Merge tag 'locking-urgent-2024-08-25' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking fix from Thomas Gleixner:
"A single fix for rt_mutex.
The deadlock detection code drops into an infinite scheduling loop
while still holding rt_mutex::wait_lock, which rightfully triggers a
'scheduling in atomic' warning.
Unlock it before that"
* tag 'locking-urgent-2024-08-25' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
rtmutex: Drop rt_mutex::wait_lock before scheduling
diff --git a/.mailmap b/.mailmap
index 8ee01d9..caf46a6 100644
--- a/.mailmap
+++ b/.mailmap
@@ -354,6 +354,8 @@
Kiran Gunda <quic_kgunda@quicinc.com> <kgunda@codeaurora.org>
Kirill Tkhai <tkhai@ya.ru> <ktkhai@virtuozzo.com>
Kishon Vijay Abraham I <kishon@kernel.org> <kishon@ti.com>
+Konrad Dybcio <konradybcio@kernel.org> <konrad.dybcio@linaro.org>
+Konrad Dybcio <konradybcio@kernel.org> <konrad.dybcio@somainline.org>
Konstantin Khlebnikov <koct9i@gmail.com> <khlebnikov@yandex-team.ru>
Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com>
Koushik <raghavendra.koushik@neterion.com>
@@ -614,6 +616,7 @@
Sricharan Ramabadhran <quic_srichara@quicinc.com> <sricharan@codeaurora.org>
Srinivas Ramana <quic_sramana@quicinc.com> <sramana@codeaurora.org>
Sriram R <quic_srirrama@quicinc.com> <srirrama@codeaurora.org>
+Sriram Yagnaraman <sriram.yagnaraman@ericsson.com> <sriram.yagnaraman@est.tech>
Stanislav Fomichev <sdf@fomichev.me> <sdf@google.com>
Stefan Wahren <wahrenst@gmx.net> <stefan.wahren@i2se.com>
Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 3258733..de725ca 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -562,7 +562,8 @@
================ =========================================
If control status is "forceoff" or "notsupported" writes
- are rejected.
+ are rejected. Note that enabling SMT on PowerPC skips
+ offline cores.
What: /sys/devices/system/cpu/cpuX/power/energy_perf_bias
Date: March 2019
diff --git a/Documentation/admin-guide/device-mapper/dm-crypt.rst b/Documentation/admin-guide/device-mapper/dm-crypt.rst
index e625830..552c915 100644
--- a/Documentation/admin-guide/device-mapper/dm-crypt.rst
+++ b/Documentation/admin-guide/device-mapper/dm-crypt.rst
@@ -162,13 +162,14 @@
Module parameters::
-max_read_size
-max_write_size
- Maximum size of read or write requests. When a request larger than this size
- is received, dm-crypt will split the request. The splitting improves
- concurrency (the split requests could be encrypted in parallel by multiple
- cores), but it also causes overhead. The user should tune these parameters to
- fit the actual workload.
+
+ max_read_size
+ max_write_size
+ Maximum size of read or write requests. When a request larger than this size
+ is received, dm-crypt will split the request. The splitting improves
+ concurrency (the split requests could be encrypted in parallel by multiple
+ cores), but it also causes overhead. The user should tune these parameters to
+ fit the actual workload.
Example scripts
diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 3db60a0..85b7092 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -239,25 +239,33 @@
ratified in commit 98918c844281 ("Merge pull request #1217 from
riscv/zawrs") of riscv-isa-manual.
-* :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance
- information about the selected set of processors.
+* :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: Deprecated. Returns similar values to
+ :c:macro:`RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF`, but the key was
+ mistakenly classified as a bitmask rather than a value.
- * :c:macro:`RISCV_HWPROBE_MISALIGNED_UNKNOWN`: The performance of misaligned
- accesses is unknown.
+* :c:macro:`RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF`: An enum value describing
+ the performance of misaligned scalar native word accesses on the selected set
+ of processors.
- * :c:macro:`RISCV_HWPROBE_MISALIGNED_EMULATED`: Misaligned accesses are
- emulated via software, either in or below the kernel. These accesses are
- always extremely slow.
+ * :c:macro:`RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN`: The performance of
+ misaligned scalar accesses is unknown.
- * :c:macro:`RISCV_HWPROBE_MISALIGNED_SLOW`: Misaligned accesses are slower
- than equivalent byte accesses. Misaligned accesses may be supported
- directly in hardware, or trapped and emulated by software.
+ * :c:macro:`RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED`: Misaligned scalar
+ accesses are emulated via software, either in or below the kernel. These
+ accesses are always extremely slow.
- * :c:macro:`RISCV_HWPROBE_MISALIGNED_FAST`: Misaligned accesses are faster
- than equivalent byte accesses.
+ * :c:macro:`RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW`: Misaligned scalar native
+ word sized accesses are slower than the equivalent quantity of byte
+ accesses. Misaligned accesses may be supported directly in hardware, or
+ trapped and emulated by software.
- * :c:macro:`RISCV_HWPROBE_MISALIGNED_UNSUPPORTED`: Misaligned accesses are
- not supported at all and will generate a misaligned address fault.
+ * :c:macro:`RISCV_HWPROBE_MISALIGNED_SCALAR_FAST`: Misaligned scalar native
+ word sized accesses are faster than the equivalent quantity of byte
+ accesses.
+
+ * :c:macro:`RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED`: Misaligned scalar
+ accesses are not supported at all and will generate a misaligned address
+ fault.
* :c:macro:`RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE`: An unsigned int which
represents the size of the Zicboz block in bytes.
diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst
index bcc370c..16f861c 100644
--- a/Documentation/core-api/workqueue.rst
+++ b/Documentation/core-api/workqueue.rst
@@ -260,7 +260,7 @@
is in flight at any given time and the work items are processed in
queueing order. While the combination of ``@max_active`` of 1 and
``WQ_UNBOUND`` used to achieve this behavior, this is no longer the
-case. Use ``alloc_ordered_queue()`` instead.
+case. Use alloc_ordered_workqueue() instead.
Example Execution Scenarios
diff --git a/Documentation/devicetree/bindings/clock/qcom,dispcc-sm6350.yaml b/Documentation/devicetree/bindings/clock/qcom,dispcc-sm6350.yaml
index a584b495..46403b9 100644
--- a/Documentation/devicetree/bindings/clock/qcom,dispcc-sm6350.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,dispcc-sm6350.yaml
@@ -7,7 +7,7 @@
title: Qualcomm Display Clock & Reset Controller on SM6350
maintainers:
- - Konrad Dybcio <konrad.dybcio@somainline.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
Qualcomm display clock control module provides the clocks, resets and power
diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-msm8994.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-msm8994.yaml
index 6b9c1d1..10afe98 100644
--- a/Documentation/devicetree/bindings/clock/qcom,gcc-msm8994.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,gcc-msm8994.yaml
@@ -7,7 +7,7 @@
title: Qualcomm Global Clock & Reset Controller on MSM8994
maintainers:
- - Konrad Dybcio <konrad.dybcio@somainline.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
Qualcomm global clock control module provides the clocks, resets and power
diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-sm6125.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-sm6125.yaml
index a5a29dc..1fe68e0 100644
--- a/Documentation/devicetree/bindings/clock/qcom,gcc-sm6125.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,gcc-sm6125.yaml
@@ -7,7 +7,7 @@
title: Qualcomm Global Clock & Reset Controller on SM6125
maintainers:
- - Konrad Dybcio <konrad.dybcio@somainline.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
Qualcomm global clock control module provides the clocks, resets and power
diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-sm6350.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-sm6350.yaml
index 2280b85..78e232f 100644
--- a/Documentation/devicetree/bindings/clock/qcom,gcc-sm6350.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,gcc-sm6350.yaml
@@ -7,7 +7,7 @@
title: Qualcomm Global Clock & Reset Controller on SM6350
maintainers:
- - Konrad Dybcio <konrad.dybcio@somainline.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
Qualcomm global clock control module provides the clocks, resets and power
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm6115-gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm6115-gpucc.yaml
index cf19f44..4ff17a9 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm6115-gpucc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm6115-gpucc.yaml
@@ -7,7 +7,7 @@
title: Qualcomm Graphics Clock & Reset Controller on SM6115
maintainers:
- - Konrad Dybcio <konrad.dybcio@linaro.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
Qualcomm graphics clock control module provides clocks, resets and power
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm6125-gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm6125-gpucc.yaml
index 374a184..10a9c96a 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm6125-gpucc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm6125-gpucc.yaml
@@ -7,7 +7,7 @@
title: Qualcomm Graphics Clock & Reset Controller on SM6125
maintainers:
- - Konrad Dybcio <konrad.dybcio@linaro.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
Qualcomm graphics clock control module provides clocks and power domains on
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm6350-camcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm6350-camcc.yaml
index fd6658c..c03b30f 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm6350-camcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm6350-camcc.yaml
@@ -7,7 +7,7 @@
title: Qualcomm Camera Clock & Reset Controller on SM6350
maintainers:
- - Konrad Dybcio <konrad.dybcio@linaro.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
Qualcomm camera clock control module provides the clocks, resets and power
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm6375-dispcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm6375-dispcc.yaml
index 183b1c7..3cd422a 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm6375-dispcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm6375-dispcc.yaml
@@ -7,7 +7,7 @@
title: Qualcomm Display Clock & Reset Controller on SM6375
maintainers:
- - Konrad Dybcio <konrad.dybcio@linaro.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
Qualcomm display clock control module provides the clocks, resets and power
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm6375-gcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm6375-gcc.yaml
index 147b75a..de4e906 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm6375-gcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm6375-gcc.yaml
@@ -7,7 +7,7 @@
title: Qualcomm Global Clock & Reset Controller on SM6375
maintainers:
- - Konrad Dybcio <konrad.dybcio@somainline.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
Qualcomm global clock control module provides the clocks, resets and power
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm6375-gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm6375-gpucc.yaml
index cf4cad7..d9dd479 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm6375-gpucc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm6375-gpucc.yaml
@@ -7,7 +7,7 @@
title: Qualcomm Graphics Clock & Reset Controller on SM6375
maintainers:
- - Konrad Dybcio <konrad.dybcio@linaro.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
Qualcomm graphics clock control module provides clocks, resets and power
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8350-videocc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8350-videocc.yaml
index 46d1d91..5c2ecec 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm8350-videocc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8350-videocc.yaml
@@ -7,7 +7,7 @@
title: Qualcomm SM8350 Video Clock & Reset Controller
maintainers:
- - Konrad Dybcio <konrad.dybcio@linaro.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
Qualcomm video clock control module provides the clocks, resets and power
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml
index 3c2cac1..d10bb00 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml
@@ -7,7 +7,7 @@
title: Qualcomm Graphics Clock & Reset Controller on SM8450
maintainers:
- - Konrad Dybcio <konrad.dybcio@linaro.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
Qualcomm graphics clock control module provides the clocks, resets and power
diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm6375-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm6375-mdss.yaml
index 8e8a288..e22b4c4 100644
--- a/Documentation/devicetree/bindings/display/msm/qcom,sm6375-mdss.yaml
+++ b/Documentation/devicetree/bindings/display/msm/qcom,sm6375-mdss.yaml
@@ -7,7 +7,7 @@
title: Qualcomm SM6375 Display MDSS
maintainers:
- - Konrad Dybcio <konrad.dybcio@linaro.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description:
SM6375 MSM Mobile Display Subsystem (MDSS), which encapsulates sub-blocks
diff --git a/Documentation/devicetree/bindings/display/panel/asus,z00t-tm5p5-nt35596.yaml b/Documentation/devicetree/bindings/display/panel/asus,z00t-tm5p5-nt35596.yaml
index 2399cab..dd614e0 100644
--- a/Documentation/devicetree/bindings/display/panel/asus,z00t-tm5p5-nt35596.yaml
+++ b/Documentation/devicetree/bindings/display/panel/asus,z00t-tm5p5-nt35596.yaml
@@ -7,7 +7,7 @@
title: ASUS Z00T TM5P5 NT35596 5.5" 1080×1920 LCD Panel
maintainers:
- - Konrad Dybcio <konradybcio@gmail.com>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |+
This panel seems to only be found in the Asus Z00T
diff --git a/Documentation/devicetree/bindings/display/panel/samsung,atna33xc20.yaml b/Documentation/devicetree/bindings/display/panel/samsung,atna33xc20.yaml
index 87c601b..032f783e 100644
--- a/Documentation/devicetree/bindings/display/panel/samsung,atna33xc20.yaml
+++ b/Documentation/devicetree/bindings/display/panel/samsung,atna33xc20.yaml
@@ -18,12 +18,12 @@
# Samsung 13.3" FHD (1920x1080 pixels) eDP AMOLED panel
- const: samsung,atna33xc20
- items:
- - enum:
- # Samsung 14.5" WQXGA+ (2880x1800 pixels) eDP AMOLED panel
- - samsung,atna45af01
- # Samsung 14.5" 3K (2944x1840 pixels) eDP AMOLED panel
- - samsung,atna45dc02
- - const: samsung,atna33xc20
+ - enum:
+ # Samsung 14.5" WQXGA+ (2880x1800 pixels) eDP AMOLED panel
+ - samsung,atna45af01
+ # Samsung 14.5" 3K (2944x1840 pixels) eDP AMOLED panel
+ - samsung,atna45dc02
+ - const: samsung,atna33xc20
enable-gpios: true
port: true
diff --git a/Documentation/devicetree/bindings/display/panel/sony,td4353-jdi.yaml b/Documentation/devicetree/bindings/display/panel/sony,td4353-jdi.yaml
index 191b692..032a989 100644
--- a/Documentation/devicetree/bindings/display/panel/sony,td4353-jdi.yaml
+++ b/Documentation/devicetree/bindings/display/panel/sony,td4353-jdi.yaml
@@ -7,7 +7,7 @@
title: Sony TD4353 JDI 5 / 5.7" 2160x1080 MIPI-DSI Panel
maintainers:
- - Konrad Dybcio <konrad.dybcio@somainline.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
The Sony TD4353 JDI is a 5 (XZ2c) / 5.7 (XZ2) inch 2160x1080
diff --git a/Documentation/devicetree/bindings/eeprom/at25.yaml b/Documentation/devicetree/bindings/eeprom/at25.yaml
index 1715b0c..c31e5e7 100644
--- a/Documentation/devicetree/bindings/eeprom/at25.yaml
+++ b/Documentation/devicetree/bindings/eeprom/at25.yaml
@@ -28,6 +28,7 @@
- anvo,anv32e61w
- atmel,at25256B
- fujitsu,mb85rs1mt
+ - fujitsu,mb85rs256
- fujitsu,mb85rs64
- microchip,at25160bn
- microchip,25lc040
diff --git a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml
index 3797210..51d48d4 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml
+++ b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml
@@ -42,6 +42,7 @@
- focaltech,ft5426
- focaltech,ft5452
- focaltech,ft6236
+ - focaltech,ft8201
- focaltech,ft8719
reg:
diff --git a/Documentation/devicetree/bindings/interconnect/qcom,sc7280-rpmh.yaml b/Documentation/devicetree/bindings/interconnect/qcom,sc7280-rpmh.yaml
index 9fce720..78210791 100644
--- a/Documentation/devicetree/bindings/interconnect/qcom,sc7280-rpmh.yaml
+++ b/Documentation/devicetree/bindings/interconnect/qcom,sc7280-rpmh.yaml
@@ -8,7 +8,7 @@
maintainers:
- Bjorn Andersson <andersson@kernel.org>
- - Konrad Dybcio <konrad.dybcio@linaro.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
RPMh interconnect providers support system bandwidth requirements through
diff --git a/Documentation/devicetree/bindings/interconnect/qcom,sc8280xp-rpmh.yaml b/Documentation/devicetree/bindings/interconnect/qcom,sc8280xp-rpmh.yaml
index 6c2da03..100c686 100644
--- a/Documentation/devicetree/bindings/interconnect/qcom,sc8280xp-rpmh.yaml
+++ b/Documentation/devicetree/bindings/interconnect/qcom,sc8280xp-rpmh.yaml
@@ -8,7 +8,7 @@
maintainers:
- Bjorn Andersson <andersson@kernel.org>
- - Konrad Dybcio <konrad.dybcio@linaro.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
RPMh interconnect providers support system bandwidth requirements through
diff --git a/Documentation/devicetree/bindings/interconnect/qcom,sm8450-rpmh.yaml b/Documentation/devicetree/bindings/interconnect/qcom,sm8450-rpmh.yaml
index 3cff7e6..300640a 100644
--- a/Documentation/devicetree/bindings/interconnect/qcom,sm8450-rpmh.yaml
+++ b/Documentation/devicetree/bindings/interconnect/qcom,sm8450-rpmh.yaml
@@ -8,7 +8,7 @@
maintainers:
- Bjorn Andersson <andersson@kernel.org>
- - Konrad Dybcio <konrad.dybcio@linaro.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
RPMh interconnect providers support system bandwidth requirements through
diff --git a/Documentation/devicetree/bindings/iommu/qcom,iommu.yaml b/Documentation/devicetree/bindings/iommu/qcom,iommu.yaml
index 571e5746d..f8cebc9 100644
--- a/Documentation/devicetree/bindings/iommu/qcom,iommu.yaml
+++ b/Documentation/devicetree/bindings/iommu/qcom,iommu.yaml
@@ -7,7 +7,7 @@
title: Qualcomm Technologies legacy IOMMU implementations
maintainers:
- - Konrad Dybcio <konrad.dybcio@linaro.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
Qualcomm "B" family devices which are not compatible with arm-smmu have
diff --git a/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml b/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml
index a1b71b3..42f9843 100644
--- a/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml
+++ b/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml
@@ -38,6 +38,10 @@
managed: true
+ phys:
+ description: A reference to the SerDes lane(s)
+ maxItems: 1
+
required:
- reg
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml
index bd3cbb4..e75393b 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml
@@ -7,7 +7,7 @@
title: Qualcomm Technologies, Inc. MDM9607 TLMM block
maintainers:
- - Konrad Dybcio <konrad.dybcio@somainline.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description:
Top Level Mode Multiplexer pin controller in Qualcomm MDM9607 SoC.
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml
index a4771f8..b262af6 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml
@@ -7,7 +7,7 @@
title: Qualcomm Technologies, Inc. SM6350 TLMM block
maintainers:
- - Konrad Dybcio <konrad.dybcio@somainline.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description:
Top Level Mode Multiplexer pin controller in Qualcomm SM6350 SoC.
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml
index 047f82863f..c11af09 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml
@@ -7,7 +7,7 @@
title: Qualcomm Technologies, Inc. SM6375 TLMM block
maintainers:
- - Konrad Dybcio <konrad.dybcio@somainline.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description:
Top Level Mode Multiplexer pin controller in Qualcomm SM6375 SoC.
diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,rpm-proc.yaml b/Documentation/devicetree/bindings/remoteproc/qcom,rpm-proc.yaml
index 7afafde..61cf4fe 100644
--- a/Documentation/devicetree/bindings/remoteproc/qcom,rpm-proc.yaml
+++ b/Documentation/devicetree/bindings/remoteproc/qcom,rpm-proc.yaml
@@ -8,7 +8,7 @@
maintainers:
- Bjorn Andersson <andersson@kernel.org>
- - Konrad Dybcio <konrad.dybcio@linaro.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
- Stephan Gerhold <stephan@gerhold.net>
description: |
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,rpm-master-stats.yaml b/Documentation/devicetree/bindings/soc/qcom/qcom,rpm-master-stats.yaml
index 9410404..ad2dcc3 100644
--- a/Documentation/devicetree/bindings/soc/qcom/qcom,rpm-master-stats.yaml
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,rpm-master-stats.yaml
@@ -7,7 +7,7 @@
title: Qualcomm Technologies, Inc. (QTI) RPM Master Stats
maintainers:
- - Konrad Dybcio <konrad.dybcio@linaro.org>
+ - Konrad Dybcio <konradybcio@kernel.org>
description: |
The Qualcomm RPM (Resource Power Manager) architecture includes a concept
diff --git a/Documentation/devicetree/bindings/usb/microchip,usb2514.yaml b/Documentation/devicetree/bindings/usb/microchip,usb2514.yaml
index 245e8c3..b14e6f3 100644
--- a/Documentation/devicetree/bindings/usb/microchip,usb2514.yaml
+++ b/Documentation/devicetree/bindings/usb/microchip,usb2514.yaml
@@ -10,7 +10,7 @@
- Fabio Estevam <festevam@gmail.com>
allOf:
- - $ref: usb-hcd.yaml#
+ - $ref: usb-device.yaml#
properties:
compatible:
@@ -36,6 +36,13 @@
- compatible
- reg
+patternProperties:
+ "^.*@[0-9a-f]{1,2}$":
+ description: The hard wired USB devices
+ type: object
+ $ref: /schemas/usb/usb-device.yaml
+ additionalProperties: true
+
unevaluatedProperties: false
examples:
diff --git a/Documentation/filesystems/caching/fscache.rst b/Documentation/filesystems/caching/fscache.rst
index a74d7b0..de1f325 100644
--- a/Documentation/filesystems/caching/fscache.rst
+++ b/Documentation/filesystems/caching/fscache.rst
@@ -318,10 +318,10 @@
Debugging
=========
-If CONFIG_FSCACHE_DEBUG is enabled, the FS-Cache facility can have runtime
-debugging enabled by adjusting the value in::
+If CONFIG_NETFS_DEBUG is enabled, the FS-Cache facility and NETFS support can
+have runtime debugging enabled by adjusting the value in::
- /sys/module/fscache/parameters/debug
+ /sys/module/netfs/parameters/debug
This is a bitmask of debugging streams to enable:
@@ -343,6 +343,6 @@
The appropriate set of values should be OR'd together and the result written to
the control file. For example::
- echo $((1|8|512)) >/sys/module/fscache/parameters/debug
+ echo $((1|8|512)) >/sys/module/netfs/parameters/debug
will turn on all function entry debugging.
diff --git a/Documentation/filesystems/erofs.rst b/Documentation/filesystems/erofs.rst
index cc4626d..c293f8e3 100644
--- a/Documentation/filesystems/erofs.rst
+++ b/Documentation/filesystems/erofs.rst
@@ -75,7 +75,7 @@
- Support merging tail-end data into a special inode as fragments.
- - Support large folios for uncompressed files.
+ - Support large folios to make use of THPs (Transparent Hugepages);
- Support direct I/O on uncompressed files to avoid double caching for loop
devices;
diff --git a/Documentation/filesystems/smb/ksmbd.rst b/Documentation/filesystems/smb/ksmbd.rst
index 6b30e43..67cb68e 100644
--- a/Documentation/filesystems/smb/ksmbd.rst
+++ b/Documentation/filesystems/smb/ksmbd.rst
@@ -13,7 +13,7 @@
The subset of performance related operations belong in kernelspace and
the other subset which belong to operations which are not really related with
performance in userspace. So, DCE/RPC management that has historically resulted
-into number of buffer overflow issues and dangerous security bugs and user
+into a number of buffer overflow issues and dangerous security bugs and user
account management are implemented in user space as ksmbd.mountd.
File operations that are related with performance (open/read/write/close etc.)
in kernel space (ksmbd). This also allows for easier integration with VFS
@@ -24,8 +24,8 @@
When the server daemon is started, It starts up a forker thread
(ksmbd/interface name) at initialization time and open a dedicated port 445
-for listening to SMB requests. Whenever new clients make request, Forker
-thread will accept the client connection and fork a new thread for dedicated
+for listening to SMB requests. Whenever new clients make a request, the Forker
+thread will accept the client connection and fork a new thread for a dedicated
communication channel between the client and the server. It allows for parallel
processing of SMB requests(commands) from clients as well as allowing for new
clients to make new connections. Each instance is named ksmbd/1~n(port number)
@@ -34,12 +34,12 @@
currently DCE/RPC commands are identified to be handled through the user space.
To further utilize the linux kernel, it has been chosen to process the commands
as workitems and to be executed in the handlers of the ksmbd-io kworker threads.
-It allows for multiplexing of the handlers as the kernel take care of initiating
+It allows for multiplexing of the handlers as the kernel takes care of initiating
extra worker threads if the load is increased and vice versa, if the load is
-decreased it destroys the extra worker threads. So, after connection is
-established with client. Dedicated ksmbd/1..n(port number) takes complete
+decreased it destroys the extra worker threads. So, after the connection is
+established with the client. Dedicated ksmbd/1..n(port number) takes complete
ownership of receiving/parsing of SMB commands. Each received command is worked
-in parallel i.e., There can be multiple clients commands which are worked in
+in parallel i.e., there can be multiple client commands which are worked in
parallel. After receiving each command a separated kernel workitem is prepared
for each command which is further queued to be handled by ksmbd-io kworkers.
So, each SMB workitem is queued to the kworkers. This allows the benefit of load
@@ -49,9 +49,9 @@
ksmbd.mountd (user space daemon)
--------------------------------
-ksmbd.mountd is userspace process to, transfer user account and password that
+ksmbd.mountd is a userspace process to, transfer the user account and password that
are registered using ksmbd.adduser (part of utils for user space). Further it
-allows sharing information parameters that parsed from smb.conf to ksmbd in
+allows sharing information parameters that are parsed from smb.conf to ksmbd in
kernel. For the execution part it has a daemon which is continuously running
and connected to the kernel interface using netlink socket, it waits for the
requests (dcerpc and share/user info). It handles RPC calls (at a minimum few
@@ -124,7 +124,7 @@
1. Download ksmbd-tools(https://github.com/cifsd-team/ksmbd-tools/releases) and
compile them.
- - Refer README(https://github.com/cifsd-team/ksmbd-tools/blob/master/README.md)
+ - Refer to README(https://github.com/cifsd-team/ksmbd-tools/blob/master/README.md)
to know how to use ksmbd.mountd/adduser/addshare/control utils
$ ./autogen.sh
@@ -133,7 +133,7 @@
2. Create /usr/local/etc/ksmbd/ksmbd.conf file, add SMB share in ksmbd.conf file.
- - Refer ksmbd.conf.example in ksmbd-utils, See ksmbd.conf manpage
+ - Refer to ksmbd.conf.example in ksmbd-utils, See ksmbd.conf manpage
for details to configure shares.
$ man ksmbd.conf
@@ -145,7 +145,7 @@
$ man ksmbd.adduser
$ sudo ksmbd.adduser -a <Enter USERNAME for SMB share access>
-4. Insert ksmbd.ko module after build your kernel. No need to load module
+4. Insert the ksmbd.ko module after you build your kernel. No need to load the module
if ksmbd is built into the kernel.
- Set ksmbd in menuconfig(e.g. $ make menuconfig)
@@ -175,7 +175,7 @@
1. Enable all component prints
# sudo ksmbd.control -d "all"
-2. Enable one of components (smb, auth, vfs, oplock, ipc, conn, rdma)
+2. Enable one of the components (smb, auth, vfs, oplock, ipc, conn, rdma)
# sudo ksmbd.control -d "smb"
3. Show what prints are enabled.
diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst
index bb5c44f8..6dc66b4 100644
--- a/Documentation/kbuild/llvm.rst
+++ b/Documentation/kbuild/llvm.rst
@@ -126,7 +126,7 @@
``ccache`` can be used with ``clang`` to improve subsequent builds, (though
KBUILD_BUILD_TIMESTAMP_ should be set to a deterministic value between builds
-in order to avoid 100% cache misses, see Reproducible_builds_ for more info):
+in order to avoid 100% cache misses, see Reproducible_builds_ for more info)::
KBUILD_BUILD_TIMESTAMP='' make LLVM=1 CC="ccache clang"
diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst
index 04f6aa3..8e30c8f 100644
--- a/Documentation/process/coding-style.rst
+++ b/Documentation/process/coding-style.rst
@@ -629,18 +629,6 @@
* with beginning and ending almost-blank lines.
*/
-For files in net/ and drivers/net/ the preferred style for long (multi-line)
-comments is a little different.
-
-.. code-block:: c
-
- /* The preferred comment style for files in net/ and drivers/net
- * looks like this.
- *
- * It is nearly the same as the generally preferred comment style,
- * but there is no initial almost-blank line.
- */
-
It's also important to comment data, whether they are basic types or derived
types. To this end, use just one data declaration per line (no commas for
multiple data declarations). This leaves you room for a small comment on each
diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst
index fe86163..30d24ee 100644
--- a/Documentation/process/maintainer-netdev.rst
+++ b/Documentation/process/maintainer-netdev.rst
@@ -355,23 +355,6 @@
with better review coverage. Re-posting large series also increases the mailing
list traffic.
-Multi-line comments
-~~~~~~~~~~~~~~~~~~~
-
-Comment style convention is slightly different for networking and most of
-the tree. Instead of this::
-
- /*
- * foobar blah blah blah
- * another line of text
- */
-
-it is requested that you make it look like this::
-
- /* foobar blah blah blah
- * another line of text
- */
-
Local variable ordering ("reverse xmas tree", "RCS")
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 3393846..b3be874 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -2592,7 +2592,7 @@
0x6030 0000 0010 004a SPSR_ABT 64 spsr[KVM_SPSR_ABT]
0x6030 0000 0010 004c SPSR_UND 64 spsr[KVM_SPSR_UND]
0x6030 0000 0010 004e SPSR_IRQ 64 spsr[KVM_SPSR_IRQ]
- 0x6060 0000 0010 0050 SPSR_FIQ 64 spsr[KVM_SPSR_FIQ]
+ 0x6030 0000 0010 0050 SPSR_FIQ 64 spsr[KVM_SPSR_FIQ]
0x6040 0000 0010 0054 V0 128 fp_regs.vregs[0] [1]_
0x6040 0000 0010 0058 V1 128 fp_regs.vregs[1] [1]_
...
diff --git a/MAINTAINERS b/MAINTAINERS
index f328373..fe83ba7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1880,6 +1880,10 @@
F: drivers/iommu/arm/
F: drivers/iommu/io-pgtable-arm*
+ARM SMMU SVA SUPPORT
+R: Jean-Philippe Brucker <jean-philippe@linaro.org>
+F: drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+
ARM SUB-ARCHITECTURES
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
@@ -2535,8 +2539,7 @@
S: Supported
W: http://www.linux4sam.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/at91/linux.git
-F: arch/arm/boot/dts/microchip/at91*
-F: arch/arm/boot/dts/microchip/sama*
+F: arch/arm/boot/dts/microchip/
F: arch/arm/include/debug/at91.S
F: arch/arm/mach-at91/
F: drivers/memory/atmel*
@@ -2745,7 +2748,7 @@
ARM/QUALCOMM SUPPORT
M: Bjorn Andersson <andersson@kernel.org>
-M: Konrad Dybcio <konrad.dybcio@linaro.org>
+M: Konrad Dybcio <konradybcio@kernel.org>
L: linux-arm-msm@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/qcom/linux.git
@@ -3504,7 +3507,9 @@
W: http://linux-atm.sourceforge.net
F: drivers/atm/
F: include/linux/atm*
+F: include/linux/sonet.h
F: include/uapi/linux/atm*
+F: include/uapi/linux/sonet.h
ATMEL MACB ETHERNET DRIVER
M: Nicolas Ferre <nicolas.ferre@microchip.com>
@@ -7106,7 +7111,7 @@
DRM DRIVER for Qualcomm Adreno GPUs
M: Rob Clark <robdclark@gmail.com>
R: Sean Paul <sean@poorly.run>
-R: Konrad Dybcio <konrad.dybcio@linaro.org>
+R: Konrad Dybcio <konradybcio@kernel.org>
L: linux-arm-msm@vger.kernel.org
L: dri-devel@lists.freedesktop.org
L: freedreno@lists.freedesktop.org
@@ -10173,7 +10178,7 @@
F: drivers/infiniband/hw/hns/
HISILICON SAS Controller
-M: Xiang Chen <chenxiang66@hisilicon.com>
+M: Yihang Li <liyihang9@huawei.com>
S: Supported
W: http://www.hisilicon.com
F: Documentation/devicetree/bindings/scsi/hisilicon-sas.txt
@@ -11993,7 +11998,7 @@
JME NETWORK DRIVER
M: Guo-Fu Tseng <cooldavid@cooldavid.org>
L: netdev@vger.kernel.org
-S: Maintained
+S: Odd Fixes
F: drivers/net/ethernet/jme.*
JOURNALLING FLASH FILE SYSTEM V2 (JFFS2)
@@ -12165,7 +12170,7 @@
M: Chuck Lever <chuck.lever@oracle.com>
M: Jeff Layton <jlayton@kernel.org>
R: Neil Brown <neilb@suse.de>
-R: Olga Kornievskaia <kolga@netapp.com>
+R: Olga Kornievskaia <okorniev@redhat.com>
R: Dai Ngo <Dai.Ngo@oracle.com>
R: Tom Talpey <tom@talpey.com>
L: linux-nfs@vger.kernel.org
@@ -15877,15 +15882,19 @@
F: include/dt-bindings/net/
F: include/linux/cn_proc.h
F: include/linux/etherdevice.h
+F: include/linux/ethtool_netlink.h
F: include/linux/fcdevice.h
F: include/linux/fddidevice.h
F: include/linux/hippidevice.h
F: include/linux/if_*
F: include/linux/inetdevice.h
-F: include/linux/netdevice.h
+F: include/linux/netdev*
+F: include/linux/platform_data/wiznet.h
F: include/uapi/linux/cn_proc.h
+F: include/uapi/linux/ethtool_netlink.h
F: include/uapi/linux/if_*
-F: include/uapi/linux/netdevice.h
+F: include/uapi/linux/netdev*
+F: tools/testing/selftests/drivers/net/
X: drivers/net/wireless/
NETWORKING DRIVERS (WIRELESS)
@@ -15936,14 +15945,28 @@
F: include/linux/framer/framer.h
F: include/linux/in.h
F: include/linux/indirect_call_wrapper.h
+F: include/linux/inet.h
+F: include/linux/inet_diag.h
F: include/linux/net.h
-F: include/linux/netdevice.h
-F: include/linux/skbuff.h
+F: include/linux/netdev*
+F: include/linux/netlink.h
+F: include/linux/netpoll.h
+F: include/linux/rtnetlink.h
+F: include/linux/seq_file_net.h
+F: include/linux/skbuff*
F: include/net/
+F: include/uapi/linux/genetlink.h
+F: include/uapi/linux/hsr_netlink.h
F: include/uapi/linux/in.h
+F: include/uapi/linux/inet_diag.h
+F: include/uapi/linux/nbd-netlink.h
F: include/uapi/linux/net.h
F: include/uapi/linux/net_namespace.h
-F: include/uapi/linux/netdevice.h
+F: include/uapi/linux/netconf.h
+F: include/uapi/linux/netdev*
+F: include/uapi/linux/netlink.h
+F: include/uapi/linux/netlink_diag.h
+F: include/uapi/linux/rtnetlink.h
F: lib/net_utils.c
F: lib/random32.c
F: net/
@@ -17415,6 +17438,7 @@
L: linuxppc-dev@lists.ozlabs.org
L: linux-pci@vger.kernel.org
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L: imx@lists.linux.dev
S: Maintained
F: drivers/pci/controller/dwc/*layerscape*
@@ -17441,6 +17465,7 @@
M: Lucas Stach <l.stach@pengutronix.de>
L: linux-pci@vger.kernel.org
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L: imx@lists.linux.dev
S: Maintained
F: Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-common.yaml
F: Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.yaml
@@ -17619,6 +17644,7 @@
PCI NATIVE HOST BRIDGE AND ENDPOINT DRIVERS
M: Lorenzo Pieralisi <lpieralisi@kernel.org>
M: Krzysztof Wilczyński <kw@linux.com>
+R: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
R: Rob Herring <robh@kernel.org>
L: linux-pci@vger.kernel.org
S: Supported
@@ -18525,7 +18551,6 @@
QCOM AUDIO (ASoC) DRIVERS
M: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
-M: Banajit Goswami <bgoswami@quicinc.com>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
L: linux-arm-msm@vger.kernel.org
S: Supported
@@ -18774,7 +18799,7 @@
QUALCOMM CORE POWER REDUCTION (CPR) AVS DRIVER
M: Bjorn Andersson <andersson@kernel.org>
-M: Konrad Dybcio <konrad.dybcio@linaro.org>
+M: Konrad Dybcio <konradybcio@kernel.org>
L: linux-pm@vger.kernel.org
L: linux-arm-msm@vger.kernel.org
S: Maintained
@@ -20354,6 +20379,7 @@
F: drivers/scsi/
F: drivers/ufs/
F: include/scsi/
+F: include/uapi/scsi/
SCSI TAPE DRIVER
M: Kai Mäkisara <Kai.Makisara@kolumbus.fi>
@@ -21054,6 +21080,7 @@
M: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
S: Maintained
F: Documentation/networking/timestamping.rst
+F: include/linux/net_tstamp.h
F: include/uapi/linux/net_tstamp.h
F: tools/testing/selftests/net/so_txtime.c
@@ -23821,10 +23848,8 @@
F: include/uapi/linux/uvcvideo.h
USB WEBCAM GADGET
-M: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
-M: Daniel Scally <dan.scally@ideasonboard.com>
L: linux-usb@vger.kernel.org
-S: Maintained
+S: Orphan
F: drivers/usb/gadget/function/*uvc*
F: drivers/usb/gadget/legacy/webcam.c
F: include/uapi/linux/usb/g_uvc.h
diff --git a/Makefile b/Makefile
index 0a364e3..d57cfc6 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 11
SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc6
NAME = Baby Opossum Posse
# *DOCUMENTATION*
@@ -1963,7 +1963,7 @@
# Protocol).
PHONY += rust-analyzer
rust-analyzer:
- $(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh
+ +$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh
$(Q)$(MAKE) $(build)=rust $@
# Script to generate missing namespace dependencies
@@ -1980,7 +1980,7 @@
quiet_cmd_gen_compile_commands = GEN $@
cmd_gen_compile_commands = $(PYTHON3) $< -a $(AR) -o $@ $(filter-out $<, $(real-prereqs))
-$(extmod_prefix)compile_commands.json: scripts/clang-tools/gen_compile_commands.py \
+$(extmod_prefix)compile_commands.json: $(srctree)/scripts/clang-tools/gen_compile_commands.py \
$(if $(KBUILD_EXTMOD),, vmlinux.a $(KBUILD_VMLINUX_LIBS)) \
$(if $(CONFIG_MODULES), $(MODORDER)) FORCE
$(call if_changed,gen_compile_commands)
diff --git a/arch/arm/boot/dts/nxp/imx/imx6dl-yapp43-common.dtsi b/arch/arm/boot/dts/nxp/imx/imx6dl-yapp43-common.dtsi
index 52a0f6e..bcf4d9c 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6dl-yapp43-common.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6dl-yapp43-common.dtsi
@@ -274,24 +274,24 @@ leds: led-controller@30 {
led@0 {
chan-name = "R";
- led-cur = /bits/ 8 <0x20>;
- max-cur = /bits/ 8 <0x60>;
+ led-cur = /bits/ 8 <0x6e>;
+ max-cur = /bits/ 8 <0xc8>;
reg = <0>;
color = <LED_COLOR_ID_RED>;
};
led@1 {
chan-name = "G";
- led-cur = /bits/ 8 <0x20>;
- max-cur = /bits/ 8 <0x60>;
+ led-cur = /bits/ 8 <0xbe>;
+ max-cur = /bits/ 8 <0xc8>;
reg = <1>;
color = <LED_COLOR_ID_GREEN>;
};
led@2 {
chan-name = "B";
- led-cur = /bits/ 8 <0x20>;
- max-cur = /bits/ 8 <0x60>;
+ led-cur = /bits/ 8 <0xbe>;
+ max-cur = /bits/ 8 <0xc8>;
reg = <2>;
color = <LED_COLOR_ID_BLUE>;
};
diff --git a/arch/arm/boot/dts/ti/omap/omap3-n900.dts b/arch/arm/boot/dts/ti/omap/omap3-n900.dts
index 07c5b96..4bde334 100644
--- a/arch/arm/boot/dts/ti/omap/omap3-n900.dts
+++ b/arch/arm/boot/dts/ti/omap/omap3-n900.dts
@@ -781,7 +781,7 @@ accelerometer@1d {
mount-matrix = "-1", "0", "0",
"0", "1", "0",
- "0", "0", "1";
+ "0", "0", "-1";
};
cam1: camera@3e {
diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c
index c30df10..9f7454b 100644
--- a/arch/arm/mach-rpc/ecard.c
+++ b/arch/arm/mach-rpc/ecard.c
@@ -1109,7 +1109,7 @@ void ecard_remove_driver(struct ecard_driver *drv)
driver_unregister(&drv->drv);
}
-static int ecard_match(struct device *_dev, struct device_driver *_drv)
+static int ecard_match(struct device *_dev, const struct device_driver *_drv)
{
struct expansion_card *ec = ECARD_DEV(_dev);
struct ecard_driver *drv = ECARD_DRV(_drv);
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
index 6b6e3ee..acf2933 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
@@ -175,7 +175,7 @@ ddr-ctrler-crit {
};
};
- core-cluster-thermal {
+ cluster-thermal {
polling-delay-passive = <1000>;
polling-delay = <5000>;
thermal-sensors = <&tmu 1>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
index 17f4e31..ab4c919 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
@@ -214,7 +214,7 @@ fman-crit {
};
};
- core-cluster-thermal {
+ cluster-thermal {
polling-delay-passive = <1000>;
polling-delay = <5000>;
thermal-sensors = <&tmu 3>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
index 200e526..5501986 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
@@ -182,7 +182,7 @@ fman-crit {
};
};
- core-cluster-thermal {
+ cluster-thermal {
polling-delay-passive = <1000>;
polling-delay = <5000>;
thermal-sensors = <&tmu 3>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
index 8ce4b6a..e3a7db2 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
@@ -131,7 +131,7 @@ its: msi-controller@6020000 {
};
thermal-zones {
- core-cluster-thermal {
+ cluster-thermal {
polling-delay-passive = <1000>;
polling-delay = <5000>;
thermal-sensors = <&tmu 0>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
index bde89de..1b306d6 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
@@ -122,7 +122,7 @@ ddr-ctrler3-crit {
};
};
- core-cluster1-thermal {
+ cluster1-thermal {
polling-delay-passive = <1000>;
polling-delay = <5000>;
thermal-sensors = <&tmu 4>;
@@ -151,7 +151,7 @@ map0 {
};
};
- core-cluster2-thermal {
+ cluster2-thermal {
polling-delay-passive = <1000>;
polling-delay = <5000>;
thermal-sensors = <&tmu 5>;
@@ -180,7 +180,7 @@ map0 {
};
};
- core-cluster3-thermal {
+ cluster3-thermal {
polling-delay-passive = <1000>;
polling-delay = <5000>;
thermal-sensors = <&tmu 6>;
@@ -209,7 +209,7 @@ map0 {
};
};
- core-cluster4-thermal {
+ cluster4-thermal {
polling-delay-passive = <1000>;
polling-delay = <5000>;
thermal-sensors = <&tmu 7>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
index 26c7ca3..bd75a65 100644
--- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
@@ -492,7 +492,7 @@ map0 {
};
};
- ddr-cluster5-thermal {
+ ddr-ctrl5-thermal {
polling-delay-passive = <1000>;
polling-delay = <5000>;
thermal-sensors = <&tmu 1>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l-rs232-rs232.dtso b/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l-rs232-rs232.dtso
index bf3e046..353ace3 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l-rs232-rs232.dtso
+++ b/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l-rs232-rs232.dtso
@@ -21,7 +21,7 @@
&gpio3 {
pinctrl-names = "default";
- pinctrcl-0 = <&pinctrl_gpio3_hog>;
+ pinctrl-0 = <&pinctrl_gpio3_hog>;
uart4_rs485_en {
gpio-hog;
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l-rs232-rs485.dtso b/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l-rs232-rs485.dtso
index f4448cd..8a75d67 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l-rs232-rs485.dtso
+++ b/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l-rs232-rs485.dtso
@@ -22,7 +22,7 @@
&gpio3 {
pinctrl-names = "default";
- pinctrcl-0 = <&pinctrl_gpio3_hog>;
+ pinctrl-0 = <&pinctrl_gpio3_hog>;
uart4_rs485_en {
gpio-hog;
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
index 17e2c19..cc9b81d 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
@@ -211,13 +211,12 @@ sound-wm8962 {
simple-audio-card,cpu {
sound-dai = <&sai3>;
+ frame-master;
+ bitclock-master;
};
simple-audio-card,codec {
sound-dai = <&wm8962>;
- clocks = <&clk IMX8MP_CLK_IPP_DO_CLKO1>;
- frame-master;
- bitclock-master;
};
};
};
@@ -507,10 +506,9 @@ &pcie_phy {
&sai3 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_sai3>;
- assigned-clocks = <&clk IMX8MP_CLK_SAI3>,
- <&clk IMX8MP_AUDIO_PLL2> ;
- assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL2_OUT>;
- assigned-clock-rates = <12288000>, <361267200>;
+ assigned-clocks = <&clk IMX8MP_CLK_SAI3>;
+ assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL1_OUT>;
+ assigned-clock-rates = <12288000>;
fsl,sai-mclk-direction-output;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts
index da8f19a..e2ee9f5 100644
--- a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts
+++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts
@@ -499,7 +499,7 @@ &usdhc2 {
pinctrl-0 = <&pinctrl_usdhc2_hs>, <&pinctrl_usdhc2_gpio>;
pinctrl-1 = <&pinctrl_usdhc2_uhs>, <&pinctrl_usdhc2_gpio>;
pinctrl-2 = <&pinctrl_usdhc2_uhs>, <&pinctrl_usdhc2_gpio>;
- cd-gpios = <&gpio3 00 GPIO_ACTIVE_LOW>;
+ cd-gpios = <&gpio3 0 GPIO_ACTIVE_LOW>;
vmmc-supply = <®_usdhc2_vmmc>;
bus-width = <4>;
no-sdio;
diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
index edbd8ca..72a9a5d 100644
--- a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
@@ -19,7 +19,7 @@ reserved-memory {
linux,cma {
compatible = "shared-dma-pool";
reusable;
- alloc-ranges = <0 0x60000000 0 0x40000000>;
+ alloc-ranges = <0 0x80000000 0 0x40000000>;
size = <0 0x10000000>;
linux,cma-default;
};
@@ -156,6 +156,7 @@ &usdhc1 {
&wdog3 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_wdog>;
+ fsl,ext-reset-output;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi
index 4a3f4235..a099302 100644
--- a/arch/arm64/boot/dts/freescale/imx93.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx93.dtsi
@@ -1105,7 +1105,7 @@ eqos: ethernet@428a0000 {
<&clk IMX93_CLK_SYS_PLL_PFD0_DIV2>;
assigned-clock-rates = <100000000>, <250000000>;
intf_mode = <&wakeupmix_gpr 0x28>;
- snps,clk-csr = <0>;
+ snps,clk-csr = <6>;
nvmem-cells = <ð_mac2>;
nvmem-cell-names = "mac-address";
status = "disabled";
diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi
index 1bbf9a0..425272a 100644
--- a/arch/arm64/boot/dts/freescale/imx95.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx95.dtsi
@@ -27,7 +27,7 @@ A55_0: cpu@0 {
reg = <0x0>;
enable-method = "psci";
#cooling-cells = <2>;
- power-domains = <&scmi_devpd IMX95_PERF_A55>;
+ power-domains = <&scmi_perf IMX95_PERF_A55>;
power-domain-names = "perf";
i-cache-size = <32768>;
i-cache-line-size = <64>;
@@ -44,7 +44,7 @@ A55_1: cpu@100 {
reg = <0x100>;
enable-method = "psci";
#cooling-cells = <2>;
- power-domains = <&scmi_devpd IMX95_PERF_A55>;
+ power-domains = <&scmi_perf IMX95_PERF_A55>;
power-domain-names = "perf";
i-cache-size = <32768>;
i-cache-line-size = <64>;
@@ -61,7 +61,7 @@ A55_2: cpu@200 {
reg = <0x200>;
enable-method = "psci";
#cooling-cells = <2>;
- power-domains = <&scmi_devpd IMX95_PERF_A55>;
+ power-domains = <&scmi_perf IMX95_PERF_A55>;
power-domain-names = "perf";
i-cache-size = <32768>;
i-cache-line-size = <64>;
@@ -78,7 +78,7 @@ A55_3: cpu@300 {
reg = <0x300>;
enable-method = "psci";
#cooling-cells = <2>;
- power-domains = <&scmi_devpd IMX95_PERF_A55>;
+ power-domains = <&scmi_perf IMX95_PERF_A55>;
power-domain-names = "perf";
i-cache-size = <32768>;
i-cache-line-size = <64>;
@@ -93,7 +93,7 @@ A55_4: cpu@400 {
device_type = "cpu";
compatible = "arm,cortex-a55";
reg = <0x400>;
- power-domains = <&scmi_devpd IMX95_PERF_A55>;
+ power-domains = <&scmi_perf IMX95_PERF_A55>;
power-domain-names = "perf";
enable-method = "psci";
#cooling-cells = <2>;
@@ -110,7 +110,7 @@ A55_5: cpu@500 {
device_type = "cpu";
compatible = "arm,cortex-a55";
reg = <0x500>;
- power-domains = <&scmi_devpd IMX95_PERF_A55>;
+ power-domains = <&scmi_perf IMX95_PERF_A55>;
power-domain-names = "perf";
enable-method = "psci";
#cooling-cells = <2>;
@@ -187,7 +187,7 @@ l3_cache: l3-cache {
compatible = "cache";
cache-size = <524288>;
cache-line-size = <64>;
- cache-sets = <1024>;
+ cache-sets = <512>;
cache-level = <3>;
cache-unified;
};
diff --git a/arch/arm64/boot/dts/qcom/ipq5332.dtsi b/arch/arm64/boot/dts/qcom/ipq5332.dtsi
index 57365658..0a74ed4 100644
--- a/arch/arm64/boot/dts/qcom/ipq5332.dtsi
+++ b/arch/arm64/boot/dts/qcom/ipq5332.dtsi
@@ -320,8 +320,8 @@ usb: usb@8af8800 {
reg = <0x08af8800 0x400>;
interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>,
- <GIC_SPI 53 IRQ_TYPE_EDGE_BOTH>,
- <GIC_SPI 52 IRQ_TYPE_EDGE_BOTH>;
+ <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "pwr_event",
"dp_hs_phy_irq",
"dm_hs_phy_irq";
diff --git a/arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts b/arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts
index 7fb980f..9caa14d 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts
+++ b/arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts
@@ -278,6 +278,13 @@ regulators-6 {
vdd-l3-supply = <&vreg_s1f_0p7>;
vdd-s1-supply = <&vph_pwr>;
vdd-s2-supply = <&vph_pwr>;
+
+ vreg_l3i_0p8: ldo3 {
+ regulator-name = "vreg_l3i_0p8";
+ regulator-min-microvolt = <880000>;
+ regulator-max-microvolt = <920000>;
+ regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+ };
};
regulators-7 {
@@ -423,11 +430,17 @@ &mdss_dp3_phy {
};
&pcie4 {
+ perst-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
+ wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
+
+ pinctrl-0 = <&pcie4_default>;
+ pinctrl-names = "default";
+
status = "okay";
};
&pcie4_phy {
- vdda-phy-supply = <&vreg_l3j_0p8>;
+ vdda-phy-supply = <&vreg_l3i_0p8>;
vdda-pll-supply = <&vreg_l3e_1p2>;
status = "okay";
@@ -517,7 +530,30 @@ nvme_reg_en: nvme-reg-en-state {
bias-disable;
};
- pcie6a_default: pcie2a-default-state {
+ pcie4_default: pcie4-default-state {
+ clkreq-n-pins {
+ pins = "gpio147";
+ function = "pcie4_clk";
+ drive-strength = <2>;
+ bias-pull-up;
+ };
+
+ perst-n-pins {
+ pins = "gpio146";
+ function = "gpio";
+ drive-strength = <2>;
+ bias-disable;
+ };
+
+ wake-n-pins {
+ pins = "gpio148";
+ function = "gpio";
+ drive-strength = <2>;
+ bias-pull-up;
+ };
+ };
+
+ pcie6a_default: pcie6a-default-state {
clkreq-n-pins {
pins = "gpio153";
function = "pcie6a_clk";
@@ -529,7 +565,7 @@ perst-n-pins {
pins = "gpio152";
function = "gpio";
drive-strength = <2>;
- bias-pull-down;
+ bias-disable;
};
wake-n-pins {
diff --git a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
index 6152bcd..e17ab82 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
+++ b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
@@ -268,7 +268,6 @@ vreg_edp_3p3: regulator-edp-3p3 {
pinctrl-0 = <&edp_reg_en>;
pinctrl-names = "default";
- regulator-always-on;
regulator-boot-on;
};
@@ -637,6 +636,14 @@ vreg_l3j_0p8: ldo3 {
};
};
+&gpu {
+ status = "okay";
+
+ zap-shader {
+ firmware-name = "qcom/x1e80100/gen70500_zap.mbn";
+ };
+};
+
&i2c0 {
clock-frequency = <400000>;
@@ -724,9 +731,13 @@ &mdss_dp3 {
aux-bus {
panel {
- compatible = "edp-panel";
+ compatible = "samsung,atna45af01", "samsung,atna33xc20";
+ enable-gpios = <&pmc8380_3_gpios 4 GPIO_ACTIVE_HIGH>;
power-supply = <&vreg_edp_3p3>;
+ pinctrl-0 = <&edp_bl_en>;
+ pinctrl-names = "default";
+
port {
edp_panel_in: endpoint {
remote-endpoint = <&mdss_dp3_out>;
@@ -756,11 +767,17 @@ &mdss_dp3_phy {
};
&pcie4 {
+ perst-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
+ wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
+
+ pinctrl-0 = <&pcie4_default>;
+ pinctrl-names = "default";
+
status = "okay";
};
&pcie4_phy {
- vdda-phy-supply = <&vreg_l3j_0p8>;
+ vdda-phy-supply = <&vreg_l3i_0p8>;
vdda-pll-supply = <&vreg_l3e_1p2>;
status = "okay";
@@ -785,6 +802,16 @@ &pcie6a_phy {
status = "okay";
};
+&pmc8380_3_gpios {
+ edp_bl_en: edp-bl-en-state {
+ pins = "gpio4";
+ function = "normal";
+ power-source = <1>; /* 1.8V */
+ input-disable;
+ output-enable;
+ };
+};
+
&qupv3_0 {
status = "okay";
};
@@ -931,7 +958,30 @@ nvme_reg_en: nvme-reg-en-state {
bias-disable;
};
- pcie6a_default: pcie2a-default-state {
+ pcie4_default: pcie4-default-state {
+ clkreq-n-pins {
+ pins = "gpio147";
+ function = "pcie4_clk";
+ drive-strength = <2>;
+ bias-pull-up;
+ };
+
+ perst-n-pins {
+ pins = "gpio146";
+ function = "gpio";
+ drive-strength = <2>;
+ bias-disable;
+ };
+
+ wake-n-pins {
+ pins = "gpio148";
+ function = "gpio";
+ drive-strength = <2>;
+ bias-pull-up;
+ };
+ };
+
+ pcie6a_default: pcie6a-default-state {
clkreq-n-pins {
pins = "gpio153";
function = "pcie6a_clk";
@@ -943,15 +993,15 @@ perst-n-pins {
pins = "gpio152";
function = "gpio";
drive-strength = <2>;
- bias-pull-down;
+ bias-disable;
};
wake-n-pins {
- pins = "gpio154";
- function = "gpio";
- drive-strength = <2>;
- bias-pull-up;
- };
+ pins = "gpio154";
+ function = "gpio";
+ drive-strength = <2>;
+ bias-pull-up;
+ };
};
tpad_default: tpad-default-state {
diff --git a/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts b/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts
index fbff558..1943bdb 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts
+++ b/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts
@@ -625,16 +625,31 @@ &mdss_dp3_phy {
};
&pcie4 {
+ perst-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
+ wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
+
+ pinctrl-0 = <&pcie4_default>;
+ pinctrl-names = "default";
+
status = "okay";
};
&pcie4_phy {
- vdda-phy-supply = <&vreg_l3j_0p8>;
+ vdda-phy-supply = <&vreg_l3i_0p8>;
vdda-pll-supply = <&vreg_l3e_1p2>;
status = "okay";
};
+&pcie4_port0 {
+ wifi@0 {
+ compatible = "pci17cb,1107";
+ reg = <0x10000 0x0 0x0 0x0 0x0>;
+
+ qcom,ath12k-calibration-variant = "LES790";
+ };
+};
+
&pcie6a {
perst-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
@@ -782,7 +797,30 @@ nvme_reg_en: nvme-reg-en-state {
bias-disable;
};
- pcie6a_default: pcie2a-default-state {
+ pcie4_default: pcie4-default-state {
+ clkreq-n-pins {
+ pins = "gpio147";
+ function = "pcie4_clk";
+ drive-strength = <2>;
+ bias-pull-up;
+ };
+
+ perst-n-pins {
+ pins = "gpio146";
+ function = "gpio";
+ drive-strength = <2>;
+ bias-disable;
+ };
+
+ wake-n-pins {
+ pins = "gpio148";
+ function = "gpio";
+ drive-strength = <2>;
+ bias-pull-up;
+ };
+ };
+
+ pcie6a_default: pcie6a-default-state {
clkreq-n-pins {
pins = "gpio153";
function = "pcie6a_clk";
@@ -794,15 +832,15 @@ perst-n-pins {
pins = "gpio152";
function = "gpio";
drive-strength = <2>;
- bias-pull-down;
+ bias-disable;
};
wake-n-pins {
- pins = "gpio154";
- function = "gpio";
- drive-strength = <2>;
- bias-pull-up;
- };
+ pins = "gpio154";
+ function = "gpio";
+ drive-strength = <2>;
+ bias-pull-up;
+ };
};
tpad_default: tpad-default-state {
diff --git a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
index 72a4f41..8098e67 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
+++ b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
@@ -606,6 +606,14 @@ vreg_l3j_0p8: ldo3 {
};
};
+&gpu {
+ status = "okay";
+
+ zap-shader {
+ firmware-name = "qcom/x1e80100/gen70500_zap.mbn";
+ };
+};
+
&lpass_tlmm {
spkr_01_sd_n_active: spkr-01-sd-n-active-state {
pins = "gpio12";
@@ -660,11 +668,17 @@ &mdss_dp3_phy {
};
&pcie4 {
+ perst-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
+ wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
+
+ pinctrl-0 = <&pcie4_default>;
+ pinctrl-names = "default";
+
status = "okay";
};
&pcie4_phy {
- vdda-phy-supply = <&vreg_l3j_0p8>;
+ vdda-phy-supply = <&vreg_l3i_0p8>;
vdda-pll-supply = <&vreg_l3e_1p2>;
status = "okay";
@@ -804,7 +818,30 @@ nvme_reg_en: nvme-reg-en-state {
bias-disable;
};
- pcie6a_default: pcie2a-default-state {
+ pcie4_default: pcie4-default-state {
+ clkreq-n-pins {
+ pins = "gpio147";
+ function = "pcie4_clk";
+ drive-strength = <2>;
+ bias-pull-up;
+ };
+
+ perst-n-pins {
+ pins = "gpio146";
+ function = "gpio";
+ drive-strength = <2>;
+ bias-disable;
+ };
+
+ wake-n-pins {
+ pins = "gpio148";
+ function = "gpio";
+ drive-strength = <2>;
+ bias-pull-up;
+ };
+ };
+
+ pcie6a_default: pcie6a-default-state {
clkreq-n-pins {
pins = "gpio153";
function = "pcie6a_clk";
@@ -816,15 +853,15 @@ perst-n-pins {
pins = "gpio152";
function = "gpio";
drive-strength = <2>;
- bias-pull-down;
+ bias-disable;
};
wake-n-pins {
- pins = "gpio154";
- function = "gpio";
- drive-strength = <2>;
- bias-pull-up;
- };
+ pins = "gpio154";
+ function = "gpio";
+ drive-strength = <2>;
+ bias-pull-up;
+ };
};
wcd_default: wcd-reset-n-active-state {
diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi
index 7bca5fc..cd732ef 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi
+++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi
@@ -2901,7 +2901,7 @@ pcie6a: pci@1bf8000 {
dma-coherent;
- linux,pci-domain = <7>;
+ linux,pci-domain = <6>;
num-lanes = <2>;
interrupts = <GIC_SPI 773 IRQ_TYPE_LEVEL_HIGH>,
@@ -2959,6 +2959,7 @@ &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
"link_down";
power-domains = <&gcc GCC_PCIE_6A_GDSC>;
+ required-opps = <&rpmhpd_opp_nom>;
phys = <&pcie6a_phy>;
phy-names = "pciephy";
@@ -3022,7 +3023,7 @@ pcie4: pci@1c08000 {
dma-coherent;
- linux,pci-domain = <5>;
+ linux,pci-domain = <4>;
num-lanes = <2>;
interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>,
@@ -3080,11 +3081,22 @@ &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
"link_down";
power-domains = <&gcc GCC_PCIE_4_GDSC>;
+ required-opps = <&rpmhpd_opp_nom>;
phys = <&pcie4_phy>;
phy-names = "pciephy";
status = "disabled";
+
+ pcie4_port0: pcie@0 {
+ device_type = "pci";
+ reg = <0x0 0x0 0x0 0x0 0x0>;
+ bus-range = <0x01 0xff>;
+
+ #address-cells = <3>;
+ #size-cells = <2>;
+ ranges;
+ };
};
pcie4_phy: phy@1c0e000 {
@@ -3155,9 +3167,10 @@ gpu: gpu@3d00000 {
interconnects = <&gem_noc MASTER_GFX3D 0 &mc_virt SLAVE_EBI1 0>;
interconnect-names = "gfx-mem";
+ status = "disabled";
+
zap-shader {
memory-region = <&gpu_microcode_mem>;
- firmware-name = "qcom/gen70500_zap.mbn";
};
gpu_opp_table: opp-table {
@@ -3288,7 +3301,7 @@ adreno_smmu: iommu@3da0000 {
reg = <0x0 0x03da0000 0x0 0x40000>;
#iommu-cells = <2>;
#global-interrupts = <1>;
- interrupts = <GIC_SPI 673 IRQ_TYPE_LEVEL_HIGH>,
+ interrupts = <GIC_SPI 674 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 678 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 679 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 680 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 7d32fca..362df93 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -887,6 +887,7 @@
CONFIG_DRM_PANEL_MANTIX_MLAF057WE51=m
CONFIG_DRM_PANEL_NOVATEK_NT36672E=m
CONFIG_DRM_PANEL_RAYDIUM_RM67191=m
+CONFIG_DRM_PANEL_SAMSUNG_ATNA33XC20=m
CONFIG_DRM_PANEL_SITRONIX_ST7703=m
CONFIG_DRM_PANEL_TRULY_NT35597_WQXGA=m
CONFIG_DRM_PANEL_VISIONOX_VTDR6130=m
diff --git a/arch/arm64/include/asm/kvm_ptrauth.h b/arch/arm64/include/asm/kvm_ptrauth.h
index d81bac2..6199c9f 100644
--- a/arch/arm64/include/asm/kvm_ptrauth.h
+++ b/arch/arm64/include/asm/kvm_ptrauth.h
@@ -104,7 +104,7 @@ alternative_else_nop_endif
#define __ptrauth_save_key(ctxt, key) \
do { \
- u64 __val; \
+ u64 __val; \
__val = read_sysreg_s(SYS_ ## key ## KEYLO_EL1); \
ctxt_sys_reg(ctxt, key ## KEYLO_EL1) = __val; \
__val = read_sysreg_s(SYS_ ## key ## KEYHI_EL1); \
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 28f665e..1aa4ecb 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -188,7 +188,7 @@ static inline void __user *__uaccess_mask_ptr(const void __user *ptr)
#define __get_mem_asm(load, reg, x, addr, label, type) \
asm_goto_output( \
"1: " load " " reg "0, [%1]\n" \
- _ASM_EXTABLE_##type##ACCESS_ERR(1b, %l2, %w0) \
+ _ASM_EXTABLE_##type##ACCESS(1b, %l2) \
: "=r" (x) \
: "r" (addr) : : label)
#else
diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c
index 0c036a9..2465f29 100644
--- a/arch/arm64/kernel/acpi_numa.c
+++ b/arch/arm64/kernel/acpi_numa.c
@@ -27,7 +27,7 @@
#include <asm/numa.h>
-static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE };
+static int acpi_early_node_map[NR_CPUS] __initdata = { [0 ... NR_CPUS - 1] = NUMA_NO_NODE };
int __init acpi_numa_get_nid(unsigned int cpu)
{
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index a096e24..b22d28e 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -355,9 +355,6 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
smp_init_cpus();
smp_build_mpidr_hash();
- /* Init percpu seeds for random tags after cpus are set up. */
- kasan_init_sw_tags();
-
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
/*
* Make sure init_thread_info.ttbr0 always generates translation
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 5e18fbc..f01f0fd 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -467,6 +467,8 @@ void __init smp_prepare_boot_cpu(void)
init_gic_priority_masking();
kasan_init_hw_tags();
+ /* Init percpu seeds for random tags after cpus are set up. */
+ kasan_init_sw_tags();
}
/*
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 58f0937..8304eb3 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -19,6 +19,7 @@
menuconfig KVM
bool "Kernel-based Virtual Machine (KVM) support"
+ depends on AS_HAS_ARMV8_4
select KVM_COMMON
select KVM_GENERIC_HARDWARE_ENABLING
select KVM_GENERIC_MMU_NOTIFIER
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index a649722..86a629a 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -10,6 +10,9 @@
obj-$(CONFIG_KVM) += kvm.o
obj-$(CONFIG_KVM) += hyp/
+CFLAGS_sys_regs.o += -Wno-override-init
+CFLAGS_handle_exit.o += -Wno-override-init
+
kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \
inject_fault.o va_layout.o handle_exit.o \
guest.o debug.o reset.o sys_regs.o stacktrace.o \
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index a7ca776..9bef763 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -164,6 +164,7 @@ static int kvm_arm_default_max_vcpus(void)
/**
* kvm_arch_init_vm - initializes a VM data structure
* @kvm: pointer to the KVM struct
+ * @type: kvm device type
*/
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
@@ -521,10 +522,10 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
static void vcpu_set_pauth_traps(struct kvm_vcpu *vcpu)
{
- if (vcpu_has_ptrauth(vcpu)) {
+ if (vcpu_has_ptrauth(vcpu) && !is_protected_kvm_enabled()) {
/*
- * Either we're running running an L2 guest, and the API/APK
- * bits come from L1's HCR_EL2, or API/APK are both set.
+ * Either we're running an L2 guest, and the API/APK bits come
+ * from L1's HCR_EL2, or API/APK are both set.
*/
if (unlikely(vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))) {
u64 val;
@@ -541,16 +542,10 @@ static void vcpu_set_pauth_traps(struct kvm_vcpu *vcpu)
* Save the host keys if there is any chance for the guest
* to use pauth, as the entry code will reload the guest
* keys in that case.
- * Protected mode is the exception to that rule, as the
- * entry into the EL2 code eagerly switch back and forth
- * between host and hyp keys (and kvm_hyp_ctxt is out of
- * reach anyway).
*/
- if (is_protected_kvm_enabled())
- return;
-
if (vcpu->arch.hcr_el2 & (HCR_API | HCR_APK)) {
struct kvm_cpu_context *ctxt;
+
ctxt = this_cpu_ptr_hyp_sym(kvm_hyp_ctxt);
ptrauth_save_keys(ctxt);
}
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index f59ccfe..37ff87d 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -27,7 +27,6 @@
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_nested.h>
-#include <asm/kvm_ptrauth.h>
#include <asm/fpsimd.h>
#include <asm/debug-monitors.h>
#include <asm/processor.h>
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 782b34b..b43426a 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -20,6 +20,8 @@
lib-objs := clear_page.o copy_page.o memcpy.o memset.o
lib-objs := $(addprefix ../../../lib/, $(lib-objs))
+CFLAGS_switch.nvhe.o += -Wno-override-init
+
hyp-obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o \
hyp-main.o hyp-smp.o psci-relay.o early_alloc.o page_alloc.o \
cache.o setup.o mm.o mem_protect.o sys_regs.o pkvm.o stacktrace.o ffa.o
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 6af179c..8f5c56d 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -173,9 +173,8 @@ static void __pmu_switch_to_host(struct kvm_vcpu *vcpu)
static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code)
{
/*
- * Make sure we handle the exit for workarounds and ptrauth
- * before the pKVM handling, as the latter could decide to
- * UNDEF.
+ * Make sure we handle the exit for workarounds before the pKVM
+ * handling, as the latter could decide to UNDEF.
*/
return (kvm_hyp_handle_sysreg(vcpu, exit_code) ||
kvm_handle_pvm_sysreg(vcpu, exit_code));
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index 3b9e546..afc4aed 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -6,6 +6,8 @@
asflags-y := -D__KVM_VHE_HYPERVISOR__
ccflags-y := -D__KVM_VHE_HYPERVISOR__
+CFLAGS_switch.o += -Wno-override-init
+
obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o
obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
../fpsimd.o ../hyp-entry.o ../exception.o
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 6981b1b..a509b63 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1540,8 +1540,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
vma_pagesize = min(vma_pagesize, (long)max_map_size);
}
- if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE)
+ /*
+ * Both the canonical IPA and fault IPA must be hugepage-aligned to
+ * ensure we find the right PFN and lay down the mapping in the right
+ * place.
+ */
+ if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) {
fault_ipa &= ~(vma_pagesize - 1);
+ ipa &= ~(vma_pagesize - 1);
+ }
gfn = ipa >> PAGE_SHIFT;
mte_allowed = kvm_vma_mte_allowed(vma);
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index de789e0..bab27f9 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -786,7 +786,7 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
if (!WARN_ON(atomic_read(&mmu->refcnt)))
kvm_free_stage2_pgd(mmu);
}
- kfree(kvm->arch.nested_mmus);
+ kvfree(kvm->arch.nested_mmus);
kvm->arch.nested_mmus = NULL;
kvm->arch.nested_mmus_size = 0;
kvm_uninit_stage2_mmu(kvm);
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index c903240..31e49da 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -33,6 +33,7 @@
#include <trace/events/kvm.h>
#include "sys_regs.h"
+#include "vgic/vgic.h"
#include "trace.h"
@@ -435,6 +436,11 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu,
{
bool g1;
+ if (!kvm_has_gicv3(vcpu->kvm)) {
+ kvm_inject_undefined(vcpu);
+ return false;
+ }
+
if (!p->is_write)
return read_from_write_only(vcpu, p, r);
diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c
index bcbc8c9..e1397ab 100644
--- a/arch/arm64/kvm/vgic/vgic-debug.c
+++ b/arch/arm64/kvm/vgic/vgic-debug.c
@@ -45,7 +45,8 @@ static void iter_next(struct kvm *kvm, struct vgic_state_iter *iter)
* Let the xarray drive the iterator after the last SPI, as the iterator
* has exhausted the sequentially-allocated INTID space.
*/
- if (iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS - 1)) {
+ if (iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS - 1) &&
+ iter->nr_lpis) {
if (iter->lpi_idx < iter->nr_lpis)
xa_find_after(&dist->lpi_xa, &iter->intid,
VGIC_LPI_MAX_INTID,
@@ -84,7 +85,7 @@ static void iter_unmark_lpis(struct kvm *kvm)
struct vgic_irq *irq;
unsigned long intid;
- xa_for_each(&dist->lpi_xa, intid, irq) {
+ xa_for_each_marked(&dist->lpi_xa, intid, irq, LPI_XA_MARK_DEBUG_ITER) {
xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER);
vgic_put_irq(kvm, irq);
}
@@ -112,7 +113,7 @@ static bool end_of_vgic(struct vgic_state_iter *iter)
return iter->dist_id > 0 &&
iter->vcpu_id == iter->nr_cpus &&
iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS) &&
- iter->lpi_idx > iter->nr_lpis;
+ (!iter->nr_lpis || iter->lpi_idx > iter->nr_lpis);
}
static void *vgic_debug_start(struct seq_file *s, loff_t *pos)
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index 7f68cf5..e7c53e8 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -417,10 +417,8 @@ static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
kfree(vgic_cpu->private_irqs);
vgic_cpu->private_irqs = NULL;
- if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
- vgic_unregister_redist_iodev(vcpu);
+ if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
- }
}
void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
@@ -438,17 +436,21 @@ void kvm_vgic_destroy(struct kvm *kvm)
unsigned long i;
mutex_lock(&kvm->slots_lock);
+ mutex_lock(&kvm->arch.config_lock);
vgic_debug_destroy(kvm);
kvm_for_each_vcpu(i, vcpu, kvm)
__kvm_vgic_vcpu_destroy(vcpu);
- mutex_lock(&kvm->arch.config_lock);
-
kvm_vgic_dist_destroy(kvm);
mutex_unlock(&kvm->arch.config_lock);
+
+ if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ vgic_unregister_redist_iodev(vcpu);
+
mutex_unlock(&kvm->slots_lock);
}
diff --git a/arch/arm64/kvm/vgic/vgic-irqfd.c b/arch/arm64/kvm/vgic/vgic-irqfd.c
index 8c711de..c314c01 100644
--- a/arch/arm64/kvm/vgic/vgic-irqfd.c
+++ b/arch/arm64/kvm/vgic/vgic-irqfd.c
@@ -9,7 +9,7 @@
#include <kvm/arm_vgic.h>
#include "vgic.h"
-/**
+/*
* vgic_irqfd_set_irq: inject the IRQ corresponding to the
* irqchip routing entry
*
@@ -75,7 +75,8 @@ static void kvm_populate_msi(struct kvm_kernel_irq_routing_entry *e,
msi->flags = e->msi.flags;
msi->devid = e->msi.devid;
}
-/**
+
+/*
* kvm_set_msi: inject the MSI corresponding to the
* MSI routing entry
*
@@ -98,7 +99,7 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
return vgic_its_inject_msi(kvm, &msi);
}
-/**
+/*
* kvm_arch_set_irq_inatomic: fast-path for irqfd injection
*/
int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index 40bb43f..ba945ba 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -2040,6 +2040,7 @@ typedef int (*entry_fn_t)(struct vgic_its *its, u32 id, void *entry,
* @start_id: the ID of the first entry in the table
* (non zero for 2d level tables)
* @fn: function to apply on each entry
+ * @opaque: pointer to opaque data
*
* Return: < 0 on error, 0 if last element was identified, 1 otherwise
* (the last element may not be found on second level tables)
@@ -2079,7 +2080,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz,
return 1;
}
-/**
+/*
* vgic_its_save_ite - Save an interrupt translation entry at @gpa
*/
static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev,
@@ -2099,6 +2100,8 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev,
/**
* vgic_its_restore_ite - restore an interrupt translation entry
+ *
+ * @its: its handle
* @event_id: id used for indexing
* @ptr: pointer to the ITE entry
* @opaque: pointer to the its_device
@@ -2231,6 +2234,7 @@ static int vgic_its_restore_itt(struct vgic_its *its, struct its_device *dev)
* @its: ITS handle
* @dev: ITS device
* @ptr: GPA
+ * @dte_esz: device table entry size
*/
static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev,
gpa_t ptr, int dte_esz)
@@ -2313,7 +2317,7 @@ static int vgic_its_device_cmp(void *priv, const struct list_head *a,
return 1;
}
-/**
+/*
* vgic_its_save_device_tables - Save the device table and all ITT
* into guest RAM
*
@@ -2386,7 +2390,7 @@ static int handle_l1_dte(struct vgic_its *its, u32 id, void *addr,
return ret;
}
-/**
+/*
* vgic_its_restore_device_tables - Restore the device table and all ITT
* from guest RAM to internal data structs
*/
@@ -2478,7 +2482,7 @@ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz)
return 1;
}
-/**
+/*
* vgic_its_save_collection_table - Save the collection table into
* guest RAM
*/
@@ -2518,7 +2522,7 @@ static int vgic_its_save_collection_table(struct vgic_its *its)
return ret;
}
-/**
+/*
* vgic_its_restore_collection_table - reads the collection table
* in guest memory and restores the ITS internal state. Requires the
* BASER registers to be restored before.
@@ -2556,7 +2560,7 @@ static int vgic_its_restore_collection_table(struct vgic_its *its)
return ret;
}
-/**
+/*
* vgic_its_save_tables_v0 - Save the ITS tables into guest ARM
* according to v0 ABI
*/
@@ -2571,7 +2575,7 @@ static int vgic_its_save_tables_v0(struct vgic_its *its)
return vgic_its_save_collection_table(its);
}
-/**
+/*
* vgic_its_restore_tables_v0 - Restore the ITS tables from guest RAM
* to internal data structs according to V0 ABI
*
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index ed6e412..3eecdd2 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -370,7 +370,7 @@ static void map_all_vpes(struct kvm *kvm)
dist->its_vm.vpes[i]->irq));
}
-/**
+/*
* vgic_v3_save_pending_tables - Save the pending tables into guest RAM
* kvm lock and all vcpu lock must be held
*/
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index f07b3dd..abe29c7 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -36,6 +36,11 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = {
* we have to disable IRQs before taking this lock and everything lower
* than it.
*
+ * The config_lock has additional ordering requirements:
+ * kvm->slots_lock
+ * kvm->srcu
+ * kvm->arch.config_lock
+ *
* If you need to take multiple locks, always take the upper lock first,
* then the lower ones, e.g. first take the its_lock, then the irq_lock.
* If you are already holding a lock and need to take a higher one, you
@@ -313,7 +318,7 @@ static bool vgic_validate_injection(struct vgic_irq *irq, bool level, void *owne
* with all locks dropped.
*/
bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq,
- unsigned long flags)
+ unsigned long flags) __releases(&irq->irq_lock)
{
struct kvm_vcpu *vcpu;
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 03d356a..8532bfe 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -186,7 +186,7 @@ bool vgic_get_phys_line_level(struct vgic_irq *irq);
void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending);
void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active);
bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq,
- unsigned long flags);
+ unsigned long flags) __releases(&irq->irq_lock);
void vgic_kick_vcpus(struct kvm *kvm);
void vgic_irq_handle_resampling(struct vgic_irq *irq,
bool lr_deactivated, bool lr_pending);
@@ -346,4 +346,11 @@ void vgic_v4_configure_vsgis(struct kvm *kvm);
void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val);
int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq);
+static inline bool kvm_has_gicv3(struct kvm *kvm)
+{
+ return (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) &&
+ irqchip_in_kernel(kvm) &&
+ kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3);
+}
+
#endif
diff --git a/arch/loongarch/include/asm/dma-direct.h b/arch/loongarch/include/asm/dma-direct.h
deleted file mode 100644
index 75ccd80..0000000
--- a/arch/loongarch/include/asm/dma-direct.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
- */
-#ifndef _LOONGARCH_DMA_DIRECT_H
-#define _LOONGARCH_DMA_DIRECT_H
-
-dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
-phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
-
-#endif /* _LOONGARCH_DMA_DIRECT_H */
diff --git a/arch/loongarch/include/asm/hw_irq.h b/arch/loongarch/include/asm/hw_irq.h
index af4f4e8..8156ffb 100644
--- a/arch/loongarch/include/asm/hw_irq.h
+++ b/arch/loongarch/include/asm/hw_irq.h
@@ -9,6 +9,8 @@
extern atomic_t irq_err_count;
+#define ARCH_IRQ_INIT_FLAGS IRQ_NOPROBE
+
/*
* interrupt-retrigger: NOP for now. This may not be appropriate for all
* machines, we'll see ...
diff --git a/arch/loongarch/include/asm/kvm_vcpu.h b/arch/loongarch/include/asm/kvm_vcpu.h
index c416cb7..8657008 100644
--- a/arch/loongarch/include/asm/kvm_vcpu.h
+++ b/arch/loongarch/include/asm/kvm_vcpu.h
@@ -76,7 +76,6 @@ static inline void kvm_restore_lasx(struct loongarch_fpu *fpu) { }
#endif
void kvm_init_timer(struct kvm_vcpu *vcpu, unsigned long hz);
-void kvm_reset_timer(struct kvm_vcpu *vcpu);
void kvm_save_timer(struct kvm_vcpu *vcpu);
void kvm_restore_timer(struct kvm_vcpu *vcpu);
diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
index 69a85f2..6ab6401 100644
--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@@ -530,6 +530,10 @@
#ifdef CONFIG_CPU_HAS_LBT
STACK_FRAME_NON_STANDARD _restore_fp
+#ifdef CONFIG_CPU_HAS_LSX
STACK_FRAME_NON_STANDARD _restore_lsx
+#endif
+#ifdef CONFIG_CPU_HAS_LASX
STACK_FRAME_NON_STANDARD _restore_lasx
#endif
+#endif
diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c
index f4991c0..adac8fc 100644
--- a/arch/loongarch/kernel/irq.c
+++ b/arch/loongarch/kernel/irq.c
@@ -102,9 +102,6 @@ void __init init_IRQ(void)
mp_ops.init_ipi();
#endif
- for (i = 0; i < NR_IRQS; i++)
- irq_set_noprobe(i);
-
for_each_possible_cpu(i) {
page = alloc_pages_node(cpu_to_node(i), GFP_KERNEL, order);
diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S
index 80e9889..0c292f8 100644
--- a/arch/loongarch/kvm/switch.S
+++ b/arch/loongarch/kvm/switch.S
@@ -277,6 +277,10 @@
#ifdef CONFIG_CPU_HAS_LBT
STACK_FRAME_NON_STANDARD kvm_restore_fpu
+#ifdef CONFIG_CPU_HAS_LSX
STACK_FRAME_NON_STANDARD kvm_restore_lsx
+#endif
+#ifdef CONFIG_CPU_HAS_LASX
STACK_FRAME_NON_STANDARD kvm_restore_lasx
#endif
+#endif
diff --git a/arch/loongarch/kvm/timer.c b/arch/loongarch/kvm/timer.c
index bcc6b6d..74a4b5c 100644
--- a/arch/loongarch/kvm/timer.c
+++ b/arch/loongarch/kvm/timer.c
@@ -188,10 +188,3 @@ void kvm_save_timer(struct kvm_vcpu *vcpu)
kvm_save_hw_gcsr(csr, LOONGARCH_CSR_ESTAT);
preempt_enable();
}
-
-void kvm_reset_timer(struct kvm_vcpu *vcpu)
-{
- write_gcsr_timercfg(0);
- kvm_write_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_TCFG, 0);
- hrtimer_cancel(&vcpu->arch.swtimer);
-}
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 16756ff..6905283 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -647,7 +647,7 @@ static int kvm_set_one_reg(struct kvm_vcpu *vcpu,
vcpu->kvm->arch.time_offset = (signed long)(v - drdtime());
break;
case KVM_REG_LOONGARCH_VCPU_RESET:
- kvm_reset_timer(vcpu);
+ vcpu->arch.st.guest_addr = 0;
memset(&vcpu->arch.irq_pending, 0, sizeof(vcpu->arch.irq_pending));
memset(&vcpu->arch.irq_clear, 0, sizeof(vcpu->arch.irq_clear));
break;
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 3827dc7..4520c57 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -193,11 +193,6 @@ asmlinkage void __init mmu_init(void)
{
unsigned int kstart, ksize;
- if (!memblock.reserved.cnt) {
- pr_emerg("Error memory count\n");
- machine_restart(NULL);
- }
-
if ((u32) memblock.memory.regions[0].size < 0x400000) {
pr_emerg("Memory must be greater than 4MB\n");
machine_restart(NULL);
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
index 368e847..5f6e9e2 100644
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@@ -303,13 +303,6 @@ int r4k_clockevent_init(void)
if (!c0_compare_int_usable())
return -ENXIO;
- /*
- * With vectored interrupts things are getting platform specific.
- * get_c0_compare_int is a hook to allow a platform to return the
- * interrupt number of its liking.
- */
- irq = get_c0_compare_int();
-
cd = &per_cpu(mips_clockevent_device, cpu);
cd->name = "MIPS";
@@ -320,7 +313,6 @@ int r4k_clockevent_init(void)
min_delta = calculate_min_delta();
cd->rating = 300;
- cd->irq = irq;
cd->cpumask = cpumask_of(cpu);
cd->set_next_event = mips_next_event;
cd->event_handler = mips_event_handler;
@@ -332,6 +324,13 @@ int r4k_clockevent_init(void)
cp0_timer_irq_installed = 1;
+ /*
+ * With vectored interrupts things are getting platform specific.
+ * get_c0_compare_int is a hook to allow a platform to return the
+ * interrupt number of its liking.
+ */
+ irq = get_c0_compare_int();
+
if (request_irq(irq, c0_compare_interrupt, flags, "timer",
c0_compare_interrupt))
pr_err("Failed to request irq %d (timer)\n", irq);
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index bda7f19..af74125 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -1724,12 +1724,16 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
c->ases |= (MIPS_ASE_LOONGSON_MMI | MIPS_ASE_LOONGSON_CAM |
MIPS_ASE_LOONGSON_EXT | MIPS_ASE_LOONGSON_EXT2);
c->ases &= ~MIPS_ASE_VZ; /* VZ of Loongson-3A2000/3000 is incomplete */
+ change_c0_config6(LOONGSON_CONF6_EXTIMER | LOONGSON_CONF6_INTIMER,
+ LOONGSON_CONF6_INTIMER);
break;
case PRID_IMP_LOONGSON_64G:
__cpu_name[cpu] = "ICT Loongson-3";
set_elf_platform(cpu, "loongson3a");
set_isa(c, MIPS_CPU_ISA_M64R2);
decode_cpucfg(c);
+ change_c0_config6(LOONGSON_CONF6_EXTIMER | LOONGSON_CONF6_INTIMER,
+ LOONGSON_CONF6_INTIMER);
break;
default:
panic("Unknown Loongson Processor ID!");
diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c
index bdb1fa8..59eca39 100644
--- a/arch/mips/kernel/csrc-r4k.c
+++ b/arch/mips/kernel/csrc-r4k.c
@@ -21,9 +21,7 @@ static struct clocksource clocksource_mips = {
.name = "MIPS",
.read = c0_hpt_read,
.mask = CLOCKSOURCE_MASK(32),
- .flags = CLOCK_SOURCE_IS_CONTINUOUS |
- CLOCK_SOURCE_MUST_VERIFY |
- CLOCK_SOURCE_VERIFY_PERCPU,
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
static u64 __maybe_unused notrace r4k_read_sched_clock(void)
diff --git a/arch/mips/sgi-ip22/ip22-gio.c b/arch/mips/sgi-ip22/ip22-gio.c
index 2738325..d20eec7 100644
--- a/arch/mips/sgi-ip22/ip22-gio.c
+++ b/arch/mips/sgi-ip22/ip22-gio.c
@@ -111,7 +111,7 @@ void gio_device_unregister(struct gio_device *giodev)
}
EXPORT_SYMBOL_GPL(gio_device_unregister);
-static int gio_bus_match(struct device *dev, struct device_driver *drv)
+static int gio_bus_match(struct device *dev, const struct device_driver *drv)
{
struct gio_device *gio_dev = to_gio_device(dev);
struct gio_driver *gio_drv = to_gio_driver(drv);
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index f4e6f2d..16bacfe 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -145,6 +145,7 @@ static inline int cpu_to_coregroup_id(int cpu)
#ifdef CONFIG_HOTPLUG_SMT
#include <linux/cpu_smt.h>
+#include <linux/cpumask.h>
#include <asm/cputhreads.h>
static inline bool topology_is_primary_thread(unsigned int cpu)
@@ -156,6 +157,18 @@ static inline bool topology_smt_thread_allowed(unsigned int cpu)
{
return cpu_thread_in_core(cpu) < cpu_smt_num_threads;
}
+
+#define topology_is_core_online topology_is_core_online
+static inline bool topology_is_core_online(unsigned int cpu)
+{
+ int i, first_cpu = cpu_first_thread_sibling(cpu);
+
+ for (i = first_cpu; i < first_cpu + threads_per_core; ++i) {
+ if (cpu_online(i))
+ return true;
+ }
+ return false;
+}
#endif
#endif /* __KERNEL__ */
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 4bd2f87..9434300 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -959,6 +959,7 @@ void __init setup_arch(char **cmdline_p)
mem_topology_setup();
/* Set max_mapnr before paging_init() */
set_max_mapnr(max_pfn);
+ high_memory = (void *)__va(max_low_pfn * PAGE_SIZE);
/*
* Release secondary cpus out of their spinloops at 0x60 now that
diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c
index 9b4a675..2978fcb 100644
--- a/arch/powerpc/mm/init-common.c
+++ b/arch/powerpc/mm/init-common.c
@@ -73,7 +73,7 @@ void setup_kup(void)
#define CTOR(shift) static void ctor_##shift(void *addr) \
{ \
- memset(addr, 0, sizeof(void *) << (shift)); \
+ memset(addr, 0, sizeof(pgd_t) << (shift)); \
}
CTOR(0); CTOR(1); CTOR(2); CTOR(3); CTOR(4); CTOR(5); CTOR(6); CTOR(7);
@@ -117,7 +117,7 @@ EXPORT_SYMBOL_GPL(pgtable_cache); /* used by kvm_hv module */
void pgtable_cache_add(unsigned int shift)
{
char *name;
- unsigned long table_size = sizeof(void *) << shift;
+ unsigned long table_size = sizeof(pgd_t) << shift;
unsigned long align = table_size;
/* When batching pgtable pointers for RCU freeing, we store
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index d325217..da21cb0 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -290,8 +290,6 @@ void __init mem_init(void)
swiotlb_init(ppc_swiotlb_enable, ppc_swiotlb_flags);
#endif
- high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
-
kasan_late_init();
memblock_free_all();
diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h
index ef01c18..ffb9484 100644
--- a/arch/riscv/include/asm/hwprobe.h
+++ b/arch/riscv/include/asm/hwprobe.h
@@ -8,7 +8,7 @@
#include <uapi/asm/hwprobe.h>
-#define RISCV_HWPROBE_MAX_KEY 8
+#define RISCV_HWPROBE_MAX_KEY 9
static inline bool riscv_hwprobe_key_is_valid(__s64 key)
{
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index b706c8e..1e153cd 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -82,6 +82,12 @@ struct riscv_hwprobe {
#define RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE 6
#define RISCV_HWPROBE_KEY_HIGHEST_VIRT_ADDRESS 7
#define RISCV_HWPROBE_KEY_TIME_CSR_FREQ 8
+#define RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF 9
+#define RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN 0
+#define RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED 1
+#define RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW 2
+#define RISCV_HWPROBE_MISALIGNED_SCALAR_FAST 3
+#define RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED 4
/* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
/* Flags */
diff --git a/arch/riscv/kernel/acpi_numa.c b/arch/riscv/kernel/acpi_numa.c
index 0231482..ff95aee 100644
--- a/arch/riscv/kernel/acpi_numa.c
+++ b/arch/riscv/kernel/acpi_numa.c
@@ -28,7 +28,7 @@
#include <asm/numa.h>
-static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE };
+static int acpi_early_node_map[NR_CPUS] __initdata = { [0 ... NR_CPUS - 1] = NUMA_NO_NODE };
int __init acpi_numa_get_nid(unsigned int cpu)
{
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index 69e5796..34ef522 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -205,6 +205,8 @@ int patch_text_set_nosync(void *addr, u8 c, size_t len)
int ret;
ret = patch_insn_set(addr, c, len);
+ if (!ret)
+ flush_icache_range((uintptr_t)addr, (uintptr_t)addr + len);
return ret;
}
@@ -239,6 +241,8 @@ int patch_text_nosync(void *addr, const void *insns, size_t len)
int ret;
ret = patch_insn_write(addr, insns, len);
+ if (!ret)
+ flush_icache_range((uintptr_t)addr, (uintptr_t)addr + len);
return ret;
}
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index 8d1b5c3..cea0ca2 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -178,13 +178,13 @@ static u64 hwprobe_misaligned(const struct cpumask *cpus)
perf = this_perf;
if (perf != this_perf) {
- perf = RISCV_HWPROBE_MISALIGNED_UNKNOWN;
+ perf = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN;
break;
}
}
if (perf == -1ULL)
- return RISCV_HWPROBE_MISALIGNED_UNKNOWN;
+ return RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN;
return perf;
}
@@ -192,12 +192,12 @@ static u64 hwprobe_misaligned(const struct cpumask *cpus)
static u64 hwprobe_misaligned(const struct cpumask *cpus)
{
if (IS_ENABLED(CONFIG_RISCV_EFFICIENT_UNALIGNED_ACCESS))
- return RISCV_HWPROBE_MISALIGNED_FAST;
+ return RISCV_HWPROBE_MISALIGNED_SCALAR_FAST;
if (IS_ENABLED(CONFIG_RISCV_EMULATED_UNALIGNED_ACCESS) && unaligned_ctl_available())
- return RISCV_HWPROBE_MISALIGNED_EMULATED;
+ return RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED;
- return RISCV_HWPROBE_MISALIGNED_SLOW;
+ return RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW;
}
#endif
@@ -225,6 +225,7 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair,
break;
case RISCV_HWPROBE_KEY_CPUPERF_0:
+ case RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF:
pair->value = hwprobe_misaligned(cpus);
break;
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 05a16b1..51ebfd2 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -319,6 +319,7 @@ void do_trap_ecall_u(struct pt_regs *regs)
regs->epc += 4;
regs->orig_a0 = regs->a0;
+ regs->a0 = -ENOSYS;
riscv_v_vstate_discard(regs);
@@ -328,8 +329,7 @@ void do_trap_ecall_u(struct pt_regs *regs)
if (syscall >= 0 && syscall < NR_syscalls)
syscall_handler(regs, syscall);
- else if (syscall != -1)
- regs->a0 = -ENOSYS;
+
/*
* Ultimately, this value will get limited by KSTACK_OFFSET_MAX(),
* so the maximum stack offset is 1k bytes (10 bits).
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index b62d5a2..192cd56 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -338,7 +338,7 @@ int handle_misaligned_load(struct pt_regs *regs)
perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr);
#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS
- *this_cpu_ptr(&misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_EMULATED;
+ *this_cpu_ptr(&misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED;
#endif
if (!unaligned_enabled)
@@ -532,13 +532,13 @@ static bool check_unaligned_access_emulated(int cpu)
unsigned long tmp_var, tmp_val;
bool misaligned_emu_detected;
- *mas_ptr = RISCV_HWPROBE_MISALIGNED_UNKNOWN;
+ *mas_ptr = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN;
__asm__ __volatile__ (
" "REG_L" %[tmp], 1(%[ptr])\n"
: [tmp] "=r" (tmp_val) : [ptr] "r" (&tmp_var) : "memory");
- misaligned_emu_detected = (*mas_ptr == RISCV_HWPROBE_MISALIGNED_EMULATED);
+ misaligned_emu_detected = (*mas_ptr == RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED);
/*
* If unaligned_ctl is already set, this means that we detected that all
* CPUS uses emulated misaligned access at boot time. If that changed
diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c
index a9a6bcb..160628a 100644
--- a/arch/riscv/kernel/unaligned_access_speed.c
+++ b/arch/riscv/kernel/unaligned_access_speed.c
@@ -34,9 +34,9 @@ static int check_unaligned_access(void *param)
struct page *page = param;
void *dst;
void *src;
- long speed = RISCV_HWPROBE_MISALIGNED_SLOW;
+ long speed = RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW;
- if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN)
+ if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN)
return 0;
/* Make an unaligned destination buffer. */
@@ -95,14 +95,14 @@ static int check_unaligned_access(void *param)
}
if (word_cycles < byte_cycles)
- speed = RISCV_HWPROBE_MISALIGNED_FAST;
+ speed = RISCV_HWPROBE_MISALIGNED_SCALAR_FAST;
ratio = div_u64((byte_cycles * 100), word_cycles);
pr_info("cpu%d: Ratio of byte access time to unaligned word access is %d.%02d, unaligned accesses are %s\n",
cpu,
ratio / 100,
ratio % 100,
- (speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow");
+ (speed == RISCV_HWPROBE_MISALIGNED_SCALAR_FAST) ? "fast" : "slow");
per_cpu(misaligned_access_speed, cpu) = speed;
@@ -110,7 +110,7 @@ static int check_unaligned_access(void *param)
* Set the value of fast_misaligned_access of a CPU. These operations
* are atomic to avoid race conditions.
*/
- if (speed == RISCV_HWPROBE_MISALIGNED_FAST)
+ if (speed == RISCV_HWPROBE_MISALIGNED_SCALAR_FAST)
cpumask_set_cpu(cpu, &fast_misaligned_access);
else
cpumask_clear_cpu(cpu, &fast_misaligned_access);
@@ -188,7 +188,7 @@ static int riscv_online_cpu(unsigned int cpu)
static struct page *buf;
/* We are already set since the last check */
- if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN)
+ if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN)
goto exit;
buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
diff --git a/arch/riscv/kernel/vendor_extensions.c b/arch/riscv/kernel/vendor_extensions.c
index b6c1e7b..a8126d1 100644
--- a/arch/riscv/kernel/vendor_extensions.c
+++ b/arch/riscv/kernel/vendor_extensions.c
@@ -38,7 +38,7 @@ bool __riscv_isa_vendor_extension_available(int cpu, unsigned long vendor, unsig
#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_ANDES
case ANDES_VENDOR_ID:
bmap = &riscv_isa_vendor_ext_list_andes.all_harts_isa_bitmap;
- cpu_bmap = &riscv_isa_vendor_ext_list_andes.per_hart_isa_bitmap[cpu];
+ cpu_bmap = riscv_isa_vendor_ext_list_andes.per_hart_isa_bitmap;
break;
#endif
default:
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 8b698d9..eb0649a 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -927,7 +927,7 @@ static void __init create_kernel_page_table(pgd_t *pgdir,
PMD_SIZE, PAGE_KERNEL_EXEC);
/* Map the data in RAM */
- end_va = kernel_map.virt_addr + XIP_OFFSET + kernel_map.size;
+ end_va = kernel_map.virt_addr + kernel_map.size;
for (va = kernel_map.virt_addr + XIP_OFFSET; va < end_va; va += PMD_SIZE)
create_pgd_mapping(pgdir, va,
kernel_map.phys_addr + (va - (kernel_map.virt_addr + XIP_OFFSET)),
@@ -1096,7 +1096,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
phys_ram_base = CONFIG_PHYS_RAM_BASE;
kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE;
- kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_sdata);
+ kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_start);
kernel_map.va_kernel_xip_pa_offset = kernel_map.virt_addr - kernel_map.xiprom;
#else
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index a822f95..c60e699 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -604,6 +604,19 @@
as a security feature that deters exploit attempts relying on
knowledge of the location of kernel internals.
+config RANDOMIZE_IDENTITY_BASE
+ bool "Randomize the address of the identity mapping base"
+ depends on RANDOMIZE_BASE
+ default DEBUG_VM
+ help
+ The identity mapping base address is pinned to zero by default.
+ Allow randomization of that base to expose otherwise missed
+ notion of physical and virtual addresses of data structures.
+ That does not have any impact on the base address at which the
+ kernel image is loaded.
+
+ If unsure, say N
+
config KERNEL_IMAGE_BASE
hex "Kernel image base address"
range 0x100000 0x1FFFFFE0000000 if !KASAN
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index ce23255..c73b511 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -162,7 +162,7 @@ static void kaslr_adjust_relocs(unsigned long min_addr, unsigned long max_addr,
loc = (long)*reloc + phys_offset;
if (loc < min_addr || loc > max_addr)
error("64-bit relocation outside of kernel!\n");
- *(u64 *)loc += offset - __START_KERNEL;
+ *(u64 *)loc += offset;
}
}
@@ -177,7 +177,7 @@ static void kaslr_adjust_got(unsigned long offset)
*/
for (entry = (u64 *)vmlinux.got_start; entry < (u64 *)vmlinux.got_end; entry++) {
if (*entry)
- *entry += offset - __START_KERNEL;
+ *entry += offset;
}
}
@@ -252,7 +252,7 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size)
vmemmap_size = SECTION_ALIGN_UP(pages) * sizeof(struct page);
/* choose kernel address space layout: 4 or 3 levels. */
- BUILD_BUG_ON(!IS_ALIGNED(__START_KERNEL, THREAD_SIZE));
+ BUILD_BUG_ON(!IS_ALIGNED(TEXT_OFFSET, THREAD_SIZE));
BUILD_BUG_ON(!IS_ALIGNED(__NO_KASLR_START_KERNEL, THREAD_SIZE));
BUILD_BUG_ON(__NO_KASLR_END_KERNEL > _REGION1_SIZE);
vsize = get_vmem_size(ident_map_size, vmemmap_size, vmalloc_size, _REGION3_SIZE);
@@ -341,7 +341,8 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size)
BUILD_BUG_ON(MAX_DCSS_ADDR > (1UL << MAX_PHYSMEM_BITS));
max_mappable = max(ident_map_size, MAX_DCSS_ADDR);
max_mappable = min(max_mappable, vmemmap_start);
- __identity_base = round_down(vmemmap_start - max_mappable, rte_size);
+ if (IS_ENABLED(CONFIG_RANDOMIZE_IDENTITY_BASE))
+ __identity_base = round_down(vmemmap_start - max_mappable, rte_size);
return asce_limit;
}
@@ -388,31 +389,25 @@ static void kaslr_adjust_vmlinux_info(long offset)
#endif
}
-static void fixup_vmlinux_info(void)
-{
- vmlinux.entry -= __START_KERNEL;
- kaslr_adjust_vmlinux_info(-__START_KERNEL);
-}
-
void startup_kernel(void)
{
- unsigned long kernel_size = vmlinux.image_size + vmlinux.bss_size;
- unsigned long nokaslr_offset_phys, kaslr_large_page_offset;
- unsigned long amode31_lma = 0;
+ unsigned long vmlinux_size = vmlinux.image_size + vmlinux.bss_size;
+ unsigned long nokaslr_text_lma, text_lma = 0, amode31_lma = 0;
+ unsigned long kernel_size = TEXT_OFFSET + vmlinux_size;
+ unsigned long kaslr_large_page_offset;
unsigned long max_physmem_end;
unsigned long asce_limit;
unsigned long safe_addr;
psw_t psw;
- fixup_vmlinux_info();
setup_lpp();
/*
* Non-randomized kernel physical start address must be _SEGMENT_SIZE
* aligned (see blow).
*/
- nokaslr_offset_phys = ALIGN(mem_safe_offset(), _SEGMENT_SIZE);
- safe_addr = PAGE_ALIGN(nokaslr_offset_phys + kernel_size);
+ nokaslr_text_lma = ALIGN(mem_safe_offset(), _SEGMENT_SIZE);
+ safe_addr = PAGE_ALIGN(nokaslr_text_lma + vmlinux_size);
/*
* Reserve decompressor memory together with decompression heap,
@@ -456,16 +451,27 @@ void startup_kernel(void)
*/
kaslr_large_page_offset = __kaslr_offset & ~_SEGMENT_MASK;
if (kaslr_enabled()) {
- unsigned long end = ident_map_size - kaslr_large_page_offset;
+ unsigned long size = vmlinux_size + kaslr_large_page_offset;
- __kaslr_offset_phys = randomize_within_range(kernel_size, _SEGMENT_SIZE, 0, end);
+ text_lma = randomize_within_range(size, _SEGMENT_SIZE, TEXT_OFFSET, ident_map_size);
}
- if (!__kaslr_offset_phys)
- __kaslr_offset_phys = nokaslr_offset_phys;
- __kaslr_offset_phys |= kaslr_large_page_offset;
+ if (!text_lma)
+ text_lma = nokaslr_text_lma;
+ text_lma |= kaslr_large_page_offset;
+
+ /*
+ * [__kaslr_offset_phys..__kaslr_offset_phys + TEXT_OFFSET] region is
+ * never accessed via the kernel image mapping as per the linker script:
+ *
+ * . = TEXT_OFFSET;
+ *
+ * Therefore, this region could be used for something else and does
+ * not need to be reserved. See how it is skipped in setup_vmem().
+ */
+ __kaslr_offset_phys = text_lma - TEXT_OFFSET;
kaslr_adjust_vmlinux_info(__kaslr_offset_phys);
- physmem_reserve(RR_VMLINUX, __kaslr_offset_phys, kernel_size);
- deploy_kernel((void *)__kaslr_offset_phys);
+ physmem_reserve(RR_VMLINUX, text_lma, vmlinux_size);
+ deploy_kernel((void *)text_lma);
/* vmlinux decompression is done, shrink reserved low memory */
physmem_reserve(RR_DECOMPRESSOR, 0, (unsigned long)_decompressor_end);
@@ -488,7 +494,7 @@ void startup_kernel(void)
amode31_lma = randomize_within_range(vmlinux.amode31_size, PAGE_SIZE, amode31_min, SZ_2G);
}
if (!amode31_lma)
- amode31_lma = __kaslr_offset_phys - vmlinux.amode31_size;
+ amode31_lma = text_lma - vmlinux.amode31_size;
physmem_reserve(RR_AMODE31, amode31_lma, vmlinux.amode31_size);
/*
@@ -504,8 +510,8 @@ void startup_kernel(void)
* - copy_bootdata() must follow setup_vmem() to propagate changes
* to bootdata made by setup_vmem()
*/
- clear_bss_section(__kaslr_offset_phys);
- kaslr_adjust_relocs(__kaslr_offset_phys, __kaslr_offset_phys + vmlinux.image_size,
+ clear_bss_section(text_lma);
+ kaslr_adjust_relocs(text_lma, text_lma + vmlinux.image_size,
__kaslr_offset, __kaslr_offset_phys);
kaslr_adjust_got(__kaslr_offset);
setup_vmem(__kaslr_offset, __kaslr_offset + kernel_size, asce_limit);
diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c
index 2847cc0..145035f 100644
--- a/arch/s390/boot/vmem.c
+++ b/arch/s390/boot/vmem.c
@@ -90,7 +90,7 @@ static void kasan_populate_shadow(unsigned long kernel_start, unsigned long kern
}
memgap_start = end;
}
- kasan_populate(kernel_start, kernel_end, POPULATE_KASAN_MAP_SHADOW);
+ kasan_populate(kernel_start + TEXT_OFFSET, kernel_end, POPULATE_KASAN_MAP_SHADOW);
kasan_populate(0, (unsigned long)__identity_va(0), POPULATE_KASAN_ZERO_SHADOW);
kasan_populate(AMODE31_START, AMODE31_END, POPULATE_KASAN_ZERO_SHADOW);
if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
@@ -475,7 +475,17 @@ void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned l
(unsigned long)__identity_va(end),
POPULATE_IDENTITY);
}
- pgtable_populate(kernel_start, kernel_end, POPULATE_KERNEL);
+
+ /*
+ * [kernel_start..kernel_start + TEXT_OFFSET] region is never
+ * accessed as per the linker script:
+ *
+ * . = TEXT_OFFSET;
+ *
+ * Therefore, skip mapping TEXT_OFFSET bytes to prevent access to
+ * [__kaslr_offset_phys..__kaslr_offset_phys + TEXT_OFFSET] region.
+ */
+ pgtable_populate(kernel_start + TEXT_OFFSET, kernel_end, POPULATE_KERNEL);
pgtable_populate(AMODE31_START, AMODE31_END, POPULATE_DIRECT);
pgtable_populate(__abs_lowcore, __abs_lowcore + sizeof(struct lowcore),
POPULATE_ABS_LOWCORE);
diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S
index a750711..66670212 100644
--- a/arch/s390/boot/vmlinux.lds.S
+++ b/arch/s390/boot/vmlinux.lds.S
@@ -109,7 +109,12 @@
#ifdef CONFIG_KERNEL_UNCOMPRESSED
. = ALIGN(PAGE_SIZE);
. += AMODE31_SIZE; /* .amode31 section */
- . = ALIGN(1 << 20); /* _SEGMENT_SIZE */
+
+ /*
+ * Make sure the location counter is not less than TEXT_OFFSET.
+ * _SEGMENT_SIZE is not available, use ALIGN(1 << 20) instead.
+ */
+ . = MAX(TEXT_OFFSET, ALIGN(1 << 20));
#else
. = ALIGN(8);
#endif
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 06416b3..16e4caa 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -279,8 +279,9 @@ static inline unsigned long virt_to_pfn(const void *kaddr)
#define AMODE31_SIZE (3 * PAGE_SIZE)
#define KERNEL_IMAGE_SIZE (512 * 1024 * 1024)
-#define __START_KERNEL 0x100000
#define __NO_KASLR_START_KERNEL CONFIG_KERNEL_IMAGE_BASE
#define __NO_KASLR_END_KERNEL (__NO_KASLR_START_KERNEL + KERNEL_IMAGE_SIZE)
+#define TEXT_OFFSET 0x100000
+
#endif /* _S390_PAGE_H */
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index 0b5f8f3..153d934 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -441,7 +441,10 @@ static inline int share(unsigned long addr, u16 cmd)
if (!uv_call(0, (u64)&uvcb))
return 0;
- return -EINVAL;
+ pr_err("%s UVC failed (rc: 0x%x, rrc: 0x%x), possible hypervisor bug.\n",
+ uvcb.header.cmd == UVC_CMD_SET_SHARED_ACCESS ? "Share" : "Unshare",
+ uvcb.header.rc, uvcb.header.rrc);
+ panic("System security cannot be guaranteed unless the system panics now.\n");
}
/*
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 4ec99f7..a3fea68 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -734,7 +734,23 @@ static void __init memblock_add_physmem_info(void)
}
/*
- * Reserve memory used for lowcore/command line/kernel image.
+ * Reserve memory used for lowcore.
+ */
+static void __init reserve_lowcore(void)
+{
+ void *lowcore_start = get_lowcore();
+ void *lowcore_end = lowcore_start + sizeof(struct lowcore);
+ void *start, *end;
+
+ if ((void *)__identity_base < lowcore_end) {
+ start = max(lowcore_start, (void *)__identity_base);
+ end = min(lowcore_end, (void *)(__identity_base + ident_map_size));
+ memblock_reserve(__pa(start), __pa(end));
+ }
+}
+
+/*
+ * Reserve memory used for absolute lowcore/command line/kernel image.
*/
static void __init reserve_kernel(void)
{
@@ -918,6 +934,7 @@ void __init setup_arch(char **cmdline_p)
/* Do some memory reservations *before* memory is added to memblock */
reserve_pgtables();
+ reserve_lowcore();
reserve_kernel();
reserve_initrd();
reserve_certificate_list();
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index e67cd40..ae5d0a9 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -39,7 +39,7 @@
SECTIONS
{
- . = __START_KERNEL;
+ . = TEXT_OFFSET;
.text : {
_stext = .; /* Start of text section */
_text = .; /* Text and read-only data */
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index bf85342..e680c6b 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -267,7 +267,12 @@ static inline unsigned long kvm_s390_get_gfn_end(struct kvm_memslots *slots)
static inline u32 kvm_s390_get_gisa_desc(struct kvm *kvm)
{
- u32 gd = virt_to_phys(kvm->arch.gisa_int.origin);
+ u32 gd;
+
+ if (!kvm->arch.gisa_int.origin)
+ return 0;
+
+ gd = virt_to_phys(kvm->arch.gisa_int.origin);
if (gd && sclp.has_gisaf)
gd |= GISA_FORMAT1;
diff --git a/arch/s390/tools/relocs.c b/arch/s390/tools/relocs.c
index a74dbd5..30a732c 100644
--- a/arch/s390/tools/relocs.c
+++ b/arch/s390/tools/relocs.c
@@ -280,7 +280,7 @@ static int do_reloc(struct section *sec, Elf_Rel *rel)
case R_390_GOTOFF64:
break;
case R_390_64:
- add_reloc(&relocs64, offset - ehdr.e_entry);
+ add_reloc(&relocs64, offset);
break;
default:
die("Unsupported relocation type: %d\n", r_type);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 94e7b5a..4a68cb3 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2192,6 +2192,8 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level,
#define kvm_arch_has_private_mem(kvm) false
#endif
+#define kvm_arch_has_readonly_mem(kvm) (!(kvm)->arch.has_protected_state)
+
static inline u16 kvm_read_ldt(void)
{
u16 ldt;
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index 923e649..913bfc9 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -286,7 +286,6 @@ static inline int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
return HV_STATUS_ACCESS_DENIED;
}
static inline void kvm_hv_vcpu_purge_flush_tlb(struct kvm_vcpu *vcpu) {}
-static inline void kvm_hv_free_pa_page(struct kvm *kvm) {}
static inline bool kvm_hv_synic_has_vector(struct kvm_vcpu *vcpu, int vector)
{
return false;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 4915acd..5bb481a 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -351,10 +351,8 @@ static void kvm_recalculate_logical_map(struct kvm_apic_map *new,
* reversing the LDR calculation to get cluster of APICs, i.e. no
* additional work is required.
*/
- if (apic_x2apic_mode(apic)) {
- WARN_ON_ONCE(ldr != kvm_apic_calc_x2apic_ldr(kvm_x2apic_id(apic)));
+ if (apic_x2apic_mode(apic))
return;
- }
if (WARN_ON_ONCE(!kvm_apic_map_get_logical_dest(new, ldr,
&cluster, &mask))) {
@@ -2966,18 +2964,28 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
struct kvm_lapic_state *s, bool set)
{
if (apic_x2apic_mode(vcpu->arch.apic)) {
+ u32 x2apic_id = kvm_x2apic_id(vcpu->arch.apic);
u32 *id = (u32 *)(s->regs + APIC_ID);
u32 *ldr = (u32 *)(s->regs + APIC_LDR);
u64 icr;
if (vcpu->kvm->arch.x2apic_format) {
- if (*id != vcpu->vcpu_id)
+ if (*id != x2apic_id)
return -EINVAL;
} else {
+ /*
+ * Ignore the userspace value when setting APIC state.
+ * KVM's model is that the x2APIC ID is readonly, e.g.
+ * KVM only supports delivering interrupts to KVM's
+ * version of the x2APIC ID. However, for backwards
+ * compatibility, don't reject attempts to set a
+ * mismatched ID for userspace that hasn't opted into
+ * x2apic_format.
+ */
if (set)
- *id >>= 24;
+ *id = x2apic_id;
else
- *id <<= 24;
+ *id = x2apic_id << 24;
}
/*
@@ -2986,7 +2994,7 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
* split to ICR+ICR2 in userspace for backwards compatibility.
*/
if (set) {
- *ldr = kvm_apic_calc_x2apic_ldr(*id);
+ *ldr = kvm_apic_calc_x2apic_ldr(x2apic_id);
icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) |
(u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 532df12..714c517 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2276,7 +2276,7 @@ static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn_start, kvm_pfn_t pf
for (gfn = gfn_start, i = 0; gfn < gfn_start + npages; gfn++, i++) {
struct sev_data_snp_launch_update fw_args = {0};
- bool assigned;
+ bool assigned = false;
int level;
ret = snp_lookup_rmpentry((u64)pfn + i, &assigned, &level);
@@ -2290,9 +2290,10 @@ static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn_start, kvm_pfn_t pf
if (src) {
void *vaddr = kmap_local_pfn(pfn + i);
- ret = copy_from_user(vaddr, src + i * PAGE_SIZE, PAGE_SIZE);
- if (ret)
+ if (copy_from_user(vaddr, src + i * PAGE_SIZE, PAGE_SIZE)) {
+ ret = -EFAULT;
goto err;
+ }
kunmap_local(vaddr);
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ef3d351..70219e4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -427,8 +427,7 @@ static void kvm_user_return_msr_cpu_online(void)
int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
{
- unsigned int cpu = smp_processor_id();
- struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu);
+ struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
int err;
value = (value & mask) | (msrs->values[slot].host & ~mask);
@@ -450,8 +449,7 @@ EXPORT_SYMBOL_GPL(kvm_set_user_return_msr);
static void drop_user_return_notifiers(void)
{
- unsigned int cpu = smp_processor_id();
- struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu);
+ struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
if (msrs->registered)
kvm_on_user_return(&msrs->urn);
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 9f735ef..4c9f20a 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -111,13 +111,20 @@ static sector_t bio_write_zeroes_limit(struct block_device *bdev)
(UINT_MAX >> SECTOR_SHIFT) & ~bs_mask);
}
+/*
+ * There is no reliable way for the SCSI subsystem to determine whether a
+ * device supports a WRITE SAME operation without actually performing a write
+ * to media. As a result, write_zeroes is enabled by default and will be
+ * disabled if a zeroing operation subsequently fails. This means that this
+ * queue limit is likely to change at runtime.
+ */
static void __blkdev_issue_write_zeroes(struct block_device *bdev,
sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
- struct bio **biop, unsigned flags)
+ struct bio **biop, unsigned flags, sector_t limit)
{
+
while (nr_sects) {
- unsigned int len = min_t(sector_t, nr_sects,
- bio_write_zeroes_limit(bdev));
+ unsigned int len = min(nr_sects, limit);
struct bio *bio;
if ((flags & BLKDEV_ZERO_KILLABLE) &&
@@ -141,12 +148,14 @@ static void __blkdev_issue_write_zeroes(struct block_device *bdev,
static int blkdev_issue_write_zeroes(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp, unsigned flags)
{
+ sector_t limit = bio_write_zeroes_limit(bdev);
struct bio *bio = NULL;
struct blk_plug plug;
int ret = 0;
blk_start_plug(&plug);
- __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp, &bio, flags);
+ __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp, &bio,
+ flags, limit);
if (bio) {
if ((flags & BLKDEV_ZERO_KILLABLE) &&
fatal_signal_pending(current)) {
@@ -265,12 +274,14 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
unsigned flags)
{
+ sector_t limit = bio_write_zeroes_limit(bdev);
+
if (bdev_read_only(bdev))
return -EPERM;
- if (bdev_write_zeroes_sectors(bdev)) {
+ if (limit) {
__blkdev_issue_write_zeroes(bdev, sector, nr_sects,
- gfp_mask, biop, flags);
+ gfp_mask, biop, flags, limit);
} else {
if (flags & BLKDEV_ZERO_NOFALLBACK)
return -EOPNOTSUPP;
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index cc57e2d..2cafcf1 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -38,6 +38,7 @@ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags,
void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
{
unsigned int users;
+ unsigned long flags;
struct blk_mq_tags *tags = hctx->tags;
/*
@@ -56,11 +57,11 @@ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
return;
}
- spin_lock_irq(&tags->lock);
+ spin_lock_irqsave(&tags->lock, flags);
users = tags->active_queues + 1;
WRITE_ONCE(tags->active_queues, users);
blk_mq_update_wake_batch(tags, users);
- spin_unlock_irq(&tags->lock);
+ spin_unlock_irqrestore(&tags->lock, flags);
}
/*
diff --git a/drivers/accessibility/speakup/genmap.c b/drivers/accessibility/speakup/genmap.c
index 0125000..0882bab 100644
--- a/drivers/accessibility/speakup/genmap.c
+++ b/drivers/accessibility/speakup/genmap.c
@@ -10,7 +10,6 @@
#include <stdio.h>
#include <libgen.h>
#include <string.h>
-#include <linux/version.h>
#include <ctype.h>
#include "utils.h"
diff --git a/drivers/accessibility/speakup/makemapdata.c b/drivers/accessibility/speakup/makemapdata.c
index d7d41bb..55e4ef8 100644
--- a/drivers/accessibility/speakup/makemapdata.c
+++ b/drivers/accessibility/speakup/makemapdata.c
@@ -10,7 +10,6 @@
#include <stdio.h>
#include <libgen.h>
#include <string.h>
-#include <linux/version.h>
#include <ctype.h>
#include "utils.h"
diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h
index 2133085..1c5218b7 100644
--- a/drivers/acpi/acpica/acevents.h
+++ b/drivers/acpi/acpica/acevents.h
@@ -188,13 +188,9 @@ acpi_ev_detach_region(union acpi_operand_object *region_obj,
u8 acpi_ns_is_locked);
void
-acpi_ev_execute_reg_methods(struct acpi_namespace_node *node,
+acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, u32 max_depth,
acpi_adr_space_type space_id, u32 function);
-void
-acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *node,
- acpi_adr_space_type space_id);
-
acpi_status
acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function);
diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
index dc6004d..cf53b95 100644
--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@@ -20,6 +20,10 @@ extern u8 acpi_gbl_default_address_spaces[];
/* Local prototypes */
+static void
+acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node,
+ acpi_adr_space_type space_id);
+
static acpi_status
acpi_ev_reg_run(acpi_handle obj_handle,
u32 level, void *context, void **return_value);
@@ -61,6 +65,7 @@ acpi_status acpi_ev_initialize_op_regions(void)
acpi_gbl_default_address_spaces
[i])) {
acpi_ev_execute_reg_methods(acpi_gbl_root_node,
+ ACPI_UINT32_MAX,
acpi_gbl_default_address_spaces
[i], ACPI_REG_CONNECT);
}
@@ -668,6 +673,7 @@ acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function)
* FUNCTION: acpi_ev_execute_reg_methods
*
* PARAMETERS: node - Namespace node for the device
+ * max_depth - Depth to which search for _REG
* space_id - The address space ID
* function - Passed to _REG: On (1) or Off (0)
*
@@ -679,7 +685,7 @@ acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function)
******************************************************************************/
void
-acpi_ev_execute_reg_methods(struct acpi_namespace_node *node,
+acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, u32 max_depth,
acpi_adr_space_type space_id, u32 function)
{
struct acpi_reg_walk_info info;
@@ -713,7 +719,7 @@ acpi_ev_execute_reg_methods(struct acpi_namespace_node *node,
* regions and _REG methods. (i.e. handlers must be installed for all
* regions of this Space ID before we can run any _REG methods)
*/
- (void)acpi_ns_walk_namespace(ACPI_TYPE_ANY, node, ACPI_UINT32_MAX,
+ (void)acpi_ns_walk_namespace(ACPI_TYPE_ANY, node, max_depth,
ACPI_NS_WALK_UNLOCK, acpi_ev_reg_run, NULL,
&info, NULL);
@@ -814,7 +820,7 @@ acpi_ev_reg_run(acpi_handle obj_handle,
*
******************************************************************************/
-void
+static void
acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node,
acpi_adr_space_type space_id)
{
diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c
index 624361a..95f7838 100644
--- a/drivers/acpi/acpica/evxfregn.c
+++ b/drivers/acpi/acpica/evxfregn.c
@@ -85,7 +85,8 @@ acpi_install_address_space_handler_internal(acpi_handle device,
/* Run all _REG methods for this address space */
if (run_reg) {
- acpi_ev_execute_reg_methods(node, space_id, ACPI_REG_CONNECT);
+ acpi_ev_execute_reg_methods(node, ACPI_UINT32_MAX, space_id,
+ ACPI_REG_CONNECT);
}
unlock_and_exit:
@@ -263,6 +264,7 @@ ACPI_EXPORT_SYMBOL(acpi_remove_address_space_handler)
* FUNCTION: acpi_execute_reg_methods
*
* PARAMETERS: device - Handle for the device
+ * max_depth - Depth to which search for _REG
* space_id - The address space ID
*
* RETURN: Status
@@ -271,7 +273,8 @@ ACPI_EXPORT_SYMBOL(acpi_remove_address_space_handler)
*
******************************************************************************/
acpi_status
-acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id)
+acpi_execute_reg_methods(acpi_handle device, u32 max_depth,
+ acpi_adr_space_type space_id)
{
struct acpi_namespace_node *node;
acpi_status status;
@@ -296,7 +299,8 @@ acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id)
/* Run all _REG methods for this address space */
- acpi_ev_execute_reg_methods(node, space_id, ACPI_REG_CONNECT);
+ acpi_ev_execute_reg_methods(node, max_depth, space_id,
+ ACPI_REG_CONNECT);
} else {
status = AE_BAD_PARAMETER;
}
@@ -306,57 +310,3 @@ acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id)
}
ACPI_EXPORT_SYMBOL(acpi_execute_reg_methods)
-
-/*******************************************************************************
- *
- * FUNCTION: acpi_execute_orphan_reg_method
- *
- * PARAMETERS: device - Handle for the device
- * space_id - The address space ID
- *
- * RETURN: Status
- *
- * DESCRIPTION: Execute an "orphan" _REG method that appears under an ACPI
- * device. This is a _REG method that has no corresponding region
- * within the device's scope.
- *
- ******************************************************************************/
-acpi_status
-acpi_execute_orphan_reg_method(acpi_handle device, acpi_adr_space_type space_id)
-{
- struct acpi_namespace_node *node;
- acpi_status status;
-
- ACPI_FUNCTION_TRACE(acpi_execute_orphan_reg_method);
-
- /* Parameter validation */
-
- if (!device) {
- return_ACPI_STATUS(AE_BAD_PARAMETER);
- }
-
- status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
- if (ACPI_FAILURE(status)) {
- return_ACPI_STATUS(status);
- }
-
- /* Convert and validate the device handle */
-
- node = acpi_ns_validate_handle(device);
- if (node) {
-
- /*
- * If an "orphan" _REG method is present in the device's scope
- * for the given address space ID, run it.
- */
-
- acpi_ev_execute_orphan_reg_method(node, space_id);
- } else {
- status = AE_BAD_PARAMETER;
- }
-
- (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
- return_ACPI_STATUS(status);
-}
-
-ACPI_EXPORT_SYMBOL(acpi_execute_orphan_reg_method)
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 299ec65..38d2f6e 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1487,12 +1487,13 @@ static bool install_gpio_irq_event_handler(struct acpi_ec *ec)
static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device,
bool call_reg)
{
- acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle;
acpi_status status;
acpi_ec_start(ec, false);
if (!test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) {
+ acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle;
+
acpi_ec_enter_noirq(ec);
status = acpi_install_address_space_handler_no_reg(scope_handle,
ACPI_ADR_SPACE_EC,
@@ -1506,10 +1507,7 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device,
}
if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) {
- acpi_execute_reg_methods(scope_handle, ACPI_ADR_SPACE_EC);
- if (scope_handle != ec->handle)
- acpi_execute_orphan_reg_method(ec->handle, ACPI_ADR_SPACE_EC);
-
+ acpi_execute_reg_methods(ec->handle, ACPI_UINT32_MAX, ACPI_ADR_SPACE_EC);
set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags);
}
@@ -1724,6 +1722,12 @@ static void acpi_ec_remove(struct acpi_device *device)
}
}
+void acpi_ec_register_opregions(struct acpi_device *adev)
+{
+ if (first_ec && first_ec->handle != adev->handle)
+ acpi_execute_reg_methods(adev->handle, 1, ACPI_ADR_SPACE_EC);
+}
+
static acpi_status
ec_parse_io_ports(struct acpi_resource *resource, void *context)
{
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 601b670..aadd4c2 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -223,6 +223,7 @@ int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit,
acpi_handle handle, acpi_ec_query_func func,
void *data);
void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit);
+void acpi_ec_register_opregions(struct acpi_device *adev);
#ifdef CONFIG_PM_SLEEP
void acpi_ec_flush_work(void);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 5977141..22ae7829 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -2273,6 +2273,8 @@ static int acpi_bus_attach(struct acpi_device *device, void *first_pass)
if (device->handler)
goto ok;
+ acpi_ec_register_opregions(device);
+
if (!device->flags.initialized) {
device->flags.power_manageable =
device->power.states[ACPI_STATE_D0].flags.valid;
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index c11cbe5b..674b9db 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -54,6 +54,8 @@ static void acpi_video_parse_cmdline(void)
acpi_backlight_cmdline = acpi_backlight_nvidia_wmi_ec;
if (!strcmp("apple_gmux", acpi_video_backlight_string))
acpi_backlight_cmdline = acpi_backlight_apple_gmux;
+ if (!strcmp("dell_uart", acpi_video_backlight_string))
+ acpi_backlight_cmdline = acpi_backlight_dell_uart;
if (!strcmp("none", acpi_video_backlight_string))
acpi_backlight_cmdline = acpi_backlight_none;
}
@@ -822,6 +824,21 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
},
/*
+ * Dell AIO (All in Ones) which advertise an UART attached backlight
+ * controller board in their ACPI tables (and may even have one), but
+ * which need native backlight control nevertheless.
+ */
+ {
+ /* https://bugzilla.redhat.com/show_bug.cgi?id=2303936 */
+ .callback = video_detect_force_native,
+ /* Dell OptiPlex 7760 AIO */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 7760 AIO"),
+ },
+ },
+
+ /*
* Models which have nvidia-ec-wmi support, but should not use it.
* Note this indicates a likely firmware bug on these models and should
* be revisited if/when Linux gets support for dynamic mux mode.
@@ -918,6 +935,7 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto
static DEFINE_MUTEX(init_mutex);
static bool nvidia_wmi_ec_present;
static bool apple_gmux_present;
+ static bool dell_uart_present;
static bool native_available;
static bool init_done;
static long video_caps;
@@ -932,6 +950,7 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto
&video_caps, NULL);
nvidia_wmi_ec_present = nvidia_wmi_ec_supported();
apple_gmux_present = apple_gmux_detect(NULL, NULL);
+ dell_uart_present = acpi_dev_present("DELL0501", NULL, -1);
init_done = true;
}
if (native)
@@ -962,6 +981,9 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto
if (apple_gmux_present)
return acpi_backlight_apple_gmux;
+ if (dell_uart_present)
+ return acpi_backlight_dell_uart;
+
/* Use ACPI video if available, except when native should be preferred. */
if ((video_caps & ACPI_VIDEO_BACKLIGHT) &&
!(native_available && prefer_native_over_acpi_video()))
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index d6f5e25..473e00a 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -951,8 +951,19 @@ static void ata_gen_passthru_sense(struct ata_queued_cmd *qc)
&sense_key, &asc, &ascq);
ata_scsi_set_sense(qc->dev, cmd, sense_key, asc, ascq);
} else {
- /* ATA PASS-THROUGH INFORMATION AVAILABLE */
- ata_scsi_set_sense(qc->dev, cmd, RECOVERED_ERROR, 0, 0x1D);
+ /*
+ * ATA PASS-THROUGH INFORMATION AVAILABLE
+ *
+ * Note: we are supposed to call ata_scsi_set_sense(), which
+ * respects the D_SENSE bit, instead of unconditionally
+ * generating the sense data in descriptor format. However,
+ * because hdparm, hddtemp, and udisks incorrectly assume sense
+ * data in descriptor format, without even looking at the
+ * RESPONSE CODE field in the returned sense data (to see which
+ * format the returned sense data is in), we are stuck with
+ * being bug compatible with older kernels.
+ */
+ scsi_build_sense(cmd, 1, RECOVERED_ERROR, 0, 0x1D);
}
}
diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
index 1b85e8b..f2f36e5 100644
--- a/drivers/ata/pata_macio.c
+++ b/drivers/ata/pata_macio.c
@@ -208,6 +208,19 @@ static const char* macio_ata_names[] = {
/* Don't let a DMA segment go all the way to 64K */
#define MAX_DBDMA_SEG 0xff00
+#ifdef CONFIG_PAGE_SIZE_64KB
+/*
+ * The SCSI core requires the segment size to cover at least a page, so
+ * for 64K page size kernels it must be at least 64K. However the
+ * hardware can't handle 64K, so pata_macio_qc_prep() will split large
+ * requests. To handle the split requests the tablesize must be halved.
+ */
+#define PATA_MACIO_MAX_SEGMENT_SIZE SZ_64K
+#define PATA_MACIO_SG_TABLESIZE (MAX_DCMDS / 2)
+#else
+#define PATA_MACIO_MAX_SEGMENT_SIZE MAX_DBDMA_SEG
+#define PATA_MACIO_SG_TABLESIZE MAX_DCMDS
+#endif
/*
* Wait 1s for disk to answer on IDE bus after a hard reset
@@ -541,7 +554,8 @@ static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc)
while (sg_len) {
/* table overflow should never happen */
- BUG_ON (pi++ >= MAX_DCMDS);
+ if (WARN_ON_ONCE(pi >= MAX_DCMDS))
+ return AC_ERR_SYSTEM;
len = (sg_len < MAX_DBDMA_SEG) ? sg_len : MAX_DBDMA_SEG;
table->command = cpu_to_le16(write ? OUTPUT_MORE: INPUT_MORE);
@@ -553,11 +567,13 @@ static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc)
addr += len;
sg_len -= len;
++table;
+ ++pi;
}
}
/* Should never happen according to Tejun */
- BUG_ON(!pi);
+ if (WARN_ON_ONCE(!pi))
+ return AC_ERR_SYSTEM;
/* Convert the last command to an input/output */
table--;
@@ -912,16 +928,10 @@ static int pata_macio_do_resume(struct pata_macio_priv *priv)
static const struct scsi_host_template pata_macio_sht = {
__ATA_BASE_SHT(DRV_NAME),
- .sg_tablesize = MAX_DCMDS,
+ .sg_tablesize = PATA_MACIO_SG_TABLESIZE,
/* We may not need that strict one */
.dma_boundary = ATA_DMA_BOUNDARY,
- /*
- * The SCSI core requires the segment size to cover at least a page, so
- * for 64K page size kernels this must be at least 64K. However the
- * hardware can't handle 64K, so pata_macio_qc_prep() will split large
- * requests.
