spin_lock(&ep->lock);
- break;
- }
- }
-
- if (!fep) {
- /*
- * The other side has completed the disconnect before
- * the end point can be removed from the list. Therefore
- * the ep lock is not locked, traverse the disconnected
- * list to find the endpoint and release the conn lock.
- */
- list_for_each_safe(pos, tmpq, &scif_info.disconnected) {
- tmpep = list_entry(pos, struct scif_endpt, list);
- if (tmpep == ep) {
- list_del(pos);
- break;
- }
- }
- mutex_unlock(&scif_info.connlock);
- return NULL;
- }
-
- init_completion(&ep->discon);
- msg.uop = SCIF_DISCNCT;
- msg.src = ep->port;
- msg.dst = ep->peer;
- msg.payload[0] = (u64)ep;
- msg.payload[1] = ep->remote_ep;
-
- err = scif_nodeqp_send(ep->remote_dev, &msg);
- spin_unlock(&ep->lock);
- mutex_unlock(&scif_info.connlock);
-
- if (!err)
- /* Wait for the remote node to respond with SCIF_DISCNT_ACK */
- wait_for_completion_timeout(&ep->discon,
- SCIF_NODE_ALIVE_TIMEOUT);
- return ep;
-}
-
-int scif_close(scif_epd_t epd)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct scif_endpt *tmpep;
- struct list_head *pos, *tmpq;
- enum scif_epd_state oldstate;
- bool flush_conn;
-
- dev_dbg(scif_info.mdev.this_device, "SCIFAPI close: ep %p %s\n",
- ep, scif_ep_states[ep->state]);
- might_sleep();
- spin_lock(&ep->lock);
- flush_conn = (ep->conn_async_state == ASYNC_CONN_INPROGRESS);
- spin_unlock(&ep->lock);
-
- if (flush_conn)
- flush_work(&scif_info.conn_work);
-
- spin_lock(&ep->lock);
- oldstate = ep->state;
-
- ep->state = SCIFEP_CLOSING;
-
- switch (oldstate) {
- case SCIFEP_ZOMBIE:
- dev_err(scif_info.mdev.this_device,
- "SCIFAPI close: zombie state unexpected\n");
- fallthrough;
- case SCIFEP_DISCONNECTED:
- spin_unlock(&ep->lock);
- scif_unregister_all_windows(epd);
- /* Remove from the disconnected list */
- mutex_lock(&scif_info.connlock);
- list_for_each_safe(pos, tmpq, &scif_info.disconnected) {
- tmpep = list_entry(pos, struct scif_endpt, list);
- if (tmpep == ep) {
- list_del(pos);
- break;
- }
- }
- mutex_unlock(&scif_info.connlock);
- break;
- case SCIFEP_UNBOUND:
- case SCIFEP_BOUND:
- case SCIFEP_CONNECTING:
- spin_unlock(&ep->lock);
- break;
- case SCIFEP_MAPPING:
- case SCIFEP_CONNECTED:
- case SCIFEP_CLOSING:
- {
- spin_unlock(&ep->lock);
- scif_unregister_all_windows(epd);
- scif_disconnect_ep(ep);
- break;
- }
- case SCIFEP_LISTENING:
- case SCIFEP_CLLISTEN:
- {
- struct scif_conreq *conreq;
- struct scifmsg msg;
- struct scif_endpt *aep;
-
- spin_unlock(&ep->lock);
- mutex_lock(&scif_info.eplock);
-
- /* remove from listen list */
- list_for_each_safe(pos, tmpq, &scif_info.listen) {
- tmpep = list_entry(pos, struct scif_endpt, list);
- if (tmpep == ep)
- list_del(pos);
- }
- /* Remove any dangling accepts */
- while (ep->acceptcnt) {
- aep = list_first_entry(&ep->li_accept,
- struct scif_endpt, liacceptlist);
- list_del(&aep->liacceptlist);
- scif_put_port(aep->port.port);
- list_for_each_safe(pos, tmpq, &scif_info.uaccept) {
- tmpep = list_entry(pos, struct scif_endpt,
- miacceptlist);
- if (tmpep == aep) {
- list_del(pos);
- break;
- }
- }
- mutex_unlock(&scif_info.eplock);
- mutex_lock(&scif_info.connlock);
- list_for_each_safe(pos, tmpq, &scif_info.connected) {
- tmpep = list_entry(pos,
- struct scif_endpt, list);
- if (tmpep == aep) {
- list_del(pos);
- break;
- }
- }
- list_for_each_safe(pos, tmpq, &scif_info.disconnected) {
- tmpep = list_entry(pos,
- struct scif_endpt, list);
- if (tmpep == aep) {
- list_del(pos);
- break;
- }
- }
- mutex_unlock(&scif_info.connlock);
- scif_teardown_ep(aep);
- mutex_lock(&scif_info.eplock);
- scif_add_epd_to_zombie_list(aep, SCIF_EPLOCK_HELD);
- ep->acceptcnt--;
- }
-
- spin_lock(&ep->lock);
- mutex_unlock(&scif_info.eplock);
-
- /* Remove and reject any pending connection requests. */
- while (ep->conreqcnt) {
- conreq = list_first_entry(&ep->conlist,
- struct scif_conreq, list);
- list_del(&conreq->list);
-
- msg.uop = SCIF_CNCT_REJ;
- msg.dst.node = conreq->msg.src.node;
- msg.dst.port = conreq->msg.src.port;
- msg.payload[0] = conreq->msg.payload[0];
- msg.payload[1] = conreq->msg.payload[1];
- /*
- * No Error Handling on purpose for scif_nodeqp_send().
- * If the remote node is lost we still want free the
- * connection requests on the self node.
- */
- scif_nodeqp_send(&scif_dev[conreq->msg.src.node],
- &msg);
- ep->conreqcnt--;
- kfree(conreq);
- }
-
- spin_unlock(&ep->lock);
- /* If a kSCIF accept is waiting wake it up */
- wake_up_interruptible(&ep->conwq);
- break;
- }
- }
- scif_put_port(ep->port.port);
- scif_anon_inode_fput(ep);
- scif_teardown_ep(ep);
- scif_add_epd_to_zombie_list(ep, !SCIF_EPLOCK_HELD);
- return 0;
-}
-EXPORT_SYMBOL_GPL(scif_close);
-
-/**
- * scif_flush() - Wakes up any blocking accepts. The endpoint will no longer
- * accept new connections.
- * @epd: The end point returned from scif_open()
- */
-int __scif_flush(scif_epd_t epd)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
-
- switch (ep->state) {
- case SCIFEP_LISTENING:
- {
- ep->state = SCIFEP_CLLISTEN;
-
- /* If an accept is waiting wake it up */
- wake_up_interruptible(&ep->conwq);
- break;
- }
- default:
- break;
- }
- return 0;
-}
-
-int scif_bind(scif_epd_t epd, u16 pn)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int ret = 0;
- int tmp;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI bind: ep %p %s requested port number %d\n",
- ep, scif_ep_states[ep->state], pn);
- if (pn) {
- /*
- * Similar to IETF RFC 1700, SCIF ports below
- * SCIF_ADMIN_PORT_END can only be bound by system (or root)
- * processes or by processes executed by privileged users.
- */
- if (pn < SCIF_ADMIN_PORT_END && !capable(CAP_SYS_ADMIN)) {
- ret = -EACCES;
- goto scif_bind_admin_exit;
- }
- }
-
- spin_lock(&ep->lock);
- if (ep->state == SCIFEP_BOUND) {
- ret = -EINVAL;
- goto scif_bind_exit;
- } else if (ep->state != SCIFEP_UNBOUND) {
- ret = -EISCONN;
- goto scif_bind_exit;
- }
-
- if (pn) {
- tmp = scif_rsrv_port(pn);
- if (tmp != pn) {
- ret = -EINVAL;
- goto scif_bind_exit;
- }
- } else {
- ret = scif_get_new_port();
- if (ret < 0)
- goto scif_bind_exit;
- pn = ret;
- }
-
- ep->state = SCIFEP_BOUND;
- ep->port.node = scif_info.nodeid;
- ep->port.port = pn;
- ep->conn_async_state = ASYNC_CONN_IDLE;
- ret = pn;
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI bind: bound to port number %d\n", pn);
-scif_bind_exit:
- spin_unlock(&ep->lock);
-scif_bind_admin_exit:
- return ret;
-}
-EXPORT_SYMBOL_GPL(scif_bind);
-
-int scif_listen(scif_epd_t epd, int backlog)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI listen: ep %p %s\n", ep, scif_ep_states[ep->state]);
- spin_lock(&ep->lock);
- switch (ep->state) {
- case SCIFEP_ZOMBIE:
- case SCIFEP_CLOSING:
- case SCIFEP_CLLISTEN:
- case SCIFEP_UNBOUND:
- case SCIFEP_DISCONNECTED:
- spin_unlock(&ep->lock);
- return -EINVAL;
- case SCIFEP_LISTENING:
- case SCIFEP_CONNECTED:
- case SCIFEP_CONNECTING:
- case SCIFEP_MAPPING:
- spin_unlock(&ep->lock);
- return -EISCONN;
- case SCIFEP_BOUND:
- break;
- }
-
- ep->state = SCIFEP_LISTENING;
- ep->backlog = backlog;
-
- ep->conreqcnt = 0;
- ep->acceptcnt = 0;
- INIT_LIST_HEAD(&ep->conlist);
- init_waitqueue_head(&ep->conwq);
- INIT_LIST_HEAD(&ep->li_accept);
- spin_unlock(&ep->lock);
-
- /*
- * Listen status is complete so delete the qp information not needed
- * on a listen before placing on the list of listening ep's
- */
- scif_teardown_ep(ep);
- ep->qp_info.qp = NULL;
-
- mutex_lock(&scif_info.eplock);
- list_add_tail(&ep->list, &scif_info.listen);
- mutex_unlock(&scif_info.eplock);
- return 0;
-}
-EXPORT_SYMBOL_GPL(scif_listen);
-
-/*
- ************************************************************************
- * SCIF connection flow:
- *
- * 1) A SCIF listening endpoint can call scif_accept(..) to wait for SCIF
- * connections via a SCIF_CNCT_REQ message
- * 2) A SCIF endpoint can initiate a SCIF connection by calling
- * scif_connect(..) which calls scif_setup_qp_connect(..) which
- * allocates the local qp for the endpoint ring buffer and then sends
- * a SCIF_CNCT_REQ to the remote node and waits for a SCIF_CNCT_GNT or
- * a SCIF_CNCT_REJ message
- * 3) The peer node handles a SCIF_CNCT_REQ via scif_cnctreq_resp(..) which
- * wakes up any threads blocked in step 1 or sends a SCIF_CNCT_REJ
- * message otherwise
- * 4) A thread blocked waiting for incoming connections allocates its local
- * endpoint QP and ring buffer following which it sends a SCIF_CNCT_GNT
- * and waits for a SCIF_CNCT_GNT(N)ACK. If the allocation fails then
- * the node sends a SCIF_CNCT_REJ message
- * 5) Upon receipt of a SCIF_CNCT_GNT or a SCIF_CNCT_REJ message the
- * connecting endpoint is woken up as part of handling
- * scif_cnctgnt_resp(..) following which it maps the remote endpoints'
- * QP, updates its outbound QP and sends a SCIF_CNCT_GNTACK message on
- * success or a SCIF_CNCT_GNTNACK message on failure and completes
- * the scif_connect(..) API
- * 6) Upon receipt of a SCIF_CNCT_GNT(N)ACK the accepting endpoint blocked
- * in step 4 is woken up and completes the scif_accept(..) API
- * 7) The SCIF connection is now established between the two SCIF endpoints.
- */
-static int scif_conn_func(struct scif_endpt *ep)
-{
- int err = 0;
- struct scifmsg msg;
- struct device *spdev;
-
- err = scif_reserve_dma_chan(ep);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- ep->state = SCIFEP_BOUND;
- goto connect_error_simple;
- }
- /* Initiate the first part of the endpoint QP setup */
- err = scif_setup_qp_connect(ep->qp_info.qp, &ep->qp_info.qp_offset,
- SCIF_ENDPT_QP_SIZE, ep->remote_dev);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s err %d qp_offset 0x%llx\n",
- __func__, err, ep->qp_info.qp_offset);
- ep->state = SCIFEP_BOUND;
- goto connect_error_simple;
- }
-
- spdev = scif_get_peer_dev(ep->remote_dev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- goto cleanup_qp;
- }
- /* Format connect message and send it */
- msg.src = ep->port;
- msg.dst = ep->conn_port;
- msg.uop = SCIF_CNCT_REQ;
- msg.payload[0] = (u64)ep;
- msg.payload[1] = ep->qp_info.qp_offset;
- err = _scif_nodeqp_send(ep->remote_dev, &msg);
- if (err)
- goto connect_error_dec;
- scif_put_peer_dev(spdev);
- /*
- * Wait for the remote node to respond with SCIF_CNCT_GNT or
- * SCIF_CNCT_REJ message.
- */
- err = wait_event_timeout(ep->conwq, ep->state != SCIFEP_CONNECTING,
- SCIF_NODE_ALIVE_TIMEOUT);
- if (!err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d timeout\n", __func__, __LINE__);
- ep->state = SCIFEP_BOUND;
- }
- spdev = scif_get_peer_dev(ep->remote_dev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- goto cleanup_qp;
- }
- if (ep->state == SCIFEP_MAPPING) {
- err = scif_setup_qp_connect_response(ep->remote_dev,
- ep->qp_info.qp,
- ep->qp_info.gnt_pld);
- /*
- * If the resource to map the queue are not available then
- * we need to tell the other side to terminate the accept
- */
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- msg.uop = SCIF_CNCT_GNTNACK;
- msg.payload[0] = ep->remote_ep;
- _scif_nodeqp_send(ep->remote_dev, &msg);
- ep->state = SCIFEP_BOUND;
- goto connect_error_dec;
- }
-
- msg.uop = SCIF_CNCT_GNTACK;
- msg.payload[0] = ep->remote_ep;
- err = _scif_nodeqp_send(ep->remote_dev, &msg);
- if (err) {
- ep->state = SCIFEP_BOUND;
- goto connect_error_dec;
- }
- ep->state = SCIFEP_CONNECTED;
- mutex_lock(&scif_info.connlock);
- list_add_tail(&ep->list, &scif_info.connected);
- mutex_unlock(&scif_info.connlock);
- dev_dbg(&ep->remote_dev->sdev->dev,
- "SCIFAPI connect: ep %p connected\n", ep);
- } else if (ep->state == SCIFEP_BOUND) {
- dev_dbg(&ep->remote_dev->sdev->dev,
- "SCIFAPI connect: ep %p connection refused\n", ep);
- err = -ECONNREFUSED;
- goto connect_error_dec;
- }
- scif_put_peer_dev(spdev);
- return err;
-connect_error_dec:
- scif_put_peer_dev(spdev);
-cleanup_qp:
- scif_cleanup_ep_qp(ep);
-connect_error_simple:
- return err;
-}
-
-/*
- * scif_conn_handler:
- *
- * Workqueue handler for servicing non-blocking SCIF connect
- *
- */
-void scif_conn_handler(struct work_struct *work)
-{
- struct scif_endpt *ep;
-
- do {
- ep = NULL;
- spin_lock(&scif_info.nb_connect_lock);
- if (!list_empty(&scif_info.nb_connect_list)) {
- ep = list_first_entry(&scif_info.nb_connect_list,
- struct scif_endpt, conn_list);
- list_del(&ep->conn_list);
- }
- spin_unlock(&scif_info.nb_connect_lock);
- if (ep) {
- ep->conn_err = scif_conn_func(ep);
- wake_up_interruptible(&ep->conn_pend_wq);
- }
- } while (ep);
-}
-
-int __scif_connect(scif_epd_t epd, struct scif_port_id *dst, bool non_block)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int err = 0;
- struct scif_dev *remote_dev;
- struct device *spdev;
-
- dev_dbg(scif_info.mdev.this_device, "SCIFAPI connect: ep %p %s\n", ep,
- scif_ep_states[ep->state]);
-
- if (!scif_dev || dst->node > scif_info.maxid)
- return -ENODEV;
-
- might_sleep();
-
- remote_dev = &scif_dev[dst->node];
- spdev = scif_get_peer_dev(remote_dev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- return err;
- }
-
- spin_lock(&ep->lock);
- switch (ep->state) {
- case SCIFEP_ZOMBIE:
- case SCIFEP_CLOSING:
- err = -EINVAL;
- break;
- case SCIFEP_DISCONNECTED:
- if (ep->conn_async_state == ASYNC_CONN_INPROGRESS)
- ep->conn_async_state = ASYNC_CONN_FLUSH_WORK;
- else
- err = -EINVAL;
- break;
- case SCIFEP_LISTENING:
- case SCIFEP_CLLISTEN:
- err = -EOPNOTSUPP;
- break;
- case SCIFEP_CONNECTING:
- case SCIFEP_MAPPING:
- if (ep->conn_async_state == ASYNC_CONN_INPROGRESS)
- err = -EINPROGRESS;
- else
- err = -EISCONN;
- break;
- case SCIFEP_CONNECTED:
- if (ep->conn_async_state == ASYNC_CONN_INPROGRESS)
- ep->conn_async_state = ASYNC_CONN_FLUSH_WORK;
- else
- err = -EISCONN;
- break;
- case SCIFEP_UNBOUND:
- err = scif_get_new_port();
- if (err < 0)
- break;
- ep->port.port = err;
- ep->port.node = scif_info.nodeid;
- ep->conn_async_state = ASYNC_CONN_IDLE;
- fallthrough;
- case SCIFEP_BOUND:
- /*
- * If a non-blocking connect has been already initiated
- * (conn_async_state is either ASYNC_CONN_INPROGRESS or
- * ASYNC_CONN_FLUSH_WORK), the end point could end up in
- * SCIF_BOUND due an error in the connection process
- * (e.g., connection refused) If conn_async_state is
- * ASYNC_CONN_INPROGRESS - transition to ASYNC_CONN_FLUSH_WORK
- * so that the error status can be collected. If the state is
- * already ASYNC_CONN_FLUSH_WORK - then set the error to
- * EINPROGRESS since some other thread is waiting to collect
- * error status.
- */
- if (ep->conn_async_state == ASYNC_CONN_INPROGRESS) {
- ep->conn_async_state = ASYNC_CONN_FLUSH_WORK;
- } else if (ep->conn_async_state == ASYNC_CONN_FLUSH_WORK) {
- err = -EINPROGRESS;
- } else {
- ep->conn_port = *dst;
- init_waitqueue_head(&ep->sendwq);
- init_waitqueue_head(&ep->recvwq);
- init_waitqueue_head(&ep->conwq);
- ep->conn_async_state = 0;
-
- if (unlikely(non_block))
- ep->conn_async_state = ASYNC_CONN_INPROGRESS;
- }
- break;
- }
-
- if (err || ep->conn_async_state == ASYNC_CONN_FLUSH_WORK)
- goto connect_simple_unlock1;
-
- ep->state = SCIFEP_CONNECTING;
- ep->remote_dev = &scif_dev[dst->node];
- ep->qp_info.qp->magic = SCIFEP_MAGIC;
- if (ep->conn_async_state == ASYNC_CONN_INPROGRESS) {
- init_waitqueue_head(&ep->conn_pend_wq);
- spin_lock(&scif_info.nb_connect_lock);
- list_add_tail(&ep->conn_list, &scif_info.nb_connect_list);
- spin_unlock(&scif_info.nb_connect_lock);
- err = -EINPROGRESS;
- schedule_work(&scif_info.conn_work);
- }
-connect_simple_unlock1:
- spin_unlock(&ep->lock);
- scif_put_peer_dev(spdev);
- if (err) {
- return err;
- } else if (ep->conn_async_state == ASYNC_CONN_FLUSH_WORK) {
- flush_work(&scif_info.conn_work);
- err = ep->conn_err;
- spin_lock(&ep->lock);
- ep->conn_async_state = ASYNC_CONN_IDLE;
- spin_unlock(&ep->lock);
- } else {
- err = scif_conn_func(ep);
- }
- return err;
-}
-
-int scif_connect(scif_epd_t epd, struct scif_port_id *dst)
-{
- return __scif_connect(epd, dst, false);
-}
-EXPORT_SYMBOL_GPL(scif_connect);
-
-/*
- * scif_accept() - Accept a connection request from the remote node
- *
- * The function accepts a connection request from the remote node. Successful
- * complete is indicate by a new end point being created and passed back
- * to the caller for future reference.
- *
- * Upon successful complete a zero will be returned and the peer information
- * will be filled in.
- *
- * If the end point is not in the listening state -EINVAL will be returned.
- *
- * If during the connection sequence resource allocation fails the -ENOMEM
- * will be returned.
- *
- * If the function is called with the ASYNC flag set and no connection requests
- * are pending it will return -EAGAIN.
- *
- * If the remote side is not sending any connection requests the caller may
- * terminate this function with a signal. If so a -EINTR will be returned.
- */
-int scif_accept(scif_epd_t epd, struct scif_port_id *peer,
- scif_epd_t *newepd, int flags)
-{
- struct scif_endpt *lep = (struct scif_endpt *)epd;
- struct scif_endpt *cep;
- struct scif_conreq *conreq;
- struct scifmsg msg;
- int err;
- struct device *spdev;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI accept: ep %p %s\n", lep, scif_ep_states[lep->state]);
-
- if (flags & ~SCIF_ACCEPT_SYNC)
- return -EINVAL;
-
- if (!peer || !newepd)
- return -EINVAL;
-
- might_sleep();
- spin_lock(&lep->lock);
- if (lep->state != SCIFEP_LISTENING) {
- spin_unlock(&lep->lock);
- return -EINVAL;
- }
-
- if (!lep->conreqcnt && !(flags & SCIF_ACCEPT_SYNC)) {
- /* No connection request present and we do not want to wait */
- spin_unlock(&lep->lock);
- return -EAGAIN;
- }
-
- lep->files = current->files;
-retry_connection:
- spin_unlock(&lep->lock);
- /* Wait for the remote node to send us a SCIF_CNCT_REQ */
- err = wait_event_interruptible(lep->conwq,
- (lep->conreqcnt ||
- (lep->state != SCIFEP_LISTENING)));
- if (err)
- return err;
-
- if (lep->state != SCIFEP_LISTENING)
- return -EINTR;
-
- spin_lock(&lep->lock);
-
- if (!lep->conreqcnt)
- goto retry_connection;
-
- /* Get the first connect request off the list */
- conreq = list_first_entry(&lep->conlist, struct scif_conreq, list);
- list_del(&conreq->list);
- lep->conreqcnt--;
- spin_unlock(&lep->lock);
-
- /* Fill in the peer information */
- peer->node = conreq->msg.src.node;
- peer->port = conreq->msg.src.port;
-
- cep = kzalloc(sizeof(*cep), GFP_KERNEL);
- if (!cep) {
- err = -ENOMEM;
- goto scif_accept_error_epalloc;
- }
- spin_lock_init(&cep->lock);
- mutex_init(&cep->sendlock);
- mutex_init(&cep->recvlock);
- cep->state = SCIFEP_CONNECTING;
- cep->remote_dev = &scif_dev[peer->node];
- cep->remote_ep = conreq->msg.payload[0];
-
- scif_rma_ep_init(cep);
-
- err = scif_reserve_dma_chan(cep);
- if (err) {
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto scif_accept_error_qpalloc;
- }
-
- cep->qp_info.qp = kzalloc(sizeof(*cep->qp_info.qp), GFP_KERNEL);
- if (!cep->qp_info.qp) {
- err = -ENOMEM;
- goto scif_accept_error_qpalloc;
- }
-
- err = scif_anon_inode_getfile(cep);
- if (err)
- goto scif_accept_error_anon_inode;
-
- cep->qp_info.qp->magic = SCIFEP_MAGIC;
- spdev = scif_get_peer_dev(cep->remote_dev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- goto scif_accept_error_map;
- }
- err = scif_setup_qp_accept(cep->qp_info.qp, &cep->qp_info.qp_offset,
- conreq->msg.payload[1], SCIF_ENDPT_QP_SIZE,
- cep->remote_dev);
- if (err) {
- dev_dbg(&cep->remote_dev->sdev->dev,
- "SCIFAPI accept: ep %p new %p scif_setup_qp_accept %d qp_offset 0x%llx\n",
- lep, cep, err, cep->qp_info.qp_offset);
- scif_put_peer_dev(spdev);
- goto scif_accept_error_map;
- }
-
- cep->port.node = lep->port.node;
- cep->port.port = lep->port.port;
- cep->peer.node = peer->node;
- cep->peer.port = peer->port;
- init_waitqueue_head(&cep->sendwq);
- init_waitqueue_head(&cep->recvwq);
- init_waitqueue_head(&cep->conwq);
-
- msg.uop = SCIF_CNCT_GNT;
- msg.src = cep->port;
- msg.payload[0] = cep->remote_ep;
- msg.payload[1] = cep->qp_info.qp_offset;
- msg.payload[2] = (u64)cep;
-
- err = _scif_nodeqp_send(cep->remote_dev, &msg);
- scif_put_peer_dev(spdev);
- if (err)
- goto scif_accept_error_map;
-retry:
- /* Wait for the remote node to respond with SCIF_CNCT_GNT(N)ACK */
- err = wait_event_timeout(cep->conwq, cep->state != SCIFEP_CONNECTING,
- SCIF_NODE_ACCEPT_TIMEOUT);
- if (!err && scifdev_alive(cep))
- goto retry;
- err = !err ? -ENODEV : 0;
- if (err)
- goto scif_accept_error_map;
- kfree(conreq);
-
- spin_lock(&cep->lock);
-
- if (cep->state == SCIFEP_CLOSING) {
- /*
- * Remote failed to allocate resources and NAKed the grant.
- * There is at this point nothing referencing the new end point.
- */
- spin_unlock(&cep->lock);
- scif_teardown_ep(cep);
- kfree(cep);
-
- /* If call with sync flag then go back and wait. */
- if (flags & SCIF_ACCEPT_SYNC) {
- spin_lock(&lep->lock);
- goto retry_connection;
- }
- return -EAGAIN;
- }
-
- scif_get_port(cep->port.port);
- *newepd = (scif_epd_t)cep;
- spin_unlock(&cep->lock);
- return 0;
-scif_accept_error_map:
- scif_anon_inode_fput(cep);
-scif_accept_error_anon_inode:
- scif_teardown_ep(cep);
-scif_accept_error_qpalloc:
- kfree(cep);
-scif_accept_error_epalloc:
- msg.uop = SCIF_CNCT_REJ;
- msg.dst.node = conreq->msg.src.node;
- msg.dst.port = conreq->msg.src.port;
- msg.payload[0] = conreq->msg.payload[0];
- msg.payload[1] = conreq->msg.payload[1];
- scif_nodeqp_send(&scif_dev[conreq->msg.src.node], &msg);
- kfree(conreq);
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_accept);
-
-/*
- * scif_msg_param_check:
- * @epd: The end point returned from scif_open()
- * @len: Length to receive
- * @flags: blocking or non blocking
- *
- * Validate parameters for messaging APIs scif_send(..)/scif_recv(..).
- */
-static inline int scif_msg_param_check(scif_epd_t epd, int len, int flags)
-{
- int ret = -EINVAL;
-
- if (len < 0)
- goto err_ret;
- if (flags && (!(flags & SCIF_RECV_BLOCK)))
- goto err_ret;
- ret = 0;
-err_ret:
- return ret;
-}
-
-static int _scif_send(scif_epd_t epd, void *msg, int len, int flags)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct scifmsg notif_msg;
- int curr_xfer_len = 0, sent_len = 0, write_count;
- int ret = 0;
- struct scif_qp *qp = ep->qp_info.qp;
-
- if (flags & SCIF_SEND_BLOCK)
- might_sleep();
-
- spin_lock(&ep->lock);
- while (sent_len != len && SCIFEP_CONNECTED == ep->state) {
- write_count = scif_rb_space(&qp->outbound_q);
- if (write_count) {
- /* Best effort to send as much data as possible */
- curr_xfer_len = min(len - sent_len, write_count);
- ret = scif_rb_write(&qp->outbound_q, msg,
- curr_xfer_len);
- if (ret < 0)
- break;
- /* Success. Update write pointer */
- scif_rb_commit(&qp->outbound_q);
- /*
- * Send a notification to the peer about the
- * produced data message.
- */
- notif_msg.src = ep->port;
- notif_msg.uop = SCIF_CLIENT_SENT;
- notif_msg.payload[0] = ep->remote_ep;
- ret = _scif_nodeqp_send(ep->remote_dev, ¬if_msg);
- if (ret)
- break;
- sent_len += curr_xfer_len;
- msg = msg + curr_xfer_len;
- continue;
- }
- curr_xfer_len = min(len - sent_len, SCIF_ENDPT_QP_SIZE - 1);
- /* Not enough RB space. return for the Non Blocking case */
- if (!(flags & SCIF_SEND_BLOCK))
- break;
-
- spin_unlock(&ep->lock);
- /* Wait for a SCIF_CLIENT_RCVD message in the Blocking case */
- ret =
- wait_event_interruptible(ep->sendwq,
- (SCIFEP_CONNECTED != ep->state) ||
- (scif_rb_space(&qp->outbound_q) >=
- curr_xfer_len));
- spin_lock(&ep->lock);
- if (ret)
- break;
- }
- if (sent_len)
- ret = sent_len;
- else if (!ret && SCIFEP_CONNECTED != ep->state)
- ret = SCIFEP_DISCONNECTED == ep->state ?
- -ECONNRESET : -ENOTCONN;
- spin_unlock(&ep->lock);
- return ret;
-}
-
-static int _scif_recv(scif_epd_t epd, void *msg, int len, int flags)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct scifmsg notif_msg;
- int curr_recv_len = 0, remaining_len = len, read_count;
- int ret = 0;
- struct scif_qp *qp = ep->qp_info.qp;
-
- if (flags & SCIF_RECV_BLOCK)
- might_sleep();
- spin_lock(&ep->lock);
- while (remaining_len && (SCIFEP_CONNECTED == ep->state ||
- SCIFEP_DISCONNECTED == ep->state)) {
- read_count = scif_rb_count(&qp->inbound_q, remaining_len);
- if (read_count) {
- /*
- * Best effort to recv as much data as there
- * are bytes to read in the RB particularly
- * important for the Non Blocking case.
- */
- curr_recv_len = min(remaining_len, read_count);
- scif_rb_get_next(&qp->inbound_q, msg, curr_recv_len);
- if (ep->state == SCIFEP_CONNECTED) {
- /*
- * Update the read pointer only if the endpoint
- * is still connected else the read pointer
- * might no longer exist since the peer has
- * freed resources!
- */
- scif_rb_update_read_ptr(&qp->inbound_q);
- /*
- * Send a notification to the peer about the
- * consumed data message only if the EP is in
- * SCIFEP_CONNECTED state.
- */
- notif_msg.src = ep->port;
- notif_msg.uop = SCIF_CLIENT_RCVD;
- notif_msg.payload[0] = ep->remote_ep;
- ret = _scif_nodeqp_send(ep->remote_dev,
- ¬if_msg);
- if (ret)
- break;
- }
- remaining_len -= curr_recv_len;
- msg = msg + curr_recv_len;
- continue;
- }
- /*
- * Bail out now if the EP is in SCIFEP_DISCONNECTED state else
- * we will keep looping forever.
- */
- if (ep->state == SCIFEP_DISCONNECTED)
- break;
- /*
- * Return in the Non Blocking case if there is no data
- * to read in this iteration.
- */
- if (!(flags & SCIF_RECV_BLOCK))
- break;
- curr_recv_len = min(remaining_len, SCIF_ENDPT_QP_SIZE - 1);
- spin_unlock(&ep->lock);
- /*
- * Wait for a SCIF_CLIENT_SEND message in the blocking case
- * or until other side disconnects.
- */
- ret =
- wait_event_interruptible(ep->recvwq,
- SCIFEP_CONNECTED != ep->state ||
- scif_rb_count(&qp->inbound_q,
- curr_recv_len)
- >= curr_recv_len);
- spin_lock(&ep->lock);
- if (ret)
- break;
- }
- if (len - remaining_len)
- ret = len - remaining_len;
- else if (!ret && ep->state != SCIFEP_CONNECTED)
- ret = ep->state == SCIFEP_DISCONNECTED ?
- -ECONNRESET : -ENOTCONN;
- spin_unlock(&ep->lock);
- return ret;
-}
-
-/**
- * scif_user_send() - Send data to connection queue
- * @epd: The end point returned from scif_open()
- * @msg: Address to place data
- * @len: Length to receive
- * @flags: blocking or non blocking
- *
- * This function is called from the driver IOCTL entry point
- * only and is a wrapper for _scif_send().
- */
-int scif_user_send(scif_epd_t epd, void __user *msg, int len, int flags)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int err = 0;
- int sent_len = 0;
- char *tmp;
- int loop_len;
- int chunk_len = min(len, (1 << (MAX_ORDER + PAGE_SHIFT - 1)));
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI send (U): ep %p %s\n", ep, scif_ep_states[ep->state]);
- if (!len)
- return 0;
-
- err = scif_msg_param_check(epd, len, flags);
- if (err)
- goto send_err;
-
- tmp = kmalloc(chunk_len, GFP_KERNEL);
- if (!tmp) {
- err = -ENOMEM;
- goto send_err;
- }
- /*
- * Grabbing the lock before breaking up the transfer in
- * multiple chunks is required to ensure that messages do
- * not get fragmented and reordered.
- */
- mutex_lock(&ep->sendlock);
- while (sent_len != len) {
- loop_len = len - sent_len;
- loop_len = min(chunk_len, loop_len);
- if (copy_from_user(tmp, msg, loop_len)) {
- err = -EFAULT;
- goto send_free_err;
- }
- err = _scif_send(epd, tmp, loop_len, flags);
- if (err < 0)
- goto send_free_err;
- sent_len += err;
- msg += err;
- if (err != loop_len)
- goto send_free_err;
- }
-send_free_err:
- mutex_unlock(&ep->sendlock);
- kfree(tmp);
-send_err:
- return err < 0 ? err : sent_len;
-}
-
-/**
- * scif_user_recv() - Receive data from connection queue
- * @epd: The end point returned from scif_open()
- * @msg: Address to place data
- * @len: Length to receive
- * @flags: blocking or non blocking
- *
- * This function is called from the driver IOCTL entry point
- * only and is a wrapper for _scif_recv().
- */
-int scif_user_recv(scif_epd_t epd, void __user *msg, int len, int flags)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int err = 0;
- int recv_len = 0;
- char *tmp;
- int loop_len;
- int chunk_len = min(len, (1 << (MAX_ORDER + PAGE_SHIFT - 1)));
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI recv (U): ep %p %s\n", ep, scif_ep_states[ep->state]);
- if (!len)
- return 0;
-
- err = scif_msg_param_check(epd, len, flags);
- if (err)
- goto recv_err;
-
- tmp = kmalloc(chunk_len, GFP_KERNEL);
- if (!tmp) {
- err = -ENOMEM;
- goto recv_err;
- }
- /*
- * Grabbing the lock before breaking up the transfer in
- * multiple chunks is required to ensure that messages do
- * not get fragmented and reordered.
- */
- mutex_lock(&ep->recvlock);
- while (recv_len != len) {
- loop_len = len - recv_len;
- loop_len = min(chunk_len, loop_len);
- err = _scif_recv(epd, tmp, loop_len, flags);
- if (err < 0)
- goto recv_free_err;
- if (copy_to_user(msg, tmp, err)) {
- err = -EFAULT;
- goto recv_free_err;
- }
- recv_len += err;
- msg += err;
- if (err != loop_len)
- goto recv_free_err;
- }
-recv_free_err:
- mutex_unlock(&ep->recvlock);
- kfree(tmp);
-recv_err:
- return err < 0 ? err : recv_len;
-}
-
-/**
- * scif_send() - Send data to connection queue
- * @epd: The end point returned from scif_open()
- * @msg: Address to place data
- * @len: Length to receive
- * @flags: blocking or non blocking
- *
- * This function is called from the kernel mode only and is
- * a wrapper for _scif_send().
- */
-int scif_send(scif_epd_t epd, void *msg, int len, int flags)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int ret;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI send (K): ep %p %s\n", ep, scif_ep_states[ep->state]);
- if (!len)
- return 0;
-
- ret = scif_msg_param_check(epd, len, flags);
- if (ret)
- return ret;
- if (!ep->remote_dev)
- return -ENOTCONN;
- /*
- * Grab the mutex lock in the blocking case only
- * to ensure messages do not get fragmented/reordered.
- * The non blocking mode is protected using spin locks
- * in _scif_send().
- */
- if (flags & SCIF_SEND_BLOCK)
- mutex_lock(&ep->sendlock);
-
- ret = _scif_send(epd, msg, len, flags);
-
- if (flags & SCIF_SEND_BLOCK)
- mutex_unlock(&ep->sendlock);
- return ret;
-}
-EXPORT_SYMBOL_GPL(scif_send);
-
-/**
- * scif_recv() - Receive data from connection queue
- * @epd: The end point returned from scif_open()
- * @msg: Address to place data
- * @len: Length to receive
- * @flags: blocking or non blocking
- *
- * This function is called from the kernel mode only and is
- * a wrapper for _scif_recv().
- */
-int scif_recv(scif_epd_t epd, void *msg, int len, int flags)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int ret;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI recv (K): ep %p %s\n", ep, scif_ep_states[ep->state]);
- if (!len)
- return 0;
-
- ret = scif_msg_param_check(epd, len, flags);
- if (ret)
- return ret;
- /*
- * Grab the mutex lock in the blocking case only
- * to ensure messages do not get fragmented/reordered.
- * The non blocking mode is protected using spin locks
- * in _scif_send().
- */
- if (flags & SCIF_RECV_BLOCK)
- mutex_lock(&ep->recvlock);
-
- ret = _scif_recv(epd, msg, len, flags);
-
- if (flags & SCIF_RECV_BLOCK)
- mutex_unlock(&ep->recvlock);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(scif_recv);
-
-static inline void _scif_poll_wait(struct file *f, wait_queue_head_t *wq,
- poll_table *p, struct scif_endpt *ep)
-{
- /*
- * Because poll_wait makes a GFP_KERNEL allocation, give up the lock
- * and regrab it afterwards. Because the endpoint state might have
- * changed while the lock was given up, the state must be checked
- * again after re-acquiring the lock. The code in __scif_pollfd(..)
- * does this.
- */
- spin_unlock(&ep->lock);
- poll_wait(f, wq, p);
- spin_lock(&ep->lock);
-}
-
-__poll_t
-__scif_pollfd(struct file *f, poll_table *wait, struct scif_endpt *ep)
-{
- __poll_t mask = 0;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI pollfd: ep %p %s\n", ep, scif_ep_states[ep->state]);
-
- spin_lock(&ep->lock);
-
- /* Endpoint is waiting for a non-blocking connect to complete */
- if (ep->conn_async_state == ASYNC_CONN_INPROGRESS) {
- _scif_poll_wait(f, &ep->conn_pend_wq, wait, ep);
- if (ep->conn_async_state == ASYNC_CONN_INPROGRESS) {
- if (ep->state == SCIFEP_CONNECTED ||
- ep->state == SCIFEP_DISCONNECTED ||
- ep->conn_err)
- mask |= EPOLLOUT;
- goto exit;
- }
- }
-
- /* Endpoint is listening for incoming connection requests */
- if (ep->state == SCIFEP_LISTENING) {
- _scif_poll_wait(f, &ep->conwq, wait, ep);
- if (ep->state == SCIFEP_LISTENING) {
- if (ep->conreqcnt)
- mask |= EPOLLIN;
- goto exit;
- }
- }
-
- /* Endpoint is connected or disconnected */
- if (ep->state == SCIFEP_CONNECTED || ep->state == SCIFEP_DISCONNECTED) {
- if (poll_requested_events(wait) & EPOLLIN)
- _scif_poll_wait(f, &ep->recvwq, wait, ep);
- if (poll_requested_events(wait) & EPOLLOUT)
- _scif_poll_wait(f, &ep->sendwq, wait, ep);
- if (ep->state == SCIFEP_CONNECTED ||
- ep->state == SCIFEP_DISCONNECTED) {
- /* Data can be read without blocking */
- if (scif_rb_count(&ep->qp_info.qp->inbound_q, 1))
- mask |= EPOLLIN;
- /* Data can be written without blocking */
- if (scif_rb_space(&ep->qp_info.qp->outbound_q))
- mask |= EPOLLOUT;
- /* Return EPOLLHUP if endpoint is disconnected */
- if (ep->state == SCIFEP_DISCONNECTED)
- mask |= EPOLLHUP;
- goto exit;
- }
- }
-
- /* Return EPOLLERR if the endpoint is in none of the above states */
- mask |= EPOLLERR;
-exit:
- spin_unlock(&ep->lock);
- return mask;
-}
-
-/**
- * scif_poll() - Kernel mode SCIF poll
- * @ufds: Array of scif_pollepd structures containing the end points
- * and events to poll on
- * @nfds: Size of the ufds array
- * @timeout_msecs: Timeout in msecs, -ve implies infinite timeout
- *
- * The code flow in this function is based on do_poll(..) in select.c
- *
- * Returns the number of endpoints which have pending events or 0 in
- * the event of a timeout. If a signal is used for wake up, -EINTR is
- * returned.
- */
-int
-scif_poll(struct scif_pollepd *ufds, unsigned int nfds, long timeout_msecs)
-{
- struct poll_wqueues table;
- poll_table *pt;
- int i, count = 0, timed_out = timeout_msecs == 0;
- __poll_t mask;
- u64 timeout = timeout_msecs < 0 ? MAX_SCHEDULE_TIMEOUT
- : msecs_to_jiffies(timeout_msecs);
-
- poll_initwait(&table);
- pt = &table.pt;
- while (1) {
- for (i = 0; i < nfds; i++) {
- pt->_key = ufds[i].events | EPOLLERR | EPOLLHUP;
- mask = __scif_pollfd(ufds[i].epd->anon,
- pt, ufds[i].epd);
- mask &= ufds[i].events | EPOLLERR | EPOLLHUP;
- if (mask) {
- count++;
- pt->_qproc = NULL;
- }
- ufds[i].revents = mask;
- }
- pt->_qproc = NULL;
- if (!count) {
- count = table.error;
- if (signal_pending(current))
- count = -EINTR;
- }
- if (count || timed_out)
- break;
-
- if (!schedule_timeout_interruptible(timeout))
- timed_out = 1;
- }
- poll_freewait(&table);
- return count;
-}
-EXPORT_SYMBOL_GPL(scif_poll);
-
-int scif_get_node_ids(u16 *nodes, int len, u16 *self)
-{
- int online = 0;
- int offset = 0;
- int node;
-
- if (!scif_is_mgmt_node())
- scif_get_node_info();
-
- *self = scif_info.nodeid;
- mutex_lock(&scif_info.conflock);
- len = min_t(int, len, scif_info.total);
- for (node = 0; node <= scif_info.maxid; node++) {
- if (_scifdev_alive(&scif_dev[node])) {
- online++;
- if (offset < len)
- nodes[offset++] = node;
- }
- }
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI get_node_ids total %d online %d filled in %d nodes\n",
- scif_info.total, online, offset);
- mutex_unlock(&scif_info.conflock);
-
- return online;
-}
-EXPORT_SYMBOL_GPL(scif_get_node_ids);
-
-static int scif_add_client_dev(struct device *dev, struct subsys_interface *si)
-{
- struct scif_client *client =
- container_of(si, struct scif_client, si);
- struct scif_peer_dev *spdev =
- container_of(dev, struct scif_peer_dev, dev);
-
- if (client->probe)
- client->probe(spdev);
- return 0;
-}
-
-static void scif_remove_client_dev(struct device *dev,
- struct subsys_interface *si)
-{
- struct scif_client *client =
- container_of(si, struct scif_client, si);
- struct scif_peer_dev *spdev =
- container_of(dev, struct scif_peer_dev, dev);
-
- if (client->remove)
- client->remove(spdev);
-}
-
-void scif_client_unregister(struct scif_client *client)
-{
- subsys_interface_unregister(&client->si);
-}
-EXPORT_SYMBOL_GPL(scif_client_unregister);
-
-int scif_client_register(struct scif_client *client)
-{
- struct subsys_interface *si = &client->si;
-
- si->name = client->name;
- si->subsys = &scif_peer_bus;
- si->add_dev = scif_add_client_dev;
- si->remove_dev = scif_remove_client_dev;
-
- return subsys_interface_register(&client->si);
-}
-EXPORT_SYMBOL_GPL(scif_client_register);
diff --git a/drivers/misc/mic/scif/scif_debugfs.c b/drivers/misc/mic/scif/scif_debugfs.c
deleted file mode 100644
index 8fe38e7c..0000000
--- a/drivers/misc/mic/scif/scif_debugfs.c
+++ /dev/null
@@ -1,116 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-
-#include "../common/mic_dev.h"
-#include "scif_main.h"
-
-/* Debugfs parent dir */
-static struct dentry *scif_dbg;
-
-static int scif_dev_show(struct seq_file *s, void *unused)
-{
- int node;
-
- seq_printf(s, "Total Nodes %d Self Node Id %d Maxid %d\n",
- scif_info.total, scif_info.nodeid,
- scif_info.maxid);
-
- if (!scif_dev)
- return 0;
-
- seq_printf(s, "%-16s\t%-16s\n", "node_id", "state");
-
- for (node = 0; node <= scif_info.maxid; node++)
- seq_printf(s, "%-16d\t%-16s\n", scif_dev[node].node,
- _scifdev_alive(&scif_dev[node]) ?
- "Running" : "Offline");
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(scif_dev);
-
-static void scif_display_window(struct scif_window *window, struct seq_file *s)
-{
- int j;
- struct scatterlist *sg;
- scif_pinned_pages_t pin = window->pinned_pages;
-
- seq_printf(s, "window %p type %d temp %d offset 0x%llx ",
- window, window->type, window->temp, window->offset);
- seq_printf(s, "nr_pages 0x%llx nr_contig_chunks 0x%x prot %d ",
- window->nr_pages, window->nr_contig_chunks, window->prot);
- seq_printf(s, "ref_count %d magic 0x%llx peer_window 0x%llx ",
- window->ref_count, window->magic, window->peer_window);
- seq_printf(s, "unreg_state 0x%x va_for_temp 0x%lx\n",
- window->unreg_state, window->va_for_temp);
-
- for (j = 0; j < window->nr_contig_chunks; j++)
- seq_printf(s, "page[%d] dma_addr 0x%llx num_pages 0x%llx\n", j,
- window->dma_addr[j], window->num_pages[j]);
-
- if (window->type == SCIF_WINDOW_SELF && pin)
- for (j = 0; j < window->nr_pages; j++)
- seq_printf(s, "page[%d] = pinned_pages %p address %p\n",
- j, pin->pages[j],
- page_address(pin->pages[j]));
-
- if (window->st)
- for_each_sg(window->st->sgl, sg, window->st->nents, j)
- seq_printf(s, "sg[%d] dma addr 0x%llx length 0x%x\n",
- j, sg_dma_address(sg), sg_dma_len(sg));
-}
-
-static void scif_display_all_windows(struct list_head *head, struct seq_file *s)
-{
- struct list_head *item;
- struct scif_window *window;
-
- list_for_each(item, head) {
- window = list_entry(item, struct scif_window, list);
- scif_display_window(window, s);
- }
-}
-
-static int scif_rma_show(struct seq_file *s, void *unused)
-{
- struct scif_endpt *ep;
- struct list_head *pos;
-
- mutex_lock(&scif_info.connlock);
- list_for_each(pos, &scif_info.connected) {
- ep = list_entry(pos, struct scif_endpt, list);
- seq_printf(s, "ep %p self windows\n", ep);
- mutex_lock(&ep->rma_info.rma_lock);
- scif_display_all_windows(&ep->rma_info.reg_list, s);
- seq_printf(s, "ep %p remote windows\n", ep);
- scif_display_all_windows(&ep->rma_info.remote_reg_list, s);
- mutex_unlock(&ep->rma_info.rma_lock);
- }
- mutex_unlock(&scif_info.connlock);
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(scif_rma);
-
-void __init scif_init_debugfs(void)
-{
- scif_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL);
-
- debugfs_create_file("scif_dev", 0444, scif_dbg, NULL, &scif_dev_fops);
- debugfs_create_file("scif_rma", 0444, scif_dbg, NULL, &scif_rma_fops);
- debugfs_create_u8("en_msg_log", 0666, scif_dbg, &scif_info.en_msg_log);
- debugfs_create_u8("p2p_enable", 0666, scif_dbg, &scif_info.p2p_enable);
-}
-
-void scif_exit_debugfs(void)
-{
- debugfs_remove_recursive(scif_dbg);
-}
diff --git a/drivers/misc/mic/scif/scif_dma.c b/drivers/misc/mic/scif/scif_dma.c
deleted file mode 100644
index 401b98e..0000000
--- a/drivers/misc/mic/scif/scif_dma.c
+++ /dev/null
@@ -1,1940 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-#include "scif_map.h"
-
-/*
- * struct scif_dma_comp_cb - SCIF DMA completion callback
- *
- * @dma_completion_func: DMA completion callback
- * @cb_cookie: DMA completion callback cookie
- * @temp_buf: Temporary buffer
- * @temp_buf_to_free: Temporary buffer to be freed
- * @is_cache: Is a kmem_cache allocated buffer
- * @dst_offset: Destination registration offset
- * @dst_window: Destination registration window
- * @len: Length of the temp buffer
- * @temp_phys: DMA address of the temp buffer
- * @sdev: The SCIF device
- * @header_padding: padding for cache line alignment
- */
-struct scif_dma_comp_cb {
- void (*dma_completion_func)(void *cookie);
- void *cb_cookie;
- u8 *temp_buf;
- u8 *temp_buf_to_free;
- bool is_cache;
- s64 dst_offset;
- struct scif_window *dst_window;
- size_t len;
- dma_addr_t temp_phys;
- struct scif_dev *sdev;
- int header_padding;
-};
-
-/**
- * struct scif_copy_work - Work for DMA copy
- *
- * @src_offset: Starting source offset
- * @dst_offset: Starting destination offset
- * @src_window: Starting src registered window
- * @dst_window: Starting dst registered window
- * @loopback: true if this is a loopback DMA transfer
- * @len: Length of the transfer
- * @comp_cb: DMA copy completion callback
- * @remote_dev: The remote SCIF peer device
- * @fence_type: polling or interrupt based
- * @ordered: is this a tail byte ordered DMA transfer
- */
-struct scif_copy_work {
- s64 src_offset;
- s64 dst_offset;
- struct scif_window *src_window;
- struct scif_window *dst_window;
- int loopback;
- size_t len;
- struct scif_dma_comp_cb *comp_cb;
- struct scif_dev *remote_dev;
- int fence_type;
- bool ordered;
-};
-
-/**
- * scif_reserve_dma_chan:
- * @ep: Endpoint Descriptor.
- *
- * This routine reserves a DMA channel for a particular
- * endpoint. All DMA transfers for an endpoint are always
- * programmed on the same DMA channel.
- */
-int scif_reserve_dma_chan(struct scif_endpt *ep)
-{
- int err = 0;
- struct scif_dev *scifdev;
- struct scif_hw_dev *sdev;
- struct dma_chan *chan;
-
- /* Loopback DMAs are not supported on the management node */
- if (!scif_info.nodeid && scifdev_self(ep->remote_dev))
- return 0;
- if (scif_info.nodeid)
- scifdev = &scif_dev[0];
- else
- scifdev = ep->remote_dev;
- sdev = scifdev->sdev;
- if (!sdev->num_dma_ch)
- return -ENODEV;
- chan = sdev->dma_ch[scifdev->dma_ch_idx];
- scifdev->dma_ch_idx = (scifdev->dma_ch_idx + 1) % sdev->num_dma_ch;
- mutex_lock(&ep->rma_info.rma_lock);
- ep->rma_info.dma_chan = chan;
- mutex_unlock(&ep->rma_info.rma_lock);
- return err;
-}
-
-#ifdef CONFIG_MMU_NOTIFIER
-/*
- * scif_rma_destroy_tcw:
- *
- * This routine destroys temporary cached windows
- */
-static
-void __scif_rma_destroy_tcw(struct scif_mmu_notif *mmn,
- u64 start, u64 len)
-{
- struct list_head *item, *tmp;
- struct scif_window *window;
- u64 start_va, end_va;
- u64 end = start + len;
-
- if (end <= start)
- return;
-
- list_for_each_safe(item, tmp, &mmn->tc_reg_list) {
- window = list_entry(item, struct scif_window, list);
- if (!len)
- break;
- start_va = window->va_for_temp;
- end_va = start_va + (window->nr_pages << PAGE_SHIFT);
- if (start < start_va && end <= start_va)
- break;
- if (start >= end_va)
- continue;
- __scif_rma_destroy_tcw_helper(window);
- }
-}
-
-static void scif_rma_destroy_tcw(struct scif_mmu_notif *mmn, u64 start, u64 len)
-{
- struct scif_endpt *ep = mmn->ep;
-
- spin_lock(&ep->rma_info.tc_lock);
- __scif_rma_destroy_tcw(mmn, start, len);
- spin_unlock(&ep->rma_info.tc_lock);
-}
-
-static void scif_rma_destroy_tcw_ep(struct scif_endpt *ep)
-{
- struct list_head *item, *tmp;
- struct scif_mmu_notif *mmn;
-
- list_for_each_safe(item, tmp, &ep->rma_info.mmn_list) {
- mmn = list_entry(item, struct scif_mmu_notif, list);
- scif_rma_destroy_tcw(mmn, 0, ULONG_MAX);
- }
-}
-
-static void __scif_rma_destroy_tcw_ep(struct scif_endpt *ep)
-{
- struct list_head *item, *tmp;
- struct scif_mmu_notif *mmn;
-
- spin_lock(&ep->rma_info.tc_lock);
- list_for_each_safe(item, tmp, &ep->rma_info.mmn_list) {
- mmn = list_entry(item, struct scif_mmu_notif, list);
- __scif_rma_destroy_tcw(mmn, 0, ULONG_MAX);
- }
- spin_unlock(&ep->rma_info.tc_lock);
-}
-
-static bool scif_rma_tc_can_cache(struct scif_endpt *ep, size_t cur_bytes)
-{
- if ((cur_bytes >> PAGE_SHIFT) > scif_info.rma_tc_limit)
- return false;
- if ((atomic_read(&ep->rma_info.tcw_total_pages)
- + (cur_bytes >> PAGE_SHIFT)) >
- scif_info.rma_tc_limit) {
- dev_info(scif_info.mdev.this_device,
- "%s %d total=%d, current=%zu reached max\n",
- __func__, __LINE__,
- atomic_read(&ep->rma_info.tcw_total_pages),
- (1 + (cur_bytes >> PAGE_SHIFT)));
- scif_rma_destroy_tcw_invalid();
- __scif_rma_destroy_tcw_ep(ep);
- }
- return true;
-}
-
-static void scif_mmu_notifier_release(struct mmu_notifier *mn,
- struct mm_struct *mm)
-{
- struct scif_mmu_notif *mmn;
-
- mmn = container_of(mn, struct scif_mmu_notif, ep_mmu_notifier);
- scif_rma_destroy_tcw(mmn, 0, ULONG_MAX);
- schedule_work(&scif_info.misc_work);
-}
-
-static int scif_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
- const struct mmu_notifier_range *range)
-{
- struct scif_mmu_notif *mmn;
-
- mmn = container_of(mn, struct scif_mmu_notif, ep_mmu_notifier);
- scif_rma_destroy_tcw(mmn, range->start, range->end - range->start);
-
- return 0;
-}
-
-static void scif_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
- const struct mmu_notifier_range *range)
-{
- /*
- * Nothing to do here, everything needed was done in
- * invalidate_range_start.
- */
-}
-
-static const struct mmu_notifier_ops scif_mmu_notifier_ops = {
- .release = scif_mmu_notifier_release,
- .clear_flush_young = NULL,
- .invalidate_range_start = scif_mmu_notifier_invalidate_range_start,
- .invalidate_range_end = scif_mmu_notifier_invalidate_range_end};
-
-static void scif_ep_unregister_mmu_notifier(struct scif_endpt *ep)
-{
- struct scif_endpt_rma_info *rma = &ep->rma_info;
- struct scif_mmu_notif *mmn = NULL;
- struct list_head *item, *tmp;
-
- mutex_lock(&ep->rma_info.mmn_lock);
- list_for_each_safe(item, tmp, &rma->mmn_list) {
- mmn = list_entry(item, struct scif_mmu_notif, list);
- mmu_notifier_unregister(&mmn->ep_mmu_notifier, mmn->mm);
- list_del(item);
- kfree(mmn);
- }
- mutex_unlock(&ep->rma_info.mmn_lock);
-}
-
-static void scif_init_mmu_notifier(struct scif_mmu_notif *mmn,
- struct mm_struct *mm, struct scif_endpt *ep)
-{
- mmn->ep = ep;
- mmn->mm = mm;
- mmn->ep_mmu_notifier.ops = &scif_mmu_notifier_ops;
- INIT_LIST_HEAD(&mmn->list);
- INIT_LIST_HEAD(&mmn->tc_reg_list);
-}
-
-static struct scif_mmu_notif *
-scif_find_mmu_notifier(struct mm_struct *mm, struct scif_endpt_rma_info *rma)
-{
- struct scif_mmu_notif *mmn;
-
- list_for_each_entry(mmn, &rma->mmn_list, list)
- if (mmn->mm == mm)
- return mmn;
- return NULL;
-}
-
-static struct scif_mmu_notif *
-scif_add_mmu_notifier(struct mm_struct *mm, struct scif_endpt *ep)
-{
- struct scif_mmu_notif *mmn
- = kzalloc(sizeof(*mmn), GFP_KERNEL);
-
- if (!mmn)
- return ERR_PTR(-ENOMEM);
-
- scif_init_mmu_notifier(mmn, current->mm, ep);
- if (mmu_notifier_register(&mmn->ep_mmu_notifier, current->mm)) {
- kfree(mmn);
- return ERR_PTR(-EBUSY);
- }
- list_add(&mmn->list, &ep->rma_info.mmn_list);
- return mmn;
-}
-
-/*
- * Called from the misc thread to destroy temporary cached windows and
- * unregister the MMU notifier for the SCIF endpoint.
- */
-void scif_mmu_notif_handler(struct work_struct *work)
-{
- struct list_head *pos, *tmpq;
- struct scif_endpt *ep;
-restart:
- scif_rma_destroy_tcw_invalid();
- spin_lock(&scif_info.rmalock);
- list_for_each_safe(pos, tmpq, &scif_info.mmu_notif_cleanup) {
- ep = list_entry(pos, struct scif_endpt, mmu_list);
- list_del(&ep->mmu_list);
- spin_unlock(&scif_info.rmalock);
- scif_rma_destroy_tcw_ep(ep);
- scif_ep_unregister_mmu_notifier(ep);
- goto restart;
- }
- spin_unlock(&scif_info.rmalock);
-}
-
-static bool scif_is_set_reg_cache(int flags)
-{
- return !!(flags & SCIF_RMA_USECACHE);
-}
-#else
-static struct scif_mmu_notif *
-scif_find_mmu_notifier(struct mm_struct *mm,
- struct scif_endpt_rma_info *rma)
-{
- return NULL;
-}
-
-static struct scif_mmu_notif *
-scif_add_mmu_notifier(struct mm_struct *mm, struct scif_endpt *ep)
-{
- return NULL;
-}
-
-void scif_mmu_notif_handler(struct work_struct *work)
-{
-}
-
-static bool scif_is_set_reg_cache(int flags)
-{
- return false;
-}
-
-static bool scif_rma_tc_can_cache(struct scif_endpt *ep, size_t cur_bytes)
-{
- return false;
-}
-#endif
-
-/**
- * scif_register_temp:
- * @epd: End Point Descriptor.
- * @addr: virtual address to/from which to copy
- * @len: length of range to copy
- * @prot: read/write protection
- * @out_offset: computed offset returned by reference.
- * @out_window: allocated registered window returned by reference.
- *
- * Create a temporary registered window. The peer will not know about this
- * window. This API is used for scif_vreadfrom()/scif_vwriteto() API's.
- */
-static int
-scif_register_temp(scif_epd_t epd, unsigned long addr, size_t len, int prot,
- off_t *out_offset, struct scif_window **out_window)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int err;
- scif_pinned_pages_t pinned_pages;
- size_t aligned_len;
-
- aligned_len = ALIGN(len, PAGE_SIZE);
-
- err = __scif_pin_pages((void *)(addr & PAGE_MASK),
- aligned_len, &prot, 0, &pinned_pages);
- if (err)
- return err;
-
- pinned_pages->prot = prot;
-
- /* Compute the offset for this registration */
- err = scif_get_window_offset(ep, 0, 0,
- aligned_len >> PAGE_SHIFT,
- (s64 *)out_offset);
- if (err)
- goto error_unpin;
-
- /* Allocate and prepare self registration window */
- *out_window = scif_create_window(ep, aligned_len >> PAGE_SHIFT,
- *out_offset, true);
- if (!*out_window) {
- scif_free_window_offset(ep, NULL, *out_offset);
- err = -ENOMEM;
- goto error_unpin;
- }
-
- (*out_window)->pinned_pages = pinned_pages;
- (*out_window)->nr_pages = pinned_pages->nr_pages;
- (*out_window)->prot = pinned_pages->prot;
-
- (*out_window)->va_for_temp = addr & PAGE_MASK;
- err = scif_map_window(ep->remote_dev, *out_window);
- if (err) {
- /* Something went wrong! Rollback */
- scif_destroy_window(ep, *out_window);
- *out_window = NULL;
- } else {
- *out_offset |= (addr - (*out_window)->va_for_temp);
- }
- return err;
-error_unpin:
- if (err)
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- scif_unpin_pages(pinned_pages);
- return err;
-}
-
-#define SCIF_DMA_TO (3 * HZ)
-
-/*
- * scif_sync_dma - Program a DMA without an interrupt descriptor
- *
- * @dev - The address of the pointer to the device instance used
- * for DMA registration.
- * @chan - DMA channel to be used.
- * @sync_wait: Wait for DMA to complete?
- *
- * Return 0 on success and -errno on error.
- */
-static int scif_sync_dma(struct scif_hw_dev *sdev, struct dma_chan *chan,
- bool sync_wait)
-{
- int err = 0;
- struct dma_async_tx_descriptor *tx = NULL;
- enum dma_ctrl_flags flags = DMA_PREP_FENCE;
- dma_cookie_t cookie;
- struct dma_device *ddev;
-
- if (!chan) {
- err = -EIO;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- return err;
- }
- ddev = chan->device;
-
- tx = ddev->device_prep_dma_memcpy(chan, 0, 0, 0, flags);
- if (!tx) {
- err = -ENOMEM;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto release;
- }
- cookie = tx->tx_submit(tx);
-
- if (dma_submit_error(cookie)) {
- err = -ENOMEM;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto release;
- }
- if (!sync_wait) {
- dma_async_issue_pending(chan);
- } else {
- if (dma_sync_wait(chan, cookie) == DMA_COMPLETE) {
- err = 0;
- } else {
- err = -EIO;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- }
- }
-release:
- return err;
-}
-
-static void scif_dma_callback(void *arg)
-{
- struct completion *done = (struct completion *)arg;
-
- complete(done);
-}
-
-#define SCIF_DMA_SYNC_WAIT true
-#define SCIF_DMA_POLL BIT(0)
-#define SCIF_DMA_INTR BIT(1)
-
-/*
- * scif_async_dma - Program a DMA with an interrupt descriptor
- *
- * @dev - The address of the pointer to the device instance used
- * for DMA registration.
- * @chan - DMA channel to be used.
- * Return 0 on success and -errno on error.
- */
-static int scif_async_dma(struct scif_hw_dev *sdev, struct dma_chan *chan)
-{
- int err = 0;
- struct dma_device *ddev;
- struct dma_async_tx_descriptor *tx = NULL;
- enum dma_ctrl_flags flags = DMA_PREP_INTERRUPT | DMA_PREP_FENCE;
- DECLARE_COMPLETION_ONSTACK(done_wait);
- dma_cookie_t cookie;
- enum dma_status status;
-
- if (!chan) {
- err = -EIO;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- return err;
- }
- ddev = chan->device;
-
- tx = ddev->device_prep_dma_memcpy(chan, 0, 0, 0, flags);
- if (!tx) {
- err = -ENOMEM;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto release;
- }
- reinit_completion(&done_wait);
- tx->callback = scif_dma_callback;
- tx->callback_param = &done_wait;
- cookie = tx->tx_submit(tx);
-
- if (dma_submit_error(cookie)) {
- err = -ENOMEM;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto release;
- }
- dma_async_issue_pending(chan);
-
- err = wait_for_completion_timeout(&done_wait, SCIF_DMA_TO);
- if (!err) {
- err = -EIO;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto release;
- }
- err = 0;
- status = dma_async_is_tx_complete(chan, cookie, NULL, NULL);
- if (status != DMA_COMPLETE) {
- err = -EIO;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto release;
- }
-release:
- return err;
-}
-
-/*
- * scif_drain_dma_poll - Drain all outstanding DMA operations for a particular
- * DMA channel via polling.
- *
- * @sdev - The SCIF device
- * @chan - DMA channel
- * Return 0 on success and -errno on error.
- */
-static int scif_drain_dma_poll(struct scif_hw_dev *sdev, struct dma_chan *chan)
-{
- if (!chan)
- return -EINVAL;
- return scif_sync_dma(sdev, chan, SCIF_DMA_SYNC_WAIT);
-}
-
-/*
- * scif_drain_dma_intr - Drain all outstanding DMA operations for a particular
- * DMA channel via interrupt based blocking wait.
- *
- * @sdev - The SCIF device
- * @chan - DMA channel
- * Return 0 on success and -errno on error.
- */
-int scif_drain_dma_intr(struct scif_hw_dev *sdev, struct dma_chan *chan)
-{
- if (!chan)
- return -EINVAL;
- return scif_async_dma(sdev, chan);
-}
-
-/**
- * scif_rma_destroy_windows:
- *
- * This routine destroys all windows queued for cleanup
- */
-void scif_rma_destroy_windows(void)
-{
- struct list_head *item, *tmp;
- struct scif_window *window;
- struct scif_endpt *ep;
- struct dma_chan *chan;
-
- might_sleep();
-restart:
- spin_lock(&scif_info.rmalock);
- list_for_each_safe(item, tmp, &scif_info.rma) {
- window = list_entry(item, struct scif_window,
- list);
- ep = (struct scif_endpt *)window->ep;
- chan = ep->rma_info.dma_chan;
-
- list_del_init(&window->list);
- spin_unlock(&scif_info.rmalock);
- if (!chan || !scifdev_alive(ep) ||
- !scif_drain_dma_intr(ep->remote_dev->sdev,
- ep->rma_info.dma_chan))
- /* Remove window from global list */
- window->unreg_state = OP_COMPLETED;
- else
- dev_warn(&ep->remote_dev->sdev->dev,
- "DMA engine hung?\n");
- if (window->unreg_state == OP_COMPLETED) {
- if (window->type == SCIF_WINDOW_SELF)
- scif_destroy_window(ep, window);
- else
- scif_destroy_remote_window(window);
- atomic_dec(&ep->rma_info.tw_refcount);
- }
- goto restart;
- }
- spin_unlock(&scif_info.rmalock);
-}
-
-/**
- * scif_rma_destroy_tcw:
- *
- * This routine destroys temporary cached registered windows
- * which have been queued for cleanup.
- */
-void scif_rma_destroy_tcw_invalid(void)
-{
- struct list_head *item, *tmp;
- struct scif_window *window;
- struct scif_endpt *ep;
- struct dma_chan *chan;
-
- might_sleep();
-restart:
- spin_lock(&scif_info.rmalock);
- list_for_each_safe(item, tmp, &scif_info.rma_tc) {
- window = list_entry(item, struct scif_window, list);
- ep = (struct scif_endpt *)window->ep;
- chan = ep->rma_info.dma_chan;
- list_del_init(&window->list);
- spin_unlock(&scif_info.rmalock);
- mutex_lock(&ep->rma_info.rma_lock);
- if (!chan || !scifdev_alive(ep) ||
- !scif_drain_dma_intr(ep->remote_dev->sdev,
- ep->rma_info.dma_chan)) {
- atomic_sub(window->nr_pages,
- &ep->rma_info.tcw_total_pages);
- scif_destroy_window(ep, window);
- atomic_dec(&ep->rma_info.tcw_refcount);
- } else {
- dev_warn(&ep->remote_dev->sdev->dev,
- "DMA engine hung?\n");
- }
- mutex_unlock(&ep->rma_info.rma_lock);
- goto restart;
- }
- spin_unlock(&scif_info.rmalock);
-}
-
-static inline
-void *_get_local_va(off_t off, struct scif_window *window, size_t len)
-{
- int page_nr = (off - window->offset) >> PAGE_SHIFT;
- off_t page_off = off & ~PAGE_MASK;
- void *va = NULL;
-
- if (window->type == SCIF_WINDOW_SELF) {
- struct page **pages = window->pinned_pages->pages;
-
- va = page_address(pages[page_nr]) + page_off;
- }
- return va;
-}
-
-static inline
-void *ioremap_remote(off_t off, struct scif_window *window,
- size_t len, struct scif_dev *dev,
- struct scif_window_iter *iter)
-{
- dma_addr_t phys = scif_off_to_dma_addr(window, off, NULL, iter);
-
- /*
- * If the DMA address is not card relative then we need the DMA
- * addresses to be an offset into the bar. The aperture base was already
- * added so subtract it here since scif_ioremap is going to add it again
- */
- if (!scifdev_self(dev) && window->type == SCIF_WINDOW_PEER &&
- dev->sdev->aper && !dev->sdev->card_rel_da)
- phys = phys - dev->sdev->aper->pa;
- return scif_ioremap(phys, len, dev);
-}
-
-static inline void
-iounmap_remote(void *virt, size_t size, struct scif_copy_work *work)
-{
- scif_iounmap(virt, size, work->remote_dev);
-}
-
-/*
- * Takes care of ordering issue caused by
- * 1. Hardware: Only in the case of cpu copy from mgmt node to card
- * because of WC memory.
- * 2. Software: If memcpy reorders copy instructions for optimization.
- * This could happen at both mgmt node and card.
- */
-static inline void
-scif_ordered_memcpy_toio(char *dst, const char *src, size_t count)
-{
- if (!count)
- return;
-
- memcpy_toio((void __iomem __force *)dst, src, --count);
- /* Order the last byte with the previous stores */
- wmb();
- *(dst + count) = *(src + count);
-}
-
-static inline void scif_unaligned_cpy_toio(char *dst, const char *src,
- size_t count, bool ordered)
-{
- if (ordered)
- scif_ordered_memcpy_toio(dst, src, count);
- else
- memcpy_toio((void __iomem __force *)dst, src, count);
-}
-
-static inline
-void scif_ordered_memcpy_fromio(char *dst, const char *src, size_t count)
-{
- if (!count)
- return;
-
- memcpy_fromio(dst, (void __iomem __force *)src, --count);
- /* Order the last byte with the previous loads */
- rmb();
- *(dst + count) = *(src + count);
-}
-
-static inline void scif_unaligned_cpy_fromio(char *dst, const char *src,
- size_t count, bool ordered)
-{
- if (ordered)
- scif_ordered_memcpy_fromio(dst, src, count);
- else
- memcpy_fromio(dst, (void __iomem __force *)src, count);
-}
-
-#define SCIF_RMA_ERROR_CODE (~(dma_addr_t)0x0)
-
-/*
- * scif_off_to_dma_addr:
- * Obtain the dma_addr given the window and the offset.
- * @window: Registered window.
- * @off: Window offset.
- * @nr_bytes: Return the number of contiguous bytes till next DMA addr index.
- * @index: Return the index of the dma_addr array found.
- * @start_off: start offset of index of the dma addr array found.
- * The nr_bytes provides the callee an estimate of the maximum possible
- * DMA xfer possible while the index/start_off provide faster lookups
- * for the next iteration.
- */
-dma_addr_t scif_off_to_dma_addr(struct scif_window *window, s64 off,
- size_t *nr_bytes, struct scif_window_iter *iter)
-{
- int i, page_nr;
- s64 start, end;
- off_t page_off;
-
- if (window->nr_pages == window->nr_contig_chunks) {
- page_nr = (off - window->offset) >> PAGE_SHIFT;
- page_off = off & ~PAGE_MASK;
-
- if (nr_bytes)
- *nr_bytes = PAGE_SIZE - page_off;
- return window->dma_addr[page_nr] | page_off;
- }
- if (iter) {
- i = iter->index;
- start = iter->offset;
- } else {
- i = 0;
- start = window->offset;
- }
- for (; i < window->nr_contig_chunks; i++) {
- end = start + (window->num_pages[i] << PAGE_SHIFT);
- if (off >= start && off < end) {
- if (iter) {
- iter->index = i;
- iter->offset = start;
- }
- if (nr_bytes)
- *nr_bytes = end - off;
- return (window->dma_addr[i] + (off - start));
- }
- start += (window->num_pages[i] << PAGE_SHIFT);
- }
- dev_err(scif_info.mdev.this_device,
- "%s %d BUG. Addr not found? window %p off 0x%llx\n",
- __func__, __LINE__, window, off);
- return SCIF_RMA_ERROR_CODE;
-}
-
-/*
- * Copy between rma window and temporary buffer
- */
-static void scif_rma_local_cpu_copy(s64 offset, struct scif_window *window,
- u8 *temp, size_t rem_len, bool to_temp)
-{
- void *window_virt;
- size_t loop_len;
- int offset_in_page;
- s64 end_offset;
-
- offset_in_page = offset & ~PAGE_MASK;
- loop_len = PAGE_SIZE - offset_in_page;
-
- if (rem_len < loop_len)
- loop_len = rem_len;
-
- window_virt = _get_local_va(offset, window, loop_len);
- if (!window_virt)
- return;
- if (to_temp)
- memcpy(temp, window_virt, loop_len);
- else
- memcpy(window_virt, temp, loop_len);
-
- offset += loop_len;
- temp += loop_len;
- rem_len -= loop_len;
-
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
- while (rem_len) {
- if (offset == end_offset) {
- window = list_next_entry(window, list);
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
- }
- loop_len = min(PAGE_SIZE, rem_len);
- window_virt = _get_local_va(offset, window, loop_len);
- if (!window_virt)
- return;
- if (to_temp)
- memcpy(temp, window_virt, loop_len);
- else
- memcpy(window_virt, temp, loop_len);
- offset += loop_len;
- temp += loop_len;
- rem_len -= loop_len;
- }
-}
-
-/**
- * scif_rma_completion_cb:
- * @data: RMA cookie
- *
- * RMA interrupt completion callback.
- */
-static void scif_rma_completion_cb(void *data)
-{
- struct scif_dma_comp_cb *comp_cb = data;
-
- /* Free DMA Completion CB. */
- if (comp_cb->dst_window)
- scif_rma_local_cpu_copy(comp_cb->dst_offset,
- comp_cb->dst_window,
- comp_cb->temp_buf +
- comp_cb->header_padding,
- comp_cb->len, false);
- scif_unmap_single(comp_cb->temp_phys, comp_cb->sdev,
- SCIF_KMEM_UNALIGNED_BUF_SIZE);
- if (comp_cb->is_cache)
- kmem_cache_free(unaligned_cache,
- comp_cb->temp_buf_to_free);
- else
- kfree(comp_cb->temp_buf_to_free);
-}
-
-/* Copies between temporary buffer and offsets provided in work */
-static int
-scif_rma_list_dma_copy_unaligned(struct scif_copy_work *work,
- u8 *temp, struct dma_chan *chan,
- bool src_local)
-{
- struct scif_dma_comp_cb *comp_cb = work->comp_cb;
- dma_addr_t window_dma_addr, temp_dma_addr;
- dma_addr_t temp_phys = comp_cb->temp_phys;
- size_t loop_len, nr_contig_bytes = 0, remaining_len = work->len;
- int offset_in_ca, ret = 0;
- s64 end_offset, offset;
- struct scif_window *window;
- void *window_virt_addr;
- size_t tail_len;
- struct dma_async_tx_descriptor *tx;
- struct dma_device *dev = chan->device;
- dma_cookie_t cookie;
-
- if (src_local) {
- offset = work->dst_offset;
- window = work->dst_window;
- } else {
- offset = work->src_offset;
- window = work->src_window;
- }
-
- offset_in_ca = offset & (L1_CACHE_BYTES - 1);
- if (offset_in_ca) {
- loop_len = L1_CACHE_BYTES - offset_in_ca;
- loop_len = min(loop_len, remaining_len);
- window_virt_addr = ioremap_remote(offset, window,
- loop_len,
- work->remote_dev,
- NULL);
- if (!window_virt_addr)
- return -ENOMEM;
- if (src_local)
- scif_unaligned_cpy_toio(window_virt_addr, temp,
- loop_len,
- work->ordered &&
- !(remaining_len - loop_len));
- else
- scif_unaligned_cpy_fromio(temp, window_virt_addr,
- loop_len, work->ordered &&
- !(remaining_len - loop_len));
- iounmap_remote(window_virt_addr, loop_len, work);
-
- offset += loop_len;
- temp += loop_len;
- temp_phys += loop_len;
- remaining_len -= loop_len;
- }
-
- offset_in_ca = offset & ~PAGE_MASK;
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
-
- tail_len = remaining_len & (L1_CACHE_BYTES - 1);
- remaining_len -= tail_len;
- while (remaining_len) {
- if (offset == end_offset) {
- window = list_next_entry(window, list);
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
- }
- if (scif_is_mgmt_node())
- temp_dma_addr = temp_phys;
- else
- /* Fix if we ever enable IOMMU on the card */
- temp_dma_addr = (dma_addr_t)virt_to_phys(temp);
- window_dma_addr = scif_off_to_dma_addr(window, offset,
- &nr_contig_bytes,
- NULL);
- loop_len = min(nr_contig_bytes, remaining_len);
- if (src_local) {
- if (work->ordered && !tail_len &&
- !(remaining_len - loop_len) &&
- loop_len != L1_CACHE_BYTES) {
- /*
- * Break up the last chunk of the transfer into
- * two steps. if there is no tail to guarantee
- * DMA ordering. SCIF_DMA_POLLING inserts
- * a status update descriptor in step 1 which
- * acts as a double sided synchronization fence
- * for the DMA engine to ensure that the last
- * cache line in step 2 is updated last.
- */
- /* Step 1) DMA: Body Length - L1_CACHE_BYTES. */
- tx =
- dev->device_prep_dma_memcpy(chan,
- window_dma_addr,
- temp_dma_addr,
- loop_len -
- L1_CACHE_BYTES,
- DMA_PREP_FENCE);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- dma_async_issue_pending(chan);
- offset += (loop_len - L1_CACHE_BYTES);
- temp_dma_addr += (loop_len - L1_CACHE_BYTES);
- window_dma_addr += (loop_len - L1_CACHE_BYTES);
- remaining_len -= (loop_len - L1_CACHE_BYTES);
- loop_len = remaining_len;
-
- /* Step 2) DMA: L1_CACHE_BYTES */
- tx =
- dev->device_prep_dma_memcpy(chan,
- window_dma_addr,
- temp_dma_addr,
- loop_len, 0);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- dma_async_issue_pending(chan);
- } else {
- tx =
- dev->device_prep_dma_memcpy(chan,
- window_dma_addr,
- temp_dma_addr,
- loop_len, 0);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- dma_async_issue_pending(chan);
- }
- } else {
- tx = dev->device_prep_dma_memcpy(chan, temp_dma_addr,
- window_dma_addr, loop_len, 0);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- dma_async_issue_pending(chan);
- }
- offset += loop_len;
- temp += loop_len;
- temp_phys += loop_len;
- remaining_len -= loop_len;
- offset_in_ca = 0;
- }
- if (tail_len) {
- if (offset == end_offset) {
- window = list_next_entry(window, list);
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
- }
- window_virt_addr = ioremap_remote(offset, window, tail_len,
- work->remote_dev,
- NULL);
- if (!window_virt_addr)
- return -ENOMEM;
- /*
- * The CPU copy for the tail bytes must be initiated only once
- * previous DMA transfers for this endpoint have completed
- * to guarantee ordering.
- */
- if (work->ordered) {
- struct scif_dev *rdev = work->remote_dev;
-
- ret = scif_drain_dma_intr(rdev->sdev, chan);
- if (ret)
- return ret;
- }
- if (src_local)
- scif_unaligned_cpy_toio(window_virt_addr, temp,
- tail_len, work->ordered);
- else
- scif_unaligned_cpy_fromio(temp, window_virt_addr,
- tail_len, work->ordered);
- iounmap_remote(window_virt_addr, tail_len, work);
- }
- tx = dev->device_prep_dma_memcpy(chan, 0, 0, 0, DMA_PREP_INTERRUPT);
- if (!tx) {
- ret = -ENOMEM;
- return ret;
- }
- tx->callback = &scif_rma_completion_cb;
- tx->callback_param = comp_cb;
- cookie = tx->tx_submit(tx);
-
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- return ret;
- }
- dma_async_issue_pending(chan);
- return 0;
-err:
- dev_err(scif_info.mdev.this_device,
- "%s %d Desc Prog Failed ret %d\n",
- __func__, __LINE__, ret);
- return ret;
-}
-
-/*
- * _scif_rma_list_dma_copy_aligned:
- *
- * Traverse all the windows and perform DMA copy.
- */
-static int _scif_rma_list_dma_copy_aligned(struct scif_copy_work *work,
- struct dma_chan *chan)
-{
- dma_addr_t src_dma_addr, dst_dma_addr;
- size_t loop_len, remaining_len, src_contig_bytes = 0;
- size_t dst_contig_bytes = 0;
- struct scif_window_iter src_win_iter;
- struct scif_window_iter dst_win_iter;
- s64 end_src_offset, end_dst_offset;
- struct scif_window *src_window = work->src_window;
- struct scif_window *dst_window = work->dst_window;
- s64 src_offset = work->src_offset, dst_offset = work->dst_offset;
- int ret = 0;
- struct dma_async_tx_descriptor *tx;
- struct dma_device *dev = chan->device;
- dma_cookie_t cookie;
-
- remaining_len = work->len;
-
- scif_init_window_iter(src_window, &src_win_iter);
- scif_init_window_iter(dst_window, &dst_win_iter);
- end_src_offset = src_window->offset +
- (src_window->nr_pages << PAGE_SHIFT);
- end_dst_offset = dst_window->offset +
- (dst_window->nr_pages << PAGE_SHIFT);
- while (remaining_len) {
- if (src_offset == end_src_offset) {
- src_window = list_next_entry(src_window, list);
- end_src_offset = src_window->offset +
- (src_window->nr_pages << PAGE_SHIFT);
- scif_init_window_iter(src_window, &src_win_iter);
- }
- if (dst_offset == end_dst_offset) {
- dst_window = list_next_entry(dst_window, list);
- end_dst_offset = dst_window->offset +
- (dst_window->nr_pages << PAGE_SHIFT);
- scif_init_window_iter(dst_window, &dst_win_iter);
- }
-
- /* compute dma addresses for transfer */
- src_dma_addr = scif_off_to_dma_addr(src_window, src_offset,
- &src_contig_bytes,
- &src_win_iter);
- dst_dma_addr = scif_off_to_dma_addr(dst_window, dst_offset,
- &dst_contig_bytes,
- &dst_win_iter);
- loop_len = min(src_contig_bytes, dst_contig_bytes);
- loop_len = min(loop_len, remaining_len);
- if (work->ordered && !(remaining_len - loop_len)) {
- /*
- * Break up the last chunk of the transfer into two
- * steps to ensure that the last byte in step 2 is
- * updated last.
- */
- /* Step 1) DMA: Body Length - 1 */
- tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
- src_dma_addr,
- loop_len - 1,
- DMA_PREP_FENCE);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- src_offset += (loop_len - 1);
- dst_offset += (loop_len - 1);
- src_dma_addr += (loop_len - 1);
- dst_dma_addr += (loop_len - 1);
- remaining_len -= (loop_len - 1);
- loop_len = remaining_len;
-
- /* Step 2) DMA: 1 BYTES */
- tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
- src_dma_addr, loop_len, 0);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- dma_async_issue_pending(chan);
- } else {
- tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
- src_dma_addr, loop_len, 0);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- }
- src_offset += loop_len;
- dst_offset += loop_len;
- remaining_len -= loop_len;
- }
- return ret;
-err:
- dev_err(scif_info.mdev.this_device,
- "%s %d Desc Prog Failed ret %d\n",
- __func__, __LINE__, ret);
- return ret;
-}
-
-/*
- * scif_rma_list_dma_copy_aligned:
- *
- * Traverse all the windows and perform DMA copy.
- */
-static int scif_rma_list_dma_copy_aligned(struct scif_copy_work *work,
- struct dma_chan *chan)
-{
- dma_addr_t src_dma_addr, dst_dma_addr;
- size_t loop_len, remaining_len, tail_len, src_contig_bytes = 0;
- size_t dst_contig_bytes = 0;
- int src_cache_off;
- s64 end_src_offset, end_dst_offset;
- struct scif_window_iter src_win_iter;
- struct scif_window_iter dst_win_iter;
- void *src_virt, *dst_virt;
- struct scif_window *src_window = work->src_window;
- struct scif_window *dst_window = work->dst_window;
- s64 src_offset = work->src_offset, dst_offset = work->dst_offset;
- int ret = 0;
- struct dma_async_tx_descriptor *tx;
- struct dma_device *dev = chan->device;
- dma_cookie_t cookie;
-
- remaining_len = work->len;
- scif_init_window_iter(src_window, &src_win_iter);
- scif_init_window_iter(dst_window, &dst_win_iter);
-
- src_cache_off = src_offset & (L1_CACHE_BYTES - 1);
- if (src_cache_off != 0) {
- /* Head */
- loop_len = L1_CACHE_BYTES - src_cache_off;
- loop_len = min(loop_len, remaining_len);
- src_dma_addr = __scif_off_to_dma_addr(src_window, src_offset);
- dst_dma_addr = __scif_off_to_dma_addr(dst_window, dst_offset);
- if (src_window->type == SCIF_WINDOW_SELF)
- src_virt = _get_local_va(src_offset, src_window,
- loop_len);
- else
- src_virt = ioremap_remote(src_offset, src_window,
- loop_len,
- work->remote_dev, NULL);
- if (!src_virt)
- return -ENOMEM;
- if (dst_window->type == SCIF_WINDOW_SELF)
- dst_virt = _get_local_va(dst_offset, dst_window,
- loop_len);
- else
- dst_virt = ioremap_remote(dst_offset, dst_window,
- loop_len,
- work->remote_dev, NULL);
- if (!dst_virt) {
- if (src_window->type != SCIF_WINDOW_SELF)
- iounmap_remote(src_virt, loop_len, work);
- return -ENOMEM;
- }
- if (src_window->type == SCIF_WINDOW_SELF)
- scif_unaligned_cpy_toio(dst_virt, src_virt, loop_len,
- remaining_len == loop_len ?
- work->ordered : false);
- else
- scif_unaligned_cpy_fromio(dst_virt, src_virt, loop_len,
- remaining_len == loop_len ?
- work->ordered : false);
- if (src_window->type != SCIF_WINDOW_SELF)
- iounmap_remote(src_virt, loop_len, work);
- if (dst_window->type != SCIF_WINDOW_SELF)
- iounmap_remote(dst_virt, loop_len, work);
- src_offset += loop_len;
- dst_offset += loop_len;
- remaining_len -= loop_len;
- }
-
- end_src_offset = src_window->offset +
- (src_window->nr_pages << PAGE_SHIFT);
- end_dst_offset = dst_window->offset +
- (dst_window->nr_pages << PAGE_SHIFT);
- tail_len = remaining_len & (L1_CACHE_BYTES - 1);
- remaining_len -= tail_len;
- while (remaining_len) {
- if (src_offset == end_src_offset) {
- src_window = list_next_entry(src_window, list);
- end_src_offset = src_window->offset +
- (src_window->nr_pages << PAGE_SHIFT);
- scif_init_window_iter(src_window, &src_win_iter);
- }
- if (dst_offset == end_dst_offset) {
- dst_window = list_next_entry(dst_window, list);
- end_dst_offset = dst_window->offset +
- (dst_window->nr_pages << PAGE_SHIFT);
- scif_init_window_iter(dst_window, &dst_win_iter);
- }
-
- /* compute dma addresses for transfer */
- src_dma_addr = scif_off_to_dma_addr(src_window, src_offset,
- &src_contig_bytes,
- &src_win_iter);
- dst_dma_addr = scif_off_to_dma_addr(dst_window, dst_offset,
- &dst_contig_bytes,
- &dst_win_iter);
- loop_len = min(src_contig_bytes, dst_contig_bytes);
- loop_len = min(loop_len, remaining_len);
- if (work->ordered && !tail_len &&
- !(remaining_len - loop_len)) {
- /*
- * Break up the last chunk of the transfer into two
- * steps. if there is no tail to gurantee DMA ordering.
- * Passing SCIF_DMA_POLLING inserts a status update
- * descriptor in step 1 which acts as a double sided
- * synchronization fence for the DMA engine to ensure
- * that the last cache line in step 2 is updated last.
- */
- /* Step 1) DMA: Body Length - L1_CACHE_BYTES. */
- tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
- src_dma_addr,
- loop_len -
- L1_CACHE_BYTES,
- DMA_PREP_FENCE);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- dma_async_issue_pending(chan);
- src_offset += (loop_len - L1_CACHE_BYTES);
- dst_offset += (loop_len - L1_CACHE_BYTES);
- src_dma_addr += (loop_len - L1_CACHE_BYTES);
- dst_dma_addr += (loop_len - L1_CACHE_BYTES);
- remaining_len -= (loop_len - L1_CACHE_BYTES);
- loop_len = remaining_len;
-
- /* Step 2) DMA: L1_CACHE_BYTES */
- tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
- src_dma_addr,
- loop_len, 0);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- dma_async_issue_pending(chan);
- } else {
- tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
- src_dma_addr,
- loop_len, 0);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- dma_async_issue_pending(chan);
- }
- src_offset += loop_len;
- dst_offset += loop_len;
- remaining_len -= loop_len;
- }
- remaining_len = tail_len;
- if (remaining_len) {
- loop_len = remaining_len;
- if (src_offset == end_src_offset)
- src_window = list_next_entry(src_window, list);
- if (dst_offset == end_dst_offset)
- dst_window = list_next_entry(dst_window, list);
-
- src_dma_addr = __scif_off_to_dma_addr(src_window, src_offset);
- dst_dma_addr = __scif_off_to_dma_addr(dst_window, dst_offset);
- /*
- * The CPU copy for the tail bytes must be initiated only once
- * previous DMA transfers for this endpoint have completed to
- * guarantee ordering.
- */
- if (work->ordered) {
- struct scif_dev *rdev = work->remote_dev;
-
- ret = scif_drain_dma_poll(rdev->sdev, chan);
- if (ret)
- return ret;
- }
- if (src_window->type == SCIF_WINDOW_SELF)
- src_virt = _get_local_va(src_offset, src_window,
- loop_len);
- else
- src_virt = ioremap_remote(src_offset, src_window,
- loop_len,
- work->remote_dev, NULL);
- if (!src_virt)
- return -ENOMEM;
-
- if (dst_window->type == SCIF_WINDOW_SELF)
- dst_virt = _get_local_va(dst_offset, dst_window,
- loop_len);
- else
- dst_virt = ioremap_remote(dst_offset, dst_window,
- loop_len,
- work->remote_dev, NULL);
- if (!dst_virt) {
- if (src_window->type != SCIF_WINDOW_SELF)
- iounmap_remote(src_virt, loop_len, work);
- return -ENOMEM;
- }
-
- if (src_window->type == SCIF_WINDOW_SELF)
- scif_unaligned_cpy_toio(dst_virt, src_virt, loop_len,
- work->ordered);
- else
- scif_unaligned_cpy_fromio(dst_virt, src_virt,
- loop_len, work->ordered);
- if (src_window->type != SCIF_WINDOW_SELF)
- iounmap_remote(src_virt, loop_len, work);
-
- if (dst_window->type != SCIF_WINDOW_SELF)
- iounmap_remote(dst_virt, loop_len, work);
- remaining_len -= loop_len;
- }
- return ret;
-err:
- dev_err(scif_info.mdev.this_device,
- "%s %d Desc Prog Failed ret %d\n",
- __func__, __LINE__, ret);
- return ret;
-}
-
-/*
- * scif_rma_list_cpu_copy:
- *
- * Traverse all the windows and perform CPU copy.
- */
-static int scif_rma_list_cpu_copy(struct scif_copy_work *work)
-{
- void *src_virt, *dst_virt;
- size_t loop_len, remaining_len;
- int src_page_off, dst_page_off;
- s64 src_offset = work->src_offset, dst_offset = work->dst_offset;
- struct scif_window *src_window = work->src_window;
- struct scif_window *dst_window = work->dst_window;
- s64 end_src_offset, end_dst_offset;
- int ret = 0;
- struct scif_window_iter src_win_iter;
- struct scif_window_iter dst_win_iter;
-
- remaining_len = work->len;
-
- scif_init_window_iter(src_window, &src_win_iter);
- scif_init_window_iter(dst_window, &dst_win_iter);
- while (remaining_len) {
- src_page_off = src_offset & ~PAGE_MASK;
- dst_page_off = dst_offset & ~PAGE_MASK;
- loop_len = min(PAGE_SIZE -
- max(src_page_off, dst_page_off),
- remaining_len);
-
- if (src_window->type == SCIF_WINDOW_SELF)
- src_virt = _get_local_va(src_offset, src_window,
- loop_len);
- else
- src_virt = ioremap_remote(src_offset, src_window,
- loop_len,
- work->remote_dev,
- &src_win_iter);
- if (!src_virt) {
- ret = -ENOMEM;
- goto error;
- }
-
- if (dst_window->type == SCIF_WINDOW_SELF)
- dst_virt = _get_local_va(dst_offset, dst_window,
- loop_len);
- else
- dst_virt = ioremap_remote(dst_offset, dst_window,
- loop_len,
- work->remote_dev,
- &dst_win_iter);
- if (!dst_virt) {
- if (src_window->type == SCIF_WINDOW_PEER)
- iounmap_remote(src_virt, loop_len, work);
- ret = -ENOMEM;
- goto error;
- }
-
- if (work->loopback) {
- memcpy(dst_virt, src_virt, loop_len);
- } else {
- if (src_window->type == SCIF_WINDOW_SELF)
- memcpy_toio((void __iomem __force *)dst_virt,
- src_virt, loop_len);
- else
- memcpy_fromio(dst_virt,
- (void __iomem __force *)src_virt,
- loop_len);
- }
- if (src_window->type == SCIF_WINDOW_PEER)
- iounmap_remote(src_virt, loop_len, work);
-
- if (dst_window->type == SCIF_WINDOW_PEER)
- iounmap_remote(dst_virt, loop_len, work);
-
- src_offset += loop_len;
- dst_offset += loop_len;
- remaining_len -= loop_len;
- if (remaining_len) {
- end_src_offset = src_window->offset +
- (src_window->nr_pages << PAGE_SHIFT);
- end_dst_offset = dst_window->offset +
- (dst_window->nr_pages << PAGE_SHIFT);
- if (src_offset == end_src_offset) {
- src_window = list_next_entry(src_window, list);
- scif_init_window_iter(src_window,
- &src_win_iter);
- }
- if (dst_offset == end_dst_offset) {
- dst_window = list_next_entry(dst_window, list);
- scif_init_window_iter(dst_window,
- &dst_win_iter);
- }
- }
- }
-error:
- return ret;
-}
-
-static int scif_rma_list_dma_copy_wrapper(struct scif_endpt *epd,
- struct scif_copy_work *work,
- struct dma_chan *chan, off_t loffset)
-{
- int src_cache_off, dst_cache_off;
- s64 src_offset = work->src_offset, dst_offset = work->dst_offset;
- u8 *temp = NULL;
- bool src_local = true;
- struct scif_dma_comp_cb *comp_cb;
- int err;
-
- if (is_dma_copy_aligned(chan->device, 1, 1, 1))
- return _scif_rma_list_dma_copy_aligned(work, chan);
-
- src_cache_off = src_offset & (L1_CACHE_BYTES - 1);
- dst_cache_off = dst_offset & (L1_CACHE_BYTES - 1);
-
- if (dst_cache_off == src_cache_off)
- return scif_rma_list_dma_copy_aligned(work, chan);
-
- if (work->loopback)
- return scif_rma_list_cpu_copy(work);
- src_local = work->src_window->type == SCIF_WINDOW_SELF;
-
- /* Allocate dma_completion cb */
- comp_cb = kzalloc(sizeof(*comp_cb), GFP_KERNEL);
- if (!comp_cb)
- goto error;
-
- work->comp_cb = comp_cb;
- comp_cb->cb_cookie = comp_cb;
- comp_cb->dma_completion_func = &scif_rma_completion_cb;
-
- if (work->len + (L1_CACHE_BYTES << 1) < SCIF_KMEM_UNALIGNED_BUF_SIZE) {
- comp_cb->is_cache = false;
- /* Allocate padding bytes to align to a cache line */
- temp = kmalloc(work->len + (L1_CACHE_BYTES << 1),
- GFP_KERNEL);
- if (!temp)
- goto free_comp_cb;
- comp_cb->temp_buf_to_free = temp;
- /* kmalloc(..) does not guarantee cache line alignment */
- if (!IS_ALIGNED((u64)temp, L1_CACHE_BYTES))
- temp = PTR_ALIGN(temp, L1_CACHE_BYTES);
- } else {
- comp_cb->is_cache = true;
- temp = kmem_cache_alloc(unaligned_cache, GFP_KERNEL);
- if (!temp)
- goto free_comp_cb;
- comp_cb->temp_buf_to_free = temp;
- }
-
- if (src_local) {
- temp += dst_cache_off;
- scif_rma_local_cpu_copy(work->src_offset, work->src_window,
- temp, work->len, true);
- } else {
- comp_cb->dst_window = work->dst_window;
- comp_cb->dst_offset = work->dst_offset;
- work->src_offset = work->src_offset - src_cache_off;
- comp_cb->len = work->len;
- work->len = ALIGN(work->len + src_cache_off, L1_CACHE_BYTES);
- comp_cb->header_padding = src_cache_off;
- }
- comp_cb->temp_buf = temp;
-
- err = scif_map_single(&comp_cb->temp_phys, temp,
- work->remote_dev, SCIF_KMEM_UNALIGNED_BUF_SIZE);
- if (err)
- goto free_temp_buf;
- comp_cb->sdev = work->remote_dev;
- if (scif_rma_list_dma_copy_unaligned(work, temp, chan, src_local) < 0)
- goto free_temp_buf;
- if (!src_local)
- work->fence_type = SCIF_DMA_INTR;
- return 0;
-free_temp_buf:
- if (comp_cb->is_cache)
- kmem_cache_free(unaligned_cache, comp_cb->temp_buf_to_free);
- else
- kfree(comp_cb->temp_buf_to_free);
-free_comp_cb:
- kfree(comp_cb);
-error:
- return -ENOMEM;
-}
-
-/**
- * scif_rma_copy:
- * @epd: end point descriptor.
- * @loffset: offset in local registered address space to/from which to copy
- * @addr: user virtual address to/from which to copy
- * @len: length of range to copy
- * @roffset: offset in remote registered address space to/from which to copy
- * @flags: flags
- * @dir: LOCAL->REMOTE or vice versa.
- * @last_chunk: true if this is the last chunk of a larger transfer
- *
- * Validate parameters, check if src/dst registered ranges requested for copy
- * are valid and initiate either CPU or DMA copy.
- */
-static int scif_rma_copy(scif_epd_t epd, off_t loffset, unsigned long addr,
- size_t len, off_t roffset, int flags,
- enum scif_rma_dir dir, bool last_chunk)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct scif_rma_req remote_req;
- struct scif_rma_req req;
- struct scif_window *local_window = NULL;
- struct scif_window *remote_window = NULL;
- struct scif_copy_work copy_work;
- bool loopback;
- int err = 0;
- struct dma_chan *chan;
- struct scif_mmu_notif *mmn = NULL;
- bool cache = false;
- struct device *spdev;
-
- err = scif_verify_epd(ep);
- if (err)
- return err;
-
- if (flags && !(flags & (SCIF_RMA_USECPU | SCIF_RMA_USECACHE |
- SCIF_RMA_SYNC | SCIF_RMA_ORDERED)))
- return -EINVAL;
-
- loopback = scifdev_self(ep->remote_dev) ? true : false;
- copy_work.fence_type = ((flags & SCIF_RMA_SYNC) && last_chunk) ?
- SCIF_DMA_POLL : 0;
- copy_work.ordered = !!((flags & SCIF_RMA_ORDERED) && last_chunk);
-
- /* Use CPU for Mgmt node <-> Mgmt node copies */
- if (loopback && scif_is_mgmt_node()) {
- flags |= SCIF_RMA_USECPU;
- copy_work.fence_type = 0x0;
- }
-
- cache = scif_is_set_reg_cache(flags);
-
- remote_req.out_window = &remote_window;
- remote_req.offset = roffset;
- remote_req.nr_bytes = len;
- /*
- * If transfer is from local to remote then the remote window
- * must be writeable and vice versa.
- */
- remote_req.prot = dir == SCIF_LOCAL_TO_REMOTE ? VM_WRITE : VM_READ;
- remote_req.type = SCIF_WINDOW_PARTIAL;
- remote_req.head = &ep->rma_info.remote_reg_list;
-
- spdev = scif_get_peer_dev(ep->remote_dev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- return err;
- }
-
- if (addr && cache) {
- mutex_lock(&ep->rma_info.mmn_lock);
- mmn = scif_find_mmu_notifier(current->mm, &ep->rma_info);
- if (!mmn)
- mmn = scif_add_mmu_notifier(current->mm, ep);
- mutex_unlock(&ep->rma_info.mmn_lock);
- if (IS_ERR(mmn)) {
- scif_put_peer_dev(spdev);
- return PTR_ERR(mmn);
- }
- cache = cache && !scif_rma_tc_can_cache(ep, len);
- }
- mutex_lock(&ep->rma_info.rma_lock);
- if (addr) {
- req.out_window = &local_window;
- req.nr_bytes = ALIGN(len + (addr & ~PAGE_MASK),
- PAGE_SIZE);
- req.va_for_temp = addr & PAGE_MASK;
- req.prot = (dir == SCIF_LOCAL_TO_REMOTE ?
- VM_READ : VM_WRITE | VM_READ);
- /* Does a valid local window exist? */
- if (mmn) {
- spin_lock(&ep->rma_info.tc_lock);
- req.head = &mmn->tc_reg_list;
- err = scif_query_tcw(ep, &req);
- spin_unlock(&ep->rma_info.tc_lock);
- }
- if (!mmn || err) {
- err = scif_register_temp(epd, req.va_for_temp,
- req.nr_bytes, req.prot,
- &loffset, &local_window);
- if (err) {
- mutex_unlock(&ep->rma_info.rma_lock);
- goto error;
- }
- if (!cache)
- goto skip_cache;
- atomic_inc(&ep->rma_info.tcw_refcount);
- atomic_add_return(local_window->nr_pages,
- &ep->rma_info.tcw_total_pages);
- if (mmn) {
- spin_lock(&ep->rma_info.tc_lock);
- scif_insert_tcw(local_window,
- &mmn->tc_reg_list);
- spin_unlock(&ep->rma_info.tc_lock);
- }
- }
-skip_cache:
- loffset = local_window->offset +
- (addr - local_window->va_for_temp);
- } else {
- req.out_window = &local_window;
- req.offset = loffset;
- /*
- * If transfer is from local to remote then the self window
- * must be readable and vice versa.
- */
- req.prot = dir == SCIF_LOCAL_TO_REMOTE ? VM_READ : VM_WRITE;
- req.nr_bytes = len;
- req.type = SCIF_WINDOW_PARTIAL;
- req.head = &ep->rma_info.reg_list;
- /* Does a valid local window exist? */
- err = scif_query_window(&req);
- if (err) {
- mutex_unlock(&ep->rma_info.rma_lock);
- goto error;
- }
- }
-
- /* Does a valid remote window exist? */
- err = scif_query_window(&remote_req);
- if (err) {
- mutex_unlock(&ep->rma_info.rma_lock);
- goto error;
- }
-
- /*
- * Prepare copy_work for submitting work to the DMA kernel thread
- * or CPU copy routine.
- */
- copy_work.len = len;
- copy_work.loopback = loopback;
- copy_work.remote_dev = ep->remote_dev;
- if (dir == SCIF_LOCAL_TO_REMOTE) {
- copy_work.src_offset = loffset;
- copy_work.src_window = local_window;
- copy_work.dst_offset = roffset;
- copy_work.dst_window = remote_window;
- } else {
- copy_work.src_offset = roffset;
- copy_work.src_window = remote_window;
- copy_work.dst_offset = loffset;
- copy_work.dst_window = local_window;
- }
-
- if (flags & SCIF_RMA_USECPU) {
- scif_rma_list_cpu_copy(©_work);
- } else {
- chan = ep->rma_info.dma_chan;
- err = scif_rma_list_dma_copy_wrapper(epd, ©_work,
- chan, loffset);
- }
- if (addr && !cache)
- atomic_inc(&ep->rma_info.tw_refcount);
-
- mutex_unlock(&ep->rma_info.rma_lock);
-
- if (last_chunk) {
- struct scif_dev *rdev = ep->remote_dev;
-
- if (copy_work.fence_type == SCIF_DMA_POLL)
- err = scif_drain_dma_poll(rdev->sdev,
- ep->rma_info.dma_chan);
- else if (copy_work.fence_type == SCIF_DMA_INTR)
- err = scif_drain_dma_intr(rdev->sdev,
- ep->rma_info.dma_chan);
- }
-
- if (addr && !cache)
- scif_queue_for_cleanup(local_window, &scif_info.rma);
- scif_put_peer_dev(spdev);
- return err;
-error:
- if (err) {
- if (addr && local_window && !cache)
- scif_destroy_window(ep, local_window);
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d len 0x%lx\n",
- __func__, __LINE__, err, len);
- }
- scif_put_peer_dev(spdev);
- return err;
-}
-
-int scif_readfrom(scif_epd_t epd, off_t loffset, size_t len,
- off_t roffset, int flags)
-{
- int err;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI readfrom: ep %p loffset 0x%lx len 0x%lx offset 0x%lx flags 0x%x\n",
- epd, loffset, len, roffset, flags);
- if (scif_unaligned(loffset, roffset)) {
- while (len > SCIF_MAX_UNALIGNED_BUF_SIZE) {
- err = scif_rma_copy(epd, loffset, 0x0,
- SCIF_MAX_UNALIGNED_BUF_SIZE,
- roffset, flags,
- SCIF_REMOTE_TO_LOCAL, false);
- if (err)
- goto readfrom_err;
- loffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
- roffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
- len -= SCIF_MAX_UNALIGNED_BUF_SIZE;
- }
- }
- err = scif_rma_copy(epd, loffset, 0x0, len,
- roffset, flags, SCIF_REMOTE_TO_LOCAL, true);
-readfrom_err:
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_readfrom);
-
-int scif_writeto(scif_epd_t epd, off_t loffset, size_t len,
- off_t roffset, int flags)
-{
- int err;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI writeto: ep %p loffset 0x%lx len 0x%lx roffset 0x%lx flags 0x%x\n",
- epd, loffset, len, roffset, flags);
- if (scif_unaligned(loffset, roffset)) {
- while (len > SCIF_MAX_UNALIGNED_BUF_SIZE) {
- err = scif_rma_copy(epd, loffset, 0x0,
- SCIF_MAX_UNALIGNED_BUF_SIZE,
- roffset, flags,
- SCIF_LOCAL_TO_REMOTE, false);
- if (err)
- goto writeto_err;
- loffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
- roffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
- len -= SCIF_MAX_UNALIGNED_BUF_SIZE;
- }
- }
- err = scif_rma_copy(epd, loffset, 0x0, len,
- roffset, flags, SCIF_LOCAL_TO_REMOTE, true);
-writeto_err:
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_writeto);
-
-int scif_vreadfrom(scif_epd_t epd, void *addr, size_t len,
- off_t roffset, int flags)
-{
- int err;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI vreadfrom: ep %p addr %p len 0x%lx roffset 0x%lx flags 0x%x\n",
- epd, addr, len, roffset, flags);
- if (scif_unaligned((off_t __force)addr, roffset)) {
- if (len > SCIF_MAX_UNALIGNED_BUF_SIZE)
- flags &= ~SCIF_RMA_USECACHE;
-
- while (len > SCIF_MAX_UNALIGNED_BUF_SIZE) {
- err = scif_rma_copy(epd, 0, (u64)addr,
- SCIF_MAX_UNALIGNED_BUF_SIZE,
- roffset, flags,
- SCIF_REMOTE_TO_LOCAL, false);
- if (err)
- goto vreadfrom_err;
- addr += SCIF_MAX_UNALIGNED_BUF_SIZE;
- roffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
- len -= SCIF_MAX_UNALIGNED_BUF_SIZE;
- }
- }
- err = scif_rma_copy(epd, 0, (u64)addr, len,
- roffset, flags, SCIF_REMOTE_TO_LOCAL, true);
-vreadfrom_err:
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_vreadfrom);
-
-int scif_vwriteto(scif_epd_t epd, void *addr, size_t len,
- off_t roffset, int flags)
-{
- int err;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI vwriteto: ep %p addr %p len 0x%lx roffset 0x%lx flags 0x%x\n",
- epd, addr, len, roffset, flags);
- if (scif_unaligned((off_t __force)addr, roffset)) {
- if (len > SCIF_MAX_UNALIGNED_BUF_SIZE)
- flags &= ~SCIF_RMA_USECACHE;
-
- while (len > SCIF_MAX_UNALIGNED_BUF_SIZE) {
- err = scif_rma_copy(epd, 0, (u64)addr,
- SCIF_MAX_UNALIGNED_BUF_SIZE,
- roffset, flags,
- SCIF_LOCAL_TO_REMOTE, false);
- if (err)
- goto vwriteto_err;
- addr += SCIF_MAX_UNALIGNED_BUF_SIZE;
- roffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
- len -= SCIF_MAX_UNALIGNED_BUF_SIZE;
- }
- }
- err = scif_rma_copy(epd, 0, (u64)addr, len,
- roffset, flags, SCIF_LOCAL_TO_REMOTE, true);
-vwriteto_err:
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_vwriteto);
diff --git a/drivers/misc/mic/scif/scif_epd.c b/drivers/misc/mic/scif/scif_epd.c
deleted file mode 100644
index 426687f..0000000
--- a/drivers/misc/mic/scif/scif_epd.c
+++ /dev/null
@@ -1,357 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-#include "scif_map.h"
-
-void scif_cleanup_ep_qp(struct scif_endpt *ep)
-{
- struct scif_qp *qp = ep->qp_info.qp;
-
- if (qp->outbound_q.rb_base) {
- scif_iounmap((void *)qp->outbound_q.rb_base,
- qp->outbound_q.size, ep->remote_dev);
- qp->outbound_q.rb_base = NULL;
- }
- if (qp->remote_qp) {
- scif_iounmap((void *)qp->remote_qp,
- sizeof(struct scif_qp), ep->remote_dev);
- qp->remote_qp = NULL;
- }
- if (qp->local_qp) {
- scif_unmap_single(qp->local_qp, ep->remote_dev,
- sizeof(struct scif_qp));
- qp->local_qp = 0x0;
- }
- if (qp->local_buf) {
- scif_unmap_single(qp->local_buf, ep->remote_dev,
- SCIF_ENDPT_QP_SIZE);
- qp->local_buf = 0;
- }
-}
-
-void scif_teardown_ep(void *endpt)
-{
- struct scif_endpt *ep = endpt;
- struct scif_qp *qp = ep->qp_info.qp;
-
- if (qp) {
- spin_lock(&ep->lock);
- scif_cleanup_ep_qp(ep);
- spin_unlock(&ep->lock);
- kfree(qp->inbound_q.rb_base);
- kfree(qp);
- }
-}
-
-/*
- * Enqueue the endpoint to the zombie list for cleanup.
- * The endpoint should not be accessed once this API returns.
- */
-void scif_add_epd_to_zombie_list(struct scif_endpt *ep, bool eplock_held)
-{
- if (!eplock_held)
- mutex_lock(&scif_info.eplock);
- spin_lock(&ep->lock);
- ep->state = SCIFEP_ZOMBIE;
- spin_unlock(&ep->lock);
- list_add_tail(&ep->list, &scif_info.zombie);
- scif_info.nr_zombies++;
- if (!eplock_held)
- mutex_unlock(&scif_info.eplock);
- schedule_work(&scif_info.misc_work);
-}
-
-static struct scif_endpt *scif_find_listen_ep(u16 port)
-{
- struct scif_endpt *ep = NULL;
- struct list_head *pos, *tmpq;
-
- mutex_lock(&scif_info.eplock);
- list_for_each_safe(pos, tmpq, &scif_info.listen) {
- ep = list_entry(pos, struct scif_endpt, list);
- if (ep->port.port == port) {
- mutex_unlock(&scif_info.eplock);
- return ep;
- }
- }
- mutex_unlock(&scif_info.eplock);
- return NULL;
-}
-
-void scif_cleanup_zombie_epd(void)
-{
- struct list_head *pos, *tmpq;
- struct scif_endpt *ep;
-
- mutex_lock(&scif_info.eplock);
- list_for_each_safe(pos, tmpq, &scif_info.zombie) {
- ep = list_entry(pos, struct scif_endpt, list);
- if (scif_rma_ep_can_uninit(ep)) {
- list_del(pos);
- scif_info.nr_zombies--;
- put_iova_domain(&ep->rma_info.iovad);
- kfree(ep);
- }
- }
- mutex_unlock(&scif_info.eplock);
-}
-
-/**
- * scif_cnctreq() - Respond to SCIF_CNCT_REQ interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * This message is initiated by the remote node to request a connection
- * to the local node. This function looks for an end point in the
- * listen state on the requested port id.
- *
- * If it finds a listening port it places the connect request on the
- * listening end points queue and wakes up any pending accept calls.
- *
- * If it does not find a listening end point it sends a connection
- * reject message to the remote node.
- */
-void scif_cnctreq(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = NULL;
- struct scif_conreq *conreq;
-
- conreq = kmalloc(sizeof(*conreq), GFP_KERNEL);
- if (!conreq)
- /* Lack of resources so reject the request. */
- goto conreq_sendrej;
-
- ep = scif_find_listen_ep(msg->dst.port);
- if (!ep)
- /* Send reject due to no listening ports */
- goto conreq_sendrej_free;
- else
- spin_lock(&ep->lock);
-
- if (ep->backlog <= ep->conreqcnt) {
- /* Send reject due to too many pending requests */
- spin_unlock(&ep->lock);
- goto conreq_sendrej_free;
- }
-
- conreq->msg = *msg;
- list_add_tail(&conreq->list, &ep->conlist);
- ep->conreqcnt++;
- wake_up_interruptible(&ep->conwq);
- spin_unlock(&ep->lock);
- return;
-
-conreq_sendrej_free:
- kfree(conreq);
-conreq_sendrej:
- msg->uop = SCIF_CNCT_REJ;
- scif_nodeqp_send(&scif_dev[msg->src.node], msg);
-}
-
-/**
- * scif_cnctgnt() - Respond to SCIF_CNCT_GNT interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * An accept() on the remote node has occurred and sent this message
- * to indicate success. Place the end point in the MAPPING state and
- * save the remote nodes memory information. Then wake up the connect
- * request so it can finish.
- */
-void scif_cnctgnt(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
- spin_lock(&ep->lock);
- if (SCIFEP_CONNECTING == ep->state) {
- ep->peer.node = msg->src.node;
- ep->peer.port = msg->src.port;
- ep->qp_info.gnt_pld = msg->payload[1];
- ep->remote_ep = msg->payload[2];
- ep->state = SCIFEP_MAPPING;
-
- wake_up(&ep->conwq);
- }
- spin_unlock(&ep->lock);
-}
-
-/**
- * scif_cnctgnt_ack() - Respond to SCIF_CNCT_GNTACK interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The remote connection request has finished mapping the local memory.
- * Place the connection in the connected state and wake up the pending
- * accept() call.
- */
-void scif_cnctgnt_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
- mutex_lock(&scif_info.connlock);
- spin_lock(&ep->lock);
- /* New ep is now connected with all resources set. */
- ep->state = SCIFEP_CONNECTED;
- list_add_tail(&ep->list, &scif_info.connected);
- wake_up(&ep->conwq);
- spin_unlock(&ep->lock);
- mutex_unlock(&scif_info.connlock);
-}
-
-/**
- * scif_cnctgnt_nack() - Respond to SCIF_CNCT_GNTNACK interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The remote connection request failed to map the local memory it was sent.
- * Place the end point in the CLOSING state to indicate it and wake up
- * the pending accept();
- */
-void scif_cnctgnt_nack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
- spin_lock(&ep->lock);
- ep->state = SCIFEP_CLOSING;
- wake_up(&ep->conwq);
- spin_unlock(&ep->lock);
-}
-
-/**
- * scif_cnctrej() - Respond to SCIF_CNCT_REJ interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The remote end has rejected the connection request. Set the end
- * point back to the bound state and wake up the pending connect().
- */
-void scif_cnctrej(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
- spin_lock(&ep->lock);
- if (SCIFEP_CONNECTING == ep->state) {
- ep->state = SCIFEP_BOUND;
- wake_up(&ep->conwq);
- }
- spin_unlock(&ep->lock);
-}
-
-/**
- * scif_discnct() - Respond to SCIF_DISCNCT interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The remote node has indicated close() has been called on its end
- * point. Remove the local end point from the connected list, set its
- * state to disconnected and ensure accesses to the remote node are
- * shutdown.
- *
- * When all accesses to the remote end have completed then send a
- * DISCNT_ACK to indicate it can remove its resources and complete
- * the close routine.
- */
-void scif_discnct(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = NULL;
- struct scif_endpt *tmpep;
- struct list_head *pos, *tmpq;
-
- mutex_lock(&scif_info.connlock);
- list_for_each_safe(pos, tmpq, &scif_info.connected) {
- tmpep = list_entry(pos, struct scif_endpt, list);
- /*
- * The local ep may have sent a disconnect and and been closed
- * due to a message response time out. It may have been
- * allocated again and formed a new connection so we want to
- * check if the remote ep matches
- */
- if (((u64)tmpep == msg->payload[1]) &&
- ((u64)tmpep->remote_ep == msg->payload[0])) {
- list_del(pos);
- ep = tmpep;
- spin_lock(&ep->lock);
- break;
- }
- }
-
- /*
- * If the terminated end is not found then this side started closing
- * before the other side sent the disconnect. If so the ep will no
- * longer be on the connected list. Regardless the other side
- * needs to be acked to let it know close is complete.
- */
- if (!ep) {
- mutex_unlock(&scif_info.connlock);
- goto discnct_ack;
- }
-
- ep->state = SCIFEP_DISCONNECTED;
- list_add_tail(&ep->list, &scif_info.disconnected);
-
- wake_up_interruptible(&ep->sendwq);
- wake_up_interruptible(&ep->recvwq);
- spin_unlock(&ep->lock);
- mutex_unlock(&scif_info.connlock);
-
-discnct_ack:
- msg->uop = SCIF_DISCNT_ACK;
- scif_nodeqp_send(&scif_dev[msg->src.node], msg);
-}
-
-/**
- * scif_discnct_ack() - Respond to SCIF_DISCNT_ACK interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Remote side has indicated it has not more references to local resources
- */
-void scif_discnt_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
- spin_lock(&ep->lock);
- ep->state = SCIFEP_DISCONNECTED;
- spin_unlock(&ep->lock);
- complete(&ep->discon);
-}
-
-/**
- * scif_clientsend() - Respond to SCIF_CLIENT_SEND interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Remote side is confirming send or receive interrupt handling is complete.
- */
-void scif_clientsend(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
- spin_lock(&ep->lock);
- if (SCIFEP_CONNECTED == ep->state)
- wake_up_interruptible(&ep->recvwq);
- spin_unlock(&ep->lock);
-}
-
-/**
- * scif_clientrcvd() - Respond to SCIF_CLIENT_RCVD interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Remote side is confirming send or receive interrupt handling is complete.
- */
-void scif_clientrcvd(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
- spin_lock(&ep->lock);
- if (SCIFEP_CONNECTED == ep->state)
- wake_up_interruptible(&ep->sendwq);
- spin_unlock(&ep->lock);
-}
diff --git a/drivers/misc/mic/scif/scif_epd.h b/drivers/misc/mic/scif/scif_epd.h
deleted file mode 100644
index 0b9dfe1..0000000
--- a/drivers/misc/mic/scif/scif_epd.h
+++ /dev/null
@@ -1,200 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#ifndef SCIF_EPD_H
-#define SCIF_EPD_H
-
-#include <linux/delay.h>
-#include <linux/scif.h>
-#include <linux/scif_ioctl.h>
-
-#define SCIF_EPLOCK_HELD true
-
-enum scif_epd_state {
- SCIFEP_UNBOUND,
- SCIFEP_BOUND,
- SCIFEP_LISTENING,
- SCIFEP_CONNECTED,
- SCIFEP_CONNECTING,
- SCIFEP_MAPPING,
- SCIFEP_CLOSING,
- SCIFEP_CLLISTEN,
- SCIFEP_DISCONNECTED,
- SCIFEP_ZOMBIE
-};
-
-/*
- * struct scif_conreq - Data structure added to the connection list.
- *
- * @msg: connection request message received
- * @list: link to list of connection requests
- */
-struct scif_conreq {
- struct scifmsg msg;
- struct list_head list;
-};
-
-/* Size of the RB for the Endpoint QP */
-#define SCIF_ENDPT_QP_SIZE 0x1000
-
-/*
- * scif_endpt_qp_info - SCIF endpoint queue pair
- *
- * @qp - Qpair for this endpoint
- * @qp_offset - DMA address of the QP
- * @gnt_pld - Payload in a SCIF_CNCT_GNT message containing the
- * physical address of the remote_qp.
- */
-struct scif_endpt_qp_info {
- struct scif_qp *qp;
- dma_addr_t qp_offset;
- dma_addr_t gnt_pld;
-};
-
-/*
- * struct scif_endpt - The SCIF endpoint data structure
- *
- * @state: end point state
- * @lock: lock synchronizing access to endpoint fields like state etc
- * @port: self port information
- * @peer: peer port information
- * @backlog: maximum pending connection requests
- * @qp_info: Endpoint QP information for SCIF messaging
- * @remote_dev: scifdev used by this endpt to communicate with remote node.
- * @remote_ep: remote endpoint
- * @conreqcnt: Keep track of number of connection requests.
- * @files: Open file information used to match the id passed in with
- * the flush routine.
- * @conlist: list of connection requests
- * @conwq: waitqueue for connection processing
- * @discon: completion used during disconnection
- * @sendwq: waitqueue used during sending messages
- * @recvwq: waitqueue used during message receipt
- * @sendlock: Synchronize ordering of messages sent
- * @recvlock: Synchronize ordering of messages received
- * @list: link to list of various endpoints like connected, listening etc
- * @li_accept: pending ACCEPTREG
- * @acceptcnt: pending ACCEPTREG cnt
- * @liacceptlist: link to listen accept
- * @miacceptlist: link to uaccept
- * @listenep: associated listen ep
- * @conn_work: Non blocking connect work
- * @conn_port: Connection port
- * @conn_err: Errors during connection
- * @conn_async_state: Async connection
- * @conn_pend_wq: Used by poll while waiting for incoming connections
- * @conn_list: List of async connection requests
- * @rma_info: Information for triggering SCIF RMA and DMA operations
- * @mmu_list: link to list of MMU notifier cleanup work
- * @anon: anonymous file for use in kernel mode scif poll
- */
-struct scif_endpt {
- enum scif_epd_state state;
- spinlock_t lock;
- struct scif_port_id port;
- struct scif_port_id peer;
- int backlog;
- struct scif_endpt_qp_info qp_info;
- struct scif_dev *remote_dev;
- u64 remote_ep;
- int conreqcnt;
- struct files_struct *files;
- struct list_head conlist;
- wait_queue_head_t conwq;
- struct completion discon;
- wait_queue_head_t sendwq;
- wait_queue_head_t recvwq;
- struct mutex sendlock;
- struct mutex recvlock;
- struct list_head list;
- struct list_head li_accept;
- int acceptcnt;
- struct list_head liacceptlist;
- struct list_head miacceptlist;
- struct scif_endpt *listenep;
- struct scif_port_id conn_port;
- int conn_err;
- int conn_async_state;
- wait_queue_head_t conn_pend_wq;
- struct list_head conn_list;
- struct scif_endpt_rma_info rma_info;
- struct list_head mmu_list;
- struct file *anon;
-};
-
-static inline int scifdev_alive(struct scif_endpt *ep)
-{
- return _scifdev_alive(ep->remote_dev);
-}
-
-/*
- * scif_verify_epd:
- * ep: SCIF endpoint
- *
- * Checks several generic error conditions and returns the
- * appropriate error.
- */
-static inline int scif_verify_epd(struct scif_endpt *ep)
-{
- if (ep->state == SCIFEP_DISCONNECTED)
- return -ECONNRESET;
-
- if (ep->state != SCIFEP_CONNECTED)
- return -ENOTCONN;
-
- if (!scifdev_alive(ep))
- return -ENODEV;
-
- return 0;
-}
-
-static inline int scif_anon_inode_getfile(scif_epd_t epd)
-{
- epd->anon = anon_inode_getfile("scif", &scif_anon_fops, NULL, 0);
-
- return PTR_ERR_OR_ZERO(epd->anon);
-}
-
-static inline void scif_anon_inode_fput(scif_epd_t epd)
-{
- if (epd->anon) {
- fput(epd->anon);
- epd->anon = NULL;
- }
-}
-
-void scif_cleanup_zombie_epd(void);
-void scif_teardown_ep(void *endpt);
-void scif_cleanup_ep_qp(struct scif_endpt *ep);
-void scif_add_epd_to_zombie_list(struct scif_endpt *ep, bool eplock_held);
-void scif_get_node_info(void);
-void scif_send_acks(struct scif_dev *dev);
-void scif_conn_handler(struct work_struct *work);
-int scif_rsrv_port(u16 port);
-void scif_get_port(u16 port);
-int scif_get_new_port(void);
-void scif_put_port(u16 port);
-int scif_user_send(scif_epd_t epd, void __user *msg, int len, int flags);
-int scif_user_recv(scif_epd_t epd, void __user *msg, int len, int flags);
-void scif_cnctreq(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_cnctgnt(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_cnctgnt_ack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_cnctgnt_nack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_cnctrej(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_discnct(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_discnt_ack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_clientsend(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_clientrcvd(struct scif_dev *scifdev, struct scifmsg *msg);
-int __scif_connect(scif_epd_t epd, struct scif_port_id *dst, bool non_block);
-int __scif_flush(scif_epd_t epd);
-int scif_mmap(struct vm_area_struct *vma, scif_epd_t epd);
-__poll_t __scif_pollfd(struct file *f, poll_table *wait,
- struct scif_endpt *ep);
-int __scif_pin_pages(void *addr, size_t len, int *out_prot,
- int map_flags, scif_pinned_pages_t *pages);
-#endif /* SCIF_EPD_H */
diff --git a/drivers/misc/mic/scif/scif_fd.c b/drivers/misc/mic/scif/scif_fd.c
deleted file mode 100644
index 3f08646..0000000
--- a/drivers/misc/mic/scif/scif_fd.c
+++ /dev/null
@@ -1,462 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-
-static int scif_fdopen(struct inode *inode, struct file *f)
-{
- struct scif_endpt *priv = scif_open();
-
- if (!priv)
- return -ENOMEM;
- f->private_data = priv;
- return 0;
-}
-
-static int scif_fdclose(struct inode *inode, struct file *f)
-{
- struct scif_endpt *priv = f->private_data;
-
- return scif_close(priv);
-}
-
-static int scif_fdmmap(struct file *f, struct vm_area_struct *vma)
-{
- struct scif_endpt *priv = f->private_data;
-
- return scif_mmap(vma, priv);
-}
-
-static __poll_t scif_fdpoll(struct file *f, poll_table *wait)
-{
- struct scif_endpt *priv = f->private_data;
-
- return __scif_pollfd(f, wait, priv);
-}
-
-static int scif_fdflush(struct file *f, fl_owner_t id)
-{
- struct scif_endpt *ep = f->private_data;
-
- spin_lock(&ep->lock);
- /*
- * The listening endpoint stashes the open file information before
- * waiting for incoming connections. The release callback would never be
- * called if the application closed the endpoint, while waiting for
- * incoming connections from a separate thread since the file descriptor
- * reference count is bumped up in the accept IOCTL. Call the flush
- * routine if the id matches the endpoint open file information so that
- * the listening endpoint can be woken up and the fd released.
- */
- if (ep->files == id)
- __scif_flush(ep);
- spin_unlock(&ep->lock);
- return 0;
-}
-
-static __always_inline void scif_err_debug(int err, const char *str)
-{
- /*
- * ENOTCONN is a common uninteresting error which is
- * flooding debug messages to the console unnecessarily.
- */
- if (err < 0 && err != -ENOTCONN)
- dev_dbg(scif_info.mdev.this_device, "%s err %d\n", str, err);
-}
-
-static long scif_fdioctl(struct file *f, unsigned int cmd, unsigned long arg)
-{
- struct scif_endpt *priv = f->private_data;
- void __user *argp = (void __user *)arg;
- int err = 0;
- struct scifioctl_msg request;
- bool non_block = false;
-
- non_block = !!(f->f_flags & O_NONBLOCK);
-
- switch (cmd) {
- case SCIF_BIND:
- {
- int pn;
-
- if (copy_from_user(&pn, argp, sizeof(pn)))
- return -EFAULT;
-
- pn = scif_bind(priv, pn);
- if (pn < 0)
- return pn;
-
- if (copy_to_user(argp, &pn, sizeof(pn)))
- return -EFAULT;
-
- return 0;
- }
- case SCIF_LISTEN:
- return scif_listen(priv, arg);
- case SCIF_CONNECT:
- {
- struct scifioctl_connect req;
- struct scif_endpt *ep = (struct scif_endpt *)priv;
-
- if (copy_from_user(&req, argp, sizeof(req)))
- return -EFAULT;
-
- err = __scif_connect(priv, &req.peer, non_block);
- if (err < 0)
- return err;
-
- req.self.node = ep->port.node;
- req.self.port = ep->port.port;
-
- if (copy_to_user(argp, &req, sizeof(req)))
- return -EFAULT;
-
- return 0;
- }
- /*
- * Accept is done in two halves. The request ioctl does the basic
- * functionality of accepting the request and returning the information
- * about it including the internal ID of the end point. The register
- * is done with the internal ID on a new file descriptor opened by the
- * requesting process.
- */
- case SCIF_ACCEPTREQ:
- {
- struct scifioctl_accept request;
- scif_epd_t *ep = (scif_epd_t *)&request.endpt;
-
- if (copy_from_user(&request, argp, sizeof(request)))
- return -EFAULT;
-
- err = scif_accept(priv, &request.peer, ep, request.flags);
- if (err < 0)
- return err;
-
- if (copy_to_user(argp, &request, sizeof(request))) {
- scif_close(*ep);
- return -EFAULT;
- }
- /*
- * Add to the list of user mode eps where the second half
- * of the accept is not yet completed.
- */
- mutex_lock(&scif_info.eplock);
- list_add_tail(&((*ep)->miacceptlist), &scif_info.uaccept);
- list_add_tail(&((*ep)->liacceptlist), &priv->li_accept);
- (*ep)->listenep = priv;
- priv->acceptcnt++;
- mutex_unlock(&scif_info.eplock);
-
- return 0;
- }
- case SCIF_ACCEPTREG:
- {
- struct scif_endpt *priv = f->private_data;
- struct scif_endpt *newep;
- struct scif_endpt *lisep;
- struct scif_endpt *fep = NULL;
- struct scif_endpt *tmpep;
- struct list_head *pos, *tmpq;
-
- /* Finally replace the pointer to the accepted endpoint */
- if (copy_from_user(&newep, argp, sizeof(void *)))
- return -EFAULT;
-
- /* Remove form the user accept queue */
- mutex_lock(&scif_info.eplock);
- list_for_each_safe(pos, tmpq, &scif_info.uaccept) {
- tmpep = list_entry(pos,
- struct scif_endpt, miacceptlist);
- if (tmpep == newep) {
- list_del(pos);
- fep = tmpep;
- break;
- }
- }
-
- if (!fep) {
- mutex_unlock(&scif_info.eplock);
- return -ENOENT;
- }
-
- lisep = newep->listenep;
- list_for_each_safe(pos, tmpq, &lisep->li_accept) {
- tmpep = list_entry(pos,
- struct scif_endpt, liacceptlist);
- if (tmpep == newep) {
- list_del(pos);
- lisep->acceptcnt--;
- break;
- }
- }
-
- mutex_unlock(&scif_info.eplock);
-
- /* Free the resources automatically created from the open. */
- scif_anon_inode_fput(priv);
- scif_teardown_ep(priv);
- scif_add_epd_to_zombie_list(priv, !SCIF_EPLOCK_HELD);
- f->private_data = newep;
- return 0;
- }
- case SCIF_SEND:
- {
- struct scif_endpt *priv = f->private_data;
-
- if (copy_from_user(&request, argp,
- sizeof(struct scifioctl_msg))) {
- err = -EFAULT;
- goto send_err;
- }
- err = scif_user_send(priv, (void __user *)request.msg,
- request.len, request.flags);
- if (err < 0)
- goto send_err;
- if (copy_to_user(&
- ((struct scifioctl_msg __user *)argp)->out_len,
- &err, sizeof(err))) {
- err = -EFAULT;
- goto send_err;
- }
- err = 0;
-send_err:
- scif_err_debug(err, "scif_send");
- return err;
- }
- case SCIF_RECV:
- {
- struct scif_endpt *priv = f->private_data;
-
- if (copy_from_user(&request, argp,
- sizeof(struct scifioctl_msg))) {
- err = -EFAULT;
- goto recv_err;
- }
-
- err = scif_user_recv(priv, (void __user *)request.msg,
- request.len, request.flags);
- if (err < 0)
- goto recv_err;
-
- if (copy_to_user(&
- ((struct scifioctl_msg __user *)argp)->out_len,
- &err, sizeof(err))) {
- err = -EFAULT;
- goto recv_err;
- }
- err = 0;
-recv_err:
- scif_err_debug(err, "scif_recv");
- return err;
- }
- case SCIF_GET_NODEIDS:
- {
- struct scifioctl_node_ids node_ids;
- int entries;
- u16 *nodes;
- void __user *unodes, *uself;
- u16 self;
-
- if (copy_from_user(&node_ids, argp, sizeof(node_ids))) {
- err = -EFAULT;
- goto getnodes_err2;
- }
-
- entries = min_t(int, scif_info.maxid, node_ids.len);
- nodes = kmalloc_array(entries, sizeof(u16), GFP_KERNEL);
- if (entries && !nodes) {
- err = -ENOMEM;
- goto getnodes_err2;
- }
- node_ids.len = scif_get_node_ids(nodes, entries, &self);
-
- unodes = (void __user *)node_ids.nodes;
- if (copy_to_user(unodes, nodes, sizeof(u16) * entries)) {
- err = -EFAULT;
- goto getnodes_err1;
- }
-
- uself = (void __user *)node_ids.self;
- if (copy_to_user(uself, &self, sizeof(u16))) {
- err = -EFAULT;
- goto getnodes_err1;
- }
-
- if (copy_to_user(argp, &node_ids, sizeof(node_ids))) {
- err = -EFAULT;
- goto getnodes_err1;
- }
-getnodes_err1:
- kfree(nodes);
-getnodes_err2:
- return err;
- }
- case SCIF_REG:
- {
- struct scif_endpt *priv = f->private_data;
- struct scifioctl_reg reg;
- off_t ret;
-
- if (copy_from_user(®, argp, sizeof(reg))) {
- err = -EFAULT;
- goto reg_err;
- }
- if (reg.flags & SCIF_MAP_KERNEL) {
- err = -EINVAL;
- goto reg_err;
- }
- ret = scif_register(priv, (void *)reg.addr, reg.len,
- reg.offset, reg.prot, reg.flags);
- if (ret < 0) {
- err = (int)ret;
- goto reg_err;
- }
-
- if (copy_to_user(&((struct scifioctl_reg __user *)argp)
- ->out_offset, &ret, sizeof(reg.out_offset))) {
- err = -EFAULT;
- goto reg_err;
- }
- err = 0;
-reg_err:
- scif_err_debug(err, "scif_register");
- return err;
- }
- case SCIF_UNREG:
- {
- struct scif_endpt *priv = f->private_data;
- struct scifioctl_unreg unreg;
-
- if (copy_from_user(&unreg, argp, sizeof(unreg))) {
- err = -EFAULT;
- goto unreg_err;
- }
- err = scif_unregister(priv, unreg.offset, unreg.len);
-unreg_err:
- scif_err_debug(err, "scif_unregister");
- return err;
- }
- case SCIF_READFROM:
- {
- struct scif_endpt *priv = f->private_data;
- struct scifioctl_copy copy;
-
- if (copy_from_user(©, argp, sizeof(copy))) {
- err = -EFAULT;
- goto readfrom_err;
- }
- err = scif_readfrom(priv, copy.loffset, copy.len, copy.roffset,
- copy.flags);
-readfrom_err:
- scif_err_debug(err, "scif_readfrom");
- return err;
- }
- case SCIF_WRITETO:
- {
- struct scif_endpt *priv = f->private_data;
- struct scifioctl_copy copy;
-
- if (copy_from_user(©, argp, sizeof(copy))) {
- err = -EFAULT;
- goto writeto_err;
- }
- err = scif_writeto(priv, copy.loffset, copy.len, copy.roffset,
- copy.flags);
-writeto_err:
- scif_err_debug(err, "scif_writeto");
- return err;
- }
- case SCIF_VREADFROM:
- {
- struct scif_endpt *priv = f->private_data;
- struct scifioctl_copy copy;
-
- if (copy_from_user(©, argp, sizeof(copy))) {
- err = -EFAULT;
- goto vreadfrom_err;
- }
- err = scif_vreadfrom(priv, (void __force *)copy.addr, copy.len,
- copy.roffset, copy.flags);
-vreadfrom_err:
- scif_err_debug(err, "scif_vreadfrom");
- return err;
- }
- case SCIF_VWRITETO:
- {
- struct scif_endpt *priv = f->private_data;
- struct scifioctl_copy copy;
-
- if (copy_from_user(©, argp, sizeof(copy))) {
- err = -EFAULT;
- goto vwriteto_err;
- }
- err = scif_vwriteto(priv, (void __force *)copy.addr, copy.len,
- copy.roffset, copy.flags);
-vwriteto_err:
- scif_err_debug(err, "scif_vwriteto");
- return err;
- }
- case SCIF_FENCE_MARK:
- {
- struct scif_endpt *priv = f->private_data;
- struct scifioctl_fence_mark mark;
- int tmp_mark = 0;
-
- if (copy_from_user(&mark, argp, sizeof(mark))) {
- err = -EFAULT;
- goto fence_mark_err;
- }
- err = scif_fence_mark(priv, mark.flags, &tmp_mark);
- if (err)
- goto fence_mark_err;
- if (copy_to_user((void __user *)mark.mark, &tmp_mark,
- sizeof(tmp_mark))) {
- err = -EFAULT;
- goto fence_mark_err;
- }
-fence_mark_err:
- scif_err_debug(err, "scif_fence_mark");
- return err;
- }
- case SCIF_FENCE_WAIT:
- {
- struct scif_endpt *priv = f->private_data;
-
- err = scif_fence_wait(priv, arg);
- scif_err_debug(err, "scif_fence_wait");
- return err;
- }
- case SCIF_FENCE_SIGNAL:
- {
- struct scif_endpt *priv = f->private_data;
- struct scifioctl_fence_signal signal;
-
- if (copy_from_user(&signal, argp, sizeof(signal))) {
- err = -EFAULT;
- goto fence_signal_err;
- }
-
- err = scif_fence_signal(priv, signal.loff, signal.lval,
- signal.roff, signal.rval, signal.flags);
-fence_signal_err:
- scif_err_debug(err, "scif_fence_signal");
- return err;
- }
- }
- return -EINVAL;
-}
-
-const struct file_operations scif_fops = {
- .open = scif_fdopen,
- .release = scif_fdclose,
- .unlocked_ioctl = scif_fdioctl,
- .mmap = scif_fdmmap,
- .poll = scif_fdpoll,
- .flush = scif_fdflush,
- .owner = THIS_MODULE,
-};
diff --git a/drivers/misc/mic/scif/scif_fence.c b/drivers/misc/mic/scif/scif_fence.c
deleted file mode 100644
index 4fedf61..0000000
--- a/drivers/misc/mic/scif/scif_fence.c
+++ /dev/null
@@ -1,783 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-
-#include "scif_main.h"
-
-/**
- * scif_recv_mark: Handle SCIF_MARK request
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The peer has requested a mark.
- */
-void scif_recv_mark(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
- int mark = 0;
- int err;
-
- err = _scif_fence_mark(ep, &mark);
- if (err)
- msg->uop = SCIF_MARK_NACK;
- else
- msg->uop = SCIF_MARK_ACK;
- msg->payload[0] = ep->remote_ep;
- msg->payload[2] = mark;
- scif_nodeqp_send(ep->remote_dev, msg);
-}
-
-/**
- * scif_recv_mark_resp: Handle SCIF_MARK_(N)ACK messages.
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The peer has responded to a SCIF_MARK message.
- */
-void scif_recv_mark_resp(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
- struct scif_fence_info *fence_req =
- (struct scif_fence_info *)msg->payload[1];
-
- mutex_lock(&ep->rma_info.rma_lock);
- if (msg->uop == SCIF_MARK_ACK) {
- fence_req->state = OP_COMPLETED;
- fence_req->dma_mark = (int)msg->payload[2];
- } else {
- fence_req->state = OP_FAILED;
- }
- mutex_unlock(&ep->rma_info.rma_lock);
- complete(&fence_req->comp);
-}
-
-/**
- * scif_recv_wait: Handle SCIF_WAIT request
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The peer has requested waiting on a fence.
- */
-void scif_recv_wait(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
- struct scif_remote_fence_info *fence;
-
- /*
- * Allocate structure for remote fence information and
- * send a NACK if the allocation failed. The peer will
- * return ENOMEM upon receiving a NACK.
- */
- fence = kmalloc(sizeof(*fence), GFP_KERNEL);
- if (!fence) {
- msg->payload[0] = ep->remote_ep;
- msg->uop = SCIF_WAIT_NACK;
- scif_nodeqp_send(ep->remote_dev, msg);
- return;
- }
-
- /* Prepare the fence request */
- memcpy(&fence->msg, msg, sizeof(struct scifmsg));
- INIT_LIST_HEAD(&fence->list);
-
- /* Insert to the global remote fence request list */
- mutex_lock(&scif_info.fencelock);
- atomic_inc(&ep->rma_info.fence_refcount);
- list_add_tail(&fence->list, &scif_info.fence);
- mutex_unlock(&scif_info.fencelock);
-
- schedule_work(&scif_info.misc_work);
-}
-
-/**
- * scif_recv_wait_resp: Handle SCIF_WAIT_(N)ACK messages.
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The peer has responded to a SCIF_WAIT message.
- */
-void scif_recv_wait_resp(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
- struct scif_fence_info *fence_req =
- (struct scif_fence_info *)msg->payload[1];
-
- mutex_lock(&ep->rma_info.rma_lock);
- if (msg->uop == SCIF_WAIT_ACK)
- fence_req->state = OP_COMPLETED;
- else
- fence_req->state = OP_FAILED;
- mutex_unlock(&ep->rma_info.rma_lock);
- complete(&fence_req->comp);
-}
-
-/**
- * scif_recv_sig_local: Handle SCIF_SIG_LOCAL request
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The peer has requested a signal on a local offset.
- */
-void scif_recv_sig_local(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
- int err;
-
- err = scif_prog_signal(ep, msg->payload[1], msg->payload[2],
- SCIF_WINDOW_SELF);
- if (err)
- msg->uop = SCIF_SIG_NACK;
- else
- msg->uop = SCIF_SIG_ACK;
- msg->payload[0] = ep->remote_ep;
- scif_nodeqp_send(ep->remote_dev, msg);
-}
-
-/**
- * scif_recv_sig_remote: Handle SCIF_SIGNAL_REMOTE request
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The peer has requested a signal on a remote offset.
- */
-void scif_recv_sig_remote(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
- int err;
-
- err = scif_prog_signal(ep, msg->payload[1], msg->payload[2],
- SCIF_WINDOW_PEER);
- if (err)
- msg->uop = SCIF_SIG_NACK;
- else
- msg->uop = SCIF_SIG_ACK;
- msg->payload[0] = ep->remote_ep;
- scif_nodeqp_send(ep->remote_dev, msg);
-}
-
-/**
- * scif_recv_sig_resp: Handle SCIF_SIG_(N)ACK messages.
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The peer has responded to a signal request.
- */
-void scif_recv_sig_resp(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
- struct scif_fence_info *fence_req =
- (struct scif_fence_info *)msg->payload[3];
-
- mutex_lock(&ep->rma_info.rma_lock);
- if (msg->uop == SCIF_SIG_ACK)
- fence_req->state = OP_COMPLETED;
- else
- fence_req->state = OP_FAILED;
- mutex_unlock(&ep->rma_info.rma_lock);
- complete(&fence_req->comp);
-}
-
-static inline void *scif_get_local_va(off_t off, struct scif_window *window)
-{
- struct page **pages = window->pinned_pages->pages;
- int page_nr = (off - window->offset) >> PAGE_SHIFT;
- off_t page_off = off & ~PAGE_MASK;
-
- return page_address(pages[page_nr]) + page_off;
-}
-
-static void scif_prog_signal_cb(void *arg)
-{
- struct scif_cb_arg *cb_arg = arg;
-
- dma_pool_free(cb_arg->ep->remote_dev->signal_pool, cb_arg->status,
- cb_arg->src_dma_addr);
- kfree(cb_arg);
-}
-
-static int _scif_prog_signal(scif_epd_t epd, dma_addr_t dst, u64 val)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct dma_chan *chan = ep->rma_info.dma_chan;
- struct dma_device *ddev = chan->device;
- bool x100 = !is_dma_copy_aligned(chan->device, 1, 1, 1);
- struct dma_async_tx_descriptor *tx;
- struct scif_status *status = NULL;
- struct scif_cb_arg *cb_arg = NULL;
- dma_addr_t src;
- dma_cookie_t cookie;
- int err;
-
- tx = ddev->device_prep_dma_memcpy(chan, 0, 0, 0, DMA_PREP_FENCE);
- if (!tx) {
- err = -ENOMEM;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto alloc_fail;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- err = (int)cookie;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto alloc_fail;
- }
- dma_async_issue_pending(chan);
- if (x100) {
- /*
- * For X100 use the status descriptor to write the value to
- * the destination.
- */
- tx = ddev->device_prep_dma_imm_data(chan, dst, val, 0);
- } else {
- status = dma_pool_alloc(ep->remote_dev->signal_pool, GFP_KERNEL,
- &src);
- if (!status) {
- err = -ENOMEM;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto alloc_fail;
- }
- status->val = val;
- status->src_dma_addr = src;
- status->ep = ep;
- src += offsetof(struct scif_status, val);
- tx = ddev->device_prep_dma_memcpy(chan, dst, src, sizeof(val),
- DMA_PREP_INTERRUPT);
- }
- if (!tx) {
- err = -ENOMEM;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto dma_fail;
- }
- if (!x100) {
- cb_arg = kmalloc(sizeof(*cb_arg), GFP_KERNEL);
- if (!cb_arg) {
- err = -ENOMEM;
- goto dma_fail;
- }
- cb_arg->src_dma_addr = src;
- cb_arg->status = status;
- cb_arg->ep = ep;
- tx->callback = scif_prog_signal_cb;
- tx->callback_param = cb_arg;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- err = -EIO;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto dma_fail;
- }
- dma_async_issue_pending(chan);
- return 0;
-dma_fail:
- if (!x100) {
- dma_pool_free(ep->remote_dev->signal_pool, status,
- src - offsetof(struct scif_status, val));
- kfree(cb_arg);
- }
-alloc_fail:
- return err;
-}
-
-/**
- * scif_prog_signal:
- * @epd: Endpoint Descriptor
- * @offset: registered address to write @val to
- * @val: Value to be written at @offset
- * @type: Type of the window.
- *
- * Arrange to write a value to the registered offset after ensuring that the
- * offset provided is indeed valid.
- */
-int scif_prog_signal(scif_epd_t epd, off_t offset, u64 val,
- enum scif_window_type type)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct scif_window *window = NULL;
- struct scif_rma_req req;
- dma_addr_t dst_dma_addr;
- int err;
-
- mutex_lock(&ep->rma_info.rma_lock);
- req.out_window = &window;
- req.offset = offset;
- req.nr_bytes = sizeof(u64);
- req.prot = SCIF_PROT_WRITE;
- req.type = SCIF_WINDOW_SINGLE;
- if (type == SCIF_WINDOW_SELF)
- req.head = &ep->rma_info.reg_list;
- else
- req.head = &ep->rma_info.remote_reg_list;
- /* Does a valid window exist? */
- err = scif_query_window(&req);
- if (err) {
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto unlock_ret;
- }
-
- if (scif_is_mgmt_node() && scifdev_self(ep->remote_dev)) {
- u64 *dst_virt;
-
- if (type == SCIF_WINDOW_SELF)
- dst_virt = scif_get_local_va(offset, window);
- else
- dst_virt =
- scif_get_local_va(offset, (struct scif_window *)
- window->peer_window);
- *dst_virt = val;
- } else {
- dst_dma_addr = __scif_off_to_dma_addr(window, offset);
- err = _scif_prog_signal(epd, dst_dma_addr, val);
- }
-unlock_ret:
- mutex_unlock(&ep->rma_info.rma_lock);
- return err;
-}
-
-static int _scif_fence_wait(scif_epd_t epd, int mark)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- dma_cookie_t cookie = mark & ~SCIF_REMOTE_FENCE;
- int err;
-
- /* Wait for DMA callback in scif_fence_mark_cb(..) */
- err = wait_event_interruptible_timeout(ep->rma_info.markwq,
- dma_async_is_tx_complete(
- ep->rma_info.dma_chan,
- cookie, NULL, NULL) ==
- DMA_COMPLETE,
- SCIF_NODE_ALIVE_TIMEOUT);
- if (!err)
- err = -ETIMEDOUT;
- else if (err > 0)
- err = 0;
- return err;
-}
-
-/**
- * scif_rma_handle_remote_fences:
- *
- * This routine services remote fence requests.
- */
-void scif_rma_handle_remote_fences(void)
-{
- struct list_head *item, *tmp;
- struct scif_remote_fence_info *fence;
- struct scif_endpt *ep;
- int mark, err;
-
- might_sleep();
- mutex_lock(&scif_info.fencelock);
- list_for_each_safe(item, tmp, &scif_info.fence) {
- fence = list_entry(item, struct scif_remote_fence_info,
- list);
- /* Remove fence from global list */
- list_del(&fence->list);
-
- /* Initiate the fence operation */
- ep = (struct scif_endpt *)fence->msg.payload[0];
- mark = fence->msg.payload[2];
- err = _scif_fence_wait(ep, mark);
- if (err)
- fence->msg.uop = SCIF_WAIT_NACK;
- else
- fence->msg.uop = SCIF_WAIT_ACK;
- fence->msg.payload[0] = ep->remote_ep;
- scif_nodeqp_send(ep->remote_dev, &fence->msg);
- kfree(fence);
- if (!atomic_sub_return(1, &ep->rma_info.fence_refcount))
- schedule_work(&scif_info.misc_work);
- }
- mutex_unlock(&scif_info.fencelock);
-}
-
-static int _scif_send_fence(scif_epd_t epd, int uop, int mark, int *out_mark)
-{
- int err;
- struct scifmsg msg;
- struct scif_fence_info *fence_req;
- struct scif_endpt *ep = (struct scif_endpt *)epd;
-
- fence_req = kmalloc(sizeof(*fence_req), GFP_KERNEL);
- if (!fence_req) {
- err = -ENOMEM;
- goto error;
- }
-
- fence_req->state = OP_IN_PROGRESS;
- init_completion(&fence_req->comp);
-
- msg.src = ep->port;
- msg.uop = uop;
- msg.payload[0] = ep->remote_ep;
- msg.payload[1] = (u64)fence_req;
- if (uop == SCIF_WAIT)
- msg.payload[2] = mark;
- spin_lock(&ep->lock);
- if (ep->state == SCIFEP_CONNECTED)
- err = scif_nodeqp_send(ep->remote_dev, &msg);
- else
- err = -ENOTCONN;
- spin_unlock(&ep->lock);
- if (err)
- goto error_free;
-retry:
- /* Wait for a SCIF_WAIT_(N)ACK message */
- err = wait_for_completion_timeout(&fence_req->comp,
- SCIF_NODE_ALIVE_TIMEOUT);
- if (!err && scifdev_alive(ep))
- goto retry;
- if (!err)
- err = -ENODEV;
- if (err > 0)
- err = 0;
- mutex_lock(&ep->rma_info.rma_lock);
- if (err < 0) {
- if (fence_req->state == OP_IN_PROGRESS)
- fence_req->state = OP_FAILED;
- }
- if (fence_req->state == OP_FAILED && !err)
- err = -ENOMEM;
- if (uop == SCIF_MARK && fence_req->state == OP_COMPLETED)
- *out_mark = SCIF_REMOTE_FENCE | fence_req->dma_mark;
- mutex_unlock(&ep->rma_info.rma_lock);
-error_free:
- kfree(fence_req);
-error:
- return err;
-}
-
-/**
- * scif_send_fence_mark:
- * @epd: end point descriptor.
- * @out_mark: Output DMA mark reported by peer.
- *
- * Send a remote fence mark request.
- */
-static int scif_send_fence_mark(scif_epd_t epd, int *out_mark)
-{
- return _scif_send_fence(epd, SCIF_MARK, 0, out_mark);
-}
-
-/**
- * scif_send_fence_wait:
- * @epd: end point descriptor.
- * @mark: DMA mark to wait for.
- *
- * Send a remote fence wait request.
- */
-static int scif_send_fence_wait(scif_epd_t epd, int mark)
-{
- return _scif_send_fence(epd, SCIF_WAIT, mark, NULL);
-}
-
-static int _scif_send_fence_signal_wait(struct scif_endpt *ep,
- struct scif_fence_info *fence_req)
-{
- int err;
-
-retry:
- /* Wait for a SCIF_SIG_(N)ACK message */
- err = wait_for_completion_timeout(&fence_req->comp,
- SCIF_NODE_ALIVE_TIMEOUT);
- if (!err && scifdev_alive(ep))
- goto retry;
- if (!err)
- err = -ENODEV;
- if (err > 0)
- err = 0;
- if (err < 0) {
- mutex_lock(&ep->rma_info.rma_lock);
- if (fence_req->state == OP_IN_PROGRESS)
- fence_req->state = OP_FAILED;
- mutex_unlock(&ep->rma_info.rma_lock);
- }
- if (fence_req->state == OP_FAILED && !err)
- err = -ENXIO;
- return err;
-}
-
-/**
- * scif_send_fence_signal:
- * @epd: endpoint descriptor
- * @loff: local offset
- * @lval: local value to write to loffset
- * @roff: remote offset
- * @rval: remote value to write to roffset
- * @flags: flags
- *
- * Sends a remote fence signal request
- */
-static int scif_send_fence_signal(scif_epd_t epd, off_t roff, u64 rval,
- off_t loff, u64 lval, int flags)
-{
- int err = 0;
- struct scifmsg msg;
- struct scif_fence_info *fence_req;
- struct scif_endpt *ep = (struct scif_endpt *)epd;
-
- fence_req = kmalloc(sizeof(*fence_req), GFP_KERNEL);
- if (!fence_req) {
- err = -ENOMEM;
- goto error;
- }
-
- fence_req->state = OP_IN_PROGRESS;
- init_completion(&fence_req->comp);
- msg.src = ep->port;
- if (flags & SCIF_SIGNAL_LOCAL) {
- msg.uop = SCIF_SIG_LOCAL;
- msg.payload[0] = ep->remote_ep;
- msg.payload[1] = roff;
- msg.payload[2] = rval;
- msg.payload[3] = (u64)fence_req;
- spin_lock(&ep->lock);
- if (ep->state == SCIFEP_CONNECTED)
- err = scif_nodeqp_send(ep->remote_dev, &msg);
- else
- err = -ENOTCONN;
- spin_unlock(&ep->lock);
- if (err)
- goto error_free;
- err = _scif_send_fence_signal_wait(ep, fence_req);
- if (err)
- goto error_free;
- }
- fence_req->state = OP_IN_PROGRESS;
-
- if (flags & SCIF_SIGNAL_REMOTE) {
- msg.uop = SCIF_SIG_REMOTE;
- msg.payload[0] = ep->remote_ep;
- msg.payload[1] = loff;
- msg.payload[2] = lval;
- msg.payload[3] = (u64)fence_req;
- spin_lock(&ep->lock);
- if (ep->state == SCIFEP_CONNECTED)
- err = scif_nodeqp_send(ep->remote_dev, &msg);
- else
- err = -ENOTCONN;
- spin_unlock(&ep->lock);
- if (err)
- goto error_free;
- err = _scif_send_fence_signal_wait(ep, fence_req);
- }
-error_free:
- kfree(fence_req);
-error:
- return err;
-}
-
-static void scif_fence_mark_cb(void *arg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)arg;
-
- wake_up_interruptible(&ep->rma_info.markwq);
- atomic_dec(&ep->rma_info.fence_refcount);
-}
-
-/**
- * _scif_fence_mark:
- * @epd: endpoint descriptor
- * @mark: DMA mark to set-up
- *
- * Set up a mark for this endpoint and return the value of the mark.
- */
-int _scif_fence_mark(scif_epd_t epd, int *mark)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct dma_chan *chan = ep->rma_info.dma_chan;
- struct dma_device *ddev = chan->device;
- struct dma_async_tx_descriptor *tx;
- dma_cookie_t cookie;
- int err;
-
- tx = ddev->device_prep_dma_memcpy(chan, 0, 0, 0, DMA_PREP_FENCE);
- if (!tx) {
- err = -ENOMEM;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- return err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- err = (int)cookie;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- return err;
- }
- dma_async_issue_pending(chan);
- tx = ddev->device_prep_dma_interrupt(chan, DMA_PREP_INTERRUPT);
- if (!tx) {
- err = -ENOMEM;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- return err;
- }
- tx->callback = scif_fence_mark_cb;
- tx->callback_param = ep;
- *mark = cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- err = (int)cookie;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- return err;
- }
- atomic_inc(&ep->rma_info.fence_refcount);
- dma_async_issue_pending(chan);
- return 0;
-}
-
-#define SCIF_LOOPB_MAGIC_MARK 0xdead
-
-int scif_fence_mark(scif_epd_t epd, int flags, int *mark)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int err = 0;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI fence_mark: ep %p flags 0x%x mark 0x%x\n",
- ep, flags, *mark);
- err = scif_verify_epd(ep);
- if (err)
- return err;
-
- /* Invalid flags? */
- if (flags & ~(SCIF_FENCE_INIT_SELF | SCIF_FENCE_INIT_PEER))
- return -EINVAL;
-
- /* At least one of init self or peer RMA should be set */
- if (!(flags & (SCIF_FENCE_INIT_SELF | SCIF_FENCE_INIT_PEER)))
- return -EINVAL;
-
- /* Exactly one of init self or peer RMA should be set but not both */
- if ((flags & SCIF_FENCE_INIT_SELF) && (flags & SCIF_FENCE_INIT_PEER))
- return -EINVAL;
-
- /*
- * Management node loopback does not need to use DMA.
- * Return a valid mark to be symmetric.
- */
- if (scifdev_self(ep->remote_dev) && scif_is_mgmt_node()) {
- *mark = SCIF_LOOPB_MAGIC_MARK;
- return 0;
- }
-
- if (flags & SCIF_FENCE_INIT_SELF)
- err = _scif_fence_mark(epd, mark);
- else
- err = scif_send_fence_mark(ep, mark);
-
- if (err)
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n", __func__, __LINE__, err);
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI fence_mark: ep %p flags 0x%x mark 0x%x err %d\n",
- ep, flags, *mark, err);
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_fence_mark);
-
-int scif_fence_wait(scif_epd_t epd, int mark)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int err = 0;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI fence_wait: ep %p mark 0x%x\n",
- ep, mark);
- err = scif_verify_epd(ep);
- if (err)
- return err;
- /*
- * Management node loopback does not need to use DMA.
- * The only valid mark provided is 0 so simply
- * return success if the mark is valid.
- */
- if (scifdev_self(ep->remote_dev) && scif_is_mgmt_node()) {
- if (mark == SCIF_LOOPB_MAGIC_MARK)
- return 0;
- else
- return -EINVAL;
- }
- if (mark & SCIF_REMOTE_FENCE)
- err = scif_send_fence_wait(epd, mark);
- else
- err = _scif_fence_wait(epd, mark);
- if (err < 0)
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n", __func__, __LINE__, err);
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_fence_wait);
-
-int scif_fence_signal(scif_epd_t epd, off_t loff, u64 lval,
- off_t roff, u64 rval, int flags)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int err = 0;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI fence_signal: ep %p loff 0x%lx lval 0x%llx roff 0x%lx rval 0x%llx flags 0x%x\n",
- ep, loff, lval, roff, rval, flags);
- err = scif_verify_epd(ep);
- if (err)
- return err;
-
- /* Invalid flags? */
- if (flags & ~(SCIF_FENCE_INIT_SELF | SCIF_FENCE_INIT_PEER |
- SCIF_SIGNAL_LOCAL | SCIF_SIGNAL_REMOTE))
- return -EINVAL;
-
- /* At least one of init self or peer RMA should be set */
- if (!(flags & (SCIF_FENCE_INIT_SELF | SCIF_FENCE_INIT_PEER)))
- return -EINVAL;
-
- /* Exactly one of init self or peer RMA should be set but not both */
- if ((flags & SCIF_FENCE_INIT_SELF) && (flags & SCIF_FENCE_INIT_PEER))
- return -EINVAL;
-
- /* At least one of SCIF_SIGNAL_LOCAL or SCIF_SIGNAL_REMOTE required */
- if (!(flags & (SCIF_SIGNAL_LOCAL | SCIF_SIGNAL_REMOTE)))
- return -EINVAL;
-
- /* Only Dword offsets allowed */
- if ((flags & SCIF_SIGNAL_LOCAL) && (loff & (sizeof(u32) - 1)))
- return -EINVAL;
-
- /* Only Dword aligned offsets allowed */
- if ((flags & SCIF_SIGNAL_REMOTE) && (roff & (sizeof(u32) - 1)))
- return -EINVAL;
-
- if (flags & SCIF_FENCE_INIT_PEER) {
- err = scif_send_fence_signal(epd, roff, rval, loff,
- lval, flags);
- } else {
- /* Local Signal in Local RAS */
- if (flags & SCIF_SIGNAL_LOCAL) {
- err = scif_prog_signal(epd, loff, lval,
- SCIF_WINDOW_SELF);
- if (err)
- goto error_ret;
- }
-
- /* Signal in Remote RAS */
- if (flags & SCIF_SIGNAL_REMOTE)
- err = scif_prog_signal(epd, roff,
- rval, SCIF_WINDOW_PEER);
- }
-error_ret:
- if (err)
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n", __func__, __LINE__, err);
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_fence_signal);
diff --git a/drivers/misc/mic/scif/scif_main.c b/drivers/misc/mic/scif/scif_main.c
deleted file mode 100644
index e2278bf..0000000
--- a/drivers/misc/mic/scif/scif_main.c
+++ /dev/null
@@ -1,351 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/module.h>
-#include <linux/idr.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-#include "../bus/scif_bus.h"
-#include "scif_peer_bus.h"
-#include "scif_main.h"
-#include "scif_map.h"
-
-struct scif_info scif_info = {
- .mdev = {
- .minor = MISC_DYNAMIC_MINOR,
- .name = "scif",
- .fops = &scif_fops,
- }
-};
-
-struct scif_dev *scif_dev;
-struct kmem_cache *unaligned_cache;
-static atomic_t g_loopb_cnt;
-
-/* Runs in the context of intr_wq */
-static void scif_intr_bh_handler(struct work_struct *work)
-{
- struct scif_dev *scifdev =
- container_of(work, struct scif_dev, intr_bh);
-
- if (scifdev_self(scifdev))
- scif_loopb_msg_handler(scifdev, scifdev->qpairs);
- else
- scif_nodeqp_intrhandler(scifdev, scifdev->qpairs);
-}
-
-int scif_setup_intr_wq(struct scif_dev *scifdev)
-{
- if (!scifdev->intr_wq) {
- snprintf(scifdev->intr_wqname, sizeof(scifdev->intr_wqname),
- "SCIF INTR %d", scifdev->node);
- scifdev->intr_wq =
- alloc_ordered_workqueue(scifdev->intr_wqname, 0);
- if (!scifdev->intr_wq)
- return -ENOMEM;
- INIT_WORK(&scifdev->intr_bh, scif_intr_bh_handler);
- }
- return 0;
-}
-
-void scif_destroy_intr_wq(struct scif_dev *scifdev)
-{
- if (scifdev->intr_wq) {
- destroy_workqueue(scifdev->intr_wq);
- scifdev->intr_wq = NULL;
- }
-}
-
-irqreturn_t scif_intr_handler(int irq, void *data)
-{
- struct scif_dev *scifdev = data;
- struct scif_hw_dev *sdev = scifdev->sdev;
-
- sdev->hw_ops->ack_interrupt(sdev, scifdev->db);
- queue_work(scifdev->intr_wq, &scifdev->intr_bh);
- return IRQ_HANDLED;
-}
-
-static void scif_qp_setup_handler(struct work_struct *work)
-{
- struct scif_dev *scifdev = container_of(work, struct scif_dev,
- qp_dwork.work);
- struct scif_hw_dev *sdev = scifdev->sdev;
- dma_addr_t da = 0;
- int err;
-
- if (scif_is_mgmt_node()) {
- struct mic_bootparam *bp = sdev->dp;
-
- da = bp->scif_card_dma_addr;
- scifdev->rdb = bp->h2c_scif_db;
- } else {
- struct mic_bootparam __iomem *bp = sdev->rdp;
-
- da = readq(&bp->scif_host_dma_addr);
- scifdev->rdb = ioread8(&bp->c2h_scif_db);
- }
- if (da) {
- err = scif_qp_response(da, scifdev);
- if (err)
- dev_err(&scifdev->sdev->dev,
- "scif_qp_response err %d\n", err);
- } else {
- schedule_delayed_work(&scifdev->qp_dwork,
- msecs_to_jiffies(1000));
- }
-}
-
-static int scif_setup_scifdev(void)
-{
- /* We support a maximum of 129 SCIF nodes including the mgmt node */
-#define MAX_SCIF_NODES 129
- int i;
- u8 num_nodes = MAX_SCIF_NODES;
-
- scif_dev = kcalloc(num_nodes, sizeof(*scif_dev), GFP_KERNEL);
- if (!scif_dev)
- return -ENOMEM;
- for (i = 0; i < num_nodes; i++) {
- struct scif_dev *scifdev = &scif_dev[i];
-
- scifdev->node = i;
- scifdev->exit = OP_IDLE;
- init_waitqueue_head(&scifdev->disconn_wq);
- mutex_init(&scifdev->lock);
- INIT_WORK(&scifdev->peer_add_work, scif_add_peer_device);
- INIT_DELAYED_WORK(&scifdev->p2p_dwork,
- scif_poll_qp_state);
- INIT_DELAYED_WORK(&scifdev->qp_dwork,
- scif_qp_setup_handler);
- INIT_LIST_HEAD(&scifdev->p2p);
- RCU_INIT_POINTER(scifdev->spdev, NULL);
- }
- return 0;
-}
-
-static void scif_destroy_scifdev(void)
-{
- kfree(scif_dev);
- scif_dev = NULL;
-}
-
-static int scif_probe(struct scif_hw_dev *sdev)
-{
- struct scif_dev *scifdev = &scif_dev[sdev->dnode];
- int rc;
-
- dev_set_drvdata(&sdev->dev, sdev);
- scifdev->sdev = sdev;
-
- if (1 == atomic_add_return(1, &g_loopb_cnt)) {
- struct scif_dev *loopb_dev = &scif_dev[sdev->snode];
-
- loopb_dev->sdev = sdev;
- rc = scif_setup_loopback_qp(loopb_dev);
- if (rc)
- goto exit;
- }
-
- rc = scif_setup_intr_wq(scifdev);
- if (rc)
- goto destroy_loopb;
- rc = scif_setup_qp(scifdev);
- if (rc)
- goto destroy_intr;
- scifdev->db = sdev->hw_ops->next_db(sdev);
- scifdev->cookie = sdev->hw_ops->request_irq(sdev, scif_intr_handler,
- "SCIF_INTR", scifdev,
- scifdev->db);
- if (IS_ERR(scifdev->cookie)) {
- rc = PTR_ERR(scifdev->cookie);
- goto free_qp;
- }
- if (scif_is_mgmt_node()) {
- struct mic_bootparam *bp = sdev->dp;
-
- bp->c2h_scif_db = scifdev->db;
- bp->scif_host_dma_addr = scifdev->qp_dma_addr;
- } else {
- struct mic_bootparam __iomem *bp = sdev->rdp;
-
- iowrite8(scifdev->db, &bp->h2c_scif_db);
- writeq(scifdev->qp_dma_addr, &bp->scif_card_dma_addr);
- }
- schedule_delayed_work(&scifdev->qp_dwork,
- msecs_to_jiffies(1000));
- return rc;
-free_qp:
- scif_free_qp(scifdev);
-destroy_intr:
- scif_destroy_intr_wq(scifdev);
-destroy_loopb:
- if (atomic_dec_and_test(&g_loopb_cnt))
- scif_destroy_loopback_qp(&scif_dev[sdev->snode]);
-exit:
- return rc;
-}
-
-void scif_stop(struct scif_dev *scifdev)
-{
- struct scif_dev *dev;
- int i;
-
- for (i = scif_info.maxid; i >= 0; i--) {
- dev = &scif_dev[i];
- if (scifdev_self(dev))
- continue;
- scif_handle_remove_node(i);
- }
-}
-
-static void scif_remove(struct scif_hw_dev *sdev)
-{
- struct scif_dev *scifdev = &scif_dev[sdev->dnode];
-
- if (scif_is_mgmt_node()) {
- struct mic_bootparam *bp = sdev->dp;
-
- bp->c2h_scif_db = -1;
- bp->scif_host_dma_addr = 0x0;
- } else {
- struct mic_bootparam __iomem *bp = sdev->rdp;
-
- iowrite8(-1, &bp->h2c_scif_db);
- writeq(0x0, &bp->scif_card_dma_addr);
- }
- if (scif_is_mgmt_node()) {
- scif_disconnect_node(scifdev->node, true);
- } else {
- scif_info.card_initiated_exit = true;
- scif_stop(scifdev);
- }
- if (atomic_dec_and_test(&g_loopb_cnt))
- scif_destroy_loopback_qp(&scif_dev[sdev->snode]);
- if (scifdev->cookie) {
- sdev->hw_ops->free_irq(sdev, scifdev->cookie, scifdev);
- scifdev->cookie = NULL;
- }
- scif_destroy_intr_wq(scifdev);
- cancel_delayed_work(&scifdev->qp_dwork);
- scif_free_qp(scifdev);
- scifdev->rdb = -1;
- scifdev->sdev = NULL;
-}
-
-static struct scif_hw_dev_id id_table[] = {
- { MIC_SCIF_DEV, SCIF_DEV_ANY_ID },
- { 0 },
-};
-
-static struct scif_driver scif_driver = {
- .driver.name = KBUILD_MODNAME,
- .driver.owner = THIS_MODULE,
- .id_table = id_table,
- .probe = scif_probe,
- .remove = scif_remove,
-};
-
-static int _scif_init(void)
-{
- int rc;
-
- mutex_init(&scif_info.eplock);
- spin_lock_init(&scif_info.rmalock);
- spin_lock_init(&scif_info.nb_connect_lock);
- spin_lock_init(&scif_info.port_lock);
- mutex_init(&scif_info.conflock);
- mutex_init(&scif_info.connlock);
- mutex_init(&scif_info.fencelock);
- INIT_LIST_HEAD(&scif_info.uaccept);
- INIT_LIST_HEAD(&scif_info.listen);
- INIT_LIST_HEAD(&scif_info.zombie);
- INIT_LIST_HEAD(&scif_info.connected);
- INIT_LIST_HEAD(&scif_info.disconnected);
- INIT_LIST_HEAD(&scif_info.rma);
- INIT_LIST_HEAD(&scif_info.rma_tc);
- INIT_LIST_HEAD(&scif_info.mmu_notif_cleanup);
- INIT_LIST_HEAD(&scif_info.fence);
- INIT_LIST_HEAD(&scif_info.nb_connect_list);
- init_waitqueue_head(&scif_info.exitwq);
- scif_info.rma_tc_limit = SCIF_RMA_TEMP_CACHE_LIMIT;
- scif_info.en_msg_log = 0;
- scif_info.p2p_enable = 1;
- rc = scif_setup_scifdev();
- if (rc)
- goto error;
- unaligned_cache = kmem_cache_create("Unaligned_DMA",
- SCIF_KMEM_UNALIGNED_BUF_SIZE,
- 0, SLAB_HWCACHE_ALIGN, NULL);
- if (!unaligned_cache) {
- rc = -ENOMEM;
- goto free_sdev;
- }
- INIT_WORK(&scif_info.misc_work, scif_misc_handler);
- INIT_WORK(&scif_info.mmu_notif_work, scif_mmu_notif_handler);
- INIT_WORK(&scif_info.conn_work, scif_conn_handler);
- idr_init(&scif_ports);
- return 0;
-free_sdev:
- scif_destroy_scifdev();
-error:
- return rc;
-}
-
-static void _scif_exit(void)
-{
- idr_destroy(&scif_ports);
- kmem_cache_destroy(unaligned_cache);
- scif_destroy_scifdev();
-}
-
-static int __init scif_init(void)
-{
- struct miscdevice *mdev = &scif_info.mdev;
- int rc;
-
- _scif_init();
- iova_cache_get();
- rc = scif_peer_bus_init();
- if (rc)
- goto exit;
- rc = scif_register_driver(&scif_driver);
- if (rc)
- goto peer_bus_exit;
- rc = misc_register(mdev);
- if (rc)
- goto unreg_scif;
- scif_init_debugfs();
- return 0;
-unreg_scif:
- scif_unregister_driver(&scif_driver);
-peer_bus_exit:
- scif_peer_bus_exit();
-exit:
- _scif_exit();
- return rc;
-}
-
-static void __exit scif_exit(void)
-{
- scif_exit_debugfs();
- misc_deregister(&scif_info.mdev);
- scif_unregister_driver(&scif_driver);
- scif_peer_bus_exit();
- iova_cache_put();
- _scif_exit();
-}
-
-module_init(scif_init);
-module_exit(scif_exit);
-
-MODULE_DEVICE_TABLE(scif, id_table);
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) SCIF driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/scif/scif_main.h b/drivers/misc/mic/scif/scif_main.h
deleted file mode 100644
index bb3ab97..0000000
--- a/drivers/misc/mic/scif/scif_main.h
+++ /dev/null
@@ -1,274 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#ifndef SCIF_MAIN_H
-#define SCIF_MAIN_H
-
-#include <linux/sched/signal.h>
-#include <linux/pci.h>
-#include <linux/miscdevice.h>
-#include <linux/dmaengine.h>
-#include <linux/iova.h>
-#include <linux/anon_inodes.h>
-#include <linux/file.h>
-#include <linux/vmalloc.h>
-#include <linux/scif.h>
-#include "../common/mic_dev.h"
-
-#define SCIF_MGMT_NODE 0
-#define SCIF_DEFAULT_WATCHDOG_TO 30
-#define SCIF_NODE_ACCEPT_TIMEOUT (3 * HZ)
-#define SCIF_NODE_ALIVE_TIMEOUT (SCIF_DEFAULT_WATCHDOG_TO * HZ)
-#define SCIF_RMA_TEMP_CACHE_LIMIT 0x20000
-
-/*
- * Generic state used for certain node QP message exchanges
- * like Unregister, Alloc etc.
- */
-enum scif_msg_state {
- OP_IDLE = 1,
- OP_IN_PROGRESS,
- OP_COMPLETED,
- OP_FAILED
-};
-
-/*
- * struct scif_info - Global SCIF information
- *
- * @nodeid: Node ID this node is to others
- * @maxid: Max known node ID
- * @total: Total number of SCIF nodes
- * @nr_zombies: number of zombie endpoints
- * @eplock: Lock to synchronize listening, zombie endpoint lists
- * @connlock: Lock to synchronize connected and disconnected lists
- * @nb_connect_lock: Synchronize non blocking connect operations
- * @port_lock: Synchronize access to SCIF ports
- * @uaccept: List of user acceptreq waiting for acceptreg
- * @listen: List of listening end points
- * @zombie: List of zombie end points with pending RMA's
- * @connected: List of end points in connected state
- * @disconnected: List of end points in disconnected state
- * @nb_connect_list: List for non blocking connections
- * @misc_work: miscellaneous SCIF tasks
- * @conflock: Lock to synchronize SCIF node configuration changes
- * @en_msg_log: Enable debug message logging
- * @p2p_enable: Enable P2P SCIF network
- * @mdev: The MISC device
- * @conn_work: Work for workqueue handling all connections
- * @exitwq: Wait queue for waiting for an EXIT node QP message response
- * @loopb_dev: Dummy SCIF device used for loopback
- * @loopb_wq: Workqueue used for handling loopback messages
- * @loopb_wqname[16]: Name of loopback workqueue
- * @loopb_work: Used for submitting work to loopb_wq
- * @loopb_recv_q: List of messages received on the loopb_wq
- * @card_initiated_exit: set when the card has initiated the exit
- * @rmalock: Synchronize access to RMA operations
- * @fencelock: Synchronize access to list of remote fences requested.
- * @rma: List of temporary registered windows to be destroyed.
- * @rma_tc: List of temporary registered & cached Windows to be destroyed
- * @fence: List of remote fence requests
- * @mmu_notif_work: Work for registration caching MMU notifier workqueue
- * @mmu_notif_cleanup: List of temporary cached windows for reg cache
- * @rma_tc_limit: RMA temporary cache limit
- */
-struct scif_info {
- u8 nodeid;
- u8 maxid;
- u8 total;
- u32 nr_zombies;
- struct mutex eplock;
- struct mutex connlock;
- spinlock_t nb_connect_lock;
- spinlock_t port_lock;
- struct list_head uaccept;
- struct list_head listen;
- struct list_head zombie;
- struct list_head connected;
- struct list_head disconnected;
- struct list_head nb_connect_list;
- struct work_struct misc_work;
- struct mutex conflock;
- u8 en_msg_log;
- u8 p2p_enable;
- struct miscdevice mdev;
- struct work_struct conn_work;
- wait_queue_head_t exitwq;
- struct scif_dev *loopb_dev;
- struct workqueue_struct *loopb_wq;
- char loopb_wqname[16];
- struct work_struct loopb_work;
- struct list_head loopb_recv_q;
- bool card_initiated_exit;
- spinlock_t rmalock;
- struct mutex fencelock;
- struct list_head rma;
- struct list_head rma_tc;
- struct list_head fence;
- struct work_struct mmu_notif_work;
- struct list_head mmu_notif_cleanup;
- unsigned long rma_tc_limit;
-};
-
-/*
- * struct scif_p2p_info - SCIF mapping information used for P2P
- *
- * @ppi_peer_id - SCIF peer node id
- * @ppi_sg - Scatter list for bar information (One for mmio and one for aper)
- * @sg_nentries - Number of entries in the scatterlist
- * @ppi_da: DMA address for MMIO and APER bars
- * @ppi_len: Length of MMIO and APER bars
- * @ppi_list: Link in list of mapping information
- */
-struct scif_p2p_info {
- u8 ppi_peer_id;
- struct scatterlist *ppi_sg[2];
- u64 sg_nentries[2];
- dma_addr_t ppi_da[2];
- u64 ppi_len[2];
-#define SCIF_PPI_MMIO 0
-#define SCIF_PPI_APER 1
- struct list_head ppi_list;
-};
-
-/*
- * struct scif_dev - SCIF remote device specific fields
- *
- * @node: Node id
- * @p2p: List of P2P mapping information
- * @qpairs: The node queue pair for exchanging control messages
- * @intr_wq: Workqueue for handling Node QP messages
- * @intr_wqname: Name of node QP workqueue for handling interrupts
- * @intr_bh: Used for submitting work to intr_wq
- * @lock: Lock used for synchronizing access to the scif device
- * @sdev: SCIF hardware device on the SCIF hardware bus
- * @db: doorbell the peer will trigger to generate an interrupt on self
- * @rdb: Doorbell to trigger on the peer to generate an interrupt on the peer
- * @cookie: Cookie received while registering the interrupt handler
- * @peer_add_work: Work for handling device_add for peer devices
- * @p2p_dwork: Delayed work to enable polling for P2P state
- * @qp_dwork: Delayed work for enabling polling for remote QP information
- * @p2p_retry: Number of times to retry polling of P2P state
- * @base_addr: P2P aperture bar base address
- * @mic_mw mmio: The peer MMIO information used for P2P
- * @spdev: SCIF peer device on the SCIF peer bus
- * @node_remove_ack_pending: True if a node_remove_ack is pending
- * @exit_ack_pending: true if an exit_ack is pending
- * @disconn_wq: Used while waiting for a node remove response
- * @disconn_rescnt: Keeps track of number of node remove requests sent
- * @exit: Status of exit message
- * @qp_dma_addr: Queue pair DMA address passed to the peer
- * @dma_ch_idx: Round robin index for DMA channels
- * @signal_pool: DMA pool used for scheduling scif_fence_signal DMA's
-*/
-struct scif_dev {
- u8 node;
- struct list_head p2p;
- struct scif_qp *qpairs;
- struct workqueue_struct *intr_wq;
- char intr_wqname[16];
- struct work_struct intr_bh;
- struct mutex lock;
- struct scif_hw_dev *sdev;
- int db;
- int rdb;
- struct mic_irq *cookie;
- struct work_struct peer_add_work;
- struct delayed_work p2p_dwork;
- struct delayed_work qp_dwork;
- int p2p_retry;
- dma_addr_t base_addr;
- struct mic_mw mmio;
- struct scif_peer_dev __rcu *spdev;
- bool node_remove_ack_pending;
- bool exit_ack_pending;
- wait_queue_head_t disconn_wq;
- atomic_t disconn_rescnt;
- enum scif_msg_state exit;
- dma_addr_t qp_dma_addr;
- int dma_ch_idx;
- struct dma_pool *signal_pool;
-};
-
-extern bool scif_reg_cache_enable;
-extern bool scif_ulimit_check;
-extern struct scif_info scif_info;
-extern struct idr scif_ports;
-extern struct bus_type scif_peer_bus;
-extern struct scif_dev *scif_dev;
-extern const struct file_operations scif_fops;
-extern const struct file_operations scif_anon_fops;
-
-/* Size of the RB for the Node QP */
-#define SCIF_NODE_QP_SIZE 0x10000
-
-#include "scif_nodeqp.h"
-#include "scif_rma.h"
-#include "scif_rma_list.h"
-
-/*
- * scifdev_self:
- * @dev: The remote SCIF Device
- *
- * Returns true if the SCIF Device passed is the self aka Loopback SCIF device.
- */
-static inline int scifdev_self(struct scif_dev *dev)
-{
- return dev->node == scif_info.nodeid;
-}
-
-static inline bool scif_is_mgmt_node(void)
-{
- return !scif_info.nodeid;
-}
-
-/*
- * scifdev_is_p2p:
- * @dev: The remote SCIF Device
- *
- * Returns true if the SCIF Device is a MIC Peer to Peer SCIF device.
- */
-static inline bool scifdev_is_p2p(struct scif_dev *dev)
-{
- if (scif_is_mgmt_node())
- return false;
- else
- return dev != &scif_dev[SCIF_MGMT_NODE] &&
- !scifdev_self(dev);
-}
-
-/*
- * scifdev_alive:
- * @scifdev: The remote SCIF Device
- *
- * Returns true if the remote SCIF Device is running or sleeping for
- * this endpoint.
- */
-static inline int _scifdev_alive(struct scif_dev *scifdev)
-{
- struct scif_peer_dev *spdev;
-
- rcu_read_lock();
- spdev = rcu_dereference(scifdev->spdev);
- rcu_read_unlock();
- return !!spdev;
-}
-
-#include "scif_epd.h"
-
-void __init scif_init_debugfs(void);
-void scif_exit_debugfs(void);
-int scif_setup_intr_wq(struct scif_dev *scifdev);
-void scif_destroy_intr_wq(struct scif_dev *scifdev);
-void scif_cleanup_scifdev(struct scif_dev *dev);
-void scif_handle_remove_node(int node);
-void scif_disconnect_node(u32 node_id, bool mgmt_initiated);
-void scif_free_qp(struct scif_dev *dev);
-void scif_misc_handler(struct work_struct *work);
-void scif_stop(struct scif_dev *scifdev);
-irqreturn_t scif_intr_handler(int irq, void *data);
-#endif /* SCIF_MAIN_H */
diff --git a/drivers/misc/mic/scif/scif_map.h b/drivers/misc/mic/scif/scif_map.h
deleted file mode 100644
index 96b7608..0000000
--- a/drivers/misc/mic/scif/scif_map.h
+++ /dev/null
@@ -1,127 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#ifndef SCIF_MAP_H
-#define SCIF_MAP_H
-
-#include "../bus/scif_bus.h"
-
-static __always_inline void *
-scif_alloc_coherent(dma_addr_t *dma_handle,
- struct scif_dev *scifdev, size_t size,
- gfp_t gfp)
-{
- void *va;
-
- if (scifdev_self(scifdev)) {
- va = kmalloc(size, gfp);
- if (va)
- *dma_handle = virt_to_phys(va);
- } else {
- va = dma_alloc_coherent(&scifdev->sdev->dev,
- size, dma_handle, gfp);
- if (va && scifdev_is_p2p(scifdev))
- *dma_handle = *dma_handle + scifdev->base_addr;
- }
- return va;
-}
-
-static __always_inline void
-scif_free_coherent(void *va, dma_addr_t local,
- struct scif_dev *scifdev, size_t size)
-{
- if (scifdev_self(scifdev)) {
- kfree(va);
- } else {
- if (scifdev_is_p2p(scifdev) && local > scifdev->base_addr)
- local = local - scifdev->base_addr;
- dma_free_coherent(&scifdev->sdev->dev,
- size, va, local);
- }
-}
-
-static __always_inline int
-scif_map_single(dma_addr_t *dma_handle,
- void *local, struct scif_dev *scifdev, size_t size)
-{
- int err = 0;
-
- if (scifdev_self(scifdev)) {
- *dma_handle = virt_to_phys((local));
- } else {
- *dma_handle = dma_map_single(&scifdev->sdev->dev,
- local, size, DMA_BIDIRECTIONAL);
- if (dma_mapping_error(&scifdev->sdev->dev, *dma_handle))
- err = -ENOMEM;
- else if (scifdev_is_p2p(scifdev))
- *dma_handle = *dma_handle + scifdev->base_addr;
- }
- if (err)
- *dma_handle = 0;
- return err;
-}
-
-static __always_inline void
-scif_unmap_single(dma_addr_t local, struct scif_dev *scifdev,
- size_t size)
-{
- if (!scifdev_self(scifdev)) {
- if (scifdev_is_p2p(scifdev))
- local = local - scifdev->base_addr;
- dma_unmap_single(&scifdev->sdev->dev, local,
- size, DMA_BIDIRECTIONAL);
- }
-}
-
-static __always_inline void *
-scif_ioremap(dma_addr_t phys, size_t size, struct scif_dev *scifdev)
-{
- void *out_virt;
- struct scif_hw_dev *sdev = scifdev->sdev;
-
- if (scifdev_self(scifdev))
- out_virt = phys_to_virt(phys);
- else
- out_virt = (void __force *)
- sdev->hw_ops->remap(sdev, phys, size);
- return out_virt;
-}
-
-static __always_inline void
-scif_iounmap(void *virt, size_t len, struct scif_dev *scifdev)
-{
- if (!scifdev_self(scifdev)) {
- struct scif_hw_dev *sdev = scifdev->sdev;
-
- sdev->hw_ops->unmap(sdev, (void __force __iomem *)virt);
- }
-}
-
-static __always_inline int
-scif_map_page(dma_addr_t *dma_handle, struct page *page,
- struct scif_dev *scifdev)
-{
- int err = 0;
-
- if (scifdev_self(scifdev)) {
- *dma_handle = page_to_phys(page);
- } else {
- struct scif_hw_dev *sdev = scifdev->sdev;
- *dma_handle = dma_map_page(&sdev->dev,
- page, 0x0, PAGE_SIZE,
- DMA_BIDIRECTIONAL);
- if (dma_mapping_error(&sdev->dev, *dma_handle))
- err = -ENOMEM;
- else if (scifdev_is_p2p(scifdev))
- *dma_handle = *dma_handle + scifdev->base_addr;
- }
- if (err)
- *dma_handle = 0;
- return err;
-}
-#endif /* SCIF_MAP_H */
diff --git a/drivers/misc/mic/scif/scif_mmap.c b/drivers/misc/mic/scif/scif_mmap.c
deleted file mode 100644
index a151d41..0000000
--- a/drivers/misc/mic/scif/scif_mmap.c
+++ /dev/null
@@ -1,690 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-
-/*
- * struct scif_vma_info - Information about a remote memory mapping
- * created via scif_mmap(..)
- * @vma: VM area struct
- * @list: link to list of active vmas
- */
-struct scif_vma_info {
- struct vm_area_struct *vma;
- struct list_head list;
-};
-
-void scif_recv_munmap(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_rma_req req;
- struct scif_window *window = NULL;
- struct scif_window *recv_window =
- (struct scif_window *)msg->payload[0];
- struct scif_endpt *ep;
-
- ep = (struct scif_endpt *)recv_window->ep;
- req.out_window = &window;
- req.offset = recv_window->offset;
- req.prot = recv_window->prot;
- req.nr_bytes = recv_window->nr_pages << PAGE_SHIFT;
- req.type = SCIF_WINDOW_FULL;
- req.head = &ep->rma_info.reg_list;
- msg->payload[0] = ep->remote_ep;
-
- mutex_lock(&ep->rma_info.rma_lock);
- /* Does a valid window exist? */
- if (scif_query_window(&req)) {
- dev_err(&scifdev->sdev->dev,
- "%s %d -ENXIO\n", __func__, __LINE__);
- msg->uop = SCIF_UNREGISTER_ACK;
- goto error;
- }
-
- scif_put_window(window, window->nr_pages);
-
- if (!window->ref_count) {
- atomic_inc(&ep->rma_info.tw_refcount);
- ep->rma_info.async_list_del = 1;
- list_del_init(&window->list);
- scif_free_window_offset(ep, window, window->offset);
- }
-error:
- mutex_unlock(&ep->rma_info.rma_lock);
- if (window && !window->ref_count)
- scif_queue_for_cleanup(window, &scif_info.rma);
-}
-
-/*
- * Remove valid remote memory mappings created via scif_mmap(..) from the
- * process address space since the remote node is lost
- */
-static void __scif_zap_mmaps(struct scif_endpt *ep)
-{
- struct list_head *item;
- struct scif_vma_info *info;
- struct vm_area_struct *vma;
- unsigned long size;
-
- spin_lock(&ep->lock);
- list_for_each(item, &ep->rma_info.vma_list) {
- info = list_entry(item, struct scif_vma_info, list);
- vma = info->vma;
- size = vma->vm_end - vma->vm_start;
- zap_vma_ptes(vma, vma->vm_start, size);
- dev_dbg(scif_info.mdev.this_device,
- "%s ep %p zap vma %p size 0x%lx\n",
- __func__, ep, info->vma, size);
- }
- spin_unlock(&ep->lock);
-}
-
-/*
- * Traverse the list of endpoints for a particular remote node and
- * zap valid remote memory mappings since the remote node is lost
- */
-static void _scif_zap_mmaps(int node, struct list_head *head)
-{
- struct scif_endpt *ep;
- struct list_head *item;
-
- mutex_lock(&scif_info.connlock);
- list_for_each(item, head) {
- ep = list_entry(item, struct scif_endpt, list);
- if (ep->remote_dev->node == node)
- __scif_zap_mmaps(ep);
- }
- mutex_unlock(&scif_info.connlock);
-}
-
-/*
- * Wrapper for removing remote memory mappings for a particular node. This API
- * is called by peer nodes as part of handling a lost node.
- */
-void scif_zap_mmaps(int node)
-{
- _scif_zap_mmaps(node, &scif_info.connected);
- _scif_zap_mmaps(node, &scif_info.disconnected);
-}
-
-/*
- * This API is only called while handling a lost node:
- * a) Remote node is dead.
- * b) Remote memory mappings have been zapped
- * So we can traverse the remote_reg_list without any locks. Since
- * the window has not yet been unregistered we can drop the ref count
- * and queue it to the cleanup thread.
- */
-static void __scif_cleanup_rma_for_zombies(struct scif_endpt *ep)
-{
- struct list_head *pos, *tmp;
- struct scif_window *window;
-
- list_for_each_safe(pos, tmp, &ep->rma_info.remote_reg_list) {
- window = list_entry(pos, struct scif_window, list);
- if (window->ref_count)
- scif_put_window(window, window->nr_pages);
- else
- dev_err(scif_info.mdev.this_device,
- "%s %d unexpected\n",
- __func__, __LINE__);
- if (!window->ref_count) {
- atomic_inc(&ep->rma_info.tw_refcount);
- list_del_init(&window->list);
- scif_queue_for_cleanup(window, &scif_info.rma);
- }
- }
-}
-
-/* Cleanup remote registration lists for zombie endpoints */
-void scif_cleanup_rma_for_zombies(int node)
-{
- struct scif_endpt *ep;
- struct list_head *item;
-
- mutex_lock(&scif_info.eplock);
- list_for_each(item, &scif_info.zombie) {
- ep = list_entry(item, struct scif_endpt, list);
- if (ep->remote_dev && ep->remote_dev->node == node)
- __scif_cleanup_rma_for_zombies(ep);
- }
- mutex_unlock(&scif_info.eplock);
- flush_work(&scif_info.misc_work);
-}
-
-/* Insert the VMA into the per endpoint VMA list */
-static int scif_insert_vma(struct scif_endpt *ep, struct vm_area_struct *vma)
-{
- struct scif_vma_info *info;
- int err = 0;
-
- info = kzalloc(sizeof(*info), GFP_KERNEL);
- if (!info) {
- err = -ENOMEM;
- goto done;
- }
- info->vma = vma;
- spin_lock(&ep->lock);
- list_add_tail(&info->list, &ep->rma_info.vma_list);
- spin_unlock(&ep->lock);
-done:
- return err;
-}
-
-/* Delete the VMA from the per endpoint VMA list */
-static void scif_delete_vma(struct scif_endpt *ep, struct vm_area_struct *vma)
-{
- struct list_head *item;
- struct scif_vma_info *info;
-
- spin_lock(&ep->lock);
- list_for_each(item, &ep->rma_info.vma_list) {
- info = list_entry(item, struct scif_vma_info, list);
- if (info->vma == vma) {
- list_del(&info->list);
- kfree(info);
- break;
- }
- }
- spin_unlock(&ep->lock);
-}
-
-static phys_addr_t scif_get_phys(phys_addr_t phys, struct scif_endpt *ep)
-{
- struct scif_dev *scifdev = (struct scif_dev *)ep->remote_dev;
- struct scif_hw_dev *sdev = scifdev->sdev;
- phys_addr_t out_phys, apt_base = 0;
-
- /*
- * If the DMA address is card relative then we need to add the
- * aperture base for mmap to work correctly
- */
- if (!scifdev_self(scifdev) && sdev->aper && sdev->card_rel_da)
- apt_base = sdev->aper->pa;
- out_phys = apt_base + phys;
- return out_phys;
-}
-
-int scif_get_pages(scif_epd_t epd, off_t offset, size_t len,
- struct scif_range **pages)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct scif_rma_req req;
- struct scif_window *window = NULL;
- int nr_pages, err, i;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI get_pinned_pages: ep %p offset 0x%lx len 0x%lx\n",
- ep, offset, len);
- err = scif_verify_epd(ep);
- if (err)
- return err;
-
- if (!len || (offset < 0) ||
- (offset + len < offset) ||
- (ALIGN(offset, PAGE_SIZE) != offset) ||
- (ALIGN(len, PAGE_SIZE) != len))
- return -EINVAL;
-
- nr_pages = len >> PAGE_SHIFT;
-
- req.out_window = &window;
- req.offset = offset;
- req.prot = 0;
- req.nr_bytes = len;
- req.type = SCIF_WINDOW_SINGLE;
- req.head = &ep->rma_info.remote_reg_list;
-
- mutex_lock(&ep->rma_info.rma_lock);
- /* Does a valid window exist? */
- err = scif_query_window(&req);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto error;
- }
-
- /* Allocate scif_range */
- *pages = kzalloc(sizeof(**pages), GFP_KERNEL);
- if (!*pages) {
- err = -ENOMEM;
- goto error;
- }
-
- /* Allocate phys addr array */
- (*pages)->phys_addr = scif_zalloc(nr_pages * sizeof(dma_addr_t));
- if (!((*pages)->phys_addr)) {
- err = -ENOMEM;
- goto error;
- }
-
- if (scif_is_mgmt_node() && !scifdev_self(ep->remote_dev)) {
- /* Allocate virtual address array */
- ((*pages)->va = scif_zalloc(nr_pages * sizeof(void *)));
- if (!(*pages)->va) {
- err = -ENOMEM;
- goto error;
- }
- }
- /* Populate the values */
- (*pages)->cookie = window;
- (*pages)->nr_pages = nr_pages;
- (*pages)->prot_flags = window->prot;
-
- for (i = 0; i < nr_pages; i++) {
- (*pages)->phys_addr[i] =
- __scif_off_to_dma_addr(window, offset +
- (i * PAGE_SIZE));
- (*pages)->phys_addr[i] = scif_get_phys((*pages)->phys_addr[i],
- ep);
- if (scif_is_mgmt_node() && !scifdev_self(ep->remote_dev))
- (*pages)->va[i] =
- ep->remote_dev->sdev->aper->va +
- (*pages)->phys_addr[i] -
- ep->remote_dev->sdev->aper->pa;
- }
-
- scif_get_window(window, nr_pages);
-error:
- mutex_unlock(&ep->rma_info.rma_lock);
- if (err) {
- if (*pages) {
- scif_free((*pages)->phys_addr,
- nr_pages * sizeof(dma_addr_t));
- scif_free((*pages)->va,
- nr_pages * sizeof(void *));
- kfree(*pages);
- *pages = NULL;
- }
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- }
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_get_pages);
-
-int scif_put_pages(struct scif_range *pages)
-{
- struct scif_endpt *ep;
- struct scif_window *window;
- struct scifmsg msg;
-
- if (!pages || !pages->cookie)
- return -EINVAL;
-
- window = pages->cookie;
-
- if (!window || window->magic != SCIFEP_MAGIC)
- return -EINVAL;
-
- ep = (struct scif_endpt *)window->ep;
- /*
- * If the state is SCIFEP_CONNECTED or SCIFEP_DISCONNECTED then the
- * callee should be allowed to release references to the pages,
- * else the endpoint was not connected in the first place,
- * hence the ENOTCONN.
- */
- if (ep->state != SCIFEP_CONNECTED && ep->state != SCIFEP_DISCONNECTED)
- return -ENOTCONN;
-
- mutex_lock(&ep->rma_info.rma_lock);
-
- scif_put_window(window, pages->nr_pages);
-
- /* Initiate window destruction if ref count is zero */
- if (!window->ref_count) {
- list_del(&window->list);
- mutex_unlock(&ep->rma_info.rma_lock);
- scif_drain_dma_intr(ep->remote_dev->sdev,
- ep->rma_info.dma_chan);
- /* Inform the peer about this window being destroyed. */
- msg.uop = SCIF_MUNMAP;
- msg.src = ep->port;
- msg.payload[0] = window->peer_window;
- /* No error handling for notification messages */
- scif_nodeqp_send(ep->remote_dev, &msg);
- /* Destroy this window from the peer's registered AS */
- scif_destroy_remote_window(window);
- } else {
- mutex_unlock(&ep->rma_info.rma_lock);
- }
-
- scif_free(pages->phys_addr, pages->nr_pages * sizeof(dma_addr_t));
- scif_free(pages->va, pages->nr_pages * sizeof(void *));
- kfree(pages);
- return 0;
-}
-EXPORT_SYMBOL_GPL(scif_put_pages);
-
-/*
- * scif_rma_list_mmap:
- *
- * Traverse the remote registration list starting from start_window:
- * 1) Create VtoP mappings via remap_pfn_range(..)
- * 2) Once step 1) and 2) complete successfully then traverse the range of
- * windows again and bump the reference count.
- * RMA lock must be held.
- */
-static int scif_rma_list_mmap(struct scif_window *start_window, s64 offset,
- int nr_pages, struct vm_area_struct *vma)
-{
- s64 end_offset, loop_offset = offset;
- struct scif_window *window = start_window;
- int loop_nr_pages, nr_pages_left = nr_pages;
- struct scif_endpt *ep = (struct scif_endpt *)start_window->ep;
- struct list_head *head = &ep->rma_info.remote_reg_list;
- int i, err = 0;
- dma_addr_t phys_addr;
- struct scif_window_iter src_win_iter;
- size_t contig_bytes = 0;
-
- might_sleep();
- list_for_each_entry_from(window, head, list) {
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
- loop_nr_pages = min_t(int,
- (end_offset - loop_offset) >> PAGE_SHIFT,
- nr_pages_left);
- scif_init_window_iter(window, &src_win_iter);
- for (i = 0; i < loop_nr_pages; i++) {
- phys_addr = scif_off_to_dma_addr(window, loop_offset,
- &contig_bytes,
- &src_win_iter);
- phys_addr = scif_get_phys(phys_addr, ep);
- err = remap_pfn_range(vma,
- vma->vm_start +
- loop_offset - offset,
- phys_addr >> PAGE_SHIFT,
- PAGE_SIZE,
- vma->vm_page_prot);
- if (err)
- goto error;
- loop_offset += PAGE_SIZE;
- }
- nr_pages_left -= loop_nr_pages;
- if (!nr_pages_left)
- break;
- }
- /*
- * No more failures expected. Bump up the ref count for all
- * the windows. Another traversal from start_window required
- * for handling errors encountered across windows during
- * remap_pfn_range(..).
- */
- loop_offset = offset;
- nr_pages_left = nr_pages;
- window = start_window;
- head = &ep->rma_info.remote_reg_list;
- list_for_each_entry_from(window, head, list) {
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
- loop_nr_pages = min_t(int,
- (end_offset - loop_offset) >> PAGE_SHIFT,
- nr_pages_left);
- scif_get_window(window, loop_nr_pages);
- nr_pages_left -= loop_nr_pages;
- loop_offset += (loop_nr_pages << PAGE_SHIFT);
- if (!nr_pages_left)
- break;
- }
-error:
- if (err)
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n", __func__, __LINE__, err);
- return err;
-}
-
-/*
- * scif_rma_list_munmap:
- *
- * Traverse the remote registration list starting from window:
- * 1) Decrement ref count.
- * 2) If the ref count drops to zero then send a SCIF_MUNMAP message to peer.
- * RMA lock must be held.
- */
-static void scif_rma_list_munmap(struct scif_window *start_window,
- s64 offset, int nr_pages)
-{
- struct scifmsg msg;
- s64 loop_offset = offset, end_offset;
- int loop_nr_pages, nr_pages_left = nr_pages;
- struct scif_endpt *ep = (struct scif_endpt *)start_window->ep;
- struct list_head *head = &ep->rma_info.remote_reg_list;
- struct scif_window *window = start_window, *_window;
-
- msg.uop = SCIF_MUNMAP;
- msg.src = ep->port;
- loop_offset = offset;
- nr_pages_left = nr_pages;
- list_for_each_entry_safe_from(window, _window, head, list) {
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
- loop_nr_pages = min_t(int,
- (end_offset - loop_offset) >> PAGE_SHIFT,
- nr_pages_left);
- scif_put_window(window, loop_nr_pages);
- if (!window->ref_count) {
- struct scif_dev *rdev = ep->remote_dev;
-
- scif_drain_dma_intr(rdev->sdev,
- ep->rma_info.dma_chan);
- /* Inform the peer about this munmap */
- msg.payload[0] = window->peer_window;
- /* No error handling for Notification messages. */
- scif_nodeqp_send(ep->remote_dev, &msg);
- list_del(&window->list);
- /* Destroy this window from the peer's registered AS */
- scif_destroy_remote_window(window);
- }
- nr_pages_left -= loop_nr_pages;
- loop_offset += (loop_nr_pages << PAGE_SHIFT);
- if (!nr_pages_left)
- break;
- }
-}
-
-/*
- * The private data field of each VMA used to mmap a remote window
- * points to an instance of struct vma_pvt
- */
-struct vma_pvt {
- struct scif_endpt *ep; /* End point for remote window */
- s64 offset; /* offset within remote window */
- bool valid_offset; /* offset is valid only if the original
- * mmap request was for a single page
- * else the offset within the vma is
- * the correct offset
- */
- struct kref ref;
-};
-
-static void vma_pvt_release(struct kref *ref)
-{
- struct vma_pvt *vmapvt = container_of(ref, struct vma_pvt, ref);
-
- kfree(vmapvt);
-}
-
-/**
- * scif_vma_open - VMA open driver callback
- * @vma: VMM memory area.
- * The open method is called by the kernel to allow the subsystem implementing
- * the VMA to initialize the area. This method is invoked any time a new
- * reference to the VMA is made (when a process forks, for example).
- * The one exception happens when the VMA is first created by mmap;
- * in this case, the driver's mmap method is called instead.
- * This function is also invoked when an existing VMA is split by the kernel
- * due to a call to munmap on a subset of the VMA resulting in two VMAs.
- * The kernel invokes this function only on one of the two VMAs.
- */
-static void scif_vma_open(struct vm_area_struct *vma)
-{
- struct vma_pvt *vmapvt = vma->vm_private_data;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI vma open: vma_start 0x%lx vma_end 0x%lx\n",
- vma->vm_start, vma->vm_end);
- scif_insert_vma(vmapvt->ep, vma);
- kref_get(&vmapvt->ref);
-}
-
-/**
- * scif_munmap - VMA close driver callback.
- * @vma: VMM memory area.
- * When an area is destroyed, the kernel calls its close operation.
- * Note that there's no usage count associated with VMA's; the area
- * is opened and closed exactly once by each process that uses it.
- */
-static void scif_munmap(struct vm_area_struct *vma)
-{
- struct scif_endpt *ep;
- struct vma_pvt *vmapvt = vma->vm_private_data;
- int nr_pages = vma_pages(vma);
- s64 offset;
- struct scif_rma_req req;
- struct scif_window *window = NULL;
- int err;
-
- might_sleep();
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI munmap: vma_start 0x%lx vma_end 0x%lx\n",
- vma->vm_start, vma->vm_end);
- ep = vmapvt->ep;
- offset = vmapvt->valid_offset ? vmapvt->offset :
- (vma->vm_pgoff) << PAGE_SHIFT;
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI munmap: ep %p nr_pages 0x%x offset 0x%llx\n",
- ep, nr_pages, offset);
- req.out_window = &window;
- req.offset = offset;
- req.nr_bytes = vma->vm_end - vma->vm_start;
- req.prot = vma->vm_flags & (VM_READ | VM_WRITE);
- req.type = SCIF_WINDOW_PARTIAL;
- req.head = &ep->rma_info.remote_reg_list;
-
- mutex_lock(&ep->rma_info.rma_lock);
-
- err = scif_query_window(&req);
- if (err)
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n", __func__, __LINE__, err);
- else
- scif_rma_list_munmap(window, offset, nr_pages);
-
- mutex_unlock(&ep->rma_info.rma_lock);
- /*
- * The kernel probably zeroes these out but we still want
- * to clean up our own mess just in case.
- */
- vma->vm_ops = NULL;
- vma->vm_private_data = NULL;
- kref_put(&vmapvt->ref, vma_pvt_release);
- scif_delete_vma(ep, vma);
-}
-
-static const struct vm_operations_struct scif_vm_ops = {
- .open = scif_vma_open,
- .close = scif_munmap,
-};
-
-/**
- * scif_mmap - Map pages in virtual address space to a remote window.
- * @vma: VMM memory area.
- * @epd: endpoint descriptor
- *
- * Return: Upon successful completion, scif_mmap() returns zero
- * else an apt error is returned as documented in scif.h
- */
-int scif_mmap(struct vm_area_struct *vma, scif_epd_t epd)
-{
- struct scif_rma_req req;
- struct scif_window *window = NULL;
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- s64 start_offset = vma->vm_pgoff << PAGE_SHIFT;
- int nr_pages = vma_pages(vma);
- int err;
- struct vma_pvt *vmapvt;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI mmap: ep %p start_offset 0x%llx nr_pages 0x%x\n",
- ep, start_offset, nr_pages);
- err = scif_verify_epd(ep);
- if (err)
- return err;
-
- might_sleep();
-
- err = scif_insert_vma(ep, vma);
- if (err)
- return err;
-
- vmapvt = kzalloc(sizeof(*vmapvt), GFP_KERNEL);
- if (!vmapvt) {
- scif_delete_vma(ep, vma);
- return -ENOMEM;
- }
-
- vmapvt->ep = ep;
- kref_init(&vmapvt->ref);
-
- req.out_window = &window;
- req.offset = start_offset;
- req.nr_bytes = vma->vm_end - vma->vm_start;
- req.prot = vma->vm_flags & (VM_READ | VM_WRITE);
- req.type = SCIF_WINDOW_PARTIAL;
- req.head = &ep->rma_info.remote_reg_list;
-
- mutex_lock(&ep->rma_info.rma_lock);
- /* Does a valid window exist? */
- err = scif_query_window(&req);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto error_unlock;
- }
-
- /* Default prot for loopback */
- if (!scifdev_self(ep->remote_dev))
- vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
-
- /*
- * VM_DONTCOPY - Do not copy this vma on fork
- * VM_DONTEXPAND - Cannot expand with mremap()
- * VM_RESERVED - Count as reserved_vm like IO
- * VM_PFNMAP - Page-ranges managed without "struct page"
- * VM_IO - Memory mapped I/O or similar
- *
- * We do not want to copy this VMA automatically on a fork(),
- * expand this VMA due to mremap() or swap out these pages since
- * the VMA is actually backed by physical pages in the remote
- * node's physical memory and not via a struct page.
- */
- vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP;
-
- if (!scifdev_self(ep->remote_dev))
- vma->vm_flags |= VM_IO | VM_PFNMAP;
-
- /* Map this range of windows */
- err = scif_rma_list_mmap(window, start_offset, nr_pages, vma);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto error_unlock;
- }
- /* Set up the driver call back */
- vma->vm_ops = &scif_vm_ops;
- vma->vm_private_data = vmapvt;
-error_unlock:
- mutex_unlock(&ep->rma_info.rma_lock);
- if (err) {
- kfree(vmapvt);
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- scif_delete_vma(ep, vma);
- }
- return err;
-}
diff --git a/drivers/misc/mic/scif/scif_nm.c b/drivers/misc/mic/scif/scif_nm.c
deleted file mode 100644
index c4d9422..0000000
--- a/drivers/misc/mic/scif/scif_nm.c
+++ /dev/null
@@ -1,229 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_peer_bus.h"
-
-#include "scif_main.h"
-#include "scif_map.h"
-
-/**
- * scif_invalidate_ep() - Set state for all connected endpoints
- * to disconnected and wake up all send/recv waitqueues
- *
- * @node: Node to invalidate
- */
-static void scif_invalidate_ep(int node)
-{
- struct scif_endpt *ep;
- struct list_head *pos, *tmpq;
-
- flush_work(&scif_info.conn_work);
- mutex_lock(&scif_info.connlock);
- list_for_each_safe(pos, tmpq, &scif_info.disconnected) {
- ep = list_entry(pos, struct scif_endpt, list);
- if (ep->remote_dev->node == node) {
- scif_unmap_all_windows(ep);
- spin_lock(&ep->lock);
- scif_cleanup_ep_qp(ep);
- spin_unlock(&ep->lock);
- }
- }
- list_for_each_safe(pos, tmpq, &scif_info.connected) {
- ep = list_entry(pos, struct scif_endpt, list);
- if (ep->remote_dev->node == node) {
- list_del(pos);
- spin_lock(&ep->lock);
- ep->state = SCIFEP_DISCONNECTED;
- list_add_tail(&ep->list, &scif_info.disconnected);
- scif_cleanup_ep_qp(ep);
- wake_up_interruptible(&ep->sendwq);
- wake_up_interruptible(&ep->recvwq);
- spin_unlock(&ep->lock);
- scif_unmap_all_windows(ep);
- }
- }
- mutex_unlock(&scif_info.connlock);
-}
-
-void scif_free_qp(struct scif_dev *scifdev)
-{
- struct scif_qp *qp = scifdev->qpairs;
-
- if (!qp)
- return;
- scif_unmap_single(qp->local_buf, scifdev, qp->inbound_q.size);
- kfree(qp->inbound_q.rb_base);
- scif_unmap_single(qp->local_qp, scifdev, sizeof(struct scif_qp));
- kfree(scifdev->qpairs);
- scifdev->qpairs = NULL;
-}
-
-static void scif_cleanup_qp(struct scif_dev *dev)
-{
- struct scif_qp *qp = &dev->qpairs[0];
-
- if (!qp)
- return;
- scif_iounmap((void *)qp->remote_qp, sizeof(struct scif_qp), dev);
- scif_iounmap((void *)qp->outbound_q.rb_base,
- sizeof(struct scif_qp), dev);
- qp->remote_qp = NULL;
- qp->local_write = 0;
- qp->inbound_q.current_write_offset = 0;
- qp->inbound_q.current_read_offset = 0;
- if (scifdev_is_p2p(dev))
- scif_free_qp(dev);
-}
-
-void scif_send_acks(struct scif_dev *dev)
-{
- struct scifmsg msg;
-
- if (dev->node_remove_ack_pending) {
- msg.uop = SCIF_NODE_REMOVE_ACK;
- msg.src.node = scif_info.nodeid;
- msg.dst.node = SCIF_MGMT_NODE;
- msg.payload[0] = dev->node;
- scif_nodeqp_send(&scif_dev[SCIF_MGMT_NODE], &msg);
- dev->node_remove_ack_pending = false;
- }
- if (dev->exit_ack_pending) {
- msg.uop = SCIF_EXIT_ACK;
- msg.src.node = scif_info.nodeid;
- msg.dst.node = dev->node;
- scif_nodeqp_send(dev, &msg);
- dev->exit_ack_pending = false;
- }
-}
-
-/**
- * scif_cleanup_scifdev - Uninitialize SCIF data structures for remote
- * SCIF device.
- * @dev: Remote SCIF device.
- */
-void scif_cleanup_scifdev(struct scif_dev *dev)
-{
- struct scif_hw_dev *sdev = dev->sdev;
-
- if (!dev->sdev)
- return;
- if (scifdev_is_p2p(dev)) {
- if (dev->cookie) {
- sdev->hw_ops->free_irq(sdev, dev->cookie, dev);
- dev->cookie = NULL;
- }
- scif_destroy_intr_wq(dev);
- }
- flush_work(&scif_info.misc_work);
- scif_destroy_p2p(dev);
- scif_invalidate_ep(dev->node);
- scif_zap_mmaps(dev->node);
- scif_cleanup_rma_for_zombies(dev->node);
- flush_work(&scif_info.misc_work);
- scif_send_acks(dev);
- if (!dev->node && scif_info.card_initiated_exit) {
- /*
- * Send an SCIF_EXIT message which is the last message from MIC
- * to the Host and wait for a SCIF_EXIT_ACK
- */
- scif_send_exit(dev);
- scif_info.card_initiated_exit = false;
- }
- scif_cleanup_qp(dev);
-}
-
-/**
- * scif_remove_node
- *
- * @node: Node to remove
- */
-void scif_handle_remove_node(int node)
-{
- struct scif_dev *scifdev = &scif_dev[node];
-
- if (scif_peer_unregister_device(scifdev))
- scif_send_acks(scifdev);
-}
-
-static int scif_send_rmnode_msg(int node, int remove_node)
-{
- struct scifmsg notif_msg;
- struct scif_dev *dev = &scif_dev[node];
-
- notif_msg.uop = SCIF_NODE_REMOVE;
- notif_msg.src.node = scif_info.nodeid;
- notif_msg.dst.node = node;
- notif_msg.payload[0] = remove_node;
- return scif_nodeqp_send(dev, ¬if_msg);
-}
-
-/**
- * scif_node_disconnect
- *
- * @node_id: source node id [in]
- * @mgmt_initiated: Disconnection initiated from the mgmt node
- *
- * Disconnect a node from the scif network.
- */
-void scif_disconnect_node(u32 node_id, bool mgmt_initiated)
-{
- int ret;
- int msg_cnt = 0;
- u32 i = 0;
- struct scif_dev *scifdev = &scif_dev[node_id];
-
- if (!node_id)
- return;
-
- atomic_set(&scifdev->disconn_rescnt, 0);
-
- /* Destroy p2p network */
- for (i = 1; i <= scif_info.maxid; i++) {
- if (i == node_id)
- continue;
- ret = scif_send_rmnode_msg(i, node_id);
- if (!ret)
- msg_cnt++;
- }
- /* Wait for the remote nodes to respond with SCIF_NODE_REMOVE_ACK */
- ret = wait_event_timeout(scifdev->disconn_wq,
- (atomic_read(&scifdev->disconn_rescnt)
- == msg_cnt), SCIF_NODE_ALIVE_TIMEOUT);
- /* Tell the card to clean up */
- if (mgmt_initiated && _scifdev_alive(scifdev))
- /*
- * Send an SCIF_EXIT message which is the last message from Host
- * to the MIC and wait for a SCIF_EXIT_ACK
- */
- scif_send_exit(scifdev);
- atomic_set(&scifdev->disconn_rescnt, 0);
- /* Tell the mgmt node to clean up */
- ret = scif_send_rmnode_msg(SCIF_MGMT_NODE, node_id);
- if (!ret)
- /* Wait for mgmt node to respond with SCIF_NODE_REMOVE_ACK */
- wait_event_timeout(scifdev->disconn_wq,
- (atomic_read(&scifdev->disconn_rescnt) == 1),
- SCIF_NODE_ALIVE_TIMEOUT);
-}
-
-void scif_get_node_info(void)
-{
- struct scifmsg msg;
- DECLARE_COMPLETION_ONSTACK(node_info);
-
- msg.uop = SCIF_GET_NODE_INFO;
- msg.src.node = scif_info.nodeid;
- msg.dst.node = SCIF_MGMT_NODE;
- msg.payload[3] = (u64)&node_info;
-
- if ((scif_nodeqp_send(&scif_dev[SCIF_MGMT_NODE], &msg)))
- return;
-
- /* Wait for a response with SCIF_GET_NODE_INFO */
- wait_for_completion(&node_info);
-}
diff --git a/drivers/misc/mic/scif/scif_nodeqp.c b/drivers/misc/mic/scif/scif_nodeqp.c
deleted file mode 100644
index 384ce08..0000000
--- a/drivers/misc/mic/scif/scif_nodeqp.c
+++ /dev/null
@@ -1,1349 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "../bus/scif_bus.h"
-#include "scif_peer_bus.h"
-#include "scif_main.h"
-#include "scif_nodeqp.h"
-#include "scif_map.h"
-
-/*
- ************************************************************************
- * SCIF node Queue Pair (QP) setup flow:
- *
- * 1) SCIF driver gets probed with a scif_hw_dev via the scif_hw_bus
- * 2) scif_setup_qp(..) allocates the local qp and calls
- * scif_setup_qp_connect(..) which allocates and maps the local
- * buffer for the inbound QP
- * 3) The local node updates the device page with the DMA address of the QP
- * 4) A delayed work is scheduled (qp_dwork) which periodically reads if
- * the peer node has updated its QP DMA address
- * 5) Once a valid non zero address is found in the QP DMA address field
- * in the device page, the local node maps the remote node's QP,
- * updates its outbound QP and sends a SCIF_INIT message to the peer
- * 6) The SCIF_INIT message is received by the peer node QP interrupt bottom
- * half handler by calling scif_init(..)
- * 7) scif_init(..) registers a new SCIF peer node by calling
- * scif_peer_register_device(..) which signifies the addition of a new
- * SCIF node
- * 8) On the mgmt node, P2P network setup/teardown is initiated if all the
- * remote nodes are online via scif_p2p_setup(..)
- * 9) For P2P setup, the host maps the remote nodes' aperture and memory
- * bars and sends a SCIF_NODE_ADD message to both nodes
- * 10) As part of scif_nodeadd, both nodes set up their local inbound
- * QPs and send a SCIF_NODE_ADD_ACK to the mgmt node
- * 11) As part of scif_node_add_ack(..) the mgmt node forwards the
- * SCIF_NODE_ADD_ACK to the remote nodes
- * 12) As part of scif_node_add_ack(..) the remote nodes update their
- * outbound QPs, make sure they can access memory on the remote node
- * and then add a new SCIF peer node by calling
- * scif_peer_register_device(..) which signifies the addition of a new
- * SCIF node.
- * 13) The SCIF network is now established across all nodes.
- *
- ************************************************************************
- * SCIF node QP teardown flow (initiated by non mgmt node):
- *
- * 1) SCIF driver gets a remove callback with a scif_hw_dev via the scif_hw_bus
- * 2) The device page QP DMA address field is updated with 0x0
- * 3) A non mgmt node now cleans up all local data structures and sends a
- * SCIF_EXIT message to the peer and waits for a SCIF_EXIT_ACK
- * 4) As part of scif_exit(..) handling scif_disconnect_node(..) is called
- * 5) scif_disconnect_node(..) sends a SCIF_NODE_REMOVE message to all the
- * peers and waits for a SCIF_NODE_REMOVE_ACK
- * 6) As part of scif_node_remove(..) a remote node unregisters the peer
- * node from the SCIF network and sends a SCIF_NODE_REMOVE_ACK
- * 7) When the mgmt node has received all the SCIF_NODE_REMOVE_ACKs
- * it sends itself a node remove message whose handling cleans up local
- * data structures and unregisters the peer node from the SCIF network
- * 8) The mgmt node sends a SCIF_EXIT_ACK
- * 9) Upon receipt of the SCIF_EXIT_ACK the node initiating the teardown
- * completes the SCIF remove routine
- * 10) The SCIF network is now torn down for the node initiating the
- * teardown sequence
- *
- ************************************************************************
- * SCIF node QP teardown flow (initiated by mgmt node):
- *
- * 1) SCIF driver gets a remove callback with a scif_hw_dev via the scif_hw_bus
- * 2) The device page QP DMA address field is updated with 0x0
- * 3) The mgmt node calls scif_disconnect_node(..)
- * 4) scif_disconnect_node(..) sends a SCIF_NODE_REMOVE message to all the peers
- * and waits for a SCIF_NODE_REMOVE_ACK
- * 5) As part of scif_node_remove(..) a remote node unregisters the peer
- * node from the SCIF network and sends a SCIF_NODE_REMOVE_ACK
- * 6) When the mgmt node has received all the SCIF_NODE_REMOVE_ACKs
- * it unregisters the peer node from the SCIF network
- * 7) The mgmt node sends a SCIF_EXIT message and waits for a SCIF_EXIT_ACK.
- * 8) A non mgmt node upon receipt of a SCIF_EXIT message calls scif_stop(..)
- * which would clean up local data structures for all SCIF nodes and
- * then send a SCIF_EXIT_ACK back to the mgmt node
- * 9) Upon receipt of the SCIF_EXIT_ACK the the mgmt node sends itself a node
- * remove message whose handling cleans up local data structures and
- * destroys any P2P mappings.
- * 10) The SCIF hardware device for which a remove callback was received is now
- * disconnected from the SCIF network.
- */
-/*
- * Initializes "local" data structures for the QP. Allocates the QP
- * ring buffer (rb) and initializes the "in bound" queue.
- */
-int scif_setup_qp_connect(struct scif_qp *qp, dma_addr_t *qp_offset,
- int local_size, struct scif_dev *scifdev)
-{
- void *local_q = qp->inbound_q.rb_base;
- int err = 0;
- u32 tmp_rd = 0;
-
- spin_lock_init(&qp->send_lock);
- spin_lock_init(&qp->recv_lock);
-
- /* Allocate rb only if not already allocated */
- if (!local_q) {
- local_q = kzalloc(local_size, GFP_KERNEL);
- if (!local_q) {
- err = -ENOMEM;
- return err;
- }
- }
-
- err = scif_map_single(&qp->local_buf, local_q, scifdev, local_size);
- if (err)
- goto kfree;
- /*
- * To setup the inbound_q, the buffer lives locally, the read pointer
- * is remote and the write pointer is local.
- */
- scif_rb_init(&qp->inbound_q,
- &tmp_rd,
- &qp->local_write,
- local_q, get_count_order(local_size));
- /*
- * The read pointer is NULL initially and it is unsafe to use the ring
- * buffer til this changes!
- */
- qp->inbound_q.read_ptr = NULL;
- err = scif_map_single(qp_offset, qp,
- scifdev, sizeof(struct scif_qp));
- if (err)
- goto unmap;
- qp->local_qp = *qp_offset;
- return err;
-unmap:
- scif_unmap_single(qp->local_buf, scifdev, local_size);
- qp->local_buf = 0;
-kfree:
- kfree(local_q);
- return err;
-}
-
-/* When the other side has already done it's allocation, this is called */
-int scif_setup_qp_accept(struct scif_qp *qp, dma_addr_t *qp_offset,
- dma_addr_t phys, int local_size,
- struct scif_dev *scifdev)
-{
- void *local_q;
- void *remote_q;
- struct scif_qp *remote_qp;
- int remote_size;
- int err = 0;
-
- spin_lock_init(&qp->send_lock);
- spin_lock_init(&qp->recv_lock);
- /* Start by figuring out where we need to point */
- remote_qp = scif_ioremap(phys, sizeof(struct scif_qp), scifdev);
- if (!remote_qp)
- return -EIO;
- qp->remote_qp = remote_qp;
- if (qp->remote_qp->magic != SCIFEP_MAGIC) {
- err = -EIO;
- goto iounmap;
- }
- qp->remote_buf = remote_qp->local_buf;
- remote_size = qp->remote_qp->inbound_q.size;
- remote_q = scif_ioremap(qp->remote_buf, remote_size, scifdev);
- if (!remote_q) {
- err = -EIO;
- goto iounmap;
- }
- qp->remote_qp->local_write = 0;
- /*
- * To setup the outbound_q, the buffer lives in remote memory,
- * the read pointer is local, the write pointer is remote
- */
- scif_rb_init(&qp->outbound_q,
- &qp->local_read,
- &qp->remote_qp->local_write,
- remote_q,
- get_count_order(remote_size));
- local_q = kzalloc(local_size, GFP_KERNEL);
- if (!local_q) {
- err = -ENOMEM;
- goto iounmap_1;
- }
- err = scif_map_single(&qp->local_buf, local_q, scifdev, local_size);
- if (err)
- goto kfree;
- qp->remote_qp->local_read = 0;
- /*
- * To setup the inbound_q, the buffer lives locally, the read pointer
- * is remote and the write pointer is local
- */
- scif_rb_init(&qp->inbound_q,
- &qp->remote_qp->local_read,
- &qp->local_write,
- local_q, get_count_order(local_size));
- err = scif_map_single(qp_offset, qp, scifdev,
- sizeof(struct scif_qp));
- if (err)
- goto unmap;
- qp->local_qp = *qp_offset;
- return err;
-unmap:
- scif_unmap_single(qp->local_buf, scifdev, local_size);
- qp->local_buf = 0;
-kfree:
- kfree(local_q);
-iounmap_1:
- scif_iounmap(remote_q, remote_size, scifdev);
- qp->outbound_q.rb_base = NULL;
-iounmap:
- scif_iounmap(qp->remote_qp, sizeof(struct scif_qp), scifdev);
- qp->remote_qp = NULL;
- return err;
-}
-
-int scif_setup_qp_connect_response(struct scif_dev *scifdev,
- struct scif_qp *qp, u64 payload)
-{
- int err = 0;
- void *r_buf;
- int remote_size;
- phys_addr_t tmp_phys;
-
- qp->remote_qp = scif_ioremap(payload, sizeof(struct scif_qp), scifdev);
-
- if (!qp->remote_qp) {
- err = -ENOMEM;
- goto error;
- }
-
- if (qp->remote_qp->magic != SCIFEP_MAGIC) {
- dev_err(&scifdev->sdev->dev,
- "SCIFEP_MAGIC mismatch between self %d remote %d\n",
- scif_dev[scif_info.nodeid].node, scifdev->node);
- err = -ENODEV;
- goto error;
- }
-
- tmp_phys = qp->remote_qp->local_buf;
- remote_size = qp->remote_qp->inbound_q.size;
- r_buf = scif_ioremap(tmp_phys, remote_size, scifdev);
-
- if (!r_buf)
- return -EIO;
-
- qp->local_read = 0;
- scif_rb_init(&qp->outbound_q,
- &qp->local_read,
- &qp->remote_qp->local_write,
- r_buf,
- get_count_order(remote_size));
- /*
- * Because the node QP may already be processing an INIT message, set
- * the read pointer so the cached read offset isn't lost
- */
- qp->remote_qp->local_read = qp->inbound_q.current_read_offset;
- /*
- * resetup the inbound_q now that we know where the
- * inbound_read really is.
- */
- scif_rb_init(&qp->inbound_q,
- &qp->remote_qp->local_read,
- &qp->local_write,
- qp->inbound_q.rb_base,
- get_count_order(qp->inbound_q.size));
-error:
- return err;
-}
-
-static __always_inline void
-scif_send_msg_intr(struct scif_dev *scifdev)
-{
- struct scif_hw_dev *sdev = scifdev->sdev;
-
- if (scifdev_is_p2p(scifdev))
- sdev->hw_ops->send_p2p_intr(sdev, scifdev->rdb, &scifdev->mmio);
- else
- sdev->hw_ops->send_intr(sdev, scifdev->rdb);
-}
-
-int scif_qp_response(phys_addr_t phys, struct scif_dev *scifdev)
-{
- int err = 0;
- struct scifmsg msg;
-
- err = scif_setup_qp_connect_response(scifdev, scifdev->qpairs, phys);
- if (!err) {
- /*
- * Now that everything is setup and mapped, we're ready
- * to tell the peer about our queue's location
- */
- msg.uop = SCIF_INIT;
- msg.dst.node = scifdev->node;
- err = scif_nodeqp_send(scifdev, &msg);
- }
- return err;
-}
-
-void scif_send_exit(struct scif_dev *scifdev)
-{
- struct scifmsg msg;
- int ret;
-
- scifdev->exit = OP_IN_PROGRESS;
- msg.uop = SCIF_EXIT;
- msg.src.node = scif_info.nodeid;
- msg.dst.node = scifdev->node;
- ret = scif_nodeqp_send(scifdev, &msg);
- if (ret)
- goto done;
- /* Wait for a SCIF_EXIT_ACK message */
- wait_event_timeout(scif_info.exitwq, scifdev->exit == OP_COMPLETED,
- SCIF_NODE_ALIVE_TIMEOUT);
-done:
- scifdev->exit = OP_IDLE;
-}
-
-int scif_setup_qp(struct scif_dev *scifdev)
-{
- int err = 0;
- int local_size;
- struct scif_qp *qp;
-
- local_size = SCIF_NODE_QP_SIZE;
-
- qp = kzalloc(sizeof(*qp), GFP_KERNEL);
- if (!qp) {
- err = -ENOMEM;
- return err;
- }
- qp->magic = SCIFEP_MAGIC;
- scifdev->qpairs = qp;
- err = scif_setup_qp_connect(qp, &scifdev->qp_dma_addr,
- local_size, scifdev);
- if (err)
- goto free_qp;
- /*
- * We're as setup as we can be. The inbound_q is setup, w/o a usable
- * outbound q. When we get a message, the read_ptr will be updated,
- * and we will pull the message.
- */
- return err;
-free_qp:
- kfree(scifdev->qpairs);
- scifdev->qpairs = NULL;
- return err;
-}
-
-static void scif_p2p_freesg(struct scatterlist *sg)
-{
- kfree(sg);
-}
-
-static struct scatterlist *
-scif_p2p_setsg(phys_addr_t pa, int page_size, int page_cnt)
-{
- struct scatterlist *sg;
- struct page *page;
- int i;
-
- sg = kmalloc_array(page_cnt, sizeof(struct scatterlist), GFP_KERNEL);
- if (!sg)
- return NULL;
- sg_init_table(sg, page_cnt);
- for (i = 0; i < page_cnt; i++) {
- page = pfn_to_page(pa >> PAGE_SHIFT);
- sg_set_page(&sg[i], page, page_size, 0);
- pa += page_size;
- }
- return sg;
-}
-
-/* Init p2p mappings required to access peerdev from scifdev */
-static struct scif_p2p_info *
-scif_init_p2p_info(struct scif_dev *scifdev, struct scif_dev *peerdev)
-{
- struct scif_p2p_info *p2p;
- int num_mmio_pages, num_aper_pages, sg_page_shift, err, num_aper_chunks;
- struct scif_hw_dev *psdev = peerdev->sdev;
- struct scif_hw_dev *sdev = scifdev->sdev;
-
- num_mmio_pages = psdev->mmio->len >> PAGE_SHIFT;
- num_aper_pages = psdev->aper->len >> PAGE_SHIFT;
-
- p2p = kzalloc(sizeof(*p2p), GFP_KERNEL);
- if (!p2p)
- return NULL;
- p2p->ppi_sg[SCIF_PPI_MMIO] = scif_p2p_setsg(psdev->mmio->pa,
- PAGE_SIZE, num_mmio_pages);
- if (!p2p->ppi_sg[SCIF_PPI_MMIO])
- goto free_p2p;
- p2p->sg_nentries[SCIF_PPI_MMIO] = num_mmio_pages;
- sg_page_shift = get_order(min(psdev->aper->len, (u64)(1 << 30)));
- num_aper_chunks = num_aper_pages >> (sg_page_shift - PAGE_SHIFT);
- p2p->ppi_sg[SCIF_PPI_APER] = scif_p2p_setsg(psdev->aper->pa,
- 1 << sg_page_shift,
- num_aper_chunks);
- p2p->sg_nentries[SCIF_PPI_APER] = num_aper_chunks;
- err = dma_map_sg(&sdev->dev, p2p->ppi_sg[SCIF_PPI_MMIO],
- num_mmio_pages, PCI_DMA_BIDIRECTIONAL);
- if (err != num_mmio_pages)
- goto scif_p2p_free;
- err = dma_map_sg(&sdev->dev, p2p->ppi_sg[SCIF_PPI_APER],
- num_aper_chunks, PCI_DMA_BIDIRECTIONAL);
- if (err != num_aper_chunks)
- goto dma_unmap;
- p2p->ppi_da[SCIF_PPI_MMIO] = sg_dma_address(p2p->ppi_sg[SCIF_PPI_MMIO]);
- p2p->ppi_da[SCIF_PPI_APER] = sg_dma_address(p2p->ppi_sg[SCIF_PPI_APER]);
- p2p->ppi_len[SCIF_PPI_MMIO] = num_mmio_pages;
- p2p->ppi_len[SCIF_PPI_APER] = num_aper_pages;
- p2p->ppi_peer_id = peerdev->node;
- return p2p;
-dma_unmap:
- dma_unmap_sg(&sdev->dev, p2p->ppi_sg[SCIF_PPI_MMIO],
- p2p->sg_nentries[SCIF_PPI_MMIO], DMA_BIDIRECTIONAL);
-scif_p2p_free:
- scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_MMIO]);
- scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_APER]);
-free_p2p:
- kfree(p2p);
- return NULL;
-}
-
-/* Uninitialize and release resources from a p2p mapping */
-static void scif_deinit_p2p_info(struct scif_dev *scifdev,
- struct scif_p2p_info *p2p)
-{
- struct scif_hw_dev *sdev = scifdev->sdev;
-
- dma_unmap_sg(&sdev->dev, p2p->ppi_sg[SCIF_PPI_MMIO],
- p2p->sg_nentries[SCIF_PPI_MMIO], DMA_BIDIRECTIONAL);
- dma_unmap_sg(&sdev->dev, p2p->ppi_sg[SCIF_PPI_APER],
- p2p->sg_nentries[SCIF_PPI_APER], DMA_BIDIRECTIONAL);
- scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_MMIO]);
- scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_APER]);
- kfree(p2p);
-}
-
-/**
- * scif_node_connect: Respond to SCIF_NODE_CONNECT interrupt message
- * @scifdev: SCIF device
- * @dst: Destination node
- *
- * Connect the src and dst node by setting up the p2p connection
- * between them. Management node here acts like a proxy.
- */
-static void scif_node_connect(struct scif_dev *scifdev, int dst)
-{
- struct scif_dev *dev_j = scifdev;
- struct scif_dev *dev_i = NULL;
- struct scif_p2p_info *p2p_ij = NULL; /* bus addr for j from i */
- struct scif_p2p_info *p2p_ji = NULL; /* bus addr for i from j */
- struct scif_p2p_info *p2p;
- struct list_head *pos, *tmp;
- struct scifmsg msg;
- int err;
- u64 tmppayload;
-
- if (dst < 1 || dst > scif_info.maxid)
- return;
-
- dev_i = &scif_dev[dst];
-
- if (!_scifdev_alive(dev_i))
- return;
- /*
- * If the p2p connection is already setup or in the process of setting
- * up then just ignore this request. The requested node will get
- * informed by SCIF_NODE_ADD_ACK or SCIF_NODE_ADD_NACK
- */
- if (!list_empty(&dev_i->p2p)) {
- list_for_each_safe(pos, tmp, &dev_i->p2p) {
- p2p = list_entry(pos, struct scif_p2p_info, ppi_list);
- if (p2p->ppi_peer_id == dev_j->node)
- return;
- }
- }
- p2p_ij = scif_init_p2p_info(dev_i, dev_j);
- if (!p2p_ij)
- return;
- p2p_ji = scif_init_p2p_info(dev_j, dev_i);
- if (!p2p_ji) {
- scif_deinit_p2p_info(dev_i, p2p_ij);
- return;
- }
- list_add_tail(&p2p_ij->ppi_list, &dev_i->p2p);
- list_add_tail(&p2p_ji->ppi_list, &dev_j->p2p);
-
- /*
- * Send a SCIF_NODE_ADD to dev_i, pass it its bus address
- * as seen from dev_j
- */
- msg.uop = SCIF_NODE_ADD;
- msg.src.node = dev_j->node;
- msg.dst.node = dev_i->node;
-
- msg.payload[0] = p2p_ji->ppi_da[SCIF_PPI_APER];
- msg.payload[1] = p2p_ij->ppi_da[SCIF_PPI_MMIO];
- msg.payload[2] = p2p_ij->ppi_da[SCIF_PPI_APER];
- msg.payload[3] = p2p_ij->ppi_len[SCIF_PPI_APER] << PAGE_SHIFT;
-
- err = scif_nodeqp_send(dev_i, &msg);
- if (err) {
- dev_err(&scifdev->sdev->dev,
- "%s %d error %d\n", __func__, __LINE__, err);
- return;
- }
-
- /* Same as above but to dev_j */
- msg.uop = SCIF_NODE_ADD;
- msg.src.node = dev_i->node;
- msg.dst.node = dev_j->node;
-
- tmppayload = msg.payload[0];
- msg.payload[0] = msg.payload[2];
- msg.payload[2] = tmppayload;
- msg.payload[1] = p2p_ji->ppi_da[SCIF_PPI_MMIO];
- msg.payload[3] = p2p_ji->ppi_len[SCIF_PPI_APER] << PAGE_SHIFT;
-
- scif_nodeqp_send(dev_j, &msg);
-}
-
-static void scif_p2p_setup(void)
-{
- int i, j;
-
- if (!scif_info.p2p_enable)
- return;
-
- for (i = 1; i <= scif_info.maxid; i++)
- if (!_scifdev_alive(&scif_dev[i]))
- return;
-
- for (i = 1; i <= scif_info.maxid; i++) {
- for (j = 1; j <= scif_info.maxid; j++) {
- struct scif_dev *scifdev = &scif_dev[i];
-
- if (i == j)
- continue;
- scif_node_connect(scifdev, j);
- }
- }
-}
-
-static char *message_types[] = {"BAD",
- "INIT",
- "EXIT",
- "SCIF_EXIT_ACK",
- "SCIF_NODE_ADD",
- "SCIF_NODE_ADD_ACK",
- "SCIF_NODE_ADD_NACK",
- "REMOVE_NODE",
- "REMOVE_NODE_ACK",
- "CNCT_REQ",
- "CNCT_GNT",
- "CNCT_GNTACK",
- "CNCT_GNTNACK",
- "CNCT_REJ",
- "DISCNCT",
- "DISCNT_ACK",
- "CLIENT_SENT",
- "CLIENT_RCVD",
- "SCIF_GET_NODE_INFO",
- "REGISTER",
- "REGISTER_ACK",
- "REGISTER_NACK",
- "UNREGISTER",
- "UNREGISTER_ACK",
- "UNREGISTER_NACK",
- "ALLOC_REQ",
- "ALLOC_GNT",
- "ALLOC_REJ",
- "FREE_PHYS",
- "FREE_VIRT",
- "MUNMAP",
- "MARK",
- "MARK_ACK",
- "MARK_NACK",
- "WAIT",
- "WAIT_ACK",
- "WAIT_NACK",
- "SIGNAL_LOCAL",
- "SIGNAL_REMOTE",
- "SIG_ACK",
- "SIG_NACK"};
-
-static void
-scif_display_message(struct scif_dev *scifdev, struct scifmsg *msg,
- const char *label)
-{
- if (!scif_info.en_msg_log)
- return;
- if (msg->uop > SCIF_MAX_MSG) {
- dev_err(&scifdev->sdev->dev,
- "%s: unknown msg type %d\n", label, msg->uop);
- return;
- }
- dev_info(&scifdev->sdev->dev,
- "%s: msg type %s, src %d:%d, dest %d:%d payload 0x%llx:0x%llx:0x%llx:0x%llx\n",
- label, message_types[msg->uop], msg->src.node, msg->src.port,
- msg->dst.node, msg->dst.port, msg->payload[0], msg->payload[1],
- msg->payload[2], msg->payload[3]);
-}
-
-int _scif_nodeqp_send(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_qp *qp = scifdev->qpairs;
- int err = -ENOMEM, loop_cnt = 0;
-
- scif_display_message(scifdev, msg, "Sent");
- if (!qp) {
- err = -EINVAL;
- goto error;
- }
- spin_lock(&qp->send_lock);
-
- while ((err = scif_rb_write(&qp->outbound_q,
- msg, sizeof(struct scifmsg)))) {
- mdelay(1);
-#define SCIF_NODEQP_SEND_TO_MSEC (3 * 1000)
- if (loop_cnt++ > (SCIF_NODEQP_SEND_TO_MSEC)) {
- err = -ENODEV;
- break;
- }
- }
- if (!err)
- scif_rb_commit(&qp->outbound_q);
- spin_unlock(&qp->send_lock);
- if (!err) {
- if (scifdev_self(scifdev))
- /*
- * For loopback we need to emulate an interrupt by
- * queuing work for the queue handling real node
- * Qp interrupts.
- */
- queue_work(scifdev->intr_wq, &scifdev->intr_bh);
- else
- scif_send_msg_intr(scifdev);
- }
-error:
- if (err)
- dev_dbg(&scifdev->sdev->dev,
- "%s %d error %d uop %d\n",
- __func__, __LINE__, err, msg->uop);
- return err;
-}
-
-/**
- * scif_nodeqp_send - Send a message on the node queue pair
- * @scifdev: Scif Device.
- * @msg: The message to be sent.
- */
-int scif_nodeqp_send(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- int err;
- struct device *spdev = NULL;
-
- if (msg->uop > SCIF_EXIT_ACK) {
- /* Don't send messages once the exit flow has begun */
- if (OP_IDLE != scifdev->exit)
- return -ENODEV;
- spdev = scif_get_peer_dev(scifdev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- return err;
- }
- }
- err = _scif_nodeqp_send(scifdev, msg);
- if (msg->uop > SCIF_EXIT_ACK)
- scif_put_peer_dev(spdev);
- return err;
-}
-
-/*
- * scif_misc_handler:
- *
- * Work queue handler for servicing miscellaneous SCIF tasks.
- * Examples include:
- * 1) Remote fence requests.
- * 2) Destruction of temporary registered windows
- * created during scif_vreadfrom()/scif_vwriteto().
- * 3) Cleanup of zombie endpoints.
- */
-void scif_misc_handler(struct work_struct *work)
-{
- scif_rma_handle_remote_fences();
- scif_rma_destroy_windows();
- scif_rma_destroy_tcw_invalid();
- scif_cleanup_zombie_epd();
-}
-
-/**
- * scif_init() - Respond to SCIF_INIT interrupt message
- * @scifdev: Remote SCIF device node
- * @msg: Interrupt message
- */
-static __always_inline void
-scif_init(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- /*
- * Allow the thread waiting for device page updates for the peer QP DMA
- * address to complete initializing the inbound_q.
- */
- flush_delayed_work(&scifdev->qp_dwork);
-
- scif_peer_register_device(scifdev);
-
- if (scif_is_mgmt_node()) {
- mutex_lock(&scif_info.conflock);
- scif_p2p_setup();
- mutex_unlock(&scif_info.conflock);
- }
-}
-
-/**
- * scif_exit() - Respond to SCIF_EXIT interrupt message
- * @scifdev: Remote SCIF device node
- * @unused: Interrupt message (unused)
- *
- * This function stops the SCIF interface for the node which sent
- * the SCIF_EXIT message and starts waiting for that node to
- * resetup the queue pair again.
- */
-static __always_inline void
-scif_exit(struct scif_dev *scifdev, struct scifmsg *unused)
-{
- scifdev->exit_ack_pending = true;
- if (scif_is_mgmt_node())
- scif_disconnect_node(scifdev->node, false);
- else
- scif_stop(scifdev);
- schedule_delayed_work(&scifdev->qp_dwork,
- msecs_to_jiffies(1000));
-}
-
-/**
- * scif_exitack() - Respond to SCIF_EXIT_ACK interrupt message
- * @scifdev: Remote SCIF device node
- * @unused: Interrupt message (unused)
- *
- */
-static __always_inline void
-scif_exit_ack(struct scif_dev *scifdev, struct scifmsg *unused)
-{
- scifdev->exit = OP_COMPLETED;
- wake_up(&scif_info.exitwq);
-}
-
-/**
- * scif_node_add() - Respond to SCIF_NODE_ADD interrupt message
- * @scifdev: Remote SCIF device node
- * @msg: Interrupt message
- *
- * When the mgmt node driver has finished initializing a MIC node queue pair it
- * marks the node as online. It then looks for all currently online MIC cards
- * and send a SCIF_NODE_ADD message to identify the ID of the new card for
- * peer to peer initialization
- *
- * The local node allocates its incoming queue and sends its address in the
- * SCIF_NODE_ADD_ACK message back to the mgmt node, the mgmt node "reflects"
- * this message to the new node
- */
-static __always_inline void
-scif_node_add(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_dev *newdev;
- dma_addr_t qp_offset;
- int qp_connect;
- struct scif_hw_dev *sdev;
-
- dev_dbg(&scifdev->sdev->dev,
- "Scifdev %d:%d received NODE_ADD msg for node %d\n",
- scifdev->node, msg->dst.node, msg->src.node);
- dev_dbg(&scifdev->sdev->dev,
- "Remote address for this node's aperture %llx\n",
- msg->payload[0]);
- newdev = &scif_dev[msg->src.node];
- newdev->node = msg->src.node;
- newdev->sdev = scif_dev[SCIF_MGMT_NODE].sdev;
- sdev = newdev->sdev;
-
- if (scif_setup_intr_wq(newdev)) {
- dev_err(&scifdev->sdev->dev,
- "failed to setup interrupts for %d\n", msg->src.node);
- goto interrupt_setup_error;
- }
- newdev->mmio.va = ioremap(msg->payload[1], sdev->mmio->len);
- if (!newdev->mmio.va) {
- dev_err(&scifdev->sdev->dev,
- "failed to map mmio for %d\n", msg->src.node);
- goto mmio_map_error;
- }
- newdev->qpairs = kzalloc(sizeof(*newdev->qpairs), GFP_KERNEL);
- if (!newdev->qpairs)
- goto qp_alloc_error;
- /*
- * Set the base address of the remote node's memory since it gets
- * added to qp_offset
- */
- newdev->base_addr = msg->payload[0];
-
- qp_connect = scif_setup_qp_connect(newdev->qpairs, &qp_offset,
- SCIF_NODE_QP_SIZE, newdev);
- if (qp_connect) {
- dev_err(&scifdev->sdev->dev,
- "failed to setup qp_connect %d\n", qp_connect);
- goto qp_connect_error;
- }
-
- newdev->db = sdev->hw_ops->next_db(sdev);
- newdev->cookie = sdev->hw_ops->request_irq(sdev, scif_intr_handler,
- "SCIF_INTR", newdev,
- newdev->db);
- if (IS_ERR(newdev->cookie))
- goto qp_connect_error;
- newdev->qpairs->magic = SCIFEP_MAGIC;
- newdev->qpairs->qp_state = SCIF_QP_OFFLINE;
-
- msg->uop = SCIF_NODE_ADD_ACK;
- msg->dst.node = msg->src.node;
- msg->src.node = scif_info.nodeid;
- msg->payload[0] = qp_offset;
- msg->payload[2] = newdev->db;
- scif_nodeqp_send(&scif_dev[SCIF_MGMT_NODE], msg);
- return;
-qp_connect_error:
- kfree(newdev->qpairs);
- newdev->qpairs = NULL;
-qp_alloc_error:
- iounmap(newdev->mmio.va);
- newdev->mmio.va = NULL;
-mmio_map_error:
-interrupt_setup_error:
- dev_err(&scifdev->sdev->dev,
- "node add failed for node %d\n", msg->src.node);
- msg->uop = SCIF_NODE_ADD_NACK;
- msg->dst.node = msg->src.node;
- msg->src.node = scif_info.nodeid;
- scif_nodeqp_send(&scif_dev[SCIF_MGMT_NODE], msg);
-}
-
-void scif_poll_qp_state(struct work_struct *work)
-{
-#define SCIF_NODE_QP_RETRY 100
-#define SCIF_NODE_QP_TIMEOUT 100
- struct scif_dev *peerdev = container_of(work, struct scif_dev,
- p2p_dwork.work);
- struct scif_qp *qp = &peerdev->qpairs[0];
-
- if (qp->qp_state != SCIF_QP_ONLINE ||
- qp->remote_qp->qp_state != SCIF_QP_ONLINE) {
- if (peerdev->p2p_retry++ == SCIF_NODE_QP_RETRY) {
- dev_err(&peerdev->sdev->dev,
- "Warning: QP check timeout with state %d\n",
- qp->qp_state);
- goto timeout;
- }
- schedule_delayed_work(&peerdev->p2p_dwork,
- msecs_to_jiffies(SCIF_NODE_QP_TIMEOUT));
- return;
- }
- return;
-timeout:
- dev_err(&peerdev->sdev->dev,
- "%s %d remote node %d offline, state = 0x%x\n",
- __func__, __LINE__, peerdev->node, qp->qp_state);
- qp->remote_qp->qp_state = SCIF_QP_OFFLINE;
- scif_peer_unregister_device(peerdev);
- scif_cleanup_scifdev(peerdev);
-}
-
-/**
- * scif_node_add_ack() - Respond to SCIF_NODE_ADD_ACK interrupt message
- * @scifdev: Remote SCIF device node
- * @msg: Interrupt message
- *
- * After a MIC node receives the SCIF_NODE_ADD_ACK message it send this
- * message to the mgmt node to confirm the sequence is finished.
- *
- */
-static __always_inline void
-scif_node_add_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_dev *peerdev;
- struct scif_qp *qp;
- struct scif_dev *dst_dev = &scif_dev[msg->dst.node];
-
- dev_dbg(&scifdev->sdev->dev,
- "Scifdev %d received SCIF_NODE_ADD_ACK msg src %d dst %d\n",
- scifdev->node, msg->src.node, msg->dst.node);
- dev_dbg(&scifdev->sdev->dev,
- "payload %llx %llx %llx %llx\n", msg->payload[0],
- msg->payload[1], msg->payload[2], msg->payload[3]);
- if (scif_is_mgmt_node()) {
- /*
- * the lock serializes with scif_qp_response_ack. The mgmt node
- * is forwarding the NODE_ADD_ACK message from src to dst we
- * need to make sure that the dst has already received a
- * NODE_ADD for src and setup its end of the qp to dst
- */
- mutex_lock(&scif_info.conflock);
- msg->payload[1] = scif_info.maxid;
- scif_nodeqp_send(dst_dev, msg);
- mutex_unlock(&scif_info.conflock);
- return;
- }
- peerdev = &scif_dev[msg->src.node];
- peerdev->sdev = scif_dev[SCIF_MGMT_NODE].sdev;
- peerdev->node = msg->src.node;
-
- qp = &peerdev->qpairs[0];
-
- if ((scif_setup_qp_connect_response(peerdev, &peerdev->qpairs[0],
- msg->payload[0])))
- goto local_error;
- peerdev->rdb = msg->payload[2];
- qp->remote_qp->qp_state = SCIF_QP_ONLINE;
-
- scif_peer_register_device(peerdev);
-
- schedule_delayed_work(&peerdev->p2p_dwork, 0);
- return;
-local_error:
- scif_cleanup_scifdev(peerdev);
-}
-
-/**
- * scif_node_add_nack: Respond to SCIF_NODE_ADD_NACK interrupt message
- * @scifdev: Remote SCIF device node
- * @msg: Interrupt message
- *
- * SCIF_NODE_ADD failed, so inform the waiting wq.
- */
-static __always_inline void
-scif_node_add_nack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- if (scif_is_mgmt_node()) {
- struct scif_dev *dst_dev = &scif_dev[msg->dst.node];
-
- dev_dbg(&scifdev->sdev->dev,
- "SCIF_NODE_ADD_NACK received from %d\n", scifdev->node);
- scif_nodeqp_send(dst_dev, msg);
- }
-}
-
-/**
- * scif_node_remove: Handle SCIF_NODE_REMOVE message
- * @scifdev: Remote SCIF device node
- * @msg: Interrupt message
- *
- * Handle node removal.
- */
-static __always_inline void
-scif_node_remove(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- int node = msg->payload[0];
- struct scif_dev *scdev = &scif_dev[node];
-
- scdev->node_remove_ack_pending = true;
- scif_handle_remove_node(node);
-}
-
-/**
- * scif_node_remove_ack: Handle SCIF_NODE_REMOVE_ACK message
- * @scifdev: Remote SCIF device node
- * @msg: Interrupt message
- *
- * The peer has acked a SCIF_NODE_REMOVE message.
- */
-static __always_inline void
-scif_node_remove_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_dev *sdev = &scif_dev[msg->payload[0]];
-
- atomic_inc(&sdev->disconn_rescnt);
- wake_up(&sdev->disconn_wq);
-}
-
-/**
- * scif_get_node_info: Respond to SCIF_GET_NODE_INFO interrupt message
- * @scifdev: Remote SCIF device node
- * @msg: Interrupt message
- *
- * Retrieve node info i.e maxid and total from the mgmt node.
- */
-static __always_inline void
-scif_get_node_info_resp(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- if (scif_is_mgmt_node()) {
- swap(msg->dst.node, msg->src.node);
- mutex_lock(&scif_info.conflock);
- msg->payload[1] = scif_info.maxid;
- msg->payload[2] = scif_info.total;
- mutex_unlock(&scif_info.conflock);
- scif_nodeqp_send(scifdev, msg);
- } else {
- struct completion *node_info =
- (struct completion *)msg->payload[3];
-
- mutex_lock(&scif_info.conflock);
- scif_info.maxid = msg->payload[1];
- scif_info.total = msg->payload[2];
- complete_all(node_info);
- mutex_unlock(&scif_info.conflock);
- }
-}
-
-static void
-scif_msg_unknown(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- /* Bogus Node Qp Message? */
- dev_err(&scifdev->sdev->dev,
- "Unknown message 0x%xn scifdev->node 0x%x\n",
- msg->uop, scifdev->node);
-}
-
-static void (*scif_intr_func[SCIF_MAX_MSG + 1])
- (struct scif_dev *, struct scifmsg *msg) = {
- scif_msg_unknown, /* Error */
- scif_init, /* SCIF_INIT */
- scif_exit, /* SCIF_EXIT */
- scif_exit_ack, /* SCIF_EXIT_ACK */
- scif_node_add, /* SCIF_NODE_ADD */
- scif_node_add_ack, /* SCIF_NODE_ADD_ACK */
- scif_node_add_nack, /* SCIF_NODE_ADD_NACK */
- scif_node_remove, /* SCIF_NODE_REMOVE */
- scif_node_remove_ack, /* SCIF_NODE_REMOVE_ACK */
- scif_cnctreq, /* SCIF_CNCT_REQ */
- scif_cnctgnt, /* SCIF_CNCT_GNT */
- scif_cnctgnt_ack, /* SCIF_CNCT_GNTACK */
- scif_cnctgnt_nack, /* SCIF_CNCT_GNTNACK */
- scif_cnctrej, /* SCIF_CNCT_REJ */
- scif_discnct, /* SCIF_DISCNCT */
- scif_discnt_ack, /* SCIF_DISCNT_ACK */
- scif_clientsend, /* SCIF_CLIENT_SENT */
- scif_clientrcvd, /* SCIF_CLIENT_RCVD */
- scif_get_node_info_resp,/* SCIF_GET_NODE_INFO */
- scif_recv_reg, /* SCIF_REGISTER */
- scif_recv_reg_ack, /* SCIF_REGISTER_ACK */
- scif_recv_reg_nack, /* SCIF_REGISTER_NACK */
- scif_recv_unreg, /* SCIF_UNREGISTER */
- scif_recv_unreg_ack, /* SCIF_UNREGISTER_ACK */
- scif_recv_unreg_nack, /* SCIF_UNREGISTER_NACK */
- scif_alloc_req, /* SCIF_ALLOC_REQ */
- scif_alloc_gnt_rej, /* SCIF_ALLOC_GNT */
- scif_alloc_gnt_rej, /* SCIF_ALLOC_REJ */
- scif_free_virt, /* SCIF_FREE_VIRT */
- scif_recv_munmap, /* SCIF_MUNMAP */
- scif_recv_mark, /* SCIF_MARK */
- scif_recv_mark_resp, /* SCIF_MARK_ACK */
- scif_recv_mark_resp, /* SCIF_MARK_NACK */
- scif_recv_wait, /* SCIF_WAIT */
- scif_recv_wait_resp, /* SCIF_WAIT_ACK */
- scif_recv_wait_resp, /* SCIF_WAIT_NACK */
- scif_recv_sig_local, /* SCIF_SIG_LOCAL */
- scif_recv_sig_remote, /* SCIF_SIG_REMOTE */
- scif_recv_sig_resp, /* SCIF_SIG_ACK */
- scif_recv_sig_resp, /* SCIF_SIG_NACK */
-};
-
-static int scif_max_msg_id = SCIF_MAX_MSG;
-/**
- * scif_nodeqp_msg_handler() - Common handler for node messages
- * @scifdev: Remote device to respond to
- * @qp: Remote memory pointer
- * @msg: The message to be handled.
- *
- * This routine calls the appropriate routine to handle a Node Qp
- * message receipt
- */
-static void
-scif_nodeqp_msg_handler(struct scif_dev *scifdev,
- struct scif_qp *qp, struct scifmsg *msg)
-{
- scif_display_message(scifdev, msg, "Rcvd");
-
- if (msg->uop > (u32)scif_max_msg_id) {
- /* Bogus Node Qp Message? */
- dev_err(&scifdev->sdev->dev,
- "Unknown message 0x%xn scifdev->node 0x%x\n",
- msg->uop, scifdev->node);
- return;
- }
-
- scif_intr_func[msg->uop](scifdev, msg);
-}
-
-/**
- * scif_nodeqp_intrhandler() - Interrupt handler for node messages
- * @scifdev: Remote device to respond to
- * @qp: Remote memory pointer
- *
- * This routine is triggered by the interrupt mechanism. It reads
- * messages from the node queue RB and calls the Node QP Message handling
- * routine.
- */
-void scif_nodeqp_intrhandler(struct scif_dev *scifdev, struct scif_qp *qp)
-{
- struct scifmsg msg;
- int read_size;
-
- do {
- read_size = scif_rb_get_next(&qp->inbound_q, &msg, sizeof(msg));
- if (!read_size)
- break;
- scif_nodeqp_msg_handler(scifdev, qp, &msg);
- /*
- * The node queue pair is unmapped so skip the read pointer
- * update after receipt of a SCIF_EXIT_ACK
- */
- if (SCIF_EXIT_ACK == msg.uop)
- break;
- scif_rb_update_read_ptr(&qp->inbound_q);
- } while (1);
-}
-
-/**
- * scif_loopb_wq_handler - Loopback Workqueue Handler.
- * @unused: loop back work (unused)
- *
- * This work queue routine is invoked by the loopback work queue handler.
- * It grabs the recv lock, dequeues any available messages from the head
- * of the loopback message list, calls the node QP message handler,
- * waits for it to return, then frees up this message and dequeues more
- * elements of the list if available.
- */
-static void scif_loopb_wq_handler(struct work_struct *unused)
-{
- struct scif_dev *scifdev = scif_info.loopb_dev;
- struct scif_qp *qp = scifdev->qpairs;
- struct scif_loopb_msg *msg;
-
- do {
- msg = NULL;
- spin_lock(&qp->recv_lock);
- if (!list_empty(&scif_info.loopb_recv_q)) {
- msg = list_first_entry(&scif_info.loopb_recv_q,
- struct scif_loopb_msg,
- list);
- list_del(&msg->list);
- }
- spin_unlock(&qp->recv_lock);
-
- if (msg) {
- scif_nodeqp_msg_handler(scifdev, qp, &msg->msg);
- kfree(msg);
- }
- } while (msg);
-}
-
-/**
- * scif_loopb_msg_handler() - Workqueue handler for loopback messages.
- * @scifdev: SCIF device
- * @qp: Queue pair.
- *
- * This work queue routine is triggered when a loopback message is received.
- *
- * We need special handling for receiving Node Qp messages on a loopback SCIF
- * device via two workqueues for receiving messages.
- *
- * The reason we need the extra workqueue which is not required with *normal*
- * non-loopback SCIF devices is the potential classic deadlock described below:
- *
- * Thread A tries to send a message on a loopback SCIF device and blocks since
- * there is no space in the RB while it has the send_lock held or another
- * lock called lock X for example.
- *
- * Thread B: The Loopback Node QP message receive workqueue receives the message
- * and tries to send a message (eg an ACK) to the loopback SCIF device. It tries
- * to grab the send lock again or lock X and deadlocks with Thread A. The RB
- * cannot be drained any further due to this classic deadlock.
- *
- * In order to avoid deadlocks as mentioned above we have an extra level of
- * indirection achieved by having two workqueues.
- * 1) The first workqueue whose handler is scif_loopb_msg_handler reads
- * messages from the Node QP RB, adds them to a list and queues work for the
- * second workqueue.
- *
- * 2) The second workqueue whose handler is scif_loopb_wq_handler dequeues
- * messages from the list, handles them, frees up the memory and dequeues
- * more elements from the list if possible.
- */
-int
-scif_loopb_msg_handler(struct scif_dev *scifdev, struct scif_qp *qp)
-{
- int read_size;
- struct scif_loopb_msg *msg;
-
- do {
- msg = kmalloc(sizeof(*msg), GFP_KERNEL);
- if (!msg)
- return -ENOMEM;
- read_size = scif_rb_get_next(&qp->inbound_q, &msg->msg,
- sizeof(struct scifmsg));
- if (read_size != sizeof(struct scifmsg)) {
- kfree(msg);
- scif_rb_update_read_ptr(&qp->inbound_q);
- break;
- }
- spin_lock(&qp->recv_lock);
- list_add_tail(&msg->list, &scif_info.loopb_recv_q);
- spin_unlock(&qp->recv_lock);
- queue_work(scif_info.loopb_wq, &scif_info.loopb_work);
- scif_rb_update_read_ptr(&qp->inbound_q);
- } while (read_size == sizeof(struct scifmsg));
- return read_size;
-}
-
-/**
- * scif_setup_loopback_qp - One time setup work for Loopback Node Qp.
- * @scifdev: SCIF device
- *
- * Sets up the required loopback workqueues, queue pairs and ring buffers
- */
-int scif_setup_loopback_qp(struct scif_dev *scifdev)
-{
- int err = 0;
- void *local_q;
- struct scif_qp *qp;
-
- err = scif_setup_intr_wq(scifdev);
- if (err)
- goto exit;
- INIT_LIST_HEAD(&scif_info.loopb_recv_q);
- snprintf(scif_info.loopb_wqname, sizeof(scif_info.loopb_wqname),
- "SCIF LOOPB %d", scifdev->node);
- scif_info.loopb_wq =
- alloc_ordered_workqueue(scif_info.loopb_wqname, 0);
- if (!scif_info.loopb_wq) {
- err = -ENOMEM;
- goto destroy_intr;
- }
- INIT_WORK(&scif_info.loopb_work, scif_loopb_wq_handler);
- /* Allocate Self Qpair */
- scifdev->qpairs = kzalloc(sizeof(*scifdev->qpairs), GFP_KERNEL);
- if (!scifdev->qpairs) {
- err = -ENOMEM;
- goto destroy_loopb_wq;
- }
-
- qp = scifdev->qpairs;
- qp->magic = SCIFEP_MAGIC;
- spin_lock_init(&qp->send_lock);
- spin_lock_init(&qp->recv_lock);
-
- local_q = kzalloc(SCIF_NODE_QP_SIZE, GFP_KERNEL);
- if (!local_q) {
- err = -ENOMEM;
- goto free_qpairs;
- }
- /*
- * For loopback the inbound_q and outbound_q are essentially the same
- * since the Node sends a message on the loopback interface to the
- * outbound_q which is then received on the inbound_q.
- */
- scif_rb_init(&qp->outbound_q,
- &qp->local_read,
- &qp->local_write,
- local_q, get_count_order(SCIF_NODE_QP_SIZE));
-
- scif_rb_init(&qp->inbound_q,
- &qp->local_read,
- &qp->local_write,
- local_q, get_count_order(SCIF_NODE_QP_SIZE));
- scif_info.nodeid = scifdev->node;
-
- scif_peer_register_device(scifdev);
-
- scif_info.loopb_dev = scifdev;
- return err;
-free_qpairs:
- kfree(scifdev->qpairs);
-destroy_loopb_wq:
- destroy_workqueue(scif_info.loopb_wq);
-destroy_intr:
- scif_destroy_intr_wq(scifdev);
-exit:
- return err;
-}
-
-/**
- * scif_destroy_loopback_qp - One time uninit work for Loopback Node Qp
- * @scifdev: SCIF device
- *
- * Destroys the workqueues and frees up the Ring Buffer and Queue Pair memory.
- */
-int scif_destroy_loopback_qp(struct scif_dev *scifdev)
-{
- scif_peer_unregister_device(scifdev);
- destroy_workqueue(scif_info.loopb_wq);
- scif_destroy_intr_wq(scifdev);
- kfree(scifdev->qpairs->outbound_q.rb_base);
- kfree(scifdev->qpairs);
- scifdev->sdev = NULL;
- scif_info.loopb_dev = NULL;
- return 0;
-}
-
-void scif_destroy_p2p(struct scif_dev *scifdev)
-{
- struct scif_dev *peer_dev;
- struct scif_p2p_info *p2p;
- struct list_head *pos, *tmp;
- int bd;
-
- mutex_lock(&scif_info.conflock);
- /* Free P2P mappings in the given node for all its peer nodes */
- list_for_each_safe(pos, tmp, &scifdev->p2p) {
- p2p = list_entry(pos, struct scif_p2p_info, ppi_list);
- dma_unmap_sg(&scifdev->sdev->dev, p2p->ppi_sg[SCIF_PPI_MMIO],
- p2p->sg_nentries[SCIF_PPI_MMIO],
- DMA_BIDIRECTIONAL);
- dma_unmap_sg(&scifdev->sdev->dev, p2p->ppi_sg[SCIF_PPI_APER],
- p2p->sg_nentries[SCIF_PPI_APER],
- DMA_BIDIRECTIONAL);
- scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_MMIO]);
- scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_APER]);
- list_del(pos);
- kfree(p2p);
- }
-
- /* Free P2P mapping created in the peer nodes for the given node */
- for (bd = SCIF_MGMT_NODE + 1; bd <= scif_info.maxid; bd++) {
- peer_dev = &scif_dev[bd];
- list_for_each_safe(pos, tmp, &peer_dev->p2p) {
- p2p = list_entry(pos, struct scif_p2p_info, ppi_list);
- if (p2p->ppi_peer_id == scifdev->node) {
- dma_unmap_sg(&peer_dev->sdev->dev,
- p2p->ppi_sg[SCIF_PPI_MMIO],
- p2p->sg_nentries[SCIF_PPI_MMIO],
- DMA_BIDIRECTIONAL);
- dma_unmap_sg(&peer_dev->sdev->dev,
- p2p->ppi_sg[SCIF_PPI_APER],
- p2p->sg_nentries[SCIF_PPI_APER],
- DMA_BIDIRECTIONAL);
- scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_MMIO]);
- scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_APER]);
- list_del(pos);
- kfree(p2p);
- }
- }
- }
- mutex_unlock(&scif_info.conflock);
-}
diff --git a/drivers/misc/mic/scif/scif_nodeqp.h b/drivers/misc/mic/scif/scif_nodeqp.h
deleted file mode 100644
index 9589627..0000000
--- a/drivers/misc/mic/scif/scif_nodeqp.h
+++ /dev/null
@@ -1,221 +0,0 @@
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * Intel SCIF driver.
- *
- */
-#ifndef SCIF_NODEQP
-#define SCIF_NODEQP
-
-#include "scif_rb.h"
-#include "scif_peer_bus.h"
-
-#define SCIF_INIT 1 /* First message sent to the peer node for discovery */
-#define SCIF_EXIT 2 /* Last message from the peer informing intent to exit */
-#define SCIF_EXIT_ACK 3 /* Response to SCIF_EXIT message */
-#define SCIF_NODE_ADD 4 /* Tell Online nodes a new node exits */
-#define SCIF_NODE_ADD_ACK 5 /* Confirm to mgmt node sequence is finished */
-#define SCIF_NODE_ADD_NACK 6 /* SCIF_NODE_ADD failed */
-#define SCIF_NODE_REMOVE 7 /* Request to deactivate a SCIF node */
-#define SCIF_NODE_REMOVE_ACK 8 /* Response to a SCIF_NODE_REMOVE message */
-#define SCIF_CNCT_REQ 9 /* Phys addr of Request connection to a port */
-#define SCIF_CNCT_GNT 10 /* Phys addr of new Grant connection request */
-#define SCIF_CNCT_GNTACK 11 /* Error type Reject a connection request */
-#define SCIF_CNCT_GNTNACK 12 /* Error type Reject a connection request */
-#define SCIF_CNCT_REJ 13 /* Error type Reject a connection request */
-#define SCIF_DISCNCT 14 /* Notify peer that connection is being terminated */
-#define SCIF_DISCNT_ACK 15 /* Notify peer that connection is being terminated */
-#define SCIF_CLIENT_SENT 16 /* Notify the peer that data has been written */
-#define SCIF_CLIENT_RCVD 17 /* Notify the peer that data has been read */
-#define SCIF_GET_NODE_INFO 18 /* Get current node mask from the mgmt node*/
-#define SCIF_REGISTER 19 /* Tell peer about a new registered window */
-#define SCIF_REGISTER_ACK 20 /* Notify peer about unregistration success */
-#define SCIF_REGISTER_NACK 21 /* Notify peer about registration success */
-#define SCIF_UNREGISTER 22 /* Tell peer about unregistering a window */
-#define SCIF_UNREGISTER_ACK 23 /* Notify peer about registration failure */
-#define SCIF_UNREGISTER_NACK 24 /* Notify peer about unregistration failure */
-#define SCIF_ALLOC_REQ 25 /* Request a mapped buffer */
-#define SCIF_ALLOC_GNT 26 /* Notify peer about allocation success */
-#define SCIF_ALLOC_REJ 27 /* Notify peer about allocation failure */
-#define SCIF_FREE_VIRT 28 /* Free previously allocated virtual memory */
-#define SCIF_MUNMAP 29 /* Acknowledgment for a SCIF_MMAP request */
-#define SCIF_MARK 30 /* SCIF Remote Fence Mark Request */
-#define SCIF_MARK_ACK 31 /* SCIF Remote Fence Mark Success */
-#define SCIF_MARK_NACK 32 /* SCIF Remote Fence Mark Failure */
-#define SCIF_WAIT 33 /* SCIF Remote Fence Wait Request */
-#define SCIF_WAIT_ACK 34 /* SCIF Remote Fence Wait Success */
-#define SCIF_WAIT_NACK 35 /* SCIF Remote Fence Wait Failure */
-#define SCIF_SIG_LOCAL 36 /* SCIF Remote Fence Local Signal Request */
-#define SCIF_SIG_REMOTE 37 /* SCIF Remote Fence Remote Signal Request */
-#define SCIF_SIG_ACK 38 /* SCIF Remote Fence Remote Signal Success */
-#define SCIF_SIG_NACK 39 /* SCIF Remote Fence Remote Signal Failure */
-#define SCIF_MAX_MSG SCIF_SIG_NACK
-
-/*
- * struct scifmsg - Node QP message format
- *
- * @src: Source information
- * @dst: Destination information
- * @uop: The message opcode
- * @payload: Unique payload format for each message
- */
-struct scifmsg {
- struct scif_port_id src;
- struct scif_port_id dst;
- u32 uop;
- u64 payload[4];
-} __packed;
-
-/*
- * struct scif_allocmsg - Used with SCIF_ALLOC_REQ to request
- * the remote note to allocate memory
- *
- * phys_addr: Physical address of the buffer
- * vaddr: Virtual address of the buffer
- * size: Size of the buffer
- * state: Current state
- * allocwq: wait queue for status
- */
-struct scif_allocmsg {
- dma_addr_t phys_addr;
- unsigned long vaddr;
- size_t size;
- enum scif_msg_state state;
- wait_queue_head_t allocwq;
-};
-
-/*
- * struct scif_qp - Node Queue Pair
- *
- * Interesting structure -- a little difficult because we can only
- * write across the PCIe, so any r/w pointer we need to read is
- * local. We only need to read the read pointer on the inbound_q
- * and read the write pointer in the outbound_q
- *
- * @magic: Magic value to ensure the peer sees the QP correctly
- * @outbound_q: The outbound ring buffer for sending messages
- * @inbound_q: The inbound ring buffer for receiving messages
- * @local_write: Local write index
- * @local_read: Local read index
- * @remote_qp: The remote queue pair
- * @local_buf: DMA address of local ring buffer
- * @local_qp: DMA address of the local queue pair data structure
- * @remote_buf: DMA address of remote ring buffer
- * @qp_state: QP state i.e. online or offline used for P2P
- * @send_lock: synchronize access to outbound queue
- * @recv_lock: Synchronize access to inbound queue
- */
-struct scif_qp {
- u64 magic;
-#define SCIFEP_MAGIC 0x5c1f000000005c1fULL
- struct scif_rb outbound_q;
- struct scif_rb inbound_q;
-
- u32 local_write __aligned(64);
- u32 local_read __aligned(64);
- struct scif_qp *remote_qp;
- dma_addr_t local_buf;
- dma_addr_t local_qp;
- dma_addr_t remote_buf;
- u32 qp_state;
-#define SCIF_QP_OFFLINE 0xdead
-#define SCIF_QP_ONLINE 0xc0de
- spinlock_t send_lock;
- spinlock_t recv_lock;
-};
-
-/*
- * struct scif_loopb_msg - An element in the loopback Node QP message list.
- *
- * @msg - The SCIF node QP message
- * @list - link in the list of messages
- */
-struct scif_loopb_msg {
- struct scifmsg msg;
- struct list_head list;
-};
-
-int scif_nodeqp_send(struct scif_dev *scifdev, struct scifmsg *msg);
-int _scif_nodeqp_send(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_nodeqp_intrhandler(struct scif_dev *scifdev, struct scif_qp *qp);
-int scif_loopb_msg_handler(struct scif_dev *scifdev, struct scif_qp *qp);
-int scif_setup_qp(struct scif_dev *scifdev);
-int scif_qp_response(phys_addr_t phys, struct scif_dev *dev);
-int scif_setup_qp_connect(struct scif_qp *qp, dma_addr_t *qp_offset,
- int local_size, struct scif_dev *scifdev);
-int scif_setup_qp_accept(struct scif_qp *qp, dma_addr_t *qp_offset,
- dma_addr_t phys, int local_size,
- struct scif_dev *scifdev);
-int scif_setup_qp_connect_response(struct scif_dev *scifdev,
- struct scif_qp *qp, u64 payload);
-int scif_setup_loopback_qp(struct scif_dev *scifdev);
-int scif_destroy_loopback_qp(struct scif_dev *scifdev);
-void scif_poll_qp_state(struct work_struct *work);
-void scif_destroy_p2p(struct scif_dev *scifdev);
-void scif_send_exit(struct scif_dev *scifdev);
-static inline struct device *scif_get_peer_dev(struct scif_dev *scifdev)
-{
- struct scif_peer_dev *spdev;
- struct device *spdev_ret;
-
- rcu_read_lock();
- spdev = rcu_dereference(scifdev->spdev);
- if (spdev)
- spdev_ret = get_device(&spdev->dev);
- else
- spdev_ret = ERR_PTR(-ENODEV);
- rcu_read_unlock();
- return spdev_ret;
-}
-
-static inline void scif_put_peer_dev(struct device *dev)
-{
- put_device(dev);
-}
-#endif /* SCIF_NODEQP */
diff --git a/drivers/misc/mic/scif/scif_peer_bus.c b/drivers/misc/mic/scif/scif_peer_bus.c
deleted file mode 100644
index 6d60830..0000000
--- a/drivers/misc/mic/scif/scif_peer_bus.c
+++ /dev/null
@@ -1,175 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-#include "../bus/scif_bus.h"
-#include "scif_peer_bus.h"
-
-static inline struct scif_peer_dev *
-dev_to_scif_peer(struct device *dev)
-{
- return container_of(dev, struct scif_peer_dev, dev);
-}
-
-struct bus_type scif_peer_bus = {
- .name = "scif_peer_bus",
-};
-
-static void scif_peer_release_dev(struct device *d)
-{
- struct scif_peer_dev *sdev = dev_to_scif_peer(d);
- struct scif_dev *scifdev = &scif_dev[sdev->dnode];
-
- scif_cleanup_scifdev(scifdev);
- kfree(sdev);
-}
-
-static int scif_peer_initialize_device(struct scif_dev *scifdev)
-{
- struct scif_peer_dev *spdev;
- int ret;
-
- spdev = kzalloc(sizeof(*spdev), GFP_KERNEL);
- if (!spdev) {
- ret = -ENOMEM;
- goto err;
- }
-
- spdev->dev.parent = scifdev->sdev->dev.parent;
- spdev->dev.release = scif_peer_release_dev;
- spdev->dnode = scifdev->node;
- spdev->dev.bus = &scif_peer_bus;
- dev_set_name(&spdev->dev, "scif_peer-dev%u", spdev->dnode);
-
- device_initialize(&spdev->dev);
- get_device(&spdev->dev);
- rcu_assign_pointer(scifdev->spdev, spdev);
-
- mutex_lock(&scif_info.conflock);
- scif_info.total++;
- scif_info.maxid = max_t(u32, spdev->dnode, scif_info.maxid);
- mutex_unlock(&scif_info.conflock);
- return 0;
-err:
- dev_err(&scifdev->sdev->dev,
- "dnode %d: initialize_device rc %d\n", scifdev->node, ret);
- return ret;
-}
-
-static int scif_peer_add_device(struct scif_dev *scifdev)
-{
- struct scif_peer_dev *spdev = rcu_dereference(scifdev->spdev);
- char pool_name[16];
- int ret;
-
- ret = device_add(&spdev->dev);
- put_device(&spdev->dev);
- if (ret) {
- dev_err(&scifdev->sdev->dev,
- "dnode %d: peer device_add failed\n", scifdev->node);
- goto put_spdev;
- }
-
- scnprintf(pool_name, sizeof(pool_name), "scif-%d", spdev->dnode);
- scifdev->signal_pool = dmam_pool_create(pool_name, &scifdev->sdev->dev,
- sizeof(struct scif_status), 1,
- 0);
- if (!scifdev->signal_pool) {
- dev_err(&scifdev->sdev->dev,
- "dnode %d: dmam_pool_create failed\n", scifdev->node);
- ret = -ENOMEM;
- goto del_spdev;
- }
- dev_dbg(&spdev->dev, "Added peer dnode %d\n", spdev->dnode);
- return 0;
-del_spdev:
- device_del(&spdev->dev);
-put_spdev:
- RCU_INIT_POINTER(scifdev->spdev, NULL);
- synchronize_rcu();
- put_device(&spdev->dev);
-
- mutex_lock(&scif_info.conflock);
- scif_info.total--;
- mutex_unlock(&scif_info.conflock);
- return ret;
-}
-
-void scif_add_peer_device(struct work_struct *work)
-{
- struct scif_dev *scifdev = container_of(work, struct scif_dev,
- peer_add_work);
-
- scif_peer_add_device(scifdev);
-}
-
-/*
- * Peer device registration is split into a device_initialize and a device_add.
- * The reason for doing this is as follows: First, peer device registration
- * itself cannot be done in the message processing thread and must be delegated
- * to another workqueue, otherwise if SCIF client probe, called during peer
- * device registration, calls scif_connect(..), it will block the message
- * processing thread causing a deadlock. Next, device_initialize is done in the
- * "top-half" message processing thread and device_add in the "bottom-half"
- * workqueue. If this is not done, SCIF_CNCT_REQ message processing executing
- * concurrently with SCIF_INIT message processing is unable to get a reference
- * on the peer device, thereby failing the connect request.
- */
-void scif_peer_register_device(struct scif_dev *scifdev)
-{
- int ret;
-
- mutex_lock(&scifdev->lock);
- ret = scif_peer_initialize_device(scifdev);
- if (ret)
- goto exit;
- schedule_work(&scifdev->peer_add_work);
-exit:
- mutex_unlock(&scifdev->lock);
-}
-
-int scif_peer_unregister_device(struct scif_dev *scifdev)
-{
- struct scif_peer_dev *spdev;
-
- mutex_lock(&scifdev->lock);
- /* Flush work to ensure device register is complete */
- flush_work(&scifdev->peer_add_work);
-
- /*
- * Continue holding scifdev->lock since theoretically unregister_device
- * can be called simultaneously from multiple threads
- */
- spdev = rcu_dereference(scifdev->spdev);
- if (!spdev) {
- mutex_unlock(&scifdev->lock);
- return -ENODEV;
- }
-
- RCU_INIT_POINTER(scifdev->spdev, NULL);
- synchronize_rcu();
- mutex_unlock(&scifdev->lock);
-
- dev_dbg(&spdev->dev, "Removing peer dnode %d\n", spdev->dnode);
- device_unregister(&spdev->dev);
-
- mutex_lock(&scif_info.conflock);
- scif_info.total--;
- mutex_unlock(&scif_info.conflock);
- return 0;
-}
-
-int scif_peer_bus_init(void)
-{
- return bus_register(&scif_peer_bus);
-}
-
-void scif_peer_bus_exit(void)
-{
- bus_unregister(&scif_peer_bus);
-}
diff --git a/drivers/misc/mic/scif/scif_peer_bus.h b/drivers/misc/mic/scif/scif_peer_bus.h
deleted file mode 100644
index 2ea4c51..0000000
--- a/drivers/misc/mic/scif/scif_peer_bus.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#ifndef _SCIF_PEER_BUS_H_
-#define _SCIF_PEER_BUS_H_
-
-#include <linux/device.h>
-#include <linux/mic_common.h>
-#include <linux/scif.h>
-
-struct scif_dev;
-
-void scif_add_peer_device(struct work_struct *work);
-void scif_peer_register_device(struct scif_dev *sdev);
-int scif_peer_unregister_device(struct scif_dev *scifdev);
-int scif_peer_bus_init(void);
-void scif_peer_bus_exit(void);
-#endif /* _SCIF_PEER_BUS_H */
diff --git a/drivers/misc/mic/scif/scif_ports.c b/drivers/misc/mic/scif/scif_ports.c
deleted file mode 100644
index 4bdb5ef..0000000
--- a/drivers/misc/mic/scif/scif_ports.c
+++ /dev/null
@@ -1,116 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/idr.h>
-
-#include "scif_main.h"
-
-#define SCIF_PORT_COUNT 0x10000 /* Ports available */
-
-struct idr scif_ports;
-
-/**
- * struct scif_port - SCIF port information
- *
- * @ref_cnt: Reference count since there can be multiple endpoints
- * created via scif_accept(..) simultaneously using a port.
- */
-struct scif_port {
- int ref_cnt;
-};
-
-/**
- * __scif_get_port - Reserve a specified port # for SCIF and add it
- * to the global list.
- * @start: lowest port # to be reserved (inclusive).
- * @end: highest port # to be reserved (exclusive).
- *
- * @return : Allocated SCIF port #, or -ENOSPC if port unavailable.
- * On memory allocation failure, returns -ENOMEM.
- */
-static int __scif_get_port(int start, int end)
-{
- int id;
- struct scif_port *port = kzalloc(sizeof(*port), GFP_ATOMIC);
-
- if (!port)
- return -ENOMEM;
- spin_lock(&scif_info.port_lock);
- id = idr_alloc(&scif_ports, port, start, end, GFP_ATOMIC);
- if (id >= 0)
- port->ref_cnt++;
- spin_unlock(&scif_info.port_lock);
- return id;
-}
-
-/**
- * scif_rsrv_port - Reserve a specified port # for SCIF.
- * @port : port # to be reserved.
- *
- * @return : Allocated SCIF port #, or -ENOSPC if port unavailable.
- * On memory allocation failure, returns -ENOMEM.
- */
-int scif_rsrv_port(u16 port)
-{
- return __scif_get_port(port, port + 1);
-}
-
-/**
- * scif_get_new_port - Get and reserve any port # for SCIF in the range
- * SCIF_PORT_RSVD + 1 to SCIF_PORT_COUNT - 1.
- *
- * @return : Allocated SCIF port #, or -ENOSPC if no ports available.
- * On memory allocation failure, returns -ENOMEM.
- */
-int scif_get_new_port(void)
-{
- return __scif_get_port(SCIF_PORT_RSVD + 1, SCIF_PORT_COUNT);
-}
-
-/**
- * scif_get_port - Increment the reference count for a SCIF port
- * @id : SCIF port
- *
- * @return : None
- */
-void scif_get_port(u16 id)
-{
- struct scif_port *port;
-
- if (!id)
- return;
- spin_lock(&scif_info.port_lock);
- port = idr_find(&scif_ports, id);
- if (port)
- port->ref_cnt++;
- spin_unlock(&scif_info.port_lock);
-}
-
-/**
- * scif_put_port - Release a reserved SCIF port
- * @id : SCIF port to be released.
- *
- * @return : None
- */
-void scif_put_port(u16 id)
-{
- struct scif_port *port;
-
- if (!id)
- return;
- spin_lock(&scif_info.port_lock);
- port = idr_find(&scif_ports, id);
- if (port) {
- port->ref_cnt--;
- if (!port->ref_cnt) {
- idr_remove(&scif_ports, id);
- kfree(port);
- }
- }
- spin_unlock(&scif_info.port_lock);
-}
diff --git a/drivers/misc/mic/scif/scif_rb.c b/drivers/misc/mic/scif/scif_rb.c
deleted file mode 100644
index e425882..0000000
--- a/drivers/misc/mic/scif/scif_rb.c
+++ /dev/null
@@ -1,240 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/circ_buf.h>
-#include <linux/types.h>
-#include <linux/io.h>
-#include <linux/errno.h>
-
-#include "scif_rb.h"
-
-#define scif_rb_ring_cnt(head, tail, size) CIRC_CNT(head, tail, size)
-#define scif_rb_ring_space(head, tail, size) CIRC_SPACE(head, tail, size)
-
-/**
- * scif_rb_init - Initializes the ring buffer
- * @rb: ring buffer
- * @read_ptr: A pointer to the read offset
- * @write_ptr: A pointer to the write offset
- * @rb_base: A pointer to the base of the ring buffer
- * @size: The size of the ring buffer in powers of two
- */
-void scif_rb_init(struct scif_rb *rb, u32 *read_ptr, u32 *write_ptr,
- void *rb_base, u8 size)
-{
- rb->rb_base = rb_base;
- rb->size = (1 << size);
- rb->read_ptr = read_ptr;
- rb->write_ptr = write_ptr;
- rb->current_read_offset = *read_ptr;
- rb->current_write_offset = *write_ptr;
-}
-
-/* Copies a message to the ring buffer -- handles the wrap around case */
-static void memcpy_torb(struct scif_rb *rb, void *header,
- void *msg, u32 size)
-{
- u32 size1, size2;
-
- if (header + size >= rb->rb_base + rb->size) {
- /* Need to call two copies if it wraps around */
- size1 = (u32)(rb->rb_base + rb->size - header);
- size2 = size - size1;
- memcpy_toio((void __iomem __force *)header, msg, size1);
- memcpy_toio((void __iomem __force *)rb->rb_base,
- msg + size1, size2);
- } else {
- memcpy_toio((void __iomem __force *)header, msg, size);
- }
-}
-
-/* Copies a message from the ring buffer -- handles the wrap around case */
-static void memcpy_fromrb(struct scif_rb *rb, void *header,
- void *msg, u32 size)
-{
- u32 size1, size2;
-
- if (header + size >= rb->rb_base + rb->size) {
- /* Need to call two copies if it wraps around */
- size1 = (u32)(rb->rb_base + rb->size - header);
- size2 = size - size1;
- memcpy_fromio(msg, (void __iomem __force *)header, size1);
- memcpy_fromio(msg + size1,
- (void __iomem __force *)rb->rb_base, size2);
- } else {
- memcpy_fromio(msg, (void __iomem __force *)header, size);
- }
-}
-
-/**
- * scif_rb_space - Query space available for writing to the RB
- * @rb: ring buffer
- *
- * Return: size available for writing to RB in bytes.
- */
-u32 scif_rb_space(struct scif_rb *rb)
-{
- rb->current_read_offset = *rb->read_ptr;
- /*
- * Update from the HW read pointer only once the peer has exposed the
- * new empty slot. This barrier is paired with the memory barrier
- * scif_rb_update_read_ptr()
- */
- mb();
- return scif_rb_ring_space(rb->current_write_offset,
- rb->current_read_offset, rb->size);
-}
-
-/**
- * scif_rb_write - Write a message to the RB
- * @rb: ring buffer
- * @msg: buffer to send the message. Must be at least size bytes long
- * @size: the size (in bytes) to be copied to the RB
- *
- * This API does not block if there isn't enough space in the RB.
- * Returns: 0 on success or -ENOMEM on failure
- */
-int scif_rb_write(struct scif_rb *rb, void *msg, u32 size)
-{
- void *header;
-
- if (scif_rb_space(rb) < size)
- return -ENOMEM;
- header = rb->rb_base + rb->current_write_offset;
- memcpy_torb(rb, header, msg, size);
- /*
- * Wait until scif_rb_commit(). Update the local ring
- * buffer data, not the shared data until commit.
- */
- rb->current_write_offset =
- (rb->current_write_offset + size) & (rb->size - 1);
- return 0;
-}
-
-/**
- * scif_rb_commit - To submit the message to let the peer fetch it
- * @rb: ring buffer
- */
-void scif_rb_commit(struct scif_rb *rb)
-{
- /*
- * We must ensure ordering between the all the data committed
- * previously before we expose the new message to the peer by
- * updating the write_ptr. This write barrier is paired with
- * the read barrier in scif_rb_count(..)
- */
- wmb();
- WRITE_ONCE(*rb->write_ptr, rb->current_write_offset);
-#ifdef CONFIG_INTEL_MIC_CARD
- /*
- * X100 Si bug: For the case where a Core is performing an EXT_WR
- * followed by a Doorbell Write, the Core must perform two EXT_WR to the
- * same address with the same data before it does the Doorbell Write.
- * This way, if ordering is violated for the Interrupt Message, it will
- * fall just behind the first Posted associated with the first EXT_WR.
- */
- WRITE_ONCE(*rb->write_ptr, rb->current_write_offset);
-#endif
-}
-
-/**
- * scif_rb_get - To get next message from the ring buffer
- * @rb: ring buffer
- * @size: Number of bytes to be read
- *
- * Return: NULL if no bytes to be read from the ring buffer, otherwise the
- * pointer to the next byte
- */
-static void *scif_rb_get(struct scif_rb *rb, u32 size)
-{
- void *header = NULL;
-
- if (scif_rb_count(rb, size) >= size)
- header = rb->rb_base + rb->current_read_offset;
- return header;
-}
-
-/*
- * scif_rb_get_next - Read from ring buffer.
- * @rb: ring buffer
- * @msg: buffer to hold the message. Must be at least size bytes long
- * @size: Number of bytes to be read
- *
- * Return: number of bytes read if available bytes are >= size, otherwise
- * returns zero.
- */
-u32 scif_rb_get_next(struct scif_rb *rb, void *msg, u32 size)
-{
- void *header = NULL;
- int read_size = 0;
-
- header = scif_rb_get(rb, size);
- if (header) {
- u32 next_cmd_offset =
- (rb->current_read_offset + size) & (rb->size - 1);
-
- read_size = size;
- rb->current_read_offset = next_cmd_offset;
- memcpy_fromrb(rb, header, msg, size);
- }
- return read_size;
-}
-
-/**
- * scif_rb_update_read_ptr
- * @rb: ring buffer
- */
-void scif_rb_update_read_ptr(struct scif_rb *rb)
-{
- u32 new_offset;
-
- new_offset = rb->current_read_offset;
- /*
- * We must ensure ordering between the all the data committed or read
- * previously before we expose the empty slot to the peer by updating
- * the read_ptr. This barrier is paired with the memory barrier in
- * scif_rb_space(..)
- */
- mb();
- WRITE_ONCE(*rb->read_ptr, new_offset);
-#ifdef CONFIG_INTEL_MIC_CARD
- /*
- * X100 Si Bug: For the case where a Core is performing an EXT_WR
- * followed by a Doorbell Write, the Core must perform two EXT_WR to the
- * same address with the same data before it does the Doorbell Write.
- * This way, if ordering is violated for the Interrupt Message, it will
- * fall just behind the first Posted associated with the first EXT_WR.
- */
- WRITE_ONCE(*rb->read_ptr, new_offset);
-#endif
-}
-
-/**
- * scif_rb_count
- * @rb: ring buffer
- * @size: Number of bytes expected to be read
- *
- * Return: number of bytes that can be read from the RB
- */
-u32 scif_rb_count(struct scif_rb *rb, u32 size)
-{
- if (scif_rb_ring_cnt(rb->current_write_offset,
- rb->current_read_offset,
- rb->size) < size) {
- rb->current_write_offset = *rb->write_ptr;
- /*
- * Update from the HW write pointer if empty only once the peer
- * has exposed the new message. This read barrier is paired
- * with the write barrier in scif_rb_commit(..)
- */
- smp_rmb();
- }
- return scif_rb_ring_cnt(rb->current_write_offset,
- rb->current_read_offset,
- rb->size);
-}
diff --git a/drivers/misc/mic/scif/scif_rb.h b/drivers/misc/mic/scif/scif_rb.h
deleted file mode 100644
index 166dffe..0000000
--- a/drivers/misc/mic/scif/scif_rb.h
+++ /dev/null
@@ -1,100 +0,0 @@
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * Intel SCIF driver.
- */
-#ifndef SCIF_RB_H
-#define SCIF_RB_H
-/*
- * This file describes a general purpose, byte based ring buffer. Writers to the
- * ring buffer need to synchronize using a lock. The same is true for readers,
- * although in practice, the ring buffer has a single reader. It is lockless
- * between producer and consumer so it can handle being used across the PCIe
- * bus. The ring buffer ensures that there are no reads across the PCIe bus for
- * performance reasons. Two of these are used to form a single bidirectional
- * queue-pair across PCIe.
- */
-/*
- * struct scif_rb - SCIF Ring Buffer
- *
- * @rb_base: The base of the memory used for storing RB messages
- * @read_ptr: Pointer to the read offset
- * @write_ptr: Pointer to the write offset
- * @size: Size of the memory in rb_base
- * @current_read_offset: Cached read offset for performance
- * @current_write_offset: Cached write offset for performance
- */
-struct scif_rb {
- void *rb_base;
- u32 *read_ptr;
- u32 *write_ptr;
- u32 size;
- u32 current_read_offset;
- u32 current_write_offset;
-};
-
-/* methods used by both */
-void scif_rb_init(struct scif_rb *rb, u32 *read_ptr, u32 *write_ptr,
- void *rb_base, u8 size);
-/* writer only methods */
-/* write a new command, then scif_rb_commit() */
-int scif_rb_write(struct scif_rb *rb, void *msg, u32 size);
-/* after write(), then scif_rb_commit() */
-void scif_rb_commit(struct scif_rb *rb);
-/* query space available for writing to a RB. */
-u32 scif_rb_space(struct scif_rb *rb);
-
-/* reader only methods */
-/* read a new message from the ring buffer of size bytes */
-u32 scif_rb_get_next(struct scif_rb *rb, void *msg, u32 size);
-/* update the read pointer so that the space can be reused */
-void scif_rb_update_read_ptr(struct scif_rb *rb);
-/* count the number of bytes that can be read */
-u32 scif_rb_count(struct scif_rb *rb, u32 size);
-#endif
diff --git a/drivers/misc/mic/scif/scif_rma.c b/drivers/misc/mic/scif/scif_rma.c
deleted file mode 100644
index 18fb9d8..0000000
--- a/drivers/misc/mic/scif/scif_rma.c
+++ /dev/null
@@ -1,1760 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/intel-iommu.h>
-#include <linux/pagemap.h>
-#include <linux/sched/mm.h>
-#include <linux/sched/signal.h>
-
-#include "scif_main.h"
-#include "scif_map.h"
-
-/* Used to skip ulimit checks for registrations with SCIF_MAP_KERNEL flag */
-#define SCIF_MAP_ULIMIT 0x40
-
-bool scif_ulimit_check = 1;
-
-/**
- * scif_rma_ep_init:
- * @ep: end point
- *
- * Initialize RMA per EP data structures.
- */
-void scif_rma_ep_init(struct scif_endpt *ep)
-{
- struct scif_endpt_rma_info *rma = &ep->rma_info;
-
- mutex_init(&rma->rma_lock);
- init_iova_domain(&rma->iovad, PAGE_SIZE, SCIF_IOVA_START_PFN);
- spin_lock_init(&rma->tc_lock);
- mutex_init(&rma->mmn_lock);
- INIT_LIST_HEAD(&rma->reg_list);
- INIT_LIST_HEAD(&rma->remote_reg_list);
- atomic_set(&rma->tw_refcount, 0);
- atomic_set(&rma->tcw_refcount, 0);
- atomic_set(&rma->tcw_total_pages, 0);
- atomic_set(&rma->fence_refcount, 0);
-
- rma->async_list_del = 0;
- rma->dma_chan = NULL;
- INIT_LIST_HEAD(&rma->mmn_list);
- INIT_LIST_HEAD(&rma->vma_list);
- init_waitqueue_head(&rma->markwq);
-}
-
-/**
- * scif_rma_ep_can_uninit:
- * @ep: end point
- *
- * Returns 1 if an endpoint can be uninitialized and 0 otherwise.
- */
-int scif_rma_ep_can_uninit(struct scif_endpt *ep)
-{
- int ret = 0;
-
- mutex_lock(&ep->rma_info.rma_lock);
- /* Destroy RMA Info only if both lists are empty */
- if (list_empty(&ep->rma_info.reg_list) &&
- list_empty(&ep->rma_info.remote_reg_list) &&
- list_empty(&ep->rma_info.mmn_list) &&
- !atomic_read(&ep->rma_info.tw_refcount) &&
- !atomic_read(&ep->rma_info.tcw_refcount) &&
- !atomic_read(&ep->rma_info.fence_refcount))
- ret = 1;
- mutex_unlock(&ep->rma_info.rma_lock);
- return ret;
-}
-
-/**
- * scif_create_pinned_pages:
- * @nr_pages: number of pages in window
- * @prot: read/write protection
- *
- * Allocate and prepare a set of pinned pages.
- */
-static struct scif_pinned_pages *
-scif_create_pinned_pages(int nr_pages, int prot)
-{
- struct scif_pinned_pages *pin;
-
- might_sleep();
- pin = scif_zalloc(sizeof(*pin));
- if (!pin)
- goto error;
-
- pin->pages = scif_zalloc(nr_pages * sizeof(*pin->pages));
- if (!pin->pages)
- goto error_free_pinned_pages;
-
- pin->prot = prot;
- pin->magic = SCIFEP_MAGIC;
- return pin;
-
-error_free_pinned_pages:
- scif_free(pin, sizeof(*pin));
-error:
- return NULL;
-}
-
-/**
- * scif_destroy_pinned_pages:
- * @pin: A set of pinned pages.
- *
- * Deallocate resources for pinned pages.
- */
-static int scif_destroy_pinned_pages(struct scif_pinned_pages *pin)
-{
- int j;
- int writeable = pin->prot & SCIF_PROT_WRITE;
- int kernel = SCIF_MAP_KERNEL & pin->map_flags;
-
- if (kernel) {
- for (j = 0; j < pin->nr_pages; j++) {
- if (pin->pages[j] && !kernel) {
- if (writeable)
- set_page_dirty_lock(pin->pages[j]);
- put_page(pin->pages[j]);
- }
- }
- } else
- unpin_user_pages_dirty_lock(pin->pages, pin->nr_pages,
- writeable);
- scif_free(pin->pages,
- pin->nr_pages * sizeof(*pin->pages));
- scif_free(pin, sizeof(*pin));
- return 0;
-}
-
-/*
- * scif_create_window:
- * @ep: end point
- * @nr_pages: number of pages
- * @offset: registration offset
- * @temp: true if a temporary window is being created
- *
- * Allocate and prepare a self registration window.
- */
-struct scif_window *scif_create_window(struct scif_endpt *ep, int nr_pages,
- s64 offset, bool temp)
-{
- struct scif_window *window;
-
- might_sleep();
- window = scif_zalloc(sizeof(*window));
- if (!window)
- goto error;
-
- window->dma_addr = scif_zalloc(nr_pages * sizeof(*window->dma_addr));
- if (!window->dma_addr)
- goto error_free_window;
-
- window->num_pages = scif_zalloc(nr_pages * sizeof(*window->num_pages));
- if (!window->num_pages)
- goto error_free_window;
-
- window->offset = offset;
- window->ep = (u64)ep;
- window->magic = SCIFEP_MAGIC;
- window->reg_state = OP_IDLE;
- init_waitqueue_head(&window->regwq);
- window->unreg_state = OP_IDLE;
- init_waitqueue_head(&window->unregwq);
- INIT_LIST_HEAD(&window->list);
- window->type = SCIF_WINDOW_SELF;
- window->temp = temp;
- return window;
-
-error_free_window:
- scif_free(window->dma_addr,
- nr_pages * sizeof(*window->dma_addr));
- scif_free(window, sizeof(*window));
-error:
- return NULL;
-}
-
-/**
- * scif_destroy_incomplete_window:
- * @ep: end point
- * @window: registration window
- *
- * Deallocate resources for self window.
- */
-static void scif_destroy_incomplete_window(struct scif_endpt *ep,
- struct scif_window *window)
-{
- int err;
- int nr_pages = window->nr_pages;
- struct scif_allocmsg *alloc = &window->alloc_handle;
- struct scifmsg msg;
-
-retry:
- /* Wait for a SCIF_ALLOC_GNT/REJ message */
- err = wait_event_timeout(alloc->allocwq,
- alloc->state != OP_IN_PROGRESS,
- SCIF_NODE_ALIVE_TIMEOUT);
- if (!err && scifdev_alive(ep))
- goto retry;
-
- mutex_lock(&ep->rma_info.rma_lock);
- if (alloc->state == OP_COMPLETED) {
- msg.uop = SCIF_FREE_VIRT;
- msg.src = ep->port;
- msg.payload[0] = ep->remote_ep;
- msg.payload[1] = window->alloc_handle.vaddr;
- msg.payload[2] = (u64)window;
- msg.payload[3] = SCIF_REGISTER;
- _scif_nodeqp_send(ep->remote_dev, &msg);
- }
- mutex_unlock(&ep->rma_info.rma_lock);
-
- scif_free_window_offset(ep, window, window->offset);
- scif_free(window->dma_addr, nr_pages * sizeof(*window->dma_addr));
- scif_free(window->num_pages, nr_pages * sizeof(*window->num_pages));
- scif_free(window, sizeof(*window));
-}
-
-/**
- * scif_unmap_window:
- * @remote_dev: SCIF remote device
- * @window: registration window
- *
- * Delete any DMA mappings created for a registered self window
- */
-void scif_unmap_window(struct scif_dev *remote_dev, struct scif_window *window)
-{
- int j;
-
- if (scif_is_iommu_enabled() && !scifdev_self(remote_dev)) {
- if (window->st) {
- dma_unmap_sg(&remote_dev->sdev->dev,
- window->st->sgl, window->st->nents,
- DMA_BIDIRECTIONAL);
- sg_free_table(window->st);
- kfree(window->st);
- window->st = NULL;
- }
- } else {
- for (j = 0; j < window->nr_contig_chunks; j++) {
- if (window->dma_addr[j]) {
- scif_unmap_single(window->dma_addr[j],
- remote_dev,
- window->num_pages[j] <<
- PAGE_SHIFT);
- window->dma_addr[j] = 0x0;
- }
- }
- }
-}
-
-static inline struct mm_struct *__scif_acquire_mm(void)
-{
- if (scif_ulimit_check)
- return get_task_mm(current);
- return NULL;
-}
-
-static inline void __scif_release_mm(struct mm_struct *mm)
-{
- if (mm)
- mmput(mm);
-}
-
-static inline int
-__scif_dec_pinned_vm_lock(struct mm_struct *mm,
- int nr_pages)
-{
- if (!mm || !nr_pages || !scif_ulimit_check)
- return 0;
-
- atomic64_sub(nr_pages, &mm->pinned_vm);
- return 0;
-}
-
-static inline int __scif_check_inc_pinned_vm(struct mm_struct *mm,
- int nr_pages)
-{
- unsigned long locked, lock_limit;
-
- if (!mm || !nr_pages || !scif_ulimit_check)
- return 0;
-
- lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
- locked = atomic64_add_return(nr_pages, &mm->pinned_vm);
-
- if ((locked > lock_limit) && !capable(CAP_IPC_LOCK)) {
- atomic64_sub(nr_pages, &mm->pinned_vm);
- dev_err(scif_info.mdev.this_device,
- "locked(%lu) > lock_limit(%lu)\n",
- locked, lock_limit);
- return -ENOMEM;
- }
- return 0;
-}
-
-/**
- * scif_destroy_window:
- * @ep: end point
- * @window: registration window
- *
- * Deallocate resources for self window.
- */
-int scif_destroy_window(struct scif_endpt *ep, struct scif_window *window)
-{
- int j;
- struct scif_pinned_pages *pinned_pages = window->pinned_pages;
- int nr_pages = window->nr_pages;
-
- might_sleep();
- if (!window->temp && window->mm) {
- __scif_dec_pinned_vm_lock(window->mm, window->nr_pages);
- __scif_release_mm(window->mm);
- window->mm = NULL;
- }
-
- scif_free_window_offset(ep, window, window->offset);
- scif_unmap_window(ep->remote_dev, window);
- /*
- * Decrement references for this set of pinned pages from
- * this window.
- */
- j = atomic_sub_return(1, &pinned_pages->ref_count);
- if (j < 0)
- dev_err(scif_info.mdev.this_device,
- "%s %d incorrect ref count %d\n",
- __func__, __LINE__, j);
- /*
- * If the ref count for pinned_pages is zero then someone
- * has already called scif_unpin_pages() for it and we should
- * destroy the page cache.
- */
- if (!j)
- scif_destroy_pinned_pages(window->pinned_pages);
- scif_free(window->dma_addr, nr_pages * sizeof(*window->dma_addr));
- scif_free(window->num_pages, nr_pages * sizeof(*window->num_pages));
- window->magic = 0;
- scif_free(window, sizeof(*window));
- return 0;
-}
-
-/**
- * scif_create_remote_lookup:
- * @remote_dev: SCIF remote device
- * @window: remote window
- *
- * Allocate and prepare lookup entries for the remote
- * end to copy over the physical addresses.
- * Returns 0 on success and appropriate errno on failure.
- */
-static int scif_create_remote_lookup(struct scif_dev *remote_dev,
- struct scif_window *window)
-{
- int i, j, err = 0;
- int nr_pages = window->nr_pages;
- bool vmalloc_dma_phys, vmalloc_num_pages;
-
- might_sleep();
- /* Map window */
- err = scif_map_single(&window->mapped_offset,
- window, remote_dev, sizeof(*window));
- if (err)
- goto error_window;
-
- /* Compute the number of lookup entries. 21 == 2MB Shift */
- window->nr_lookup = ALIGN(nr_pages * PAGE_SIZE,
- ((2) * 1024 * 1024)) >> 21;
-
- window->dma_addr_lookup.lookup =
- scif_alloc_coherent(&window->dma_addr_lookup.offset,
- remote_dev, window->nr_lookup *
- sizeof(*window->dma_addr_lookup.lookup),
- GFP_KERNEL | __GFP_ZERO);
- if (!window->dma_addr_lookup.lookup) {
- err = -ENOMEM;
- goto error_window;
- }
-
- window->num_pages_lookup.lookup =
- scif_alloc_coherent(&window->num_pages_lookup.offset,
- remote_dev, window->nr_lookup *
- sizeof(*window->num_pages_lookup.lookup),
- GFP_KERNEL | __GFP_ZERO);
- if (!window->num_pages_lookup.lookup) {
- err = -ENOMEM;
- goto error_window;
- }
-
- vmalloc_dma_phys = is_vmalloc_addr(&window->dma_addr[0]);
- vmalloc_num_pages = is_vmalloc_addr(&window->num_pages[0]);
-
- /* Now map each of the pages containing physical addresses */
- for (i = 0, j = 0; i < nr_pages; i += SCIF_NR_ADDR_IN_PAGE, j++) {
- err = scif_map_page(&window->dma_addr_lookup.lookup[j],
- vmalloc_dma_phys ?
- vmalloc_to_page(&window->dma_addr[i]) :
- virt_to_page(&window->dma_addr[i]),
- remote_dev);
- if (err)
- goto error_window;
- err = scif_map_page(&window->num_pages_lookup.lookup[j],
- vmalloc_num_pages ?
- vmalloc_to_page(&window->num_pages[i]) :
- virt_to_page(&window->num_pages[i]),
- remote_dev);
- if (err)
- goto error_window;
- }
- return 0;
-error_window:
- return err;
-}
-
-/**
- * scif_destroy_remote_lookup:
- * @remote_dev: SCIF remote device
- * @window: remote window
- *
- * Destroy lookup entries used for the remote
- * end to copy over the physical addresses.
- */
-static void scif_destroy_remote_lookup(struct scif_dev *remote_dev,
- struct scif_window *window)
-{
- int i, j;
-
- if (window->nr_lookup) {
- struct scif_rma_lookup *lup = &window->dma_addr_lookup;
- struct scif_rma_lookup *npup = &window->num_pages_lookup;
-
- for (i = 0, j = 0; i < window->nr_pages;
- i += SCIF_NR_ADDR_IN_PAGE, j++) {
- if (lup->lookup && lup->lookup[j])
- scif_unmap_single(lup->lookup[j],
- remote_dev,
- PAGE_SIZE);
- if (npup->lookup && npup->lookup[j])
- scif_unmap_single(npup->lookup[j],
- remote_dev,
- PAGE_SIZE);
- }
- if (lup->lookup)
- scif_free_coherent(lup->lookup, lup->offset,
- remote_dev, window->nr_lookup *
- sizeof(*lup->lookup));
- if (npup->lookup)
- scif_free_coherent(npup->lookup, npup->offset,
- remote_dev, window->nr_lookup *
- sizeof(*npup->lookup));
- if (window->mapped_offset)
- scif_unmap_single(window->mapped_offset,
- remote_dev, sizeof(*window));
- window->nr_lookup = 0;
- }
-}
-
-/**
- * scif_create_remote_window:
- * @scifdev: SCIF device
- * @nr_pages: number of pages in window
- *
- * Allocate and prepare a remote registration window.
- */
-static struct scif_window *
-scif_create_remote_window(struct scif_dev *scifdev, int nr_pages)
-{
- struct scif_window *window;
-
- might_sleep();
- window = scif_zalloc(sizeof(*window));
- if (!window)
- goto error_ret;
-
- window->magic = SCIFEP_MAGIC;
- window->nr_pages = nr_pages;
-
- window->dma_addr = scif_zalloc(nr_pages * sizeof(*window->dma_addr));
- if (!window->dma_addr)
- goto error_window;
-
- window->num_pages = scif_zalloc(nr_pages *
- sizeof(*window->num_pages));
- if (!window->num_pages)
- goto error_window;
-
- if (scif_create_remote_lookup(scifdev, window))
- goto error_window;
-
- window->type = SCIF_WINDOW_PEER;
- window->unreg_state = OP_IDLE;
- INIT_LIST_HEAD(&window->list);
- return window;
-error_window:
- scif_destroy_remote_window(window);
-error_ret:
- return NULL;
-}
-
-/**
- * scif_destroy_remote_window:
- * @window: remote registration window
- *
- * Deallocate resources for remote window.
- */
-void
-scif_destroy_remote_window(struct scif_window *window)
-{
- scif_free(window->dma_addr, window->nr_pages *
- sizeof(*window->dma_addr));
- scif_free(window->num_pages, window->nr_pages *
- sizeof(*window->num_pages));
- window->magic = 0;
- scif_free(window, sizeof(*window));
-}
-
-/**
- * scif_iommu_map: create DMA mappings if the IOMMU is enabled
- * @remote_dev: SCIF remote device
- * @window: remote registration window
- *
- * Map the physical pages using dma_map_sg(..) and then detect the number
- * of contiguous DMA mappings allocated
- */
-static int scif_iommu_map(struct scif_dev *remote_dev,
- struct scif_window *window)
-{
- struct scatterlist *sg;
- int i, err;
- scif_pinned_pages_t pin = window->pinned_pages;
-
- window->st = kzalloc(sizeof(*window->st), GFP_KERNEL);
- if (!window->st)
- return -ENOMEM;
-
- err = sg_alloc_table(window->st, window->nr_pages, GFP_KERNEL);
- if (err)
- return err;
-
- for_each_sg(window->st->sgl, sg, window->st->nents, i)
- sg_set_page(sg, pin->pages[i], PAGE_SIZE, 0x0);
-
- err = dma_map_sg(&remote_dev->sdev->dev, window->st->sgl,
- window->st->nents, DMA_BIDIRECTIONAL);
- if (!err)
- return -ENOMEM;
- /* Detect contiguous ranges of DMA mappings */
- sg = window->st->sgl;
- for (i = 0; sg; i++) {
- dma_addr_t last_da;
-
- window->dma_addr[i] = sg_dma_address(sg);
- window->num_pages[i] = sg_dma_len(sg) >> PAGE_SHIFT;
- last_da = sg_dma_address(sg) + sg_dma_len(sg);
- while ((sg = sg_next(sg)) && sg_dma_address(sg) == last_da) {
- window->num_pages[i] +=
- (sg_dma_len(sg) >> PAGE_SHIFT);
- last_da = window->dma_addr[i] +
- sg_dma_len(sg);
- }
- window->nr_contig_chunks++;
- }
- return 0;
-}
-
-/**
- * scif_map_window:
- * @remote_dev: SCIF remote device
- * @window: self registration window
- *
- * Map pages of a window into the aperture/PCI.
- * Also determine addresses required for DMA.
- */
-int
-scif_map_window(struct scif_dev *remote_dev, struct scif_window *window)
-{
- int i, j, k, err = 0, nr_contig_pages;
- scif_pinned_pages_t pin;
- phys_addr_t phys_prev, phys_curr;
-
- might_sleep();
-
- pin = window->pinned_pages;
-
- if (intel_iommu_enabled && !scifdev_self(remote_dev))
- return scif_iommu_map(remote_dev, window);
-
- for (i = 0, j = 0; i < window->nr_pages; i += nr_contig_pages, j++) {
- phys_prev = page_to_phys(pin->pages[i]);
- nr_contig_pages = 1;
-
- /* Detect physically contiguous chunks */
- for (k = i + 1; k < window->nr_pages; k++) {
- phys_curr = page_to_phys(pin->pages[k]);
- if (phys_curr != (phys_prev + PAGE_SIZE))
- break;
- phys_prev = phys_curr;
- nr_contig_pages++;
- }
- window->num_pages[j] = nr_contig_pages;
- window->nr_contig_chunks++;
- if (scif_is_mgmt_node()) {
- /*
- * Management node has to deal with SMPT on X100 and
- * hence the DMA mapping is required
- */
- err = scif_map_single(&window->dma_addr[j],
- phys_to_virt(page_to_phys(
- pin->pages[i])),
- remote_dev,
- nr_contig_pages << PAGE_SHIFT);
- if (err)
- return err;
- } else {
- window->dma_addr[j] = page_to_phys(pin->pages[i]);
- }
- }
- return err;
-}
-
-/**
- * scif_send_scif_unregister:
- * @ep: end point
- * @window: self registration window
- *
- * Send a SCIF_UNREGISTER message.
- */
-static int scif_send_scif_unregister(struct scif_endpt *ep,
- struct scif_window *window)
-{
- struct scifmsg msg;
-
- msg.uop = SCIF_UNREGISTER;
- msg.src = ep->port;
- msg.payload[0] = window->alloc_handle.vaddr;
- msg.payload[1] = (u64)window;
- return scif_nodeqp_send(ep->remote_dev, &msg);
-}
-
-/**
- * scif_unregister_window:
- * @window: self registration window
- *
- * Send an unregistration request and wait for a response.
- */
-int scif_unregister_window(struct scif_window *window)
-{
- int err = 0;
- struct scif_endpt *ep = (struct scif_endpt *)window->ep;
- bool send_msg = false;
-
- might_sleep();
- switch (window->unreg_state) {
- case OP_IDLE:
- {
- window->unreg_state = OP_IN_PROGRESS;
- send_msg = true;
- }
- fallthrough;
- case OP_IN_PROGRESS:
- {
- scif_get_window(window, 1);
- mutex_unlock(&ep->rma_info.rma_lock);
- if (send_msg) {
- err = scif_send_scif_unregister(ep, window);
- if (err) {
- window->unreg_state = OP_COMPLETED;
- goto done;
- }
- } else {
- /* Return ENXIO since unregistration is in progress */
- mutex_lock(&ep->rma_info.rma_lock);
- return -ENXIO;
- }
-retry:
- /* Wait for a SCIF_UNREGISTER_(N)ACK message */
- err = wait_event_timeout(window->unregwq,
- window->unreg_state != OP_IN_PROGRESS,
- SCIF_NODE_ALIVE_TIMEOUT);
- if (!err && scifdev_alive(ep))
- goto retry;
- if (!err) {
- err = -ENODEV;
- window->unreg_state = OP_COMPLETED;
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n", __func__, __LINE__, err);
- }
- if (err > 0)
- err = 0;
-done:
- mutex_lock(&ep->rma_info.rma_lock);
- scif_put_window(window, 1);
- break;
- }
- case OP_FAILED:
- {
- if (!scifdev_alive(ep)) {
- err = -ENODEV;
- window->unreg_state = OP_COMPLETED;
- }
- break;
- }
- case OP_COMPLETED:
- break;
- default:
- err = -ENODEV;
- }
-
- if (window->unreg_state == OP_COMPLETED && window->ref_count)
- scif_put_window(window, window->nr_pages);
-
- if (!window->ref_count) {
- atomic_inc(&ep->rma_info.tw_refcount);
- list_del_init(&window->list);
- scif_free_window_offset(ep, window, window->offset);
- mutex_unlock(&ep->rma_info.rma_lock);
- if ((!!(window->pinned_pages->map_flags & SCIF_MAP_KERNEL)) &&
- scifdev_alive(ep)) {
- scif_drain_dma_intr(ep->remote_dev->sdev,
- ep->rma_info.dma_chan);
- } else {
- if (!__scif_dec_pinned_vm_lock(window->mm,
- window->nr_pages)) {
- __scif_release_mm(window->mm);
- window->mm = NULL;
- }
- }
- scif_queue_for_cleanup(window, &scif_info.rma);
- mutex_lock(&ep->rma_info.rma_lock);
- }
- return err;
-}
-
-/**
- * scif_send_alloc_request:
- * @ep: end point
- * @window: self registration window
- *
- * Send a remote window allocation request
- */
-static int scif_send_alloc_request(struct scif_endpt *ep,
- struct scif_window *window)
-{
- struct scifmsg msg;
- struct scif_allocmsg *alloc = &window->alloc_handle;
-
- /* Set up the Alloc Handle */
- alloc->state = OP_IN_PROGRESS;
- init_waitqueue_head(&alloc->allocwq);
-
- /* Send out an allocation request */
- msg.uop = SCIF_ALLOC_REQ;
- msg.payload[1] = window->nr_pages;
- msg.payload[2] = (u64)&window->alloc_handle;
- return _scif_nodeqp_send(ep->remote_dev, &msg);
-}
-
-/**
- * scif_prep_remote_window:
- * @ep: end point
- * @window: self registration window
- *
- * Send a remote window allocation request, wait for an allocation response,
- * and prepares the remote window by copying over the page lists
- */
-static int scif_prep_remote_window(struct scif_endpt *ep,
- struct scif_window *window)
-{
- struct scifmsg msg;
- struct scif_window *remote_window;
- struct scif_allocmsg *alloc = &window->alloc_handle;
- dma_addr_t *dma_phys_lookup, *tmp, *num_pages_lookup, *tmp1;
- int i = 0, j = 0;
- int nr_contig_chunks, loop_nr_contig_chunks;
- int remaining_nr_contig_chunks, nr_lookup;
- int err, map_err;
-
- map_err = scif_map_window(ep->remote_dev, window);
- if (map_err)
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d map_err %d\n", __func__, __LINE__, map_err);
- remaining_nr_contig_chunks = window->nr_contig_chunks;
- nr_contig_chunks = window->nr_contig_chunks;
-retry:
- /* Wait for a SCIF_ALLOC_GNT/REJ message */
- err = wait_event_timeout(alloc->allocwq,
- alloc->state != OP_IN_PROGRESS,
- SCIF_NODE_ALIVE_TIMEOUT);
- mutex_lock(&ep->rma_info.rma_lock);
- /* Synchronize with the thread waking up allocwq */
- mutex_unlock(&ep->rma_info.rma_lock);
- if (!err && scifdev_alive(ep))
- goto retry;
-
- if (!err)
- err = -ENODEV;
-
- if (err > 0)
- err = 0;
- else
- return err;
-
- /* Bail out. The remote end rejected this request */
- if (alloc->state == OP_FAILED)
- return -ENOMEM;
-
- if (map_err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, map_err);
- msg.uop = SCIF_FREE_VIRT;
- msg.src = ep->port;
- msg.payload[0] = ep->remote_ep;
- msg.payload[1] = window->alloc_handle.vaddr;
- msg.payload[2] = (u64)window;
- msg.payload[3] = SCIF_REGISTER;
- spin_lock(&ep->lock);
- if (ep->state == SCIFEP_CONNECTED)
- err = _scif_nodeqp_send(ep->remote_dev, &msg);
- else
- err = -ENOTCONN;
- spin_unlock(&ep->lock);
- return err;
- }
-
- remote_window = scif_ioremap(alloc->phys_addr, sizeof(*window),
- ep->remote_dev);
-
- /* Compute the number of lookup entries. 21 == 2MB Shift */
- nr_lookup = ALIGN(nr_contig_chunks, SCIF_NR_ADDR_IN_PAGE)
- >> ilog2(SCIF_NR_ADDR_IN_PAGE);
-
- dma_phys_lookup =
- scif_ioremap(remote_window->dma_addr_lookup.offset,
- nr_lookup *
- sizeof(*remote_window->dma_addr_lookup.lookup),
- ep->remote_dev);
- num_pages_lookup =
- scif_ioremap(remote_window->num_pages_lookup.offset,
- nr_lookup *
- sizeof(*remote_window->num_pages_lookup.lookup),
- ep->remote_dev);
-
- while (remaining_nr_contig_chunks) {
- loop_nr_contig_chunks = min_t(int, remaining_nr_contig_chunks,
- (int)SCIF_NR_ADDR_IN_PAGE);
- /* #1/2 - Copy physical addresses over to the remote side */
-
- /* #2/2 - Copy DMA addresses (addresses that are fed into the
- * DMA engine) We transfer bus addresses which are then
- * converted into a MIC physical address on the remote
- * side if it is a MIC, if the remote node is a mgmt node we
- * transfer the MIC physical address
- */
- tmp = scif_ioremap(dma_phys_lookup[j],
- loop_nr_contig_chunks *
- sizeof(*window->dma_addr),
- ep->remote_dev);
- tmp1 = scif_ioremap(num_pages_lookup[j],
- loop_nr_contig_chunks *
- sizeof(*window->num_pages),
- ep->remote_dev);
- if (scif_is_mgmt_node()) {
- memcpy_toio((void __force __iomem *)tmp,
- &window->dma_addr[i], loop_nr_contig_chunks
- * sizeof(*window->dma_addr));
- memcpy_toio((void __force __iomem *)tmp1,
- &window->num_pages[i], loop_nr_contig_chunks
- * sizeof(*window->num_pages));
- } else {
- if (scifdev_is_p2p(ep->remote_dev)) {
- /*
- * add remote node's base address for this node
- * to convert it into a MIC address
- */
- int m;
- dma_addr_t dma_addr;
-
- for (m = 0; m < loop_nr_contig_chunks; m++) {
- dma_addr = window->dma_addr[i + m] +
- ep->remote_dev->base_addr;
- writeq(dma_addr,
- (void __force __iomem *)&tmp[m]);
- }
- memcpy_toio((void __force __iomem *)tmp1,
- &window->num_pages[i],
- loop_nr_contig_chunks
- * sizeof(*window->num_pages));
- } else {
- /* Mgmt node or loopback - transfer DMA
- * addresses as is, this is the same as a
- * MIC physical address (we use the dma_addr
- * and not the phys_addr array since the
- * phys_addr is only setup if there is a mmap()
- * request from the mgmt node)
- */
- memcpy_toio((void __force __iomem *)tmp,
- &window->dma_addr[i],
- loop_nr_contig_chunks *
- sizeof(*window->dma_addr));
- memcpy_toio((void __force __iomem *)tmp1,
- &window->num_pages[i],
- loop_nr_contig_chunks *
- sizeof(*window->num_pages));
- }
- }
- remaining_nr_contig_chunks -= loop_nr_contig_chunks;
- i += loop_nr_contig_chunks;
- j++;
- scif_iounmap(tmp, loop_nr_contig_chunks *
- sizeof(*window->dma_addr), ep->remote_dev);
- scif_iounmap(tmp1, loop_nr_contig_chunks *
- sizeof(*window->num_pages), ep->remote_dev);
- }
-
- /* Prepare the remote window for the peer */
- remote_window->peer_window = (u64)window;
- remote_window->offset = window->offset;
- remote_window->prot = window->prot;
- remote_window->nr_contig_chunks = nr_contig_chunks;
- remote_window->ep = ep->remote_ep;
- scif_iounmap(num_pages_lookup,
- nr_lookup *
- sizeof(*remote_window->num_pages_lookup.lookup),
- ep->remote_dev);
- scif_iounmap(dma_phys_lookup,
- nr_lookup *
- sizeof(*remote_window->dma_addr_lookup.lookup),
- ep->remote_dev);
- scif_iounmap(remote_window, sizeof(*remote_window), ep->remote_dev);
- window->peer_window = alloc->vaddr;
- return err;
-}
-
-/**
- * scif_send_scif_register:
- * @ep: end point
- * @window: self registration window
- *
- * Send a SCIF_REGISTER message if EP is connected and wait for a
- * SCIF_REGISTER_(N)ACK message else send a SCIF_FREE_VIRT
- * message so that the peer can free its remote window allocated earlier.
- */
-static int scif_send_scif_register(struct scif_endpt *ep,
- struct scif_window *window)
-{
- int err = 0;
- struct scifmsg msg;
-
- msg.src = ep->port;
- msg.payload[0] = ep->remote_ep;
- msg.payload[1] = window->alloc_handle.vaddr;
- msg.payload[2] = (u64)window;
- spin_lock(&ep->lock);
- if (ep->state == SCIFEP_CONNECTED) {
- msg.uop = SCIF_REGISTER;
- window->reg_state = OP_IN_PROGRESS;
- err = _scif_nodeqp_send(ep->remote_dev, &msg);
- spin_unlock(&ep->lock);
- if (!err) {
-retry:
- /* Wait for a SCIF_REGISTER_(N)ACK message */
- err = wait_event_timeout(window->regwq,
- window->reg_state !=
- OP_IN_PROGRESS,
- SCIF_NODE_ALIVE_TIMEOUT);
- if (!err && scifdev_alive(ep))
- goto retry;
- err = !err ? -ENODEV : 0;
- if (window->reg_state == OP_FAILED)
- err = -ENOTCONN;
- }
- } else {
- msg.uop = SCIF_FREE_VIRT;
- msg.payload[3] = SCIF_REGISTER;
- err = _scif_nodeqp_send(ep->remote_dev, &msg);
- spin_unlock(&ep->lock);
- if (!err)
- err = -ENOTCONN;
- }
- return err;
-}
-
-/**
- * scif_get_window_offset:
- * @ep: end point descriptor
- * @flags: flags
- * @offset: offset hint
- * @num_pages: number of pages
- * @out_offset: computed offset returned by reference.
- *
- * Compute/Claim a new offset for this EP.
- */
-int scif_get_window_offset(struct scif_endpt *ep, int flags, s64 offset,
- int num_pages, s64 *out_offset)
-{
- s64 page_index;
- struct iova *iova_ptr;
- int err = 0;
-
- if (flags & SCIF_MAP_FIXED) {
- page_index = SCIF_IOVA_PFN(offset);
- iova_ptr = reserve_iova(&ep->rma_info.iovad, page_index,
- page_index + num_pages - 1);
- if (!iova_ptr)
- err = -EADDRINUSE;
- } else {
- iova_ptr = alloc_iova(&ep->rma_info.iovad, num_pages,
- SCIF_DMA_63BIT_PFN - 1, 0);
- if (!iova_ptr)
- err = -ENOMEM;
- }
- if (!err)
- *out_offset = (iova_ptr->pfn_lo) << PAGE_SHIFT;
- return err;
-}
-
-/**
- * scif_free_window_offset:
- * @ep: end point descriptor
- * @window: registration window
- * @offset: Offset to be freed
- *
- * Free offset for this EP. The callee is supposed to grab
- * the RMA mutex before calling this API.
- */
-void scif_free_window_offset(struct scif_endpt *ep,
- struct scif_window *window, s64 offset)
-{
- if ((window && !window->offset_freed) || !window) {
- free_iova(&ep->rma_info.iovad, offset >> PAGE_SHIFT);
- if (window)
- window->offset_freed = true;
- }
-}
-
-/**
- * scif_alloc_req: Respond to SCIF_ALLOC_REQ interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Remote side is requesting a memory allocation.
- */
-void scif_alloc_req(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- int err;
- struct scif_window *window = NULL;
- int nr_pages = msg->payload[1];
-
- window = scif_create_remote_window(scifdev, nr_pages);
- if (!window) {
- err = -ENOMEM;
- goto error;
- }
-
- /* The peer's allocation request is granted */
- msg->uop = SCIF_ALLOC_GNT;
- msg->payload[0] = (u64)window;
- msg->payload[1] = window->mapped_offset;
- err = scif_nodeqp_send(scifdev, msg);
- if (err)
- scif_destroy_remote_window(window);
- return;
-error:
- /* The peer's allocation request is rejected */
- dev_err(&scifdev->sdev->dev,
- "%s %d error %d alloc_ptr %p nr_pages 0x%x\n",
- __func__, __LINE__, err, window, nr_pages);
- msg->uop = SCIF_ALLOC_REJ;
- scif_nodeqp_send(scifdev, msg);
-}
-
-/**
- * scif_alloc_gnt_rej: Respond to SCIF_ALLOC_GNT/REJ interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Remote side responded to a memory allocation.
- */
-void scif_alloc_gnt_rej(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_allocmsg *handle = (struct scif_allocmsg *)msg->payload[2];
- struct scif_window *window = container_of(handle, struct scif_window,
- alloc_handle);
- struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-
- mutex_lock(&ep->rma_info.rma_lock);
- handle->vaddr = msg->payload[0];
- handle->phys_addr = msg->payload[1];
- if (msg->uop == SCIF_ALLOC_GNT)
- handle->state = OP_COMPLETED;
- else
- handle->state = OP_FAILED;
- wake_up(&handle->allocwq);
- mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-/**
- * scif_free_virt: Respond to SCIF_FREE_VIRT interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Free up memory kmalloc'd earlier.
- */
-void scif_free_virt(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_window *window = (struct scif_window *)msg->payload[1];
-
- scif_destroy_remote_window(window);
-}
-
-static void
-scif_fixup_aper_base(struct scif_dev *dev, struct scif_window *window)
-{
- int j;
- struct scif_hw_dev *sdev = dev->sdev;
- phys_addr_t apt_base = 0;
-
- /*
- * Add the aperture base if the DMA address is not card relative
- * since the DMA addresses need to be an offset into the bar
- */
- if (!scifdev_self(dev) && window->type == SCIF_WINDOW_PEER &&
- sdev->aper && !sdev->card_rel_da)
- apt_base = sdev->aper->pa;
- else
- return;
-
- for (j = 0; j < window->nr_contig_chunks; j++) {
- if (window->num_pages[j])
- window->dma_addr[j] += apt_base;
- else
- break;
- }
-}
-
-/**
- * scif_recv_reg: Respond to SCIF_REGISTER interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Update remote window list with a new registered window.
- */
-void scif_recv_reg(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
- struct scif_window *window =
- (struct scif_window *)msg->payload[1];
-
- mutex_lock(&ep->rma_info.rma_lock);
- spin_lock(&ep->lock);
- if (ep->state == SCIFEP_CONNECTED) {
- msg->uop = SCIF_REGISTER_ACK;
- scif_nodeqp_send(ep->remote_dev, msg);
- scif_fixup_aper_base(ep->remote_dev, window);
- /* No further failures expected. Insert new window */
- scif_insert_window(window, &ep->rma_info.remote_reg_list);
- } else {
- msg->uop = SCIF_REGISTER_NACK;
- scif_nodeqp_send(ep->remote_dev, msg);
- }
- spin_unlock(&ep->lock);
- mutex_unlock(&ep->rma_info.rma_lock);
- /* free up any lookup resources now that page lists are transferred */
- scif_destroy_remote_lookup(ep->remote_dev, window);
- /*
- * We could not insert the window but we need to
- * destroy the window.
- */
- if (msg->uop == SCIF_REGISTER_NACK)
- scif_destroy_remote_window(window);
-}
-
-/**
- * scif_recv_unreg: Respond to SCIF_UNREGISTER interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Remove window from remote registration list;
- */
-void scif_recv_unreg(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_rma_req req;
- struct scif_window *window = NULL;
- struct scif_window *recv_window =
- (struct scif_window *)msg->payload[0];
- struct scif_endpt *ep;
- int del_window = 0;
-
- ep = (struct scif_endpt *)recv_window->ep;
- req.out_window = &window;
- req.offset = recv_window->offset;
- req.prot = 0;
- req.nr_bytes = recv_window->nr_pages << PAGE_SHIFT;
- req.type = SCIF_WINDOW_FULL;
- req.head = &ep->rma_info.remote_reg_list;
- msg->payload[0] = ep->remote_ep;
-
- mutex_lock(&ep->rma_info.rma_lock);
- /* Does a valid window exist? */
- if (scif_query_window(&req)) {
- dev_err(&scifdev->sdev->dev,
- "%s %d -ENXIO\n", __func__, __LINE__);
- msg->uop = SCIF_UNREGISTER_ACK;
- goto error;
- }
- if (window) {
- if (window->ref_count)
- scif_put_window(window, window->nr_pages);
- else
- dev_err(&scifdev->sdev->dev,
- "%s %d ref count should be +ve\n",
- __func__, __LINE__);
- window->unreg_state = OP_COMPLETED;
- if (!window->ref_count) {
- msg->uop = SCIF_UNREGISTER_ACK;
- atomic_inc(&ep->rma_info.tw_refcount);
- ep->rma_info.async_list_del = 1;
- list_del_init(&window->list);
- del_window = 1;
- } else {
- /* NACK! There are valid references to this window */
- msg->uop = SCIF_UNREGISTER_NACK;
- }
- } else {
- /* The window did not make its way to the list at all. ACK */
- msg->uop = SCIF_UNREGISTER_ACK;
- scif_destroy_remote_window(recv_window);
- }
-error:
- mutex_unlock(&ep->rma_info.rma_lock);
- if (del_window)
- scif_drain_dma_intr(ep->remote_dev->sdev,
- ep->rma_info.dma_chan);
- scif_nodeqp_send(ep->remote_dev, msg);
- if (del_window)
- scif_queue_for_cleanup(window, &scif_info.rma);
-}
-
-/**
- * scif_recv_reg_ack: Respond to SCIF_REGISTER_ACK interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Wake up the window waiting to complete registration.
- */
-void scif_recv_reg_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_window *window =
- (struct scif_window *)msg->payload[2];
- struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-
- mutex_lock(&ep->rma_info.rma_lock);
- window->reg_state = OP_COMPLETED;
- wake_up(&window->regwq);
- mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-/**
- * scif_recv_reg_nack: Respond to SCIF_REGISTER_NACK interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Wake up the window waiting to inform it that registration
- * cannot be completed.
- */
-void scif_recv_reg_nack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_window *window =
- (struct scif_window *)msg->payload[2];
- struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-
- mutex_lock(&ep->rma_info.rma_lock);
- window->reg_state = OP_FAILED;
- wake_up(&window->regwq);
- mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-/**
- * scif_recv_unreg_ack: Respond to SCIF_UNREGISTER_ACK interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Wake up the window waiting to complete unregistration.
- */
-void scif_recv_unreg_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_window *window =
- (struct scif_window *)msg->payload[1];
- struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-
- mutex_lock(&ep->rma_info.rma_lock);
- window->unreg_state = OP_COMPLETED;
- wake_up(&window->unregwq);
- mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-/**
- * scif_recv_unreg_nack: Respond to SCIF_UNREGISTER_NACK interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Wake up the window waiting to inform it that unregistration
- * cannot be completed immediately.
- */
-void scif_recv_unreg_nack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_window *window =
- (struct scif_window *)msg->payload[1];
- struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-
- mutex_lock(&ep->rma_info.rma_lock);
- window->unreg_state = OP_FAILED;
- wake_up(&window->unregwq);
- mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-int __scif_pin_pages(void *addr, size_t len, int *out_prot,
- int map_flags, scif_pinned_pages_t *pages)
-{
- struct scif_pinned_pages *pinned_pages;
- int nr_pages, err = 0, i;
- bool vmalloc_addr = false;
- bool try_upgrade = false;
- int prot = *out_prot;
- int ulimit = 0;
- struct mm_struct *mm = NULL;
-
- /* Unsupported flags */
- if (map_flags & ~(SCIF_MAP_KERNEL | SCIF_MAP_ULIMIT))
- return -EINVAL;
- ulimit = !!(map_flags & SCIF_MAP_ULIMIT);
-
- /* Unsupported protection requested */
- if (prot & ~(SCIF_PROT_READ | SCIF_PROT_WRITE))
- return -EINVAL;
-
- /* addr/len must be page aligned. len should be non zero */
- if (!len ||
- (ALIGN((u64)addr, PAGE_SIZE) != (u64)addr) ||
- (ALIGN((u64)len, PAGE_SIZE) != (u64)len))
- return -EINVAL;
-
- might_sleep();
-
- nr_pages = len >> PAGE_SHIFT;
-
- /* Allocate a set of pinned pages */
- pinned_pages = scif_create_pinned_pages(nr_pages, prot);
- if (!pinned_pages)
- return -ENOMEM;
-
- if (map_flags & SCIF_MAP_KERNEL) {
- if (is_vmalloc_addr(addr))
- vmalloc_addr = true;
-
- for (i = 0; i < nr_pages; i++) {
- if (vmalloc_addr)
- pinned_pages->pages[i] =
- vmalloc_to_page(addr + (i * PAGE_SIZE));
- else
- pinned_pages->pages[i] =
- virt_to_page(addr + (i * PAGE_SIZE));
- }
- pinned_pages->nr_pages = nr_pages;
- pinned_pages->map_flags = SCIF_MAP_KERNEL;
- } else {
- /*
- * SCIF supports registration caching. If a registration has
- * been requested with read only permissions, then we try
- * to pin the pages with RW permissions so that a subsequent
- * transfer with RW permission can hit the cache instead of
- * invalidating it. If the upgrade fails with RW then we
- * revert back to R permission and retry
- */
- if (prot == SCIF_PROT_READ)
- try_upgrade = true;
- prot |= SCIF_PROT_WRITE;
-retry:
- mm = current->mm;
- if (ulimit) {
- err = __scif_check_inc_pinned_vm(mm, nr_pages);
- if (err) {
- pinned_pages->nr_pages = 0;
- goto error_unmap;
- }
- }
-
- pinned_pages->nr_pages = pin_user_pages_fast(
- (u64)addr,
- nr_pages,
- (prot & SCIF_PROT_WRITE) ? FOLL_WRITE : 0,
- pinned_pages->pages);
- if (nr_pages != pinned_pages->nr_pages) {
- if (pinned_pages->nr_pages < 0)
- pinned_pages->nr_pages = 0;
- if (try_upgrade) {
- if (ulimit)
- __scif_dec_pinned_vm_lock(mm, nr_pages);
- /* Roll back any pinned pages */
- unpin_user_pages(pinned_pages->pages,
- pinned_pages->nr_pages);
- prot &= ~SCIF_PROT_WRITE;
- try_upgrade = false;
- goto retry;
- }
- }
- pinned_pages->map_flags = 0;
- }
-
- if (pinned_pages->nr_pages < nr_pages) {
- err = -EFAULT;
- goto dec_pinned;
- }
-
- *out_prot = prot;
- atomic_set(&pinned_pages->ref_count, 1);
- *pages = pinned_pages;
- return err;
-dec_pinned:
- if (ulimit)
- __scif_dec_pinned_vm_lock(mm, nr_pages);
- /* Something went wrong! Rollback */
-error_unmap:
- scif_destroy_pinned_pages(pinned_pages);
- *pages = NULL;
- dev_dbg(scif_info.mdev.this_device,
- "%s %d err %d len 0x%lx\n", __func__, __LINE__, err, len);
- return err;
-}
-
-int scif_pin_pages(void *addr, size_t len, int prot,
- int map_flags, scif_pinned_pages_t *pages)
-{
- return __scif_pin_pages(addr, len, &prot, map_flags, pages);
-}
-EXPORT_SYMBOL_GPL(scif_pin_pages);
-
-int scif_unpin_pages(scif_pinned_pages_t pinned_pages)
-{
- int err = 0, ret;
-
- if (!pinned_pages || SCIFEP_MAGIC != pinned_pages->magic)
- return -EINVAL;
-
- ret = atomic_sub_return(1, &pinned_pages->ref_count);
- if (ret < 0) {
- dev_err(scif_info.mdev.this_device,
- "%s %d scif_unpin_pages called without pinning? rc %d\n",
- __func__, __LINE__, ret);
- return -EINVAL;
- }
- /*
- * Destroy the window if the ref count for this set of pinned
- * pages has dropped to zero. If it is positive then there is
- * a valid registered window which is backed by these pages and
- * it will be destroyed once all such windows are unregistered.
- */
- if (!ret)
- err = scif_destroy_pinned_pages(pinned_pages);
-
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_unpin_pages);
-
-static inline void
-scif_insert_local_window(struct scif_window *window, struct scif_endpt *ep)
-{
- mutex_lock(&ep->rma_info.rma_lock);
- scif_insert_window(window, &ep->rma_info.reg_list);
- mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-off_t scif_register_pinned_pages(scif_epd_t epd,
- scif_pinned_pages_t pinned_pages,
- off_t offset, int map_flags)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- s64 computed_offset;
- struct scif_window *window;
- int err;
- size_t len;
- struct device *spdev;
-
- /* Unsupported flags */
- if (map_flags & ~SCIF_MAP_FIXED)
- return -EINVAL;
-
- len = pinned_pages->nr_pages << PAGE_SHIFT;
-
- /*
- * Offset is not page aligned/negative or offset+len
- * wraps around with SCIF_MAP_FIXED.
- */
- if ((map_flags & SCIF_MAP_FIXED) &&
- ((ALIGN(offset, PAGE_SIZE) != offset) ||
- (offset < 0) ||
- (len > LONG_MAX - offset)))
- return -EINVAL;
-
- might_sleep();
-
- err = scif_verify_epd(ep);
- if (err)
- return err;
- /*
- * It is an error to pass pinned_pages to scif_register_pinned_pages()
- * after calling scif_unpin_pages().
- */
- if (!atomic_add_unless(&pinned_pages->ref_count, 1, 0))
- return -EINVAL;
-
- /* Compute the offset for this registration */
- err = scif_get_window_offset(ep, map_flags, offset,
- len, &computed_offset);
- if (err) {
- atomic_sub(1, &pinned_pages->ref_count);
- return err;
- }
-
- /* Allocate and prepare self registration window */
- window = scif_create_window(ep, pinned_pages->nr_pages,
- computed_offset, false);
- if (!window) {
- atomic_sub(1, &pinned_pages->ref_count);
- scif_free_window_offset(ep, NULL, computed_offset);
- return -ENOMEM;
- }
-
- window->pinned_pages = pinned_pages;
- window->nr_pages = pinned_pages->nr_pages;
- window->prot = pinned_pages->prot;
-
- spdev = scif_get_peer_dev(ep->remote_dev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- scif_destroy_window(ep, window);
- return err;
- }
- err = scif_send_alloc_request(ep, window);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto error_unmap;
- }
-
- /* Prepare the remote registration window */
- err = scif_prep_remote_window(ep, window);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto error_unmap;
- }
-
- /* Tell the peer about the new window */
- err = scif_send_scif_register(ep, window);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto error_unmap;
- }
-
- scif_put_peer_dev(spdev);
- /* No further failures expected. Insert new window */
- scif_insert_local_window(window, ep);
- return computed_offset;
-error_unmap:
- scif_destroy_window(ep, window);
- scif_put_peer_dev(spdev);
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_register_pinned_pages);
-
-off_t scif_register(scif_epd_t epd, void *addr, size_t len, off_t offset,
- int prot, int map_flags)
-{
- scif_pinned_pages_t pinned_pages;
- off_t err;
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- s64 computed_offset;
- struct scif_window *window;
- struct mm_struct *mm = NULL;
- struct device *spdev;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI register: ep %p addr %p len 0x%lx offset 0x%lx prot 0x%x map_flags 0x%x\n",
- epd, addr, len, offset, prot, map_flags);
- /* Unsupported flags */
- if (map_flags & ~(SCIF_MAP_FIXED | SCIF_MAP_KERNEL))
- return -EINVAL;
-
- /*
- * Offset is not page aligned/negative or offset+len
- * wraps around with SCIF_MAP_FIXED.
- */
- if ((map_flags & SCIF_MAP_FIXED) &&
- ((ALIGN(offset, PAGE_SIZE) != offset) ||
- (offset < 0) ||
- (len > LONG_MAX - offset)))
- return -EINVAL;
-
- /* Unsupported protection requested */
- if (prot & ~(SCIF_PROT_READ | SCIF_PROT_WRITE))
- return -EINVAL;
-
- /* addr/len must be page aligned. len should be non zero */
- if (!len || (ALIGN((u64)addr, PAGE_SIZE) != (u64)addr) ||
- (ALIGN(len, PAGE_SIZE) != len))
- return -EINVAL;
-
- might_sleep();
-
- err = scif_verify_epd(ep);
- if (err)
- return err;
-
- /* Compute the offset for this registration */
- err = scif_get_window_offset(ep, map_flags, offset,
- len >> PAGE_SHIFT, &computed_offset);
- if (err)
- return err;
-
- spdev = scif_get_peer_dev(ep->remote_dev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- scif_free_window_offset(ep, NULL, computed_offset);
- return err;
- }
- /* Allocate and prepare self registration window */
- window = scif_create_window(ep, len >> PAGE_SHIFT,
- computed_offset, false);
- if (!window) {
- scif_free_window_offset(ep, NULL, computed_offset);
- scif_put_peer_dev(spdev);
- return -ENOMEM;
- }
-
- window->nr_pages = len >> PAGE_SHIFT;
-
- err = scif_send_alloc_request(ep, window);
- if (err) {
- scif_destroy_incomplete_window(ep, window);
- scif_put_peer_dev(spdev);
- return err;
- }
-
- if (!(map_flags & SCIF_MAP_KERNEL)) {
- mm = __scif_acquire_mm();
- map_flags |= SCIF_MAP_ULIMIT;
- }
- /* Pin down the pages */
- err = __scif_pin_pages(addr, len, &prot,
- map_flags & (SCIF_MAP_KERNEL | SCIF_MAP_ULIMIT),
- &pinned_pages);
- if (err) {
- scif_destroy_incomplete_window(ep, window);
- __scif_release_mm(mm);
- goto error;
- }
-
- window->pinned_pages = pinned_pages;
- window->prot = pinned_pages->prot;
- window->mm = mm;
-
- /* Prepare the remote registration window */
- err = scif_prep_remote_window(ep, window);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %ld\n", __func__, __LINE__, err);
- goto error_unmap;
- }
-
- /* Tell the peer about the new window */
- err = scif_send_scif_register(ep, window);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %ld\n", __func__, __LINE__, err);
- goto error_unmap;
- }
-
- scif_put_peer_dev(spdev);
- /* No further failures expected. Insert new window */
- scif_insert_local_window(window, ep);
- dev_dbg(&ep->remote_dev->sdev->dev,
- "SCIFAPI register: ep %p addr %p len 0x%lx computed_offset 0x%llx\n",
- epd, addr, len, computed_offset);
- return computed_offset;
-error_unmap:
- scif_destroy_window(ep, window);
-error:
- scif_put_peer_dev(spdev);
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %ld\n", __func__, __LINE__, err);
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_register);
-
-int
-scif_unregister(scif_epd_t epd, off_t offset, size_t len)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct scif_window *window = NULL;
- struct scif_rma_req req;
- int nr_pages, err;
- struct device *spdev;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI unregister: ep %p offset 0x%lx len 0x%lx\n",
- ep, offset, len);
- /* len must be page aligned. len should be non zero */
- if (!len ||
- (ALIGN((u64)len, PAGE_SIZE) != (u64)len))
- return -EINVAL;
-
- /* Offset is not page aligned or offset+len wraps around */
- if ((ALIGN(offset, PAGE_SIZE) != offset) ||
- (offset < 0) ||
- (len > LONG_MAX - offset))
- return -EINVAL;
-
- err = scif_verify_epd(ep);
- if (err)
- return err;
-
- might_sleep();
- nr_pages = len >> PAGE_SHIFT;
-
- req.out_window = &window;
- req.offset = offset;
- req.prot = 0;
- req.nr_bytes = len;
- req.type = SCIF_WINDOW_FULL;
- req.head = &ep->rma_info.reg_list;
-
- spdev = scif_get_peer_dev(ep->remote_dev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- return err;
- }
- mutex_lock(&ep->rma_info.rma_lock);
- /* Does a valid window exist? */
- err = scif_query_window(&req);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto error;
- }
- /* Unregister all the windows in this range */
- err = scif_rma_list_unregister(window, offset, nr_pages);
- if (err)
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
-error:
- mutex_unlock(&ep->rma_info.rma_lock);
- scif_put_peer_dev(spdev);
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_unregister);
diff --git a/drivers/misc/mic/scif/scif_rma.h b/drivers/misc/mic/scif/scif_rma.h
deleted file mode 100644
index 964dd0f..0000000
--- a/drivers/misc/mic/scif/scif_rma.h
+++ /dev/null
@@ -1,477 +0,0 @@
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * Intel SCIF driver.
- *
- */
-#ifndef SCIF_RMA_H
-#define SCIF_RMA_H
-
-#include <linux/intel-iommu.h>
-#include <linux/mmu_notifier.h>
-
-#include "../bus/scif_bus.h"
-
-/* If this bit is set then the mark is a remote fence mark */
-#define SCIF_REMOTE_FENCE_BIT 31
-/* Magic value used to indicate a remote fence request */
-#define SCIF_REMOTE_FENCE BIT_ULL(SCIF_REMOTE_FENCE_BIT)
-
-#define SCIF_MAX_UNALIGNED_BUF_SIZE (1024 * 1024ULL)
-#define SCIF_KMEM_UNALIGNED_BUF_SIZE (SCIF_MAX_UNALIGNED_BUF_SIZE + \
- (L1_CACHE_BYTES << 1))
-
-#define SCIF_IOVA_START_PFN (1)
-#define SCIF_IOVA_PFN(addr) ((addr) >> PAGE_SHIFT)
-#define SCIF_DMA_64BIT_PFN SCIF_IOVA_PFN(DMA_BIT_MASK(64))
-#define SCIF_DMA_63BIT_PFN SCIF_IOVA_PFN(DMA_BIT_MASK(63))
-
-/*
- * struct scif_endpt_rma_info - Per Endpoint Remote Memory Access Information
- *
- * @reg_list: List of registration windows for self
- * @remote_reg_list: List of registration windows for peer
- * @iovad: Offset generator
- * @rma_lock: Synchronizes access to self/remote list and also protects the
- * window from being destroyed while RMAs are in progress.
- * @tc_lock: Synchronizes access to temporary cached windows list
- * for SCIF Registration Caching.
- * @mmn_lock: Synchronizes access to the list of MMU notifiers registered
- * @tw_refcount: Keeps track of number of outstanding temporary registered
- * windows created by scif_vreadfrom/scif_vwriteto which have
- * not been destroyed.
- * @tcw_refcount: Same as tw_refcount but for temporary cached windows
- * @tcw_total_pages: Same as tcw_refcount but in terms of pages pinned
- * @mmn_list: MMU notifier so that we can destroy the windows when required
- * @fence_refcount: Keeps track of number of outstanding remote fence
- * requests which have been received by the peer.
- * @dma_chan: DMA channel used for all DMA transfers for this endpoint.
- * @async_list_del: Detect asynchronous list entry deletion
- * @vma_list: List of vmas with remote memory mappings
- * @markwq: Wait queue used for scif_fence_mark/scif_fence_wait
-*/
-struct scif_endpt_rma_info {
- struct list_head reg_list;
- struct list_head remote_reg_list;
- struct iova_domain iovad;
- struct mutex rma_lock;
- spinlock_t tc_lock;
- struct mutex mmn_lock;
- atomic_t tw_refcount;
- atomic_t tcw_refcount;
- atomic_t tcw_total_pages;
- struct list_head mmn_list;
- atomic_t fence_refcount;
- struct dma_chan *dma_chan;
- int async_list_del;
- struct list_head vma_list;
- wait_queue_head_t markwq;
-};
-
-/*
- * struct scif_fence_info - used for tracking fence requests
- *
- * @state: State of this transfer
- * @wq: Fences wait on this queue
- * @dma_mark: Used for storing the DMA mark
- */
-struct scif_fence_info {
- enum scif_msg_state state;
- struct completion comp;
- int dma_mark;
-};
-
-/*
- * struct scif_remote_fence_info - used for tracking remote fence requests
- *
- * @msg: List of SCIF node QP fence messages
- * @list: Link to list of remote fence requests
- */
-struct scif_remote_fence_info {
- struct scifmsg msg;
- struct list_head list;
-};
-
-/*
- * Specifies whether an RMA operation can span across partial windows, a single
- * window or multiple contiguous windows. Mmaps can span across partial windows.
- * Unregistration can span across complete windows. scif_get_pages() can span a
- * single window. A window can also be of type self or peer.
- */
-enum scif_window_type {
- SCIF_WINDOW_PARTIAL,
- SCIF_WINDOW_SINGLE,
- SCIF_WINDOW_FULL,
- SCIF_WINDOW_SELF,
- SCIF_WINDOW_PEER
-};
-
-/* The number of physical addresses that can be stored in a PAGE. */
-#define SCIF_NR_ADDR_IN_PAGE (0x1000 >> 3)
-
-/*
- * struct scif_rma_lookup - RMA lookup data structure for page list transfers
- *
- * Store an array of lookup offsets. Each offset in this array maps
- * one 4K page containing 512 physical addresses i.e. 2MB. 512 such
- * offsets in a 4K page will correspond to 1GB of registered address space.
-
- * @lookup: Array of offsets
- * @offset: DMA offset of lookup array
- */
-struct scif_rma_lookup {
- dma_addr_t *lookup;
- dma_addr_t offset;
-};
-
-/*
- * struct scif_pinned_pages - A set of pinned pages obtained with
- * scif_pin_pages() which could be part of multiple registered
- * windows across different end points.
- *
- * @nr_pages: Number of pages which is defined as a s64 instead of an int
- * to avoid sign extension with buffers >= 2GB
- * @prot: read/write protections
- * @map_flags: Flags specified during the pin operation
- * @ref_count: Reference count bumped in terms of number of pages
- * @magic: A magic value
- * @pages: Array of pointers to struct pages populated with get_user_pages(..)
- */
-struct scif_pinned_pages {
- s64 nr_pages;
- int prot;
- int map_flags;
- atomic_t ref_count;
- u64 magic;
- struct page **pages;
-};
-
-/*
- * struct scif_status - Stores DMA status update information
- *
- * @src_dma_addr: Source buffer DMA address
- * @val: src location for value to be written to the destination
- * @ep: SCIF endpoint
- */
-struct scif_status {
- dma_addr_t src_dma_addr;
- u64 val;
- struct scif_endpt *ep;
-};
-
-/*
- * struct scif_cb_arg - Stores the argument of the callback func
- *
- * @src_dma_addr: Source buffer DMA address
- * @status: DMA status
- * @ep: SCIF endpoint
- */
-struct scif_cb_arg {
- dma_addr_t src_dma_addr;
- struct scif_status *status;
- struct scif_endpt *ep;
-};
-
-/*
- * struct scif_window - Registration Window for Self and Remote
- *
- * @nr_pages: Number of pages which is defined as a s64 instead of an int
- * to avoid sign extension with buffers >= 2GB
- * @nr_contig_chunks: Number of contiguous physical chunks
- * @prot: read/write protections
- * @ref_count: reference count in terms of number of pages
- * @magic: Cookie to detect corruption
- * @offset: registered offset
- * @va_for_temp: va address that this window represents
- * @dma_mark: Used to determine if all DMAs against the window are done
- * @ep: Pointer to EP. Useful for passing EP around with messages to
- avoid expensive list traversals.
- * @list: link to list of windows for the endpoint
- * @type: self or peer window
- * @peer_window: Pointer to peer window. Useful for sending messages to peer
- * without requiring an extra list traversal
- * @unreg_state: unregistration state
- * @offset_freed: True if the offset has been freed
- * @temp: True for temporary windows created via scif_vreadfrom/scif_vwriteto
- * @mm: memory descriptor for the task_struct which initiated the RMA
- * @st: scatter gather table for DMA mappings with IOMMU enabled
- * @pinned_pages: The set of pinned_pages backing this window
- * @alloc_handle: Handle for sending ALLOC_REQ
- * @regwq: Wait Queue for an registration (N)ACK
- * @reg_state: Registration state
- * @unregwq: Wait Queue for an unregistration (N)ACK
- * @dma_addr_lookup: Lookup for physical addresses used for DMA
- * @nr_lookup: Number of entries in lookup
- * @mapped_offset: Offset used to map the window by the peer
- * @dma_addr: Array of physical addresses used for Mgmt node & MIC initiated DMA
- * @num_pages: Array specifying number of pages for each physical address
- */
-struct scif_window {
- s64 nr_pages;
- int nr_contig_chunks;
- int prot;
- int ref_count;
- u64 magic;
- s64 offset;
- unsigned long va_for_temp;
- int dma_mark;
- u64 ep;
- struct list_head list;
- enum scif_window_type type;
- u64 peer_window;
- enum scif_msg_state unreg_state;
- bool offset_freed;
- bool temp;
- struct mm_struct *mm;
- struct sg_table *st;
- union {
- struct {
- struct scif_pinned_pages *pinned_pages;
- struct scif_allocmsg alloc_handle;
- wait_queue_head_t regwq;
- enum scif_msg_state reg_state;
- wait_queue_head_t unregwq;
- };
- struct {
- struct scif_rma_lookup dma_addr_lookup;
- struct scif_rma_lookup num_pages_lookup;
- int nr_lookup;
- dma_addr_t mapped_offset;
- };
- };
- dma_addr_t *dma_addr;
- u64 *num_pages;
-} __packed;
-
-/*
- * scif_mmu_notif - SCIF mmu notifier information
- *
- * @mmu_notifier ep_mmu_notifier: MMU notifier operations
- * @tc_reg_list: List of temp registration windows for self
- * @mm: memory descriptor for the task_struct which initiated the RMA
- * @ep: SCIF endpoint
- * @list: link to list of MMU notifier information
- */
-struct scif_mmu_notif {
-#ifdef CONFIG_MMU_NOTIFIER
- struct mmu_notifier ep_mmu_notifier;
-#endif
- struct list_head tc_reg_list;
- struct mm_struct *mm;
- struct scif_endpt *ep;
- struct list_head list;
-};
-
-enum scif_rma_dir {
- SCIF_LOCAL_TO_REMOTE,
- SCIF_REMOTE_TO_LOCAL
-};
-
-extern struct kmem_cache *unaligned_cache;
-/* Initialize RMA for this EP */
-void scif_rma_ep_init(struct scif_endpt *ep);
-/* Check if epd can be uninitialized */
-int scif_rma_ep_can_uninit(struct scif_endpt *ep);
-/* Obtain a new offset. Callee must grab RMA lock */
-int scif_get_window_offset(struct scif_endpt *ep, int flags,
- s64 offset, int nr_pages, s64 *out_offset);
-/* Free offset. Callee must grab RMA lock */
-void scif_free_window_offset(struct scif_endpt *ep,
- struct scif_window *window, s64 offset);
-/* Create self registration window */
-struct scif_window *scif_create_window(struct scif_endpt *ep, int nr_pages,
- s64 offset, bool temp);
-/* Destroy self registration window.*/
-int scif_destroy_window(struct scif_endpt *ep, struct scif_window *window);
-void scif_unmap_window(struct scif_dev *remote_dev, struct scif_window *window);
-/* Map pages of self window to Aperture/PCI */
-int scif_map_window(struct scif_dev *remote_dev,
- struct scif_window *window);
-/* Unregister a self window */
-int scif_unregister_window(struct scif_window *window);
-/* Destroy remote registration window */
-void
-scif_destroy_remote_window(struct scif_window *window);
-/* remove valid remote memory mappings from process address space */
-void scif_zap_mmaps(int node);
-/* Query if any applications have remote memory mappings */
-bool scif_rma_do_apps_have_mmaps(int node);
-/* Cleanup remote registration lists for zombie endpoints */
-void scif_cleanup_rma_for_zombies(int node);
-/* Reserve a DMA channel for a particular endpoint */
-int scif_reserve_dma_chan(struct scif_endpt *ep);
-/* Setup a DMA mark for an endpoint */
-int _scif_fence_mark(scif_epd_t epd, int *mark);
-int scif_prog_signal(scif_epd_t epd, off_t offset, u64 val,
- enum scif_window_type type);
-void scif_alloc_req(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_alloc_gnt_rej(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_free_virt(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_reg(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_unreg(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_reg_ack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_reg_nack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_unreg_ack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_unreg_nack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_munmap(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_mark(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_mark_resp(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_wait(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_wait_resp(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_sig_local(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_sig_remote(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_sig_resp(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_mmu_notif_handler(struct work_struct *work);
-void scif_rma_handle_remote_fences(void);
-void scif_rma_destroy_windows(void);
-void scif_rma_destroy_tcw_invalid(void);
-int scif_drain_dma_intr(struct scif_hw_dev *sdev, struct dma_chan *chan);
-
-struct scif_window_iter {
- s64 offset;
- int index;
-};
-
-static inline void
-scif_init_window_iter(struct scif_window *window, struct scif_window_iter *iter)
-{
- iter->offset = window->offset;
- iter->index = 0;
-}
-
-dma_addr_t scif_off_to_dma_addr(struct scif_window *window, s64 off,
- size_t *nr_bytes,
- struct scif_window_iter *iter);
-static inline
-dma_addr_t __scif_off_to_dma_addr(struct scif_window *window, s64 off)
-{
- return scif_off_to_dma_addr(window, off, NULL, NULL);
-}
-
-static inline bool scif_unaligned(off_t src_offset, off_t dst_offset)
-{
- src_offset = src_offset & (L1_CACHE_BYTES - 1);
- dst_offset = dst_offset & (L1_CACHE_BYTES - 1);
- return !(src_offset == dst_offset);
-}
-
-/*
- * scif_zalloc:
- * @size: Size of the allocation request.
- *
- * Helper API which attempts to allocate zeroed pages via
- * __get_free_pages(..) first and then falls back on
- * vzalloc(..) if that fails.
- */
-static inline void *scif_zalloc(size_t size)
-{
- void *ret = NULL;
- size_t align = ALIGN(size, PAGE_SIZE);
-
- if (align && get_order(align) < MAX_ORDER)
- ret = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
- get_order(align));
- return ret ? ret : vzalloc(align);
-}
-
-/*
- * scif_free:
- * @addr: Address to be freed.
- * @size: Size of the allocation.
- * Helper API which frees memory allocated via scif_zalloc().
- */
-static inline void scif_free(void *addr, size_t size)
-{
- size_t align = ALIGN(size, PAGE_SIZE);
-
- if (is_vmalloc_addr(addr))
- vfree(addr);
- else
- free_pages((unsigned long)addr, get_order(align));
-}
-
-static inline void scif_get_window(struct scif_window *window, int nr_pages)
-{
- window->ref_count += nr_pages;
-}
-
-static inline void scif_put_window(struct scif_window *window, int nr_pages)
-{
- window->ref_count -= nr_pages;
-}
-
-static inline void scif_set_window_ref(struct scif_window *window, int nr_pages)
-{
- window->ref_count = nr_pages;
-}
-
-static inline void
-scif_queue_for_cleanup(struct scif_window *window, struct list_head *list)
-{
- spin_lock(&scif_info.rmalock);
- list_add_tail(&window->list, list);
- spin_unlock(&scif_info.rmalock);
- schedule_work(&scif_info.misc_work);
-}
-
-static inline void __scif_rma_destroy_tcw_helper(struct scif_window *window)
-{
- list_del_init(&window->list);
- scif_queue_for_cleanup(window, &scif_info.rma_tc);
-}
-
-static inline bool scif_is_iommu_enabled(void)
-{
-#ifdef CONFIG_INTEL_IOMMU
- return intel_iommu_enabled;
-#else
- return false;
-#endif
-}
-#endif /* SCIF_RMA_H */
diff --git a/drivers/misc/mic/scif/scif_rma_list.c b/drivers/misc/mic/scif/scif_rma_list.c
deleted file mode 100644
index ef923ba..0000000
--- a/drivers/misc/mic/scif/scif_rma_list.c
+++ /dev/null
@@ -1,282 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-#include <linux/mmu_notifier.h>
-#include <linux/highmem.h>
-
-/*
- * scif_insert_tcw:
- *
- * Insert a temp window to the temp registration list sorted by va_for_temp.
- * RMA lock must be held.
- */
-void scif_insert_tcw(struct scif_window *window, struct list_head *head)
-{
- struct scif_window *curr = NULL;
- struct scif_window *prev = list_entry(head, struct scif_window, list);
- struct list_head *item;
-
- INIT_LIST_HEAD(&window->list);
- /* Compare with tail and if the entry is new tail add it to the end */
- if (!list_empty(head)) {
- curr = list_entry(head->prev, struct scif_window, list);
- if (curr->va_for_temp < window->va_for_temp) {
- list_add_tail(&window->list, head);
- return;
- }
- }
- list_for_each(item, head) {
- curr = list_entry(item, struct scif_window, list);
- if (curr->va_for_temp > window->va_for_temp)
- break;
- prev = curr;
- }
- list_add(&window->list, &prev->list);
-}
-
-/*
- * scif_insert_window:
- *
- * Insert a window to the self registration list sorted by offset.
- * RMA lock must be held.
- */
-void scif_insert_window(struct scif_window *window, struct list_head *head)
-{
- struct scif_window *curr = NULL, *prev = NULL;
- struct list_head *item;
-
- INIT_LIST_HEAD(&window->list);
- list_for_each(item, head) {
- curr = list_entry(item, struct scif_window, list);
- if (curr->offset > window->offset)
- break;
- prev = curr;
- }
- if (!prev)
- list_add(&window->list, head);
- else
- list_add(&window->list, &prev->list);
- scif_set_window_ref(window, window->nr_pages);
-}
-
-/*
- * scif_query_tcw:
- *
- * Query the temp cached registration list of ep for an overlapping window
- * in case of permission mismatch, destroy the previous window. if permissions
- * match and overlap is partial, destroy the window but return the new range
- * RMA lock must be held.
- */
-int scif_query_tcw(struct scif_endpt *ep, struct scif_rma_req *req)
-{
- struct list_head *item, *temp, *head = req->head;
- struct scif_window *window;
- u64 start_va_window, start_va_req = req->va_for_temp;
- u64 end_va_window, end_va_req = start_va_req + req->nr_bytes;
-
- if (!req->nr_bytes)
- return -EINVAL;
- /*
- * Avoid traversing the entire list to find out that there
- * is no entry that matches
- */
- if (!list_empty(head)) {
- window = list_last_entry(head, struct scif_window, list);
- end_va_window = window->va_for_temp +
- (window->nr_pages << PAGE_SHIFT);
- if (start_va_req > end_va_window)
- return -ENXIO;
- }
- list_for_each_safe(item, temp, head) {
- window = list_entry(item, struct scif_window, list);
- start_va_window = window->va_for_temp;
- end_va_window = window->va_for_temp +
- (window->nr_pages << PAGE_SHIFT);
- if (start_va_req < start_va_window &&
- end_va_req < start_va_window)
- break;
- if (start_va_req >= end_va_window)
- continue;
- if ((window->prot & req->prot) == req->prot) {
- if (start_va_req >= start_va_window &&
- end_va_req <= end_va_window) {
- *req->out_window = window;
- return 0;
- }
- /* expand window */
- if (start_va_req < start_va_window) {
- req->nr_bytes +=
- start_va_window - start_va_req;
- req->va_for_temp = start_va_window;
- }
- if (end_va_req >= end_va_window)
- req->nr_bytes += end_va_window - end_va_req;
- }
- /* Destroy the old window to create a new one */
- __scif_rma_destroy_tcw_helper(window);
- break;
- }
- return -ENXIO;
-}
-
-/*
- * scif_query_window:
- *
- * Query the registration list and check if a valid contiguous
- * range of windows exist.
- * RMA lock must be held.
- */
-int scif_query_window(struct scif_rma_req *req)
-{
- struct list_head *item;
- struct scif_window *window;
- s64 end_offset, offset = req->offset;
- u64 tmp_min, nr_bytes_left = req->nr_bytes;
-
- if (!req->nr_bytes)
- return -EINVAL;
-
- list_for_each(item, req->head) {
- window = list_entry(item, struct scif_window, list);
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
- if (offset < window->offset)
- /* Offset not found! */
- return -ENXIO;
- if (offset >= end_offset)
- continue;
- /* Check read/write protections. */
- if ((window->prot & req->prot) != req->prot)
- return -EPERM;
- if (nr_bytes_left == req->nr_bytes)
- /* Store the first window */
- *req->out_window = window;
- tmp_min = min((u64)end_offset - offset, nr_bytes_left);
- nr_bytes_left -= tmp_min;
- offset += tmp_min;
- /*
- * Range requested encompasses
- * multiple windows contiguously.
- */
- if (!nr_bytes_left) {
- /* Done for partial window */
- if (req->type == SCIF_WINDOW_PARTIAL ||
- req->type == SCIF_WINDOW_SINGLE)
- return 0;
- /* Extra logic for full windows */
- if (offset == end_offset)
- /* Spanning multiple whole windows */
- return 0;
- /* Not spanning multiple whole windows */
- return -ENXIO;
- }
- if (req->type == SCIF_WINDOW_SINGLE)
- break;
- }
- dev_err(scif_info.mdev.this_device,
- "%s %d ENXIO\n", __func__, __LINE__);
- return -ENXIO;
-}
-
-/*
- * scif_rma_list_unregister:
- *
- * Traverse the self registration list starting from window:
- * 1) Call scif_unregister_window(..)
- * RMA lock must be held.
- */
-int scif_rma_list_unregister(struct scif_window *window,
- s64 offset, int nr_pages)
-{
- struct scif_endpt *ep = (struct scif_endpt *)window->ep;
- struct list_head *head = &ep->rma_info.reg_list;
- s64 end_offset;
- int err = 0;
- int loop_nr_pages;
- struct scif_window *_window;
-
- list_for_each_entry_safe_from(window, _window, head, list) {
- end_offset = window->offset + (window->nr_pages << PAGE_SHIFT);
- loop_nr_pages = min((int)((end_offset - offset) >> PAGE_SHIFT),
- nr_pages);
- err = scif_unregister_window(window);
- if (err)
- return err;
- nr_pages -= loop_nr_pages;
- offset += (loop_nr_pages << PAGE_SHIFT);
- if (!nr_pages)
- break;
- }
- return 0;
-}
-
-/*
- * scif_unmap_all_window:
- *
- * Traverse all the windows in the self registration list and:
- * 1) Delete any DMA mappings created
- */
-void scif_unmap_all_windows(scif_epd_t epd)
-{
- struct list_head *item, *tmp;
- struct scif_window *window;
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct list_head *head = &ep->rma_info.reg_list;
-
- mutex_lock(&ep->rma_info.rma_lock);
- list_for_each_safe(item, tmp, head) {
- window = list_entry(item, struct scif_window, list);
- scif_unmap_window(ep->remote_dev, window);
- }
- mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-/*
- * scif_unregister_all_window:
- *
- * Traverse all the windows in the self registration list and:
- * 1) Call scif_unregister_window(..)
- * RMA lock must be held.
- */
-int scif_unregister_all_windows(scif_epd_t epd)
-{
- struct list_head *item, *tmp;
- struct scif_window *window;
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct list_head *head = &ep->rma_info.reg_list;
- int err = 0;
-
- mutex_lock(&ep->rma_info.rma_lock);
-retry:
- item = NULL;
- tmp = NULL;
- list_for_each_safe(item, tmp, head) {
- window = list_entry(item, struct scif_window, list);
- ep->rma_info.async_list_del = 0;
- err = scif_unregister_window(window);
- if (err)
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n",
- __func__, __LINE__, err);
- /*
- * Need to restart list traversal if there has been
- * an asynchronous list entry deletion.
- */
- if (READ_ONCE(ep->rma_info.async_list_del))
- goto retry;
- }
- mutex_unlock(&ep->rma_info.rma_lock);
- if (!list_empty(&ep->rma_info.mmn_list)) {
- spin_lock(&scif_info.rmalock);
- list_add_tail(&ep->mmu_list, &scif_info.mmu_notif_cleanup);
- spin_unlock(&scif_info.rmalock);
- schedule_work(&scif_info.mmu_notif_work);
- }
- return err;
-}
diff --git a/drivers/misc/mic/scif/scif_rma_list.h b/drivers/misc/mic/scif/scif_rma_list.h
deleted file mode 100644
index 0f8e0ed..0000000
--- a/drivers/misc/mic/scif/scif_rma_list.h
+++ /dev/null
@@ -1,48 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#ifndef SCIF_RMA_LIST_H
-#define SCIF_RMA_LIST_H
-
-/*
- * struct scif_rma_req - Self Registration list RMA Request query
- *
- * @out_window - Returns the window if found
- * @offset: Starting offset
- * @nr_bytes: number of bytes
- * @prot: protection requested i.e. read or write or both
- * @type: Specify single, partial or multiple windows
- * @head: Head of list on which to search
- * @va_for_temp: VA for searching temporary cached windows
- */
-struct scif_rma_req {
- struct scif_window **out_window;
- union {
- s64 offset;
- unsigned long va_for_temp;
- };
- size_t nr_bytes;
- int prot;
- enum scif_window_type type;
- struct list_head *head;
-};
-
-/* Insert */
-void scif_insert_window(struct scif_window *window, struct list_head *head);
-void scif_insert_tcw(struct scif_window *window,
- struct list_head *head);
-/* Query */
-int scif_query_window(struct scif_rma_req *request);
-int scif_query_tcw(struct scif_endpt *ep, struct scif_rma_req *request);
-/* Called from close to unregister all self windows */
-int scif_unregister_all_windows(scif_epd_t epd);
-void scif_unmap_all_windows(scif_epd_t epd);
-/* Traverse list and unregister */
-int scif_rma_list_unregister(struct scif_window *window, s64 offset,
- int nr_pages);
-#endif /* SCIF_RMA_LIST_H */
diff --git a/drivers/misc/mic/vop/Makefile b/drivers/misc/mic/vop/Makefile
deleted file mode 100644
index 51b9b00..0000000
--- a/drivers/misc/mic/vop/Makefile
+++ /dev/null
@@ -1,10 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Makefile - Intel MIC Linux driver.
-# Copyright(c) 2016, Intel Corporation.
-#
-obj-$(CONFIG_VOP) := vop.o
-
-vop-objs += vop_main.o
-vop-objs += vop_debugfs.o
-vop-objs += vop_vringh.o
diff --git a/drivers/misc/mic/vop/vop_debugfs.c b/drivers/misc/mic/vop/vop_debugfs.c
deleted file mode 100644
index 9d4f175..0000000
--- a/drivers/misc/mic/vop/vop_debugfs.c
+++ /dev/null
@@ -1,184 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Intel Virtio Over PCIe (VOP) driver.
- */
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-
-#include "vop_main.h"
-
-static int vop_dp_show(struct seq_file *s, void *pos)
-{
- struct mic_device_desc *d;
- struct mic_device_ctrl *dc;
- struct mic_vqconfig *vqconfig;
- __u32 *features;
- __u8 *config;
- struct vop_info *vi = s->private;
- struct vop_device *vpdev = vi->vpdev;
- struct mic_bootparam *bootparam = vpdev->hw_ops->get_dp(vpdev);
- int j, k;
-
- seq_printf(s, "Bootparam: magic 0x%x\n",
- bootparam->magic);
- seq_printf(s, "Bootparam: h2c_config_db %d\n",
- bootparam->h2c_config_db);
- seq_printf(s, "Bootparam: node_id %d\n",
- bootparam->node_id);
- seq_printf(s, "Bootparam: c2h_scif_db %d\n",
- bootparam->c2h_scif_db);
- seq_printf(s, "Bootparam: h2c_scif_db %d\n",
- bootparam->h2c_scif_db);
- seq_printf(s, "Bootparam: scif_host_dma_addr 0x%llx\n",
- bootparam->scif_host_dma_addr);
- seq_printf(s, "Bootparam: scif_card_dma_addr 0x%llx\n",
- bootparam->scif_card_dma_addr);
-
- for (j = sizeof(*bootparam);
- j < MIC_DP_SIZE; j += mic_total_desc_size(d)) {
- d = (void *)bootparam + j;
- dc = (void *)d + mic_aligned_desc_size(d);
-
- /* end of list */
- if (d->type == 0)
- break;
-
- if (d->type == -1)
- continue;
-
- seq_printf(s, "Type %d ", d->type);
- seq_printf(s, "Num VQ %d ", d->num_vq);
- seq_printf(s, "Feature Len %d\n", d->feature_len);
- seq_printf(s, "Config Len %d ", d->config_len);
- seq_printf(s, "Shutdown Status %d\n", d->status);
-
- for (k = 0; k < d->num_vq; k++) {
- vqconfig = mic_vq_config(d) + k;
- seq_printf(s, "vqconfig[%d]: ", k);
- seq_printf(s, "address 0x%llx ",
- vqconfig->address);
- seq_printf(s, "num %d ", vqconfig->num);
- seq_printf(s, "used address 0x%llx\n",
- vqconfig->used_address);
- }
-
- features = (__u32 *)mic_vq_features(d);
- seq_printf(s, "Features: Host 0x%x ", features[0]);
- seq_printf(s, "Guest 0x%x\n", features[1]);
-
- config = mic_vq_configspace(d);
- for (k = 0; k < d->config_len; k++)
- seq_printf(s, "config[%d]=%d\n", k, config[k]);
-
- seq_puts(s, "Device control:\n");
- seq_printf(s, "Config Change %d ", dc->config_change);
- seq_printf(s, "Vdev reset %d\n", dc->vdev_reset);
- seq_printf(s, "Guest Ack %d ", dc->guest_ack);
- seq_printf(s, "Host ack %d\n", dc->host_ack);
- seq_printf(s, "Used address updated %d ",
- dc->used_address_updated);
- seq_printf(s, "Vdev 0x%llx\n", dc->vdev);
- seq_printf(s, "c2h doorbell %d ", dc->c2h_vdev_db);
- seq_printf(s, "h2c doorbell %d\n", dc->h2c_vdev_db);
- }
- schedule_work(&vi->hotplug_work);
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(vop_dp);
-
-static int vop_vdev_info_show(struct seq_file *s, void *unused)
-{
- struct vop_info *vi = s->private;
- struct list_head *pos, *tmp;
- struct vop_vdev *vdev;
- int i, j;
-
- mutex_lock(&vi->vop_mutex);
- list_for_each_safe(pos, tmp, &vi->vdev_list) {
- vdev = list_entry(pos, struct vop_vdev, list);
- seq_printf(s, "VDEV type %d state %s in %ld out %ld in_dma %ld out_dma %ld\n",
- vdev->virtio_id,
- vop_vdevup(vdev) ? "UP" : "DOWN",
- vdev->in_bytes,
- vdev->out_bytes,
- vdev->in_bytes_dma,
- vdev->out_bytes_dma);
- for (i = 0; i < MIC_MAX_VRINGS; i++) {
- struct vring_desc *desc;
- struct vring_avail *avail;
- struct vring_used *used;
- struct vop_vringh *vvr = &vdev->vvr[i];
- struct vringh *vrh = &vvr->vrh;
- int num = vrh->vring.num;
-
- if (!num)
- continue;
- desc = vrh->vring.desc;
- seq_printf(s, "vring i %d avail_idx %d",
- i, vvr->vring.info->avail_idx & (num - 1));
- seq_printf(s, " vring i %d avail_idx %d\n",
- i, vvr->vring.info->avail_idx);
- seq_printf(s, "vrh i %d weak_barriers %d",
- i, vrh->weak_barriers);
- seq_printf(s, " last_avail_idx %d last_used_idx %d",
- vrh->last_avail_idx, vrh->last_used_idx);
- seq_printf(s, " completed %d\n", vrh->completed);
- for (j = 0; j < num; j++) {
- seq_printf(s, "desc[%d] addr 0x%llx len %d",
- j, desc->addr, desc->len);
- seq_printf(s, " flags 0x%x next %d\n",
- desc->flags, desc->next);
- desc++;
- }
- avail = vrh->vring.avail;
- seq_printf(s, "avail flags 0x%x idx %d\n",
- vringh16_to_cpu(vrh, avail->flags),
- vringh16_to_cpu(vrh,
- avail->idx) & (num - 1));
- seq_printf(s, "avail flags 0x%x idx %d\n",
- vringh16_to_cpu(vrh, avail->flags),
- vringh16_to_cpu(vrh, avail->idx));
- for (j = 0; j < num; j++)
- seq_printf(s, "avail ring[%d] %d\n",
- j, avail->ring[j]);
- used = vrh->vring.used;
- seq_printf(s, "used flags 0x%x idx %d\n",
- vringh16_to_cpu(vrh, used->flags),
- vringh16_to_cpu(vrh, used->idx) & (num - 1));
- seq_printf(s, "used flags 0x%x idx %d\n",
- vringh16_to_cpu(vrh, used->flags),
- vringh16_to_cpu(vrh, used->idx));
- for (j = 0; j < num; j++)
- seq_printf(s, "used ring[%d] id %d len %d\n",
- j, vringh32_to_cpu(vrh,
- used->ring[j].id),
- vringh32_to_cpu(vrh,
- used->ring[j].len));
- }
- }
- mutex_unlock(&vi->vop_mutex);
-
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(vop_vdev_info);
-
-void vop_init_debugfs(struct vop_info *vi)
-{
- char name[16];
-
- snprintf(name, sizeof(name), "%s%d", KBUILD_MODNAME, vi->vpdev->dnode);
- vi->dbg = debugfs_create_dir(name, NULL);
- debugfs_create_file("dp", 0444, vi->dbg, vi, &vop_dp_fops);
- debugfs_create_file("vdev_info", 0444, vi->dbg, vi, &vop_vdev_info_fops);
-}
-
-void vop_exit_debugfs(struct vop_info *vi)
-{
- debugfs_remove_recursive(vi->dbg);
-}
diff --git a/drivers/misc/mic/vop/vop_main.c b/drivers/misc/mic/vop/vop_main.c
deleted file mode 100644
index 714b94f..0000000
--- a/drivers/misc/mic/vop/vop_main.c
+++ /dev/null
@@ -1,784 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Adapted from:
- *
- * virtio for kvm on s390
- *
- * Copyright IBM Corp. 2008
- *
- * Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
- *
- * Intel Virtio Over PCIe (VOP) driver.
- */
-#include <linux/delay.h>
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/dma-mapping.h>
-#include <linux/io-64-nonatomic-lo-hi.h>
-
-#include "vop_main.h"
-
-#define VOP_MAX_VRINGS 4
-
-/*
- * _vop_vdev - Allocated per virtio device instance injected by the peer.
- *
- * @vdev: Virtio device
- * @desc: Virtio device page descriptor
- * @dc: Virtio device control
- * @vpdev: VOP device which is the parent for this virtio device
- * @vr: Buffer for accessing the VRING
- * @used_virt: Virtual address of used ring
- * @used: DMA address of used ring
- * @used_size: Size of the used buffer
- * @reset_done: Track whether VOP reset is complete
- * @virtio_cookie: Cookie returned upon requesting a interrupt
- * @c2h_vdev_db: The doorbell used by the guest to interrupt the host
- * @h2c_vdev_db: The doorbell used by the host to interrupt the guest
- * @dnode: The destination node
- */
-struct _vop_vdev {
- struct virtio_device vdev;
- struct mic_device_desc __iomem *desc;
- struct mic_device_ctrl __iomem *dc;
- struct vop_device *vpdev;
- void __iomem *vr[VOP_MAX_VRINGS];
- void *used_virt[VOP_MAX_VRINGS];
- dma_addr_t used[VOP_MAX_VRINGS];
- int used_size[VOP_MAX_VRINGS];
- struct completion reset_done;
- struct mic_irq *virtio_cookie;
- int c2h_vdev_db;
- int h2c_vdev_db;
- int dnode;
-};
-
-#define to_vopvdev(vd) container_of(vd, struct _vop_vdev, vdev)
-
-#define _vop_aligned_desc_size(d) __mic_align(_vop_desc_size(d), 8)
-
-/* Helper API to obtain the parent of the virtio device */
-static inline struct device *_vop_dev(struct _vop_vdev *vdev)
-{
- return vdev->vdev.dev.parent;
-}
-
-static inline unsigned _vop_desc_size(struct mic_device_desc __iomem *desc)
-{
- return sizeof(*desc)
- + ioread8(&desc->num_vq) * sizeof(struct mic_vqconfig)
- + ioread8(&desc->feature_len) * 2
- + ioread8(&desc->config_len);
-}
-
-static inline struct mic_vqconfig __iomem *
-_vop_vq_config(struct mic_device_desc __iomem *desc)
-{
- return (struct mic_vqconfig __iomem *)(desc + 1);
-}
-
-static inline u8 __iomem *
-_vop_vq_features(struct mic_device_desc __iomem *desc)
-{
- return (u8 __iomem *)(_vop_vq_config(desc) + ioread8(&desc->num_vq));
-}
-
-static inline u8 __iomem *
-_vop_vq_configspace(struct mic_device_desc __iomem *desc)
-{
- return _vop_vq_features(desc) + ioread8(&desc->feature_len) * 2;
-}
-
-static inline unsigned
-_vop_total_desc_size(struct mic_device_desc __iomem *desc)
-{
- return _vop_aligned_desc_size(desc) + sizeof(struct mic_device_ctrl);
-}
-
-/* This gets the device's feature bits. */
-static u64 vop_get_features(struct virtio_device *vdev)
-{
- unsigned int i, bits;
- u64 features = 0;
- struct mic_device_desc __iomem *desc = to_vopvdev(vdev)->desc;
- u8 __iomem *in_features = _vop_vq_features(desc);
- int feature_len = ioread8(&desc->feature_len);
-
- bits = min_t(unsigned, feature_len, sizeof(vdev->features)) * 8;
- for (i = 0; i < bits; i++)
- if (ioread8(&in_features[i / 8]) & (BIT(i % 8)))
- features |= BIT_ULL(i);
-
- return features;
-}
-
-static void vop_transport_features(struct virtio_device *vdev)
-{
- /*
- * Packed ring isn't enabled on virtio_vop for now,
- * because virtio_vop uses vring_new_virtqueue() which
- * creates virtio rings on preallocated memory.
- */
- __virtio_clear_bit(vdev, VIRTIO_F_RING_PACKED);
- __virtio_set_bit(vdev, VIRTIO_F_ACCESS_PLATFORM);
-}
-
-static int vop_finalize_features(struct virtio_device *vdev)
-{
- unsigned int i, bits;
- struct mic_device_desc __iomem *desc = to_vopvdev(vdev)->desc;
- u8 feature_len = ioread8(&desc->feature_len);
- /* Second half of bitmap is features we accept. */
- u8 __iomem *out_features =
- _vop_vq_features(desc) + feature_len;
-
- /* Give virtio_ring a chance to accept features. */
- vring_transport_features(vdev);
-
- /* Give virtio_vop a chance to accept features. */
- vop_transport_features(vdev);
-
- memset_io(out_features, 0, feature_len);
- bits = min_t(unsigned, feature_len,
- sizeof(vdev->features)) * 8;
- for (i = 0; i < bits; i++) {
- if (__virtio_test_bit(vdev, i))
- iowrite8(ioread8(&out_features[i / 8]) | (1 << (i % 8)),
- &out_features[i / 8]);
- }
- return 0;
-}
-
-/*
- * Reading and writing elements in config space
- */
-static void vop_get(struct virtio_device *vdev, unsigned int offset,
- void *buf, unsigned len)
-{
- struct mic_device_desc __iomem *desc = to_vopvdev(vdev)->desc;
-
- if (offset + len > ioread8(&desc->config_len))
- return;
- memcpy_fromio(buf, _vop_vq_configspace(desc) + offset, len);
-}
-
-static void vop_set(struct virtio_device *vdev, unsigned int offset,
- const void *buf, unsigned len)
-{
- struct mic_device_desc __iomem *desc = to_vopvdev(vdev)->desc;
-
- if (offset + len > ioread8(&desc->config_len))
- return;
- memcpy_toio(_vop_vq_configspace(desc) + offset, buf, len);
-}
-
-/*
- * The operations to get and set the status word just access the status
- * field of the device descriptor. set_status also interrupts the host
- * to tell about status changes.
- */
-static u8 vop_get_status(struct virtio_device *vdev)
-{
- return ioread8(&to_vopvdev(vdev)->desc->status);
-}
-
-static void vop_set_status(struct virtio_device *dev, u8 status)
-{
- struct _vop_vdev *vdev = to_vopvdev(dev);
- struct vop_device *vpdev = vdev->vpdev;
-
- if (!status)
- return;
- iowrite8(status, &vdev->desc->status);
- vpdev->hw_ops->send_intr(vpdev, vdev->c2h_vdev_db);
-}
-
-/* Inform host on a virtio device reset and wait for ack from host */
-static void vop_reset_inform_host(struct virtio_device *dev)
-{
- struct _vop_vdev *vdev = to_vopvdev(dev);
- struct mic_device_ctrl __iomem *dc = vdev->dc;
- struct vop_device *vpdev = vdev->vpdev;
- int retry;
-
- iowrite8(0, &dc->host_ack);
- iowrite8(1, &dc->vdev_reset);
- vpdev->hw_ops->send_intr(vpdev, vdev->c2h_vdev_db);
-
- /* Wait till host completes all card accesses and acks the reset */
- for (retry = 100; retry--;) {
- if (ioread8(&dc->host_ack))
- break;
- msleep(100);
- }
-
- dev_dbg(_vop_dev(vdev), "%s: retry: %d\n", __func__, retry);
-
- /* Reset status to 0 in case we timed out */
- iowrite8(0, &vdev->desc->status);
-}
-
-static void vop_reset(struct virtio_device *dev)
-{
- struct _vop_vdev *vdev = to_vopvdev(dev);
-
- dev_dbg(_vop_dev(vdev), "%s: virtio id %d\n",
- __func__, dev->id.device);
-
- vop_reset_inform_host(dev);
- complete_all(&vdev->reset_done);
-}
-
-/*
- * The virtio_ring code calls this API when it wants to notify the Host.
- */
-static bool vop_notify(struct virtqueue *vq)
-{
- struct _vop_vdev *vdev = vq->priv;
- struct vop_device *vpdev = vdev->vpdev;
-
- vpdev->hw_ops->send_intr(vpdev, vdev->c2h_vdev_db);
- return true;
-}
-
-static void vop_del_vq(struct virtqueue *vq, int n)
-{
- struct _vop_vdev *vdev = to_vopvdev(vq->vdev);
- struct vop_device *vpdev = vdev->vpdev;
-
- dma_unmap_single(&vpdev->dev, vdev->used[n],
- vdev->used_size[n], DMA_BIDIRECTIONAL);
- free_pages((unsigned long)vdev->used_virt[n],
- get_order(vdev->used_size[n]));
- vring_del_virtqueue(vq);
- vpdev->hw_ops->unmap(vpdev, vdev->vr[n]);
- vdev->vr[n] = NULL;
-}
-
-static void vop_del_vqs(struct virtio_device *dev)
-{
- struct _vop_vdev *vdev = to_vopvdev(dev);
- struct virtqueue *vq, *n;
- int idx = 0;
-
- dev_dbg(_vop_dev(vdev), "%s\n", __func__);
-
- list_for_each_entry_safe(vq, n, &dev->vqs, list)
- vop_del_vq(vq, idx++);
-}
-
-static struct virtqueue *vop_new_virtqueue(unsigned int index,
- unsigned int num,
- struct virtio_device *vdev,
- bool context,
- void *pages,
- bool (*notify)(struct virtqueue *vq),
- void (*callback)(struct virtqueue *vq),
- const char *name,
- void *used)
-{
- bool weak_barriers = false;
- struct vring vring;
-
- vring_init(&vring, num, pages, MIC_VIRTIO_RING_ALIGN);
- vring.used = used;
-
- return __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
- notify, callback, name);
-}
-
-/*
- * This routine will assign vring's allocated in host/io memory. Code in
- * virtio_ring.c however continues to access this io memory as if it were local
- * memory without io accessors.
- */
-static struct virtqueue *vop_find_vq(struct virtio_device *dev,
- unsigned index,
- void (*callback)(struct virtqueue *vq),
- const char *name, bool ctx)
-{
- struct _vop_vdev *vdev = to_vopvdev(dev);
- struct vop_device *vpdev = vdev->vpdev;
- struct mic_vqconfig __iomem *vqconfig;
- struct mic_vqconfig config;
- struct virtqueue *vq;
- void __iomem *va;
- struct _mic_vring_info __iomem *info;
- void *used;
- int vr_size, _vr_size, err, magic;
- u8 type = ioread8(&vdev->desc->type);
-
- if (index >= ioread8(&vdev->desc->num_vq))
- return ERR_PTR(-ENOENT);
-
- if (!name)
- return ERR_PTR(-ENOENT);
-
- /* First assign the vring's allocated in host memory */
- vqconfig = _vop_vq_config(vdev->desc) + index;
- memcpy_fromio(&config, vqconfig, sizeof(config));
- _vr_size = round_up(vring_size(le16_to_cpu(config.num), MIC_VIRTIO_RING_ALIGN), 4);
- vr_size = PAGE_ALIGN(_vr_size + sizeof(struct _mic_vring_info));
- va = vpdev->hw_ops->remap(vpdev, le64_to_cpu(config.address), vr_size);
- if (!va)
- return ERR_PTR(-ENOMEM);
- vdev->vr[index] = va;
- memset_io(va, 0x0, _vr_size);
-
- info = va + _vr_size;
- magic = ioread32(&info->magic);
-
- if (WARN(magic != MIC_MAGIC + type + index, "magic mismatch")) {
- err = -EIO;
- goto unmap;
- }
-
- vdev->used_size[index] = PAGE_ALIGN(sizeof(__u16) * 3 +
- sizeof(struct vring_used_elem) *
- le16_to_cpu(config.num));
- used = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
- get_order(vdev->used_size[index]));
- vdev->used_virt[index] = used;
- if (!used) {
- err = -ENOMEM;
- dev_err(_vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto unmap;
- }
-
- vq = vop_new_virtqueue(index, le16_to_cpu(config.num), dev, ctx,
- (void __force *)va, vop_notify, callback,
- name, used);
- if (!vq) {
- err = -ENOMEM;
- goto free_used;
- }
-
- vdev->used[index] = dma_map_single(&vpdev->dev, used,
- vdev->used_size[index],
- DMA_BIDIRECTIONAL);
- if (dma_mapping_error(&vpdev->dev, vdev->used[index])) {
- err = -ENOMEM;
- dev_err(_vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto del_vq;
- }
- writeq(vdev->used[index], &vqconfig->used_address);
-
- vq->priv = vdev;
- return vq;
-del_vq:
- vring_del_virtqueue(vq);
-free_used:
- free_pages((unsigned long)used,
- get_order(vdev->used_size[index]));
-unmap:
- vpdev->hw_ops->unmap(vpdev, vdev->vr[index]);
- return ERR_PTR(err);
-}
-
-static int vop_find_vqs(struct virtio_device *dev, unsigned nvqs,
- struct virtqueue *vqs[],
- vq_callback_t *callbacks[],
- const char * const names[], const bool *ctx,
- struct irq_affinity *desc)
-{
- struct _vop_vdev *vdev = to_vopvdev(dev);
- struct vop_device *vpdev = vdev->vpdev;
- struct mic_device_ctrl __iomem *dc = vdev->dc;
- int i, err, retry, queue_idx = 0;
-
- /* We must have this many virtqueues. */
- if (nvqs > ioread8(&vdev->desc->num_vq))
- return -ENOENT;
-
- for (i = 0; i < nvqs; ++i) {
- if (!names[i]) {
- vqs[i] = NULL;
- continue;
- }
-
- dev_dbg(_vop_dev(vdev), "%s: %d: %s\n",
- __func__, i, names[i]);
- vqs[i] = vop_find_vq(dev, queue_idx++, callbacks[i], names[i],
- ctx ? ctx[i] : false);
- if (IS_ERR(vqs[i])) {
- err = PTR_ERR(vqs[i]);
- goto error;
- }
- }
-
- iowrite8(1, &dc->used_address_updated);
- /*
- * Send an interrupt to the host to inform it that used
- * rings have been re-assigned.
- */
- vpdev->hw_ops->send_intr(vpdev, vdev->c2h_vdev_db);
- for (retry = 100; --retry;) {
- if (!ioread8(&dc->used_address_updated))
- break;
- msleep(100);
- }
-
- dev_dbg(_vop_dev(vdev), "%s: retry: %d\n", __func__, retry);
- if (!retry) {
- err = -ENODEV;
- goto error;
- }
-
- return 0;
-error:
- vop_del_vqs(dev);
- return err;
-}
-
-/*
- * The config ops structure as defined by virtio config
- */
-static const struct virtio_config_ops vop_vq_config_ops = {
- .get_features = vop_get_features,
- .finalize_features = vop_finalize_features,
- .get = vop_get,
- .set = vop_set,
- .get_status = vop_get_status,
- .set_status = vop_set_status,
- .reset = vop_reset,
- .find_vqs = vop_find_vqs,
- .del_vqs = vop_del_vqs,
-};
-
-static irqreturn_t vop_virtio_intr_handler(int irq, void *data)
-{
- struct _vop_vdev *vdev = data;
- struct vop_device *vpdev = vdev->vpdev;
- struct virtqueue *vq;
-
- vpdev->hw_ops->ack_interrupt(vpdev, vdev->h2c_vdev_db);
- list_for_each_entry(vq, &vdev->vdev.vqs, list)
- vring_interrupt(0, vq);
-
- return IRQ_HANDLED;
-}
-
-static void vop_virtio_release_dev(struct device *_d)
-{
- struct virtio_device *vdev =
- container_of(_d, struct virtio_device, dev);
- struct _vop_vdev *vop_vdev =
- container_of(vdev, struct _vop_vdev, vdev);
-
- kfree(vop_vdev);
-}
-
-/*
- * adds a new device and register it with virtio
- * appropriate drivers are loaded by the device model
- */
-static int _vop_add_device(struct mic_device_desc __iomem *d,
- unsigned int offset, struct vop_device *vpdev,
- int dnode)
-{
- struct _vop_vdev *vdev, *reg_dev = NULL;
- int ret;
- u8 type = ioread8(&d->type);
-
- vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
- if (!vdev)
- return -ENOMEM;
-
- vdev->vpdev = vpdev;
- vdev->vdev.dev.parent = &vpdev->dev;
- vdev->vdev.dev.release = vop_virtio_release_dev;
- vdev->vdev.id.device = type;
- vdev->vdev.config = &vop_vq_config_ops;
- vdev->desc = d;
- vdev->dc = (void __iomem *)d + _vop_aligned_desc_size(d);
- vdev->dnode = dnode;
- vdev->vdev.priv = (void *)(unsigned long)dnode;
- init_completion(&vdev->reset_done);
-
- vdev->h2c_vdev_db = vpdev->hw_ops->next_db(vpdev);
- vdev->virtio_cookie = vpdev->hw_ops->request_irq(vpdev,
- vop_virtio_intr_handler, "virtio intr",
- vdev, vdev->h2c_vdev_db);
- if (IS_ERR(vdev->virtio_cookie)) {
- ret = PTR_ERR(vdev->virtio_cookie);
- goto kfree;
- }
- iowrite8((u8)vdev->h2c_vdev_db, &vdev->dc->h2c_vdev_db);
- vdev->c2h_vdev_db = ioread8(&vdev->dc->c2h_vdev_db);
-
- ret = register_virtio_device(&vdev->vdev);
- reg_dev = vdev;
- if (ret) {
- dev_err(_vop_dev(vdev),
- "Failed to register vop device %u type %u\n",
- offset, type);
- goto free_irq;
- }
- writeq((unsigned long)vdev, &vdev->dc->vdev);
- dev_dbg(_vop_dev(vdev), "%s: registered vop device %u type %u vdev %p\n",
- __func__, offset, type, vdev);
-
- return 0;
-
-free_irq:
- vpdev->hw_ops->free_irq(vpdev, vdev->virtio_cookie, vdev);
-kfree:
- if (reg_dev)
- put_device(&vdev->vdev.dev);
- else
- kfree(vdev);
- return ret;
-}
-
-/*
- * match for a vop device with a specific desc pointer
- */
-static int vop_match_desc(struct device *dev, void *data)
-{
- struct virtio_device *_dev = dev_to_virtio(dev);
- struct _vop_vdev *vdev = to_vopvdev(_dev);
-
- return vdev->desc == (void __iomem *)data;
-}
-
-static struct _vop_vdev *vop_dc_to_vdev(struct mic_device_ctrl __iomem *dc)
-{
- return (struct _vop_vdev *)(unsigned long)readq(&dc->vdev);
-}
-
-static void _vop_handle_config_change(struct mic_device_desc __iomem *d,
- unsigned int offset,
- struct vop_device *vpdev)
-{
- struct mic_device_ctrl __iomem *dc
- = (void __iomem *)d + _vop_aligned_desc_size(d);
- struct _vop_vdev *vdev = vop_dc_to_vdev(dc);
-
- if (ioread8(&dc->config_change) != MIC_VIRTIO_PARAM_CONFIG_CHANGED)
- return;
-
- dev_dbg(&vpdev->dev, "%s %d\n", __func__, __LINE__);
- virtio_config_changed(&vdev->vdev);
- iowrite8(1, &dc->guest_ack);
-}
-
-/*
- * removes a virtio device if a hot remove event has been
- * requested by the host.
- */
-static int _vop_remove_device(struct mic_device_desc __iomem *d,
- unsigned int offset, struct vop_device *vpdev)
-{
- struct mic_device_ctrl __iomem *dc
- = (void __iomem *)d + _vop_aligned_desc_size(d);
- struct _vop_vdev *vdev = vop_dc_to_vdev(dc);
- u8 status;
- int ret = -1;
-
- if (ioread8(&dc->config_change) == MIC_VIRTIO_PARAM_DEV_REMOVE) {
- struct device *dev = get_device(&vdev->vdev.dev);
-
- dev_dbg(&vpdev->dev,
- "%s %d config_change %d type %d vdev %p\n",
- __func__, __LINE__,
- ioread8(&dc->config_change), ioread8(&d->type), vdev);
- status = ioread8(&d->status);
- reinit_completion(&vdev->reset_done);
- unregister_virtio_device(&vdev->vdev);
- vpdev->hw_ops->free_irq(vpdev, vdev->virtio_cookie, vdev);
- iowrite8(-1, &dc->h2c_vdev_db);
- if (status & VIRTIO_CONFIG_S_DRIVER_OK)
- wait_for_completion(&vdev->reset_done);
- put_device(dev);
- iowrite8(1, &dc->guest_ack);
- dev_dbg(&vpdev->dev, "%s %d guest_ack %d\n",
- __func__, __LINE__, ioread8(&dc->guest_ack));
- iowrite8(-1, &d->type);
- ret = 0;
- }
- return ret;
-}
-
-#define REMOVE_DEVICES true
-
-static void _vop_scan_devices(void __iomem *dp, struct vop_device *vpdev,
- bool remove, int dnode)
-{
- s8 type;
- unsigned int i;
- struct mic_device_desc __iomem *d;
- struct mic_device_ctrl __iomem *dc;
- struct device *dev;
-
- for (i = sizeof(struct mic_bootparam);
- i < MIC_DP_SIZE; i += _vop_total_desc_size(d)) {
- d = dp + i;
- dc = (void __iomem *)d + _vop_aligned_desc_size(d);
- /*
- * This read barrier is paired with the corresponding write
- * barrier on the host which is inserted before adding or
- * removing a virtio device descriptor, by updating the type.
- */
- rmb();
- type = ioread8(&d->type);
-
- /* end of list */
- if (type == 0)
- break;
-
- if (type == -1)
- continue;
-
- /* device already exists */
- dev = device_find_child(&vpdev->dev, (void __force *)d,
- vop_match_desc);
- if (dev) {
- if (remove)
- iowrite8(MIC_VIRTIO_PARAM_DEV_REMOVE,
- &dc->config_change);
- put_device(dev);
- _vop_handle_config_change(d, i, vpdev);
- _vop_remove_device(d, i, vpdev);
- if (remove) {
- iowrite8(0, &dc->config_change);
- iowrite8(0, &dc->guest_ack);
- }
- continue;
- }
-
- /* new device */
- dev_dbg(&vpdev->dev, "%s %d Adding new virtio device %p\n",
- __func__, __LINE__, d);
- if (!remove)
- _vop_add_device(d, i, vpdev, dnode);
- }
-}
-
-static void vop_scan_devices(struct vop_info *vi,
- struct vop_device *vpdev, bool remove)
-{
- void __iomem *dp = vpdev->hw_ops->get_remote_dp(vpdev);
-
- if (!dp)
- return;
- mutex_lock(&vi->vop_mutex);
- _vop_scan_devices(dp, vpdev, remove, vpdev->dnode);
- mutex_unlock(&vi->vop_mutex);
-}
-
-/*
- * vop_hotplug_device tries to find changes in the device page.
- */
-static void vop_hotplug_devices(struct work_struct *work)
-{
- struct vop_info *vi = container_of(work, struct vop_info,
- hotplug_work);
-
- vop_scan_devices(vi, vi->vpdev, !REMOVE_DEVICES);
-}
-
-/*
- * Interrupt handler for hot plug/config changes etc.
- */
-static irqreturn_t vop_extint_handler(int irq, void *data)
-{
- struct vop_info *vi = data;
- struct mic_bootparam __iomem *bp;
- struct vop_device *vpdev = vi->vpdev;
-
- bp = vpdev->hw_ops->get_remote_dp(vpdev);
- dev_dbg(&vpdev->dev, "%s %d hotplug work\n",
- __func__, __LINE__);
- vpdev->hw_ops->ack_interrupt(vpdev, ioread8(&bp->h2c_config_db));
- schedule_work(&vi->hotplug_work);
- return IRQ_HANDLED;
-}
-
-static int vop_driver_probe(struct vop_device *vpdev)
-{
- struct vop_info *vi;
- int rc;
-
- vi = kzalloc(sizeof(*vi), GFP_KERNEL);
- if (!vi) {
- rc = -ENOMEM;
- goto exit;
- }
- dev_set_drvdata(&vpdev->dev, vi);
- vi->vpdev = vpdev;
-
- mutex_init(&vi->vop_mutex);
- INIT_WORK(&vi->hotplug_work, vop_hotplug_devices);
- if (vpdev->dnode) {
- rc = vop_host_init(vi);
- if (rc < 0)
- goto free;
- } else {
- struct mic_bootparam __iomem *bootparam;
-
- vop_scan_devices(vi, vpdev, !REMOVE_DEVICES);
-
- vi->h2c_config_db = vpdev->hw_ops->next_db(vpdev);
- vi->cookie = vpdev->hw_ops->request_irq(vpdev,
- vop_extint_handler,
- "virtio_config_intr",
- vi, vi->h2c_config_db);
- if (IS_ERR(vi->cookie)) {
- rc = PTR_ERR(vi->cookie);
- goto free;
- }
- bootparam = vpdev->hw_ops->get_remote_dp(vpdev);
- iowrite8(vi->h2c_config_db, &bootparam->h2c_config_db);
- }
- vop_init_debugfs(vi);
- return 0;
-free:
- kfree(vi);
-exit:
- return rc;
-}
-
-static void vop_driver_remove(struct vop_device *vpdev)
-{
- struct vop_info *vi = dev_get_drvdata(&vpdev->dev);
-
- if (vpdev->dnode) {
- vop_host_uninit(vi);
- } else {
- struct mic_bootparam __iomem *bootparam =
- vpdev->hw_ops->get_remote_dp(vpdev);
- if (bootparam)
- iowrite8(-1, &bootparam->h2c_config_db);
- vpdev->hw_ops->free_irq(vpdev, vi->cookie, vi);
- flush_work(&vi->hotplug_work);
- vop_scan_devices(vi, vpdev, REMOVE_DEVICES);
- }
- vop_exit_debugfs(vi);
- kfree(vi);
-}
-
-static const struct vop_device_id id_table[] = {
- { VOP_DEV_TRNSP, VOP_DEV_ANY_ID },
- { 0 },
-};
-
-static struct vop_driver vop_driver = {
- .driver.name = KBUILD_MODNAME,
- .driver.owner = THIS_MODULE,
- .id_table = id_table,
- .probe = vop_driver_probe,
- .remove = vop_driver_remove,
-};
-
-module_vop_driver(vop_driver);
-
-MODULE_DEVICE_TABLE(mbus, id_table);
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) Virtio Over PCIe (VOP) driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/vop/vop_main.h b/drivers/misc/mic/vop/vop_main.h
deleted file mode 100644
index 2451d92..0000000
--- a/drivers/misc/mic/vop/vop_main.h
+++ /dev/null
@@ -1,158 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Intel Virtio Over PCIe (VOP) driver.
- */
-#ifndef _VOP_MAIN_H_
-#define _VOP_MAIN_H_
-
-#include <linux/vringh.h>
-#include <linux/virtio_config.h>
-#include <linux/virtio.h>
-#include <linux/miscdevice.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-
-#include "../bus/vop_bus.h"
-
-/*
- * Note on endianness.
- * 1. Host can be both BE or LE
- * 2. Guest/card is LE. Host uses le_to_cpu to access desc/avail
- * rings and ioreadXX/iowriteXX to access used ring.
- * 3. Device page exposed by host to guest contains LE values. Guest
- * accesses these using ioreadXX/iowriteXX etc. This way in general we
- * obey the virtio spec according to which guest works with native
- * endianness and host is aware of guest endianness and does all
- * required endianness conversion.
- * 4. Data provided from user space to guest (in ADD_DEVICE and
- * CONFIG_CHANGE ioctl's) is not interpreted by the driver and should be
- * in guest endianness.
- */
-
-/*
- * vop_info - Allocated per invocation of VOP probe
- *
- * @vpdev: VOP device
- * @hotplug_work: Handle virtio device creation, deletion and configuration
- * @cookie: Cookie received upon requesting a virtio configuration interrupt
- * @h2c_config_db: The doorbell used by the peer to indicate a config change
- * @vdev_list: List of "active" virtio devices injected in the peer node
- * @vop_mutex: Synchronize access to the device page as well as serialize
- * creation/deletion of virtio devices on the peer node
- * @dp: Peer device page information
- * @dbg: Debugfs entry
- * @dma_ch: The DMA channel used by this transport for data transfers.
- * @name: Name for this transport used in misc device creation.
- * @miscdev: The misc device registered.
- */
-struct vop_info {
- struct vop_device *vpdev;
- struct work_struct hotplug_work;
- struct mic_irq *cookie;
- int h2c_config_db;
- struct list_head vdev_list;
- struct mutex vop_mutex;
- void __iomem *dp;
- struct dentry *dbg;
- struct dma_chan *dma_ch;
- char name[16];
- struct miscdevice miscdev;
-};
-
-/**
- * struct vop_vringh - Virtio ring host information.
- *
- * @vring: The VOP vring used for setting up user space mappings.
- * @vrh: The host VRINGH used for accessing the card vrings.
- * @riov: The VRINGH read kernel IOV.
- * @wiov: The VRINGH write kernel IOV.
- * @head: The VRINGH head index address passed to vringh_getdesc_kern(..).
- * @vr_mutex: Mutex for synchronizing access to the VRING.
- * @buf: Temporary kernel buffer used to copy in/out data
- * from/to the card via DMA.
- * @buf_da: dma address of buf.
- * @vdev: Back pointer to VOP virtio device for vringh_notify(..).
- */
-struct vop_vringh {
- struct mic_vring vring;
- struct vringh vrh;
- struct vringh_kiov riov;
- struct vringh_kiov wiov;
- u16 head;
- struct mutex vr_mutex;
- void *buf;
- dma_addr_t buf_da;
- struct vop_vdev *vdev;
-};
-
-/**
- * struct vop_vdev - Host information for a card Virtio device.
- *
- * @virtio_id - Virtio device id.
- * @waitq - Waitqueue to allow ring3 apps to poll.
- * @vpdev - pointer to VOP bus device.
- * @poll_wake - Used for waking up threads blocked in poll.
- * @out_bytes - Debug stats for number of bytes copied from host to card.
- * @in_bytes - Debug stats for number of bytes copied from card to host.
- * @out_bytes_dma - Debug stats for number of bytes copied from host to card
- * using DMA.
- * @in_bytes_dma - Debug stats for number of bytes copied from card to host
- * using DMA.
- * @tx_len_unaligned - Debug stats for number of bytes copied to the card where
- * the transfer length did not have the required DMA alignment.
- * @tx_dst_unaligned - Debug stats for number of bytes copied where the
- * destination address on the card did not have the required DMA alignment.
- * @vvr - Store per VRING data structures.
- * @virtio_bh_work - Work struct used to schedule virtio bottom half handling.
- * @dd - Virtio device descriptor.
- * @dc - Virtio device control fields.
- * @list - List of Virtio devices.
- * @virtio_db - The doorbell used by the card to interrupt the host.
- * @virtio_cookie - The cookie returned while requesting interrupts.
- * @vi: Transport information.
- * @vdev_mutex: Mutex synchronizing virtio device injection,
- * removal and data transfers.
- * @destroy: Track if a virtio device is being destroyed.
- * @deleted: The virtio device has been deleted.
- */
-struct vop_vdev {
- int virtio_id;
- wait_queue_head_t waitq;
- struct vop_device *vpdev;
- int poll_wake;
- unsigned long out_bytes;
- unsigned long in_bytes;
- unsigned long out_bytes_dma;
- unsigned long in_bytes_dma;
- unsigned long tx_len_unaligned;
- unsigned long tx_dst_unaligned;
- unsigned long rx_dst_unaligned;
- struct vop_vringh vvr[MIC_MAX_VRINGS];
- struct work_struct virtio_bh_work;
- struct mic_device_desc *dd;
- struct mic_device_ctrl *dc;
- struct list_head list;
- int virtio_db;
- struct mic_irq *virtio_cookie;
- struct vop_info *vi;
- struct mutex vdev_mutex;
- struct completion destroy;
- bool deleted;
-};
-
-/* Helper API to check if a virtio device is running */
-static inline bool vop_vdevup(struct vop_vdev *vdev)
-{
- return !!vdev->dd->status;
-}
-
-void vop_init_debugfs(struct vop_info *vi);
-void vop_exit_debugfs(struct vop_info *vi);
-int vop_host_init(struct vop_info *vi);
-void vop_host_uninit(struct vop_info *vi);
-#endif
diff --git a/drivers/misc/mic/vop/vop_vringh.c b/drivers/misc/mic/vop/vop_vringh.c
deleted file mode 100644
index 7014ffe..0000000
--- a/drivers/misc/mic/vop/vop_vringh.c
+++ /dev/null
@@ -1,1166 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Intel Virtio Over PCIe (VOP) driver.
- */
-#include <linux/sched.h>
-#include <linux/poll.h>
-#include <linux/dma-mapping.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-
-#include <linux/mic_ioctl.h>
-#include "vop_main.h"
-
-/* Helper API to obtain the VOP PCIe device */
-static inline struct device *vop_dev(struct vop_vdev *vdev)
-{
- return vdev->vpdev->dev.parent;
-}
-
-/* Helper API to check if a virtio device is initialized */
-static inline int vop_vdev_inited(struct vop_vdev *vdev)
-{
- if (!vdev)
- return -EINVAL;
- /* Device has not been created yet */
- if (!vdev->dd || !vdev->dd->type) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, -EINVAL);
- return -EINVAL;
- }
- /* Device has been removed/deleted */
- if (vdev->dd->type == -1) {
- dev_dbg(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, -ENODEV);
- return -ENODEV;
- }
- return 0;
-}
-
-static void _vop_notify(struct vringh *vrh)
-{
- struct vop_vringh *vvrh = container_of(vrh, struct vop_vringh, vrh);
- struct vop_vdev *vdev = vvrh->vdev;
- struct vop_device *vpdev = vdev->vpdev;
- s8 db = vdev->dc->h2c_vdev_db;
-
- if (db != -1)
- vpdev->hw_ops->send_intr(vpdev, db);
-}
-
-static void vop_virtio_init_post(struct vop_vdev *vdev)
-{
- struct mic_vqconfig *vqconfig = mic_vq_config(vdev->dd);
- struct vop_device *vpdev = vdev->vpdev;
- int i, used_size;
-
- for (i = 0; i < vdev->dd->num_vq; i++) {
- used_size = PAGE_ALIGN(sizeof(u16) * 3 +
- sizeof(struct vring_used_elem) *
- le16_to_cpu(vqconfig->num));
- if (!le64_to_cpu(vqconfig[i].used_address)) {
- dev_warn(vop_dev(vdev), "used_address zero??\n");
- continue;
- }
- vdev->vvr[i].vrh.vring.used =
- (void __force *)vpdev->hw_ops->remap(
- vpdev,
- le64_to_cpu(vqconfig[i].used_address),
- used_size);
- }
-
- vdev->dc->used_address_updated = 0;
-
- dev_info(vop_dev(vdev), "%s: device type %d LINKUP\n",
- __func__, vdev->virtio_id);
-}
-
-static inline void vop_virtio_device_reset(struct vop_vdev *vdev)
-{
- int i;
-
- dev_dbg(vop_dev(vdev), "%s: status %d device type %d RESET\n",
- __func__, vdev->dd->status, vdev->virtio_id);
-
- for (i = 0; i < vdev->dd->num_vq; i++)
- /*
- * Avoid lockdep false positive. The + 1 is for the vop
- * mutex which is held in the reset devices code path.
- */
- mutex_lock_nested(&vdev->vvr[i].vr_mutex, i + 1);
-
- /* 0 status means "reset" */
- vdev->dd->status = 0;
- vdev->dc->vdev_reset = 0;
- vdev->dc->host_ack = 1;
-
- for (i = 0; i < vdev->dd->num_vq; i++) {
- struct vringh *vrh = &vdev->vvr[i].vrh;
-
- vdev->vvr[i].vring.info->avail_idx = 0;
- vrh->completed = 0;
- vrh->last_avail_idx = 0;
- vrh->last_used_idx = 0;
- }
-
- for (i = 0; i < vdev->dd->num_vq; i++)
- mutex_unlock(&vdev->vvr[i].vr_mutex);
-}
-
-static void vop_virtio_reset_devices(struct vop_info *vi)
-{
- struct list_head *pos, *tmp;
- struct vop_vdev *vdev;
-
- list_for_each_safe(pos, tmp, &vi->vdev_list) {
- vdev = list_entry(pos, struct vop_vdev, list);
- vop_virtio_device_reset(vdev);
- vdev->poll_wake = 1;
- wake_up(&vdev->waitq);
- }
-}
-
-static void vop_bh_handler(struct work_struct *work)
-{
- struct vop_vdev *vdev = container_of(work, struct vop_vdev,
- virtio_bh_work);
-
- if (vdev->dc->used_address_updated)
- vop_virtio_init_post(vdev);
-
- if (vdev->dc->vdev_reset)
- vop_virtio_device_reset(vdev);
-
- vdev->poll_wake = 1;
- wake_up(&vdev->waitq);
-}
-
-static irqreturn_t _vop_virtio_intr_handler(int irq, void *data)
-{
- struct vop_vdev *vdev = data;
- struct vop_device *vpdev = vdev->vpdev;
-
- vpdev->hw_ops->ack_interrupt(vpdev, vdev->virtio_db);
- schedule_work(&vdev->virtio_bh_work);
- return IRQ_HANDLED;
-}
-
-static int vop_virtio_config_change(struct vop_vdev *vdev, void *argp)
-{
- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wake);
- int ret = 0, retry, i;
- struct vop_device *vpdev = vdev->vpdev;
- struct vop_info *vi = dev_get_drvdata(&vpdev->dev);
- struct mic_bootparam *bootparam = vpdev->hw_ops->get_dp(vpdev);
- s8 db = bootparam->h2c_config_db;
-
- mutex_lock(&vi->vop_mutex);
- for (i = 0; i < vdev->dd->num_vq; i++)
- mutex_lock_nested(&vdev->vvr[i].vr_mutex, i + 1);
-
- if (db == -1 || vdev->dd->type == -1) {
- ret = -EIO;
- goto exit;
- }
-
- memcpy(mic_vq_configspace(vdev->dd), argp, vdev->dd->config_len);
- vdev->dc->config_change = MIC_VIRTIO_PARAM_CONFIG_CHANGED;
- vpdev->hw_ops->send_intr(vpdev, db);
-
- for (retry = 100; retry--;) {
- ret = wait_event_timeout(wake, vdev->dc->guest_ack,
- msecs_to_jiffies(100));
- if (ret)
- break;
- }
-
- dev_dbg(vop_dev(vdev),
- "%s %d retry: %d\n", __func__, __LINE__, retry);
- vdev->dc->config_change = 0;
- vdev->dc->guest_ack = 0;
-exit:
- for (i = 0; i < vdev->dd->num_vq; i++)
- mutex_unlock(&vdev->vvr[i].vr_mutex);
- mutex_unlock(&vi->vop_mutex);
- return ret;
-}
-
-static int vop_copy_dp_entry(struct vop_vdev *vdev,
- struct mic_device_desc *argp, __u8 *type,
- struct mic_device_desc **devpage)
-{
- struct vop_device *vpdev = vdev->vpdev;
- struct mic_device_desc *devp;
- struct mic_vqconfig *vqconfig;
- int ret = 0, i;
- bool slot_found = false;
-
- vqconfig = mic_vq_config(argp);
- for (i = 0; i < argp->num_vq; i++) {
- if (le16_to_cpu(vqconfig[i].num) > MIC_MAX_VRING_ENTRIES) {
- ret = -EINVAL;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- goto exit;
- }
- }
-
- /* Find the first free device page entry */
- for (i = sizeof(struct mic_bootparam);
- i < MIC_DP_SIZE - mic_total_desc_size(argp);
- i += mic_total_desc_size(devp)) {
- devp = vpdev->hw_ops->get_dp(vpdev) + i;
- if (devp->type == 0 || devp->type == -1) {
- slot_found = true;
- break;
- }
- }
- if (!slot_found) {
- ret = -EINVAL;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- goto exit;
- }
- /*
- * Save off the type before doing the memcpy. Type will be set in the
- * end after completing all initialization for the new device.
- */
- *type = argp->type;
- argp->type = 0;
- memcpy(devp, argp, mic_desc_size(argp));
-
- *devpage = devp;
-exit:
- return ret;
-}
-
-static void vop_init_device_ctrl(struct vop_vdev *vdev,
- struct mic_device_desc *devpage)
-{
- struct mic_device_ctrl *dc;
-
- dc = (void *)devpage + mic_aligned_desc_size(devpage);
-
- dc->config_change = 0;
- dc->guest_ack = 0;
- dc->vdev_reset = 0;
- dc->host_ack = 0;
- dc->used_address_updated = 0;
- dc->c2h_vdev_db = -1;
- dc->h2c_vdev_db = -1;
- vdev->dc = dc;
-}
-
-static int vop_virtio_add_device(struct vop_vdev *vdev,
- struct mic_device_desc *argp)
-{
- struct vop_info *vi = vdev->vi;
- struct vop_device *vpdev = vi->vpdev;
- struct mic_device_desc *dd = NULL;
- struct mic_vqconfig *vqconfig;
- int vr_size, i, j, ret;
- u8 type = 0;
- s8 db = -1;
- char irqname[16];
- struct mic_bootparam *bootparam;
- u16 num;
- dma_addr_t vr_addr;
-
- bootparam = vpdev->hw_ops->get_dp(vpdev);
- init_waitqueue_head(&vdev->waitq);
- INIT_LIST_HEAD(&vdev->list);
- vdev->vpdev = vpdev;
-
- ret = vop_copy_dp_entry(vdev, argp, &type, &dd);
- if (ret) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- return ret;
- }
-
- vop_init_device_ctrl(vdev, dd);
-
- vdev->dd = dd;
- vdev->virtio_id = type;
- vqconfig = mic_vq_config(dd);
- INIT_WORK(&vdev->virtio_bh_work, vop_bh_handler);
-
- for (i = 0; i < dd->num_vq; i++) {
- struct vop_vringh *vvr = &vdev->vvr[i];
- struct mic_vring *vr = &vdev->vvr[i].vring;
-
- num = le16_to_cpu(vqconfig[i].num);
- mutex_init(&vvr->vr_mutex);
- vr_size = PAGE_ALIGN(round_up(vring_size(num, MIC_VIRTIO_RING_ALIGN), 4) +
- sizeof(struct _mic_vring_info));
- vr->va = (void *)
- __get_free_pages(GFP_KERNEL | __GFP_ZERO,
- get_order(vr_size));
- if (!vr->va) {
- ret = -ENOMEM;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- goto err;
- }
- vr->len = vr_size;
- vr->info = vr->va + round_up(vring_size(num, MIC_VIRTIO_RING_ALIGN), 4);
- vr->info->magic = cpu_to_le32(MIC_MAGIC + vdev->virtio_id + i);
- vr_addr = dma_map_single(&vpdev->dev, vr->va, vr_size,
- DMA_BIDIRECTIONAL);
- if (dma_mapping_error(&vpdev->dev, vr_addr)) {
- free_pages((unsigned long)vr->va, get_order(vr_size));
- ret = -ENOMEM;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- goto err;
- }
- vqconfig[i].address = cpu_to_le64(vr_addr);
-
- vring_init(&vr->vr, num, vr->va, MIC_VIRTIO_RING_ALIGN);
- ret = vringh_init_kern(&vvr->vrh,
- *(u32 *)mic_vq_features(vdev->dd),
- num, false, vr->vr.desc, vr->vr.avail,
- vr->vr.used);
- if (ret) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- goto err;
- }
- vringh_kiov_init(&vvr->riov, NULL, 0);
- vringh_kiov_init(&vvr->wiov, NULL, 0);
- vvr->head = USHRT_MAX;
- vvr->vdev = vdev;
- vvr->vrh.notify = _vop_notify;
- dev_dbg(&vpdev->dev,
- "%s %d index %d va %p info %p vr_size 0x%x\n",
- __func__, __LINE__, i, vr->va, vr->info, vr_size);
- vvr->buf = (void *)__get_free_pages(GFP_KERNEL,
- get_order(VOP_INT_DMA_BUF_SIZE));
- vvr->buf_da = dma_map_single(&vpdev->dev,
- vvr->buf, VOP_INT_DMA_BUF_SIZE,
- DMA_BIDIRECTIONAL);
- }
-
- snprintf(irqname, sizeof(irqname), "vop%dvirtio%d", vpdev->index,
- vdev->virtio_id);
- vdev->virtio_db = vpdev->hw_ops->next_db(vpdev);
- vdev->virtio_cookie = vpdev->hw_ops->request_irq(vpdev,
- _vop_virtio_intr_handler, irqname, vdev,
- vdev->virtio_db);
- if (IS_ERR(vdev->virtio_cookie)) {
- ret = PTR_ERR(vdev->virtio_cookie);
- dev_dbg(&vpdev->dev, "request irq failed\n");
- goto err;
- }
-
- vdev->dc->c2h_vdev_db = vdev->virtio_db;
-
- /*
- * Order the type update with previous stores. This write barrier
- * is paired with the corresponding read barrier before the uncached
- * system memory read of the type, on the card while scanning the
- * device page.
- */
- smp_wmb();
- dd->type = type;
- argp->type = type;
-
- if (bootparam) {
- db = bootparam->h2c_config_db;
- if (db != -1)
- vpdev->hw_ops->send_intr(vpdev, db);
- }
- dev_dbg(&vpdev->dev, "Added virtio id %d db %d\n", dd->type, db);
- return 0;
-err:
- vqconfig = mic_vq_config(dd);
- for (j = 0; j < i; j++) {
- struct vop_vringh *vvr = &vdev->vvr[j];
-
- dma_unmap_single(&vpdev->dev, le64_to_cpu(vqconfig[j].address),
- vvr->vring.len, DMA_BIDIRECTIONAL);
- free_pages((unsigned long)vvr->vring.va,
- get_order(vvr->vring.len));
- }
- return ret;
-}
-
-static void vop_dev_remove(struct vop_info *pvi, struct mic_device_ctrl *devp,
- struct vop_device *vpdev)
-{
- struct mic_bootparam *bootparam = vpdev->hw_ops->get_dp(vpdev);
- s8 db;
- int ret, retry;
- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wake);
-
- devp->config_change = MIC_VIRTIO_PARAM_DEV_REMOVE;
- db = bootparam->h2c_config_db;
- if (db != -1)
- vpdev->hw_ops->send_intr(vpdev, db);
- else
- goto done;
- for (retry = 15; retry--;) {
- ret = wait_event_timeout(wake, devp->guest_ack,
- msecs_to_jiffies(1000));
- if (ret)
- break;
- }
-done:
- devp->config_change = 0;
- devp->guest_ack = 0;
-}
-
-static void vop_virtio_del_device(struct vop_vdev *vdev)
-{
- struct vop_info *vi = vdev->vi;
- struct vop_device *vpdev = vdev->vpdev;
- int i;
- struct mic_vqconfig *vqconfig;
- struct mic_bootparam *bootparam = vpdev->hw_ops->get_dp(vpdev);
-
- if (!bootparam)
- goto skip_hot_remove;
- vop_dev_remove(vi, vdev->dc, vpdev);
-skip_hot_remove:
- vpdev->hw_ops->free_irq(vpdev, vdev->virtio_cookie, vdev);
- flush_work(&vdev->virtio_bh_work);
- vqconfig = mic_vq_config(vdev->dd);
- for (i = 0; i < vdev->dd->num_vq; i++) {
- struct vop_vringh *vvr = &vdev->vvr[i];
-
- dma_unmap_single(&vpdev->dev,
- vvr->buf_da, VOP_INT_DMA_BUF_SIZE,
- DMA_BIDIRECTIONAL);
- free_pages((unsigned long)vvr->buf,
- get_order(VOP_INT_DMA_BUF_SIZE));
- vringh_kiov_cleanup(&vvr->riov);
- vringh_kiov_cleanup(&vvr->wiov);
- dma_unmap_single(&vpdev->dev, le64_to_cpu(vqconfig[i].address),
- vvr->vring.len, DMA_BIDIRECTIONAL);
- free_pages((unsigned long)vvr->vring.va,
- get_order(vvr->vring.len));
- }
- /*
- * Order the type update with previous stores. This write barrier
- * is paired with the corresponding read barrier before the uncached
- * system memory read of the type, on the card while scanning the
- * device page.
- */
- smp_wmb();
- vdev->dd->type = -1;
-}
-
-/*
- * vop_sync_dma - Wrapper for synchronous DMAs.
- *
- * @dev - The address of the pointer to the device instance used
- * for DMA registration.
- * @dst - destination DMA address.
- * @src - source DMA address.
- * @len - size of the transfer.
- *
- * Return DMA_SUCCESS on success
- */
-static int vop_sync_dma(struct vop_vdev *vdev, dma_addr_t dst, dma_addr_t src,
- size_t len)
-{
- int err = 0;
- struct dma_device *ddev;
- struct dma_async_tx_descriptor *tx;
- struct vop_info *vi = dev_get_drvdata(&vdev->vpdev->dev);
- struct dma_chan *vop_ch = vi->dma_ch;
-
- if (!vop_ch) {
- err = -EBUSY;
- goto error;
- }
- ddev = vop_ch->device;
- tx = ddev->device_prep_dma_memcpy(vop_ch, dst, src, len,
- DMA_PREP_FENCE);
- if (!tx) {
- err = -ENOMEM;
- goto error;
- } else {
- dma_cookie_t cookie;
-
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- err = -ENOMEM;
- goto error;
- }
- dma_async_issue_pending(vop_ch);
- err = dma_sync_wait(vop_ch, cookie);
- }
-error:
- if (err)
- dev_err(&vi->vpdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- return err;
-}
-
-#define VOP_USE_DMA true
-
-/*
- * Initiates the copies across the PCIe bus from card memory to a user
- * space buffer. When transfers are done using DMA, source/destination
- * addresses and transfer length must follow the alignment requirements of
- * the MIC DMA engine.
- */
-static int vop_virtio_copy_to_user(struct vop_vdev *vdev, void __user *ubuf,
- size_t len, u64 daddr, size_t dlen,
- int vr_idx)
-{
- struct vop_device *vpdev = vdev->vpdev;
- void __iomem *dbuf = vpdev->hw_ops->remap(vpdev, daddr, len);
- struct vop_vringh *vvr = &vdev->vvr[vr_idx];
- struct vop_info *vi = dev_get_drvdata(&vpdev->dev);
- size_t dma_alignment;
- bool x200;
- size_t dma_offset, partlen;
- int err;
-
- if (!VOP_USE_DMA || !vi->dma_ch) {
- if (copy_to_user(ubuf, (void __force *)dbuf, len)) {
- err = -EFAULT;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto err;
- }
- vdev->in_bytes += len;
- err = 0;
- goto err;
- }
-
- dma_alignment = 1 << vi->dma_ch->device->copy_align;
- x200 = is_dma_copy_aligned(vi->dma_ch->device, 1, 1, 1);
-
- dma_offset = daddr - round_down(daddr, dma_alignment);
- daddr -= dma_offset;
- len += dma_offset;
- /*
- * X100 uses DMA addresses as seen by the card so adding
- * the aperture base is not required for DMA. However x200
- * requires DMA addresses to be an offset into the bar so
- * add the aperture base for x200.
- */
- if (x200)
- daddr += vpdev->aper->pa;
- while (len) {
- partlen = min_t(size_t, len, VOP_INT_DMA_BUF_SIZE);
- err = vop_sync_dma(vdev, vvr->buf_da, daddr,
- ALIGN(partlen, dma_alignment));
- if (err) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto err;
- }
- if (copy_to_user(ubuf, vvr->buf + dma_offset,
- partlen - dma_offset)) {
- err = -EFAULT;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto err;
- }
- daddr += partlen;
- ubuf += partlen;
- dbuf += partlen;
- vdev->in_bytes_dma += partlen;
- vdev->in_bytes += partlen;
- len -= partlen;
- dma_offset = 0;
- }
- err = 0;
-err:
- vpdev->hw_ops->unmap(vpdev, dbuf);
- dev_dbg(vop_dev(vdev),
- "%s: ubuf %p dbuf %p len 0x%zx vr_idx 0x%x\n",
- __func__, ubuf, dbuf, len, vr_idx);
- return err;
-}
-
-/*
- * Initiates copies across the PCIe bus from a user space buffer to card
- * memory. When transfers are done using DMA, source/destination addresses
- * and transfer length must follow the alignment requirements of the MIC
- * DMA engine.
- */
-static int vop_virtio_copy_from_user(struct vop_vdev *vdev, void __user *ubuf,
- size_t len, u64 daddr, size_t dlen,
- int vr_idx)
-{
- struct vop_device *vpdev = vdev->vpdev;
- void __iomem *dbuf = vpdev->hw_ops->remap(vpdev, daddr, len);
- struct vop_vringh *vvr = &vdev->vvr[vr_idx];
- struct vop_info *vi = dev_get_drvdata(&vdev->vpdev->dev);
- size_t dma_alignment;
- bool x200;
- size_t partlen;
- bool dma = VOP_USE_DMA && vi->dma_ch;
- int err = 0;
- size_t offset = 0;
-
- if (dma) {
- dma_alignment = 1 << vi->dma_ch->device->copy_align;
- x200 = is_dma_copy_aligned(vi->dma_ch->device, 1, 1, 1);
-
- if (daddr & (dma_alignment - 1)) {
- vdev->tx_dst_unaligned += len;
- dma = false;
- } else if (ALIGN(len, dma_alignment) > dlen) {
- vdev->tx_len_unaligned += len;
- dma = false;
- }
- }
-
- if (!dma)
- goto memcpy;
-
- /*
- * X100 uses DMA addresses as seen by the card so adding
- * the aperture base is not required for DMA. However x200
- * requires DMA addresses to be an offset into the bar so
- * add the aperture base for x200.
- */
- if (x200)
- daddr += vpdev->aper->pa;
- while (len) {
- partlen = min_t(size_t, len, VOP_INT_DMA_BUF_SIZE);
-
- if (copy_from_user(vvr->buf, ubuf, partlen)) {
- err = -EFAULT;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto err;
- }
- err = vop_sync_dma(vdev, daddr, vvr->buf_da,
- ALIGN(partlen, dma_alignment));
- if (err) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto err;
- }
- daddr += partlen;
- ubuf += partlen;
- dbuf += partlen;
- vdev->out_bytes_dma += partlen;
- vdev->out_bytes += partlen;
- len -= partlen;
- }
-memcpy:
- /*
- * We are copying to IO below and should ideally use something
- * like copy_from_user_toio(..) if it existed.
- */
- while (len) {
- partlen = min_t(size_t, len, VOP_INT_DMA_BUF_SIZE);
-
- if (copy_from_user(vvr->buf, ubuf + offset, partlen)) {
- err = -EFAULT;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto err;
- }
- memcpy_toio(dbuf + offset, vvr->buf, partlen);
- offset += partlen;
- vdev->out_bytes += partlen;
- len -= partlen;
- }
- err = 0;
-err:
- vpdev->hw_ops->unmap(vpdev, dbuf);
- dev_dbg(vop_dev(vdev),
- "%s: ubuf %p dbuf %p len 0x%zx vr_idx 0x%x\n",
- __func__, ubuf, dbuf, len, vr_idx);
- return err;
-}
-
-#define MIC_VRINGH_READ true
-
-/* Determine the total number of bytes consumed in a VRINGH KIOV */
-static inline u32 vop_vringh_iov_consumed(struct vringh_kiov *iov)
-{
- int i;
- u32 total = iov->consumed;
-
- for (i = 0; i < iov->i; i++)
- total += iov->iov[i].iov_len;
- return total;
-}
-
-/*
- * Traverse the VRINGH KIOV and issue the APIs to trigger the copies.
- * This API is heavily based on the vringh_iov_xfer(..) implementation
- * in vringh.c. The reason we cannot reuse vringh_iov_pull_kern(..)
- * and vringh_iov_push_kern(..) directly is because there is no
- * way to override the VRINGH xfer(..) routines as of v3.10.
- */
-static int vop_vringh_copy(struct vop_vdev *vdev, struct vringh_kiov *iov,
- void __user *ubuf, size_t len, bool read, int vr_idx,
- size_t *out_len)
-{
- int ret = 0;
- size_t partlen, tot_len = 0;
-
- while (len && iov->i < iov->used) {
- struct kvec *kiov = &iov->iov[iov->i];
- unsigned long daddr = (unsigned long)kiov->iov_base;
-
- partlen = min(kiov->iov_len, len);
- if (read)
- ret = vop_virtio_copy_to_user(vdev, ubuf, partlen,
- daddr,
- kiov->iov_len,
- vr_idx);
- else
- ret = vop_virtio_copy_from_user(vdev, ubuf, partlen,
- daddr,
- kiov->iov_len,
- vr_idx);
- if (ret) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- break;
- }
- len -= partlen;
- ubuf += partlen;
- tot_len += partlen;
- iov->consumed += partlen;
- kiov->iov_len -= partlen;
- kiov->iov_base += partlen;
- if (!kiov->iov_len) {
- /* Fix up old iov element then increment. */
- kiov->iov_len = iov->consumed;
- kiov->iov_base -= iov->consumed;
-
- iov->consumed = 0;
- iov->i++;
- }
- }
- *out_len = tot_len;
- return ret;
-}
-
-/*
- * Use the standard VRINGH infrastructure in the kernel to fetch new
- * descriptors, initiate the copies and update the used ring.
- */
-static int _vop_virtio_copy(struct vop_vdev *vdev, struct mic_copy_desc *copy)
-{
- int ret = 0;
- u32 iovcnt = copy->iovcnt;
- struct iovec iov;
- struct iovec __user *u_iov = copy->iov;
- void __user *ubuf = NULL;
- struct vop_vringh *vvr = &vdev->vvr[copy->vr_idx];
- struct vringh_kiov *riov = &vvr->riov;
- struct vringh_kiov *wiov = &vvr->wiov;
- struct vringh *vrh = &vvr->vrh;
- u16 *head = &vvr->head;
- struct mic_vring *vr = &vvr->vring;
- size_t len = 0, out_len;
-
- copy->out_len = 0;
- /* Fetch a new IOVEC if all previous elements have been processed */
- if (riov->i == riov->used && wiov->i == wiov->used) {
- ret = vringh_getdesc_kern(vrh, riov, wiov,
- head, GFP_KERNEL);
- /* Check if there are available descriptors */
- if (ret <= 0)
- return ret;
- }
- while (iovcnt) {
- if (!len) {
- /* Copy over a new iovec from user space. */
- ret = copy_from_user(&iov, u_iov, sizeof(*u_iov));
- if (ret) {
- ret = -EINVAL;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- break;
- }
- len = iov.iov_len;
- ubuf = iov.iov_base;
- }
- /* Issue all the read descriptors first */
- ret = vop_vringh_copy(vdev, riov, ubuf, len,
- MIC_VRINGH_READ, copy->vr_idx, &out_len);
- if (ret) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- break;
- }
- len -= out_len;
- ubuf += out_len;
- copy->out_len += out_len;
- /* Issue the write descriptors next */
- ret = vop_vringh_copy(vdev, wiov, ubuf, len,
- !MIC_VRINGH_READ, copy->vr_idx, &out_len);
- if (ret) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- break;
- }
- len -= out_len;
- ubuf += out_len;
- copy->out_len += out_len;
- if (!len) {
- /* One user space iovec is now completed */
- iovcnt--;
- u_iov++;
- }
- /* Exit loop if all elements in KIOVs have been processed. */
- if (riov->i == riov->used && wiov->i == wiov->used)
- break;
- }
- /*
- * Update the used ring if a descriptor was available and some data was
- * copied in/out and the user asked for a used ring update.
- */
- if (*head != USHRT_MAX && copy->out_len && copy->update_used) {
- u32 total = 0;
-
- /* Determine the total data consumed */
- total += vop_vringh_iov_consumed(riov);
- total += vop_vringh_iov_consumed(wiov);
- vringh_complete_kern(vrh, *head, total);
- *head = USHRT_MAX;
- if (vringh_need_notify_kern(vrh) > 0)
- vringh_notify(vrh);
- vringh_kiov_cleanup(riov);
- vringh_kiov_cleanup(wiov);
- /* Update avail idx for user space */
- vr->info->avail_idx = vrh->last_avail_idx;
- }
- return ret;
-}
-
-static inline int vop_verify_copy_args(struct vop_vdev *vdev,
- struct mic_copy_desc *copy)
-{
- if (!vdev || copy->vr_idx >= vdev->dd->num_vq)
- return -EINVAL;
- return 0;
-}
-
-/* Copy a specified number of virtio descriptors in a chain */
-static int vop_virtio_copy_desc(struct vop_vdev *vdev,
- struct mic_copy_desc *copy)
-{
- int err;
- struct vop_vringh *vvr;
-
- err = vop_verify_copy_args(vdev, copy);
- if (err)
- return err;
-
- vvr = &vdev->vvr[copy->vr_idx];
- mutex_lock(&vvr->vr_mutex);
- if (!vop_vdevup(vdev)) {
- err = -ENODEV;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto err;
- }
- err = _vop_virtio_copy(vdev, copy);
- if (err) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- }
-err:
- mutex_unlock(&vvr->vr_mutex);
- return err;
-}
-
-static int vop_open(struct inode *inode, struct file *f)
-{
- struct vop_vdev *vdev;
- struct vop_info *vi = container_of(f->private_data,
- struct vop_info, miscdev);
-
- vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
- if (!vdev)
- return -ENOMEM;
- vdev->vi = vi;
- mutex_init(&vdev->vdev_mutex);
- f->private_data = vdev;
- init_completion(&vdev->destroy);
- complete(&vdev->destroy);
- return 0;
-}
-
-static int vop_release(struct inode *inode, struct file *f)
-{
- struct vop_vdev *vdev = f->private_data, *vdev_tmp;
- struct vop_info *vi = vdev->vi;
- struct list_head *pos, *tmp;
- bool found = false;
-
- mutex_lock(&vdev->vdev_mutex);
- if (vdev->deleted)
- goto unlock;
- mutex_lock(&vi->vop_mutex);
- list_for_each_safe(pos, tmp, &vi->vdev_list) {
- vdev_tmp = list_entry(pos, struct vop_vdev, list);
- if (vdev == vdev_tmp) {
- vop_virtio_del_device(vdev);
- list_del(pos);
- found = true;
- break;
- }
- }
- mutex_unlock(&vi->vop_mutex);
-unlock:
- mutex_unlock(&vdev->vdev_mutex);
- if (!found)
- wait_for_completion(&vdev->destroy);
- f->private_data = NULL;
- kfree(vdev);
- return 0;
-}
-
-static long vop_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
-{
- struct vop_vdev *vdev = f->private_data;
- struct vop_info *vi = vdev->vi;
- void __user *argp = (void __user *)arg;
- int ret;
-
- switch (cmd) {
- case MIC_VIRTIO_ADD_DEVICE:
- {
- struct mic_device_desc dd, *dd_config;
-
- if (copy_from_user(&dd, argp, sizeof(dd)))
- return -EFAULT;
-
- if (mic_aligned_desc_size(&dd) > MIC_MAX_DESC_BLK_SIZE ||
- dd.num_vq > MIC_MAX_VRINGS)
- return -EINVAL;
-
- dd_config = memdup_user(argp, mic_desc_size(&dd));
- if (IS_ERR(dd_config))
- return PTR_ERR(dd_config);
-
- /* Ensure desc has not changed between the two reads */
- if (memcmp(&dd, dd_config, sizeof(dd))) {
- ret = -EINVAL;
- goto free_ret;
- }
- mutex_lock(&vdev->vdev_mutex);
- mutex_lock(&vi->vop_mutex);
- ret = vop_virtio_add_device(vdev, dd_config);
- if (ret)
- goto unlock_ret;
- list_add_tail(&vdev->list, &vi->vdev_list);
-unlock_ret:
- mutex_unlock(&vi->vop_mutex);
- mutex_unlock(&vdev->vdev_mutex);
-free_ret:
- kfree(dd_config);
- return ret;
- }
- case MIC_VIRTIO_COPY_DESC:
- {
- struct mic_copy_desc copy;
-
- mutex_lock(&vdev->vdev_mutex);
- ret = vop_vdev_inited(vdev);
- if (ret)
- goto _unlock_ret;
-
- if (copy_from_user(©, argp, sizeof(copy))) {
- ret = -EFAULT;
- goto _unlock_ret;
- }
-
- ret = vop_virtio_copy_desc(vdev, ©);
- if (ret < 0)
- goto _unlock_ret;
- if (copy_to_user(
- &((struct mic_copy_desc __user *)argp)->out_len,
- ©.out_len, sizeof(copy.out_len)))
- ret = -EFAULT;
-_unlock_ret:
- mutex_unlock(&vdev->vdev_mutex);
- return ret;
- }
- case MIC_VIRTIO_CONFIG_CHANGE:
- {
- void *buf;
-
- mutex_lock(&vdev->vdev_mutex);
- ret = vop_vdev_inited(vdev);
- if (ret)
- goto __unlock_ret;
- buf = memdup_user(argp, vdev->dd->config_len);
- if (IS_ERR(buf)) {
- ret = PTR_ERR(buf);
- goto __unlock_ret;
- }
- ret = vop_virtio_config_change(vdev, buf);
- kfree(buf);
-__unlock_ret:
- mutex_unlock(&vdev->vdev_mutex);
- return ret;
- }
- default:
- return -ENOIOCTLCMD;
- };
- return 0;
-}
-
-/*
- * We return EPOLLIN | EPOLLOUT from poll when new buffers are enqueued, and
- * not when previously enqueued buffers may be available. This means that
- * in the card->host (TX) path, when userspace is unblocked by poll it
- * must drain all available descriptors or it can stall.