- */
- .max_segment_size = SZ_64K,
+ .max_segment_size = PATA_MACIO_MAX_SEGMENT_SIZE,
.device_configure = pata_macio_device_configure,
.sdev_groups = ata_common_sdev_groups,
.can_queue = ATA_DEF_QUEUE,
diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
index e7f713c..a876024 100644
--- a/drivers/atm/idt77252.c
+++ b/drivers/atm/idt77252.c
@@ -1118,8 +1118,8 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe)
rpp->len += skb->len;
if (stat & SAR_RSQE_EPDU) {
+ unsigned int len, truesize;
unsigned char *l1l2;
- unsigned int len;
l1l2 = (unsigned char *) ((unsigned long) skb->data + skb->len - 6);
@@ -1189,14 +1189,15 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe)
ATM_SKB(skb)->vcc = vcc;
__net_timestamp(skb);
+ truesize = skb->truesize;
vcc->push(vcc, skb);
atomic_inc(&vcc->stats->rx);
- if (skb->truesize > SAR_FB_SIZE_3)
+ if (truesize > SAR_FB_SIZE_3)
add_rx_skb(card, 3, SAR_FB_SIZE_3, 1);
- else if (skb->truesize > SAR_FB_SIZE_2)
+ else if (truesize > SAR_FB_SIZE_2)
add_rx_skb(card, 2, SAR_FB_SIZE_2, 1);
- else if (skb->truesize > SAR_FB_SIZE_1)
+ else if (truesize > SAR_FB_SIZE_1)
add_rx_skb(card, 1, SAR_FB_SIZE_1, 1);
else
add_rx_skb(card, 0, SAR_FB_SIZE_0, 1);
diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index 2ebc970..1ccbb515 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -12,6 +12,7 @@
#include <linux/acpi.h>
#include <acpi/acpi_bus.h>
#include <asm/unaligned.h>
+#include <linux/efi.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
@@ -26,6 +27,8 @@
#define ECDSA_OFFSET 644
#define ECDSA_HEADER_LEN 320
+#define BTINTEL_EFI_DSBR L"UefiCnvCommonDSBR"
+
enum {
DSM_SET_WDISABLE2_DELAY = 1,
DSM_SET_RESET_METHOD = 3,
@@ -2616,6 +2619,120 @@ static u8 btintel_classify_pkt_type(struct hci_dev *hdev, struct sk_buff *skb)
return hci_skb_pkt_type(skb);
}
+/*
+ * UefiCnvCommonDSBR UEFI variable provides information from the OEM platforms
+ * if they have replaced the BRI (Bluetooth Radio Interface) resistor to
+ * overcome the potential STEP errors on their designs. Based on the
+ * configauration, bluetooth firmware shall adjust the BRI response line drive
+ * strength. The below structure represents DSBR data.
+ * struct {
+ * u8 header;
+ * u32 dsbr;
+ * } __packed;
+ *
+ * header - defines revision number of the structure
+ * dsbr - defines drive strength BRI response
+ * bit0
+ * 0 - instructs bluetooth firmware to use default values
+ * 1 - instructs bluetooth firmware to override default values
+ * bit3:1
+ * Reserved
+ * bit7:4
+ * DSBR override values (only if bit0 is set. Default value is 0xF
+ * bit31:7
+ * Reserved
+ * Expected values for dsbr field:
+ * 1. 0xF1 - indicates that the resistor on board is 33 Ohm
+ * 2. 0x00 or 0xB1 - indicates that the resistor on board is 10 Ohm
+ * 3. Non existing UEFI variable or invalid (none of the above) - indicates
+ * that the resistor on board is 10 Ohm
+ * Even if uefi variable is not present, driver shall send 0xfc0a command to
+ * firmware to use default values.
+ *
+ */
+static int btintel_uefi_get_dsbr(u32 *dsbr_var)
+{
+ struct btintel_dsbr {
+ u8 header;
+ u32 dsbr;
+ } __packed data;
+
+ efi_status_t status;
+ unsigned long data_size = 0;
+ efi_guid_t guid = EFI_GUID(0xe65d8884, 0xd4af, 0x4b20, 0x8d, 0x03,
+ 0x77, 0x2e, 0xcc, 0x3d, 0xa5, 0x31);
+
+ if (!IS_ENABLED(CONFIG_EFI))
+ return -EOPNOTSUPP;
+
+ if (!efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE))
+ return -EOPNOTSUPP;
+
+ status = efi.get_variable(BTINTEL_EFI_DSBR, &guid, NULL, &data_size,
+ NULL);
+
+ if (status != EFI_BUFFER_TOO_SMALL || !data_size)
+ return -EIO;
+
+ status = efi.get_variable(BTINTEL_EFI_DSBR, &guid, NULL, &data_size,
+ &data);
+
+ if (status != EFI_SUCCESS)
+ return -ENXIO;
+
+ *dsbr_var = data.dsbr;
+ return 0;
+}
+
+static int btintel_set_dsbr(struct hci_dev *hdev, struct intel_version_tlv *ver)
+{
+ struct btintel_dsbr_cmd {
+ u8 enable;
+ u8 dsbr;
+ } __packed;
+
+ struct btintel_dsbr_cmd cmd;
+ struct sk_buff *skb;
+ u8 status;
+ u32 dsbr;
+ bool apply_dsbr;
+ int err;
+
+ /* DSBR command needs to be sent for BlazarI + B0 step product after
+ * downloading IML image.
+ */
+ apply_dsbr = (ver->img_type == BTINTEL_IMG_IML &&
+ ((ver->cnvi_top & 0xfff) == BTINTEL_CNVI_BLAZARI) &&
+ INTEL_CNVX_TOP_STEP(ver->cnvi_top) == 0x01);
+
+ if (!apply_dsbr)
+ return 0;
+
+ dsbr = 0;
+ err = btintel_uefi_get_dsbr(&dsbr);
+ if (err < 0)
+ bt_dev_dbg(hdev, "Error reading efi: %ls (%d)",
+ BTINTEL_EFI_DSBR, err);
+
+ cmd.enable = dsbr & BIT(0);
+ cmd.dsbr = dsbr >> 4 & 0xF;
+
+ bt_dev_info(hdev, "dsbr: enable: 0x%2.2x value: 0x%2.2x", cmd.enable,
+ cmd.dsbr);
+
+ skb = __hci_cmd_sync(hdev, 0xfc0a, sizeof(cmd), &cmd, HCI_CMD_TIMEOUT);
+ if (IS_ERR(skb))
+ return -bt_to_errno(PTR_ERR(skb));
+
+ status = skb->data[0];
+ kfree_skb(skb);
+
+ if (status)
+ return -bt_to_errno(status);
+
+ return 0;
+}
+
int btintel_bootloader_setup_tlv(struct hci_dev *hdev,
struct intel_version_tlv *ver)
{
@@ -2650,6 +2767,13 @@ int btintel_bootloader_setup_tlv(struct hci_dev *hdev,
if (err)
return err;
+ /* set drive strength of BRI response */
+ err = btintel_set_dsbr(hdev, ver);
+ if (err) {
+ bt_dev_err(hdev, "Failed to send dsbr command (%d)", err);
+ return err;
+ }
+
/* If image type returned is BTINTEL_IMG_IML, then controller supports
* intermediate loader image
*/
@@ -2945,9 +3069,6 @@ static int btintel_setup_combined(struct hci_dev *hdev)
INTEL_ROM_LEGACY_NO_WBS_SUPPORT))
set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED,
&hdev->quirks);
- if (ver.hw_variant == 0x08 && ver.fw_variant == 0x22)
- set_bit(HCI_QUIRK_VALID_LE_STATES,
- &hdev->quirks);
err = btintel_legacy_rom_setup(hdev, &ver);
break;
@@ -2956,7 +3077,6 @@ static int btintel_setup_combined(struct hci_dev *hdev)
case 0x12: /* ThP */
case 0x13: /* HrP */
case 0x14: /* CcP */
- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
fallthrough;
case 0x0c: /* WsP */
/* Apply the device specific HCI quirks
@@ -3048,9 +3168,6 @@ static int btintel_setup_combined(struct hci_dev *hdev)
/* These variants don't seem to support LE Coded PHY */
set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks);
- /* Set Valid LE States quirk */
- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
-
/* Setup MSFT Extension support */
btintel_set_msft_opcode(hdev, ver.hw_variant);
@@ -3076,9 +3193,6 @@ static int btintel_setup_combined(struct hci_dev *hdev)
*/
set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
- /* Apply LE States quirk from solar onwards */
- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
-
/* Setup MSFT Extension support */
btintel_set_msft_opcode(hdev,
INTEL_HW_VARIANT(ver_tlv.cnvi_bt));
diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index 0d1a041..1c7631f 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -1180,9 +1180,6 @@ static int btintel_pcie_setup(struct hci_dev *hdev)
*/
set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
- /* Apply LE States quirk from solar onwards */
- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
-
/* Setup MSFT Extension support */
btintel_set_msft_opcode(hdev,
INTEL_HW_VARIANT(ver_tlv.cnvi_bt));
diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c
index 39d6898..497e4c8 100644
--- a/drivers/bluetooth/btmtksdio.c
+++ b/drivers/bluetooth/btmtksdio.c
@@ -1148,9 +1148,6 @@ static int btmtksdio_setup(struct hci_dev *hdev)
}
}
- /* Valid LE States quirk for MediaTek 7921 */
- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
-
break;
case 0x7663:
case 0x7668:
diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index 31d3dd9..ad1ec6f 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -449,6 +449,23 @@ static bool ps_wakeup(struct btnxpuart_dev *nxpdev)
return false;
}
+static void ps_cleanup(struct btnxpuart_dev *nxpdev)
+{
+ struct ps_data *psdata = &nxpdev->psdata;
+ u8 ps_state;
+
+ mutex_lock(&psdata->ps_lock);
+ ps_state = psdata->ps_state;
+ mutex_unlock(&psdata->ps_lock);
+
+ if (ps_state != PS_STATE_AWAKE)
+ ps_control(psdata->hdev, PS_STATE_AWAKE);
+
+ ps_cancel_timer(nxpdev);
+ cancel_work_sync(&psdata->work);
+ mutex_destroy(&psdata->ps_lock);
+}
+
static int send_ps_cmd(struct hci_dev *hdev, void *data)
{
struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
@@ -1363,7 +1380,6 @@ static int btnxpuart_close(struct hci_dev *hdev)
{
struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
- ps_wakeup(nxpdev);
serdev_device_close(nxpdev->serdev);
skb_queue_purge(&nxpdev->txq);
if (!IS_ERR_OR_NULL(nxpdev->rx_skb)) {
@@ -1516,8 +1532,8 @@ static void nxp_serdev_remove(struct serdev_device *serdev)
nxpdev->new_baudrate = nxpdev->fw_init_baudrate;
nxp_set_baudrate_cmd(hdev, NULL);
}
- ps_cancel_timer(nxpdev);
}
+ ps_cleanup(nxpdev);
hci_unregister_dev(hdev);
hci_free_dev(hdev);
}
diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index f2f3714..fd7991e 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -1287,7 +1287,6 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev)
case CHIP_ID_8852C:
case CHIP_ID_8851B:
case CHIP_ID_8852BT:
- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
/* RTL8852C needs to transmit mSBC data continuously without
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index acdba5d..51d9d45 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -3956,8 +3956,8 @@ static int btusb_probe(struct usb_interface *intf,
if (id->driver_info & BTUSB_WIDEBAND_SPEECH)
set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
- if (id->driver_info & BTUSB_VALID_LE_STATES)
- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
+ if (!(id->driver_info & BTUSB_VALID_LE_STATES))
+ set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks);
if (id->driver_info & BTUSB_DIGIANSWER) {
data->cmdreq_type = USB_TYPE_VENDOR;
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 45adc15..4b1ad7e 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -2474,8 +2474,8 @@ static int qca_serdev_probe(struct serdev_device *serdev)
set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED,
&hdev->quirks);
- if (data->capabilities & QCA_CAP_VALID_LE_STATES)
- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
+ if (!(data->capabilities & QCA_CAP_VALID_LE_STATES))
+ set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks);
}
return 0;
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index c4046f8..43e9ac5 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -425,8 +425,6 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode)
if (opcode & 0x80)
set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks);
- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
-
if (hci_register_dev(hdev) < 0) {
BT_ERR("Can't register HCI device");
hci_free_dev(hdev);
diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c
index d3989b2..1e5b107 100644
--- a/drivers/char/tpm/tpm_ibmvtpm.c
+++ b/drivers/char/tpm/tpm_ibmvtpm.c
@@ -698,6 +698,10 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev,
rc = tpm2_get_cc_attrs_tbl(chip);
if (rc)
goto init_irq_cleanup;
+
+ rc = tpm2_sessions_init(chip);
+ if (rc)
+ goto init_irq_cleanup;
}
return tpm_chip_register(chip);
diff --git a/drivers/char/xillybus/xillyusb.c b/drivers/char/xillybus/xillyusb.c
index 5a5afa1..45771b1 100644
--- a/drivers/char/xillybus/xillyusb.c
+++ b/drivers/char/xillybus/xillyusb.c
@@ -50,6 +50,7 @@ MODULE_LICENSE("GPL v2");
static const char xillyname[] = "xillyusb";
static unsigned int fifo_buf_order;
+static struct workqueue_struct *wakeup_wq;
#define USB_VENDOR_ID_XILINX 0x03fd
#define USB_VENDOR_ID_ALTERA 0x09fb
@@ -569,10 +570,6 @@ static void cleanup_dev(struct kref *kref)
* errors if executed. The mechanism relies on that xdev->error is assigned
* a non-zero value by report_io_error() prior to queueing wakeup_all(),
* which prevents bulk_in_work() from calling process_bulk_in().
- *
- * The fact that wakeup_all() and bulk_in_work() are queued on the same
- * workqueue makes their concurrent execution very unlikely, however the
- * kernel's API doesn't seem to ensure this strictly.
*/
static void wakeup_all(struct work_struct *work)
@@ -627,7 +624,7 @@ static void report_io_error(struct xillyusb_dev *xdev,
if (do_once) {
kref_get(&xdev->kref); /* xdev is used by work item */
- queue_work(xdev->workq, &xdev->wakeup_workitem);
+ queue_work(wakeup_wq, &xdev->wakeup_workitem);
}
}
@@ -1906,6 +1903,13 @@ static const struct file_operations xillyusb_fops = {
static int xillyusb_setup_base_eps(struct xillyusb_dev *xdev)
{
+ struct usb_device *udev = xdev->udev;
+
+ /* Verify that device has the two fundamental bulk in/out endpoints */
+ if (usb_pipe_type_check(udev, usb_sndbulkpipe(udev, MSG_EP_NUM)) ||
+ usb_pipe_type_check(udev, usb_rcvbulkpipe(udev, IN_EP_NUM)))
+ return -ENODEV;
+
xdev->msg_ep = endpoint_alloc(xdev, MSG_EP_NUM | USB_DIR_OUT,
bulk_out_work, 1, 2);
if (!xdev->msg_ep)
@@ -1935,14 +1939,15 @@ static int setup_channels(struct xillyusb_dev *xdev,
__le16 *chandesc,
int num_channels)
{
- struct xillyusb_channel *chan;
+ struct usb_device *udev = xdev->udev;
+ struct xillyusb_channel *chan, *new_channels;
int i;
chan = kcalloc(num_channels, sizeof(*chan), GFP_KERNEL);
if (!chan)
return -ENOMEM;
- xdev->channels = chan;
+ new_channels = chan;
for (i = 0; i < num_channels; i++, chan++) {
unsigned int in_desc = le16_to_cpu(*chandesc++);
@@ -1971,6 +1976,15 @@ static int setup_channels(struct xillyusb_dev *xdev,
*/
if ((out_desc & 0x80) && i < 14) { /* Entry is valid */
+ if (usb_pipe_type_check(udev,
+ usb_sndbulkpipe(udev, i + 2))) {
+ dev_err(xdev->dev,
+ "Missing BULK OUT endpoint %d\n",
+ i + 2);
+ kfree(new_channels);
+ return -ENODEV;
+ }
+
chan->writable = 1;
chan->out_synchronous = !!(out_desc & 0x40);
chan->out_seekable = !!(out_desc & 0x20);
@@ -1980,6 +1994,7 @@ static int setup_channels(struct xillyusb_dev *xdev,
}
}
+ xdev->channels = new_channels;
return 0;
}
@@ -2096,9 +2111,11 @@ static int xillyusb_discovery(struct usb_interface *interface)
* just after responding with the IDT, there is no reason for any
* work item to be running now. To be sure that xdev->channels
* is updated on anything that might run in parallel, flush the
- * workqueue, which rarely does anything.
+ * device's workqueue and the wakeup work item. This rarely
+ * does anything.
*/
flush_workqueue(xdev->workq);
+ flush_work(&xdev->wakeup_workitem);
xdev->num_channels = num_channels;
@@ -2258,6 +2275,10 @@ static int __init xillyusb_init(void)
{
int rc = 0;
+ wakeup_wq = alloc_workqueue(xillyname, 0, 0);
+ if (!wakeup_wq)
+ return -ENOMEM;
+
if (LOG2_INITIAL_FIFO_BUF_SIZE > PAGE_SHIFT)
fifo_buf_order = LOG2_INITIAL_FIFO_BUF_SIZE - PAGE_SHIFT;
else
@@ -2265,12 +2286,17 @@ static int __init xillyusb_init(void)
rc = usb_register(&xillyusb_driver);
+ if (rc)
+ destroy_workqueue(wakeup_wq);
+
return rc;
}
static void __exit xillyusb_exit(void)
{
usb_deregister(&xillyusb_driver);
+
+ destroy_workqueue(wakeup_wq);
}
module_init(xillyusb_init);
diff --git a/drivers/clk/thead/clk-th1520-ap.c b/drivers/clk/thead/clk-th1520-ap.c
index cbc176b..17e32ae 100644
--- a/drivers/clk/thead/clk-th1520-ap.c
+++ b/drivers/clk/thead/clk-th1520-ap.c
@@ -738,7 +738,7 @@ static struct ccu_div vp_axi_clk = {
.hw.init = CLK_HW_INIT_PARENTS_HW("vp-axi",
video_pll_clk_parent,
&ccu_div_ops,
- 0),
+ CLK_IGNORE_UNUSED),
},
};
diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c
index 66b73c3..b731866 100644
--- a/drivers/cpufreq/amd-pstate-ut.c
+++ b/drivers/cpufreq/amd-pstate-ut.c
@@ -160,14 +160,17 @@ static void amd_pstate_ut_check_perf(u32 index)
lowest_perf = AMD_CPPC_LOWEST_PERF(cap1);
}
- if ((highest_perf != READ_ONCE(cpudata->highest_perf)) ||
- (nominal_perf != READ_ONCE(cpudata->nominal_perf)) ||
+ if (highest_perf != READ_ONCE(cpudata->highest_perf) && !cpudata->hw_prefcore) {
+ pr_err("%s cpu%d highest=%d %d highest perf doesn't match\n",
+ __func__, cpu, highest_perf, cpudata->highest_perf);
+ goto skip_test;
+ }
+ if ((nominal_perf != READ_ONCE(cpudata->nominal_perf)) ||
(lowest_nonlinear_perf != READ_ONCE(cpudata->lowest_nonlinear_perf)) ||
(lowest_perf != READ_ONCE(cpudata->lowest_perf))) {
amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
- pr_err("%s cpu%d highest=%d %d nominal=%d %d lowest_nonlinear=%d %d lowest=%d %d, they should be equal!\n",
- __func__, cpu, highest_perf, cpudata->highest_perf,
- nominal_perf, cpudata->nominal_perf,
+ pr_err("%s cpu%d nominal=%d %d lowest_nonlinear=%d %d lowest=%d %d, they should be equal!\n",
+ __func__, cpu, nominal_perf, cpudata->nominal_perf,
lowest_nonlinear_perf, cpudata->lowest_nonlinear_perf,
lowest_perf, cpudata->lowest_perf);
goto skip_test;
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 68c616b..89bda7a 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -321,7 +321,7 @@ static inline int pstate_enable(bool enable)
return 0;
for_each_present_cpu(cpu) {
- unsigned long logical_id = topology_logical_die_id(cpu);
+ unsigned long logical_id = topology_logical_package_id(cpu);
if (test_bit(logical_id, &logical_proc_id_mask))
continue;
@@ -692,7 +692,7 @@ static int amd_pstate_cpu_boost_update(struct cpufreq_policy *policy, bool on)
struct amd_cpudata *cpudata = policy->driver_data;
struct cppc_perf_ctrls perf_ctrls;
u32 highest_perf, nominal_perf, nominal_freq, max_freq;
- int ret;
+ int ret = 0;
highest_perf = READ_ONCE(cpudata->highest_perf);
nominal_perf = READ_ONCE(cpudata->nominal_perf);
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index a663e75..51132a5 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -834,11 +834,13 @@ static void cxl_disable_rch_root_ints(struct cxl_dport *dport)
void cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport)
{
struct device *dport_dev = dport->dport_dev;
- struct pci_host_bridge *host_bridge;
- host_bridge = to_pci_host_bridge(dport_dev);
- if (host_bridge->native_aer)
- dport->rcrb.aer_cap = cxl_rcrb_to_aer(dport_dev, dport->rcrb.base);
+ if (dport->rch) {
+ struct pci_host_bridge *host_bridge = to_pci_host_bridge(dport_dev);
+
+ if (host_bridge->native_aer)
+ dport->rcrb.aer_cap = cxl_rcrb_to_aer(dport_dev, dport->rcrb.base);
+ }
dport->reg_map.host = host;
cxl_dport_map_regs(dport);
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-core.c b/drivers/dma/dw-edma/dw-hdma-v0-core.c
index 10e8f07..e3f8db4 100644
--- a/drivers/dma/dw-edma/dw-hdma-v0-core.c
+++ b/drivers/dma/dw-edma/dw-hdma-v0-core.c
@@ -17,8 +17,8 @@ enum dw_hdma_control {
DW_HDMA_V0_CB = BIT(0),
DW_HDMA_V0_TCB = BIT(1),
DW_HDMA_V0_LLP = BIT(2),
- DW_HDMA_V0_LIE = BIT(3),
- DW_HDMA_V0_RIE = BIT(4),
+ DW_HDMA_V0_LWIE = BIT(3),
+ DW_HDMA_V0_RWIE = BIT(4),
DW_HDMA_V0_CCS = BIT(8),
DW_HDMA_V0_LLE = BIT(9),
};
@@ -195,25 +195,14 @@ static void dw_hdma_v0_write_ll_link(struct dw_edma_chunk *chunk,
static void dw_hdma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
{
struct dw_edma_burst *child;
- struct dw_edma_chan *chan = chunk->chan;
u32 control = 0, i = 0;
- int j;
if (chunk->cb)
control = DW_HDMA_V0_CB;
- j = chunk->bursts_alloc;
- list_for_each_entry(child, &chunk->burst->list, list) {
- j--;
- if (!j) {
- control |= DW_HDMA_V0_LIE;
- if (!(chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL))
- control |= DW_HDMA_V0_RIE;
- }
-
+ list_for_each_entry(child, &chunk->burst->list, list)
dw_hdma_v0_write_ll_data(chunk, i++, control, child->sz,
child->sar, child->dar);
- }
control = DW_HDMA_V0_LLP | DW_HDMA_V0_TCB;
if (!chunk->cb)
@@ -247,10 +236,11 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
if (first) {
/* Enable engine */
SET_CH_32(dw, chan->dir, chan->id, ch_en, BIT(0));
- /* Interrupt enable&unmask - done, abort */
- tmp = GET_CH_32(dw, chan->dir, chan->id, int_setup) |
- HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK |
- HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_ABORT_INT_EN;
+ /* Interrupt unmask - stop, abort */
+ tmp = GET_CH_32(dw, chan->dir, chan->id, int_setup);
+ tmp &= ~(HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK);
+ /* Interrupt enable - stop, abort */
+ tmp |= HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_ABORT_INT_EN;
if (!(dw->chip->flags & DW_EDMA_CHIP_LOCAL))
tmp |= HDMA_V0_REMOTE_STOP_INT_EN | HDMA_V0_REMOTE_ABORT_INT_EN;
SET_CH_32(dw, chan->dir, chan->id, int_setup, tmp);
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 5f7d690..dd75f97 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -16,6 +16,7 @@
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/io.h>
+#include <linux/log2.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/slab.h>
@@ -621,12 +622,10 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
struct dw_desc *prev;
struct dw_desc *first;
u32 ctllo, ctlhi;
- u8 m_master = dwc->dws.m_master;
- u8 lms = DWC_LLP_LMS(m_master);
+ u8 lms = DWC_LLP_LMS(dwc->dws.m_master);
dma_addr_t reg;
unsigned int reg_width;
unsigned int mem_width;
- unsigned int data_width = dw->pdata->data_width[m_master];
unsigned int i;
struct scatterlist *sg;
size_t total_len = 0;
@@ -660,7 +659,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
mem = sg_dma_address(sg);
len = sg_dma_len(sg);
- mem_width = __ffs(data_width | mem | len);
+ mem_width = __ffs(sconfig->src_addr_width | mem | len);
slave_sg_todev_fill_desc:
desc = dwc_desc_get(dwc);
@@ -720,7 +719,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
lli_write(desc, sar, reg);
lli_write(desc, dar, mem);
lli_write(desc, ctlhi, ctlhi);
- mem_width = __ffs(data_width | mem);
+ mem_width = __ffs(sconfig->dst_addr_width | mem);
lli_write(desc, ctllo, ctllo | DWC_CTLL_DST_WIDTH(mem_width));
desc->len = dlen;
@@ -780,20 +779,108 @@ bool dw_dma_filter(struct dma_chan *chan, void *param)
}
EXPORT_SYMBOL_GPL(dw_dma_filter);
-static int dwc_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
+static int dwc_verify_maxburst(struct dma_chan *chan)
+{
+ struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+
+ dwc->dma_sconfig.src_maxburst =
+ clamp(dwc->dma_sconfig.src_maxburst, 1U, dwc->max_burst);
+ dwc->dma_sconfig.dst_maxburst =
+ clamp(dwc->dma_sconfig.dst_maxburst, 1U, dwc->max_burst);
+
+ dwc->dma_sconfig.src_maxburst =
+ rounddown_pow_of_two(dwc->dma_sconfig.src_maxburst);
+ dwc->dma_sconfig.dst_maxburst =
+ rounddown_pow_of_two(dwc->dma_sconfig.dst_maxburst);
+
+ return 0;
+}
+
+static int dwc_verify_p_buswidth(struct dma_chan *chan)
{
struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
struct dw_dma *dw = to_dw_dma(chan->device);
+ u32 reg_width, max_width;
+
+ if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV)
+ reg_width = dwc->dma_sconfig.dst_addr_width;
+ else if (dwc->dma_sconfig.direction == DMA_DEV_TO_MEM)
+ reg_width = dwc->dma_sconfig.src_addr_width;
+ else /* DMA_MEM_TO_MEM */
+ return 0;
+
+ max_width = dw->pdata->data_width[dwc->dws.p_master];
+
+ /* Fall-back to 1-byte transfer width if undefined */
+ if (reg_width == DMA_SLAVE_BUSWIDTH_UNDEFINED)
+ reg_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
+ else if (!is_power_of_2(reg_width) || reg_width > max_width)
+ return -EINVAL;
+ else /* bus width is valid */
+ return 0;
+
+ /* Update undefined addr width value */
+ if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV)
+ dwc->dma_sconfig.dst_addr_width = reg_width;
+ else /* DMA_DEV_TO_MEM */
+ dwc->dma_sconfig.src_addr_width = reg_width;
+
+ return 0;
+}
+
+static int dwc_verify_m_buswidth(struct dma_chan *chan)
+{
+ struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+ struct dw_dma *dw = to_dw_dma(chan->device);
+ u32 reg_width, reg_burst, mem_width;
+
+ mem_width = dw->pdata->data_width[dwc->dws.m_master];
+
+ /*
+ * It's possible to have a data portion locked in the DMA FIFO in case
+ * of the channel suspension. Subsequent channel disabling will cause
+ * that data silent loss. In order to prevent that maintain the src and
+ * dst transfer widths coherency by means of the relation:
+ * (CTLx.SRC_TR_WIDTH * CTLx.SRC_MSIZE >= CTLx.DST_TR_WIDTH)
+ * Look for the details in the commit message that brings this change.
+ *
+ * Note the DMA configs utilized in the calculations below must have
+ * been verified to have correct values by this method call.
+ */
+ if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV) {
+ reg_width = dwc->dma_sconfig.dst_addr_width;
+ if (mem_width < reg_width)
+ return -EINVAL;
+
+ dwc->dma_sconfig.src_addr_width = mem_width;
+ } else if (dwc->dma_sconfig.direction == DMA_DEV_TO_MEM) {
+ reg_width = dwc->dma_sconfig.src_addr_width;
+ reg_burst = dwc->dma_sconfig.src_maxburst;
+
+ dwc->dma_sconfig.dst_addr_width = min(mem_width, reg_width * reg_burst);
+ }
+
+ return 0;
+}
+
+static int dwc_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
+{
+ struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+ int ret;
memcpy(&dwc->dma_sconfig, sconfig, sizeof(*sconfig));
- dwc->dma_sconfig.src_maxburst =
- clamp(dwc->dma_sconfig.src_maxburst, 0U, dwc->max_burst);
- dwc->dma_sconfig.dst_maxburst =
- clamp(dwc->dma_sconfig.dst_maxburst, 0U, dwc->max_burst);
+ ret = dwc_verify_maxburst(chan);
+ if (ret)
+ return ret;
- dw->encode_maxburst(dwc, &dwc->dma_sconfig.src_maxburst);
- dw->encode_maxburst(dwc, &dwc->dma_sconfig.dst_maxburst);
+ ret = dwc_verify_p_buswidth(chan);
+ if (ret)
+ return ret;
+
+ ret = dwc_verify_m_buswidth(chan);
+ if (ret)
+ return ret;
return 0;
}
@@ -1068,7 +1155,7 @@ int do_dma_probe(struct dw_dma_chip *chip)
bool autocfg = false;
unsigned int dw_params;
unsigned int i;
- int err;
+ int ret;
dw->pdata = devm_kzalloc(chip->dev, sizeof(*dw->pdata), GFP_KERNEL);
if (!dw->pdata)
@@ -1084,7 +1171,7 @@ int do_dma_probe(struct dw_dma_chip *chip)
autocfg = dw_params >> DW_PARAMS_EN & 1;
if (!autocfg) {
- err = -EINVAL;
+ ret = -EINVAL;
goto err_pdata;
}
@@ -1104,7 +1191,7 @@ int do_dma_probe(struct dw_dma_chip *chip)
pdata->chan_allocation_order = CHAN_ALLOCATION_ASCENDING;
pdata->chan_priority = CHAN_PRIORITY_ASCENDING;
} else if (chip->pdata->nr_channels > DW_DMA_MAX_NR_CHANNELS) {
- err = -EINVAL;
+ ret = -EINVAL;
goto err_pdata;
} else {
memcpy(dw->pdata, chip->pdata, sizeof(*dw->pdata));
@@ -1116,7 +1203,7 @@ int do_dma_probe(struct dw_dma_chip *chip)
dw->chan = devm_kcalloc(chip->dev, pdata->nr_channels, sizeof(*dw->chan),
GFP_KERNEL);
if (!dw->chan) {
- err = -ENOMEM;
+ ret = -ENOMEM;
goto err_pdata;
}
@@ -1134,15 +1221,15 @@ int do_dma_probe(struct dw_dma_chip *chip)
sizeof(struct dw_desc), 4, 0);
if (!dw->desc_pool) {
dev_err(chip->dev, "No memory for descriptors dma pool\n");
- err = -ENOMEM;
+ ret = -ENOMEM;
goto err_pdata;
}
tasklet_setup(&dw->tasklet, dw_dma_tasklet);
- err = request_irq(chip->irq, dw_dma_interrupt, IRQF_SHARED,
+ ret = request_irq(chip->irq, dw_dma_interrupt, IRQF_SHARED,
dw->name, dw);
- if (err)
+ if (ret)
goto err_pdata;
INIT_LIST_HEAD(&dw->dma.channels);
@@ -1254,8 +1341,8 @@ int do_dma_probe(struct dw_dma_chip *chip)
*/
dma_set_max_seg_size(dw->dma.dev, dw->chan[0].block_size);
- err = dma_async_device_register(&dw->dma);
- if (err)
+ ret = dma_async_device_register(&dw->dma);
+ if (ret)
goto err_dma_register;
dev_info(chip->dev, "DesignWare DMA Controller, %d channels\n",
@@ -1269,7 +1356,7 @@ int do_dma_probe(struct dw_dma_chip *chip)
free_irq(chip->irq, dw);
err_pdata:
pm_runtime_put_sync_suspend(chip->dev);
- return err;
+ return ret;
}
int do_dma_remove(struct dw_dma_chip *chip)
diff --git a/drivers/dma/dw/dw.c b/drivers/dma/dw/dw.c
index a486226..6766142 100644
--- a/drivers/dma/dw/dw.c
+++ b/drivers/dma/dw/dw.c
@@ -64,28 +64,37 @@ static size_t dw_dma_block2bytes(struct dw_dma_chan *dwc, u32 block, u32 width)
return DWC_CTLH_BLOCK_TS(block) << width;
}
-static u32 dw_dma_prepare_ctllo(struct dw_dma_chan *dwc)
-{
- struct dma_slave_config *sconfig = &dwc->dma_sconfig;
- u8 smsize = (dwc->direction == DMA_DEV_TO_MEM) ? sconfig->src_maxburst : 0;
- u8 dmsize = (dwc->direction == DMA_MEM_TO_DEV) ? sconfig->dst_maxburst : 0;
- u8 p_master = dwc->dws.p_master;
- u8 m_master = dwc->dws.m_master;
- u8 dms = (dwc->direction == DMA_MEM_TO_DEV) ? p_master : m_master;
- u8 sms = (dwc->direction == DMA_DEV_TO_MEM) ? p_master : m_master;
-
- return DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN |
- DWC_CTLL_DST_MSIZE(dmsize) | DWC_CTLL_SRC_MSIZE(smsize) |
- DWC_CTLL_DMS(dms) | DWC_CTLL_SMS(sms);
-}
-
-static void dw_dma_encode_maxburst(struct dw_dma_chan *dwc, u32 *maxburst)
+static inline u8 dw_dma_encode_maxburst(u32 maxburst)
{
/*
* Fix burst size according to dw_dmac. We need to convert them as:
* 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3.
*/
- *maxburst = *maxburst > 1 ? fls(*maxburst) - 2 : 0;
+ return maxburst > 1 ? fls(maxburst) - 2 : 0;
+}
+
+static u32 dw_dma_prepare_ctllo(struct dw_dma_chan *dwc)
+{
+ struct dma_slave_config *sconfig = &dwc->dma_sconfig;
+ u8 smsize = 0, dmsize = 0;
+ u8 sms, dms;
+
+ if (dwc->direction == DMA_MEM_TO_DEV) {
+ sms = dwc->dws.m_master;
+ dms = dwc->dws.p_master;
+ dmsize = dw_dma_encode_maxburst(sconfig->dst_maxburst);
+ } else if (dwc->direction == DMA_DEV_TO_MEM) {
+ sms = dwc->dws.p_master;
+ dms = dwc->dws.m_master;
+ smsize = dw_dma_encode_maxburst(sconfig->src_maxburst);
+ } else /* DMA_MEM_TO_MEM */ {
+ sms = dwc->dws.m_master;
+ dms = dwc->dws.m_master;
+ }
+
+ return DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN |
+ DWC_CTLL_DST_MSIZE(dmsize) | DWC_CTLL_SRC_MSIZE(smsize) |
+ DWC_CTLL_DMS(dms) | DWC_CTLL_SMS(sms);
}
static void dw_dma_set_device_name(struct dw_dma *dw, int id)
@@ -116,7 +125,6 @@ int dw_dma_probe(struct dw_dma_chip *chip)
dw->suspend_chan = dw_dma_suspend_chan;
dw->resume_chan = dw_dma_resume_chan;
dw->prepare_ctllo = dw_dma_prepare_ctllo;
- dw->encode_maxburst = dw_dma_encode_maxburst;
dw->bytes2block = dw_dma_bytes2block;
dw->block2bytes = dw_dma_block2bytes;
diff --git a/drivers/dma/dw/idma32.c b/drivers/dma/dw/idma32.c
index 58f4078..dac617c 100644
--- a/drivers/dma/dw/idma32.c
+++ b/drivers/dma/dw/idma32.c
@@ -199,21 +199,25 @@ static size_t idma32_block2bytes(struct dw_dma_chan *dwc, u32 block, u32 width)
return IDMA32C_CTLH_BLOCK_TS(block);
}
+static inline u8 idma32_encode_maxburst(u32 maxburst)
+{
+ return maxburst > 1 ? fls(maxburst) - 1 : 0;
+}
+
static u32 idma32_prepare_ctllo(struct dw_dma_chan *dwc)
{
struct dma_slave_config *sconfig = &dwc->dma_sconfig;
- u8 smsize = (dwc->direction == DMA_DEV_TO_MEM) ? sconfig->src_maxburst : 0;
- u8 dmsize = (dwc->direction == DMA_MEM_TO_DEV) ? sconfig->dst_maxburst : 0;
+ u8 smsize = 0, dmsize = 0;
+
+ if (dwc->direction == DMA_MEM_TO_DEV)
+ dmsize = idma32_encode_maxburst(sconfig->dst_maxburst);
+ else if (dwc->direction == DMA_DEV_TO_MEM)
+ smsize = idma32_encode_maxburst(sconfig->src_maxburst);
return DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN |
DWC_CTLL_DST_MSIZE(dmsize) | DWC_CTLL_SRC_MSIZE(smsize);
}
-static void idma32_encode_maxburst(struct dw_dma_chan *dwc, u32 *maxburst)
-{
- *maxburst = *maxburst > 1 ? fls(*maxburst) - 1 : 0;
-}
-
static void idma32_set_device_name(struct dw_dma *dw, int id)
{
snprintf(dw->name, sizeof(dw->name), "idma32:dmac%d", id);
@@ -270,7 +274,6 @@ int idma32_dma_probe(struct dw_dma_chip *chip)
dw->suspend_chan = idma32_suspend_chan;
dw->resume_chan = idma32_resume_chan;
dw->prepare_ctllo = idma32_prepare_ctllo;
- dw->encode_maxburst = idma32_encode_maxburst;
dw->bytes2block = idma32_bytes2block;
dw->block2bytes = idma32_block2bytes;
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index 7d9d4c9..47c58ad 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -29,7 +29,7 @@ static int dw_probe(struct platform_device *pdev)
struct dw_dma_chip_pdata *data;
struct dw_dma_chip *chip;
struct device *dev = &pdev->dev;
- int err;
+ int ret;
match = device_get_match_data(dev);
if (!match)
@@ -51,9 +51,9 @@ static int dw_probe(struct platform_device *pdev)
if (IS_ERR(chip->regs))
return PTR_ERR(chip->regs);
- err = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
- if (err)
- return err;
+ ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+ if (ret)
+ return ret;
if (!data->pdata)
data->pdata = dev_get_platdata(dev);
@@ -69,14 +69,14 @@ static int dw_probe(struct platform_device *pdev)
chip->clk = devm_clk_get_optional(chip->dev, "hclk");
if (IS_ERR(chip->clk))
return PTR_ERR(chip->clk);
- err = clk_prepare_enable(chip->clk);
- if (err)
- return err;
+ ret = clk_prepare_enable(chip->clk);
+ if (ret)
+ return ret;
pm_runtime_enable(&pdev->dev);
- err = data->probe(chip);
- if (err)
+ ret = data->probe(chip);
+ if (ret)
goto err_dw_dma_probe;
platform_set_drvdata(pdev, data);
@@ -90,7 +90,7 @@ static int dw_probe(struct platform_device *pdev)
err_dw_dma_probe:
pm_runtime_disable(&pdev->dev);
clk_disable_unprepare(chip->clk);
- return err;
+ return ret;
}
static void dw_remove(struct platform_device *pdev)
diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h
index 76654bd..5969d9c 100644
--- a/drivers/dma/dw/regs.h
+++ b/drivers/dma/dw/regs.h
@@ -327,7 +327,6 @@ struct dw_dma {
void (*suspend_chan)(struct dw_dma_chan *dwc, bool drain);
void (*resume_chan)(struct dw_dma_chan *dwc, bool drain);
u32 (*prepare_ctllo)(struct dw_dma_chan *dwc);
- void (*encode_maxburst)(struct dw_dma_chan *dwc, u32 *maxburst);
u32 (*bytes2block)(struct dw_dma_chan *dwc, size_t bytes,
unsigned int width, size_t *len);
size_t (*block2bytes)(struct dw_dma_chan *dwc, u32 block, u32 width);
diff --git a/drivers/dma/stm32/stm32-dma3.c b/drivers/dma/stm32/stm32-dma3.c
index 4087e02..0be6e94 100644
--- a/drivers/dma/stm32/stm32-dma3.c
+++ b/drivers/dma/stm32/stm32-dma3.c
@@ -403,6 +403,7 @@ static struct stm32_dma3_swdesc *stm32_dma3_chan_desc_alloc(struct stm32_dma3_ch
swdesc = kzalloc(struct_size(swdesc, lli, count), GFP_NOWAIT);
if (!swdesc)
return NULL;
+ swdesc->lli_size = count;
for (i = 0; i < count; i++) {
swdesc->lli[i].hwdesc = dma_pool_zalloc(chan->lli_pool, GFP_NOWAIT,
@@ -410,7 +411,6 @@ static struct stm32_dma3_swdesc *stm32_dma3_chan_desc_alloc(struct stm32_dma3_ch
if (!swdesc->lli[i].hwdesc)
goto err_pool_free;
}
- swdesc->lli_size = count;
swdesc->ccr = 0;
/* Set LL base address */
diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c
index 7e6c04a..6ab9bfb 100644
--- a/drivers/dma/ti/omap-dma.c
+++ b/drivers/dma/ti/omap-dma.c
@@ -1186,10 +1186,10 @@ static struct dma_async_tx_descriptor *omap_dma_prep_dma_cyclic(
d->dev_addr = dev_addr;
d->fi = burst;
d->es = es;
+ d->sglen = 1;
d->sg[0].addr = buf_addr;
d->sg[0].en = period_len / es_bytes[es];
d->sg[0].fn = buf_len / period_len;
- d->sglen = 1;
d->ccr = c->ccr;
if (dir == DMA_DEV_TO_MEM)
@@ -1258,10 +1258,10 @@ static struct dma_async_tx_descriptor *omap_dma_prep_dma_memcpy(
d->dev_addr = src;
d->fi = 0;
d->es = data_type;
+ d->sglen = 1;
d->sg[0].en = len / BIT(data_type);
d->sg[0].fn = 1;
d->sg[0].addr = dest;
- d->sglen = 1;
d->ccr = c->ccr;
d->ccr |= CCR_DST_AMODE_POSTINC | CCR_SRC_AMODE_POSTINC;
@@ -1309,6 +1309,7 @@ static struct dma_async_tx_descriptor *omap_dma_prep_dma_interleaved(
if (data_type > CSDP_DATA_TYPE_32)
data_type = CSDP_DATA_TYPE_32;
+ d->sglen = 1;
sg = &d->sg[0];
d->dir = DMA_MEM_TO_MEM;
d->dev_addr = xt->src_start;
@@ -1316,7 +1317,6 @@ static struct dma_async_tx_descriptor *omap_dma_prep_dma_interleaved(
sg->en = xt->sgl[0].size / BIT(data_type);
sg->fn = xt->numf;
sg->addr = xt->dst_start;
- d->sglen = 1;
d->ccr = c->ccr;
src_icg = dmaengine_get_src_icg(xt, &xt->sgl[0]);
diff --git a/drivers/firmware/microchip/mpfs-auto-update.c b/drivers/firmware/microchip/mpfs-auto-update.c
index 30de4789..9ca5ee5 100644
--- a/drivers/firmware/microchip/mpfs-auto-update.c
+++ b/drivers/firmware/microchip/mpfs-auto-update.c
@@ -166,7 +166,7 @@ static enum fw_upload_err mpfs_auto_update_poll_complete(struct fw_upload *fw_up
*/
ret = wait_for_completion_timeout(&priv->programming_complete,
msecs_to_jiffies(AUTO_UPDATE_TIMEOUT_MS));
- if (ret)
+ if (!ret)
return FW_UPLOAD_ERR_TIMEOUT;
return FW_UPLOAD_ERR_NONE;
diff --git a/drivers/firmware/qcom/qcom_scm-smc.c b/drivers/firmware/qcom/qcom_scm-smc.c
index dca5f3f..2b4c282 100644
--- a/drivers/firmware/qcom/qcom_scm-smc.c
+++ b/drivers/firmware/qcom/qcom_scm-smc.c
@@ -73,7 +73,7 @@ int scm_get_wq_ctx(u32 *wq_ctx, u32 *flags, u32 *more_pending)
struct arm_smccc_res get_wq_res;
struct arm_smccc_args get_wq_ctx = {0};
- get_wq_ctx.args[0] = ARM_SMCCC_CALL_VAL(ARM_SMCCC_STD_CALL,
+ get_wq_ctx.args[0] = ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,
ARM_SMCCC_SMC_64, ARM_SMCCC_OWNER_SIP,
SCM_SMC_FNID(QCOM_SCM_SVC_WAITQ, QCOM_SCM_WAITQ_GET_WQ_CTX));
diff --git a/drivers/firmware/qcom/qcom_tzmem.c b/drivers/firmware/qcom/qcom_tzmem.c
index 17948cf..92b3651 100644
--- a/drivers/firmware/qcom/qcom_tzmem.c
+++ b/drivers/firmware/qcom/qcom_tzmem.c
@@ -40,7 +40,6 @@ struct qcom_tzmem_pool {
};
struct qcom_tzmem_chunk {
- phys_addr_t paddr;
size_t size;
struct qcom_tzmem_pool *owner;
};
@@ -78,6 +77,7 @@ static bool qcom_tzmem_using_shm_bridge;
/* List of machines that are known to not support SHM bridge correctly. */
static const char *const qcom_tzmem_blacklist[] = {
"qcom,sc8180x",
+ "qcom,sdm670", /* failure in GPU firmware loading */
"qcom,sdm845", /* reset in rmtfs memory assignment */
"qcom,sm8150", /* reset in rmtfs memory assignment */
NULL
@@ -385,7 +385,6 @@ void *qcom_tzmem_alloc(struct qcom_tzmem_pool *pool, size_t size, gfp_t gfp)
return NULL;
}
- chunk->paddr = gen_pool_virt_to_phys(pool->genpool, vaddr);
chunk->size = size;
chunk->owner = pool;
@@ -431,25 +430,37 @@ void qcom_tzmem_free(void *vaddr)
EXPORT_SYMBOL_GPL(qcom_tzmem_free);
/**
- * qcom_tzmem_to_phys() - Map the virtual address of a TZ buffer to physical.
- * @vaddr: Virtual address of the buffer allocated from a TZ memory pool.
+ * qcom_tzmem_to_phys() - Map the virtual address of TZ memory to physical.
+ * @vaddr: Virtual address of memory allocated from a TZ memory pool.
*
- * Can be used in any context. The address must have been returned by a call
- * to qcom_tzmem_alloc().
+ * Can be used in any context. The address must point to memory allocated
+ * using qcom_tzmem_alloc().
*
- * Returns: Physical address of the buffer.
+ * Returns:
+ * Physical address mapped from the virtual or 0 if the mapping failed.
*/
phys_addr_t qcom_tzmem_to_phys(void *vaddr)
{
struct qcom_tzmem_chunk *chunk;
+ struct radix_tree_iter iter;
+ void __rcu **slot;
+ phys_addr_t ret;
guard(spinlock_irqsave)(&qcom_tzmem_chunks_lock);
- chunk = radix_tree_lookup(&qcom_tzmem_chunks, (unsigned long)vaddr);
- if (!chunk)
- return 0;
+ radix_tree_for_each_slot(slot, &qcom_tzmem_chunks, &iter, 0) {
+ chunk = radix_tree_deref_slot_protected(slot,
+ &qcom_tzmem_chunks_lock);
- return chunk->paddr;
+ ret = gen_pool_virt_to_phys(chunk->owner->genpool,
+ (unsigned long)vaddr);
+ if (ret == -1)
+ continue;
+
+ return ret;
+ }
+
+ return 0;
}
EXPORT_SYMBOL_GPL(qcom_tzmem_to_phys);
diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c
index 921f615..02a07d3 100644
--- a/drivers/firmware/sysfb.c
+++ b/drivers/firmware/sysfb.c
@@ -39,6 +39,8 @@ static struct platform_device *pd;
static DEFINE_MUTEX(disable_lock);
static bool disabled;
+static struct device *sysfb_parent_dev(const struct screen_info *si);
+
static bool sysfb_unregister(void)
{
if (IS_ERR_OR_NULL(pd))
@@ -52,6 +54,7 @@ static bool sysfb_unregister(void)
/**
* sysfb_disable() - disable the Generic System Framebuffers support
+ * @dev: the device to check if non-NULL
*
* This disables the registration of system framebuffer devices that match the
* generic drivers that make use of the system framebuffer set up by firmware.
@@ -61,17 +64,21 @@ static bool sysfb_unregister(void)
* Context: The function can sleep. A @disable_lock mutex is acquired to serialize
* against sysfb_init(), that registers a system framebuffer device.
*/
-void sysfb_disable(void)
+void sysfb_disable(struct device *dev)
{
+ struct screen_info *si = &screen_info;
+
mutex_lock(&disable_lock);
- sysfb_unregister();
- disabled = true;
+ if (!dev || dev == sysfb_parent_dev(si)) {
+ sysfb_unregister();
+ disabled = true;
+ }
mutex_unlock(&disable_lock);
}
EXPORT_SYMBOL_GPL(sysfb_disable);
#if defined(CONFIG_PCI)
-static __init bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev)
+static bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev)
{
/*
* TODO: Try to integrate this code into the PCI subsystem
@@ -87,13 +94,13 @@ static __init bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev)
return true;
}
#else
-static __init bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev)
+static bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev)
{
return false;
}
#endif
-static __init struct device *sysfb_parent_dev(const struct screen_info *si)
+static struct device *sysfb_parent_dev(const struct screen_info *si)
{
struct pci_dev *pdev;
diff --git a/drivers/gpio/gpio-mlxbf3.c b/drivers/gpio/gpio-mlxbf3.c
index d5906d4..10ea712 100644
--- a/drivers/gpio/gpio-mlxbf3.c
+++ b/drivers/gpio/gpio-mlxbf3.c
@@ -39,6 +39,8 @@
#define MLXBF_GPIO_CAUSE_OR_EVTEN0 0x14
#define MLXBF_GPIO_CAUSE_OR_CLRCAUSE 0x18
+#define MLXBF_GPIO_CLR_ALL_INTS GENMASK(31, 0)
+
struct mlxbf3_gpio_context {
struct gpio_chip gc;
@@ -82,6 +84,8 @@ static void mlxbf3_gpio_irq_disable(struct irq_data *irqd)
val = readl(gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0);
val &= ~BIT(offset);
writel(val, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0);
+
+ writel(BIT(offset), gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_CLRCAUSE);
raw_spin_unlock_irqrestore(&gs->gc.bgpio_lock, flags);
gpiochip_disable_irq(gc, offset);
@@ -253,6 +257,15 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev)
return 0;
}
+static void mlxbf3_gpio_shutdown(struct platform_device *pdev)
+{
+ struct mlxbf3_gpio_context *gs = platform_get_drvdata(pdev);
+
+ /* Disable and clear all interrupts */
+ writel(0, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0);
+ writel(MLXBF_GPIO_CLR_ALL_INTS, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_CLRCAUSE);
+}
+
static const struct acpi_device_id mlxbf3_gpio_acpi_match[] = {
{ "MLNXBF33", 0 },
{}
@@ -265,6 +278,7 @@ static struct platform_driver mlxbf3_gpio_driver = {
.acpi_match_table = mlxbf3_gpio_acpi_match,
},
.probe = mlxbf3_gpio_probe,
+ .shutdown = mlxbf3_gpio_shutdown,
};
module_platform_driver(mlxbf3_gpio_driver);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 9aa952f..6dfdff5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1057,6 +1057,9 @@ static int amdgpu_cs_patch_ibs(struct amdgpu_cs_parser *p,
r = amdgpu_ring_parse_cs(ring, p, job, ib);
if (r)
return r;
+
+ if (ib->sa_bo)
+ ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo);
} else {
ib->ptr = (uint32_t *)kptr;
r = amdgpu_ring_patch_cs_in_place(ring, p, job, ib);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 5cb33ac..c43d1b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -685,16 +685,24 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
switch (args->in.op) {
case AMDGPU_CTX_OP_ALLOC_CTX:
+ if (args->in.flags)
+ return -EINVAL;
r = amdgpu_ctx_alloc(adev, fpriv, filp, priority, &id);
args->out.alloc.ctx_id = id;
break;
case AMDGPU_CTX_OP_FREE_CTX:
+ if (args->in.flags)
+ return -EINVAL;
r = amdgpu_ctx_free(fpriv, id);
break;
case AMDGPU_CTX_OP_QUERY_STATE:
+ if (args->in.flags)
+ return -EINVAL;
r = amdgpu_ctx_query(adev, fpriv, id, &args->out);
break;
case AMDGPU_CTX_OP_QUERY_STATE2:
+ if (args->in.flags)
+ return -EINVAL;
r = amdgpu_ctx_query2(adev, fpriv, id, &args->out);
break;
case AMDGPU_CTX_OP_GET_STABLE_PSTATE:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index ac108fc..4bd61c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -278,7 +278,7 @@ static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev,
msg = RREG32(mmMP0_SMN_C2PMSG_33);
if (msg & 0x80000000)
break;
- usleep_range(1000, 1100);
+ msleep(1);
}
}
@@ -1500,6 +1500,7 @@ union gc_info {
struct gc_info_v1_0 v1;
struct gc_info_v1_1 v1_1;
struct gc_info_v1_2 v1_2;
+ struct gc_info_v1_3 v1_3;
struct gc_info_v2_0 v2;
struct gc_info_v2_1 v2_1;
};
@@ -1558,6 +1559,16 @@ static int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
adev->gfx.config.gc_gl1c_size_per_instance = le32_to_cpu(gc_info->v1_2.gc_gl1c_size_per_instance);
adev->gfx.config.gc_gl2c_per_gpu = le32_to_cpu(gc_info->v1_2.gc_gl2c_per_gpu);
}
+ if (le16_to_cpu(gc_info->v1.header.version_minor) >= 3) {
+ adev->gfx.config.gc_tcp_size_per_cu = le32_to_cpu(gc_info->v1_3.gc_tcp_size_per_cu);
+ adev->gfx.config.gc_tcp_cache_line_size = le32_to_cpu(gc_info->v1_3.gc_tcp_cache_line_size);
+ adev->gfx.config.gc_instruction_cache_size_per_sqc = le32_to_cpu(gc_info->v1_3.gc_instruction_cache_size_per_sqc);
+ adev->gfx.config.gc_instruction_cache_line_size = le32_to_cpu(gc_info->v1_3.gc_instruction_cache_line_size);
+ adev->gfx.config.gc_scalar_data_cache_size_per_sqc = le32_to_cpu(gc_info->v1_3.gc_scalar_data_cache_size_per_sqc);
+ adev->gfx.config.gc_scalar_data_cache_line_size = le32_to_cpu(gc_info->v1_3.gc_scalar_data_cache_line_size);
+ adev->gfx.config.gc_tcc_size = le32_to_cpu(gc_info->v1_3.gc_tcc_size);
+ adev->gfx.config.gc_tcc_cache_line_size = le32_to_cpu(gc_info->v1_3.gc_tcc_cache_line_size);
+ }
break;
case 2:
adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->v2.gc_num_se);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 8245260..c770cb2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -509,6 +509,16 @@ int amdgpu_gfx_disable_kcq(struct amdgpu_device *adev, int xcc_id)
int i, r = 0;
int j;
+ if (adev->enable_mes) {
+ for (i = 0; i < adev->gfx.num_compute_rings; i++) {
+ j = i + xcc_id * adev->gfx.num_compute_rings;
+ amdgpu_mes_unmap_legacy_queue(adev,
+ &adev->gfx.compute_ring[j],
+ RESET_QUEUES, 0, 0);
+ }
+ return 0;
+ }
+
if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
return -EINVAL;
@@ -551,6 +561,18 @@ int amdgpu_gfx_disable_kgq(struct amdgpu_device *adev, int xcc_id)
int i, r = 0;
int j;
+ if (adev->enable_mes) {
+ if (amdgpu_gfx_is_master_xcc(adev, xcc_id)) {
+ for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
+ j = i + xcc_id * adev->gfx.num_gfx_rings;
+ amdgpu_mes_unmap_legacy_queue(adev,
+ &adev->gfx.gfx_ring[j],
+ PREEMPT_QUEUES, 0, 0);
+ }
+ }
+ return 0;
+ }
+
if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
return -EINVAL;
@@ -995,7 +1017,7 @@ uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg, uint32_t xcc_
if (amdgpu_device_skip_hw_access(adev))
return 0;
- if (adev->mes.ring.sched.ready)
+ if (adev->mes.ring[0].sched.ready)
return amdgpu_mes_rreg(adev, reg);
BUG_ON(!ring->funcs->emit_rreg);
@@ -1065,7 +1087,7 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v, uint3
if (amdgpu_device_skip_hw_access(adev))
return;
- if (adev->mes.ring.sched.ready) {
+ if (adev->mes.ring[0].sched.ready) {
amdgpu_mes_wreg(adev, reg, v);
return;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index ddda94e..56cc58e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -240,6 +240,12 @@ struct amdgpu_gfx_config {
uint32_t gc_tcp_size_per_cu;
uint32_t gc_num_cu_per_sqc;
uint32_t gc_tcc_size;
+ uint32_t gc_tcp_cache_line_size;
+ uint32_t gc_instruction_cache_size_per_sqc;
+ uint32_t gc_instruction_cache_line_size;
+ uint32_t gc_scalar_data_cache_size_per_sqc;
+ uint32_t gc_scalar_data_cache_line_size;
+ uint32_t gc_tcc_cache_line_size;
};
struct amdgpu_cu_info {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index c026590..b49b365 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -589,7 +589,8 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev)
ring = adev->rings[i];
vmhub = ring->vm_hub;
- if (ring == &adev->mes.ring ||
+ if (ring == &adev->mes.ring[0] ||
+ ring == &adev->mes.ring[1] ||
ring == &adev->umsch_mm.ring)
continue;
@@ -761,7 +762,7 @@ void amdgpu_gmc_fw_reg_write_reg_wait(struct amdgpu_device *adev,
unsigned long flags;
uint32_t seq;
- if (adev->mes.ring.sched.ready) {
+ if (adev->mes.ring[0].sched.ready) {
amdgpu_mes_reg_write_reg_wait(adev, reg0, reg1,
ref, mask);
return;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index dac88d2..1cb1ec7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -135,9 +135,11 @@ int amdgpu_mes_init(struct amdgpu_device *adev)
idr_init(&adev->mes.queue_id_idr);
ida_init(&adev->mes.doorbell_ida);
spin_lock_init(&adev->mes.queue_id_lock);
- spin_lock_init(&adev->mes.ring_lock);
mutex_init(&adev->mes.mutex_hidden);
+ for (i = 0; i < AMDGPU_MAX_MES_PIPES; i++)
+ spin_lock_init(&adev->mes.ring_lock[i]);
+
adev->mes.total_max_queue = AMDGPU_FENCE_MES_QUEUE_ID_MASK;
adev->mes.vmid_mask_mmhub = 0xffffff00;
adev->mes.vmid_mask_gfxhub = 0xffffff00;
@@ -163,36 +165,38 @@ int amdgpu_mes_init(struct amdgpu_device *adev)
adev->mes.sdma_hqd_mask[i] = 0xfc;
}
- r = amdgpu_device_wb_get(adev, &adev->mes.sch_ctx_offs);
- if (r) {
- dev_err(adev->dev,
- "(%d) ring trail_fence_offs wb alloc failed\n", r);
- goto error_ids;
- }
- adev->mes.sch_ctx_gpu_addr =
- adev->wb.gpu_addr + (adev->mes.sch_ctx_offs * 4);
- adev->mes.sch_ctx_ptr =
- (uint64_t *)&adev->wb.wb[adev->mes.sch_ctx_offs];
+ for (i = 0; i < AMDGPU_MAX_MES_PIPES; i++) {
+ r = amdgpu_device_wb_get(adev, &adev->mes.sch_ctx_offs[i]);
+ if (r) {
+ dev_err(adev->dev,
+ "(%d) ring trail_fence_offs wb alloc failed\n",
+ r);
+ goto error;
+ }
+ adev->mes.sch_ctx_gpu_addr[i] =
+ adev->wb.gpu_addr + (adev->mes.sch_ctx_offs[i] * 4);
+ adev->mes.sch_ctx_ptr[i] =
+ (uint64_t *)&adev->wb.wb[adev->mes.sch_ctx_offs[i]];
- r = amdgpu_device_wb_get(adev, &adev->mes.query_status_fence_offs);
- if (r) {
- amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs);
- dev_err(adev->dev,
- "(%d) query_status_fence_offs wb alloc failed\n", r);
- goto error_ids;
+ r = amdgpu_device_wb_get(adev,
+ &adev->mes.query_status_fence_offs[i]);
+ if (r) {
+ dev_err(adev->dev,
+ "(%d) query_status_fence_offs wb alloc failed\n",
+ r);
+ goto error;
+ }
+ adev->mes.query_status_fence_gpu_addr[i] = adev->wb.gpu_addr +
+ (adev->mes.query_status_fence_offs[i] * 4);
+ adev->mes.query_status_fence_ptr[i] =
+ (uint64_t *)&adev->wb.wb[adev->mes.query_status_fence_offs[i]];
}
- adev->mes.query_status_fence_gpu_addr =
- adev->wb.gpu_addr + (adev->mes.query_status_fence_offs * 4);
- adev->mes.query_status_fence_ptr =
- (uint64_t *)&adev->wb.wb[adev->mes.query_status_fence_offs];
r = amdgpu_device_wb_get(adev, &adev->mes.read_val_offs);
if (r) {
- amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs);
- amdgpu_device_wb_free(adev, adev->mes.query_status_fence_offs);
dev_err(adev->dev,
"(%d) read_val_offs alloc failed\n", r);
- goto error_ids;
+ goto error;
}
adev->mes.read_val_gpu_addr =
adev->wb.gpu_addr + (adev->mes.read_val_offs * 4);
@@ -212,10 +216,16 @@ int amdgpu_mes_init(struct amdgpu_device *adev)
error_doorbell:
amdgpu_mes_doorbell_free(adev);
error:
- amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs);
- amdgpu_device_wb_free(adev, adev->mes.query_status_fence_offs);
- amdgpu_device_wb_free(adev, adev->mes.read_val_offs);
-error_ids:
+ for (i = 0; i < AMDGPU_MAX_MES_PIPES; i++) {
+ if (adev->mes.sch_ctx_ptr[i])
+ amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs[i]);
+ if (adev->mes.query_status_fence_ptr[i])
+ amdgpu_device_wb_free(adev,
+ adev->mes.query_status_fence_offs[i]);
+ }
+ if (adev->mes.read_val_ptr)
+ amdgpu_device_wb_free(adev, adev->mes.read_val_offs);
+
idr_destroy(&adev->mes.pasid_idr);
idr_destroy(&adev->mes.gang_id_idr);
idr_destroy(&adev->mes.queue_id_idr);
@@ -226,13 +236,22 @@ int amdgpu_mes_init(struct amdgpu_device *adev)
void amdgpu_mes_fini(struct amdgpu_device *adev)
{
+ int i;
+
amdgpu_bo_free_kernel(&adev->mes.event_log_gpu_obj,
&adev->mes.event_log_gpu_addr,
&adev->mes.event_log_cpu_addr);
- amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs);
- amdgpu_device_wb_free(adev, adev->mes.query_status_fence_offs);
- amdgpu_device_wb_free(adev, adev->mes.read_val_offs);
+ for (i = 0; i < AMDGPU_MAX_MES_PIPES; i++) {
+ if (adev->mes.sch_ctx_ptr[i])
+ amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs[i]);
+ if (adev->mes.query_status_fence_ptr[i])
+ amdgpu_device_wb_free(adev,
+ adev->mes.query_status_fence_offs[i]);
+ }
+ if (adev->mes.read_val_ptr)
+ amdgpu_device_wb_free(adev, adev->mes.read_val_offs);
+
amdgpu_mes_doorbell_free(adev);
idr_destroy(&adev->mes.pasid_idr);
@@ -1499,7 +1518,7 @@ int amdgpu_mes_init_microcode(struct amdgpu_device *adev, int pipe)
amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix,
sizeof(ucode_prefix));
- if (adev->enable_uni_mes && pipe == AMDGPU_MES_SCHED_PIPE) {
+ if (adev->enable_uni_mes) {
snprintf(fw_name, sizeof(fw_name),
"amdgpu/%s_uni_mes.bin", ucode_prefix);
} else if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(11, 0, 0) &&
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
index 2d659c6..0bc837d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
@@ -82,8 +82,8 @@ struct amdgpu_mes {
uint64_t default_process_quantum;
uint64_t default_gang_quantum;
- struct amdgpu_ring ring;
- spinlock_t ring_lock;
+ struct amdgpu_ring ring[AMDGPU_MAX_MES_PIPES];
+ spinlock_t ring_lock[AMDGPU_MAX_MES_PIPES];
const struct firmware *fw[AMDGPU_MAX_MES_PIPES];
@@ -112,12 +112,12 @@ struct amdgpu_mes {
uint32_t gfx_hqd_mask[AMDGPU_MES_MAX_GFX_PIPES];
uint32_t sdma_hqd_mask[AMDGPU_MES_MAX_SDMA_PIPES];
uint32_t aggregated_doorbells[AMDGPU_MES_PRIORITY_NUM_LEVELS];
- uint32_t sch_ctx_offs;
- uint64_t sch_ctx_gpu_addr;
- uint64_t *sch_ctx_ptr;
- uint32_t query_status_fence_offs;
- uint64_t query_status_fence_gpu_addr;
- uint64_t *query_status_fence_ptr;
+ uint32_t sch_ctx_offs[AMDGPU_MAX_MES_PIPES];
+ uint64_t sch_ctx_gpu_addr[AMDGPU_MAX_MES_PIPES];
+ uint64_t *sch_ctx_ptr[AMDGPU_MAX_MES_PIPES];
+ uint32_t query_status_fence_offs[AMDGPU_MAX_MES_PIPES];
+ uint64_t query_status_fence_gpu_addr[AMDGPU_MAX_MES_PIPES];
+ uint64_t *query_status_fence_ptr[AMDGPU_MAX_MES_PIPES];
uint32_t read_val_offs;
uint64_t read_val_gpu_addr;
uint32_t *read_val_ptr;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
index 0c85600..38face9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
@@ -166,6 +166,9 @@ static ssize_t ta_if_load_debugfs_write(struct file *fp, const char *buf, size_t
if (ret)
return -EFAULT;
+ if (ta_bin_len > PSP_1_MEG)
+ return -EINVAL;
+
copy_pos += sizeof(uint32_t);
ta_bin = kzalloc(ta_bin_len, GFP_KERNEL);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index ad49cec..e6344a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -212,6 +212,8 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
*/
if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
sched_hw_submission = max(sched_hw_submission, 256);
+ if (ring->funcs->type == AMDGPU_RING_TYPE_MES)
+ sched_hw_submission = 8;
else if (ring == &adev->sdma.instance[0].page)
sched_hw_submission = 256;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 1a5439a..c87d68d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -461,8 +461,11 @@ struct amdgpu_vcn5_fw_shared {
struct amdgpu_fw_shared_unified_queue_struct sq;
uint8_t pad1[8];
struct amdgpu_fw_shared_fw_logging fw_log;
+ uint8_t pad2[20];
struct amdgpu_fw_shared_rb_setup rb_setup;
- uint8_t pad2[4];
+ struct amdgpu_fw_shared_smu_interface_info smu_dpm_interface;
+ struct amdgpu_fw_shared_drm_key_wa drm_key_wa;
+ uint8_t pad3[9];
};
#define VCN_BLOCK_ENCODE_DISABLE_MASK 0x80
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 111c380..b287a82 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -858,7 +858,7 @@ void amdgpu_virt_post_reset(struct amdgpu_device *adev)
adev->gfx.is_poweron = false;
}
- adev->mes.ring.sched.ready = false;
+ adev->mes.ring[0].sched.ready = false;
}
bool amdgpu_virt_fw_load_skip_check(struct amdgpu_device *adev, uint32_t ucode_id)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 2957702..e444e62 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -4116,6 +4116,7 @@ static void gfx_v10_0_check_gfxoff_flag(struct amdgpu_device *adev)
static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
{
+ char fw_name[53];
char ucode_prefix[30];
const char *wks = "";
int err;
@@ -4149,8 +4150,8 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_CE);
if (!amdgpu_sriov_vf(adev)) {
- err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw,
- "amdgpu/%s_rlc.bin", ucode_prefix);
+ snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", ucode_prefix);
+ err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
if (err)
goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index 506fa80..e45d23e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -3005,7 +3005,7 @@ static int gfx_v12_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
(order_base_2(prop->queue_size / 4) - 1));
tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, RPTR_BLOCK_SIZE,
(order_base_2(AMDGPU_GPU_PAGE_SIZE / 4) - 1));
- tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 0);
+ tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1);
tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH, 0);
tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1);
@@ -3546,33 +3546,9 @@ static int gfx_v12_0_hw_init(void *handle)
return r;
}
-static int gfx_v12_0_kiq_disable_kgq(struct amdgpu_device *adev)
-{
- struct amdgpu_kiq *kiq = &adev->gfx.kiq[0];
- struct amdgpu_ring *kiq_ring = &kiq->ring;
- int i, r = 0;
-
- if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
- return -EINVAL;
-
- if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size *
- adev->gfx.num_gfx_rings))
- return -ENOMEM;
-
- for (i = 0; i < adev->gfx.num_gfx_rings; i++)
- kiq->pmf->kiq_unmap_queues(kiq_ring, &adev->gfx.gfx_ring[i],
- PREEMPT_QUEUES, 0, 0);
-
- if (adev->gfx.kiq[0].ring.sched.ready)
- r = amdgpu_ring_test_helper(kiq_ring);
-
- return r;
-}
-
static int gfx_v12_0_hw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- int r;
uint32_t tmp;
amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0);
@@ -3580,8 +3556,7 @@ static int gfx_v12_0_hw_fini(void *handle)
if (!adev->no_hw_access) {
if (amdgpu_async_gfx_ring) {
- r = gfx_v12_0_kiq_disable_kgq(adev);
- if (r)
+ if (amdgpu_gfx_disable_kgq(adev, 0))
DRM_ERROR("KGQ disable failed\n");
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index b88a6fa..2797fd8 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -231,7 +231,7 @@ static void gmc_v11_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
/* This is necessary for SRIOV as well as for GFXOFF to function
* properly under bare metal
*/
- if ((adev->gfx.kiq[0].ring.sched.ready || adev->mes.ring.sched.ready) &&
+ if ((adev->gfx.kiq[0].ring.sched.ready || adev->mes.ring[0].sched.ready) &&
(amdgpu_sriov_runtime(adev) || !amdgpu_sriov_vf(adev))) {
amdgpu_gmc_fw_reg_write_reg_wait(adev, req, ack, inv_req,
1 << vmid, GET_INST(GC, 0));
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
index 26efce9..edcb5351 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
@@ -299,7 +299,7 @@ static void gmc_v12_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
/* This is necessary for SRIOV as well as for GFXOFF to function
* properly under bare metal
*/
- if ((adev->gfx.kiq[0].ring.sched.ready || adev->mes.ring.sched.ready) &&
+ if ((adev->gfx.kiq[0].ring.sched.ready || adev->mes.ring[0].sched.ready) &&
(amdgpu_sriov_runtime(adev) || !amdgpu_sriov_vf(adev))) {
struct amdgpu_vmhub *hub = &adev->vmhub[vmhub];
const unsigned eng = 17;
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
index 99adf36..98aa3cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
@@ -538,11 +538,11 @@ void jpeg_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring,
amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET,
0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+ amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8)));
amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JPEG_VMID_INTERNAL_OFFSET,
0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+ amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8)));
amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET,
0, 0, PACKETJ_TYPE0));
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
index ad524dd..6ae5a78 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
@@ -23,6 +23,7 @@
#include "amdgpu.h"
#include "amdgpu_jpeg.h"
+#include "amdgpu_cs.h"
#include "soc15.h"
#include "soc15d.h"
#include "jpeg_v4_0_3.h"
@@ -782,11 +783,15 @@ void jpeg_v4_0_3_dec_ring_emit_ib(struct amdgpu_ring *ring,
amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET,
0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+
+ if (ring->funcs->parse_cs)
+ amdgpu_ring_write(ring, 0);
+ else
+ amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8)));
amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JPEG_VMID_INTERNAL_OFFSET,
0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+ amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8)));
amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET,
0, 0, PACKETJ_TYPE0));
@@ -1084,6 +1089,7 @@ static const struct amdgpu_ring_funcs jpeg_v4_0_3_dec_ring_vm_funcs = {
.get_rptr = jpeg_v4_0_3_dec_ring_get_rptr,
.get_wptr = jpeg_v4_0_3_dec_ring_get_wptr,
.set_wptr = jpeg_v4_0_3_dec_ring_set_wptr,
+ .parse_cs = jpeg_v4_0_3_dec_ring_parse_cs,
.emit_frame_size =
SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
@@ -1248,3 +1254,56 @@ static void jpeg_v4_0_3_set_ras_funcs(struct amdgpu_device *adev)
{
adev->jpeg.ras = &jpeg_v4_0_3_ras;
}
+
+/**
+ * jpeg_v4_0_3_dec_ring_parse_cs - command submission parser
+ *
+ * @parser: Command submission parser context
+ * @job: the job to parse
+ * @ib: the IB to parse
+ *
+ * Parse the command stream, return -EINVAL for invalid packet,
+ * 0 otherwise
+ */
+int jpeg_v4_0_3_dec_ring_parse_cs(struct amdgpu_cs_parser *parser,
+ struct amdgpu_job *job,
+ struct amdgpu_ib *ib)
+{
+ uint32_t i, reg, res, cond, type;
+ struct amdgpu_device *adev = parser->adev;
+
+ for (i = 0; i < ib->length_dw ; i += 2) {
+ reg = CP_PACKETJ_GET_REG(ib->ptr[i]);
+ res = CP_PACKETJ_GET_RES(ib->ptr[i]);
+ cond = CP_PACKETJ_GET_COND(ib->ptr[i]);
+ type = CP_PACKETJ_GET_TYPE(ib->ptr[i]);
+
+ if (res) /* only support 0 at the moment */
+ return -EINVAL;
+
+ switch (type) {
+ case PACKETJ_TYPE0:
+ if (cond != PACKETJ_CONDITION_CHECK0 || reg < JPEG_REG_RANGE_START || reg > JPEG_REG_RANGE_END) {
+ dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]);
+ return -EINVAL;
+ }
+ break;
+ case PACKETJ_TYPE3:
+ if (cond != PACKETJ_CONDITION_CHECK3 || reg < JPEG_REG_RANGE_START || reg > JPEG_REG_RANGE_END) {
+ dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]);
+ return -EINVAL;
+ }
+ break;
+ case PACKETJ_TYPE6:
+ if (ib->ptr[i] == CP_PACKETJ_NOP)
+ continue;
+ dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]);
+ return -EINVAL;
+ default:
+ dev_err(adev->dev, "Unknown packet type %d !\n", type);
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h
index 747a3e5..71c54b2 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h
@@ -46,6 +46,9 @@
#define JRBC_DEC_EXTERNAL_REG_WRITE_ADDR 0x18000
+#define JPEG_REG_RANGE_START 0x4000
+#define JPEG_REG_RANGE_END 0x41c2
+
extern const struct amdgpu_ip_block_version jpeg_v4_0_3_ip_block;
void jpeg_v4_0_3_dec_ring_emit_ib(struct amdgpu_ring *ring,
@@ -62,5 +65,7 @@ void jpeg_v4_0_3_dec_ring_insert_end(struct amdgpu_ring *ring);
void jpeg_v4_0_3_dec_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
void jpeg_v4_0_3_dec_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
uint32_t val, uint32_t mask);
-
+int jpeg_v4_0_3_dec_ring_parse_cs(struct amdgpu_cs_parser *parser,
+ struct amdgpu_job *job,
+ struct amdgpu_ib *ib);
#endif /* __JPEG_V4_0_3_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
index d694a27..f4daff9 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
@@ -646,6 +646,7 @@ static const struct amdgpu_ring_funcs jpeg_v5_0_0_dec_ring_vm_funcs = {
.get_rptr = jpeg_v5_0_0_dec_ring_get_rptr,
.get_wptr = jpeg_v5_0_0_dec_ring_get_wptr,
.set_wptr = jpeg_v5_0_0_dec_ring_set_wptr,
+ .parse_cs = jpeg_v4_0_3_dec_ring_parse_cs,
.emit_frame_size =
SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index f934364..2ea8223 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -162,13 +162,13 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
union MESAPI__QUERY_MES_STATUS mes_status_pkt;
signed long timeout = 3000000; /* 3000 ms */
struct amdgpu_device *adev = mes->adev;
- struct amdgpu_ring *ring = &mes->ring;
+ struct amdgpu_ring *ring = &mes->ring[0];
struct MES_API_STATUS *api_status;
union MESAPI__MISC *x_pkt = pkt;
const char *op_str, *misc_op_str;
unsigned long flags;
u64 status_gpu_addr;
- u32 status_offset;
+ u32 seq, status_offset;
u64 *status_ptr;
signed long r;
int ret;
@@ -191,11 +191,18 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
status_ptr = (u64 *)&adev->wb.wb[status_offset];
*status_ptr = 0;
- spin_lock_irqsave(&mes->ring_lock, flags);
+ spin_lock_irqsave(&mes->ring_lock[0], flags);
r = amdgpu_ring_alloc(ring, (size + sizeof(mes_status_pkt)) / 4);
if (r)
goto error_unlock_free;
+ seq = ++ring->fence_drv.sync_seq;
+ r = amdgpu_fence_wait_polling(ring,
+ seq - ring->fence_drv.num_fences_mask,
+ timeout);
+ if (r < 1)
+ goto error_undo;
+
api_status = (struct MES_API_STATUS *)((char *)pkt + api_status_off);
api_status->api_completion_fence_addr = status_gpu_addr;
api_status->api_completion_fence_value = 1;
@@ -208,14 +215,13 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
mes_status_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
mes_status_pkt.api_status.api_completion_fence_addr =
ring->fence_drv.gpu_addr;
- mes_status_pkt.api_status.api_completion_fence_value =
- ++ring->fence_drv.sync_seq;
+ mes_status_pkt.api_status.api_completion_fence_value = seq;
amdgpu_ring_write_multiple(ring, &mes_status_pkt,
sizeof(mes_status_pkt) / 4);
amdgpu_ring_commit(ring);
- spin_unlock_irqrestore(&mes->ring_lock, flags);
+ spin_unlock_irqrestore(&mes->ring_lock[0], flags);
op_str = mes_v11_0_get_op_string(x_pkt);
misc_op_str = mes_v11_0_get_misc_op_string(x_pkt);
@@ -229,7 +235,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
dev_dbg(adev->dev, "MES msg=%d was emitted\n",
x_pkt->header.opcode);
- r = amdgpu_fence_wait_polling(ring, ring->fence_drv.sync_seq, timeout);
+ r = amdgpu_fence_wait_polling(ring, seq, timeout);
if (r < 1 || !*status_ptr) {
if (misc_op_str)
@@ -252,8 +258,12 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
amdgpu_device_wb_free(adev, status_offset);
return 0;
+error_undo:
+ dev_err(adev->dev, "MES ring buffer is full.\n");
+ amdgpu_ring_undo(ring);
+
error_unlock_free:
- spin_unlock_irqrestore(&mes->ring_lock, flags);
+ spin_unlock_irqrestore(&mes->ring_lock[0], flags);
error_wb_free:
amdgpu_device_wb_free(adev, status_offset);
@@ -512,9 +522,9 @@ static int mes_v11_0_set_hw_resources(struct amdgpu_mes *mes)
mes_set_hw_res_pkt.vmid_mask_gfxhub = mes->vmid_mask_gfxhub;
mes_set_hw_res_pkt.gds_size = adev->gds.gds_size;
mes_set_hw_res_pkt.paging_vmid = 0;
- mes_set_hw_res_pkt.g_sch_ctx_gpu_mc_ptr = mes->sch_ctx_gpu_addr;
+ mes_set_hw_res_pkt.g_sch_ctx_gpu_mc_ptr = mes->sch_ctx_gpu_addr[0];
mes_set_hw_res_pkt.query_status_fence_gpu_mc_ptr =
- mes->query_status_fence_gpu_addr;
+ mes->query_status_fence_gpu_addr[0];
for (i = 0; i < MAX_COMPUTE_PIPES; i++)
mes_set_hw_res_pkt.compute_hqd_mask[i] =
@@ -1015,7 +1025,7 @@ static int mes_v11_0_kiq_enable_queue(struct amdgpu_device *adev)
return r;
}
- kiq->pmf->kiq_map_queues(kiq_ring, &adev->mes.ring);
+ kiq->pmf->kiq_map_queues(kiq_ring, &adev->mes.ring[0]);
return amdgpu_ring_test_helper(kiq_ring);
}
@@ -1029,7 +1039,7 @@ static int mes_v11_0_queue_init(struct amdgpu_device *adev,
if (pipe == AMDGPU_MES_KIQ_PIPE)
ring = &adev->gfx.kiq[0].ring;
else if (pipe == AMDGPU_MES_SCHED_PIPE)
- ring = &adev->mes.ring;
+ ring = &adev->mes.ring[0];
else
BUG();
@@ -1071,7 +1081,7 @@ static int mes_v11_0_ring_init(struct amdgpu_device *adev)
{
struct amdgpu_ring *ring;
- ring = &adev->mes.ring;
+ ring = &adev->mes.ring[0];
ring->funcs = &mes_v11_0_ring_funcs;
@@ -1124,7 +1134,7 @@ static int mes_v11_0_mqd_sw_init(struct amdgpu_device *adev,
if (pipe == AMDGPU_MES_KIQ_PIPE)
ring = &adev->gfx.kiq[0].ring;
else if (pipe == AMDGPU_MES_SCHED_PIPE)
- ring = &adev->mes.ring;
+ ring = &adev->mes.ring[0];
else
BUG();
@@ -1200,9 +1210,6 @@ static int mes_v11_0_sw_fini(void *handle)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
int pipe;
- amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs);
- amdgpu_device_wb_free(adev, adev->mes.query_status_fence_offs);
-
for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) {
kfree(adev->mes.mqd_backup[pipe]);
@@ -1216,12 +1223,12 @@ static int mes_v11_0_sw_fini(void *handle)
&adev->gfx.kiq[0].ring.mqd_gpu_addr,
&adev->gfx.kiq[0].ring.mqd_ptr);
- amdgpu_bo_free_kernel(&adev->mes.ring.mqd_obj,
- &adev->mes.ring.mqd_gpu_addr,
- &adev->mes.ring.mqd_ptr);
+ amdgpu_bo_free_kernel(&adev->mes.ring[0].mqd_obj,
+ &adev->mes.ring[0].mqd_gpu_addr,
+ &adev->mes.ring[0].mqd_ptr);
amdgpu_ring_fini(&adev->gfx.kiq[0].ring);
- amdgpu_ring_fini(&adev->mes.ring);
+ amdgpu_ring_fini(&adev->mes.ring[0]);
if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
mes_v11_0_free_ucode_buffers(adev, AMDGPU_MES_KIQ_PIPE);
@@ -1332,9 +1339,9 @@ static int mes_v11_0_kiq_hw_init(struct amdgpu_device *adev)
static int mes_v11_0_kiq_hw_fini(struct amdgpu_device *adev)
{
- if (adev->mes.ring.sched.ready) {
- mes_v11_0_kiq_dequeue(&adev->mes.ring);
- adev->mes.ring.sched.ready = false;
+ if (adev->mes.ring[0].sched.ready) {
+ mes_v11_0_kiq_dequeue(&adev->mes.ring[0]);
+ adev->mes.ring[0].sched.ready = false;
}
if (amdgpu_sriov_vf(adev)) {
@@ -1352,7 +1359,7 @@ static int mes_v11_0_hw_init(void *handle)
int r;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (adev->mes.ring.sched.ready)
+ if (adev->mes.ring[0].sched.ready)
goto out;
if (!adev->enable_mes_kiq) {
@@ -1397,7 +1404,7 @@ static int mes_v11_0_hw_init(void *handle)
* with MES enabled.
*/
adev->gfx.kiq[0].ring.sched.ready = false;
- adev->mes.ring.sched.ready = true;
+ adev->mes.ring[0].sched.ready = true;
return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 0713bc3..e39a58d 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -142,19 +142,20 @@ static const char *mes_v12_0_get_misc_op_string(union MESAPI__MISC *x_pkt)
}
static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
- void *pkt, int size,
- int api_status_off)
+ int pipe, void *pkt, int size,
+ int api_status_off)
{
union MESAPI__QUERY_MES_STATUS mes_status_pkt;
signed long timeout = 3000000; /* 3000 ms */
struct amdgpu_device *adev = mes->adev;
- struct amdgpu_ring *ring = &mes->ring;
+ struct amdgpu_ring *ring = &mes->ring[pipe];
+ spinlock_t *ring_lock = &mes->ring_lock[pipe];
struct MES_API_STATUS *api_status;
union MESAPI__MISC *x_pkt = pkt;
const char *op_str, *misc_op_str;
unsigned long flags;
u64 status_gpu_addr;
- u32 status_offset;
+ u32 seq, status_offset;
u64 *status_ptr;
signed long r;
int ret;
@@ -177,11 +178,18 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
status_ptr = (u64 *)&adev->wb.wb[status_offset];
*status_ptr = 0;
- spin_lock_irqsave(&mes->ring_lock, flags);
+ spin_lock_irqsave(ring_lock, flags);
r = amdgpu_ring_alloc(ring, (size + sizeof(mes_status_pkt)) / 4);
if (r)
goto error_unlock_free;
+ seq = ++ring->fence_drv.sync_seq;
+ r = amdgpu_fence_wait_polling(ring,
+ seq - ring->fence_drv.num_fences_mask,
+ timeout);
+ if (r < 1)
+ goto error_undo;
+
api_status = (struct MES_API_STATUS *)((char *)pkt + api_status_off);
api_status->api_completion_fence_addr = status_gpu_addr;
api_status->api_completion_fence_value = 1;
@@ -194,39 +202,39 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
mes_status_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
mes_status_pkt.api_status.api_completion_fence_addr =
ring->fence_drv.gpu_addr;
- mes_status_pkt.api_status.api_completion_fence_value =
- ++ring->fence_drv.sync_seq;
+ mes_status_pkt.api_status.api_completion_fence_value = seq;
amdgpu_ring_write_multiple(ring, &mes_status_pkt,
sizeof(mes_status_pkt) / 4);
amdgpu_ring_commit(ring);
- spin_unlock_irqrestore(&mes->ring_lock, flags);
+ spin_unlock_irqrestore(ring_lock, flags);
op_str = mes_v12_0_get_op_string(x_pkt);
misc_op_str = mes_v12_0_get_misc_op_string(x_pkt);
if (misc_op_str)
- dev_dbg(adev->dev, "MES msg=%s (%s) was emitted\n", op_str,
- misc_op_str);
+ dev_dbg(adev->dev, "MES(%d) msg=%s (%s) was emitted\n",
+ pipe, op_str, misc_op_str);
else if (op_str)
- dev_dbg(adev->dev, "MES msg=%s was emitted\n", op_str);
+ dev_dbg(adev->dev, "MES(%d) msg=%s was emitted\n",
+ pipe, op_str);
else
- dev_dbg(adev->dev, "MES msg=%d was emitted\n",
- x_pkt->header.opcode);
+ dev_dbg(adev->dev, "MES(%d) msg=%d was emitted\n",
+ pipe, x_pkt->header.opcode);
- r = amdgpu_fence_wait_polling(ring, ring->fence_drv.sync_seq, timeout);
+ r = amdgpu_fence_wait_polling(ring, seq, timeout);
if (r < 1 || !*status_ptr) {
if (misc_op_str)
- dev_err(adev->dev, "MES failed to respond to msg=%s (%s)\n",
- op_str, misc_op_str);
+ dev_err(adev->dev, "MES(%d) failed to respond to msg=%s (%s)\n",
+ pipe, op_str, misc_op_str);
else if (op_str)
- dev_err(adev->dev, "MES failed to respond to msg=%s\n",
- op_str);
+ dev_err(adev->dev, "MES(%d) failed to respond to msg=%s\n",
+ pipe, op_str);
else
- dev_err(adev->dev, "MES failed to respond to msg=%d\n",
- x_pkt->header.opcode);
+ dev_err(adev->dev, "MES(%d) failed to respond to msg=%d\n",
+ pipe, x_pkt->header.opcode);
while (halt_if_hws_hang)
schedule();
@@ -238,8 +246,12 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
amdgpu_device_wb_free(adev, status_offset);
return 0;
+error_undo:
+ dev_err(adev->dev, "MES ring buffer is full.\n");
+ amdgpu_ring_undo(ring);
+
error_unlock_free:
- spin_unlock_irqrestore(&mes->ring_lock, flags);
+ spin_unlock_irqrestore(ring_lock, flags);
error_wb_free:
amdgpu_device_wb_free(adev, status_offset);
@@ -254,6 +266,8 @@ static int convert_to_mes_queue_type(int queue_type)
return MES_QUEUE_TYPE_COMPUTE;
else if (queue_type == AMDGPU_RING_TYPE_SDMA)
return MES_QUEUE_TYPE_SDMA;
+ else if (queue_type == AMDGPU_RING_TYPE_MES)
+ return MES_QUEUE_TYPE_SCHQ;
else
BUG();
return -1;
@@ -311,6 +325,7 @@ static int mes_v12_0_add_hw_queue(struct amdgpu_mes *mes,
mes_add_queue_pkt.gds_size = input->queue_size;
return mes_v12_0_submit_pkt_and_poll_completion(mes,
+ AMDGPU_MES_SCHED_PIPE,
&mes_add_queue_pkt, sizeof(mes_add_queue_pkt),
offsetof(union MESAPI__ADD_QUEUE, api_status));
}
@@ -330,6 +345,7 @@ static int mes_v12_0_remove_hw_queue(struct amdgpu_mes *mes,
mes_remove_queue_pkt.gang_context_addr = input->gang_context_addr;
return mes_v12_0_submit_pkt_and_poll_completion(mes,
+ AMDGPU_MES_SCHED_PIPE,
&mes_remove_queue_pkt, sizeof(mes_remove_queue_pkt),
offsetof(union MESAPI__REMOVE_QUEUE, api_status));
}
@@ -338,6 +354,7 @@ static int mes_v12_0_map_legacy_queue(struct amdgpu_mes *mes,
struct mes_map_legacy_queue_input *input)
{
union MESAPI__ADD_QUEUE mes_add_queue_pkt;
+ int pipe;
memset(&mes_add_queue_pkt, 0, sizeof(mes_add_queue_pkt));
@@ -354,7 +371,12 @@ static int mes_v12_0_map_legacy_queue(struct amdgpu_mes *mes,
convert_to_mes_queue_type(input->queue_type);
mes_add_queue_pkt.map_legacy_kq = 1;
- return mes_v12_0_submit_pkt_and_poll_completion(mes,
+ if (mes->adev->enable_uni_mes)
+ pipe = AMDGPU_MES_KIQ_PIPE;
+ else
+ pipe = AMDGPU_MES_SCHED_PIPE;
+
+ return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe,
&mes_add_queue_pkt, sizeof(mes_add_queue_pkt),
offsetof(union MESAPI__ADD_QUEUE, api_status));
}
@@ -363,6 +385,7 @@ static int mes_v12_0_unmap_legacy_queue(struct amdgpu_mes *mes,
struct mes_unmap_legacy_queue_input *input)
{
union MESAPI__REMOVE_QUEUE mes_remove_queue_pkt;
+ int pipe;
memset(&mes_remove_queue_pkt, 0, sizeof(mes_remove_queue_pkt));
@@ -387,7 +410,12 @@ static int mes_v12_0_unmap_legacy_queue(struct amdgpu_mes *mes,
convert_to_mes_queue_type(input->queue_type);
}
- return mes_v12_0_submit_pkt_and_poll_completion(mes,
+ if (mes->adev->enable_uni_mes)
+ pipe = AMDGPU_MES_KIQ_PIPE;
+ else
+ pipe = AMDGPU_MES_SCHED_PIPE;
+
+ return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe,
&mes_remove_queue_pkt, sizeof(mes_remove_queue_pkt),
offsetof(union MESAPI__REMOVE_QUEUE, api_status));
}
@@ -404,7 +432,7 @@ static int mes_v12_0_resume_gang(struct amdgpu_mes *mes,
return 0;
}
-static int mes_v12_0_query_sched_status(struct amdgpu_mes *mes)
+static int mes_v12_0_query_sched_status(struct amdgpu_mes *mes, int pipe)
{
union MESAPI__QUERY_MES_STATUS mes_status_pkt;
@@ -414,7 +442,7 @@ static int mes_v12_0_query_sched_status(struct amdgpu_mes *mes)
mes_status_pkt.header.opcode = MES_SCH_API_QUERY_SCHEDULER_STATUS;
mes_status_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
- return mes_v12_0_submit_pkt_and_poll_completion(mes,
+ return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe,
&mes_status_pkt, sizeof(mes_status_pkt),
offsetof(union MESAPI__QUERY_MES_STATUS, api_status));
}
@@ -423,6 +451,7 @@ static int mes_v12_0_misc_op(struct amdgpu_mes *mes,
struct mes_misc_op_input *input)
{
union MESAPI__MISC misc_pkt;
+ int pipe;
memset(&misc_pkt, 0, sizeof(misc_pkt));
@@ -475,12 +504,17 @@ static int mes_v12_0_misc_op(struct amdgpu_mes *mes,
return -EINVAL;
}
- return mes_v12_0_submit_pkt_and_poll_completion(mes,
+ if (mes->adev->enable_uni_mes)
+ pipe = AMDGPU_MES_KIQ_PIPE;
+ else
+ pipe = AMDGPU_MES_SCHED_PIPE;
+
+ return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe,
&misc_pkt, sizeof(misc_pkt),
offsetof(union MESAPI__MISC, api_status));
}
-static int mes_v12_0_set_hw_resources_1(struct amdgpu_mes *mes)
+static int mes_v12_0_set_hw_resources_1(struct amdgpu_mes *mes, int pipe)
{
union MESAPI_SET_HW_RESOURCES_1 mes_set_hw_res_1_pkt;
@@ -491,12 +525,12 @@ static int mes_v12_0_set_hw_resources_1(struct amdgpu_mes *mes)
mes_set_hw_res_1_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
mes_set_hw_res_1_pkt.mes_kiq_unmap_timeout = 100;
- return mes_v12_0_submit_pkt_and_poll_completion(mes,
+ return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe,
&mes_set_hw_res_1_pkt, sizeof(mes_set_hw_res_1_pkt),
offsetof(union MESAPI_SET_HW_RESOURCES_1, api_status));
}
-static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes)
+static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe)
{
int i;
struct amdgpu_device *adev = mes->adev;
@@ -508,27 +542,33 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes)
mes_set_hw_res_pkt.header.opcode = MES_SCH_API_SET_HW_RSRC;
mes_set_hw_res_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
- mes_set_hw_res_pkt.vmid_mask_mmhub = mes->vmid_mask_mmhub;
- mes_set_hw_res_pkt.vmid_mask_gfxhub = mes->vmid_mask_gfxhub;
- mes_set_hw_res_pkt.gds_size = adev->gds.gds_size;
- mes_set_hw_res_pkt.paging_vmid = 0;
- mes_set_hw_res_pkt.g_sch_ctx_gpu_mc_ptr = mes->sch_ctx_gpu_addr;
+ if (pipe == AMDGPU_MES_SCHED_PIPE) {
+ mes_set_hw_res_pkt.vmid_mask_mmhub = mes->vmid_mask_mmhub;
+ mes_set_hw_res_pkt.vmid_mask_gfxhub = mes->vmid_mask_gfxhub;
+ mes_set_hw_res_pkt.gds_size = adev->gds.gds_size;
+ mes_set_hw_res_pkt.paging_vmid = 0;
+
+ for (i = 0; i < MAX_COMPUTE_PIPES; i++)
+ mes_set_hw_res_pkt.compute_hqd_mask[i] =
+ mes->compute_hqd_mask[i];
+
+ for (i = 0; i < MAX_GFX_PIPES; i++)
+ mes_set_hw_res_pkt.gfx_hqd_mask[i] =
+ mes->gfx_hqd_mask[i];
+
+ for (i = 0; i < MAX_SDMA_PIPES; i++)
+ mes_set_hw_res_pkt.sdma_hqd_mask[i] =
+ mes->sdma_hqd_mask[i];
+
+ for (i = 0; i < AMD_PRIORITY_NUM_LEVELS; i++)
+ mes_set_hw_res_pkt.aggregated_doorbells[i] =
+ mes->aggregated_doorbells[i];
+ }
+
+ mes_set_hw_res_pkt.g_sch_ctx_gpu_mc_ptr =
+ mes->sch_ctx_gpu_addr[pipe];
mes_set_hw_res_pkt.query_status_fence_gpu_mc_ptr =
- mes->query_status_fence_gpu_addr;
-
- for (i = 0; i < MAX_COMPUTE_PIPES; i++)
- mes_set_hw_res_pkt.compute_hqd_mask[i] =
- mes->compute_hqd_mask[i];
-
- for (i = 0; i < MAX_GFX_PIPES; i++)
- mes_set_hw_res_pkt.gfx_hqd_mask[i] = mes->gfx_hqd_mask[i];
-
- for (i = 0; i < MAX_SDMA_PIPES; i++)
- mes_set_hw_res_pkt.sdma_hqd_mask[i] = mes->sdma_hqd_mask[i];
-
- for (i = 0; i < AMD_PRIORITY_NUM_LEVELS; i++)
- mes_set_hw_res_pkt.aggregated_doorbells[i] =
- mes->aggregated_doorbells[i];
+ mes->query_status_fence_gpu_addr[pipe];
for (i = 0; i < 5; i++) {
mes_set_hw_res_pkt.gc_base[i] = adev->reg_offset[GC_HWIP][0][i];
@@ -556,7 +596,7 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes)
mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr = mes->event_log_gpu_addr;
}
- return mes_v12_0_submit_pkt_and_poll_completion(mes,
+ return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe,
&mes_set_hw_res_pkt, sizeof(mes_set_hw_res_pkt),
offsetof(union MESAPI_SET_HW_RESOURCES, api_status));
}
@@ -734,16 +774,11 @@ static void mes_v12_0_enable(struct amdgpu_device *adev, bool enable)
if (enable) {
data = RREG32_SOC15(GC, 0, regCP_MES_CNTL);
data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE0_RESET, 1);
- data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_RESET,
- (!adev->enable_uni_mes && adev->enable_mes_kiq) ? 1 : 0);
+ data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_RESET, 1);
WREG32_SOC15(GC, 0, regCP_MES_CNTL, data);
mutex_lock(&adev->srbm_mutex);
for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) {
- if ((!adev->enable_mes_kiq || adev->enable_uni_mes) &&
- pipe == AMDGPU_MES_KIQ_PIPE)
- continue;
-
soc21_grbm_select(adev, 3, pipe, 0, 0);
ucode_addr = adev->mes.uc_start_addr[pipe] >> 2;
@@ -757,8 +792,7 @@ static void mes_v12_0_enable(struct amdgpu_device *adev, bool enable)
/* unhalt MES and activate pipe0 */
data = REG_SET_FIELD(0, CP_MES_CNTL, MES_PIPE0_ACTIVE, 1);
- data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_ACTIVE,
- (!adev->enable_uni_mes && adev->enable_mes_kiq) ? 1 : 0);
+ data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_ACTIVE, 1);
WREG32_SOC15(GC, 0, regCP_MES_CNTL, data);
if (amdgpu_emu_mode)
@@ -774,8 +808,7 @@ static void mes_v12_0_enable(struct amdgpu_device *adev, bool enable)
data = REG_SET_FIELD(data, CP_MES_CNTL,
MES_INVALIDATE_ICACHE, 1);
data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE0_RESET, 1);
- data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_RESET,
- (!adev->enable_uni_mes && adev->enable_mes_kiq) ? 1 : 0);
+ data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_RESET, 1);
data = REG_SET_FIELD(data, CP_MES_CNTL, MES_HALT, 1);
WREG32_SOC15(GC, 0, regCP_MES_CNTL, data);
}
@@ -790,10 +823,6 @@ static void mes_v12_0_set_ucode_start_addr(struct amdgpu_device *adev)
mutex_lock(&adev->srbm_mutex);
for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) {
- if ((!adev->enable_mes_kiq || adev->enable_uni_mes) &&
- pipe == AMDGPU_MES_KIQ_PIPE)
- continue;
-
/* me=3, queue=0 */
soc21_grbm_select(adev, 3, pipe, 0, 0);
@@ -1085,7 +1114,7 @@ static int mes_v12_0_kiq_enable_queue(struct amdgpu_device *adev)
return r;
}
- kiq->pmf->kiq_map_queues(kiq_ring, &adev->mes.ring);
+ kiq->pmf->kiq_map_queues(kiq_ring, &adev->mes.ring[0]);
r = amdgpu_ring_test_ring(kiq_ring);
if (r) {
@@ -1101,14 +1130,12 @@ static int mes_v12_0_queue_init(struct amdgpu_device *adev,
struct amdgpu_ring *ring;
int r;
- if (pipe == AMDGPU_MES_KIQ_PIPE)
+ if (!adev->enable_uni_mes && pipe == AMDGPU_MES_KIQ_PIPE)
ring = &adev->gfx.kiq[0].ring;
- else if (pipe == AMDGPU_MES_SCHED_PIPE)
- ring = &adev->mes.ring;
else
- BUG();
+ ring = &adev->mes.ring[pipe];
- if ((pipe == AMDGPU_MES_SCHED_PIPE) &&
+ if ((adev->enable_uni_mes || pipe == AMDGPU_MES_SCHED_PIPE) &&
(amdgpu_in_reset(adev) || adev->in_suspend)) {
*(ring->wptr_cpu_addr) = 0;
*(ring->rptr_cpu_addr) = 0;
@@ -1120,13 +1147,12 @@ static int mes_v12_0_queue_init(struct amdgpu_device *adev,
return r;
if (pipe == AMDGPU_MES_SCHED_PIPE) {
- if (adev->enable_uni_mes) {
- mes_v12_0_queue_init_register(ring);
- } else {
+ if (adev->enable_uni_mes)
+ r = amdgpu_mes_map_legacy_queue(adev, ring);
+ else
r = mes_v12_0_kiq_enable_queue(adev);
- if (r)
- return r;
- }
+ if (r)
+ return r;
} else {
mes_v12_0_queue_init_register(ring);
}
@@ -1146,25 +1172,29 @@ static int mes_v12_0_queue_init(struct amdgpu_device *adev,
return 0;
}
-static int mes_v12_0_ring_init(struct amdgpu_device *adev)
+static int mes_v12_0_ring_init(struct amdgpu_device *adev, int pipe)
{
struct amdgpu_ring *ring;
- ring = &adev->mes.ring;
+ ring = &adev->mes.ring[pipe];
ring->funcs = &mes_v12_0_ring_funcs;
ring->me = 3;
- ring->pipe = 0;
+ ring->pipe = pipe;
ring->queue = 0;
ring->ring_obj = NULL;
ring->use_doorbell = true;
- ring->doorbell_index = adev->doorbell_index.mes_ring0 << 1;
- ring->eop_gpu_addr = adev->mes.eop_gpu_addr[AMDGPU_MES_SCHED_PIPE];
+ ring->eop_gpu_addr = adev->mes.eop_gpu_addr[pipe];
ring->no_scheduler = true;
sprintf(ring->name, "mes_%d.%d.%d", ring->me, ring->pipe, ring->queue);
+ if (pipe == AMDGPU_MES_SCHED_PIPE)
+ ring->doorbell_index = adev->doorbell_index.mes_ring0 << 1;
+ else
+ ring->doorbell_index = adev->doorbell_index.mes_ring1 << 1;
+
return amdgpu_ring_init(adev, ring, 1024, NULL, 0,
AMDGPU_RING_PRIO_DEFAULT, NULL);
}
@@ -1178,7 +1208,7 @@ static int mes_v12_0_kiq_ring_init(struct amdgpu_device *adev)
ring = &adev->gfx.kiq[0].ring;
ring->me = 3;
- ring->pipe = adev->enable_uni_mes ? 0 : 1;
+ ring->pipe = 1;
ring->queue = 0;
ring->adev = NULL;
@@ -1200,12 +1230,10 @@ static int mes_v12_0_mqd_sw_init(struct amdgpu_device *adev,
int r, mqd_size = sizeof(struct v12_compute_mqd);
struct amdgpu_ring *ring;
- if (pipe == AMDGPU_MES_KIQ_PIPE)
+ if (!adev->enable_uni_mes && pipe == AMDGPU_MES_KIQ_PIPE)
ring = &adev->gfx.kiq[0].ring;
- else if (pipe == AMDGPU_MES_SCHED_PIPE)
- ring = &adev->mes.ring;
else
- BUG();
+ ring = &adev->mes.ring[pipe];
if (ring->mqd_obj)
return 0;
@@ -1246,9 +1274,6 @@ static int mes_v12_0_sw_init(void *handle)
return r;
for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) {
- if (!adev->enable_mes_kiq && pipe == AMDGPU_MES_KIQ_PIPE)
- continue;
-
r = mes_v12_0_allocate_eop_buf(adev, pipe);
if (r)
return r;
@@ -1256,18 +1281,15 @@ static int mes_v12_0_sw_init(void *handle)
r = mes_v12_0_mqd_sw_init(adev, pipe);
if (r)
return r;
- }
- if (adev->enable_mes_kiq) {
- r = mes_v12_0_kiq_ring_init(adev);
+ if (!adev->enable_uni_mes && pipe == AMDGPU_MES_KIQ_PIPE)
+ r = mes_v12_0_kiq_ring_init(adev);
+ else
+ r = mes_v12_0_ring_init(adev, pipe);
if (r)
return r;
}
- r = mes_v12_0_ring_init(adev);
- if (r)
- return r;
-
return 0;
}
@@ -1276,9 +1298,6 @@ static int mes_v12_0_sw_fini(void *handle)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
int pipe;
- amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs);
- amdgpu_device_wb_free(adev, adev->mes.query_status_fence_offs);
-
for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) {
kfree(adev->mes.mqd_backup[pipe]);
@@ -1286,18 +1305,21 @@ static int mes_v12_0_sw_fini(void *handle)
&adev->mes.eop_gpu_addr[pipe],
NULL);
amdgpu_ucode_release(&adev->mes.fw[pipe]);
+
+ if (adev->enable_uni_mes || pipe == AMDGPU_MES_SCHED_PIPE) {
+ amdgpu_bo_free_kernel(&adev->mes.ring[pipe].mqd_obj,
+ &adev->mes.ring[pipe].mqd_gpu_addr,
+ &adev->mes.ring[pipe].mqd_ptr);
+ amdgpu_ring_fini(&adev->mes.ring[pipe]);
+ }
}
- amdgpu_bo_free_kernel(&adev->gfx.kiq[0].ring.mqd_obj,
- &adev->gfx.kiq[0].ring.mqd_gpu_addr,
- &adev->gfx.kiq[0].ring.mqd_ptr);
-
- amdgpu_bo_free_kernel(&adev->mes.ring.mqd_obj,
- &adev->mes.ring.mqd_gpu_addr,
- &adev->mes.ring.mqd_ptr);
-
- amdgpu_ring_fini(&adev->gfx.kiq[0].ring);
- amdgpu_ring_fini(&adev->mes.ring);
+ if (!adev->enable_uni_mes) {
+ amdgpu_bo_free_kernel(&adev->gfx.kiq[0].ring.mqd_obj,
+ &adev->gfx.kiq[0].ring.mqd_gpu_addr,
+ &adev->gfx.kiq[0].ring.mqd_ptr);
+ amdgpu_ring_fini(&adev->gfx.kiq[0].ring);
+ }
if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
mes_v12_0_free_ucode_buffers(adev, AMDGPU_MES_KIQ_PIPE);
@@ -1341,7 +1363,7 @@ static void mes_v12_0_kiq_dequeue_sched(struct amdgpu_device *adev)
soc21_grbm_select(adev, 0, 0, 0, 0);
mutex_unlock(&adev->srbm_mutex);
- adev->mes.ring.sched.ready = false;
+ adev->mes.ring[0].sched.ready = false;
}
static void mes_v12_0_kiq_setting(struct amdgpu_ring *ring)
@@ -1362,10 +1384,10 @@ static int mes_v12_0_kiq_hw_init(struct amdgpu_device *adev)
{
int r = 0;
- mes_v12_0_kiq_setting(&adev->gfx.kiq[0].ring);
-
if (adev->enable_uni_mes)
- return mes_v12_0_hw_init(adev);
+ mes_v12_0_kiq_setting(&adev->mes.ring[AMDGPU_MES_KIQ_PIPE]);
+ else
+ mes_v12_0_kiq_setting(&adev->gfx.kiq[0].ring);
if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
@@ -1392,6 +1414,14 @@ static int mes_v12_0_kiq_hw_init(struct amdgpu_device *adev)
if (r)
goto failure;
+ if (adev->enable_uni_mes) {
+ r = mes_v12_0_set_hw_resources(&adev->mes, AMDGPU_MES_KIQ_PIPE);
+ if (r)
+ goto failure;
+
+ mes_v12_0_set_hw_resources_1(&adev->mes, AMDGPU_MES_KIQ_PIPE);
+ }
+
r = mes_v12_0_hw_init(adev);
if (r)
goto failure;
@@ -1405,9 +1435,15 @@ static int mes_v12_0_kiq_hw_init(struct amdgpu_device *adev)
static int mes_v12_0_kiq_hw_fini(struct amdgpu_device *adev)
{
- if (adev->mes.ring.sched.ready) {
- mes_v12_0_kiq_dequeue_sched(adev);
- adev->mes.ring.sched.ready = false;
+ if (adev->mes.ring[0].sched.ready) {
+ if (adev->enable_uni_mes)
+ amdgpu_mes_unmap_legacy_queue(adev,
+ &adev->mes.ring[AMDGPU_MES_SCHED_PIPE],
+ RESET_QUEUES, 0, 0);
+ else
+ mes_v12_0_kiq_dequeue_sched(adev);
+
+ adev->mes.ring[0].sched.ready = false;
}
mes_v12_0_enable(adev, false);
@@ -1420,10 +1456,10 @@ static int mes_v12_0_hw_init(void *handle)
int r;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (adev->mes.ring.sched.ready)
+ if (adev->mes.ring[0].sched.ready)
goto out;
- if (!adev->enable_mes_kiq || adev->enable_uni_mes) {
+ if (!adev->enable_mes_kiq) {
if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
r = mes_v12_0_load_microcode(adev,
AMDGPU_MES_SCHED_PIPE, true);
@@ -1443,23 +1479,23 @@ static int mes_v12_0_hw_init(void *handle)
mes_v12_0_enable(adev, true);
}
+ /* Enable the MES to handle doorbell ring on unmapped queue */
+ mes_v12_0_enable_unmapped_doorbell_handling(&adev->mes, true);
+
r = mes_v12_0_queue_init(adev, AMDGPU_MES_SCHED_PIPE);
if (r)
goto failure;
- r = mes_v12_0_set_hw_resources(&adev->mes);
+ r = mes_v12_0_set_hw_resources(&adev->mes, AMDGPU_MES_SCHED_PIPE);
if (r)
goto failure;
if (adev->enable_uni_mes)
- mes_v12_0_set_hw_resources_1(&adev->mes);
+ mes_v12_0_set_hw_resources_1(&adev->mes, AMDGPU_MES_SCHED_PIPE);
mes_v12_0_init_aggregated_doorbell(&adev->mes);
- /* Enable the MES to handle doorbell ring on unmapped queue */
- mes_v12_0_enable_unmapped_doorbell_handling(&adev->mes, true);
-
- r = mes_v12_0_query_sched_status(&adev->mes);
+ r = mes_v12_0_query_sched_status(&adev->mes, AMDGPU_MES_SCHED_PIPE);
if (r) {
DRM_ERROR("MES is busy\n");
goto failure;
@@ -1472,7 +1508,7 @@ static int mes_v12_0_hw_init(void *handle)
* with MES enabled.
*/
adev->gfx.kiq[0].ring.sched.ready = false;
- adev->mes.ring.sched.ready = true;
+ adev->mes.ring[0].sched.ready = true;
return 0;
@@ -1515,17 +1551,7 @@ static int mes_v12_0_early_init(void *handle)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
int pipe, r;
- if (adev->enable_uni_mes) {
- r = amdgpu_mes_init_microcode(adev, AMDGPU_MES_SCHED_PIPE);
- if (!r)
- return 0;
-
- adev->enable_uni_mes = false;
- }
-
for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) {
- if (!adev->enable_mes_kiq && pipe == AMDGPU_MES_KIQ_PIPE)
- continue;
r = amdgpu_mes_init_microcode(adev, pipe);
if (r)
return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index af1e901..2e72d44 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -176,14 +176,16 @@ static void sdma_v5_2_ring_set_wptr(struct amdgpu_ring *ring)
DRM_DEBUG("calling WDOORBELL64(0x%08x, 0x%016llx)\n",
ring->doorbell_index, ring->wptr << 2);
WDOORBELL64(ring->doorbell_index, ring->wptr << 2);
- /* SDMA seems to miss doorbells sometimes when powergating kicks in.
- * Updating the wptr directly will wake it. This is only safe because
- * we disallow gfxoff in begin_use() and then allow it again in end_use().
- */
- WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR),
- lower_32_bits(ring->wptr << 2));
- WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI),
- upper_32_bits(ring->wptr << 2));
+ if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) == IP_VERSION(5, 2, 1)) {
+ /* SDMA seems to miss doorbells sometimes when powergating kicks in.
+ * Updating the wptr directly will wake it. This is only safe because
+ * we disallow gfxoff in begin_use() and then allow it again in end_use().
+ */
+ WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR),
+ lower_32_bits(ring->wptr << 2));
+ WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI),
+ upper_32_bits(ring->wptr << 2));
+ }
} else {
DRM_DEBUG("Not using doorbell -- "
"mmSDMA%i_GFX_RB_WPTR == 0x%08x "
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15d.h b/drivers/gpu/drm/amd/amdgpu/soc15d.h
index 2357ff3..e74e198 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15d.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15d.h
@@ -76,6 +76,12 @@
((cond & 0xF) << 24) | \
((type & 0xF) << 28))
+#define CP_PACKETJ_NOP 0x60000000
+#define CP_PACKETJ_GET_REG(x) ((x) & 0x3FFFF)
+#define CP_PACKETJ_GET_RES(x) (((x) >> 18) & 0x3F)
+#define CP_PACKETJ_GET_COND(x) (((x) >> 24) & 0xF)
+#define CP_PACKETJ_GET_TYPE(x) (((x) >> 28) & 0xF)
+
/* Packet 3 types */
#define PACKET3_NOP 0x10
#define PACKET3_SET_BASE 0x11
diff --git a/drivers/gpu/drm/amd/amdgpu/soc24.c b/drivers/gpu/drm/amd/amdgpu/soc24.c
index 7d641d0..b0c3678 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc24.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc24.c
@@ -406,6 +406,7 @@ static int soc24_common_early_init(void *handle)
AMD_CG_SUPPORT_ATHUB_MGCG |
AMD_CG_SUPPORT_ATHUB_LS |
AMD_CG_SUPPORT_MC_MGCG |
+ AMD_CG_SUPPORT_HDP_SD |
AMD_CG_SUPPORT_MC_LS;
adev->pg_flags = AMD_PG_SUPPORT_VCN |
AMD_PG_SUPPORT_JPEG |
@@ -424,6 +425,7 @@ static int soc24_common_early_init(void *handle)
AMD_CG_SUPPORT_ATHUB_MGCG |
AMD_CG_SUPPORT_ATHUB_LS |
AMD_CG_SUPPORT_MC_MGCG |
+ AMD_CG_SUPPORT_HDP_SD |
AMD_CG_SUPPORT_MC_LS;
adev->pg_flags = AMD_PG_SUPPORT_VCN |
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
index b7a08e7..d163d92 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
@@ -187,6 +187,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
m->cp_hqd_pq_control |=
ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
+ m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
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 7e7929f..983a977 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2893,6 +2893,9 @@ static int dm_suspend(void *handle)
hpd_rx_irq_work_suspend(dm);
+ if (adev->dm.dc->caps.ips_support)
+ dc_allow_idle_optimizations(adev->dm.dc, true);
+
dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D3);
dc_dmub_srv_set_power_state(dm->dc->ctx->dmub_srv, DC_ACPI_CM_POWER_STATE_D3);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 915eb2c..2e9f6da 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -804,12 +804,25 @@ struct dsc_mst_fairness_params {
};
#if defined(CONFIG_DRM_AMD_DC_FP)
-static int kbps_to_peak_pbn(int kbps)
+static uint16_t get_fec_overhead_multiplier(struct dc_link *dc_link)
+{
+ u8 link_coding_cap;
+ uint16_t fec_overhead_multiplier_x1000 = PBN_FEC_OVERHEAD_MULTIPLIER_8B_10B;
+
+ link_coding_cap = dc_link_dp_mst_decide_link_encoding_format(dc_link);
+ if (link_coding_cap == DP_128b_132b_ENCODING)
+ fec_overhead_multiplier_x1000 = PBN_FEC_OVERHEAD_MULTIPLIER_128B_132B;
+
+ return fec_overhead_multiplier_x1000;
+}
+
+static int kbps_to_peak_pbn(int kbps, uint16_t fec_overhead_multiplier_x1000)
{
u64 peak_kbps = kbps;
peak_kbps *= 1006;
- peak_kbps = div_u64(peak_kbps, 1000);
+ peak_kbps *= fec_overhead_multiplier_x1000;
+ peak_kbps = div_u64(peak_kbps, 1000 * 1000);
return (int) DIV64_U64_ROUND_UP(peak_kbps * 64, (54 * 8 * 1000));
}
@@ -910,11 +923,12 @@ static int increase_dsc_bpp(struct drm_atomic_state *state,
int link_timeslots_used;
int fair_pbn_alloc;
int ret = 0;
+ uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link);
for (i = 0; i < count; i++) {
if (vars[i + k].dsc_enabled) {
initial_slack[i] =
- kbps_to_peak_pbn(params[i].bw_range.max_kbps) - vars[i + k].pbn;
+ kbps_to_peak_pbn(params[i].bw_range.max_kbps, fec_overhead_multiplier_x1000) - vars[i + k].pbn;
bpp_increased[i] = false;
remaining_to_increase += 1;
} else {
@@ -1010,6 +1024,7 @@ static int try_disable_dsc(struct drm_atomic_state *state,
int next_index;
int remaining_to_try = 0;
int ret;
+ uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link);
for (i = 0; i < count; i++) {
if (vars[i + k].dsc_enabled
@@ -1039,7 +1054,7 @@ static int try_disable_dsc(struct drm_atomic_state *state,
if (next_index == -1)
break;
- vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps);
+ vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps, fec_overhead_multiplier_x1000);
ret = drm_dp_atomic_find_time_slots(state,
params[next_index].port->mgr,
params[next_index].port,
@@ -1052,8 +1067,7 @@ static int try_disable_dsc(struct drm_atomic_state *state,
vars[next_index].dsc_enabled = false;
vars[next_index].bpp_x16 = 0;
} else {
- vars[next_index].pbn = kbps_to_peak_pbn(
- params[next_index].bw_range.max_kbps);
+ vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps, fec_overhead_multiplier_x1000);
ret = drm_dp_atomic_find_time_slots(state,
params[next_index].port->mgr,
params[next_index].port,
@@ -1082,6 +1096,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
int count = 0;
int i, k, ret;
bool debugfs_overwrite = false;
+ uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link);
memset(params, 0, sizeof(params));
@@ -1146,7 +1161,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
/* Try no compression */
for (i = 0; i < count; i++) {
vars[i + k].aconnector = params[i].aconnector;
- vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
+ vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps, fec_overhead_multiplier_x1000);
vars[i + k].dsc_enabled = false;
vars[i + k].bpp_x16 = 0;
ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, params[i].port,
@@ -1165,7 +1180,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
/* Try max compression */
for (i = 0; i < count; i++) {
if (params[i].compression_possible && params[i].clock_force_enable != DSC_CLK_FORCE_DISABLE) {
- vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps);
+ vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps, fec_overhead_multiplier_x1000);
vars[i + k].dsc_enabled = true;
vars[i + k].bpp_x16 = params[i].bw_range.min_target_bpp_x16;
ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr,
@@ -1173,7 +1188,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
if (ret < 0)
return ret;
} else {
- vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
+ vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps, fec_overhead_multiplier_x1000);
vars[i + k].dsc_enabled = false;
vars[i + k].bpp_x16 = 0;
ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
index fa84d34..600d6e2 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
@@ -46,6 +46,9 @@
#define SYNAPTICS_CASCADED_HUB_ID 0x5A
#define IS_SYNAPTICS_CASCADED_PANAMERA(devName, data) ((IS_SYNAPTICS_PANAMERA(devName) && ((int)data[2] == SYNAPTICS_CASCADED_HUB_ID)) ? 1 : 0)
+#define PBN_FEC_OVERHEAD_MULTIPLIER_8B_10B 1031
+#define PBN_FEC_OVERHEAD_MULTIPLIER_128B_132B 1000
+
enum mst_msg_ready_type {
NONE_MSG_RDY_EVENT = 0,
DOWN_REP_MSG_RDY_EVENT = 1,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index a83bd03..5cb11cc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -28,6 +28,7 @@
#include <drm/drm_blend.h>
#include <drm/drm_gem_atomic_helper.h>
#include <drm/drm_plane_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
#include <drm/drm_fourcc.h>
#include "amdgpu.h"
@@ -935,10 +936,14 @@ static int amdgpu_dm_plane_helper_prepare_fb(struct drm_plane *plane,
}
afb = to_amdgpu_framebuffer(new_state->fb);
- obj = new_state->fb->obj[0];
+ obj = drm_gem_fb_get_obj(new_state->fb, 0);
+ if (!obj) {
+ DRM_ERROR("Failed to get obj from framebuffer\n");
+ return -EINVAL;
+ }
+
rbo = gem_to_amdgpu_bo(obj);
adev = amdgpu_ttm_adev(rbo->tbo.bdev);
-
r = amdgpu_bo_reserve(rbo, true);
if (r) {
dev_err(adev->dev, "fail to reserve bo (%d)\n", r);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
index ff03b1d..14a902f 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
@@ -3589,7 +3589,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
(int)hubp->curs_attr.width || pos_cpy.x
<= (int)hubp->curs_attr.width +
pipe_ctx->plane_state->src_rect.x) {
- pos_cpy.x = temp_x + viewport_width;
+ pos_cpy.x = 2 * viewport_width - temp_x;
}
}
} else {
@@ -3682,7 +3682,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
(int)hubp->curs_attr.width || pos_cpy.x
<= (int)hubp->curs_attr.width +
pipe_ctx->plane_state->src_rect.x) {
- pos_cpy.x = 2 * viewport_width - temp_x;
+ pos_cpy.x = temp_x + viewport_width;
}
}
} else {
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
index 9a3cc05..8e0588b 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
@@ -1778,6 +1778,9 @@ static bool dcn321_resource_construct(
dc->caps.color.mpc.ogam_rom_caps.hlg = 0;
dc->caps.color.mpc.ocsc = 1;
+ /* Use pipe context based otg sync logic */
+ dc->config.use_pipe_ctx_sync_logic = true;
+
dc->config.dc_mode_clk_limit_support = true;
dc->config.enable_windowed_mpo_odm = true;
/* read VBIOS LTTPR caps */
diff --git a/drivers/gpu/drm/amd/include/discovery.h b/drivers/gpu/drm/amd/include/discovery.h
index 46bf19c..710e328 100644
--- a/drivers/gpu/drm/amd/include/discovery.h
+++ b/drivers/gpu/drm/amd/include/discovery.h
@@ -258,6 +258,48 @@ struct gc_info_v1_2 {
uint32_t gc_gl2c_per_gpu;
};
+struct gc_info_v1_3 {
+ struct gpu_info_header header;
+ uint32_t gc_num_se;
+ uint32_t gc_num_wgp0_per_sa;
+ uint32_t gc_num_wgp1_per_sa;
+ uint32_t gc_num_rb_per_se;
+ uint32_t gc_num_gl2c;
+ uint32_t gc_num_gprs;
+ uint32_t gc_num_max_gs_thds;
+ uint32_t gc_gs_table_depth;
+ uint32_t gc_gsprim_buff_depth;
+ uint32_t gc_parameter_cache_depth;
+ uint32_t gc_double_offchip_lds_buffer;
+ uint32_t gc_wave_size;
+ uint32_t gc_max_waves_per_simd;
+ uint32_t gc_max_scratch_slots_per_cu;
+ uint32_t gc_lds_size;
+ uint32_t gc_num_sc_per_se;
+ uint32_t gc_num_sa_per_se;
+ uint32_t gc_num_packer_per_sc;
+ uint32_t gc_num_gl2a;
+ uint32_t gc_num_tcp_per_sa;
+ uint32_t gc_num_sdp_interface;
+ uint32_t gc_num_tcps;
+ uint32_t gc_num_tcp_per_wpg;
+ uint32_t gc_tcp_l1_size;
+ uint32_t gc_num_sqc_per_wgp;
+ uint32_t gc_l1_instruction_cache_size_per_sqc;
+ uint32_t gc_l1_data_cache_size_per_sqc;
+ uint32_t gc_gl1c_per_sa;
+ uint32_t gc_gl1c_size_per_instance;
+ uint32_t gc_gl2c_per_gpu;
+ uint32_t gc_tcp_size_per_cu;
+ uint32_t gc_tcp_cache_line_size;
+ uint32_t gc_instruction_cache_size_per_sqc;
+ uint32_t gc_instruction_cache_line_size;
+ uint32_t gc_scalar_data_cache_size_per_sqc;
+ uint32_t gc_scalar_data_cache_line_size;
+ uint32_t gc_tcc_size;
+ uint32_t gc_tcc_cache_line_size;
+};
+
struct gc_info_v2_0 {
struct gpu_info_header header;
diff --git a/drivers/gpu/drm/amd/include/mes_v12_api_def.h b/drivers/gpu/drm/amd/include/mes_v12_api_def.h
index 4cf2c9f..101e2fe 100644
--- a/drivers/gpu/drm/amd/include/mes_v12_api_def.h
+++ b/drivers/gpu/drm/amd/include/mes_v12_api_def.h
@@ -97,6 +97,7 @@ enum MES_QUEUE_TYPE {
MES_QUEUE_TYPE_SDMA,
MES_QUEUE_TYPE_MAX,
+ MES_QUEUE_TYPE_SCHQ = MES_QUEUE_TYPE_MAX,
};
struct MES_API_STATUS {
@@ -242,8 +243,12 @@ union MESAPI_SET_HW_RESOURCES {
uint32_t send_write_data : 1;
uint32_t os_tdr_timeout_override : 1;
uint32_t use_rs64mem_for_proc_gang_ctx : 1;
+ uint32_t halt_on_misaligned_access : 1;
+ uint32_t use_add_queue_unmap_flag_addr : 1;
+ uint32_t enable_mes_sch_stb_log : 1;
+ uint32_t limit_single_process : 1;
uint32_t unmapped_doorbell_handling: 2;
- uint32_t reserved : 15;
+ uint32_t reserved : 11;
};
uint32_t uint32_all;
};
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 9d7454b..74e35f8 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -2224,8 +2224,9 @@ static int smu_bump_power_profile_mode(struct smu_context *smu,
}
static int smu_adjust_power_state_dynamic(struct smu_context *smu,
- enum amd_dpm_forced_level level,
- bool skip_display_settings)
+ enum amd_dpm_forced_level level,
+ bool skip_display_settings,
+ bool force_update)
{
int ret = 0;
int index = 0;
@@ -2254,7 +2255,7 @@ static int smu_adjust_power_state_dynamic(struct smu_context *smu,
}
}
- if (smu_dpm_ctx->dpm_level != level) {
+ if (force_update || smu_dpm_ctx->dpm_level != level) {
ret = smu_asic_set_performance_level(smu, level);
if (ret) {
dev_err(smu->adev->dev, "Failed to set performance level!");
@@ -2265,13 +2266,12 @@ static int smu_adjust_power_state_dynamic(struct smu_context *smu,
smu_dpm_ctx->dpm_level = level;
}
- if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL &&
- smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) {
+ if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) {
index = fls(smu->workload_mask);
index = index > 0 && index <= WORKLOAD_POLICY_MAX ? index - 1 : 0;
workload[0] = smu->workload_setting[index];
- if (smu->power_profile_mode != workload[0])
+ if (force_update || smu->power_profile_mode != workload[0])
smu_bump_power_profile_mode(smu, workload, 0);
}
@@ -2292,11 +2292,13 @@ static int smu_handle_task(struct smu_context *smu,
ret = smu_pre_display_config_changed(smu);
if (ret)
return ret;
- ret = smu_adjust_power_state_dynamic(smu, level, false);
+ ret = smu_adjust_power_state_dynamic(smu, level, false, false);
break;
case AMD_PP_TASK_COMPLETE_INIT:
+ ret = smu_adjust_power_state_dynamic(smu, level, true, true);
+ break;
case AMD_PP_TASK_READJUST_POWER_STATE:
- ret = smu_adjust_power_state_dynamic(smu, level, true);
+ ret = smu_adjust_power_state_dynamic(smu, level, true, false);
break;
default:
break;
@@ -2343,8 +2345,7 @@ static int smu_switch_power_profile(void *handle,
workload[0] = smu->workload_setting[index];
}
- if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL &&
- smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM)
+ if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM)
smu_bump_power_profile_mode(smu, workload, 0);
return 0;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_2_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_2_ppsmc.h
index de2e442..87ca5ce 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_2_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_2_ppsmc.h
@@ -92,7 +92,6 @@
//Resets
#define PPSMC_MSG_PrepareMp1ForUnload 0x2E
-#define PPSMC_MSG_Mode1Reset 0x2F
//Set SystemVirtual DramAddrHigh
#define PPSMC_MSG_SetSystemVirtualDramAddrHigh 0x30
@@ -119,11 +118,12 @@
//STB to dram log
#define PPSMC_MSG_DumpSTBtoDram 0x3D
-#define PPSMC_MSG_STBtoDramLogSetDramAddrHigh 0x3E
-#define PPSMC_MSG_STBtoDramLogSetDramAddrLow 0x3F
+#define PPSMC_MSG_STBtoDramLogSetDramAddress 0x3E
+#define PPSMC_MSG_DummyUndefined 0x3F
#define PPSMC_MSG_STBtoDramLogSetDramSize 0x40
#define PPSMC_MSG_SetOBMTraceBufferLogging 0x41
+#define PPSMC_MSG_UseProfilingMode 0x42
#define PPSMC_MSG_AllowGfxDcs 0x43
#define PPSMC_MSG_DisallowGfxDcs 0x44
#define PPSMC_MSG_EnableAudioStutterWA 0x45
@@ -135,6 +135,16 @@
#define PPSMC_MSG_SetBadMemoryPagesRetiredFlagsPerChannel 0x4B
#define PPSMC_MSG_SetPriorityDeltaGain 0x4C
#define PPSMC_MSG_AllowIHHostInterrupt 0x4D
+#define PPSMC_MSG_EnableShadowDpm 0x4E
#define PPSMC_MSG_Mode3Reset 0x4F
-#define PPSMC_Message_Count 0x50
+#define PPSMC_MSG_SetDriverDramAddr 0x50
+#define PPSMC_MSG_SetToolsDramAddr 0x51
+#define PPSMC_MSG_TransferTableSmu2DramWithAddr 0x52
+#define PPSMC_MSG_TransferTableDram2SmuWithAddr 0x53
+#define PPSMC_MSG_GetAllRunningSmuFeatures 0x54
+#define PPSMC_MSG_GetSvi3Voltage 0x55
+#define PPSMC_MSG_UpdatePolicy 0x56
+#define PPSMC_MSG_ExtPwrConnSupport 0x57
+#define PPSMC_MSG_PreloadSwPstateForUclkOverDrive 0x58
+#define PPSMC_Message_Count 0x59
#endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 78c3f94..9974c9f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -121,6 +121,7 @@ struct mca_ras_info {
#define P2S_TABLE_ID_A 0x50325341
#define P2S_TABLE_ID_X 0x50325358
+#define P2S_TABLE_ID_3 0x50325303
// clang-format off
static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COUNT] = {
@@ -271,14 +272,18 @@ static int smu_v13_0_6_init_microcode(struct smu_context *smu)
struct amdgpu_device *adev = smu->adev;
uint32_t p2s_table_id = P2S_TABLE_ID_A;
int ret = 0, i, p2stable_count;
+ int var = (adev->pdev->device & 0xF);
char ucode_prefix[15];
/* No need to load P2S tables in IOV mode */
if (amdgpu_sriov_vf(adev))
return 0;
- if (!(adev->flags & AMD_IS_APU))
+ if (!(adev->flags & AMD_IS_APU)) {
p2s_table_id = P2S_TABLE_ID_X;
+ if (var == 0x5)
+ p2s_table_id = P2S_TABLE_ID_3;
+ }
amdgpu_ucode_ip_version_decode(adev, MP1_HWIP, ucode_prefix,
sizeof(ucode_prefix));
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index a7d0231..7bc95c4 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -2378,7 +2378,7 @@ static int smu_v13_0_7_get_power_profile_mode(struct smu_context *smu, char *buf
size += sysfs_emit_at(buf, size, " ");
for (i = 0; i <= PP_SMC_POWER_PROFILE_WINDOW3D; i++)
- size += sysfs_emit_at(buf, size, "%-14s%s", amdgpu_pp_profile_name[i],
+ size += sysfs_emit_at(buf, size, "%d %-14s%s", i, amdgpu_pp_profile_name[i],
(i == smu->power_profile_mode) ? "* " : " ");
size += sysfs_emit_at(buf, size, "\n");
@@ -2408,7 +2408,7 @@ static int smu_v13_0_7_get_power_profile_mode(struct smu_context *smu, char *buf
do { \
size += sysfs_emit_at(buf, size, "%-30s", #field); \
for (j = 0; j <= PP_SMC_POWER_PROFILE_WINDOW3D; j++) \
- size += sysfs_emit_at(buf, size, "%-16d", activity_monitor_external[j].DpmActivityMonitorCoeffInt.field); \
+ size += sysfs_emit_at(buf, size, "%-18d", activity_monitor_external[j].DpmActivityMonitorCoeffInt.field); \
size += sysfs_emit_at(buf, size, "\n"); \
} while (0)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index e1a2790..0c09b8c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -115,7 +115,6 @@ static struct cmn2asic_msg_mapping smu_v14_0_2_message_map[SMU_MSG_MAX_COUNT] =
MSG_MAP(SetMGpuFanBoostLimitRpm, PPSMC_MSG_SetMGpuFanBoostLimitRpm, 0),
MSG_MAP(GetPptLimit, PPSMC_MSG_GetPptLimit, 0),
MSG_MAP(NotifyPowerSource, PPSMC_MSG_NotifyPowerSource, 0),
- MSG_MAP(Mode1Reset, PPSMC_MSG_Mode1Reset, 0),
MSG_MAP(PrepareMp1ForUnload, PPSMC_MSG_PrepareMp1ForUnload, 0),
MSG_MAP(DFCstateControl, PPSMC_MSG_SetExternalClientDfCstateAllow, 0),
MSG_MAP(ArmD3, PPSMC_MSG_ArmD3, 0),
@@ -1824,50 +1823,6 @@ static void smu_v14_0_2_set_smu_mailbox_registers(struct smu_context *smu)
smu->debug_resp_reg = SOC15_REG_OFFSET(MP1, 0, regMP1_SMN_C2PMSG_54);
}
-static int smu_v14_0_2_smu_send_bad_mem_page_num(struct smu_context *smu,
- uint32_t size)
-{
- int ret = 0;
-
- /* message SMU to update the bad page number on SMUBUS */
- ret = smu_cmn_send_smc_msg_with_param(smu,
- SMU_MSG_SetNumBadMemoryPagesRetired,
- size, NULL);
- if (ret)
- dev_err(smu->adev->dev,
- "[%s] failed to message SMU to update bad memory pages number\n",
- __func__);
-
- return ret;
-}
-
-static int smu_v14_0_2_send_bad_mem_channel_flag(struct smu_context *smu,
- uint32_t size)
-{
- int ret = 0;
-
- /* message SMU to update the bad channel info on SMUBUS */
- ret = smu_cmn_send_smc_msg_with_param(smu,
- SMU_MSG_SetBadMemoryPagesRetiredFlagsPerChannel,
- size, NULL);
- if (ret)
- dev_err(smu->adev->dev,
- "[%s] failed to message SMU to update bad memory pages channel info\n",
- __func__);
-
- return ret;
-}
-
-static ssize_t smu_v14_0_2_get_ecc_info(struct smu_context *smu,
- void *table)
-{
- int ret = 0;
-
- // TODO
-
- return ret;
-}
-
static ssize_t smu_v14_0_2_get_gpu_metrics(struct smu_context *smu,
void **table)
{
@@ -2015,12 +1970,9 @@ static const struct pptable_funcs smu_v14_0_2_ppt_funcs = {
.enable_gfx_features = smu_v14_0_2_enable_gfx_features,
.set_mp1_state = smu_v14_0_2_set_mp1_state,
.set_df_cstate = smu_v14_0_2_set_df_cstate,
- .send_hbm_bad_pages_num = smu_v14_0_2_smu_send_bad_mem_page_num,
- .send_hbm_bad_channel_flag = smu_v14_0_2_send_bad_mem_channel_flag,
#if 0
.gpo_control = smu_v14_0_gpo_control,
#endif
- .get_ecc_info = smu_v14_0_2_get_ecc_info,
};
void smu_v14_0_2_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index c16c767..0830cae 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -208,6 +208,18 @@ static const struct dmi_system_id orientation_data[] = {
DMI_MATCH(DMI_BOARD_NAME, "KUN"),
},
.driver_data = (void *)&lcd1600x2560_rightside_up,
+ }, { /* AYN Loki Max */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ayn"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Loki Max"),
+ },
+ .driver_data = (void *)&lcd1080x1920_leftside_up,
+ }, { /* AYN Loki Zero */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ayn"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Loki Zero"),
+ },
+ .driver_data = (void *)&lcd1080x1920_leftside_up,
}, { /* Chuwi HiBook (CWI514) */
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "Hampoo"),
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 59f11af..dc75a92 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -5935,6 +5935,18 @@ intel_dp_detect(struct drm_connector *connector,
else
status = connector_status_disconnected;
+ if (status != connector_status_disconnected &&
+ !intel_dp_mst_verify_dpcd_state(intel_dp))
+ /*
+ * This requires retrying detection for instance to re-enable
+ * the MST mode that got reset via a long HPD pulse. The retry
+ * will happen either via the hotplug handler's retry logic,
+ * ensured by setting the connector here to SST/disconnected,
+ * or via a userspace connector probing in response to the
+ * hotplug uevent sent when removing the MST connectors.
+ */
+ status = connector_status_disconnected;
+
if (status == connector_status_disconnected) {
memset(&intel_dp->compliance, 0, sizeof(intel_dp->compliance));
memset(intel_connector->dp.dsc_dpcd, 0, sizeof(intel_connector->dp.dsc_dpcd));
diff --git a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
index 2edffe6..b0101d72 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
@@ -39,7 +39,9 @@ static u32 transcoder_to_stream_enc_status(enum transcoder cpu_transcoder)
static void intel_dp_hdcp_wait_for_cp_irq(struct intel_connector *connector,
int timeout)
{
- struct intel_hdcp *hdcp = &connector->hdcp;
+ struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+ struct intel_dp *dp = &dig_port->dp;
+ struct intel_hdcp *hdcp = &dp->attached_connector->hdcp;
long ret;
#define C (hdcp->cp_irq_count_cached != atomic_read(&hdcp->cp_irq_count))
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 27ce5c3..17978a1f 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -1998,3 +1998,43 @@ bool intel_dp_mst_crtc_needs_modeset(struct intel_atomic_state *state,
return false;
}
+
+/*
+ * intel_dp_mst_verify_dpcd_state - verify the MST SW enabled state wrt. the DPCD
+ * @intel_dp: DP port object
+ *
+ * Verify if @intel_dp's MST enabled SW state matches the corresponding DPCD
+ * state. A long HPD pulse - not long enough to be detected as a disconnected
+ * state - could've reset the DPCD state, which requires tearing
+ * down/recreating the MST topology.
+ *
+ * Returns %true if the SW MST enabled and DPCD states match, %false
+ * otherwise.
+ */
+bool intel_dp_mst_verify_dpcd_state(struct intel_dp *intel_dp)
+{
+ struct intel_display *display = to_intel_display(intel_dp);
+ struct intel_connector *connector = intel_dp->attached_connector;
+ struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
+ struct intel_encoder *encoder = &dig_port->base;
+ int ret;
+ u8 val;
+
+ if (!intel_dp->is_mst)
+ return true;
+
+ ret = drm_dp_dpcd_readb(intel_dp->mst_mgr.aux, DP_MSTM_CTRL, &val);
+
+ /* Adjust the expected register value for SST + SideBand. */
+ if (ret < 0 || val != (DP_MST_EN | DP_UP_REQ_EN | DP_UPSTREAM_IS_SRC)) {
+ drm_dbg_kms(display->drm,
+ "[CONNECTOR:%d:%s][ENCODER:%d:%s] MST mode got reset, removing topology (ret=%d, ctrl=0x%02x)\n",
+ connector->base.base.id, connector->base.name,
+ encoder->base.base.id, encoder->base.name,
+ ret, val);
+
+ return false;
+ }
+
+ return true;
+}
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.h b/drivers/gpu/drm/i915/display/intel_dp_mst.h
index 8ca1d59..9e4c767 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.h
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.h
@@ -27,5 +27,6 @@ int intel_dp_mst_atomic_check_link(struct intel_atomic_state *state,
struct intel_link_bw_limits *limits);
bool intel_dp_mst_crtc_needs_modeset(struct intel_atomic_state *state,
struct intel_crtc *crtc);
+bool intel_dp_mst_verify_dpcd_state(struct intel_dp *intel_dp);
#endif /* __INTEL_DP_MST_H__ */
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index eae5b5e..931d2cf 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -1870,7 +1870,6 @@ static const struct dmi_system_id vlv_dsi_dmi_quirk_table[] = {
/* Lenovo Yoga Tab 3 Pro YT3-X90F */
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
- DMI_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"),
DMI_MATCH(DMI_PRODUCT_VERSION, "Blade3-10A-001"),
},
.driver_data = (void *)vlv_dsi_lenovo_yoga_tab3_backlight_fixup,
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c
index 3b69bc6..551b0d7 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c
@@ -212,6 +212,37 @@ int intel_gsc_fw_get_binary_info(struct intel_uc_fw *gsc_fw, const void *data, s
}
}
+ if (IS_ARROWLAKE(gt->i915)) {
+ bool too_old = false;
+
+ /*
+ * ARL requires a newer firmware than MTL did (102.0.10.1878) but the
+ * firmware is actually common. So, need to do an explicit version check
+ * here rather than using a separate table entry. And if the older
+ * MTL-only version is found, then just don't use GSC rather than aborting
+ * the driver load.
+ */
+ if (gsc->release.major < 102) {
+ too_old = true;
+ } else if (gsc->release.major == 102) {
+ if (gsc->release.minor == 0) {
+ if (gsc->release.patch < 10) {
+ too_old = true;
+ } else if (gsc->release.patch == 10) {
+ if (gsc->release.build < 1878)
+ too_old = true;
+ }
+ }
+ }
+
+ if (too_old) {
+ gt_info(gt, "GSC firmware too old for ARL, got %d.%d.%d.%d but need at least 102.0.10.1878",
+ gsc->release.major, gsc->release.minor,
+ gsc->release.patch, gsc->release.build);
+ return -EINVAL;
+ }
+ }
+
return 0;
}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index d80278e..ec33ad9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -698,12 +698,18 @@ static int check_gsc_manifest(struct intel_gt *gt,
const struct firmware *fw,
struct intel_uc_fw *uc_fw)
{
+ int ret;
+
switch (uc_fw->type) {
case INTEL_UC_FW_TYPE_HUC:
- intel_huc_fw_get_binary_info(uc_fw, fw->data, fw->size);
+ ret = intel_huc_fw_get_binary_info(uc_fw, fw->data, fw->size);
+ if (ret)
+ return ret;
break;
case INTEL_UC_FW_TYPE_GSC:
- intel_gsc_fw_get_binary_info(uc_fw, fw->data, fw->size);
+ ret = intel_gsc_fw_get_binary_info(uc_fw, fw->data, fw->size);
+ if (ret)
+ return ret;
break;
default:
MISSING_CASE(uc_fw->type);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d7723dd..110340e 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -546,6 +546,8 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
#define IS_LUNARLAKE(i915) (0 && i915)
#define IS_BATTLEMAGE(i915) (0 && i915)
+#define IS_ARROWLAKE(i915) \
+ IS_SUBPLATFORM(i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_ARL)
#define IS_DG2_G10(i915) \
IS_SUBPLATFORM(i915, INTEL_DG2, INTEL_SUBPLATFORM_G10)
#define IS_DG2_G11(i915) \
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index d26de37..eede541 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -203,6 +203,10 @@ static const u16 subplatform_g12_ids[] = {
INTEL_DG2_G12_IDS(ID),
};
+static const u16 subplatform_arl_ids[] = {
+ INTEL_ARL_IDS(ID),
+};
+
static bool find_devid(u16 id, const u16 *p, unsigned int num)
{
for (; num; num--, p++) {
@@ -260,6 +264,9 @@ static void intel_device_info_subplatform_init(struct drm_i915_private *i915)
} else if (find_devid(devid, subplatform_g12_ids,
ARRAY_SIZE(subplatform_g12_ids))) {
mask = BIT(INTEL_SUBPLATFORM_G12);
+ } else if (find_devid(devid, subplatform_arl_ids,
+ ARRAY_SIZE(subplatform_arl_ids))) {
+ mask = BIT(INTEL_SUBPLATFORM_ARL);
}
GEM_BUG_ON(mask & ~INTEL_SUBPLATFORM_MASK);
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index d1a2abc..df73ef9 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -127,6 +127,9 @@ enum intel_platform {
#define INTEL_SUBPLATFORM_N 1
#define INTEL_SUBPLATFORM_RPLU 2
+/* MTL */
+#define INTEL_SUBPLATFORM_ARL 0
+
enum intel_ppgtt_type {
INTEL_PPGTT_NONE = I915_GEM_PPGTT_NONE,
INTEL_PPGTT_ALIASING = I915_GEM_PPGTT_ALIASING,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index ae5c6ec..77b50c5 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -539,8 +539,8 @@ static int mtk_drm_kms_init(struct drm_device *drm)
}
/* IGT will check if the cursor size is configured */
- drm->mode_config.cursor_width = drm->mode_config.max_width;
- drm->mode_config.cursor_height = drm->mode_config.max_height;
+ drm->mode_config.cursor_width = 512;
+ drm->mode_config.cursor_height = 512;
/* Use OVL device for all DMA memory allocations */
crtc = drm_crtc_from_index(drm, 0);
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 1c66267..ecc3fc5 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -99,7 +99,7 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
* was a bad idea, and is only provided for backwards
* compatibility for older targets.
*/
- return -ENODEV;
+ return -ENOENT;
}
if (IS_ERR(fw)) {
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 34c56e8..3b171bf 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -1171,8 +1171,6 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc,
cstate->num_mixers = num_lm;
- dpu_enc->connector = conn_state->connector;
-
for (i = 0; i < dpu_enc->num_phys_encs; i++) {
struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
@@ -1270,6 +1268,8 @@ static void dpu_encoder_virt_atomic_enable(struct drm_encoder *drm_enc,
dpu_enc->commit_done_timedout = false;
+ dpu_enc->connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc);
+
cur_mode = &dpu_enc->base.crtc->state->adjusted_mode;
dpu_enc->wide_bus_en = dpu_encoder_is_widebus_enabled(drm_enc);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
index fc178ec..648c8d0a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
@@ -308,8 +308,8 @@ static const u32 wb2_formats_rgb_yuv[] = {
{ \
.maxdwnscale = SSPP_UNITY_SCALE, \
.maxupscale = SSPP_UNITY_SCALE, \
- .format_list = plane_formats_yuv, \
- .num_formats = ARRAY_SIZE(plane_formats_yuv), \
+ .format_list = plane_formats, \
+ .num_formats = ARRAY_SIZE(plane_formats), \
.virt_format_list = plane_formats, \
.virt_num_formats = ARRAY_SIZE(plane_formats), \
}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
index e2adc93..935ff6f 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
@@ -31,24 +31,14 @@
* @fmt: Pointer to format string
*/
#define DPU_DEBUG(fmt, ...) \
- do { \
- if (drm_debug_enabled(DRM_UT_KMS)) \
- DRM_DEBUG(fmt, ##__VA_ARGS__); \
- else \
- pr_debug(fmt, ##__VA_ARGS__); \
- } while (0)
+ DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__)
/**
* DPU_DEBUG_DRIVER - macro for hardware driver logging
* @fmt: Pointer to format string
*/
#define DPU_DEBUG_DRIVER(fmt, ...) \
- do { \
- if (drm_debug_enabled(DRM_UT_DRIVER)) \
- DRM_ERROR(fmt, ##__VA_ARGS__); \
- else \
- pr_debug(fmt, ##__VA_ARGS__); \
- } while (0)
+ DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__)
#define DPU_ERROR(fmt, ...) pr_err("[dpu error]" fmt, ##__VA_ARGS__)
#define DPU_ERROR_RATELIMITED(fmt, ...) pr_err_ratelimited("[dpu error]" fmt, ##__VA_ARGS__)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index 40c4dd2..29298e0 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -681,6 +681,9 @@ static int dpu_plane_prepare_fb(struct drm_plane *plane,
new_state->fb, &layout);
if (ret) {
DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret);
+ if (pstate->aspace)
+ msm_framebuffer_cleanup(new_state->fb, pstate->aspace,
+ pstate->needs_dirtyfb);
return ret;
}
@@ -744,10 +747,9 @@ static int dpu_plane_atomic_check_pipe(struct dpu_plane *pdpu,
min_src_size = MSM_FORMAT_IS_YUV(fmt) ? 2 : 1;
if (MSM_FORMAT_IS_YUV(fmt) &&
- (!pipe->sspp->cap->sblk->scaler_blk.len ||
- !pipe->sspp->cap->sblk->csc_blk.len)) {
+ !pipe->sspp->cap->sblk->csc_blk.len) {
DPU_DEBUG_PLANE(pdpu,
- "plane doesn't have scaler/csc for yuv\n");
+ "plane doesn't have csc for yuv\n");
return -EINVAL;
}
@@ -864,6 +866,10 @@ static int dpu_plane_atomic_check(struct drm_plane *plane,
max_linewidth = pdpu->catalog->caps->max_linewidth;
+ drm_rect_rotate(&pipe_cfg->src_rect,
+ new_plane_state->fb->width, new_plane_state->fb->height,
+ new_plane_state->rotation);
+
if ((drm_rect_width(&pipe_cfg->src_rect) > max_linewidth) ||
_dpu_plane_calc_clk(&crtc_state->adjusted_mode, pipe_cfg) > max_mdp_clk_rate) {
/*
@@ -913,6 +919,14 @@ static int dpu_plane_atomic_check(struct drm_plane *plane,
r_pipe_cfg->dst_rect.x1 = pipe_cfg->dst_rect.x2;
}
+ drm_rect_rotate_inv(&pipe_cfg->src_rect,
+ new_plane_state->fb->width, new_plane_state->fb->height,
+ new_plane_state->rotation);
+ if (r_pipe->sspp)
+ drm_rect_rotate_inv(&r_pipe_cfg->src_rect,
+ new_plane_state->fb->width, new_plane_state->fb->height,
+ new_plane_state->rotation);
+
ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, fmt, &crtc_state->adjusted_mode);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
index 7bc8a9f..f342fc5 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -1286,6 +1286,8 @@ static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl,
link_info.rate = ctrl->link->link_params.rate;
link_info.capabilities = DP_LINK_CAP_ENHANCED_FRAMING;
+ dp_link_reset_phy_params_vx_px(ctrl->link);
+
dp_aux_link_configure(ctrl->aux, &link_info);
if (drm_dp_max_downspread(dpcd))
diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c
index a916b5f..6ff6c9e 100644
--- a/drivers/gpu/drm/msm/dp/dp_panel.c
+++ b/drivers/gpu/drm/msm/dp/dp_panel.c
@@ -90,22 +90,22 @@ static int dp_panel_read_dpcd(struct dp_panel *dp_panel)
static u32 dp_panel_get_supported_bpp(struct dp_panel *dp_panel,
u32 mode_edid_bpp, u32 mode_pclk_khz)
{
- struct dp_link_info *link_info;
+ const struct dp_link_info *link_info;
const u32 max_supported_bpp = 30, min_supported_bpp = 18;
- u32 bpp = 0, data_rate_khz = 0;
+ u32 bpp, data_rate_khz;
- bpp = min_t(u32, mode_edid_bpp, max_supported_bpp);
+ bpp = min(mode_edid_bpp, max_supported_bpp);
link_info = &dp_panel->link_info;
data_rate_khz = link_info->num_lanes * link_info->rate * 8;
- while (bpp > min_supported_bpp) {
+ do {
if (mode_pclk_khz * bpp <= data_rate_khz)
- break;
+ return bpp;
bpp -= 6;
- }
+ } while (bpp > min_supported_bpp);
- return bpp;
+ return min_supported_bpp;
}
int dp_panel_read_sink_caps(struct dp_panel *dp_panel,
@@ -423,8 +423,9 @@ int dp_panel_init_panel_info(struct dp_panel *dp_panel)
drm_mode->clock);
drm_dbg_dp(panel->drm_dev, "bpp = %d\n", dp_panel->dp_mode.bpp);
- dp_panel->dp_mode.bpp = max_t(u32, 18,
- min_t(u32, dp_panel->dp_mode.bpp, 30));
+ dp_panel->dp_mode.bpp = dp_panel_get_mode_bpp(dp_panel, dp_panel->dp_mode.bpp,
+ dp_panel->dp_mode.drm_mode.clock);
+
drm_dbg_dp(panel->drm_dev, "updated bpp = %d\n",
dp_panel->dp_mode.bpp);
diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c
index d90b947..faa88fd 100644
--- a/drivers/gpu/drm/msm/msm_mdss.c
+++ b/drivers/gpu/drm/msm/msm_mdss.c
@@ -577,7 +577,7 @@ static const struct msm_mdss_data sc7180_data = {
.ubwc_enc_version = UBWC_2_0,
.ubwc_dec_version = UBWC_2_0,
.ubwc_static = 0x1e,
- .highest_bank_bit = 0x3,
+ .highest_bank_bit = 0x1,
.reg_bus_bw = 76800,
};
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
index adc60b2..0af01a0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
@@ -205,7 +205,8 @@ nvkm_firmware_dtor(struct nvkm_firmware *fw)
break;
case NVKM_FIRMWARE_IMG_DMA:
nvkm_memory_unref(&memory);
- dma_free_coherent(fw->device->dev, sg_dma_len(&fw->mem.sgl), fw->img, fw->phys);
+ dma_free_noncoherent(fw->device->dev, sg_dma_len(&fw->mem.sgl),
+ fw->img, fw->phys, DMA_TO_DEVICE);
break;
case NVKM_FIRMWARE_IMG_SGT:
nvkm_memory_unref(&memory);
@@ -236,10 +237,12 @@ nvkm_firmware_ctor(const struct nvkm_firmware_func *func, const char *name,
break;
case NVKM_FIRMWARE_IMG_DMA: {
dma_addr_t addr;
-
len = ALIGN(fw->len, PAGE_SIZE);
- fw->img = dma_alloc_coherent(fw->device->dev, len, &addr, GFP_KERNEL);
+ fw->img = dma_alloc_noncoherent(fw->device->dev,
+ len, &addr,
+ DMA_TO_DEVICE,
+ GFP_KERNEL);
if (fw->img) {
memcpy(fw->img, src, fw->len);
fw->phys = addr;
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
index 80a480b1..a1c8545f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
@@ -89,6 +89,12 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct nvkm_subdev *user,
nvkm_falcon_fw_dtor_sigs(fw);
}
+ /* after last write to the img, sync dma mappings */
+ dma_sync_single_for_device(fw->fw.device->dev,
+ fw->fw.phys,
+ sg_dma_len(&fw->fw.mem.sgl),
+ DMA_TO_DEVICE);
+
FLCNFW_DBG(fw, "resetting");
fw->func->reset(fw);
diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c
index 2241e53..dec6913 100644
--- a/drivers/gpu/drm/rockchip/inno_hdmi.c
+++ b/drivers/gpu/drm/rockchip/inno_hdmi.c
@@ -279,7 +279,6 @@ static int inno_hdmi_upload_frame(struct drm_connector *connector,
const u8 *buffer, size_t len)
{
struct inno_hdmi *hdmi = connector_to_inno_hdmi(connector);
- u8 packed_frame[HDMI_MAXIMUM_INFO_FRAME_SIZE];
ssize_t i;
if (type != HDMI_INFOFRAME_TYPE_AVI) {
@@ -291,8 +290,7 @@ static int inno_hdmi_upload_frame(struct drm_connector *connector,
inno_hdmi_disable_frame(connector, type);
for (i = 0; i < len; i++)
- hdmi_writeb(hdmi, HDMI_CONTROL_PACKET_ADDR + i,
- packed_frame[i]);
+ hdmi_writeb(hdmi, HDMI_CONTROL_PACKET_ADDR + i, buffer[i]);
return 0;
}
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 9bd7453..ad1e623 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -134,6 +134,8 @@ v3d_job_start_stats(struct v3d_job *job, enum v3d_queue queue)
struct v3d_stats *local_stats = &file->stats[queue];
u64 now = local_clock();
+ preempt_disable();
+
write_seqcount_begin(&local_stats->lock);
local_stats->start_ns = now;
write_seqcount_end(&local_stats->lock);
@@ -141,6 +143,8 @@ v3d_job_start_stats(struct v3d_job *job, enum v3d_queue queue)
write_seqcount_begin(&global_stats->lock);
global_stats->start_ns = now;
write_seqcount_end(&global_stats->lock);
+
+ preempt_enable();
}
static void
@@ -162,8 +166,10 @@ v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue)
struct v3d_stats *local_stats = &file->stats[queue];
u64 now = local_clock();
+ preempt_disable();
v3d_stats_update(local_stats, now);
v3d_stats_update(global_stats, now);
+ preempt_enable();
}
static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job)
@@ -315,7 +321,7 @@ v3d_csd_job_run(struct drm_sched_job *sched_job)
struct v3d_dev *v3d = job->base.v3d;
struct drm_device *dev = &v3d->drm;
struct dma_fence *fence;
- int i, csd_cfg0_reg, csd_cfg_reg_count;
+ int i, csd_cfg0_reg;
v3d->csd_job = job;
@@ -335,9 +341,17 @@ v3d_csd_job_run(struct drm_sched_job *sched_job)
v3d_switch_perfmon(v3d, &job->base);
csd_cfg0_reg = V3D_CSD_QUEUED_CFG0(v3d->ver);
- csd_cfg_reg_count = v3d->ver < 71 ? 6 : 7;
- for (i = 1; i <= csd_cfg_reg_count; i++)
+ for (i = 1; i <= 6; i++)
V3D_CORE_WRITE(0, csd_cfg0_reg + 4 * i, job->args.cfg[i]);
+
+ /* Although V3D 7.1 has an eighth configuration register, we are not
+ * using it. Therefore, make sure it remains unused.
+ *
+ * XXX: Set the CFG7 register
+ */
+ if (v3d->ver >= 71)
+ V3D_CORE_WRITE(0, V3D_V7_CSD_QUEUED_CFG7, 0);
+
/* CFG0 write kicks off the job. */
V3D_CORE_WRITE(0, csd_cfg0_reg, job->args.cfg[0]);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
index 717d624..890a66a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
@@ -27,6 +27,8 @@
**************************************************************************/
#include "vmwgfx_drv.h"
+
+#include "vmwgfx_bo.h"
#include <linux/highmem.h>
/*
@@ -420,13 +422,105 @@ static int vmw_bo_cpu_blit_line(struct vmw_bo_blit_line_data *d,
return 0;
}
+static void *map_external(struct vmw_bo *bo, struct iosys_map *map)
+{
+ struct vmw_private *vmw =
+ container_of(bo->tbo.bdev, struct vmw_private, bdev);
+ void *ptr = NULL;
+ int ret;
+
+ if (bo->tbo.base.import_attach) {
+ ret = dma_buf_vmap(bo->tbo.base.dma_buf, map);
+ if (ret) {
+ drm_dbg_driver(&vmw->drm,
+ "Wasn't able to map external bo!\n");
+ goto out;
+ }
+ ptr = map->vaddr;
+ } else {
+ ptr = vmw_bo_map_and_cache(bo);
+ }
+
+out:
+ return ptr;
+}
+
+static void unmap_external(struct vmw_bo *bo, struct iosys_map *map)
+{
+ if (bo->tbo.base.import_attach)
+ dma_buf_vunmap(bo->tbo.base.dma_buf, map);
+ else
+ vmw_bo_unmap(bo);
+}
+
+static int vmw_external_bo_copy(struct vmw_bo *dst, u32 dst_offset,
+ u32 dst_stride, struct vmw_bo *src,
+ u32 src_offset, u32 src_stride,
+ u32 width_in_bytes, u32 height,
+ struct vmw_diff_cpy *diff)
+{
+ struct vmw_private *vmw =
+ container_of(dst->tbo.bdev, struct vmw_private, bdev);
+ size_t dst_size = dst->tbo.resource->size;
+ size_t src_size = src->tbo.resource->size;
+ struct iosys_map dst_map = {0};
+ struct iosys_map src_map = {0};
+ int ret, i;
+ int x_in_bytes;
+ u8 *vsrc;
+ u8 *vdst;
+
+ vsrc = map_external(src, &src_map);
+ if (!vsrc) {
+ drm_dbg_driver(&vmw->drm, "Wasn't able to map src\n");
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ vdst = map_external(dst, &dst_map);
+ if (!vdst) {
+ drm_dbg_driver(&vmw->drm, "Wasn't able to map dst\n");
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ vsrc += src_offset;
+ vdst += dst_offset;
+ if (src_stride == dst_stride) {
+ dst_size -= dst_offset;
+ src_size -= src_offset;
+ memcpy(vdst, vsrc,
+ min(dst_stride * height, min(dst_size, src_size)));
+ } else {
+ WARN_ON(dst_stride < width_in_bytes);
+ for (i = 0; i < height; ++i) {
+ memcpy(vdst, vsrc, width_in_bytes);
+ vsrc += src_stride;
+ vdst += dst_stride;
+ }
+ }
+
+ x_in_bytes = (dst_offset % dst_stride);
+ diff->rect.x1 = x_in_bytes / diff->cpp;
+ diff->rect.y1 = ((dst_offset - x_in_bytes) / dst_stride);
+ diff->rect.x2 = diff->rect.x1 + width_in_bytes / diff->cpp;
+ diff->rect.y2 = diff->rect.y1 + height;
+
+ ret = 0;
+out:
+ unmap_external(src, &src_map);
+ unmap_external(dst, &dst_map);
+
+ return ret;
+}
+
/**
* vmw_bo_cpu_blit - in-kernel cpu blit.
*
- * @dst: Destination buffer object.
+ * @vmw_dst: Destination buffer object.
* @dst_offset: Destination offset of blit start in bytes.
* @dst_stride: Destination stride in bytes.
- * @src: Source buffer object.
+ * @vmw_src: Source buffer object.
* @src_offset: Source offset of blit start in bytes.
* @src_stride: Source stride in bytes.
* @w: Width of blit.
@@ -444,13 +538,15 @@ static int vmw_bo_cpu_blit_line(struct vmw_bo_blit_line_data *d,
* Neither of the buffer objects may be placed in PCI memory
* (Fixed memory in TTM terminology) when using this function.
*/
-int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
+int vmw_bo_cpu_blit(struct vmw_bo *vmw_dst,
u32 dst_offset, u32 dst_stride,
- struct ttm_buffer_object *src,
+ struct vmw_bo *vmw_src,
u32 src_offset, u32 src_stride,
u32 w, u32 h,
struct vmw_diff_cpy *diff)
{
+ struct ttm_buffer_object *src = &vmw_src->tbo;
+ struct ttm_buffer_object *dst = &vmw_dst->tbo;
struct ttm_operation_ctx ctx = {
.interruptible = false,
.no_wait_gpu = false
@@ -460,6 +556,11 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
int ret = 0;
struct page **dst_pages = NULL;
struct page **src_pages = NULL;
+ bool src_external = (src->ttm->page_flags & TTM_TT_FLAG_EXTERNAL) != 0;
+ bool dst_external = (dst->ttm->page_flags & TTM_TT_FLAG_EXTERNAL) != 0;
+
+ if (WARN_ON(dst == src))
+ return -EINVAL;
/* Buffer objects need to be either pinned or reserved: */
if (!(dst->pin_count))
@@ -479,6 +580,11 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
return ret;
}
+ if (src_external || dst_external)
+ return vmw_external_bo_copy(vmw_dst, dst_offset, dst_stride,
+ vmw_src, src_offset, src_stride,
+ w, h, diff);
+
if (!src->ttm->pages && src->ttm->sg) {
src_pages = kvmalloc_array(src->ttm->num_pages,
sizeof(struct page *), GFP_KERNEL);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
index f42ebc4..a0e433f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -360,6 +360,8 @@ void *vmw_bo_map_and_cache_size(struct vmw_bo *vbo, size_t size)
void *virtual;
int ret;
+ atomic_inc(&vbo->map_count);
+
virtual = ttm_kmap_obj_virtual(&vbo->map, ¬_used);
if (virtual)
return virtual;
@@ -383,11 +385,17 @@ void *vmw_bo_map_and_cache_size(struct vmw_bo *vbo, size_t size)
*/
void vmw_bo_unmap(struct vmw_bo *vbo)
{
+ int map_count;
+
if (vbo->map.bo == NULL)
return;
- ttm_bo_kunmap(&vbo->map);
- vbo->map.bo = NULL;
+ map_count = atomic_dec_return(&vbo->map_count);
+
+ if (!map_count) {
+ ttm_bo_kunmap(&vbo->map);
+ vbo->map.bo = NULL;
+ }
}
@@ -421,6 +429,7 @@ static int vmw_bo_init(struct vmw_private *dev_priv,
vmw_bo->tbo.priority = 3;
vmw_bo->res_tree = RB_ROOT;
xa_init(&vmw_bo->detached_resources);
+ atomic_set(&vmw_bo->map_count, 0);
params->size = ALIGN(params->size, PAGE_SIZE);
drm_gem_private_object_init(vdev, &vmw_bo->tbo.base, params->size);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
index 62b4342..43b5439 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
@@ -71,6 +71,8 @@ struct vmw_bo_params {
* @map: Kmap object for semi-persistent mappings
* @res_tree: RB tree of resources using this buffer object as a backing MOB
* @res_prios: Eviction priority counts for attached resources
+ * @map_count: The number of currently active maps. Will differ from the
+ * cpu_writers because it includes kernel maps.
* @cpu_writers: Number of synccpu write grabs. Protected by reservation when
* increased. May be decreased without reservation.
* @dx_query_ctx: DX context if this buffer object is used as a DX query MOB
@@ -90,6 +92,7 @@ struct vmw_bo {
u32 res_prios[TTM_MAX_BO_PRIORITY];
struct xarray detached_resources;
+ atomic_t map_count;
atomic_t cpu_writers;
/* Not ref-counted. Protected by binding_mutex */
struct vmw_resource *dx_query_ctx;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 32f50e5..3f4719b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -1353,9 +1353,9 @@ void vmw_diff_memcpy(struct vmw_diff_cpy *diff, u8 *dest, const u8 *src,
void vmw_memcpy(struct vmw_diff_cpy *diff, u8 *dest, const u8 *src, size_t n);
-int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
+int vmw_bo_cpu_blit(struct vmw_bo *dst,
u32 dst_offset, u32 dst_stride,
- struct ttm_buffer_object *src,
+ struct vmw_bo *src,
u32 src_offset, u32 src_stride,
u32 w, u32 h,
struct vmw_diff_cpy *diff);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 5453f7c..fab155a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -502,7 +502,7 @@ static void vmw_stdu_bo_cpu_commit(struct vmw_kms_dirty *dirty)
container_of(dirty->unit, typeof(*stdu), base);
s32 width, height;
s32 src_pitch, dst_pitch;
- struct ttm_buffer_object *src_bo, *dst_bo;
+ struct vmw_bo *src_bo, *dst_bo;
u32 src_offset, dst_offset;
struct vmw_diff_cpy diff = VMW_CPU_BLIT_DIFF_INITIALIZER(stdu->cpp);
@@ -517,11 +517,11 @@ static void vmw_stdu_bo_cpu_commit(struct vmw_kms_dirty *dirty)
/* Assume we are blitting from Guest (bo) to Host (display_srf) */
src_pitch = stdu->display_srf->metadata.base_size.width * stdu->cpp;
- src_bo = &stdu->display_srf->res.guest_memory_bo->tbo;
+ src_bo = stdu->display_srf->res.guest_memory_bo;
src_offset = ddirty->top * src_pitch + ddirty->left * stdu->cpp;
dst_pitch = ddirty->pitch;
- dst_bo = &ddirty->buf->tbo;
+ dst_bo = ddirty->buf;
dst_offset = ddirty->fb_top * dst_pitch + ddirty->fb_left * stdu->cpp;
(void) vmw_bo_cpu_blit(dst_bo, dst_offset, dst_pitch,
@@ -1170,7 +1170,7 @@ vmw_stdu_bo_populate_update_cpu(struct vmw_du_update_plane *update, void *cmd,
struct vmw_diff_cpy diff = VMW_CPU_BLIT_DIFF_INITIALIZER(0);
struct vmw_stdu_update_gb_image *cmd_img = cmd;
struct vmw_stdu_update *cmd_update;
- struct ttm_buffer_object *src_bo, *dst_bo;
+ struct vmw_bo *src_bo, *dst_bo;
u32 src_offset, dst_offset;
s32 src_pitch, dst_pitch;
s32 width, height;
@@ -1184,11 +1184,11 @@ vmw_stdu_bo_populate_update_cpu(struct vmw_du_update_plane *update, void *cmd,
diff.cpp = stdu->cpp;
- dst_bo = &stdu->display_srf->res.guest_memory_bo->tbo;
+ dst_bo = stdu->display_srf->res.guest_memory_bo;
dst_pitch = stdu->display_srf->metadata.base_size.width * stdu->cpp;
dst_offset = bb->y1 * dst_pitch + bb->x1 * stdu->cpp;
- src_bo = &vfbbo->buffer->tbo;
+ src_bo = vfbbo->buffer;
src_pitch = update->vfb->base.pitches[0];
src_offset = bo_update->fb_top * src_pitch + bo_update->fb_left *
stdu->cpp;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 8ae6a76..1625b30 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -2283,9 +2283,11 @@ int vmw_dumb_create(struct drm_file *file_priv,
/*
* Without mob support we're just going to use raw memory buffer
* because we wouldn't be able to support full surface coherency
- * without mobs
+ * without mobs. There also no reason to support surface coherency
+ * without 3d (i.e. gpu usage on the host) because then all the
+ * contents is going to be rendered guest side.
*/
- if (!dev_priv->has_mob) {
+ if (!dev_priv->has_mob || !vmw_supports_3d(dev_priv)) {
int cpp = DIV_ROUND_UP(args->bpp, 8);
switch (cpp) {
diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 628c245..e97c9da 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -25,12 +25,14 @@
uses_generated_oob := \
$(obj)/xe_ggtt.o \
+ $(obj)/xe_device.o \
$(obj)/xe_gsc.o \
$(obj)/xe_gt.o \
$(obj)/xe_guc.o \
$(obj)/xe_guc_ads.o \
$(obj)/xe_guc_pc.o \
$(obj)/xe_migrate.o \
+ $(obj)/xe_pat.o \
$(obj)/xe_ring_ops.o \
$(obj)/xe_vm.o \
$(obj)/xe_wa.o \
diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c
index 8b83dcf..49de4e4 100644
--- a/drivers/gpu/drm/xe/display/xe_display.c
+++ b/drivers/gpu/drm/xe/display/xe_display.c
@@ -132,6 +132,7 @@ static void xe_display_fini_noirq(void *arg)
return;
intel_display_driver_remove_noirq(xe);
+ intel_opregion_cleanup(xe);
}
int xe_display_init_noirq(struct xe_device *xe)
@@ -157,8 +158,10 @@ int xe_display_init_noirq(struct xe_device *xe)
intel_display_device_info_runtime_init(xe);
err = intel_display_driver_probe_noirq(xe);
- if (err)
+ if (err) {
+ intel_opregion_cleanup(xe);
return err;
+ }
return devm_add_action_or_reset(xe->drm.dev, xe_display_fini_noirq, xe);
}
@@ -280,6 +283,27 @@ static bool suspend_to_idle(void)
return false;
}
+static void xe_display_flush_cleanup_work(struct xe_device *xe)
+{
+ struct intel_crtc *crtc;
+
+ for_each_intel_crtc(&xe->drm, crtc) {
+ struct drm_crtc_commit *commit;
+
+ spin_lock(&crtc->base.commit_lock);
+ commit = list_first_entry_or_null(&crtc->base.commit_list,
+ struct drm_crtc_commit, commit_entry);
+ if (commit)
+ drm_crtc_commit_get(commit);
+ spin_unlock(&crtc->base.commit_lock);
+
+ if (commit) {
+ wait_for_completion(&commit->cleanup_done);
+ drm_crtc_commit_put(commit);
+ }
+ }
+}
+
void xe_display_pm_suspend(struct xe_device *xe, bool runtime)
{
bool s2idle = suspend_to_idle();
@@ -297,6 +321,8 @@ void xe_display_pm_suspend(struct xe_device *xe, bool runtime)
if (!runtime)
intel_display_driver_suspend(xe);
+ xe_display_flush_cleanup_work(xe);
+
intel_dp_mst_suspend(xe);
intel_hpd_cancel_work(xe);
diff --git a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c
index 9e860c6..ccd0d87 100644
--- a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c
+++ b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c
@@ -7,6 +7,8 @@
#include "intel_display_types.h"
#include "intel_dsb_buffer.h"
#include "xe_bo.h"
+#include "xe_device.h"
+#include "xe_device_types.h"
#include "xe_gt.h"
u32 intel_dsb_buffer_ggtt_offset(struct intel_dsb_buffer *dsb_buf)
@@ -16,7 +18,10 @@ u32 intel_dsb_buffer_ggtt_offset(struct intel_dsb_buffer *dsb_buf)
void intel_dsb_buffer_write(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val)
{
+ struct xe_device *xe = dsb_buf->vma->bo->tile->xe;
+
iosys_map_wr(&dsb_buf->vma->bo->vmap, idx * 4, u32, val);
+ xe_device_l2_flush(xe);
}
u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx)
@@ -26,9 +31,12 @@ u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx)
void intel_dsb_buffer_memset(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val, size_t size)
{
+ struct xe_device *xe = dsb_buf->vma->bo->tile->xe;
+
WARN_ON(idx > (dsb_buf->buf_size - size) / sizeof(*dsb_buf->cmd_buf));
iosys_map_memset(&dsb_buf->vma->bo->vmap, idx * 4, val, size);
+ xe_device_l2_flush(xe);
}
bool intel_dsb_buffer_create(struct intel_crtc *crtc, struct intel_dsb_buffer *dsb_buf, size_t size)
diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c
index 423f367..d7db44e 100644
--- a/drivers/gpu/drm/xe/display/xe_fb_pin.c
+++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c
@@ -10,6 +10,7 @@
#include "intel_fb.h"
#include "intel_fb_pin.h"
#include "xe_bo.h"
+#include "xe_device.h"
#include "xe_ggtt.h"
#include "xe_gt.h"
#include "xe_pm.h"
@@ -304,6 +305,8 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb,
if (ret)
goto err_unpin;
+ /* Ensure DPT writes are flushed */
+ xe_device_l2_flush(xe);
return vma;
err_unpin:
diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
index d44564b..3c28650 100644
--- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
@@ -80,6 +80,9 @@
#define LE_CACHEABILITY_MASK REG_GENMASK(1, 0)
#define LE_CACHEABILITY(value) REG_FIELD_PREP(LE_CACHEABILITY_MASK, value)
+#define XE2_GAMREQSTRM_CTRL XE_REG(0x4194)
+#define CG_DIS_CNTLBUS REG_BIT(6)
+
#define CCS_AUX_INV XE_REG(0x4208)
#define VD0_AUX_INV XE_REG(0x4218)
@@ -372,6 +375,11 @@
#define XEHPC_L3CLOS_MASK(i) XE_REG_MCR(0xb194 + (i) * 8)
+#define XE2_GLOBAL_INVAL XE_REG(0xb404)
+
+#define SCRATCH1LPFC XE_REG(0xb474)
+#define EN_L3_RW_CCS_CACHE_FLUSH REG_BIT(0)
+
#define XE2LPM_L3SQCREG5 XE_REG_MCR(0xb658)
#define XE2_TDF_CTRL XE_REG(0xb418)
@@ -429,6 +437,7 @@
#define DIS_FIX_EOT1_FLUSH REG_BIT(9)
#define TDL_TSL_CHICKEN XE_REG_MCR(0xe4c4, XE_REG_OPTION_MASKED)
+#define STK_ID_RESTRICT REG_BIT(12)
#define SLM_WMTP_RESTORE REG_BIT(11)
#define ROW_CHICKEN XE_REG_MCR(0xe4f0, XE_REG_OPTION_MASKED)
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 31192d9..261d3d6 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -1575,7 +1575,7 @@ struct xe_bo *xe_bo_create_from_data(struct xe_device *xe, struct xe_tile *tile,
return bo;
}
-static void __xe_bo_unpin_map_no_vm(struct drm_device *drm, void *arg)
+static void __xe_bo_unpin_map_no_vm(void *arg)
{
xe_bo_unpin_map_no_vm(arg);
}
@@ -1590,7 +1590,7 @@ struct xe_bo *xe_managed_bo_create_pin_map(struct xe_device *xe, struct xe_tile
if (IS_ERR(bo))
return bo;
- ret = drmm_add_action_or_reset(&xe->drm, __xe_bo_unpin_map_no_vm, bo);
+ ret = devm_add_action_or_reset(xe->drm.dev, __xe_bo_unpin_map_no_vm, bo);
if (ret)
return ERR_PTR(ret);
@@ -1638,7 +1638,7 @@ int xe_managed_bo_reinit_in_vram(struct xe_device *xe, struct xe_tile *tile, str
if (IS_ERR(bo))
return PTR_ERR(bo);
- drmm_release_action(&xe->drm, __xe_bo_unpin_map_no_vm, *src);
+ devm_release_action(xe->drm.dev, __xe_bo_unpin_map_no_vm, *src);
*src = bo;
return 0;
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 7610941..c89deff 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -54,6 +54,9 @@
#include "xe_vm.h"
#include "xe_vram.h"
#include "xe_wait_user_fence.h"
+#include "xe_wa.h"
+
+#include <generated/xe_wa_oob.h>
static int xe_file_open(struct drm_device *dev, struct drm_file *file)
{
@@ -87,9 +90,55 @@ static int xe_file_open(struct drm_device *dev, struct drm_file *file)
spin_unlock(&xe->clients.lock);
file->driver_priv = xef;
+ kref_init(&xef->refcount);
+
return 0;
}
+static void xe_file_destroy(struct kref *ref)
+{
+ struct xe_file *xef = container_of(ref, struct xe_file, refcount);
+ struct xe_device *xe = xef->xe;
+
+ xa_destroy(&xef->exec_queue.xa);
+ mutex_destroy(&xef->exec_queue.lock);
+ xa_destroy(&xef->vm.xa);
+ mutex_destroy(&xef->vm.lock);
+
+ spin_lock(&xe->clients.lock);
+ xe->clients.count--;
+ spin_unlock(&xe->clients.lock);
+
+ xe_drm_client_put(xef->client);
+ kfree(xef);
+}
+
+/**
+ * xe_file_get() - Take a reference to the xe file object
+ * @xef: Pointer to the xe file
+ *
+ * Anyone with a pointer to xef must take a reference to the xe file
+ * object using this call.
+ *
+ * Return: xe file pointer
+ */
+struct xe_file *xe_file_get(struct xe_file *xef)
+{
+ kref_get(&xef->refcount);
+ return xef;
+}
+
+/**
+ * xe_file_put() - Drop a reference to the xe file object
+ * @xef: Pointer to the xe file
+ *
+ * Used to drop reference to the xef object
+ */
+void xe_file_put(struct xe_file *xef)
+{
+ kref_put(&xef->refcount, xe_file_destroy);
+}
+
static void xe_file_close(struct drm_device *dev, struct drm_file *file)
{
struct xe_device *xe = to_xe_device(dev);
@@ -98,6 +147,8 @@ static void xe_file_close(struct drm_device *dev, struct drm_file *file)
struct xe_exec_queue *q;
unsigned long idx;
+ xe_pm_runtime_get(xe);
+
/*
* No need for exec_queue.lock here as there is no contention for it
* when FD is closing as IOCTLs presumably can't be modifying the
@@ -108,21 +159,14 @@ static void xe_file_close(struct drm_device *dev, struct drm_file *file)
xe_exec_queue_kill(q);
xe_exec_queue_put(q);
}
- xa_destroy(&xef->exec_queue.xa);
- mutex_destroy(&xef->exec_queue.lock);
mutex_lock(&xef->vm.lock);
xa_for_each(&xef->vm.xa, idx, vm)
xe_vm_close_and_put(vm);
mutex_unlock(&xef->vm.lock);
- xa_destroy(&xef->vm.xa);
- mutex_destroy(&xef->vm.lock);
- spin_lock(&xe->clients.lock);
- xe->clients.count--;
- spin_unlock(&xe->clients.lock);
+ xe_file_put(xef);
- xe_drm_client_put(xef->client);
- kfree(xef);
+ xe_pm_runtime_put(xe);
}
static const struct drm_ioctl_desc xe_ioctls[] = {
@@ -779,6 +823,11 @@ void xe_device_td_flush(struct xe_device *xe)
if (!IS_DGFX(xe) || GRAPHICS_VER(xe) < 20)
return;
+ if (XE_WA(xe_root_mmio_gt(xe), 16023588340)) {
+ xe_device_l2_flush(xe);
+ return;
+ }
+
for_each_gt(gt, xe, id) {
if (xe_gt_is_media_type(gt))
continue;
@@ -802,6 +851,30 @@ void xe_device_td_flush(struct xe_device *xe)
}
}
+void xe_device_l2_flush(struct xe_device *xe)
+{
+ struct xe_gt *gt;
+ int err;
+
+ gt = xe_root_mmio_gt(xe);
+
+ if (!XE_WA(gt, 16023588340))
+ return;
+
+ err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
+ if (err)
+ return;
+
+ spin_lock(>->global_invl_lock);
+ xe_mmio_write32(gt, XE2_GLOBAL_INVAL, 0x1);
+
+ if (xe_mmio_wait32(gt, XE2_GLOBAL_INVAL, 0x1, 0x0, 150, NULL, true))
+ xe_gt_err_once(gt, "Global invalidation timeout\n");
+ spin_unlock(>->global_invl_lock);
+
+ xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
+}
+
u32 xe_device_ccs_bytes(struct xe_device *xe, u64 size)
{
return xe_device_has_flat_ccs(xe) ?
diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index bb07f56..533ccfb 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -162,6 +162,7 @@ u64 xe_device_canonicalize_addr(struct xe_device *xe, u64 address);
u64 xe_device_uncanonicalize_addr(struct xe_device *xe, u64 address);
void xe_device_td_flush(struct xe_device *xe);
+void xe_device_l2_flush(struct xe_device *xe);
static inline bool xe_device_wedged(struct xe_device *xe)
{
@@ -170,4 +171,7 @@ static inline bool xe_device_wedged(struct xe_device *xe)
void xe_device_declare_wedged(struct xe_device *xe);
+struct xe_file *xe_file_get(struct xe_file *xef);
+void xe_file_put(struct xe_file *xef);
+
#endif
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 3bca6d3..cbc582b 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -566,6 +566,9 @@ struct xe_file {
/** @client: drm client */
struct xe_drm_client *client;
+
+ /** @refcount: ref count of this xe file */
+ struct kref refcount;
};
#endif
diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c
index 6a26923..7ddd599 100644
--- a/drivers/gpu/drm/xe/xe_drm_client.c
+++ b/drivers/gpu/drm/xe/xe_drm_client.c
@@ -251,11 +251,8 @@ static void show_run_ticks(struct drm_printer *p, struct drm_file *file)
/* Accumulate all the exec queues from this client */
mutex_lock(&xef->exec_queue.lock);
- xa_for_each(&xef->exec_queue.xa, i, q) {
+ xa_for_each(&xef->exec_queue.xa, i, q)
xe_exec_queue_update_run_ticks(q);
- xef->run_ticks[q->class] += q->run_ticks - q->old_run_ticks;
- q->old_run_ticks = q->run_ticks;
- }
mutex_unlock(&xef->exec_queue.lock);
/* Get the total GPU cycles */
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 0ba3783..9731dcd 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -37,6 +37,10 @@ static void __xe_exec_queue_free(struct xe_exec_queue *q)
{
if (q->vm)
xe_vm_put(q->vm);
+
+ if (q->xef)
+ xe_file_put(q->xef);
+
kfree(q);
}
@@ -101,22 +105,35 @@ static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe,
static int __xe_exec_queue_init(struct xe_exec_queue *q)
{
+ struct xe_vm *vm = q->vm;
int i, err;
+ if (vm) {
+ err = xe_vm_lock(vm, true);
+ if (err)
+ return err;
+ }
+
for (i = 0; i < q->width; ++i) {
q->lrc[i] = xe_lrc_create(q->hwe, q->vm, SZ_16K);
if (IS_ERR(q->lrc[i])) {
err = PTR_ERR(q->lrc[i]);
- goto err_lrc;
+ goto err_unlock;
}
}
+ if (vm)
+ xe_vm_unlock(vm);
+
err = q->ops->init(q);
if (err)
goto err_lrc;
return 0;
+err_unlock:
+ if (vm)
+ xe_vm_unlock(vm);
err_lrc:
for (i = i - 1; i >= 0; --i)
xe_lrc_put(q->lrc[i]);
@@ -136,15 +153,7 @@ struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *v
if (IS_ERR(q))
return q;
- if (vm) {
- err = xe_vm_lock(vm, true);
- if (err)
- goto err_post_alloc;
- }
-
err = __xe_exec_queue_init(q);
- if (vm)
- xe_vm_unlock(vm);
if (err)
goto err_post_alloc;
@@ -634,7 +643,6 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
if (xe_vm_in_preempt_fence_mode(vm)) {
q->lr.context = dma_fence_context_alloc(1);
- spin_lock_init(&q->lr.lock);
err = xe_vm_add_compute_exec_queue(vm, q);
if (XE_IOCTL_DBG(xe, err))
@@ -649,6 +657,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
goto kill_exec_queue;
args->exec_queue_id = id;
+ q->xef = xe_file_get(xef);
return 0;
@@ -762,6 +771,7 @@ bool xe_exec_queue_is_idle(struct xe_exec_queue *q)
*/
void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
{
+ struct xe_file *xef;
struct xe_lrc *lrc;
u32 old_ts, new_ts;
@@ -773,6 +783,8 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
if (!q->vm || !q->vm->xef)
return;
+ xef = q->vm->xef;
+
/*
* Only sample the first LRC. For parallel submission, all of them are
* scheduled together and we compensate that below by multiplying by
@@ -783,7 +795,7 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
*/
lrc = q->lrc[0];
new_ts = xe_lrc_update_timestamp(lrc, &old_ts);
- q->run_ticks += (new_ts - old_ts) * q->width;
+ xef->run_ticks[q->class] += (new_ts - old_ts) * q->width;
}
void xe_exec_queue_kill(struct xe_exec_queue *q)
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 201588e..f6ee0ae 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -38,6 +38,9 @@ enum xe_exec_queue_priority {
* a kernel object.
*/
struct xe_exec_queue {
+ /** @xef: Back pointer to xe file if this is user created exec queue */
+ struct xe_file *xef;
+
/** @gt: graphics tile this exec queue can submit to */
struct xe_gt *gt;
/**
@@ -123,8 +126,6 @@ struct xe_exec_queue {
u32 seqno;
/** @lr.link: link into VM's list of exec queues */
struct list_head link;
- /** @lr.lock: preemption fences lock */
- spinlock_t lock;
} lr;
/** @ops: submission backend exec queue operations */
@@ -139,10 +140,6 @@ struct xe_exec_queue {
* Protected by @vm's resv. Unused if @vm == NULL.
*/
u64 tlb_flush_seqno;
- /** @old_run_ticks: prior hw engine class run time in ticks for this exec queue */
- u64 old_run_ticks;
- /** @run_ticks: hw engine class run time in ticks for this exec queue */
- u64 run_ticks;
/** @lrc: logical ring context for this exec queue */
struct xe_lrc *lrc[];
};
diff --git a/drivers/gpu/drm/xe/xe_gsc.c b/drivers/gpu/drm/xe/xe_gsc.c
index f8239a1..2a61265 100644
--- a/drivers/gpu/drm/xe/xe_gsc.c
+++ b/drivers/gpu/drm/xe/xe_gsc.c
@@ -260,7 +260,7 @@ static int gsc_upload_and_init(struct xe_gsc *gsc)
struct xe_tile *tile = gt_to_tile(gt);
int ret;
- if (XE_WA(gt, 14018094691)) {
+ if (XE_WA(tile->primary_gt, 14018094691)) {
ret = xe_force_wake_get(gt_to_fw(tile->primary_gt), XE_FORCEWAKE_ALL);
/*
@@ -278,7 +278,7 @@ static int gsc_upload_and_init(struct xe_gsc *gsc)
ret = gsc_upload(gsc);
- if (XE_WA(gt, 14018094691))
+ if (XE_WA(tile->primary_gt, 14018094691))
xe_force_wake_put(gt_to_fw(tile->primary_gt), XE_FORCEWAKE_ALL);
if (ret)
@@ -437,7 +437,7 @@ int xe_gsc_init(struct xe_gsc *gsc)
return ret;
}
-static void free_resources(struct drm_device *drm, void *arg)
+static void free_resources(void *arg)
{
struct xe_gsc *gsc = arg;
@@ -501,7 +501,7 @@ int xe_gsc_init_post_hwconfig(struct xe_gsc *gsc)
gsc->q = q;
gsc->wq = wq;
- err = drmm_add_action_or_reset(&xe->drm, free_resources, gsc);
+ err = devm_add_action_or_reset(xe->drm.dev, free_resources, gsc);
if (err)
return err;
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 31b2e64..b9bcbbe 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -11,6 +11,8 @@
#include <drm/xe_drm.h>
#include <generated/xe_wa_oob.h>
+#include <generated/xe_wa_oob.h>
+
#include "instructions/xe_gfxpipe_commands.h"
#include "instructions/xe_mi_commands.h"
#include "regs/xe_gt_regs.h"
@@ -95,6 +97,51 @@ void xe_gt_sanitize(struct xe_gt *gt)
gt->uc.guc.submission_state.enabled = false;
}
+static void xe_gt_enable_host_l2_vram(struct xe_gt *gt)
+{
+ u32 reg;
+ int err;
+
+ if (!XE_WA(gt, 16023588340))
+ return;
+
+ err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
+ if (WARN_ON(err))
+ return;
+
+ if (!xe_gt_is_media_type(gt)) {
+ xe_mmio_write32(gt, SCRATCH1LPFC, EN_L3_RW_CCS_CACHE_FLUSH);
+ reg = xe_mmio_read32(gt, XE2_GAMREQSTRM_CTRL);
+ reg |= CG_DIS_CNTLBUS;
+ xe_mmio_write32(gt, XE2_GAMREQSTRM_CTRL, reg);
+ }
+
+ xe_gt_mcr_multicast_write(gt, XEHPC_L3CLOS_MASK(3), 0x3);
+ xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
+}
+
+static void xe_gt_disable_host_l2_vram(struct xe_gt *gt)
+{
+ u32 reg;
+ int err;
+
+ if (!XE_WA(gt, 16023588340))
+ return;
+
+ if (xe_gt_is_media_type(gt))
+ return;
+
+ err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
+ if (WARN_ON(err))
+ return;
+
+ reg = xe_mmio_read32(gt, XE2_GAMREQSTRM_CTRL);
+ reg &= ~CG_DIS_CNTLBUS;
+ xe_mmio_write32(gt, XE2_GAMREQSTRM_CTRL, reg);
+
+ xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
+}
+
/**
* xe_gt_remove() - Clean up the GT structures before driver removal
* @gt: the GT object
@@ -111,6 +158,8 @@ void xe_gt_remove(struct xe_gt *gt)
for (i = 0; i < XE_ENGINE_CLASS_MAX; ++i)
xe_hw_fence_irq_finish(>->fence_irq[i]);
+
+ xe_gt_disable_host_l2_vram(gt);
}
static void gt_reset_worker(struct work_struct *w);
@@ -339,6 +388,7 @@ int xe_gt_init_early(struct xe_gt *gt)
xe_force_wake_init_gt(gt, gt_to_fw(gt));
xe_pcode_init(gt);
+ spin_lock_init(>->global_invl_lock);
return 0;
}
@@ -508,6 +558,7 @@ int xe_gt_init_hwconfig(struct xe_gt *gt)
xe_gt_mcr_init_early(gt);
xe_pat_init(gt);
+ xe_gt_enable_host_l2_vram(gt);
err = xe_uc_init(>->uc);
if (err)
@@ -643,6 +694,8 @@ static int do_gt_restart(struct xe_gt *gt)
xe_pat_init(gt);
+ xe_gt_enable_host_l2_vram(gt);
+
xe_gt_mcr_set_implicit_defaults(gt);
xe_reg_sr_apply_mmio(>->reg_sr, gt);
@@ -796,6 +849,8 @@ int xe_gt_suspend(struct xe_gt *gt)
xe_gt_idle_disable_pg(gt);
+ xe_gt_disable_host_l2_vram(gt);
+
XE_WARN_ON(xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL));
xe_gt_dbg(gt, "suspended\n");
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 9292d54..b2a7fa5 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -382,6 +382,18 @@ static void pf_queue_work_func(struct work_struct *w)
static void acc_queue_work_func(struct work_struct *w);
+static void pagefault_fini(void *arg)
+{
+ struct xe_gt *gt = arg;
+ struct xe_device *xe = gt_to_xe(gt);
+
+ if (!xe->info.has_usm)
+ return;
+
+ destroy_workqueue(gt->usm.acc_wq);
+ destroy_workqueue(gt->usm.pf_wq);
+}
+
int xe_gt_pagefault_init(struct xe_gt *gt)
{
struct xe_device *xe = gt_to_xe(gt);
@@ -409,10 +421,12 @@ int xe_gt_pagefault_init(struct xe_gt *gt)
gt->usm.acc_wq = alloc_workqueue("xe_gt_access_counter_work_queue",
WQ_UNBOUND | WQ_HIGHPRI,
NUM_ACC_QUEUE);
- if (!gt->usm.acc_wq)
+ if (!gt->usm.acc_wq) {
+ destroy_workqueue(gt->usm.pf_wq);
return -ENOMEM;
+ }
- return 0;
+ return devm_add_action_or_reset(xe->drm.dev, pagefault_fini, gt);
}
void xe_gt_pagefault_reset(struct xe_gt *gt)
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
index 4699b78..b6f0a72 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -1927,6 +1927,7 @@ static int pf_validate_vf_config(struct xe_gt *gt, unsigned int vfid)
{
struct xe_gt *primary_gt = gt_to_tile(gt)->primary_gt;
struct xe_device *xe = gt_to_xe(gt);
+ bool is_primary = !xe_gt_is_media_type(gt);
bool valid_ggtt, valid_ctxs, valid_dbs;
bool valid_any, valid_all;
@@ -1935,13 +1936,17 @@ static int pf_validate_vf_config(struct xe_gt *gt, unsigned int vfid)
valid_dbs = pf_get_vf_config_dbs(gt, vfid);
/* note that GuC doorbells are optional */
- valid_any = valid_ggtt || valid_ctxs || valid_dbs;
- valid_all = valid_ggtt && valid_ctxs;
+ valid_any = valid_ctxs || valid_dbs;
+ valid_all = valid_ctxs;
+
+ /* and GGTT/LMEM is configured on primary GT only */
+ valid_all = valid_all && valid_ggtt;
+ valid_any = valid_any || (valid_ggtt && is_primary);
if (IS_DGFX(xe)) {
bool valid_lmem = pf_get_vf_config_ggtt(primary_gt, vfid);
- valid_any = valid_any || valid_lmem;
+ valid_any = valid_any || (valid_lmem && is_primary);
valid_all = valid_all && valid_lmem;
}
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
index 41e46a0..8892d6c 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
@@ -850,7 +850,7 @@ static struct vf_runtime_reg *vf_lookup_reg(struct xe_gt *gt, u32 addr)
xe_gt_assert(gt, IS_SRIOV_VF(gt_to_xe(gt)));
- return bsearch(&key, runtime->regs, runtime->regs_size, sizeof(key),
+ return bsearch(&key, runtime->regs, runtime->num_regs, sizeof(key),
vf_runtime_reg_cmp);
}
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index d935997..481d83d 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -13,10 +13,13 @@
#include "xe_guc.h"
#include "xe_guc_ct.h"
#include "xe_mmio.h"
+#include "xe_pm.h"
#include "xe_sriov.h"
#include "xe_trace.h"
#include "regs/xe_guc_regs.h"
+#define FENCE_STACK_BIT DMA_FENCE_FLAG_USER_BITS
+
/*
* TLB inval depends on pending commands in the CT queue and then the real
* invalidation time. Double up the time to process full CT queue
@@ -33,6 +36,24 @@ static long tlb_timeout_jiffies(struct xe_gt *gt)
return hw_tlb_timeout + 2 * delay;
}
+static void
+__invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence)
+{
+ bool stack = test_bit(FENCE_STACK_BIT, &fence->base.flags);
+
+ trace_xe_gt_tlb_invalidation_fence_signal(xe, fence);
+ xe_gt_tlb_invalidation_fence_fini(fence);
+ dma_fence_signal(&fence->base);
+ if (!stack)
+ dma_fence_put(&fence->base);
+}
+
+static void
+invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence)
+{
+ list_del(&fence->link);
+ __invalidation_fence_signal(xe, fence);
+}
static void xe_gt_tlb_fence_timeout(struct work_struct *work)
{
@@ -54,10 +75,8 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work)
xe_gt_err(gt, "TLB invalidation fence timeout, seqno=%d recv=%d",
fence->seqno, gt->tlb_invalidation.seqno_recv);
- list_del(&fence->link);
fence->base.error = -ETIME;
- dma_fence_signal(&fence->base);
- dma_fence_put(&fence->base);
+ invalidation_fence_signal(xe, fence);
}
if (!list_empty(>->tlb_invalidation.pending_fences))
queue_delayed_work(system_wq,
@@ -87,21 +106,6 @@ int xe_gt_tlb_invalidation_init(struct xe_gt *gt)
return 0;
}
-static void
-__invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence)
-{
- trace_xe_gt_tlb_invalidation_fence_signal(xe, fence);
- dma_fence_signal(&fence->base);
- dma_fence_put(&fence->base);
-}
-
-static void
-invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence)
-{
- list_del(&fence->link);
- __invalidation_fence_signal(xe, fence);
-}
-
/**
* xe_gt_tlb_invalidation_reset - Initialize GT TLB invalidation reset
* @gt: graphics tile
@@ -111,7 +115,6 @@ invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fe
void xe_gt_tlb_invalidation_reset(struct xe_gt *gt)
{
struct xe_gt_tlb_invalidation_fence *fence, *next;
- struct xe_guc *guc = >->uc.guc;
int pending_seqno;
/*
@@ -134,7 +137,6 @@ void xe_gt_tlb_invalidation_reset(struct xe_gt *gt)
else
pending_seqno = gt->tlb_invalidation.seqno - 1;
WRITE_ONCE(gt->tlb_invalidation.seqno_recv, pending_seqno);
- wake_up_all(&guc->ct.wq);
list_for_each_entry_safe(fence, next,
>->tlb_invalidation.pending_fences, link)
@@ -165,6 +167,8 @@ static int send_tlb_invalidation(struct xe_guc *guc,
int seqno;
int ret;
+ xe_gt_assert(gt, fence);
+
/*
* XXX: The seqno algorithm relies on TLB invalidation being processed
* in order which they currently are, if that changes the algorithm will
@@ -173,10 +177,8 @@ static int send_tlb_invalidation(struct xe_guc *guc,
mutex_lock(&guc->ct.lock);
seqno = gt->tlb_invalidation.seqno;
- if (fence) {
- fence->seqno = seqno;
- trace_xe_gt_tlb_invalidation_fence_send(xe, fence);
- }
+ fence->seqno = seqno;
+ trace_xe_gt_tlb_invalidation_fence_send(xe, fence);
action[1] = seqno;
ret = xe_guc_ct_send_locked(&guc->ct, action, len,
G2H_LEN_DW_TLB_INVALIDATE, 1);
@@ -209,7 +211,6 @@ static int send_tlb_invalidation(struct xe_guc *guc,
TLB_INVALIDATION_SEQNO_MAX;
if (!gt->tlb_invalidation.seqno)
gt->tlb_invalidation.seqno = 1;
- ret = seqno;
}
mutex_unlock(&guc->ct.lock);
@@ -223,14 +224,16 @@ static int send_tlb_invalidation(struct xe_guc *guc,
/**
* xe_gt_tlb_invalidation_guc - Issue a TLB invalidation on this GT for the GuC
* @gt: graphics tile
+ * @fence: invalidation fence which will be signal on TLB invalidation
+ * completion
*
* Issue a TLB invalidation for the GuC. Completion of TLB is asynchronous and
- * caller can use seqno + xe_gt_tlb_invalidation_wait to wait for completion.
+ * caller can use the invalidation fence to wait for completion.
*
- * Return: Seqno which can be passed to xe_gt_tlb_invalidation_wait on success,
- * negative error code on error.
+ * Return: 0 on success, negative error code on error
*/
-static int xe_gt_tlb_invalidation_guc(struct xe_gt *gt)
+static int xe_gt_tlb_invalidation_guc(struct xe_gt *gt,
+ struct xe_gt_tlb_invalidation_fence *fence)
{
u32 action[] = {
XE_GUC_ACTION_TLB_INVALIDATION,
@@ -238,7 +241,7 @@ static int xe_gt_tlb_invalidation_guc(struct xe_gt *gt)
MAKE_INVAL_OP(XE_GUC_TLB_INVAL_GUC),
};
- return send_tlb_invalidation(>->uc.guc, NULL, action,
+ return send_tlb_invalidation(>->uc.guc, fence, action,
ARRAY_SIZE(action));
}
@@ -257,13 +260,17 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt)
if (xe_guc_ct_enabled(>->uc.guc.ct) &&
gt->uc.guc.submission_state.enabled) {
- int seqno;
+ struct xe_gt_tlb_invalidation_fence fence;
+ int ret;
- seqno = xe_gt_tlb_invalidation_guc(gt);
- if (seqno <= 0)
- return seqno;
+ xe_gt_tlb_invalidation_fence_init(gt, &fence, true);
+ ret = xe_gt_tlb_invalidation_guc(gt, &fence);
+ if (ret < 0) {
+ xe_gt_tlb_invalidation_fence_fini(&fence);
+ return ret;
+ }
- xe_gt_tlb_invalidation_wait(gt, seqno);
+ xe_gt_tlb_invalidation_fence_wait(&fence);
} else if (xe_device_uc_enabled(xe) && !xe_device_wedged(xe)) {
if (IS_SRIOV_VF(xe))
return 0;
@@ -290,18 +297,16 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt)
*
* @gt: graphics tile
* @fence: invalidation fence which will be signal on TLB invalidation
- * completion, can be NULL
+ * completion
* @start: start address
* @end: end address
* @asid: address space id
*
* Issue a range based TLB invalidation if supported, if not fallback to a full
- * TLB invalidation. Completion of TLB is asynchronous and caller can either use
- * the invalidation fence or seqno + xe_gt_tlb_invalidation_wait to wait for
- * completion.
+ * TLB invalidation. Completion of TLB is asynchronous and caller can use
+ * the invalidation fence to wait for completion.
*
- * Return: Seqno which can be passed to xe_gt_tlb_invalidation_wait on success,
- * negative error code on error.
+ * Return: Negative error code on error, 0 on success
*/
int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
struct xe_gt_tlb_invalidation_fence *fence,
@@ -312,11 +317,11 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
u32 action[MAX_TLB_INVALIDATION_LEN];
int len = 0;
+ xe_gt_assert(gt, fence);
+
/* Execlists not supported */
if (gt_to_xe(gt)->info.force_execlist) {
- if (fence)
- __invalidation_fence_signal(xe, fence);
-
+ __invalidation_fence_signal(xe, fence);
return 0;
}
@@ -382,12 +387,10 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
* @vma: VMA to invalidate
*
* Issue a range based TLB invalidation if supported, if not fallback to a full
- * TLB invalidation. Completion of TLB is asynchronous and caller can either use
- * the invalidation fence or seqno + xe_gt_tlb_invalidation_wait to wait for
- * completion.
+ * TLB invalidation. Completion of TLB is asynchronous and caller can use
+ * the invalidation fence to wait for completion.
*
- * Return: Seqno which can be passed to xe_gt_tlb_invalidation_wait on success,
- * negative error code on error.
+ * Return: Negative error code on error, 0 on success
*/
int xe_gt_tlb_invalidation_vma(struct xe_gt *gt,
struct xe_gt_tlb_invalidation_fence *fence,
@@ -401,43 +404,6 @@ int xe_gt_tlb_invalidation_vma(struct xe_gt *gt,
}
/**
- * xe_gt_tlb_invalidation_wait - Wait for TLB to complete
- * @gt: graphics tile
- * @seqno: seqno to wait which was returned from xe_gt_tlb_invalidation
- *
- * Wait for tlb_timeout_jiffies() for a TLB invalidation to complete.
- *
- * Return: 0 on success, -ETIME on TLB invalidation timeout
- */
-int xe_gt_tlb_invalidation_wait(struct xe_gt *gt, int seqno)
-{
- struct xe_guc *guc = >->uc.guc;
- int ret;
-
- /* Execlists not supported */
- if (gt_to_xe(gt)->info.force_execlist)
- return 0;
-
- /*
- * XXX: See above, this algorithm only works if seqno are always in
- * order
- */
- ret = wait_event_timeout(guc->ct.wq,
- tlb_invalidation_seqno_past(gt, seqno),
- tlb_timeout_jiffies(gt));
- if (!ret) {
- struct drm_printer p = xe_gt_err_printer(gt);
-
- xe_gt_err(gt, "TLB invalidation time'd out, seqno=%d, recv=%d\n",
- seqno, gt->tlb_invalidation.seqno_recv);
- xe_guc_ct_print(&guc->ct, &p, true);
- return -ETIME;
- }
-
- return 0;
-}
-
-/**
* xe_guc_tlb_invalidation_done_handler - TLB invalidation done handler
* @guc: guc
* @msg: message indicating TLB invalidation done
@@ -480,12 +446,7 @@ int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len)
return 0;
}
- /*
- * wake_up_all() and wait_event_timeout() already have the correct
- * barriers.
- */
WRITE_ONCE(gt->tlb_invalidation.seqno_recv, msg[0]);
- wake_up_all(&guc->ct.wq);
list_for_each_entry_safe(fence, next,
>->tlb_invalidation.pending_fences, link) {
@@ -508,3 +469,59 @@ int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len)
return 0;
}
+
+static const char *
+invalidation_fence_get_driver_name(struct dma_fence *dma_fence)
+{
+ return "xe";
+}
+
+static const char *
+invalidation_fence_get_timeline_name(struct dma_fence *dma_fence)
+{
+ return "invalidation_fence";
+}
+
+static const struct dma_fence_ops invalidation_fence_ops = {
+ .get_driver_name = invalidation_fence_get_driver_name,
+ .get_timeline_name = invalidation_fence_get_timeline_name,
+};
+
+/**
+ * xe_gt_tlb_invalidation_fence_init - Initialize TLB invalidation fence
+ * @gt: GT
+ * @fence: TLB invalidation fence to initialize
+ * @stack: fence is stack variable
+ *
+ * Initialize TLB invalidation fence for use. xe_gt_tlb_invalidation_fence_fini
+ * must be called if fence is not signaled.
+ */
+void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
+ struct xe_gt_tlb_invalidation_fence *fence,
+ bool stack)
+{
+ xe_pm_runtime_get_noresume(gt_to_xe(gt));
+
+ spin_lock_irq(>->tlb_invalidation.lock);
+ dma_fence_init(&fence->base, &invalidation_fence_ops,
+ >->tlb_invalidation.lock,
+ dma_fence_context_alloc(1), 1);
+ spin_unlock_irq(>->tlb_invalidation.lock);
+ INIT_LIST_HEAD(&fence->link);
+ if (stack)
+ set_bit(FENCE_STACK_BIT, &fence->base.flags);
+ else
+ dma_fence_get(&fence->base);
+ fence->gt = gt;
+}
+
+/**
+ * xe_gt_tlb_invalidation_fence_fini - Finalize TLB invalidation fence
+ * @fence: TLB invalidation fence to finalize
+ *
+ * Drop PM ref which fence took durinig init.
+ */
+void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence)
+{
+ xe_pm_runtime_put(gt_to_xe(fence->gt));
+}
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
index bf3bebd..a84065f 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
@@ -23,7 +23,17 @@ int xe_gt_tlb_invalidation_vma(struct xe_gt *gt,
int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
struct xe_gt_tlb_invalidation_fence *fence,
u64 start, u64 end, u32 asid);
-int xe_gt_tlb_invalidation_wait(struct xe_gt *gt, int seqno);
int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
+void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
+ struct xe_gt_tlb_invalidation_fence *fence,
+ bool stack);
+void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence);
+
+static inline void
+xe_gt_tlb_invalidation_fence_wait(struct xe_gt_tlb_invalidation_fence *fence)
+{
+ dma_fence_wait(&fence->base, false);
+}
+
#endif /* _XE_GT_TLB_INVALIDATION_ */
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h
index 934c828..de6e825 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h
@@ -8,6 +8,8 @@
#include <linux/dma-fence.h>
+struct xe_gt;
+
/**
* struct xe_gt_tlb_invalidation_fence - XE GT TLB invalidation fence
*
@@ -17,6 +19,8 @@
struct xe_gt_tlb_invalidation_fence {
/** @base: dma fence base */
struct dma_fence base;
+ /** @gt: GT which fence belong to */
+ struct xe_gt *gt;
/** @link: link into list of pending tlb fences */
struct list_head link;
/** @seqno: seqno of TLB invalidation to signal fence one */
diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
index 6b5e0b4..38a0d0e 100644
--- a/drivers/gpu/drm/xe/xe_gt_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_types.h
@@ -362,6 +362,12 @@ struct xe_gt {
*/
spinlock_t mcr_lock;
+ /**
+ * @global_invl_lock: protects the register for the duration
+ * of a global invalidation of l2 cache
+ */
+ spinlock_t global_invl_lock;
+
/** @wa_active: keep track of active workarounds */
struct {
/** @wa_active.gt: bitmap with active GT workarounds */
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 7d2e937..64afc90 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -327,6 +327,8 @@ static void xe_guc_ct_set_state(struct xe_guc_ct *ct,
xe_gt_assert(ct_to_gt(ct), ct->g2h_outstanding == 0 ||
state == XE_GUC_CT_STATE_STOPPED);
+ if (ct->g2h_outstanding)
+ xe_pm_runtime_put(ct_to_xe(ct));
ct->g2h_outstanding = 0;
ct->state = state;
@@ -495,10 +497,15 @@ static void h2g_reserve_space(struct xe_guc_ct *ct, u32 cmd_len)
static void __g2h_reserve_space(struct xe_guc_ct *ct, u32 g2h_len, u32 num_g2h)
{
xe_gt_assert(ct_to_gt(ct), g2h_len <= ct->ctbs.g2h.info.space);
+ xe_gt_assert(ct_to_gt(ct), (!g2h_len && !num_g2h) ||
+ (g2h_len && num_g2h));
if (g2h_len) {
lockdep_assert_held(&ct->fast_lock);
+ if (!ct->g2h_outstanding)
+ xe_pm_runtime_get_noresume(ct_to_xe(ct));
+
ct->ctbs.g2h.info.space -= g2h_len;
ct->g2h_outstanding += num_g2h;
}
@@ -511,7 +518,8 @@ static void __g2h_release_space(struct xe_guc_ct *ct, u32 g2h_len)
ct->ctbs.g2h.info.size - ct->ctbs.g2h.info.resv_space);
ct->ctbs.g2h.info.space += g2h_len;
- --ct->g2h_outstanding;
+ if (!--ct->g2h_outstanding)
+ xe_pm_runtime_put(ct_to_xe(ct));
}
static void g2h_release_space(struct xe_guc_ct *ct, u32 g2h_len)
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 8d7e7f4..77b0f0d 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -284,7 +284,7 @@ static void guc_submit_fini(struct drm_device *drm, void *arg)
free_submit_wq(guc);
}
-static void guc_submit_wedged_fini(struct drm_device *drm, void *arg)
+static void guc_submit_wedged_fini(void *arg)
{
struct xe_guc *guc = arg;
struct xe_exec_queue *q;
@@ -877,7 +877,7 @@ void xe_guc_submit_wedge(struct xe_guc *guc)
xe_gt_assert(guc_to_gt(guc), guc_to_xe(guc)->wedged.mode);
- err = drmm_add_action_or_reset(&guc_to_xe(guc)->drm,
+ err = devm_add_action_or_reset(guc_to_xe(guc)->drm.dev,
guc_submit_wedged_fini, guc);
if (err) {
drm_err(&xe->drm, "Failed to register xe_guc_submit clean-up on wedged.mode=2. Although device is wedged.\n");
@@ -1393,6 +1393,8 @@ static void guc_exec_queue_process_msg(struct xe_sched_msg *msg)
default:
XE_WARN_ON("Unknown message type");
}
+
+ xe_pm_runtime_put(guc_to_xe(exec_queue_to_guc(msg->private_data)));
}
static const struct drm_sched_backend_ops drm_sched_ops = {
@@ -1482,6 +1484,8 @@ static void guc_exec_queue_kill(struct xe_exec_queue *q)
static void guc_exec_queue_add_msg(struct xe_exec_queue *q, struct xe_sched_msg *msg,
u32 opcode)
{
+ xe_pm_runtime_get_noresume(guc_to_xe(exec_queue_to_guc(q)));
+
INIT_LIST_HEAD(&msg->link);
msg->opcode = opcode;
msg->private_data = q;
diff --git a/drivers/gpu/drm/xe/xe_hw_fence.c b/drivers/gpu/drm/xe/xe_hw_fence.c
index 45a9789..0b4f12b 100644
--- a/drivers/gpu/drm/xe/xe_hw_fence.c
+++ b/drivers/gpu/drm/xe/xe_hw_fence.c
@@ -148,20 +148,20 @@ static const char *xe_hw_fence_get_driver_name(struct dma_fence *dma_fence)
{
struct xe_hw_fence *fence = to_xe_hw_fence(dma_fence);
- return dev_name(gt_to_xe(fence->ctx->gt)->drm.dev);
+ return dev_name(fence->xe->drm.dev);
}
static const char *xe_hw_fence_get_timeline_name(struct dma_fence *dma_fence)
{
struct xe_hw_fence *fence = to_xe_hw_fence(dma_fence);
- return fence->ctx->name;
+ return fence->name;
}
static bool xe_hw_fence_signaled(struct dma_fence *dma_fence)
{
struct xe_hw_fence *fence = to_xe_hw_fence(dma_fence);
- struct xe_device *xe = gt_to_xe(fence->ctx->gt);
+ struct xe_device *xe = fence->xe;
u32 seqno = xe_map_rd(xe, &fence->seqno_map, 0, u32);
return dma_fence->error ||
@@ -253,7 +253,8 @@ void xe_hw_fence_init(struct dma_fence *fence, struct xe_hw_fence_ctx *ctx,
struct xe_hw_fence *hw_fence =
container_of(fence, typeof(*hw_fence), dma);
- hw_fence->ctx = ctx;
+ hw_fence->xe = gt_to_xe(ctx->gt);
+ snprintf(hw_fence->name, sizeof(hw_fence->name), "%s", ctx->name);
hw_fence->seqno_map = seqno_map;
INIT_LIST_HEAD(&hw_fence->irq_link);
diff --git a/drivers/gpu/drm/xe/xe_hw_fence_types.h b/drivers/gpu/drm/xe/xe_hw_fence_types.h
index b33c495..364a61f 100644
--- a/drivers/gpu/drm/xe/xe_hw_fence_types.h
+++ b/drivers/gpu/drm/xe/xe_hw_fence_types.h
@@ -12,6 +12,7 @@
#include <linux/list.h>
#include <linux/spinlock.h>
+struct xe_device;
struct xe_gt;
/**
@@ -61,8 +62,10 @@ struct xe_hw_fence_ctx {
struct xe_hw_fence {
/** @dma: base dma fence for hardware fence context */
struct dma_fence dma;
- /** @ctx: hardware fence context */
- struct xe_hw_fence_ctx *ctx;
+ /** @xe: Xe device for hw fence driver name */
+ struct xe_device *xe;
+ /** @name: name of hardware fence context */
+ char name[MAX_FENCE_NAME_LEN];
/** @seqno_map: I/O map for seqno */
struct iosys_map seqno_map;
/** @irq_link: Link in struct xe_hw_fence_irq.pending */
diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c
index 832ea81..1faeca7 100644
--- a/drivers/gpu/drm/xe/xe_hwmon.c
+++ b/drivers/gpu/drm/xe/xe_hwmon.c
@@ -450,7 +450,7 @@ static int xe_hwmon_pcode_write_i1(struct xe_gt *gt, u32 uval)
{
return xe_pcode_write(gt, PCODE_MBOX(PCODE_POWER_SETUP,
POWER_SETUP_SUBCOMMAND_WRITE_I1, 0),
- uval);
+ (uval & POWER_SETUP_I1_DATA_MASK));
}
static int xe_hwmon_power_curr_crit_read(struct xe_hwmon *hwmon, int channel,
diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
index f92faad..aa68cac 100644
--- a/drivers/gpu/drm/xe/xe_mmio.c
+++ b/drivers/gpu/drm/xe/xe_mmio.c
@@ -30,7 +30,8 @@ static void tiles_fini(void *arg)
int id;
for_each_tile(tile, xe, id)
- tile->mmio.regs = NULL;
+ if (tile != xe_device_get_root_tile(xe))
+ tile->mmio.regs = NULL;
}
int xe_mmio_probe_tiles(struct xe_device *xe)
@@ -91,9 +92,11 @@ int xe_mmio_probe_tiles(struct xe_device *xe)
static void mmio_fini(void *arg)
{
struct xe_device *xe = arg;
+ struct xe_tile *root_tile = xe_device_get_root_tile(xe);
pci_iounmap(to_pci_dev(xe->drm.dev), xe->mmio.regs);
xe->mmio.regs = NULL;
+ root_tile->mmio.regs = NULL;
}
int xe_mmio_init(struct xe_device *xe)
@@ -121,12 +124,29 @@ int xe_mmio_init(struct xe_device *xe)
return devm_add_action_or_reset(xe->drm.dev, mmio_fini, xe);
}
+static void mmio_flush_pending_writes(struct xe_gt *gt)
+{
+#define DUMMY_REG_OFFSET 0x130030
+ struct xe_tile *tile = gt_to_tile(gt);
+ int i;
+
+ if (tile->xe->info.platform != XE_LUNARLAKE)
+ return;
+
+ /* 4 dummy writes */
+ for (i = 0; i < 4; i++)
+ writel(0, tile->mmio.regs + DUMMY_REG_OFFSET);
+}
+
u8 xe_mmio_read8(struct xe_gt *gt, struct xe_reg reg)
{
struct xe_tile *tile = gt_to_tile(gt);
u32 addr = xe_mmio_adjusted_addr(gt, reg.addr);
u8 val;
+ /* Wa_15015404425 */
+ mmio_flush_pending_writes(gt);
+
val = readb((reg.ext ? tile->mmio_ext.regs : tile->mmio.regs) + addr);
trace_xe_reg_rw(gt, false, addr, val, sizeof(val));
@@ -139,6 +159,9 @@ u16 xe_mmio_read16(struct xe_gt *gt, struct xe_reg reg)
u32 addr = xe_mmio_adjusted_addr(gt, reg.addr);
u16 val;
+ /* Wa_15015404425 */
+ mmio_flush_pending_writes(gt);
+
val = readw((reg.ext ? tile->mmio_ext.regs : tile->mmio.regs) + addr);
trace_xe_reg_rw(gt, false, addr, val, sizeof(val));
@@ -160,6 +183,9 @@ u32 xe_mmio_read32(struct xe_gt *gt, struct xe_reg reg)
u32 addr = xe_mmio_adjusted_addr(gt, reg.addr);
u32 val;
+ /* Wa_15015404425 */
+ mmio_flush_pending_writes(gt);
+
if (!reg.vf && IS_SRIOV_VF(gt_to_xe(gt)))
val = xe_gt_sriov_vf_read32(gt, reg);
else
diff --git a/drivers/gpu/drm/xe/xe_observation.c b/drivers/gpu/drm/xe/xe_observation.c
index fcb584b..a78c92a 100644
--- a/drivers/gpu/drm/xe/xe_observation.c
+++ b/drivers/gpu/drm/xe/xe_observation.c
@@ -66,7 +66,6 @@ static struct ctl_table observation_ctl_table[] = {
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
- {}
};
/**
diff --git a/drivers/gpu/drm/xe/xe_pat.c b/drivers/gpu/drm/xe/xe_pat.c
index 4ee32ee..722278c 100644
--- a/drivers/gpu/drm/xe/xe_pat.c
+++ b/drivers/gpu/drm/xe/xe_pat.c
@@ -7,6 +7,8 @@
#include <drm/xe_drm.h>
+#include <generated/xe_wa_oob.h>
+
#include "regs/xe_reg_defs.h"
#include "xe_assert.h"
#include "xe_device.h"
@@ -15,6 +17,7 @@
#include "xe_gt_mcr.h"
#include "xe_mmio.h"
#include "xe_sriov.h"
+#include "xe_wa.h"
#define _PAT_ATS 0x47fc
#define _PAT_INDEX(index) _PICK_EVEN_2RANGES(index, 8, \
@@ -382,7 +385,13 @@ void xe_pat_init_early(struct xe_device *xe)
if (GRAPHICS_VER(xe) == 20) {
xe->pat.ops = &xe2_pat_ops;
xe->pat.table = xe2_pat_table;
- xe->pat.n_entries = ARRAY_SIZE(xe2_pat_table);
+
+ /* Wa_16023588340. XXX: Should use XE_WA */
+ if (GRAPHICS_VERx100(xe) == 2001)
+ xe->pat.n_entries = 28; /* Disable CLOS3 */
+ else
+ xe->pat.n_entries = ARRAY_SIZE(xe2_pat_table);
+
xe->pat.idx[XE_CACHE_NONE] = 3;
xe->pat.idx[XE_CACHE_WT] = 15;
xe->pat.idx[XE_CACHE_WB] = 2;
diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index de3b5df..9a3f618 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -91,13 +91,13 @@ int xe_pm_suspend(struct xe_device *xe)
for_each_gt(gt, xe, id)
xe_gt_suspend_prepare(gt);
+ xe_display_pm_suspend(xe, false);
+
/* FIXME: Super racey... */
err = xe_bo_evict_all(xe);
if (err)
goto err;
- xe_display_pm_suspend(xe, false);
-
for_each_gt(gt, xe, id) {
err = xe_gt_suspend(gt);
if (err) {
@@ -151,11 +151,11 @@ int xe_pm_resume(struct xe_device *xe)
xe_irq_resume(xe);
- xe_display_pm_resume(xe, false);
-
for_each_gt(gt, xe, id)
xe_gt_resume(gt);
+ xe_display_pm_resume(xe, false);
+
err = xe_bo_restore_user(xe);
if (err)
goto err;
@@ -363,10 +363,11 @@ int xe_pm_runtime_suspend(struct xe_device *xe)
mutex_unlock(&xe->mem_access.vram_userfault.lock);
if (xe->d3cold.allowed) {
+ xe_display_pm_suspend(xe, true);
+
err = xe_bo_evict_all(xe);
if (err)
goto out;
- xe_display_pm_suspend(xe, true);
}
for_each_gt(gt, xe, id) {
diff --git a/drivers/gpu/drm/xe/xe_preempt_fence.c b/drivers/gpu/drm/xe/xe_preempt_fence.c
index e8b8ae5..c453f45 100644
--- a/drivers/gpu/drm/xe/xe_preempt_fence.c
+++ b/drivers/gpu/drm/xe/xe_preempt_fence.c
@@ -128,8 +128,9 @@ xe_preempt_fence_arm(struct xe_preempt_fence *pfence, struct xe_exec_queue *q,
{
list_del_init(&pfence->link);
pfence->q = xe_exec_queue_get(q);
+ spin_lock_init(&pfence->lock);
dma_fence_init(&pfence->base, &preempt_fence_ops,
- &q->lr.lock, context, seqno);
+ &pfence->lock, context, seqno);
return &pfence->base;
}
diff --git a/drivers/gpu/drm/xe/xe_preempt_fence_types.h b/drivers/gpu/drm/xe/xe_preempt_fence_types.h
index b54b5c2..312c337 100644
--- a/drivers/gpu/drm/xe/xe_preempt_fence_types.h
+++ b/drivers/gpu/drm/xe/xe_preempt_fence_types.h
@@ -25,6 +25,8 @@ struct xe_preempt_fence {
struct xe_exec_queue *q;
/** @preempt_work: work struct which issues preemption */
struct work_struct preempt_work;
+ /** @lock: dma-fence fence lock */
+ spinlock_t lock;
/** @error: preempt fence is in error state */
int error;
};
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index ade9e7a..31a751a 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -1115,23 +1115,6 @@ struct invalidation_fence {
u32 asid;
};
-static const char *
-invalidation_fence_get_driver_name(struct dma_fence *dma_fence)
-{
- return "xe";
-}
-
-static const char *
-invalidation_fence_get_timeline_name(struct dma_fence *dma_fence)
-{
- return "invalidation_fence";
-}
-
-static const struct dma_fence_ops invalidation_fence_ops = {
- .get_driver_name = invalidation_fence_get_driver_name,
- .get_timeline_name = invalidation_fence_get_timeline_name,
-};
-
static void invalidation_fence_cb(struct dma_fence *fence,
struct dma_fence_cb *cb)
{
@@ -1170,15 +1153,8 @@ static int invalidation_fence_init(struct xe_gt *gt,
trace_xe_gt_tlb_invalidation_fence_create(gt_to_xe(gt), &ifence->base);
- spin_lock_irq(>->tlb_invalidation.lock);
- dma_fence_init(&ifence->base.base, &invalidation_fence_ops,
- >->tlb_invalidation.lock,
- dma_fence_context_alloc(1), 1);
- spin_unlock_irq(>->tlb_invalidation.lock);
+ xe_gt_tlb_invalidation_fence_init(gt, &ifence->base, false);
- INIT_LIST_HEAD(&ifence->base.link);
-
- dma_fence_get(&ifence->base.base); /* Ref for caller */
ifence->fence = fence;
ifence->gt = gt;
ifence->start = start;
diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
index 44d534e..9628f9d 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@@ -171,12 +171,13 @@ void xe_sched_job_destroy(struct kref *ref)
struct xe_sched_job *job =
container_of(ref, struct xe_sched_job, refcount);
struct xe_device *xe = job_to_xe(job);
+ struct xe_exec_queue *q = job->q;
xe_sched_job_free_fences(job);
- xe_exec_queue_put(job->q);
dma_fence_put(job->fence);
drm_sched_job_cleanup(&job->drm);
job_free(job);
+ xe_exec_queue_put(q);
xe_pm_runtime_put(xe);
}
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index c4e018a..e8d31e0 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -53,14 +53,18 @@ static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr,
u64 value)
{
struct xe_user_fence *ufence;
+ u64 __user *ptr = u64_to_user_ptr(addr);
+
+ if (!access_ok(ptr, sizeof(ptr)))
+ return ERR_PTR(-EFAULT);
ufence = kmalloc(sizeof(*ufence), GFP_KERNEL);
if (!ufence)
- return NULL;
+ return ERR_PTR(-ENOMEM);
ufence->xe = xe;
kref_init(&ufence->refcount);
- ufence->addr = u64_to_user_ptr(addr);
+ ufence->addr = ptr;
ufence->value = value;
ufence->mm = current->mm;
mmgrab(ufence->mm);
@@ -183,8 +187,8 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
} else {
sync->ufence = user_fence_create(xe, sync_in.addr,
sync_in.timeline_value);
- if (XE_IOCTL_DBG(xe, !sync->ufence))
- return -ENOMEM;
+ if (XE_IOCTL_DBG(xe, IS_ERR(sync->ufence)))
+ return PTR_ERR(sync->ufence);
}
break;
diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
index baba14f..01837f6 100644
--- a/drivers/gpu/drm/xe/xe_trace.h
+++ b/drivers/gpu/drm/xe/xe_trace.h
@@ -309,7 +309,7 @@ DECLARE_EVENT_CLASS(xe_hw_fence,
TP_ARGS(fence),
TP_STRUCT__entry(
- __string(dev, __dev_name_gt(fence->ctx->gt))
+ __string(dev, __dev_name_xe(fence->xe))
__field(u64, ctx)
__field(u32, seqno)
__field(struct xe_hw_fence *, fence)
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 5b166fa..50e8fc4 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1601,6 +1601,10 @@ static void vm_destroy_work_func(struct work_struct *w)
XE_WARN_ON(vm->pt_root[id]);
trace_xe_vm_free(vm);
+
+ if (vm->xef)
+ xe_file_put(vm->xef);
+
kfree(vm);
}
@@ -1916,7 +1920,7 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
}
args->vm_id = id;
- vm->xef = xef;
+ vm->xef = xe_file_get(xef);
/* Record BO memory for VM pagetable created against client */
for_each_tile(tile, xe, id)
@@ -3337,10 +3341,11 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
{
struct xe_device *xe = xe_vma_vm(vma)->xe;
struct xe_tile *tile;
- u32 tile_needs_invalidate = 0;
- int seqno[XE_MAX_TILES_PER_DEVICE];
+ struct xe_gt_tlb_invalidation_fence
+ fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
u8 id;
- int ret;
+ u32 fence_id = 0;
+ int ret = 0;
xe_assert(xe, !xe_vma_is_null(vma));
trace_xe_vma_invalidate(vma);
@@ -3365,29 +3370,43 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
for_each_tile(tile, xe, id) {
if (xe_pt_zap_ptes(tile, vma)) {
- tile_needs_invalidate |= BIT(id);
xe_device_wmb(xe);
- /*
- * FIXME: We potentially need to invalidate multiple
- * GTs within the tile
- */
- seqno[id] = xe_gt_tlb_invalidation_vma(tile->primary_gt, NULL, vma);
- if (seqno[id] < 0)
- return seqno[id];
+ xe_gt_tlb_invalidation_fence_init(tile->primary_gt,
+ &fence[fence_id],
+ true);
+
+ ret = xe_gt_tlb_invalidation_vma(tile->primary_gt,
+ &fence[fence_id], vma);
+ if (ret < 0) {
+ xe_gt_tlb_invalidation_fence_fini(&fence[fence_id]);
+ goto wait;
+ }
+ ++fence_id;
+
+ if (!tile->media_gt)
+ continue;
+
+ xe_gt_tlb_invalidation_fence_init(tile->media_gt,
+ &fence[fence_id],
+ true);
+
+ ret = xe_gt_tlb_invalidation_vma(tile->media_gt,
+ &fence[fence_id], vma);
+ if (ret < 0) {
+ xe_gt_tlb_invalidation_fence_fini(&fence[fence_id]);
+ goto wait;
+ }
+ ++fence_id;
}
}
- for_each_tile(tile, xe, id) {
- if (tile_needs_invalidate & BIT(id)) {
- ret = xe_gt_tlb_invalidation_wait(tile->primary_gt, seqno[id]);
- if (ret < 0)
- return ret;
- }
- }
+wait:
+ for (id = 0; id < fence_id; ++id)
+ xe_gt_tlb_invalidation_fence_wait(&fence[id]);
vma->tile_invalidated = vma->tile_mask;
- return 0;
+ return ret;
}
struct xe_vm_snapshot {
diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
index c7bf086..e648265d 100644
--- a/drivers/gpu/drm/xe/xe_wa.c
+++ b/drivers/gpu/drm/xe/xe_wa.c
@@ -486,6 +486,10 @@ static const struct xe_rtp_entry_sr engine_was[] = {
XE_RTP_RULES(GRAPHICS_VERSION(2004), FUNC(xe_rtp_match_first_render_or_compute)),
XE_RTP_ACTIONS(SET(TDL_TSL_CHICKEN, SLM_WMTP_RESTORE))
},
+ { XE_RTP_NAME("14021402888"),
+ XE_RTP_RULES(GRAPHICS_VERSION(2004), ENGINE_CLASS(RENDER)),
+ XE_RTP_ACTIONS(SET(HALF_SLICE_CHICKEN7, CLEAR_OPTIMIZATION_DISABLE))
+ },
/* Xe2_HPG */
@@ -538,6 +542,20 @@ static const struct xe_rtp_entry_sr engine_was[] = {
XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)),
XE_RTP_ACTIONS(SET(HALF_SLICE_CHICKEN7, CLEAR_OPTIMIZATION_DISABLE))
},
+ { XE_RTP_NAME("14021821874"),
+ XE_RTP_RULES(GRAPHICS_VERSION(2001), FUNC(xe_rtp_match_first_render_or_compute)),
+ XE_RTP_ACTIONS(SET(TDL_TSL_CHICKEN, STK_ID_RESTRICT))
+ },
+
+ /* Xe2_LPM */
+
+ { XE_RTP_NAME("16021639441"),
+ XE_RTP_RULES(MEDIA_VERSION(2000)),
+ XE_RTP_ACTIONS(SET(CSFE_CHICKEN1(0),
+ GHWSP_CSB_REPORT_DIS |
+ PPHWSP_CSB_AND_TIMESTAMP_REPORT_DIS,
+ XE_RTP_ACTION_FLAG(ENGINE_BASE)))
+ },
/* Xe2_HPM */
diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index 26066be..08f73368 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -29,3 +29,4 @@
13011645652 GRAPHICS_VERSION(2004)
22019338487 MEDIA_VERSION(2000)
GRAPHICS_VERSION(2001)
+16023588340 GRAPHICS_VERSION(2001)
diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_hid.c b/drivers/hid/amd-sfh-hid/amd_sfh_hid.c
index 705b523..81f3024 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_hid.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_hid.c
@@ -171,11 +171,13 @@ int amdtp_hid_probe(u32 cur_hid_dev, struct amdtp_cl_data *cli_data)
void amdtp_hid_remove(struct amdtp_cl_data *cli_data)
{
int i;
+ struct amdtp_hid_data *hid_data;
for (i = 0; i < cli_data->num_hid_devices; ++i) {
if (cli_data->hid_sensor_hubs[i]) {
- kfree(cli_data->hid_sensor_hubs[i]->driver_data);
+ hid_data = cli_data->hid_sensor_hubs[i]->driver_data;
hid_destroy_device(cli_data->hid_sensor_hubs[i]);
+ kfree(hid_data);
cli_data->hid_sensor_hubs[i] = NULL;
}
}
diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index 37e6d25..a282388 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -1249,6 +1249,9 @@ static const struct hid_device_id asus_devices[] = {
USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY),
QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD },
{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
+ USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X),
+ QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD),
QUIRK_ROG_CLAYMORE_II_KEYBOARD },
{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
diff --git a/drivers/hid/hid-cougar.c b/drivers/hid/hid-cougar.c
index cb8bd8a..0fa785f 100644
--- a/drivers/hid/hid-cougar.c
+++ b/drivers/hid/hid-cougar.c
@@ -106,7 +106,7 @@ static void cougar_fix_g6_mapping(void)
static __u8 *cougar_report_fixup(struct hid_device *hdev, __u8 *rdesc,
unsigned int *rsize)
{
- if (rdesc[2] == 0x09 && rdesc[3] == 0x02 &&
+ if (*rsize >= 117 && rdesc[2] == 0x09 && rdesc[3] == 0x02 &&
(rdesc[115] | rdesc[116] << 8) >= HID_MAX_USAGES) {
hid_info(hdev,
"usage count exceeds max: fixing up report descriptor\n");
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 72d56ee..781c5aa 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -210,6 +210,7 @@
#define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_KEYBOARD3 0x1a30
#define USB_DEVICE_ID_ASUSTEK_ROG_Z13_LIGHTBAR 0x18c6
#define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY 0x1abe
+#define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X 0x1b4c
#define USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD 0x196b
#define USB_DEVICE_ID_ASUSTEK_FX503VD_KEYBOARD 0x1869
@@ -520,6 +521,8 @@
#define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_E100 0xe100
#define I2C_VENDOR_ID_GOODIX 0x27c6
+#define I2C_DEVICE_ID_GOODIX_01E8 0x01e8
+#define I2C_DEVICE_ID_GOODIX_01E9 0x01e9
#define I2C_DEVICE_ID_GOODIX_01F0 0x01f0
#define USB_VENDOR_ID_GOODTOUCH 0x1aad
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 56fc788..99812c0 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -1441,6 +1441,30 @@ static int mt_event(struct hid_device *hid, struct hid_field *field,
return 0;
}
+static __u8 *mt_report_fixup(struct hid_device *hdev, __u8 *rdesc,
+ unsigned int *size)
+{
+ if (hdev->vendor == I2C_VENDOR_ID_GOODIX &&
+ (hdev->product == I2C_DEVICE_ID_GOODIX_01E8 ||
+ hdev->product == I2C_DEVICE_ID_GOODIX_01E9)) {
+ if (rdesc[607] == 0x15) {
+ rdesc[607] = 0x25;
+ dev_info(
+ &hdev->dev,
+ "GT7868Q report descriptor fixup is applied.\n");
+ } else {
+ dev_info(
+ &hdev->dev,
+ "The byte is not expected for fixing the report descriptor. \
+It's possible that the touchpad firmware is not suitable for applying the fix. \
+got: %x\n",
+ rdesc[607]);
+ }
+ }
+
+ return rdesc;
+}
+
static void mt_report(struct hid_device *hid, struct hid_report *report)
{
struct mt_device *td = hid_get_drvdata(hid);
@@ -2035,6 +2059,14 @@ static const struct hid_device_id mt_devices[] = {
MT_BT_DEVICE(USB_VENDOR_ID_FRUCTEL,
USB_DEVICE_ID_GAMETEL_MT_MODE) },
+ /* Goodix GT7868Q devices */
+ { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU,
+ HID_DEVICE(BUS_I2C, HID_GROUP_ANY, I2C_VENDOR_ID_GOODIX,
+ I2C_DEVICE_ID_GOODIX_01E8) },
+ { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU,
+ HID_DEVICE(BUS_I2C, HID_GROUP_ANY, I2C_VENDOR_ID_GOODIX,
+ I2C_DEVICE_ID_GOODIX_01E8) },
+
/* GoodTouch panels */
{ .driver_data = MT_CLS_NSMU,
MT_USB_DEVICE(USB_VENDOR_ID_GOODTOUCH,
@@ -2270,6 +2302,7 @@ static struct hid_driver mt_driver = {
.feature_mapping = mt_feature_mapping,
.usage_table = mt_grabbed_usages,
.event = mt_event,
+ .report_fixup = mt_report_fixup,
.report = mt_report,
.suspend = pm_ptr(mt_suspend),
.reset_resume = pm_ptr(mt_reset_resume),
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 1f45649..2541fa2 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -1878,12 +1878,14 @@ static void wacom_map_usage(struct input_dev *input, struct hid_usage *usage,
int fmax = field->logical_maximum;
unsigned int equivalent_usage = wacom_equivalent_usage(usage->hid);
int resolution_code = code;
- int resolution = hidinput_calc_abs_res(field, resolution_code);
+ int resolution;
if (equivalent_usage == HID_DG_TWIST) {
resolution_code = ABS_RZ;
}
+ resolution = hidinput_calc_abs_res(field, resolution_code);
+
if (equivalent_usage == HID_GD_X) {
fmin += features->offset_left;
fmax -= features->offset_right;
diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c
index 6bb8d7b..ee396f2 100644
--- a/drivers/hwmon/asus-ec-sensors.c
+++ b/drivers/hwmon/asus-ec-sensors.c
@@ -420,7 +420,7 @@ static const struct ec_board_info board_info_strix_b550_i_gaming = {
static const struct ec_board_info board_info_strix_x570_e_gaming = {
.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
- SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM |
+ SENSOR_TEMP_T_SENSOR |
SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU |
SENSOR_IN_CPU_CORE,
.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
diff --git a/drivers/hwmon/pt5161l.c b/drivers/hwmon/pt5161l.c
index b0d58a2..a9f0b23 100644
--- a/drivers/hwmon/pt5161l.c
+++ b/drivers/hwmon/pt5161l.c
@@ -427,7 +427,7 @@ static int pt5161l_read(struct device *dev, enum hwmon_sensor_types type,
struct pt5161l_data *data = dev_get_drvdata(dev);
int ret;
u8 buf[8];
- long adc_code;
+ u32 adc_code;
switch (attr) {
case hwmon_temp_input:
@@ -449,7 +449,7 @@ static int pt5161l_read(struct device *dev, enum hwmon_sensor_types type,
adc_code = buf[3] << 24 | buf[2] << 16 | buf[1] << 8 | buf[0];
if (adc_code == 0 || adc_code >= 0x3ff) {
- dev_dbg(dev, "Invalid adc_code %lx\n", adc_code);
+ dev_dbg(dev, "Invalid adc_code %x\n", adc_code);
return -EIO;
}
diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c
index 365e37b..06e836e 100644
--- a/drivers/i2c/busses/i2c-qcom-geni.c
+++ b/drivers/i2c/busses/i2c-qcom-geni.c
@@ -986,8 +986,10 @@ static int __maybe_unused geni_i2c_runtime_resume(struct device *dev)
return ret;
ret = clk_prepare_enable(gi2c->core_clk);
- if (ret)
+ if (ret) {
+ geni_icc_disable(&gi2c->se);
return ret;
+ }
ret = geni_se_resources_on(&gi2c->se);
if (ret) {
diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c
index 85b31ed..1df5b42 100644
--- a/drivers/i2c/busses/i2c-tegra.c
+++ b/drivers/i2c/busses/i2c-tegra.c
@@ -1802,9 +1802,9 @@ static int tegra_i2c_probe(struct platform_device *pdev)
* domain.
*
* VI I2C device shouldn't be marked as IRQ-safe because VI I2C won't
- * be used for atomic transfers.
+ * be used for atomic transfers. ACPI device is not IRQ safe also.
*/
- if (!IS_VI(i2c_dev))
+ if (!IS_VI(i2c_dev) && !has_acpi_companion(i2c_dev->dev))
pm_runtime_irq_safe(i2c_dev->dev);
pm_runtime_enable(i2c_dev->dev);
diff --git a/drivers/input/joystick/adc-joystick.c b/drivers/input/joystick/adc-joystick.c
index 5f46a71..de1fa4c 100644
--- a/drivers/input/joystick/adc-joystick.c
+++ b/drivers/input/joystick/adc-joystick.c
@@ -182,8 +182,11 @@ static int adc_joystick_set_axes(struct device *dev, struct adc_joystick *joy)
swap(range[0], range[1]);
}
- fwnode_property_read_u32(child, "abs-fuzz", &fuzz);
- fwnode_property_read_u32(child, "abs-flat", &flat);
+ if (fwnode_property_read_u32(child, "abs-fuzz", &fuzz))
+ fuzz = 0;
+
+ if (fwnode_property_read_u32(child, "abs-flat", &flat))
+ flat = 0;
input_set_abs_params(joy->input, axes[i].code,
range[0], range[1], fuzz, flat);
diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
index d23f322..445856c 100644
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@@ -417,6 +417,20 @@ static int uinput_validate_absinfo(struct input_dev *dev, unsigned int code,
return -EINVAL;
}
+ /*
+ * Limit number of contacts to a reasonable value (100). This
+ * ensures that we need less than 2 pages for struct input_mt
+ * (we are not using in-kernel slot assignment so not going to
+ * allocate memory for the "red" table), and we should have no
+ * trouble getting this much memory.
+ */
+ if (code == ABS_MT_SLOT && max > 99) {
+ printk(KERN_DEBUG
+ "%s: unreasonably large number of slots requested: %d\n",
+ UINPUT_NAME, max);
+ return -EINVAL;
+ }
+
return 0;
}
diff --git a/drivers/input/mouse/cypress_ps2.c b/drivers/input/mouse/cypress_ps2.c
index b3c34eb..9446657 100644
--- a/drivers/input/mouse/cypress_ps2.c
+++ b/drivers/input/mouse/cypress_ps2.c
@@ -91,48 +91,6 @@ static int cypress_ps2_ext_cmd(struct psmouse *psmouse, u8 prefix, u8 nibble)
return rc;
}
-static int cypress_ps2_read_cmd_status(struct psmouse *psmouse,
- u8 cmd, u8 *param)
-{
- struct ps2dev *ps2dev = &psmouse->ps2dev;
- enum psmouse_state old_state;
- int pktsize;
- int rc;
-
- ps2_begin_command(ps2dev);
-
- old_state = psmouse->state;
- psmouse->state = PSMOUSE_CMD_MODE;
- psmouse->pktcnt = 0;
-
- pktsize = (cmd == CYTP_CMD_READ_TP_METRICS) ? 8 : 3;
- memset(param, 0, pktsize);
-
- rc = cypress_ps2_sendbyte(psmouse, PSMOUSE_CMD_GETINFO & 0xff);
- if (rc)
- goto out;
-
- if (!wait_event_timeout(ps2dev->wait,
- psmouse->pktcnt >= pktsize,
- msecs_to_jiffies(CYTP_CMD_TIMEOUT))) {
- rc = -ETIMEDOUT;
- goto out;
- }
-
- memcpy(param, psmouse->packet, pktsize);
-
- psmouse_dbg(psmouse, "Command 0x%02x response data (0x): %*ph\n",
- cmd, pktsize, param);
-
-out:
- psmouse->state = old_state;
- psmouse->pktcnt = 0;
-
- ps2_end_command(ps2dev);
-
- return rc;
-}
-
static bool cypress_verify_cmd_state(struct psmouse *psmouse, u8 cmd, u8* param)
{
bool rate_match = false;
@@ -166,6 +124,8 @@ static bool cypress_verify_cmd_state(struct psmouse *psmouse, u8 cmd, u8* param)
static int cypress_send_ext_cmd(struct psmouse *psmouse, u8 cmd, u8 *param)
{
u8 cmd_prefix = PSMOUSE_CMD_SETRES & 0xff;
+ unsigned int resp_size = cmd == CYTP_CMD_READ_TP_METRICS ? 8 : 3;
+ unsigned int ps2_cmd = (PSMOUSE_CMD_GETINFO & 0xff) | (resp_size << 8);
int tries = CYTP_PS2_CMD_TRIES;
int error;
@@ -179,10 +139,18 @@ static int cypress_send_ext_cmd(struct psmouse *psmouse, u8 cmd, u8 *param)
cypress_ps2_ext_cmd(psmouse, cmd_prefix, DECODE_CMD_BB(cmd));
cypress_ps2_ext_cmd(psmouse, cmd_prefix, DECODE_CMD_AA(cmd));
- error = cypress_ps2_read_cmd_status(psmouse, cmd, param);
- if (!error && cypress_verify_cmd_state(psmouse, cmd, param))
- return 0;
+ error = ps2_command(&psmouse->ps2dev, param, ps2_cmd);
+ if (error) {
+ psmouse_dbg(psmouse, "Command 0x%02x failed: %d\n",
+ cmd, error);
+ } else {
+ psmouse_dbg(psmouse,
+ "Command 0x%02x response data (0x): %*ph\n",
+ cmd, resp_size, param);
+ if (cypress_verify_cmd_state(psmouse, cmd, param))
+ return 0;
+ }
} while (--tries > 0);
return -EIO;
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 38191c3..380aa16 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -189,6 +189,7 @@ static const char * const smbus_pnp_ids[] = {
"LEN2054", /* E480 */
"LEN2055", /* E580 */
"LEN2068", /* T14 Gen 1 */
+ "SYN3015", /* HP EliteBook 840 G2 */
"SYN3052", /* HP EliteBook 840 G4 */
"SYN3221", /* HP 15-ay000 */
"SYN323d", /* HP Spectre X360 13-w013dx */
diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index 5b50475..bad238f 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -83,6 +83,7 @@ static inline void i8042_write_command(int val)
#define SERIO_QUIRK_KBDRESET BIT(12)
#define SERIO_QUIRK_DRITEK BIT(13)
#define SERIO_QUIRK_NOPNP BIT(14)
+#define SERIO_QUIRK_FORCENORESTORE BIT(15)
/* Quirk table for different mainboards. Options similar or identical to i8042
* module parameters.
@@ -627,6 +628,15 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
.driver_data = (void *)(SERIO_QUIRK_NOMUX)
},
{
+ /* Fujitsu Lifebook E756 */
+ /* https://bugzilla.suse.com/show_bug.cgi?id=1229056 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E756"),
+ },
+ .driver_data = (void *)(SERIO_QUIRK_NOMUX)
+ },
+ {
/* Fujitsu Lifebook E5411 */
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU CLIENT COMPUTING LIMITED"),
@@ -1149,18 +1159,10 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
},
{
- /*
- * Setting SERIO_QUIRK_NOMUX or SERIO_QUIRK_RESET_ALWAYS makes
- * the keyboard very laggy for ~5 seconds after boot and
- * sometimes also after resume.
- * However both are required for the keyboard to not fail
- * completely sometimes after boot or resume.
- */
.matches = {
DMI_MATCH(DMI_BOARD_NAME, "N150CU"),
},
- .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
- SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+ .driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
},
{
.matches = {
@@ -1685,6 +1687,8 @@ static void __init i8042_check_quirks(void)
if (quirks & SERIO_QUIRK_NOPNP)
i8042_nopnp = true;
#endif
+ if (quirks & SERIO_QUIRK_FORCENORESTORE)
+ i8042_forcenorestore = true;
}
#else
static inline void i8042_check_quirks(void) {}
@@ -1718,7 +1722,7 @@ static int __init i8042_platform_init(void)
i8042_check_quirks();
- pr_debug("Active quirks (empty means none):%s%s%s%s%s%s%s%s%s%s%s%s%s\n",
+ pr_debug("Active quirks (empty means none):%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n",
i8042_nokbd ? " nokbd" : "",
i8042_noaux ? " noaux" : "",
i8042_nomux ? " nomux" : "",
@@ -1738,10 +1742,11 @@ static int __init i8042_platform_init(void)
"",
#endif
#ifdef CONFIG_PNP
- i8042_nopnp ? " nopnp" : "");
+ i8042_nopnp ? " nopnp" : "",
#else
- "");
+ "",
#endif
+ i8042_forcenorestore ? " forcenorestore" : "");
retval = i8042_pnp_init();
if (retval)
diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index e0fb1db..8ec4872 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -115,6 +115,10 @@ module_param_named(nopnp, i8042_nopnp, bool, 0);
MODULE_PARM_DESC(nopnp, "Do not use PNP to detect controller settings");
#endif
+static bool i8042_forcenorestore;
+module_param_named(forcenorestore, i8042_forcenorestore, bool, 0);
+MODULE_PARM_DESC(forcenorestore, "Force no restore on s3 resume, copying s2idle behaviour");
+
#define DEBUG
#ifdef DEBUG
static bool i8042_debug;
@@ -1232,7 +1236,7 @@ static int i8042_pm_suspend(struct device *dev)
{
int i;
- if (pm_suspend_via_firmware())
+ if (!i8042_forcenorestore && pm_suspend_via_firmware())
i8042_controller_reset(true);
/* Set up serio interrupts for system wakeup. */
@@ -1248,7 +1252,7 @@ static int i8042_pm_suspend(struct device *dev)
static int i8042_pm_resume_noirq(struct device *dev)
{
- if (!pm_resume_via_firmware())
+ if (i8042_forcenorestore || !pm_resume_via_firmware())
i8042_interrupt(0, NULL);
return 0;
@@ -1271,7 +1275,7 @@ static int i8042_pm_resume(struct device *dev)
* not restore the controller state to whatever it had been at boot
* time, so we do not need to do anything.
*/
- if (!pm_suspend_via_firmware())
+ if (i8042_forcenorestore || !pm_suspend_via_firmware())
return 0;
/*
diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c
index 4247283..f89c0dd 100644
--- a/drivers/input/touchscreen/ads7846.c
+++ b/drivers/input/touchscreen/ads7846.c
@@ -824,7 +824,7 @@ static void ads7846_read_state(struct ads7846 *ts)
m = &ts->msg[msg_idx];
error = spi_sync(ts->spi, m);
if (error) {
- dev_err(&ts->spi->dev, "spi_sync --> %d\n", error);
+ dev_err_ratelimited(&ts->spi->dev, "spi_sync --> %d\n", error);
packet->ignore = true;
return;
}
diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c
index 42f99e5..e70415f 100644
--- a/drivers/input/touchscreen/edt-ft5x06.c
+++ b/drivers/input/touchscreen/edt-ft5x06.c
@@ -1474,6 +1474,10 @@ static const struct edt_i2c_chip_data edt_ft6236_data = {
.max_support_points = 2,
};
+static const struct edt_i2c_chip_data edt_ft8201_data = {
+ .max_support_points = 10,
+};
+
static const struct edt_i2c_chip_data edt_ft8719_data = {
.max_support_points = 10,
};
@@ -1485,6 +1489,7 @@ static const struct i2c_device_id edt_ft5x06_ts_id[] = {
{ .name = "ft5452", .driver_data = (long)&edt_ft5452_data },
/* Note no edt- prefix for compatibility with the ft6236.c driver */
{ .name = "ft6236", .driver_data = (long)&edt_ft6236_data },
+ { .name = "ft8201", .driver_data = (long)&edt_ft8201_data },
{ .name = "ft8719", .driver_data = (long)&edt_ft8719_data },
{ /* sentinel */ }
};
@@ -1500,6 +1505,7 @@ static const struct of_device_id edt_ft5x06_of_match[] = {
{ .compatible = "focaltech,ft5452", .data = &edt_ft5452_data },
/* Note focaltech vendor prefix for compatibility with ft6236.c */
{ .compatible = "focaltech,ft6236", .data = &edt_ft6236_data },
+ { .compatible = "focaltech,ft8201", .data = &edt_ft8201_data },
{ .compatible = "focaltech,ft8719", .data = &edt_ft8719_data },
{ /* sentinel */ }
};
diff --git a/drivers/input/touchscreen/himax_hx83112b.c b/drivers/input/touchscreen/himax_hx83112b.c
index 9ed3bcc..896a145 100644
--- a/drivers/input/touchscreen/himax_hx83112b.c
+++ b/drivers/input/touchscreen/himax_hx83112b.c
@@ -130,17 +130,6 @@ static int himax_bus_read(struct himax_ts_data *ts, u32 address, void *dst,
return 0;
}
-static int himax_read_mcu(struct himax_ts_data *ts, u32 address, u32 *dst)
-{
- int error;
-
- error = himax_bus_read(ts, address, dst, sizeof(dst));
- if (error)
- return error;
-
- return 0;
-}
-
static void himax_reset(struct himax_ts_data *ts)
{
gpiod_set_value_cansleep(ts->gpiod_rst, 1);
@@ -160,7 +149,8 @@ static int himax_read_product_id(struct himax_ts_data *ts, u32 *product_id)
{
int error;
- error = himax_read_mcu(ts, HIMAX_REG_ADDR_ICID, product_id);
+ error = himax_bus_read(ts, HIMAX_REG_ADDR_ICID, product_id,
+ sizeof(*product_id));
if (error)
return error;
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index a31460f..ed2b106 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1777,7 +1777,7 @@ static int arm_smmu_handle_evt(struct arm_smmu_device *smmu, u64 *evt)
goto out_unlock;
}
- iommu_report_device_fault(master->dev, &fault_evt);
+ ret = iommu_report_device_fault(master->dev, &fault_evt);
out_unlock:
mutex_unlock(&smmu->streams_mutex);
return ret;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 9ff8b83..4aa070c 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1944,6 +1944,7 @@ static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8
{
struct intel_iommu *iommu = info->iommu;
struct context_entry *context;
+ u16 did;
spin_lock(&iommu->lock);
context = iommu_context_addr(iommu, bus, devfn, 0);
@@ -1952,10 +1953,11 @@ static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8
return;
}
+ did = context_domain_id(context);
context_clear_entry(context);
__iommu_flush_cache(iommu, context, sizeof(*context));
spin_unlock(&iommu->lock);
- intel_context_flush_present(info, context, true);
+ intel_context_flush_present(info, context, did, true);
}
static int domain_setup_first_level(struct intel_iommu *iommu,
@@ -4249,6 +4251,7 @@ static int context_flip_pri(struct device_domain_info *info, bool enable)
struct intel_iommu *iommu = info->iommu;
u8 bus = info->bus, devfn = info->devfn;
struct context_entry *context;
+ u16 did;
spin_lock(&iommu->lock);
if (context_copied(iommu, bus, devfn)) {
@@ -4261,6 +4264,7 @@ static int context_flip_pri(struct device_domain_info *info, bool enable)
spin_unlock(&iommu->lock);
return -ENODEV;
}
+ did = context_domain_id(context);
if (enable)
context_set_sm_pre(context);
@@ -4269,7 +4273,7 @@ static int context_flip_pri(struct device_domain_info *info, bool enable)
if (!ecap_coherent(iommu->ecap))
clflush_cache_range(context, sizeof(*context));
- intel_context_flush_present(info, context, true);
+ intel_context_flush_present(info, context, did, true);
spin_unlock(&iommu->lock);
return 0;
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index b67c14d..a969be2 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -1154,7 +1154,7 @@ void cache_tag_flush_range_np(struct dmar_domain *domain, unsigned long start,
void intel_context_flush_present(struct device_domain_info *info,
struct context_entry *context,
- bool affect_domains);
+ u16 did, bool affect_domains);
#ifdef CONFIG_INTEL_IOMMU_SVM
void intel_svm_check(struct intel_iommu *iommu);
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 5792c81..b51fc26 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -683,6 +683,7 @@ static void device_pasid_table_teardown(struct device *dev, u8 bus, u8 devfn)
struct device_domain_info *info = dev_iommu_priv_get(dev);
struct intel_iommu *iommu = info->iommu;
struct context_entry *context;
+ u16 did;
spin_lock(&iommu->lock);
context = iommu_context_addr(iommu, bus, devfn, false);
@@ -691,10 +692,11 @@ static void device_pasid_table_teardown(struct device *dev, u8 bus, u8 devfn)
return;
}
+ did = context_domain_id(context);
context_clear_entry(context);
__iommu_flush_cache(iommu, context, sizeof(*context));
spin_unlock(&iommu->lock);
- intel_context_flush_present(info, context, false);
+ intel_context_flush_present(info, context, did, false);
}
static int pci_pasid_table_teardown(struct pci_dev *pdev, u16 alias, void *data)
@@ -885,10 +887,9 @@ static void __context_flush_dev_iotlb(struct device_domain_info *info)
*/
void intel_context_flush_present(struct device_domain_info *info,
struct context_entry *context,
- bool flush_domains)
+ u16 did, bool flush_domains)
{
struct intel_iommu *iommu = info->iommu;
- u16 did = context_domain_id(context);
struct pasid_entry *pte;
int i;
diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c
index cd679c1..4674e61 100644
--- a/drivers/iommu/io-pgfault.c
+++ b/drivers/iommu/io-pgfault.c
@@ -115,6 +115,59 @@ static struct iopf_group *iopf_group_alloc(struct iommu_fault_param *iopf_param,
return group;
}
+static struct iommu_attach_handle *find_fault_handler(struct device *dev,
+ struct iopf_fault *evt)
+{
+ struct iommu_fault *fault = &evt->fault;
+ struct iommu_attach_handle *attach_handle;
+
+ if (fault->prm.flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID) {
+ attach_handle = iommu_attach_handle_get(dev->iommu_group,
+ fault->prm.pasid, 0);
+ if (IS_ERR(attach_handle)) {
+ const struct iommu_ops *ops = dev_iommu_ops(dev);
+
+ if (!ops->user_pasid_table)
+ return NULL;
+ /*
+ * The iommu driver for this device supports user-
+ * managed PASID table. Therefore page faults for
+ * any PASID should go through the NESTING domain
+ * attached to the device RID.
+ */
+ attach_handle = iommu_attach_handle_get(
+ dev->iommu_group, IOMMU_NO_PASID,
+ IOMMU_DOMAIN_NESTED);
+ if (IS_ERR(attach_handle))
+ return NULL;
+ }
+ } else {
+ attach_handle = iommu_attach_handle_get(dev->iommu_group,
+ IOMMU_NO_PASID, 0);
+
+ if (IS_ERR(attach_handle))
+ return NULL;
+ }
+
+ if (!attach_handle->domain->iopf_handler)
+ return NULL;
+
+ return attach_handle;
+}
+
+static void iopf_error_response(struct device *dev, struct iopf_fault *evt)
+{
+ const struct iommu_ops *ops = dev_iommu_ops(dev);
+ struct iommu_fault *fault = &evt->fault;
+ struct iommu_page_response resp = {
+ .pasid = fault->prm.pasid,
+ .grpid = fault->prm.grpid,
+ .code = IOMMU_PAGE_RESP_INVALID
+ };
+
+ ops->page_response(dev, evt, &resp);
+}
+
/**
* iommu_report_device_fault() - Report fault event to device driver
* @dev: the device
@@ -153,23 +206,39 @@ static struct iopf_group *iopf_group_alloc(struct iommu_fault_param *iopf_param,
* handling framework should guarantee that the iommu domain could only be
* freed after the device has stopped generating page faults (or the iommu
* hardware has been set to block the page faults) and the pending page faults
- * have been flushed.
+ * have been flushed. In case no page fault handler is attached or no iopf params
+ * are setup, then the ops->page_response() is called to complete the evt.
+ *
+ * Returns 0 on success, or an error in case of a bad/failed iopf setup.
*/
-void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt)
+int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt)
{
+ struct iommu_attach_handle *attach_handle;
struct iommu_fault *fault = &evt->fault;
struct iommu_fault_param *iopf_param;
struct iopf_group abort_group = {};
struct iopf_group *group;
+ attach_handle = find_fault_handler(dev, evt);
+ if (!attach_handle)
+ goto err_bad_iopf;
+
+ /*
+ * Something has gone wrong if a fault capable domain is attached but no
+ * iopf_param is setup
+ */
iopf_param = iopf_get_dev_fault_param(dev);
if (WARN_ON(!iopf_param))
- return;
+ goto err_bad_iopf;
if (!(fault->prm.flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE)) {
- report_partial_fault(iopf_param, fault);
+ int ret;
+
+ ret = report_partial_fault(iopf_param, fault);
iopf_put_dev_fault_param(iopf_param);
/* A request that is not the last does not need to be ack'd */
+
+ return ret;
}
/*
@@ -184,38 +253,7 @@ void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt)
if (group == &abort_group)
goto err_abort;
- if (fault->prm.flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID) {
- group->attach_handle = iommu_attach_handle_get(dev->iommu_group,
- fault->prm.pasid,
- 0);
- if (IS_ERR(group->attach_handle)) {
- const struct iommu_ops *ops = dev_iommu_ops(dev);
-
- if (!ops->user_pasid_table)
- goto err_abort;
-
- /*
- * The iommu driver for this device supports user-
- * managed PASID table. Therefore page faults for
- * any PASID should go through the NESTING domain
- * attached to the device RID.