- */
-static __poll_t vop_poll(struct file *f, poll_table *wait)
-{
- struct vop_vdev *vdev = f->private_data;
- __poll_t mask = 0;
-
- mutex_lock(&vdev->vdev_mutex);
- if (vop_vdev_inited(vdev)) {
- mask = EPOLLERR;
- goto done;
- }
- poll_wait(f, &vdev->waitq, wait);
- if (vop_vdev_inited(vdev)) {
- mask = EPOLLERR;
- } else if (vdev->poll_wake) {
- vdev->poll_wake = 0;
- mask = EPOLLIN | EPOLLOUT;
- }
-done:
- mutex_unlock(&vdev->vdev_mutex);
- return mask;
-}
-
-static inline int
-vop_query_offset(struct vop_vdev *vdev, unsigned long offset,
- unsigned long *size, unsigned long *pa)
-{
- struct vop_device *vpdev = vdev->vpdev;
- unsigned long start = MIC_DP_SIZE;
- int i;
-
- /*
- * MMAP interface is as follows:
- * offset region
- * 0x0 virtio device_page
- * 0x1000 first vring
- * 0x1000 + size of 1st vring second vring
- * ....
- */
- if (!offset) {
- *pa = virt_to_phys(vpdev->hw_ops->get_dp(vpdev));
- *size = MIC_DP_SIZE;
- return 0;
- }
-
- for (i = 0; i < vdev->dd->num_vq; i++) {
- struct vop_vringh *vvr = &vdev->vvr[i];
-
- if (offset == start) {
- *pa = virt_to_phys(vvr->vring.va);
- *size = vvr->vring.len;
- return 0;
- }
- start += vvr->vring.len;
- }
- return -1;
-}
-
-/*
- * Maps the device page and virtio rings to user space for readonly access.
- */
-static int vop_mmap(struct file *f, struct vm_area_struct *vma)
-{
- struct vop_vdev *vdev = f->private_data;
- unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
- unsigned long pa, size = vma->vm_end - vma->vm_start, size_rem = size;
- int i, err;
-
- err = vop_vdev_inited(vdev);
- if (err)
- goto ret;
- if (vma->vm_flags & VM_WRITE) {
- err = -EACCES;
- goto ret;
- }
- while (size_rem) {
- i = vop_query_offset(vdev, offset, &size, &pa);
- if (i < 0) {
- err = -EINVAL;
- goto ret;
- }
- err = remap_pfn_range(vma, vma->vm_start + offset,
- pa >> PAGE_SHIFT, size,
- vma->vm_page_prot);
- if (err)
- goto ret;
- size_rem -= size;
- offset += size;
- }
-ret:
- return err;
-}
-
-static const struct file_operations vop_fops = {
- .open = vop_open,
- .release = vop_release,
- .unlocked_ioctl = vop_ioctl,
- .poll = vop_poll,
- .mmap = vop_mmap,
- .owner = THIS_MODULE,
-};
-
-int vop_host_init(struct vop_info *vi)
-{
- int rc;
- struct miscdevice *mdev;
- struct vop_device *vpdev = vi->vpdev;
-
- INIT_LIST_HEAD(&vi->vdev_list);
- vi->dma_ch = vpdev->dma_ch;
- mdev = &vi->miscdev;
- mdev->minor = MISC_DYNAMIC_MINOR;
- snprintf(vi->name, sizeof(vi->name), "vop_virtio%d", vpdev->index);
- mdev->name = vi->name;
- mdev->fops = &vop_fops;
- mdev->parent = &vpdev->dev;
-
- rc = misc_register(mdev);
- if (rc)
- dev_err(&vpdev->dev, "%s failed rc %d\n", __func__, rc);
- return rc;
-}
-
-void vop_host_uninit(struct vop_info *vi)
-{
- struct list_head *pos, *tmp;
- struct vop_vdev *vdev;
-
- mutex_lock(&vi->vop_mutex);
- vop_virtio_reset_devices(vi);
- list_for_each_safe(pos, tmp, &vi->vdev_list) {
- vdev = list_entry(pos, struct vop_vdev, list);
- list_del(pos);
- reinit_completion(&vdev->destroy);
- mutex_unlock(&vi->vop_mutex);
- mutex_lock(&vdev->vdev_mutex);
- vop_virtio_del_device(vdev);
- vdev->deleted = true;
- mutex_unlock(&vdev->vdev_mutex);
- complete(&vdev->destroy);
- mutex_lock(&vi->vop_mutex);
- }
- mutex_unlock(&vi->vop_mutex);
- misc_deregister(&vi->miscdev);
-}
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index 4143141..acb9c81 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -572,17 +572,6 @@
TMIO_MASK_INIT_RCAR2);
}
-/*
- * This is a temporary workaround! This driver used 'hw_reset' wrongly and the
- * fix for that showed a regression. So, we mimic the old behaviour until the
- * proper solution is found.
- */
-static void renesas_sdhi_hw_reset(struct mmc_host *mmc)
-{
- struct tmio_mmc_host *host = mmc_priv(mmc);
- renesas_sdhi_reset(host);
-}
-
#define SH_MOBILE_SDHI_MIN_TAP_ROW 3
static int renesas_sdhi_select_tuning(struct tmio_mmc_host *host)
@@ -1020,8 +1009,6 @@
if (of_data && of_data->scc_offset) {
priv->scc_ctl = host->ctl + of_data->scc_offset;
host->reset = renesas_sdhi_reset;
- host->ops.hw_reset = renesas_sdhi_hw_reset;
- host->mmc->caps |= MMC_CAP_HW_RESET;
}
}
@@ -1160,6 +1147,7 @@
tmio_mmc_host_remove(host);
renesas_sdhi_clk_disable(host);
+ tmio_mmc_host_free(host);
return 0;
}
diff --git a/drivers/mmc/host/sdhci-esdhc.h b/drivers/mmc/host/sdhci-esdhc.h
index a30796e..6de02f0 100644
--- a/drivers/mmc/host/sdhci-esdhc.h
+++ b/drivers/mmc/host/sdhci-esdhc.h
@@ -5,6 +5,7 @@
* Copyright (c) 2007 Freescale Semiconductor, Inc.
* Copyright (c) 2009 MontaVista Software, Inc.
* Copyright (c) 2010 Pengutronix e.K.
+ * Copyright 2020 NXP
* Author: Wolfram Sang <kernel@pengutronix.de>
*/
@@ -88,6 +89,7 @@
/* DLL Config 0 Register */
#define ESDHC_DLLCFG0 0x160
#define ESDHC_DLL_ENABLE 0x80000000
+#define ESDHC_DLL_RESET 0x40000000
#define ESDHC_DLL_FREQ_SEL 0x08000000
/* DLL Config 1 Register */
diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c
index 829ccef..d25a4b5 100644
--- a/drivers/mmc/host/sdhci-of-arasan.c
+++ b/drivers/mmc/host/sdhci-of-arasan.c
@@ -30,7 +30,10 @@
#define SDHCI_ARASAN_VENDOR_REGISTER 0x78
#define SDHCI_ARASAN_ITAPDLY_REGISTER 0xF0F8
+#define SDHCI_ARASAN_ITAPDLY_SEL_MASK 0xFF
+
#define SDHCI_ARASAN_OTAPDLY_REGISTER 0xF0FC
+#define SDHCI_ARASAN_OTAPDLY_SEL_MASK 0x3F
#define SDHCI_ARASAN_CQE_BASE_ADDR 0x200
#define VENDOR_ENHANCED_STROBE BIT(0)
@@ -600,14 +603,8 @@
u8 tap_delay, tap_max = 0;
int ret;
- /*
- * This is applicable for SDHCI_SPEC_300 and above
- * ZynqMP does not set phase for <=25MHz clock.
- * If degrees is zero, no need to do anything.
- */
- if (host->version < SDHCI_SPEC_300 ||
- host->timing == MMC_TIMING_LEGACY ||
- host->timing == MMC_TIMING_UHS_SDR12 || !degrees)
+ /* This is applicable for SDHCI_SPEC_300 and above */
+ if (host->version < SDHCI_SPEC_300)
return 0;
switch (host->timing) {
@@ -638,6 +635,9 @@
if (ret)
pr_err("Error setting Output Tap Delay\n");
+ /* Release DLL Reset */
+ zynqmp_pm_sd_dll_reset(node_id, PM_DLL_RESET_RELEASE);
+
return ret;
}
@@ -668,16 +668,13 @@
u8 tap_delay, tap_max = 0;
int ret;
- /*
- * This is applicable for SDHCI_SPEC_300 and above
- * ZynqMP does not set phase for <=25MHz clock.
- * If degrees is zero, no need to do anything.
- */
- if (host->version < SDHCI_SPEC_300 ||
- host->timing == MMC_TIMING_LEGACY ||
- host->timing == MMC_TIMING_UHS_SDR12 || !degrees)
+ /* This is applicable for SDHCI_SPEC_300 and above */
+ if (host->version < SDHCI_SPEC_300)
return 0;
+ /* Assert DLL Reset */
+ zynqmp_pm_sd_dll_reset(node_id, PM_DLL_RESET_ASSERT);
+
switch (host->timing) {
case MMC_TIMING_MMC_HS:
case MMC_TIMING_SD_HS:
@@ -733,14 +730,8 @@
struct sdhci_host *host = sdhci_arasan->host;
u8 tap_delay, tap_max = 0;
- /*
- * This is applicable for SDHCI_SPEC_300 and above
- * Versal does not set phase for <=25MHz clock.
- * If degrees is zero, no need to do anything.
- */
- if (host->version < SDHCI_SPEC_300 ||
- host->timing == MMC_TIMING_LEGACY ||
- host->timing == MMC_TIMING_UHS_SDR12 || !degrees)
+ /* This is applicable for SDHCI_SPEC_300 and above */
+ if (host->version < SDHCI_SPEC_300)
return 0;
switch (host->timing) {
@@ -773,6 +764,7 @@
regval = sdhci_readl(host, SDHCI_ARASAN_OTAPDLY_REGISTER);
regval |= SDHCI_OTAPDLY_ENABLE;
sdhci_writel(host, regval, SDHCI_ARASAN_OTAPDLY_REGISTER);
+ regval &= ~SDHCI_ARASAN_OTAPDLY_SEL_MASK;
regval |= tap_delay;
sdhci_writel(host, regval, SDHCI_ARASAN_OTAPDLY_REGISTER);
}
@@ -804,14 +796,8 @@
struct sdhci_host *host = sdhci_arasan->host;
u8 tap_delay, tap_max = 0;
- /*
- * This is applicable for SDHCI_SPEC_300 and above
- * Versal does not set phase for <=25MHz clock.
- * If degrees is zero, no need to do anything.
- */
- if (host->version < SDHCI_SPEC_300 ||
- host->timing == MMC_TIMING_LEGACY ||
- host->timing == MMC_TIMING_UHS_SDR12 || !degrees)
+ /* This is applicable for SDHCI_SPEC_300 and above */
+ if (host->version < SDHCI_SPEC_300)
return 0;
switch (host->timing) {
@@ -846,6 +832,7 @@
sdhci_writel(host, regval, SDHCI_ARASAN_ITAPDLY_REGISTER);
regval |= SDHCI_ITAPDLY_ENABLE;
sdhci_writel(host, regval, SDHCI_ARASAN_ITAPDLY_REGISTER);
+ regval &= ~SDHCI_ARASAN_ITAPDLY_SEL_MASK;
regval |= tap_delay;
sdhci_writel(host, regval, SDHCI_ARASAN_ITAPDLY_REGISTER);
regval &= ~SDHCI_ITAPDLY_CHGWIN;
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 0b45eff..ab5ab96 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -4,6 +4,7 @@
*
* Copyright (c) 2007, 2010, 2012 Freescale Semiconductor, Inc.
* Copyright (c) 2009 MontaVista Software, Inc.
+ * Copyright 2020 NXP
*
* Authors: Xiaobo Xie <X.Xie@freescale.com>
* Anton Vorontsov <avorontsov@ru.mvista.com>
@@ -19,6 +20,7 @@
#include <linux/clk.h>
#include <linux/ktime.h>
#include <linux/dma-mapping.h>
+#include <linux/iopoll.h>
#include <linux/mmc/host.h>
#include <linux/mmc/mmc.h>
#include "sdhci-pltfm.h"
@@ -743,6 +745,21 @@
if (host->mmc->actual_clock == MMC_HS200_MAX_DTR)
temp |= ESDHC_DLL_FREQ_SEL;
sdhci_writel(host, temp, ESDHC_DLLCFG0);
+
+ temp |= ESDHC_DLL_RESET;
+ sdhci_writel(host, temp, ESDHC_DLLCFG0);
+ udelay(1);
+ temp &= ~ESDHC_DLL_RESET;
+ sdhci_writel(host, temp, ESDHC_DLLCFG0);
+
+ /* Wait max 20 ms */
+ if (read_poll_timeout(sdhci_readl, temp,
+ temp & ESDHC_DLL_STS_SLV_LOCK,
+ 10, 20000, false,
+ host, ESDHC_DLLSTAT0))
+ pr_err("%s: timeout for delay chain lock.\n",
+ mmc_hostname(host->mmc));
+
temp = sdhci_readl(host, ESDHC_TBCTL);
sdhci_writel(host, temp | ESDHC_HS400_WNDW_ADJUST, ESDHC_TBCTL);
@@ -1052,6 +1069,17 @@
esdhc_tuning_block_enable(host, true);
+ /*
+ * The eSDHC controller takes the data timeout value into account
+ * during tuning. If the SD card is too slow sending the response, the
+ * timer will expire and a "Buffer Read Ready" interrupt without data
+ * is triggered. This leads to tuning errors.
+ *
+ * Just set the timeout to the maximum value because the core will
+ * already take care of it in sdhci_send_tuning().
+ */
+ sdhci_writeb(host, 0xe, SDHCI_TIMEOUT_CONTROL);
+
hs400_tuning = host->flags & SDHCI_HS400_TUNING;
do {
@@ -1296,6 +1324,8 @@
static struct soc_device_attribute soc_unreliable_pulse_detection[] = {
{ .family = "QorIQ LX2160A", .revision = "1.0", },
+ { .family = "QorIQ LX2160A", .revision = "2.0", },
+ { .family = "QorIQ LS1028A", .revision = "1.0", },
{ },
};
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 23da7f7..9552708 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -665,6 +665,15 @@
}
}
+static void sdhci_intel_set_uhs_signaling(struct sdhci_host *host,
+ unsigned int timing)
+{
+ /* Set UHS timing to SDR25 for High Speed mode */
+ if (timing == MMC_TIMING_MMC_HS || timing == MMC_TIMING_SD_HS)
+ timing = MMC_TIMING_UHS_SDR25;
+ sdhci_set_uhs_signaling(host, timing);
+}
+
#define INTEL_HS400_ES_REG 0x78
#define INTEL_HS400_ES_BIT BIT(0)
@@ -721,7 +730,7 @@
.enable_dma = sdhci_pci_enable_dma,
.set_bus_width = sdhci_set_bus_width,
.reset = sdhci_reset,
- .set_uhs_signaling = sdhci_set_uhs_signaling,
+ .set_uhs_signaling = sdhci_intel_set_uhs_signaling,
.hw_reset = sdhci_pci_hw_reset,
};
@@ -731,7 +740,7 @@
.enable_dma = sdhci_pci_enable_dma,
.set_bus_width = sdhci_set_bus_width,
.reset = sdhci_cqhci_reset,
- .set_uhs_signaling = sdhci_set_uhs_signaling,
+ .set_uhs_signaling = sdhci_intel_set_uhs_signaling,
.hw_reset = sdhci_pci_hw_reset,
.irq = sdhci_cqhci_irq,
};
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 592a55a..3561ae8 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1384,9 +1384,11 @@
/*
* In case of Version 4.10 or later, use of 'Auto CMD Auto
* Select' is recommended rather than use of 'Auto CMD12
- * Enable' or 'Auto CMD23 Enable'.
+ * Enable' or 'Auto CMD23 Enable'. We require Version 4 Mode
+ * here because some controllers (e.g sdhci-of-dwmshc) expect it.
*/
- if (host->version >= SDHCI_SPEC_410 && (use_cmd12 || use_cmd23)) {
+ if (host->version >= SDHCI_SPEC_410 && host->v4_mode &&
+ (use_cmd12 || use_cmd23)) {
*mode |= SDHCI_TRNS_AUTO_SEL;
ctrl2 = sdhci_readw(host, SDHCI_HOST_CONTROL2);
diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c
index 2fce051..cb4149f 100644
--- a/drivers/mmc/host/tmio_mmc_core.c
+++ b/drivers/mmc/host/tmio_mmc_core.c
@@ -175,6 +175,8 @@
if (host->reset)
host->reset(host);
+ tmio_mmc_abort_dma(host);
+
if (host->pdata->flags & TMIO_MMC_SDIO_IRQ) {
sd_ctrl_write16(host, CTL_SDIO_IRQ_MASK, host->sdio_irq_mask);
sd_ctrl_write16(host, CTL_TRANSACTION_CTL, 0x0001);
@@ -223,8 +225,6 @@
/* Ready for new calls */
host->mrq = NULL;
-
- tmio_mmc_abort_dma(host);
mmc_request_done(host->mmc, mrq);
}
@@ -927,6 +927,9 @@
switch (ios->power_mode) {
case MMC_POWER_OFF:
tmio_mmc_power_off(host);
+ /* Downgrade ensures a sane state for tuning HW (e.g. SCC) */
+ if (host->mmc->ops->hs400_downgrade)
+ host->mmc->ops->hs400_downgrade(host->mmc);
host->set_clock(host, 0);
break;
case MMC_POWER_UP:
diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c
index 0e7a9b6..e345f9d 100644
--- a/drivers/mtd/nand/raw/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c
@@ -707,6 +707,30 @@
{
struct mtd_info *mtd = nand_to_mtd(chip);
struct fsl_ifc_mtd *priv = nand_get_controller_data(chip);
+ struct fsl_ifc_ctrl *ctrl = priv->ctrl;
+ struct fsl_ifc_global __iomem *ifc_global = ctrl->gregs;
+ u32 csor;
+
+ csor = ifc_in32(&ifc_global->csor_cs[priv->bank].csor);
+
+ /* Must also set CSOR_NAND_ECC_ENC_EN if DEC_EN set */
+ if (csor & CSOR_NAND_ECC_DEC_EN) {
+ chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
+ mtd_set_ooblayout(mtd, &fsl_ifc_ooblayout_ops);
+
+ /* Hardware generates ECC per 512 Bytes */
+ chip->ecc.size = 512;
+ if ((csor & CSOR_NAND_ECC_MODE_MASK) == CSOR_NAND_ECC_MODE_4) {
+ chip->ecc.bytes = 8;
+ chip->ecc.strength = 4;
+ } else {
+ chip->ecc.bytes = 16;
+ chip->ecc.strength = 8;
+ }
+ } else {
+ chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
+ chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
+ }
dev_dbg(priv->dev, "%s: nand->numchips = %d\n", __func__,
nanddev_ntargets(&chip->base));
@@ -910,25 +934,6 @@
return -ENODEV;
}
- /* Must also set CSOR_NAND_ECC_ENC_EN if DEC_EN set */
- if (csor & CSOR_NAND_ECC_DEC_EN) {
- chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
- mtd_set_ooblayout(mtd, &fsl_ifc_ooblayout_ops);
-
- /* Hardware generates ECC per 512 Bytes */
- chip->ecc.size = 512;
- if ((csor & CSOR_NAND_ECC_MODE_MASK) == CSOR_NAND_ECC_MODE_4) {
- chip->ecc.bytes = 8;
- chip->ecc.strength = 4;
- } else {
- chip->ecc.bytes = 16;
- chip->ecc.strength = 8;
- }
- } else {
- chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
- chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
- }
-
ret = fsl_ifc_sram_init(priv);
if (ret)
return ret;
diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c
index d4200eb..684c51e 100644
--- a/drivers/mtd/nand/raw/mxc_nand.c
+++ b/drivers/mtd/nand/raw/mxc_nand.c
@@ -1681,6 +1681,11 @@
struct mxc_nand_host *host = nand_get_controller_data(chip);
struct device *dev = mtd->dev.parent;
+ chip->ecc.bytes = host->devtype_data->eccbytes;
+ host->eccsize = host->devtype_data->eccsize;
+ chip->ecc.size = 512;
+ mtd_set_ooblayout(mtd, host->devtype_data->ooblayout);
+
switch (chip->ecc.engine_type) {
case NAND_ECC_ENGINE_TYPE_ON_HOST:
chip->ecc.read_page = mxc_nand_read_page;
@@ -1836,19 +1841,7 @@
if (host->devtype_data->axi_offset)
host->regs_axi = host->base + host->devtype_data->axi_offset;
- this->ecc.bytes = host->devtype_data->eccbytes;
- host->eccsize = host->devtype_data->eccsize;
-
this->legacy.select_chip = host->devtype_data->select_chip;
- this->ecc.size = 512;
- mtd_set_ooblayout(mtd, host->devtype_data->ooblayout);
-
- if (host->pdata.hw_ecc) {
- this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
- } else {
- this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
- this->ecc.algo = NAND_ECC_ALGO_HAMMING;
- }
/* NAND bus width determines access functions used by upper layer */
if (host->pdata.width == 2)
diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
index b31a581..550bda4 100644
--- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c
+++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
@@ -1708,6 +1708,13 @@
return -EINVAL;
}
+ /* Default ECC settings in case they are not set in the device tree */
+ if (!chip->ecc.size)
+ chip->ecc.size = FMC2_ECC_STEP_SIZE;
+
+ if (!chip->ecc.strength)
+ chip->ecc.strength = FMC2_ECC_BCH8;
+
ret = nand_ecc_choose_conf(chip, &stm32_fmc2_nfc_ecc_caps,
mtd->oobsize - FMC2_BBM_LEN);
if (ret) {
@@ -1727,8 +1734,7 @@
mtd_set_ooblayout(mtd, &stm32_fmc2_nfc_ooblayout_ops);
- if (chip->options & NAND_BUSWIDTH_16)
- stm32_fmc2_nfc_set_buswidth_16(nfc, true);
+ stm32_fmc2_nfc_setup(chip);
return 0;
}
@@ -1952,11 +1958,6 @@
chip->options |= NAND_BUSWIDTH_AUTO | NAND_NO_SUBPAGE_WRITE |
NAND_USES_DMA;
- /* Default ECC settings */
- chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
- chip->ecc.size = FMC2_ECC_STEP_SIZE;
- chip->ecc.strength = FMC2_ECC_BCH8;
-
/* Scan to find existence of the device */
ret = nand_scan(chip, nand->ncs);
if (ret)
diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c
index 0369d98..f0ae7a0 100644
--- a/drivers/mtd/spi-nor/core.c
+++ b/drivers/mtd/spi-nor/core.c
@@ -2701,11 +2701,10 @@
memcpy(&sfdp_params, nor->params, sizeof(sfdp_params));
- if (spi_nor_parse_sfdp(nor, &sfdp_params)) {
+ if (spi_nor_parse_sfdp(nor, nor->params)) {
+ memcpy(nor->params, &sfdp_params, sizeof(*nor->params));
nor->addr_width = 0;
nor->flags &= ~SNOR_F_4B_OPCODES;
- } else {
- memcpy(nor->params, &sfdp_params, sizeof(*nor->params));
}
}
@@ -3009,13 +3008,15 @@
/* already configured from SFDP */
} else if (nor->info->addr_width) {
nor->addr_width = nor->info->addr_width;
- } else if (nor->mtd.size > 0x1000000) {
- /* enable 4-byte addressing if the device exceeds 16MiB */
- nor->addr_width = 4;
} else {
nor->addr_width = 3;
}
+ if (nor->addr_width == 3 && nor->mtd.size > 0x1000000) {
+ /* enable 4-byte addressing if the device exceeds 16MiB */
+ nor->addr_width = 4;
+ }
+
if (nor->addr_width > SPI_NOR_MAX_ADDR_WIDTH) {
dev_dbg(nor->dev, "address width is too large: %u\n",
nor->addr_width);
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index b70ded3..81e39d7 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -512,9 +512,13 @@
*/
struct sk_buff *skb = priv->echo_skb[idx];
struct canfd_frame *cf = (struct canfd_frame *)skb->data;
- u8 len = cf->len;
- *len_ptr = len;
+ /* get the real payload length for netdev statistics */
+ if (cf->can_id & CAN_RTR_FLAG)
+ *len_ptr = 0;
+ else
+ *len_ptr = cf->len;
+
priv->echo_skb[idx] = NULL;
return skb;
@@ -538,7 +542,11 @@
if (!skb)
return 0;
- netif_rx(skb);
+ skb_get(skb);
+ if (netif_rx(skb) == NET_RX_SUCCESS)
+ dev_consume_skb_any(skb);
+ else
+ dev_kfree_skb_any(skb);
return len;
}
@@ -584,7 +592,7 @@
cf->can_id |= CAN_ERR_RESTARTED;
- netif_rx(skb);
+ netif_rx_ni(skb);
stats->rx_packets++;
stats->rx_bytes += cf->can_dlc;
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 4d594e9..99e5f27 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -217,7 +217,7 @@
* MX8MP FlexCAN3 03.00.17.01 yes yes no yes yes yes
* VF610 FlexCAN3 ? no yes no yes yes? no
* LS1021A FlexCAN2 03.00.04.00 no yes no no yes no
- * LX2160A FlexCAN3 03.00.23.00 no yes no no yes yes
+ * LX2160A FlexCAN3 03.00.23.00 no yes no yes yes yes
*
* Some SOCs do not have the RX_WARN & TX_WARN interrupt line connected.
*/
@@ -400,19 +400,19 @@
static const struct flexcan_devtype_data fsl_vf610_devtype_data = {
.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_OFF_TIMESTAMP |
- FLEXCAN_QUIRK_BROKEN_PERR_STATE,
+ FLEXCAN_QUIRK_BROKEN_PERR_STATE | FLEXCAN_QUIRK_SUPPORT_ECC,
};
static const struct flexcan_devtype_data fsl_ls1021a_r2_devtype_data = {
.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
- FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_BROKEN_PERR_STATE |
- FLEXCAN_QUIRK_USE_OFF_TIMESTAMP,
+ FLEXCAN_QUIRK_BROKEN_PERR_STATE | FLEXCAN_QUIRK_USE_OFF_TIMESTAMP,
};
static const struct flexcan_devtype_data fsl_lx2160a_r1_devtype_data = {
.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_BROKEN_PERR_STATE |
- FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | FLEXCAN_QUIRK_SUPPORT_FD,
+ FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | FLEXCAN_QUIRK_SUPPORT_FD |
+ FLEXCAN_QUIRK_SUPPORT_ECC,
};
static const struct can_bittiming_const flexcan_bittiming_const = {
@@ -728,8 +728,10 @@
int err;
err = pm_runtime_get_sync(priv->dev);
- if (err < 0)
+ if (err < 0) {
+ pm_runtime_put_noidle(priv->dev);
return err;
+ }
err = __flexcan_get_berr_counter(dev, bec);
@@ -1565,14 +1567,10 @@
priv->write(reg_ctrl2, ®s->ctrl2);
}
- err = flexcan_transceiver_enable(priv);
- if (err)
- goto out_chip_disable;
-
/* synchronize with the can bus */
err = flexcan_chip_unfreeze(priv);
if (err)
- goto out_transceiver_disable;
+ goto out_chip_disable;
priv->can.state = CAN_STATE_ERROR_ACTIVE;
@@ -1590,8 +1588,6 @@
return 0;
- out_transceiver_disable:
- flexcan_transceiver_disable(priv);
out_chip_disable:
flexcan_chip_disable(priv);
return err;
@@ -1621,7 +1617,6 @@
priv->write(priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_ALL,
®s->ctrl);
- flexcan_transceiver_disable(priv);
priv->can.state = CAN_STATE_STOPPED;
return 0;
@@ -1654,17 +1649,23 @@
}
err = pm_runtime_get_sync(priv->dev);
- if (err < 0)
+ if (err < 0) {
+ pm_runtime_put_noidle(priv->dev);
return err;
+ }
err = open_candev(dev);
if (err)
goto out_runtime_put;
- err = request_irq(dev->irq, flexcan_irq, IRQF_SHARED, dev->name, dev);
+ err = flexcan_transceiver_enable(priv);
if (err)
goto out_close;
+ err = request_irq(dev->irq, flexcan_irq, IRQF_SHARED, dev->name, dev);
+ if (err)
+ goto out_transceiver_disable;
+
if (priv->can.ctrlmode & CAN_CTRLMODE_FD)
priv->mb_size = sizeof(struct flexcan_mb) + CANFD_MAX_DLEN;
else
@@ -1716,6 +1717,8 @@
can_rx_offload_del(&priv->offload);
out_free_irq:
free_irq(dev->irq, dev);
+ out_transceiver_disable:
+ flexcan_transceiver_disable(priv);
out_close:
close_candev(dev);
out_runtime_put:
@@ -1734,6 +1737,7 @@
can_rx_offload_del(&priv->offload);
free_irq(dev->irq, dev);
+ flexcan_transceiver_disable(priv);
close_candev(dev);
pm_runtime_put(priv->dev);
@@ -1852,7 +1856,7 @@
return -EINVAL;
/* stop mode property format is:
- * <&gpr req_gpr>.
+ * <&gpr req_gpr req_bit>.
*/
ret = of_property_read_u32_array(np, "fsl,stop-mode", out_val,
ARRAY_SIZE(out_val));
@@ -2062,6 +2066,8 @@
{
struct net_device *dev = platform_get_drvdata(pdev);
+ device_set_wakeup_enable(&pdev->dev, false);
+ device_set_wakeup_capable(&pdev->dev, false);
unregister_flexcandev(dev);
pm_runtime_disable(&pdev->dev);
free_candev(dev);
diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index 6f76691..72acd1b 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -287,12 +287,12 @@
static const struct can_bittiming_const kvaser_pciefd_bittiming_const = {
.name = KVASER_PCIEFD_DRV_NAME,
.tseg1_min = 1,
- .tseg1_max = 255,
+ .tseg1_max = 512,
.tseg2_min = 1,
.tseg2_max = 32,
.sjw_max = 16,
.brp_min = 1,
- .brp_max = 4096,
+ .brp_max = 8192,
.brp_inc = 1,
};
diff --git a/drivers/net/can/m_can/Kconfig b/drivers/net/can/m_can/Kconfig
index 48be627..5f9f819 100644
--- a/drivers/net/can/m_can/Kconfig
+++ b/drivers/net/can/m_can/Kconfig
@@ -16,7 +16,8 @@
config CAN_M_CAN_TCAN4X5X
depends on CAN_M_CAN
- depends on REGMAP_SPI
+ depends on SPI
+ select REGMAP_SPI
tristate "TCAN4X5X M_CAN device"
help
Say Y here if you want support for Texas Instruments TCAN4x5x
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 02c5795..f3fc37e 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -665,7 +665,7 @@
unsigned int ecr;
switch (new_state) {
- case CAN_STATE_ERROR_ACTIVE:
+ case CAN_STATE_ERROR_WARNING:
/* error warning state */
cdev->can.can_stats.error_warning++;
cdev->can.state = CAN_STATE_ERROR_WARNING;
@@ -694,7 +694,7 @@
__m_can_get_berr_counter(dev, &bec);
switch (new_state) {
- case CAN_STATE_ERROR_ACTIVE:
+ case CAN_STATE_ERROR_WARNING:
/* error warning state */
cf->can_id |= CAN_ERR_CRTL;
cf->data[1] = (bec.txerr > bec.rxerr) ?
@@ -956,6 +956,8 @@
struct net_device_stats *stats = &dev->stats;
u32 ir;
+ if (pm_runtime_suspended(cdev->dev))
+ return IRQ_NONE;
ir = m_can_read(cdev, M_CAN_IR);
if (!ir)
return IRQ_NONE;
@@ -1414,6 +1416,9 @@
/* disable all interrupts */
m_can_disable_all_interrupts(cdev);
+ /* Set init mode to disengage from the network */
+ m_can_config_endisable(cdev, true);
+
/* set the state as STOPPED */
cdev->can.state = CAN_STATE_STOPPED;
}
@@ -1812,6 +1817,12 @@
}
EXPORT_SYMBOL_GPL(m_can_class_allocate_dev);
+void m_can_class_free_dev(struct net_device *net)
+{
+ free_candev(net);
+}
+EXPORT_SYMBOL_GPL(m_can_class_free_dev);
+
int m_can_class_register(struct m_can_classdev *m_can_dev)
{
int ret;
@@ -1850,7 +1861,6 @@
if (ret) {
if (m_can_dev->pm_clock_support)
pm_runtime_disable(m_can_dev->dev);
- free_candev(m_can_dev->net);
}
return ret;
@@ -1908,8 +1918,6 @@
unregister_candev(m_can_dev->net);
m_can_clk_stop(m_can_dev);
-
- free_candev(m_can_dev->net);
}
EXPORT_SYMBOL_GPL(m_can_class_unregister);
diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h
index 49f42b5..b2699a7 100644
--- a/drivers/net/can/m_can/m_can.h
+++ b/drivers/net/can/m_can/m_can.h
@@ -99,6 +99,7 @@
};
struct m_can_classdev *m_can_class_allocate_dev(struct device *dev);
+void m_can_class_free_dev(struct net_device *net);
int m_can_class_register(struct m_can_classdev *cdev);
void m_can_class_unregister(struct m_can_classdev *cdev);
int m_can_class_get_clocks(struct m_can_classdev *cdev);
diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c
index e6d0cb9..161cb9b 100644
--- a/drivers/net/can/m_can/m_can_platform.c
+++ b/drivers/net/can/m_can/m_can_platform.c
@@ -67,32 +67,36 @@
return -ENOMEM;
priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
- if (!priv)
- return -ENOMEM;
+ if (!priv) {
+ ret = -ENOMEM;
+ goto probe_fail;
+ }
mcan_class->device_data = priv;
- m_can_class_get_clocks(mcan_class);
+ ret = m_can_class_get_clocks(mcan_class);
+ if (ret)
+ goto probe_fail;
res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "m_can");
addr = devm_ioremap_resource(&pdev->dev, res);
irq = platform_get_irq_byname(pdev, "int0");
if (IS_ERR(addr) || irq < 0) {
ret = -EINVAL;
- goto failed_ret;
+ goto probe_fail;
}
/* message ram could be shared */
res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "message_ram");
if (!res) {
ret = -ENODEV;
- goto failed_ret;
+ goto probe_fail;
}
mram_addr = devm_ioremap(&pdev->dev, res->start, resource_size(res));
if (!mram_addr) {
ret = -ENOMEM;
- goto failed_ret;
+ goto probe_fail;
}
priv->base = addr;
@@ -111,9 +115,10 @@
m_can_init_ram(mcan_class);
- ret = m_can_class_register(mcan_class);
+ return m_can_class_register(mcan_class);
-failed_ret:
+probe_fail:
+ m_can_class_free_dev(mcan_class->net);
return ret;
}
@@ -134,6 +139,8 @@
m_can_class_unregister(mcan_class);
+ m_can_class_free_dev(mcan_class->net);
+
platform_set_drvdata(pdev, NULL);
return 0;
diff --git a/drivers/net/can/m_can/tcan4x5x.c b/drivers/net/can/m_can/tcan4x5x.c
index eacd428..e5d7d85 100644
--- a/drivers/net/can/m_can/tcan4x5x.c
+++ b/drivers/net/can/m_can/tcan4x5x.c
@@ -440,14 +440,18 @@
return -ENOMEM;
priv = devm_kzalloc(&spi->dev, sizeof(*priv), GFP_KERNEL);
- if (!priv)
- return -ENOMEM;
+ if (!priv) {
+ ret = -ENOMEM;
+ goto out_m_can_class_free_dev;
+ }
priv->power = devm_regulator_get_optional(&spi->dev, "vsup");
- if (PTR_ERR(priv->power) == -EPROBE_DEFER)
- return -EPROBE_DEFER;
- else
+ if (PTR_ERR(priv->power) == -EPROBE_DEFER) {
+ ret = -EPROBE_DEFER;
+ goto out_m_can_class_free_dev;
+ } else {
priv->power = NULL;
+ }
mcan_class->device_data = priv;
@@ -460,8 +464,10 @@
}
/* Sanity check */
- if (freq < 20000000 || freq > TCAN4X5X_EXT_CLK_DEF)
- return -ERANGE;
+ if (freq < 20000000 || freq > TCAN4X5X_EXT_CLK_DEF) {
+ ret = -ERANGE;
+ goto out_m_can_class_free_dev;
+ }
priv->reg_offset = TCAN4X5X_MCAN_OFFSET;
priv->mram_start = TCAN4X5X_MRAM_START;
@@ -487,6 +493,10 @@
priv->regmap = devm_regmap_init(&spi->dev, &tcan4x5x_bus,
&spi->dev, &tcan4x5x_regmap);
+ if (IS_ERR(priv->regmap)) {
+ ret = PTR_ERR(priv->regmap);
+ goto out_clk;
+ }
ret = tcan4x5x_power_enable(priv->power, 1);
if (ret)
@@ -514,8 +524,10 @@
clk_disable_unprepare(mcan_class->cclk);
clk_disable_unprepare(mcan_class->hclk);
}
-
+ out_m_can_class_free_dev:
+ m_can_class_free_dev(mcan_class->net);
dev_err(&spi->dev, "Probe failed, err=%d\n", ret);
+
return ret;
}
@@ -523,9 +535,11 @@
{
struct tcan4x5x_priv *priv = spi_get_drvdata(spi);
+ m_can_class_unregister(priv->mcan_dev);
+
tcan4x5x_power_enable(priv->power, 0);
- m_can_class_unregister(priv->mcan_dev);
+ m_can_class_free_dev(priv->mcan_dev->net);
return 0;
}
diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c
index 10aa3e4..40c33b8 100644
--- a/drivers/net/can/peak_canfd/peak_canfd.c
+++ b/drivers/net/can/peak_canfd/peak_canfd.c
@@ -262,8 +262,7 @@
cf_len = get_can_dlc(pucan_msg_get_dlc(msg));
/* if this frame is an echo, */
- if ((rx_msg_flags & PUCAN_MSG_LOOPED_BACK) &&
- !(rx_msg_flags & PUCAN_MSG_SELF_RECEIVE)) {
+ if (rx_msg_flags & PUCAN_MSG_LOOPED_BACK) {
unsigned long flags;
spin_lock_irqsave(&priv->echo_lock, flags);
@@ -277,7 +276,13 @@
netif_wake_queue(priv->ndev);
spin_unlock_irqrestore(&priv->echo_lock, flags);
- return 0;
+
+ /* if this frame is only an echo, stop here. Otherwise,
+ * continue to push this application self-received frame into
+ * its own rx queue.
+ */
+ if (!(rx_msg_flags & PUCAN_MSG_SELF_RECEIVE))
+ return 0;
}
/* otherwise, it should be pushed into rx fifo */
diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c
index 3b18026..6e95193 100644
--- a/drivers/net/can/rx-offload.c
+++ b/drivers/net/can/rx-offload.c
@@ -245,7 +245,7 @@
if (skb_queue_len(&offload->skb_queue) >
offload->skb_queue_len_max) {
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return -ENOBUFS;
}
@@ -290,7 +290,7 @@
{
if (skb_queue_len(&offload->skb_queue) >
offload->skb_queue_len_max) {
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return -ENOBUFS;
}
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index c3f4954..9c215f7 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -75,11 +75,11 @@
{
switch (model) {
case MCP251XFD_MODEL_MCP2517FD:
- return "MCP2517FD"; break;
+ return "MCP2517FD";
case MCP251XFD_MODEL_MCP2518FD:
- return "MCP2518FD"; break;
+ return "MCP2518FD";
case MCP251XFD_MODEL_MCP251XFD:
- return "MCP251xFD"; break;
+ return "MCP251xFD";
}
return "<unknown>";
@@ -95,21 +95,21 @@
{
switch (mode) {
case MCP251XFD_REG_CON_MODE_MIXED:
- return "Mixed (CAN FD/CAN 2.0)"; break;
+ return "Mixed (CAN FD/CAN 2.0)";
case MCP251XFD_REG_CON_MODE_SLEEP:
- return "Sleep"; break;
+ return "Sleep";
case MCP251XFD_REG_CON_MODE_INT_LOOPBACK:
- return "Internal Loopback"; break;
+ return "Internal Loopback";
case MCP251XFD_REG_CON_MODE_LISTENONLY:
- return "Listen Only"; break;
+ return "Listen Only";
case MCP251XFD_REG_CON_MODE_CONFIG:
- return "Configuration"; break;
+ return "Configuration";
case MCP251XFD_REG_CON_MODE_EXT_LOOPBACK:
- return "External Loopback"; break;
+ return "External Loopback";
case MCP251XFD_REG_CON_MODE_CAN2_0:
- return "CAN 2.0"; break;
+ return "CAN 2.0";
case MCP251XFD_REG_CON_MODE_RESTRICTED:
- return "Restricted Operation"; break;
+ return "Restricted Operation";
}
return "<unknown>";
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
index ba25902..314f868 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
@@ -173,7 +173,7 @@
memcpy(&buf_tx->cmd, reg, sizeof(buf_tx->cmd));
if (MCP251XFD_SANITIZE_SPI)
memset(buf_tx->data, 0x0, val_len);
- };
+ }
err = spi_sync(spi, &msg);
if (err)
@@ -330,17 +330,17 @@
goto out;
}
- netdev_dbg(priv->ndev,
- "CRC read error at address 0x%04x (length=%zd, data=%*ph, CRC=0x%04x) retrying.\n",
- reg, val_len, (int)val_len, buf_rx->data,
- get_unaligned_be16(buf_rx->data + val_len));
+ netdev_info(priv->ndev,
+ "CRC read error at address 0x%04x (length=%zd, data=%*ph, CRC=0x%04x) retrying.\n",
+ reg, val_len, (int)val_len, buf_rx->data,
+ get_unaligned_be16(buf_rx->data + val_len));
}
if (err) {
- netdev_info(priv->ndev,
- "CRC read error at address 0x%04x (length=%zd, data=%*ph, CRC=0x%04x).\n",
- reg, val_len, (int)val_len, buf_rx->data,
- get_unaligned_be16(buf_rx->data + val_len));
+ netdev_err(priv->ndev,
+ "CRC read error at address 0x%04x (length=%zd, data=%*ph, CRC=0x%04x).\n",
+ reg, val_len, (int)val_len, buf_rx->data,
+ get_unaligned_be16(buf_rx->data + val_len));
return err;
}
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 1d63006..2c22f40 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -881,7 +881,8 @@
priv->base = devm_platform_ioremap_resource_byname(pdev, "hecc");
if (IS_ERR(priv->base)) {
dev_err(&pdev->dev, "hecc ioremap failed\n");
- return PTR_ERR(priv->base);
+ err = PTR_ERR(priv->base);
+ goto probe_exit_candev;
}
/* handle hecc-ram memory */
@@ -889,20 +890,22 @@
"hecc-ram");
if (IS_ERR(priv->hecc_ram)) {
dev_err(&pdev->dev, "hecc-ram ioremap failed\n");
- return PTR_ERR(priv->hecc_ram);
+ err = PTR_ERR(priv->hecc_ram);
+ goto probe_exit_candev;
}
/* handle mbx memory */
priv->mbx = devm_platform_ioremap_resource_byname(pdev, "mbx");
if (IS_ERR(priv->mbx)) {
dev_err(&pdev->dev, "mbx ioremap failed\n");
- return PTR_ERR(priv->mbx);
+ err = PTR_ERR(priv->mbx);
+ goto probe_exit_candev;
}
irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
if (!irq) {
dev_err(&pdev->dev, "No irq resource\n");
- goto probe_exit;
+ goto probe_exit_candev;
}
priv->ndev = ndev;
@@ -933,7 +936,7 @@
err = clk_prepare_enable(priv->clk);
if (err) {
dev_err(&pdev->dev, "clk_prepare_enable() failed\n");
- goto probe_exit_clk;
+ goto probe_exit_release_clk;
}
priv->offload.mailbox_read = ti_hecc_mailbox_read;
@@ -942,7 +945,7 @@
err = can_rx_offload_add_timestamp(ndev, &priv->offload);
if (err) {
dev_err(&pdev->dev, "can_rx_offload_add_timestamp() failed\n");
- goto probe_exit_clk;
+ goto probe_exit_disable_clk;
}
err = register_candev(ndev);
@@ -960,11 +963,13 @@
probe_exit_offload:
can_rx_offload_del(&priv->offload);
-probe_exit_clk:
+probe_exit_disable_clk:
+ clk_disable_unprepare(priv->clk);
+probe_exit_release_clk:
clk_put(priv->clk);
probe_exit_candev:
free_candev(ndev);
-probe_exit:
+
return err;
}
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
index 7ab87a7..218fadc 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -367,7 +367,7 @@
.tseg2_max = 32,
.sjw_max = 16,
.brp_min = 1,
- .brp_max = 4096,
+ .brp_max = 8192,
.brp_inc = 1,
};
diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c
index 5857b37..e97f2e0 100644
--- a/drivers/net/can/usb/mcba_usb.c
+++ b/drivers/net/can/usb/mcba_usb.c
@@ -326,8 +326,6 @@
if (!ctx)
return NETDEV_TX_BUSY;
- can_put_echo_skb(skb, priv->netdev, ctx->ndx);
-
if (cf->can_id & CAN_EFF_FLAG) {
/* SIDH | SIDL | EIDH | EIDL
* 28 - 21 | 20 19 18 x x x 17 16 | 15 - 8 | 7 - 0
@@ -357,6 +355,8 @@
if (cf->can_id & CAN_RTR_FLAG)
usb_msg.dlc |= MCBA_DLC_RTR_MASK;
+ can_put_echo_skb(skb, priv->netdev, ctx->ndx);
+
err = mcba_usb_xmit(priv, (struct mcba_usb_msg *)&usb_msg, ctx);
if (err)
goto xmit_failed;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index d91df34..204ccb2 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -130,14 +130,55 @@
/* protect from getting time before setting now */
if (ktime_to_ns(time_ref->tv_host)) {
u64 delta_us;
+ s64 delta_ts = 0;
- delta_us = ts - time_ref->ts_dev_2;
- if (ts < time_ref->ts_dev_2)
- delta_us &= (1 << time_ref->adapter->ts_used_bits) - 1;
+ /* General case: dev_ts_1 < dev_ts_2 < ts, with:
+ *
+ * - dev_ts_1 = previous sync timestamp
+ * - dev_ts_2 = last sync timestamp
+ * - ts = event timestamp
+ * - ts_period = known sync period (theoretical)
+ * ~ dev_ts2 - dev_ts1
+ * *but*:
+ *
+ * - time counters wrap (see adapter->ts_used_bits)
+ * - sometimes, dev_ts_1 < ts < dev_ts2
+ *
+ * "normal" case (sync time counters increase):
+ * must take into account case when ts wraps (tsw)
+ *
+ * < ts_period > < >
+ * | | |
+ * ---+--------+----+-------0-+--+-->
+ * ts_dev_1 | ts_dev_2 |
+ * ts tsw
+ */
+ if (time_ref->ts_dev_1 < time_ref->ts_dev_2) {
+ /* case when event time (tsw) wraps */
+ if (ts < time_ref->ts_dev_1)
+ delta_ts = BIT_ULL(time_ref->adapter->ts_used_bits);
- delta_us += time_ref->ts_total;
+ /* Otherwise, sync time counter (ts_dev_2) has wrapped:
+ * handle case when event time (tsn) hasn't.
+ *
+ * < ts_period > < >
+ * | | |
+ * ---+--------+--0-+---------+--+-->
+ * ts_dev_1 | ts_dev_2 |
+ * tsn ts
+ */
+ } else if (time_ref->ts_dev_1 < ts) {
+ delta_ts = -BIT_ULL(time_ref->adapter->ts_used_bits);
+ }
- delta_us *= time_ref->adapter->us_per_ts_scale;
+ /* add delay between last sync and event timestamps */
+ delta_ts += (signed int)(ts - time_ref->ts_dev_2);
+
+ /* add time from beginning to last sync */
+ delta_ts += time_ref->ts_total;
+
+ /* convert ticks number into microseconds */
+ delta_us = delta_ts * time_ref->adapter->us_per_ts_scale;
delta_us >>= time_ref->adapter->us_per_ts_shift;
*time = ktime_add_us(time_ref->tv_host_0, delta_us);
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index ab63fd9..d29d205 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -468,12 +468,18 @@
struct pucan_msg *rx_msg)
{
struct pucan_rx_msg *rm = (struct pucan_rx_msg *)rx_msg;
- struct peak_usb_device *dev = usb_if->dev[pucan_msg_get_channel(rm)];
- struct net_device *netdev = dev->netdev;
+ struct peak_usb_device *dev;
+ struct net_device *netdev;
struct canfd_frame *cfd;
struct sk_buff *skb;
const u16 rx_msg_flags = le16_to_cpu(rm->flags);
+ if (pucan_msg_get_channel(rm) >= ARRAY_SIZE(usb_if->dev))
+ return -ENOMEM;
+
+ dev = usb_if->dev[pucan_msg_get_channel(rm)];
+ netdev = dev->netdev;
+
if (rx_msg_flags & PUCAN_MSG_EXT_DATA_LEN) {
/* CANFD frame case */
skb = alloc_canfd_skb(netdev, &cfd);
@@ -519,15 +525,21 @@
struct pucan_msg *rx_msg)
{
struct pucan_status_msg *sm = (struct pucan_status_msg *)rx_msg;
- struct peak_usb_device *dev = usb_if->dev[pucan_stmsg_get_channel(sm)];
- struct pcan_usb_fd_device *pdev =
- container_of(dev, struct pcan_usb_fd_device, dev);
+ struct pcan_usb_fd_device *pdev;
enum can_state new_state = CAN_STATE_ERROR_ACTIVE;
enum can_state rx_state, tx_state;
- struct net_device *netdev = dev->netdev;
+ struct peak_usb_device *dev;
+ struct net_device *netdev;
struct can_frame *cf;
struct sk_buff *skb;
+ if (pucan_stmsg_get_channel(sm) >= ARRAY_SIZE(usb_if->dev))
+ return -ENOMEM;
+
+ dev = usb_if->dev[pucan_stmsg_get_channel(sm)];
+ pdev = container_of(dev, struct pcan_usb_fd_device, dev);
+ netdev = dev->netdev;
+
/* nothing should be sent while in BUS_OFF state */
if (dev->can.state == CAN_STATE_BUS_OFF)
return 0;
@@ -579,9 +591,14 @@
struct pucan_msg *rx_msg)
{
struct pucan_error_msg *er = (struct pucan_error_msg *)rx_msg;
- struct peak_usb_device *dev = usb_if->dev[pucan_ermsg_get_channel(er)];
- struct pcan_usb_fd_device *pdev =
- container_of(dev, struct pcan_usb_fd_device, dev);
+ struct pcan_usb_fd_device *pdev;
+ struct peak_usb_device *dev;
+
+ if (pucan_ermsg_get_channel(er) >= ARRAY_SIZE(usb_if->dev))
+ return -EINVAL;
+
+ dev = usb_if->dev[pucan_ermsg_get_channel(er)];
+ pdev = container_of(dev, struct pcan_usb_fd_device, dev);
/* keep a trace of tx and rx error counters for later use */
pdev->bec.txerr = er->tx_err_cnt;
@@ -595,11 +612,17 @@
struct pucan_msg *rx_msg)
{
struct pcan_ufd_ovr_msg *ov = (struct pcan_ufd_ovr_msg *)rx_msg;
- struct peak_usb_device *dev = usb_if->dev[pufd_omsg_get_channel(ov)];
- struct net_device *netdev = dev->netdev;
+ struct peak_usb_device *dev;
+ struct net_device *netdev;
struct can_frame *cf;
struct sk_buff *skb;
+ if (pufd_omsg_get_channel(ov) >= ARRAY_SIZE(usb_if->dev))
+ return -EINVAL;
+
+ dev = usb_if->dev[pufd_omsg_get_channel(ov)];
+ netdev = dev->netdev;
+
/* allocate an skb to store the error frame */
skb = alloc_can_err_skb(netdev, &cf);
if (!skb)
@@ -716,6 +739,9 @@
u16 tx_msg_size, tx_msg_flags;
u8 can_dlc;
+ if (cfd->len > CANFD_MAX_DLEN)
+ return -EINVAL;
+
tx_msg_size = ALIGN(sizeof(struct pucan_tx_msg) + cfd->len, 4);
tx_msg->size = cpu_to_le16(tx_msg_size);
tx_msg->type = cpu_to_le16(PUCAN_MSG_CAN_TX);
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 6c4d00d..48d746e 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -1395,7 +1395,7 @@
if (ret < 0) {
netdev_err(ndev, "%s: pm_runtime_get failed(%d)\n",
__func__, ret);
- return ret;
+ goto err;
}
ret = request_irq(ndev->irq, xcan_interrupt, priv->irq_flags,
@@ -1479,6 +1479,7 @@
if (ret < 0) {
netdev_err(ndev, "%s: pm_runtime_get failed(%d)\n",
__func__, ret);
+ pm_runtime_put(priv->dev);
return ret;
}
@@ -1793,7 +1794,7 @@
if (ret < 0) {
netdev_err(ndev, "%s: pm_runtime_get failed(%d)\n",
__func__, ret);
- goto err_pmdisable;
+ goto err_disableclks;
}
if (priv->read_reg(priv, XCAN_SR_OFFSET) != XCAN_SR_CONFIG_MASK) {
@@ -1828,7 +1829,6 @@
err_disableclks:
pm_runtime_put(priv->dev);
-err_pmdisable:
pm_runtime_disable(&pdev->dev);
err_free:
free_candev(ndev);
diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c
index 74db81d..09701c1 100644
--- a/drivers/net/dsa/lantiq_gswip.c
+++ b/drivers/net/dsa/lantiq_gswip.c
@@ -26,6 +26,7 @@
*/
#include <linux/clk.h>
+#include <linux/delay.h>
#include <linux/etherdevice.h>
#include <linux/firmware.h>
#include <linux/if_bridge.h>
@@ -1837,6 +1838,16 @@
i++;
}
+ /* The standalone PHY11G requires 300ms to be fully
+ * initialized and ready for any MDIO communication after being
+ * taken out of reset. For the SoC-internal GPHY variant there
+ * is no (known) documentation for the minimum time after a
+ * reset. Use the same value as for the standalone variant as
+ * some users have reported internal PHYs not being detected
+ * without any delay.
+ */
+ msleep(300);
+
return 0;
remove_gphy:
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index bd297ae..34cca0a 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2297,6 +2297,8 @@
usleep_range(10000, 20000);
gpiod_set_value_cansleep(gpiod, 0);
usleep_range(10000, 20000);
+
+ mv88e6xxx_g1_wait_eeprom_done(chip);
}
}
diff --git a/drivers/net/dsa/mv88e6xxx/devlink.c b/drivers/net/dsa/mv88e6xxx/devlink.c
index 10cd1bf..ade04c0 100644
--- a/drivers/net/dsa/mv88e6xxx/devlink.c
+++ b/drivers/net/dsa/mv88e6xxx/devlink.c
@@ -393,8 +393,10 @@
mv88e6xxx_reg_lock(chip);
err = mv88e6xxx_fid_map(chip, fid_bitmap);
- if (err)
+ if (err) {
+ kfree(table);
goto out;
+ }
while (1) {
fid = find_next_bit(fid_bitmap, MV88E6XXX_N_FID, fid + 1);
diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c
index f62aa83..33d443a 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.c
+++ b/drivers/net/dsa/mv88e6xxx/global1.c
@@ -75,6 +75,37 @@
return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_STS, bit, 1);
}
+void mv88e6xxx_g1_wait_eeprom_done(struct mv88e6xxx_chip *chip)
+{
+ const unsigned long timeout = jiffies + 1 * HZ;
+ u16 val;
+ int err;
+
+ /* Wait up to 1 second for the switch to finish reading the
+ * EEPROM.
+ */
+ while (time_before(jiffies, timeout)) {
+ err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &val);
+ if (err) {
+ dev_err(chip->dev, "Error reading status");
+ return;
+ }
+
+ /* If the switch is still resetting, it may not
+ * respond on the bus, and so MDIO read returns
+ * 0xffff. Differentiate between that, and waiting for
+ * the EEPROM to be done by bit 0 being set.
+ */
+ if (val != 0xffff &&
+ val & BIT(MV88E6XXX_G1_STS_IRQ_EEPROM_DONE))
+ return;
+
+ usleep_range(1000, 2000);
+ }
+
+ dev_err(chip->dev, "Timeout waiting for EEPROM done");
+}
+
/* Offset 0x01: Switch MAC Address Register Bytes 0 & 1
* Offset 0x02: Switch MAC Address Register Bytes 2 & 3
* Offset 0x03: Switch MAC Address Register Bytes 4 & 5
diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h
index 1e3546f..e05abe6 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.h
+++ b/drivers/net/dsa/mv88e6xxx/global1.h
@@ -278,6 +278,7 @@
int mv88e6185_g1_reset(struct mv88e6xxx_chip *chip);
int mv88e6352_g1_reset(struct mv88e6xxx_chip *chip);
int mv88e6250_g1_reset(struct mv88e6xxx_chip *chip);
+void mv88e6xxx_g1_wait_eeprom_done(struct mv88e6xxx_chip *chip);
int mv88e6185_g1_ppu_enable(struct mv88e6xxx_chip *chip);
int mv88e6185_g1_ppu_disable(struct mv88e6xxx_chip *chip);
diff --git a/drivers/net/dsa/mv88e6xxx/global1_vtu.c b/drivers/net/dsa/mv88e6xxx/global1_vtu.c
index 48390b7..1048509 100644
--- a/drivers/net/dsa/mv88e6xxx/global1_vtu.c
+++ b/drivers/net/dsa/mv88e6xxx/global1_vtu.c
@@ -125,11 +125,9 @@
* Offset 0x08: VTU/STU Data Register 2
* Offset 0x09: VTU/STU Data Register 3
*/
-
-static int mv88e6185_g1_vtu_data_read(struct mv88e6xxx_chip *chip,
- struct mv88e6xxx_vtu_entry *entry)
+static int mv88e6185_g1_vtu_stu_data_read(struct mv88e6xxx_chip *chip,
+ u16 *regs)
{
- u16 regs[3];
int i;
/* Read all 3 VTU/STU Data registers */
@@ -142,12 +140,45 @@
return err;
}
- /* Extract MemberTag and PortState data */
+ return 0;
+}
+
+static int mv88e6185_g1_vtu_data_read(struct mv88e6xxx_chip *chip,
+ struct mv88e6xxx_vtu_entry *entry)
+{
+ u16 regs[3];
+ int err;
+ int i;
+
+ err = mv88e6185_g1_vtu_stu_data_read(chip, regs);
+ if (err)
+ return err;
+
+ /* Extract MemberTag data */
for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
unsigned int member_offset = (i % 4) * 4;
- unsigned int state_offset = member_offset + 2;
entry->member[i] = (regs[i / 4] >> member_offset) & 0x3;
+ }
+
+ return 0;
+}
+
+static int mv88e6185_g1_stu_data_read(struct mv88e6xxx_chip *chip,
+ struct mv88e6xxx_vtu_entry *entry)
+{
+ u16 regs[3];
+ int err;
+ int i;
+
+ err = mv88e6185_g1_vtu_stu_data_read(chip, regs);
+ if (err)
+ return err;
+
+ /* Extract PortState data */
+ for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
+ unsigned int state_offset = (i % 4) * 4 + 2;
+
entry->state[i] = (regs[i / 4] >> state_offset) & 0x3;
}
@@ -349,6 +380,10 @@
if (err)
return err;
+ err = mv88e6185_g1_stu_data_read(chip, entry);
+ if (err)
+ return err;
+
/* VTU DBNum[3:0] are located in VTU Operation 3:0
* VTU DBNum[7:4] are located in VTU Operation 11:8
*/
@@ -374,11 +409,6 @@
return err;
if (entry->valid) {
- /* Fetch (and mask) VLAN PortState data from the STU */
- err = mv88e6xxx_g1_vtu_stu_get(chip, entry);
- if (err)
- return err;
-
err = mv88e6185_g1_vtu_data_read(chip, entry);
if (err)
return err;
@@ -386,6 +416,15 @@
err = mv88e6xxx_g1_vtu_fid_read(chip, entry);
if (err)
return err;
+
+ /* Fetch VLAN PortState data from the STU */
+ err = mv88e6xxx_g1_vtu_stu_get(chip, entry);
+ if (err)
+ return err;
+
+ err = mv88e6185_g1_stu_data_read(chip, entry);
+ if (err)
+ return err;
}
return 0;
diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c
index 53064e0..5bdac66 100644
--- a/drivers/net/dsa/qca8k.c
+++ b/drivers/net/dsa/qca8k.c
@@ -1219,8 +1219,8 @@
priv->port_mtu[port] = new_mtu;
for (i = 0; i < QCA8K_NUM_PORTS; i++)
- if (priv->port_mtu[port] > mtu)
- mtu = priv->port_mtu[port];
+ if (priv->port_mtu[i] > mtu)
+ mtu = priv->port_mtu[i];
/* Include L2 header / FCS length */
qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, mtu + ETH_HLEN + ETH_FCS_LEN);
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 0c12cf7..3f65f2b 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -2543,8 +2543,8 @@
* various kernel subsystems to support the mechanics required by a
* fixed-high-32-bit system.
*/
- if ((dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0) ||
- (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0)) {
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+ if (err) {
dev_err(&pdev->dev, "No usable DMA configuration,aborting\n");
goto err_dma;
}
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index 098b032..ff9f96d 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -2312,8 +2312,8 @@
* various kernel subsystems to support the mechanics required by a
* fixed-high-32-bit system.
*/
- if ((dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0) ||
- (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0)) {
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+ if (err) {
dev_err(&pdev->dev, "No usable DMA configuration,aborting\n");
goto err_dma;
}
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index 74c1778..b455b60 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -2383,7 +2383,8 @@
goto err_out_free_dev;
}
- if (dma_set_mask_and_coherent(sdev->dma_dev, DMA_BIT_MASK(30))) {
+ err = dma_set_mask_and_coherent(sdev->dma_dev, DMA_BIT_MASK(30));
+ if (err) {
dev_err(sdev->dev,
"Required 30BIT DMA mask unsupported by the system\n");
goto err_out_powerdown;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index fa14786..7c21aaa8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1160,16 +1160,6 @@
schedule_work(&bp->sp_task);
}
-static void bnxt_cancel_sp_work(struct bnxt *bp)
-{
- if (BNXT_PF(bp)) {
- flush_workqueue(bnxt_pf_wq);
- } else {
- cancel_work_sync(&bp->sp_task);
- cancel_delayed_work_sync(&bp->fw_reset_task);
- }
-}
-
static void bnxt_sched_reset(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
{
if (!rxr->bnapi->in_reset) {
@@ -4109,7 +4099,8 @@
bnxt_free_ntp_fltrs(bp, irq_re_init);
if (irq_re_init) {
bnxt_free_ring_stats(bp);
- if (!(bp->fw_cap & BNXT_FW_CAP_PORT_STATS_NO_RESET))
+ if (!(bp->fw_cap & BNXT_FW_CAP_PORT_STATS_NO_RESET) ||
+ test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
bnxt_free_port_stats(bp);
bnxt_free_ring_grps(bp);
bnxt_free_vnics(bp);
@@ -4362,7 +4353,8 @@
u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM;
u16 dst = BNXT_HWRM_CHNL_CHIMP;
- if (BNXT_NO_FW_ACCESS(bp))
+ if (BNXT_NO_FW_ACCESS(bp) &&
+ le16_to_cpu(req->req_type) != HWRM_FUNC_RESET)
return -EBUSY;
if (msg_len > BNXT_HWRM_MAX_REQ_LEN) {
@@ -7766,6 +7758,7 @@
{
u64 sw_tmp;
+ hw &= mask;
sw_tmp = (*sw & ~mask) | hw;
if (hw < (*sw & mask))
sw_tmp += mask + 1;
@@ -9789,7 +9782,10 @@
{
int rc = 0;
- rc = __bnxt_open_nic(bp, irq_re_init, link_re_init);
+ if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state))
+ rc = -EIO;
+ if (!rc)
+ rc = __bnxt_open_nic(bp, irq_re_init, link_re_init);
if (rc) {
netdev_err(bp->dev, "nic open fail (rc: %x)\n", rc);
dev_close(bp->dev);
@@ -12108,15 +12104,17 @@
if (BNXT_PF(bp))
bnxt_sriov_disable(bp);
- clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
- bnxt_cancel_sp_work(bp);
- bp->sp_event = 0;
-
- bnxt_dl_fw_reporters_destroy(bp, true);
if (BNXT_PF(bp))
devlink_port_type_clear(&bp->dl_port);
pci_disable_pcie_error_reporting(pdev);
unregister_netdev(dev);
+ clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+ /* Flush any pending tasks */
+ cancel_work_sync(&bp->sp_task);
+ cancel_delayed_work_sync(&bp->fw_reset_task);
+ bp->sp_event = 0;
+
+ bnxt_dl_fw_reporters_destroy(bp, true);
bnxt_dl_unregister(bp);
bnxt_shutdown_tc(bp);
@@ -12860,6 +12858,9 @@
return PCI_ERS_RESULT_DISCONNECT;
}
+ if (state == pci_channel_io_frozen)
+ set_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, &bp->state);
+
if (netif_running(netdev))
bnxt_close(netdev);
@@ -12886,7 +12887,7 @@
{
struct net_device *netdev = pci_get_drvdata(pdev);
struct bnxt *bp = netdev_priv(netdev);
- int err = 0;
+ int err = 0, off;
pci_ers_result_t result = PCI_ERS_RESULT_DISCONNECT;
netdev_info(bp->dev, "PCI Slot Reset\n");
@@ -12898,6 +12899,20 @@
"Cannot re-enable PCI device after reset.\n");
} else {
pci_set_master(pdev);
+ /* Upon fatal error, our device internal logic that latches to
+ * BAR value is getting reset and will restore only upon
+ * rewritting the BARs.
+ *
+ * As pci_restore_state() does not re-write the BARs if the
+ * value is same as saved value earlier, driver needs to
+ * write the BARs to 0 to force restore, in case of fatal error.
+ */
+ if (test_and_clear_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN,
+ &bp->state)) {
+ for (off = PCI_BASE_ADDRESS_0;
+ off <= PCI_BASE_ADDRESS_5; off += 4)
+ pci_write_config_dword(bp->pdev, off, 0);
+ }
pci_restore_state(pdev);
pci_save_state(pdev);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 21ef1c2..47b3c31 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1781,6 +1781,7 @@
#define BNXT_STATE_ABORT_ERR 5
#define BNXT_STATE_FW_FATAL_COND 6
#define BNXT_STATE_DRV_REGISTERED 7
+#define BNXT_STATE_PCI_CHANNEL_IO_FROZEN 8
#define BNXT_NO_FW_ACCESS(bp) \
(test_bit(BNXT_STATE_FW_FATAL_COND, &(bp)->state) || \
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 53687bc..1471c9a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2079,6 +2079,9 @@
struct hwrm_nvm_get_dev_info_input req = {0};
int rc;
+ if (BNXT_VF(bp))
+ return -EOPNOTSUPP;
+
bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_GET_DEV_INFO, -1, -1);
mutex_lock(&bp->hwrm_cmd_lock);
rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
@@ -2997,7 +3000,7 @@
/* Read A2 portion of the EEPROM */
if (length) {
start -= ETH_MODULE_SFF_8436_LEN;
- rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A2, 1,
+ rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A2, 0,
start, length, data);
}
return rc;
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 883e47c..286f034 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1929,7 +1929,8 @@
static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev)
{
- bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb);
+ bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb) ||
+ skb_is_nonlinear(*skb);
int padlen = ETH_ZLEN - (*skb)->len;
int headroom = skb_headroom(*skb);
int tailroom = skb_tailroom(*skb);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 3352dad..2730860 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -2124,6 +2124,9 @@
void cxgb4_write_sgl(const struct sk_buff *skb, struct sge_txq *q,
struct ulptx_sgl *sgl, u64 *end, unsigned int start,
const dma_addr_t *addr);
+void cxgb4_write_partial_sgl(const struct sk_buff *skb, struct sge_txq *q,
+ struct ulptx_sgl *sgl, u64 *end,
+ const dma_addr_t *addr, u32 start, u32 send_len);
void cxgb4_ring_tx_db(struct adapter *adap, struct sge_txq *q, int n);
int t4_set_vlan_acl(struct adapter *adap, unsigned int mbox, unsigned int vf,
u16 vlan);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 0273f40..17410fe 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -3573,6 +3573,8 @@
atomic64_read(&adap->ch_ktls_stats.ktls_tx_complete_pkts));
seq_printf(seq, "TX trim pkts : %20llu\n",
atomic64_read(&adap->ch_ktls_stats.ktls_tx_trimmed_pkts));
+ seq_printf(seq, "TX sw fallback : %20llu\n",
+ atomic64_read(&adap->ch_ktls_stats.ktls_tx_fallback));
while (i < MAX_NPORTS) {
ktls_port = &adap->ch_ktls_stats.ktls_port[i];
seq_printf(seq, "Port %d\n", i);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index 6ec5f2f..4e55f70 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -145,13 +145,13 @@
int err;
/* do a set-tcb for smac-sel and CWR bit.. */
- err = set_tcb_tflag(adap, f, f->tid, TF_CCTRL_CWR_S, 1, 1);
- if (err)
- goto smac_err;
-
err = set_tcb_field(adap, f, f->tid, TCB_SMAC_SEL_W,
TCB_SMAC_SEL_V(TCB_SMAC_SEL_M),
TCB_SMAC_SEL_V(f->smt->idx), 1);
+ if (err)
+ goto smac_err;
+
+ err = set_tcb_tflag(adap, f, f->tid, TF_CCTRL_CWR_S, 1, 1);
if (!err)
return 0;
@@ -862,6 +862,7 @@
FW_FILTER_WR_DIRSTEERHASH_V(f->fs.dirsteerhash) |
FW_FILTER_WR_LPBK_V(f->fs.action == FILTER_SWITCH) |
FW_FILTER_WR_DMAC_V(f->fs.newdmac) |
+ FW_FILTER_WR_SMAC_V(f->fs.newsmac) |
FW_FILTER_WR_INSVLAN_V(f->fs.newvlan == VLAN_INSERT ||
f->fs.newvlan == VLAN_REWRITE) |
FW_FILTER_WR_RMVLAN_V(f->fs.newvlan == VLAN_REMOVE ||
@@ -879,7 +880,7 @@
FW_FILTER_WR_OVLAN_VLD_V(f->fs.val.ovlan_vld) |
FW_FILTER_WR_IVLAN_VLDM_V(f->fs.mask.ivlan_vld) |
FW_FILTER_WR_OVLAN_VLDM_V(f->fs.mask.ovlan_vld));
- fwr->smac_sel = 0;
+ fwr->smac_sel = f->smt->idx;
fwr->rx_chan_rx_rpl_iq =
htons(FW_FILTER_WR_RX_CHAN_V(0) |
FW_FILTER_WR_RX_RPL_IQ_V(adapter->sge.fw_evtq.abs_id));
@@ -1323,11 +1324,8 @@
TX_QUEUE_V(f->fs.nat_mode) |
T5_OPT_2_VALID_F |
RX_CHANNEL_V(cxgb4_port_e2cchan(f->dev)) |
- CONG_CNTRL_V((f->fs.action == FILTER_DROP) |
- (f->fs.dirsteer << 1)) |
PACE_V((f->fs.maskhash) |
- ((f->fs.dirsteerhash) << 1)) |
- CCTRL_ECN_V(f->fs.action == FILTER_SWITCH));
+ ((f->fs.dirsteerhash) << 1)));
}
static void mk_act_open_req(struct filter_entry *f, struct sk_buff *skb,
@@ -1363,11 +1361,8 @@
TX_QUEUE_V(f->fs.nat_mode) |
T5_OPT_2_VALID_F |
RX_CHANNEL_V(cxgb4_port_e2cchan(f->dev)) |
- CONG_CNTRL_V((f->fs.action == FILTER_DROP) |
- (f->fs.dirsteer << 1)) |
PACE_V((f->fs.maskhash) |
- ((f->fs.dirsteerhash) << 1)) |
- CCTRL_ECN_V(f->fs.action == FILTER_SWITCH));
+ ((f->fs.dirsteerhash) << 1)));
}
static int cxgb4_set_hash_filter(struct net_device *dev,
@@ -2039,6 +2034,20 @@
}
return;
}
+ switch (f->fs.action) {
+ case FILTER_PASS:
+ if (f->fs.dirsteer)
+ set_tcb_tflag(adap, f, tid,
+ TF_DIRECT_STEER_S, 1, 1);
+ break;
+ case FILTER_DROP:
+ set_tcb_tflag(adap, f, tid, TF_DROP_S, 1, 1);
+ break;
+ case FILTER_SWITCH:
+ set_tcb_tflag(adap, f, tid, TF_LPBK_S, 1, 1);
+ break;
+ }
+
break;
default:
@@ -2106,22 +2115,11 @@
if (ctx)
ctx->result = 0;
} else if (ret == FW_FILTER_WR_FLT_ADDED) {
- int err = 0;
-
- if (f->fs.newsmac)
- err = configure_filter_smac(adap, f);
-
- if (!err) {
- f->pending = 0; /* async setup completed */
- f->valid = 1;
- if (ctx) {
- ctx->result = 0;
- ctx->tid = idx;
- }
- } else {
- clear_filter(adap, f);
- if (ctx)
- ctx->result = err;
+ f->pending = 0; /* async setup completed */
+ f->valid = 1;
+ if (ctx) {
+ ctx->result = 0;
+ ctx->tid = idx;
}
} else {
/* Something went wrong. Issue a warning about the
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index a952fe1..7fd264a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -1176,6 +1176,7 @@
txq = netdev_pick_tx(dev, skb, sb_dev);
if (xfrm_offload(skb) || is_ptp_enabled(skb, dev) ||
skb->encapsulation ||
+ cxgb4_is_ktls_skb(skb) ||
(proto != IPPROTO_TCP && proto != IPPROTO_UDP))
txq = txq % pi->nqsets;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index b169776..1b49f2f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -388,6 +388,7 @@
atomic64_t ktls_tx_retransmit_pkts;
atomic64_t ktls_tx_complete_pkts;
atomic64_t ktls_tx_trimmed_pkts;
+ atomic64_t ktls_tx_fallback;
};
#endif
@@ -493,6 +494,11 @@
#endif
};
+static inline bool cxgb4_is_ktls_skb(struct sk_buff *skb)
+{
+ return skb->sk && tls_is_sk_tx_device_offloaded(skb->sk);
+}
+
void cxgb4_uld_enable(struct adapter *adap);
void cxgb4_register_uld(enum cxgb4_uld type, const struct cxgb4_uld_info *p);
int cxgb4_unregister_uld(enum cxgb4_uld type);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index a9e9c7a..196652a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -890,6 +890,114 @@
}
EXPORT_SYMBOL(cxgb4_write_sgl);
+/* cxgb4_write_partial_sgl - populate SGL for partial packet
+ * @skb: the packet
+ * @q: the Tx queue we are writing into
+ * @sgl: starting location for writing the SGL
+ * @end: points right after the end of the SGL
+ * @addr: the list of bus addresses for the SGL elements
+ * @start: start offset in the SKB where partial data starts
+ * @len: length of data from @start to send out
+ *
+ * This API will handle sending out partial data of a skb if required.
+ * Unlike cxgb4_write_sgl, @start can be any offset into the skb data,
+ * and @len will decide how much data after @start offset to send out.
+ */
+void cxgb4_write_partial_sgl(const struct sk_buff *skb, struct sge_txq *q,
+ struct ulptx_sgl *sgl, u64 *end,
+ const dma_addr_t *addr, u32 start, u32 len)
+{
+ struct ulptx_sge_pair buf[MAX_SKB_FRAGS / 2 + 1] = {0}, *to;
+ u32 frag_size, skb_linear_data_len = skb_headlen(skb);
+ struct skb_shared_info *si = skb_shinfo(skb);
+ u8 i = 0, frag_idx = 0, nfrags = 0;
+ skb_frag_t *frag;
+
+ /* Fill the first SGL either from linear data or from partial
+ * frag based on @start.
+ */
+ if (unlikely(start < skb_linear_data_len)) {
+ frag_size = min(len, skb_linear_data_len - start);
+ sgl->len0 = htonl(frag_size);
+ sgl->addr0 = cpu_to_be64(addr[0] + start);
+ len -= frag_size;
+ nfrags++;
+ } else {
+ start -= skb_linear_data_len;
+ frag = &si->frags[frag_idx];
+ frag_size = skb_frag_size(frag);
+ /* find the first frag */
+ while (start >= frag_size) {
+ start -= frag_size;
+ frag_idx++;
+ frag = &si->frags[frag_idx];
+ frag_size = skb_frag_size(frag);
+ }
+
+ frag_size = min(len, skb_frag_size(frag) - start);
+ sgl->len0 = cpu_to_be32(frag_size);
+ sgl->addr0 = cpu_to_be64(addr[frag_idx + 1] + start);
+ len -= frag_size;
+ nfrags++;
+ frag_idx++;
+ }
+
+ /* If the entire partial data fit in one SGL, then send it out
+ * now.
+ */
+ if (!len)
+ goto done;
+
+ /* Most of the complexity below deals with the possibility we hit the
+ * end of the queue in the middle of writing the SGL. For this case
+ * only we create the SGL in a temporary buffer and then copy it.
+ */
+ to = (u8 *)end > (u8 *)q->stat ? buf : sgl->sge;
+
+ /* If the skb couldn't fit in first SGL completely, fill the
+ * rest of the frags in subsequent SGLs. Note that each SGL
+ * pair can store 2 frags.
+ */
+ while (len) {
+ frag_size = min(len, skb_frag_size(&si->frags[frag_idx]));
+ to->len[i & 1] = cpu_to_be32(frag_size);
+ to->addr[i & 1] = cpu_to_be64(addr[frag_idx + 1]);
+ if (i && (i & 1))
+ to++;
+ nfrags++;
+ frag_idx++;
+ i++;
+ len -= frag_size;
+ }
+
+ /* If we ended in an odd boundary, then set the second SGL's
+ * length in the pair to 0.
+ */
+ if (i & 1)
+ to->len[1] = cpu_to_be32(0);
+
+ /* Copy from temporary buffer to Tx ring, in case we hit the
+ * end of the queue in the middle of writing the SGL.
+ */
+ if (unlikely((u8 *)end > (u8 *)q->stat)) {
+ u32 part0 = (u8 *)q->stat - (u8 *)sgl->sge, part1;
+
+ if (likely(part0))
+ memcpy(sgl->sge, buf, part0);
+ part1 = (u8 *)end - (u8 *)q->stat;
+ memcpy(q->desc, (u8 *)buf + part0, part1);
+ end = (void *)q->desc + part1;
+ }
+
+ /* 0-pad to multiple of 16 */
+ if ((uintptr_t)end & 8)
+ *end = 0;
+done:
+ sgl->cmd_nsge = htonl(ULPTX_CMD_V(ULP_TX_SC_DSGL) |
+ ULPTX_NSGE_V(nfrags));
+}
+EXPORT_SYMBOL(cxgb4_write_partial_sgl);
+
/* This function copies 64 byte coalesced work request to
* memory mapped BAR2 space. For coalesced WR SGE fetches
* data from the FIFO instead of from Host.
@@ -1422,7 +1530,8 @@
#endif /* CHELSIO_IPSEC_INLINE */
#if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
- if (skb->decrypted)
+ if (cxgb4_is_ktls_skb(skb) &&
+ (skb->len - (skb_transport_offset(skb) + tcp_hdrlen(skb))))
return adap->uld[CXGB4_ULD_KTLS].tx_handler(skb, dev);
#endif /* CHELSIO_TLS_DEVICE */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h b/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h
index 50232e0..92473dd 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h
@@ -50,6 +50,10 @@
#define TCB_T_FLAGS_M 0xffffffffffffffffULL
#define TCB_T_FLAGS_V(x) ((__u64)(x) << TCB_T_FLAGS_S)
+#define TF_DROP_S 22
+#define TF_DIRECT_STEER_S 23
+#define TF_LPBK_S 59
+
#define TF_CCTRL_ECE_S 60
#define TF_CCTRL_CWR_S 61
#define TF_CCTRL_RFR_S 62
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
index 5195f69..c24485c 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
@@ -14,6 +14,50 @@
static LIST_HEAD(uld_ctx_list);
static DEFINE_MUTEX(dev_mutex);
+/* chcr_get_nfrags_to_send: get the remaining nfrags after start offset
+ * @skb: skb
+ * @start: start offset.
+ * @len: how much data to send after @start
+ */
+static int chcr_get_nfrags_to_send(struct sk_buff *skb, u32 start, u32 len)
+{
+ struct skb_shared_info *si = skb_shinfo(skb);
+ u32 frag_size, skb_linear_data_len = skb_headlen(skb);
+ u8 nfrags = 0, frag_idx = 0;
+ skb_frag_t *frag;
+
+ /* if its a linear skb then return 1 */
+ if (!skb_is_nonlinear(skb))
+ return 1;
+
+ if (unlikely(start < skb_linear_data_len)) {
+ frag_size = min(len, skb_linear_data_len - start);
+ start = 0;
+ } else {
+ start -= skb_linear_data_len;
+
+ frag = &si->frags[frag_idx];
+ frag_size = skb_frag_size(frag);
+ while (start >= frag_size) {
+ start -= frag_size;
+ frag_idx++;
+ frag = &si->frags[frag_idx];
+ frag_size = skb_frag_size(frag);
+ }
+ frag_size = min(len, skb_frag_size(frag) - start);
+ }
+ len -= frag_size;
+ nfrags++;
+
+ while (len) {
+ frag_size = min(len, skb_frag_size(&si->frags[frag_idx]));
+ len -= frag_size;
+ nfrags++;
+ frag_idx++;
+ }
+ return nfrags;
+}
+
static int chcr_init_tcb_fields(struct chcr_ktls_info *tx_info);
/*
* chcr_ktls_save_keys: calculate and save crypto keys.
@@ -689,7 +733,8 @@
}
static void *__chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info,
- u32 tid, void *pos, u16 word, u64 mask,
+ u32 tid, void *pos, u16 word,
+ struct sge_eth_txq *q, u64 mask,
u64 val, u32 reply)
{
struct cpl_set_tcb_field_core *cpl;
@@ -698,7 +743,10 @@
/* ULP_TXPKT */
txpkt = pos;
- txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) | ULP_TXPKT_DEST_V(0));
+ txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) |
+ ULP_TXPKT_CHANNELID_V(tx_info->port_id) |
+ ULP_TXPKT_FID_V(q->q.cntxt_id) |
+ ULP_TXPKT_RO_F);
txpkt->len = htonl(DIV_ROUND_UP(CHCR_SET_TCB_FIELD_LEN, 16));
/* ULPTX_IDATA sub-command */
@@ -753,7 +801,7 @@
} else {
u8 buf[48] = {0};
- __chcr_write_cpl_set_tcb_ulp(tx_info, tid, buf, word,
+ __chcr_write_cpl_set_tcb_ulp(tx_info, tid, buf, word, q,
mask, val, reply);
return chcr_copy_to_txd(buf, &q->q, pos,
@@ -761,7 +809,7 @@
}
}
- pos = __chcr_write_cpl_set_tcb_ulp(tx_info, tid, pos, word,
+ pos = __chcr_write_cpl_set_tcb_ulp(tx_info, tid, pos, word, q,
mask, val, reply);
/* check again if we are at the end of the queue */
@@ -783,11 +831,11 @@
*/
static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info,
struct sge_eth_txq *q, u64 tcp_seq,
- u64 tcp_ack, u64 tcp_win)
+ u64 tcp_ack, u64 tcp_win, bool offset)
{
bool first_wr = ((tx_info->prev_ack == 0) && (tx_info->prev_win == 0));
struct ch_ktls_port_stats_debug *port_stats;
- u32 len, cpl = 0, ndesc, wr_len;
+ u32 len, cpl = 0, ndesc, wr_len, wr_mid = 0;
struct fw_ulptx_wr *wr;
int credits;
void *pos;
@@ -803,6 +851,11 @@
return NETDEV_TX_BUSY;
}
+ if (unlikely(credits < ETHTXQ_STOP_THRES)) {
+ chcr_eth_txq_stop(q);
+ wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+ }
+
pos = &q->q.desc[q->q.pidx];
/* make space for WR, we'll fill it later when we know all the cpls
* being sent out and have complete length.
@@ -818,7 +871,7 @@
cpl++;
}
/* reset snd una if it's a re-transmit pkt */
- if (tcp_seq != tx_info->prev_seq) {
+ if (tcp_seq != tx_info->prev_seq || offset) {
/* reset snd_una */
port_stats =
&tx_info->adap->ch_ktls_stats.ktls_port[tx_info->port_id];
@@ -827,7 +880,8 @@
TCB_SND_UNA_RAW_V
(TCB_SND_UNA_RAW_M),
TCB_SND_UNA_RAW_V(0), 0);
- atomic64_inc(&port_stats->ktls_tx_ooo);
+ if (tcp_seq != tx_info->prev_seq)
+ atomic64_inc(&port_stats->ktls_tx_ooo);
cpl++;
}
/* update ack */
@@ -856,7 +910,8 @@
wr->op_to_compl = htonl(FW_WR_OP_V(FW_ULPTX_WR));
wr->cookie = 0;
/* fill len in wr field */
- wr->flowid_len16 = htonl(FW_WR_LEN16_V(DIV_ROUND_UP(len, 16)));
+ wr->flowid_len16 = htonl(wr_mid |
+ FW_WR_LEN16_V(DIV_ROUND_UP(len, 16)));
ndesc = DIV_ROUND_UP(len, 64);
chcr_txq_advance(&q->q, ndesc);
@@ -866,34 +921,14 @@
}
/*
- * chcr_ktls_skb_copy
- * @nskb - new skb where the frags to be added.
- * @skb - old skb from which frags will be copied.
- */
-static void chcr_ktls_skb_copy(struct sk_buff *skb, struct sk_buff *nskb)
-{
- int i;
-
- for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
- skb_shinfo(nskb)->frags[i] = skb_shinfo(skb)->frags[i];
- __skb_frag_ref(&skb_shinfo(nskb)->frags[i]);
- }
-
- skb_shinfo(nskb)->nr_frags = skb_shinfo(skb)->nr_frags;
- nskb->len += skb->data_len;
- nskb->data_len = skb->data_len;
- nskb->truesize += skb->data_len;
-}
-
-/*
* chcr_ktls_get_tx_flits
* returns number of flits to be sent out, it includes key context length, WR
* size and skb fragments.
*/
static unsigned int
-chcr_ktls_get_tx_flits(const struct sk_buff *skb, unsigned int key_ctx_len)
+chcr_ktls_get_tx_flits(u32 nr_frags, unsigned int key_ctx_len)
{
- return chcr_sgl_len(skb_shinfo(skb)->nr_frags) +
+ return chcr_sgl_len(nr_frags) +
DIV_ROUND_UP(key_ctx_len + CHCR_KTLS_WR_SIZE, 8);
}
@@ -957,8 +992,10 @@
struct tcphdr *tcp;
int len16, pktlen;
struct iphdr *ip;
+ u32 wr_mid = 0;
int credits;
u8 buf[150];
+ u64 cntrl1;
void *pos;
iplen = skb_network_header_len(skb);
@@ -967,7 +1004,7 @@
/* packet length = eth hdr len + ip hdr len + tcp hdr len
* (including options).
*/
- pktlen = skb->len - skb->data_len;
+ pktlen = skb_transport_offset(skb) + tcp_hdrlen(skb);
ctrl = sizeof(*cpl) + pktlen;
len16 = DIV_ROUND_UP(sizeof(*wr) + ctrl, 16);
@@ -980,6 +1017,11 @@
return NETDEV_TX_BUSY;
}
+ if (unlikely(credits < ETHTXQ_STOP_THRES)) {
+ chcr_eth_txq_stop(q);
+ wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+ }
+
pos = &q->q.desc[q->q.pidx];
wr = pos;
@@ -987,7 +1029,7 @@
wr->op_immdlen = htonl(FW_WR_OP_V(FW_ETH_TX_PKT_WR) |
FW_WR_IMMDLEN_V(ctrl));
- wr->equiq_to_len16 = htonl(FW_WR_LEN16_V(len16));
+ wr->equiq_to_len16 = htonl(wr_mid | FW_WR_LEN16_V(len16));
wr->r3 = 0;
cpl = (void *)(wr + 1);
@@ -997,22 +1039,28 @@
TXPKT_PF_V(tx_info->adap->pf));
cpl->pack = 0;
cpl->len = htons(pktlen);
- /* checksum offload */
- cpl->ctrl1 = 0;
-
- pos = cpl + 1;
memcpy(buf, skb->data, pktlen);
if (tx_info->ip_family == AF_INET) {
/* we need to correct ip header len */
ip = (struct iphdr *)(buf + maclen);
ip->tot_len = htons(pktlen - maclen);
+ cntrl1 = TXPKT_CSUM_TYPE_V(TX_CSUM_TCPIP);
#if IS_ENABLED(CONFIG_IPV6)
} else {
ip6 = (struct ipv6hdr *)(buf + maclen);
ip6->payload_len = htons(pktlen - maclen - iplen);
+ cntrl1 = TXPKT_CSUM_TYPE_V(TX_CSUM_TCPIP6);
#endif
}
+
+ cntrl1 |= T6_TXPKT_ETHHDR_LEN_V(maclen - ETH_HLEN) |
+ TXPKT_IPHDR_LEN_V(iplen);
+ /* checksum offload */
+ cpl->ctrl1 = cpu_to_be64(cntrl1);
+
+ pos = cpl + 1;
+
/* now take care of the tcp header, if fin is not set then clear push
* bit as well, and if fin is set, it will be sent at the last so we
* need to update the tcp sequence number as per the last packet.
@@ -1031,71 +1079,6 @@
return 0;
}
-/* chcr_ktls_skb_shift - Shifts request length paged data from skb to another.
- * @tgt- buffer into which tail data gets added
- * @skb- buffer from which the paged data comes from
- * @shiftlen- shift up to this many bytes
- */
-static int chcr_ktls_skb_shift(struct sk_buff *tgt, struct sk_buff *skb,
- int shiftlen)
-{
- skb_frag_t *fragfrom, *fragto;
- int from, to, todo;
-
- WARN_ON(shiftlen > skb->data_len);
-
- todo = shiftlen;
- from = 0;
- to = 0;
- fragfrom = &skb_shinfo(skb)->frags[from];
-
- while ((todo > 0) && (from < skb_shinfo(skb)->nr_frags)) {
- fragfrom = &skb_shinfo(skb)->frags[from];
- fragto = &skb_shinfo(tgt)->frags[to];
-
- if (todo >= skb_frag_size(fragfrom)) {
- *fragto = *fragfrom;
- todo -= skb_frag_size(fragfrom);
- from++;
- to++;
-
- } else {
- __skb_frag_ref(fragfrom);
- skb_frag_page_copy(fragto, fragfrom);
- skb_frag_off_copy(fragto, fragfrom);
- skb_frag_size_set(fragto, todo);
-
- skb_frag_off_add(fragfrom, todo);
- skb_frag_size_sub(fragfrom, todo);
- todo = 0;
-
- to++;
- break;
- }
- }
-
- /* Ready to "commit" this state change to tgt */
- skb_shinfo(tgt)->nr_frags = to;
-
- /* Reposition in the original skb */
- to = 0;
- while (from < skb_shinfo(skb)->nr_frags)
- skb_shinfo(skb)->frags[to++] = skb_shinfo(skb)->frags[from++];
-
- skb_shinfo(skb)->nr_frags = to;
-
- WARN_ON(todo > 0 && !skb_shinfo(skb)->nr_frags);
-
- skb->len -= shiftlen;
- skb->data_len -= shiftlen;
- skb->truesize -= shiftlen;
- tgt->len += shiftlen;
- tgt->data_len += shiftlen;
- tgt->truesize += shiftlen;
-
- return shiftlen;
-}
-
/*
* chcr_ktls_xmit_wr_complete: This sends out the complete record. If an skb
* received has partial end part of the record, send out the complete record, so
@@ -1111,6 +1094,8 @@
static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb,
struct chcr_ktls_info *tx_info,
struct sge_eth_txq *q, u32 tcp_seq,
+ bool is_last_wr, u32 data_len,
+ u32 skb_offset, u32 nfrags,
bool tcp_push, u32 mss)
{
u32 len16, wr_mid = 0, flits = 0, ndesc, cipher_start;
@@ -1126,7 +1111,7 @@
u64 *end;
/* get the number of flits required */
- flits = chcr_ktls_get_tx_flits(skb, tx_info->key_ctx_len);
+ flits = chcr_ktls_get_tx_flits(nfrags, tx_info->key_ctx_len);
/* number of descriptors */
ndesc = chcr_flits_to_desc(flits);
/* check if enough credits available */
@@ -1155,6 +1140,9 @@
return NETDEV_TX_BUSY;
}
+ if (!is_last_wr)
+ skb_get(skb);
+
pos = &q->q.desc[q->q.pidx];
end = (u64 *)pos + flits;
/* FW_ULPTX_WR */
@@ -1187,7 +1175,7 @@
CPL_TX_SEC_PDU_CPLLEN_V(CHCR_CPL_TX_SEC_PDU_LEN_64BIT) |
CPL_TX_SEC_PDU_PLACEHOLDER_V(1) |
CPL_TX_SEC_PDU_IVINSRTOFST_V(TLS_HEADER_SIZE + 1));
- cpl->pldlen = htonl(skb->data_len);
+ cpl->pldlen = htonl(data_len);
/* encryption should start after tls header size + iv size */
cipher_start = TLS_HEADER_SIZE + tx_info->iv_size + 1;
@@ -1229,7 +1217,7 @@
/* CPL_TX_DATA */
tx_data = (void *)pos;
OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid));
- tx_data->len = htonl(TX_DATA_MSS_V(mss) | TX_LENGTH_V(skb->data_len));
+ tx_data->len = htonl(TX_DATA_MSS_V(mss) | TX_LENGTH_V(data_len));
tx_data->rsvd = htonl(tcp_seq);
@@ -1249,8 +1237,8 @@
}
/* send the complete packet except the header */
- cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len,
- sgl_sdesc->addr);
+ cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr,
+ skb_offset, data_len);
sgl_sdesc->skb = skb;
chcr_txq_advance(&q->q, ndesc);
@@ -1282,10 +1270,11 @@
struct sge_eth_txq *q,
u32 tcp_seq, bool tcp_push, u32 mss,
u32 tls_rec_offset, u8 *prior_data,
- u32 prior_data_len)
+ u32 prior_data_len, u32 data_len,
+ u32 skb_offset)
{
+ u32 len16, wr_mid = 0, cipher_start, nfrags;
struct adapter *adap = tx_info->adap;
- u32 len16, wr_mid = 0, cipher_start;
unsigned int flits = 0, ndesc;
int credits, left, last_desc;
struct tx_sw_desc *sgl_sdesc;
@@ -1298,10 +1287,11 @@
void *pos;
u64 *end;
+ nfrags = chcr_get_nfrags_to_send(skb, skb_offset, data_len);
/* get the number of flits required, it's a partial record so 2 flits
* (AES_BLOCK_SIZE) will be added.
*/
- flits = chcr_ktls_get_tx_flits(skb, tx_info->key_ctx_len) + 2;
+ flits = chcr_ktls_get_tx_flits(nfrags, tx_info->key_ctx_len) + 2;
/* get the correct 8 byte IV of this record */
iv_record = cpu_to_be64(tx_info->iv + tx_info->record_no);
/* If it's a middle record and not 16 byte aligned to run AES CTR, need
@@ -1373,7 +1363,7 @@
htonl(CPL_TX_SEC_PDU_OPCODE_V(CPL_TX_SEC_PDU) |
CPL_TX_SEC_PDU_CPLLEN_V(CHCR_CPL_TX_SEC_PDU_LEN_64BIT) |
CPL_TX_SEC_PDU_IVINSRTOFST_V(1));
- cpl->pldlen = htonl(skb->data_len + AES_BLOCK_LEN + prior_data_len);
+ cpl->pldlen = htonl(data_len + AES_BLOCK_LEN + prior_data_len);
cpl->aadstart_cipherstop_hi =
htonl(CPL_TX_SEC_PDU_CIPHERSTART_V(cipher_start));
cpl->cipherstop_lo_authinsert = 0;
@@ -1404,7 +1394,7 @@
tx_data = (void *)pos;
OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid));
tx_data->len = htonl(TX_DATA_MSS_V(mss) |
- TX_LENGTH_V(skb->data_len + prior_data_len));
+ TX_LENGTH_V(data_len + prior_data_len));
tx_data->rsvd = htonl(tcp_seq);
tx_data->flags = htonl(TX_BYPASS_F);
if (tcp_push)
@@ -1437,8 +1427,8 @@
if (prior_data_len)
pos = chcr_copy_to_txd(prior_data, &q->q, pos, 16);
/* send the complete packet except the header */
- cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len,
- sgl_sdesc->addr);
+ cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr,
+ skb_offset, data_len);
sgl_sdesc->skb = skb;
chcr_txq_advance(&q->q, ndesc);
@@ -1466,6 +1456,7 @@
struct sk_buff *skb, u32 tcp_seq, u32 mss,
bool tcp_push, struct sge_eth_txq *q,
u32 port_id, u8 *prior_data,
+ u32 data_len, u32 skb_offset,
u32 prior_data_len)
{
int credits, left, len16, last_desc;
@@ -1475,14 +1466,16 @@
struct ulptx_idata *idata;
struct ulp_txpkt *ulptx;
struct fw_ulptx_wr *wr;
- u32 wr_mid = 0;
+ u32 wr_mid = 0, nfrags;
void *pos;
u64 *end;
flits = DIV_ROUND_UP(CHCR_PLAIN_TX_DATA_LEN, 8);
- flits += chcr_sgl_len(skb_shinfo(skb)->nr_frags);
+ nfrags = chcr_get_nfrags_to_send(skb, skb_offset, data_len);
+ flits += chcr_sgl_len(nfrags);
if (prior_data_len)
flits += 2;
+
/* WR will need len16 */
len16 = DIV_ROUND_UP(flits, 2);
/* check how many descriptors needed */
@@ -1535,7 +1528,7 @@
tx_data = (struct cpl_tx_data *)(idata + 1);
OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid));
tx_data->len = htonl(TX_DATA_MSS_V(mss) |
- TX_LENGTH_V(skb->data_len + prior_data_len));
+ TX_LENGTH_V(data_len + prior_data_len));
/* set tcp seq number */
tx_data->rsvd = htonl(tcp_seq);
tx_data->flags = htonl(TX_BYPASS_F);
@@ -1559,8 +1552,8 @@
end = pos + left;
}
/* send the complete packet including the header */
- cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len,
- sgl_sdesc->addr);
+ cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr,
+ skb_offset, data_len);
sgl_sdesc->skb = skb;
chcr_txq_advance(&q->q, ndesc);
@@ -1568,12 +1561,96 @@
return 0;
}
+static int chcr_ktls_tunnel_pkt(struct chcr_ktls_info *tx_info,
+ struct sk_buff *skb,
+ struct sge_eth_txq *q)
+{
+ u32 ctrl, iplen, maclen, wr_mid = 0, len16;
+ struct tx_sw_desc *sgl_sdesc;
+ struct fw_eth_tx_pkt_wr *wr;
+ struct cpl_tx_pkt_core *cpl;
+ unsigned int flits, ndesc;
+ int credits, last_desc;
+ u64 cntrl1, *end;
+ void *pos;
+
+ ctrl = sizeof(*cpl);
+ flits = DIV_ROUND_UP(sizeof(*wr) + ctrl, 8);
+
+ flits += chcr_sgl_len(skb_shinfo(skb)->nr_frags + 1);
+ len16 = DIV_ROUND_UP(flits, 2);
+ /* check how many descriptors needed */
+ ndesc = DIV_ROUND_UP(flits, 8);
+
+ credits = chcr_txq_avail(&q->q) - ndesc;
+ if (unlikely(credits < 0)) {
+ chcr_eth_txq_stop(q);
+ return -ENOMEM;
+ }
+
+ if (unlikely(credits < ETHTXQ_STOP_THRES)) {
+ chcr_eth_txq_stop(q);
+ wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+ }
+
+ last_desc = q->q.pidx + ndesc - 1;
+ if (last_desc >= q->q.size)
+ last_desc -= q->q.size;
+ sgl_sdesc = &q->q.sdesc[last_desc];
+
+ if (unlikely(cxgb4_map_skb(tx_info->adap->pdev_dev, skb,
+ sgl_sdesc->addr) < 0)) {
+ memset(sgl_sdesc->addr, 0, sizeof(sgl_sdesc->addr));
+ q->mapping_err++;
+ return -ENOMEM;
+ }
+
+ iplen = skb_network_header_len(skb);
+ maclen = skb_mac_header_len(skb);
+
+ pos = &q->q.desc[q->q.pidx];
+ end = (u64 *)pos + flits;
+ wr = pos;
+
+ /* Firmware work request header */
+ wr->op_immdlen = htonl(FW_WR_OP_V(FW_ETH_TX_PKT_WR) |
+ FW_WR_IMMDLEN_V(ctrl));
+
+ wr->equiq_to_len16 = htonl(wr_mid | FW_WR_LEN16_V(len16));
+ wr->r3 = 0;
+
+ cpl = (void *)(wr + 1);
+
+ /* CPL header */
+ cpl->ctrl0 = htonl(TXPKT_OPCODE_V(CPL_TX_PKT) |
+ TXPKT_INTF_V(tx_info->tx_chan) |
+ TXPKT_PF_V(tx_info->adap->pf));
+ cpl->pack = 0;
+ cntrl1 = TXPKT_CSUM_TYPE_V(tx_info->ip_family == AF_INET ?
+ TX_CSUM_TCPIP : TX_CSUM_TCPIP6);
+ cntrl1 |= T6_TXPKT_ETHHDR_LEN_V(maclen - ETH_HLEN) |
+ TXPKT_IPHDR_LEN_V(iplen);
+ /* checksum offload */
+ cpl->ctrl1 = cpu_to_be64(cntrl1);
+ cpl->len = htons(skb->len);
+
+ pos = cpl + 1;
+
+ cxgb4_write_sgl(skb, &q->q, pos, end, 0, sgl_sdesc->addr);
+ sgl_sdesc->skb = skb;
+ chcr_txq_advance(&q->q, ndesc);
+ cxgb4_ring_tx_db(tx_info->adap, &q->q, ndesc);
+ return 0;
+}
+
/*
* chcr_ktls_copy_record_in_skb
* @nskb - new skb where the frags to be added.
+ * @skb - old skb, to copy socket and destructor details.
* @record - specific record which has complete 16k record in frags.
*/
static void chcr_ktls_copy_record_in_skb(struct sk_buff *nskb,
+ struct sk_buff *skb,
struct tls_record_info *record)
{
int i = 0;
@@ -1588,6 +1665,9 @@
nskb->data_len = record->len;
nskb->len += record->len;
nskb->truesize += record->len;
+ nskb->sk = skb->sk;
+ nskb->destructor = skb->destructor;
+ refcount_add(nskb->truesize, &nskb->sk->sk_wmem_alloc);
}
/*
@@ -1659,7 +1739,7 @@
struct sk_buff *skb,
struct tls_record_info *record,
u32 tcp_seq, int mss, bool tcp_push_no_fin,
- struct sge_eth_txq *q,
+ struct sge_eth_txq *q, u32 skb_offset,
u32 tls_end_offset, bool last_wr)
{
struct sk_buff *nskb = NULL;
@@ -1668,30 +1748,37 @@
nskb = skb;
atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_complete_pkts);
} else {
- dev_kfree_skb_any(skb);
-
- nskb = alloc_skb(0, GFP_KERNEL);
- if (!nskb)
+ nskb = alloc_skb(0, GFP_ATOMIC);
+ if (!nskb) {
+ dev_kfree_skb_any(skb);
return NETDEV_TX_BUSY;
+ }
+
/* copy complete record in skb */
- chcr_ktls_copy_record_in_skb(nskb, record);
+ chcr_ktls_copy_record_in_skb(nskb, skb, record);
/* packet is being sent from the beginning, update the tcp_seq
* accordingly.
*/
tcp_seq = tls_record_start_seq(record);
- /* reset snd una, so the middle record won't send the already
- * sent part.
- */
- if (chcr_ktls_update_snd_una(tx_info, q))
- goto out;
+ /* reset skb offset */
+ skb_offset = 0;
+
+ if (last_wr)
+ dev_kfree_skb_any(skb);
+
+ last_wr = true;
+
atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_end_pkts);
}
if (chcr_ktls_xmit_wr_complete(nskb, tx_info, q, tcp_seq,
+ last_wr, record->len, skb_offset,
+ record->num_frags,
(last_wr && tcp_push_no_fin),
mss)) {
goto out;
}
+ tx_info->prev_seq = record->end_seq;
return 0;
out:
dev_kfree_skb_any(nskb);
@@ -1723,41 +1810,47 @@
struct sk_buff *skb,
struct tls_record_info *record,
u32 tcp_seq, int mss, bool tcp_push_no_fin,
+ u32 data_len, u32 skb_offset,
struct sge_eth_txq *q, u32 tls_end_offset)
{
u32 tls_rec_offset = tcp_seq - tls_record_start_seq(record);
u8 prior_data[16] = {0};
u32 prior_data_len = 0;
- u32 data_len;
/* check if the skb is ending in middle of tag/HASH, its a big
* trouble, send the packet before the HASH.
*/
- int remaining_record = tls_end_offset - skb->data_len;
+ int remaining_record = tls_end_offset - data_len;
if (remaining_record > 0 &&
remaining_record < TLS_CIPHER_AES_GCM_128_TAG_SIZE) {
- int trimmed_len = skb->data_len -
- (TLS_CIPHER_AES_GCM_128_TAG_SIZE - remaining_record);
- struct sk_buff *tmp_skb = NULL;
- /* don't process the pkt if it is only a partial tag */
- if (skb->data_len < TLS_CIPHER_AES_GCM_128_TAG_SIZE)
- goto out;
+ int trimmed_len = 0;
- WARN_ON(trimmed_len > skb->data_len);
+ if (tls_end_offset > TLS_CIPHER_AES_GCM_128_TAG_SIZE)
+ trimmed_len = data_len -
+ (TLS_CIPHER_AES_GCM_128_TAG_SIZE -
+ remaining_record);
+ if (!trimmed_len)
+ return FALLBACK;
- /* shift to those many bytes */
- tmp_skb = alloc_skb(0, GFP_KERNEL);
- if (unlikely(!tmp_skb))
- goto out;
+ WARN_ON(trimmed_len > data_len);
- chcr_ktls_skb_shift(tmp_skb, skb, trimmed_len);
- /* free the last trimmed portion */
- dev_kfree_skb_any(skb);
- skb = tmp_skb;
+ data_len = trimmed_len;
atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_trimmed_pkts);
}
- data_len = skb->data_len;
+
+ /* check if it is only the header part. */
+ if (tls_rec_offset + data_len <= (TLS_HEADER_SIZE + tx_info->iv_size)) {
+ if (chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss,
+ tcp_push_no_fin, q,
+ tx_info->port_id, prior_data,
+ data_len, skb_offset, prior_data_len))
+ goto out;
+
+ tx_info->prev_seq = tcp_seq + data_len;
+ return 0;
+ }
+
/* check if the middle record's start point is 16 byte aligned. CTR
* needs 16 byte aligned start point to start encryption.
*/
@@ -1818,9 +1911,6 @@
}
/* reset tcp_seq as per the prior_data_required len */
tcp_seq -= prior_data_len;
- /* include prio_data_len for further calculation.
- */
- data_len += prior_data_len;
}
/* reset snd una, so the middle record won't send the already
* sent part.
@@ -1829,37 +1919,54 @@
goto out;
atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_middle_pkts);
} else {
- /* Else means, its a partial first part of the record. Check if
- * its only the header, don't need to send for encryption then.
- */
- if (data_len <= TLS_HEADER_SIZE + tx_info->iv_size) {
- if (chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss,
- tcp_push_no_fin, q,
- tx_info->port_id,
- prior_data,
- prior_data_len)) {
- goto out;
- }
- return 0;
- }
atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_start_pkts);
}
if (chcr_ktls_xmit_wr_short(skb, tx_info, q, tcp_seq, tcp_push_no_fin,
mss, tls_rec_offset, prior_data,
- prior_data_len)) {
+ prior_data_len, data_len, skb_offset)) {
goto out;
}
+ tx_info->prev_seq = tcp_seq + data_len + prior_data_len;
return 0;
out:
dev_kfree_skb_any(skb);
return NETDEV_TX_BUSY;
}
+static int chcr_ktls_sw_fallback(struct sk_buff *skb,
+ struct chcr_ktls_info *tx_info,
+ struct sge_eth_txq *q)
+{
+ u32 data_len, skb_offset;
+ struct sk_buff *nskb;
+ struct tcphdr *th;
+
+ nskb = tls_encrypt_skb(skb);
+
+ if (!nskb)
+ return 0;
+
+ th = tcp_hdr(nskb);
+ skb_offset = skb_transport_offset(nskb) + tcp_hdrlen(nskb);
+ data_len = nskb->len - skb_offset;
+ skb_tx_timestamp(nskb);
+
+ if (chcr_ktls_tunnel_pkt(tx_info, nskb, q))
+ goto out;
+
+ tx_info->prev_seq = ntohl(th->seq) + data_len;
+ atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_fallback);
+ return 0;
+out:
+ dev_kfree_skb_any(nskb);
+ return 0;
+}
/* nic tls TX handler */
static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev)
{
+ u32 tls_end_offset, tcp_seq, skb_data_len, skb_offset;
struct ch_ktls_port_stats_debug *port_stats;
struct chcr_ktls_ofld_ctx_tx *tx_ctx;
struct ch_ktls_stats_debug *stats;
@@ -1867,20 +1974,17 @@
int data_len, qidx, ret = 0, mss;
struct tls_record_info *record;
struct chcr_ktls_info *tx_info;
- u32 tls_end_offset, tcp_seq;
struct tls_context *tls_ctx;
- struct sk_buff *local_skb;
struct sge_eth_txq *q;
struct adapter *adap;
unsigned long flags;
tcp_seq = ntohl(th->seq);
+ skb_offset = skb_transport_offset(skb) + tcp_hdrlen(skb);
+ skb_data_len = skb->len - skb_offset;
+ data_len = skb_data_len;
- mss = skb_is_gso(skb) ? skb_shinfo(skb)->gso_size : skb->data_len;
-
- /* check if we haven't set it for ktls offload */
- if (!skb->sk || !tls_is_sk_tx_device_offloaded(skb->sk))
- goto out;
+ mss = skb_is_gso(skb) ? skb_shinfo(skb)->gso_size : data_len;
tls_ctx = tls_get_ctx(skb->sk);
if (unlikely(tls_ctx->netdev != dev))
@@ -1892,14 +1996,6 @@
if (unlikely(!tx_info))
goto out;
- /* don't touch the original skb, make a new skb to extract each records
- * and send them separately.
- */
- local_skb = alloc_skb(0, GFP_KERNEL);
-
- if (unlikely(!local_skb))
- return NETDEV_TX_BUSY;
-
adap = tx_info->adap;
stats = &adap->ch_ktls_stats;
port_stats = &stats->ktls_port[tx_info->port_id];
@@ -1914,20 +2010,7 @@
if (ret)
return NETDEV_TX_BUSY;
}
- /* update tcb */
- ret = chcr_ktls_xmit_tcb_cpls(tx_info, q, ntohl(th->seq),
- ntohl(th->ack_seq),
- ntohs(th->window));
- if (ret) {
- dev_kfree_skb_any(local_skb);
- return NETDEV_TX_BUSY;
- }
- /* copy skb contents into local skb */
- chcr_ktls_skb_copy(skb, local_skb);
-
- /* go through the skb and send only one record at a time. */
- data_len = skb->data_len;
/* TCP segments can be in received either complete or partial.
* chcr_end_part_handler will handle cases if complete record or end
* part of the record is received. Incase of partial end part of record,
@@ -1952,10 +2035,64 @@
goto out;
}
+ tls_end_offset = record->end_seq - tcp_seq;
+
+ pr_debug("seq 0x%x, end_seq 0x%x prev_seq 0x%x, datalen 0x%x\n",
+ tcp_seq, record->end_seq, tx_info->prev_seq, data_len);
+ /* update tcb for the skb */
+ if (skb_data_len == data_len) {
+ u32 tx_max = tcp_seq;
+
+ if (!tls_record_is_start_marker(record) &&
+ tls_end_offset < TLS_CIPHER_AES_GCM_128_TAG_SIZE)
+ tx_max = record->end_seq -
+ TLS_CIPHER_AES_GCM_128_TAG_SIZE;
+
+ ret = chcr_ktls_xmit_tcb_cpls(tx_info, q, tx_max,
+ ntohl(th->ack_seq),
+ ntohs(th->window),
+ tls_end_offset !=
+ record->len);
+ if (ret) {
+ spin_unlock_irqrestore(&tx_ctx->base.lock,
+ flags);
+ goto out;
+ }
+
+ if (th->fin)
+ skb_get(skb);
+ }
+
if (unlikely(tls_record_is_start_marker(record))) {
- spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
atomic64_inc(&port_stats->ktls_tx_skip_no_sync_data);
- goto out;
+ /* If tls_end_offset < data_len, means there is some
+ * data after start marker, which needs encryption, send
+ * plaintext first and take skb refcount. else send out
+ * complete pkt as plaintext.
+ */
+ if (tls_end_offset < data_len)
+ skb_get(skb);
+ else
+ tls_end_offset = data_len;
+
+ ret = chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss,
+ (!th->fin && th->psh), q,
+ tx_info->port_id, NULL,
+ tls_end_offset, skb_offset,
+ 0);
+
+ spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
+ if (ret) {
+ /* free the refcount taken earlier */
+ if (tls_end_offset < data_len)
+ dev_kfree_skb_any(skb);
+ goto out;
+ }
+
+ data_len -= tls_end_offset;
+ tcp_seq = record->end_seq;
+ skb_offset += tls_end_offset;
+ continue;
}
/* increase page reference count of the record, so that there
@@ -1967,73 +2104,64 @@
/* lock cleared */
spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
- tls_end_offset = record->end_seq - tcp_seq;
- pr_debug("seq 0x%x, end_seq 0x%x prev_seq 0x%x, datalen 0x%x\n",
- tcp_seq, record->end_seq, tx_info->prev_seq, data_len);
/* if a tls record is finishing in this SKB */
if (tls_end_offset <= data_len) {
- struct sk_buff *nskb = NULL;
-
- if (tls_end_offset < data_len) {
- nskb = alloc_skb(0, GFP_KERNEL);
- if (unlikely(!nskb)) {
- ret = -ENOMEM;
- goto clear_ref;
- }
-
- chcr_ktls_skb_shift(nskb, local_skb,
- tls_end_offset);
- } else {
- /* its the only record in this skb, directly
- * point it.
- */
- nskb = local_skb;
- }
- ret = chcr_end_part_handler(tx_info, nskb, record,
+ ret = chcr_end_part_handler(tx_info, skb, record,
tcp_seq, mss,
(!th->fin && th->psh), q,
+ skb_offset,
tls_end_offset,
- (nskb == local_skb));
-
- if (ret && nskb != local_skb)
- dev_kfree_skb_any(local_skb);
+ skb_offset +
+ tls_end_offset == skb->len);
data_len -= tls_end_offset;
/* tcp_seq increment is required to handle next record.
*/
tcp_seq += tls_end_offset;
+ skb_offset += tls_end_offset;
} else {
- ret = chcr_short_record_handler(tx_info, local_skb,
+ ret = chcr_short_record_handler(tx_info, skb,
record, tcp_seq, mss,
(!th->fin && th->psh),
+ data_len, skb_offset,
q, tls_end_offset);
data_len = 0;
}
-clear_ref:
+
/* clear the frag ref count which increased locally before */
for (i = 0; i < record->num_frags; i++) {
/* clear the frag ref count */
__skb_frag_unref(&record->frags[i]);
}
/* if any failure, come out from the loop. */
- if (ret)
- goto out;
+ if (ret) {
+ if (th->fin)
+ dev_kfree_skb_any(skb);
+
+ if (ret == FALLBACK)
+ return chcr_ktls_sw_fallback(skb, tx_info, q);
+
+ return NETDEV_TX_OK;
+ }
+
/* length should never be less than 0 */
WARN_ON(data_len < 0);
} while (data_len > 0);
- tx_info->prev_seq = ntohl(th->seq) + skb->data_len;
atomic64_inc(&port_stats->ktls_tx_encrypted_packets);
- atomic64_add(skb->data_len, &port_stats->ktls_tx_encrypted_bytes);
+ atomic64_add(skb_data_len, &port_stats->ktls_tx_encrypted_bytes);
/* tcp finish is set, send a separate tcp msg including all the options
* as well.
*/
- if (th->fin)
+ if (th->fin) {
chcr_ktls_write_tcp_options(tx_info, skb, q, tx_info->tx_chan);
+ dev_kfree_skb_any(skb);
+ }
+ return NETDEV_TX_OK;
out:
dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h
index c1651b1..18b3b1f 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h
@@ -26,6 +26,7 @@
#define CHCR_KTLS_WR_SIZE (CHCR_PLAIN_TX_DATA_LEN +\
sizeof(struct cpl_tx_sec_pdu))
+#define FALLBACK 35
enum ch_ktls_open_state {
CH_KTLS_OPEN_SUCCESS = 0,
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
index ec4f790..96d5616 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
@@ -212,7 +212,7 @@
{
if (likely(skb && !skb_shared(skb) && !skb_cloned(skb))) {
__skb_trim(skb, 0);
- refcount_add(2, &skb->users);
+ refcount_inc(&skb->users);
} else {
skb = alloc_skb(len, GFP_KERNEL | __GFP_NOFAIL);
}
@@ -772,14 +772,13 @@
if (rpl->status != CPL_ERR_NONE) {
pr_info("Unexpected PASS_OPEN_RPL status %u for STID %u\n",
rpl->status, stid);
- return CPL_RET_BUF_DONE;
+ } else {
+ cxgb4_free_stid(cdev->tids, stid, listen_ctx->lsk->sk_family);
+ sock_put(listen_ctx->lsk);
+ kfree(listen_ctx);
+ module_put(THIS_MODULE);
}
- cxgb4_free_stid(cdev->tids, stid, listen_ctx->lsk->sk_family);
- sock_put(listen_ctx->lsk);
- kfree(listen_ctx);
- module_put(THIS_MODULE);
-
- return 0;
+ return CPL_RET_BUF_DONE;
}
static int chtls_close_listsrv_rpl(struct chtls_dev *cdev, struct sk_buff *skb)
@@ -796,15 +795,13 @@
if (rpl->status != CPL_ERR_NONE) {
pr_info("Unexpected CLOSE_LISTSRV_RPL status %u for STID %u\n",
rpl->status, stid);
- return CPL_RET_BUF_DONE;
+ } else {
+ cxgb4_free_stid(cdev->tids, stid, listen_ctx->lsk->sk_family);
+ sock_put(listen_ctx->lsk);
+ kfree(listen_ctx);
+ module_put(THIS_MODULE);
}
-
- cxgb4_free_stid(cdev->tids, stid, listen_ctx->lsk->sk_family);
- sock_put(listen_ctx->lsk);
- kfree(listen_ctx);
- module_put(THIS_MODULE);
-
- return 0;
+ return CPL_RET_BUF_DONE;
}
static void chtls_purge_wr_queue(struct sock *sk)
@@ -1514,7 +1511,6 @@
struct chtls_sock *csk = sk->sk_user_data;
local_bh_disable();
- bh_lock_sock(sk);
release_tcp_port(sk); /* release the port immediately */
spin_lock(&reap_list_lock);
@@ -1523,7 +1519,6 @@
if (!csk->passive_reap_next)
schedule_work(&reap_task);
spin_unlock(&reap_list_lock);
- bh_unlock_sock(sk);
local_bh_enable();
}
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c
index f1820ac..62c8290 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c
@@ -383,6 +383,9 @@
if (ret)
goto out_notcb;
+ if (unlikely(csk_flag(sk, CSK_ABORT_SHUTDOWN)))
+ goto out_notcb;
+
set_wr_txq(skb, CPL_PRIORITY_DATA, csk->tlshws.txqid);
csk->wr_credits -= DIV_ROUND_UP(len, 16);
csk->wr_unacked += DIV_ROUND_UP(len, 16);
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
index 9fb5ca6..188d871 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
@@ -1585,6 +1585,7 @@
tp->urg_data = 0;
if ((avail + offset) >= skb->len) {
+ struct sk_buff *next_skb;
if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_TLS_HDR) {
tp->copied_seq += skb->len;
hws->rcvpld = skb->hdr_len;
@@ -1595,8 +1596,10 @@
chtls_free_skb(sk, skb);
buffers_freed++;
hws->copied_seq = 0;
- if (copied >= target &&
- !skb_peek(&sk->sk_receive_queue))
+ next_skb = skb_peek(&sk->sk_receive_queue);
+ if (copied >= target && !next_skb)
+ break;
+ if (ULP_SKB_CB(next_skb)->flags & ULPCB_FLAG_TLS_HDR)
break;
}
} while (len > 0);
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 00024dd..80fb1f5 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -1907,6 +1907,8 @@
clk_disable_unprepare(priv->rclk);
clk_disable_unprepare(priv->clk);
err_ncsi_dev:
+ if (priv->ndev)
+ ncsi_unregister_dev(priv->ndev);
ftgmac100_destroy_mdio(netdev);
err_setup_mdio:
iounmap(priv->base);
@@ -1926,6 +1928,8 @@
netdev = platform_get_drvdata(pdev);
priv = netdev_priv(netdev);
+ if (priv->ndev)
+ ncsi_unregister_dev(priv->ndev);
unregister_netdev(netdev);
clk_disable_unprepare(priv->rclk);
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 06cc863..d9c2859 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -174,12 +174,17 @@
#define DPAA_PARSE_RESULTS_SIZE sizeof(struct fman_prs_result)
#define DPAA_TIME_STAMP_SIZE 8
#define DPAA_HASH_RESULTS_SIZE 8
-#ifdef CONFIG_DPAA_ERRATUM_A050385
-#define DPAA_RX_PRIV_DATA_SIZE (DPAA_A050385_ALIGN - (DPAA_PARSE_RESULTS_SIZE\
- + DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE))
-#else
-#define DPAA_RX_PRIV_DATA_SIZE (u16)(DPAA_TX_PRIV_DATA_SIZE + \
+#define DPAA_HWA_SIZE (DPAA_PARSE_RESULTS_SIZE + DPAA_TIME_STAMP_SIZE \
+ + DPAA_HASH_RESULTS_SIZE)
+#define DPAA_RX_PRIV_DATA_DEFAULT_SIZE (DPAA_TX_PRIV_DATA_SIZE + \
dpaa_rx_extra_headroom)
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+#define DPAA_RX_PRIV_DATA_A050385_SIZE (DPAA_A050385_ALIGN - DPAA_HWA_SIZE)
+#define DPAA_RX_PRIV_DATA_SIZE (fman_has_errata_a050385() ? \
+ DPAA_RX_PRIV_DATA_A050385_SIZE : \
+ DPAA_RX_PRIV_DATA_DEFAULT_SIZE)
+#else
+#define DPAA_RX_PRIV_DATA_SIZE DPAA_RX_PRIV_DATA_DEFAULT_SIZE
#endif
#define DPAA_ETH_PCD_RXQ_NUM 128
@@ -2840,7 +2845,8 @@
return err;
}
-static inline u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl)
+static u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl,
+ enum port_type port)
{
u16 headroom;
@@ -2854,10 +2860,12 @@
*
* Also make sure the headroom is a multiple of data_align bytes
*/
- headroom = (u16)(bl->priv_data_size + DPAA_PARSE_RESULTS_SIZE +
- DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE);
+ headroom = (u16)(bl[port].priv_data_size + DPAA_HWA_SIZE);
- return ALIGN(headroom, DPAA_FD_DATA_ALIGNMENT);
+ if (port == RX)
+ return ALIGN(headroom, DPAA_FD_RX_DATA_ALIGNMENT);
+ else
+ return ALIGN(headroom, DPAA_FD_DATA_ALIGNMENT);
}
static int dpaa_eth_probe(struct platform_device *pdev)
@@ -3025,8 +3033,8 @@
goto free_dpaa_fqs;
}
- priv->tx_headroom = dpaa_get_headroom(&priv->buf_layout[TX]);
- priv->rx_headroom = dpaa_get_headroom(&priv->buf_layout[RX]);
+ priv->tx_headroom = dpaa_get_headroom(priv->buf_layout, TX);
+ priv->rx_headroom = dpaa_get_headroom(priv->buf_layout, RX);
/* All real interfaces need their ports initialized */
err = dpaa_eth_init_ports(mac_dev, dpaa_bp, &port_fqs,
diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig
index 0fa18b0..d99ea0f 100644
--- a/drivers/net/ethernet/freescale/enetc/Kconfig
+++ b/drivers/net/ethernet/freescale/enetc/Kconfig
@@ -16,6 +16,7 @@
config FSL_ENETC_VF
tristate "ENETC VF driver"
depends on PCI && PCI_MSI
+ select FSL_ENETC_MDIO
select PHYLINK
select DIMLIB
help
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 52be6e3..fc2075e 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -33,7 +33,10 @@
return NETDEV_TX_BUSY;
}
+ enetc_lock_mdio();
count = enetc_map_tx_buffs(tx_ring, skb, priv->active_offloads);
+ enetc_unlock_mdio();
+
if (unlikely(!count))
goto drop_packet_err;
@@ -239,7 +242,7 @@
skb_tx_timestamp(skb);
/* let H/W know BD ring has been updated */
- enetc_wr_reg(tx_ring->tpir, i); /* includes wmb() */
+ enetc_wr_reg_hot(tx_ring->tpir, i); /* includes wmb() */
return count;
@@ -262,12 +265,16 @@
struct enetc_int_vector *v = data;
int i;
+ enetc_lock_mdio();
+
/* disable interrupts */
- enetc_wr_reg(v->rbier, 0);
- enetc_wr_reg(v->ricr1, v->rx_ictt);
+ enetc_wr_reg_hot(v->rbier, 0);
+ enetc_wr_reg_hot(v->ricr1, v->rx_ictt);
for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS)
- enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i), 0);
+ enetc_wr_reg_hot(v->tbier_base + ENETC_BDR_OFF(i), 0);
+
+ enetc_unlock_mdio();
napi_schedule(&v->napi);
@@ -334,19 +341,23 @@
v->rx_napi_work = false;
+ enetc_lock_mdio();
+
/* enable interrupts */
- enetc_wr_reg(v->rbier, ENETC_RBIER_RXTIE);
+ enetc_wr_reg_hot(v->rbier, ENETC_RBIER_RXTIE);
for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS)
- enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i),
- ENETC_TBIER_TXTIE);
+ enetc_wr_reg_hot(v->tbier_base + ENETC_BDR_OFF(i),
+ ENETC_TBIER_TXTIE);
+
+ enetc_unlock_mdio();
return work_done;
}
static int enetc_bd_ready_count(struct enetc_bdr *tx_ring, int ci)
{
- int pi = enetc_rd_reg(tx_ring->tcir) & ENETC_TBCIR_IDX_MASK;
+ int pi = enetc_rd_reg_hot(tx_ring->tcir) & ENETC_TBCIR_IDX_MASK;
return pi >= ci ? pi - ci : tx_ring->bd_count - ci + pi;
}
@@ -386,7 +397,10 @@
i = tx_ring->next_to_clean;
tx_swbd = &tx_ring->tx_swbd[i];
+
+ enetc_lock_mdio();
bds_to_clean = enetc_bd_ready_count(tx_ring, i);
+ enetc_unlock_mdio();
do_tstamp = false;
@@ -429,16 +443,20 @@
tx_swbd = tx_ring->tx_swbd;
}
+ enetc_lock_mdio();
+
/* BD iteration loop end */
if (is_eof) {
tx_frm_cnt++;
/* re-arm interrupt source */
- enetc_wr_reg(tx_ring->idr, BIT(tx_ring->index) |
- BIT(16 + tx_ring->index));
+ enetc_wr_reg_hot(tx_ring->idr, BIT(tx_ring->index) |
+ BIT(16 + tx_ring->index));
}
if (unlikely(!bds_to_clean))
bds_to_clean = enetc_bd_ready_count(tx_ring, i);
+
+ enetc_unlock_mdio();
}
tx_ring->next_to_clean = i;
@@ -515,8 +533,6 @@
if (likely(j)) {
rx_ring->next_to_alloc = i; /* keep track from page reuse */
rx_ring->next_to_use = i;
- /* update ENETC's consumer index */
- enetc_wr_reg(rx_ring->rcir, i);
}
return j;
@@ -534,8 +550,8 @@
u64 tstamp;
if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_TSTMP) {
- lo = enetc_rd(hw, ENETC_SICTR0);
- hi = enetc_rd(hw, ENETC_SICTR1);
+ lo = enetc_rd_reg_hot(hw->reg + ENETC_SICTR0);
+ hi = enetc_rd_reg_hot(hw->reg + ENETC_SICTR1);
rxbd = enetc_rxbd_ext(rxbd);
tstamp_lo = le32_to_cpu(rxbd->ext.tstamp);
if (lo <= tstamp_lo)
@@ -684,23 +700,31 @@
u32 bd_status;
u16 size;
+ enetc_lock_mdio();
+
if (cleaned_cnt >= ENETC_RXBD_BUNDLE) {
int count = enetc_refill_rx_ring(rx_ring, cleaned_cnt);
+ /* update ENETC's consumer index */
+ enetc_wr_reg_hot(rx_ring->rcir, rx_ring->next_to_use);
cleaned_cnt -= count;
}
rxbd = enetc_rxbd(rx_ring, i);
bd_status = le32_to_cpu(rxbd->r.lstatus);
- if (!bd_status)
+ if (!bd_status) {
+ enetc_unlock_mdio();
break;
+ }
- enetc_wr_reg(rx_ring->idr, BIT(rx_ring->index));
+ enetc_wr_reg_hot(rx_ring->idr, BIT(rx_ring->index));
dma_rmb(); /* for reading other rxbd fields */
size = le16_to_cpu(rxbd->r.buf_len);
skb = enetc_map_rx_buff_to_skb(rx_ring, i, size);
- if (!skb)
+ if (!skb) {
+ enetc_unlock_mdio();
break;
+ }
enetc_get_offloads(rx_ring, rxbd, skb);
@@ -712,6 +736,7 @@
if (unlikely(bd_status &
ENETC_RXBD_LSTATUS(ENETC_RXBD_ERR_MASK))) {
+ enetc_unlock_mdio();
dev_kfree_skb(skb);
while (!(bd_status & ENETC_RXBD_LSTATUS_F)) {
dma_rmb();
@@ -751,6 +776,8 @@
enetc_process_skb(rx_ring, skb);
+ enetc_unlock_mdio();
+
napi_gro_receive(napi, skb);
rx_frm_cnt++;
@@ -1225,6 +1252,7 @@
rx_ring->idr = hw->reg + ENETC_SIRXIDR;
enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring));
+ enetc_wr(hw, ENETC_SIRXIDR, rx_ring->next_to_use);
/* enable ring */
enetc_rxbdr_wr(hw, idx, ENETC_RBMR, rbmr);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index 17cf7c9..eb6bbf1 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -324,14 +324,100 @@
void __iomem *global;
};
-/* general register accessors */
-#define enetc_rd_reg(reg) ioread32((reg))
-#define enetc_wr_reg(reg, val) iowrite32((val), (reg))
+/* ENETC register accessors */
+
+/* MDIO issue workaround (on LS1028A) -
+ * Due to a hardware issue, an access to MDIO registers
+ * that is concurrent with other ENETC register accesses
+ * may lead to the MDIO access being dropped or corrupted.
+ * To protect the MDIO accesses a readers-writers locking
+ * scheme is used, where the MDIO register accesses are
+ * protected by write locks to insure exclusivity, while
+ * the remaining ENETC registers are accessed under read
+ * locks since they only compete with MDIO accesses.
+ */
+extern rwlock_t enetc_mdio_lock;
+
+/* use this locking primitive only on the fast datapath to
+ * group together multiple non-MDIO register accesses to
+ * minimize the overhead of the lock
+ */
+static inline void enetc_lock_mdio(void)
+{
+ read_lock(&enetc_mdio_lock);
+}
+
+static inline void enetc_unlock_mdio(void)
+{
+ read_unlock(&enetc_mdio_lock);
+}
+
+/* use these accessors only on the fast datapath under
+ * the enetc_lock_mdio() locking primitive to minimize
+ * the overhead of the lock
+ */
+static inline u32 enetc_rd_reg_hot(void __iomem *reg)
+{
+ lockdep_assert_held(&enetc_mdio_lock);
+
+ return ioread32(reg);
+}
+
+static inline void enetc_wr_reg_hot(void __iomem *reg, u32 val)
+{
+ lockdep_assert_held(&enetc_mdio_lock);
+
+ iowrite32(val, reg);
+}
+
+/* internal helpers for the MDIO w/a */
+static inline u32 _enetc_rd_reg_wa(void __iomem *reg)
+{
+ u32 val;
+
+ enetc_lock_mdio();
+ val = ioread32(reg);
+ enetc_unlock_mdio();
+
+ return val;
+}
+
+static inline void _enetc_wr_reg_wa(void __iomem *reg, u32 val)
+{
+ enetc_lock_mdio();
+ iowrite32(val, reg);
+ enetc_unlock_mdio();
+}
+
+static inline u32 _enetc_rd_mdio_reg_wa(void __iomem *reg)
+{
+ unsigned long flags;
+ u32 val;
+
+ write_lock_irqsave(&enetc_mdio_lock, flags);
+ val = ioread32(reg);
+ write_unlock_irqrestore(&enetc_mdio_lock, flags);
+
+ return val;
+}
+
+static inline void _enetc_wr_mdio_reg_wa(void __iomem *reg, u32 val)
+{
+ unsigned long flags;
+
+ write_lock_irqsave(&enetc_mdio_lock, flags);
+ iowrite32(val, reg);
+ write_unlock_irqrestore(&enetc_mdio_lock, flags);
+}
+
#ifdef ioread64
-#define enetc_rd_reg64(reg) ioread64((reg))
+static inline u64 _enetc_rd_reg64(void __iomem *reg)
+{
+ return ioread64(reg);
+}
#else
/* using this to read out stats on 32b systems */
-static inline u64 enetc_rd_reg64(void __iomem *reg)
+static inline u64 _enetc_rd_reg64(void __iomem *reg)
{
u32 low, high, tmp;
@@ -345,12 +431,29 @@
}
#endif
+static inline u64 _enetc_rd_reg64_wa(void __iomem *reg)
+{
+ u64 val;
+
+ enetc_lock_mdio();
+ val = _enetc_rd_reg64(reg);
+ enetc_unlock_mdio();
+
+ return val;
+}
+
+/* general register accessors */
+#define enetc_rd_reg(reg) _enetc_rd_reg_wa((reg))
+#define enetc_wr_reg(reg, val) _enetc_wr_reg_wa((reg), (val))
#define enetc_rd(hw, off) enetc_rd_reg((hw)->reg + (off))
#define enetc_wr(hw, off, val) enetc_wr_reg((hw)->reg + (off), val)
-#define enetc_rd64(hw, off) enetc_rd_reg64((hw)->reg + (off))
+#define enetc_rd64(hw, off) _enetc_rd_reg64_wa((hw)->reg + (off))
/* port register accessors - PF only */
#define enetc_port_rd(hw, off) enetc_rd_reg((hw)->port + (off))
#define enetc_port_wr(hw, off, val) enetc_wr_reg((hw)->port + (off), val)
+#define enetc_port_rd_mdio(hw, off) _enetc_rd_mdio_reg_wa((hw)->port + (off))
+#define enetc_port_wr_mdio(hw, off, val) _enetc_wr_mdio_reg_wa(\
+ (hw)->port + (off), val)
/* global register accessors - PF only */
#define enetc_global_rd(hw, off) enetc_rd_reg((hw)->global + (off))
#define enetc_global_wr(hw, off, val) enetc_wr_reg((hw)->global + (off), val)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c
index 48c32a1..ee0116e 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c
@@ -16,13 +16,13 @@
static inline u32 _enetc_mdio_rd(struct enetc_mdio_priv *mdio_priv, int off)
{
- return enetc_port_rd(mdio_priv->hw, mdio_priv->mdio_base + off);
+ return enetc_port_rd_mdio(mdio_priv->hw, mdio_priv->mdio_base + off);
}
static inline void _enetc_mdio_wr(struct enetc_mdio_priv *mdio_priv, int off,
u32 val)
{
- enetc_port_wr(mdio_priv->hw, mdio_priv->mdio_base + off, val);
+ enetc_port_wr_mdio(mdio_priv->hw, mdio_priv->mdio_base + off, val);
}
#define enetc_mdio_rd(mdio_priv, off) \
@@ -174,3 +174,7 @@
return hw;
}
EXPORT_SYMBOL_GPL(enetc_hw_alloc);
+
+/* Lock for MDIO access errata on LS1028A */
+DEFINE_RWLOCK(enetc_mdio_lock);
+EXPORT_SYMBOL_GPL(enetc_mdio_lock);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
index c81be32..827f74e 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
@@ -402,7 +402,7 @@
u32 num_entries;
refcount_t refcount;
struct hlist_node node;
- struct action_gate_entry entries[0];
+ struct action_gate_entry entries[];
};
/* Only enable the green color frame now
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 832a2175..c527f4e 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -456,6 +456,12 @@
*/
#define FEC_QUIRK_HAS_FRREG (1 << 16)
+/* Some FEC hardware blocks need the MMFR cleared at setup time to avoid
+ * the generation of an MII event. This must be avoided in the older
+ * FEC blocks where it will stop MII events being generated.
+ */
+#define FEC_QUIRK_CLEAR_SETUP_MII (1 << 17)
+
struct bufdesc_prop {
int qid;
/* Address of Rx and Tx buffers */
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 8f7eca1..04f24c6 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -100,14 +100,14 @@
static const struct fec_devinfo fec_imx28_info = {
.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME |
FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC |
- FEC_QUIRK_HAS_FRREG,
+ FEC_QUIRK_HAS_FRREG | FEC_QUIRK_CLEAR_SETUP_MII,
};
static const struct fec_devinfo fec_imx6q_info = {
.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 |
- FEC_QUIRK_HAS_RACC,
+ FEC_QUIRK_HAS_RACC | FEC_QUIRK_CLEAR_SETUP_MII,
};
static const struct fec_devinfo fec_mvf600_info = {
@@ -119,7 +119,8 @@
FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB |
FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE |
- FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE,
+ FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE |
+ FEC_QUIRK_CLEAR_SETUP_MII,
};
static const struct fec_devinfo fec_imx6ul_info = {
@@ -127,7 +128,7 @@
FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR007885 |
FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC |
- FEC_QUIRK_HAS_COALESCE,
+ FEC_QUIRK_HAS_COALESCE | FEC_QUIRK_CLEAR_SETUP_MII,
};
static struct platform_device_id fec_devtype[] = {
@@ -1807,7 +1808,7 @@
int ret = 0, frame_start, frame_addr, frame_op;
bool is_c45 = !!(regnum & MII_ADDR_C45);
- ret = pm_runtime_get_sync(dev);
+ ret = pm_runtime_resume_and_get(dev);
if (ret < 0)
return ret;
@@ -1866,11 +1867,9 @@
int ret, frame_start, frame_addr;
bool is_c45 = !!(regnum & MII_ADDR_C45);
- ret = pm_runtime_get_sync(dev);
+ ret = pm_runtime_resume_and_get(dev);
if (ret < 0)
return ret;
- else
- ret = 0;
if (is_c45) {
frame_start = FEC_MMFR_ST_C45;
@@ -2134,15 +2133,17 @@
if (suppress_preamble)
fep->phy_speed |= BIT(7);
- /* Clear MMFR to avoid to generate MII event by writing MSCR.
- * MII event generation condition:
- * - writing MSCR:
- * - mmfr[31:0]_not_zero & mscr[7:0]_is_zero &
- * mscr_reg_data_in[7:0] != 0
- * - writing MMFR:
- * - mscr[7:0]_not_zero
- */
- writel(0, fep->hwp + FEC_MII_DATA);
+ if (fep->quirks & FEC_QUIRK_CLEAR_SETUP_MII) {
+ /* Clear MMFR to avoid to generate MII event by writing MSCR.
+ * MII event generation condition:
+ * - writing MSCR:
+ * - mmfr[31:0]_not_zero & mscr[7:0]_is_zero &
+ * mscr_reg_data_in[7:0] != 0
+ * - writing MMFR:
+ * - mscr[7:0]_not_zero
+ */
+ writel(0, fep->hwp + FEC_MII_DATA);
+ }
writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
@@ -2272,7 +2273,7 @@
u32 i, off;
int ret;
- ret = pm_runtime_get_sync(dev);
+ ret = pm_runtime_resume_and_get(dev);
if (ret < 0)
return;
@@ -2973,7 +2974,7 @@
int ret;
bool reset_again;
- ret = pm_runtime_get_sync(&fep->pdev->dev);
+ ret = pm_runtime_resume_and_get(&fep->pdev->dev);
if (ret < 0)
return ret;
@@ -3767,7 +3768,7 @@
struct device_node *np = pdev->dev.of_node;
int ret;
- ret = pm_runtime_get_sync(&pdev->dev);
+ ret = pm_runtime_resume_and_get(&pdev->dev);
if (ret < 0)
return ret;
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 41dd3d0..d391a45 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -1829,20 +1829,12 @@
fcb_len = GMAC_FCB_LEN + GMAC_TXPAL_LEN;
/* make space for additional header when fcb is needed */
- if (fcb_len && unlikely(skb_headroom(skb) < fcb_len)) {
- struct sk_buff *skb_new;
-
- skb_new = skb_realloc_headroom(skb, fcb_len);
- if (!skb_new) {
+ if (fcb_len) {
+ if (unlikely(skb_cow_head(skb, fcb_len))) {
dev->stats.tx_errors++;
dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
-
- if (skb->sk)
- skb_set_owner_w(skb_new, skb->sk);
- dev_consume_skb_any(skb);
- skb = skb_new;
}
/* total number of fragments in the SKB */
@@ -3380,7 +3372,7 @@
if (dev->features & NETIF_F_IP_CSUM ||
priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER)
- dev->needed_headroom = GMAC_FCB_LEN;
+ dev->needed_headroom = GMAC_FCB_LEN + GMAC_TXPAL_LEN;
/* Initializing some of the rx/tx queue level parameters */
for (i = 0; i < priv->num_tx_queues; i++) {
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 714b501..ba8869c 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -1358,7 +1358,7 @@
(ugeth->phy_interface == PHY_INTERFACE_MODE_RTBI)) {
upsmr |= UCC_GETH_UPSMR_TBIM;
}
- if ((ugeth->phy_interface == PHY_INTERFACE_MODE_SGMII))
+ if (ugeth->phy_interface == PHY_INTERFACE_MODE_SGMII)
upsmr |= UCC_GETH_UPSMR_SGMM;
out_be32(&uf_regs->upsmr, upsmr);
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h
index 281de83..015796a 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.h
+++ b/drivers/net/ethernet/google/gve/gve_adminq.h
@@ -198,7 +198,7 @@
struct gve_stats_report {
__be64 written_count;
- struct stats stats[0];
+ struct stats stats[];
};
static_assert(sizeof(struct gve_stats_report) == 8);
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 48a4331..02e7d74 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -116,9 +116,8 @@
priv->tx_cfg.num_queues;
rx_stats_num = (GVE_RX_STATS_REPORT_NUM + NIC_RX_STATS_REPORT_NUM) *
priv->rx_cfg.num_queues;
- priv->stats_report_len = sizeof(struct gve_stats_report) +
- (tx_stats_num + rx_stats_num) *
- sizeof(struct stats);
+ priv->stats_report_len = struct_size(priv->stats_report, stats,
+ tx_stats_num + rx_stats_num);
priv->stats_report =
dma_alloc_coherent(&priv->pdev->dev, priv->stats_report_len,
&priv->stats_report_bus, GFP_KERNEL);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 15f69fa..e8495f5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -1373,7 +1373,7 @@
return ret;
}
- return ret;
+ return 0;
}
int hclge_pause_setup_hw(struct hclge_dev *hdev, bool init)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 50c84c5..c8e3fdd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -3262,8 +3262,8 @@
hclgevf_uninit_msi(hdev);
}
- hclgevf_pci_uninit(hdev);
hclgevf_cmd_uninit(hdev);
+ hclgevf_pci_uninit(hdev);
hclgevf_uninit_mac_list(hdev);
}
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 7ef3369..c3ec9ce 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1031,12 +1031,6 @@
ret = -EOPNOTSUPP;
}
- if (!ether_addr_equal(ether_header->h_source, netdev->dev_addr)) {
- netdev_dbg(netdev, "source packet MAC address does not match veth device's, dropping packet.\n");
- netdev->stats.tx_dropped++;
- ret = -EOPNOTSUPP;
- }
-
return ret;
}
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 8148f79..da15913 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1185,18 +1185,27 @@
if (adapter->state != VNIC_CLOSED) {
rc = ibmvnic_login(netdev);
if (rc)
- return rc;
+ goto out;
rc = init_resources(adapter);
if (rc) {
netdev_err(netdev, "failed to initialize resources\n");
release_resources(adapter);
- return rc;
+ goto out;
}
}
rc = __ibmvnic_open(netdev);
+out:
+ /*
+ * If open fails due to a pending failover, set device state and
+ * return. Device operation will be handled by reset routine.
+ */
+ if (rc && adapter->failover_pending) {
+ adapter->state = VNIC_OPEN;
+ rc = 0;
+ }
return rc;
}
@@ -1815,9 +1824,13 @@
int rc;
rc = 0;
- ether_addr_copy(adapter->mac_addr, addr->sa_data);
- if (adapter->state != VNIC_PROBED)
+ if (!is_valid_ether_addr(addr->sa_data))
+ return -EADDRNOTAVAIL;
+
+ if (adapter->state != VNIC_PROBED) {
+ ether_addr_copy(adapter->mac_addr, addr->sa_data);
rc = __ibmvnic_set_mac(netdev, addr->sa_data);
+ }
return rc;
}
@@ -1918,6 +1931,13 @@
rwi->reset_reason);
rtnl_lock();
+ /*
+ * Now that we have the rtnl lock, clear any pending failover.
+ * This will ensure ibmvnic_open() has either completed or will
+ * block until failover is complete.
+ */
+ if (rwi->reset_reason == VNIC_RESET_FAILOVER)
+ adapter->failover_pending = false;
netif_carrier_off(netdev);
adapter->reset_reason = rwi->reset_reason;
@@ -2198,6 +2218,13 @@
/* CHANGE_PARAM requestor holds rtnl_lock */
rc = do_change_param_reset(adapter, rwi, reset_state);
} else if (adapter->force_reset_recovery) {
+ /*
+ * Since we are doing a hard reset now, clear the
+ * failover_pending flag so we don't ignore any
+ * future MOBILITY or other resets.
+ */
+ adapter->failover_pending = false;
+
/* Transport event occurred during previous reset */
if (adapter->wait_for_reset) {
/* Previous was CHANGE_PARAM; caller locked */
@@ -2262,9 +2289,15 @@
unsigned long flags;
int ret;
+ /*
+ * If failover is pending don't schedule any other reset.
+ * Instead let the failover complete. If there is already a
+ * a failover reset scheduled, we will detect and drop the
+ * duplicate reset when walking the ->rwi_list below.
+ */
if (adapter->state == VNIC_REMOVING ||
adapter->state == VNIC_REMOVED ||
- adapter->failover_pending) {
+ (adapter->failover_pending && reason != VNIC_RESET_FAILOVER)) {
ret = EBUSY;
netdev_dbg(netdev, "Adapter removing or pending failover, skipping reset\n");
goto err;
@@ -4709,7 +4742,6 @@
case IBMVNIC_CRQ_INIT:
dev_info(dev, "Partner initialized\n");
adapter->from_passive_init = true;
- adapter->failover_pending = false;
if (!completion_done(&adapter->init_done)) {
complete(&adapter->init_done);
adapter->init_done_rc = -EIO;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index c96e2f2..4919d22d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -2713,6 +2713,10 @@
spin_unlock_bh(&vsi->mac_filter_hash_lock);
goto error_param;
}
+ if (is_valid_ether_addr(al->list[i].addr) &&
+ is_zero_ether_addr(vf->default_lan_addr.addr))
+ ether_addr_copy(vf->default_lan_addr.addr,
+ al->list[i].addr);
}
}
spin_unlock_bh(&vsi->mac_filter_hash_lock);
@@ -2740,6 +2744,7 @@
{
struct virtchnl_ether_addr_list *al =
(struct virtchnl_ether_addr_list *)msg;
+ bool was_unimac_deleted = false;
struct i40e_pf *pf = vf->pf;
struct i40e_vsi *vsi = NULL;
i40e_status ret = 0;
@@ -2759,6 +2764,8 @@
ret = I40E_ERR_INVALID_MAC_ADDR;
goto error_param;
}
+ if (ether_addr_equal(al->list[i].addr, vf->default_lan_addr.addr))
+ was_unimac_deleted = true;
}
vsi = pf->vsi[vf->lan_vsi_idx];
@@ -2779,10 +2786,25 @@
dev_err(&pf->pdev->dev, "Unable to program VF %d MAC filters, error %d\n",
vf->vf_id, ret);
+ if (vf->trusted && was_unimac_deleted) {
+ struct i40e_mac_filter *f;
+ struct hlist_node *h;
+ u8 *macaddr = NULL;
+ int bkt;
+
+ /* set last unicast mac address as default */
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
+ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
+ if (is_valid_ether_addr(f->macaddr))
+ macaddr = f->macaddr;
+ }
+ if (macaddr)
+ ether_addr_copy(vf->default_lan_addr.addr, macaddr);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
+ }
error_param:
/* send the response to the VF */
- return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_ETH_ADDR,
- ret);
+ return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_ETH_ADDR, ret);
}
/**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 6acede0..567fd67 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -281,8 +281,8 @@
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
unsigned int xdp_res, xdp_xmit = 0;
+ bool failure = false;
struct sk_buff *skb;
- bool failure;
while (likely(total_rx_packets < (unsigned int)budget)) {
union i40e_rx_desc *rx_desc;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 9112dff..b673ac1 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -3891,21 +3891,23 @@
}
/**
- * igc_get_stats - Get System Network Statistics
+ * igc_get_stats64 - Get System Network Statistics
* @netdev: network interface device structure
+ * @stats: rtnl_link_stats64 pointer
*
* Returns the address of the device statistics structure.
* The statistics are updated here and also from the timer callback.
*/
-static struct net_device_stats *igc_get_stats(struct net_device *netdev)
+static void igc_get_stats64(struct net_device *netdev,
+ struct rtnl_link_stats64 *stats)
{
struct igc_adapter *adapter = netdev_priv(netdev);
+ spin_lock(&adapter->stats64_lock);
if (!test_bit(__IGC_RESETTING, &adapter->state))
igc_update_stats(adapter);
-
- /* only return the current stats */
- return &netdev->stats;
+ memcpy(stats, &adapter->stats64, sizeof(*stats));
+ spin_unlock(&adapter->stats64_lock);
}
static netdev_features_t igc_fix_features(struct net_device *netdev,
@@ -4855,7 +4857,7 @@
.ndo_set_rx_mode = igc_set_rx_mode,
.ndo_set_mac_address = igc_set_mac,
.ndo_change_mtu = igc_change_mtu,
- .ndo_get_stats = igc_get_stats,
+ .ndo_get_stats64 = igc_get_stats64,
.ndo_fix_features = igc_fix_features,
.ndo_set_features = igc_set_features,
.ndo_features_check = igc_features_check,
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 54b0bf5..4a9041e 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2287,6 +2287,7 @@
dma_sync_single_for_cpu(dev->dev.parent,
rx_desc->buf_phys_addr,
len, dma_dir);
+ rx_desc->buf_phys_addr = 0;
if (data_len > 0 && sinfo->nr_frags < MAX_SKB_FRAGS) {
skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags];
@@ -2295,8 +2296,8 @@
skb_frag_size_set(frag, data_len);
__skb_frag_set_page(frag, page);
sinfo->nr_frags++;
-
- rx_desc->buf_phys_addr = 0;
+ } else {
+ page_pool_put_full_page(rxq->page_pool, page, true);
}
*size -= len;
}
diff --git a/drivers/net/ethernet/marvell/prestera/Kconfig b/drivers/net/ethernet/marvell/prestera/Kconfig
index b1fcc44..b6f20e2 100644
--- a/drivers/net/ethernet/marvell/prestera/Kconfig
+++ b/drivers/net/ethernet/marvell/prestera/Kconfig
@@ -6,6 +6,7 @@
config PRESTERA
tristate "Marvell Prestera Switch ASICs support"
depends on NET_SWITCHDEV && VLAN_8021Q
+ depends on BRIDGE || BRIDGE=n
select NET_DEVLINK
help
This driver supports Marvell Prestera Switch ASICs family.
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c
index 1b97ada..be56776 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c
@@ -676,7 +676,8 @@
if (err)
return err;
- if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(30))) {
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(30));
+ if (err) {
dev_err(&pdev->dev, "fail to set DMA mask\n");
goto err_dma_mask;
}
@@ -702,8 +703,10 @@
dev_info(fw->dev.dev, "Prestera FW is ready\n");
fw->wq = alloc_workqueue("prestera_fw_wq", WQ_HIGHPRI, 1);
- if (!fw->wq)
+ if (!fw->wq) {
+ err = -ENOMEM;
goto err_wq_alloc;
+ }
INIT_WORK(&fw->evt_work, prestera_fw_evt_work_fn);
diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index 1325055..a8641a4 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -966,6 +966,7 @@
mtk_star_adjust_link, 0, priv->phy_intf);
if (!priv->phydev) {
netdev_err(ndev, "failed to connect to PHY\n");
+ ret = -ENODEV;
goto err_free_irq;
}
@@ -1053,7 +1054,7 @@
err_drop_packet:
dev_kfree_skb(skb);
ndev->stats.tx_dropped++;
- return NETDEV_TX_BUSY;
+ return NETDEV_TX_OK;
}
/* Returns the number of bytes sent or a negative number on the first
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index f6ff962..f6cfec81 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -1864,8 +1864,8 @@
#define INIT_HCA_LOG_RD_OFFSET (INIT_HCA_QPC_OFFSET + 0x77)
#define INIT_HCA_MCAST_OFFSET 0x0c0
#define INIT_HCA_MC_BASE_OFFSET (INIT_HCA_MCAST_OFFSET + 0x00)
-#define INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x12)
-#define INIT_HCA_LOG_MC_HASH_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x16)
+#define INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x13)
+#define INIT_HCA_LOG_MC_HASH_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x17)
#define INIT_HCA_UC_STEERING_OFFSET (INIT_HCA_MCAST_OFFSET + 0x18)
#define INIT_HCA_LOG_MC_TABLE_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x1b)
#define INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN 0x6
@@ -1873,7 +1873,7 @@
#define INIT_HCA_DRIVER_VERSION_SZ 0x40
#define INIT_HCA_FS_PARAM_OFFSET 0x1d0
#define INIT_HCA_FS_BASE_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x00)
-#define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x12)
+#define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x13)
#define INIT_HCA_FS_A0_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x18)
#define INIT_HCA_FS_LOG_TABLE_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x1b)
#define INIT_HCA_FS_ETH_BITS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x21)
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 650ae08..8f020f2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -182,8 +182,8 @@
u64 cmpt_base;
u64 mtt_base;
u64 global_caps;
- u16 log_mc_entry_sz;
- u16 log_mc_hash_sz;
+ u8 log_mc_entry_sz;
+ u8 log_mc_hash_sz;
u16 hca_core_clock; /* Internal Clock Frequency (in MHz) */
u8 log_num_qps;
u8 log_num_srqs;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
index 3e44e4d..95f2b26 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
@@ -187,7 +187,7 @@
struct mlx5e_priv *priv;
/* A given netdev is not a representor or not a slave of LAG configuration */
- if (!mlx5e_eswitch_rep(netdev) || !bond_slave_get_rtnl(netdev))
+ if (!mlx5e_eswitch_rep(netdev) || !netif_is_lag_port(netdev))
return false;
priv = netdev_priv(netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index e36e505..d29af7b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -107,12 +107,16 @@
mlx5e_tc_encap_flows_del(priv, e, &flow_list);
if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) {
+ struct net_device *route_dev;
+
ether_addr_copy(e->h_dest, ha);
ether_addr_copy(eth->h_dest, ha);
/* Update the encap source mac, in case that we delete
* the flows when encap source mac changed.
*/
- ether_addr_copy(eth->h_source, e->route_dev->dev_addr);
+ route_dev = __dev_get_by_index(dev_net(priv->netdev), e->route_dev_ifindex);
+ if (route_dev)
+ ether_addr_copy(eth->h_source, route_dev->dev_addr);
mlx5e_tc_encap_flows_add(priv, e, &flow_list);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 7cce85f..90930e5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -77,13 +77,13 @@
return 0;
}
-static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
- struct net_device *mirred_dev,
- struct net_device **out_dev,
- struct net_device **route_dev,
- struct flowi4 *fl4,
- struct neighbour **out_n,
- u8 *out_ttl)
+static int mlx5e_route_lookup_ipv4_get(struct mlx5e_priv *priv,
+ struct net_device *mirred_dev,
+ struct net_device **out_dev,
+ struct net_device **route_dev,
+ struct flowi4 *fl4,
+ struct neighbour **out_n,
+ u8 *out_ttl)
{
struct neighbour *n;
struct rtable *rt;
@@ -117,18 +117,28 @@
ip_rt_put(rt);
return ret;
}
+ dev_hold(*route_dev);
if (!(*out_ttl))
*out_ttl = ip4_dst_hoplimit(&rt->dst);
n = dst_neigh_lookup(&rt->dst, &fl4->daddr);
ip_rt_put(rt);
- if (!n)
+ if (!n) {
+ dev_put(*route_dev);
return -ENOMEM;
+ }
*out_n = n;
return 0;
}
+static void mlx5e_route_lookup_ipv4_put(struct net_device *route_dev,
+ struct neighbour *n)
+{
+ neigh_release(n);
+ dev_put(route_dev);
+}
+
static const char *mlx5e_netdev_kind(struct net_device *dev)
{
if (dev->rtnl_link_ops)
@@ -193,8 +203,8 @@
fl4.saddr = tun_key->u.ipv4.src;
ttl = tun_key->ttl;
- err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev, &route_dev,
- &fl4, &n, &ttl);
+ err = mlx5e_route_lookup_ipv4_get(priv, mirred_dev, &out_dev, &route_dev,
+ &fl4, &n, &ttl);
if (err)
return err;
@@ -223,7 +233,7 @@
e->m_neigh.family = n->ops->family;
memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
e->out_dev = out_dev;
- e->route_dev = route_dev;
+ e->route_dev_ifindex = route_dev->ifindex;
/* It's important to add the neigh to the hash table before checking
* the neigh validity state. So if we'll get a notification, in case the
@@ -278,7 +288,7 @@
e->flags |= MLX5_ENCAP_ENTRY_VALID;
mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
- neigh_release(n);
+ mlx5e_route_lookup_ipv4_put(route_dev, n);
return err;
destroy_neigh_entry:
@@ -286,18 +296,18 @@
free_encap:
kfree(encap_header);
release_neigh:
- neigh_release(n);
+ mlx5e_route_lookup_ipv4_put(route_dev, n);
return err;
}
#if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
-static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
- struct net_device *mirred_dev,
- struct net_device **out_dev,
- struct net_device **route_dev,
- struct flowi6 *fl6,
- struct neighbour **out_n,
- u8 *out_ttl)
+static int mlx5e_route_lookup_ipv6_get(struct mlx5e_priv *priv,
+ struct net_device *mirred_dev,
+ struct net_device **out_dev,
+ struct net_device **route_dev,
+ struct flowi6 *fl6,
+ struct neighbour **out_n,
+ u8 *out_ttl)
{
struct dst_entry *dst;
struct neighbour *n;
@@ -318,15 +328,25 @@
return ret;
}
+ dev_hold(*route_dev);
n = dst_neigh_lookup(dst, &fl6->daddr);
dst_release(dst);
- if (!n)
+ if (!n) {
+ dev_put(*route_dev);
return -ENOMEM;
+ }
*out_n = n;
return 0;
}
+static void mlx5e_route_lookup_ipv6_put(struct net_device *route_dev,
+ struct neighbour *n)
+{
+ neigh_release(n);
+ dev_put(route_dev);
+}
+
int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
struct net_device *mirred_dev,
struct mlx5e_encap_entry *e)
@@ -348,8 +368,8 @@
fl6.daddr = tun_key->u.ipv6.dst;
fl6.saddr = tun_key->u.ipv6.src;
- err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev, &route_dev,
- &fl6, &n, &ttl);
+ err = mlx5e_route_lookup_ipv6_get(priv, mirred_dev, &out_dev, &route_dev,
+ &fl6, &n, &ttl);
if (err)
return err;
@@ -378,7 +398,7 @@
e->m_neigh.family = n->ops->family;
memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
e->out_dev = out_dev;
- e->route_dev = route_dev;
+ e->route_dev_ifindex = route_dev->ifindex;
/* It's importent to add the neigh to the hash table before checking
* the neigh validity state. So if we'll get a notification, in case the
@@ -433,7 +453,7 @@
e->flags |= MLX5_ENCAP_ENTRY_VALID;
mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
- neigh_release(n);
+ mlx5e_route_lookup_ipv6_put(route_dev, n);
return err;
destroy_neigh_entry:
@@ -441,7 +461,7 @@
free_encap:
kfree(encap_header);
release_neigh:
- neigh_release(n);
+ mlx5e_route_lookup_ipv6_put(route_dev, n);
return err;
}
#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 4e574ac..be3465b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -122,9 +122,9 @@
set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
/* TX queue is created active. */
- spin_lock(&c->async_icosq_lock);
+ spin_lock_bh(&c->async_icosq_lock);
mlx5e_trigger_irq(&c->async_icosq);
- spin_unlock(&c->async_icosq_lock);
+ spin_unlock_bh(&c->async_icosq_lock);
}
void mlx5e_deactivate_xsk(struct mlx5e_channel *c)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
index fb671a4..8e96260 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -36,9 +36,9 @@
if (test_and_set_bit(MLX5E_SQ_STATE_PENDING_XSK_TX, &c->async_icosq.state))
return 0;
- spin_lock(&c->async_icosq_lock);
+ spin_lock_bh(&c->async_icosq_lock);
mlx5e_trigger_irq(&c->async_icosq);
- spin_unlock(&c->async_icosq_lock);
+ spin_unlock_bh(&c->async_icosq_lock);
}
return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 0e45590..381a9c8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -64,13 +64,13 @@
if (!spec)
return -ENOMEM;
- /* Action to copy 7 bit ipsec_syndrome to regB[0:6] */
+ /* Action to copy 7 bit ipsec_syndrome to regB[24:30] */
MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY);
MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME);
MLX5_SET(copy_action_in, action, src_offset, 0);
MLX5_SET(copy_action_in, action, length, 7);
MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B);
- MLX5_SET(copy_action_in, action, dst_offset, 0);
+ MLX5_SET(copy_action_in, action, dst_offset, 24);
modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL,
1, action);
@@ -488,13 +488,13 @@
setup_fte_common(attrs, ipsec_obj_id, spec, &flow_act);
- /* Set 1 bit ipsec marker */
- /* Set 24 bit ipsec_obj_id */
+ /* Set bit[31] ipsec marker */
+ /* Set bit[23-0] ipsec_obj_id */
MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_B);
- MLX5_SET(set_action_in, action, data, (ipsec_obj_id << 1) | 0x1);
- MLX5_SET(set_action_in, action, offset, 7);
- MLX5_SET(set_action_in, action, length, 25);
+ MLX5_SET(set_action_in, action, data, (ipsec_obj_id | BIT(31)));
+ MLX5_SET(set_action_in, action, offset, 0);
+ MLX5_SET(set_action_in, action, length, 32);
modify_hdr = mlx5_modify_header_alloc(priv->mdev, MLX5_FLOW_NAMESPACE_KERNEL,
1, action);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index 11e31a3..a9b4560 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -453,7 +453,6 @@
struct mlx5_cqe64 *cqe)
{
u32 ipsec_meta_data = be32_to_cpu(cqe->ft_metadata);
- u8 ipsec_syndrome = ipsec_meta_data & 0xFF;
struct mlx5e_priv *priv;
struct xfrm_offload *xo;
struct xfrm_state *xs;
@@ -481,7 +480,7 @@
xo = xfrm_offload(skb);
xo->flags = CRYPTO_DONE;
- switch (ipsec_syndrome & MLX5_IPSEC_METADATA_SYNDROM_MASK) {
+ switch (MLX5_IPSEC_METADATA_SYNDROM(ipsec_meta_data)) {
case MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_DECRYPTED:
xo->status = CRYPTO_SUCCESS;
if (WARN_ON_ONCE(priv->ipsec->no_trailer))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
index 056dacb..9df9b9a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
@@ -39,9 +39,10 @@
#include "en.h"
#include "en/txrx.h"
-#define MLX5_IPSEC_METADATA_MARKER_MASK (0x80)
-#define MLX5_IPSEC_METADATA_SYNDROM_MASK (0x7F)
-#define MLX5_IPSEC_METADATA_HANDLE(metadata) (((metadata) >> 8) & 0xFF)
+/* Bit31: IPsec marker, Bit30-24: IPsec syndrome, Bit23-0: IPsec obj id */
+#define MLX5_IPSEC_METADATA_MARKER(metadata) (((metadata) >> 31) & 0x1)
+#define MLX5_IPSEC_METADATA_SYNDROM(metadata) (((metadata) >> 24) & GENMASK(6, 0))
+#define MLX5_IPSEC_METADATA_HANDLE(metadata) ((metadata) & GENMASK(23, 0))
struct mlx5e_accel_tx_ipsec_state {
struct xfrm_offload *xo;
@@ -78,7 +79,7 @@
static inline bool mlx5_ipsec_is_rx_flow(struct mlx5_cqe64 *cqe)
{
- return !!(MLX5_IPSEC_METADATA_MARKER_MASK & be32_to_cpu(cqe->ft_metadata));
+ return MLX5_IPSEC_METADATA_MARKER(be32_to_cpu(cqe->ft_metadata));
}
static inline bool mlx5e_ipsec_is_tx_flow(struct mlx5e_accel_tx_ipsec_state *ipsec_st)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index ccaccb9..6a1d825 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -188,7 +188,7 @@
err = 0;
sq = &c->async_icosq;
- spin_lock(&c->async_icosq_lock);
+ spin_lock_bh(&c->async_icosq_lock);
cseg = post_static_params(sq, priv_rx);
if (IS_ERR(cseg))
@@ -199,7 +199,7 @@
mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
unlock:
- spin_unlock(&c->async_icosq_lock);
+ spin_unlock_bh(&c->async_icosq_lock);
return err;
@@ -265,10 +265,10 @@
BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1);
- spin_lock(&sq->channel->async_icosq_lock);
+ spin_lock_bh(&sq->channel->async_icosq_lock);
if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) {
- spin_unlock(&sq->channel->async_icosq_lock);
+ spin_unlock_bh(&sq->channel->async_icosq_lock);
err = -ENOSPC;
goto err_dma_unmap;
}
@@ -299,7 +299,7 @@
icosq_fill_wi(sq, pi, &wi);
sq->pc++;
mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
- spin_unlock(&sq->channel->async_icosq_lock);
+ spin_unlock_bh(&sq->channel->async_icosq_lock);
return 0;
@@ -360,7 +360,7 @@
err = 0;
sq = &c->async_icosq;
- spin_lock(&c->async_icosq_lock);
+ spin_lock_bh(&c->async_icosq_lock);
cseg = post_static_params(sq, priv_rx);
if (IS_ERR(cseg)) {
@@ -372,7 +372,7 @@
mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
priv_rx->stats->tls_resync_res_ok++;
unlock:
- spin_unlock(&c->async_icosq_lock);
+ spin_unlock_bh(&c->async_icosq_lock);
return err;
}
@@ -476,19 +476,22 @@
depth += sizeof(struct tcphdr);
- if (unlikely(!sk || sk->sk_state == TCP_TIME_WAIT))
+ if (unlikely(!sk))
return;
+ if (unlikely(sk->sk_state == TCP_TIME_WAIT))
+ goto unref;
+
if (unlikely(!resync_queue_get_psv(sk)))
- return;
-
- skb->sk = sk;
- skb->destructor = sock_edemux;
+ goto unref;
seq = th->seq;
datalen = skb->len - depth;
tls_offload_rx_resync_async_request_start(sk, seq, datalen);
rq->stats->tls_resync_req_start++;
+
+unref:
+ sock_gen_put(sk);
}
void mlx5e_ktls_rx_resync(struct net_device *netdev, struct sock *sk,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b3f02aa..ebce979 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5253,6 +5253,7 @@
mlx5e_disable_async_events(priv);
mlx5_lag_remove(mdev);
+ mlx5_vxlan_reset_to_default(mdev->vxlan);
}
int mlx5e_update_nic_rx(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 9020d14..8932c38 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -186,7 +186,7 @@
unsigned char h_dest[ETH_ALEN]; /* destination eth addr */
struct net_device *out_dev;
- struct net_device *route_dev;
+ int route_dev_ifindex;
struct mlx5e_tc_tunnel *tunnel;
int reformat_type;
u8 flags;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 599f5b5..6628a01 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1584,7 +1584,7 @@
} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq)));
out:
- if (rq->xdp_prog)
+ if (rcu_access_pointer(rq->xdp_prog))
mlx5e_xdp_rx_poll_complete(rq);
mlx5_cqwq_update_db_record(cqwq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index e3a968e..ce710f2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -4658,6 +4658,7 @@
return flow;
err_free:
+ dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts);
mlx5e_flow_put(priv, flow);
out:
return ERR_PTR(err);
@@ -4802,6 +4803,7 @@
return 0;
err_free:
+ dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts);
mlx5e_flow_put(priv, flow);
out:
return err;
@@ -5227,8 +5229,10 @@
tc->ct = mlx5_tc_ct_init(priv, tc->chains, &priv->fs.tc.mod_hdr,
MLX5_FLOW_NAMESPACE_KERNEL);
- if (IS_ERR(tc->ct))
+ if (IS_ERR(tc->ct)) {
+ err = PTR_ERR(tc->ct);
goto err_ct;
+ }
tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event;
err = register_netdevice_notifier_dev_net(priv->netdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 3b97900..4a2ce24 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -283,6 +283,9 @@
reg_b = be32_to_cpu(cqe->ft_metadata);
+ if (reg_b >> (MLX5E_TC_TABLE_CHAIN_TAG_BITS + ZONE_RESTORE_BITS))
+ return false;
+
chain = reg_b & MLX5E_TC_TABLE_CHAIN_TAG_MASK;
if (chain)
return true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 82b4419..6dd3ea3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -144,7 +144,9 @@
memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz);
}
-/* RM 2311217: no L4 inner checksum for IPsec tunnel type packet */
+/* If packet is not IP's CHECKSUM_PARTIAL (e.g. icmd packet),
+ * need to set L3 checksum flag for IPsec
+ */
static void
ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
struct mlx5_wqe_eth_seg *eseg)
@@ -154,7 +156,6 @@
eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM;
sq->stats->csum_partial_inner++;
} else {
- eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
sq->stats->csum_partial++;
}
}
@@ -162,11 +163,6 @@
static inline void
mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg)
{
- if (unlikely(eseg->flow_table_metadata & cpu_to_be32(MLX5_ETH_WQE_FT_META_IPSEC))) {
- ipsec_txwqe_build_eseg_csum(sq, skb, eseg);
- return;
- }
-
if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM;
if (skb->encapsulation) {
@@ -177,6 +173,9 @@
eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
sq->stats->csum_partial++;
}
+ } else if (unlikely(eseg->flow_table_metadata & cpu_to_be32(MLX5_ETH_WQE_FT_META_IPSEC))) {
+ ipsec_txwqe_build_eseg_csum(sq, skb, eseg);
+
} else
sq->stats->csum_none++;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 6e6a9a56..d4ee0a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1142,6 +1142,10 @@
struct mlx5_vport *vport;
vport = mlx5_eswitch_get_vport(esw, vport_num);
+
+ if (!vport->qos.enabled)
+ return -EOPNOTSUPP;
+
MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps);
return mlx5_modify_scheduling_element_cmd(esw->dev,
@@ -1408,6 +1412,7 @@
int i;
mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) {
+ memset(&vport->qos, 0, sizeof(vport->qos));
memset(&vport->info, 0, sizeof(vport->info));
vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
}
@@ -1902,8 +1907,6 @@
ether_addr_copy(hw_addr, vport->info.mac);
*hw_addr_len = ETH_ALEN;
err = 0;
- } else {
- NL_SET_ERR_MSG_MOD(extack, "Eswitch vport is disabled");
}
mutex_unlock(&esw->state_lock);
return err;
@@ -2223,12 +2226,15 @@
max_guarantee = evport->info.min_rate;
}
- return max_t(u32, max_guarantee / fw_max_bw_share, 1);
+ if (max_guarantee)
+ return max_t(u32, max_guarantee / fw_max_bw_share, 1);
+ return 0;
}
-static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider)
+static int normalize_vports_min_rate(struct mlx5_eswitch *esw)
{
u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+ u32 divider = calculate_vports_min_rate_divider(esw);
struct mlx5_vport *evport;
u32 vport_max_rate;
u32 vport_min_rate;
@@ -2241,9 +2247,9 @@
continue;
vport_min_rate = evport->info.min_rate;
vport_max_rate = evport->info.max_rate;
- bw_share = MLX5_MIN_BW_SHARE;
+ bw_share = 0;
- if (vport_min_rate)
+ if (divider)
bw_share = MLX5_RATE_TO_BW_SHARE(vport_min_rate,
divider,
fw_max_bw_share);
@@ -2268,7 +2274,6 @@
struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
u32 fw_max_bw_share;
u32 previous_min_rate;
- u32 divider;
bool min_rate_supported;
bool max_rate_supported;
int err = 0;
@@ -2293,8 +2298,7 @@
previous_min_rate = evport->info.min_rate;
evport->info.min_rate = min_rate;
- divider = calculate_vports_min_rate_divider(esw);
- err = normalize_vports_min_rate(esw, divider);
+ err = normalize_vports_min_rate(esw);
if (err) {
evport->info.min_rate = previous_min_rate;
goto unlock;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 1609183..9fdd992 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -534,6 +534,13 @@
goto out;
}
+ if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_PORT &&
+ --fte->dests_size) {
+ fte->modify_mask |= BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION);
+ fte->action.action &= ~MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+ goto out;
+ }
+
if ((fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) &&
--fte->dests_size) {
fte->modify_mask |=
@@ -2010,10 +2017,11 @@
down_write_ref_node(&fte->node, false);
for (i = handle->num_rules - 1; i >= 0; i--)
tree_remove_node(&handle->rule[i]->node, true);
- if (fte->modify_mask && fte->dests_size) {
- modify_fte(fte);
+ if (fte->dests_size) {
+ if (fte->modify_mask)
+ modify_fte(fte);
up_write_ref_node(&fte->node, false);
- } else {
+ } else if (list_empty(&fte->node.children)) {
del_hw_fte(&fte->node);
/* Avoid double call to del_hw_fte */
fte->node.del_hw_func = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index d046db7..3a9fa62 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -90,9 +90,4 @@
u32 key_type, u32 *p_key_id);
void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id);
-static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
-{
- return devlink_net(priv_to_devlink(dev));
-}
-
#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
index 3315afe..3808440 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
@@ -168,6 +168,17 @@
void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan)
{
+ if (!mlx5_vxlan_allowed(vxlan))
+ return;
+
+ mlx5_vxlan_del_port(vxlan, IANA_VXLAN_UDP_PORT);
+ WARN_ON(!hash_empty(vxlan->htable));
+
+ kfree(vxlan);
+}
+
+void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan)
+{
struct mlx5_vxlan_port *vxlanp;
struct hlist_node *tmp;
int bkt;
@@ -175,12 +186,12 @@
if (!mlx5_vxlan_allowed(vxlan))
return;
- /* Lockless since we are the only hash table consumers*/
hash_for_each_safe(vxlan->htable, bkt, tmp, vxlanp, hlist) {
- hash_del(&vxlanp->hlist);
- mlx5_vxlan_core_del_port_cmd(vxlan->mdev, vxlanp->udp_port);
- kfree(vxlanp);
+ /* Don't delete default UDP port added by the HW.
+ * Remove only user configured ports
+ */
+ if (vxlanp->udp_port == IANA_VXLAN_UDP_PORT)
+ continue;
+ mlx5_vxlan_del_port(vxlan, vxlanp->udp_port);
}
-
- kfree(vxlan);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
index ec76652..34ef662 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
@@ -56,6 +56,7 @@
int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port);
int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port);
bool mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port);
+void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan);
#else
static inline struct mlx5_vxlan*
mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-EOPNOTSUPP); }
@@ -63,6 +64,7 @@
static inline int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; }
static inline int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; }
static inline bool mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port) { return false; }
+static inline void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan) { return; }
#endif
#endif /* __MLX5_VXLAN_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
index 872e991..a619d90 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
@@ -6,6 +6,7 @@
config MLXSW_CORE
tristate "Mellanox Technologies Switch ASICs support"
select NET_DEVLINK
+ select MLXFW
help
This driver supports Mellanox Technologies Switch ASICs family.
@@ -82,7 +83,6 @@
select GENERIC_ALLOCATOR
select PARMAN
select OBJAGG
- select MLXFW
imply PTP_1588_CLOCK
select NET_PTP_CLASSIFY if PTP_1588_CLOCK
default m
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 7f77c2a..1a86535 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -571,7 +571,8 @@
if (trans->core->fw_flash_in_progress)
timeout = msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_DURING_FW_FLASH_MS);
- queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw, timeout);
+ queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw,
+ timeout << trans->retries);
}
static int mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core,
@@ -620,6 +621,9 @@
err = mlxsw_emad_transmit(trans->core, trans);
if (err == 0)
return;
+
+ if (!atomic_dec_and_test(&trans->active))
+ return;
} else {
err = -EIO;
}
@@ -2064,6 +2068,8 @@
if (!reload)
devlink_resources_unregister(devlink, NULL);
mlxsw_core->bus->fini(mlxsw_core->bus_priv);
+ if (!reload)
+ devlink_free(devlink);
return;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 16b47fc..b08853f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1174,11 +1174,14 @@
u32 eth_proto_cap, eth_proto_admin, eth_proto_oper;
const struct mlxsw_sp_port_type_speed_ops *ops;
char ptys_pl[MLXSW_REG_PTYS_LEN];
+ u32 eth_proto_cap_masked;
int err;
ops = mlxsw_sp->port_type_speed_ops;
- /* Set advertised speeds to supported speeds. */
+ /* Set advertised speeds to speeds supported by both the driver
+ * and the device.
+ */
ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port,
0, false);
err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
@@ -1187,8 +1190,10 @@
ops->reg_ptys_eth_unpack(mlxsw_sp, ptys_pl, ð_proto_cap,
ð_proto_admin, ð_proto_oper);
+ eth_proto_cap_masked = ops->ptys_proto_cap_masked_get(eth_proto_cap);
ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port,
- eth_proto_cap, mlxsw_sp_port->link.autoneg);
+ eth_proto_cap_masked,
+ mlxsw_sp_port->link.autoneg);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 3e26eb6..74b3959 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -342,6 +342,7 @@
u32 *p_eth_proto_cap,
u32 *p_eth_proto_admin,
u32 *p_eth_proto_oper);
+ u32 (*ptys_proto_cap_masked_get)(u32 eth_proto_cap);
};
static inline struct net_device *
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
index 2096b64..5406164 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
@@ -1303,6 +1303,20 @@
p_eth_proto_oper);
}
+static u32 mlxsw_sp1_ptys_proto_cap_masked_get(u32 eth_proto_cap)
+{
+ u32 ptys_proto_cap_masked = 0;
+ int i;
+
+ for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) {
+ if (mlxsw_sp1_port_link_mode[i].mask & eth_proto_cap)
+ ptys_proto_cap_masked |=
+ mlxsw_sp1_port_link_mode[i].mask;
+ }
+
+ return ptys_proto_cap_masked;
+}
+
const struct mlxsw_sp_port_type_speed_ops mlxsw_sp1_port_type_speed_ops = {
.from_ptys_supported_port = mlxsw_sp1_from_ptys_supported_port,
.from_ptys_link = mlxsw_sp1_from_ptys_link,
@@ -1313,6 +1327,7 @@
.to_ptys_speed = mlxsw_sp1_to_ptys_speed,
.reg_ptys_eth_pack = mlxsw_sp1_reg_ptys_eth_pack,
.reg_ptys_eth_unpack = mlxsw_sp1_reg_ptys_eth_unpack,
+ .ptys_proto_cap_masked_get = mlxsw_sp1_ptys_proto_cap_masked_get,
};
static const enum ethtool_link_mode_bit_indices
@@ -1731,6 +1746,20 @@
p_eth_proto_admin, p_eth_proto_oper);
}
+static u32 mlxsw_sp2_ptys_proto_cap_masked_get(u32 eth_proto_cap)
+{
+ u32 ptys_proto_cap_masked = 0;
+ int i;
+
+ for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) {
+ if (mlxsw_sp2_port_link_mode[i].mask & eth_proto_cap)
+ ptys_proto_cap_masked |=
+ mlxsw_sp2_port_link_mode[i].mask;
+ }
+
+ return ptys_proto_cap_masked;
+}
+
const struct mlxsw_sp_port_type_speed_ops mlxsw_sp2_port_type_speed_ops = {
.from_ptys_supported_port = mlxsw_sp2_from_ptys_supported_port,
.from_ptys_link = mlxsw_sp2_from_ptys_link,
@@ -1741,4 +1770,5 @@
.to_ptys_speed = mlxsw_sp2_to_ptys_speed,
.reg_ptys_eth_pack = mlxsw_sp2_reg_ptys_eth_pack,
.reg_ptys_eth_unpack = mlxsw_sp2_reg_ptys_eth_unpack,
+ .ptys_proto_cap_masked_get = mlxsw_sp2_ptys_proto_cap_masked_get,
};
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index a1938842..b319c22 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -148,7 +148,8 @@
int_sts = lan743x_csr_read(adapter, INT_STS);
if (int_sts & INT_BIT_SW_GP_) {
- lan743x_csr_write(adapter, INT_STS, INT_BIT_SW_GP_);
+ /* disable the interrupt to prevent repeated re-triggering */
+ lan743x_csr_write(adapter, INT_EN_CLR, INT_BIT_SW_GP_);
intr->software_isr_flag = 1;
}
}
@@ -674,14 +675,12 @@
static int lan743x_dp_write(struct lan743x_adapter *adapter,
u32 select, u32 addr, u32 length, u32 *buf)
{
- int ret = -EIO;
u32 dp_sel;
int i;
- mutex_lock(&adapter->dp_lock);
if (lan743x_csr_wait_for_bit(adapter, DP_SEL, DP_SEL_DPRDY_,
1, 40, 100, 100))
- goto unlock;
+ return -EIO;
dp_sel = lan743x_csr_read(adapter, DP_SEL);
dp_sel &= ~DP_SEL_MASK_;
dp_sel |= select;
@@ -693,13 +692,10 @@
lan743x_csr_write(adapter, DP_CMD, DP_CMD_WRITE_);
if (lan743x_csr_wait_for_bit(adapter, DP_SEL, DP_SEL_DPRDY_,
1, 40, 100, 100))
- goto unlock;
+ return -EIO;
}
- ret = 0;
-unlock:
- mutex_unlock(&adapter->dp_lock);
- return ret;
+ return 0;
}
static u32 lan743x_mac_mii_access(u16 id, u16 index, int read)
@@ -1019,16 +1015,16 @@
static int lan743x_phy_open(struct lan743x_adapter *adapter)
{
struct lan743x_phy *phy = &adapter->phy;
+ struct phy_device *phydev = NULL;
struct device_node *phynode;
- struct phy_device *phydev;
struct net_device *netdev;
int ret = -EIO;
netdev = adapter->netdev;
phynode = of_node_get(adapter->pdev->dev.of_node);
- adapter->phy_mode = PHY_INTERFACE_MODE_GMII;
if (phynode) {
+ /* try devicetree phy, or fixed link */
of_get_phy_mode(phynode, &adapter->phy_mode);
if (of_phy_is_fixed_link(phynode)) {
@@ -1044,13 +1040,15 @@
lan743x_phy_link_status_change, 0,
adapter->phy_mode);
of_node_put(phynode);
- if (!phydev)
- goto return_error;
- } else {
+ }
+
+ if (!phydev) {
+ /* try internal phy */
phydev = phy_find_first(adapter->mdiobus);
if (!phydev)
goto return_error;
+ adapter->phy_mode = PHY_INTERFACE_MODE_GMII;
ret = phy_connect_direct(netdev, phydev,
lan743x_phy_link_status_change,
adapter->phy_mode);
@@ -1310,13 +1308,13 @@
goto clear_active;
if (!(buffer_info->flags & TX_BUFFER_INFO_FLAG_TIMESTAMP_REQUESTED)) {
- dev_kfree_skb(buffer_info->skb);
+ dev_kfree_skb_any(buffer_info->skb);
goto clear_skb;
}
if (cleanup) {
lan743x_ptp_unrequest_tx_timestamp(tx->adapter);
- dev_kfree_skb(buffer_info->skb);
+ dev_kfree_skb_any(buffer_info->skb);
} else {
ignore_sync = (buffer_info->flags &
TX_BUFFER_INFO_FLAG_IGNORE_SYNC) != 0;
@@ -1626,7 +1624,7 @@
if (required_number_of_descriptors >
lan743x_tx_get_avail_desc(tx)) {
if (required_number_of_descriptors > (tx->ring_size - 1)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_irq(skb);
} else {
/* save to overflow buffer */
tx->overflow_skb = skb;
@@ -1659,7 +1657,7 @@
start_frame_length,
do_timestamp,
skb->ip_summed == CHECKSUM_PARTIAL)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_irq(skb);
goto unlock;
}
@@ -1678,7 +1676,7 @@
* frame assembler clean up was performed inside
* lan743x_tx_frame_add_fragment
*/
- dev_kfree_skb(skb);
+ dev_kfree_skb_irq(skb);
goto unlock;
}
}
@@ -2733,7 +2731,6 @@
adapter->intr.irq = adapter->pdev->irq;
lan743x_csr_write(adapter, INT_EN_CLR, 0xFFFFFFFF);
- mutex_init(&adapter->dp_lock);
ret = lan743x_gpio_init(adapter);
if (ret)
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index c61a4041..a536f4a 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -712,9 +712,6 @@
struct lan743x_csr csr;
struct lan743x_intr intr;
- /* lock, used to prevent concurrent access to data port */
- struct mutex dp_lock;
-
struct lan743x_gpio gpio;
struct lan743x_ptp ptp;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
index 545c99b..dc5fbc2 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
@@ -333,7 +333,7 @@
union ionic_dev_cmd cmd = {
.vf_setattr.opcode = IONIC_CMD_VF_SETATTR,
.vf_setattr.attr = attr,
- .vf_setattr.vf_index = vf,
+ .vf_setattr.vf_index = cpu_to_le16(vf),
};
int err;
@@ -391,7 +391,7 @@
{
union ionic_dev_cmd cmd = {
.q_identify.opcode = IONIC_CMD_Q_IDENTIFY,
- .q_identify.lif_type = lif_type,
+ .q_identify.lif_type = cpu_to_le16(lif_type),
.q_identify.type = qtype,
.q_identify.ver = qver,
};
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
index c109cd5..6c243b1 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
@@ -29,6 +29,7 @@
int res_index;
};
+#ifndef __CHECKER__
/* Registers */
static_assert(sizeof(struct ionic_intr) == 32);
@@ -119,6 +120,7 @@
static_assert(sizeof(struct ionic_vf_setattr_comp) == 16);
static_assert(sizeof(struct ionic_vf_getattr_cmd) == 64);
static_assert(sizeof(struct ionic_vf_getattr_comp) == 16);
+#endif /* __CHECKER__ */
struct ionic_devinfo {
u8 asic_type;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
index ed9808f..35c72d4 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
@@ -126,6 +126,11 @@
ethtool_link_ksettings_zero_link_mode(ks, supported);
+ if (!idev->port_info) {
+ netdev_err(netdev, "port_info not initialized\n");
+ return -EOPNOTSUPP;
+ }
+
/* The port_info data is found in a DMA space that the NIC keeps
* up-to-date, so there's no need to request the data from the
* NIC, we already have it in our memory space.
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_fw.c b/drivers/net/ethernet/pensando/ionic/ionic_fw.c
index f492ae4..d7bbf33 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_fw.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_fw.c
@@ -27,9 +27,9 @@
{
union ionic_dev_cmd cmd = {
.fw_download.opcode = IONIC_CMD_FW_DOWNLOAD,
- .fw_download.offset = offset,
- .fw_download.addr = addr,
- .fw_download.length = length
+ .fw_download.offset = cpu_to_le32(offset),
+ .fw_download.addr = cpu_to_le64(addr),
+ .fw_download.length = cpu_to_le32(length),
};
ionic_dev_cmd_go(idev, &cmd);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index d655a7a..a12df39 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -1656,7 +1656,6 @@
if (lif->rxqcqs) {
for (i = 0; i < lif->nxqs && lif->rxqcqs[i]; i++) {
ionic_lif_qcq_deinit(lif, lif->rxqcqs[i]);
- ionic_rx_flush(&lif->rxqcqs[i]->cq);
ionic_rx_empty(&lif->rxqcqs[i]->q);
}
}
@@ -1915,11 +1914,11 @@
ret = -EINVAL;
} else {
ivf->vf = vf;
- ivf->vlan = ionic->vfs[vf].vlanid;
+ ivf->vlan = le16_to_cpu(ionic->vfs[vf].vlanid);
ivf->qos = 0;
ivf->spoofchk = ionic->vfs[vf].spoofchk;
ivf->linkstate = ionic->vfs[vf].linkstate;
- ivf->max_tx_rate = ionic->vfs[vf].maxrate;
+ ivf->max_tx_rate = le32_to_cpu(ionic->vfs[vf].maxrate);
ivf->trusted = ionic->vfs[vf].trusted;
ether_addr_copy(ivf->mac, ionic->vfs[vf].macaddr);
}
@@ -2019,7 +2018,7 @@
ret = ionic_set_vf_config(ionic, vf,
IONIC_VF_ATTR_VLAN, (u8 *)&vlan);
if (!ret)
- ionic->vfs[vf].vlanid = vlan;
+ ionic->vfs[vf].vlanid = cpu_to_le16(vlan);
}
up_write(&ionic->vf_op_lock);
@@ -2048,7 +2047,7 @@
ret = ionic_set_vf_config(ionic, vf,
IONIC_VF_ATTR_RATE, (u8 *)&tx_max);
if (!ret)
- lif->ionic->vfs[vf].maxrate = tx_max;
+ lif->ionic->vfs[vf].maxrate = cpu_to_le32(tx_max);
}
up_write(&ionic->vf_op_lock);
@@ -2981,14 +2980,14 @@
static void ionic_lif_queue_identify(struct ionic_lif *lif)
{
+ union ionic_q_identity __iomem *q_ident;
struct ionic *ionic = lif->ionic;
- union ionic_q_identity *q_ident;
struct ionic_dev *idev;
int qtype;
int err;
idev = &lif->ionic->idev;
- q_ident = (union ionic_q_identity *)&idev->dev_cmd_regs->data;
+ q_ident = (union ionic_q_identity __iomem *)&idev->dev_cmd_regs->data;
for (qtype = 0; qtype < ARRAY_SIZE(ionic_qtype_versions); qtype++) {
struct ionic_qtype_info *qti = &lif->qtype_info[qtype];
@@ -3011,14 +3010,14 @@
ionic_qtype_versions[qtype]);
err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT);
if (!err) {
- qti->version = q_ident->version;
- qti->supported = q_ident->supported;
- qti->features = le64_to_cpu(q_ident->features);
- qti->desc_sz = le16_to_cpu(q_ident->desc_sz);
- qti->comp_sz = le16_to_cpu(q_ident->comp_sz);
- qti->sg_desc_sz = le16_to_cpu(q_ident->sg_desc_sz);
- qti->max_sg_elems = le16_to_cpu(q_ident->max_sg_elems);
- qti->sg_desc_stride = le16_to_cpu(q_ident->sg_desc_stride);
+ qti->version = readb(&q_ident->version);
+ qti->supported = readb(&q_ident->supported);
+ qti->features = readq(&q_ident->features);
+ qti->desc_sz = readw(&q_ident->desc_sz);
+ qti->comp_sz = readw(&q_ident->comp_sz);
+ qti->sg_desc_sz = readw(&q_ident->sg_desc_sz);
+ qti->max_sg_elems = readw(&q_ident->max_sg_elems);
+ qti->sg_desc_stride = readw(&q_ident->sg_desc_stride);
}
mutex_unlock(&ionic->dev_cmd_lock);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index ee07408..d355676 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -311,7 +311,7 @@
static void ionic_dev_cmd_clean(struct ionic *ionic)
{
- union ionic_dev_cmd_regs *regs = ionic->idev.dev_cmd_regs;
+ union __iomem ionic_dev_cmd_regs *regs = ionic->idev.dev_cmd_regs;
iowrite32(0, ®s->doorbell);
memset_io(®s->cmd, 0, sizeof(regs->cmd));
@@ -333,7 +333,7 @@
*/
max_wait = jiffies + (max_seconds * HZ);
try_again:
- opcode = idev->dev_cmd_regs->cmd.cmd.opcode;
+ opcode = readb(&idev->dev_cmd_regs->cmd.cmd.opcode);
start_time = jiffies;
do {
done = ionic_dev_cmd_done(idev);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.h b/drivers/net/ethernet/pensando/ionic/ionic_stats.h
index 3f54351..2a72583 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_stats.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.h
@@ -49,7 +49,7 @@
(*((u64 *)(((u8 *)(base_ptr)) + (desc_ptr)->offset)))
#define IONIC_READ_STAT_LE64(base_ptr, desc_ptr) \
- __le64_to_cpu(*((u64 *)(((u8 *)(base_ptr)) + (desc_ptr)->offset)))
+ __le64_to_cpu(*((__le64 *)(((u8 *)(base_ptr)) + (desc_ptr)->offset)))
struct ionic_stat_desc {
char name[ETH_GSTRING_LEN];
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 169ac4f..b3d2250 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -200,7 +200,7 @@
if (likely(netdev->features & NETIF_F_RXCSUM)) {
if (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_CALC) {
skb->ip_summed = CHECKSUM_COMPLETE;
- skb->csum = (__wsum)le16_to_cpu(comp->csum);
+ skb->csum = (__force __wsum)le16_to_cpu(comp->csum);
stats->csum_complete++;
}
} else {
@@ -253,19 +253,6 @@
return true;
}
-void ionic_rx_flush(struct ionic_cq *cq)
-{
- struct ionic_dev *idev = &cq->lif->ionic->idev;
- u32 work_done;
-
- work_done = ionic_cq_service(cq, cq->num_descs,
- ionic_rx_service, NULL, NULL);
-
- if (work_done)
- ionic_intr_credits(idev->intr_ctrl, cq->bound_intr->index,
- work_done, IONIC_INTR_CRED_RESET_COALESCE);
-}
-
static int ionic_rx_page_alloc(struct ionic_queue *q,
struct ionic_page_info *page_info)
{
@@ -413,22 +400,20 @@
void ionic_rx_empty(struct ionic_queue *q)
{
struct ionic_desc_info *desc_info;
- struct ionic_rxq_desc *desc;
- unsigned int i;
- u16 idx;
+ struct ionic_page_info *page_info;
+ unsigned int i, j;
- idx = q->tail_idx;
- while (idx != q->head_idx) {
- desc_info = &q->info[idx];
- desc = desc_info->desc;
- desc->addr = 0;
- desc->len = 0;
+ for (i = 0; i < q->num_descs; i++) {
+ desc_info = &q->info[i];
+ for (j = 0; j < IONIC_RX_MAX_SG_ELEMS + 1; j++) {
+ page_info = &desc_info->pages[j];
+ if (page_info->page)
+ ionic_rx_page_free(q, page_info);
+ }
- for (i = 0; i < desc_info->npages; i++)
- ionic_rx_page_free(q, &desc_info->pages[i]);
-
+ desc_info->npages = 0;
+ desc_info->cb = NULL;
desc_info->cb_arg = NULL;
- idx = (idx + 1) & (q->num_descs - 1);
}
}
@@ -812,6 +797,7 @@
skb_frag_t *frag;
bool start, done;
bool outer_csum;
+ dma_addr_t addr;
bool has_vlan;
u16 desc_len;
u8 desc_nsge;
@@ -893,11 +879,10 @@
if (frag_left > 0) {
len = min(frag_left, left);
frag_left -= len;
- elem->addr =
- cpu_to_le64(ionic_tx_map_frag(q, frag,
- offset, len));
- if (dma_mapping_error(dev, elem->addr))
+ addr = ionic_tx_map_frag(q, frag, offset, len);
+ if (dma_mapping_error(dev, addr))
goto err_out_abort;
+ elem->addr = cpu_to_le64(addr);
elem->len = cpu_to_le16(len);
elem++;
desc_nsge++;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.h b/drivers/net/ethernet/pensando/ionic/ionic_txrx.h
index a5883be0..7667b72 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.h
@@ -4,7 +4,6 @@
#ifndef _IONIC_TXRX_H_
#define _IONIC_TXRX_H_
-void ionic_rx_flush(struct ionic_cq *cq);
void ionic_tx_flush(struct ionic_cq *cq);
void ionic_rx_fill(struct ionic_queue *q);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 0e4cd88..0a22f8c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -1647,9 +1647,9 @@
ilog2(rounded_conn_num));
STORE_RT_REG_AGG(p_hwfn, SRC_REG_FIRSTFREE_RT_OFFSET,
- p_hwfn->p_cxt_mngr->first_free);
+ p_hwfn->p_cxt_mngr->src_t2.first_free);
STORE_RT_REG_AGG(p_hwfn, SRC_REG_LASTFREE_RT_OFFSET,
- p_hwfn->p_cxt_mngr->last_free);
+ p_hwfn->p_cxt_mngr->src_t2.last_free);
}
/* Timers PF */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.h b/drivers/net/ethernet/qlogic/qed/qed_cxt.h
index 8b64495..056e796 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.h
@@ -326,9 +326,6 @@
/* SRC T2 */
struct qed_src_t2 src_t2;
- u32 t2_num_pages;
- u64 first_free;
- u64 last_free;
/* total number of SRQ's for this hwfn */
u32 srq_count;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index 512cbef..a998611 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -2754,14 +2754,18 @@
iwarp_info->partial_fpdus = kcalloc((u16)p_hwfn->p_rdma_info->num_qps,
sizeof(*iwarp_info->partial_fpdus),
GFP_KERNEL);
- if (!iwarp_info->partial_fpdus)
+ if (!iwarp_info->partial_fpdus) {
+ rc = -ENOMEM;
goto err;
+ }
iwarp_info->max_num_partial_fpdus = (u16)p_hwfn->p_rdma_info->num_qps;
iwarp_info->mpa_intermediate_buf = kzalloc(buff_size, GFP_KERNEL);
- if (!iwarp_info->mpa_intermediate_buf)
+ if (!iwarp_info->mpa_intermediate_buf) {
+ rc = -ENOMEM;
goto err;
+ }
/* The mpa_bufs array serves for pending RX packets received on the
* mpa ll2 that don't have place on the tx ring and require later
@@ -2771,8 +2775,10 @@
iwarp_info->mpa_bufs = kcalloc(data.input.rx_num_desc,
sizeof(*iwarp_info->mpa_bufs),
GFP_KERNEL);
- if (!iwarp_info->mpa_bufs)
+ if (!iwarp_info->mpa_bufs) {
+ rc = -ENOMEM;
goto err;
+ }
INIT_LIST_HEAD(&iwarp_info->mpa_buf_pending_list);
INIT_LIST_HEAD(&iwarp_info->mpa_buf_list);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index b8af59f..d2c1907 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -2231,7 +2231,8 @@
/* Boot either flash image or firmware image from host file system */
if (qlcnic_load_fw_file == 1) {
- if (qlcnic_83xx_load_fw_image_from_host(adapter))
+ err = qlcnic_83xx_load_fw_image_from_host(adapter);
+ if (err)
return err;
} else {
QLC_SHARED_REG_WR32(adapter, QLCNIC_FW_IMG_VALID,
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
index 29a7bfa..3d7d3ab 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
@@ -188,6 +188,11 @@
dev = skb->dev;
port = rmnet_get_port_rcu(dev);
+ if (unlikely(!port)) {
+ atomic_long_inc(&skb->dev->rx_nohandler);
+ kfree_skb(skb);
+ goto done;
+ }
switch (port->rmnet_mode) {
case RMNET_EPMODE_VND:
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 3b6ddc7..85d9c3e 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4080,9 +4080,17 @@
return -EIO;
}
-static bool rtl_test_hw_pad_bug(struct rtl8169_private *tp, struct sk_buff *skb)
+static bool rtl_test_hw_pad_bug(struct rtl8169_private *tp)
{
- return skb->len < ETH_ZLEN && tp->mac_version == RTL_GIGA_MAC_VER_34;
+ switch (tp->mac_version) {
+ case RTL_GIGA_MAC_VER_34:
+ case RTL_GIGA_MAC_VER_60:
+ case RTL_GIGA_MAC_VER_61:
+ case RTL_GIGA_MAC_VER_63:
+ return true;
+ default:
+ return false;
+ }
}
static void rtl8169_tso_csum_v1(struct sk_buff *skb, u32 *opts)
@@ -4154,8 +4162,9 @@
opts[1] |= transport_offset << TCPHO_SHIFT;
} else {
- if (unlikely(rtl_test_hw_pad_bug(tp, skb)))
- return !eth_skb_pad(skb);
+ if (unlikely(skb->len < ETH_ZLEN && rtl_test_hw_pad_bug(tp)))
+ /* eth_skb_pad would free the skb on error */
+ return !__skb_put_padto(skb, ETH_ZLEN, false);
}
return true;
@@ -4334,18 +4343,9 @@
rtl_chip_supports_csum_v2(tp))
features &= ~NETIF_F_ALL_TSO;
} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
- if (skb->len < ETH_ZLEN) {
- switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_11:
- case RTL_GIGA_MAC_VER_12:
- case RTL_GIGA_MAC_VER_17:
- case RTL_GIGA_MAC_VER_34:
- features &= ~NETIF_F_CSUM_MASK;
- break;
- default:
- break;
- }
- }
+ /* work around hw bug on some chip versions */
+ if (skb->len < ETH_ZLEN)
+ features &= ~NETIF_F_CSUM_MASK;
if (transport_offset > TCPHO_MAX &&
rtl_chip_supports_csum_v2(tp))
@@ -4573,7 +4573,7 @@
}
rtl_irq_disable(tp);
- napi_schedule_irqoff(&tp->napi);
+ napi_schedule(&tp->napi);
out:
rtl_ack_events(tp, status);
@@ -4746,7 +4746,7 @@
rtl_request_firmware(tp);
retval = request_irq(pci_irq_vector(pdev, 0), rtl8169_interrupt,
- IRQF_NO_THREAD | IRQF_SHARED, dev->name, tp);
+ IRQF_SHARED, dev->name, tp);
if (retval < 0)
goto err_release_fw_2;
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 9c4df4e..bd30505 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1744,12 +1744,16 @@
config.flags = 0;
config.tx_type = priv->tstamp_tx_ctrl ? HWTSTAMP_TX_ON :
HWTSTAMP_TX_OFF;
- if (priv->tstamp_rx_ctrl & RAVB_RXTSTAMP_TYPE_V2_L2_EVENT)
+ switch (priv->tstamp_rx_ctrl & RAVB_RXTSTAMP_TYPE) {
+ case RAVB_RXTSTAMP_TYPE_V2_L2_EVENT:
config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
- else if (priv->tstamp_rx_ctrl & RAVB_RXTSTAMP_TYPE_ALL)
+ break;
+ case RAVB_RXTSTAMP_TYPE_ALL:
config.rx_filter = HWTSTAMP_FILTER_ALL;
- else
+ break;
+ default:
config.rx_filter = HWTSTAMP_FILTER_NONE;
+ }
return copy_to_user(req->ifr_data, &config, sizeof(config)) ?
-EFAULT : 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
index f61cb99..82b1c7a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
@@ -113,8 +113,10 @@
/* Enable TX clock */
if (dwmac->data->tx_clk_en) {
dwmac->tx_clk = devm_clk_get(&pdev->dev, "tx_clk");
- if (IS_ERR(dwmac->tx_clk))
+ if (IS_ERR(dwmac->tx_clk)) {
+ ret = PTR_ERR(dwmac->tx_clk);
goto err_remove_config_dt;
+ }
clk_prepare_enable(dwmac->tx_clk);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index b6e5e3e..81ee0a0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -625,13 +625,6 @@
if (ret)
return ret;
- if (plat->eee_usecs_rate > 0) {
- u32 tx_lpi_usec;
-
- tx_lpi_usec = (plat->eee_usecs_rate / 1000000) - 1;
- writel(tx_lpi_usec, res.addr + GMAC_1US_TIC_COUNTER);
- }
-
ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
if (ret < 0)
return ret;
@@ -641,6 +634,13 @@
res.wol_irq = pci_irq_vector(pdev, 0);
res.irq = pci_irq_vector(pdev, 0);
+ if (plat->eee_usecs_rate > 0) {
+ u32 tx_lpi_usec;
+
+ tx_lpi_usec = (plat->eee_usecs_rate / 1000000) - 1;
+ writel(tx_lpi_usec, res.addr + GMAC_1US_TIC_COUNTER);
+ }
+
ret = stmmac_dvr_probe(&pdev->dev, plat, &res);
if (ret) {
pci_free_irq_vectors(pdev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
index cb87d31..57a53a6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -23,7 +23,7 @@
return readl_poll_timeout(ioaddr + DMA_BUS_MODE, value,
!(value & DMA_BUS_MODE_SFT_RESET),
- 10000, 100000);
+ 10000, 200000);
}
/* CSR1 enables the transmit DMA to check for new descriptor */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 220626a..ba45fe2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4757,6 +4757,7 @@
ch->priv_data = priv;
ch->index = queue;
+ spin_lock_init(&ch->lock);
if (queue < priv->plat->rx_queues_to_use) {
netif_napi_add(dev, &ch->rx_napi, stmmac_napi_poll_rx,
@@ -5246,6 +5247,7 @@
return ret;
}
+ rtnl_lock();
mutex_lock(&priv->lock);
stmmac_reset_queues_param(priv);
@@ -5261,6 +5263,7 @@
stmmac_enable_all_queues(priv);
mutex_unlock(&priv->lock);
+ rtnl_unlock();
if (!device_may_wakeup(priv->device) || !priv->plat->pmt) {
rtnl_lock();
diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c
index 75056c1..5dc60ec 100644
--- a/drivers/net/ethernet/ti/am65-cpts.c
+++ b/drivers/net/ethernet/ti/am65-cpts.c
@@ -1001,8 +1001,7 @@
if (IS_ERR_OR_NULL(cpts->ptp_clock)) {
dev_err(dev, "Failed to register ptp clk %ld\n",
PTR_ERR(cpts->ptp_clock));
- if (!cpts->ptp_clock)
- ret = -ENODEV;
+ ret = cpts->ptp_clock ? PTR_ERR(cpts->ptp_clock) : -ENODEV;
goto refclk_disable;
}
cpts->phc_index = ptp_clock_index(cpts->ptp_clock);
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 9fd1f77..b0f00b4 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -838,9 +838,12 @@
if (ret < 0)
goto err_cleanup;
- if (cpts_register(cpsw->cpts))
- dev_err(priv->dev, "error registering cpts device\n");
-
+ if (cpsw->cpts) {
+ if (cpts_register(cpsw->cpts))
+ dev_err(priv->dev, "error registering cpts device\n");
+ else
+ writel(0x10, &cpsw->wr_regs->misc_en);
+ }
}
cpsw_restore(priv);
@@ -1631,6 +1634,7 @@
CPSW_MAX_QUEUES, CPSW_MAX_QUEUES);
if (!ndev) {
dev_err(dev, "error allocating net_device\n");
+ ret = -ENOMEM;
goto clean_cpts;
}
@@ -1716,7 +1720,6 @@
/* Enable misc CPTS evnt_pend IRQ */
cpts_set_irqpoll(cpsw->cpts, false);
- writel(0x10, &cpsw->wr_regs->misc_en);
skip_cpts:
cpsw_notice(priv, probe,
diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c
index 4d02c51..4619c3a 100644
--- a/drivers/net/ethernet/ti/cpsw_ethtool.c
+++ b/drivers/net/ethernet/ti/cpsw_ethtool.c
@@ -728,7 +728,6 @@
(1 << HWTSTAMP_TX_ON);
info->rx_filters =
(1 << HWTSTAMP_FILTER_NONE) |
- (1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT) |
(1 << HWTSTAMP_FILTER_PTP_V2_EVENT);
return 0;
}
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index f779d2e..2f5e0ad 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -873,8 +873,12 @@
if (ret < 0)
goto err_cleanup;
- if (cpts_register(cpsw->cpts))
- dev_err(priv->dev, "error registering cpts device\n");
+ if (cpsw->cpts) {
+ if (cpts_register(cpsw->cpts))
+ dev_err(priv->dev, "error registering cpts device\n");
+ else
+ writel(0x10, &cpsw->wr_regs->misc_en);
+ }
napi_enable(&cpsw->napi_rx);
napi_enable(&cpsw->napi_tx);
@@ -2006,7 +2010,6 @@
/* Enable misc CPTS evnt_pend IRQ */
cpts_set_irqpoll(cpsw->cpts, false);
- writel(0x10, &cpsw->wr_regs->misc_en);
skip_cpts:
ret = cpsw_register_notifiers(cpsw);
diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
index 51cc29f..31c5e36 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.c
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -639,13 +639,10 @@
break;
case HWTSTAMP_FILTER_ALL:
case HWTSTAMP_FILTER_NTP_ALL:
- return -ERANGE;
case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
- priv->rx_ts_enabled = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
- cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
- break;
+ return -ERANGE;
case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index d07008a..1426bfc 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -224,8 +224,7 @@
if (ip_tunnel_collect_metadata() || gs->collect_md) {
__be16 flags;
- flags = TUNNEL_KEY | TUNNEL_GENEVE_OPT |
- (gnvh->oam ? TUNNEL_OAM : 0) |
+ flags = TUNNEL_KEY | (gnvh->oam ? TUNNEL_OAM : 0) |
(gnvh->critical ? TUNNEL_CRIT_OPT : 0);
tun_dst = udp_tun_rx_dst(skb, geneve_get_sk_family(gs), flags,
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 030a1a5..dc668ed 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -657,10 +657,6 @@
gtp = netdev_priv(dev);
- err = gtp_encap_enable(gtp, data);
- if (err < 0)
- return err;
-
if (!data[IFLA_GTP_PDP_HASHSIZE]) {
hashsize = 1024;
} else {
@@ -671,12 +667,16 @@
err = gtp_hashtable_new(gtp, hashsize);
if (err < 0)
- goto out_encap;
+ return err;
+
+ err = gtp_encap_enable(gtp, data);
+ if (err < 0)
+ goto out_hashtable;
err = register_netdevice(dev);
if (err < 0) {
netdev_dbg(dev, "failed to register new netdev %d\n", err);
- goto out_hashtable;
+ goto out_encap;
}
gn = net_generic(dev_net(dev), gtp_net_id);
@@ -687,11 +687,11 @@
return 0;
+out_encap:
+ gtp_encap_disable(gtp);
out_hashtable:
kfree(gtp->addr_hash);
kfree(gtp->tid_hash);
-out_encap:
- gtp_encap_disable(gtp);
return err;
}
diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c
index 43f5f5d9..e8599bb 100644
--- a/drivers/net/ipa/gsi_trans.c
+++ b/drivers/net/ipa/gsi_trans.c
@@ -362,22 +362,31 @@
return trans;
}
-/* Free a previously-allocated transaction (used only in case of error) */
+/* Free a previously-allocated transaction */
void gsi_trans_free(struct gsi_trans *trans)
{
+ refcount_t *refcount = &trans->refcount;
struct gsi_trans_info *trans_info;
+ bool last;
- if (!refcount_dec_and_test(&trans->refcount))
+ /* We must hold the lock to release the last reference */
+ if (refcount_dec_not_one(refcount))
return;
trans_info = &trans->gsi->channel[trans->channel_id].trans_info;
spin_lock_bh(&trans_info->spinlock);
- list_del(&trans->links);
+ /* Reference might have been added before we got the lock */
+ last = refcount_dec_and_test(refcount);
+ if (last)
+ list_del(&trans->links);
spin_unlock_bh(&trans_info->spinlock);
+ if (!last)
+ return;
+
ipa_gsi_trans_release(trans);
/* Releasing the reserved TREs implicitly frees the sgl[] and
@@ -397,15 +406,24 @@
/* assert(which < trans->tre_count); */
- /* Set the page information for the buffer. We also need to fill in
- * the DMA address and length for the buffer (something dma_map_sg()
- * normally does).
+ /* Commands are quite different from data transfer requests.
+ * Their payloads come from a pool whose memory is allocated
+ * using dma_alloc_coherent(). We therefore do *not* map them
+ * for DMA (unlike what we do for pages and skbs).
+ *
+ * When a transaction completes, the SGL is normally unmapped.
+ * A command transaction has direction DMA_NONE, which tells
+ * gsi_trans_complete() to skip the unmapping step.
+ *
+ * The only things we use directly in a command scatter/gather
+ * entry are the DMA address and length. We still need the SG
+ * table flags to be maintained though, so assign a NULL page
+ * pointer for that purpose.
*/
sg = &trans->sgl[which];
-
- sg_set_buf(sg, buf, size);
+ sg_assign_page(sg, NULL);
sg_dma_address(sg) = addr;
- sg_dma_len(sg) = sg->length;
+ sg_dma_len(sg) = size;
info = &trans->info[which];
info->opcode = opcode;
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index d070614..e7972e8 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -96,6 +96,7 @@
.open = simple_open,
.write = nsim_dev_take_snapshot_write,
.llseek = generic_file_llseek,
+ .owner = THIS_MODULE,
};
static ssize_t nsim_dev_trap_fa_cookie_read(struct file *file,
@@ -188,6 +189,7 @@
.read = nsim_dev_trap_fa_cookie_read,
.write = nsim_dev_trap_fa_cookie_write,
.llseek = generic_file_llseek,
+ .owner = THIS_MODULE,
};
static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
diff --git a/drivers/net/netdevsim/health.c b/drivers/net/netdevsim/health.c
index 62958b2..21e2974 100644
--- a/drivers/net/netdevsim/health.c
+++ b/drivers/net/netdevsim/health.c
@@ -261,6 +261,7 @@
.open = simple_open,
.write = nsim_dev_health_break_write,
.llseek = generic_file_llseek,
+ .owner = THIS_MODULE,
};
int nsim_dev_health_init(struct nsim_dev *nsim_dev, struct devlink *devlink)
diff --git a/drivers/net/netdevsim/udp_tunnels.c b/drivers/net/netdevsim/udp_tunnels.c
index 6ab023a..02dc312 100644
--- a/drivers/net/netdevsim/udp_tunnels.c
+++ b/drivers/net/netdevsim/udp_tunnels.c
@@ -124,6 +124,7 @@
.open = simple_open,
.write = nsim_udp_tunnels_info_reset_write,
.llseek = generic_file_llseek,
+ .owner = THIS_MODULE,
};
int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev,
diff --git a/drivers/net/phy/mscc/mscc_macsec.c b/drivers/net/phy/mscc/mscc_macsec.c
index 6cf9b79..10be266 100644
--- a/drivers/net/phy/mscc/mscc_macsec.c
+++ b/drivers/net/phy/mscc/mscc_macsec.c
@@ -981,7 +981,6 @@
switch (phydev->phy_id & phydev->drv->phy_id_mask) {
case PHY_ID_VSC856X:
- case PHY_ID_VSC8575:
case PHY_ID_VSC8582:
case PHY_ID_VSC8584:
INIT_LIST_HEAD(&vsc8531->macsec_flows);
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index fb1db71..575580d 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -551,6 +551,8 @@
{
PHY_ID_MATCH_EXACT(0x00008201),
.name = "RTL8201CP Ethernet",
+ .read_page = rtl821x_read_page,
+ .write_page = rtl821x_write_page,
}, {
PHY_ID_MATCH_EXACT(0x001cc816),
.name = "RTL8201F Fast Ethernet",
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 1d18c10..34aa196 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -2389,7 +2389,8 @@
continue;
sfp->gpio_irq[i] = gpiod_to_irq(sfp->gpio[i]);
- if (!sfp->gpio_irq[i]) {
+ if (sfp->gpio_irq[i] < 0) {
+ sfp->gpio_irq[i] = 0;
sfp->need_poll = true;
continue;
}
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index ec97669..0fc39ac 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -291,8 +291,10 @@
return ret;
ret = clk_set_rate(priv->refclk, 50 * 1000 * 1000);
- if (ret)
+ if (ret) {
+ clk_disable_unprepare(priv->refclk);
return ret;
+ }
return 0;
}
diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c
index ca89d82..c4568a4 100644
--- a/drivers/net/usb/cx82310_eth.c
+++ b/drivers/net/usb/cx82310_eth.c
@@ -197,7 +197,8 @@
}
/* enable ethernet mode (?) */
- if (cx82310_enable_ethernet(dev))
+ ret = cx82310_enable_ethernet(dev);
+ if (ret)
goto err;
/* get the MAC address */
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index a322f51..fc378ff 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1070,7 +1070,7 @@
{QMI_FIXED_INTF(0x05c6, 0x9011, 4)},
{QMI_FIXED_INTF(0x05c6, 0x9021, 1)},
{QMI_FIXED_INTF(0x05c6, 0x9022, 2)},
- {QMI_FIXED_INTF(0x05c6, 0x9025, 4)}, /* Alcatel-sbell ASB TL131 TDD LTE (China Mobile) */
+ {QMI_QUIRK_SET_DTR(0x05c6, 0x9025, 4)}, /* Alcatel-sbell ASB TL131 TDD LTE (China Mobile) */
{QMI_FIXED_INTF(0x05c6, 0x9026, 3)},
{QMI_FIXED_INTF(0x05c6, 0x902e, 5)},
{QMI_FIXED_INTF(0x05c6, 0x9031, 5)},
@@ -1309,6 +1309,7 @@
{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */
{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)}, /* Telit LE920, LE920A4 */
+ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1230, 2)}, /* Telit LE910Cx */
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1260, 2)}, /* Telit LE910Cx */
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1261, 2)}, /* Telit LE910Cx */
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1900, 1)}, /* Telit LN940 series */
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 60c1aad..f2793ff 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -608,8 +608,7 @@
return ret;
}
-static int vrf_finish_direct(struct net *net, struct sock *sk,
- struct sk_buff *skb)
+static void vrf_finish_direct(struct sk_buff *skb)
{
struct net_device *vrf_dev = skb->dev;
@@ -628,7 +627,8 @@
skb_pull(skb, ETH_HLEN);
}
- return 1;
+ /* reset skb device */
+ nf_reset_ct(skb);
}
#if IS_ENABLED(CONFIG_IPV6)
@@ -707,15 +707,41 @@
return skb;
}
+static int vrf_output6_direct_finish(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
+{
+ vrf_finish_direct(skb);
+
+ return vrf_ip6_local_out(net, sk, skb);
+}
+
static int vrf_output6_direct(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
+ int err = 1;
+
skb->protocol = htons(ETH_P_IPV6);
- return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
- net, sk, skb, NULL, skb->dev,
- vrf_finish_direct,
- !(IPCB(skb)->flags & IPSKB_REROUTED));
+ if (!(IPCB(skb)->flags & IPSKB_REROUTED))
+ err = nf_hook(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb,
+ NULL, skb->dev, vrf_output6_direct_finish);
+
+ if (likely(err == 1))
+ vrf_finish_direct(skb);
+
+ return err;
+}
+
+static int vrf_ip6_out_direct_finish(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
+{
+ int err;
+
+ err = vrf_output6_direct(net, sk, skb);
+ if (likely(err == 1))
+ err = vrf_ip6_local_out(net, sk, skb);
+
+ return err;
}
static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev,
@@ -728,18 +754,15 @@
skb->dev = vrf_dev;
err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk,
- skb, NULL, vrf_dev, vrf_output6_direct);
+ skb, NULL, vrf_dev, vrf_ip6_out_direct_finish);
if (likely(err == 1))
err = vrf_output6_direct(net, sk, skb);
- /* reset skb device */
if (likely(err == 1))
- nf_reset_ct(skb);
- else
- skb = NULL;
+ return skb;
- return skb;
+ return NULL;
}
static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
@@ -919,15 +942,41 @@
return skb;
}
+static int vrf_output_direct_finish(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
+{
+ vrf_finish_direct(skb);
+
+ return vrf_ip_local_out(net, sk, skb);
+}
+
static int vrf_output_direct(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
+ int err = 1;
+
skb->protocol = htons(ETH_P_IP);
- return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
- net, sk, skb, NULL, skb->dev,
- vrf_finish_direct,
- !(IPCB(skb)->flags & IPSKB_REROUTED));
+ if (!(IPCB(skb)->flags & IPSKB_REROUTED))
+ err = nf_hook(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb,
+ NULL, skb->dev, vrf_output_direct_finish);
+
+ if (likely(err == 1))
+ vrf_finish_direct(skb);
+
+ return err;
+}
+
+static int vrf_ip_out_direct_finish(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
+{
+ int err;
+
+ err = vrf_output_direct(net, sk, skb);
+ if (likely(err == 1))
+ err = vrf_ip_local_out(net, sk, skb);
+
+ return err;
}
static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev,
@@ -940,18 +989,15 @@
skb->dev = vrf_dev;
err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk,
- skb, NULL, vrf_dev, vrf_output_direct);
+ skb, NULL, vrf_dev, vrf_ip_out_direct_finish);
if (likely(err == 1))
err = vrf_output_direct(net, sk, skb);
- /* reset skb device */
if (likely(err == 1))
- nf_reset_ct(skb);
- else
- skb = NULL;
+ return skb;
- return skb;
+ return NULL;
}
static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c
index f8aed06..2369ca2 100644
--- a/drivers/net/wan/cosa.c
+++ b/drivers/net/wan/cosa.c
@@ -889,6 +889,7 @@
chan->tx_status = 1;
spin_unlock_irqrestore(&cosa->lock, flags);
up(&chan->wsem);
+ kfree(kbuf);
return -ERESTARTSYS;
}
}
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 95ef494..9b01afc 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2060,8 +2060,6 @@
if (id->nsattr & NVME_NS_ATTR_RO)
set_disk_ro(disk, true);
- else
- set_disk_ro(disk, false);
}
static inline bool nvme_first_scan(struct gendisk *disk)
@@ -2125,7 +2123,7 @@
if (blk_queue_is_zoned(ns->queue)) {
ret = nvme_revalidate_zones(ns);
- if (ret)
+ if (ret && !nvme_first_scan(ns->disk))
return ret;
}
@@ -4582,8 +4580,7 @@
}
EXPORT_SYMBOL_GPL(nvme_start_queues);
-
-void nvme_sync_queues(struct nvme_ctrl *ctrl)
+void nvme_sync_io_queues(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
@@ -4591,7 +4588,12 @@
list_for_each_entry(ns, &ctrl->namespaces, list)
blk_sync_queue(ns->queue);
up_read(&ctrl->namespaces_rwsem);
+}
+EXPORT_SYMBOL_GPL(nvme_sync_io_queues);
+void nvme_sync_queues(struct nvme_ctrl *ctrl)
+{
+ nvme_sync_io_queues(ctrl);
if (ctrl->admin_q)
blk_sync_queue(ctrl->admin_q);
}
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 3c002bd..f4c2464 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -146,7 +146,8 @@
/* fc_ctrl flags values - specified as bit positions */
#define ASSOC_ACTIVE 0
-#define FCCTRL_TERMIO 1
+#define ASSOC_FAILED 1
+#define FCCTRL_TERMIO 2
struct nvme_fc_ctrl {
spinlock_t lock;
@@ -157,7 +158,6 @@
u32 cnum;
bool ioq_live;
- atomic_t err_work_active;
u64 association_id;
struct nvmefc_ls_rcv_op *rcv_disconn;
@@ -167,7 +167,6 @@
struct blk_mq_tag_set tag_set;
struct delayed_work connect_work;
- struct work_struct err_work;
struct kref ref;
unsigned long flags;
@@ -2414,24 +2413,97 @@
nvme_fc_ctrl_put(ctrl);
}
+/*
+ * This routine is used by the transport when it needs to find active
+ * io on a queue that is to be terminated. The transport uses
+ * blk_mq_tagset_busy_itr() to find the busy requests, which then invoke
+ * this routine to kill them on a 1 by 1 basis.