- */
- group->attach_handle =
- iommu_attach_handle_get(dev->iommu_group,
- IOMMU_NO_PASID,
- IOMMU_DOMAIN_NESTED);
- if (IS_ERR(group->attach_handle))
- goto err_abort;
- }
- } else {
- group->attach_handle =
- iommu_attach_handle_get(dev->iommu_group, IOMMU_NO_PASID, 0);
- if (IS_ERR(group->attach_handle))
- goto err_abort;
- }
-
- if (!group->attach_handle->domain->iopf_handler)
- goto err_abort;
+ group->attach_handle = attach_handle;
/*
* On success iopf_handler must call iopf_group_response() and
@@ -224,7 +262,7 @@ void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt)
if (group->attach_handle->domain->iopf_handler(group))
goto err_abort;
- return;
+ return 0;
err_abort:
dev_warn_ratelimited(dev, "iopf with pasid %d aborted\n",
@@ -234,6 +272,14 @@ void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt)
__iopf_free_group(group);
else
iopf_free_group(group);
+
+ return 0;
+
+err_bad_iopf:
+ if (fault->type == IOMMU_FAULT_PAGE_REQ)
+ iopf_error_response(dev, evt);
+
+ return -EINVAL;
}
EXPORT_SYMBOL_GPL(iommu_report_device_fault);
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 75f244a..06ffc68 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -552,9 +552,8 @@ static int arm_v7s_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
paddr >= (1ULL << data->iop.cfg.oas)))
return -ERANGE;
- /* If no access, then nothing to do */
if (!(prot & (IOMMU_READ | IOMMU_WRITE)))
- return 0;
+ return -EINVAL;
while (pgcount--) {
ret = __arm_v7s_map(data, iova, paddr, pgsize, prot, 1, data->pgd,
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index f5d9fd1..ff4149a 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -515,9 +515,8 @@ static int arm_lpae_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
if (WARN_ON(iaext || paddr >> cfg->oas))
return -ERANGE;
- /* If no access, then nothing to do */
if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
- return 0;
+ return -EINVAL;
prot = arm_lpae_prot_to_pte(data, iommu_prot);
ret = __arm_lpae_map(data, iova, paddr, pgsize, pgcount, prot, lvl,
diff --git a/drivers/iommu/io-pgtable-dart.c b/drivers/iommu/io-pgtable-dart.c
index ad28031..c004640 100644
--- a/drivers/iommu/io-pgtable-dart.c
+++ b/drivers/iommu/io-pgtable-dart.c
@@ -245,9 +245,8 @@ static int dart_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
if (WARN_ON(paddr >> cfg->oas))
return -ERANGE;
- /* If no access, then nothing to do */
if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
- return 0;
+ return -EINVAL;
tbl = dart_get_table(data, iova);
diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index 9a7ec59..3214a4c 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -526,7 +526,7 @@ iommufd_device_do_replace(struct iommufd_device *idev,
err_unresv:
if (hwpt_is_paging(hwpt))
iommufd_group_remove_reserved_iova(igroup,
- to_hwpt_paging(old_hwpt));
+ to_hwpt_paging(hwpt));
err_unlock:
mutex_unlock(&idev->igroup->lock);
return ERR_PTR(rc);
diff --git a/drivers/iommu/iommufd/ioas.c b/drivers/iommu/iommufd/ioas.c
index 7422482..157a89b 100644
--- a/drivers/iommu/iommufd/ioas.c
+++ b/drivers/iommu/iommufd/ioas.c
@@ -213,6 +213,10 @@ int iommufd_ioas_map(struct iommufd_ucmd *ucmd)
if (cmd->iova >= ULONG_MAX || cmd->length >= ULONG_MAX)
return -EOVERFLOW;
+ if (!(cmd->flags &
+ (IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)))
+ return -EINVAL;
+
ioas = iommufd_get_ioas(ucmd->ictx, cmd->ioas_id);
if (IS_ERR(ioas))
return PTR_ERR(ioas);
@@ -253,6 +257,10 @@ int iommufd_ioas_copy(struct iommufd_ucmd *ucmd)
cmd->dst_iova >= ULONG_MAX)
return -EOVERFLOW;
+ if (!(cmd->flags &
+ (IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)))
+ return -EINVAL;
+
src_ioas = iommufd_get_ioas(ucmd->ictx, cmd->src_ioas_id);
if (IS_ERR(src_ioas))
return PTR_ERR(src_ioas);
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index f95e32e..222cfc1 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -273,7 +273,7 @@ static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain,
return 0;
}
-const struct iommu_dirty_ops dirty_ops = {
+static const struct iommu_dirty_ops dirty_ops = {
.set_dirty_tracking = mock_domain_set_dirty_tracking,
.read_and_clear_dirty = mock_domain_read_and_clear_dirty,
};
diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c
index 51af63c..be35c53 100644
--- a/drivers/irqchip/irq-gic-v2m.c
+++ b/drivers/irqchip/irq-gic-v2m.c
@@ -407,12 +407,12 @@ static int __init gicv2m_of_init(struct fwnode_handle *parent_handle,
ret = gicv2m_init_one(&child->fwnode, spi_start, nr_spis,
&res, 0);
- if (ret) {
- of_node_put(child);
+ if (ret)
break;
- }
}
+ if (ret && child)
+ of_node_put(child);
if (!ret)
ret = gicv2m_allocate_domains(parent);
if (ret)
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 9b34596..fdec478 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1330,12 +1330,6 @@ static void its_send_vmovp(struct its_vpe *vpe)
}
/*
- * Protect against concurrent updates of the mapping state on
- * individual VMs.
- */
- guard(raw_spinlock_irqsave)(&vpe->its_vm->vmapp_lock);
-
- /*
* Yet another marvel of the architecture. If using the
* its_list "feature", we need to make sure that all ITSs
* receive all VMOVP commands in the same order. The only way
@@ -3824,7 +3818,14 @@ static int its_vpe_set_affinity(struct irq_data *d,
* protect us, and that we must ensure nobody samples vpe->col_idx
* during the update, hence the lock below which must also be
* taken on any vLPI handling path that evaluates vpe->col_idx.
+ *
+ * Finally, we must protect ourselves against concurrent updates of
+ * the mapping state on this VM should the ITS list be in use (see
+ * the shortcut in its_send_vmovp() otherewise).
*/
+ if (its_list_map)
+ raw_spin_lock(&vpe->its_vm->vmapp_lock);
+
from = vpe_to_cpuid_lock(vpe, &flags);
table_mask = gic_data_rdist_cpu(from)->vpe_table_mask;
@@ -3854,6 +3855,9 @@ static int its_vpe_set_affinity(struct irq_data *d,
irq_data_update_effective_affinity(d, cpumask_of(cpu));
vpe_to_cpuid_unlock(vpe, flags);
+ if (its_list_map)
+ raw_spin_unlock(&vpe->its_vm->vmapp_lock);
+
return IRQ_SET_MASK_OK_DONE;
}
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index c19083b..74f21e0 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -1154,14 +1154,8 @@ static void gic_update_rdist_properties(void)
gic_data.rdists.has_vpend_valid_dirty ? "Valid+Dirty " : "");
}
-static void gic_cpu_sys_reg_init(void)
+static void gic_cpu_sys_reg_enable(void)
{
- int i, cpu = smp_processor_id();
- u64 mpidr = gic_cpu_to_affinity(cpu);
- u64 need_rss = MPIDR_RS(mpidr);
- bool group0;
- u32 pribits;
-
/*
* Need to check that the SRE bit has actually been set. If
* not, it means that SRE is disabled at EL2. We're going to
@@ -1172,6 +1166,16 @@ static void gic_cpu_sys_reg_init(void)
if (!gic_enable_sre())
pr_err("GIC: unable to set SRE (disabled at EL2), panic ahead\n");
+}
+
+static void gic_cpu_sys_reg_init(void)
+{
+ int i, cpu = smp_processor_id();
+ u64 mpidr = gic_cpu_to_affinity(cpu);
+ u64 need_rss = MPIDR_RS(mpidr);
+ bool group0;
+ u32 pribits;
+
pribits = gic_get_pribits();
group0 = gic_has_group0();
@@ -1333,6 +1337,7 @@ static int gic_check_rdist(unsigned int cpu)
static int gic_starting_cpu(unsigned int cpu)
{
+ gic_cpu_sys_reg_enable();
gic_cpu_init();
if (gic_dist_supports_lpis())
@@ -1498,6 +1503,7 @@ static int gic_cpu_pm_notifier(struct notifier_block *self,
if (cmd == CPU_PM_EXIT) {
if (gic_dist_security_disabled())
gic_enable_redist(true);
+ gic_cpu_sys_reg_enable();
gic_cpu_sys_reg_init();
} else if (cmd == CPU_PM_ENTER && gic_dist_security_disabled()) {
gic_write_grpen1(0);
@@ -2070,6 +2076,7 @@ static int __init gic_init_bases(phys_addr_t dist_phys_base,
gic_update_rdist_properties();
+ gic_cpu_sys_reg_enable();
gic_prio_init();
gic_dist_init();
gic_cpu_init();
diff --git a/drivers/irqchip/irq-msi-lib.c b/drivers/irqchip/irq-msi-lib.c
index b5b9000..d8e29fc 100644
--- a/drivers/irqchip/irq-msi-lib.c
+++ b/drivers/irqchip/irq-msi-lib.c
@@ -128,6 +128,9 @@ int msi_lib_irq_domain_select(struct irq_domain *d, struct irq_fwspec *fwspec,
const struct msi_parent_ops *ops = d->msi_parent_ops;
u32 busmask = BIT(bus_token);
+ if (!ops)
+ return 0;
+
if (fwspec->fwnode != d->fwnode || fwspec->param_count != 0)
return 0;
@@ -135,6 +138,6 @@ int msi_lib_irq_domain_select(struct irq_domain *d, struct irq_fwspec *fwspec,
if (bus_token == ops->bus_select_token)
return 1;
- return ops && !!(ops->bus_select_mask & busmask);
+ return !!(ops->bus_select_mask & busmask);
}
EXPORT_SYMBOL_GPL(msi_lib_irq_domain_select);
diff --git a/drivers/irqchip/irq-riscv-aplic-main.c b/drivers/irqchip/irq-riscv-aplic-main.c
index 28dd175..981fad6 100644
--- a/drivers/irqchip/irq-riscv-aplic-main.c
+++ b/drivers/irqchip/irq-riscv-aplic-main.c
@@ -175,9 +175,9 @@ static int aplic_probe(struct platform_device *pdev)
/* Map the MMIO registers */
regs = devm_platform_ioremap_resource(pdev, 0);
- if (!regs) {
+ if (IS_ERR(regs)) {
dev_err(dev, "failed map MMIO registers\n");
- return -ENOMEM;
+ return PTR_ERR(regs);
}
/*
diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index 9e22f7e..4d9ea71 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -3,6 +3,7 @@
* Copyright (C) 2017 SiFive
* Copyright (C) 2018 Christoph Hellwig
*/
+#define pr_fmt(fmt) "riscv-plic: " fmt
#include <linux/cpu.h>
#include <linux/interrupt.h>
#include <linux/io.h>
@@ -63,7 +64,7 @@
#define PLIC_QUIRK_EDGE_INTERRUPT 0
struct plic_priv {
- struct device *dev;
+ struct fwnode_handle *fwnode;
struct cpumask lmask;
struct irq_domain *irqdomain;
void __iomem *regs;
@@ -378,8 +379,8 @@ static void plic_handle_irq(struct irq_desc *desc)
int err = generic_handle_domain_irq(handler->priv->irqdomain,
hwirq);
if (unlikely(err)) {
- dev_warn_ratelimited(handler->priv->dev,
- "can't find mapping for hwirq %lu\n", hwirq);
+ pr_warn_ratelimited("%pfwP: can't find mapping for hwirq %lu\n",
+ handler->priv->fwnode, hwirq);
}
}
@@ -408,7 +409,8 @@ static int plic_starting_cpu(unsigned int cpu)
enable_percpu_irq(plic_parent_irq,
irq_get_trigger_type(plic_parent_irq));
else
- dev_warn(handler->priv->dev, "cpu%d: parent irq not available\n", cpu);
+ pr_warn("%pfwP: cpu%d: parent irq not available\n",
+ handler->priv->fwnode, cpu);
plic_set_threshold(handler, PLIC_ENABLE_THRESHOLD);
return 0;
@@ -424,38 +426,36 @@ static const struct of_device_id plic_match[] = {
{}
};
-static int plic_parse_nr_irqs_and_contexts(struct platform_device *pdev,
+static int plic_parse_nr_irqs_and_contexts(struct fwnode_handle *fwnode,
u32 *nr_irqs, u32 *nr_contexts)
{
- struct device *dev = &pdev->dev;
int rc;
/*
* Currently, only OF fwnode is supported so extend this
* function for ACPI support.
*/
- if (!is_of_node(dev->fwnode))
+ if (!is_of_node(fwnode))
return -EINVAL;
- rc = of_property_read_u32(to_of_node(dev->fwnode), "riscv,ndev", nr_irqs);
+ rc = of_property_read_u32(to_of_node(fwnode), "riscv,ndev", nr_irqs);
if (rc) {
- dev_err(dev, "riscv,ndev property not available\n");
+ pr_err("%pfwP: riscv,ndev property not available\n", fwnode);
return rc;
}
- *nr_contexts = of_irq_count(to_of_node(dev->fwnode));
+ *nr_contexts = of_irq_count(to_of_node(fwnode));
if (WARN_ON(!(*nr_contexts))) {
- dev_err(dev, "no PLIC context available\n");
+ pr_err("%pfwP: no PLIC context available\n", fwnode);
return -EINVAL;
}
return 0;
}
-static int plic_parse_context_parent(struct platform_device *pdev, u32 context,
+static int plic_parse_context_parent(struct fwnode_handle *fwnode, u32 context,
u32 *parent_hwirq, int *parent_cpu)
{
- struct device *dev = &pdev->dev;
struct of_phandle_args parent;
unsigned long hartid;
int rc;
@@ -464,10 +464,10 @@ static int plic_parse_context_parent(struct platform_device *pdev, u32 context,
* Currently, only OF fwnode is supported so extend this
* function for ACPI support.
*/
- if (!is_of_node(dev->fwnode))
+ if (!is_of_node(fwnode))
return -EINVAL;
- rc = of_irq_parse_one(to_of_node(dev->fwnode), context, &parent);
+ rc = of_irq_parse_one(to_of_node(fwnode), context, &parent);
if (rc)
return rc;
@@ -480,48 +480,55 @@ static int plic_parse_context_parent(struct platform_device *pdev, u32 context,
return 0;
}
-static int plic_probe(struct platform_device *pdev)
+static int plic_probe(struct fwnode_handle *fwnode)
{
int error = 0, nr_contexts, nr_handlers = 0, cpu, i;
- struct device *dev = &pdev->dev;
unsigned long plic_quirks = 0;
struct plic_handler *handler;
u32 nr_irqs, parent_hwirq;
struct plic_priv *priv;
irq_hw_number_t hwirq;
+ void __iomem *regs;
- if (is_of_node(dev->fwnode)) {
+ if (is_of_node(fwnode)) {
const struct of_device_id *id;
- id = of_match_node(plic_match, to_of_node(dev->fwnode));
+ id = of_match_node(plic_match, to_of_node(fwnode));
if (id)
plic_quirks = (unsigned long)id->data;
+
+ regs = of_iomap(to_of_node(fwnode), 0);
+ if (!regs)
+ return -ENOMEM;
+ } else {
+ return -ENODEV;
}
- error = plic_parse_nr_irqs_and_contexts(pdev, &nr_irqs, &nr_contexts);
+ error = plic_parse_nr_irqs_and_contexts(fwnode, &nr_irqs, &nr_contexts);
if (error)
- return error;
+ goto fail_free_regs;
- priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
- if (!priv)
- return -ENOMEM;
+ priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+ if (!priv) {
+ error = -ENOMEM;
+ goto fail_free_regs;
+ }
- priv->dev = dev;
+ priv->fwnode = fwnode;
priv->plic_quirks = plic_quirks;
priv->nr_irqs = nr_irqs;
+ priv->regs = regs;
- priv->regs = devm_platform_ioremap_resource(pdev, 0);
- if (WARN_ON(!priv->regs))
- return -EIO;
-
- priv->prio_save = devm_bitmap_zalloc(dev, nr_irqs, GFP_KERNEL);
- if (!priv->prio_save)
- return -ENOMEM;
+ priv->prio_save = bitmap_zalloc(nr_irqs, GFP_KERNEL);
+ if (!priv->prio_save) {
+ error = -ENOMEM;
+ goto fail_free_priv;
+ }
for (i = 0; i < nr_contexts; i++) {
- error = plic_parse_context_parent(pdev, i, &parent_hwirq, &cpu);
+ error = plic_parse_context_parent(fwnode, i, &parent_hwirq, &cpu);
if (error) {
- dev_warn(dev, "hwirq for context%d not found\n", i);
+ pr_warn("%pfwP: hwirq for context%d not found\n", fwnode, i);
continue;
}
@@ -543,7 +550,7 @@ static int plic_probe(struct platform_device *pdev)
}
if (cpu < 0) {
- dev_warn(dev, "Invalid cpuid for context %d\n", i);
+ pr_warn("%pfwP: Invalid cpuid for context %d\n", fwnode, i);
continue;
}
@@ -554,7 +561,7 @@ static int plic_probe(struct platform_device *pdev)
*/
handler = per_cpu_ptr(&plic_handlers, cpu);
if (handler->present) {
- dev_warn(dev, "handler already present for context %d.\n", i);
+ pr_warn("%pfwP: handler already present for context %d.\n", fwnode, i);
plic_set_threshold(handler, PLIC_DISABLE_THRESHOLD);
goto done;
}
@@ -568,8 +575,8 @@ static int plic_probe(struct platform_device *pdev)
i * CONTEXT_ENABLE_SIZE;
handler->priv = priv;
- handler->enable_save = devm_kcalloc(dev, DIV_ROUND_UP(nr_irqs, 32),
- sizeof(*handler->enable_save), GFP_KERNEL);
+ handler->enable_save = kcalloc(DIV_ROUND_UP(nr_irqs, 32),
+ sizeof(*handler->enable_save), GFP_KERNEL);
if (!handler->enable_save)
goto fail_cleanup_contexts;
done:
@@ -581,7 +588,7 @@ static int plic_probe(struct platform_device *pdev)
nr_handlers++;
}
- priv->irqdomain = irq_domain_add_linear(to_of_node(dev->fwnode), nr_irqs + 1,
+ priv->irqdomain = irq_domain_add_linear(to_of_node(fwnode), nr_irqs + 1,
&plic_irqdomain_ops, priv);
if (WARN_ON(!priv->irqdomain))
goto fail_cleanup_contexts;
@@ -619,13 +626,13 @@ static int plic_probe(struct platform_device *pdev)
}
}
- dev_info(dev, "mapped %d interrupts with %d handlers for %d contexts.\n",
- nr_irqs, nr_handlers, nr_contexts);
+ pr_info("%pfwP: mapped %d interrupts with %d handlers for %d contexts.\n",
+ fwnode, nr_irqs, nr_handlers, nr_contexts);
return 0;
fail_cleanup_contexts:
for (i = 0; i < nr_contexts; i++) {
- if (plic_parse_context_parent(pdev, i, &parent_hwirq, &cpu))
+ if (plic_parse_context_parent(fwnode, i, &parent_hwirq, &cpu))
continue;
if (parent_hwirq != RV_IRQ_EXT || cpu < 0)
continue;
@@ -634,17 +641,37 @@ static int plic_probe(struct platform_device *pdev)
handler->present = false;
handler->hart_base = NULL;
handler->enable_base = NULL;
+ kfree(handler->enable_save);
handler->enable_save = NULL;
handler->priv = NULL;
}
- return -ENOMEM;
+ bitmap_free(priv->prio_save);
+fail_free_priv:
+ kfree(priv);
+fail_free_regs:
+ iounmap(regs);
+ return error;
+}
+
+static int plic_platform_probe(struct platform_device *pdev)
+{
+ return plic_probe(pdev->dev.fwnode);
}
static struct platform_driver plic_driver = {
.driver = {
.name = "riscv-plic",
.of_match_table = plic_match,
+ .suppress_bind_attrs = true,
},
- .probe = plic_probe,
+ .probe = plic_platform_probe,
};
builtin_platform_driver(plic_driver);
+
+static int __init plic_early_probe(struct device_node *node,
+ struct device_node *parent)
+{
+ return plic_probe(&node->fwnode);
+}
+
+IRQCHIP_DECLARE(riscv, "allwinner,sun20i-d1-plic", plic_early_probe);
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index c2c07bf..f299ff3 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1181,8 +1181,26 @@ static int do_resume(struct dm_ioctl *param)
suspend_flags &= ~DM_SUSPEND_LOCKFS_FLAG;
if (param->flags & DM_NOFLUSH_FLAG)
suspend_flags |= DM_SUSPEND_NOFLUSH_FLAG;
- if (!dm_suspended_md(md))
- dm_suspend(md, suspend_flags);
+ if (!dm_suspended_md(md)) {
+ r = dm_suspend(md, suspend_flags);
+ if (r) {
+ down_write(&_hash_lock);
+ hc = dm_get_mdptr(md);
+ if (hc && !hc->new_map) {
+ hc->new_map = new_map;
+ new_map = NULL;
+ } else {
+ r = -ENXIO;
+ }
+ up_write(&_hash_lock);
+ if (new_map) {
+ dm_sync_table(md);
+ dm_table_destroy(new_map);
+ }
+ dm_put(md);
+ return r;
+ }
+ }
old_size = dm_get_size(md);
old_map = dm_swap_table(md, new_map);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 97fab208..87bb903 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2737,7 +2737,7 @@ static int dm_wait_for_bios_completion(struct mapped_device *md, unsigned int ta
break;
if (signal_pending_state(task_state, current)) {
- r = -EINTR;
+ r = -ERESTARTSYS;
break;
}
@@ -2762,7 +2762,7 @@ static int dm_wait_for_completion(struct mapped_device *md, unsigned int task_st
break;
if (signal_pending_state(task_state, current)) {
- r = -EINTR;
+ r = -ERESTARTSYS;
break;
}
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 04698fd..d48c4fa 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -277,7 +277,7 @@ static void sm_metadata_destroy(struct dm_space_map *sm)
{
struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
- kfree(smm);
+ kvfree(smm);
}
static int sm_metadata_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count)
@@ -772,7 +772,7 @@ struct dm_space_map *dm_sm_metadata_init(void)
{
struct sm_metadata *smm;
- smm = kmalloc(sizeof(*smm), GFP_KERNEL);
+ smm = kvmalloc(sizeof(*smm), GFP_KERNEL);
if (!smm)
return ERR_PTR(-ENOMEM);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 7acfe7c..761989d 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -617,6 +617,12 @@ static int choose_first_rdev(struct r1conf *conf, struct r1bio *r1_bio,
return -1;
}
+static bool rdev_in_recovery(struct md_rdev *rdev, struct r1bio *r1_bio)
+{
+ return !test_bit(In_sync, &rdev->flags) &&
+ rdev->recovery_offset < r1_bio->sector + r1_bio->sectors;
+}
+
static int choose_bb_rdev(struct r1conf *conf, struct r1bio *r1_bio,
int *max_sectors)
{
@@ -635,6 +641,7 @@ static int choose_bb_rdev(struct r1conf *conf, struct r1bio *r1_bio,
rdev = conf->mirrors[disk].rdev;
if (!rdev || test_bit(Faulty, &rdev->flags) ||
+ rdev_in_recovery(rdev, r1_bio) ||
test_bit(WriteMostly, &rdev->flags))
continue;
@@ -673,7 +680,8 @@ static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio,
rdev = conf->mirrors[disk].rdev;
if (!rdev || test_bit(Faulty, &rdev->flags) ||
- !test_bit(WriteMostly, &rdev->flags))
+ !test_bit(WriteMostly, &rdev->flags) ||
+ rdev_in_recovery(rdev, r1_bio))
continue;
/* there are no bad blocks, we can use this disk */
@@ -733,9 +741,7 @@ static bool rdev_readable(struct md_rdev *rdev, struct r1bio *r1_bio)
if (!rdev || test_bit(Faulty, &rdev->flags))
return false;
- /* still in recovery */
- if (!test_bit(In_sync, &rdev->flags) &&
- rdev->recovery_offset < r1_bio->sector + r1_bio->sectors)
+ if (rdev_in_recovery(rdev, r1_bio))
return false;
/* don't read from slow disk unless have to */
diff --git a/drivers/media/usb/dvb-usb/dvb-usb-init.c b/drivers/media/usb/dvb-usb/dvb-usb-init.c
index 22d83ac..fbf5801 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb-init.c
+++ b/drivers/media/usb/dvb-usb/dvb-usb-init.c
@@ -23,40 +23,11 @@ static int dvb_usb_force_pid_filter_usage;
module_param_named(force_pid_filter_usage, dvb_usb_force_pid_filter_usage, int, 0444);
MODULE_PARM_DESC(force_pid_filter_usage, "force all dvb-usb-devices to use a PID filter, if any (default: 0).");
-static int dvb_usb_check_bulk_endpoint(struct dvb_usb_device *d, u8 endpoint)
-{
- if (endpoint) {
- int ret;
-
- ret = usb_pipe_type_check(d->udev, usb_sndbulkpipe(d->udev, endpoint));
- if (ret)
- return ret;
- ret = usb_pipe_type_check(d->udev, usb_rcvbulkpipe(d->udev, endpoint));
- if (ret)
- return ret;
- }
- return 0;
-}
-
-static void dvb_usb_clear_halt(struct dvb_usb_device *d, u8 endpoint)
-{
- if (endpoint) {
- usb_clear_halt(d->udev, usb_sndbulkpipe(d->udev, endpoint));
- usb_clear_halt(d->udev, usb_rcvbulkpipe(d->udev, endpoint));
- }
-}
-
static int dvb_usb_adapter_init(struct dvb_usb_device *d, short *adapter_nrs)
{
struct dvb_usb_adapter *adap;
int ret, n, o;
- ret = dvb_usb_check_bulk_endpoint(d, d->props.generic_bulk_ctrl_endpoint);
- if (ret)
- return ret;
- ret = dvb_usb_check_bulk_endpoint(d, d->props.generic_bulk_ctrl_endpoint_response);
- if (ret)
- return ret;
for (n = 0; n < d->props.num_adapters; n++) {
adap = &d->adapter[n];
adap->dev = d;
@@ -132,8 +103,10 @@ static int dvb_usb_adapter_init(struct dvb_usb_device *d, short *adapter_nrs)
* when reloading the driver w/o replugging the device
* sometimes a timeout occurs, this helps
*/
- dvb_usb_clear_halt(d, d->props.generic_bulk_ctrl_endpoint);
- dvb_usb_clear_halt(d, d->props.generic_bulk_ctrl_endpoint_response);
+ if (d->props.generic_bulk_ctrl_endpoint != 0) {
+ usb_clear_halt(d->udev, usb_sndbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint));
+ usb_clear_halt(d->udev, usb_rcvbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint));
+ }
return 0;
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 5204fda..339d126 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -2085,16 +2085,6 @@ static int fastrpc_req_mem_map(struct fastrpc_user *fl, char __user *argp)
return err;
}
-static int is_attach_rejected(struct fastrpc_user *fl)
-{
- /* Check if the device node is non-secure */
- if (!fl->is_secure_dev) {
- dev_dbg(&fl->cctx->rpdev->dev, "untrusted app trying to attach to privileged DSP PD\n");
- return -EACCES;
- }
- return 0;
-}
-
static long fastrpc_device_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
@@ -2107,19 +2097,13 @@ static long fastrpc_device_ioctl(struct file *file, unsigned int cmd,
err = fastrpc_invoke(fl, argp);
break;
case FASTRPC_IOCTL_INIT_ATTACH:
- err = is_attach_rejected(fl);
- if (!err)
- err = fastrpc_init_attach(fl, ROOT_PD);
+ err = fastrpc_init_attach(fl, ROOT_PD);
break;
case FASTRPC_IOCTL_INIT_ATTACH_SNS:
- err = is_attach_rejected(fl);
- if (!err)
- err = fastrpc_init_attach(fl, SENSORS_PD);
+ err = fastrpc_init_attach(fl, SENSORS_PD);
break;
case FASTRPC_IOCTL_INIT_CREATE_STATIC:
- err = is_attach_rejected(fl);
- if (!err)
- err = fastrpc_init_create_static_process(fl, argp);
+ err = fastrpc_init_create_static_process(fl, argp);
break;
case FASTRPC_IOCTL_INIT_CREATE:
err = fastrpc_init_create_process(fl, argp);
diff --git a/drivers/misc/lkdtm/refcount.c b/drivers/misc/lkdtm/refcount.c
index 5cd488f..8f744be 100644
--- a/drivers/misc/lkdtm/refcount.c
+++ b/drivers/misc/lkdtm/refcount.c
@@ -182,6 +182,21 @@ static void lkdtm_REFCOUNT_SUB_AND_TEST_NEGATIVE(void)
check_negative(&neg, 3);
}
+/*
+ * A refcount_sub_and_test() by zero when the counter is at zero should act like
+ * refcount_sub_and_test() above when going negative.
+ */
+static void lkdtm_REFCOUNT_SUB_AND_TEST_ZERO(void)
+{
+ refcount_t neg = REFCOUNT_INIT(0);
+
+ pr_info("attempting bad refcount_sub_and_test() at zero\n");
+ if (refcount_sub_and_test(0, &neg))
+ pr_warn("Weird: refcount_sub_and_test() reported zero\n");
+
+ check_negative(&neg, 0);
+}
+
static void check_from_zero(refcount_t *ref)
{
switch (refcount_read(ref)) {
@@ -400,6 +415,7 @@ static struct crashtype crashtypes[] = {
CRASHTYPE(REFCOUNT_DEC_NEGATIVE),
CRASHTYPE(REFCOUNT_DEC_AND_TEST_NEGATIVE),
CRASHTYPE(REFCOUNT_SUB_AND_TEST_NEGATIVE),
+ CRASHTYPE(REFCOUNT_SUB_AND_TEST_ZERO),
CRASHTYPE(REFCOUNT_INC_ZERO),
CRASHTYPE(REFCOUNT_ADD_ZERO),
CRASHTYPE(REFCOUNT_INC_SATURATED),
diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c
index 8f7f587..b7f627a 100644
--- a/drivers/mmc/core/mmc_test.c
+++ b/drivers/mmc/core/mmc_test.c
@@ -3125,13 +3125,13 @@ static ssize_t mtf_test_write(struct file *file, const char __user *buf,
test->buffer = kzalloc(BUFFER_SIZE, GFP_KERNEL);
#ifdef CONFIG_HIGHMEM
test->highmem = alloc_pages(GFP_KERNEL | __GFP_HIGHMEM, BUFFER_ORDER);
+ if (!test->highmem) {
+ count = -ENOMEM;
+ goto free_test_buffer;
+ }
#endif
-#ifdef CONFIG_HIGHMEM
- if (test->buffer && test->highmem) {
-#else
if (test->buffer) {
-#endif
mutex_lock(&mmc_test_lock);
mmc_test_run(test, testcase);
mutex_unlock(&mmc_test_lock);
@@ -3139,6 +3139,7 @@ static ssize_t mtf_test_write(struct file *file, const char __user *buf,
#ifdef CONFIG_HIGHMEM
__free_pages(test->highmem, BUFFER_ORDER);
+free_test_buffer:
#endif
kfree(test->buffer);
kfree(test);
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 2333ef4..e9f6e4e 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -3299,6 +3299,10 @@ int dw_mci_probe(struct dw_mci *host)
host->biu_clk = devm_clk_get(host->dev, "biu");
if (IS_ERR(host->biu_clk)) {
dev_dbg(host->dev, "biu clock not available\n");
+ ret = PTR_ERR(host->biu_clk);
+ if (ret == -EPROBE_DEFER)
+ return ret;
+
} else {
ret = clk_prepare_enable(host->biu_clk);
if (ret) {
@@ -3310,6 +3314,10 @@ int dw_mci_probe(struct dw_mci *host)
host->ciu_clk = devm_clk_get(host->dev, "ciu");
if (IS_ERR(host->ciu_clk)) {
dev_dbg(host->dev, "ciu clock not available\n");
+ ret = PTR_ERR(host->ciu_clk);
+ if (ret == -EPROBE_DEFER)
+ goto err_clk_biu;
+
host->bus_hz = host->pdata->bus_hz;
} else {
ret = clk_prepare_enable(host->ciu_clk);
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index a94835b..e386f78 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -1230,7 +1230,7 @@ static bool msdc_cmd_done(struct msdc_host *host, int events,
}
if (!sbc_error && !(events & MSDC_INT_CMDRDY)) {
- if (events & MSDC_INT_CMDTMO ||
+ if ((events & MSDC_INT_CMDTMO && !host->hs400_tuning) ||
(!mmc_op_tuning(cmd->opcode) && !host->hs400_tuning))
/*
* should not clear fifo/interrupt as the tune data
@@ -1323,9 +1323,9 @@ static void msdc_start_command(struct msdc_host *host,
static void msdc_cmd_next(struct msdc_host *host,
struct mmc_request *mrq, struct mmc_command *cmd)
{
- if ((cmd->error &&
- !(cmd->error == -EILSEQ &&
- (mmc_op_tuning(cmd->opcode) || host->hs400_tuning))) ||
+ if ((cmd->error && !host->hs400_tuning &&
+ !(cmd->error == -EILSEQ &&
+ mmc_op_tuning(cmd->opcode))) ||
(mrq->sbc && mrq->sbc->error))
msdc_request_done(host, mrq);
else if (cmd == mrq->sbc)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 1cd92c1..bb9c3d6 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -427,6 +427,8 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs,
struct netlink_ext_ack *extack)
{
struct net_device *bond_dev = xs->xso.dev;
+ struct net_device *real_dev;
+ netdevice_tracker tracker;
struct bond_ipsec *ipsec;
struct bonding *bond;
struct slave *slave;
@@ -438,74 +440,80 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs,
rcu_read_lock();
bond = netdev_priv(bond_dev);
slave = rcu_dereference(bond->curr_active_slave);
- if (!slave) {
- rcu_read_unlock();
- return -ENODEV;
+ real_dev = slave ? slave->dev : NULL;
+ netdev_hold(real_dev, &tracker, GFP_ATOMIC);
+ rcu_read_unlock();
+ if (!real_dev) {
+ err = -ENODEV;
+ goto out;
}
- if (!slave->dev->xfrmdev_ops ||
- !slave->dev->xfrmdev_ops->xdo_dev_state_add ||
- netif_is_bond_master(slave->dev)) {
+ if (!real_dev->xfrmdev_ops ||
+ !real_dev->xfrmdev_ops->xdo_dev_state_add ||
+ netif_is_bond_master(real_dev)) {
NL_SET_ERR_MSG_MOD(extack, "Slave does not support ipsec offload");
- rcu_read_unlock();
- return -EINVAL;
+ err = -EINVAL;
+ goto out;
}
- ipsec = kmalloc(sizeof(*ipsec), GFP_ATOMIC);
+ ipsec = kmalloc(sizeof(*ipsec), GFP_KERNEL);
if (!ipsec) {
- rcu_read_unlock();
- return -ENOMEM;
+ err = -ENOMEM;
+ goto out;
}
- xs->xso.real_dev = slave->dev;
- err = slave->dev->xfrmdev_ops->xdo_dev_state_add(xs, extack);
+ xs->xso.real_dev = real_dev;
+ err = real_dev->xfrmdev_ops->xdo_dev_state_add(xs, extack);
if (!err) {
ipsec->xs = xs;
INIT_LIST_HEAD(&ipsec->list);
- spin_lock_bh(&bond->ipsec_lock);
+ mutex_lock(&bond->ipsec_lock);
list_add(&ipsec->list, &bond->ipsec_list);
- spin_unlock_bh(&bond->ipsec_lock);
+ mutex_unlock(&bond->ipsec_lock);
} else {
kfree(ipsec);
}
- rcu_read_unlock();
+out:
+ netdev_put(real_dev, &tracker);
return err;
}
static void bond_ipsec_add_sa_all(struct bonding *bond)
{
struct net_device *bond_dev = bond->dev;
+ struct net_device *real_dev;
struct bond_ipsec *ipsec;
struct slave *slave;
- rcu_read_lock();
- slave = rcu_dereference(bond->curr_active_slave);
- if (!slave)
- goto out;
+ slave = rtnl_dereference(bond->curr_active_slave);
+ real_dev = slave ? slave->dev : NULL;
+ if (!real_dev)
+ return;
- if (!slave->dev->xfrmdev_ops ||
- !slave->dev->xfrmdev_ops->xdo_dev_state_add ||
- netif_is_bond_master(slave->dev)) {
- spin_lock_bh(&bond->ipsec_lock);
+ mutex_lock(&bond->ipsec_lock);
+ if (!real_dev->xfrmdev_ops ||
+ !real_dev->xfrmdev_ops->xdo_dev_state_add ||
+ netif_is_bond_master(real_dev)) {
if (!list_empty(&bond->ipsec_list))
- slave_warn(bond_dev, slave->dev,
+ slave_warn(bond_dev, real_dev,
"%s: no slave xdo_dev_state_add\n",
__func__);
- spin_unlock_bh(&bond->ipsec_lock);
goto out;
}
- spin_lock_bh(&bond->ipsec_lock);
list_for_each_entry(ipsec, &bond->ipsec_list, list) {
- ipsec->xs->xso.real_dev = slave->dev;
- if (slave->dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) {
- slave_warn(bond_dev, slave->dev, "%s: failed to add SA\n", __func__);
+ /* If new state is added before ipsec_lock acquired */
+ if (ipsec->xs->xso.real_dev == real_dev)
+ continue;
+
+ ipsec->xs->xso.real_dev = real_dev;
+ if (real_dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) {
+ slave_warn(bond_dev, real_dev, "%s: failed to add SA\n", __func__);
ipsec->xs->xso.real_dev = NULL;
}
}
- spin_unlock_bh(&bond->ipsec_lock);
out:
- rcu_read_unlock();
+ mutex_unlock(&bond->ipsec_lock);
}
/**
@@ -515,6 +523,8 @@ static void bond_ipsec_add_sa_all(struct bonding *bond)
static void bond_ipsec_del_sa(struct xfrm_state *xs)
{
struct net_device *bond_dev = xs->xso.dev;
+ struct net_device *real_dev;
+ netdevice_tracker tracker;
struct bond_ipsec *ipsec;
struct bonding *bond;
struct slave *slave;
@@ -525,6 +535,9 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs)
rcu_read_lock();
bond = netdev_priv(bond_dev);
slave = rcu_dereference(bond->curr_active_slave);
+ real_dev = slave ? slave->dev : NULL;
+ netdev_hold(real_dev, &tracker, GFP_ATOMIC);
+ rcu_read_unlock();
if (!slave)
goto out;
@@ -532,18 +545,19 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs)
if (!xs->xso.real_dev)
goto out;
- WARN_ON(xs->xso.real_dev != slave->dev);
+ WARN_ON(xs->xso.real_dev != real_dev);
- if (!slave->dev->xfrmdev_ops ||
- !slave->dev->xfrmdev_ops->xdo_dev_state_delete ||
- netif_is_bond_master(slave->dev)) {
- slave_warn(bond_dev, slave->dev, "%s: no slave xdo_dev_state_delete\n", __func__);
+ if (!real_dev->xfrmdev_ops ||
+ !real_dev->xfrmdev_ops->xdo_dev_state_delete ||
+ netif_is_bond_master(real_dev)) {
+ slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_delete\n", __func__);
goto out;
}
- slave->dev->xfrmdev_ops->xdo_dev_state_delete(xs);
+ real_dev->xfrmdev_ops->xdo_dev_state_delete(xs);
out:
- spin_lock_bh(&bond->ipsec_lock);
+ netdev_put(real_dev, &tracker);
+ mutex_lock(&bond->ipsec_lock);
list_for_each_entry(ipsec, &bond->ipsec_list, list) {
if (ipsec->xs == xs) {
list_del(&ipsec->list);
@@ -551,41 +565,72 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs)
break;
}
}
- spin_unlock_bh(&bond->ipsec_lock);
- rcu_read_unlock();
+ mutex_unlock(&bond->ipsec_lock);
}
static void bond_ipsec_del_sa_all(struct bonding *bond)
{
struct net_device *bond_dev = bond->dev;
+ struct net_device *real_dev;
struct bond_ipsec *ipsec;
struct slave *slave;
- rcu_read_lock();
- slave = rcu_dereference(bond->curr_active_slave);
- if (!slave) {
- rcu_read_unlock();
+ slave = rtnl_dereference(bond->curr_active_slave);
+ real_dev = slave ? slave->dev : NULL;
+ if (!real_dev)
return;
- }
- spin_lock_bh(&bond->ipsec_lock);
+ mutex_lock(&bond->ipsec_lock);
list_for_each_entry(ipsec, &bond->ipsec_list, list) {
if (!ipsec->xs->xso.real_dev)
continue;
- if (!slave->dev->xfrmdev_ops ||
- !slave->dev->xfrmdev_ops->xdo_dev_state_delete ||
- netif_is_bond_master(slave->dev)) {
- slave_warn(bond_dev, slave->dev,
+ if (!real_dev->xfrmdev_ops ||
+ !real_dev->xfrmdev_ops->xdo_dev_state_delete ||
+ netif_is_bond_master(real_dev)) {
+ slave_warn(bond_dev, real_dev,
"%s: no slave xdo_dev_state_delete\n",
__func__);
} else {
- slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
+ real_dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
+ if (real_dev->xfrmdev_ops->xdo_dev_state_free)
+ real_dev->xfrmdev_ops->xdo_dev_state_free(ipsec->xs);
}
- ipsec->xs->xso.real_dev = NULL;
}
- spin_unlock_bh(&bond->ipsec_lock);
+ mutex_unlock(&bond->ipsec_lock);
+}
+
+static void bond_ipsec_free_sa(struct xfrm_state *xs)
+{
+ struct net_device *bond_dev = xs->xso.dev;
+ struct net_device *real_dev;
+ netdevice_tracker tracker;
+ struct bonding *bond;
+ struct slave *slave;
+
+ if (!bond_dev)
+ return;
+
+ rcu_read_lock();
+ bond = netdev_priv(bond_dev);
+ slave = rcu_dereference(bond->curr_active_slave);
+ real_dev = slave ? slave->dev : NULL;
+ netdev_hold(real_dev, &tracker, GFP_ATOMIC);
rcu_read_unlock();
+
+ if (!slave)
+ goto out;
+
+ if (!xs->xso.real_dev)
+ goto out;
+
+ WARN_ON(xs->xso.real_dev != real_dev);
+
+ if (real_dev && real_dev->xfrmdev_ops &&
+ real_dev->xfrmdev_ops->xdo_dev_state_free)
+ real_dev->xfrmdev_ops->xdo_dev_state_free(xs);
+out:
+ netdev_put(real_dev, &tracker);
}
/**
@@ -599,39 +644,36 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
struct net_device *real_dev;
struct slave *curr_active;
struct bonding *bond;
- int err;
+ bool ok = false;
bond = netdev_priv(bond_dev);
rcu_read_lock();
curr_active = rcu_dereference(bond->curr_active_slave);
+ if (!curr_active)
+ goto out;
real_dev = curr_active->dev;
- if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
- err = false;
+ if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)
goto out;
- }
- if (!xs->xso.real_dev) {
- err = false;
+ if (!xs->xso.real_dev)
goto out;
- }
if (!real_dev->xfrmdev_ops ||
!real_dev->xfrmdev_ops->xdo_dev_offload_ok ||
- netif_is_bond_master(real_dev)) {
- err = false;
+ netif_is_bond_master(real_dev))
goto out;
- }
- err = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
+ ok = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
out:
rcu_read_unlock();
- return err;
+ return ok;
}
static const struct xfrmdev_ops bond_xfrmdev_ops = {
.xdo_dev_state_add = bond_ipsec_add_sa,
.xdo_dev_state_delete = bond_ipsec_del_sa,
+ .xdo_dev_state_free = bond_ipsec_free_sa,
.xdo_dev_offload_ok = bond_ipsec_offload_ok,
};
#endif /* CONFIG_XFRM_OFFLOAD */
@@ -5882,7 +5924,7 @@ void bond_setup(struct net_device *bond_dev)
/* set up xfrm device ops (only supported in active-backup right now) */
bond_dev->xfrmdev_ops = &bond_xfrmdev_ops;
INIT_LIST_HEAD(&bond->ipsec_list);
- spin_lock_init(&bond->ipsec_lock);
+ mutex_init(&bond->ipsec_lock);
#endif /* CONFIG_XFRM_OFFLOAD */
/* don't acquire bond device's netif_tx_lock when transmitting */
@@ -5931,6 +5973,10 @@ static void bond_uninit(struct net_device *bond_dev)
__bond_release_one(bond_dev, slave->dev, true, true);
netdev_info(bond_dev, "Released all slaves\n");
+#ifdef CONFIG_XFRM_OFFLOAD
+ mutex_destroy(&bond->ipsec_lock);
+#endif /* CONFIG_XFRM_OFFLOAD */
+
bond_set_slave_arr(bond, NULL, NULL);
list_del_rcu(&bond->bond_list);
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index bc80fb6..95d59a1 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -936,7 +936,7 @@ static int bond_option_active_slave_set(struct bonding *bond,
/* check to see if we are clearing active */
if (!slave_dev) {
netdev_dbg(bond->dev, "Clearing current active slave\n");
- RCU_INIT_POINTER(bond->curr_active_slave, NULL);
+ bond_change_active_slave(bond, NULL);
bond_select_active_slave(bond);
} else {
struct slave *old_active = rtnl_dereference(bond->curr_active_slave);
diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c
index f0bd46e..050f17c 100644
--- a/drivers/net/dsa/microchip/ksz_ptp.c
+++ b/drivers/net/dsa/microchip/ksz_ptp.c
@@ -266,7 +266,6 @@ static int ksz_ptp_enable_mode(struct ksz_device *dev)
struct ksz_port *prt;
struct dsa_port *dp;
bool tag_en = false;
- int ret;
dsa_switch_for_each_user_port(dp, dev->ds) {
prt = &dev->ports[dp->index];
@@ -277,9 +276,7 @@ static int ksz_ptp_enable_mode(struct ksz_device *dev)
}
if (tag_en) {
- ret = ptp_schedule_worker(ptp_data->clock, 0);
- if (ret)
- return ret;
+ ptp_schedule_worker(ptp_data->clock, 0);
} else {
ptp_cancel_worker_sync(ptp_data->clock);
}
diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c
index ce3b369..c47f068 100644
--- a/drivers/net/dsa/mv88e6xxx/global1_atu.c
+++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c
@@ -457,7 +457,8 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id)
trace_mv88e6xxx_atu_full_violation(chip->dev, spid,
entry.portvec, entry.mac,
fid);
- chip->ports[spid].atu_full_violation++;
+ if (spid < ARRAY_SIZE(chip->ports))
+ chip->ports[spid].atu_full_violation++;
}
return IRQ_HANDLED;
diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index e554699..4a705f7 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -61,11 +61,46 @@ static int felix_cpu_port_for_conduit(struct dsa_switch *ds,
return cpu_dp->index;
}
+/**
+ * felix_update_tag_8021q_rx_rule - Update VCAP ES0 tag_8021q rule after
+ * vlan_filtering change
+ * @outer_tagging_rule: Pointer to VCAP filter on which the update is performed
+ * @vlan_filtering: Current bridge VLAN filtering setting
+ *
+ * Source port identification for tag_8021q is done using VCAP ES0 rules on the
+ * CPU port(s). The ES0 tag B (inner tag from the packet) can be configured as
+ * either:
+ * - push_inner_tag=0: the inner tag is never pushed into the frame
+ * (and we lose info about the classified VLAN). This is
+ * good when the classified VLAN is a discardable quantity
+ * for the software RX path: it is either set to
+ * OCELOT_STANDALONE_PVID, or to
+ * ocelot_vlan_unaware_pvid(bridge).
+ * - push_inner_tag=1: the inner tag is always pushed. This is good when the
+ * classified VLAN is not a discardable quantity (the port
+ * is under a VLAN-aware bridge, and software needs to
+ * continue processing the packet in the same VLAN as the
+ * hardware).
+ * The point is that what is good for a VLAN-unaware port is not good for a
+ * VLAN-aware port, and vice versa. Thus, the RX tagging rules must be kept in
+ * sync with the VLAN filtering state of the port.
+ */
+static void
+felix_update_tag_8021q_rx_rule(struct ocelot_vcap_filter *outer_tagging_rule,
+ bool vlan_filtering)
+{
+ if (vlan_filtering)
+ outer_tagging_rule->action.push_inner_tag = OCELOT_ES0_TAG;
+ else
+ outer_tagging_rule->action.push_inner_tag = OCELOT_NO_ES0_TAG;
+}
+
/* Set up VCAP ES0 rules for pushing a tag_8021q VLAN towards the CPU such that
* the tagger can perform RX source port identification.
*/
static int felix_tag_8021q_vlan_add_rx(struct dsa_switch *ds, int port,
- int upstream, u16 vid)
+ int upstream, u16 vid,
+ bool vlan_filtering)
{
struct ocelot_vcap_filter *outer_tagging_rule;
struct ocelot *ocelot = ds->priv;
@@ -96,6 +131,14 @@ static int felix_tag_8021q_vlan_add_rx(struct dsa_switch *ds, int port,
outer_tagging_rule->action.tag_a_tpid_sel = OCELOT_TAG_TPID_SEL_8021AD;
outer_tagging_rule->action.tag_a_vid_sel = 1;
outer_tagging_rule->action.vid_a_val = vid;
+ felix_update_tag_8021q_rx_rule(outer_tagging_rule, vlan_filtering);
+ outer_tagging_rule->action.tag_b_tpid_sel = OCELOT_TAG_TPID_SEL_8021Q;
+ /* Leave TAG_B_VID_SEL at 0 (Classified VID + VID_B_VAL). Since we also
+ * leave VID_B_VAL at 0, this makes ES0 tag B (the inner tag) equal to
+ * the classified VID, which we need to see in the DSA tagger's receive
+ * path. Note: the inner tag is only visible in the packet when pushed
+ * (push_inner_tag == OCELOT_ES0_TAG).
+ */
err = ocelot_vcap_filter_add(ocelot, outer_tagging_rule, NULL);
if (err)
@@ -227,6 +270,7 @@ static int felix_tag_8021q_vlan_del_tx(struct dsa_switch *ds, int port, u16 vid)
static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid,
u16 flags)
{
+ struct dsa_port *dp = dsa_to_port(ds, port);
struct dsa_port *cpu_dp;
int err;
@@ -234,11 +278,12 @@ static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid,
* membership, which we aren't. So we don't need to add any VCAP filter
* for the CPU port.
*/
- if (!dsa_is_user_port(ds, port))
+ if (!dsa_port_is_user(dp))
return 0;
dsa_switch_for_each_cpu_port(cpu_dp, ds) {
- err = felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid);
+ err = felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid,
+ dsa_port_is_vlan_filtering(dp));
if (err)
return err;
}
@@ -258,10 +303,11 @@ static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid,
static int felix_tag_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid)
{
+ struct dsa_port *dp = dsa_to_port(ds, port);
struct dsa_port *cpu_dp;
int err;
- if (!dsa_is_user_port(ds, port))
+ if (!dsa_port_is_user(dp))
return 0;
dsa_switch_for_each_cpu_port(cpu_dp, ds) {
@@ -278,11 +324,41 @@ static int felix_tag_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid)
del_tx_failed:
dsa_switch_for_each_cpu_port(cpu_dp, ds)
- felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid);
+ felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid,
+ dsa_port_is_vlan_filtering(dp));
return err;
}
+static int felix_update_tag_8021q_rx_rules(struct dsa_switch *ds, int port,
+ bool vlan_filtering)
+{
+ struct ocelot_vcap_filter *outer_tagging_rule;
+ struct ocelot_vcap_block *block_vcap_es0;
+ struct ocelot *ocelot = ds->priv;
+ struct dsa_port *cpu_dp;
+ unsigned long cookie;
+ int err;
+
+ block_vcap_es0 = &ocelot->block[VCAP_ES0];
+
+ dsa_switch_for_each_cpu_port(cpu_dp, ds) {
+ cookie = OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port,
+ cpu_dp->index);
+
+ outer_tagging_rule = ocelot_vcap_block_find_filter_by_id(block_vcap_es0,
+ cookie, false);
+
+ felix_update_tag_8021q_rx_rule(outer_tagging_rule, vlan_filtering);
+
+ err = ocelot_vcap_filter_replace(ocelot, outer_tagging_rule);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
static int felix_trap_get_cpu_port(struct dsa_switch *ds,
const struct ocelot_vcap_filter *trap)
{
@@ -528,7 +604,19 @@ static int felix_tag_8021q_setup(struct dsa_switch *ds)
* so we need to be careful that there are no extra frames to be
* dequeued over MMIO, since we would never know to discard them.
*/
+ ocelot_lock_xtr_grp_bh(ocelot, 0);
ocelot_drain_cpu_queue(ocelot, 0);
+ ocelot_unlock_xtr_grp_bh(ocelot, 0);
+
+ /* Problem: when using push_inner_tag=1 for ES0 tag B, we lose info
+ * about whether the received packets were VLAN-tagged on the wire,
+ * since they are always tagged on egress towards the CPU port.
+ *
+ * Since using push_inner_tag=1 is unavoidable for VLAN-aware bridges,
+ * we must work around the fallout by untagging in software to make
+ * untagged reception work more or less as expected.
+ */
+ ds->untag_vlan_aware_bridge_pvid = true;
return 0;
}
@@ -554,6 +642,8 @@ static void felix_tag_8021q_teardown(struct dsa_switch *ds)
ocelot_port_teardown_dsa_8021q_cpu(ocelot, dp->index);
dsa_tag_8021q_unregister(ds);
+
+ ds->untag_vlan_aware_bridge_pvid = false;
}
static unsigned long felix_tag_8021q_get_host_fwd_mask(struct dsa_switch *ds)
@@ -1008,8 +1098,23 @@ static int felix_vlan_filtering(struct dsa_switch *ds, int port, bool enabled,
struct netlink_ext_ack *extack)
{
struct ocelot *ocelot = ds->priv;
+ bool using_tag_8021q;
+ struct felix *felix;
+ int err;
- return ocelot_port_vlan_filtering(ocelot, port, enabled, extack);
+ err = ocelot_port_vlan_filtering(ocelot, port, enabled, extack);
+ if (err)
+ return err;
+
+ felix = ocelot_to_felix(ocelot);
+ using_tag_8021q = felix->tag_proto == DSA_TAG_PROTO_OCELOT_8021Q;
+ if (using_tag_8021q) {
+ err = felix_update_tag_8021q_rx_rules(ds, port, enabled);
+ if (err)
+ return err;
+ }
+
+ return 0;
}
static int felix_vlan_add(struct dsa_switch *ds, int port,
@@ -1518,6 +1623,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work)
int port = xmit_work->dp->index;
int retries = 10;
+ ocelot_lock_inj_grp(ocelot, 0);
+
do {
if (ocelot_can_inject(ocelot, 0))
break;
@@ -1526,6 +1633,7 @@ static void felix_port_deferred_xmit(struct kthread_work *work)
} while (--retries);
if (!retries) {
+ ocelot_unlock_inj_grp(ocelot, 0);
dev_err(ocelot->dev, "port %d failed to inject skb\n",
port);
ocelot_port_purge_txtstamp_skb(ocelot, port, skb);
@@ -1535,6 +1643,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work)
ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb);
+ ocelot_unlock_inj_grp(ocelot, 0);
+
consume_skb(skb);
kfree(xmit_work);
}
@@ -1694,6 +1804,8 @@ static bool felix_check_xtr_pkt(struct ocelot *ocelot)
if (!felix->info->quirk_no_xtr_irq)
return false;
+ ocelot_lock_xtr_grp(ocelot, grp);
+
while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) {
struct sk_buff *skb;
unsigned int type;
@@ -1730,6 +1842,8 @@ static bool felix_check_xtr_pkt(struct ocelot *ocelot)
ocelot_drain_cpu_queue(ocelot, 0);
}
+ ocelot_unlock_xtr_grp(ocelot, grp);
+
return true;
}
diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c
index d9d3e30..e3f95d2 100644
--- a/drivers/net/dsa/vitesse-vsc73xx-core.c
+++ b/drivers/net/dsa/vitesse-vsc73xx-core.c
@@ -40,6 +40,10 @@
#define VSC73XX_BLOCK_ARBITER 0x5 /* Only subblock 0 */
#define VSC73XX_BLOCK_SYSTEM 0x7 /* Only subblock 0 */
+/* MII Block subblock */
+#define VSC73XX_BLOCK_MII_INTERNAL 0x0 /* Internal MDIO subblock */
+#define VSC73XX_BLOCK_MII_EXTERNAL 0x1 /* External MDIO subblock */
+
#define CPU_PORT 6 /* CPU port */
/* MAC Block registers */
@@ -225,6 +229,8 @@
#define VSC73XX_MII_CMD 0x1
#define VSC73XX_MII_DATA 0x2
+#define VSC73XX_MII_STAT_BUSY BIT(3)
+
/* Arbiter block 5 registers */
#define VSC73XX_ARBEMPTY 0x0c
#define VSC73XX_ARBDISC 0x0e
@@ -299,6 +305,7 @@
#define IS_739X(a) (IS_7395(a) || IS_7398(a))
#define VSC73XX_POLL_SLEEP_US 1000
+#define VSC73XX_MDIO_POLL_SLEEP_US 5
#define VSC73XX_POLL_TIMEOUT_US 10000
struct vsc73xx_counter {
@@ -527,6 +534,22 @@ static int vsc73xx_detect(struct vsc73xx *vsc)
return 0;
}
+static int vsc73xx_mdio_busy_check(struct vsc73xx *vsc)
+{
+ int ret, err;
+ u32 val;
+
+ ret = read_poll_timeout(vsc73xx_read, err,
+ err < 0 || !(val & VSC73XX_MII_STAT_BUSY),
+ VSC73XX_MDIO_POLL_SLEEP_US,
+ VSC73XX_POLL_TIMEOUT_US, false, vsc,
+ VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL,
+ VSC73XX_MII_STAT, &val);
+ if (ret)
+ return ret;
+ return err;
+}
+
static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum)
{
struct vsc73xx *vsc = ds->priv;
@@ -534,12 +557,20 @@ static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum)
u32 val;
int ret;
+ ret = vsc73xx_mdio_busy_check(vsc);
+ if (ret)
+ return ret;
+
/* Setting bit 26 means "read" */
cmd = BIT(26) | (phy << 21) | (regnum << 16);
ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd);
if (ret)
return ret;
- msleep(2);
+
+ ret = vsc73xx_mdio_busy_check(vsc);
+ if (ret)
+ return ret;
+
ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MII, 0, 2, &val);
if (ret)
return ret;
@@ -563,18 +594,11 @@ static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum,
u32 cmd;
int ret;
- /* It was found through tedious experiments that this router
- * chip really hates to have it's PHYs reset. They
- * never recover if that happens: autonegotiation stops
- * working after a reset. Just filter out this command.
- * (Resetting the whole chip is OK.)
- */
- if (regnum == 0 && (val & BIT(15))) {
- dev_info(vsc->dev, "reset PHY - disallowed\n");
- return 0;
- }
+ ret = vsc73xx_mdio_busy_check(vsc);
+ if (ret)
+ return ret;
- cmd = (phy << 21) | (regnum << 16);
+ cmd = (phy << 21) | (regnum << 16) | val;
ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd);
if (ret)
return ret;
@@ -957,6 +981,11 @@ static void vsc73xx_mac_link_up(struct phylink_config *config,
if (duplex == DUPLEX_FULL)
val |= VSC73XX_MAC_CFG_FDX;
+ else
+ /* In datasheet description ("Port Mode Procedure" in 5.6.2)
+ * this bit is configured only for half duplex.
+ */
+ val |= VSC73XX_MAC_CFG_WEXC_DIS;
/* This routine is described in the datasheet (below ARBDISC register
* description)
@@ -967,7 +996,6 @@ static void vsc73xx_mac_link_up(struct phylink_config *config,
get_random_bytes(&seed, 1);
val |= seed << VSC73XX_MAC_CFG_SEED_OFFSET;
val |= VSC73XX_MAC_CFG_SEED_LOAD;
- val |= VSC73XX_MAC_CFG_WEXC_DIS;
/* Those bits are responsible for MTU only. Kernel takes care about MTU,
* let's enable +8 bytes frame length unconditionally.
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index e27e108..04a623b3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5056,7 +5056,7 @@ void bnxt_del_one_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr)
list_del_init(&fltr->list);
}
-void bnxt_clear_usr_fltrs(struct bnxt *bp, bool all)
+static void bnxt_clear_usr_fltrs(struct bnxt *bp, bool all)
{
struct bnxt_filter_base *usr_fltr, *tmp;
@@ -10248,7 +10248,7 @@ static void bnxt_hwrm_realloc_rss_ctx_vnic(struct bnxt *bp)
}
}
-void bnxt_clear_rss_ctxs(struct bnxt *bp)
+static void bnxt_clear_rss_ctxs(struct bnxt *bp)
{
struct ethtool_rxfh_context *ctx;
unsigned long context;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 6bbdc71..059a6f8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2790,7 +2790,6 @@ void bnxt_set_ring_params(struct bnxt *);
int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode);
void bnxt_insert_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr);
void bnxt_del_one_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr);
-void bnxt_clear_usr_fltrs(struct bnxt *bp, bool all);
int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap,
int bmap_size, bool async_only);
int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp);
@@ -2842,7 +2841,6 @@ int bnxt_hwrm_vnic_rss_cfg_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic);
int __bnxt_setup_vnic_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic);
void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
bool all);
-void bnxt_clear_rss_ctxs(struct bnxt *bp);
int bnxt_open_nic(struct bnxt *, bool, bool);
int bnxt_half_open_nic(struct bnxt *bp);
void bnxt_half_close_nic(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 9dadc89..4cf9bf8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -968,9 +968,6 @@ static int bnxt_set_channels(struct net_device *dev,
return -EINVAL;
}
- bnxt_clear_usr_fltrs(bp, true);
- if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
- bnxt_clear_rss_ctxs(bp);
if (netif_running(dev)) {
if (BNXT_PF(bp)) {
/* TODO CHIMP_FW: Send message to all VF's
@@ -2000,7 +1997,6 @@ static int bnxt_set_rxfh(struct net_device *dev,
bnxt_modify_rss(bp, NULL, NULL, rxfh);
- bnxt_clear_usr_fltrs(bp, false);
if (netif_running(bp->dev)) {
bnxt_close_nic(bp, false, false);
rc = bnxt_open_nic(bp, false, false);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 345681d..f88b641 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -297,11 +297,6 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
* redirect is coming from a frame received by the
* bnxt_en driver.
*/
- rx_buf = &rxr->rx_buf_ring[cons];
- mapping = rx_buf->mapping - bp->rx_dma_offset;
- dma_unmap_page_attrs(&pdev->dev, mapping,
- BNXT_RX_PAGE_SIZE, bp->rx_dir,
- DMA_ATTR_WEAK_ORDERING);
/* if we are unable to allocate a new buffer, abort and reuse */
if (bnxt_alloc_rx_data(bp, rxr, rxr->rx_prod, GFP_ATOMIC)) {
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 11665be..dcd3f54 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -5250,8 +5250,8 @@ static int __maybe_unused macb_suspend(struct device *dev)
if (bp->wol & MACB_WOL_ENABLED) {
/* Check for IP address in WOL ARP mode */
idev = __in_dev_get_rcu(bp->dev);
- if (idev && idev->ifa_list)
- ifa = rcu_access_pointer(idev->ifa_list);
+ if (idev)
+ ifa = rcu_dereference(idev->ifa_list);
if ((bp->wolopts & WAKE_ARP) && !ifa) {
netdev_err(netdev, "IP address not assigned as required by WoL walk ARP\n");
return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index a40c266..608cc6a 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -1054,18 +1054,12 @@ static int phy_interface_mode(u8 lmac_type)
static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
{
- struct lmac *lmac, **priv;
+ struct lmac *lmac;
u64 cfg;
lmac = &bgx->lmac[lmacid];
lmac->bgx = bgx;
- lmac->netdev = alloc_netdev_dummy(sizeof(struct lmac *));
- if (!lmac->netdev)
- return -ENOMEM;
- priv = netdev_priv(lmac->netdev);
- *priv = lmac;
-
if ((lmac->lmac_type == BGX_MODE_SGMII) ||
(lmac->lmac_type == BGX_MODE_QSGMII) ||
(lmac->lmac_type == BGX_MODE_RGMII)) {
@@ -1191,7 +1185,6 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
(lmac->lmac_type != BGX_MODE_10G_KR) && lmac->phydev)
phy_disconnect(lmac->phydev);
- free_netdev(lmac->netdev);
lmac->phydev = NULL;
}
@@ -1653,6 +1646,23 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
bgx_get_qlm_mode(bgx);
+ for (lmac = 0; lmac < bgx->lmac_count; lmac++) {
+ struct lmac *lmacp, **priv;
+
+ lmacp = &bgx->lmac[lmac];
+ lmacp->netdev = alloc_netdev_dummy(sizeof(struct lmac *));
+
+ if (!lmacp->netdev) {
+ for (int i = 0; i < lmac; i++)
+ free_netdev(bgx->lmac[i].netdev);
+ err = -ENOMEM;
+ goto err_enable;
+ }
+
+ priv = netdev_priv(lmacp->netdev);
+ *priv = lmacp;
+ }
+
err = bgx_init_phy(bgx);
if (err)
goto err_enable;
@@ -1692,8 +1702,10 @@ static void bgx_remove(struct pci_dev *pdev)
u8 lmac;
/* Disable all LMACs */
- for (lmac = 0; lmac < bgx->lmac_count; lmac++)
+ for (lmac = 0; lmac < bgx->lmac_count; lmac++) {
bgx_lmac_disable(bgx, lmac);
+ free_netdev(bgx->lmac[lmac].netdev);
+ }
pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index 786ceae..dd9e684 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -1244,7 +1244,8 @@ static u64 hash_filter_ntuple(struct ch_filter_specification *fs,
* in the Compressed Filter Tuple.
*/
if (tp->vlan_shift >= 0 && fs->mask.ivlan)
- ntuple |= (FT_VLAN_VLD_F | fs->val.ivlan) << tp->vlan_shift;
+ ntuple |= (u64)(FT_VLAN_VLD_F |
+ fs->val.ivlan) << tp->vlan_shift;
if (tp->port_shift >= 0 && fs->mask.iport)
ntuple |= (u64)fs->val.iport << tp->port_shift;
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index fddfd1d..4c546c3 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -572,7 +572,7 @@ static bool ftgmac100_rx_packet(struct ftgmac100 *priv, int *processed)
(*processed)++;
return true;
- drop:
+drop:
/* Clean rxdes0 (which resets own bit) */
rxdes->rxdes0 = cpu_to_le32(status & priv->rxdes0_edorr_mask);
priv->rx_pointer = ftgmac100_next_rx_pointer(priv, pointer);
@@ -656,6 +656,11 @@ static bool ftgmac100_tx_complete_packet(struct ftgmac100 *priv)
ftgmac100_free_tx_packet(priv, pointer, skb, txdes, ctl_stat);
txdes->txdes0 = cpu_to_le32(ctl_stat & priv->txdes0_edotr_mask);
+ /* Ensure the descriptor config is visible before setting the tx
+ * pointer.
+ */
+ smp_wmb();
+
priv->tx_clean_pointer = ftgmac100_next_tx_pointer(priv, pointer);
return true;
@@ -809,6 +814,11 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb,
dma_wmb();
first->txdes0 = cpu_to_le32(f_ctl_stat);
+ /* Ensure the descriptor config is visible before setting the tx
+ * pointer.
+ */
+ smp_wmb();
+
/* Update next TX pointer */
priv->tx_pointer = pointer;
@@ -829,7 +839,7 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb,
return NETDEV_TX_OK;
- dma_err:
+dma_err:
if (net_ratelimit())
netdev_err(netdev, "map tx fragment failed\n");
@@ -851,7 +861,7 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb,
* last fragment, so we know ftgmac100_free_tx_packet()
* hasn't freed the skb yet.
*/
- drop:
+drop:
/* Drop the packet */
dev_kfree_skb_any(skb);
netdev->stats.tx_dropped++;
@@ -1344,7 +1354,7 @@ static void ftgmac100_reset(struct ftgmac100 *priv)
ftgmac100_init_all(priv, true);
netdev_dbg(netdev, "Reset done !\n");
- bail:
+bail:
if (priv->mii_bus)
mutex_unlock(&priv->mii_bus->mdio_lock);
if (netdev->phydev)
@@ -1543,15 +1553,15 @@ static int ftgmac100_open(struct net_device *netdev)
return 0;
- err_ncsi:
+err_ncsi:
napi_disable(&priv->napi);
netif_stop_queue(netdev);
- err_alloc:
+err_alloc:
ftgmac100_free_buffers(priv);
free_irq(netdev->irq, netdev);
- err_irq:
+err_irq:
netif_napi_del(&priv->napi);
- err_hw:
+err_hw:
iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
ftgmac100_free_rings(priv);
return err;
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index a71f848..a293b08 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -2638,13 +2638,14 @@ static int dpaa2_switch_refill_bp(struct ethsw_core *ethsw)
static int dpaa2_switch_seed_bp(struct ethsw_core *ethsw)
{
- int *count, i;
+ int *count, ret, i;
for (i = 0; i < DPAA2_ETHSW_NUM_BUFS; i += BUFS_PER_CMD) {
+ ret = dpaa2_switch_add_bufs(ethsw, ethsw->bpid);
count = ðsw->buf_count;
- *count += dpaa2_switch_add_bufs(ethsw, ethsw->bpid);
+ *count += ret;
- if (unlikely(*count < BUFS_PER_CMD))
+ if (unlikely(ret < BUFS_PER_CMD))
return -ENOMEM;
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index a5fc020..4cbc4d0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -5724,6 +5724,9 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
struct net_device *netdev = handle->kinfo.netdev;
struct hns3_nic_priv *priv = netdev_priv(netdev);
+ if (!test_bit(HNS3_NIC_STATE_DOWN, &priv->state))
+ hns3_nic_net_stop(netdev);
+
if (!test_and_clear_bit(HNS3_NIC_STATE_INITED, &priv->state)) {
netdev_warn(netdev, "already uninitialized\n");
return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index e132c2f..cc7f46c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -1598,8 +1598,7 @@ static void hclge_query_reg_info_of_ssu(struct hclge_dev *hdev)
{
u32 loop_para[HCLGE_MOD_MSG_PARA_ARRAY_MAX_SIZE] = {0};
struct hclge_mod_reg_common_msg msg;
- u8 i, j, num;
- u32 loop_time;
+ u8 i, j, num, loop_time;
num = ARRAY_SIZE(hclge_ssu_reg_common_msg);
for (i = 0; i < num; i++) {
@@ -1609,7 +1608,8 @@ static void hclge_query_reg_info_of_ssu(struct hclge_dev *hdev)
loop_time = 1;
loop_para[0] = 0;
if (msg.need_para) {
- loop_time = hdev->ae_dev->dev_specs.tnl_num;
+ loop_time = min(hdev->ae_dev->dev_specs.tnl_num,
+ HCLGE_MOD_MSG_PARA_ARRAY_MAX_SIZE);
for (j = 0; j < loop_time; j++)
loop_para[j] = j + 1;
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 82574ce..6c33195 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2653,8 +2653,17 @@ static int hclge_cfg_mac_speed_dup_h(struct hnae3_handle *handle, int speed,
{
struct hclge_vport *vport = hclge_get_vport(handle);
struct hclge_dev *hdev = vport->back;
+ int ret;
- return hclge_cfg_mac_speed_dup(hdev, speed, duplex, lane_num);
+ ret = hclge_cfg_mac_speed_dup(hdev, speed, duplex, lane_num);
+
+ if (ret)
+ return ret;
+
+ hdev->hw.mac.req_speed = speed;
+ hdev->hw.mac.req_duplex = duplex;
+
+ return 0;
}
static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable)
@@ -2956,17 +2965,20 @@ static int hclge_mac_init(struct hclge_dev *hdev)
if (!test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state))
hdev->hw.mac.duplex = HCLGE_MAC_FULL;
- ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed,
- hdev->hw.mac.duplex, hdev->hw.mac.lane_num);
- if (ret)
- return ret;
-
if (hdev->hw.mac.support_autoneg) {
ret = hclge_set_autoneg_en(hdev, hdev->hw.mac.autoneg);
if (ret)
return ret;
}
+ if (!hdev->hw.mac.autoneg) {
+ ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.req_speed,
+ hdev->hw.mac.req_duplex,
+ hdev->hw.mac.lane_num);
+ if (ret)
+ return ret;
+ }
+
mac->link = 0;
if (mac->user_fec_mode & BIT(HNAE3_FEC_USER_DEF)) {
@@ -11444,7 +11456,7 @@ static void hclge_pci_uninit(struct hclge_dev *hdev)
pcim_iounmap(pdev, hdev->hw.hw.io_base);
pci_free_irq_vectors(pdev);
- pci_release_mem_regions(pdev);
+ pci_release_regions(pdev);
pci_disable_device(pdev);
}
@@ -11516,8 +11528,8 @@ static void hclge_reset_done(struct hnae3_ae_dev *ae_dev)
dev_err(&hdev->pdev->dev, "fail to rebuild, ret=%d\n", ret);
hdev->reset_type = HNAE3_NONE_RESET;
- clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state);
- up(&hdev->reset_sem);
+ if (test_and_clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state))
+ up(&hdev->reset_sem);
}
static void hclge_clear_resetting_state(struct hclge_dev *hdev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index 85fb11d..8007965 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -191,6 +191,9 @@ static void hclge_mac_adjust_link(struct net_device *netdev)
if (ret)
netdev_err(netdev, "failed to adjust link.\n");
+ hdev->hw.mac.req_speed = (u32)speed;
+ hdev->hw.mac.req_duplex = (u8)duplex;
+
ret = hclge_cfg_flowctrl(hdev);
if (ret)
netdev_err(netdev, "failed to configure flow control.\n");
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 3735d2f..094a7c7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1747,8 +1747,8 @@ static void hclgevf_reset_done(struct hnae3_ae_dev *ae_dev)
ret);
hdev->reset_type = HNAE3_NONE_RESET;
- clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state);
- up(&hdev->reset_sem);
+ if (test_and_clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state))
+ up(&hdev->reset_sem);
}
static u32 hclgevf_get_fw_version(struct hnae3_handle *handle)
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
index 00fed5a..62ef8e2 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
@@ -337,7 +337,7 @@ int ice_devlink_create_pf_port(struct ice_pf *pf)
return -EIO;
attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
- attrs.phys.port_number = pf->hw.bus.func;
+ attrs.phys.port_number = pf->hw.pf_id;
/* As FW supports only port split options for whole device,
* set port split options only for first PF.
@@ -455,7 +455,7 @@ int ice_devlink_create_vf_port(struct ice_vf *vf)
return -EINVAL;
attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF;
- attrs.pci_vf.pf = pf->hw.bus.func;
+ attrs.pci_vf.pf = pf->hw.pf_id;
attrs.pci_vf.vf = vf->vf_id;
ice_devlink_set_switch_id(pf, &attrs.switch_id);
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 1facf17..f448d3a 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -513,6 +513,25 @@ static void ice_xsk_pool_fill_cb(struct ice_rx_ring *ring)
}
/**
+ * ice_get_frame_sz - calculate xdp_buff::frame_sz
+ * @rx_ring: the ring being configured
+ *
+ * Return frame size based on underlying PAGE_SIZE
+ */
+static unsigned int ice_get_frame_sz(struct ice_rx_ring *rx_ring)
+{
+ unsigned int frame_sz;
+
+#if (PAGE_SIZE >= 8192)
+ frame_sz = rx_ring->rx_buf_len;
+#else
+ frame_sz = ice_rx_pg_size(rx_ring) / 2;
+#endif
+
+ return frame_sz;
+}
+
+/**
* ice_vsi_cfg_rxq - Configure an Rx queue
* @ring: the ring being configured
*
@@ -576,7 +595,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
}
}
- xdp_init_buff(&ring->xdp, ice_rx_pg_size(ring) / 2, &ring->xdp_rxq);
+ xdp_init_buff(&ring->xdp, ice_get_frame_sz(ring), &ring->xdp_rxq);
ring->xdp.data = NULL;
ring->xdp_ext.pkt_ctx = &ring->pkt_ctx;
err = ice_setup_rx_ctx(ring);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 8d25b69..c9bc3f1 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -522,30 +522,6 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
}
/**
- * ice_rx_frame_truesize
- * @rx_ring: ptr to Rx ring
- * @size: size
- *
- * calculate the truesize with taking into the account PAGE_SIZE of
- * underlying arch
- */
-static unsigned int
-ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size)
-{
- unsigned int truesize;
-
-#if (PAGE_SIZE < 8192)
- truesize = ice_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */
-#else
- truesize = rx_ring->rx_offset ?
- SKB_DATA_ALIGN(rx_ring->rx_offset + size) +
- SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
- SKB_DATA_ALIGN(size);
-#endif
- return truesize;
-}
-
-/**
* ice_run_xdp - Executes an XDP program on initialized xdp_buff
* @rx_ring: Rx ring
* @xdp: xdp_buff used as input to the XDP program
@@ -837,16 +813,15 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf)
if (!dev_page_is_reusable(page))
return false;
-#if (PAGE_SIZE < 8192)
/* if we are only owner of page we can reuse it */
if (unlikely(rx_buf->pgcnt - pagecnt_bias > 1))
return false;
-#else
+#if (PAGE_SIZE >= 8192)
#define ICE_LAST_OFFSET \
- (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_2048)
+ (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_3072)
if (rx_buf->page_offset > ICE_LAST_OFFSET)
return false;
-#endif /* PAGE_SIZE < 8192) */
+#endif /* PAGE_SIZE >= 8192) */
/* If we have drained the page fragment pool we need to update
* the pagecnt_bias and page count so that we fully restock the
@@ -949,12 +924,7 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
struct ice_rx_buf *rx_buf;
rx_buf = &rx_ring->rx_buf[ntc];
- rx_buf->pgcnt =
-#if (PAGE_SIZE < 8192)
- page_count(rx_buf->page);
-#else
- 0;
-#endif
+ rx_buf->pgcnt = page_count(rx_buf->page);
prefetchw(rx_buf->page);
if (!size)
@@ -1160,11 +1130,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
bool failure;
u32 first;
- /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
-#if (PAGE_SIZE < 8192)
- xdp->frame_sz = ice_rx_frame_truesize(rx_ring, 0);
-#endif
-
xdp_prog = READ_ONCE(rx_ring->xdp_prog);
if (xdp_prog) {
xdp_ring = rx_ring->xdp_ring;
@@ -1223,10 +1188,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
hard_start = page_address(rx_buf->page) + rx_buf->page_offset -
offset;
xdp_prepare_buff(xdp, hard_start, offset, size, !!offset);
-#if (PAGE_SIZE > 4096)
- /* At larger PAGE_SIZE, frame_sz depend on len size */
- xdp->frame_sz = ice_rx_frame_truesize(rx_ring, size);
-#endif
xdp_buff_clear_frags_flag(xdp);
} else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) {
break;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 11be39f..33a42b4 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -4808,6 +4808,7 @@ static void igb_set_rx_buffer_len(struct igb_adapter *adapter,
#if (PAGE_SIZE < 8192)
if (adapter->max_frame_size > IGB_MAX_FRAME_BUILD_SKB ||
+ IGB_2K_TOO_SMALL_WITH_PADDING ||
rd32(E1000_RCTL) & E1000_RCTL_SBP)
set_ring_uses_large_buffer(rx_ring);
#endif
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 5f92b3c..511384f 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -404,6 +404,12 @@
#define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */
#define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */
+/* Retry Buffer Control */
+#define IGC_RETX_CTL 0x041C
+#define IGC_RETX_CTL_WATERMARK_MASK 0xF
+#define IGC_RETX_CTL_QBVFULLTH_SHIFT 8 /* QBV Retry Buffer Full Threshold */
+#define IGC_RETX_CTL_QBVFULLEN 0x1000 /* Enable QBV Retry Buffer Full Threshold */
+
/* Transmit Scheduling Latency */
/* Latency between transmission scheduling (LaunchTime) and the time
* the packet is transmitted to the network in nanosecond.
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 8daf938..dfd6c00 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -6315,12 +6315,16 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
if (!validate_schedule(adapter, qopt))
return -EINVAL;
+ igc_ptp_read(adapter, &now);
+
+ if (igc_tsn_is_taprio_activated_by_user(adapter) &&
+ is_base_time_past(qopt->base_time, &now))
+ adapter->qbv_config_change_errors++;
+
adapter->cycle_time = qopt->cycle_time;
adapter->base_time = qopt->base_time;
adapter->taprio_offload_enable = true;
- igc_ptp_read(adapter, &now);
-
for (n = 0; n < qopt->num_entries; n++) {
struct tc_taprio_sched_entry *e = &qopt->entries[n];
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c
index 22cefb1..d68fa7f 100644
--- a/drivers/net/ethernet/intel/igc/igc_tsn.c
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.c
@@ -49,12 +49,19 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter)
return new_flags;
}
+static bool igc_tsn_is_tx_mode_in_tsn(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+
+ return !!(rd32(IGC_TQAVCTRL) & IGC_TQAVCTRL_TRANSMIT_MODE_TSN);
+}
+
void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter)
{
struct igc_hw *hw = &adapter->hw;
u16 txoffset;
- if (!is_any_launchtime(adapter))
+ if (!igc_tsn_is_tx_mode_in_tsn(adapter))
return;
switch (adapter->link_speed) {
@@ -78,6 +85,23 @@ void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter)
wr32(IGC_GTXOFFSET, txoffset);
}
+static void igc_tsn_restore_retx_default(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+ u32 retxctl;
+
+ retxctl = rd32(IGC_RETX_CTL) & IGC_RETX_CTL_WATERMARK_MASK;
+ wr32(IGC_RETX_CTL, retxctl);
+}
+
+bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+
+ return (rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) &&
+ adapter->taprio_offload_enable;
+}
+
/* Returns the TSN specific registers to their default values after
* the adapter is reset.
*/
@@ -91,6 +115,9 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter)
wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT);
wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT);
+ if (igc_is_device_id_i226(hw))
+ igc_tsn_restore_retx_default(adapter);
+
tqavctrl = rd32(IGC_TQAVCTRL);
tqavctrl &= ~(IGC_TQAVCTRL_TRANSMIT_MODE_TSN |
IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS);
@@ -111,6 +138,25 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter)
return 0;
}
+/* To partially fix i226 HW errata, reduce MAC internal buffering from 192 Bytes
+ * to 88 Bytes by setting RETX_CTL register using the recommendation from:
+ * a) Ethernet Controller I225/I226 Specification Update Rev 2.1
+ * Item 9: TSN: Packet Transmission Might Cross the Qbv Window
+ * b) I225/6 SW User Manual Rev 1.2.4: Section 8.11.5 Retry Buffer Control
+ */
+static void igc_tsn_set_retx_qbvfullthreshold(struct igc_adapter *adapter)
+{
+ struct igc_hw *hw = &adapter->hw;
+ u32 retxctl, watermark;
+
+ retxctl = rd32(IGC_RETX_CTL);
+ watermark = retxctl & IGC_RETX_CTL_WATERMARK_MASK;
+ /* Set QBVFULLTH value using watermark and set QBVFULLEN */
+ retxctl |= (watermark << IGC_RETX_CTL_QBVFULLTH_SHIFT) |
+ IGC_RETX_CTL_QBVFULLEN;
+ wr32(IGC_RETX_CTL, retxctl);
+}
+
static int igc_tsn_enable_offload(struct igc_adapter *adapter)
{
struct igc_hw *hw = &adapter->hw;
@@ -123,6 +169,9 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter)
wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_TSN);
wr32(IGC_TXPBS, IGC_TXPBSIZE_TSN);
+ if (igc_is_device_id_i226(hw))
+ igc_tsn_set_retx_qbvfullthreshold(adapter);
+
for (i = 0; i < adapter->num_tx_queues; i++) {
struct igc_ring *ring = adapter->tx_ring[i];
u32 txqctl = 0;
@@ -262,14 +311,6 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter)
s64 n = div64_s64(ktime_sub_ns(systim, base_time), cycle);
base_time = ktime_add_ns(base_time, (n + 1) * cycle);
-
- /* Increase the counter if scheduling into the past while
- * Gate Control List (GCL) is running.
- */
- if ((rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) &&
- (adapter->tc_setup_type == TC_SETUP_QDISC_TAPRIO) &&
- (adapter->qbv_count > 1))
- adapter->qbv_config_change_errors++;
} else {
if (igc_is_device_id_i226(hw)) {
ktime_t adjust_time, expires_time;
@@ -331,15 +372,22 @@ int igc_tsn_reset(struct igc_adapter *adapter)
return err;
}
+static bool igc_tsn_will_tx_mode_change(struct igc_adapter *adapter)
+{
+ bool any_tsn_enabled = !!(igc_tsn_new_flags(adapter) &
+ IGC_FLAG_TSN_ANY_ENABLED);
+
+ return (any_tsn_enabled && !igc_tsn_is_tx_mode_in_tsn(adapter)) ||
+ (!any_tsn_enabled && igc_tsn_is_tx_mode_in_tsn(adapter));
+}
+
int igc_tsn_offload_apply(struct igc_adapter *adapter)
{
- struct igc_hw *hw = &adapter->hw;
-
- /* Per I225/6 HW Design Section 7.5.2.1, transmit mode
- * cannot be changed dynamically. Require reset the adapter.
+ /* Per I225/6 HW Design Section 7.5.2.1 guideline, if tx mode change
+ * from legacy->tsn or tsn->legacy, then reset adapter is needed.
*/
if (netif_running(adapter->netdev) &&
- (igc_is_device_id_i225(hw) || !adapter->qbv_count)) {
+ igc_tsn_will_tx_mode_change(adapter)) {
schedule_work(&adapter->reset_task);
return 0;
}
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h
index b53e6af..98ec845 100644
--- a/drivers/net/ethernet/intel/igc/igc_tsn.h
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.h
@@ -7,5 +7,6 @@
int igc_tsn_offload_apply(struct igc_adapter *adapter);
int igc_tsn_reset(struct igc_adapter *adapter);
void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter);
+bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter);
#endif /* _IGC_BASE_H */
diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index b06e245..d8be0e4 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -946,15 +946,13 @@ jme_udpsum(struct sk_buff *skb)
if (skb->protocol != htons(ETH_P_IP))
return csum;
skb_set_network_header(skb, ETH_HLEN);
- if ((ip_hdr(skb)->protocol != IPPROTO_UDP) ||
- (skb->len < (ETH_HLEN +
- (ip_hdr(skb)->ihl << 2) +
- sizeof(struct udphdr)))) {
+
+ if (ip_hdr(skb)->protocol != IPPROTO_UDP ||
+ skb->len < (ETH_HLEN + ip_hdrlen(skb) + sizeof(struct udphdr))) {
skb_reset_network_header(skb);
return csum;
}
- skb_set_transport_header(skb,
- ETH_HLEN + (ip_hdr(skb)->ihl << 2));
+ skb_set_transport_header(skb, ETH_HLEN + ip_hdrlen(skb));
csum = udp_hdr(skb)->check;
skb_reset_transport_header(skb);
skb_reset_network_header(skb);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index 3e09d22..daf4b95 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -632,7 +632,9 @@ int rvu_mbox_handler_cpt_inline_ipsec_cfg(struct rvu *rvu,
return ret;
}
-static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req)
+static bool validate_and_update_reg_offset(struct rvu *rvu,
+ struct cpt_rd_wr_reg_msg *req,
+ u64 *reg_offset)
{
u64 offset = req->reg_offset;
int blkaddr, num_lfs, lf;
@@ -663,6 +665,11 @@ static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req)
if (lf < 0)
return false;
+ /* Translate local LF's offset to global CPT LF's offset to
+ * access LFX register.
+ */
+ *reg_offset = (req->reg_offset & 0xFF000) + (lf << 3);
+
return true;
} else if (!(req->hdr.pcifunc & RVU_PFVF_FUNC_MASK)) {
/* Registers that can be accessed from PF */
@@ -697,7 +704,7 @@ int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu,
struct cpt_rd_wr_reg_msg *rsp)
{
u64 offset = req->reg_offset;
- int blkaddr, lf;
+ int blkaddr;
blkaddr = validate_and_get_cpt_blkaddr(req->blkaddr);
if (blkaddr < 0)
@@ -708,18 +715,10 @@ int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu,
!is_cpt_vf(rvu, req->hdr.pcifunc))
return CPT_AF_ERR_ACCESS_DENIED;
- if (!is_valid_offset(rvu, req))
+ if (!validate_and_update_reg_offset(rvu, req, &offset))
return CPT_AF_ERR_ACCESS_DENIED;
- /* Translate local LF used by VFs to global CPT LF */
- lf = rvu_get_lf(rvu, &rvu->hw->block[blkaddr], req->hdr.pcifunc,
- (offset & 0xFFF) >> 3);
-
- /* Translate local LF's offset to global CPT LF's offset */
- offset &= 0xFF000;
- offset += lf << 3;
-
- rsp->reg_offset = offset;
+ rsp->reg_offset = req->reg_offset;
rsp->ret_val = req->ret_val;
rsp->is_write = req->is_write;
diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c
index 61334a7..e212a4b 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed.c
@@ -2666,14 +2666,15 @@ mtk_wed_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_pri
{
struct mtk_wed_flow_block_priv *priv = cb_priv;
struct flow_cls_offload *cls = type_data;
- struct mtk_wed_hw *hw = priv->hw;
+ struct mtk_wed_hw *hw = NULL;
- if (!tc_can_offload(priv->dev))
+ if (!priv || !tc_can_offload(priv->dev))
return -EOPNOTSUPP;
if (type != TC_SETUP_CLSFLOWER)
return -EOPNOTSUPP;
+ hw = priv->hw;
return mtk_flow_offload_cmd(hw->eth, cls, hw->index);
}
@@ -2729,6 +2730,7 @@ mtk_wed_setup_tc_block(struct mtk_wed_hw *hw, struct net_device *dev,
flow_block_cb_remove(block_cb, f);
list_del(&block_cb->driver_list);
kfree(block_cb->cb_priv);
+ block_cb->cb_priv = NULL;
}
return 0;
default:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 5fd82c67..d9e2414 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -130,7 +130,7 @@ struct page_pool;
#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW 0x2
#define MLX5E_DEFAULT_LRO_TIMEOUT 32
-#define MLX5E_LRO_TIMEOUT_ARR_SIZE 4
+#define MLX5E_DEFAULT_SHAMPO_TIMEOUT 1024
#define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC 0x10
#define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE 0x3
@@ -998,6 +998,7 @@ void mlx5e_build_ptys2ethtool_map(void);
bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev, u8 page_shift,
enum mlx5e_mpwrq_umr_mode umr_mode);
+void mlx5e_shampo_fill_umr(struct mlx5e_rq *rq, int len);
void mlx5e_shampo_dealloc_hd(struct mlx5e_rq *rq);
void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 6c9cccc..64b62ed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -928,7 +928,7 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
MLX5_SET(wq, wq, log_headers_entry_size,
mlx5e_shampo_get_log_hd_entry_size(mdev, params));
MLX5_SET(rqc, rqc, reservation_timeout,
- params->packet_merge.timeout);
+ mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_SHAMPO_TIMEOUT));
MLX5_SET(rqc, rqc, shampo_match_criteria_type,
params->packet_merge.shampo.match_criteria_type);
MLX5_SET(rqc, rqc, shampo_no_match_alignment_granularity,
@@ -1087,6 +1087,20 @@ static u32 mlx5e_shampo_icosq_sz(struct mlx5_core_dev *mdev,
return wqebbs;
}
+#define MLX5E_LRO_TIMEOUT_ARR_SIZE 4
+
+u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout)
+{
+ int i;
+
+ /* The supported periods are organized in ascending order */
+ for (i = 0; i < MLX5E_LRO_TIMEOUT_ARR_SIZE - 1; i++)
+ if (MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]) >= wanted_timeout)
+ break;
+
+ return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]);
+}
+
static u32 mlx5e_mpwrq_total_umr_wqebbs(struct mlx5_core_dev *mdev,
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
index 749b2ec..3f8986f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
@@ -108,6 +108,7 @@ u32 mlx5e_shampo_hd_per_wqe(struct mlx5_core_dev *mdev,
u32 mlx5e_shampo_hd_per_wq(struct mlx5_core_dev *mdev,
struct mlx5e_params *params,
struct mlx5e_rq_param *rq_param);
+u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout);
u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 22918b2..09433b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -146,7 +146,9 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx)
return err;
}
+ mutex_lock(&priv->state_lock);
err = mlx5e_safe_reopen_channels(priv);
+ mutex_unlock(&priv->state_lock);
if (!err) {
to_ctx->status = 1; /* all channels recovered */
return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 3eccdad..773624b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -734,7 +734,7 @@ mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
if (num_tuples <= 0) {
netdev_warn(priv->netdev, "%s: flow is not valid %d\n",
__func__, num_tuples);
- return num_tuples;
+ return num_tuples < 0 ? num_tuples : -EINVAL;
}
eth_ft = get_flow_table(priv, fs, num_tuples);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 6f686fa..16b67c4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1236,6 +1236,14 @@ void mlx5e_free_rx_missing_descs(struct mlx5e_rq *rq)
rq->mpwqe.actual_wq_head = wq->head;
rq->mpwqe.umr_in_progress = 0;
rq->mpwqe.umr_completed = 0;
+
+ if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) {
+ struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
+ u16 len;
+
+ len = (shampo->pi - shampo->ci) & shampo->hd_per_wq;
+ mlx5e_shampo_fill_umr(rq, len);
+ }
}
void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
@@ -3020,15 +3028,18 @@ int mlx5e_update_tx_netdev_queues(struct mlx5e_priv *priv)
static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv,
struct mlx5e_params *params)
{
- struct mlx5_core_dev *mdev = priv->mdev;
- int num_comp_vectors, ix, irq;
-
- num_comp_vectors = mlx5_comp_vectors_max(mdev);
+ int ix;
for (ix = 0; ix < params->num_channels; ix++) {
- cpumask_clear(priv->scratchpad.cpumask);
+ int num_comp_vectors, irq, vec_ix;
+ struct mlx5_core_dev *mdev;
- for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) {
+ mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, ix);
+ num_comp_vectors = mlx5_comp_vectors_max(mdev);
+ cpumask_clear(priv->scratchpad.cpumask);
+ vec_ix = mlx5_sd_ch_ix_get_vec_ix(mdev, ix);
+
+ for (irq = vec_ix; irq < num_comp_vectors; irq += params->num_channels) {
int cpu = mlx5_comp_vector_get_cpu(mdev, irq);
cpumask_set_cpu(cpu, priv->scratchpad.cpumask);
@@ -5167,18 +5178,6 @@ const struct net_device_ops mlx5e_netdev_ops = {
#endif
};
-static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout)
-{
- int i;
-
- /* The supported periods are organized in ascending order */
- for (i = 0; i < MLX5E_LRO_TIMEOUT_ARR_SIZE - 1; i++)
- if (MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]) >= wanted_timeout)
- break;
-
- return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]);
-}
-
void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu)
{
struct mlx5e_params *params = &priv->channels.params;
@@ -5308,7 +5307,7 @@ static void mlx5e_get_queue_stats_rx(struct net_device *dev, int i,
struct mlx5e_rq_stats *rq_stats;
ASSERT_RTNL();
- if (mlx5e_is_uplink_rep(priv))
+ if (mlx5e_is_uplink_rep(priv) || !priv->stats_nch)
return;
channel_stats = priv->channel_stats[i];
@@ -5328,6 +5327,9 @@ static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i,
struct mlx5e_sq_stats *sq_stats;
ASSERT_RTNL();
+ if (!priv->stats_nch)
+ return;
+
/* no special case needed for ptp htb etc since txq2sq_stats is kept up
* to date for active sq_stats, otherwise get_base_stats takes care of
* inactive sqs.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 225da8d..de9d010 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -735,6 +735,7 @@ static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq)
ksm_entries = bitmap_find_window(shampo->bitmap,
shampo->hd_per_wqe,
shampo->hd_per_wq, shampo->pi);
+ ksm_entries = ALIGN_DOWN(ksm_entries, MLX5E_SHAMPO_WQ_HEADER_PER_PAGE);
if (!ksm_entries)
return 0;
@@ -962,26 +963,31 @@ void mlx5e_free_icosq_descs(struct mlx5e_icosq *sq)
sq->cc = sqcc;
}
-static void mlx5e_handle_shampo_hd_umr(struct mlx5e_shampo_umr umr,
- struct mlx5e_icosq *sq)
+void mlx5e_shampo_fill_umr(struct mlx5e_rq *rq, int len)
{
- struct mlx5e_channel *c = container_of(sq, struct mlx5e_channel, icosq);
- struct mlx5e_shampo_hd *shampo;
- /* assume 1:1 relationship between RQ and icosq */
- struct mlx5e_rq *rq = &c->rq;
- int end, from, len = umr.len;
+ struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
+ int end, from, full_len = len;
- shampo = rq->mpwqe.shampo;
end = shampo->hd_per_wq;
from = shampo->ci;
- if (from + len > shampo->hd_per_wq) {
+ if (from + len > end) {
len -= end - from;
bitmap_set(shampo->bitmap, from, end - from);
from = 0;
}
bitmap_set(shampo->bitmap, from, len);
- shampo->ci = (shampo->ci + umr.len) & (shampo->hd_per_wq - 1);
+ shampo->ci = (shampo->ci + full_len) & (shampo->hd_per_wq - 1);
+}
+
+static void mlx5e_handle_shampo_hd_umr(struct mlx5e_shampo_umr umr,
+ struct mlx5e_icosq *sq)
+{
+ struct mlx5e_channel *c = container_of(sq, struct mlx5e_channel, icosq);
+ /* assume 1:1 relationship between RQ and icosq */
+ struct mlx5e_rq *rq = &c->rq;
+
+ mlx5e_shampo_fill_umr(rq, umr.len);
}
int mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c
index 234cd00..b7d4b1a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c
@@ -386,7 +386,8 @@ static int ipsec_fs_roce_tx_mpv_create(struct mlx5_core_dev *mdev,
return -EOPNOTSUPP;
peer_priv = mlx5_devcom_get_next_peer_data(*ipsec_roce->devcom, &tmp);
- if (!peer_priv) {
+ if (!peer_priv || !peer_priv->ipsec) {
+ mlx5_core_err(mdev, "IPsec not supported on master device\n");
err = -EOPNOTSUPP;
goto release_peer;
}
@@ -455,7 +456,8 @@ static int ipsec_fs_roce_rx_mpv_create(struct mlx5_core_dev *mdev,
return -EOPNOTSUPP;
peer_priv = mlx5_devcom_get_next_peer_data(*ipsec_roce->devcom, &tmp);
- if (!peer_priv) {
+ if (!peer_priv || !peer_priv->ipsec) {
+ mlx5_core_err(mdev, "IPsec not supported on master device\n");
err = -EOPNOTSUPP;
goto release_peer;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
index f6deb5a..eeb0b7e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
@@ -126,7 +126,7 @@ static bool mlx5_sd_is_supported(struct mlx5_core_dev *dev, u8 host_buses)
}
static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm,
- u8 *host_buses, u8 *sd_group)
+ u8 *host_buses)
{
u32 out[MLX5_ST_SZ_DW(mpir_reg)];
int err;
@@ -135,10 +135,6 @@ static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm,
if (err)
return err;
- err = mlx5_query_nic_vport_sd_group(dev, sd_group);
- if (err)
- return err;
-
*sdm = MLX5_GET(mpir_reg, out, sdm);
*host_buses = MLX5_GET(mpir_reg, out, host_buses);
@@ -166,19 +162,23 @@ static int sd_init(struct mlx5_core_dev *dev)
if (mlx5_core_is_ecpf(dev))
return 0;
+ err = mlx5_query_nic_vport_sd_group(dev, &sd_group);
+ if (err)
+ return err;
+
+ if (!sd_group)
+ return 0;
+
if (!MLX5_CAP_MCAM_REG(dev, mpir))
return 0;
- err = mlx5_query_sd(dev, &sdm, &host_buses, &sd_group);
+ err = mlx5_query_sd(dev, &sdm, &host_buses);
if (err)
return err;
if (!sdm)
return 0;
- if (!sd_group)
- return 0;
-
group_id = mlx5_sd_group_id(dev, sd_group);
if (!mlx5_sd_is_supported(dev, host_buses)) {
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h
index bc94e75..e777770 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h
@@ -40,6 +40,7 @@
*/
#define MLXBF_GIGE_BCAST_MAC_FILTER_IDX 0
#define MLXBF_GIGE_LOCAL_MAC_FILTER_IDX 1
+#define MLXBF_GIGE_MAX_FILTER_IDX 3
/* Define for broadcast MAC literal */
#define BCAST_MAC_ADDR 0xFFFFFFFFFFFF
@@ -175,6 +176,13 @@ enum mlxbf_gige_res {
int mlxbf_gige_mdio_probe(struct platform_device *pdev,
struct mlxbf_gige *priv);
void mlxbf_gige_mdio_remove(struct mlxbf_gige *priv);
+
+void mlxbf_gige_enable_multicast_rx(struct mlxbf_gige *priv);
+void mlxbf_gige_disable_multicast_rx(struct mlxbf_gige *priv);
+void mlxbf_gige_enable_mac_rx_filter(struct mlxbf_gige *priv,
+ unsigned int index);
+void mlxbf_gige_disable_mac_rx_filter(struct mlxbf_gige *priv,
+ unsigned int index);
void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv,
unsigned int index, u64 dmac);
void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv,
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
index b157f0f..385a56ac 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
@@ -168,6 +168,10 @@ static int mlxbf_gige_open(struct net_device *netdev)
if (err)
goto napi_deinit;
+ mlxbf_gige_enable_mac_rx_filter(priv, MLXBF_GIGE_BCAST_MAC_FILTER_IDX);
+ mlxbf_gige_enable_mac_rx_filter(priv, MLXBF_GIGE_LOCAL_MAC_FILTER_IDX);
+ mlxbf_gige_enable_multicast_rx(priv);
+
/* Set bits in INT_EN that we care about */
int_en = MLXBF_GIGE_INT_EN_HW_ACCESS_ERROR |
MLXBF_GIGE_INT_EN_TX_CHECKSUM_INPUTS |
@@ -379,6 +383,7 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
void __iomem *plu_base;
void __iomem *base;
int addr, phy_irq;
+ unsigned int i;
int err;
base = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MAC);
@@ -423,6 +428,11 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
priv->rx_q_entries = MLXBF_GIGE_DEFAULT_RXQ_SZ;
priv->tx_q_entries = MLXBF_GIGE_DEFAULT_TXQ_SZ;
+ for (i = 0; i <= MLXBF_GIGE_MAX_FILTER_IDX; i++)
+ mlxbf_gige_disable_mac_rx_filter(priv, i);
+ mlxbf_gige_disable_multicast_rx(priv);
+ mlxbf_gige_disable_promisc(priv);
+
/* Write initial MAC address to hardware */
mlxbf_gige_initial_mac(priv);
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h
index 98a8681..4d14cb13 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h
@@ -62,6 +62,8 @@
#define MLXBF_GIGE_TX_STATUS_DATA_FIFO_FULL BIT(1)
#define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_START 0x0520
#define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_END 0x0528
+#define MLXBF_GIGE_RX_MAC_FILTER_GENERAL 0x0530
+#define MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST BIT(1)
#define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC 0x0540
#define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC_EN BIT(0)
#define MLXBF_GIGE_RX_MAC_FILTER_COUNT_PASS 0x0548
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c
index 6999843..eb62620 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c
@@ -11,22 +11,60 @@
#include "mlxbf_gige.h"
#include "mlxbf_gige_regs.h"
-void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv,
- unsigned int index, u64 dmac)
+void mlxbf_gige_enable_multicast_rx(struct mlxbf_gige *priv)
+{
+ void __iomem *base = priv->base;
+ u64 data;
+
+ data = readq(base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL);
+ data |= MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST;
+ writeq(data, base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL);
+}
+
+void mlxbf_gige_disable_multicast_rx(struct mlxbf_gige *priv)
+{
+ void __iomem *base = priv->base;
+ u64 data;
+
+ data = readq(base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL);
+ data &= ~MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST;
+ writeq(data, base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL);
+}
+
+void mlxbf_gige_enable_mac_rx_filter(struct mlxbf_gige *priv,
+ unsigned int index)
{
void __iomem *base = priv->base;
u64 control;
- /* Write destination MAC to specified MAC RX filter */
- writeq(dmac, base + MLXBF_GIGE_RX_MAC_FILTER +
- (index * MLXBF_GIGE_RX_MAC_FILTER_STRIDE));
-
/* Enable MAC receive filter mask for specified index */
control = readq(base + MLXBF_GIGE_CONTROL);
control |= (MLXBF_GIGE_CONTROL_EN_SPECIFIC_MAC << index);
writeq(control, base + MLXBF_GIGE_CONTROL);
}
+void mlxbf_gige_disable_mac_rx_filter(struct mlxbf_gige *priv,
+ unsigned int index)
+{
+ void __iomem *base = priv->base;
+ u64 control;
+
+ /* Disable MAC receive filter mask for specified index */
+ control = readq(base + MLXBF_GIGE_CONTROL);
+ control &= ~(MLXBF_GIGE_CONTROL_EN_SPECIFIC_MAC << index);
+ writeq(control, base + MLXBF_GIGE_CONTROL);
+}
+
+void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv,
+ unsigned int index, u64 dmac)
+{
+ void __iomem *base = priv->base;
+
+ /* Write destination MAC to specified MAC RX filter */
+ writeq(dmac, base + MLXBF_GIGE_RX_MAC_FILTER +
+ (index * MLXBF_GIGE_RX_MAC_FILTER_STRIDE));
+}
+
void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv,
unsigned int index, u64 *dmac)
{
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index cafded2..a00f915 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -52,32 +52,6 @@ static int mana_hwc_verify_resp_msg(const struct hwc_caller_ctx *caller_ctx,
return 0;
}
-static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len,
- const struct gdma_resp_hdr *resp_msg)
-{
- struct hwc_caller_ctx *ctx;
- int err;
-
- if (!test_bit(resp_msg->response.hwc_msg_id,
- hwc->inflight_msg_res.map)) {
- dev_err(hwc->dev, "hwc_rx: invalid msg_id = %u\n",
- resp_msg->response.hwc_msg_id);
- return;
- }
-
- ctx = hwc->caller_ctx + resp_msg->response.hwc_msg_id;
- err = mana_hwc_verify_resp_msg(ctx, resp_msg, resp_len);
- if (err)
- goto out;
-
- ctx->status_code = resp_msg->status;
-
- memcpy(ctx->output_buf, resp_msg, resp_len);
-out:
- ctx->error = err;
- complete(&ctx->comp_event);
-}
-
static int mana_hwc_post_rx_wqe(const struct hwc_wq *hwc_rxq,
struct hwc_work_request *req)
{
@@ -101,6 +75,40 @@ static int mana_hwc_post_rx_wqe(const struct hwc_wq *hwc_rxq,
return err;
}
+static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len,
+ struct hwc_work_request *rx_req)
+{
+ const struct gdma_resp_hdr *resp_msg = rx_req->buf_va;
+ struct hwc_caller_ctx *ctx;
+ int err;
+
+ if (!test_bit(resp_msg->response.hwc_msg_id,
+ hwc->inflight_msg_res.map)) {
+ dev_err(hwc->dev, "hwc_rx: invalid msg_id = %u\n",
+ resp_msg->response.hwc_msg_id);
+ mana_hwc_post_rx_wqe(hwc->rxq, rx_req);
+ return;
+ }
+
+ ctx = hwc->caller_ctx + resp_msg->response.hwc_msg_id;
+ err = mana_hwc_verify_resp_msg(ctx, resp_msg, resp_len);
+ if (err)
+ goto out;
+
+ ctx->status_code = resp_msg->status;
+
+ memcpy(ctx->output_buf, resp_msg, resp_len);
+out:
+ ctx->error = err;
+
+ /* Must post rx wqe before complete(), otherwise the next rx may
+ * hit no_wqe error.
+ */
+ mana_hwc_post_rx_wqe(hwc->rxq, rx_req);
+
+ complete(&ctx->comp_event);
+}
+
static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self,
struct gdma_event *event)
{
@@ -235,14 +243,12 @@ static void mana_hwc_rx_event_handler(void *ctx, u32 gdma_rxq_id,
return;
}
- mana_hwc_handle_resp(hwc, rx_oob->tx_oob_data_size, resp);
+ mana_hwc_handle_resp(hwc, rx_oob->tx_oob_data_size, rx_req);
- /* Do no longer use 'resp', because the buffer is posted to the HW
- * in the below mana_hwc_post_rx_wqe().
+ /* Can no longer use 'resp', because the buffer is posted to the HW
+ * in mana_hwc_handle_resp() above.
*/
resp = NULL;
-
- mana_hwc_post_rx_wqe(hwc_rxq, rx_req);
}
static void mana_hwc_tx_event_handler(void *ctx, u32 gdma_txq_id,
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index d2f07e1..39f56973 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -599,7 +599,11 @@ static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size,
else
*headroom = XDP_PACKET_HEADROOM;
- *alloc_size = mtu + MANA_RXBUF_PAD + *headroom;
+ *alloc_size = SKB_DATA_ALIGN(mtu + MANA_RXBUF_PAD + *headroom);
+
+ /* Using page pool in this case, so alloc_size is PAGE_SIZE */
+ if (*alloc_size < PAGE_SIZE)
+ *alloc_size = PAGE_SIZE;
*datasize = mtu + ETH_HLEN;
}
@@ -1788,7 +1792,6 @@ static void mana_poll_rx_cq(struct mana_cq *cq)
static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue)
{
struct mana_cq *cq = context;
- u8 arm_bit;
int w;
WARN_ON_ONCE(cq->gdma_cq != gdma_queue);
@@ -1799,16 +1802,23 @@ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue)
mana_poll_tx_cq(cq);
w = cq->work_done;
+ cq->work_done_since_doorbell += w;
- if (w < cq->budget &&
- napi_complete_done(&cq->napi, w)) {
- arm_bit = SET_ARM_BIT;
- } else {
- arm_bit = 0;
+ if (w < cq->budget) {
+ mana_gd_ring_cq(gdma_queue, SET_ARM_BIT);
+ cq->work_done_since_doorbell = 0;
+ napi_complete_done(&cq->napi, w);
+ } else if (cq->work_done_since_doorbell >
+ cq->gdma_cq->queue_size / COMP_ENTRY_SIZE * 4) {
+ /* MANA hardware requires at least one doorbell ring every 8
+ * wraparounds of CQ even if there is no need to arm the CQ.
+ * This driver rings the doorbell as soon as we have exceeded
+ * 4 wraparounds.
+ */
+ mana_gd_ring_cq(gdma_queue, 0);
+ cq->work_done_since_doorbell = 0;
}
- mana_gd_ring_cq(gdma_queue, arm_bit);
-
return w;
}
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index ed2fb44..3d72aa7 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -453,9 +453,158 @@ static u16 ocelot_vlan_unaware_pvid(struct ocelot *ocelot,
return VLAN_N_VID - bridge_num - 1;
}
+/**
+ * ocelot_update_vlan_reclassify_rule() - Make switch aware only to bridge VLAN TPID
+ *
+ * @ocelot: Switch private data structure
+ * @port: Index of ingress port
+ *
+ * IEEE 802.1Q-2018 clauses "5.5 C-VLAN component conformance" and "5.6 S-VLAN
+ * component conformance" suggest that a C-VLAN component should only recognize
+ * and filter on C-Tags, and an S-VLAN component should only recognize and
+ * process based on C-Tags.
+ *
+ * In Linux, as per commit 1a0b20b25732 ("Merge branch 'bridge-next'"), C-VLAN
+ * components are largely represented by a bridge with vlan_protocol 802.1Q,
+ * and S-VLAN components by a bridge with vlan_protocol 802.1ad.
+ *
+ * Currently the driver only offloads vlan_protocol 802.1Q, but the hardware
+ * design is non-conformant, because the switch assigns each frame to a VLAN
+ * based on an entirely different question, as detailed in figure "Basic VLAN
+ * Classification Flow" from its manual and reproduced below.
+ *
+ * Set TAG_TYPE, PCP, DEI, VID to port-default values in VLAN_CFG register
+ * if VLAN_AWARE_ENA[port] and frame has outer tag then:
+ * if VLAN_INNER_TAG_ENA[port] and frame has inner tag then:
+ * TAG_TYPE = (Frame.InnerTPID <> 0x8100)
+ * Set PCP, DEI, VID to values from inner VLAN header
+ * else:
+ * TAG_TYPE = (Frame.OuterTPID <> 0x8100)
+ * Set PCP, DEI, VID to values from outer VLAN header
+ * if VID == 0 then:
+ * VID = VLAN_CFG.VLAN_VID
+ *
+ * Summarized, the switch will recognize both 802.1Q and 802.1ad TPIDs as VLAN
+ * "with equal rights", and just set the TAG_TYPE bit to 0 (if 802.1Q) or to 1
+ * (if 802.1ad). It will classify based on whichever of the tags is "outer", no
+ * matter what TPID that may have (or "inner", if VLAN_INNER_TAG_ENA[port]).
+ *
+ * In the VLAN Table, the TAG_TYPE information is not accessible - just the
+ * classified VID is - so it is as if each VLAN Table entry is for 2 VLANs:
+ * C-VLAN X, and S-VLAN X.
+ *
+ * Whereas the Linux bridge behavior is to only filter on frames with a TPID
+ * equal to the vlan_protocol, and treat everything else as VLAN-untagged.
+ *
+ * Consider an ingress packet tagged with 802.1ad VID=3 and 802.1Q VID=5,
+ * received on a bridge vlan_filtering=1 vlan_protocol=802.1Q port. This frame
+ * should be treated as 802.1Q-untagged, and classified to the PVID of that
+ * bridge port. Not to VID=3, and not to VID=5.
+ *
+ * The VCAP IS1 TCAM has everything we need to overwrite the choices made in
+ * the basic VLAN classification pipeline: it can match on TAG_TYPE in the key,
+ * and it can modify the classified VID in the action. Thus, for each port
+ * under a vlan_filtering bridge, we can insert a rule in VCAP IS1 lookup 0 to
+ * match on 802.1ad tagged frames and modify their classified VID to the 802.1Q
+ * PVID of the port. This effectively makes it appear to the outside world as
+ * if those packets were processed as VLAN-untagged.
+ *
+ * The rule needs to be updated each time the bridge PVID changes, and needs
+ * to be deleted if the bridge PVID is deleted, or if the port becomes
+ * VLAN-unaware.
+ */
+static int ocelot_update_vlan_reclassify_rule(struct ocelot *ocelot, int port)
+{
+ unsigned long cookie = OCELOT_VCAP_IS1_VLAN_RECLASSIFY(ocelot, port);
+ struct ocelot_vcap_block *block_vcap_is1 = &ocelot->block[VCAP_IS1];
+ struct ocelot_port *ocelot_port = ocelot->ports[port];
+ const struct ocelot_bridge_vlan *pvid_vlan;
+ struct ocelot_vcap_filter *filter;
+ int err, val, pcp, dei;
+ bool vid_replace_ena;
+ u16 vid;
+
+ pvid_vlan = ocelot_port->pvid_vlan;
+ vid_replace_ena = ocelot_port->vlan_aware && pvid_vlan;
+
+ filter = ocelot_vcap_block_find_filter_by_id(block_vcap_is1, cookie,
+ false);
+ if (!vid_replace_ena) {
+ /* If the reclassification filter doesn't need to exist, delete
+ * it if it was previously installed, and exit doing nothing
+ * otherwise.
+ */
+ if (filter)
+ return ocelot_vcap_filter_del(ocelot, filter);
+
+ return 0;
+ }
+
+ /* The reclassification rule must apply. See if it already exists
+ * or if it must be created.
+ */
+
+ /* Treating as VLAN-untagged means using as classified VID equal to
+ * the bridge PVID, and PCP/DEI set to the port default QoS values.
+ */
+ vid = pvid_vlan->vid;
+ val = ocelot_read_gix(ocelot, ANA_PORT_QOS_CFG, port);
+ pcp = ANA_PORT_QOS_CFG_QOS_DEFAULT_VAL_X(val);
+ dei = !!(val & ANA_PORT_QOS_CFG_DP_DEFAULT_VAL);
+
+ if (filter) {
+ bool changed = false;
+
+ /* Filter exists, just update it */
+ if (filter->action.vid != vid) {
+ filter->action.vid = vid;
+ changed = true;
+ }
+ if (filter->action.pcp != pcp) {
+ filter->action.pcp = pcp;
+ changed = true;
+ }
+ if (filter->action.dei != dei) {
+ filter->action.dei = dei;
+ changed = true;
+ }
+
+ if (!changed)
+ return 0;
+
+ return ocelot_vcap_filter_replace(ocelot, filter);
+ }
+
+ /* Filter doesn't exist, create it */
+ filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+ if (!filter)
+ return -ENOMEM;
+
+ filter->key_type = OCELOT_VCAP_KEY_ANY;
+ filter->ingress_port_mask = BIT(port);
+ filter->vlan.tpid = OCELOT_VCAP_BIT_1;
+ filter->prio = 1;
+ filter->id.cookie = cookie;
+ filter->id.tc_offload = false;
+ filter->block_id = VCAP_IS1;
+ filter->type = OCELOT_VCAP_FILTER_OFFLOAD;
+ filter->lookup = 0;
+ filter->action.vid_replace_ena = true;
+ filter->action.pcp_dei_ena = true;
+ filter->action.vid = vid;
+ filter->action.pcp = pcp;
+ filter->action.dei = dei;
+
+ err = ocelot_vcap_filter_add(ocelot, filter, NULL);
+ if (err)
+ kfree(filter);
+
+ return err;
+}
+
/* Default vlan to clasify for untagged frames (may be zero) */
-static void ocelot_port_set_pvid(struct ocelot *ocelot, int port,
- const struct ocelot_bridge_vlan *pvid_vlan)
+static int ocelot_port_set_pvid(struct ocelot *ocelot, int port,
+ const struct ocelot_bridge_vlan *pvid_vlan)
{
struct ocelot_port *ocelot_port = ocelot->ports[port];
u16 pvid = ocelot_vlan_unaware_pvid(ocelot, ocelot_port->bridge);
@@ -475,15 +624,23 @@ static void ocelot_port_set_pvid(struct ocelot *ocelot, int port,
* happens automatically), but also 802.1p traffic which gets
* classified to VLAN 0, but that is always in our RX filter, so it
* would get accepted were it not for this setting.
+ *
+ * Also, we only support the bridge 802.1Q VLAN protocol, so
+ * 802.1ad-tagged frames (carrying S-Tags) should be considered
+ * 802.1Q-untagged, and also dropped.
*/
if (!pvid_vlan && ocelot_port->vlan_aware)
val = ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
- ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA;
+ ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA |
+ ANA_PORT_DROP_CFG_DROP_S_TAGGED_ENA;
ocelot_rmw_gix(ocelot, val,
ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
- ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA,
+ ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA |
+ ANA_PORT_DROP_CFG_DROP_S_TAGGED_ENA,
ANA_PORT_DROP_CFG, port);
+
+ return ocelot_update_vlan_reclassify_rule(ocelot, port);
}
static struct ocelot_bridge_vlan *ocelot_bridge_vlan_find(struct ocelot *ocelot,
@@ -631,7 +788,10 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M,
ANA_PORT_VLAN_CFG, port);
- ocelot_port_set_pvid(ocelot, port, ocelot_port->pvid_vlan);
+ err = ocelot_port_set_pvid(ocelot, port, ocelot_port->pvid_vlan);
+ if (err)
+ return err;
+
ocelot_port_manage_port_tag(ocelot, port);
return 0;
@@ -684,9 +844,12 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
return err;
/* Default ingress vlan classification */
- if (pvid)
- ocelot_port_set_pvid(ocelot, port,
- ocelot_bridge_vlan_find(ocelot, vid));
+ if (pvid) {
+ err = ocelot_port_set_pvid(ocelot, port,
+ ocelot_bridge_vlan_find(ocelot, vid));
+ if (err)
+ return err;
+ }
/* Untagged egress vlan clasification */
ocelot_port_manage_port_tag(ocelot, port);
@@ -712,8 +875,11 @@ int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid)
return err;
/* Ingress */
- if (del_pvid)
- ocelot_port_set_pvid(ocelot, port, NULL);
+ if (del_pvid) {
+ err = ocelot_port_set_pvid(ocelot, port, NULL);
+ if (err)
+ return err;
+ }
/* Egress */
ocelot_port_manage_port_tag(ocelot, port);
@@ -1099,6 +1265,48 @@ void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb,
}
EXPORT_SYMBOL(ocelot_ptp_rx_timestamp);
+void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp)
+ __acquires(&ocelot->inj_lock)
+{
+ spin_lock(&ocelot->inj_lock);
+}
+EXPORT_SYMBOL_GPL(ocelot_lock_inj_grp);
+
+void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp)
+ __releases(&ocelot->inj_lock)
+{
+ spin_unlock(&ocelot->inj_lock);
+}
+EXPORT_SYMBOL_GPL(ocelot_unlock_inj_grp);
+
+void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp)
+ __acquires(&ocelot->inj_lock)
+{
+ spin_lock(&ocelot->inj_lock);
+}
+EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp);
+
+void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp)
+ __releases(&ocelot->inj_lock)
+{
+ spin_unlock(&ocelot->inj_lock);
+}
+EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp);
+
+void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp)
+ __acquires(&ocelot->xtr_lock)
+{
+ spin_lock_bh(&ocelot->xtr_lock);
+}
+EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp_bh);
+
+void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp)
+ __releases(&ocelot->xtr_lock)
+{
+ spin_unlock_bh(&ocelot->xtr_lock);
+}
+EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp_bh);
+
int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb)
{
u64 timestamp, src_port, len;
@@ -1109,6 +1317,8 @@ int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb)
u32 val, *buf;
int err;
+ lockdep_assert_held(&ocelot->xtr_lock);
+
err = ocelot_xtr_poll_xfh(ocelot, grp, xfh);
if (err)
return err;
@@ -1184,6 +1394,8 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp)
{
u32 val = ocelot_read(ocelot, QS_INJ_STATUS);
+ lockdep_assert_held(&ocelot->inj_lock);
+
if (!(val & QS_INJ_STATUS_FIFO_RDY(BIT(grp))))
return false;
if (val & QS_INJ_STATUS_WMARK_REACHED(BIT(grp)))
@@ -1193,28 +1405,55 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp)
}
EXPORT_SYMBOL(ocelot_can_inject);
-void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag)
+/**
+ * ocelot_ifh_set_basic - Set basic information in Injection Frame Header
+ * @ifh: Pointer to Injection Frame Header memory
+ * @ocelot: Switch private data structure
+ * @port: Egress port number
+ * @rew_op: Egress rewriter operation for PTP
+ * @skb: Pointer to socket buffer (packet)
+ *
+ * Populate the Injection Frame Header with basic information for this skb: the
+ * analyzer bypass bit, destination port, VLAN info, egress rewriter info.
+ */
+void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port,
+ u32 rew_op, struct sk_buff *skb)
{
+ struct ocelot_port *ocelot_port = ocelot->ports[port];
+ struct net_device *dev = skb->dev;
+ u64 vlan_tci, tag_type;
+ int qos_class;
+
+ ocelot_xmit_get_vlan_info(skb, ocelot_port->bridge, &vlan_tci,
+ &tag_type);
+
+ qos_class = netdev_get_num_tc(dev) ?
+ netdev_get_prio_tc_map(dev, skb->priority) : skb->priority;
+
+ memset(ifh, 0, OCELOT_TAG_LEN);
ocelot_ifh_set_bypass(ifh, 1);
+ ocelot_ifh_set_src(ifh, BIT_ULL(ocelot->num_phys_ports));
ocelot_ifh_set_dest(ifh, BIT_ULL(port));
- ocelot_ifh_set_tag_type(ifh, IFH_TAG_TYPE_C);
- if (vlan_tag)
- ocelot_ifh_set_vlan_tci(ifh, vlan_tag);
+ ocelot_ifh_set_qos_class(ifh, qos_class);
+ ocelot_ifh_set_tag_type(ifh, tag_type);
+ ocelot_ifh_set_vlan_tci(ifh, vlan_tci);
if (rew_op)
ocelot_ifh_set_rew_op(ifh, rew_op);
}
-EXPORT_SYMBOL(ocelot_ifh_port_set);
+EXPORT_SYMBOL(ocelot_ifh_set_basic);
void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp,
u32 rew_op, struct sk_buff *skb)
{
- u32 ifh[OCELOT_TAG_LEN / 4] = {0};
+ u32 ifh[OCELOT_TAG_LEN / 4];
unsigned int i, count, last;
+ lockdep_assert_held(&ocelot->inj_lock);
+
ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) |
QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp);
- ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb));
+ ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb);
for (i = 0; i < OCELOT_TAG_LEN / 4; i++)
ocelot_write_rix(ocelot, ifh[i], QS_INJ_WR, grp);
@@ -1247,6 +1486,8 @@ EXPORT_SYMBOL(ocelot_port_inject_frame);
void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp)
{
+ lockdep_assert_held(&ocelot->xtr_lock);
+
while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp))
ocelot_read_rix(ocelot, QS_XTR_RD, grp);
}
@@ -2532,7 +2773,7 @@ int ocelot_port_set_default_prio(struct ocelot *ocelot, int port, u8 prio)
ANA_PORT_QOS_CFG,
port);
- return 0;
+ return ocelot_update_vlan_reclassify_rule(ocelot, port);
}
EXPORT_SYMBOL_GPL(ocelot_port_set_default_prio);
@@ -2929,6 +3170,8 @@ int ocelot_init(struct ocelot *ocelot)
mutex_init(&ocelot->fwd_domain_lock);
spin_lock_init(&ocelot->ptp_clock_lock);
spin_lock_init(&ocelot->ts_id_lock);
+ spin_lock_init(&ocelot->inj_lock);
+ spin_lock_init(&ocelot->xtr_lock);
ocelot->owq = alloc_ordered_workqueue("ocelot-owq", 0);
if (!ocelot->owq)
diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c
index 312a468..00326ae 100644
--- a/drivers/net/ethernet/mscc/ocelot_fdma.c
+++ b/drivers/net/ethernet/mscc/ocelot_fdma.c
@@ -665,8 +665,7 @@ static int ocelot_fdma_prepare_skb(struct ocelot *ocelot, int port, u32 rew_op,
ifh = skb_push(skb, OCELOT_TAG_LEN);
skb_put(skb, ETH_FCS_LEN);
- memset(ifh, 0, OCELOT_TAG_LEN);
- ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb));
+ ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb);
return 0;
}
diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c
index 73cdec5..5734b86 100644
--- a/drivers/net/ethernet/mscc/ocelot_vcap.c
+++ b/drivers/net/ethernet/mscc/ocelot_vcap.c
@@ -695,6 +695,7 @@ static void is1_entry_set(struct ocelot *ocelot, int ix,
vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_L2_MC, filter->dmac_mc);
vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_L2_BC, filter->dmac_bc);
vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_VLAN_TAGGED, tag->tagged);
+ vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_TPID, tag->tpid);
vcap_key_set(vcap, &data, VCAP_IS1_HK_VID,
tag->vid.value, tag->vid.mask);
vcap_key_set(vcap, &data, VCAP_IS1_HK_PCP,
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
index 993212c..c09dd2e 100644
--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -51,6 +51,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
struct ocelot *ocelot = arg;
int grp = 0, err;
+ ocelot_lock_xtr_grp(ocelot, grp);
+
while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) {
struct sk_buff *skb;
@@ -69,6 +71,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
if (err < 0)
ocelot_drain_cpu_queue(ocelot, 0);
+ ocelot_unlock_xtr_grp(ocelot, grp);
+
return IRQ_HANDLED;
}
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
index c647033..f2f07bf 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
@@ -32,7 +32,7 @@
#define IONIC_ADMIN_DOORBELL_DEADLINE (HZ / 2) /* 500ms */
#define IONIC_TX_DOORBELL_DEADLINE (HZ / 100) /* 10ms */
#define IONIC_RX_MIN_DOORBELL_DEADLINE (HZ / 100) /* 10ms */
-#define IONIC_RX_MAX_DOORBELL_DEADLINE (HZ * 5) /* 5s */
+#define IONIC_RX_MAX_DOORBELL_DEADLINE (HZ * 4) /* 4s */
struct ionic_dev_bar {
void __iomem *vaddr;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index aa0cc31..86774d9 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -3220,7 +3220,7 @@ int ionic_lif_alloc(struct ionic *ionic)
netdev->netdev_ops = &ionic_netdev_ops;
ionic_ethtool_set_ops(netdev);
- netdev->watchdog_timeo = 2 * HZ;
+ netdev->watchdog_timeo = 5 * HZ;
netif_carrier_off(netdev);
lif->identity = lid;
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 3e51b3a..e3451be 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -1452,6 +1452,7 @@ static const struct prueth_pdata am654_icssg_pdata = {
static const struct prueth_pdata am64x_icssg_pdata = {
.fdqring_mode = K3_RINGACC_RING_MODE_RING,
+ .quirk_10m_link_issue = 1,
.switch_mode = 1,
};
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
index ec54b18..a5e9b77 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
@@ -124,8 +124,12 @@ static int ngbe_phylink_init(struct wx *wx)
MAC_SYM_PAUSE | MAC_ASYM_PAUSE;
config->mac_managed_pm = true;
- phy_mode = PHY_INTERFACE_MODE_RGMII_ID;
- __set_bit(PHY_INTERFACE_MODE_RGMII_ID, config->supported_interfaces);
+ /* The MAC only has add the Tx delay and it can not be modified.
+ * So just disable TX delay in PHY, and it is does not matter to
+ * internal phy.
+ */
+ phy_mode = PHY_INTERFACE_MODE_RGMII_RXID;
+ __set_bit(PHY_INTERFACE_MODE_RGMII_RXID, config->supported_interfaces);
phylink = phylink_create(config, NULL, phy_mode, &ngbe_mac_ops);
if (IS_ERR(phylink))
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index fa5500d..09c9f97 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -160,16 +160,17 @@
#define XAE_RCW1_OFFSET 0x00000404 /* Rx Configuration Word 1 */
#define XAE_TC_OFFSET 0x00000408 /* Tx Configuration */
#define XAE_FCC_OFFSET 0x0000040C /* Flow Control Configuration */
-#define XAE_EMMC_OFFSET 0x00000410 /* EMAC mode configuration */
-#define XAE_PHYC_OFFSET 0x00000414 /* RGMII/SGMII configuration */
+#define XAE_EMMC_OFFSET 0x00000410 /* MAC speed configuration */
+#define XAE_PHYC_OFFSET 0x00000414 /* RX Max Frame Configuration */
#define XAE_ID_OFFSET 0x000004F8 /* Identification register */
-#define XAE_MDIO_MC_OFFSET 0x00000500 /* MII Management Config */
-#define XAE_MDIO_MCR_OFFSET 0x00000504 /* MII Management Control */
-#define XAE_MDIO_MWD_OFFSET 0x00000508 /* MII Management Write Data */
-#define XAE_MDIO_MRD_OFFSET 0x0000050C /* MII Management Read Data */
+#define XAE_MDIO_MC_OFFSET 0x00000500 /* MDIO Setup */
+#define XAE_MDIO_MCR_OFFSET 0x00000504 /* MDIO Control */
+#define XAE_MDIO_MWD_OFFSET 0x00000508 /* MDIO Write Data */
+#define XAE_MDIO_MRD_OFFSET 0x0000050C /* MDIO Read Data */
#define XAE_UAW0_OFFSET 0x00000700 /* Unicast address word 0 */
#define XAE_UAW1_OFFSET 0x00000704 /* Unicast address word 1 */
-#define XAE_FMI_OFFSET 0x00000708 /* Filter Mask Index */
+#define XAE_FMI_OFFSET 0x00000708 /* Frame Filter Control */
+#define XAE_FFE_OFFSET 0x0000070C /* Frame Filter Enable */
#define XAE_AF0_OFFSET 0x00000710 /* Address Filter 0 */
#define XAE_AF1_OFFSET 0x00000714 /* Address Filter 1 */
@@ -308,7 +309,7 @@
*/
#define XAE_UAW1_UNICASTADDR_MASK 0x0000FFFF
-/* Bit masks for Axi Ethernet FMI register */
+/* Bit masks for Axi Ethernet FMC register */
#define XAE_FMI_PM_MASK 0x80000000 /* Promis. mode enable */
#define XAE_FMI_IND_MASK 0x00000003 /* Index Mask */
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 02fdf66..9aeb7b9 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -432,7 +432,7 @@ static int netdev_set_mac_address(struct net_device *ndev, void *p)
*/
static void axienet_set_multicast_list(struct net_device *ndev)
{
- int i;
+ int i = 0;
u32 reg, af0reg, af1reg;
struct axienet_local *lp = netdev_priv(ndev);
@@ -450,7 +450,10 @@ static void axienet_set_multicast_list(struct net_device *ndev)
} else if (!netdev_mc_empty(ndev)) {
struct netdev_hw_addr *ha;
- i = 0;
+ reg = axienet_ior(lp, XAE_FMI_OFFSET);
+ reg &= ~XAE_FMI_PM_MASK;
+ axienet_iow(lp, XAE_FMI_OFFSET, reg);
+
netdev_for_each_mc_addr(ha, ndev) {
if (i >= XAE_MULTICAST_CAM_TABLE_NUM)
break;
@@ -469,6 +472,7 @@ static void axienet_set_multicast_list(struct net_device *ndev)
axienet_iow(lp, XAE_FMI_OFFSET, reg);
axienet_iow(lp, XAE_AF0_OFFSET, af0reg);
axienet_iow(lp, XAE_AF1_OFFSET, af1reg);
+ axienet_iow(lp, XAE_FFE_OFFSET, 1);
i++;
}
} else {
@@ -476,18 +480,15 @@ static void axienet_set_multicast_list(struct net_device *ndev)
reg &= ~XAE_FMI_PM_MASK;
axienet_iow(lp, XAE_FMI_OFFSET, reg);
-
- for (i = 0; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) {
- reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00;
- reg |= i;
-
- axienet_iow(lp, XAE_FMI_OFFSET, reg);
- axienet_iow(lp, XAE_AF0_OFFSET, 0);
- axienet_iow(lp, XAE_AF1_OFFSET, 0);
- }
-
dev_info(&ndev->dev, "Promiscuous mode disabled.\n");
}
+
+ for (; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) {
+ reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00;
+ reg |= i;
+ axienet_iow(lp, XAE_FMI_OFFSET, reg);
+ axienet_iow(lp, XAE_FFE_OFFSET, 0);
+ }
}
/**
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 427b91a..2e94d10 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1269,6 +1269,9 @@ static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev)
if (skb_cow_head(skb, dev->needed_headroom))
goto tx_err;
+ if (!pskb_inet_may_pull(skb))
+ goto tx_err;
+
skb_reset_inner_headers(skb);
/* PDP context lookups in gtp_build_skb_*() need rcu read-side lock. */
@@ -1650,7 +1653,7 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
sock = sockfd_lookup(fd, &err);
if (!sock) {
pr_debug("gtp socket fd=%d not found\n", fd);
- return NULL;
+ return ERR_PTR(err);
}
sk = sock->sk;
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 8786591..25e5bfb 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -555,7 +555,7 @@ static int rtl8211f_led_hw_control_set(struct phy_device *phydev, u8 index,
unsigned long rules)
{
const u16 mask = RTL8211F_LEDCR_MASK << (RTL8211F_LEDCR_SHIFT * index);
- u16 reg = RTL8211F_LEDCR_MODE; /* Mode B */
+ u16 reg = 0;
if (index >= RTL8211F_LED_COUNT)
return -EINVAL;
@@ -575,6 +575,7 @@ static int rtl8211f_led_hw_control_set(struct phy_device *phydev, u8 index,
}
reg <<= RTL8211F_LEDCR_SHIFT * index;
+ reg |= RTL8211F_LEDCR_MODE; /* Mode B */
return phy_modify_paged(phydev, 0xd04, RTL8211F_LEDCR, mask, reg);
}
diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index 897b979..3b5fcaf 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -237,16 +237,6 @@ static int vsc739x_config_init(struct phy_device *phydev)
return 0;
}
-static int vsc73xx_config_aneg(struct phy_device *phydev)
-{
- /* The VSC73xx switches does not like to be instructed to
- * do autonegotiation in any way, it prefers that you just go
- * with the power-on/reset defaults. Writing some registers will
- * just make autonegotiation permanently fail.
- */
- return 0;
-}
-
/* This adds a skew for both TX and RX clocks, so the skew should only be
* applied to "rgmii-id" interfaces. It may not work as expected
* on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces.
@@ -444,7 +434,6 @@ static struct phy_driver vsc82xx_driver[] = {
.phy_id_mask = 0x000ffff0,
/* PHY_GBIT_FEATURES */
.config_init = vsc738x_config_init,
- .config_aneg = vsc73xx_config_aneg,
.read_page = vsc73xx_read_page,
.write_page = vsc73xx_write_page,
}, {
@@ -453,7 +442,6 @@ static struct phy_driver vsc82xx_driver[] = {
.phy_id_mask = 0x000ffff0,
/* PHY_GBIT_FEATURES */
.config_init = vsc738x_config_init,
- .config_aneg = vsc73xx_config_aneg,
.read_page = vsc73xx_read_page,
.write_page = vsc73xx_write_page,
}, {
@@ -462,7 +450,6 @@ static struct phy_driver vsc82xx_driver[] = {
.phy_id_mask = 0x000ffff0,
/* PHY_GBIT_FEATURES */
.config_init = vsc739x_config_init,
- .config_aneg = vsc73xx_config_aneg,
.read_page = vsc73xx_read_page,
.write_page = vsc73xx_write_page,
}, {
@@ -471,7 +458,6 @@ static struct phy_driver vsc82xx_driver[] = {
.phy_id_mask = 0x000ffff0,
/* PHY_GBIT_FEATURES */
.config_init = vsc739x_config_init,
- .config_aneg = vsc73xx_config_aneg,
.read_page = vsc73xx_read_page,
.write_page = vsc73xx_write_page,
}, {
diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c
index ec20953..4f032b1 100644
--- a/drivers/net/pse-pd/pse_core.c
+++ b/drivers/net/pse-pd/pse_core.c
@@ -401,9 +401,14 @@ devm_pse_pi_regulator_register(struct pse_controller_dev *pcdev,
rdesc->ops = &pse_pi_ops;
rdesc->owner = pcdev->owner;
- rinit_data->constraints.valid_ops_mask = REGULATOR_CHANGE_STATUS |
- REGULATOR_CHANGE_CURRENT;
- rinit_data->constraints.max_uA = MAX_PI_CURRENT;
+ rinit_data->constraints.valid_ops_mask = REGULATOR_CHANGE_STATUS;
+
+ if (pcdev->ops->pi_set_current_limit) {
+ rinit_data->constraints.valid_ops_mask |=
+ REGULATOR_CHANGE_CURRENT;
+ rinit_data->constraints.max_uA = MAX_PI_CURRENT;
+ }
+
rinit_data->supply_regulator = "vpwr";
rconfig.dev = pcdev->dev;
diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c
index 687d70c..46afb95 100644
--- a/drivers/net/usb/ipheth.c
+++ b/drivers/net/usb/ipheth.c
@@ -286,10 +286,11 @@ static void ipheth_rcvbulk_callback(struct urb *urb)
return;
}
- if (urb->actual_length <= IPHETH_IP_ALIGN) {
- dev->net->stats.rx_length_errors++;
- return;
- }
+ /* iPhone may periodically send URBs with no payload
+ * on the "bulk in" endpoint. It is safe to ignore them.
+ */
+ if (urb->actual_length == 0)
+ goto rx_submit;
/* RX URBs starting with 0x00 0x01 do not encapsulate Ethernet frames,
* but rather are control frames. Their purpose is not documented, and
@@ -298,7 +299,8 @@ static void ipheth_rcvbulk_callback(struct urb *urb)
* URB received from the bulk IN endpoint.
*/
if (unlikely
- (((char *)urb->transfer_buffer)[0] == 0 &&
+ (urb->actual_length == 4 &&
+ ((char *)urb->transfer_buffer)[0] == 0 &&
((char *)urb->transfer_buffer)[1] == 1))
goto rx_submit;
@@ -306,7 +308,6 @@ static void ipheth_rcvbulk_callback(struct urb *urb)
if (retval != 0) {
dev_err(&dev->intf->dev, "%s: callback retval: %d\n",
__func__, retval);
- return;
}
rx_submit:
@@ -354,13 +355,14 @@ static int ipheth_carrier_set(struct ipheth_device *dev)
0x02, /* index */
dev->ctrl_buf, IPHETH_CTRL_BUF_SIZE,
IPHETH_CTRL_TIMEOUT);
- if (retval < 0) {
+ if (retval <= 0) {
dev_err(&dev->intf->dev, "%s: usb_control_msg: %d\n",
__func__, retval);
return retval;
}
- if (dev->ctrl_buf[0] == IPHETH_CARRIER_ON) {
+ if ((retval == 1 && dev->ctrl_buf[0] == IPHETH_CARRIER_ON) ||
+ (retval >= 2 && dev->ctrl_buf[1] == IPHETH_CARRIER_ON)) {
netif_carrier_on(dev->net);
if (dev->tx_urb->status != -EINPROGRESS)
netif_wake_queue(dev->net);
@@ -475,8 +477,8 @@ static int ipheth_close(struct net_device *net)
{
struct ipheth_device *dev = netdev_priv(net);
- cancel_delayed_work_sync(&dev->carrier_work);
netif_stop_queue(net);
+ cancel_delayed_work_sync(&dev->carrier_work);
return 0;
}
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 3f10c72..c6af189 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2867,8 +2867,8 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
if (err < 0)
goto err_xdp_reg_mem_model;
- virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi);
netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, qp_index));
+ virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi);
virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi);
return 0;
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index d08c043..44406e0 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -162,6 +162,60 @@ static int ath12k_dp_prepare_htt_metadata(struct sk_buff *skb)
return 0;
}
+static void ath12k_dp_tx_move_payload(struct sk_buff *skb,
+ unsigned long delta,
+ bool head)
+{
+ unsigned long len = skb->len;
+
+ if (head) {
+ skb_push(skb, delta);
+ memmove(skb->data, skb->data + delta, len);
+ skb_trim(skb, len);
+ } else {
+ skb_put(skb, delta);
+ memmove(skb->data + delta, skb->data, len);
+ skb_pull(skb, delta);
+ }
+}
+
+static int ath12k_dp_tx_align_payload(struct ath12k_base *ab,
+ struct sk_buff **pskb)
+{
+ u32 iova_mask = ab->hw_params->iova_mask;
+ unsigned long offset, delta1, delta2;
+ struct sk_buff *skb2, *skb = *pskb;
+ unsigned int headroom = skb_headroom(skb);
+ int tailroom = skb_tailroom(skb);
+ int ret = 0;
+
+ offset = (unsigned long)skb->data & iova_mask;
+ delta1 = offset;
+ delta2 = iova_mask - offset + 1;
+
+ if (headroom >= delta1) {
+ ath12k_dp_tx_move_payload(skb, delta1, true);
+ } else if (tailroom >= delta2) {
+ ath12k_dp_tx_move_payload(skb, delta2, false);
+ } else {
+ skb2 = skb_realloc_headroom(skb, iova_mask);
+ if (!skb2) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ dev_kfree_skb_any(skb);
+
+ offset = (unsigned long)skb2->data & iova_mask;
+ if (offset)
+ ath12k_dp_tx_move_payload(skb2, offset, true);
+ *pskb = skb2;
+ }
+
+out:
+ return ret;
+}
+
int ath12k_dp_tx(struct ath12k *ar, struct ath12k_vif *arvif,
struct sk_buff *skb)
{
@@ -184,6 +238,7 @@ int ath12k_dp_tx(struct ath12k *ar, struct ath12k_vif *arvif,
bool tcl_ring_retry;
bool msdu_ext_desc = false;
bool add_htt_metadata = false;
+ u32 iova_mask = ab->hw_params->iova_mask;
if (test_bit(ATH12K_FLAG_CRASH_FLUSH, &ar->ab->dev_flags))
return -ESHUTDOWN;
@@ -279,6 +334,23 @@ int ath12k_dp_tx(struct ath12k *ar, struct ath12k_vif *arvif,
goto fail_remove_tx_buf;
}
+ if (iova_mask &&
+ (unsigned long)skb->data & iova_mask) {
+ ret = ath12k_dp_tx_align_payload(ab, &skb);
+ if (ret) {
+ ath12k_warn(ab, "failed to align TX buffer %d\n", ret);
+ /* don't bail out, give original buffer
+ * a chance even unaligned.
+ */
+ goto map;
+ }
+
+ /* hdr is pointing to a wrong place after alignment,
+ * so refresh it for later use.
+ */
+ hdr = (void *)skb->data;
+ }
+map:
ti.paddr = dma_map_single(ab->dev, skb->data, skb->len, DMA_TO_DEVICE);
if (dma_mapping_error(ab->dev, ti.paddr)) {
atomic_inc(&ab->soc_stats.tx_err.misc_fail);
diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c
index 2e11ea7..7b0b6a7 100644
--- a/drivers/net/wireless/ath/ath12k/hw.c
+++ b/drivers/net/wireless/ath/ath12k/hw.c
@@ -924,6 +924,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
.acpi_guid = NULL,
.supports_dynamic_smps_6ghz = true,
+
+ .iova_mask = 0,
},
{
.name = "wcn7850 hw2.0",
@@ -1000,6 +1002,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
.acpi_guid = &wcn7850_uuid,
.supports_dynamic_smps_6ghz = false,
+
+ .iova_mask = ATH12K_PCIE_MAX_PAYLOAD_SIZE - 1,
},
{
.name = "qcn9274 hw2.0",
@@ -1072,6 +1076,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
.acpi_guid = NULL,
.supports_dynamic_smps_6ghz = true,
+
+ .iova_mask = 0,
},
};
diff --git a/drivers/net/wireless/ath/ath12k/hw.h b/drivers/net/wireless/ath/ath12k/hw.h
index e792eb6..b1d302c 100644
--- a/drivers/net/wireless/ath/ath12k/hw.h
+++ b/drivers/net/wireless/ath/ath12k/hw.h
@@ -96,6 +96,8 @@
#define ATH12K_M3_FILE "m3.bin"
#define ATH12K_REGDB_FILE_NAME "regdb.bin"
+#define ATH12K_PCIE_MAX_PAYLOAD_SIZE 128
+
enum ath12k_hw_rate_cck {
ATH12K_HW_RATE_CCK_LP_11M = 0,
ATH12K_HW_RATE_CCK_LP_5_5M,
@@ -215,6 +217,8 @@ struct ath12k_hw_params {
const guid_t *acpi_guid;
bool supports_dynamic_smps_6ghz;
+
+ u32 iova_mask;
};
struct ath12k_hw_ops {
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 8106297..ce41c81 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -9193,6 +9193,7 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah)
hw->vif_data_size = sizeof(struct ath12k_vif);
hw->sta_data_size = sizeof(struct ath12k_sta);
+ hw->extra_tx_headroom = ab->hw_params->iova_mask;
wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_STA_TX_PWR);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 1585a56..d4cc5fa 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -4320,9 +4320,16 @@ brcmf_pmksa_v3_op(struct brcmf_if *ifp, struct cfg80211_pmksa *pmksa,
/* Single PMK operation */
pmk_op->count = cpu_to_le16(1);
length += sizeof(struct brcmf_pmksa_v3);
- memcpy(pmk_op->pmk[0].bssid, pmksa->bssid, ETH_ALEN);
- memcpy(pmk_op->pmk[0].pmkid, pmksa->pmkid, WLAN_PMKID_LEN);
- pmk_op->pmk[0].pmkid_len = WLAN_PMKID_LEN;
+ if (pmksa->bssid)
+ memcpy(pmk_op->pmk[0].bssid, pmksa->bssid, ETH_ALEN);
+ if (pmksa->pmkid) {
+ memcpy(pmk_op->pmk[0].pmkid, pmksa->pmkid, WLAN_PMKID_LEN);
+ pmk_op->pmk[0].pmkid_len = WLAN_PMKID_LEN;
+ }
+ if (pmksa->ssid && pmksa->ssid_len) {
+ memcpy(pmk_op->pmk[0].ssid.SSID, pmksa->ssid, pmksa->ssid_len);
+ pmk_op->pmk[0].ssid.SSID_len = pmksa->ssid_len;
+ }
pmk_op->pmk[0].time_left = cpu_to_le32(alive ? BRCMF_PMKSA_NO_EXPIRY : 0);
}
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index 79774c8..8c8880b 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -725,22 +725,25 @@ int iwl_acpi_get_wgds_table(struct iwl_fw_runtime *fwrt)
entry = &wifi_pkg->package.elements[entry_idx];
entry_idx++;
if (entry->type != ACPI_TYPE_INTEGER ||
- entry->integer.value > num_profiles) {
+ entry->integer.value > num_profiles ||
+ entry->integer.value <
+ rev_data[idx].min_profiles) {
ret = -EINVAL;
goto out_free;
}
- num_profiles = entry->integer.value;
/*
- * this also validates >= min_profiles since we
- * otherwise wouldn't have gotten the data when
- * looking up in ACPI
+ * Check to see if we received package count
+ * same as max # of profiles
*/
if (wifi_pkg->package.count !=
hdr_size + profile_size * num_profiles) {
ret = -EINVAL;
goto out_free;
}
+
+ /* Number of valid profiles */
+ num_profiles = entry->integer.value;
}
goto read_table;
}
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index fa57df3..fb2ea38 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -3348,7 +3348,7 @@ void iwl_fw_dbg_stop_restart_recording(struct iwl_fw_runtime *fwrt,
{
int ret __maybe_unused = 0;
- if (test_bit(STATUS_FW_ERROR, &fwrt->trans->status))
+ if (!iwl_trans_fw_running(fwrt->trans))
return;
if (fw_has_capa(&fwrt->fw->ucode_capa,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
index 595fa6d..8ef5ed2 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
@@ -85,6 +85,10 @@ struct iwl_cfg;
* May sleep
* @wimax_active: invoked when WiMax becomes active. May sleep
* @time_point: called when transport layer wants to collect debug data
+ * @device_powered_off: called upon resume from hibernation but not only.
+ * Op_mode needs to reset its internal state because the device did not
+ * survive the system state transition. The firmware is no longer running,
+ * etc...
*/
struct iwl_op_mode_ops {
struct iwl_op_mode *(*start)(struct iwl_trans *trans,
@@ -107,6 +111,7 @@ struct iwl_op_mode_ops {
void (*time_point)(struct iwl_op_mode *op_mode,
enum iwl_fw_ini_time_point tp_id,
union iwl_dbg_tlv_tp_data *tp_data);
+ void (*device_powered_off)(struct iwl_op_mode *op_mode);
};
int iwl_opmode_register(const char *name, const struct iwl_op_mode_ops *ops);
@@ -204,4 +209,11 @@ static inline void iwl_op_mode_time_point(struct iwl_op_mode *op_mode,
op_mode->ops->time_point(op_mode, tp_id, tp_data);
}
+static inline void iwl_op_mode_device_powered_off(struct iwl_op_mode *op_mode)
+{
+ if (!op_mode || !op_mode->ops || !op_mode->ops->device_powered_off)
+ return;
+ op_mode->ops->device_powered_off(op_mode);
+}
+
#endif /* __iwl_op_mode_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 6148acb..0ef48ef 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -1128,8 +1128,8 @@ static inline void iwl_trans_fw_error(struct iwl_trans *trans, bool sync)
/* prevent double restarts due to the same erroneous FW */
if (!test_and_set_bit(STATUS_FW_ERROR, &trans->status)) {
- iwl_op_mode_nic_error(trans->op_mode, sync);
trans->state = IWL_TRANS_NO_FW;
+ iwl_op_mode_nic_error(trans->op_mode, sync);
}
}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index b4d6505..99a541d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -3439,6 +3439,16 @@ static int __iwl_mvm_resume(struct iwl_mvm *mvm, bool test)
mutex_lock(&mvm->mutex);
+ /* Apparently, the device went away and device_powered_off() was called,
+ * don't even try to read the rt_status, the device is currently
+ * inaccessible.
+ */
+ if (!test_bit(IWL_MVM_STATUS_IN_D3, &mvm->status)) {
+ IWL_INFO(mvm,
+ "Can't resume, device_powered_off() was called during wowlan\n");
+ goto err;
+ }
+
mvm->last_reset_or_resume_time_jiffies = jiffies;
/* get the BSS vif pointer again */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 835a05b9..625ccf5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -5818,6 +5818,10 @@ static void iwl_mvm_flush_no_vif(struct iwl_mvm *mvm, u32 queues, bool drop)
int i;
if (!iwl_mvm_has_new_tx_api(mvm)) {
+ /* we can't ask the firmware anything if it is dead */
+ if (test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED,
+ &mvm->status))
+ return;
if (drop) {
guard(mvm)(mvm);
iwl_mvm_flush_tx_path(mvm,
@@ -5911,8 +5915,11 @@ void iwl_mvm_mac_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
/* this can take a while, and we may need/want other operations
* to succeed while doing this, so do it without the mutex held
+ * If the firmware is dead, this can't work...
*/
- if (!drop && !iwl_mvm_has_new_tx_api(mvm))
+ if (!drop && !iwl_mvm_has_new_tx_api(mvm) &&
+ !test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED,
+ &mvm->status))
iwl_trans_wait_tx_queues_empty(mvm->trans, msk);
}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index b7dcae7..b9daaff 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -1198,10 +1198,12 @@ static void iwl_mvm_trig_link_selection(struct wiphy *wiphy,
struct iwl_mvm *mvm =
container_of(wk, struct iwl_mvm, trig_link_selection_wk);
+ mutex_lock(&mvm->mutex);
ieee80211_iterate_active_interfaces(mvm->hw,
IEEE80211_IFACE_ITER_NORMAL,
iwl_mvm_find_link_selection_vif,
NULL);
+ mutex_unlock(&mvm->mutex);
}
static struct iwl_op_mode *
@@ -1511,6 +1513,8 @@ void iwl_mvm_stop_device(struct iwl_mvm *mvm)
clear_bit(IWL_MVM_STATUS_FIRMWARE_RUNNING, &mvm->status);
+ iwl_mvm_pause_tcm(mvm, false);
+
iwl_fw_dbg_stop_sync(&mvm->fwrt);
iwl_trans_stop_device(mvm->trans);
iwl_free_fw_paging(&mvm->fwrt);
@@ -2090,6 +2094,20 @@ static void iwl_op_mode_mvm_time_point(struct iwl_op_mode *op_mode,
iwl_dbg_tlv_time_point(&mvm->fwrt, tp_id, tp_data);
}
+static void iwl_op_mode_mvm_device_powered_off(struct iwl_op_mode *op_mode)
+{
+ struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
+
+ mutex_lock(&mvm->mutex);
+ clear_bit(IWL_MVM_STATUS_IN_D3, &mvm->status);
+ mvm->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED;
+ iwl_mvm_stop_device(mvm);
+#ifdef CONFIG_PM
+ mvm->fast_resume = false;
+#endif
+ mutex_unlock(&mvm->mutex);
+}
+
#define IWL_MVM_COMMON_OPS \
/* these could be differentiated */ \
.queue_full = iwl_mvm_stop_sw_queue, \
@@ -2102,7 +2120,8 @@ static void iwl_op_mode_mvm_time_point(struct iwl_op_mode *op_mode,
/* as we only register one, these MUST be common! */ \
.start = iwl_op_mode_mvm_start, \
.stop = iwl_op_mode_mvm_stop, \
- .time_point = iwl_op_mode_mvm_time_point
+ .time_point = iwl_op_mode_mvm_time_point, \
+ .device_powered_off = iwl_op_mode_mvm_device_powered_off
static const struct iwl_op_mode_ops iwl_mvm_ops = {
IWL_MVM_COMMON_OPS,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 8e0df31..1cc9c42 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -48,6 +48,8 @@
/* Number of iterations on the channel for mei filtered scan */
#define IWL_MEI_SCAN_NUM_ITER 5U
+#define WFA_TPC_IE_LEN 9
+
struct iwl_mvm_scan_timing_params {
u32 suspend_time;
u32 max_out_time;
@@ -303,8 +305,8 @@ static int iwl_mvm_max_scan_ie_fw_cmd_room(struct iwl_mvm *mvm)
max_probe_len = SCAN_OFFLOAD_PROBE_REQ_SIZE;
- /* we create the 802.11 header and SSID element */
- max_probe_len -= 24 + 2;
+ /* we create the 802.11 header SSID element and WFA TPC element */
+ max_probe_len -= 24 + 2 + WFA_TPC_IE_LEN;
/* DS parameter set element is added on 2.4GHZ band if required */
if (iwl_mvm_rrm_scan_needed(mvm))
@@ -731,8 +733,6 @@ static u8 *iwl_mvm_copy_and_insert_ds_elem(struct iwl_mvm *mvm, const u8 *ies,
return newpos;
}
-#define WFA_TPC_IE_LEN 9
-
static void iwl_mvm_add_tpc_report_ie(u8 *pos)
{
pos[0] = WLAN_EID_VENDOR_SPECIFIC;
@@ -837,8 +837,8 @@ static inline bool iwl_mvm_scan_fits(struct iwl_mvm *mvm, int n_ssids,
return ((n_ssids <= PROBE_OPTION_MAX) &&
(n_channels <= mvm->fw->ucode_capa.n_scan_channels) &
(ies->common_ie_len +
- ies->len[NL80211_BAND_2GHZ] +
- ies->len[NL80211_BAND_5GHZ] <=
+ ies->len[NL80211_BAND_2GHZ] + ies->len[NL80211_BAND_5GHZ] +
+ ies->len[NL80211_BAND_6GHZ] <=
iwl_mvm_max_scan_ie_fw_cmd_room(mvm)));
}
@@ -1659,6 +1659,17 @@ iwl_mvm_umac_scan_cfg_channels_v7(struct iwl_mvm *mvm,
cfg->v2.channel_num = channels[i]->hw_value;
if (cfg80211_channel_is_psc(channels[i]))
cfg->flags = 0;
+
+ if (band == NL80211_BAND_6GHZ) {
+ /* 6 GHz channels should only appear in a scan request
+ * that has scan_6ghz set. The only exception is MLO
+ * scan, which has to be passive.
+ */
+ WARN_ON_ONCE(cfg->flags != 0);
+ cfg->flags =
+ cpu_to_le32(IWL_UHB_CHAN_CFG_FLAG_FORCE_PASSIVE);
+ }
+
cfg->v2.iter_count = 1;
cfg->v2.iter_interval = 0;
if (version < 17)
@@ -3168,18 +3179,16 @@ int iwl_mvm_sched_scan_start(struct iwl_mvm *mvm,
params.n_channels = j;
}
- if (non_psc_included &&
- !iwl_mvm_scan_fits(mvm, req->n_ssids, ies, params.n_channels)) {
- kfree(params.channels);
- return -ENOBUFS;
+ if (!iwl_mvm_scan_fits(mvm, req->n_ssids, ies, params.n_channels)) {
+ ret = -ENOBUFS;
+ goto out;
}
uid = iwl_mvm_build_scan_cmd(mvm, vif, &hcmd, ¶ms, type);
-
- if (non_psc_included)
- kfree(params.channels);
- if (uid < 0)
- return uid;
+ if (uid < 0) {
+ ret = uid;
+ goto out;
+ }
ret = iwl_mvm_send_cmd(mvm, &hcmd);
if (!ret) {
@@ -3197,6 +3206,9 @@ int iwl_mvm_sched_scan_start(struct iwl_mvm *mvm,
mvm->sched_scan_pass_all = SCHED_SCAN_PASS_ALL_DISABLED;
}
+out:
+ if (non_psc_included)
+ kfree(params.channels);
return ret;
}
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
index e63efbf..ae93a72 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
@@ -89,7 +89,8 @@ iwl_pcie_ctxt_info_dbg_enable(struct iwl_trans *trans,
}
break;
default:
- IWL_ERR(trans, "WRT: Invalid buffer destination\n");
+ IWL_DEBUG_FW(trans, "WRT: Invalid buffer destination (%d)\n",
+ le32_to_cpu(fw_mon_cfg->buf_location));
}
out:
if (dbg_flags)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 9ad4346..84fd932 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1577,11 +1577,12 @@ static int iwl_pci_suspend(struct device *device)
return 0;
}
-static int iwl_pci_resume(struct device *device)
+static int _iwl_pci_resume(struct device *device, bool restore)
{
struct pci_dev *pdev = to_pci_dev(device);
struct iwl_trans *trans = pci_get_drvdata(pdev);
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+ bool device_was_powered_off = false;
/* Before you put code here, think about WoWLAN. You cannot check here
* whether WoWLAN is enabled or not, and your code will run even if
@@ -1597,6 +1598,26 @@ static int iwl_pci_resume(struct device *device)
if (!trans->op_mode)
return 0;
+ /*
+ * Scratch value was altered, this means the device was powered off, we
+ * need to reset it completely.
+ * Note: MAC (bits 0:7) will be cleared upon suspend even with wowlan,
+ * so assume that any bits there mean that the device is usable.
+ */
+ if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ &&
+ !iwl_read32(trans, CSR_FUNC_SCRATCH))
+ device_was_powered_off = true;
+
+ if (restore || device_was_powered_off) {
+ trans->state = IWL_TRANS_NO_FW;
+ /* Hope for the best here ... If one of those steps fails we
+ * won't really know how to recover.
+ */
+ iwl_pcie_prepare_card_hw(trans);
+ iwl_finish_nic_init(trans);
+ iwl_op_mode_device_powered_off(trans->op_mode);
+ }
+
/* In WOWLAN, let iwl_trans_pcie_d3_resume do the rest of the work */
if (test_bit(STATUS_DEVICE_ENABLED, &trans->status))
return 0;
@@ -1617,9 +1638,23 @@ static int iwl_pci_resume(struct device *device)
return 0;
}
+static int iwl_pci_restore(struct device *device)
+{
+ return _iwl_pci_resume(device, true);
+}
+
+static int iwl_pci_resume(struct device *device)
+{
+ return _iwl_pci_resume(device, false);
+}
+
static const struct dev_pm_ops iwl_dev_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(iwl_pci_suspend,
- iwl_pci_resume)
+ .suspend = pm_sleep_ptr(iwl_pci_suspend),
+ .resume = pm_sleep_ptr(iwl_pci_resume),
+ .freeze = pm_sleep_ptr(iwl_pci_suspend),
+ .thaw = pm_sleep_ptr(iwl_pci_resume),
+ .poweroff = pm_sleep_ptr(iwl_pci_suspend),
+ .restore = pm_sleep_ptr(iwl_pci_restore),
};
#define IWL_PM_OPS (&iwl_dev_pm_ops)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index b59de4f..27a7e0b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -639,7 +639,8 @@ void iwl_trans_pcie_tx_reset(struct iwl_trans *trans);
int iwl_pcie_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq,
int slots_num, bool cmd_queue);
-dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, void *addr);
+dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, unsigned int offset,
+ unsigned int len);
struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb,
struct iwl_cmd_meta *cmd_meta,
u8 **hdr, unsigned int hdr_room);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 2e780fb..b1846abb 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -168,6 +168,7 @@ static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans,
struct ieee80211_hdr *hdr = (void *)skb->data;
unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room;
unsigned int mss = skb_shinfo(skb)->gso_size;
+ unsigned int data_offset = 0;
dma_addr_t start_hdr_phys;
u16 length, amsdu_pad;
u8 *start_hdr;
@@ -260,7 +261,8 @@ static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans,
int ret;
tb_len = min_t(unsigned int, tso.size, data_left);
- tb_phys = iwl_pcie_get_sgt_tb_phys(sgt, tso.data);
+ tb_phys = iwl_pcie_get_sgt_tb_phys(sgt, data_offset,
+ tb_len);
/* Not a real mapping error, use direct comparison */
if (unlikely(tb_phys == DMA_MAPPING_ERROR))
goto out_err;
@@ -272,6 +274,7 @@ static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans,
goto out_err;
data_left -= tb_len;
+ data_offset += tb_len;
tso_build_data(skb, &tso, tb_len);
}
}
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 22d482a..9fe050f 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -1814,23 +1814,31 @@ static void *iwl_pcie_get_page_hdr(struct iwl_trans *trans,
/**
* iwl_pcie_get_sgt_tb_phys - Find TB address in mapped SG list
* @sgt: scatter gather table
- * @addr: Virtual address
+ * @offset: Offset into the mapped memory (i.e. SKB payload data)
+ * @len: Length of the area
*
- * Find the entry that includes the address for the given address and return
- * correct physical address for the TB entry.
+ * Find the DMA address that corresponds to the SKB payload data at the
+ * position given by @offset.
*
* Returns: Address for TB entry
*/
-dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, void *addr)
+dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, unsigned int offset,
+ unsigned int len)
{
struct scatterlist *sg;
+ unsigned int sg_offset = 0;
int i;
+ /*
+ * Search the mapped DMA areas in the SG for the area that contains the
+ * data at offset with the given length.
+ */
for_each_sgtable_dma_sg(sgt, sg, i) {
- if (addr >= sg_virt(sg) &&
- (u8 *)addr < (u8 *)sg_virt(sg) + sg_dma_len(sg))
- return sg_dma_address(sg) +
- ((unsigned long)addr - (unsigned long)sg_virt(sg));
+ if (offset >= sg_offset &&
+ offset + len <= sg_offset + sg_dma_len(sg))
+ return sg_dma_address(sg) + offset - sg_offset;
+
+ sg_offset += sg_dma_len(sg);
}
WARN_ON_ONCE(1);
@@ -1875,7 +1883,9 @@ struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb,
sg_init_table(sgt->sgl, skb_shinfo(skb)->nr_frags + 1);
- sgt->orig_nents = skb_to_sgvec(skb, sgt->sgl, 0, skb->len);
+ /* Only map the data, not the header (it is copied to the TSO page) */
+ sgt->orig_nents = skb_to_sgvec(skb, sgt->sgl, skb_headlen(skb),
+ skb->data_len);
if (WARN_ON_ONCE(sgt->orig_nents <= 0))
return NULL;
@@ -1900,6 +1910,7 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
struct ieee80211_hdr *hdr = (void *)skb->data;
unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room;
unsigned int mss = skb_shinfo(skb)->gso_size;
+ unsigned int data_offset = 0;
u16 length, iv_len, amsdu_pad;
dma_addr_t start_hdr_phys;
u8 *start_hdr, *pos_hdr;
@@ -2000,7 +2011,7 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
data_left);
dma_addr_t tb_phys;
- tb_phys = iwl_pcie_get_sgt_tb_phys(sgt, tso.data);
+ tb_phys = iwl_pcie_get_sgt_tb_phys(sgt, data_offset, size);
/* Not a real mapping error, use direct comparison */
if (unlikely(tb_phys == DMA_MAPPING_ERROR))
return -EINVAL;
@@ -2011,6 +2022,7 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
tb_phys, size);
data_left -= size;
+ data_offset += size;
tso_build_data(skb, &tso, size);
}
}
diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 155eb0f..bf35c92 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -4363,11 +4363,27 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
if (ISSUPP_ADHOC_ENABLED(adapter->fw_cap_info))
wiphy->interface_modes |= BIT(NL80211_IFTYPE_ADHOC);
- wiphy->bands[NL80211_BAND_2GHZ] = &mwifiex_band_2ghz;
- if (adapter->config_bands & BAND_A)
- wiphy->bands[NL80211_BAND_5GHZ] = &mwifiex_band_5ghz;
- else
+ wiphy->bands[NL80211_BAND_2GHZ] = devm_kmemdup(adapter->dev,
+ &mwifiex_band_2ghz,
+ sizeof(mwifiex_band_2ghz),
+ GFP_KERNEL);
+ if (!wiphy->bands[NL80211_BAND_2GHZ]) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ if (adapter->config_bands & BAND_A) {
+ wiphy->bands[NL80211_BAND_5GHZ] = devm_kmemdup(adapter->dev,
+ &mwifiex_band_5ghz,
+ sizeof(mwifiex_band_5ghz),
+ GFP_KERNEL);
+ if (!wiphy->bands[NL80211_BAND_5GHZ]) {
+ ret = -ENOMEM;
+ goto err;
+ }
+ } else {
wiphy->bands[NL80211_BAND_5GHZ] = NULL;
+ }
if (adapter->drcs_enabled && ISSUPP_DRCS_ENABLED(adapter->fw_cap_info))
wiphy->iface_combinations = &mwifiex_iface_comb_ap_sta_drcs;
@@ -4461,8 +4477,7 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
if (ret < 0) {
mwifiex_dbg(adapter, ERROR,
"%s: wiphy_register failed: %d\n", __func__, ret);
- wiphy_free(wiphy);
- return ret;
+ goto err;
}
if (!adapter->regd) {
@@ -4504,4 +4519,9 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
adapter->wiphy = wiphy;
return ret;
+
+err:
+ wiphy_free(wiphy);
+
+ return ret;
}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 1bab93d..23b2288 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -1183,7 +1183,7 @@ static void mt7921_ipv6_addr_change(struct ieee80211_hw *hw,
struct inet6_dev *idev)
{
struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
- struct mt792x_dev *dev = mvif->phy->dev;
+ struct mt792x_dev *dev = mt792x_hw_dev(hw);
struct inet6_ifaddr *ifa;
struct in6_addr ns_addrs[IEEE80211_BSS_ARP_ADDR_LIST_LEN];
struct sk_buff *skb;
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c
index 700c6e2..ff458fb 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c
@@ -181,11 +181,11 @@ static void _rtl92du_init_queue_reserved_page(struct ieee80211_hw *hw,
struct rtl_hal *rtlhal = rtl_hal(rtlpriv);
u32 txqpagenum, txqpageunit;
u32 txqremainingpage;
+ u32 value32 = 0;
u32 numhq = 0;
u32 numlq = 0;
u32 numnq = 0;
u32 numpubq;
- u32 value32;
if (rtlhal->macphymode != SINGLEMAC_SINGLEPHY) {
numpubq = NORMAL_PAGE_NUM_PUBQ_92D_DUAL_MAC;
diff --git a/drivers/net/wireless/silabs/wfx/sta.c b/drivers/net/wireless/silabs/wfx/sta.c
index 216d43c..7c04810 100644
--- a/drivers/net/wireless/silabs/wfx/sta.c
+++ b/drivers/net/wireless/silabs/wfx/sta.c
@@ -352,8 +352,11 @@ static int wfx_set_mfp_ap(struct wfx_vif *wvif)
ptr = (u16 *)cfg80211_find_ie(WLAN_EID_RSN, skb->data + ieoffset,
skb->len - ieoffset);
- if (unlikely(!ptr))
+ if (!ptr) {
+ /* No RSN IE is fine in open networks */
+ ret = 0;
goto free_skb;
+ }
ptr += pairwise_cipher_suite_count_offset;
if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb)))
diff --git a/drivers/nfc/pn533/pn533.c b/drivers/nfc/pn533/pn533.c
index b19c39d..e2bc673 100644
--- a/drivers/nfc/pn533/pn533.c
+++ b/drivers/nfc/pn533/pn533.c
@@ -1723,6 +1723,11 @@ static int pn533_start_poll(struct nfc_dev *nfc_dev,
}
pn533_poll_create_mod_list(dev, im_protocols, tm_protocols);
+ if (!dev->poll_mod_count) {
+ nfc_err(dev->dev,
+ "Poll mod list is empty\n");
+ return -EINVAL;
+ }
/* Do not always start polling from the same modulation */
get_random_bytes(&rand_mod, sizeof(rand_mod));
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 1ae8b23..210fb77 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -498,7 +498,7 @@ static int pmem_attach_disk(struct device *dev,
}
if (fua)
lim.features |= BLK_FEAT_FUA;
- if (is_nd_pfn(dev))
+ if (is_nd_pfn(dev) || pmem_should_map_pages(dev))
lim.features |= BLK_FEAT_DAX;
if (!devm_request_mem_region(dev, res->start, resource_size(res),
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 33fa01c..0dc8bcc 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4612,7 +4612,6 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
{
nvme_mpath_stop(ctrl);
nvme_auth_stop(ctrl);
- nvme_stop_keep_alive(ctrl);
nvme_stop_failfast_work(ctrl);
flush_work(&ctrl->async_event_work);
cancel_work_sync(&ctrl->fw_act_work);
@@ -4648,6 +4647,7 @@ EXPORT_SYMBOL_GPL(nvme_start_ctrl);
void nvme_uninit_ctrl(struct nvme_ctrl *ctrl)
{
+ nvme_stop_keep_alive(ctrl);
nvme_hwmon_exit(ctrl);
nvme_fault_inject_fini(&ctrl->fault_inject);
dev_pm_qos_hide_latency_tolerance(ctrl->device);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index ae5314d..da5794713 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -301,7 +301,6 @@ struct nvme_ctrl {
struct opal_dev *opal_dev;
- char name[12];
u16 cntlid;
u16 mtfa;
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index c94203c..8fd6310 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -344,7 +344,8 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
struct device_node *p;
const __be32 *addr;
u32 intsize;
- int i, res;
+ int i, res, addr_len;
+ __be32 addr_buf[3] = { 0 };
pr_debug("of_irq_parse_one: dev=%pOF, index=%d\n", device, index);
@@ -353,13 +354,19 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
return of_irq_parse_oldworld(device, index, out_irq);
/* Get the reg property (if any) */
- addr = of_get_property(device, "reg", NULL);
+ addr = of_get_property(device, "reg", &addr_len);
+
+ /* Prevent out-of-bounds read in case of longer interrupt parent address size */
+ if (addr_len > (3 * sizeof(__be32)))
+ addr_len = 3 * sizeof(__be32);
+ if (addr)
+ memcpy(addr_buf, addr, addr_len);
/* Try the new-style interrupts-extended first */
res = of_parse_phandle_with_args(device, "interrupts-extended",
"#interrupt-cells", index, out_irq);
if (!res)
- return of_irq_parse_raw(addr, out_irq);
+ return of_irq_parse_raw(addr_buf, out_irq);
/* Look for the interrupt parent. */
p = of_irq_find_parent(device);
@@ -389,7 +396,7 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
/* Check if there are any interrupt-map translations to process */
- res = of_irq_parse_raw(addr, out_irq);
+ res = of_irq_parse_raw(addr_buf, out_irq);
out:
of_node_put(p);
return res;
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 389d4ea..ef622d4 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -592,7 +592,7 @@ static int __init of_platform_default_populate_init(void)
* This can happen for example on DT systems that do EFI
* booting and may provide a GOP handle to the EFI stub.
*/
- sysfb_disable();
+ sysfb_disable(NULL);
of_platform_device_create(node, NULL, NULL);
of_node_put(node);
}
diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c
index 236229f..a9b263f 100644
--- a/drivers/pci/controller/dwc/pcie-qcom-ep.c
+++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c
@@ -58,6 +58,7 @@
#define PARF_DEBUG_CNT_AUX_CLK_IN_L1SUB_L2 0xc88
#define PARF_DEVICE_TYPE 0x1000
#define PARF_BDF_TO_SID_CFG 0x2c00
+#define PARF_INT_ALL_5_MASK 0x2dcc
/* PARF_INT_ALL_{STATUS/CLEAR/MASK} register fields */
#define PARF_INT_ALL_LINK_DOWN BIT(1)
@@ -127,6 +128,9 @@
/* PARF_CFG_BITS register fields */
#define PARF_CFG_BITS_REQ_EXIT_L1SS_MSI_LTR_EN BIT(1)
+/* PARF_INT_ALL_5_MASK fields */
+#define PARF_INT_ALL_5_MHI_RAM_DATA_PARITY_ERR BIT(0)
+
/* ELBI registers */
#define ELBI_SYS_STTS 0x08
#define ELBI_CS2_ENABLE 0xa4
@@ -158,10 +162,12 @@ enum qcom_pcie_ep_link_status {
* struct qcom_pcie_ep_cfg - Per SoC config struct
* @hdma_support: HDMA support on this SoC
* @override_no_snoop: Override NO_SNOOP attribute in TLP to enable cache snooping
+ * @disable_mhi_ram_parity_check: Disable MHI RAM data parity error check
*/
struct qcom_pcie_ep_cfg {
bool hdma_support;
bool override_no_snoop;
+ bool disable_mhi_ram_parity_check;
};
/**
@@ -480,6 +486,12 @@ static int qcom_pcie_perst_deassert(struct dw_pcie *pci)
PARF_INT_ALL_LINK_UP | PARF_INT_ALL_EDMA;
writel_relaxed(val, pcie_ep->parf + PARF_INT_ALL_MASK);
+ if (pcie_ep->cfg && pcie_ep->cfg->disable_mhi_ram_parity_check) {
+ val = readl_relaxed(pcie_ep->parf + PARF_INT_ALL_5_MASK);
+ val &= ~PARF_INT_ALL_5_MHI_RAM_DATA_PARITY_ERR;
+ writel_relaxed(val, pcie_ep->parf + PARF_INT_ALL_5_MASK);
+ }
+
ret = dw_pcie_ep_init_registers(&pcie_ep->pci.ep);
if (ret) {
dev_err(dev, "Failed to complete initialization: %d\n", ret);
@@ -901,6 +913,7 @@ static void qcom_pcie_ep_remove(struct platform_device *pdev)
static const struct qcom_pcie_ep_cfg cfg_1_34_0 = {
.hdma_support = true,
.override_no_snoop = true,
+ .disable_mhi_ram_parity_check = true,
};
static const struct of_device_id qcom_pcie_ep_match[] = {
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 0180edf..6f953e3 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -261,6 +261,7 @@ struct qcom_pcie {
const struct qcom_pcie_cfg *cfg;
struct dentry *debugfs;
bool suspended;
+ bool use_pm_opp;
};
#define to_qcom_pcie(x) dev_get_drvdata((x)->dev)
@@ -1433,7 +1434,7 @@ static void qcom_pcie_icc_opp_update(struct qcom_pcie *pcie)
dev_err(pci->dev, "Failed to set bandwidth for PCIe-MEM interconnect path: %d\n",
ret);
}
- } else {
+ } else if (pcie->use_pm_opp) {
freq_mbps = pcie_dev_speed_mbps(pcie_link_speed[speed]);
if (freq_mbps < 0)
return;
@@ -1592,6 +1593,8 @@ static int qcom_pcie_probe(struct platform_device *pdev)
max_freq);
goto err_pm_runtime_put;
}
+
+ pcie->use_pm_opp = true;
} else {
/* Skip ICC init if OPP is supported as it is handled by OPP */
ret = qcom_pcie_icc_init(pcie);
@@ -1683,7 +1686,7 @@ static int qcom_pcie_suspend_noirq(struct device *dev)
if (ret)
dev_err(dev, "Failed to disable CPU-PCIe interconnect path: %d\n", ret);
- if (!pcie->icc_mem)
+ if (pcie->use_pm_opp)
dev_pm_opp_set_opp(pcie->pci->dev, NULL);
}
return ret;
diff --git a/drivers/phy/freescale/phy-fsl-imx8mq-usb.c b/drivers/phy/freescale/phy-fsl-imx8mq-usb.c
index 0b9a59d5b..adc6394 100644
--- a/drivers/phy/freescale/phy-fsl-imx8mq-usb.c
+++ b/drivers/phy/freescale/phy-fsl-imx8mq-usb.c
@@ -176,7 +176,7 @@ static void imx8m_get_phy_tuning_data(struct imx8mq_usb_phy *imx_phy)
imx_phy->comp_dis_tune =
phy_comp_dis_tune_from_property(imx_phy->comp_dis_tune);
- if (device_property_read_u32(dev, "fsl,pcs-tx-deemph-3p5db-attenuation-db",
+ if (device_property_read_u32(dev, "fsl,phy-pcs-tx-deemph-3p5db-attenuation-db",
&imx_phy->pcs_tx_deemph_3p5db))
imx_phy->pcs_tx_deemph_3p5db = PHY_TUNE_DEFAULT;
else
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
index 5b36cc7..06cd978 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
@@ -1245,8 +1245,8 @@ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_serdes_tbl[] = {
static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_ln_shrd_tbl[] = {
QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RXCLK_DIV2_CTRL, 0x01),
QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_DFE_DAC_ENABLE1, 0x88),
- QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_TX_ADAPT_POST_THRESH1, 0x00),
- QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_TX_ADAPT_POST_THRESH2, 0x1f),
+ QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_TX_ADAPT_POST_THRESH1, 0x02),
+ QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_TX_ADAPT_POST_THRESH2, 0x0d),
QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MODE_RATE_0_1_B0, 0xd4),
QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MODE_RATE_0_1_B1, 0x12),
QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MODE_RATE_0_1_B2, 0xdb),
@@ -1263,6 +1263,7 @@ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_ln_shrd_tbl[] = {
QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MARG_COARSE_THRESH4_RATE3, 0x1f),
QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MARG_COARSE_THRESH5_RATE3, 0x1f),
QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MARG_COARSE_THRESH6_RATE3, 0x1f),
+ QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_SUMMER_CAL_SPD_MODE, 0x5b),
};
static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_tx_tbl[] = {
@@ -1286,12 +1287,15 @@ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_rx_tbl[] = {
QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_DFE_1, 0x01),
QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_DFE_2, 0x01),
QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_DFE_3, 0x45),
- QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_VGA_CAL_MAN_VAL, 0x0b),
+ QMP_PHY_INIT_CFG_LANE(QSERDES_V6_20_RX_VGA_CAL_MAN_VAL, 0x0a, 1),
+ QMP_PHY_INIT_CFG_LANE(QSERDES_V6_20_RX_VGA_CAL_MAN_VAL, 0x0b, 2),
+ QMP_PHY_INIT_CFG(QSERDES_V6_20_VGA_CAL_CNTRL1, 0x00),
QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_GM_CAL, 0x0d),
QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_EQU_ADAPTOR_CNTRL4, 0x0b),
QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_SIGDET_ENABLES, 0x1c),
QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_PHPRE_CTRL, 0x20),
- QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38),
+ QMP_PHY_INIT_CFG_LANE(QSERDES_V6_20_RX_DFE_CTLE_POST_CAL_OFFSET, 0x3a, 1),
+ QMP_PHY_INIT_CFG_LANE(QSERDES_V6_20_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38, 2),
QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_Q_PI_INTRINSIC_BIAS_RATE32, 0x39),
QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B0, 0x14),
QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B1, 0xb3),
@@ -1307,6 +1311,7 @@ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_rx_tbl[] = {
QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B4, 0x4b),
QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B5, 0x76),
QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B6, 0xff),
+ QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_TX_ADPT_CTRL, 0x10),
};
static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_pcs_tbl[] = {
@@ -1314,6 +1319,8 @@ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_pcs_tbl[] = {
QMP_PHY_INIT_CFG(QPHY_V6_20_PCS_RX_SIGDET_LVL, 0xcc),
QMP_PHY_INIT_CFG(QPHY_V6_20_PCS_EQ_CONFIG4, 0x00),
QMP_PHY_INIT_CFG(QPHY_V6_20_PCS_EQ_CONFIG5, 0x22),
+ QMP_PHY_INIT_CFG(QPHY_V6_20_PCS_TX_RX_CONFIG1, 0x04),
+ QMP_PHY_INIT_CFG(QPHY_V6_20_PCS_TX_RX_CONFIG2, 0x02),
};
static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_pcs_misc_tbl[] = {
@@ -1324,11 +1331,13 @@ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_pcs_misc_tbl[] = {
QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G4_PRE_GAIN, 0x2e),
QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_RX_MARGINING_CONFIG1, 0x03),
QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_RX_MARGINING_CONFIG3, 0x28),
+ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G3_RXEQEVAL_TIME, 0x27),
+ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G4_RXEQEVAL_TIME, 0x27),
QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_TX_RX_CONFIG, 0xc0),
QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_POWER_STATE_CONFIG2, 0x1d),
- QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_RX_MARGINING_CONFIG5, 0x0f),
- QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G3_FOM_EQ_CONFIG5, 0xf2),
- QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G4_FOM_EQ_CONFIG5, 0xf2),
+ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_RX_MARGINING_CONFIG5, 0x18),
+ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G3_FOM_EQ_CONFIG5, 0x7a),
+ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G4_FOM_EQ_CONFIG5, 0x8a),
};
static const struct qmp_phy_init_tbl sm8250_qmp_pcie_serdes_tbl[] = {
diff --git a/drivers/phy/samsung/phy-exynos5-usbdrd.c b/drivers/phy/samsung/phy-exynos5-usbdrd.c
index df52b78..9cbf901 100644
--- a/drivers/phy/samsung/phy-exynos5-usbdrd.c
+++ b/drivers/phy/samsung/phy-exynos5-usbdrd.c
@@ -1745,7 +1745,7 @@ static int exynos5_usbdrd_phy_probe(struct platform_device *pdev)
sizeof(*phy_drd->regulators),
GFP_KERNEL);
if (!phy_drd->regulators)
- return ENOMEM;
+ return -ENOMEM;
regulator_bulk_set_supply_names(phy_drd->regulators,
drv_data->regulator_names,
drv_data->n_regulators);
diff --git a/drivers/phy/xilinx/phy-zynqmp.c b/drivers/phy/xilinx/phy-zynqmp.c
index cb15041..e657900 100644
--- a/drivers/phy/xilinx/phy-zynqmp.c
+++ b/drivers/phy/xilinx/phy-zynqmp.c
@@ -160,6 +160,24 @@ static const char *const xpsgtr_icm_str[] = {
/* Timeout values */
#define TIMEOUT_US 1000
+/* Lane 0/1/2/3 offset */
+#define DIG_8(n) ((0x4000 * (n)) + 0x1074)
+#define ILL13(n) ((0x4000 * (n)) + 0x1994)
+#define DIG_10(n) ((0x4000 * (n)) + 0x107c)
+#define RST_DLY(n) ((0x4000 * (n)) + 0x19a4)
+#define BYP_15(n) ((0x4000 * (n)) + 0x1038)
+#define BYP_12(n) ((0x4000 * (n)) + 0x102c)
+#define MISC3(n) ((0x4000 * (n)) + 0x19ac)
+#define EQ11(n) ((0x4000 * (n)) + 0x1978)
+
+static u32 save_reg_address[] = {
+ /* Lane 0/1/2/3 Register */
+ DIG_8(0), ILL13(0), DIG_10(0), RST_DLY(0), BYP_15(0), BYP_12(0), MISC3(0), EQ11(0),
+ DIG_8(1), ILL13(1), DIG_10(1), RST_DLY(1), BYP_15(1), BYP_12(1), MISC3(1), EQ11(1),
+ DIG_8(2), ILL13(2), DIG_10(2), RST_DLY(2), BYP_15(2), BYP_12(2), MISC3(2), EQ11(2),
+ DIG_8(3), ILL13(3), DIG_10(3), RST_DLY(3), BYP_15(3), BYP_12(3), MISC3(3), EQ11(3),
+};
+
struct xpsgtr_dev;
/**
@@ -209,6 +227,7 @@ struct xpsgtr_phy {
* @tx_term_fix: fix for GT issue
* @saved_icm_cfg0: stored value of ICM CFG0 register
* @saved_icm_cfg1: stored value of ICM CFG1 register
+ * @saved_regs: registers to be saved/restored during suspend/resume
*/
struct xpsgtr_dev {
struct device *dev;
@@ -221,6 +240,7 @@ struct xpsgtr_dev {
bool tx_term_fix;
unsigned int saved_icm_cfg0;
unsigned int saved_icm_cfg1;
+ u32 *saved_regs;
};
/*
@@ -294,6 +314,32 @@ static inline void xpsgtr_clr_set_phy(struct xpsgtr_phy *gtr_phy,
writel((readl(addr) & ~clr) | set, addr);
}
+/**
+ * xpsgtr_save_lane_regs - Saves registers on suspend
+ * @gtr_dev: pointer to phy controller context structure
+ */
+static void xpsgtr_save_lane_regs(struct xpsgtr_dev *gtr_dev)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(save_reg_address); i++)
+ gtr_dev->saved_regs[i] = xpsgtr_read(gtr_dev,
+ save_reg_address[i]);
+}
+
+/**
+ * xpsgtr_restore_lane_regs - Restores registers on resume
+ * @gtr_dev: pointer to phy controller context structure
+ */
+static void xpsgtr_restore_lane_regs(struct xpsgtr_dev *gtr_dev)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(save_reg_address); i++)
+ xpsgtr_write(gtr_dev, save_reg_address[i],
+ gtr_dev->saved_regs[i]);
+}
+
/*
* Hardware Configuration
*/
@@ -837,6 +883,8 @@ static int xpsgtr_runtime_suspend(struct device *dev)
gtr_dev->saved_icm_cfg0 = xpsgtr_read(gtr_dev, ICM_CFG0);
gtr_dev->saved_icm_cfg1 = xpsgtr_read(gtr_dev, ICM_CFG1);
+ xpsgtr_save_lane_regs(gtr_dev);
+
return 0;
}
@@ -847,6 +895,8 @@ static int xpsgtr_runtime_resume(struct device *dev)
unsigned int i;
bool skip_phy_init;
+ xpsgtr_restore_lane_regs(gtr_dev);
+
icm_cfg0 = xpsgtr_read(gtr_dev, ICM_CFG0);
icm_cfg1 = xpsgtr_read(gtr_dev, ICM_CFG1);
@@ -994,6 +1044,12 @@ static int xpsgtr_probe(struct platform_device *pdev)
return ret;
}
+ gtr_dev->saved_regs = devm_kmalloc(gtr_dev->dev,
+ sizeof(save_reg_address),
+ GFP_KERNEL);
+ if (!gtr_dev->saved_regs)
+ return -ENOMEM;
+
return 0;
}
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c
index b7921b5..54301fb 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c
@@ -709,32 +709,35 @@ static int mtk_pinconf_bias_set_rsel(struct mtk_pinctrl *hw,
{
int err, rsel_val;
- if (!pullup && arg == MTK_DISABLE)
- return 0;
-
if (hw->rsel_si_unit) {
/* find pin rsel_index from pin_rsel array*/
err = mtk_hw_pin_rsel_lookup(hw, desc, pullup, arg, &rsel_val);
if (err)
- goto out;
+ return err;
} else {
- if (arg < MTK_PULL_SET_RSEL_000 ||
- arg > MTK_PULL_SET_RSEL_111) {
- err = -EINVAL;
- goto out;
- }
+ if (arg < MTK_PULL_SET_RSEL_000 || arg > MTK_PULL_SET_RSEL_111)
+ return -EINVAL;
rsel_val = arg - MTK_PULL_SET_RSEL_000;
}
- err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_RSEL, rsel_val);
- if (err)
- goto out;
+ return mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_RSEL, rsel_val);
+}
- err = mtk_pinconf_bias_set_pu_pd(hw, desc, pullup, MTK_ENABLE);
+static int mtk_pinconf_bias_set_pu_pd_rsel(struct mtk_pinctrl *hw,
+ const struct mtk_pin_desc *desc,
+ u32 pullup, u32 arg)
+{
+ u32 enable = arg == MTK_DISABLE ? MTK_DISABLE : MTK_ENABLE;
+ int err;
-out:
- return err;
+ if (arg != MTK_DISABLE) {
+ err = mtk_pinconf_bias_set_rsel(hw, desc, pullup, arg);
+ if (err)
+ return err;
+ }
+
+ return mtk_pinconf_bias_set_pu_pd(hw, desc, pullup, enable);
}
int mtk_pinconf_bias_set_combo(struct mtk_pinctrl *hw,
@@ -750,22 +753,22 @@ int mtk_pinconf_bias_set_combo(struct mtk_pinctrl *hw,
try_all_type = MTK_PULL_TYPE_MASK;
if (try_all_type & MTK_PULL_RSEL_TYPE) {
- err = mtk_pinconf_bias_set_rsel(hw, desc, pullup, arg);
+ err = mtk_pinconf_bias_set_pu_pd_rsel(hw, desc, pullup, arg);
if (!err)
- return err;
+ return 0;
}
if (try_all_type & MTK_PULL_PU_PD_TYPE) {
err = mtk_pinconf_bias_set_pu_pd(hw, desc, pullup, arg);
if (!err)
- return err;
+ return 0;
}
if (try_all_type & MTK_PULL_PULLSEL_TYPE) {
err = mtk_pinconf_bias_set_pullsel_pullen(hw, desc,
pullup, arg);
if (!err)
- return err;
+ return 0;
}
if (try_all_type & MTK_PULL_PUPD_R1R0_TYPE)
@@ -803,9 +806,9 @@ static int mtk_rsel_get_si_unit(struct mtk_pinctrl *hw,
return 0;
}
-static int mtk_pinconf_bias_get_rsel(struct mtk_pinctrl *hw,
- const struct mtk_pin_desc *desc,
- u32 *pullup, u32 *enable)
+static int mtk_pinconf_bias_get_pu_pd_rsel(struct mtk_pinctrl *hw,
+ const struct mtk_pin_desc *desc,
+ u32 *pullup, u32 *enable)
{
int pu, pd, rsel, err;
@@ -939,22 +942,22 @@ int mtk_pinconf_bias_get_combo(struct mtk_pinctrl *hw,
try_all_type = MTK_PULL_TYPE_MASK;
if (try_all_type & MTK_PULL_RSEL_TYPE) {
- err = mtk_pinconf_bias_get_rsel(hw, desc, pullup, enable);
+ err = mtk_pinconf_bias_get_pu_pd_rsel(hw, desc, pullup, enable);
if (!err)
- return err;
+ return 0;
}
if (try_all_type & MTK_PULL_PU_PD_TYPE) {
err = mtk_pinconf_bias_get_pu_pd(hw, desc, pullup, enable);
if (!err)
- return err;
+ return 0;
}
if (try_all_type & MTK_PULL_PULLSEL_TYPE) {
err = mtk_pinconf_bias_get_pullsel_pullen(hw, desc,
pullup, enable);
if (!err)
- return err;
+ return 0;
}
if (try_all_type & MTK_PULL_PUPD_R1R0_TYPE)
diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c
index b3c3f5f..93ab277 100644
--- a/drivers/pinctrl/pinctrl-at91.c
+++ b/drivers/pinctrl/pinctrl-at91.c
@@ -1403,8 +1403,11 @@ static int at91_pinctrl_probe(struct platform_device *pdev)
/* We will handle a range of GPIO pins */
for (i = 0; i < gpio_banks; i++)
- if (gpio_chips[i])
+ if (gpio_chips[i]) {
pinctrl_add_gpio_range(info->pctl, &gpio_chips[i]->range);
+ gpiochip_add_pin_range(&gpio_chips[i]->chip, dev_name(info->pctl->dev), 0,
+ gpio_chips[i]->range.pin_base, gpio_chips[i]->range.npins);
+ }
dev_info(dev, "initialized AT91 pinctrl driver\n");
diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index 0eacaf1..6878bc8 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -3795,7 +3795,7 @@ static struct rockchip_pin_bank rk3328_pin_banks[] = {
PIN_BANK_IOMUX_FLAGS(0, 32, "gpio0", 0, 0, 0, 0),
PIN_BANK_IOMUX_FLAGS(1, 32, "gpio1", 0, 0, 0, 0),
PIN_BANK_IOMUX_FLAGS(2, 32, "gpio2", 0,
- 0,
+ IOMUX_WIDTH_2BIT,
IOMUX_WIDTH_3BIT,
0),
PIN_BANK_IOMUX_FLAGS(3, 32, "gpio3",
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index 4c6bfab..4da3c3f 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -345,6 +345,8 @@ static int pcs_get_function(struct pinctrl_dev *pctldev, unsigned pin,
return -ENOTSUPP;
fselector = setting->func;
function = pinmux_generic_get_function(pctldev, fselector);
+ if (!function)
+ return -EINVAL;
*func = function->data;
if (!(*func)) {
dev_err(pcs->dev, "%s could not find function%i\n",
diff --git a/drivers/pinctrl/qcom/pinctrl-x1e80100.c b/drivers/pinctrl/qcom/pinctrl-x1e80100.c
index e30e938..65ed933 100644
--- a/drivers/pinctrl/qcom/pinctrl-x1e80100.c
+++ b/drivers/pinctrl/qcom/pinctrl-x1e80100.c
@@ -1805,26 +1805,29 @@ static const struct msm_pingroup x1e80100_groups[] = {
[235] = PINGROUP(235, aon_cci, qdss_gpio, _, _, _, _, _, _, _),
[236] = PINGROUP(236, aon_cci, qdss_gpio, _, _, _, _, _, _, _),
[237] = PINGROUP(237, _, _, _, _, _, _, _, _, _),
- [238] = UFS_RESET(ufs_reset, 0x1f9000),
- [239] = SDC_QDSD_PINGROUP(sdc2_clk, 0x1f2000, 14, 6),
- [240] = SDC_QDSD_PINGROUP(sdc2_cmd, 0x1f2000, 11, 3),
- [241] = SDC_QDSD_PINGROUP(sdc2_data, 0x1f2000, 9, 0),
+ [238] = UFS_RESET(ufs_reset, 0xf9000),
+ [239] = SDC_QDSD_PINGROUP(sdc2_clk, 0xf2000, 14, 6),
+ [240] = SDC_QDSD_PINGROUP(sdc2_cmd, 0xf2000, 11, 3),
+ [241] = SDC_QDSD_PINGROUP(sdc2_data, 0xf2000, 9, 0),
};
static const struct msm_gpio_wakeirq_map x1e80100_pdc_map[] = {
{ 0, 72 }, { 2, 70 }, { 3, 71 }, { 6, 123 }, { 7, 67 }, { 11, 85 },
- { 15, 68 }, { 18, 122 }, { 19, 69 }, { 21, 158 }, { 23, 143 }, { 26, 129 },
- { 27, 144 }, { 28, 77 }, { 29, 78 }, { 30, 92 }, { 32, 145 }, { 33, 115 },
- { 34, 130 }, { 35, 146 }, { 36, 147 }, { 39, 80 }, { 43, 148 }, { 47, 149 },
- { 51, 79 }, { 53, 89 }, { 59, 87 }, { 64, 90 }, { 65, 106 }, { 66, 142 },
- { 67, 88 }, { 71, 91 }, { 75, 152 }, { 79, 153 }, { 80, 125 }, { 81, 128 },
- { 84, 137 }, { 85, 155 }, { 87, 156 }, { 91, 157 }, { 92, 138 }, { 94, 140 },
- { 95, 141 }, { 113, 84 }, { 121, 73 }, { 123, 74 }, { 129, 76 }, { 131, 82 },
- { 134, 83 }, { 141, 93 }, { 144, 94 }, { 147, 96 }, { 148, 97 }, { 150, 102 },
- { 151, 103 }, { 153, 104 }, { 156, 105 }, { 157, 107 }, { 163, 98 }, { 166, 112 },
- { 172, 99 }, { 181, 101 }, { 184, 116 }, { 193, 40 }, { 193, 117 }, { 196, 108 },
- { 203, 133 }, { 212, 120 }, { 213, 150 }, { 214, 121 }, { 215, 118 }, { 217, 109 },
- { 220, 110 }, { 221, 111 }, { 222, 124 }, { 224, 131 }, { 225, 132 },
+ { 13, 86 }, { 15, 68 }, { 18, 122 }, { 19, 69 }, { 21, 158 }, { 23, 143 },
+ { 24, 126 }, { 26, 129 }, { 27, 144 }, { 28, 77 }, { 29, 78 }, { 30, 92 },
+ { 31, 159 }, { 32, 145 }, { 33, 115 }, { 34, 130 }, { 35, 146 }, { 36, 147 },
+ { 38, 113 }, { 39, 80 }, { 43, 148 }, { 47, 149 }, { 51, 79 }, { 53, 89 },
+ { 55, 81 }, { 59, 87 }, { 64, 90 }, { 65, 106 }, { 66, 142 }, { 67, 88 },
+ { 68, 151 }, { 71, 91 }, { 75, 152 }, { 79, 153 }, { 80, 125 }, { 81, 128 },
+ { 83, 154 }, { 84, 137 }, { 85, 155 }, { 87, 156 }, { 91, 157 }, { 92, 138 },
+ { 93, 139 }, { 94, 140 }, { 95, 141 }, { 113, 84 }, { 121, 73 }, { 123, 74 },
+ { 125, 75 }, { 129, 76 }, { 131, 82 }, { 134, 83 }, { 141, 93 }, { 144, 94 },
+ { 145, 95 }, { 147, 96 }, { 148, 97 }, { 150, 102 }, { 151, 103 }, { 153, 104 },
+ { 154, 100 }, { 156, 105 }, { 157, 107 }, { 163, 98 }, { 166, 112 }, { 172, 99 },
+ { 175, 114 }, { 181, 101 }, { 184, 116 }, { 193, 117 }, { 196, 108 }, { 203, 133 },
+ { 208, 134 }, { 212, 120 }, { 213, 150 }, { 214, 121 }, { 215, 118 }, { 217, 109 },
+ { 219, 119 }, { 220, 110 }, { 221, 111 }, { 222, 124 }, { 224, 131 }, { 225, 132 },
+ { 228, 135 }, { 230, 136 }, { 232, 162 },
};
static const struct msm_pinctrl_soc_data x1e80100_pinctrl = {
diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
index 4ce080c..1d0d6c2 100644
--- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
+++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
@@ -793,12 +793,12 @@ static int jh7110_irq_set_type(struct irq_data *d, unsigned int trigger)
case IRQ_TYPE_LEVEL_HIGH:
irq_type = 0; /* 0: level triggered */
edge_both = 0; /* 0: ignored */
- polarity = mask; /* 1: high level */
+ polarity = 0; /* 0: high level */
break;
case IRQ_TYPE_LEVEL_LOW:
irq_type = 0; /* 0: level triggered */
edge_both = 0; /* 0: ignored */
- polarity = 0; /* 0: low level */
+ polarity = mask; /* 1: low level */
break;
default:
return -EINVAL;
diff --git a/drivers/platform/surface/aggregator/controller.c b/drivers/platform/surface/aggregator/controller.c
index 7fc602e..7e89f54 100644
--- a/drivers/platform/surface/aggregator/controller.c
+++ b/drivers/platform/surface/aggregator/controller.c
@@ -1354,7 +1354,8 @@ void ssam_controller_destroy(struct ssam_controller *ctrl)
if (ctrl->state == SSAM_CONTROLLER_UNINITIALIZED)
return;
- WARN_ON(ctrl->state != SSAM_CONTROLLER_STOPPED);
+ WARN_ON(ctrl->state != SSAM_CONTROLLER_STOPPED &&
+ ctrl->state != SSAM_CONTROLLER_INITIALIZED);
/*
* Note: New events could still have been received after the previous
diff --git a/drivers/platform/surface/surface_aggregator_registry.c b/drivers/platform/surface/surface_aggregator_registry.c
index 1c4d74d..a23dff3 100644
--- a/drivers/platform/surface/surface_aggregator_registry.c
+++ b/drivers/platform/surface/surface_aggregator_registry.c
@@ -265,7 +265,9 @@ static const struct software_node *ssam_node_group_sl5[] = {
&ssam_node_root,
&ssam_node_bat_ac,
&ssam_node_bat_main,
- &ssam_node_tmp_perf_profile,
+ &ssam_node_tmp_perf_profile_with_fan,
+ &ssam_node_tmp_sensors,
+ &ssam_node_fan_speed,
&ssam_node_hid_main_keyboard,
&ssam_node_hid_main_touchpad,
&ssam_node_hid_main_iid5,
@@ -273,8 +275,24 @@ static const struct software_node *ssam_node_group_sl5[] = {
NULL,
};
-/* Devices for Surface Laptop Studio. */
-static const struct software_node *ssam_node_group_sls[] = {
+/* Devices for Surface Laptop 6. */
+static const struct software_node *ssam_node_group_sl6[] = {
+ &ssam_node_root,
+ &ssam_node_bat_ac,
+ &ssam_node_bat_main,
+ &ssam_node_tmp_perf_profile_with_fan,
+ &ssam_node_tmp_sensors,
+ &ssam_node_fan_speed,
+ &ssam_node_hid_main_keyboard,
+ &ssam_node_hid_main_touchpad,
+ &ssam_node_hid_main_iid5,
+ &ssam_node_hid_sam_sensors,
+ &ssam_node_hid_sam_ucm_ucsi,
+ NULL,
+};
+
+/* Devices for Surface Laptop Studio 1. */
+static const struct software_node *ssam_node_group_sls1[] = {
&ssam_node_root,
&ssam_node_bat_ac,
&ssam_node_bat_main,
@@ -289,6 +307,22 @@ static const struct software_node *ssam_node_group_sls[] = {
NULL,
};
+/* Devices for Surface Laptop Studio 2. */
+static const struct software_node *ssam_node_group_sls2[] = {
+ &ssam_node_root,
+ &ssam_node_bat_ac,
+ &ssam_node_bat_main,
+ &ssam_node_tmp_perf_profile_with_fan,
+ &ssam_node_tmp_sensors,
+ &ssam_node_fan_speed,
+ &ssam_node_pos_tablet_switch,
+ &ssam_node_hid_sam_keyboard,
+ &ssam_node_hid_sam_penstash,
+ &ssam_node_hid_sam_sensors,
+ &ssam_node_hid_sam_ucm_ucsi,
+ NULL,
+};
+
/* Devices for Surface Laptop Go. */
static const struct software_node *ssam_node_group_slg1[] = {
&ssam_node_root,
@@ -324,7 +358,7 @@ static const struct software_node *ssam_node_group_sp8[] = {
NULL,
};
-/* Devices for Surface Pro 9 */
+/* Devices for Surface Pro 9 and 10 */
static const struct software_node *ssam_node_group_sp9[] = {
&ssam_node_root,
&ssam_node_hub_kip,
@@ -365,6 +399,9 @@ static const struct acpi_device_id ssam_platform_hub_match[] = {
/* Surface Pro 9 */
{ "MSHW0343", (unsigned long)ssam_node_group_sp9 },
+ /* Surface Pro 10 */
+ { "MSHW0510", (unsigned long)ssam_node_group_sp9 },
+
/* Surface Book 2 */
{ "MSHW0107", (unsigned long)ssam_node_group_gen5 },
@@ -389,14 +426,23 @@ static const struct acpi_device_id ssam_platform_hub_match[] = {
/* Surface Laptop 5 */
{ "MSHW0350", (unsigned long)ssam_node_group_sl5 },
+ /* Surface Laptop 6 */
+ { "MSHW0530", (unsigned long)ssam_node_group_sl6 },
+
/* Surface Laptop Go 1 */
{ "MSHW0118", (unsigned long)ssam_node_group_slg1 },
/* Surface Laptop Go 2 */
{ "MSHW0290", (unsigned long)ssam_node_group_slg1 },
- /* Surface Laptop Studio */
- { "MSHW0123", (unsigned long)ssam_node_group_sls },
+ /* Surface Laptop Go 3 */
+ { "MSHW0440", (unsigned long)ssam_node_group_slg1 },
+
+ /* Surface Laptop Studio 1 */
+ { "MSHW0123", (unsigned long)ssam_node_group_sls1 },
+
+ /* Surface Laptop Studio 2 */
+ { "MSHW0360", (unsigned long)ssam_node_group_sls2 },
{ },
};
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 665fa95..ddfccc2 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -477,6 +477,7 @@
tristate "Lenovo Yoga Tablet Mode Control"
depends on ACPI_WMI
depends on INPUT
+ depends on IDEAPAD_LAPTOP
select INPUT_SPARSEKMAP
help
This driver maps the Tablet Mode Control switch to SW_TABLET_MODE input
diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c
index c3e51f0..bbb8edb 100644
--- a/drivers/platform/x86/amd/pmc/pmc.c
+++ b/drivers/platform/x86/amd/pmc/pmc.c
@@ -359,6 +359,7 @@ static void amd_pmc_get_ip_info(struct amd_pmc_dev *dev)
dev->smu_msg = 0x538;
break;
case PCI_DEVICE_ID_AMD_1AH_M20H_ROOT:
+ case PCI_DEVICE_ID_AMD_1AH_M60H_ROOT:
dev->num_ips = 22;
dev->s2d_msg_id = 0xDE;
dev->smu_msg = 0x938;
@@ -597,6 +598,7 @@ static int amd_pmc_idlemask_read(struct amd_pmc_dev *pdev, struct device *dev,
val = amd_pmc_reg_read(pdev, AMD_PMC_SCRATCH_REG_YC);
break;
case PCI_DEVICE_ID_AMD_1AH_M20H_ROOT:
+ case PCI_DEVICE_ID_AMD_1AH_M60H_ROOT:
val = amd_pmc_reg_read(pdev, AMD_PMC_SCRATCH_REG_1AH);
break;
default:
@@ -630,6 +632,7 @@ static bool amd_pmc_is_stb_supported(struct amd_pmc_dev *dev)
case AMD_CPU_ID_CB:
case AMD_CPU_ID_PS:
case PCI_DEVICE_ID_AMD_1AH_M20H_ROOT:
+ case PCI_DEVICE_ID_AMD_1AH_M60H_ROOT:
return true;
default:
return false;
diff --git a/drivers/platform/x86/amd/pmf/spc.c b/drivers/platform/x86/amd/pmf/spc.c
index a3dec14..3c153fb 100644
--- a/drivers/platform/x86/amd/pmf/spc.c
+++ b/drivers/platform/x86/amd/pmf/spc.c
@@ -150,36 +150,26 @@ static int amd_pmf_get_slider_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_
return 0;
}
-static int amd_pmf_get_sensor_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in)
+static void amd_pmf_get_sensor_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in)
{
struct amd_sfh_info sfh_info;
- int ret;
+
+ /* Get the latest information from SFH */
+ in->ev_info.user_present = false;
/* Get ALS data */
- ret = amd_get_sfh_info(&sfh_info, MT_ALS);
- if (!ret)
+ if (!amd_get_sfh_info(&sfh_info, MT_ALS))
in->ev_info.ambient_light = sfh_info.ambient_light;
else
- return ret;
+ dev_dbg(dev->dev, "ALS is not enabled/detected\n");
/* get HPD data */
- ret = amd_get_sfh_info(&sfh_info, MT_HPD);
- if (ret)
- return ret;
-
- switch (sfh_info.user_present) {
- case SFH_NOT_DETECTED:
- in->ev_info.user_present = 0xff; /* assume no sensors connected */
- break;
- case SFH_USER_PRESENT:
- in->ev_info.user_present = 1;
- break;
- case SFH_USER_AWAY:
- in->ev_info.user_present = 0;
- break;
+ if (!amd_get_sfh_info(&sfh_info, MT_HPD)) {
+ if (sfh_info.user_present == SFH_USER_PRESENT)
+ in->ev_info.user_present = true;
+ } else {
+ dev_dbg(dev->dev, "HPD is not enabled/detected\n");
}
-
- return 0;
}
void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in)
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index fceffe2..ed3633c 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -145,6 +145,10 @@ static struct quirk_entry quirk_asus_ignore_fan = {
.wmi_ignore_fan = true,
};
+static struct quirk_entry quirk_asus_zenbook_duo_kbd = {
+ .ignore_key_wlan = true,
+};
+
static int dmi_matched(const struct dmi_system_id *dmi)
{
pr_info("Identified laptop model '%s'\n", dmi->ident);
@@ -516,6 +520,15 @@ static const struct dmi_system_id asus_quirks[] = {
},
.driver_data = &quirk_asus_ignore_fan,
},
+ {
+ .callback = dmi_matched,
+ .ident = "ASUS Zenbook Duo UX8406MA",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "UX8406MA"),
+ },
+ .driver_data = &quirk_asus_zenbook_duo_kbd,
+ },
{},
};
@@ -630,7 +643,12 @@ static void asus_nb_wmi_key_filter(struct asus_wmi_driver *asus_wmi, int *code,
case 0x32: /* Volume Mute */
if (atkbd_reports_vol_keys)
*code = ASUS_WMI_KEY_IGNORE;
-
+ break;
+ case 0x5D: /* Wireless console Toggle */
+ case 0x5E: /* Wireless console Enable */
+ case 0x5F: /* Wireless console Disable */
+ if (quirks->ignore_key_wlan)
+ *code = ASUS_WMI_KEY_IGNORE;
break;
}
}
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index cc73593..37636e5 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -146,6 +146,20 @@ static const char * const ashs_ids[] = { "ATK4001", "ATK4002", NULL };
static int throttle_thermal_policy_write(struct asus_wmi *);
+static const struct dmi_system_id asus_ally_mcu_quirk[] = {
+ {
+ .matches = {
+ DMI_MATCH(DMI_BOARD_NAME, "RC71L"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_BOARD_NAME, "RC72L"),
+ },
+ },
+ { },
+};
+
static bool ashs_present(void)
{
int i = 0;
@@ -4685,7 +4699,7 @@ static int asus_wmi_add(struct platform_device *pdev)
asus->dgpu_disable_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_DGPU);
asus->kbd_rgb_state_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_TUF_RGB_STATE);
asus->ally_mcu_usb_switch = acpi_has_method(NULL, ASUS_USB0_PWR_EC0_CSEE)
- && dmi_match(DMI_BOARD_NAME, "RC71L");
+ && dmi_check_system(asus_ally_mcu_quirk);
if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_MINI_LED_MODE))
asus->mini_led_dev_id = ASUS_WMI_DEVID_MINI_LED_MODE;
diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h
index cc30f18..d02f15f 100644
--- a/drivers/platform/x86/asus-wmi.h
+++ b/drivers/platform/x86/asus-wmi.h
@@ -40,6 +40,7 @@ struct quirk_entry {
bool wmi_force_als_set;
bool wmi_ignore_fan;
bool filter_i8042_e1_extended_codes;
+ bool ignore_key_wlan;
enum asus_wmi_tablet_switch_mode tablet_switch_mode;
int wapf;
/*
diff --git a/drivers/platform/x86/dell/Kconfig b/drivers/platform/x86/dell/Kconfig
index 85a78ef..309236c 100644
--- a/drivers/platform/x86/dell/Kconfig
+++ b/drivers/platform/x86/dell/Kconfig
@@ -161,6 +161,7 @@
config DELL_UART_BACKLIGHT
tristate "Dell AIO UART Backlight driver"
depends on ACPI
+ depends on ACPI_VIDEO
depends on BACKLIGHT_CLASS_DEVICE
depends on SERIAL_DEV_BUS
help
diff --git a/drivers/platform/x86/dell/dell-uart-backlight.c b/drivers/platform/x86/dell/dell-uart-backlight.c
index 87d2a20..3995f90 100644
--- a/drivers/platform/x86/dell/dell-uart-backlight.c
+++ b/drivers/platform/x86/dell/dell-uart-backlight.c
@@ -20,6 +20,7 @@
#include <linux/string.h>
#include <linux/types.h>
#include <linux/wait.h>
+#include <acpi/video.h>
#include "../serdev_helpers.h"
/* The backlight controller must respond within 1 second */
@@ -332,10 +333,17 @@ struct serdev_device_driver dell_uart_bl_serdev_driver = {
static int dell_uart_bl_pdev_probe(struct platform_device *pdev)
{
+ enum acpi_backlight_type bl_type;
struct serdev_device *serdev;
struct device *ctrl_dev;
int ret;
+ bl_type = acpi_video_get_backlight_type();
+ if (bl_type != acpi_backlight_dell_uart) {
+ dev_dbg(&pdev->dev, "Not loading (ACPI backlight type = %d)\n", bl_type);
+ return -ENODEV;
+ }
+
ctrl_dev = get_serdev_controller("DELL0501", NULL, 0, "serial0");
if (IS_ERR(ctrl_dev))
return PTR_ERR(ctrl_dev);
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index 1ace711..98ec30f 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -126,6 +126,7 @@ struct ideapad_rfk_priv {
struct ideapad_private {
struct acpi_device *adev;
+ struct mutex vpc_mutex; /* protects the VPC calls */
struct rfkill *rfk[IDEAPAD_RFKILL_DEV_NUM];
struct ideapad_rfk_priv rfk_priv[IDEAPAD_RFKILL_DEV_NUM];
struct platform_device *platform_device;
@@ -146,6 +147,7 @@ struct ideapad_private {
bool touchpad_ctrl_via_ec : 1;
bool ctrl_ps2_aux_port : 1;
bool usb_charging : 1;
+ bool ymc_ec_trigger : 1;
} features;
struct {
bool initialized;
@@ -194,6 +196,12 @@ MODULE_PARM_DESC(touchpad_ctrl_via_ec,
"Enable registering a 'touchpad' sysfs-attribute which can be used to manually "
"tell the EC to enable/disable the touchpad. This may not work on all models.");
+static bool ymc_ec_trigger __read_mostly;
+module_param(ymc_ec_trigger, bool, 0444);
+MODULE_PARM_DESC(ymc_ec_trigger,
+ "Enable EC triggering work-around to force emitting tablet mode events. "
+ "If you need this please report this to: platform-driver-x86@vger.kernel.org");
+
/*
* shared data
*/
@@ -294,6 +302,8 @@ static int debugfs_status_show(struct seq_file *s, void *data)
struct ideapad_private *priv = s->private;
unsigned long value;
+ guard(mutex)(&priv->vpc_mutex);
+
if (!read_ec_data(priv->adev->handle, VPCCMD_R_BL_MAX, &value))
seq_printf(s, "Backlight max: %lu\n", value);
if (!read_ec_data(priv->adev->handle, VPCCMD_R_BL, &value))
@@ -412,7 +422,8 @@ static ssize_t camera_power_show(struct device *dev,
unsigned long result;
int err;
- err = read_ec_data(priv->adev->handle, VPCCMD_R_CAMERA, &result);
+ scoped_guard(mutex, &priv->vpc_mutex)
+ err = read_ec_data(priv->adev->handle, VPCCMD_R_CAMERA, &result);
if (err)
return err;
@@ -431,7 +442,8 @@ static ssize_t camera_power_store(struct device *dev,
if (err)
return err;
- err = write_ec_cmd(priv->adev->handle, VPCCMD_W_CAMERA, state);
+ scoped_guard(mutex, &priv->vpc_mutex)
+ err = write_ec_cmd(priv->adev->handle, VPCCMD_W_CAMERA, state);
if (err)
return err;
@@ -484,7 +496,8 @@ static ssize_t fan_mode_show(struct device *dev,
unsigned long result;
int err;
- err = read_ec_data(priv->adev->handle, VPCCMD_R_FAN, &result);
+ scoped_guard(mutex, &priv->vpc_mutex)
+ err = read_ec_data(priv->adev->handle, VPCCMD_R_FAN, &result);
if (err)
return err;
@@ -506,7 +519,8 @@ static ssize_t fan_mode_store(struct device *dev,
if (state > 4 || state == 3)
return -EINVAL;
- err = write_ec_cmd(priv->adev->handle, VPCCMD_W_FAN, state);
+ scoped_guard(mutex, &priv->vpc_mutex)
+ err = write_ec_cmd(priv->adev->handle, VPCCMD_W_FAN, state);
if (err)
return err;
@@ -591,7 +605,8 @@ static ssize_t touchpad_show(struct device *dev,
unsigned long result;
int err;
- err = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &result);
+ scoped_guard(mutex, &priv->vpc_mutex)
+ err = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &result);
if (err)
return err;
@@ -612,7 +627,8 @@ static ssize_t touchpad_store(struct device *dev,
if (err)
return err;
- err = write_ec_cmd(priv->adev->handle, VPCCMD_W_TOUCHPAD, state);
+ scoped_guard(mutex, &priv->vpc_mutex)
+ err = write_ec_cmd(priv->adev->handle, VPCCMD_W_TOUCHPAD, state);
if (err)
return err;
@@ -1005,6 +1021,8 @@ static int ideapad_rfk_set(void *data, bool blocked)
struct ideapad_rfk_priv *priv = data;
int opcode = ideapad_rfk_data[priv->dev].opcode;
+ guard(mutex)(&priv->priv->vpc_mutex);
+
return write_ec_cmd(priv->priv->adev->handle, opcode, !blocked);
}
@@ -1018,6 +1036,8 @@ static void ideapad_sync_rfk_state(struct ideapad_private *priv)
int i;
if (priv->features.hw_rfkill_switch) {
+ guard(mutex)(&priv->vpc_mutex);
+
if (read_ec_data(priv->adev->handle, VPCCMD_R_RF, &hw_blocked))
return;
hw_blocked = !hw_blocked;
@@ -1191,8 +1211,9 @@ static void ideapad_input_novokey(struct ideapad_private *priv)
{
unsigned long long_pressed;
- if (read_ec_data(priv->adev->handle, VPCCMD_R_NOVO, &long_pressed))
- return;
+ scoped_guard(mutex, &priv->vpc_mutex)
+ if (read_ec_data(priv->adev->handle, VPCCMD_R_NOVO, &long_pressed))
+ return;
if (long_pressed)
ideapad_input_report(priv, 17);
@@ -1204,8 +1225,9 @@ static void ideapad_check_special_buttons(struct ideapad_private *priv)
{
unsigned long bit, value;
- if (read_ec_data(priv->adev->handle, VPCCMD_R_SPECIAL_BUTTONS, &value))
- return;
+ scoped_guard(mutex, &priv->vpc_mutex)
+ if (read_ec_data(priv->adev->handle, VPCCMD_R_SPECIAL_BUTTONS, &value))
+ return;
for_each_set_bit (bit, &value, 16) {
switch (bit) {
@@ -1238,6 +1260,8 @@ static int ideapad_backlight_get_brightness(struct backlight_device *blightdev)
unsigned long now;
int err;
+ guard(mutex)(&priv->vpc_mutex);
+
err = read_ec_data(priv->adev->handle, VPCCMD_R_BL, &now);
if (err)
return err;
@@ -1250,6 +1274,8 @@ static int ideapad_backlight_update_status(struct backlight_device *blightdev)
struct ideapad_private *priv = bl_get_data(blightdev);
int err;
+ guard(mutex)(&priv->vpc_mutex);
+
err = write_ec_cmd(priv->adev->handle, VPCCMD_W_BL,
blightdev->props.brightness);
if (err)
@@ -1327,6 +1353,8 @@ static void ideapad_backlight_notify_power(struct ideapad_private *priv)
if (!blightdev)
return;
+ guard(mutex)(&priv->vpc_mutex);
+
if (read_ec_data(priv->adev->handle, VPCCMD_R_BL_POWER, &power))
return;
@@ -1339,7 +1367,8 @@ static void ideapad_backlight_notify_brightness(struct ideapad_private *priv)
/* if we control brightness via acpi video driver */
if (!priv->blightdev)
- read_ec_data(priv->adev->handle, VPCCMD_R_BL, &now);
+ scoped_guard(mutex, &priv->vpc_mutex)
+ read_ec_data(priv->adev->handle, VPCCMD_R_BL, &now);
else
backlight_force_update(priv->blightdev, BACKLIGHT_UPDATE_HOTKEY);
}
@@ -1564,7 +1593,8 @@ static void ideapad_sync_touchpad_state(struct ideapad_private *priv, bool send_
int ret;
/* Without reading from EC touchpad LED doesn't switch state */
- ret = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &value);
+ scoped_guard(mutex, &priv->vpc_mutex)
+ ret = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &value);
if (ret)
return;
@@ -1592,16 +1622,92 @@ static void ideapad_sync_touchpad_state(struct ideapad_private *priv, bool send_
priv->r_touchpad_val = value;
}
+static const struct dmi_system_id ymc_ec_trigger_quirk_dmi_table[] = {
+ {
+ /* Lenovo Yoga 7 14ARB7 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "82QF"),
+ },
+ },
+ {
+ /* Lenovo Yoga 7 14ACN6 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "82N7"),
+ },
+ },
+ { }
+};
+
+static void ideapad_laptop_trigger_ec(void)
+{
+ struct ideapad_private *priv;
+ int ret;
+
+ guard(mutex)(&ideapad_shared_mutex);
+
+ priv = ideapad_shared;
+ if (!priv)
+ return;
+
+ if (!priv->features.ymc_ec_trigger)
+ return;
+
+ scoped_guard(mutex, &priv->vpc_mutex)
+ ret = write_ec_cmd(priv->adev->handle, VPCCMD_W_YMC, 1);
+ if (ret)
+ dev_warn(&priv->platform_device->dev, "Could not write YMC: %d\n", ret);
+}
+
+static int ideapad_laptop_nb_notify(struct notifier_block *nb,
+ unsigned long action, void *data)
+{
+ switch (action) {
+ case IDEAPAD_LAPTOP_YMC_EVENT:
+ ideapad_laptop_trigger_ec();
+ break;
+ }
+
+ return 0;
+}
+
+static struct notifier_block ideapad_laptop_notifier = {
+ .notifier_call = ideapad_laptop_nb_notify,
+};
+
+static BLOCKING_NOTIFIER_HEAD(ideapad_laptop_chain_head);
+
+int ideapad_laptop_register_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&ideapad_laptop_chain_head, nb);
+}
+EXPORT_SYMBOL_NS_GPL(ideapad_laptop_register_notifier, IDEAPAD_LAPTOP);
+
+int ideapad_laptop_unregister_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_unregister(&ideapad_laptop_chain_head, nb);
+}
+EXPORT_SYMBOL_NS_GPL(ideapad_laptop_unregister_notifier, IDEAPAD_LAPTOP);
+
+void ideapad_laptop_call_notifier(unsigned long action, void *data)
+{
+ blocking_notifier_call_chain(&ideapad_laptop_chain_head, action, data);
+}
+EXPORT_SYMBOL_NS_GPL(ideapad_laptop_call_notifier, IDEAPAD_LAPTOP);
+
static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data)
{
struct ideapad_private *priv = data;
unsigned long vpc1, vpc2, bit;
- if (read_ec_data(handle, VPCCMD_R_VPC1, &vpc1))
- return;
+ scoped_guard(mutex, &priv->vpc_mutex) {
+ if (read_ec_data(handle, VPCCMD_R_VPC1, &vpc1))
+ return;
- if (read_ec_data(handle, VPCCMD_R_VPC2, &vpc2))
- return;
+ if (read_ec_data(handle, VPCCMD_R_VPC2, &vpc2))
+ return;
+ }
vpc1 = (vpc2 << 8) | vpc1;
@@ -1728,6 +1834,8 @@ static void ideapad_check_features(struct ideapad_private *priv)
priv->features.ctrl_ps2_aux_port =
ctrl_ps2_aux_port || dmi_check_system(ctrl_ps2_aux_port_list);
priv->features.touchpad_ctrl_via_ec = touchpad_ctrl_via_ec;
+ priv->features.ymc_ec_trigger =
+ ymc_ec_trigger || dmi_check_system(ymc_ec_trigger_quirk_dmi_table);
if (!read_ec_data(handle, VPCCMD_R_FAN, &val))
priv->features.fan_mode = true;
@@ -1906,6 +2014,10 @@ static int ideapad_acpi_add(struct platform_device *pdev)
priv->adev = adev;
priv->platform_device = pdev;
+ err = devm_mutex_init(&pdev->dev, &priv->vpc_mutex);
+ if (err)
+ return err;
+
ideapad_check_features(priv);
err = ideapad_sysfs_init(priv);
@@ -1974,6 +2086,8 @@ static int ideapad_acpi_add(struct platform_device *pdev)
if (err)
goto shared_init_failed;
+ ideapad_laptop_register_notifier(&ideapad_laptop_notifier);
+
return 0;
shared_init_failed:
@@ -2006,6 +2120,8 @@ static void ideapad_acpi_remove(struct platform_device *pdev)
struct ideapad_private *priv = dev_get_drvdata(&pdev->dev);
int i;
+ ideapad_laptop_unregister_notifier(&ideapad_laptop_notifier);
+
ideapad_shared_exit(priv);
acpi_remove_notify_handler(priv->adev->handle,
diff --git a/drivers/platform/x86/ideapad-laptop.h b/drivers/platform/x86/ideapad-laptop.h
index 4498a96..948cc618 100644
--- a/drivers/platform/x86/ideapad-laptop.h
+++ b/drivers/platform/x86/ideapad-laptop.h
@@ -12,6 +12,15 @@
#include <linux/acpi.h>
#include <linux/jiffies.h>
#include <linux/errno.h>
+#include <linux/notifier.h>
+
+enum ideapad_laptop_notifier_actions {
+ IDEAPAD_LAPTOP_YMC_EVENT,
+};
+
+int ideapad_laptop_register_notifier(struct notifier_block *nb);
+int ideapad_laptop_unregister_notifier(struct notifier_block *nb);
+void ideapad_laptop_call_notifier(unsigned long action, void *data);
enum {
VPCCMD_R_VPC1 = 0x10,
diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
index 7fa3600..4045823 100644
--- a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
+++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
@@ -1549,8 +1549,7 @@ int tpmi_sst_dev_add(struct auxiliary_device *auxdev)
goto unlock_free;
}
- ret = sst_main(auxdev, &pd_info[i]);
- if (ret) {
+ if (sst_main(auxdev, &pd_info[i])) {
/*
* This entry is not valid, hardware can partially
* populate dies. In this case MMIO will have 0xFFs.
diff --git a/drivers/platform/x86/lenovo-ymc.c b/drivers/platform/x86/lenovo-ymc.c
index e1fbc35..e0bbd6a 100644
--- a/drivers/platform/x86/lenovo-ymc.c
+++ b/drivers/platform/x86/lenovo-ymc.c
@@ -20,32 +20,10 @@
#define LENOVO_YMC_QUERY_INSTANCE 0
#define LENOVO_YMC_QUERY_METHOD 0x01
-static bool ec_trigger __read_mostly;
-module_param(ec_trigger, bool, 0444);
-MODULE_PARM_DESC(ec_trigger, "Enable EC triggering work-around to force emitting tablet mode events");
-
static bool force;
module_param(force, bool, 0444);
MODULE_PARM_DESC(force, "Force loading on boards without a convertible DMI chassis-type");
-static const struct dmi_system_id ec_trigger_quirk_dmi_table[] = {
- {
- /* Lenovo Yoga 7 14ARB7 */
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
- DMI_MATCH(DMI_PRODUCT_NAME, "82QF"),
- },
- },
- {
- /* Lenovo Yoga 7 14ACN6 */
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
- DMI_MATCH(DMI_PRODUCT_NAME, "82N7"),
- },
- },
- { }
-};
-
static const struct dmi_system_id allowed_chasis_types_dmi_table[] = {
{
.matches = {
@@ -62,21 +40,8 @@ static const struct dmi_system_id allowed_chasis_types_dmi_table[] = {
struct lenovo_ymc_private {
struct input_dev *input_dev;
- struct acpi_device *ec_acpi_dev;
};
-static void lenovo_ymc_trigger_ec(struct wmi_device *wdev, struct lenovo_ymc_private *priv)
-{
- int err;
-
- if (!priv->ec_acpi_dev)
- return;
-
- err = write_ec_cmd(priv->ec_acpi_dev->handle, VPCCMD_W_YMC, 1);
- if (err)
- dev_warn(&wdev->dev, "Could not write YMC: %d\n", err);
-}
-
static const struct key_entry lenovo_ymc_keymap[] = {
/* Laptop */
{ KE_SW, 0x01, { .sw = { SW_TABLET_MODE, 0 } } },
@@ -125,11 +90,9 @@ static void lenovo_ymc_notify(struct wmi_device *wdev, union acpi_object *data)
free_obj:
kfree(obj);
- lenovo_ymc_trigger_ec(wdev, priv);
+ ideapad_laptop_call_notifier(IDEAPAD_LAPTOP_YMC_EVENT, &code);
}
-static void acpi_dev_put_helper(void *p) { acpi_dev_put(p); }
-
static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx)
{
struct lenovo_ymc_private *priv;
@@ -143,29 +106,10 @@ static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx)
return -ENODEV;
}
- ec_trigger |= dmi_check_system(ec_trigger_quirk_dmi_table);
-
priv = devm_kzalloc(&wdev->dev, sizeof(*priv), GFP_KERNEL);
if (!priv)
return -ENOMEM;
- if (ec_trigger) {
- pr_debug("Lenovo YMC enable EC triggering.\n");
- priv->ec_acpi_dev = acpi_dev_get_first_match_dev("VPC2004", NULL, -1);
-
- if (!priv->ec_acpi_dev) {
- dev_err(&wdev->dev, "Could not find EC ACPI device.\n");
- return -ENODEV;
- }
- err = devm_add_action_or_reset(&wdev->dev,
- acpi_dev_put_helper, priv->ec_acpi_dev);
- if (err) {
- dev_err(&wdev->dev,
- "Could not clean up EC ACPI device: %d\n", err);
- return err;
- }
- }
-
input_dev = devm_input_allocate_device(&wdev->dev);
if (!input_dev)
return -ENOMEM;
@@ -192,7 +136,6 @@ static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx)
dev_set_drvdata(&wdev->dev, priv);
/* Report the state for the first time on probe */
- lenovo_ymc_trigger_ec(wdev, priv);
lenovo_ymc_notify(wdev, NULL);
return 0;
}
@@ -217,3 +160,4 @@ module_wmi_driver(lenovo_ymc_driver);
MODULE_AUTHOR("Gergo Koteles <soyer@irl.hu>");
MODULE_DESCRIPTION("Lenovo Yoga Mode Control driver");
MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(IDEAPAD_LAPTOP);
diff --git a/drivers/platform/x86/x86-android-tablets/dmi.c b/drivers/platform/x86/x86-android-tablets/dmi.c
index 141a2d2..387dd09 100644
--- a/drivers/platform/x86/x86-android-tablets/dmi.c
+++ b/drivers/platform/x86/x86-android-tablets/dmi.c
@@ -140,7 +140,6 @@ const struct dmi_system_id x86_android_tablet_ids[] __initconst = {
/* Lenovo Yoga Tab 3 Pro YT3-X90F */
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
- DMI_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"),
DMI_MATCH(DMI_PRODUCT_VERSION, "Blade3-10A-001"),
},
.driver_data = (void *)&lenovo_yt3_info,
diff --git a/drivers/pmdomain/imx/imx93-pd.c b/drivers/pmdomain/imx/imx93-pd.c
index 1e94b499..d750a7d 100644
--- a/drivers/pmdomain/imx/imx93-pd.c
+++ b/drivers/pmdomain/imx/imx93-pd.c
@@ -20,6 +20,7 @@
#define FUNC_STAT_PSW_STAT_MASK BIT(0)
#define FUNC_STAT_RST_STAT_MASK BIT(2)
#define FUNC_STAT_ISO_STAT_MASK BIT(4)
+#define FUNC_STAT_SSAR_STAT_MASK BIT(8)
struct imx93_power_domain {
struct generic_pm_domain genpd;
@@ -50,7 +51,7 @@ static int imx93_pd_on(struct generic_pm_domain *genpd)
writel(val, addr + MIX_SLICE_SW_CTRL_OFF);
ret = readl_poll_timeout(addr + MIX_FUNC_STAT_OFF, val,
- !(val & FUNC_STAT_ISO_STAT_MASK), 1, 10000);
+ !(val & FUNC_STAT_SSAR_STAT_MASK), 1, 10000);
if (ret) {
dev_err(domain->dev, "pd_on timeout: name: %s, stat: %x\n", genpd->name, val);
return ret;
@@ -72,7 +73,7 @@ static int imx93_pd_off(struct generic_pm_domain *genpd)
writel(val, addr + MIX_SLICE_SW_CTRL_OFF);
ret = readl_poll_timeout(addr + MIX_FUNC_STAT_OFF, val,
- val & FUNC_STAT_PSW_STAT_MASK, 1, 1000);
+ val & FUNC_STAT_PSW_STAT_MASK, 1, 10000);
if (ret) {
dev_err(domain->dev, "pd_off timeout: name: %s, stat: %x\n", genpd->name, val);
return ret;
diff --git a/drivers/pmdomain/imx/scu-pd.c b/drivers/pmdomain/imx/scu-pd.c
index 05841b0..01d465d 100644
--- a/drivers/pmdomain/imx/scu-pd.c
+++ b/drivers/pmdomain/imx/scu-pd.c
@@ -223,11 +223,6 @@ static const struct imx_sc_pd_range imx8qxp_scu_pd_ranges[] = {
{ "lvds1-pwm", IMX_SC_R_LVDS_1_PWM_0, 1, false, 0 },
{ "lvds1-lpi2c", IMX_SC_R_LVDS_1_I2C_0, 2, true, 0 },
- { "mipi1", IMX_SC_R_MIPI_1, 1, 0 },
- { "mipi1-pwm0", IMX_SC_R_MIPI_1_PWM_0, 1, 0 },
- { "mipi1-i2c", IMX_SC_R_MIPI_1_I2C_0, 2, 1 },
- { "lvds1", IMX_SC_R_LVDS_1, 1, 0 },
-
/* DC SS */
{ "dc0", IMX_SC_R_DC_0, 1, false, 0 },
{ "dc0-pll", IMX_SC_R_DC_0_PLL_0, 2, true, 0 },
diff --git a/drivers/power/sequencing/pwrseq-qcom-wcn.c b/drivers/power/sequencing/pwrseq-qcom-wcn.c
index 42dacfd..7008794 100644
--- a/drivers/power/sequencing/pwrseq-qcom-wcn.c
+++ b/drivers/power/sequencing/pwrseq-qcom-wcn.c
@@ -283,11 +283,18 @@ static int pwrseq_qcom_wcn_probe(struct platform_device *pdev)
"Failed to get the Bluetooth enable GPIO\n");
ctx->wlan_gpio = devm_gpiod_get_optional(dev, "wlan-enable",
- GPIOD_OUT_LOW);
+ GPIOD_ASIS);
if (IS_ERR(ctx->wlan_gpio))
return dev_err_probe(dev, PTR_ERR(ctx->wlan_gpio),
"Failed to get the WLAN enable GPIO\n");
+ /*
+ * Set direction to output but keep the current value in order to not
+ * disable the WLAN module accidentally if it's already powered on.
+ */
+ gpiod_direction_output(ctx->wlan_gpio,
+ gpiod_get_value_cansleep(ctx->wlan_gpio));
+
ctx->clk = devm_clk_get_optional(dev, NULL);
if (IS_ERR(ctx->clk))
return dev_err_probe(dev, PTR_ERR(ctx->clk),
diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c
index 49bef4a..8b3df3e 100644
--- a/drivers/power/supply/qcom_battmgr.c
+++ b/drivers/power/supply/qcom_battmgr.c
@@ -1387,12 +1387,16 @@ static int qcom_battmgr_probe(struct auxiliary_device *adev,
"failed to register wireless charing power supply\n");
}
- battmgr->client = devm_pmic_glink_register_client(dev,
- PMIC_GLINK_OWNER_BATTMGR,
- qcom_battmgr_callback,
- qcom_battmgr_pdr_notify,
- battmgr);
- return PTR_ERR_OR_ZERO(battmgr->client);
+ battmgr->client = devm_pmic_glink_client_alloc(dev, PMIC_GLINK_OWNER_BATTMGR,
+ qcom_battmgr_callback,
+ qcom_battmgr_pdr_notify,
+ battmgr);
+ if (IS_ERR(battmgr->client))
+ return PTR_ERR(battmgr->client);
+
+ pmic_glink_client_register(battmgr->client);
+
+ return 0;
}
static const struct auxiliary_device_id qcom_battmgr_id_table[] = {
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 0a97cfe..42a4a996 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -1601,9 +1601,15 @@ static int dasd_ese_needs_format(struct dasd_block *block, struct irb *irb)
if (!sense)
return 0;
- return !!(sense[1] & SNS1_NO_REC_FOUND) ||
- !!(sense[1] & SNS1_FILE_PROTECTED) ||
- scsw_cstat(&irb->scsw) == SCHN_STAT_INCORR_LEN;
+ if (sense[1] & SNS1_NO_REC_FOUND)
+ return 1;
+
+ if ((sense[1] & SNS1_INV_TRACK_FORMAT) &&
+ scsw_is_tm(&irb->scsw) &&
+ !(sense[2] & SNS2_ENV_DATA_PRESENT))
+ return 1;
+
+ return 0;
}
static int dasd_ese_oos_cond(u8 *sense)
@@ -1624,7 +1630,7 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm,
struct dasd_device *device;
unsigned long now;
int nrf_suppressed = 0;
- int fp_suppressed = 0;
+ int it_suppressed = 0;
struct request *req;
u8 *sense = NULL;
int expires;
@@ -1679,8 +1685,9 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm,
*/
sense = dasd_get_sense(irb);
if (sense) {
- fp_suppressed = (sense[1] & SNS1_FILE_PROTECTED) &&
- test_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags);
+ it_suppressed = (sense[1] & SNS1_INV_TRACK_FORMAT) &&
+ !(sense[2] & SNS2_ENV_DATA_PRESENT) &&
+ test_bit(DASD_CQR_SUPPRESS_IT, &cqr->flags);
nrf_suppressed = (sense[1] & SNS1_NO_REC_FOUND) &&
test_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags);
@@ -1695,7 +1702,7 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm,
return;
}
}
- if (!(fp_suppressed || nrf_suppressed))
+ if (!(it_suppressed || nrf_suppressed))
device->discipline->dump_sense_dbf(device, irb, "int");
if (device->features & DASD_FEATURE_ERPLOG)
@@ -2459,14 +2466,17 @@ static int _dasd_sleep_on_queue(struct list_head *ccw_queue, int interruptible)
rc = 0;
list_for_each_entry_safe(cqr, n, ccw_queue, blocklist) {
/*
- * In some cases the 'File Protected' or 'Incorrect Length'
- * error might be expected and error recovery would be
- * unnecessary in these cases. Check if the according suppress
- * bit is set.
+ * In some cases certain errors might be expected and
+ * error recovery would be unnecessary in these cases.
+ * Check if the according suppress bit is set.
*/
sense = dasd_get_sense(&cqr->irb);
- if (sense && sense[1] & SNS1_FILE_PROTECTED &&
- test_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags))
+ if (sense && (sense[1] & SNS1_INV_TRACK_FORMAT) &&
+ !(sense[2] & SNS2_ENV_DATA_PRESENT) &&
+ test_bit(DASD_CQR_SUPPRESS_IT, &cqr->flags))
+ continue;
+ if (sense && (sense[1] & SNS1_NO_REC_FOUND) &&
+ test_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags))
continue;
if (scsw_cstat(&cqr->irb.scsw) == 0x40 &&
test_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags))
diff --git a/drivers/s390/block/dasd_3990_erp.c b/drivers/s390/block/dasd_3990_erp.c
index bbbacfc..d0aa267 100644
--- a/drivers/s390/block/dasd_3990_erp.c
+++ b/drivers/s390/block/dasd_3990_erp.c
@@ -1386,14 +1386,8 @@ dasd_3990_erp_file_prot(struct dasd_ccw_req * erp)
struct dasd_device *device = erp->startdev;
- /*
- * In some cases the 'File Protected' error might be expected and
- * log messages shouldn't be written then.
- * Check if the according suppress bit is set.
- */
- if (!test_bit(DASD_CQR_SUPPRESS_FP, &erp->flags))
- dev_err(&device->cdev->dev,
- "Accessing the DASD failed because of a hardware error\n");
+ dev_err(&device->cdev->dev,
+ "Accessing the DASD failed because of a hardware error\n");
return dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED);
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 9388b5c..90b1064 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -2275,6 +2275,7 @@ dasd_eckd_analysis_ccw(struct dasd_device *device)
cqr->status = DASD_CQR_FILLED;
/* Set flags to suppress output for expected errors */
set_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags);
+ set_bit(DASD_CQR_SUPPRESS_IT, &cqr->flags);
return cqr;
}
@@ -2556,7 +2557,6 @@ dasd_eckd_build_check_tcw(struct dasd_device *base, struct format_data_t *fdata,
cqr->buildclk = get_tod_clock();
cqr->status = DASD_CQR_FILLED;
/* Set flags to suppress output for expected errors */
- set_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags);
set_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags);
return cqr;
@@ -4130,8 +4130,6 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single(
/* Set flags to suppress output for expected errors */
if (dasd_eckd_is_ese(basedev)) {
- set_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags);
- set_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags);
set_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags);
}
@@ -4633,9 +4631,8 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_tpm_track(
/* Set flags to suppress output for expected errors */
if (dasd_eckd_is_ese(basedev)) {
- set_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags);
- set_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags);
set_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags);
+ set_bit(DASD_CQR_SUPPRESS_IT, &cqr->flags);
}
return cqr;
@@ -5780,36 +5777,32 @@ static void dasd_eckd_dump_sense(struct dasd_device *device,
{
u8 *sense = dasd_get_sense(irb);
- if (scsw_is_tm(&irb->scsw)) {
- /*
- * In some cases the 'File Protected' or 'Incorrect Length'
- * error might be expected and log messages shouldn't be written
- * then. Check if the according suppress bit is set.
- */
- if (sense && (sense[1] & SNS1_FILE_PROTECTED) &&
- test_bit(DASD_CQR_SUPPRESS_FP, &req->flags))
- return;
- if (scsw_cstat(&irb->scsw) == 0x40 &&
- test_bit(DASD_CQR_SUPPRESS_IL, &req->flags))
- return;
+ /*
+ * In some cases certain errors might be expected and
+ * log messages shouldn't be written then.
+ * Check if the according suppress bit is set.
+ */
+ if (sense && (sense[1] & SNS1_INV_TRACK_FORMAT) &&
+ !(sense[2] & SNS2_ENV_DATA_PRESENT) &&
+ test_bit(DASD_CQR_SUPPRESS_IT, &req->flags))
+ return;
+ if (sense && sense[0] & SNS0_CMD_REJECT &&
+ test_bit(DASD_CQR_SUPPRESS_CR, &req->flags))
+ return;
+
+ if (sense && sense[1] & SNS1_NO_REC_FOUND &&
+ test_bit(DASD_CQR_SUPPRESS_NRF, &req->flags))
+ return;
+
+ if (scsw_cstat(&irb->scsw) == 0x40 &&
+ test_bit(DASD_CQR_SUPPRESS_IL, &req->flags))
+ return;
+
+ if (scsw_is_tm(&irb->scsw))
dasd_eckd_dump_sense_tcw(device, req, irb);
- } else {
- /*
- * In some cases the 'Command Reject' or 'No Record Found'
- * error might be expected and log messages shouldn't be
- * written then. Check if the according suppress bit is set.
- */
- if (sense && sense[0] & SNS0_CMD_REJECT &&
- test_bit(DASD_CQR_SUPPRESS_CR, &req->flags))
- return;
-
- if (sense && sense[1] & SNS1_NO_REC_FOUND &&
- test_bit(DASD_CQR_SUPPRESS_NRF, &req->flags))
- return;
-
+ else
dasd_eckd_dump_sense_ccw(device, req, irb);
- }
}
static int dasd_eckd_reload_device(struct dasd_device *device)
diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c
index 1aa426b..6da47a6 100644
--- a/drivers/s390/block/dasd_genhd.c
+++ b/drivers/s390/block/dasd_genhd.c
@@ -41,7 +41,6 @@ int dasd_gendisk_alloc(struct dasd_block *block)
*/
.max_segment_size = PAGE_SIZE,
.seg_boundary_mask = PAGE_SIZE - 1,
- .dma_alignment = PAGE_SIZE - 1,
.max_segments = USHRT_MAX,
};
struct gendisk *gdp;
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index e5f4053..81cfb5c 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -196,7 +196,7 @@ struct dasd_ccw_req {
* The following flags are used to suppress output of certain errors.
*/
#define DASD_CQR_SUPPRESS_NRF 4 /* Suppress 'No Record Found' error */
-#define DASD_CQR_SUPPRESS_FP 5 /* Suppress 'File Protected' error*/
+#define DASD_CQR_SUPPRESS_IT 5 /* Suppress 'Invalid Track' error*/
#define DASD_CQR_SUPPRESS_IL 6 /* Suppress 'Incorrect Length' error */
#define DASD_CQR_SUPPRESS_CR 7 /* Suppress 'Command Reject' error */
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 0998b17..f9f682f 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -971,11 +971,16 @@ int ap_driver_register(struct ap_driver *ap_drv, struct module *owner,
char *name)
{
struct device_driver *drv = &ap_drv->driver;
+ int rc;
drv->bus = &ap_bus_type;
drv->owner = owner;
drv->name = name;
- return driver_register(drv);
+ rc = driver_register(drv);
+
+ ap_check_bindings_complete();
+
+ return rc;
}
EXPORT_SYMBOL(ap_driver_register);
diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c
index bd99c54..0f64b02 100644
--- a/drivers/scsi/aacraid/comminit.c
+++ b/drivers/scsi/aacraid/comminit.c
@@ -642,6 +642,7 @@ struct aac_dev *aac_init_adapter(struct aac_dev *dev)
if (aac_comm_init(dev)<0){
kfree(dev->queues);
+ dev->queues = NULL;
return NULL;
}
/*
@@ -649,6 +650,7 @@ struct aac_dev *aac_init_adapter(struct aac_dev *dev)
*/
if (aac_fib_setup(dev) < 0) {
kfree(dev->queues);
+ dev->queues = NULL;
return NULL;
}
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index 4156419..4756a3f 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -5410,7 +5410,7 @@ lpfc_get_cgnbuf_info(struct bsg_job *job)
struct get_cgnbuf_info_req *cgnbuf_req;
struct lpfc_cgn_info *cp;
uint8_t *cgn_buff;
- int size, cinfosz;
+ size_t size, cinfosz;
int rc = 0;
if (job->request_len < sizeof(struct fc_bsg_request) +
diff --git a/drivers/scsi/mpi3mr/mpi3mr_app.c b/drivers/scsi/mpi3mr/mpi3mr_app.c
index 8b0eded..01f035f 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_app.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_app.c
@@ -100,7 +100,8 @@ void mpi3mr_alloc_diag_bufs(struct mpi3mr_ioc *mrioc)
dprint_init(mrioc,
"trying to allocate trace diag buffer of size = %dKB\n",
trace_size / 1024);
- if (mpi3mr_alloc_trace_buffer(mrioc, trace_size)) {
+ if (get_order(trace_size) > MAX_PAGE_ORDER ||
+ mpi3mr_alloc_trace_buffer(mrioc, trace_size)) {
retry = true;
trace_size -= trace_dec_size;
dprint_init(mrioc, "trace diag buffer allocation failed\n"
@@ -118,8 +119,12 @@ void mpi3mr_alloc_diag_bufs(struct mpi3mr_ioc *mrioc)
diag_buffer->type = MPI3_DIAG_BUFFER_TYPE_FW;
diag_buffer->status = MPI3MR_HDB_BUFSTATUS_NOT_ALLOCATED;
if ((mrioc->facts.diag_fw_sz < fw_size) && (fw_size >= fw_min_size)) {
- diag_buffer->addr = dma_alloc_coherent(&mrioc->pdev->dev,
- fw_size, &diag_buffer->dma_addr, GFP_KERNEL);
+ if (get_order(fw_size) <= MAX_PAGE_ORDER) {
+ diag_buffer->addr
+ = dma_alloc_coherent(&mrioc->pdev->dev, fw_size,
+ &diag_buffer->dma_addr,
+ GFP_KERNEL);
+ }
if (!retry)
dprint_init(mrioc,
"%s:trying to allocate firmware diag buffer of size = %dKB\n",
diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c
index ca8f132..6168945 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_os.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_os.c
@@ -5234,6 +5234,7 @@ mpi3mr_probe(struct pci_dev *pdev, const struct pci_device_id *id)
spin_lock_init(&mrioc->watchdog_lock);
spin_lock_init(&mrioc->chain_buf_lock);
spin_lock_init(&mrioc->sas_node_lock);
+ spin_lock_init(&mrioc->trigger_lock);
INIT_LIST_HEAD(&mrioc->fwevt_list);
INIT_LIST_HEAD(&mrioc->tgtdev_list);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 699f4f9..9db8694 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1823,13 +1823,15 @@ static int sd_sync_cache(struct scsi_disk *sdkp)
(sshdr.asc == 0x74 && sshdr.ascq == 0x71)) /* drive is password locked */
/* this is no error here */
return 0;
+
/*
- * This drive doesn't support sync and there's not much
- * we can do because this is called during shutdown
- * or suspend so just return success so those operations
- * can proceed.
+ * If a format is in progress or if the drive does not
+ * support sync, there is not much we can do because
+ * this is called during shutdown or suspend so just
+ * return success so those operations can proceed.
*/
- if (sshdr.sense_key == ILLEGAL_REQUEST)
+ if ((sshdr.asc == 0x04 && sshdr.ascq == 0x04) ||
+ sshdr.sense_key == ILLEGAL_REQUEST)
return 0;
}
@@ -3308,6 +3310,9 @@ static void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer)
static unsigned int sd_discard_mode(struct scsi_disk *sdkp)
{
+ if (!sdkp->lbpme)
+ return SD_LBP_FULL;
+
if (!sdkp->lbpvpd) {
/* LBP VPD page not provided */
if (sdkp->max_unmap_blocks)
diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c
index 7e90745..4dc8aba 100644
--- a/drivers/soc/fsl/qbman/qman.c
+++ b/drivers/soc/fsl/qbman/qman.c
@@ -2546,11 +2546,6 @@ int qman_delete_cgr(struct qman_cgr *cgr)
}
EXPORT_SYMBOL(qman_delete_cgr);
-struct cgr_comp {
- struct qman_cgr *cgr;
- struct completion completion;
-};
-
static void qman_delete_cgr_smp_call(void *p)
{
qman_delete_cgr((struct qman_cgr *)p);
diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index 7f02f05..74b9121 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -77,7 +77,7 @@
select QCOM_QMI_HELPERS
select QCOM_PDR_MSG
select AUXILIARY_BUS
- depends on NET && QRTR
+ depends on NET && QRTR && (ARCH_QCOM || COMPILE_TEST)
default QCOM_RPROC_COMMON
help
The Protection Domain Mapper maps registered services to the domains
diff --git a/drivers/soc/qcom/cmd-db.c b/drivers/soc/qcom/cmd-db.c
index d845726..ae66c26 100644
--- a/drivers/soc/qcom/cmd-db.c
+++ b/drivers/soc/qcom/cmd-db.c
@@ -349,7 +349,7 @@ static int cmd_db_dev_probe(struct platform_device *pdev)
return -EINVAL;
}
- cmd_db_header = memremap(rmem->base, rmem->size, MEMREMAP_WB);
+ cmd_db_header = memremap(rmem->base, rmem->size, MEMREMAP_WC);
if (!cmd_db_header) {
ret = -ENOMEM;
cmd_db_header = NULL;
diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c
index 9ebc0ba..96062229 100644
--- a/drivers/soc/qcom/pmic_glink.c
+++ b/drivers/soc/qcom/pmic_glink.c
@@ -66,15 +66,14 @@ static void _devm_pmic_glink_release_client(struct device *dev, void *res)
spin_unlock_irqrestore(&pg->client_lock, flags);
}
-struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev,
- unsigned int id,
- void (*cb)(const void *, size_t, void *),
- void (*pdr)(void *, int),
- void *priv)
+struct pmic_glink_client *devm_pmic_glink_client_alloc(struct device *dev,
+ unsigned int id,
+ void (*cb)(const void *, size_t, void *),
+ void (*pdr)(void *, int),
+ void *priv)
{
struct pmic_glink_client *client;
struct pmic_glink *pg = dev_get_drvdata(dev->parent);
- unsigned long flags;
client = devres_alloc(_devm_pmic_glink_release_client, sizeof(*client), GFP_KERNEL);
if (!client)
@@ -85,6 +84,18 @@ struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev,
client->cb = cb;
client->pdr_notify = pdr;
client->priv = priv;
+ INIT_LIST_HEAD(&client->node);
+
+ devres_add(dev, client);
+
+ return client;
+}
+EXPORT_SYMBOL_GPL(devm_pmic_glink_client_alloc);
+
+void pmic_glink_client_register(struct pmic_glink_client *client)
+{
+ struct pmic_glink *pg = client->pg;
+ unsigned long flags;
mutex_lock(&pg->state_lock);
spin_lock_irqsave(&pg->client_lock, flags);
@@ -95,17 +106,22 @@ struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev,
spin_unlock_irqrestore(&pg->client_lock, flags);
mutex_unlock(&pg->state_lock);
- devres_add(dev, client);
-
- return client;
}
-EXPORT_SYMBOL_GPL(devm_pmic_glink_register_client);
+EXPORT_SYMBOL_GPL(pmic_glink_client_register);
int pmic_glink_send(struct pmic_glink_client *client, void *data, size_t len)
{
struct pmic_glink *pg = client->pg;
+ int ret;
- return rpmsg_send(pg->ept, data, len);
+ mutex_lock(&pg->state_lock);
+ if (!pg->ept)
+ ret = -ECONNRESET;
+ else
+ ret = rpmsg_send(pg->ept, data, len);
+ mutex_unlock(&pg->state_lock);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(pmic_glink_send);
@@ -175,7 +191,7 @@ static void pmic_glink_state_notify_clients(struct pmic_glink *pg)
if (pg->pdr_state == SERVREG_SERVICE_STATE_UP && pg->ept)
new_state = SERVREG_SERVICE_STATE_UP;
} else {
- if (pg->pdr_state == SERVREG_SERVICE_STATE_UP && pg->ept)
+ if (pg->pdr_state == SERVREG_SERVICE_STATE_DOWN || !pg->ept)
new_state = SERVREG_SERVICE_STATE_DOWN;
}
diff --git a/drivers/soc/qcom/pmic_glink_altmode.c b/drivers/soc/qcom/pmic_glink_altmode.c
index 1e0808b..463b1c5 100644
--- a/drivers/soc/qcom/pmic_glink_altmode.c
+++ b/drivers/soc/qcom/pmic_glink_altmode.c
@@ -520,12 +520,17 @@ static int pmic_glink_altmode_probe(struct auxiliary_device *adev,
return ret;
}
- altmode->client = devm_pmic_glink_register_client(dev,
- altmode->owner_id,
- pmic_glink_altmode_callback,
- pmic_glink_altmode_pdr_notify,
- altmode);
- return PTR_ERR_OR_ZERO(altmode->client);
+ altmode->client = devm_pmic_glink_client_alloc(dev,
+ altmode->owner_id,
+ pmic_glink_altmode_callback,
+ pmic_glink_altmode_pdr_notify,
+ altmode);
+ if (IS_ERR(altmode->client))
+ return PTR_ERR(altmode->client);
+
+ pmic_glink_client_register(altmode->client);
+
+ return 0;
}
static const struct auxiliary_device_id pmic_glink_altmode_id_table[] = {
diff --git a/drivers/soc/qcom/qcom_pd_mapper.c b/drivers/soc/qcom/qcom_pd_mapper.c
index a4c0070..2228595 100644
--- a/drivers/soc/qcom/qcom_pd_mapper.c
+++ b/drivers/soc/qcom/qcom_pd_mapper.c
@@ -517,7 +517,7 @@ static const struct qcom_pdm_domain_data *sm8550_domains[] = {
NULL,
};
-static const struct of_device_id qcom_pdm_domains[] = {
+static const struct of_device_id qcom_pdm_domains[] __maybe_unused = {
{ .compatible = "qcom,apq8064", .data = NULL, },
{ .compatible = "qcom,apq8074", .data = NULL, },
{ .compatible = "qcom,apq8084", .data = NULL, },
@@ -635,6 +635,8 @@ static int qcom_pdm_probe(struct auxiliary_device *auxdev,
ret = PTR_ERR(data);
else
__qcom_pdm_data = data;
+ } else {
+ refcount_inc(&__qcom_pdm_data->refcnt);
}
auxiliary_set_drvdata(auxdev, __qcom_pdm_data);
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index 7aa4900..f275143 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -1291,18 +1291,18 @@ struct sdw_dpn_prop *sdw_get_slave_dpn_prop(struct sdw_slave *slave,
unsigned int port_num)
{
struct sdw_dpn_prop *dpn_prop;
- u8 num_ports;
+ unsigned long mask;
int i;
if (direction == SDW_DATA_DIR_TX) {
- num_ports = hweight32(slave->prop.source_ports);
+ mask = slave->prop.source_ports;
dpn_prop = slave->prop.src_dpn_prop;
} else {
- num_ports = hweight32(slave->prop.sink_ports);
+ mask = slave->prop.sink_ports;
dpn_prop = slave->prop.sink_dpn_prop;
}
- for (i = 0; i < num_ports; i++) {
+ for_each_set_bit(i, &mask, 32) {
if (dpn_prop[i].num == port_num)
return &dpn_prop[i];
}
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 05ebb03..d4607cb 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -2000,13 +2000,25 @@ static int cqspi_runtime_resume(struct device *dev)
static int cqspi_suspend(struct device *dev)
{
struct cqspi_st *cqspi = dev_get_drvdata(dev);
+ int ret;
- return spi_controller_suspend(cqspi->host);
+ ret = spi_controller_suspend(cqspi->host);
+ if (ret)
+ return ret;
+
+ return pm_runtime_force_suspend(dev);
}
static int cqspi_resume(struct device *dev)
{
struct cqspi_st *cqspi = dev_get_drvdata(dev);
+ int ret;
+
+ ret = pm_runtime_force_resume(dev);
+ if (ret) {
+ dev_err(dev, "pm_runtime_force_resume failed on resume\n");
+ return ret;
+ }
return spi_controller_resume(cqspi->host);
}
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index be261ac..350c5d9 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -82,6 +82,10 @@
#define TCR_RXMSK BIT(19)
#define TCR_TXMSK BIT(18)
+struct fsl_lpspi_devtype_data {
+ u8 prescale_max;
+};
+
struct lpspi_config {
u8 bpw;
u8 chip_select;
@@ -119,10 +123,25 @@ struct fsl_lpspi_data {
bool usedma;
struct completion dma_rx_completion;
struct completion dma_tx_completion;
+
+ const struct fsl_lpspi_devtype_data *devtype_data;
+};
+
+/*
+ * ERR051608 fixed or not:
+ * https://www.nxp.com/docs/en/errata/i.MX93_1P87f.pdf
+ */
+static struct fsl_lpspi_devtype_data imx93_lpspi_devtype_data = {
+ .prescale_max = 1,
+};
+
+static struct fsl_lpspi_devtype_data imx7ulp_lpspi_devtype_data = {
+ .prescale_max = 8,
};
static const struct of_device_id fsl_lpspi_dt_ids[] = {
- { .compatible = "fsl,imx7ulp-spi", },
+ { .compatible = "fsl,imx7ulp-spi", .data = &imx7ulp_lpspi_devtype_data,},
+ { .compatible = "fsl,imx93-spi", .data = &imx93_lpspi_devtype_data,},
{ /* sentinel */ }
};
MODULE_DEVICE_TABLE(of, fsl_lpspi_dt_ids);
@@ -297,9 +316,11 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi)
{
struct lpspi_config config = fsl_lpspi->config;
unsigned int perclk_rate, scldiv, div;
+ u8 prescale_max;
u8 prescale;
perclk_rate = clk_get_rate(fsl_lpspi->clk_per);
+ prescale_max = fsl_lpspi->devtype_data->prescale_max;
if (!config.speed_hz) {
dev_err(fsl_lpspi->dev,
@@ -315,7 +336,7 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi)
div = DIV_ROUND_UP(perclk_rate, config.speed_hz);
- for (prescale = 0; prescale < 8; prescale++) {
+ for (prescale = 0; prescale < prescale_max; prescale++) {
scldiv = div / (1 << prescale) - 2;
if (scldiv < 256) {
fsl_lpspi->config.prescale = prescale;
@@ -822,6 +843,7 @@ static int fsl_lpspi_init_rpm(struct fsl_lpspi_data *fsl_lpspi)
static int fsl_lpspi_probe(struct platform_device *pdev)
{
+ const struct fsl_lpspi_devtype_data *devtype_data;
struct fsl_lpspi_data *fsl_lpspi;
struct spi_controller *controller;
struct resource *res;
@@ -830,6 +852,10 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
u32 temp;
bool is_target;
+ devtype_data = of_device_get_match_data(&pdev->dev);
+ if (!devtype_data)
+ return -ENODEV;
+
is_target = of_property_read_bool((&pdev->dev)->of_node, "spi-slave");
if (is_target)
controller = devm_spi_alloc_target(&pdev->dev,
@@ -848,6 +874,7 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
fsl_lpspi->is_target = is_target;
fsl_lpspi->is_only_cs1 = of_property_read_bool((&pdev->dev)->of_node,
"fsl,spi-only-use-cs1-sel");
+ fsl_lpspi->devtype_data = devtype_data;
init_completion(&fsl_lpspi->xfer_done);
diff --git a/drivers/spi/spi-pxa2xx-pci.c b/drivers/spi/spi-pxa2xx-pci.c
index 616d032..cc8dcf7 100644
--- a/drivers/spi/spi-pxa2xx-pci.c
+++ b/drivers/spi/spi-pxa2xx-pci.c
@@ -11,6 +11,7 @@
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/pm.h>
+#include <linux/pm_runtime.h>
#include <linux/sprintf.h>
#include <linux/string.h>
#include <linux/types.h>
@@ -297,11 +298,23 @@ static int pxa2xx_spi_pci_probe(struct pci_dev *dev,
return ret;
ssp->irq = pci_irq_vector(dev, 0);
- return pxa2xx_spi_probe(&dev->dev, ssp);
+ ret = pxa2xx_spi_probe(&dev->dev, ssp, pdata);
+ if (ret)
+ return ret;
+
+ pm_runtime_set_autosuspend_delay(&dev->dev, 50);
+ pm_runtime_use_autosuspend(&dev->dev);
+ pm_runtime_put_autosuspend(&dev->dev);
+ pm_runtime_allow(&dev->dev);
+
+ return 0;
}
static void pxa2xx_spi_pci_remove(struct pci_dev *dev)
{
+ pm_runtime_forbid(&dev->dev);
+ pm_runtime_get_noresume(&dev->dev);
+
pxa2xx_spi_remove(&dev->dev);
}
diff --git a/drivers/spi/spi-pxa2xx-platform.c b/drivers/spi/spi-pxa2xx-platform.c
index 98a8ceb..595af9f 100644
--- a/drivers/spi/spi-pxa2xx-platform.c
+++ b/drivers/spi/spi-pxa2xx-platform.c
@@ -7,6 +7,7 @@
#include <linux/init.h>
#include <linux/mod_devicetable.h>
#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
#include <linux/property.h>
#include <linux/types.h>
@@ -63,7 +64,7 @@ static struct ssp_device *pxa2xx_spi_ssp_request(struct platform_device *pdev)
ssp = pxa_ssp_request(pdev->id, pdev->name);
if (!ssp)
- return ssp;
+ return NULL;
status = devm_add_action_or_reset(&pdev->dev, pxa2xx_spi_ssp_release, ssp);
if (status)
@@ -142,14 +143,13 @@ static int pxa2xx_spi_platform_probe(struct platform_device *pdev)
struct pxa2xx_spi_controller *platform_info;
struct device *dev = &pdev->dev;
struct ssp_device *ssp;
+ int ret;
platform_info = dev_get_platdata(dev);
if (!platform_info) {
platform_info = pxa2xx_spi_init_pdata(pdev);
if (IS_ERR(platform_info))
return dev_err_probe(dev, PTR_ERR(platform_info), "missing platform data\n");
-
- dev->platform_data = platform_info;
}
ssp = pxa2xx_spi_ssp_request(pdev);
@@ -158,12 +158,28 @@ static int pxa2xx_spi_platform_probe(struct platform_device *pdev)
if (!ssp)
ssp = &platform_info->ssp;
- return pxa2xx_spi_probe(dev, ssp);
+ pm_runtime_set_autosuspend_delay(dev, 50);
+ pm_runtime_use_autosuspend(dev);
+ pm_runtime_set_active(dev);
+ pm_runtime_enable(dev);
+
+ ret = pxa2xx_spi_probe(dev, ssp, platform_info);
+ if (ret)
+ pm_runtime_disable(dev);
+
+ return ret;
}
static void pxa2xx_spi_platform_remove(struct platform_device *pdev)
{
- pxa2xx_spi_remove(&pdev->dev);
+ struct device *dev = &pdev->dev;
+
+ pm_runtime_get_sync(dev);
+
+ pxa2xx_spi_remove(dev);
+
+ pm_runtime_put_noidle(dev);
+ pm_runtime_disable(dev);
}
static const struct acpi_device_id pxa2xx_spi_acpi_match[] = {
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 16b96eb..bf1f34b0 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -1277,16 +1277,15 @@ static size_t pxa2xx_spi_max_dma_transfer_size(struct spi_device *spi)
return MAX_DMA_LEN;
}
-int pxa2xx_spi_probe(struct device *dev, struct ssp_device *ssp)
+int pxa2xx_spi_probe(struct device *dev, struct ssp_device *ssp,
+ struct pxa2xx_spi_controller *platform_info)
{
- struct pxa2xx_spi_controller *platform_info;
struct spi_controller *controller;
struct driver_data *drv_data;
const struct lpss_config *config;
int status;
u32 tmp;
- platform_info = dev_get_platdata(dev);
if (platform_info->is_target)
controller = devm_spi_alloc_target(dev, sizeof(*drv_data));
else
@@ -1450,24 +1449,16 @@ int pxa2xx_spi_probe(struct device *dev, struct ssp_device *ssp)
}
}
- pm_runtime_set_autosuspend_delay(dev, 50);
- pm_runtime_use_autosuspend(dev);
- pm_runtime_set_active(dev);
- pm_runtime_enable(dev);
-
/* Register with the SPI framework */
dev_set_drvdata(dev, drv_data);
status = spi_register_controller(controller);
if (status) {
dev_err_probe(dev, status, "problem registering SPI controller\n");
- goto out_error_pm_runtime_enabled;
+ goto out_error_clock_enabled;
}
return status;
-out_error_pm_runtime_enabled:
- pm_runtime_disable(dev);
-
out_error_clock_enabled:
clk_disable_unprepare(ssp->clk);
@@ -1484,8 +1475,6 @@ void pxa2xx_spi_remove(struct device *dev)
struct driver_data *drv_data = dev_get_drvdata(dev);
struct ssp_device *ssp = drv_data->ssp;
- pm_runtime_get_sync(dev);
-
spi_unregister_controller(drv_data->controller);
/* Disable the SSP at the peripheral and SOC level */
@@ -1496,9 +1485,6 @@ void pxa2xx_spi_remove(struct device *dev)
if (drv_data->controller_info->enable_dma)
pxa2xx_spi_dma_release(drv_data);
- pm_runtime_put_noidle(dev);
- pm_runtime_disable(dev);
-
/* Release IRQ */
free_irq(ssp->irq, drv_data);
}
diff --git a/drivers/spi/spi-pxa2xx.h b/drivers/spi/spi-pxa2xx.h
index a470d3d..447be03 100644
--- a/drivers/spi/spi-pxa2xx.h
+++ b/drivers/spi/spi-pxa2xx.h
@@ -132,7 +132,8 @@ extern void pxa2xx_spi_dma_stop(struct driver_data *drv_data);
extern int pxa2xx_spi_dma_setup(struct driver_data *drv_data);
extern void pxa2xx_spi_dma_release(struct driver_data *drv_data);
-int pxa2xx_spi_probe(struct device *dev, struct ssp_device *ssp);
+int pxa2xx_spi_probe(struct device *dev, struct ssp_device *ssp,
+ struct pxa2xx_spi_controller *platform_info);
void pxa2xx_spi_remove(struct device *dev);
extern const struct dev_pm_ops pxa2xx_spi_pm_ops;
diff --git a/drivers/spi/spi-zynqmp-gqspi.c b/drivers/spi/spi-zynqmp-gqspi.c
index 99524a3..558c466 100644
--- a/drivers/spi/spi-zynqmp-gqspi.c
+++ b/drivers/spi/spi-zynqmp-gqspi.c
@@ -1033,6 +1033,18 @@ static int __maybe_unused zynqmp_runtime_resume(struct device *dev)
return 0;
}
+static unsigned long zynqmp_qspi_timeout(struct zynqmp_qspi *xqspi, u8 bits,
+ unsigned long bytes)
+{
+ unsigned long timeout;
+
+ /* Assume we are at most 2x slower than the nominal bus speed */
+ timeout = mult_frac(bytes, 2 * 8 * MSEC_PER_SEC,
+ bits * xqspi->speed_hz);
+ /* And add 100 ms for scheduling delays */
+ return msecs_to_jiffies(timeout + 100);
+}
+
/**
* zynqmp_qspi_exec_op() - Initiates the QSPI transfer
* @mem: The SPI memory
@@ -1049,6 +1061,7 @@ static int zynqmp_qspi_exec_op(struct spi_mem *mem,
{
struct zynqmp_qspi *xqspi = spi_controller_get_devdata
(mem->spi->controller);
+ unsigned long timeout;
int err = 0, i;
u32 genfifoentry = 0;
u16 opcode = op->cmd.opcode;
@@ -1077,8 +1090,10 @@ static int zynqmp_qspi_exec_op(struct spi_mem *mem,
zynqmp_gqspi_write(xqspi, GQSPI_IER_OFST,
GQSPI_IER_GENFIFOEMPTY_MASK |
GQSPI_IER_TXNOT_FULL_MASK);
- if (!wait_for_completion_timeout
- (&xqspi->data_completion, msecs_to_jiffies(1000))) {
+ timeout = zynqmp_qspi_timeout(xqspi, op->cmd.buswidth,
+ op->cmd.nbytes);
+ if (!wait_for_completion_timeout(&xqspi->data_completion,
+ timeout)) {
err = -ETIMEDOUT;
goto return_err;
}
@@ -1104,8 +1119,10 @@ static int zynqmp_qspi_exec_op(struct spi_mem *mem,
GQSPI_IER_TXEMPTY_MASK |
GQSPI_IER_GENFIFOEMPTY_MASK |
GQSPI_IER_TXNOT_FULL_MASK);
- if (!wait_for_completion_timeout
- (&xqspi->data_completion, msecs_to_jiffies(1000))) {
+ timeout = zynqmp_qspi_timeout(xqspi, op->addr.buswidth,
+ op->addr.nbytes);
+ if (!wait_for_completion_timeout(&xqspi->data_completion,
+ timeout)) {
err = -ETIMEDOUT;
goto return_err;
}
@@ -1173,8 +1190,9 @@ static int zynqmp_qspi_exec_op(struct spi_mem *mem,
GQSPI_IER_RXEMPTY_MASK);
}
}
- if (!wait_for_completion_timeout
- (&xqspi->data_completion, msecs_to_jiffies(1000)))
+ timeout = zynqmp_qspi_timeout(xqspi, op->data.buswidth,
+ op->data.nbytes);
+ if (!wait_for_completion_timeout(&xqspi->data_completion, timeout))
err = -ETIMEDOUT;
}
diff --git a/drivers/staging/media/atomisp/include/linux/atomisp.h b/drivers/staging/media/atomisp/include/linux/atomisp.h
index 16c9da1..fefbe3c 100644
--- a/drivers/staging/media/atomisp/include/linux/atomisp.h
+++ b/drivers/staging/media/atomisp/include/linux/atomisp.h
@@ -20,7 +20,6 @@
#define _ATOM_ISP_H
#include <linux/types.h>
-#include <linux/version.h>
/* struct media_device_info.hw_revision */
#define ATOMISP_HW_REVISION_MASK 0x0000ff00
diff --git a/drivers/staging/media/atomisp/pci/ia_css_stream_public.h b/drivers/staging/media/atomisp/pci/ia_css_stream_public.h
index 961c612..aad860e 100644
--- a/drivers/staging/media/atomisp/pci/ia_css_stream_public.h
+++ b/drivers/staging/media/atomisp/pci/ia_css_stream_public.h
@@ -27,12 +27,16 @@
#include "ia_css_prbs.h"
#include "ia_css_input_port.h"
-/* Input modes, these enumerate all supported input modes.