+ *
+ * As FC allocates FC exchange for each io, the transport must contact
+ * the LLDD to terminate the exchange, thus releasing the FC exchange.
+ * After terminating the exchange the LLDD will call the transport's
+ * normal io done path for the request, but it will have an aborted
+ * status. The done path will return the io request back to the block
+ * layer with an error status.
+ */
+static bool
+nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
+{
+ struct nvme_ctrl *nctrl = data;
+ struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
+ struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req);
+
+ __nvme_fc_abort_op(ctrl, op);
+ return true;
+}
+
+/*
+ * This routine runs through all outstanding commands on the association
+ * and aborts them. This routine is typically be called by the
+ * delete_association routine. It is also called due to an error during
+ * reconnect. In that scenario, it is most likely a command that initializes
+ * the controller, including fabric Connect commands on io queues, that
+ * may have timed out or failed thus the io must be killed for the connect
+ * thread to see the error.
+ */
+static void
+__nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues)
+{
+ /*
+ * If io queues are present, stop them and terminate all outstanding
+ * ios on them. As FC allocates FC exchange for each io, the
+ * transport must contact the LLDD to terminate the exchange,
+ * thus releasing the FC exchange. We use blk_mq_tagset_busy_itr()
+ * to tell us what io's are busy and invoke a transport routine
+ * to kill them with the LLDD. After terminating the exchange
+ * the LLDD will call the transport's normal io done path, but it
+ * will have an aborted status. The done path will return the
+ * io requests back to the block layer as part of normal completions
+ * (but with error status).
+ */
+ if (ctrl->ctrl.queue_count > 1) {
+ nvme_stop_queues(&ctrl->ctrl);
+ blk_mq_tagset_busy_iter(&ctrl->tag_set,
+ nvme_fc_terminate_exchange, &ctrl->ctrl);
+ blk_mq_tagset_wait_completed_request(&ctrl->tag_set);
+ if (start_queues)
+ nvme_start_queues(&ctrl->ctrl);
+ }
+
+ /*
+ * Other transports, which don't have link-level contexts bound
+ * to sqe's, would try to gracefully shutdown the controller by
+ * writing the registers for shutdown and polling (call
+ * nvme_shutdown_ctrl()). Given a bunch of i/o was potentially
+ * just aborted and we will wait on those contexts, and given
+ * there was no indication of how live the controlelr is on the
+ * link, don't send more io to create more contexts for the
+ * shutdown. Let the controller fail via keepalive failure if
+ * its still present.
+ */
+
+ /*
+ * clean up the admin queue. Same thing as above.
+ */
+ blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
+ nvme_fc_terminate_exchange, &ctrl->ctrl);
+ blk_mq_tagset_wait_completed_request(&ctrl->admin_tag_set);
+}
+
static void
nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
{
- int active;
-
/*
- * if an error (io timeout, etc) while (re)connecting,
- * it's an error on creating the new association.
- * Start the error recovery thread if it hasn't already
- * been started. It is expected there could be multiple
- * ios hitting this path before things are cleaned up.
+ * if an error (io timeout, etc) while (re)connecting, the remote
+ * port requested terminating of the association (disconnect_ls)
+ * or an error (timeout or abort) occurred on an io while creating
+ * the controller. Abort any ios on the association and let the
+ * create_association error path resolve things.
*/
if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
- active = atomic_xchg(&ctrl->err_work_active, 1);
- if (!active && !queue_work(nvme_fc_wq, &ctrl->err_work)) {
- atomic_set(&ctrl->err_work_active, 0);
- WARN_ON(1);
- }
+ __nvme_fc_abort_outstanding_ios(ctrl, true);
+ set_bit(ASSOC_FAILED, &ctrl->flags);
return;
}
@@ -2745,30 +2817,6 @@
nvme_fc_ctrl_put(ctrl);
}
-/*
- * This routine is used by the transport when it needs to find active
- * io on a queue that is to be terminated. The transport uses
- * blk_mq_tagset_busy_itr() to find the busy requests, which then invoke
- * this routine to kill them on a 1 by 1 basis.
- *
- * As FC allocates FC exchange for each io, the transport must contact
- * the LLDD to terminate the exchange, thus releasing the FC exchange.
- * After terminating the exchange the LLDD will call the transport's
- * normal io done path for the request, but it will have an aborted
- * status. The done path will return the io request back to the block
- * layer with an error status.
- */
-static bool
-nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
-{
- struct nvme_ctrl *nctrl = data;
- struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
- struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req);
-
- __nvme_fc_abort_op(ctrl, op);
- return true;
-}
-
static const struct blk_mq_ops nvme_fc_mq_ops = {
.queue_rq = nvme_fc_queue_rq,
@@ -2988,6 +3036,8 @@
ctrl->cnum, ctrl->lport->localport.port_name,
ctrl->rport->remoteport.port_name, ctrl->ctrl.opts->subsysnqn);
+ clear_bit(ASSOC_FAILED, &ctrl->flags);
+
/*
* Create the admin queue
*/
@@ -3016,7 +3066,7 @@
*/
ret = nvme_enable_ctrl(&ctrl->ctrl);
- if (ret)
+ if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
goto out_disconnect_admin_queue;
ctrl->ctrl.max_segments = ctrl->lport->ops->max_sgl_segments;
@@ -3026,7 +3076,7 @@
blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
ret = nvme_init_identify(&ctrl->ctrl);
- if (ret)
+ if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
goto out_disconnect_admin_queue;
/* sanity checks */
@@ -3071,9 +3121,9 @@
ret = nvme_fc_create_io_queues(ctrl);
else
ret = nvme_fc_recreate_io_queues(ctrl);
- if (ret)
- goto out_term_aen_ops;
}
+ if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
+ goto out_term_aen_ops;
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
@@ -3108,60 +3158,6 @@
/*
- * This routine runs through all outstanding commands on the association
- * and aborts them. This routine is typically be called by the
- * delete_association routine. It is also called due to an error during
- * reconnect. In that scenario, it is most likely a command that initializes
- * the controller, including fabric Connect commands on io queues, that
- * may have timed out or failed thus the io must be killed for the connect
- * thread to see the error.
- */
-static void
-__nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues)
-{
- /*
- * If io queues are present, stop them and terminate all outstanding
- * ios on them. As FC allocates FC exchange for each io, the
- * transport must contact the LLDD to terminate the exchange,
- * thus releasing the FC exchange. We use blk_mq_tagset_busy_itr()
- * to tell us what io's are busy and invoke a transport routine
- * to kill them with the LLDD. After terminating the exchange
- * the LLDD will call the transport's normal io done path, but it
- * will have an aborted status. The done path will return the
- * io requests back to the block layer as part of normal completions
- * (but with error status).
- */
- if (ctrl->ctrl.queue_count > 1) {
- nvme_stop_queues(&ctrl->ctrl);
- blk_mq_tagset_busy_iter(&ctrl->tag_set,
- nvme_fc_terminate_exchange, &ctrl->ctrl);
- blk_mq_tagset_wait_completed_request(&ctrl->tag_set);
- if (start_queues)
- nvme_start_queues(&ctrl->ctrl);
- }
-
- /*
- * Other transports, which don't have link-level contexts bound
- * to sqe's, would try to gracefully shutdown the controller by
- * writing the registers for shutdown and polling (call
- * nvme_shutdown_ctrl()). Given a bunch of i/o was potentially
- * just aborted and we will wait on those contexts, and given
- * there was no indication of how live the controlelr is on the
- * link, don't send more io to create more contexts for the
- * shutdown. Let the controller fail via keepalive failure if
- * its still present.
- */
-
- /*
- * clean up the admin queue. Same thing as above.
- */
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
- blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
- nvme_fc_terminate_exchange, &ctrl->ctrl);
- blk_mq_tagset_wait_completed_request(&ctrl->admin_tag_set);
-}
-
-/*
* This routine stops operation of the controller on the host side.
* On the host os stack side: Admin and IO queues are stopped,
* outstanding ios on them terminated via FC ABTS.
@@ -3237,7 +3233,6 @@
{
struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
- cancel_work_sync(&ctrl->err_work);
cancel_delayed_work_sync(&ctrl->connect_work);
/*
* kill the association on the link side. this will block
@@ -3292,78 +3287,34 @@
}
static void
-__nvme_fc_terminate_io(struct nvme_fc_ctrl *ctrl)
-{
- /*
- * if state is CONNECTING - the error occurred as part of a
- * reconnect attempt. Abort any ios on the association and
- * let the create_association error paths resolve things.
- */
- if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
- __nvme_fc_abort_outstanding_ios(ctrl, true);
- return;
- }
-
- /*
- * For any other state, kill the association. As this routine
- * is a common io abort routine for resetting and such, after
- * the association is terminated, ensure that the state is set
- * to CONNECTING.
- */
-
- nvme_stop_keep_alive(&ctrl->ctrl);
-
- /* will block will waiting for io to terminate */
- nvme_fc_delete_association(ctrl);
-
- if (ctrl->ctrl.state != NVME_CTRL_CONNECTING &&
- !nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING))
- dev_err(ctrl->ctrl.device,
- "NVME-FC{%d}: error_recovery: Couldn't change state "
- "to CONNECTING\n", ctrl->cnum);
-}
-
-static void
nvme_fc_reset_ctrl_work(struct work_struct *work)
{
struct nvme_fc_ctrl *ctrl =
container_of(work, struct nvme_fc_ctrl, ctrl.reset_work);
- int ret;
-
- __nvme_fc_terminate_io(ctrl);
nvme_stop_ctrl(&ctrl->ctrl);
- if (ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE)
- ret = nvme_fc_create_association(ctrl);
- else
- ret = -ENOTCONN;
+ /* will block will waiting for io to terminate */
+ nvme_fc_delete_association(ctrl);
- if (ret)
- nvme_fc_reconnect_or_delete(ctrl, ret);
- else
- dev_info(ctrl->ctrl.device,
- "NVME-FC{%d}: controller reset complete\n",
- ctrl->cnum);
+ if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING))
+ dev_err(ctrl->ctrl.device,
+ "NVME-FC{%d}: error_recovery: Couldn't change state "
+ "to CONNECTING\n", ctrl->cnum);
+
+ if (ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE) {
+ if (!queue_delayed_work(nvme_wq, &ctrl->connect_work, 0)) {
+ dev_err(ctrl->ctrl.device,
+ "NVME-FC{%d}: failed to schedule connect "
+ "after reset\n", ctrl->cnum);
+ } else {
+ flush_delayed_work(&ctrl->connect_work);
+ }
+ } else {
+ nvme_fc_reconnect_or_delete(ctrl, -ENOTCONN);
+ }
}
-static void
-nvme_fc_connect_err_work(struct work_struct *work)
-{
- struct nvme_fc_ctrl *ctrl =
- container_of(work, struct nvme_fc_ctrl, err_work);
-
- __nvme_fc_terminate_io(ctrl);
-
- atomic_set(&ctrl->err_work_active, 0);
-
- /*
- * Rescheduling the connection after recovering
- * from the io error is left to the reconnect work
- * item, which is what should have stalled waiting on
- * the io that had the error that scheduled this work.
- */
-}
static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = {
.name = "fc",
@@ -3491,7 +3442,6 @@
ctrl->dev = lport->dev;
ctrl->cnum = idx;
ctrl->ioq_live = false;
- atomic_set(&ctrl->err_work_active, 0);
init_waitqueue_head(&ctrl->ioabort_wait);
get_device(ctrl->dev);
@@ -3499,7 +3449,6 @@
INIT_WORK(&ctrl->ctrl.reset_work, nvme_fc_reset_ctrl_work);
INIT_DELAYED_WORK(&ctrl->connect_work, nvme_fc_connect_ctrl_work);
- INIT_WORK(&ctrl->err_work, nvme_fc_connect_err_work);
spin_lock_init(&ctrl->lock);
/* io queue count */
@@ -3592,7 +3541,6 @@
fail_ctrl:
nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING);
cancel_work_sync(&ctrl->ctrl.reset_work);
- cancel_work_sync(&ctrl->err_work);
cancel_delayed_work_sync(&ctrl->connect_work);
ctrl->ctrl.opts = NULL;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index cc11113..bc330bf 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -602,6 +602,7 @@
void nvme_start_queues(struct nvme_ctrl *ctrl);
void nvme_kill_queues(struct nvme_ctrl *ctrl);
void nvme_sync_queues(struct nvme_ctrl *ctrl);
+void nvme_sync_io_queues(struct nvme_ctrl *ctrl);
void nvme_unfreeze(struct nvme_ctrl *ctrl);
void nvme_wait_freeze(struct nvme_ctrl *ctrl);
int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index df8f361..0578ff2 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -198,6 +198,7 @@
u32 q_depth;
u16 cq_vector;
u16 sq_tail;
+ u16 last_sq_tail;
u16 cq_head;
u16 qid;
u8 cq_phase;
@@ -455,11 +456,24 @@
return 0;
}
-static inline void nvme_write_sq_db(struct nvme_queue *nvmeq)
+/*
+ * Write sq tail if we are asked to, or if the next command would wrap.
+ */
+static inline void nvme_write_sq_db(struct nvme_queue *nvmeq, bool write_sq)
{
+ if (!write_sq) {
+ u16 next_tail = nvmeq->sq_tail + 1;
+
+ if (next_tail == nvmeq->q_depth)
+ next_tail = 0;
+ if (next_tail != nvmeq->last_sq_tail)
+ return;
+ }
+
if (nvme_dbbuf_update_and_check_event(nvmeq->sq_tail,
nvmeq->dbbuf_sq_db, nvmeq->dbbuf_sq_ei))
writel(nvmeq->sq_tail, nvmeq->q_db);
+ nvmeq->last_sq_tail = nvmeq->sq_tail;
}
/**
@@ -476,8 +490,7 @@
cmd, sizeof(*cmd));
if (++nvmeq->sq_tail == nvmeq->q_depth)
nvmeq->sq_tail = 0;
- if (write_sq)
- nvme_write_sq_db(nvmeq);
+ nvme_write_sq_db(nvmeq, write_sq);
spin_unlock(&nvmeq->sq_lock);
}
@@ -486,7 +499,8 @@
struct nvme_queue *nvmeq = hctx->driver_data;
spin_lock(&nvmeq->sq_lock);
- nvme_write_sq_db(nvmeq);
+ if (nvmeq->sq_tail != nvmeq->last_sq_tail)
+ nvme_write_sq_db(nvmeq, true);
spin_unlock(&nvmeq->sq_lock);
}
@@ -1496,6 +1510,7 @@
struct nvme_dev *dev = nvmeq->dev;
nvmeq->sq_tail = 0;
+ nvmeq->last_sq_tail = 0;
nvmeq->cq_head = 0;
nvmeq->cq_phase = 1;
nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index aad829a..65e3d0e 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -122,7 +122,6 @@
struct sockaddr_storage src_addr;
struct nvme_ctrl ctrl;
- struct mutex teardown_lock;
bool use_inline_data;
u32 io_queues[HCTX_MAX_TYPES];
};
@@ -1010,8 +1009,8 @@
static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
bool remove)
{
- mutex_lock(&ctrl->teardown_lock);
blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ blk_sync_queue(ctrl->ctrl.admin_q);
nvme_rdma_stop_queue(&ctrl->queues[0]);
if (ctrl->ctrl.admin_tagset) {
blk_mq_tagset_busy_iter(ctrl->ctrl.admin_tagset,
@@ -1021,16 +1020,15 @@
if (remove)
blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
nvme_rdma_destroy_admin_queue(ctrl, remove);
- mutex_unlock(&ctrl->teardown_lock);
}
static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
bool remove)
{
- mutex_lock(&ctrl->teardown_lock);
if (ctrl->ctrl.queue_count > 1) {
nvme_start_freeze(&ctrl->ctrl);
nvme_stop_queues(&ctrl->ctrl);
+ nvme_sync_io_queues(&ctrl->ctrl);
nvme_rdma_stop_io_queues(ctrl);
if (ctrl->ctrl.tagset) {
blk_mq_tagset_busy_iter(ctrl->ctrl.tagset,
@@ -1041,7 +1039,6 @@
nvme_start_queues(&ctrl->ctrl);
nvme_rdma_destroy_io_queues(ctrl, remove);
}
- mutex_unlock(&ctrl->teardown_lock);
}
static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
@@ -1768,6 +1765,14 @@
return;
}
+ /* sanity checking for received data length */
+ if (unlikely(wc->byte_len < len)) {
+ dev_err(queue->ctrl->ctrl.device,
+ "Unexpected nvme completion length(%d)\n", wc->byte_len);
+ nvme_rdma_error_recovery(queue->ctrl);
+ return;
+ }
+
ib_dma_sync_single_for_cpu(ibdev, qe->dma, len, DMA_FROM_DEVICE);
/*
* AEN requests are special as they don't time out and can
@@ -1890,10 +1895,10 @@
priv.hsqsize = cpu_to_le16(queue->ctrl->ctrl.sqsize);
}
- ret = rdma_connect(queue->cm_id, ¶m);
+ ret = rdma_connect_locked(queue->cm_id, ¶m);
if (ret) {
dev_err(ctrl->ctrl.device,
- "rdma_connect failed (%d).\n", ret);
+ "rdma_connect_locked failed (%d).\n", ret);
goto out_destroy_queue_ib;
}
@@ -1968,16 +1973,12 @@
{
struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
struct nvme_rdma_queue *queue = req->queue;
- struct nvme_rdma_ctrl *ctrl = queue->ctrl;
- /* fence other contexts that may complete the command */
- mutex_lock(&ctrl->teardown_lock);
nvme_rdma_stop_queue(queue);
- if (!blk_mq_request_completed(rq)) {
+ if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) {
nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
blk_mq_complete_request(rq);
}
- mutex_unlock(&ctrl->teardown_lock);
}
static enum blk_eh_timer_return
@@ -2312,7 +2313,6 @@
return ERR_PTR(-ENOMEM);
ctrl->ctrl.opts = opts;
INIT_LIST_HEAD(&ctrl->list);
- mutex_init(&ctrl->teardown_lock);
if (!(opts->mask & NVMF_OPT_TRSVCID)) {
opts->trsvcid =
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index d6a3e14..c0c3332 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -124,7 +124,6 @@
struct sockaddr_storage src_addr;
struct nvme_ctrl ctrl;
- struct mutex teardown_lock;
struct work_struct err_work;
struct delayed_work connect_work;
struct nvme_tcp_request async_req;
@@ -1886,8 +1885,8 @@
static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
bool remove)
{
- mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
blk_mq_quiesce_queue(ctrl->admin_q);
+ blk_sync_queue(ctrl->admin_q);
nvme_tcp_stop_queue(ctrl, 0);
if (ctrl->admin_tagset) {
blk_mq_tagset_busy_iter(ctrl->admin_tagset,
@@ -1897,18 +1896,17 @@
if (remove)
blk_mq_unquiesce_queue(ctrl->admin_q);
nvme_tcp_destroy_admin_queue(ctrl, remove);
- mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
}
static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
bool remove)
{
- mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
if (ctrl->queue_count <= 1)
- goto out;
+ return;
blk_mq_quiesce_queue(ctrl->admin_q);
nvme_start_freeze(ctrl);
nvme_stop_queues(ctrl);
+ nvme_sync_io_queues(ctrl);
nvme_tcp_stop_io_queues(ctrl);
if (ctrl->tagset) {
blk_mq_tagset_busy_iter(ctrl->tagset,
@@ -1918,8 +1916,6 @@
if (remove)
nvme_start_queues(ctrl);
nvme_tcp_destroy_io_queues(ctrl, remove);
-out:
- mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
}
static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
@@ -2171,14 +2167,11 @@
struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
- /* fence other contexts that may complete the command */
- mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue));
- if (!blk_mq_request_completed(rq)) {
+ if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) {
nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
blk_mq_complete_request(rq);
}
- mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
}
static enum blk_eh_timer_return
@@ -2455,7 +2448,6 @@
nvme_tcp_reconnect_ctrl_work);
INIT_WORK(&ctrl->err_work, nvme_tcp_error_recovery_work);
INIT_WORK(&ctrl->ctrl.reset_work, nvme_reset_ctrl_work);
- mutex_init(&ctrl->teardown_lock);
if (!(opts->mask & NVMF_OPT_TRSVCID)) {
opts->trsvcid =
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index aafcbc4..957b39a 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -907,8 +907,6 @@
req->error_loc = NVMET_NO_ERROR_LOC;
req->error_slba = 0;
- trace_nvmet_req_init(req, req->cmd);
-
/* no support for fused commands yet */
if (unlikely(flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND))) {
req->error_loc = offsetof(struct nvme_common_command, flags);
@@ -938,6 +936,8 @@
if (status)
goto fail;
+ trace_nvmet_req_init(req, req->cmd);
+
if (unlikely(!percpu_ref_tryget_live(&sq->ref))) {
status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
goto fail;
diff --git a/drivers/nvme/target/trace.h b/drivers/nvme/target/trace.h
index 0458046..c14e324 100644
--- a/drivers/nvme/target/trace.h
+++ b/drivers/nvme/target/trace.h
@@ -46,19 +46,12 @@
return req->sq->ctrl;
}
-static inline void __assign_disk_name(char *name, struct nvmet_req *req,
- bool init)
+static inline void __assign_req_name(char *name, struct nvmet_req *req)
{
- struct nvmet_ctrl *ctrl = nvmet_req_to_ctrl(req);
- struct nvmet_ns *ns;
-
- if ((init && req->sq->qid) || (!init && req->cq->qid)) {
- ns = nvmet_find_namespace(ctrl, req->cmd->rw.nsid);
- strncpy(name, ns->device_path, DISK_NAME_LEN);
- return;
- }
-
- memset(name, 0, DISK_NAME_LEN);
+ if (req->ns)
+ strncpy(name, req->ns->device_path, DISK_NAME_LEN);
+ else
+ memset(name, 0, DISK_NAME_LEN);
}
#endif
@@ -81,7 +74,7 @@
TP_fast_assign(
__entry->cmd = cmd;
__entry->ctrl = nvmet_req_to_ctrl(req);
- __assign_disk_name(__entry->disk, req, true);
+ __assign_req_name(__entry->disk, req);
__entry->qid = req->sq->qid;
__entry->cid = cmd->common.command_id;
__entry->opcode = cmd->common.opcode;
@@ -121,7 +114,7 @@
__entry->cid = req->cqe->command_id;
__entry->result = le64_to_cpu(req->cqe->result.u64);
__entry->status = le16_to_cpu(req->cqe->status) >> 1;
- __assign_disk_name(__entry->disk, req, false);
+ __assign_req_name(__entry->disk, req);
),
TP_printk("nvmet%s: %sqid=%d, cmdid=%u, res=%#llx, status=%#x",
__print_ctrl_name(__entry->ctrl),
diff --git a/drivers/of/address.c b/drivers/of/address.c
index eb9ab4f..1c3257a 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -1034,11 +1034,13 @@
*/
bool of_dma_is_coherent(struct device_node *np)
{
- struct device_node *node = of_node_get(np);
+ struct device_node *node;
if (IS_ENABLED(CONFIG_OF_DMA_DEFAULT_COHERENT))
return true;
+ node = of_node_get(np);
+
while (node) {
if (of_property_read_bool(node, "dma-coherent")) {
of_node_put(node);
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 655dee4..aedfaaa 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -93,7 +93,7 @@
{
const struct iommu_ops *iommu;
const struct bus_dma_region *map = NULL;
- dma_addr_t dma_start = 0;
+ u64 dma_start = 0;
u64 mask, end, size = 0;
bool coherent;
int ret;
@@ -109,10 +109,10 @@
return ret == -ENODEV ? 0 : ret;
} else {
const struct bus_dma_region *r = map;
- dma_addr_t dma_end = 0;
+ u64 dma_end = 0;
/* Determine the overall bounds of all DMA regions */
- for (dma_start = ~(dma_addr_t)0; r->size; r++) {
+ for (dma_start = ~0; r->size; r++) {
/* Take lower and upper limits */
if (r->dma_start < dma_start)
dma_start = r->dma_start;
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index bcd1544..a7fbc5e 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -200,6 +200,16 @@
if (ra->base > rb->base)
return 1;
+ /*
+ * Put the dynamic allocations (address == 0, size == 0) before static
+ * allocations at address 0x0 so that overlap detection works
+ * correctly.
+ */
+ if (ra->size < rb->size)
+ return -1;
+ if (ra->size > rb->size)
+ return 1;
+
return 0;
}
@@ -217,8 +227,7 @@
this = &reserved_mem[i];
next = &reserved_mem[i + 1];
- if (!(this->base && next->base))
- continue;
+
if (this->base + this->size > next->base) {
phys_addr_t this_end, next_end;
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 2483e76..0e0a526 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -1181,6 +1181,10 @@
struct opp_device *opp_dev, *temp;
int i;
+ /* Drop the lock as soon as we can */
+ list_del(&opp_table->node);
+ mutex_unlock(&opp_table_lock);
+
_of_clear_opp_table(opp_table);
/* Release clk */
@@ -1208,10 +1212,7 @@
mutex_destroy(&opp_table->genpd_virt_dev_lock);
mutex_destroy(&opp_table->lock);
- list_del(&opp_table->node);
kfree(opp_table);
-
- mutex_unlock(&opp_table_lock);
}
void dev_pm_opp_put_opp_table(struct opp_table *opp_table)
@@ -1930,7 +1931,7 @@
return ERR_PTR(-EINVAL);
opp_table = dev_pm_opp_get_opp_table(dev);
- if (!IS_ERR(opp_table))
+ if (IS_ERR(opp_table))
return opp_table;
/* This should be called before OPPs are initialized */
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 874b587..9faeb83 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -944,6 +944,8 @@
nr -= 2;
}
+ return 0;
+
remove_static_opp:
_opp_remove_all_static(opp_table);
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 674f32d..44c2a65 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -586,8 +586,12 @@
* ATU, so we should not program the ATU here.
*/
if (pp->bridge->child_ops == &dw_child_pcie_ops) {
- struct resource_entry *entry =
- resource_list_first_type(&pp->bridge->windows, IORESOURCE_MEM);
+ struct resource_entry *tmp, *entry = NULL;
+
+ /* Get last memory resource entry */
+ resource_list_for_each_entry(tmp, &pp->bridge->windows)
+ if (resource_type(tmp->res) == IORESOURCE_MEM)
+ entry = tmp;
dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX0,
PCIE_ATU_TYPE_MEM, entry->res->start,
diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index eee8283..ed13e81 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -958,25 +958,16 @@
}
/*
- * We can't use devm_of_pci_get_host_bridge_resources() because we
- * need to parse our special DT properties encoding the MEM and IO
- * apertures.
+ * devm_of_pci_get_host_bridge_resources() only sets up translateable resources,
+ * so we need extra resource setup parsing our special DT properties encoding
+ * the MEM and IO apertures.
*/
static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie)
{
struct device *dev = &pcie->pdev->dev;
- struct device_node *np = dev->of_node;
struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie);
int ret;
- /* Get the bus range */
- ret = of_pci_parse_bus_range(np, &pcie->busn);
- if (ret) {
- dev_err(dev, "failed to parse bus-range property: %d\n", ret);
- return ret;
- }
- pci_add_resource(&bridge->windows, &pcie->busn);
-
/* Get the PCIe memory aperture */
mvebu_mbus_get_pcie_mem_aperture(&pcie->mem);
if (resource_size(&pcie->mem) == 0) {
@@ -986,6 +977,9 @@
pcie->mem.name = "PCI MEM";
pci_add_resource(&bridge->windows, &pcie->mem);
+ ret = devm_request_resource(dev, &iomem_resource, &pcie->mem);
+ if (ret)
+ return ret;
/* Get the PCIe IO aperture */
mvebu_mbus_get_pcie_io_aperture(&pcie->io);
@@ -999,9 +993,12 @@
pcie->realio.name = "PCI I/O";
pci_add_resource(&bridge->windows, &pcie->realio);
+ ret = devm_request_resource(dev, &ioport_resource, &pcie->realio);
+ if (ret)
+ return ret;
}
- return devm_request_pci_bus_resources(dev, &bridge->windows);
+ return 0;
}
/*
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 6d4d5a2..e578d34 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3516,8 +3516,13 @@
{
dev->acs_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
- if (dev->acs_cap)
- pci_enable_acs(dev);
+ /*
+ * Attempt to enable ACS regardless of capability because some Root
+ * Ports (e.g. those quirked with *_intel_pch_acs_*) do not have
+ * the standard ACS capability but still support ACS via those
+ * quirks.
+ */
+ pci_enable_acs(dev);
}
/**
diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.c b/drivers/pinctrl/aspeed/pinctrl-aspeed.c
index 6a94eae..d6b8495 100644
--- a/drivers/pinctrl/aspeed/pinctrl-aspeed.c
+++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.c
@@ -286,13 +286,14 @@
static bool aspeed_expr_is_gpio(const struct aspeed_sig_expr *expr)
{
/*
- * The signal type is GPIO if the signal name has "GPIO" as a prefix.
+ * The signal type is GPIO if the signal name has "GPI" as a prefix.
* strncmp (rather than strcmp) is used to implement the prefix
* requirement.
*
- * expr->signal might look like "GPIOT3" in the GPIO case.
+ * expr->signal might look like "GPIOB1" in the GPIO case.
+ * expr->signal might look like "GPIT0" in the GPI case.
*/
- return strncmp(expr->signal, "GPIO", 4) == 0;
+ return strncmp(expr->signal, "GPI", 3) == 0;
}
static bool aspeed_gpio_in_exprs(const struct aspeed_sig_expr **exprs)
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 154ce3f..1c10ab1 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -62,10 +62,10 @@
#define PADCFG1_TERM_UP BIT(13)
#define PADCFG1_TERM_SHIFT 10
#define PADCFG1_TERM_MASK GENMASK(12, 10)
-#define PADCFG1_TERM_20K 4
-#define PADCFG1_TERM_2K 3
-#define PADCFG1_TERM_5K 2
-#define PADCFG1_TERM_1K 1
+#define PADCFG1_TERM_20K BIT(2)
+#define PADCFG1_TERM_5K BIT(1)
+#define PADCFG1_TERM_1K BIT(0)
+#define PADCFG1_TERM_833 (BIT(1) | BIT(0))
#define PADCFG2 0x008
#define PADCFG2_DEBEN BIT(0)
@@ -549,12 +549,12 @@
return -EINVAL;
switch (term) {
+ case PADCFG1_TERM_833:
+ *arg = 833;
+ break;
case PADCFG1_TERM_1K:
*arg = 1000;
break;
- case PADCFG1_TERM_2K:
- *arg = 2000;
- break;
case PADCFG1_TERM_5K:
*arg = 5000;
break;
@@ -570,6 +570,11 @@
return -EINVAL;
switch (term) {
+ case PADCFG1_TERM_833:
+ if (!(community->features & PINCTRL_FEATURE_1K_PD))
+ return -EINVAL;
+ *arg = 833;
+ break;
case PADCFG1_TERM_1K:
if (!(community->features & PINCTRL_FEATURE_1K_PD))
return -EINVAL;
@@ -678,6 +683,10 @@
value |= PADCFG1_TERM_UP;
+ /* Set default strength value in case none is given */
+ if (arg == 1)
+ arg = 5000;
+
switch (arg) {
case 20000:
value |= PADCFG1_TERM_20K << PADCFG1_TERM_SHIFT;
@@ -685,12 +694,12 @@
case 5000:
value |= PADCFG1_TERM_5K << PADCFG1_TERM_SHIFT;
break;
- case 2000:
- value |= PADCFG1_TERM_2K << PADCFG1_TERM_SHIFT;
- break;
case 1000:
value |= PADCFG1_TERM_1K << PADCFG1_TERM_SHIFT;
break;
+ case 833:
+ value |= PADCFG1_TERM_833 << PADCFG1_TERM_SHIFT;
+ break;
default:
ret = -EINVAL;
}
@@ -700,6 +709,10 @@
case PIN_CONFIG_BIAS_PULL_DOWN:
value &= ~(PADCFG1_TERM_UP | PADCFG1_TERM_MASK);
+ /* Set default strength value in case none is given */
+ if (arg == 1)
+ arg = 5000;
+
switch (arg) {
case 20000:
value |= PADCFG1_TERM_20K << PADCFG1_TERM_SHIFT;
@@ -714,6 +727,13 @@
}
value |= PADCFG1_TERM_1K << PADCFG1_TERM_SHIFT;
break;
+ case 833:
+ if (!(community->features & PINCTRL_FEATURE_1K_PD)) {
+ ret = -EINVAL;
+ break;
+ }
+ value |= PADCFG1_TERM_833 << PADCFG1_TERM_SHIFT;
+ break;
default:
ret = -EINVAL;
}
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 9a760f5..4aea3e0 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -156,7 +156,7 @@
pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF);
pin_reg &= ~BIT(DB_TMR_LARGE_OFF);
} else if (debounce < 250000) {
- time = debounce / 15600;
+ time = debounce / 15625;
pin_reg |= time & DB_TMR_OUT_MASK;
pin_reg &= ~BIT(DB_TMR_OUT_UNIT_OFF);
pin_reg |= BIT(DB_TMR_LARGE_OFF);
@@ -166,14 +166,14 @@
pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF);
pin_reg |= BIT(DB_TMR_LARGE_OFF);
} else {
- pin_reg &= ~DB_CNTRl_MASK;
+ pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF);
ret = -EINVAL;
}
} else {
pin_reg &= ~BIT(DB_TMR_OUT_UNIT_OFF);
pin_reg &= ~BIT(DB_TMR_LARGE_OFF);
pin_reg &= ~DB_TMR_OUT_MASK;
- pin_reg &= ~DB_CNTRl_MASK;
+ pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF);
}
writel(pin_reg, gpio_dev->base + offset * 4);
raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c
index c8e50a5..621909b 100644
--- a/drivers/pinctrl/pinctrl-ingenic.c
+++ b/drivers/pinctrl/pinctrl-ingenic.c
@@ -635,44 +635,44 @@
static int jz4770_uart3_hwflow_pins[] = { 0x88, 0x89, };
static int jz4770_ssi0_dt_a_pins[] = { 0x15, };
static int jz4770_ssi0_dt_b_pins[] = { 0x35, };
-static int jz4770_ssi0_dt_d_pins[] = { 0x55, };
-static int jz4770_ssi0_dt_e_pins[] = { 0x71, };
+static int jz4770_ssi0_dt_d_pins[] = { 0x75, };
+static int jz4770_ssi0_dt_e_pins[] = { 0x91, };
static int jz4770_ssi0_dr_a_pins[] = { 0x14, };
static int jz4770_ssi0_dr_b_pins[] = { 0x34, };
-static int jz4770_ssi0_dr_d_pins[] = { 0x54, };
-static int jz4770_ssi0_dr_e_pins[] = { 0x6e, };
+static int jz4770_ssi0_dr_d_pins[] = { 0x74, };
+static int jz4770_ssi0_dr_e_pins[] = { 0x8e, };
static int jz4770_ssi0_clk_a_pins[] = { 0x12, };
static int jz4770_ssi0_clk_b_pins[] = { 0x3c, };
-static int jz4770_ssi0_clk_d_pins[] = { 0x58, };
-static int jz4770_ssi0_clk_e_pins[] = { 0x6f, };
+static int jz4770_ssi0_clk_d_pins[] = { 0x78, };
+static int jz4770_ssi0_clk_e_pins[] = { 0x8f, };
static int jz4770_ssi0_gpc_b_pins[] = { 0x3e, };
-static int jz4770_ssi0_gpc_d_pins[] = { 0x56, };
-static int jz4770_ssi0_gpc_e_pins[] = { 0x73, };
+static int jz4770_ssi0_gpc_d_pins[] = { 0x76, };
+static int jz4770_ssi0_gpc_e_pins[] = { 0x93, };
static int jz4770_ssi0_ce0_a_pins[] = { 0x13, };
static int jz4770_ssi0_ce0_b_pins[] = { 0x3d, };
-static int jz4770_ssi0_ce0_d_pins[] = { 0x59, };
-static int jz4770_ssi0_ce0_e_pins[] = { 0x70, };
+static int jz4770_ssi0_ce0_d_pins[] = { 0x79, };
+static int jz4770_ssi0_ce0_e_pins[] = { 0x90, };
static int jz4770_ssi0_ce1_b_pins[] = { 0x3f, };
-static int jz4770_ssi0_ce1_d_pins[] = { 0x57, };
-static int jz4770_ssi0_ce1_e_pins[] = { 0x72, };
+static int jz4770_ssi0_ce1_d_pins[] = { 0x77, };
+static int jz4770_ssi0_ce1_e_pins[] = { 0x92, };
static int jz4770_ssi1_dt_b_pins[] = { 0x35, };
-static int jz4770_ssi1_dt_d_pins[] = { 0x55, };
-static int jz4770_ssi1_dt_e_pins[] = { 0x71, };
+static int jz4770_ssi1_dt_d_pins[] = { 0x75, };
+static int jz4770_ssi1_dt_e_pins[] = { 0x91, };
static int jz4770_ssi1_dr_b_pins[] = { 0x34, };
-static int jz4770_ssi1_dr_d_pins[] = { 0x54, };
-static int jz4770_ssi1_dr_e_pins[] = { 0x6e, };
+static int jz4770_ssi1_dr_d_pins[] = { 0x74, };
+static int jz4770_ssi1_dr_e_pins[] = { 0x8e, };
static int jz4770_ssi1_clk_b_pins[] = { 0x3c, };
-static int jz4770_ssi1_clk_d_pins[] = { 0x58, };
-static int jz4770_ssi1_clk_e_pins[] = { 0x6f, };
+static int jz4770_ssi1_clk_d_pins[] = { 0x78, };
+static int jz4770_ssi1_clk_e_pins[] = { 0x8f, };
static int jz4770_ssi1_gpc_b_pins[] = { 0x3e, };
-static int jz4770_ssi1_gpc_d_pins[] = { 0x56, };
-static int jz4770_ssi1_gpc_e_pins[] = { 0x73, };
+static int jz4770_ssi1_gpc_d_pins[] = { 0x76, };
+static int jz4770_ssi1_gpc_e_pins[] = { 0x93, };
static int jz4770_ssi1_ce0_b_pins[] = { 0x3d, };
-static int jz4770_ssi1_ce0_d_pins[] = { 0x59, };
-static int jz4770_ssi1_ce0_e_pins[] = { 0x70, };
+static int jz4770_ssi1_ce0_d_pins[] = { 0x79, };
+static int jz4770_ssi1_ce0_e_pins[] = { 0x90, };
static int jz4770_ssi1_ce1_b_pins[] = { 0x3f, };
-static int jz4770_ssi1_ce1_d_pins[] = { 0x57, };
-static int jz4770_ssi1_ce1_e_pins[] = { 0x72, };
+static int jz4770_ssi1_ce1_d_pins[] = { 0x77, };
+static int jz4770_ssi1_ce1_e_pins[] = { 0x92, };
static int jz4770_mmc0_1bit_a_pins[] = { 0x12, 0x13, 0x14, };
static int jz4770_mmc0_4bit_a_pins[] = { 0x15, 0x16, 0x17, };
static int jz4770_mmc0_1bit_e_pins[] = { 0x9c, 0x9d, 0x94, };
@@ -1050,35 +1050,35 @@
static int jz4780_ssi0_dt_a_21_pins[] = { 0x15, };
static int jz4780_ssi0_dt_a_28_pins[] = { 0x1c, };
static int jz4780_ssi0_dt_b_pins[] = { 0x3d, };
-static int jz4780_ssi0_dt_d_pins[] = { 0x59, };
+static int jz4780_ssi0_dt_d_pins[] = { 0x79, };
static int jz4780_ssi0_dr_a_20_pins[] = { 0x14, };
static int jz4780_ssi0_dr_a_27_pins[] = { 0x1b, };
static int jz4780_ssi0_dr_b_pins[] = { 0x34, };
-static int jz4780_ssi0_dr_d_pins[] = { 0x54, };
+static int jz4780_ssi0_dr_d_pins[] = { 0x74, };
static int jz4780_ssi0_clk_a_pins[] = { 0x12, };
static int jz4780_ssi0_clk_b_5_pins[] = { 0x25, };
static int jz4780_ssi0_clk_b_28_pins[] = { 0x3c, };
-static int jz4780_ssi0_clk_d_pins[] = { 0x58, };
+static int jz4780_ssi0_clk_d_pins[] = { 0x78, };
static int jz4780_ssi0_gpc_b_pins[] = { 0x3e, };
-static int jz4780_ssi0_gpc_d_pins[] = { 0x56, };
+static int jz4780_ssi0_gpc_d_pins[] = { 0x76, };
static int jz4780_ssi0_ce0_a_23_pins[] = { 0x17, };
static int jz4780_ssi0_ce0_a_25_pins[] = { 0x19, };
static int jz4780_ssi0_ce0_b_pins[] = { 0x3f, };
-static int jz4780_ssi0_ce0_d_pins[] = { 0x57, };
+static int jz4780_ssi0_ce0_d_pins[] = { 0x77, };
static int jz4780_ssi0_ce1_b_pins[] = { 0x35, };
-static int jz4780_ssi0_ce1_d_pins[] = { 0x55, };
+static int jz4780_ssi0_ce1_d_pins[] = { 0x75, };
static int jz4780_ssi1_dt_b_pins[] = { 0x3d, };
-static int jz4780_ssi1_dt_d_pins[] = { 0x59, };
+static int jz4780_ssi1_dt_d_pins[] = { 0x79, };
static int jz4780_ssi1_dr_b_pins[] = { 0x34, };
-static int jz4780_ssi1_dr_d_pins[] = { 0x54, };
+static int jz4780_ssi1_dr_d_pins[] = { 0x74, };
static int jz4780_ssi1_clk_b_pins[] = { 0x3c, };
-static int jz4780_ssi1_clk_d_pins[] = { 0x58, };
+static int jz4780_ssi1_clk_d_pins[] = { 0x78, };
static int jz4780_ssi1_gpc_b_pins[] = { 0x3e, };
-static int jz4780_ssi1_gpc_d_pins[] = { 0x56, };
+static int jz4780_ssi1_gpc_d_pins[] = { 0x76, };
static int jz4780_ssi1_ce0_b_pins[] = { 0x3f, };
-static int jz4780_ssi1_ce0_d_pins[] = { 0x57, };
+static int jz4780_ssi1_ce0_d_pins[] = { 0x77, };
static int jz4780_ssi1_ce1_b_pins[] = { 0x35, };
-static int jz4780_ssi1_ce1_d_pins[] = { 0x55, };
+static int jz4780_ssi1_ce1_d_pins[] = { 0x75, };
static int jz4780_mmc0_8bit_a_pins[] = { 0x04, 0x05, 0x06, 0x07, 0x18, };
static int jz4780_i2c3_pins[] = { 0x6a, 0x6b, };
static int jz4780_i2c4_e_pins[] = { 0x8c, 0x8d, };
diff --git a/drivers/pinctrl/pinctrl-mcp23s08_spi.c b/drivers/pinctrl/pinctrl-mcp23s08_spi.c
index 1f47a66..9ae1031 100644
--- a/drivers/pinctrl/pinctrl-mcp23s08_spi.c
+++ b/drivers/pinctrl/pinctrl-mcp23s08_spi.c
@@ -119,13 +119,15 @@
return -EINVAL;
}
- copy = devm_kmemdup(dev, &config, sizeof(config), GFP_KERNEL);
+ copy = devm_kmemdup(dev, config, sizeof(*config), GFP_KERNEL);
if (!copy)
return -ENOMEM;
copy->name = name;
mcp->regmap = devm_regmap_init(dev, &mcp23sxx_spi_regmap, mcp, copy);
+ if (IS_ERR(mcp->regmap))
+ dev_err(dev, "regmap init failed for %s\n", mcp->chip.label);
return PTR_ERR_OR_ZERO(mcp->regmap);
}
diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index 0401c1d..aa1a1c8 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -3155,7 +3155,9 @@
if (!bank->domain)
return -ENXIO;
+ clk_enable(bank->clk);
virq = irq_create_mapping(bank->domain, offset);
+ clk_disable(bank->clk);
return (virq) ? : -ENXIO;
}
@@ -3194,7 +3196,7 @@
irq = __ffs(pend);
pend &= ~BIT(irq);
- virq = irq_linear_revmap(bank->domain, irq);
+ virq = irq_find_mapping(bank->domain, irq);
if (!virq) {
dev_err(bank->drvdata->dev, "unmapped irq %d\n", irq);
@@ -3373,7 +3375,7 @@
unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
struct irq_chip_generic *gc;
int ret;
- int i, j;
+ int i;
for (i = 0; i < ctrl->nr_banks; ++i, ++bank) {
if (!bank->valid) {
@@ -3400,7 +3402,7 @@
ret = irq_alloc_domain_generic_chips(bank->domain, 32, 1,
"rockchip_gpio_irq", handle_level_irq,
- clr, 0, IRQ_GC_INIT_MASK_CACHE);
+ clr, 0, 0);
if (ret) {
dev_err(&pdev->dev, "could not alloc generic chips for bank %s\n",
bank->name);
@@ -3409,14 +3411,6 @@
continue;
}
- /*
- * Linux assumes that all interrupts start out disabled/masked.
- * Our driver only uses the concept of masked and always keeps
- * things enabled, so for us that's all masked and all enabled.
- */
- writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTMASK);
- writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTEN);
-
gc = irq_get_domain_generic_chip(bank->domain, 0);
gc->reg_base = bank->reg_base;
gc->private = bank;
@@ -3433,13 +3427,17 @@
gc->chip_types[0].chip.irq_set_type = rockchip_irq_set_type;
gc->wake_enabled = IRQ_MSK(bank->nr_pins);
+ /*
+ * Linux assumes that all interrupts start out disabled/masked.
+ * Our driver only uses the concept of masked and always keeps
+ * things enabled, so for us that's all masked and all enabled.
+ */
+ writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTMASK);
+ writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTEN);
+ gc->mask_cache = 0xffffffff;
+
irq_set_chained_handler_and_data(bank->irq,
rockchip_irq_demux, bank);
-
- /* map the gpio irqs here, when the clock is still running */
- for (j = 0 ; j < 32 ; j++)
- irq_create_mapping(bank->domain, j);
-
clk_disable(bank->clk);
}
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index c4bcda9..77a25bd 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -815,21 +815,14 @@
static void msm_gpio_irq_enable(struct irq_data *d)
{
- /*
- * Clear the interrupt that may be pending before we enable
- * the line.
- * This is especially a problem with the GPIOs routed to the
- * PDC. These GPIOs are direct-connect interrupts to the GIC.
- * Disabling the interrupt line at the PDC does not prevent
- * the interrupt from being latched at the GIC. The state at
- * GIC needs to be cleared before enabling.
- */
- if (d->parent_data) {
- irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, 0);
- irq_chip_enable_parent(d);
- }
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct msm_pinctrl *pctrl = gpiochip_get_data(gc);
- msm_gpio_irq_clear_unmask(d, true);
+ if (d->parent_data)
+ irq_chip_enable_parent(d);
+
+ if (!test_bit(d->hwirq, pctrl->skip_wake_irqs))
+ msm_gpio_irq_clear_unmask(d, true);
}
static void msm_gpio_irq_disable(struct irq_data *d)
@@ -1104,6 +1097,19 @@
ret = -EINVAL;
goto out;
}
+
+ /*
+ * Clear the interrupt that may be pending before we enable
+ * the line.
+ * This is especially a problem with the GPIOs routed to the
+ * PDC. These GPIOs are direct-connect interrupts to the GIC.
+ * Disabling the interrupt line at the PDC does not prevent
+ * the interrupt from being latched at the GIC. The state at
+ * GIC needs to be cleared before enabling.
+ */
+ if (d->parent_data && test_bit(d->hwirq, pctrl->skip_wake_irqs))
+ irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, 0);
+
return 0;
out:
module_put(gc->owner);
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8250.c b/drivers/pinctrl/qcom/pinctrl-sm8250.c
index 826df0d..af144e7 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8250.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8250.c
@@ -1313,6 +1313,22 @@
[183] = SDC_PINGROUP(sdc2_data, 0xb7000, 9, 0),
};
+static const struct msm_gpio_wakeirq_map sm8250_pdc_map[] = {
+ { 0, 79 }, { 1, 84 }, { 2, 80 }, { 3, 82 }, { 4, 107 }, { 7, 43 },
+ { 11, 42 }, { 14, 44 }, { 15, 52 }, { 19, 67 }, { 23, 68 }, { 24, 105 },
+ { 27, 92 }, { 28, 106 }, { 31, 69 }, { 35, 70 }, { 39, 37 },
+ { 40, 108 }, { 43, 71 }, { 45, 72 }, { 47, 83 }, { 51, 74 }, { 55, 77 },
+ { 59, 78 }, { 63, 75 }, { 64, 81 }, { 65, 87 }, { 66, 88 }, { 67, 89 },
+ { 68, 54 }, { 70, 85 }, { 77, 46 }, { 80, 90 }, { 81, 91 }, { 83, 97 },
+ { 84, 98 }, { 86, 99 }, { 87, 100 }, { 88, 101 }, { 89, 102 },
+ { 92, 103 }, { 93, 104 }, { 100, 53 }, { 103, 47 }, { 104, 48 },
+ { 108, 49 }, { 109, 94 }, { 110, 95 }, { 111, 96 }, { 112, 55 },
+ { 113, 56 }, { 118, 50 }, { 121, 51 }, { 122, 57 }, { 123, 58 },
+ { 124, 45 }, { 126, 59 }, { 128, 76 }, { 129, 86 }, { 132, 93 },
+ { 133, 65 }, { 134, 66 }, { 136, 62 }, { 137, 63 }, { 138, 64 },
+ { 142, 60 }, { 143, 61 }
+};
+
static const struct msm_pinctrl_soc_data sm8250_pinctrl = {
.pins = sm8250_pins,
.npins = ARRAY_SIZE(sm8250_pins),
@@ -1323,6 +1339,8 @@
.ngpios = 181,
.tiles = sm8250_tiles,
.ntiles = ARRAY_SIZE(sm8250_tiles),
+ .wakeirq_map = sm8250_pdc_map,
+ .nwakeirq_map = ARRAY_SIZE(sm8250_pdc_map),
};
static int sm8250_pinctrl_probe(struct platform_device *pdev)
diff --git a/drivers/pnp/core.c b/drivers/pnp/core.c
index 3bf18d7..a50ab00 100644
--- a/drivers/pnp/core.c
+++ b/drivers/pnp/core.c
@@ -51,7 +51,7 @@
}
/**
- * pnp_protocol_register - adds a pnp protocol to the pnp layer
+ * pnp_register_protocol - adds a pnp protocol to the pnp layer
* @protocol: pointer to the corresponding pnp_protocol structure
*
* Ex protocols: ISAPNP, PNPBIOS, etc
@@ -91,7 +91,7 @@
}
/**
- * pnp_protocol_unregister - removes a pnp protocol from the pnp layer
+ * pnp_unregister_protocol - removes a pnp protocol from the pnp layer
* @protocol: pointer to the corresponding pnp_protocol structure
*/
void pnp_unregister_protocol(struct pnp_protocol *protocol)
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 0b2830e..70d6d52 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -620,7 +620,7 @@
case ARBITRARY_UNIT:
default:
return value;
- };
+ }
if (to_raw)
return div64_u64(value, units) * scale;
diff --git a/drivers/powercap/powercap_sys.c b/drivers/powercap/powercap_sys.c
index f808c5f..3f0b8e2 100644
--- a/drivers/powercap/powercap_sys.c
+++ b/drivers/powercap/powercap_sys.c
@@ -367,9 +367,9 @@
&dev_attr_max_energy_range_uj.attr;
if (power_zone->ops->get_energy_uj) {
if (power_zone->ops->reset_energy_uj)
- dev_attr_energy_uj.attr.mode = S_IWUSR | S_IRUGO;
+ dev_attr_energy_uj.attr.mode = S_IWUSR | S_IRUSR;
else
- dev_attr_energy_uj.attr.mode = S_IRUGO;
+ dev_attr_energy_uj.attr.mode = S_IRUSR;
power_zone->zone_dev_attrs[count++] =
&dev_attr_energy_uj.attr;
}
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index a4ffd71..42bbd99 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1315,7 +1315,6 @@
/**
* set_machine_constraints - sets regulator constraints
* @rdev: regulator source
- * @constraints: constraints to apply
*
* Allows platform initialisation code to define and constrain
* regulator circuits e.g. valid voltage/current ranges, etc. NOTE:
@@ -1323,21 +1322,11 @@
* regulator operations to proceed i.e. set_voltage, set_current_limit,
* set_mode.
*/
-static int set_machine_constraints(struct regulator_dev *rdev,
- const struct regulation_constraints *constraints)
+static int set_machine_constraints(struct regulator_dev *rdev)
{
int ret = 0;
const struct regulator_ops *ops = rdev->desc->ops;
- if (constraints)
- rdev->constraints = kmemdup(constraints, sizeof(*constraints),
- GFP_KERNEL);
- else
- rdev->constraints = kzalloc(sizeof(*constraints),
- GFP_KERNEL);
- if (!rdev->constraints)
- return -ENOMEM;
-
ret = machine_constraints_voltage(rdev, rdev->constraints);
if (ret != 0)
return ret;
@@ -1852,6 +1841,15 @@
}
}
+ if (r == rdev) {
+ dev_err(dev, "Supply for %s (%s) resolved to itself\n",
+ rdev->desc->name, rdev->supply_name);
+ if (!have_full_constraints())
+ return -EINVAL;
+ r = dummy_regulator_rdev;
+ get_device(&r->dev);
+ }
+
/*
* If the supply's parent device is not the same as the
* regulator's parent device, then ensure the parent device
@@ -4165,6 +4163,8 @@
ret = rdev->desc->fixed_uV;
} else if (rdev->supply) {
ret = regulator_get_voltage_rdev(rdev->supply->rdev);
+ } else if (rdev->supply_name) {
+ return -EPROBE_DEFER;
} else {
return -EINVAL;
}
@@ -5144,7 +5144,6 @@
regulator_register(const struct regulator_desc *regulator_desc,
const struct regulator_config *cfg)
{
- const struct regulation_constraints *constraints = NULL;
const struct regulator_init_data *init_data;
struct regulator_config *config = NULL;
static atomic_t regulator_no = ATOMIC_INIT(-1);
@@ -5283,14 +5282,23 @@
/* set regulator constraints */
if (init_data)
- constraints = &init_data->constraints;
+ rdev->constraints = kmemdup(&init_data->constraints,
+ sizeof(*rdev->constraints),
+ GFP_KERNEL);
+ else
+ rdev->constraints = kzalloc(sizeof(*rdev->constraints),
+ GFP_KERNEL);
+ if (!rdev->constraints) {
+ ret = -ENOMEM;
+ goto wash;
+ }
if (init_data && init_data->supply_regulator)
rdev->supply_name = init_data->supply_regulator;
else if (regulator_desc->supply_name)
rdev->supply_name = regulator_desc->supply_name;
- ret = set_machine_constraints(rdev, constraints);
+ ret = set_machine_constraints(rdev);
if (ret == -EPROBE_DEFER) {
/* Regulator might be in bypass mode and so needs its supply
* to set the constraints */
@@ -5299,7 +5307,7 @@
* that is just being created */
ret = regulator_resolve_supply(rdev);
if (!ret)
- ret = set_machine_constraints(rdev, constraints);
+ ret = set_machine_constraints(rdev);
else
rdev_dbg(rdev, "unable to resolve supply early: %pe\n",
ERR_PTR(ret));
@@ -5841,13 +5849,14 @@
if (rdev->use_count)
goto unlock;
- /* If we can't read the status assume it's on. */
+ /* If we can't read the status assume it's always on. */
if (ops->is_enabled)
enabled = ops->is_enabled(rdev);
else
enabled = 1;
- if (!enabled)
+ /* But if reading the status failed, assume that it's off. */
+ if (enabled <= 0)
goto unlock;
if (have_full_constraints()) {
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index 7e8ba92..01a12cf 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -836,11 +836,14 @@
* the switched regulator till yet.
*/
if (pfuze_chip->flags & PFUZE_FLAG_DISABLE_SW) {
- if (pfuze_chip->regulator_descs[i].sw_reg) {
- desc->ops = &pfuze100_sw_disable_regulator_ops;
- desc->enable_val = 0x8;
- desc->disable_val = 0x0;
- desc->enable_time = 500;
+ if (pfuze_chip->chip_id == PFUZE100 ||
+ pfuze_chip->chip_id == PFUZE200) {
+ if (pfuze_chip->regulator_descs[i].sw_reg) {
+ desc->ops = &pfuze100_sw_disable_regulator_ops;
+ desc->enable_val = 0x8;
+ desc->disable_val = 0x0;
+ desc->enable_time = 500;
+ }
}
}
diff --git a/drivers/regulator/ti-abb-regulator.c b/drivers/regulator/ti-abb-regulator.c
index 3e60bff..9f0a4d5 100644
--- a/drivers/regulator/ti-abb-regulator.c
+++ b/drivers/regulator/ti-abb-regulator.c
@@ -342,8 +342,17 @@
return ret;
}
- /* If data is exactly the same, then just update index, no change */
info = &abb->info[sel];
+ /*
+ * When Linux kernel is starting up, we are'nt sure of the
+ * Bias configuration that bootloader has configured.
+ * So, we get to know the actual setting the first time
+ * we are asked to transition.
+ */
+ if (abb->current_info_idx == -EINVAL)
+ goto just_set_abb;
+
+ /* If data is exactly the same, then just update index, no change */
oinfo = &abb->info[abb->current_info_idx];
if (!memcmp(info, oinfo, sizeof(*info))) {
dev_dbg(dev, "%s: Same data new idx=%d, old idx=%d\n", __func__,
@@ -351,6 +360,7 @@
goto out;
}
+just_set_abb:
ret = ti_abb_set_opp(rdev, abb, info);
out:
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 485cbfc..ef738b4 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -680,7 +680,10 @@
{
struct ap_device *ap_dev = to_ap_dev(dev);
struct ap_driver *ap_drv = to_ap_drv(dev->driver);
- int card, queue, devres, drvres, rc;
+ int card, queue, devres, drvres, rc = -ENODEV;
+
+ if (!get_device(dev))
+ return rc;
if (is_queue_dev(dev)) {
/*
@@ -697,7 +700,7 @@
mutex_unlock(&ap_perms_mutex);
drvres = ap_drv->flags & AP_DRIVER_FLAG_DEFAULT;
if (!!devres != !!drvres)
- return -ENODEV;
+ goto out;
}
/* Add queue/card to list of active queues/cards */
@@ -718,6 +721,9 @@
ap_dev->drv = NULL;
}
+out:
+ if (rc)
+ put_device(dev);
return rc;
}
@@ -744,6 +750,8 @@
hash_del(&to_ap_queue(dev)->hnode);
spin_unlock_bh(&ap_queues_lock);
+ put_device(dev);
+
return 0;
}
@@ -1371,6 +1379,8 @@
__func__, ac->id, dom);
goto put_dev_and_continue;
}
+ /* get it and thus adjust reference counter */
+ get_device(dev);
if (decfg)
AP_DBF_INFO("%s(%d,%d) new (decfg) queue device created\n",
__func__, ac->id, dom);
diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index 99cb60e..dd84995 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -35,9 +35,6 @@
#define PROTKEYBLOBBUFSIZE 256 /* protected key buffer size used internal */
#define MAXAPQNSINLIST 64 /* max 64 apqns within a apqn list */
-/* mask of available pckmo subfunctions, fetched once at module init */
-static cpacf_mask_t pckmo_functions;
-
/*
* debug feature data and functions
*/
@@ -91,6 +88,9 @@
const struct pkey_clrkey *clrkey,
struct pkey_protkey *protkey)
{
+ /* mask of available pckmo subfunctions */
+ static cpacf_mask_t pckmo_functions;
+
long fc;
int keysize;
u8 paramblock[64];
@@ -114,11 +114,13 @@
return -EINVAL;
}
- /*
- * Check if the needed pckmo subfunction is available.
- * These subfunctions can be enabled/disabled by customers
- * in the LPAR profile or may even change on the fly.
- */
+ /* Did we already check for PCKMO ? */
+ if (!pckmo_functions.bytes[0]) {
+ /* no, so check now */
+ if (!cpacf_query(CPACF_PCKMO, &pckmo_functions))
+ return -ENODEV;
+ }
+ /* check for the pckmo subfunction we need now */
if (!cpacf_test_func(&pckmo_functions, fc)) {
DEBUG_ERR("%s pckmo functions not available\n", __func__);
return -ENODEV;
@@ -2058,7 +2060,7 @@
*/
static int __init pkey_init(void)
{
- cpacf_mask_t kmc_functions;
+ cpacf_mask_t func_mask;
/*
* The pckmo instruction should be available - even if we don't
@@ -2066,15 +2068,15 @@
* is also the minimum level for the kmc instructions which
* are able to work with protected keys.
*/
- if (!cpacf_query(CPACF_PCKMO, &pckmo_functions))
+ if (!cpacf_query(CPACF_PCKMO, &func_mask))
return -ENODEV;
/* check for kmc instructions available */
- if (!cpacf_query(CPACF_KMC, &kmc_functions))
+ if (!cpacf_query(CPACF_KMC, &func_mask))
return -ENODEV;
- if (!cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_128) ||
- !cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_192) ||
- !cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_256))
+ if (!cpacf_test_func(&func_mask, CPACF_KMC_PAES_128) ||
+ !cpacf_test_func(&func_mask, CPACF_KMC_PAES_192) ||
+ !cpacf_test_func(&func_mask, CPACF_KMC_PAES_256))
return -ENODEV;
pkey_debug_init();
diff --git a/drivers/s390/crypto/zcrypt_card.c b/drivers/s390/crypto/zcrypt_card.c
index e342eb8..33b2388 100644
--- a/drivers/s390/crypto/zcrypt_card.c
+++ b/drivers/s390/crypto/zcrypt_card.c
@@ -157,11 +157,6 @@
{
int rc;
- rc = sysfs_create_group(&zc->card->ap_dev.device.kobj,
- &zcrypt_card_attr_group);
- if (rc)
- return rc;
-
spin_lock(&zcrypt_list_lock);
list_add_tail(&zc->list, &zcrypt_card_list);
spin_unlock(&zcrypt_list_lock);
@@ -170,6 +165,14 @@
ZCRYPT_DBF(DBF_INFO, "card=%02x register online=1\n", zc->card->id);
+ rc = sysfs_create_group(&zc->card->ap_dev.device.kobj,
+ &zcrypt_card_attr_group);
+ if (rc) {
+ spin_lock(&zcrypt_list_lock);
+ list_del_init(&zc->list);
+ spin_unlock(&zcrypt_list_lock);
+ }
+
return rc;
}
EXPORT_SYMBOL(zcrypt_card_register);
diff --git a/drivers/s390/crypto/zcrypt_queue.c b/drivers/s390/crypto/zcrypt_queue.c
index 3c20706..5062eae 100644
--- a/drivers/s390/crypto/zcrypt_queue.c
+++ b/drivers/s390/crypto/zcrypt_queue.c
@@ -180,7 +180,6 @@
&zcrypt_queue_attr_group);
if (rc)
goto out;
- get_device(&zq->queue->ap_dev.device);
if (zq->ops->rng) {
rc = zcrypt_rng_device_add();
@@ -192,7 +191,6 @@
out_unregister:
sysfs_remove_group(&zq->queue->ap_dev.device.kobj,
&zcrypt_queue_attr_group);
- put_device(&zq->queue->ap_dev.device);
out:
spin_lock(&zcrypt_list_lock);
list_del_init(&zq->list);
@@ -220,12 +218,10 @@
list_del_init(&zq->list);
zcrypt_device_count--;
spin_unlock(&zcrypt_list_lock);
- zcrypt_card_put(zc);
if (zq->ops->rng)
zcrypt_rng_device_remove();
sysfs_remove_group(&zq->queue->ap_dev.device.kobj,
&zcrypt_queue_attr_group);
- put_device(&zq->queue->ap_dev.device);
- zcrypt_queue_put(zq);
+ zcrypt_card_put(zc);
}
EXPORT_SYMBOL(zcrypt_queue_unregister);
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index fe96ca3c..26cc943 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -390,7 +390,7 @@
}
static struct ism_systemeid SYSTEM_EID = {
- .seid_string = "IBM-SYSZ-IBMSEID00000000",
+ .seid_string = "IBM-SYSZ-ISMSEID00000000",
.serial_number = "0000",
.type = "0000",
};
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index f32da0c..308bda2e 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -658,8 +658,8 @@
rcu_read_lock();
list_for_each_entry_rcu(h,
&tmp_pg->dh_list, node) {
- /* h->sdev should always be valid */
- BUG_ON(!h->sdev);
+ if (!h->sdev)
+ continue;
h->sdev->access_state = desc[0];
}
rcu_read_unlock();
@@ -705,7 +705,8 @@
pg->expiry = 0;
rcu_read_lock();
list_for_each_entry_rcu(h, &pg->dh_list, node) {
- BUG_ON(!h->sdev);
+ if (!h->sdev)
+ continue;
h->sdev->access_state =
(pg->state & SCSI_ACCESS_STATE_MASK);
if (pg->pref)
@@ -1147,7 +1148,6 @@
spin_lock(&h->pg_lock);
pg = rcu_dereference_protected(h->pg, lockdep_is_held(&h->pg_lock));
rcu_assign_pointer(h->pg, NULL);
- h->sdev = NULL;
spin_unlock(&h->pg_lock);
if (pg) {
spin_lock_irq(&pg->lock);
@@ -1156,6 +1156,7 @@
kref_put(&pg->kref, release_port_group);
}
sdev->handler_data = NULL;
+ synchronize_rcu();
kfree(h);
}
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 128583d..c8dd858 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -445,7 +445,7 @@
}
}
- if (scmd) {
+ if (scmd && hisi_hba->shost->nr_hw_queues) {
unsigned int dq_index;
u32 blk_tag;
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 83ce4f1..8df70c9 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -8855,7 +8855,7 @@
/* hook into SCSI subsystem */
rc = hpsa_scsi_add_host(h);
if (rc)
- goto clean7; /* perf, sg, cmd, irq, shost, pci, lu, aer/h */
+ goto clean8; /* lastlogicals, perf, sg, cmd, irq, shost, pci, lu, aer/h */
/* Monitor the controller for firmware lockups */
h->heartbeat_sample_interval = HEARTBEAT_SAMPLE_INTERVAL;
@@ -8870,6 +8870,8 @@
HPSA_EVENT_MONITOR_INTERVAL);
return 0;
+clean8: /* lastlogicals, perf, sg, cmd, irq, shost, pci, lu, aer/h */
+ kfree(h->lastlogicals);
clean7: /* perf, sg, cmd, irq, shost, pci, lu, aer/h */
hpsa_free_performant_mode(h);
h->access.set_intr_mask(h, HPSA_INTR_OFF);
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index b1f3017..29fcc44 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -807,13 +807,29 @@
}
/**
+ * ibmvscsi_set_request_limit - Set the adapter request_limit in response to
+ * an adapter failure, reset, or SRP Login. Done under host lock to prevent
+ * race with SCSI command submission.
+ * @hostdata: adapter to adjust
+ * @limit: new request limit
+ */
+static void ibmvscsi_set_request_limit(struct ibmvscsi_host_data *hostdata, int limit)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(hostdata->host->host_lock, flags);
+ atomic_set(&hostdata->request_limit, limit);
+ spin_unlock_irqrestore(hostdata->host->host_lock, flags);
+}
+
+/**
* ibmvscsi_reset_host - Reset the connection to the server
* @hostdata: struct ibmvscsi_host_data to reset
*/
static void ibmvscsi_reset_host(struct ibmvscsi_host_data *hostdata)
{
scsi_block_requests(hostdata->host);
- atomic_set(&hostdata->request_limit, 0);
+ ibmvscsi_set_request_limit(hostdata, 0);
purge_requests(hostdata, DID_ERROR);
hostdata->action = IBMVSCSI_HOST_ACTION_RESET;
@@ -1146,13 +1162,13 @@
dev_info(hostdata->dev, "SRP_LOGIN_REJ reason %u\n",
evt_struct->xfer_iu->srp.login_rej.reason);
/* Login failed. */
- atomic_set(&hostdata->request_limit, -1);
+ ibmvscsi_set_request_limit(hostdata, -1);
return;
default:
dev_err(hostdata->dev, "Invalid login response typecode 0x%02x!\n",
evt_struct->xfer_iu->srp.login_rsp.opcode);
/* Login failed. */
- atomic_set(&hostdata->request_limit, -1);
+ ibmvscsi_set_request_limit(hostdata, -1);
return;
}
@@ -1163,7 +1179,7 @@
* This value is set rather than added to request_limit because
* request_limit could have been set to -1 by this client.
*/
- atomic_set(&hostdata->request_limit,
+ ibmvscsi_set_request_limit(hostdata,
be32_to_cpu(evt_struct->xfer_iu->srp.login_rsp.req_lim_delta));
/* If we had any pending I/Os, kick them */
@@ -1195,13 +1211,13 @@
login->req_buf_fmt = cpu_to_be16(SRP_BUF_FORMAT_DIRECT |
SRP_BUF_FORMAT_INDIRECT);
- spin_lock_irqsave(hostdata->host->host_lock, flags);
/* Start out with a request limit of 0, since this is negotiated in
* the login request we are just sending and login requests always
* get sent by the driver regardless of request_limit.
*/
- atomic_set(&hostdata->request_limit, 0);
+ ibmvscsi_set_request_limit(hostdata, 0);
+ spin_lock_irqsave(hostdata->host->host_lock, flags);
rc = ibmvscsi_send_srp_event(evt_struct, hostdata, login_timeout * 2);
spin_unlock_irqrestore(hostdata->host->host_lock, flags);
dev_info(hostdata->dev, "sent SRP login\n");
@@ -1781,7 +1797,7 @@
return;
case VIOSRP_CRQ_XPORT_EVENT: /* Hypervisor telling us the connection is closed */
scsi_block_requests(hostdata->host);
- atomic_set(&hostdata->request_limit, 0);
+ ibmvscsi_set_request_limit(hostdata, 0);
if (crq->format == 0x06) {
/* We need to re-setup the interpartition connection */
dev_info(hostdata->dev, "Re-enabling adapter!\n");
@@ -2137,12 +2153,12 @@
}
hostdata->action = IBMVSCSI_HOST_ACTION_NONE;
+ spin_unlock_irqrestore(hostdata->host->host_lock, flags);
if (rc) {
- atomic_set(&hostdata->request_limit, -1);
+ ibmvscsi_set_request_limit(hostdata, -1);
dev_err(hostdata->dev, "error after %s\n", action);
}
- spin_unlock_irqrestore(hostdata->host->host_lock, flags);
scsi_unblock_requests(hostdata->host);
}
@@ -2226,7 +2242,7 @@
init_waitqueue_head(&hostdata->work_wait_q);
hostdata->host = host;
hostdata->dev = dev;
- atomic_set(&hostdata->request_limit, -1);
+ ibmvscsi_set_request_limit(hostdata, -1);
hostdata->host->max_sectors = IBMVSCSI_MAX_SECTORS_DEFAULT;
if (map_persist_bufs(hostdata)) {
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 93230cd..e4cc92b 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -1740,6 +1740,13 @@
reply_q->irq_poll_scheduled = false;
reply_q->irq_line_enable = true;
enable_irq(reply_q->os_irq);
+ /*
+ * Go for one more round of processing the
+ * reply descriptor post queue incase if HBA
+ * Firmware has posted some reply descriptors
+ * while reenabling the IRQ.
+ */
+ _base_process_reply_queue(reply_q);
}
return num_entries;
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 1f90051..b7a1dc2 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -554,10 +554,12 @@
fcport = qla_rport->fcport;
- if (!qpair || !fcport || (qpair && !qpair->fw_started) ||
- (fcport && fcport->deleted))
+ if (!qpair || !fcport)
return -ENODEV;
+ if (!qpair->fw_started || fcport->deleted)
+ return -EBUSY;
+
vha = fcport->vha;
if (!(fcport->nvme_flag & NVME_FLAG_REGISTERED))
diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c
index 84f4416..bd8623e 100644
--- a/drivers/scsi/qla2xxx/qla_tmpl.c
+++ b/drivers/scsi/qla2xxx/qla_tmpl.c
@@ -1001,10 +1001,8 @@
{
ulong flags = 0;
-#ifndef __CHECKER__
if (!hardware_locked)
spin_lock_irqsave(&vha->hw->hardware_lock, flags);
-#endif
if (!vha->hw->mpi_fw_dump) {
ql_log(ql_log_warn, vha, 0x02f3, "-> mpi_fwdump no buffer\n");
} else {
@@ -1050,10 +1048,8 @@
}
bailout:
-#ifndef __CHECKER__
if (!hardware_locked)
spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
-#endif
}
void
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index f2437a7..9af50e6 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -1714,15 +1714,16 @@
*/
static struct async_scan_data *scsi_prep_async_scan(struct Scsi_Host *shost)
{
- struct async_scan_data *data;
+ struct async_scan_data *data = NULL;
unsigned long flags;
if (strncmp(scsi_scan_type, "sync", 4) == 0)
return NULL;
+ mutex_lock(&shost->scan_mutex);
if (shost->async_scan) {
shost_printk(KERN_DEBUG, shost, "%s called twice\n", __func__);
- return NULL;
+ goto err;
}
data = kmalloc(sizeof(*data), GFP_KERNEL);
@@ -1733,7 +1734,6 @@
goto err;
init_completion(&data->prev_finished);
- mutex_lock(&shost->scan_mutex);
spin_lock_irqsave(shost->host_lock, flags);
shost->async_scan = 1;
spin_unlock_irqrestore(shost->host_lock, flags);
@@ -1748,6 +1748,7 @@
return data;
err:
+ mutex_unlock(&shost->scan_mutex);
kfree(data);
return NULL;
}
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index b8f573a..7a160b8 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -1627,12 +1627,12 @@
*/
fallthrough;
case CLKS_OFF:
- ufshcd_scsi_block_requests(hba);
hba->clk_gating.state = REQ_CLKS_ON;
trace_ufshcd_clk_gating(dev_name(hba->dev),
hba->clk_gating.state);
- queue_work(hba->clk_gating.clk_gating_workq,
- &hba->clk_gating.ungate_work);
+ if (queue_work(hba->clk_gating.clk_gating_workq,
+ &hba->clk_gating.ungate_work))
+ ufshcd_scsi_block_requests(hba);
/*
* fall through to check if we should wait for this
* work to be done or not.
@@ -2115,10 +2115,20 @@
unsigned long flags;
if (wait_for_completion_timeout(&uic_cmd->done,
- msecs_to_jiffies(UIC_CMD_TIMEOUT)))
+ msecs_to_jiffies(UIC_CMD_TIMEOUT))) {
ret = uic_cmd->argument2 & MASK_UIC_COMMAND_RESULT;
- else
+ } else {
ret = -ETIMEDOUT;
+ dev_err(hba->dev,
+ "uic cmd 0x%x with arg3 0x%x completion timeout\n",
+ uic_cmd->command, uic_cmd->argument3);
+
+ if (!uic_cmd->cmd_active) {
+ dev_err(hba->dev, "%s: UIC cmd has been completed, return the result\n",
+ __func__);
+ ret = uic_cmd->argument2 & MASK_UIC_COMMAND_RESULT;
+ }
+ }
spin_lock_irqsave(hba->host->host_lock, flags);
hba->active_uic_cmd = NULL;
@@ -2150,6 +2160,7 @@
if (completion)
init_completion(&uic_cmd->done);
+ uic_cmd->cmd_active = 1;
ufshcd_dispatch_uic_cmd(hba, uic_cmd);
return 0;
@@ -3807,10 +3818,18 @@
dev_err(hba->dev,
"pwr ctrl cmd 0x%x with mode 0x%x completion timeout\n",
cmd->command, cmd->argument3);
+
+ if (!cmd->cmd_active) {
+ dev_err(hba->dev, "%s: Power Mode Change operation has been completed, go check UPMCRS\n",
+ __func__);
+ goto check_upmcrs;
+ }
+
ret = -ETIMEDOUT;
goto out;
}
+check_upmcrs:
status = ufshcd_get_upmcrs(hba);
if (status != PWR_LOCAL) {
dev_err(hba->dev,
@@ -4902,11 +4921,14 @@
ufshcd_get_uic_cmd_result(hba);
hba->active_uic_cmd->argument3 =
ufshcd_get_dme_attr_val(hba);
+ if (!hba->uic_async_done)
+ hba->active_uic_cmd->cmd_active = 0;
complete(&hba->active_uic_cmd->done);
retval = IRQ_HANDLED;
}
if ((intr_status & UFSHCD_UIC_PWR_MASK) && hba->uic_async_done) {
+ hba->active_uic_cmd->cmd_active = 0;
complete(hba->uic_async_done);
retval = IRQ_HANDLED;
}
@@ -8906,6 +8928,7 @@
blk_mq_free_tag_set(&hba->tmf_tag_set);
blk_cleanup_queue(hba->cmd_queue);
scsi_remove_host(hba->host);
+ destroy_workqueue(hba->eh_wq);
/* disable interrupts */
ufshcd_disable_intr(hba, hba->intr_mask);
ufshcd_hba_stop(hba);
@@ -9206,6 +9229,7 @@
exit_gating:
ufshcd_exit_clk_scaling(hba);
ufshcd_exit_clk_gating(hba);
+ destroy_workqueue(hba->eh_wq);
out_disable:
hba->is_irq_enabled = false;
ufshcd_hba_exit(hba);
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 47eb143..e0f00a4 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -64,6 +64,7 @@
* @argument1: UIC command argument 1
* @argument2: UIC command argument 2
* @argument3: UIC command argument 3
+ * @cmd_active: Indicate if UIC command is outstanding
* @done: UIC command completion
*/
struct uic_command {
@@ -71,6 +72,7 @@
u32 argument1;
u32 argument2;
u32 argument3;
+ int cmd_active;
struct completion done;
};
diff --git a/drivers/soc/ti/ti_sci_pm_domains.c b/drivers/soc/ti/ti_sci_pm_domains.c
index af2126d2..8afb3f45 100644
--- a/drivers/soc/ti/ti_sci_pm_domains.c
+++ b/drivers/soc/ti/ti_sci_pm_domains.c
@@ -91,7 +91,7 @@
struct genpd_onecell_data *genpd_data = data;
unsigned int idx = genpdspec->args[0];
- if (genpdspec->args_count < 2)
+ if (genpdspec->args_count != 1 && genpdspec->args_count != 2)
return ERR_PTR(-EINVAL);
if (idx >= genpd_data->num_domains) {
diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index 14c9d01..c028446 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -1327,7 +1327,7 @@
data = of_id->data;
- master = spi_alloc_master(dev, sizeof(struct bcm_qspi));
+ master = devm_spi_alloc_master(dev, sizeof(struct bcm_qspi));
if (!master) {
dev_err(dev, "error allocating spi_master\n");
return -ENOMEM;
@@ -1367,21 +1367,17 @@
if (res) {
qspi->base[MSPI] = devm_ioremap_resource(dev, res);
- if (IS_ERR(qspi->base[MSPI])) {
- ret = PTR_ERR(qspi->base[MSPI]);
- goto qspi_resource_err;
- }
+ if (IS_ERR(qspi->base[MSPI]))
+ return PTR_ERR(qspi->base[MSPI]);
} else {
- goto qspi_resource_err;
+ return 0;
}
res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "bspi");
if (res) {
qspi->base[BSPI] = devm_ioremap_resource(dev, res);
- if (IS_ERR(qspi->base[BSPI])) {
- ret = PTR_ERR(qspi->base[BSPI]);
- goto qspi_resource_err;
- }
+ if (IS_ERR(qspi->base[BSPI]))
+ return PTR_ERR(qspi->base[BSPI]);
qspi->bspi_mode = true;
} else {
qspi->bspi_mode = false;
@@ -1392,18 +1388,14 @@
res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cs_reg");
if (res) {
qspi->base[CHIP_SELECT] = devm_ioremap_resource(dev, res);
- if (IS_ERR(qspi->base[CHIP_SELECT])) {
- ret = PTR_ERR(qspi->base[CHIP_SELECT]);
- goto qspi_resource_err;
- }
+ if (IS_ERR(qspi->base[CHIP_SELECT]))
+ return PTR_ERR(qspi->base[CHIP_SELECT]);
}
qspi->dev_ids = kcalloc(num_irqs, sizeof(struct bcm_qspi_dev_id),
GFP_KERNEL);
- if (!qspi->dev_ids) {
- ret = -ENOMEM;
- goto qspi_resource_err;
- }
+ if (!qspi->dev_ids)
+ return -ENOMEM;
for (val = 0; val < num_irqs; val++) {
irq = -1;
@@ -1484,7 +1476,7 @@
qspi->xfer_mode.addrlen = -1;
qspi->xfer_mode.hp = -1;
- ret = devm_spi_register_master(&pdev->dev, master);
+ ret = spi_register_master(master);
if (ret < 0) {
dev_err(dev, "can't register master\n");
goto qspi_reg_err;
@@ -1497,8 +1489,6 @@
clk_disable_unprepare(qspi->clk);
qspi_probe_err:
kfree(qspi->dev_ids);
-qspi_resource_err:
- spi_master_put(master);
return ret;
}
/* probe function to be called by SoC specific platform driver probe */
@@ -1508,10 +1498,10 @@
{
struct bcm_qspi *qspi = platform_get_drvdata(pdev);
+ spi_unregister_master(qspi->master);
bcm_qspi_hw_uninit(qspi);
clk_disable_unprepare(qspi->clk);
kfree(qspi->dev_ids);
- spi_unregister_master(qspi->master);
return 0;
}
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index b87116e..197485f 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -1193,7 +1193,6 @@
struct spi_controller *ctlr = spi->controller;
struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
struct gpio_chip *chip;
- enum gpio_lookup_flags lflags;
u32 cs;
/*
@@ -1259,21 +1258,9 @@
if (!chip)
return 0;
- /*
- * Retrieve the corresponding GPIO line used for CS.
- * The inversion semantics will be handled by the GPIO core
- * code, so we pass GPIOD_OUT_LOW for "unasserted" and
- * the correct flag for inversion semantics. The SPI_CS_HIGH
- * on spi->mode cannot be checked for polarity in this case
- * as the flag use_gpio_descriptors enforces SPI_CS_HIGH.
- */
- if (of_property_read_bool(spi->dev.of_node, "spi-cs-high"))
- lflags = GPIO_ACTIVE_HIGH;
- else
- lflags = GPIO_ACTIVE_LOW;
spi->cs_gpiod = gpiochip_request_own_desc(chip, 8 - spi->chip_select,
DRV_NAME,
- lflags,
+ GPIO_LOOKUP_FLAGS_DEFAULT,
GPIOD_OUT_LOW);
if (IS_ERR(spi->cs_gpiod))
return PTR_ERR(spi->cs_gpiod);
@@ -1291,7 +1278,7 @@
struct bcm2835_spi *bs;
int err;
- ctlr = spi_alloc_master(&pdev->dev, ALIGN(sizeof(*bs),
+ ctlr = devm_spi_alloc_master(&pdev->dev, ALIGN(sizeof(*bs),
dma_get_cache_alignment()));
if (!ctlr)
return -ENOMEM;
@@ -1312,23 +1299,17 @@
bs->ctlr = ctlr;
bs->regs = devm_platform_ioremap_resource(pdev, 0);
- if (IS_ERR(bs->regs)) {
- err = PTR_ERR(bs->regs);
- goto out_controller_put;
- }
+ if (IS_ERR(bs->regs))
+ return PTR_ERR(bs->regs);
bs->clk = devm_clk_get(&pdev->dev, NULL);
- if (IS_ERR(bs->clk)) {
- err = dev_err_probe(&pdev->dev, PTR_ERR(bs->clk),
- "could not get clk\n");
- goto out_controller_put;
- }
+ if (IS_ERR(bs->clk))
+ return dev_err_probe(&pdev->dev, PTR_ERR(bs->clk),
+ "could not get clk\n");
bs->irq = platform_get_irq(pdev, 0);
- if (bs->irq <= 0) {
- err = bs->irq ? bs->irq : -ENODEV;
- goto out_controller_put;
- }
+ if (bs->irq <= 0)
+ return bs->irq ? bs->irq : -ENODEV;
clk_prepare_enable(bs->clk);
@@ -1362,8 +1343,6 @@
bcm2835_dma_release(ctlr, bs);
out_clk_disable:
clk_disable_unprepare(bs->clk);
-out_controller_put:
- spi_controller_put(ctlr);
return err;
}
diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c
index 03b034c..1a26865 100644
--- a/drivers/spi/spi-bcm2835aux.c
+++ b/drivers/spi/spi-bcm2835aux.c
@@ -494,7 +494,7 @@
unsigned long clk_hz;
int err;
- master = spi_alloc_master(&pdev->dev, sizeof(*bs));
+ master = devm_spi_alloc_master(&pdev->dev, sizeof(*bs));
if (!master)
return -ENOMEM;
@@ -524,29 +524,25 @@
/* the main area */
bs->regs = devm_platform_ioremap_resource(pdev, 0);
- if (IS_ERR(bs->regs)) {
- err = PTR_ERR(bs->regs);
- goto out_master_put;
- }
+ if (IS_ERR(bs->regs))
+ return PTR_ERR(bs->regs);
bs->clk = devm_clk_get(&pdev->dev, NULL);
if (IS_ERR(bs->clk)) {
err = PTR_ERR(bs->clk);
dev_err(&pdev->dev, "could not get clk: %d\n", err);
- goto out_master_put;
+ return err;
}
bs->irq = platform_get_irq(pdev, 0);
- if (bs->irq <= 0) {
- err = bs->irq ? bs->irq : -ENODEV;
- goto out_master_put;
- }
+ if (bs->irq <= 0)
+ return bs->irq ? bs->irq : -ENODEV;
/* this also enables the HW block */
err = clk_prepare_enable(bs->clk);
if (err) {
dev_err(&pdev->dev, "could not prepare clock: %d\n", err);
- goto out_master_put;
+ return err;
}
/* just checking if the clock returns a sane value */
@@ -581,8 +577,6 @@
out_clk_disable:
clk_disable_unprepare(bs->clk);
-out_master_put:
- spi_master_put(master);
return err;
}
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 40938cf..ba7d40c 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -1260,12 +1260,14 @@
/* Obtain QSPI reset control */
rstc = devm_reset_control_get_optional_exclusive(dev, "qspi");
if (IS_ERR(rstc)) {
+ ret = PTR_ERR(rstc);
dev_err(dev, "Cannot get QSPI reset.\n");
goto probe_reset_failed;
}
rstc_ocp = devm_reset_control_get_optional_exclusive(dev, "qspi-ocp");
if (IS_ERR(rstc_ocp)) {
+ ret = PTR_ERR(rstc_ocp);
dev_err(dev, "Cannot get QSPI OCP reset.\n");
goto probe_reset_failed;
}
diff --git a/drivers/spi/spi-dw-core.c b/drivers/spi/spi-dw-core.c
index 2e50cc0..0b2236a 100644
--- a/drivers/spi/spi-dw-core.c
+++ b/drivers/spi/spi-dw-core.c
@@ -357,11 +357,11 @@
dw_writel(dws, DW_SPI_TXFTLR, level);
dw_writel(dws, DW_SPI_RXFTLR, level - 1);
+ dws->transfer_handler = dw_spi_transfer_handler;
+
imask = SPI_INT_TXEI | SPI_INT_TXOI | SPI_INT_RXUI | SPI_INT_RXOI |
SPI_INT_RXFI;
spi_umask_intr(dws, imask);
-
- dws->transfer_handler = dw_spi_transfer_handler;
}
/*
diff --git a/drivers/spi/spi-fsi.c b/drivers/spi/spi-fsi.c
index 8a440c7..3920cd3 100644
--- a/drivers/spi/spi-fsi.c
+++ b/drivers/spi/spi-fsi.c
@@ -477,7 +477,7 @@
rc = fsi_spi_check_mux(ctx->fsi, ctx->dev);
if (rc)
- return rc;
+ goto error;
list_for_each_entry(transfer, &mesg->transfers, transfer_list) {
struct fsi_spi_sequence seq;
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 3967afa..1a08c1d 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -1080,12 +1080,11 @@
#ifdef CONFIG_PM_SLEEP
static int dspi_suspend(struct device *dev)
{
- struct spi_controller *ctlr = dev_get_drvdata(dev);
- struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);
+ struct fsl_dspi *dspi = dev_get_drvdata(dev);
if (dspi->irq)
disable_irq(dspi->irq);
- spi_controller_suspend(ctlr);
+ spi_controller_suspend(dspi->ctlr);
clk_disable_unprepare(dspi->clk);
pinctrl_pm_select_sleep_state(dev);
@@ -1095,8 +1094,7 @@
static int dspi_resume(struct device *dev)
{
- struct spi_controller *ctlr = dev_get_drvdata(dev);
- struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);
+ struct fsl_dspi *dspi = dev_get_drvdata(dev);
int ret;
pinctrl_pm_select_default_state(dev);
@@ -1104,7 +1102,7 @@
ret = clk_prepare_enable(dspi->clk);
if (ret)
return ret;
- spi_controller_resume(ctlr);
+ spi_controller_resume(dspi->ctlr);
if (dspi->irq)
enable_irq(dspi->irq);
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 986b979..a2886ee 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -938,9 +938,6 @@
spi_controller_get_devdata(controller);
pm_runtime_disable(fsl_lpspi->dev);
-
- spi_master_put(controller);
-
return 0;
}
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 060b1f5..4b80e27 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -1676,15 +1676,18 @@
goto out_master_put;
}
- pm_runtime_enable(spi_imx->dev);
+ ret = clk_prepare_enable(spi_imx->clk_per);
+ if (ret)
+ goto out_master_put;
+
+ ret = clk_prepare_enable(spi_imx->clk_ipg);
+ if (ret)
+ goto out_put_per;
+
pm_runtime_set_autosuspend_delay(spi_imx->dev, MXC_RPM_TIMEOUT);
pm_runtime_use_autosuspend(spi_imx->dev);
-
- ret = pm_runtime_get_sync(spi_imx->dev);
- if (ret < 0) {
- dev_err(spi_imx->dev, "failed to enable clock\n");
- goto out_runtime_pm_put;
- }
+ pm_runtime_set_active(spi_imx->dev);
+ pm_runtime_enable(spi_imx->dev);
spi_imx->spi_clk = clk_get_rate(spi_imx->clk_per);
/*
@@ -1722,8 +1725,12 @@
spi_imx_sdma_exit(spi_imx);
out_runtime_pm_put:
pm_runtime_dont_use_autosuspend(spi_imx->dev);
- pm_runtime_put_sync(spi_imx->dev);
+ pm_runtime_set_suspended(&pdev->dev);
pm_runtime_disable(spi_imx->dev);
+
+ clk_disable_unprepare(spi_imx->clk_ipg);
+out_put_per:
+ clk_disable_unprepare(spi_imx->clk_per);
out_master_put:
spi_master_put(master);
diff --git a/drivers/spi/spi-npcm-fiu.c b/drivers/spi/spi-npcm-fiu.c
index 341f7cf..1cb9329 100644
--- a/drivers/spi/spi-npcm-fiu.c
+++ b/drivers/spi/spi-npcm-fiu.c
@@ -679,7 +679,7 @@
struct resource *res;
int id;
- ctrl = spi_alloc_master(dev, sizeof(*fiu));
+ ctrl = devm_spi_alloc_master(dev, sizeof(*fiu));
if (!ctrl)
return -ENOMEM;
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 0cab239..05c75f8 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -812,18 +812,16 @@
enable = !enable;
if (spi->cs_gpiod || gpio_is_valid(spi->cs_gpio)) {
- /*
- * Honour the SPI_NO_CS flag and invert the enable line, as
- * active low is default for SPI. Execution paths that handle
- * polarity inversion in gpiolib (such as device tree) will
- * enforce active high using the SPI_CS_HIGH resulting in a
- * double inversion through the code above.
- */
if (!(spi->mode & SPI_NO_CS)) {
if (spi->cs_gpiod)
+ /* polarity handled by gpiolib */
gpiod_set_value_cansleep(spi->cs_gpiod,
- !enable);
+ enable1);
else
+ /*
+ * invert the enable line, as active low is
+ * default for SPI.
+ */
gpio_set_value_cansleep(spi->cs_gpio, !enable);
}
/* Some SPI masters need both GPIO CS & slave_select */
@@ -1992,15 +1990,6 @@
}
spi->chip_select = value;
- /*
- * For descriptors associated with the device, polarity inversion is
- * handled in the gpiolib, so all gpio chip selects are "active high"
- * in the logical sense, the gpiolib will invert the line if need be.
- */
- if ((ctlr->use_gpio_descriptors) && ctlr->cs_gpiods &&
- ctlr->cs_gpiods[spi->chip_select])
- spi->mode |= SPI_CS_HIGH;
-
/* Device speed */
if (!of_property_read_u32(nc, "spi-max-frequency", &value))
spi->max_speed_hz = value;
@@ -2453,6 +2442,49 @@
}
EXPORT_SYMBOL_GPL(__spi_alloc_controller);
+static void devm_spi_release_controller(struct device *dev, void *ctlr)
+{
+ spi_controller_put(*(struct spi_controller **)ctlr);
+}
+
+/**
+ * __devm_spi_alloc_controller - resource-managed __spi_alloc_controller()
+ * @dev: physical device of SPI controller
+ * @size: how much zeroed driver-private data to allocate
+ * @slave: whether to allocate an SPI master (false) or SPI slave (true)
+ * Context: can sleep
+ *
+ * Allocate an SPI controller and automatically release a reference on it
+ * when @dev is unbound from its driver. Drivers are thus relieved from
+ * having to call spi_controller_put().
+ *
+ * The arguments to this function are identical to __spi_alloc_controller().
+ *
+ * Return: the SPI controller structure on success, else NULL.
+ */
+struct spi_controller *__devm_spi_alloc_controller(struct device *dev,
+ unsigned int size,
+ bool slave)
+{
+ struct spi_controller **ptr, *ctlr;
+
+ ptr = devres_alloc(devm_spi_release_controller, sizeof(*ptr),
+ GFP_KERNEL);
+ if (!ptr)
+ return NULL;
+
+ ctlr = __spi_alloc_controller(dev, size, slave);
+ if (ctlr) {
+ *ptr = ctlr;
+ devres_add(dev, ptr);
+ } else {
+ devres_free(ptr);
+ }
+
+ return ctlr;
+}
+EXPORT_SYMBOL_GPL(__devm_spi_alloc_controller);
+
#ifdef CONFIG_OF
static int of_spi_get_gpio_numbers(struct spi_controller *ctlr)
{
@@ -2789,6 +2821,11 @@
}
EXPORT_SYMBOL_GPL(devm_spi_register_controller);
+static int devm_spi_match_controller(struct device *dev, void *res, void *ctlr)
+{
+ return *(struct spi_controller **)res == ctlr;
+}
+
static int __unregister(struct device *dev, void *null)
{
spi_unregister_device(to_spi_device(dev));
@@ -2830,7 +2867,15 @@
list_del(&ctlr->list);
mutex_unlock(&board_lock);
- device_unregister(&ctlr->dev);
+ device_del(&ctlr->dev);
+
+ /* Release the last reference on the controller if its driver
+ * has not yet been converted to devm_spi_alloc_master/slave().
+ */
+ if (!devres_find(ctlr->dev.parent, devm_spi_release_controller,
+ devm_spi_match_controller, ctlr))
+ put_device(&ctlr->dev);
+
/* free bus id */
mutex_lock(&board_lock);
if (found == ctlr)
diff --git a/drivers/staging/comedi/drivers/cb_pcidas.c b/drivers/staging/comedi/drivers/cb_pcidas.c
index 48ec2ee..d740c47 100644
--- a/drivers/staging/comedi/drivers/cb_pcidas.c
+++ b/drivers/staging/comedi/drivers/cb_pcidas.c
@@ -1342,6 +1342,7 @@
if (dev->irq && board->has_ao_fifo) {
dev->write_subdev = s;
s->subdev_flags |= SDF_CMD_WRITE;
+ s->len_chanlist = s->n_chan;
s->do_cmdtest = cb_pcidas_ao_cmdtest;
s->do_cmd = cb_pcidas_ao_cmd;
s->cancel = cb_pcidas_ao_cancel;
diff --git a/drivers/staging/fieldbus/anybuss/arcx-anybus.c b/drivers/staging/fieldbus/anybuss/arcx-anybus.c
index 5b8d0ba..b5fded1 100644
--- a/drivers/staging/fieldbus/anybuss/arcx-anybus.c
+++ b/drivers/staging/fieldbus/anybuss/arcx-anybus.c
@@ -293,7 +293,7 @@
regulator = devm_regulator_register(dev, &can_power_desc, &config);
if (IS_ERR(regulator)) {
err = PTR_ERR(regulator);
- goto out_reset;
+ goto out_ida;
}
/* make controller info visible to userspace */
cd->class_dev = kzalloc(sizeof(*cd->class_dev), GFP_KERNEL);
diff --git a/drivers/staging/octeon/ethernet-mdio.c b/drivers/staging/octeon/ethernet-mdio.c
index cfb673a..0bf54584 100644
--- a/drivers/staging/octeon/ethernet-mdio.c
+++ b/drivers/staging/octeon/ethernet-mdio.c
@@ -147,12 +147,6 @@
phy_node = of_parse_phandle(priv->of_node, "phy-handle", 0);
if (!phy_node && of_phy_is_fixed_link(priv->of_node)) {
- int rc;
-
- rc = of_phy_register_fixed_link(priv->of_node);
- if (rc)
- return rc;
-
phy_node = of_node_get(priv->of_node);
}
if (!phy_node)
diff --git a/drivers/staging/octeon/ethernet-rx.c b/drivers/staging/octeon/ethernet-rx.c
index 2c16230..9ebd665 100644
--- a/drivers/staging/octeon/ethernet-rx.c
+++ b/drivers/staging/octeon/ethernet-rx.c
@@ -69,15 +69,17 @@
else
port = work->word1.cn38xx.ipprt;
- if ((work->word2.snoip.err_code == 10) && (work->word1.len <= 64)) {
+ if ((work->word2.snoip.err_code == 10) && (work->word1.len <= 64))
/*
* Ignore length errors on min size packets. Some
* equipment incorrectly pads packets to 64+4FCS
* instead of 60+4FCS. Note these packets still get
* counted as frame errors.
*/
- } else if (work->word2.snoip.err_code == 5 ||
- work->word2.snoip.err_code == 7) {
+ return 0;
+
+ if (work->word2.snoip.err_code == 5 ||
+ work->word2.snoip.err_code == 7) {
/*
* We received a packet with either an alignment error
* or a FCS error. This may be signalling that we are
@@ -108,7 +110,10 @@
/* Port received 0xd5 preamble */
work->packet_ptr.s.addr += i + 1;
work->word1.len -= i + 5;
- } else if ((*ptr & 0xf) == 0xd) {
+ return 0;
+ }
+
+ if ((*ptr & 0xf) == 0xd) {
/* Port received 0xd preamble */
work->packet_ptr.s.addr += i;
work->word1.len -= i + 4;
@@ -118,21 +123,20 @@
((*(ptr + 1) & 0xf) << 4);
ptr++;
}
- } else {
- printk_ratelimited("Port %d unknown preamble, packet dropped\n",
- port);
- cvm_oct_free_work(work);
- return 1;
+ return 0;
}
+
+ printk_ratelimited("Port %d unknown preamble, packet dropped\n",
+ port);
+ cvm_oct_free_work(work);
+ return 1;
}
- } else {
- printk_ratelimited("Port %d receive error code %d, packet dropped\n",
- port, work->word2.snoip.err_code);
- cvm_oct_free_work(work);
- return 1;
}
- return 0;
+ printk_ratelimited("Port %d receive error code %d, packet dropped\n",
+ port, work->word2.snoip.err_code);
+ cvm_oct_free_work(work);
+ return 1;
}
static void copy_segments_to_skb(struct cvmx_wqe *work, struct sk_buff *skb)
diff --git a/drivers/staging/octeon/ethernet.c b/drivers/staging/octeon/ethernet.c
index 204f0b1..5dea6e9 100644
--- a/drivers/staging/octeon/ethernet.c
+++ b/drivers/staging/octeon/ethernet.c
@@ -13,6 +13,7 @@
#include <linux/phy.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
+#include <linux/of_mdio.h>
#include <linux/of_net.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
@@ -892,6 +893,14 @@
break;
}
+ if (priv->of_node && of_phy_is_fixed_link(priv->of_node)) {
+ if (of_phy_register_fixed_link(priv->of_node)) {
+ netdev_err(dev, "Failed to register fixed link for interface %d, port %d\n",
+ interface, priv->port);
+ dev->netdev_ops = NULL;
+ }
+ }
+
if (!dev->netdev_ops) {
free_netdev(dev);
} else if (register_netdev(dev) < 0) {
diff --git a/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c b/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c
index 3a42025..9097bcb 100644
--- a/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c
+++ b/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c
@@ -179,6 +179,9 @@
/* ordered workqueue to process all bulk operations */
struct workqueue_struct *bulk_wq;
+
+ /* handle for a vchiq instance */
+ struct vchiq_instance *vchiq_instance;
};
static struct mmal_msg_context *
@@ -1840,6 +1843,7 @@
mutex_unlock(&instance->vchiq_mutex);
+ vchiq_shutdown(instance->vchiq_instance);
flush_workqueue(instance->bulk_wq);
destroy_workqueue(instance->bulk_wq);
@@ -1856,6 +1860,7 @@
int vchiq_mmal_init(struct vchiq_mmal_instance **out_instance)
{
int status;
+ int err = -ENODEV;
struct vchiq_mmal_instance *instance;
static struct vchiq_instance *vchiq_instance;
struct vchiq_service_params_kernel params = {
@@ -1890,17 +1895,21 @@
status = vchiq_connect(vchiq_instance);
if (status) {
pr_err("Failed to connect VCHI instance (status=%d)\n", status);
- return -EIO;
+ err = -EIO;
+ goto err_shutdown_vchiq;
}
instance = kzalloc(sizeof(*instance), GFP_KERNEL);
- if (!instance)
- return -ENOMEM;
+ if (!instance) {
+ err = -ENOMEM;
+ goto err_shutdown_vchiq;
+ }
mutex_init(&instance->vchiq_mutex);
instance->bulk_scratch = vmalloc(PAGE_SIZE);
+ instance->vchiq_instance = vchiq_instance;
mutex_init(&instance->context_map_lock);
idr_init_base(&instance->context_map, 1);
@@ -1932,7 +1941,9 @@
err_free:
vfree(instance->bulk_scratch);
kfree(instance);
- return -ENODEV;
+err_shutdown_vchiq:
+ vchiq_shutdown(vchiq_instance);
+ return err;
}
EXPORT_SYMBOL_GPL(vchiq_mmal_init);
diff --git a/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml b/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml
index 43b5630..510edd1 100644
--- a/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml
+++ b/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml
@@ -24,7 +24,7 @@
In addition, it is recommended to declare a mmc-pwrseq on SDIO host above
WFx. Without it, you may encounter issues with warm boot. The mmc-pwrseq
should be compatible with mmc-pwrseq-simple. Please consult
- Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.txt for more
+ Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.yaml for more
information.
For SPI':'
diff --git a/drivers/staging/wfx/bh.c b/drivers/staging/wfx/bh.c
index 2ffa587..ed53d0b 100644
--- a/drivers/staging/wfx/bh.c
+++ b/drivers/staging/wfx/bh.c
@@ -21,7 +21,7 @@
if (!wdev->pdata.gpio_wakeup)
return;
- if (gpiod_get_value_cansleep(wdev->pdata.gpio_wakeup) >= 0)
+ if (gpiod_get_value_cansleep(wdev->pdata.gpio_wakeup) > 0)
return;
if (wfx_api_older_than(wdev, 1, 4)) {
diff --git a/drivers/staging/wfx/data_tx.c b/drivers/staging/wfx/data_tx.c
index 41f6a60..36b36ef 100644
--- a/drivers/staging/wfx/data_tx.c
+++ b/drivers/staging/wfx/data_tx.c
@@ -31,13 +31,13 @@
}
return rate->idx + 14;
}
+ // WFx only support 2GHz, else band information should be retrieved
+ // from ieee80211_tx_info
+ band = wdev->hw->wiphy->bands[NL80211_BAND_2GHZ];
if (rate->idx >= band->n_bitrates) {
WARN(1, "wrong rate->idx value: %d", rate->idx);
return -1;
}
- // WFx only support 2GHz, else band information should be retrieved
- // from ieee80211_tx_info
- band = wdev->hw->wiphy->bands[NL80211_BAND_2GHZ];
return band->bitrates[rate->idx].hw_value;
}
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index ea84d08..590e6d0 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -194,7 +194,7 @@
uint8_t tmr_type;
uint32_t tmr_cmd_cnt;
- int16_t tmr_cmd_ids[0];
+ int16_t tmr_cmd_ids[];
};
/*
diff --git a/drivers/tee/amdtee/amdtee_private.h b/drivers/tee/amdtee/amdtee_private.h
index d7f798c..337c8d8 100644
--- a/drivers/tee/amdtee/amdtee_private.h
+++ b/drivers/tee/amdtee/amdtee_private.h
@@ -64,9 +64,13 @@
/**
* struct amdtee_context_data - AMD-TEE driver context data
* @sess_list: Keeps track of sessions opened in current TEE context
+ * @shm_list: Keeps track of buffers allocated and mapped in current TEE
+ * context
*/
struct amdtee_context_data {
struct list_head sess_list;
+ struct list_head shm_list;
+ struct mutex shm_mutex; /* synchronizes access to @shm_list */
};
struct amdtee_driver_data {
@@ -89,10 +93,6 @@
u32 buf_id;
};
-struct amdtee_shm_context {
- struct list_head shmdata_list;
-};
-
#define LOWER_TWO_BYTE_MASK 0x0000FFFF
/**
diff --git a/drivers/tee/amdtee/core.c b/drivers/tee/amdtee/core.c
index 27b4cd7..8a6a8f3 100644
--- a/drivers/tee/amdtee/core.c
+++ b/drivers/tee/amdtee/core.c
@@ -20,7 +20,6 @@
static struct amdtee_driver_data *drv_data;
static DEFINE_MUTEX(session_list_mutex);
-static struct amdtee_shm_context shmctx;
static void amdtee_get_version(struct tee_device *teedev,
struct tee_ioctl_version_data *vers)
@@ -42,7 +41,8 @@
return -ENOMEM;
INIT_LIST_HEAD(&ctxdata->sess_list);
- INIT_LIST_HEAD(&shmctx.shmdata_list);
+ INIT_LIST_HEAD(&ctxdata->shm_list);
+ mutex_init(&ctxdata->shm_mutex);
ctx->data = ctxdata;
return 0;
@@ -86,6 +86,7 @@
list_del(&sess->list_node);
release_session(sess);
}
+ mutex_destroy(&ctxdata->shm_mutex);
kfree(ctxdata);
ctx->data = NULL;
@@ -152,14 +153,17 @@
u32 get_buffer_id(struct tee_shm *shm)
{
- u32 buf_id = 0;
+ struct amdtee_context_data *ctxdata = shm->ctx->data;
struct amdtee_shm_data *shmdata;
+ u32 buf_id = 0;
- list_for_each_entry(shmdata, &shmctx.shmdata_list, shm_node)
+ mutex_lock(&ctxdata->shm_mutex);
+ list_for_each_entry(shmdata, &ctxdata->shm_list, shm_node)
if (shmdata->kaddr == shm->kaddr) {
buf_id = shmdata->buf_id;
break;
}
+ mutex_unlock(&ctxdata->shm_mutex);
return buf_id;
}
@@ -333,8 +337,9 @@
int amdtee_map_shmem(struct tee_shm *shm)
{
- struct shmem_desc shmem;
+ struct amdtee_context_data *ctxdata;
struct amdtee_shm_data *shmnode;
+ struct shmem_desc shmem;
int rc, count;
u32 buf_id;
@@ -362,7 +367,10 @@
shmnode->kaddr = shm->kaddr;
shmnode->buf_id = buf_id;
- list_add(&shmnode->shm_node, &shmctx.shmdata_list);
+ ctxdata = shm->ctx->data;
+ mutex_lock(&ctxdata->shm_mutex);
+ list_add(&shmnode->shm_node, &ctxdata->shm_list);
+ mutex_unlock(&ctxdata->shm_mutex);
pr_debug("buf_id :[%x] kaddr[%p]\n", shmnode->buf_id, shmnode->kaddr);
@@ -371,6 +379,7 @@
void amdtee_unmap_shmem(struct tee_shm *shm)
{
+ struct amdtee_context_data *ctxdata;
struct amdtee_shm_data *shmnode;
u32 buf_id;
@@ -381,12 +390,15 @@
/* Unmap the shared memory from TEE */
handle_unmap_shmem(buf_id);
- list_for_each_entry(shmnode, &shmctx.shmdata_list, shm_node)
+ ctxdata = shm->ctx->data;
+ mutex_lock(&ctxdata->shm_mutex);
+ list_for_each_entry(shmnode, &ctxdata->shm_list, shm_node)
if (buf_id == shmnode->buf_id) {
list_del(&shmnode->shm_node);
kfree(shmnode);
break;
}
+ mutex_unlock(&ctxdata->shm_mutex);
}
int amdtee_invoke_func(struct tee_context *ctx,
diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c
index f53bf33..6ade4a5 100644
--- a/drivers/tee/tee_core.c
+++ b/drivers/tee/tee_core.c
@@ -200,7 +200,8 @@
int name_len;
int rc;
- if (connection_method == TEE_IOCTL_LOGIN_PUBLIC) {
+ if (connection_method == TEE_IOCTL_LOGIN_PUBLIC ||
+ connection_method == TEE_IOCTL_LOGIN_REE_KERNEL) {
/* Nil UUID to be passed to TEE environment */
uuid_copy(uuid, &uuid_null);
return 0;
diff --git a/drivers/thermal/ti-soc-thermal/ti-bandgap.c b/drivers/thermal/ti-soc-thermal/ti-bandgap.c
index 5e59616..dcac99f 100644
--- a/drivers/thermal/ti-soc-thermal/ti-bandgap.c
+++ b/drivers/thermal/ti-soc-thermal/ti-bandgap.c
@@ -20,6 +20,7 @@
#include <linux/err.h>
#include <linux/types.h>
#include <linux/spinlock.h>
+#include <linux/sys_soc.h>
#include <linux/reboot.h>
#include <linux/of_device.h>
#include <linux/of_platform.h>
@@ -864,6 +865,17 @@
return bgp;
}
+/*
+ * List of SoCs on which the CPU PM notifier can cause erros on the DTEMP
+ * readout.
+ * Enabled notifier on these machines results in erroneous, random values which
+ * could trigger unexpected thermal shutdown.
+ */
+static const struct soc_device_attribute soc_no_cpu_notifier[] = {
+ { .machine = "OMAP4430" },
+ { /* sentinel */ },
+};
+
/*** Device driver call backs ***/
static
@@ -1020,7 +1032,8 @@
#ifdef CONFIG_PM_SLEEP
bgp->nb.notifier_call = bandgap_omap_cpu_notifier;
- cpu_pm_register_notifier(&bgp->nb);
+ if (!soc_device_match(soc_no_cpu_notifier))
+ cpu_pm_register_notifier(&bgp->nb);
#endif
return 0;
@@ -1056,7 +1069,8 @@
struct ti_bandgap *bgp = platform_get_drvdata(pdev);
int i;
- cpu_pm_unregister_notifier(&bgp->nb);
+ if (!soc_device_match(soc_no_cpu_notifier))
+ cpu_pm_unregister_notifier(&bgp->nb);
/* Remove sensor interfaces */
for (i = 0; i < bgp->conf->sensor_count; i++) {
diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c
index 3680b27..ed65d2b 100644
--- a/drivers/thunderbolt/debugfs.c
+++ b/drivers/thunderbolt/debugfs.c
@@ -9,6 +9,7 @@
#include <linux/debugfs.h>
#include <linux/pm_runtime.h>
+#include <linux/uaccess.h>
#include "tb.h"
diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c
index b51fc3f..977ba91 100644
--- a/drivers/thunderbolt/icm.c
+++ b/drivers/thunderbolt/icm.c
@@ -2284,6 +2284,8 @@
case PCI_DEVICE_ID_INTEL_TGL_NHI0:
case PCI_DEVICE_ID_INTEL_TGL_NHI1:
+ case PCI_DEVICE_ID_INTEL_TGL_H_NHI0:
+ case PCI_DEVICE_ID_INTEL_TGL_H_NHI1:
icm->is_supported = icm_tgl_is_supported;
icm->driver_ready = icm_icl_driver_ready;
icm->set_uuid = icm_icl_set_uuid;
diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c
index 3f79baa..db80dc5 100644
--- a/drivers/thunderbolt/nhi.c
+++ b/drivers/thunderbolt/nhi.c
@@ -406,12 +406,23 @@
ring->vector = ret;
- ring->irq = pci_irq_vector(ring->nhi->pdev, ring->vector);
- if (ring->irq < 0)
- return ring->irq;
+ ret = pci_irq_vector(ring->nhi->pdev, ring->vector);
+ if (ret < 0)
+ goto err_ida_remove;
+
+ ring->irq = ret;
irqflags = no_suspend ? IRQF_NO_SUSPEND : 0;
- return request_irq(ring->irq, ring_msix, irqflags, "thunderbolt", ring);
+ ret = request_irq(ring->irq, ring_msix, irqflags, "thunderbolt", ring);
+ if (ret)
+ goto err_ida_remove;
+
+ return 0;
+
+err_ida_remove:
+ ida_simple_remove(&nhi->msix_ida, ring->vector);
+
+ return ret;
}
static void ring_release_msix(struct tb_ring *ring)
@@ -1334,6 +1345,10 @@
.driver_data = (kernel_ulong_t)&icl_nhi_ops },
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_NHI1),
.driver_data = (kernel_ulong_t)&icl_nhi_ops },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_H_NHI0),
+ .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_H_NHI1),
+ .driver_data = (kernel_ulong_t)&icl_nhi_ops },
/* Any USB4 compliant host */
{ PCI_DEVICE_CLASS(PCI_CLASS_SERIAL_USB_USB4, ~0) },
diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h
index 80162e4..4e0861d 100644
--- a/drivers/thunderbolt/nhi.h
+++ b/drivers/thunderbolt/nhi.h
@@ -75,6 +75,8 @@
#define PCI_DEVICE_ID_INTEL_ICL_NHI0 0x8a17
#define PCI_DEVICE_ID_INTEL_TGL_NHI0 0x9a1b
#define PCI_DEVICE_ID_INTEL_TGL_NHI1 0x9a1d
+#define PCI_DEVICE_ID_INTEL_TGL_H_NHI0 0x9a1f
+#define PCI_DEVICE_ID_INTEL_TGL_H_NHI1 0x9a21
#define PCI_CLASS_SERIAL_USB_USB4 0x0c0340
diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h
index a9995e2..8ea360b 100644
--- a/drivers/thunderbolt/tb.h
+++ b/drivers/thunderbolt/tb.h
@@ -784,6 +784,8 @@
switch (sw->config.device_id) {
case PCI_DEVICE_ID_INTEL_TGL_NHI0:
case PCI_DEVICE_ID_INTEL_TGL_NHI1:
+ case PCI_DEVICE_ID_INTEL_TGL_H_NHI0:
+ case PCI_DEVICE_ID_INTEL_TGL_H_NHI1:
return true;
}
}
diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c
index 40f1357..f2583b4 100644
--- a/drivers/thunderbolt/usb4.c
+++ b/drivers/thunderbolt/usb4.c
@@ -421,8 +421,12 @@
* upstream USB4 port.
*/
tb_switch_for_each_port(sw, port) {
+ if (!tb_port_is_null(port))
+ continue;
if (!route && tb_is_upstream_port(port))
continue;
+ if (!port->cap_usb4)
+ continue;
ret = tb_port_read(port, &val, TB_CFG_PORT,
port->cap_usb4 + PORT_CS_19, 1);
diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c
index 4890785..c00ad81 100644
--- a/drivers/thunderbolt/xdomain.c
+++ b/drivers/thunderbolt/xdomain.c
@@ -881,6 +881,7 @@
id = ida_simple_get(&xd->service_ids, 0, 0, GFP_KERNEL);
if (id < 0) {
+ kfree(svc->key);
kfree(svc);
break;
}
diff --git a/drivers/tty/serial/21285.c b/drivers/tty/serial/21285.c
index 718e010..09baef4 100644
--- a/drivers/tty/serial/21285.c
+++ b/drivers/tty/serial/21285.c
@@ -50,25 +50,25 @@
static bool is_enabled(struct uart_port *port, int bit)
{
- unsigned long private_data = (unsigned long)port->private_data;
+ unsigned long *private_data = (unsigned long *)&port->private_data;
- if (test_bit(bit, &private_data))
+ if (test_bit(bit, private_data))
return true;
return false;
}
static void enable(struct uart_port *port, int bit)
{
- unsigned long private_data = (unsigned long)port->private_data;
+ unsigned long *private_data = (unsigned long *)&port->private_data;
- set_bit(bit, &private_data);
+ set_bit(bit, private_data);
}
static void disable(struct uart_port *port, int bit)
{
- unsigned long private_data = (unsigned long)port->private_data;
+ unsigned long *private_data = (unsigned long *)&port->private_data;
- clear_bit(bit, &private_data);
+ clear_bit(bit, private_data);
}
#define is_tx_enabled(port) is_enabled(port, tx_enabled_bit)
diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c
index 41f4120..fa876e2 100644
--- a/drivers/tty/serial/8250/8250_mtk.c
+++ b/drivers/tty/serial/8250/8250_mtk.c
@@ -317,7 +317,7 @@
*/
baud = tty_termios_baud_rate(termios);
- serial8250_do_set_termios(port, termios, old);
+ serial8250_do_set_termios(port, termios, NULL);
tty_termios_encode_baud_rate(termios, baud, baud);
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 1044fc3..28f22e5 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -522,6 +522,7 @@
depends on OF
select SERIAL_EARLYCON
select SERIAL_CORE_CONSOLE
+ default y if SERIAL_IMX_CONSOLE
help
If you have enabled the earlycon on the Freescale IMX
CPU you can make it the earlycon by answering Y to this option.
diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index ff4b88c..bd047e1 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -314,9 +314,10 @@
/* Forward declare this for the dma callbacks*/
static void lpuart_dma_tx_complete(void *arg);
-static inline bool is_ls1028a_lpuart(struct lpuart_port *sport)
+static inline bool is_layerscape_lpuart(struct lpuart_port *sport)
{
- return sport->devtype == LS1028A_LPUART;
+ return (sport->devtype == LS1021A_LPUART ||
+ sport->devtype == LS1028A_LPUART);
}
static inline bool is_imx8qxp_lpuart(struct lpuart_port *sport)
@@ -1701,11 +1702,11 @@
UARTFIFO_FIFOSIZE_MASK);
/*
- * The LS1028A has a fixed length of 16 words. Although it supports the
- * RX/TXSIZE fields their encoding is different. Eg the reference manual
- * states 0b101 is 16 words.
+ * The LS1021A and LS1028A have a fixed FIFO depth of 16 words.
+ * Although they support the RX/TXSIZE fields, their encoding is
+ * different. Eg the reference manual states 0b101 is 16 words.
*/
- if (is_ls1028a_lpuart(sport)) {
+ if (is_layerscape_lpuart(sport)) {
sport->rxfifo_size = 16;
sport->txfifo_size = 16;
sport->port.fifosize = sport->txfifo_size;
diff --git a/drivers/tty/serial/serial_txx9.c b/drivers/tty/serial/serial_txx9.c
index b4d89e3..7a07e72 100644
--- a/drivers/tty/serial/serial_txx9.c
+++ b/drivers/tty/serial/serial_txx9.c
@@ -1280,6 +1280,9 @@
#ifdef ENABLE_SERIAL_TXX9_PCI
ret = pci_register_driver(&serial_txx9_pci_driver);
+ if (ret) {
+ platform_driver_unregister(&serial_txx9_plat_driver);
+ }
#endif
if (ret == 0)
goto out;
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 7a4c025..9f8b9a5 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -1515,10 +1515,12 @@
tty->ops->shutdown(tty);
tty_save_termios(tty);
tty_driver_remove_tty(tty->driver, tty);
- tty->port->itty = NULL;
+ if (tty->port)
+ tty->port->itty = NULL;
if (tty->link)
tty->link->port->itty = NULL;
- tty_buffer_cancel_work(tty->port);
+ if (tty->port)
+ tty_buffer_cancel_work(tty->port);
if (tty->link)
tty_buffer_cancel_work(tty->link->port);
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index 0db53b5..78acc27 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -743,8 +743,13 @@
return;
if ((unsigned)value < ARRAY_SIZE(func_table)) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&func_buf_lock, flags);
if (func_table[value])
puts_queue(vc, func_table[value]);
+ spin_unlock_irqrestore(&func_buf_lock, flags);
+
} else
pr_err("k_fn called with value=%d\n", value);
}
@@ -1991,13 +1996,11 @@
#undef s
#undef v
-/* FIXME: This one needs untangling and locking */
+/* FIXME: This one needs untangling */
int vt_do_kdgkb_ioctl(int cmd, struct kbsentry __user *user_kdgkb, int perm)
{
struct kbsentry *kbs;
- char *p;
u_char *q;
- u_char __user *up;
int sz, fnw_sz;
int delta;
char *first_free, *fj, *fnw;
@@ -2023,23 +2026,19 @@
i = array_index_nospec(kbs->kb_func, MAX_NR_FUNC);
switch (cmd) {
- case KDGKBSENT:
- sz = sizeof(kbs->kb_string) - 1; /* sz should have been
- a struct member */
- up = user_kdgkb->kb_string;
- p = func_table[i];
- if(p)
- for ( ; *p && sz; p++, sz--)
- if (put_user(*p, up++)) {
- ret = -EFAULT;
- goto reterr;
- }
- if (put_user('\0', up)) {
- ret = -EFAULT;
- goto reterr;
- }
- kfree(kbs);
- return ((p && *p) ? -EOVERFLOW : 0);
+ case KDGKBSENT: {
+ /* size should have been a struct member */
+ ssize_t len = sizeof(user_kdgkb->kb_string);
+
+ spin_lock_irqsave(&func_buf_lock, flags);
+ len = strlcpy(kbs->kb_string, func_table[i] ? : "", len);
+ spin_unlock_irqrestore(&func_buf_lock, flags);
+
+ ret = copy_to_user(user_kdgkb->kb_string, kbs->kb_string,
+ len + 1) ? -EFAULT : 0;
+
+ goto reterr;
+ }
case KDSKBSENT:
if (!perm) {
ret = -EPERM;
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 9506a76..d04a162 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -4704,27 +4704,6 @@
return rc;
}
-static int con_font_copy(struct vc_data *vc, struct console_font_op *op)
-{
- int con = op->height;
- int rc;
-
-
- console_lock();
- if (vc->vc_mode != KD_TEXT)
- rc = -EINVAL;
- else if (!vc->vc_sw->con_font_copy)
- rc = -ENOSYS;
- else if (con < 0 || !vc_cons_allocated(con))
- rc = -ENOTTY;
- else if (con == vc->vc_num) /* nothing to do */
- rc = 0;
- else
- rc = vc->vc_sw->con_font_copy(vc, con);
- console_unlock();
- return rc;
-}
-
int con_font_op(struct vc_data *vc, struct console_font_op *op)
{
switch (op->op) {
@@ -4735,7 +4714,8 @@
case KD_FONT_OP_SET_DEFAULT:
return con_font_default(vc, op);
case KD_FONT_OP_COPY:
- return con_font_copy(vc, op);
+ /* was buggy and never really used */
+ return -EINVAL;
}
return -ENOSYS;
}
diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c
index 0a33b8a..5f61b25a9 100644
--- a/drivers/tty/vt/vt_ioctl.c
+++ b/drivers/tty/vt/vt_ioctl.c
@@ -484,7 +484,7 @@
return 0;
}
-static inline int do_fontx_ioctl(int cmd,
+static inline int do_fontx_ioctl(struct vc_data *vc, int cmd,
struct consolefontdesc __user *user_cfd,
struct console_font_op *op)
{
@@ -502,15 +502,16 @@
op->height = cfdarg.charheight;
op->charcount = cfdarg.charcount;
op->data = cfdarg.chardata;
- return con_font_op(vc_cons[fg_console].d, op);
- case GIO_FONTX: {
+ return con_font_op(vc, op);
+
+ case GIO_FONTX:
op->op = KD_FONT_OP_GET;
op->flags = KD_FONT_FLAG_OLD;
op->width = 8;
op->height = cfdarg.charheight;
op->charcount = cfdarg.charcount;
op->data = cfdarg.chardata;
- i = con_font_op(vc_cons[fg_console].d, op);
+ i = con_font_op(vc, op);
if (i)
return i;
cfdarg.charheight = op->height;
@@ -518,12 +519,11 @@
if (copy_to_user(user_cfd, &cfdarg, sizeof(struct consolefontdesc)))
return -EFAULT;
return 0;
- }
}
return -EINVAL;
}
-static int vt_io_fontreset(struct console_font_op *op)
+static int vt_io_fontreset(struct vc_data *vc, struct console_font_op *op)
{
int ret;
@@ -537,19 +537,19 @@
op->op = KD_FONT_OP_SET_DEFAULT;
op->data = NULL;
- ret = con_font_op(vc_cons[fg_console].d, op);
+ ret = con_font_op(vc, op);
if (ret)
return ret;
console_lock();
- con_set_default_unimap(vc_cons[fg_console].d);
+ con_set_default_unimap(vc);
console_unlock();
return 0;
}
static inline int do_unimap_ioctl(int cmd, struct unimapdesc __user *user_ud,
- struct vc_data *vc)
+ bool perm, struct vc_data *vc)
{
struct unimapdesc tmp;
@@ -557,9 +557,11 @@
return -EFAULT;
switch (cmd) {
case PIO_UNIMAP:
+ if (!perm)
+ return -EPERM;
return con_set_unimap(vc, tmp.entry_ct, tmp.entries);
case GIO_UNIMAP:
- if (fg_console != vc->vc_num)
+ if (!perm && fg_console != vc->vc_num)
return -EPERM;
return con_get_unimap(vc, tmp.entry_ct, &(user_ud->entry_ct),
tmp.entries);
@@ -582,7 +584,7 @@
op.height = 0;
op.charcount = 256;
op.data = up;
- return con_font_op(vc_cons[fg_console].d, &op);
+ return con_font_op(vc, &op);
case GIO_FONT:
op.op = KD_FONT_OP_GET;
@@ -591,7 +593,7 @@
op.height = 32;
op.charcount = 256;
op.data = up;
- return con_font_op(vc_cons[fg_console].d, &op);
+ return con_font_op(vc, &op);
case PIO_CMAP:
if (!perm)
@@ -607,13 +609,13 @@
fallthrough;
case GIO_FONTX:
- return do_fontx_ioctl(cmd, up, &op);
+ return do_fontx_ioctl(vc, cmd, up, &op);
case PIO_FONTRESET:
if (!perm)
return -EPERM;
- return vt_io_fontreset(&op);
+ return vt_io_fontreset(vc, &op);
case PIO_SCRNMAP:
if (!perm)
@@ -639,10 +641,7 @@
case PIO_UNIMAP:
case GIO_UNIMAP:
- if (!perm)
- return -EPERM;
-
- return do_unimap_ioctl(cmd, up, vc);
+ return do_unimap_ioctl(cmd, up, perm, vc);
default:
return -ENOIOCTLCMD;
@@ -1067,8 +1066,9 @@
};
static inline int
-compat_fontx_ioctl(int cmd, struct compat_consolefontdesc __user *user_cfd,
- int perm, struct console_font_op *op)
+compat_fontx_ioctl(struct vc_data *vc, int cmd,
+ struct compat_consolefontdesc __user *user_cfd,
+ int perm, struct console_font_op *op)
{
struct compat_consolefontdesc cfdarg;
int i;
@@ -1086,7 +1086,8 @@
op->height = cfdarg.charheight;
op->charcount = cfdarg.charcount;
op->data = compat_ptr(cfdarg.chardata);
- return con_font_op(vc_cons[fg_console].d, op);
+ return con_font_op(vc, op);
+
case GIO_FONTX:
op->op = KD_FONT_OP_GET;
op->flags = KD_FONT_FLAG_OLD;
@@ -1094,7 +1095,7 @@
op->height = cfdarg.charheight;
op->charcount = cfdarg.charcount;
op->data = compat_ptr(cfdarg.chardata);
- i = con_font_op(vc_cons[fg_console].d, op);
+ i = con_font_op(vc, op);
if (i)
return i;
cfdarg.charheight = op->height;
@@ -1184,7 +1185,7 @@
*/
case PIO_FONTX:
case GIO_FONTX:
- return compat_fontx_ioctl(cmd, up, perm, &op);
+ return compat_fontx_ioctl(vc, cmd, up, perm, &op);
case KDFONTOP:
return compat_kdfontop_ioctl(up, perm, &op, vc);
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index 6dca744..be06f1a 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -413,10 +413,10 @@
return retval;
}
-static void uio_free_minor(struct uio_device *idev)
+static void uio_free_minor(unsigned long minor)
{
mutex_lock(&minor_lock);
- idr_remove(&uio_idr, idev->minor);
+ idr_remove(&uio_idr, minor);
mutex_unlock(&minor_lock);
}
@@ -990,7 +990,7 @@
err_uio_dev_add_attributes:
device_del(&idev->dev);
err_device_create:
- uio_free_minor(idev);
+ uio_free_minor(idev->minor);
put_device(&idev->dev);
return ret;
}
@@ -1042,11 +1042,13 @@
void uio_unregister_device(struct uio_info *info)
{
struct uio_device *idev;
+ unsigned long minor;
if (!info || !info->uio_dev)
return;
idev = info->uio_dev;
+ minor = idev->minor;
mutex_lock(&idev->info_lock);
uio_dev_del_attributes(idev);
@@ -1062,7 +1064,7 @@
device_unregister(&idev->dev);
- uio_free_minor(idev);
+ uio_free_minor(minor);
return;
}
diff --git a/drivers/usb/cdns3/ep0.c b/drivers/usb/cdns3/ep0.c
index 4761c85..d3121a3 100644
--- a/drivers/usb/cdns3/ep0.c
+++ b/drivers/usb/cdns3/ep0.c
@@ -137,48 +137,36 @@
struct usb_ctrlrequest *ctrl_req)
{
enum usb_device_state device_state = priv_dev->gadget.state;
- struct cdns3_endpoint *priv_ep;
u32 config = le16_to_cpu(ctrl_req->wValue);
int result = 0;
- int i;
switch (device_state) {
case USB_STATE_ADDRESS:
- /* Configure non-control EPs */
- for (i = 0; i < CDNS3_ENDPOINTS_MAX_COUNT; i++) {
- priv_ep = priv_dev->eps[i];
- if (!priv_ep)
- continue;
-
- if (priv_ep->flags & EP_CLAIMED)
- cdns3_ep_config(priv_ep);
- }
-
result = cdns3_ep0_delegate_req(priv_dev, ctrl_req);
- if (result)
- return result;
-
- if (!config) {
- cdns3_hw_reset_eps_config(priv_dev);
- usb_gadget_set_state(&priv_dev->gadget,
- USB_STATE_ADDRESS);
- }
+ if (result || !config)
+ goto reset_config;
break;
case USB_STATE_CONFIGURED:
result = cdns3_ep0_delegate_req(priv_dev, ctrl_req);
+ if (!config && !result)
+ goto reset_config;
- if (!config && !result) {
- cdns3_hw_reset_eps_config(priv_dev);
- usb_gadget_set_state(&priv_dev->gadget,
- USB_STATE_ADDRESS);
- }
break;
default:
- result = -EINVAL;
+ return -EINVAL;
}
+ return 0;
+
+reset_config:
+ if (result != USB_GADGET_DELAYED_STATUS)
+ cdns3_hw_reset_eps_config(priv_dev);
+
+ usb_gadget_set_state(&priv_dev->gadget,
+ USB_STATE_ADDRESS);
+
return result;
}
@@ -705,6 +693,7 @@
unsigned long flags;
int ret = 0;
u8 zlp = 0;
+ int i;
spin_lock_irqsave(&priv_dev->lock, flags);
trace_cdns3_ep0_queue(priv_dev, request);
@@ -720,6 +709,17 @@
u32 val;
cdns3_select_ep(priv_dev, 0x00);
+
+ /*
+ * Configure all non-control EPs which are not enabled by class driver
+ */
+ for (i = 0; i < CDNS3_ENDPOINTS_MAX_COUNT; i++) {
+ priv_ep = priv_dev->eps[i];
+ if (priv_ep && priv_ep->flags & EP_CLAIMED &&
+ !(priv_ep->flags & EP_ENABLED))
+ cdns3_ep_config(priv_ep, 0);
+ }
+
cdns3_set_hw_configuration(priv_dev);
cdns3_ep0_complete_setup(priv_dev, 0, 1);
/* wait until configuration set */
@@ -811,6 +811,7 @@
struct cdns3_usb_regs __iomem *regs;
struct cdns3_endpoint *priv_ep;
u32 max_packet_size = 64;
+ u32 ep_cfg;
regs = priv_dev->regs;
@@ -842,8 +843,10 @@
BIT(0) | BIT(16));
}
- writel(EP_CFG_ENABLE | EP_CFG_MAXPKTSIZE(max_packet_size),
- ®s->ep_cfg);
+ ep_cfg = EP_CFG_ENABLE | EP_CFG_MAXPKTSIZE(max_packet_size);
+
+ if (!(priv_ep->flags & EP_CONFIGURED))
+ writel(ep_cfg, ®s->ep_cfg);
writel(EP_STS_EN_SETUPEN | EP_STS_EN_DESCMISEN | EP_STS_EN_TRBERREN,
®s->ep_sts_en);
@@ -851,8 +854,10 @@
/* init ep in */
cdns3_select_ep(priv_dev, USB_DIR_IN);
- writel(EP_CFG_ENABLE | EP_CFG_MAXPKTSIZE(max_packet_size),
- ®s->ep_cfg);
+ if (!(priv_ep->flags & EP_CONFIGURED))
+ writel(ep_cfg, ®s->ep_cfg);
+
+ priv_ep->flags |= EP_CONFIGURED;
writel(EP_STS_EN_SETUPEN | EP_STS_EN_TRBERREN, ®s->ep_sts_en);
diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c
index 6e7b70a..66c1e67 100644
--- a/drivers/usb/cdns3/gadget.c
+++ b/drivers/usb/cdns3/gadget.c
@@ -296,6 +296,8 @@
*/
void cdns3_hw_reset_eps_config(struct cdns3_device *priv_dev)
{
+ int i;
+
writel(USB_CONF_CFGRST, &priv_dev->regs->usb_conf);
cdns3_allow_enable_l1(priv_dev, 0);
@@ -304,6 +306,10 @@
priv_dev->out_mem_is_allocated = 0;
priv_dev->wait_for_setup = 0;
priv_dev->using_streams = 0;
+
+ for (i = 0; i < CDNS3_ENDPOINTS_MAX_COUNT; i++)
+ if (priv_dev->eps[i])
+ priv_dev->eps[i]->flags &= ~EP_CONFIGURED;
}
/**
@@ -506,7 +512,6 @@
while (!list_empty(&priv_ep->wa2_descmiss_req_list)) {
int chunk_end;
- int length;
descmiss_priv_req =
cdns3_next_priv_request(&priv_ep->wa2_descmiss_req_list);
@@ -517,7 +522,6 @@
break;
chunk_end = descmiss_priv_req->flags & REQUEST_INTERNAL_CH;
- length = request->actual + descmiss_req->actual;
request->status = descmiss_req->status;
__cdns3_descmiss_copy_data(request, descmiss_req);
list_del_init(&descmiss_priv_req->list);
@@ -1746,11 +1750,8 @@
static void cdns3_disconnect_gadget(struct cdns3_device *priv_dev)
{
- if (priv_dev->gadget_driver && priv_dev->gadget_driver->disconnect) {
- spin_unlock(&priv_dev->lock);
+ if (priv_dev->gadget_driver && priv_dev->gadget_driver->disconnect)
priv_dev->gadget_driver->disconnect(&priv_dev->gadget);
- spin_lock(&priv_dev->lock);
- }
}
/**
@@ -1761,6 +1762,7 @@
*/
static void cdns3_check_usb_interrupt_proceed(struct cdns3_device *priv_dev,
u32 usb_ists)
+__must_hold(&priv_dev->lock)
{
int speed = 0;
@@ -1785,7 +1787,9 @@
/* Disconnection detected */
if (usb_ists & (USB_ISTS_DIS2I | USB_ISTS_DISI)) {
+ spin_unlock(&priv_dev->lock);
cdns3_disconnect_gadget(priv_dev);
+ spin_lock(&priv_dev->lock);
priv_dev->gadget.speed = USB_SPEED_UNKNOWN;
usb_gadget_set_state(&priv_dev->gadget, USB_STATE_NOTATTACHED);
cdns3_hw_reset_eps_config(priv_dev);
@@ -1979,27 +1983,6 @@
return 0;
}
-static void cdns3_stream_ep_reconfig(struct cdns3_device *priv_dev,
- struct cdns3_endpoint *priv_ep)
-{
- if (!priv_ep->use_streams || priv_dev->gadget.speed < USB_SPEED_SUPER)
- return;
-
- if (priv_dev->dev_ver >= DEV_VER_V3) {
- u32 mask = BIT(priv_ep->num + (priv_ep->dir ? 16 : 0));
-
- /*
- * Stream capable endpoints are handled by using ep_tdl
- * register. Other endpoints use TDL from TRB feature.
- */
- cdns3_clear_register_bit(&priv_dev->regs->tdl_from_trb, mask);
- }
-
- /* Enable Stream Bit TDL chk and SID chk */
- cdns3_set_register_bit(&priv_dev->regs->ep_cfg, EP_CFG_STREAM_EN |
- EP_CFG_TDL_CHK | EP_CFG_SID_CHK);
-}
-
static void cdns3_configure_dmult(struct cdns3_device *priv_dev,
struct cdns3_endpoint *priv_ep)
{
@@ -2037,8 +2020,9 @@
/**
* cdns3_ep_config Configure hardware endpoint
* @priv_ep: extended endpoint object
+ * @enable: set EP_CFG_ENABLE bit in ep_cfg register.
*/
-void cdns3_ep_config(struct cdns3_endpoint *priv_ep)
+int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable)
{
bool is_iso_ep = (priv_ep->type == USB_ENDPOINT_XFER_ISOC);
struct cdns3_device *priv_dev = priv_ep->cdns3_dev;
@@ -2099,7 +2083,7 @@
break;
default:
/* all other speed are not supported */
- return;
+ return -EINVAL;
}
if (max_packet_size == 1024)
@@ -2109,11 +2093,33 @@
else
priv_ep->trb_burst_size = 16;
- ret = cdns3_ep_onchip_buffer_reserve(priv_dev, buffering + 1,
- !!priv_ep->dir);
- if (ret) {
- dev_err(priv_dev->dev, "onchip mem is full, ep is invalid\n");
- return;
+ /* onchip buffer is only allocated before configuration */
+ if (!priv_dev->hw_configured_flag) {
+ ret = cdns3_ep_onchip_buffer_reserve(priv_dev, buffering + 1,
+ !!priv_ep->dir);
+ if (ret) {
+ dev_err(priv_dev->dev, "onchip mem is full, ep is invalid\n");
+ return ret;
+ }
+ }
+
+ if (enable)
+ ep_cfg |= EP_CFG_ENABLE;
+
+ if (priv_ep->use_streams && priv_dev->gadget.speed >= USB_SPEED_SUPER) {
+ if (priv_dev->dev_ver >= DEV_VER_V3) {
+ u32 mask = BIT(priv_ep->num + (priv_ep->dir ? 16 : 0));
+
+ /*
+ * Stream capable endpoints are handled by using ep_tdl
+ * register. Other endpoints use TDL from TRB feature.
+ */
+ cdns3_clear_register_bit(&priv_dev->regs->tdl_from_trb,
+ mask);
+ }
+
+ /* Enable Stream Bit TDL chk and SID chk */
+ ep_cfg |= EP_CFG_STREAM_EN | EP_CFG_TDL_CHK | EP_CFG_SID_CHK;
}
ep_cfg |= EP_CFG_MAXPKTSIZE(max_packet_size) |
@@ -2123,9 +2129,12 @@
cdns3_select_ep(priv_dev, bEndpointAddress);
writel(ep_cfg, &priv_dev->regs->ep_cfg);
+ priv_ep->flags |= EP_CONFIGURED;
dev_dbg(priv_dev->dev, "Configure %s: with val %08x\n",
priv_ep->name, ep_cfg);
+
+ return 0;
}
/* Find correct direction for HW endpoint according to description */
@@ -2266,7 +2275,7 @@
u32 bEndpointAddress;
unsigned long flags;
int enable = 1;
- int ret;
+ int ret = 0;
int val;
priv_ep = ep_to_cdns3_ep(ep);
@@ -2305,6 +2314,17 @@
bEndpointAddress = priv_ep->num | priv_ep->dir;
cdns3_select_ep(priv_dev, bEndpointAddress);
+ /*
+ * For some versions of controller at some point during ISO OUT traffic
+ * DMA reads Transfer Ring for the EP which has never got doorbell.
+ * This issue was detected only on simulation, but to avoid this issue
+ * driver add protection against it. To fix it driver enable ISO OUT
+ * endpoint before setting DRBL. This special treatment of ISO OUT
+ * endpoints are recommended by controller specification.
+ */
+ if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && !priv_ep->dir)
+ enable = 0;
+
if (usb_ss_max_streams(comp_desc) && usb_endpoint_xfer_bulk(desc)) {
/*
* Enable stream support (SS mode) related interrupts
@@ -2315,13 +2335,17 @@
EP_STS_EN_SIDERREN | EP_STS_EN_MD_EXITEN |
EP_STS_EN_STREAMREN;
priv_ep->use_streams = true;
- cdns3_stream_ep_reconfig(priv_dev, priv_ep);
+ ret = cdns3_ep_config(priv_ep, enable);
priv_dev->using_streams |= true;
}
+ } else {
+ ret = cdns3_ep_config(priv_ep, enable);
}
- ret = cdns3_allocate_trb_pool(priv_ep);
+ if (ret)
+ goto exit;
+ ret = cdns3_allocate_trb_pool(priv_ep);
if (ret)
goto exit;
@@ -2351,20 +2375,6 @@
writel(reg, &priv_dev->regs->ep_sts_en);
- /*
- * For some versions of controller at some point during ISO OUT traffic
- * DMA reads Transfer Ring for the EP which has never got doorbell.
- * This issue was detected only on simulation, but to avoid this issue
- * driver add protection against it. To fix it driver enable ISO OUT
- * endpoint before setting DRBL. This special treatment of ISO OUT
- * endpoints are recommended by controller specification.
- */
- if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && !priv_ep->dir)
- enable = 0;
-
- if (enable)
- cdns3_set_register_bit(&priv_dev->regs->ep_cfg, EP_CFG_ENABLE);
-
ep->desc = desc;
priv_ep->flags &= ~(EP_PENDING_REQUEST | EP_STALLED | EP_STALL_PENDING |
EP_QUIRK_ISO_OUT_EN | EP_QUIRK_EXTRA_BUF_EN);
@@ -3265,10 +3275,13 @@
}
static int cdns3_gadget_suspend(struct cdns3 *cdns, bool do_wakeup)
+__must_hold(&cdns->lock)
{
struct cdns3_device *priv_dev = cdns->gadget_dev;
+ spin_unlock(&cdns->lock);
cdns3_disconnect_gadget(priv_dev);
+ spin_lock(&cdns->lock);
priv_dev->gadget.speed = USB_SPEED_UNKNOWN;
usb_gadget_set_state(&priv_dev->gadget, USB_STATE_NOTATTACHED);
diff --git a/drivers/usb/cdns3/gadget.h b/drivers/usb/cdns3/gadget.h
index 1ccecd2..21fa461 100644
--- a/drivers/usb/cdns3/gadget.h
+++ b/drivers/usb/cdns3/gadget.h
@@ -1072,7 +1072,7 @@
#define TRB_TDL_SS_SIZE_GET(p) (((p) & GENMASK(23, 17)) >> 17)
/* transfer_len bitmasks - bits 31:24 */
-#define TRB_BURST_LEN(p) (((p) << 24) & GENMASK(31, 24))
+#define TRB_BURST_LEN(p) ((unsigned int)((p) << 24) & GENMASK(31, 24))
#define TRB_BURST_LEN_GET(p) (((p) & GENMASK(31, 24)) >> 24)
/* Data buffer pointer bitmasks*/
@@ -1159,6 +1159,7 @@
#define EP_QUIRK_EXTRA_BUF_DET BIT(12)
#define EP_QUIRK_EXTRA_BUF_EN BIT(13)
#define EP_TDLCHK_EN BIT(15)
+#define EP_CONFIGURED BIT(16)
u32 flags;
struct cdns3_request *descmis_req;
@@ -1360,7 +1361,7 @@
int cdns3_init_ep0(struct cdns3_device *priv_dev,
struct cdns3_endpoint *priv_ep);
void cdns3_ep0_config(struct cdns3_device *priv_dev);
-void cdns3_ep_config(struct cdns3_endpoint *priv_ep);
+int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable);
void cdns3_check_ep0_interrupt_proceed(struct cdns3_device *priv_dev, int dir);
int __cdns3_gadget_wakeup(struct cdns3_device *priv_dev);
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 30ef946..f52f1bc 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -508,6 +508,7 @@
"%s - cooling babbling device\n", __func__);
usb_mark_last_busy(acm->dev);
set_bit(rb->index, &acm->urbs_in_error_delay);
+ set_bit(ACM_ERROR_DELAY, &acm->flags);
cooldown = true;
break;
default:
@@ -533,7 +534,7 @@
if (stopped || stalled || cooldown) {
if (stalled)
- schedule_work(&acm->work);
+ schedule_delayed_work(&acm->dwork, 0);
else if (cooldown)
schedule_delayed_work(&acm->dwork, HZ / 2);
return;
@@ -563,13 +564,13 @@
acm_write_done(acm, wb);
spin_unlock_irqrestore(&acm->write_lock, flags);
set_bit(EVENT_TTY_WAKEUP, &acm->flags);
- schedule_work(&acm->work);
+ schedule_delayed_work(&acm->dwork, 0);
}
static void acm_softint(struct work_struct *work)
{
int i;
- struct acm *acm = container_of(work, struct acm, work);
+ struct acm *acm = container_of(work, struct acm, dwork.work);
if (test_bit(EVENT_RX_STALL, &acm->flags)) {
smp_mb(); /* against acm_suspend() */
@@ -585,7 +586,7 @@
if (test_and_clear_bit(ACM_ERROR_DELAY, &acm->flags)) {
for (i = 0; i < acm->rx_buflimit; i++)
if (test_and_clear_bit(i, &acm->urbs_in_error_delay))
- acm_submit_read_urb(acm, i, GFP_NOIO);
+ acm_submit_read_urb(acm, i, GFP_KERNEL);
}
if (test_and_clear_bit(EVENT_TTY_WAKEUP, &acm->flags))
@@ -1351,7 +1352,6 @@
acm->ctrlsize = ctrlsize;
acm->readsize = readsize;
acm->rx_buflimit = num_rx_buf;
- INIT_WORK(&acm->work, acm_softint);
INIT_DELAYED_WORK(&acm->dwork, acm_softint);
init_waitqueue_head(&acm->wioctl);
spin_lock_init(&acm->write_lock);
@@ -1561,7 +1561,6 @@
}
acm_kill_urbs(acm);
- cancel_work_sync(&acm->work);
cancel_delayed_work_sync(&acm->dwork);
tty_unregister_device(acm_tty_driver, acm->minor);
@@ -1604,7 +1603,6 @@
return 0;
acm_kill_urbs(acm);
- cancel_work_sync(&acm->work);
cancel_delayed_work_sync(&acm->dwork);
acm->urbs_in_error_delay = 0;
@@ -1695,6 +1693,15 @@
{ USB_DEVICE(0x0870, 0x0001), /* Metricom GS Modem */
.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
},
+ { USB_DEVICE(0x045b, 0x023c), /* Renesas USB Download mode */
+ .driver_info = DISABLE_ECHO, /* Don't echo banner */
+ },
+ { USB_DEVICE(0x045b, 0x0248), /* Renesas USB Download mode */
+ .driver_info = DISABLE_ECHO, /* Don't echo banner */
+ },
+ { USB_DEVICE(0x045b, 0x024D), /* Renesas USB Download mode */
+ .driver_info = DISABLE_ECHO, /* Don't echo banner */
+ },
{ USB_DEVICE(0x0e8d, 0x0003), /* FIREFLY, MediaTek Inc; andrey.arapov@gmail.com */
.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
},
diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h
index 9dce179..8aef5eb 100644
--- a/drivers/usb/class/cdc-acm.h
+++ b/drivers/usb/class/cdc-acm.h
@@ -112,8 +112,7 @@
# define ACM_ERROR_DELAY 3
unsigned long urbs_in_error_delay; /* these need to be restarted after a delay */
struct usb_cdc_line_coding line; /* bits, stop, parity */
- struct work_struct work; /* work queue entry for various purposes*/
- struct delayed_work dwork; /* for cool downs needed in error recovery */
+ struct delayed_work dwork; /* work queue entry for various purposes */
unsigned int ctrlin; /* input control lines (DCD, DSR, RI, break, overruns) */
unsigned int ctrlout; /* output control lines (DTR, RTS) */
struct async_icount iocount; /* counters for control line changes */
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 98b7449..4dfa44d 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -839,6 +839,22 @@
return NULL;
}
+bool usb_driver_applicable(struct usb_device *udev,
+ struct usb_device_driver *udrv)
+{
+ if (udrv->id_table && udrv->match)
+ return usb_device_match_id(udev, udrv->id_table) != NULL &&
+ udrv->match(udev);
+
+ if (udrv->id_table)
+ return usb_device_match_id(udev, udrv->id_table) != NULL;
+
+ if (udrv->match)
+ return udrv->match(udev);
+
+ return false;
+}
+
static int usb_device_match(struct device *dev, struct device_driver *drv)
{
/* devices and interfaces are handled separately */
@@ -853,17 +869,14 @@
udev = to_usb_device(dev);
udrv = to_usb_device_driver(drv);
- if (udrv->id_table)
- return usb_device_match_id(udev, udrv->id_table) != NULL;
-
- if (udrv->match)
- return udrv->match(udev);
-
/* If the device driver under consideration does not have a
* id_table or a match function, then let the driver's probe
* function decide.
*/
- return 1;
+ if (!udrv->id_table && !udrv->match)
+ return 1;
+
+ return usb_driver_applicable(udev, udrv);
} else if (is_usb_interface(dev)) {
struct usb_interface *intf;
@@ -941,8 +954,7 @@
return 0;
udev = to_usb_device(dev);
- if (usb_device_match_id(udev, new_udriver->id_table) == NULL &&
- (!new_udriver->match || new_udriver->match(udev) == 0))
+ if (!usb_driver_applicable(udev, new_udriver))
return 0;
ret = device_reprobe(dev);
diff --git a/drivers/usb/core/generic.c b/drivers/usb/core/generic.c
index 22c887f..26f9fb9 100644
--- a/drivers/usb/core/generic.c
+++ b/drivers/usb/core/generic.c
@@ -205,9 +205,7 @@
udrv = to_usb_device_driver(drv);
if (udrv == &usb_generic_driver)
return 0;
- if (usb_device_match_id(udev, udrv->id_table) != NULL)
- return 1;
- return (udrv->match && udrv->match(udev));
+ return usb_driver_applicable(udev, udrv);
}
static bool usb_generic_driver_match(struct usb_device *udev)
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 10574fa..a1e3a03 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -378,6 +378,9 @@
{ USB_DEVICE(0x0926, 0x3333), .driver_info =
USB_QUIRK_CONFIG_INTF_STRINGS },
+ /* Kingston DataTraveler 3.0 */
+ { USB_DEVICE(0x0951, 0x1666), .driver_info = USB_QUIRK_NO_LPM },
+
/* X-Rite/Gretag-Macbeth Eye-One Pro display colorimeter */
{ USB_DEVICE(0x0971, 0x2000), .driver_info = USB_QUIRK_NO_SET_INTF },
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index c893f54..82538da 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -74,6 +74,8 @@
const struct usb_device_id *id);
extern const struct usb_device_id *usb_device_match_id(struct usb_device *udev,
const struct usb_device_id *id);
+extern bool usb_driver_applicable(struct usb_device *udev,
+ struct usb_device_driver *udrv);
extern void usb_forced_unbind_intf(struct usb_interface *intf);
extern void usb_unbind_and_rebind_marked_interfaces(struct usb_device *udev);
diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c
index e282067..5f18acac 100644
--- a/drivers/usb/dwc2/platform.c
+++ b/drivers/usb/dwc2/platform.c
@@ -608,10 +608,13 @@
#endif /* CONFIG_USB_DWC2_PERIPHERAL || CONFIG_USB_DWC2_DUAL_ROLE */
return 0;
+#if IS_ENABLED(CONFIG_USB_DWC2_PERIPHERAL) || \
+ IS_ENABLED(CONFIG_USB_DWC2_DUAL_ROLE)
error_debugfs:
dwc2_debugfs_exit(hsotg);
if (hsotg->hcd_enabled)
dwc2_hcd_remove(hsotg);
+#endif
error_drd:
dwc2_drd_exit(hsotg);
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index bdf0925..841daec 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/**
+/*
* core.c - DesignWare USB3 DRD Controller Core file
*
* Copyright (C) 2010-2011 Texas Instruments Incorporated - https://www.ti.com
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 74323b1..2f95f08 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -1277,7 +1277,7 @@
#define DWC3_DEPEVT_EPCMDCMPLT 0x07
/**
- * struct dwc3_event_depvt - Device Endpoint Events
+ * struct dwc3_event_depevt - Device Endpoint Events
* @one_bit: indicates this is an endpoint event (not used)
* @endpoint_number: number of the endpoint
* @endpoint_event: The event we have:
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 242b621..bae6a70 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -40,6 +40,7 @@
#define PCI_DEVICE_ID_INTEL_TGPLP 0xa0ee
#define PCI_DEVICE_ID_INTEL_TGPH 0x43ee
#define PCI_DEVICE_ID_INTEL_JSP 0x4dee
+#define PCI_DEVICE_ID_INTEL_ADLS 0x7ae1
#define PCI_INTEL_BXT_DSM_GUID "732b85d5-b7a7-4a1b-9ba0-4bbd00ffd511"
#define PCI_INTEL_BXT_FUNC_PMU_PWR 4
@@ -367,6 +368,9 @@
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_JSP),
(kernel_ulong_t) &dwc3_pci_intel_properties, },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ADLS),
+ (kernel_ulong_t) &dwc3_pci_intel_properties, },
+
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_NL_USB),
(kernel_ulong_t) &dwc3_pci_amd_properties, },
{ } /* Terminating Entry */
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index 7be3903..8b668ef 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -1058,10 +1058,11 @@
{
unsigned int direction = !dwc->ep0_expect_in;
+ dwc->delayed_status = false;
+
if (dwc->ep0state != EP0_STATUS_PHASE)
return;
- dwc->delayed_status = false;
__dwc3_ep0_do_control_status(dwc, dwc->eps[direction]);
}
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 05b176c..c6d455f 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1245,7 +1245,7 @@
EXPORT_SYMBOL_GPL(usb_string_id);
/**
- * usb_string_ids() - allocate unused string IDs in batch
+ * usb_string_ids_tab() - allocate unused string IDs in batch
* @cdev: the device whose string descriptor IDs are being allocated
* @str: an array of usb_string objects to assign numbers to
* Context: single threaded during gadget setup
diff --git a/drivers/usb/gadget/legacy/raw_gadget.c b/drivers/usb/gadget/legacy/raw_gadget.c
index e01e366..062dfac 100644
--- a/drivers/usb/gadget/legacy/raw_gadget.c
+++ b/drivers/usb/gadget/legacy/raw_gadget.c
@@ -564,9 +564,12 @@
return -ENODEV;
}
length = min(arg.length, event->length);
- if (copy_to_user((void __user *)value, event, sizeof(*event) + length))
+ if (copy_to_user((void __user *)value, event, sizeof(*event) + length)) {
+ kfree(event);
return -EFAULT;
+ }
+ kfree(event);
return 0;
}
diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c
index de528e3..ad6ff9c 100644
--- a/drivers/usb/gadget/udc/fsl_udc_core.c
+++ b/drivers/usb/gadget/udc/fsl_udc_core.c
@@ -1051,7 +1051,7 @@
u32 bitmask;
struct ep_queue_head *qh;
- if (!_ep || _ep->desc || !(_ep->desc->bEndpointAddress&0xF))
+ if (!_ep || !_ep->desc || !(_ep->desc->bEndpointAddress&0xF))
return -ENODEV;
ep = container_of(_ep, struct fsl_ep, ep);
diff --git a/drivers/usb/gadget/udc/goku_udc.c b/drivers/usb/gadget/udc/goku_udc.c
index 25c1d6a..3e1267d3 100644
--- a/drivers/usb/gadget/udc/goku_udc.c
+++ b/drivers/usb/gadget/udc/goku_udc.c
@@ -1760,6 +1760,7 @@
goto err;
}
+ pci_set_drvdata(pdev, dev);
spin_lock_init(&dev->lock);
dev->pdev = pdev;
dev->gadget.ops = &goku_ops;
@@ -1793,7 +1794,6 @@
}
dev->regs = (struct goku_udc_regs __iomem *) base;
- pci_set_drvdata(pdev, dev);
INFO(dev, "%s\n", driver_desc);
INFO(dev, "version: " DRIVER_VERSION " %s\n", dmastr());
INFO(dev, "irq %d, pci mem %p\n", pdev->irq, base);
diff --git a/drivers/usb/host/ehci-tegra.c b/drivers/usb/host/ehci-tegra.c
index e077b2c..869d9c4 100644
--- a/drivers/usb/host/ehci-tegra.c
+++ b/drivers/usb/host/ehci-tegra.c
@@ -479,8 +479,8 @@
u_phy->otg->host = hcd_to_bus(hcd);
irq = platform_get_irq(pdev, 0);
- if (!irq) {
- err = -ENODEV;
+ if (irq < 0) {
+ err = irq;
goto cleanup_phy;
}
diff --git a/drivers/usb/host/fsl-mph-dr-of.c b/drivers/usb/host/fsl-mph-dr-of.c
index ae8f60f..44a7e58 100644
--- a/drivers/usb/host/fsl-mph-dr-of.c
+++ b/drivers/usb/host/fsl-mph-dr-of.c
@@ -94,10 +94,13 @@
pdev->dev.coherent_dma_mask = ofdev->dev.coherent_dma_mask;
- if (!pdev->dev.dma_mask)
+ if (!pdev->dev.dma_mask) {
pdev->dev.dma_mask = &ofdev->dev.coherent_dma_mask;
- else
- dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
+ } else {
+ retval = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
+ if (retval)
+ goto error;
+ }
retval = platform_device_add_data(pdev, pdata, sizeof(*pdata));
if (retval)
diff --git a/drivers/usb/host/xhci-histb.c b/drivers/usb/host/xhci-histb.c
index 5546e7e..0836985 100644
--- a/drivers/usb/host/xhci-histb.c
+++ b/drivers/usb/host/xhci-histb.c
@@ -240,7 +240,7 @@
/* Initialize dma_mask and coherent_dma_mask to 32-bits */
ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
if (ret)
- return ret;
+ goto disable_pm;
hcd = usb_create_hcd(driver, dev, dev_name(dev));
if (!hcd) {
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index fe405cd..138ba45 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -2252,8 +2252,8 @@
if (!rhub->num_ports)
return;
- rhub->ports = kcalloc_node(rhub->num_ports, sizeof(rhub->ports), flags,
- dev_to_node(dev));
+ rhub->ports = kcalloc_node(rhub->num_ports, sizeof(*rhub->ports),
+ flags, dev_to_node(dev));
for (i = 0; i < HCS_MAX_PORTS(xhci->hcs_params1); i++) {
if (xhci->hw_ports[i].rhub != rhub ||
xhci->hw_ports[i].hcd_portnum == DUPLICATE_ENTRY)
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index c26c06e..bf89172 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -23,6 +23,8 @@
#define SSIC_PORT_CFG2_OFFSET 0x30
#define PROG_DONE (1 << 30)
#define SSIC_PORT_UNUSED (1 << 31)
+#define SPARSE_DISABLE_BIT 17
+#define SPARSE_CNTL_ENABLE 0xC12C
/* Device for a quirk */
#define PCI_VENDOR_ID_FRESCO_LOGIC 0x1b73
@@ -161,6 +163,9 @@
(pdev->device == 0x15e0 || pdev->device == 0x15e1))
xhci->quirks |= XHCI_SNPS_BROKEN_SUSPEND;
+ if (pdev->vendor == PCI_VENDOR_ID_AMD && pdev->device == 0x15e5)
+ xhci->quirks |= XHCI_DISABLE_SPARSE;
+
if (pdev->vendor == PCI_VENDOR_ID_AMD)
xhci->quirks |= XHCI_TRUST_TX_LENGTH;
@@ -498,6 +503,15 @@
readl(reg);
}
+static void xhci_sparse_control_quirk(struct usb_hcd *hcd)
+{
+ u32 reg;
+
+ reg = readl(hcd->regs + SPARSE_CNTL_ENABLE);
+ reg &= ~BIT(SPARSE_DISABLE_BIT);
+ writel(reg, hcd->regs + SPARSE_CNTL_ENABLE);
+}
+
static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup)
{
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
@@ -517,6 +531,9 @@
if (xhci->quirks & XHCI_SSIC_PORT_UNUSED)
xhci_ssic_port_unused_quirk(hcd, true);
+ if (xhci->quirks & XHCI_DISABLE_SPARSE)
+ xhci_sparse_control_quirk(hcd);
+
ret = xhci_suspend(xhci, do_wakeup);
if (ret && (xhci->quirks & XHCI_SSIC_PORT_UNUSED))
xhci_ssic_port_unused_quirk(hcd, false);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 482fe8c..d4a8d0e 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3533,11 +3533,14 @@
xhci_dbg(xhci, "Slot %u ep ctx %u now has streams.\n",
udev->slot_id, ep_index);
vdev->eps[ep_index].ep_state |= EP_HAS_STREAMS;
- xhci_debugfs_create_stream_files(xhci, vdev, ep_index);
}
xhci_free_command(xhci, config_cmd);
spin_unlock_irqrestore(&xhci->lock, flags);
+ for (i = 0; i < num_eps; i++) {
+ ep_index = xhci_get_endpoint_index(&eps[i]->desc);
+ xhci_debugfs_create_stream_files(xhci, vdev, ep_index);
+ }
/* Subtract 1 for stream 0, which drivers can't use */
return num_streams - 1;
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 8be8837..ebb359e 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1877,6 +1877,7 @@
#define XHCI_SNPS_BROKEN_SUSPEND BIT_ULL(35)
#define XHCI_RENESAS_FW_QUIRK BIT_ULL(36)
#define XHCI_SKIP_PHY_INIT BIT_ULL(37)
+#define XHCI_DISABLE_SPARSE BIT_ULL(38)
unsigned int num_active_eps;
unsigned int limit_active_eps;
diff --git a/drivers/usb/misc/apple-mfi-fastcharge.c b/drivers/usb/misc/apple-mfi-fastcharge.c
index b403094..9de0171 100644
--- a/drivers/usb/misc/apple-mfi-fastcharge.c
+++ b/drivers/usb/misc/apple-mfi-fastcharge.c
@@ -120,8 +120,10 @@
dev_dbg(&mfi->udev->dev, "prop: %d\n", psp);
ret = pm_runtime_get_sync(&mfi->udev->dev);
- if (ret < 0)
+ if (ret < 0) {
+ pm_runtime_put_noidle(&mfi->udev->dev);
return ret;
+ }
switch (psp) {
case POWER_SUPPLY_PROP_CHARGE_TYPE:
@@ -163,17 +165,23 @@
.property_is_writeable = apple_mfi_fc_property_is_writeable
};
+static bool mfi_fc_match(struct usb_device *udev)
+{
+ int idProduct;
+
+ idProduct = le16_to_cpu(udev->descriptor.idProduct);
+ /* See comment above mfi_fc_id_table[] */
+ return (idProduct >= 0x1200 && idProduct <= 0x12ff);
+}
+
static int mfi_fc_probe(struct usb_device *udev)
{
struct power_supply_config battery_cfg = {};
struct mfi_device *mfi = NULL;
- int err, idProduct;
+ int err;
- idProduct = le16_to_cpu(udev->descriptor.idProduct);
- /* See comment above mfi_fc_id_table[] */
- if (idProduct < 0x1200 || idProduct > 0x12ff) {
+ if (!mfi_fc_match(udev))
return -ENODEV;
- }
mfi = kzalloc(sizeof(struct mfi_device), GFP_KERNEL);
if (!mfi) {
@@ -220,6 +228,7 @@
.probe = mfi_fc_probe,
.disconnect = mfi_fc_disconnect,
.id_table = mfi_fc_id_table,
+ .match = mfi_fc_match,
.generic_subclass = 1,
};
diff --git a/drivers/usb/mtu3/mtu3_gadget.c b/drivers/usb/mtu3/mtu3_gadget.c
index 1de5c9a..38f17d6 100644
--- a/drivers/usb/mtu3/mtu3_gadget.c
+++ b/drivers/usb/mtu3/mtu3_gadget.c
@@ -564,6 +564,7 @@
spin_unlock_irqrestore(&mtu->lock, flags);
+ synchronize_irq(mtu->irq);
return 0;
}
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index 30085b2..5892f3c 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -429,10 +429,12 @@
struct platform_device *parent = to_platform_device(dev->parent);
const struct dsps_musb_wrapper *wrp = glue->wrp;
void __iomem *reg_base;
+ struct resource *r;
u32 rev, val;
int ret;
- reg_base = devm_platform_ioremap_resource_byname(parent, "control");
+ r = platform_get_resource_byname(parent, IORESOURCE_MEM, "control");
+ reg_base = devm_ioremap_resource(dev, r);
if (IS_ERR(reg_base))
return PTR_ERR(reg_base);
musb->ctrl_base = reg_base;
diff --git a/drivers/usb/serial/cyberjack.c b/drivers/usb/serial/cyberjack.c
index 8219706..2e40908 100644
--- a/drivers/usb/serial/cyberjack.c
+++ b/drivers/usb/serial/cyberjack.c
@@ -357,11 +357,12 @@
struct device *dev = &port->dev;
int status = urb->status;
unsigned long flags;
+ bool resubmitted = false;
- set_bit(0, &port->write_urbs_free);
if (status) {
dev_dbg(dev, "%s - nonzero write bulk status received: %d\n",
__func__, status);
+ set_bit(0, &port->write_urbs_free);
return;
}
@@ -394,6 +395,8 @@
goto exit;
}
+ resubmitted = true;
+
dev_dbg(dev, "%s - priv->wrsent=%d\n", __func__, priv->wrsent);
dev_dbg(dev, "%s - priv->wrfilled=%d\n", __func__, priv->wrfilled);
@@ -410,6 +413,8 @@
exit:
spin_unlock_irqrestore(&priv->lock, flags);
+ if (!resubmitted)
+ set_bit(0, &port->write_urbs_free);
usb_serial_port_softint(port);
}
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 2a3bfd6..54ca85c 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -250,6 +250,7 @@
#define QUECTEL_PRODUCT_EP06 0x0306
#define QUECTEL_PRODUCT_EM12 0x0512
#define QUECTEL_PRODUCT_RM500Q 0x0800
+#define QUECTEL_PRODUCT_EC200T 0x6026
#define CMOTECH_VENDOR_ID 0x16d8
#define CMOTECH_PRODUCT_6001 0x6001
@@ -1117,6 +1118,7 @@
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x10),
.driver_info = ZLP },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) },
{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
@@ -1189,6 +1191,8 @@
.driver_info = NCTRL(0) | RSVD(1) },
{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1054, 0xff), /* Telit FT980-KS */
.driver_info = NCTRL(2) | RSVD(3) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1055, 0xff), /* Telit FN980 (PCIe) */
+ .driver_info = NCTRL(0) | RSVD(1) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
.driver_info = NCTRL(0) | RSVD(1) | RSVD(3) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),
@@ -1201,6 +1205,8 @@
.driver_info = NCTRL(0) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
.driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1203, 0xff), /* Telit LE910Cx (RNDIS) */
+ .driver_info = NCTRL(2) | RSVD(3) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4),
.driver_info = NCTRL(0) | RSVD(1) | RSVD(2) | RSVD(3) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920),
@@ -1215,6 +1221,10 @@
{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1213, 0xff) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1214),
.driver_info = NCTRL(0) | RSVD(1) | RSVD(2) | RSVD(3) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1230, 0xff), /* Telit LE910Cx (rmnet) */
+ .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1231, 0xff), /* Telit LE910Cx (RNDIS) */
+ .driver_info = NCTRL(2) | RSVD(3) },
{ USB_DEVICE(TELIT_VENDOR_ID, 0x1260),
.driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
{ USB_DEVICE(TELIT_VENDOR_ID, 0x1261),
diff --git a/drivers/usb/typec/mux.c b/drivers/usb/typec/mux.c
index b069a51..cf720e9 100644
--- a/drivers/usb/typec/mux.c
+++ b/drivers/usb/typec/mux.c
@@ -71,7 +71,7 @@
EXPORT_SYMBOL_GPL(fwnode_typec_switch_get);
/**
- * typec_put_switch - Release USB Type-C orientation switch
+ * typec_switch_put - Release USB Type-C orientation switch
* @sw: USB Type-C orientation switch
*
* Decrement reference count for @sw.
diff --git a/drivers/usb/typec/stusb160x.c b/drivers/usb/typec/stusb160x.c
index ce0bd7b..2a618f0 100644
--- a/drivers/usb/typec/stusb160x.c
+++ b/drivers/usb/typec/stusb160x.c
@@ -544,11 +544,10 @@
*/
ret = fwnode_property_read_string(fwnode, "power-role", &cap_str);
if (!ret) {
- chip->port_type = typec_find_port_power_role(cap_str);
- if (chip->port_type < 0) {
- ret = chip->port_type;
+ ret = typec_find_port_power_role(cap_str);
+ if (ret < 0)
return ret;
- }
+ chip->port_type = ret;
}
chip->capability.type = chip->port_type;
@@ -565,15 +564,13 @@
*/
ret = fwnode_property_read_string(fwnode, "power-opmode", &cap_str);
if (!ret) {
- chip->pwr_opmode = typec_find_pwr_opmode(cap_str);
+ ret = typec_find_pwr_opmode(cap_str);
/* Power delivery not yet supported */
- if (chip->pwr_opmode < 0 ||
- chip->pwr_opmode == TYPEC_PWR_MODE_PD) {
- ret = chip->pwr_opmode < 0 ? chip->pwr_opmode : -EINVAL;
- dev_err(chip->dev, "bad power operation mode: %d\n",
- chip->pwr_opmode);
- return ret;
+ if (ret < 0 || ret == TYPEC_PWR_MODE_PD) {
+ dev_err(chip->dev, "bad power operation mode: %d\n", ret);
+ return -EINVAL;
}
+ chip->pwr_opmode = ret;
}
return 0;
@@ -632,6 +629,7 @@
{ .compatible = "st,stusb1600", .data = &stusb1600_regmap_config},
{},
};
+MODULE_DEVICE_TABLE(of, stusb160x_of_match);
static int stusb160x_probe(struct i2c_client *client)
{
@@ -729,8 +727,8 @@
}
chip->port = typec_register_port(chip->dev, &chip->capability);
- if (!chip->port) {
- ret = -ENODEV;
+ if (IS_ERR(chip->port)) {
+ ret = PTR_ERR(chip->port);
goto all_reg_disable;
}
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 55535c4..a6fae1f 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -2890,6 +2890,9 @@
static void tcpm_detach(struct tcpm_port *port)
{
+ if (tcpm_port_is_disconnected(port))
+ port->hard_reset_count = 0;
+
if (!port->attached)
return;
@@ -2898,9 +2901,6 @@
port->tcpc->set_bist_data(port->tcpc, false);
}
- if (tcpm_port_is_disconnected(port))
- port->hard_reset_count = 0;
-
tcpm_reset_port(port);
}
diff --git a/drivers/usb/typec/ucsi/psy.c b/drivers/usb/typec/ucsi/psy.c
index 26ed0b5..571a51e 100644
--- a/drivers/usb/typec/ucsi/psy.c
+++ b/drivers/usb/typec/ucsi/psy.c
@@ -238,4 +238,13 @@
return;
power_supply_unregister(con->psy);
+ con->psy = NULL;
+}
+
+void ucsi_port_psy_changed(struct ucsi_connector *con)
+{
+ if (IS_ERR_OR_NULL(con->psy))
+ return;
+
+ power_supply_changed(con->psy);
}
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 758b988..51a570d 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -643,8 +643,10 @@
role = !!(con->status.flags & UCSI_CONSTAT_PWR_DIR);
if (con->status.change & UCSI_CONSTAT_POWER_OPMODE_CHANGE ||
- con->status.change & UCSI_CONSTAT_POWER_LEVEL_CHANGE)
+ con->status.change & UCSI_CONSTAT_POWER_LEVEL_CHANGE) {
ucsi_pwr_opmode_change(con);
+ ucsi_port_psy_changed(con);
+ }
if (con->status.change & UCSI_CONSTAT_POWER_DIR_CHANGE) {
typec_set_pwr_role(con->port, role);
@@ -674,6 +676,8 @@
ucsi_register_partner(con);
else
ucsi_unregister_partner(con);
+
+ ucsi_port_psy_changed(con);
}
if (con->status.change & UCSI_CONSTAT_CAM_CHANGE) {
@@ -994,6 +998,7 @@
!!(con->status.flags & UCSI_CONSTAT_PWR_DIR));
ucsi_pwr_opmode_change(con);
ucsi_register_partner(con);
+ ucsi_port_psy_changed(con);
}
if (con->partner) {
diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h
index cba6f77..b7a92f2 100644
--- a/drivers/usb/typec/ucsi/ucsi.h
+++ b/drivers/usb/typec/ucsi/ucsi.h
@@ -340,9 +340,11 @@
#if IS_ENABLED(CONFIG_POWER_SUPPLY)
int ucsi_register_port_psy(struct ucsi_connector *con);
void ucsi_unregister_port_psy(struct ucsi_connector *con);
+void ucsi_port_psy_changed(struct ucsi_connector *con);
#else
static inline int ucsi_register_port_psy(struct ucsi_connector *con) { return 0; }
static inline void ucsi_unregister_port_psy(struct ucsi_connector *con) { }
+static inline void ucsi_port_psy_changed(struct ucsi_connector *con) { }
#endif /* CONFIG_POWER_SUPPLY */
#if IS_ENABLED(CONFIG_TYPEC_DP_ALTMODE)
diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig
index d7d32b6..358f604 100644
--- a/drivers/vdpa/Kconfig
+++ b/drivers/vdpa/Kconfig
@@ -13,6 +13,7 @@
depends on RUNTIME_TESTING_MENU && HAS_DMA
select DMA_OPS
select VHOST_RING
+ select GENERIC_NET_UTILS
default n
help
vDPA networking device simulator which loop TX traffic back
diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index ef1c550..4b61956 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -239,7 +239,6 @@
u64 paend;
struct scatterlist *sg;
struct device *dma = mvdev->mdev->device;
- int ret;
for (map = vhost_iotlb_itree_first(iotlb, mr->start, mr->end - 1);
map; map = vhost_iotlb_itree_next(map, start, mr->end - 1)) {
@@ -277,8 +276,8 @@
done:
mr->log_size = log_entity_size;
mr->nsg = nsg;
- ret = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0);
- if (!ret)
+ err = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0);
+ if (!err)
goto err_map;
err = create_direct_mr(mvdev, mr);
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 2629911..6a90fdb 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -38,6 +38,10 @@
module_param(batch_mapping, int, 0444);
MODULE_PARM_DESC(batch_mapping, "Batched mapping 1 -Enable; 0 - Disable");
+static char *macaddr;
+module_param(macaddr, charp, 0);
+MODULE_PARM_DESC(macaddr, "Ethernet MAC address");
+
struct vdpasim_virtqueue {
struct vringh vring;
struct vringh_kiov iov;
@@ -60,7 +64,8 @@
static u64 vdpasim_features = (1ULL << VIRTIO_F_ANY_LAYOUT) |
(1ULL << VIRTIO_F_VERSION_1) |
- (1ULL << VIRTIO_F_ACCESS_PLATFORM);
+ (1ULL << VIRTIO_F_ACCESS_PLATFORM) |
+ (1ULL << VIRTIO_NET_F_MAC);
/* State of each vdpasim device */
struct vdpasim {
@@ -361,7 +366,9 @@
spin_lock_init(&vdpasim->iommu_lock);
dev = &vdpasim->vdpa.dev;
- dev->coherent_dma_mask = DMA_BIT_MASK(64);
+ dev->dma_mask = &dev->coherent_dma_mask;
+ if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)))
+ goto err_iommu;
set_dma_ops(dev, &vdpasim_dma_ops);
vdpasim->iommu = vhost_iotlb_alloc(2048, 0);
@@ -372,7 +379,15 @@
if (!vdpasim->buffer)
goto err_iommu;
- eth_random_addr(vdpasim->config.mac);
+ if (macaddr) {
+ mac_pton(macaddr, vdpasim->config.mac);
+ if (!is_valid_ether_addr(vdpasim->config.mac)) {
+ ret = -EADDRNOTAVAIL;
+ goto err_iommu;
+ }
+ } else {
+ eth_random_addr(vdpasim->config.mac);
+ }
vringh_set_iotlb(&vdpasim->vqs[0].vring, vdpasim->iommu);
vringh_set_iotlb(&vdpasim->vqs[1].vring, vdpasim->iommu);
@@ -574,6 +589,16 @@
return vdpasim->generation;
}
+static struct vdpa_iova_range vdpasim_get_iova_range(struct vdpa_device *vdpa)
+{
+ struct vdpa_iova_range range = {
+ .first = 0ULL,
+ .last = ULLONG_MAX,
+ };
+
+ return range;
+}
+
static int vdpasim_set_map(struct vdpa_device *vdpa,
struct vhost_iotlb *iotlb)
{
@@ -657,6 +682,7 @@
.get_config = vdpasim_get_config,
.set_config = vdpasim_set_config,
.get_generation = vdpasim_get_generation,
+ .get_iova_range = vdpasim_get_iova_range,
.dma_map = vdpasim_dma_map,
.dma_unmap = vdpasim_dma_unmap,
.free = vdpasim_free,
@@ -683,6 +709,7 @@
.get_config = vdpasim_get_config,
.set_config = vdpasim_set_config,
.get_generation = vdpasim_get_generation,
+ .get_iova_range = vdpasim_get_iova_range,
.set_map = vdpasim_set_map,
.free = vdpasim_free,
};
diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c
index 0113a98..f27e251 100644
--- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c
+++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c
@@ -248,7 +248,9 @@
info.size = vdev->regions[info.index].size;
info.flags = vdev->regions[info.index].flags;
- return copy_to_user((void __user *)arg, &info, minsz);
+ if (copy_to_user((void __user *)arg, &info, minsz))
+ return -EFAULT;
+ return 0;
}
case VFIO_DEVICE_GET_IRQ_INFO:
{
@@ -267,7 +269,9 @@
info.flags = VFIO_IRQ_INFO_EVENTFD;
info.count = 1;
- return copy_to_user((void __user *)arg, &info, minsz);
+ if (copy_to_user((void __user *)arg, &info, minsz))
+ return -EFAULT;
+ return 0;
}
case VFIO_DEVICE_SET_IRQS:
{
@@ -468,7 +472,7 @@
{
struct vfio_fsl_mc_device *vdev = device_data;
struct fsl_mc_device *mc_dev = vdev->mc_dev;
- int index;
+ unsigned int index;
index = vma->vm_pgoff >> (VFIO_FSL_MC_OFFSET_SHIFT - PAGE_SHIFT);
diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
index c80dceb..0d9f300 100644
--- a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
+++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
@@ -13,7 +13,7 @@
#include "linux/fsl/mc.h"
#include "vfio_fsl_mc_private.h"
-int vfio_fsl_mc_irqs_allocate(struct vfio_fsl_mc_device *vdev)
+static int vfio_fsl_mc_irqs_allocate(struct vfio_fsl_mc_device *vdev)
{
struct fsl_mc_device *mc_dev = vdev->mc_dev;
struct vfio_fsl_mc_irq *mc_irq;
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index fbd2b34..e619017 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -385,7 +385,7 @@
pdev->vendor == PCI_VENDOR_ID_INTEL &&
IS_ENABLED(CONFIG_VFIO_PCI_IGD)) {
ret = vfio_pci_igd_init(vdev);
- if (ret) {
+ if (ret && ret != -ENODEV) {
pci_warn(pdev, "Failed to setup Intel IGD regions\n");
goto disable_exit;
}
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 9e353c4..a0b5fc8 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -356,34 +356,60 @@
return done;
}
-static int vfio_pci_ioeventfd_handler(void *opaque, void *unused)
+static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd,
+ bool test_mem)
{
- struct vfio_pci_ioeventfd *ioeventfd = opaque;
-
switch (ioeventfd->count) {
case 1:
- vfio_pci_iowrite8(ioeventfd->vdev, ioeventfd->test_mem,
+ vfio_pci_iowrite8(ioeventfd->vdev, test_mem,
ioeventfd->data, ioeventfd->addr);
break;
case 2:
- vfio_pci_iowrite16(ioeventfd->vdev, ioeventfd->test_mem,
+ vfio_pci_iowrite16(ioeventfd->vdev, test_mem,
ioeventfd->data, ioeventfd->addr);
break;
case 4:
- vfio_pci_iowrite32(ioeventfd->vdev, ioeventfd->test_mem,
+ vfio_pci_iowrite32(ioeventfd->vdev, test_mem,
ioeventfd->data, ioeventfd->addr);
break;
#ifdef iowrite64
case 8:
- vfio_pci_iowrite64(ioeventfd->vdev, ioeventfd->test_mem,
+ vfio_pci_iowrite64(ioeventfd->vdev, test_mem,
ioeventfd->data, ioeventfd->addr);
break;
#endif
}
+}
+
+static int vfio_pci_ioeventfd_handler(void *opaque, void *unused)
+{
+ struct vfio_pci_ioeventfd *ioeventfd = opaque;
+ struct vfio_pci_device *vdev = ioeventfd->vdev;
+
+ if (ioeventfd->test_mem) {
+ if (!down_read_trylock(&vdev->memory_lock))
+ return 1; /* Lock contended, use thread */
+ if (!__vfio_pci_memory_enabled(vdev)) {
+ up_read(&vdev->memory_lock);
+ return 0;
+ }
+ }
+
+ vfio_pci_ioeventfd_do_write(ioeventfd, false);
+
+ if (ioeventfd->test_mem)
+ up_read(&vdev->memory_lock);
return 0;
}
+static void vfio_pci_ioeventfd_thread(void *opaque, void *unused)
+{
+ struct vfio_pci_ioeventfd *ioeventfd = opaque;
+
+ vfio_pci_ioeventfd_do_write(ioeventfd, ioeventfd->test_mem);
+}
+
long vfio_pci_ioeventfd(struct vfio_pci_device *vdev, loff_t offset,
uint64_t data, int count, int fd)
{
@@ -457,7 +483,8 @@
ioeventfd->test_mem = vdev->pdev->resource[bar].flags & IORESOURCE_MEM;
ret = vfio_virqfd_enable(ioeventfd, vfio_pci_ioeventfd_handler,
- NULL, NULL, &ioeventfd->virqfd, fd);
+ vfio_pci_ioeventfd_thread, NULL,
+ &ioeventfd->virqfd, fd);
if (ret) {
kfree(ioeventfd);
goto out_unlock;
diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c
index c0771a9..fb4b385 100644
--- a/drivers/vfio/platform/vfio_platform_common.c
+++ b/drivers/vfio/platform/vfio_platform_common.c
@@ -267,7 +267,7 @@
ret = pm_runtime_get_sync(vdev->device);
if (ret < 0)
- goto err_pm;
+ goto err_rst;
ret = vfio_platform_call_reset(vdev, &extra_dbg);
if (ret && vdev->reset_required) {
@@ -284,7 +284,6 @@
err_rst:
pm_runtime_put(vdev->device);
-err_pm:
vfio_platform_irq_cleanup(vdev);
err_irq:
vfio_platform_regions_cleanup(vdev);
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index bb2684c..67e8276 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -1993,6 +1993,7 @@
list_splice_tail(iova_copy, iova);
}
+
static int vfio_iommu_type1_attach_group(void *iommu_data,
struct iommu_group *iommu_group)
{
@@ -2009,18 +2010,10 @@
mutex_lock(&iommu->lock);
- list_for_each_entry(d, &iommu->domain_list, next) {
- if (find_iommu_group(d, iommu_group)) {
- mutex_unlock(&iommu->lock);
- return -EINVAL;
- }
- }
-
- if (iommu->external_domain) {
- if (find_iommu_group(iommu->external_domain, iommu_group)) {
- mutex_unlock(&iommu->lock);
- return -EINVAL;
- }
+ /* Check for duplicates */
+ if (vfio_iommu_find_iommu_group(iommu, iommu_group)) {
+ mutex_unlock(&iommu->lock);
+ return -EINVAL;
}
group = kzalloc(sizeof(*group), GFP_KERNEL);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index b22adf0..f22fce5 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -52,7 +52,6 @@
#define VHOST_SCSI_VERSION "v0.1"
#define VHOST_SCSI_NAMELEN 256
#define VHOST_SCSI_MAX_CDB_SIZE 32
-#define VHOST_SCSI_DEFAULT_TAGS 256
#define VHOST_SCSI_PREALLOC_SGLS 2048
#define VHOST_SCSI_PREALLOC_UPAGES 2048
#define VHOST_SCSI_PREALLOC_PROT_SGLS 2048
@@ -140,6 +139,7 @@
struct se_portal_group se_tpg;
/* Pointer back to vhost_scsi, protected by tv_tpg_mutex */
struct vhost_scsi *vhost_scsi;
+ struct list_head tmf_queue;
};
struct vhost_scsi_tport {
@@ -189,6 +189,9 @@
* Writers must also take dev mutex and flush under it.
*/
int inflight_idx;
+ struct vhost_scsi_cmd *scsi_cmds;
+ struct sbitmap scsi_tags;
+ int max_cmds;
};
struct vhost_scsi {
@@ -209,6 +212,20 @@
int vs_events_nr; /* num of pending events, protected by vq->mutex */
};
+struct vhost_scsi_tmf {
+ struct vhost_work vwork;
+ struct vhost_scsi_tpg *tpg;
+ struct vhost_scsi *vhost;
+ struct vhost_scsi_virtqueue *svq;
+ struct list_head queue_entry;
+
+ struct se_cmd se_cmd;
+ struct vhost_scsi_inflight *inflight;
+ struct iovec resp_iov;
+ int in_iovs;
+ int vq_desc;
+};
+
/*
* Context for processing request and control queue operations.
*/
@@ -320,11 +337,13 @@
return 1;
}
-static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
+static void vhost_scsi_release_cmd_res(struct se_cmd *se_cmd)
{
struct vhost_scsi_cmd *tv_cmd = container_of(se_cmd,
struct vhost_scsi_cmd, tvc_se_cmd);
- struct se_session *se_sess = tv_cmd->tvc_nexus->tvn_se_sess;
+ struct vhost_scsi_virtqueue *svq = container_of(tv_cmd->tvc_vq,
+ struct vhost_scsi_virtqueue, vq);
+ struct vhost_scsi_inflight *inflight = tv_cmd->inflight;
int i;
if (tv_cmd->tvc_sgl_count) {
@@ -336,8 +355,36 @@
put_page(sg_page(&tv_cmd->tvc_prot_sgl[i]));
}
- vhost_scsi_put_inflight(tv_cmd->inflight);
- target_free_tag(se_sess, se_cmd);
+ sbitmap_clear_bit(&svq->scsi_tags, se_cmd->map_tag);
+ vhost_scsi_put_inflight(inflight);
+}
+
+static void vhost_scsi_release_tmf_res(struct vhost_scsi_tmf *tmf)
+{
+ struct vhost_scsi_tpg *tpg = tmf->tpg;
+ struct vhost_scsi_inflight *inflight = tmf->inflight;
+
+ mutex_lock(&tpg->tv_tpg_mutex);
+ list_add_tail(&tpg->tmf_queue, &tmf->queue_entry);
+ mutex_unlock(&tpg->tv_tpg_mutex);
+ vhost_scsi_put_inflight(inflight);
+}
+
+static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
+{
+ if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) {
+ struct vhost_scsi_tmf *tmf = container_of(se_cmd,
+ struct vhost_scsi_tmf, se_cmd);
+
+ vhost_work_queue(&tmf->vhost->dev, &tmf->vwork);
+ } else {
+ struct vhost_scsi_cmd *cmd = container_of(se_cmd,
+ struct vhost_scsi_cmd, tvc_se_cmd);
+ struct vhost_scsi *vs = cmd->tvc_vhost;
+
+ llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list);
+ vhost_work_queue(&vs->dev, &vs->vs_completion_work);
+ }
}
static u32 vhost_scsi_sess_get_index(struct se_session *se_sess)
@@ -362,34 +409,24 @@
return 0;
}
-static void vhost_scsi_complete_cmd(struct vhost_scsi_cmd *cmd)
-{
- struct vhost_scsi *vs = cmd->tvc_vhost;
-
- llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list);
-
- vhost_work_queue(&vs->dev, &vs->vs_completion_work);
-}
-
static int vhost_scsi_queue_data_in(struct se_cmd *se_cmd)
{
- struct vhost_scsi_cmd *cmd = container_of(se_cmd,
- struct vhost_scsi_cmd, tvc_se_cmd);
- vhost_scsi_complete_cmd(cmd);
+ transport_generic_free_cmd(se_cmd, 0);
return 0;
}
static int vhost_scsi_queue_status(struct se_cmd *se_cmd)
{
- struct vhost_scsi_cmd *cmd = container_of(se_cmd,
- struct vhost_scsi_cmd, tvc_se_cmd);
- vhost_scsi_complete_cmd(cmd);
+ transport_generic_free_cmd(se_cmd, 0);
return 0;
}
static void vhost_scsi_queue_tm_rsp(struct se_cmd *se_cmd)
{
- return;
+ struct vhost_scsi_tmf *tmf = container_of(se_cmd, struct vhost_scsi_tmf,
+ se_cmd);
+
+ transport_generic_free_cmd(&tmf->se_cmd, 0);
}
static void vhost_scsi_aborted_task(struct se_cmd *se_cmd)
@@ -429,15 +466,6 @@
return evt;
}
-static void vhost_scsi_free_cmd(struct vhost_scsi_cmd *cmd)
-{
- struct se_cmd *se_cmd = &cmd->tvc_se_cmd;
-
- /* TODO locking against target/backend threads? */
- transport_generic_free_cmd(se_cmd, 0);
-
-}
-
static int vhost_scsi_check_stop_free(struct se_cmd *se_cmd)
{
return target_put_sess_cmd(se_cmd);
@@ -556,7 +584,7 @@
} else
pr_err("Faulted on virtio_scsi_cmd_resp\n");
- vhost_scsi_free_cmd(cmd);
+ vhost_scsi_release_cmd_res(se_cmd);
}
vq = -1;
@@ -566,31 +594,31 @@
}
static struct vhost_scsi_cmd *
-vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
+vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
unsigned char *cdb, u64 scsi_tag, u16 lun, u8 task_attr,
u32 exp_data_len, int data_direction)
{
+ struct vhost_scsi_virtqueue *svq = container_of(vq,
+ struct vhost_scsi_virtqueue, vq);
struct vhost_scsi_cmd *cmd;
struct vhost_scsi_nexus *tv_nexus;
- struct se_session *se_sess;
struct scatterlist *sg, *prot_sg;
struct page **pages;
- int tag, cpu;
+ int tag;
tv_nexus = tpg->tpg_nexus;
if (!tv_nexus) {
pr_err("Unable to locate active struct vhost_scsi_nexus\n");
return ERR_PTR(-EIO);
}
- se_sess = tv_nexus->tvn_se_sess;
- tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
+ tag = sbitmap_get(&svq->scsi_tags, 0, false);
if (tag < 0) {
pr_err("Unable to obtain tag for vhost_scsi_cmd\n");
return ERR_PTR(-ENOMEM);
}
- cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[tag];
+ cmd = &svq->scsi_cmds[tag];
sg = cmd->tvc_sgl;
prot_sg = cmd->tvc_prot_sgl;
pages = cmd->tvc_upages;
@@ -599,7 +627,6 @@
cmd->tvc_prot_sgl = prot_sg;
cmd->tvc_upages = pages;
cmd->tvc_se_cmd.map_tag = tag;
- cmd->tvc_se_cmd.map_cpu = cpu;
cmd->tvc_tag = scsi_tag;
cmd->tvc_lun = lun;
cmd->tvc_task_attr = task_attr;
@@ -907,6 +934,11 @@
return ret;
}
+static u16 vhost_buf_to_lun(u8 *lun_buf)
+{
+ return ((lun_buf[2] << 8) | lun_buf[3]) & 0x3FFF;
+}
+
static void
vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
{
@@ -1045,12 +1077,12 @@
tag = vhost64_to_cpu(vq, v_req_pi.tag);
task_attr = v_req_pi.task_attr;
cdb = &v_req_pi.cdb[0];
- lun = ((v_req_pi.lun[2] << 8) | v_req_pi.lun[3]) & 0x3FFF;
+ lun = vhost_buf_to_lun(v_req_pi.lun);
} else {
tag = vhost64_to_cpu(vq, v_req.tag);
task_attr = v_req.task_attr;
cdb = &v_req.cdb[0];
- lun = ((v_req.lun[2] << 8) | v_req.lun[3]) & 0x3FFF;
+ lun = vhost_buf_to_lun(v_req.lun);
}
/*
* Check that the received CDB size does not exceeded our
@@ -1065,11 +1097,11 @@
scsi_command_size(cdb), VHOST_SCSI_MAX_CDB_SIZE);
goto err;
}
- cmd = vhost_scsi_get_tag(vq, tpg, cdb, tag, lun, task_attr,
+ cmd = vhost_scsi_get_cmd(vq, tpg, cdb, tag, lun, task_attr,
exp_data_len + prot_bytes,
data_direction);
if (IS_ERR(cmd)) {
- vq_err(vq, "vhost_scsi_get_tag failed %ld\n",
+ vq_err(vq, "vhost_scsi_get_cmd failed %ld\n",
PTR_ERR(cmd));
goto err;
}
@@ -1088,7 +1120,7 @@
&prot_iter, exp_data_len,
&data_iter))) {
vq_err(vq, "Failed to map iov to sgl\n");
- vhost_scsi_release_cmd(&cmd->tvc_se_cmd);
+ vhost_scsi_release_cmd_res(&cmd->tvc_se_cmd);
goto err;
}
}
@@ -1124,9 +1156,9 @@
}
static void
-vhost_scsi_send_tmf_reject(struct vhost_scsi *vs,
- struct vhost_virtqueue *vq,
- struct vhost_scsi_ctx *vc)
+vhost_scsi_send_tmf_resp(struct vhost_scsi *vs, struct vhost_virtqueue *vq,
+ int in_iovs, int vq_desc, struct iovec *resp_iov,
+ int tmf_resp_code)
{
struct virtio_scsi_ctrl_tmf_resp rsp;
struct iov_iter iov_iter;
@@ -1134,17 +1166,87 @@
pr_debug("%s\n", __func__);
memset(&rsp, 0, sizeof(rsp));
- rsp.response = VIRTIO_SCSI_S_FUNCTION_REJECTED;
+ rsp.response = tmf_resp_code;
- iov_iter_init(&iov_iter, READ, &vq->iov[vc->out], vc->in, sizeof(rsp));
+ iov_iter_init(&iov_iter, READ, resp_iov, in_iovs, sizeof(rsp));
ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter);
if (likely(ret == sizeof(rsp)))
- vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
+ vhost_add_used_and_signal(&vs->dev, vq, vq_desc, 0);
else
pr_err("Faulted on virtio_scsi_ctrl_tmf_resp\n");
}
+static void vhost_scsi_tmf_resp_work(struct vhost_work *work)
+{
+ struct vhost_scsi_tmf *tmf = container_of(work, struct vhost_scsi_tmf,
+ vwork);
+ int resp_code;
+
+ if (tmf->se_cmd.se_tmr_req->response == TMR_FUNCTION_COMPLETE)
+ resp_code = VIRTIO_SCSI_S_FUNCTION_SUCCEEDED;
+ else
+ resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED;
+
+ vhost_scsi_send_tmf_resp(tmf->vhost, &tmf->svq->vq, tmf->in_iovs,
+ tmf->vq_desc, &tmf->resp_iov, resp_code);
+ vhost_scsi_release_tmf_res(tmf);
+}
+
+static void
+vhost_scsi_handle_tmf(struct vhost_scsi *vs, struct vhost_scsi_tpg *tpg,
+ struct vhost_virtqueue *vq,
+ struct virtio_scsi_ctrl_tmf_req *vtmf,
+ struct vhost_scsi_ctx *vc)
+{
+ struct vhost_scsi_virtqueue *svq = container_of(vq,
+ struct vhost_scsi_virtqueue, vq);
+ struct vhost_scsi_tmf *tmf;
+
+ if (vhost32_to_cpu(vq, vtmf->subtype) !=
+ VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET)
+ goto send_reject;
+
+ if (!tpg->tpg_nexus || !tpg->tpg_nexus->tvn_se_sess) {
+ pr_err("Unable to locate active struct vhost_scsi_nexus for LUN RESET.\n");
+ goto send_reject;
+ }
+
+ mutex_lock(&tpg->tv_tpg_mutex);
+ if (list_empty(&tpg->tmf_queue)) {
+ pr_err("Missing reserve TMF. Could not handle LUN RESET.\n");
+ mutex_unlock(&tpg->tv_tpg_mutex);
+ goto send_reject;
+ }
+
+ tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf,
+ queue_entry);
+ list_del_init(&tmf->queue_entry);
+ mutex_unlock(&tpg->tv_tpg_mutex);
+
+ tmf->tpg = tpg;
+ tmf->vhost = vs;
+ tmf->svq = svq;
+ tmf->resp_iov = vq->iov[vc->out];
+ tmf->vq_desc = vc->head;
+ tmf->in_iovs = vc->in;
+ tmf->inflight = vhost_scsi_get_inflight(vq);
+
+ if (target_submit_tmr(&tmf->se_cmd, tpg->tpg_nexus->tvn_se_sess, NULL,
+ vhost_buf_to_lun(vtmf->lun), NULL,
+ TMR_LUN_RESET, GFP_KERNEL, 0,
+ TARGET_SCF_ACK_KREF) < 0) {
+ vhost_scsi_release_tmf_res(tmf);
+ goto send_reject;
+ }
+
+ return;
+
+send_reject:
+ vhost_scsi_send_tmf_resp(vs, vq, vc->in, vc->head, &vq->iov[vc->out],
+ VIRTIO_SCSI_S_FUNCTION_REJECTED);
+}
+
static void
vhost_scsi_send_an_resp(struct vhost_scsi *vs,
struct vhost_virtqueue *vq,
@@ -1170,6 +1272,7 @@
static void
vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
{
+ struct vhost_scsi_tpg *tpg;
union {
__virtio32 type;
struct virtio_scsi_ctrl_an_req an;
@@ -1251,12 +1354,12 @@
vc.req += typ_size;
vc.req_size -= typ_size;
- ret = vhost_scsi_get_req(vq, &vc, NULL);
+ ret = vhost_scsi_get_req(vq, &vc, &tpg);
if (ret)
goto err;
if (v_req.type == VIRTIO_SCSI_T_TMF)
- vhost_scsi_send_tmf_reject(vs, vq, &vc);
+ vhost_scsi_handle_tmf(vs, tpg, vq, &v_req.tmf, &vc);
else
vhost_scsi_send_an_resp(vs, vq, &vc);
err:
@@ -1373,6 +1476,83 @@
wait_for_completion(&old_inflight[i]->comp);
}
+static void vhost_scsi_destroy_vq_cmds(struct vhost_virtqueue *vq)
+{
+ struct vhost_scsi_virtqueue *svq = container_of(vq,
+ struct vhost_scsi_virtqueue, vq);
+ struct vhost_scsi_cmd *tv_cmd;
+ unsigned int i;
+
+ if (!svq->scsi_cmds)
+ return;
+
+ for (i = 0; i < svq->max_cmds; i++) {
+ tv_cmd = &svq->scsi_cmds[i];
+
+ kfree(tv_cmd->tvc_sgl);
+ kfree(tv_cmd->tvc_prot_sgl);
+ kfree(tv_cmd->tvc_upages);
+ }
+
+ sbitmap_free(&svq->scsi_tags);
+ kfree(svq->scsi_cmds);
+ svq->scsi_cmds = NULL;
+}
+
+static int vhost_scsi_setup_vq_cmds(struct vhost_virtqueue *vq, int max_cmds)
+{
+ struct vhost_scsi_virtqueue *svq = container_of(vq,
+ struct vhost_scsi_virtqueue, vq);
+ struct vhost_scsi_cmd *tv_cmd;
+ unsigned int i;
+
+ if (svq->scsi_cmds)
+ return 0;
+
+ if (sbitmap_init_node(&svq->scsi_tags, max_cmds, -1, GFP_KERNEL,
+ NUMA_NO_NODE))
+ return -ENOMEM;
+ svq->max_cmds = max_cmds;
+
+ svq->scsi_cmds = kcalloc(max_cmds, sizeof(*tv_cmd), GFP_KERNEL);
+ if (!svq->scsi_cmds) {
+ sbitmap_free(&svq->scsi_tags);
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < max_cmds; i++) {
+ tv_cmd = &svq->scsi_cmds[i];
+
+ tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS,
+ sizeof(struct scatterlist),
+ GFP_KERNEL);
+ if (!tv_cmd->tvc_sgl) {
+ pr_err("Unable to allocate tv_cmd->tvc_sgl\n");
+ goto out;
+ }
+
+ tv_cmd->tvc_upages = kcalloc(VHOST_SCSI_PREALLOC_UPAGES,
+ sizeof(struct page *),
+ GFP_KERNEL);
+ if (!tv_cmd->tvc_upages) {
+ pr_err("Unable to allocate tv_cmd->tvc_upages\n");
+ goto out;
+ }
+
+ tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS,
+ sizeof(struct scatterlist),
+ GFP_KERNEL);
+ if (!tv_cmd->tvc_prot_sgl) {
+ pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n");
+ goto out;
+ }
+ }
+ return 0;
+out:
+ vhost_scsi_destroy_vq_cmds(vq);
+ return -ENOMEM;
+}
+
/*
* Called from vhost_scsi_ioctl() context to walk the list of available
* vhost_scsi_tpg with an active struct vhost_scsi_nexus
@@ -1427,10 +1607,9 @@
if (!strcmp(tv_tport->tport_name, t->vhost_wwpn)) {
if (vs->vs_tpg && vs->vs_tpg[tpg->tport_tpgt]) {
- kfree(vs_tpg);
mutex_unlock(&tpg->tv_tpg_mutex);
ret = -EEXIST;
- goto out;
+ goto undepend;
}
/*
* In order to ensure individual vhost-scsi configfs
@@ -1442,9 +1621,8 @@
ret = target_depend_item(&se_tpg->tpg_group.cg_item);
if (ret) {
pr_warn("target_depend_item() failed: %d\n", ret);
- kfree(vs_tpg);
mutex_unlock(&tpg->tv_tpg_mutex);
- goto out;
+ goto undepend;
}
tpg->tv_tpg_vhost_count++;
tpg->vhost_scsi = vs;
@@ -1457,6 +1635,16 @@
if (match) {
memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn,
sizeof(vs->vs_vhost_wwpn));
+
+ for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++) {
+ vq = &vs->vqs[i].vq;
+ if (!vhost_vq_is_setup(vq))
+ continue;
+
+ if (vhost_scsi_setup_vq_cmds(vq, vq->num))
+ goto destroy_vq_cmds;
+ }
+
for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
vq = &vs->vqs[i].vq;
mutex_lock(&vq->mutex);
@@ -1476,7 +1664,22 @@
vhost_scsi_flush(vs);
kfree(vs->vs_tpg);
vs->vs_tpg = vs_tpg;
+ goto out;
+destroy_vq_cmds:
+ for (i--; i >= VHOST_SCSI_VQ_IO; i--) {
+ if (!vhost_vq_get_backend(&vs->vqs[i].vq))
+ vhost_scsi_destroy_vq_cmds(&vs->vqs[i].vq);
+ }
+undepend:
+ for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) {
+ tpg = vs_tpg[i];
+ if (tpg) {
+ tpg->tv_tpg_vhost_count--;
+ target_undepend_item(&tpg->se_tpg.tpg_group.cg_item);
+ }
+ }
+ kfree(vs_tpg);
out:
mutex_unlock(&vs->dev.mutex);
mutex_unlock(&vhost_scsi_mutex);
@@ -1549,6 +1752,12 @@
mutex_lock(&vq->mutex);
vhost_vq_set_backend(vq, NULL);
mutex_unlock(&vq->mutex);
+ /*
+ * Make sure cmds are not running before tearing them
+ * down.
+ */
+ vhost_scsi_flush(vs);
+ vhost_scsi_destroy_vq_cmds(vq);
}
}
/*
@@ -1811,11 +2020,19 @@
{
struct vhost_scsi_tpg *tpg = container_of(se_tpg,
struct vhost_scsi_tpg, se_tpg);
+ struct vhost_scsi_tmf *tmf;
+
+ tmf = kzalloc(sizeof(*tmf), GFP_KERNEL);
+ if (!tmf)
+ return -ENOMEM;
+ INIT_LIST_HEAD(&tmf->queue_entry);
+ vhost_work_init(&tmf->vwork, vhost_scsi_tmf_resp_work);
mutex_lock(&vhost_scsi_mutex);
mutex_lock(&tpg->tv_tpg_mutex);
tpg->tv_tpg_port_count++;
+ list_add_tail(&tmf->queue_entry, &tpg->tmf_queue);
mutex_unlock(&tpg->tv_tpg_mutex);
vhost_scsi_hotplug(tpg, lun);
@@ -1830,11 +2047,16 @@
{
struct vhost_scsi_tpg *tpg = container_of(se_tpg,
struct vhost_scsi_tpg, se_tpg);
+ struct vhost_scsi_tmf *tmf;
mutex_lock(&vhost_scsi_mutex);
mutex_lock(&tpg->tv_tpg_mutex);
tpg->tv_tpg_port_count--;
+ tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf,
+ queue_entry);
+ list_del(&tmf->queue_entry);
+ kfree(tmf);
mutex_unlock(&tpg->tv_tpg_mutex);
vhost_scsi_hotunplug(tpg, lun);
@@ -1842,23 +2064,6 @@
mutex_unlock(&vhost_scsi_mutex);
}
-static void vhost_scsi_free_cmd_map_res(struct se_session *se_sess)
-{
- struct vhost_scsi_cmd *tv_cmd;
- unsigned int i;
-
- if (!se_sess->sess_cmd_map)
- return;
-
- for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) {
- tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i];
-
- kfree(tv_cmd->tvc_sgl);
- kfree(tv_cmd->tvc_prot_sgl);
- kfree(tv_cmd->tvc_upages);
- }
-}
-
static ssize_t vhost_scsi_tpg_attrib_fabric_prot_type_store(
struct config_item *item, const char *page, size_t count)
{
@@ -1898,45 +2103,6 @@
NULL,
};
-static int vhost_scsi_nexus_cb(struct se_portal_group *se_tpg,
- struct se_session *se_sess, void *p)
-{
- struct vhost_scsi_cmd *tv_cmd;
- unsigned int i;
-
- for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) {
- tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i];
-
- tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS,
- sizeof(struct scatterlist),
- GFP_KERNEL);
- if (!tv_cmd->tvc_sgl) {
- pr_err("Unable to allocate tv_cmd->tvc_sgl\n");
- goto out;
- }
-
- tv_cmd->tvc_upages = kcalloc(VHOST_SCSI_PREALLOC_UPAGES,
- sizeof(struct page *),
- GFP_KERNEL);
- if (!tv_cmd->tvc_upages) {
- pr_err("Unable to allocate tv_cmd->tvc_upages\n");
- goto out;
- }
-
- tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS,
- sizeof(struct scatterlist),
- GFP_KERNEL);
- if (!tv_cmd->tvc_prot_sgl) {
- pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n");
- goto out;
- }
- }
- return 0;
-out:
- vhost_scsi_free_cmd_map_res(se_sess);
- return -ENOMEM;
-}
-
static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg,
const char *name)
{
@@ -1960,12 +2126,9 @@
* struct se_node_acl for the vhost_scsi struct se_portal_group with
* the SCSI Initiator port name of the passed configfs group 'name'.
*/
- tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg,
- VHOST_SCSI_DEFAULT_TAGS,
- sizeof(struct vhost_scsi_cmd),
+ tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg, 0, 0,
TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS,
- (unsigned char *)name, tv_nexus,
- vhost_scsi_nexus_cb);
+ (unsigned char *)name, tv_nexus, NULL);
if (IS_ERR(tv_nexus->tvn_se_sess)) {
mutex_unlock(&tpg->tv_tpg_mutex);
kfree(tv_nexus);
@@ -2015,7 +2178,6 @@
" %s Initiator Port: %s\n", vhost_scsi_dump_proto_id(tpg->tport),
tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
- vhost_scsi_free_cmd_map_res(se_sess);
/*
* Release the SCSI I_T Nexus to the emulated vhost Target Port
*/
@@ -2155,6 +2317,7 @@
}
mutex_init(&tpg->tv_tpg_mutex);
INIT_LIST_HEAD(&tpg->tv_tpg_list);
+ INIT_LIST_HEAD(&tpg->tmf_queue);
tpg->tport = tport;
tpg->tport_tpgt = tpgt;
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index a2dbc85..2754f30 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -47,6 +47,7 @@
int minor;
struct eventfd_ctx *config_ctx;
int in_batch;
+ struct vdpa_iova_range range;
};
static DEFINE_IDA(vhost_vdpa_ida);
@@ -103,6 +104,9 @@
vq->call_ctx.producer.token = vq->call_ctx.ctx;
vq->call_ctx.producer.irq = irq;
ret = irq_bypass_register_producer(&vq->call_ctx.producer);
+ if (unlikely(ret))
+ dev_info(&v->dev, "vq %u, irq bypass producer (token %p) registration fails, ret = %d\n",
+ qid, vq->call_ctx.producer.token, ret);
}
static void vhost_vdpa_unsetup_vq_irq(struct vhost_vdpa *v, u16 qid)
@@ -337,6 +341,16 @@
return 0;
}
+static long vhost_vdpa_get_iova_range(struct vhost_vdpa *v, u32 __user *argp)
+{
+ struct vhost_vdpa_iova_range range = {
+ .first = v->range.first,
+ .last = v->range.last,
+ };
+
+ return copy_to_user(argp, &range, sizeof(range));
+}
+
static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
void __user *argp)
{
@@ -421,12 +435,11 @@
void __user *argp = (void __user *)arg;
u64 __user *featurep = argp;
u64 features;
- long r;
+ long r = 0;
if (cmd == VHOST_SET_BACKEND_FEATURES) {
- r = copy_from_user(&features, featurep, sizeof(features));
- if (r)
- return r;
+ if (copy_from_user(&features, featurep, sizeof(features)))
+ return -EFAULT;
if (features & ~VHOST_VDPA_BACKEND_FEATURES)
return -EOPNOTSUPP;
vhost_set_backend_features(&v->vdev, features);
@@ -469,7 +482,11 @@
break;
case VHOST_GET_BACKEND_FEATURES:
features = VHOST_VDPA_BACKEND_FEATURES;
- r = copy_to_user(featurep, &features, sizeof(features));
+ if (copy_to_user(featurep, &features, sizeof(features)))
+ r = -EFAULT;
+ break;
+ case VHOST_VDPA_GET_IOVA_RANGE:
+ r = vhost_vdpa_get_iova_range(v, argp);
break;
default:
r = vhost_dev_ioctl(&v->vdev, cmd, argp);
@@ -588,19 +605,25 @@
struct vhost_dev *dev = &v->vdev;
struct vhost_iotlb *iotlb = dev->iotlb;
struct page **page_list;
- struct vm_area_struct **vmas;
+ unsigned long list_size = PAGE_SIZE / sizeof(struct page *);
unsigned int gup_flags = FOLL_LONGTERM;
- unsigned long map_pfn, last_pfn = 0;
- unsigned long npages, lock_limit;
- unsigned long i, nmap = 0;
+ unsigned long npages, cur_base, map_pfn, last_pfn = 0;
+ unsigned long locked, lock_limit, pinned, i;
u64 iova = msg->iova;
- long pinned;
int ret = 0;
+ if (msg->iova < v->range.first ||
+ msg->iova + msg->size - 1 > v->range.last)
+ return -EINVAL;
+
if (vhost_iotlb_itree_first(iotlb, msg->iova,
msg->iova + msg->size - 1))
return -EEXIST;
+ page_list = (struct page **) __get_free_page(GFP_KERNEL);
+ if (!page_list)
+ return -ENOMEM;
+
if (msg->perm & VHOST_ACCESS_WO)
gup_flags |= FOLL_WRITE;
@@ -608,86 +631,61 @@
if (!npages)
return -EINVAL;
- page_list = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL);
- vmas = kvmalloc_array(npages, sizeof(struct vm_area_struct *),
- GFP_KERNEL);
- if (!page_list || !vmas) {
- ret = -ENOMEM;
- goto free;
- }
-
mmap_read_lock(dev->mm);
+ locked = atomic64_add_return(npages, &dev->mm->pinned_vm);
lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
- if (npages + atomic64_read(&dev->mm->pinned_vm) > lock_limit) {
+
+ if (locked > lock_limit) {
ret = -ENOMEM;
- goto unlock;
+ goto out;
}
- pinned = pin_user_pages(msg->uaddr & PAGE_MASK, npages, gup_flags,
- page_list, vmas);
- if (npages != pinned) {
- if (pinned < 0) {
- ret = pinned;
- } else {
- unpin_user_pages(page_list, pinned);
- ret = -ENOMEM;
- }
- goto unlock;
- }
-
+ cur_base = msg->uaddr & PAGE_MASK;
iova &= PAGE_MASK;
- map_pfn = page_to_pfn(page_list[0]);
- /* One more iteration to avoid extra vdpa_map() call out of loop. */
- for (i = 0; i <= npages; i++) {
- unsigned long this_pfn;
- u64 csize;
+ while (npages) {
+ pinned = min_t(unsigned long, npages, list_size);
+ ret = pin_user_pages(cur_base, pinned,
+ gup_flags, page_list, NULL);
+ if (ret != pinned)
+ goto out;
- /* The last chunk may have no valid PFN next to it */
- this_pfn = i < npages ? page_to_pfn(page_list[i]) : -1UL;
+ if (!last_pfn)
+ map_pfn = page_to_pfn(page_list[0]);
- if (last_pfn && (this_pfn == -1UL ||
- this_pfn != last_pfn + 1)) {
- /* Pin a contiguous chunk of memory */
- csize = last_pfn - map_pfn + 1;
- ret = vhost_vdpa_map(v, iova, csize << PAGE_SHIFT,
- map_pfn << PAGE_SHIFT,
- msg->perm);
- if (ret) {
- /*
- * Unpin the rest chunks of memory on the
- * flight with no corresponding vdpa_map()
- * calls having been made yet. On the other
- * hand, vdpa_unmap() in the failure path
- * is in charge of accounting the number of
- * pinned pages for its own.
- * This asymmetrical pattern of accounting
- * is for efficiency to pin all pages at
- * once, while there is no other callsite
- * of vdpa_map() than here above.
- */
- unpin_user_pages(&page_list[nmap],
- npages - nmap);
- goto out;
+ for (i = 0; i < ret; i++) {
+ unsigned long this_pfn = page_to_pfn(page_list[i]);
+ u64 csize;
+
+ if (last_pfn && (this_pfn != last_pfn + 1)) {
+ /* Pin a contiguous chunk of memory */
+ csize = (last_pfn - map_pfn + 1) << PAGE_SHIFT;
+ if (vhost_vdpa_map(v, iova, csize,
+ map_pfn << PAGE_SHIFT,
+ msg->perm))
+ goto out;
+ map_pfn = this_pfn;
+ iova += csize;
}
- atomic64_add(csize, &dev->mm->pinned_vm);
- nmap += csize;
- iova += csize << PAGE_SHIFT;
- map_pfn = this_pfn;
+
+ last_pfn = this_pfn;
}
- last_pfn = this_pfn;
+
+ cur_base += ret << PAGE_SHIFT;
+ npages -= ret;
}
- WARN_ON(nmap != npages);
+ /* Pin the rest chunk */
+ ret = vhost_vdpa_map(v, iova, (last_pfn - map_pfn + 1) << PAGE_SHIFT,
+ map_pfn << PAGE_SHIFT, msg->perm);
out:
- if (ret)
+ if (ret) {
vhost_vdpa_unmap(v, msg->iova, msg->size);
-unlock:
+ atomic64_sub(npages, &dev->mm->pinned_vm);
+ }
mmap_read_unlock(dev->mm);
-free:
- kvfree(vmas);
- kvfree(page_list);
+ free_page((unsigned long)page_list);
return ret;
}
@@ -783,6 +781,27 @@
v->domain = NULL;
}
+static void vhost_vdpa_set_iova_range(struct vhost_vdpa *v)
+{
+ struct vdpa_iova_range *range = &v->range;
+ struct iommu_domain_geometry geo;
+ struct vdpa_device *vdpa = v->vdpa;
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ if (ops->get_iova_range) {
+ *range = ops->get_iova_range(vdpa);
+ } else if (v->domain &&
+ !iommu_domain_get_attr(v->domain,
+ DOMAIN_ATTR_GEOMETRY, &geo) &&
+ geo.force_aperture) {
+ range->first = geo.aperture_start;
+ range->last = geo.aperture_end;
+ } else {
+ range->first = 0;
+ range->last = ULLONG_MAX;
+ }
+}
+
static int vhost_vdpa_open(struct inode *inode, struct file *filep)
{
struct vhost_vdpa *v;
@@ -823,6 +842,8 @@
if (r)
goto err_init_iotlb;
+ vhost_vdpa_set_iova_range(v);
+
filep->private_data = v;
return 0;
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 5c835a2..a262e12 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -304,6 +304,12 @@
memset(&call_ctx->producer, 0x0, sizeof(struct irq_bypass_producer));
}
+bool vhost_vq_is_setup(struct vhost_virtqueue *vq)
+{
+ return vq->avail && vq->desc && vq->used && vhost_vq_access_ok(vq);
+}
+EXPORT_SYMBOL_GPL(vhost_vq_is_setup);
+
static void vhost_vq_reset(struct vhost_dev *dev,
struct vhost_virtqueue *vq)
{
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index e016cd3..b063324 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -190,6 +190,7 @@
struct vhost_log *log, unsigned int *log_num);
void vhost_discard_vq_desc(struct vhost_virtqueue *, int n);
+bool vhost_vq_is_setup(struct vhost_virtqueue *vq);
int vhost_vq_init_access(struct vhost_virtqueue *);
int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len);
int vhost_add_used_n(struct vhost_virtqueue *, struct vring_used_elem *heads,
diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index 02411d8..5bc86f4 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -47,6 +47,7 @@
#include <linux/module.h>
#include <linux/kernel.h>
+#include <linux/vmalloc.h>
#include <linux/init.h>
#include <linux/completion.h>
#include <linux/fb.h>
@@ -1114,8 +1115,15 @@
getmem_done:
remove_conflicting_framebuffers(info->apertures,
KBUILD_MODNAME, false);
- if (!gen2vm)
+
+ if (gen2vm) {
+ /* framebuffer is reallocated, clear screen_info to avoid misuse from kexec */
+ screen_info.lfb_size = 0;
+ screen_info.lfb_base = 0;
+ screen_info.orig_video_isVGA = 0;
+ } else {
pci_dev_put(pdev);
+ }
kfree(info->apertures);
return 0;
diff --git a/drivers/virt/nitro_enclaves/ne_misc_dev.c b/drivers/virt/nitro_enclaves/ne_misc_dev.c
index f06622b..f1964ea 100644
--- a/drivers/virt/nitro_enclaves/ne_misc_dev.c
+++ b/drivers/virt/nitro_enclaves/ne_misc_dev.c
@@ -1505,10 +1505,8 @@
poll_wait(file, &ne_enclave->eventq, wait);
- if (!ne_enclave->has_event)
- return mask;
-
- mask = POLLHUP;
+ if (ne_enclave->has_event)
+ mask |= EPOLLHUP;
return mask;
}
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 71ce1b7..2b385c1 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -395,8 +395,7 @@
*/
trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
- map = swiotlb_tbl_map_single(dev, virt_to_phys(xen_io_tlb_start),
- phys, size, size, dir, attrs);
+ map = swiotlb_tbl_map_single(dev, phys, size, size, dir, attrs);
if (map == (phys_addr_t)DMA_MAPPING_ERROR)
return DMA_MAPPING_ERROR;
diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index 52233fa..887b673 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -589,7 +589,7 @@
*/
void afs_unuse_cell(struct afs_net *net, struct afs_cell *cell, enum afs_cell_trace reason)
{
- unsigned int debug_id = cell->debug_id;
+ unsigned int debug_id;
time64_t now, expire_delay;
int u, a;
@@ -604,6 +604,7 @@
if (cell->vl_servers->nr_servers)
expire_delay = afs_cell_gc_delay;
+ debug_id = cell->debug_id;
u = atomic_read(&cell->ref);
a = atomic_dec_return(&cell->active);
trace_afs_cell(debug_id, u, a, reason);
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 1d2e61e..1bb5b9d 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -281,8 +281,7 @@
if (ret < 0)
goto error;
- set_page_private(req->pages[i], 1);
- SetPagePrivate(req->pages[i]);
+ attach_page_private(req->pages[i], (void *)1);
unlock_page(req->pages[i]);
i++;
} else {
@@ -1975,8 +1974,7 @@
_enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, page->index);
- set_page_private(page, 0);
- ClearPagePrivate(page);
+ detach_page_private(page);
/* The directory will need reloading. */
if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
@@ -2003,8 +2001,6 @@
afs_stat_v(dvnode, n_inval);
/* we clean up only if the entire page is being invalidated */
- if (offset == 0 && length == PAGE_SIZE) {
- set_page_private(page, 0);
- ClearPagePrivate(page);
- }
+ if (offset == 0 && length == PAGE_SIZE)
+ detach_page_private(page);
}
diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c
index b108528..2ffe09a 100644
--- a/fs/afs/dir_edit.c
+++ b/fs/afs/dir_edit.c
@@ -243,10 +243,8 @@
index, gfp);
if (!page)
goto error;
- if (!PagePrivate(page)) {
- set_page_private(page, 1);
- SetPagePrivate(page);
- }
+ if (!PagePrivate(page))
+ attach_page_private(page, (void *)1);
dir_page = kmap(page);
}
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 371d148..85f5adf 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -33,6 +33,7 @@
.write_iter = afs_file_write,
.mmap = afs_file_mmap,
.splice_read = generic_file_splice_read,
+ .splice_write = iter_file_splice_write,
.fsync = afs_fsync,
.lock = afs_lock,
.flock = afs_flock,
@@ -601,6 +602,63 @@
}
/*
+ * Adjust the dirty region of the page on truncation or full invalidation,
+ * getting rid of the markers altogether if the region is entirely invalidated.