- * Note that not all ISP modes support all input modes.
+/*
+ * Input modes, these enumerate all supported input modes.
+ * This enum is part of the atomisp firmware ABI and must
+ * NOT be changed!
+ * Note that not all ISP modes support all input modes.
*/
enum ia_css_input_mode {
IA_CSS_INPUT_MODE_SENSOR, /** data from sensor */
IA_CSS_INPUT_MODE_FIFO, /** data from input-fifo */
+ IA_CSS_INPUT_MODE_TPG, /** data from test-pattern generator */
IA_CSS_INPUT_MODE_PRBS, /** data from pseudo-random bit stream */
IA_CSS_INPUT_MODE_MEMORY, /** data from a frame in memory */
IA_CSS_INPUT_MODE_BUFFERED_SENSOR /** data is sent through mipi buffer */
diff --git a/drivers/staging/media/atomisp/pci/sh_css_internal.h b/drivers/staging/media/atomisp/pci/sh_css_internal.h
index a2d972e..959e7f5 100644
--- a/drivers/staging/media/atomisp/pci/sh_css_internal.h
+++ b/drivers/staging/media/atomisp/pci/sh_css_internal.h
@@ -344,7 +344,14 @@ struct sh_css_sp_input_formatter_set {
#define IA_CSS_MIPI_SIZE_CHECK_MAX_NOF_ENTRIES_PER_PORT (3)
-/* SP configuration information */
+/*
+ * SP configuration information
+ *
+ * This struct is part of the atomisp firmware ABI and is directly copied
+ * to ISP DRAM by sh_css_store_sp_group_to_ddr()
+ *
+ * Do NOT change this struct's layout or remove seemingly unused fields!
+ */
struct sh_css_sp_config {
u8 no_isp_sync; /* Signal host immediately after start */
u8 enable_raw_pool_locking; /** Enable Raw Buffer Locking for HALv3 Support */
@@ -354,6 +361,10 @@ struct sh_css_sp_config {
host (true) or when they are passed to the preview/video pipe
(false). */
+ /*
+ * Note the fields below are only used on the ISP2400 not on the ISP2401,
+ * sh_css_store_sp_group_to_ddr() skip copying these when run on the ISP2401.
+ */
struct {
u8 a_changed;
u8 b_changed;
@@ -363,11 +374,13 @@ struct sh_css_sp_config {
} input_formatter;
sync_generator_cfg_t sync_gen;
+ tpg_cfg_t tpg;
prbs_cfg_t prbs;
input_system_cfg_t input_circuit;
u8 input_circuit_cfg_changed;
- u32 mipi_sizes_for_check[N_CSI_PORTS][IA_CSS_MIPI_SIZE_CHECK_MAX_NOF_ENTRIES_PER_PORT];
- u8 enable_isys_event_queue;
+ u32 mipi_sizes_for_check[N_CSI_PORTS][IA_CSS_MIPI_SIZE_CHECK_MAX_NOF_ENTRIES_PER_PORT];
+ /* These last 2 fields are used on both the ISP2400 and the ISP2401 */
+ u8 enable_isys_event_queue;
u8 disable_cont_vf;
};
diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c
index 4a2e869..daed67d 100644
--- a/drivers/thermal/gov_bang_bang.c
+++ b/drivers/thermal/gov_bang_bang.c
@@ -13,6 +13,28 @@
#include "thermal_core.h"
+static void bang_bang_set_instance_target(struct thermal_instance *instance,
+ unsigned int target)
+{
+ if (instance->target != 0 && instance->target != 1 &&
+ instance->target != THERMAL_NO_TARGET)
+ pr_debug("Unexpected state %ld of thermal instance %s in bang-bang\n",
+ instance->target, instance->name);
+
+ /*
+ * Enable the fan when the trip is crossed on the way up and disable it
+ * when the trip is crossed on the way down.
+ */
+ instance->target = target;
+ instance->initialized = true;
+
+ dev_dbg(&instance->cdev->device, "target=%ld\n", instance->target);
+
+ mutex_lock(&instance->cdev->lock);
+ __thermal_cdev_update(instance->cdev);
+ mutex_unlock(&instance->cdev->lock);
+}
+
/**
* bang_bang_control - controls devices associated with the given zone
* @tz: thermal_zone_device
@@ -54,33 +76,60 @@ static void bang_bang_control(struct thermal_zone_device *tz,
tz->temperature, trip->hysteresis);
list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
- if (instance->trip != trip)
+ if (instance->trip == trip)
+ bang_bang_set_instance_target(instance, crossed_up);
+ }
+}
+
+static void bang_bang_manage(struct thermal_zone_device *tz)
+{
+ const struct thermal_trip_desc *td;
+ struct thermal_instance *instance;
+
+ /* If the code below has run already, nothing needs to be done. */
+ if (tz->governor_data)
+ return;
+
+ for_each_trip_desc(tz, td) {
+ const struct thermal_trip *trip = &td->trip;
+
+ if (tz->temperature >= td->threshold ||
+ trip->temperature == THERMAL_TEMP_INVALID ||
+ trip->type == THERMAL_TRIP_CRITICAL ||
+ trip->type == THERMAL_TRIP_HOT)
continue;
- if (instance->target != 0 && instance->target != 1 &&
- instance->target != THERMAL_NO_TARGET)
- pr_debug("Unexpected state %ld of thermal instance %s in bang-bang\n",
- instance->target, instance->name);
-
/*
- * Enable the fan when the trip is crossed on the way up and
- * disable it when the trip is crossed on the way down.
+ * If the initial cooling device state is "on", but the zone
+ * temperature is not above the trip point, the core will not
+ * call bang_bang_control() until the zone temperature reaches
+ * the trip point temperature which may be never. In those
+ * cases, set the initial state of the cooling device to 0.
*/
- instance->target = crossed_up;
-
- dev_dbg(&instance->cdev->device, "target=%ld\n", instance->target);
-
- mutex_lock(&instance->cdev->lock);
- instance->cdev->updated = false; /* cdev needs update */
- mutex_unlock(&instance->cdev->lock);
+ list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+ if (!instance->initialized && instance->trip == trip)
+ bang_bang_set_instance_target(instance, 0);
+ }
}
- list_for_each_entry(instance, &tz->thermal_instances, tz_node)
- thermal_cdev_update(instance->cdev);
+ tz->governor_data = (void *)true;
+}
+
+static void bang_bang_update_tz(struct thermal_zone_device *tz,
+ enum thermal_notify_event reason)
+{
+ /*
+ * Let bang_bang_manage() know that it needs to walk trips after binding
+ * a new cdev and after system resume.
+ */
+ if (reason == THERMAL_TZ_BIND_CDEV || reason == THERMAL_TZ_RESUME)
+ tz->governor_data = NULL;
}
static struct thermal_governor thermal_gov_bang_bang = {
.name = "bang_bang",
.trip_crossed = bang_bang_control,
+ .manage = bang_bang_manage,
+ .update_tz = bang_bang_update_tz,
};
THERMAL_GOVERNOR_DECLARE(thermal_gov_bang_bang);
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 95c399f..e6669ae 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1728,7 +1728,8 @@ static void thermal_zone_device_resume(struct work_struct *work)
thermal_debug_tz_resume(tz);
thermal_zone_device_init(tz);
- __thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
+ thermal_governor_update_tz(tz, THERMAL_TZ_RESUME);
+ __thermal_zone_device_update(tz, THERMAL_TZ_RESUME);
complete(&tz->resume);
tz->resuming = false;
diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c
index 7dd67bf..939d3e5 100644
--- a/drivers/thermal/thermal_debugfs.c
+++ b/drivers/thermal/thermal_debugfs.c
@@ -178,11 +178,11 @@ struct thermal_debugfs {
void thermal_debug_init(void)
{
d_root = debugfs_create_dir("thermal", NULL);
- if (!d_root)
+ if (IS_ERR(d_root))
return;
d_cdev = debugfs_create_dir("cooling_devices", d_root);
- if (!d_cdev)
+ if (IS_ERR(d_cdev))
return;
d_tz = debugfs_create_dir("thermal_zones", d_root);
@@ -202,7 +202,7 @@ static struct thermal_debugfs *thermal_debugfs_add_id(struct dentry *d, int id)
snprintf(ids, IDSLENGTH, "%d", id);
thermal_dbg->d_top = debugfs_create_dir(ids, d);
- if (!thermal_dbg->d_top) {
+ if (IS_ERR(thermal_dbg->d_top)) {
kfree(thermal_dbg);
return NULL;
}
diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c
index aa34b6e..1f25269 100644
--- a/drivers/thermal/thermal_of.c
+++ b/drivers/thermal/thermal_of.c
@@ -125,7 +125,7 @@ static int thermal_of_populate_trip(struct device_node *np,
static struct thermal_trip *thermal_of_trips_init(struct device_node *np, int *ntrips)
{
struct thermal_trip *tt;
- struct device_node *trips, *trip;
+ struct device_node *trips;
int ret, count;
trips = of_get_child_by_name(np, "trips");
@@ -150,7 +150,7 @@ static struct thermal_trip *thermal_of_trips_init(struct device_node *np, int *n
*ntrips = count;
count = 0;
- for_each_child_of_node(trips, trip) {
+ for_each_child_of_node_scoped(trips, trip) {
ret = thermal_of_populate_trip(trip, &tt[count++]);
if (ret)
goto out_kfree;
@@ -184,14 +184,14 @@ static struct device_node *of_thermal_zone_find(struct device_node *sensor, int
* Search for each thermal zone, a defined sensor
* corresponding to the one passed as parameter
*/
- for_each_available_child_of_node(np, tz) {
+ for_each_available_child_of_node_scoped(np, child) {
int count, i;
- count = of_count_phandle_with_args(tz, "thermal-sensors",
+ count = of_count_phandle_with_args(child, "thermal-sensors",
"#thermal-sensor-cells");
if (count <= 0) {
- pr_err("%pOFn: missing thermal sensor\n", tz);
+ pr_err("%pOFn: missing thermal sensor\n", child);
tz = ERR_PTR(-EINVAL);
goto out;
}
@@ -200,18 +200,19 @@ static struct device_node *of_thermal_zone_find(struct device_node *sensor, int
int ret;
- ret = of_parse_phandle_with_args(tz, "thermal-sensors",
+ ret = of_parse_phandle_with_args(child, "thermal-sensors",
"#thermal-sensor-cells",
i, &sensor_specs);
if (ret < 0) {
- pr_err("%pOFn: Failed to read thermal-sensors cells: %d\n", tz, ret);
+ pr_err("%pOFn: Failed to read thermal-sensors cells: %d\n", child, ret);
tz = ERR_PTR(ret);
goto out;
}
if ((sensor == sensor_specs.np) && id == (sensor_specs.args_count ?
sensor_specs.args[0] : 0)) {
- pr_debug("sensor %pOFn id=%d belongs to %pOFn\n", sensor, id, tz);
+ pr_debug("sensor %pOFn id=%d belongs to %pOFn\n", sensor, id, child);
+ tz = no_free_ptr(child);
goto out;
}
}
@@ -491,7 +492,8 @@ static struct thermal_zone_device *thermal_of_zone_register(struct device_node *
trips = thermal_of_trips_init(np, &ntrips);
if (IS_ERR(trips)) {
pr_err("Failed to find trip points for %pOFn id=%d\n", sensor, id);
- return ERR_CAST(trips);
+ ret = PTR_ERR(trips);
+ goto out_of_node_put;
}
ret = thermal_of_monitor_init(np, &delay, &pdelay);
@@ -519,6 +521,7 @@ static struct thermal_zone_device *thermal_of_zone_register(struct device_node *
goto out_kfree_trips;
}
+ of_node_put(np);
kfree(trips);
ret = thermal_zone_device_enable(tz);
@@ -533,6 +536,8 @@ static struct thermal_zone_device *thermal_of_zone_register(struct device_node *
out_kfree_trips:
kfree(trips);
+out_of_node_put:
+ of_node_put(np);
return ERR_PTR(ret);
}
diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c
index 11185cc..9ed4bb2 100644
--- a/drivers/thunderbolt/debugfs.c
+++ b/drivers/thunderbolt/debugfs.c
@@ -323,16 +323,17 @@ static ssize_t port_sb_regs_write(struct file *file, const char __user *user_buf
if (mutex_lock_interruptible(&tb->lock)) {
ret = -ERESTARTSYS;
- goto out_rpm_put;
+ goto out;
}
ret = sb_regs_write(port, port_sb_regs, ARRAY_SIZE(port_sb_regs),
USB4_SB_TARGET_ROUTER, 0, buf, count, ppos);
mutex_unlock(&tb->lock);
-out_rpm_put:
+out:
pm_runtime_mark_last_busy(&sw->dev);
pm_runtime_put_autosuspend(&sw->dev);
+ free_page((unsigned long)buf);
return ret < 0 ? ret : count;
}
@@ -355,16 +356,17 @@ static ssize_t retimer_sb_regs_write(struct file *file,
if (mutex_lock_interruptible(&tb->lock)) {
ret = -ERESTARTSYS;
- goto out_rpm_put;
+ goto out;
}
ret = sb_regs_write(rt->port, retimer_sb_regs, ARRAY_SIZE(retimer_sb_regs),
USB4_SB_TARGET_RETIMER, rt->index, buf, count, ppos);
mutex_unlock(&tb->lock);
-out_rpm_put:
+out:
pm_runtime_mark_last_busy(&rt->dev);
pm_runtime_put_autosuspend(&rt->dev);
+ free_page((unsigned long)buf);
return ret < 0 ? ret : count;
}
diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 326433d..6a2116c 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -3392,6 +3392,7 @@ void tb_switch_remove(struct tb_switch *sw)
tb_switch_remove(port->remote->sw);
port->remote = NULL;
} else if (port->xdomain) {
+ port->xdomain->is_unplugged = true;
tb_xdomain_remove(port->xdomain);
port->xdomain = NULL;
}
diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
index 1af9aed..afef1dd 100644
--- a/drivers/tty/serial/8250/8250_omap.c
+++ b/drivers/tty/serial/8250/8250_omap.c
@@ -27,7 +27,6 @@
#include <linux/pm_wakeirq.h>
#include <linux/dma-mapping.h>
#include <linux/sys_soc.h>
-#include <linux/pm_domain.h>
#include "8250.h"
@@ -119,12 +118,6 @@
#define UART_OMAP_TO_L 0x26
#define UART_OMAP_TO_H 0x27
-/*
- * Copy of the genpd flags for the console.
- * Only used if console suspend is disabled
- */
-static unsigned int genpd_flags_console;
-
struct omap8250_priv {
void __iomem *membase;
int line;
@@ -1655,7 +1648,6 @@ static int omap8250_suspend(struct device *dev)
{
struct omap8250_priv *priv = dev_get_drvdata(dev);
struct uart_8250_port *up = serial8250_get_port(priv->line);
- struct generic_pm_domain *genpd = pd_to_genpd(dev->pm_domain);
int err = 0;
serial8250_suspend_port(priv->line);
@@ -1666,19 +1658,8 @@ static int omap8250_suspend(struct device *dev)
if (!device_may_wakeup(dev))
priv->wer = 0;
serial_out(up, UART_OMAP_WER, priv->wer);
- if (uart_console(&up->port)) {
- if (console_suspend_enabled)
- err = pm_runtime_force_suspend(dev);
- else {
- /*
- * The pd shall not be powered-off (no console suspend).
- * Make copy of genpd flags before to set it always on.
- * The original value is restored during the resume.
- */
- genpd_flags_console = genpd->flags;
- genpd->flags |= GENPD_FLAG_ALWAYS_ON;
- }
- }
+ if (uart_console(&up->port) && console_suspend_enabled)
+ err = pm_runtime_force_suspend(dev);
flush_work(&priv->qos_work);
return err;
@@ -1688,16 +1669,12 @@ static int omap8250_resume(struct device *dev)
{
struct omap8250_priv *priv = dev_get_drvdata(dev);
struct uart_8250_port *up = serial8250_get_port(priv->line);
- struct generic_pm_domain *genpd = pd_to_genpd(dev->pm_domain);
int err;
if (uart_console(&up->port) && console_suspend_enabled) {
- if (console_suspend_enabled) {
- err = pm_runtime_force_resume(dev);
- if (err)
- return err;
- } else
- genpd->flags = genpd_flags_console;
+ err = pm_runtime_force_resume(dev);
+ if (err)
+ return err;
}
serial8250_resume_port(priv->line);
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 0a90964..09b246c 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -2514,7 +2514,7 @@ static const struct uart_ops atmel_pops = {
};
static const struct serial_rs485 atmel_rs485_supported = {
- .flags = SER_RS485_ENABLED | SER_RS485_RTS_AFTER_SEND | SER_RS485_RX_DURING_TX,
+ .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RX_DURING_TX,
.delay_rts_before_send = 1,
.delay_rts_after_send = 1,
};
diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index 615291e..77efa7e 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -2923,6 +2923,7 @@ static int lpuart_probe(struct platform_device *pdev)
pm_runtime_set_autosuspend_delay(&pdev->dev, UART_AUTOSUSPEND_TIMEOUT);
pm_runtime_set_active(&pdev->dev);
pm_runtime_enable(&pdev->dev);
+ pm_runtime_mark_last_busy(&pdev->dev);
ret = lpuart_global_reset(sport);
if (ret)
diff --git a/drivers/tty/vt/conmakehash.c b/drivers/tty/vt/conmakehash.c
index 82d9db6..a931fcd 100644
--- a/drivers/tty/vt/conmakehash.c
+++ b/drivers/tty/vt/conmakehash.c
@@ -11,8 +11,6 @@
* Copyright (C) 1995-1997 H. Peter Anvin
*/
-#include <libgen.h>
-#include <linux/limits.h>
#include <stdio.h>
#include <stdlib.h>
#include <sysexits.h>
@@ -79,7 +77,6 @@ int main(int argc, char *argv[])
{
FILE *ctbl;
const char *tblname;
- char base_tblname[PATH_MAX];
char buffer[65536];
int fontlen;
int i, nuni, nent;
@@ -245,20 +242,15 @@ int main(int argc, char *argv[])
for ( i = 0 ; i < fontlen ; i++ )
nuni += unicount[i];
- strncpy(base_tblname, tblname, PATH_MAX);
- base_tblname[PATH_MAX - 1] = 0;
printf("\
/*\n\
- * Do not edit this file; it was automatically generated by\n\
- *\n\
- * conmakehash %s > [this file]\n\
- *\n\
+ * Automatically generated file; Do not edit.\n\
*/\n\
\n\
#include <linux/types.h>\n\
\n\
u8 dfont_unicount[%d] = \n\
-{\n\t", basename(base_tblname), fontlen);
+{\n\t", fontlen);
for ( i = 0 ; i < fontlen ; i++ )
{
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 0b3d0c8..a6f818c 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -2426,7 +2426,11 @@ static inline int ufshcd_hba_capabilities(struct ufs_hba *hba)
* 0h: legacy single doorbell support is available
* 1h: indicate that legacy single doorbell support has been removed
*/
- hba->lsdb_sup = !FIELD_GET(MASK_LSDB_SUPPORT, hba->capabilities);
+ if (!(hba->quirks & UFSHCD_QUIRK_BROKEN_LSDBS_CAP))
+ hba->lsdb_sup = !FIELD_GET(MASK_LSDB_SUPPORT, hba->capabilities);
+ else
+ hba->lsdb_sup = true;
+
if (!hba->mcq_sup)
return 0;
diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index 810e637..c87fdc8 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -857,6 +857,9 @@ static void ufs_qcom_advertise_quirks(struct ufs_hba *hba)
if (host->hw_ver.major > 0x3)
hba->quirks |= UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH;
+
+ if (of_device_is_compatible(hba->dev->of_node, "qcom,sm8550-ufshc"))
+ hba->quirks |= UFSHCD_QUIRK_BROKEN_LSDBS_CAP;
}
static void ufs_qcom_set_phy_gear(struct ufs_qcom_host *host)
@@ -1847,7 +1850,8 @@ static void ufs_qcom_remove(struct platform_device *pdev)
}
static const struct of_device_id ufs_qcom_of_match[] __maybe_unused = {
- { .compatible = "qcom,ufshc"},
+ { .compatible = "qcom,ufshc" },
+ { .compatible = "qcom,sm8550-ufshc" },
{},
};
MODULE_DEVICE_TABLE(of, ufs_qcom_of_match);
diff --git a/drivers/usb/cdns3/cdnsp-gadget.h b/drivers/usb/cdns3/cdnsp-gadget.h
index dbee6f0..84887df 100644
--- a/drivers/usb/cdns3/cdnsp-gadget.h
+++ b/drivers/usb/cdns3/cdnsp-gadget.h
@@ -811,6 +811,7 @@ struct cdnsp_stream_info {
* generate Missed Service Error Event.
* Set skip flag when receive a Missed Service Error Event and
* process the missed tds on the endpoint ring.
+ * @wa1_nop_trb: hold pointer to NOP trb.
*/
struct cdnsp_ep {
struct usb_ep endpoint;
@@ -838,6 +839,8 @@ struct cdnsp_ep {
#define EP_UNCONFIGURED BIT(7)
bool skip;
+ union cdnsp_trb *wa1_nop_trb;
+
};
/**
diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c
index 02f297f..dbd83d3 100644
--- a/drivers/usb/cdns3/cdnsp-ring.c
+++ b/drivers/usb/cdns3/cdnsp-ring.c
@@ -402,7 +402,7 @@ static u64 cdnsp_get_hw_deq(struct cdnsp_device *pdev,
struct cdnsp_stream_ctx *st_ctx;
struct cdnsp_ep *pep;
- pep = &pdev->eps[stream_id];
+ pep = &pdev->eps[ep_index];
if (pep->ep_state & EP_HAS_STREAMS) {
st_ctx = &pep->stream_info.stream_ctx_array[stream_id];
@@ -1905,6 +1905,23 @@ int cdnsp_queue_bulk_tx(struct cdnsp_device *pdev, struct cdnsp_request *preq)
return ret;
/*
+ * workaround 1: STOP EP command on LINK TRB with TC bit set to 1
+ * causes that internal cycle bit can have incorrect state after
+ * command complete. In consequence empty transfer ring can be
+ * incorrectly detected when EP is resumed.
+ * NOP TRB before LINK TRB avoid such scenario. STOP EP command is
+ * then on NOP TRB and internal cycle bit is not changed and have
+ * correct value.
+ */
+ if (pep->wa1_nop_trb) {
+ field = le32_to_cpu(pep->wa1_nop_trb->trans_event.flags);
+ field ^= TRB_CYCLE;
+
+ pep->wa1_nop_trb->trans_event.flags = cpu_to_le32(field);
+ pep->wa1_nop_trb = NULL;
+ }
+
+ /*
* Don't give the first TRB to the hardware (by toggling the cycle bit)
* until we've finished creating all the other TRBs. The ring's cycle
* state may change as we enqueue the other TRBs, so save it too.
@@ -1999,6 +2016,17 @@ int cdnsp_queue_bulk_tx(struct cdnsp_device *pdev, struct cdnsp_request *preq)
send_addr = addr;
}
+ if (cdnsp_trb_is_link(ring->enqueue + 1)) {
+ field = TRB_TYPE(TRB_TR_NOOP) | TRB_IOC;
+ if (!ring->cycle_state)
+ field |= TRB_CYCLE;
+
+ pep->wa1_nop_trb = ring->enqueue;
+
+ cdnsp_queue_trb(pdev, ring, 0, 0x0, 0x0,
+ TRB_INTR_TARGET(0), field);
+ }
+
cdnsp_check_trb_math(preq, enqd_len);
ret = cdnsp_giveback_first_trb(pdev, pep, preq->request.stream_id,
start_cycle, start_trb);
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 0e7439d..0c1b69d 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1761,6 +1761,9 @@ static const struct usb_device_id acm_ids[] = {
{ USB_DEVICE(0x11ca, 0x0201), /* VeriFone Mx870 Gadget Serial */
.driver_info = SINGLE_RX_URB,
},
+ { USB_DEVICE(0x1901, 0x0006), /* GE Healthcare Patient Monitor UI Controller */
+ .driver_info = DISABLE_ECHO, /* DISABLE ECHO in termios flag */
+ },
{ USB_DEVICE(0x1965, 0x0018), /* Uniden UBC125XLT */
.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
},
diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c
index d83231d..61b6d97 100644
--- a/drivers/usb/core/sysfs.c
+++ b/drivers/usb/core/sysfs.c
@@ -670,6 +670,7 @@ static int add_power_attributes(struct device *dev)
static void remove_power_attributes(struct device *dev)
{
+ sysfs_unmerge_group(&dev->kobj, &usb3_hardware_lpm_attr_group);
sysfs_unmerge_group(&dev->kobj, &usb2_hardware_lpm_attr_group);
sysfs_unmerge_group(&dev->kobj, &power_attr_group);
}
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 734de2a..ccc3895 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -564,9 +564,17 @@ int dwc3_event_buffers_setup(struct dwc3 *dwc)
void dwc3_event_buffers_cleanup(struct dwc3 *dwc)
{
struct dwc3_event_buffer *evt;
+ u32 reg;
if (!dwc->ev_buf)
return;
+ /*
+ * Exynos platforms may not be able to access event buffer if the
+ * controller failed to halt on dwc3_core_exit().
+ */
+ reg = dwc3_readl(dwc->regs, DWC3_DSTS);
+ if (!(reg & DWC3_DSTS_DEVCTRLHLT))
+ return;
evt = dwc->ev_buf;
diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index d5c77db..2a11fc0 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -522,11 +522,13 @@ static int dwc3_omap_probe(struct platform_device *pdev)
if (ret) {
dev_err(dev, "failed to request IRQ #%d --> %d\n",
omap->irq, ret);
- goto err1;
+ goto err2;
}
dwc3_omap_enable_irqs(omap);
return 0;
+err2:
+ of_platform_depopulate(dev);
err1:
pm_runtime_put_sync(dev);
pm_runtime_disable(dev);
diff --git a/drivers/usb/dwc3/dwc3-st.c b/drivers/usb/dwc3/dwc3-st.c
index 211360e..c8c7cd0 100644
--- a/drivers/usb/dwc3/dwc3-st.c
+++ b/drivers/usb/dwc3/dwc3-st.c
@@ -219,10 +219,8 @@ static int st_dwc3_probe(struct platform_device *pdev)
dwc3_data->regmap = regmap;
res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "syscfg-reg");
- if (!res) {
- ret = -ENXIO;
- goto undo_platform_dev_alloc;
- }
+ if (!res)
+ return -ENXIO;
dwc3_data->syscfg_reg_off = res->start;
@@ -233,8 +231,7 @@ static int st_dwc3_probe(struct platform_device *pdev)
devm_reset_control_get_exclusive(dev, "powerdown");
if (IS_ERR(dwc3_data->rstc_pwrdn)) {
dev_err(&pdev->dev, "could not get power controller\n");
- ret = PTR_ERR(dwc3_data->rstc_pwrdn);
- goto undo_platform_dev_alloc;
+ return PTR_ERR(dwc3_data->rstc_pwrdn);
}
/* Manage PowerDown */
@@ -269,7 +266,7 @@ static int st_dwc3_probe(struct platform_device *pdev)
if (!child_pdev) {
dev_err(dev, "failed to find dwc3 core device\n");
ret = -ENODEV;
- goto err_node_put;
+ goto depopulate;
}
dwc3_data->dr_mode = usb_get_dr_mode(&child_pdev->dev);
@@ -285,6 +282,7 @@ static int st_dwc3_probe(struct platform_device *pdev)
ret = st_dwc3_drd_init(dwc3_data);
if (ret) {
dev_err(dev, "drd initialisation failed\n");
+ of_platform_depopulate(dev);
goto undo_softreset;
}
@@ -294,14 +292,14 @@ static int st_dwc3_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, dwc3_data);
return 0;
+depopulate:
+ of_platform_depopulate(dev);
err_node_put:
of_node_put(child);
undo_softreset:
reset_control_assert(dwc3_data->rstc_rst);
undo_powerdown:
reset_control_assert(dwc3_data->rstc_pwrdn);
-undo_platform_dev_alloc:
- platform_device_put(pdev);
return ret;
}
diff --git a/drivers/usb/dwc3/dwc3-xilinx.c b/drivers/usb/dwc3/dwc3-xilinx.c
index bb4d894..f1298b1 100644
--- a/drivers/usb/dwc3/dwc3-xilinx.c
+++ b/drivers/usb/dwc3/dwc3-xilinx.c
@@ -327,9 +327,14 @@ static int dwc3_xlnx_probe(struct platform_device *pdev)
goto err_pm_set_suspended;
pm_suspend_ignore_children(dev, false);
- return pm_runtime_resume_and_get(dev);
+ ret = pm_runtime_resume_and_get(dev);
+ if (ret < 0)
+ goto err_pm_set_suspended;
+
+ return 0;
err_pm_set_suspended:
+ of_platform_depopulate(dev);
pm_runtime_set_suspended(dev);
err_clk_put:
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index d96ffbe..c9533a9 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -232,7 +232,8 @@ void dwc3_ep0_stall_and_restart(struct dwc3 *dwc)
/* stall is always issued on EP0 */
dep = dwc->eps[0];
__dwc3_gadget_ep_set_halt(dep, 1, false);
- dep->flags = DWC3_EP_ENABLED;
+ dep->flags &= DWC3_EP_RESOURCE_ALLOCATED;
+ dep->flags |= DWC3_EP_ENABLED;
dwc->delayed_status = false;
if (!list_empty(&dep->pending_list)) {
diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c
index d41f5f3..a9edd60 100644
--- a/drivers/usb/gadget/function/uvc_video.c
+++ b/drivers/usb/gadget/function/uvc_video.c
@@ -753,6 +753,7 @@ int uvcg_video_enable(struct uvc_video *video)
video->req_int_count = 0;
uvc_video_ep_queue_initial_requests(video);
+ queue_work(video->async_wq, &video->pump);
return ret;
}
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index d7654f4..937ce5f 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1872,7 +1872,7 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
cancel_delayed_work_sync(&xhci->cmd_timer);
- for (i = 0; i < xhci->max_interrupters; i++) {
+ for (i = 0; xhci->interrupters && i < xhci->max_interrupters; i++) {
if (xhci->interrupters[i]) {
xhci_remove_interrupter(xhci, xhci->interrupters[i]);
xhci_free_interrupter(xhci, xhci->interrupters[i]);
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index b7517c3..4ea2c3e 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -2910,6 +2910,7 @@ static int handle_tx_event(struct xhci_hcd *xhci,
process_isoc_td(xhci, ep, ep_ring, td, ep_trb, event);
else
process_bulk_intr_td(xhci, ep, ep_ring, td, ep_trb, event);
+ return 0;
check_endpoint_halted:
if (xhci_halted_host_endpoint(ep_ctx, trb_comp_code))
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 0a8cf6c..efdf4c2 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -2837,7 +2837,7 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
xhci->num_active_eps);
return -ENOMEM;
}
- if ((xhci->quirks & XHCI_SW_BW_CHECKING) &&
+ if ((xhci->quirks & XHCI_SW_BW_CHECKING) && !ctx_change &&
xhci_reserve_bandwidth(xhci, virt_dev, command->in_ctx)) {
if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK))
xhci_free_host_resources(xhci, ctrl_ctx);
@@ -4200,8 +4200,10 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev,
mutex_unlock(&xhci->mutex);
ret = xhci_disable_slot(xhci, udev->slot_id);
xhci_free_virt_device(xhci, udev->slot_id);
- if (!ret)
- xhci_alloc_dev(hcd, udev);
+ if (!ret) {
+ if (xhci_alloc_dev(hcd, udev) == 1)
+ xhci_setup_addressable_virt_dev(xhci, udev);
+ }
kfree(command->completion);
kfree(command);
return -EPROTO;
diff --git a/drivers/usb/misc/usb-ljca.c b/drivers/usb/misc/usb-ljca.c
index 2d30fc1..1a8d5e8 100644
--- a/drivers/usb/misc/usb-ljca.c
+++ b/drivers/usb/misc/usb-ljca.c
@@ -169,6 +169,7 @@ static const struct acpi_device_id ljca_gpio_hids[] = {
{ "INTC1096" },
{ "INTC100B" },
{ "INTC10D1" },
+ { "INTC10B5" },
{},
};
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 311040f..176f387 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -619,6 +619,8 @@ static void option_instat_callback(struct urb *urb);
/* MeiG Smart Technology products */
#define MEIGSMART_VENDOR_ID 0x2dee
+/* MeiG Smart SRM825L based on Qualcomm 315 */
+#define MEIGSMART_PRODUCT_SRM825L 0x4d22
/* MeiG Smart SLM320 based on UNISOC UIS8910 */
#define MEIGSMART_PRODUCT_SLM320 0x4d41
@@ -2366,6 +2368,9 @@ static const struct usb_device_id option_ids[] = {
{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM320, 0xff, 0, 0) },
+ { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x30) },
+ { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x60) },
{ } /* Terminating entry */
};
MODULE_DEVICE_TABLE(usb, option_ids);
diff --git a/drivers/usb/typec/mux/fsa4480.c b/drivers/usb/typec/mux/fsa4480.c
index cd23533..f71dba8 100644
--- a/drivers/usb/typec/mux/fsa4480.c
+++ b/drivers/usb/typec/mux/fsa4480.c
@@ -274,7 +274,7 @@ static int fsa4480_probe(struct i2c_client *client)
return dev_err_probe(dev, PTR_ERR(fsa->regmap), "failed to initialize regmap\n");
ret = regmap_read(fsa->regmap, FSA4480_DEVICE_ID, &val);
- if (ret || !val)
+ if (ret)
return dev_err_probe(dev, -ENODEV, "FSA4480 not found\n");
dev_dbg(dev, "Found FSA4480 v%lu.%lu (Vendor ID = %lu)\n",
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index cce3981..4b02d64 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -5655,7 +5655,6 @@ static void run_state_machine(struct tcpm_port *port)
break;
case PORT_RESET:
tcpm_reset_port(port);
- port->pd_events = 0;
if (port->self_powered)
tcpm_set_cc(port, TYPEC_CC_OPEN);
else
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 432a2d6..4039851 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -137,7 +137,7 @@ static int ucsi_run_command(struct ucsi *ucsi, u64 command, u32 *cci,
if (ret)
return ret;
- return err;
+ return err ?: UCSI_CCI_LENGTH(*cci);
}
static int ucsi_read_error(struct ucsi *ucsi, u8 connector_num)
diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c
index 16c3284..6aace19 100644
--- a/drivers/usb/typec/ucsi/ucsi_glink.c
+++ b/drivers/usb/typec/ucsi/ucsi_glink.c
@@ -68,6 +68,9 @@ struct pmic_glink_ucsi {
struct work_struct notify_work;
struct work_struct register_work;
+ spinlock_t state_lock;
+ bool ucsi_registered;
+ bool pd_running;
u8 read_buf[UCSI_BUF_SIZE];
};
@@ -244,8 +247,20 @@ static void pmic_glink_ucsi_notify(struct work_struct *work)
static void pmic_glink_ucsi_register(struct work_struct *work)
{
struct pmic_glink_ucsi *ucsi = container_of(work, struct pmic_glink_ucsi, register_work);
+ unsigned long flags;
+ bool pd_running;
- ucsi_register(ucsi->ucsi);
+ spin_lock_irqsave(&ucsi->state_lock, flags);
+ pd_running = ucsi->pd_running;
+ spin_unlock_irqrestore(&ucsi->state_lock, flags);
+
+ if (!ucsi->ucsi_registered && pd_running) {
+ ucsi_register(ucsi->ucsi);
+ ucsi->ucsi_registered = true;
+ } else if (ucsi->ucsi_registered && !pd_running) {
+ ucsi_unregister(ucsi->ucsi);
+ ucsi->ucsi_registered = false;
+ }
}
static void pmic_glink_ucsi_callback(const void *data, size_t len, void *priv)
@@ -269,11 +284,12 @@ static void pmic_glink_ucsi_callback(const void *data, size_t len, void *priv)
static void pmic_glink_ucsi_pdr_notify(void *priv, int state)
{
struct pmic_glink_ucsi *ucsi = priv;
+ unsigned long flags;
- if (state == SERVREG_SERVICE_STATE_UP)
- schedule_work(&ucsi->register_work);
- else if (state == SERVREG_SERVICE_STATE_DOWN)
- ucsi_unregister(ucsi->ucsi);
+ spin_lock_irqsave(&ucsi->state_lock, flags);
+ ucsi->pd_running = (state == SERVREG_SERVICE_STATE_UP);
+ spin_unlock_irqrestore(&ucsi->state_lock, flags);
+ schedule_work(&ucsi->register_work);
}
static void pmic_glink_ucsi_destroy(void *data)
@@ -320,6 +336,7 @@ static int pmic_glink_ucsi_probe(struct auxiliary_device *adev,
INIT_WORK(&ucsi->register_work, pmic_glink_ucsi_register);
init_completion(&ucsi->read_ack);
init_completion(&ucsi->write_ack);
+ spin_lock_init(&ucsi->state_lock);
mutex_init(&ucsi->lock);
ucsi->ucsi = ucsi_create(dev, &pmic_glink_ucsi_ops);
@@ -367,12 +384,16 @@ static int pmic_glink_ucsi_probe(struct auxiliary_device *adev,
ucsi->port_orientation[port] = desc;
}
- ucsi->client = devm_pmic_glink_register_client(dev,
- PMIC_GLINK_OWNER_USBC,
- pmic_glink_ucsi_callback,
- pmic_glink_ucsi_pdr_notify,
- ucsi);
- return PTR_ERR_OR_ZERO(ucsi->client);
+ ucsi->client = devm_pmic_glink_client_alloc(dev, PMIC_GLINK_OWNER_USBC,
+ pmic_glink_ucsi_callback,
+ pmic_glink_ucsi_pdr_notify,
+ ucsi);
+ if (IS_ERR(ucsi->client))
+ return PTR_ERR(ucsi->client);
+
+ pmic_glink_client_register(ucsi->client);
+
+ return 0;
}
static void pmic_glink_ucsi_remove(struct auxiliary_device *adev)
diff --git a/drivers/video/aperture.c b/drivers/video/aperture.c
index 561be8f..2b5a1e6 100644
--- a/drivers/video/aperture.c
+++ b/drivers/video/aperture.c
@@ -293,7 +293,7 @@ int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t si
* ask for this, so let's assume that a real driver for the display
* was already probed and prevent sysfb to register devices later.
*/
- sysfb_disable();
+ sysfb_disable(NULL);
aperture_detach_devices(base, size);
@@ -346,15 +346,10 @@ EXPORT_SYMBOL(__aperture_remove_legacy_vga_devices);
*/
int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *name)
{
- bool primary = false;
resource_size_t base, size;
int bar, ret = 0;
- if (pdev == vga_default_device())
- primary = true;
-
- if (primary)
- sysfb_disable();
+ sysfb_disable(&pdev->dev);
for (bar = 0; bar < PCI_STD_NUM_BARS; ++bar) {
if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM))
@@ -370,7 +365,7 @@ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *na
* that consumes the VGA framebuffer I/O range. Remove this
* device as well.
*/
- if (primary)
+ if (pdev == vga_default_device())
ret = __aperture_remove_legacy_vga_devices(pdev);
return ret;
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index a97ceb1..24fdc74 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -75,7 +75,8 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq)
/* if we just extended the file size, any portion not in
* cache won't be on server and is zeroes */
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (subreq->rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
netfs_subreq_terminated(subreq, err ?: total, false);
}
diff --git a/fs/afs/file.c b/fs/afs/file.c
index c3f0c45..ec1be00 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -242,7 +242,8 @@ static void afs_fetch_data_notify(struct afs_operation *op)
req->error = error;
if (subreq) {
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (subreq->rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
netfs_subreq_terminated(subreq, error ?: req->actual_len, false);
req->subreq = NULL;
} else if (req->done) {
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 3acf5e0..a95e776 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -695,13 +695,18 @@ static void afs_setattr_edit_file(struct afs_operation *op)
{
struct afs_vnode_param *vp = &op->file[0];
struct afs_vnode *vnode = vp->vnode;
+ struct inode *inode = &vnode->netfs.inode;
if (op->setattr.attr->ia_valid & ATTR_SIZE) {
loff_t size = op->setattr.attr->ia_size;
- loff_t i_size = op->setattr.old_i_size;
+ loff_t old = op->setattr.old_i_size;
- if (size != i_size) {
- truncate_setsize(&vnode->netfs.inode, size);
+ /* Note: inode->i_size was updated by afs_apply_status() inside
+ * the I/O and callback locks.
+ */
+
+ if (size != old) {
+ truncate_pagecache(inode, size);
netfs_resize_file(&vnode->netfs, size, true);
fscache_resize_cookie(afs_vnode_cache(vnode), size);
}
diff --git a/fs/attr.c b/fs/attr.c
index 825007d..c04d19b 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -487,9 +487,17 @@ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry,
error = security_inode_setattr(idmap, dentry, attr);
if (error)
return error;
- error = try_break_deleg(inode, delegated_inode);
- if (error)
- return error;
+
+ /*
+ * If ATTR_DELEG is set, then these attributes are being set on
+ * behalf of the holder of a write delegation. We want to avoid
+ * breaking the delegation in this case.
+ */
+ if (!(ia_valid & ATTR_DELEG)) {
+ error = try_break_deleg(inode, delegated_inode);
+ if (error)
+ return error;
+ }
if (inode->i_op->setattr)
error = inode->i_op->setattr(idmap, dentry, attr);
diff --git a/fs/backing-file.c b/fs/backing-file.c
index afb5574..8860dac 100644
--- a/fs/backing-file.c
+++ b/fs/backing-file.c
@@ -303,13 +303,16 @@ ssize_t backing_file_splice_write(struct pipe_inode_info *pipe,
if (WARN_ON_ONCE(!(out->f_mode & FMODE_BACKING)))
return -EIO;
+ if (!out->f_op->splice_write)
+ return -EINVAL;
+
ret = file_remove_privs(ctx->user_file);
if (ret)
return ret;
old_cred = override_creds(ctx->cred);
file_start_write(out);
- ret = iter_file_splice_write(pipe, out, ppos, len, flags);
+ ret = out->f_op->splice_write(pipe, out, ppos, len, flags);
file_end_write(out);
revert_creds(old_cred);
diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c
index d9c5a92..ba46f1c 100644
--- a/fs/bcachefs/alloc_background.c
+++ b/fs/bcachefs/alloc_background.c
@@ -196,121 +196,119 @@ static unsigned bch_alloc_v1_val_u64s(const struct bch_alloc *a)
return DIV_ROUND_UP(bytes, sizeof(u64));
}
-int bch2_alloc_v1_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_alloc_v1_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct bkey_s_c_alloc a = bkey_s_c_to_alloc(k);
int ret = 0;
/* allow for unknown fields */
- bkey_fsck_err_on(bkey_val_u64s(a.k) < bch_alloc_v1_val_u64s(a.v), c, err,
- alloc_v1_val_size_bad,
+ bkey_fsck_err_on(bkey_val_u64s(a.k) < bch_alloc_v1_val_u64s(a.v),
+ c, alloc_v1_val_size_bad,
"incorrect value size (%zu < %u)",
bkey_val_u64s(a.k), bch_alloc_v1_val_u64s(a.v));
fsck_err:
return ret;
}
-int bch2_alloc_v2_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_alloc_v2_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct bkey_alloc_unpacked u;
int ret = 0;
- bkey_fsck_err_on(bch2_alloc_unpack_v2(&u, k), c, err,
- alloc_v2_unpack_error,
+ bkey_fsck_err_on(bch2_alloc_unpack_v2(&u, k),
+ c, alloc_v2_unpack_error,
"unpack error");
fsck_err:
return ret;
}
-int bch2_alloc_v3_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_alloc_v3_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct bkey_alloc_unpacked u;
int ret = 0;
- bkey_fsck_err_on(bch2_alloc_unpack_v3(&u, k), c, err,
- alloc_v2_unpack_error,
+ bkey_fsck_err_on(bch2_alloc_unpack_v3(&u, k),
+ c, alloc_v2_unpack_error,
"unpack error");
fsck_err:
return ret;
}
-int bch2_alloc_v4_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags, struct printbuf *err)
+int bch2_alloc_v4_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
- struct bkey_s_c_alloc_v4 a = bkey_s_c_to_alloc_v4(k);
+ struct bch_alloc_v4 a;
int ret = 0;
- bkey_fsck_err_on(alloc_v4_u64s_noerror(a.v) > bkey_val_u64s(k.k), c, err,
- alloc_v4_val_size_bad,
+ bkey_val_copy(&a, bkey_s_c_to_alloc_v4(k));
+
+ bkey_fsck_err_on(alloc_v4_u64s_noerror(&a) > bkey_val_u64s(k.k),
+ c, alloc_v4_val_size_bad,
"bad val size (%u > %zu)",
- alloc_v4_u64s_noerror(a.v), bkey_val_u64s(k.k));
+ alloc_v4_u64s_noerror(&a), bkey_val_u64s(k.k));
- bkey_fsck_err_on(!BCH_ALLOC_V4_BACKPOINTERS_START(a.v) &&
- BCH_ALLOC_V4_NR_BACKPOINTERS(a.v), c, err,
- alloc_v4_backpointers_start_bad,
+ bkey_fsck_err_on(!BCH_ALLOC_V4_BACKPOINTERS_START(&a) &&
+ BCH_ALLOC_V4_NR_BACKPOINTERS(&a),
+ c, alloc_v4_backpointers_start_bad,
"invalid backpointers_start");
- bkey_fsck_err_on(alloc_data_type(*a.v, a.v->data_type) != a.v->data_type, c, err,
- alloc_key_data_type_bad,
+ bkey_fsck_err_on(alloc_data_type(a, a.data_type) != a.data_type,
+ c, alloc_key_data_type_bad,
"invalid data type (got %u should be %u)",
- a.v->data_type, alloc_data_type(*a.v, a.v->data_type));
+ a.data_type, alloc_data_type(a, a.data_type));
for (unsigned i = 0; i < 2; i++)
- bkey_fsck_err_on(a.v->io_time[i] > LRU_TIME_MAX,
- c, err,
- alloc_key_io_time_bad,
+ bkey_fsck_err_on(a.io_time[i] > LRU_TIME_MAX,
+ c, alloc_key_io_time_bad,
"invalid io_time[%s]: %llu, max %llu",
i == READ ? "read" : "write",
- a.v->io_time[i], LRU_TIME_MAX);
+ a.io_time[i], LRU_TIME_MAX);
- unsigned stripe_sectors = BCH_ALLOC_V4_BACKPOINTERS_START(a.v) * sizeof(u64) >
+ unsigned stripe_sectors = BCH_ALLOC_V4_BACKPOINTERS_START(&a) * sizeof(u64) >
offsetof(struct bch_alloc_v4, stripe_sectors)
- ? a.v->stripe_sectors
+ ? a.stripe_sectors
: 0;
- switch (a.v->data_type) {
+ switch (a.data_type) {
case BCH_DATA_free:
case BCH_DATA_need_gc_gens:
case BCH_DATA_need_discard:
bkey_fsck_err_on(stripe_sectors ||
- a.v->dirty_sectors ||
- a.v->cached_sectors ||
- a.v->stripe,
- c, err, alloc_key_empty_but_have_data,
+ a.dirty_sectors ||
+ a.cached_sectors ||
+ a.stripe,
+ c, alloc_key_empty_but_have_data,
"empty data type free but have data %u.%u.%u %u",
stripe_sectors,
- a.v->dirty_sectors,
- a.v->cached_sectors,
- a.v->stripe);
+ a.dirty_sectors,
+ a.cached_sectors,
+ a.stripe);
break;
case BCH_DATA_sb:
case BCH_DATA_journal:
case BCH_DATA_btree:
case BCH_DATA_user:
case BCH_DATA_parity:
- bkey_fsck_err_on(!a.v->dirty_sectors &&
+ bkey_fsck_err_on(!a.dirty_sectors &&
!stripe_sectors,
- c, err, alloc_key_dirty_sectors_0,
+ c, alloc_key_dirty_sectors_0,
"data_type %s but dirty_sectors==0",
- bch2_data_type_str(a.v->data_type));
+ bch2_data_type_str(a.data_type));
break;
case BCH_DATA_cached:
- bkey_fsck_err_on(!a.v->cached_sectors ||
- a.v->dirty_sectors ||
+ bkey_fsck_err_on(!a.cached_sectors ||
+ a.dirty_sectors ||
stripe_sectors ||
- a.v->stripe,
- c, err, alloc_key_cached_inconsistency,
+ a.stripe,
+ c, alloc_key_cached_inconsistency,
"data type inconsistency");
- bkey_fsck_err_on(!a.v->io_time[READ] &&
+ bkey_fsck_err_on(!a.io_time[READ] &&
c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_to_lru_refs,
- c, err, alloc_key_cached_but_read_time_zero,
+ c, alloc_key_cached_but_read_time_zero,
"cached bucket with read_time == 0");
break;
case BCH_DATA_stripe:
@@ -513,14 +511,13 @@ static unsigned alloc_gen(struct bkey_s_c k, unsigned offset)
: 0;
}
-int bch2_bucket_gens_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_bucket_gens_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
int ret = 0;
- bkey_fsck_err_on(bkey_val_bytes(k.k) != sizeof(struct bch_bucket_gens), c, err,
- bucket_gens_val_size_bad,
+ bkey_fsck_err_on(bkey_val_bytes(k.k) != sizeof(struct bch_bucket_gens),
+ c, bucket_gens_val_size_bad,
"bad val size (%zu != %zu)",
bkey_val_bytes(k.k), sizeof(struct bch_bucket_gens));
fsck_err:
@@ -561,7 +558,7 @@ int bch2_bucket_gens_init(struct bch_fs *c)
struct bpos pos = alloc_gens_pos(iter.pos, &offset);
int ret2 = 0;
- if (have_bucket_gens_key && bkey_cmp(iter.pos, pos)) {
+ if (have_bucket_gens_key && !bkey_eq(g.k.p, pos)) {
ret2 = bch2_btree_insert_trans(trans, BTREE_ID_bucket_gens, &g.k_i, 0) ?:
bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc);
if (ret2)
@@ -829,7 +826,19 @@ int bch2_trigger_alloc(struct btree_trans *trans,
struct bch_alloc_v4 old_a_convert;
const struct bch_alloc_v4 *old_a = bch2_alloc_to_v4(old, &old_a_convert);
- struct bch_alloc_v4 *new_a = bkey_s_to_alloc_v4(new).v;
+
+ struct bch_alloc_v4 *new_a;
+ if (likely(new.k->type == KEY_TYPE_alloc_v4)) {
+ new_a = bkey_s_to_alloc_v4(new).v;
+ } else {
+ BUG_ON(!(flags & (BTREE_TRIGGER_gc|BTREE_TRIGGER_check_repair)));
+
+ struct bkey_i_alloc_v4 *new_ka = bch2_alloc_to_v4_mut_inlined(trans, new.s_c);
+ ret = PTR_ERR_OR_ZERO(new_ka);
+ if (unlikely(ret))
+ goto err;
+ new_a = &new_ka->v;
+ }
if (flags & BTREE_TRIGGER_transactional) {
alloc_data_type_set(new_a, new_a->data_type);
@@ -1865,26 +1874,26 @@ static void bch2_do_discards_work(struct work_struct *work)
trace_discard_buckets(c, s.seen, s.open, s.need_journal_commit, s.discarded,
bch2_err_str(ret));
- bch2_write_ref_put(c, BCH_WRITE_REF_discard);
percpu_ref_put(&ca->io_ref);
+ bch2_write_ref_put(c, BCH_WRITE_REF_discard);
}
void bch2_dev_do_discards(struct bch_dev *ca)
{
struct bch_fs *c = ca->fs;
- if (!bch2_dev_get_ioref(c, ca->dev_idx, WRITE))
+ if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_discard))
return;
- if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_discard))
- goto put_ioref;
+ if (!bch2_dev_get_ioref(c, ca->dev_idx, WRITE))
+ goto put_write_ref;
if (queue_work(c->write_ref_wq, &ca->discard_work))
return;
- bch2_write_ref_put(c, BCH_WRITE_REF_discard);
-put_ioref:
percpu_ref_put(&ca->io_ref);
+put_write_ref:
+ bch2_write_ref_put(c, BCH_WRITE_REF_discard);
}
void bch2_do_discards(struct bch_fs *c)
diff --git a/fs/bcachefs/alloc_background.h b/fs/bcachefs/alloc_background.h
index 96a0444..fd790b0 100644
--- a/fs/bcachefs/alloc_background.h
+++ b/fs/bcachefs/alloc_background.h
@@ -150,7 +150,9 @@ static inline void alloc_data_type_set(struct bch_alloc_v4 *a, enum bch_data_typ
static inline u64 alloc_lru_idx_read(struct bch_alloc_v4 a)
{
- return a.data_type == BCH_DATA_cached ? a.io_time[READ] : 0;
+ return a.data_type == BCH_DATA_cached
+ ? a.io_time[READ] & LRU_TIME_MAX
+ : 0;
}
#define DATA_TYPES_MOVABLE \
@@ -240,52 +242,48 @@ struct bkey_i_alloc_v4 *bch2_alloc_to_v4_mut(struct btree_trans *, struct bkey_s
int bch2_bucket_io_time_reset(struct btree_trans *, unsigned, size_t, int);
-int bch2_alloc_v1_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
-int bch2_alloc_v2_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
-int bch2_alloc_v3_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
-int bch2_alloc_v4_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_alloc_v1_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
+int bch2_alloc_v2_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
+int bch2_alloc_v3_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
+int bch2_alloc_v4_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
void bch2_alloc_v4_swab(struct bkey_s);
void bch2_alloc_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
#define bch2_bkey_ops_alloc ((struct bkey_ops) { \
- .key_invalid = bch2_alloc_v1_invalid, \
+ .key_validate = bch2_alloc_v1_validate, \
.val_to_text = bch2_alloc_to_text, \
.trigger = bch2_trigger_alloc, \
.min_val_size = 8, \
})
#define bch2_bkey_ops_alloc_v2 ((struct bkey_ops) { \
- .key_invalid = bch2_alloc_v2_invalid, \
+ .key_validate = bch2_alloc_v2_validate, \
.val_to_text = bch2_alloc_to_text, \
.trigger = bch2_trigger_alloc, \
.min_val_size = 8, \
})
#define bch2_bkey_ops_alloc_v3 ((struct bkey_ops) { \
- .key_invalid = bch2_alloc_v3_invalid, \
+ .key_validate = bch2_alloc_v3_validate, \
.val_to_text = bch2_alloc_to_text, \
.trigger = bch2_trigger_alloc, \
.min_val_size = 16, \
})
#define bch2_bkey_ops_alloc_v4 ((struct bkey_ops) { \
- .key_invalid = bch2_alloc_v4_invalid, \
+ .key_validate = bch2_alloc_v4_validate, \
.val_to_text = bch2_alloc_to_text, \
.swab = bch2_alloc_v4_swab, \
.trigger = bch2_trigger_alloc, \
.min_val_size = 48, \
})
-int bch2_bucket_gens_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_bucket_gens_validate(struct bch_fs *, struct bkey_s_c,
+ enum bch_validate_flags);
void bch2_bucket_gens_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
#define bch2_bkey_ops_bucket_gens ((struct bkey_ops) { \
- .key_invalid = bch2_bucket_gens_invalid, \
+ .key_validate = bch2_bucket_gens_validate, \
.val_to_text = bch2_bucket_gens_to_text, \
})
diff --git a/fs/bcachefs/alloc_background_format.h b/fs/bcachefs/alloc_background_format.h
index 47d9d00..f754a29 100644
--- a/fs/bcachefs/alloc_background_format.h
+++ b/fs/bcachefs/alloc_background_format.h
@@ -69,6 +69,7 @@ struct bch_alloc_v4 {
__u64 io_time[2];
__u32 stripe;
__u32 nr_external_backpointers;
+ /* end of fields in original version of alloc_v4 */
__u64 fragmentation_lru;
__u32 stripe_sectors;
__u32 pad;
diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index 3cc0247..d4da634 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -47,9 +47,8 @@ static bool extent_matches_bp(struct bch_fs *c,
return false;
}
-int bch2_backpointer_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_backpointer_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(k);
@@ -68,8 +67,7 @@ int bch2_backpointer_invalid(struct bch_fs *c, struct bkey_s_c k,
bkey_fsck_err_on((bp.v->bucket_offset >> MAX_EXTENT_COMPRESS_RATIO_SHIFT) >= ca->mi.bucket_size ||
!bpos_eq(bp.k->p, bp_pos),
- c, err,
- backpointer_bucket_offset_wrong,
+ c, backpointer_bucket_offset_wrong,
"backpointer bucket_offset wrong");
fsck_err:
return ret;
@@ -763,27 +761,22 @@ static int bch2_get_btree_in_memory_pos(struct btree_trans *trans,
btree < BTREE_ID_NR && !ret;
btree++) {
unsigned depth = (BIT_ULL(btree) & btree_leaf_mask) ? 0 : 1;
- struct btree_iter iter;
- struct btree *b;
if (!(BIT_ULL(btree) & btree_leaf_mask) &&
!(BIT_ULL(btree) & btree_interior_mask))
continue;
- bch2_trans_begin(trans);
-
- __for_each_btree_node(trans, iter, btree,
+ ret = __for_each_btree_node(trans, iter, btree,
btree == start.btree ? start.pos : POS_MIN,
- 0, depth, BTREE_ITER_prefetch, b, ret) {
+ 0, depth, BTREE_ITER_prefetch, b, ({
mem_may_pin -= btree_buf_bytes(b);
if (mem_may_pin <= 0) {
c->btree_cache.pinned_nodes_end = *end =
BBPOS(btree, b->key.k.p);
- bch2_trans_iter_exit(trans, &iter);
- return 0;
+ break;
}
- }
- bch2_trans_iter_exit(trans, &iter);
+ 0;
+ }));
}
return ret;
diff --git a/fs/bcachefs/backpointers.h b/fs/bcachefs/backpointers.h
index 6021de1..7daecad 100644
--- a/fs/bcachefs/backpointers.h
+++ b/fs/bcachefs/backpointers.h
@@ -18,14 +18,13 @@ static inline u64 swab40(u64 x)
((x & 0xff00000000ULL) >> 32));
}
-int bch2_backpointer_invalid(struct bch_fs *, struct bkey_s_c k,
- enum bch_validate_flags, struct printbuf *);
+int bch2_backpointer_validate(struct bch_fs *, struct bkey_s_c k, enum bch_validate_flags);
void bch2_backpointer_to_text(struct printbuf *, const struct bch_backpointer *);
void bch2_backpointer_k_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
void bch2_backpointer_swab(struct bkey_s);
#define bch2_bkey_ops_backpointer ((struct bkey_ops) { \
- .key_invalid = bch2_backpointer_invalid, \
+ .key_validate = bch2_backpointer_validate, \
.val_to_text = bch2_backpointer_k_to_text, \
.swab = bch2_backpointer_swab, \
.min_val_size = 32, \
diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index eedf2d6..0c7086e 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -447,6 +447,7 @@ BCH_DEBUG_PARAMS_DEBUG()
x(blocked_journal_low_on_space) \
x(blocked_journal_low_on_pin) \
x(blocked_journal_max_in_flight) \
+ x(blocked_key_cache_flush) \
x(blocked_allocate) \
x(blocked_allocate_open_bucket) \
x(blocked_write_buffer_full) \
diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index b25f863..14ce726 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -676,7 +676,9 @@ struct bch_sb_field_ext {
x(mi_btree_bitmap, BCH_VERSION(1, 7)) \
x(bucket_stripe_sectors, BCH_VERSION(1, 8)) \
x(disk_accounting_v2, BCH_VERSION(1, 9)) \
- x(disk_accounting_v3, BCH_VERSION(1, 10))
+ x(disk_accounting_v3, BCH_VERSION(1, 10)) \
+ x(disk_accounting_inum, BCH_VERSION(1, 11)) \
+ x(rebalance_work_acct_fix, BCH_VERSION(1, 12))
enum bcachefs_metadata_version {
bcachefs_metadata_version_min = 9,
diff --git a/fs/bcachefs/bkey.h b/fs/bcachefs/bkey.h
index 9363571..e34cb2b 100644
--- a/fs/bcachefs/bkey.h
+++ b/fs/bcachefs/bkey.h
@@ -10,9 +10,10 @@
#include "vstructs.h"
enum bch_validate_flags {
- BCH_VALIDATE_write = (1U << 0),
- BCH_VALIDATE_commit = (1U << 1),
- BCH_VALIDATE_journal = (1U << 2),
+ BCH_VALIDATE_write = BIT(0),
+ BCH_VALIDATE_commit = BIT(1),
+ BCH_VALIDATE_journal = BIT(2),
+ BCH_VALIDATE_silent = BIT(3),
};
#if 0
diff --git a/fs/bcachefs/bkey_methods.c b/fs/bcachefs/bkey_methods.c
index 5f07cf8..88d8958 100644
--- a/fs/bcachefs/bkey_methods.c
+++ b/fs/bcachefs/bkey_methods.c
@@ -27,27 +27,27 @@ const char * const bch2_bkey_types[] = {
NULL
};
-static int deleted_key_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags, struct printbuf *err)
+static int deleted_key_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
return 0;
}
#define bch2_bkey_ops_deleted ((struct bkey_ops) { \
- .key_invalid = deleted_key_invalid, \
+ .key_validate = deleted_key_validate, \
})
#define bch2_bkey_ops_whiteout ((struct bkey_ops) { \
- .key_invalid = deleted_key_invalid, \
+ .key_validate = deleted_key_validate, \
})
-static int empty_val_key_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags, struct printbuf *err)
+static int empty_val_key_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
int ret = 0;
- bkey_fsck_err_on(bkey_val_bytes(k.k), c, err,
- bkey_val_size_nonzero,
+ bkey_fsck_err_on(bkey_val_bytes(k.k),
+ c, bkey_val_size_nonzero,
"incorrect value size (%zu != 0)",
bkey_val_bytes(k.k));
fsck_err:
@@ -55,11 +55,11 @@ static int empty_val_key_invalid(struct bch_fs *c, struct bkey_s_c k,
}
#define bch2_bkey_ops_error ((struct bkey_ops) { \
- .key_invalid = empty_val_key_invalid, \
+ .key_validate = empty_val_key_validate, \
})
-static int key_type_cookie_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags, struct printbuf *err)
+static int key_type_cookie_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
return 0;
}
@@ -73,17 +73,17 @@ static void key_type_cookie_to_text(struct printbuf *out, struct bch_fs *c,
}
#define bch2_bkey_ops_cookie ((struct bkey_ops) { \
- .key_invalid = key_type_cookie_invalid, \
+ .key_validate = key_type_cookie_validate, \
.val_to_text = key_type_cookie_to_text, \
.min_val_size = 8, \
})
#define bch2_bkey_ops_hash_whiteout ((struct bkey_ops) {\
- .key_invalid = empty_val_key_invalid, \
+ .key_validate = empty_val_key_validate, \
})
-static int key_type_inline_data_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags, struct printbuf *err)
+static int key_type_inline_data_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
return 0;
}
@@ -98,9 +98,9 @@ static void key_type_inline_data_to_text(struct printbuf *out, struct bch_fs *c,
datalen, min(datalen, 32U), d.v->data);
}
-#define bch2_bkey_ops_inline_data ((struct bkey_ops) { \
- .key_invalid = key_type_inline_data_invalid, \
- .val_to_text = key_type_inline_data_to_text, \
+#define bch2_bkey_ops_inline_data ((struct bkey_ops) { \
+ .key_validate = key_type_inline_data_validate, \
+ .val_to_text = key_type_inline_data_to_text, \
})
static bool key_type_set_merge(struct bch_fs *c, struct bkey_s l, struct bkey_s_c r)
@@ -110,7 +110,7 @@ static bool key_type_set_merge(struct bch_fs *c, struct bkey_s l, struct bkey_s_
}
#define bch2_bkey_ops_set ((struct bkey_ops) { \
- .key_invalid = empty_val_key_invalid, \
+ .key_validate = empty_val_key_validate, \
.key_merge = key_type_set_merge, \
})
@@ -123,9 +123,8 @@ const struct bkey_ops bch2_bkey_ops[] = {
const struct bkey_ops bch2_bkey_null_ops = {
};
-int bch2_bkey_val_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_bkey_val_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
if (test_bit(BCH_FS_no_invalid_checks, &c->flags))
return 0;
@@ -133,15 +132,15 @@ int bch2_bkey_val_invalid(struct bch_fs *c, struct bkey_s_c k,
const struct bkey_ops *ops = bch2_bkey_type_ops(k.k->type);
int ret = 0;
- bkey_fsck_err_on(bkey_val_bytes(k.k) < ops->min_val_size, c, err,
- bkey_val_size_too_small,
+ bkey_fsck_err_on(bkey_val_bytes(k.k) < ops->min_val_size,
+ c, bkey_val_size_too_small,
"bad val size (%zu < %u)",
bkey_val_bytes(k.k), ops->min_val_size);
- if (!ops->key_invalid)
+ if (!ops->key_validate)
return 0;
- ret = ops->key_invalid(c, k, flags, err);
+ ret = ops->key_validate(c, k, flags);
fsck_err:
return ret;
}
@@ -161,18 +160,17 @@ const char *bch2_btree_node_type_str(enum btree_node_type type)
return type == BKEY_TYPE_btree ? "internal btree node" : bch2_btree_id_str(type - 1);
}
-int __bch2_bkey_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum btree_node_type type,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int __bch2_bkey_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum btree_node_type type,
+ enum bch_validate_flags flags)
{
if (test_bit(BCH_FS_no_invalid_checks, &c->flags))
return 0;
int ret = 0;
- bkey_fsck_err_on(k.k->u64s < BKEY_U64s, c, err,
- bkey_u64s_too_small,
+ bkey_fsck_err_on(k.k->u64s < BKEY_U64s,
+ c, bkey_u64s_too_small,
"u64s too small (%u < %zu)", k.k->u64s, BKEY_U64s);
if (type >= BKEY_TYPE_NR)
@@ -180,8 +178,8 @@ int __bch2_bkey_invalid(struct bch_fs *c, struct bkey_s_c k,
bkey_fsck_err_on(k.k->type < KEY_TYPE_MAX &&
(type == BKEY_TYPE_btree || (flags & BCH_VALIDATE_commit)) &&
- !(bch2_key_types_allowed[type] & BIT_ULL(k.k->type)), c, err,
- bkey_invalid_type_for_btree,
+ !(bch2_key_types_allowed[type] & BIT_ULL(k.k->type)),
+ c, bkey_invalid_type_for_btree,
"invalid key type for btree %s (%s)",
bch2_btree_node_type_str(type),
k.k->type < KEY_TYPE_MAX
@@ -189,17 +187,17 @@ int __bch2_bkey_invalid(struct bch_fs *c, struct bkey_s_c k,
: "(unknown)");
if (btree_node_type_is_extents(type) && !bkey_whiteout(k.k)) {
- bkey_fsck_err_on(k.k->size == 0, c, err,
- bkey_extent_size_zero,
+ bkey_fsck_err_on(k.k->size == 0,
+ c, bkey_extent_size_zero,
"size == 0");
- bkey_fsck_err_on(k.k->size > k.k->p.offset, c, err,
- bkey_extent_size_greater_than_offset,
+ bkey_fsck_err_on(k.k->size > k.k->p.offset,
+ c, bkey_extent_size_greater_than_offset,
"size greater than offset (%u > %llu)",
k.k->size, k.k->p.offset);
} else {
- bkey_fsck_err_on(k.k->size, c, err,
- bkey_size_nonzero,
+ bkey_fsck_err_on(k.k->size,
+ c, bkey_size_nonzero,
"size != 0");
}
@@ -207,12 +205,12 @@ int __bch2_bkey_invalid(struct bch_fs *c, struct bkey_s_c k,
enum btree_id btree = type - 1;
if (btree_type_has_snapshots(btree)) {
- bkey_fsck_err_on(!k.k->p.snapshot, c, err,
- bkey_snapshot_zero,
+ bkey_fsck_err_on(!k.k->p.snapshot,
+ c, bkey_snapshot_zero,
"snapshot == 0");
} else if (!btree_type_has_snapshot_field(btree)) {
- bkey_fsck_err_on(k.k->p.snapshot, c, err,
- bkey_snapshot_nonzero,
+ bkey_fsck_err_on(k.k->p.snapshot,
+ c, bkey_snapshot_nonzero,
"nonzero snapshot");
} else {
/*
@@ -221,34 +219,33 @@ int __bch2_bkey_invalid(struct bch_fs *c, struct bkey_s_c k,
*/
}
- bkey_fsck_err_on(bkey_eq(k.k->p, POS_MAX), c, err,
- bkey_at_pos_max,
+ bkey_fsck_err_on(bkey_eq(k.k->p, POS_MAX),
+ c, bkey_at_pos_max,
"key at POS_MAX");
}
fsck_err:
return ret;
}
-int bch2_bkey_invalid(struct bch_fs *c, struct bkey_s_c k,
+int bch2_bkey_validate(struct bch_fs *c, struct bkey_s_c k,
enum btree_node_type type,
- enum bch_validate_flags flags,
- struct printbuf *err)
+ enum bch_validate_flags flags)
{
- return __bch2_bkey_invalid(c, k, type, flags, err) ?:
- bch2_bkey_val_invalid(c, k, flags, err);
+ return __bch2_bkey_validate(c, k, type, flags) ?:
+ bch2_bkey_val_validate(c, k, flags);
}
int bch2_bkey_in_btree_node(struct bch_fs *c, struct btree *b,
- struct bkey_s_c k, struct printbuf *err)
+ struct bkey_s_c k, enum bch_validate_flags flags)
{
int ret = 0;
- bkey_fsck_err_on(bpos_lt(k.k->p, b->data->min_key), c, err,
- bkey_before_start_of_btree_node,
+ bkey_fsck_err_on(bpos_lt(k.k->p, b->data->min_key),
+ c, bkey_before_start_of_btree_node,
"key before start of btree node");
- bkey_fsck_err_on(bpos_gt(k.k->p, b->data->max_key), c, err,
- bkey_after_end_of_btree_node,
+ bkey_fsck_err_on(bpos_gt(k.k->p, b->data->max_key),
+ c, bkey_after_end_of_btree_node,
"key past end of btree node");
fsck_err:
return ret;
diff --git a/fs/bcachefs/bkey_methods.h b/fs/bcachefs/bkey_methods.h
index baef072..3df3dd2 100644
--- a/fs/bcachefs/bkey_methods.h
+++ b/fs/bcachefs/bkey_methods.h
@@ -14,15 +14,15 @@ extern const char * const bch2_bkey_types[];
extern const struct bkey_ops bch2_bkey_null_ops;
/*
- * key_invalid: checks validity of @k, returns 0 if good or -EINVAL if bad. If
+ * key_validate: checks validity of @k, returns 0 if good or -EINVAL if bad. If
* invalid, entire key will be deleted.
*
* When invalid, error string is returned via @err. @rw indicates whether key is
* being read or written; more aggressive checks can be enabled when rw == WRITE.
*/
struct bkey_ops {
- int (*key_invalid)(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags, struct printbuf *err);
+ int (*key_validate)(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags);
void (*val_to_text)(struct printbuf *, struct bch_fs *,
struct bkey_s_c);
void (*swab)(struct bkey_s);
@@ -48,14 +48,13 @@ static inline const struct bkey_ops *bch2_bkey_type_ops(enum bch_bkey_type type)
: &bch2_bkey_null_ops;
}
-int bch2_bkey_val_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
-int __bch2_bkey_invalid(struct bch_fs *, struct bkey_s_c, enum btree_node_type,
- enum bch_validate_flags, struct printbuf *);
-int bch2_bkey_invalid(struct bch_fs *, struct bkey_s_c, enum btree_node_type,
- enum bch_validate_flags, struct printbuf *);
-int bch2_bkey_in_btree_node(struct bch_fs *, struct btree *,
- struct bkey_s_c, struct printbuf *);
+int bch2_bkey_val_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
+int __bch2_bkey_validate(struct bch_fs *, struct bkey_s_c, enum btree_node_type,
+ enum bch_validate_flags);
+int bch2_bkey_validate(struct bch_fs *, struct bkey_s_c, enum btree_node_type,
+ enum bch_validate_flags);
+int bch2_bkey_in_btree_node(struct bch_fs *, struct btree *, struct bkey_s_c,
+ enum bch_validate_flags);
void bch2_bpos_to_text(struct printbuf *, struct bpos);
void bch2_bkey_to_text(struct printbuf *, const struct bkey *);
diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c
index f5d85b5..e52a06d 100644
--- a/fs/bcachefs/btree_cache.c
+++ b/fs/bcachefs/btree_cache.c
@@ -159,6 +159,16 @@ struct btree *__bch2_btree_node_mem_alloc(struct bch_fs *c)
return b;
}
+void bch2_btree_node_to_freelist(struct bch_fs *c, struct btree *b)
+{
+ mutex_lock(&c->btree_cache.lock);
+ list_move(&b->list, &c->btree_cache.freeable);
+ mutex_unlock(&c->btree_cache.lock);
+
+ six_unlock_write(&b->c.lock);
+ six_unlock_intent(&b->c.lock);
+}
+
/* Btree in memory cache - hash table */
void bch2_btree_node_hash_remove(struct btree_cache *bc, struct btree *b)
@@ -736,6 +746,13 @@ struct btree *bch2_btree_node_mem_alloc(struct btree_trans *trans, bool pcpu_rea
start_time);
memalloc_nofs_restore(flags);
+
+ int ret = bch2_trans_relock(trans);
+ if (unlikely(ret)) {
+ bch2_btree_node_to_freelist(c, b);
+ return ERR_PTR(ret);
+ }
+
return b;
err:
mutex_lock(&bc->lock);
@@ -856,6 +873,10 @@ static noinline struct btree *bch2_btree_node_fill(struct btree_trans *trans,
bch2_btree_node_read(trans, b, sync);
+ int ret = bch2_trans_relock(trans);
+ if (ret)
+ return ERR_PTR(ret);
+
if (!sync)
return NULL;
@@ -974,6 +995,10 @@ static struct btree *__bch2_btree_node_get(struct btree_trans *trans, struct btr
bch2_btree_node_wait_on_read(b);
+ ret = bch2_trans_relock(trans);
+ if (ret)
+ return ERR_PTR(ret);
+
/*
* should_be_locked is not set on this path yet, so we need to
* relock it specifically:
diff --git a/fs/bcachefs/btree_cache.h b/fs/bcachefs/btree_cache.h
index c0eb87a0..f820640 100644
--- a/fs/bcachefs/btree_cache.h
+++ b/fs/bcachefs/btree_cache.h
@@ -12,6 +12,8 @@ struct btree_iter;
void bch2_recalc_btree_reserve(struct bch_fs *);
+void bch2_btree_node_to_freelist(struct bch_fs *, struct btree *);
+
void bch2_btree_node_hash_remove(struct btree_cache *, struct btree *);
int __bch2_btree_node_hash_insert(struct btree_cache *, struct btree *);
int bch2_btree_node_hash_insert(struct btree_cache *, struct btree *,
diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 6cbf2aa..eb3002c 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -741,12 +741,9 @@ static int bch2_gc_btrees(struct bch_fs *c)
static int bch2_mark_superblocks(struct bch_fs *c)
{
- mutex_lock(&c->sb_lock);
gc_pos_set(c, gc_phase(GC_PHASE_sb));
- int ret = bch2_trans_mark_dev_sbs_flags(c, BTREE_TRIGGER_gc);
- mutex_unlock(&c->sb_lock);
- return ret;
+ return bch2_trans_mark_dev_sbs_flags(c, BTREE_TRIGGER_gc);
}
static void bch2_gc_free(struct bch_fs *c)
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 2c42443..56ea9a7 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -836,14 +836,13 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
return ret;
}
-static int bset_key_invalid(struct bch_fs *c, struct btree *b,
- struct bkey_s_c k,
- bool updated_range, int rw,
- struct printbuf *err)
+static int bset_key_validate(struct bch_fs *c, struct btree *b,
+ struct bkey_s_c k,
+ bool updated_range, int rw)
{
- return __bch2_bkey_invalid(c, k, btree_node_type(b), READ, err) ?:
- (!updated_range ? bch2_bkey_in_btree_node(c, b, k, err) : 0) ?:
- (rw == WRITE ? bch2_bkey_val_invalid(c, k, READ, err) : 0);
+ return __bch2_bkey_validate(c, k, btree_node_type(b), 0) ?:
+ (!updated_range ? bch2_bkey_in_btree_node(c, b, k, 0) : 0) ?:
+ (rw == WRITE ? bch2_bkey_val_validate(c, k, 0) : 0);
}
static bool bkey_packed_valid(struct bch_fs *c, struct btree *b,
@@ -858,12 +857,9 @@ static bool bkey_packed_valid(struct bch_fs *c, struct btree *b,
if (!bkeyp_u64s_valid(&b->format, k))
return false;
- struct printbuf buf = PRINTBUF;
struct bkey tmp;
struct bkey_s u = __bkey_disassemble(b, k, &tmp);
- bool ret = __bch2_bkey_invalid(c, u.s_c, btree_node_type(b), READ, &buf);
- printbuf_exit(&buf);
- return ret;
+ return !__bch2_bkey_validate(c, u.s_c, btree_node_type(b), BCH_VALIDATE_silent);
}
static int validate_bset_keys(struct bch_fs *c, struct btree *b,
@@ -915,19 +911,11 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b,
u = __bkey_disassemble(b, k, &tmp);
- printbuf_reset(&buf);
- if (bset_key_invalid(c, b, u.s_c, updated_range, write, &buf)) {
- printbuf_reset(&buf);
- bset_key_invalid(c, b, u.s_c, updated_range, write, &buf);
- prt_printf(&buf, "\n ");
- bch2_bkey_val_to_text(&buf, c, u.s_c);
-
- btree_err(-BCH_ERR_btree_node_read_err_fixable,
- c, NULL, b, i, k,
- btree_node_bad_bkey,
- "invalid bkey: %s", buf.buf);
+ ret = bset_key_validate(c, b, u.s_c, updated_range, write);
+ if (ret == -BCH_ERR_fsck_delete_bkey)
goto drop_this_key;
- }
+ if (ret)
+ goto fsck_err;
if (write)
bch2_bkey_compat(b->c.level, b->c.btree_id, version,
@@ -1228,23 +1216,10 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
struct bkey tmp;
struct bkey_s u = __bkey_disassemble(b, k, &tmp);
- printbuf_reset(&buf);
-
- if (bch2_bkey_val_invalid(c, u.s_c, READ, &buf) ||
+ ret = bch2_bkey_val_validate(c, u.s_c, READ);
+ if (ret == -BCH_ERR_fsck_delete_bkey ||
(bch2_inject_invalid_keys &&
!bversion_cmp(u.k->version, MAX_VERSION))) {
- printbuf_reset(&buf);
-
- prt_printf(&buf, "invalid bkey: ");
- bch2_bkey_val_invalid(c, u.s_c, READ, &buf);
- prt_printf(&buf, "\n ");
- bch2_bkey_val_to_text(&buf, c, u.s_c);
-
- btree_err(-BCH_ERR_btree_node_read_err_fixable,
- c, NULL, b, i, k,
- btree_node_bad_bkey,
- "%s", buf.buf);
-
btree_keys_account_key_drop(&b->nr, 0, k);
i->u64s = cpu_to_le16(le16_to_cpu(i->u64s) - k->u64s);
@@ -1253,6 +1228,8 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
set_btree_bset_end(b, b->set);
continue;
}
+ if (ret)
+ goto fsck_err;
if (u.k->type == KEY_TYPE_btree_ptr_v2) {
struct bkey_s_btree_ptr_v2 bp = bkey_s_to_btree_ptr_v2(u);
@@ -1767,6 +1744,8 @@ static int __bch2_btree_root_read(struct btree_trans *trans, enum btree_id id,
set_btree_node_read_in_flight(b);
+ /* we can't pass the trans to read_done() for fsck errors, so it must be unlocked */
+ bch2_trans_unlock(trans);
bch2_btree_node_read(trans, b, true);
if (btree_node_read_error(b)) {
@@ -1952,18 +1931,14 @@ static void btree_node_write_endio(struct bio *bio)
static int validate_bset_for_write(struct bch_fs *c, struct btree *b,
struct bset *i, unsigned sectors)
{
- struct printbuf buf = PRINTBUF;
bool saw_error;
- int ret;
- ret = bch2_bkey_invalid(c, bkey_i_to_s_c(&b->key),
- BKEY_TYPE_btree, WRITE, &buf);
-
- if (ret)
- bch2_fs_inconsistent(c, "invalid btree node key before write: %s", buf.buf);
- printbuf_exit(&buf);
- if (ret)
+ int ret = bch2_bkey_validate(c, bkey_i_to_s_c(&b->key),
+ BKEY_TYPE_btree, WRITE);
+ if (ret) {
+ bch2_fs_inconsistent(c, "invalid btree node key before write");
return ret;
+ }
ret = validate_bset_keys(c, b, i, WRITE, false, &saw_error) ?:
validate_bset(c, NULL, b, i, b->written, sectors, WRITE, false, &saw_error);
diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index aa8a049..2e84d22 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -1900,6 +1900,7 @@ struct btree *bch2_btree_iter_peek_node(struct btree_iter *iter)
goto out;
}
+/* Only kept for -tools */
struct btree *bch2_btree_iter_peek_node_and_restart(struct btree_iter *iter)
{
struct btree *b;
diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h
index c772586..222b7ce 100644
--- a/fs/bcachefs/btree_iter.h
+++ b/fs/bcachefs/btree_iter.h
@@ -569,6 +569,15 @@ static inline struct bkey_s_c bch2_bkey_get_iter(struct btree_trans *trans,
bkey_s_c_to_##_type(__bch2_bkey_get_iter(_trans, _iter, \
_btree_id, _pos, _flags, KEY_TYPE_##_type))
+#define bkey_val_copy(_dst_v, _src_k) \
+do { \
+ unsigned b = min_t(unsigned, sizeof(*_dst_v), \
+ bkey_val_bytes(_src_k.k)); \
+ memcpy(_dst_v, _src_k.v, b); \
+ if (b < sizeof(*_dst_v)) \
+ memset((void *) (_dst_v) + b, 0, sizeof(*_dst_v) - b); \
+} while (0)
+
static inline int __bch2_bkey_get_val_typed(struct btree_trans *trans,
unsigned btree_id, struct bpos pos,
unsigned flags, unsigned type,
@@ -600,23 +609,35 @@ void bch2_trans_srcu_unlock(struct btree_trans *);
u32 bch2_trans_begin(struct btree_trans *);
-/*
- * XXX
- * this does not handle transaction restarts from bch2_btree_iter_next_node()
- * correctly
- */
-#define __for_each_btree_node(_trans, _iter, _btree_id, _start, \
- _locks_want, _depth, _flags, _b, _ret) \
- for (bch2_trans_node_iter_init((_trans), &(_iter), (_btree_id), \
- _start, _locks_want, _depth, _flags); \
- (_b) = bch2_btree_iter_peek_node_and_restart(&(_iter)), \
- !((_ret) = PTR_ERR_OR_ZERO(_b)) && (_b); \
- (_b) = bch2_btree_iter_next_node(&(_iter)))
+#define __for_each_btree_node(_trans, _iter, _btree_id, _start, \
+ _locks_want, _depth, _flags, _b, _do) \
+({ \
+ bch2_trans_begin((_trans)); \
+ \
+ struct btree_iter _iter; \
+ bch2_trans_node_iter_init((_trans), &_iter, (_btree_id), \
+ _start, _locks_want, _depth, _flags); \
+ int _ret3 = 0; \
+ do { \
+ _ret3 = lockrestart_do((_trans), ({ \
+ struct btree *_b = bch2_btree_iter_peek_node(&_iter); \
+ if (!_b) \
+ break; \
+ \
+ PTR_ERR_OR_ZERO(_b) ?: (_do); \
+ })) ?: \
+ lockrestart_do((_trans), \
+ PTR_ERR_OR_ZERO(bch2_btree_iter_next_node(&_iter))); \
+ } while (!_ret3); \
+ \
+ bch2_trans_iter_exit((_trans), &(_iter)); \
+ _ret3; \
+})
#define for_each_btree_node(_trans, _iter, _btree_id, _start, \
- _flags, _b, _ret) \
- __for_each_btree_node(_trans, _iter, _btree_id, _start, \
- 0, 0, _flags, _b, _ret)
+ _flags, _b, _do) \
+ __for_each_btree_node(_trans, _iter, _btree_id, _start, \
+ 0, 0, _flags, _b, _do)
static inline struct bkey_s_c bch2_btree_iter_peek_prev_type(struct btree_iter *iter,
unsigned flags)
diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c
index f2f2e52..fda7998 100644
--- a/fs/bcachefs/btree_key_cache.c
+++ b/fs/bcachefs/btree_key_cache.c
@@ -497,11 +497,6 @@ int bch2_btree_path_traverse_cached(struct btree_trans *trans, struct btree_path
path->l[1].b = NULL;
- if (bch2_btree_node_relock_notrace(trans, path, 0)) {
- path->uptodate = BTREE_ITER_UPTODATE;
- return 0;
- }
-
int ret;
do {
ret = btree_path_traverse_cached_fast(trans, path);
@@ -731,6 +726,7 @@ void bch2_btree_key_cache_drop(struct btree_trans *trans,
mark_btree_node_locked(trans, path, 0, BTREE_NODE_UNLOCKED);
btree_path_set_dirty(path, BTREE_ITER_NEED_TRAVERSE);
+ path->should_be_locked = false;
}
static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink,
@@ -782,6 +778,20 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink,
rcu_read_lock();
tbl = rht_dereference_rcu(bc->table.tbl, &bc->table);
+
+ /*
+ * Scanning is expensive while a rehash is in progress - most elements
+ * will be on the new hashtable, if it's in progress
+ *
+ * A rehash could still start while we're scanning - that's ok, we'll
+ * still see most elements.
+ */
+ if (unlikely(tbl->nest)) {
+ rcu_read_unlock();
+ srcu_read_unlock(&c->btree_trans_barrier, srcu_idx);
+ return SHRINK_STOP;
+ }
+
if (bc->shrink_iter >= tbl->size)
bc->shrink_iter = 0;
start = bc->shrink_iter;
@@ -789,7 +799,7 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink,
do {
struct rhash_head *pos, *next;
- pos = rht_ptr_rcu(rht_bucket(tbl, bc->shrink_iter));
+ pos = rht_ptr_rcu(&tbl->buckets[bc->shrink_iter]);
while (!rht_is_a_nulls(pos)) {
next = rht_dereference_bucket_rcu(pos->next, tbl, bc->shrink_iter);
@@ -870,12 +880,22 @@ void bch2_fs_btree_key_cache_exit(struct btree_key_cache *bc)
while (atomic_long_read(&bc->nr_keys)) {
rcu_read_lock();
tbl = rht_dereference_rcu(bc->table.tbl, &bc->table);
- if (tbl)
+ if (tbl) {
+ if (tbl->nest) {
+ /* wait for in progress rehash */
+ rcu_read_unlock();
+ mutex_lock(&bc->table.mutex);
+ mutex_unlock(&bc->table.mutex);
+ rcu_read_lock();
+ continue;
+ }
for (i = 0; i < tbl->size; i++)
- rht_for_each_entry_rcu(ck, pos, tbl, i, hash) {
+ while (pos = rht_ptr_rcu(&tbl->buckets[i]), !rht_is_a_nulls(pos)) {
+ ck = container_of(pos, struct bkey_cached, hash);
bkey_cached_evict(bc, ck);
list_add(&ck->list, &items);
}
+ }
rcu_read_unlock();
}
diff --git a/fs/bcachefs/btree_key_cache.h b/fs/bcachefs/btree_key_cache.h
index e6b2cd0..51d6289 100644
--- a/fs/bcachefs/btree_key_cache.h
+++ b/fs/bcachefs/btree_key_cache.h
@@ -11,13 +11,27 @@ static inline size_t bch2_nr_btree_keys_need_flush(struct bch_fs *c)
return max_t(ssize_t, 0, nr_dirty - max_dirty);
}
-static inline bool bch2_btree_key_cache_must_wait(struct bch_fs *c)
+static inline ssize_t __bch2_btree_key_cache_must_wait(struct bch_fs *c)
{
size_t nr_dirty = atomic_long_read(&c->btree_key_cache.nr_dirty);
size_t nr_keys = atomic_long_read(&c->btree_key_cache.nr_keys);
size_t max_dirty = 4096 + (nr_keys * 3) / 4;
- return nr_dirty > max_dirty;
+ return nr_dirty - max_dirty;
+}
+
+static inline bool bch2_btree_key_cache_must_wait(struct bch_fs *c)
+{
+ return __bch2_btree_key_cache_must_wait(c) > 0;
+}
+
+static inline bool bch2_btree_key_cache_wait_done(struct bch_fs *c)
+{
+ size_t nr_dirty = atomic_long_read(&c->btree_key_cache.nr_dirty);
+ size_t nr_keys = atomic_long_read(&c->btree_key_cache.nr_keys);
+ size_t max_dirty = 2048 + (nr_keys * 5) / 8;
+
+ return nr_dirty <= max_dirty;
}
int bch2_btree_key_cache_journal_flush(struct journal *,
diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c
index 0011072..b28c649 100644
--- a/fs/bcachefs/btree_node_scan.c
+++ b/fs/bcachefs/btree_node_scan.c
@@ -530,7 +530,7 @@ int bch2_get_scanned_nodes(struct bch_fs *c, enum btree_id btree,
bch_verbose(c, "%s(): recovering %s", __func__, buf.buf);
printbuf_exit(&buf);
- BUG_ON(bch2_bkey_invalid(c, bkey_i_to_s_c(&tmp.k), BKEY_TYPE_btree, 0, NULL));
+ BUG_ON(bch2_bkey_validate(c, bkey_i_to_s_c(&tmp.k), BKEY_TYPE_btree, 0));
ret = bch2_journal_key_insert(c, btree, level + 1, &tmp.k);
if (ret)
diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index cca336f..a0101d9 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -712,7 +712,7 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
a->k.version = journal_pos_to_bversion(&trans->journal_res,
(u64 *) entry - (u64 *) trans->journal_entries);
BUG_ON(bversion_zero(a->k.version));
- ret = bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), false);
+ ret = bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), false, false);
if (ret)
goto revert_fs_usage;
}
@@ -798,7 +798,7 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
struct bkey_s_accounting a = bkey_i_to_s_accounting(entry2->start);
bch2_accounting_neg(a);
- bch2_accounting_mem_mod_locked(trans, a.c, false);
+ bch2_accounting_mem_mod_locked(trans, a.c, false, false);
bch2_accounting_neg(a);
}
percpu_up_read(&c->mark_lock);
@@ -818,50 +818,6 @@ static noinline void bch2_drop_overwrites_from_journal(struct btree_trans *trans
bch2_journal_key_overwritten(trans->c, i->btree_id, i->level, i->k->k.p);
}
-static noinline int bch2_trans_commit_bkey_invalid(struct btree_trans *trans,
- enum bch_validate_flags flags,
- struct btree_insert_entry *i,
- struct printbuf *err)
-{
- struct bch_fs *c = trans->c;
-
- printbuf_reset(err);
- prt_printf(err, "invalid bkey on insert from %s -> %ps\n",
- trans->fn, (void *) i->ip_allocated);
- printbuf_indent_add(err, 2);
-
- bch2_bkey_val_to_text(err, c, bkey_i_to_s_c(i->k));
- prt_newline(err);
-
- bch2_bkey_invalid(c, bkey_i_to_s_c(i->k), i->bkey_type, flags, err);
- bch2_print_string_as_lines(KERN_ERR, err->buf);
-
- bch2_inconsistent_error(c);
- bch2_dump_trans_updates(trans);
-
- return -EINVAL;
-}
-
-static noinline int bch2_trans_commit_journal_entry_invalid(struct btree_trans *trans,
- struct jset_entry *i)
-{
- struct bch_fs *c = trans->c;
- struct printbuf buf = PRINTBUF;
-
- prt_printf(&buf, "invalid bkey on insert from %s\n", trans->fn);
- printbuf_indent_add(&buf, 2);
-
- bch2_journal_entry_to_text(&buf, c, i);
- prt_newline(&buf);
-
- bch2_print_string_as_lines(KERN_ERR, buf.buf);
-
- bch2_inconsistent_error(c);
- bch2_dump_trans_updates(trans);
-
- return -EINVAL;
-}
-
static int bch2_trans_commit_journal_pin_flush(struct journal *j,
struct journal_entry_pin *_pin, u64 seq)
{
@@ -927,7 +883,7 @@ static inline int do_bch2_trans_commit(struct btree_trans *trans, unsigned flags
static int journal_reclaim_wait_done(struct bch_fs *c)
{
int ret = bch2_journal_error(&c->journal) ?:
- !bch2_btree_key_cache_must_wait(c);
+ bch2_btree_key_cache_wait_done(c);
if (!ret)
journal_reclaim_kick(&c->journal);
@@ -973,9 +929,13 @@ int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags,
bch2_trans_unlock(trans);
trace_and_count(c, trans_blocked_journal_reclaim, trans, trace_ip);
+ track_event_change(&c->times[BCH_TIME_blocked_key_cache_flush], true);
wait_event_freezable(c->journal.reclaim_wait,
(ret = journal_reclaim_wait_done(c)));
+
+ track_event_change(&c->times[BCH_TIME_blocked_key_cache_flush], false);
+
if (ret < 0)
break;
@@ -1060,20 +1020,19 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
goto out_reset;
trans_for_each_update(trans, i) {
- struct printbuf buf = PRINTBUF;
enum bch_validate_flags invalid_flags = 0;
if (!(flags & BCH_TRANS_COMMIT_no_journal_res))
invalid_flags |= BCH_VALIDATE_write|BCH_VALIDATE_commit;
- if (unlikely(bch2_bkey_invalid(c, bkey_i_to_s_c(i->k),
- i->bkey_type, invalid_flags, &buf)))
- ret = bch2_trans_commit_bkey_invalid(trans, invalid_flags, i, &buf);
- btree_insert_entry_checks(trans, i);
- printbuf_exit(&buf);
-
- if (ret)
+ ret = bch2_bkey_validate(c, bkey_i_to_s_c(i->k),
+ i->bkey_type, invalid_flags);
+ if (unlikely(ret)){
+ bch2_trans_inconsistent(trans, "invalid bkey on insert from %s -> %ps\n",
+ trans->fn, (void *) i->ip_allocated);
return ret;
+ }
+ btree_insert_entry_checks(trans, i);
}
for (struct jset_entry *i = trans->journal_entries;
@@ -1084,13 +1043,14 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
if (!(flags & BCH_TRANS_COMMIT_no_journal_res))
invalid_flags |= BCH_VALIDATE_write|BCH_VALIDATE_commit;
- if (unlikely(bch2_journal_entry_validate(c, NULL, i,
- bcachefs_metadata_version_current,
- CPU_BIG_ENDIAN, invalid_flags)))
- ret = bch2_trans_commit_journal_entry_invalid(trans, i);
-
- if (ret)
+ ret = bch2_journal_entry_validate(c, NULL, i,
+ bcachefs_metadata_version_current,
+ CPU_BIG_ENDIAN, invalid_flags);
+ if (unlikely(ret)) {
+ bch2_trans_inconsistent(trans, "invalid journal entry on insert from %s\n",
+ trans->fn);
return ret;
+ }
}
if (unlikely(!test_bit(BCH_FS_may_go_rw, &c->flags))) {
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index e61f969..8fd1120 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -317,6 +317,12 @@ static struct btree *__bch2_btree_node_alloc(struct btree_trans *trans,
: 0;
int ret;
+ b = bch2_btree_node_mem_alloc(trans, interior_node);
+ if (IS_ERR(b))
+ return b;
+
+ BUG_ON(b->ob.nr);
+
mutex_lock(&c->btree_reserve_cache_lock);
if (c->btree_reserve_cache_nr > nr_reserve) {
struct btree_alloc *a =
@@ -325,10 +331,9 @@ static struct btree *__bch2_btree_node_alloc(struct btree_trans *trans,
obs = a->ob;
bkey_copy(&tmp.k, &a->k);
mutex_unlock(&c->btree_reserve_cache_lock);
- goto mem_alloc;
+ goto out;
}
mutex_unlock(&c->btree_reserve_cache_lock);
-
retry:
ret = bch2_alloc_sectors_start_trans(trans,
c->opts.metadata_target ?:
@@ -341,7 +346,7 @@ static struct btree *__bch2_btree_node_alloc(struct btree_trans *trans,
c->opts.metadata_replicas_required),
watermark, 0, cl, &wp);
if (unlikely(ret))
- return ERR_PTR(ret);
+ goto err;
if (wp->sectors_free < btree_sectors(c)) {
struct open_bucket *ob;
@@ -360,19 +365,16 @@ static struct btree *__bch2_btree_node_alloc(struct btree_trans *trans,
bch2_open_bucket_get(c, wp, &obs);
bch2_alloc_sectors_done(c, wp);
-mem_alloc:
- b = bch2_btree_node_mem_alloc(trans, interior_node);
+out:
+ bkey_copy(&b->key, &tmp.k);
+ b->ob = obs;
six_unlock_write(&b->c.lock);
six_unlock_intent(&b->c.lock);
- /* we hold cannibalize_lock: */
- BUG_ON(IS_ERR(b));
- BUG_ON(b->ob.nr);
-
- bkey_copy(&b->key, &tmp.k);
- b->ob = obs;
-
return b;
+err:
+ bch2_btree_node_to_freelist(c, b);
+ return ERR_PTR(ret);
}
static struct btree *bch2_btree_node_alloc(struct btree_update *as,
@@ -1364,18 +1366,10 @@ static void bch2_insert_fixup_btree_ptr(struct btree_update *as,
if (unlikely(!test_bit(JOURNAL_replay_done, &c->journal.flags)))
bch2_journal_key_overwritten(c, b->c.btree_id, b->c.level, insert->k.p);
- if (bch2_bkey_invalid(c, bkey_i_to_s_c(insert),
- btree_node_type(b), WRITE, &buf) ?:
- bch2_bkey_in_btree_node(c, b, bkey_i_to_s_c(insert), &buf)) {
- printbuf_reset(&buf);
- prt_printf(&buf, "inserting invalid bkey\n ");
- bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(insert));
- prt_printf(&buf, "\n ");
- bch2_bkey_invalid(c, bkey_i_to_s_c(insert),
- btree_node_type(b), WRITE, &buf);
- bch2_bkey_in_btree_node(c, b, bkey_i_to_s_c(insert), &buf);
-
- bch2_fs_inconsistent(c, "%s", buf.buf);
+ if (bch2_bkey_validate(c, bkey_i_to_s_c(insert),
+ btree_node_type(b), BCH_VALIDATE_write) ?:
+ bch2_bkey_in_btree_node(c, b, bkey_i_to_s_c(insert), BCH_VALIDATE_write)) {
+ bch2_fs_inconsistent(c, "%s: inserting invalid bkey", __func__);
dump_stack();
}
@@ -2447,6 +2441,9 @@ int bch2_btree_node_update_key(struct btree_trans *trans, struct btree_iter *ite
}
new_hash = bch2_btree_node_mem_alloc(trans, false);
+ ret = PTR_ERR_OR_ZERO(new_hash);
+ if (ret)
+ goto err;
}
path->intent_ref++;
@@ -2454,14 +2451,9 @@ int bch2_btree_node_update_key(struct btree_trans *trans, struct btree_iter *ite
commit_flags, skip_triggers);
--path->intent_ref;
- if (new_hash) {
- mutex_lock(&c->btree_cache.lock);
- list_move(&new_hash->list, &c->btree_cache.freeable);
- mutex_unlock(&c->btree_cache.lock);
-
- six_unlock_write(&new_hash->c.lock);
- six_unlock_intent(&new_hash->c.lock);
- }
+ if (new_hash)
+ bch2_btree_node_to_freelist(c, new_hash);
+err:
closure_sync(&cl);
bch2_btree_cache_cannibalize_unlock(trans);
return ret;
@@ -2530,6 +2522,10 @@ int bch2_btree_root_alloc_fake_trans(struct btree_trans *trans, enum btree_id id
b = bch2_btree_node_mem_alloc(trans, false);
bch2_btree_cache_cannibalize_unlock(trans);
+ ret = PTR_ERR_OR_ZERO(b);
+ if (ret)
+ return ret;
+
set_btree_node_fake(b);
set_btree_node_need_rewrite(b);
b->c.level = level;
@@ -2561,7 +2557,7 @@ int bch2_btree_root_alloc_fake_trans(struct btree_trans *trans, enum btree_id id
void bch2_btree_root_alloc_fake(struct bch_fs *c, enum btree_id id, unsigned level)
{
- bch2_trans_run(c, bch2_btree_root_alloc_fake_trans(trans, id, level));
+ bch2_trans_run(c, lockrestart_do(trans, bch2_btree_root_alloc_fake_trans(trans, id, level)));
}
static void bch2_btree_update_to_text(struct printbuf *out, struct btree_update *as)
diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c
index 9f7004e..a227442 100644
--- a/fs/bcachefs/buckets.c
+++ b/fs/bcachefs/buckets.c
@@ -699,7 +699,8 @@ static int bch2_trigger_stripe_ptr(struct btree_trans *trans,
static int __trigger_extent(struct btree_trans *trans,
enum btree_id btree_id, unsigned level,
struct bkey_s_c k,
- enum btree_iter_update_trigger_flags flags)
+ enum btree_iter_update_trigger_flags flags,
+ s64 *replicas_sectors)
{
bool gc = flags & BTREE_TRIGGER_gc;
struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
@@ -708,7 +709,6 @@ static int __trigger_extent(struct btree_trans *trans,
enum bch_data_type data_type = bkey_is_btree_ptr(k.k)
? BCH_DATA_btree
: BCH_DATA_user;
- s64 replicas_sectors = 0;
int ret = 0;
struct disk_accounting_pos acc_replicas_key = {
@@ -739,7 +739,7 @@ static int __trigger_extent(struct btree_trans *trans,
if (ret)
return ret;
} else if (!p.has_ec) {
- replicas_sectors += disk_sectors;
+ *replicas_sectors += disk_sectors;
acc_replicas_key.replicas.devs[acc_replicas_key.replicas.nr_devs++] = p.ptr.dev;
} else {
ret = bch2_trigger_stripe_ptr(trans, k, p, data_type, disk_sectors, flags);
@@ -777,7 +777,7 @@ static int __trigger_extent(struct btree_trans *trans,
}
if (acc_replicas_key.replicas.nr_devs) {
- ret = bch2_disk_accounting_mod(trans, &acc_replicas_key, &replicas_sectors, 1, gc);
+ ret = bch2_disk_accounting_mod(trans, &acc_replicas_key, replicas_sectors, 1, gc);
if (ret)
return ret;
}
@@ -787,7 +787,7 @@ static int __trigger_extent(struct btree_trans *trans,
.type = BCH_DISK_ACCOUNTING_snapshot,
.snapshot.id = k.k->p.snapshot,
};
- ret = bch2_disk_accounting_mod(trans, &acc_snapshot_key, &replicas_sectors, 1, gc);
+ ret = bch2_disk_accounting_mod(trans, &acc_snapshot_key, replicas_sectors, 1, gc);
if (ret)
return ret;
}
@@ -807,16 +807,21 @@ static int __trigger_extent(struct btree_trans *trans,
.type = BCH_DISK_ACCOUNTING_btree,
.btree.id = btree_id,
};
- ret = bch2_disk_accounting_mod(trans, &acc_btree_key, &replicas_sectors, 1, gc);
+ ret = bch2_disk_accounting_mod(trans, &acc_btree_key, replicas_sectors, 1, gc);
if (ret)
return ret;
- }
-
- if (bch2_bkey_rebalance_opts(k)) {
- struct disk_accounting_pos acc = {
- .type = BCH_DISK_ACCOUNTING_rebalance_work,
+ } else {
+ bool insert = !(flags & BTREE_TRIGGER_overwrite);
+ struct disk_accounting_pos acc_inum_key = {
+ .type = BCH_DISK_ACCOUNTING_inum,
+ .inum.inum = k.k->p.inode,
};
- ret = bch2_disk_accounting_mod(trans, &acc, &replicas_sectors, 1, gc);
+ s64 v[3] = {
+ insert ? 1 : -1,
+ insert ? k.k->size : -((s64) k.k->size),
+ *replicas_sectors,
+ };
+ ret = bch2_disk_accounting_mod(trans, &acc_inum_key, v, ARRAY_SIZE(v), gc);
if (ret)
return ret;
}
@@ -829,6 +834,7 @@ int bch2_trigger_extent(struct btree_trans *trans,
struct bkey_s_c old, struct bkey_s new,
enum btree_iter_update_trigger_flags flags)
{
+ struct bch_fs *c = trans->c;
struct bkey_ptrs_c new_ptrs = bch2_bkey_ptrs_c(new.s_c);
struct bkey_ptrs_c old_ptrs = bch2_bkey_ptrs_c(old);
unsigned new_ptrs_bytes = (void *) new_ptrs.end - (void *) new_ptrs.start;
@@ -844,22 +850,54 @@ int bch2_trigger_extent(struct btree_trans *trans,
new_ptrs_bytes))
return 0;
- if (flags & BTREE_TRIGGER_transactional) {
- struct bch_fs *c = trans->c;
- int mod = (int) bch2_bkey_needs_rebalance(c, new.s_c) -
- (int) bch2_bkey_needs_rebalance(c, old);
+ if (flags & (BTREE_TRIGGER_transactional|BTREE_TRIGGER_gc)) {
+ s64 old_replicas_sectors = 0, new_replicas_sectors = 0;
- if (mod) {
+ if (old.k->type) {
+ int ret = __trigger_extent(trans, btree, level, old,
+ flags & ~BTREE_TRIGGER_insert,
+ &old_replicas_sectors);
+ if (ret)
+ return ret;
+ }
+
+ if (new.k->type) {
+ int ret = __trigger_extent(trans, btree, level, new.s_c,
+ flags & ~BTREE_TRIGGER_overwrite,
+ &new_replicas_sectors);
+ if (ret)
+ return ret;
+ }
+
+ int need_rebalance_delta = 0;
+ s64 need_rebalance_sectors_delta = 0;
+
+ s64 s = bch2_bkey_sectors_need_rebalance(c, old);
+ need_rebalance_delta -= s != 0;
+ need_rebalance_sectors_delta -= s;
+
+ s = bch2_bkey_sectors_need_rebalance(c, old);
+ need_rebalance_delta += s != 0;
+ need_rebalance_sectors_delta += s;
+
+ if ((flags & BTREE_TRIGGER_transactional) && need_rebalance_delta) {
int ret = bch2_btree_bit_mod_buffered(trans, BTREE_ID_rebalance_work,
- new.k->p, mod > 0);
+ new.k->p, need_rebalance_delta > 0);
+ if (ret)
+ return ret;
+ }
+
+ if (need_rebalance_sectors_delta) {
+ struct disk_accounting_pos acc = {
+ .type = BCH_DISK_ACCOUNTING_rebalance_work,
+ };
+ int ret = bch2_disk_accounting_mod(trans, &acc, &need_rebalance_sectors_delta, 1,
+ flags & BTREE_TRIGGER_gc);
if (ret)
return ret;
}
}
- if (flags & (BTREE_TRIGGER_transactional|BTREE_TRIGGER_gc))
- return trigger_run_overwrite_then_insert(__trigger_extent, trans, btree, level, old, new, flags);
-
return 0;
}
@@ -901,7 +939,6 @@ static int __bch2_trans_mark_metadata_bucket(struct btree_trans *trans,
enum bch_data_type type,
unsigned sectors)
{
- struct bch_fs *c = trans->c;
struct btree_iter iter;
int ret = 0;
@@ -911,7 +948,7 @@ static int __bch2_trans_mark_metadata_bucket(struct btree_trans *trans,
return PTR_ERR(a);
if (a->v.data_type && type && a->v.data_type != type) {
- bch2_fsck_err(c, FSCK_CAN_IGNORE|FSCK_NEED_FSCK,
+ bch2_fsck_err(trans, FSCK_CAN_IGNORE|FSCK_NEED_FSCK,
bucket_metadata_type_mismatch,
"bucket %llu:%llu gen %u different types of data in same bucket: %s, %s\n"
"while marking %s",
@@ -1032,13 +1069,18 @@ static int bch2_trans_mark_metadata_sectors(struct btree_trans *trans,
static int __bch2_trans_mark_dev_sb(struct btree_trans *trans, struct bch_dev *ca,
enum btree_iter_update_trigger_flags flags)
{
- struct bch_sb_layout *layout = &ca->disk_sb.sb->layout;
+ struct bch_fs *c = trans->c;
+
+ mutex_lock(&c->sb_lock);
+ struct bch_sb_layout layout = ca->disk_sb.sb->layout;
+ mutex_unlock(&c->sb_lock);
+
u64 bucket = 0;
unsigned i, bucket_sectors = 0;
int ret;
- for (i = 0; i < layout->nr_superblocks; i++) {
- u64 offset = le64_to_cpu(layout->sb_offset[i]);
+ for (i = 0; i < layout.nr_superblocks; i++) {
+ u64 offset = le64_to_cpu(layout.sb_offset[i]);
if (offset == BCH_SB_SECTOR) {
ret = bch2_trans_mark_metadata_sectors(trans, ca,
@@ -1049,7 +1091,7 @@ static int __bch2_trans_mark_dev_sb(struct btree_trans *trans, struct bch_dev *c
}
ret = bch2_trans_mark_metadata_sectors(trans, ca, offset,
- offset + (1 << layout->sb_max_size_bits),
+ offset + (1 << layout.sb_max_size_bits),
BCH_DATA_sb, &bucket, &bucket_sectors, flags);
if (ret)
return ret;
diff --git a/fs/bcachefs/buckets_waiting_for_journal.c b/fs/bcachefs/buckets_waiting_for_journal.c
index ec1b636e..f9fb150 100644
--- a/fs/bcachefs/buckets_waiting_for_journal.c
+++ b/fs/bcachefs/buckets_waiting_for_journal.c
@@ -93,7 +93,7 @@ int bch2_set_bucket_needs_journal_commit(struct buckets_waiting_for_journal *b,
.dev_bucket = (u64) dev << 56 | bucket,
.journal_seq = journal_seq,
};
- size_t i, size, new_bits, nr_elements = 1, nr_rehashes = 0;
+ size_t i, size, new_bits, nr_elements = 1, nr_rehashes = 0, nr_rehashes_this_size = 0;
int ret = 0;
mutex_lock(&b->lock);
@@ -106,8 +106,8 @@ int bch2_set_bucket_needs_journal_commit(struct buckets_waiting_for_journal *b,
for (i = 0; i < size; i++)
nr_elements += t->d[i].journal_seq > flushed_seq;
- new_bits = t->bits + (nr_elements * 3 > size);
-
+ new_bits = ilog2(roundup_pow_of_two(nr_elements * 3));
+realloc:
n = kvmalloc(sizeof(*n) + (sizeof(n->d[0]) << new_bits), GFP_KERNEL);
if (!n) {
ret = -BCH_ERR_ENOMEM_buckets_waiting_for_journal_set;
@@ -115,7 +115,16 @@ int bch2_set_bucket_needs_journal_commit(struct buckets_waiting_for_journal *b,
}
retry_rehash:
+ if (nr_rehashes_this_size == 3) {
+ new_bits++;
+ nr_rehashes_this_size = 0;
+ kvfree(n);
+ goto realloc;
+ }
+
nr_rehashes++;
+ nr_rehashes_this_size++;
+
bucket_table_init(n, new_bits);
tmp = new;
diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c
index 0087b85..004894a 100644
--- a/fs/bcachefs/data_update.c
+++ b/fs/bcachefs/data_update.c
@@ -20,6 +20,76 @@
#include "subvolume.h"
#include "trace.h"
+static void bkey_put_dev_refs(struct bch_fs *c, struct bkey_s_c k)
+{
+ struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
+
+ bkey_for_each_ptr(ptrs, ptr)
+ bch2_dev_put(bch2_dev_have_ref(c, ptr->dev));
+}
+
+static bool bkey_get_dev_refs(struct bch_fs *c, struct bkey_s_c k)
+{
+ struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
+
+ bkey_for_each_ptr(ptrs, ptr) {
+ if (!bch2_dev_tryget(c, ptr->dev)) {
+ bkey_for_each_ptr(ptrs, ptr2) {
+ if (ptr2 == ptr)
+ break;
+ bch2_dev_put(bch2_dev_have_ref(c, ptr2->dev));
+ }
+ return false;
+ }
+ }
+ return true;
+}
+
+static void bkey_nocow_unlock(struct bch_fs *c, struct bkey_s_c k)
+{
+ struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
+
+ bkey_for_each_ptr(ptrs, ptr) {
+ struct bch_dev *ca = bch2_dev_have_ref(c, ptr->dev);
+ struct bpos bucket = PTR_BUCKET_POS(ca, ptr);
+
+ bch2_bucket_nocow_unlock(&c->nocow_locks, bucket, 0);
+ }
+}
+
+static bool bkey_nocow_lock(struct bch_fs *c, struct moving_context *ctxt, struct bkey_s_c k)
+{
+ struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
+
+ bkey_for_each_ptr(ptrs, ptr) {
+ struct bch_dev *ca = bch2_dev_have_ref(c, ptr->dev);
+ struct bpos bucket = PTR_BUCKET_POS(ca, ptr);
+
+ if (ctxt) {
+ bool locked;
+
+ move_ctxt_wait_event(ctxt,
+ (locked = bch2_bucket_nocow_trylock(&c->nocow_locks, bucket, 0)) ||
+ list_empty(&ctxt->ios));
+
+ if (!locked)
+ bch2_bucket_nocow_lock(&c->nocow_locks, bucket, 0);
+ } else {
+ if (!bch2_bucket_nocow_trylock(&c->nocow_locks, bucket, 0)) {
+ bkey_for_each_ptr(ptrs, ptr2) {
+ if (ptr2 == ptr)
+ break;
+
+ bucket = PTR_BUCKET_POS(ca, ptr2);
+ bch2_bucket_nocow_unlock(&c->nocow_locks, bucket, 0);
+ }
+ return false;
+ }
+ }
+ }
+ return true;
+}
+
static void trace_move_extent_finish2(struct bch_fs *c, struct bkey_s_c k)
{
if (trace_move_extent_finish_enabled()) {
@@ -250,10 +320,8 @@ static int __bch2_data_update_index_update(struct btree_trans *trans,
* it's been hard to reproduce, so this should give us some more
* information when it does occur:
*/
- struct printbuf err = PRINTBUF;
- int invalid = bch2_bkey_invalid(c, bkey_i_to_s_c(insert), __btree_node_type(0, m->btree_id), 0, &err);
- printbuf_exit(&err);
-
+ int invalid = bch2_bkey_validate(c, bkey_i_to_s_c(insert), __btree_node_type(0, m->btree_id),
+ BCH_VALIDATE_commit);
if (invalid) {
struct printbuf buf = PRINTBUF;
@@ -269,6 +337,7 @@ static int __bch2_data_update_index_update(struct btree_trans *trans,
printbuf_exit(&buf);
bch2_fatal_error(c);
+ ret = -EIO;
goto out;
}
@@ -357,17 +426,11 @@ void bch2_data_update_read_done(struct data_update *m,
void bch2_data_update_exit(struct data_update *update)
{
struct bch_fs *c = update->op.c;
- struct bkey_ptrs_c ptrs =
- bch2_bkey_ptrs_c(bkey_i_to_s_c(update->k.k));
+ struct bkey_s_c k = bkey_i_to_s_c(update->k.k);
- bkey_for_each_ptr(ptrs, ptr) {
- struct bch_dev *ca = bch2_dev_have_ref(c, ptr->dev);
- if (c->opts.nocow_enabled)
- bch2_bucket_nocow_unlock(&c->nocow_locks,
- PTR_BUCKET_POS(ca, ptr), 0);
- bch2_dev_put(ca);
- }
-
+ if (c->opts.nocow_enabled)
+ bkey_nocow_unlock(c, k);
+ bkey_put_dev_refs(c, k);
bch2_bkey_buf_exit(&update->k, c);
bch2_disk_reservation_put(c, &update->op.res);
bch2_bio_free_pages_pool(c, &update->op.wbio.bio);
@@ -477,6 +540,9 @@ void bch2_data_update_opts_to_text(struct printbuf *out, struct bch_fs *c,
bch2_compression_opt_to_text(out, background_compression(*io_opts));
prt_newline(out);
+ prt_str(out, "opts.replicas:\t");
+ prt_u64(out, io_opts->data_replicas);
+
prt_str(out, "extra replicas:\t");
prt_u64(out, data_opts->extra_replicas);
}
@@ -545,7 +611,6 @@ int bch2_data_update_init(struct btree_trans *trans,
const union bch_extent_entry *entry;
struct extent_ptr_decoded p;
unsigned i, reserve_sectors = k.k->size * data_opts.extra_replicas;
- unsigned ptrs_locked = 0;
int ret = 0;
/*
@@ -556,6 +621,15 @@ int bch2_data_update_init(struct btree_trans *trans,
if (unlikely(k.k->p.snapshot && !bch2_snapshot_equiv(c, k.k->p.snapshot)))
return -BCH_ERR_data_update_done;
+ if (!bkey_get_dev_refs(c, k))
+ return -BCH_ERR_data_update_done;
+
+ if (c->opts.nocow_enabled &&
+ !bkey_nocow_lock(c, ctxt, k)) {
+ bkey_put_dev_refs(c, k);
+ return -BCH_ERR_nocow_lock_blocked;
+ }
+
bch2_bkey_buf_init(&m->k);
bch2_bkey_buf_reassemble(&m->k, c, k);
m->btree_id = btree_id;
@@ -577,40 +651,24 @@ int bch2_data_update_init(struct btree_trans *trans,
m->op.compression_opt = background_compression(io_opts);
m->op.watermark = m->data_opts.btree_insert_flags & BCH_WATERMARK_MASK;
- bkey_for_each_ptr(ptrs, ptr) {
- if (!bch2_dev_tryget(c, ptr->dev)) {
- bkey_for_each_ptr(ptrs, ptr2) {
- if (ptr2 == ptr)
- break;
- bch2_dev_put(bch2_dev_have_ref(c, ptr2->dev));
- }
- return -BCH_ERR_data_update_done;
- }
- }
-
unsigned durability_have = 0, durability_removing = 0;
i = 0;
bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
- struct bch_dev *ca = bch2_dev_have_ref(c, p.ptr.dev);
- struct bpos bucket = PTR_BUCKET_POS(ca, &p.ptr);
- bool locked;
+ if (!p.ptr.cached) {
+ rcu_read_lock();
+ if (BIT(i) & m->data_opts.rewrite_ptrs) {
+ if (crc_is_compressed(p.crc))
+ reserve_sectors += k.k->size;
- rcu_read_lock();
- if (((1U << i) & m->data_opts.rewrite_ptrs)) {
- BUG_ON(p.ptr.cached);
-
- if (crc_is_compressed(p.crc))
- reserve_sectors += k.k->size;
-
- m->op.nr_replicas += bch2_extent_ptr_desired_durability(c, &p);
- durability_removing += bch2_extent_ptr_desired_durability(c, &p);
- } else if (!p.ptr.cached &&
- !((1U << i) & m->data_opts.kill_ptrs)) {
- bch2_dev_list_add_dev(&m->op.devs_have, p.ptr.dev);
- durability_have += bch2_extent_ptr_durability(c, &p);
+ m->op.nr_replicas += bch2_extent_ptr_desired_durability(c, &p);
+ durability_removing += bch2_extent_ptr_desired_durability(c, &p);
+ } else if (!(BIT(i) & m->data_opts.kill_ptrs)) {
+ bch2_dev_list_add_dev(&m->op.devs_have, p.ptr.dev);
+ durability_have += bch2_extent_ptr_durability(c, &p);
+ }
+ rcu_read_unlock();
}
- rcu_read_unlock();
/*
* op->csum_type is normally initialized from the fs/file's
@@ -625,24 +683,6 @@ int bch2_data_update_init(struct btree_trans *trans,
if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible)
m->op.incompressible = true;
- if (c->opts.nocow_enabled) {
- if (ctxt) {
- move_ctxt_wait_event(ctxt,
- (locked = bch2_bucket_nocow_trylock(&c->nocow_locks,
- bucket, 0)) ||
- list_empty(&ctxt->ios));
-
- if (!locked)
- bch2_bucket_nocow_lock(&c->nocow_locks, bucket, 0);
- } else {
- if (!bch2_bucket_nocow_trylock(&c->nocow_locks, bucket, 0)) {
- ret = -BCH_ERR_nocow_lock_blocked;
- goto err;
- }
- }
- ptrs_locked |= (1U << i);
- }
-
i++;
}
@@ -656,16 +696,6 @@ int bch2_data_update_init(struct btree_trans *trans,
* Increasing replication is an explicit operation triggered by
* rereplicate, currently, so that users don't get an unexpected -ENOSPC
*/
- if (!(m->data_opts.write_flags & BCH_WRITE_CACHED) &&
- !durability_required) {
- m->data_opts.kill_ptrs |= m->data_opts.rewrite_ptrs;
- m->data_opts.rewrite_ptrs = 0;
- /* if iter == NULL, it's just a promote */
- if (iter)
- ret = bch2_extent_drop_ptrs(trans, iter, k, m->data_opts);
- goto done;
- }
-
m->op.nr_replicas = min(durability_removing, durability_required) +
m->data_opts.extra_replicas;
@@ -677,48 +707,38 @@ int bch2_data_update_init(struct btree_trans *trans,
if (!(durability_have + durability_removing))
m->op.nr_replicas = max((unsigned) m->op.nr_replicas, 1);
- if (!m->op.nr_replicas) {
- struct printbuf buf = PRINTBUF;
-
- bch2_data_update_to_text(&buf, m);
- WARN(1, "trying to move an extent, but nr_replicas=0\n%s", buf.buf);
- printbuf_exit(&buf);
- ret = -BCH_ERR_data_update_done;
- goto done;
- }
-
m->op.nr_replicas_required = m->op.nr_replicas;
+ /*
+ * It might turn out that we don't need any new replicas, if the
+ * replicas or durability settings have been changed since the extent
+ * was written:
+ */
+ if (!m->op.nr_replicas) {
+ m->data_opts.kill_ptrs |= m->data_opts.rewrite_ptrs;
+ m->data_opts.rewrite_ptrs = 0;
+ /* if iter == NULL, it's just a promote */
+ if (iter)
+ ret = bch2_extent_drop_ptrs(trans, iter, k, m->data_opts);
+ goto out;
+ }
+
if (reserve_sectors) {
ret = bch2_disk_reservation_add(c, &m->op.res, reserve_sectors,
m->data_opts.extra_replicas
? 0
: BCH_DISK_RESERVATION_NOFAIL);
if (ret)
- goto err;
+ goto out;
}
if (bkey_extent_is_unwritten(k)) {
bch2_update_unwritten_extent(trans, m);
- goto done;
+ goto out;
}
return 0;
-err:
- i = 0;
- bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
- struct bch_dev *ca = bch2_dev_have_ref(c, p.ptr.dev);
- struct bpos bucket = PTR_BUCKET_POS(ca, &p.ptr);
- if ((1U << i) & ptrs_locked)
- bch2_bucket_nocow_unlock(&c->nocow_locks, bucket, 0);
- bch2_dev_put(ca);
- i++;
- }
-
- bch2_bkey_buf_exit(&m->k, c);
- bch2_bio_free_pages_pool(c, &m->op.wbio.bio);
- return ret;
-done:
+out:
bch2_data_update_exit(m);
return ret ?: -BCH_ERR_data_update_done;
}
diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c
index ebabab1..45aec1af 100644
--- a/fs/bcachefs/debug.c
+++ b/fs/bcachefs/debug.c
@@ -397,47 +397,27 @@ static ssize_t bch2_read_btree_formats(struct file *file, char __user *buf,
size_t size, loff_t *ppos)
{
struct dump_iter *i = file->private_data;
- struct btree_trans *trans;
- struct btree_iter iter;
- struct btree *b;
- ssize_t ret;
i->ubuf = buf;
i->size = size;
i->ret = 0;
- ret = flush_buf(i);
+ ssize_t ret = flush_buf(i);
if (ret)
return ret;
if (bpos_eq(SPOS_MAX, i->from))
return i->ret;
- trans = bch2_trans_get(i->c);
-retry:
- bch2_trans_begin(trans);
+ return bch2_trans_run(i->c,
+ for_each_btree_node(trans, iter, i->id, i->from, 0, b, ({
+ bch2_btree_node_to_text(&i->buf, i->c, b);
+ i->from = !bpos_eq(SPOS_MAX, b->key.k.p)
+ ? bpos_successor(b->key.k.p)
+ : b->key.k.p;
- for_each_btree_node(trans, iter, i->id, i->from, 0, b, ret) {
- bch2_btree_node_to_text(&i->buf, i->c, b);
- i->from = !bpos_eq(SPOS_MAX, b->key.k.p)
- ? bpos_successor(b->key.k.p)
- : b->key.k.p;
-
- ret = drop_locks_do(trans, flush_buf(i));
- if (ret)
- break;
- }
- bch2_trans_iter_exit(trans, &iter);
-
- if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
- goto retry;
-
- bch2_trans_put(trans);
-
- if (!ret)
- ret = flush_buf(i);
-
- return ret ?: i->ret;
+ drop_locks_do(trans, flush_buf(i));
+ }))) ?: i->ret;
}
static const struct file_operations btree_format_debug_ops = {
diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c
index d743da8..32bfdf1 100644
--- a/fs/bcachefs/dirent.c
+++ b/fs/bcachefs/dirent.c
@@ -100,20 +100,19 @@ const struct bch_hash_desc bch2_dirent_hash_desc = {
.is_visible = dirent_is_visible,
};
-int bch2_dirent_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_dirent_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k);
struct qstr d_name = bch2_dirent_get_name(d);
int ret = 0;
- bkey_fsck_err_on(!d_name.len, c, err,
- dirent_empty_name,
+ bkey_fsck_err_on(!d_name.len,
+ c, dirent_empty_name,
"empty name");
- bkey_fsck_err_on(bkey_val_u64s(k.k) > dirent_val_u64s(d_name.len), c, err,
- dirent_val_too_big,
+ bkey_fsck_err_on(bkey_val_u64s(k.k) > dirent_val_u64s(d_name.len),
+ c, dirent_val_too_big,
"value too big (%zu > %u)",
bkey_val_u64s(k.k), dirent_val_u64s(d_name.len));
@@ -121,27 +120,27 @@ int bch2_dirent_invalid(struct bch_fs *c, struct bkey_s_c k,
* Check new keys don't exceed the max length
* (older keys may be larger.)