+ */
+static void afs_invalidate_dirty(struct page *page, unsigned int offset,
+ unsigned int length)
+{
+ struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
+ unsigned long priv;
+ unsigned int f, t, end = offset + length;
+
+ priv = page_private(page);
+
+ /* we clean up only if the entire page is being invalidated */
+ if (offset == 0 && length == thp_size(page))
+ goto full_invalidate;
+
+ /* If the page was dirtied by page_mkwrite(), the PTE stays writable
+ * and we don't get another notification to tell us to expand it
+ * again.
+ */
+ if (afs_is_page_dirty_mmapped(priv))
+ return;
+
+ /* We may need to shorten the dirty region */
+ f = afs_page_dirty_from(priv);
+ t = afs_page_dirty_to(priv);
+
+ if (t <= offset || f >= end)
+ return; /* Doesn't overlap */
+
+ if (f < offset && t > end)
+ return; /* Splits the dirty region - just absorb it */
+
+ if (f >= offset && t <= end)
+ goto undirty;
+
+ if (f < offset)
+ t = offset;
+ else
+ f = end;
+ if (f == t)
+ goto undirty;
+
+ priv = afs_page_dirty(f, t);
+ set_page_private(page, priv);
+ trace_afs_page_dirty(vnode, tracepoint_string("trunc"), page->index, priv);
+ return;
+
+undirty:
+ trace_afs_page_dirty(vnode, tracepoint_string("undirty"), page->index, priv);
+ clear_page_dirty_for_io(page);
+full_invalidate:
+ priv = (unsigned long)detach_page_private(page);
+ trace_afs_page_dirty(vnode, tracepoint_string("inval"), page->index, priv);
+}
+
+/*
* invalidate part or all of a page
* - release a page and clean up its private data if offset is 0 (indicating
* the entire page)
@@ -608,31 +666,23 @@
static void afs_invalidatepage(struct page *page, unsigned int offset,
unsigned int length)
{
- struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
- unsigned long priv;
-
_enter("{%lu},%u,%u", page->index, offset, length);
BUG_ON(!PageLocked(page));
+#ifdef CONFIG_AFS_FSCACHE
/* we clean up only if the entire page is being invalidated */
if (offset == 0 && length == PAGE_SIZE) {
-#ifdef CONFIG_AFS_FSCACHE
if (PageFsCache(page)) {
struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
fscache_wait_on_page_write(vnode->cache, page);
fscache_uncache_page(vnode->cache, page);
}
+ }
#endif
- if (PagePrivate(page)) {
- priv = page_private(page);
- trace_afs_page_dirty(vnode, tracepoint_string("inval"),
- page->index, priv);
- set_page_private(page, 0);
- ClearPagePrivate(page);
- }
- }
+ if (PagePrivate(page))
+ afs_invalidate_dirty(page, offset, length);
_leave("");
}
@@ -660,11 +710,9 @@
#endif
if (PagePrivate(page)) {
- priv = page_private(page);
+ priv = (unsigned long)detach_page_private(page);
trace_afs_page_dirty(vnode, tracepoint_string("rel"),
page->index, priv);
- set_page_private(page, 0);
- ClearPagePrivate(page);
}
/* indicate that the page can be released */
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 81b0485..14d5d75 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -812,6 +812,7 @@
pgoff_t last; /* last page in mapping to deal with */
unsigned first_offset; /* offset into mapping[first] */
unsigned last_to; /* amount of mapping[last] */
+ bool laundering; /* Laundering page, PG_writeback not set */
} store;
struct {
struct iattr *attr;
@@ -857,6 +858,62 @@
u64 data_version;
} __packed;
+/*
+ * We use page->private to hold the amount of the page that we've written to,
+ * splitting the field into two parts. However, we need to represent a range
+ * 0...PAGE_SIZE, so we reduce the resolution if the size of the page
+ * exceeds what we can encode.
+ */
+#ifdef CONFIG_64BIT
+#define __AFS_PAGE_PRIV_MASK 0x7fffffffUL
+#define __AFS_PAGE_PRIV_SHIFT 32
+#define __AFS_PAGE_PRIV_MMAPPED 0x80000000UL
+#else
+#define __AFS_PAGE_PRIV_MASK 0x7fffUL
+#define __AFS_PAGE_PRIV_SHIFT 16
+#define __AFS_PAGE_PRIV_MMAPPED 0x8000UL
+#endif
+
+static inline unsigned int afs_page_dirty_resolution(void)
+{
+ int shift = PAGE_SHIFT - (__AFS_PAGE_PRIV_SHIFT - 1);
+ return (shift > 0) ? shift : 0;
+}
+
+static inline size_t afs_page_dirty_from(unsigned long priv)
+{
+ unsigned long x = priv & __AFS_PAGE_PRIV_MASK;
+
+ /* The lower bound is inclusive */
+ return x << afs_page_dirty_resolution();
+}
+
+static inline size_t afs_page_dirty_to(unsigned long priv)
+{
+ unsigned long x = (priv >> __AFS_PAGE_PRIV_SHIFT) & __AFS_PAGE_PRIV_MASK;
+
+ /* The upper bound is immediately beyond the region */
+ return (x + 1) << afs_page_dirty_resolution();
+}
+
+static inline unsigned long afs_page_dirty(size_t from, size_t to)
+{
+ unsigned int res = afs_page_dirty_resolution();
+ from >>= res;
+ to = (to - 1) >> res;
+ return (to << __AFS_PAGE_PRIV_SHIFT) | from;
+}
+
+static inline unsigned long afs_page_dirty_mmapped(unsigned long priv)
+{
+ return priv | __AFS_PAGE_PRIV_MMAPPED;
+}
+
+static inline bool afs_is_page_dirty_mmapped(unsigned long priv)
+{
+ return priv & __AFS_PAGE_PRIV_MMAPPED;
+}
+
#include <trace/events/afs.h>
/*****************************************************************************/
diff --git a/fs/afs/write.c b/fs/afs/write.c
index da12abd..c9195fc 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -76,7 +76,7 @@
*/
int afs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
- struct page **pagep, void **fsdata)
+ struct page **_page, void **fsdata)
{
struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
struct page *page;
@@ -90,11 +90,6 @@
_enter("{%llx:%llu},{%lx},%u,%u",
vnode->fid.vid, vnode->fid.vnode, index, from, to);
- /* We want to store information about how much of a page is altered in
- * page->private.
- */
- BUILD_BUG_ON(PAGE_SIZE > 32768 && sizeof(page->private) < 8);
-
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
@@ -110,9 +105,6 @@
SetPageUptodate(page);
}
- /* page won't leak in error case: it eventually gets cleaned off LRU */
- *pagep = page;
-
try_again:
/* See if this page is already partially written in a way that we can
* merge the new write with.
@@ -120,8 +112,8 @@
t = f = 0;
if (PagePrivate(page)) {
priv = page_private(page);
- f = priv & AFS_PRIV_MAX;
- t = priv >> AFS_PRIV_SHIFT;
+ f = afs_page_dirty_from(priv);
+ t = afs_page_dirty_to(priv);
ASSERTCMP(f, <=, t);
}
@@ -138,21 +130,9 @@
if (!test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags) &&
(to < f || from > t))
goto flush_conflicting_write;
- if (from < f)
- f = from;
- if (to > t)
- t = to;
- } else {
- f = from;
- t = to;
}
- priv = (unsigned long)t << AFS_PRIV_SHIFT;
- priv |= f;
- trace_afs_page_dirty(vnode, tracepoint_string("begin"),
- page->index, priv);
- SetPagePrivate(page);
- set_page_private(page, priv);
+ *_page = page;
_leave(" = 0");
return 0;
@@ -162,17 +142,18 @@
flush_conflicting_write:
_debug("flush conflict");
ret = write_one_page(page);
- if (ret < 0) {
- _leave(" = %d", ret);
- return ret;
- }
+ if (ret < 0)
+ goto error;
ret = lock_page_killable(page);
- if (ret < 0) {
- _leave(" = %d", ret);
- return ret;
- }
+ if (ret < 0)
+ goto error;
goto try_again;
+
+error:
+ put_page(page);
+ _leave(" = %d", ret);
+ return ret;
}
/*
@@ -184,12 +165,18 @@
{
struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
struct key *key = afs_file_key(file);
+ unsigned long priv;
+ unsigned int f, from = pos & (PAGE_SIZE - 1);
+ unsigned int t, to = from + copied;
loff_t i_size, maybe_i_size;
- int ret;
+ int ret = 0;
_enter("{%llx:%llu},{%lx}",
vnode->fid.vid, vnode->fid.vnode, page->index);
+ if (copied == 0)
+ goto out;
+
maybe_i_size = pos + copied;
i_size = i_size_read(&vnode->vfs_inode);
@@ -215,6 +202,25 @@
SetPageUptodate(page);
}
+ if (PagePrivate(page)) {
+ priv = page_private(page);
+ f = afs_page_dirty_from(priv);
+ t = afs_page_dirty_to(priv);
+ if (from < f)
+ f = from;
+ if (to > t)
+ t = to;
+ priv = afs_page_dirty(f, t);
+ set_page_private(page, priv);
+ trace_afs_page_dirty(vnode, tracepoint_string("dirty+"),
+ page->index, priv);
+ } else {
+ priv = afs_page_dirty(from, to);
+ attach_page_private(page, (void *)priv);
+ trace_afs_page_dirty(vnode, tracepoint_string("dirty"),
+ page->index, priv);
+ }
+
set_page_dirty(page);
if (PageDirty(page))
_debug("dirtied");
@@ -334,10 +340,9 @@
ASSERTCMP(pv.nr, ==, count);
for (loop = 0; loop < count; loop++) {
- priv = page_private(pv.pages[loop]);
+ priv = (unsigned long)detach_page_private(pv.pages[loop]);
trace_afs_page_dirty(vnode, tracepoint_string("clear"),
pv.pages[loop]->index, priv);
- set_page_private(pv.pages[loop], 0);
end_page_writeback(pv.pages[loop]);
}
first += count;
@@ -396,7 +401,8 @@
op->ctime = op->file[0].scb.status.mtime_client;
afs_vnode_commit_status(op, &op->file[0]);
if (op->error == 0) {
- afs_pages_written_back(vnode, op->store.first, op->store.last);
+ if (!op->store.laundering)
+ afs_pages_written_back(vnode, op->store.first, op->store.last);
afs_stat_v(vnode, n_stores);
atomic_long_add((op->store.last * PAGE_SIZE + op->store.last_to) -
(op->store.first * PAGE_SIZE + op->store.first_offset),
@@ -415,7 +421,7 @@
*/
static int afs_store_data(struct address_space *mapping,
pgoff_t first, pgoff_t last,
- unsigned offset, unsigned to)
+ unsigned offset, unsigned to, bool laundering)
{
struct afs_vnode *vnode = AFS_FS_I(mapping->host);
struct afs_operation *op;
@@ -448,6 +454,7 @@
op->store.last = last;
op->store.first_offset = offset;
op->store.last_to = to;
+ op->store.laundering = laundering;
op->mtime = vnode->vfs_inode.i_mtime;
op->flags |= AFS_OPERATION_UNINTR;
op->ops = &afs_store_data_operation;
@@ -509,8 +516,8 @@
*/
start = primary_page->index;
priv = page_private(primary_page);
- offset = priv & AFS_PRIV_MAX;
- to = priv >> AFS_PRIV_SHIFT;
+ offset = afs_page_dirty_from(priv);
+ to = afs_page_dirty_to(priv);
trace_afs_page_dirty(vnode, tracepoint_string("store"),
primary_page->index, priv);
@@ -555,8 +562,8 @@
}
priv = page_private(page);
- f = priv & AFS_PRIV_MAX;
- t = priv >> AFS_PRIV_SHIFT;
+ f = afs_page_dirty_from(priv);
+ t = afs_page_dirty_to(priv);
if (f != 0 &&
!test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags)) {
unlock_page(page);
@@ -601,7 +608,7 @@
if (end > i_size)
to = i_size & ~PAGE_MASK;
- ret = afs_store_data(mapping, first, last, offset, to);
+ ret = afs_store_data(mapping, first, last, offset, to, false);
switch (ret) {
case 0:
ret = count;
@@ -857,12 +864,14 @@
*/
wait_on_page_writeback(vmf->page);
- priv = (unsigned long)PAGE_SIZE << AFS_PRIV_SHIFT; /* To */
- priv |= 0; /* From */
+ priv = afs_page_dirty(0, PAGE_SIZE);
+ priv = afs_page_dirty_mmapped(priv);
trace_afs_page_dirty(vnode, tracepoint_string("mkwrite"),
vmf->page->index, priv);
- SetPagePrivate(vmf->page);
- set_page_private(vmf->page, priv);
+ if (PagePrivate(vmf->page))
+ set_page_private(vmf->page, priv);
+ else
+ attach_page_private(vmf->page, (void *)priv);
file_update_time(file);
sb_end_pagefault(inode->i_sb);
@@ -915,19 +924,18 @@
f = 0;
t = PAGE_SIZE;
if (PagePrivate(page)) {
- f = priv & AFS_PRIV_MAX;
- t = priv >> AFS_PRIV_SHIFT;
+ f = afs_page_dirty_from(priv);
+ t = afs_page_dirty_to(priv);
}
trace_afs_page_dirty(vnode, tracepoint_string("launder"),
page->index, priv);
- ret = afs_store_data(mapping, page->index, page->index, t, f);
+ ret = afs_store_data(mapping, page->index, page->index, t, f, true);
}
+ priv = (unsigned long)detach_page_private(page);
trace_afs_page_dirty(vnode, tracepoint_string("laundered"),
page->index, priv);
- set_page_private(page, 0);
- ClearPagePrivate(page);
#ifdef CONFIG_AFS_FSCACHE
if (PageFsCache(page)) {
diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c
index 84f3c4f..95c573d 100644
--- a/fs/afs/xattr.c
+++ b/fs/afs/xattr.c
@@ -85,7 +85,7 @@
if (acl->size <= size)
memcpy(buffer, acl->data, acl->size);
else
- op->error = -ERANGE;
+ ret = -ERANGE;
}
}
@@ -148,11 +148,6 @@
.set = afs_xattr_set_acl,
};
-static void yfs_acl_put(struct afs_operation *op)
-{
- yfs_free_opaque_acl(op->yacl);
-}
-
static const struct afs_operation_ops yfs_fetch_opaque_acl_operation = {
.issue_yfs_rpc = yfs_fs_fetch_opaque_acl,
.success = afs_acl_success,
@@ -246,7 +241,7 @@
static const struct afs_operation_ops yfs_store_opaque_acl2_operation = {
.issue_yfs_rpc = yfs_fs_store_opaque_acl2,
.success = afs_acl_success,
- .put = yfs_acl_put,
+ .put = afs_acl_put,
};
/*
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 3b1239b..bd787e7 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -1990,6 +1990,7 @@
memcpy(bp, acl->data, acl->size);
if (acl->size != size)
memset((void *)bp + acl->size, 0, size - acl->size);
+ bp += size / sizeof(__be32);
yfs_check_req(call, bp);
trace_afs_make_fs_call(call, &vp->fid);
diff --git a/fs/aio.c b/fs/aio.c
index c45c20d..6a21d89 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1572,7 +1572,7 @@
* we return to userspace.
*/
if (S_ISREG(file_inode(file)->i_mode)) {
- __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
+ sb_start_write(file_inode(file)->i_sb);
__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
}
req->ki_flags |= IOCB_WRITE;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index b6b3d05..fa50e89 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1690,7 +1690,7 @@
struct elf_thread_core_info *next;
struct task_struct *task;
struct elf_prstatus prstatus;
- struct memelfnote notes[0];
+ struct memelfnote notes[];
};
struct elf_note_info {
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index b3268f4..771a036 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -544,7 +544,18 @@
int level = ref->level;
struct btrfs_key search_key = ref->key_for_search;
- root = btrfs_get_fs_root(fs_info, ref->root_id, false);
+ /*
+ * If we're search_commit_root we could possibly be holding locks on
+ * other tree nodes. This happens when qgroups does backref walks when
+ * adding new delayed refs. To deal with this we need to look in cache
+ * for the root, and if we don't find it then we need to search the
+ * tree_root's commit root, thus the btrfs_get_fs_root_commit_root usage
+ * here.
+ */
+ if (path->search_commit_root)
+ root = btrfs_get_fs_root_commit_root(fs_info, path, ref->root_id);
+ else
+ root = btrfs_get_fs_root(fs_info, ref->root_id, false);
if (IS_ERR(root)) {
ret = PTR_ERR(root);
goto out_free;
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index c0f1d68..3ba6f38 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -2024,6 +2024,7 @@
key.offset = 0;
btrfs_release_path(path);
}
+ btrfs_release_path(path);
list_for_each_entry(space_info, &info->space_info, list) {
int i;
diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c
index 7e1549a..bc920af 100644
--- a/fs/btrfs/block-rsv.c
+++ b/fs/btrfs/block-rsv.c
@@ -511,7 +511,8 @@
/*DEFAULT_RATELIMIT_BURST*/ 1);
if (__ratelimit(&_rs))
WARN(1, KERN_DEBUG
- "BTRFS: block rsv returned %d\n", ret);
+ "BTRFS: block rsv %d returned %d\n",
+ block_rsv->type, ret);
}
try_reserve:
ret = btrfs_reserve_metadata_bytes(root, block_rsv, blocksize,
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index aac3d6f..0378933 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3564,6 +3564,8 @@
int btrfs_reada_wait(void *handle);
void btrfs_reada_detach(void *handle);
int btree_readahead_hook(struct extent_buffer *eb, int err);
+void btrfs_reada_remove_dev(struct btrfs_device *dev);
+void btrfs_reada_undo_remove_dev(struct btrfs_device *dev);
static inline int is_fstree(u64 rootid)
{
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 4a0243c..1063853 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -91,6 +91,17 @@
ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0);
if (ret) {
no_valid_dev_replace_entry_found:
+ /*
+ * We don't have a replace item or it's corrupted. If there is
+ * a replace target, fail the mount.
+ */
+ if (btrfs_find_device(fs_info->fs_devices,
+ BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) {
+ btrfs_err(fs_info,
+ "found replace target device without a valid replace item");
+ ret = -EUCLEAN;
+ goto out;
+ }
ret = 0;
dev_replace->replace_state =
BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED;
@@ -143,8 +154,19 @@
case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
- dev_replace->srcdev = NULL;
- dev_replace->tgtdev = NULL;
+ /*
+ * We don't have an active replace item but if there is a
+ * replace target, fail the mount.
+ */
+ if (btrfs_find_device(fs_info->fs_devices,
+ BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) {
+ btrfs_err(fs_info,
+ "replace devid present without an active replace item");
+ ret = -EUCLEAN;
+ } else {
+ dev_replace->srcdev = NULL;
+ dev_replace->tgtdev = NULL;
+ }
break;
case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
@@ -688,6 +710,9 @@
}
btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
+ if (!scrub_ret)
+ btrfs_reada_remove_dev(src_device);
+
/*
* We have to use this loop approach because at this point src_device
* has to be available for transaction commit to complete, yet new
@@ -696,6 +721,7 @@
while (1) {
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
+ btrfs_reada_undo_remove_dev(src_device);
mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
return PTR_ERR(trans);
}
@@ -746,6 +772,7 @@
up_write(&dev_replace->rwsem);
mutex_unlock(&fs_info->chunk_mutex);
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+ btrfs_reada_undo_remove_dev(src_device);
btrfs_rm_dev_replace_blocked(fs_info);
if (tgt_device)
btrfs_destroy_dev_replace_tgtdev(tgt_device);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8e34386..af97ddc 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1281,32 +1281,26 @@
return 0;
}
-struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
- struct btrfs_key *key)
+static struct btrfs_root *read_tree_root_path(struct btrfs_root *tree_root,
+ struct btrfs_path *path,
+ struct btrfs_key *key)
{
struct btrfs_root *root;
struct btrfs_fs_info *fs_info = tree_root->fs_info;
- struct btrfs_path *path;
u64 generation;
int ret;
int level;
- path = btrfs_alloc_path();
- if (!path)
- return ERR_PTR(-ENOMEM);
-
root = btrfs_alloc_root(fs_info, key->objectid, GFP_NOFS);
- if (!root) {
- ret = -ENOMEM;
- goto alloc_fail;
- }
+ if (!root)
+ return ERR_PTR(-ENOMEM);
ret = btrfs_find_root(tree_root, key, path,
&root->root_item, &root->root_key);
if (ret) {
if (ret > 0)
ret = -ENOENT;
- goto find_fail;
+ goto fail;
}
generation = btrfs_root_generation(&root->root_item);
@@ -1317,21 +1311,31 @@
if (IS_ERR(root->node)) {
ret = PTR_ERR(root->node);
root->node = NULL;
- goto find_fail;
+ goto fail;
} else if (!btrfs_buffer_uptodate(root->node, generation, 0)) {
ret = -EIO;
- goto find_fail;
+ goto fail;
}
root->commit_root = btrfs_root_node(root);
-out:
- btrfs_free_path(path);
return root;
-
-find_fail:
+fail:
btrfs_put_root(root);
-alloc_fail:
- root = ERR_PTR(ret);
- goto out;
+ return ERR_PTR(ret);
+}
+
+struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
+ struct btrfs_key *key)
+{
+ struct btrfs_root *root;
+ struct btrfs_path *path;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return ERR_PTR(-ENOMEM);
+ root = read_tree_root_path(tree_root, path, key);
+ btrfs_free_path(path);
+
+ return root;
}
/*
@@ -1419,6 +1423,31 @@
return root;
}
+static struct btrfs_root *btrfs_get_global_root(struct btrfs_fs_info *fs_info,
+ u64 objectid)
+{
+ if (objectid == BTRFS_ROOT_TREE_OBJECTID)
+ return btrfs_grab_root(fs_info->tree_root);
+ if (objectid == BTRFS_EXTENT_TREE_OBJECTID)
+ return btrfs_grab_root(fs_info->extent_root);
+ if (objectid == BTRFS_CHUNK_TREE_OBJECTID)
+ return btrfs_grab_root(fs_info->chunk_root);
+ if (objectid == BTRFS_DEV_TREE_OBJECTID)
+ return btrfs_grab_root(fs_info->dev_root);
+ if (objectid == BTRFS_CSUM_TREE_OBJECTID)
+ return btrfs_grab_root(fs_info->csum_root);
+ if (objectid == BTRFS_QUOTA_TREE_OBJECTID)
+ return btrfs_grab_root(fs_info->quota_root) ?
+ fs_info->quota_root : ERR_PTR(-ENOENT);
+ if (objectid == BTRFS_UUID_TREE_OBJECTID)
+ return btrfs_grab_root(fs_info->uuid_root) ?
+ fs_info->uuid_root : ERR_PTR(-ENOENT);
+ if (objectid == BTRFS_FREE_SPACE_TREE_OBJECTID)
+ return btrfs_grab_root(fs_info->free_space_root) ?
+ fs_info->free_space_root : ERR_PTR(-ENOENT);
+ return NULL;
+}
+
int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
struct btrfs_root *root)
{
@@ -1518,25 +1547,9 @@
struct btrfs_key key;
int ret;
- if (objectid == BTRFS_ROOT_TREE_OBJECTID)
- return btrfs_grab_root(fs_info->tree_root);
- if (objectid == BTRFS_EXTENT_TREE_OBJECTID)
- return btrfs_grab_root(fs_info->extent_root);
- if (objectid == BTRFS_CHUNK_TREE_OBJECTID)
- return btrfs_grab_root(fs_info->chunk_root);
- if (objectid == BTRFS_DEV_TREE_OBJECTID)
- return btrfs_grab_root(fs_info->dev_root);
- if (objectid == BTRFS_CSUM_TREE_OBJECTID)
- return btrfs_grab_root(fs_info->csum_root);
- if (objectid == BTRFS_QUOTA_TREE_OBJECTID)
- return btrfs_grab_root(fs_info->quota_root) ?
- fs_info->quota_root : ERR_PTR(-ENOENT);
- if (objectid == BTRFS_UUID_TREE_OBJECTID)
- return btrfs_grab_root(fs_info->uuid_root) ?
- fs_info->uuid_root : ERR_PTR(-ENOENT);
- if (objectid == BTRFS_FREE_SPACE_TREE_OBJECTID)
- return btrfs_grab_root(fs_info->free_space_root) ?
- fs_info->free_space_root : ERR_PTR(-ENOENT);
+ root = btrfs_get_global_root(fs_info, objectid);
+ if (root)
+ return root;
again:
root = btrfs_lookup_fs_root(fs_info, objectid);
if (root) {
@@ -1622,6 +1635,52 @@
}
/*
+ * btrfs_get_fs_root_commit_root - return a root for the given objectid
+ * @fs_info: the fs_info
+ * @objectid: the objectid we need to lookup
+ *
+ * This is exclusively used for backref walking, and exists specifically because
+ * of how qgroups does lookups. Qgroups will do a backref lookup at delayed ref
+ * creation time, which means we may have to read the tree_root in order to look
+ * up a fs root that is not in memory. If the root is not in memory we will
+ * read the tree root commit root and look up the fs root from there. This is a
+ * temporary root, it will not be inserted into the radix tree as it doesn't
+ * have the most uptodate information, it'll simply be discarded once the
+ * backref code is finished using the root.
+ */
+struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info,
+ struct btrfs_path *path,
+ u64 objectid)
+{
+ struct btrfs_root *root;
+ struct btrfs_key key;
+
+ ASSERT(path->search_commit_root && path->skip_locking);
+
+ /*
+ * This can return -ENOENT if we ask for a root that doesn't exist, but
+ * since this is called via the backref walking code we won't be looking
+ * up a root that doesn't exist, unless there's corruption. So if root
+ * != NULL just return it.
+ */
+ root = btrfs_get_global_root(fs_info, objectid);
+ if (root)
+ return root;
+
+ root = btrfs_lookup_fs_root(fs_info, objectid);
+ if (root)
+ return root;
+
+ key.objectid = objectid;
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ key.offset = (u64)-1;
+ root = read_tree_root_path(fs_info->tree_root, path, &key);
+ btrfs_release_path(path);
+
+ return root;
+}
+
+/*
* called by the kthread helper functions to finally call the bio end_io
* functions. This is where read checksum verification actually happens
*/
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index fee69ce..182540b 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -69,6 +69,9 @@
u64 objectid, bool check_ref);
struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
u64 objectid, dev_t anon_dev);
+struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info,
+ struct btrfs_path *path,
+ u64 objectid);
void btrfs_free_fs_info(struct btrfs_fs_info *fs_info);
int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 3b21fee..5fd60b1 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3185,7 +3185,7 @@
struct btrfs_tree_block_info *bi;
if (item_size < sizeof(*ei) + sizeof(*bi)) {
btrfs_crit(info,
-"invalid extent item size for key (%llu, %u, %llu) owner %llu, has %u expect >= %lu",
+"invalid extent item size for key (%llu, %u, %llu) owner %llu, has %u expect >= %zu",
key.objectid, key.type, key.offset,
owner_objectid, item_size,
sizeof(*ei) + sizeof(*bi));
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 0ff6594..87355a3 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -3628,7 +3628,8 @@
inode_lock_shared(inode);
ret = btrfs_direct_IO(iocb, to);
inode_unlock_shared(inode);
- if (ret < 0)
+ if (ret < 0 || !iov_iter_count(to) ||
+ iocb->ki_pos >= i_size_read(file_inode(iocb->ki_filp)))
return ret;
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 936c313..da58c58 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9672,10 +9672,16 @@
* clear_offset by our extent size.
*/
clear_offset += ins.offset;
- btrfs_dec_block_group_reservations(fs_info, ins.objectid);
last_alloc = ins.offset;
trans = insert_prealloc_file_extent(trans, inode, &ins, cur_offset);
+ /*
+ * Now that we inserted the prealloc extent we can finally
+ * decrement the number of reservations in the block group.
+ * If we did it before, we could race with relocation and have
+ * relocation miss the reserved extent, making it fail later.
+ */
+ btrfs_dec_block_group_reservations(fs_info, ins.objectid);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
btrfs_free_reserved_extent(fs_info, ins.objectid,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index ab408a2..69a3841 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1274,6 +1274,7 @@
u64 page_start;
u64 page_end;
u64 page_cnt;
+ u64 start = (u64)start_index << PAGE_SHIFT;
int ret;
int i;
int i_done;
@@ -1290,8 +1291,7 @@
page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1);
ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved,
- start_index << PAGE_SHIFT,
- page_cnt << PAGE_SHIFT);
+ start, page_cnt << PAGE_SHIFT);
if (ret)
return ret;
i_done = 0;
@@ -1380,8 +1380,7 @@
btrfs_mod_outstanding_extents(BTRFS_I(inode), 1);
spin_unlock(&BTRFS_I(inode)->lock);
btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved,
- start_index << PAGE_SHIFT,
- (page_cnt - i_done) << PAGE_SHIFT, true);
+ start, (page_cnt - i_done) << PAGE_SHIFT, true);
}
@@ -1408,8 +1407,7 @@
put_page(pages[i]);
}
btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved,
- start_index << PAGE_SHIFT,
- page_cnt << PAGE_SHIFT, true);
+ start, page_cnt << PAGE_SHIFT, true);
btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT);
extent_changeset_free(data_reserved);
return ret;
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 580899b..77c5474 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1026,6 +1026,10 @@
btrfs_item_key_to_cpu(leaf, &found_key, slot);
if (found_key.type == BTRFS_ROOT_REF_KEY) {
+
+ /* Release locks on tree_root before we access quota_root */
+ btrfs_release_path(path);
+
ret = add_qgroup_item(trans, quota_root,
found_key.offset);
if (ret) {
@@ -1044,6 +1048,20 @@
btrfs_abort_transaction(trans, ret);
goto out_free_path;
}
+ ret = btrfs_search_slot_for_read(tree_root, &found_key,
+ path, 1, 0);
+ if (ret < 0) {
+ btrfs_abort_transaction(trans, ret);
+ goto out_free_path;
+ }
+ if (ret > 0) {
+ /*
+ * Shouldn't happen, but in case it does we
+ * don't need to do the btrfs_next_item, just
+ * continue.
+ */
+ continue;
+ }
}
ret = btrfs_next_item(tree_root, path);
if (ret < 0) {
@@ -3417,24 +3435,20 @@
{
struct rb_node *node;
struct rb_node *next;
- struct ulist_node *entry = NULL;
+ struct ulist_node *entry;
int ret = 0;
node = reserved->range_changed.root.rb_node;
+ if (!node)
+ return 0;
while (node) {
entry = rb_entry(node, struct ulist_node, rb_node);
if (entry->val < start)
node = node->rb_right;
- else if (entry)
- node = node->rb_left;
else
- break;
+ node = node->rb_left;
}
- /* Empty changeset */
- if (!entry)
- return 0;
-
if (entry->val > start && rb_prev(&entry->rb_node))
entry = rb_entry(rb_prev(&entry->rb_node), struct ulist_node,
rb_node);
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 9d4f531..d9a166e 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -421,6 +421,9 @@
if (!dev->bdev)
continue;
+ if (test_bit(BTRFS_DEV_STATE_NO_READA, &dev->dev_state))
+ continue;
+
if (dev_replace_is_ongoing &&
dev == fs_info->dev_replace.tgtdev) {
/*
@@ -445,6 +448,8 @@
}
have_zone = 1;
}
+ if (!have_zone)
+ radix_tree_delete(&fs_info->reada_tree, index);
spin_unlock(&fs_info->reada_lock);
up_read(&fs_info->dev_replace.rwsem);
@@ -1020,3 +1025,45 @@
kref_put(&rc->refcnt, reada_control_release);
}
+
+/*
+ * Before removing a device (device replace or device remove ioctls), call this
+ * function to wait for all existing readahead requests on the device and to
+ * make sure no one queues more readahead requests for the device.
+ *
+ * Must be called without holding neither the device list mutex nor the device
+ * replace semaphore, otherwise it will deadlock.
+ */
+void btrfs_reada_remove_dev(struct btrfs_device *dev)
+{
+ struct btrfs_fs_info *fs_info = dev->fs_info;
+
+ /* Serialize with readahead extent creation at reada_find_extent(). */
+ spin_lock(&fs_info->reada_lock);
+ set_bit(BTRFS_DEV_STATE_NO_READA, &dev->dev_state);
+ spin_unlock(&fs_info->reada_lock);
+
+ /*
+ * There might be readahead requests added to the radix trees which
+ * were not yet added to the readahead work queue. We need to start
+ * them and wait for their completion, otherwise we can end up with
+ * use-after-free problems when dropping the last reference on the
+ * readahead extents and their zones, as they need to access the
+ * device structure.
+ */
+ reada_start_machine(fs_info);
+ btrfs_flush_workqueue(fs_info->readahead_workers);
+}
+
+/*
+ * If when removing a device (device replace or device remove ioctls) an error
+ * happens after calling btrfs_reada_remove_dev(), call this to undo what that
+ * function did. This is safe to call even if btrfs_reada_remove_dev() was not
+ * called before.
+ */
+void btrfs_reada_undo_remove_dev(struct btrfs_device *dev)
+{
+ spin_lock(&dev->fs_info->reada_lock);
+ clear_bit(BTRFS_DEV_STATE_NO_READA, &dev->dev_state);
+ spin_unlock(&dev->fs_info->reada_lock);
+}
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index 7f03dbe..78693d3 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -860,6 +860,7 @@
"dropping a ref for a root that doesn't have a ref on the block");
dump_block_entry(fs_info, be);
dump_ref_action(fs_info, ra);
+ kfree(ref);
kfree(ra);
goto out_unlock;
}
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 3602806..9ba92d8 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1648,6 +1648,7 @@
struct btrfs_root_item *root_item;
struct btrfs_path *path;
struct extent_buffer *leaf;
+ int reserve_level;
int level;
int max_level;
int replaced = 0;
@@ -1696,7 +1697,8 @@
* Thus the needed metadata size is at most root_level * nodesize,
* and * 2 since we have two trees to COW.
*/
- min_reserved = fs_info->nodesize * btrfs_root_level(root_item) * 2;
+ reserve_level = max_t(int, 1, btrfs_root_level(root_item));
+ min_reserved = fs_info->nodesize * reserve_level * 2;
memset(&next_key, 0, sizeof(next_key));
while (1) {
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index cf63f1e..e71e758 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3866,8 +3866,9 @@
if (!is_dev_replace && !readonly &&
!test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) {
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
- btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable",
- rcu_str_deref(dev->name));
+ btrfs_err_in_rcu(fs_info,
+ "scrub on devid %llu: filesystem on %s is not writable",
+ devid, rcu_str_deref(dev->name));
ret = -EROFS;
goto out;
}
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index f0ffd5e..8784b74 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -760,18 +760,36 @@
u64 type;
u64 features;
bool mixed = false;
+ int raid_index;
+ int nparity;
+ int ncopies;
length = btrfs_chunk_length(leaf, chunk);
stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk);
type = btrfs_chunk_type(leaf, chunk);
+ raid_index = btrfs_bg_flags_to_raid_index(type);
+ ncopies = btrfs_raid_array[raid_index].ncopies;
+ nparity = btrfs_raid_array[raid_index].nparity;
if (!num_stripes) {
chunk_err(leaf, chunk, logical,
"invalid chunk num_stripes, have %u", num_stripes);
return -EUCLEAN;
}
+ if (num_stripes < ncopies) {
+ chunk_err(leaf, chunk, logical,
+ "invalid chunk num_stripes < ncopies, have %u < %d",
+ num_stripes, ncopies);
+ return -EUCLEAN;
+ }
+ if (nparity && num_stripes == nparity) {
+ chunk_err(leaf, chunk, logical,
+ "invalid chunk num_stripes == nparity, have %u == %d",
+ num_stripes, nparity);
+ return -EUCLEAN;
+ }
if (!IS_ALIGNED(logical, fs_info->sectorsize)) {
chunk_err(leaf, chunk, logical,
"invalid chunk logical, have %llu should aligned to %u",
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 58b9c41..a6406b3 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -431,7 +431,7 @@
atomic_set(&dev->reada_in_flight, 0);
atomic_set(&dev->dev_stats_ccnt, 0);
- btrfs_device_data_ordered_init(dev);
+ btrfs_device_data_ordered_init(dev, fs_info);
INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
extent_io_tree_init(fs_info, &dev->alloc_state,
@@ -1056,22 +1056,13 @@
continue;
}
- if (device->devid == BTRFS_DEV_REPLACE_DEVID) {
- /*
- * In the first step, keep the device which has
- * the correct fsid and the devid that is used
- * for the dev_replace procedure.
- * In the second step, the dev_replace state is
- * read from the device tree and it is known
- * whether the procedure is really active or
- * not, which means whether this device is
- * used or whether it should be removed.
- */
- if (step == 0 || test_bit(BTRFS_DEV_STATE_REPLACE_TGT,
- &device->dev_state)) {
- continue;
- }
- }
+ /*
+ * We have already validated the presence of BTRFS_DEV_REPLACE_DEVID,
+ * in btrfs_init_dev_replace() so just continue.
+ */
+ if (device->devid == BTRFS_DEV_REPLACE_DEVID)
+ continue;
+
if (device->bdev) {
blkdev_put(device->bdev, device->mode);
device->bdev = NULL;
@@ -1080,9 +1071,6 @@
if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
list_del_init(&device->dev_alloc_list);
clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
- if (!test_bit(BTRFS_DEV_STATE_REPLACE_TGT,
- &device->dev_state))
- fs_devices->rw_devices--;
}
list_del_init(&device->dev_list);
fs_devices->num_devices--;
@@ -2099,6 +2087,8 @@
mutex_unlock(&uuid_mutex);
ret = btrfs_shrink_device(device, 0);
+ if (!ret)
+ btrfs_reada_remove_dev(device);
mutex_lock(&uuid_mutex);
if (ret)
goto error_undo;
@@ -2179,6 +2169,7 @@
return ret;
error_undo:
+ btrfs_reada_undo_remove_dev(device);
if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
mutex_lock(&fs_info->chunk_mutex);
list_add(&device->dev_alloc_list,
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index bf27ac0..232f02b 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -39,10 +39,10 @@
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
#include <linux/seqlock.h>
#define __BTRFS_NEED_DEVICE_DATA_ORDERED
-#define btrfs_device_data_ordered_init(device) \
- seqcount_init(&device->data_seqcount)
+#define btrfs_device_data_ordered_init(device, info) \
+ seqcount_mutex_init(&device->data_seqcount, &info->chunk_mutex)
#else
-#define btrfs_device_data_ordered_init(device) do { } while (0)
+#define btrfs_device_data_ordered_init(device, info) do { } while (0)
#endif
#define BTRFS_DEV_STATE_WRITEABLE (0)
@@ -50,6 +50,7 @@
#define BTRFS_DEV_STATE_MISSING (2)
#define BTRFS_DEV_STATE_REPLACE_TGT (3)
#define BTRFS_DEV_STATE_FLUSH_SENT (4)
+#define BTRFS_DEV_STATE_NO_READA (5)
struct btrfs_device {
struct list_head dev_list; /* device_list_mutex */
@@ -71,7 +72,8 @@
blk_status_t last_flush_error;
#ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED
- seqcount_t data_seqcount;
+ /* A seqcount_t with associated chunk_mutex (for lockdep) */
+ seqcount_mutex_t data_seqcount;
#endif
/* the internal btrfs device id */
@@ -162,11 +164,9 @@
static inline void \
btrfs_device_set_##name(struct btrfs_device *dev, u64 size) \
{ \
- preempt_disable(); \
write_seqcount_begin(&dev->data_seqcount); \
dev->name = size; \
write_seqcount_end(&dev->data_seqcount); \
- preempt_enable(); \
}
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
#define BTRFS_DEVICE_GETSET_FUNCS(name) \
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 3080cda..8bda092 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -121,7 +121,7 @@
_debug("reissue read");
ret = bmapping->a_ops->readpage(NULL, backpage);
if (ret < 0)
- goto unlock_discard;
+ goto discard;
}
/* but the page may have been read before the monitor was installed, so
@@ -138,6 +138,7 @@
unlock_discard:
unlock_page(backpage);
+discard:
spin_lock_irq(&object->work_lock);
list_del(&monitor->op_link);
spin_unlock_irq(&object->work_lock);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 5027bbd..ded4229 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -4074,7 +4074,7 @@
vino.snap, inode);
mutex_lock(&session->s_mutex);
- session->s_seq++;
+ inc_session_sequence(session);
dout(" mds%d seq %lld cap seq %u\n", session->s_mds, session->s_seq,
(unsigned)seq);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 08f1c0c..8f1d750 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -4231,7 +4231,7 @@
dname.len, dname.name);
mutex_lock(&session->s_mutex);
- session->s_seq++;
+ inc_session_sequence(session);
if (!inode) {
dout("handle_lease no inode %llx\n", vino.ino);
@@ -4385,29 +4385,49 @@
bool check_session_state(struct ceph_mds_session *s)
{
- if (s->s_state == CEPH_MDS_SESSION_CLOSING) {
- dout("resending session close request for mds%d\n",
- s->s_mds);
- request_close_session(s);
- return false;
- }
- if (s->s_ttl && time_after(jiffies, s->s_ttl)) {
- if (s->s_state == CEPH_MDS_SESSION_OPEN) {
+ switch (s->s_state) {
+ case CEPH_MDS_SESSION_OPEN:
+ if (s->s_ttl && time_after(jiffies, s->s_ttl)) {
s->s_state = CEPH_MDS_SESSION_HUNG;
pr_info("mds%d hung\n", s->s_mds);
}
- }
- if (s->s_state == CEPH_MDS_SESSION_NEW ||
- s->s_state == CEPH_MDS_SESSION_RESTARTING ||
- s->s_state == CEPH_MDS_SESSION_CLOSED ||
- s->s_state == CEPH_MDS_SESSION_REJECTED)
- /* this mds is failed or recovering, just wait */
+ break;
+ case CEPH_MDS_SESSION_CLOSING:
+ /* Should never reach this when we're unmounting */
+ WARN_ON_ONCE(true);
+ fallthrough;
+ case CEPH_MDS_SESSION_NEW:
+ case CEPH_MDS_SESSION_RESTARTING:
+ case CEPH_MDS_SESSION_CLOSED:
+ case CEPH_MDS_SESSION_REJECTED:
return false;
+ }
return true;
}
/*
+ * If the sequence is incremented while we're waiting on a REQUEST_CLOSE reply,
+ * then we need to retransmit that request.
+ */
+void inc_session_sequence(struct ceph_mds_session *s)
+{
+ lockdep_assert_held(&s->s_mutex);
+
+ s->s_seq++;
+
+ if (s->s_state == CEPH_MDS_SESSION_CLOSING) {
+ int ret;
+
+ dout("resending session close request for mds%d\n", s->s_mds);
+ ret = request_close_session(s);
+ if (ret < 0)
+ pr_err("unable to close session to mds%d: %d\n",
+ s->s_mds, ret);
+ }
+}
+
+/*
* delayed work -- periodically trim expired leases, renew caps with mds
*/
static void schedule_delayed(struct ceph_mds_client *mdsc)
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index cbf8af4..f5adbeb 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -480,6 +480,7 @@
extern const char *ceph_mds_op_name(int op);
extern bool check_session_state(struct ceph_mds_session *s);
+void inc_session_sequence(struct ceph_mds_session *s);
extern struct ceph_mds_session *
__ceph_lookup_mds_session(struct ceph_mds_client *, int mds);
diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index 83cb4f2..9b785f11 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -53,7 +53,7 @@
/* increment msg sequence number */
mutex_lock(&session->s_mutex);
- session->s_seq++;
+ inc_session_sequence(session);
mutex_unlock(&session->s_mutex);
/* lookup inode */
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 0da39c1..b611f82 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -873,7 +873,7 @@
ceph_snap_op_name(op), split, trace_len);
mutex_lock(&session->s_mutex);
- session->s_seq++;
+ inc_session_sequence(session);
mutex_unlock(&session->s_mutex);
down_write(&mdsc->snap_rwsem);
diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c
index 89bffa8..c57bebf 100644
--- a/fs/crypto/inline_crypt.c
+++ b/fs/crypto/inline_crypt.c
@@ -74,7 +74,7 @@
int i;
/* The file must need contents encryption, not filenames encryption */
- if (!fscrypt_needs_contents_encryption(inode))
+ if (!S_ISREG(inode->i_mode))
return 0;
/* The crypto mode must have a blk-crypto counterpart */
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index d3c3e5d..d595abb 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -269,9 +269,7 @@
* New inodes may not have an inode number assigned yet.
* Hashing their inode number is delayed until later.
*/
- if (ci->ci_inode->i_ino == 0)
- WARN_ON(!(ci->ci_inode->i_state & I_CREATING));
- else
+ if (ci->ci_inode->i_ino)
fscrypt_hash_inode_number(ci, mk);
return 0;
}
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index a768a09..686e0ad 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -1127,24 +1127,23 @@
* file will be created in the root of the debugfs filesystem.
* @read_fn: function pointer called to print the seq_file content.
*/
-struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name,
- struct dentry *parent,
- int (*read_fn)(struct seq_file *s,
- void *data))
+void debugfs_create_devm_seqfile(struct device *dev, const char *name,
+ struct dentry *parent,
+ int (*read_fn)(struct seq_file *s, void *data))
{
struct debugfs_devm_entry *entry;
if (IS_ERR(parent))
- return ERR_PTR(-ENOENT);
+ return;
entry = devm_kzalloc(dev, sizeof(*entry), GFP_KERNEL);
if (!entry)
- return ERR_PTR(-ENOMEM);
+ return;
entry->read = read_fn;
entry->dev = dev;
- return debugfs_create_file(name, S_IRUGO, parent, entry,
- &debugfs_devm_entry_ops);
+ debugfs_create_file(name, S_IRUGO, parent, entry,
+ &debugfs_devm_entry_ops);
}
EXPORT_SYMBOL_GPL(debugfs_create_devm_seqfile);
diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index 139d0be..3e21c0e 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -107,11 +107,9 @@
i_gid_write(inode, le32_to_cpu(die->i_gid));
set_nlink(inode, le32_to_cpu(die->i_nlink));
- /* ns timestamp */
- inode->i_mtime.tv_sec = inode->i_ctime.tv_sec =
- le64_to_cpu(die->i_ctime);
- inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec =
- le32_to_cpu(die->i_ctime_nsec);
+ /* extended inode has its own timestamp */
+ inode->i_ctime.tv_sec = le64_to_cpu(die->i_ctime);
+ inode->i_ctime.tv_nsec = le32_to_cpu(die->i_ctime_nsec);
inode->i_size = le64_to_cpu(die->i_size);
@@ -149,11 +147,9 @@
i_gid_write(inode, le16_to_cpu(dic->i_gid));
set_nlink(inode, le16_to_cpu(dic->i_nlink));
- /* use build time to derive all file time */
- inode->i_mtime.tv_sec = inode->i_ctime.tv_sec =
- sbi->build_time;
- inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec =
- sbi->build_time_nsec;
+ /* use build time for compact inodes */
+ inode->i_ctime.tv_sec = sbi->build_time;
+ inode->i_ctime.tv_nsec = sbi->build_time_nsec;
inode->i_size = le32_to_cpu(dic->i_size);
if (erofs_inode_is_data_compressed(vi->datalayout))
@@ -167,6 +163,11 @@
goto err_out;
}
+ inode->i_mtime.tv_sec = inode->i_ctime.tv_sec;
+ inode->i_atime.tv_sec = inode->i_ctime.tv_sec;
+ inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec;
+ inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec;
+
if (!nblks)
/* measure inode.i_blocks as generic filesystems */
inode->i_blocks = roundup(inode->i_size, EROFS_BLKSIZ) >> 9;
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 50912a5..86fd3bf 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1078,8 +1078,11 @@
cond_resched();
goto repeat;
}
- set_page_private(page, (unsigned long)pcl);
- SetPagePrivate(page);
+
+ if (tocache) {
+ set_page_private(page, (unsigned long)pcl);
+ SetPagePrivate(page);
+ }
out: /* the only exit (for tracing and debugging) */
return page;
}
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 5b81f3b..ca50c90 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -669,68 +669,8 @@
};
#ifdef CONFIG_UNICODE
-static int ext4_d_compare(const struct dentry *dentry, unsigned int len,
- const char *str, const struct qstr *name)
-{
- struct qstr qstr = {.name = str, .len = len };
- const struct dentry *parent = READ_ONCE(dentry->d_parent);
- const struct inode *inode = d_inode_rcu(parent);
- char strbuf[DNAME_INLINE_LEN];
-
- if (!inode || !IS_CASEFOLDED(inode) ||
- !EXT4_SB(inode->i_sb)->s_encoding) {
- if (len != name->len)
- return -1;
- return memcmp(str, name->name, len);
- }
-
- /*
- * If the dentry name is stored in-line, then it may be concurrently
- * modified by a rename. If this happens, the VFS will eventually retry
- * the lookup, so it doesn't matter what ->d_compare() returns.
- * However, it's unsafe to call utf8_strncasecmp() with an unstable
- * string. Therefore, we have to copy the name into a temporary buffer.
- */
- if (len <= DNAME_INLINE_LEN - 1) {
- memcpy(strbuf, str, len);
- strbuf[len] = 0;
- qstr.name = strbuf;
- /* prevent compiler from optimizing out the temporary buffer */
- barrier();
- }
-
- return ext4_ci_compare(inode, name, &qstr, false);
-}
-
-static int ext4_d_hash(const struct dentry *dentry, struct qstr *str)
-{
- const struct ext4_sb_info *sbi = EXT4_SB(dentry->d_sb);
- const struct unicode_map *um = sbi->s_encoding;
- const struct inode *inode = d_inode_rcu(dentry);
- unsigned char *norm;
- int len, ret = 0;
-
- if (!inode || !IS_CASEFOLDED(inode) || !um)
- return 0;
-
- norm = kmalloc(PATH_MAX, GFP_ATOMIC);
- if (!norm)
- return -ENOMEM;
-
- len = utf8_casefold(um, str, norm, PATH_MAX);
- if (len < 0) {
- if (ext4_has_strict_mode(sbi))
- ret = -EINVAL;
- goto out;
- }
- str->hash = full_name_hash(dentry, norm, len);
-out:
- kfree(norm);
- return ret;
-}
-
const struct dentry_operations ext4_dentry_ops = {
- .d_hash = ext4_d_hash,
- .d_compare = ext4_d_compare,
+ .d_hash = generic_ci_d_hash,
+ .d_compare = generic_ci_d_compare,
};
#endif
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 254d1c2..bf94294 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1028,9 +1028,6 @@
* protected by sbi->s_fc_lock.
*/
- /* Fast commit subtid when this inode was committed */
- unsigned int i_fc_committed_subtid;
-
/* Start of lblk range that needs to be committed in this fast commit */
ext4_lblk_t i_fc_lblk_start;
@@ -1166,10 +1163,6 @@
#define EXT4_VALID_FS 0x0001 /* Unmounted cleanly */
#define EXT4_ERROR_FS 0x0002 /* Errors detected */
#define EXT4_ORPHAN_FS 0x0004 /* Orphans being recovered */
-#define EXT4_FC_INELIGIBLE 0x0008 /* Fast commit ineligible */
-#define EXT4_FC_COMMITTING 0x0010 /* File system underoing a fast
- * commit.
- */
#define EXT4_FC_REPLAY 0x0020 /* Fast commit replay ongoing */
/*
@@ -1238,13 +1231,13 @@
blocks */
#define EXT4_MOUNT2_HURD_COMPAT 0x00000004 /* Support HURD-castrated
file systems */
-#define EXT4_MOUNT2_DAX_NEVER 0x00000008 /* Do not allow Direct Access */
-#define EXT4_MOUNT2_DAX_INODE 0x00000010 /* For printing options only */
-
#define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM 0x00000008 /* User explicitly
specified journal checksum */
#define EXT4_MOUNT2_JOURNAL_FAST_COMMIT 0x00000010 /* Journal fast commit */
+#define EXT4_MOUNT2_DAX_NEVER 0x00000020 /* Do not allow Direct Access */
+#define EXT4_MOUNT2_DAX_INODE 0x00000040 /* For printing options only */
+
#define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \
~EXT4_MOUNT_##opt
@@ -1426,12 +1419,6 @@
#ifdef __KERNEL__
-/*
- * run-time mount flags
- */
-#define EXT4_MF_MNTDIR_SAMPLED 0x0001
-#define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */
-
#ifdef CONFIG_FS_ENCRYPTION
#define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_policy.policy != NULL)
#else
@@ -1444,14 +1431,6 @@
#define EXT4_ENC_UTF8_12_1 1
/*
- * Flags for ext4_sb_info.s_encoding_flags.
- */
-#define EXT4_ENC_STRICT_MODE_FL (1 << 0)
-
-#define ext4_has_strict_mode(sbi) \
- (sbi->s_encoding_flags & EXT4_ENC_STRICT_MODE_FL)
-
-/*
* fourth extended-fs super-block data in memory
*/
struct ext4_sb_info {
@@ -1474,7 +1453,7 @@
struct buffer_head * __rcu *s_group_desc;
unsigned int s_mount_opt;
unsigned int s_mount_opt2;
- unsigned int s_mount_flags;
+ unsigned long s_mount_flags;
unsigned int s_def_mount_opt;
ext4_fsblk_t s_sb_block;
atomic64_t s_resv_clusters;
@@ -1500,10 +1479,6 @@
struct kobject s_kobj;
struct completion s_kobj_unregister;
struct super_block *s_sb;
-#ifdef CONFIG_UNICODE
- struct unicode_map *s_encoding;
- __u16 s_encoding_flags;
-#endif
/* Journaling */
struct journal_s *s_journal;
@@ -1707,6 +1682,34 @@
})
/*
+ * run-time mount flags
+ */
+enum {
+ EXT4_MF_MNTDIR_SAMPLED,
+ EXT4_MF_FS_ABORTED, /* Fatal error detected */
+ EXT4_MF_FC_INELIGIBLE, /* Fast commit ineligible */
+ EXT4_MF_FC_COMMITTING /* File system underoing a fast
+ * commit.
+ */
+};
+
+static inline void ext4_set_mount_flag(struct super_block *sb, int bit)
+{
+ set_bit(bit, &EXT4_SB(sb)->s_mount_flags);
+}
+
+static inline void ext4_clear_mount_flag(struct super_block *sb, int bit)
+{
+ clear_bit(bit, &EXT4_SB(sb)->s_mount_flags);
+}
+
+static inline int ext4_test_mount_flag(struct super_block *sb, int bit)
+{
+ return test_bit(bit, &EXT4_SB(sb)->s_mount_flags);
+}
+
+
+/*
* Simulate_fail codes
*/
#define EXT4_SIM_BBITMAP_EIO 1
@@ -1875,6 +1878,13 @@
#define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010
#define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020
#define EXT4_FEATURE_COMPAT_SPARSE_SUPER2 0x0200
+/*
+ * The reason why "FAST_COMMIT" is a compat feature is that, FS becomes
+ * incompatible only if fast commit blocks are present in the FS. Since we
+ * clear the journal (and thus the fast commit blocks), we don't mark FS as
+ * incompatible. We also have a JBD2 incompat feature, which gets set when
+ * there are fast commit blocks present in the journal.
+ */
#define EXT4_FEATURE_COMPAT_FAST_COMMIT 0x0400
#define EXT4_FEATURE_COMPAT_STABLE_INODES 0x0800
@@ -2743,12 +2753,16 @@
int ext4_fc_info_show(struct seq_file *seq, void *v);
void ext4_fc_init(struct super_block *sb, journal_t *journal);
void ext4_fc_init_inode(struct inode *inode);
-void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start,
+void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start,
ext4_lblk_t end);
-void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry);
-void ext4_fc_track_link(struct inode *inode, struct dentry *dentry);
-void ext4_fc_track_create(struct inode *inode, struct dentry *dentry);
-void ext4_fc_track_inode(struct inode *inode);
+void __ext4_fc_track_unlink(handle_t *handle, struct inode *inode,
+ struct dentry *dentry);
+void __ext4_fc_track_link(handle_t *handle, struct inode *inode,
+ struct dentry *dentry);
+void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry);
+void ext4_fc_track_link(handle_t *handle, struct dentry *dentry);
+void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
+void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
void ext4_fc_mark_ineligible(struct super_block *sb, int reason);
void ext4_fc_start_ineligible(struct super_block *sb, int reason);
void ext4_fc_stop_ineligible(struct super_block *sb);
@@ -3464,7 +3478,7 @@
extern int ext4_ci_compare(const struct inode *parent,
const struct qstr *fname,
const struct qstr *entry, bool quick);
-extern int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
+extern int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name,
struct inode *inode);
extern int __ext4_link(struct inode *dir, struct inode *inode,
struct dentry *dentry);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 559100f..17d7096 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -1471,16 +1471,16 @@
}
/*
- * search the closest allocated block to the right for *logical
- * and returns it at @logical + it's physical address at @phys
- * if *logical is the largest allocated block, the function
- * returns 0 at @phys
- * return value contains 0 (success) or error code
+ * Search the closest allocated block to the right for *logical
+ * and returns it at @logical + it's physical address at @phys.
+ * If not exists, return 0 and @phys is set to 0. We will return
+ * 1 which means we found an allocated block and ret_ex is valid.
+ * Or return a (< 0) error code.
*/
static int ext4_ext_search_right(struct inode *inode,
struct ext4_ext_path *path,
ext4_lblk_t *logical, ext4_fsblk_t *phys,
- struct ext4_extent **ret_ex)
+ struct ext4_extent *ret_ex)
{
struct buffer_head *bh = NULL;
struct ext4_extent_header *eh;
@@ -1574,10 +1574,11 @@
found_extent:
*logical = le32_to_cpu(ex->ee_block);
*phys = ext4_ext_pblock(ex);
- *ret_ex = ex;
+ if (ret_ex)
+ *ret_ex = *ex;
if (bh)
put_bh(bh);
- return 0;
+ return 1;
}
/*
@@ -2868,8 +2869,8 @@
*/
lblk = ex_end + 1;
err = ext4_ext_search_right(inode, path, &lblk, &pblk,
- &ex);
- if (err)
+ NULL);
+ if (err < 0)
goto out;
if (pblk) {
partial.pclu = EXT4_B2C(sbi, pblk);
@@ -3723,7 +3724,6 @@
err = ext4_ext_dirty(handle, inode, path + path->p_depth);
out:
ext4_ext_show_leaf(inode, path);
- ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1);
return err;
}
@@ -3795,7 +3795,6 @@
if (*allocated > map->m_len)
*allocated = map->m_len;
map->m_len = *allocated;
- ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1);
return 0;
}
@@ -4039,7 +4038,7 @@
struct ext4_map_blocks *map, int flags)
{
struct ext4_ext_path *path = NULL;
- struct ext4_extent newex, *ex, *ex2;
+ struct ext4_extent newex, *ex, ex2;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
ext4_fsblk_t newblock = 0, pblk;
int err = 0, depth, ret;
@@ -4175,15 +4174,14 @@
if (err)
goto out;
ar.lright = map->m_lblk;
- ex2 = NULL;
err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright, &ex2);
- if (err)
+ if (err < 0)
goto out;
/* Check if the extent after searching to the right implies a
* cluster we can use. */
- if ((sbi->s_cluster_ratio > 1) && ex2 &&
- get_implied_cluster_alloc(inode->i_sb, map, ex2, path)) {
+ if ((sbi->s_cluster_ratio > 1) && err &&
+ get_implied_cluster_alloc(inode->i_sb, map, &ex2, path)) {
ar.len = allocated = map->m_len;
newblock = map->m_pblk;
goto got_allocated_blocks;
@@ -4329,7 +4327,6 @@
map->m_len = ar.len;
allocated = map->m_len;
ext4_ext_show_leaf(inode, path);
- ext4_fc_track_range(inode, map->m_lblk, map->m_lblk + map->m_len - 1);
out:
ext4_ext_drop_refs(path);
kfree(path);
@@ -4602,7 +4599,7 @@
ret = ext4_mark_inode_dirty(handle, inode);
if (unlikely(ret))
goto out_handle;
- ext4_fc_track_range(inode, offset >> inode->i_sb->s_blocksize_bits,
+ ext4_fc_track_range(handle, inode, offset >> inode->i_sb->s_blocksize_bits,
(offset + len - 1) >> inode->i_sb->s_blocksize_bits);
/* Zero out partial block at the edges of the range */
ret = ext4_zero_partial_blocks(handle, inode, offset, len);
@@ -4651,8 +4648,6 @@
FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |
FALLOC_FL_INSERT_RANGE))
return -EOPNOTSUPP;
- ext4_fc_track_range(inode, offset >> blkbits,
- (offset + len - 1) >> blkbits);
ext4_fc_start_update(inode);
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 447c8d9..f2033e1 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -83,7 +83,7 @@
*
* Atomicity of commits
* --------------------
- * In order to gaurantee atomicity during the commit operation, fast commit
+ * In order to guarantee atomicity during the commit operation, fast commit
* uses "EXT4_FC_TAG_TAIL" tag that marks a fast commit as complete. Tail
* tag contains CRC of the contents and TID of the transaction after which
* this fast commit should be applied. Recovery code replays fast commit
@@ -152,7 +152,31 @@
INIT_LIST_HEAD(&ei->i_fc_list);
init_waitqueue_head(&ei->i_fc_wait);
atomic_set(&ei->i_fc_updates, 0);
- ei->i_fc_committed_subtid = 0;
+}
+
+/* This function must be called with sbi->s_fc_lock held. */
+static void ext4_fc_wait_committing_inode(struct inode *inode)
+__releases(&EXT4_SB(inode->i_sb)->s_fc_lock)
+{
+ wait_queue_head_t *wq;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+
+#if (BITS_PER_LONG < 64)
+ DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
+ EXT4_STATE_FC_COMMITTING);
+ wq = bit_waitqueue(&ei->i_state_flags,
+ EXT4_STATE_FC_COMMITTING);
+#else
+ DEFINE_WAIT_BIT(wait, &ei->i_flags,
+ EXT4_STATE_FC_COMMITTING);
+ wq = bit_waitqueue(&ei->i_flags,
+ EXT4_STATE_FC_COMMITTING);
+#endif
+ lockdep_assert_held(&EXT4_SB(inode->i_sb)->s_fc_lock);
+ prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
+ spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+ schedule();
+ finish_wait(wq, &wait.wq_entry);
}
/*
@@ -176,22 +200,7 @@
goto out;
if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) {
- wait_queue_head_t *wq;
-#if (BITS_PER_LONG < 64)
- DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
- EXT4_STATE_FC_COMMITTING);
- wq = bit_waitqueue(&ei->i_state_flags,
- EXT4_STATE_FC_COMMITTING);
-#else
- DEFINE_WAIT_BIT(wait, &ei->i_flags,
- EXT4_STATE_FC_COMMITTING);
- wq = bit_waitqueue(&ei->i_flags,
- EXT4_STATE_FC_COMMITTING);
-#endif
- prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
- spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
- schedule();
- finish_wait(wq, &wait.wq_entry);
+ ext4_fc_wait_committing_inode(inode);
goto restart;
}
out:
@@ -234,26 +243,10 @@
}
if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) {
- wait_queue_head_t *wq;
-#if (BITS_PER_LONG < 64)
- DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
- EXT4_STATE_FC_COMMITTING);
- wq = bit_waitqueue(&ei->i_state_flags,
- EXT4_STATE_FC_COMMITTING);
-#else
- DEFINE_WAIT_BIT(wait, &ei->i_flags,
- EXT4_STATE_FC_COMMITTING);
- wq = bit_waitqueue(&ei->i_flags,
- EXT4_STATE_FC_COMMITTING);
-#endif
- prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
- spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
- schedule();
- finish_wait(wq, &wait.wq_entry);
+ ext4_fc_wait_committing_inode(inode);
goto restart;
}
- if (!list_empty(&ei->i_fc_list))
- list_del_init(&ei->i_fc_list);
+ list_del_init(&ei->i_fc_list);
spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
}
@@ -269,7 +262,7 @@
(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
return;
- sbi->s_mount_state |= EXT4_FC_INELIGIBLE;
+ ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
WARN_ON(reason >= EXT4_FC_REASON_MAX);
sbi->s_fc_stats.fc_ineligible_reason_count[reason]++;
}
@@ -292,7 +285,7 @@
}
/*
- * Stop a fast commit ineligible update. We set EXT4_FC_INELIGIBLE flag here
+ * Stop a fast commit ineligible update. We set EXT4_MF_FC_INELIGIBLE flag here
* to ensure that after stopping the ineligible update, at least one full
* commit takes place.
*/
@@ -302,14 +295,14 @@
(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
return;
- EXT4_SB(sb)->s_mount_state |= EXT4_FC_INELIGIBLE;
+ ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
atomic_dec(&EXT4_SB(sb)->s_fc_ineligible_updates);
}
static inline int ext4_fc_is_ineligible(struct super_block *sb)
{
- return (EXT4_SB(sb)->s_mount_state & EXT4_FC_INELIGIBLE) ||
- atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates);
+ return (ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE) ||
+ atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates));
}
/*
@@ -323,13 +316,14 @@
* If enqueue is set, this function enqueues the inode in fast commit list.
*/
static int ext4_fc_track_template(
- struct inode *inode, int (*__fc_track_fn)(struct inode *, void *, bool),
+ handle_t *handle, struct inode *inode,
+ int (*__fc_track_fn)(struct inode *, void *, bool),
void *args, int enqueue)
{
- tid_t running_txn_tid;
bool update = false;
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ tid_t tid = 0;
int ret;
if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
@@ -339,15 +333,13 @@
if (ext4_fc_is_ineligible(inode->i_sb))
return -EINVAL;
- running_txn_tid = sbi->s_journal ?
- sbi->s_journal->j_commit_sequence + 1 : 0;
-
+ tid = handle->h_transaction->t_tid;
mutex_lock(&ei->i_fc_lock);
- if (running_txn_tid == ei->i_sync_tid) {
+ if (tid == ei->i_sync_tid) {
update = true;
} else {
ext4_fc_reset_inode(inode);
- ei->i_sync_tid = running_txn_tid;
+ ei->i_sync_tid = tid;
}
ret = __fc_track_fn(inode, args, update);
mutex_unlock(&ei->i_fc_lock);
@@ -358,7 +350,7 @@
spin_lock(&sbi->s_fc_lock);
if (list_empty(&EXT4_I(inode)->i_fc_list))
list_add_tail(&EXT4_I(inode)->i_fc_list,
- (sbi->s_mount_state & EXT4_FC_COMMITTING) ?
+ (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) ?
&sbi->s_fc_q[FC_Q_STAGING] :
&sbi->s_fc_q[FC_Q_MAIN]);
spin_unlock(&sbi->s_fc_lock);
@@ -384,7 +376,7 @@
mutex_unlock(&ei->i_fc_lock);
node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS);
if (!node) {
- ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_MEM);
+ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM);
mutex_lock(&ei->i_fc_lock);
return -ENOMEM;
}
@@ -397,7 +389,7 @@
if (!node->fcd_name.name) {
kmem_cache_free(ext4_fc_dentry_cachep, node);
ext4_fc_mark_ineligible(inode->i_sb,
- EXT4_FC_REASON_MEM);
+ EXT4_FC_REASON_NOMEM);
mutex_lock(&ei->i_fc_lock);
return -ENOMEM;
}
@@ -411,7 +403,7 @@
node->fcd_name.len = dentry->d_name.len;
spin_lock(&sbi->s_fc_lock);
- if (sbi->s_mount_state & EXT4_FC_COMMITTING)
+ if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING))
list_add_tail(&node->fcd_list,
&sbi->s_fc_dentry_q[FC_Q_STAGING]);
else
@@ -422,7 +414,8 @@
return 0;
}
-void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry)
+void __ext4_fc_track_unlink(handle_t *handle,
+ struct inode *inode, struct dentry *dentry)
{
struct __track_dentry_update_args args;
int ret;
@@ -430,12 +423,18 @@
args.dentry = dentry;
args.op = EXT4_FC_TAG_UNLINK;
- ret = ext4_fc_track_template(inode, __track_dentry_update,
+ ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
(void *)&args, 0);
trace_ext4_fc_track_unlink(inode, dentry, ret);
}
-void ext4_fc_track_link(struct inode *inode, struct dentry *dentry)
+void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry)
+{
+ __ext4_fc_track_unlink(handle, d_inode(dentry), dentry);
+}
+
+void __ext4_fc_track_link(handle_t *handle,
+ struct inode *inode, struct dentry *dentry)
{
struct __track_dentry_update_args args;
int ret;
@@ -443,20 +442,26 @@
args.dentry = dentry;
args.op = EXT4_FC_TAG_LINK;
- ret = ext4_fc_track_template(inode, __track_dentry_update,
+ ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
(void *)&args, 0);
trace_ext4_fc_track_link(inode, dentry, ret);
}
-void ext4_fc_track_create(struct inode *inode, struct dentry *dentry)
+void ext4_fc_track_link(handle_t *handle, struct dentry *dentry)
+{
+ __ext4_fc_track_link(handle, d_inode(dentry), dentry);
+}
+
+void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
{
struct __track_dentry_update_args args;
+ struct inode *inode = d_inode(dentry);
int ret;
args.dentry = dentry;
args.op = EXT4_FC_TAG_CREAT;
- ret = ext4_fc_track_template(inode, __track_dentry_update,
+ ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
(void *)&args, 0);
trace_ext4_fc_track_create(inode, dentry, ret);
}
@@ -472,14 +477,20 @@
return 0;
}
-void ext4_fc_track_inode(struct inode *inode)
+void ext4_fc_track_inode(handle_t *handle, struct inode *inode)
{
int ret;
if (S_ISDIR(inode->i_mode))
return;
- ret = ext4_fc_track_template(inode, __track_inode, NULL, 1);
+ if (ext4_should_journal_data(inode)) {
+ ext4_fc_mark_ineligible(inode->i_sb,
+ EXT4_FC_REASON_INODE_JOURNAL_DATA);
+ return;
+ }
+
+ ret = ext4_fc_track_template(handle, inode, __track_inode, NULL, 1);
trace_ext4_fc_track_inode(inode, ret);
}
@@ -515,7 +526,7 @@
return 0;
}
-void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start,
+void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start,
ext4_lblk_t end)
{
struct __track_range_args args;
@@ -527,7 +538,7 @@
args.start = start;
args.end = end;
- ret = ext4_fc_track_template(inode, __track_range, &args, 1);
+ ret = ext4_fc_track_template(handle, inode, __track_range, &args, 1);
trace_ext4_fc_track_range(inode, start, end, ret);
}
@@ -537,10 +548,11 @@
int write_flags = REQ_SYNC;
struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh;
+ /* TODO: REQ_FUA | REQ_PREFLUSH is unnecessarily expensive. */
if (test_opt(sb, BARRIER))
write_flags |= REQ_FUA | REQ_PREFLUSH;
lock_buffer(bh);
- clear_buffer_dirty(bh);
+ set_buffer_dirty(bh);
set_buffer_uptodate(bh);
bh->b_end_io = ext4_end_buffer_io_sync;
submit_bh(REQ_OP_WRITE, write_flags, bh);
@@ -846,7 +858,7 @@
int ret = 0;
spin_lock(&sbi->s_fc_lock);
- sbi->s_mount_state |= EXT4_FC_COMMITTING;
+ ext4_set_mount_flag(sb, EXT4_MF_FC_COMMITTING);
list_for_each(pos, &sbi->s_fc_q[FC_Q_MAIN]) {
ei = list_entry(pos, struct ext4_inode_info, i_fc_list);
ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING);
@@ -900,6 +912,8 @@
/* Commit all the directory entry updates */
static int ext4_fc_commit_dentry_updates(journal_t *journal, u32 *crc)
+__acquires(&sbi->s_fc_lock)
+__releases(&sbi->s_fc_lock)
{
struct super_block *sb = (struct super_block *)(journal->j_private);
struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -964,7 +978,6 @@
fc_dentry->fcd_parent, fc_dentry->fcd_ino,
fc_dentry->fcd_name.len,
fc_dentry->fcd_name.name, crc)) {
- spin_lock(&sbi->s_fc_lock);
ret = -ENOSPC;
goto lock_and_exit;
}
@@ -997,6 +1010,13 @@
if (ret)
return ret;
+ /*
+ * If file system device is different from journal device, issue a cache
+ * flush before we start writing fast commit blocks.
+ */
+ if (journal->j_fs_dev != journal->j_dev)
+ blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS);
+
blk_start_plug(&plug);
if (sbi->s_fc_bytes == 0) {
/*
@@ -1032,8 +1052,6 @@
if (ret)
goto out;
spin_lock(&sbi->s_fc_lock);
- EXT4_I(inode)->i_fc_committed_subtid =
- atomic_read(&sbi->s_fc_subtid);
}
spin_unlock(&sbi->s_fc_lock);
@@ -1132,7 +1150,7 @@
"Fast commit ended with blks = %d, reason = %d, subtid - %d",
nblks, reason, subtid);
if (reason == EXT4_FC_REASON_FC_FAILED)
- return jbd2_fc_end_commit_fallback(journal, commit_tid);
+ return jbd2_fc_end_commit_fallback(journal);
if (reason == EXT4_FC_REASON_FC_START_FAILED ||
reason == EXT4_FC_REASON_INELIGIBLE)
return jbd2_complete_transaction(journal, commit_tid);
@@ -1191,8 +1209,8 @@
list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
&sbi->s_fc_q[FC_Q_STAGING]);
- sbi->s_mount_state &= ~EXT4_FC_COMMITTING;
- sbi->s_mount_state &= ~EXT4_FC_INELIGIBLE;
+ ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
+ ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
if (full)
sbi->s_fc_bytes = 0;
@@ -1264,7 +1282,7 @@
return 0;
}
- ret = __ext4_unlink(old_parent, &entry, inode);
+ ret = __ext4_unlink(NULL, old_parent, &entry, inode);
/* -ENOENT ok coz it might not exist anymore. */
if (ret == -ENOENT)
ret = 0;
@@ -1617,8 +1635,10 @@
if (ret == 0) {
/* Range is not mapped */
path = ext4_find_extent(inode, cur, NULL, 0);
- if (!path)
- continue;
+ if (IS_ERR(path)) {
+ iput(inode);
+ return 0;
+ }
memset(&newex, 0, sizeof(newex));
newex.ee_block = cpu_to_le32(cur);
ext4_ext_store_pblock(
@@ -2087,13 +2107,9 @@
if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
return;
journal->j_fc_cleanup_callback = ext4_fc_cleanup;
- if (jbd2_fc_init(journal, EXT4_NUM_FC_BLKS)) {
- pr_warn("Error while enabling fast commits, turning off.");
- ext4_clear_feature_fast_commit(sb);
- }
}
-const char *fc_ineligible_reasons[] = {
+static const char *fc_ineligible_reasons[] = {
"Extended attributes changed",
"Cross rename",
"Journal flag changed",
@@ -2102,6 +2118,7 @@
"Resize",
"Dir renamed",
"Falloc range op",
+ "Data journalling",
"FC Commit Failed"
};
diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h
index 06907d4..3a6e5a1 100644
--- a/fs/ext4/fast_commit.h
+++ b/fs/ext4/fast_commit.h
@@ -3,9 +3,6 @@
#ifndef __FAST_COMMIT_H__
#define __FAST_COMMIT_H__
-/* Number of blocks in journal area to allocate for fast commits */
-#define EXT4_NUM_FC_BLKS 256
-
/* Fast commit tags */
#define EXT4_FC_TAG_ADD_RANGE 0x0001
#define EXT4_FC_TAG_DEL_RANGE 0x0002
@@ -100,11 +97,12 @@
EXT4_FC_REASON_XATTR = 0,
EXT4_FC_REASON_CROSS_RENAME,
EXT4_FC_REASON_JOURNAL_FLAG_CHANGE,
- EXT4_FC_REASON_MEM,
+ EXT4_FC_REASON_NOMEM,
EXT4_FC_REASON_SWAP_BOOT,
EXT4_FC_REASON_RESIZE,
EXT4_FC_REASON_RENAME_DIR,
EXT4_FC_REASON_FALLOC_RANGE,
+ EXT4_FC_REASON_INODE_JOURNAL_DATA,
EXT4_FC_COMMIT_FAILED,
EXT4_FC_REASON_MAX
};
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index d85412d..3ed8c04 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -761,7 +761,6 @@
if (!daxdev_mapping_supported(vma, dax_dev))
return -EOPNOTSUPP;
- ext4_fc_start_update(inode);
file_accessed(file);
if (IS_DAX(file_inode(file))) {
vma->vm_ops = &ext4_dax_vm_ops;
@@ -769,7 +768,6 @@
} else {
vma->vm_ops = &ext4_file_vm_ops;
}
- ext4_fc_stop_update(inode);
return 0;
}
@@ -782,13 +780,13 @@
handle_t *handle;
int err;
- if (likely(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED))
+ if (likely(ext4_test_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED)))
return 0;
if (sb_rdonly(sb) || !sb_start_intwrite_trylock(sb))
return 0;
- sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
+ ext4_set_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED);
/*
* Sample where the filesystem has been mounted and
* store it in the superblock for sysadmin convenience
diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c
index b232c276..4c2a9fe 100644
--- a/fs/ext4/fsmap.c
+++ b/fs/ext4/fsmap.c
@@ -280,7 +280,7 @@
/* Fabricate an rmap entry for the external log device. */
irec.fmr_physical = journal->j_blk_offset;
- irec.fmr_length = journal->j_maxlen;
+ irec.fmr_length = journal->j_total_len;
irec.fmr_owner = EXT4_FMR_OWN_LOG;
irec.fmr_flags = 0;
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 81a545f..a42ca95 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -143,7 +143,7 @@
if (sb_rdonly(inode->i_sb)) {
/* Make sure that we read updated s_mount_flags value */
smp_rmb();
- if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
+ if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))
ret = -EROFS;
goto out;
}
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index 2924261..a92eb79 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -275,7 +275,7 @@
struct dx_hash_info *hinfo)
{
#ifdef CONFIG_UNICODE
- const struct unicode_map *um = EXT4_SB(dir->i_sb)->s_encoding;
+ const struct unicode_map *um = dir->i_sb->s_encoding;
int r, dlen;
unsigned char *buff;
struct qstr qstr = {.name = name, .len = len };
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index caa5147..b41512d 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -1880,6 +1880,7 @@
ext4_write_lock_xattr(inode, &no_expand);
if (!ext4_has_inline_data(inode)) {
+ ext4_write_unlock_xattr(inode, &no_expand);
*has_inline = 0;
ext4_journal_stop(handle);
return 0;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 03c2253..0d8385a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -327,6 +327,8 @@
ext4_xattr_inode_array_free(ea_inode_array);
return;
no_delete:
+ if (!list_empty(&EXT4_I(inode)->i_fc_list))
+ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM);
ext4_clear_inode(inode); /* We must guarantee clearing of inode... */
}
@@ -730,7 +732,7 @@
if (ret)
return ret;
}
- ext4_fc_track_range(inode, map->m_lblk,
+ ext4_fc_track_range(handle, inode, map->m_lblk,
map->m_lblk + map->m_len - 1);
}
@@ -1918,7 +1920,7 @@
}
if (ret == 0)
ret = err;
- err = ext4_jbd2_inode_add_write(handle, inode, 0, len);
+ err = ext4_jbd2_inode_add_write(handle, inode, page_offset(page), len);
if (ret == 0)
ret = err;
EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
@@ -2440,7 +2442,7 @@
struct super_block *sb = inode->i_sb;
if (ext4_forced_shutdown(EXT4_SB(sb)) ||
- EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+ ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
goto invalidate_dirty_pages;
/*
* Let the uper layers retry transient errors.
@@ -2674,7 +2676,7 @@
* the stack trace.
*/
if (unlikely(ext4_forced_shutdown(EXT4_SB(mapping->host->i_sb)) ||
- sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
+ ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))) {
ret = -EROFS;
goto out_writepages;
}
@@ -3307,10 +3309,11 @@
if (journal) {
if (jbd2_transaction_committed(journal,
- EXT4_I(inode)->i_datasync_tid))
- return true;
- return atomic_read(&EXT4_SB(inode->i_sb)->s_fc_subtid) >=
- EXT4_I(inode)->i_fc_committed_subtid;
+ EXT4_I(inode)->i_datasync_tid))
+ return false;
+ if (test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
+ return !list_empty(&EXT4_I(inode)->i_fc_list);
+ return true;
}
/* Any metadata buffers to write? */
@@ -4107,7 +4110,7 @@
up_write(&EXT4_I(inode)->i_data_sem);
}
- ext4_fc_track_range(inode, first_block, stop_block);
+ ext4_fc_track_range(handle, inode, first_block, stop_block);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
@@ -5440,14 +5443,14 @@
}
if (shrink)
- ext4_fc_track_range(inode,
+ ext4_fc_track_range(handle, inode,
(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
inode->i_sb->s_blocksize_bits,
(oldsize > 0 ? oldsize - 1 : 0) >>
inode->i_sb->s_blocksize_bits);
else
ext4_fc_track_range(
- inode,
+ handle, inode,
(oldsize > 0 ? oldsize - 1 : oldsize) >>
inode->i_sb->s_blocksize_bits,
(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
@@ -5697,7 +5700,7 @@
put_bh(iloc->bh);
return -EIO;
}
- ext4_fc_track_inode(inode);
+ ext4_fc_track_inode(handle, inode);
if (IS_I_VERSION(inode))
inode_inc_iversion(inode);
@@ -6157,7 +6160,8 @@
if (ext4_walk_page_buffers(handle, page_buffers(page),
0, len, NULL, write_end_fn))
goto out_error;
- if (ext4_jbd2_inode_add_write(handle, inode, 0, len))
+ if (ext4_jbd2_inode_add_write(handle, inode,
+ page_offset(page), len))
goto out_error;
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
} else {
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 85abbfb..24af9ed 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4477,7 +4477,7 @@
{
ext4_group_t i, ngroups;
- if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+ if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
return;
ngroups = ext4_get_groups_count(sb);
@@ -4508,7 +4508,7 @@
{
struct super_block *sb = ac->ac_sb;
- if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+ if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
return;
mb_debug(sb, "Can't allocate:"
@@ -5167,7 +5167,7 @@
struct super_block *sb = ar->inode->i_sb;
ext4_group_t group;
ext4_grpblk_t blkoff;
- int i;
+ int i = sb->s_blocksize;
ext4_fsblk_t goal, block;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 5159830..3350926 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1285,8 +1285,8 @@
int ext4_ci_compare(const struct inode *parent, const struct qstr *name,
const struct qstr *entry, bool quick)
{
- const struct ext4_sb_info *sbi = EXT4_SB(parent->i_sb);
- const struct unicode_map *um = sbi->s_encoding;
+ const struct super_block *sb = parent->i_sb;
+ const struct unicode_map *um = sb->s_encoding;
int ret;
if (quick)
@@ -1298,7 +1298,7 @@
/* Handle invalid character sequence as either an error
* or as an opaque byte sequence.
*/
- if (ext4_has_strict_mode(sbi))
+ if (sb_has_strict_encoding(sb))
return -EINVAL;
if (name->len != entry->len)
@@ -1315,7 +1315,7 @@
{
int len;
- if (!IS_CASEFOLDED(dir) || !EXT4_SB(dir->i_sb)->s_encoding) {
+ if (!IS_CASEFOLDED(dir) || !dir->i_sb->s_encoding) {
cf_name->name = NULL;
return;
}
@@ -1324,7 +1324,7 @@
if (!cf_name->name)
return;
- len = utf8_casefold(EXT4_SB(dir->i_sb)->s_encoding,
+ len = utf8_casefold(dir->i_sb->s_encoding,
iname, cf_name->name,
EXT4_NAME_LEN);
if (len <= 0) {
@@ -1361,7 +1361,7 @@
#endif
#ifdef CONFIG_UNICODE
- if (EXT4_SB(parent->i_sb)->s_encoding && IS_CASEFOLDED(parent)) {
+ if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent)) {
if (fname->cf_name.name) {
struct qstr cf = {.name = fname->cf_name.name,
.len = fname->cf_name.len};
@@ -2180,9 +2180,6 @@
struct buffer_head *bh = NULL;
struct ext4_dir_entry_2 *de;
struct super_block *sb;
-#ifdef CONFIG_UNICODE
- struct ext4_sb_info *sbi;
-#endif
struct ext4_filename fname;
int retval;
int dx_fallback=0;
@@ -2199,9 +2196,8 @@
return -EINVAL;
#ifdef CONFIG_UNICODE
- sbi = EXT4_SB(sb);
- if (ext4_has_strict_mode(sbi) && IS_CASEFOLDED(dir) &&
- sbi->s_encoding && utf8_validate(sbi->s_encoding, &dentry->d_name))
+ if (sb_has_strict_encoding(sb) && IS_CASEFOLDED(dir) &&
+ sb->s_encoding && utf8_validate(sb->s_encoding, &dentry->d_name))
return -EINVAL;
#endif
@@ -2610,7 +2606,7 @@
bool excl)
{
handle_t *handle;
- struct inode *inode, *inode_save;
+ struct inode *inode;
int err, credits, retries = 0;
err = dquot_initialize(dir);
@@ -2628,11 +2624,9 @@
inode->i_op = &ext4_file_inode_operations;
inode->i_fop = &ext4_file_operations;
ext4_set_aops(inode);
- inode_save = inode;
- ihold(inode_save);
err = ext4_add_nondir(handle, dentry, &inode);
- ext4_fc_track_create(inode_save, dentry);
- iput(inode_save);
+ if (!err)
+ ext4_fc_track_create(handle, dentry);
}
if (handle)
ext4_journal_stop(handle);
@@ -2647,7 +2641,7 @@
umode_t mode, dev_t rdev)
{
handle_t *handle;
- struct inode *inode, *inode_save;
+ struct inode *inode;
int err, credits, retries = 0;
err = dquot_initialize(dir);
@@ -2664,12 +2658,9 @@
if (!IS_ERR(inode)) {
init_special_inode(inode, inode->i_mode, rdev);
inode->i_op = &ext4_special_inode_operations;
- inode_save = inode;
- ihold(inode_save);
err = ext4_add_nondir(handle, dentry, &inode);
if (!err)
- ext4_fc_track_create(inode_save, dentry);
- iput(inode_save);
+ ext4_fc_track_create(handle, dentry);
}
if (handle)
ext4_journal_stop(handle);
@@ -2833,7 +2824,6 @@
iput(inode);
goto out_retry;
}
- ext4_fc_track_create(inode, dentry);
ext4_inc_count(dir);
ext4_update_dx_flag(dir);
@@ -2841,6 +2831,7 @@
if (err)
goto out_clear_inode;
d_instantiate_new(dentry, inode);
+ ext4_fc_track_create(handle, dentry);
if (IS_DIRSYNC(dir))
ext4_handle_sync(handle);
@@ -3175,7 +3166,7 @@
goto end_rmdir;
ext4_dec_count(dir);
ext4_update_dx_flag(dir);
- ext4_fc_track_unlink(inode, dentry);
+ ext4_fc_track_unlink(handle, dentry);
retval = ext4_mark_inode_dirty(handle, dir);
#ifdef CONFIG_UNICODE
@@ -3196,13 +3187,12 @@
return retval;
}
-int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
+int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name,
struct inode *inode)
{
int retval = -ENOENT;
struct buffer_head *bh;
struct ext4_dir_entry_2 *de;
- handle_t *handle = NULL;
int skip_remove_dentry = 0;
bh = ext4_find_entry(dir, d_name, &de, NULL);
@@ -3221,14 +3211,7 @@
if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
skip_remove_dentry = 1;
else
- goto out_bh;
- }
-
- handle = ext4_journal_start(dir, EXT4_HT_DIR,
- EXT4_DATA_TRANS_BLOCKS(dir->i_sb));
- if (IS_ERR(handle)) {
- retval = PTR_ERR(handle);
- goto out_bh;
+ goto out;
}
if (IS_DIRSYNC(dir))
@@ -3237,12 +3220,12 @@
if (!skip_remove_dentry) {
retval = ext4_delete_entry(handle, dir, de, bh);
if (retval)
- goto out_handle;
+ goto out;
dir->i_ctime = dir->i_mtime = current_time(dir);
ext4_update_dx_flag(dir);
retval = ext4_mark_inode_dirty(handle, dir);
if (retval)
- goto out_handle;
+ goto out;
} else {
retval = 0;
}
@@ -3256,15 +3239,14 @@
inode->i_ctime = current_time(inode);
retval = ext4_mark_inode_dirty(handle, inode);
-out_handle:
- ext4_journal_stop(handle);
-out_bh:
+out:
brelse(bh);
return retval;
}
static int ext4_unlink(struct inode *dir, struct dentry *dentry)
{
+ handle_t *handle;
int retval;
if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
@@ -3282,9 +3264,16 @@
if (retval)
goto out_trace;
- retval = __ext4_unlink(dir, &dentry->d_name, d_inode(dentry));
+ handle = ext4_journal_start(dir, EXT4_HT_DIR,
+ EXT4_DATA_TRANS_BLOCKS(dir->i_sb));
+ if (IS_ERR(handle)) {
+ retval = PTR_ERR(handle);
+ goto out_trace;
+ }
+
+ retval = __ext4_unlink(handle, dir, &dentry->d_name, d_inode(dentry));
if (!retval)
- ext4_fc_track_unlink(d_inode(dentry), dentry);
+ ext4_fc_track_unlink(handle, dentry);
#ifdef CONFIG_UNICODE
/* VFS negative dentries are incompatible with Encoding and
* Case-insensitiveness. Eventually we'll want avoid
@@ -3295,6 +3284,8 @@
if (IS_CASEFOLDED(dir))
d_invalidate(dentry);
#endif
+ if (handle)
+ ext4_journal_stop(handle);
out_trace:
trace_ext4_unlink_exit(dentry, retval);
@@ -3451,7 +3442,6 @@
err = ext4_add_entry(handle, dentry, inode);
if (!err) {
- ext4_fc_track_link(inode, dentry);
err = ext4_mark_inode_dirty(handle, inode);
/* this can happen only for tmpfile being
* linked the first time
@@ -3459,6 +3449,7 @@
if (inode->i_nlink == 1)
ext4_orphan_del(handle, inode);
d_instantiate(dentry, inode);
+ ext4_fc_track_link(handle, dentry);
} else {
drop_nlink(inode);
iput(inode);
@@ -3919,9 +3910,9 @@
EXT4_FC_REASON_RENAME_DIR);
} else {
if (new.inode)
- ext4_fc_track_unlink(new.inode, new.dentry);
- ext4_fc_track_link(old.inode, new.dentry);
- ext4_fc_track_unlink(old.inode, old.dentry);
+ ext4_fc_track_unlink(handle, new.dentry);
+ __ext4_fc_track_link(handle, old.inode, new.dentry);
+ __ext4_fc_track_unlink(handle, old.inode, old.dentry);
}
if (new.inode) {
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 2fe141ff..6633b20 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -289,18 +289,7 @@
if (!ext4_has_metadata_csum(sb))
return;
- /*
- * Locking the superblock prevents the scenario
- * where:
- * 1) a first thread pauses during checksum calculation.
- * 2) a second thread updates the superblock, recalculates
- * the checksum, and updates s_checksum
- * 3) the first thread resumes and finishes its checksum calculation
- * and updates s_checksum with a potentially stale or torn value.
- */
- lock_buffer(EXT4_SB(sb)->s_sbh);
es->s_checksum = ext4_superblock_csum(sb, es);
- unlock_buffer(EXT4_SB(sb)->s_sbh);
}
ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
@@ -686,7 +675,7 @@
if (!test_opt(sb, ERRORS_CONT)) {
journal_t *journal = EXT4_SB(sb)->s_journal;
- EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+ ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
if (journal)
jbd2_journal_abort(journal, -EIO);
}
@@ -904,7 +893,7 @@
va_end(args);
if (sb_rdonly(sb) == 0) {
- EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+ ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
if (EXT4_SB(sb)->s_journal)
jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
@@ -1288,7 +1277,7 @@
fs_put_dax(sbi->s_daxdev);
fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
#ifdef CONFIG_UNICODE
- utf8_unload(sbi->s_encoding);
+ utf8_unload(sb->s_encoding);
#endif
kfree(sbi);
}
@@ -1716,11 +1705,10 @@
Opt_dioread_nolock, Opt_dioread_lock,
Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
- Opt_prefetch_block_bitmaps, Opt_no_fc,
+ Opt_prefetch_block_bitmaps,
#ifdef CONFIG_EXT4_DEBUG
- Opt_fc_debug_max_replay,
+ Opt_fc_debug_max_replay, Opt_fc_debug_force
#endif
- Opt_fc_debug_force
};
static const match_table_t tokens = {
@@ -1807,9 +1795,8 @@
{Opt_init_itable, "init_itable=%u"},
{Opt_init_itable, "init_itable"},
{Opt_noinit_itable, "noinit_itable"},
- {Opt_no_fc, "no_fc"},
- {Opt_fc_debug_force, "fc_debug_force"},
#ifdef CONFIG_EXT4_DEBUG
+ {Opt_fc_debug_force, "fc_debug_force"},
{Opt_fc_debug_max_replay, "fc_debug_max_replay=%u"},
#endif
{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
@@ -2027,8 +2014,8 @@
{Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA |
EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA),
MOPT_CLEAR | MOPT_Q},
- {Opt_usrjquota, 0, MOPT_Q},
- {Opt_grpjquota, 0, MOPT_Q},
+ {Opt_usrjquota, 0, MOPT_Q | MOPT_STRING},
+ {Opt_grpjquota, 0, MOPT_Q | MOPT_STRING},
{Opt_offusrjquota, 0, MOPT_Q},
{Opt_offgrpjquota, 0, MOPT_Q},
{Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT},
@@ -2039,11 +2026,9 @@
{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
{Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS,
MOPT_SET},
- {Opt_no_fc, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
- MOPT_CLEAR | MOPT_2 | MOPT_EXT4_ONLY},
+#ifdef CONFIG_EXT4_DEBUG
{Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY},
-#ifdef CONFIG_EXT4_DEBUG
{Opt_fc_debug_max_replay, 0, MOPT_GTE0},
#endif
{Opt_err, 0, 0}
@@ -2153,7 +2138,7 @@
ext4_msg(sb, KERN_WARNING, "Ignoring removed %s option", opt);
return 1;
case Opt_abort:
- sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
+ ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
return 1;
case Opt_i_version:
sb->s_flags |= SB_I_VERSION;
@@ -3976,7 +3961,7 @@
* loaded or not
*/
if (sbi->s_journal && !sbi->s_journal_bdev)
- overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen);
+ overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len);
else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) {
/* j_inum for internal journal is non-zero */
j_inode = ext4_get_journal_inode(sb, j_inum);
@@ -4303,7 +4288,7 @@
goto failed_mount;
#ifdef CONFIG_UNICODE
- if (ext4_has_feature_casefold(sb) && !sbi->s_encoding) {
+ if (ext4_has_feature_casefold(sb) && !sb->s_encoding) {
const struct ext4_sb_encodings *encoding_info;
struct unicode_map *encoding;
__u16 encoding_flags;
@@ -4334,15 +4319,16 @@
"%s-%s with flags 0x%hx", encoding_info->name,
encoding_info->version?:"\b", encoding_flags);
- sbi->s_encoding = encoding;
- sbi->s_encoding_flags = encoding_flags;
+ sb->s_encoding = encoding;
+ sb->s_encoding_flags = encoding_flags;
}
#endif
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
- printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, and O_DIRECT support!\n");
+ printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, O_DIRECT and fast_commit support!\n");
/* can't mount with both data=journal and dioread_nolock. */
clear_opt(sb, DIOREAD_NOLOCK);
+ clear_opt2(sb, JOURNAL_FAST_COMMIT);
if (test_opt2(sb, EXPLICIT_DELALLOC)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"both data=journal and delalloc");
@@ -4777,8 +4763,8 @@
INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_MAIN]);
INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]);
sbi->s_fc_bytes = 0;
- sbi->s_mount_state &= ~EXT4_FC_INELIGIBLE;
- sbi->s_mount_state &= ~EXT4_FC_COMMITTING;
+ ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+ ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
spin_lock_init(&sbi->s_fc_lock);
memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats));
sbi->s_fc_replay_state.fc_regions = NULL;
@@ -4857,6 +4843,14 @@
goto failed_mount_wq;
}
+ if (test_opt2(sb, JOURNAL_FAST_COMMIT) &&
+ !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
+ JBD2_FEATURE_INCOMPAT_FAST_COMMIT)) {
+ ext4_msg(sb, KERN_ERR,
+ "Failed to set fast commit journal feature");
+ goto failed_mount_wq;
+ }
+
/* We have now updated the journal if required, so we can
* validate the data journaling mode. */
switch (test_opt(sb, DATA_FLAGS)) {
@@ -4975,7 +4969,7 @@
}
#ifdef CONFIG_UNICODE
- if (sbi->s_encoding)
+ if (sb->s_encoding)
sb->s_d_op = &ext4_dentry_ops;
#endif
@@ -5184,7 +5178,7 @@
crypto_free_shash(sbi->s_chksum_driver);
#ifdef CONFIG_UNICODE
- utf8_unload(sbi->s_encoding);
+ utf8_unload(sb->s_encoding);
#endif
#ifdef CONFIG_QUOTA
@@ -5872,7 +5866,7 @@
goto restore_opts;
}
- if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
+ if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
ext4_abort(sb, EXT4_ERR_ESHUTDOWN, "Abort forced by user");
sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
@@ -5886,7 +5880,7 @@
}
if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) {
- if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
+ if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) {
err = -EROFS;
goto restore_opts;
}
@@ -6560,10 +6554,6 @@
brelse(bh);
out:
if (inode->i_size < off + len) {
- ext4_fc_track_range(inode,
- (inode->i_size > 0 ? inode->i_size - 1 : 0)
- >> inode->i_sb->s_blocksize_bits,
- (off + len) >> inode->i_sb->s_blocksize_bits);
i_size_write(inode, off + len);
EXT4_I(inode)->i_disksize = inode->i_size;
err2 = ext4_mark_inode_dirty(handle, inode);
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 5ff33d1..4e27fe6 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -315,6 +315,7 @@
EXT4_ATTR_FEATURE(verity);
#endif
EXT4_ATTR_FEATURE(metadata_csum_seed);
+EXT4_ATTR_FEATURE(fast_commit);
static struct attribute *ext4_feat_attrs[] = {
ATTR_LIST(lazy_itable_init),
@@ -331,6 +332,7 @@
ATTR_LIST(verity),
#endif
ATTR_LIST(metadata_csum_seed),
+ ATTR_LIST(fast_commit),
NULL,
};
ATTRIBUTE_GROUPS(ext4_feat);
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 9cd2eca..cc4f987 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -77,7 +77,7 @@
if (error)
return error;
if (!buffer_mapped(bh_result))
- return -EIO;
+ return -ENODATA;
return 0;
}
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 8dff9cbd..62d9081 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -1301,12 +1301,8 @@
trace_gfs2_bmap(ip, bh_map, lblock, create, 1);
ret = gfs2_iomap_get(inode, pos, length, flags, &iomap, &mp);
- if (!ret && iomap.type == IOMAP_HOLE) {
- if (create)
- ret = gfs2_iomap_alloc(inode, &iomap, &mp);
- else
- ret = -ENODATA;
- }
+ if (create && !ret && iomap.type == IOMAP_HOLE)
+ ret = gfs2_iomap_alloc(inode, &iomap, &mp);
release_metapath(&mp);
if (ret)
goto out;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 5441c17..d98a2e5 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1078,7 +1078,8 @@
out_free:
kfree(gl->gl_lksb.sb_lvbptr);
kmem_cache_free(cachep, gl);
- atomic_dec(&sdp->sd_glock_disposal);
+ if (atomic_dec_and_test(&sdp->sd_glock_disposal))
+ wake_up(&sdp->sd_glock_wait);
out:
return ret;
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index aa3f523..67f2921 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -165,6 +165,31 @@
}
/**
+ * gfs2_rgrp_metasync - sync out the metadata of a resource group
+ * @gl: the glock protecting the resource group
+ *
+ */
+
+static int gfs2_rgrp_metasync(struct gfs2_glock *gl)
+{
+ struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+ struct address_space *metamapping = &sdp->sd_aspace;
+ struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
+ const unsigned bsize = sdp->sd_sb.sb_bsize;
+ loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK;
+ loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
+ int error;
+
+ filemap_fdatawrite_range(metamapping, start, end);
+ error = filemap_fdatawait_range(metamapping, start, end);
+ WARN_ON_ONCE(error && !gfs2_withdrawn(sdp));
+ mapping_set_error(metamapping, error);
+ if (error)
+ gfs2_io_error(sdp);
+ return error;
+}
+
+/**
* rgrp_go_sync - sync out the metadata for this glock
* @gl: the glock
*
@@ -176,11 +201,7 @@
static int rgrp_go_sync(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
- struct address_space *mapping = &sdp->sd_aspace;
struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
- const unsigned bsize = sdp->sd_sb.sb_bsize;
- loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK;
- loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
int error;
if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
@@ -189,10 +210,7 @@
gfs2_log_flush(sdp, gl, GFS2_LOG_HEAD_FLUSH_NORMAL |
GFS2_LFC_RGRP_GO_SYNC);
- filemap_fdatawrite_range(mapping, start, end);
- error = filemap_fdatawait_range(mapping, start, end);
- WARN_ON_ONCE(error && !gfs2_withdrawn(sdp));
- mapping_set_error(mapping, error);
+ error = gfs2_rgrp_metasync(gl);
if (!error)
error = gfs2_ail_empty_gl(gl);
gfs2_free_clones(rgd);
@@ -266,7 +284,24 @@
}
/**
- * inode_go_sync - Sync the dirty data and/or metadata for an inode glock
+ * gfs2_inode_metasync - sync out the metadata of an inode
+ * @gl: the glock protecting the inode
+ *
+ */
+int gfs2_inode_metasync(struct gfs2_glock *gl)
+{
+ struct address_space *metamapping = gfs2_glock2aspace(gl);
+ int error;
+
+ filemap_fdatawrite(metamapping);
+ error = filemap_fdatawait(metamapping);
+ if (error)
+ gfs2_io_error(gl->gl_name.ln_sbd);
+ return error;
+}
+
+/**
+ * inode_go_sync - Sync the dirty metadata of an inode
* @gl: the glock protecting the inode
*
*/
@@ -297,8 +332,7 @@
error = filemap_fdatawait(mapping);
mapping_set_error(mapping, error);
}
- ret = filemap_fdatawait(metamapping);
- mapping_set_error(metamapping, ret);
+ ret = gfs2_inode_metasync(gl);
if (!error)
error = ret;
gfs2_ail_empty_gl(gl);
@@ -537,7 +571,18 @@
int error = 0;
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
- if (gl->gl_req == LM_ST_EXCLUSIVE && !gfs2_withdrawn(sdp)) {
+ /*
+ * We need to check gl_state == LM_ST_SHARED here and not gl_req ==
+ * LM_ST_EXCLUSIVE. That's because when any node does a freeze,
+ * all the nodes should have the freeze glock in SH mode and they all
+ * call do_xmote: One for EX and the others for UN. They ALL must
+ * freeze locally, and they ALL must queue freeze work. The freeze_work
+ * calls freeze_func, which tries to reacquire the freeze glock in SH,
+ * effectively waiting for the thaw on the node who holds it in EX.
+ * Once thawed, the work func acquires the freeze glock in
+ * SH and everybody goes back to thawed.
+ */
+ if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp)) {
atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE);
error = freeze_super(sdp->sd_vfs);
if (error) {
diff --git a/fs/gfs2/glops.h b/fs/gfs2/glops.h
index 2dd192e..695898a 100644
--- a/fs/gfs2/glops.h
+++ b/fs/gfs2/glops.h
@@ -22,6 +22,7 @@
extern const struct gfs2_glock_operations gfs2_journal_glops;
extern const struct gfs2_glock_operations *gfs2_glops_list[];
+extern int gfs2_inode_metasync(struct gfs2_glock *gl);
extern void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync);
#endif /* __GLOPS_DOT_H__ */
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 6774865..077ccb1 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -180,7 +180,8 @@
error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
if (unlikely(error))
goto fail;
- gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl);
+ if (blktype != GFS2_BLKST_UNLINKED)
+ gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl);
glock_set_object(ip->i_iopen_gh.gh_gl, ip);
gfs2_glock_put(io_gl);
io_gl = NULL;
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 9133b31..2e93140 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -132,6 +132,8 @@
spin_unlock(&sdp->sd_ail_lock);
ret = generic_writepages(mapping, wbc);
spin_lock(&sdp->sd_ail_lock);
+ if (ret == -ENODATA) /* if a jdata write into a new hole */
+ ret = 0; /* ignore it */
if (ret || wbc->nr_to_write <= 0)
break;
return -EBUSY;
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index ed69298..3922b26 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -22,6 +22,7 @@
#include "incore.h"
#include "inode.h"
#include "glock.h"
+#include "glops.h"
#include "log.h"
#include "lops.h"
#include "meta_io.h"
@@ -817,41 +818,19 @@
return error;
}
-/**
- * gfs2_meta_sync - Sync all buffers associated with a glock
- * @gl: The glock
- *
- */
-
-void gfs2_meta_sync(struct gfs2_glock *gl)
-{
- struct address_space *mapping = gfs2_glock2aspace(gl);
- struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
- int error;
-
- if (mapping == NULL)
- mapping = &sdp->sd_aspace;
-
- filemap_fdatawrite(mapping);
- error = filemap_fdatawait(mapping);
-
- if (error)
- gfs2_io_error(gl->gl_name.ln_sbd);
-}
-
static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
{
struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
if (error) {
- gfs2_meta_sync(ip->i_gl);
+ gfs2_inode_metasync(ip->i_gl);
return;
}
if (pass != 1)
return;
- gfs2_meta_sync(ip->i_gl);
+ gfs2_inode_metasync(ip->i_gl);
fs_info(sdp, "jid=%u: Replayed %u of %u blocks\n",
jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
@@ -1060,14 +1039,14 @@
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
if (error) {
- gfs2_meta_sync(ip->i_gl);
+ gfs2_inode_metasync(ip->i_gl);
return;
}
if (pass != 1)
return;
/* data sync? */
- gfs2_meta_sync(ip->i_gl);
+ gfs2_inode_metasync(ip->i_gl);
fs_info(sdp, "jid=%u: Replayed %u of %u data blocks\n",
jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h
index 4a3d8ae..fbdbb08 100644
--- a/fs/gfs2/lops.h
+++ b/fs/gfs2/lops.h
@@ -27,8 +27,6 @@
extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh);
extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
struct gfs2_log_header_host *head, bool keep_cache);
-extern void gfs2_meta_sync(struct gfs2_glock *gl);
-
static inline unsigned int buf_limit(struct gfs2_sbd *sdp)
{
unsigned int limit;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 7a7e3c1..61fce59 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -633,8 +633,10 @@
if (IS_ERR(sdp->sd_statfs_inode)) {
error = PTR_ERR(sdp->sd_statfs_inode);
fs_err(sdp, "can't read in statfs inode: %d\n", error);
- goto fail;
+ goto out;
}
+ if (sdp->sd_args.ar_spectator)
+ goto out;
pn = gfs2_lookup_simple(master, "per_node");
if (IS_ERR(pn)) {
@@ -682,15 +684,17 @@
iput(pn);
put_statfs:
iput(sdp->sd_statfs_inode);
-fail:
+out:
return error;
}
/* Uninitialize and free up memory used by the list of statfs inodes */
static void uninit_statfs(struct gfs2_sbd *sdp)
{
- gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
- free_local_statfs_inodes(sdp);
+ if (!sdp->sd_args.ar_spectator) {
+ gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
+ free_local_statfs_inodes(sdp);
+ }
iput(sdp->sd_statfs_inode);
}
@@ -704,7 +708,7 @@
if (undo) {
jindex = 0;
- goto fail_jinode_gh;
+ goto fail_statfs;
}
sdp->sd_jindex = gfs2_lookup_simple(master, "jindex");
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index b5cbe21..c26c68e 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -349,7 +349,7 @@
mark_buffer_dirty(bh);
brelse(bh);
- gfs2_meta_sync(ip->i_gl);
+ gfs2_inode_metasync(ip->i_gl);
out:
return error;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index ee491bb..f7addc6 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -719,9 +719,9 @@
}
gfs2_free_clones(rgd);
+ return_all_reservations(rgd);
kfree(rgd->rd_bits);
rgd->rd_bits = NULL;
- return_all_reservations(rgd);
kmem_cache_free(gfs2_rgrpd_cachep, rgd);
}
}
@@ -1370,6 +1370,9 @@
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
+ return -EROFS;
+
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
@@ -2526,13 +2529,13 @@
rbm.rgd = rgd;
error = gfs2_rbm_from_block(&rbm, no_addr);
- if (WARN_ON_ONCE(error))
- goto fail;
-
- if (gfs2_testbit(&rbm, false) != type)
- error = -ESTALE;
+ if (!WARN_ON_ONCE(error)) {
+ if (gfs2_testbit(&rbm, false) != type)
+ error = -ESTALE;
+ }
gfs2_glock_dq_uninit(&rgd_gh);
+
fail:
return error;
}
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index b285192b..b3d951a 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -738,6 +738,7 @@
gfs2_jindex_free(sdp);
/* Take apart glock structures and buffer lists */
gfs2_gl_hash_clear(sdp);
+ truncate_inode_pages_final(&sdp->sd_aspace);
gfs2_delete_debugfs_file(sdp);
/* Unmount the locking protocol */
gfs2_lm_unmount(sdp);
diff --git a/fs/hfs/btree.h b/fs/hfs/btree.h
index dcc2aab..4ba45ca 100644
--- a/fs/hfs/btree.h
+++ b/fs/hfs/btree.h
@@ -60,7 +60,7 @@
wait_queue_head_t lock_wq;
atomic_t refcnt;
unsigned int page_offset;
- struct page *page[0];
+ struct page *page[];
};
#define HFS_BNODE_ERROR 0
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 3b03fff..a92de51 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -117,7 +117,7 @@
wait_queue_head_t lock_wq;
atomic_t refcnt;
unsigned int page_offset;
- struct page *page[0];
+ struct page *page[];
};
#define HFS_BNODE_LOCK 0
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 02894df7..b53c055 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -482,6 +482,10 @@
current->files = work->identity->files;
current->nsproxy = work->identity->nsproxy;
task_unlock(current);
+ if (!work->identity->files) {
+ /* failed grabbing files, ensure work gets cancelled */
+ work->flags |= IO_WQ_WORK_CANCEL;
+ }
}
if ((work->flags & IO_WQ_WORK_FS) && current->fs != work->identity->fs)
current->fs = work->identity->fs;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index b42dfa0..4ead291 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -995,20 +995,33 @@
if (mm) {
kthread_unuse_mm(mm);
mmput(mm);
+ current->mm = NULL;
}
}
static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx)
{
- if (!current->mm) {
- if (unlikely(!(ctx->flags & IORING_SETUP_SQPOLL) ||
- !ctx->sqo_task->mm ||
- !mmget_not_zero(ctx->sqo_task->mm)))
- return -EFAULT;
- kthread_use_mm(ctx->sqo_task->mm);
+ struct mm_struct *mm;
+
+ if (current->mm)
+ return 0;
+
+ /* Should never happen */
+ if (unlikely(!(ctx->flags & IORING_SETUP_SQPOLL)))
+ return -EFAULT;
+
+ task_lock(ctx->sqo_task);
+ mm = ctx->sqo_task->mm;
+ if (unlikely(!mm || !mmget_not_zero(mm)))
+ mm = NULL;
+ task_unlock(ctx->sqo_task);
+
+ if (mm) {
+ kthread_use_mm(mm);
+ return 0;
}
- return 0;
+ return -EFAULT;
}
static int io_sq_thread_acquire_mm(struct io_ring_ctx *ctx,
@@ -1274,9 +1287,12 @@
/* add one for this request */
refcount_inc(&id->count);
- /* drop old identity, assign new one. one ref for req, one for tctx */
- if (req->work.identity != tctx->identity &&
- refcount_sub_and_test(2, &req->work.identity->count))
+ /* drop tctx and req identity references, if needed */
+ if (tctx->identity != &tctx->__identity &&
+ refcount_dec_and_test(&tctx->identity->count))
+ kfree(tctx->identity);
+ if (req->work.identity != &tctx->__identity &&
+ refcount_dec_and_test(&req->work.identity->count))
kfree(req->work.identity);
req->work.identity = id;
@@ -1365,6 +1381,9 @@
io_req_init_async(req);
id = req->work.identity;
+ if (req->flags & REQ_F_FORCE_ASYNC)
+ req->work.flags |= IO_WQ_WORK_CONCURRENT;
+
if (req->flags & REQ_F_ISREG) {
if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL))
io_wq_hash_work(&req->work, file_inode(req->file));
@@ -1574,14 +1593,29 @@
}
}
-static inline bool io_match_files(struct io_kiocb *req,
- struct files_struct *files)
+static inline bool __io_match_files(struct io_kiocb *req,
+ struct files_struct *files)
{
+ return ((req->flags & REQ_F_WORK_INITIALIZED) &&
+ (req->work.flags & IO_WQ_WORK_FILES)) &&
+ req->work.identity->files == files;
+}
+
+static bool io_match_files(struct io_kiocb *req,
+ struct files_struct *files)
+{
+ struct io_kiocb *link;
+
if (!files)
return true;
- if ((req->flags & REQ_F_WORK_INITIALIZED) &&
- (req->work.flags & IO_WQ_WORK_FILES))
- return req->work.identity->files == files;
+ if (__io_match_files(req, files))
+ return true;
+ if (req->flags & REQ_F_LINK_HEAD) {
+ list_for_each_entry(link, &req->link_list, link_list) {
+ if (__io_match_files(link, files))
+ return true;
+ }
+ }
return false;
}
@@ -1665,7 +1699,8 @@
WRITE_ONCE(cqe->user_data, req->user_data);
WRITE_ONCE(cqe->res, res);
WRITE_ONCE(cqe->flags, cflags);
- } else if (ctx->cq_overflow_flushed || req->task->io_uring->in_idle) {
+ } else if (ctx->cq_overflow_flushed ||
+ atomic_read(&req->task->io_uring->in_idle)) {
/*
* If we're in ring overflow flush mode, or in task cancel mode,
* then we cannot store the request for later flushing, we need
@@ -1835,7 +1870,7 @@
io_dismantle_req(req);
percpu_counter_dec(&tctx->inflight);
- if (tctx->in_idle)
+ if (atomic_read(&tctx->in_idle))
wake_up(&tctx->wait);
put_task_struct(req->task);
@@ -1846,59 +1881,39 @@
percpu_ref_put(&ctx->refs);
}
-static bool io_link_cancel_timeout(struct io_kiocb *req)
+static void io_kill_linked_timeout(struct io_kiocb *req)
{
- struct io_timeout_data *io = req->async_data;
struct io_ring_ctx *ctx = req->ctx;
- int ret;
-
- ret = hrtimer_try_to_cancel(&io->timer);
- if (ret != -1) {
- io_cqring_fill_event(req, -ECANCELED);
- io_commit_cqring(ctx);
- req->flags &= ~REQ_F_LINK_HEAD;
- io_put_req_deferred(req, 1);
- return true;
- }
-
- return false;
-}
-
-static bool __io_kill_linked_timeout(struct io_kiocb *req)
-{
struct io_kiocb *link;
- bool wake_ev;
+ bool cancelled = false;
+ unsigned long flags;
- if (list_empty(&req->link_list))
- return false;
- link = list_first_entry(&req->link_list, struct io_kiocb, link_list);
- if (link->opcode != IORING_OP_LINK_TIMEOUT)
- return false;
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+ link = list_first_entry_or_null(&req->link_list, struct io_kiocb,
+ link_list);
/*
* Can happen if a linked timeout fired and link had been like
* req -> link t-out -> link t-out [-> ...]
*/
- if (!(link->flags & REQ_F_LTIMEOUT_ACTIVE))
- return false;
+ if (link && (link->flags & REQ_F_LTIMEOUT_ACTIVE)) {
+ struct io_timeout_data *io = link->async_data;
+ int ret;
- list_del_init(&link->link_list);
- wake_ev = io_link_cancel_timeout(link);
+ list_del_init(&link->link_list);
+ ret = hrtimer_try_to_cancel(&io->timer);
+ if (ret != -1) {
+ io_cqring_fill_event(link, -ECANCELED);
+ io_commit_cqring(ctx);
+ cancelled = true;
+ }
+ }
req->flags &= ~REQ_F_LINK_TIMEOUT;
- return wake_ev;
-}
-
-static void io_kill_linked_timeout(struct io_kiocb *req)
-{
- struct io_ring_ctx *ctx = req->ctx;
- unsigned long flags;
- bool wake_ev;
-
- spin_lock_irqsave(&ctx->completion_lock, flags);
- wake_ev = __io_kill_linked_timeout(req);
spin_unlock_irqrestore(&ctx->completion_lock, flags);
- if (wake_ev)
+ if (cancelled) {
io_cqring_ev_posted(ctx);
+ io_put_req(link);
+ }
}
static struct io_kiocb *io_req_link_next(struct io_kiocb *req)
@@ -3532,8 +3547,7 @@
* we return to userspace.
*/
if (req->flags & REQ_F_ISREG) {
- __sb_start_write(file_inode(req->file)->i_sb,
- SB_FREEZE_WRITE, true);
+ sb_start_write(file_inode(req->file)->i_sb);
__sb_writers_release(file_inode(req->file)->i_sb,
SB_FREEZE_WRITE);
}
@@ -4977,8 +4991,10 @@
/* make sure double remove sees this as being gone */
wait->private = NULL;
spin_unlock(&poll->head->lock);
- if (!done)
- __io_async_wake(req, poll, mask, io_poll_task_func);
+ if (!done) {
+ /* use wait func handler, so it matches the rq type */
+ poll->wait.func(&poll->wait, mode, sync, key);
+ }
}
refcount_dec(&req->refs);
return 1;
@@ -6180,7 +6196,6 @@
static void __io_queue_sqe(struct io_kiocb *req, struct io_comp_state *cs)
{
struct io_kiocb *linked_timeout;
- struct io_kiocb *nxt;
const struct cred *old_creds = NULL;
int ret;
@@ -6206,7 +6221,6 @@
*/
if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
if (!io_arm_poll_handler(req)) {
-punt:
/*
* Queued up for async execution, worker will release
* submit reference when the iocb is actually submitted.
@@ -6216,33 +6230,25 @@
if (linked_timeout)
io_queue_linked_timeout(linked_timeout);
- goto exit;
- }
+ } else if (likely(!ret)) {
+ /* drop submission reference */
+ req = io_put_req_find_next(req);
+ if (linked_timeout)
+ io_queue_linked_timeout(linked_timeout);
- if (unlikely(ret)) {
+ if (req) {
+ if (!(req->flags & REQ_F_FORCE_ASYNC))
+ goto again;
+ io_queue_async_work(req);
+ }
+ } else {
/* un-prep timeout, so it'll be killed as any other linked */
req->flags &= ~REQ_F_LINK_TIMEOUT;
req_set_fail_links(req);
io_put_req(req);
io_req_complete(req, ret);
- goto exit;
}
- /* drop submission reference */
- nxt = io_put_req_find_next(req);
- if (linked_timeout)
- io_queue_linked_timeout(linked_timeout);
-
- if (nxt) {
- req = nxt;
-
- if (req->flags & REQ_F_FORCE_ASYNC) {
- linked_timeout = NULL;
- goto punt;
- }
- goto again;
- }
-exit:
if (old_creds)
revert_creds(old_creds);
}
@@ -6266,13 +6272,6 @@
if (unlikely(ret))
goto fail_req;
}
-
- /*
- * Never try inline submit of IOSQE_ASYNC is set, go straight
- * to async execution.
- */
- io_req_init_async(req);
- req->work.flags |= IO_WQ_WORK_CONCURRENT;
io_queue_async_work(req);
} else {
if (sqe) {
@@ -7727,7 +7726,8 @@
xa_init(&tctx->xa);
init_waitqueue_head(&tctx->wait);
tctx->last = NULL;
- tctx->in_idle = 0;
+ atomic_set(&tctx->in_idle, 0);
+ tctx->sqpoll = false;
io_init_identity(&tctx->__identity);
tctx->identity = &tctx->__identity;
task->io_uring = tctx;
@@ -8420,22 +8420,6 @@
return false;
}
-static bool io_match_link_files(struct io_kiocb *req,
- struct files_struct *files)
-{
- struct io_kiocb *link;
-
- if (io_match_files(req, files))
- return true;
- if (req->flags & REQ_F_LINK_HEAD) {
- list_for_each_entry(link, &req->link_list, link_list) {
- if (io_match_files(link, files))
- return true;
- }
- }
- return false;
-}
-
/*
* We're looking to cancel 'req' because it's holding on to our files, but
* 'req' could be a link to another request. See if it is, and cancel that
@@ -8485,7 +8469,21 @@
static bool io_cancel_link_cb(struct io_wq_work *work, void *data)
{
- return io_match_link(container_of(work, struct io_kiocb, work), data);
+ struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+ bool ret;
+
+ if (req->flags & REQ_F_LINK_TIMEOUT) {
+ unsigned long flags;
+ struct io_ring_ctx *ctx = req->ctx;
+
+ /* protect against races with linked timeouts */
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+ ret = io_match_link(req, data);
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+ } else {
+ ret = io_match_link(req, data);
+ }
+ return ret;
}
static void io_attempt_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req)
@@ -8511,6 +8509,7 @@
}
static void io_cancel_defer_files(struct io_ring_ctx *ctx,
+ struct task_struct *task,
struct files_struct *files)
{
struct io_defer_entry *de = NULL;
@@ -8518,7 +8517,8 @@
spin_lock_irq(&ctx->completion_lock);
list_for_each_entry_reverse(de, &ctx->defer_list, list) {
- if (io_match_link_files(de->req, files)) {
+ if (io_task_match(de->req, task) &&
+ io_match_files(de->req, files)) {
list_cut_position(&list, &ctx->defer_list, &de->list);
break;
}
@@ -8544,7 +8544,6 @@
if (list_empty_careful(&ctx->inflight_list))
return false;
- io_cancel_defer_files(ctx, files);
/* cancel all at once, should be faster than doing it one by one*/
io_wq_cancel_cb(ctx->io_wq, io_wq_files_match, files, true);
@@ -8630,8 +8629,16 @@
{
struct task_struct *task = current;
- if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data)
+ if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
task = ctx->sq_data->thread;
+ atomic_inc(&task->io_uring->in_idle);
+ io_sq_thread_park(ctx->sq_data);
+ }
+
+ if (files)
+ io_cancel_defer_files(ctx, NULL, files);
+ else
+ io_cancel_defer_files(ctx, task, NULL);
io_cqring_overflow_flush(ctx, true, task, files);
@@ -8639,12 +8646,23 @@
io_run_task_work();
cond_resched();
}
+
+ if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
+ atomic_dec(&task->io_uring->in_idle);
+ /*
+ * If the files that are going away are the ones in the thread
+ * identity, clear them out.
+ */
+ if (task->io_uring->identity->files == files)
+ task->io_uring->identity->files = NULL;
+ io_sq_thread_unpark(ctx->sq_data);
+ }
}
/*
* Note that this task has used io_uring. We use it for cancelation purposes.
*/
-static int io_uring_add_task_file(struct file *file)
+static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file)
{
struct io_uring_task *tctx = current->io_uring;
@@ -8666,6 +8684,14 @@
tctx->last = file;
}
+ /*
+ * This is race safe in that the task itself is doing this, hence it
+ * cannot be going through the exit/cancel paths at the same time.
+ * This cannot be modified while exit/cancel is running.
+ */
+ if (!tctx->sqpoll && (ctx->flags & IORING_SETUP_SQPOLL))
+ tctx->sqpoll = true;
+
return 0;
}
@@ -8707,7 +8733,7 @@
unsigned long index;
/* make sure overflow events are dropped */
- tctx->in_idle = true;
+ atomic_inc(&tctx->in_idle);
xa_for_each(&tctx->xa, index, file) {
struct io_ring_ctx *ctx = file->private_data;
@@ -8716,6 +8742,35 @@
if (files)
io_uring_del_task_file(file);
}
+
+ atomic_dec(&tctx->in_idle);
+}
+
+static s64 tctx_inflight(struct io_uring_task *tctx)
+{
+ unsigned long index;
+ struct file *file;
+ s64 inflight;
+
+ inflight = percpu_counter_sum(&tctx->inflight);
+ if (!tctx->sqpoll)
+ return inflight;
+
+ /*
+ * If we have SQPOLL rings, then we need to iterate and find them, and
+ * add the pending count for those.
+ */
+ xa_for_each(&tctx->xa, index, file) {
+ struct io_ring_ctx *ctx = file->private_data;
+
+ if (ctx->flags & IORING_SETUP_SQPOLL) {
+ struct io_uring_task *__tctx = ctx->sqo_task->io_uring;
+
+ inflight += percpu_counter_sum(&__tctx->inflight);
+ }
+ }
+
+ return inflight;
}
/*
@@ -8729,11 +8784,11 @@
s64 inflight;
/* make sure overflow events are dropped */
- tctx->in_idle = true;
+ atomic_inc(&tctx->in_idle);
do {
/* read completions before cancelations */
- inflight = percpu_counter_sum(&tctx->inflight);
+ inflight = tctx_inflight(tctx);
if (!inflight)
break;
__io_uring_files_cancel(NULL);
@@ -8744,13 +8799,13 @@
* If we've seen completions, retry. This avoids a race where
* a completion comes in before we did prepare_to_wait().
*/
- if (inflight != percpu_counter_sum(&tctx->inflight))
+ if (inflight != tctx_inflight(tctx))
continue;
schedule();
} while (1);
finish_wait(&tctx->wait, &wait);
- tctx->in_idle = false;
+ atomic_dec(&tctx->in_idle);
}
static int io_uring_flush(struct file *file, void *data)
@@ -8895,7 +8950,7 @@
io_sqpoll_wait_sq(ctx);
submitted = to_submit;
} else if (to_submit) {
- ret = io_uring_add_task_file(f.file);
+ ret = io_uring_add_task_file(ctx, f.file);
if (unlikely(ret))
goto out;
mutex_lock(&ctx->uring_lock);
@@ -8932,7 +8987,8 @@
#ifdef CONFIG_PROC_FS
static int io_uring_show_cred(int id, void *p, void *data)
{
- const struct cred *cred = p;
+ struct io_identity *iod = p;
+ const struct cred *cred = iod->creds;
struct seq_file *m = data;
struct user_namespace *uns = seq_user_ns(m);
struct group_info *gi;
@@ -9124,7 +9180,7 @@
#if defined(CONFIG_UNIX)
ctx->ring_sock->file = file;
#endif
- if (unlikely(io_uring_add_task_file(file))) {
+ if (unlikely(io_uring_add_task_file(ctx, file))) {
file = ERR_PTR(-ENOMEM);
goto err_fd;
}
@@ -9169,6 +9225,7 @@
* to a power-of-two, if it isn't already. We do NOT impose
* any cq vs sq ring sizing.
*/
+ p->cq_entries = roundup_pow_of_two(p->cq_entries);
if (p->cq_entries < p->sq_entries)
return -EINVAL;
if (p->cq_entries > IORING_MAX_CQ_ENTRIES) {
@@ -9176,7 +9233,6 @@
return -EINVAL;
p->cq_entries = IORING_MAX_CQ_ENTRIES;
}
- p->cq_entries = roundup_pow_of_two(p->cq_entries);
} else {
p->cq_entries = 2 * p->sq_entries;
}
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 8180061..10cc797 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1374,6 +1374,7 @@
WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list));
WARN_ON_ONCE(!PageLocked(page));
WARN_ON_ONCE(PageWriteback(page));
+ WARN_ON_ONCE(PageDirty(page));
/*
* We cannot cancel the ioend directly here on error. We may have
@@ -1382,33 +1383,22 @@
* appropriately.
*/
if (unlikely(error)) {
+ /*
+ * Let the filesystem know what portion of the current page
+ * failed to map. If the page wasn't been added to ioend, it
+ * won't be affected by I/O completion and we must unlock it
+ * now.
+ */
+ if (wpc->ops->discard_page)
+ wpc->ops->discard_page(page, file_offset);
if (!count) {
- /*
- * If the current page hasn't been added to ioend, it
- * won't be affected by I/O completions and we must
- * discard and unlock it right here.
- */
- if (wpc->ops->discard_page)
- wpc->ops->discard_page(page);
ClearPageUptodate(page);
unlock_page(page);
goto done;
}
-
- /*
- * If the page was not fully cleaned, we need to ensure that the
- * higher layers come back to it correctly. That means we need
- * to keep the page dirty, and for WB_SYNC_ALL writeback we need
- * to ensure the PAGECACHE_TAG_TOWRITE index mark is not removed
- * so another attempt to write this page in this writeback sweep
- * will be made.
- */
- set_page_writeback_keepwrite(page);
- } else {
- clear_page_dirty_for_io(page);
- set_page_writeback(page);
}
+ set_page_writeback(page);
unlock_page(page);
/*
diff --git a/fs/isofs/rock.h b/fs/isofs/rock.h
index 1558cf2..ee9660e 100644
--- a/fs/isofs/rock.h
+++ b/fs/isofs/rock.h
@@ -22,7 +22,7 @@
__u8 len_des;
__u8 len_src;
__u8 ext_ver;
- __u8 data[0];
+ __u8 data[];
} __attribute__ ((packed));
struct RR_RR_s {
@@ -44,7 +44,7 @@
struct SL_component {
__u8 flags;
__u8 len;
- __u8 text[0];
+ __u8 text[];
} __attribute__ ((packed));
struct RR_SL_s {
@@ -54,7 +54,7 @@
struct RR_NM_s {
__u8 flags;
- char name[0];
+ char name[];
} __attribute__ ((packed));
struct RR_CL_s {
@@ -71,7 +71,7 @@
struct RR_TF_s {
__u8 flags;
- struct stamp times[0]; /* Variable number of these beasts */
+ struct stamp times[]; /* Variable number of these beasts */
} __attribute__ ((packed));
/* Linux-specific extension for transparent decompression */
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 263f02a..472932b 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -106,6 +106,8 @@
* for a checkpoint to free up some space in the log.
*/
void __jbd2_log_wait_for_space(journal_t *journal)
+__acquires(&journal->j_state_lock)
+__releases(&journal->j_state_lock)
{
int nblocks, space_left;
/* assert_spin_locked(&journal->j_state_lock); */
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index fa688e1..b121d7d 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -450,6 +450,15 @@
schedule();
write_lock(&journal->j_state_lock);
finish_wait(&journal->j_fc_wait, &wait);
+ /*
+ * TODO: by blocking fast commits here, we are increasing
+ * fsync() latency slightly. Strictly speaking, we don't need
+ * to block fast commits until the transaction enters T_FLUSH
+ * state. So an optimization is possible where we block new fast
+ * commits here and wait for existing ones to complete
+ * just before we enter T_FLUSH. That way, the existing fast
+ * commits and this full commit can proceed parallely.
+ */
}
write_unlock(&journal->j_state_lock);
@@ -801,7 +810,7 @@
if (first_block < journal->j_tail)
freed += journal->j_last - journal->j_first;
/* Update tail only if we free significant amount of space */
- if (freed < journal->j_maxlen / 4)
+ if (freed < jbd2_journal_get_max_txn_bufs(journal))
update_tail = 0;
}
J_ASSERT(commit_transaction->t_state == T_COMMIT);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 0c7c42b..0c3d5e3 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -727,6 +727,8 @@
*/
int jbd2_fc_begin_commit(journal_t *journal, tid_t tid)
{
+ if (unlikely(is_journal_aborted(journal)))
+ return -EIO;
/*
* Fast commits only allowed if at least one full commit has
* been processed.
@@ -734,10 +736,12 @@
if (!journal->j_stats.ts_tid)
return -EINVAL;
- if (tid <= journal->j_commit_sequence)
- return -EALREADY;
-
write_lock(&journal->j_state_lock);
+ if (tid <= journal->j_commit_sequence) {
+ write_unlock(&journal->j_state_lock);
+ return -EALREADY;
+ }
+
if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
(journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) {
DEFINE_WAIT(wait);
@@ -777,13 +781,19 @@
int jbd2_fc_end_commit(journal_t *journal)
{
- return __jbd2_fc_end_commit(journal, 0, 0);
+ return __jbd2_fc_end_commit(journal, 0, false);
}
EXPORT_SYMBOL(jbd2_fc_end_commit);
-int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid)
+int jbd2_fc_end_commit_fallback(journal_t *journal)
{
- return __jbd2_fc_end_commit(journal, tid, 1);
+ tid_t tid;
+
+ read_lock(&journal->j_state_lock);
+ tid = journal->j_running_transaction ?
+ journal->j_running_transaction->t_tid : 0;
+ read_unlock(&journal->j_state_lock);
+ return __jbd2_fc_end_commit(journal, tid, true);
}
EXPORT_SYMBOL(jbd2_fc_end_commit_fallback);
@@ -865,7 +875,6 @@
int fc_off;
*bh_out = NULL;
- write_lock(&journal->j_state_lock);
if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) {
fc_off = journal->j_fc_off;
@@ -874,7 +883,6 @@
} else {
ret = -EINVAL;
}
- write_unlock(&journal->j_state_lock);
if (ret)
return ret;
@@ -887,11 +895,7 @@
if (!bh)
return -ENOMEM;
- lock_buffer(bh);
- clear_buffer_uptodate(bh);
- set_buffer_dirty(bh);
- unlock_buffer(bh);
journal->j_fc_wbuf[fc_off] = bh;
*bh_out = bh;
@@ -909,9 +913,7 @@
struct buffer_head *bh;
int i, j_fc_off;
- read_lock(&journal->j_state_lock);
j_fc_off = journal->j_fc_off;
- read_unlock(&journal->j_state_lock);
/*
* Wait in reverse order to minimize chances of us being woken up before
@@ -939,9 +941,7 @@
struct buffer_head *bh;
int i, j_fc_off;
- read_lock(&journal->j_state_lock);
j_fc_off = journal->j_fc_off;
- read_unlock(&journal->j_state_lock);
/*
* Wait in reverse order to minimize chances of us being woken up before
@@ -1348,23 +1348,16 @@
journal->j_dev = bdev;
journal->j_fs_dev = fs_dev;
journal->j_blk_offset = start;
- journal->j_maxlen = len;
+ journal->j_total_len = len;
/* We need enough buffers to write out full descriptor block. */
n = journal->j_blocksize / jbd2_min_tag_size();
journal->j_wbufsize = n;
+ journal->j_fc_wbuf = NULL;
journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *),
GFP_KERNEL);
if (!journal->j_wbuf)
goto err_cleanup;
- if (journal->j_fc_wbufsize > 0) {
- journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize,
- sizeof(struct buffer_head *),
- GFP_KERNEL);
- if (!journal->j_fc_wbuf)
- goto err_cleanup;
- }
-
bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize);
if (!bh) {
pr_err("%s: Cannot get buffer for journal superblock\n",
@@ -1378,23 +1371,11 @@
err_cleanup:
kfree(journal->j_wbuf);
- kfree(journal->j_fc_wbuf);
jbd2_journal_destroy_revoke(journal);
kfree(journal);
return NULL;
}
-int jbd2_fc_init(journal_t *journal, int num_fc_blks)
-{
- journal->j_fc_wbufsize = num_fc_blks;
- journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize,
- sizeof(struct buffer_head *), GFP_KERNEL);
- if (!journal->j_fc_wbuf)
- return -ENOMEM;
- return 0;
-}
-EXPORT_SYMBOL(jbd2_fc_init);
-
/* jbd2_journal_init_dev and jbd2_journal_init_inode:
*
* Create a journal structure assigned some fixed set of disk blocks to
@@ -1512,16 +1493,7 @@
}
journal->j_first = first;
-
- if (jbd2_has_feature_fast_commit(journal) &&
- journal->j_fc_wbufsize > 0) {
- journal->j_fc_last = last;
- journal->j_last = last - journal->j_fc_wbufsize;
- journal->j_fc_first = journal->j_last + 1;
- journal->j_fc_off = 0;
- } else {
- journal->j_last = last;
- }
+ journal->j_last = last;
journal->j_head = journal->j_first;
journal->j_tail = journal->j_first;
@@ -1531,7 +1503,14 @@
journal->j_commit_sequence = journal->j_transaction_sequence - 1;
journal->j_commit_request = journal->j_commit_sequence;
- journal->j_max_transaction_buffers = journal->j_maxlen / 4;
+ journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal);
+
+ /*
+ * Now that journal recovery is done, turn fast commits off here. This
+ * way, if fast commit was enabled before the crash but if now FS has
+ * disabled it, we don't enable fast commits.
+ */
+ jbd2_clear_feature_fast_commit(journal);
/*
* As a special case, if the on-disk copy is already marked as needing
@@ -1792,15 +1771,15 @@
goto out;
}
- if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen)
- journal->j_maxlen = be32_to_cpu(sb->s_maxlen);
- else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) {
+ if (be32_to_cpu(sb->s_maxlen) < journal->j_total_len)
+ journal->j_total_len = be32_to_cpu(sb->s_maxlen);
+ else if (be32_to_cpu(sb->s_maxlen) > journal->j_total_len) {
printk(KERN_WARNING "JBD2: journal file too short\n");
goto out;
}
if (be32_to_cpu(sb->s_first) == 0 ||
- be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
+ be32_to_cpu(sb->s_first) >= journal->j_total_len) {
printk(KERN_WARNING
"JBD2: Invalid start block of journal: %u\n",
be32_to_cpu(sb->s_first));
@@ -1872,6 +1851,7 @@
{
int err;
journal_superblock_t *sb;
+ int num_fc_blocks;
err = journal_get_superblock(journal);
if (err)
@@ -1883,15 +1863,17 @@
journal->j_tail = be32_to_cpu(sb->s_start);
journal->j_first = be32_to_cpu(sb->s_first);
journal->j_errno = be32_to_cpu(sb->s_errno);
+ journal->j_last = be32_to_cpu(sb->s_maxlen);
- if (jbd2_has_feature_fast_commit(journal) &&
- journal->j_fc_wbufsize > 0) {
+ if (jbd2_has_feature_fast_commit(journal)) {
journal->j_fc_last = be32_to_cpu(sb->s_maxlen);
- journal->j_last = journal->j_fc_last - journal->j_fc_wbufsize;
+ num_fc_blocks = be32_to_cpu(sb->s_num_fc_blks);
+ if (!num_fc_blocks)
+ num_fc_blocks = JBD2_MIN_FC_BLOCKS;
+ if (journal->j_last - num_fc_blocks >= JBD2_MIN_JOURNAL_BLOCKS)
+ journal->j_last = journal->j_fc_last - num_fc_blocks;
journal->j_fc_first = journal->j_last + 1;
journal->j_fc_off = 0;
- } else {
- journal->j_last = be32_to_cpu(sb->s_maxlen);
}
return 0;
@@ -1954,9 +1936,6 @@
*/
journal->j_flags &= ~JBD2_ABORT;
- if (journal->j_fc_wbufsize > 0)
- jbd2_journal_set_features(journal, 0, 0,
- JBD2_FEATURE_INCOMPAT_FAST_COMMIT);
/* OK, we've finished with the dynamic journal bits:
* reinitialise the dynamic contents of the superblock in memory
* and reset them on disk. */
@@ -2040,8 +2019,7 @@
jbd2_journal_destroy_revoke(journal);
if (journal->j_chksum_driver)
crypto_free_shash(journal->j_chksum_driver);
- if (journal->j_fc_wbufsize > 0)
- kfree(journal->j_fc_wbuf);
+ kfree(journal->j_fc_wbuf);
kfree(journal->j_wbuf);
kfree(journal);
@@ -2116,6 +2094,37 @@
return 0;
}
+static int
+jbd2_journal_initialize_fast_commit(journal_t *journal)
+{
+ journal_superblock_t *sb = journal->j_superblock;
+ unsigned long long num_fc_blks;
+
+ num_fc_blks = be32_to_cpu(sb->s_num_fc_blks);
+ if (num_fc_blks == 0)
+ num_fc_blks = JBD2_MIN_FC_BLOCKS;
+ if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS)
+ return -ENOSPC;
+
+ /* Are we called twice? */
+ WARN_ON(journal->j_fc_wbuf != NULL);
+ journal->j_fc_wbuf = kmalloc_array(num_fc_blks,
+ sizeof(struct buffer_head *), GFP_KERNEL);
+ if (!journal->j_fc_wbuf)
+ return -ENOMEM;
+
+ journal->j_fc_wbufsize = num_fc_blks;
+ journal->j_fc_last = journal->j_last;
+ journal->j_last = journal->j_fc_last - num_fc_blks;
+ journal->j_fc_first = journal->j_last + 1;
+ journal->j_fc_off = 0;
+ journal->j_free = journal->j_last - journal->j_first;
+ journal->j_max_transaction_buffers =
+ jbd2_journal_get_max_txn_bufs(journal);
+
+ return 0;
+}
+
/**
* int jbd2_journal_set_features() - Mark a given journal feature in the superblock
* @journal: Journal to act on.
@@ -2159,6 +2168,13 @@
sb = journal->j_superblock;
+ if (incompat & JBD2_FEATURE_INCOMPAT_FAST_COMMIT) {
+ if (jbd2_journal_initialize_fast_commit(journal)) {
+ pr_err("JBD2: Cannot enable fast commits.\n");
+ return 0;
+ }
+ }
+
/* Load the checksum driver if necessary */
if ((journal->j_chksum_driver == NULL) &&
INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index eb26061..dc0694f 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -74,8 +74,8 @@
/* Do up to 128K of readahead */
max = start + (128 * 1024 / journal->j_blocksize);
- if (max > journal->j_maxlen)
- max = journal->j_maxlen;
+ if (max > journal->j_total_len)
+ max = journal->j_total_len;
/* Do the readahead itself. We'll submit MAXBUF buffer_heads at
* a time to the block device IO layer. */
@@ -134,7 +134,7 @@
*bhp = NULL;
- if (offset >= journal->j_maxlen) {
+ if (offset >= journal->j_total_len) {
printk(KERN_ERR "JBD2: corrupted journal superblock\n");
return -EFSCORRUPTED;
}
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 4398573..d54f046 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -195,8 +195,10 @@
DEFINE_WAIT(wait);
if (WARN_ON(!journal->j_running_transaction ||
- journal->j_running_transaction->t_state != T_SWITCH))
+ journal->j_running_transaction->t_state != T_SWITCH)) {
+ read_unlock(&journal->j_state_lock);
return;
+ }
prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
TASK_UNINTERRUPTIBLE);
read_unlock(&journal->j_state_lock);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index cb52db9..4e011ad 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -955,7 +955,6 @@
static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
{
- struct inode *inode = file_inode(filp);
struct nfs_open_dir_context *dir_ctx = filp->private_data;
dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n",
@@ -967,15 +966,15 @@
case SEEK_SET:
if (offset < 0)
return -EINVAL;
- inode_lock(inode);
+ spin_lock(&filp->f_lock);
break;
case SEEK_CUR:
if (offset == 0)
return filp->f_pos;
- inode_lock(inode);
+ spin_lock(&filp->f_lock);
offset += filp->f_pos;
if (offset < 0) {
- inode_unlock(inode);
+ spin_unlock(&filp->f_lock);
return -EINVAL;
}
}
@@ -987,7 +986,7 @@
dir_ctx->dir_cookie = 0;
dir_ctx->duped = 0;
}
- inode_unlock(inode);
+ spin_unlock(&filp->f_lock);
return offset;
}
@@ -998,13 +997,9 @@
static int nfs_fsync_dir(struct file *filp, loff_t start, loff_t end,
int datasync)
{
- struct inode *inode = file_inode(filp);
-
dfprintk(FILE, "NFS: fsync dir(%pD2) datasync %d\n", filp, datasync);
- inode_lock(inode);
- nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
- inode_unlock(inode);
+ nfs_inc_stats(file_inode(filp), NFSIOS_VFSFSYNC);
return 0;
}
diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c
index b51424f..6c2ce79 100644
--- a/fs/nfs/nfs42xattr.c
+++ b/fs/nfs/nfs42xattr.c
@@ -1047,8 +1047,10 @@
void nfs4_xattr_cache_exit(void)
{
+ unregister_shrinker(&nfs4_xattr_large_entry_shrinker);
unregister_shrinker(&nfs4_xattr_entry_shrinker);
unregister_shrinker(&nfs4_xattr_cache_shrinker);
+ list_lru_destroy(&nfs4_xattr_large_entry_lru);
list_lru_destroy(&nfs4_xattr_entry_lru);
list_lru_destroy(&nfs4_xattr_cache_lru);
kmem_cache_destroy(nfs4_xattr_cache_cachep);
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 0dc31ad..6e060a8 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -196,7 +196,7 @@
1 + nfs4_xattr_name_maxsz + 1)
#define decode_setxattr_maxsz (op_decode_hdr_maxsz + decode_change_info_maxsz)
#define encode_listxattrs_maxsz (op_encode_hdr_maxsz + 2 + 1)
-#define decode_listxattrs_maxsz (op_decode_hdr_maxsz + 2 + 1 + 1)
+#define decode_listxattrs_maxsz (op_decode_hdr_maxsz + 2 + 1 + 1 + 1)
#define encode_removexattr_maxsz (op_encode_hdr_maxsz + 1 + \
nfs4_xattr_name_maxsz)
#define decode_removexattr_maxsz (op_decode_hdr_maxsz + \
@@ -531,7 +531,7 @@
{
__be32 *p;
- encode_op_hdr(xdr, OP_LISTXATTRS, decode_listxattrs_maxsz + 1, hdr);
+ encode_op_hdr(xdr, OP_LISTXATTRS, decode_listxattrs_maxsz, hdr);
p = reserve_space(xdr, 12);
if (unlikely(!p))
diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c
index 8d32788..fa14830 100644
--- a/fs/nfs/nfsroot.c
+++ b/fs/nfs/nfsroot.c
@@ -88,7 +88,13 @@
#define NFS_ROOT "/tftpboot/%s"
/* Default NFSROOT mount options. */
+#if defined(CONFIG_NFS_V2)
#define NFS_DEF_OPTIONS "vers=2,tcp,rsize=4096,wsize=4096"
+#elif defined(CONFIG_NFS_V3)
+#define NFS_DEF_OPTIONS "vers=3,tcp,rsize=4096,wsize=4096"
+#else
+#define NFS_DEF_OPTIONS "vers=4,tcp,rsize=4096,wsize=4096"
+#endif
/* Parameters passed from the kernel command line */
static char nfs_root_parms[NFS_MAXPATHLEN + 1] __initdata = "";
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 1446861..a633044 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -316,10 +316,6 @@
fh_copy(&resp->dirfh, &argp->fh);
fh_init(&resp->fh, NFS3_FHSIZE);
- if (argp->ftype == 0 || argp->ftype >= NF3BAD) {
- resp->status = nfserr_inval;
- goto out;
- }
if (argp->ftype == NF3CHR || argp->ftype == NF3BLK) {
rdev = MKDEV(argp->major, argp->minor);
if (MAJOR(rdev) != argp->major ||
@@ -328,7 +324,7 @@
goto out;
}
} else if (argp->ftype != NF3SOCK && argp->ftype != NF3FIFO) {
- resp->status = nfserr_inval;
+ resp->status = nfserr_badtype;
goto out;
}
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 9c23b6a..2277f83 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -1114,6 +1114,7 @@
{
struct nfsd3_pathconfres *resp = rqstp->rq_resp;
+ *p++ = resp->status;
*p++ = xdr_zero; /* no post_op_attr */
if (resp->status == 0) {
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index ad2fa1a..e83b217 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1299,7 +1299,7 @@
struct nfsd_file *dst)
{
nfs42_ssc_close(src->nf_file);
- nfsd_file_put(src);
+ /* 'src' is freed by nfsd4_do_async_copy */
nfsd_file_put(dst);
mntput(ss_mnt);
}
@@ -1486,6 +1486,7 @@
cb_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL);
if (!cb_copy)
goto out;
+ refcount_set(&cb_copy->refcount, 1);
memcpy(&cb_copy->cp_res, ©->cp_res, sizeof(copy->cp_res));
cb_copy->cp_clp = copy->cp_clp;
cb_copy->nfserr = copy->nfserr;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index b9a9d69..db52e84 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -877,7 +877,7 @@
goto done;
}
- trace_ocfs2_journal_init_maxlen(j_journal->j_maxlen);
+ trace_ocfs2_journal_init_maxlen(j_journal->j_total_len);
*dirty = (le32_to_cpu(di->id1.journal1.ij_flags) &
OCFS2_JOURNAL_DIRTY_FL);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 1d91dd1..2febc76 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1713,6 +1713,7 @@
oi->ip_blkno = 0ULL;
oi->ip_clusters = 0;
+ oi->ip_next_orphan = NULL;
ocfs2_resv_init_once(&oi->ip_la_data_resv);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 0f70700..b362523 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1049,6 +1049,8 @@
oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
OOM_SCORE_ADJ_MAX;
put_task_struct(task);
+ if (oom_adj > OOM_ADJUST_MAX)
+ oom_adj = OOM_ADJUST_MAX;
len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj);
return simple_read_from_buffer(buf, count, ppos, buffer, len);
}
diff --git a/fs/proc/cpuinfo.c b/fs/proc/cpuinfo.c
index d0989a4..419760f 100644
--- a/fs/proc/cpuinfo.c
+++ b/fs/proc/cpuinfo.c
@@ -19,7 +19,7 @@
static const struct proc_ops cpuinfo_proc_ops = {
.proc_flags = PROC_ENTRY_PERMANENT,
.proc_open = cpuinfo_open,
- .proc_read = seq_read,
+ .proc_read_iter = seq_read_iter,
.proc_lseek = seq_lseek,
.proc_release = seq_release,
};
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 2f9fa17..b846632 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -590,7 +590,7 @@
static const struct proc_ops proc_seq_ops = {
/* not permanent -- can call into arbitrary seq_operations */
.proc_open = proc_seq_open,
- .proc_read = seq_read,
+ .proc_read_iter = seq_read_iter,
.proc_lseek = seq_lseek,
.proc_release = proc_seq_release,
};
@@ -621,7 +621,7 @@
static const struct proc_ops proc_single_ops = {
/* not permanent -- can call into arbitrary ->single_show */
.proc_open = proc_single_open,
- .proc_read = seq_read,
+ .proc_read_iter = seq_read_iter,
.proc_lseek = seq_lseek,
.proc_release = single_release,
};
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 58c075e..bde6b6f 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -597,6 +597,7 @@
.llseek = proc_reg_llseek,
.read_iter = proc_reg_read_iter,
.write = proc_reg_write,
+ .splice_read = generic_file_splice_read,
.poll = proc_reg_poll,
.unlocked_ioctl = proc_reg_unlocked_ioctl,
.mmap = proc_reg_mmap,
@@ -622,6 +623,7 @@
static const struct file_operations proc_iter_file_ops_compat = {
.llseek = proc_reg_llseek,
.read_iter = proc_reg_read_iter,
+ .splice_read = generic_file_splice_read,
.write = proc_reg_write,
.poll = proc_reg_poll,
.unlocked_ioctl = proc_reg_unlocked_ioctl,
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 46b3293..4695b6d 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -226,7 +226,7 @@
static const struct proc_ops stat_proc_ops = {
.proc_flags = PROC_ENTRY_PERMANENT,
.proc_open = stat_open,
- .proc_read = seq_read,
+ .proc_read_iter = seq_read_iter,
.proc_lseek = seq_lseek,
.proc_release = single_release,
};
diff --git a/fs/select.c b/fs/select.c
index 7aef495..ebfebdf 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -97,7 +97,7 @@
struct poll_table_page {
struct poll_table_page * next;
struct poll_table_entry * entry;
- struct poll_table_entry entries[0];
+ struct poll_table_entry entries[];
};
#define POLL_TABLE_FULL(table) \
@@ -836,7 +836,7 @@
struct poll_list {
struct poll_list *next;
int len;
- struct pollfd entries[0];
+ struct pollfd entries[];
};
#define POLLFD_PER_PAGE ((PAGE_SIZE-sizeof(struct poll_list)) / sizeof(struct pollfd))
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 31219c1..3b20e21 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -18,6 +18,7 @@
#include <linux/mm.h>
#include <linux/printk.h>
#include <linux/string_helpers.h>
+#include <linux/uio.h>
#include <linux/uaccess.h>
#include <asm/page.h>
@@ -146,7 +147,28 @@
*/
ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
{
- struct seq_file *m = file->private_data;
+ struct iovec iov = { .iov_base = buf, .iov_len = size};
+ struct kiocb kiocb;
+ struct iov_iter iter;
+ ssize_t ret;
+
+ init_sync_kiocb(&kiocb, file);
+ iov_iter_init(&iter, READ, &iov, 1, size);
+
+ kiocb.ki_pos = *ppos;
+ ret = seq_read_iter(&kiocb, &iter);
+ *ppos = kiocb.ki_pos;
+ return ret;
+}
+EXPORT_SYMBOL(seq_read);
+
+/*
+ * Ready-made ->f_op->read_iter()
+ */
+ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+ struct seq_file *m = iocb->ki_filp->private_data;
+ size_t size = iov_iter_count(iter);
size_t copied = 0;
size_t n;
void *p;
@@ -158,14 +180,14 @@
* if request is to read from zero offset, reset iterator to first
* record as it might have been already advanced by previous requests
*/
- if (*ppos == 0) {
+ if (iocb->ki_pos == 0) {
m->index = 0;
m->count = 0;
}
- /* Don't assume *ppos is where we left it */
- if (unlikely(*ppos != m->read_pos)) {
- while ((err = traverse(m, *ppos)) == -EAGAIN)
+ /* Don't assume ki_pos is where we left it */
+ if (unlikely(iocb->ki_pos != m->read_pos)) {
+ while ((err = traverse(m, iocb->ki_pos)) == -EAGAIN)
;
if (err) {
/* With prejudice... */
@@ -174,7 +196,7 @@
m->count = 0;
goto Done;
} else {
- m->read_pos = *ppos;
+ m->read_pos = iocb->ki_pos;
}
}
@@ -187,13 +209,11 @@
/* if not empty - flush it first */
if (m->count) {
n = min(m->count, size);
- err = copy_to_user(buf, m->buf + m->from, n);
- if (err)
+ if (copy_to_iter(m->buf + m->from, n, iter) != n)
goto Efault;
m->count -= n;
m->from += n;
size -= n;
- buf += n;
copied += n;
if (!size)
goto Done;
@@ -254,8 +274,7 @@
}
m->op->stop(m, p);
n = min(m->count, size);
- err = copy_to_user(buf, m->buf, n);
- if (err)
+ if (copy_to_iter(m->buf, n, iter) != n)
goto Efault;
copied += n;
m->count -= n;
@@ -264,7 +283,7 @@
if (!copied)
copied = err;
else {
- *ppos += copied;
+ iocb->ki_pos += copied;
m->read_pos += copied;
}
mutex_unlock(&m->lock);
@@ -276,7 +295,7 @@
err = -EFAULT;
goto Done;
}
-EXPORT_SYMBOL(seq_read);
+EXPORT_SYMBOL(seq_read_iter);
/**
* seq_lseek - ->llseek() method for sequential files.
diff --git a/fs/super.c b/fs/super.c
index a51c208..98bb062 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1631,55 +1631,6 @@
}
EXPORT_SYMBOL(super_setup_bdi);
-/*
- * This is an internal function, please use sb_end_{write,pagefault,intwrite}
- * instead.
- */
-void __sb_end_write(struct super_block *sb, int level)
-{
- percpu_up_read(sb->s_writers.rw_sem + level-1);
-}
-EXPORT_SYMBOL(__sb_end_write);
-
-/*
- * This is an internal function, please use sb_start_{write,pagefault,intwrite}
- * instead.
- */
-int __sb_start_write(struct super_block *sb, int level, bool wait)
-{
- bool force_trylock = false;
- int ret = 1;
-
-#ifdef CONFIG_LOCKDEP
- /*
- * We want lockdep to tell us about possible deadlocks with freezing
- * but it's it bit tricky to properly instrument it. Getting a freeze
- * protection works as getting a read lock but there are subtle
- * problems. XFS for example gets freeze protection on internal level
- * twice in some cases, which is OK only because we already hold a
- * freeze protection also on higher level. Due to these cases we have
- * to use wait == F (trylock mode) which must not fail.
- */
- if (wait) {
- int i;
-
- for (i = 0; i < level - 1; i++)
- if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) {
- force_trylock = true;
- break;
- }
- }
-#endif
- if (wait && !force_trylock)
- percpu_down_read(sb->s_writers.rw_sem + level-1);
- else
- ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1);
-
- WARN_ON(force_trylock && !ret);
- return ret;
-}
-EXPORT_SYMBOL(__sb_start_write);
-
/**
* sb_wait_write - wait until all writers to given file system finish
* @sb: the super for which we wait
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 852b536..1564001 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2467,6 +2467,7 @@
new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno);
new->xefi_blockcount = 1;
new->xefi_oinfo = *oinfo;
+ new->xefi_skip_discard = false;
trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index e1bd484..6747e97 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -52,9 +52,9 @@
{
xfs_fsblock_t xefi_startblock;/* starting fs block number */
xfs_extlen_t xefi_blockcount;/* number of blocks in extent */
+ bool xefi_skip_discard;
struct list_head xefi_list;
struct xfs_owner_info xefi_oinfo; /* extent owner */
- bool xefi_skip_discard;
};
#define XFS_BMAP_MAX_NMAP 4
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 340c83f..2668ebe 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -1514,7 +1514,7 @@
* record for our insertion point. This will also give us the record for
* start block contiguity tests.
*/
- error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, flags,
+ error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, oldext,
&PREV, &i);
if (error)
goto done;
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index beb81c8..577a663 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -243,8 +243,8 @@
else if (y > x)
return -1;
- x = XFS_RMAP_OFF(be64_to_cpu(kp->rm_offset));
- y = rec->rm_offset;
+ x = be64_to_cpu(kp->rm_offset);
+ y = xfs_rmap_irec_offset_pack(rec);
if (x > y)
return 1;
else if (y > x)
@@ -275,8 +275,8 @@
else if (y > x)
return -1;
- x = XFS_RMAP_OFF(be64_to_cpu(kp1->rm_offset));
- y = XFS_RMAP_OFF(be64_to_cpu(kp2->rm_offset));
+ x = be64_to_cpu(kp1->rm_offset);
+ y = be64_to_cpu(kp2->rm_offset);
if (x > y)
return 1;
else if (y > x)
@@ -390,8 +390,8 @@
return 1;
else if (a > b)
return 0;
- a = XFS_RMAP_OFF(be64_to_cpu(k1->rmap.rm_offset));
- b = XFS_RMAP_OFF(be64_to_cpu(k2->rmap.rm_offset));
+ a = be64_to_cpu(k1->rmap.rm_offset);
+ b = be64_to_cpu(k2->rmap.rm_offset);
if (a <= b)
return 1;
return 0;
@@ -420,8 +420,8 @@
return 1;
else if (a > b)
return 0;
- a = XFS_RMAP_OFF(be64_to_cpu(r1->rmap.rm_offset));
- b = XFS_RMAP_OFF(be64_to_cpu(r2->rmap.rm_offset));
+ a = be64_to_cpu(r1->rmap.rm_offset);
+ b = be64_to_cpu(r2->rmap.rm_offset);
if (a <= b)
return 1;
return 0;
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 955302e..412e2ec 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -113,6 +113,8 @@
if (info->whichfork == XFS_ATTR_FORK)
rflags |= XFS_RMAP_ATTR_FORK;
+ if (irec->br_state == XFS_EXT_UNWRITTEN)
+ rflags |= XFS_RMAP_UNWRITTEN;
/*
* CoW staging extents are owned (on disk) by the refcountbt, so
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 3aa85b6..bb25ff1 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -121,8 +121,7 @@
goto bad;
/* rt flags require rt device */
- if ((flags & (XFS_DIFLAG_REALTIME | XFS_DIFLAG_RTINHERIT)) &&
- !mp->m_rtdev_targp)
+ if ((flags & XFS_DIFLAG_REALTIME) && !mp->m_rtdev_targp)
goto bad;
/* new rt bitmap flag only valid for rbmino */
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index beaeb6f..dd672e6 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -170,7 +170,6 @@
*/
INIT_LIST_HEAD(&worklist);
rbno = NULLAGBLOCK;
- nr = 1;
/* Make sure the fragments actually /are/ in agbno order. */
bno = 0;
@@ -184,15 +183,14 @@
* Find all the rmaps that start at or before the refc extent,
* and put them on the worklist.
*/
+ nr = 0;
list_for_each_entry_safe(frag, n, &refchk->fragments, list) {
- if (frag->rm.rm_startblock > refchk->bno)
- goto done;
+ if (frag->rm.rm_startblock > refchk->bno || nr > target_nr)
+ break;
bno = frag->rm.rm_startblock + frag->rm.rm_blockcount;
if (bno < rbno)
rbno = bno;
list_move_tail(&frag->list, &worklist);
- if (nr == target_nr)
- break;
nr++;
}
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 55d126d..4304c64 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -346,8 +346,8 @@
ssize_t count = i_blocksize(inode);
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + count);
- xfs_fileoff_t cow_fsb = NULLFILEOFF;
- int whichfork = XFS_DATA_FORK;
+ xfs_fileoff_t cow_fsb;
+ int whichfork;
struct xfs_bmbt_irec imap;
struct xfs_iext_cursor icur;
int retries = 0;
@@ -381,6 +381,8 @@
* landed in a hole and we skip the block.
*/
retry:
+ cow_fsb = NULLFILEOFF;
+ whichfork = XFS_DATA_FORK;
xfs_ilock(ip, XFS_ILOCK_SHARED);
ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
(ip->i_df.if_flags & XFS_IFEXTENTS));
@@ -527,13 +529,15 @@
*/
static void
xfs_discard_page(
- struct page *page)
+ struct page *page,
+ loff_t fileoff)
{
struct inode *inode = page->mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
- loff_t offset = page_offset(page);
- xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, offset);
+ unsigned int pageoff = offset_in_page(fileoff);
+ xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, fileoff);
+ xfs_fileoff_t pageoff_fsb = XFS_B_TO_FSBT(mp, pageoff);
int error;
if (XFS_FORCED_SHUTDOWN(mp))
@@ -541,14 +545,14 @@
xfs_alert_ratelimited(mp,
"page discard on page "PTR_FMT", inode 0x%llx, offset %llu.",
- page, ip->i_ino, offset);
+ page, ip->i_ino, fileoff);
error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
- i_blocks_per_page(inode, page));
+ i_blocks_per_page(inode, page) - pageoff_fsb);
if (error && !XFS_FORCED_SHUTDOWN(mp))
xfs_alert(mp, "page discard unable to remove delalloc mapping.");
out_invalidate:
- iomap_invalidatepage(page, 0, PAGE_SIZE);
+ iomap_invalidatepage(page, pageoff, PAGE_SIZE - pageoff);
}
static const struct iomap_writeback_ops xfs_writeback_ops = {
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 5e16545..1414ab7 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -911,6 +911,16 @@
error = iomap_zero_range(inode, oldsize, newsize - oldsize,
&did_zeroing, &xfs_buffered_write_iomap_ops);
} else {
+ /*
+ * iomap won't detect a dirty page over an unwritten block (or a
+ * cow block over a hole) and subsequently skips zeroing the
+ * newly post-EOF portion of the page. Flush the new EOF to
+ * convert the block before the pagecache truncate.
+ */
+ error = filemap_write_and_wait_range(inode->i_mapping, newsize,
+ newsize);
+ if (error)
+ return error;
error = iomap_truncate_page(inode, newsize, &did_zeroing,
&xfs_buffered_write_iomap_ops);
}
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index b101feb..f3082a9 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -134,7 +134,7 @@
goto out_unlock;
error = invalidate_inode_pages2(inode->i_mapping);
if (WARN_ON_ONCE(error))
- return error;
+ goto out_unlock;
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 16098dc..6fa05fb 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1502,7 +1502,8 @@
&xfs_buffered_write_iomap_ops);
if (error)
goto out;
- error = filemap_write_and_wait(inode->i_mapping);
+
+ error = filemap_write_and_wait_range(inode->i_mapping, offset, len);
if (error)
goto out;
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 798027b..640f094 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -13,6 +13,7 @@
#ifndef __ASSEMBLY__
+#include <linux/compiler.h>
#include <asm/rwonce.h>
#ifndef nop
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 35e4a53..6432a7f 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -114,21 +114,21 @@
#define __this_cpu_generic_read_nopreempt(pcp) \
({ \
- typeof(pcp) __ret; \
+ typeof(pcp) ___ret; \
preempt_disable_notrace(); \
- __ret = READ_ONCE(*raw_cpu_ptr(&(pcp))); \
+ ___ret = READ_ONCE(*raw_cpu_ptr(&(pcp))); \
preempt_enable_notrace(); \
- __ret; \
+ ___ret; \
})
#define __this_cpu_generic_read_noirq(pcp) \
({ \
- typeof(pcp) __ret; \
- unsigned long __flags; \
- raw_local_irq_save(__flags); \
- __ret = raw_cpu_generic_read(pcp); \
- raw_local_irq_restore(__flags); \
- __ret; \
+ typeof(pcp) ___ret; \
+ unsigned long ___flags; \
+ raw_local_irq_save(___flags); \
+ ___ret = raw_cpu_generic_read(pcp); \
+ raw_local_irq_restore(___flags); \
+ ___ret; \
})
#define this_cpu_generic_read(pcp) \
diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h
index 45f9872..4973328 100644
--- a/include/asm-generic/uaccess.h
+++ b/include/asm-generic/uaccess.h
@@ -12,7 +12,8 @@
#ifdef CONFIG_UACCESS_MEMCPY
#include <asm/unaligned.h>
-static inline int __get_user_fn(size_t size, const void __user *from, void *to)
+static __always_inline int
+__get_user_fn(size_t size, const void __user *from, void *to)
{
BUILD_BUG_ON(!__builtin_constant_p(size));
@@ -37,7 +38,8 @@
}
#define __get_user_fn(sz, u, k) __get_user_fn(sz, u, k)
-static inline int __put_user_fn(size_t size, void __user *to, void *from)
+static __always_inline int
+__put_user_fn(size_t size, void __user *to, void *from)
{
BUILD_BUG_ON(!__builtin_constant_p(size));
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index cd14444..b2b3d81 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -701,6 +701,7 @@
#ifdef CONFIG_CONSTRUCTORS
#define KERNEL_CTORS() . = ALIGN(8); \
__ctors_start = .; \
+ KEEP(*(SORT(.ctors.*))) \
KEEP(*(.ctors)) \
KEEP(*(SORT(.init_array.*))) \
KEEP(*(.init_array)) \
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index da53aeb..a53243a 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -1836,7 +1836,7 @@
* @link_rate: Requested Link rate from DPCD 0x219
* @num_lanes: Number of lanes requested by sing through DPCD 0x220
* @phy_pattern: DP Phy test pattern from DPCD 0x248
- * @hb2_reset: DP HBR2_COMPLIANCE_SCRAMBLER_RESET from DCPD 0x24A and 0x24B
+ * @hbr2_reset: DP HBR2_COMPLIANCE_SCRAMBLER_RESET from DCPD 0x24A and 0x24B
* @custom80: DP Test_80BIT_CUSTOM_PATTERN from DPCDs 0x250 through 0x259
* @enhanced_frame_cap: flag for enhanced frame capability.
*/
diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h
index b27a0e2..e97daf6 100644
--- a/include/drm/drm_edid.h
+++ b/include/drm/drm_edid.h
@@ -359,13 +359,6 @@
}
#endif
-/**
- * drm_edid_are_equal - compare two edid blobs.
- * @edid1: pointer to first blob
- * @edid2: pointer to second blob
- * This helper can be used during probing to determine if
- * edid had changed.
- */
bool drm_edid_are_equal(const struct edid *edid1, const struct edid *edid2);
int
diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h
index 1c94174..f32d179e 100644
--- a/include/drm/drm_print.h
+++ b/include/drm/drm_print.h
@@ -338,7 +338,7 @@
const char *format, ...);
/**
- * Error output.
+ * DRM_DEV_ERROR() - Error output.
*
* @dev: device pointer
* @fmt: printf() like format string.
@@ -347,10 +347,12 @@
drm_dev_printk(dev, KERN_ERR, "*ERROR* " fmt, ##__VA_ARGS__)
/**
- * Rate limited error output. Like DRM_ERROR() but won't flood the log.
+ * DRM_DEV_ERROR_RATELIMITED() - Rate limited error output.
*
* @dev: device pointer
* @fmt: printf() like format string.
+ *
+ * Like DRM_ERROR() but won't flood the log.
*/
#define DRM_DEV_ERROR_RATELIMITED(dev, fmt, ...) \
({ \
@@ -375,15 +377,27 @@
})
/**
- * Debug output.
+ * DRM_DEV_DEBUG() - Debug output for generic drm code
*
* @dev: device pointer
* @fmt: printf() like format string.
*/
#define DRM_DEV_DEBUG(dev, fmt, ...) \
drm_dev_dbg(dev, DRM_UT_CORE, fmt, ##__VA_ARGS__)
+/**
+ * DRM_DEV_DEBUG_DRIVER() - Debug output for vendor specific part of the driver
+ *
+ * @dev: device pointer
+ * @fmt: printf() like format string.
+ */
#define DRM_DEV_DEBUG_DRIVER(dev, fmt, ...) \
drm_dev_dbg(dev, DRM_UT_DRIVER, fmt, ##__VA_ARGS__)
+/**
+ * DRM_DEV_DEBUG_KMS() - Debug output for modesetting code
+ *
+ * @dev: device pointer
+ * @fmt: printf() like format string.
+ */
#define DRM_DEV_DEBUG_KMS(dev, fmt, ...) \
drm_dev_dbg(dev, DRM_UT_KMS, fmt, ##__VA_ARGS__)
diff --git a/include/kunit/test.h b/include/kunit/test.h
index 9197da7..df60be7 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -252,13 +252,14 @@
}
#endif /* IS_BUILTIN(CONFIG_KUNIT) */
+#ifdef MODULE
/**
- * kunit_test_suites() - used to register one or more &struct kunit_suite
- * with KUnit.
+ * kunit_test_suites_for_module() - used to register one or more
+ * &struct kunit_suite with KUnit.
*
- * @suites_list...: a statically allocated list of &struct kunit_suite.
+ * @__suites: a statically allocated list of &struct kunit_suite.
*
- * Registers @suites_list with the test framework. See &struct kunit_suite for
+ * Registers @__suites with the test framework. See &struct kunit_suite for
* more information.
*
* If a test suite is built-in, module_init() gets translated into
@@ -267,7 +268,6 @@
* module_{init|exit} functions for the builtin case when registering
* suites via kunit_test_suites() below.
*/
-#ifdef MODULE
#define kunit_test_suites_for_module(__suites) \
static int __init kunit_test_suites_init(void) \
{ \
@@ -294,7 +294,7 @@
* kunit_test_suites() - used to register one or more &struct kunit_suite
* with KUnit.
*
- * @suites: a statically allocated list of &struct kunit_suite.
+ * @__suites: a statically allocated list of &struct kunit_suite.
*
* Registers @suites with the test framework. See &struct kunit_suite for
* more information.
@@ -308,10 +308,10 @@
* module.
*
*/
-#define kunit_test_suites(...) \
+#define kunit_test_suites(__suites...) \
__kunit_test_suites(__UNIQUE_ID(array), \
__UNIQUE_ID(suites), \
- __VA_ARGS__)
+ ##__suites)
#define kunit_test_suite(suite) kunit_test_suites(&suite)
@@ -1105,7 +1105,7 @@
KUNIT_ASSERTION(test, \
strcmp(__left, __right) op 0, \
kunit_binary_str_assert, \
- KUNIT_INIT_BINARY_ASSERT_STRUCT(test, \
+ KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(test, \
assert_type, \
#op, \
#left, \
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 885c9ff..f860645 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -87,6 +87,8 @@
ARM_SMCCC_SMC_32, \
0, 0x7fff)
+#define SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED 1
+
/* Paravirtualised time calls (defined by ARM DEN0057A) */
#define ARM_SMCCC_HV_PV_TIME_FEATURES \
ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index b23eeca..794b2a3 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -235,6 +235,8 @@
* @flags: Zero or more BLK_MQ_F_* flags.
* @driver_data: Pointer to data owned by the block driver that created this
* tag set.
+ * @active_queues_shared_sbitmap:
+ * number of active request queues per tag set.
* @__bitmap_tags: A shared tags sbitmap, used over all hctx's
* @__breserved_tags:
* A shared reserved tags sbitmap, used over all hctx's
diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h
index 900b9f4..fc61cf4 100644
--- a/include/linux/can/skb.h
+++ b/include/linux/can/skb.h
@@ -61,21 +61,17 @@
*/
static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb)
{
- if (skb_shared(skb)) {
- struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+ struct sk_buff *nskb;
- if (likely(nskb)) {
- can_skb_set_owner(nskb, skb->sk);
- consume_skb(skb);
- return nskb;
- } else {
- kfree_skb(skb);
- return NULL;
- }
+ nskb = skb_clone(skb, GFP_ATOMIC);
+ if (unlikely(!nskb)) {
+ kfree_skb(skb);
+ return NULL;
}
- /* we can assume to have an unshared skb with proper owner */
- return skb;
+ can_skb_set_owner(nskb, skb->sk);
+ consume_skb(skb);
+ return nskb;
}
#endif /* !_CAN_SKB_H */
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 230604e..dd7233c 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -60,12 +60,6 @@
#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
#endif
-/* The following are for compatibility with GCC, from compiler-gcc.h,
- * and may be redefined here because they should not be shared with other
- * compilers, like ICC.
- */
-#define barrier() __asm__ __volatile__("" : : : "memory")
-
#if __has_feature(shadow_call_stack)
# define __noscs __attribute__((__no_sanitize__("shadow-call-stack")))
#endif
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index d1e3c68..74c6c04 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -15,25 +15,6 @@
# error Sorry, your version of GCC is too old - please use 4.9 or newer.
#endif
-/* Optimization barrier */
-
-/* The "volatile" is due to gcc bugs */
-#define barrier() __asm__ __volatile__("": : :"memory")
-/*
- * This version is i.e. to prevent dead stores elimination on @ptr
- * where gcc and llvm may behave differently when otherwise using
- * normal barrier(): while gcc behavior gets along with a normal
- * barrier(), llvm needs an explicit input variable to be assumed
- * clobbered. The issue is as follows: while the inline asm might
- * access any memory it wants, the compiler could have fit all of
- * @ptr into memory registers instead, and since @ptr never escaped
- * from that, it proved that the inline asm wasn't touching any of
- * it. This version works well with both compilers, i.e. we're telling
- * the compiler that the inline asm absolutely may see the contents
- * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495
- */
-#define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory")
-
/*
* This macro obfuscates arithmetic on a variable address so that gcc
* shouldn't recognize the original var, and make assumptions about it.
@@ -175,5 +156,3 @@
#else
#define __diag_GCC_8(s)
#endif
-
-#define __no_fgcse __attribute__((optimize("-fno-gcse")))
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index e512f55..b8fe0c2 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -80,11 +80,25 @@
/* Optimization barrier */
#ifndef barrier
-# define barrier() __memory_barrier()
+/* The "volatile" is due to gcc bugs */
+# define barrier() __asm__ __volatile__("": : :"memory")
#endif
#ifndef barrier_data
-# define barrier_data(ptr) barrier()
+/*
+ * This version is i.e. to prevent dead stores elimination on @ptr
+ * where gcc and llvm may behave differently when otherwise using
+ * normal barrier(): while gcc behavior gets along with a normal
+ * barrier(), llvm needs an explicit input variable to be assumed
+ * clobbered. The issue is as follows: while the inline asm might
+ * access any memory it wants, the compiler could have fit all of
+ * @ptr into memory registers instead, and since @ptr never escaped
+ * from that, it proved that the inline asm wasn't touching any of
+ * it. This version works well with both compilers, i.e. we're telling
+ * the compiler that the inline asm absolutely may see the contents
+ * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495
+ */
+# define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory")
#endif
/* workaround for GCC PR82365 if needed */
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 6e390d5..ac3fa37 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -247,10 +247,6 @@
#define asm_inline asm
#endif
-#ifndef __no_fgcse
-# define __no_fgcse
-#endif
-
/* Are two types/vars the same type (ignoring qualifiers)? */
#define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index fa37b1c..acbad3b 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -110,6 +110,12 @@
bool fast_switch_enabled;
/*
+ * Set if the CPUFREQ_GOV_STRICT_TARGET flag is set for the current
+ * governor.
+ */
+ bool strict_target;
+
+ /*
* Preferred average time interval between consecutive invocations of
* the driver to set the frequency for this policy. To be set by the
* scaling driver (0, which is the default, means no preference).
@@ -298,7 +304,7 @@
struct cpufreq_driver {
char name[CPUFREQ_NAME_LEN];
- u8 flags;
+ u16 flags;
void *driver_data;
/* needed by all drivers */
@@ -422,9 +428,18 @@
*/
#define CPUFREQ_IS_COOLING_DEV BIT(7)
+/*
+ * Set by drivers that need to update internale upper and lower boundaries along
+ * with the target frequency and so the core and governors should also invoke
+ * the diver if the target frequency does not change, but the policy min or max
+ * may have changed.
+ */
+#define CPUFREQ_NEED_UPDATE_LIMITS BIT(8)
+
int cpufreq_register_driver(struct cpufreq_driver *driver_data);
int cpufreq_unregister_driver(struct cpufreq_driver *driver_data);
+bool cpufreq_driver_test_flags(u16 flags);
const char *cpufreq_get_current_driver(void);
void *cpufreq_get_driver_data(void);
@@ -561,12 +576,20 @@
char *buf);
int (*store_setspeed) (struct cpufreq_policy *policy,
unsigned int freq);
- /* For governors which change frequency dynamically by themselves */
- bool dynamic_switching;
struct list_head governor_list;
struct module *owner;
+ u8 flags;
};
+/* Governor flags */
+
+/* For governors which change frequency dynamically by themselves */
+#define CPUFREQ_GOV_DYNAMIC_SWITCHING BIT(0)
+
+/* For governors wanting the target frequency to be set exactly */
+#define CPUFREQ_GOV_STRICT_TARGET BIT(1)
+
+
/* Pass a target to the cpufreq driver */
unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
unsigned int target_freq);
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index 851dd1f..d6c4cc9 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -144,10 +144,9 @@
struct dentry *parent,
struct debugfs_u32_array *array);
-struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name,
- struct dentry *parent,
- int (*read_fn)(struct seq_file *s,
- void *data));
+void debugfs_create_devm_seqfile(struct device *dev, const char *name,
+ struct dentry *parent,
+ int (*read_fn)(struct seq_file *s, void *data));
bool debugfs_initialized(void);
@@ -327,13 +326,12 @@
{
}
-static inline struct dentry *debugfs_create_devm_seqfile(struct device *dev,
- const char *name,
- struct dentry *parent,
- int (*read_fn)(struct seq_file *s,
- void *data))
+static inline void debugfs_create_devm_seqfile(struct device *dev,
+ const char *name,
+ struct dentry *parent,
+ int (*read_fn)(struct seq_file *s,
+ void *data))
{
- return ERR_PTR(-ENODEV);
}
static inline ssize_t debugfs_read_file_bool(struct file *file,
diff --git a/include/linux/dma/ti-cppi5.h b/include/linux/dma/ti-cppi5.h
index 5896441..efa2f03 100644
--- a/include/linux/dma/ti-cppi5.h
+++ b/include/linux/dma/ti-cppi5.h
@@ -47,7 +47,7 @@
u32 buf_info1;
u32 org_buf_len;
u64 org_buf_ptr;
- u32 epib[0];
+ u32 epib[];
} __packed;
#define CPPI5_DESC_MIN_ALIGN (16U)
@@ -139,7 +139,7 @@
*/
struct cppi5_monolithic_desc_t {
struct cppi5_desc_hdr_t hdr;
- u32 epib[0];
+ u32 epib[];
};
#define CPPI5_INFO2_MDESC_DATA_OFFSET_SHIFT (18U)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 72d62cb..1b62397 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -558,21 +558,21 @@
DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
#define __BPF_PROG_RUN(prog, ctx, dfunc) ({ \
- u32 ret; \
+ u32 __ret; \
cant_migrate(); \
if (static_branch_unlikely(&bpf_stats_enabled_key)) { \
- struct bpf_prog_stats *stats; \
- u64 start = sched_clock(); \
- ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \
- stats = this_cpu_ptr(prog->aux->stats); \
- u64_stats_update_begin(&stats->syncp); \
- stats->cnt++; \
- stats->nsecs += sched_clock() - start; \
- u64_stats_update_end(&stats->syncp); \
+ struct bpf_prog_stats *__stats; \
+ u64 __start = sched_clock(); \
+ __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \
+ __stats = this_cpu_ptr(prog->aux->stats); \
+ u64_stats_update_begin(&__stats->syncp); \
+ __stats->cnt++; \
+ __stats->nsecs += sched_clock() - __start; \
+ u64_stats_update_end(&__stats->syncp); \
} else { \
- ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \
+ __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \
} \
- ret; })
+ __ret; })
#define BPF_PROG_RUN(prog, ctx) \
__BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0bd1264..8667d0c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1580,8 +1580,24 @@
* Snapshotting support.
*/
-void __sb_end_write(struct super_block *sb, int level);
-int __sb_start_write(struct super_block *sb, int level, bool wait);
+/*
+ * These are internal functions, please use sb_start_{write,pagefault,intwrite}
+ * instead.
+ */
+static inline void __sb_end_write(struct super_block *sb, int level)
+{
+ percpu_up_read(sb->s_writers.rw_sem + level-1);
+}
+
+static inline void __sb_start_write(struct super_block *sb, int level)
+{
+ percpu_down_read(sb->s_writers.rw_sem + level - 1);
+}
+
+static inline bool __sb_start_write_trylock(struct super_block *sb, int level)
+{
+ return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1);
+}
#define __sb_writers_acquired(sb, lev) \
percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
@@ -1645,12 +1661,12 @@
*/
static inline void sb_start_write(struct super_block *sb)
{
- __sb_start_write(sb, SB_FREEZE_WRITE, true);
+ __sb_start_write(sb, SB_FREEZE_WRITE);
}
-static inline int sb_start_write_trylock(struct super_block *sb)
+static inline bool sb_start_write_trylock(struct super_block *sb)
{
- return __sb_start_write(sb, SB_FREEZE_WRITE, false);
+ return __sb_start_write_trylock(sb, SB_FREEZE_WRITE);
}
/**
@@ -1674,7 +1690,7 @@
*/
static inline void sb_start_pagefault(struct super_block *sb)
{
- __sb_start_write(sb, SB_FREEZE_PAGEFAULT, true);
+ __sb_start_write(sb, SB_FREEZE_PAGEFAULT);
}
/*
@@ -1692,12 +1708,12 @@
*/
static inline void sb_start_intwrite(struct super_block *sb)
{
- __sb_start_write(sb, SB_FREEZE_FS, true);
+ __sb_start_write(sb, SB_FREEZE_FS);
}
-static inline int sb_start_intwrite_trylock(struct super_block *sb)
+static inline bool sb_start_intwrite_trylock(struct super_block *sb)
{
- return __sb_start_write(sb, SB_FREEZE_FS, false);
+ return __sb_start_write_trylock(sb, SB_FREEZE_FS);
}
@@ -2756,14 +2772,14 @@
{
if (!S_ISREG(file_inode(file)->i_mode))
return;
- __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
+ sb_start_write(file_inode(file)->i_sb);
}
static inline bool file_start_write_trylock(struct file *file)
{
if (!S_ISREG(file_inode(file)->i_mode))
return true;
- return __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, false);
+ return sb_start_write_trylock(file_inode(file)->i_sb);
}
static inline void file_end_write(struct file *file)
@@ -3285,7 +3301,7 @@
*/
struct simple_transaction_argresp {
ssize_t size;
- char data[0];
+ char data[];
};
#define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp))
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 38f23d7..03da3f6 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -315,7 +315,7 @@
extern void disk_block_events(struct gendisk *disk);
extern void disk_unblock_events(struct gendisk *disk);
extern void disk_flush_events(struct gendisk *disk, unsigned int mask);
-void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
+bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
bool update_bdev);
/* drivers/char/random.c */
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index fbf5b3e..d956987 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -798,7 +798,6 @@
extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
extern int dmar_disabled;
extern int intel_iommu_enabled;
-extern int intel_iommu_tboot_noforce;
extern int intel_iommu_gfx_mapped;
#else
static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 868364c..35b2d84 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -30,7 +30,8 @@
struct percpu_counter inflight;
struct io_identity __identity;
struct io_identity *identity;
- bool in_idle;
+ atomic_t in_idle;
+ bool sqpoll;
};
#if defined(CONFIG_IO_URING)
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 172b339..5bd3cac 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -221,7 +221,7 @@
* Optional, allows the file system to discard state on a page where
* we failed to submit any I/O.
*/
- void (*discard_page)(struct page *page);
+ void (*discard_page)(struct page *page, loff_t fileoff);
};
struct iomap_writepage_ctx {
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index fb3d71a..1c49fd6 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -68,6 +68,7 @@
extern void jbd2_free(void *ptr, size_t size);
#define JBD2_MIN_JOURNAL_BLOCKS 1024
+#define JBD2_MIN_FC_BLOCKS 256
#ifdef __KERNEL__
@@ -263,7 +264,10 @@
/* 0x0050 */
__u8 s_checksum_type; /* checksum type */
__u8 s_padding2[3];
- __u32 s_padding[42];
+/* 0x0054 */
+ __be32 s_num_fc_blks; /* Number of fast commit blocks */
+/* 0x0058 */
+ __u32 s_padding[41];
__be32 s_checksum; /* crc32c(superblock) */
/* 0x0100 */
@@ -941,8 +945,9 @@
/**
* @j_fc_off:
*
- * Number of fast commit blocks currently allocated.
- * [j_state_lock].
+ * Number of fast commit blocks currently allocated. Accessed only
+ * during fast commit. Currently only process can do fast commit, so
+ * this field is not protected by any lock.
*/
unsigned long j_fc_off;
@@ -985,9 +990,9 @@
struct block_device *j_fs_dev;
/**
- * @j_maxlen: Total maximum capacity of the journal region on disk.
+ * @j_total_len: Total maximum capacity of the journal region on disk.
*/
- unsigned int j_maxlen;
+ unsigned int j_total_len;
/**
* @j_reserved_credits:
@@ -1105,8 +1110,9 @@
struct buffer_head **j_wbuf;
/**
- * @j_fc_wbuf: Array of fast commit bhs for
- * jbd2_journal_commit_transaction.
+ * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only
+ * during a fast commit. Currently only process can do fast commit, so
+ * this field is not protected by any lock.
*/
struct buffer_head **j_fc_wbuf;
@@ -1253,7 +1259,7 @@
*/
void (*j_fc_cleanup_callback)(struct journal_s *journal, int);
- /*
+ /**
* @j_fc_replay_callback:
*
* File-system specific function that performs replay of a fast
@@ -1611,16 +1617,20 @@
extern int jbd2_cleanup_journal_tail(journal_t *);
/* Fast commit related APIs */
-int jbd2_fc_init(journal_t *journal, int num_fc_blks);
int jbd2_fc_begin_commit(journal_t *journal, tid_t tid);
int jbd2_fc_end_commit(journal_t *journal);
-int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid);
+int jbd2_fc_end_commit_fallback(journal_t *journal);
int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out);
int jbd2_submit_inode_data(struct jbd2_inode *jinode);
int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode);
int jbd2_fc_wait_bufs(journal_t *journal, int num_blks);
int jbd2_fc_release_bufs(journal_t *journal);
+static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal)
+{
+ return (journal->j_total_len - journal->j_fc_wbufsize) / 4;
+}
+
/*
* is_journal_abort
*
diff --git a/include/linux/jhash.h b/include/linux/jhash.h
index cfb62e9..ab7f8c1 100644
--- a/include/linux/jhash.h
+++ b/include/linux/jhash.h
@@ -99,6 +99,7 @@
case 2: a += (u32)k[1]<<8; fallthrough;
case 1: a += k[0];
__jhash_final(a, b, c);
+ break;
case 0: /* Nothing left to add */
break;
}
@@ -136,6 +137,7 @@
case 2: b += k[1]; fallthrough;
case 1: a += k[0];
__jhash_final(a, b, c);
+ break;
case 0: /* Nothing left to add */
break;
}
diff --git a/include/linux/mailbox/zynqmp-ipi-message.h b/include/linux/mailbox/zynqmp-ipi-message.h
index 9542b41..35ce84c 100644
--- a/include/linux/mailbox/zynqmp-ipi-message.h
+++ b/include/linux/mailbox/zynqmp-ipi-message.h
@@ -14,7 +14,7 @@
*/
struct zynqmp_ipi_message {
size_t len;
- u8 data[0];
+ u8 data[];
};
#endif /* _LINUX_ZYNQMP_IPI_MESSAGE_H_ */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e391e3c..a80c59a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -900,12 +900,19 @@
static inline void memcg_memory_event(struct mem_cgroup *memcg,
enum memcg_memory_event event)
{
+ bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX ||
+ event == MEMCG_SWAP_FAIL;
+
atomic_long_inc(&memcg->memory_events_local[event]);
- cgroup_file_notify(&memcg->events_local_file);
+ if (!swap_event)
+ cgroup_file_notify(&memcg->events_local_file);
do {
atomic_long_inc(&memcg->memory_events[event]);
- cgroup_file_notify(&memcg->events_file);
+ if (swap_event)
+ cgroup_file_notify(&memcg->swap_events_file);
+ else
+ cgroup_file_notify(&memcg->events_file);
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
break;
diff --git a/include/linux/mic_bus.h b/include/linux/mic_bus.h
deleted file mode 100644
index e99c789..0000000
--- a/include/linux/mic_bus.h
+++ /dev/null
@@ -1,100 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel MIC Bus driver.
- *
- * This implementation is very similar to the virtio bus driver
- * implementation @ include/linux/virtio.h.
- */
-#ifndef _MIC_BUS_H_
-#define _MIC_BUS_H_
-/*
- * Everything a mbus driver needs to work with any particular mbus
- * implementation.
- */
-#include <linux/interrupt.h>
-#include <linux/dma-mapping.h>
-
-struct mbus_device_id {
- __u32 device;
- __u32 vendor;
-};
-
-#define MBUS_DEV_DMA_HOST 2
-#define MBUS_DEV_DMA_MIC 3
-#define MBUS_DEV_ANY_ID 0xffffffff
-
-/**
- * mbus_device - representation of a device using mbus
- * @mmio_va: virtual address of mmio space
- * @hw_ops: the hardware ops supported by this device.
- * @id: the device type identification (used to match it with a driver).
- * @dev: underlying device.
- * be used to communicate with.
- * @index: unique position on the mbus bus
- */
-struct mbus_device {
- void __iomem *mmio_va;
- struct mbus_hw_ops *hw_ops;
- struct mbus_device_id id;
- struct device dev;
- int index;
-};
-
-/**
- * mbus_driver - operations for a mbus I/O driver
- * @driver: underlying device driver (populate name and owner).
- * @id_table: the ids serviced by this driver.
- * @probe: the function to call when a device is found. Returns 0 or -errno.
- * @remove: the function to call when a device is removed.
- */
-struct mbus_driver {
- struct device_driver driver;
- const struct mbus_device_id *id_table;
- int (*probe)(struct mbus_device *dev);
- void (*scan)(struct mbus_device *dev);
- void (*remove)(struct mbus_device *dev);
-};
-
-/**
- * struct mic_irq - opaque pointer used as cookie
- */
-struct mic_irq;
-
-/**
- * mbus_hw_ops - Hardware operations for accessing a MIC device on the MIC bus.
- */
-struct mbus_hw_ops {
- struct mic_irq* (*request_threaded_irq)(struct mbus_device *mbdev,
- irq_handler_t handler,
- irq_handler_t thread_fn,
- const char *name, void *data,
- int intr_src);
- void (*free_irq)(struct mbus_device *mbdev,
- struct mic_irq *cookie, void *data);
- void (*ack_interrupt)(struct mbus_device *mbdev, int num);
-};
-
-struct mbus_device *
-mbus_register_device(struct device *pdev, int id, const struct dma_map_ops *dma_ops,
- struct mbus_hw_ops *hw_ops, int index,
- void __iomem *mmio_va);
-void mbus_unregister_device(struct mbus_device *mbdev);
-
-int mbus_register_driver(struct mbus_driver *drv);
-void mbus_unregister_driver(struct mbus_driver *drv);
-
-static inline struct mbus_device *dev_to_mbus(struct device *_dev)
-{
- return container_of(_dev, struct mbus_device, dev);
-}
-
-static inline struct mbus_driver *drv_to_mbus(struct device_driver *drv)
-{
- return container_of(drv, struct mbus_driver, driver);
-}
-
-#endif /* _MIC_BUS_H */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index add8509..0f23e1e 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1213,4 +1213,22 @@
return val.vbool;
}
+/**
+ * mlx5_core_net - Provide net namespace of the mlx5_core_dev
+ * @dev: mlx5 core device
+ *
+ * mlx5_core_net() returns the net namespace of mlx5 core device.
+ * This can be called only in below described limited context.
+ * (a) When a devlink instance for mlx5_core is registered and
+ * when devlink reload operation is disabled.
+ * or
+ * (b) during devlink reload reload_down() and reload_up callbacks
+ * where it is ensured that devlink instance's net namespace is
+ * stable.
+ */
+static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
+{
+ return devlink_net(priv_to_devlink(dev));
+}
+
#endif /* MLX5_DRIVER_H */
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 651591a..a092346 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -5823,7 +5823,7 @@
u8 reserved_at_68[0x10];
u8 num_of_actions[0x8];
- union mlx5_ifc_set_add_copy_action_in_auto_bits actions[0];
+ union mlx5_ifc_set_add_copy_action_in_auto_bits actions[];
};
struct mlx5_ifc_dealloc_modify_header_context_out_bits {
@@ -9761,7 +9761,7 @@
u8 reserved_at_60[0x20];
- u8 data[0][0x20];
+ u8 data[][0x20];
};
enum {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ef360fe..db6ae4d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2759,6 +2759,15 @@
return VM_FAULT_NOPAGE;
}
+#ifndef io_remap_pfn_range
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+ unsigned long addr, unsigned long pfn,
+ unsigned long size, pgprot_t prot)
+{
+ return remap_pfn_range(vma, addr, pfn, size, pgprot_decrypted(prot));
+}
+#endif
+
static inline vm_fault_t vmf_error(int err)
{
if (err == -ENOMEM)
diff --git a/include/linux/module.h b/include/linux/module.h
index 7ccdf87..6264617 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -740,7 +740,7 @@
}
/* Get/put a kernel symbol (calls should be symmetric) */
-#define symbol_get(x) ({ extern typeof(x) x __attribute__((weak)); &(x); })
+#define symbol_get(x) ({ extern typeof(x) x __attribute__((weak,visibility("hidden"))); &(x); })
#define symbol_put(x) do { } while (0)
#define symbol_put_addr(x) do { } while (0)
diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 89016d0..f6267e2 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -24,6 +24,12 @@
const u_int16_t attr_count; /* number of nlattr's */
};
+enum nfnl_abort_action {
+ NFNL_ABORT_NONE = 0,
+ NFNL_ABORT_AUTOLOAD,
+ NFNL_ABORT_VALIDATE,
+};
+
struct nfnetlink_subsystem {
const char *name;
__u8 subsys_id; /* nfnetlink subsystem ID */
@@ -31,7 +37,8 @@
const struct nfnl_callback *cb; /* callback for individual types */
struct module *owner;
int (*commit)(struct net *net, struct sk_buff *skb);
- int (*abort)(struct net *net, struct sk_buff *skb, bool autoload);
+ int (*abort)(struct net *net, struct sk_buff *skb,
+ enum nfnl_abort_action action);
void (*cleanup)(struct net *net);
bool (*valid_genid)(struct net *net, u32 genid);
};
diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h
index 082e2c4..5b70ca8 100644
--- a/include/linux/netfilter_ipv4.h
+++ b/include/linux/netfilter_ipv4.h
@@ -16,7 +16,7 @@
u_int32_t mark;
};
-int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned addr_type);
+int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned addr_type);
struct nf_queue_entry;
diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h
index 9b67394..48314ad 100644
--- a/include/linux/netfilter_ipv6.h
+++ b/include/linux/netfilter_ipv6.h
@@ -42,7 +42,7 @@
#if IS_MODULE(CONFIG_IPV6)
int (*chk_addr)(struct net *net, const struct in6_addr *addr,
const struct net_device *dev, int strict);
- int (*route_me_harder)(struct net *net, struct sk_buff *skb);
+ int (*route_me_harder)(struct net *net, struct sock *sk, struct sk_buff *skb);
int (*dev_get_saddr)(struct net *net, const struct net_device *dev,
const struct in6_addr *daddr, unsigned int srcprefs,
struct in6_addr *saddr);
@@ -143,9 +143,9 @@
#endif
}
-int ip6_route_me_harder(struct net *net, struct sk_buff *skb);
+int ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb);
-static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb)
+static inline int nf_ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb)
{
#if IS_MODULE(CONFIG_IPV6)
const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
@@ -153,9 +153,9 @@
if (!v6_ops)
return -EHOSTUNREACH;
- return v6_ops->route_me_harder(net, skb);
+ return v6_ops->route_me_harder(net, sk, skb);
#elif IS_BUILTIN(CONFIG_IPV6)
- return ip6_route_me_harder(net, skb);
+ return ip6_route_me_harder(net, sk, skb);
#else
return -EHOSTUNREACH;
#endif
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index c77b7c31..e1e19c1 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -344,9 +344,9 @@
/**
* find_lock_page - locate, pin and lock a pagecache page
* @mapping: the address_space to search
- * @offset: the page index
+ * @index: the page index
*
- * Looks up the page cache entry at @mapping & @offset. If there is a
+ * Looks up the page cache entry at @mapping & @index. If there is a
* page cache page, it is returned locked and with an increased
* refcount.
*
@@ -363,9 +363,9 @@
/**
* find_lock_head - Locate, pin and lock a pagecache page.
* @mapping: The address_space to search.
- * @offset: The page index.
+ * @index: The page index.
*
- * Looks up the page cache entry at @mapping & @offset. If there is a
+ * Looks up the page cache entry at @mapping & @index. If there is a
* page cache page, its head page is returned locked and with an increased
* refcount.
*
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 0c19d27..96450f6 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1022,13 +1022,7 @@
struct perf_callchain_entry *callchain;
u64 aux_size;
- /*
- * regs_user may point to task_pt_regs or to regs_user_copy, depending
- * on arch details.
- */
struct perf_regs regs_user;
- struct pt_regs regs_user_copy;
-
struct perf_regs regs_intr;
u64 stack_user_size;
@@ -1400,11 +1394,14 @@
extern void perf_event_addr_filters_sync(struct perf_event *event);
extern int perf_output_begin(struct perf_output_handle *handle,
+ struct perf_sample_data *data,
struct perf_event *event, unsigned int size);
extern int perf_output_begin_forward(struct perf_output_handle *handle,
- struct perf_event *event,
- unsigned int size);
+ struct perf_sample_data *data,
+ struct perf_event *event,
+ unsigned int size);
extern int perf_output_begin_backward(struct perf_output_handle *handle,
+ struct perf_sample_data *data,
struct perf_event *event,
unsigned int size);
diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
index 2d12e97..f632c57 100644
--- a/include/linux/perf_regs.h
+++ b/include/linux/perf_regs.h
@@ -20,8 +20,7 @@
int perf_reg_validate(u64 mask);
u64 perf_reg_abi(struct task_struct *task);
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy);
+ struct pt_regs *regs);
#else
#define PERF_REG_EXTENDED_MASK 0
@@ -42,8 +41,7 @@
}
static inline void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
regs_user->regs = task_pt_regs(current);
regs_user->abi = perf_reg_abi(current);
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 38c33ea..71125a4 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1427,10 +1427,6 @@
#endif /* !__ASSEMBLY__ */
-#ifndef io_remap_pfn_range
-#define io_remap_pfn_range remap_pfn_range
-#endif
-
#ifndef has_transparent_hugepage
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define has_transparent_hugepage() 1
diff --git a/include/linux/phy.h b/include/linux/phy.h
index eb3cb1a..56563e5e0 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -147,16 +147,8 @@
PHY_INTERFACE_MODE_MAX,
} phy_interface_t;
-/**
+/*
* phy_supported_speeds - return all speeds currently supported by a PHY device
- * @phy: The PHY device to return supported speeds of.
- * @speeds: buffer to store supported speeds in.
- * @size: size of speeds buffer.
- *
- * Description: Returns the number of supported speeds, and fills
- * the speeds buffer with the supported speeds. If speeds buffer is
- * too small to contain all currently supported speeds, will return as
- * many speeds as can fit.
*/
unsigned int phy_supported_speeds(struct phy_device *phy,
unsigned int *speeds,
@@ -1022,14 +1014,9 @@
regnum, mask, set);
}
-/**
+/*
* phy_read_mmd - Convenience function for reading a register
* from an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to read from
- * @regnum: The register on the MMD to read
- *
- * Same rules as for phy_read();
*/
int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
@@ -1064,38 +1051,21 @@
__ret; \
})
-/**
+/*
* __phy_read_mmd - Convenience function for reading a register
* from an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to read from
- * @regnum: The register on the MMD to read
- *
- * Same rules as for __phy_read();
*/
int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
-/**
+/*
* phy_write_mmd - Convenience function for writing a register
* on an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to write to
- * @regnum: The register on the MMD to read
- * @val: value to write to @regnum
- *
- * Same rules as for phy_write();
*/
int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val);
-/**
+/*
* __phy_write_mmd - Convenience function for writing a register
* on an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to write to
- * @regnum: The register on the MMD to read
- * @val: value to write to @regnum
- *
- * Same rules as for __phy_write();
*/
int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val);
diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h
index 1fcfe9e..a3a9a87 100644
--- a/include/linux/platform_data/cros_ec_commands.h
+++ b/include/linux/platform_data/cros_ec_commands.h
@@ -1419,7 +1419,7 @@
uint16_t num_banks_total;
/* Number of banks described in banks array. */
uint16_t num_banks_desc;
- struct ec_flash_bank banks[0];
+ struct ec_flash_bank banks[];
} __ec_align4;
/*
@@ -2420,12 +2420,12 @@
/* Total amount of vector lost */
uint16_t total_lost;
/* Lost events since the last fifo_info, per sensors */
- uint16_t lost[0];
+ uint16_t lost[];
} __ec_todo_packed;
struct ec_response_motion_sense_fifo_data {
uint32_t number_data;
- struct ec_response_motion_sensor_data data[0];
+ struct ec_response_motion_sensor_data data[];
} __ec_todo_packed;
/* List supported activity recognition */
@@ -3093,7 +3093,7 @@
uint8_t algorithm;
uint8_t num_params;
uint8_t reserved[2];
- float val[0];
+ float val[];
} __ec_align4;
struct ec_params_tmp006_set_calibration_v1 {
@@ -3101,7 +3101,7 @@
uint8_t algorithm;
uint8_t num_params;
uint8_t reserved;
- float val[0];
+ float val[];
} __ec_align4;
@@ -5076,7 +5076,7 @@
uint8_t type; /* event type : see PD_EVENT_xx below */
uint8_t size_port; /* [7:5] port number [4:0] payload size in bytes */
uint16_t data; /* type-defined data payload */
- uint8_t payload[0]; /* optional additional data payload: 0..16 bytes */
+ uint8_t payload[]; /* optional additional data payload: 0..16 bytes */
} __ec_align4;
/* The timestamp is the microsecond counter shifted to get about a ms. */
@@ -5789,7 +5789,7 @@
struct ec_response_tp_frame_info {
uint32_t n_frames;
- uint32_t frame_sizes[0];
+ uint32_t frame_sizes[];
} __ec_align4;
/* Create a snapshot of current frame readings */
diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h
index 4a415ae..0259968 100644
--- a/include/linux/platform_data/cros_ec_proto.h
+++ b/include/linux/platform_data/cros_ec_proto.h
@@ -69,7 +69,7 @@
uint32_t outsize;
uint32_t insize;
uint32_t result;
- uint8_t data[0];
+ uint8_t data[];
};
/**
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 18b02dc..b492ae0 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -54,11 +54,10 @@
extern void pm_runtime_update_max_time_suspended(struct device *dev,
s64 delta_ns);
extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable);
-extern void pm_runtime_clean_up_links(struct device *dev);
extern void pm_runtime_get_suppliers(struct device *dev);
extern void pm_runtime_put_suppliers(struct device *dev);
extern void pm_runtime_new_link(struct device *dev);
-extern void pm_runtime_drop_link(struct device *dev);
+extern void pm_runtime_drop_link(struct device_link *link);
/**
* pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter.
@@ -276,11 +275,10 @@
struct device *dev) { return 0; }
static inline void pm_runtime_set_memalloc_noio(struct device *dev,
bool enable){}
-static inline void pm_runtime_clean_up_links(struct device *dev) {}
static inline void pm_runtime_get_suppliers(struct device *dev) {}
static inline void pm_runtime_put_suppliers(struct device *dev) {}
static inline void pm_runtime_new_link(struct device *dev) {}
-static inline void pm_runtime_drop_link(struct device *dev) {}
+static inline void pm_runtime_drop_link(struct device_link *link) {}
#endif /* !CONFIG_PM */
@@ -389,6 +387,27 @@
}
/**
+ * pm_runtime_resume_and_get - Bump up usage counter of a device and resume it.
+ * @dev: Target device.
+ *
+ * Resume @dev synchronously and if that is successful, increment its runtime
+ * PM usage counter. Return 0 if the runtime PM usage counter of @dev has been
+ * incremented or a negative error code otherwise.
+ */
+static inline int pm_runtime_resume_and_get(struct device *dev)
+{
+ int ret;
+
+ ret = __pm_runtime_resume(dev, RPM_GET_PUT);
+ if (ret < 0) {
+ pm_runtime_put_noidle(dev);
+ return ret;
+ }
+
+ return 0;
+}
+
+/**
* pm_runtime_put - Drop device usage counter and queue up "idle check" if 0.
* @dev: Target device.
*
diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index 7fabb1a..497990c 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -147,24 +147,6 @@
return atomic_read(&r->refs);
}
-/**
- * refcount_add_not_zero - add a value to a refcount unless it is 0
- * @i: the value to add to the refcount
- * @r: the refcount
- *
- * Will saturate at REFCOUNT_SATURATED and WARN.
- *
- * Provides no memory ordering, it is assumed the caller has guaranteed the
- * object memory to be stable (RCU, etc.). It does provide a control dependency
- * and thereby orders future stores. See the comment on top.
- *
- * Use of this function is not recommended for the normal reference counting
- * use case in which references are taken and released one at a time. In these
- * cases, refcount_inc(), or one of its variants, should instead be used to
- * increment a reference count.
- *
- * Return: false if the passed refcount is 0, true otherwise
- */
static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp)
{
int old = refcount_read(r);
@@ -183,11 +165,42 @@
return old;
}
+/**
+ * refcount_add_not_zero - add a value to a refcount unless it is 0
+ * @i: the value to add to the refcount
+ * @r: the refcount
+ *
+ * Will saturate at REFCOUNT_SATURATED and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time. In these
+ * cases, refcount_inc(), or one of its variants, should instead be used to
+ * increment a reference count.
+ *
+ * Return: false if the passed refcount is 0, true otherwise
+ */
static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r)
{
return __refcount_add_not_zero(i, r, NULL);
}
+static inline void __refcount_add(int i, refcount_t *r, int *oldp)
+{
+ int old = atomic_fetch_add_relaxed(i, &r->refs);
+
+ if (oldp)
+ *oldp = old;
+
+ if (unlikely(!old))
+ refcount_warn_saturate(r, REFCOUNT_ADD_UAF);
+ else if (unlikely(old < 0 || old + i < 0))
+ refcount_warn_saturate(r, REFCOUNT_ADD_OVF);
+}
+
/**
* refcount_add - add a value to a refcount
* @i: the value to add to the refcount
@@ -204,24 +217,16 @@
* cases, refcount_inc(), or one of its variants, should instead be used to
* increment a reference count.
*/
-static inline void __refcount_add(int i, refcount_t *r, int *oldp)
-{
- int old = atomic_fetch_add_relaxed(i, &r->refs);
-
- if (oldp)
- *oldp = old;
-
- if (unlikely(!old))
- refcount_warn_saturate(r, REFCOUNT_ADD_UAF);
- else if (unlikely(old < 0 || old + i < 0))
- refcount_warn_saturate(r, REFCOUNT_ADD_OVF);
-}
-
static inline void refcount_add(int i, refcount_t *r)
{
__refcount_add(i, r, NULL);
}
+static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp)
+{
+ return __refcount_add_not_zero(1, r, oldp);
+}
+
/**
* refcount_inc_not_zero - increment a refcount unless it is 0
* @r: the refcount to increment
@@ -235,16 +240,16 @@
*
* Return: true if the increment was successful, false otherwise
*/
-static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp)
-{
- return __refcount_add_not_zero(1, r, oldp);
-}
-
static inline __must_check bool refcount_inc_not_zero(refcount_t *r)
{
return __refcount_inc_not_zero(r, NULL);
}
+static inline void __refcount_inc(refcount_t *r, int *oldp)
+{
+ __refcount_add(1, r, oldp);
+}
+
/**
* refcount_inc - increment a refcount
* @r: the refcount to increment
@@ -257,16 +262,29 @@
* Will WARN if the refcount is 0, as this represents a possible use-after-free
* condition.
*/
-static inline void __refcount_inc(refcount_t *r, int *oldp)
-{
- __refcount_add(1, r, oldp);
-}
-
static inline void refcount_inc(refcount_t *r)
{
__refcount_inc(r, NULL);
}
+static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp)
+{
+ int old = atomic_fetch_sub_release(i, &r->refs);
+
+ if (oldp)
+ *oldp = old;
+
+ if (old == i) {
+ smp_acquire__after_ctrl_dep();
+ return true;
+ }
+
+ if (unlikely(old < 0 || old - i < 0))
+ refcount_warn_saturate(r, REFCOUNT_SUB_UAF);
+
+ return false;
+}
+
/**
* refcount_sub_and_test - subtract from a refcount and test if it is 0
* @i: amount to subtract from the refcount
@@ -287,29 +305,16 @@
*
* Return: true if the resulting refcount is 0, false otherwise
*/
-static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp)
-{
- int old = atomic_fetch_sub_release(i, &r->refs);
-
- if (oldp)
- *oldp = old;
-
- if (old == i) {
- smp_acquire__after_ctrl_dep();
- return true;
- }
-
- if (unlikely(old < 0 || old - i < 0))
- refcount_warn_saturate(r, REFCOUNT_SUB_UAF);
-
- return false;
-}
-
static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r)
{
return __refcount_sub_and_test(i, r, NULL);
}
+static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp)
+{
+ return __refcount_sub_and_test(1, r, oldp);
+}
+
/**
* refcount_dec_and_test - decrement a refcount and test if it is 0
* @r: the refcount
@@ -323,16 +328,22 @@
*
* Return: true if the resulting refcount is 0, false otherwise
*/
-static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp)
-{
- return __refcount_sub_and_test(1, r, oldp);
-}
-
static inline __must_check bool refcount_dec_and_test(refcount_t *r)
{
return __refcount_dec_and_test(r, NULL);
}
+static inline void __refcount_dec(refcount_t *r, int *oldp)
+{
+ int old = atomic_fetch_sub_release(1, &r->refs);
+
+ if (oldp)
+ *oldp = old;
+
+ if (unlikely(old <= 1))
+ refcount_warn_saturate(r, REFCOUNT_DEC_LEAK);
+}
+
/**
* refcount_dec - decrement a refcount
* @r: the refcount
@@ -343,17 +354,6 @@
* Provides release memory ordering, such that prior loads and stores are done
* before.
*/
-static inline void __refcount_dec(refcount_t *r, int *oldp)
-{
- int old = atomic_fetch_sub_release(1, &r->refs);
-
- if (oldp)
- *oldp = old;
-
- if (unlikely(old <= 1))
- refcount_warn_saturate(r, REFCOUNT_DEC_LEAK);
-}
-
static inline void refcount_dec(refcount_t *r)
{
__refcount_dec(r, NULL);
diff --git a/include/linux/scif.h b/include/linux/scif.h
deleted file mode 100644
index 329e695..0000000
--- a/include/linux/scif.h
+++ /dev/null
@@ -1,1339 +0,0 @@
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * Intel SCIF driver.
- *
- */
-#ifndef __SCIF_H__
-#define __SCIF_H__
-
-#include <linux/types.h>
-#include <linux/poll.h>
-#include <linux/device.h>
-#include <linux/scif_ioctl.h>
-
-#define SCIF_ACCEPT_SYNC 1
-#define SCIF_SEND_BLOCK 1
-#define SCIF_RECV_BLOCK 1
-
-enum {
- SCIF_PROT_READ = (1 << 0),
- SCIF_PROT_WRITE = (1 << 1)
-};
-
-enum {
- SCIF_MAP_FIXED = 0x10,
- SCIF_MAP_KERNEL = 0x20,
-};
-
-enum {
- SCIF_FENCE_INIT_SELF = (1 << 0),
- SCIF_FENCE_INIT_PEER = (1 << 1),
- SCIF_SIGNAL_LOCAL = (1 << 4),
- SCIF_SIGNAL_REMOTE = (1 << 5)
-};
-
-enum {
- SCIF_RMA_USECPU = (1 << 0),
- SCIF_RMA_USECACHE = (1 << 1),
- SCIF_RMA_SYNC = (1 << 2),
- SCIF_RMA_ORDERED = (1 << 3)
-};
-
-/* End of SCIF Admin Reserved Ports */
-#define SCIF_ADMIN_PORT_END 1024
-
-/* End of SCIF Reserved Ports */
-#define SCIF_PORT_RSVD 1088
-
-typedef struct scif_endpt *scif_epd_t;
-typedef struct scif_pinned_pages *scif_pinned_pages_t;
-
-/**
- * struct scif_range - SCIF registered range used in kernel mode
- * @cookie: cookie used internally by SCIF
- * @nr_pages: number of pages of PAGE_SIZE
- * @prot_flags: R/W protection
- * @phys_addr: Array of bus addresses
- * @va: Array of kernel virtual addresses backed by the pages in the phys_addr
- * array. The va is populated only when called on the host for a remote
- * SCIF connection on MIC. This is required to support the use case of DMA
- * between MIC and another device which is not a SCIF node e.g., an IB or
- * ethernet NIC.
- */
-struct scif_range {
- void *cookie;
- int nr_pages;
- int prot_flags;
- dma_addr_t *phys_addr;
- void __iomem **va;
-};
-
-/**
- * struct scif_pollepd - SCIF endpoint to be monitored via scif_poll
- * @epd: SCIF endpoint
- * @events: requested events
- * @revents: returned events
- */
-struct scif_pollepd {
- scif_epd_t epd;
- __poll_t events;
- __poll_t revents;
-};
-
-/**
- * scif_peer_dev - representation of a peer SCIF device
- *
- * Peer devices show up as PCIe devices for the mgmt node but not the cards.
- * The mgmt node discovers all the cards on the PCIe bus and informs the other
- * cards about their peers. Upon notification of a peer a node adds a peer
- * device to the peer bus to maintain symmetry in the way devices are
- * discovered across all nodes in the SCIF network.
- *
- * @dev: underlying device
- * @dnode - The destination node which this device will communicate with.
- */
-struct scif_peer_dev {
- struct device dev;
- u8 dnode;
-};
-
-/**
- * scif_client - representation of a SCIF client
- * @name: client name
- * @probe - client method called when a peer device is registered
- * @remove - client method called when a peer device is unregistered
- * @si - subsys_interface used internally for implementing SCIF clients
- */
-struct scif_client {
- const char *name;
- void (*probe)(struct scif_peer_dev *spdev);
- void (*remove)(struct scif_peer_dev *spdev);
- struct subsys_interface si;
-};
-
-#define SCIF_OPEN_FAILED ((scif_epd_t)-1)
-#define SCIF_REGISTER_FAILED ((off_t)-1)
-#define SCIF_MMAP_FAILED ((void *)-1)
-
-/**
- * scif_open() - Create an endpoint
- *
- * Return:
- * Upon successful completion, scif_open() returns an endpoint descriptor to
- * be used in subsequent SCIF functions calls to refer to that endpoint;
- * otherwise in user mode SCIF_OPEN_FAILED (that is ((scif_epd_t)-1)) is
- * returned and errno is set to indicate the error; in kernel mode a NULL
- * scif_epd_t is returned.
- *
- * Errors:
- * ENOMEM - Insufficient kernel memory was available
- */
-scif_epd_t scif_open(void);
-
-/**
- * scif_bind() - Bind an endpoint to a port
- * @epd: endpoint descriptor
- * @pn: port number
- *
- * scif_bind() binds endpoint epd to port pn, where pn is a port number on the
- * local node. If pn is zero, a port number greater than or equal to
- * SCIF_PORT_RSVD is assigned and returned. Each endpoint may be bound to
- * exactly one local port. Ports less than 1024 when requested can only be bound
- * by system (or root) processes or by processes executed by privileged users.
- *
- * Return:
- * Upon successful completion, scif_bind() returns the port number to which epd
- * is bound; otherwise in user mode -1 is returned and errno is set to
- * indicate the error; in kernel mode the negative of one of the following
- * errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * EINVAL - the endpoint or the port is already bound
- * EISCONN - The endpoint is already connected
- * ENOSPC - No port number available for assignment
- * EACCES - The port requested is protected and the user is not the superuser
- */
-int scif_bind(scif_epd_t epd, u16 pn);
-
-/**
- * scif_listen() - Listen for connections on an endpoint
- * @epd: endpoint descriptor
- * @backlog: maximum pending connection requests
- *
- * scif_listen() marks the endpoint epd as a listening endpoint - that is, as
- * an endpoint that will be used to accept incoming connection requests. Once
- * so marked, the endpoint is said to be in the listening state and may not be
- * used as the endpoint of a connection.
- *
- * The endpoint, epd, must have been bound to a port.
- *
- * The backlog argument defines the maximum length to which the queue of
- * pending connections for epd may grow. If a connection request arrives when
- * the queue is full, the client may receive an error with an indication that
- * the connection was refused.
- *
- * Return:
- * Upon successful completion, scif_listen() returns 0; otherwise in user mode
- * -1 is returned and errno is set to indicate the error; in kernel mode the
- * negative of one of the following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * EINVAL - the endpoint is not bound to a port
- * EISCONN - The endpoint is already connected or listening
- */
-int scif_listen(scif_epd_t epd, int backlog);
-
-/**
- * scif_connect() - Initiate a connection on a port
- * @epd: endpoint descriptor
- * @dst: global id of port to which to connect
- *
- * The scif_connect() function requests the connection of endpoint epd to remote
- * port dst. If the connection is successful, a peer endpoint, bound to dst, is
- * created on node dst.node. On successful return, the connection is complete.
- *
- * If the endpoint epd has not already been bound to a port, scif_connect()
- * will bind it to an unused local port.
- *
- * A connection is terminated when an endpoint of the connection is closed,
- * either explicitly by scif_close(), or when a process that owns one of the
- * endpoints of the connection is terminated.
- *
- * In user space, scif_connect() supports an asynchronous connection mode
- * if the application has set the O_NONBLOCK flag on the endpoint via the
- * fcntl() system call. Setting this flag will result in the calling process
- * not to wait during scif_connect().
- *
- * Return:
- * Upon successful completion, scif_connect() returns the port ID to which the
- * endpoint, epd, is bound; otherwise in user mode -1 is returned and errno is
- * set to indicate the error; in kernel mode the negative of one of the
- * following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNREFUSED - The destination was not listening for connections or refused
- * the connection request
- * EINVAL - dst.port is not a valid port ID
- * EISCONN - The endpoint is already connected
- * ENOMEM - No buffer space is available
- * ENODEV - The destination node does not exist, or the node is lost or existed,
- * but is not currently in the network since it may have crashed
- * ENOSPC - No port number available for assignment
- * EOPNOTSUPP - The endpoint is listening and cannot be connected
- */
-int scif_connect(scif_epd_t epd, struct scif_port_id *dst);
-
-/**
- * scif_accept() - Accept a connection on an endpoint
- * @epd: endpoint descriptor
- * @peer: global id of port to which connected
- * @newepd: new connected endpoint descriptor
- * @flags: flags
- *
- * The scif_accept() call extracts the first connection request from the queue
- * of pending connections for the port on which epd is listening. scif_accept()
- * creates a new endpoint, bound to the same port as epd, and allocates a new
- * SCIF endpoint descriptor, returned in newepd, for the endpoint. The new
- * endpoint is connected to the endpoint through which the connection was
- * requested. epd is unaffected by this call, and remains in the listening
- * state.
- *
- * On successful return, peer holds the global port identifier (node id and
- * local port number) of the port which requested the connection.
- *
- * A connection is terminated when an endpoint of the connection is closed,
- * either explicitly by scif_close(), or when a process that owns one of the
- * endpoints of the connection is terminated.
- *
- * The number of connections that can (subsequently) be accepted on epd is only
- * limited by system resources (memory).
- *
- * The flags argument is formed by OR'ing together zero or more of the
- * following values.
- * SCIF_ACCEPT_SYNC - block until a connection request is presented. If
- * SCIF_ACCEPT_SYNC is not in flags, and no pending
- * connections are present on the queue, scif_accept()
- * fails with an EAGAIN error
- *
- * In user mode, the select() and poll() functions can be used to determine
- * when there is a connection request. In kernel mode, the scif_poll()
- * function may be used for this purpose. A readable event will be delivered
- * when a connection is requested.
- *
- * Return:
- * Upon successful completion, scif_accept() returns 0; otherwise in user mode
- * -1 is returned and errno is set to indicate the error; in kernel mode the
- * negative of one of the following errors is returned.
- *
- * Errors:
- * EAGAIN - SCIF_ACCEPT_SYNC is not set and no connections are present to be
- * accepted or SCIF_ACCEPT_SYNC is not set and remote node failed to complete
- * its connection request
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * EINTR - Interrupted function
- * EINVAL - epd is not a listening endpoint, or flags is invalid, or peer is
- * NULL, or newepd is NULL
- * ENODEV - The requesting node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOMEM - Not enough space
- * ENOENT - Secondary part of epd registration failed
- */
-int scif_accept(scif_epd_t epd, struct scif_port_id *peer, scif_epd_t
- *newepd, int flags);
-
-/**
- * scif_close() - Close an endpoint
- * @epd: endpoint descriptor
- *
- * scif_close() closes an endpoint and performs necessary teardown of
- * facilities associated with that endpoint.
- *
- * If epd is a listening endpoint then it will no longer accept connection
- * requests on the port to which it is bound. Any pending connection requests
- * are rejected.
- *
- * If epd is a connected endpoint, then its peer endpoint is also closed. RMAs
- * which are in-process through epd or its peer endpoint will complete before
- * scif_close() returns. Registered windows of the local and peer endpoints are
- * released as if scif_unregister() was called against each window.
- *
- * Closing a SCIF endpoint does not affect local registered memory mapped by
- * a SCIF endpoint on a remote node. The local memory remains mapped by the peer
- * SCIF endpoint explicitly removed by calling munmap(..) by the peer.