*/
- bkey_fsck_err_on((flags & BCH_VALIDATE_commit) && d_name.len > BCH_NAME_MAX, c, err,
- dirent_name_too_long,
+ bkey_fsck_err_on((flags & BCH_VALIDATE_commit) && d_name.len > BCH_NAME_MAX,
+ c, dirent_name_too_long,
"dirent name too big (%u > %u)",
d_name.len, BCH_NAME_MAX);
- bkey_fsck_err_on(d_name.len != strnlen(d_name.name, d_name.len), c, err,
- dirent_name_embedded_nul,
+ bkey_fsck_err_on(d_name.len != strnlen(d_name.name, d_name.len),
+ c, dirent_name_embedded_nul,
"dirent has stray data after name's NUL");
bkey_fsck_err_on((d_name.len == 1 && !memcmp(d_name.name, ".", 1)) ||
- (d_name.len == 2 && !memcmp(d_name.name, "..", 2)), c, err,
- dirent_name_dot_or_dotdot,
+ (d_name.len == 2 && !memcmp(d_name.name, "..", 2)),
+ c, dirent_name_dot_or_dotdot,
"invalid name");
- bkey_fsck_err_on(memchr(d_name.name, '/', d_name.len), c, err,
- dirent_name_has_slash,
+ bkey_fsck_err_on(memchr(d_name.name, '/', d_name.len),
+ c, dirent_name_has_slash,
"name with /");
bkey_fsck_err_on(d.v->d_type != DT_SUBVOL &&
- le64_to_cpu(d.v->d_inum) == d.k->p.inode, c, err,
- dirent_to_itself,
+ le64_to_cpu(d.v->d_inum) == d.k->p.inode,
+ c, dirent_to_itself,
"dirent points to own directory");
fsck_err:
return ret;
diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h
index 24037e6..8945145 100644
--- a/fs/bcachefs/dirent.h
+++ b/fs/bcachefs/dirent.h
@@ -7,12 +7,11 @@
enum bch_validate_flags;
extern const struct bch_hash_desc bch2_dirent_hash_desc;
-int bch2_dirent_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_dirent_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
void bch2_dirent_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
#define bch2_bkey_ops_dirent ((struct bkey_ops) { \
- .key_invalid = bch2_dirent_invalid, \
+ .key_validate = bch2_dirent_validate, \
.val_to_text = bch2_dirent_to_text, \
.min_val_size = 16, \
})
diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c
index 046ac92..e972e2b 100644
--- a/fs/bcachefs/disk_accounting.c
+++ b/fs/bcachefs/disk_accounting.c
@@ -126,9 +126,8 @@ static inline bool is_zero(char *start, char *end)
#define field_end(p, member) (((void *) (&p.member)) + sizeof(p.member))
-int bch2_accounting_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_accounting_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct disk_accounting_pos acc_k;
bpos_to_disk_accounting_pos(&acc_k, k.k->p);
@@ -144,18 +143,18 @@ int bch2_accounting_invalid(struct bch_fs *c, struct bkey_s_c k,
break;
case BCH_DISK_ACCOUNTING_replicas:
bkey_fsck_err_on(!acc_k.replicas.nr_devs,
- c, err, accounting_key_replicas_nr_devs_0,
+ c, accounting_key_replicas_nr_devs_0,
"accounting key replicas entry with nr_devs=0");
bkey_fsck_err_on(acc_k.replicas.nr_required > acc_k.replicas.nr_devs ||
(acc_k.replicas.nr_required > 1 &&
acc_k.replicas.nr_required == acc_k.replicas.nr_devs),
- c, err, accounting_key_replicas_nr_required_bad,
+ c, accounting_key_replicas_nr_required_bad,
"accounting key replicas entry with bad nr_required");
for (unsigned i = 0; i + 1 < acc_k.replicas.nr_devs; i++)
- bkey_fsck_err_on(acc_k.replicas.devs[i] > acc_k.replicas.devs[i + 1],
- c, err, accounting_key_replicas_devs_unsorted,
+ bkey_fsck_err_on(acc_k.replicas.devs[i] >= acc_k.replicas.devs[i + 1],
+ c, accounting_key_replicas_devs_unsorted,
"accounting key replicas entry with unsorted devs");
end = (void *) &acc_k.replicas + replicas_entry_bytes(&acc_k.replicas);
@@ -178,7 +177,7 @@ int bch2_accounting_invalid(struct bch_fs *c, struct bkey_s_c k,
}
bkey_fsck_err_on(!is_zero(end, (void *) (&acc_k + 1)),
- c, err, accounting_key_junk_at_end,
+ c, accounting_key_junk_at_end,
"junk at end of accounting key");
fsck_err:
return ret;
@@ -528,6 +527,9 @@ int bch2_gc_accounting_done(struct bch_fs *c)
struct disk_accounting_pos acc_k;
bpos_to_disk_accounting_pos(&acc_k, e->pos);
+ if (acc_k.type >= BCH_DISK_ACCOUNTING_TYPE_NR)
+ continue;
+
u64 src_v[BCH_ACCOUNTING_MAX_COUNTERS];
u64 dst_v[BCH_ACCOUNTING_MAX_COUNTERS];
@@ -564,7 +566,7 @@ int bch2_gc_accounting_done(struct bch_fs *c)
struct { __BKEY_PADDED(k, BCH_ACCOUNTING_MAX_COUNTERS); } k_i;
accounting_key_init(&k_i.k, &acc_k, src_v, nr);
- bch2_accounting_mem_mod_locked(trans, bkey_i_to_s_c_accounting(&k_i.k), false);
+ bch2_accounting_mem_mod_locked(trans, bkey_i_to_s_c_accounting(&k_i.k), false, false);
preempt_disable();
struct bch_fs_usage_base *dst = this_cpu_ptr(c->usage);
@@ -593,7 +595,7 @@ static int accounting_read_key(struct btree_trans *trans, struct bkey_s_c k)
return 0;
percpu_down_read(&c->mark_lock);
- int ret = __bch2_accounting_mem_mod(c, bkey_s_c_to_accounting(k), false);
+ int ret = bch2_accounting_mem_mod_locked(trans, bkey_s_c_to_accounting(k), false, true);
percpu_up_read(&c->mark_lock);
if (bch2_accounting_key_is_zero(bkey_s_c_to_accounting(k)) &&
@@ -760,6 +762,15 @@ void bch2_verify_accounting_clean(struct bch_fs *c)
struct bkey_s_c_accounting a = bkey_s_c_to_accounting(k);
unsigned nr = bch2_accounting_counters(k.k);
+ struct disk_accounting_pos acc_k;
+ bpos_to_disk_accounting_pos(&acc_k, k.k->p);
+
+ if (acc_k.type >= BCH_DISK_ACCOUNTING_TYPE_NR)
+ continue;
+
+ if (acc_k.type == BCH_DISK_ACCOUNTING_inum)
+ continue;
+
bch2_accounting_mem_read(c, k.k->p, v, nr);
if (memcmp(a.v->d, v, nr * sizeof(u64))) {
@@ -775,9 +786,6 @@ void bch2_verify_accounting_clean(struct bch_fs *c)
mismatch = true;
}
- struct disk_accounting_pos acc_k;
- bpos_to_disk_accounting_pos(&acc_k, a.k->p);
-
switch (acc_k.type) {
case BCH_DISK_ACCOUNTING_persistent_reserved:
base.reserved += acc_k.persistent_reserved.nr_replicas * a.v->d[0];
diff --git a/fs/bcachefs/disk_accounting.h b/fs/bcachefs/disk_accounting.h
index 3d3f25e..f29fd0d 100644
--- a/fs/bcachefs/disk_accounting.h
+++ b/fs/bcachefs/disk_accounting.h
@@ -82,14 +82,13 @@ int bch2_disk_accounting_mod(struct btree_trans *, struct disk_accounting_pos *,
s64 *, unsigned, bool);
int bch2_mod_dev_cached_sectors(struct btree_trans *, unsigned, s64, bool);
-int bch2_accounting_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_accounting_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
void bch2_accounting_key_to_text(struct printbuf *, struct disk_accounting_pos *);
void bch2_accounting_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
void bch2_accounting_swab(struct bkey_s);
#define bch2_bkey_ops_accounting ((struct bkey_ops) { \
- .key_invalid = bch2_accounting_invalid, \
+ .key_validate = bch2_accounting_validate, \
.val_to_text = bch2_accounting_to_text, \
.swab = bch2_accounting_swab, \
.min_val_size = 8, \
@@ -107,8 +106,40 @@ static inline int accounting_pos_cmp(const void *_l, const void *_r)
int bch2_accounting_mem_insert(struct bch_fs *, struct bkey_s_c_accounting, bool);
void bch2_accounting_mem_gc(struct bch_fs *);
-static inline int __bch2_accounting_mem_mod(struct bch_fs *c, struct bkey_s_c_accounting a, bool gc)
+/*
+ * Update in memory counters so they match the btree update we're doing; called
+ * from transaction commit path
+ */
+static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, struct bkey_s_c_accounting a, bool gc, bool read)
{
+ struct bch_fs *c = trans->c;
+ struct disk_accounting_pos acc_k;
+ bpos_to_disk_accounting_pos(&acc_k, a.k->p);
+
+ if (acc_k.type == BCH_DISK_ACCOUNTING_inum)
+ return 0;
+
+ if (!gc && !read) {
+ switch (acc_k.type) {
+ case BCH_DISK_ACCOUNTING_persistent_reserved:
+ trans->fs_usage_delta.reserved += acc_k.persistent_reserved.nr_replicas * a.v->d[0];
+ break;
+ case BCH_DISK_ACCOUNTING_replicas:
+ fs_usage_data_type_to_base(&trans->fs_usage_delta, acc_k.replicas.data_type, a.v->d[0]);
+ break;
+ case BCH_DISK_ACCOUNTING_dev_data_type:
+ rcu_read_lock();
+ struct bch_dev *ca = bch2_dev_rcu(c, acc_k.dev_data_type.dev);
+ if (ca) {
+ this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].buckets, a.v->d[0]);
+ this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].sectors, a.v->d[1]);
+ this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].fragmented, a.v->d[2]);
+ }
+ rcu_read_unlock();
+ break;
+ }
+ }
+
struct bch_accounting_mem *acc = &c->accounting;
unsigned idx;
@@ -130,45 +161,10 @@ static inline int __bch2_accounting_mem_mod(struct bch_fs *c, struct bkey_s_c_ac
return 0;
}
-/*
- * Update in memory counters so they match the btree update we're doing; called
- * from transaction commit path
- */
-static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, struct bkey_s_c_accounting a, bool gc)
-{
- struct bch_fs *c = trans->c;
-
- if (!gc) {
- struct disk_accounting_pos acc_k;
- bpos_to_disk_accounting_pos(&acc_k, a.k->p);
-
- switch (acc_k.type) {
- case BCH_DISK_ACCOUNTING_persistent_reserved:
- trans->fs_usage_delta.reserved += acc_k.persistent_reserved.nr_replicas * a.v->d[0];
- break;
- case BCH_DISK_ACCOUNTING_replicas:
- fs_usage_data_type_to_base(&trans->fs_usage_delta, acc_k.replicas.data_type, a.v->d[0]);
- break;
- case BCH_DISK_ACCOUNTING_dev_data_type:
- rcu_read_lock();
- struct bch_dev *ca = bch2_dev_rcu(c, acc_k.dev_data_type.dev);
- if (ca) {
- this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].buckets, a.v->d[0]);
- this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].sectors, a.v->d[1]);
- this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].fragmented, a.v->d[2]);
- }
- rcu_read_unlock();
- break;
- }
- }
-
- return __bch2_accounting_mem_mod(c, a, gc);
-}
-
static inline int bch2_accounting_mem_add(struct btree_trans *trans, struct bkey_s_c_accounting a, bool gc)
{
percpu_down_read(&trans->c->mark_lock);
- int ret = bch2_accounting_mem_mod_locked(trans, a, gc);
+ int ret = bch2_accounting_mem_mod_locked(trans, a, gc, false);
percpu_up_read(&trans->c->mark_lock);
return ret;
}
diff --git a/fs/bcachefs/disk_accounting_format.h b/fs/bcachefs/disk_accounting_format.h
index a93cf26..7b6e6c9 100644
--- a/fs/bcachefs/disk_accounting_format.h
+++ b/fs/bcachefs/disk_accounting_format.h
@@ -103,7 +103,8 @@ static inline bool data_type_is_hidden(enum bch_data_type type)
x(compression, 4) \
x(snapshot, 5) \
x(btree, 6) \
- x(rebalance_work, 7)
+ x(rebalance_work, 7) \
+ x(inum, 8)
enum disk_accounting_type {
#define x(f, nr) BCH_DISK_ACCOUNTING_##f = nr,
@@ -136,6 +137,10 @@ struct bch_acct_btree {
__u32 id;
} __packed;
+struct bch_acct_inum {
+ __u64 inum;
+} __packed;
+
struct bch_acct_rebalance_work {
};
@@ -152,6 +157,7 @@ struct disk_accounting_pos {
struct bch_acct_snapshot snapshot;
struct bch_acct_btree btree;
struct bch_acct_rebalance_work rebalance_work;
+ struct bch_acct_inum inum;
} __packed;
} __packed;
struct bpos _pad;
diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c
index 84f1cbf..141a4c6 100644
--- a/fs/bcachefs/ec.c
+++ b/fs/bcachefs/ec.c
@@ -107,24 +107,23 @@ struct ec_bio {
/* Stripes btree keys: */
-int bch2_stripe_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_stripe_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
const struct bch_stripe *s = bkey_s_c_to_stripe(k).v;
int ret = 0;
bkey_fsck_err_on(bkey_eq(k.k->p, POS_MIN) ||
- bpos_gt(k.k->p, POS(0, U32_MAX)), c, err,
- stripe_pos_bad,
+ bpos_gt(k.k->p, POS(0, U32_MAX)),
+ c, stripe_pos_bad,
"stripe at bad pos");
- bkey_fsck_err_on(bkey_val_u64s(k.k) < stripe_val_u64s(s), c, err,
- stripe_val_size_bad,
+ bkey_fsck_err_on(bkey_val_u64s(k.k) < stripe_val_u64s(s),
+ c, stripe_val_size_bad,
"incorrect value size (%zu < %u)",
bkey_val_u64s(k.k), stripe_val_u64s(s));
- ret = bch2_bkey_ptrs_invalid(c, k, flags, err);
+ ret = bch2_bkey_ptrs_validate(c, k, flags);
fsck_err:
return ret;
}
diff --git a/fs/bcachefs/ec.h b/fs/bcachefs/ec.h
index 84a23ee..90962b3c 100644
--- a/fs/bcachefs/ec.h
+++ b/fs/bcachefs/ec.h
@@ -8,8 +8,7 @@
enum bch_validate_flags;
-int bch2_stripe_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_stripe_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
void bch2_stripe_to_text(struct printbuf *, struct bch_fs *,
struct bkey_s_c);
int bch2_trigger_stripe(struct btree_trans *, enum btree_id, unsigned,
@@ -17,7 +16,7 @@ int bch2_trigger_stripe(struct btree_trans *, enum btree_id, unsigned,
enum btree_iter_update_trigger_flags);
#define bch2_bkey_ops_stripe ((struct bkey_ops) { \
- .key_invalid = bch2_stripe_invalid, \
+ .key_validate = bch2_stripe_validate, \
.val_to_text = bch2_stripe_to_text, \
.swab = bch2_ptr_swab, \
.trigger = bch2_trigger_stripe, \
diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h
index a268af3..742dcdd 100644
--- a/fs/bcachefs/errcode.h
+++ b/fs/bcachefs/errcode.h
@@ -166,6 +166,7 @@
x(0, journal_reclaim_would_deadlock) \
x(EINVAL, fsck) \
x(BCH_ERR_fsck, fsck_fix) \
+ x(BCH_ERR_fsck, fsck_delete_bkey) \
x(BCH_ERR_fsck, fsck_ignore) \
x(BCH_ERR_fsck, fsck_errors_not_fixed) \
x(BCH_ERR_fsck, fsck_repair_unimplemented) \
@@ -256,7 +257,6 @@
x(BCH_ERR_nopromote, nopromote_in_flight) \
x(BCH_ERR_nopromote, nopromote_no_writes) \
x(BCH_ERR_nopromote, nopromote_enomem) \
- x(0, need_inode_lock) \
x(0, invalid_snapshot_node) \
x(0, option_needs_open_fs)
diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c
index a62b631..95afa7b 100644
--- a/fs/bcachefs/error.c
+++ b/fs/bcachefs/error.c
@@ -416,6 +416,28 @@ int __bch2_fsck_err(struct bch_fs *c,
return ret;
}
+int __bch2_bkey_fsck_err(struct bch_fs *c,
+ struct bkey_s_c k,
+ enum bch_fsck_flags flags,
+ enum bch_sb_error_id err,
+ const char *fmt, ...)
+{
+ struct printbuf buf = PRINTBUF;
+ va_list args;
+
+ prt_str(&buf, "invalid bkey ");
+ bch2_bkey_val_to_text(&buf, c, k);
+ prt_str(&buf, "\n ");
+ va_start(args, fmt);
+ prt_vprintf(&buf, fmt, args);
+ va_end(args);
+ prt_str(&buf, ": delete?");
+
+ int ret = __bch2_fsck_err(c, NULL, flags, err, "%s", buf.buf);
+ printbuf_exit(&buf);
+ return ret;
+}
+
void bch2_flush_fsck_errs(struct bch_fs *c)
{
struct fsck_err_state *s, *n;
diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h
index 995e6bb..2f1b869 100644
--- a/fs/bcachefs/error.h
+++ b/fs/bcachefs/error.h
@@ -4,6 +4,7 @@
#include <linux/list.h>
#include <linux/printk.h>
+#include "bkey_types.h"
#include "sb-errors.h"
struct bch_dev;
@@ -166,24 +167,30 @@ void bch2_flush_fsck_errs(struct bch_fs *);
#define fsck_err_on(cond, c, _err_type, ...) \
__fsck_err_on(cond, c, FSCK_CAN_FIX|FSCK_CAN_IGNORE, _err_type, __VA_ARGS__)
-__printf(4, 0)
-static inline void bch2_bkey_fsck_err(struct bch_fs *c,
- struct printbuf *err_msg,
- enum bch_sb_error_id err_type,
- const char *fmt, ...)
-{
- va_list args;
+__printf(5, 6)
+int __bch2_bkey_fsck_err(struct bch_fs *,
+ struct bkey_s_c,
+ enum bch_fsck_flags,
+ enum bch_sb_error_id,
+ const char *, ...);
- va_start(args, fmt);
- prt_vprintf(err_msg, fmt, args);
- va_end(args);
-}
-
-#define bkey_fsck_err(c, _err_msg, _err_type, ...) \
+/*
+ * for now, bkey fsck errors are always handled by deleting the entire key -
+ * this will change at some point
+ */
+#define bkey_fsck_err(c, _err_type, _err_msg, ...) \
do { \
- prt_printf(_err_msg, __VA_ARGS__); \
- bch2_sb_error_count(c, BCH_FSCK_ERR_##_err_type); \
- ret = -BCH_ERR_invalid_bkey; \
+ if ((flags & BCH_VALIDATE_silent)) { \
+ ret = -BCH_ERR_fsck_delete_bkey; \
+ goto fsck_err; \
+ } \
+ int _ret = __bch2_bkey_fsck_err(c, k, FSCK_CAN_FIX, \
+ BCH_FSCK_ERR_##_err_type, \
+ _err_msg, ##__VA_ARGS__); \
+ if (_ret != -BCH_ERR_fsck_fix && \
+ _ret != -BCH_ERR_fsck_ignore) \
+ ret = _ret; \
+ ret = -BCH_ERR_fsck_delete_bkey; \
goto fsck_err; \
} while (0)
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index 0797319..eb31bda 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -171,17 +171,16 @@ int bch2_bkey_pick_read_device(struct bch_fs *c, struct bkey_s_c k,
/* KEY_TYPE_btree_ptr: */
-int bch2_btree_ptr_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_btree_ptr_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
int ret = 0;
- bkey_fsck_err_on(bkey_val_u64s(k.k) > BCH_REPLICAS_MAX, c, err,
- btree_ptr_val_too_big,
+ bkey_fsck_err_on(bkey_val_u64s(k.k) > BCH_REPLICAS_MAX,
+ c, btree_ptr_val_too_big,
"value too big (%zu > %u)", bkey_val_u64s(k.k), BCH_REPLICAS_MAX);
- ret = bch2_bkey_ptrs_invalid(c, k, flags, err);
+ ret = bch2_bkey_ptrs_validate(c, k, flags);
fsck_err:
return ret;
}
@@ -192,28 +191,27 @@ void bch2_btree_ptr_to_text(struct printbuf *out, struct bch_fs *c,
bch2_bkey_ptrs_to_text(out, c, k);
}
-int bch2_btree_ptr_v2_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_btree_ptr_v2_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct bkey_s_c_btree_ptr_v2 bp = bkey_s_c_to_btree_ptr_v2(k);
int ret = 0;
bkey_fsck_err_on(bkey_val_u64s(k.k) > BKEY_BTREE_PTR_VAL_U64s_MAX,
- c, err, btree_ptr_v2_val_too_big,
+ c, btree_ptr_v2_val_too_big,
"value too big (%zu > %zu)",
bkey_val_u64s(k.k), BKEY_BTREE_PTR_VAL_U64s_MAX);
bkey_fsck_err_on(bpos_ge(bp.v->min_key, bp.k->p),
- c, err, btree_ptr_v2_min_key_bad,
+ c, btree_ptr_v2_min_key_bad,
"min_key > key");
if (flags & BCH_VALIDATE_write)
bkey_fsck_err_on(!bp.v->sectors_written,
- c, err, btree_ptr_v2_written_0,
+ c, btree_ptr_v2_written_0,
"sectors_written == 0");
- ret = bch2_bkey_ptrs_invalid(c, k, flags, err);
+ ret = bch2_bkey_ptrs_validate(c, k, flags);
fsck_err:
return ret;
}
@@ -399,15 +397,14 @@ bool bch2_extent_merge(struct bch_fs *c, struct bkey_s l, struct bkey_s_c r)
/* KEY_TYPE_reservation: */
-int bch2_reservation_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_reservation_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct bkey_s_c_reservation r = bkey_s_c_to_reservation(k);
int ret = 0;
- bkey_fsck_err_on(!r.v->nr_replicas || r.v->nr_replicas > BCH_REPLICAS_MAX, c, err,
- reservation_key_nr_replicas_invalid,
+ bkey_fsck_err_on(!r.v->nr_replicas || r.v->nr_replicas > BCH_REPLICAS_MAX,
+ c, reservation_key_nr_replicas_invalid,
"invalid nr_replicas (%u)", r.v->nr_replicas);
fsck_err:
return ret;
@@ -932,8 +929,29 @@ bool bch2_extents_match(struct bkey_s_c k1, struct bkey_s_c k2)
bkey_for_each_ptr_decode(k2.k, ptrs2, p2, entry2)
if (p1.ptr.dev == p2.ptr.dev &&
p1.ptr.gen == p2.ptr.gen &&
+
+ /*
+ * This checks that the two pointers point
+ * to the same region on disk - adjusting
+ * for the difference in where the extents
+ * start, since one may have been trimmed:
+ */
(s64) p1.ptr.offset + p1.crc.offset - bkey_start_offset(k1.k) ==
- (s64) p2.ptr.offset + p2.crc.offset - bkey_start_offset(k2.k))
+ (s64) p2.ptr.offset + p2.crc.offset - bkey_start_offset(k2.k) &&
+
+ /*
+ * This additionally checks that the
+ * extents overlap on disk, since the
+ * previous check may trigger spuriously
+ * when one extent is immediately partially
+ * overwritten with another extent (so that
+ * on disk they are adjacent) and
+ * compression is in use:
+ */
+ ((p1.ptr.offset >= p2.ptr.offset &&
+ p1.ptr.offset < p2.ptr.offset + p2.crc.compressed_size) ||
+ (p2.ptr.offset >= p1.ptr.offset &&
+ p2.ptr.offset < p1.ptr.offset + p1.crc.compressed_size)))
return true;
return false;
@@ -1020,6 +1038,8 @@ void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *c, const struc
prt_printf(out, "ptr: %u:%llu:%u gen %u",
ptr->dev, b, offset, ptr->gen);
+ if (ca->mi.durability != 1)
+ prt_printf(out, " d=%u", ca->mi.durability);
if (ptr->cached)
prt_str(out, " cached");
if (ptr->unwritten)
@@ -1102,14 +1122,12 @@ void bch2_bkey_ptrs_to_text(struct printbuf *out, struct bch_fs *c,
}
}
-
-static int extent_ptr_invalid(struct bch_fs *c,
- struct bkey_s_c k,
- enum bch_validate_flags flags,
- const struct bch_extent_ptr *ptr,
- unsigned size_ondisk,
- bool metadata,
- struct printbuf *err)
+static int extent_ptr_validate(struct bch_fs *c,
+ struct bkey_s_c k,
+ enum bch_validate_flags flags,
+ const struct bch_extent_ptr *ptr,
+ unsigned size_ondisk,
+ bool metadata)
{
int ret = 0;
@@ -1128,28 +1146,27 @@ static int extent_ptr_invalid(struct bch_fs *c,
struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
bkey_for_each_ptr(ptrs, ptr2)
- bkey_fsck_err_on(ptr != ptr2 && ptr->dev == ptr2->dev, c, err,
- ptr_to_duplicate_device,
+ bkey_fsck_err_on(ptr != ptr2 && ptr->dev == ptr2->dev,
+ c, ptr_to_duplicate_device,
"multiple pointers to same device (%u)", ptr->dev);
- bkey_fsck_err_on(bucket >= nbuckets, c, err,
- ptr_after_last_bucket,
+ bkey_fsck_err_on(bucket >= nbuckets,
+ c, ptr_after_last_bucket,
"pointer past last bucket (%llu > %llu)", bucket, nbuckets);
- bkey_fsck_err_on(bucket < first_bucket, c, err,
- ptr_before_first_bucket,
+ bkey_fsck_err_on(bucket < first_bucket,
+ c, ptr_before_first_bucket,
"pointer before first bucket (%llu < %u)", bucket, first_bucket);
- bkey_fsck_err_on(bucket_offset + size_ondisk > bucket_size, c, err,
- ptr_spans_multiple_buckets,
+ bkey_fsck_err_on(bucket_offset + size_ondisk > bucket_size,
+ c, ptr_spans_multiple_buckets,
"pointer spans multiple buckets (%u + %u > %u)",
bucket_offset, size_ondisk, bucket_size);
fsck_err:
return ret;
}
-int bch2_bkey_ptrs_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_bkey_ptrs_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
const union bch_extent_entry *entry;
@@ -1164,25 +1181,24 @@ int bch2_bkey_ptrs_invalid(struct bch_fs *c, struct bkey_s_c k,
size_ondisk = btree_sectors(c);
bkey_extent_entry_for_each(ptrs, entry) {
- bkey_fsck_err_on(__extent_entry_type(entry) >= BCH_EXTENT_ENTRY_MAX, c, err,
- extent_ptrs_invalid_entry,
- "invalid extent entry type (got %u, max %u)",
- __extent_entry_type(entry), BCH_EXTENT_ENTRY_MAX);
+ bkey_fsck_err_on(__extent_entry_type(entry) >= BCH_EXTENT_ENTRY_MAX,
+ c, extent_ptrs_invalid_entry,
+ "invalid extent entry type (got %u, max %u)",
+ __extent_entry_type(entry), BCH_EXTENT_ENTRY_MAX);
bkey_fsck_err_on(bkey_is_btree_ptr(k.k) &&
- !extent_entry_is_ptr(entry), c, err,
- btree_ptr_has_non_ptr,
+ !extent_entry_is_ptr(entry),
+ c, btree_ptr_has_non_ptr,
"has non ptr field");
switch (extent_entry_type(entry)) {
case BCH_EXTENT_ENTRY_ptr:
- ret = extent_ptr_invalid(c, k, flags, &entry->ptr,
- size_ondisk, false, err);
+ ret = extent_ptr_validate(c, k, flags, &entry->ptr, size_ondisk, false);
if (ret)
return ret;
- bkey_fsck_err_on(entry->ptr.cached && have_ec, c, err,
- ptr_cached_and_erasure_coded,
+ bkey_fsck_err_on(entry->ptr.cached && have_ec,
+ c, ptr_cached_and_erasure_coded,
"cached, erasure coded ptr");
if (!entry->ptr.unwritten)
@@ -1199,44 +1215,50 @@ int bch2_bkey_ptrs_invalid(struct bch_fs *c, struct bkey_s_c k,
case BCH_EXTENT_ENTRY_crc128:
crc = bch2_extent_crc_unpack(k.k, entry_to_crc(entry));
- bkey_fsck_err_on(crc.offset + crc.live_size > crc.uncompressed_size, c, err,
- ptr_crc_uncompressed_size_too_small,
+ bkey_fsck_err_on(crc.offset + crc.live_size > crc.uncompressed_size,
+ c, ptr_crc_uncompressed_size_too_small,
"checksum offset + key size > uncompressed size");
- bkey_fsck_err_on(!bch2_checksum_type_valid(c, crc.csum_type), c, err,
- ptr_crc_csum_type_unknown,
+ bkey_fsck_err_on(!bch2_checksum_type_valid(c, crc.csum_type),
+ c, ptr_crc_csum_type_unknown,
"invalid checksum type");
- bkey_fsck_err_on(crc.compression_type >= BCH_COMPRESSION_TYPE_NR, c, err,
- ptr_crc_compression_type_unknown,
+ bkey_fsck_err_on(crc.compression_type >= BCH_COMPRESSION_TYPE_NR,
+ c, ptr_crc_compression_type_unknown,
"invalid compression type");
if (bch2_csum_type_is_encryption(crc.csum_type)) {
if (nonce == UINT_MAX)
nonce = crc.offset + crc.nonce;
else if (nonce != crc.offset + crc.nonce)
- bkey_fsck_err(c, err, ptr_crc_nonce_mismatch,
+ bkey_fsck_err(c, ptr_crc_nonce_mismatch,
"incorrect nonce");
}
- bkey_fsck_err_on(crc_since_last_ptr, c, err,
- ptr_crc_redundant,
+ bkey_fsck_err_on(crc_since_last_ptr,
+ c, ptr_crc_redundant,
"redundant crc entry");
crc_since_last_ptr = true;
bkey_fsck_err_on(crc_is_encoded(crc) &&
(crc.uncompressed_size > c->opts.encoded_extent_max >> 9) &&
- (flags & (BCH_VALIDATE_write|BCH_VALIDATE_commit)), c, err,
- ptr_crc_uncompressed_size_too_big,
+ (flags & (BCH_VALIDATE_write|BCH_VALIDATE_commit)),
+ c, ptr_crc_uncompressed_size_too_big,
"too large encoded extent");
size_ondisk = crc.compressed_size;
break;
case BCH_EXTENT_ENTRY_stripe_ptr:
- bkey_fsck_err_on(have_ec, c, err,
- ptr_stripe_redundant,
+ bkey_fsck_err_on(have_ec,
+ c, ptr_stripe_redundant,
"redundant stripe entry");
have_ec = true;
break;
case BCH_EXTENT_ENTRY_rebalance: {
+ /*
+ * this shouldn't be a fsck error, for forward
+ * compatibility; the rebalance code should just refetch
+ * the compression opt if it's unknown
+ */
+#if 0
const struct bch_extent_rebalance *r = &entry->rebalance;
if (!bch2_compression_opt_valid(r->compression)) {
@@ -1245,28 +1267,29 @@ int bch2_bkey_ptrs_invalid(struct bch_fs *c, struct bkey_s_c k,
opt.type, opt.level);
return -BCH_ERR_invalid_bkey;
}
+#endif
break;
}
}
}
- bkey_fsck_err_on(!nr_ptrs, c, err,
- extent_ptrs_no_ptrs,
+ bkey_fsck_err_on(!nr_ptrs,
+ c, extent_ptrs_no_ptrs,
"no ptrs");
- bkey_fsck_err_on(nr_ptrs > BCH_BKEY_PTRS_MAX, c, err,
- extent_ptrs_too_many_ptrs,
+ bkey_fsck_err_on(nr_ptrs > BCH_BKEY_PTRS_MAX,
+ c, extent_ptrs_too_many_ptrs,
"too many ptrs: %u > %u", nr_ptrs, BCH_BKEY_PTRS_MAX);
- bkey_fsck_err_on(have_written && have_unwritten, c, err,
- extent_ptrs_written_and_unwritten,
+ bkey_fsck_err_on(have_written && have_unwritten,
+ c, extent_ptrs_written_and_unwritten,
"extent with unwritten and written ptrs");
- bkey_fsck_err_on(k.k->type != KEY_TYPE_extent && have_unwritten, c, err,
- extent_ptrs_unwritten,
+ bkey_fsck_err_on(k.k->type != KEY_TYPE_extent && have_unwritten,
+ c, extent_ptrs_unwritten,
"has unwritten ptrs");
- bkey_fsck_err_on(crc_since_last_ptr, c, err,
- extent_ptrs_redundant_crc,
+ bkey_fsck_err_on(crc_since_last_ptr,
+ c, extent_ptrs_redundant_crc,
"redundant crc entry");
- bkey_fsck_err_on(have_ec, c, err,
- extent_ptrs_redundant_stripe,
+ bkey_fsck_err_on(have_ec,
+ c, extent_ptrs_redundant_stripe,
"redundant stripe entry");
fsck_err:
return ret;
@@ -1377,6 +1400,45 @@ bool bch2_bkey_needs_rebalance(struct bch_fs *c, struct bkey_s_c k)
return r != NULL;
}
+static u64 __bch2_bkey_sectors_need_rebalance(struct bch_fs *c, struct bkey_s_c k,
+ unsigned target, unsigned compression)
+{
+ struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
+ const union bch_extent_entry *entry;
+ struct extent_ptr_decoded p;
+ u64 sectors = 0;
+
+ if (compression) {
+ unsigned compression_type = bch2_compression_opt_to_type(compression);
+
+ bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
+ if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible ||
+ p.ptr.unwritten) {
+ sectors = 0;
+ goto incompressible;
+ }
+
+ if (!p.ptr.cached && p.crc.compression_type != compression_type)
+ sectors += p.crc.compressed_size;
+ }
+ }
+incompressible:
+ if (target && bch2_target_accepts_data(c, BCH_DATA_user, target)) {
+ bkey_for_each_ptr_decode(k.k, ptrs, p, entry)
+ if (!p.ptr.cached && !bch2_dev_in_target(c, p.ptr.dev, target))
+ sectors += p.crc.compressed_size;
+ }
+
+ return sectors;
+}
+
+u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *c, struct bkey_s_c k)
+{
+ const struct bch_extent_rebalance *r = bch2_bkey_rebalance_opts(k);
+
+ return r ? __bch2_bkey_sectors_need_rebalance(c, k, r->target, r->compression) : 0;
+}
+
int bch2_bkey_set_needs_rebalance(struct bch_fs *c, struct bkey_i *_k,
struct bch_io_opts *opts)
{
diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h
index facdb8a..709dd83 100644
--- a/fs/bcachefs/extents.h
+++ b/fs/bcachefs/extents.h
@@ -409,26 +409,26 @@ int bch2_bkey_pick_read_device(struct bch_fs *, struct bkey_s_c,
/* KEY_TYPE_btree_ptr: */
-int bch2_btree_ptr_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_btree_ptr_validate(struct bch_fs *, struct bkey_s_c,
+ enum bch_validate_flags);
void bch2_btree_ptr_to_text(struct printbuf *, struct bch_fs *,
struct bkey_s_c);
-int bch2_btree_ptr_v2_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_btree_ptr_v2_validate(struct bch_fs *, struct bkey_s_c,
+ enum bch_validate_flags);
void bch2_btree_ptr_v2_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
void bch2_btree_ptr_v2_compat(enum btree_id, unsigned, unsigned,
int, struct bkey_s);
#define bch2_bkey_ops_btree_ptr ((struct bkey_ops) { \
- .key_invalid = bch2_btree_ptr_invalid, \
+ .key_validate = bch2_btree_ptr_validate, \
.val_to_text = bch2_btree_ptr_to_text, \
.swab = bch2_ptr_swab, \
.trigger = bch2_trigger_extent, \
})
#define bch2_bkey_ops_btree_ptr_v2 ((struct bkey_ops) { \
- .key_invalid = bch2_btree_ptr_v2_invalid, \
+ .key_validate = bch2_btree_ptr_v2_validate, \
.val_to_text = bch2_btree_ptr_v2_to_text, \
.swab = bch2_ptr_swab, \
.compat = bch2_btree_ptr_v2_compat, \
@@ -441,7 +441,7 @@ void bch2_btree_ptr_v2_compat(enum btree_id, unsigned, unsigned,
bool bch2_extent_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c);
#define bch2_bkey_ops_extent ((struct bkey_ops) { \
- .key_invalid = bch2_bkey_ptrs_invalid, \
+ .key_validate = bch2_bkey_ptrs_validate, \
.val_to_text = bch2_bkey_ptrs_to_text, \
.swab = bch2_ptr_swab, \
.key_normalize = bch2_extent_normalize, \
@@ -451,13 +451,13 @@ bool bch2_extent_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c);
/* KEY_TYPE_reservation: */
-int bch2_reservation_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_reservation_validate(struct bch_fs *, struct bkey_s_c,
+ enum bch_validate_flags);
void bch2_reservation_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
bool bch2_reservation_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c);
#define bch2_bkey_ops_reservation ((struct bkey_ops) { \
- .key_invalid = bch2_reservation_invalid, \
+ .key_validate = bch2_reservation_validate, \
.val_to_text = bch2_reservation_to_text, \
.key_merge = bch2_reservation_merge, \
.trigger = bch2_trigger_reservation, \
@@ -683,8 +683,8 @@ bool bch2_extent_normalize(struct bch_fs *, struct bkey_s);
void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *, const struct bch_extent_ptr *);
void bch2_bkey_ptrs_to_text(struct printbuf *, struct bch_fs *,
struct bkey_s_c);
-int bch2_bkey_ptrs_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_bkey_ptrs_validate(struct bch_fs *, struct bkey_s_c,
+ enum bch_validate_flags);
void bch2_ptr_swab(struct bkey_s);
@@ -692,6 +692,7 @@ const struct bch_extent_rebalance *bch2_bkey_rebalance_opts(struct bkey_s_c);
unsigned bch2_bkey_ptrs_need_rebalance(struct bch_fs *, struct bkey_s_c,
unsigned, unsigned);
bool bch2_bkey_needs_rebalance(struct bch_fs *, struct bkey_s_c);
+u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *, struct bkey_s_c);
int bch2_bkey_set_needs_rebalance(struct bch_fs *, struct bkey_i *,
struct bch_io_opts *);
diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c
index cc33d76..ec8c427 100644
--- a/fs/bcachefs/fs-io-buffered.c
+++ b/fs/bcachefs/fs-io-buffered.c
@@ -534,7 +534,7 @@ static int __bch2_writepage(struct folio *folio,
if (f_sectors > w->tmp_sectors) {
kfree(w->tmp);
- w->tmp = kcalloc(f_sectors, sizeof(struct bch_folio_sector), __GFP_NOFAIL);
+ w->tmp = kcalloc(f_sectors, sizeof(struct bch_folio_sector), GFP_NOFS|__GFP_NOFAIL);
w->tmp_sectors = f_sectors;
}
@@ -802,8 +802,7 @@ static noinline void folios_trunc(folios *fs, struct folio **fi)
static int __bch2_buffered_write(struct bch_inode_info *inode,
struct address_space *mapping,
struct iov_iter *iter,
- loff_t pos, unsigned len,
- bool inode_locked)
+ loff_t pos, unsigned len)
{
struct bch_fs *c = inode->v.i_sb->s_fs_info;
struct bch2_folio_reservation res;
@@ -827,15 +826,6 @@ static int __bch2_buffered_write(struct bch_inode_info *inode,
BUG_ON(!fs.nr);
- /*
- * If we're not using the inode lock, we need to lock all the folios for
- * atomiticity of writes vs. other writes:
- */
- if (!inode_locked && folio_end_pos(darray_last(fs)) < end) {
- ret = -BCH_ERR_need_inode_lock;
- goto out;
- }
-
f = darray_first(fs);
if (pos != folio_pos(f) && !folio_test_uptodate(f)) {
ret = bch2_read_single_folio(f, mapping);
@@ -932,10 +922,8 @@ static int __bch2_buffered_write(struct bch_inode_info *inode,
end = pos + copied;
spin_lock(&inode->v.i_lock);
- if (end > inode->v.i_size) {
- BUG_ON(!inode_locked);
+ if (end > inode->v.i_size)
i_size_write(&inode->v, end);
- }
spin_unlock(&inode->v.i_lock);
f_pos = pos;
@@ -979,68 +967,12 @@ static ssize_t bch2_buffered_write(struct kiocb *iocb, struct iov_iter *iter)
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct bch_inode_info *inode = file_bch_inode(file);
- loff_t pos;
- bool inode_locked = false;
- ssize_t written = 0, written2 = 0, ret = 0;
-
- /*
- * We don't take the inode lock unless i_size will be changing. Folio
- * locks provide exclusion with other writes, and the pagecache add lock
- * provides exclusion with truncate and hole punching.
- *
- * There is one nasty corner case where atomicity would be broken
- * without great care: when copying data from userspace to the page
- * cache, we do that with faults disable - a page fault would recurse
- * back into the filesystem, taking filesystem locks again, and
- * deadlock; so it's done with faults disabled, and we fault in the user
- * buffer when we aren't holding locks.
- *
- * If we do part of the write, but we then race and in the userspace
- * buffer have been evicted and are no longer resident, then we have to
- * drop our folio locks to re-fault them in, breaking write atomicity.
- *
- * To fix this, we restart the write from the start, if we weren't
- * holding the inode lock.
- *
- * There is another wrinkle after that; if we restart the write from the
- * start, and then get an unrecoverable error, we _cannot_ claim to
- * userspace that we did not write data we actually did - so we must
- * track (written2) the most we ever wrote.
- */
-
- if ((iocb->ki_flags & IOCB_APPEND) ||
- (iocb->ki_pos + iov_iter_count(iter) > i_size_read(&inode->v))) {
- inode_lock(&inode->v);
- inode_locked = true;
- }
-
- ret = generic_write_checks(iocb, iter);
- if (ret <= 0)
- goto unlock;
-
- ret = file_remove_privs_flags(file, !inode_locked ? IOCB_NOWAIT : 0);
- if (ret) {
- if (!inode_locked) {
- inode_lock(&inode->v);
- inode_locked = true;
- ret = file_remove_privs_flags(file, 0);
- }
- if (ret)
- goto unlock;
- }
-
- ret = file_update_time(file);
- if (ret)
- goto unlock;
-
- pos = iocb->ki_pos;
+ loff_t pos = iocb->ki_pos;
+ ssize_t written = 0;
+ int ret = 0;
bch2_pagecache_add_get(inode);
- if (!inode_locked &&
- (iocb->ki_pos + iov_iter_count(iter) > i_size_read(&inode->v)))
- goto get_inode_lock;
-
do {
unsigned offset = pos & (PAGE_SIZE - 1);
unsigned bytes = iov_iter_count(iter);
@@ -1065,17 +997,12 @@ static ssize_t bch2_buffered_write(struct kiocb *iocb, struct iov_iter *iter)
}
}
- if (unlikely(bytes != iov_iter_count(iter) && !inode_locked))
- goto get_inode_lock;
-
if (unlikely(fatal_signal_pending(current))) {
ret = -EINTR;
break;
}
- ret = __bch2_buffered_write(inode, mapping, iter, pos, bytes, inode_locked);
- if (ret == -BCH_ERR_need_inode_lock)
- goto get_inode_lock;
+ ret = __bch2_buffered_write(inode, mapping, iter, pos, bytes);
if (unlikely(ret < 0))
break;
@@ -1096,46 +1023,50 @@ static ssize_t bch2_buffered_write(struct kiocb *iocb, struct iov_iter *iter)
}
pos += ret;
written += ret;
- written2 = max(written, written2);
-
- if (ret != bytes && !inode_locked)
- goto get_inode_lock;
ret = 0;
balance_dirty_pages_ratelimited(mapping);
-
- if (0) {
-get_inode_lock:
- bch2_pagecache_add_put(inode);
- inode_lock(&inode->v);
- inode_locked = true;
- bch2_pagecache_add_get(inode);
-
- iov_iter_revert(iter, written);
- pos -= written;
- written = 0;
- ret = 0;
- }
} while (iov_iter_count(iter));
+
bch2_pagecache_add_put(inode);
-unlock:
- if (inode_locked)
- inode_unlock(&inode->v);
- iocb->ki_pos += written;
-
- ret = max(written, written2) ?: ret;
- if (ret > 0)
- ret = generic_write_sync(iocb, ret);
- return ret;
+ return written ? written : ret;
}
-ssize_t bch2_write_iter(struct kiocb *iocb, struct iov_iter *iter)
+ssize_t bch2_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
- ssize_t ret = iocb->ki_flags & IOCB_DIRECT
- ? bch2_direct_write(iocb, iter)
- : bch2_buffered_write(iocb, iter);
+ struct file *file = iocb->ki_filp;
+ struct bch_inode_info *inode = file_bch_inode(file);
+ ssize_t ret;
+ if (iocb->ki_flags & IOCB_DIRECT) {
+ ret = bch2_direct_write(iocb, from);
+ goto out;
+ }
+
+ inode_lock(&inode->v);
+
+ ret = generic_write_checks(iocb, from);
+ if (ret <= 0)
+ goto unlock;
+
+ ret = file_remove_privs(file);
+ if (ret)
+ goto unlock;
+
+ ret = file_update_time(file);
+ if (ret)
+ goto unlock;
+
+ ret = bch2_buffered_write(iocb, from);
+ if (likely(ret > 0))
+ iocb->ki_pos += ret;
+unlock:
+ inode_unlock(&inode->v);
+
+ if (ret > 0)
+ ret = generic_write_sync(iocb, ret);
+out:
return bch2_err_class(ret);
}
diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c
index aea8132..99c7fe9 100644
--- a/fs/bcachefs/fs-ioctl.c
+++ b/fs/bcachefs/fs-ioctl.c
@@ -328,9 +328,8 @@ static int bch2_ioc_setlabel(struct bch_fs *c,
mutex_lock(&c->sb_lock);
strscpy(c->disk_sb.sb->label, label, BCH_SB_LABEL_SIZE);
- mutex_unlock(&c->sb_lock);
-
ret = bch2_write_super(c);
+ mutex_unlock(&c->sb_lock);
mnt_drop_write_file(file);
return ret;
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index 15fc41e..94c392a 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -193,7 +193,7 @@ static struct bch_inode_info *bch2_inode_insert(struct bch_fs *c, struct bch_ino
* only insert fully created inodes in the inode hash table. But
* discard_new_inode() expects it to be set...
*/
- inode->v.i_flags |= I_NEW;
+ inode->v.i_state |= I_NEW;
/*
* We don't want bch2_evict_inode() to delete the inode on disk,
* we just raced and had another inode in cache. Normally new
diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 9138944..83bd31b 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -2006,7 +2006,6 @@ static int check_dirent_to_subvol(struct btree_trans *trans, struct btree_iter *
if (ret) {
bch_err(c, "subvol %u points to missing inode root %llu", target_subvol, target_inum);
ret = -BCH_ERR_fsck_repair_unimplemented;
- ret = 0;
goto err;
}
@@ -2216,6 +2215,8 @@ int bch2_check_xattrs(struct bch_fs *c)
NULL, NULL,
BCH_TRANS_COMMIT_no_enospc,
check_xattr(trans, &iter, k, &hash_info, &inode)));
+
+ inode_walker_exit(&inode);
bch_err_fn(c, ret);
return ret;
}
@@ -2469,8 +2470,7 @@ static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c ino
: bch2_inode_unpack(inode_k, &inode);
if (ret) {
/* Should have been caught in dirents pass */
- if (!bch2_err_matches(ret, BCH_ERR_transaction_restart))
- bch_err(c, "error looking up parent directory: %i", ret);
+ bch_err_msg(c, ret, "error looking up parent directory");
break;
}
diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c
index 1e20020..2be6be3 100644
--- a/fs/bcachefs/inode.c
+++ b/fs/bcachefs/inode.c
@@ -434,100 +434,98 @@ struct bkey_i *bch2_inode_to_v3(struct btree_trans *trans, struct bkey_i *k)
return &inode_p->inode.k_i;
}
-static int __bch2_inode_invalid(struct bch_fs *c, struct bkey_s_c k, struct printbuf *err)
+static int __bch2_inode_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct bch_inode_unpacked unpacked;
int ret = 0;
- bkey_fsck_err_on(k.k->p.inode, c, err,
- inode_pos_inode_nonzero,
+ bkey_fsck_err_on(k.k->p.inode,
+ c, inode_pos_inode_nonzero,
"nonzero k.p.inode");
- bkey_fsck_err_on(k.k->p.offset < BLOCKDEV_INODE_MAX, c, err,
- inode_pos_blockdev_range,
+ bkey_fsck_err_on(k.k->p.offset < BLOCKDEV_INODE_MAX,
+ c, inode_pos_blockdev_range,
"fs inode in blockdev range");
- bkey_fsck_err_on(bch2_inode_unpack(k, &unpacked), c, err,
- inode_unpack_error,
+ bkey_fsck_err_on(bch2_inode_unpack(k, &unpacked),
+ c, inode_unpack_error,
"invalid variable length fields");
- bkey_fsck_err_on(unpacked.bi_data_checksum >= BCH_CSUM_OPT_NR + 1, c, err,
- inode_checksum_type_invalid,
+ bkey_fsck_err_on(unpacked.bi_data_checksum >= BCH_CSUM_OPT_NR + 1,
+ c, inode_checksum_type_invalid,
"invalid data checksum type (%u >= %u",
unpacked.bi_data_checksum, BCH_CSUM_OPT_NR + 1);
bkey_fsck_err_on(unpacked.bi_compression &&
- !bch2_compression_opt_valid(unpacked.bi_compression - 1), c, err,
- inode_compression_type_invalid,
+ !bch2_compression_opt_valid(unpacked.bi_compression - 1),
+ c, inode_compression_type_invalid,
"invalid compression opt %u", unpacked.bi_compression - 1);
bkey_fsck_err_on((unpacked.bi_flags & BCH_INODE_unlinked) &&
- unpacked.bi_nlink != 0, c, err,
- inode_unlinked_but_nlink_nonzero,
+ unpacked.bi_nlink != 0,
+ c, inode_unlinked_but_nlink_nonzero,
"flagged as unlinked but bi_nlink != 0");
- bkey_fsck_err_on(unpacked.bi_subvol && !S_ISDIR(unpacked.bi_mode), c, err,
- inode_subvol_root_but_not_dir,
+ bkey_fsck_err_on(unpacked.bi_subvol && !S_ISDIR(unpacked.bi_mode),
+ c, inode_subvol_root_but_not_dir,
"subvolume root but not a directory");
fsck_err:
return ret;
}
-int bch2_inode_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_inode_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct bkey_s_c_inode inode = bkey_s_c_to_inode(k);
int ret = 0;
- bkey_fsck_err_on(INODE_STR_HASH(inode.v) >= BCH_STR_HASH_NR, c, err,
- inode_str_hash_invalid,
+ bkey_fsck_err_on(INODE_STR_HASH(inode.v) >= BCH_STR_HASH_NR,
+ c, inode_str_hash_invalid,
"invalid str hash type (%llu >= %u)",
INODE_STR_HASH(inode.v), BCH_STR_HASH_NR);
- ret = __bch2_inode_invalid(c, k, err);
+ ret = __bch2_inode_validate(c, k, flags);
fsck_err:
return ret;
}
-int bch2_inode_v2_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_inode_v2_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct bkey_s_c_inode_v2 inode = bkey_s_c_to_inode_v2(k);
int ret = 0;
- bkey_fsck_err_on(INODEv2_STR_HASH(inode.v) >= BCH_STR_HASH_NR, c, err,
- inode_str_hash_invalid,
+ bkey_fsck_err_on(INODEv2_STR_HASH(inode.v) >= BCH_STR_HASH_NR,
+ c, inode_str_hash_invalid,
"invalid str hash type (%llu >= %u)",
INODEv2_STR_HASH(inode.v), BCH_STR_HASH_NR);
- ret = __bch2_inode_invalid(c, k, err);
+ ret = __bch2_inode_validate(c, k, flags);
fsck_err:
return ret;
}
-int bch2_inode_v3_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_inode_v3_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct bkey_s_c_inode_v3 inode = bkey_s_c_to_inode_v3(k);
int ret = 0;
bkey_fsck_err_on(INODEv3_FIELDS_START(inode.v) < INODEv3_FIELDS_START_INITIAL ||
- INODEv3_FIELDS_START(inode.v) > bkey_val_u64s(inode.k), c, err,
- inode_v3_fields_start_bad,
+ INODEv3_FIELDS_START(inode.v) > bkey_val_u64s(inode.k),
+ c, inode_v3_fields_start_bad,
"invalid fields_start (got %llu, min %u max %zu)",
INODEv3_FIELDS_START(inode.v),
INODEv3_FIELDS_START_INITIAL,
bkey_val_u64s(inode.k));
- bkey_fsck_err_on(INODEv3_STR_HASH(inode.v) >= BCH_STR_HASH_NR, c, err,
- inode_str_hash_invalid,
+ bkey_fsck_err_on(INODEv3_STR_HASH(inode.v) >= BCH_STR_HASH_NR,
+ c, inode_str_hash_invalid,
"invalid str hash type (%llu >= %u)",
INODEv3_STR_HASH(inode.v), BCH_STR_HASH_NR);
- ret = __bch2_inode_invalid(c, k, err);
+ ret = __bch2_inode_validate(c, k, flags);
fsck_err:
return ret;
}
@@ -625,14 +623,13 @@ int bch2_trigger_inode(struct btree_trans *trans,
return 0;
}
-int bch2_inode_generation_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_inode_generation_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
int ret = 0;
- bkey_fsck_err_on(k.k->p.inode, c, err,
- inode_pos_inode_nonzero,
+ bkey_fsck_err_on(k.k->p.inode,
+ c, inode_pos_inode_nonzero,
"nonzero k.p.inode");
fsck_err:
return ret;
diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h
index da0e4a7..f1fcb4c 100644
--- a/fs/bcachefs/inode.h
+++ b/fs/bcachefs/inode.h
@@ -9,12 +9,12 @@
enum bch_validate_flags;
extern const char * const bch2_inode_opts[];
-int bch2_inode_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
-int bch2_inode_v2_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
-int bch2_inode_v3_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_inode_validate(struct bch_fs *, struct bkey_s_c,
+ enum bch_validate_flags);
+int bch2_inode_v2_validate(struct bch_fs *, struct bkey_s_c,
+ enum bch_validate_flags);
+int bch2_inode_v3_validate(struct bch_fs *, struct bkey_s_c,
+ enum bch_validate_flags);
void bch2_inode_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
int bch2_trigger_inode(struct btree_trans *, enum btree_id, unsigned,
@@ -22,21 +22,21 @@ int bch2_trigger_inode(struct btree_trans *, enum btree_id, unsigned,
enum btree_iter_update_trigger_flags);
#define bch2_bkey_ops_inode ((struct bkey_ops) { \
- .key_invalid = bch2_inode_invalid, \
+ .key_validate = bch2_inode_validate, \
.val_to_text = bch2_inode_to_text, \
.trigger = bch2_trigger_inode, \
.min_val_size = 16, \
})
#define bch2_bkey_ops_inode_v2 ((struct bkey_ops) { \
- .key_invalid = bch2_inode_v2_invalid, \
+ .key_validate = bch2_inode_v2_validate, \
.val_to_text = bch2_inode_to_text, \
.trigger = bch2_trigger_inode, \
.min_val_size = 32, \
})
#define bch2_bkey_ops_inode_v3 ((struct bkey_ops) { \
- .key_invalid = bch2_inode_v3_invalid, \
+ .key_validate = bch2_inode_v3_validate, \
.val_to_text = bch2_inode_to_text, \
.trigger = bch2_trigger_inode, \
.min_val_size = 48, \
@@ -49,12 +49,12 @@ static inline bool bkey_is_inode(const struct bkey *k)
k->type == KEY_TYPE_inode_v3;
}
-int bch2_inode_generation_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_inode_generation_validate(struct bch_fs *, struct bkey_s_c,
+ enum bch_validate_flags);
void bch2_inode_generation_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
#define bch2_bkey_ops_inode_generation ((struct bkey_ops) { \
- .key_invalid = bch2_inode_generation_invalid, \
+ .key_validate = bch2_inode_generation_validate, \
.val_to_text = bch2_inode_generation_to_text, \
.min_val_size = 8, \
})
diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index 649e3a0..f5f7db5 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -1260,7 +1260,7 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq)
}
if (!had_entries)
- j->last_empty_seq = cur_seq;
+ j->last_empty_seq = cur_seq - 1; /* to match j->seq */
spin_lock(&j->lock);
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index 7a833a3..7664b68 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -332,7 +332,6 @@ static int journal_validate_key(struct bch_fs *c,
{
int write = flags & BCH_VALIDATE_write;
void *next = vstruct_next(entry);
- struct printbuf buf = PRINTBUF;
int ret = 0;
if (journal_entry_err_on(!k->k.u64s,
@@ -368,34 +367,21 @@ static int journal_validate_key(struct bch_fs *c,
bch2_bkey_compat(level, btree_id, version, big_endian,
write, NULL, bkey_to_packed(k));
- if (bch2_bkey_invalid(c, bkey_i_to_s_c(k),
- __btree_node_type(level, btree_id), write, &buf)) {
- printbuf_reset(&buf);
- journal_entry_err_msg(&buf, version, jset, entry);
- prt_newline(&buf);
- printbuf_indent_add(&buf, 2);
-
- bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(k));
- prt_newline(&buf);
- bch2_bkey_invalid(c, bkey_i_to_s_c(k),
- __btree_node_type(level, btree_id), write, &buf);
-
- mustfix_fsck_err(c, journal_entry_bkey_invalid,
- "%s", buf.buf);
-
+ ret = bch2_bkey_validate(c, bkey_i_to_s_c(k),
+ __btree_node_type(level, btree_id), write);
+ if (ret == -BCH_ERR_fsck_delete_bkey) {
le16_add_cpu(&entry->u64s, -((u16) k->k.u64s));
memmove(k, bkey_next(k), next - (void *) bkey_next(k));
journal_entry_null_range(vstruct_next(entry), next);
-
- printbuf_exit(&buf);
return FSCK_DELETED_KEY;
}
+ if (ret)
+ goto fsck_err;
if (write)
bch2_bkey_compat(level, btree_id, version, big_endian,
write, NULL, bkey_to_packed(k));
fsck_err:
- printbuf_exit(&buf);
return ret;
}
diff --git a/fs/bcachefs/journal_sb.c b/fs/bcachefs/journal_sb.c
index db80e50..62b910f 100644
--- a/fs/bcachefs/journal_sb.c
+++ b/fs/bcachefs/journal_sb.c
@@ -104,6 +104,7 @@ static int bch2_sb_journal_v2_validate(struct bch_sb *sb, struct bch_sb_field *f
struct bch_sb_field_journal_v2 *journal = field_to_type(f, journal_v2);
struct bch_member m = bch2_sb_member_get(sb, sb->dev_idx);
int ret = -BCH_ERR_invalid_sb_journal;
+ u64 sum = 0;
unsigned nr;
unsigned i;
struct u64_range *b;
@@ -119,6 +120,15 @@ static int bch2_sb_journal_v2_validate(struct bch_sb *sb, struct bch_sb_field *f
for (i = 0; i < nr; i++) {
b[i].start = le64_to_cpu(journal->d[i].start);
b[i].end = b[i].start + le64_to_cpu(journal->d[i].nr);
+
+ if (b[i].end <= b[i].start) {
+ prt_printf(err, "journal buckets entry with bad nr: %llu+%llu",
+ le64_to_cpu(journal->d[i].start),
+ le64_to_cpu(journal->d[i].nr));
+ goto err;
+ }
+
+ sum += le64_to_cpu(journal->d[i].nr);
}
sort(b, nr, sizeof(*b), u64_range_cmp, NULL);
@@ -148,6 +158,11 @@ static int bch2_sb_journal_v2_validate(struct bch_sb *sb, struct bch_sb_field *f
}
}
+ if (sum > UINT_MAX) {
+ prt_printf(err, "too many journal buckets: %llu > %u", sum, UINT_MAX);
+ goto err;
+ }
+
ret = 0;
err:
kfree(b);
diff --git a/fs/bcachefs/lru.c b/fs/bcachefs/lru.c
index 83b1586..96f2f4f 100644
--- a/fs/bcachefs/lru.c
+++ b/fs/bcachefs/lru.c
@@ -10,14 +10,13 @@
#include "recovery.h"
/* KEY_TYPE_lru is obsolete: */
-int bch2_lru_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_lru_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
int ret = 0;
- bkey_fsck_err_on(!lru_pos_time(k.k->p), c, err,
- lru_entry_at_time_0,
+ bkey_fsck_err_on(!lru_pos_time(k.k->p),
+ c, lru_entry_at_time_0,
"lru entry at time=0");
fsck_err:
return ret;
diff --git a/fs/bcachefs/lru.h b/fs/bcachefs/lru.h
index 5bd8974..e6a7d82 100644
--- a/fs/bcachefs/lru.h
+++ b/fs/bcachefs/lru.h
@@ -33,14 +33,13 @@ static inline enum bch_lru_type lru_type(struct bkey_s_c l)
return BCH_LRU_read;
}
-int bch2_lru_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_lru_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
void bch2_lru_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
void bch2_lru_pos_to_text(struct printbuf *, struct bpos);
#define bch2_bkey_ops_lru ((struct bkey_ops) { \
- .key_invalid = bch2_lru_invalid, \
+ .key_validate = bch2_lru_validate, \
.val_to_text = bch2_lru_to_text, \
.min_val_size = 8, \
})
diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c
index deef4f0..d86565b 100644
--- a/fs/bcachefs/movinggc.c
+++ b/fs/bcachefs/movinggc.c
@@ -383,7 +383,7 @@ static int bch2_copygc_thread(void *arg)
if (min_member_capacity == U64_MAX)
min_member_capacity = 128 * 2048;
- bch2_trans_unlock_long(ctxt.trans);
+ move_buckets_wait(&ctxt, buckets, true);
bch2_kthread_io_clock_wait(clock, last + (min_member_capacity >> 6),
MAX_SCHEDULE_TIMEOUT);
}
diff --git a/fs/bcachefs/quota.c b/fs/bcachefs/quota.c
index a0cca8b..c32a05e 100644
--- a/fs/bcachefs/quota.c
+++ b/fs/bcachefs/quota.c
@@ -59,13 +59,13 @@ const struct bch_sb_field_ops bch_sb_field_ops_quota = {
.to_text = bch2_sb_quota_to_text,
};
-int bch2_quota_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags, struct printbuf *err)
+int bch2_quota_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
int ret = 0;
- bkey_fsck_err_on(k.k->p.inode >= QTYP_NR, c, err,
- quota_type_invalid,
+ bkey_fsck_err_on(k.k->p.inode >= QTYP_NR,
+ c, quota_type_invalid,
"invalid quota type (%llu >= %u)",
k.k->p.inode, QTYP_NR);
fsck_err:
diff --git a/fs/bcachefs/quota.h b/fs/bcachefs/quota.h
index 02d37a3..a62abcc 100644
--- a/fs/bcachefs/quota.h
+++ b/fs/bcachefs/quota.h
@@ -8,12 +8,11 @@
enum bch_validate_flags;
extern const struct bch_sb_field_ops bch_sb_field_ops_quota;
-int bch2_quota_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_quota_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
void bch2_quota_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
#define bch2_bkey_ops_quota ((struct bkey_ops) { \
- .key_invalid = bch2_quota_invalid, \
+ .key_validate = bch2_quota_validate, \
.val_to_text = bch2_quota_to_text, \
.min_val_size = 32, \
})
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index d89eb43c..36de1c6 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -241,7 +241,13 @@ static int journal_sort_seq_cmp(const void *_l, const void *_r)
const struct journal_key *l = *((const struct journal_key **)_l);
const struct journal_key *r = *((const struct journal_key **)_r);
- return cmp_int(l->journal_seq, r->journal_seq);
+ /*
+ * Map 0 to U64_MAX, so that keys with journal_seq === 0 come last
+ *
+ * journal_seq == 0 means that the key comes from early repair, and
+ * should be inserted last so as to avoid overflowing the journal
+ */
+ return cmp_int(l->journal_seq - 1, r->journal_seq - 1);
}
int bch2_journal_replay(struct bch_fs *c)
@@ -322,6 +328,7 @@ int bch2_journal_replay(struct bch_fs *c)
}
}
+ bch2_trans_unlock_long(trans);
/*
* Now, replay any remaining keys in the order in which they appear in
* the journal, unpinning those journal entries as we go:
diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c
index 5f92715..e59c0ab 100644
--- a/fs/bcachefs/reflink.c
+++ b/fs/bcachefs/reflink.c
@@ -29,15 +29,14 @@ static inline unsigned bkey_type_to_indirect(const struct bkey *k)
/* reflink pointers */
-int bch2_reflink_p_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_reflink_p_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k);
int ret = 0;
bkey_fsck_err_on(le64_to_cpu(p.v->idx) < le32_to_cpu(p.v->front_pad),
- c, err, reflink_p_front_pad_bad,
+ c, reflink_p_front_pad_bad,
"idx < front_pad (%llu < %u)",
le64_to_cpu(p.v->idx), le32_to_cpu(p.v->front_pad));
fsck_err:
@@ -256,11 +255,10 @@ int bch2_trigger_reflink_p(struct btree_trans *trans,
/* indirect extents */
-int bch2_reflink_v_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_reflink_v_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
- return bch2_bkey_ptrs_invalid(c, k, flags, err);
+ return bch2_bkey_ptrs_validate(c, k, flags);
}
void bch2_reflink_v_to_text(struct printbuf *out, struct bch_fs *c,
@@ -311,9 +309,8 @@ int bch2_trigger_reflink_v(struct btree_trans *trans,
/* indirect inline data */
-int bch2_indirect_inline_data_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_indirect_inline_data_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
return 0;
}
diff --git a/fs/bcachefs/reflink.h b/fs/bcachefs/reflink.h
index e894f3a..51afe11 100644
--- a/fs/bcachefs/reflink.h
+++ b/fs/bcachefs/reflink.h
@@ -4,41 +4,37 @@
enum bch_validate_flags;
-int bch2_reflink_p_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
-void bch2_reflink_p_to_text(struct printbuf *, struct bch_fs *,
- struct bkey_s_c);
+int bch2_reflink_p_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
+void bch2_reflink_p_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
bool bch2_reflink_p_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c);
int bch2_trigger_reflink_p(struct btree_trans *, enum btree_id, unsigned,
struct bkey_s_c, struct bkey_s,
enum btree_iter_update_trigger_flags);
#define bch2_bkey_ops_reflink_p ((struct bkey_ops) { \
- .key_invalid = bch2_reflink_p_invalid, \
+ .key_validate = bch2_reflink_p_validate, \
.val_to_text = bch2_reflink_p_to_text, \
.key_merge = bch2_reflink_p_merge, \
.trigger = bch2_trigger_reflink_p, \
.min_val_size = 16, \
})
-int bch2_reflink_v_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
-void bch2_reflink_v_to_text(struct printbuf *, struct bch_fs *,
- struct bkey_s_c);
+int bch2_reflink_v_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
+void bch2_reflink_v_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
int bch2_trigger_reflink_v(struct btree_trans *, enum btree_id, unsigned,
struct bkey_s_c, struct bkey_s,
enum btree_iter_update_trigger_flags);
#define bch2_bkey_ops_reflink_v ((struct bkey_ops) { \
- .key_invalid = bch2_reflink_v_invalid, \
+ .key_validate = bch2_reflink_v_validate, \
.val_to_text = bch2_reflink_v_to_text, \
.swab = bch2_ptr_swab, \
.trigger = bch2_trigger_reflink_v, \
.min_val_size = 8, \
})
-int bch2_indirect_inline_data_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_indirect_inline_data_validate(struct bch_fs *, struct bkey_s_c,
+ enum bch_validate_flags);
void bch2_indirect_inline_data_to_text(struct printbuf *,
struct bch_fs *, struct bkey_s_c);
int bch2_trigger_indirect_inline_data(struct btree_trans *,
@@ -47,7 +43,7 @@ int bch2_trigger_indirect_inline_data(struct btree_trans *,
enum btree_iter_update_trigger_flags);
#define bch2_bkey_ops_indirect_inline_data ((struct bkey_ops) { \
- .key_invalid = bch2_indirect_inline_data_invalid, \
+ .key_validate = bch2_indirect_inline_data_validate, \
.val_to_text = bch2_indirect_inline_data_to_text, \
.trigger = bch2_trigger_indirect_inline_data, \
.min_val_size = 8, \
diff --git a/fs/bcachefs/replicas.c b/fs/bcachefs/replicas.c
index 1223b71..12b1d28 100644
--- a/fs/bcachefs/replicas.c
+++ b/fs/bcachefs/replicas.c
@@ -451,7 +451,8 @@ int bch2_replicas_gc2(struct bch_fs *c)
.type = BCH_DISK_ACCOUNTING_replicas,
};
- memcpy(&k.replicas, e, replicas_entry_bytes(e));
+ unsafe_memcpy(&k.replicas, e, replicas_entry_bytes(e),
+ "embedded variable length struct");
struct bpos p = disk_accounting_pos_to_bpos(&k);
diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c
index 6c4469f..c7e4cdd 100644
--- a/fs/bcachefs/sb-downgrade.c
+++ b/fs/bcachefs/sb-downgrade.c
@@ -72,7 +72,13 @@
BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0, \
BCH_FSCK_ERR_accounting_key_replicas_nr_required_bad, \
BCH_FSCK_ERR_accounting_key_replicas_devs_unsorted, \
- BCH_FSCK_ERR_accounting_key_junk_at_end)
+ BCH_FSCK_ERR_accounting_key_junk_at_end) \
+ x(disk_accounting_inum, \
+ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \
+ BCH_FSCK_ERR_accounting_mismatch) \
+ x(rebalance_work_acct_fix, \
+ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \
+ BCH_FSCK_ERR_accounting_mismatch)
#define DOWNGRADE_TABLE() \
x(bucket_stripe_sectors, \
@@ -104,7 +110,11 @@
BCH_FSCK_ERR_fs_usage_nr_inodes_wrong, \
BCH_FSCK_ERR_fs_usage_persistent_reserved_wrong, \
BCH_FSCK_ERR_fs_usage_replicas_wrong, \
- BCH_FSCK_ERR_bkey_version_in_future)
+ BCH_FSCK_ERR_accounting_replicas_not_marked, \
+ BCH_FSCK_ERR_bkey_version_in_future) \
+ x(rebalance_work_acct_fix, \
+ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \
+ BCH_FSCK_ERR_accounting_mismatch)
struct upgrade_downgrade_entry {
u64 recovery_passes;
diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index d3a4986..f0c1470 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -23,7 +23,7 @@ enum bch_fsck_flags {
x(jset_past_bucket_end, 9, 0) \
x(jset_seq_blacklisted, 10, 0) \
x(journal_entries_missing, 11, 0) \
- x(journal_entry_replicas_not_marked, 12, 0) \
+ x(journal_entry_replicas_not_marked, 12, FSCK_AUTOFIX) \
x(journal_entry_past_jset_end, 13, 0) \
x(journal_entry_replicas_data_mismatch, 14, 0) \
x(journal_entry_bkey_u64s_0, 15, 0) \
@@ -288,10 +288,10 @@ enum bch_fsck_flags {
x(invalid_btree_id, 274, 0) \
x(alloc_key_io_time_bad, 275, 0) \
x(alloc_key_fragmentation_lru_wrong, 276, FSCK_AUTOFIX) \
- x(accounting_key_junk_at_end, 277, 0) \
- x(accounting_key_replicas_nr_devs_0, 278, 0) \
- x(accounting_key_replicas_nr_required_bad, 279, 0) \
- x(accounting_key_replicas_devs_unsorted, 280, 0) \
+ x(accounting_key_junk_at_end, 277, FSCK_AUTOFIX) \
+ x(accounting_key_replicas_nr_devs_0, 278, FSCK_AUTOFIX) \
+ x(accounting_key_replicas_nr_required_bad, 279, FSCK_AUTOFIX) \
+ x(accounting_key_replicas_devs_unsorted, 280, FSCK_AUTOFIX) \
enum bch_sb_error_id {
#define x(t, n, ...) BCH_FSCK_ERR_##t = n,
diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index 96744b1..8b18a9b 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -31,15 +31,14 @@ void bch2_snapshot_tree_to_text(struct printbuf *out, struct bch_fs *c,
le32_to_cpu(t.v->root_snapshot));
}
-int bch2_snapshot_tree_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_snapshot_tree_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
int ret = 0;
bkey_fsck_err_on(bkey_gt(k.k->p, POS(0, U32_MAX)) ||
- bkey_lt(k.k->p, POS(0, 1)), c, err,
- snapshot_tree_pos_bad,
+ bkey_lt(k.k->p, POS(0, 1)),
+ c, snapshot_tree_pos_bad,
"bad pos");
fsck_err:
return ret;
@@ -225,55 +224,54 @@ void bch2_snapshot_to_text(struct printbuf *out, struct bch_fs *c,
le32_to_cpu(s.v->skip[2]));
}
-int bch2_snapshot_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_snapshot_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct bkey_s_c_snapshot s;
u32 i, id;
int ret = 0;
bkey_fsck_err_on(bkey_gt(k.k->p, POS(0, U32_MAX)) ||
- bkey_lt(k.k->p, POS(0, 1)), c, err,
- snapshot_pos_bad,
+ bkey_lt(k.k->p, POS(0, 1)),
+ c, snapshot_pos_bad,
"bad pos");
s = bkey_s_c_to_snapshot(k);
id = le32_to_cpu(s.v->parent);
- bkey_fsck_err_on(id && id <= k.k->p.offset, c, err,
- snapshot_parent_bad,
+ bkey_fsck_err_on(id && id <= k.k->p.offset,
+ c, snapshot_parent_bad,
"bad parent node (%u <= %llu)",
id, k.k->p.offset);
- bkey_fsck_err_on(le32_to_cpu(s.v->children[0]) < le32_to_cpu(s.v->children[1]), c, err,
- snapshot_children_not_normalized,
+ bkey_fsck_err_on(le32_to_cpu(s.v->children[0]) < le32_to_cpu(s.v->children[1]),
+ c, snapshot_children_not_normalized,
"children not normalized");
- bkey_fsck_err_on(s.v->children[0] && s.v->children[0] == s.v->children[1], c, err,
- snapshot_child_duplicate,
+ bkey_fsck_err_on(s.v->children[0] && s.v->children[0] == s.v->children[1],
+ c, snapshot_child_duplicate,
"duplicate child nodes");
for (i = 0; i < 2; i++) {
id = le32_to_cpu(s.v->children[i]);
- bkey_fsck_err_on(id >= k.k->p.offset, c, err,
- snapshot_child_bad,
+ bkey_fsck_err_on(id >= k.k->p.offset,
+ c, snapshot_child_bad,
"bad child node (%u >= %llu)",
id, k.k->p.offset);
}
if (bkey_val_bytes(k.k) > offsetof(struct bch_snapshot, skip)) {
bkey_fsck_err_on(le32_to_cpu(s.v->skip[0]) > le32_to_cpu(s.v->skip[1]) ||
- le32_to_cpu(s.v->skip[1]) > le32_to_cpu(s.v->skip[2]), c, err,
- snapshot_skiplist_not_normalized,
+ le32_to_cpu(s.v->skip[1]) > le32_to_cpu(s.v->skip[2]),
+ c, snapshot_skiplist_not_normalized,
"skiplist not normalized");
for (i = 0; i < ARRAY_SIZE(s.v->skip); i++) {
id = le32_to_cpu(s.v->skip[i]);
- bkey_fsck_err_on(id && id < le32_to_cpu(s.v->parent), c, err,
- snapshot_skiplist_bad,
+ bkey_fsck_err_on(id && id < le32_to_cpu(s.v->parent),
+ c, snapshot_skiplist_bad,
"bad skiplist node %u", id);
}
}
diff --git a/fs/bcachefs/snapshot.h b/fs/bcachefs/snapshot.h
index 31b0ee0..eb5ef64 100644
--- a/fs/bcachefs/snapshot.h
+++ b/fs/bcachefs/snapshot.h
@@ -5,11 +5,11 @@
enum bch_validate_flags;
void bch2_snapshot_tree_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
-int bch2_snapshot_tree_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_snapshot_tree_validate(struct bch_fs *, struct bkey_s_c,
+ enum bch_validate_flags);
#define bch2_bkey_ops_snapshot_tree ((struct bkey_ops) { \
- .key_invalid = bch2_snapshot_tree_invalid, \
+ .key_validate = bch2_snapshot_tree_validate, \
.val_to_text = bch2_snapshot_tree_to_text, \
.min_val_size = 8, \
})
@@ -19,14 +19,13 @@ struct bkey_i_snapshot_tree *__bch2_snapshot_tree_create(struct btree_trans *);
int bch2_snapshot_tree_lookup(struct btree_trans *, u32, struct bch_snapshot_tree *);
void bch2_snapshot_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
-int bch2_snapshot_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_snapshot_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
int bch2_mark_snapshot(struct btree_trans *, enum btree_id, unsigned,
struct bkey_s_c, struct bkey_s,
enum btree_iter_update_trigger_flags);
#define bch2_bkey_ops_snapshot ((struct bkey_ops) { \
- .key_invalid = bch2_snapshot_invalid, \
+ .key_validate = bch2_snapshot_validate, \
.val_to_text = bch2_snapshot_to_text, \
.trigger = bch2_mark_snapshot, \
.min_val_size = 24, \
diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c
index f56720b..dbe834c 100644
--- a/fs/bcachefs/subvolume.c
+++ b/fs/bcachefs/subvolume.c
@@ -207,23 +207,23 @@ int bch2_check_subvol_children(struct bch_fs *c)
/* Subvolumes: */
-int bch2_subvolume_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags, struct printbuf *err)
+int bch2_subvolume_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct bkey_s_c_subvolume subvol = bkey_s_c_to_subvolume(k);
int ret = 0;
bkey_fsck_err_on(bkey_lt(k.k->p, SUBVOL_POS_MIN) ||
- bkey_gt(k.k->p, SUBVOL_POS_MAX), c, err,
- subvol_pos_bad,
+ bkey_gt(k.k->p, SUBVOL_POS_MAX),
+ c, subvol_pos_bad,
"invalid pos");
- bkey_fsck_err_on(!subvol.v->snapshot, c, err,
- subvol_snapshot_bad,
+ bkey_fsck_err_on(!subvol.v->snapshot,
+ c, subvol_snapshot_bad,
"invalid snapshot");
- bkey_fsck_err_on(!subvol.v->inode, c, err,
- subvol_inode_bad,
+ bkey_fsck_err_on(!subvol.v->inode,
+ c, subvol_inode_bad,
"invalid inode");
fsck_err:
return ret;
diff --git a/fs/bcachefs/subvolume.h b/fs/bcachefs/subvolume.h
index afa5e87..a8299ba 100644
--- a/fs/bcachefs/subvolume.h
+++ b/fs/bcachefs/subvolume.h
@@ -10,15 +10,14 @@ enum bch_validate_flags;
int bch2_check_subvols(struct bch_fs *);
int bch2_check_subvol_children(struct bch_fs *);
-int bch2_subvolume_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_subvolume_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
void bch2_subvolume_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
int bch2_subvolume_trigger(struct btree_trans *, enum btree_id, unsigned,
struct bkey_s_c, struct bkey_s,
enum btree_iter_update_trigger_flags);
#define bch2_bkey_ops_subvolume ((struct bkey_ops) { \
- .key_invalid = bch2_subvolume_invalid, \
+ .key_validate = bch2_subvolume_validate, \
.val_to_text = bch2_subvolume_to_text, \
.trigger = bch2_subvolume_trigger, \
.min_val_size = 16, \
diff --git a/fs/bcachefs/trace.c b/fs/bcachefs/trace.c
index dc48b52..dfad1d0 100644
--- a/fs/bcachefs/trace.c
+++ b/fs/bcachefs/trace.c
@@ -4,6 +4,7 @@
#include "buckets.h"
#include "btree_cache.h"
#include "btree_iter.h"
+#include "btree_key_cache.h"
#include "btree_locking.h"
#include "btree_update_interior.h"
#include "keylist.h"
diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h
index d0e6b9d..c62f003 100644
--- a/fs/bcachefs/trace.h
+++ b/fs/bcachefs/trace.h
@@ -988,10 +988,33 @@ TRACE_EVENT(trans_restart_split_race,
__entry->u64s_remaining)
);
-DEFINE_EVENT(transaction_event, trans_blocked_journal_reclaim,
+TRACE_EVENT(trans_blocked_journal_reclaim,
TP_PROTO(struct btree_trans *trans,
unsigned long caller_ip),
- TP_ARGS(trans, caller_ip)
+ TP_ARGS(trans, caller_ip),
+
+ TP_STRUCT__entry(
+ __array(char, trans_fn, 32 )
+ __field(unsigned long, caller_ip )
+
+ __field(unsigned long, key_cache_nr_keys )
+ __field(unsigned long, key_cache_nr_dirty )
+ __field(long, must_wait )
+ ),
+
+ TP_fast_assign(
+ strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn));
+ __entry->caller_ip = caller_ip;
+ __entry->key_cache_nr_keys = atomic_long_read(&trans->c->btree_key_cache.nr_keys);
+ __entry->key_cache_nr_dirty = atomic_long_read(&trans->c->btree_key_cache.nr_dirty);
+ __entry->must_wait = __bch2_btree_key_cache_must_wait(trans->c);
+ ),
+
+ TP_printk("%s %pS key cache keys %lu dirty %lu must_wait %li",
+ __entry->trans_fn, (void *) __entry->caller_ip,
+ __entry->key_cache_nr_keys,
+ __entry->key_cache_nr_dirty,
+ __entry->must_wait)
);
TRACE_EVENT(trans_restart_journal_preres_get,
diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c
index 138320e..1b85544 100644
--- a/fs/bcachefs/util.c
+++ b/fs/bcachefs/util.c
@@ -416,7 +416,6 @@ void bch2_time_stats_to_text(struct printbuf *out, struct bch2_time_stats *stats
printbuf_tabstop_push(out, TABSTOP_SIZE + 2);
prt_printf(out, "\tsince mount\r\trecent\r\n");
- prt_printf(out, "recent");
printbuf_tabstops_reset(out);
printbuf_tabstop_push(out, out->indent + 20);
diff --git a/fs/bcachefs/xattr.c b/fs/bcachefs/xattr.c
index c11bf6d..331f944 100644
--- a/fs/bcachefs/xattr.c
+++ b/fs/bcachefs/xattr.c
@@ -70,17 +70,16 @@ const struct bch_hash_desc bch2_xattr_hash_desc = {
.cmp_bkey = xattr_cmp_bkey,
};
-int bch2_xattr_invalid(struct bch_fs *c, struct bkey_s_c k,
- enum bch_validate_flags flags,
- struct printbuf *err)
+int bch2_xattr_validate(struct bch_fs *c, struct bkey_s_c k,
+ enum bch_validate_flags flags)
{
struct bkey_s_c_xattr xattr = bkey_s_c_to_xattr(k);
unsigned val_u64s = xattr_val_u64s(xattr.v->x_name_len,
le16_to_cpu(xattr.v->x_val_len));
int ret = 0;
- bkey_fsck_err_on(bkey_val_u64s(k.k) < val_u64s, c, err,
- xattr_val_size_too_small,
+ bkey_fsck_err_on(bkey_val_u64s(k.k) < val_u64s,
+ c, xattr_val_size_too_small,
"value too small (%zu < %u)",
bkey_val_u64s(k.k), val_u64s);
@@ -88,17 +87,17 @@ int bch2_xattr_invalid(struct bch_fs *c, struct bkey_s_c k,
val_u64s = xattr_val_u64s(xattr.v->x_name_len,
le16_to_cpu(xattr.v->x_val_len) + 4);
- bkey_fsck_err_on(bkey_val_u64s(k.k) > val_u64s, c, err,
- xattr_val_size_too_big,
+ bkey_fsck_err_on(bkey_val_u64s(k.k) > val_u64s,
+ c, xattr_val_size_too_big,
"value too big (%zu > %u)",
bkey_val_u64s(k.k), val_u64s);
- bkey_fsck_err_on(!bch2_xattr_type_to_handler(xattr.v->x_type), c, err,
- xattr_invalid_type,
+ bkey_fsck_err_on(!bch2_xattr_type_to_handler(xattr.v->x_type),
+ c, xattr_invalid_type,
"invalid type (%u)", xattr.v->x_type);
- bkey_fsck_err_on(memchr(xattr.v->x_name, '\0', xattr.v->x_name_len), c, err,
- xattr_name_invalid_chars,
+ bkey_fsck_err_on(memchr(xattr.v->x_name, '\0', xattr.v->x_name_len),
+ c, xattr_name_invalid_chars,
"xattr name has invalid characters");
fsck_err:
return ret;
@@ -613,10 +612,20 @@ static int bch2_xattr_bcachefs_get_effective(
name, buffer, size, true);
}
+/* Noop - xattrs in the bcachefs_effective namespace are inherited */
+static int bch2_xattr_bcachefs_set_effective(const struct xattr_handler *handler,
+ struct mnt_idmap *idmap,
+ struct dentry *dentry, struct inode *vinode,
+ const char *name, const void *value,
+ size_t size, int flags)
+{
+ return 0;
+}
+
static const struct xattr_handler bch_xattr_bcachefs_effective_handler = {
.prefix = "bcachefs_effective.",
.get = bch2_xattr_bcachefs_get_effective,
- .set = bch2_xattr_bcachefs_set,
+ .set = bch2_xattr_bcachefs_set_effective,
};
#endif /* NO_BCACHEFS_FS */
diff --git a/fs/bcachefs/xattr.h b/fs/bcachefs/xattr.h
index 1574b9e..c188a5a 100644
--- a/fs/bcachefs/xattr.h
+++ b/fs/bcachefs/xattr.h
@@ -6,12 +6,11 @@
extern const struct bch_hash_desc bch2_xattr_hash_desc;
-int bch2_xattr_invalid(struct bch_fs *, struct bkey_s_c,
- enum bch_validate_flags, struct printbuf *);
+int bch2_xattr_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
void bch2_xattr_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
#define bch2_bkey_ops_xattr ((struct bkey_ops) { \
- .key_invalid = bch2_xattr_invalid, \
+ .key_validate = bch2_xattr_validate, \
.val_to_text = bch2_xattr_to_text, \
.min_val_size = 8, \
})
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 28a3439..4fe5bb9 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -589,6 +589,9 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
if (bprm->have_execfd)
nitems++;
+#ifdef ELF_HWCAP2
+ nitems++;
+#endif
csp = sp;
sp -= nitems * 2 * sizeof(unsigned long);
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index c26545d..cd6d5bb 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -72,8 +72,10 @@
#ifdef CONFIG_BINFMT_FLAT_NO_DATA_START_OFFSET
#define DATA_START_OFFSET_WORDS (0)
+#define MAX_SHARED_LIBS_UPDATE (0)
#else
#define DATA_START_OFFSET_WORDS (MAX_SHARED_LIBS)
+#define MAX_SHARED_LIBS_UPDATE (MAX_SHARED_LIBS)
#endif
struct lib_info {
@@ -880,7 +882,7 @@ static int load_flat_binary(struct linux_binprm *bprm)
return res;
/* Update data segment pointers for all libraries */
- for (i = 0; i < MAX_SHARED_LIBS; i++) {
+ for (i = 0; i < MAX_SHARED_LIBS_UPDATE; i++) {
if (!libinfo.lib_list[i].loaded)
continue;
for (j = 0; j < MAX_SHARED_LIBS; j++) {
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index f04d931..b4e31ae 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -668,7 +668,6 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
{
struct btrfs_inode *inode = bbio->inode;
struct btrfs_fs_info *fs_info = bbio->fs_info;
- struct btrfs_bio *orig_bbio = bbio;
struct bio *bio = &bbio->bio;
u64 logical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
u64 length = bio->bi_iter.bi_size;
@@ -706,7 +705,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
bbio->saved_iter = bio->bi_iter;
ret = btrfs_lookup_bio_sums(bbio);
if (ret)
- goto fail_put_bio;
+ goto fail;
}
if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
@@ -740,13 +739,13 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
ret = btrfs_bio_csum(bbio);
if (ret)
- goto fail_put_bio;
+ goto fail;
} else if (use_append ||
(btrfs_is_zoned(fs_info) && inode &&
inode->flags & BTRFS_INODE_NODATASUM)) {
ret = btrfs_alloc_dummy_sum(bbio);
if (ret)
- goto fail_put_bio;
+ goto fail;
}
}
@@ -754,12 +753,23 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
done:
return map_length == length;
-fail_put_bio:
- if (map_length < length)
- btrfs_cleanup_bio(bbio);
fail:
btrfs_bio_counter_dec(fs_info);
- btrfs_bio_end_io(orig_bbio, ret);
+ /*
+ * We have split the original bbio, now we have to end both the current
+ * @bbio and remaining one, as the remaining one will never be submitted.
+ */
+ if (map_length < length) {
+ struct btrfs_bio *remaining = bbio->private;
+
+ ASSERT(bbio->bio.bi_pool == &btrfs_clone_bioset);
+ ASSERT(remaining);
+
+ remaining->bio.bi_status = ret;
+ btrfs_orig_bbio_end_io(remaining);
+ }
+ bbio->bio.bi_status = ret;
+ btrfs_orig_bbio_end_io(bbio);
/* Do not submit another chunk */
return true;
}
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 2ac9296..06a9e05 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -1134,6 +1134,73 @@ btrfs_find_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs, u64 byt
return find_ref_head(delayed_refs, bytenr, false);
}
+static int find_comp(struct btrfs_delayed_ref_node *entry, u64 root, u64 parent)
+{
+ int type = parent ? BTRFS_SHARED_BLOCK_REF_KEY : BTRFS_TREE_BLOCK_REF_KEY;
+
+ if (type < entry->type)
+ return -1;
+ if (type > entry->type)
+ return 1;
+
+ if (type == BTRFS_TREE_BLOCK_REF_KEY) {
+ if (root < entry->ref_root)
+ return -1;
+ if (root > entry->ref_root)
+ return 1;
+ } else {
+ if (parent < entry->parent)
+ return -1;
+ if (parent > entry->parent)
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * Check to see if a given root/parent reference is attached to the head. This
+ * only checks for BTRFS_ADD_DELAYED_REF references that match, as that
+ * indicates the reference exists for the given root or parent. This is for
+ * tree blocks only.
+ *
+ * @head: the head of the bytenr we're searching.
+ * @root: the root objectid of the reference if it is a normal reference.
+ * @parent: the parent if this is a shared backref.
+ */
+bool btrfs_find_delayed_tree_ref(struct btrfs_delayed_ref_head *head,
+ u64 root, u64 parent)
+{
+ struct rb_node *node;
+ bool found = false;
+
+ lockdep_assert_held(&head->mutex);
+
+ spin_lock(&head->lock);
+ node = head->ref_tree.rb_root.rb_node;
+ while (node) {
+ struct btrfs_delayed_ref_node *entry;
+ int ret;
+
+ entry = rb_entry(node, struct btrfs_delayed_ref_node, ref_node);
+ ret = find_comp(entry, root, parent);
+ if (ret < 0) {
+ node = node->rb_left;
+ } else if (ret > 0) {
+ node = node->rb_right;
+ } else {
+ /*
+ * We only want to count ADD actions, as drops mean the
+ * ref doesn't exist.
+ */
+ if (entry->action == BTRFS_ADD_DELAYED_REF)
+ found = true;
+ break;
+ }
+ }
+ spin_unlock(&head->lock);
+ return found;
+}
+
void __cold btrfs_delayed_ref_exit(void)
{
kmem_cache_destroy(btrfs_delayed_ref_head_cachep);
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index ef15e99..05f634e 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -389,6 +389,8 @@ void btrfs_dec_delayed_refs_rsv_bg_updates(struct btrfs_fs_info *fs_info);
int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info,
enum btrfs_reserve_flush_enum flush);
bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info);
+bool btrfs_find_delayed_tree_ref(struct btrfs_delayed_ref_head *head,
+ u64 root, u64 parent);
static inline u64 btrfs_delayed_ref_owner(struct btrfs_delayed_ref_node *node)
{
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index ff9f0d41..feec49e 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5472,23 +5472,62 @@ static int check_ref_exists(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 bytenr, u64 parent,
int level)
{
+ struct btrfs_delayed_ref_root *delayed_refs;
+ struct btrfs_delayed_ref_head *head;
struct btrfs_path *path;
struct btrfs_extent_inline_ref *iref;
int ret;
+ bool exists = false;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
-
+again:
ret = lookup_extent_backref(trans, path, &iref, bytenr,
root->fs_info->nodesize, parent,
btrfs_root_id(root), level, 0);
+ if (ret != -ENOENT) {
+ /*
+ * If we get 0 then we found our reference, return 1, else
+ * return the error if it's not -ENOENT;
+ */
+ btrfs_free_path(path);
+ return (ret < 0 ) ? ret : 1;
+ }
+
+ /*
+ * We could have a delayed ref with this reference, so look it up while
+ * we're holding the path open to make sure we don't race with the
+ * delayed ref running.
+ */
+ delayed_refs = &trans->transaction->delayed_refs;
+ spin_lock(&delayed_refs->lock);
+ head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
+ if (!head)
+ goto out;
+ if (!mutex_trylock(&head->mutex)) {
+ /*
+ * We're contended, means that the delayed ref is running, get a
+ * reference and wait for the ref head to be complete and then
+ * try again.
+ */
+ refcount_inc(&head->refs);
+ spin_unlock(&delayed_refs->lock);
+
+ btrfs_release_path(path);
+
+ mutex_lock(&head->mutex);
+ mutex_unlock(&head->mutex);
+ btrfs_put_delayed_ref_head(head);
+ goto again;
+ }
+
+ exists = btrfs_find_delayed_tree_ref(head, root->root_key.objectid, parent);
+ mutex_unlock(&head->mutex);
+out:
+ spin_unlock(&delayed_refs->lock);
btrfs_free_path(path);
- if (ret == -ENOENT)
- return 0;
- if (ret < 0)
- return ret;
- return 1;
+ return exists ? 1 : 0;
}
/*
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index aa7f814..c73cd4f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1496,6 +1496,13 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
free_extent_map(em);
em = NULL;
+ /*
+ * Although the PageDirty bit might be cleared before entering
+ * this function, subpage dirty bit is not cleared.
+ * So clear subpage dirty bit here so next time we won't submit
+ * page for range already written to disk.
+ */
+ btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, iosize);
btrfs_set_range_writeback(inode, cur, cur + iosize - 1);
if (!PageWriteback(page)) {
btrfs_err(inode->root->fs_info,
@@ -1503,13 +1510,6 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
page->index, cur, end);
}
- /*
- * Although the PageDirty bit is cleared before entering this
- * function, subpage dirty bit is not cleared.
- * So clear subpage dirty bit here so next time we won't submit
- * page for range already written to disk.
- */
- btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, iosize);
submit_extent_page(bio_ctrl, disk_bytenr, page, iosize,
cur - page_offset(page));
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 23b65dc..10ac5f6 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -1147,8 +1147,7 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c
return 0;
/*
- * We want to be fast because we can be called from any path trying to
- * allocate memory, so if the lock is busy we don't want to spend time
+ * We want to be fast so if the lock is busy we don't want to spend time
* waiting for it - either some task is about to do IO for the inode or
* we may have another task shrinking extent maps, here in this code, so
* skip this inode.
@@ -1191,9 +1190,7 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c
/*
* Stop if we need to reschedule or there's contention on the
* lock. This is to avoid slowing other tasks trying to take the
- * lock and because the shrinker might be called during a memory
- * allocation path and we want to avoid taking a very long time
- * and slowing down all sorts of tasks.
+ * lock.
*/
if (need_resched() || rwlock_needbreak(&tree->lock))
break;
@@ -1222,12 +1219,7 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx
if (ctx->scanned >= ctx->nr_to_scan)
break;
- /*
- * We may be called from memory allocation paths, so we don't
- * want to take too much time and slowdown tasks.
- */
- if (need_resched())
- break;
+ cond_resched();
inode = btrfs_find_first_inode(root, min_ino);
}
@@ -1285,14 +1277,12 @@ long btrfs_free_extent_maps(struct btrfs_fs_info *fs_info, long nr_to_scan)
ctx.last_ino);
}
- /*
- * We may be called from memory allocation paths, so we don't want to
- * take too much time and slowdown tasks, so stop if we need reschedule.
- */
- while (ctx.scanned < ctx.nr_to_scan && !need_resched()) {
+ while (ctx.scanned < ctx.nr_to_scan) {
struct btrfs_root *root;
unsigned long count;
+ cond_resched();
+
spin_lock(&fs_info->fs_roots_radix_lock);
count = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
(void **)&root,
diff --git a/fs/btrfs/fiemap.c b/fs/btrfs/fiemap.c
index 8f95f3e..df7f09f 100644
--- a/fs/btrfs/fiemap.c
+++ b/fs/btrfs/fiemap.c
@@ -637,7 +637,7 @@ static int extent_fiemap(struct btrfs_inode *inode,
struct btrfs_path *path;
struct fiemap_cache cache = { 0 };
struct btrfs_backref_share_check_ctx *backref_ctx;
- u64 last_extent_end;
+ u64 last_extent_end = 0;
u64 prev_extent_end;
u64 range_start;
u64 range_end;
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index f5996a4..eaa1dbd 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -2697,15 +2697,16 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
u64 offset = bytenr - block_group->start;
u64 to_free, to_unusable;
int bg_reclaim_threshold = 0;
- bool initial = ((size == block_group->length) && (block_group->alloc_offset == 0));
+ bool initial;
u64 reclaimable_unusable;
- WARN_ON(!initial && offset + size > block_group->zone_capacity);
+ spin_lock(&block_group->lock);
+ initial = ((size == block_group->length) && (block_group->alloc_offset == 0));
+ WARN_ON(!initial && offset + size > block_group->zone_capacity);
if (!initial)
bg_reclaim_threshold = READ_ONCE(sinfo->bg_reclaim_threshold);
- spin_lock(&ctl->tree_lock);
if (!used)
to_free = size;
else if (initial)
@@ -2718,7 +2719,9 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
to_free = offset + size - block_group->alloc_offset;
to_unusable = size - to_free;
+ spin_lock(&ctl->tree_lock);
ctl->free_space += to_free;
+ spin_unlock(&ctl->tree_lock);
/*
* If the block group is read-only, we should account freed space into
* bytes_readonly.
@@ -2727,11 +2730,8 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
block_group->zone_unusable += to_unusable;
WARN_ON(block_group->zone_unusable > block_group->length);
}
- spin_unlock(&ctl->tree_lock);
if (!used) {
- spin_lock(&block_group->lock);
block_group->alloc_offset -= size;
- spin_unlock(&block_group->lock);
}
reclaimable_unusable = block_group->zone_unusable -
@@ -2745,6 +2745,8 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
btrfs_mark_bg_to_reclaim(block_group);
}
+ spin_unlock(&block_group->lock);
+
return 0;
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 333b0e8..b1b6564 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4195,6 +4195,7 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
btrfs_i_size_write(dir, dir->vfs_inode.i_size - name->len * 2);
inode_inc_iversion(&inode->vfs_inode);
+ inode_set_ctime_current(&inode->vfs_inode);
inode_inc_iversion(&dir->vfs_inode);
inode_set_mtime_to_ts(&dir->vfs_inode, inode_set_ctime_current(&dir->vfs_inode));
ret = btrfs_update_inode(trans, dir);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 5d57a28..7d6f5d9 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -4185,6 +4185,8 @@ static int try_flush_qgroup(struct btrfs_root *root)
return 0;
}
+ btrfs_run_delayed_iputs(root->fs_info);
+ btrfs_wait_on_delayed_iputs(root->fs_info);
ret = btrfs_start_delalloc_snapshot(root, true);
if (ret < 0)
goto out;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 4ca711a..619fa0b 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -347,7 +347,7 @@ struct name_cache_entry {
int ret;
int need_later_update;
int name_len;
- char name[];
+ char name[] __counted_by(name_len);
};
/* See the comment at lru_cache.h about struct btrfs_lru_cache_entry. */
@@ -6157,25 +6157,51 @@ static int send_write_or_clone(struct send_ctx *sctx,
u64 offset = key->offset;
u64 end;
u64 bs = sctx->send_root->fs_info->sectorsize;
+ struct btrfs_file_extent_item *ei;
+ u64 disk_byte;
+ u64 data_offset;
+ u64 num_bytes;
+ struct btrfs_inode_info info = { 0 };
end = min_t(u64, btrfs_file_extent_end(path), sctx->cur_inode_size);
if (offset >= end)
return 0;
- if (clone_root && IS_ALIGNED(end, bs)) {
- struct btrfs_file_extent_item *ei;
- u64 disk_byte;
- u64 data_offset;
+ num_bytes = end - offset;
- ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
- struct btrfs_file_extent_item);
- disk_byte = btrfs_file_extent_disk_bytenr(path->nodes[0], ei);
- data_offset = btrfs_file_extent_offset(path->nodes[0], ei);
- ret = clone_range(sctx, path, clone_root, disk_byte,
- data_offset, offset, end - offset);
- } else {
- ret = send_extent_data(sctx, path, offset, end - offset);
- }
+ if (!clone_root)
+ goto write_data;
+
+ if (IS_ALIGNED(end, bs))
+ goto clone_data;
+
+ /*
+ * If the extent end is not aligned, we can clone if the extent ends at
+ * the i_size of the inode and the clone range ends at the i_size of the
+ * source inode, otherwise the clone operation fails with -EINVAL.
+ */
+ if (end != sctx->cur_inode_size)
+ goto write_data;
+
+ ret = get_inode_info(clone_root->root, clone_root->ino, &info);
+ if (ret < 0)
+ return ret;
+
+ if (clone_root->offset + num_bytes == info.size)
+ goto clone_data;
+
+write_data:
+ ret = send_extent_data(sctx, path, offset, num_bytes);
+ sctx->cur_inode_next_write_offset = end;
+ return ret;
+
+clone_data:
+ ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_file_extent_item);
+ disk_byte = btrfs_file_extent_disk_bytenr(path->nodes[0], ei);
+ data_offset = btrfs_file_extent_offset(path->nodes[0], ei);
+ ret = clone_range(sctx, path, clone_root, disk_byte, data_offset, offset,
+ num_bytes);
sctx->cur_inode_next_write_offset = end;
return ret;
}
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 68e14fd..c691784b 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -1985,8 +1985,8 @@ static bool is_reclaim_urgent(struct btrfs_space_info *space_info)
return unalloc < data_chunk_size;
}
-static int do_reclaim_sweep(struct btrfs_fs_info *fs_info,
- struct btrfs_space_info *space_info, int raid)
+static void do_reclaim_sweep(struct btrfs_fs_info *fs_info,
+ struct btrfs_space_info *space_info, int raid)
{
struct btrfs_block_group *bg;
int thresh_pct;
@@ -2031,7 +2031,6 @@ static int do_reclaim_sweep(struct btrfs_fs_info *fs_info,
}
up_read(&space_info->groups_sem);
- return 0;
}
void btrfs_space_info_update_reclaimable(struct btrfs_space_info *space_info, s64 bytes)
@@ -2074,21 +2073,15 @@ bool btrfs_should_periodic_reclaim(struct btrfs_space_info *space_info)
return ret;
}
-int btrfs_reclaim_sweep(struct btrfs_fs_info *fs_info)
+void btrfs_reclaim_sweep(struct btrfs_fs_info *fs_info)
{
- int ret;
int raid;
struct btrfs_space_info *space_info;
list_for_each_entry(space_info, &fs_info->space_info, list) {
if (!btrfs_should_periodic_reclaim(space_info))
continue;
- for (raid = 0; raid < BTRFS_NR_RAID_TYPES; raid++) {
- ret = do_reclaim_sweep(fs_info, space_info, raid);
- if (ret)
- return ret;
- }
+ for (raid = 0; raid < BTRFS_NR_RAID_TYPES; raid++)
+ do_reclaim_sweep(fs_info, space_info, raid);
}
-
- return ret;
}
diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h
index 88b4422..5602026 100644
--- a/fs/btrfs/space-info.h
+++ b/fs/btrfs/space-info.h
@@ -294,6 +294,6 @@ void btrfs_space_info_update_reclaimable(struct btrfs_space_info *space_info, s6
void btrfs_set_periodic_reclaim_ready(struct btrfs_space_info *space_info, bool ready);
bool btrfs_should_periodic_reclaim(struct btrfs_space_info *space_info);
int btrfs_calc_reclaim_threshold(struct btrfs_space_info *space_info);
-int btrfs_reclaim_sweep(struct btrfs_fs_info *fs_info);
+void btrfs_reclaim_sweep(struct btrfs_fs_info *fs_info);
#endif /* BTRFS_SPACE_INFO_H */
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 83478de..98fa0f3 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -28,6 +28,7 @@
#include <linux/btrfs.h>
#include <linux/security.h>
#include <linux/fs_parser.h>
+#include <linux/swap.h>
#include "messages.h"
#include "delayed-inode.h"
#include "ctree.h"
@@ -2401,7 +2402,13 @@ static long btrfs_nr_cached_objects(struct super_block *sb, struct shrink_contro
trace_btrfs_extent_map_shrinker_count(fs_info, nr);
- return nr;
+ /*
+ * Only report the real number for DEBUG builds, as there are reports of
+ * serious performance degradation caused by too frequent shrinks.
+ */
+ if (IS_ENABLED(CONFIG_BTRFS_DEBUG))
+ return nr;
+ return 0;
}
static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_control *sc)
@@ -2409,6 +2416,15 @@ static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_cont
const long nr_to_scan = min_t(unsigned long, LONG_MAX, sc->nr_to_scan);
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+ /*
+ * We may be called from any task trying to allocate memory and we don't
+ * want to slow it down with scanning and dropping extent maps. It would
+ * also cause heavy lock contention if many tasks concurrently enter
+ * here. Therefore only allow kswapd tasks to scan and drop extent maps.
+ */
+ if (!current_is_kswapd())
+ return 0;
+
return btrfs_free_extent_maps(fs_info, nr_to_scan);
}
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index a825fa5..634d699 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -569,9 +569,10 @@ static int check_dir_item(struct extent_buffer *leaf,
/* dir type check */
dir_type = btrfs_dir_ftype(leaf, di);
- if (unlikely(dir_type >= BTRFS_FT_MAX)) {
+ if (unlikely(dir_type <= BTRFS_FT_UNKNOWN ||
+ dir_type >= BTRFS_FT_MAX)) {
dir_item_err(leaf, slot,
- "invalid dir item type, have %u expect [0, %u)",
+ "invalid dir item type, have %u expect (0, %u)",
dir_type, BTRFS_FT_MAX);
return -EUCLEAN;
}
@@ -1763,6 +1764,72 @@ static int check_raid_stripe_extent(const struct extent_buffer *leaf,
return 0;
}
+static int check_dev_extent_item(const struct extent_buffer *leaf,
+ const struct btrfs_key *key,
+ int slot,
+ struct btrfs_key *prev_key)
+{
+ struct btrfs_dev_extent *de;
+ const u32 sectorsize = leaf->fs_info->sectorsize;
+
+ de = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent);
+ /* Basic fixed member checks. */
+ if (unlikely(btrfs_dev_extent_chunk_tree(leaf, de) !=
+ BTRFS_CHUNK_TREE_OBJECTID)) {
+ generic_err(leaf, slot,
+ "invalid dev extent chunk tree id, has %llu expect %llu",
+ btrfs_dev_extent_chunk_tree(leaf, de),
+ BTRFS_CHUNK_TREE_OBJECTID);
+ return -EUCLEAN;
+ }
+ if (unlikely(btrfs_dev_extent_chunk_objectid(leaf, de) !=
+ BTRFS_FIRST_CHUNK_TREE_OBJECTID)) {
+ generic_err(leaf, slot,
+ "invalid dev extent chunk objectid, has %llu expect %llu",
+ btrfs_dev_extent_chunk_objectid(leaf, de),
+ BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+ return -EUCLEAN;
+ }
+ /* Alignment check. */
+ if (unlikely(!IS_ALIGNED(key->offset, sectorsize))) {
+ generic_err(leaf, slot,
+ "invalid dev extent key.offset, has %llu not aligned to %u",
+ key->offset, sectorsize);
+ return -EUCLEAN;
+ }
+ if (unlikely(!IS_ALIGNED(btrfs_dev_extent_chunk_offset(leaf, de),
+ sectorsize))) {
+ generic_err(leaf, slot,
+ "invalid dev extent chunk offset, has %llu not aligned to %u",
+ btrfs_dev_extent_chunk_objectid(leaf, de),
+ sectorsize);
+ return -EUCLEAN;
+ }
+ if (unlikely(!IS_ALIGNED(btrfs_dev_extent_length(leaf, de),
+ sectorsize))) {
+ generic_err(leaf, slot,
+ "invalid dev extent length, has %llu not aligned to %u",
+ btrfs_dev_extent_length(leaf, de), sectorsize);
+ return -EUCLEAN;
+ }
+ /* Overlap check with previous dev extent. */
+ if (slot && prev_key->objectid == key->objectid &&
+ prev_key->type == key->type) {
+ struct btrfs_dev_extent *prev_de;
+ u64 prev_len;
+
+ prev_de = btrfs_item_ptr(leaf, slot - 1, struct btrfs_dev_extent);
+ prev_len = btrfs_dev_extent_length(leaf, prev_de);
+ if (unlikely(prev_key->offset + prev_len > key->offset)) {
+ generic_err(leaf, slot,
+ "dev extent overlap, prev offset %llu len %llu current offset %llu",
+ prev_key->objectid, prev_len, key->offset);
+ return -EUCLEAN;
+ }
+ }
+ return 0;
+}
+
/*
* Common point to switch the item-specific validation.
*/
@@ -1799,6 +1866,9 @@ static enum btrfs_tree_block_status check_leaf_item(struct extent_buffer *leaf,
case BTRFS_DEV_ITEM_KEY:
ret = check_dev_item(leaf, key, slot);
break;
+ case BTRFS_DEV_EXTENT_KEY:
+ ret = check_dev_extent_item(leaf, key, slot, prev_key);
+ break;
case BTRFS_INODE_ITEM_KEY:
ret = check_inode_item(leaf, key, slot);
break;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 8c16bc5..c4744a0 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -246,7 +246,8 @@ static void finish_netfs_read(struct ceph_osd_request *req)
if (err >= 0) {
if (sparse && err > 0)
err = ceph_sparse_ext_map_end(op);
- if (err < subreq->len)
+ if (err < subreq->len &&
+ subreq->rreq->origin != NETFS_DIO_READ)
__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
if (IS_ENCRYPTED(inode) && err > 0) {
err = ceph_fscrypt_decrypt_extents(inode,
@@ -282,7 +283,8 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
size_t len;
int mode;
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
__clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
if (subreq->start >= inode->i_size)
@@ -424,6 +426,9 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
struct ceph_netfs_request_data *priv;
int ret = 0;
+ /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */
+ __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags);
+
if (rreq->origin != NETFS_READAHEAD)
return 0;
@@ -498,6 +503,11 @@ const struct netfs_request_ops ceph_netfs_ops = {
};
#ifdef CONFIG_CEPH_FSCACHE
+static void ceph_set_page_fscache(struct page *page)
+{
+ folio_start_private_2(page_folio(page)); /* [DEPRECATED] */
+}
+
static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async)
{
struct inode *inode = priv;
@@ -515,6 +525,10 @@ static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, b
ceph_fscache_write_terminated, inode, true, caching);
}
#else
+static inline void ceph_set_page_fscache(struct page *page)
+{
+}
+
static inline void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching)
{
}
@@ -706,6 +720,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
len = wlen;
set_page_writeback(page);
+ if (caching)
+ ceph_set_page_fscache(page);
ceph_fscache_write_to_cache(inode, page_off, len, caching);
if (IS_ENCRYPTED(inode)) {
@@ -789,6 +805,8 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc)
return AOP_WRITEPAGE_ACTIVATE;
}
+ folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */
+
err = writepage_nounlock(page, wbc);
if (err == -ERESTARTSYS) {
/* direct memory reclaimer was killed by SIGKILL. return 0
@@ -1062,7 +1080,8 @@ static int ceph_writepages_start(struct address_space *mapping,
unlock_page(page);
break;
}
- if (PageWriteback(page)) {
+ if (PageWriteback(page) ||
+ PagePrivate2(page) /* [DEPRECATED] */) {
if (wbc->sync_mode == WB_SYNC_NONE) {
doutc(cl, "%p under writeback\n", page);
unlock_page(page);
@@ -1070,6 +1089,7 @@ static int ceph_writepages_start(struct address_space *mapping,
}
doutc(cl, "waiting on writeback %p\n", page);
wait_on_page_writeback(page);
+ folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */
}
if (!clear_page_dirty_for_io(page)) {
@@ -1254,6 +1274,8 @@ static int ceph_writepages_start(struct address_space *mapping,
}
set_page_writeback(page);
+ if (caching)
+ ceph_set_page_fscache(page);
len += thp_size(page);
}
ceph_fscache_write_to_cache(inode, offset, len, caching);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 8f8de8f..4a8eec4 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -577,8 +577,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
/* Set parameters for the netfs library */
netfs_inode_init(&ci->netfs, &ceph_netfs_ops, false);
- /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */
- __set_bit(NETFS_ICTX_USE_PGPRIV2, &ci->netfs.flags);
spin_lock_init(&ci->i_ceph_lock);
@@ -697,6 +695,7 @@ void ceph_evict_inode(struct inode *inode)
percpu_counter_dec(&mdsc->metric.total_inodes);
+ netfs_wait_for_outstanding_io(inode);
truncate_inode_pages_final(&inode->i_data);
if (inode->i_state & I_PINNING_NETFS_WB)
ceph_fscache_unuse_cookie(inode, true);
diff --git a/fs/dcache.c b/fs/dcache.c
index 3d8daae..6386b9b 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -96,11 +96,16 @@ EXPORT_SYMBOL(dotdot_name);
*
* This hash-function tries to avoid losing too many bits of hash
* information, yet avoid using a prime hash-size or similar.
+ *
+ * Marking the variables "used" ensures that the compiler doesn't
+ * optimize them away completely on architectures with runtime
+ * constant infrastructure, this allows debuggers to see their
+ * values. But updating these values has no effect on those arches.
*/
-static unsigned int d_hash_shift __ro_after_init;
+static unsigned int d_hash_shift __ro_after_init __used;
-static struct hlist_bl_head *dentry_hashtable __ro_after_init;
+static struct hlist_bl_head *dentry_hashtable __ro_after_init __used;
static inline struct hlist_bl_head *d_hash(unsigned long hashlen)
{
diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c
index 2193a67..c3b90ab 100644
--- a/fs/erofs/dir.c
+++ b/fs/erofs/dir.c
@@ -8,19 +8,15 @@
static int erofs_fill_dentries(struct inode *dir, struct dir_context *ctx,
void *dentry_blk, struct erofs_dirent *de,
- unsigned int nameoff, unsigned int maxsize)
+ unsigned int nameoff0, unsigned int maxsize)
{
- const struct erofs_dirent *end = dentry_blk + nameoff;
+ const struct erofs_dirent *end = dentry_blk + nameoff0;
while (de < end) {
- const char *de_name;
+ unsigned char d_type = fs_ftype_to_dtype(de->file_type);
+ unsigned int nameoff = le16_to_cpu(de->nameoff);
+ const char *de_name = (char *)dentry_blk + nameoff;
unsigned int de_namelen;
- unsigned char d_type;
-
- d_type = fs_ftype_to_dtype(de->file_type);
-
- nameoff = le16_to_cpu(de->nameoff);
- de_name = (char *)dentry_blk + nameoff;
/* the last dirent in the block? */
if (de + 1 >= end)
@@ -52,21 +48,20 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx)
struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
struct super_block *sb = dir->i_sb;
unsigned long bsz = sb->s_blocksize;
- const size_t dirsize = i_size_read(dir);
- unsigned int i = erofs_blknr(sb, ctx->pos);
unsigned int ofs = erofs_blkoff(sb, ctx->pos);
int err = 0;
bool initial = true;
buf.mapping = dir->i_mapping;
- while (ctx->pos < dirsize) {
+ while (ctx->pos < dir->i_size) {
+ erofs_off_t dbstart = ctx->pos - ofs;
struct erofs_dirent *de;
unsigned int nameoff, maxsize;
- de = erofs_bread(&buf, erofs_pos(sb, i), EROFS_KMAP);
+ de = erofs_bread(&buf, dbstart, EROFS_KMAP);
if (IS_ERR(de)) {
erofs_err(sb, "fail to readdir of logical block %u of nid %llu",
- i, EROFS_I(dir)->nid);
+ erofs_blknr(sb, dbstart), EROFS_I(dir)->nid);
err = PTR_ERR(de);
break;
}
@@ -79,25 +74,19 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx)
break;
}
- maxsize = min_t(unsigned int, dirsize - ctx->pos + ofs, bsz);
-
+ maxsize = min_t(unsigned int, dir->i_size - dbstart, bsz);
/* search dirents at the arbitrary position */
if (initial) {
initial = false;
-
ofs = roundup(ofs, sizeof(struct erofs_dirent));
- ctx->pos = erofs_pos(sb, i) + ofs;
- if (ofs >= nameoff)
- goto skip_this;
+ ctx->pos = dbstart + ofs;
}
err = erofs_fill_dentries(dir, ctx, de, (void *)de + ofs,
nameoff, maxsize);
if (err)
break;
-skip_this:
- ctx->pos = erofs_pos(sb, i) + maxsize;
- ++i;
+ ctx->pos = dbstart + maxsize;
ofs = 0;
}
erofs_put_metabuf(&buf);
diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index 43c09aa..419432b 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -257,25 +257,23 @@ static int erofs_fill_inode(struct inode *inode)
goto out_unlock;
}
+ mapping_set_large_folios(inode->i_mapping);
if (erofs_inode_is_data_compressed(vi->datalayout)) {
#ifdef CONFIG_EROFS_FS_ZIP
DO_ONCE_LITE_IF(inode->i_blkbits != PAGE_SHIFT,
erofs_info, inode->i_sb,
"EXPERIMENTAL EROFS subpage compressed block support in use. Use at your own risk!");
inode->i_mapping->a_ops = &z_erofs_aops;
- err = 0;
- goto out_unlock;
-#endif
+#else
err = -EOPNOTSUPP;
- goto out_unlock;
- }
- inode->i_mapping->a_ops = &erofs_raw_access_aops;
- mapping_set_large_folios(inode->i_mapping);
-#ifdef CONFIG_EROFS_FS_ONDEMAND
- if (erofs_is_fscache_mode(inode->i_sb))
- inode->i_mapping->a_ops = &erofs_fscache_access_aops;
#endif
-
+ } else {
+ inode->i_mapping->a_ops = &erofs_raw_access_aops;
+#ifdef CONFIG_EROFS_FS_ONDEMAND
+ if (erofs_is_fscache_mode(inode->i_sb))
+ inode->i_mapping->a_ops = &erofs_fscache_access_aops;
+#endif
+ }
out_unlock:
erofs_put_metabuf(&buf);
return err;
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 7366076..45dc15e 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -220,7 +220,7 @@ struct erofs_buf {
};
#define __EROFS_BUF_INITIALIZER ((struct erofs_buf){ .page = NULL })
-#define erofs_blknr(sb, addr) ((addr) >> (sb)->s_blocksize_bits)
+#define erofs_blknr(sb, addr) ((erofs_blk_t)((addr) >> (sb)->s_blocksize_bits))
#define erofs_blkoff(sb, addr) ((addr) & ((sb)->s_blocksize - 1))
#define erofs_pos(sb, blk) ((erofs_off_t)(blk) << (sb)->s_blocksize_bits)
#define erofs_iblks(i) (round_up((i)->i_size, i_blocksize(i)) >> (i)->i_blkbits)
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 32ce5b3..6cb5c891 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -108,22 +108,6 @@ static void erofs_free_inode(struct inode *inode)
kmem_cache_free(erofs_inode_cachep, vi);
}
-static bool check_layout_compatibility(struct super_block *sb,
- struct erofs_super_block *dsb)
-{
- const unsigned int feature = le32_to_cpu(dsb->feature_incompat);
-
- EROFS_SB(sb)->feature_incompat = feature;
-
- /* check if current kernel meets all mandatory requirements */
- if (feature & (~EROFS_ALL_FEATURE_INCOMPAT)) {
- erofs_err(sb, "unidentified incompatible feature %x, please upgrade kernel",
- feature & ~EROFS_ALL_FEATURE_INCOMPAT);
- return false;
- }
- return true;
-}
-
/* read variable-sized metadata, offset will be aligned by 4-byte */
void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
erofs_off_t *offset, int *lengthp)
@@ -279,7 +263,7 @@ static int erofs_scan_devices(struct super_block *sb,
static int erofs_read_superblock(struct super_block *sb)
{
- struct erofs_sb_info *sbi;
+ struct erofs_sb_info *sbi = EROFS_SB(sb);
struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
struct erofs_super_block *dsb;
void *data;
@@ -291,9 +275,7 @@ static int erofs_read_superblock(struct super_block *sb)
return PTR_ERR(data);
}
- sbi = EROFS_SB(sb);
dsb = (struct erofs_super_block *)(data + EROFS_SUPER_OFFSET);
-
ret = -EINVAL;
if (le32_to_cpu(dsb->magic) != EROFS_SUPER_MAGIC_V1) {
erofs_err(sb, "cannot find valid erofs superblock");
@@ -318,8 +300,12 @@ static int erofs_read_superblock(struct super_block *sb)
}
ret = -EINVAL;
- if (!check_layout_compatibility(sb, dsb))
+ sbi->feature_incompat = le32_to_cpu(dsb->feature_incompat);
+ if (sbi->feature_incompat & ~EROFS_ALL_FEATURE_INCOMPAT) {
+ erofs_err(sb, "unidentified incompatible feature %x, please upgrade kernel",
+ sbi->feature_incompat & ~EROFS_ALL_FEATURE_INCOMPAT);
goto out;
+ }
sbi->sb_size = 128 + dsb->sb_extslots * EROFS_SB_EXTSLOT_SIZE;
if (sbi->sb_size > PAGE_SIZE - EROFS_SUPER_OFFSET) {
diff --git a/fs/erofs/zutil.c b/fs/erofs/zutil.c
index 9b53883..37afe20 100644
--- a/fs/erofs/zutil.c
+++ b/fs/erofs/zutil.c
@@ -111,7 +111,8 @@ int z_erofs_gbuf_growsize(unsigned int nrpages)
out:
if (i < z_erofs_gbuf_count && tmp_pages) {
for (j = 0; j < nrpages; ++j)
- if (tmp_pages[j] && tmp_pages[j] != gbuf->pages[j])
+ if (tmp_pages[j] && (j >= gbuf->nrpages ||
+ tmp_pages[j] != gbuf->pages[j]))
__free_page(tmp_pages[j]);
kfree(tmp_pages);
}
diff --git a/fs/exec.c b/fs/exec.c
index a126e3d..50e76cc 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1692,6 +1692,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file)
unsigned int mode;
vfsuid_t vfsuid;
vfsgid_t vfsgid;
+ int err;
if (!mnt_may_suid(file->f_path.mnt))
return;
@@ -1708,12 +1709,17 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file)
/* Be careful if suid/sgid is set */
inode_lock(inode);
- /* reload atomically mode/uid/gid now that lock held */
+ /* Atomically reload and check mode/uid/gid now that lock held. */
mode = inode->i_mode;
vfsuid = i_uid_into_vfsuid(idmap, inode);
vfsgid = i_gid_into_vfsgid(idmap, inode);
+ err = inode_permission(idmap, inode, MAY_EXEC);
inode_unlock(inode);
+ /* Did the exec bit vanish out from under us? Give up. */
+ if (err)
+ return;
+
/* We ignore suid/sgid if there are no mappings for them in the ns */
if (!vfsuid_has_mapping(bprm->cred->user_ns, vfsuid) ||
!vfsgid_has_mapping(bprm->cred->user_ns, vfsgid))
diff --git a/fs/file.c b/fs/file.c
index a11e59b..655338e 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -46,27 +46,23 @@ static void free_fdtable_rcu(struct rcu_head *rcu)
#define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr))
#define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long))
+#define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds
/*
* Copy 'count' fd bits from the old table to the new table and clear the extra
* space if any. This does not copy the file pointers. Called with the files
* spinlock held for write.
*/
-static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt,
- unsigned int count)
+static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt,
+ unsigned int copy_words)
{
- unsigned int cpy, set;
+ unsigned int nwords = fdt_words(nfdt);
- cpy = count / BITS_PER_BYTE;
- set = (nfdt->max_fds - count) / BITS_PER_BYTE;
- memcpy(nfdt->open_fds, ofdt->open_fds, cpy);
- memset((char *)nfdt->open_fds + cpy, 0, set);
- memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy);
- memset((char *)nfdt->close_on_exec + cpy, 0, set);
-
- cpy = BITBIT_SIZE(count);
- set = BITBIT_SIZE(nfdt->max_fds) - cpy;
- memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy);
- memset((char *)nfdt->full_fds_bits + cpy, 0, set);
+ bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds,
+ copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG);
+ bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec,
+ copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG);
+ bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits,
+ copy_words, nwords);
}
/*
@@ -84,7 +80,7 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
memcpy(nfdt->fd, ofdt->fd, cpy);
memset((char *)nfdt->fd + cpy, 0, set);
- copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds);
+ copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt));
}
/*
@@ -379,7 +375,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int
open_files = sane_fdtable_size(old_fdt, max_fds);
}
- copy_fd_bitmaps(new_fdt, old_fdt, open_files);
+ copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG);
old_fds = old_fdt->fd;
new_fds = new_fdt->fd;
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 9eb191b..7146038 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1618,9 +1618,11 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
this_num = min_t(unsigned, num, PAGE_SIZE - offset);
err = fuse_copy_page(cs, &page, offset, this_num, 0);
- if (!err && offset == 0 &&
- (this_num == PAGE_SIZE || file_size == end))
+ if (!PageUptodate(page) && !err && offset == 0 &&
+ (this_num == PAGE_SIZE || file_size == end)) {
+ zero_user_segment(page, this_num, PAGE_SIZE);
SetPageUptodate(page);
+ }
unlock_page(page);
put_page(page);
diff --git a/fs/inode.c b/fs/inode.c
index 8667094..10c4619 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -488,6 +488,39 @@ static void inode_lru_list_del(struct inode *inode)
this_cpu_dec(nr_unused);
}
+static void inode_pin_lru_isolating(struct inode *inode)
+{
+ lockdep_assert_held(&inode->i_lock);
+ WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE));
+ inode->i_state |= I_LRU_ISOLATING;
+}
+
+static void inode_unpin_lru_isolating(struct inode *inode)
+{
+ spin_lock(&inode->i_lock);
+ WARN_ON(!(inode->i_state & I_LRU_ISOLATING));
+ inode->i_state &= ~I_LRU_ISOLATING;
+ smp_mb();
+ wake_up_bit(&inode->i_state, __I_LRU_ISOLATING);
+ spin_unlock(&inode->i_lock);
+}
+
+static void inode_wait_for_lru_isolating(struct inode *inode)
+{
+ spin_lock(&inode->i_lock);
+ if (inode->i_state & I_LRU_ISOLATING) {
+ DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING);
+ wait_queue_head_t *wqh;
+
+ wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING);
+ spin_unlock(&inode->i_lock);
+ __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE);
+ spin_lock(&inode->i_lock);
+ WARN_ON(inode->i_state & I_LRU_ISOLATING);
+ }
+ spin_unlock(&inode->i_lock);
+}
+
/**
* inode_sb_list_add - add inode to the superblock list of inodes
* @inode: inode to add
@@ -657,6 +690,8 @@ static void evict(struct inode *inode)
inode_sb_list_del(inode);
+ inode_wait_for_lru_isolating(inode);
+
/*
* Wait for flusher thread to be done with the inode so that filesystem
* does not start destroying it while writeback is still running. Since
@@ -855,7 +890,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item,
* be under pressure before the cache inside the highmem zone.