- *
- * If the peer endpoint's receive queue is not empty at the time that epd is
- * closed, then the peer endpoint can be passed as the endpoint parameter to
- * scif_recv() until the receive queue is empty.
- *
- * epd is freed and may no longer be accessed.
- *
- * Return:
- * Upon successful completion, scif_close() returns 0; otherwise in user mode
- * -1 is returned and errno is set to indicate the error; in kernel mode the
- * negative of one of the following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- */
-int scif_close(scif_epd_t epd);
-
-/**
- * scif_send() - Send a message
- * @epd: endpoint descriptor
- * @msg: message buffer address
- * @len: message length
- * @flags: blocking mode flags
- *
- * scif_send() sends data to the peer of endpoint epd. Up to len bytes of data
- * are copied from memory starting at address msg. On successful execution the
- * return value of scif_send() is the number of bytes that were sent, and is
- * zero if no bytes were sent because len was zero. scif_send() may be called
- * only when the endpoint is in a connected state.
- *
- * If a scif_send() call is non-blocking, then it sends only those bytes which
- * can be sent without waiting, up to a maximum of len bytes.
- *
- * If a scif_send() call is blocking, then it normally returns after sending
- * all len bytes. If a blocking call is interrupted or the connection is
- * reset, the call is considered successful if some bytes were sent or len is
- * zero, otherwise the call is considered unsuccessful.
- *
- * In user mode, the select() and poll() functions can be used to determine
- * when the send queue is not full. In kernel mode, the scif_poll() function
- * may be used for this purpose.
- *
- * It is recommended that scif_send()/scif_recv() only be used for short
- * control-type message communication between SCIF endpoints. The SCIF RMA
- * APIs are expected to provide better performance for transfer sizes of
- * 1024 bytes or longer for the current MIC hardware and software
- * implementation.
- *
- * scif_send() will block until the entire message is sent if SCIF_SEND_BLOCK
- * is passed as the flags argument.
- *
- * Return:
- * Upon successful completion, scif_send() returns the number of bytes sent;
- * otherwise in user mode -1 is returned and errno is set to indicate the
- * error; in kernel mode the negative of one of the following errors is
- * returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - flags is invalid, or len is negative
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOMEM - Not enough space
- * ENOTCONN - The endpoint is not connected
- */
-int scif_send(scif_epd_t epd, void *msg, int len, int flags);
-
-/**
- * scif_recv() - Receive a message
- * @epd: endpoint descriptor
- * @msg: message buffer address
- * @len: message buffer length
- * @flags: blocking mode flags
- *
- * scif_recv() receives data from the peer of endpoint epd. Up to len bytes of
- * data are copied to memory starting at address msg. On successful execution
- * the return value of scif_recv() is the number of bytes that were received,
- * and is zero if no bytes were received because len was zero. scif_recv() may
- * be called only when the endpoint is in a connected state.
- *
- * If a scif_recv() call is non-blocking, then it receives only those bytes
- * which can be received without waiting, up to a maximum of len bytes.
- *
- * If a scif_recv() call is blocking, then it normally returns after receiving
- * all len bytes. If the blocking call was interrupted due to a disconnection,
- * subsequent calls to scif_recv() will copy all bytes received upto the point
- * of disconnection.
- *
- * In user mode, the select() and poll() functions can be used to determine
- * when data is available to be received. In kernel mode, the scif_poll()
- * function may be used for this purpose.
- *
- * It is recommended that scif_send()/scif_recv() only be used for short
- * control-type message communication between SCIF endpoints. The SCIF RMA
- * APIs are expected to provide better performance for transfer sizes of
- * 1024 bytes or longer for the current MIC hardware and software
- * implementation.
- *
- * scif_recv() will block until the entire message is received if
- * SCIF_RECV_BLOCK is passed as the flags argument.
- *
- * Return:
- * Upon successful completion, scif_recv() returns the number of bytes
- * received; otherwise in user mode -1 is returned and errno is set to
- * indicate the error; in kernel mode the negative of one of the following
- * errors is returned.
- *
- * Errors:
- * EAGAIN - The destination node is returning from a low power state
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - flags is invalid, or len is negative
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOMEM - Not enough space
- * ENOTCONN - The endpoint is not connected
- */
-int scif_recv(scif_epd_t epd, void *msg, int len, int flags);
-
-/**
- * scif_register() - Mark a memory region for remote access.
- * @epd: endpoint descriptor
- * @addr: starting virtual address
- * @len: length of range
- * @offset: offset of window
- * @prot_flags: read/write protection flags
- * @map_flags: mapping flags
- *
- * The scif_register() function opens a window, a range of whole pages of the
- * registered address space of the endpoint epd, starting at offset po and
- * continuing for len bytes. The value of po, further described below, is a
- * function of the parameters offset and len, and the value of map_flags. Each
- * page of the window represents the physical memory page which backs the
- * corresponding page of the range of virtual address pages starting at addr
- * and continuing for len bytes. addr and len are constrained to be multiples
- * of the page size. A successful scif_register() call returns po.
- *
- * When SCIF_MAP_FIXED is set in the map_flags argument, po will be offset
- * exactly, and offset is constrained to be a multiple of the page size. The
- * mapping established by scif_register() will not replace any existing
- * registration; an error is returned if any page within the range [offset,
- * offset + len - 1] intersects an existing window.
- *
- * When SCIF_MAP_FIXED is not set, the implementation uses offset in an
- * implementation-defined manner to arrive at po. The po value so chosen will
- * be an area of the registered address space that the implementation deems
- * suitable for a mapping of len bytes. An offset value of 0 is interpreted as
- * granting the implementation complete freedom in selecting po, subject to
- * constraints described below. A non-zero value of offset is taken to be a
- * suggestion of an offset near which the mapping should be placed. When the
- * implementation selects a value for po, it does not replace any extant
- * window. In all cases, po will be a multiple of the page size.
- *
- * The physical pages which are so represented by a window are available for
- * access in calls to mmap(), scif_readfrom(), scif_writeto(),
- * scif_vreadfrom(), and scif_vwriteto(). While a window is registered, the
- * physical pages represented by the window will not be reused by the memory
- * subsystem for any other purpose. Note that the same physical page may be
- * represented by multiple windows.
- *
- * Subsequent operations which change the memory pages to which virtual
- * addresses are mapped (such as mmap(), munmap()) have no effect on
- * existing window.
- *
- * If the process will fork(), it is recommended that the registered
- * virtual address range be marked with MADV_DONTFORK. Doing so will prevent
- * problems due to copy-on-write semantics.
- *
- * The prot_flags argument is formed by OR'ing together one or more of the
- * following values.
- * SCIF_PROT_READ - allow read operations from the window
- * SCIF_PROT_WRITE - allow write operations to the window
- *
- * Return:
- * Upon successful completion, scif_register() returns the offset at which the
- * mapping was placed (po); otherwise in user mode SCIF_REGISTER_FAILED (that
- * is (off_t *)-1) is returned and errno is set to indicate the error; in
- * kernel mode the negative of one of the following errors is returned.
- *
- * Errors:
- * EADDRINUSE - SCIF_MAP_FIXED is set in map_flags, and pages in the range
- * [offset, offset + len -1] are already registered
- * EAGAIN - The mapping could not be performed due to lack of resources
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - map_flags is invalid, or prot_flags is invalid, or SCIF_MAP_FIXED is
- * set in flags, and offset is not a multiple of the page size, or addr is not a
- * multiple of the page size, or len is not a multiple of the page size, or is
- * 0, or offset is negative
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOMEM - Not enough space
- * ENOTCONN -The endpoint is not connected
- */
-off_t scif_register(scif_epd_t epd, void *addr, size_t len, off_t offset,
- int prot_flags, int map_flags);
-
-/**
- * scif_unregister() - Mark a memory region for remote access.
- * @epd: endpoint descriptor
- * @offset: start of range to unregister
- * @len: length of range to unregister
- *
- * The scif_unregister() function closes those previously registered windows
- * which are entirely within the range [offset, offset + len - 1]. It is an
- * error to specify a range which intersects only a subrange of a window.
- *
- * On a successful return, pages within the window may no longer be specified
- * in calls to mmap(), scif_readfrom(), scif_writeto(), scif_vreadfrom(),
- * scif_vwriteto(), scif_get_pages, and scif_fence_signal(). The window,
- * however, continues to exist until all previous references against it are
- * removed. A window is referenced if there is a mapping to it created by
- * mmap(), or if scif_get_pages() was called against the window
- * (and the pages have not been returned via scif_put_pages()). A window is
- * also referenced while an RMA, in which some range of the window is a source
- * or destination, is in progress. Finally a window is referenced while some
- * offset in that window was specified to scif_fence_signal(), and the RMAs
- * marked by that call to scif_fence_signal() have not completed. While a
- * window is in this state, its registered address space pages are not
- * available for use in a new registered window.
- *
- * When all such references to the window have been removed, its references to
- * all the physical pages which it represents are removed. Similarly, the
- * registered address space pages of the window become available for
- * registration in a new window.
- *
- * Return:
- * Upon successful completion, scif_unregister() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned. In the event of an
- * error, no windows are unregistered.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - the range [offset, offset + len - 1] intersects a subrange of a
- * window, or offset is negative
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - Offsets in the range [offset, offset + len - 1] are invalid for the
- * registered address space of epd
- */
-int scif_unregister(scif_epd_t epd, off_t offset, size_t len);
-
-/**
- * scif_readfrom() - Copy from a remote address space
- * @epd: endpoint descriptor
- * @loffset: offset in local registered address space to
- * which to copy
- * @len: length of range to copy
- * @roffset: offset in remote registered address space
- * from which to copy
- * @rma_flags: transfer mode flags
- *
- * scif_readfrom() copies len bytes from the remote registered address space of
- * the peer of endpoint epd, starting at the offset roffset to the local
- * registered address space of epd, starting at the offset loffset.
- *
- * Each of the specified ranges [loffset, loffset + len - 1] and [roffset,
- * roffset + len - 1] must be within some registered window or windows of the
- * local and remote nodes. A range may intersect multiple registered windows,
- * but only if those windows are contiguous in the registered address space.
- *
- * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using
- * programmed read/writes. Otherwise the data is copied using DMA. If rma_-
- * flags includes SCIF_RMA_SYNC, then scif_readfrom() will return after the
- * transfer is complete. Otherwise, the transfer may be performed asynchron-
- * ously. The order in which any two asynchronous RMA operations complete
- * is non-deterministic. The synchronization functions, scif_fence_mark()/
- * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to
- * the completion of asynchronous RMA operations on the same endpoint.
- *
- * The DMA transfer of individual bytes is not guaranteed to complete in
- * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last
- * cacheline or partial cacheline of the source range will become visible on
- * the destination node after all other transferred data in the source
- * range has become visible on the destination node.
- *
- * The optimal DMA performance will likely be realized if both
- * loffset and roffset are cacheline aligned (are a multiple of 64). Lower
- * performance will likely be realized if loffset and roffset are not
- * cacheline aligned but are separated by some multiple of 64. The lowest level
- * of performance is likely if loffset and roffset are not separated by a
- * multiple of 64.
- *
- * The rma_flags argument is formed by ORing together zero or more of the
- * following values.
- * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA
- * engine.
- * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the
- * transfer has completed. Passing this flag results in the
- * current implementation busy waiting and consuming CPU cycles
- * while the DMA transfer is in progress for best performance by
- * avoiding the interrupt latency.
- * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of
- * the source range becomes visible on the destination node
- * after all other transferred data in the source range has
- * become visible on the destination
- *
- * Return:
- * Upon successful completion, scif_readfrom() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EACCES - Attempt to write to a read-only range
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - rma_flags is invalid
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - The range [loffset, loffset + len - 1] is invalid for the registered
- * address space of epd, or, The range [roffset, roffset + len - 1] is invalid
- * for the registered address space of the peer of epd, or loffset or roffset
- * is negative
- */
-int scif_readfrom(scif_epd_t epd, off_t loffset, size_t len, off_t
- roffset, int rma_flags);
-
-/**
- * scif_writeto() - Copy to a remote address space
- * @epd: endpoint descriptor
- * @loffset: offset in local registered address space
- * from which to copy
- * @len: length of range to copy
- * @roffset: offset in remote registered address space to
- * which to copy
- * @rma_flags: transfer mode flags
- *
- * scif_writeto() copies len bytes from the local registered address space of
- * epd, starting at the offset loffset to the remote registered address space
- * of the peer of endpoint epd, starting at the offset roffset.
- *
- * Each of the specified ranges [loffset, loffset + len - 1] and [roffset,
- * roffset + len - 1] must be within some registered window or windows of the
- * local and remote nodes. A range may intersect multiple registered windows,
- * but only if those windows are contiguous in the registered address space.
- *
- * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using
- * programmed read/writes. Otherwise the data is copied using DMA. If rma_-
- * flags includes SCIF_RMA_SYNC, then scif_writeto() will return after the
- * transfer is complete. Otherwise, the transfer may be performed asynchron-
- * ously. The order in which any two asynchronous RMA operations complete
- * is non-deterministic. The synchronization functions, scif_fence_mark()/
- * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to
- * the completion of asynchronous RMA operations on the same endpoint.
- *
- * The DMA transfer of individual bytes is not guaranteed to complete in
- * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last
- * cacheline or partial cacheline of the source range will become visible on
- * the destination node after all other transferred data in the source
- * range has become visible on the destination node.
- *
- * The optimal DMA performance will likely be realized if both
- * loffset and roffset are cacheline aligned (are a multiple of 64). Lower
- * performance will likely be realized if loffset and roffset are not cacheline
- * aligned but are separated by some multiple of 64. The lowest level of
- * performance is likely if loffset and roffset are not separated by a multiple
- * of 64.
- *
- * The rma_flags argument is formed by ORing together zero or more of the
- * following values.
- * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA
- * engine.
- * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the
- * transfer has completed. Passing this flag results in the
- * current implementation busy waiting and consuming CPU cycles
- * while the DMA transfer is in progress for best performance by
- * avoiding the interrupt latency.
- * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of
- * the source range becomes visible on the destination node
- * after all other transferred data in the source range has
- * become visible on the destination
- *
- * Return:
- * Upon successful completion, scif_readfrom() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EACCES - Attempt to write to a read-only range
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - rma_flags is invalid
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - The range [loffset, loffset + len - 1] is invalid for the registered
- * address space of epd, or, The range [roffset , roffset + len -1] is invalid
- * for the registered address space of the peer of epd, or loffset or roffset
- * is negative
- */
-int scif_writeto(scif_epd_t epd, off_t loffset, size_t len, off_t
- roffset, int rma_flags);
-
-/**
- * scif_vreadfrom() - Copy from a remote address space
- * @epd: endpoint descriptor
- * @addr: address to which to copy
- * @len: length of range to copy
- * @roffset: offset in remote registered address space
- * from which to copy
- * @rma_flags: transfer mode flags
- *
- * scif_vreadfrom() copies len bytes from the remote registered address
- * space of the peer of endpoint epd, starting at the offset roffset, to local
- * memory, starting at addr.
- *
- * The specified range [roffset, roffset + len - 1] must be within some
- * registered window or windows of the remote nodes. The range may
- * intersect multiple registered windows, but only if those windows are
- * contiguous in the registered address space.
- *
- * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using
- * programmed read/writes. Otherwise the data is copied using DMA. If rma_-
- * flags includes SCIF_RMA_SYNC, then scif_vreadfrom() will return after the
- * transfer is complete. Otherwise, the transfer may be performed asynchron-
- * ously. The order in which any two asynchronous RMA operations complete
- * is non-deterministic. The synchronization functions, scif_fence_mark()/
- * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to
- * the completion of asynchronous RMA operations on the same endpoint.
- *
- * The DMA transfer of individual bytes is not guaranteed to complete in
- * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last
- * cacheline or partial cacheline of the source range will become visible on
- * the destination node after all other transferred data in the source
- * range has become visible on the destination node.
- *
- * If rma_flags includes SCIF_RMA_USECACHE, then the physical pages which back
- * the specified local memory range may be remain in a pinned state even after
- * the specified transfer completes. This may reduce overhead if some or all of
- * the same virtual address range is referenced in a subsequent call of
- * scif_vreadfrom() or scif_vwriteto().
- *
- * The optimal DMA performance will likely be realized if both
- * addr and roffset are cacheline aligned (are a multiple of 64). Lower
- * performance will likely be realized if addr and roffset are not
- * cacheline aligned but are separated by some multiple of 64. The lowest level
- * of performance is likely if addr and roffset are not separated by a
- * multiple of 64.
- *
- * The rma_flags argument is formed by ORing together zero or more of the
- * following values.
- * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA
- * engine.
- * SCIF_RMA_USECACHE - enable registration caching
- * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the
- * transfer has completed. Passing this flag results in the
- * current implementation busy waiting and consuming CPU cycles
- * while the DMA transfer is in progress for best performance by
- * avoiding the interrupt latency.
- * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of
- * the source range becomes visible on the destination node
- * after all other transferred data in the source range has
- * become visible on the destination
- *
- * Return:
- * Upon successful completion, scif_vreadfrom() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EACCES - Attempt to write to a read-only range
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - rma_flags is invalid
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - Offsets in the range [roffset, roffset + len - 1] are invalid for the
- * registered address space of epd
- */
-int scif_vreadfrom(scif_epd_t epd, void *addr, size_t len, off_t roffset,
- int rma_flags);
-
-/**
- * scif_vwriteto() - Copy to a remote address space
- * @epd: endpoint descriptor
- * @addr: address from which to copy
- * @len: length of range to copy
- * @roffset: offset in remote registered address space to
- * which to copy
- * @rma_flags: transfer mode flags
- *
- * scif_vwriteto() copies len bytes from the local memory, starting at addr, to
- * the remote registered address space of the peer of endpoint epd, starting at
- * the offset roffset.
- *
- * The specified range [roffset, roffset + len - 1] must be within some
- * registered window or windows of the remote nodes. The range may intersect
- * multiple registered windows, but only if those windows are contiguous in the
- * registered address space.
- *
- * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using
- * programmed read/writes. Otherwise the data is copied using DMA. If rma_-
- * flags includes SCIF_RMA_SYNC, then scif_vwriteto() will return after the
- * transfer is complete. Otherwise, the transfer may be performed asynchron-
- * ously. The order in which any two asynchronous RMA operations complete
- * is non-deterministic. The synchronization functions, scif_fence_mark()/
- * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to
- * the completion of asynchronous RMA operations on the same endpoint.
- *
- * The DMA transfer of individual bytes is not guaranteed to complete in
- * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last
- * cacheline or partial cacheline of the source range will become visible on
- * the destination node after all other transferred data in the source
- * range has become visible on the destination node.
- *
- * If rma_flags includes SCIF_RMA_USECACHE, then the physical pages which back
- * the specified local memory range may be remain in a pinned state even after
- * the specified transfer completes. This may reduce overhead if some or all of
- * the same virtual address range is referenced in a subsequent call of
- * scif_vreadfrom() or scif_vwriteto().
- *
- * The optimal DMA performance will likely be realized if both
- * addr and offset are cacheline aligned (are a multiple of 64). Lower
- * performance will likely be realized if addr and offset are not cacheline
- * aligned but are separated by some multiple of 64. The lowest level of
- * performance is likely if addr and offset are not separated by a multiple of
- * 64.
- *
- * The rma_flags argument is formed by ORing together zero or more of the
- * following values.
- * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA
- * engine.
- * SCIF_RMA_USECACHE - allow registration caching
- * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the
- * transfer has completed. Passing this flag results in the
- * current implementation busy waiting and consuming CPU cycles
- * while the DMA transfer is in progress for best performance by
- * avoiding the interrupt latency.
- * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of
- * the source range becomes visible on the destination node
- * after all other transferred data in the source range has
- * become visible on the destination
- *
- * Return:
- * Upon successful completion, scif_vwriteto() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EACCES - Attempt to write to a read-only range
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - rma_flags is invalid
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - Offsets in the range [roffset, roffset + len - 1] are invalid for the
- * registered address space of epd
- */
-int scif_vwriteto(scif_epd_t epd, void *addr, size_t len, off_t roffset,
- int rma_flags);
-
-/**
- * scif_fence_mark() - Mark previously issued RMAs
- * @epd: endpoint descriptor
- * @flags: control flags
- * @mark: marked value returned as output.
- *
- * scif_fence_mark() returns after marking the current set of all uncompleted
- * RMAs initiated through the endpoint epd or the current set of all
- * uncompleted RMAs initiated through the peer of endpoint epd. The RMAs are
- * marked with a value returned at mark. The application may subsequently call
- * scif_fence_wait(), passing the value returned at mark, to await completion
- * of all RMAs so marked.
- *
- * The flags argument has exactly one of the following values.
- * SCIF_FENCE_INIT_SELF - RMA operations initiated through endpoint
- * epd are marked
- * SCIF_FENCE_INIT_PEER - RMA operations initiated through the peer
- * of endpoint epd are marked
- *
- * Return:
- * Upon successful completion, scif_fence_mark() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - flags is invalid
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENOMEM - Insufficient kernel memory was available
- */
-int scif_fence_mark(scif_epd_t epd, int flags, int *mark);
-
-/**
- * scif_fence_wait() - Wait for completion of marked RMAs
- * @epd: endpoint descriptor
- * @mark: mark request
- *
- * scif_fence_wait() returns after all RMAs marked with mark have completed.
- * The value passed in mark must have been obtained in a previous call to
- * scif_fence_mark().
- *
- * Return:
- * Upon successful completion, scif_fence_wait() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENOMEM - Insufficient kernel memory was available
- */
-int scif_fence_wait(scif_epd_t epd, int mark);
-
-/**
- * scif_fence_signal() - Request a memory update on completion of RMAs
- * @epd: endpoint descriptor
- * @loff: local offset
- * @lval: local value to write to loffset
- * @roff: remote offset
- * @rval: remote value to write to roffset
- * @flags: flags
- *
- * scif_fence_signal() returns after marking the current set of all uncompleted
- * RMAs initiated through the endpoint epd or marking the current set of all
- * uncompleted RMAs initiated through the peer of endpoint epd.
- *
- * If flags includes SCIF_SIGNAL_LOCAL, then on completion of the RMAs in the
- * marked set, lval is written to memory at the address corresponding to offset
- * loff in the local registered address space of epd. loff must be within a
- * registered window. If flags includes SCIF_SIGNAL_REMOTE, then on completion
- * of the RMAs in the marked set, rval is written to memory at the address
- * corresponding to offset roff in the remote registered address space of epd.
- * roff must be within a remote registered window of the peer of epd. Note
- * that any specified offset must be DWORD (4 byte / 32 bit) aligned.
- *
- * The flags argument is formed by OR'ing together the following.
- * Exactly one of the following values.
- * SCIF_FENCE_INIT_SELF - RMA operations initiated through endpoint
- * epd are marked
- * SCIF_FENCE_INIT_PEER - RMA operations initiated through the peer
- * of endpoint epd are marked
- * One or more of the following values.
- * SCIF_SIGNAL_LOCAL - On completion of the marked set of RMAs, write lval to
- * memory at the address corresponding to offset loff in the local
- * registered address space of epd.
- * SCIF_SIGNAL_REMOTE - On completion of the marked set of RMAs, write rval to
- * memory at the address corresponding to offset roff in the remote
- * registered address space of epd.
- *
- * Return:
- * Upon successful completion, scif_fence_signal() returns 0; otherwise in
- * user mode -1 is returned and errno is set to indicate the error; in kernel
- * mode the negative of one of the following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - flags is invalid, or loff or roff are not DWORD aligned
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - loff is invalid for the registered address of epd, or roff is invalid
- * for the registered address space, of the peer of epd
- */
-int scif_fence_signal(scif_epd_t epd, off_t loff, u64 lval, off_t roff,
- u64 rval, int flags);
-
-/**
- * scif_get_node_ids() - Return information about online nodes
- * @nodes: array in which to return online node IDs
- * @len: number of entries in the nodes array
- * @self: address to place the node ID of the local node
- *
- * scif_get_node_ids() fills in the nodes array with up to len node IDs of the
- * nodes in the SCIF network. If there is not enough space in nodes, as
- * indicated by the len parameter, only len node IDs are returned in nodes. The
- * return value of scif_get_node_ids() is the total number of nodes currently in
- * the SCIF network. By checking the return value against the len parameter,
- * the user may determine if enough space for nodes was allocated.
- *
- * The node ID of the local node is returned at self.
- *
- * Return:
- * Upon successful completion, scif_get_node_ids() returns the actual number of
- * online nodes in the SCIF network including 'self'; otherwise in user mode
- * -1 is returned and errno is set to indicate the error; in kernel mode no
- * errors are returned.
- */
-int scif_get_node_ids(u16 *nodes, int len, u16 *self);
-
-/**
- * scif_pin_pages() - Pin a set of pages
- * @addr: Virtual address of range to pin
- * @len: Length of range to pin
- * @prot_flags: Page protection flags
- * @map_flags: Page classification flags
- * @pinned_pages: Handle to pinned pages
- *
- * scif_pin_pages() pins (locks in physical memory) the physical pages which
- * back the range of virtual address pages starting at addr and continuing for
- * len bytes. addr and len are constrained to be multiples of the page size. A
- * successful scif_pin_pages() call returns a handle to pinned_pages which may
- * be used in subsequent calls to scif_register_pinned_pages().
- *
- * The pages will remain pinned as long as there is a reference against the
- * scif_pinned_pages_t value returned by scif_pin_pages() and until
- * scif_unpin_pages() is called, passing the scif_pinned_pages_t value. A
- * reference is added to a scif_pinned_pages_t value each time a window is
- * created by calling scif_register_pinned_pages() and passing the
- * scif_pinned_pages_t value. A reference is removed from a
- * scif_pinned_pages_t value each time such a window is deleted.
- *
- * Subsequent operations which change the memory pages to which virtual
- * addresses are mapped (such as mmap(), munmap()) have no effect on the
- * scif_pinned_pages_t value or windows created against it.
- *
- * If the process will fork(), it is recommended that the registered
- * virtual address range be marked with MADV_DONTFORK. Doing so will prevent
- * problems due to copy-on-write semantics.
- *
- * The prot_flags argument is formed by OR'ing together one or more of the
- * following values.
- * SCIF_PROT_READ - allow read operations against the pages
- * SCIF_PROT_WRITE - allow write operations against the pages
- * The map_flags argument can be set as SCIF_MAP_KERNEL to interpret addr as a
- * kernel space address. By default, addr is interpreted as a user space
- * address.
- *
- * Return:
- * Upon successful completion, scif_pin_pages() returns 0; otherwise the
- * negative of one of the following errors is returned.
- *
- * Errors:
- * EINVAL - prot_flags is invalid, map_flags is invalid, or offset is negative
- * ENOMEM - Not enough space
- */
-int scif_pin_pages(void *addr, size_t len, int prot_flags, int map_flags,
- scif_pinned_pages_t *pinned_pages);
-
-/**
- * scif_unpin_pages() - Unpin a set of pages
- * @pinned_pages: Handle to pinned pages to be unpinned
- *
- * scif_unpin_pages() prevents scif_register_pinned_pages() from registering new
- * windows against pinned_pages. The physical pages represented by pinned_pages
- * will remain pinned until all windows previously registered against
- * pinned_pages are deleted (the window is scif_unregister()'d and all
- * references to the window are removed (see scif_unregister()).
- *
- * pinned_pages must have been obtain from a previous call to scif_pin_pages().
- * After calling scif_unpin_pages(), it is an error to pass pinned_pages to
- * scif_register_pinned_pages().
- *
- * Return:
- * Upon successful completion, scif_unpin_pages() returns 0; otherwise the
- * negative of one of the following errors is returned.
- *
- * Errors:
- * EINVAL - pinned_pages is not valid
- */
-int scif_unpin_pages(scif_pinned_pages_t pinned_pages);
-
-/**
- * scif_register_pinned_pages() - Mark a memory region for remote access.
- * @epd: endpoint descriptor
- * @pinned_pages: Handle to pinned pages
- * @offset: Registered address space offset
- * @map_flags: Flags which control where pages are mapped
- *
- * The scif_register_pinned_pages() function opens a window, a range of whole
- * pages of the registered address space of the endpoint epd, starting at
- * offset po. The value of po, further described below, is a function of the
- * parameters offset and pinned_pages, and the value of map_flags. Each page of
- * the window represents a corresponding physical memory page of the range
- * represented by pinned_pages; the length of the window is the same as the
- * length of range represented by pinned_pages. A successful
- * scif_register_pinned_pages() call returns po as the return value.
- *
- * When SCIF_MAP_FIXED is set in the map_flags argument, po will be offset
- * exactly, and offset is constrained to be a multiple of the page size. The
- * mapping established by scif_register_pinned_pages() will not replace any
- * existing registration; an error is returned if any page of the new window
- * would intersect an existing window.
- *
- * When SCIF_MAP_FIXED is not set, the implementation uses offset in an
- * implementation-defined manner to arrive at po. The po so chosen will be an
- * area of the registered address space that the implementation deems suitable
- * for a mapping of the required size. An offset value of 0 is interpreted as
- * granting the implementation complete freedom in selecting po, subject to
- * constraints described below. A non-zero value of offset is taken to be a
- * suggestion of an offset near which the mapping should be placed. When the
- * implementation selects a value for po, it does not replace any extant
- * window. In all cases, po will be a multiple of the page size.
- *
- * The physical pages which are so represented by a window are available for
- * access in calls to scif_get_pages(), scif_readfrom(), scif_writeto(),
- * scif_vreadfrom(), and scif_vwriteto(). While a window is registered, the
- * physical pages represented by the window will not be reused by the memory
- * subsystem for any other purpose. Note that the same physical page may be
- * represented by multiple windows.
- *
- * Windows created by scif_register_pinned_pages() are unregistered by
- * scif_unregister().
- *
- * The map_flags argument can be set to SCIF_MAP_FIXED which interprets a
- * fixed offset.
- *
- * Return:
- * Upon successful completion, scif_register_pinned_pages() returns the offset
- * at which the mapping was placed (po); otherwise the negative of one of the
- * following errors is returned.
- *
- * Errors:
- * EADDRINUSE - SCIF_MAP_FIXED is set in map_flags and pages in the new window
- * would intersect an existing window
- * EAGAIN - The mapping could not be performed due to lack of resources
- * ECONNRESET - Connection reset by peer
- * EINVAL - map_flags is invalid, or SCIF_MAP_FIXED is set in map_flags, and
- * offset is not a multiple of the page size, or offset is negative
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOMEM - Not enough space
- * ENOTCONN - The endpoint is not connected
- */
-off_t scif_register_pinned_pages(scif_epd_t epd,
- scif_pinned_pages_t pinned_pages,
- off_t offset, int map_flags);
-
-/**
- * scif_get_pages() - Add references to remote registered pages
- * @epd: endpoint descriptor
- * @offset: remote registered offset
- * @len: length of range of pages
- * @pages: returned scif_range structure
- *
- * scif_get_pages() returns the addresses of the physical pages represented by
- * those pages of the registered address space of the peer of epd, starting at
- * offset and continuing for len bytes. offset and len are constrained to be
- * multiples of the page size.
- *
- * All of the pages in the specified range [offset, offset + len - 1] must be
- * within a single window of the registered address space of the peer of epd.
- *
- * The addresses are returned as a virtually contiguous array pointed to by the
- * phys_addr component of the scif_range structure whose address is returned in
- * pages. The nr_pages component of scif_range is the length of the array. The
- * prot_flags component of scif_range holds the protection flag value passed
- * when the pages were registered.
- *
- * Each physical page whose address is returned by scif_get_pages() remains
- * available and will not be released for reuse until the scif_range structure
- * is returned in a call to scif_put_pages(). The scif_range structure returned
- * by scif_get_pages() must be unmodified.
- *
- * It is an error to call scif_close() on an endpoint on which a scif_range
- * structure of that endpoint has not been returned to scif_put_pages().
- *
- * Return:
- * Upon successful completion, scif_get_pages() returns 0; otherwise the
- * negative of one of the following errors is returned.
- * Errors:
- * ECONNRESET - Connection reset by peer.
- * EINVAL - offset is not a multiple of the page size, or offset is negative, or
- * len is not a multiple of the page size
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - Offsets in the range [offset, offset + len - 1] are invalid
- * for the registered address space of the peer epd
- */
-int scif_get_pages(scif_epd_t epd, off_t offset, size_t len,
- struct scif_range **pages);
-
-/**
- * scif_put_pages() - Remove references from remote registered pages
- * @pages: pages to be returned
- *
- * scif_put_pages() releases a scif_range structure previously obtained by
- * calling scif_get_pages(). The physical pages represented by pages may
- * be reused when the window which represented those pages is unregistered.
- * Therefore, those pages must not be accessed after calling scif_put_pages().
- *
- * Return:
- * Upon successful completion, scif_put_pages() returns 0; otherwise the
- * negative of one of the following errors is returned.
- * Errors:
- * EINVAL - pages does not point to a valid scif_range structure, or
- * the scif_range structure pointed to by pages was already returned
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- */
-int scif_put_pages(struct scif_range *pages);
-
-/**
- * scif_poll() - Wait for some event on an endpoint
- * @epds: Array of endpoint descriptors
- * @nepds: Length of epds
- * @timeout: Upper limit on time for which scif_poll() will block
- *
- * scif_poll() waits for one of a set of endpoints to become ready to perform
- * an I/O operation.
- *
- * The epds argument specifies the endpoint descriptors to be examined and the
- * events of interest for each endpoint descriptor. epds is a pointer to an
- * array with one member for each open endpoint descriptor of interest.
- *
- * The number of items in the epds array is specified in nepds. The epd field
- * of scif_pollepd is an endpoint descriptor of an open endpoint. The field
- * events is a bitmask specifying the events which the application is
- * interested in. The field revents is an output parameter, filled by the
- * kernel with the events that actually occurred. The bits returned in revents
- * can include any of those specified in events, or one of the values EPOLLERR,
- * EPOLLHUP, or EPOLLNVAL. (These three bits are meaningless in the events
- * field, and will be set in the revents field whenever the corresponding
- * condition is true.)
- *
- * If none of the events requested (and no error) has occurred for any of the
- * endpoint descriptors, then scif_poll() blocks until one of the events occurs.
- *
- * The timeout argument specifies an upper limit on the time for which
- * scif_poll() will block, in milliseconds. Specifying a negative value in
- * timeout means an infinite timeout.
- *
- * The following bits may be set in events and returned in revents.
- * EPOLLIN - Data may be received without blocking. For a connected
- * endpoint, this means that scif_recv() may be called without blocking. For a
- * listening endpoint, this means that scif_accept() may be called without
- * blocking.
- * EPOLLOUT - Data may be sent without blocking. For a connected endpoint, this
- * means that scif_send() may be called without blocking. EPOLLOUT may also be
- * used to block waiting for a non-blocking connect to complete. This bit value
- * has no meaning for a listening endpoint and is ignored if specified.
- *
- * The following bits are only returned in revents, and are ignored if set in
- * events.
- * EPOLLERR - An error occurred on the endpoint
- * EPOLLHUP - The connection to the peer endpoint was disconnected
- * EPOLLNVAL - The specified endpoint descriptor is invalid.
- *
- * Return:
- * Upon successful completion, scif_poll() returns a non-negative value. A
- * positive value indicates the total number of endpoint descriptors that have
- * been selected (that is, endpoint descriptors for which the revents member is
- * non-zero). A value of 0 indicates that the call timed out and no endpoint
- * descriptors have been selected. Otherwise in user mode -1 is returned and
- * errno is set to indicate the error; in kernel mode the negative of one of
- * the following errors is returned.
- *
- * Errors:
- * EINTR - A signal occurred before any requested event
- * EINVAL - The nepds argument is greater than {OPEN_MAX}
- * ENOMEM - There was no space to allocate file descriptor tables
- */
-int scif_poll(struct scif_pollepd *epds, unsigned int nepds, long timeout);
-
-/**
- * scif_client_register() - Register a SCIF client
- * @client: client to be registered
- *
- * scif_client_register() registers a SCIF client. The probe() method
- * of the client is called when SCIF peer devices come online and the
- * remove() method is called when the peer devices disappear.
- *
- * Return:
- * Upon successful completion, scif_client_register() returns a non-negative
- * value. Otherwise the return value is the same as subsys_interface_register()
- * in the kernel.
- */
-int scif_client_register(struct scif_client *client);
-
-/**
- * scif_client_unregister() - Unregister a SCIF client
- * @client: client to be unregistered
- *
- * scif_client_unregister() unregisters a SCIF client.
- *
- * Return:
- * None
- */
-void scif_client_unregister(struct scif_client *client);
-
-#endif /* __SCIF_H__ */
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index 813614d..b83b3ae3 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -107,6 +107,7 @@
char *mangle_path(char *s, const char *p, const char *esc);
int seq_open(struct file *, const struct seq_operations *);
ssize_t seq_read(struct file *, char __user *, size_t, loff_t *);
+ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter);
loff_t seq_lseek(struct file *, loff_t, int);
int seq_release(struct inode *, struct file *);
int seq_write(struct seq_file *seq, const void *data, size_t len);
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 7bbc0e9..b256f9c 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -238,6 +238,7 @@
memset(&set->sig[1], 0, sizeof(long)*(_NSIG_WORDS-1));
break;
case 2: set->sig[1] = 0;
+ break;
case 1: ;
}
}
@@ -250,6 +251,7 @@
memset(&set->sig[1], -1, sizeof(long)*(_NSIG_WORDS-1));
break;
case 2: set->sig[1] = -1;
+ break;
case 1: ;
}
}
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 99380c0..b390fda 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -734,6 +734,25 @@
return __spi_alloc_controller(host, size, true);
}
+struct spi_controller *__devm_spi_alloc_controller(struct device *dev,
+ unsigned int size,
+ bool slave);
+
+static inline struct spi_controller *devm_spi_alloc_master(struct device *dev,
+ unsigned int size)
+{
+ return __devm_spi_alloc_controller(dev, size, false);
+}
+
+static inline struct spi_controller *devm_spi_alloc_slave(struct device *dev,
+ unsigned int size)
+{
+ if (!IS_ENABLED(CONFIG_SPI_SLAVE))
+ return NULL;
+
+ return __devm_spi_alloc_controller(dev, size, true);
+}
+
extern int spi_register_controller(struct spi_controller *ctlr);
extern int devm_spi_register_controller(struct device *dev,
struct spi_controller *ctlr);
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 513913f..fbdc657 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -5,6 +5,7 @@
#include <linux/dma-direction.h>
#include <linux/init.h>
#include <linux/types.h>
+#include <linux/limits.h>
struct device;
struct page;
@@ -45,13 +46,9 @@
SYNC_FOR_DEVICE = 1,
};
-extern phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
- dma_addr_t tbl_dma_addr,
- phys_addr_t phys,
- size_t mapping_size,
- size_t alloc_size,
- enum dma_data_direction dir,
- unsigned long attrs);
+phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
+ size_t mapping_size, size_t alloc_size,
+ enum dma_data_direction dir, unsigned long attrs);
extern void swiotlb_tbl_unmap_single(struct device *hwdev,
phys_addr_t tlb_addr,
diff --git a/include/linux/time64.h b/include/linux/time64.h
index c9dcb3e..5117cb5 100644
--- a/include/linux/time64.h
+++ b/include/linux/time64.h
@@ -124,6 +124,10 @@
*/
static inline s64 timespec64_to_ns(const struct timespec64 *ts)
{
+ /* Prevent multiplication overflow */
+ if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX)
+ return KTIME_MAX;
+
return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec;
}
diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index 2040696..a2d229a 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -437,7 +437,7 @@
#define OS_STRING_IDX 0xEE
/**
- * struct usb_composite_device - represents one composite usb gadget
+ * struct usb_composite_dev - represents one composite usb gadget
* @gadget: read-only, abstracts the gadget's usb peripheral controller
* @req: used for control responses; buffer is pre-allocated
* @os_desc_req: used for OS descriptors responses; buffer is pre-allocated
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index eae0bfd..30bc7a7 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -53,6 +53,16 @@
};
/**
+ * vDPA IOVA range - the IOVA range support by the device
+ * @first: start of the IOVA range
+ * @last: end of the IOVA range
+ */
+struct vdpa_iova_range {
+ u64 first;
+ u64 last;
+};
+
+/**
* vDPA_config_ops - operations for configuring a vDPA device.
* Note: vDPA device drivers are required to implement all of the
* operations unless it is mentioned to be optional in the following
@@ -151,6 +161,10 @@
* @get_generation: Get device config generation (optional)
* @vdev: vdpa device
* Returns u32: device generation
+ * @get_iova_range: Get supported iova range (optional)
+ * @vdev: vdpa device
+ * Returns the iova range supported by
+ * the device.
* @set_map: Set device memory mapping (optional)
* Needed for device that using device
* specific DMA translation (on-chip IOMMU)
@@ -216,6 +230,7 @@
void (*set_config)(struct vdpa_device *vdev, unsigned int offset,
const void *buf, unsigned int len);
u32 (*get_generation)(struct vdpa_device *vdev);
+ struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev);
/* DMA ops */
int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb);
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 661edfc..d5ab8d9 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1444,7 +1444,7 @@
enum cfg80211_station_type statype);
/**
- * enum station_info_rate_flags - bitrate info flags
+ * enum rate_info_flags - bitrate info flags
*
* Used by the driver to indicate the specific rate transmission
* type for 802.11n transmissions.
@@ -1517,7 +1517,7 @@
};
/**
- * enum station_info_rate_flags - bitrate info flags
+ * enum bss_param_flags - bitrate info flags
*
* Used by the driver to indicate the specific rate transmission
* type for 802.11n transmissions.
@@ -6467,7 +6467,8 @@
struct ieee80211_channel *channel, gfp_t gfp);
/**
- * cfg80211_notify_new_candidate - notify cfg80211 of a new mesh peer candidate
+ * cfg80211_notify_new_peer_candidate - notify cfg80211 of a new mesh peer
+ * candidate
*
* @dev: network device
* @macaddr: the MAC address of the new candidate
@@ -7606,7 +7607,7 @@
void cfg80211_unregister_wdev(struct wireless_dev *wdev);
/**
- * struct cfg80211_ft_event - FT Information Elements
+ * struct cfg80211_ft_event_params - FT Information Elements
* @ies: FT IEs
* @ies_len: length of the FT IE in bytes
* @target_ap: target AP's MAC address
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 02ccd32..6162067 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -478,9 +478,11 @@
const void *from, int len,
__be16 flags)
{
- memcpy(ip_tunnel_info_opts(info), from, len);
info->options_len = len;
- info->key.tun_flags |= flags;
+ if (len > 0) {
+ memcpy(ip_tunnel_info_opts(info), from, len);
+ info->key.tun_flags |= flags;
+ }
}
static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate)
@@ -526,7 +528,6 @@
__be16 flags)
{
info->options_len = 0;
- info->key.tun_flags |= flags;
}
#endif /* CONFIG_INET */
diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h
index a21e8b1..851029e 100644
--- a/include/net/ipv6_frag.h
+++ b/include/net/ipv6_frag.h
@@ -108,5 +108,35 @@
rcu_read_unlock();
inet_frag_put(&fq->q);
}
+
+/* Check if the upper layer header is truncated in the first fragment. */
+static inline bool
+ipv6frag_thdr_truncated(struct sk_buff *skb, int start, u8 *nexthdrp)
+{
+ u8 nexthdr = *nexthdrp;
+ __be16 frag_off;
+ int offset;
+
+ offset = ipv6_skip_exthdr(skb, start, &nexthdr, &frag_off);
+ if (offset < 0 || (frag_off & htons(IP6_OFFSET)))
+ return false;
+ switch (nexthdr) {
+ case NEXTHDR_TCP:
+ offset += sizeof(struct tcphdr);
+ break;
+ case NEXTHDR_UDP:
+ offset += sizeof(struct udphdr);
+ break;
+ case NEXTHDR_ICMP:
+ offset += sizeof(struct icmp6hdr);
+ break;
+ default:
+ offset += 1;
+ }
+ if (offset > skb->len)
+ return true;
+ return false;
+}
+
#endif
#endif
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index e8e295d..dcdba968 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -3311,7 +3311,7 @@
};
/**
- * enum ieee80211_reconfig_complete_type - reconfig type
+ * enum ieee80211_reconfig_type - reconfig type
*
* This enum is used by the reconfig_complete() callback to indicate what
* reconfiguration type was completed.
@@ -6334,7 +6334,8 @@
int band, struct ieee80211_sta **sta);
/**
- * Sanity-check and parse the radiotap header of injected frames
+ * ieee80211_parse_tx_radiotap - Sanity-check and parse the radiotap header
+ * of injected frames
* @skb: packet injected by userspace
* @dev: the &struct device of this 802.11 device
*/
@@ -6389,7 +6390,7 @@
void ieee80211_update_p2p_noa(struct ieee80211_noa_data *data, u32 tsf);
/**
- * ieee80211_tdls_oper - request userspace to perform a TDLS operation
+ * ieee80211_tdls_oper_request - request userspace to perform a TDLS operation
* @vif: virtual interface
* @peer: the peer's destination address
* @oper: the requested TDLS operation
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 81ee175..22ced13 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -204,6 +204,7 @@
int (*pconstructor)(struct pneigh_entry *);
void (*pdestructor)(struct pneigh_entry *);
void (*proxy_redo)(struct sk_buff *skb);
+ int (*is_multicast)(const void *pkey);
bool (*allow_add)(const struct net_device *dev,
struct netlink_ext_ack *extack);
char *id;
diff --git a/include/net/tls.h b/include/net/tls.h
index baf1e99..cf14730 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -300,7 +300,8 @@
#define TLS_DEVICE_RESYNC_ASYNC_LOGMAX 13
struct tls_offload_resync_async {
atomic64_t req;
- u32 loglen;
+ u16 loglen;
+ u16 rcd_delta;
u32 log[TLS_DEVICE_RESYNC_ASYNC_LOGMAX];
};
@@ -471,6 +472,18 @@
return (i == -1);
}
+static inline void tls_bigint_subtract(unsigned char *seq, int n)
+{
+ u64 rcd_sn;
+ __be64 *p;
+
+ BUILD_BUG_ON(TLS_MAX_REC_SEQ_SIZE != 8);
+
+ p = (__be64 *)seq;
+ rcd_sn = be64_to_cpu(*p);
+ *p = cpu_to_be64(rcd_sn - n);
+}
+
static inline struct tls_context *tls_get_ctx(const struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
@@ -639,6 +652,7 @@
atomic64_set(&rx_ctx->resync_async->req, ((u64)ntohl(seq) << 32) |
((u64)len << 16) | RESYNC_REQ | RESYNC_REQ_ASYNC);
rx_ctx->resync_async->loglen = 0;
+ rx_ctx->resync_async->rcd_delta = 0;
}
static inline void
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 0140d08..01755b8 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -86,7 +86,7 @@
void xp_destroy(struct xsk_buff_pool *pool);
void xp_release(struct xdp_buff_xsk *xskb);
void xp_get_pool(struct xsk_buff_pool *pool);
-void xp_put_pool(struct xsk_buff_pool *pool);
+bool xp_put_pool(struct xsk_buff_pool *pool);
void xp_clear_dev(struct xsk_buff_pool *pool);
void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index c672ae1..32a67af 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -227,19 +227,9 @@
int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr,
int *qp_attr_mask);
-/**
- * rdma_connect - Initiate an active connection request.
- * @id: Connection identifier to connect.
- * @conn_param: Connection information used for connected QPs.
- *
- * Users must have resolved a route for the rdma_cm_id to connect with
- * by having called rdma_resolve_route before calling this routine.
- *
- * This call will either connect to a remote QP or obtain remote QP
- * information for unconnected rdma_cm_id's. The actual operation is
- * based on the rdma_cm_id's port space.
- */
int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param);
+int rdma_connect_locked(struct rdma_cm_id *id,
+ struct rdma_conn_param *conn_param);
int rdma_connect_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
struct rdma_ucm_ece *ece);
diff --git a/include/sound/control.h b/include/sound/control.h
index e128cff..77d9fa1 100644
--- a/include/sound/control.h
+++ b/include/sound/control.h
@@ -42,7 +42,7 @@
snd_ctl_elem_iface_t iface; /* interface identifier */
unsigned int device; /* device/client number */
unsigned int subdevice; /* subdevice (substream) number */
- const unsigned char *name; /* ASCII name of item */
+ const char *name; /* ASCII name of item */
unsigned int index; /* index of item */
unsigned int access; /* access rights */
unsigned int count; /* count of same elements */
diff --git a/include/sound/core.h b/include/sound/core.h
index 381a010..0462c57 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -332,7 +332,8 @@
#define snd_BUG() WARN(1, "BUG?\n")
/**
- * Suppress high rates of output when CONFIG_SND_DEBUG is enabled.
+ * snd_printd_ratelimit - Suppress high rates of output when
+ * CONFIG_SND_DEBUG is enabled.
*/
#define snd_printd_ratelimit() printk_ratelimit()
diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 2ba5df2..2336bf9 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -1284,8 +1284,8 @@
}
/**
- * snd_pcm_sgbuf_chunk_size - Compute the max size that fits within the contig.
- * page from the given size
+ * snd_pcm_sgbuf_get_chunk_size - Compute the max size that fits within the
+ * contig. page from the given size
* @substream: PCM substream
* @ofs: byte offset
* @size: byte size to examine
diff --git a/include/sound/rt1015.h b/include/sound/rt1015.h
new file mode 100644
index 0000000..70a7538
--- /dev/null
+++ b/include/sound/rt1015.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * linux/sound/rt1015.h -- Platform data for RT1015
+ *
+ * Copyright 2020 Realtek Microelectronics
+ */
+
+#ifndef __LINUX_SND_RT1015_H
+#define __LINUX_SND_RT1015_H
+
+struct rt1015_platform_data {
+ unsigned int power_up_delay_ms;
+};
+
+#endif
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 8eb4923..4eef374 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -966,19 +966,6 @@
__entry->vnode, __entry->off, __entry->i_size)
);
-/*
- * We use page->private to hold the amount of the page that we've written to,
- * splitting the field into two parts. However, we need to represent a range
- * 0...PAGE_SIZE inclusive, so we can't support 64K pages on a 32-bit system.
- */
-#if PAGE_SIZE > 32768
-#define AFS_PRIV_MAX 0xffffffff
-#define AFS_PRIV_SHIFT 32
-#else
-#define AFS_PRIV_MAX 0xffff
-#define AFS_PRIV_SHIFT 16
-#endif
-
TRACE_EVENT(afs_page_dirty,
TP_PROTO(struct afs_vnode *vnode, const char *where,
pgoff_t page, unsigned long priv),
@@ -999,10 +986,11 @@
__entry->priv = priv;
),
- TP_printk("vn=%p %lx %s %lu-%lu",
+ TP_printk("vn=%p %lx %s %zx-%zx%s",
__entry->vnode, __entry->page, __entry->where,
- __entry->priv & AFS_PRIV_MAX,
- __entry->priv >> AFS_PRIV_SHIFT)
+ afs_page_dirty_from(__entry->priv),
+ afs_page_dirty_to(__entry->priv),
+ afs_is_page_dirty_mmapped(__entry->priv) ? " M" : "")
);
TRACE_EVENT(afs_call_state,
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index b14314fc..70ae549 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -100,11 +100,12 @@
{ EXT4_FC_REASON_XATTR, "XATTR"}, \
{ EXT4_FC_REASON_CROSS_RENAME, "CROSS_RENAME"}, \
{ EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \
- { EXT4_FC_REASON_MEM, "NO_MEM"}, \
+ { EXT4_FC_REASON_NOMEM, "NO_MEM"}, \
{ EXT4_FC_REASON_SWAP_BOOT, "SWAP_BOOT"}, \
{ EXT4_FC_REASON_RESIZE, "RESIZE"}, \
{ EXT4_FC_REASON_RENAME_DIR, "RENAME_DIR"}, \
- { EXT4_FC_REASON_FALLOC_RANGE, "FALLOC_RANGE"})
+ { EXT4_FC_REASON_FALLOC_RANGE, "FALLOC_RANGE"}, \
+ { EXT4_FC_REASON_INODE_JOURNAL_DATA, "INODE_JOURNAL_DATA"})
TRACE_EVENT(ext4_other_inode_update_time,
TP_PROTO(struct inode *inode, ino_t orig_ino),
@@ -2917,17 +2918,18 @@
),
TP_printk("dev %d:%d fc ineligible reasons:\n"
- "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s,%d; "
+ "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d; "
"num_commits:%ld, ineligible: %ld, numblks: %ld",
MAJOR(__entry->dev), MINOR(__entry->dev),
FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR),
FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME),
FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE),
- FC_REASON_NAME_STAT(EXT4_FC_REASON_MEM),
+ FC_REASON_NAME_STAT(EXT4_FC_REASON_NOMEM),
FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT),
FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE),
FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR),
FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE),
+ FC_REASON_NAME_STAT(EXT4_FC_REASON_INODE_JOURNAL_DATA),
__entry->sbi->s_fc_stats.fc_num_commits,
__entry->sbi->s_fc_stats.fc_ineligible_commits,
__entry->sbi->s_fc_stats.fc_numblks)
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index f45b3c0..2a03263 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -68,7 +68,8 @@
TP_fast_assign(
__entry->task_id = task->tk_pid;
- __entry->client_id = task->tk_client->cl_clid;
+ __entry->client_id = task->tk_client ?
+ task->tk_client->cl_clid : -1;
__entry->head_base = xdr->head[0].iov_base;
__entry->head_len = xdr->head[0].iov_len;
__entry->tail_base = xdr->tail[0].iov_base;
@@ -655,10 +656,10 @@
__field(size_t, tail_len)
__field(unsigned int, page_len)
__field(unsigned int, len)
- __string(progname,
- xdr->rqst->rq_task->tk_client->cl_program->name)
- __string(procedure,
- xdr->rqst->rq_task->tk_msg.rpc_proc->p_name)
+ __string(progname, xdr->rqst ?
+ xdr->rqst->rq_task->tk_client->cl_program->name : "unknown")
+ __string(procedure, xdr->rqst ?
+ xdr->rqst->rq_task->tk_msg.rpc_proc->p_name : "unknown")
),
TP_fast_assign(
diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h
index 07865c6..2072c26 100644
--- a/include/uapi/linux/gpio.h
+++ b/include/uapi/linux/gpio.h
@@ -26,7 +26,7 @@
* struct gpiochip_info - Information about a certain GPIO chip
* @name: the Linux kernel name of this GPIO chip
* @label: a functional name for this GPIO chip, such as a product
- * number, may be empty
+ * number, may be empty (i.e. label[0] == '\0')
* @lines: number of GPIO lines on this chip
*/
struct gpiochip_info {
@@ -98,7 +98,7 @@
* identifying which field of the attribute union is in use.
* @GPIO_V2_LINE_ATTR_ID_FLAGS: flags field is in use
* @GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES: values field is in use
- * @GPIO_V2_LINE_ATTR_ID_DEBOUNCE: debounce_period_us is in use
+ * @GPIO_V2_LINE_ATTR_ID_DEBOUNCE: debounce_period_us field is in use
*/
enum gpio_v2_line_attr_id {
GPIO_V2_LINE_ATTR_ID_FLAGS = 1,
@@ -110,17 +110,17 @@
* struct gpio_v2_line_attribute - a configurable attribute of a line
* @id: attribute identifier with value from &enum gpio_v2_line_attr_id
* @padding: reserved for future use and must be zero filled
- * @flags: if id is GPIO_V2_LINE_ATTR_ID_FLAGS, the flags for the GPIO
- * line, with values from enum gpio_v2_line_flag, such as
- * GPIO_V2_LINE_FLAG_ACTIVE_LOW, GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed
+ * @flags: if id is %GPIO_V2_LINE_ATTR_ID_FLAGS, the flags for the GPIO
+ * line, with values from &enum gpio_v2_line_flag, such as
+ * %GPIO_V2_LINE_FLAG_ACTIVE_LOW, %GPIO_V2_LINE_FLAG_OUTPUT etc, added
* together. This overrides the default flags contained in the &struct
* gpio_v2_line_config for the associated line.
- * @values: if id is GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES, a bitmap
+ * @values: if id is %GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES, a bitmap
* containing the values to which the lines will be set, with each bit
* number corresponding to the index into &struct
* gpio_v2_line_request.offsets.
- * @debounce_period_us: if id is GPIO_V2_LINE_ATTR_ID_DEBOUNCE, the desired
- * debounce period, in microseconds
+ * @debounce_period_us: if id is %GPIO_V2_LINE_ATTR_ID_DEBOUNCE, the
+ * desired debounce period, in microseconds
*/
struct gpio_v2_line_attribute {
__u32 id;
@@ -147,12 +147,12 @@
/**
* struct gpio_v2_line_config - Configuration for GPIO lines
- * @flags: flags for the GPIO lines, with values from enum
- * gpio_v2_line_flag, such as GPIO_V2_LINE_FLAG_ACTIVE_LOW,
- * GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed together. This is the default for
+ * @flags: flags for the GPIO lines, with values from &enum
+ * gpio_v2_line_flag, such as %GPIO_V2_LINE_FLAG_ACTIVE_LOW,
+ * %GPIO_V2_LINE_FLAG_OUTPUT etc, added together. This is the default for
* all requested lines but may be overridden for particular lines using
- * attrs.
- * @num_attrs: the number of attributes in attrs
+ * @attrs.
+ * @num_attrs: the number of attributes in @attrs
* @padding: reserved for future use and must be zero filled
* @attrs: the configuration attributes associated with the requested
* lines. Any attribute should only be associated with a particular line
@@ -175,17 +175,17 @@
* "my-bitbanged-relay"
* @config: requested configuration for the lines.
* @num_lines: number of lines requested in this request, i.e. the number
- * of valid fields in the GPIO_V2_LINES_MAX sized arrays, set to 1 to
+ * of valid fields in the %GPIO_V2_LINES_MAX sized arrays, set to 1 to
* request a single line
* @event_buffer_size: a suggested minimum number of line events that the
* kernel should buffer. This is only relevant if edge detection is
* enabled in the configuration. Note that this is only a suggested value
* and the kernel may allocate a larger buffer or cap the size of the
* buffer. If this field is zero then the buffer size defaults to a minimum
- * of num_lines*16.
+ * of @num_lines * 16.
* @padding: reserved for future use and must be zero filled
* @fd: if successful this field will contain a valid anonymous file handle
- * after a GPIO_GET_LINE_IOCTL operation, zero or negative value means
+ * after a %GPIO_GET_LINE_IOCTL operation, zero or negative value means
* error
*/
struct gpio_v2_line_request {
@@ -203,15 +203,16 @@
* struct gpio_v2_line_info - Information about a certain GPIO line
* @name: the name of this GPIO line, such as the output pin of the line on
* the chip, a rail or a pin header name on a board, as specified by the
- * GPIO chip, may be empty
+ * GPIO chip, may be empty (i.e. name[0] == '\0')
* @consumer: a functional name for the consumer of this GPIO line as set
* by whatever is using it, will be empty if there is no current user but
* may also be empty if the consumer doesn't set this up
- * @flags: flags for the GPIO line, such as GPIO_V2_LINE_FLAG_ACTIVE_LOW,
- * GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed together
* @offset: the local offset on this GPIO chip, fill this in when
* requesting the line information from the kernel
- * @num_attrs: the number of attributes in attrs
+ * @num_attrs: the number of attributes in @attrs
+ * @flags: flags for the GPIO lines, with values from &enum
+ * gpio_v2_line_flag, such as %GPIO_V2_LINE_FLAG_ACTIVE_LOW,
+ * %GPIO_V2_LINE_FLAG_OUTPUT etc, added together.
* @attrs: the configuration attributes associated with the line
* @padding: reserved for future use
*/
@@ -244,7 +245,7 @@
* of a GPIO line
* @info: updated line information
* @timestamp_ns: estimate of time of status change occurrence, in nanoseconds
- * @event_type: the type of change with a value from enum
+ * @event_type: the type of change with a value from &enum
* gpio_v2_line_changed_type
* @padding: reserved for future use
*/
@@ -269,10 +270,10 @@
/**
* struct gpio_v2_line_event - The actual event being pushed to userspace
* @timestamp_ns: best estimate of time of event occurrence, in nanoseconds.
- * The timestamp_ns is read from CLOCK_MONOTONIC and is intended to allow the
- * accurate measurement of the time between events. It does not provide
+ * The @timestamp_ns is read from %CLOCK_MONOTONIC and is intended to allow
+ * the accurate measurement of the time between events. It does not provide
* the wall-clock time.
- * @id: event identifier with value from enum gpio_v2_line_event_id
+ * @id: event identifier with value from &enum gpio_v2_line_event_id
* @offset: the offset of the line that triggered the event
* @seqno: the sequence number for this event in the sequence of events for
* all the lines in this line request
@@ -291,7 +292,7 @@
};
/*
- * ABI v1
+ * ABI v1
*
* This version of the ABI is deprecated.
* Use the latest version of the ABI, defined above, instead.
@@ -314,13 +315,13 @@
* @flags: various flags for this line
* @name: the name of this GPIO line, such as the output pin of the line on the
* chip, a rail or a pin header name on a board, as specified by the gpio
- * chip, may be empty
+ * chip, may be empty (i.e. name[0] == '\0')
* @consumer: a functional name for the consumer of this GPIO line as set by
* whatever is using it, will be empty if there is no current user but may
* also be empty if the consumer doesn't set this up
*
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_info instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_info instead.
*/
struct gpioline_info {
__u32 line_offset;
@@ -344,17 +345,18 @@
* of a GPIO line
* @info: updated line information
* @timestamp: estimate of time of status change occurrence, in nanoseconds
- * @event_type: one of GPIOLINE_CHANGED_REQUESTED, GPIOLINE_CHANGED_RELEASED
- * and GPIOLINE_CHANGED_CONFIG
+ * @event_type: one of %GPIOLINE_CHANGED_REQUESTED,
+ * %GPIOLINE_CHANGED_RELEASED and %GPIOLINE_CHANGED_CONFIG
+ * @padding: reserved for future use
*
- * Note: struct gpioline_info embedded here has 32-bit alignment on its own,
+ * The &struct gpioline_info embedded here has 32-bit alignment on its own,
* but it works fine with 64-bit alignment too. With its 72 byte size, we can
* guarantee there are no implicit holes between it and subsequent members.
* The 20-byte padding at the end makes sure we don't add any implicit padding
* at the end of the structure on 64-bit architectures.
*
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_info_changed instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_info_changed instead.
*/
struct gpioline_info_changed {
struct gpioline_info info;
@@ -378,13 +380,13 @@
* @lineoffsets: an array of desired lines, specified by offset index for the
* associated GPIO device
* @flags: desired flags for the desired GPIO lines, such as
- * GPIOHANDLE_REQUEST_OUTPUT, GPIOHANDLE_REQUEST_ACTIVE_LOW etc, OR:ed
+ * %GPIOHANDLE_REQUEST_OUTPUT, %GPIOHANDLE_REQUEST_ACTIVE_LOW etc, added
* together. Note that even if multiple lines are requested, the same flags
* must be applicable to all of them, if you want lines with individual
* flags set, request them one by one. It is possible to select
* a batch of input or output lines, but they must all have the same
* characteristics, i.e. all inputs or all outputs, all active low etc
- * @default_values: if the GPIOHANDLE_REQUEST_OUTPUT is set for a requested
+ * @default_values: if the %GPIOHANDLE_REQUEST_OUTPUT is set for a requested
* line, this specifies the default output value, should be 0 (low) or
* 1 (high), anything else than 0 or 1 will be interpreted as 1 (high)
* @consumer_label: a desired consumer label for the selected GPIO line(s)
@@ -392,11 +394,11 @@
* @lines: number of lines requested in this request, i.e. the number of
* valid fields in the above arrays, set to 1 to request a single line
* @fd: if successful this field will contain a valid anonymous file handle
- * after a GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value
+ * after a %GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value
* means error
*
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_request instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_request instead.
*/
struct gpiohandle_request {
__u32 lineoffsets[GPIOHANDLES_MAX];
@@ -410,15 +412,15 @@
/**
* struct gpiohandle_config - Configuration for a GPIO handle request
* @flags: updated flags for the requested GPIO lines, such as
- * GPIOHANDLE_REQUEST_OUTPUT, GPIOHANDLE_REQUEST_ACTIVE_LOW etc, OR:ed
+ * %GPIOHANDLE_REQUEST_OUTPUT, %GPIOHANDLE_REQUEST_ACTIVE_LOW etc, added
* together
- * @default_values: if the GPIOHANDLE_REQUEST_OUTPUT is set in flags,
+ * @default_values: if the %GPIOHANDLE_REQUEST_OUTPUT is set in flags,
* this specifies the default output value, should be 0 (low) or
* 1 (high), anything else than 0 or 1 will be interpreted as 1 (high)
* @padding: reserved for future use and should be zero filled
*
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_config instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_config instead.
*/
struct gpiohandle_config {
__u32 flags;
@@ -432,8 +434,8 @@
* state of a line, when setting the state of lines these should contain
* the desired target state
*
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_values instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_values instead.
*/
struct gpiohandle_data {
__u8 values[GPIOHANDLES_MAX];
@@ -449,17 +451,17 @@
* @lineoffset: the desired line to subscribe to events from, specified by
* offset index for the associated GPIO device
* @handleflags: desired handle flags for the desired GPIO line, such as
- * GPIOHANDLE_REQUEST_ACTIVE_LOW or GPIOHANDLE_REQUEST_OPEN_DRAIN
+ * %GPIOHANDLE_REQUEST_ACTIVE_LOW or %GPIOHANDLE_REQUEST_OPEN_DRAIN
* @eventflags: desired flags for the desired GPIO event line, such as
- * GPIOEVENT_REQUEST_RISING_EDGE or GPIOEVENT_REQUEST_FALLING_EDGE
+ * %GPIOEVENT_REQUEST_RISING_EDGE or %GPIOEVENT_REQUEST_FALLING_EDGE
* @consumer_label: a desired consumer label for the selected GPIO line(s)
* such as "my-listener"
* @fd: if successful this field will contain a valid anonymous file handle
- * after a GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value
+ * after a %GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value
* means error
*
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_request instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_request instead.
*/
struct gpioevent_request {
__u32 lineoffset;
@@ -469,7 +471,7 @@
int fd;
};
-/**
+/*
* GPIO event types
*/
#define GPIOEVENT_EVENT_RISING_EDGE 0x01
@@ -480,8 +482,8 @@
* @timestamp: best estimate of time of event occurrence, in nanoseconds
* @id: event identifier
*
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_event instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_event instead.
*/
struct gpioevent_data {
__u64 timestamp;
diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h
index c1661fe..0564fd7 100644
--- a/include/uapi/linux/icmpv6.h
+++ b/include/uapi/linux/icmpv6.h
@@ -138,6 +138,7 @@
#define ICMPV6_HDR_FIELD 0
#define ICMPV6_UNK_NEXTHDR 1
#define ICMPV6_UNK_OPTION 2
+#define ICMPV6_HDR_INCOMP 3
/*
* constants for (set|get)sockopt
diff --git a/include/uapi/linux/mic_common.h b/include/uapi/linux/mic_common.h
deleted file mode 100644
index 504e523..0000000
--- a/include/uapi/linux/mic_common.h
+++ /dev/null
@@ -1,235 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Intel MIC driver.
- *
- */
-#ifndef __MIC_COMMON_H_
-#define __MIC_COMMON_H_
-
-#include <linux/virtio_ring.h>
-
-#define __mic_align(a, x) (((a) + (x) - 1) & ~((x) - 1))
-
-/**
- * struct mic_device_desc: Virtio device information shared between the
- * virtio driver and userspace backend
- *
- * @type: Device type: console/network/disk etc. Type 0/-1 terminates.
- * @num_vq: Number of virtqueues.
- * @feature_len: Number of bytes of feature bits. Multiply by 2: one for
- host features and one for guest acknowledgements.
- * @config_len: Number of bytes of the config array after virtqueues.
- * @status: A status byte, written by the Guest.
- * @config: Start of the following variable length config.
- */
-struct mic_device_desc {
- __s8 type;
- __u8 num_vq;
- __u8 feature_len;
- __u8 config_len;
- __u8 status;
- __le64 config[0];
-} __attribute__ ((aligned(8)));
-
-/**
- * struct mic_device_ctrl: Per virtio device information in the device page
- * used internally by the host and card side drivers.
- *
- * @vdev: Used for storing MIC vdev information by the guest.
- * @config_change: Set to 1 by host when a config change is requested.
- * @vdev_reset: Set to 1 by guest to indicate virtio device has been reset.
- * @guest_ack: Set to 1 by guest to ack a command.
- * @host_ack: Set to 1 by host to ack a command.
- * @used_address_updated: Set to 1 by guest when the used address should be
- * updated.
- * @c2h_vdev_db: The doorbell number to be used by guest. Set by host.
- * @h2c_vdev_db: The doorbell number to be used by host. Set by guest.
- */
-struct mic_device_ctrl {
- __le64 vdev;
- __u8 config_change;
- __u8 vdev_reset;
- __u8 guest_ack;
- __u8 host_ack;
- __u8 used_address_updated;
- __s8 c2h_vdev_db;
- __s8 h2c_vdev_db;
-} __attribute__ ((aligned(8)));
-
-/**
- * struct mic_bootparam: Virtio device independent information in device page
- *
- * @magic: A magic value used by the card to ensure it can see the host
- * @h2c_config_db: Host to Card Virtio config doorbell set by card
- * @node_id: Unique id of the node
- * @h2c_scif_db - Host to card SCIF doorbell set by card
- * @c2h_scif_db - Card to host SCIF doorbell set by host
- * @scif_host_dma_addr - SCIF host queue pair DMA address
- * @scif_card_dma_addr - SCIF card queue pair DMA address
- */
-struct mic_bootparam {
- __le32 magic;
- __s8 h2c_config_db;
- __u8 node_id;
- __u8 h2c_scif_db;
- __u8 c2h_scif_db;
- __u64 scif_host_dma_addr;
- __u64 scif_card_dma_addr;
-} __attribute__ ((aligned(8)));
-
-/**
- * struct mic_device_page: High level representation of the device page
- *
- * @bootparam: The bootparam structure is used for sharing information and
- * status updates between MIC host and card drivers.
- * @desc: Array of MIC virtio device descriptors.
- */
-struct mic_device_page {
- struct mic_bootparam bootparam;
- struct mic_device_desc desc[0];
-};
-/**
- * struct mic_vqconfig: This is how we expect the device configuration field
- * for a virtqueue to be laid out in config space.
- *
- * @address: Guest/MIC physical address of the virtio ring
- * (avail and desc rings)
- * @used_address: Guest/MIC physical address of the used ring
- * @num: The number of entries in the virtio_ring
- */
-struct mic_vqconfig {
- __le64 address;
- __le64 used_address;
- __le16 num;
-} __attribute__ ((aligned(8)));
-
-/*
- * The alignment to use between consumer and producer parts of vring.
- * This is pagesize for historical reasons.
- */
-#define MIC_VIRTIO_RING_ALIGN 4096
-
-#define MIC_MAX_VRINGS 4
-#define MIC_VRING_ENTRIES 128
-
-/*
- * Max vring entries (power of 2) to ensure desc and avail rings
- * fit in a single page
- */
-#define MIC_MAX_VRING_ENTRIES 128
-
-/**
- * Max size of the desc block in bytes: includes:
- * - struct mic_device_desc
- * - struct mic_vqconfig (num_vq of these)
- * - host and guest features
- * - virtio device config space
- */
-#define MIC_MAX_DESC_BLK_SIZE 256
-
-/**
- * struct _mic_vring_info - Host vring info exposed to userspace backend
- * for the avail index and magic for the card.
- *
- * @avail_idx: host avail idx
- * @magic: A magic debug cookie.
- */
-struct _mic_vring_info {
- __u16 avail_idx;
- __le32 magic;
-};
-
-/**
- * struct mic_vring - Vring information.
- *
- * @vr: The virtio ring.
- * @info: Host vring information exposed to the userspace backend for the
- * avail index and magic for the card.
- * @va: The va for the buffer allocated for vr and info.
- * @len: The length of the buffer required for allocating vr and info.
- */
-struct mic_vring {
- struct vring vr;
- struct _mic_vring_info *info;
- void *va;
- int len;
-};
-
-#define mic_aligned_desc_size(d) __mic_align(mic_desc_size(d), 8)
-
-#ifndef INTEL_MIC_CARD
-static inline unsigned mic_desc_size(const struct mic_device_desc *desc)
-{
- return sizeof(*desc) + desc->num_vq * sizeof(struct mic_vqconfig)
- + desc->feature_len * 2 + desc->config_len;
-}
-
-static inline struct mic_vqconfig *
-mic_vq_config(const struct mic_device_desc *desc)
-{
- return (struct mic_vqconfig *)(desc + 1);
-}
-
-static inline __u8 *mic_vq_features(const struct mic_device_desc *desc)
-{
- return (__u8 *)(mic_vq_config(desc) + desc->num_vq);
-}
-
-static inline __u8 *mic_vq_configspace(const struct mic_device_desc *desc)
-{
- return mic_vq_features(desc) + desc->feature_len * 2;
-}
-static inline unsigned mic_total_desc_size(struct mic_device_desc *desc)
-{
- return mic_aligned_desc_size(desc) + sizeof(struct mic_device_ctrl);
-}
-#endif
-
-/* Device page size */
-#define MIC_DP_SIZE 4096
-
-#define MIC_MAGIC 0xc0ffee00
-
-/**
- * enum mic_states - MIC states.
- */
-enum mic_states {
- MIC_READY = 0,
- MIC_BOOTING,
- MIC_ONLINE,
- MIC_SHUTTING_DOWN,
- MIC_RESETTING,
- MIC_RESET_FAILED,
- MIC_LAST
-};
-
-/**
- * enum mic_status - MIC status reported by card after
- * a host or card initiated shutdown or a card crash.
- */
-enum mic_status {
- MIC_NOP = 0,
- MIC_CRASHED,
- MIC_HALTED,
- MIC_POWER_OFF,
- MIC_RESTART,
- MIC_STATUS_LAST
-};
-
-#endif
diff --git a/include/uapi/linux/mic_ioctl.h b/include/uapi/linux/mic_ioctl.h
deleted file mode 100644
index 687b9cd..0000000
--- a/include/uapi/linux/mic_ioctl.h
+++ /dev/null
@@ -1,77 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Intel MIC Host driver.
- *
- */
-#ifndef _MIC_IOCTL_H_
-#define _MIC_IOCTL_H_
-
-#include <linux/types.h>
-
-/*
- * mic_copy - MIC virtio descriptor copy.
- *
- * @iov: An array of IOVEC structures containing user space buffers.
- * @iovcnt: Number of IOVEC structures in iov.
- * @vr_idx: The vring index.
- * @update_used: A non zero value results in used index being updated.
- * @out_len: The aggregate of the total length written to or read from
- * the virtio device.
- */
-struct mic_copy_desc {
-#ifdef __KERNEL__
- struct iovec __user *iov;
-#else
- struct iovec *iov;
-#endif
- __u32 iovcnt;
- __u8 vr_idx;
- __u8 update_used;
- __u32 out_len;
-};
-
-/*
- * Add a new virtio device
- * The (struct mic_device_desc *) pointer points to a device page entry
- * for the virtio device consisting of:
- * - struct mic_device_desc
- * - struct mic_vqconfig (num_vq of these)
- * - host and guest features
- * - virtio device config space
- * The total size referenced by the pointer should equal the size returned
- * by desc_size() in mic_common.h
- */
-#define MIC_VIRTIO_ADD_DEVICE _IOWR('s', 1, struct mic_device_desc *)
-
-/*
- * Copy the number of entries in the iovec and update the used index
- * if requested by the user.
- */
-#define MIC_VIRTIO_COPY_DESC _IOWR('s', 2, struct mic_copy_desc *)
-
-/*
- * Notify virtio device of a config change
- * The (__u8 *) pointer points to config space values for the device
- * as they should be written into the device page. The total size
- * referenced by the pointer should equal the config_len field of struct
- * mic_device_desc.
- */
-#define MIC_VIRTIO_CONFIG_CHANGE _IOWR('s', 5, __u8 *)
-
-#endif
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index 7523218..c998860 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -146,4 +146,8 @@
/* Set event fd for config interrupt*/
#define VHOST_VDPA_SET_CONFIG_CALL _IOW(VHOST_VIRTIO, 0x77, int)
+
+/* Get the valid iova range */
+#define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \
+ struct vhost_vdpa_iova_range)
#endif
diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h
index 9a269a8..f7f6a3a 100644
--- a/include/uapi/linux/vhost_types.h
+++ b/include/uapi/linux/vhost_types.h
@@ -138,6 +138,15 @@
__u8 buf[0];
};
+/* vhost vdpa IOVA range
+ * @first: First address that can be mapped by vhost-vDPA
+ * @last: Last address that can be mapped by vhost-vDPA
+ */
+struct vhost_vdpa_iova_range {
+ __u64 first;
+ __u64 last;
+};
+
/* Feature bits */
/* Log all write descriptors. Can be changed while device is active. */
#define VHOST_F_LOG_ALL 26
diff --git a/include/uapi/sound/compress_offload.h b/include/uapi/sound/compress_offload.h
index 7184265..9555f31 100644
--- a/include/uapi/sound/compress_offload.h
+++ b/include/uapi/sound/compress_offload.h
@@ -144,7 +144,7 @@
__u32 value[8];
} __attribute__((packed, aligned(4)));
-/**
+/*
* compress path ioctl definitions
* SNDRV_COMPRESS_GET_CAPS: Query capability of DSP
* SNDRV_COMPRESS_GET_CODEC_CAPS: Query capability of a codec
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index 06b0b57e..d1b3889 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -484,9 +484,6 @@
enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc);
enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat);
-enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code);
-int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat);
-bool ipu_pixelformat_is_planar(u32 pixelformat);
int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees,
bool hflip, bool vflip);
int ipu_rot_mode_to_degrees(int *degrees, enum ipu_rotate_mode mode,
diff --git a/init/main.c b/init/main.c
index 130376e..20baced 100644
--- a/init/main.c
+++ b/init/main.c
@@ -269,14 +269,24 @@
u32 size, csum;
char *data;
u32 *hdr;
+ int i;
if (!initrd_end)
return NULL;
data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN;
- if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN))
- return NULL;
+ /*
+ * Since Grub may align the size of initrd to 4, we must
+ * check the preceding 3 bytes as well.
+ */
+ for (i = 0; i < 4; i++) {
+ if (!memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN))
+ goto found;
+ data--;
+ }
+ return NULL;
+found:
hdr = (u32 *)(data - 8);
size = hdr[0];
csum = hdr[1];
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index bdc8cd1..c1b9f71 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,6 +1,10 @@
# SPDX-License-Identifier: GPL-2.0
obj-y := core.o
-CFLAGS_core.o += $(call cc-disable-warning, override-init)
+ifneq ($(CONFIG_BPF_JIT_ALWAYS_ON),y)
+# ___bpf_prog_run() needs GCSE disabled on x86; see 3193c0836f203 for details
+cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse
+endif
+CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o
obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 78ea8a7..56cc5a9 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -13,6 +13,7 @@
#include <linux/bpf_verifier.h>
#include <net/bpf_sk_storage.h>
#include <linux/bpf_local_storage.h>
+#include <linux/btf_ids.h>
/* For every LSM hook that allows attachment of BPF programs, declare a nop
* function where a BPF program can be attached.
@@ -26,7 +27,11 @@
#include <linux/lsm_hook_defs.h>
#undef LSM_HOOK
-#define BPF_LSM_SYM_PREFX "bpf_lsm_"
+#define LSM_HOOK(RET, DEFAULT, NAME, ...) BTF_ID(func, bpf_lsm_##NAME)
+BTF_SET_START(bpf_lsm_hooks)
+#include <linux/lsm_hook_defs.h>
+#undef LSM_HOOK
+BTF_SET_END(bpf_lsm_hooks)
int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
const struct bpf_prog *prog)
@@ -37,8 +42,7 @@
return -EINVAL;
}
- if (strncmp(BPF_LSM_SYM_PREFX, prog->aux->attach_func_name,
- sizeof(BPF_LSM_SYM_PREFX) - 1)) {
+ if (!btf_id_set_contains(&bpf_lsm_hooks, prog->aux->attach_btf_id)) {
bpf_log(vlog, "attach_btf_id %u points to wrong type name %s\n",
prog->aux->attach_btf_id, prog->aux->attach_func_name);
return -EINVAL;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9268d77..55454d2 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1369,7 +1369,7 @@
*
* Decode and execute eBPF instructions.
*/
-static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
+static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
{
#define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y
#define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 1815e97..1fccba6 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -821,6 +821,32 @@
}
}
+static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr,
+ void *value, bool onallcpus)
+{
+ /* When using prealloc and not setting the initial value on all cpus,
+ * zero-fill element values for other cpus (just as what happens when
+ * not using prealloc). Otherwise, bpf program has no way to ensure
+ * known initial values for cpus other than current one
+ * (onallcpus=false always when coming from bpf prog).
+ */
+ if (htab_is_prealloc(htab) && !onallcpus) {
+ u32 size = round_up(htab->map.value_size, 8);
+ int current_cpu = raw_smp_processor_id();
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ if (cpu == current_cpu)
+ bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value,
+ size);
+ else
+ memset(per_cpu_ptr(pptr, cpu), 0, size);
+ }
+ } else {
+ pcpu_copy_value(htab, pptr, value, onallcpus);
+ }
+}
+
static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab)
{
return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS &&
@@ -891,7 +917,7 @@
}
}
- pcpu_copy_value(htab, pptr, value, onallcpus);
+ pcpu_init_value(htab, pptr, value, onallcpus);
if (!prealloc)
htab_elem_set_ptr(l_new, key_size, pptr);
@@ -1183,7 +1209,7 @@
pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
value, onallcpus);
} else {
- pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size),
+ pcpu_init_value(htab, htab_elem_get_ptr(l_new, key_size),
value, onallcpus);
hlist_nulls_add_head_rcu(&l_new->hash_node, head);
l_new = NULL;
diff --git a/kernel/bpf/preload/Kconfig b/kernel/bpf/preload/Kconfig
index ace4911..26bced2 100644
--- a/kernel/bpf/preload/Kconfig
+++ b/kernel/bpf/preload/Kconfig
@@ -6,6 +6,7 @@
menuconfig BPF_PRELOAD
bool "Preload BPF file system with kernel specific program and map iterators"
depends on BPF
+ depends on BPF_SYSCALL
# The dependency on !COMPILE_TEST prevents it from being enabled
# in allmodconfig or allyesconfig configurations
depends on !COMPILE_TEST
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6200519..1388bf7 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7786,9 +7786,11 @@
struct tnum range = tnum_range(0, 1);
enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
int err;
+ const bool is_subprog = env->cur_state->frame[0]->subprogno;
/* LSM and struct_ops func-ptr's return type could be "void" */
- if ((prog_type == BPF_PROG_TYPE_STRUCT_OPS ||
+ if (!is_subprog &&
+ (prog_type == BPF_PROG_TYPE_STRUCT_OPS ||
prog_type == BPF_PROG_TYPE_LSM) &&
!prog->aux->attach_func_proto->type)
return 0;
@@ -7808,6 +7810,16 @@
return -EACCES;
}
+ reg = cur_regs(env) + BPF_REG_0;
+ if (is_subprog) {
+ if (reg->type != SCALAR_VALUE) {
+ verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n",
+ reg_type_str[reg->type]);
+ return -EINVAL;
+ }
+ return 0;
+ }
+
switch (prog_type) {
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG ||
@@ -7861,7 +7873,6 @@
return 0;
}
- reg = cur_regs(env) + BPF_REG_0;
if (reg->type != SCALAR_VALUE) {
verbose(env, "At program exit the register R0 is not a known value (%s)\n",
reg_type_str[reg->type]);
@@ -9572,12 +9583,13 @@
struct bpf_insn *insn,
struct bpf_insn_aux_data *aux)
{
- u32 datasec_id, type, id = insn->imm;
const struct btf_var_secinfo *vsi;
const struct btf_type *datasec;
const struct btf_type *t;
const char *sym_name;
bool percpu = false;
+ u32 type, id = insn->imm;
+ s32 datasec_id;
u64 addr;
int i;
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index b4eea0a..781b9dc 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -229,6 +229,7 @@
io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
}
io_tlb_index = 0;
+ no_iotlb_memory = false;
if (verbose)
swiotlb_print_info();
@@ -260,9 +261,11 @@
if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose))
return;
- if (io_tlb_start)
+ if (io_tlb_start) {
memblock_free_early(io_tlb_start,
PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+ io_tlb_start = 0;
+ }
pr_warn("Cannot allocate buffer");
no_iotlb_memory = true;
}
@@ -360,6 +363,7 @@
io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
}
io_tlb_index = 0;
+ no_iotlb_memory = false;
swiotlb_print_info();
@@ -441,14 +445,11 @@
}
}
-phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
- dma_addr_t tbl_dma_addr,
- phys_addr_t orig_addr,
- size_t mapping_size,
- size_t alloc_size,
- enum dma_data_direction dir,
- unsigned long attrs)
+phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr,
+ size_t mapping_size, size_t alloc_size,
+ enum dma_data_direction dir, unsigned long attrs)
{
+ dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(hwdev, io_tlb_start);
unsigned long flags;
phys_addr_t tlb_addr;
unsigned int nslots, stride, index, wrap;
@@ -667,9 +668,8 @@
trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
swiotlb_force);
- swiotlb_addr = swiotlb_tbl_map_single(dev,
- phys_to_dma_unencrypted(dev, io_tlb_start),
- paddr, size, size, dir, attrs);
+ swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, dir,
+ attrs);
if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
return DMA_MAPPING_ERROR;
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 2b83666..e9e2df3 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -337,10 +337,10 @@
* already contains a warning when RCU is not watching, so no point
* in having another one here.
*/
+ lockdep_hardirqs_off(CALLER_ADDR0);
instrumentation_begin();
rcu_irq_enter_check_tick();
- /* Use the combo lockdep/tracing function */
- trace_hardirqs_off();
+ trace_hardirqs_off_finish();
instrumentation_end();
return ret;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index da467e1..dc568ca 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2312,9 +2312,6 @@
event_sched_out(event, cpuctx, ctx);
perf_pmu_enable(ctx->pmu);
-
- if (group_event->attr.exclusive)
- cpuctx->exclusive = 0;
}
#define DETACH_GROUP 0x01UL
@@ -2583,11 +2580,8 @@
pmu->start_txn(pmu, PERF_PMU_TXN_ADD);
- if (event_sched_in(group_event, cpuctx, ctx)) {
- pmu->cancel_txn(pmu);
- perf_mux_hrtimer_restart(cpuctx);
- return -EAGAIN;
- }
+ if (event_sched_in(group_event, cpuctx, ctx))
+ goto error;
/*
* Schedule in siblings as one group (if any):
@@ -2616,10 +2610,8 @@
}
event_sched_out(group_event, cpuctx, ctx);
+error:
pmu->cancel_txn(pmu);
-
- perf_mux_hrtimer_restart(cpuctx);
-
return -EAGAIN;
}
@@ -2645,7 +2637,7 @@
* If this group is exclusive and there are already
* events on the CPU, it can't go on.
*/
- if (event->attr.exclusive && cpuctx->active_oncpu)
+ if (event->attr.exclusive && !list_empty(get_event_list(event)))
return 0;
/*
* Otherwise, try to add it if all previous groups were able
@@ -3679,6 +3671,7 @@
*can_add_hw = 0;
ctx->rotate_necessary = 1;
+ perf_mux_hrtimer_restart(cpuctx);
}
return 0;
@@ -6374,14 +6367,13 @@
}
static void perf_sample_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
if (user_mode(regs)) {
regs_user->abi = perf_reg_abi(current);
regs_user->regs = regs;
} else if (!(current->flags & PF_KTHREAD)) {
- perf_get_regs_user(regs_user, regs, regs_user_copy);
+ perf_get_regs_user(regs_user, regs);
} else {
regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
regs_user->regs = NULL;
@@ -7083,8 +7075,7 @@
}
if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
- perf_sample_regs_user(&data->regs_user, regs,
- &data->regs_user_copy);
+ perf_sample_regs_user(&data->regs_user, regs);
if (sample_type & PERF_SAMPLE_REGS_USER) {
/* regs dump ABI info */
@@ -7186,6 +7177,7 @@
struct perf_sample_data *data,
struct pt_regs *regs,
int (*output_begin)(struct perf_output_handle *,
+ struct perf_sample_data *,
struct perf_event *,
unsigned int))
{
@@ -7198,7 +7190,7 @@
perf_prepare_sample(&header, data, event, regs);
- err = output_begin(&handle, event, header.size);
+ err = output_begin(&handle, data, event, header.size);
if (err)
goto exit;
@@ -7264,7 +7256,7 @@
int ret;
perf_event_header__init_id(&read_event.header, &sample, event);
- ret = perf_output_begin(&handle, event, read_event.header.size);
+ ret = perf_output_begin(&handle, &sample, event, read_event.header.size);
if (ret)
return;
@@ -7533,7 +7525,7 @@
perf_event_header__init_id(&task_event->event_id.header, &sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, &sample, event,
task_event->event_id.header.size);
if (ret)
goto out;
@@ -7636,7 +7628,7 @@
return;
perf_event_header__init_id(&comm_event->event_id.header, &sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, &sample, event,
comm_event->event_id.header.size);
if (ret)
@@ -7736,7 +7728,7 @@
perf_event_header__init_id(&namespaces_event->event_id.header,
&sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, &sample, event,
namespaces_event->event_id.header.size);
if (ret)
goto out;
@@ -7863,7 +7855,7 @@
perf_event_header__init_id(&cgroup_event->event_id.header,
&sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, &sample, event,
cgroup_event->event_id.header.size);
if (ret)
goto out;
@@ -7989,7 +7981,7 @@
}
perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, &sample, event,
mmap_event->event_id.header.size);
if (ret)
goto out;
@@ -8299,7 +8291,7 @@
int ret;
perf_event_header__init_id(&rec.header, &sample, event);
- ret = perf_output_begin(&handle, event, rec.header.size);
+ ret = perf_output_begin(&handle, &sample, event, rec.header.size);
if (ret)
return;
@@ -8333,7 +8325,7 @@
perf_event_header__init_id(&lost_samples_event.header, &sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, &sample, event,
lost_samples_event.header.size);
if (ret)
return;
@@ -8388,7 +8380,7 @@
perf_event_header__init_id(&se->event_id.header, &sample, event);
- ret = perf_output_begin(&handle, event, se->event_id.header.size);
+ ret = perf_output_begin(&handle, &sample, event, se->event_id.header.size);
if (ret)
return;
@@ -8463,7 +8455,7 @@
perf_event_header__init_id(&throttle_event.header, &sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, &sample, event,
throttle_event.header.size);
if (ret)
return;
@@ -8506,7 +8498,7 @@
perf_event_header__init_id(&ksymbol_event->event_id.header,
&sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, &sample, event,
ksymbol_event->event_id.header.size);
if (ret)
return;
@@ -8596,7 +8588,7 @@
perf_event_header__init_id(&bpf_event->event_id.header,
&sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, data, event,
bpf_event->event_id.header.size);
if (ret)
return;
@@ -8705,7 +8697,8 @@
perf_event_header__init_id(&text_poke_event->event_id.header, &sample, event);
- ret = perf_output_begin(&handle, event, text_poke_event->event_id.header.size);
+ ret = perf_output_begin(&handle, &sample, event,
+ text_poke_event->event_id.header.size);
if (ret)
return;
@@ -8786,7 +8779,7 @@
rec.tid = perf_event_tid(event, current);
perf_event_header__init_id(&rec.header, &sample, event);
- ret = perf_output_begin(&handle, event, rec.header.size);
+ ret = perf_output_begin(&handle, &sample, event, rec.header.size);
if (ret)
return;
@@ -10085,6 +10078,7 @@
if (token == IF_SRC_FILE || token == IF_SRC_FILEADDR) {
int fpos = token == IF_SRC_FILE ? 2 : 1;
+ kfree(filename);
filename = match_strdup(&args[fpos]);
if (!filename) {
ret = -ENOMEM;
@@ -10131,16 +10125,13 @@
*/
ret = -EOPNOTSUPP;
if (!event->ctx->task)
- goto fail_free_name;
+ goto fail;
/* look up the path and grab its inode */
ret = kern_path(filename, LOOKUP_FOLLOW,
&filter->path);
if (ret)
- goto fail_free_name;
-
- kfree(filename);
- filename = NULL;
+ goto fail;
ret = -EINVAL;
if (!filter->path.dentry ||
@@ -10160,13 +10151,13 @@
if (state != IF_STATE_ACTION)
goto fail;
+ kfree(filename);
kfree(orig);
return 0;
-fail_free_name:
- kfree(filename);
fail:
+ kfree(filename);
free_filters_list(filters);
kfree(orig);
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index fcbf561..228801e 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -205,16 +205,12 @@
static inline int get_recursion_context(int *recursion)
{
- int rctx;
+ unsigned int pc = preempt_count();
+ unsigned char rctx = 0;
- if (unlikely(in_nmi()))
- rctx = 3;
- else if (in_irq())
- rctx = 2;
- else if (in_softirq())
- rctx = 1;
- else
- rctx = 0;
+ rctx += !!(pc & (NMI_MASK));
+ rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK));
+ rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET));
if (recursion[rctx])
return -1;
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 192b8ab..ef91ae7 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -147,6 +147,7 @@
static __always_inline int
__perf_output_begin(struct perf_output_handle *handle,
+ struct perf_sample_data *data,
struct perf_event *event, unsigned int size,
bool backward)
{
@@ -237,18 +238,16 @@
handle->size = (1UL << page_shift) - offset;
if (unlikely(have_lost)) {
- struct perf_sample_data sample_data;
-
lost_event.header.size = sizeof(lost_event);
lost_event.header.type = PERF_RECORD_LOST;
lost_event.header.misc = 0;
lost_event.id = event->id;
lost_event.lost = local_xchg(&rb->lost, 0);
- perf_event_header__init_id(&lost_event.header,
- &sample_data, event);
+ /* XXX mostly redundant; @data is already fully initializes */
+ perf_event_header__init_id(&lost_event.header, data, event);
perf_output_put(handle, lost_event);
- perf_event__output_id_sample(event, handle, &sample_data);
+ perf_event__output_id_sample(event, handle, data);
}
return 0;
@@ -263,22 +262,25 @@
}
int perf_output_begin_forward(struct perf_output_handle *handle,
- struct perf_event *event, unsigned int size)
+ struct perf_sample_data *data,
+ struct perf_event *event, unsigned int size)
{
- return __perf_output_begin(handle, event, size, false);
+ return __perf_output_begin(handle, data, event, size, false);
}
int perf_output_begin_backward(struct perf_output_handle *handle,
+ struct perf_sample_data *data,
struct perf_event *event, unsigned int size)
{
- return __perf_output_begin(handle, event, size, true);
+ return __perf_output_begin(handle, data, event, size, true);
}
int perf_output_begin(struct perf_output_handle *handle,
+ struct perf_sample_data *data,
struct perf_event *event, unsigned int size)
{
- return __perf_output_begin(handle, event, size,
+ return __perf_output_begin(handle, data, event, size,
unlikely(is_write_backward(event)));
}
diff --git a/kernel/exit.c b/kernel/exit.c
index 87a2d51..1f236ed 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -454,7 +454,10 @@
mmap_read_unlock(mm);
self.task = current;
- self.next = xchg(&core_state->dumper.next, &self);
+ if (self.task->flags & PF_SIGNALED)
+ self.next = xchg(&core_state->dumper.next, &self);
+ else
+ self.task = NULL;
/*
* Implies mb(), the result of xchg() must be visible
* to core_state->dumper.
diff --git a/kernel/fail_function.c b/kernel/fail_function.c
index 63b3491..b0b1ad9 100644
--- a/kernel/fail_function.c
+++ b/kernel/fail_function.c
@@ -253,7 +253,7 @@
if (copy_from_user(buf, buffer, count)) {
ret = -EFAULT;
- goto out;
+ goto out_free;
}
buf[count] = '\0';
sym = strstrip(buf);
@@ -307,8 +307,9 @@
ret = count;
}
out:
- kfree(buf);
mutex_unlock(&fei_lock);
+out_free:
+ kfree(buf);
return ret;
}
diff --git a/kernel/fork.c b/kernel/fork.c
index 32083db..6d26638 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2167,14 +2167,9 @@
/* ok, now we should be set up.. */
p->pid = pid_nr(pid);
if (clone_flags & CLONE_THREAD) {
- p->exit_signal = -1;
p->group_leader = current->group_leader;
p->tgid = current->tgid;
} else {
- if (clone_flags & CLONE_PARENT)
- p->exit_signal = current->group_leader->exit_signal;
- else
- p->exit_signal = args->exit_signal;
p->group_leader = p;
p->tgid = p->pid;
}
@@ -2218,9 +2213,14 @@
if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
p->real_parent = current->real_parent;
p->parent_exec_id = current->parent_exec_id;
+ if (clone_flags & CLONE_THREAD)
+ p->exit_signal = -1;
+ else
+ p->exit_signal = current->group_leader->exit_signal;
} else {
p->real_parent = current;
p->parent_exec_id = current->self_exec_id;
+ p->exit_signal = args->exit_signal;
}
klp_copy_process(p);
diff --git a/kernel/futex.c b/kernel/futex.c
index be68ac0..00259c7 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -788,8 +788,9 @@
*/
if (pi_state->owner) {
struct task_struct *owner;
+ unsigned long flags;
- raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+ raw_spin_lock_irqsave(&pi_state->pi_mutex.wait_lock, flags);
owner = pi_state->owner;
if (owner) {
raw_spin_lock(&owner->pi_lock);
@@ -797,7 +798,7 @@
raw_spin_unlock(&owner->pi_lock);
}
rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner);
- raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+ raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags);
}
if (current->pi_state_cache) {
@@ -1503,8 +1504,10 @@
*/
newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
- if (unlikely(should_fail_futex(true)))
+ if (unlikely(should_fail_futex(true))) {
ret = -EFAULT;
+ goto out_unlock;
+ }
ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
if (!ret && (curval != uval)) {
@@ -2378,10 +2381,22 @@
}
/*
- * Since we just failed the trylock; there must be an owner.
+ * The trylock just failed, so either there is an owner or
+ * there is a higher priority waiter than this one.
*/
newowner = rt_mutex_owner(&pi_state->pi_mutex);
- BUG_ON(!newowner);
+ /*
+ * If the higher priority waiter has not yet taken over the
+ * rtmutex then newowner is NULL. We can't return here with
+ * that state because it's inconsistent vs. the user space
+ * state. So drop the locks and try again. It's a valid
+ * situation and not any different from the other retry
+ * conditions.
+ */
+ if (unlikely(!newowner)) {
+ err = -EAGAIN;
+ goto handle_err;
+ }
} else {
WARN_ON_ONCE(argowner != current);
if (oldowner == current) {
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index ce76f49..396ebae 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -225,8 +225,7 @@
* Process updating of timeout sysctl
*/
int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
- void __user *buffer,
- size_t *lenp, loff_t *ppos)
+ void *buffer, size_t *lenp, loff_t *ppos)
{
int ret;
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 10a5aff..164a031 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -82,6 +82,7 @@
# Generic IRQ IPI support
config GENERIC_IRQ_IPI
bool
+ select IRQ_DOMAIN_HIERARCHY
# Generic MSI interrupt support
config GENERIC_MSI_IRQ
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 8a12a25..41fdbb7 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1249,7 +1249,13 @@
*head = &kretprobe_inst_table[hash];
hlist_lock = kretprobe_table_lock_ptr(hash);
- raw_spin_lock_irqsave(hlist_lock, *flags);
+ /*
+ * Nested is a workaround that will soon not be needed.
+ * There's other protections that make sure the same lock
+ * is not taken on the same CPU that lockdep is unaware of.
+ * Differentiate when it is taken in NMI context.
+ */
+ raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi());
}
NOKPROBE_SYMBOL(kretprobe_hash_lock);
@@ -1258,7 +1264,13 @@
__acquires(hlist_lock)
{
raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
- raw_spin_lock_irqsave(hlist_lock, *flags);
+ /*
+ * Nested is a workaround that will soon not be needed.
+ * There's other protections that make sure the same lock
+ * is not taken on the same CPU that lockdep is unaware of.
+ * Differentiate when it is taken in NMI context.
+ */
+ raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi());
}
NOKPROBE_SYMBOL(kretprobe_table_lock);
@@ -2028,7 +2040,12 @@
/* TODO: consider to only swap the RA after the last pre_handler fired */
hash = hash_ptr(current, KPROBE_HASH_BITS);
- raw_spin_lock_irqsave(&rp->lock, flags);
+ /*
+ * Nested is a workaround that will soon not be needed.
+ * There's other protections that make sure the same lock
+ * is not taken on the same CPU that lockdep is unaware of.
+ */
+ raw_spin_lock_irqsave_nested(&rp->lock, flags, 1);
if (!hlist_empty(&rp->free_instances)) {
ri = hlist_entry(rp->free_instances.first,
struct kretprobe_instance, hlist);
@@ -2039,7 +2056,7 @@
ri->task = current;
if (rp->entry_handler && rp->entry_handler(ri, regs)) {
- raw_spin_lock_irqsave(&rp->lock, flags);
+ raw_spin_lock_irqsave_nested(&rp->lock, flags, 1);
hlist_add_head(&ri->hlist, &rp->free_instances);
raw_spin_unlock_irqrestore(&rp->lock, flags);
return 0;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index e29773c..933a625 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -897,7 +897,8 @@
/* Move the work from worker->delayed_work_list. */
WARN_ON_ONCE(list_empty(&work->node));
list_del_init(&work->node);
- kthread_insert_work(worker, work, &worker->work_list);
+ if (!work->canceling)
+ kthread_insert_work(worker, work, &worker->work_list);
raw_spin_unlock_irqrestore(&worker->lock, flags);
}
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 3e99dfe..d9fb9e1 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -84,7 +84,7 @@
if (!debug_locks)
return false;
- if (raw_cpu_read(lockdep_recursion))
+ if (this_cpu_read(lockdep_recursion))
return false;
if (current->lockdep_recursion)
@@ -2765,7 +2765,9 @@
* (Note that this has to be done separately, because the graph cannot
* detect such classes of deadlocks.)
*
- * Returns: 0 on deadlock detected, 1 on OK, 2 on recursive read
+ * Returns: 0 on deadlock detected, 1 on OK, 2 if another lock with the same
+ * lock class is held but nest_lock is also held, i.e. we rely on the
+ * nest_lock to avoid the deadlock.
*/
static int
check_deadlock(struct task_struct *curr, struct held_lock *next)
@@ -2788,7 +2790,7 @@
* lock class (i.e. read_lock(lock)+read_lock(lock)):
*/
if ((next->read == 2) && prev->read)
- return 2;
+ continue;
/*
* We're holding the nest_lock, which serializes this lock's
@@ -3593,15 +3595,12 @@
if (!ret)
return 0;
/*
- * Mark recursive read, as we jump over it when
- * building dependencies (just like we jump over
- * trylock entries):
- */
- if (ret == 2)
- hlock->read = 2;
- /*
* Add dependency only if this lock is not the head
- * of the chain, and if it's not a secondary read-lock:
+ * of the chain, and if the new lock introduces no more
+ * lock dependency (because we already hold a lock with the
+ * same lock class) nor deadlock (because the nest_lock
+ * serializes nesting locks), see the comments for
+ * check_deadlock().
*/
if (!chain_head && ret != 2) {
if (!check_prevs_add(curr, hlock))
@@ -4057,7 +4056,7 @@
if (unlikely(in_nmi()))
return;
- if (unlikely(__this_cpu_read(lockdep_recursion)))
+ if (unlikely(this_cpu_read(lockdep_recursion)))
return;
if (unlikely(lockdep_hardirqs_enabled())) {
@@ -4126,7 +4125,7 @@
goto skip_checks;
}
- if (unlikely(__this_cpu_read(lockdep_recursion)))
+ if (unlikely(this_cpu_read(lockdep_recursion)))
return;
if (lockdep_hardirqs_enabled()) {
@@ -4396,6 +4395,9 @@
if (unlikely(hlock_class(this)->usage_mask & new_mask))
goto unlock;
+ if (!hlock_class(this)->usage_mask)
+ debug_atomic_dec(nr_unused_locks);
+
hlock_class(this)->usage_mask |= new_mask;
if (new_bit < LOCK_TRACE_STATES) {
@@ -4403,19 +4405,10 @@
return 0;
}
- switch (new_bit) {
- case 0 ... LOCK_USED-1:
+ if (new_bit < LOCK_USED) {
ret = mark_lock_irq(curr, this, new_bit);
if (!ret)
return 0;
- break;
-
- case LOCK_USED:
- debug_atomic_dec(nr_unused_locks);
- break;
-
- default:
- break;
}
unlock:
diff --git a/kernel/panic.c b/kernel/panic.c
index 396142e..332736a 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -605,7 +605,8 @@
panic("panic_on_warn set ...\n");
}
- dump_stack();
+ if (!regs)
+ dump_stack();
print_irqtrace_events(current);
diff --git a/kernel/params.c b/kernel/params.c
index 3835fb8..164d793 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -530,7 +530,7 @@
{
unsigned int num;
struct attribute_group grp;
- struct param_attribute attrs[0];
+ struct param_attribute attrs[];
};
#ifdef CONFIG_SYSFS
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 4b6a54d..45b054b 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -146,7 +146,7 @@
BUG_ON(in_atomic());
/*
- * Now that the whole userspace is frozen we need to disbale
+ * Now that the whole userspace is frozen we need to disable
* the OOM killer to disallow any further interference with
* killable tasks. There is no guarantee oom victims will
* ever reach a point they go away we have to wait with a timeout.
diff --git a/kernel/printk/printk_ringbuffer.c b/kernel/printk/printk_ringbuffer.c
index 24a960a..6b15256 100644
--- a/kernel/printk/printk_ringbuffer.c
+++ b/kernel/printk/printk_ringbuffer.c
@@ -345,7 +345,7 @@
*/
struct prb_data_block {
unsigned long id;
- char data[0];
+ char data[];
};
/*
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 06895ef..bd04b09 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -409,7 +409,7 @@
*
* The caller must have disabled interrupts and must not be idle.
*/
-void rcu_momentary_dyntick_idle(void)
+notrace void rcu_momentary_dyntick_idle(void)
{
int special;
@@ -4077,7 +4077,6 @@
smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
}
-#ifdef CONFIG_HOTPLUG_CPU
/*
* The outgoing function has no further need of RCU, so remove it from
* the rcu_node tree's ->qsmaskinitnext bit masks.
@@ -4117,6 +4116,7 @@
rdp->cpu_started = false;
}
+#ifdef CONFIG_HOTPLUG_CPU
/*
* The outgoing CPU has just passed through the dying-idle state, and we
* are being invoked from the CPU that was IPIed to continue the offline
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 0fde39b8..ca21d28 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -249,13 +249,16 @@
/*
* Scan the current list of tasks blocked within RCU read-side critical
- * sections, printing out the tid of each.
+ * sections, printing out the tid of each of the first few of them.
*/
-static int rcu_print_task_stall(struct rcu_node *rnp)
+static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
+ __releases(rnp->lock)
{
+ int i = 0;
int ndetected = 0;
struct rcu_stall_chk_rdr rscr;
struct task_struct *t;
+ struct task_struct *ts[8];
if (!rcu_preempt_blocked_readers_cgp(rnp))
return 0;
@@ -264,6 +267,14 @@
t = list_entry(rnp->gp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
+ get_task_struct(t);
+ ts[i++] = t;
+ if (i >= ARRAY_SIZE(ts))
+ break;
+ }
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ for (i--; i; i--) {
+ t = ts[i];
if (!try_invoke_on_locked_down_task(t, check_slow_task, &rscr))
pr_cont(" P%d", t->pid);
else
@@ -273,6 +284,7 @@
".q"[rscr.rs.b.need_qs],
".e"[rscr.rs.b.exp_hint],
".l"[rscr.on_blkd_list]);
+ put_task_struct(t);
ndetected++;
}
pr_cont("\n");
@@ -293,8 +305,9 @@
* Because preemptible RCU does not exist, we never have to check for
* tasks blocked within RCU read-side critical sections.
*/
-static int rcu_print_task_stall(struct rcu_node *rnp)
+static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
{
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return 0;
}
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
@@ -472,7 +485,6 @@
pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name);
rcu_for_each_leaf_node(rnp) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- ndetected += rcu_print_task_stall(rnp);
if (rnp->qsmask != 0) {
for_each_leaf_node_possible_cpu(rnp, cpu)
if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
@@ -480,7 +492,7 @@
ndetected++;
}
}
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ ndetected += rcu_print_task_stall(rnp, flags); // Releases rnp->lock.
}
for_each_possible_cpu(cpu)
diff --git a/kernel/reboot.c b/kernel/reboot.c
index e7b78d5..af6f23d 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -551,22 +551,22 @@
break;
case 's':
- {
- int rc;
-
- if (isdigit(*(str+1))) {
- rc = kstrtoint(str+1, 0, &reboot_cpu);
- if (rc)
- return rc;
- } else if (str[1] == 'm' && str[2] == 'p' &&
- isdigit(*(str+3))) {
- rc = kstrtoint(str+3, 0, &reboot_cpu);
- if (rc)
- return rc;
- } else
+ if (isdigit(*(str+1)))
+ reboot_cpu = simple_strtoul(str+1, NULL, 0);
+ else if (str[1] == 'm' && str[2] == 'p' &&
+ isdigit(*(str+3)))
+ reboot_cpu = simple_strtoul(str+3, NULL, 0);
+ else
*mode = REBOOT_SOFT;
+ if (reboot_cpu >= num_possible_cpus()) {
+ pr_err("Ignoring the CPU number in reboot= option. "
+ "CPU %d exceeds possible cpu number %d\n",
+ reboot_cpu, num_possible_cpus());
+ reboot_cpu = 0;
+ break;
+ }
break;
- }
+
case 'g':
*mode = REBOOT_GPIO;
break;
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index e254745..97d318b 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -102,8 +102,12 @@
static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
unsigned int next_freq)
{
- if (sg_policy->next_freq == next_freq)
- return false;
+ if (!sg_policy->need_freq_update) {
+ if (sg_policy->next_freq == next_freq)
+ return false;
+ } else {
+ sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+ }
sg_policy->next_freq = next_freq;
sg_policy->last_freq_update_time = time;
@@ -164,7 +168,6 @@
if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
return sg_policy->next_freq;
- sg_policy->need_freq_update = false;
sg_policy->cached_raw_freq = freq;
return cpufreq_driver_resolve_freq(policy, freq);
}
@@ -440,7 +443,6 @@
struct sugov_policy *sg_policy = sg_cpu->sg_policy;
unsigned long util, max;
unsigned int next_f;
- bool busy;
unsigned int cached_freq = sg_policy->cached_raw_freq;
sugov_iowait_boost(sg_cpu, time, flags);
@@ -451,9 +453,6 @@
if (!sugov_should_update_freq(sg_policy, time))
return;
- /* Limits may have changed, don't skip frequency update */
- busy = !sg_policy->need_freq_update && sugov_cpu_is_busy(sg_cpu);
-
util = sugov_get_util(sg_cpu);
max = sg_cpu->max;
util = sugov_iowait_apply(sg_cpu, time, util, max);
@@ -462,7 +461,7 @@
* Do not reduce the frequency if the CPU has not been idle
* recently, as the reduction is likely to be premature then.
*/
- if (busy && next_f < sg_policy->next_freq) {
+ if (sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
next_f = sg_policy->next_freq;
/* Restore cached freq as next_freq has changed */
@@ -827,9 +826,10 @@
sg_policy->next_freq = 0;
sg_policy->work_in_progress = false;
sg_policy->limits_changed = false;
- sg_policy->need_freq_update = false;
sg_policy->cached_raw_freq = 0;
+ sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+
for_each_cpu(cpu, policy->cpus) {
struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
@@ -881,7 +881,7 @@
struct cpufreq_governor schedutil_gov = {
.name = "schedutil",
.owner = THIS_MODULE,
- .dynamic_switching = true,
+ .flags = CPUFREQ_GOV_DYNAMIC_SWITCHING,
.init = sugov_init,
.exit = sugov_exit,
.start = sugov_start,
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 0655524..2357921 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -251,7 +251,7 @@
unsigned long flags = *(unsigned long *)table->data;
size_t data_size = 0;
size_t len = 0;
- char *tmp;
+ char *tmp, *buf;
int idx;
if (write)
@@ -269,17 +269,17 @@
return 0;
}
- tmp = kcalloc(data_size + 1, sizeof(*tmp), GFP_KERNEL);
- if (!tmp)
+ buf = kcalloc(data_size + 1, sizeof(*buf), GFP_KERNEL);
+ if (!buf)
return -ENOMEM;
for_each_set_bit(idx, &flags, __SD_FLAG_CNT) {
char *name = sd_flag_debug[idx].name;
- len += snprintf(tmp + len, strlen(name) + 2, "%s ", name);
+ len += snprintf(buf + len, strlen(name) + 2, "%s ", name);
}
- tmp += *ppos;
+ tmp = buf + *ppos;
len -= *ppos;
if (len > *lenp)
@@ -294,7 +294,7 @@
*lenp = len;
*ppos += len;
- kfree(tmp);
+ kfree(buf);
return 0;
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 290f9e3..8917d2d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6172,21 +6172,21 @@
static int
select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
{
- unsigned long best_cap = 0;
+ unsigned long task_util, best_cap = 0;
int cpu, best_cpu = -1;
struct cpumask *cpus;
- sync_entity_load_avg(&p->se);
-
cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
+ task_util = uclamp_task_util(p);
+
for_each_cpu_wrap(cpu, cpus, target) {
unsigned long cpu_cap = capacity_of(cpu);
if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu))
continue;
- if (task_fits_capacity(p, cpu_cap))
+ if (fits_capacity(task_util, cpu_cap))
return cpu;
if (cpu_cap > best_cap) {
@@ -6198,44 +6198,42 @@
return best_cpu;
}
+static inline bool asym_fits_capacity(int task_util, int cpu)
+{
+ if (static_branch_unlikely(&sched_asym_cpucapacity))
+ return fits_capacity(task_util, capacity_of(cpu));
+
+ return true;
+}
+
/*
* Try and locate an idle core/thread in the LLC cache domain.
*/
static int select_idle_sibling(struct task_struct *p, int prev, int target)
{
struct sched_domain *sd;
+ unsigned long task_util;
int i, recent_used_cpu;
/*
- * For asymmetric CPU capacity systems, our domain of interest is
- * sd_asym_cpucapacity rather than sd_llc.
+ * On asymmetric system, update task utilization because we will check
+ * that the task fits with cpu's capacity.
*/
if (static_branch_unlikely(&sched_asym_cpucapacity)) {
- sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
- /*
- * On an asymmetric CPU capacity system where an exclusive
- * cpuset defines a symmetric island (i.e. one unique
- * capacity_orig value through the cpuset), the key will be set
- * but the CPUs within that cpuset will not have a domain with
- * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric
- * capacity path.
- */
- if (!sd)
- goto symmetric;
-
- i = select_idle_capacity(p, sd, target);
- return ((unsigned)i < nr_cpumask_bits) ? i : target;
+ sync_entity_load_avg(&p->se);
+ task_util = uclamp_task_util(p);
}
-symmetric:
- if (available_idle_cpu(target) || sched_idle_cpu(target))
+ if ((available_idle_cpu(target) || sched_idle_cpu(target)) &&
+ asym_fits_capacity(task_util, target))
return target;
/*
* If the previous CPU is cache affine and idle, don't be stupid:
*/
if (prev != target && cpus_share_cache(prev, target) &&
- (available_idle_cpu(prev) || sched_idle_cpu(prev)))
+ (available_idle_cpu(prev) || sched_idle_cpu(prev)) &&
+ asym_fits_capacity(task_util, prev))
return prev;
/*
@@ -6258,7 +6256,8 @@
recent_used_cpu != target &&
cpus_share_cache(recent_used_cpu, target) &&
(available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
- cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) {
+ cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) &&
+ asym_fits_capacity(task_util, recent_used_cpu)) {
/*
* Replace recent_used_cpu with prev as it is a potential
* candidate for the next wake:
@@ -6267,6 +6266,26 @@
return recent_used_cpu;
}
+ /*
+ * For asymmetric CPU capacity systems, our domain of interest is
+ * sd_asym_cpucapacity rather than sd_llc.
+ */
+ if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+ sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
+ /*
+ * On an asymmetric CPU capacity system where an exclusive
+ * cpuset defines a symmetric island (i.e. one unique
+ * capacity_orig value through the cpuset), the key will be set
+ * but the CPUs within that cpuset will not have a domain with
+ * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric
+ * capacity path.
+ */
+ if (sd) {
+ i = select_idle_capacity(p, sd, target);
+ return ((unsigned)i < nr_cpumask_bits) ? i : target;
+ }
+ }
+
sd = rcu_dereference(per_cpu(sd_llc, target));
if (!sd)
return target;
@@ -9031,7 +9050,8 @@
* emptying busiest.
*/
if (local->group_type == group_has_spare) {
- if (busiest->group_type > group_fully_busy) {
+ if ((busiest->group_type > group_fully_busy) &&
+ !(env->sd->flags & SD_SHARE_PKG_RESOURCES)) {
/*
* If busiest is overloaded, try to fill spare
* capacity. This might end up creating spare capacity
diff --git a/kernel/signal.c b/kernel/signal.c
index a38b3ed..ef8f2a2 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -391,16 +391,17 @@
void task_join_group_stop(struct task_struct *task)
{
+ unsigned long mask = current->jobctl & JOBCTL_STOP_SIGMASK;
+ struct signal_struct *sig = current->signal;
+
+ if (sig->group_stop_count) {
+ sig->group_stop_count++;
+ mask |= JOBCTL_STOP_CONSUME;
+ } else if (!(sig->flags & SIGNAL_STOP_STOPPED))
+ return;
+
/* Have the new thread join an on-going signal group stop */
- unsigned long jobctl = current->jobctl;
- if (jobctl & JOBCTL_STOP_PENDING) {
- struct signal_struct *sig = current->signal;
- unsigned long signr = jobctl & JOBCTL_STOP_SIGMASK;
- unsigned long gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME;
- if (task_set_jobctl_pending(task, signr | gstop)) {
- sig->group_stop_count++;
- }
- }
+ task_set_jobctl_pending(task, mask | JOBCTL_STOP_PENDING);
}
/*
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 865bb02..890b79cf 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -178,7 +178,7 @@
set_state(msdata, msdata->state + 1);
}
-void __weak stop_machine_yield(const struct cpumask *cpumask)
+notrace void __weak stop_machine_yield(const struct cpumask *cpumask)
{
cpu_relax();
}
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 3624b9b..387b4be 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -425,11 +425,6 @@
debug_object_deactivate(timer, &hrtimer_debug_descr);
}
-static inline void debug_hrtimer_free(struct hrtimer *timer)
-{
- debug_object_free(timer, &hrtimer_debug_descr);
-}
-
static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
enum hrtimer_mode mode);
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index ca4e6d5..00629e6 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -172,10 +172,6 @@
u64 oval, nval, ointerval, ninterval;
struct cpu_itimer *it = &tsk->signal->it[clock_id];
- /*
- * Use the to_ktime conversion because that clamps the maximum
- * value to KTIME_MAX and avoid multiplication overflows.
- */
nval = timespec64_to_ns(&value->it_value);
ninterval = timespec64_to_ns(&value->it_interval);
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 0642013..b1b9b12 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -68,13 +68,13 @@
return (cyc * mult) >> shift;
}
-struct clock_read_data *sched_clock_read_begin(unsigned int *seq)
+notrace struct clock_read_data *sched_clock_read_begin(unsigned int *seq)
{
*seq = raw_read_seqcount_latch(&cd.seq);
return cd.read_data + (*seq & 1);
}
-int sched_clock_read_retry(unsigned int seq)
+notrace int sched_clock_read_retry(unsigned int seq)
{
return read_seqcount_latch_retry(&cd.seq, seq);
}
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index de37e33..c3ad64f 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -732,11 +732,6 @@
debug_object_deactivate(timer, &timer_debug_descr);
}
-static inline void debug_timer_free(struct timer_list *timer)
-{
- debug_object_free(timer, &timer_debug_descr);
-}
-
static inline void debug_timer_assert_init(struct timer_list *timer)
{
debug_object_assert_init(timer, &timer_debug_descr);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 4517c8b..048c655 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -181,6 +181,16 @@
{
int ret;
+ /*
+ * NB: We rely on strncpy_from_user() not copying junk past the NUL
+ * terminator into `dst`.
+ *
+ * strncpy_from_user() does long-sized strides in the fast path. If the
+ * strncpy does not mask out the bytes after the NUL in `unsafe_ptr`,
+ * then there could be junk after the NUL in `dst`. If user takes `dst`
+ * and keys a hash map with it, then semantically identical strings can
+ * occupy multiple entries in the map.
+ */
ret = strncpy_from_user_nofault(dst, unsafe_ptr, size);
if (unlikely(ret < 0))
memset(dst, 0, size);
@@ -1198,7 +1208,7 @@
*btf = bpf_get_btf_vmlinux();
if (IS_ERR_OR_NULL(*btf))
- return PTR_ERR(*btf);
+ return IS_ERR(*btf) ? PTR_ERR(*btf) : -EINVAL;
if (ptr->type_id > 0)
*btf_id = ptr->type_id;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 7f45fd9..dc83b3f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -438,14 +438,16 @@
};
/*
* Used for which event context the event is in.
- * NMI = 0
- * IRQ = 1
- * SOFTIRQ = 2
- * NORMAL = 3
+ * TRANSITION = 0
+ * NMI = 1
+ * IRQ = 2
+ * SOFTIRQ = 3
+ * NORMAL = 4
*
* See trace_recursive_lock() comment below for more details.
*/
enum {
+ RB_CTX_TRANSITION,
RB_CTX_NMI,
RB_CTX_IRQ,
RB_CTX_SOFTIRQ,
@@ -3014,10 +3016,10 @@
* a bit of overhead in something as critical as function tracing,
* we use a bitmask trick.
*
- * bit 0 = NMI context
- * bit 1 = IRQ context
- * bit 2 = SoftIRQ context
- * bit 3 = normal context.
+ * bit 1 = NMI context
+ * bit 2 = IRQ context
+ * bit 3 = SoftIRQ context
+ * bit 4 = normal context.
*
* This works because this is the order of contexts that can
* preempt other contexts. A SoftIRQ never preempts an IRQ
@@ -3040,6 +3042,30 @@
* The least significant bit can be cleared this way, and it
* just so happens that it is the same bit corresponding to
* the current context.
+ *
+ * Now the TRANSITION bit breaks the above slightly. The TRANSITION bit
+ * is set when a recursion is detected at the current context, and if
+ * the TRANSITION bit is already set, it will fail the recursion.
+ * This is needed because there's a lag between the changing of
+ * interrupt context and updating the preempt count. In this case,
+ * a false positive will be found. To handle this, one extra recursion
+ * is allowed, and this is done by the TRANSITION bit. If the TRANSITION
+ * bit is already set, then it is considered a recursion and the function
+ * ends. Otherwise, the TRANSITION bit is set, and that bit is returned.
+ *
+ * On the trace_recursive_unlock(), the TRANSITION bit will be the first
+ * to be cleared. Even if it wasn't the context that set it. That is,
+ * if an interrupt comes in while NORMAL bit is set and the ring buffer
+ * is called before preempt_count() is updated, since the check will
+ * be on the NORMAL bit, the TRANSITION bit will then be set. If an
+ * NMI then comes in, it will set the NMI bit, but when the NMI code
+ * does the trace_recursive_unlock() it will clear the TRANSTION bit
+ * and leave the NMI bit set. But this is fine, because the interrupt
+ * code that set the TRANSITION bit will then clear the NMI bit when it
+ * calls trace_recursive_unlock(). If another NMI comes in, it will
+ * set the TRANSITION bit and continue.
+ *
+ * Note: The TRANSITION bit only handles a single transition between context.
*/
static __always_inline int
@@ -3055,8 +3081,16 @@
bit = pc & NMI_MASK ? RB_CTX_NMI :
pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ;
- if (unlikely(val & (1 << (bit + cpu_buffer->nest))))
- return 1;
+ if (unlikely(val & (1 << (bit + cpu_buffer->nest)))) {
+ /*
+ * It is possible that this was called by transitioning
+ * between interrupt context, and preempt_count() has not
+ * been updated yet. In this case, use the TRANSITION bit.
+ */
+ bit = RB_CTX_TRANSITION;
+ if (val & (1 << (bit + cpu_buffer->nest)))
+ return 1;
+ }
val |= (1 << (bit + cpu_buffer->nest));
cpu_buffer->current_context = val;
@@ -3071,8 +3105,8 @@
cpu_buffer->current_context - (1 << cpu_buffer->nest);
}
-/* The recursive locking above uses 4 bits */
-#define NESTED_BITS 4
+/* The recursive locking above uses 5 bits */
+#define NESTED_BITS 5
/**
* ring_buffer_nest_start - Allow to trace while nested
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 5289717..410cfeb 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2750,7 +2750,7 @@
/*
* If tracing is off, but we have triggers enabled
* we still need to look at the event data. Use the temp_buffer
- * to store the trace event for the tigger to use. It's recusive
+ * to store the trace event for the trigger to use. It's recursive
* safe and will not be recorded anywhere.
*/
if (!entry && trace_file->flags & EVENT_FILE_FL_TRIGGER_COND) {
@@ -2952,7 +2952,7 @@
stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1;
/* This should never happen. If it does, yell once and skip */
- if (WARN_ON_ONCE(stackidx > FTRACE_KSTACK_NESTING))
+ if (WARN_ON_ONCE(stackidx >= FTRACE_KSTACK_NESTING))
goto out;
/*
@@ -3132,7 +3132,7 @@
/* Interrupts must see nesting incremented before we use the buffer */
barrier();
- return &buffer->buffer[buffer->nesting][0];
+ return &buffer->buffer[buffer->nesting - 1][0];
}
static void put_trace_buf(void)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index f3f5e77..1dadef4 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -637,6 +637,12 @@
* function is called to clear it.
*/
TRACE_GRAPH_NOTRACE_BIT,
+
+ /*
+ * When transitioning between context, the preempt_count() may
+ * not be correct. Allow for a single recursion to cover this case.
+ */
+ TRACE_TRANSITION_BIT,
};
#define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0)
@@ -691,14 +697,27 @@
return 0;
bit = trace_get_context_bit() + start;
- if (unlikely(val & (1 << bit)))
- return -1;
+ if (unlikely(val & (1 << bit))) {
+ /*
+ * It could be that preempt_count has not been updated during
+ * a switch between contexts. Allow for a single recursion.
+ */
+ bit = TRACE_TRANSITION_BIT;
+ if (trace_recursion_test(bit))
+ return -1;
+ trace_recursion_set(bit);
+ barrier();
+ return bit + 1;
+ }
+
+ /* Normal check passed, clear the transition to allow it again */
+ trace_recursion_clear(TRACE_TRANSITION_BIT);
val |= 1 << bit;
current->trace_recursion = val;
barrier();
- return bit;
+ return bit + 1;
}
static __always_inline void trace_clear_recursion(int bit)
@@ -708,6 +727,7 @@
if (!bit)
return;
+ bit--;
bit = 1 << bit;
val &= ~bit;
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 3212e2c..881df99 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -584,7 +584,8 @@
{
struct synth_field *field;
const char *prefix = NULL, *field_type = argv[0], *field_name, *array;
- int len, ret = 0;
+ int len, ret = -ENOMEM;
+ struct seq_buf s;
ssize_t size;
if (field_type[0] == ';')
@@ -616,10 +617,9 @@
len--;
field->name = kmemdup_nul(field_name, len, GFP_KERNEL);
- if (!field->name) {
- ret = -ENOMEM;
+ if (!field->name)
goto free;
- }
+
if (!is_good_name(field->name)) {
synth_err(SYNTH_ERR_BAD_NAME, errpos(field_name));
ret = -EINVAL;
@@ -630,29 +630,29 @@
field_type++;
len = strlen(field_type) + 1;
- if (array) {
- int l = strlen(array);
+ if (array)
+ len += strlen(array);
- if (l && array[l - 1] == ';')
- l--;
- len += l;
- }
if (prefix)
len += strlen(prefix);
field->type = kzalloc(len, GFP_KERNEL);
- if (!field->type) {
- ret = -ENOMEM;
+ if (!field->type)
goto free;
- }
+
+ seq_buf_init(&s, field->type, len);
if (prefix)
- strcat(field->type, prefix);
- strcat(field->type, field_type);
+ seq_buf_puts(&s, prefix);
+ seq_buf_puts(&s, field_type);
if (array) {
- strcat(field->type, array);
- if (field->type[len - 1] == ';')
- field->type[len - 1] = '\0';
+ seq_buf_puts(&s, array);
+ if (s.buffer[s.len - 1] == ';')
+ s.len--;
}
+ if (WARN_ON_ONCE(!seq_buf_buffer_left(&s)))
+ goto free;
+
+ s.buffer[s.len] = '\0';
size = synth_field_size(field->type);
if (size < 0) {
@@ -663,14 +663,19 @@
if (synth_field_is_string(field->type)) {
char *type;
- type = kzalloc(sizeof("__data_loc ") + strlen(field->type) + 1, GFP_KERNEL);
- if (!type) {
- ret = -ENOMEM;
+ len = sizeof("__data_loc ") + strlen(field->type) + 1;
+ type = kzalloc(len, GFP_KERNEL);
+ if (!type)
goto free;
- }
- strcat(type, "__data_loc ");
- strcat(type, field->type);
+ seq_buf_init(&s, type, len);
+ seq_buf_puts(&s, "__data_loc ");
+ seq_buf_puts(&s, field->type);
+
+ if (WARN_ON_ONCE(!seq_buf_buffer_left(&s)))
+ goto free;
+ s.buffer[s.len] = '\0';
+
kfree(field->type);
field->type = type;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index b5e3496..4738ad4 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -492,8 +492,13 @@
unregister_ftrace_function(&test_rec_probe);
ret = -1;
- if (trace_selftest_recursion_cnt != 1) {
- pr_cont("*callback not called once (%d)* ",
+ /*
+ * Recursion allows for transitions between context,
+ * and may call the callback twice.
+ */
+ if (trace_selftest_recursion_cnt != 1 &&
+ trace_selftest_recursion_cnt != 2) {
+ pr_cont("*callback not called once (or twice) (%d)* ",
trace_selftest_recursion_cnt);
goto out;
}
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 26efd22..3f659f8 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -50,7 +50,7 @@
*/
struct tp_probes {
struct rcu_head rcu;
- struct tracepoint_func probes[0];
+ struct tracepoint_func probes[];
};
static inline void *allocate_probes(int count)
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 5abb5b2..7110906 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -44,8 +44,6 @@
int __read_mostly watchdog_thresh = 10;
static int __read_mostly nmi_watchdog_available;
-static struct cpumask watchdog_allowed_mask __read_mostly;
-
struct cpumask watchdog_cpumask __read_mostly;
unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
@@ -162,6 +160,8 @@
int __read_mostly sysctl_softlockup_all_cpu_backtrace;
#endif
+static struct cpumask watchdog_allowed_mask __read_mostly;
+
/* Global variables, exported for sysctl */
unsigned int __read_mostly softlockup_panic =
CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index d7a7bc3..c789b39 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2446,4 +2446,6 @@
endmenu # "Kernel Testing and Coverage"
+source "Documentation/Kconfig"
+
endmenu # Kernel hacking
diff --git a/lib/crc32test.c b/lib/crc32test.c
index 97d6a57..61ddce2 100644
--- a/lib/crc32test.c
+++ b/lib/crc32test.c
@@ -683,7 +683,6 @@
/* reduce OS noise */
local_irq_save(flags);
- local_irq_disable();
nsec = ktime_get_ns();
for (i = 0; i < 100; i++) {
@@ -694,7 +693,6 @@
nsec = ktime_get_ns() - nsec;
local_irq_restore(flags);
- local_irq_enable();
pr_info("crc32c: CRC_LE_BITS = %d\n", CRC_LE_BITS);
@@ -768,7 +766,6 @@
/* reduce OS noise */
local_irq_save(flags);
- local_irq_disable();
nsec = ktime_get_ns();
for (i = 0; i < 100; i++) {
@@ -783,7 +780,6 @@
nsec = ktime_get_ns() - nsec;
local_irq_restore(flags);
- local_irq_enable();
pr_info("crc32: CRC_LE_BITS = %d, CRC_BE BITS = %d\n",
CRC_LE_BITS, CRC_BE_BITS);
diff --git a/lib/fonts/font_10x18.c b/lib/fonts/font_10x18.c
index 0e2deac..e02f9df 100644
--- a/lib/fonts/font_10x18.c
+++ b/lib/fonts/font_10x18.c
@@ -8,7 +8,7 @@
#define FONTDATAMAX 9216
-static struct font_data fontdata_10x18 = {
+static const struct font_data fontdata_10x18 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, 0x00, /* 0000000000 */
diff --git a/lib/fonts/font_6x10.c b/lib/fonts/font_6x10.c
index 87da8ac..6e3c4b7 100644
--- a/lib/fonts/font_6x10.c
+++ b/lib/fonts/font_6x10.c
@@ -3,7 +3,7 @@
#define FONTDATAMAX 2560
-static struct font_data fontdata_6x10 = {
+static const struct font_data fontdata_6x10 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 00000000 */
diff --git a/lib/fonts/font_6x11.c b/lib/fonts/font_6x11.c
index 5e975df..2d22a24 100644
--- a/lib/fonts/font_6x11.c
+++ b/lib/fonts/font_6x11.c
@@ -9,7 +9,7 @@
#define FONTDATAMAX (11*256)
-static struct font_data fontdata_6x11 = {
+static const struct font_data fontdata_6x11 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 00000000 */
diff --git a/lib/fonts/font_6x8.c b/lib/fonts/font_6x8.c
index 700039a9..e7442a0 100644
--- a/lib/fonts/font_6x8.c
+++ b/lib/fonts/font_6x8.c
@@ -3,7 +3,7 @@
#define FONTDATAMAX 2048
-static struct font_data fontdata_6x8 = {
+static const struct font_data fontdata_6x8 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 000000 */
diff --git a/lib/fonts/font_7x14.c b/lib/fonts/font_7x14.c
index 86d298f..9cc7ae2 100644
--- a/lib/fonts/font_7x14.c
+++ b/lib/fonts/font_7x14.c
@@ -8,7 +8,7 @@
#define FONTDATAMAX 3584
-static struct font_data fontdata_7x14 = {
+static const struct font_data fontdata_7x14 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 0000000 */
diff --git a/lib/fonts/font_8x16.c b/lib/fonts/font_8x16.c
index 37cedd3..bab25dc 100644
--- a/lib/fonts/font_8x16.c
+++ b/lib/fonts/font_8x16.c
@@ -10,7 +10,7 @@
#define FONTDATAMAX 4096
-static struct font_data fontdata_8x16 = {
+static const struct font_data fontdata_8x16 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 00000000 */
diff --git a/lib/fonts/font_8x8.c b/lib/fonts/font_8x8.c
index 8ab6955..109d057 100644
--- a/lib/fonts/font_8x8.c
+++ b/lib/fonts/font_8x8.c
@@ -9,7 +9,7 @@
#define FONTDATAMAX 2048
-static struct font_data fontdata_8x8 = {
+static const struct font_data fontdata_8x8 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 00000000 */
diff --git a/lib/fonts/font_acorn_8x8.c b/lib/fonts/font_acorn_8x8.c
index 069b3e8..fb395f0 100644
--- a/lib/fonts/font_acorn_8x8.c
+++ b/lib/fonts/font_acorn_8x8.c
@@ -5,7 +5,7 @@
#define FONTDATAMAX 2048
-static struct font_data acorndata_8x8 = {
+static const struct font_data acorndata_8x8 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 00 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* ^@ */
/* 01 */ 0x7e, 0x81, 0xa5, 0x81, 0xbd, 0x99, 0x81, 0x7e, /* ^A */
diff --git a/lib/fonts/font_mini_4x6.c b/lib/fonts/font_mini_4x6.c
index 1449876..592774a 100644
--- a/lib/fonts/font_mini_4x6.c
+++ b/lib/fonts/font_mini_4x6.c
@@ -43,7 +43,7 @@
#define FONTDATAMAX 1536
-static struct font_data fontdata_mini_4x6 = {
+static const struct font_data fontdata_mini_4x6 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/*{*/
/* Char 0: ' ' */
diff --git a/lib/fonts/font_pearl_8x8.c b/lib/fonts/font_pearl_8x8.c
index 32d6555..a6f95eb 100644
--- a/lib/fonts/font_pearl_8x8.c
+++ b/lib/fonts/font_pearl_8x8.c
@@ -14,7 +14,7 @@
#define FONTDATAMAX 2048
-static struct font_data fontdata_pearl8x8 = {
+static const struct font_data fontdata_pearl8x8 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 00000000 */
diff --git a/lib/fonts/font_sun12x22.c b/lib/fonts/font_sun12x22.c
index 641a6b4..a5b65bd 100644
--- a/lib/fonts/font_sun12x22.c
+++ b/lib/fonts/font_sun12x22.c
@@ -3,7 +3,7 @@
#define FONTDATAMAX 11264
-static struct font_data fontdata_sun12x22 = {
+static const struct font_data fontdata_sun12x22 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, 0x00, /* 000000000000 */
diff --git a/lib/fonts/font_sun8x16.c b/lib/fonts/font_sun8x16.c
index 193fe6d..e577e76 100644
--- a/lib/fonts/font_sun8x16.c
+++ b/lib/fonts/font_sun8x16.c
@@ -3,7 +3,7 @@
#define FONTDATAMAX 4096
-static struct font_data fontdata_sun8x16 = {
+static const struct font_data fontdata_sun8x16 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
/* */ 0x00,0x00,0x7e,0x81,0xa5,0x81,0x81,0xbd,0x99,0x81,0x81,0x7e,0x00,0x00,0x00,0x00,
diff --git a/lib/fonts/font_ter16x32.c b/lib/fonts/font_ter16x32.c
index 91b9c28..f7c3abb 100644
--- a/lib/fonts/font_ter16x32.c
+++ b/lib/fonts/font_ter16x32.c
@@ -4,7 +4,7 @@
#define FONTDATAMAX 16384
-static struct font_data fontdata_ter16x32 = {
+static const struct font_data fontdata_ter16x32 = {
{ 0, 0, FONTDATAMAX, 0 }, {
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x7f, 0xfc, 0x7f, 0xfc,
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 0a482ef..a597789 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -933,7 +933,7 @@
sg_miter_start(&miter, sgl, nents, sg_flags);
if (!sg_miter_skip(&miter, skip))
- return false;
+ return 0;
while ((offset < buflen) && sg_miter_next(&miter)) {
unsigned int len;
diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c
index e6d5fcc..122d8d0 100644
--- a/lib/strncpy_from_user.c
+++ b/lib/strncpy_from_user.c
@@ -35,17 +35,32 @@
goto byte_at_a_time;
while (max >= sizeof(unsigned long)) {
- unsigned long c, data;
+ unsigned long c, data, mask;
/* Fall back to byte-at-a-time if we get a page fault */
unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time);
- *(unsigned long *)(dst+res) = c;
+ /*
+ * Note that we mask out the bytes following the NUL. This is
+ * important to do because string oblivious code may read past
+ * the NUL. For those routines, we don't want to give them
+ * potentially random bytes after the NUL in `src`.
+ *
+ * One example of such code is BPF map keys. BPF treats map keys
+ * as an opaque set of bytes. Without the post-NUL mask, any BPF
+ * maps keyed by strings returned from strncpy_from_user() may
+ * have multiple entries for semantically identical strings.
+ */
if (has_zero(c, &data, &constants)) {
data = prep_zero_mask(c, data, &constants);
data = create_zero_mask(data);
+ mask = zero_bytemask(data);
+ *(unsigned long *)(dst+res) = c & mask;
return res + find_zero(data);
}
+
+ *(unsigned long *)(dst+res) = c;
+
res += sizeof(unsigned long);
max -= sizeof(unsigned long);
}
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 63c2617..662f862 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -216,6 +216,12 @@
u64 words[2];
} *ptr1, *ptr2;
+ /* This test is specifically crafted for the generic mode. */
+ if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_GENERIC required\n");
+ return;
+ }
+
ptr1 = kmalloc(sizeof(*ptr1) - 3, GFP_KERNEL);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1);
@@ -227,6 +233,23 @@
kfree(ptr2);
}
+static void kmalloc_uaf_16(struct kunit *test)
+{
+ struct {
+ u64 words[2];
+ } *ptr1, *ptr2;
+
+ ptr1 = kmalloc(sizeof(*ptr1), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1);
+
+ ptr2 = kmalloc(sizeof(*ptr2), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2);
+ kfree(ptr2);
+
+ KUNIT_EXPECT_KASAN_FAIL(test, *ptr1 = *ptr2);
+ kfree(ptr1);
+}
+
static void kmalloc_oob_memset_2(struct kunit *test)
{
char *ptr;
@@ -429,6 +452,12 @@
volatile int i = 3;
char *p = &global_array[ARRAY_SIZE(global_array) + i];
+ /* Only generic mode instruments globals. */
+ if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_GENERIC required");
+ return;
+ }
+
KUNIT_EXPECT_KASAN_FAIL(test, *(volatile char *)p);
}
@@ -467,6 +496,12 @@
char alloca_array[i];
char *p = alloca_array - 1;
+ /* Only generic mode instruments dynamic allocas. */
+ if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_GENERIC required");
+ return;
+ }
+
if (!IS_ENABLED(CONFIG_KASAN_STACK)) {
kunit_info(test, "CONFIG_KASAN_STACK is not enabled");
return;
@@ -481,6 +516,12 @@
char alloca_array[i];
char *p = alloca_array + i;
+ /* Only generic mode instruments dynamic allocas. */
+ if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_GENERIC required");
+ return;
+ }
+
if (!IS_ENABLED(CONFIG_KASAN_STACK)) {
kunit_info(test, "CONFIG_KASAN_STACK is not enabled");
return;
@@ -551,6 +592,9 @@
return;
}
+ if (OOB_TAG_OFF)
+ size = round_up(size, OOB_TAG_OFF);
+
ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
@@ -573,6 +617,9 @@
return;
}
+ if (OOB_TAG_OFF)
+ size = round_up(size, OOB_TAG_OFF);
+
ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
memset(arr, 0, sizeof(arr));
@@ -619,13 +666,50 @@
KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = strnlen(ptr, 1));
}
-static void kasan_bitops(struct kunit *test)
+static void kasan_bitops_modify(struct kunit *test, int nr, void *addr)
{
+ KUNIT_EXPECT_KASAN_FAIL(test, set_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __set_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, clear_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, clear_bit_unlock(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit_unlock(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, change_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __change_bit(nr, addr));
+}
+
+static void kasan_bitops_test_and_modify(struct kunit *test, int nr, void *addr)
+{
+ KUNIT_EXPECT_KASAN_FAIL(test, test_and_set_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __test_and_set_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, test_and_set_bit_lock(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, test_and_clear_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __test_and_clear_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, test_and_change_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __test_and_change_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = test_bit(nr, addr));
+
+#if defined(clear_bit_unlock_is_negative_byte)
+ KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result =
+ clear_bit_unlock_is_negative_byte(nr, addr));
+#endif
+}
+
+static void kasan_bitops_generic(struct kunit *test)
+{
+ long *bits;
+
+ /* This test is specifically crafted for the generic mode. */
+ if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_GENERIC required\n");
+ return;
+ }
+
/*
* Allocate 1 more byte, which causes kzalloc to round up to 16-bytes;
* this way we do not actually corrupt other memory.
*/
- long *bits = kzalloc(sizeof(*bits) + 1, GFP_KERNEL);
+ bits = kzalloc(sizeof(*bits) + 1, GFP_KERNEL);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, bits);
/*
@@ -633,55 +717,34 @@
* below accesses are still out-of-bounds, since bitops are defined to
* operate on the whole long the bit is in.
*/
- KUNIT_EXPECT_KASAN_FAIL(test, set_bit(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, __set_bit(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, clear_bit(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, clear_bit_unlock(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit_unlock(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, change_bit(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, __change_bit(BITS_PER_LONG, bits));
+ kasan_bitops_modify(test, BITS_PER_LONG, bits);
/*
* Below calls try to access bit beyond allocated memory.
*/
- KUNIT_EXPECT_KASAN_FAIL(test,
- test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+ kasan_bitops_test_and_modify(test, BITS_PER_LONG + BITS_PER_BYTE, bits);
- KUNIT_EXPECT_KASAN_FAIL(test,
- __test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+ kfree(bits);
+}
- KUNIT_EXPECT_KASAN_FAIL(test,
- test_and_set_bit_lock(BITS_PER_LONG + BITS_PER_BYTE, bits));
+static void kasan_bitops_tags(struct kunit *test)
+{
+ long *bits;
- KUNIT_EXPECT_KASAN_FAIL(test,
- test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+ /* This test is specifically crafted for the tag-based mode. */
+ if (IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_SW_TAGS required\n");
+ return;
+ }
- KUNIT_EXPECT_KASAN_FAIL(test,
- __test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+ /* Allocation size will be rounded to up granule size, which is 16. */
+ bits = kzalloc(sizeof(*bits), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_ERR_OR_NULL(test, bits);
- KUNIT_EXPECT_KASAN_FAIL(test,
- test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+ /* Do the accesses past the 16 allocated bytes. */
+ kasan_bitops_modify(test, BITS_PER_LONG, &bits[1]);
+ kasan_bitops_test_and_modify(test, BITS_PER_LONG + BITS_PER_BYTE, &bits[1]);
- KUNIT_EXPECT_KASAN_FAIL(test,
- __test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test,
- kasan_int_result =
- test_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
-
-#if defined(clear_bit_unlock_is_negative_byte)
- KUNIT_EXPECT_KASAN_FAIL(test,
- kasan_int_result = clear_bit_unlock_is_negative_byte(
- BITS_PER_LONG + BITS_PER_BYTE, bits));
-#endif
kfree(bits);
}
@@ -728,6 +791,7 @@
KUNIT_CASE(kmalloc_oob_krealloc_more),
KUNIT_CASE(kmalloc_oob_krealloc_less),
KUNIT_CASE(kmalloc_oob_16),
+ KUNIT_CASE(kmalloc_uaf_16),
KUNIT_CASE(kmalloc_oob_in_memset),
KUNIT_CASE(kmalloc_oob_memset_2),
KUNIT_CASE(kmalloc_oob_memset_4),
@@ -751,7 +815,8 @@
KUNIT_CASE(kasan_memchr),
KUNIT_CASE(kasan_memcmp),
KUNIT_CASE(kasan_strings),
- KUNIT_CASE(kasan_bitops),
+ KUNIT_CASE(kasan_bitops_generic),
+ KUNIT_CASE(kasan_bitops_tags),
KUNIT_CASE(kmalloc_double_kzfree),
KUNIT_CASE(vmalloc_oob),
{}
diff --git a/mm/compaction.c b/mm/compaction.c
index 6e0ee56..13cb7a9 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -817,6 +817,10 @@
* delay for some time until fewer pages are isolated
*/
while (unlikely(too_many_isolated(pgdat))) {
+ /* stop isolation if there are still pages not migrated */
+ if (cc->nr_migratepages)
+ return 0;
+
/* async migration should just abort */
if (cc->mode == MIGRATE_ASYNC)
return 0;
@@ -1012,8 +1016,8 @@
isolate_success:
list_add(&page->lru, &cc->migratepages);
- cc->nr_migratepages++;
- nr_isolated++;
+ cc->nr_migratepages += compound_nr(page);
+ nr_isolated += compound_nr(page);
/*
* Avoid isolating too much unless this block is being
@@ -1021,7 +1025,7 @@
* or a lock is contended. For contention, isolate quickly to
* potentially remove one source of contention.
*/
- if (cc->nr_migratepages == COMPACT_CLUSTER_MAX &&
+ if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX &&
!cc->rescan && !cc->contended) {
++low_pfn;
break;
@@ -1132,7 +1136,7 @@
if (!pfn)
break;
- if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
+ if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX)
break;
}
diff --git a/mm/gup.c b/mm/gup.c
index 102877e..98eb8e6 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1647,8 +1647,11 @@
/*
* drop the above get_user_pages reference.
*/
- for (i = 0; i < nr_pages; i++)
- put_page(pages[i]);
+ if (gup_flags & FOLL_PIN)
+ unpin_user_pages(pages, nr_pages);
+ else
+ for (i = 0; i < nr_pages; i++)
+ put_page(pages[i]);
if (migrate_pages(&cma_page_list, alloc_migration_target, NULL,
(unsigned long)&mtc, MIGRATE_SYNC, MR_CONTIG_RANGE)) {
@@ -1728,8 +1731,11 @@
goto out;
if (check_dax_vmas(vmas_tmp, rc)) {
- for (i = 0; i < rc; i++)
- put_page(pages[i]);
+ if (gup_flags & FOLL_PIN)
+ unpin_user_pages(pages, rc);
+ else
+ for (i = 0; i < rc; i++)
+ put_page(pages[i]);
rc = -EOPNOTSUPP;
goto out;
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index fe76f8f..37f15c3 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -648,6 +648,8 @@
}
del += t - f;
+ hugetlb_cgroup_uncharge_file_region(
+ resv, rg, t - f);
/* New entry for end of split region */
nrg->from = t;
@@ -660,9 +662,6 @@
/* Original entry is trimmed */
rg->to = f;
- hugetlb_cgroup_uncharge_file_region(
- resv, rg, nrg->to - nrg->from);
-
list_add(&nrg->link, &rg->link);
nrg = NULL;
break;
@@ -678,17 +677,17 @@
}
if (f <= rg->from) { /* Trim beginning of region */
- del += t - rg->from;
- rg->from = t;
-
hugetlb_cgroup_uncharge_file_region(resv, rg,
t - rg->from);
- } else { /* Trim end of region */
- del += rg->to - f;
- rg->to = f;
+ del += t - rg->from;
+ rg->from = t;
+ } else { /* Trim end of region */
hugetlb_cgroup_uncharge_file_region(resv, rg,
rg->to - f);
+
+ del += rg->to - f;
+ rg->to = f;
}
}
@@ -1569,103 +1568,23 @@
}
/*
- * Find address_space associated with hugetlbfs page.
- * Upon entry page is locked and page 'was' mapped although mapped state
- * could change. If necessary, use anon_vma to find vma and associated
- * address space. The returned mapping may be stale, but it can not be
- * invalid as page lock (which is held) is required to destroy mapping.
- */
-static struct address_space *_get_hugetlb_page_mapping(struct page *hpage)
-{
- struct anon_vma *anon_vma;
- pgoff_t pgoff_start, pgoff_end;
- struct anon_vma_chain *avc;
- struct address_space *mapping = page_mapping(hpage);
-
- /* Simple file based mapping */
- if (mapping)
- return mapping;
-
- /*
- * Even anonymous hugetlbfs mappings are associated with an
- * underlying hugetlbfs file (see hugetlb_file_setup in mmap
- * code). Find a vma associated with the anonymous vma, and
- * use the file pointer to get address_space.
- */
- anon_vma = page_lock_anon_vma_read(hpage);
- if (!anon_vma)
- return mapping; /* NULL */
-
- /* Use first found vma */
- pgoff_start = page_to_pgoff(hpage);
- pgoff_end = pgoff_start + pages_per_huge_page(page_hstate(hpage)) - 1;
- anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root,
- pgoff_start, pgoff_end) {
- struct vm_area_struct *vma = avc->vma;
-
- mapping = vma->vm_file->f_mapping;
- break;
- }
-
- anon_vma_unlock_read(anon_vma);
- return mapping;
-}
-
-/*
* Find and lock address space (mapping) in write mode.
*
- * Upon entry, the page is locked which allows us to find the mapping
- * even in the case of an anon page. However, locking order dictates
- * the i_mmap_rwsem be acquired BEFORE the page lock. This is hugetlbfs
- * specific. So, we first try to lock the sema while still holding the
- * page lock. If this works, great! If not, then we need to drop the
- * page lock and then acquire i_mmap_rwsem and reacquire page lock. Of
- * course, need to revalidate state along the way.
+ * Upon entry, the page is locked which means that page_mapping() is
+ * stable. Due to locking order, we can only trylock_write. If we can
+ * not get the lock, simply return NULL to caller.
*/
struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage)
{
- struct address_space *mapping, *mapping2;
+ struct address_space *mapping = page_mapping(hpage);
- mapping = _get_hugetlb_page_mapping(hpage);
-retry:
if (!mapping)
return mapping;
- /*
- * If no contention, take lock and return
- */
if (i_mmap_trylock_write(mapping))
return mapping;
- /*
- * Must drop page lock and wait on mapping sema.
- * Note: Once page lock is dropped, mapping could become invalid.
- * As a hack, increase map count until we lock page again.
- */
- atomic_inc(&hpage->_mapcount);
- unlock_page(hpage);
- i_mmap_lock_write(mapping);
- lock_page(hpage);
- atomic_add_negative(-1, &hpage->_mapcount);
-
- /* verify page is still mapped */
- if (!page_mapped(hpage)) {
- i_mmap_unlock_write(mapping);
- return NULL;
- }
-
- /*
- * Get address space again and verify it is the same one
- * we locked. If not, drop lock and retry.
- */
- mapping2 = _get_hugetlb_page_mapping(hpage);
- if (mapping2 != mapping) {
- i_mmap_unlock_write(mapping);
- mapping = mapping2;
- goto retry;
- }
-
- return mapping;
+ return NULL;
}
pgoff_t __basepage_index(struct page *page)
@@ -2443,6 +2362,9 @@
rsv_adjust = hugepage_subpool_put_pages(spool, 1);
hugetlb_acct_memory(h, -rsv_adjust);
+ if (deferred_reserve)
+ hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h),
+ pages_per_huge_page(h), page);
}
return page;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3a24e3b..3dcbf24 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4110,11 +4110,17 @@
(u64)memsw * PAGE_SIZE);
for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
+ unsigned long nr;
+
if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
continue;
+ nr = memcg_page_state(memcg, memcg1_stats[i]);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ if (memcg1_stats[i] == NR_ANON_THPS)
+ nr *= HPAGE_PMD_NR;
+#endif
seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i],
- (u64)memcg_page_state(memcg, memcg1_stats[i]) *
- PAGE_SIZE);
+ (u64)nr * PAGE_SIZE);
}
for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
@@ -5339,17 +5345,22 @@
memcg->swappiness = mem_cgroup_swappiness(parent);
memcg->oom_kill_disable = parent->oom_kill_disable;
}
- if (parent && parent->use_hierarchy) {
+ if (!parent) {
+ page_counter_init(&memcg->memory, NULL);
+ page_counter_init(&memcg->swap, NULL);
+ page_counter_init(&memcg->kmem, NULL);
+ page_counter_init(&memcg->tcpmem, NULL);
+ } else if (parent->use_hierarchy) {
memcg->use_hierarchy = true;
page_counter_init(&memcg->memory, &parent->memory);
page_counter_init(&memcg->swap, &parent->swap);
page_counter_init(&memcg->kmem, &parent->kmem);
page_counter_init(&memcg->tcpmem, &parent->tcpmem);
} else {
- page_counter_init(&memcg->memory, NULL);
- page_counter_init(&memcg->swap, NULL);
- page_counter_init(&memcg->kmem, NULL);
- page_counter_init(&memcg->tcpmem, NULL);
+ page_counter_init(&memcg->memory, &root_mem_cgroup->memory);
+ page_counter_init(&memcg->swap, &root_mem_cgroup->swap);
+ page_counter_init(&memcg->kmem, &root_mem_cgroup->kmem);
+ page_counter_init(&memcg->tcpmem, &root_mem_cgroup->tcpmem);
/*
* Deeper hierachy with use_hierarchy == false doesn't make
* much sense so let cgroup subsystem know about this
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index c0bb186..5d880d4 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1057,27 +1057,25 @@
if (!PageHuge(hpage)) {
unmap_success = try_to_unmap(hpage, ttu);
} else {
- /*
- * For hugetlb pages, try_to_unmap could potentially call
- * huge_pmd_unshare. Because of this, take semaphore in
- * write mode here and set TTU_RMAP_LOCKED to indicate we
- * have taken the lock at this higer level.
- *
- * Note that the call to hugetlb_page_mapping_lock_write
- * is necessary even if mapping is already set. It handles
- * ugliness of potentially having to drop page lock to obtain
- * i_mmap_rwsem.
- */
- mapping = hugetlb_page_mapping_lock_write(hpage);
-
- if (mapping) {
- unmap_success = try_to_unmap(hpage,
+ if (!PageAnon(hpage)) {
+ /*
+ * For hugetlb pages in shared mappings, try_to_unmap
+ * could potentially call huge_pmd_unshare. Because of
+ * this, take semaphore in write mode here and set
+ * TTU_RMAP_LOCKED to indicate we have taken the lock
+ * at this higer level.
+ */
+ mapping = hugetlb_page_mapping_lock_write(hpage);
+ if (mapping) {
+ unmap_success = try_to_unmap(hpage,
ttu|TTU_RMAP_LOCKED);
- i_mmap_unlock_write(mapping);
+ i_mmap_unlock_write(mapping);
+ } else {
+ pr_info("Memory failure: %#lx: could not lock mapping for mapped huge page\n", pfn);
+ unmap_success = false;
+ }
} else {
- pr_info("Memory failure: %#lx: could not find mapping for mapped huge page\n",
- pfn);
- unmap_success = false;
+ unmap_success = try_to_unmap(hpage, ttu);
}
}
if (!unmap_success)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 3fde772..3ca4898 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -525,7 +525,7 @@
unsigned long flags = qp->flags;
int ret;
bool has_unmovable = false;
- pte_t *pte;
+ pte_t *pte, *mapped_pte;
spinlock_t *ptl;
ptl = pmd_trans_huge_lock(pmd, vma);
@@ -539,7 +539,7 @@
if (pmd_trans_unstable(pmd))
return 0;
- pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE) {
if (!pte_present(*pte))
continue;
@@ -571,7 +571,7 @@
} else
break;
}
- pte_unmap_unlock(pte - 1, ptl);
+ pte_unmap_unlock(mapped_pte, ptl);
cond_resched();
if (has_unmovable)
diff --git a/mm/memremap.c b/mm/memremap.c
index 73a206d..16b2fb4 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -41,28 +41,24 @@
DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
EXPORT_SYMBOL(devmap_managed_key);
-static void devmap_managed_enable_put(void)
+static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
{
- static_branch_dec(&devmap_managed_key);
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
+ pgmap->type == MEMORY_DEVICE_FS_DAX)
+ static_branch_dec(&devmap_managed_key);
}
-static int devmap_managed_enable_get(struct dev_pagemap *pgmap)
+static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
{
- if (pgmap->type == MEMORY_DEVICE_PRIVATE &&
- (!pgmap->ops || !pgmap->ops->page_free)) {
- WARN(1, "Missing page_free method\n");
- return -EINVAL;
- }
-
- static_branch_inc(&devmap_managed_key);
- return 0;
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
+ pgmap->type == MEMORY_DEVICE_FS_DAX)
+ static_branch_inc(&devmap_managed_key);
}
#else
-static int devmap_managed_enable_get(struct dev_pagemap *pgmap)
+static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
{
- return -EINVAL;
}
-static void devmap_managed_enable_put(void)
+static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
{
}
#endif /* CONFIG_DEV_PAGEMAP_OPS */
@@ -169,7 +165,7 @@
pageunmap_range(pgmap, i);
WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n");
- devmap_managed_enable_put();
+ devmap_managed_enable_put(pgmap);
}
EXPORT_SYMBOL_GPL(memunmap_pages);
@@ -307,7 +303,6 @@
.pgprot = PAGE_KERNEL,
};
const int nr_range = pgmap->nr_range;
- bool need_devmap_managed = true;
int error, i;
if (WARN_ONCE(!nr_range, "nr_range must be specified\n"))
@@ -323,6 +318,10 @@
WARN(1, "Missing migrate_to_ram method\n");
return ERR_PTR(-EINVAL);
}
+ if (!pgmap->ops->page_free) {
+ WARN(1, "Missing page_free method\n");
+ return ERR_PTR(-EINVAL);
+ }
if (!pgmap->owner) {
WARN(1, "Missing owner\n");
return ERR_PTR(-EINVAL);
@@ -336,11 +335,9 @@
}
break;
case MEMORY_DEVICE_GENERIC:
- need_devmap_managed = false;
break;
case MEMORY_DEVICE_PCI_P2PDMA:
params.pgprot = pgprot_noncached(params.pgprot);
- need_devmap_managed = false;
break;
default:
WARN(1, "Invalid pgmap type %d\n", pgmap->type);
@@ -364,11 +361,7 @@
}
}
- if (need_devmap_managed) {
- error = devmap_managed_enable_get(pgmap);
- if (error)
- return ERR_PTR(error);
- }
+ devmap_managed_enable_get(pgmap);
/*
* Clear the pgmap nr_range as it will be incremented for each
diff --git a/mm/migrate.c b/mm/migrate.c
index 5ca5842..5795cb8 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1328,34 +1328,38 @@
goto put_anon;
if (page_mapped(hpage)) {
- /*
- * try_to_unmap could potentially call huge_pmd_unshare.
- * Because of this, take semaphore in write mode here and
- * set TTU_RMAP_LOCKED to let lower levels know we have
- * taken the lock.
- */
- mapping = hugetlb_page_mapping_lock_write(hpage);
- if (unlikely(!mapping))
- goto unlock_put_anon;
+ bool mapping_locked = false;
+ enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK|
+ TTU_IGNORE_ACCESS;
- try_to_unmap(hpage,
- TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS|
- TTU_RMAP_LOCKED);
+ if (!PageAnon(hpage)) {
+ /*
+ * In shared mappings, try_to_unmap could potentially
+ * call huge_pmd_unshare. Because of this, take
+ * semaphore in write mode here and set TTU_RMAP_LOCKED
+ * to let lower levels know we have taken the lock.
+ */
+ mapping = hugetlb_page_mapping_lock_write(hpage);
+ if (unlikely(!mapping))
+ goto unlock_put_anon;
+
+ mapping_locked = true;
+ ttu |= TTU_RMAP_LOCKED;
+ }
+
+ try_to_unmap(hpage, ttu);
page_was_mapped = 1;
- /*
- * Leave mapping locked until after subsequent call to
- * remove_migration_ptes()
- */
+
+ if (mapping_locked)
+ i_mmap_unlock_write(mapping);
}
if (!page_mapped(hpage))
rc = move_to_new_page(new_hpage, hpage, mode);
- if (page_was_mapped) {
+ if (page_was_mapped)
remove_migration_ptes(hpage,
- rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, true);
- i_mmap_unlock_write(mapping);
- }
+ rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, false);
unlock_put_anon:
unlock_page(new_hpage);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 23f5066..eaa227a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5103,6 +5103,11 @@
if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
goto refill;
+ if (unlikely(nc->pfmemalloc)) {
+ free_the_page(page, compound_order(page));
+ goto refill;
+ }
+
#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
/* if size can vary use size else just use PAGE_SIZE */
size = nc->size;
diff --git a/mm/percpu.c b/mm/percpu.c
index 66a93f0..ad7a37e 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1315,8 +1315,8 @@
region_size = ALIGN(start_offset + map_size, lcm_align);
/* allocate chunk */
- alloc_size = sizeof(struct pcpu_chunk) +
- BITS_TO_LONGS(region_size >> PAGE_SHIFT) * sizeof(unsigned long);
+ alloc_size = struct_size(chunk, populated,
+ BITS_TO_LONGS(region_size >> PAGE_SHIFT));
chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
if (!chunk)
panic("%s: Failed to allocate %zu bytes\n", __func__,
@@ -2521,8 +2521,8 @@
pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT;
pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
pcpu_atom_size = ai->atom_size;
- pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) +
- BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long);
+ pcpu_chunk_struct_size = struct_size(chunk, populated,
+ BITS_TO_LONGS(pcpu_unit_pages));
pcpu_stats_save_ai(ai);
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index fd12da8..702250f 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -5,6 +5,7 @@
* Copyright (C) 2010-2011 Christopher Yeoh <cyeoh@au1.ibm.com>, IBM Corp.
*/
+#include <linux/compat.h>
#include <linux/mm.h>
#include <linux/uio.h>
#include <linux/sched.h>
@@ -273,7 +274,8 @@
return rc;
if (!iov_iter_count(&iter))
goto free_iov_l;
- iov_r = iovec_from_user(rvec, riovcnt, UIO_FASTIOV, iovstack_r, false);
+ iov_r = iovec_from_user(rvec, riovcnt, UIO_FASTIOV, iovstack_r,
+ in_compat_syscall());
if (IS_ERR(iov_r)) {
rc = PTR_ERR(iov_r);
goto free_iov_l;
diff --git a/mm/rmap.c b/mm/rmap.c
index 1b84945..31b2932 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1413,9 +1413,6 @@
/*
* If sharing is possible, start and end will be adjusted
* accordingly.
- *
- * If called for a huge page, caller must hold i_mmap_rwsem
- * in write mode as it is possible to call huge_pmd_unshare.
*/
adjust_range_if_pmd_sharing_possible(vma, &range.start,
&range.end);
@@ -1462,7 +1459,7 @@
subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
address = pvmw.address;
- if (PageHuge(page)) {
+ if (PageHuge(page) && !PageAnon(page)) {
/*
* To call huge_pmd_unshare, i_mmap_rwsem must be
* held in write mode. Caller needs to explicitly
diff --git a/mm/slub.c b/mm/slub.c
index b30be23..34dcc09 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2852,7 +2852,7 @@
object = c->freelist;
page = c->page;
- if (unlikely(!object || !node_match(page, node))) {
+ if (unlikely(!object || !page || !node_match(page, node))) {
object = __slab_alloc(s, gfpflags, node, addr, c);
} else {
void *next_object = get_freepointer_safe(s, object);
diff --git a/mm/truncate.c b/mm/truncate.c
index 18cec39..960edf5 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -528,7 +528,7 @@
}
EXPORT_SYMBOL(truncate_inode_pages_final);
-unsigned long __invalidate_mapping_pages(struct address_space *mapping,
+static unsigned long __invalidate_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t end, unsigned long *nr_pagevec)
{
pgoff_t indices[PAGEVEC_SIZE];
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1b8f0e0..7b4e31e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1516,7 +1516,8 @@
nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc,
TTU_IGNORE_ACCESS, &stat, true);
list_splice(&clean_pages, page_list);
- mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -nr_reclaimed);
+ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
+ -(long)nr_reclaimed);
/*
* Since lazyfree pages are isolated from file LRU from the beginning,
* they will rotate back to anonymous LRU in the end if it failed to
@@ -1526,7 +1527,7 @@
mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON,
stat.nr_lazyfree_fail);
mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
- -stat.nr_lazyfree_fail);
+ -(long)stat.nr_lazyfree_fail);
return nr_reclaimed;
}
diff --git a/net/atm/lec.c b/net/atm/lec.c
index dbabb65..7226c78 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -954,9 +954,8 @@
{
struct lec_state *state = seq->private;
- v = lec_get_idx(state, 1);
- *pos += !!PTR_ERR(v);
- return v;
+ ++*pos;
+ return lec_get_idx(state, 1);
}
static int lec_seq_show(struct seq_file *seq, void *v)
diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c
index 8579bfe..4b39534 100644
--- a/net/bluetooth/msft.c
+++ b/net/bluetooth/msft.c
@@ -12,12 +12,13 @@
struct msft_cp_read_supported_features {
__u8 sub_opcode;
} __packed;
+
struct msft_rp_read_supported_features {
__u8 status;
__u8 sub_opcode;
__le64 features;
__u8 evt_prefix_len;
- __u8 evt_prefix[0];
+ __u8 evt_prefix[];
} __packed;
struct msft_data {
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 6f742fe..7730c8f 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -207,6 +207,7 @@
{
struct net_bridge *br = netdev_priv(dev);
+ netdev_stats_to_stats64(stats, &dev->stats);
dev_fetch_sw_netstats(stats, br->stats);
}
diff --git a/net/can/Kconfig b/net/can/Kconfig
index 224e5e0..7c9958d 100644
--- a/net/can/Kconfig
+++ b/net/can/Kconfig
@@ -62,8 +62,9 @@
communication between CAN nodes via two defined CAN Identifiers.
As CAN frames can only transport a small amount of data bytes
(max. 8 bytes for 'classic' CAN and max. 64 bytes for CAN FD) this
- segmentation is needed to transport longer PDUs as needed e.g. for
- vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN traffic.
+ segmentation is needed to transport longer Protocol Data Units (PDU)
+ as needed e.g. for vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN
+ traffic.
This protocol driver implements data transfers according to
ISO 15765-2:2016 for 'classic' CAN and CAN FD frame types.
If you want to perform automotive vehicle diagnostic services (UDS),
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 6373ab9..5d124c1 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -677,16 +677,25 @@
{
struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
- if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU ||
- cfd->len > CAN_MAX_DLEN)) {
- pr_warn_once("PF_CAN: dropped non conform CAN skbuf: dev type %d, len %d, datalen %d\n",
+ if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU)) {
+ pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d\n",
+ dev->type, skb->len);
+ goto free_skb;
+ }
+
+ /* This check is made separately since cfd->len would be uninitialized if skb->len = 0. */
+ if (unlikely(cfd->len > CAN_MAX_DLEN)) {
+ pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d, datalen %d\n",
dev->type, skb->len, cfd->len);
- kfree_skb(skb);
- return NET_RX_DROP;
+ goto free_skb;
}
can_receive(skb, dev);
return NET_RX_SUCCESS;
+
+free_skb:
+ kfree_skb(skb);
+ return NET_RX_DROP;
}
static int canfd_rcv(struct sk_buff *skb, struct net_device *dev,
@@ -694,16 +703,25 @@
{
struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
- if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU ||
- cfd->len > CANFD_MAX_DLEN)) {
- pr_warn_once("PF_CAN: dropped non conform CAN FD skbuf: dev type %d, len %d, datalen %d\n",
+ if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU)) {
+ pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d\n",
+ dev->type, skb->len);
+ goto free_skb;
+ }
+
+ /* This check is made separately since cfd->len would be uninitialized if skb->len = 0. */
+ if (unlikely(cfd->len > CANFD_MAX_DLEN)) {
+ pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d, datalen %d\n",
dev->type, skb->len, cfd->len);
- kfree_skb(skb);
- return NET_RX_DROP;
+ goto free_skb;
}
can_receive(skb, dev);
return NET_RX_SUCCESS;
+
+free_skb:
+ kfree_skb(skb);
+ return NET_RX_DROP;
}
/* af_can protocol functions */
diff --git a/net/can/isotp.c b/net/can/isotp.c
index 4c20628..d78ab13 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -252,14 +252,16 @@
static u8 padlen(u8 datalen)
{
- const u8 plen[] = {8, 8, 8, 8, 8, 8, 8, 8, 8, /* 0 - 8 */
- 12, 12, 12, 12, /* 9 - 12 */
- 16, 16, 16, 16, /* 13 - 16 */
- 20, 20, 20, 20, /* 17 - 20 */
- 24, 24, 24, 24, /* 21 - 24 */
- 32, 32, 32, 32, 32, 32, 32, 32, /* 25 - 32 */
- 48, 48, 48, 48, 48, 48, 48, 48, /* 33 - 40 */
- 48, 48, 48, 48, 48, 48, 48, 48}; /* 41 - 48 */
+ static const u8 plen[] = {
+ 8, 8, 8, 8, 8, 8, 8, 8, 8, /* 0 - 8 */
+ 12, 12, 12, 12, /* 9 - 12 */
+ 16, 16, 16, 16, /* 13 - 16 */
+ 20, 20, 20, 20, /* 17 - 20 */
+ 24, 24, 24, 24, /* 21 - 24 */
+ 32, 32, 32, 32, 32, 32, 32, 32, /* 25 - 32 */
+ 48, 48, 48, 48, 48, 48, 48, 48, /* 33 - 40 */
+ 48, 48, 48, 48, 48, 48, 48, 48 /* 41 - 48 */
+ };
if (datalen > 48)
return 64;
@@ -569,10 +571,6 @@
return 0;
}
- /* no creation of flow control frames */
- if (so->opt.flags & CAN_ISOTP_LISTEN_MODE)
- return 0;
-
/* perform blocksize handling, if enabled */
if (!so->rxfc.bs || ++so->rx.bs < so->rxfc.bs) {
/* start rx timeout watchdog */
@@ -581,6 +579,10 @@
return 0;
}
+ /* no creation of flow control frames */
+ if (so->opt.flags & CAN_ISOTP_LISTEN_MODE)
+ return 0;
+
/* we reached the specified blocksize so->rxfc.bs */
isotp_send_fc(sk, ae, ISOTP_FC_CTS);
return 0;
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 1be4c89..f239665 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -475,6 +475,12 @@
goto out_release_sock;
}
+ if (!(ndev->flags & IFF_UP)) {
+ dev_put(ndev);
+ ret = -ENETDOWN;
+ goto out_release_sock;
+ }
+
priv = j1939_netdev_start(ndev);
dev_put(ndev);
if (IS_ERR(priv)) {
diff --git a/net/can/proc.c b/net/can/proc.c
index 550928b..5ea8695 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -462,6 +462,9 @@
*/
void can_remove_proc(struct net *net)
{
+ if (!net->can.proc_dir)
+ return;
+
if (net->can.pde_stats)
remove_proc_entry(CAN_PROC_STATS, net->can.proc_dir);
@@ -486,6 +489,5 @@
if (net->can.pde_rcvlist_sff)
remove_proc_entry(CAN_PROC_RCVLIST_SFF, net->can.proc_dir);
- if (net->can.proc_dir)
- remove_proc_entry("can", net->proc_net);
+ remove_proc_entry("can", net->proc_net);
}
diff --git a/net/core/devlink.c b/net/core/devlink.c
index a578634..4b02115 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1448,7 +1448,7 @@
err = ops->sb_occ_port_pool_get(devlink_port, devlink_sb->index,
pool_index, &cur, &max);
if (err && err != -EOPNOTSUPP)
- return err;
+ goto sb_occ_get_failure;
if (!err) {
if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur))
goto nla_put_failure;
@@ -1461,8 +1461,10 @@
return 0;
nla_put_failure:
+ err = -EMSGSIZE;
+sb_occ_get_failure:
genlmsg_cancel(msg, hdr);
- return -EMSGSIZE;
+ return err;
}
static int devlink_nl_cmd_sb_port_pool_get_doit(struct sk_buff *skb,
@@ -4213,10 +4215,12 @@
if (err)
goto nla_put_failure;
- if (region->port)
- if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
- region->port->index))
+ if (region->port) {
+ err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+ region->port->index);
+ if (err)
goto nla_put_failure;
+ }
err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name);
if (err)
@@ -4265,10 +4269,12 @@
if (err)
goto out_cancel_msg;
- if (region->port)
- if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
- region->port->index))
+ if (region->port) {
+ err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+ region->port->index);
+ if (err)
goto out_cancel_msg;
+ }
err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME,
region->ops->name);
@@ -4915,8 +4921,10 @@
index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
port = devlink_port_get_by_index(devlink, index);
- if (!port)
- return -ENODEV;
+ if (!port) {
+ err = -ENODEV;
+ goto out_unlock;
+ }
}
region_name = nla_data(attrs[DEVLINK_ATTR_REGION_NAME]);
@@ -4962,10 +4970,12 @@
if (err)
goto nla_put_failure;
- if (region->port)
- if (nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX,
- region->port->index))
+ if (region->port) {
+ err = nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX,
+ region->port->index);
+ if (err)
goto nla_put_failure;
+ }
err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name);
if (err)
@@ -8246,8 +8256,6 @@
{
struct devlink_port_attrs *attrs = &devlink_port->attrs;
- if (WARN_ON(devlink_port->registered))
- return -EEXIST;
devlink_port->attrs_set = true;
attrs->flavour = flavour;
if (attrs->switch_id.id_len) {
@@ -8271,6 +8279,8 @@
{
int ret;
+ if (WARN_ON(devlink_port->registered))
+ return;
devlink_port->attrs = *attrs;
ret = __devlink_port_attrs_set(devlink_port, attrs->flavour);
if (ret)
@@ -8293,6 +8303,8 @@
struct devlink_port_attrs *attrs = &devlink_port->attrs;
int ret;
+ if (WARN_ON(devlink_port->registered))
+ return;
ret = __devlink_port_attrs_set(devlink_port,
DEVLINK_PORT_FLAVOUR_PCI_PF);
if (ret)
@@ -8318,6 +8330,8 @@
struct devlink_port_attrs *attrs = &devlink_port->attrs;
int ret;
+ if (WARN_ON(devlink_port->registered))
+ return;
ret = __devlink_port_attrs_set(devlink_port,
DEVLINK_PORT_FLAVOUR_PCI_VF);
if (ret)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 8e39e28..9500d28 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -235,6 +235,8 @@
write_lock(&n->lock);
if ((n->nud_state == NUD_FAILED) ||
+ (tbl->is_multicast &&
+ tbl->is_multicast(n->primary_key)) ||
time_after(tref, n->updated))
remove = true;
write_unlock(&n->lock);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index c310c7c..9609482 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -29,6 +29,7 @@
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/if_vlan.h>
+#include <net/dsa.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/addrconf.h>
@@ -657,15 +658,15 @@
int netpoll_setup(struct netpoll *np)
{
- struct net_device *ndev = NULL;
+ struct net_device *ndev = NULL, *dev = NULL;
+ struct net *net = current->nsproxy->net_ns;
struct in_device *in_dev;
int err;
rtnl_lock();
- if (np->dev_name[0]) {
- struct net *net = current->nsproxy->net_ns;
+ if (np->dev_name[0])
ndev = __dev_get_by_name(net, np->dev_name);
- }
+
if (!ndev) {
np_err(np, "%s doesn't exist, aborting\n", np->dev_name);
err = -ENODEV;
@@ -673,6 +674,19 @@
}
dev_hold(ndev);
+ /* bring up DSA management network devices up first */
+ for_each_netdev(net, dev) {
+ if (!netdev_uses_dsa(dev))
+ continue;
+
+ err = dev_change_flags(dev, dev->flags | IFF_UP, NULL);
+ if (err < 0) {
+ np_err(np, "%s failed to open %s\n",
+ np->dev_name, dev->name);
+ goto put;
+ }
+ }
+
if (netdev_master_upper_dev_get(ndev)) {
np_err(np, "%s is a slave device, aborting\n", np->dev_name);
err = -EBUSY;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 654182e..25cdbb2 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -170,10 +170,12 @@
struct scatterlist *sge = sk_msg_elem(msg, i);
u32 len = sge->length;
- if (charge)
- sk_mem_uncharge(sk, len);
- if (!msg->skb)
+ /* When the skb owns the memory we free it from consume_skb path. */
+ if (!msg->skb) {
+ if (charge)
+ sk_mem_uncharge(sk, len);
put_page(sg_page(sge));
+ }
memset(sge, 0, sizeof(*sge));
return len;
}
@@ -397,28 +399,45 @@
}
EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);
-static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
+static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
+ struct sk_buff *skb)
{
- struct sock *sk = psock->sk;
- int copied = 0, num_sge;
struct sk_msg *msg;
+ if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
+ return NULL;
+
+ if (!sk_rmem_schedule(sk, skb, skb->truesize))
+ return NULL;
+
msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
if (unlikely(!msg))
- return -EAGAIN;
- if (!sk_rmem_schedule(sk, skb, skb->len)) {
- kfree(msg);
- return -EAGAIN;
- }
+ return NULL;
sk_msg_init(msg);
+ return msg;
+}
+
+static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
+ struct sk_psock *psock,
+ struct sock *sk,
+ struct sk_msg *msg)
+{
+ int num_sge, copied;
+
+ /* skb linearize may fail with ENOMEM, but lets simply try again
+ * later if this happens. Under memory pressure we don't want to
+ * drop the skb. We need to linearize the skb so that the mapping
+ * in skb_to_sgvec can not error.
+ */
+ if (skb_linearize(skb))
+ return -EAGAIN;
num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len);
if (unlikely(num_sge < 0)) {
kfree(msg);
return num_sge;
}
- sk_mem_charge(sk, skb->len);
copied = skb->len;
msg->sg.start = 0;
msg->sg.size = copied;
@@ -430,6 +449,48 @@
return copied;
}
+static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb);
+
+static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
+{
+ struct sock *sk = psock->sk;
+ struct sk_msg *msg;
+
+ /* If we are receiving on the same sock skb->sk is already assigned,
+ * skip memory accounting and owner transition seeing it already set
+ * correctly.
+ */
+ if (unlikely(skb->sk == sk))
+ return sk_psock_skb_ingress_self(psock, skb);
+ msg = sk_psock_create_ingress_msg(sk, skb);
+ if (!msg)
+ return -EAGAIN;
+
+ /* This will transition ownership of the data from the socket where
+ * the BPF program was run initiating the redirect to the socket
+ * we will eventually receive this data on. The data will be released
+ * from skb_consume found in __tcp_bpf_recvmsg() after its been copied
+ * into user buffers.
+ */
+ skb_set_owner_r(skb, sk);
+ return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+}
+
+/* Puts an skb on the ingress queue of the socket already assigned to the
+ * skb. In this case we do not need to check memory limits or skb_set_owner_r
+ * because the skb is already accounted for here.
+ */
+static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb)
+{
+ struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
+ struct sock *sk = psock->sk;
+
+ if (unlikely(!msg))
+ return -EAGAIN;
+ sk_msg_init(msg);
+ return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+}
+
static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
u32 off, u32 len, bool ingress)
{
@@ -789,7 +850,7 @@
* retrying later from workqueue.
*/
if (skb_queue_empty(&psock->ingress_skb)) {
- err = sk_psock_skb_ingress(psock, skb);
+ err = sk_psock_skb_ingress_self(psock, skb);
}
if (err < 0) {
skb_queue_tail(&psock->ingress_skb, skb);
diff --git a/net/ethtool/features.c b/net/ethtool/features.c
index 8ee4cdb..1c9f4df 100644
--- a/net/ethtool/features.c
+++ b/net/ethtool/features.c
@@ -280,7 +280,7 @@
active_diff_mask, compact);
}
if (mod)
- ethtool_notify(dev, ETHTOOL_MSG_FEATURES_NTF, NULL);
+ netdev_features_change(dev);
out_rtnl:
rtnl_unlock();
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 687971d..922dd73 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -125,6 +125,7 @@
static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb);
static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb);
static void parp_redo(struct sk_buff *skb);
+static int arp_is_multicast(const void *pkey);
static const struct neigh_ops arp_generic_ops = {
.family = AF_INET,
@@ -156,6 +157,7 @@
.key_eq = arp_key_eq,
.constructor = arp_constructor,
.proxy_redo = parp_redo,
+ .is_multicast = arp_is_multicast,
.id = "arp_cache",
.parms = {
.tbl = &arp_tbl,
@@ -928,6 +930,10 @@
arp_process(dev_net(skb->dev), NULL, skb);
}
+static int arp_is_multicast(const void *pkey)
+{
+ return ipv4_is_multicast(*((__be32 *)pkey));
+}
/*
* Receive an arp request from the device layer.
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 86a23e4a..b87140a 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -696,7 +696,7 @@
cfg->fc_gw4 = *((__be32 *)via->rtvia_addr);
break;
case AF_INET6:
-#ifdef CONFIG_IPV6
+#if IS_ENABLED(CONFIG_IPV6)
if (alen != sizeof(struct in6_addr)) {
NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA");
return -EINVAL;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 366a450..93474b1 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -479,8 +479,10 @@
r->idiag_inode = 0;
if (net_admin && nla_put_u32(skb, INET_DIAG_MARK,
- inet_rsk(reqsk)->ir_mark))
+ inet_rsk(reqsk)->ir_mark)) {
+ nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
+ }
nlmsg_end(skb, nlh);
return 0;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 8b04d1d..ee65c92 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -608,9 +608,6 @@
ttl = ip4_dst_hoplimit(&rt->dst);
}
- if (!df && skb->protocol == htons(ETH_P_IP))
- df = inner_iph->frag_off & htons(IP_DF);
-
headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len;
if (headroom > dev->needed_headroom)
dev->needed_headroom = headroom;
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 25f1caf..e25be2d 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -263,7 +263,7 @@
const struct icmphdr *icmph = icmp_hdr(skb);
const struct iphdr *iph = ip_hdr(skb);
- if (mtu <= 576 || iph->frag_off != htons(IP_DF))
+ if (mtu < 576 || iph->frag_off != htons(IP_DF))
return 0;
if (ipv4_is_lbcast(iph->daddr) || ipv4_is_multicast(iph->daddr) ||
@@ -359,7 +359,7 @@
__be16 frag_off;
int offset;
- if (mtu <= IPV6_MIN_MTU)
+ if (mtu < IPV6_MIN_MTU)
return 0;
if (stype == IPV6_ADDR_ANY || stype == IPV6_ADDR_MULTICAST ||
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index a058213..7c84103 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -17,17 +17,19 @@
#include <net/netfilter/nf_queue.h>
/* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
-int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_type)
+int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int addr_type)
{
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
struct flowi4 fl4 = {};
__be32 saddr = iph->saddr;
- const struct sock *sk = skb_to_full_sk(skb);
- __u8 flags = sk ? inet_sk_flowi_flags(sk) : 0;
+ __u8 flags;
struct net_device *dev = skb_dst(skb)->dev;
unsigned int hh_len;
+ sk = sk_to_full_sk(sk);
+ flags = sk ? inet_sk_flowi_flags(sk) : 0;
+
if (addr_type == RTN_UNSPEC)
addr_type = inet_addr_type_dev_table(net, dev, saddr);
if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index f703a71..8330795 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -62,7 +62,7 @@
iph->daddr != daddr ||
skb->mark != mark ||
iph->tos != tos) {
- err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+ err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
if (err < 0)
ret = NF_DROP_ERR(err);
}
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 9dcfa4e..93b0773 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -145,7 +145,7 @@
ip4_dst_hoplimit(skb_dst(nskb)));
nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
- if (ip_route_me_harder(net, nskb, RTN_UNSPEC))
+ if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC))
goto free_nskb;
niph = ip_hdr(nskb);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 6ac473b..00dc3f9 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -331,7 +331,7 @@
__u32 cookie = ntohl(th->ack_seq) - 1;
struct sock *ret = sk;
struct request_sock *req;
- int mss;
+ int full_space, mss;
struct rtable *rt;
__u8 rcv_wscale;
struct flowi4 fl4;
@@ -427,8 +427,13 @@
/* Try to redo what tcp_v4_send_synack did. */
req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
+ /* limit the window selection if the user enforce a smaller rx buffer */
+ full_space = tcp_full_space(sk);
+ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+ (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
+ req->rsk_window_clamp = full_space;
- tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
+ tcp_select_initial_window(sk, full_space, req->mss,
&req->rsk_rcv_wnd, &req->rsk_window_clamp,
ireq->wscale_ok, &rcv_wscale,
dst_metric(&rt->dst, RTAX_INITRWND));
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bae4284..b2bc3d7 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -485,6 +485,8 @@
return true;
if (tcp_rmem_pressure(sk))
return true;
+ if (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss)
+ return true;
}
if (sk->sk_prot->stream_memory_read)
return sk->sk_prot->stream_memory_read(sk);
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 6c4d79b..6ea3dc2 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -945,7 +945,7 @@
filter_expired = after(tcp_jiffies32,
bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ);
if (rs->rtt_us >= 0 &&
- (rs->rtt_us <= bbr->min_rtt_us ||
+ (rs->rtt_us < bbr->min_rtt_us ||
(filter_expired && !rs->is_ack_delayed))) {
bbr->min_rtt_us = rs->rtt_us;
bbr->min_rtt_stamp = tcp_jiffies32;
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 37f4cb2b..bc7d2a5 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -15,8 +15,8 @@
{
struct iov_iter *iter = &msg->msg_iter;
int peek = flags & MSG_PEEK;
- int i, ret, copied = 0;
struct sk_msg *msg_rx;
+ int i, copied = 0;
msg_rx = list_first_entry_or_null(&psock->ingress_msg,
struct sk_msg, list);
@@ -37,17 +37,16 @@
page = sg_page(sge);
if (copied + copy > len)
copy = len - copied;
- ret = copy_page_to_iter(page, sge->offset, copy, iter);
- if (ret != copy) {
- msg_rx->sg.start = i;
- return -EFAULT;
- }
+ copy = copy_page_to_iter(page, sge->offset, copy, iter);
+ if (!copy)
+ return copied ? copied : -EFAULT;
copied += copy;
if (likely(!peek)) {
sge->offset += copy;
sge->length -= copy;
- sk_mem_uncharge(sk, copy);
+ if (!msg_rx->skb)
+ sk_mem_uncharge(sk, copy);
msg_rx->sg.size -= copy;
if (!sge->length) {
@@ -56,6 +55,11 @@
put_page(page);
}
} else {
+ /* Lets not optimize peek case if copy_page_to_iter
+ * didn't copy the entire length lets just break.
+ */
+ if (copy != sge->length)
+ return copied;
sk_msg_iter_var_next(i);
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fc44583..389d1b3 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4908,7 +4908,8 @@
int avail = tp->rcv_nxt - tp->copied_seq;
if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) &&
- !sock_flag(sk, SOCK_DONE))
+ !sock_flag(sk, SOCK_DONE) &&
+ tcp_receive_window(tp) > inet_csk(sk)->icsk_ack.rcv_mss)
return;
sk->sk_data_ready(sk);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index e67a66f..c62805c 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -366,7 +366,7 @@
static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
struct sk_buff *skb)
{
- struct udphdr *uh = udp_hdr(skb);
+ struct udphdr *uh = udp_gro_udphdr(skb);
struct sk_buff *pp = NULL;
struct udphdr *uh2;
struct sk_buff *p;
@@ -500,12 +500,22 @@
}
EXPORT_SYMBOL(udp_gro_receive);
+static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
+ __be16 dport)
+{
+ const struct iphdr *iph = skb_gro_network_header(skb);
+
+ return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
+ iph->daddr, dport, inet_iif(skb),
+ inet_sdif(skb), &udp_table, NULL);
+}
+
INDIRECT_CALLABLE_SCOPE
struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb)
{
struct udphdr *uh = udp_gro_udphdr(skb);
+ struct sock *sk = NULL;
struct sk_buff *pp;
- struct sock *sk;
if (unlikely(!uh))
goto flush;
@@ -523,7 +533,10 @@
skip:
NAPI_GRO_CB(skb)->is_ipv6 = 0;
rcu_read_lock();
- sk = static_branch_unlikely(&udp_encap_needed_key) ? udp4_lib_lookup_skb(skb, uh->source, uh->dest) : NULL;
+
+ if (static_branch_unlikely(&udp_encap_needed_key))
+ sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest);
+
pp = udp_gro_receive(head, skb, uh, sk);
rcu_read_unlock();
return pp;
diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c
index dc19aff..fb0648e 100644
--- a/net/ipv4/xfrm4_tunnel.c
+++ b/net/ipv4/xfrm4_tunnel.c
@@ -64,14 +64,14 @@
static struct xfrm_tunnel xfrm_tunnel_handler __read_mostly = {
.handler = xfrm_tunnel_rcv,
.err_handler = xfrm_tunnel_err,
- .priority = 3,
+ .priority = 4,
};
#if IS_ENABLED(CONFIG_IPV6)
static struct xfrm_tunnel xfrm64_tunnel_handler __read_mostly = {
.handler = xfrm_tunnel_rcv,
.err_handler = xfrm_tunnel_err,
- .priority = 2,
+ .priority = 3,
};
#endif
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 01146b6..8b6eb38 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5022,8 +5022,10 @@
return -EMSGSIZE;
if (args->netnsid >= 0 &&
- nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid))
+ nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) {
+ nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
+ }
put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex);
if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 ||
@@ -5054,8 +5056,10 @@
return -EMSGSIZE;
if (args->netnsid >= 0 &&
- nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid))
+ nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) {
+ nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
+ }
put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex);
if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 ||
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index d88d976..440080d 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -588,7 +588,8 @@
memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len);
memset(ah->auth_data, 0, ahp->icv_trunc_len);
- if (ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN))
+ err = ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN);
+ if (err)
goto out_free;
ip6h->priority = 0;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index ec448b7..8956144 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -158,7 +158,13 @@
tp = skb_header_pointer(skb,
ptr+offsetof(struct icmp6hdr, icmp6_type),
sizeof(_type), &_type);
- if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
+
+ /* Based on RFC 8200, Section 4.5 Fragment Header, return
+ * false if this is a fragment packet with no icmp header info.
+ */
+ if (!tp && frag_off != 0)
+ return false;
+ else if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
return true;
}
return false;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a0217e5..648db3f 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1271,6 +1271,8 @@
if (max_headroom > dev->needed_headroom)
dev->needed_headroom = max_headroom;
+ skb_set_inner_ipproto(skb, proto);
+
err = ip6_tnl_encap(skb, t, &proto, fl6);
if (err)
return err;
@@ -1280,8 +1282,6 @@
ipv6_push_frag_opts(skb, &opt.ops, &proto);
}
- skb_set_inner_ipproto(skb, proto);
-
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
ipv6h = ipv6_hdr(skb);
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 27f29b9..7671747 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -81,6 +81,7 @@
static int pndisc_constructor(struct pneigh_entry *n);
static void pndisc_destructor(struct pneigh_entry *n);
static void pndisc_redo(struct sk_buff *skb);
+static int ndisc_is_multicast(const void *pkey);
static const struct neigh_ops ndisc_generic_ops = {
.family = AF_INET6,
@@ -115,6 +116,7 @@
.pconstructor = pndisc_constructor,
.pdestructor = pndisc_destructor,
.proxy_redo = pndisc_redo,
+ .is_multicast = ndisc_is_multicast,
.allow_add = ndisc_allow_add,
.id = "ndisc_cache",
.parms = {
@@ -1706,6 +1708,11 @@
kfree_skb(skb);
}
+static int ndisc_is_multicast(const void *pkey)
+{
+ return ipv6_addr_is_multicast((struct in6_addr *)pkey);
+}
+
static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb)
{
struct inet6_dev *idev = __in6_dev_get(skb->dev);
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 6d0e942..ab9a279 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -20,10 +20,10 @@
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#include "../bridge/br_private.h"
-int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
+int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff *skb)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
- struct sock *sk = sk_to_full_sk(skb->sk);
+ struct sock *sk = sk_to_full_sk(sk_partial);
unsigned int hh_len;
struct dst_entry *dst;
int strict = (ipv6_addr_type(&iph->daddr) &
@@ -84,7 +84,7 @@
if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
!ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
skb->mark != rt_info->mark)
- return ip6_route_me_harder(entry->state.net, skb);
+ return ip6_route_me_harder(entry->state.net, entry->state.sk, skb);
}
return 0;
}
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index 1a27486..cee7480 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -57,7 +57,7 @@
skb->mark != mark ||
ipv6_hdr(skb)->hop_limit != hop_limit ||
flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
- err = ip6_route_me_harder(state->net, skb);
+ err = ip6_route_me_harder(state->net, state->sk, skb);
if (err < 0)
ret = NF_DROP_ERR(err);
}
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 054d287..c129ad3 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -440,6 +440,7 @@
int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
{
u16 savethdr = skb->transport_header;
+ u8 nexthdr = NEXTHDR_FRAGMENT;
int fhoff, nhoff, ret;
struct frag_hdr *fhdr;
struct frag_queue *fq;
@@ -455,6 +456,14 @@
if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0)
return 0;
+ /* Discard the first fragment if it does not include all headers
+ * RFC 8200, Section 4.5
+ */
+ if (ipv6frag_thdr_truncated(skb, fhoff, &nexthdr)) {
+ pr_debug("Drop incomplete fragment\n");
+ return 0;
+ }
+
if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr)))
return -ENOMEM;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 1f5d4d1..47a0dc4 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -42,6 +42,8 @@
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/export.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
#include <net/sock.h>
#include <net/snmp.h>
@@ -322,6 +324,7 @@
struct frag_queue *fq;
const struct ipv6hdr *hdr = ipv6_hdr(skb);
struct net *net = dev_net(skb_dst(skb)->dev);
+ u8 nexthdr;
int iif;
if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
@@ -351,6 +354,20 @@
return 1;
}
+ /* RFC 8200, Section 4.5 Fragment Header:
+ * If the first fragment does not include all headers through an
+ * Upper-Layer header, then that fragment should be discarded and
+ * an ICMP Parameter Problem, Code 3, message should be sent to
+ * the source of the fragment, with the Pointer field set to zero.
+ */
+ nexthdr = hdr->nexthdr;
+ if (ipv6frag_thdr_truncated(skb, skb_transport_offset(skb), &nexthdr)) {
+ __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
+ IPSTATS_MIB_INHDRERRORS);
+ icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0);
+ return -1;
+ }
+
iif = skb->dev ? skb->dev->ifindex : 0;
fq = fq_find(net, fhdr->identification, hdr, iif);
if (fq) {
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 5e2c34c..5e7983c 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1128,7 +1128,6 @@
if (tdev && !netif_is_l3_master(tdev)) {
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
- dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
dev->mtu = tdev->mtu - t_hlen;
if (dev->mtu < IPV6_MIN_MTU)
dev->mtu = IPV6_MIN_MTU;
@@ -1426,7 +1425,6 @@
dev->priv_destructor = ipip6_dev_free;
dev->type = ARPHRD_SIT;
- dev->hard_header_len = LL_MAX_HEADER + t_hlen;
dev->mtu = ETH_DATA_LEN - t_hlen;
dev->min_mtu = IPV6_MIN_MTU;
dev->max_mtu = IP6_MAX_MTU - t_hlen;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index e796a64..9b6cae1 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -136,7 +136,7 @@
__u32 cookie = ntohl(th->ack_seq) - 1;
struct sock *ret = sk;
struct request_sock *req;
- int mss;
+ int full_space, mss;
struct dst_entry *dst;
__u8 rcv_wscale;
u32 tsoff = 0;
@@ -241,7 +241,13 @@
}
req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
- tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
+ /* limit the window selection if the user enforce a smaller rx buffer */
+ full_space = tcp_full_space(sk);
+ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+ (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
+ req->rsk_window_clamp = full_space;
+
+ tcp_select_initial_window(sk, full_space, req->mss,
&req->rsk_rcv_wnd, &req->rsk_window_clamp,
ireq->wscale_ok, &rcv_wscale,
dst_metric(dst, RTAX_INITRWND));
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 584157a..f9e888d 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -111,12 +111,22 @@
return segs;
}
+static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
+ __be16 dport)
+{
+ const struct ipv6hdr *iph = skb_gro_network_header(skb);
+
+ return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
+ &iph->daddr, dport, inet6_iif(skb),
+ inet6_sdif(skb), &udp_table, NULL);
+}
+
INDIRECT_CALLABLE_SCOPE
struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb)
{
struct udphdr *uh = udp_gro_udphdr(skb);
+ struct sock *sk = NULL;
struct sk_buff *pp;
- struct sock *sk;
if (unlikely(!uh))
goto flush;
@@ -135,7 +145,10 @@
skip:
NAPI_GRO_CB(skb)->is_ipv6 = 1;
rcu_read_lock();
- sk = static_branch_unlikely(&udpv6_encap_needed_key) ? udp6_lib_lookup_skb(skb, uh->source, uh->dest) : NULL;
+
+ if (static_branch_unlikely(&udpv6_encap_needed_key))
+ sk = udp6_gro_lookup_skb(skb, uh->source, uh->dest);
+
pp = udp_gro_receive(head, skb, uh, sk);
rcu_read_unlock();
return pp;
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 25b7ebd..f696d46 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -303,13 +303,13 @@
static struct xfrm6_tunnel xfrm6_tunnel_handler __read_mostly = {
.handler = xfrm6_tunnel_rcv,
.err_handler = xfrm6_tunnel_err,
- .priority = 2,
+ .priority = 3,
};
static struct xfrm6_tunnel xfrm46_tunnel_handler __read_mostly = {
.handler = xfrm6_tunnel_rcv,
.err_handler = xfrm6_tunnel_err,
- .priority = 2,
+ .priority = 3,
};
static int __net_init xfrm6_tunnel_net_init(struct net *net)
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index d805720..047238f 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1434,7 +1434,8 @@
break;
}
- if (how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) {
+ if ((how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) &&
+ sk->sk_state == IUCV_CONNECTED) {
if (iucv->transport == AF_IUCV_TRANS_IUCV) {
txmsg.class = 0;
txmsg.tag = 0;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index f400240..6adfcb9 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -5464,6 +5464,7 @@
struct cfg80211_assoc_request *req)
{
bool is_6ghz = req->bss->channel->band == NL80211_BAND_6GHZ;
+ bool is_5ghz = req->bss->channel->band == NL80211_BAND_5GHZ;
struct ieee80211_local *local = sdata->local;
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
struct ieee80211_bss *bss = (void *)req->bss->priv;
@@ -5616,7 +5617,7 @@
if (vht_ie && vht_ie[1] >= sizeof(struct ieee80211_vht_cap))
memcpy(&assoc_data->ap_vht_cap, vht_ie + 2,
sizeof(struct ieee80211_vht_cap));
- else if (!is_6ghz)
+ else if (is_5ghz)
ifmgd->flags |= IEEE80211_STA_DISABLE_VHT |
IEEE80211_STA_DISABLE_HE;
rcu_read_unlock();
diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c
index 86bc469..b13b1da 100644
--- a/net/mac80211/rc80211_minstrel.c
+++ b/net/mac80211/rc80211_minstrel.c
@@ -274,7 +274,7 @@
success = !!(info->flags & IEEE80211_TX_STAT_ACK);
for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) {
- if (ar[i].idx < 0)
+ if (ar[i].idx < 0 || !ar[i].count)
break;
ndx = rix_to_ndx(mi, ar[i].idx);
@@ -287,12 +287,6 @@
mi->r[ndx].stats.success += success;
}
- if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) && (i >= 0))
- mi->sample_packets++;
-
- if (mi->sample_deferred > 0)
- mi->sample_deferred--;
-
if (time_after(jiffies, mi->last_stats_update +
mp->update_interval / (mp->new_avg ? 2 : 1)))
minstrel_update_stats(mp, mi);
@@ -367,7 +361,7 @@
return;
delta = (mi->total_packets * sampling_ratio / 100) -
- (mi->sample_packets + mi->sample_deferred / 2);
+ mi->sample_packets;
/* delta < 0: no sampling required */
prev_sample = mi->prev_sample;
@@ -376,7 +370,6 @@
return;
if (mi->total_packets >= 10000) {
- mi->sample_deferred = 0;
mi->sample_packets = 0;
mi->total_packets = 0;
} else if (delta > mi->n_rates * 2) {
@@ -401,19 +394,8 @@
* rate sampling method should be used.
* Respect such rates that are not sampled for 20 interations.
*/
- if (mrr_capable &&
- msr->perfect_tx_time > mr->perfect_tx_time &&
- msr->stats.sample_skipped < 20) {
- /* Only use IEEE80211_TX_CTL_RATE_CTRL_PROBE to mark
- * packets that have the sampling rate deferred to the
- * second MRR stage. Increase the sample counter only
- * if the deferred sample rate was actually used.
- * Use the sample_deferred counter to make sure that
- * the sampling is not done in large bursts */
- info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE;
- rate++;
- mi->sample_deferred++;
- } else {
+ if (msr->perfect_tx_time < mr->perfect_tx_time ||
+ msr->stats.sample_skipped >= 20) {
if (!msr->sample_limit)
return;
@@ -433,6 +415,7 @@
rate->idx = mi->r[ndx].rix;
rate->count = minstrel_get_retry_count(&mi->r[ndx], info);
+ info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE;
}
diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h
index dbb43bc..86cd80b 100644
--- a/net/mac80211/rc80211_minstrel.h
+++ b/net/mac80211/rc80211_minstrel.h
@@ -126,7 +126,6 @@
u8 max_prob_rate;
unsigned int total_packets;
unsigned int sample_packets;
- int sample_deferred;
unsigned int sample_row;
unsigned int sample_column;
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index fb4f2b9..ec6973e 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -258,6 +258,24 @@
*/
void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
{
+ /*
+ * If we had used sta_info_pre_move_state() then we might not
+ * have gone through the state transitions down again, so do
+ * it here now (and warn if it's inserted).
+ *
+ * This will clear state such as fast TX/RX that may have been
+ * allocated during state transitions.
+ */
+ while (sta->sta_state > IEEE80211_STA_NONE) {
+ int ret;
+
+ WARN_ON_ONCE(test_sta_flag(sta, WLAN_STA_INSERTED));
+
+ ret = sta_info_move_state(sta, sta->sta_state - 1);
+ if (WARN_ONCE(ret, "sta_info_move_state() returned %d\n", ret))
+ break;
+ }
+
if (sta->rate_ctrl)
rate_control_free_sta(sta);
@@ -687,7 +705,7 @@
out_drop_sta:
local->num_sta--;
synchronize_net();
- __cleanup_single_sta(sta);
+ cleanup_single_sta(sta);
out_err:
mutex_unlock(&local->sta_mtx);
kfree(sinfo);
@@ -706,19 +724,13 @@
err = sta_info_insert_check(sta);
if (err) {
+ sta_info_free(local, sta);
mutex_unlock(&local->sta_mtx);
rcu_read_lock();
- goto out_free;
+ return err;
}
- err = sta_info_insert_finish(sta);
- if (err)
- goto out_free;
-
- return 0;
- out_free:
- sta_info_free(local, sta);
- return err;
+ return sta_info_insert_finish(sta);
}
int sta_info_insert(struct sta_info *sta)
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 00ae81e..7afd076 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -785,7 +785,7 @@
void sta_info_stop(struct ieee80211_local *local);
/**
- * sta_info_flush - flush matching STA entries from the STA table
+ * __sta_info_flush - flush matching STA entries from the STA table
*
* Returns the number of removed STA entries.
*
@@ -794,6 +794,13 @@
*/
int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans);
+/**
+ * sta_info_flush - flush matching STA entries from the STA table
+ *
+ * Returns the number of removed STA entries.
+ *
+ * @sdata: sdata to remove all stations from
+ */
static inline int sta_info_flush(struct ieee80211_sub_if_data *sdata)
{
return __sta_info_flush(sdata, false);
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 6feb451..3485610 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -49,7 +49,8 @@
int ac;
if (info->flags & (IEEE80211_TX_CTL_NO_PS_BUFFER |
- IEEE80211_TX_CTL_AMPDU)) {
+ IEEE80211_TX_CTL_AMPDU |
+ IEEE80211_TX_CTL_HW_80211_ENCAP)) {
ieee80211_free_txskb(&local->hw, skb);
return;
}
@@ -915,15 +916,6 @@
ieee80211_mpsp_trigger_process(
ieee80211_get_qos_ctl(hdr), sta, true, acked);
- if (!acked && test_sta_flag(sta, WLAN_STA_PS_STA)) {
- /*
- * The STA is in power save mode, so assume
- * that this TX packet failed because of that.
- */
- ieee80211_handle_filtered_frame(local, sta, skb);
- return;
- }
-
if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL) &&
(ieee80211_is_data(hdr->frame_control)) &&
(rates_idx != -1))
@@ -1150,6 +1142,12 @@
-info->status.ack_signal);
}
} else if (test_sta_flag(sta, WLAN_STA_PS_STA)) {
+ /*
+ * The STA is in power save mode, so assume
+ * that this TX packet failed because of that.
+ */
+ if (skb)
+ ieee80211_handle_filtered_frame(local, sta, skb);
return;
} else if (noack_success) {
/* nothing to do here, do not account as lost */
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 8ba10a4..56a4d0d 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1942,19 +1942,24 @@
/* device xmit handlers */
+enum ieee80211_encrypt {
+ ENCRYPT_NO,
+ ENCRYPT_MGMT,
+ ENCRYPT_DATA,
+};
+
static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb,
- int head_need, bool may_encrypt)
+ int head_need,
+ enum ieee80211_encrypt encrypt)
{
struct ieee80211_local *local = sdata->local;
- struct ieee80211_hdr *hdr;
bool enc_tailroom;
int tail_need = 0;
- hdr = (struct ieee80211_hdr *) skb->data;
- enc_tailroom = may_encrypt &&
- (sdata->crypto_tx_tailroom_needed_cnt ||
- ieee80211_is_mgmt(hdr->frame_control));
+ enc_tailroom = encrypt == ENCRYPT_MGMT ||
+ (encrypt == ENCRYPT_DATA &&
+ sdata->crypto_tx_tailroom_needed_cnt);
if (enc_tailroom) {
tail_need = IEEE80211_ENCRYPT_TAILROOM;
@@ -1985,23 +1990,29 @@
{
struct ieee80211_local *local = sdata->local;
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
- struct ieee80211_hdr *hdr;
+ struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
int headroom;
- bool may_encrypt;
+ enum ieee80211_encrypt encrypt;
- may_encrypt = !(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT);
+ if (info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT)
+ encrypt = ENCRYPT_NO;
+ else if (ieee80211_is_mgmt(hdr->frame_control))
+ encrypt = ENCRYPT_MGMT;
+ else
+ encrypt = ENCRYPT_DATA;
headroom = local->tx_headroom;
- if (may_encrypt)
+ if (encrypt != ENCRYPT_NO)
headroom += sdata->encrypt_headroom;
headroom -= skb_headroom(skb);
headroom = max_t(int, 0, headroom);
- if (ieee80211_skb_resize(sdata, skb, headroom, may_encrypt)) {
+ if (ieee80211_skb_resize(sdata, skb, headroom, encrypt)) {
ieee80211_free_txskb(&local->hw, skb);
return;
}
+ /* reload after potential resize */
hdr = (struct ieee80211_hdr *) skb->data;
info->control.vif = &sdata->vif;
@@ -2828,7 +2839,7 @@
head_need += sdata->encrypt_headroom;
head_need += local->tx_headroom;
head_need = max_t(int, 0, head_need);
- if (ieee80211_skb_resize(sdata, skb, head_need, true)) {
+ if (ieee80211_skb_resize(sdata, skb, head_need, ENCRYPT_DATA)) {
ieee80211_free_txskb(&local->hw, skb);
skb = NULL;
return ERR_PTR(-ENOMEM);
@@ -3502,7 +3513,7 @@
if (unlikely(ieee80211_skb_resize(sdata, skb,
max_t(int, extra_head + hw_headroom -
skb_headroom(skb), 0),
- false))) {
+ ENCRYPT_NO))) {
kfree_skb(skb);
return true;
}
@@ -3619,13 +3630,14 @@
tx.skb = skb;
tx.sdata = vif_to_sdata(info->control.vif);
- if (txq->sta && !(info->flags & IEEE80211_TX_CTL_INJECTED)) {
+ if (txq->sta) {
tx.sta = container_of(txq->sta, struct sta_info, sta);
/*
* Drop unicast frames to unauthorised stations unless they are
- * EAPOL frames from the local station.
+ * injected frames or EAPOL frames from the local station.
*/
- if (unlikely(ieee80211_is_data(hdr->frame_control) &&
+ if (unlikely(!(info->flags & IEEE80211_TX_CTL_INJECTED) &&
+ ieee80211_is_data(hdr->frame_control) &&
!ieee80211_vif_is_mesh(&tx.sdata->vif) &&
tx.sdata->vif.type != NL80211_IFTYPE_OCB &&
!is_multicast_ether_addr(hdr->addr1) &&
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 185dacb3..88f2a7a 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -274,6 +274,15 @@
skb_ext_reset(skb);
skb_orphan(skb);
+ /* try to fetch required memory from subflow */
+ if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
+ if (ssk->sk_forward_alloc < skb->truesize)
+ goto drop;
+ __sk_mem_reclaim(ssk, skb->truesize);
+ if (!sk_rmem_schedule(sk, skb, skb->truesize))
+ goto drop;
+ }
+
/* the skb map_seq accounts for the skb offset:
* mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq
* value
@@ -301,6 +310,7 @@
* will retransmit as needed, if needed.
*/
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
+drop:
mptcp_drop(sk, skb);
return false;
}
@@ -2457,6 +2467,7 @@
.memory_pressure = &tcp_memory_pressure,
.stream_memory_free = mptcp_memory_free,
.sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem),
+ .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem),
.sysctl_mem = sysctl_tcp_mem,
.obj_size = sizeof(struct mptcp_sock),
.slab_flags = SLAB_TYPESAFE_BY_RCU,
diff --git a/net/mptcp/token.c b/net/mptcp/token.c
index 8b47c4b..feb4b9f 100644
--- a/net/mptcp/token.c
+++ b/net/mptcp/token.c
@@ -291,7 +291,7 @@
{
struct mptcp_sock *ret = NULL;
struct hlist_nulls_node *pos;
- int slot, num;
+ int slot, num = 0;
for (slot = *s_slot; slot <= token_mask; *s_num = 0, slot++) {
struct token_bucket *bucket = &token_hash[slot];
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index f1be3e3..a9cb355 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -1726,9 +1726,6 @@
ndp->ptype.dev = dev;
dev_add_pack(&ndp->ptype);
- /* Set up generic netlink interface */
- ncsi_init_netlink(dev);
-
pdev = to_platform_device(dev->dev.parent);
if (pdev) {
np = pdev->dev.of_node;
@@ -1892,8 +1889,6 @@
list_del_rcu(&ndp->node);
spin_unlock_irqrestore(&ncsi_dev_lock, flags);
- ncsi_unregister_netlink(nd->dev);
-
kfree(ndp);
}
EXPORT_SYMBOL_GPL(ncsi_unregister_dev);
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index adddc77..bb5f165 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -766,24 +766,8 @@
.n_small_ops = ARRAY_SIZE(ncsi_ops),
};
-int ncsi_init_netlink(struct net_device *dev)
+static int __init ncsi_init_netlink(void)
{
- int rc;
-
- rc = genl_register_family(&ncsi_genl_family);
- if (rc)
- netdev_err(dev, "ncsi: failed to register netlink family\n");
-
- return rc;
+ return genl_register_family(&ncsi_genl_family);
}
-
-int ncsi_unregister_netlink(struct net_device *dev)
-{
- int rc;
-
- rc = genl_unregister_family(&ncsi_genl_family);
- if (rc)
- netdev_err(dev, "ncsi: failed to unregister netlink family\n");
-
- return rc;
-}
+subsys_initcall(ncsi_init_netlink);
diff --git a/net/ncsi/ncsi-netlink.h b/net/ncsi/ncsi-netlink.h
index 7502723..39a1a9d 100644
--- a/net/ncsi/ncsi-netlink.h
+++ b/net/ncsi/ncsi-netlink.h
@@ -22,7 +22,4 @@
struct nlmsghdr *nlhdr,
int err);
-int ncsi_init_netlink(struct net_device *dev);
-int ncsi_unregister_netlink(struct net_device *dev);
-
#endif /* __NCSI_NETLINK_H__ */
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 6f35832..7cff6e5 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -637,13 +637,14 @@
if (SET_WITH_COUNTER(set)) {
struct ip_set_counter *counter = ext_counter(data, set);
+ ip_set_update_counter(counter, ext, flags);
+
if (flags & IPSET_FLAG_MATCH_COUNTERS &&
!(ip_set_match_counter(ip_set_get_packets(counter),
mext->packets, mext->packets_op) &&
ip_set_match_counter(ip_set_get_bytes(counter),
mext->bytes, mext->bytes_op)))
return false;
- ip_set_update_counter(counter, ext, flags);
}
if (SET_WITH_SKBINFO(set))
ip_set_get_skbinfo(ext_skbinfo(data, set),
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index cc3c275..c0b8215 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -742,12 +742,12 @@
struct dst_entry *dst = skb_dst(skb);
if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) &&
- ip6_route_me_harder(ipvs->net, skb) != 0)
+ ip6_route_me_harder(ipvs->net, skb->sk, skb) != 0)
return 1;
} else
#endif
if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
- ip_route_me_harder(ipvs->net, skb, RTN_LOCAL) != 0)
+ ip_route_me_harder(ipvs->net, skb->sk, skb, RTN_LOCAL) != 0)
return 1;
return 0;
diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c
index 59151dc..e87b6bd 100644
--- a/net/netfilter/nf_nat_proto.c
+++ b/net/netfilter/nf_nat_proto.c
@@ -715,7 +715,7 @@
if (ct->tuplehash[dir].tuple.dst.u3.ip !=
ct->tuplehash[!dir].tuple.src.u3.ip) {
- err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+ err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
if (err < 0)
ret = NF_DROP_ERR(err);
}
@@ -953,7 +953,7 @@
if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
&ct->tuplehash[!dir].tuple.src.u3)) {
- err = nf_ip6_route_me_harder(state->net, skb);
+ err = nf_ip6_route_me_harder(state->net, state->sk, skb);
if (err < 0)
ret = NF_DROP_ERR(err);
}
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 9cca35d2..d7d34a6 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -446,7 +446,7 @@
skb_dst_set_noref(nskb, skb_dst(skb));
nskb->protocol = htons(ETH_P_IP);
- if (ip_route_me_harder(net, nskb, RTN_UNSPEC))
+ if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC))
goto free_nskb;
if (nfct) {
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 65cb8e3..0f58e98 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -7137,7 +7137,7 @@
GFP_KERNEL);
kfree(buf);
- if (ctx->report &&
+ if (!ctx->report &&
!nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
return;
@@ -7259,7 +7259,7 @@
audit_log_nfcfg("?:0;?:0", 0, net->nft.base_seq,
AUDIT_NFT_OP_GEN_REGISTER, GFP_KERNEL);
- if (nlmsg_report(nlh) &&
+ if (!nlmsg_report(nlh) &&
!nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
return;
@@ -8053,12 +8053,16 @@
kfree(trans);
}
-static int __nf_tables_abort(struct net *net, bool autoload)
+static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
{
struct nft_trans *trans, *next;
struct nft_trans_elem *te;
struct nft_hook *hook;
+ if (action == NFNL_ABORT_VALIDATE &&
+ nf_tables_validate(net) < 0)
+ return -EAGAIN;
+
list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list,
list) {
switch (trans->msg_type) {
@@ -8190,7 +8194,7 @@
nf_tables_abort_release(trans);
}
- if (autoload)
+ if (action == NFNL_ABORT_AUTOLOAD)
nf_tables_module_autoload(net);
else
nf_tables_module_autoload_cleanup(net);
@@ -8203,9 +8207,10 @@
nft_validate_state_update(net, NFT_VALIDATE_SKIP);
}
-static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload)
+static int nf_tables_abort(struct net *net, struct sk_buff *skb,
+ enum nfnl_abort_action action)
{
- int ret = __nf_tables_abort(net, autoload);
+ int ret = __nf_tables_abort(net, action);
mutex_unlock(&net->nft.commit_mutex);
@@ -8836,7 +8841,7 @@
{
mutex_lock(&net->nft.commit_mutex);
if (!list_empty(&net->nft.commit_list))
- __nf_tables_abort(net, false);
+ __nf_tables_abort(net, NFNL_ABORT_NONE);
__nft_release_tables(net);
mutex_unlock(&net->nft.commit_mutex);
WARN_ON_ONCE(!list_empty(&net->nft.tables));
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 2daa1f6..d3df66a 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -333,7 +333,7 @@
return netlink_ack(skb, nlh, -EINVAL, NULL);
replay:
status = 0;
-
+replay_abort:
skb = netlink_skb_clone(oskb, GFP_KERNEL);
if (!skb)
return netlink_ack(oskb, nlh, -ENOMEM, NULL);
@@ -499,7 +499,7 @@
}
done:
if (status & NFNL_BATCH_REPLAY) {
- ss->abort(net, oskb, true);
+ ss->abort(net, oskb, NFNL_ABORT_AUTOLOAD);
nfnl_err_reset(&err_list);
kfree_skb(skb);
module_put(ss->owner);
@@ -510,11 +510,25 @@
status |= NFNL_BATCH_REPLAY;
goto done;
} else if (err) {
- ss->abort(net, oskb, false);
+ ss->abort(net, oskb, NFNL_ABORT_NONE);
netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL);
}
} else {
- ss->abort(net, oskb, false);
+ enum nfnl_abort_action abort_action;
+
+ if (status & NFNL_BATCH_FAILURE)
+ abort_action = NFNL_ABORT_NONE;
+ else
+ abort_action = NFNL_ABORT_VALIDATE;
+
+ err = ss->abort(net, oskb, abort_action);
+ if (err == -EAGAIN) {
+ nfnl_err_reset(&err_list);
+ kfree_skb(skb);
+ module_put(ss->owner);
+ status |= NFNL_BATCH_FAILURE;
+ goto replay_abort;
+ }
}
if (ss->cleanup)
ss->cleanup(net);
diff --git a/net/netfilter/nft_chain_route.c b/net/netfilter/nft_chain_route.c
index 8826bbe..edd02cd 100644
--- a/net/netfilter/nft_chain_route.c
+++ b/net/netfilter/nft_chain_route.c
@@ -42,7 +42,7 @@
iph->daddr != daddr ||
skb->mark != mark ||
iph->tos != tos) {
- err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+ err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
if (err < 0)
ret = NF_DROP_ERR(err);
}
@@ -92,7 +92,7 @@
skb->mark != mark ||
ipv6_hdr(skb)->hop_limit != hop_limit ||
flowlabel != *((u32 *)ipv6_hdr(skb)))) {
- err = nf_ip6_route_me_harder(state->net, skb);
+ err = nf_ip6_route_me_harder(state->net, state->sk, skb);
if (err < 0)
ret = NF_DROP_ERR(err);
}
diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c
index cedf47a..2182d36 100644
--- a/net/netfilter/utils.c
+++ b/net/netfilter/utils.c
@@ -191,8 +191,8 @@
skb->mark == rt_info->mark &&
iph->daddr == rt_info->daddr &&
iph->saddr == rt_info->saddr))
- return ip_route_me_harder(entry->state.net, skb,
- RTN_UNSPEC);
+ return ip_route_me_harder(entry->state.net, entry->state.sk,
+ skb, RTN_UNSPEC);
}
#endif
return 0;
diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c
index 2e8e3f7..ccb4916 100644
--- a/net/netlabel/netlabel_unlabeled.c
+++ b/net/netlabel/netlabel_unlabeled.c
@@ -1166,12 +1166,13 @@
struct netlbl_unlhsh_walk_arg cb_arg;
u32 skip_bkt = cb->args[0];
u32 skip_chain = cb->args[1];
- u32 iter_bkt;
- u32 iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0;
+ u32 skip_addr4 = cb->args[2];
+ u32 iter_bkt, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0;
struct netlbl_unlhsh_iface *iface;
struct list_head *iter_list;
struct netlbl_af4list *addr4;
#if IS_ENABLED(CONFIG_IPV6)
+ u32 skip_addr6 = cb->args[3];
struct netlbl_af6list *addr6;
#endif
@@ -1182,7 +1183,7 @@
rcu_read_lock();
for (iter_bkt = skip_bkt;
iter_bkt < rcu_dereference(netlbl_unlhsh)->size;
- iter_bkt++, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0) {
+ iter_bkt++) {
iter_list = &rcu_dereference(netlbl_unlhsh)->tbl[iter_bkt];
list_for_each_entry_rcu(iface, iter_list, list) {
if (!iface->valid ||
@@ -1190,7 +1191,7 @@
continue;
netlbl_af4list_foreach_rcu(addr4,
&iface->addr4_list) {
- if (iter_addr4++ < cb->args[2])
+ if (iter_addr4++ < skip_addr4)
continue;
if (netlbl_unlabel_staticlist_gen(
NLBL_UNLABEL_C_STATICLIST,
@@ -1203,10 +1204,12 @@
goto unlabel_staticlist_return;
}
}
+ iter_addr4 = 0;
+ skip_addr4 = 0;
#if IS_ENABLED(CONFIG_IPV6)
netlbl_af6list_foreach_rcu(addr6,
&iface->addr6_list) {
- if (iter_addr6++ < cb->args[3])
+ if (iter_addr6++ < skip_addr6)
continue;
if (netlbl_unlabel_staticlist_gen(
NLBL_UNLABEL_C_STATICLIST,
@@ -1219,8 +1222,12 @@
goto unlabel_staticlist_return;
}
}
+ iter_addr6 = 0;
+ skip_addr6 = 0;
#endif /* IPv6 */
}
+ iter_chain = 0;
+ skip_chain = 0;
}
unlabel_staticlist_return:
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 832f898..9d6ef6c 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1703,13 +1703,13 @@
parms.port_no = OVSP_LOCAL;
parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID];
- err = ovs_dp_change(dp, a);
- if (err)
- goto err_destroy_meters;
-
/* So far only local changes have been made, now need the lock. */
ovs_lock();
+ err = ovs_dp_change(dp, a);
+ if (err)
+ goto err_unlock_and_destroy_meters;
+
vport = new_vport(&parms);
if (IS_ERR(vport)) {
err = PTR_ERR(vport);
@@ -1725,8 +1725,7 @@
ovs_dp_reset_user_features(skb, info);
}
- ovs_unlock();
- goto err_destroy_meters;
+ goto err_unlock_and_destroy_meters;
}
err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
@@ -1741,7 +1740,8 @@
ovs_notify(&dp_datapath_genl_family, reply, info);
return 0;
-err_destroy_meters:
+err_unlock_and_destroy_meters:
+ ovs_unlock();
ovs_meters_exit(dp);
err_destroy_ports:
kfree(dp->ports);
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index f3486a3..c89c8da 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -390,7 +390,7 @@
}
int ovs_flow_tbl_masks_cache_resize(struct flow_table *table, u32 size)
{
- struct mask_cache *mc = rcu_dereference(table->mask_cache);
+ struct mask_cache *mc = rcu_dereference_ovsl(table->mask_cache);
struct mask_cache *new;
if (size == mc->cache_size)
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 06603dd..b36b606 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -956,9 +956,10 @@
rds_ib_cm_fill_conn_param(conn, &conn_param, &dp,
conn->c_proposed_version,
UINT_MAX, UINT_MAX, isv6);
- ret = rdma_connect(cm_id, &conn_param);
+ ret = rdma_connect_locked(cm_id, &conn_param);
if (ret)
- rds_ib_conn_error(conn, "rdma_connect failed (%d)\n", ret);
+ rds_ib_conn_error(conn, "rdma_connect_locked failed (%d)\n",
+ ret);
out:
/* Beware - returning non-zero tells the rdma_cm to destroy
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index 971c73c..97101c5 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -876,6 +876,9 @@
rfkill->suspended = false;
+ if (!rfkill->registered)
+ return 0;
+
if (!rfkill->persistent) {
cur = !!(rfkill->state & RFKILL_BLOCK_SW);
rfkill_set_block(rfkill, cur);
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index f40bf97..5c7456e 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -426,6 +426,7 @@
module_init(mpls_init_module);
module_exit(mpls_cleanup_module);
+MODULE_SOFTDEP("post: mpls_gso");
MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("MPLS manipulation actions");
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index faeabff..838b3fd 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -652,12 +652,12 @@
block_cb->indr.binder_type,
&block->flow_block, tcf_block_shared(block),
&extack);
+ rtnl_lock();
down_write(&block->cb_lock);
list_del(&block_cb->driver_list);
list_move(&block_cb->list, &bo.cb_list);
- up_write(&block->cb_lock);
- rtnl_lock();
tcf_block_unbind(block, &bo);
+ up_write(&block->cb_lock);
rtnl_unlock();
}
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 84f8277..0c345e4 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -330,7 +330,7 @@
/* default uniform distribution */
if (dist == NULL)
- return ((rnd % (2 * sigma)) + mu) - sigma;
+ return ((rnd % (2 * (u32)sigma)) + mu) - sigma;
t = dist->table[rnd % dist->size];
x = (sigma % NETEM_DIST_SCALE) * t;
@@ -812,6 +812,10 @@
q->slot_config.max_packets = INT_MAX;
if (q->slot_config.max_bytes == 0)
q->slot_config.max_bytes = INT_MAX;
+
+ /* capping dist_jitter to the range acceptable by tabledist() */
+ q->slot_config.dist_jitter = min_t(__s64, INT_MAX, abs(q->slot_config.dist_jitter));
+
q->slot.packets_left = q->slot_config.max_packets;
q->slot.bytes_left = q->slot_config.max_bytes;
if (q->slot_config.min_delay | q->slot_config.max_delay |
@@ -1037,6 +1041,9 @@
if (tb[TCA_NETEM_SLOT])
get_slot(q, tb[TCA_NETEM_SLOT]);
+ /* capping jitter to the range acceptable by tabledist() */
+ q->jitter = min_t(s64, abs(q->jitter), INT_MAX);
+
return ret;
get_table_failure:
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 55d4fc6..d508f6f 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -449,7 +449,7 @@
else {
if (!mod_timer(&t->proto_unreach_timer,
jiffies + (HZ/20)))
- sctp_association_hold(asoc);
+ sctp_transport_hold(t);
}
} else {
struct net *net = sock_net(sk);
@@ -458,7 +458,7 @@
"encountered!\n", __func__);
if (del_timer(&t->proto_unreach_timer))
- sctp_association_put(asoc);
+ sctp_transport_put(t);
sctp_do_sm(net, SCTP_EVENT_T_OTHER,
SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH),
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index aa821e7..0948f14 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -419,7 +419,7 @@
/* Try again later. */
if (!mod_timer(&transport->proto_unreach_timer,
jiffies + (HZ/20)))
- sctp_association_hold(asoc);
+ sctp_transport_hold(transport);
goto out_unlock;
}
@@ -435,7 +435,7 @@
out_unlock:
bh_unlock_sock(sk);
- sctp_association_put(asoc);
+ sctp_transport_put(transport);
}
/* Handle the timeout of the RE-CONFIG timer. */
@@ -1601,12 +1601,12 @@
break;
case SCTP_CMD_INIT_FAILED:
- sctp_cmd_init_failed(commands, asoc, cmd->obj.u32);
+ sctp_cmd_init_failed(commands, asoc, cmd->obj.u16);
break;
case SCTP_CMD_ASSOC_FAILED:
sctp_cmd_assoc_failed(commands, asoc, event_type,
- subtype, chunk, cmd->obj.u32);
+ subtype, chunk, cmd->obj.u16);
break;
case SCTP_CMD_INIT_COUNTER_INC:
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 806af58..60fcf31 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -133,7 +133,7 @@
/* Delete the ICMP proto unreachable timer if it's active. */
if (del_timer(&transport->proto_unreach_timer))
- sctp_association_put(transport->asoc);
+ sctp_transport_put(transport);
sctp_transport_put(transport);
}
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 82be0bd..5dd4faa 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -979,7 +979,8 @@
/* check if smc modes and versions of CLC proposal and accept match */
rc = smc_connect_check_aclc(ini, aclc);
- version = aclc->hdr.version == SMC_V1 ? SMC_V1 : version;
+ version = aclc->hdr.version == SMC_V1 ? SMC_V1 : SMC_V2;
+ ini->smcd_version = version;
if (rc)
goto vlan_cleanup;
@@ -1317,10 +1318,10 @@
/* listen worker: decline and fall back if possible */
static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
- struct smc_init_info *ini, u8 version)
+ int local_first, u8 version)
{
/* RDMA setup failed, switch back to TCP */
- if (ini->first_contact_local)
+ if (local_first)
smc_lgr_cleanup_early(&new_smc->conn);
else
smc_conn_free(&new_smc->conn);
@@ -1768,7 +1769,8 @@
out_unlock:
mutex_unlock(&smc_server_lgr_pending);
out_decl:
- smc_listen_decline(new_smc, rc, ini, version);
+ smc_listen_decline(new_smc, rc, ini ? ini->first_contact_local : 0,
+ version);
out_free:
kfree(ini);
kfree(buf);
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index b3f46ab..c579d1d 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -124,7 +124,7 @@
struct smc_clnt_opts_area_hdr hdr;
u8 roce[16]; /* RoCEv2 GID */
u8 reserved[16];
- u8 user_eids[0][SMC_MAX_EID_LEN];
+ u8 user_eids[][SMC_MAX_EID_LEN];
};
struct smc_clc_msg_proposal_prefix { /* prefix part of clc proposal message*/
@@ -143,7 +143,7 @@
struct smc_clc_smcd_v2_extension {
u8 system_eid[SMC_MAX_EID_LEN];
u8 reserved[16];
- struct smc_clc_smcd_gid_chid gidchid[0];
+ struct smc_clc_smcd_gid_chid gidchid[];
};
struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index d790c43..af96f81 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1309,7 +1309,8 @@
ini->ism_peer_gid[ini->ism_selected]) :
smcr_lgr_match(lgr, ini->ib_lcl, role, ini->ib_clcqpn)) &&
!lgr->sync_err &&
- lgr->vlan_id == ini->vlan_id &&
+ (ini->smcd_version == SMC_V2 ||
+ lgr->vlan_id == ini->vlan_id) &&
(role == SMC_CLNT || ini->is_smcd ||
lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) {
/* link group found */
@@ -1615,8 +1616,11 @@
rc = smc_ism_register_dmb(lgr, bufsize, buf_desc);
if (rc) {
kfree(buf_desc);
- return (rc == -ENOMEM) ? ERR_PTR(-EAGAIN) :
- ERR_PTR(-EIO);
+ if (rc == -ENOMEM)
+ return ERR_PTR(-EAGAIN);
+ if (rc == -ENOSPC)
+ return ERR_PTR(-ENOSPC);
+ return ERR_PTR(-EIO);
}
buf_desc->pages = virt_to_page(buf_desc->cpu_addr);
/* CDC header stored in buf. So, pretend it was smaller */
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 1c314db..fc766b5 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -198,9 +198,9 @@
rcu_read_lock();
ndev = rdma_read_gid_attr_ndev_rcu(attr);
if (!IS_ERR(ndev) &&
- ((!vlan_id && !is_vlan_dev(attr->ndev)) ||
- (vlan_id && is_vlan_dev(attr->ndev) &&
- vlan_dev_vlan_id(attr->ndev) == vlan_id)) &&
+ ((!vlan_id && !is_vlan_dev(ndev)) ||
+ (vlan_id && is_vlan_dev(ndev) &&
+ vlan_dev_vlan_id(ndev) == vlan_id)) &&
attr->gid_type == IB_GID_TYPE_ROCE) {
rcu_read_unlock();
if (gid)
diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c
index a18b36b..3aad6ef 100644
--- a/net/sunrpc/sysctl.c
+++ b/net/sunrpc/sysctl.c
@@ -63,19 +63,20 @@
void *buffer, size_t *lenp, loff_t *ppos)
{
char tmpbuf[256];
- size_t len;
+ ssize_t len;
- if ((*ppos && !write) || !*lenp) {
+ if (write || *ppos) {
*lenp = 0;
return 0;
}
len = svc_print_xprts(tmpbuf, sizeof(tmpbuf));
- *lenp = memory_read_from_buffer(buffer, *lenp, ppos, tmpbuf, len);
+ len = memory_read_from_buffer(buffer, *lenp, ppos, tmpbuf, len);
- if (*lenp < 0) {
+ if (len < 0) {
*lenp = 0;
return -EINVAL;
}
+ *lenp = len;
return 0;
}
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 2a78aa7..32c79c5 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -150,12 +150,11 @@
if (fragid == FIRST_FRAGMENT) {
if (unlikely(head))
goto err;
- if (skb_cloned(frag))
- frag = skb_copy(frag, GFP_ATOMIC);
+ *buf = NULL;
+ frag = skb_unshare(frag, GFP_ATOMIC);
if (unlikely(!frag))
goto err;
head = *headbuf = frag;
- *buf = NULL;
TIPC_SKB_CB(head)->tail = NULL;
if (skb_is_nonlinear(head)) {
skb_walk_frags(head, tail) {
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index 5f6f860..13f3143 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -664,12 +664,18 @@
ret = tipc_topsrv_work_start(srv);
if (ret < 0)
- return ret;
+ goto err_start;
ret = tipc_topsrv_create_listener(srv);
if (ret < 0)
- tipc_topsrv_work_stop(srv);
+ goto err_create;
+ return 0;
+
+err_create:
+ tipc_topsrv_work_stop(srv);
+err_start:
+ kfree(srv);
return ret;
}
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index cec8622..54d3e161 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -694,36 +694,51 @@
static bool
tls_device_rx_resync_async(struct tls_offload_resync_async *resync_async,
- s64 resync_req, u32 *seq)
+ s64 resync_req, u32 *seq, u16 *rcd_delta)
{
u32 is_async = resync_req & RESYNC_REQ_ASYNC;
u32 req_seq = resync_req >> 32;
u32 req_end = req_seq + ((resync_req >> 16) & 0xffff);
+ u16 i;
+
+ *rcd_delta = 0;
if (is_async) {
+ /* shouldn't get to wraparound:
+ * too long in async stage, something bad happened
+ */
+ if (WARN_ON_ONCE(resync_async->rcd_delta == USHRT_MAX))
+ return false;
+
/* asynchronous stage: log all headers seq such that
* req_seq <= seq <= end_seq, and wait for real resync request
*/
- if (between(*seq, req_seq, req_end) &&
+ if (before(*seq, req_seq))
+ return false;
+ if (!after(*seq, req_end) &&
resync_async->loglen < TLS_DEVICE_RESYNC_ASYNC_LOGMAX)
resync_async->log[resync_async->loglen++] = *seq;
+ resync_async->rcd_delta++;
+
return false;
}
/* synchronous stage: check against the logged entries and
* proceed to check the next entries if no match was found
*/
- while (resync_async->loglen) {
- if (req_seq == resync_async->log[resync_async->loglen - 1] &&
- atomic64_try_cmpxchg(&resync_async->req,
- &resync_req, 0)) {
- resync_async->loglen = 0;
+ for (i = 0; i < resync_async->loglen; i++)
+ if (req_seq == resync_async->log[i] &&
+ atomic64_try_cmpxchg(&resync_async->req, &resync_req, 0)) {
+ *rcd_delta = resync_async->rcd_delta - i;
*seq = req_seq;
+ resync_async->loglen = 0;
+ resync_async->rcd_delta = 0;
return true;
}
- resync_async->loglen--;
- }
+
+ resync_async->loglen = 0;
+ resync_async->rcd_delta = 0;
if (req_seq == *seq &&
atomic64_try_cmpxchg(&resync_async->req,
@@ -741,6 +756,7 @@
u32 sock_data, is_req_pending;
struct tls_prot_info *prot;
s64 resync_req;
+ u16 rcd_delta;
u32 req_seq;
if (tls_ctx->rx_conf != TLS_HW)
@@ -786,8 +802,9 @@
return;
if (!tls_device_rx_resync_async(rx_ctx->resync_async,
- resync_req, &seq))
+ resync_req, &seq, &rcd_delta))
return;
+ tls_bigint_subtract(rcd_sn, rcd_delta);
break;
}
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 95ab5545..2fe9e2c 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1913,7 +1913,7 @@
* another message type
*/
msg->msg_flags |= MSG_EOR;
- if (ctx->control != TLS_RECORD_TYPE_DATA)
+ if (control != TLS_RECORD_TYPE_DATA)
goto recv_end;
} else {
break;
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 9e93bc2..d10916a 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -438,7 +438,7 @@
case SOCK_STREAM:
if (vsock_use_local_transport(remote_cid))
new_transport = transport_local;
- else if (remote_cid <= VMADDR_CID_HOST)
+ else if (remote_cid <= VMADDR_CID_HOST || !transport_h2g)
new_transport = transport_g2h;
else
new_transport = transport_h2g;
@@ -739,7 +739,7 @@
vsk->buffer_min_size = psk->buffer_min_size;
vsk->buffer_max_size = psk->buffer_max_size;
} else {
- vsk->trusted = capable(CAP_NET_ADMIN);
+ vsk->trusted = ns_capable_noaudit(&init_user_ns, CAP_NET_ADMIN);
vsk->owner = get_current_cred();
vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT;
vsk->buffer_size = VSOCK_DEFAULT_BUFFER_SIZE;
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 9f23923..240282c 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1250,8 +1250,7 @@
}
EXPORT_SYMBOL(cfg80211_stop_iface);
-void cfg80211_init_wdev(struct cfg80211_registered_device *rdev,
- struct wireless_dev *wdev)
+void cfg80211_init_wdev(struct wireless_dev *wdev)
{
mutex_init(&wdev->mtx);
INIT_LIST_HEAD(&wdev->event_list);
@@ -1262,6 +1261,30 @@
spin_lock_init(&wdev->pmsr_lock);
INIT_WORK(&wdev->pmsr_free_wk, cfg80211_pmsr_free_wk);
+#ifdef CONFIG_CFG80211_WEXT
+ wdev->wext.default_key = -1;
+ wdev->wext.default_mgmt_key = -1;
+ wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC;
+#endif
+
+ if (wdev->wiphy->flags & WIPHY_FLAG_PS_ON_BY_DEFAULT)
+ wdev->ps = true;
+ else
+ wdev->ps = false;
+ /* allow mac80211 to determine the timeout */
+ wdev->ps_timeout = -1;
+
+ if ((wdev->iftype == NL80211_IFTYPE_STATION ||
+ wdev->iftype == NL80211_IFTYPE_P2P_CLIENT ||
+ wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr)
+ wdev->netdev->priv_flags |= IFF_DONT_BRIDGE;
+
+ INIT_WORK(&wdev->disconnect_wk, cfg80211_autodisconnect_wk);
+}
+
+void cfg80211_register_wdev(struct cfg80211_registered_device *rdev,
+ struct wireless_dev *wdev)
+{
/*
* We get here also when the interface changes network namespaces,
* as it's registered into the new one, but we don't want it to
@@ -1295,6 +1318,11 @@
switch (state) {
case NETDEV_POST_INIT:
SET_NETDEV_DEVTYPE(dev, &wiphy_type);
+ wdev->netdev = dev;
+ /* can only change netns with wiphy */
+ dev->features |= NETIF_F_NETNS_LOCAL;
+
+ cfg80211_init_wdev(wdev);
break;
case NETDEV_REGISTER:
/*
@@ -1302,35 +1330,12 @@
* called within code protected by it when interfaces
* are added with nl80211.
*/
- /* can only change netns with wiphy */
- dev->features |= NETIF_F_NETNS_LOCAL;
-
if (sysfs_create_link(&dev->dev.kobj, &rdev->wiphy.dev.kobj,
"phy80211")) {
pr_err("failed to add phy80211 symlink to netdev!\n");
}
- wdev->netdev = dev;
-#ifdef CONFIG_CFG80211_WEXT
- wdev->wext.default_key = -1;
- wdev->wext.default_mgmt_key = -1;
- wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC;
-#endif
- if (wdev->wiphy->flags & WIPHY_FLAG_PS_ON_BY_DEFAULT)
- wdev->ps = true;
- else
- wdev->ps = false;
- /* allow mac80211 to determine the timeout */
- wdev->ps_timeout = -1;
-
- if ((wdev->iftype == NL80211_IFTYPE_STATION ||
- wdev->iftype == NL80211_IFTYPE_P2P_CLIENT ||
- wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr)
- dev->priv_flags |= IFF_DONT_BRIDGE;
-
- INIT_WORK(&wdev->disconnect_wk, cfg80211_autodisconnect_wk);
-
- cfg80211_init_wdev(rdev, wdev);
+ cfg80211_register_wdev(rdev, wdev);
break;
case NETDEV_GOING_DOWN:
cfg80211_leave(rdev, wdev);
diff --git a/net/wireless/core.h b/net/wireless/core.h
index e1ec9ac..e3e9686 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -209,8 +209,9 @@
int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
struct net *net);
-void cfg80211_init_wdev(struct cfg80211_registered_device *rdev,
- struct wireless_dev *wdev);
+void cfg80211_init_wdev(struct wireless_dev *wdev);
+void cfg80211_register_wdev(struct cfg80211_registered_device *rdev,
+ struct wireless_dev *wdev);
static inline void wdev_lock(struct wireless_dev *wdev)
__acquires(wdev)
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 554796a..a77174b 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3885,7 +3885,8 @@
* P2P Device and NAN do not have a netdev, so don't go
* through the netdev notifier and must be added here
*/
- cfg80211_init_wdev(rdev, wdev);
+ cfg80211_init_wdev(wdev);
+ cfg80211_register_wdev(rdev, wdev);
break;
default:
break;
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 3dab859..a04fdfb 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -3616,7 +3616,7 @@
power_rule = ®_rule->power_rule;
if (reg_rule->flags & NL80211_RRF_AUTO_BW)
- snprintf(bw, sizeof(bw), "%d KHz, %d KHz AUTO",
+ snprintf(bw, sizeof(bw), "%d KHz, %u KHz AUTO",
freq_range->max_bandwidth_khz,
reg_get_max_bandwidth(rd, reg_rule));
else
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 0bbb283f..a10487e 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -825,7 +825,7 @@
sock->state = SS_CONNECTED;
rc = 0;
out_put_neigh:
- if (rc) {
+ if (rc && x25->neighbour) {
read_lock_bh(&x25_list_lock);
x25_neigh_put(x25->neighbour);
x25->neighbour = NULL;
@@ -1050,6 +1050,7 @@
makex25->lci = lci;
makex25->dest_addr = dest_addr;
makex25->source_addr = source_addr;
+ x25_neigh_hold(nb);
makex25->neighbour = nb;
makex25->facilities = facilities;
makex25->dte_facilities= dte_facilities;
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index b71a32e..cfbec39 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -1146,7 +1146,8 @@
if (!sock_flag(sk, SOCK_DEAD))
return;
- xp_put_pool(xs->pool);
+ if (!xp_put_pool(xs->pool))
+ xdp_put_umem(xs->umem);
sk_refcnt_debug_dec(sk);
}
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 64c9e55..8a3bf4e 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -251,15 +251,18 @@
refcount_inc(&pool->users);
}
-void xp_put_pool(struct xsk_buff_pool *pool)
+bool xp_put_pool(struct xsk_buff_pool *pool)
{
if (!pool)
- return;
+ return false;
if (refcount_dec_and_test(&pool->users)) {
INIT_WORK(&pool->work, xp_release_deferred);
schedule_work(&pool->work);
+ return true;
}
+
+ return false;
}
static struct xsk_dma_map *xp_find_dma_map(struct xsk_buff_pool *pool)
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index aa4cdcf..9b8e292 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -803,14 +803,14 @@
.handler = xfrmi6_rcv_tunnel,
.cb_handler = xfrmi_rcv_cb,
.err_handler = xfrmi6_err,
- .priority = -1,
+ .priority = 2,
};
static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = {
.handler = xfrmi6_rcv_tunnel,
.cb_handler = xfrmi_rcv_cb,
.err_handler = xfrmi6_err,
- .priority = -1,
+ .priority = 2,
};
#endif
@@ -848,14 +848,14 @@
.handler = xfrmi4_rcv_tunnel,
.cb_handler = xfrmi_rcv_cb,
.err_handler = xfrmi4_err,
- .priority = -1,
+ .priority = 3,
};
static struct xfrm_tunnel xfrmi_ipip6_handler __read_mostly = {
.handler = xfrmi4_rcv_tunnel,
.cb_handler = xfrmi_rcv_cb,
.err_handler = xfrmi4_err,
- .priority = -1,
+ .priority = 2,
};
#endif
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index bbd4643..a77da7a 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2004,6 +2004,7 @@
int err = -ENOENT;
__be32 minspi = htonl(low);
__be32 maxspi = htonl(high);
+ __be32 newspi = 0;
u32 mark = x->mark.v & x->mark.m;
spin_lock_bh(&x->lock);
@@ -2022,21 +2023,22 @@
xfrm_state_put(x0);
goto unlock;
}
- x->id.spi = minspi;
+ newspi = minspi;
} else {
u32 spi = 0;
for (h = 0; h < high-low+1; h++) {
spi = low + prandom_u32()%(high-low+1);
x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
if (x0 == NULL) {
- x->id.spi = htonl(spi);
+ newspi = htonl(spi);
break;
}
xfrm_state_put(x0);
}
}
- if (x->id.spi) {
+ if (newspi) {
spin_lock_bh(&net->xfrm.xfrm_state_lock);
+ x->id.spi = newspi;
h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c
index 4a74531..b68bd2f 100644
--- a/samples/bpf/task_fd_query_user.c
+++ b/samples/bpf/task_fd_query_user.c
@@ -290,7 +290,7 @@
int main(int argc, char **argv)
{
- struct rlimit r = {1024*1024, RLIM_INFINITY};
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
extern char __executable_start;
char filename[256], buf[256];
__u64 uprobe_file_offset;
diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c
index 3e36b3e..3d6eab7 100644
--- a/samples/bpf/tracex2_user.c
+++ b/samples/bpf/tracex2_user.c
@@ -116,7 +116,7 @@
int main(int ac, char **argv)
{
- struct rlimit r = {1024*1024, RLIM_INFINITY};
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
long key, next_key, value;
struct bpf_link *links[2];
struct bpf_program *prog;
diff --git a/samples/bpf/tracex3_user.c b/samples/bpf/tracex3_user.c
index 70e9877..83e0fecb 100644
--- a/samples/bpf/tracex3_user.c
+++ b/samples/bpf/tracex3_user.c
@@ -107,7 +107,7 @@
int main(int ac, char **argv)
{
- struct rlimit r = {1024*1024, RLIM_INFINITY};
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
struct bpf_link *links[2];
struct bpf_program *prog;
struct bpf_object *obj;
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index 6fb8dbd..f78cb18 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -765,7 +765,7 @@
int main(int argc, char **argv)
{
- struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
char *prog_name = "xdp_cpu_map5_lb_hash_ip_pairs";
char *mprog_filename = "xdp_redirect_kern.o";
char *redir_interface = NULL, *redir_map = NULL;
diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c
index caa4e7f..93fa1bc 100644
--- a/samples/bpf/xdp_rxq_info_user.c
+++ b/samples/bpf/xdp_rxq_info_user.c
@@ -450,7 +450,7 @@
int main(int argc, char **argv)
{
__u32 cfg_options= NO_TOUCH ; /* Default: Don't touch packet memory */
- struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
struct bpf_prog_load_attr prog_load_attr = {
.prog_type = BPF_PROG_TYPE_XDP,
};
diff --git a/samples/mic/mpssd/.gitignore b/samples/mic/mpssd/.gitignore
deleted file mode 100644
index aa03f1e..0000000
--- a/samples/mic/mpssd/.gitignore
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-mpssd
diff --git a/samples/mic/mpssd/Makefile b/samples/mic/mpssd/Makefile
deleted file mode 100644
index a7a6e0c7..0000000
--- a/samples/mic/mpssd/Makefile
+++ /dev/null
@@ -1,28 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-ifndef CROSS_COMPILE
-uname_M := $(shell uname -m 2>/dev/null || echo not)
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
-
-ifeq ($(ARCH),x86)
-
-PROGS := mpssd
-CC = $(CROSS_COMPILE)gcc
-CFLAGS := -I../../../usr/include -I../../../tools/include
-
-ifdef DEBUG
-CFLAGS += -DDEBUG=$(DEBUG)
-endif
-
-all: $(PROGS)
-mpssd: mpssd.c sysfs.c
- $(CC) $(CFLAGS) mpssd.c sysfs.c -o mpssd -lpthread
-
-install:
- install mpssd /usr/sbin/mpssd
- install micctrl /usr/sbin/micctrl
-
-clean:
- rm -fr $(PROGS)
-
-endif
-endif
diff --git a/samples/mic/mpssd/micctrl b/samples/mic/mpssd/micctrl
deleted file mode 100755
index 030a60b..0000000
--- a/samples/mic/mpssd/micctrl
+++ /dev/null
@@ -1,162 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0-only
-# Intel MIC Platform Software Stack (MPSS)
-#
-# Copyright(c) 2013 Intel Corporation.
-#
-# Intel MIC User Space Tools.
-#
-# micctrl - Controls MIC boot/start/stop.
-#
-# chkconfig: 2345 95 05
-# description: start MPSS stack processing.
-#
-### BEGIN INIT INFO
-# Provides: micctrl
-### END INIT INFO
-
-# Source function library.
-. /etc/init.d/functions
-
-sysfs="/sys/class/mic"
-
-_status()
-{
- f=$sysfs/$1
- echo -e $1 state: "`cat $f/state`" shutdown_status: "`cat $f/shutdown_status`"
-}
-
-status()
-{
- if [ "`echo $1 | head -c3`" == "mic" ]; then
- _status $1
- return $?
- fi
- for f in $sysfs/*
- do
- _status `basename $f`
- RETVAL=$?
- [ $RETVAL -ne 0 ] && return $RETVAL
- done
- return 0
-}
-
-_reset()
-{
- f=$sysfs/$1
- echo reset > $f/state
-}
-
-reset()
-{
- if [ "`echo $1 | head -c3`" == "mic" ]; then
- _reset $1
- return $?
- fi
- for f in $sysfs/*
- do
- _reset `basename $f`
- RETVAL=$?
- [ $RETVAL -ne 0 ] && return $RETVAL
- done
- return 0
-}
-
-_boot()
-{
- f=$sysfs/$1
- echo "linux" > $f/bootmode
- echo "mic/uos.img" > $f/firmware
- echo "mic/$1.image" > $f/ramdisk
- echo "boot" > $f/state
-}
-
-boot()
-{
- if [ "`echo $1 | head -c3`" == "mic" ]; then
- _boot $1
- return $?
- fi
- for f in $sysfs/*
- do
- _boot `basename $f`
- RETVAL=$?
- [ $RETVAL -ne 0 ] && return $RETVAL
- done
- return 0
-}
-
-_shutdown()
-{
- f=$sysfs/$1
- echo shutdown > $f/state
-}
-
-shutdown()
-{
- if [ "`echo $1 | head -c3`" == "mic" ]; then
- _shutdown $1
- return $?
- fi
- for f in $sysfs/*
- do
- _shutdown `basename $f`
- RETVAL=$?
- [ $RETVAL -ne 0 ] && return $RETVAL
- done
- return 0
-}
-
-_wait()
-{
- f=$sysfs/$1
- while [ "`cat $f/state`" != "offline" -a "`cat $f/state`" != "online" ]
- do
- sleep 1
- echo -e "Waiting for $1 to go offline"
- done
-}
-
-wait()
-{
- if [ "`echo $1 | head -c3`" == "mic" ]; then
- _wait $1
- return $?
- fi
- # Wait for the cards to go offline
- for f in $sysfs/*
- do
- _wait `basename $f`
- RETVAL=$?
- [ $RETVAL -ne 0 ] && return $RETVAL
- done
- return 0
-}
-
-if [ ! -d "$sysfs" ]; then
- echo -e $"Module unloaded "
- exit 3
-fi
-
-case $1 in
- -s)
- status $2
- ;;
- -r)
- reset $2
- ;;
- -b)
- boot $2
- ;;
- -S)
- shutdown $2
- ;;
- -w)
- wait $2
- ;;
- *)
- echo $"Usage: $0 {-s (status) |-r (reset) |-b (boot) |-S (shutdown) |-w (wait)}"
- exit 2
-esac
-
-exit $?
diff --git a/samples/mic/mpssd/mpss b/samples/mic/mpssd/mpss
deleted file mode 100755
index 248ac73..0000000
--- a/samples/mic/mpssd/mpss
+++ /dev/null
@@ -1,189 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0-only
-# Intel MIC Platform Software Stack (MPSS)
-#
-# Copyright(c) 2013 Intel Corporation.
-#
-# Intel MIC User Space Tools.
-#
-# mpss Start mpssd.
-#
-# chkconfig: 2345 95 05
-# description: start MPSS stack processing.
-#
-### BEGIN INIT INFO
-# Provides: mpss
-# Required-Start:
-# Required-Stop:
-# Short-Description: MPSS stack control
-# Description: MPSS stack control
-### END INIT INFO
-
-# Source function library.
-. /etc/init.d/functions
-
-exec=/usr/sbin/mpssd
-sysfs="/sys/class/mic"
-mic_modules="mic_host mic_x100_dma scif vop"
-
-start()
-{
- [ -x $exec ] || exit 5
-
- if [ "`ps -e | awk '{print $4}' | grep mpssd | head -1`" = "mpssd" ]; then
- echo -e $"MPSSD already running! "
- success
- echo
- return 0
- fi
-
- echo -e $"Starting MPSS Stack"
- echo -e $"Loading MIC drivers:" $mic_modules
-
- modprobe -a $mic_modules
- RETVAL=$?
- if [ $RETVAL -ne 0 ]; then
- failure
- echo
- return $RETVAL
- fi
-
- # Start the daemon
- echo -n $"Starting MPSSD "
- $exec
- RETVAL=$?
- if [ $RETVAL -ne 0 ]; then
- failure
- echo
- return $RETVAL
- fi
- success
- echo
-
- sleep 5
-
- # Boot the cards
- micctrl -b
-
- # Wait till ping works
- for f in $sysfs/*
- do
- count=100
- ipaddr=`cat $f/cmdline`
- ipaddr=${ipaddr#*address,}
- ipaddr=`echo $ipaddr | cut -d, -f1 | cut -d\; -f1`
- while [ $count -ge 0 ]
- do
- echo -e "Pinging "`basename $f`" "
- ping -c 1 $ipaddr &> /dev/null
- RETVAL=$?
- if [ $RETVAL -eq 0 ]; then
- success
- break
- fi
- sleep 1
- count=`expr $count - 1`
- done
- [ $RETVAL -ne 0 ] && failure || success
- echo
- done
- return $RETVAL
-}
-
-stop()
-{
- echo -e $"Shutting down MPSS Stack: "
-
- # Bail out if module is unloaded
- if [ ! -d "$sysfs" ]; then
- echo -n $"Module unloaded "
- success
- echo
- return 0
- fi
-
- # Shut down the cards.
- micctrl -S
-
- # Wait for the cards to go offline
- for f in $sysfs/*
- do
- while [ "`cat $f/state`" != "ready" ]
- do
- sleep 1
- echo -e "Waiting for "`basename $f`" to become ready"
- done
- done
-
- # Display the status of the cards
- micctrl -s
-
- # Kill MPSSD now
- echo -n $"Killing MPSSD"
- killall -9 mpssd 2>/dev/null
- RETVAL=$?
- [ $RETVAL -ne 0 ] && failure || success
- echo
- return $RETVAL
-}
-
-restart()
-{
- stop
- sleep 5
- start
-}
-
-status()
-{
- micctrl -s
- if [ "`ps -e | awk '{print $4}' | grep mpssd | head -n 1`" = "mpssd" ]; then
- echo "mpssd is running"
- else
- echo "mpssd is stopped"
- fi
- return 0
-}
-
-unload()
-{
- if [ ! -d "$sysfs" ]; then
- echo -n $"No MIC_HOST Module: "
- success
- echo
- return
- fi
-
- stop
-
- sleep 5
- echo -n $"Removing MIC drivers:" $mic_modules
- modprobe -r $mic_modules
- RETVAL=$?
- [ $RETVAL -ne 0 ] && failure || success
- echo
- return $RETVAL
-}
-
-case $1 in
- start)
- start
- ;;
- stop)
- stop
- ;;
- restart)
- restart
- ;;
- status)
- status
- ;;
- unload)
- unload
- ;;
- *)
- echo $"Usage: $0 {start|stop|restart|status|unload}"
- exit 2
-esac
-
-exit $?
diff --git a/samples/mic/mpssd/mpssd.c b/samples/mic/mpssd/mpssd.c
deleted file mode 100644
index c03a05d..0000000
--- a/samples/mic/mpssd/mpssd.c
+++ /dev/null
@@ -1,1815 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC User Space Tools.
- */
-
-#define _GNU_SOURCE
-
-#include <stdlib.h>
-#include <fcntl.h>
-#include <getopt.h>
-#include <assert.h>
-#include <unistd.h>
-#include <stdbool.h>
-#include <signal.h>
-#include <poll.h>
-#include <features.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-#include <sys/mman.h>
-#include <sys/socket.h>
-#include <linux/virtio_ring.h>
-#include <linux/virtio_net.h>
-#include <linux/virtio_console.h>
-#include <linux/virtio_blk.h>
-#include <linux/version.h>
-#include "mpssd.h"
-#include <linux/mic_ioctl.h>
-#include <linux/mic_common.h>
-#include <tools/endian.h>
-
-static void *init_mic(void *arg);
-
-static FILE *logfp;
-static struct mic_info mic_list;
-
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-
-#define min_t(type, x, y) ({ \
- type __min1 = (x); \
- type __min2 = (y); \
- __min1 < __min2 ? __min1 : __min2; })
-
-/* align addr on a size boundary - adjust address up/down if needed */
-#define _ALIGN_DOWN(addr, size) ((addr)&(~((size)-1)))
-#define _ALIGN_UP(addr, size) _ALIGN_DOWN(addr + size - 1, size)
-
-/* align addr on a size boundary - adjust address up if needed */
-#define _ALIGN(addr, size) _ALIGN_UP(addr, size)
-
-/* to align the pointer to the (next) page boundary */
-#define PAGE_ALIGN(addr) _ALIGN(addr, PAGE_SIZE)
-
-#define READ_ONCE(x) (*(volatile typeof(x) *)&(x))
-
-#define GSO_ENABLED 1
-#define MAX_GSO_SIZE (64 * 1024)
-#define ETH_H_LEN 14
-#define MAX_NET_PKT_SIZE (_ALIGN_UP(MAX_GSO_SIZE + ETH_H_LEN, 64))
-#define MIC_DEVICE_PAGE_END 0x1000
-
-#ifndef VIRTIO_NET_HDR_F_DATA_VALID
-#define VIRTIO_NET_HDR_F_DATA_VALID 2 /* Csum is valid */
-#endif
-
-static struct {
- struct mic_device_desc dd;
- struct mic_vqconfig vqconfig[2];
- __u32 host_features, guest_acknowledgements;
- struct virtio_console_config cons_config;
-} virtcons_dev_page = {
- .dd = {
- .type = VIRTIO_ID_CONSOLE,
- .num_vq = ARRAY_SIZE(virtcons_dev_page.vqconfig),
- .feature_len = sizeof(virtcons_dev_page.host_features),
- .config_len = sizeof(virtcons_dev_page.cons_config),
- },
- .vqconfig[0] = {
- .num = htole16(MIC_VRING_ENTRIES),
- },
- .vqconfig[1] = {
- .num = htole16(MIC_VRING_ENTRIES),
- },
-};
-
-static struct {
- struct mic_device_desc dd;
- struct mic_vqconfig vqconfig[2];
- __u32 host_features, guest_acknowledgements;
- struct virtio_net_config net_config;
-} virtnet_dev_page = {
- .dd = {
- .type = VIRTIO_ID_NET,
- .num_vq = ARRAY_SIZE(virtnet_dev_page.vqconfig),
- .feature_len = sizeof(virtnet_dev_page.host_features),
- .config_len = sizeof(virtnet_dev_page.net_config),
- },
- .vqconfig[0] = {
- .num = htole16(MIC_VRING_ENTRIES),
- },
- .vqconfig[1] = {
- .num = htole16(MIC_VRING_ENTRIES),
- },
-#if GSO_ENABLED
- .host_features = htole32(
- 1 << VIRTIO_NET_F_CSUM |
- 1 << VIRTIO_NET_F_GSO |
- 1 << VIRTIO_NET_F_GUEST_TSO4 |
- 1 << VIRTIO_NET_F_GUEST_TSO6 |
- 1 << VIRTIO_NET_F_GUEST_ECN),
-#else
- .host_features = 0,
-#endif
-};
-
-static const char *mic_config_dir = "/etc/mpss";
-static const char *virtblk_backend = "VIRTBLK_BACKEND";
-static struct {
- struct mic_device_desc dd;
- struct mic_vqconfig vqconfig[1];
- __u32 host_features, guest_acknowledgements;
- struct virtio_blk_config blk_config;
-} virtblk_dev_page = {
- .dd = {
- .type = VIRTIO_ID_BLOCK,
- .num_vq = ARRAY_SIZE(virtblk_dev_page.vqconfig),
- .feature_len = sizeof(virtblk_dev_page.host_features),
- .config_len = sizeof(virtblk_dev_page.blk_config),
- },
- .vqconfig[0] = {
- .num = htole16(MIC_VRING_ENTRIES),
- },
- .host_features =
- htole32(1<<VIRTIO_BLK_F_SEG_MAX),
- .blk_config = {
- .seg_max = htole32(MIC_VRING_ENTRIES - 2),
- .capacity = htole64(0),
- }
-};
-
-static char *myname;
-
-static int
-tap_configure(struct mic_info *mic, char *dev)
-{
- pid_t pid;
- char *ifargv[7];
- char ipaddr[IFNAMSIZ];
- int ret = 0;
-
- pid = fork();
- if (pid == 0) {
- ifargv[0] = "ip";
- ifargv[1] = "link";
- ifargv[2] = "set";
- ifargv[3] = dev;
- ifargv[4] = "up";
- ifargv[5] = NULL;
- mpsslog("Configuring %s\n", dev);
- ret = execvp("ip", ifargv);
- if (ret < 0) {
- mpsslog("%s execvp failed errno %s\n",
- mic->name, strerror(errno));
- return ret;
- }
- }
- if (pid < 0) {
- mpsslog("%s fork failed errno %s\n",
- mic->name, strerror(errno));
- return ret;
- }
-
- ret = waitpid(pid, NULL, 0);
- if (ret < 0) {
- mpsslog("%s waitpid failed errno %s\n",
- mic->name, strerror(errno));
- return ret;
- }
-
- snprintf(ipaddr, IFNAMSIZ, "172.31.%d.254/24", mic->id + 1);
-
- pid = fork();
- if (pid == 0) {
- ifargv[0] = "ip";
- ifargv[1] = "addr";
- ifargv[2] = "add";
- ifargv[3] = ipaddr;
- ifargv[4] = "dev";
- ifargv[5] = dev;
- ifargv[6] = NULL;
- mpsslog("Configuring %s ipaddr %s\n", dev, ipaddr);
- ret = execvp("ip", ifargv);
- if (ret < 0) {
- mpsslog("%s execvp failed errno %s\n",
- mic->name, strerror(errno));
- return ret;
- }
- }
- if (pid < 0) {
- mpsslog("%s fork failed errno %s\n",
- mic->name, strerror(errno));
- return ret;
- }
-
- ret = waitpid(pid, NULL, 0);
- if (ret < 0) {
- mpsslog("%s waitpid failed errno %s\n",
- mic->name, strerror(errno));
- return ret;
- }
- mpsslog("MIC name %s %s %d DONE!\n",
- mic->name, __func__, __LINE__);
- return 0;
-}
-
-static int tun_alloc(struct mic_info *mic, char *dev)
-{
- struct ifreq ifr;
- int fd, err;
-#if GSO_ENABLED
- unsigned offload;
-#endif
- fd = open("/dev/net/tun", O_RDWR);
- if (fd < 0) {
- mpsslog("Could not open /dev/net/tun %s\n", strerror(errno));
- goto done;
- }
-
- memset(&ifr, 0, sizeof(ifr));
-
- ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR;
- if (*dev)
- strncpy(ifr.ifr_name, dev, IFNAMSIZ);
-
- err = ioctl(fd, TUNSETIFF, (void *)&ifr);
- if (err < 0) {
- mpsslog("%s %s %d TUNSETIFF failed %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- close(fd);
- return err;
- }
-#if GSO_ENABLED
- offload = TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | TUN_F_TSO_ECN;
-
- err = ioctl(fd, TUNSETOFFLOAD, offload);
- if (err < 0) {
- mpsslog("%s %s %d TUNSETOFFLOAD failed %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- close(fd);
- return err;
- }
-#endif
- strcpy(dev, ifr.ifr_name);
- mpsslog("Created TAP %s\n", dev);
-done:
- return fd;
-}
-
-#define NET_FD_VIRTIO_NET 0
-#define NET_FD_TUN 1
-#define MAX_NET_FD 2
-
-static void set_dp(struct mic_info *mic, int type, void *dp)
-{
- switch (type) {
- case VIRTIO_ID_CONSOLE:
- mic->mic_console.console_dp = dp;
- return;
- case VIRTIO_ID_NET:
- mic->mic_net.net_dp = dp;
- return;
- case VIRTIO_ID_BLOCK:
- mic->mic_virtblk.block_dp = dp;
- return;
- }
- mpsslog("%s %s %d not found\n", mic->name, __func__, type);
- assert(0);
-}
-
-static void *get_dp(struct mic_info *mic, int type)
-{
- switch (type) {
- case VIRTIO_ID_CONSOLE:
- return mic->mic_console.console_dp;
- case VIRTIO_ID_NET:
- return mic->mic_net.net_dp;
- case VIRTIO_ID_BLOCK:
- return mic->mic_virtblk.block_dp;
- }
- mpsslog("%s %s %d not found\n", mic->name, __func__, type);
- assert(0);
- return NULL;
-}
-
-static struct mic_device_desc *get_device_desc(struct mic_info *mic, int type)
-{
- struct mic_device_desc *d;
- int i;
- void *dp = get_dp(mic, type);
-
- for (i = sizeof(struct mic_bootparam); i < PAGE_SIZE;
- i += mic_total_desc_size(d)) {
- d = dp + i;
-
- /* End of list */
- if (d->type == 0)
- break;
-
- if (d->type == -1)
- continue;
-
- mpsslog("%s %s d-> type %d d %p\n",
- mic->name, __func__, d->type, d);
-
- if (d->type == (__u8)type)
- return d;
- }
- mpsslog("%s %s %d not found\n", mic->name, __func__, type);
- return NULL;
-}
-
-/* See comments in vhost.c for explanation of next_desc() */
-static unsigned next_desc(struct vring_desc *desc)
-{
- unsigned int next;
-
- if (!(le16toh(desc->flags) & VRING_DESC_F_NEXT))
- return -1U;
- next = le16toh(desc->next);
- return next;
-}
-
-/* Sum up all the IOVEC length */
-static ssize_t
-sum_iovec_len(struct mic_copy_desc *copy)
-{
- ssize_t sum = 0;
- unsigned int i;
-
- for (i = 0; i < copy->iovcnt; i++)
- sum += copy->iov[i].iov_len;
- return sum;
-}
-
-static inline void verify_out_len(struct mic_info *mic,
- struct mic_copy_desc *copy)
-{
- if (copy->out_len != sum_iovec_len(copy)) {
- mpsslog("%s %s %d BUG copy->out_len 0x%x len 0x%zx\n",
- mic->name, __func__, __LINE__,
- copy->out_len, sum_iovec_len(copy));
- assert(copy->out_len == sum_iovec_len(copy));
- }
-}
-
-/* Display an iovec */
-static void
-disp_iovec(struct mic_info *mic, struct mic_copy_desc *copy,
- const char *s, int line)
-{
- unsigned int i;
-
- for (i = 0; i < copy->iovcnt; i++)
- mpsslog("%s %s %d copy->iov[%d] addr %p len 0x%zx\n",
- mic->name, s, line, i,
- copy->iov[i].iov_base, copy->iov[i].iov_len);
-}
-
-static inline __u16 read_avail_idx(struct mic_vring *vr)
-{
- return READ_ONCE(vr->info->avail_idx);
-}
-
-static inline void txrx_prepare(int type, bool tx, struct mic_vring *vr,
- struct mic_copy_desc *copy, ssize_t len)
-{
- copy->vr_idx = tx ? 0 : 1;
- copy->update_used = true;
- if (type == VIRTIO_ID_NET)
- copy->iov[1].iov_len = len - sizeof(struct virtio_net_hdr);
- else
- copy->iov[0].iov_len = len;
-}
-
-/* Central API which triggers the copies */
-static int
-mic_virtio_copy(struct mic_info *mic, int fd,
- struct mic_vring *vr, struct mic_copy_desc *copy)
-{
- int ret;
-
- ret = ioctl(fd, MIC_VIRTIO_COPY_DESC, copy);
- if (ret) {
- mpsslog("%s %s %d errno %s ret %d\n",
- mic->name, __func__, __LINE__,
- strerror(errno), ret);
- }
- return ret;
-}
-
-static inline unsigned _vring_size(unsigned int num, unsigned long align)
-{
- return _ALIGN_UP(((sizeof(struct vring_desc) * num + sizeof(__u16) * (3 + num)
- + align - 1) & ~(align - 1))
- + sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num, 4);
-}
-
-/*
- * This initialization routine requires at least one
- * vring i.e. vr0. vr1 is optional.
- */
-static void *
-init_vr(struct mic_info *mic, int fd, int type,
- struct mic_vring *vr0, struct mic_vring *vr1, int num_vq)
-{
- int vr_size;
- char *va;
-
- vr_size = PAGE_ALIGN(_vring_size(MIC_VRING_ENTRIES,
- MIC_VIRTIO_RING_ALIGN) +
- sizeof(struct _mic_vring_info));
- va = mmap(NULL, MIC_DEVICE_PAGE_END + vr_size * num_vq,
- PROT_READ, MAP_SHARED, fd, 0);
- if (MAP_FAILED == va) {
- mpsslog("%s %s %d mmap failed errno %s\n",
- mic->name, __func__, __LINE__,
- strerror(errno));
- goto done;
- }
- set_dp(mic, type, va);
- vr0->va = (struct mic_vring *)&va[MIC_DEVICE_PAGE_END];
- vr0->info = vr0->va +
- _vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN);
- vring_init(&vr0->vr,
- MIC_VRING_ENTRIES, vr0->va, MIC_VIRTIO_RING_ALIGN);
- mpsslog("%s %s vr0 %p vr0->info %p vr_size 0x%x vring 0x%x ",
- __func__, mic->name, vr0->va, vr0->info, vr_size,
- _vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN));
- mpsslog("magic 0x%x expected 0x%x\n",
- le32toh(vr0->info->magic), MIC_MAGIC + type);
- assert(le32toh(vr0->info->magic) == MIC_MAGIC + type);
- if (vr1) {
- vr1->va = (struct mic_vring *)
- &va[MIC_DEVICE_PAGE_END + vr_size];
- vr1->info = vr1->va + _vring_size(MIC_VRING_ENTRIES,
- MIC_VIRTIO_RING_ALIGN);
- vring_init(&vr1->vr,
- MIC_VRING_ENTRIES, vr1->va, MIC_VIRTIO_RING_ALIGN);
- mpsslog("%s %s vr1 %p vr1->info %p vr_size 0x%x vring 0x%x ",
- __func__, mic->name, vr1->va, vr1->info, vr_size,
- _vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN));
- mpsslog("magic 0x%x expected 0x%x\n",
- le32toh(vr1->info->magic), MIC_MAGIC + type + 1);
- assert(le32toh(vr1->info->magic) == MIC_MAGIC + type + 1);
- }
-done:
- return va;
-}
-
-static int
-wait_for_card_driver(struct mic_info *mic, int fd, int type)
-{
- struct pollfd pollfd;
- int err;
- struct mic_device_desc *desc = get_device_desc(mic, type);
- __u8 prev_status;
-
- if (!desc)
- return -ENODEV;
- prev_status = desc->status;
- pollfd.fd = fd;
- mpsslog("%s %s Waiting .... desc-> type %d status 0x%x\n",
- mic->name, __func__, type, desc->status);
-
- while (1) {
- pollfd.events = POLLIN;
- pollfd.revents = 0;
- err = poll(&pollfd, 1, -1);
- if (err < 0) {
- mpsslog("%s %s poll failed %s\n",
- mic->name, __func__, strerror(errno));
- continue;
- }
-
- if (pollfd.revents) {
- if (desc->status != prev_status) {
- mpsslog("%s %s Waiting... desc-> type %d "
- "status 0x%x\n",
- mic->name, __func__, type,
- desc->status);
- prev_status = desc->status;
- }
- if (desc->status & VIRTIO_CONFIG_S_DRIVER_OK) {
- mpsslog("%s %s poll.revents %d\n",
- mic->name, __func__, pollfd.revents);
- mpsslog("%s %s desc-> type %d status 0x%x\n",
- mic->name, __func__, type,
- desc->status);
- break;
- }
- }
- }
- return 0;
-}
-
-/* Spin till we have some descriptors */
-static void
-spin_for_descriptors(struct mic_info *mic, struct mic_vring *vr)
-{
- __u16 avail_idx = read_avail_idx(vr);
-
- while (avail_idx == le16toh(READ_ONCE(vr->vr.avail->idx))) {
-#ifdef DEBUG
- mpsslog("%s %s waiting for desc avail %d info_avail %d\n",
- mic->name, __func__,
- le16toh(vr->vr.avail->idx), vr->info->avail_idx);
-#endif
- sched_yield();
- }
-}
-
-static void *
-virtio_net(void *arg)
-{
- static __u8 vnet_hdr[2][sizeof(struct virtio_net_hdr)];
- static __u8 vnet_buf[2][MAX_NET_PKT_SIZE] __attribute__ ((aligned(64)));
- struct iovec vnet_iov[2][2] = {
- { { .iov_base = vnet_hdr[0], .iov_len = sizeof(vnet_hdr[0]) },
- { .iov_base = vnet_buf[0], .iov_len = sizeof(vnet_buf[0]) } },
- { { .iov_base = vnet_hdr[1], .iov_len = sizeof(vnet_hdr[1]) },
- { .iov_base = vnet_buf[1], .iov_len = sizeof(vnet_buf[1]) } },
- };
- struct iovec *iov0 = vnet_iov[0], *iov1 = vnet_iov[1];
- struct mic_info *mic = (struct mic_info *)arg;
- char if_name[IFNAMSIZ];
- struct pollfd net_poll[MAX_NET_FD];
- struct mic_vring tx_vr, rx_vr;
- struct mic_copy_desc copy;
- struct mic_device_desc *desc;
- int err;
-
- snprintf(if_name, IFNAMSIZ, "mic%d", mic->id);
- mic->mic_net.tap_fd = tun_alloc(mic, if_name);
- if (mic->mic_net.tap_fd < 0)
- goto done;
-
- if (tap_configure(mic, if_name))
- goto done;
- mpsslog("MIC name %s id %d\n", mic->name, mic->id);
-
- net_poll[NET_FD_VIRTIO_NET].fd = mic->mic_net.virtio_net_fd;
- net_poll[NET_FD_VIRTIO_NET].events = POLLIN;
- net_poll[NET_FD_TUN].fd = mic->mic_net.tap_fd;
- net_poll[NET_FD_TUN].events = POLLIN;
-
- if (MAP_FAILED == init_vr(mic, mic->mic_net.virtio_net_fd,
- VIRTIO_ID_NET, &tx_vr, &rx_vr,
- virtnet_dev_page.dd.num_vq)) {
- mpsslog("%s init_vr failed %s\n",
- mic->name, strerror(errno));
- goto done;
- }
-
- copy.iovcnt = 2;
- desc = get_device_desc(mic, VIRTIO_ID_NET);
-
- while (1) {
- ssize_t len;
-
- net_poll[NET_FD_VIRTIO_NET].revents = 0;
- net_poll[NET_FD_TUN].revents = 0;
-
- /* Start polling for data from tap and virtio net */
- err = poll(net_poll, 2, -1);
- if (err < 0) {
- mpsslog("%s poll failed %s\n",
- __func__, strerror(errno));
- continue;
- }
- if (!(desc->status & VIRTIO_CONFIG_S_DRIVER_OK)) {
- err = wait_for_card_driver(mic,
- mic->mic_net.virtio_net_fd,
- VIRTIO_ID_NET);
- if (err) {
- mpsslog("%s %s %d Exiting...\n",
- mic->name, __func__, __LINE__);
- break;
- }
- }
- /*
- * Check if there is data to be read from TUN and write to
- * virtio net fd if there is.
- */
- if (net_poll[NET_FD_TUN].revents & POLLIN) {
- copy.iov = iov0;
- len = readv(net_poll[NET_FD_TUN].fd,
- copy.iov, copy.iovcnt);
- if (len > 0) {
- struct virtio_net_hdr *hdr
- = (struct virtio_net_hdr *)vnet_hdr[0];
-
- /* Disable checksums on the card since we are on
- a reliable PCIe link */
- hdr->flags |= VIRTIO_NET_HDR_F_DATA_VALID;
-#ifdef DEBUG
- mpsslog("%s %s %d hdr->flags 0x%x ", mic->name,
- __func__, __LINE__, hdr->flags);
- mpsslog("copy.out_len %d hdr->gso_type 0x%x\n",
- copy.out_len, hdr->gso_type);
-#endif
-#ifdef DEBUG
- disp_iovec(mic, ©, __func__, __LINE__);
- mpsslog("%s %s %d read from tap 0x%lx\n",
- mic->name, __func__, __LINE__,
- len);
-#endif
- spin_for_descriptors(mic, &tx_vr);
- txrx_prepare(VIRTIO_ID_NET, 1, &tx_vr, ©,
- len);
-
- err = mic_virtio_copy(mic,
- mic->mic_net.virtio_net_fd, &tx_vr,
- ©);
- if (err < 0) {
- mpsslog("%s %s %d mic_virtio_copy %s\n",
- mic->name, __func__, __LINE__,
- strerror(errno));
- }
- if (!err)
- verify_out_len(mic, ©);
-#ifdef DEBUG
- disp_iovec(mic, ©, __func__, __LINE__);
- mpsslog("%s %s %d wrote to net 0x%lx\n",
- mic->name, __func__, __LINE__,
- sum_iovec_len(©));
-#endif
- /* Reinitialize IOV for next run */
- iov0[1].iov_len = MAX_NET_PKT_SIZE;
- } else if (len < 0) {
- disp_iovec(mic, ©, __func__, __LINE__);
- mpsslog("%s %s %d read failed %s ", mic->name,
- __func__, __LINE__, strerror(errno));
- mpsslog("cnt %d sum %zd\n",
- copy.iovcnt, sum_iovec_len(©));
- }
- }
-
- /*
- * Check if there is data to be read from virtio net and
- * write to TUN if there is.
- */
- if (net_poll[NET_FD_VIRTIO_NET].revents & POLLIN) {
- while (rx_vr.info->avail_idx !=
- le16toh(rx_vr.vr.avail->idx)) {
- copy.iov = iov1;
- txrx_prepare(VIRTIO_ID_NET, 0, &rx_vr, ©,
- MAX_NET_PKT_SIZE
- + sizeof(struct virtio_net_hdr));
-
- err = mic_virtio_copy(mic,
- mic->mic_net.virtio_net_fd, &rx_vr,
- ©);
- if (!err) {
-#ifdef DEBUG
- struct virtio_net_hdr *hdr
- = (struct virtio_net_hdr *)
- vnet_hdr[1];
-
- mpsslog("%s %s %d hdr->flags 0x%x, ",
- mic->name, __func__, __LINE__,
- hdr->flags);
- mpsslog("out_len %d gso_type 0x%x\n",
- copy.out_len,
- hdr->gso_type);
-#endif
- /* Set the correct output iov_len */
- iov1[1].iov_len = copy.out_len -
- sizeof(struct virtio_net_hdr);
- verify_out_len(mic, ©);
-#ifdef DEBUG
- disp_iovec(mic, ©, __func__,
- __LINE__);
- mpsslog("%s %s %d ",
- mic->name, __func__, __LINE__);
- mpsslog("read from net 0x%lx\n",
- sum_iovec_len(©));
-#endif
- len = writev(net_poll[NET_FD_TUN].fd,
- copy.iov, copy.iovcnt);
- if (len != sum_iovec_len(©)) {
- mpsslog("Tun write failed %s ",
- strerror(errno));
- mpsslog("len 0x%zx ", len);
- mpsslog("read_len 0x%zx\n",
- sum_iovec_len(©));
- } else {
-#ifdef DEBUG
- disp_iovec(mic, ©, __func__,
- __LINE__);
- mpsslog("%s %s %d ",
- mic->name, __func__,
- __LINE__);
- mpsslog("wrote to tap 0x%lx\n",
- len);
-#endif
- }
- } else {
- mpsslog("%s %s %d mic_virtio_copy %s\n",
- mic->name, __func__, __LINE__,
- strerror(errno));
- break;
- }
- }
- }
- if (net_poll[NET_FD_VIRTIO_NET].revents & POLLERR)
- mpsslog("%s: %s: POLLERR\n", __func__, mic->name);
- }
-done:
- pthread_exit(NULL);
-}
-
-/* virtio_console */
-#define VIRTIO_CONSOLE_FD 0
-#define MONITOR_FD (VIRTIO_CONSOLE_FD + 1)
-#define MAX_CONSOLE_FD (MONITOR_FD + 1) /* must be the last one + 1 */
-#define MAX_BUFFER_SIZE PAGE_SIZE
-
-static void *
-virtio_console(void *arg)
-{
- static __u8 vcons_buf[2][PAGE_SIZE];
- struct iovec vcons_iov[2] = {
- { .iov_base = vcons_buf[0], .iov_len = sizeof(vcons_buf[0]) },
- { .iov_base = vcons_buf[1], .iov_len = sizeof(vcons_buf[1]) },
- };
- struct iovec *iov0 = &vcons_iov[0], *iov1 = &vcons_iov[1];
- struct mic_info *mic = (struct mic_info *)arg;
- int err;
- struct pollfd console_poll[MAX_CONSOLE_FD];
- int pty_fd;
- char *pts_name;
- ssize_t len;
- struct mic_vring tx_vr, rx_vr;
- struct mic_copy_desc copy;
- struct mic_device_desc *desc;
-
- pty_fd = posix_openpt(O_RDWR);
- if (pty_fd < 0) {
- mpsslog("can't open a pseudoterminal master device: %s\n",
- strerror(errno));
- goto _return;
- }
- pts_name = ptsname(pty_fd);
- if (pts_name == NULL) {
- mpsslog("can't get pts name\n");
- goto _close_pty;
- }
- printf("%s console message goes to %s\n", mic->name, pts_name);
- mpsslog("%s console message goes to %s\n", mic->name, pts_name);
- err = grantpt(pty_fd);
- if (err < 0) {
- mpsslog("can't grant access: %s %s\n",
- pts_name, strerror(errno));
- goto _close_pty;
- }
- err = unlockpt(pty_fd);
- if (err < 0) {
- mpsslog("can't unlock a pseudoterminal: %s %s\n",
- pts_name, strerror(errno));
- goto _close_pty;
- }
- console_poll[MONITOR_FD].fd = pty_fd;
- console_poll[MONITOR_FD].events = POLLIN;
-
- console_poll[VIRTIO_CONSOLE_FD].fd = mic->mic_console.virtio_console_fd;
- console_poll[VIRTIO_CONSOLE_FD].events = POLLIN;
-
- if (MAP_FAILED == init_vr(mic, mic->mic_console.virtio_console_fd,
- VIRTIO_ID_CONSOLE, &tx_vr, &rx_vr,
- virtcons_dev_page.dd.num_vq)) {
- mpsslog("%s init_vr failed %s\n",
- mic->name, strerror(errno));
- goto _close_pty;
- }
-
- copy.iovcnt = 1;
- desc = get_device_desc(mic, VIRTIO_ID_CONSOLE);
-
- for (;;) {
- console_poll[MONITOR_FD].revents = 0;
- console_poll[VIRTIO_CONSOLE_FD].revents = 0;
- err = poll(console_poll, MAX_CONSOLE_FD, -1);
- if (err < 0) {
- mpsslog("%s %d: poll failed: %s\n", __func__, __LINE__,
- strerror(errno));
- continue;
- }
- if (!(desc->status & VIRTIO_CONFIG_S_DRIVER_OK)) {
- err = wait_for_card_driver(mic,
- mic->mic_console.virtio_console_fd,
- VIRTIO_ID_CONSOLE);
- if (err) {
- mpsslog("%s %s %d Exiting...\n",
- mic->name, __func__, __LINE__);
- break;
- }
- }
-
- if (console_poll[MONITOR_FD].revents & POLLIN) {
- copy.iov = iov0;
- len = readv(pty_fd, copy.iov, copy.iovcnt);
- if (len > 0) {
-#ifdef DEBUG
- disp_iovec(mic, ©, __func__, __LINE__);
- mpsslog("%s %s %d read from tap 0x%lx\n",
- mic->name, __func__, __LINE__,
- len);
-#endif
- spin_for_descriptors(mic, &tx_vr);
- txrx_prepare(VIRTIO_ID_CONSOLE, 1, &tx_vr,
- ©, len);
-
- err = mic_virtio_copy(mic,
- mic->mic_console.virtio_console_fd,
- &tx_vr, ©);
- if (err < 0) {
- mpsslog("%s %s %d mic_virtio_copy %s\n",
- mic->name, __func__, __LINE__,
- strerror(errno));
- }
- if (!err)
- verify_out_len(mic, ©);
-#ifdef DEBUG
- disp_iovec(mic, ©, __func__, __LINE__);
- mpsslog("%s %s %d wrote to net 0x%lx\n",
- mic->name, __func__, __LINE__,
- sum_iovec_len(©));
-#endif
- /* Reinitialize IOV for next run */
- iov0->iov_len = PAGE_SIZE;
- } else if (len < 0) {
- disp_iovec(mic, ©, __func__, __LINE__);
- mpsslog("%s %s %d read failed %s ",
- mic->name, __func__, __LINE__,
- strerror(errno));
- mpsslog("cnt %d sum %zd\n",
- copy.iovcnt, sum_iovec_len(©));
- }
- }
-
- if (console_poll[VIRTIO_CONSOLE_FD].revents & POLLIN) {
- while (rx_vr.info->avail_idx !=
- le16toh(rx_vr.vr.avail->idx)) {
- copy.iov = iov1;
- txrx_prepare(VIRTIO_ID_CONSOLE, 0, &rx_vr,
- ©, PAGE_SIZE);
-
- err = mic_virtio_copy(mic,
- mic->mic_console.virtio_console_fd,
- &rx_vr, ©);
- if (!err) {
- /* Set the correct output iov_len */
- iov1->iov_len = copy.out_len;
- verify_out_len(mic, ©);
-#ifdef DEBUG
- disp_iovec(mic, ©, __func__,
- __LINE__);
- mpsslog("%s %s %d ",
- mic->name, __func__, __LINE__);
- mpsslog("read from net 0x%lx\n",
- sum_iovec_len(©));
-#endif
- len = writev(pty_fd,
- copy.iov, copy.iovcnt);
- if (len != sum_iovec_len(©)) {
- mpsslog("Tun write failed %s ",
- strerror(errno));
- mpsslog("len 0x%zx ", len);
- mpsslog("read_len 0x%zx\n",
- sum_iovec_len(©));
- } else {
-#ifdef DEBUG
- disp_iovec(mic, ©, __func__,
- __LINE__);
- mpsslog("%s %s %d ",
- mic->name, __func__,
- __LINE__);
- mpsslog("wrote to tap 0x%lx\n",
- len);
-#endif
- }
- } else {
- mpsslog("%s %s %d mic_virtio_copy %s\n",
- mic->name, __func__, __LINE__,
- strerror(errno));
- break;
- }
- }
- }
- if (console_poll[NET_FD_VIRTIO_NET].revents & POLLERR)
- mpsslog("%s: %s: POLLERR\n", __func__, mic->name);
- }
-_close_pty:
- close(pty_fd);
-_return:
- pthread_exit(NULL);
-}
-
-static void
-add_virtio_device(struct mic_info *mic, struct mic_device_desc *dd)
-{
- char path[PATH_MAX];
- int fd, err;
-
- snprintf(path, PATH_MAX, "/dev/vop_virtio%d", mic->id);
- fd = open(path, O_RDWR);
- if (fd < 0) {
- mpsslog("Could not open %s %s\n", path, strerror(errno));
- return;
- }
-
- err = ioctl(fd, MIC_VIRTIO_ADD_DEVICE, dd);
- if (err < 0) {
- mpsslog("Could not add %d %s\n", dd->type, strerror(errno));
- close(fd);
- return;
- }
- switch (dd->type) {
- case VIRTIO_ID_NET:
- mic->mic_net.virtio_net_fd = fd;
- mpsslog("Added VIRTIO_ID_NET for %s\n", mic->name);
- break;
- case VIRTIO_ID_CONSOLE:
- mic->mic_console.virtio_console_fd = fd;
- mpsslog("Added VIRTIO_ID_CONSOLE for %s\n", mic->name);
- break;
- case VIRTIO_ID_BLOCK:
- mic->mic_virtblk.virtio_block_fd = fd;
- mpsslog("Added VIRTIO_ID_BLOCK for %s\n", mic->name);
- break;
- }
-}
-
-static bool
-set_backend_file(struct mic_info *mic)
-{
- FILE *config;
- char buff[PATH_MAX], *line, *evv, *p;
-
- snprintf(buff, PATH_MAX, "%s/mpssd%03d.conf", mic_config_dir, mic->id);
- config = fopen(buff, "r");
- if (config == NULL)
- return false;
- do { /* look for "virtblk_backend=XXXX" */
- line = fgets(buff, PATH_MAX, config);
- if (line == NULL)
- break;
- if (*line == '#')
- continue;
- p = strchr(line, '\n');
- if (p)
- *p = '\0';
- } while (strncmp(line, virtblk_backend, strlen(virtblk_backend)) != 0);
- fclose(config);
- if (line == NULL)
- return false;
- evv = strchr(line, '=');
- if (evv == NULL)
- return false;
- mic->mic_virtblk.backend_file = malloc(strlen(evv) + 1);
- if (mic->mic_virtblk.backend_file == NULL) {
- mpsslog("%s %d can't allocate memory\n", mic->name, mic->id);
- return false;
- }
- strcpy(mic->mic_virtblk.backend_file, evv + 1);
- return true;
-}
-
-#define SECTOR_SIZE 512
-static bool
-set_backend_size(struct mic_info *mic)
-{
- mic->mic_virtblk.backend_size = lseek(mic->mic_virtblk.backend, 0,
- SEEK_END);
- if (mic->mic_virtblk.backend_size < 0) {
- mpsslog("%s: can't seek: %s\n",
- mic->name, mic->mic_virtblk.backend_file);
- return false;
- }
- virtblk_dev_page.blk_config.capacity =
- mic->mic_virtblk.backend_size / SECTOR_SIZE;
- if ((mic->mic_virtblk.backend_size % SECTOR_SIZE) != 0)
- virtblk_dev_page.blk_config.capacity++;
-
- virtblk_dev_page.blk_config.capacity =
- htole64(virtblk_dev_page.blk_config.capacity);
-
- return true;
-}
-
-static bool
-open_backend(struct mic_info *mic)
-{
- if (!set_backend_file(mic))
- goto _error_exit;
- mic->mic_virtblk.backend = open(mic->mic_virtblk.backend_file, O_RDWR);
- if (mic->mic_virtblk.backend < 0) {
- mpsslog("%s: can't open: %s\n", mic->name,
- mic->mic_virtblk.backend_file);
- goto _error_free;
- }
- if (!set_backend_size(mic))
- goto _error_close;
- mic->mic_virtblk.backend_addr = mmap(NULL,
- mic->mic_virtblk.backend_size,
- PROT_READ|PROT_WRITE, MAP_SHARED,
- mic->mic_virtblk.backend, 0L);
- if (mic->mic_virtblk.backend_addr == MAP_FAILED) {
- mpsslog("%s: can't map: %s %s\n",
- mic->name, mic->mic_virtblk.backend_file,
- strerror(errno));
- goto _error_close;
- }
- return true;
-
- _error_close:
- close(mic->mic_virtblk.backend);
- _error_free:
- free(mic->mic_virtblk.backend_file);
- _error_exit:
- return false;
-}
-
-static void
-close_backend(struct mic_info *mic)
-{
- munmap(mic->mic_virtblk.backend_addr, mic->mic_virtblk.backend_size);
- close(mic->mic_virtblk.backend);
- free(mic->mic_virtblk.backend_file);
-}
-
-static bool
-start_virtblk(struct mic_info *mic, struct mic_vring *vring)
-{
- if (((unsigned long)&virtblk_dev_page.blk_config % 8) != 0) {
- mpsslog("%s: blk_config is not 8 byte aligned.\n",
- mic->name);
- return false;
- }
- add_virtio_device(mic, &virtblk_dev_page.dd);
- if (MAP_FAILED == init_vr(mic, mic->mic_virtblk.virtio_block_fd,
- VIRTIO_ID_BLOCK, vring, NULL,
- virtblk_dev_page.dd.num_vq)) {
- mpsslog("%s init_vr failed %s\n",
- mic->name, strerror(errno));
- return false;
- }
- return true;
-}
-
-static void
-stop_virtblk(struct mic_info *mic)
-{
- int vr_size, ret;
-
- vr_size = PAGE_ALIGN(_vring_size(MIC_VRING_ENTRIES,
- MIC_VIRTIO_RING_ALIGN) +
- sizeof(struct _mic_vring_info));
- ret = munmap(mic->mic_virtblk.block_dp,
- MIC_DEVICE_PAGE_END + vr_size * virtblk_dev_page.dd.num_vq);
- if (ret < 0)
- mpsslog("%s munmap errno %d\n", mic->name, errno);
- close(mic->mic_virtblk.virtio_block_fd);
-}
-
-static __u8
-header_error_check(struct vring_desc *desc)
-{
- if (le32toh(desc->len) != sizeof(struct virtio_blk_outhdr)) {
- mpsslog("%s() %d: length is not sizeof(virtio_blk_outhd)\n",
- __func__, __LINE__);
- return -EIO;
- }
- if (!(le16toh(desc->flags) & VRING_DESC_F_NEXT)) {
- mpsslog("%s() %d: alone\n",
- __func__, __LINE__);
- return -EIO;
- }
- if (le16toh(desc->flags) & VRING_DESC_F_WRITE) {
- mpsslog("%s() %d: not read\n",
- __func__, __LINE__);
- return -EIO;
- }
- return 0;
-}
-
-static int
-read_header(int fd, struct virtio_blk_outhdr *hdr, __u32 desc_idx)
-{
- struct iovec iovec;
- struct mic_copy_desc copy;
-
- iovec.iov_len = sizeof(*hdr);
- iovec.iov_base = hdr;
- copy.iov = &iovec;
- copy.iovcnt = 1;
- copy.vr_idx = 0; /* only one vring on virtio_block */
- copy.update_used = false; /* do not update used index */
- return ioctl(fd, MIC_VIRTIO_COPY_DESC, ©);
-}
-
-static int
-transfer_blocks(int fd, struct iovec *iovec, __u32 iovcnt)
-{
- struct mic_copy_desc copy;
-
- copy.iov = iovec;
- copy.iovcnt = iovcnt;
- copy.vr_idx = 0; /* only one vring on virtio_block */
- copy.update_used = false; /* do not update used index */
- return ioctl(fd, MIC_VIRTIO_COPY_DESC, ©);
-}
-
-static __u8
-status_error_check(struct vring_desc *desc)
-{
- if (le32toh(desc->len) != sizeof(__u8)) {
- mpsslog("%s() %d: length is not sizeof(status)\n",
- __func__, __LINE__);
- return -EIO;
- }
- return 0;
-}
-
-static int
-write_status(int fd, __u8 *status)
-{
- struct iovec iovec;
- struct mic_copy_desc copy;
-
- iovec.iov_base = status;
- iovec.iov_len = sizeof(*status);
- copy.iov = &iovec;
- copy.iovcnt = 1;
- copy.vr_idx = 0; /* only one vring on virtio_block */
- copy.update_used = true; /* Update used index */
- return ioctl(fd, MIC_VIRTIO_COPY_DESC, ©);
-}
-
-#ifndef VIRTIO_BLK_T_GET_ID
-#define VIRTIO_BLK_T_GET_ID 8
-#endif
-
-static void *
-virtio_block(void *arg)
-{
- struct mic_info *mic = (struct mic_info *)arg;
- int ret;
- struct pollfd block_poll;
- struct mic_vring vring;
- __u16 avail_idx;
- __u32 desc_idx;
- struct vring_desc *desc;
- struct iovec *iovec, *piov;
- __u8 status;
- __u32 buffer_desc_idx;
- struct virtio_blk_outhdr hdr;
- void *fos;
-
- for (;;) { /* forever */
- if (!open_backend(mic)) { /* No virtblk */
- for (mic->mic_virtblk.signaled = 0;
- !mic->mic_virtblk.signaled;)
- sleep(1);
- continue;
- }
-
- /* backend file is specified. */
- if (!start_virtblk(mic, &vring))
- goto _close_backend;
- iovec = malloc(sizeof(*iovec) *
- le32toh(virtblk_dev_page.blk_config.seg_max));
- if (!iovec) {
- mpsslog("%s: can't alloc iovec: %s\n",
- mic->name, strerror(ENOMEM));
- goto _stop_virtblk;
- }
-
- block_poll.fd = mic->mic_virtblk.virtio_block_fd;
- block_poll.events = POLLIN;
- for (mic->mic_virtblk.signaled = 0;
- !mic->mic_virtblk.signaled;) {
- block_poll.revents = 0;
- /* timeout in 1 sec to see signaled */
- ret = poll(&block_poll, 1, 1000);
- if (ret < 0) {
- mpsslog("%s %d: poll failed: %s\n",
- __func__, __LINE__,
- strerror(errno));
- continue;
- }
-
- if (!(block_poll.revents & POLLIN)) {
-#ifdef DEBUG
- mpsslog("%s %d: block_poll.revents=0x%x\n",
- __func__, __LINE__, block_poll.revents);
-#endif
- continue;
- }
-
- /* POLLIN */
- while (vring.info->avail_idx !=
- le16toh(vring.vr.avail->idx)) {
- /* read header element */
- avail_idx =
- vring.info->avail_idx &
- (vring.vr.num - 1);
- desc_idx = le16toh(
- vring.vr.avail->ring[avail_idx]);
- desc = &vring.vr.desc[desc_idx];
-#ifdef DEBUG
- mpsslog("%s() %d: avail_idx=%d ",
- __func__, __LINE__,
- vring.info->avail_idx);
- mpsslog("vring.vr.num=%d desc=%p\n",
- vring.vr.num, desc);
-#endif
- status = header_error_check(desc);
- ret = read_header(
- mic->mic_virtblk.virtio_block_fd,
- &hdr, desc_idx);
- if (ret < 0) {
- mpsslog("%s() %d %s: ret=%d %s\n",
- __func__, __LINE__,
- mic->name, ret,
- strerror(errno));
- break;
- }
- /* buffer element */
- piov = iovec;
- status = 0;
- fos = mic->mic_virtblk.backend_addr +
- (hdr.sector * SECTOR_SIZE);
- buffer_desc_idx = next_desc(desc);
- desc_idx = buffer_desc_idx;
- for (desc = &vring.vr.desc[buffer_desc_idx];
- desc->flags & VRING_DESC_F_NEXT;
- desc_idx = next_desc(desc),
- desc = &vring.vr.desc[desc_idx]) {
- piov->iov_len = desc->len;
- piov->iov_base = fos;
- piov++;
- fos += desc->len;
- }
- /* Returning NULLs for VIRTIO_BLK_T_GET_ID. */
- if (hdr.type & ~(VIRTIO_BLK_T_OUT |
- VIRTIO_BLK_T_GET_ID)) {
- /*
- VIRTIO_BLK_T_IN - does not do
- anything. Probably for documenting.
- VIRTIO_BLK_T_SCSI_CMD - for
- virtio_scsi.
- VIRTIO_BLK_T_FLUSH - turned off in
- config space.
- VIRTIO_BLK_T_BARRIER - defined but not
- used in anywhere.
- */
- mpsslog("%s() %d: type %x ",
- __func__, __LINE__,
- hdr.type);
- mpsslog("is not supported\n");
- status = -ENOTSUP;
-
- } else {
- ret = transfer_blocks(
- mic->mic_virtblk.virtio_block_fd,
- iovec,
- piov - iovec);
- if (ret < 0 &&
- status != 0)
- status = ret;
- }
- /* write status and update used pointer */
- if (status != 0)
- status = status_error_check(desc);
- ret = write_status(
- mic->mic_virtblk.virtio_block_fd,
- &status);
-#ifdef DEBUG
- mpsslog("%s() %d: write status=%d on desc=%p\n",
- __func__, __LINE__,
- status, desc);
-#endif
- }
- }
- free(iovec);
-_stop_virtblk:
- stop_virtblk(mic);
-_close_backend:
- close_backend(mic);
- } /* forever */
-
- pthread_exit(NULL);
-}
-
-static void
-reset(struct mic_info *mic)
-{
-#define RESET_TIMEOUT 120
- int i = RESET_TIMEOUT;
- setsysfs(mic->name, "state", "reset");
- while (i) {
- char *state;
- state = readsysfs(mic->name, "state");
- if (!state)
- goto retry;
- mpsslog("%s: %s %d state %s\n",
- mic->name, __func__, __LINE__, state);
-
- if (!strcmp(state, "ready")) {
- free(state);
- break;
- }
- free(state);
-retry:
- sleep(1);
- i--;
- }
-}
-
-static int
-get_mic_shutdown_status(struct mic_info *mic, char *shutdown_status)
-{
- if (!strcmp(shutdown_status, "nop"))
- return MIC_NOP;
- if (!strcmp(shutdown_status, "crashed"))
- return MIC_CRASHED;
- if (!strcmp(shutdown_status, "halted"))
- return MIC_HALTED;
- if (!strcmp(shutdown_status, "poweroff"))
- return MIC_POWER_OFF;
- if (!strcmp(shutdown_status, "restart"))
- return MIC_RESTART;
- mpsslog("%s: BUG invalid status %s\n", mic->name, shutdown_status);
- /* Invalid state */
- assert(0);
-};
-
-static int get_mic_state(struct mic_info *mic)
-{
- char *state = NULL;
- enum mic_states mic_state;
-
- while (!state) {
- state = readsysfs(mic->name, "state");
- sleep(1);
- }
- mpsslog("%s: %s %d state %s\n",
- mic->name, __func__, __LINE__, state);
-
- if (!strcmp(state, "ready")) {
- mic_state = MIC_READY;
- } else if (!strcmp(state, "booting")) {
- mic_state = MIC_BOOTING;
- } else if (!strcmp(state, "online")) {
- mic_state = MIC_ONLINE;
- } else if (!strcmp(state, "shutting_down")) {
- mic_state = MIC_SHUTTING_DOWN;
- } else if (!strcmp(state, "reset_failed")) {
- mic_state = MIC_RESET_FAILED;
- } else if (!strcmp(state, "resetting")) {
- mic_state = MIC_RESETTING;
- } else {
- mpsslog("%s: BUG invalid state %s\n", mic->name, state);
- assert(0);
- }
-
- free(state);
- return mic_state;
-};
-
-static void mic_handle_shutdown(struct mic_info *mic)
-{
-#define SHUTDOWN_TIMEOUT 60
- int i = SHUTDOWN_TIMEOUT;
- char *shutdown_status;
- while (i) {
- shutdown_status = readsysfs(mic->name, "shutdown_status");
- if (!shutdown_status) {
- sleep(1);
- continue;
- }
- mpsslog("%s: %s %d shutdown_status %s\n",
- mic->name, __func__, __LINE__, shutdown_status);
- switch (get_mic_shutdown_status(mic, shutdown_status)) {
- case MIC_RESTART:
- mic->restart = 1;
- case MIC_HALTED:
- case MIC_POWER_OFF:
- case MIC_CRASHED:
- free(shutdown_status);
- goto reset;
- default:
- break;
- }
- free(shutdown_status);
- sleep(1);
- i--;
- }
-reset:
- if (!i)
- mpsslog("%s: %s %d timing out waiting for shutdown_status %s\n",
- mic->name, __func__, __LINE__, shutdown_status);
- reset(mic);
-}
-
-static int open_state_fd(struct mic_info *mic)
-{
- char pathname[PATH_MAX];
- int fd;
-
- snprintf(pathname, PATH_MAX - 1, "%s/%s/%s",
- MICSYSFSDIR, mic->name, "state");
-
- fd = open(pathname, O_RDONLY);
- if (fd < 0)
- mpsslog("%s: opening file %s failed %s\n",
- mic->name, pathname, strerror(errno));
- return fd;
-}
-
-static int block_till_state_change(int fd, struct mic_info *mic)
-{
- struct pollfd ufds[1];
- char value[PAGE_SIZE];
- int ret;
-
- ufds[0].fd = fd;
- ufds[0].events = POLLERR | POLLPRI;
- ret = poll(ufds, 1, -1);
- if (ret < 0) {
- mpsslog("%s: %s %d poll failed %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- return ret;
- }
-
- ret = lseek(fd, 0, SEEK_SET);
- if (ret < 0) {
- mpsslog("%s: %s %d Failed to seek to 0: %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- return ret;
- }
-
- ret = read(fd, value, sizeof(value));
- if (ret < 0) {
- mpsslog("%s: %s %d Failed to read sysfs entry: %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- return ret;
- }
-
- return 0;
-}
-
-static void *
-mic_config(void *arg)
-{
- struct mic_info *mic = (struct mic_info *)arg;
- int fd, ret, stat = 0;
-
- fd = open_state_fd(mic);
- if (fd < 0) {
- mpsslog("%s: %s %d open state fd failed %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- goto exit;
- }
-
- do {
- ret = block_till_state_change(fd, mic);
- if (ret < 0) {
- mpsslog("%s: %s %d block_till_state_change error %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- goto close_exit;
- }
-
- switch (get_mic_state(mic)) {
- case MIC_SHUTTING_DOWN:
- mic_handle_shutdown(mic);
- break;
- case MIC_READY:
- case MIC_RESET_FAILED:
- ret = kill(mic->pid, SIGTERM);
- mpsslog("%s: %s %d kill pid %d ret %d\n",
- mic->name, __func__, __LINE__,
- mic->pid, ret);
- if (!ret) {
- ret = waitpid(mic->pid, &stat,
- WIFSIGNALED(stat));
- mpsslog("%s: %s %d waitpid ret %d pid %d\n",
- mic->name, __func__, __LINE__,
- ret, mic->pid);
- }
- if (mic->boot_on_resume) {
- setsysfs(mic->name, "state", "boot");
- mic->boot_on_resume = 0;
- }
- goto close_exit;
- default:
- break;
- }
- } while (1);
-
-close_exit:
- close(fd);
-exit:
- init_mic(mic);
- pthread_exit(NULL);
-}
-
-static void
-set_cmdline(struct mic_info *mic)
-{
- char buffer[PATH_MAX];
- int len;
-
- len = snprintf(buffer, PATH_MAX,
- "clocksource=tsc highres=off nohz=off ");
- len += snprintf(buffer + len, PATH_MAX - len,
- "cpufreq_on;corec6_off;pc3_off;pc6_off ");
- len += snprintf(buffer + len, PATH_MAX - len,
- "ifcfg=static;address,172.31.%d.1;netmask,255.255.255.0",
- mic->id + 1);
-
- setsysfs(mic->name, "cmdline", buffer);
- mpsslog("%s: Command line: \"%s\"\n", mic->name, buffer);
- snprintf(buffer, PATH_MAX, "172.31.%d.1", mic->id + 1);
- mpsslog("%s: IPADDR: \"%s\"\n", mic->name, buffer);
-}
-
-static void
-set_log_buf_info(struct mic_info *mic)
-{
- int fd;
- off_t len;
- char system_map[] = "/lib/firmware/mic/System.map";
- char *map, *temp, log_buf[17] = {'\0'};
-
- fd = open(system_map, O_RDONLY);
- if (fd < 0) {
- mpsslog("%s: Opening System.map failed: %d\n",
- mic->name, errno);
- return;
- }
- len = lseek(fd, 0, SEEK_END);
- if (len < 0) {
- mpsslog("%s: Reading System.map size failed: %d\n",
- mic->name, errno);
- close(fd);
- return;
- }
- map = mmap(NULL, len, PROT_READ, MAP_PRIVATE, fd, 0);
- if (map == MAP_FAILED) {
- mpsslog("%s: mmap of System.map failed: %d\n",
- mic->name, errno);
- close(fd);
- return;
- }
- temp = strstr(map, "__log_buf");
- if (!temp) {
- mpsslog("%s: __log_buf not found: %d\n", mic->name, errno);
- munmap(map, len);
- close(fd);
- return;
- }
- strncpy(log_buf, temp - 19, 16);
- setsysfs(mic->name, "log_buf_addr", log_buf);
- mpsslog("%s: log_buf_addr: %s\n", mic->name, log_buf);
- temp = strstr(map, "log_buf_len");
- if (!temp) {
- mpsslog("%s: log_buf_len not found: %d\n", mic->name, errno);
- munmap(map, len);
- close(fd);
- return;
- }
- strncpy(log_buf, temp - 19, 16);
- setsysfs(mic->name, "log_buf_len", log_buf);
- mpsslog("%s: log_buf_len: %s\n", mic->name, log_buf);
- munmap(map, len);
- close(fd);
-}
-
-static void
-change_virtblk_backend(int x, siginfo_t *siginfo, void *p)
-{
- struct mic_info *mic;
-
- for (mic = mic_list.next; mic != NULL; mic = mic->next)
- mic->mic_virtblk.signaled = 1/* true */;
-}
-
-static void
-set_mic_boot_params(struct mic_info *mic)
-{
- set_log_buf_info(mic);
- set_cmdline(mic);
-}
-
-static void *
-init_mic(void *arg)
-{
- struct mic_info *mic = (struct mic_info *)arg;
- struct sigaction ignore = {
- .sa_flags = 0,
- .sa_handler = SIG_IGN
- };
- struct sigaction act = {
- .sa_flags = SA_SIGINFO,
- .sa_sigaction = change_virtblk_backend,
- };
- char buffer[PATH_MAX];
- int err, fd;
-
- /*
- * Currently, one virtio block device is supported for each MIC card
- * at a time. Any user (or test) can send a SIGUSR1 to the MIC daemon.
- * The signal informs the virtio block backend about a change in the
- * configuration file which specifies the virtio backend file name on
- * the host. Virtio block backend then re-reads the configuration file
- * and switches to the new block device. This signalling mechanism may
- * not be required once multiple virtio block devices are supported by
- * the MIC daemon.
- */
- sigaction(SIGUSR1, &ignore, NULL);
-retry:
- fd = open_state_fd(mic);
- if (fd < 0) {
- mpsslog("%s: %s %d open state fd failed %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- sleep(2);
- goto retry;
- }
-
- if (mic->restart) {
- snprintf(buffer, PATH_MAX, "boot");
- setsysfs(mic->name, "state", buffer);
- mpsslog("%s restarting mic %d\n",
- mic->name, mic->restart);
- mic->restart = 0;
- }
-
- while (1) {
- while (block_till_state_change(fd, mic)) {
- mpsslog("%s: %s %d block_till_state_change error %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- sleep(2);
- continue;
- }
-
- if (get_mic_state(mic) == MIC_BOOTING)
- break;
- }
-
- mic->pid = fork();
- switch (mic->pid) {
- case 0:
- add_virtio_device(mic, &virtcons_dev_page.dd);
- add_virtio_device(mic, &virtnet_dev_page.dd);
- err = pthread_create(&mic->mic_console.console_thread, NULL,
- virtio_console, mic);
- if (err)
- mpsslog("%s virtcons pthread_create failed %s\n",
- mic->name, strerror(err));
- err = pthread_create(&mic->mic_net.net_thread, NULL,
- virtio_net, mic);
- if (err)
- mpsslog("%s virtnet pthread_create failed %s\n",
- mic->name, strerror(err));
- err = pthread_create(&mic->mic_virtblk.block_thread, NULL,
- virtio_block, mic);
- if (err)
- mpsslog("%s virtblk pthread_create failed %s\n",
- mic->name, strerror(err));
- sigemptyset(&act.sa_mask);
- err = sigaction(SIGUSR1, &act, NULL);
- if (err)
- mpsslog("%s sigaction SIGUSR1 failed %s\n",
- mic->name, strerror(errno));
- while (1)
- sleep(60);
- case -1:
- mpsslog("fork failed MIC name %s id %d errno %d\n",
- mic->name, mic->id, errno);
- break;
- default:
- err = pthread_create(&mic->config_thread, NULL,
- mic_config, mic);
- if (err)
- mpsslog("%s mic_config pthread_create failed %s\n",
- mic->name, strerror(err));
- }
-
- return NULL;
-}
-
-static void
-start_daemon(void)
-{
- struct mic_info *mic;
- int err;
-
- for (mic = mic_list.next; mic; mic = mic->next) {
- set_mic_boot_params(mic);
- err = pthread_create(&mic->init_thread, NULL, init_mic, mic);
- if (err)
- mpsslog("%s init_mic pthread_create failed %s\n",
- mic->name, strerror(err));
- }
-
- while (1)
- sleep(60);
-}
-
-static int
-init_mic_list(void)
-{
- struct mic_info *mic = &mic_list;
- struct dirent *file;
- DIR *dp;
- int cnt = 0;
-
- dp = opendir(MICSYSFSDIR);
- if (!dp)
- return 0;
-
- while ((file = readdir(dp)) != NULL) {
- if (!strncmp(file->d_name, "mic", 3)) {
- mic->next = calloc(1, sizeof(struct mic_info));
- if (mic->next) {
- mic = mic->next;
- mic->id = atoi(&file->d_name[3]);
- mic->name = malloc(strlen(file->d_name) + 16);
- if (mic->name)
- strcpy(mic->name, file->d_name);
- mpsslog("MIC name %s id %d\n", mic->name,
- mic->id);
- cnt++;
- }
- }
- }
-
- closedir(dp);
- return cnt;
-}
-
-void
-mpsslog(char *format, ...)
-{
- va_list args;
- char buffer[4096];
- char ts[52], *ts1;
- time_t t;
-
- if (logfp == NULL)
- return;
-
- va_start(args, format);
- vsprintf(buffer, format, args);
- va_end(args);
-
- time(&t);
- ts1 = ctime_r(&t, ts);
- ts1[strlen(ts1) - 1] = '\0';
- fprintf(logfp, "%s: %s", ts1, buffer);
-
- fflush(logfp);
-}
-
-int
-main(int argc, char *argv[])
-{
- int cnt;
- pid_t pid;
-
- myname = argv[0];
-
- logfp = fopen(LOGFILE_NAME, "a+");
- if (!logfp) {
- fprintf(stderr, "cannot open logfile '%s'\n", LOGFILE_NAME);
- exit(1);
- }
- pid = fork();
- switch (pid) {
- case 0:
- break;
- case -1:
- exit(2);
- default:
- exit(0);
- }
-
- mpsslog("MIC Daemon start\n");
-
- cnt = init_mic_list();
- if (cnt == 0) {
- mpsslog("MIC module not loaded\n");
- exit(3);
- }
- mpsslog("MIC found %d devices\n", cnt);
-
- start_daemon();
-
- exit(0);
-}
diff --git a/samples/mic/mpssd/mpssd.h b/samples/mic/mpssd/mpssd.h
deleted file mode 100644
index 5f98bda..0000000
--- a/samples/mic/mpssd/mpssd.h
+++ /dev/null
@@ -1,89 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC User Space Tools.
- */
-#ifndef _MPSSD_H_
-#define _MPSSD_H_
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <fcntl.h>
-#include <unistd.h>
-#include <dirent.h>
-#include <libgen.h>
-#include <pthread.h>
-#include <stdarg.h>
-#include <time.h>
-#include <errno.h>
-#include <sys/dir.h>
-#include <sys/ioctl.h>
-#include <sys/poll.h>
-#include <sys/types.h>
-#include <sys/socket.h>
-#include <sys/stat.h>
-#include <sys/mman.h>
-#include <sys/utsname.h>
-#include <sys/wait.h>
-#include <netinet/in.h>
-#include <arpa/inet.h>
-#include <netdb.h>
-#include <signal.h>
-#include <limits.h>
-#include <syslog.h>
-#include <getopt.h>
-#include <net/if.h>
-#include <linux/if_tun.h>
-#include <linux/virtio_ids.h>
-
-#define MICSYSFSDIR "/sys/class/mic"
-#define LOGFILE_NAME "/var/log/mpssd"
-#define PAGE_SIZE 4096
-
-struct mic_console_info {
- pthread_t console_thread;
- int virtio_console_fd;
- void *console_dp;
-};
-
-struct mic_net_info {
- pthread_t net_thread;
- int virtio_net_fd;
- int tap_fd;
- void *net_dp;
-};
-
-struct mic_virtblk_info {
- pthread_t block_thread;
- int virtio_block_fd;
- void *block_dp;
- volatile sig_atomic_t signaled;
- char *backend_file;
- int backend;
- void *backend_addr;
- long backend_size;
-};
-
-struct mic_info {
- int id;
- char *name;
- pthread_t config_thread;
- pthread_t init_thread;
- pid_t pid;
- struct mic_console_info mic_console;
- struct mic_net_info mic_net;
- struct mic_virtblk_info mic_virtblk;
- int restart;
- int boot_on_resume;
- struct mic_info *next;
-};
-
-__attribute__((format(printf, 1, 2)))
-void mpsslog(char *format, ...);
-char *readsysfs(char *dir, char *entry);
-int setsysfs(char *dir, char *entry, char *value);
-#endif
diff --git a/samples/mic/mpssd/sysfs.c b/samples/mic/mpssd/sysfs.c
deleted file mode 100644
index 3fb08eb..0000000
--- a/samples/mic/mpssd/sysfs.c
+++ /dev/null
@@ -1,91 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC User Space Tools.
- */
-
-#include "mpssd.h"
-
-#define PAGE_SIZE 4096
-
-char *
-readsysfs(char *dir, char *entry)
-{
- char filename[PATH_MAX];
- char value[PAGE_SIZE];
- char *string = NULL;
- int fd;
- int len;
-
- if (dir == NULL)
- snprintf(filename, PATH_MAX, "%s/%s", MICSYSFSDIR, entry);
- else
- snprintf(filename, PATH_MAX,
- "%s/%s/%s", MICSYSFSDIR, dir, entry);
-
- fd = open(filename, O_RDONLY);
- if (fd < 0) {
- mpsslog("Failed to open sysfs entry '%s': %s\n",
- filename, strerror(errno));
- return NULL;
- }
-
- len = read(fd, value, sizeof(value));
- if (len < 0) {
- mpsslog("Failed to read sysfs entry '%s': %s\n",
- filename, strerror(errno));
- goto readsys_ret;
- }
- if (len == 0)
- goto readsys_ret;
-
- value[len - 1] = '\0';
-
- string = malloc(strlen(value) + 1);
- if (string)
- strcpy(string, value);
-
-readsys_ret:
- close(fd);
- return string;
-}
-
-int
-setsysfs(char *dir, char *entry, char *value)
-{
- char filename[PATH_MAX];
- char *oldvalue;
- int fd, ret = 0;
-
- if (dir == NULL)
- snprintf(filename, PATH_MAX, "%s/%s", MICSYSFSDIR, entry);
- else
- snprintf(filename, PATH_MAX, "%s/%s/%s",
- MICSYSFSDIR, dir, entry);
-
- oldvalue = readsysfs(dir, entry);
-
- fd = open(filename, O_RDWR);
- if (fd < 0) {
- ret = errno;
- mpsslog("Failed to open sysfs entry '%s': %s\n",
- filename, strerror(errno));
- goto done;
- }
-
- if (!oldvalue || strcmp(value, oldvalue)) {
- if (write(fd, value, strlen(value)) < 0) {
- ret = errno;
- mpsslog("Failed to write new sysfs entry '%s': %s\n",
- filename, strerror(errno));
- }
- }
- close(fd);
-done:
- if (oldvalue)
- free(oldvalue);
- return ret;
-}
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 6769caa..3148437 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -408,6 +408,7 @@
'struct bpf_perf_event_data',
'struct bpf_perf_event_value',
'struct bpf_pidns_info',
+ 'struct bpf_redir_neigh',
'struct bpf_sock',
'struct bpf_sock_addr',
'struct bpf_sock_ops',
diff --git a/scripts/get_abi.pl b/scripts/get_abi.pl
index c738cb79..68dab82 100755
--- a/scripts/get_abi.pl
+++ b/scripts/get_abi.pl
@@ -2,18 +2,28 @@
# SPDX-License-Identifier: GPL-2.0
use strict;
+use warnings;
+use utf8;
use Pod::Usage;
use Getopt::Long;
use File::Find;
use Fcntl ':mode';
-my $help;
-my $man;
-my $debug;
+my $help = 0;
+my $man = 0;
+my $debug = 0;
+my $enable_lineno = 0;
my $prefix="Documentation/ABI";
+#
+# If true, assumes that the description is formatted with ReST
+#
+my $description_is_rst = 1;
+
GetOptions(
"debug|d+" => \$debug,
+ "enable-lineno" => \$enable_lineno,
+ "rst-source!" => \$description_is_rst,
"dir=s" => \$prefix,
'help|?' => \$help,
man => \$man
@@ -32,6 +42,7 @@
require Data::Dumper if ($debug);
my %data;
+my %symbols;
#
# Displays an error message, printing file name and line
@@ -39,7 +50,15 @@
sub parse_error($$$$) {
my ($file, $ln, $msg, $data) = @_;
- print STDERR "file $file#$ln: $msg at\n\t$data";
+ $data =~ s/\s+$/\n/;
+
+ print STDERR "Warning: file $file#$ln:\n\t$msg";
+
+ if ($data ne "") {
+ print STDERR ". Line\n\t\t$data";
+ } else {
+ print STDERR "\n";
+ }
}
#
@@ -55,24 +74,28 @@
my $name = $file;
$name =~ s,.*/,,;
- my $nametag = "File $name";
+ my $fn = $file;
+ $fn =~ s,Documentation/ABI/,,;
+
+ my $nametag = "File $fn";
$data{$nametag}->{what} = "File $name";
$data{$nametag}->{type} = "File";
$data{$nametag}->{file} = $name;
$data{$nametag}->{filepath} = $file;
$data{$nametag}->{is_file} = 1;
+ $data{$nametag}->{line_no} = 1;
my $type = $file;
$type =~ s,.*/(.*)/.*,$1,;
my $what;
my $new_what;
- my $tag;
+ my $tag = "";
my $ln;
my $xrefs;
my $space;
my @labels;
- my $label;
+ my $label = "";
print STDERR "Opening $file\n" if ($debug > 1);
open IN, $file;
@@ -95,16 +118,26 @@
# Invalid, but it is a common mistake
if ($new_tag eq "where") {
- parse_error($file, $ln, "tag 'Where' is invalid. Should be 'What:' instead", $_);
+ parse_error($file, $ln, "tag 'Where' is invalid. Should be 'What:' instead", "");
$new_tag = "what";
}
if ($new_tag =~ m/what/) {
$space = "";
+ $content =~ s/[,.;]$//;
+
+ push @{$symbols{$content}->{file}}, " $file:" . ($ln - 1);
+
if ($tag =~ m/what/) {
$what .= ", " . $content;
} else {
- parse_error($file, $ln, "What '$what' doesn't have a description", "") if ($what && !$data{$what}->{description});
+ if ($what) {
+ parse_error($file, $ln, "What '$what' doesn't have a description", "") if (!$data{$what}->{description});
+
+ foreach my $w(split /, /, $what) {
+ $symbols{$w}->{xref} = $what;
+ };
+ }
$what = $content;
$label = $content;
@@ -113,7 +146,7 @@
push @labels, [($content, $label)];
$tag = $new_tag;
- push @{$data{$nametag}->{xrefs}}, [($content, $label)] if ($data{$nametag}->{what});
+ push @{$data{$nametag}->{symbols}}, $content if ($data{$nametag}->{what});
next;
}
@@ -121,30 +154,44 @@
$tag = $new_tag;
if ($new_what) {
- @{$data{$what}->{label}} = @labels if ($data{$nametag}->{what});
+ @{$data{$what}->{label_list}} = @labels if ($data{$nametag}->{what});
@labels = ();
$label = "";
$new_what = 0;
$data{$what}->{type} = $type;
- $data{$what}->{file} = $name;
- $data{$what}->{filepath} = $file;
+ if (!defined($data{$what}->{file})) {
+ $data{$what}->{file} = $name;
+ $data{$what}->{filepath} = $file;
+ } else {
+ if ($name ne $data{$what}->{file}) {
+ $data{$what}->{file} .= " " . $name;
+ $data{$what}->{filepath} .= " " . $file;
+ }
+ }
print STDERR "\twhat: $what\n" if ($debug > 1);
+ $data{$what}->{line_no} = $ln;
+ } else {
+ $data{$what}->{line_no} = $ln if (!defined($data{$what}->{line_no}));
}
if (!$what) {
parse_error($file, $ln, "'What:' should come first:", $_);
next;
}
- if ($tag eq "description") {
- next if ($content =~ m/^\s*$/);
- if ($content =~ m/^(\s*)(.*)/) {
- my $new_content = $2;
- $space = $new_tag . $sep . $1;
- while ($space =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {}
- $space =~ s/./ /g;
- $data{$what}->{$tag} .= "$new_content\n";
+ if ($new_tag eq "description") {
+ $sep =~ s,:, ,;
+ $content = ' ' x length($new_tag) . $sep . $content;
+ while ($content =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {}
+ if ($content =~ m/^(\s*)(\S.*)$/) {
+ # Preserve initial spaces for the first line
+ $space = $1;
+ $content = "$2\n";
+ $data{$what}->{$tag} .= $content;
+ } else {
+ undef($space);
}
+
} else {
$data{$what}->{$tag} = $content;
}
@@ -159,29 +206,24 @@
}
if ($tag eq "description") {
- if (!$data{$what}->{description}) {
- next if (m/^\s*\n/);
- if (m/^(\s*)(.*)/) {
+ my $content = $_;
+ while ($content =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {}
+ if (m/^\s*\n/) {
+ $data{$what}->{$tag} .= "\n";
+ next;
+ }
+
+ if (!defined($space)) {
+ # Preserve initial spaces for the first line
+ if ($content =~ m/^(\s*)(\S.*)$/) {
$space = $1;
- while ($space =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {}
- $data{$what}->{$tag} .= "$2\n";
+ $content = "$2\n";
}
} else {
- my $content = $_;
- if (m/^\s*\n/) {
- $data{$what}->{$tag} .= $content;
- next;
- }
-
- while ($content =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {}
$space = "" if (!($content =~ s/^($space)//));
-
- # Compress spaces with tabs
- $content =~ s<^ {8}> <\t>;
- $content =~ s<^ {1,7}\t> <\t>;
- $content =~ s< {1,7}\t> <\t>;
- $data{$what}->{$tag} .= $content;
}
+ $data{$what}->{$tag} .= $content;
+
next;
}
if (m/^\s*(.*)/) {
@@ -191,32 +233,26 @@
}
# Everything else is error
- parse_error($file, $ln, "Unexpected line:", $_);
+ parse_error($file, $ln, "Unexpected content", $_);
}
- $data{$nametag}->{description} =~ s/^\n+//;
+ $data{$nametag}->{description} =~ s/^\n+// if ($data{$nametag}->{description});
+ if ($what) {
+ parse_error($file, $ln, "What '$what' doesn't have a description", "") if (!$data{$what}->{description});
+
+ foreach my $w(split /, /,$what) {
+ $symbols{$w}->{xref} = $what;
+ };
+ }
close IN;
}
-#
-# Outputs the book on ReST format
-#
+sub create_labels {
+ my %labels;
-my %labels;
+ foreach my $what (keys %data) {
+ next if ($data{$what}->{file} eq "File");
-sub output_rest {
- foreach my $what (sort {
- ($data{$a}->{type} eq "File") cmp ($data{$b}->{type} eq "File") ||
- $a cmp $b
- } keys %data) {
- my $type = $data{$what}->{type};
- my $file = $data{$what}->{file};
- my $filepath = $data{$what}->{filepath};
-
- my $w = $what;
- $w =~ s/([\(\)\_\-\*\=\^\~\\])/\\$1/g;
-
-
- foreach my $p (@{$data{$what}->{label}}) {
+ foreach my $p (@{$data{$what}->{label_list}}) {
my ($content, $label) = @{$p};
$label = "abi_" . $label . " ";
$label =~ tr/A-Z/a-z/;
@@ -233,81 +269,167 @@
}
$labels{$label} = 1;
- $data{$what}->{label} .= $label;
-
- printf ".. _%s:\n\n", $label;
+ $data{$what}->{label} = $label;
# only one label is enough
last;
}
+ }
+}
+#
+# Outputs the book on ReST format
+#
- $filepath =~ s,.*/(.*/.*),\1,;;
- $filepath =~ s,[/\-],_,g;;
- my $fileref = "abi_file_".$filepath;
+# \b doesn't work well with paths. So, we need to define something else
+my $bondary = qr { (?<![\w\/\`\{])(?=[\w\/\`\{])|(?<=[\w\/\`\{])(?![\w\/\`\{]) }x;
- if ($type eq "File") {
- my $bar = $w;
- $bar =~ s/./-/g;
+sub output_rest {
+ create_labels();
- print ".. _$fileref:\n\n";
- print "$w\n$bar\n\n";
- } else {
- my @names = split /\s*,\s*/,$w;
+ my $part = "";
+ foreach my $what (sort {
+ ($data{$a}->{type} eq "File") cmp ($data{$b}->{type} eq "File") ||
+ $a cmp $b
+ } keys %data) {
+ my $type = $data{$what}->{type};
+
+ my @file = split / /, $data{$what}->{file};
+ my @filepath = split / /, $data{$what}->{filepath};
+
+ if ($enable_lineno) {
+ printf "#define LINENO %s%s#%s\n\n",
+ $prefix, $file[0],
+ $data{$what}->{line_no};
+ }
+
+ my $w = $what;
+ $w =~ s/([\(\)\_\-\*\=\^\~\\])/\\$1/g;
+
+ if ($type ne "File") {
+ my $cur_part = $what;
+ if ($what =~ '/') {
+ if ($what =~ m#^(\/?(?:[\w\-]+\/?){1,2})#) {
+ $cur_part = "Symbols under $1";
+ $cur_part =~ s,/$,,;
+ }
+ }
+
+ if ($cur_part ne "" && $part ne $cur_part) {
+ $part = $cur_part;
+ my $bar = $part;
+ $bar =~ s/./-/g;
+ print "$part\n$bar\n\n";
+ }
+
+ printf ".. _%s:\n\n", $data{$what}->{label};
+
+ my @names = split /, /,$w;
my $len = 0;
foreach my $name (@names) {
+ $name = "**$name**";
$len = length($name) if (length($name) > $len);
}
- print "What:\n\n";
-
print "+-" . "-" x $len . "-+\n";
foreach my $name (@names) {
printf "| %s", $name . " " x ($len - length($name)) . " |\n";
print "+-" . "-" x $len . "-+\n";
}
+
print "\n";
}
- print "Defined on file :ref:`$file <$fileref>`\n\n" if ($type ne "File");
+ for (my $i = 0; $i < scalar(@filepath); $i++) {
+ my $path = $filepath[$i];
+ my $f = $file[$i];
- my $desc = $data{$what}->{description};
- $desc =~ s/^\s+//;
+ $path =~ s,.*/(.*/.*),$1,;;
+ $path =~ s,[/\-],_,g;;
+ my $fileref = "abi_file_".$path;
- # Remove title markups from the description, as they won't work
- $desc =~ s/\n[\-\*\=\^\~]+\n/\n/g;
+ if ($type eq "File") {
+ print ".. _$fileref:\n\n";
+ } else {
+ print "Defined on file :ref:`$f <$fileref>`\n\n";
+ }
+ }
+
+ if ($type eq "File") {
+ my $bar = $w;
+ $bar =~ s/./-/g;
+ print "$w\n$bar\n\n";
+ }
+
+ my $desc = "";
+ $desc = $data{$what}->{description} if (defined($data{$what}->{description}));
+ $desc =~ s/\s+$/\n/;
if (!($desc =~ /^\s*$/)) {
- if ($desc =~ m/\:\n/ || $desc =~ m/\n[\t ]+/ || $desc =~ m/[\x00-\x08\x0b-\x1f\x7b-\xff]/) {
- # put everything inside a code block
- $desc =~ s/\n/\n /g;
+ if ($description_is_rst) {
+ # Remove title markups from the description
+ # Having titles inside ABI files will only work if extra
+ # care would be taken in order to strictly follow the same
+ # level order for each markup.
+ $desc =~ s/\n[\-\*\=\^\~]+\n/\n\n/g;
- print "::\n\n";
- print " $desc\n\n";
- } else {
- # Escape any special chars from description
- $desc =~s/([\x00-\x08\x0b-\x1f\x21-\x2a\x2d\x2f\x3c-\x40\x5c\x5e-\x60\x7b-\xff])/\\$1/g;
+ # Enrich text by creating cross-references
+
+ $desc =~ s,Documentation/(?!devicetree)(\S+)\.rst,:doc:`/$1`,g;
+
+ my @matches = $desc =~ m,Documentation/ABI/([\w\/\-]+),;
+ foreach my $f (@matches) {
+ my $xref = $f;
+ my $path = $f;
+ $path =~ s,.*/(.*/.*),$1,;;
+ $path =~ s,[/\-],_,g;;
+ $xref .= " <abi_file_" . $path . ">";
+ $desc =~ s,\bDocumentation/ABI/$f\b,:ref:`$xref`,g;
+ }
+
+ @matches = $desc =~ m,$bondary(/sys/[^\s\.\,\;\:\*\s\`\'\(\)]+)$bondary,;
+
+ foreach my $s (@matches) {
+ if (defined($data{$s}) && defined($data{$s}->{label})) {
+ my $xref = $s;
+
+ $xref =~ s/([\x00-\x1f\x21-\x2f\x3a-\x40\x7b-\xff])/\\$1/g;
+ $xref = ":ref:`$xref <" . $data{$s}->{label} . ">`";
+
+ $desc =~ s,$bondary$s$bondary,$xref,g;
+ }
+ }
print "$desc\n\n";
+ } else {
+ $desc =~ s/^\s+//;
+
+ # Remove title markups from the description, as they won't work
+ $desc =~ s/\n[\-\*\=\^\~]+\n/\n\n/g;
+
+ if ($desc =~ m/\:\n/ || $desc =~ m/\n[\t ]+/ || $desc =~ m/[\x00-\x08\x0b-\x1f\x7b-\xff]/) {
+ # put everything inside a code block
+ $desc =~ s/\n/\n /g;
+
+ print "::\n\n";
+ print " $desc\n\n";
+ } else {
+ # Escape any special chars from description
+ $desc =~s/([\x00-\x08\x0b-\x1f\x21-\x2a\x2d\x2f\x3c-\x40\x5c\x5e-\x60\x7b-\xff])/\\$1/g;
+ print "$desc\n\n";
+ }
}
} else {
print "DESCRIPTION MISSING for $what\n\n" if (!$data{$what}->{is_file});
}
- if ($data{$what}->{xrefs}) {
+ if ($data{$what}->{symbols}) {
printf "Has the following ABI:\n\n";
- foreach my $p(@{$data{$what}->{xrefs}}) {
- my ($content, $label) = @{$p};
- $label = "abi_" . $label . " ";
- $label =~ tr/A-Z/a-z/;
-
- # Convert special chars to "_"
- $label =~s/([\x00-\x2f\x3a-\x40\x5b-\x60\x7b-\xff])/_/g;
- $label =~ s,_+,_,g;
- $label =~ s,_$,,;
+ foreach my $content(@{$data{$what}->{symbols}}) {
+ my $label = $data{$symbols{$content}->{xref}}->{label};
# Escape special chars from content
$content =~s/([\x00-\x1f\x21-\x2f\x3a-\x40\x7b-\xff])/\\$1/g;
@@ -315,6 +437,14 @@
print "- :ref:`$content <$label>`\n\n";
}
}
+
+ if (defined($data{$what}->{users})) {
+ my $users = $data{$what}->{users};
+
+ $users =~ s/\n/\n\t/g;
+ printf "Users:\n\t%s\n\n", $users if ($users ne "");
+ }
+
}
}
@@ -335,27 +465,34 @@
print "\n$what\n$bar\n\n";
- my $kernelversion = $data{$what}->{kernelversion};
- my $contact = $data{$what}->{contact};
- my $users = $data{$what}->{users};
- my $date = $data{$what}->{date};
- my $desc = $data{$what}->{description};
- $kernelversion =~ s/^\s+//;
- $contact =~ s/^\s+//;
- $users =~ s/^\s+//;
- $users =~ s/\n//g;
- $date =~ s/^\s+//;
- $desc =~ s/^\s+//;
+ my $kernelversion = $data{$what}->{kernelversion} if (defined($data{$what}->{kernelversion}));
+ my $contact = $data{$what}->{contact} if (defined($data{$what}->{contact}));
+ my $users = $data{$what}->{users} if (defined($data{$what}->{users}));
+ my $date = $data{$what}->{date} if (defined($data{$what}->{date}));
+ my $desc = $data{$what}->{description} if (defined($data{$what}->{description}));
+
+ $kernelversion =~ s/^\s+// if ($kernelversion);
+ $contact =~ s/^\s+// if ($contact);
+ if ($users) {
+ $users =~ s/^\s+//;
+ $users =~ s/\n//g;
+ }
+ $date =~ s/^\s+// if ($date);
+ $desc =~ s/^\s+// if ($desc);
printf "Kernel version:\t\t%s\n", $kernelversion if ($kernelversion);
printf "Date:\t\t\t%s\n", $date if ($date);
printf "Contact:\t\t%s\n", $contact if ($contact);
printf "Users:\t\t\t%s\n", $users if ($users);
- print "Defined on file:\t$file\n\n";
+ print "Defined on file(s):\t$file\n\n";
print "Description:\n\n$desc";
}
}
+# Ensure that the prefix will always end with a slash
+# While this is not needed for find, it makes the patch nicer
+# with --enable-lineno
+$prefix =~ s,/?$,/,;
#
# Parses all ABI files located at $prefix dir
@@ -367,12 +504,23 @@
#
# Handles the command
#
-if ($cmd eq "rest") {
- output_rest;
-} elsif ($cmd eq "search") {
+if ($cmd eq "search") {
search_symbols;
-}
+} else {
+ if ($cmd eq "rest") {
+ output_rest;
+ }
+ # Warn about duplicated ABI entries
+ foreach my $what(sort keys %symbols) {
+ my @files = @{$symbols{$what}->{file}};
+
+ next if (scalar(@files) == 1);
+
+ printf STDERR "Warning: $what is defined %d times: @files\n",
+ scalar(@files);
+ }
+}
__END__
@@ -382,7 +530,8 @@
=head1 SYNOPSIS
-B<abi_book.pl> [--debug] [--man] [--help] [--dir=<dir>] <COMAND> [<ARGUMENT>]
+B<abi_book.pl> [--debug] [--enable-lineno] [--man] [--help]
+ [--(no-)rst-source] [--dir=<dir>] <COMAND> [<ARGUMENT>]
Where <COMMAND> can be:
@@ -405,6 +554,17 @@
Changes the location of the ABI search. By default, it uses
the Documentation/ABI directory.
+=item B<--rst-source> and B<--no-rst-source>
+
+The input file may be using ReST syntax or not. Those two options allow
+selecting between a rst-compliant source ABI (--rst-source), or a
+plain text that may be violating ReST spec, so it requres some escaping
+logic (--no-rst-source).
+
+=item B<--enable-lineno>
+
+Enable output of #define LINENO lines.
+
=item B<--debug>
Put the script in verbose mode, useful for debugging. Can be called multiple
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index c8f6b11..f699cf0 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -1092,7 +1092,11 @@
print "\n\n.. c:type:: " . $name . "\n\n";
} else {
my $name = $args{'struct'};
- print "\n\n.. c:struct:: " . $name . "\n\n";
+ if ($args{'type'} eq 'union') {
+ print "\n\n.. c:union:: " . $name . "\n\n";
+ } else {
+ print "\n\n.. c:struct:: " . $name . "\n\n";
+ }
}
print_lineno($declaration_start_line);
$lineprefix = " ";
@@ -1427,20 +1431,25 @@
}
}
+my $typedef_type = qr { ((?:\s+[\w\*]+){1,8})\s* }x;
+my $typedef_ident = qr { \*?\s*(\w\S+)\s* }x;
+my $typedef_args = qr { \s*\((.*)\); }x;
+
+my $typedef1 = qr { typedef$typedef_type\($typedef_ident\)$typedef_args }x;
+my $typedef2 = qr { typedef$typedef_type$typedef_ident$typedef_args }x;
+
sub dump_typedef($$) {
my $x = shift;
my $file = shift;
$x =~ s@/\*.*?\*/@@gos; # strip comments.
- # Parse function prototypes
- if ($x =~ /typedef\s+(\w+)\s*\(\*\s*(\w\S+)\s*\)\s*\((.*)\);/ ||
- $x =~ /typedef\s+(\w+)\s*(\w\S+)\s*\s*\((.*)\);/) {
-
- # Function typedefs
+ # Parse function typedef prototypes
+ if ($x =~ $typedef1 || $x =~ $typedef2) {
$return_type = $1;
$declaration_name = $2;
my $args = $3;
+ $return_type =~ s/^\s+//;
create_parameterlist($args, ',', $file, $declaration_name);
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 3804307..6ebefec 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -101,7 +101,7 @@
struct tpm_digest *digests;
struct ima_template_desc *template_desc; /* template descriptor */
u32 template_data_len;
- struct ima_field_data template_data[0]; /* template related data */
+ struct ima_field_data template_data[]; /* template related data */
};
struct ima_queue_entry {
diff --git a/security/selinux/ibpkey.c b/security/selinux/ibpkey.c
index f68a761..3a63a98 100644
--- a/security/selinux/ibpkey.c
+++ b/security/selinux/ibpkey.c
@@ -151,8 +151,10 @@
* is valid, it just won't be added to the cache.
*/
new = kzalloc(sizeof(*new), GFP_ATOMIC);
- if (!new)
+ if (!new) {
+ ret = -ENOMEM;
goto out;
+ }
new->psec.subnet_prefix = subnet_prefix;
new->psec.pkey = pkey_num;
diff --git a/sound/core/control.c b/sound/core/control.c
index 421ddc7..3b44378 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -1539,7 +1539,7 @@
unlock:
up_write(&card->controls_rwsem);
- return 0;
+ return err;
}
static int snd_ctl_elem_add_user(struct snd_ctl_file *file,
@@ -1925,8 +1925,8 @@
#ifdef CONFIG_COMPAT
/**
- * snd_ctl_unregister_ioctl - de-register the device-specific compat 32bit
- * control-ioctls
+ * snd_ctl_unregister_ioctl_compat - de-register the device-specific compat
+ * 32bit control-ioctls
* @fcn: ioctl callback function to unregister
*/
int snd_ctl_unregister_ioctl_compat(snd_kctl_ioctl_func_t fcn)
diff --git a/sound/core/pcm_dmaengine.c b/sound/core/pcm_dmaengine.c
index 4d059ff..4d0e8fe5 100644
--- a/sound/core/pcm_dmaengine.c
+++ b/sound/core/pcm_dmaengine.c
@@ -356,7 +356,8 @@
EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_close);
/**
- * snd_dmaengine_pcm_release_chan_close - Close a dmaengine based PCM substream and release channel
+ * snd_dmaengine_pcm_close_release_chan - Close a dmaengine based PCM
+ * substream and release channel
* @substream: PCM substream
*
* Releases the DMA channel associated with the PCM substream.
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index d531e1b..bda3514 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -490,7 +490,7 @@
EXPORT_SYMBOL(snd_pcm_set_ops);
/**
- * snd_pcm_sync - set the PCM sync id
+ * snd_pcm_set_sync - set the PCM sync id
* @substream: the pcm substream
*
* Sets the PCM sync identifier for the card.
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 9e0b2d7..47b155a 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -112,7 +112,7 @@
EXPORT_SYMBOL_GPL(snd_pcm_stream_lock);
/**
- * snd_pcm_stream_lock - Unlock the PCM stream
+ * snd_pcm_stream_unlock - Unlock the PCM stream
* @substream: PCM substream
*
* This unlocks the PCM stream that has been locked via snd_pcm_stream_lock().
@@ -595,7 +595,7 @@
}
/**
- * snd_pcm_hw_param_choose - choose a configuration defined by @params
+ * snd_pcm_hw_params_choose - choose a configuration defined by @params
* @pcm: PCM instance
* @params: the hw_params instance
*
diff --git a/sound/firewire/fireworks/fireworks_transaction.c b/sound/firewire/fireworks/fireworks_transaction.c
index 0f533f5..9f8c53b 100644
--- a/sound/firewire/fireworks/fireworks_transaction.c
+++ b/sound/firewire/fireworks/fireworks_transaction.c
@@ -123,7 +123,7 @@
t = (struct snd_efw_transaction *)data;
length = min_t(size_t, be32_to_cpu(t->length) * sizeof(u32), length);
- spin_lock_irq(&efw->lock);
+ spin_lock(&efw->lock);
if (efw->push_ptr < efw->pull_ptr)
capacity = (unsigned int)(efw->pull_ptr - efw->push_ptr);
@@ -190,7 +190,7 @@
copy_resp_to_buf(efw, data, length, rcode);
end:
- spin_unlock_irq(&instances_lock);
+ spin_unlock(&instances_lock);
}
static void
diff --git a/sound/hda/ext/hdac_ext_controller.c b/sound/hda/ext/hdac_ext_controller.c
index 4d060d5..b0c0ef824 100644
--- a/sound/hda/ext/hdac_ext_controller.c
+++ b/sound/hda/ext/hdac_ext_controller.c
@@ -148,6 +148,8 @@
return NULL;
if (bus->idx != bus_idx)
return NULL;
+ if (addr < 0 || addr > 31)
+ return NULL;
list_for_each_entry(hlink, &bus->hlink_list, list) {
for (i = 0; i < HDA_MAX_CODECS; i++) {
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index a356c21..4bb58e8 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -2934,7 +2934,7 @@
snd_hdac_leave_pm(&codec->core);
}
-static int hda_codec_runtime_suspend(struct device *dev)
+static int hda_codec_suspend(struct device *dev)
{
struct hda_codec *codec = dev_to_hda_codec(dev);
unsigned int state;
@@ -2953,7 +2953,7 @@
return 0;
}
-static int hda_codec_runtime_resume(struct device *dev)
+static int hda_codec_resume(struct device *dev)
{
struct hda_codec *codec = dev_to_hda_codec(dev);
@@ -2967,57 +2967,70 @@
pm_runtime_mark_last_busy(dev);
return 0;
}
+
+static int hda_codec_runtime_suspend(struct device *dev)
+{
+ return hda_codec_suspend(dev);
+}
+
+static int hda_codec_runtime_resume(struct device *dev)
+{
+ return hda_codec_resume(dev);
+}
+
#endif /* CONFIG_PM */
#ifdef CONFIG_PM_SLEEP
-static int hda_codec_force_resume(struct device *dev)
+static int hda_codec_pm_prepare(struct device *dev)
+{
+ return pm_runtime_suspended(dev);
+}
+
+static void hda_codec_pm_complete(struct device *dev)
{
struct hda_codec *codec = dev_to_hda_codec(dev);
- int ret;
- ret = pm_runtime_force_resume(dev);
- /* schedule jackpoll work for jack detection update */
- if (codec->jackpoll_interval ||
- (pm_runtime_suspended(dev) && hda_codec_need_resume(codec)))
- schedule_delayed_work(&codec->jackpoll_work,
- codec->jackpoll_interval);
- return ret;
+ if (pm_runtime_suspended(dev) && (codec->jackpoll_interval ||
+ hda_codec_need_resume(codec) || codec->forced_resume))
+ pm_request_resume(dev);
}
static int hda_codec_pm_suspend(struct device *dev)
{
dev->power.power_state = PMSG_SUSPEND;
- return pm_runtime_force_suspend(dev);
+ return hda_codec_suspend(dev);
}
static int hda_codec_pm_resume(struct device *dev)
{
dev->power.power_state = PMSG_RESUME;
- return hda_codec_force_resume(dev);
+ return hda_codec_resume(dev);
}
static int hda_codec_pm_freeze(struct device *dev)
{
dev->power.power_state = PMSG_FREEZE;
- return pm_runtime_force_suspend(dev);
+ return hda_codec_suspend(dev);
}
static int hda_codec_pm_thaw(struct device *dev)
{
dev->power.power_state = PMSG_THAW;
- return hda_codec_force_resume(dev);
+ return hda_codec_resume(dev);
}
static int hda_codec_pm_restore(struct device *dev)
{
dev->power.power_state = PMSG_RESTORE;
- return hda_codec_force_resume(dev);
+ return hda_codec_resume(dev);
}
#endif /* CONFIG_PM_SLEEP */
/* referred in hda_bind.c */
const struct dev_pm_ops hda_codec_driver_pm = {
#ifdef CONFIG_PM_SLEEP
+ .prepare = hda_codec_pm_prepare,
+ .complete = hda_codec_pm_complete,
.suspend = hda_codec_pm_suspend,
.resume = hda_codec_pm_resume,
.freeze = hda_codec_pm_freeze,
diff --git a/sound/pci/hda/hda_controller.h b/sound/pci/hda/hda_controller.h
index be63ead..68f96687 100644
--- a/sound/pci/hda/hda_controller.h
+++ b/sound/pci/hda/hda_controller.h
@@ -41,7 +41,7 @@
/* 24 unused */
#define AZX_DCAPS_COUNT_LPIB_DELAY (1 << 25) /* Take LPIB as delay */
#define AZX_DCAPS_PM_RUNTIME (1 << 26) /* runtime PM support */
-#define AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP (1 << 27) /* Workaround for spurious wakeups after suspend */
+/* 27 unused */
#define AZX_DCAPS_CORBRP_SELF_CLEAR (1 << 28) /* CORBRP clears itself after reset */
#define AZX_DCAPS_NO_MSI64 (1 << 29) /* Stick to 32-bit MSIs */
#define AZX_DCAPS_SEPARATE_STREAM_TAG (1 << 30) /* capture and playback use separate stream tag */
@@ -143,6 +143,7 @@
unsigned int align_buffer_size:1;
unsigned int region_requested:1;
unsigned int disabled:1; /* disabled by vga_switcheroo */
+ unsigned int pm_prepared:1;
/* GTS present */
unsigned int gts_present:1;
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 749b880..6852668 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -297,8 +297,7 @@
/* PCH for HSW/BDW; with runtime PM */
/* no i915 binding for this as HSW/BDW has another controller for HDMI */
#define AZX_DCAPS_INTEL_PCH \
- (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\
- AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
+ (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME)
/* HSW HDMI */
#define AZX_DCAPS_INTEL_HASWELL \
@@ -985,7 +984,7 @@
display_power(chip, false);
}
-static void __azx_runtime_resume(struct azx *chip, bool from_rt)
+static void __azx_runtime_resume(struct azx *chip)
{
struct hda_intel *hda = container_of(chip, struct hda_intel, chip);
struct hdac_bus *bus = azx_bus(chip);
@@ -1002,7 +1001,8 @@
azx_init_pci(chip);
hda_intel_init_chip(chip, true);
- if (from_rt) {
+ /* Avoid codec resume if runtime resume is for system suspend */
+ if (!chip->pm_prepared) {
list_for_each_codec(codec, &chip->bus) {
if (codec->relaxed_resume)
continue;
@@ -1018,6 +1018,29 @@
}
#ifdef CONFIG_PM_SLEEP
+static int azx_prepare(struct device *dev)
+{
+ struct snd_card *card = dev_get_drvdata(dev);
+ struct azx *chip;
+
+ chip = card->private_data;
+ chip->pm_prepared = 1;
+
+ /* HDA controller always requires different WAKEEN for runtime suspend
+ * and system suspend, so don't use direct-complete here.
+ */
+ return 0;
+}
+
+static void azx_complete(struct device *dev)
+{
+ struct snd_card *card = dev_get_drvdata(dev);
+ struct azx *chip;
+
+ chip = card->private_data;
+ chip->pm_prepared = 0;
+}
+
static int azx_suspend(struct device *dev)
{
struct snd_card *card = dev_get_drvdata(dev);
@@ -1029,15 +1052,7 @@
chip = card->private_data;
bus = azx_bus(chip);
- snd_power_change_state(card, SNDRV_CTL_POWER_D3hot);
- /* An ugly workaround: direct call of __azx_runtime_suspend() and
- * __azx_runtime_resume() for old Intel platforms that suffer from
- * spurious wakeups after S3 suspend
- */
- if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
- __azx_runtime_suspend(chip);
- else
- pm_runtime_force_suspend(dev);
+ __azx_runtime_suspend(chip);
if (bus->irq >= 0) {
free_irq(bus->irq, chip);
bus->irq = -1;
@@ -1066,11 +1081,7 @@
if (azx_acquire_irq(chip, 1) < 0)
return -EIO;
- if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
- __azx_runtime_resume(chip, false);
- else
- pm_runtime_force_resume(dev);
- snd_power_change_state(card, SNDRV_CTL_POWER_D0);
+ __azx_runtime_resume(chip);
trace_azx_resume(chip);
return 0;
@@ -1118,10 +1129,7 @@
chip = card->private_data;
/* enable controller wake up event */
- if (snd_power_get_state(card) == SNDRV_CTL_POWER_D0) {
- azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) |
- STATESTS_INT_MASK);
- }
+ azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) | STATESTS_INT_MASK);
__azx_runtime_suspend(chip);
trace_azx_runtime_suspend(chip);
@@ -1132,18 +1140,14 @@
{
struct snd_card *card = dev_get_drvdata(dev);
struct azx *chip;
- bool from_rt = snd_power_get_state(card) == SNDRV_CTL_POWER_D0;
if (!azx_is_pm_ready(card))
return 0;
chip = card->private_data;
- __azx_runtime_resume(chip, from_rt);
+ __azx_runtime_resume(chip);
/* disable controller Wake Up event*/
- if (from_rt) {
- azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) &
- ~STATESTS_INT_MASK);
- }
+ azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) & ~STATESTS_INT_MASK);
trace_azx_runtime_resume(chip);
return 0;
@@ -1177,6 +1181,8 @@
static const struct dev_pm_ops azx_pm = {
SET_SYSTEM_SLEEP_PM_OPS(azx_suspend, azx_resume)
#ifdef CONFIG_PM_SLEEP
+ .prepare = azx_prepare,
+ .complete = azx_complete,
.freeze_noirq = azx_freeze_noirq,
.thaw_noirq = azx_thaw_noirq,
#endif
@@ -2356,6 +2362,7 @@
if (azx_has_pm_runtime(chip)) {
pm_runtime_use_autosuspend(&pci->dev);
+ pm_runtime_allow(&pci->dev);
pm_runtime_put_autosuspend(&pci->dev);
}
@@ -2499,6 +2506,9 @@
/* DG1 */
{ PCI_DEVICE(0x8086, 0x490d),
.driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
+ /* Alderlake-S */
+ { PCI_DEVICE(0x8086, 0x7ad0),
+ .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
/* Elkhart Lake */
{ PCI_DEVICE(0x8086, 0x4b55),
.driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index e0c38f2..d8370a4 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -9183,6 +9183,8 @@
case QUIRK_AE5:
ca0132_mmio_init_ae5(codec);
break;
+ default:
+ break;
}
}
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index ccd1df0..b0068f8 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -4274,6 +4274,7 @@
HDA_CODEC_ENTRY(0x8086280f, "Icelake HDMI", patch_i915_icl_hdmi),
HDA_CODEC_ENTRY(0x80862812, "Tigerlake HDMI", patch_i915_tgl_hdmi),
HDA_CODEC_ENTRY(0x80862814, "DG1 HDMI", patch_i915_tgl_hdmi),
+HDA_CODEC_ENTRY(0x80862815, "Alderlake HDMI", patch_i915_tgl_hdmi),
HDA_CODEC_ENTRY(0x80862816, "Rocketlake HDMI", patch_i915_tgl_hdmi),
HDA_CODEC_ENTRY(0x8086281a, "Jasperlake HDMI", patch_i915_icl_hdmi),
HDA_CODEC_ENTRY(0x8086281b, "Elkhartlake HDMI", patch_i915_icl_hdmi),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index f239872..739dbaf 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2522,13 +2522,23 @@
SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX),
SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x9506, "Clevo P955HQ", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x950A, "Clevo P955H[PR]", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x95e3, "Clevo P955[ER]T", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x95e4, "Clevo P955ER", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x95e5, "Clevo P955EE6", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x95e6, "Clevo P950R[CDF]", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1558, 0x96e1, "Clevo P960[ER][CDFN]-K", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1558, 0x97e1, "Clevo P970[ER][CDFN]", ALC1220_FIXUP_CLEVO_P950),
- SND_PCI_QUIRK(0x1558, 0x65d1, "Clevo PB51[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
- SND_PCI_QUIRK(0x1558, 0x67d1, "Clevo PB71[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+ SND_PCI_QUIRK(0x1558, 0x97e2, "Clevo P970RC-M", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1558, 0x50d3, "Clevo PC50[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+ SND_PCI_QUIRK(0x1558, 0x65d1, "Clevo PB51[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+ SND_PCI_QUIRK(0x1558, 0x65d2, "Clevo PB51R[CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+ SND_PCI_QUIRK(0x1558, 0x65e1, "Clevo PB51[ED][DF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+ SND_PCI_QUIRK(0x1558, 0x67d1, "Clevo PB71[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+ SND_PCI_QUIRK(0x1558, 0x67e1, "Clevo PB71[DE][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
SND_PCI_QUIRK(0x1558, 0x70d1, "Clevo PC70[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
SND_PCI_QUIRK(0x1558, 0x7714, "Clevo X170", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
@@ -4216,6 +4226,12 @@
alc_fixup_hp_gpio_led(codec, action, 0x02, 0x20);
}
+static void alc287_fixup_hp_gpio_led(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ alc_fixup_hp_gpio_led(codec, action, 0x10, 0);
+}
+
/* turn on/off mic-mute LED per capture hook via VREF change */
static int vref_micmute_led_set(struct led_classdev *led_cdev,
enum led_brightness brightness)
@@ -6008,6 +6024,27 @@
snd_hda_override_wcaps(codec, 0x03, 0);
}
+static void alc_combo_jack_hp_jd_restart(struct hda_codec *codec)
+{
+ switch (codec->core.vendor_id) {
+ case 0x10ec0274:
+ case 0x10ec0294:
+ case 0x10ec0225:
+ case 0x10ec0295:
+ case 0x10ec0299:
+ alc_update_coef_idx(codec, 0x4a, 0x8000, 1 << 15); /* Reset HP JD */
+ alc_update_coef_idx(codec, 0x4a, 0x8000, 0 << 15);
+ break;
+ case 0x10ec0235:
+ case 0x10ec0236:
+ case 0x10ec0255:
+ case 0x10ec0256:
+ alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */
+ alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15);
+ break;
+ }
+}
+
static void alc295_fixup_chromebook(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
@@ -6018,16 +6055,7 @@
spec->ultra_low_power = true;
break;
case HDA_FIXUP_ACT_INIT:
- switch (codec->core.vendor_id) {
- case 0x10ec0295:
- alc_update_coef_idx(codec, 0x4a, 0x8000, 1 << 15); /* Reset HP JD */
- alc_update_coef_idx(codec, 0x4a, 0x8000, 0 << 15);
- break;
- case 0x10ec0236:
- alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */
- alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15);
- break;
- }
+ alc_combo_jack_hp_jd_restart(codec);
break;
}
}
@@ -6083,6 +6111,16 @@
alc_write_coef_idx(codec, 0x65, 0x0);
}
+static void alc274_fixup_hp_headset_mic(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ switch (action) {
+ case HDA_FIXUP_ACT_INIT:
+ alc_combo_jack_hp_jd_restart(codec);
+ break;
+ }
+}
+
/* for hda_fixup_thinkpad_acpi() */
#include "thinkpad_helper.c"
@@ -6277,6 +6315,11 @@
ALC256_FIXUP_INTEL_NUC8_RUGGED,
ALC255_FIXUP_XIAOMI_HEADSET_MIC,
ALC274_FIXUP_HP_MIC,
+ ALC274_FIXUP_HP_HEADSET_MIC,
+ ALC256_FIXUP_ASUS_HPE,
+ ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK,
+ ALC287_FIXUP_HP_GPIO_LED,
+ ALC256_FIXUP_HP_HEADSET_MIC,
};
static const struct hda_fixup alc269_fixups[] = {
@@ -7664,6 +7707,37 @@
{ }
},
},
+ [ALC274_FIXUP_HP_HEADSET_MIC] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc274_fixup_hp_headset_mic,
+ .chained = true,
+ .chain_id = ALC274_FIXUP_HP_MIC
+ },
+ [ALC256_FIXUP_ASUS_HPE] = {
+ .type = HDA_FIXUP_VERBS,
+ .v.verbs = (const struct hda_verb[]) {
+ /* Set EAPD high */
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x0f },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x7778 },
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC
+ },
+ [ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc_fixup_headset_jack,
+ .chained = true,
+ .chain_id = ALC269_FIXUP_THINKPAD_ACPI
+ },
+ [ALC287_FIXUP_HP_GPIO_LED] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc287_fixup_hp_gpio_led,
+ },
+ [ALC256_FIXUP_HP_HEADSET_MIC] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc274_fixup_hp_headset_mic,
+ },
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -7815,10 +7889,11 @@
SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED),
SND_PCI_QUIRK(0x103c, 0x8729, "HP", ALC285_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT),
- SND_PCI_QUIRK(0x103c, 0x874e, "HP", ALC274_FIXUP_HP_MIC),
SND_PCI_QUIRK(0x103c, 0x8760, "HP", ALC285_FIXUP_HP_MUTE_LED),
SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED),
SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED),
+ SND_PCI_QUIRK(0x103c, 0x87f4, "HP", ALC287_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -7848,6 +7923,7 @@
SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC),
+ SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE),
SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401),
SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS),
@@ -7883,11 +7959,49 @@
SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1558, 0x1323, "Clevo N130ZU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1558, 0x1325, "System76 Darter Pro (darp5)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x1401, "Clevo L140[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x1403, "Clevo N140CU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x1404, "Clevo N150CU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x14a1, "Clevo L141MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x4018, "Clevo NV40M[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x4019, "Clevo NV40MZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x4020, "Clevo NV40MB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x40a1, "Clevo NL40GU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x40c1, "Clevo NL40[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x40d1, "Clevo NL41DU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x50a3, "Clevo NJ51GU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x50b3, "Clevo NK50S[BEZ]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x50b6, "Clevo NK50S5", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x50b8, "Clevo NK50SZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x50d5, "Clevo NP50D5", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x50f0, "Clevo NH50A[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x50f3, "Clevo NH58DPQ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x5101, "Clevo S510WU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x5157, "Clevo W517GU1", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x51a1, "Clevo NS50MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x70a1, "Clevo NB70T[HJK]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x70b3, "Clevo NK70SB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8228, "Clevo NR40BU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8520, "Clevo NH50D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8521, "Clevo NH77D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8535, "Clevo NH50D[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8536, "Clevo NH79D[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1558, 0x8550, "System76 Gazelle (gaze14)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1558, 0x8551, "System76 Gazelle (gaze14)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1558, 0x8560, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x1558, 0x8561, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1558, 0x8668, "Clevo NP50B[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8680, "Clevo NJ50LU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8686, "Clevo NH50[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8a20, "Clevo NH55DCQ-Y", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8a51, "Clevo NH70RCQ-Y", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8d50, "Clevo NH55RCQ-M", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x951d, "Clevo N950T[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x961d, "Clevo N960S[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x971d, "Clevo N970T[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0xa500, "Clevo NL53RU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS),
SND_PCI_QUIRK(0x17aa, 0x1048, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE),
@@ -7925,6 +8039,8 @@
SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
SND_PCI_QUIRK(0x17aa, 0x22be, "Thinkpad X1 Carbon 8th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
+ SND_PCI_QUIRK(0x17aa, 0x22c1, "Thinkpad P1 Gen 3", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK),
+ SND_PCI_QUIRK(0x17aa, 0x22c2, "Thinkpad X1 Extreme Gen 3", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK),
SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
@@ -8237,6 +8353,10 @@
{0x19, 0x02a11020},
{0x1a, 0x02a11030},
{0x21, 0x0221101f}),
+ SND_HDA_PIN_QUIRK(0x10ec0236, 0x103c, "HP", ALC256_FIXUP_HP_HEADSET_MIC,
+ {0x14, 0x90170110},
+ {0x19, 0x02a11020},
+ {0x21, 0x02211030}),
SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE,
{0x14, 0x90170110},
{0x21, 0x02211020}),
@@ -8339,6 +8459,14 @@
{0x1a, 0x90a70130},
{0x1b, 0x90170110},
{0x21, 0x03211020}),
+ SND_HDA_PIN_QUIRK(0x10ec0256, 0x103c, "HP", ALC256_FIXUP_HP_HEADSET_MIC,
+ {0x14, 0x90170110},
+ {0x19, 0x02a11020},
+ {0x21, 0x0221101f}),
+ SND_HDA_PIN_QUIRK(0x10ec0274, 0x103c, "HP", ALC274_FIXUP_HP_HEADSET_MIC,
+ {0x17, 0x90170110},
+ {0x19, 0x03a11030},
+ {0x21, 0x03211020}),
SND_HDA_PIN_QUIRK(0x10ec0280, 0x103c, "HP", ALC280_FIXUP_HP_GPIO4,
{0x12, 0x90a60130},
{0x14, 0x90170110},
diff --git a/sound/pci/mixart/mixart_core.c b/sound/pci/mixart/mixart_core.c
index 0bdd33b..fb8895a 100644
--- a/sound/pci/mixart/mixart_core.c
+++ b/sound/pci/mixart/mixart_core.c
@@ -70,7 +70,6 @@
unsigned int i;
#endif
- mutex_lock(&mgr->msg_lock);
err = 0;
/* copy message descriptor from miXart to driver */
@@ -119,8 +118,6 @@
writel_be(headptr, MIXART_MEM(mgr, MSG_OUTBOUND_FREE_HEAD));
_clean_exit:
- mutex_unlock(&mgr->msg_lock);
-
return err;
}
@@ -258,7 +255,9 @@
resp.data = resp_data;
resp.size = max_resp_size;
+ mutex_lock(&mgr->msg_lock);
err = get_msg(mgr, &resp, msg_frame);
+ mutex_unlock(&mgr->msg_lock);
if( request->message_id != resp.message_id )
dev_err(&mgr->pci->dev, "RESPONSE ERROR!\n");
diff --git a/sound/soc/atmel/mchp-spdiftx.c b/sound/soc/atmel/mchp-spdiftx.c
index 82c1eec..3bd350a 100644
--- a/sound/soc/atmel/mchp-spdiftx.c
+++ b/sound/soc/atmel/mchp-spdiftx.c
@@ -487,7 +487,6 @@
}
mchp_spdiftx_channel_status_write(dev);
spin_unlock_irqrestore(&ctrl->lock, flags);
- mr |= SPDIFTX_MR_VALID1 | SPDIFTX_MR_VALID2;
if (dev->gclk_enabled) {
clk_disable_unprepare(dev->gclk);
diff --git a/sound/soc/codecs/cs42l51.c b/sound/soc/codecs/cs42l51.c
index 097c4e8..c61b17d 100644
--- a/sound/soc/codecs/cs42l51.c
+++ b/sound/soc/codecs/cs42l51.c
@@ -254,8 +254,28 @@
&cs42l51_adcr_mux_controls),
};
+static int mclk_event(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *kcontrol, int event)
+{
+ struct snd_soc_component *comp = snd_soc_dapm_to_component(w->dapm);
+ struct cs42l51_private *cs42l51 = snd_soc_component_get_drvdata(comp);
+
+ switch (event) {
+ case SND_SOC_DAPM_PRE_PMU:
+ return clk_prepare_enable(cs42l51->mclk_handle);
+ case SND_SOC_DAPM_POST_PMD:
+ /* Delay mclk shutdown to fulfill power-down sequence requirements */
+ msleep(20);
+ clk_disable_unprepare(cs42l51->mclk_handle);
+ break;
+ }
+
+ return 0;
+}
+
static const struct snd_soc_dapm_widget cs42l51_dapm_mclk_widgets[] = {
- SND_SOC_DAPM_CLOCK_SUPPLY("MCLK")
+ SND_SOC_DAPM_SUPPLY("MCLK", SND_SOC_NOPM, 0, 0, mclk_event,
+ SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
};
static const struct snd_soc_dapm_route cs42l51_routes[] = {
diff --git a/sound/soc/codecs/rt1015.c b/sound/soc/codecs/rt1015.c
index 25fe2dd..3db0729 100644
--- a/sound/soc/codecs/rt1015.c
+++ b/sound/soc/codecs/rt1015.c
@@ -27,10 +27,15 @@
#include <sound/soc-dapm.h>
#include <sound/soc.h>
#include <sound/tlv.h>
+#include <sound/rt1015.h>
#include "rl6231.h"
#include "rt1015.h"
+static const struct rt1015_platform_data i2s_default_platform_data = {
+ .power_up_delay_ms = 50,
+};
+
static const struct reg_default rt1015_reg[] = {
{ 0x0000, 0x0000 },
{ 0x0004, 0xa000 },
@@ -539,7 +544,7 @@
struct rt1015_priv *rt1015 = container_of(work, struct rt1015_priv,
flush_work.work);
struct snd_soc_component *component = rt1015->component;
- unsigned int val, i = 0, count = 20;
+ unsigned int val, i = 0, count = 200;
while (i < count) {
usleep_range(1000, 1500);
@@ -650,6 +655,7 @@
case SND_SOC_DAPM_POST_PMU:
if (rt1015->hw_config == RT1015_HW_28)
schedule_delayed_work(&rt1015->flush_work, msecs_to_jiffies(10));
+ msleep(rt1015->pdata.power_up_delay_ms);
break;
default:
break;
@@ -1067,9 +1073,16 @@
MODULE_DEVICE_TABLE(acpi, rt1015_acpi_match);
#endif
+static void rt1015_parse_dt(struct rt1015_priv *rt1015, struct device *dev)
+{
+ device_property_read_u32(dev, "realtek,power-up-delay-ms",
+ &rt1015->pdata.power_up_delay_ms);
+}
+
static int rt1015_i2c_probe(struct i2c_client *i2c,
const struct i2c_device_id *id)
{
+ struct rt1015_platform_data *pdata = dev_get_platdata(&i2c->dev);
struct rt1015_priv *rt1015;
int ret;
unsigned int val;
@@ -1081,6 +1094,13 @@
i2c_set_clientdata(i2c, rt1015);
+ rt1015->pdata = i2s_default_platform_data;
+
+ if (pdata)
+ rt1015->pdata = *pdata;
+ else
+ rt1015_parse_dt(rt1015, &i2c->dev);
+
rt1015->regmap = devm_regmap_init_i2c(i2c, &rt1015_regmap);
if (IS_ERR(rt1015->regmap)) {
ret = PTR_ERR(rt1015->regmap);
diff --git a/sound/soc/codecs/rt1015.h b/sound/soc/codecs/rt1015.h
index d3fdd30..15cadb3 100644
--- a/sound/soc/codecs/rt1015.h
+++ b/sound/soc/codecs/rt1015.h
@@ -12,6 +12,7 @@
#ifndef __RT1015_H__
#define __RT1015_H__
+#include <sound/rt1015.h>
#define RT1015_DEVICE_ID_VAL 0x1011
#define RT1015_DEVICE_ID_VAL2 0x1015
@@ -380,6 +381,7 @@
struct rt1015_priv {
struct snd_soc_component *component;
+ struct rt1015_platform_data pdata;
struct regmap *regmap;
int sysclk;
int sysclk_src;
diff --git a/sound/soc/codecs/wcd9335.c b/sound/soc/codecs/wcd9335.c
index f2d9d52..4d2b1ec7 100644
--- a/sound/soc/codecs/wcd9335.c
+++ b/sound/soc/codecs/wcd9335.c
@@ -618,7 +618,7 @@
"ZERO", "RX_MIX_TX8", "DEC8", "DEC8_192"
};
-static const DECLARE_TLV_DB_SCALE(digital_gain, 0, 1, 0);
+static const DECLARE_TLV_DB_SCALE(digital_gain, -8400, 100, -8400);
static const DECLARE_TLV_DB_SCALE(line_gain, 0, 7, 1);
static const DECLARE_TLV_DB_SCALE(analog_gain, 0, 25, 1);
static const DECLARE_TLV_DB_SCALE(ear_pa_gain, 0, 150, 0);
diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c
index 35697b0..40f682f 100644
--- a/sound/soc/codecs/wcd934x.c
+++ b/sound/soc/codecs/wcd934x.c
@@ -551,7 +551,7 @@
struct soc_bytes_ext bytes_ext;
};
-static const DECLARE_TLV_DB_SCALE(digital_gain, 0, 1, 0);
+static const DECLARE_TLV_DB_SCALE(digital_gain, -8400, 100, -8400);
static const DECLARE_TLV_DB_SCALE(line_gain, 0, 7, 1);
static const DECLARE_TLV_DB_SCALE(analog_gain, 0, 25, 1);
static const DECLARE_TLV_DB_SCALE(ear_pa_gain, 0, 150, 0);
diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c
index 68e774e..4530b74 100644
--- a/sound/soc/codecs/wsa881x.c
+++ b/sound/soc/codecs/wsa881x.c
@@ -1026,6 +1026,8 @@
.id = 0,
.playback = {
.stream_name = "SPKR Playback",
+ .rates = SNDRV_PCM_RATE_48000,
+ .formats = SNDRV_PCM_FMTBIT_S16_LE,
.rate_max = 48000,
.rate_min = 48000,
.channels_min = 1,
diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig
index d5bae5d..a5b446d 100644
--- a/sound/soc/intel/Kconfig
+++ b/sound/soc/intel/Kconfig
@@ -15,22 +15,6 @@
if SND_SOC_INTEL_SST_TOPLEVEL
-config SND_SST_IPC
- tristate
- # This option controls the IPC core for HiFi2 platforms
-
-config SND_SST_IPC_PCI
- tristate
- select SND_SST_IPC
- # This option controls the PCI-based IPC for HiFi2 platforms
- # (Medfield, Merrifield).
-
-config SND_SST_IPC_ACPI
- tristate
- select SND_SST_IPC
- # This option controls the ACPI-based IPC for HiFi2 platforms
- # (Baytrail, Cherrytrail)
-
config SND_SOC_INTEL_SST
tristate
@@ -57,7 +41,6 @@
config SND_SST_ATOM_HIFI2_PLATFORM_PCI
tristate "PCI HiFi2 (Merrifield) Platforms"
depends on X86 && PCI
- select SND_SST_IPC_PCI
select SND_SST_ATOM_HIFI2_PLATFORM
help
If you have a Intel Merrifield/Edison platform, then
@@ -70,7 +53,6 @@
tristate "ACPI HiFi2 (Baytrail, Cherrytrail) Platforms"
default ACPI
depends on X86 && ACPI && PCI
- select SND_SST_IPC_ACPI
select SND_SST_ATOM_HIFI2_PLATFORM
select SND_SOC_ACPI_INTEL_MATCH
select IOSF_MBI
diff --git a/sound/soc/intel/atom/Makefile b/sound/soc/intel/atom/Makefile
index a9326d5..c66f03f 100644
--- a/sound/soc/intel/atom/Makefile
+++ b/sound/soc/intel/atom/Makefile
@@ -6,4 +6,4 @@
obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM) += snd-soc-sst-atom-hifi2-platform.o
# DSP driver
-obj-$(CONFIG_SND_SST_IPC) += sst/
+obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM) += sst/
diff --git a/sound/soc/intel/atom/sst/Makefile b/sound/soc/intel/atom/sst/Makefile
index f17c905..5761d30 100644
--- a/sound/soc/intel/atom/sst/Makefile
+++ b/sound/soc/intel/atom/sst/Makefile
@@ -3,6 +3,6 @@
snd-intel-sst-pci-objs += sst_pci.o
snd-intel-sst-acpi-objs += sst_acpi.o
-obj-$(CONFIG_SND_SST_IPC) += snd-intel-sst-core.o
-obj-$(CONFIG_SND_SST_IPC_PCI) += snd-intel-sst-pci.o
-obj-$(CONFIG_SND_SST_IPC_ACPI) += snd-intel-sst-acpi.o
+obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM) += snd-intel-sst-core.o
+obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM_PCI) += snd-intel-sst-pci.o
+obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM_ACPI) += snd-intel-sst-acpi.o
diff --git a/sound/soc/intel/boards/kbl_rt5663_max98927.c b/sound/soc/intel/boards/kbl_rt5663_max98927.c
index 3ea4602..9a4b3d0 100644
--- a/sound/soc/intel/boards/kbl_rt5663_max98927.c
+++ b/sound/soc/intel/boards/kbl_rt5663_max98927.c
@@ -401,17 +401,40 @@
struct snd_interval *chan = hw_param_interval(params,
SNDRV_PCM_HW_PARAM_CHANNELS);
struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
- struct snd_soc_dpcm *dpcm = container_of(
- params, struct snd_soc_dpcm, hw_params);
- struct snd_soc_dai_link *fe_dai_link = dpcm->fe->dai_link;
- struct snd_soc_dai_link *be_dai_link = dpcm->be->dai_link;
+ struct snd_soc_dpcm *dpcm, *rtd_dpcm = NULL;
+
+ /*
+ * The following loop will be called only for playback stream
+ * In this platform, there is only one playback device on every SSP
+ */
+ for_each_dpcm_fe(rtd, SNDRV_PCM_STREAM_PLAYBACK, dpcm) {
+ rtd_dpcm = dpcm;
+ break;
+ }
+
+ /*
+ * This following loop will be called only for capture stream
+ * In this platform, there is only one capture device on every SSP
+ */
+ for_each_dpcm_fe(rtd, SNDRV_PCM_STREAM_CAPTURE, dpcm) {
+ rtd_dpcm = dpcm;
+ break;
+ }
+
+ if (!rtd_dpcm)
+ return -EINVAL;
+
+ /*
+ * The above 2 loops are mutually exclusive based on the stream direction,
+ * thus rtd_dpcm variable will never be overwritten
+ */
/*
* The ADSP will convert the FE rate to 48k, stereo, 24 bit
*/
- if (!strcmp(fe_dai_link->name, "Kbl Audio Port") ||
- !strcmp(fe_dai_link->name, "Kbl Audio Headset Playback") ||
- !strcmp(fe_dai_link->name, "Kbl Audio Capture Port")) {
+ if (!strcmp(rtd_dpcm->fe->dai_link->name, "Kbl Audio Port") ||
+ !strcmp(rtd_dpcm->fe->dai_link->name, "Kbl Audio Headset Playback") ||
+ !strcmp(rtd_dpcm->fe->dai_link->name, "Kbl Audio Capture Port")) {
rate->min = rate->max = 48000;
chan->min = chan->max = 2;
snd_mask_none(fmt);
@@ -421,7 +444,7 @@
* The speaker on the SSP0 supports S16_LE and not S24_LE.
* thus changing the mask here
*/
- if (!strcmp(be_dai_link->name, "SSP0-Codec"))
+ if (!strcmp(rtd_dpcm->be->dai_link->name, "SSP0-Codec"))
snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S16_LE);
return 0;
diff --git a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
index 922cd01..f95546c 100644
--- a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
+++ b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
@@ -700,6 +700,8 @@
switch (level) {
case SND_SOC_BIAS_PREPARE:
if (dapm->bias_level == SND_SOC_BIAS_ON) {
+ if (!__clk_is_enabled(priv->mclk))
+ return 0;
dev_dbg(card->dev, "Disable mclk");
clk_disable_unprepare(priv->mclk);
} else {
diff --git a/sound/soc/intel/catpt/dsp.c b/sound/soc/intel/catpt/dsp.c
index 7d29685..9e807b9 100644
--- a/sound/soc/intel/catpt/dsp.c
+++ b/sound/soc/intel/catpt/dsp.c
@@ -267,9 +267,12 @@
reg, (reg & CATPT_ISD_DCPWM),
500, 10000);
if (ret) {
- dev_err(cdev->dev, "await WAITI timeout\n");
- mutex_unlock(&cdev->clk_mutex);
- return ret;
+ dev_warn(cdev->dev, "await WAITI timeout\n");
+ /* no signal - only high clock selection allowed */
+ if (lp) {
+ mutex_unlock(&cdev->clk_mutex);
+ return 0;
+ }
}
}
diff --git a/sound/soc/intel/catpt/pcm.c b/sound/soc/intel/catpt/pcm.c
index f78018c..408e64e 100644
--- a/sound/soc/intel/catpt/pcm.c
+++ b/sound/soc/intel/catpt/pcm.c
@@ -458,10 +458,6 @@
if (ret)
return CATPT_IPC_ERROR(ret);
- ret = catpt_dsp_update_lpclock(cdev);
- if (ret)
- return ret;
-
ret = catpt_dai_apply_usettings(dai, stream);
if (ret)
return ret;
@@ -500,6 +496,7 @@
case SNDRV_PCM_TRIGGER_RESUME:
case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
resume_stream:
+ catpt_dsp_update_lpclock(cdev);
ret = catpt_ipc_resume_stream(cdev, stream->info.stream_hw_id);
if (ret)
return CATPT_IPC_ERROR(ret);
@@ -507,11 +504,11 @@
case SNDRV_PCM_TRIGGER_STOP:
stream->prepared = false;
- catpt_dsp_update_lpclock(cdev);
fallthrough;
case SNDRV_PCM_TRIGGER_SUSPEND:
case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
ret = catpt_ipc_pause_stream(cdev, stream->info.stream_hw_id);
+ catpt_dsp_update_lpclock(cdev);
if (ret)
return CATPT_IPC_ERROR(ret);
break;
@@ -534,6 +531,8 @@
dsppos = bytes_to_frames(r, pos->stream_position);
+ if (!stream->prepared)
+ goto exit;
/* only offload is set_write_pos driven */
if (stream->template->type != CATPT_STRM_TYPE_RENDER)
goto exit;
@@ -667,7 +666,17 @@
break;
}
+ /* see if this is a new configuration */
+ if (!memcmp(&cdev->devfmt[devfmt.iface], &devfmt, sizeof(devfmt)))
+ return 0;
+
+ pm_runtime_get_sync(cdev->dev);
+
ret = catpt_ipc_set_device_format(cdev, &devfmt);
+
+ pm_runtime_mark_last_busy(cdev->dev);
+ pm_runtime_put_autosuspend(cdev->dev);
+
if (ret)
return CATPT_IPC_ERROR(ret);
diff --git a/sound/soc/intel/keembay/kmb_platform.c b/sound/soc/intel/keembay/kmb_platform.c
index f54b710..291a686 100644
--- a/sound/soc/intel/keembay/kmb_platform.c
+++ b/sound/soc/intel/keembay/kmb_platform.c
@@ -487,9 +487,9 @@
kmb_i2s->xfer_resolution = 0x02;
break;
case SNDRV_PCM_FORMAT_S24_LE:
- config->data_width = 24;
- kmb_i2s->ccr = 0x08;
- kmb_i2s->xfer_resolution = 0x04;
+ config->data_width = 32;
+ kmb_i2s->ccr = 0x14;
+ kmb_i2s->xfer_resolution = 0x05;
break;
case SNDRV_PCM_FORMAT_S32_LE:
config->data_width = 32;
diff --git a/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c b/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c
index c2c1eb16..26e7d9a 100644
--- a/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c
+++ b/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c
@@ -630,15 +630,34 @@
},
};
+static const struct snd_kcontrol_new mt8183_da7219_rt1015_snd_controls[] = {
+ SOC_DAPM_PIN_SWITCH("Left Spk"),
+ SOC_DAPM_PIN_SWITCH("Right Spk"),
+};
+
+static const
+struct snd_soc_dapm_widget mt8183_da7219_rt1015_dapm_widgets[] = {
+ SND_SOC_DAPM_SPK("Left Spk", NULL),
+ SND_SOC_DAPM_SPK("Right Spk", NULL),
+ SND_SOC_DAPM_PINCTRL("TDM_OUT_PINCTRL",
+ "aud_tdm_out_on", "aud_tdm_out_off"),
+};
+
+static const struct snd_soc_dapm_route mt8183_da7219_rt1015_dapm_routes[] = {
+ {"Left Spk", NULL, "Left SPO"},
+ {"Right Spk", NULL, "Right SPO"},
+ {"I2S Playback", NULL, "TDM_OUT_PINCTRL"},
+};
+
static struct snd_soc_card mt8183_da7219_rt1015_card = {
.name = "mt8183_da7219_rt1015",
.owner = THIS_MODULE,
- .controls = mt8183_da7219_max98357_snd_controls,
- .num_controls = ARRAY_SIZE(mt8183_da7219_max98357_snd_controls),
- .dapm_widgets = mt8183_da7219_max98357_dapm_widgets,
- .num_dapm_widgets = ARRAY_SIZE(mt8183_da7219_max98357_dapm_widgets),
- .dapm_routes = mt8183_da7219_max98357_dapm_routes,
- .num_dapm_routes = ARRAY_SIZE(mt8183_da7219_max98357_dapm_routes),
+ .controls = mt8183_da7219_rt1015_snd_controls,
+ .num_controls = ARRAY_SIZE(mt8183_da7219_rt1015_snd_controls),
+ .dapm_widgets = mt8183_da7219_rt1015_dapm_widgets,
+ .num_dapm_widgets = ARRAY_SIZE(mt8183_da7219_rt1015_dapm_widgets),
+ .dapm_routes = mt8183_da7219_rt1015_dapm_routes,
+ .num_dapm_routes = ARRAY_SIZE(mt8183_da7219_rt1015_dapm_routes),
.dai_link = mt8183_da7219_dai_links,
.num_links = ARRAY_SIZE(mt8183_da7219_dai_links),
.aux_dev = &mt8183_da7219_max98357_headset_dev,
diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c
index ba2aca3..9d17c87 100644
--- a/sound/soc/qcom/lpass-cpu.c
+++ b/sound/soc/qcom/lpass-cpu.c
@@ -80,6 +80,12 @@
dev_err(dai->dev, "error in enabling mi2s osr clk: %d\n", ret);
return ret;
}
+ ret = clk_prepare(drvdata->mi2s_bit_clk[dai->driver->id]);
+ if (ret) {
+ dev_err(dai->dev, "error in enabling mi2s bit clk: %d\n", ret);
+ clk_disable_unprepare(drvdata->mi2s_osr_clk[dai->driver->id]);
+ return ret;
+ }
return 0;
}
@@ -88,9 +94,8 @@
{
struct lpass_data *drvdata = snd_soc_dai_get_drvdata(dai);
- clk_disable_unprepare(drvdata->mi2s_bit_clk[dai->driver->id]);
-
clk_disable_unprepare(drvdata->mi2s_osr_clk[dai->driver->id]);
+ clk_unprepare(drvdata->mi2s_bit_clk[dai->driver->id]);
}
static int lpass_cpu_daiops_hw_params(struct snd_pcm_substream *substream,
@@ -303,10 +308,10 @@
dev_err(dai->dev, "error writing to i2sctl reg: %d\n",
ret);
- ret = clk_prepare_enable(drvdata->mi2s_bit_clk[id]);
+ ret = clk_enable(drvdata->mi2s_bit_clk[id]);
if (ret) {
dev_err(dai->dev, "error in enabling mi2s bit clk: %d\n", ret);
- clk_disable_unprepare(drvdata->mi2s_osr_clk[id]);
+ clk_disable(drvdata->mi2s_osr_clk[id]);
return ret;
}
@@ -324,6 +329,7 @@
if (ret)
dev_err(dai->dev, "error writing to i2sctl reg: %d\n",
ret);
+ clk_disable(drvdata->mi2s_bit_clk[dai->driver->id]);
break;
}
diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c
index 36d1512..7a3fdf8 100644
--- a/sound/soc/qcom/lpass-platform.c
+++ b/sound/soc/qcom/lpass-platform.c
@@ -122,8 +122,10 @@
else
dma_ch = 0;
- if (dma_ch < 0)
+ if (dma_ch < 0) {
+ kfree(data);
return dma_ch;
+ }
if (cpu_dai->driver->id == LPASS_DP_RX) {
map = drvdata->hdmiif_map;
@@ -147,6 +149,7 @@
ret = snd_pcm_hw_constraint_integer(runtime,
SNDRV_PCM_HW_PARAM_PERIODS);
if (ret < 0) {
+ kfree(data);
dev_err(soc_runtime->dev, "setting constraints failed: %d\n",
ret);
return -EINVAL;
diff --git a/sound/soc/qcom/lpass-sc7180.c b/sound/soc/qcom/lpass-sc7180.c
index c6292f9e..bc998d5 100644
--- a/sound/soc/qcom/lpass-sc7180.c
+++ b/sound/soc/qcom/lpass-sc7180.c
@@ -188,7 +188,7 @@
.micmode = REG_FIELD_ID(0x1000, 4, 8, 3, 0x1000),
.micmono = REG_FIELD_ID(0x1000, 3, 3, 3, 0x1000),
.wssrc = REG_FIELD_ID(0x1000, 2, 2, 3, 0x1000),
- .bitwidth = REG_FIELD_ID(0x1000, 0, 0, 3, 0x1000),
+ .bitwidth = REG_FIELD_ID(0x1000, 0, 1, 3, 0x1000),
.rdma_dyncclk = REG_FIELD_ID(0xC000, 21, 21, 5, 0x1000),
.rdma_bursten = REG_FIELD_ID(0xC000, 20, 20, 5, 0x1000),
diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c
index ab1bf23..6c2760e 100644
--- a/sound/soc/qcom/sdm845.c
+++ b/sound/soc/qcom/sdm845.c
@@ -17,6 +17,7 @@
#include "qdsp6/q6afe.h"
#include "../codecs/rt5663.h"
+#define DRIVER_NAME "sdm845"
#define DEFAULT_SAMPLE_RATE_48K 48000
#define DEFAULT_MCLK_RATE 24576000
#define TDM_BCLK_RATE 6144000
@@ -552,6 +553,7 @@
if (!data)
return -ENOMEM;
+ card->driver_name = DRIVER_NAME;
card->dapm_widgets = sdm845_snd_widgets;
card->num_dapm_widgets = ARRAY_SIZE(sdm845_snd_widgets);
card->dev = dev;
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index ea3986a..05a085f 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -2341,7 +2341,7 @@
}
/**
- * snd_soc_unregister_dai - Unregister DAIs from the ASoC core
+ * snd_soc_unregister_dais - Unregister DAIs from the ASoC core
*
* @component: The component for which the DAIs should be unregistered
*/
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 980f2c3..7f87b44 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -1276,7 +1276,7 @@
}
/**
- * snd_soc_dapm_get_connected_widgets - query audio path and it's widgets.
+ * snd_soc_dapm_dai_get_connected_widgets - query audio path and it's widgets.
* @dai: the soc DAI.
* @stream: stream direction.
* @list: list of active widgets for this stream.
diff --git a/sound/soc/sof/loader.c b/sound/soc/sof/loader.c
index 68ed454..ba9ed66 100644
--- a/sound/soc/sof/loader.c
+++ b/sound/soc/sof/loader.c
@@ -118,6 +118,11 @@
case SOF_IPC_EXT_CC_INFO:
ret = get_cc_info(sdev, ext_hdr);
break;
+ case SOF_IPC_EXT_UNUSED:
+ case SOF_IPC_EXT_PROBE_INFO:
+ case SOF_IPC_EXT_USER_ABI_INFO:
+ /* They are supported but we don't do anything here */
+ break;
default:
dev_warn(sdev->dev, "warning: unknown ext header type %d size 0x%x\n",
ext_hdr->type, ext_hdr->hdr.size);
diff --git a/sound/usb/card.c b/sound/usb/card.c
index fa764b6..4457214 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -379,6 +379,10 @@
DEVICE_NAME(0x046d, 0x0990, "Logitech, Inc.", "QuickCam Pro 9000"),
+ /* ASUS ROG Strix */
+ PROFILE_NAME(0x0b05, 0x1917,
+ "Realtek", "ALC1220-VB-DT", "Realtek-ALC1220-VB-Desktop"),
+
/* Dell WD15 Dock */
PROFILE_NAME(0x0bda, 0x4014, "Dell", "WD15 Dock", "Dell-WD15-Dock"),
/* Dell WD19 Dock */
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index c369c81..a7212f1 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -561,7 +561,8 @@
},
{ /* ASUS ROG Strix */
.id = USB_ID(0x0b05, 0x1917),
- .map = asus_rog_map,
+ .map = trx40_mobo_map,
+ .connector_map = trx40_mobo_connector_map,
},
{ /* MSI TRX40 Creator */
.id = USB_ID(0x0db0, 0x0d64),
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index b401ee8..a860303 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -336,6 +336,7 @@
switch (subs->stream->chip->usb_id) {
case USB_ID(0x0763, 0x2030): /* M-Audio Fast Track C400 */
case USB_ID(0x0763, 0x2031): /* M-Audio Fast Track C600 */
+ case USB_ID(0x22f0, 0x0006): /* Allen&Heath Qu-16 */
ep = 0x81;
ifnum = 3;
goto add_sync_ep_from_ifnum;
@@ -345,6 +346,7 @@
ifnum = 2;
goto add_sync_ep_from_ifnum;
case USB_ID(0x2466, 0x8003): /* Fractal Audio Axe-Fx II */
+ case USB_ID(0x0499, 0x172a): /* Yamaha MODX */
ep = 0x86;
ifnum = 2;
goto add_sync_ep_from_ifnum;
@@ -352,6 +354,10 @@
ep = 0x81;
ifnum = 2;
goto add_sync_ep_from_ifnum;
+ case USB_ID(0x1686, 0xf029): /* Zoom UAC-2 */
+ ep = 0x82;
+ ifnum = 2;
+ goto add_sync_ep_from_ifnum;
case USB_ID(0x1397, 0x0001): /* Behringer UFX1604 */
case USB_ID(0x1397, 0x0002): /* Behringer UFX1204 */
ep = 0x81;
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index b4fa80e..c50be2f 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1672,13 +1672,13 @@
&& (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
msleep(20);
- /* Zoom R16/24, Logitech H650e/H570e, Jabra 550a, Kingston HyperX
- * needs a tiny delay here, otherwise requests like get/set
- * frequency return as failed despite actually succeeding.
+ /* Zoom R16/24, many Logitech(at least H650e/H570e/BCC950),
+ * Jabra 550a, Kingston HyperX needs a tiny delay here,
+ * otherwise requests like get/set frequency return
+ * as failed despite actually succeeding.
*/
if ((chip->usb_id == USB_ID(0x1686, 0x00dd) ||
- chip->usb_id == USB_ID(0x046d, 0x0a46) ||
- chip->usb_id == USB_ID(0x046d, 0x0a56) ||
+ USB_ID_VENDOR(chip->usb_id) == 0x046d || /* Logitech */
chip->usb_id == USB_ID(0x0b0e, 0x0349) ||
chip->usb_id == USB_ID(0x0951, 0x16ad)) &&
(requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
@@ -1800,6 +1800,7 @@
case 0x278b: /* Rotel? */
case 0x292b: /* Gustard/Ess based devices */
case 0x2ab6: /* T+A devices */
+ case 0x3353: /* Khadas devices */
case 0x3842: /* EVGA */
case 0xc502: /* HiBy devices */
if (fp->dsd_raw)
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index ba85bb2..1c17c3a 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -159,6 +159,21 @@
struct kvm_arch_memory_slot {
};
+/*
+ * PMU filter structure. Describe a range of events with a particular
+ * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER.
+ */
+struct kvm_pmu_event_filter {
+ __u16 base_event;
+ __u16 nevents;
+
+#define KVM_PMU_EVENT_ALLOW 0
+#define KVM_PMU_EVENT_DENY 1
+
+ __u8 action;
+ __u8 pad[3];
+};
+
/* for KVM_GET/SET_VCPU_EVENTS */
struct kvm_vcpu_events {
struct {
@@ -242,6 +257,15 @@
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2
+
+/*
+ * Only two states can be presented by the host kernel:
+ * - NOT_REQUIRED: the guest doesn't need to do anything
+ * - NOT_AVAIL: the guest isn't mitigated (it can still use SSBS if available)
+ *
+ * All the other values are deprecated. The host still accepts all
+ * values (they are ABI), but will narrow them to the above two.
+ */
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2)
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1
@@ -329,6 +353,7 @@
#define KVM_ARM_VCPU_PMU_V3_CTRL 0
#define KVM_ARM_VCPU_PMU_V3_IRQ 0
#define KVM_ARM_VCPU_PMU_V3_INIT 1
+#define KVM_ARM_VCPU_PMU_V3_FILTER 2
#define KVM_ARM_VCPU_TIMER_CTRL 1
#define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0
#define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1
diff --git a/tools/arch/s390/include/uapi/asm/sie.h b/tools/arch/s390/include/uapi/asm/sie.h
index 6ca1e68..ede3186 100644
--- a/tools/arch/s390/include/uapi/asm/sie.h
+++ b/tools/arch/s390/include/uapi/asm/sie.h
@@ -29,7 +29,7 @@
{ 0x13, "SIGP conditional emergency signal" }, \
{ 0x15, "SIGP sense running" }, \
{ 0x16, "SIGP set multithreading"}, \
- { 0x17, "SIGP store additional status ait address"}
+ { 0x17, "SIGP store additional status at address"}
#define icpt_prog_codes \
{ 0x0001, "Prog Operation" }, \
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 2901d5d..dad350d 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -96,7 +96,7 @@
#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */
#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */
#define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */
-/* free ( 3*32+17) */
+#define X86_FEATURE_SME_COHERENT ( 3*32+17) /* "" AMD hardware-enforced cache coherency */
#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */
#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */
#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */
@@ -236,6 +236,7 @@
#define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */
#define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
+#define X86_FEATURE_SEV_ES ( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
@@ -288,6 +289,7 @@
#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */
#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */
#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */
+#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
@@ -353,6 +355,7 @@
#define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */
#define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */
#define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */
+#define X86_FEATURE_ENQCMD (16*32+29) /* ENQCMD and ENQCMDS instructions */
/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */
@@ -368,6 +371,7 @@
#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */
#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
#define X86_FEATURE_SERIALIZE (18*32+14) /* SERIALIZE instruction */
+#define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */
#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
#define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */
#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 4ea8584..5861d34 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -56,6 +56,12 @@
# define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31))
#endif
+#ifdef CONFIG_IOMMU_SUPPORT
+# define DISABLE_ENQCMD 0
+#else
+# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -75,7 +81,8 @@
#define DISABLED_MASK13 0
#define DISABLED_MASK14 0
#define DISABLED_MASK15 0
-#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
+#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
+ DISABLE_ENQCMD)
#define DISABLED_MASK17 0
#define DISABLED_MASK18 0
#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 2859ee4..972a34d 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -257,6 +257,9 @@
#define MSR_IA32_LASTINTFROMIP 0x000001dd
#define MSR_IA32_LASTINTTOIP 0x000001de
+#define MSR_IA32_PASID 0x00000d93
+#define MSR_IA32_PASID_VALID BIT_ULL(31)
+
/* DEBUGCTLMSR bits (others vary by model): */
#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */
#define DEBUGCTLMSR_BTF_SHIFT 1
@@ -464,11 +467,15 @@
#define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
#define MSR_AMD64_IBSCTL 0xc001103a
#define MSR_AMD64_IBSBRTARGET 0xc001103b
+#define MSR_AMD64_ICIBSEXTDCTL 0xc001103c
#define MSR_AMD64_IBSOPDATA4 0xc001103d
#define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */
+#define MSR_AMD64_SEV_ES_GHCB 0xc0010130
#define MSR_AMD64_SEV 0xc0010131
#define MSR_AMD64_SEV_ENABLED_BIT 0
+#define MSR_AMD64_SEV_ES_ENABLED_BIT 1
#define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
+#define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
@@ -857,11 +864,14 @@
#define MSR_CORE_PERF_FIXED_CTR0 0x00000309
#define MSR_CORE_PERF_FIXED_CTR1 0x0000030a
#define MSR_CORE_PERF_FIXED_CTR2 0x0000030b
+#define MSR_CORE_PERF_FIXED_CTR3 0x0000030c
#define MSR_CORE_PERF_FIXED_CTR_CTRL 0x0000038d
#define MSR_CORE_PERF_GLOBAL_STATUS 0x0000038e
#define MSR_CORE_PERF_GLOBAL_CTRL 0x0000038f
#define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x00000390
+#define MSR_PERF_METRICS 0x00000329
+
/* PERF_GLOBAL_OVF_CTL bits */
#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT 55
#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI (1ULL << MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT)
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index 6847d85..3ff0d48 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -54,7 +54,7 @@
#endif
#ifdef CONFIG_X86_64
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
/* Paravirtualized systems may not have PSE or PGE available */
#define NEED_PSE 0
#define NEED_PGE 0
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 0780f97..89e5f3d 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -192,6 +192,26 @@
__u32 indices[0];
};
+/* Maximum size of any access bitmap in bytes */
+#define KVM_MSR_FILTER_MAX_BITMAP_SIZE 0x600
+
+/* for KVM_X86_SET_MSR_FILTER */
+struct kvm_msr_filter_range {
+#define KVM_MSR_FILTER_READ (1 << 0)
+#define KVM_MSR_FILTER_WRITE (1 << 1)
+ __u32 flags;
+ __u32 nmsrs; /* number of msrs in bitmap */
+ __u32 base; /* MSR index the bitmap starts at */
+ __u8 *bitmap; /* a 1 bit allows the operations in flags, 0 denies */
+};
+
+#define KVM_MSR_FILTER_MAX_RANGES 16
+struct kvm_msr_filter {
+#define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
+#define KVM_MSR_FILTER_DEFAULT_DENY (1 << 0)
+ __u32 flags;
+ struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
+};
struct kvm_cpuid_entry {
__u32 function;
diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
index 2e8a30f0..f1d8307 100644
--- a/tools/arch/x86/include/uapi/asm/svm.h
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -29,6 +29,7 @@
#define SVM_EXIT_WRITE_DR6 0x036
#define SVM_EXIT_WRITE_DR7 0x037
#define SVM_EXIT_EXCP_BASE 0x040
+#define SVM_EXIT_LAST_EXCP 0x05f
#define SVM_EXIT_INTR 0x060
#define SVM_EXIT_NMI 0x061
#define SVM_EXIT_SMI 0x062
@@ -76,10 +77,21 @@
#define SVM_EXIT_MWAIT_COND 0x08c
#define SVM_EXIT_XSETBV 0x08d
#define SVM_EXIT_RDPRU 0x08e
+#define SVM_EXIT_INVPCID 0x0a2
#define SVM_EXIT_NPF 0x400
#define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401
#define SVM_EXIT_AVIC_UNACCELERATED_ACCESS 0x402
+/* SEV-ES software-defined VMGEXIT events */
+#define SVM_VMGEXIT_MMIO_READ 0x80000001
+#define SVM_VMGEXIT_MMIO_WRITE 0x80000002
+#define SVM_VMGEXIT_NMI_COMPLETE 0x80000003
+#define SVM_VMGEXIT_AP_HLT_LOOP 0x80000004
+#define SVM_VMGEXIT_AP_JUMP_TABLE 0x80000005
+#define SVM_VMGEXIT_SET_AP_JUMP_TABLE 0
+#define SVM_VMGEXIT_GET_AP_JUMP_TABLE 1
+#define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff
+
#define SVM_EXIT_ERR -1
#define SVM_EXIT_REASONS \
@@ -171,6 +183,7 @@
{ SVM_EXIT_MONITOR, "monitor" }, \
{ SVM_EXIT_MWAIT, "mwait" }, \
{ SVM_EXIT_XSETBV, "xsetbv" }, \
+ { SVM_EXIT_INVPCID, "invpcid" }, \
{ SVM_EXIT_NPF, "npf" }, \
{ SVM_EXIT_AVIC_INCOMPLETE_IPI, "avic_incomplete_ipi" }, \
{ SVM_EXIT_AVIC_UNACCELERATED_ACCESS, "avic_unaccelerated_access" }, \
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 0b5b8ae..1e299ac 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -16,8 +16,6 @@
* to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
*/
-.weak memcpy
-
/*
* memcpy - Copy a memory block.
*
@@ -30,7 +28,7 @@
* rax original destination
*/
SYM_FUNC_START_ALIAS(__memcpy)
-SYM_FUNC_START_LOCAL(memcpy)
+SYM_FUNC_START_WEAK(memcpy)
ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
"jmp memcpy_erms", X86_FEATURE_ERMS
@@ -51,14 +49,14 @@
* memcpy_erms() - enhanced fast string memcpy. This is faster and
* simpler than memcpy. Use memcpy_erms when possible.
*/
-SYM_FUNC_START(memcpy_erms)
+SYM_FUNC_START_LOCAL(memcpy_erms)
movq %rdi, %rax
movq %rdx, %rcx
rep movsb
ret
SYM_FUNC_END(memcpy_erms)
-SYM_FUNC_START(memcpy_orig)
+SYM_FUNC_START_LOCAL(memcpy_orig)
movq %rdi, %rax
cmpq $0x20, %rdx
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index fd5d25a..0bfd26e 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -4,8 +4,7 @@
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
#include <asm/alternative-asm.h>
-
-.weak memset
+#include <asm/export.h>
/*
* ISO C memset - set a memory block to a byte value. This function uses fast
@@ -18,7 +17,7 @@
*
* rax original destination
*/
-SYM_FUNC_START_ALIAS(memset)
+SYM_FUNC_START_WEAK(memset)
SYM_FUNC_START(__memset)
/*
* Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
@@ -44,6 +43,8 @@
ret
SYM_FUNC_END(__memset)
SYM_FUNC_END_ALIAS(memset)
+EXPORT_SYMBOL(memset)
+EXPORT_SYMBOL(__memset)
/*
* ISO C memset - set a memory block to a byte value. This function uses
@@ -56,7 +57,7 @@
*
* rax original destination
*/
-SYM_FUNC_START(memset_erms)
+SYM_FUNC_START_LOCAL(memset_erms)
movq %rdi,%r9
movb %sil,%al
movq %rdx,%rcx
@@ -65,7 +66,7 @@
ret
SYM_FUNC_END(memset_erms)
-SYM_FUNC_START(memset_orig)
+SYM_FUNC_START_LOCAL(memset_orig)
movq %rdi,%r10
/* expand byte value */
diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c
index a43a6f1..359960a 100644
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -843,9 +843,14 @@
else
p_err("missing %s%s%s%s%s%s%s%srequired for full feature probing; run as root or use 'unprivileged'",
capability_msg(bpf_caps, 0),
+#ifdef CAP_BPF
capability_msg(bpf_caps, 1),
capability_msg(bpf_caps, 2),
- capability_msg(bpf_caps, 3));
+ capability_msg(bpf_caps, 3)
+#else
+ "", "", "", "", "", ""
+#endif /* CAP_BPF */
+ );
goto exit_free;
}
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index 910e7ba..3fae61e 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -578,8 +578,8 @@
ifindex = net_parse_dev(&argc, &argv);
if (ifindex < 1) {
- close(progfd);
- return -EINVAL;
+ err = -EINVAL;
+ goto cleanup;
}
if (argc) {
@@ -587,8 +587,8 @@
overwrite = true;
} else {
p_err("expected 'overwrite', got: '%s'?", *argv);
- close(progfd);
- return -EINVAL;
+ err = -EINVAL;
+ goto cleanup;
}
}
@@ -596,17 +596,17 @@
if (is_prefix("xdp", attach_type_strings[attach_type]))
err = do_attach_detach_xdp(progfd, attach_type, ifindex,
overwrite);
-
- if (err < 0) {
+ if (err) {
p_err("interface %s attach failed: %s",
attach_type_strings[attach_type], strerror(-err));
- return err;
+ goto cleanup;
}
if (json_output)
jsonw_null(json_wtr);
-
- return 0;
+cleanup:
+ close(progfd);
+ return err;
}
static int do_detach(int argc, char **argv)
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index d942c1e..acdb2c24 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -940,7 +940,7 @@
}
if (*attach_type == BPF_FLOW_DISSECTOR) {
- *mapfd = -1;
+ *mapfd = 0;
return 0;
}
diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c
index 4e3512f..ce5b65e 100644
--- a/tools/bpf/bpftool/skeleton/profiler.bpf.c
+++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c
@@ -70,7 +70,7 @@
static inline void
fexit_update_maps(u32 id, struct bpf_perf_event_value *after)
{
- struct bpf_perf_event_value *before, diff, *accum;
+ struct bpf_perf_event_value *before, diff;
before = bpf_map_lookup_elem(&fentry_readings, &id);
/* only account samples with a valid fentry_reading */
@@ -95,7 +95,7 @@
{
struct bpf_perf_event_value readings[MAX_NUM_MATRICS];
u32 cpu = bpf_get_smp_processor_id();
- u32 i, one = 1, zero = 0;
+ u32 i, zero = 0;
int err;
u64 *count;
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index a04e813..4648738 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -185,7 +185,6 @@
main_test_libperl();
main_test_hello();
main_test_libelf();
- main_test_libelf_mmap();
main_test_get_current_dir_name();
main_test_gettid();
main_test_glibc();
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index b9d4322..95c072b 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -27,18 +27,6 @@
#define __pure __attribute__((pure))
#endif
#define noinline __attribute__((noinline))
-#ifdef __has_attribute
-#if __has_attribute(disable_tail_calls)
-#define __no_tail_call __attribute__((disable_tail_calls))
-#endif
-#endif
-#ifndef __no_tail_call
-#if GCC_VERSION > 40201
-#define __no_tail_call __attribute__((optimize("no-optimize-sibling-calls")))
-#else
-#define __no_tail_call
-#endif
-#endif
#ifndef __packed
#define __packed __attribute__((packed))
#endif
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 2b3f735..d22a974 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -47,9 +47,6 @@
#ifndef noinline
#define noinline
#endif
-#ifndef __no_tail_call
-#define __no_tail_call
-#endif
/* Are two types/vars the same type (ignoring qualifiers)? */
#ifndef __same_type
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index f2b5d72..2056318 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -857,9 +857,11 @@
__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
#define __NR_faccessat2 439
__SYSCALL(__NR_faccessat2, sys_faccessat2)
+#define __NR_process_madvise 440
+__SYSCALL(__NR_process_madvise, sys_process_madvise)
#undef __NR_syscalls
-#define __NR_syscalls 440
+#define __NR_syscalls 441
/*
* 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 0054606..fa1f3d6 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -619,6 +619,12 @@
*/
#define I915_PARAM_PERF_REVISION 54
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See
+ * I915_EXEC_USE_EXTENSIONS.
+ */
+#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55
+
/* Must be kept compact -- no holes and well documented */
typedef struct drm_i915_getparam {
@@ -1046,6 +1052,38 @@
__u32 flags;
};
+/**
+ * See drm_i915_gem_execbuffer_ext_timeline_fences.
+ */
+#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
+
+/**
+ * This structure describes an array of drm_syncobj and associated points for
+ * timeline variants of drm_syncobj. It is invalid to append this structure to
+ * the execbuf if I915_EXEC_FENCE_ARRAY is set.
+ */
+struct drm_i915_gem_execbuffer_ext_timeline_fences {
+ struct i915_user_extension base;
+
+ /**
+ * Number of element in the handles_ptr & value_ptr arrays.
+ */
+ __u64 fence_count;
+
+ /**
+ * Pointer to an array of struct drm_i915_gem_exec_fence of length
+ * fence_count.
+ */
+ __u64 handles_ptr;
+
+ /**
+ * Pointer to an array of u64 values of length fence_count. Values
+ * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline
+ * drm_syncobj is invalid as it turns a drm_syncobj into a binary one.
+ */
+ __u64 values_ptr;
+};
+
struct drm_i915_gem_execbuffer2 {
/**
* List of gem_exec_object2 structs
@@ -1062,8 +1100,14 @@
__u32 num_cliprects;
/**
* This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
- * is not set. If I915_EXEC_FENCE_ARRAY is set, then this is a
- * struct drm_i915_gem_exec_fence *fences.
+ * & I915_EXEC_USE_EXTENSIONS are not set.
+ *
+ * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array
+ * of struct drm_i915_gem_exec_fence and num_cliprects is the length
+ * of the array.
+ *
+ * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a
+ * single struct i915_user_extension and num_cliprects is 0.
*/
__u64 cliprects_ptr;
#define I915_EXEC_RING_MASK (0x3f)
@@ -1181,7 +1225,16 @@
*/
#define I915_EXEC_FENCE_SUBMIT (1 << 20)
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1))
+/*
+ * Setting I915_EXEC_USE_EXTENSIONS implies that
+ * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked
+ * list of i915_user_extension. Each i915_user_extension node is the base of a
+ * larger structure. The list of supported structures are listed in the
+ * drm_i915_gem_execbuffer_ext enum.
+ */
+#define I915_EXEC_USE_EXTENSIONS (1 << 21)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1))
#define I915_EXEC_CONTEXT_ID_MASK (0xffffffff)
#define i915_execbuffer2_set_context_id(eb2, context) \
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index 7875709..e5de603 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -45,7 +45,6 @@
__u8 flags;
__u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
};
-#define fscrypt_policy fscrypt_policy_v1
/*
* Process-subscribed "logon" key description prefix and payload format.
@@ -156,9 +155,9 @@
__u32 __out_reserved[13];
};
-#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy)
+#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy_v1)
#define FS_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16])
-#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy_v1)
#define FS_IOC_GET_ENCRYPTION_POLICY_EX _IOWR('f', 22, __u8[9]) /* size + version */
#define FS_IOC_ADD_ENCRYPTION_KEY _IOWR('f', 23, struct fscrypt_add_key_arg)
#define FS_IOC_REMOVE_ENCRYPTION_KEY _IOWR('f', 24, struct fscrypt_remove_key_arg)
@@ -170,6 +169,7 @@
/* old names; don't add anything new here! */
#ifndef __KERNEL__
+#define fscrypt_policy fscrypt_policy_v1
#define FS_KEY_DESCRIPTOR_SIZE FSCRYPT_KEY_DESCRIPTOR_SIZE
#define FS_POLICY_FLAGS_PAD_4 FSCRYPT_POLICY_FLAGS_PAD_4
#define FS_POLICY_FLAGS_PAD_8 FSCRYPT_POLICY_FLAGS_PAD_8
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 7d8eced..ca41220 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -248,6 +248,8 @@
#define KVM_EXIT_IOAPIC_EOI 26
#define KVM_EXIT_HYPERV 27
#define KVM_EXIT_ARM_NISV 28
+#define KVM_EXIT_X86_RDMSR 29
+#define KVM_EXIT_X86_WRMSR 30
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
@@ -413,6 +415,17 @@
__u64 esr_iss;
__u64 fault_ipa;
} arm_nisv;
+ /* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */
+ struct {
+ __u8 error; /* user -> kernel */
+ __u8 pad[7];
+#define KVM_MSR_EXIT_REASON_INVAL (1 << 0)
+#define KVM_MSR_EXIT_REASON_UNKNOWN (1 << 1)
+#define KVM_MSR_EXIT_REASON_FILTER (1 << 2)
+ __u32 reason; /* kernel -> user */
+ __u32 index; /* kernel -> user */
+ __u64 data; /* kernel <-> user */
+ } msr;
/* Fix the size of the union. */
char padding[256];
};
@@ -1037,6 +1050,9 @@
#define KVM_CAP_SMALLER_MAXPHYADDR 185
#define KVM_CAP_S390_DIAG318 186
#define KVM_CAP_STEAL_TIME 187
+#define KVM_CAP_X86_USER_SPACE_MSR 188
+#define KVM_CAP_X86_MSR_FILTER 189
+#define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1538,6 +1554,9 @@
/* Available with KVM_CAP_S390_PROTECTED */
#define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
+/* Available with KVM_CAP_X86_MSR_FILTER */
+#define KVM_X86_SET_MSR_FILTER _IOW(KVMIO, 0xc6, struct kvm_msr_filter)
+
/* Secure Encrypted Virtualization command */
enum sev_cmd_id {
/* Guest initialization commands */
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index 923cc16..f55bc68 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -27,6 +27,7 @@
#define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT
#define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK
+#define MAP_HUGE_16KB HUGETLB_FLAG_ENCODE_16KB
#define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB
#define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB
#define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB
diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
index 96a0240..dd8306e 100644
--- a/tools/include/uapi/linux/mount.h
+++ b/tools/include/uapi/linux/mount.h
@@ -16,6 +16,7 @@
#define MS_REMOUNT 32 /* Alter flags of a mounted FS */
#define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */
#define MS_DIRSYNC 128 /* Directory modifications are synchronous */
+#define MS_NOSYMFOLLOW 256 /* Do not follow symlinks */
#define MS_NOATIME 1024 /* Do not update access times. */
#define MS_NODIRATIME 2048 /* Do not update directory access times */
#define MS_BIND 4096
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 3e5dcdd..b95d3c4 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -1196,7 +1196,7 @@
#define PERF_MEM_SNOOPX_FWD 0x01 /* forward */
/* 1 free */
-#define PERF_MEM_SNOOPX_SHIFT 38
+#define PERF_MEM_SNOOPX_SHIFT 38
/* locked instruction */
#define PERF_MEM_LOCK_NA 0x01 /* not available */
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index 07b4f81..7f08277 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -233,6 +233,15 @@
#define PR_SET_TAGGED_ADDR_CTRL 55
#define PR_GET_TAGGED_ADDR_CTRL 56
# define PR_TAGGED_ADDR_ENABLE (1UL << 0)
+/* MTE tag check fault modes */
+# define PR_MTE_TCF_SHIFT 1
+# define PR_MTE_TCF_NONE (0UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_SYNC (1UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_ASYNC (2UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_MASK (3UL << PR_MTE_TCF_SHIFT)
+/* MTE tag inclusion mask */
+# define PR_MTE_TAG_SHIFT 3
+# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT)
/* Control reclaim behavior when allocating memory */
#define PR_SET_IO_FLUSHER 57
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index 7523218..c998860 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -146,4 +146,8 @@
/* Set event fd for config interrupt*/
#define VHOST_VDPA_SET_CONFIG_CALL _IOW(VHOST_VIRTIO, 0x77, int)
+
+/* Get the valid iova range */
+#define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \
+ struct vhost_vdpa_iova_range)
#endif
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 5f9abed..55bd78b 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -146,6 +146,7 @@
awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \
sort -u | wc -l)
VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \
+ sed 's/\[.*\]//' | \
awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \
grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
@@ -214,6 +215,7 @@
awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \
sort -u > $(OUTPUT)libbpf_global_syms.tmp; \
readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \
+ sed 's/\[.*\]//' | \
awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \
grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \
sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \
diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h
index d9b385f..10a4c4c 100644
--- a/tools/lib/bpf/hashmap.h
+++ b/tools/lib/bpf/hashmap.h
@@ -15,6 +15,9 @@
static inline size_t hash_bits(size_t h, int bits)
{
/* shuffle bits and return requested number of upper bits */
+ if (bits == 0)
+ return 0;
+
#if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__)
/* LP64 case */
return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits);
@@ -174,17 +177,17 @@
* @key: key to iterate entries for
*/
#define hashmap__for_each_key_entry(map, cur, _key) \
- for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
- map->cap_bits); \
- map->buckets ? map->buckets[bkt] : NULL; }); \
+ for (cur = map->buckets \
+ ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+ : NULL; \
cur; \
cur = cur->next) \
if (map->equal_fn(cur->key, (_key), map->ctx))
#define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \
- for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
- map->cap_bits); \
- cur = map->buckets ? map->buckets[bkt] : NULL; }); \
+ for (cur = map->buckets \
+ ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+ : NULL; \
cur && ({ tmp = cur->next; true; }); \
cur = tmp) \
if (map->equal_fn(cur->key, (_key), map->ctx))
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 3130341..28baee7 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -560,8 +560,6 @@
const char *name, size_t sec_idx, const char *sec_name,
size_t sec_off, void *insn_data, size_t insn_data_sz)
{
- int i;
-
if (insn_data_sz == 0 || insn_data_sz % BPF_INSN_SZ || sec_off % BPF_INSN_SZ) {
pr_warn("sec '%s': corrupted program '%s', offset %zu, size %zu\n",
sec_name, name, sec_off, insn_data_sz);
@@ -600,13 +598,6 @@
goto errout;
memcpy(prog->insns, insn_data, insn_data_sz);
- for (i = 0; i < prog->insns_cnt; i++) {
- if (insn_is_subprog_call(&prog->insns[i])) {
- obj->has_subcalls = true;
- break;
- }
- }
-
return 0;
errout:
pr_warn("sec '%s': failed to allocate memory for prog '%s'\n", sec_name, name);
@@ -3280,7 +3271,19 @@
static bool prog_is_subprog(const struct bpf_object *obj,
const struct bpf_program *prog)
{
- return prog->sec_idx == obj->efile.text_shndx && obj->has_subcalls;
+ /* For legacy reasons, libbpf supports an entry-point BPF programs
+ * without SEC() attribute, i.e., those in the .text section. But if
+ * there are 2 or more such programs in the .text section, they all
+ * must be subprograms called from entry-point BPF programs in
+ * designated SEC()'tions, otherwise there is no way to distinguish
+ * which of those programs should be loaded vs which are a subprogram.
+ * Similarly, if there is a function/program in .text and at least one
+ * other BPF program with custom SEC() attribute, then we just assume
+ * .text programs are subprograms (even if they are not called from
+ * other programs), because libbpf never explicitly supported mixing
+ * SEC()-designated BPF programs and .text entry-point BPF programs.
+ */
+ return prog->sec_idx == obj->efile.text_shndx && obj->nr_programs > 1;
}
struct bpf_program *
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index e3c98c0..9bc537d 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -891,13 +891,16 @@
void xsk_socket__delete(struct xsk_socket *xsk)
{
size_t desc_sz = sizeof(struct xdp_desc);
- struct xsk_ctx *ctx = xsk->ctx;
struct xdp_mmap_offsets off;
+ struct xsk_umem *umem;
+ struct xsk_ctx *ctx;
int err;
if (!xsk)
return;
+ ctx = xsk->ctx;
+ umem = ctx->umem;
if (ctx->prog_fd != -1) {
xsk_delete_bpf_maps(xsk);
close(ctx->prog_fd);
@@ -917,11 +920,11 @@
xsk_put_ctx(ctx);
- ctx->umem->refcount--;
+ umem->refcount--;
/* Do not close an fd that also has an associated umem connected
* to it.
*/
- if (xsk->fd != ctx->umem->fd)
+ if (xsk->fd != umem->fd)
close(xsk->fd);
free(xsk);
}
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 6890fc4b..ce8516e 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -749,6 +749,7 @@
PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null)
PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS))
+ PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS))
PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS))
FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 3478096..3798192 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -361,12 +361,13 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
#
-# x32-specific system call numbers start at 512 to avoid cache impact
-# for native 64-bit operation. The __x32_compat_sys stubs are created
-# on-the-fly for compat_sys_*() compatibility system calls if X86_X32
-# is defined.
+# Due to a historical design error, certain syscalls are numbered differently
+# in x32 as compared to native x86_64. These syscalls have numbers 512-547.
+# Do not add new syscalls to this range. Numbers 548 and above are available
+# for non-x32 use.
#
512 x32 rt_sigaction compat_sys_rt_sigaction
513 x32 rt_sigreturn compat_sys_x32_rt_sigreturn
@@ -404,3 +405,5 @@
545 x32 execveat compat_sys_execveat
546 x32 preadv2 compat_sys_preadv64v2
547 x32 pwritev2 compat_sys_pwritev64v2
+# This is the end of the legacy x32 range. Numbers 548 and above are
+# not special and are not to be used for x32-specific syscalls.
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
index 4e40402..478078f 100644
--- a/tools/perf/arch/x86/tests/dwarf-unwind.c
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -38,6 +38,13 @@
stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
memcpy(buf, (void *) sp, stack_size);
+#ifdef MEMORY_SANITIZER
+ /*
+ * Copying the stack may copy msan poison, avoid false positives in the
+ * unwinder by removing the poison here.
+ */
+ __msan_unpoison(buf, stack_size);
+#endif
stack->data = (char *) buf;
stack->size = stack_size;
return 0;
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index 9ad015a..6eb45a2 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -2,6 +2,9 @@
/* Various wrappers to make the kernel .S file build in user-space: */
+// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it
+#define SYM_FUNC_START_LOCAL(name) \
+ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
#define memcpy MEMCPY /* don't hide glibc's memcpy() */
#define altinstr_replacement text
#define globl p2align 4; .globl
diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S
index d550bd5..6f093c4 100644
--- a/tools/perf/bench/mem-memset-x86-64-asm.S
+++ b/tools/perf/bench/mem-memset-x86-64-asm.S
@@ -1,4 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
+// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it
+#define SYM_FUNC_START_LOCAL(name) \
+ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
#define memset MEMSET /* don't hide glibc's memset() */
#define altinstr_replacement text
#define globl p2align 4; .globl
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 452a75f..0462dc8 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -779,25 +779,15 @@
dsos__hit_all(session);
/*
* The AUX areas have been removed and replaced with
- * synthesized hardware events, so clear the feature flag and
- * remove the evsel.
+ * synthesized hardware events, so clear the feature flag.
*/
if (inject->itrace_synth_opts.set) {
- struct evsel *evsel;
-
perf_header__clear_feat(&session->header,
HEADER_AUXTRACE);
if (inject->itrace_synth_opts.last_branch ||
inject->itrace_synth_opts.add_last_branch)
perf_header__set_feat(&session->header,
HEADER_BRANCH_STACK);
- evsel = perf_evlist__id2evsel_strict(session->evlist,
- inject->aux_id);
- if (evsel) {
- pr_debug("Deleting %s\n", evsel__name(evsel));
- evlist__remove(session->evlist, evsel);
- evsel__delete(evsel);
- }
}
session->header.data_offset = output_data_offset;
session->header.data_size = inject->bytes_written;
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index f0a1dba..a2f1e53 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -406,7 +406,7 @@
struct lock_seq_stat *seq;
const char *name = evsel__strval(evsel, sample, "name");
u64 tmp = evsel__intval(evsel, sample, "lockdep_addr");
- int flag = evsel__intval(evsel, sample, "flag");
+ int flag = evsel__intval(evsel, sample, "flags");
memcpy(&addr, &tmp, sizeof(void *));
@@ -621,7 +621,7 @@
case SEQ_STATE_READ_ACQUIRED:
seq->read_count--;
BUG_ON(seq->read_count < 0);
- if (!seq->read_count) {
+ if (seq->read_count) {
ls->nr_release++;
goto end;
}
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 44a75f2..de80534 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -4639,9 +4639,9 @@
err = 0;
if (lists[0]) {
- struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event",
- "event selector. use 'perf list' to list available events",
- parse_events_option);
+ struct option o = {
+ .value = &trace->evlist,
+ };
err = parse_events_option(&o, lists[0], 0);
}
out:
@@ -4655,9 +4655,12 @@
{
struct trace *trace = opt->value;
- if (!list_empty(&trace->evlist->core.entries))
- return parse_cgroups(opt, str, unset);
-
+ if (!list_empty(&trace->evlist->core.entries)) {
+ struct option o = {
+ .value = &trace->evlist,
+ };
+ return parse_cgroups(&o, str, unset);
+ }
trace->cgroup = evlist__findnew_cgroup(trace->evlist, str);
return 0;
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index de31935..00f4fcf 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -329,7 +329,7 @@
},
{
"BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
- "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+ "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time",
"MetricGroup": "Memory_BW;SoC",
"MetricName": "DRAM_BW_Use"
},
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index f31794d..0dd8b13 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -323,7 +323,7 @@
},
{
"BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
- "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+ "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time",
"MetricGroup": "Memory_BW;SoC",
"MetricName": "DRAM_BW_Use"
},
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 2491d16..8363809 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -95,7 +95,7 @@
return strcmp((const char *) symbol, funcs[idx]);
}
-__no_tail_call noinline int test_dwarf_unwind__thread(struct thread *thread)
+noinline int test_dwarf_unwind__thread(struct thread *thread)
{
struct perf_sample sample;
unsigned long cnt = 0;
@@ -126,7 +126,7 @@
static int global_unwind_retval = -INT_MAX;
-__no_tail_call noinline int test_dwarf_unwind__compare(void *p1, void *p2)
+noinline int test_dwarf_unwind__compare(void *p1, void *p2)
{
/* Any possible value should be 'thread' */
struct thread *thread = *(struct thread **)p1;
@@ -145,7 +145,7 @@
return p1 - p2;
}
-__no_tail_call noinline int test_dwarf_unwind__krava_3(struct thread *thread)
+noinline int test_dwarf_unwind__krava_3(struct thread *thread)
{
struct thread *array[2] = {thread, thread};
void *fp = &bsearch;
@@ -164,12 +164,12 @@
return global_unwind_retval;
}
-__no_tail_call noinline int test_dwarf_unwind__krava_2(struct thread *thread)
+noinline int test_dwarf_unwind__krava_2(struct thread *thread)
{
return test_dwarf_unwind__krava_3(thread);
}
-__no_tail_call noinline int test_dwarf_unwind__krava_1(struct thread *thread)
+noinline int test_dwarf_unwind__krava_1(struct thread *thread)
{
return test_dwarf_unwind__krava_2(thread);
}
diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh
index 8d84fdb..18fde2f 100755
--- a/tools/perf/tests/shell/test_arm_coresight.sh
+++ b/tools/perf/tests/shell/test_arm_coresight.sh
@@ -44,7 +44,7 @@
# touch 6512 1 branches:u: ffffb22082e0 strcmp+0xa0 (/lib/aarch64-linux-gnu/ld-2.27.so)
# touch 6512 1 branches:u: ffffb2208320 strcmp+0xe0 (/lib/aarch64-linux-gnu/ld-2.27.so)
perf script -F,-time -i ${perfdata} | \
- egrep " +$1 +[0-9]+ .* +branches:([u|k]:)? +"
+ egrep " +$1 +[0-9]+ .* +branches:(.*:)? +"
}
perf_report_branch_samples() {
@@ -105,7 +105,7 @@
# `> device_name = 'tmc_etf0'
device_name=$(basename $path)
- if is_device_sink $path $devce_name; then
+ if is_device_sink $path $device_name; then
record_touch_file $device_name $2 &&
perf_script_branch_samples touch &&
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index a07626f..b0e1880 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2963,7 +2963,7 @@
struct popup_action actions[MAX_OPTIONS];
int nr_options = 0;
int key = -1;
- char buf[64];
+ char buf[128];
int delay_secs = hbt ? hbt->refresh : 0;
#define HIST_BROWSER_HELP_COMMON \
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 8763772..6b410c3 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -102,6 +102,8 @@
const u8 *raw = build_id->data;
size_t i;
+ bf[0] = 0x0;
+
for (i = 0; i < build_id->size; ++i) {
sprintf(bid, "%02x", *raw);
++raw;
diff --git a/tools/perf/util/hashmap.c b/tools/perf/util/hashmap.c
index a405dad..3c20b12 100644
--- a/tools/perf/util/hashmap.c
+++ b/tools/perf/util/hashmap.c
@@ -15,6 +15,9 @@
/* make sure libbpf doesn't use kernel-only integer typedefs */
#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+/* prevent accidental re-addition of reallocarray() */
+#pragma GCC poison reallocarray
+
/* start with 4 buckets */
#define HASHMAP_MIN_CAP_BITS 2
diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h
index e0af36b..d9b385f 100644
--- a/tools/perf/util/hashmap.h
+++ b/tools/perf/util/hashmap.h
@@ -25,6 +25,18 @@
#endif
}
+/* generic C-string hashing function */
+static inline size_t str_hash(const char *s)
+{
+ size_t h = 0;
+
+ while (*s) {
+ h = h * 31 + *s;
+ s++;
+ }
+ return h;
+}
+
typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx);
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
index b8a5159..5acf053 100644
--- a/tools/perf/util/include/linux/linkage.h
+++ b/tools/perf/util/include/linux/linkage.h
@@ -25,6 +25,7 @@
/* SYM_L_* -- linkage of symbols */
#define SYM_L_GLOBAL(name) .globl name
+#define SYM_L_WEAK(name) .weak name
#define SYM_L_LOCAL(name) /* nothing */
#define ALIGN __ALIGN
@@ -84,6 +85,12 @@
SYM_END(name, SYM_T_FUNC)
#endif
+/* SYM_FUNC_START_WEAK -- use for weak functions */
+#ifndef SYM_FUNC_START_WEAK
+#define SYM_FUNC_START_WEAK(name) \
+ SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN)
+#endif
+
/*
* SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START,
* SYM_FUNC_START_WEAK, ...
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 7d4194f..15385ea 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -786,11 +786,20 @@
union perf_event *event,
struct perf_sample *sample __maybe_unused)
{
+ struct symbol *sym;
struct map *map;
map = maps__find(&machine->kmaps, event->ksymbol.addr);
- if (map)
+ if (!map)
+ return 0;
+
+ if (map != machine->vmlinux_map)
maps__remove(&machine->kmaps, map);
+ else {
+ sym = dso__find_symbol(map->dso, map->map_ip(map, map->start));
+ if (sym)
+ dso__delete_symbol(map->dso, sym);
+ }
return 0;
}
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 7cbd024..c83c2c6 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1592,7 +1592,6 @@
static int python_start_script(const char *script, int argc, const char **argv)
{
struct tables *tables = &tables_global;
- PyMODINIT_FUNC (*initfunc)(void);
#if PY_MAJOR_VERSION < 3
const char **command_line;
#else
@@ -1607,20 +1606,18 @@
FILE *fp;
#if PY_MAJOR_VERSION < 3
- initfunc = initperf_trace_context;
command_line = malloc((argc + 1) * sizeof(const char *));
command_line[0] = script;
for (i = 1; i < argc + 1; i++)
command_line[i] = argv[i - 1];
+ PyImport_AppendInittab(name, initperf_trace_context);
#else
- initfunc = PyInit_perf_trace_context;
command_line = malloc((argc + 1) * sizeof(wchar_t *));
command_line[0] = Py_DecodeLocale(script, NULL);
for (i = 1; i < argc + 1; i++)
command_line[i] = Py_DecodeLocale(argv[i - 1], NULL);
+ PyImport_AppendInittab(name, PyInit_perf_trace_context);
#endif
-
- PyImport_AppendInittab(name, initfunc);
Py_Initialize();
#if PY_MAJOR_VERSION < 3
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 7a5f037..0980802 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -595,6 +595,7 @@
event->mmap2.maj = bswap_32(event->mmap2.maj);
event->mmap2.min = bswap_32(event->mmap2.min);
event->mmap2.ino = bswap_64(event->mmap2.ino);
+ event->mmap2.ino_generation = bswap_64(event->mmap2.ino_generation);
if (sample_id_all) {
void *data = &event->mmap2.filename;
@@ -710,6 +711,18 @@
swap_sample_id_all(event, &event->namespaces.link_info[i]);
}
+static void perf_event__cgroup_swap(union perf_event *event, bool sample_id_all)
+{
+ event->cgroup.id = bswap_64(event->cgroup.id);
+
+ if (sample_id_all) {
+ void *data = &event->cgroup.path;
+
+ data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
+ swap_sample_id_all(event, data);
+ }
+}
+
static u8 revbyte(u8 b)
{
int rev = (b >> 4) | ((b & 0xf) << 4);
@@ -952,6 +965,7 @@
[PERF_RECORD_SWITCH] = perf_event__switch_swap,
[PERF_RECORD_SWITCH_CPU_WIDE] = perf_event__switch_swap,
[PERF_RECORD_NAMESPACES] = perf_event__namespaces_swap,
+ [PERF_RECORD_CGROUP] = perf_event__cgroup_swap,
[PERF_RECORD_TEXT_POKE] = perf_event__text_poke_swap,
[PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap,
[PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap,
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 6138866..0d14abd 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -515,6 +515,13 @@
}
}
+void dso__delete_symbol(struct dso *dso, struct symbol *sym)
+{
+ rb_erase_cached(&sym->rb_node, &dso->symbols);
+ symbol__delete(sym);
+ dso__reset_find_symbol_cache(dso);
+}
+
struct symbol *dso__find_symbol(struct dso *dso, u64 addr)
{
if (dso->last_find_result.addr != addr || dso->last_find_result.symbol == NULL) {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index f4801c4..954d6a0 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -131,6 +131,8 @@
void dso__insert_symbol(struct dso *dso,
struct symbol *sym);
+void dso__delete_symbol(struct dso *dso,
+ struct symbol *sym);
struct symbol *dso__find_symbol(struct dso *dso, u64 addr);
struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name);
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index 2b65512..f3e3c94 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -12,11 +12,12 @@
override CFLAGS += -O2 -Wall -I../../../include
override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"'
override CFLAGS += -DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"'
+override CFLAGS += -D_FILE_OFFSET_BITS=64
override CFLAGS += -D_FORTIFY_SOURCE=2
%: %.c
@mkdir -p $(BUILD_OUTPUT)
- $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap
+ $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap -lrt
.PHONY : clean
clean :
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index a6db83a..f6b7e85 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -335,7 +335,7 @@
.SH REFERENCES
Volume 3B: System Programming Guide"
-http://www.intel.com/products/processor/manuals/
+https://www.intel.com/products/processor/manuals/
.SH FILES
.ta
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 33b3708..f3a1746 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -79,6 +79,7 @@
unsigned long long cpuidle_cur_cpu_lpi_us;
unsigned long long cpuidle_cur_sys_lpi_us;
unsigned int gfx_cur_mhz;
+unsigned int gfx_act_mhz;
unsigned int tcc_activation_temp;
unsigned int tcc_activation_temp_override;
double rapl_power_units, rapl_time_units;
@@ -210,13 +211,14 @@
unsigned long long pkg_both_core_gfxe_c0;
long long gfx_rc6_ms;
unsigned int gfx_mhz;
+ unsigned int gfx_act_mhz;
unsigned int package_id;
- unsigned int energy_pkg; /* MSR_PKG_ENERGY_STATUS */
- unsigned int energy_dram; /* MSR_DRAM_ENERGY_STATUS */
- unsigned int energy_cores; /* MSR_PP0_ENERGY_STATUS */
- unsigned int energy_gfx; /* MSR_PP1_ENERGY_STATUS */
- unsigned int rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */
- unsigned int rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */
+ unsigned long long energy_pkg; /* MSR_PKG_ENERGY_STATUS */
+ unsigned long long energy_dram; /* MSR_DRAM_ENERGY_STATUS */
+ unsigned long long energy_cores; /* MSR_PP0_ENERGY_STATUS */
+ unsigned long long energy_gfx; /* MSR_PP1_ENERGY_STATUS */
+ unsigned long long rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */
+ unsigned long long rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */
unsigned int pkg_temp_c;
unsigned long long counter[MAX_ADDED_COUNTERS];
} *package_even, *package_odd;
@@ -259,6 +261,113 @@
#define SYSFS_PERCPU (1 << 1)
};
+/*
+ * The accumulated sum of MSR is defined as a monotonic
+ * increasing MSR, it will be accumulated periodically,
+ * despite its register's bit width.
+ */
+enum {
+ IDX_PKG_ENERGY,
+ IDX_DRAM_ENERGY,
+ IDX_PP0_ENERGY,
+ IDX_PP1_ENERGY,
+ IDX_PKG_PERF,
+ IDX_DRAM_PERF,
+ IDX_COUNT,
+};
+
+int get_msr_sum(int cpu, off_t offset, unsigned long long *msr);
+
+struct msr_sum_array {
+ /* get_msr_sum() = sum + (get_msr() - last) */
+ struct {
+ /*The accumulated MSR value is updated by the timer*/
+ unsigned long long sum;
+ /*The MSR footprint recorded in last timer*/
+ unsigned long long last;
+ } entries[IDX_COUNT];
+};
+
+/* The percpu MSR sum array.*/
+struct msr_sum_array *per_cpu_msr_sum;
+
+int idx_to_offset(int idx)
+{
+ int offset;
+
+ switch (idx) {
+ case IDX_PKG_ENERGY:
+ offset = MSR_PKG_ENERGY_STATUS;
+ break;
+ case IDX_DRAM_ENERGY:
+ offset = MSR_DRAM_ENERGY_STATUS;
+ break;
+ case IDX_PP0_ENERGY:
+ offset = MSR_PP0_ENERGY_STATUS;
+ break;
+ case IDX_PP1_ENERGY:
+ offset = MSR_PP1_ENERGY_STATUS;
+ break;
+ case IDX_PKG_PERF:
+ offset = MSR_PKG_PERF_STATUS;
+ break;
+ case IDX_DRAM_PERF:
+ offset = MSR_DRAM_PERF_STATUS;
+ break;
+ default:
+ offset = -1;
+ }
+ return offset;
+}
+
+int offset_to_idx(int offset)
+{
+ int idx;
+
+ switch (offset) {
+ case MSR_PKG_ENERGY_STATUS:
+ idx = IDX_PKG_ENERGY;
+ break;
+ case MSR_DRAM_ENERGY_STATUS:
+ idx = IDX_DRAM_ENERGY;
+ break;
+ case MSR_PP0_ENERGY_STATUS:
+ idx = IDX_PP0_ENERGY;
+ break;
+ case MSR_PP1_ENERGY_STATUS:
+ idx = IDX_PP1_ENERGY;
+ break;
+ case MSR_PKG_PERF_STATUS:
+ idx = IDX_PKG_PERF;
+ break;
+ case MSR_DRAM_PERF_STATUS:
+ idx = IDX_DRAM_PERF;
+ break;
+ default:
+ idx = -1;
+ }
+ return idx;
+}
+
+int idx_valid(int idx)
+{
+ switch (idx) {
+ case IDX_PKG_ENERGY:
+ return do_rapl & RAPL_PKG;
+ case IDX_DRAM_ENERGY:
+ return do_rapl & RAPL_DRAM;
+ case IDX_PP0_ENERGY:
+ return do_rapl & RAPL_CORES_ENERGY_STATUS;
+ case IDX_PP1_ENERGY:
+ return do_rapl & RAPL_GFX;
+ case IDX_PKG_PERF:
+ return do_rapl & RAPL_PKG_PERF_STATUS;
+ case IDX_DRAM_PERF:
+ return do_rapl & RAPL_DRAM_PERF_STATUS;
+ default:
+ return 0;
+ }
+}
struct sys_counters {
unsigned int added_thread_counters;
unsigned int added_core_counters;
@@ -451,6 +560,7 @@
{ 0x0, "APIC" },
{ 0x0, "X2APIC" },
{ 0x0, "Die" },
+ { 0x0, "GFXAMHz" },
};
#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
@@ -505,6 +615,7 @@
#define BIC_APIC (1ULL << 48)
#define BIC_X2APIC (1ULL << 49)
#define BIC_Die (1ULL << 50)
+#define BIC_GFXACTMHz (1ULL << 51)
#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
@@ -724,6 +835,9 @@
if (DO_BIC(BIC_GFXMHz))
outp += sprintf(outp, "%sGFXMHz", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_GFXACTMHz))
+ outp += sprintf(outp, "%sGFXAMHz", (printed++ ? delim : ""));
+
if (DO_BIC(BIC_Totl_c0))
outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : ""));
if (DO_BIC(BIC_Any_c0))
@@ -858,13 +972,13 @@
outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi);
outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi);
- outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg);
- outp += sprintf(outp, "Joules COR: %0X\n", p->energy_cores);
- outp += sprintf(outp, "Joules GFX: %0X\n", p->energy_gfx);
- outp += sprintf(outp, "Joules RAM: %0X\n", p->energy_dram);
- outp += sprintf(outp, "Throttle PKG: %0X\n",
+ outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg);
+ outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores);
+ outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx);
+ outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram);
+ outp += sprintf(outp, "Throttle PKG: %0llX\n",
p->rapl_pkg_perf_status);
- outp += sprintf(outp, "Throttle RAM: %0X\n",
+ outp += sprintf(outp, "Throttle RAM: %0llX\n",
p->rapl_dram_perf_status);
outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c);
@@ -1062,14 +1176,7 @@
}
}
- /*
- * If measurement interval exceeds minimum RAPL Joule Counter range,
- * indicate that results are suspect by printing "**" in fraction place.
- */
- if (interval_float < rapl_joule_counter_range)
- fmt8 = "%s%.2f";
- else
- fmt8 = "%6.0f**";
+ fmt8 = "%s%.2f";
if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float);
@@ -1098,6 +1205,10 @@
if (DO_BIC(BIC_GFXMHz))
outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_mhz);
+ /* GFXACTMHz */
+ if (DO_BIC(BIC_GFXACTMHz))
+ outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_act_mhz);
+
/* Totl%C0, Any%C0 GFX%C0 CPUGFX% */
if (DO_BIC(BIC_Totl_c0))
outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0/tsc);
@@ -1210,11 +1321,7 @@
}
#define DELTA_WRAP32(new, old) \
- if (new > old) { \
- old = new - old; \
- } else { \
- old = 0x100000000 + new - old; \
- }
+ old = ((((unsigned long long)new << 32) - ((unsigned long long)old << 32)) >> 32);
int
delta_package(struct pkg_data *new, struct pkg_data *old)
@@ -1253,13 +1360,14 @@
old->gfx_rc6_ms = new->gfx_rc6_ms - old->gfx_rc6_ms;
old->gfx_mhz = new->gfx_mhz;
+ old->gfx_act_mhz = new->gfx_act_mhz;
- DELTA_WRAP32(new->energy_pkg, old->energy_pkg);
- DELTA_WRAP32(new->energy_cores, old->energy_cores);
- DELTA_WRAP32(new->energy_gfx, old->energy_gfx);
- DELTA_WRAP32(new->energy_dram, old->energy_dram);
- DELTA_WRAP32(new->rapl_pkg_perf_status, old->rapl_pkg_perf_status);
- DELTA_WRAP32(new->rapl_dram_perf_status, old->rapl_dram_perf_status);
+ old->energy_pkg = new->energy_pkg - old->energy_pkg;
+ old->energy_cores = new->energy_cores - old->energy_cores;
+ old->energy_gfx = new->energy_gfx - old->energy_gfx;
+ old->energy_dram = new->energy_dram - old->energy_dram;
+ old->rapl_pkg_perf_status = new->rapl_pkg_perf_status - old->rapl_pkg_perf_status;
+ old->rapl_dram_perf_status = new->rapl_dram_perf_status - old->rapl_dram_perf_status;
for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
if (mp->format == FORMAT_RAW)
@@ -1469,6 +1577,7 @@
p->gfx_rc6_ms = 0;
p->gfx_mhz = 0;
+ p->gfx_act_mhz = 0;
for (i = 0, mp = sys.tp; mp; i++, mp = mp->next)
t->counter[i] = 0;
@@ -1564,6 +1673,7 @@
average.packages.gfx_rc6_ms = p->gfx_rc6_ms;
average.packages.gfx_mhz = p->gfx_mhz;
+ average.packages.gfx_act_mhz = p->gfx_act_mhz;
average.packages.pkg_temp_c = MAX(average.packages.pkg_temp_c, p->pkg_temp_c);
@@ -1784,7 +1894,7 @@
int i;
if (cpu_migrate(cpu)) {
- fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+ fprintf(outf, "get_counters: Could not migrate to CPU %d\n", cpu);
return -1;
}
@@ -1966,39 +2076,39 @@
p->sys_lpi = cpuidle_cur_sys_lpi_us;
if (do_rapl & RAPL_PKG) {
- if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr))
+ if (get_msr_sum(cpu, MSR_PKG_ENERGY_STATUS, &msr))
return -13;
- p->energy_pkg = msr & 0xFFFFFFFF;
+ p->energy_pkg = msr;
}
if (do_rapl & RAPL_CORES_ENERGY_STATUS) {
- if (get_msr(cpu, MSR_PP0_ENERGY_STATUS, &msr))
+ if (get_msr_sum(cpu, MSR_PP0_ENERGY_STATUS, &msr))
return -14;
- p->energy_cores = msr & 0xFFFFFFFF;
+ p->energy_cores = msr;
}
if (do_rapl & RAPL_DRAM) {
- if (get_msr(cpu, MSR_DRAM_ENERGY_STATUS, &msr))
+ if (get_msr_sum(cpu, MSR_DRAM_ENERGY_STATUS, &msr))
return -15;
- p->energy_dram = msr & 0xFFFFFFFF;
+ p->energy_dram = msr;
}
if (do_rapl & RAPL_GFX) {
- if (get_msr(cpu, MSR_PP1_ENERGY_STATUS, &msr))
+ if (get_msr_sum(cpu, MSR_PP1_ENERGY_STATUS, &msr))
return -16;
- p->energy_gfx = msr & 0xFFFFFFFF;
+ p->energy_gfx = msr;
}
if (do_rapl & RAPL_PKG_PERF_STATUS) {
- if (get_msr(cpu, MSR_PKG_PERF_STATUS, &msr))
+ if (get_msr_sum(cpu, MSR_PKG_PERF_STATUS, &msr))
return -16;
- p->rapl_pkg_perf_status = msr & 0xFFFFFFFF;
+ p->rapl_pkg_perf_status = msr;
}
if (do_rapl & RAPL_DRAM_PERF_STATUS) {
- if (get_msr(cpu, MSR_DRAM_PERF_STATUS, &msr))
+ if (get_msr_sum(cpu, MSR_DRAM_PERF_STATUS, &msr))
return -16;
- p->rapl_dram_perf_status = msr & 0xFFFFFFFF;
+ p->rapl_dram_perf_status = msr;
}
if (do_rapl & RAPL_AMD_F17H) {
- if (get_msr(cpu, MSR_PKG_ENERGY_STAT, &msr))
+ if (get_msr_sum(cpu, MSR_PKG_ENERGY_STAT, &msr))
return -13;
- p->energy_pkg = msr & 0xFFFFFFFF;
+ p->energy_pkg = msr;
}
if (DO_BIC(BIC_PkgTmp)) {
if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
@@ -2012,6 +2122,9 @@
if (DO_BIC(BIC_GFXMHz))
p->gfx_mhz = gfx_cur_mhz;
+ if (DO_BIC(BIC_GFXACTMHz))
+ p->gfx_act_mhz = gfx_act_mhz;
+
for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
if (get_mp(cpu, mp, &p->counter[i]))
return -10;
@@ -2173,6 +2286,7 @@
case INTEL_FAM6_ATOM_GOLDMONT:
case INTEL_FAM6_SKYLAKE_X:
case INTEL_FAM6_ATOM_GOLDMONT_D:
+ case INTEL_FAM6_ATOM_TREMONT_D:
return 1;
}
return 0;
@@ -2650,7 +2764,12 @@
sprintf(path,
"/sys/devices/system/cpu/cpu%d/topology/thread_siblings", cpu);
- filep = fopen_or_die(path, "r");
+ filep = fopen(path, "r");
+
+ if (!filep) {
+ warnx("%s: open failed", path);
+ return -1;
+ }
do {
offset -= BITMASK_SIZE;
if (fscanf(filep, "%lx%c", &map, &character) != 2)
@@ -2763,18 +2882,25 @@
{
free_all_buffers();
setup_all_buffers();
- printf("turbostat: re-initialized with num_cpus %d\n", topo.num_cpus);
+ fprintf(outf, "turbostat: re-initialized with num_cpus %d\n", topo.num_cpus);
}
void set_max_cpu_num(void)
{
FILE *filep;
+ int base_cpu;
unsigned long dummy;
+ char pathname[64];
+ base_cpu = sched_getcpu();
+ if (base_cpu < 0)
+ err(1, "cannot find calling cpu ID");
+ sprintf(pathname,
+ "/sys/devices/system/cpu/cpu%d/topology/thread_siblings",
+ base_cpu);
+
+ filep = fopen_or_die(pathname, "r");
topo.max_cpu_num = 0;
- filep = fopen_or_die(
- "/sys/devices/system/cpu/cpu0/topology/thread_siblings",
- "r");
while (fscanf(filep, "%lx,", &dummy) == 1)
topo.max_cpu_num += BITMASK_SIZE;
fclose(filep);
@@ -2916,6 +3042,33 @@
}
/*
+ * snapshot_gfx_cur_mhz()
+ *
+ * record snapshot of
+ * /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz
+ *
+ * return 1 if config change requires a restart, else return 0
+ */
+int snapshot_gfx_act_mhz(void)
+{
+ static FILE *fp;
+ int retval;
+
+ if (fp == NULL)
+ fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r");
+ else {
+ rewind(fp);
+ fflush(fp);
+ }
+
+ retval = fscanf(fp, "%d", &gfx_act_mhz);
+ if (retval != 1)
+ err(1, "GFX ACT MHz");
+
+ return 0;
+}
+
+/*
* snapshot_cpu_lpi()
*
* record snapshot of
@@ -2980,6 +3133,9 @@
if (DO_BIC(BIC_GFXMHz))
snapshot_gfx_mhz();
+ if (DO_BIC(BIC_GFXACTMHz))
+ snapshot_gfx_act_mhz();
+
if (DO_BIC(BIC_CPU_LPI))
snapshot_cpu_lpi_us();
@@ -3057,6 +3213,111 @@
}
}
+int get_msr_sum(int cpu, off_t offset, unsigned long long *msr)
+{
+ int ret, idx;
+ unsigned long long msr_cur, msr_last;
+
+ if (!per_cpu_msr_sum)
+ return 1;
+
+ idx = offset_to_idx(offset);
+ if (idx < 0)
+ return idx;
+ /* get_msr_sum() = sum + (get_msr() - last) */
+ ret = get_msr(cpu, offset, &msr_cur);
+ if (ret)
+ return ret;
+ msr_last = per_cpu_msr_sum[cpu].entries[idx].last;
+ DELTA_WRAP32(msr_cur, msr_last);
+ *msr = msr_last + per_cpu_msr_sum[cpu].entries[idx].sum;
+
+ return 0;
+}
+
+timer_t timerid;
+
+/* Timer callback, update the sum of MSRs periodically. */
+static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+ int i, ret;
+ int cpu = t->cpu_id;
+
+ for (i = IDX_PKG_ENERGY; i < IDX_COUNT; i++) {
+ unsigned long long msr_cur, msr_last;
+ int offset;
+
+ if (!idx_valid(i))
+ continue;
+ offset = idx_to_offset(i);
+ if (offset < 0)
+ continue;
+ ret = get_msr(cpu, offset, &msr_cur);
+ if (ret) {
+ fprintf(outf, "Can not update msr(0x%x)\n", offset);
+ continue;
+ }
+
+ msr_last = per_cpu_msr_sum[cpu].entries[i].last;
+ per_cpu_msr_sum[cpu].entries[i].last = msr_cur & 0xffffffff;
+
+ DELTA_WRAP32(msr_cur, msr_last);
+ per_cpu_msr_sum[cpu].entries[i].sum += msr_last;
+ }
+ return 0;
+}
+
+static void
+msr_record_handler(union sigval v)
+{
+ for_all_cpus(update_msr_sum, EVEN_COUNTERS);
+}
+
+void msr_sum_record(void)
+{
+ struct itimerspec its;
+ struct sigevent sev;
+
+ per_cpu_msr_sum = calloc(topo.max_cpu_num + 1, sizeof(struct msr_sum_array));
+ if (!per_cpu_msr_sum) {
+ fprintf(outf, "Can not allocate memory for long time MSR.\n");
+ return;
+ }
+ /*
+ * Signal handler might be restricted, so use thread notifier instead.
+ */
+ memset(&sev, 0, sizeof(struct sigevent));
+ sev.sigev_notify = SIGEV_THREAD;
+ sev.sigev_notify_function = msr_record_handler;
+
+ sev.sigev_value.sival_ptr = &timerid;
+ if (timer_create(CLOCK_REALTIME, &sev, &timerid) == -1) {
+ fprintf(outf, "Can not create timer.\n");
+ goto release_msr;
+ }
+
+ its.it_value.tv_sec = 0;
+ its.it_value.tv_nsec = 1;
+ /*
+ * A wraparound time has been calculated early.
+ * Some sources state that the peak power for a
+ * microprocessor is usually 1.5 times the TDP rating,
+ * use 2 * TDP for safety.
+ */
+ its.it_interval.tv_sec = rapl_joule_counter_range / 2;
+ its.it_interval.tv_nsec = 0;
+
+ if (timer_settime(timerid, 0, &its, NULL) == -1) {
+ fprintf(outf, "Can not set timer.\n");
+ goto release_timer;
+ }
+ return;
+
+ release_timer:
+ timer_delete(timerid);
+ release_msr:
+ free(per_cpu_msr_sum);
+}
void turbostat_loop()
{
@@ -3075,7 +3336,7 @@
if (retval < -1) {
exit(retval);
} else if (retval == -1) {
- if (restarted > 1) {
+ if (restarted > 10) {
exit(retval);
}
re_initialize();
@@ -3279,6 +3540,7 @@
case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */
case INTEL_FAM6_ATOM_TREMONT: /* EHL */
+ case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */
pkg_cstate_limits = glm_pkg_cstate_limits;
break;
default:
@@ -3361,6 +3623,17 @@
}
return 0;
}
+int is_jvl(unsigned int family, unsigned int model)
+{
+ if (!genuine_intel)
+ return 0;
+
+ switch (model) {
+ case INTEL_FAM6_ATOM_TREMONT_D:
+ return 1;
+ }
+ return 0;
+}
int has_turbo_ratio_limit(unsigned int family, unsigned int model)
{
@@ -3475,6 +3748,20 @@
}
static void
+remove_underbar(char *s)
+{
+ char *to = s;
+
+ while (*s) {
+ if (*s != '_')
+ *to++ = *s;
+ s++;
+ }
+
+ *to = 0;
+}
+
+static void
dump_cstate_pstate_config_info(unsigned int family, unsigned int model)
{
if (!do_nhm_platform_info)
@@ -3530,9 +3817,6 @@
int state;
char *sp;
- if (!DO_BIC(BIC_sysfs))
- return;
-
if (access("/sys/devices/system/cpu/cpuidle", R_OK)) {
fprintf(outf, "cpuidle not loaded\n");
return;
@@ -3559,6 +3843,8 @@
*sp = '\0';
fclose(input);
+ remove_underbar(name_buf);
+
sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc",
base_cpu, state);
input = fopen(path, "r");
@@ -3645,7 +3931,7 @@
return 0;
if (cpu_migrate(cpu)) {
- fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+ fprintf(outf, "print_epb: Could not migrate to CPU %d\n", cpu);
return -1;
}
@@ -3689,7 +3975,7 @@
return 0;
if (cpu_migrate(cpu)) {
- fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+ fprintf(outf, "print_hwp: Could not migrate to CPU %d\n", cpu);
return -1;
}
@@ -3777,7 +4063,7 @@
return 0;
if (cpu_migrate(cpu)) {
- fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+ fprintf(outf, "print_perf_limit: Could not migrate to CPU %d\n", cpu);
return -1;
}
@@ -3881,13 +4167,8 @@
double get_tdp_amd(unsigned int family)
{
- switch (family) {
- case 0x17:
- case 0x18:
- default:
- /* This is the max stock TDP of HEDT/Server Fam17h chips */
- return 250.0;
- }
+ /* This is the max stock TDP of HEDT/Server Fam17h+ chips */
+ return 280.0;
}
/*
@@ -3959,6 +4240,14 @@
BIC_PRESENT(BIC_GFXWatt);
}
break;
+ case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */
+ do_rapl = RAPL_PKG | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
+ BIC_PRESENT(BIC_PKG__);
+ if (rapl_joules)
+ BIC_PRESENT(BIC_Pkg_J);
+ else
+ BIC_PRESENT(BIC_PkgWatt);
+ break;
case INTEL_FAM6_SKYLAKE_L: /* SKL */
case INTEL_FAM6_CANNONLAKE_L: /* CNL */
do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO;
@@ -4069,27 +4358,20 @@
if (max_extended_level >= 0x80000007) {
__cpuid(0x80000007, eax, ebx, ecx, edx);
- /* RAPL (Fam 17h) */
+ /* RAPL (Fam 17h+) */
has_rapl = edx & (1 << 14);
}
- if (!has_rapl)
+ if (!has_rapl || family < 0x17)
return;
- switch (family) {
- case 0x17: /* Zen, Zen+ */
- case 0x18: /* Hygon Dhyana */
- do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY;
- if (rapl_joules) {
- BIC_PRESENT(BIC_Pkg_J);
- BIC_PRESENT(BIC_Cor_J);
- } else {
- BIC_PRESENT(BIC_PkgWatt);
- BIC_PRESENT(BIC_CorWatt);
- }
- break;
- default:
- return;
+ do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY;
+ if (rapl_joules) {
+ BIC_PRESENT(BIC_Pkg_J);
+ BIC_PRESENT(BIC_Cor_J);
+ } else {
+ BIC_PRESENT(BIC_PkgWatt);
+ BIC_PRESENT(BIC_CorWatt);
}
if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr))
@@ -4162,7 +4444,7 @@
return 0;
if (cpu_migrate(cpu)) {
- fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+ fprintf(outf, "print_thermal: Could not migrate to CPU %d\n", cpu);
return -1;
}
@@ -4234,7 +4516,7 @@
cpu = t->cpu_id;
if (cpu_migrate(cpu)) {
- fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+ fprintf(outf, "print_rapl: Could not migrate to CPU %d\n", cpu);
return -1;
}
@@ -4361,6 +4643,7 @@
case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */
case INTEL_FAM6_ATOM_TREMONT: /* EHL */
+ case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */
return 1;
}
return 0;
@@ -4507,12 +4790,33 @@
* below this value, including the Digital Thermal Sensor (DTS),
* Package Thermal Management Sensor (PTM), and thermal event thresholds.
*/
-int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+int read_tcc_activation_temp()
{
unsigned long long msr;
- unsigned int target_c_local;
- int cpu;
+ unsigned int tcc, target_c, offset_c;
+ /* Temperature Target MSR is Nehalem and newer only */
+ if (!do_nhm_platform_info)
+ return 0;
+
+ if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr))
+ return 0;
+
+ target_c = (msr >> 16) & 0xFF;
+
+ offset_c = (msr >> 24) & 0xF;
+
+ tcc = target_c - offset_c;
+
+ if (!quiet)
+ fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C) (%d default - %d offset)\n",
+ base_cpu, msr, tcc, target_c, offset_c);
+
+ return tcc;
+}
+
+int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
/* tcc_activation_temp is used only for dts or ptm */
if (!(do_dts || do_ptm))
return 0;
@@ -4521,43 +4825,18 @@
if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
return 0;
- cpu = t->cpu_id;
- if (cpu_migrate(cpu)) {
- fprintf(outf, "Could not migrate to CPU %d\n", cpu);
- return -1;
- }
-
if (tcc_activation_temp_override != 0) {
tcc_activation_temp = tcc_activation_temp_override;
- fprintf(outf, "cpu%d: Using cmdline TCC Target (%d C)\n",
- cpu, tcc_activation_temp);
+ fprintf(outf, "Using cmdline TCC Target (%d C)\n", tcc_activation_temp);
return 0;
}
- /* Temperature Target MSR is Nehalem and newer only */
- if (!do_nhm_platform_info)
- goto guess;
+ tcc_activation_temp = read_tcc_activation_temp();
+ if (tcc_activation_temp)
+ return 0;
- if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr))
- goto guess;
-
- target_c_local = (msr >> 16) & 0xFF;
-
- if (!quiet)
- fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n",
- cpu, msr, target_c_local);
-
- if (!target_c_local)
- goto guess;
-
- tcc_activation_temp = target_c_local;
-
- return 0;
-
-guess:
tcc_activation_temp = TJMAX_DEFAULT;
- fprintf(outf, "cpu%d: Guessing tjMax %d C, Please use -T to specify\n",
- cpu, tcc_activation_temp);
+ fprintf(outf, "Guessing tjMax %d C, Please use -T to specify\n", tcc_activation_temp);
return 0;
}
@@ -4685,19 +4964,46 @@
case INTEL_FAM6_ICELAKE_NNPI:
case INTEL_FAM6_TIGERLAKE_L:
case INTEL_FAM6_TIGERLAKE:
+ case INTEL_FAM6_ROCKETLAKE:
+ case INTEL_FAM6_LAKEFIELD:
+ case INTEL_FAM6_ALDERLAKE:
return INTEL_FAM6_CANNONLAKE_L;
- case INTEL_FAM6_ATOM_TREMONT_D:
- return INTEL_FAM6_ATOM_GOLDMONT_D;
-
case INTEL_FAM6_ATOM_TREMONT_L:
return INTEL_FAM6_ATOM_TREMONT;
case INTEL_FAM6_ICELAKE_X:
+ case INTEL_FAM6_SAPPHIRERAPIDS_X:
return INTEL_FAM6_SKYLAKE_X;
}
return model;
}
+
+void print_dev_latency(void)
+{
+ char *path = "/dev/cpu_dma_latency";
+ int fd;
+ int value;
+ int retval;
+
+ fd = open(path, O_RDONLY);
+ if (fd < 0) {
+ warn("fopen %s\n", path);
+ return;
+ }
+
+ retval = read(fd, (void *)&value, sizeof(int));
+ if (retval != sizeof(int)) {
+ warn("read %s\n", path);
+ close(fd);
+ return;
+ }
+ fprintf(outf, "/dev/cpu_dma_latency: %d usec (%s)\n",
+ value, value == 2000000000 ? "default" : "constrained");
+
+ close(fd);
+}
+
void process_cpuid()
{
unsigned int eax, ebx, ecx, edx;
@@ -4916,6 +5222,14 @@
BIC_PRESENT(BIC_Mod_c6);
use_c1_residency_msr = 1;
}
+ if (is_jvl(family, model)) {
+ BIC_NOT_PRESENT(BIC_CPU_c3);
+ BIC_NOT_PRESENT(BIC_CPU_c7);
+ BIC_NOT_PRESENT(BIC_Pkgpc2);
+ BIC_NOT_PRESENT(BIC_Pkgpc3);
+ BIC_NOT_PRESENT(BIC_Pkgpc6);
+ BIC_NOT_PRESENT(BIC_Pkgpc7);
+ }
if (is_dnv(family, model)) {
BIC_PRESENT(BIC_CPU_c1);
BIC_NOT_PRESENT(BIC_CPU_c3);
@@ -4935,9 +5249,12 @@
BIC_NOT_PRESENT(BIC_Pkgpc7);
}
if (has_c8910_msrs(family, model)) {
- BIC_PRESENT(BIC_Pkgpc8);
- BIC_PRESENT(BIC_Pkgpc9);
- BIC_PRESENT(BIC_Pkgpc10);
+ if (pkg_cstate_limit >= PCL__8)
+ BIC_PRESENT(BIC_Pkgpc8);
+ if (pkg_cstate_limit >= PCL__9)
+ BIC_PRESENT(BIC_Pkgpc9);
+ if (pkg_cstate_limit >= PCL_10)
+ BIC_PRESENT(BIC_Pkgpc10);
}
do_irtl_hsw = has_c8910_msrs(family, model);
if (has_skl_msrs(family, model)) {
@@ -4967,6 +5284,8 @@
dump_cstate_pstate_config_info(family, model);
if (!quiet)
+ print_dev_latency();
+ if (!quiet)
dump_sysfs_cstate_config();
if (!quiet)
dump_sysfs_pstate_config();
@@ -4980,6 +5299,9 @@
if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
BIC_PRESENT(BIC_GFXMHz);
+ if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK))
+ BIC_PRESENT(BIC_GFXACTMHz);
+
if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK))
BIC_PRESENT(BIC_CPU_LPI);
else
@@ -5390,7 +5712,7 @@
}
void print_version() {
- fprintf(outf, "turbostat version 20.03.20"
+ fprintf(outf, "turbostat version 20.09.30"
" - Len Brown <lenb@kernel.org>\n");
}
@@ -5597,6 +5919,8 @@
*sp = '%';
*(sp + 1) = '\0';
+ remove_underbar(name_buf);
+
fclose(input);
sprintf(path, "cpuidle/state%d/time", state);
@@ -5624,6 +5948,8 @@
*sp = '\0';
fclose(input);
+ remove_underbar(name_buf);
+
sprintf(path, "cpuidle/state%d/usage", state);
if (is_deferred_skip(name_buf))
@@ -5868,6 +6194,7 @@
return 0;
}
+ msr_sum_record();
/*
* if any params left, it must be a command to fork
*/
diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
index 3fe1eed..ff6c666 100644
--- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
+++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
@@ -622,6 +622,57 @@
}
}
+/*
+ * Open a file, and exit on failure
+ */
+FILE *fopen_or_die(const char *path, const char *mode)
+{
+ FILE *filep = fopen(path, "r");
+
+ if (!filep)
+ err(1, "%s: open failed", path);
+ return filep;
+}
+
+void err_on_hypervisor(void)
+{
+ FILE *cpuinfo;
+ char *flags, *hypervisor;
+ char *buffer;
+
+ /* On VMs /proc/cpuinfo contains a "flags" entry for hypervisor */
+ cpuinfo = fopen_or_die("/proc/cpuinfo", "ro");
+
+ buffer = malloc(4096);
+ if (!buffer) {
+ fclose(cpuinfo);
+ err(-ENOMEM, "buffer malloc fail");
+ }
+
+ if (!fread(buffer, 1024, 1, cpuinfo)) {
+ fclose(cpuinfo);
+ free(buffer);
+ err(1, "Reading /proc/cpuinfo failed");
+ }
+
+ flags = strstr(buffer, "flags");
+ rewind(cpuinfo);
+ fseek(cpuinfo, flags - buffer, SEEK_SET);
+ if (!fgets(buffer, 4096, cpuinfo)) {
+ fclose(cpuinfo);
+ free(buffer);
+ err(1, "Reading /proc/cpuinfo failed");
+ }
+ fclose(cpuinfo);
+
+ hypervisor = strstr(buffer, "hypervisor");
+
+ free(buffer);
+
+ if (hypervisor)
+ err(-1,
+ "not supported on this virtual machine");
+}
int get_msr(int cpu, int offset, unsigned long long *msr)
{
@@ -635,8 +686,10 @@
err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname);
retval = pread(fd, msr, sizeof(*msr), offset);
- if (retval != sizeof(*msr))
+ if (retval != sizeof(*msr)) {
+ err_on_hypervisor();
err(-1, "%s offset 0x%llx read failed", pathname, (unsigned long long)offset);
+ }
if (debug > 1)
fprintf(stderr, "get_msr(cpu%d, 0x%X, 0x%llX)\n", cpu, offset, *msr);
@@ -1086,18 +1139,6 @@
return 0;
}
-/*
- * Open a file, and exit on failure
- */
-FILE *fopen_or_die(const char *path, const char *mode)
-{
- FILE *filep = fopen(path, "r");
-
- if (!filep)
- err(1, "%s: open failed", path);
- return filep;
-}
-
unsigned int get_pkg_num(int cpu)
{
FILE *fp;
diff --git a/tools/testing/kunit/.gitattributes b/tools/testing/kunit/.gitattributes
deleted file mode 100644
index 5b7da1f..0000000
--- a/tools/testing/kunit/.gitattributes
+++ /dev/null
@@ -1 +0,0 @@
-test_data/* binary
diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py
index ebf5f57..d4f7846 100755
--- a/tools/testing/kunit/kunit.py
+++ b/tools/testing/kunit/kunit.py
@@ -11,7 +11,6 @@
import sys
import os
import time
-import shutil
from collections import namedtuple
from enum import Enum, auto
@@ -44,11 +43,6 @@
BUILD_FAILURE = auto()
TEST_FAILURE = auto()
-def create_default_kunitconfig():
- if not os.path.exists(kunit_kernel.kunitconfig_path):
- shutil.copyfile('arch/um/configs/kunit_defconfig',
- kunit_kernel.kunitconfig_path)
-
def get_kernel_root_path():
parts = sys.argv[0] if not __file__ else __file__
parts = os.path.realpath(parts).split('tools/testing/kunit')
@@ -61,7 +55,6 @@
kunit_parser.print_with_timestamp('Configuring KUnit Kernel ...')
config_start = time.time()
- create_default_kunitconfig()
success = linux.build_reconfig(request.build_dir, request.make_options)
config_end = time.time()
if not success:
@@ -262,12 +255,12 @@
if not os.path.exists(cli_args.build_dir):
os.mkdir(cli_args.build_dir)
- if not os.path.exists(kunit_kernel.kunitconfig_path):
- create_default_kunitconfig()
-
if not linux:
linux = kunit_kernel.LinuxSourceTree()
+ linux.create_kunitconfig(cli_args.build_dir)
+ linux.read_kunitconfig(cli_args.build_dir)
+
request = KunitRequest(cli_args.raw_output,
cli_args.timeout,
cli_args.jobs,
@@ -283,12 +276,12 @@
not os.path.exists(cli_args.build_dir)):
os.mkdir(cli_args.build_dir)
- if not os.path.exists(kunit_kernel.kunitconfig_path):
- create_default_kunitconfig()
-
if not linux:
linux = kunit_kernel.LinuxSourceTree()
+ linux.create_kunitconfig(cli_args.build_dir)
+ linux.read_kunitconfig(cli_args.build_dir)
+
request = KunitConfigRequest(cli_args.build_dir,
cli_args.make_options)
result = config_tests(linux, request)
@@ -301,6 +294,9 @@
if not linux:
linux = kunit_kernel.LinuxSourceTree()
+ linux.create_kunitconfig(cli_args.build_dir)
+ linux.read_kunitconfig(cli_args.build_dir)
+
request = KunitBuildRequest(cli_args.jobs,
cli_args.build_dir,
cli_args.alltests,
@@ -315,6 +311,9 @@
if not linux:
linux = kunit_kernel.LinuxSourceTree()
+ linux.create_kunitconfig(cli_args.build_dir)
+ linux.read_kunitconfig(cli_args.build_dir)
+
exec_request = KunitExecRequest(cli_args.timeout,
cli_args.build_dir,
cli_args.alltests)
@@ -337,7 +336,7 @@
kunit_output = f.read().splitlines()
request = KunitParseRequest(cli_args.raw_output,
kunit_output,
- cli_args.build_dir,
+ None,
cli_args.json)
result = parse_tests(request)
if result.status != KunitStatus.SUCCESS:
diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py
index b557b1e..2e3cc0f 100644
--- a/tools/testing/kunit/kunit_kernel.py
+++ b/tools/testing/kunit/kunit_kernel.py
@@ -6,10 +6,10 @@
# Author: Felix Guo <felixguoxiuping@gmail.com>
# Author: Brendan Higgins <brendanhiggins@google.com>
-
import logging
import subprocess
import os
+import shutil
import signal
from contextlib import ExitStack
@@ -18,8 +18,10 @@
import kunit_parser
KCONFIG_PATH = '.config'
-kunitconfig_path = '.kunitconfig'
+KUNITCONFIG_PATH = '.kunitconfig'
+DEFAULT_KUNITCONFIG_PATH = 'arch/um/configs/kunit_defconfig'
BROKEN_ALLCONFIG_PATH = 'tools/testing/kunit/configs/broken_on_uml.config'
+OUTFILE_PATH = 'test.log'
class ConfigError(Exception):
"""Represents an error trying to configure the Linux kernel."""
@@ -82,36 +84,51 @@
if build_dir:
command += ['O=' + build_dir]
try:
- subprocess.check_output(command, stderr=subprocess.STDOUT)
+ proc = subprocess.Popen(command,
+ stderr=subprocess.PIPE,
+ stdout=subprocess.DEVNULL)
except OSError as e:
- raise BuildError('Could not call execute make: ' + str(e))
- except subprocess.CalledProcessError as e:
- raise BuildError(e.output.decode())
+ raise BuildError('Could not call make command: ' + str(e))
+ _, stderr = proc.communicate()
+ if proc.returncode != 0:
+ raise BuildError(stderr.decode())
+ if stderr: # likely only due to build warnings
+ print(stderr.decode())
- def linux_bin(self, params, timeout, build_dir, outfile):
+ def linux_bin(self, params, timeout, build_dir):
"""Runs the Linux UML binary. Must be named 'linux'."""
linux_bin = './linux'
if build_dir:
linux_bin = os.path.join(build_dir, 'linux')
+ outfile = get_outfile_path(build_dir)
with open(outfile, 'w') as output:
process = subprocess.Popen([linux_bin] + params,
stdout=output,
stderr=subprocess.STDOUT)
process.wait(timeout)
-
def get_kconfig_path(build_dir):
kconfig_path = KCONFIG_PATH
if build_dir:
kconfig_path = os.path.join(build_dir, KCONFIG_PATH)
return kconfig_path
+def get_kunitconfig_path(build_dir):
+ kunitconfig_path = KUNITCONFIG_PATH
+ if build_dir:
+ kunitconfig_path = os.path.join(build_dir, KUNITCONFIG_PATH)
+ return kunitconfig_path
+
+def get_outfile_path(build_dir):
+ outfile_path = OUTFILE_PATH
+ if build_dir:
+ outfile_path = os.path.join(build_dir, OUTFILE_PATH)
+ return outfile_path
+
class LinuxSourceTree(object):
"""Represents a Linux kernel source tree with KUnit tests."""
def __init__(self):
- self._kconfig = kunit_config.Kconfig()
- self._kconfig.read_from_file(kunitconfig_path)
self._ops = LinuxSourceTreeOperations()
signal.signal(signal.SIGINT, self.signal_handler)
@@ -123,6 +140,16 @@
return False
return True
+ def create_kunitconfig(self, build_dir, defconfig=DEFAULT_KUNITCONFIG_PATH):
+ kunitconfig_path = get_kunitconfig_path(build_dir)
+ if not os.path.exists(kunitconfig_path):
+ shutil.copyfile(defconfig, kunitconfig_path)
+
+ def read_kunitconfig(self, build_dir):
+ kunitconfig_path = get_kunitconfig_path(build_dir)
+ self._kconfig = kunit_config.Kconfig()
+ self._kconfig.read_from_file(kunitconfig_path)
+
def validate_config(self, build_dir):
kconfig_path = get_kconfig_path(build_dir)
validated_kconfig = kunit_config.Kconfig()
@@ -178,8 +205,8 @@
def run_kernel(self, args=[], build_dir='', timeout=None):
args.extend(['mem=1G'])
- outfile = 'test.log'
- self._ops.linux_bin(args, timeout, build_dir, outfile)
+ self._ops.linux_bin(args, timeout, build_dir)
+ outfile = get_outfile_path(build_dir)
subprocess.call(['stty', 'sane'])
with open(outfile, 'r') as file:
for line in file:
diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py
index 8019e3d..bbfe1b4 100644
--- a/tools/testing/kunit/kunit_parser.py
+++ b/tools/testing/kunit/kunit_parser.py
@@ -12,7 +12,7 @@
from datetime import datetime
from enum import Enum, auto
from functools import reduce
-from typing import List
+from typing import List, Optional, Tuple
TestResult = namedtuple('TestResult', ['status','suites','log'])
@@ -54,6 +54,7 @@
def isolate_kunit_output(kernel_output):
started = False
for line in kernel_output:
+ line = line.rstrip() # line always has a trailing \n
if kunit_start_re.search(line):
prefix_len = len(line.split('TAP version')[0])
started = True
@@ -65,8 +66,7 @@
def raw_output(kernel_output):
for line in kernel_output:
- print(line)
- yield line
+ print(line.rstrip())
DIVIDER = '=' * 60
@@ -152,7 +152,7 @@
else:
return False
-def parse_test_case(lines: List[str]) -> TestCase:
+def parse_test_case(lines: List[str]) -> Optional[TestCase]:
test_case = TestCase()
save_non_diagnositic(lines, test_case)
while parse_diagnostic(lines, test_case):
@@ -164,7 +164,7 @@
SUBTEST_HEADER = re.compile(r'^[\s]+# Subtest: (.*)$')
-def parse_subtest_header(lines: List[str]) -> str:
+def parse_subtest_header(lines: List[str]) -> Optional[str]:
consume_non_diagnositic(lines)
if not lines:
return None
@@ -177,7 +177,7 @@
SUBTEST_PLAN = re.compile(r'[\s]+[0-9]+\.\.([0-9]+)')
-def parse_subtest_plan(lines: List[str]) -> int:
+def parse_subtest_plan(lines: List[str]) -> Optional[int]:
consume_non_diagnositic(lines)
match = SUBTEST_PLAN.match(lines[0])
if match:
@@ -231,7 +231,7 @@
max_test_case_status = bubble_up_errors(lambda x: x.status, test_suite.cases)
return max_status(max_test_case_status, test_suite.status)
-def parse_test_suite(lines: List[str], expected_suite_index: int) -> TestSuite:
+def parse_test_suite(lines: List[str], expected_suite_index: int) -> Optional[TestSuite]:
if not lines:
return None
consume_non_diagnositic(lines)
@@ -242,7 +242,7 @@
return None
test_suite.name = name
expected_test_case_num = parse_subtest_plan(lines)
- if not expected_test_case_num:
+ if expected_test_case_num is None:
return None
while expected_test_case_num > 0:
test_case = parse_test_case(lines)
@@ -272,7 +272,7 @@
TEST_PLAN = re.compile(r'[0-9]+\.\.([0-9]+)')
-def parse_test_plan(lines: List[str]) -> int:
+def parse_test_plan(lines: List[str]) -> Optional[int]:
consume_non_diagnositic(lines)
match = TEST_PLAN.match(lines[0])
if match:
@@ -311,7 +311,7 @@
else:
return TestResult(TestStatus.NO_TESTS, [], lines)
-def print_and_count_results(test_result: TestResult) -> None:
+def print_and_count_results(test_result: TestResult) -> Tuple[int, int, int]:
total_tests = 0
failed_tests = 0
crashed_tests = 0
diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py
index 99c3c56..497ab51 100755
--- a/tools/testing/kunit/kunit_tool_test.py
+++ b/tools/testing/kunit/kunit_tool_test.py
@@ -102,7 +102,7 @@
'test_data/test_output_isolated_correctly.log')
file = open(log_path)
result = kunit_parser.isolate_kunit_output(file.readlines())
- self.assertContains('TAP version 14\n', result)
+ self.assertContains('TAP version 14', result)
self.assertContains(' # Subtest: example', result)
self.assertContains(' 1..2', result)
self.assertContains(' ok 1 - example_simple_test', result)
@@ -115,7 +115,7 @@
'test_data/test_pound_sign.log')
with open(log_path) as file:
result = kunit_parser.isolate_kunit_output(file.readlines())
- self.assertContains('TAP version 14\n', result)
+ self.assertContains('TAP version 14', result)
self.assertContains(' # Subtest: kunit-resource-test', result)
self.assertContains(' 1..5', result)
self.assertContains(' ok 1 - kunit_resource_test_init_resources', result)
@@ -179,7 +179,7 @@
print_mock = mock.patch('builtins.print').start()
result = kunit_parser.parse_run_tests(
kunit_parser.isolate_kunit_output(file.readlines()))
- print_mock.assert_any_call(StrContains("no kunit output detected"))
+ print_mock.assert_any_call(StrContains('no tests run!'))
print_mock.stop()
file.close()
@@ -198,39 +198,57 @@
'test_data/test_config_printk_time.log')
with open(prefix_log) as file:
result = kunit_parser.parse_run_tests(file.readlines())
- self.assertEqual('kunit-resource-test', result.suites[0].name)
+ self.assertEqual(
+ kunit_parser.TestStatus.SUCCESS,
+ result.status)
+ self.assertEqual('kunit-resource-test', result.suites[0].name)
def test_ignores_multiple_prefixes(self):
prefix_log = get_absolute_path(
'test_data/test_multiple_prefixes.log')
with open(prefix_log) as file:
result = kunit_parser.parse_run_tests(file.readlines())
- self.assertEqual('kunit-resource-test', result.suites[0].name)
+ self.assertEqual(
+ kunit_parser.TestStatus.SUCCESS,
+ result.status)
+ self.assertEqual('kunit-resource-test', result.suites[0].name)
def test_prefix_mixed_kernel_output(self):
mixed_prefix_log = get_absolute_path(
'test_data/test_interrupted_tap_output.log')
with open(mixed_prefix_log) as file:
result = kunit_parser.parse_run_tests(file.readlines())
- self.assertEqual('kunit-resource-test', result.suites[0].name)
+ self.assertEqual(
+ kunit_parser.TestStatus.SUCCESS,
+ result.status)
+ self.assertEqual('kunit-resource-test', result.suites[0].name)
def test_prefix_poundsign(self):
pound_log = get_absolute_path('test_data/test_pound_sign.log')
with open(pound_log) as file:
result = kunit_parser.parse_run_tests(file.readlines())
- self.assertEqual('kunit-resource-test', result.suites[0].name)
+ self.assertEqual(
+ kunit_parser.TestStatus.SUCCESS,
+ result.status)
+ self.assertEqual('kunit-resource-test', result.suites[0].name)
def test_kernel_panic_end(self):
panic_log = get_absolute_path('test_data/test_kernel_panic_interrupt.log')
with open(panic_log) as file:
result = kunit_parser.parse_run_tests(file.readlines())
- self.assertEqual('kunit-resource-test', result.suites[0].name)
+ self.assertEqual(
+ kunit_parser.TestStatus.TEST_CRASHED,
+ result.status)
+ self.assertEqual('kunit-resource-test', result.suites[0].name)
def test_pound_no_prefix(self):
pound_log = get_absolute_path('test_data/test_pound_no_prefix.log')
with open(pound_log) as file:
result = kunit_parser.parse_run_tests(file.readlines())
- self.assertEqual('kunit-resource-test', result.suites[0].name)
+ self.assertEqual(
+ kunit_parser.TestStatus.SUCCESS,
+ result.status)
+ self.assertEqual('kunit-resource-test', result.suites[0].name)
class KUnitJsonTest(unittest.TestCase):
diff --git a/tools/testing/kunit/test_data/test_config_printk_time.log b/tools/testing/kunit/test_data/test_config_printk_time.log
index c02ca77..6bdb57f 100644
--- a/tools/testing/kunit/test_data/test_config_printk_time.log
+++ b/tools/testing/kunit/test_data/test_config_printk_time.log
@@ -1,6 +1,7 @@
[ 0.060000] printk: console [mc-1] enabled
[ 0.060000] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
[ 0.060000] TAP version 14
+[ 0.060000] 1..3
[ 0.060000] # Subtest: kunit-resource-test
[ 0.060000] 1..5
[ 0.060000] ok 1 - kunit_resource_test_init_resources
@@ -28,4 +29,4 @@
[ 0.060000] Stack:
[ 0.060000] 602086f8 601bc260 705c0000 705c0000
[ 0.060000] 602086f8 6005fcec 705c0000 6002c6ab
-[ 0.060000] 6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file
+[ 0.060000] 6005fcec 601bc260 705c0000 3000000010
diff --git a/tools/testing/kunit/test_data/test_interrupted_tap_output.log b/tools/testing/kunit/test_data/test_interrupted_tap_output.log
index 5c73fb3..1fb6777 100644
--- a/tools/testing/kunit/test_data/test_interrupted_tap_output.log
+++ b/tools/testing/kunit/test_data/test_interrupted_tap_output.log
@@ -1,6 +1,7 @@
[ 0.060000] printk: console [mc-1] enabled
[ 0.060000] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
[ 0.060000] TAP version 14
+[ 0.060000] 1..3
[ 0.060000] # Subtest: kunit-resource-test
[ 0.060000] 1..5
[ 0.060000] ok 1 - kunit_resource_test_init_resources
@@ -34,4 +35,4 @@
[ 0.060000] Stack:
[ 0.060000] 602086f8 601bc260 705c0000 705c0000
[ 0.060000] 602086f8 6005fcec 705c0000 6002c6ab
-[ 0.060000] 6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file
+[ 0.060000] 6005fcec 601bc260 705c0000 3000000010
diff --git a/tools/testing/kunit/test_data/test_kernel_panic_interrupt.log b/tools/testing/kunit/test_data/test_kernel_panic_interrupt.log
index c045eee..a014ffe 100644
--- a/tools/testing/kunit/test_data/test_kernel_panic_interrupt.log
+++ b/tools/testing/kunit/test_data/test_kernel_panic_interrupt.log
@@ -1,6 +1,7 @@
[ 0.060000] printk: console [mc-1] enabled
[ 0.060000] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
[ 0.060000] TAP version 14
+[ 0.060000] 1..3
[ 0.060000] # Subtest: kunit-resource-test
[ 0.060000] 1..5
[ 0.060000] ok 1 - kunit_resource_test_init_resources
@@ -22,4 +23,4 @@
[ 0.060000] Stack:
[ 0.060000] 602086f8 601bc260 705c0000 705c0000
[ 0.060000] 602086f8 6005fcec 705c0000 6002c6ab
-[ 0.060000] 6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file
+[ 0.060000] 6005fcec 601bc260 705c0000 3000000010
diff --git a/tools/testing/kunit/test_data/test_multiple_prefixes.log b/tools/testing/kunit/test_data/test_multiple_prefixes.log
index bc48407..0ad7848 100644
--- a/tools/testing/kunit/test_data/test_multiple_prefixes.log
+++ b/tools/testing/kunit/test_data/test_multiple_prefixes.log
@@ -1,6 +1,7 @@
[ 0.060000][ T1] printk: console [mc-1] enabled
[ 0.060000][ T1] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
[ 0.060000][ T1] TAP version 14
+[ 0.060000][ T1] 1..3
[ 0.060000][ T1] # Subtest: kunit-resource-test
[ 0.060000][ T1] 1..5
[ 0.060000][ T1] ok 1 - kunit_resource_test_init_resources
@@ -28,4 +29,4 @@
[ 0.060000][ T1] Stack:
[ 0.060000][ T1] 602086f8 601bc260 705c0000 705c0000
[ 0.060000][ T1] 602086f8 6005fcec 705c0000 6002c6ab
-[ 0.060000][ T1] 6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file
+[ 0.060000][ T1] 6005fcec 601bc260 705c0000 3000000010
diff --git a/tools/testing/kunit/test_data/test_pound_no_prefix.log b/tools/testing/kunit/test_data/test_pound_no_prefix.log
index 2ceb360..dc4cf09 100644
--- a/tools/testing/kunit/test_data/test_pound_no_prefix.log
+++ b/tools/testing/kunit/test_data/test_pound_no_prefix.log
@@ -1,6 +1,7 @@
printk: console [mc-1] enabled
random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
TAP version 14
+ 1..3
# Subtest: kunit-resource-test
1..5
ok 1 - kunit_resource_test_init_resources
@@ -30,4 +31,4 @@
Stack:
602086f8 601bc260 705c0000 705c0000
602086f8 6005fcec 705c0000 6002c6ab
- 6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file
+ 6005fcec 601bc260 705c0000 3000000010
diff --git a/tools/testing/kunit/test_data/test_pound_sign.log b/tools/testing/kunit/test_data/test_pound_sign.log
index 28ffa5b..3f358e3a7 100644
--- a/tools/testing/kunit/test_data/test_pound_sign.log
+++ b/tools/testing/kunit/test_data/test_pound_sign.log
@@ -1,6 +1,7 @@
[ 0.060000] printk: console [mc-1] enabled
[ 0.060000] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
[ 0.060000] TAP version 14
+[ 0.060000] 1..3
[ 0.060000] # Subtest: kunit-resource-test
[ 0.060000] 1..5
[ 0.060000] ok 1 - kunit_resource_test_init_resources
diff --git a/tools/testing/scatterlist/linux/mm.h b/tools/testing/scatterlist/linux/mm.h
index 6ae907f..f9a1200 100644
--- a/tools/testing/scatterlist/linux/mm.h
+++ b/tools/testing/scatterlist/linux/mm.h
@@ -33,6 +33,7 @@
#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask))
#define ALIGN(x, a) __ALIGN_KERNEL((x), (a))
+#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a))
#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE)
diff --git a/tools/testing/scatterlist/main.c b/tools/testing/scatterlist/main.c
index b2c7e9f..f561aed 100644
--- a/tools/testing/scatterlist/main.c
+++ b/tools/testing/scatterlist/main.c
@@ -52,9 +52,9 @@
{
const unsigned int sgmax = SCATTERLIST_MAX_SEGMENT;
struct test *test, tests[] = {
- { -EINVAL, 1, pfn(0), PAGE_SIZE, PAGE_SIZE + 1, 1 },
{ -EINVAL, 1, pfn(0), PAGE_SIZE, 0, 1 },
- { -EINVAL, 1, pfn(0), PAGE_SIZE, sgmax + 1, 1 },
+ { 0, 1, pfn(0), PAGE_SIZE, PAGE_SIZE + 1, 1 },
+ { 0, 1, pfn(0), PAGE_SIZE, sgmax + 1, 1 },
{ 0, 1, pfn(0), PAGE_SIZE, sgmax, 1 },
{ 0, 1, pfn(0), 1, sgmax, 1 },
{ 0, 2, pfn(0, 1), 2 * PAGE_SIZE, sgmax, 1 },
diff --git a/tools/testing/selftests/arm64/mte/check_buffer_fill.c b/tools/testing/selftests/arm64/mte/check_buffer_fill.c
index 242635d..c9fa141 100644
--- a/tools/testing/selftests/arm64/mte/check_buffer_fill.c
+++ b/tools/testing/selftests/arm64/mte/check_buffer_fill.c
@@ -417,6 +417,9 @@
/* Register SIGSEGV handler */
mte_register_signal(SIGSEGV, mte_default_handler);
+ /* Set test plan */
+ ksft_set_plan(20);
+
/* Buffer by byte tests */
evaluate_test(check_buffer_by_byte(USE_MMAP, MTE_SYNC_ERR),
"Check buffer correctness by byte with sync err mode and mmap memory\n");
diff --git a/tools/testing/selftests/arm64/mte/check_child_memory.c b/tools/testing/selftests/arm64/mte/check_child_memory.c
index 97bebde..43bd94f 100644
--- a/tools/testing/selftests/arm64/mte/check_child_memory.c
+++ b/tools/testing/selftests/arm64/mte/check_child_memory.c
@@ -163,6 +163,9 @@
mte_register_signal(SIGSEGV, mte_default_handler);
mte_register_signal(SIGBUS, mte_default_handler);
+ /* Set test plan */
+ ksft_set_plan(12);
+
evaluate_test(check_child_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE),
"Check child anonymous memory with private mapping, precise mode and mmap memory\n");
evaluate_test(check_child_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_SHARED),
diff --git a/tools/testing/selftests/arm64/mte/check_ksm_options.c b/tools/testing/selftests/arm64/mte/check_ksm_options.c
index bc41ae6..3b23c4d 100644
--- a/tools/testing/selftests/arm64/mte/check_ksm_options.c
+++ b/tools/testing/selftests/arm64/mte/check_ksm_options.c
@@ -140,6 +140,10 @@
/* Register signal handlers */
mte_register_signal(SIGBUS, mte_default_handler);
mte_register_signal(SIGSEGV, mte_default_handler);
+
+ /* Set test plan */
+ ksft_set_plan(4);
+
/* Enable KSM */
mte_ksm_setup();
diff --git a/tools/testing/selftests/arm64/mte/check_mmap_options.c b/tools/testing/selftests/arm64/mte/check_mmap_options.c
index 33b13b8..a04b12c 100644
--- a/tools/testing/selftests/arm64/mte/check_mmap_options.c
+++ b/tools/testing/selftests/arm64/mte/check_mmap_options.c
@@ -205,7 +205,11 @@
mte_register_signal(SIGBUS, mte_default_handler);
mte_register_signal(SIGSEGV, mte_default_handler);
+ /* Set test plan */
+ ksft_set_plan(22);
+
mte_enable_pstate_tco();
+
evaluate_test(check_anonymous_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE, TAG_CHECK_OFF),
"Check anonymous memory with private mapping, sync error mode, mmap memory and tag check off\n");
evaluate_test(check_file_memory_mapping(USE_MPROTECT, MTE_SYNC_ERR, MAP_PRIVATE, TAG_CHECK_OFF),
diff --git a/tools/testing/selftests/arm64/mte/check_tags_inclusion.c b/tools/testing/selftests/arm64/mte/check_tags_inclusion.c
index 94d245a..deaef1f 100644
--- a/tools/testing/selftests/arm64/mte/check_tags_inclusion.c
+++ b/tools/testing/selftests/arm64/mte/check_tags_inclusion.c
@@ -170,6 +170,9 @@
/* Register SIGSEGV handler */
mte_register_signal(SIGSEGV, mte_default_handler);
+ /* Set test plan */
+ ksft_set_plan(4);
+
evaluate_test(check_single_included_tags(USE_MMAP, MTE_SYNC_ERR),
"Check an included tag value with sync mode\n");
evaluate_test(check_multiple_included_tags(USE_MMAP, MTE_SYNC_ERR),
diff --git a/tools/testing/selftests/arm64/mte/check_user_mem.c b/tools/testing/selftests/arm64/mte/check_user_mem.c
index 594e98e..4bfa80f 100644
--- a/tools/testing/selftests/arm64/mte/check_user_mem.c
+++ b/tools/testing/selftests/arm64/mte/check_user_mem.c
@@ -92,9 +92,13 @@
err = mte_default_setup();
if (err)
return err;
+
/* Register signal handlers */
mte_register_signal(SIGSEGV, mte_default_handler);
+ /* Set test plan */
+ ksft_set_plan(4);
+
evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE),
"Check memory access from kernel in sync mode, private mapping and mmap memory\n");
evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_SYNC_ERR, MAP_SHARED),
diff --git a/tools/testing/selftests/bpf/prog_tests/map_init.c b/tools/testing/selftests/bpf/prog_tests/map_init.c
new file mode 100644
index 0000000..14a3110
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/map_init.c
@@ -0,0 +1,214 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */
+
+#include <test_progs.h>
+#include "test_map_init.skel.h"
+
+#define TEST_VALUE 0x1234
+#define FILL_VALUE 0xdeadbeef
+
+static int nr_cpus;
+static int duration;
+
+typedef unsigned long long map_key_t;
+typedef unsigned long long map_value_t;
+typedef struct {
+ map_value_t v; /* padding */
+} __bpf_percpu_val_align pcpu_map_value_t;
+
+
+static int map_populate(int map_fd, int num)
+{
+ pcpu_map_value_t value[nr_cpus];
+ int i, err;
+ map_key_t key;
+
+ for (i = 0; i < nr_cpus; i++)
+ bpf_percpu(value, i) = FILL_VALUE;
+
+ for (key = 1; key <= num; key++) {
+ err = bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST);
+ if (!ASSERT_OK(err, "bpf_map_update_elem"))
+ return -1;
+ }
+
+ return 0;
+}
+
+static struct test_map_init *setup(enum bpf_map_type map_type, int map_sz,
+ int *map_fd, int populate)
+{
+ struct test_map_init *skel;
+ int err;
+
+ skel = test_map_init__open();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return NULL;
+
+ err = bpf_map__set_type(skel->maps.hashmap1, map_type);
+ if (!ASSERT_OK(err, "bpf_map__set_type"))
+ goto error;
+
+ err = bpf_map__set_max_entries(skel->maps.hashmap1, map_sz);
+ if (!ASSERT_OK(err, "bpf_map__set_max_entries"))
+ goto error;
+
+ err = test_map_init__load(skel);
+ if (!ASSERT_OK(err, "skel_load"))
+ goto error;
+
+ *map_fd = bpf_map__fd(skel->maps.hashmap1);
+ if (CHECK(*map_fd < 0, "bpf_map__fd", "failed\n"))
+ goto error;
+
+ err = map_populate(*map_fd, populate);
+ if (!ASSERT_OK(err, "map_populate"))
+ goto error_map;
+
+ return skel;
+
+error_map:
+ close(*map_fd);
+error:
+ test_map_init__destroy(skel);
+ return NULL;
+}
+
+/* executes bpf program that updates map with key, value */
+static int prog_run_insert_elem(struct test_map_init *skel, map_key_t key,
+ map_value_t value)
+{
+ struct test_map_init__bss *bss;
+
+ bss = skel->bss;
+
+ bss->inKey = key;
+ bss->inValue = value;
+ bss->inPid = getpid();
+
+ if (!ASSERT_OK(test_map_init__attach(skel), "skel_attach"))
+ return -1;
+
+ /* Let tracepoint trigger */
+ syscall(__NR_getpgid);
+
+ test_map_init__detach(skel);
+
+ return 0;
+}
+
+static int check_values_one_cpu(pcpu_map_value_t *value, map_value_t expected)
+{
+ int i, nzCnt = 0;
+ map_value_t val;
+
+ for (i = 0; i < nr_cpus; i++) {
+ val = bpf_percpu(value, i);
+ if (val) {
+ if (CHECK(val != expected, "map value",
+ "unexpected for cpu %d: 0x%llx\n", i, val))
+ return -1;
+ nzCnt++;
+ }
+ }
+
+ if (CHECK(nzCnt != 1, "map value", "set for %d CPUs instead of 1!\n",
+ nzCnt))
+ return -1;
+
+ return 0;
+}
+
+/* Add key=1 elem with values set for all CPUs
+ * Delete elem key=1
+ * Run bpf prog that inserts new key=1 elem with value=0x1234
+ * (bpf prog can only set value for current CPU)
+ * Lookup Key=1 and check value is as expected for all CPUs:
+ * value set by bpf prog for one CPU, 0 for all others
+ */
+static void test_pcpu_map_init(void)
+{
+ pcpu_map_value_t value[nr_cpus];
+ struct test_map_init *skel;
+ int map_fd, err;
+ map_key_t key;
+
+ /* max 1 elem in map so insertion is forced to reuse freed entry */
+ skel = setup(BPF_MAP_TYPE_PERCPU_HASH, 1, &map_fd, 1);
+ if (!ASSERT_OK_PTR(skel, "prog_setup"))
+ return;
+
+ /* delete element so the entry can be re-used*/
+ key = 1;
+ err = bpf_map_delete_elem(map_fd, &key);
+ if (!ASSERT_OK(err, "bpf_map_delete_elem"))
+ goto cleanup;
+
+ /* run bpf prog that inserts new elem, re-using the slot just freed */
+ err = prog_run_insert_elem(skel, key, TEST_VALUE);
+ if (!ASSERT_OK(err, "prog_run_insert_elem"))
+ goto cleanup;
+
+ /* check that key=1 was re-created by bpf prog */
+ err = bpf_map_lookup_elem(map_fd, &key, value);
+ if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
+ goto cleanup;
+
+ /* and has expected values */
+ check_values_one_cpu(value, TEST_VALUE);
+
+cleanup:
+ test_map_init__destroy(skel);
+}
+
+/* Add key=1 and key=2 elems with values set for all CPUs
+ * Run bpf prog that inserts new key=3 elem
+ * (only for current cpu; other cpus should have initial value = 0)
+ * Lookup Key=1 and check value is as expected for all CPUs
+ */
+static void test_pcpu_lru_map_init(void)
+{
+ pcpu_map_value_t value[nr_cpus];
+ struct test_map_init *skel;
+ int map_fd, err;
+ map_key_t key;
+
+ /* Set up LRU map with 2 elements, values filled for all CPUs.
+ * With these 2 elements, the LRU map is full
+ */
+ skel = setup(BPF_MAP_TYPE_LRU_PERCPU_HASH, 2, &map_fd, 2);
+ if (!ASSERT_OK_PTR(skel, "prog_setup"))
+ return;
+
+ /* run bpf prog that inserts new key=3 element, re-using LRU slot */
+ key = 3;
+ err = prog_run_insert_elem(skel, key, TEST_VALUE);
+ if (!ASSERT_OK(err, "prog_run_insert_elem"))
+ goto cleanup;
+
+ /* check that key=3 replaced one of earlier elements */
+ err = bpf_map_lookup_elem(map_fd, &key, value);
+ if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
+ goto cleanup;
+
+ /* and has expected values */
+ check_values_one_cpu(value, TEST_VALUE);
+
+cleanup:
+ test_map_init__destroy(skel);
+}
+
+void test_map_init(void)
+{
+ nr_cpus = bpf_num_possible_cpus();
+ if (nr_cpus <= 1) {
+ printf("%s:SKIP: >1 cpu needed for this test\n", __func__);
+ test__skip();
+ return;
+ }
+
+ if (test__start_subtest("pcpu_map_init"))
+ test_pcpu_map_init();
+ if (test__start_subtest("pcpu_lru_map_init"))
+ test_pcpu_lru_map_init();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c b/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c
new file mode 100644
index 0000000..e419298
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "test_probe_read_user_str.skel.h"
+
+static const char str1[] = "mestring";
+static const char str2[] = "mestringalittlebigger";
+static const char str3[] = "mestringblubblubblubblubblub";
+
+static int test_one_str(struct test_probe_read_user_str *skel, const char *str,
+ size_t len)
+{
+ int err, duration = 0;
+ char buf[256];
+
+ /* Ensure bytes after string are ones */
+ memset(buf, 1, sizeof(buf));
+ memcpy(buf, str, len);
+
+ /* Give prog our userspace pointer */
+ skel->bss->user_ptr = buf;
+
+ /* Trigger tracepoint */
+ usleep(1);
+
+ /* Did helper fail? */
+ if (CHECK(skel->bss->ret < 0, "prog_ret", "prog returned: %ld\n",
+ skel->bss->ret))
+ return 1;
+
+ /* Check that string was copied correctly */
+ err = memcmp(skel->bss->buf, str, len);
+ if (CHECK(err, "memcmp", "prog copied wrong string"))
+ return 1;
+
+ /* Now check that no extra trailing bytes were copied */
+ memset(buf, 0, sizeof(buf));
+ err = memcmp(skel->bss->buf + len, buf, sizeof(buf) - len);
+ if (CHECK(err, "memcmp", "trailing bytes were not stripped"))
+ return 1;
+
+ return 0;
+}
+
+void test_probe_read_user_str(void)
+{
+ struct test_probe_read_user_str *skel;
+ int err, duration = 0;
+
+ skel = test_probe_read_user_str__open_and_load();
+ if (CHECK(!skel, "test_probe_read_user_str__open_and_load",
+ "skeleton open and load failed\n"))
+ return;
+
+ /* Give pid to bpf prog so it doesn't read from anyone else */
+ skel->bss->pid = getpid();
+
+ err = test_probe_read_user_str__attach(skel);
+ if (CHECK(err, "test_probe_read_user_str__attach",
+ "skeleton attach failed: %d\n", err))
+ goto out;
+
+ if (test_one_str(skel, str1, sizeof(str1)))
+ goto out;
+ if (test_one_str(skel, str2, sizeof(str2)))
+ goto out;
+ if (test_one_str(skel, str3, sizeof(str3)))
+ goto out;
+
+out:
+ test_probe_read_user_str__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c
index 29188d6..51fac97 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c
@@ -138,7 +138,8 @@
*/
buf = 0x40;
- if (setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1) < 0) {
+ err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1);
+ if (err < 0) {
log_err("Failed to call setsockopt(IP_TOS)");
goto detach;
}
diff --git a/tools/testing/selftests/bpf/prog_tests/subprogs.c b/tools/testing/selftests/bpf/prog_tests/subprogs.c
index a00abf5..3f3d2ac 100644
--- a/tools/testing/selftests/bpf/prog_tests/subprogs.c
+++ b/tools/testing/selftests/bpf/prog_tests/subprogs.c
@@ -3,12 +3,14 @@
#include <test_progs.h>
#include <time.h>
#include "test_subprogs.skel.h"
+#include "test_subprogs_unused.skel.h"
static int duration;
void test_subprogs(void)
{
struct test_subprogs *skel;
+ struct test_subprogs_unused *skel2;
int err;
skel = test_subprogs__open_and_load();
@@ -26,6 +28,10 @@
CHECK(skel->bss->res3 != 19, "res3", "got %d, exp %d\n", skel->bss->res3, 19);
CHECK(skel->bss->res4 != 36, "res4", "got %d, exp %d\n", skel->bss->res4, 36);
+ skel2 = test_subprogs_unused__open_and_load();
+ ASSERT_OK_PTR(skel2, "unused_progs_skel");
+ test_subprogs_unused__destroy(skel2);
+
cleanup:
test_subprogs__destroy(skel);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
index 193002b..32e4348 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
@@ -60,6 +60,7 @@
{ "test_global_func5.o" , "expected pointer to ctx, but got PTR" },
{ "test_global_func6.o" , "modified ctx ptr R2" },
{ "test_global_func7.o" , "foo() doesn't return scalar" },
+ { "test_global_func8.o" },
};
libbpf_print_fn_t old_print_fn = NULL;
int err, i, duration = 0;
diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h
index 0057831..30982a7 100644
--- a/tools/testing/selftests/bpf/progs/profiler.inc.h
+++ b/tools/testing/selftests/bpf/progs/profiler.inc.h
@@ -243,7 +243,10 @@
}
}
-int pids_cgrp_id = 1;
+extern bool CONFIG_CGROUP_PIDS __kconfig __weak;
+enum cgroup_subsys_id___local {
+ pids_cgrp_id___local = 123, /* value doesn't matter */
+};
static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
struct task_struct* task,
@@ -253,7 +256,9 @@
BPF_CORE_READ(task, nsproxy, cgroup_ns, root_cset, dfl_cgrp, kn);
struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn);
- if (ENABLE_CGROUP_V1_RESOLVER) {
+ if (ENABLE_CGROUP_V1_RESOLVER && CONFIG_CGROUP_PIDS) {
+ int cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id___local,
+ pids_cgrp_id___local);
#ifdef UNROLL
#pragma unroll
#endif
@@ -262,7 +267,7 @@
BPF_CORE_READ(task, cgroups, subsys[i]);
if (subsys != NULL) {
int subsys_id = BPF_CORE_READ(subsys, ss, id);
- if (subsys_id == pids_cgrp_id) {
+ if (subsys_id == cgrp_id) {
proc_kernfs = BPF_CORE_READ(subsys, cgroup, kn);
root_kernfs = BPF_CORE_READ(subsys, ss, root, kf_root, kn);
break;
diff --git a/tools/testing/selftests/bpf/progs/test_global_func8.c b/tools/testing/selftests/bpf/progs/test_global_func8.c
new file mode 100644
index 0000000..d55a654
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func8.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__noinline int foo(struct __sk_buff *skb)
+{
+ return bpf_get_prandom_u32();
+}
+
+SEC("cgroup_skb/ingress")
+int test_cls(struct __sk_buff *skb)
+{
+ if (!foo(skb))
+ return 0;
+
+ return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_map_init.c b/tools/testing/selftests/bpf/progs/test_map_init.c
new file mode 100644
index 0000000..c89d28ea
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_map_init.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+__u64 inKey = 0;
+__u64 inValue = 0;
+__u32 inPid = 0;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+ __uint(max_entries, 2);
+ __type(key, __u64);
+ __type(value, __u64);
+} hashmap1 SEC(".maps");
+
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int sysenter_getpgid(const void *ctx)
+{
+ /* Just do it for once, when called from our own test prog. This
+ * ensures the map value is only updated for a single CPU.
+ */
+ int cur_pid = bpf_get_current_pid_tgid() >> 32;
+
+ if (cur_pid == inPid)
+ bpf_map_update_elem(&hashmap1, &inKey, &inValue, BPF_NOEXIST);
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c b/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c
new file mode 100644
index 0000000..3ae398b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#include <sys/types.h>
+
+pid_t pid = 0;
+long ret = 0;
+void *user_ptr = 0;
+char buf[256] = {};
+
+SEC("tracepoint/syscalls/sys_enter_nanosleep")
+int on_write(void *ctx)
+{
+ if (pid != (bpf_get_current_pid_tgid() >> 32))
+ return 0;
+
+ ret = bpf_probe_read_user_str(buf, sizeof(buf), user_ptr);
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_subprogs_unused.c b/tools/testing/selftests/bpf/progs/test_subprogs_unused.c
new file mode 100644
index 0000000..bc49e05
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_subprogs_unused.c
@@ -0,0 +1,21 @@
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+
+const char LICENSE[] SEC("license") = "GPL";
+
+__attribute__((unused)) __noinline int unused1(int x)
+{
+ return x + 1;
+}
+
+static __attribute__((unused)) __noinline int unused2(int x)
+{
+ return x + 2;
+}
+
+SEC("raw_tp/sys_enter")
+int main_prog(void *ctx)
+{
+ return 0;
+}
diff --git a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c
index 55bd387..52d3f03 100644
--- a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c
+++ b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c
@@ -145,7 +145,7 @@
test_clone3_supported();
EXPECT_EQ(getuid(), 0)
- XFAIL(return, "Skipping all tests as non-root\n");
+ SKIP(return, "Skipping all tests as non-root");
memset(&set_tid, 0, sizeof(set_tid));
diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c
index c99b98b..575b391 100644
--- a/tools/testing/selftests/core/close_range_test.c
+++ b/tools/testing/selftests/core/close_range_test.c
@@ -44,7 +44,7 @@
fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
ASSERT_GE(fd, 0) {
if (errno == ENOENT)
- XFAIL(return, "Skipping test since /dev/null does not exist");
+ SKIP(return, "Skipping test since /dev/null does not exist");
}
open_fds[i] = fd;
@@ -52,7 +52,7 @@
EXPECT_EQ(-1, sys_close_range(open_fds[0], open_fds[100], -1)) {
if (errno == ENOSYS)
- XFAIL(return, "close_range() syscall not supported");
+ SKIP(return, "close_range() syscall not supported");
}
EXPECT_EQ(0, sys_close_range(open_fds[0], open_fds[50], 0));
@@ -108,7 +108,7 @@
fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
ASSERT_GE(fd, 0) {
if (errno == ENOENT)
- XFAIL(return, "Skipping test since /dev/null does not exist");
+ SKIP(return, "Skipping test since /dev/null does not exist");
}
open_fds[i] = fd;
@@ -197,7 +197,7 @@
fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
ASSERT_GE(fd, 0) {
if (errno == ENOENT)
- XFAIL(return, "Skipping test since /dev/null does not exist");
+ SKIP(return, "Skipping test since /dev/null does not exist");
}
open_fds[i] = fd;
diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c
index 1d27f52..477cbb0 100644
--- a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c
+++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c
@@ -74,7 +74,7 @@
ret = mount(NULL, binderfs_mntpt, "binder", 0, 0);
EXPECT_EQ(ret, 0) {
if (errno == ENODEV)
- XFAIL(goto out, "binderfs missing");
+ SKIP(goto out, "binderfs missing");
TH_LOG("%s - Failed to mount binderfs", strerror(errno));
goto rmdir;
}
@@ -475,10 +475,10 @@
TEST(binderfs_test_privileged)
{
if (geteuid() != 0)
- XFAIL(return, "Tests are not run as root. Skipping privileged tests");
+ SKIP(return, "Tests are not run as root. Skipping privileged tests");
if (__do_binderfs_test(_metadata))
- XFAIL(return, "The Android binderfs filesystem is not available");
+ SKIP(return, "The Android binderfs filesystem is not available");
}
TEST(binderfs_test_unprivileged)
@@ -511,7 +511,7 @@
ret = wait_for_pid(pid);
if (ret) {
if (ret == 2)
- XFAIL(return, "The Android binderfs filesystem is not available");
+ SKIP(return, "The Android binderfs filesystem is not available");
ASSERT_EQ(ret, 0) {
TH_LOG("wait_for_pid() failed");
}
diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c
index d979ff1..8f82f99 100644
--- a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c
+++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c
@@ -3282,4 +3282,99 @@
close(ctx.epfd);
}
+struct epoll61_ctx {
+ int epfd;
+ int evfd;
+};
+
+static void *epoll61_write_eventfd(void *ctx_)
+{
+ struct epoll61_ctx *ctx = ctx_;
+ int64_t l = 1;
+
+ usleep(10950);
+ write(ctx->evfd, &l, sizeof(l));
+ return NULL;
+}
+
+static void *epoll61_epoll_with_timeout(void *ctx_)
+{
+ struct epoll61_ctx *ctx = ctx_;
+ struct epoll_event events[1];
+ int n;
+
+ n = epoll_wait(ctx->epfd, events, 1, 11);
+ /*
+ * If epoll returned the eventfd, write on the eventfd to wake up the
+ * blocking poller.
+ */
+ if (n == 1) {
+ int64_t l = 1;
+
+ write(ctx->evfd, &l, sizeof(l));
+ }
+ return NULL;
+}
+
+static void *epoll61_blocking_epoll(void *ctx_)
+{
+ struct epoll61_ctx *ctx = ctx_;
+ struct epoll_event events[1];
+
+ epoll_wait(ctx->epfd, events, 1, -1);
+ return NULL;
+}
+
+TEST(epoll61)
+{
+ struct epoll61_ctx ctx;
+ struct epoll_event ev;
+ int i, r;
+
+ ctx.epfd = epoll_create1(0);
+ ASSERT_GE(ctx.epfd, 0);
+ ctx.evfd = eventfd(0, EFD_NONBLOCK);
+ ASSERT_GE(ctx.evfd, 0);
+
+ ev.events = EPOLLIN | EPOLLET | EPOLLERR | EPOLLHUP;
+ ev.data.ptr = NULL;
+ r = epoll_ctl(ctx.epfd, EPOLL_CTL_ADD, ctx.evfd, &ev);
+ ASSERT_EQ(r, 0);
+
+ /*
+ * We are testing a race. Repeat the test case 1000 times to make it
+ * more likely to fail in case of a bug.
+ */
+ for (i = 0; i < 1000; i++) {
+ pthread_t threads[3];
+ int n;
+
+ /*
+ * Start 3 threads:
+ * Thread 1 sleeps for 10.9ms and writes to the evenfd.
+ * Thread 2 calls epoll with a timeout of 11ms.
+ * Thread 3 calls epoll with a timeout of -1.
+ *
+ * The eventfd write by Thread 1 should either wakeup Thread 2
+ * or Thread 3. If it wakes up Thread 2, Thread 2 writes on the
+ * eventfd to wake up Thread 3.
+ *
+ * If no events are missed, all three threads should eventually
+ * be joinable.
+ */
+ ASSERT_EQ(pthread_create(&threads[0], NULL,
+ epoll61_write_eventfd, &ctx), 0);
+ ASSERT_EQ(pthread_create(&threads[1], NULL,
+ epoll61_epoll_with_timeout, &ctx), 0);
+ ASSERT_EQ(pthread_create(&threads[2], NULL,
+ epoll61_blocking_epoll, &ctx), 0);
+
+ for (n = 0; n < ARRAY_SIZE(threads); ++n)
+ ASSERT_EQ(pthread_join(threads[n], NULL), 0);
+ }
+
+ close(ctx.epfd);
+ close(ctx.evfd);
+}
+
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc
index 3bcd4c3..b4da41d 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc
@@ -6,7 +6,7 @@
echo 0 > events/enable
echo > dynamic_events
-PLACE=kernel_clone
+PLACE=$FUNCTION_FORK
echo "p:myevent1 $PLACE" >> dynamic_events
echo "r:myevent2 $PLACE" >> dynamic_events
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/clear_select_events.tc b/tools/testing/selftests/ftrace/test.d/dynevent/clear_select_events.tc
index 4389619..3a0e288 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/clear_select_events.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/clear_select_events.tc
@@ -6,7 +6,7 @@
echo 0 > events/enable
echo > dynamic_events
-PLACE=kernel_clone
+PLACE=$FUNCTION_FORK
setup_events() {
echo "p:myevent1 $PLACE" >> dynamic_events
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/generic_clear_event.tc b/tools/testing/selftests/ftrace/test.d/dynevent/generic_clear_event.tc
index a8603bd..d3e138e 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/generic_clear_event.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/generic_clear_event.tc
@@ -6,7 +6,7 @@
echo 0 > events/enable
echo > dynamic_events
-PLACE=kernel_clone
+PLACE=$FUNCTION_FORK
setup_events() {
echo "p:myevent1 $PLACE" >> dynamic_events
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc
index acb17ce..8054196 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc
@@ -39,7 +39,7 @@
disable_tracing
echo do_execve* > set_ftrace_filter
- echo *do_fork >> set_ftrace_filter
+ echo $FUNCTION_FORK >> set_ftrace_filter
echo $PID > set_ftrace_notrace_pid
echo function > current_tracer
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
index 9f0a968..2f72112 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
@@ -39,7 +39,7 @@
disable_tracing
echo do_execve* > set_ftrace_filter
- echo *do_fork >> set_ftrace_filter
+ echo $FUNCTION_FORK >> set_ftrace_filter
echo $PID > set_ftrace_pid
echo function > current_tracer
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
index 98305d7..191d116 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
@@ -4,9 +4,9 @@
# requires: set_ftrace_filter
# flags: instance
-echo kernel_clone:stacktrace >> set_ftrace_filter
+echo $FUNCTION_FORK:stacktrace >> set_ftrace_filter
-grep -q "kernel_clone:stacktrace:unlimited" set_ftrace_filter
+grep -q "$FUNCTION_FORK:stacktrace:unlimited" set_ftrace_filter
(echo "forked"; sleep 1)
diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions
index c5dec55..a6fac92 100644
--- a/tools/testing/selftests/ftrace/test.d/functions
+++ b/tools/testing/selftests/ftrace/test.d/functions
@@ -133,6 +133,13 @@
ping $LOCALHOST -c 1 || sleep .001 || usleep 1 || sleep 1
}
+# The fork function in the kernel was renamed from "_do_fork" to
+# "kernel_fork". As older tests should still work with older kernels
+# as well as newer kernels, check which version of fork is used on this
+# kernel so that the tests can use the fork function for the running kernel.
+FUNCTION_FORK=`(if grep '\bkernel_clone\b' /proc/kallsyms > /dev/null; then
+ echo kernel_clone; else echo '_do_fork'; fi)`
+
# Since probe event command may include backslash, explicitly use printf "%s"
# to NOT interpret it.
ftrace_errlog_check() { # err-prefix command-with-error-pos-by-^ command-file
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
index 9737cd0..2428a3ed 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
@@ -3,7 +3,7 @@
# description: Kprobe dynamic event - adding and removing
# requires: kprobe_events
-echo p:myevent kernel_clone > kprobe_events
+echo p:myevent $FUNCTION_FORK > kprobe_events
grep myevent kprobe_events
test -d events/kprobes/myevent
echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
index f9a40af..010a8b1 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
@@ -3,7 +3,7 @@
# description: Kprobe dynamic event - busy event check
# requires: kprobe_events
-echo p:myevent kernel_clone > kprobe_events
+echo p:myevent $FUNCTION_FORK > kprobe_events
test -d events/kprobes/myevent
echo 1 > events/kprobes/myevent/enable
echo > kprobe_events && exit_fail # this must fail
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
index eb543d3..a96a1dc 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
@@ -3,13 +3,13 @@
# description: Kprobe dynamic event with arguments
# requires: kprobe_events
-echo 'p:testprobe kernel_clone $stack $stack0 +0($stack)' > kprobe_events
+echo "p:testprobe $FUNCTION_FORK \$stack \$stack0 +0(\$stack)" > kprobe_events
grep testprobe kprobe_events | grep -q 'arg1=\$stack arg2=\$stack0 arg3=+0(\$stack)'
test -d events/kprobes/testprobe
echo 1 > events/kprobes/testprobe/enable
( echo "forked")
-grep testprobe trace | grep 'kernel_clone' | \
+grep testprobe trace | grep "$FUNCTION_FORK" | \
grep -q 'arg1=0x[[:xdigit:]]* arg2=0x[[:xdigit:]]* arg3=0x[[:xdigit:]]*$'
echo 0 > events/kprobes/testprobe/enable
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc
index 4e5b63b..a053ee2 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc
@@ -5,7 +5,7 @@
grep -A1 "fetcharg:" README | grep -q "\$comm" || exit_unsupported # this is too old
-echo 'p:testprobe kernel_clone comm=$comm ' > kprobe_events
+echo "p:testprobe $FUNCTION_FORK comm=\$comm " > kprobe_events
grep testprobe kprobe_events | grep -q 'comm=$comm'
test -d events/kprobes/testprobe
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
index a1d7058..84285a6 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
@@ -30,13 +30,13 @@
: "Test get argument (1)"
echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):string" > kprobe_events
echo 1 > events/kprobes/testprobe/enable
-echo "p:test kernel_clone" >> kprobe_events
+echo "p:test $FUNCTION_FORK" >> kprobe_events
grep -qe "testprobe.* arg1=\"test\"" trace
echo 0 > events/kprobes/testprobe/enable
: "Test get argument (2)"
echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):string arg2=+0(${ARG1}):string" > kprobe_events
echo 1 > events/kprobes/testprobe/enable
-echo "p:test kernel_clone" >> kprobe_events
+echo "p:test $FUNCTION_FORK" >> kprobe_events
grep -qe "testprobe.* arg1=\"test\" arg2=\"test\"" trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc
index bd25dd0..717130e 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc
@@ -14,12 +14,12 @@
fi
: "Test get basic types symbol argument"
-echo "p:testprobe_u kernel_clone arg1=@linux_proc_banner:u64 arg2=@linux_proc_banner:u32 arg3=@linux_proc_banner:u16 arg4=@linux_proc_banner:u8" > kprobe_events
-echo "p:testprobe_s kernel_clone arg1=@linux_proc_banner:s64 arg2=@linux_proc_banner:s32 arg3=@linux_proc_banner:s16 arg4=@linux_proc_banner:s8" >> kprobe_events
+echo "p:testprobe_u $FUNCTION_FORK arg1=@linux_proc_banner:u64 arg2=@linux_proc_banner:u32 arg3=@linux_proc_banner:u16 arg4=@linux_proc_banner:u8" > kprobe_events
+echo "p:testprobe_s $FUNCTION_FORK arg1=@linux_proc_banner:s64 arg2=@linux_proc_banner:s32 arg3=@linux_proc_banner:s16 arg4=@linux_proc_banner:s8" >> kprobe_events
if grep -q "x8/16/32/64" README; then
- echo "p:testprobe_x kernel_clone arg1=@linux_proc_banner:x64 arg2=@linux_proc_banner:x32 arg3=@linux_proc_banner:x16 arg4=@linux_proc_banner:x8" >> kprobe_events
+ echo "p:testprobe_x $FUNCTION_FORK arg1=@linux_proc_banner:x64 arg2=@linux_proc_banner:x32 arg3=@linux_proc_banner:x16 arg4=@linux_proc_banner:x8" >> kprobe_events
fi
-echo "p:testprobe_bf kernel_clone arg1=@linux_proc_banner:b8@4/32" >> kprobe_events
+echo "p:testprobe_bf $FUNCTION_FORK arg1=@linux_proc_banner:b8@4/32" >> kprobe_events
echo 1 > events/kprobes/enable
(echo "forked")
echo 0 > events/kprobes/enable
@@ -27,7 +27,7 @@
grep "testprobe_bf:.* arg1=.*" trace
: "Test get string symbol argument"
-echo "p:testprobe_str kernel_clone arg1=@linux_proc_banner:string" > kprobe_events
+echo "p:testprobe_str $FUNCTION_FORK arg1=@linux_proc_banner:string" > kprobe_events
echo 1 > events/kprobes/enable
(echo "forked")
echo 0 > events/kprobes/enable
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
index 91fcce1c..25b7708 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
@@ -4,7 +4,7 @@
# requires: kprobe_events "x8/16/32/64":README
gen_event() { # Bitsize
- echo "p:testprobe kernel_clone \$stack0:s$1 \$stack0:u$1 \$stack0:x$1 \$stack0:b4@4/$1"
+ echo "p:testprobe $FUNCTION_FORK \$stack0:s$1 \$stack0:u$1 \$stack0:x$1 \$stack0:b4@4/$1"
}
check_types() { # s-type u-type x-type bf-type width
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc
index a30a9c0..d25d01a 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc
@@ -9,12 +9,16 @@
:;: "user-memory access syntax and ustring working on user memory";:
echo 'p:myevent do_sys_open path=+0($arg2):ustring path2=+u0($arg2):string' \
> kprobe_events
+echo 'p:myevent2 do_sys_openat2 path=+0($arg2):ustring path2=+u0($arg2):string' \
+ >> kprobe_events
grep myevent kprobe_events | \
grep -q 'path=+0($arg2):ustring path2=+u0($arg2):string'
echo 1 > events/kprobes/myevent/enable
+echo 1 > events/kprobes/myevent2/enable
echo > /dev/null
echo 0 > events/kprobes/myevent/enable
+echo 0 > events/kprobes/myevent2/enable
grep myevent trace | grep -q 'path="/dev/null" path2="/dev/null"'
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
index 0d17909..5556292 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
@@ -5,29 +5,29 @@
# prepare
echo nop > current_tracer
-echo kernel_clone > set_ftrace_filter
-echo 'p:testprobe kernel_clone' > kprobe_events
+echo $FUNCTION_FORK > set_ftrace_filter
+echo "p:testprobe $FUNCTION_FORK" > kprobe_events
# kprobe on / ftrace off
echo 1 > events/kprobes/testprobe/enable
echo > trace
( echo "forked")
grep testprobe trace
-! grep 'kernel_clone <-' trace
+! grep "$FUNCTION_FORK <-" trace
# kprobe on / ftrace on
echo function > current_tracer
echo > trace
( echo "forked")
grep testprobe trace
-grep 'kernel_clone <-' trace
+grep "$FUNCTION_FORK <-" trace
# kprobe off / ftrace on
echo 0 > events/kprobes/testprobe/enable
echo > trace
( echo "forked")
! grep testprobe trace
-grep 'kernel_clone <-' trace
+grep "$FUNCTION_FORK <-" trace
# kprobe on / ftrace on
echo 1 > events/kprobes/testprobe/enable
@@ -35,11 +35,11 @@
echo > trace
( echo "forked")
grep testprobe trace
-grep 'kernel_clone <-' trace
+grep "$FUNCTION_FORK <-" trace
# kprobe on / ftrace off
echo nop > current_tracer
echo > trace
( echo "forked")
grep testprobe trace
-! grep 'kernel_clone <-' trace
+! grep "$FUNCTION_FORK <-" trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_multiprobe.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_multiprobe.tc
index 45d90b6..f0d5b77 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_multiprobe.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_multiprobe.tc
@@ -4,7 +4,7 @@
# requires: kprobe_events "Create/append/":README
# Choose 2 symbols for target
-SYM1=kernel_clone
+SYM1=$FUNCTION_FORK
SYM2=do_exit
EVENT_NAME=kprobes/testevent
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
index 1b5550e..fa928b4 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
@@ -86,15 +86,15 @@
# multiprobe errors
if grep -q "Create/append/" README && grep -q "imm-value" README; then
-echo 'p:kprobes/testevent kernel_clone' > kprobe_events
+echo "p:kprobes/testevent $FUNCTION_FORK" > kprobe_events
check_error '^r:kprobes/testevent do_exit' # DIFF_PROBE_TYPE
# Explicitly use printf "%s" to not interpret \1
-printf "%s" 'p:kprobes/testevent kernel_clone abcd=\1' > kprobe_events
-check_error 'p:kprobes/testevent kernel_clone ^bcd=\1' # DIFF_ARG_TYPE
-check_error 'p:kprobes/testevent kernel_clone ^abcd=\1:u8' # DIFF_ARG_TYPE
-check_error 'p:kprobes/testevent kernel_clone ^abcd=\"foo"' # DIFF_ARG_TYPE
-check_error '^p:kprobes/testevent kernel_clone abcd=\1' # SAME_PROBE
+printf "%s" "p:kprobes/testevent $FUNCTION_FORK abcd=\\1" > kprobe_events
+check_error "p:kprobes/testevent $FUNCTION_FORK ^bcd=\\1" # DIFF_ARG_TYPE
+check_error "p:kprobes/testevent $FUNCTION_FORK ^abcd=\\1:u8" # DIFF_ARG_TYPE
+check_error "p:kprobes/testevent $FUNCTION_FORK ^abcd=\\\"foo\"" # DIFF_ARG_TYPE
+check_error "^p:kprobes/testevent $FUNCTION_FORK abcd=\\1" # SAME_PROBE
fi
# %return suffix errors
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
index 7ae492c..197cc2a 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
@@ -4,14 +4,14 @@
# requires: kprobe_events
# Add new kretprobe event
-echo 'r:testprobe2 kernel_clone $retval' > kprobe_events
+echo "r:testprobe2 $FUNCTION_FORK \$retval" > kprobe_events
grep testprobe2 kprobe_events | grep -q 'arg1=\$retval'
test -d events/kprobes/testprobe2
echo 1 > events/kprobes/testprobe2/enable
( echo "forked")
-cat trace | grep testprobe2 | grep -q '<- kernel_clone'
+cat trace | grep testprobe2 | grep -q "<- $FUNCTION_FORK"
echo 0 > events/kprobes/testprobe2/enable
echo '-:testprobe2' >> kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc b/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc
index c4093fc..98166fa 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc
@@ -4,7 +4,7 @@
# requires: kprobe_events
! grep -q 'myevent' kprobe_profile
-echo p:myevent kernel_clone > kprobe_events
+echo "p:myevent $FUNCTION_FORK" > kprobe_events
grep -q 'myevent[[:space:]]*0[[:space:]]*0$' kprobe_profile
echo 1 > events/kprobes/myevent/enable
( echo "forked" )
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index f19804d..edce854 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -126,7 +126,7 @@
snprintf(_metadata->results->reason, \
sizeof(_metadata->results->reason), fmt, ##__VA_ARGS__); \
if (TH_LOG_ENABLED) { \
- fprintf(TH_LOG_STREAM, "# SKIP %s\n", \
+ fprintf(TH_LOG_STREAM, "# SKIP %s\n", \
_metadata->results->reason); \
} \
_metadata->passed = 1; \
@@ -432,7 +432,7 @@
*/
/**
- * ASSERT_EQ(expected, seen)
+ * ASSERT_EQ()
*
* @expected: expected value
* @seen: measured value
@@ -443,7 +443,7 @@
__EXPECT(expected, #expected, seen, #seen, ==, 1)
/**
- * ASSERT_NE(expected, seen)
+ * ASSERT_NE()
*
* @expected: expected value
* @seen: measured value
@@ -454,7 +454,7 @@
__EXPECT(expected, #expected, seen, #seen, !=, 1)
/**
- * ASSERT_LT(expected, seen)
+ * ASSERT_LT()
*
* @expected: expected value
* @seen: measured value
@@ -465,7 +465,7 @@
__EXPECT(expected, #expected, seen, #seen, <, 1)
/**
- * ASSERT_LE(expected, seen)
+ * ASSERT_LE()
*
* @expected: expected value
* @seen: measured value
@@ -476,7 +476,7 @@
__EXPECT(expected, #expected, seen, #seen, <=, 1)
/**
- * ASSERT_GT(expected, seen)
+ * ASSERT_GT()
*
* @expected: expected value
* @seen: measured value
@@ -487,7 +487,7 @@
__EXPECT(expected, #expected, seen, #seen, >, 1)
/**
- * ASSERT_GE(expected, seen)
+ * ASSERT_GE()
*
* @expected: expected value
* @seen: measured value
@@ -498,7 +498,7 @@
__EXPECT(expected, #expected, seen, #seen, >=, 1)
/**
- * ASSERT_NULL(seen)
+ * ASSERT_NULL()
*
* @seen: measured value
*
@@ -508,7 +508,7 @@
__EXPECT(NULL, "NULL", seen, #seen, ==, 1)
/**
- * ASSERT_TRUE(seen)
+ * ASSERT_TRUE()
*
* @seen: measured value
*
@@ -518,7 +518,7 @@
__EXPECT(0, "0", seen, #seen, !=, 1)
/**
- * ASSERT_FALSE(seen)
+ * ASSERT_FALSE()
*
* @seen: measured value
*
@@ -528,7 +528,7 @@
__EXPECT(0, "0", seen, #seen, ==, 1)
/**
- * ASSERT_STREQ(expected, seen)
+ * ASSERT_STREQ()
*
* @expected: expected value
* @seen: measured value
@@ -539,7 +539,7 @@
__EXPECT_STR(expected, seen, ==, 1)
/**
- * ASSERT_STRNE(expected, seen)
+ * ASSERT_STRNE()
*
* @expected: expected value
* @seen: measured value
@@ -550,7 +550,7 @@
__EXPECT_STR(expected, seen, !=, 1)
/**
- * EXPECT_EQ(expected, seen)
+ * EXPECT_EQ()
*
* @expected: expected value
* @seen: measured value
@@ -561,7 +561,7 @@
__EXPECT(expected, #expected, seen, #seen, ==, 0)
/**
- * EXPECT_NE(expected, seen)
+ * EXPECT_NE()
*
* @expected: expected value
* @seen: measured value
@@ -572,7 +572,7 @@
__EXPECT(expected, #expected, seen, #seen, !=, 0)
/**
- * EXPECT_LT(expected, seen)
+ * EXPECT_LT()
*
* @expected: expected value
* @seen: measured value
@@ -583,7 +583,7 @@
__EXPECT(expected, #expected, seen, #seen, <, 0)
/**
- * EXPECT_LE(expected, seen)
+ * EXPECT_LE()
*
* @expected: expected value
* @seen: measured value
@@ -594,7 +594,7 @@
__EXPECT(expected, #expected, seen, #seen, <=, 0)
/**
- * EXPECT_GT(expected, seen)
+ * EXPECT_GT()
*
* @expected: expected value
* @seen: measured value
@@ -605,7 +605,7 @@
__EXPECT(expected, #expected, seen, #seen, >, 0)
/**
- * EXPECT_GE(expected, seen)
+ * EXPECT_GE()
*
* @expected: expected value
* @seen: measured value
@@ -616,7 +616,7 @@
__EXPECT(expected, #expected, seen, #seen, >=, 0)
/**
- * EXPECT_NULL(seen)
+ * EXPECT_NULL()
*
* @seen: measured value
*
@@ -626,7 +626,7 @@
__EXPECT(NULL, "NULL", seen, #seen, ==, 0)
/**
- * EXPECT_TRUE(seen)
+ * EXPECT_TRUE()
*
* @seen: measured value
*
@@ -636,7 +636,7 @@
__EXPECT(0, "0", seen, #seen, !=, 0)
/**
- * EXPECT_FALSE(seen)
+ * EXPECT_FALSE()
*
* @seen: measured value
*
@@ -646,7 +646,7 @@
__EXPECT(0, "0", seen, #seen, ==, 0)
/**
- * EXPECT_STREQ(expected, seen)
+ * EXPECT_STREQ()
*
* @expected: expected value
* @seen: measured value
@@ -657,7 +657,7 @@
__EXPECT_STR(expected, seen, ==, 0)
/**
- * EXPECT_STRNE(expected, seen)
+ * EXPECT_STRNE()
*
* @expected: expected value
* @seen: measured value
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 307ceaa..7a2c242 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,10 +1,13 @@
# SPDX-License-Identifier: GPL-2.0-only
+/aarch64/get-reg-list
+/aarch64/get-reg-list-sve
/s390x/memop
/s390x/resets
/s390x/sync_regs_test
/x86_64/cr4_cpuid_sync_test
/x86_64/debug_regs
/x86_64/evmcs_test
+/x86_64/kvm_pv_test
/x86_64/hyperv_cpuid
/x86_64/mmio_warning_test
/x86_64/platform_info_test
@@ -15,6 +18,7 @@
/x86_64/vmx_preemption_timer_test
/x86_64/svm_vmcall_test
/x86_64/sync_regs_test
+/x86_64/vmx_apic_access_test
/x86_64/vmx_close_while_nested_test
/x86_64/vmx_dirty_log_test
/x86_64/vmx_set_nested_state_test
@@ -23,6 +27,7 @@
/clear_dirty_log_test
/demand_paging_test
/dirty_log_test
+/dirty_log_perf_test
/kvm_create_max_vcpus
/set_memory_region_test
/steal_time
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 7ebe71f..3d14ef7 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -34,13 +34,14 @@
endif
LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c
-LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c
+LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S
LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c
LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c
TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
+TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
@@ -49,6 +50,7 @@
TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test
TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
+TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
@@ -57,14 +59,15 @@
TEST_GEN_PROGS_x86_64 += x86_64/debug_regs
TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test
TEST_GEN_PROGS_x86_64 += x86_64/user_msr_test
-TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
TEST_GEN_PROGS_x86_64 += demand_paging_test
TEST_GEN_PROGS_x86_64 += dirty_log_test
+TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
TEST_GEN_PROGS_x86_64 += set_memory_region_test
TEST_GEN_PROGS_x86_64 += steal_time
-TEST_GEN_PROGS_aarch64 += clear_dirty_log_test
+TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
+TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list-sve
TEST_GEN_PROGS_aarch64 += demand_paging_test
TEST_GEN_PROGS_aarch64 += dirty_log_test
TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus
@@ -110,14 +113,21 @@
include ../lib.mk
STATIC_LIBS := $(OUTPUT)/libkvm.a
-LIBKVM_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM))
-EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS) cscope.*
+LIBKVM_C := $(filter %.c,$(LIBKVM))
+LIBKVM_S := $(filter %.S,$(LIBKVM))
+LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
+LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S))
+EXTRA_CLEAN += $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(STATIC_LIBS) cscope.*
-x := $(shell mkdir -p $(sort $(dir $(LIBKVM_OBJ))))
-$(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c
+x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ))))
+$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
-$(OUTPUT)/libkvm.a: $(LIBKVM_OBJ)
+$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S
+ $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
+
+LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)
+$(OUTPUT)/libkvm.a: $(LIBKVM_OBJS)
$(AR) crs $@ $^
x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c
new file mode 100644
index 0000000..efba766
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c
@@ -0,0 +1,3 @@
+// SPDX-License-Identifier: GPL-2.0
+#define REG_LIST_SVE
+#include "get-reg-list.c"
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
new file mode 100644
index 0000000..33218a3
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -0,0 +1,841 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Check for KVM_GET_REG_LIST regressions.
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ *
+ * When attempting to migrate from a host with an older kernel to a host
+ * with a newer kernel we allow the newer kernel on the destination to
+ * list new registers with get-reg-list. We assume they'll be unused, at
+ * least until the guest reboots, and so they're relatively harmless.
+ * However, if the destination host with the newer kernel is missing
+ * registers which the source host with the older kernel has, then that's
+ * a regression in get-reg-list. This test checks for that regression by
+ * checking the current list against a blessed list. We should never have
+ * missing registers, but if new ones appear then they can probably be
+ * added to the blessed list. A completely new blessed list can be created
+ * by running the test with the --list command line argument.
+ *
+ * Note, the blessed list should be created from the oldest possible
+ * kernel. We can't go older than v4.15, though, because that's the first
+ * release to expose the ID system registers in KVM_GET_REG_LIST, see
+ * commit 93390c0a1b20 ("arm64: KVM: Hide unsupported AArch64 CPU features
+ * from guests"). Also, one must use the --core-reg-fixup command line
+ * option when running on an older kernel that doesn't include df205b5c6328
+ * ("KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST")
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "kvm_util.h"
+#include "test_util.h"
+#include "processor.h"
+
+#ifdef REG_LIST_SVE
+#define reg_list_sve() (true)
+#else
+#define reg_list_sve() (false)
+#endif
+
+#define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK)
+
+#define for_each_reg(i) \
+ for ((i) = 0; (i) < reg_list->n; ++(i))
+
+#define for_each_missing_reg(i) \
+ for ((i) = 0; (i) < blessed_n; ++(i)) \
+ if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i]))
+
+#define for_each_new_reg(i) \
+ for ((i) = 0; (i) < reg_list->n; ++(i)) \
+ if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i]))
+
+
+static struct kvm_reg_list *reg_list;
+
+static __u64 base_regs[], vregs[], sve_regs[], rejects_set[];
+static __u64 base_regs_n, vregs_n, sve_regs_n, rejects_set_n;
+static __u64 *blessed_reg, blessed_n;
+
+static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg)
+{
+ int i;
+
+ for (i = 0; i < nr_regs; ++i)
+ if (reg == regs[i])
+ return true;
+ return false;
+}
+
+static const char *str_with_index(const char *template, __u64 index)
+{
+ char *str, *p;
+ int n;
+
+ str = strdup(template);
+ p = strstr(str, "##");
+ n = sprintf(p, "%lld", index);
+ strcat(p + n, strstr(template, "##") + 2);
+
+ return (const char *)str;
+}
+
+#define CORE_REGS_XX_NR_WORDS 2
+#define CORE_SPSR_XX_NR_WORDS 2
+#define CORE_FPREGS_XX_NR_WORDS 4
+
+static const char *core_id_to_str(__u64 id)
+{
+ __u64 core_off = id & ~REG_MASK, idx;
+
+ /*
+ * core_off is the offset into struct kvm_regs
+ */
+ switch (core_off) {
+ case KVM_REG_ARM_CORE_REG(regs.regs[0]) ...
+ KVM_REG_ARM_CORE_REG(regs.regs[30]):
+ idx = (core_off - KVM_REG_ARM_CORE_REG(regs.regs[0])) / CORE_REGS_XX_NR_WORDS;
+ TEST_ASSERT(idx < 31, "Unexpected regs.regs index: %lld", idx);
+ return str_with_index("KVM_REG_ARM_CORE_REG(regs.regs[##])", idx);
+ case KVM_REG_ARM_CORE_REG(regs.sp):
+ return "KVM_REG_ARM_CORE_REG(regs.sp)";
+ case KVM_REG_ARM_CORE_REG(regs.pc):
+ return "KVM_REG_ARM_CORE_REG(regs.pc)";
+ case KVM_REG_ARM_CORE_REG(regs.pstate):
+ return "KVM_REG_ARM_CORE_REG(regs.pstate)";
+ case KVM_REG_ARM_CORE_REG(sp_el1):
+ return "KVM_REG_ARM_CORE_REG(sp_el1)";
+ case KVM_REG_ARM_CORE_REG(elr_el1):
+ return "KVM_REG_ARM_CORE_REG(elr_el1)";
+ case KVM_REG_ARM_CORE_REG(spsr[0]) ...
+ KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
+ idx = (core_off - KVM_REG_ARM_CORE_REG(spsr[0])) / CORE_SPSR_XX_NR_WORDS;
+ TEST_ASSERT(idx < KVM_NR_SPSR, "Unexpected spsr index: %lld", idx);
+ return str_with_index("KVM_REG_ARM_CORE_REG(spsr[##])", idx);
+ case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+ KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+ idx = (core_off - KVM_REG_ARM_CORE_REG(fp_regs.vregs[0])) / CORE_FPREGS_XX_NR_WORDS;
+ TEST_ASSERT(idx < 32, "Unexpected fp_regs.vregs index: %lld", idx);
+ return str_with_index("KVM_REG_ARM_CORE_REG(fp_regs.vregs[##])", idx);
+ case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+ return "KVM_REG_ARM_CORE_REG(fp_regs.fpsr)";
+ case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+ return "KVM_REG_ARM_CORE_REG(fp_regs.fpcr)";
+ }
+
+ TEST_FAIL("Unknown core reg id: 0x%llx", id);
+ return NULL;
+}
+
+static const char *sve_id_to_str(__u64 id)
+{
+ __u64 sve_off, n, i;
+
+ if (id == KVM_REG_ARM64_SVE_VLS)
+ return "KVM_REG_ARM64_SVE_VLS";
+
+ sve_off = id & ~(REG_MASK | ((1ULL << 5) - 1));
+ i = id & (KVM_ARM64_SVE_MAX_SLICES - 1);
+
+ TEST_ASSERT(i == 0, "Currently we don't expect slice > 0, reg id 0x%llx", id);
+
+ switch (sve_off) {
+ case KVM_REG_ARM64_SVE_ZREG_BASE ...
+ KVM_REG_ARM64_SVE_ZREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_ZREGS - 1:
+ n = (id >> 5) & (KVM_ARM64_SVE_NUM_ZREGS - 1);
+ TEST_ASSERT(id == KVM_REG_ARM64_SVE_ZREG(n, 0),
+ "Unexpected bits set in SVE ZREG id: 0x%llx", id);
+ return str_with_index("KVM_REG_ARM64_SVE_ZREG(##, 0)", n);
+ case KVM_REG_ARM64_SVE_PREG_BASE ...
+ KVM_REG_ARM64_SVE_PREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_PREGS - 1:
+ n = (id >> 5) & (KVM_ARM64_SVE_NUM_PREGS - 1);
+ TEST_ASSERT(id == KVM_REG_ARM64_SVE_PREG(n, 0),
+ "Unexpected bits set in SVE PREG id: 0x%llx", id);
+ return str_with_index("KVM_REG_ARM64_SVE_PREG(##, 0)", n);
+ case KVM_REG_ARM64_SVE_FFR_BASE:
+ TEST_ASSERT(id == KVM_REG_ARM64_SVE_FFR(0),
+ "Unexpected bits set in SVE FFR id: 0x%llx", id);
+ return "KVM_REG_ARM64_SVE_FFR(0)";
+ }
+
+ return NULL;
+}
+
+static void print_reg(__u64 id)
+{
+ unsigned op0, op1, crn, crm, op2;
+ const char *reg_size = NULL;
+
+ TEST_ASSERT((id & KVM_REG_ARCH_MASK) == KVM_REG_ARM64,
+ "KVM_REG_ARM64 missing in reg id: 0x%llx", id);
+
+ switch (id & KVM_REG_SIZE_MASK) {
+ case KVM_REG_SIZE_U8:
+ reg_size = "KVM_REG_SIZE_U8";
+ break;
+ case KVM_REG_SIZE_U16:
+ reg_size = "KVM_REG_SIZE_U16";
+ break;
+ case KVM_REG_SIZE_U32:
+ reg_size = "KVM_REG_SIZE_U32";
+ break;
+ case KVM_REG_SIZE_U64:
+ reg_size = "KVM_REG_SIZE_U64";
+ break;
+ case KVM_REG_SIZE_U128:
+ reg_size = "KVM_REG_SIZE_U128";
+ break;
+ case KVM_REG_SIZE_U256:
+ reg_size = "KVM_REG_SIZE_U256";
+ break;
+ case KVM_REG_SIZE_U512:
+ reg_size = "KVM_REG_SIZE_U512";
+ break;
+ case KVM_REG_SIZE_U1024:
+ reg_size = "KVM_REG_SIZE_U1024";
+ break;
+ case KVM_REG_SIZE_U2048:
+ reg_size = "KVM_REG_SIZE_U2048";
+ break;
+ default:
+ TEST_FAIL("Unexpected reg size: 0x%llx in reg id: 0x%llx",
+ (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id);
+ }
+
+ switch (id & KVM_REG_ARM_COPROC_MASK) {
+ case KVM_REG_ARM_CORE:
+ printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_CORE | %s,\n", reg_size, core_id_to_str(id));
+ break;
+ case KVM_REG_ARM_DEMUX:
+ TEST_ASSERT(!(id & ~(REG_MASK | KVM_REG_ARM_DEMUX_ID_MASK | KVM_REG_ARM_DEMUX_VAL_MASK)),
+ "Unexpected bits set in DEMUX reg id: 0x%llx", id);
+ printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | %lld,\n",
+ reg_size, id & KVM_REG_ARM_DEMUX_VAL_MASK);
+ break;
+ case KVM_REG_ARM64_SYSREG:
+ op0 = (id & KVM_REG_ARM64_SYSREG_OP0_MASK) >> KVM_REG_ARM64_SYSREG_OP0_SHIFT;
+ op1 = (id & KVM_REG_ARM64_SYSREG_OP1_MASK) >> KVM_REG_ARM64_SYSREG_OP1_SHIFT;
+ crn = (id & KVM_REG_ARM64_SYSREG_CRN_MASK) >> KVM_REG_ARM64_SYSREG_CRN_SHIFT;
+ crm = (id & KVM_REG_ARM64_SYSREG_CRM_MASK) >> KVM_REG_ARM64_SYSREG_CRM_SHIFT;
+ op2 = (id & KVM_REG_ARM64_SYSREG_OP2_MASK) >> KVM_REG_ARM64_SYSREG_OP2_SHIFT;
+ TEST_ASSERT(id == ARM64_SYS_REG(op0, op1, crn, crm, op2),
+ "Unexpected bits set in SYSREG reg id: 0x%llx", id);
+ printf("\tARM64_SYS_REG(%d, %d, %d, %d, %d),\n", op0, op1, crn, crm, op2);
+ break;
+ case KVM_REG_ARM_FW:
+ TEST_ASSERT(id == KVM_REG_ARM_FW_REG(id & 0xffff),
+ "Unexpected bits set in FW reg id: 0x%llx", id);
+ printf("\tKVM_REG_ARM_FW_REG(%lld),\n", id & 0xffff);
+ break;
+ case KVM_REG_ARM64_SVE:
+ if (reg_list_sve())
+ printf("\t%s,\n", sve_id_to_str(id));
+ else
+ TEST_FAIL("KVM_REG_ARM64_SVE is an unexpected coproc type in reg id: 0x%llx", id);
+ break;
+ default:
+ TEST_FAIL("Unexpected coproc type: 0x%llx in reg id: 0x%llx",
+ (id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT, id);
+ }
+}
+
+/*
+ * Older kernels listed each 32-bit word of CORE registers separately.
+ * For 64 and 128-bit registers we need to ignore the extra words. We
+ * also need to fixup the sizes, because the older kernels stated all
+ * registers were 64-bit, even when they weren't.
+ */
+static void core_reg_fixup(void)
+{
+ struct kvm_reg_list *tmp;
+ __u64 id, core_off;
+ int i;
+
+ tmp = calloc(1, sizeof(*tmp) + reg_list->n * sizeof(__u64));
+
+ for (i = 0; i < reg_list->n; ++i) {
+ id = reg_list->reg[i];
+
+ if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM_CORE) {
+ tmp->reg[tmp->n++] = id;
+ continue;
+ }
+
+ core_off = id & ~REG_MASK;
+
+ switch (core_off) {
+ case 0x52: case 0xd2: case 0xd6:
+ /*
+ * These offsets are pointing at padding.
+ * We need to ignore them too.
+ */
+ continue;
+ case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+ KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+ if (core_off & 3)
+ continue;
+ id &= ~KVM_REG_SIZE_MASK;
+ id |= KVM_REG_SIZE_U128;
+ tmp->reg[tmp->n++] = id;
+ continue;
+ case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+ case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+ id &= ~KVM_REG_SIZE_MASK;
+ id |= KVM_REG_SIZE_U32;
+ tmp->reg[tmp->n++] = id;
+ continue;
+ default:
+ if (core_off & 1)
+ continue;
+ tmp->reg[tmp->n++] = id;
+ break;
+ }
+ }
+
+ free(reg_list);
+ reg_list = tmp;
+}
+
+static void prepare_vcpu_init(struct kvm_vcpu_init *init)
+{
+ if (reg_list_sve())
+ init->features[0] |= 1 << KVM_ARM_VCPU_SVE;
+}
+
+static void finalize_vcpu(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ int feature;
+
+ if (reg_list_sve()) {
+ feature = KVM_ARM_VCPU_SVE;
+ vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_FINALIZE, &feature);
+ }
+}
+
+static void check_supported(void)
+{
+ if (reg_list_sve() && !kvm_check_cap(KVM_CAP_ARM_SVE)) {
+ fprintf(stderr, "SVE not available, skipping tests\n");
+ exit(KSFT_SKIP);
+ }
+}
+
+int main(int ac, char **av)
+{
+ struct kvm_vcpu_init init = { .target = -1, };
+ int new_regs = 0, missing_regs = 0, i;
+ int failed_get = 0, failed_set = 0, failed_reject = 0;
+ bool print_list = false, fixup_core_regs = false;
+ struct kvm_vm *vm;
+ __u64 *vec_regs;
+
+ check_supported();
+
+ for (i = 1; i < ac; ++i) {
+ if (strcmp(av[i], "--core-reg-fixup") == 0)
+ fixup_core_regs = true;
+ else if (strcmp(av[i], "--list") == 0)
+ print_list = true;
+ else
+ fprintf(stderr, "Ignoring unknown option: %s\n", av[i]);
+ }
+
+ vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+ prepare_vcpu_init(&init);
+ aarch64_vcpu_add_default(vm, 0, &init, NULL);
+ finalize_vcpu(vm, 0);
+
+ reg_list = vcpu_get_reg_list(vm, 0);
+
+ if (fixup_core_regs)
+ core_reg_fixup();
+
+ if (print_list) {
+ putchar('\n');
+ for_each_reg(i)
+ print_reg(reg_list->reg[i]);
+ putchar('\n');
+ return 0;
+ }
+
+ /*
+ * We only test that we can get the register and then write back the
+ * same value. Some registers may allow other values to be written
+ * back, but others only allow some bits to be changed, and at least
+ * for ID registers set will fail if the value does not exactly match
+ * what was returned by get. If registers that allow other values to
+ * be written need to have the other values tested, then we should
+ * create a new set of tests for those in a new independent test
+ * executable.
+ */
+ for_each_reg(i) {
+ uint8_t addr[2048 / 8];
+ struct kvm_one_reg reg = {
+ .id = reg_list->reg[i],
+ .addr = (__u64)&addr,
+ };
+ int ret;
+
+ ret = _vcpu_ioctl(vm, 0, KVM_GET_ONE_REG, ®);
+ if (ret) {
+ puts("Failed to get ");
+ print_reg(reg.id);
+ putchar('\n');
+ ++failed_get;
+ }
+
+ /* rejects_set registers are rejected after KVM_ARM_VCPU_FINALIZE */
+ if (find_reg(rejects_set, rejects_set_n, reg.id)) {
+ ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®);
+ if (ret != -1 || errno != EPERM) {
+ printf("Failed to reject (ret=%d, errno=%d) ", ret, errno);
+ print_reg(reg.id);
+ putchar('\n');
+ ++failed_reject;
+ }
+ continue;
+ }
+
+ ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®);
+ if (ret) {
+ puts("Failed to set ");
+ print_reg(reg.id);
+ putchar('\n');
+ ++failed_set;
+ }
+ }
+
+ if (reg_list_sve()) {
+ blessed_n = base_regs_n + sve_regs_n;
+ vec_regs = sve_regs;
+ } else {
+ blessed_n = base_regs_n + vregs_n;
+ vec_regs = vregs;
+ }
+
+ blessed_reg = calloc(blessed_n, sizeof(__u64));
+ for (i = 0; i < base_regs_n; ++i)
+ blessed_reg[i] = base_regs[i];
+ for (i = 0; i < blessed_n - base_regs_n; ++i)
+ blessed_reg[base_regs_n + i] = vec_regs[i];
+
+ for_each_new_reg(i)
+ ++new_regs;
+
+ for_each_missing_reg(i)
+ ++missing_regs;
+
+ if (new_regs || missing_regs) {
+ printf("Number blessed registers: %5lld\n", blessed_n);
+ printf("Number registers: %5lld\n", reg_list->n);
+ }
+
+ if (new_regs) {
+ printf("\nThere are %d new registers.\n"
+ "Consider adding them to the blessed reg "
+ "list with the following lines:\n\n", new_regs);
+ for_each_new_reg(i)
+ print_reg(reg_list->reg[i]);
+ putchar('\n');
+ }
+
+ if (missing_regs) {
+ printf("\nThere are %d missing registers.\n"
+ "The following lines are missing registers:\n\n", missing_regs);
+ for_each_missing_reg(i)
+ print_reg(blessed_reg[i]);
+ putchar('\n');
+ }
+
+ TEST_ASSERT(!missing_regs && !failed_get && !failed_set && !failed_reject,
+ "There are %d missing registers; "
+ "%d registers failed get; %d registers failed set; %d registers failed reject",
+ missing_regs, failed_get, failed_set, failed_reject);
+
+ return 0;
+}
+
+/*
+ * The current blessed list was primed with the output of kernel version
+ * v4.15 with --core-reg-fixup and then later updated with new registers.
+ */
+static __u64 base_regs[] = {
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[0]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[1]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[2]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[3]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[4]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[5]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[6]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[7]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[8]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[9]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[10]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[11]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[12]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[13]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[14]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[15]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[16]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[17]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[18]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[19]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[20]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[21]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[22]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[23]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[24]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[25]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[26]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[27]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[28]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[29]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[30]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.sp),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pc),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pstate),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(sp_el1),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(elr_el1),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[0]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[1]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[2]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[3]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[4]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpsr),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpcr),
+ KVM_REG_ARM_FW_REG(0),
+ KVM_REG_ARM_FW_REG(1),
+ KVM_REG_ARM_FW_REG(2),
+ ARM64_SYS_REG(3, 3, 14, 3, 1), /* CNTV_CTL_EL0 */
+ ARM64_SYS_REG(3, 3, 14, 3, 2), /* CNTV_CVAL_EL0 */
+ ARM64_SYS_REG(3, 3, 14, 0, 2),
+ ARM64_SYS_REG(3, 0, 0, 0, 0), /* MIDR_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 0, 6), /* REVIDR_EL1 */
+ ARM64_SYS_REG(3, 1, 0, 0, 1), /* CLIDR_EL1 */
+ ARM64_SYS_REG(3, 1, 0, 0, 7), /* AIDR_EL1 */
+ ARM64_SYS_REG(3, 3, 0, 0, 1), /* CTR_EL0 */
+ ARM64_SYS_REG(2, 0, 0, 0, 4),
+ ARM64_SYS_REG(2, 0, 0, 0, 5),
+ ARM64_SYS_REG(2, 0, 0, 0, 6),
+ ARM64_SYS_REG(2, 0, 0, 0, 7),
+ ARM64_SYS_REG(2, 0, 0, 1, 4),
+ ARM64_SYS_REG(2, 0, 0, 1, 5),
+ ARM64_SYS_REG(2, 0, 0, 1, 6),
+ ARM64_SYS_REG(2, 0, 0, 1, 7),
+ ARM64_SYS_REG(2, 0, 0, 2, 0), /* MDCCINT_EL1 */
+ ARM64_SYS_REG(2, 0, 0, 2, 2), /* MDSCR_EL1 */
+ ARM64_SYS_REG(2, 0, 0, 2, 4),
+ ARM64_SYS_REG(2, 0, 0, 2, 5),
+ ARM64_SYS_REG(2, 0, 0, 2, 6),
+ ARM64_SYS_REG(2, 0, 0, 2, 7),
+ ARM64_SYS_REG(2, 0, 0, 3, 4),
+ ARM64_SYS_REG(2, 0, 0, 3, 5),
+ ARM64_SYS_REG(2, 0, 0, 3, 6),
+ ARM64_SYS_REG(2, 0, 0, 3, 7),
+ ARM64_SYS_REG(2, 0, 0, 4, 4),
+ ARM64_SYS_REG(2, 0, 0, 4, 5),
+ ARM64_SYS_REG(2, 0, 0, 4, 6),
+ ARM64_SYS_REG(2, 0, 0, 4, 7),
+ ARM64_SYS_REG(2, 0, 0, 5, 4),
+ ARM64_SYS_REG(2, 0, 0, 5, 5),
+ ARM64_SYS_REG(2, 0, 0, 5, 6),
+ ARM64_SYS_REG(2, 0, 0, 5, 7),
+ ARM64_SYS_REG(2, 0, 0, 6, 4),
+ ARM64_SYS_REG(2, 0, 0, 6, 5),
+ ARM64_SYS_REG(2, 0, 0, 6, 6),
+ ARM64_SYS_REG(2, 0, 0, 6, 7),
+ ARM64_SYS_REG(2, 0, 0, 7, 4),
+ ARM64_SYS_REG(2, 0, 0, 7, 5),
+ ARM64_SYS_REG(2, 0, 0, 7, 6),
+ ARM64_SYS_REG(2, 0, 0, 7, 7),
+ ARM64_SYS_REG(2, 0, 0, 8, 4),
+ ARM64_SYS_REG(2, 0, 0, 8, 5),
+ ARM64_SYS_REG(2, 0, 0, 8, 6),
+ ARM64_SYS_REG(2, 0, 0, 8, 7),
+ ARM64_SYS_REG(2, 0, 0, 9, 4),
+ ARM64_SYS_REG(2, 0, 0, 9, 5),
+ ARM64_SYS_REG(2, 0, 0, 9, 6),
+ ARM64_SYS_REG(2, 0, 0, 9, 7),
+ ARM64_SYS_REG(2, 0, 0, 10, 4),
+ ARM64_SYS_REG(2, 0, 0, 10, 5),
+ ARM64_SYS_REG(2, 0, 0, 10, 6),
+ ARM64_SYS_REG(2, 0, 0, 10, 7),
+ ARM64_SYS_REG(2, 0, 0, 11, 4),
+ ARM64_SYS_REG(2, 0, 0, 11, 5),
+ ARM64_SYS_REG(2, 0, 0, 11, 6),
+ ARM64_SYS_REG(2, 0, 0, 11, 7),
+ ARM64_SYS_REG(2, 0, 0, 12, 4),
+ ARM64_SYS_REG(2, 0, 0, 12, 5),
+ ARM64_SYS_REG(2, 0, 0, 12, 6),
+ ARM64_SYS_REG(2, 0, 0, 12, 7),
+ ARM64_SYS_REG(2, 0, 0, 13, 4),
+ ARM64_SYS_REG(2, 0, 0, 13, 5),
+ ARM64_SYS_REG(2, 0, 0, 13, 6),
+ ARM64_SYS_REG(2, 0, 0, 13, 7),
+ ARM64_SYS_REG(2, 0, 0, 14, 4),
+ ARM64_SYS_REG(2, 0, 0, 14, 5),
+ ARM64_SYS_REG(2, 0, 0, 14, 6),
+ ARM64_SYS_REG(2, 0, 0, 14, 7),
+ ARM64_SYS_REG(2, 0, 0, 15, 4),
+ ARM64_SYS_REG(2, 0, 0, 15, 5),
+ ARM64_SYS_REG(2, 0, 0, 15, 6),
+ ARM64_SYS_REG(2, 0, 0, 15, 7),
+ ARM64_SYS_REG(2, 4, 0, 7, 0), /* DBGVCR32_EL2 */
+ ARM64_SYS_REG(3, 0, 0, 0, 5), /* MPIDR_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 1, 0), /* ID_PFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 1, 1), /* ID_PFR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 1, 2), /* ID_DFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 1, 3), /* ID_AFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 1, 4), /* ID_MMFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 1, 5), /* ID_MMFR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 1, 6), /* ID_MMFR2_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 1, 7), /* ID_MMFR3_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 2, 0), /* ID_ISAR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 2, 1), /* ID_ISAR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 2, 2), /* ID_ISAR2_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 2, 3), /* ID_ISAR3_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 2, 4), /* ID_ISAR4_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 2, 5), /* ID_ISAR5_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 2, 6), /* ID_MMFR4_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 2, 7), /* ID_ISAR6_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 3, 0), /* MVFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 3, 1), /* MVFR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 3, 2), /* MVFR2_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 3, 3),
+ ARM64_SYS_REG(3, 0, 0, 3, 4), /* ID_PFR2_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 3, 5), /* ID_DFR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 3, 6), /* ID_MMFR5_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 3, 7),
+ ARM64_SYS_REG(3, 0, 0, 4, 0), /* ID_AA64PFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 4, 1), /* ID_AA64PFR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 4, 2),
+ ARM64_SYS_REG(3, 0, 0, 4, 3),
+ ARM64_SYS_REG(3, 0, 0, 4, 4), /* ID_AA64ZFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 4, 5),
+ ARM64_SYS_REG(3, 0, 0, 4, 6),
+ ARM64_SYS_REG(3, 0, 0, 4, 7),
+ ARM64_SYS_REG(3, 0, 0, 5, 0), /* ID_AA64DFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 5, 1), /* ID_AA64DFR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 5, 2),
+ ARM64_SYS_REG(3, 0, 0, 5, 3),
+ ARM64_SYS_REG(3, 0, 0, 5, 4), /* ID_AA64AFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 5, 5), /* ID_AA64AFR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 5, 6),
+ ARM64_SYS_REG(3, 0, 0, 5, 7),
+ ARM64_SYS_REG(3, 0, 0, 6, 0), /* ID_AA64ISAR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 6, 1), /* ID_AA64ISAR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 6, 2),
+ ARM64_SYS_REG(3, 0, 0, 6, 3),
+ ARM64_SYS_REG(3, 0, 0, 6, 4),
+ ARM64_SYS_REG(3, 0, 0, 6, 5),
+ ARM64_SYS_REG(3, 0, 0, 6, 6),
+ ARM64_SYS_REG(3, 0, 0, 6, 7),
+ ARM64_SYS_REG(3, 0, 0, 7, 0), /* ID_AA64MMFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 7, 1), /* ID_AA64MMFR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 7, 2), /* ID_AA64MMFR2_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 7, 3),
+ ARM64_SYS_REG(3, 0, 0, 7, 4),
+ ARM64_SYS_REG(3, 0, 0, 7, 5),
+ ARM64_SYS_REG(3, 0, 0, 7, 6),
+ ARM64_SYS_REG(3, 0, 0, 7, 7),
+ ARM64_SYS_REG(3, 0, 1, 0, 0), /* SCTLR_EL1 */
+ ARM64_SYS_REG(3, 0, 1, 0, 1), /* ACTLR_EL1 */
+ ARM64_SYS_REG(3, 0, 1, 0, 2), /* CPACR_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 0, 0), /* TTBR0_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 0, 1), /* TTBR1_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 0, 2), /* TCR_EL1 */
+ ARM64_SYS_REG(3, 0, 5, 1, 0), /* AFSR0_EL1 */
+ ARM64_SYS_REG(3, 0, 5, 1, 1), /* AFSR1_EL1 */
+ ARM64_SYS_REG(3, 0, 5, 2, 0), /* ESR_EL1 */
+ ARM64_SYS_REG(3, 0, 6, 0, 0), /* FAR_EL1 */
+ ARM64_SYS_REG(3, 0, 7, 4, 0), /* PAR_EL1 */
+ ARM64_SYS_REG(3, 0, 9, 14, 1), /* PMINTENSET_EL1 */
+ ARM64_SYS_REG(3, 0, 9, 14, 2), /* PMINTENCLR_EL1 */
+ ARM64_SYS_REG(3, 0, 10, 2, 0), /* MAIR_EL1 */
+ ARM64_SYS_REG(3, 0, 10, 3, 0), /* AMAIR_EL1 */
+ ARM64_SYS_REG(3, 0, 12, 0, 0), /* VBAR_EL1 */
+ ARM64_SYS_REG(3, 0, 12, 1, 1), /* DISR_EL1 */
+ ARM64_SYS_REG(3, 0, 13, 0, 1), /* CONTEXTIDR_EL1 */
+ ARM64_SYS_REG(3, 0, 13, 0, 4), /* TPIDR_EL1 */
+ ARM64_SYS_REG(3, 0, 14, 1, 0), /* CNTKCTL_EL1 */
+ ARM64_SYS_REG(3, 2, 0, 0, 0), /* CSSELR_EL1 */
+ ARM64_SYS_REG(3, 3, 9, 12, 0), /* PMCR_EL0 */
+ ARM64_SYS_REG(3, 3, 9, 12, 1), /* PMCNTENSET_EL0 */
+ ARM64_SYS_REG(3, 3, 9, 12, 2), /* PMCNTENCLR_EL0 */
+ ARM64_SYS_REG(3, 3, 9, 12, 3), /* PMOVSCLR_EL0 */
+ ARM64_SYS_REG(3, 3, 9, 12, 4), /* PMSWINC_EL0 */
+ ARM64_SYS_REG(3, 3, 9, 12, 5), /* PMSELR_EL0 */
+ ARM64_SYS_REG(3, 3, 9, 13, 0), /* PMCCNTR_EL0 */
+ ARM64_SYS_REG(3, 3, 9, 14, 0), /* PMUSERENR_EL0 */
+ ARM64_SYS_REG(3, 3, 9, 14, 3), /* PMOVSSET_EL0 */
+ ARM64_SYS_REG(3, 3, 13, 0, 2), /* TPIDR_EL0 */
+ ARM64_SYS_REG(3, 3, 13, 0, 3), /* TPIDRRO_EL0 */
+ ARM64_SYS_REG(3, 3, 14, 8, 0),
+ ARM64_SYS_REG(3, 3, 14, 8, 1),
+ ARM64_SYS_REG(3, 3, 14, 8, 2),
+ ARM64_SYS_REG(3, 3, 14, 8, 3),
+ ARM64_SYS_REG(3, 3, 14, 8, 4),
+ ARM64_SYS_REG(3, 3, 14, 8, 5),
+ ARM64_SYS_REG(3, 3, 14, 8, 6),
+ ARM64_SYS_REG(3, 3, 14, 8, 7),
+ ARM64_SYS_REG(3, 3, 14, 9, 0),
+ ARM64_SYS_REG(3, 3, 14, 9, 1),
+ ARM64_SYS_REG(3, 3, 14, 9, 2),
+ ARM64_SYS_REG(3, 3, 14, 9, 3),
+ ARM64_SYS_REG(3, 3, 14, 9, 4),
+ ARM64_SYS_REG(3, 3, 14, 9, 5),
+ ARM64_SYS_REG(3, 3, 14, 9, 6),
+ ARM64_SYS_REG(3, 3, 14, 9, 7),
+ ARM64_SYS_REG(3, 3, 14, 10, 0),
+ ARM64_SYS_REG(3, 3, 14, 10, 1),
+ ARM64_SYS_REG(3, 3, 14, 10, 2),
+ ARM64_SYS_REG(3, 3, 14, 10, 3),
+ ARM64_SYS_REG(3, 3, 14, 10, 4),
+ ARM64_SYS_REG(3, 3, 14, 10, 5),
+ ARM64_SYS_REG(3, 3, 14, 10, 6),
+ ARM64_SYS_REG(3, 3, 14, 10, 7),
+ ARM64_SYS_REG(3, 3, 14, 11, 0),
+ ARM64_SYS_REG(3, 3, 14, 11, 1),
+ ARM64_SYS_REG(3, 3, 14, 11, 2),
+ ARM64_SYS_REG(3, 3, 14, 11, 3),
+ ARM64_SYS_REG(3, 3, 14, 11, 4),
+ ARM64_SYS_REG(3, 3, 14, 11, 5),
+ ARM64_SYS_REG(3, 3, 14, 11, 6),
+ ARM64_SYS_REG(3, 3, 14, 12, 0),
+ ARM64_SYS_REG(3, 3, 14, 12, 1),
+ ARM64_SYS_REG(3, 3, 14, 12, 2),
+ ARM64_SYS_REG(3, 3, 14, 12, 3),
+ ARM64_SYS_REG(3, 3, 14, 12, 4),
+ ARM64_SYS_REG(3, 3, 14, 12, 5),
+ ARM64_SYS_REG(3, 3, 14, 12, 6),
+ ARM64_SYS_REG(3, 3, 14, 12, 7),
+ ARM64_SYS_REG(3, 3, 14, 13, 0),
+ ARM64_SYS_REG(3, 3, 14, 13, 1),
+ ARM64_SYS_REG(3, 3, 14, 13, 2),
+ ARM64_SYS_REG(3, 3, 14, 13, 3),
+ ARM64_SYS_REG(3, 3, 14, 13, 4),
+ ARM64_SYS_REG(3, 3, 14, 13, 5),
+ ARM64_SYS_REG(3, 3, 14, 13, 6),
+ ARM64_SYS_REG(3, 3, 14, 13, 7),
+ ARM64_SYS_REG(3, 3, 14, 14, 0),
+ ARM64_SYS_REG(3, 3, 14, 14, 1),
+ ARM64_SYS_REG(3, 3, 14, 14, 2),
+ ARM64_SYS_REG(3, 3, 14, 14, 3),
+ ARM64_SYS_REG(3, 3, 14, 14, 4),
+ ARM64_SYS_REG(3, 3, 14, 14, 5),
+ ARM64_SYS_REG(3, 3, 14, 14, 6),
+ ARM64_SYS_REG(3, 3, 14, 14, 7),
+ ARM64_SYS_REG(3, 3, 14, 15, 0),
+ ARM64_SYS_REG(3, 3, 14, 15, 1),
+ ARM64_SYS_REG(3, 3, 14, 15, 2),
+ ARM64_SYS_REG(3, 3, 14, 15, 3),
+ ARM64_SYS_REG(3, 3, 14, 15, 4),
+ ARM64_SYS_REG(3, 3, 14, 15, 5),
+ ARM64_SYS_REG(3, 3, 14, 15, 6),
+ ARM64_SYS_REG(3, 3, 14, 15, 7), /* PMCCFILTR_EL0 */
+ ARM64_SYS_REG(3, 4, 3, 0, 0), /* DACR32_EL2 */
+ ARM64_SYS_REG(3, 4, 5, 0, 1), /* IFSR32_EL2 */
+ ARM64_SYS_REG(3, 4, 5, 3, 0), /* FPEXC32_EL2 */
+ KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 0,
+ KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 1,
+ KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 2,
+};
+static __u64 base_regs_n = ARRAY_SIZE(base_regs);
+
+static __u64 vregs[] = {
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[1]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[2]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[3]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[4]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[5]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[6]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[7]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[8]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[9]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[10]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[11]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[12]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[13]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[14]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[15]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[16]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[17]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[18]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[19]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[20]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[21]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[22]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[23]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[24]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[25]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[26]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[27]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[28]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[29]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[30]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]),
+};
+static __u64 vregs_n = ARRAY_SIZE(vregs);
+
+static __u64 sve_regs[] = {
+ KVM_REG_ARM64_SVE_VLS,
+ KVM_REG_ARM64_SVE_ZREG(0, 0),
+ KVM_REG_ARM64_SVE_ZREG(1, 0),
+ KVM_REG_ARM64_SVE_ZREG(2, 0),
+ KVM_REG_ARM64_SVE_ZREG(3, 0),
+ KVM_REG_ARM64_SVE_ZREG(4, 0),
+ KVM_REG_ARM64_SVE_ZREG(5, 0),
+ KVM_REG_ARM64_SVE_ZREG(6, 0),
+ KVM_REG_ARM64_SVE_ZREG(7, 0),
+ KVM_REG_ARM64_SVE_ZREG(8, 0),
+ KVM_REG_ARM64_SVE_ZREG(9, 0),
+ KVM_REG_ARM64_SVE_ZREG(10, 0),
+ KVM_REG_ARM64_SVE_ZREG(11, 0),
+ KVM_REG_ARM64_SVE_ZREG(12, 0),
+ KVM_REG_ARM64_SVE_ZREG(13, 0),
+ KVM_REG_ARM64_SVE_ZREG(14, 0),
+ KVM_REG_ARM64_SVE_ZREG(15, 0),
+ KVM_REG_ARM64_SVE_ZREG(16, 0),
+ KVM_REG_ARM64_SVE_ZREG(17, 0),
+ KVM_REG_ARM64_SVE_ZREG(18, 0),
+ KVM_REG_ARM64_SVE_ZREG(19, 0),
+ KVM_REG_ARM64_SVE_ZREG(20, 0),
+ KVM_REG_ARM64_SVE_ZREG(21, 0),
+ KVM_REG_ARM64_SVE_ZREG(22, 0),
+ KVM_REG_ARM64_SVE_ZREG(23, 0),
+ KVM_REG_ARM64_SVE_ZREG(24, 0),
+ KVM_REG_ARM64_SVE_ZREG(25, 0),
+ KVM_REG_ARM64_SVE_ZREG(26, 0),
+ KVM_REG_ARM64_SVE_ZREG(27, 0),
+ KVM_REG_ARM64_SVE_ZREG(28, 0),
+ KVM_REG_ARM64_SVE_ZREG(29, 0),
+ KVM_REG_ARM64_SVE_ZREG(30, 0),
+ KVM_REG_ARM64_SVE_ZREG(31, 0),
+ KVM_REG_ARM64_SVE_PREG(0, 0),
+ KVM_REG_ARM64_SVE_PREG(1, 0),
+ KVM_REG_ARM64_SVE_PREG(2, 0),
+ KVM_REG_ARM64_SVE_PREG(3, 0),
+ KVM_REG_ARM64_SVE_PREG(4, 0),
+ KVM_REG_ARM64_SVE_PREG(5, 0),
+ KVM_REG_ARM64_SVE_PREG(6, 0),
+ KVM_REG_ARM64_SVE_PREG(7, 0),
+ KVM_REG_ARM64_SVE_PREG(8, 0),
+ KVM_REG_ARM64_SVE_PREG(9, 0),
+ KVM_REG_ARM64_SVE_PREG(10, 0),
+ KVM_REG_ARM64_SVE_PREG(11, 0),
+ KVM_REG_ARM64_SVE_PREG(12, 0),
+ KVM_REG_ARM64_SVE_PREG(13, 0),
+ KVM_REG_ARM64_SVE_PREG(14, 0),
+ KVM_REG_ARM64_SVE_PREG(15, 0),
+ KVM_REG_ARM64_SVE_FFR(0),
+ ARM64_SYS_REG(3, 0, 1, 2, 0), /* ZCR_EL1 */
+};
+static __u64 sve_regs_n = ARRAY_SIZE(sve_regs);
+
+static __u64 rejects_set[] = {
+#ifdef REG_LIST_SVE
+ KVM_REG_ARM64_SVE_VLS,
+#endif
+};
+static __u64 rejects_set_n = ARRAY_SIZE(rejects_set);
diff --git a/tools/testing/selftests/kvm/clear_dirty_log_test.c b/tools/testing/selftests/kvm/clear_dirty_log_test.c
deleted file mode 100644
index 11672ec..0000000
--- a/tools/testing/selftests/kvm/clear_dirty_log_test.c
+++ /dev/null
@@ -1,6 +0,0 @@
-#define USE_CLEAR_DIRTY_LOG
-#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0)
-#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1)
-#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
- KVM_DIRTY_LOG_INITIALLY_SET)
-#include "dirty_log_test.c"
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 360cd3e..3d96a7b 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -21,20 +21,12 @@
#include <linux/bitops.h>
#include <linux/userfaultfd.h>
-#include "test_util.h"
-#include "kvm_util.h"
+#include "perf_test_util.h"
#include "processor.h"
+#include "test_util.h"
#ifdef __NR_userfaultfd
-/* The memory slot index demand page */
-#define TEST_MEM_SLOT_INDEX 1
-
-/* Default guest test virtual memory offset */
-#define DEFAULT_GUEST_TEST_MEM 0xc0000000
-
-#define DEFAULT_GUEST_TEST_MEM_SIZE (1 << 30) /* 1G */
-
#ifdef PRINT_PER_PAGE_UPDATES
#define PER_PAGE_DEBUG(...) printf(__VA_ARGS__)
#else
@@ -47,77 +39,17 @@
#define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__)
#endif
-#define MAX_VCPUS 512
-
-/*
- * Guest/Host shared variables. Ensure addr_gva2hva() and/or
- * sync_global_to/from_guest() are used when accessing from
- * the host. READ/WRITE_ONCE() should also be used with anything
- * that may change.
- */
-static uint64_t host_page_size;
-static uint64_t guest_page_size;
-
static char *guest_data_prototype;
-/*
- * Guest physical memory offset of the testing memory slot.
- * This will be set to the topmost valid physical address minus
- * the test memory size.
- */
-static uint64_t guest_test_phys_mem;
-
-/*
- * Guest virtual memory offset of the testing memory slot.
- * Must not conflict with identity mapped test code.
- */
-static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
-
-struct vcpu_args {
- uint64_t gva;
- uint64_t pages;
-
- /* Only used by the host userspace part of the vCPU thread */
- int vcpu_id;
- struct kvm_vm *vm;
-};
-
-static struct vcpu_args vcpu_args[MAX_VCPUS];
-
-/*
- * Continuously write to the first 8 bytes of each page in the demand paging
- * memory region.
- */
-static void guest_code(uint32_t vcpu_id)
-{
- uint64_t gva;
- uint64_t pages;
- int i;
-
- /* Make sure vCPU args data structure is not corrupt. */
- GUEST_ASSERT(vcpu_args[vcpu_id].vcpu_id == vcpu_id);
-
- gva = vcpu_args[vcpu_id].gva;
- pages = vcpu_args[vcpu_id].pages;
-
- for (i = 0; i < pages; i++) {
- uint64_t addr = gva + (i * guest_page_size);
-
- addr &= ~(host_page_size - 1);
- *(uint64_t *)addr = 0x0123456789ABCDEF;
- }
-
- GUEST_SYNC(1);
-}
-
static void *vcpu_worker(void *data)
{
int ret;
- struct vcpu_args *args = (struct vcpu_args *)data;
- struct kvm_vm *vm = args->vm;
- int vcpu_id = args->vcpu_id;
+ struct vcpu_args *vcpu_args = (struct vcpu_args *)data;
+ int vcpu_id = vcpu_args->vcpu_id;
+ struct kvm_vm *vm = perf_test_args.vm;
struct kvm_run *run;
- struct timespec start, end, ts_diff;
+ struct timespec start;
+ struct timespec ts_diff;
vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
run = vcpu_state(vm, vcpu_id);
@@ -133,52 +65,18 @@
exit_reason_str(run->exit_reason));
}
- clock_gettime(CLOCK_MONOTONIC, &end);
- ts_diff = timespec_sub(end, start);
+ ts_diff = timespec_diff_now(start);
PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id,
ts_diff.tv_sec, ts_diff.tv_nsec);
return NULL;
}
-#define PAGE_SHIFT_4K 12
-#define PTES_PER_4K_PT 512
-
-static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus,
- uint64_t vcpu_memory_bytes)
-{
- struct kvm_vm *vm;
- uint64_t pages = DEFAULT_GUEST_PHY_PAGES;
-
- /* Account for a few pages per-vCPU for stacks */
- pages += DEFAULT_STACK_PGS * vcpus;
-
- /*
- * Reserve twice the ammount of memory needed to map the test region and
- * the page table / stacks region, at 4k, for page tables. Do the
- * calculation with 4K page size: the smallest of all archs. (e.g., 64K
- * page size guest will need even less memory for page tables).
- */
- pages += (2 * pages) / PTES_PER_4K_PT;
- pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) /
- PTES_PER_4K_PT;
- pages = vm_adjust_num_guest_pages(mode, pages);
-
- pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
-
- vm = _vm_create(mode, pages, O_RDWR);
- kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
-#ifdef __x86_64__
- vm_create_irqchip(vm);
-#endif
- return vm;
-}
-
static int handle_uffd_page_request(int uffd, uint64_t addr)
{
pid_t tid;
struct timespec start;
- struct timespec end;
+ struct timespec ts_diff;
struct uffdio_copy copy;
int r;
@@ -186,7 +84,7 @@
copy.src = (uint64_t)guest_data_prototype;
copy.dst = addr;
- copy.len = host_page_size;
+ copy.len = perf_test_args.host_page_size;
copy.mode = 0;
clock_gettime(CLOCK_MONOTONIC, &start);
@@ -198,12 +96,12 @@
return r;
}
- clock_gettime(CLOCK_MONOTONIC, &end);
+ ts_diff = timespec_diff_now(start);
PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid,
- timespec_to_ns(timespec_sub(end, start)));
+ timespec_to_ns(ts_diff));
PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n",
- host_page_size, addr, tid);
+ perf_test_args.host_page_size, addr, tid);
return 0;
}
@@ -223,7 +121,8 @@
int pipefd = uffd_args->pipefd;
useconds_t delay = uffd_args->delay;
int64_t pages = 0;
- struct timespec start, end, ts_diff;
+ struct timespec start;
+ struct timespec ts_diff;
clock_gettime(CLOCK_MONOTONIC, &start);
while (!quit_uffd_thread) {
@@ -292,8 +191,7 @@
pages++;
}
- clock_gettime(CLOCK_MONOTONIC, &end);
- ts_diff = timespec_sub(end, start);
+ ts_diff = timespec_diff_now(start);
PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n",
pages, ts_diff.tv_sec, ts_diff.tv_nsec,
pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
@@ -351,99 +249,54 @@
}
static void run_test(enum vm_guest_mode mode, bool use_uffd,
- useconds_t uffd_delay, int vcpus,
- uint64_t vcpu_memory_bytes)
+ useconds_t uffd_delay)
{
pthread_t *vcpu_threads;
pthread_t *uffd_handler_threads = NULL;
struct uffd_handler_args *uffd_args = NULL;
- struct timespec start, end, ts_diff;
+ struct timespec start;
+ struct timespec ts_diff;
int *pipefds = NULL;
struct kvm_vm *vm;
- uint64_t guest_num_pages;
int vcpu_id;
int r;
- vm = create_vm(mode, vcpus, vcpu_memory_bytes);
+ vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size);
- guest_page_size = vm_get_page_size(vm);
+ perf_test_args.wr_fract = 1;
- TEST_ASSERT(vcpu_memory_bytes % guest_page_size == 0,
- "Guest memory size is not guest page size aligned.");
-
- guest_num_pages = (vcpus * vcpu_memory_bytes) / guest_page_size;
- guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
-
- /*
- * If there should be more memory in the guest test region than there
- * can be pages in the guest, it will definitely cause problems.
- */
- TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
- "Requested more guest memory than address space allows.\n"
- " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
- guest_num_pages, vm_get_max_gfn(vm), vcpus,
- vcpu_memory_bytes);
-
- host_page_size = getpagesize();
- TEST_ASSERT(vcpu_memory_bytes % host_page_size == 0,
- "Guest memory size is not host page size aligned.");
-
- guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
- guest_page_size;
- guest_test_phys_mem &= ~(host_page_size - 1);
-
-#ifdef __s390x__
- /* Align to 1M (segment size) */
- guest_test_phys_mem &= ~((1 << 20) - 1);
-#endif
-
- pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
-
- /* Add an extra memory slot for testing demand paging */
- vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
- guest_test_phys_mem,
- TEST_MEM_SLOT_INDEX,
- guest_num_pages, 0);
-
- /* Do mapping for the demand paging memory slot */
- virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
-
- ucall_init(vm, NULL);
-
- guest_data_prototype = malloc(host_page_size);
+ guest_data_prototype = malloc(perf_test_args.host_page_size);
TEST_ASSERT(guest_data_prototype,
"Failed to allocate buffer for guest data pattern");
- memset(guest_data_prototype, 0xAB, host_page_size);
+ memset(guest_data_prototype, 0xAB, perf_test_args.host_page_size);
- vcpu_threads = malloc(vcpus * sizeof(*vcpu_threads));
+ vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
TEST_ASSERT(vcpu_threads, "Memory allocation failed");
+ add_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
+
if (use_uffd) {
uffd_handler_threads =
- malloc(vcpus * sizeof(*uffd_handler_threads));
+ malloc(nr_vcpus * sizeof(*uffd_handler_threads));
TEST_ASSERT(uffd_handler_threads, "Memory allocation failed");
- uffd_args = malloc(vcpus * sizeof(*uffd_args));
+ uffd_args = malloc(nr_vcpus * sizeof(*uffd_args));
TEST_ASSERT(uffd_args, "Memory allocation failed");
- pipefds = malloc(sizeof(int) * vcpus * 2);
+ pipefds = malloc(sizeof(int) * nr_vcpus * 2);
TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd");
- }
- for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
- vm_paddr_t vcpu_gpa;
- void *vcpu_hva;
+ for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+ vm_paddr_t vcpu_gpa;
+ void *vcpu_hva;
- vm_vcpu_add_default(vm, vcpu_id, guest_code);
+ vcpu_gpa = guest_test_phys_mem + (vcpu_id * guest_percpu_mem_size);
+ PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+ vcpu_id, vcpu_gpa, vcpu_gpa + guest_percpu_mem_size);
- vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes);
- PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
- vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes);
+ /* Cache the HVA pointer of the region */
+ vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
- /* Cache the HVA pointer of the region */
- vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
-
- if (use_uffd) {
/*
* Set up user fault fd to handle demand paging
* requests.
@@ -456,53 +309,41 @@
&uffd_handler_threads[vcpu_id],
pipefds[vcpu_id * 2],
uffd_delay, &uffd_args[vcpu_id],
- vcpu_hva, vcpu_memory_bytes);
+ vcpu_hva, guest_percpu_mem_size);
if (r < 0)
exit(-r);
}
-
-#ifdef __x86_64__
- vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid());
-#endif
-
- vcpu_args[vcpu_id].vm = vm;
- vcpu_args[vcpu_id].vcpu_id = vcpu_id;
- vcpu_args[vcpu_id].gva = guest_test_virt_mem +
- (vcpu_id * vcpu_memory_bytes);
- vcpu_args[vcpu_id].pages = vcpu_memory_bytes / guest_page_size;
}
/* Export the shared variables to the guest */
- sync_global_to_guest(vm, host_page_size);
- sync_global_to_guest(vm, guest_page_size);
- sync_global_to_guest(vm, vcpu_args);
+ sync_global_to_guest(vm, perf_test_args);
pr_info("Finished creating vCPUs and starting uffd threads\n");
clock_gettime(CLOCK_MONOTONIC, &start);
- for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+ for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
- &vcpu_args[vcpu_id]);
+ &perf_test_args.vcpu_args[vcpu_id]);
}
pr_info("Started all vCPUs\n");
/* Wait for the vcpu threads to quit */
- for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+ for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
pthread_join(vcpu_threads[vcpu_id], NULL);
PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id);
}
- pr_info("All vCPU threads joined\n");
+ ts_diff = timespec_diff_now(start);
- clock_gettime(CLOCK_MONOTONIC, &end);
+ pr_info("All vCPU threads joined\n");
if (use_uffd) {
char c;
/* Tell the user fault fd handler threads to quit */
- for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+ for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
r = write(pipefds[vcpu_id * 2 + 1], &c, 1);
TEST_ASSERT(r == 1, "Unable to write to pipefd");
@@ -510,11 +351,11 @@
}
}
- ts_diff = timespec_sub(end, start);
pr_info("Total guest execution time: %ld.%.9lds\n",
ts_diff.tv_sec, ts_diff.tv_nsec);
pr_info("Overall demand paging rate: %f pgs/sec\n",
- guest_num_pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
+ perf_test_args.vcpu_args[0].pages * nr_vcpus /
+ ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
ucall_uninit(vm);
kvm_vm_free(vm);
@@ -568,9 +409,8 @@
int main(int argc, char *argv[])
{
+ int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
bool mode_selected = false;
- uint64_t vcpu_memory_bytes = DEFAULT_GUEST_TEST_MEM_SIZE;
- int vcpus = 1;
unsigned int mode;
int opt, i;
bool use_uffd = false;
@@ -619,15 +459,12 @@
"A negative UFFD delay is not supported.");
break;
case 'b':
- vcpu_memory_bytes = parse_size(optarg);
+ guest_percpu_mem_size = parse_size(optarg);
break;
case 'v':
- vcpus = atoi(optarg);
- TEST_ASSERT(vcpus > 0,
- "Must have a positive number of vCPUs");
- TEST_ASSERT(vcpus <= MAX_VCPUS,
- "This test does not currently support\n"
- "more than %d vCPUs.", MAX_VCPUS);
+ nr_vcpus = atoi(optarg);
+ TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus,
+ "Invalid number of vcpus, must be between 1 and %d", max_vcpus);
break;
case 'h':
default:
@@ -642,7 +479,7 @@
TEST_ASSERT(guest_modes[i].supported,
"Guest mode ID %d (%s) not supported.",
i, vm_guest_mode_string(i));
- run_test(i, use_uffd, uffd_delay, vcpus, vcpu_memory_bytes);
+ run_test(i, use_uffd, uffd_delay);
}
return 0;
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
new file mode 100644
index 0000000..85c9b8f
--- /dev/null
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -0,0 +1,376 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM dirty page logging performance test
+ *
+ * Based on dirty_log_test.c
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ * Copyright (C) 2020, Google, Inc.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <time.h>
+#include <pthread.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+
+#include "kvm_util.h"
+#include "perf_test_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+/* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/
+#define TEST_HOST_LOOP_N 2UL
+
+/* Host variables */
+static bool host_quit;
+static uint64_t iteration;
+static uint64_t vcpu_last_completed_iteration[MAX_VCPUS];
+
+static void *vcpu_worker(void *data)
+{
+ int ret;
+ struct kvm_vm *vm = perf_test_args.vm;
+ uint64_t pages_count = 0;
+ struct kvm_run *run;
+ struct timespec start;
+ struct timespec ts_diff;
+ struct timespec total = (struct timespec){0};
+ struct timespec avg;
+ struct vcpu_args *vcpu_args = (struct vcpu_args *)data;
+ int vcpu_id = vcpu_args->vcpu_id;
+
+ vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+ run = vcpu_state(vm, vcpu_id);
+
+ while (!READ_ONCE(host_quit)) {
+ uint64_t current_iteration = READ_ONCE(iteration);
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ ret = _vcpu_run(vm, vcpu_id);
+ ts_diff = timespec_diff_now(start);
+
+ TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+ TEST_ASSERT(get_ucall(vm, vcpu_id, NULL) == UCALL_SYNC,
+ "Invalid guest sync status: exit_reason=%s\n",
+ exit_reason_str(run->exit_reason));
+
+ pr_debug("Got sync event from vCPU %d\n", vcpu_id);
+ vcpu_last_completed_iteration[vcpu_id] = current_iteration;
+ pr_debug("vCPU %d updated last completed iteration to %lu\n",
+ vcpu_id, vcpu_last_completed_iteration[vcpu_id]);
+
+ if (current_iteration) {
+ pages_count += vcpu_args->pages;
+ total = timespec_add(total, ts_diff);
+ pr_debug("vCPU %d iteration %lu dirty memory time: %ld.%.9lds\n",
+ vcpu_id, current_iteration, ts_diff.tv_sec,
+ ts_diff.tv_nsec);
+ } else {
+ pr_debug("vCPU %d iteration %lu populate memory time: %ld.%.9lds\n",
+ vcpu_id, current_iteration, ts_diff.tv_sec,
+ ts_diff.tv_nsec);
+ }
+
+ while (current_iteration == READ_ONCE(iteration) &&
+ !READ_ONCE(host_quit)) {}
+ }
+
+ avg = timespec_div(total, vcpu_last_completed_iteration[vcpu_id]);
+ pr_debug("\nvCPU %d dirtied 0x%lx pages over %lu iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
+ vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id],
+ total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec);
+
+ return NULL;
+}
+
+#ifdef USE_CLEAR_DIRTY_LOG
+static u64 dirty_log_manual_caps;
+#endif
+
+static void run_test(enum vm_guest_mode mode, unsigned long iterations,
+ uint64_t phys_offset, int wr_fract)
+{
+ pthread_t *vcpu_threads;
+ struct kvm_vm *vm;
+ unsigned long *bmap;
+ uint64_t guest_num_pages;
+ uint64_t host_num_pages;
+ int vcpu_id;
+ struct timespec start;
+ struct timespec ts_diff;
+ struct timespec get_dirty_log_total = (struct timespec){0};
+ struct timespec vcpu_dirty_total = (struct timespec){0};
+ struct timespec avg;
+#ifdef USE_CLEAR_DIRTY_LOG
+ struct kvm_enable_cap cap = {};
+ struct timespec clear_dirty_log_total = (struct timespec){0};
+#endif
+
+ vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size);
+
+ perf_test_args.wr_fract = wr_fract;
+
+ guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm);
+ guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
+ host_num_pages = vm_num_host_pages(mode, guest_num_pages);
+ bmap = bitmap_alloc(host_num_pages);
+
+#ifdef USE_CLEAR_DIRTY_LOG
+ cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
+ cap.args[0] = dirty_log_manual_caps;
+ vm_enable_cap(vm, &cap);
+#endif
+
+ vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
+ TEST_ASSERT(vcpu_threads, "Memory allocation failed");
+
+ add_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
+
+ sync_global_to_guest(vm, perf_test_args);
+
+ /* Start the iterations */
+ iteration = 0;
+ host_quit = false;
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+ pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
+ &perf_test_args.vcpu_args[vcpu_id]);
+ }
+
+ /* Allow the vCPU to populate memory */
+ pr_debug("Starting iteration %lu - Populating\n", iteration);
+ while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration)
+ pr_debug("Waiting for vcpu_last_completed_iteration == %lu\n",
+ iteration);
+
+ ts_diff = timespec_diff_now(start);
+ pr_info("Populate memory time: %ld.%.9lds\n",
+ ts_diff.tv_sec, ts_diff.tv_nsec);
+
+ /* Enable dirty logging */
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX,
+ KVM_MEM_LOG_DIRTY_PAGES);
+ ts_diff = timespec_diff_now(start);
+ pr_info("Enabling dirty logging time: %ld.%.9lds\n\n",
+ ts_diff.tv_sec, ts_diff.tv_nsec);
+
+ while (iteration < iterations) {
+ /*
+ * Incrementing the iteration number will start the vCPUs
+ * dirtying memory again.
+ */
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ iteration++;
+
+ pr_debug("Starting iteration %lu\n", iteration);
+ for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+ while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration)
+ pr_debug("Waiting for vCPU %d vcpu_last_completed_iteration == %lu\n",
+ vcpu_id, iteration);
+ }
+
+ ts_diff = timespec_diff_now(start);
+ vcpu_dirty_total = timespec_add(vcpu_dirty_total, ts_diff);
+ pr_info("Iteration %lu dirty memory time: %ld.%.9lds\n",
+ iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
+
+ ts_diff = timespec_diff_now(start);
+ get_dirty_log_total = timespec_add(get_dirty_log_total,
+ ts_diff);
+ pr_info("Iteration %lu get dirty log time: %ld.%.9lds\n",
+ iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
+
+#ifdef USE_CLEAR_DIRTY_LOG
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
+ host_num_pages);
+
+ ts_diff = timespec_diff_now(start);
+ clear_dirty_log_total = timespec_add(clear_dirty_log_total,
+ ts_diff);
+ pr_info("Iteration %lu clear dirty log time: %ld.%.9lds\n",
+ iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
+#endif
+ }
+
+ /* Tell the vcpu thread to quit */
+ host_quit = true;
+ for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
+ pthread_join(vcpu_threads[vcpu_id], NULL);
+
+ /* Disable dirty logging */
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, 0);
+ ts_diff = timespec_diff_now(start);
+ pr_info("Disabling dirty logging time: %ld.%.9lds\n",
+ ts_diff.tv_sec, ts_diff.tv_nsec);
+
+ avg = timespec_div(get_dirty_log_total, iterations);
+ pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
+ iterations, get_dirty_log_total.tv_sec,
+ get_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
+
+#ifdef USE_CLEAR_DIRTY_LOG
+ avg = timespec_div(clear_dirty_log_total, iterations);
+ pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
+ iterations, clear_dirty_log_total.tv_sec,
+ clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
+#endif
+
+ free(bmap);
+ free(vcpu_threads);
+ ucall_uninit(vm);
+ kvm_vm_free(vm);
+}
+
+struct guest_mode {
+ bool supported;
+ bool enabled;
+};
+static struct guest_mode guest_modes[NUM_VM_MODES];
+
+#define guest_mode_init(mode, supported, enabled) ({ \
+ guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
+})
+
+static void help(char *name)
+{
+ int i;
+
+ puts("");
+ printf("usage: %s [-h] [-i iterations] [-p offset] "
+ "[-m mode] [-b vcpu bytes] [-v vcpus]\n", name);
+ puts("");
+ printf(" -i: specify iteration counts (default: %"PRIu64")\n",
+ TEST_HOST_LOOP_N);
+ printf(" -p: specify guest physical test memory offset\n"
+ " Warning: a low offset can conflict with the loaded test code.\n");
+ printf(" -m: specify the guest mode ID to test "
+ "(default: test all supported modes)\n"
+ " This option may be used multiple times.\n"
+ " Guest mode IDs:\n");
+ for (i = 0; i < NUM_VM_MODES; ++i) {
+ printf(" %d: %s%s\n", i, vm_guest_mode_string(i),
+ guest_modes[i].supported ? " (supported)" : "");
+ }
+ printf(" -b: specify the size of the memory region which should be\n"
+ " dirtied by each vCPU. e.g. 10M or 3G.\n"
+ " (default: 1G)\n");
+ printf(" -f: specify the fraction of pages which should be written to\n"
+ " as opposed to simply read, in the form\n"
+ " 1/<fraction of pages to write>.\n"
+ " (default: 1 i.e. all pages are written to.)\n");
+ printf(" -v: specify the number of vCPUs to run.\n");
+ puts("");
+ exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+ unsigned long iterations = TEST_HOST_LOOP_N;
+ bool mode_selected = false;
+ uint64_t phys_offset = 0;
+ unsigned int mode;
+ int opt, i;
+ int wr_fract = 1;
+
+#ifdef USE_CLEAR_DIRTY_LOG
+ dirty_log_manual_caps =
+ kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+ if (!dirty_log_manual_caps) {
+ print_skip("KVM_CLEAR_DIRTY_LOG not available");
+ exit(KSFT_SKIP);
+ }
+ dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
+ KVM_DIRTY_LOG_INITIALLY_SET);
+#endif
+
+#ifdef __x86_64__
+ guest_mode_init(VM_MODE_PXXV48_4K, true, true);
+#endif
+#ifdef __aarch64__
+ guest_mode_init(VM_MODE_P40V48_4K, true, true);
+ guest_mode_init(VM_MODE_P40V48_64K, true, true);
+
+ {
+ unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+
+ if (limit >= 52)
+ guest_mode_init(VM_MODE_P52V48_64K, true, true);
+ if (limit >= 48) {
+ guest_mode_init(VM_MODE_P48V48_4K, true, true);
+ guest_mode_init(VM_MODE_P48V48_64K, true, true);
+ }
+ }
+#endif
+#ifdef __s390x__
+ guest_mode_init(VM_MODE_P40V48_4K, true, true);
+#endif
+
+ while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:")) != -1) {
+ switch (opt) {
+ case 'i':
+ iterations = strtol(optarg, NULL, 10);
+ break;
+ case 'p':
+ phys_offset = strtoull(optarg, NULL, 0);
+ break;
+ case 'm':
+ if (!mode_selected) {
+ for (i = 0; i < NUM_VM_MODES; ++i)
+ guest_modes[i].enabled = false;
+ mode_selected = true;
+ }
+ mode = strtoul(optarg, NULL, 10);
+ TEST_ASSERT(mode < NUM_VM_MODES,
+ "Guest mode ID %d too big", mode);
+ guest_modes[mode].enabled = true;
+ break;
+ case 'b':
+ guest_percpu_mem_size = parse_size(optarg);
+ break;
+ case 'f':
+ wr_fract = atoi(optarg);
+ TEST_ASSERT(wr_fract >= 1,
+ "Write fraction cannot be less than one");
+ break;
+ case 'v':
+ nr_vcpus = atoi(optarg);
+ TEST_ASSERT(nr_vcpus > 0,
+ "Must have a positive number of vCPUs");
+ TEST_ASSERT(nr_vcpus <= MAX_VCPUS,
+ "This test does not currently support\n"
+ "more than %d vCPUs.", MAX_VCPUS);
+ break;
+ case 'h':
+ default:
+ help(argv[0]);
+ break;
+ }
+ }
+
+ TEST_ASSERT(iterations >= 2, "The test should have at least two iterations");
+
+ pr_info("Test iterations: %"PRIu64"\n", iterations);
+
+ for (i = 0; i < NUM_VM_MODES; ++i) {
+ if (!guest_modes[i].enabled)
+ continue;
+ TEST_ASSERT(guest_modes[i].supported,
+ "Guest mode ID %d (%s) not supported.",
+ i, vm_guest_mode_string(i));
+ run_test(i, iterations, phys_offset, wr_fract);
+ }
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 752ec15..54da9cc2 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -128,6 +128,78 @@
static uint64_t host_clear_count;
static uint64_t host_track_next_count;
+enum log_mode_t {
+ /* Only use KVM_GET_DIRTY_LOG for logging */
+ LOG_MODE_DIRTY_LOG = 0,
+
+ /* Use both KVM_[GET|CLEAR]_DIRTY_LOG for logging */
+ LOG_MODE_CLEAR_LOG = 1,
+
+ LOG_MODE_NUM,
+
+ /* Run all supported modes */
+ LOG_MODE_ALL = LOG_MODE_NUM,
+};
+
+/* Mode of logging to test. Default is to run all supported modes */
+static enum log_mode_t host_log_mode_option = LOG_MODE_ALL;
+/* Logging mode for current run */
+static enum log_mode_t host_log_mode;
+
+static bool clear_log_supported(void)
+{
+ return kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+}
+
+static void clear_log_create_vm_done(struct kvm_vm *vm)
+{
+ struct kvm_enable_cap cap = {};
+ u64 manual_caps;
+
+ manual_caps = kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+ TEST_ASSERT(manual_caps, "MANUAL_CAPS is zero!");
+ manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
+ KVM_DIRTY_LOG_INITIALLY_SET);
+ cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
+ cap.args[0] = manual_caps;
+ vm_enable_cap(vm, &cap);
+}
+
+static void dirty_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
+ void *bitmap, uint32_t num_pages)
+{
+ kvm_vm_get_dirty_log(vm, slot, bitmap);
+}
+
+static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
+ void *bitmap, uint32_t num_pages)
+{
+ kvm_vm_get_dirty_log(vm, slot, bitmap);
+ kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages);
+}
+
+struct log_mode {
+ const char *name;
+ /* Return true if this mode is supported, otherwise false */
+ bool (*supported)(void);
+ /* Hook when the vm creation is done (before vcpu creation) */
+ void (*create_vm_done)(struct kvm_vm *vm);
+ /* Hook to collect the dirty pages into the bitmap provided */
+ void (*collect_dirty_pages) (struct kvm_vm *vm, int slot,
+ void *bitmap, uint32_t num_pages);
+} log_modes[LOG_MODE_NUM] = {
+ {
+ .name = "dirty-log",
+ .collect_dirty_pages = dirty_log_collect_dirty_pages,
+ },
+ {
+ .name = "clear-log",
+ .supported = clear_log_supported,
+ .create_vm_done = clear_log_create_vm_done,
+ .collect_dirty_pages = clear_log_collect_dirty_pages,
+ },
+};
+
/*
* We use this bitmap to track some pages that should have its dirty
* bit set in the _next_ iteration. For example, if we detected the
@@ -137,6 +209,44 @@
*/
static unsigned long *host_bmap_track;
+static void log_modes_dump(void)
+{
+ int i;
+
+ printf("all");
+ for (i = 0; i < LOG_MODE_NUM; i++)
+ printf(", %s", log_modes[i].name);
+ printf("\n");
+}
+
+static bool log_mode_supported(void)
+{
+ struct log_mode *mode = &log_modes[host_log_mode];
+
+ if (mode->supported)
+ return mode->supported();
+
+ return true;
+}
+
+static void log_mode_create_vm_done(struct kvm_vm *vm)
+{
+ struct log_mode *mode = &log_modes[host_log_mode];
+
+ if (mode->create_vm_done)
+ mode->create_vm_done(vm);
+}
+
+static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot,
+ void *bitmap, uint32_t num_pages)
+{
+ struct log_mode *mode = &log_modes[host_log_mode];
+
+ TEST_ASSERT(mode->collect_dirty_pages != NULL,
+ "collect_dirty_pages() is required for any log mode!");
+ mode->collect_dirty_pages(vm, slot, bitmap, num_pages);
+}
+
static void generate_random_array(uint64_t *guest_array, uint64_t size)
{
uint64_t i;
@@ -195,7 +305,7 @@
page);
}
- if (test_bit_le(page, bmap)) {
+ if (test_and_clear_bit_le(page, bmap)) {
host_dirty_count++;
/*
* If the bit is set, the value written onto
@@ -252,11 +362,12 @@
pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
- vm = _vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+ vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
#ifdef __x86_64__
vm_create_irqchip(vm);
#endif
+ log_mode_create_vm_done(vm);
vm_vcpu_add_default(vm, vcpuid, guest_code);
return vm;
}
@@ -264,10 +375,6 @@
#define DIRTY_MEM_BITS 30 /* 1G */
#define PAGE_SHIFT_4K 12
-#ifdef USE_CLEAR_DIRTY_LOG
-static u64 dirty_log_manual_caps;
-#endif
-
static void run_test(enum vm_guest_mode mode, unsigned long iterations,
unsigned long interval, uint64_t phys_offset)
{
@@ -275,6 +382,12 @@
struct kvm_vm *vm;
unsigned long *bmap;
+ if (!log_mode_supported()) {
+ print_skip("Log mode '%s' not supported",
+ log_modes[host_log_mode].name);
+ return;
+ }
+
/*
* We reserve page table for 2 times of extra dirty mem which
* will definitely cover the original (1G+) test range. Here
@@ -317,14 +430,6 @@
bmap = bitmap_alloc(host_num_pages);
host_bmap_track = bitmap_alloc(host_num_pages);
-#ifdef USE_CLEAR_DIRTY_LOG
- struct kvm_enable_cap cap = {};
-
- cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
- cap.args[0] = dirty_log_manual_caps;
- vm_enable_cap(vm, &cap);
-#endif
-
/* Add an extra memory slot for testing dirty logging */
vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
guest_test_phys_mem,
@@ -362,11 +467,8 @@
while (iteration < iterations) {
/* Give the vcpu thread some time to dirty some pages */
usleep(interval * 1000);
- kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
-#ifdef USE_CLEAR_DIRTY_LOG
- kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
- host_num_pages);
-#endif
+ log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX,
+ bmap, host_num_pages);
vm_dirty_log_verify(mode, bmap);
iteration++;
sync_global_to_guest(vm, iteration);
@@ -410,6 +512,9 @@
TEST_HOST_LOOP_INTERVAL);
printf(" -p: specify guest physical test memory offset\n"
" Warning: a low offset can conflict with the loaded test code.\n");
+ printf(" -M: specify the host logging mode "
+ "(default: run all log modes). Supported modes: \n\t");
+ log_modes_dump();
printf(" -m: specify the guest mode ID to test "
"(default: test all supported modes)\n"
" This option may be used multiple times.\n"
@@ -429,18 +534,7 @@
bool mode_selected = false;
uint64_t phys_offset = 0;
unsigned int mode;
- int opt, i;
-
-#ifdef USE_CLEAR_DIRTY_LOG
- dirty_log_manual_caps =
- kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
- if (!dirty_log_manual_caps) {
- print_skip("KVM_CLEAR_DIRTY_LOG not available");
- exit(KSFT_SKIP);
- }
- dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
- KVM_DIRTY_LOG_INITIALLY_SET);
-#endif
+ int opt, i, j;
#ifdef __x86_64__
guest_mode_init(VM_MODE_PXXV48_4K, true, true);
@@ -464,7 +558,7 @@
guest_mode_init(VM_MODE_P40V48_4K, true, true);
#endif
- while ((opt = getopt(argc, argv, "hi:I:p:m:")) != -1) {
+ while ((opt = getopt(argc, argv, "hi:I:p:m:M:")) != -1) {
switch (opt) {
case 'i':
iterations = strtol(optarg, NULL, 10);
@@ -486,6 +580,26 @@
"Guest mode ID %d too big", mode);
guest_modes[mode].enabled = true;
break;
+ case 'M':
+ if (!strcmp(optarg, "all")) {
+ host_log_mode_option = LOG_MODE_ALL;
+ break;
+ }
+ for (i = 0; i < LOG_MODE_NUM; i++) {
+ if (!strcmp(optarg, log_modes[i].name)) {
+ pr_info("Setting log mode to: '%s'\n",
+ optarg);
+ host_log_mode_option = i;
+ break;
+ }
+ }
+ if (i == LOG_MODE_NUM) {
+ printf("Log mode '%s' invalid. Please choose "
+ "from: ", optarg);
+ log_modes_dump();
+ exit(1);
+ }
+ break;
case 'h':
default:
help(argv[0]);
@@ -507,7 +621,18 @@
TEST_ASSERT(guest_modes[i].supported,
"Guest mode ID %d (%s) not supported.",
i, vm_guest_mode_string(i));
- run_test(i, iterations, interval, phys_offset);
+ if (host_log_mode_option == LOG_MODE_ALL) {
+ /* Run each log mode */
+ for (j = 0; j < LOG_MODE_NUM; j++) {
+ pr_info("Testing Log Mode '%s'\n",
+ log_modes[j].name);
+ host_log_mode = j;
+ run_test(i, iterations, interval, phys_offset);
+ }
+ } else {
+ host_log_mode = host_log_mode_option;
+ run_test(i, iterations, interval, phys_offset);
+ }
}
return 0;
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 919e161..7d29aa7 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -63,9 +63,11 @@
int kvm_check_cap(long cap);
int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap);
+int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
+ struct kvm_enable_cap *cap);
+void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size);
struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
-struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
void kvm_vm_free(struct kvm_vm *vmp);
void kvm_vm_restart(struct kvm_vm *vmp, int perm);
void kvm_vm_release(struct kvm_vm *vmp);
@@ -149,6 +151,7 @@
struct kvm_guest_debug *debug);
void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
struct kvm_mp_state *mp_state);
+struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid);
void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
@@ -294,6 +297,8 @@
memcpy(&(g), _p, sizeof(g)); \
})
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid);
+
/* Common ucalls */
enum {
UCALL_NONE,
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
new file mode 100644
index 0000000..2618052
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -0,0 +1,198 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * tools/testing/selftests/kvm/include/perf_test_util.h
+ *
+ * Copyright (C) 2020, Google LLC.
+ */
+
+#ifndef SELFTEST_KVM_PERF_TEST_UTIL_H
+#define SELFTEST_KVM_PERF_TEST_UTIL_H
+
+#include "kvm_util.h"
+#include "processor.h"
+
+#define MAX_VCPUS 512
+
+#define PAGE_SHIFT_4K 12
+#define PTES_PER_4K_PT 512
+
+#define TEST_MEM_SLOT_INDEX 1
+
+/* Default guest test virtual memory offset */
+#define DEFAULT_GUEST_TEST_MEM 0xc0000000
+
+#define DEFAULT_PER_VCPU_MEM_SIZE (1 << 30) /* 1G */
+
+/*
+ * Guest physical memory offset of the testing memory slot.
+ * This will be set to the topmost valid physical address minus
+ * the test memory size.
+ */
+static uint64_t guest_test_phys_mem;
+
+/*
+ * Guest virtual memory offset of the testing memory slot.
+ * Must not conflict with identity mapped test code.
+ */
+static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
+static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
+
+/* Number of VCPUs for the test */
+static int nr_vcpus = 1;
+
+struct vcpu_args {
+ uint64_t gva;
+ uint64_t pages;
+
+ /* Only used by the host userspace part of the vCPU thread */
+ int vcpu_id;
+};
+
+struct perf_test_args {
+ struct kvm_vm *vm;
+ uint64_t host_page_size;
+ uint64_t guest_page_size;
+ int wr_fract;
+
+ struct vcpu_args vcpu_args[MAX_VCPUS];
+};
+
+static struct perf_test_args perf_test_args;
+
+/*
+ * Continuously write to the first 8 bytes of each page in the
+ * specified region.
+ */
+static void guest_code(uint32_t vcpu_id)
+{
+ struct vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+ uint64_t gva;
+ uint64_t pages;
+ int i;
+
+ /* Make sure vCPU args data structure is not corrupt. */
+ GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id);
+
+ gva = vcpu_args->gva;
+ pages = vcpu_args->pages;
+
+ while (true) {
+ for (i = 0; i < pages; i++) {
+ uint64_t addr = gva + (i * perf_test_args.guest_page_size);
+
+ if (i % perf_test_args.wr_fract == 0)
+ *(uint64_t *)addr = 0x0123456789ABCDEF;
+ else
+ READ_ONCE(*(uint64_t *)addr);
+ }
+
+ GUEST_SYNC(1);
+ }
+}
+
+static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus,
+ uint64_t vcpu_memory_bytes)
+{
+ struct kvm_vm *vm;
+ uint64_t pages = DEFAULT_GUEST_PHY_PAGES;
+ uint64_t guest_num_pages;
+
+ /* Account for a few pages per-vCPU for stacks */
+ pages += DEFAULT_STACK_PGS * vcpus;
+
+ /*
+ * Reserve twice the ammount of memory needed to map the test region and
+ * the page table / stacks region, at 4k, for page tables. Do the
+ * calculation with 4K page size: the smallest of all archs. (e.g., 64K
+ * page size guest will need even less memory for page tables).
+ */
+ pages += (2 * pages) / PTES_PER_4K_PT;
+ pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) /
+ PTES_PER_4K_PT;
+ pages = vm_adjust_num_guest_pages(mode, pages);
+
+ pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
+
+ vm = vm_create(mode, pages, O_RDWR);
+ kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+#ifdef __x86_64__
+ vm_create_irqchip(vm);
+#endif
+
+ perf_test_args.vm = vm;
+ perf_test_args.guest_page_size = vm_get_page_size(vm);
+ perf_test_args.host_page_size = getpagesize();
+
+ TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
+ "Guest memory size is not guest page size aligned.");
+
+ guest_num_pages = (vcpus * vcpu_memory_bytes) /
+ perf_test_args.guest_page_size;
+ guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
+
+ /*
+ * If there should be more memory in the guest test region than there
+ * can be pages in the guest, it will definitely cause problems.
+ */
+ TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
+ "Requested more guest memory than address space allows.\n"
+ " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
+ guest_num_pages, vm_get_max_gfn(vm), vcpus,
+ vcpu_memory_bytes);
+
+ TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0,
+ "Guest memory size is not host page size aligned.");
+
+ guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
+ perf_test_args.guest_page_size;
+ guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1);
+
+#ifdef __s390x__
+ /* Align to 1M (segment size) */
+ guest_test_phys_mem &= ~((1 << 20) - 1);
+#endif
+
+ pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+
+ /* Add an extra memory slot for testing */
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+ guest_test_phys_mem,
+ TEST_MEM_SLOT_INDEX,
+ guest_num_pages, 0);
+
+ /* Do mapping for the demand paging memory slot */
+ virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
+
+ ucall_init(vm, NULL);
+
+ return vm;
+}
+
+static void add_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes)
+{
+ vm_paddr_t vcpu_gpa;
+ struct vcpu_args *vcpu_args;
+ int vcpu_id;
+
+ for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+ vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+
+ vm_vcpu_add_default(vm, vcpu_id, guest_code);
+
+#ifdef __x86_64__
+ vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid());
+#endif
+
+ vcpu_args->vcpu_id = vcpu_id;
+ vcpu_args->gva = guest_test_virt_mem +
+ (vcpu_id * vcpu_memory_bytes);
+ vcpu_args->pages = vcpu_memory_bytes /
+ perf_test_args.guest_page_size;
+
+ vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes);
+ pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+ vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes);
+ }
+}
+
+#endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 5eb01bf..ffffa56 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -64,5 +64,7 @@
struct timespec timespec_add_ns(struct timespec ts, int64_t ns);
struct timespec timespec_add(struct timespec ts1, struct timespec ts2);
struct timespec timespec_sub(struct timespec ts1, struct timespec ts2);
+struct timespec timespec_diff_now(struct timespec start);
+struct timespec timespec_div(struct timespec ts, int divisor);
#endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 82b7fe1..8e61340 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -36,6 +36,8 @@
#define X86_CR4_SMAP (1ul << 21)
#define X86_CR4_PKE (1ul << 22)
+#define UNEXPECTED_VECTOR_PORT 0xfff0u
+
/* General Registers in 64-Bit Mode */
struct gpr64_regs {
u64 rax;
@@ -59,7 +61,7 @@
struct desc64 {
uint16_t limit0;
uint16_t base0;
- unsigned base1:8, s:1, type:4, dpl:2, p:1;
+ unsigned base1:8, type:4, s:1, dpl:2, p:1;
unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8;
uint32_t base3;
uint32_t zero1;
@@ -239,6 +241,11 @@
return idt;
}
+static inline void outl(uint16_t port, uint32_t value)
+{
+ __asm__ __volatile__("outl %%eax, %%dx" : : "d"(port), "a"(value));
+}
+
#define SET_XMM(__var, __xmm) \
asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm)
@@ -338,6 +345,35 @@
uint32_t kvm_get_cpuid_max_extended(void);
void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits);
+struct ex_regs {
+ uint64_t rax, rcx, rdx, rbx;
+ uint64_t rbp, rsi, rdi;
+ uint64_t r8, r9, r10, r11;
+ uint64_t r12, r13, r14, r15;
+ uint64_t vector;
+ uint64_t error_code;
+ uint64_t rip;
+ uint64_t cs;
+ uint64_t rflags;
+};
+
+void vm_init_descriptor_tables(struct kvm_vm *vm);
+void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid);
+void vm_handle_exception(struct kvm_vm *vm, int vector,
+ void (*handler)(struct ex_regs *));
+
+/*
+ * set_cpuid() - overwrites a matching cpuid entry with the provided value.
+ * matches based on ent->function && ent->index. returns true
+ * if a match was found and successfully overwritten.
+ * @cpuid: the kvm cpuid list to modify.
+ * @ent: cpuid entry to insert
+ */
+bool set_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 *ent);
+
+uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
+ uint64_t a3);
+
/*
* Basic CPU control in CR0
*/
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 54d624d..e78d7e2 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -573,6 +573,10 @@
void *eptp_hva;
uint64_t eptp_gpa;
void *eptp;
+
+ void *apic_access_hva;
+ uint64_t apic_access_gpa;
+ void *apic_access;
};
union vmx_basic {
@@ -615,5 +619,7 @@
uint32_t memslot, uint32_t eptp_memslot);
void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
uint32_t eptp_memslot);
+void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint32_t eptp_memslot);
#endif /* SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 2afa661..d6c32c3 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -350,3 +350,7 @@
va_end(ap);
}
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
index c8e0ec2..2f37b90 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
@@ -94,6 +94,9 @@
struct kvm_run *run = vcpu_state(vm, vcpu_id);
struct ucall ucall = {};
+ if (uc)
+ memset(uc, 0, sizeof(*uc));
+
if (run->exit_reason == KVM_EXIT_MMIO &&
run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) {
vm_vaddr_t gva;
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 74776ee..126c672 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -14,6 +14,7 @@
#include <sys/mman.h>
#include <sys/types.h>
#include <sys/stat.h>
+#include <unistd.h>
#include <linux/kernel.h>
#define KVM_UTIL_PGS_PER_HUGEPG 512
@@ -85,6 +86,34 @@
return ret;
}
+/* VCPU Enable Capability
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpu_id - VCPU
+ * cap - Capability
+ *
+ * Output Args: None
+ *
+ * Return: On success, 0. On failure a TEST_ASSERT failure is produced.
+ *
+ * Enables a capability (KVM_CAP_*) on the VCPU.
+ */
+int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
+ struct kvm_enable_cap *cap)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpu_id);
+ int r;
+
+ TEST_ASSERT(vcpu, "cannot find vcpu %d", vcpu_id);
+
+ r = ioctl(vcpu->fd, KVM_ENABLE_CAP, cap);
+ TEST_ASSERT(!r, "KVM_ENABLE_CAP vCPU ioctl failed,\n"
+ " rc: %i, errno: %i", r, errno);
+
+ return r;
+}
+
static void vm_open(struct kvm_vm *vm, int perm)
{
vm->kvm_fd = open(KVM_DEV_PATH, perm);
@@ -151,7 +180,7 @@
* descriptor to control the created VM is created with the permissions
* given by perm (e.g. O_RDWR).
*/
-struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
+struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
{
struct kvm_vm *vm;
@@ -242,11 +271,6 @@
return vm;
}
-struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
-{
- return _vm_create(mode, phy_pages, perm);
-}
-
/*
* VM Restart
*
@@ -664,13 +688,21 @@
/* As needed perform madvise */
if (src_type == VM_MEM_SRC_ANONYMOUS || src_type == VM_MEM_SRC_ANONYMOUS_THP) {
- ret = madvise(region->host_mem, npages * vm->page_size,
- src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE);
- TEST_ASSERT(ret == 0, "madvise failed,\n"
- " addr: %p\n"
- " length: 0x%lx\n"
- " src_type: %x",
- region->host_mem, npages * vm->page_size, src_type);
+ struct stat statbuf;
+
+ ret = stat("/sys/kernel/mm/transparent_hugepage", &statbuf);
+ TEST_ASSERT(ret == 0 || (ret == -1 && errno == ENOENT),
+ "stat /sys/kernel/mm/transparent_hugepage");
+
+ TEST_ASSERT(ret == 0 || src_type != VM_MEM_SRC_ANONYMOUS_THP,
+ "VM_MEM_SRC_ANONYMOUS_THP requires THP to be configured in the host kernel");
+
+ if (ret == 0) {
+ ret = madvise(region->host_mem, npages * vm->page_size,
+ src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE);
+ TEST_ASSERT(ret == 0, "madvise failed, addr: %p length: 0x%lx src_type: %x",
+ region->host_mem, npages * vm->page_size, src_type);
+ }
}
region->unused_phy_pages = sparsebit_alloc();
@@ -1195,6 +1227,9 @@
do {
rc = ioctl(vcpu->fd, KVM_RUN, NULL);
} while (rc == -1 && errno == EINTR);
+
+ assert_on_unhandled_exception(vm, vcpuid);
+
return rc;
}
@@ -1252,6 +1287,35 @@
}
/*
+ * VM VCPU Get Reg List
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ *
+ * Output Args:
+ * None
+ *
+ * Return:
+ * A pointer to an allocated struct kvm_reg_list
+ *
+ * Get the list of guest registers which are supported for
+ * KVM_GET_ONE_REG/KVM_SET_ONE_REG calls
+ */
+struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct kvm_reg_list reg_list_n = { .n = 0 }, *reg_list;
+ int ret;
+
+ ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, ®_list_n);
+ TEST_ASSERT(ret == -1 && errno == E2BIG, "KVM_GET_REG_LIST n=0");
+ reg_list = calloc(1, sizeof(*reg_list) + reg_list_n.n * sizeof(__u64));
+ reg_list->n = reg_list_n.n;
+ vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, reg_list);
+ return reg_list;
+}
+
+/*
* VM VCPU Regs Get
*
* Input Args:
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 2ef44652..f07d383 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -50,6 +50,8 @@
vm_paddr_t pgd;
vm_vaddr_t gdt;
vm_vaddr_t tss;
+ vm_vaddr_t idt;
+ vm_vaddr_t handlers;
};
struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid);
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index a88c5d6..7349bb2 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -241,3 +241,7 @@
fprintf(stream, "%*spstate: psw: 0x%.16llx:0x%.16llx\n",
indent, "", vcpu->state->psw_mask, vcpu->state->psw_addr);
}
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+}
diff --git a/tools/testing/selftests/kvm/lib/s390x/ucall.c b/tools/testing/selftests/kvm/lib/s390x/ucall.c
index fd589dc..9d3b0f1 100644
--- a/tools/testing/selftests/kvm/lib/s390x/ucall.c
+++ b/tools/testing/selftests/kvm/lib/s390x/ucall.c
@@ -38,6 +38,9 @@
struct kvm_run *run = vcpu_state(vm, vcpu_id);
struct ucall ucall = {};
+ if (uc)
+ memset(uc, 0, sizeof(*uc));
+
if (run->exit_reason == KVM_EXIT_S390_SIEIC &&
run->s390_sieic.icptcode == 4 &&
(run->s390_sieic.ipa >> 8) == 0x83 && /* 0x83 means DIAGNOSE */
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 689e97c..8e04c0b 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -4,10 +4,13 @@
*
* Copyright (C) 2020, Google LLC.
*/
-#include <stdlib.h>
+
+#include <assert.h>
#include <ctype.h>
#include <limits.h>
-#include <assert.h>
+#include <stdlib.h>
+#include <time.h>
+
#include "test_util.h"
/*
@@ -81,6 +84,21 @@
return timespec_add_ns((struct timespec){0}, ns1 - ns2);
}
+struct timespec timespec_diff_now(struct timespec start)
+{
+ struct timespec end;
+
+ clock_gettime(CLOCK_MONOTONIC, &end);
+ return timespec_sub(end, start);
+}
+
+struct timespec timespec_div(struct timespec ts, int divisor)
+{
+ int64_t ns = timespec_to_ns(ts) / divisor;
+
+ return timespec_add_ns((struct timespec){0}, ns);
+}
+
void print_skip(const char *fmt, ...)
{
va_list ap;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86_64/handlers.S
new file mode 100644
index 0000000..aaf7bc7
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/handlers.S
@@ -0,0 +1,81 @@
+handle_exception:
+ push %r15
+ push %r14
+ push %r13
+ push %r12
+ push %r11
+ push %r10
+ push %r9
+ push %r8
+
+ push %rdi
+ push %rsi
+ push %rbp
+ push %rbx
+ push %rdx
+ push %rcx
+ push %rax
+ mov %rsp, %rdi
+
+ call route_exception
+
+ pop %rax
+ pop %rcx
+ pop %rdx
+ pop %rbx
+ pop %rbp
+ pop %rsi
+ pop %rdi
+ pop %r8
+ pop %r9
+ pop %r10
+ pop %r11
+ pop %r12
+ pop %r13
+ pop %r14
+ pop %r15
+
+ /* Discard vector and error code. */
+ add $16, %rsp
+ iretq
+
+/*
+ * Build the handle_exception wrappers which push the vector/error code on the
+ * stack and an array of pointers to those wrappers.
+ */
+.pushsection .rodata
+.globl idt_handlers
+idt_handlers:
+.popsection
+
+.macro HANDLERS has_error from to
+ vector = \from
+ .rept \to - \from + 1
+ .align 8
+
+ /* Fetch current address and append it to idt_handlers. */
+ current_handler = .
+.pushsection .rodata
+.quad current_handler
+.popsection
+
+ .if ! \has_error
+ pushq $0
+ .endif
+ pushq $vector
+ jmp handle_exception
+ vector = vector + 1
+ .endr
+.endm
+
+.global idt_handler_code
+idt_handler_code:
+ HANDLERS has_error=0 from=0 to=7
+ HANDLERS has_error=1 from=8 to=8
+ HANDLERS has_error=0 from=9 to=9
+ HANDLERS has_error=1 from=10 to=14
+ HANDLERS has_error=0 from=15 to=16
+ HANDLERS has_error=1 from=17 to=17
+ HANDLERS has_error=0 from=18 to=255
+
+.section .note.GNU-stack, "", %progbits
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index f6eb34e..d10c5c0 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -12,9 +12,18 @@
#include "../kvm_util_internal.h"
#include "processor.h"
+#ifndef NUM_INTERRUPTS
+#define NUM_INTERRUPTS 256
+#endif
+
+#define DEFAULT_CODE_SELECTOR 0x8
+#define DEFAULT_DATA_SELECTOR 0x10
+
/* Minimum physical address used for virtual translation tables. */
#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
+vm_vaddr_t exception_handlers;
+
/* Virtual translation table structure declarations */
struct pageMapL4Entry {
uint64_t present:1;
@@ -392,11 +401,12 @@
desc->limit0 = segp->limit & 0xFFFF;
desc->base0 = segp->base & 0xFFFF;
desc->base1 = segp->base >> 16;
- desc->s = segp->s;
desc->type = segp->type;
+ desc->s = segp->s;
desc->dpl = segp->dpl;
desc->p = segp->present;
desc->limit1 = segp->limit >> 16;
+ desc->avl = segp->avl;
desc->l = segp->l;
desc->db = segp->db;
desc->g = segp->g;
@@ -556,9 +566,9 @@
sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
kvm_seg_set_unusable(&sregs.ldt);
- kvm_seg_set_kernel_code_64bit(vm, 0x8, &sregs.cs);
- kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.ds);
- kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.es);
+ kvm_seg_set_kernel_code_64bit(vm, DEFAULT_CODE_SELECTOR, &sregs.cs);
+ kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.ds);
+ kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.es);
kvm_setup_tss_64bit(vm, &sregs.tr, 0x18, gdt_memslot, pgd_memslot);
break;
@@ -1118,3 +1128,131 @@
*va_bits = (entry->eax >> 8) & 0xff;
}
}
+
+struct idt_entry {
+ uint16_t offset0;
+ uint16_t selector;
+ uint16_t ist : 3;
+ uint16_t : 5;
+ uint16_t type : 4;
+ uint16_t : 1;
+ uint16_t dpl : 2;
+ uint16_t p : 1;
+ uint16_t offset1;
+ uint32_t offset2; uint32_t reserved;
+};
+
+static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr,
+ int dpl, unsigned short selector)
+{
+ struct idt_entry *base =
+ (struct idt_entry *)addr_gva2hva(vm, vm->idt);
+ struct idt_entry *e = &base[vector];
+
+ memset(e, 0, sizeof(*e));
+ e->offset0 = addr;
+ e->selector = selector;
+ e->ist = 0;
+ e->type = 14;
+ e->dpl = dpl;
+ e->p = 1;
+ e->offset1 = addr >> 16;
+ e->offset2 = addr >> 32;
+}
+
+void kvm_exit_unexpected_vector(uint32_t value)
+{
+ outl(UNEXPECTED_VECTOR_PORT, value);
+}
+
+void route_exception(struct ex_regs *regs)
+{
+ typedef void(*handler)(struct ex_regs *);
+ handler *handlers = (handler *)exception_handlers;
+
+ if (handlers && handlers[regs->vector]) {
+ handlers[regs->vector](regs);
+ return;
+ }
+
+ kvm_exit_unexpected_vector(regs->vector);
+}
+
+void vm_init_descriptor_tables(struct kvm_vm *vm)
+{
+ extern void *idt_handlers;
+ int i;
+
+ vm->idt = vm_vaddr_alloc(vm, getpagesize(), 0x2000, 0, 0);
+ vm->handlers = vm_vaddr_alloc(vm, 256 * sizeof(void *), 0x2000, 0, 0);
+ /* Handlers have the same address in both address spaces.*/
+ for (i = 0; i < NUM_INTERRUPTS; i++)
+ set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0,
+ DEFAULT_CODE_SELECTOR);
+}
+
+void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct kvm_sregs sregs;
+
+ vcpu_sregs_get(vm, vcpuid, &sregs);
+ sregs.idt.base = vm->idt;
+ sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1;
+ sregs.gdt.base = vm->gdt;
+ sregs.gdt.limit = getpagesize() - 1;
+ kvm_seg_set_kernel_data_64bit(NULL, DEFAULT_DATA_SELECTOR, &sregs.gs);
+ vcpu_sregs_set(vm, vcpuid, &sregs);
+ *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
+}
+
+void vm_handle_exception(struct kvm_vm *vm, int vector,
+ void (*handler)(struct ex_regs *))
+{
+ vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers);
+
+ handlers[vector] = (vm_vaddr_t)handler;
+}
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ if (vcpu_state(vm, vcpuid)->exit_reason == KVM_EXIT_IO
+ && vcpu_state(vm, vcpuid)->io.port == UNEXPECTED_VECTOR_PORT
+ && vcpu_state(vm, vcpuid)->io.size == 4) {
+ /* Grab pointer to io data */
+ uint32_t *data = (void *)vcpu_state(vm, vcpuid)
+ + vcpu_state(vm, vcpuid)->io.data_offset;
+
+ TEST_ASSERT(false,
+ "Unexpected vectored event in guest (vector:0x%x)",
+ *data);
+ }
+}
+
+bool set_cpuid(struct kvm_cpuid2 *cpuid,
+ struct kvm_cpuid_entry2 *ent)
+{
+ int i;
+
+ for (i = 0; i < cpuid->nent; i++) {
+ struct kvm_cpuid_entry2 *cur = &cpuid->entries[i];
+
+ if (cur->function != ent->function || cur->index != ent->index)
+ continue;
+
+ memcpy(cur, ent, sizeof(struct kvm_cpuid_entry2));
+ return true;
+ }
+
+ return false;
+}
+
+uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
+ uint64_t a3)
+{
+ uint64_t r;
+
+ asm volatile("vmcall"
+ : "=a"(r)
+ : "b"(a0), "c"(a1), "d"(a2), "S"(a3));
+ return r;
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c
index da4d89a..a348997 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c
@@ -40,6 +40,9 @@
struct kvm_run *run = vcpu_state(vm, vcpu_id);
struct ucall ucall = {};
+ if (uc)
+ memset(uc, 0, sizeof(*uc));
+
if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) {
struct kvm_regs regs;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index f1e00d4..2448b30 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -542,3 +542,12 @@
vmx->eptp_hva = addr_gva2hva(vm, (uintptr_t)vmx->eptp);
vmx->eptp_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->eptp);
}
+
+void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint32_t eptp_memslot)
+{
+ vmx->apic_access = (void *)vm_vaddr_alloc(vm, getpagesize(),
+ 0x10000, 0, 0);
+ vmx->apic_access_hva = addr_gva2hva(vm, (uintptr_t)vmx->apic_access);
+ vmx->apic_access_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->apic_access);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
new file mode 100644
index 0000000..b10a274
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020, Google LLC.
+ *
+ * Tests for KVM paravirtual feature disablement
+ */
+#include <asm/kvm_para.h>
+#include <linux/kvm_para.h>
+#include <stdint.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+extern unsigned char rdmsr_start;
+extern unsigned char rdmsr_end;
+
+static u64 do_rdmsr(u32 idx)
+{
+ u32 lo, hi;
+
+ asm volatile("rdmsr_start: rdmsr;"
+ "rdmsr_end:"
+ : "=a"(lo), "=c"(hi)
+ : "c"(idx));
+
+ return (((u64) hi) << 32) | lo;
+}
+
+extern unsigned char wrmsr_start;
+extern unsigned char wrmsr_end;
+
+static void do_wrmsr(u32 idx, u64 val)
+{
+ u32 lo, hi;
+
+ lo = val;
+ hi = val >> 32;
+
+ asm volatile("wrmsr_start: wrmsr;"
+ "wrmsr_end:"
+ : : "a"(lo), "c"(idx), "d"(hi));
+}
+
+static int nr_gp;
+
+static void guest_gp_handler(struct ex_regs *regs)
+{
+ unsigned char *rip = (unsigned char *)regs->rip;
+ bool r, w;
+
+ r = rip == &rdmsr_start;
+ w = rip == &wrmsr_start;
+ GUEST_ASSERT(r || w);
+
+ nr_gp++;
+
+ if (r)
+ regs->rip = (uint64_t)&rdmsr_end;
+ else
+ regs->rip = (uint64_t)&wrmsr_end;
+}
+
+struct msr_data {
+ uint32_t idx;
+ const char *name;
+};
+
+#define TEST_MSR(msr) { .idx = msr, .name = #msr }
+#define UCALL_PR_MSR 0xdeadbeef
+#define PR_MSR(msr) ucall(UCALL_PR_MSR, 1, msr)
+
+/*
+ * KVM paravirtual msrs to test. Expect a #GP if any of these msrs are read or
+ * written, as the KVM_CPUID_FEATURES leaf is cleared.
+ */
+static struct msr_data msrs_to_test[] = {
+ TEST_MSR(MSR_KVM_SYSTEM_TIME),
+ TEST_MSR(MSR_KVM_SYSTEM_TIME_NEW),
+ TEST_MSR(MSR_KVM_WALL_CLOCK),
+ TEST_MSR(MSR_KVM_WALL_CLOCK_NEW),
+ TEST_MSR(MSR_KVM_ASYNC_PF_EN),
+ TEST_MSR(MSR_KVM_STEAL_TIME),
+ TEST_MSR(MSR_KVM_PV_EOI_EN),
+ TEST_MSR(MSR_KVM_POLL_CONTROL),
+ TEST_MSR(MSR_KVM_ASYNC_PF_INT),
+ TEST_MSR(MSR_KVM_ASYNC_PF_ACK),
+};
+
+static void test_msr(struct msr_data *msr)
+{
+ PR_MSR(msr);
+ do_rdmsr(msr->idx);
+ GUEST_ASSERT(READ_ONCE(nr_gp) == 1);
+
+ nr_gp = 0;
+ do_wrmsr(msr->idx, 0);
+ GUEST_ASSERT(READ_ONCE(nr_gp) == 1);
+ nr_gp = 0;
+}
+
+struct hcall_data {
+ uint64_t nr;
+ const char *name;
+};
+
+#define TEST_HCALL(hc) { .nr = hc, .name = #hc }
+#define UCALL_PR_HCALL 0xdeadc0de
+#define PR_HCALL(hc) ucall(UCALL_PR_HCALL, 1, hc)
+
+/*
+ * KVM hypercalls to test. Expect -KVM_ENOSYS when called, as the corresponding
+ * features have been cleared in KVM_CPUID_FEATURES.
+ */
+static struct hcall_data hcalls_to_test[] = {
+ TEST_HCALL(KVM_HC_KICK_CPU),
+ TEST_HCALL(KVM_HC_SEND_IPI),
+ TEST_HCALL(KVM_HC_SCHED_YIELD),
+};
+
+static void test_hcall(struct hcall_data *hc)
+{
+ uint64_t r;
+
+ PR_HCALL(hc);
+ r = kvm_hypercall(hc->nr, 0, 0, 0, 0);
+ GUEST_ASSERT(r == -KVM_ENOSYS);
+}
+
+static void guest_main(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(msrs_to_test); i++) {
+ test_msr(&msrs_to_test[i]);
+ }
+
+ for (i = 0; i < ARRAY_SIZE(hcalls_to_test); i++) {
+ test_hcall(&hcalls_to_test[i]);
+ }
+
+ GUEST_DONE();
+}
+
+static void clear_kvm_cpuid_features(struct kvm_cpuid2 *cpuid)
+{
+ struct kvm_cpuid_entry2 ent = {0};
+
+ ent.function = KVM_CPUID_FEATURES;
+ TEST_ASSERT(set_cpuid(cpuid, &ent),
+ "failed to clear KVM_CPUID_FEATURES leaf");
+}
+
+static void pr_msr(struct ucall *uc)
+{
+ struct msr_data *msr = (struct msr_data *)uc->args[0];
+
+ pr_info("testing msr: %s (%#x)\n", msr->name, msr->idx);
+}
+
+static void pr_hcall(struct ucall *uc)
+{
+ struct hcall_data *hc = (struct hcall_data *)uc->args[0];
+
+ pr_info("testing hcall: %s (%lu)\n", hc->name, hc->nr);
+}
+
+static void handle_abort(struct ucall *uc)
+{
+ TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0],
+ __FILE__, uc->args[1]);
+}
+
+#define VCPU_ID 0
+
+static void enter_guest(struct kvm_vm *vm)
+{
+ struct kvm_run *run;
+ struct ucall uc;
+ int r;
+
+ run = vcpu_state(vm, VCPU_ID);
+
+ while (true) {
+ r = _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(!r, "vcpu_run failed: %d\n", r);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "unexpected exit reason: %u (%s)",
+ run->exit_reason, exit_reason_str(run->exit_reason));
+
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_PR_MSR:
+ pr_msr(&uc);
+ break;
+ case UCALL_PR_HCALL:
+ pr_hcall(&uc);
+ break;
+ case UCALL_ABORT:
+ handle_abort(&uc);
+ return;
+ case UCALL_DONE:
+ return;
+ }
+ }
+}
+
+int main(void)
+{
+ struct kvm_enable_cap cap = {0};
+ struct kvm_cpuid2 *best;
+ struct kvm_vm *vm;
+
+ if (!kvm_check_cap(KVM_CAP_ENFORCE_PV_FEATURE_CPUID)) {
+ pr_info("will skip kvm paravirt restriction tests.\n");
+ return 0;
+ }
+
+ vm = vm_create_default(VCPU_ID, 0, guest_main);
+
+ cap.cap = KVM_CAP_ENFORCE_PV_FEATURE_CPUID;
+ cap.args[0] = 1;
+ vcpu_enable_cap(vm, VCPU_ID, &cap);
+
+ best = kvm_get_supported_cpuid();
+ clear_kvm_cpuid_features(best);
+ vcpu_set_cpuid(vm, VCPU_ID, best);
+
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vm, VCPU_ID);
+ vm_handle_exception(vm, GP_VECTOR, guest_gp_handler);
+
+ enter_guest(vm);
+ kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
new file mode 100644
index 0000000..1f65342
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vmx_apic_access_test
+ *
+ * Copyright (C) 2020, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * The first subtest simply checks to see that an L2 guest can be
+ * launched with a valid APIC-access address that is backed by a
+ * page of L1 physical memory.
+ *
+ * The second subtest sets the APIC-access address to a (valid) L1
+ * physical address that is not backed by memory. KVM can't handle
+ * this situation, so resuming L2 should result in a KVM exit for
+ * internal error (emulation). This is not an architectural
+ * requirement. It is just a shortcoming of KVM. The internal error
+ * is unfortunate, but it's better than what used to happen!
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "kselftest.h"
+
+#define VCPU_ID 0
+
+/* The virtual machine object. */
+static struct kvm_vm *vm;
+
+static void l2_guest_code(void)
+{
+ /* Exit to L1 */
+ __asm__ __volatile__("vmcall");
+}
+
+static void l1_guest_code(struct vmx_pages *vmx_pages, unsigned long high_gpa)
+{
+#define L2_GUEST_STACK_SIZE 64
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+ uint32_t control;
+
+ GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+ GUEST_ASSERT(load_vmcs(vmx_pages));
+
+ /* Prepare the VMCS for L2 execution. */
+ prepare_vmcs(vmx_pages, l2_guest_code,
+ &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+ control = vmreadz(CPU_BASED_VM_EXEC_CONTROL);
+ control |= CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
+ vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
+ control = vmreadz(SECONDARY_VM_EXEC_CONTROL);
+ control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+ vmwrite(SECONDARY_VM_EXEC_CONTROL, control);
+ vmwrite(APIC_ACCESS_ADDR, vmx_pages->apic_access_gpa);
+
+ /* Try to launch L2 with the memory-backed APIC-access address. */
+ GUEST_SYNC(vmreadz(APIC_ACCESS_ADDR));
+ GUEST_ASSERT(!vmlaunch());
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+ vmwrite(APIC_ACCESS_ADDR, high_gpa);
+
+ /* Try to resume L2 with the unbacked APIC-access address. */
+ GUEST_SYNC(vmreadz(APIC_ACCESS_ADDR));
+ GUEST_ASSERT(!vmresume());
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+ GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+ unsigned long apic_access_addr = ~0ul;
+ unsigned int paddr_width;
+ unsigned int vaddr_width;
+ vm_vaddr_t vmx_pages_gva;
+ unsigned long high_gpa;
+ struct vmx_pages *vmx;
+ bool done = false;
+
+ nested_vmx_check_supported();
+
+ vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
+ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+ kvm_get_cpu_address_width(&paddr_width, &vaddr_width);
+ high_gpa = (1ul << paddr_width) - getpagesize();
+ if ((unsigned long)DEFAULT_GUEST_PHY_PAGES * getpagesize() > high_gpa) {
+ print_skip("No unbacked physical page available");
+ exit(KSFT_SKIP);
+ }
+
+ vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+ prepare_virtualize_apic_accesses(vmx, vm, 0);
+ vcpu_args_set(vm, VCPU_ID, 2, vmx_pages_gva, high_gpa);
+
+ while (!done) {
+ volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+ struct ucall uc;
+
+ vcpu_run(vm, VCPU_ID);
+ if (apic_access_addr == high_gpa) {
+ TEST_ASSERT(run->exit_reason ==
+ KVM_EXIT_INTERNAL_ERROR,
+ "Got exit reason other than KVM_EXIT_INTERNAL_ERROR: %u (%s)\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+ TEST_ASSERT(run->internal.suberror ==
+ KVM_INTERNAL_ERROR_EMULATION,
+ "Got internal suberror other than KVM_INTERNAL_ERROR_EMULATION: %u\n",
+ run->internal.suberror);
+ break;
+ }
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_ABORT:
+ TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+ __FILE__, uc.args[1]);
+ /* NOT REACHED */
+ case UCALL_SYNC:
+ apic_access_addr = uc.args[1];
+ break;
+ case UCALL_DONE:
+ done = true;
+ break;
+ default:
+ TEST_ASSERT(false, "Unknown ucall %lu", uc.cmd);
+ }
+ }
+ kvm_vm_free(vm);
+ return 0;
+}
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 30848ca..a5ce26d 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -136,7 +136,7 @@
ifeq ($(OVERRIDE_TARGETS),)
LOCAL_HDRS := $(selfdir)/kselftest_harness.h $(selfdir)/kselftest.h
$(OUTPUT)/%:%.c $(LOCAL_HDRS)
- $(LINK.c) $^ $(LDLIBS) -o $@
+ $(LINK.c) $(filter-out $(LOCAL_HDRS),$^) $(LDLIBS) -o $@
$(OUTPUT)/%.o:%.S
$(COMPILE.S) $^ -o $@
diff --git a/tools/testing/selftests/pidfd/config b/tools/testing/selftests/pidfd/config
index bb11de9..f6f2965 100644
--- a/tools/testing/selftests/pidfd/config
+++ b/tools/testing/selftests/pidfd/config
@@ -4,3 +4,4 @@
CONFIG_PID_NS=y
CONFIG_NET_NS=y
CONFIG_CGROUPS=y
+CONFIG_CHECKPOINT_RESTORE=y
diff --git a/tools/testing/selftests/pidfd/pidfd_getfd_test.c b/tools/testing/selftests/pidfd/pidfd_getfd_test.c
index 7758c98..0930e24 100644
--- a/tools/testing/selftests/pidfd/pidfd_getfd_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_getfd_test.c
@@ -204,7 +204,10 @@
fd = sys_pidfd_getfd(self->pidfd, self->remote_fd, 0);
ASSERT_GE(fd, 0);
- EXPECT_EQ(0, sys_kcmp(getpid(), self->pid, KCMP_FILE, fd, self->remote_fd));
+ ret = sys_kcmp(getpid(), self->pid, KCMP_FILE, fd, self->remote_fd);
+ if (ret < 0 && errno == ENOSYS)
+ SKIP(return, "kcmp() syscall not supported");
+ EXPECT_EQ(ret, 0);
ret = fcntl(fd, F_GETFD);
ASSERT_GE(ret, 0);
diff --git a/tools/testing/selftests/pidfd/pidfd_open_test.c b/tools/testing/selftests/pidfd/pidfd_open_test.c
index b9fe75f..8a59438 100644
--- a/tools/testing/selftests/pidfd/pidfd_open_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_open_test.c
@@ -6,7 +6,6 @@
#include <inttypes.h>
#include <limits.h>
#include <linux/types.h>
-#include <linux/wait.h>
#include <sched.h>
#include <signal.h>
#include <stdbool.h>
diff --git a/tools/testing/selftests/pidfd/pidfd_poll_test.c b/tools/testing/selftests/pidfd/pidfd_poll_test.c
index 4b11544..6108112 100644
--- a/tools/testing/selftests/pidfd/pidfd_poll_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_poll_test.c
@@ -3,7 +3,6 @@
#define _GNU_SOURCE
#include <errno.h>
#include <linux/types.h>
-#include <linux/wait.h>
#include <poll.h>
#include <signal.h>
#include <stdbool.h>
diff --git a/tools/testing/selftests/pidfd/pidfd_setns_test.c b/tools/testing/selftests/pidfd/pidfd_setns_test.c
index 1f085b9..6e2f2cd 100644
--- a/tools/testing/selftests/pidfd/pidfd_setns_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_setns_test.c
@@ -16,7 +16,6 @@
#include <unistd.h>
#include <sys/socket.h>
#include <sys/stat.h>
-#include <linux/kcmp.h>
#include "pidfd.h"
#include "../clone3/clone3_selftests.h"
diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c
index c585aaa..529eb70 100644
--- a/tools/testing/selftests/pidfd/pidfd_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_test.c
@@ -330,7 +330,7 @@
ksft_exit_fail_msg("%s test: Failed to recycle pid %d\n",
test_name, PID_RECYCLE);
case PIDFD_SKIP:
- ksft_print_msg("%s test: Skipping test\n", test_name);
+ ksft_test_result_skip("%s test: Skipping test\n", test_name);
ret = 0;
break;
case PIDFD_XFAIL:
diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h
index 052b5a7..b7d188f 100644
--- a/tools/testing/selftests/powerpc/include/utils.h
+++ b/tools/testing/selftests/powerpc/include/utils.h
@@ -42,6 +42,11 @@
int perf_event_disable(int fd);
int perf_event_reset(int fd);
+struct perf_event_read {
+ __u64 nr;
+ __u64 l1d_misses;
+};
+
#if !defined(__GLIBC_PREREQ) || !__GLIBC_PREREQ(2, 30)
#include <unistd.h>
#include <sys/syscall.h>
diff --git a/tools/testing/selftests/powerpc/security/.gitignore b/tools/testing/selftests/powerpc/security/.gitignore
index f795e06..4257a1f1 100644
--- a/tools/testing/selftests/powerpc/security/.gitignore
+++ b/tools/testing/selftests/powerpc/security/.gitignore
@@ -1,2 +1,3 @@
# SPDX-License-Identifier: GPL-2.0-only
rfi_flush
+entry_flush
diff --git a/tools/testing/selftests/powerpc/security/Makefile b/tools/testing/selftests/powerpc/security/Makefile
index eadbbff..f25e854 100644
--- a/tools/testing/selftests/powerpc/security/Makefile
+++ b/tools/testing/selftests/powerpc/security/Makefile
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: GPL-2.0+
-TEST_GEN_PROGS := rfi_flush spectre_v2
+TEST_GEN_PROGS := rfi_flush entry_flush spectre_v2
top_srcdir = ../../../../..
CFLAGS += -I../../../../../usr/include
@@ -11,3 +11,5 @@
$(OUTPUT)/spectre_v2: CFLAGS += -m64
$(OUTPUT)/spectre_v2: ../pmu/event.c branch_loops.S
+$(OUTPUT)/rfi_flush: flush_utils.c
+$(OUTPUT)/entry_flush: flush_utils.c
diff --git a/tools/testing/selftests/powerpc/security/entry_flush.c b/tools/testing/selftests/powerpc/security/entry_flush.c
new file mode 100644
index 0000000..78cf914
--- /dev/null
+++ b/tools/testing/selftests/powerpc/security/entry_flush.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+/*
+ * Copyright 2018 IBM Corporation.
+ */
+
+#define __SANE_USERSPACE_TYPES__
+
+#include <sys/types.h>
+#include <stdint.h>
+#include <malloc.h>
+#include <unistd.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+#include "utils.h"
+#include "flush_utils.h"
+
+int entry_flush_test(void)
+{
+ char *p;
+ int repetitions = 10;
+ int fd, passes = 0, iter, rc = 0;
+ struct perf_event_read v;
+ __u64 l1d_misses_total = 0;
+ unsigned long iterations = 100000, zero_size = 24 * 1024;
+ unsigned long l1d_misses_expected;
+ int rfi_flush_orig;
+ int entry_flush, entry_flush_orig;
+
+ SKIP_IF(geteuid() != 0);
+
+ // The PMU event we use only works on Power7 or later
+ SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06));
+
+ if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) {
+ perror("Unable to read powerpc/rfi_flush debugfs file");
+ SKIP_IF(1);
+ }
+
+ if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) {
+ perror("Unable to read powerpc/entry_flush debugfs file");
+ SKIP_IF(1);
+ }
+
+ if (rfi_flush_orig != 0) {
+ if (write_debugfs_file("powerpc/rfi_flush", 0) < 0) {
+ perror("error writing to powerpc/rfi_flush debugfs file");
+ FAIL_IF(1);
+ }
+ }
+
+ entry_flush = entry_flush_orig;
+
+ fd = perf_event_open_counter(PERF_TYPE_RAW, /* L1d miss */ 0x400f0, -1);
+ FAIL_IF(fd < 0);
+
+ p = (char *)memalign(zero_size, CACHELINE_SIZE);
+
+ FAIL_IF(perf_event_enable(fd));
+
+ // disable L1 prefetching
+ set_dscr(1);
+
+ iter = repetitions;
+
+ /*
+ * We expect to see l1d miss for each cacheline access when entry_flush
+ * is set. Allow a small variation on this.
+ */
+ l1d_misses_expected = iterations * (zero_size / CACHELINE_SIZE - 2);
+
+again:
+ FAIL_IF(perf_event_reset(fd));
+
+ syscall_loop(p, iterations, zero_size);
+
+ FAIL_IF(read(fd, &v, sizeof(v)) != sizeof(v));
+
+ if (entry_flush && v.l1d_misses >= l1d_misses_expected)
+ passes++;
+ else if (!entry_flush && v.l1d_misses < (l1d_misses_expected / 2))
+ passes++;
+
+ l1d_misses_total += v.l1d_misses;
+
+ while (--iter)
+ goto again;
+
+ if (passes < repetitions) {
+ printf("FAIL (L1D misses with entry_flush=%d: %llu %c %lu) [%d/%d failures]\n",
+ entry_flush, l1d_misses_total, entry_flush ? '<' : '>',
+ entry_flush ? repetitions * l1d_misses_expected :
+ repetitions * l1d_misses_expected / 2,
+ repetitions - passes, repetitions);
+ rc = 1;
+ } else {
+ printf("PASS (L1D misses with entry_flush=%d: %llu %c %lu) [%d/%d pass]\n",
+ entry_flush, l1d_misses_total, entry_flush ? '>' : '<',
+ entry_flush ? repetitions * l1d_misses_expected :
+ repetitions * l1d_misses_expected / 2,
+ passes, repetitions);
+ }
+
+ if (entry_flush == entry_flush_orig) {
+ entry_flush = !entry_flush_orig;
+ if (write_debugfs_file("powerpc/entry_flush", entry_flush) < 0) {
+ perror("error writing to powerpc/entry_flush debugfs file");
+ return 1;
+ }
+ iter = repetitions;
+ l1d_misses_total = 0;
+ passes = 0;
+ goto again;
+ }
+
+ perf_event_disable(fd);
+ close(fd);
+
+ set_dscr(0);
+
+ if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) {
+ perror("unable to restore original value of powerpc/rfi_flush debugfs file");
+ return 1;
+ }
+
+ if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) {
+ perror("unable to restore original value of powerpc/entry_flush debugfs file");
+ return 1;
+ }
+
+ return rc;
+}
+
+int main(int argc, char *argv[])
+{
+ return test_harness(entry_flush_test, "entry_flush_test");
+}
diff --git a/tools/testing/selftests/powerpc/security/flush_utils.c b/tools/testing/selftests/powerpc/security/flush_utils.c
new file mode 100644
index 0000000..0c3c4c4
--- /dev/null
+++ b/tools/testing/selftests/powerpc/security/flush_utils.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+/*
+ * Copyright 2018 IBM Corporation.
+ */
+
+#define __SANE_USERSPACE_TYPES__
+
+#include <sys/types.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+#include "utils.h"
+#include "flush_utils.h"
+
+static inline __u64 load(void *addr)
+{
+ __u64 tmp;
+
+ asm volatile("ld %0,0(%1)" : "=r"(tmp) : "b"(addr));
+
+ return tmp;
+}
+
+void syscall_loop(char *p, unsigned long iterations,
+ unsigned long zero_size)
+{
+ for (unsigned long i = 0; i < iterations; i++) {
+ for (unsigned long j = 0; j < zero_size; j += CACHELINE_SIZE)
+ load(p + j);
+ getppid();
+ }
+}
+
+static void sigill_handler(int signr, siginfo_t *info, void *unused)
+{
+ static int warned;
+ ucontext_t *ctx = (ucontext_t *)unused;
+ unsigned long *pc = &UCONTEXT_NIA(ctx);
+
+ /* mtspr 3,RS to check for move to DSCR below */
+ if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) {
+ if (!warned++)
+ printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n");
+ *pc += 4;
+ } else {
+ printf("SIGILL at %p\n", pc);
+ abort();
+ }
+}
+
+void set_dscr(unsigned long val)
+{
+ static int init;
+ struct sigaction sa;
+
+ if (!init) {
+ memset(&sa, 0, sizeof(sa));
+ sa.sa_sigaction = sigill_handler;
+ sa.sa_flags = SA_SIGINFO;
+ if (sigaction(SIGILL, &sa, NULL))
+ perror("sigill_handler");
+ init = 1;
+ }
+
+ asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR));
+}
diff --git a/tools/testing/selftests/powerpc/security/flush_utils.h b/tools/testing/selftests/powerpc/security/flush_utils.h
new file mode 100644
index 0000000..07a5eb3
--- /dev/null
+++ b/tools/testing/selftests/powerpc/security/flush_utils.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+/*
+ * Copyright 2018 IBM Corporation.
+ */
+
+#ifndef _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H
+#define _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H
+
+#define CACHELINE_SIZE 128
+
+void syscall_loop(char *p, unsigned long iterations,
+ unsigned long zero_size);
+
+void set_dscr(unsigned long val);
+
+#endif /* _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H */
diff --git a/tools/testing/selftests/powerpc/security/rfi_flush.c b/tools/testing/selftests/powerpc/security/rfi_flush.c
index 93a65bd..7565fd7 100644
--- a/tools/testing/selftests/powerpc/security/rfi_flush.c
+++ b/tools/testing/selftests/powerpc/security/rfi_flush.c
@@ -10,71 +10,12 @@
#include <stdint.h>
#include <malloc.h>
#include <unistd.h>
-#include <signal.h>
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include "utils.h"
+#include "flush_utils.h"
-#define CACHELINE_SIZE 128
-
-struct perf_event_read {
- __u64 nr;
- __u64 l1d_misses;
-};
-
-static inline __u64 load(void *addr)
-{
- __u64 tmp;
-
- asm volatile("ld %0,0(%1)" : "=r"(tmp) : "b"(addr));
-
- return tmp;
-}
-
-static void syscall_loop(char *p, unsigned long iterations,
- unsigned long zero_size)
-{
- for (unsigned long i = 0; i < iterations; i++) {
- for (unsigned long j = 0; j < zero_size; j += CACHELINE_SIZE)
- load(p + j);
- getppid();
- }
-}
-
-static void sigill_handler(int signr, siginfo_t *info, void *unused)
-{
- static int warned = 0;
- ucontext_t *ctx = (ucontext_t *)unused;
- unsigned long *pc = &UCONTEXT_NIA(ctx);
-
- /* mtspr 3,RS to check for move to DSCR below */
- if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) {
- if (!warned++)
- printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n");
- *pc += 4;
- } else {
- printf("SIGILL at %p\n", pc);
- abort();
- }
-}
-
-static void set_dscr(unsigned long val)
-{
- static int init = 0;
- struct sigaction sa;
-
- if (!init) {
- memset(&sa, 0, sizeof(sa));
- sa.sa_sigaction = sigill_handler;
- sa.sa_flags = SA_SIGINFO;
- if (sigaction(SIGILL, &sa, NULL))
- perror("sigill_handler");
- init = 1;
- }
-
- asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR));
-}
int rfi_flush_test(void)
{
@@ -85,19 +26,33 @@
__u64 l1d_misses_total = 0;
unsigned long iterations = 100000, zero_size = 24 * 1024;
unsigned long l1d_misses_expected;
- int rfi_flush_org, rfi_flush;
+ int rfi_flush_orig, rfi_flush;
+ int have_entry_flush, entry_flush_orig;
SKIP_IF(geteuid() != 0);
// The PMU event we use only works on Power7 or later
SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06));
- if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_org)) {
+ if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) {
perror("Unable to read powerpc/rfi_flush debugfs file");
SKIP_IF(1);
}
- rfi_flush = rfi_flush_org;
+ if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) {
+ have_entry_flush = 0;
+ } else {
+ have_entry_flush = 1;
+
+ if (entry_flush_orig != 0) {
+ if (write_debugfs_file("powerpc/entry_flush", 0) < 0) {
+ perror("error writing to powerpc/entry_flush debugfs file");
+ return 1;
+ }
+ }
+ }
+
+ rfi_flush = rfi_flush_orig;
fd = perf_event_open_counter(PERF_TYPE_RAW, /* L1d miss */ 0x400f0, -1);
FAIL_IF(fd < 0);
@@ -106,6 +61,7 @@
FAIL_IF(perf_event_enable(fd));
+ // disable L1 prefetching
set_dscr(1);
iter = repetitions;
@@ -147,8 +103,8 @@
repetitions * l1d_misses_expected / 2,
passes, repetitions);
- if (rfi_flush == rfi_flush_org) {
- rfi_flush = !rfi_flush_org;
+ if (rfi_flush == rfi_flush_orig) {
+ rfi_flush = !rfi_flush_orig;
if (write_debugfs_file("powerpc/rfi_flush", rfi_flush) < 0) {
perror("error writing to powerpc/rfi_flush debugfs file");
return 1;
@@ -164,11 +120,19 @@
set_dscr(0);
- if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_org) < 0) {
+ if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) {
perror("unable to restore original value of powerpc/rfi_flush debugfs file");
return 1;
}
+ if (have_entry_flush) {
+ if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) {
+ perror("unable to restore original value of powerpc/entry_flush "
+ "debugfs file");
+ return 1;
+ }
+ }
+
return rc;
}
diff --git a/tools/testing/selftests/proc/proc-loadavg-001.c b/tools/testing/selftests/proc/proc-loadavg-001.c
index 471e2aa..fb4fe91 100644
--- a/tools/testing/selftests/proc/proc-loadavg-001.c
+++ b/tools/testing/selftests/proc/proc-loadavg-001.c
@@ -14,7 +14,6 @@
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
/* Test that /proc/loadavg correctly reports last pid in pid namespace. */
-#define _GNU_SOURCE
#include <errno.h>
#include <sched.h>
#include <sys/types.h>
diff --git a/tools/testing/selftests/proc/proc-self-syscall.c b/tools/testing/selftests/proc/proc-self-syscall.c
index 9f6d000..8511dcf 100644
--- a/tools/testing/selftests/proc/proc-self-syscall.c
+++ b/tools/testing/selftests/proc/proc-self-syscall.c
@@ -13,7 +13,6 @@
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
-#define _GNU_SOURCE
#include <unistd.h>
#include <sys/syscall.h>
#include <sys/types.h>
diff --git a/tools/testing/selftests/proc/proc-uptime-002.c b/tools/testing/selftests/proc/proc-uptime-002.c
index 30e2b78..e7ceabe 100644
--- a/tools/testing/selftests/proc/proc-uptime-002.c
+++ b/tools/testing/selftests/proc/proc-uptime-002.c
@@ -15,7 +15,6 @@
*/
// Test that values in /proc/uptime increment monotonically
// while shifting across CPUs.
-#define _GNU_SOURCE
#undef NDEBUG
#include <assert.h>
#include <unistd.h>
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
index bb543bf..361235a 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
@@ -100,7 +100,7 @@
],
"cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop",
"expExitCode": "0",
- "verifyCmd": "$TC filter show terse dev $DEV2 ingress",
+ "verifyCmd": "$TC -br filter show dev $DEV2 ingress",
"matchPattern": "filter protocol ip pref 1 flower.*handle",
"matchCount": "1",
"teardown": [
@@ -119,7 +119,7 @@
],
"cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop",
"expExitCode": "0",
- "verifyCmd": "$TC filter show terse dev $DEV2 ingress",
+ "verifyCmd": "$TC -br filter show dev $DEV2 ingress",
"matchPattern": " dst_mac e4:11:22:11:4a:51",
"matchCount": "0",
"teardown": [
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index d77f482..74c69b7 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -316,6 +316,14 @@
n2 ping -W 1 -c 1 192.168.241.1
n1 wg set wg0 peer "$pub2" persistent-keepalive 0
+# Test that sk_bound_dev_if works
+n1 ping -I wg0 -c 1 -W 1 192.168.241.2
+# What about when the mark changes and the packet must be rerouted?
+n1 iptables -t mangle -I OUTPUT -j MARK --set-xmark 1
+n1 ping -c 1 -W 1 192.168.241.2 # First the boring case
+n1 ping -I wg0 -c 1 -W 1 192.168.241.2 # Then the sk_bound_dev_if case
+n1 iptables -t mangle -D OUTPUT -j MARK --set-xmark 1
+
# Test that onion routing works, even when it loops
n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5
ip1 addr add 192.168.242.1/24 dev wg0
diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config
index d531de1..4eecb43 100644
--- a/tools/testing/selftests/wireguard/qemu/kernel.config
+++ b/tools/testing/selftests/wireguard/qemu/kernel.config
@@ -18,10 +18,12 @@
CONFIG_NETFILTER_XTABLES=y
CONFIG_NETFILTER_XT_NAT=y
CONFIG_NETFILTER_XT_MATCH_LENGTH=y
+CONFIG_NETFILTER_XT_MARK=y
CONFIG_NF_CONNTRACK_IPV4=y
CONFIG_NF_NAT_IPV4=y
CONFIG_IP_NF_IPTABLES=y
CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_MANGLE=y
CONFIG_IP_NF_NAT=y
CONFIG_IP_ADVANCED_ROUTER=y
CONFIG_IP_MULTIPLE_TABLES=y