*/
if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) {
- __iget(inode);
+ inode_pin_lru_isolating(inode);
spin_unlock(&inode->i_lock);
spin_unlock(lru_lock);
if (remove_inode_buffers(inode)) {
@@ -867,7 +902,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item,
__count_vm_events(PGINODESTEAL, reap);
mm_account_reclaimed_pages(reap);
}
- iput(inode);
+ inode_unpin_lru_isolating(inode);
spin_lock(lru_lock);
return LRU_RETRY;
}
diff --git a/fs/libfs.c b/fs/libfs.c
index 8aa3487..02602d0 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -450,6 +450,14 @@ void simple_offset_destroy(struct offset_ctx *octx)
mtree_destroy(&octx->mt);
}
+static int offset_dir_open(struct inode *inode, struct file *file)
+{
+ struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode);
+
+ file->private_data = (void *)ctx->next_offset;
+ return 0;
+}
+
/**
* offset_dir_llseek - Advance the read position of a directory descriptor
* @file: an open directory whose position is to be updated
@@ -463,6 +471,9 @@ void simple_offset_destroy(struct offset_ctx *octx)
*/
static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence)
{
+ struct inode *inode = file->f_inode;
+ struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode);
+
switch (whence) {
case SEEK_CUR:
offset += file->f_pos;
@@ -476,7 +487,8 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence)
}
/* In this case, ->private_data is protected by f_pos_lock */
- file->private_data = NULL;
+ if (!offset)
+ file->private_data = (void *)ctx->next_offset;
return vfs_setpos(file, offset, LONG_MAX);
}
@@ -507,7 +519,7 @@ static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry)
inode->i_ino, fs_umode_to_dtype(inode->i_mode));
}
-static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
+static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, long last_index)
{
struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode);
struct dentry *dentry;
@@ -515,17 +527,21 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
while (true) {
dentry = offset_find_next(octx, ctx->pos);
if (!dentry)
- return ERR_PTR(-ENOENT);
+ return;
+
+ if (dentry2offset(dentry) >= last_index) {
+ dput(dentry);
+ return;
+ }
if (!offset_dir_emit(ctx, dentry)) {
dput(dentry);
- break;
+ return;
}
ctx->pos = dentry2offset(dentry) + 1;
dput(dentry);
}
- return NULL;
}
/**
@@ -552,22 +568,19 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
static int offset_readdir(struct file *file, struct dir_context *ctx)
{
struct dentry *dir = file->f_path.dentry;
+ long last_index = (long)file->private_data;
lockdep_assert_held(&d_inode(dir)->i_rwsem);
if (!dir_emit_dots(file, ctx))
return 0;
- /* In this case, ->private_data is protected by f_pos_lock */
- if (ctx->pos == DIR_OFFSET_MIN)
- file->private_data = NULL;
- else if (file->private_data == ERR_PTR(-ENOENT))
- return 0;
- file->private_data = offset_iterate_dir(d_inode(dir), ctx);
+ offset_iterate_dir(d_inode(dir), ctx, last_index);
return 0;
}
const struct file_operations simple_offset_dir_operations = {
+ .open = offset_dir_open,
.llseek = offset_dir_llseek,
.iterate_shared = offset_readdir,
.read = generic_read_dir,
diff --git a/fs/locks.c b/fs/locks.c
index 9afb16e..e45cad4 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2984,7 +2984,7 @@ static int __init filelock_init(void)
filelock_cache = kmem_cache_create("file_lock_cache",
sizeof(struct file_lock), 0, SLAB_PANIC, NULL);
- filelease_cache = kmem_cache_create("file_lock_cache",
+ filelease_cache = kmem_cache_create("file_lease_cache",
sizeof(struct file_lease), 0, SLAB_PANIC, NULL);
for_each_possible_cpu(i) {
diff --git a/fs/netfs/Kconfig b/fs/netfs/Kconfig
index 1b78e8b..7701c03 100644
--- a/fs/netfs/Kconfig
+++ b/fs/netfs/Kconfig
@@ -24,7 +24,7 @@
config NETFS_DEBUG
bool "Enable dynamic debugging netfslib and FS-Cache"
- depends on NETFS
+ depends on NETFS_SUPPORT
help
This permits debugging to be dynamically enabled in the local caching
management module. If this is set, the debugging output may be
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index a688d4c..27c750d 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -10,6 +10,97 @@
#include "internal.h"
/*
+ * [DEPRECATED] Unlock the folios in a read operation for when the filesystem
+ * is using PG_private_2 and direct writing to the cache from here rather than
+ * marking the page for writeback.
+ *
+ * Note that we don't touch folio->private in this code.
+ */
+static void netfs_rreq_unlock_folios_pgpriv2(struct netfs_io_request *rreq,
+ size_t *account)
+{
+ struct netfs_io_subrequest *subreq;
+ struct folio *folio;
+ pgoff_t start_page = rreq->start / PAGE_SIZE;
+ pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1;
+ bool subreq_failed = false;
+
+ XA_STATE(xas, &rreq->mapping->i_pages, start_page);
+
+ /* Walk through the pagecache and the I/O request lists simultaneously.
+ * We may have a mixture of cached and uncached sections and we only
+ * really want to write out the uncached sections. This is slightly
+ * complicated by the possibility that we might have huge pages with a
+ * mixture inside.
+ */
+ subreq = list_first_entry(&rreq->subrequests,
+ struct netfs_io_subrequest, rreq_link);
+ subreq_failed = (subreq->error < 0);
+
+ trace_netfs_rreq(rreq, netfs_rreq_trace_unlock_pgpriv2);
+
+ rcu_read_lock();
+ xas_for_each(&xas, folio, last_page) {
+ loff_t pg_end;
+ bool pg_failed = false;
+ bool folio_started = false;
+
+ if (xas_retry(&xas, folio))
+ continue;
+
+ pg_end = folio_pos(folio) + folio_size(folio) - 1;
+
+ for (;;) {
+ loff_t sreq_end;
+
+ if (!subreq) {
+ pg_failed = true;
+ break;
+ }
+
+ if (!folio_started &&
+ test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags) &&
+ fscache_operation_valid(&rreq->cache_resources)) {
+ trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache);
+ folio_start_private_2(folio);
+ folio_started = true;
+ }
+
+ pg_failed |= subreq_failed;
+ sreq_end = subreq->start + subreq->len - 1;
+ if (pg_end < sreq_end)
+ break;
+
+ *account += subreq->transferred;
+ if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) {
+ subreq = list_next_entry(subreq, rreq_link);
+ subreq_failed = (subreq->error < 0);
+ } else {
+ subreq = NULL;
+ subreq_failed = false;
+ }
+
+ if (pg_end == sreq_end)
+ break;
+ }
+
+ if (!pg_failed) {
+ flush_dcache_folio(folio);
+ folio_mark_uptodate(folio);
+ }
+
+ if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) {
+ if (folio->index == rreq->no_unlock_folio &&
+ test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags))
+ _debug("no unlock");
+ else
+ folio_unlock(folio);
+ }
+ }
+ rcu_read_unlock();
+}
+
+/*
* Unlock the folios in a read operation. We need to set PG_writeback on any
* folios we're going to write back before we unlock them.
*
@@ -35,6 +126,12 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
}
}
+ /* Handle deprecated PG_private_2 case. */
+ if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) {
+ netfs_rreq_unlock_folios_pgpriv2(rreq, &account);
+ goto out;
+ }
+
/* Walk through the pagecache and the I/O request lists simultaneously.
* We may have a mixture of cached and uncached sections and we only
* really want to write out the uncached sections. This is slightly
@@ -52,7 +149,6 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
loff_t pg_end;
bool pg_failed = false;
bool wback_to_cache = false;
- bool folio_started = false;
if (xas_retry(&xas, folio))
continue;
@@ -66,17 +162,8 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
pg_failed = true;
break;
}
- if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) {
- if (!folio_started && test_bit(NETFS_SREQ_COPY_TO_CACHE,
- &subreq->flags)) {
- trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache);
- folio_start_private_2(folio);
- folio_started = true;
- }
- } else {
- wback_to_cache |=
- test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
- }
+
+ wback_to_cache |= test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
pg_failed |= subreq_failed;
sreq_end = subreq->start + subreq->len - 1;
if (pg_end < sreq_end)
@@ -124,6 +211,7 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
}
rcu_read_unlock();
+out:
task_io_account_read(account);
if (rreq->netfs_ops->done)
rreq->netfs_ops->done(rreq);
@@ -395,7 +483,7 @@ static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len,
}
/**
- * netfs_write_begin - Helper to prepare for writing
+ * netfs_write_begin - Helper to prepare for writing [DEPRECATED]
* @ctx: The netfs context
* @file: The file to read from
* @mapping: The mapping to read from
@@ -426,6 +514,9 @@ static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len,
* inode before calling this.
*
* This is usable whether or not caching is enabled.
+ *
+ * Note that this should be considered deprecated and netfs_perform_write()
+ * used instead.
*/
int netfs_write_begin(struct netfs_inode *ctx,
struct file *file, struct address_space *mapping,
@@ -466,7 +557,7 @@ int netfs_write_begin(struct netfs_inode *ctx,
if (!netfs_is_cache_enabled(ctx) &&
netfs_skip_folio_read(folio, pos, len, false)) {
netfs_stat(&netfs_n_rh_write_zskip);
- goto have_folio;
+ goto have_folio_no_wait;
}
rreq = netfs_alloc_request(mapping, file,
@@ -507,6 +598,10 @@ int netfs_write_begin(struct netfs_inode *ctx,
netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
have_folio:
+ ret = folio_wait_private_2_killable(folio);
+ if (ret < 0)
+ goto error;
+have_folio_no_wait:
*_folio = folio;
_leave(" = 0");
return 0;
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 4726c31..ca53c5d 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -184,7 +184,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
unsigned int bdp_flags = (iocb->ki_flags & IOCB_NOWAIT) ? BDP_ASYNC : 0;
ssize_t written = 0, ret, ret2;
loff_t i_size, pos = iocb->ki_pos, from, to;
- size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
+ size_t max_chunk = mapping_max_folio_size(mapping);
bool maybe_trouble = false;
if (unlikely(test_bit(NETFS_ICTX_WRITETHROUGH, &ctx->flags) ||
diff --git a/fs/netfs/fscache_cookie.c b/fs/netfs/fscache_cookie.c
index bce2492..d4d4b3a 100644
--- a/fs/netfs/fscache_cookie.c
+++ b/fs/netfs/fscache_cookie.c
@@ -741,6 +741,10 @@ static void fscache_cookie_state_machine(struct fscache_cookie *cookie)
spin_lock(&cookie->lock);
}
if (test_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags)) {
+ if (atomic_read(&cookie->n_accesses) != 0)
+ /* still being accessed: postpone it */
+ break;
+
__fscache_set_cookie_state(cookie,
FSCACHE_COOKIE_STATE_LRU_DISCARDING);
wake = true;
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index c93851b..9431285 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -99,6 +99,146 @@ static void netfs_rreq_completed(struct netfs_io_request *rreq, bool was_async)
}
/*
+ * [DEPRECATED] Deal with the completion of writing the data to the cache. We
+ * have to clear the PG_fscache bits on the folios involved and release the
+ * caller's ref.
+ *
+ * May be called in softirq mode and we inherit a ref from the caller.
+ */
+static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq,
+ bool was_async)
+{
+ struct netfs_io_subrequest *subreq;
+ struct folio *folio;
+ pgoff_t unlocked = 0;
+ bool have_unlocked = false;
+
+ rcu_read_lock();
+
+ list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+ XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE);
+
+ xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) {
+ if (xas_retry(&xas, folio))
+ continue;
+
+ /* We might have multiple writes from the same huge
+ * folio, but we mustn't unlock a folio more than once.
+ */
+ if (have_unlocked && folio->index <= unlocked)
+ continue;
+ unlocked = folio_next_index(folio) - 1;
+ trace_netfs_folio(folio, netfs_folio_trace_end_copy);
+ folio_end_private_2(folio);
+ have_unlocked = true;
+ }
+ }
+
+ rcu_read_unlock();
+ netfs_rreq_completed(rreq, was_async);
+}
+
+static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error,
+ bool was_async) /* [DEPRECATED] */
+{
+ struct netfs_io_subrequest *subreq = priv;
+ struct netfs_io_request *rreq = subreq->rreq;
+
+ if (IS_ERR_VALUE(transferred_or_error)) {
+ netfs_stat(&netfs_n_rh_write_failed);
+ trace_netfs_failure(rreq, subreq, transferred_or_error,
+ netfs_fail_copy_to_cache);
+ } else {
+ netfs_stat(&netfs_n_rh_write_done);
+ }
+
+ trace_netfs_sreq(subreq, netfs_sreq_trace_write_term);
+
+ /* If we decrement nr_copy_ops to 0, the ref belongs to us. */
+ if (atomic_dec_and_test(&rreq->nr_copy_ops))
+ netfs_rreq_unmark_after_write(rreq, was_async);
+
+ netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated);
+}
+
+/*
+ * [DEPRECATED] Perform any outstanding writes to the cache. We inherit a ref
+ * from the caller.
+ */
+static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq)
+{
+ struct netfs_cache_resources *cres = &rreq->cache_resources;
+ struct netfs_io_subrequest *subreq, *next, *p;
+ struct iov_iter iter;
+ int ret;
+
+ trace_netfs_rreq(rreq, netfs_rreq_trace_copy);
+
+ /* We don't want terminating writes trying to wake us up whilst we're
+ * still going through the list.
+ */
+ atomic_inc(&rreq->nr_copy_ops);
+
+ list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) {
+ if (!test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) {
+ list_del_init(&subreq->rreq_link);
+ netfs_put_subrequest(subreq, false,
+ netfs_sreq_trace_put_no_copy);
+ }
+ }
+
+ list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+ /* Amalgamate adjacent writes */
+ while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) {
+ next = list_next_entry(subreq, rreq_link);
+ if (next->start != subreq->start + subreq->len)
+ break;
+ subreq->len += next->len;
+ list_del_init(&next->rreq_link);
+ netfs_put_subrequest(next, false,
+ netfs_sreq_trace_put_merged);
+ }
+
+ ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len,
+ subreq->len, rreq->i_size, true);
+ if (ret < 0) {
+ trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write);
+ trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip);
+ continue;
+ }
+
+ iov_iter_xarray(&iter, ITER_SOURCE, &rreq->mapping->i_pages,
+ subreq->start, subreq->len);
+
+ atomic_inc(&rreq->nr_copy_ops);
+ netfs_stat(&netfs_n_rh_write);
+ netfs_get_subrequest(subreq, netfs_sreq_trace_get_copy_to_cache);
+ trace_netfs_sreq(subreq, netfs_sreq_trace_write);
+ cres->ops->write(cres, subreq->start, &iter,
+ netfs_rreq_copy_terminated, subreq);
+ }
+
+ /* If we decrement nr_copy_ops to 0, the usage ref belongs to us. */
+ if (atomic_dec_and_test(&rreq->nr_copy_ops))
+ netfs_rreq_unmark_after_write(rreq, false);
+}
+
+static void netfs_rreq_write_to_cache_work(struct work_struct *work) /* [DEPRECATED] */
+{
+ struct netfs_io_request *rreq =
+ container_of(work, struct netfs_io_request, work);
+
+ netfs_rreq_do_write_to_cache(rreq);
+}
+
+static void netfs_rreq_write_to_cache(struct netfs_io_request *rreq) /* [DEPRECATED] */
+{
+ rreq->work.func = netfs_rreq_write_to_cache_work;
+ if (!queue_work(system_unbound_wq, &rreq->work))
+ BUG();
+}
+
+/*
* Handle a short read.
*/
static void netfs_rreq_short_read(struct netfs_io_request *rreq,
@@ -166,6 +306,7 @@ static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq)
break;
subreq->source = NETFS_DOWNLOAD_FROM_SERVER;
subreq->error = 0;
+ __set_bit(NETFS_SREQ_RETRYING, &subreq->flags);
netfs_stat(&netfs_n_rh_download_instead);
trace_netfs_sreq(subreq, netfs_sreq_trace_download_instead);
netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
@@ -173,6 +314,8 @@ static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq)
netfs_reset_subreq_iter(rreq, subreq);
netfs_read_from_server(rreq, subreq);
} else if (test_bit(NETFS_SREQ_SHORT_IO, &subreq->flags)) {
+ __set_bit(NETFS_SREQ_RETRYING, &subreq->flags);
+ netfs_reset_subreq_iter(rreq, subreq);
netfs_rreq_short_read(rreq, subreq);
}
}
@@ -225,7 +368,8 @@ static void netfs_rreq_assess_dio(struct netfs_io_request *rreq)
if (subreq->error || subreq->transferred == 0)
break;
transferred += subreq->transferred;
- if (subreq->transferred < subreq->len)
+ if (subreq->transferred < subreq->len ||
+ test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags))
break;
}
@@ -275,6 +419,10 @@ static void netfs_rreq_assess(struct netfs_io_request *rreq, bool was_async)
clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS);
+ if (test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags) &&
+ test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags))
+ return netfs_rreq_write_to_cache(rreq);
+
netfs_rreq_completed(rreq, was_async);
}
@@ -356,7 +504,8 @@ void netfs_subreq_terminated(struct netfs_io_subrequest *subreq,
subreq->error = 0;
subreq->transferred += transferred_or_error;
- if (subreq->transferred < subreq->len)
+ if (subreq->transferred < subreq->len &&
+ !test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags))
goto incomplete;
complete:
@@ -386,7 +535,8 @@ void netfs_subreq_terminated(struct netfs_io_subrequest *subreq,
if (transferred_or_error == 0) {
if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) {
- subreq->error = -ENODATA;
+ if (rreq->origin != NETFS_DIO_READ)
+ subreq->error = -ENODATA;
goto failed;
}
} else {
@@ -457,9 +607,14 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
}
if (subreq->len > ictx->zero_point - subreq->start)
subreq->len = ictx->zero_point - subreq->start;
+
+ /* We limit buffered reads to the EOF, but let the
+ * server deal with larger-than-EOF DIO/unbuffered
+ * reads.
+ */
+ if (subreq->len > rreq->i_size - subreq->start)
+ subreq->len = rreq->i_size - subreq->start;
}
- if (subreq->len > rreq->i_size - subreq->start)
- subreq->len = rreq->i_size - subreq->start;
if (rreq->rsize && subreq->len > rreq->rsize)
subreq->len = rreq->rsize;
@@ -595,11 +750,10 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
do {
_debug("submit %llx + %llx >= %llx",
rreq->start, rreq->submitted, rreq->i_size);
- if (rreq->origin == NETFS_DIO_READ &&
- rreq->start + rreq->submitted >= rreq->i_size)
- break;
if (!netfs_rreq_submit_slice(rreq, &io_iter))
break;
+ if (test_bit(NETFS_SREQ_NO_PROGRESS, &rreq->flags))
+ break;
if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) &&
test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags))
break;
@@ -630,10 +784,13 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
TASK_UNINTERRUPTIBLE);
ret = rreq->error;
- if (ret == 0 && rreq->submitted < rreq->len &&
- rreq->origin != NETFS_DIO_READ) {
- trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read);
- ret = -EIO;
+ if (ret == 0) {
+ if (rreq->origin == NETFS_DIO_READ) {
+ ret = rreq->transferred;
+ } else if (rreq->submitted < rreq->len) {
+ trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read);
+ ret = -EIO;
+ }
}
} else {
/* If we decrement nr_outstanding to 0, the ref belongs to us. */
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 83e644b..c1f321c 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -97,10 +97,22 @@ EXPORT_SYMBOL(netfs_clear_inode_writeback);
void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
{
struct netfs_folio *finfo;
+ struct netfs_inode *ctx = netfs_inode(folio_inode(folio));
size_t flen = folio_size(folio);
_enter("{%lx},%zx,%zx", folio->index, offset, length);
+ if (offset == 0 && length == flen) {
+ unsigned long long i_size = i_size_read(&ctx->inode);
+ unsigned long long fpos = folio_pos(folio), end;
+
+ end = umin(fpos + flen, i_size);
+ if (fpos < i_size && end > ctx->zero_point)
+ ctx->zero_point = end;
+ }
+
+ folio_wait_private_2(folio); /* [DEPRECATED] */
+
if (!folio_test_private(folio))
return;
@@ -113,18 +125,34 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
/* We have a partially uptodate page from a streaming write. */
unsigned int fstart = finfo->dirty_offset;
unsigned int fend = fstart + finfo->dirty_len;
- unsigned int end = offset + length;
+ unsigned int iend = offset + length;
if (offset >= fend)
return;
- if (end <= fstart)
+ if (iend <= fstart)
return;
- if (offset <= fstart && end >= fend)
- goto erase_completely;
- if (offset <= fstart && end > fstart)
- goto reduce_len;
- if (offset > fstart && end >= fend)
- goto move_start;
+
+ /* The invalidation region overlaps the data. If the region
+ * covers the start of the data, we either move along the start
+ * or just erase the data entirely.
+ */
+ if (offset <= fstart) {
+ if (iend >= fend)
+ goto erase_completely;
+ /* Move the start of the data. */
+ finfo->dirty_len = fend - iend;
+ finfo->dirty_offset = offset;
+ return;
+ }
+
+ /* Reduce the length of the data if the invalidation region
+ * covers the tail part.
+ */
+ if (iend >= fend) {
+ finfo->dirty_len = offset - fstart;
+ return;
+ }
+
/* A partial write was split. The caller has already zeroed
* it, so just absorb the hole.
*/
@@ -137,12 +165,6 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
folio_clear_uptodate(folio);
kfree(finfo);
return;
-reduce_len:
- finfo->dirty_len = offset + length - finfo->dirty_offset;
- return;
-move_start:
- finfo->dirty_len -= offset - finfo->dirty_offset;
- finfo->dirty_offset = offset;
}
EXPORT_SYMBOL(netfs_invalidate_folio);
@@ -159,12 +181,20 @@ bool netfs_release_folio(struct folio *folio, gfp_t gfp)
struct netfs_inode *ctx = netfs_inode(folio_inode(folio));
unsigned long long end;
- end = folio_pos(folio) + folio_size(folio);
+ if (folio_test_dirty(folio))
+ return false;
+
+ end = umin(folio_pos(folio) + folio_size(folio), i_size_read(&ctx->inode));
if (end > ctx->zero_point)
ctx->zero_point = end;
if (folio_test_private(folio))
return false;
+ if (unlikely(folio_test_private_2(folio))) { /* [DEPRECATED] */
+ if (current_is_kswapd() || !(gfp & __GFP_FS))
+ return false;
+ folio_wait_private_2(folio);
+ }
fscache_note_page_release(netfs_i_cookie(ctx));
return true;
}
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index f4a6427..0294df7 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -24,10 +24,6 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
struct netfs_io_request *rreq;
mempool_t *mempool = ctx->ops->request_pool ?: &netfs_request_pool;
struct kmem_cache *cache = mempool->pool_data;
- bool is_unbuffered = (origin == NETFS_UNBUFFERED_WRITE ||
- origin == NETFS_DIO_READ ||
- origin == NETFS_DIO_WRITE);
- bool cached = !is_unbuffered && netfs_is_cache_enabled(ctx);
int ret;
for (;;) {
@@ -56,12 +52,6 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
refcount_set(&rreq->ref, 1);
__set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
- if (cached) {
- __set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags);
- if (test_bit(NETFS_ICTX_USE_PGPRIV2, &ctx->flags))
- /* Filesystem uses deprecated PG_private_2 marking. */
- __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags);
- }
if (file && file->f_flags & O_NONBLOCK)
__set_bit(NETFS_RREQ_NONBLOCK, &rreq->flags);
if (rreq->netfs_ops->init_request) {
diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
index 426cf87..ae7a204 100644
--- a/fs/netfs/write_collect.c
+++ b/fs/netfs/write_collect.c
@@ -33,6 +33,7 @@
int netfs_folio_written_back(struct folio *folio)
{
enum netfs_folio_trace why = netfs_folio_trace_clear;
+ struct netfs_inode *ictx = netfs_inode(folio->mapping->host);
struct netfs_folio *finfo;
struct netfs_group *group = NULL;
int gcount = 0;
@@ -41,6 +42,12 @@ int netfs_folio_written_back(struct folio *folio)
/* Streaming writes cannot be redirtied whilst under writeback,
* so discard the streaming record.
*/
+ unsigned long long fend;
+
+ fend = folio_pos(folio) + finfo->dirty_offset + finfo->dirty_len;
+ if (fend > ictx->zero_point)
+ ictx->zero_point = fend;
+
folio_detach_private(folio);
group = finfo->netfs_group;
gcount++;
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index 9258d30..3f7e37e 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -94,6 +94,8 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping,
{
struct netfs_io_request *wreq;
struct netfs_inode *ictx;
+ bool is_buffered = (origin == NETFS_WRITEBACK ||
+ origin == NETFS_WRITETHROUGH);
wreq = netfs_alloc_request(mapping, file, start, 0, origin);
if (IS_ERR(wreq))
@@ -102,7 +104,7 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping,
_enter("R=%x", wreq->debug_id);
ictx = netfs_inode(wreq->inode);
- if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags))
+ if (is_buffered && netfs_is_cache_enabled(ictx))
fscache_begin_write_operation(&wreq->cache_resources, netfs_i_cookie(ictx));
wreq->contiguity = wreq->start;
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 29c49a7..6df77f0 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -118,7 +118,9 @@ static __be32 decode_bitmap(struct xdr_stream *xdr, uint32_t *bitmap)
if (likely(attrlen > 0))
bitmap[0] = ntohl(*p++);
if (attrlen > 1)
- bitmap[1] = ntohl(*p);
+ bitmap[1] = ntohl(*p++);
+ if (attrlen > 2)
+ bitmap[2] = ntohl(*p);
return 0;
}
@@ -446,7 +448,7 @@ static __be32 decode_recallany_args(struct svc_rqst *rqstp,
void *argp)
{
struct cb_recallanyargs *args = argp;
- uint32_t bitmap[2];
+ uint32_t bitmap[3];
__be32 *p, status;
p = xdr_inline_decode(xdr, 4);
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index d5edb3b..20cb200 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -647,6 +647,9 @@ static int nfs_server_return_marked_delegations(struct nfs_server *server,
prev = delegation;
continue;
}
+ inode = nfs_delegation_grab_inode(delegation);
+ if (inode == NULL)
+ continue;
if (prev) {
struct inode *tmp = nfs_delegation_grab_inode(prev);
@@ -657,12 +660,6 @@ static int nfs_server_return_marked_delegations(struct nfs_server *server,
}
}
- inode = nfs_delegation_grab_inode(delegation);
- if (inode == NULL) {
- rcu_read_unlock();
- iput(to_put);
- goto restart;
- }
delegation = nfs_start_delegation_return_locked(NFS_I(inode));
rcu_read_unlock();
@@ -1184,7 +1181,6 @@ static int nfs_server_reap_unclaimed_delegations(struct nfs_server *server,
struct inode *inode;
restart:
rcu_read_lock();
-restart_locked:
list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
if (test_bit(NFS_DELEGATION_INODE_FREEING,
&delegation->flags) ||
@@ -1195,7 +1191,7 @@ static int nfs_server_reap_unclaimed_delegations(struct nfs_server *server,
continue;
inode = nfs_delegation_grab_inode(delegation);
if (inode == NULL)
- goto restart_locked;
+ continue;
delegation = nfs_start_delegation_return_locked(NFS_I(inode));
rcu_read_unlock();
if (delegation != NULL) {
@@ -1318,7 +1314,6 @@ static int nfs_server_reap_expired_delegations(struct nfs_server *server,
restart:
rcu_read_lock();
-restart_locked:
list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
if (test_bit(NFS_DELEGATION_INODE_FREEING,
&delegation->flags) ||
@@ -1330,7 +1325,7 @@ static int nfs_server_reap_expired_delegations(struct nfs_server *server,
continue;
inode = nfs_delegation_grab_inode(delegation);
if (inode == NULL)
- goto restart_locked;
+ continue;
spin_lock(&delegation->lock);
cred = get_cred_rcu(delegation->cred);
nfs4_stateid_copy(&stateid, &delegation->stateid);
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 7202ce8..7a558de 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -265,6 +265,8 @@ static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *fi
{
rreq->netfs_priv = get_nfs_open_context(nfs_file_open_context(file));
rreq->debug_id = atomic_inc_return(&nfs_netfs_debug_id);
+ /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */
+ __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags);
return 0;
}
@@ -361,7 +363,8 @@ void nfs_netfs_read_completion(struct nfs_pgio_header *hdr)
return;
sreq = netfs->sreq;
- if (test_bit(NFS_IOHDR_EOF, &hdr->flags))
+ if (test_bit(NFS_IOHDR_EOF, &hdr->flags) &&
+ sreq->rreq->origin != NETFS_DIO_READ)
__set_bit(NETFS_SREQ_CLEAR_TAIL, &sreq->flags);
if (hdr->error)
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index fbed002..e8adae1 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -81,8 +81,6 @@ static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs)
static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi)
{
netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops, false);
- /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */
- __set_bit(NETFS_ICTX_USE_PGPRIV2, &nfsi->netfs.flags);
}
extern void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr);
extern void nfs_netfs_read_completion(struct nfs_pgio_header *hdr);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 8883016..b8ffbe5 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3931,7 +3931,8 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
FATTR4_WORD0_CASE_INSENSITIVE |
FATTR4_WORD0_CASE_PRESERVING;
if (minorversion)
- bitmask[2] = FATTR4_WORD2_SUPPATTR_EXCLCREAT;
+ bitmask[2] = FATTR4_WORD2_SUPPATTR_EXCLCREAT |
+ FATTR4_WORD2_OPEN_ARGUMENTS;
status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
if (status == 0) {
@@ -9997,6 +9998,7 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
fallthrough;
default:
task->tk_status = 0;
+ lrp->res.lrs_present = 0;
fallthrough;
case 0:
break;
@@ -10010,9 +10012,11 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
task->tk_status = 0;
break;
case -NFS4ERR_DELAY:
- if (nfs4_async_handle_error(task, server, NULL, NULL) != -EAGAIN)
- break;
- goto out_restart;
+ if (nfs4_async_handle_error(task, server, NULL, NULL) ==
+ -EAGAIN)
+ goto out_restart;
+ lrp->res.lrs_present = 0;
+ break;
}
return;
out_restart:
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index aa69848..0d16b38 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1284,10 +1284,9 @@ void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo,
LIST_HEAD(freeme);
spin_lock(&inode->i_lock);
- if (!pnfs_layout_is_valid(lo) ||
- !nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid))
+ if (!nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid))
goto out_unlock;
- if (stateid) {
+ if (stateid && pnfs_layout_is_valid(lo)) {
u32 seq = be32_to_cpu(arg_stateid->seqid);
pnfs_mark_matching_lsegs_invalid(lo, &freeme, range, seq);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index cbbd486..97b3860 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -47,6 +47,7 @@
#include <linux/vfs.h>
#include <linux/inet.h>
#include <linux/in6.h>
+#include <linux/sched.h>
#include <linux/slab.h>
#include <net/ipv6.h>
#include <linux/netdevice.h>
@@ -228,6 +229,7 @@ static int __nfs_list_for_each_server(struct list_head *head,
ret = fn(server, data);
if (ret)
goto out;
+ cond_resched();
rcu_read_lock();
}
rcu_read_unlock();
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index a20c2c9..a366fb1 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2789,15 +2789,18 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st)
deny & NFS4_SHARE_ACCESS_READ ? "r" : "-",
deny & NFS4_SHARE_ACCESS_WRITE ? "w" : "-");
- spin_lock(&nf->fi_lock);
- file = find_any_file_locked(nf);
- if (file) {
- nfs4_show_superblock(s, file);
- seq_puts(s, ", ");
- nfs4_show_fname(s, file);
- seq_puts(s, ", ");
- }
- spin_unlock(&nf->fi_lock);
+ if (nf) {
+ spin_lock(&nf->fi_lock);
+ file = find_any_file_locked(nf);
+ if (file) {
+ nfs4_show_superblock(s, file);
+ seq_puts(s, ", ");
+ nfs4_show_fname(s, file);
+ seq_puts(s, ", ");
+ }
+ spin_unlock(&nf->fi_lock);
+ } else
+ seq_puts(s, "closed, ");
nfs4_show_owner(s, oo);
if (st->sc_status & SC_STATUS_ADMIN_REVOKED)
seq_puts(s, ", admin-revoked");
@@ -3075,9 +3078,9 @@ nfsd4_cb_getattr_release(struct nfsd4_callback *cb)
struct nfs4_delegation *dp =
container_of(ncf, struct nfs4_delegation, dl_cb_fattr);
- nfs4_put_stid(&dp->dl_stid);
clear_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags);
wake_up_bit(&ncf->ncf_cb_flags, CB_GETATTR_BUSY);
+ nfs4_put_stid(&dp->dl_stid);
}
static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = {
@@ -8812,7 +8815,7 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
/**
* nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict
* @rqstp: RPC transaction context
- * @inode: file to be checked for a conflict
+ * @dentry: dentry of inode to be checked for a conflict
* @modified: return true if file was modified
* @size: new size of file if modified is true
*
@@ -8827,16 +8830,16 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
* code is returned.
*/
__be32
-nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode,
+nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry,
bool *modified, u64 *size)
{
__be32 status;
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
struct file_lock_context *ctx;
struct file_lease *fl;
- struct nfs4_delegation *dp;
struct iattr attrs;
struct nfs4_cb_fattr *ncf;
+ struct inode *inode = d_inode(dentry);
*modified = false;
ctx = locks_inode_context(inode);
@@ -8856,17 +8859,26 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode,
*/
if (type == F_RDLCK)
break;
- goto break_lease;
+
+ nfsd_stats_wdeleg_getattr_inc(nn);
+ spin_unlock(&ctx->flc_lock);
+
+ status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
+ if (status != nfserr_jukebox ||
+ !nfsd_wait_for_delegreturn(rqstp, inode))
+ return status;
+ return 0;
}
if (type == F_WRLCK) {
- dp = fl->c.flc_owner;
+ struct nfs4_delegation *dp = fl->c.flc_owner;
+
if (dp->dl_recall.cb_clp == *(rqstp->rq_lease_breaker)) {
spin_unlock(&ctx->flc_lock);
return 0;
}
-break_lease:
nfsd_stats_wdeleg_getattr_inc(nn);
dp = fl->c.flc_owner;
+ refcount_inc(&dp->dl_stid.sc_count);
ncf = &dp->dl_cb_fattr;
nfs4_cb_getattr(&dp->dl_cb_fattr);
spin_unlock(&ctx->flc_lock);
@@ -8876,27 +8888,37 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode,
/* Recall delegation only if client didn't respond */
status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
if (status != nfserr_jukebox ||
- !nfsd_wait_for_delegreturn(rqstp, inode))
+ !nfsd_wait_for_delegreturn(rqstp, inode)) {
+ nfs4_put_stid(&dp->dl_stid);
return status;
+ }
}
if (!ncf->ncf_file_modified &&
(ncf->ncf_initial_cinfo != ncf->ncf_cb_change ||
ncf->ncf_cur_fsize != ncf->ncf_cb_fsize))
ncf->ncf_file_modified = true;
if (ncf->ncf_file_modified) {
+ int err;
+
/*
* Per section 10.4.3 of RFC 8881, the server would
* not update the file's metadata with the client's
* modified size
*/
attrs.ia_mtime = attrs.ia_ctime = current_time(inode);
- attrs.ia_valid = ATTR_MTIME | ATTR_CTIME;
- setattr_copy(&nop_mnt_idmap, inode, &attrs);
- mark_inode_dirty(inode);
+ attrs.ia_valid = ATTR_MTIME | ATTR_CTIME | ATTR_DELEG;
+ inode_lock(inode);
+ err = notify_change(&nop_mnt_idmap, dentry, &attrs, NULL);
+ inode_unlock(inode);
+ if (err) {
+ nfs4_put_stid(&dp->dl_stid);
+ return nfserrno(err);
+ }
ncf->ncf_cur_fsize = ncf->ncf_cb_fsize;
*size = ncf->ncf_cur_fsize;
*modified = true;
}
+ nfs4_put_stid(&dp->dl_stid);
return 0;
}
break;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 42b41d5..97f5837 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3545,6 +3545,9 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
args.dentry = dentry;
args.ignore_crossmnt = (ignore_crossmnt != 0);
args.acl = NULL;
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+ args.context = NULL;
+#endif
/*
* Make a local copy of the attribute bitmap that can be modified.
@@ -3562,7 +3565,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
}
args.size = 0;
if (attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) {
- status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry),
+ status = nfsd4_deleg_getattr_conflict(rqstp, dentry,
&file_modified, &size);
if (status)
goto out;
@@ -3617,7 +3620,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
args.contextsupport = false;
#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
- args.context = NULL;
if ((attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) ||
attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) {
if (exp->ex_flags & NFSEXP_SECURITY_LABEL)
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index ffc2170..ec4559e 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -781,5 +781,5 @@ static inline bool try_to_expire_client(struct nfs4_client *clp)
}
extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp,
- struct inode *inode, bool *file_modified, u64 *size);
+ struct dentry *dentry, bool *file_modified, u64 *size);
#endif /* NFSD4_STATE_H */
diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c
index 4860fcc..d0568c0 100644
--- a/fs/overlayfs/params.c
+++ b/fs/overlayfs/params.c
@@ -353,6 +353,8 @@ static void ovl_add_layer(struct fs_context *fc, enum ovl_opt layer,
case Opt_datadir_add:
ctx->nr_data++;
fallthrough;
+ case Opt_lowerdir:
+ fallthrough;
case Opt_lowerdir_add:
WARN_ON(ctx->nr >= ctx->capacity);
l = &ctx->lower[ctx->nr++];
@@ -365,10 +367,9 @@ static void ovl_add_layer(struct fs_context *fc, enum ovl_opt layer,
}
}
-static int ovl_parse_layer(struct fs_context *fc, struct fs_parameter *param,
- enum ovl_opt layer)
+static int ovl_parse_layer(struct fs_context *fc, const char *layer_name, enum ovl_opt layer)
{
- char *name = kstrdup(param->string, GFP_KERNEL);
+ char *name = kstrdup(layer_name, GFP_KERNEL);
bool upper = (layer == Opt_upperdir || layer == Opt_workdir);
struct path path;
int err;
@@ -376,7 +377,7 @@ static int ovl_parse_layer(struct fs_context *fc, struct fs_parameter *param,
if (!name)
return -ENOMEM;
- if (upper)
+ if (upper || layer == Opt_lowerdir)
err = ovl_mount_dir(name, &path);
else
err = ovl_mount_dir_noesc(name, &path);
@@ -432,7 +433,6 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
{
int err;
struct ovl_fs_context *ctx = fc->fs_private;
- struct ovl_fs_context_layer *l;
char *dup = NULL, *iter;
ssize_t nr_lower, nr;
bool data_layer = false;
@@ -449,7 +449,7 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
return 0;
if (*name == ':') {
- pr_err("cannot append lower layer");
+ pr_err("cannot append lower layer\n");
return -EINVAL;
}
@@ -472,35 +472,11 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
goto out_err;
}
- if (nr_lower > ctx->capacity) {
- err = -ENOMEM;
- l = krealloc_array(ctx->lower, nr_lower, sizeof(*ctx->lower),
- GFP_KERNEL_ACCOUNT);
- if (!l)
- goto out_err;
-
- ctx->lower = l;
- ctx->capacity = nr_lower;
- }
-
iter = dup;
- l = ctx->lower;
- for (nr = 0; nr < nr_lower; nr++, l++) {
- ctx->nr++;
- memset(l, 0, sizeof(*l));
-
- err = ovl_mount_dir(iter, &l->path);
+ for (nr = 0; nr < nr_lower; nr++) {
+ err = ovl_parse_layer(fc, iter, Opt_lowerdir);
if (err)
- goto out_put;
-
- err = ovl_mount_dir_check(fc, &l->path, Opt_lowerdir, iter, false);
- if (err)
- goto out_put;
-
- err = -ENOMEM;
- l->name = kstrdup(iter, GFP_KERNEL_ACCOUNT);
- if (!l->name)
- goto out_put;
+ goto out_err;
if (data_layer)
ctx->nr_data++;
@@ -517,8 +493,8 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
* there are no data layers.
*/
if (ctx->nr_data > 0) {
- pr_err("regular lower layers cannot follow data lower layers");
- goto out_put;
+ pr_err("regular lower layers cannot follow data lower layers\n");
+ goto out_err;
}
data_layer = false;
@@ -532,9 +508,6 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
kfree(dup);
return 0;
-out_put:
- ovl_reset_lowerdirs(ctx);
-
out_err:
kfree(dup);
@@ -582,7 +555,7 @@ static int ovl_parse_param(struct fs_context *fc, struct fs_parameter *param)
case Opt_datadir_add:
case Opt_upperdir:
case Opt_workdir:
- err = ovl_parse_layer(fc, param, opt);
+ err = ovl_parse_layer(fc, param->string, opt);
break;
case Opt_default_permissions:
config->default_permissions = true;
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 68758b6..0addcc8 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -126,7 +126,7 @@ static int romfs_read_folio(struct file *file, struct folio *folio)
}
}
- buf = folio_zero_tail(folio, fillsize, buf);
+ buf = folio_zero_tail(folio, fillsize, buf + fillsize);
kunmap_local(buf);
folio_end_read(folio, ret == 0);
return ret;
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 2c4b357..2a2523c 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -75,9 +75,9 @@ unsigned int sign_CIFS_PDUs = 1;
/*
* Global transaction id (XID) information
*/
-unsigned int GlobalCurrentXid; /* protected by GlobalMid_Sem */
-unsigned int GlobalTotalActiveXid; /* prot by GlobalMid_Sem */
-unsigned int GlobalMaxActiveXid; /* prot by GlobalMid_Sem */
+unsigned int GlobalCurrentXid; /* protected by GlobalMid_Lock */
+unsigned int GlobalTotalActiveXid; /* prot by GlobalMid_Lock */
+unsigned int GlobalMaxActiveXid; /* prot by GlobalMid_Lock */
spinlock_t GlobalMid_Lock; /* protects above & list operations on midQ entries */
/*
@@ -1341,7 +1341,6 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
struct cifsFileInfo *smb_file_target;
struct cifs_tcon *src_tcon;
struct cifs_tcon *target_tcon;
- unsigned long long destend, fstart, fend;
ssize_t rc;
cifs_dbg(FYI, "copychunk range\n");
@@ -1391,25 +1390,13 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
goto unlock;
}
- destend = destoff + len - 1;
-
- /* Flush the folios at either end of the destination range to prevent
- * accidental loss of dirty data outside of the range.
+ /* Flush and invalidate all the folios in the destination region. If
+ * the copy was successful, then some of the flush is extra overhead,
+ * but we need to allow for the copy failing in some way (eg. ENOSPC).
*/
- fstart = destoff;
- fend = destend;
-
- rc = cifs_flush_folio(target_inode, destoff, &fstart, &fend, true);
+ rc = filemap_invalidate_inode(target_inode, true, destoff, destoff + len - 1);
if (rc)
goto unlock;
- rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false);
- if (rc)
- goto unlock;
- if (fend > target_cifsi->netfs.zero_point)
- target_cifsi->netfs.zero_point = fend + 1;
-
- /* Discard all the folios that overlap the destination region. */
- truncate_inode_pages_range(&target_inode->i_data, fstart, fend);
fscache_invalidate(cifs_inode_cookie(target_inode), NULL,
i_size_read(target_inode), 0);
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 5c9b3e6..9eae864 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -254,7 +254,6 @@ struct cifs_open_info_data {
struct smb_rqst {
struct kvec *rq_iov; /* array of kvecs */
unsigned int rq_nvec; /* number of kvecs in array */
- size_t rq_iter_size; /* Amount of data in ->rq_iter */
struct iov_iter rq_iter; /* Data iterator */
struct xarray rq_buffer; /* Page buffer for encryption */
};
@@ -1486,6 +1485,7 @@ struct cifs_io_subrequest {
struct cifs_io_request *req;
};
ssize_t got_bytes;
+ size_t actual_len;
unsigned int xid;
int result;
bool have_xid;
@@ -2017,9 +2017,9 @@ extern spinlock_t cifs_tcp_ses_lock;
/*
* Global transaction id (XID) information
*/
-extern unsigned int GlobalCurrentXid; /* protected by GlobalMid_Sem */
-extern unsigned int GlobalTotalActiveXid; /* prot by GlobalMid_Sem */
-extern unsigned int GlobalMaxActiveXid; /* prot by GlobalMid_Sem */
+extern unsigned int GlobalCurrentXid; /* protected by GlobalMid_Lock */
+extern unsigned int GlobalTotalActiveXid; /* prot by GlobalMid_Lock */
+extern unsigned int GlobalMaxActiveXid; /* prot by GlobalMid_Lock */
extern spinlock_t GlobalMid_Lock; /* protects above & list operations on midQ entries */
/*
diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 595c4b673..6dce70f 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -1713,7 +1713,6 @@ cifs_async_writev(struct cifs_io_subrequest *wdata)
rqst.rq_iov = iov;
rqst.rq_nvec = 2;
rqst.rq_iter = wdata->subreq.io_iter;
- rqst.rq_iter_size = iov_iter_count(&wdata->subreq.io_iter);
cifs_dbg(FYI, "async write at %llu %zu bytes\n",
wdata->subreq.start, wdata->subreq.len);
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index d2307162..c1c1427 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -4194,6 +4194,9 @@ tlink_rb_insert(struct rb_root *root, struct tcon_link *new_tlink)
*
* If one doesn't exist then insert a new tcon_link struct into the tree and
* try to construct a new one.
+ *
+ * REMEMBER to call cifs_put_tlink() after successful calls to cifs_sb_tlink,
+ * to avoid refcount issues
*/
struct tcon_link *
cifs_sb_tlink(struct cifs_sb_info *cifs_sb)
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index b2405dd..2d38748 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -111,6 +111,7 @@ static void cifs_issue_write(struct netfs_io_subrequest *subreq)
goto fail;
}
+ wdata->actual_len = wdata->subreq.len;
rc = adjust_credits(wdata->server, wdata, cifs_trace_rw_credits_issue_write_adjust);
if (rc)
goto fail;
@@ -153,7 +154,7 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq)
struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq);
struct TCP_Server_Info *server = req->server;
struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb);
- size_t rsize = 0;
+ size_t rsize;
int rc;
rdata->xid = get_xid();
@@ -166,8 +167,8 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq)
cifs_sb->ctx);
- rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize, &rsize,
- &rdata->credits);
+ rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize,
+ &rsize, &rdata->credits);
if (rc) {
subreq->error = rc;
return false;
@@ -183,7 +184,8 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq)
server->credits, server->in_flight, 0,
cifs_trace_rw_credits_read_submit);
- subreq->len = min_t(size_t, subreq->len, rsize);
+ subreq->len = umin(subreq->len, rsize);
+ rdata->actual_len = subreq->len;
#ifdef CONFIG_CIFS_SMB_DIRECT
if (server->smbd_conn)
@@ -203,12 +205,39 @@ static void cifs_req_issue_read(struct netfs_io_subrequest *subreq)
struct netfs_io_request *rreq = subreq->rreq;
struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq);
struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq);
+ struct TCP_Server_Info *server = req->server;
+ struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb);
int rc = 0;
cifs_dbg(FYI, "%s: op=%08x[%x] mapping=%p len=%zu/%zu\n",
__func__, rreq->debug_id, subreq->debug_index, rreq->mapping,
subreq->transferred, subreq->len);
+ if (test_bit(NETFS_SREQ_RETRYING, &subreq->flags)) {
+ /*
+ * As we're issuing a retry, we need to negotiate some new
+ * credits otherwise the server may reject the op with
+ * INVALID_PARAMETER. Note, however, we may get back less
+ * credit than we need to complete the op, in which case, we
+ * shorten the op and rely on additional rounds of retry.
+ */
+ size_t rsize = umin(subreq->len - subreq->transferred,
+ cifs_sb->ctx->rsize);
+
+ rc = server->ops->wait_mtu_credits(server, rsize, &rdata->actual_len,
+ &rdata->credits);
+ if (rc)
+ goto out;
+
+ rdata->credits.in_flight_check = 1;
+
+ trace_smb3_rw_credits(rdata->rreq->debug_id,
+ rdata->subreq.debug_index,
+ rdata->credits.value,
+ server->credits, server->in_flight, 0,
+ cifs_trace_rw_credits_read_resubmit);
+ }
+
if (req->cfile->invalidHandle) {
do {
rc = cifs_reopen_file(req->cfile, true);
@@ -217,7 +246,8 @@ static void cifs_req_issue_read(struct netfs_io_subrequest *subreq)
goto out;
}
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (subreq->rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
rc = rdata->server->ops->async_readv(rdata);
out:
@@ -315,7 +345,7 @@ static void cifs_free_subrequest(struct netfs_io_subrequest *subreq)
#endif
}
- if (rdata->credits.value != 0)
+ if (rdata->credits.value != 0) {
trace_smb3_rw_credits(rdata->rreq->debug_id,
rdata->subreq.debug_index,
rdata->credits.value,
@@ -323,8 +353,12 @@ static void cifs_free_subrequest(struct netfs_io_subrequest *subreq)
rdata->server ? rdata->server->in_flight : 0,
-rdata->credits.value,
cifs_trace_rw_credits_free_subreq);
+ if (rdata->server)
+ add_credits_and_wake_if(rdata->server, &rdata->credits, 0);
+ else
+ rdata->credits.value = 0;
+ }
- add_credits_and_wake_if(rdata->server, &rdata->credits, 0);
if (rdata->have_xid)
free_xid(rdata->xid);
}
@@ -2749,6 +2783,7 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
struct inode *inode = file->f_mapping->host;
struct cifsInodeInfo *cinode = CIFS_I(inode);
struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
+ struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
ssize_t rc;
rc = netfs_start_io_write(inode);
@@ -2765,12 +2800,16 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
if (rc <= 0)
goto out;
- if (!cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(from),
+ if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) &&
+ (cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(from),
server->vals->exclusive_lock_type, 0,
- NULL, CIFS_WRITE_OP))
- rc = netfs_buffered_write_iter_locked(iocb, from, NULL);
- else
+ NULL, CIFS_WRITE_OP))) {
rc = -EACCES;
+ goto out;
+ }
+
+ rc = netfs_buffered_write_iter_locked(iocb, from, NULL);
+
out:
up_read(&cinode->lock_sem);
netfs_end_io_write(inode);
@@ -2902,9 +2941,7 @@ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to)
if (!CIFS_CACHE_READ(cinode))
return netfs_unbuffered_read_iter(iocb, to);
- if (cap_unix(tcon->ses) &&
- (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
- ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) {
+ if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0) {
if (iocb->ki_flags & IOCB_DIRECT)
return netfs_unbuffered_read_iter(iocb, to);
return netfs_buffered_read_iter(iocb, to);
diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c
index 44dbaf9..9bb5c86 100644
--- a/fs/smb/client/ioctl.c
+++ b/fs/smb/client/ioctl.c
@@ -229,9 +229,11 @@ static int cifs_shutdown(struct super_block *sb, unsigned long arg)
shutdown_good:
trace_smb3_shutdown_done(flags, tcon->tid);
+ cifs_put_tlink(tlink);
return 0;
shutdown_out_err:
trace_smb3_shutdown_err(rc, flags, tcon->tid);
+ cifs_put_tlink(tlink);
return rc;
}
diff --git a/fs/smb/client/link.c b/fs/smb/client/link.c
index d86da949..80099bb 100644
--- a/fs/smb/client/link.c
+++ b/fs/smb/client/link.c
@@ -588,6 +588,7 @@ cifs_symlink(struct mnt_idmap *idmap, struct inode *inode,
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink)) {
rc = PTR_ERR(tlink);
+ /* BB could be clearer if skipped put_tlink on error here, but harmless */
goto symlink_exit;
}
pTcon = tlink_tcon(tlink);
diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c
index 689d8a5..48c2758 100644
--- a/fs/smb/client/reparse.c
+++ b/fs/smb/client/reparse.c
@@ -378,6 +378,8 @@ int parse_reparse_point(struct reparse_data_buffer *buf,
u32 plen, struct cifs_sb_info *cifs_sb,
bool unicode, struct cifs_open_info_data *data)
{
+ struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
+
data->reparse.buf = buf;
/* See MS-FSCC 2.1.2 */
@@ -394,12 +396,13 @@ int parse_reparse_point(struct reparse_data_buffer *buf,
case IO_REPARSE_TAG_LX_FIFO:
case IO_REPARSE_TAG_LX_CHR:
case IO_REPARSE_TAG_LX_BLK:
- return 0;
+ break;
default:
- cifs_dbg(VFS, "%s: unhandled reparse tag: 0x%08x\n",
- __func__, le32_to_cpu(buf->ReparseTag));
- return -EOPNOTSUPP;
+ cifs_tcon_dbg(VFS | ONCE, "unhandled reparse tag: 0x%08x\n",
+ le32_to_cpu(buf->ReparseTag));
+ break;
}
+ return 0;
}
int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb,
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 322cabc..4df84eb 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -301,7 +301,7 @@ smb2_adjust_credits(struct TCP_Server_Info *server,
unsigned int /*enum smb3_rw_credits_trace*/ trace)
{
struct cifs_credits *credits = &subreq->credits;
- int new_val = DIV_ROUND_UP(subreq->subreq.len, SMB2_MAX_BUFFER_SIZE);
+ int new_val = DIV_ROUND_UP(subreq->actual_len, SMB2_MAX_BUFFER_SIZE);
int scredits, in_flight;
if (!credits->value || credits->value == new_val)
@@ -3237,13 +3237,15 @@ static long smb3_zero_data(struct file *file, struct cifs_tcon *tcon,
}
static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
- loff_t offset, loff_t len, bool keep_size)
+ unsigned long long offset, unsigned long long len,
+ bool keep_size)
{
struct cifs_ses *ses = tcon->ses;
struct inode *inode = file_inode(file);
struct cifsInodeInfo *cifsi = CIFS_I(inode);
struct cifsFileInfo *cfile = file->private_data;
- unsigned long long new_size;
+ struct netfs_inode *ictx = netfs_inode(inode);
+ unsigned long long i_size, new_size, remote_size;
long rc;
unsigned int xid;
@@ -3255,6 +3257,16 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
inode_lock(inode);
filemap_invalidate_lock(inode->i_mapping);
+ i_size = i_size_read(inode);
+ remote_size = ictx->remote_i_size;
+ if (offset + len >= remote_size && offset < i_size) {
+ unsigned long long top = umin(offset + len, i_size);
+
+ rc = filemap_write_and_wait_range(inode->i_mapping, offset, top - 1);
+ if (rc < 0)
+ goto zero_range_exit;
+ }
+
/*
* We zero the range through ioctl, so we need remove the page caches
* first, otherwise the data may be inconsistent with the server.
@@ -3305,6 +3317,7 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
struct inode *inode = file_inode(file);
struct cifsFileInfo *cfile = file->private_data;
struct file_zero_data_information fsctl_buf;
+ unsigned long long end = offset + len, i_size, remote_i_size;
long rc;
unsigned int xid;
__u8 set_sparse = 1;
@@ -3336,6 +3349,27 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
(char *)&fsctl_buf,
sizeof(struct file_zero_data_information),
CIFSMaxBufSize, NULL, NULL);
+
+ if (rc)
+ goto unlock;
+
+ /* If there's dirty data in the buffer that would extend the EOF if it
+ * were written, then we need to move the EOF marker over to the lower
+ * of the high end of the hole and the proposed EOF. The problem is
+ * that we locally hole-punch the tail of the dirty data, the proposed
+ * EOF update will end up in the wrong place.
+ */
+ i_size = i_size_read(inode);
+ remote_i_size = netfs_inode(inode)->remote_i_size;
+ if (end > remote_i_size && i_size > remote_i_size) {
+ unsigned long long extend_to = umin(end, i_size);
+ rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
+ cfile->fid.volatile_fid, cfile->pid, extend_to);
+ if (rc >= 0)
+ netfs_inode(inode)->remote_i_size = extend_to;
+ }
+
+unlock:
filemap_invalidate_unlock(inode->i_mapping);
out:
inode_unlock(inode);
@@ -4446,7 +4480,6 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, int num_rqst,
}
iov_iter_xarray(&new->rq_iter, ITER_SOURCE,
buffer, 0, size);
- new->rq_iter_size = size;
}
}
@@ -4492,7 +4525,6 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf,
rqst.rq_nvec = 2;
if (iter) {
rqst.rq_iter = *iter;
- rqst.rq_iter_size = iov_iter_count(iter);
iter_size = iov_iter_count(iter);
}
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 83facb5..88dc49d 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -4441,7 +4441,7 @@ smb2_new_read_req(void **buf, unsigned int *total_len,
* If we want to do a RDMA write, fill in and append
* smbd_buffer_descriptor_v1 to the end of read request
*/
- if (smb3_use_rdma_offload(io_parms)) {
+ if (rdata && smb3_use_rdma_offload(io_parms)) {
struct smbd_buffer_descriptor_v1 *v1;
bool need_invalidate = server->dialect == SMB30_PROT_ID;
@@ -4507,6 +4507,7 @@ static void
smb2_readv_callback(struct mid_q_entry *mid)
{
struct cifs_io_subrequest *rdata = mid->callback_data;
+ struct netfs_inode *ictx = netfs_inode(rdata->rreq->inode);
struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink);
struct TCP_Server_Info *server = rdata->server;
struct smb2_hdr *shdr =
@@ -4523,16 +4524,15 @@ smb2_readv_callback(struct mid_q_entry *mid)
if (rdata->got_bytes) {
rqst.rq_iter = rdata->subreq.io_iter;
- rqst.rq_iter_size = iov_iter_count(&rdata->subreq.io_iter);
}
WARN_ONCE(rdata->server != mid->server,
"rdata server %p != mid server %p",
rdata->server, mid->server);
- cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu\n",
+ cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu/%zu\n",
__func__, mid->mid, mid->mid_state, rdata->result,
- rdata->subreq.len);
+ rdata->actual_len, rdata->subreq.len - rdata->subreq.transferred);
switch (mid->mid_state) {
case MID_RESPONSE_RECEIVED:
@@ -4586,22 +4586,29 @@ smb2_readv_callback(struct mid_q_entry *mid)
rdata->subreq.debug_index,
rdata->xid,
rdata->req->cfile->fid.persistent_fid,
- tcon->tid, tcon->ses->Suid, rdata->subreq.start,
- rdata->subreq.len, rdata->result);
+ tcon->tid, tcon->ses->Suid,
+ rdata->subreq.start + rdata->subreq.transferred,
+ rdata->actual_len,
+ rdata->result);
} else
trace_smb3_read_done(rdata->rreq->debug_id,
rdata->subreq.debug_index,
rdata->xid,
rdata->req->cfile->fid.persistent_fid,
tcon->tid, tcon->ses->Suid,
- rdata->subreq.start, rdata->got_bytes);
+ rdata->subreq.start + rdata->subreq.transferred,
+ rdata->got_bytes);
if (rdata->result == -ENODATA) {
- /* We may have got an EOF error because fallocate
- * failed to enlarge the file.
- */
- if (rdata->subreq.start < rdata->subreq.rreq->i_size)
+ __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags);
+ rdata->result = 0;
+ } else {
+ if (rdata->got_bytes < rdata->actual_len &&
+ rdata->subreq.start + rdata->subreq.transferred + rdata->got_bytes ==
+ ictx->remote_i_size) {
+ __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags);
rdata->result = 0;
+ }
}
trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value,
server->credits, server->in_flight,
@@ -4622,6 +4629,7 @@ smb2_async_readv(struct cifs_io_subrequest *rdata)
{
int rc, flags = 0;
char *buf;
+ struct netfs_io_subrequest *subreq = &rdata->subreq;
struct smb2_hdr *shdr;
struct cifs_io_parms io_parms;
struct smb_rqst rqst = { .rq_iov = rdata->iov,
@@ -4632,15 +4640,15 @@ smb2_async_readv(struct cifs_io_subrequest *rdata)
int credit_request;
cifs_dbg(FYI, "%s: offset=%llu bytes=%zu\n",
- __func__, rdata->subreq.start, rdata->subreq.len);
+ __func__, subreq->start, subreq->len);
if (!rdata->server)
rdata->server = cifs_pick_channel(tcon->ses);
io_parms.tcon = tlink_tcon(rdata->req->cfile->tlink);
io_parms.server = server = rdata->server;
- io_parms.offset = rdata->subreq.start;
- io_parms.length = rdata->subreq.len;
+ io_parms.offset = subreq->start + subreq->transferred;
+ io_parms.length = rdata->actual_len;
io_parms.persistent_fid = rdata->req->cfile->fid.persistent_fid;
io_parms.volatile_fid = rdata->req->cfile->fid.volatile_fid;
io_parms.pid = rdata->req->pid;
@@ -4655,11 +4663,13 @@ smb2_async_readv(struct cifs_io_subrequest *rdata)
rdata->iov[0].iov_base = buf;
rdata->iov[0].iov_len = total_len;
+ rdata->got_bytes = 0;
+ rdata->result = 0;
shdr = (struct smb2_hdr *)buf;
if (rdata->credits.value > 0) {
- shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->subreq.len,
+ shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->actual_len,
SMB2_MAX_BUFFER_SIZE));
credit_request = le16_to_cpu(shdr->CreditCharge) + 8;
if (server->credits >= server->max_credits)
@@ -4683,11 +4693,11 @@ smb2_async_readv(struct cifs_io_subrequest *rdata)
if (rc) {
cifs_stats_fail_inc(io_parms.tcon, SMB2_READ_HE);
trace_smb3_read_err(rdata->rreq->debug_id,
- rdata->subreq.debug_index,
+ subreq->debug_index,
rdata->xid, io_parms.persistent_fid,
io_parms.tcon->tid,
io_parms.tcon->ses->Suid,
- io_parms.offset, io_parms.length, rc);
+ io_parms.offset, rdata->actual_len, rc);
}
async_readv_out:
@@ -4914,6 +4924,13 @@ smb2_async_writev(struct cifs_io_subrequest *wdata)
if (rc)
goto out;
+ rqst.rq_iov = iov;
+ rqst.rq_iter = wdata->subreq.io_iter;
+
+ rqst.rq_iov[0].iov_len = total_len - 1;
+ rqst.rq_iov[0].iov_base = (char *)req;
+ rqst.rq_nvec += 1;
+
if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
@@ -4925,6 +4942,7 @@ smb2_async_writev(struct cifs_io_subrequest *wdata)
req->WriteChannelInfoOffset = 0;
req->WriteChannelInfoLength = 0;
req->Channel = SMB2_CHANNEL_NONE;
+ req->Length = cpu_to_le32(io_parms->length);
req->Offset = cpu_to_le64(io_parms->offset);
req->DataOffset = cpu_to_le16(
offsetof(struct smb2_write_req, Buffer));
@@ -4944,7 +4962,6 @@ smb2_async_writev(struct cifs_io_subrequest *wdata)
*/
if (smb3_use_rdma_offload(io_parms)) {
struct smbd_buffer_descriptor_v1 *v1;
- size_t data_size = iov_iter_count(&wdata->subreq.io_iter);
bool need_invalidate = server->dialect == SMB30_PROT_ID;
wdata->mr = smbd_register_mr(server->smbd_conn, &wdata->subreq.io_iter,
@@ -4953,9 +4970,10 @@ smb2_async_writev(struct cifs_io_subrequest *wdata)
rc = -EAGAIN;
goto async_writev_out;
}
+ /* For RDMA read, I/O size is in RemainingBytes not in Length */
+ req->RemainingBytes = req->Length;
req->Length = 0;
req->DataOffset = 0;
- req->RemainingBytes = cpu_to_le32(data_size);
req->Channel = SMB2_CHANNEL_RDMA_V1_INVALIDATE;
if (need_invalidate)
req->Channel = SMB2_CHANNEL_RDMA_V1;
@@ -4967,31 +4985,22 @@ smb2_async_writev(struct cifs_io_subrequest *wdata)
v1->offset = cpu_to_le64(wdata->mr->mr->iova);
v1->token = cpu_to_le32(wdata->mr->mr->rkey);
v1->length = cpu_to_le32(wdata->mr->mr->length);
+
+ rqst.rq_iov[0].iov_len += sizeof(*v1);
+
+ /*
+ * We keep wdata->subreq.io_iter,
+ * but we have to truncate rqst.rq_iter
+ */
+ iov_iter_truncate(&rqst.rq_iter, 0);
}
#endif
- iov[0].iov_len = total_len - 1;
- iov[0].iov_base = (char *)req;
- rqst.rq_iov = iov;
- rqst.rq_nvec = 1;
- rqst.rq_iter = wdata->subreq.io_iter;
- rqst.rq_iter_size = iov_iter_count(&rqst.rq_iter);
if (test_bit(NETFS_SREQ_RETRYING, &wdata->subreq.flags))
smb2_set_replay(server, &rqst);
-#ifdef CONFIG_CIFS_SMB_DIRECT
- if (wdata->mr)
- iov[0].iov_len += sizeof(struct smbd_buffer_descriptor_v1);
-#endif
- cifs_dbg(FYI, "async write at %llu %u bytes iter=%zx\n",
- io_parms->offset, io_parms->length, iov_iter_count(&rqst.rq_iter));
-#ifdef CONFIG_CIFS_SMB_DIRECT
- /* For RDMA read, I/O size is in RemainingBytes not in Length */
- if (!wdata->mr)
- req->Length = cpu_to_le32(io_parms->length);
-#else
- req->Length = cpu_to_le32(io_parms->length);
-#endif
+ cifs_dbg(FYI, "async write at %llu %u bytes iter=%zx\n",
+ io_parms->offset, io_parms->length, iov_iter_count(&wdata->subreq.io_iter));
if (wdata->credits.value > 0) {
shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->subreq.len,
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index 0f0c10c..8e99640 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -30,6 +30,7 @@
EM(cifs_trace_rw_credits_old_session, "old-session") \
EM(cifs_trace_rw_credits_read_response_add, "rd-resp-add") \
EM(cifs_trace_rw_credits_read_response_clear, "rd-resp-clr") \
+ EM(cifs_trace_rw_credits_read_resubmit, "rd-resubmit") \
EM(cifs_trace_rw_credits_read_submit, "rd-submit ") \
EM(cifs_trace_rw_credits_write_prepare, "wr-prepare ") \
EM(cifs_trace_rw_credits_write_response_add, "wr-resp-add") \
diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h
index c3ee421..c769f9d 100644
--- a/fs/smb/common/smb2pdu.h
+++ b/fs/smb/common/smb2pdu.h
@@ -1216,6 +1216,8 @@ struct create_context {
);
__u8 Buffer[];
} __packed;
+static_assert(offsetof(struct create_context, Buffer) == sizeof(struct create_context_hdr),
+ "struct member likely outside of __struct_group()");
struct smb2_create_req {
struct smb2_hdr hdr;
diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c
index 09e1e77..7889df8 100644
--- a/fs/smb/server/connection.c
+++ b/fs/smb/server/connection.c
@@ -165,11 +165,43 @@ void ksmbd_all_conn_set_status(u64 sess_id, u32 status)
up_read(&conn_list_lock);
}
-void ksmbd_conn_wait_idle(struct ksmbd_conn *conn, u64 sess_id)
+void ksmbd_conn_wait_idle(struct ksmbd_conn *conn)
{
wait_event(conn->req_running_q, atomic_read(&conn->req_running) < 2);
}
+int ksmbd_conn_wait_idle_sess_id(struct ksmbd_conn *curr_conn, u64 sess_id)
+{
+ struct ksmbd_conn *conn;
+ int rc, retry_count = 0, max_timeout = 120;
+ int rcount = 1;
+
+retry_idle:
+ if (retry_count >= max_timeout)
+ return -EIO;
+
+ down_read(&conn_list_lock);
+ list_for_each_entry(conn, &conn_list, conns_list) {
+ if (conn->binding || xa_load(&conn->sessions, sess_id)) {
+ if (conn == curr_conn)
+ rcount = 2;
+ if (atomic_read(&conn->req_running) >= rcount) {
+ rc = wait_event_timeout(conn->req_running_q,
+ atomic_read(&conn->req_running) < rcount,
+ HZ);
+ if (!rc) {
+ up_read(&conn_list_lock);
+ retry_count++;
+ goto retry_idle;
+ }
+ }
+ }
+ }
+ up_read(&conn_list_lock);
+
+ return 0;
+}
+
int ksmbd_conn_write(struct ksmbd_work *work)
{
struct ksmbd_conn *conn = work->conn;
diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h
index 5c2845e..5b94717 100644
--- a/fs/smb/server/connection.h
+++ b/fs/smb/server/connection.h
@@ -145,7 +145,8 @@ extern struct list_head conn_list;
extern struct rw_semaphore conn_list_lock;
bool ksmbd_conn_alive(struct ksmbd_conn *conn);
-void ksmbd_conn_wait_idle(struct ksmbd_conn *conn, u64 sess_id);
+void ksmbd_conn_wait_idle(struct ksmbd_conn *conn);
+int ksmbd_conn_wait_idle_sess_id(struct ksmbd_conn *curr_conn, u64 sess_id);
struct ksmbd_conn *ksmbd_conn_alloc(void);
void ksmbd_conn_free(struct ksmbd_conn *conn);
bool ksmbd_conn_lookup_dialect(struct ksmbd_conn *c);
diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c
index e0a6b75..d8d0307 100644
--- a/fs/smb/server/mgmt/share_config.c
+++ b/fs/smb/server/mgmt/share_config.c
@@ -15,6 +15,7 @@
#include "share_config.h"
#include "user_config.h"
#include "user_session.h"
+#include "../connection.h"
#include "../transport_ipc.h"
#include "../misc.h"
@@ -120,12 +121,13 @@ static int parse_veto_list(struct ksmbd_share_config *share,
return 0;
}
-static struct ksmbd_share_config *share_config_request(struct unicode_map *um,
+static struct ksmbd_share_config *share_config_request(struct ksmbd_work *work,
const char *name)
{
struct ksmbd_share_config_response *resp;
struct ksmbd_share_config *share = NULL;
struct ksmbd_share_config *lookup;
+ struct unicode_map *um = work->conn->um;
int ret;
resp = ksmbd_ipc_share_config_request(name);
@@ -181,7 +183,14 @@ static struct ksmbd_share_config *share_config_request(struct unicode_map *um,
KSMBD_SHARE_CONFIG_VETO_LIST(resp),
resp->veto_list_sz);
if (!ret && share->path) {
+ if (__ksmbd_override_fsids(work, share)) {
+ kill_share(share);
+ share = NULL;
+ goto out;
+ }
+
ret = kern_path(share->path, 0, &share->vfs_path);
+ ksmbd_revert_fsids(work);
if (ret) {
ksmbd_debug(SMB, "failed to access '%s'\n",
share->path);
@@ -214,7 +223,7 @@ static struct ksmbd_share_config *share_config_request(struct unicode_map *um,
return share;
}
-struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um,
+struct ksmbd_share_config *ksmbd_share_config_get(struct ksmbd_work *work,
const char *name)
{
struct ksmbd_share_config *share;
@@ -227,7 +236,7 @@ struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um,
if (share)
return share;
- return share_config_request(um, name);
+ return share_config_request(work, name);
}
bool ksmbd_share_veto_filename(struct ksmbd_share_config *share,
diff --git a/fs/smb/server/mgmt/share_config.h b/fs/smb/server/mgmt/share_config.h
index 5f59175..d4ac2dd 100644
--- a/fs/smb/server/mgmt/share_config.h
+++ b/fs/smb/server/mgmt/share_config.h
@@ -11,6 +11,8 @@
#include <linux/path.h>
#include <linux/unicode.h>
+struct ksmbd_work;
+
struct ksmbd_share_config {
char *name;
char *path;
@@ -68,7 +70,7 @@ static inline void ksmbd_share_config_put(struct ksmbd_share_config *share)
__ksmbd_share_config_put(share);
}
-struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um,
+struct ksmbd_share_config *ksmbd_share_config_get(struct ksmbd_work *work,
const char *name);
bool ksmbd_share_veto_filename(struct ksmbd_share_config *share,
const char *filename);
diff --git a/fs/smb/server/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c
index d2c81a8..94a52a7 100644
--- a/fs/smb/server/mgmt/tree_connect.c
+++ b/fs/smb/server/mgmt/tree_connect.c
@@ -16,17 +16,18 @@
#include "user_session.h"
struct ksmbd_tree_conn_status
-ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess,
- const char *share_name)
+ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name)
{
struct ksmbd_tree_conn_status status = {-ENOENT, NULL};
struct ksmbd_tree_connect_response *resp = NULL;
struct ksmbd_share_config *sc;
struct ksmbd_tree_connect *tree_conn = NULL;
struct sockaddr *peer_addr;
+ struct ksmbd_conn *conn = work->conn;
+ struct ksmbd_session *sess = work->sess;
int ret;
- sc = ksmbd_share_config_get(conn->um, share_name);
+ sc = ksmbd_share_config_get(work, share_name);
if (!sc)
return status;
@@ -61,7 +62,7 @@ ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess,
struct ksmbd_share_config *new_sc;
ksmbd_share_config_del(sc);
- new_sc = ksmbd_share_config_get(conn->um, share_name);
+ new_sc = ksmbd_share_config_get(work, share_name);
if (!new_sc) {
pr_err("Failed to update stale share config\n");
status.ret = -ESTALE;
diff --git a/fs/smb/server/mgmt/tree_connect.h b/fs/smb/server/mgmt/tree_connect.h
index 6377a70..a42cdd0 100644
--- a/fs/smb/server/mgmt/tree_connect.h
+++ b/fs/smb/server/mgmt/tree_connect.h
@@ -13,6 +13,7 @@
struct ksmbd_share_config;
struct ksmbd_user;
struct ksmbd_conn;
+struct ksmbd_work;
enum {
TREE_NEW = 0,
@@ -50,8 +51,7 @@ static inline int test_tree_conn_flag(struct ksmbd_tree_connect *tree_conn,
struct ksmbd_session;
struct ksmbd_tree_conn_status
-ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess,
- const char *share_name);
+ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name);
void ksmbd_tree_connect_put(struct ksmbd_tree_connect *tcon);
int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess,
diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c
index 162a126..99416ce 100644
--- a/fs/smb/server/mgmt/user_session.c
+++ b/fs/smb/server/mgmt/user_session.c
@@ -311,6 +311,7 @@ void destroy_previous_session(struct ksmbd_conn *conn,
{
struct ksmbd_session *prev_sess;
struct ksmbd_user *prev_user;
+ int err;
down_write(&sessions_table_lock);
down_write(&conn->session_lock);
@@ -325,8 +326,16 @@ void destroy_previous_session(struct ksmbd_conn *conn,
memcmp(user->passkey, prev_user->passkey, user->passkey_sz))
goto out;
+ ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_RECONNECT);
+ err = ksmbd_conn_wait_idle_sess_id(conn, id);
+ if (err) {
+ ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_NEGOTIATE);
+ goto out;
+ }
+
ksmbd_destroy_file_table(&prev_sess->file_table);
prev_sess->state = SMB2_SESSION_EXPIRED;
+ ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_NEGOTIATE);
ksmbd_launch_ksmbd_durable_scavenger();
out:
up_write(&conn->session_lock);
diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
index a8f52c4..e546ffa 100644
--- a/fs/smb/server/oplock.c
+++ b/fs/smb/server/oplock.c
@@ -1510,7 +1510,7 @@ void create_lease_buf(u8 *rbuf, struct lease *lease)
* parse_lease_state() - parse lease context containted in file open request
* @open_req: buffer containing smb2 file open(create) request
*
- * Return: oplock state, -ENOENT if create lease context not found
+ * Return: allocated lease context object on success, otherwise NULL
*/
struct lease_ctx_info *parse_lease_state(void *open_req)
{
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 37a39ab..20846a4 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -519,7 +519,7 @@ int init_smb2_rsp_hdr(struct ksmbd_work *work)
* smb2_allocate_rsp_buf() - allocate smb2 response buffer
* @work: smb work containing smb request buffer
*
- * Return: 0 on success, otherwise -ENOMEM
+ * Return: 0 on success, otherwise error
*/
int smb2_allocate_rsp_buf(struct ksmbd_work *work)
{
@@ -1370,7 +1370,8 @@ static int ntlm_negotiate(struct ksmbd_work *work,
}
sz = le16_to_cpu(rsp->SecurityBufferOffset);
- memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, spnego_blob_len);
+ unsafe_memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, spnego_blob_len,
+ /* alloc is larger than blob, see smb2_allocate_rsp_buf() */);
rsp->SecurityBufferLength = cpu_to_le16(spnego_blob_len);
out:
@@ -1453,7 +1454,9 @@ static int ntlm_authenticate(struct ksmbd_work *work,
return -ENOMEM;
sz = le16_to_cpu(rsp->SecurityBufferOffset);
- memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, spnego_blob_len);
+ unsafe_memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob,
+ spnego_blob_len,
+ /* alloc is larger than blob, see smb2_allocate_rsp_buf() */);
rsp->SecurityBufferLength = cpu_to_le16(spnego_blob_len);
kfree(spnego_blob);
}
@@ -1955,7 +1958,7 @@ int smb2_tree_connect(struct ksmbd_work *work)
ksmbd_debug(SMB, "tree connect request for tree %s treename %s\n",
name, treename);
- status = ksmbd_tree_conn_connect(conn, sess, name);
+ status = ksmbd_tree_conn_connect(work, name);
if (status.ret == KSMBD_TREE_CONN_STATUS_OK)
rsp->hdr.Id.SyncId.TreeId = cpu_to_le32(status.tree_conn->id);
else
@@ -2210,7 +2213,7 @@ int smb2_session_logoff(struct ksmbd_work *work)
ksmbd_conn_unlock(conn);
ksmbd_close_session_fds(work);
- ksmbd_conn_wait_idle(conn, sess_id);
+ ksmbd_conn_wait_idle(conn);
/*
* Re-lookup session to validate if session is deleted
@@ -2767,8 +2770,8 @@ static int parse_durable_handle_context(struct ksmbd_work *work,
}
}
- if (((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) ||
- req_op_level == SMB2_OPLOCK_LEVEL_BATCH)) {
+ if ((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) ||
+ req_op_level == SMB2_OPLOCK_LEVEL_BATCH) {
dh_info->CreateGuid =
durable_v2_blob->CreateGuid;
dh_info->persistent =
@@ -2788,8 +2791,8 @@ static int parse_durable_handle_context(struct ksmbd_work *work,
goto out;
}
- if (((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) ||
- req_op_level == SMB2_OPLOCK_LEVEL_BATCH)) {
+ if ((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) ||
+ req_op_level == SMB2_OPLOCK_LEVEL_BATCH) {
ksmbd_debug(SMB, "Request for durable open\n");
dh_info->type = dh_idx;
}
@@ -3093,7 +3096,6 @@ int smb2_open(struct ksmbd_work *work)
goto err_out;
}
- file_present = true;
idmap = mnt_idmap(path.mnt);
} else {
if (rc != -ENOENT)
@@ -3411,7 +3413,7 @@ int smb2_open(struct ksmbd_work *work)
goto err_out1;
}
} else {
- if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) {
+ if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE && lc) {
if (S_ISDIR(file_inode(filp)->i_mode)) {
lc->req_state &= ~SMB2_LEASE_WRITE_CACHING_LE;
lc->is_dir = true;
@@ -3710,7 +3712,7 @@ int smb2_open(struct ksmbd_work *work)
kfree(name);
kfree(lc);
- return 0;
+ return rc;
}
static int readdir_info_level_struct_sz(int info_level)
@@ -4406,7 +4408,8 @@ int smb2_query_dir(struct ksmbd_work *work)
rsp->OutputBufferLength = cpu_to_le32(0);
rsp->Buffer[0] = 0;
rc = ksmbd_iov_pin_rsp(work, (void *)rsp,
- sizeof(struct smb2_query_directory_rsp));
+ offsetof(struct smb2_query_directory_rsp, Buffer)
+ + 1);
if (rc)
goto err_out;
} else {
@@ -5357,7 +5360,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
"NTFS", PATH_MAX, conn->local_nls, 0);
len = len * 2;
info->FileSystemNameLen = cpu_to_le32(len);
- sz = sizeof(struct filesystem_attribute_info) - 2 + len;
+ sz = sizeof(struct filesystem_attribute_info) + len;
rsp->OutputBufferLength = cpu_to_le32(sz);
break;
}
@@ -5383,7 +5386,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
len = len * 2;
info->VolumeLabelSize = cpu_to_le32(len);
info->Reserved = 0;
- sz = sizeof(struct filesystem_vol_info) - 2 + len;
+ sz = sizeof(struct filesystem_vol_info) + len;
rsp->OutputBufferLength = cpu_to_le32(sz);
break;
}
@@ -5596,6 +5599,11 @@ int smb2_query_info(struct ksmbd_work *work)
ksmbd_debug(SMB, "GOT query info request\n");
+ if (ksmbd_override_fsids(work)) {
+ rc = -ENOMEM;
+ goto err_out;
+ }
+
switch (req->InfoType) {
case SMB2_O_INFO_FILE:
ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILE\n");
@@ -5614,6 +5622,7 @@ int smb2_query_info(struct ksmbd_work *work)
req->InfoType);
rc = -EOPNOTSUPP;
}
+ ksmbd_revert_fsids(work);
if (!rc) {
rsp->StructureSize = cpu_to_le16(9);
@@ -5623,6 +5632,7 @@ int smb2_query_info(struct ksmbd_work *work)
le32_to_cpu(rsp->OutputBufferLength));
}
+err_out:
if (rc < 0) {
if (rc == -EACCES)
rsp->hdr.Status = STATUS_ACCESS_DENIED;
diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c
index 474dadf..13818ec 100644
--- a/fs/smb/server/smb_common.c
+++ b/fs/smb/server/smb_common.c
@@ -732,10 +732,10 @@ bool is_asterisk(char *p)
return p && p[0] == '*';
}
-int ksmbd_override_fsids(struct ksmbd_work *work)
+int __ksmbd_override_fsids(struct ksmbd_work *work,
+ struct ksmbd_share_config *share)
{
struct ksmbd_session *sess = work->sess;
- struct ksmbd_share_config *share = work->tcon->share_conf;
struct cred *cred;
struct group_info *gi;
unsigned int uid;
@@ -775,6 +775,11 @@ int ksmbd_override_fsids(struct ksmbd_work *work)
return 0;
}
+int ksmbd_override_fsids(struct ksmbd_work *work)
+{
+ return __ksmbd_override_fsids(work, work->tcon->share_conf);
+}
+
void ksmbd_revert_fsids(struct ksmbd_work *work)
{
const struct cred *cred;
diff --git a/fs/smb/server/smb_common.h b/fs/smb/server/smb_common.h
index f109251..cc1d6df 100644
--- a/fs/smb/server/smb_common.h
+++ b/fs/smb/server/smb_common.h
@@ -213,7 +213,7 @@ struct filesystem_attribute_info {
__le32 Attributes;
__le32 MaxPathNameComponentLength;
__le32 FileSystemNameLen;
- __le16 FileSystemName[1]; /* do not have to save this - get subset? */
+ __le16 FileSystemName[]; /* do not have to save this - get subset? */
} __packed;
struct filesystem_device_info {
@@ -226,7 +226,7 @@ struct filesystem_vol_info {
__le32 SerialNumber;
__le32 VolumeLabelSize;
__le16 Reserved;
- __le16 VolumeLabel[1];
+ __le16 VolumeLabel[];
} __packed;
struct filesystem_info {
@@ -447,6 +447,8 @@ int ksmbd_extract_shortname(struct ksmbd_conn *conn,
int ksmbd_smb_negotiate_common(struct ksmbd_work *work, unsigned int command);
int ksmbd_smb_check_shared_mode(struct file *filp, struct ksmbd_file *curr_fp);
+int __ksmbd_override_fsids(struct ksmbd_work *work,
+ struct ksmbd_share_config *share);
int ksmbd_override_fsids(struct ksmbd_work *work);
void ksmbd_revert_fsids(struct ksmbd_work *work);
diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c
index 16bd693..d5918eb 100644
--- a/fs/squashfs/inode.c
+++ b/fs/squashfs/inode.c
@@ -279,8 +279,13 @@ int squashfs_read_inode(struct inode *inode, long long ino)
if (err < 0)
goto failed_read;
- set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
inode->i_size = le32_to_cpu(sqsh_ino->symlink_size);
+ if (inode->i_size > PAGE_SIZE) {
+ ERROR("Corrupted symlink\n");
+ return -EINVAL;
+ }
+
+ set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
inode->i_op = &squashfs_symlink_inode_ops;
inode_nohighmem(inode);
inode->i_data.a_ops = &squashfs_symlink_aops;
diff --git a/fs/super.c b/fs/super.c
index 38d72a3..b7913b5 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1802,8 +1802,8 @@ int vfs_get_tree(struct fs_context *fc)
return error;
if (!fc->root) {
- pr_err("Filesystem %s get_tree() didn't set fc->root\n",
- fc->fs_type->name);
+ pr_err("Filesystem %s get_tree() didn't set fc->root, returned %i\n",
+ fc->fs_type->name, error);
/* We don't know what the locking state of the superblock is -
* if there is a superblock.
*/
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 496e2f7..797d5b5 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -749,7 +749,7 @@ xfs_finobt_count_blocks(
if (error)
return error;
- cur = xfs_inobt_init_cursor(pag, tp, agbp);
+ cur = xfs_finobt_init_cursor(pag, tp, agbp);
error = xfs_btree_count_blocks(cur, tree_blocks);
xfs_btree_del_cursor(cur, error);
xfs_trans_brelse(tp, agbp);
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 513b50d..79babea 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -514,12 +514,18 @@ xfs_dinode_verify(
return __this_address;
}
- if (dip->di_version > 1) {
+ /*
+ * Historical note: xfsprogs in the 3.2 era set up its incore inodes to
+ * have di_nlink track the link count, even if the actual filesystem
+ * only supported V1 inodes (i.e. di_onlink). When writing out the
+ * ondisk inode, it would set both the ondisk di_nlink and di_onlink to
+ * the the incore di_nlink value, which is why we cannot check for
+ * di_nlink==0 on a V1 inode. V2/3 inodes would get written out with
+ * di_onlink==0, so we can check that.
+ */
+ if (dip->di_version >= 2) {
if (dip->di_onlink)
return __this_address;
- } else {
- if (dip->di_nlink)
- return __this_address;
}
/* don't allow invalid i_size */
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 24a15bf..5ab2ac5 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -938,7 +938,13 @@ xchk_bmap(
}
break;
case XFS_ATTR_FORK:
- if (!xfs_has_attr(mp) && !xfs_has_attr2(mp))
+ /*
+ * "attr" means that an attr fork was created at some point in
+ * the life of this filesystem. "attr2" means that inodes have
+ * variable-sized data/attr fork areas. Hence we only check
+ * attr here.
+ */
+ if (!xfs_has_attr(mp))
xchk_ino_set_corrupt(sc, sc->ip->i_ino);
break;
default:
diff --git a/fs/xfs/scrub/xfile.c b/fs/xfs/scrub/xfile.c
index d848222..9b5d98f 100644
--- a/fs/xfs/scrub/xfile.c
+++ b/fs/xfs/scrub/xfile.c
@@ -293,7 +293,7 @@ xfile_get_folio(
* (potentially last) reference in xfile_put_folio.
*/
if (flags & XFILE_ALLOC)
- folio_set_dirty(folio);
+ folio_mark_dirty(folio);
return folio;
}
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 6f0fc7f..25f5dff 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -158,8 +158,7 @@ static int
xfs_trim_gather_extents(
struct xfs_perag *pag,
struct xfs_trim_cur *tcur,
- struct xfs_busy_extents *extents,
- uint64_t *blocks_trimmed)
+ struct xfs_busy_extents *extents)
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_trans *tp;
@@ -280,7 +279,6 @@ xfs_trim_gather_extents(
xfs_extent_busy_insert_discard(pag, fbno, flen,
&extents->extent_list);
- *blocks_trimmed += flen;
next_extent:
if (tcur->by_bno)
error = xfs_btree_increment(cur, 0, &i);
@@ -327,8 +325,7 @@ xfs_trim_perag_extents(
struct xfs_perag *pag,
xfs_agblock_t start,
xfs_agblock_t end,
- xfs_extlen_t minlen,
- uint64_t *blocks_trimmed)
+ xfs_extlen_t minlen)
{
struct xfs_trim_cur tcur = {
.start = start,
@@ -354,8 +351,7 @@ xfs_trim_perag_extents(
extents->owner = extents;
INIT_LIST_HEAD(&extents->extent_list);
- error = xfs_trim_gather_extents(pag, &tcur, extents,
- blocks_trimmed);
+ error = xfs_trim_gather_extents(pag, &tcur, extents);
if (error) {
kfree(extents);
break;
@@ -389,8 +385,7 @@ xfs_trim_datadev_extents(
struct xfs_mount *mp,
xfs_daddr_t start,
xfs_daddr_t end,
- xfs_extlen_t minlen,
- uint64_t *blocks_trimmed)
+ xfs_extlen_t minlen)
{
xfs_agnumber_t start_agno, end_agno;
xfs_agblock_t start_agbno, end_agbno;
@@ -411,8 +406,7 @@ xfs_trim_datadev_extents(
if (start_agno == end_agno)
agend = end_agbno;
- error = xfs_trim_perag_extents(pag, start_agbno, agend, minlen,
- blocks_trimmed);
+ error = xfs_trim_perag_extents(pag, start_agbno, agend, minlen);
if (error)
last_error = error;
@@ -431,9 +425,6 @@ struct xfs_trim_rtdev {
/* list of rt extents to free */
struct list_head extent_list;
- /* pointer to count of blocks trimmed */
- uint64_t *blocks_trimmed;
-
/* minimum length that caller allows us to trim */
xfs_rtblock_t minlen_fsb;
@@ -551,7 +542,6 @@ xfs_trim_gather_rtextent(
busyp->length = rlen;
INIT_LIST_HEAD(&busyp->list);
list_add_tail(&busyp->list, &tr->extent_list);
- *tr->blocks_trimmed += rlen;
tr->restart_rtx = rec->ar_startext + rec->ar_extcount;
return 0;
@@ -562,13 +552,11 @@ xfs_trim_rtdev_extents(
struct xfs_mount *mp,
xfs_daddr_t start,
xfs_daddr_t end,
- xfs_daddr_t minlen,
- uint64_t *blocks_trimmed)
+ xfs_daddr_t minlen)
{
struct xfs_rtalloc_rec low = { };
struct xfs_rtalloc_rec high = { };
struct xfs_trim_rtdev tr = {
- .blocks_trimmed = blocks_trimmed,
.minlen_fsb = XFS_BB_TO_FSB(mp, minlen),
};
struct xfs_trans *tp;
@@ -634,7 +622,7 @@ xfs_trim_rtdev_extents(
return error;
}
#else
-# define xfs_trim_rtdev_extents(m,s,e,n,b) (-EOPNOTSUPP)
+# define xfs_trim_rtdev_extents(...) (-EOPNOTSUPP)
#endif /* CONFIG_XFS_RT */
/*
@@ -661,7 +649,6 @@ xfs_ioc_trim(
xfs_daddr_t start, end;
xfs_extlen_t minlen;
xfs_rfsblock_t max_blocks;
- uint64_t blocks_trimmed = 0;
int error, last_error = 0;
if (!capable(CAP_SYS_ADMIN))
@@ -706,15 +693,13 @@ xfs_ioc_trim(
end = start + BTOBBT(range.len) - 1;
if (bdev_max_discard_sectors(mp->m_ddev_targp->bt_bdev)) {
- error = xfs_trim_datadev_extents(mp, start, end, minlen,
- &blocks_trimmed);
+ error = xfs_trim_datadev_extents(mp, start, end, minlen);
if (error)
last_error = error;
}
if (rt_bdev && !xfs_trim_should_stop()) {
- error = xfs_trim_rtdev_extents(mp, start, end, minlen,
- &blocks_trimmed);
+ error = xfs_trim_rtdev_extents(mp, start, end, minlen);
if (error)
last_error = error;
}
@@ -722,7 +707,8 @@ xfs_ioc_trim(
if (last_error)
return last_error;
- range.len = XFS_FSB_TO_B(mp, blocks_trimmed);
+ range.len = min_t(unsigned long long, range.len,
+ XFS_FSB_TO_B(mp, max_blocks));
if (copy_to_user(urange, &range, sizeof(range)))
return -EFAULT;
return 0;
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 85dbb464..71f3235 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -71,7 +71,7 @@ xfs_fsmap_owner_to_rmap(
switch (src->fmr_owner) {
case 0: /* "lowest owner id possible" */
case -1ULL: /* "highest owner id possible" */
- dest->rm_owner = 0;
+ dest->rm_owner = src->fmr_owner;
break;
case XFS_FMR_OWN_FREE:
dest->rm_owner = XFS_RMAP_OWN_NULL;
@@ -162,6 +162,7 @@ struct xfs_getfsmap_info {
xfs_daddr_t next_daddr; /* next daddr we expect */
/* daddr of low fsmap key when we're using the rtbitmap */
xfs_daddr_t low_daddr;
+ xfs_daddr_t end_daddr; /* daddr of high fsmap key */
u64 missing_owner; /* owner of holes */
u32 dev; /* device id */
/*
@@ -182,6 +183,7 @@ struct xfs_getfsmap_dev {
int (*fn)(struct xfs_trans *tp,
const struct xfs_fsmap *keys,
struct xfs_getfsmap_info *info);
+ sector_t nr_sectors;
};
/* Compare two getfsmap device handlers. */
@@ -252,7 +254,7 @@ xfs_getfsmap_rec_before_start(
const struct xfs_rmap_irec *rec,
xfs_daddr_t rec_daddr)
{
- if (info->low_daddr != -1ULL)
+ if (info->low_daddr != XFS_BUF_DADDR_NULL)
return rec_daddr < info->low_daddr;
if (info->low.rm_blockcount)
return xfs_rmap_compare(rec, &info->low) < 0;
@@ -294,6 +296,18 @@ xfs_getfsmap_helper(
return 0;
}
+ /*
+ * For an info->last query, we're looking for a gap between the last
+ * mapping emitted and the high key specified by userspace. If the
+ * user's query spans less than 1 fsblock, then info->high and
+ * info->low will have the same rm_startblock, which causes rec_daddr
+ * and next_daddr to be the same. Therefore, use the end_daddr that
+ * we calculated from userspace's high key to synthesize the record.
+ * Note that if the btree query found a mapping, there won't be a gap.
+ */
+ if (info->last && info->end_daddr != XFS_BUF_DADDR_NULL)
+ rec_daddr = info->end_daddr;
+
/* Are we just counting mappings? */
if (info->head->fmh_count == 0) {
if (info->head->fmh_entries == UINT_MAX)
@@ -904,17 +918,21 @@ xfs_getfsmap(
/* Set up our device handlers. */
memset(handlers, 0, sizeof(handlers));
+ handlers[0].nr_sectors = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
handlers[0].dev = new_encode_dev(mp->m_ddev_targp->bt_dev);
if (use_rmap)
handlers[0].fn = xfs_getfsmap_datadev_rmapbt;
else
handlers[0].fn = xfs_getfsmap_datadev_bnobt;
if (mp->m_logdev_targp != mp->m_ddev_targp) {
+ handlers[1].nr_sectors = XFS_FSB_TO_BB(mp,
+ mp->m_sb.sb_logblocks);
handlers[1].dev = new_encode_dev(mp->m_logdev_targp->bt_dev);
handlers[1].fn = xfs_getfsmap_logdev;
}
#ifdef CONFIG_XFS_RT
if (mp->m_rtdev_targp) {
+ handlers[2].nr_sectors = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks);
handlers[2].dev = new_encode_dev(mp->m_rtdev_targp->bt_dev);
handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap;
}
@@ -946,6 +964,7 @@ xfs_getfsmap(
info.next_daddr = head->fmh_keys[0].fmr_physical +
head->fmh_keys[0].fmr_length;
+ info.end_daddr = XFS_BUF_DADDR_NULL;
info.fsmap_recs = fsmap_recs;
info.head = head;
@@ -966,8 +985,11 @@ xfs_getfsmap(
* low key, zero out the low key so that we get
* everything from the beginning.
*/
- if (handlers[i].dev == head->fmh_keys[1].fmr_device)
+ if (handlers[i].dev == head->fmh_keys[1].fmr_device) {
dkeys[1] = head->fmh_keys[1];
+ info.end_daddr = min(handlers[i].nr_sectors - 1,
+ dkeys[1].fmr_physical);
+ }
if (handlers[i].dev > head->fmh_keys[0].fmr_device)
memset(&dkeys[0], 0, sizeof(struct xfs_fsmap));
@@ -983,7 +1005,7 @@ xfs_getfsmap(
info.dev = handlers[i].dev;
info.last = false;
info.pag = NULL;
- info.low_daddr = -1ULL;
+ info.low_daddr = XFS_BUF_DADDR_NULL;
info.low.rm_blockcount = 0;
error = handlers[i].fn(tp, dkeys, &info);
if (error)
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 4e933db..6b13666 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -483,6 +483,17 @@ xfs_ioctl_setattr_xflags(
/* Can't change realtime flag if any extents are allocated. */
if (ip->i_df.if_nextents || ip->i_delayed_blks)
return -EINVAL;
+
+ /*
+ * If S_DAX is enabled on this file, we can only switch the
+ * device if both support fsdax. We can't update S_DAX because
+ * there might be other threads walking down the access paths.
+ */
+ if (IS_DAX(VFS_I(ip)) &&
+ (mp->m_ddev_targp->bt_daxdev == NULL ||
+ (mp->m_rtdev_targp &&
+ mp->m_rtdev_targp->bt_daxdev == NULL)))
+ return -EINVAL;
}
if (rtflag) {
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 0c3e96c..ebeab8e 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -785,6 +785,39 @@ xfs_alloc_rsum_cache(
}
/*
+ * If we changed the rt extent size (meaning there was no rt volume previously)
+ * and the root directory had EXTSZINHERIT and RTINHERIT set, it's possible
+ * that the extent size hint on the root directory is no longer congruent with
+ * the new rt extent size. Log the rootdir inode to fix this.
+ */
+static int
+xfs_growfs_rt_fixup_extsize(
+ struct xfs_mount *mp)
+{
+ struct xfs_inode *ip = mp->m_rootip;
+ struct xfs_trans *tp;
+ int error = 0;
+
+ xfs_ilock(ip, XFS_IOLOCK_EXCL);
+ if (!(ip->i_diflags & XFS_DIFLAG_RTINHERIT) ||
+ !(ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT))
+ goto out_iolock;
+
+ error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_ichange, 0, 0, false,
+ &tp);
+ if (error)
+ goto out_iolock;
+
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+ error = xfs_trans_commit(tp);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+out_iolock:
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ return error;
+}
+
+/*
* Visible (exported) functions.
*/
@@ -812,6 +845,7 @@ xfs_growfs_rt(
xfs_extlen_t rsumblocks; /* current number of rt summary blks */
xfs_sb_t *sbp; /* old superblock */
uint8_t *rsum_cache; /* old summary cache */
+ xfs_agblock_t old_rextsize = mp->m_sb.sb_rextsize;
sbp = &mp->m_sb;
@@ -821,34 +855,39 @@ xfs_growfs_rt(
/* Needs to have been mounted with an rt device. */
if (!XFS_IS_REALTIME_MOUNT(mp))
return -EINVAL;
+
+ if (!mutex_trylock(&mp->m_growlock))
+ return -EWOULDBLOCK;
/*
* Mount should fail if the rt bitmap/summary files don't load, but
* we'll check anyway.
*/
+ error = -EINVAL;
if (!mp->m_rbmip || !mp->m_rsumip)
- return -EINVAL;
+ goto out_unlock;
/* Shrink not supported. */
if (in->newblocks <= sbp->sb_rblocks)
- return -EINVAL;
+ goto out_unlock;
/* Can only change rt extent size when adding rt volume. */
if (sbp->sb_rblocks > 0 && in->extsize != sbp->sb_rextsize)
- return -EINVAL;
+ goto out_unlock;
/* Range check the extent size. */
if (XFS_FSB_TO_B(mp, in->extsize) > XFS_MAX_RTEXTSIZE ||
XFS_FSB_TO_B(mp, in->extsize) < XFS_MIN_RTEXTSIZE)
- return -EINVAL;
+ goto out_unlock;
/* Unsupported realtime features. */
+ error = -EOPNOTSUPP;
if (xfs_has_rmapbt(mp) || xfs_has_reflink(mp) || xfs_has_quota(mp))
- return -EOPNOTSUPP;
+ goto out_unlock;
nrblocks = in->newblocks;
error = xfs_sb_validate_fsb_count(sbp, nrblocks);
if (error)
- return error;
+ goto out_unlock;
/*
* Read in the last block of the device, make sure it exists.
*/
@@ -856,7 +895,7 @@ xfs_growfs_rt(
XFS_FSB_TO_BB(mp, nrblocks - 1),
XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
if (error)
- return error;
+ goto out_unlock;
xfs_buf_relse(bp);
/*
@@ -864,8 +903,10 @@ xfs_growfs_rt(
*/
nrextents = nrblocks;
do_div(nrextents, in->extsize);
- if (!xfs_validate_rtextents(nrextents))
- return -EINVAL;
+ if (!xfs_validate_rtextents(nrextents)) {
+ error = -EINVAL;
+ goto out_unlock;
+ }
nrbmblocks = xfs_rtbitmap_blockcount(mp, nrextents);
nrextslog = xfs_compute_rextslog(nrextents);
nrsumlevels = nrextslog + 1;
@@ -876,8 +917,11 @@ xfs_growfs_rt(
* the log. This prevents us from getting a log overflow,
* since we'll log basically the whole summary file at once.
*/
- if (nrsumblocks > (mp->m_sb.sb_logblocks >> 1))
- return -EINVAL;
+ if (nrsumblocks > (mp->m_sb.sb_logblocks >> 1)) {
+ error = -EINVAL;
+ goto out_unlock;
+ }
+
/*
* Get the old block counts for bitmap and summary inodes.
* These can't change since other growfs callers are locked out.
@@ -889,10 +933,10 @@ xfs_growfs_rt(
*/
error = xfs_growfs_rt_alloc(mp, rbmblocks, nrbmblocks, mp->m_rbmip);
if (error)
- return error;
+ goto out_unlock;
error = xfs_growfs_rt_alloc(mp, rsumblocks, nrsumblocks, mp->m_rsumip);
if (error)
- return error;
+ goto out_unlock;
rsum_cache = mp->m_rsum_cache;
if (nrbmblocks != sbp->sb_rbmblocks)
@@ -1036,6 +1080,12 @@ xfs_growfs_rt(
if (error)
goto out_free;
+ if (old_rextsize != in->extsize) {
+ error = xfs_growfs_rt_fixup_extsize(mp);
+ if (error)
+ goto out_free;
+ }
+
/* Update secondary superblocks now the physical grow has completed */
error = xfs_update_secondary_sbs(mp);
@@ -1059,6 +1109,8 @@ xfs_growfs_rt(
}
}
+out_unlock:
+ mutex_unlock(&mp->m_growlock);
return error;
}
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 0fafcc9..8ede9d0 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -644,7 +644,12 @@ xfsaild(
set_freezable();
while (1) {
- if (tout)
+ /*
+ * Long waits of 50ms or more occur when we've run out of items
+ * to push, so we only want uninterruptible state if we're
+ * actually blocked on something.
+ */
+ if (tout && tout <= 20)
set_current_state(TASK_KILLABLE|TASK_FREEZABLE);
else
set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 80dc36f..9f1c1d2 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -660,13 +660,10 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status
void *context))
ACPI_EXTERNAL_RETURN_STATUS(acpi_status
acpi_execute_reg_methods(acpi_handle device,
+ u32 nax_depth,
acpi_adr_space_type
space_id))
ACPI_EXTERNAL_RETURN_STATUS(acpi_status
- acpi_execute_orphan_reg_method(acpi_handle device,
- acpi_adr_space_type
- space_id))
-ACPI_EXTERNAL_RETURN_STATUS(acpi_status
acpi_remove_address_space_handler(acpi_handle
device,
acpi_adr_space_type
diff --git a/include/acpi/video.h b/include/acpi/video.h
index 3d538d4..044c463 100644
--- a/include/acpi/video.h
+++ b/include/acpi/video.h
@@ -50,6 +50,7 @@ enum acpi_backlight_type {
acpi_backlight_native,
acpi_backlight_nvidia_wmi_ec,
acpi_backlight_apple_gmux,
+ acpi_backlight_dell_uart,
};
#if IS_ENABLED(CONFIG_ACPI_VIDEO)
diff --git a/include/drm/intel/i915_pciids.h b/include/drm/intel/i915_pciids.h
index b21374f..2bf03eb 100644
--- a/include/drm/intel/i915_pciids.h
+++ b/include/drm/intel/i915_pciids.h
@@ -772,15 +772,18 @@
INTEL_ATS_M75_IDS(MACRO__, ## __VA_ARGS__)
/* MTL */
-#define INTEL_MTL_IDS(MACRO__, ...) \
- MACRO__(0x7D40, ## __VA_ARGS__), \
+#define INTEL_ARL_IDS(MACRO__, ...) \
MACRO__(0x7D41, ## __VA_ARGS__), \
- MACRO__(0x7D45, ## __VA_ARGS__), \
MACRO__(0x7D51, ## __VA_ARGS__), \
+ MACRO__(0x7D67, ## __VA_ARGS__), \
+ MACRO__(0x7DD1, ## __VA_ARGS__)
+
+#define INTEL_MTL_IDS(MACRO__, ...) \
+ INTEL_ARL_IDS(MACRO__, ## __VA_ARGS__), \
+ MACRO__(0x7D40, ## __VA_ARGS__), \
+ MACRO__(0x7D45, ## __VA_ARGS__), \
MACRO__(0x7D55, ## __VA_ARGS__), \
MACRO__(0x7D60, ## __VA_ARGS__), \
- MACRO__(0x7D67, ## __VA_ARGS__), \
- MACRO__(0x7DD1, ## __VA_ARGS__), \
MACRO__(0x7DD5, ## __VA_ARGS__)
/* LNL */
diff --git a/include/drm/ttm/ttm_bo.h b/include/drm/ttm/ttm_bo.h
index ef0f52f..6ccf96c 100644
--- a/include/drm/ttm/ttm_bo.h
+++ b/include/drm/ttm/ttm_bo.h
@@ -39,11 +39,7 @@
#include "ttm_device.h"
/* Default number of pre-faulted pages in the TTM fault handler */
-#if CONFIG_PGTABLE_LEVELS > 2
-#define TTM_BO_VM_NUM_PREFAULT (1 << (PMD_SHIFT - PAGE_SHIFT))
-#else
#define TTM_BO_VM_NUM_PREFAULT 16
-#endif
struct iosys_map;
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 8c4768c..d3b66d7 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -270,6 +270,18 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst,
dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits);
}
+static inline void bitmap_copy_and_extend(unsigned long *to,
+ const unsigned long *from,
+ unsigned int count, unsigned int size)
+{
+ unsigned int copy = BITS_TO_LONGS(count);
+
+ memcpy(to, from, copy * sizeof(long));
+ if (count % BITS_PER_LONG)
+ to[copy - 1] &= BITMAP_LAST_WORD_MASK(count);
+ memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long));
+}
+
/*
* On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64
* machines the order of hi and lo parts of numbers match the bitmap structure.
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index e85ec73..b7664d5 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1296,12 +1296,7 @@ bdev_max_secure_erase_sectors(struct block_device *bdev)
static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev)
{
- struct request_queue *q = bdev_get_queue(bdev);
-
- if (q)
- return q->limits.max_write_zeroes_sectors;
-
- return 0;
+ return bdev_get_queue(bdev)->limits.max_write_zeroes_sectors;
}
static inline bool bdev_nonrot(struct block_device *bdev)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 6503c85..7b776da 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -856,8 +856,8 @@ static inline u32 type_flag(u32 type)
/* only use after check_attach_btf_id() */
static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog)
{
- return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->dst_prog) ?
- prog->aux->dst_prog->type : prog->type;
+ return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->saved_dst_prog_type) ?
+ prog->aux->saved_dst_prog_type : prog->type;
}
static inline bool bpf_prog_check_recur(const struct bpf_prog *prog)
diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h
index dca2969..6fbfbde 100644
--- a/include/linux/dsa/ocelot.h
+++ b/include/linux/dsa/ocelot.h
@@ -5,6 +5,8 @@
#ifndef _NET_DSA_TAG_OCELOT_H
#define _NET_DSA_TAG_OCELOT_H
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
#include <linux/kthread.h>
#include <linux/packing.h>
#include <linux/skbuff.h>
@@ -273,4 +275,49 @@ static inline u32 ocelot_ptp_rew_op(struct sk_buff *skb)
return rew_op;
}
+/**
+ * ocelot_xmit_get_vlan_info: Determine VLAN_TCI and TAG_TYPE for injected frame
+ * @skb: Pointer to socket buffer
+ * @br: Pointer to bridge device that the port is under, if any
+ * @vlan_tci:
+ * @tag_type:
+ *
+ * If the port is under a VLAN-aware bridge, remove the VLAN header from the
+ * payload and move it into the DSA tag, which will make the switch classify
+ * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero,
+ * which is the pvid of standalone ports (OCELOT_STANDALONE_PVID), although not
+ * of VLAN-unaware bridge ports (that would be ocelot_vlan_unaware_pvid()).
+ * Anyway, VID 0 is fine because it is stripped on egress for these port modes,
+ * and source address learning is not performed for packets injected from the
+ * CPU anyway, so it doesn't matter that the VID is "wrong".
+ */
+static inline void ocelot_xmit_get_vlan_info(struct sk_buff *skb,
+ struct net_device *br,
+ u64 *vlan_tci, u64 *tag_type)
+{
+ struct vlan_ethhdr *hdr;
+ u16 proto, tci;
+
+ if (!br || !br_vlan_enabled(br)) {
+ *vlan_tci = 0;
+ *tag_type = IFH_TAG_TYPE_C;
+ return;
+ }
+
+ hdr = (struct vlan_ethhdr *)skb_mac_header(skb);
+ br_vlan_get_proto(br, &proto);
+
+ if (ntohs(hdr->h_vlan_proto) == proto) {
+ vlan_remove_tag(skb, &tci);
+ *vlan_tci = tci;
+ } else {
+ rcu_read_lock();
+ br_vlan_get_pvid_rcu(br, &tci);
+ rcu_read_unlock();
+ *vlan_tci = tci;
+ }
+
+ *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C;
+}
+
#endif
diff --git a/include/linux/file.h b/include/linux/file.h
index 237931f..59b146a 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -110,7 +110,7 @@ DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T),
*
* f = dentry_open(&path, O_RDONLY, current_cred());
* if (IS_ERR(f))
- * return PTR_ERR(fd);
+ * return PTR_ERR(f);
*
* fd_install(fd, f);
* return take_fd(fd);
diff --git a/include/linux/firmware/qcom/qcom_qseecom.h b/include/linux/firmware/qcom/qcom_qseecom.h
index 1dc5b3b..3387897b 100644
--- a/include/linux/firmware/qcom/qcom_qseecom.h
+++ b/include/linux/firmware/qcom/qcom_qseecom.h
@@ -26,51 +26,6 @@ struct qseecom_client {
};
/**
- * qseecom_scm_dev() - Get the SCM device associated with the QSEECOM client.
- * @client: The QSEECOM client device.
- *
- * Returns the SCM device under which the provided QSEECOM client device
- * operates. This function is intended to be used for DMA allocations.
- */
-static inline struct device *qseecom_scm_dev(struct qseecom_client *client)
-{
- return client->aux_dev.dev.parent->parent;
-}
-
-/**
- * qseecom_dma_alloc() - Allocate DMA memory for a QSEECOM client.
- * @client: The QSEECOM client to allocate the memory for.
- * @size: The number of bytes to allocate.
- * @dma_handle: Pointer to where the DMA address should be stored.
- * @gfp: Allocation flags.
- *
- * Wrapper function for dma_alloc_coherent(), allocating DMA memory usable for
- * TZ/QSEECOM communication. Refer to dma_alloc_coherent() for details.
- */
-static inline void *qseecom_dma_alloc(struct qseecom_client *client, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp)
-{
- return dma_alloc_coherent(qseecom_scm_dev(client), size, dma_handle, gfp);
-}
-
-/**
- * dma_free_coherent() - Free QSEECOM DMA memory.
- * @client: The QSEECOM client for which the memory has been allocated.
- * @size: The number of bytes allocated.
- * @cpu_addr: Virtual memory address to free.
- * @dma_handle: DMA memory address to free.
- *
- * Wrapper function for dma_free_coherent(), freeing memory previously
- * allocated with qseecom_dma_alloc(). Refer to dma_free_coherent() for
- * details.
- */
-static inline void qseecom_dma_free(struct qseecom_client *client, size_t size,
- void *cpu_addr, dma_addr_t dma_handle)
-{
- return dma_free_coherent(qseecom_scm_dev(client), size, cpu_addr, dma_handle);
-}
-
-/**
* qcom_qseecom_app_send() - Send to and receive data from a given QSEE app.
* @client: The QSEECOM client associated with the target app.
* @req: Request buffer sent to the app (must be TZ memory).
diff --git a/include/linux/fs.h b/include/linux/fs.h
index fd34b57..6ca11e2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -210,6 +210,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
#define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */
#define ATTR_TIMES_SET (1 << 16)
#define ATTR_TOUCH (1 << 17)
+#define ATTR_DELEG (1 << 18) /* Delegated attrs. Don't break write delegations */
/*
* Whiteout is represented by a char device. The following constants define the
@@ -2392,6 +2393,9 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
*
* I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback.
*
+ * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding
+ * i_count.
+ *
* Q: What is the difference between I_WILL_FREE and I_FREEING?
*/
#define I_DIRTY_SYNC (1 << 0)
@@ -2415,6 +2419,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
#define I_DONTCACHE (1 << 16)
#define I_SYNC_QUEUED (1 << 17)
#define I_PINNING_NETFS_WB (1 << 18)
+#define __I_LRU_ISOLATING 19
+#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING)
#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index c9bf68c..45bf05a 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -944,10 +944,37 @@ static inline bool htlb_allow_alloc_fallback(int reason)
static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
struct mm_struct *mm, pte_t *pte)
{
- if (huge_page_size(h) == PMD_SIZE)
+ const unsigned long size = huge_page_size(h);
+
+ VM_WARN_ON(size == PAGE_SIZE);
+
+ /*
+ * hugetlb must use the exact same PT locks as core-mm page table
+ * walkers would. When modifying a PTE table, hugetlb must take the
+ * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD
+ * PT lock etc.
+ *
+ * The expectation is that any hugetlb folio smaller than a PMD is
+ * always mapped into a single PTE table and that any hugetlb folio
+ * smaller than a PUD (but at least as big as a PMD) is always mapped
+ * into a single PMD table.
+ *
+ * If that does not hold for an architecture, then that architecture
+ * must disable split PT locks such that all *_lockptr() functions
+ * will give us the same result: the per-MM PT lock.
+ *
+ * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where
+ * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr()
+ * and core-mm would use pmd_lockptr(). However, in such configurations
+ * split PMD locks are disabled -- they don't make sense on a single
+ * PGDIR page table -- and the end result is the same.
+ */
+ if (size >= PUD_SIZE)
+ return pud_lockptr(mm, (pud_t *) pte);
+ else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE))
return pmd_lockptr(mm, (pmd_t *) pte);
- VM_BUG_ON(huge_page_size(h) == PAGE_SIZE);
- return &mm->page_table_lock;
+ /* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */
+ return ptep_lockptr(mm, pte);
}
#ifndef hugepages_supported
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 7eedd0c..377def4 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -1066,7 +1066,7 @@ static inline int of_i2c_get_board_info(struct device *dev,
struct acpi_resource;
struct acpi_resource_i2c_serialbus;
-#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_I2C)
+#if IS_REACHABLE(CONFIG_ACPI) && IS_REACHABLE(CONFIG_I2C)
bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares,
struct acpi_resource_i2c_serialbus **i2c);
int i2c_acpi_client_count(struct acpi_device *adev);
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 4d47f2c..bd722f4 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -795,8 +795,6 @@ extern int iommu_attach_device(struct iommu_domain *domain,
struct device *dev);
extern void iommu_detach_device(struct iommu_domain *domain,
struct device *dev);
-extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
- struct device *dev, ioasid_t pasid);
extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
@@ -1565,7 +1563,7 @@ struct iopf_queue *iopf_queue_alloc(const char *name);
void iopf_queue_free(struct iopf_queue *queue);
int iopf_queue_discard_partial(struct iopf_queue *queue);
void iopf_free_group(struct iopf_group *group);
-void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt);
+int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt);
void iopf_group_response(struct iopf_group *group,
enum iommu_page_response_code status);
#else
@@ -1603,9 +1601,10 @@ static inline void iopf_free_group(struct iopf_group *group)
{
}
-static inline void
+static inline int
iommu_report_device_fault(struct device *dev, struct iopf_fault *evt)
{
+ return -ENODEV;
}
static inline void iopf_group_response(struct iopf_group *group,
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 79a6b1a..b23c6d4 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -715,6 +715,13 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
}
#endif
+#ifndef kvm_arch_has_readonly_mem
+static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm)
+{
+ return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM);
+}
+#endif
+
struct kvm_memslots {
u64 generation;
atomic_long_t last_used_slot;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c4b238a..6549d09 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2920,6 +2920,13 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
return ptlock_ptr(page_ptdesc(pmd_page(*pmd)));
}
+static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte)
+{
+ BUILD_BUG_ON(IS_ENABLED(CONFIG_HIGHPTE));
+ BUILD_BUG_ON(MAX_PTRS_PER_PTE * sizeof(pte_t) > PAGE_SIZE);
+ return ptlock_ptr(virt_to_ptdesc(pte));
+}
+
static inline bool ptlock_init(struct ptdesc *ptdesc)
{
/*
@@ -2944,6 +2951,10 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
{
return &mm->page_table_lock;
}
+static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte)
+{
+ return &mm->page_table_lock;
+}
static inline void ptlock_cache_init(void) {}
static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; }
static inline void ptlock_free(struct ptdesc *ptdesc) {}
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 4145889..1dc6248f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -220,8 +220,6 @@ enum node_stat_item {
PGDEMOTE_KSWAPD,
PGDEMOTE_DIRECT,
PGDEMOTE_KHUGEPAGED,
- NR_MEMMAP, /* page metadata allocated through buddy allocator */
- NR_MEMMAP_BOOT, /* page metadata allocated through boot allocator */
NR_VM_NODE_STAT_ITEMS
};
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 5d02889..c47443e 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -73,8 +73,6 @@ struct netfs_inode {
#define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */
#define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */
#define NETFS_ICTX_WRITETHROUGH 2 /* Write-through caching */
-#define NETFS_ICTX_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark
- * write to cache on read */
};
/*
@@ -200,6 +198,7 @@ struct netfs_io_subrequest {
#define NETFS_SREQ_NEED_RETRY 9 /* Set if the filesystem requests a retry */
#define NETFS_SREQ_RETRYING 10 /* Set if we're retrying */
#define NETFS_SREQ_FAILED 11 /* Set if the subreq failed unretryably */
+#define NETFS_SREQ_HIT_EOF 12 /* Set if we hit the EOF */
};
enum netfs_io_origin {
@@ -269,7 +268,6 @@ struct netfs_io_request {
#define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */
#define NETFS_RREQ_FAILED 4 /* The request failed */
#define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */
-#define NETFS_RREQ_WRITE_TO_CACHE 7 /* Need to write to the cache */
#define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */
#define NETFS_RREQ_NONBLOCK 9 /* Don't block if possible (O_NONBLOCK) */
#define NETFS_RREQ_BLOCKED 10 /* We blocked */
diff --git a/include/linux/panic.h b/include/linux/panic.h
index 3130e0b..54d90b6 100644
--- a/include/linux/panic.h
+++ b/include/linux/panic.h
@@ -16,6 +16,7 @@ extern void oops_enter(void);
extern void oops_exit(void);
extern bool oops_may_print(void);
+extern bool panic_triggering_all_cpu_backtrace;
extern int panic_timeout;
extern unsigned long panic_print;
extern int panic_on_oops;
diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h
index 18cd0c0..207f0c8 100644
--- a/include/linux/pgalloc_tag.h
+++ b/include/linux/pgalloc_tag.h
@@ -43,6 +43,18 @@ static inline void put_page_tag_ref(union codetag_ref *ref)
page_ext_put(page_ext_from_codetag_ref(ref));
}
+static inline void clear_page_tag_ref(struct page *page)
+{
+ if (mem_alloc_profiling_enabled()) {
+ union codetag_ref *ref = get_page_tag_ref(page);
+
+ if (ref) {
+ set_codetag_empty(ref);
+ put_page_tag_ref(ref);
+ }
+ }
+}
+
static inline void pgalloc_tag_add(struct page *page, struct task_struct *task,
unsigned int nr)
{
@@ -126,6 +138,7 @@ static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr)
static inline union codetag_ref *get_page_tag_ref(struct page *page) { return NULL; }
static inline void put_page_tag_ref(union codetag_ref *ref) {}
+static inline void clear_page_tag_ref(struct page *page) {}
static inline void pgalloc_tag_add(struct page *page, struct task_struct *task,
unsigned int nr) {}
static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {}
diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index 59b3b75..35f039e 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -266,12 +266,12 @@ bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp)
if (oldp)
*oldp = old;
- if (old == i) {
+ if (old > 0 && old == i) {
smp_acquire__after_ctrl_dep();
return true;
}
- if (unlikely(old < 0 || old - i < 0))
+ if (unlikely(old <= 0 || old - i < 0))
refcount_warn_saturate(r, REFCOUNT_SUB_UAF);
return false;
diff --git a/include/linux/soc/qcom/pmic_glink.h b/include/linux/soc/qcom/pmic_glink.h
index fd124aa..7cddf10 100644
--- a/include/linux/soc/qcom/pmic_glink.h
+++ b/include/linux/soc/qcom/pmic_glink.h
@@ -23,10 +23,11 @@ struct pmic_glink_hdr {
int pmic_glink_send(struct pmic_glink_client *client, void *data, size_t len);
-struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev,
- unsigned int id,
- void (*cb)(const void *, size_t, void *),
- void (*pdr)(void *, int),
- void *priv);
+struct pmic_glink_client *devm_pmic_glink_client_alloc(struct device *dev,
+ unsigned int id,
+ void (*cb)(const void *, size_t, void *),
+ void (*pdr)(void *, int),
+ void *priv);
+void pmic_glink_client_register(struct pmic_glink_client *client);
#endif
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index e4f3f3d..d47d5f1 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -902,12 +902,29 @@ extern int devm_spi_register_controller(struct device *dev,
struct spi_controller *ctlr);
extern void spi_unregister_controller(struct spi_controller *ctlr);
-#if IS_ENABLED(CONFIG_ACPI)
+#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_SPI_MASTER)
extern struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev);
extern struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr,
struct acpi_device *adev,
int index);
int acpi_spi_count_resources(struct acpi_device *adev);
+#else
+static inline struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev)
+{
+ return NULL;
+}
+
+static inline struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr,
+ struct acpi_device *adev,
+ int index)
+{
+ return ERR_PTR(-ENODEV);
+}
+
+static inline int acpi_spi_count_resources(struct acpi_device *adev)
+{
+ return 0;
+}
#endif
/*
diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h
index c9cb657..bef5f06 100644
--- a/include/linux/sysfb.h
+++ b/include/linux/sysfb.h
@@ -58,11 +58,11 @@ struct efifb_dmi_info {
#ifdef CONFIG_SYSFB
-void sysfb_disable(void);
+void sysfb_disable(struct device *dev);
#else /* CONFIG_SYSFB */
-static inline void sysfb_disable(void)
+static inline void sysfb_disable(struct device *dev)
{
}
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 25fbf96..b86ddca 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -55,6 +55,7 @@ enum thermal_notify_event {
THERMAL_TZ_BIND_CDEV, /* Cooling dev is bind to the thermal zone */
THERMAL_TZ_UNBIND_CDEV, /* Cooling dev is unbind from the thermal zone */
THERMAL_INSTANCE_WEIGHT_CHANGED, /* Thermal instance weight changed */
+ THERMAL_TZ_RESUME, /* Thermal zone is resuming after system sleep */
};
/**
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 23cd179..9eb77c9 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -34,10 +34,13 @@ struct reclaim_stat {
unsigned nr_lazyfree_fail;
};
-enum writeback_stat_item {
+/* Stat data for system wide items */
+enum vm_stat_item {
NR_DIRTY_THRESHOLD,
NR_DIRTY_BG_THRESHOLD,
- NR_VM_WRITEBACK_STAT_ITEMS,
+ NR_MEMMAP_PAGES, /* page metadata allocated through buddy allocator */
+ NR_MEMMAP_BOOT_PAGES, /* page metadata allocated through boot allocator */
+ NR_VM_STAT_ITEMS,
};
#ifdef CONFIG_VM_EVENT_COUNTERS
@@ -514,21 +517,13 @@ static inline const char *lru_list_name(enum lru_list lru)
return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_"
}
-static inline const char *writeback_stat_name(enum writeback_stat_item item)
-{
- return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
- NR_VM_NUMA_EVENT_ITEMS +
- NR_VM_NODE_STAT_ITEMS +
- item];
-}
-
#if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG)
static inline const char *vm_event_name(enum vm_event_item item)
{
return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
NR_VM_NUMA_EVENT_ITEMS +
NR_VM_NODE_STAT_ITEMS +
- NR_VM_WRITEBACK_STAT_ITEMS +
+ NR_VM_STAT_ITEMS +
item];
}
#endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */
@@ -625,7 +620,6 @@ static inline void lruvec_stat_sub_folio(struct folio *folio,
lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio));
}
-void __meminit mod_node_early_perpage_metadata(int nid, long delta);
-void __meminit store_early_perpage_metadata(void);
-
+void memmap_boot_pages_add(long delta);
+void memmap_pages_add(long delta);
#endif /* _LINUX_VMSTAT_H */
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 535701e..24d970f 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -230,8 +230,12 @@ struct vsock_tap {
int vsock_add_tap(struct vsock_tap *vt);
int vsock_remove_tap(struct vsock_tap *vt);
void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque);
+int __vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+ int flags);
int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
int flags);
+int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
+ size_t len, int flags);
int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
size_t len, int flags);
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index e372a88..d1d0730 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -206,14 +206,17 @@ enum {
*/
HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED,
- /* When this quirk is set, the controller has validated that
- * LE states reported through the HCI_LE_READ_SUPPORTED_STATES are
- * valid. This mechanism is necessary as many controllers have
- * been seen has having trouble initiating a connectable
- * advertisement despite the state combination being reported as
- * supported.
+ /* When this quirk is set, the LE states reported through the
+ * HCI_LE_READ_SUPPORTED_STATES are invalid/broken.
+ *
+ * This mechanism is necessary as many controllers have been seen has
+ * having trouble initiating a connectable advertisement despite the
+ * state combination being reported as supported.
+ *
+ * This quirk can be set before hci_register_dev is called or
+ * during the hdev->setup vendor callback.
*/
- HCI_QUIRK_VALID_LE_STATES,
+ HCI_QUIRK_BROKEN_LE_STATES,
/* When this quirk is set, then erroneous data reporting
* is ignored. This is mainly due to the fact that the HCI
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 3102089..e449dba 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -825,7 +825,7 @@ extern struct mutex hci_cb_list_lock;
} while (0)
#define hci_dev_le_state_simultaneous(hdev) \
- (test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) && \
+ (!test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) && \
(hdev->le_states[4] & 0x08) && /* Central */ \
(hdev->le_states[4] & 0x40) && /* Peripheral */ \
(hdev->le_states[3] & 0x10)) /* Simultaneous */
diff --git a/include/net/bonding.h b/include/net/bonding.h
index b61fb1a..8bb5f01 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -260,7 +260,7 @@ struct bonding {
#ifdef CONFIG_XFRM_OFFLOAD
struct list_head ipsec_list;
/* protecting ipsec_list */
- spinlock_t ipsec_lock;
+ struct mutex ipsec_lock;
#endif /* CONFIG_XFRM_OFFLOAD */
struct bpf_prog *xdp_prog;
};
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 9b09aca..522f1da 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -68,7 +68,7 @@ static inline bool sk_can_busy_loop(struct sock *sk)
static inline unsigned long busy_loop_current_time(void)
{
#ifdef CONFIG_NET_RX_BUSY_POLL
- return (unsigned long)(local_clock() >> 10);
+ return (unsigned long)(ktime_get_ns() >> 10);
#else
return 0;
#endif
diff --git a/include/net/dsa.h b/include/net/dsa.h
index b06f97a..d7a6c29 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -403,14 +403,18 @@ struct dsa_switch {
*/
u32 configure_vlan_while_not_filtering:1;
- /* If the switch driver always programs the CPU port as egress tagged
- * despite the VLAN configuration indicating otherwise, then setting
- * @untag_bridge_pvid will force the DSA receive path to pop the
- * bridge's default_pvid VLAN tagged frames to offer a consistent
- * behavior between a vlan_filtering=0 and vlan_filtering=1 bridge
- * device.
+ /* Pop the default_pvid of VLAN-unaware bridge ports from tagged frames.
+ * DEPRECATED: Do NOT set this field in new drivers. Instead look at
+ * the dsa_software_vlan_untag() comments.
*/
u32 untag_bridge_pvid:1;
+ /* Pop the default_pvid of VLAN-aware bridge ports from tagged frames.
+ * Useful if the switch cannot preserve the VLAN tag as seen on the
+ * wire for user port ingress, and chooses to send all frames as
+ * VLAN-tagged to the CPU, including those which were originally
+ * untagged.
+ */
+ u32 untag_vlan_aware_bridge_pvid:1;
/* Let DSA manage the FDB entries towards the
* CPU, based on the software bridge database.
diff --git a/include/net/kcm.h b/include/net/kcm.h
index 90279e5..441e993 100644
--- a/include/net/kcm.h
+++ b/include/net/kcm.h
@@ -70,6 +70,7 @@ struct kcm_sock {
struct work_struct tx_work;
struct list_head wait_psock_list;
struct sk_buff *seq_skb;
+ struct mutex tx_mutex;
u32 tx_stopped : 1;
/* Don't use bit fields here, these are set under different locks */
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 6439fd8..7caa334 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -275,6 +275,7 @@ struct mana_cq {
/* NAPI data */
struct napi_struct napi;
int work_done;
+ int work_done_since_doorbell;
int budget;
};
diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h
index 60a7d0c..fcf9672 100644
--- a/include/net/netfilter/nf_tables_ipv4.h
+++ b/include/net/netfilter/nf_tables_ipv4.h
@@ -19,7 +19,7 @@ static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt)
static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt)
{
struct iphdr *iph, _iph;
- u32 len, thoff;
+ u32 len, thoff, skb_len;
iph = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb),
sizeof(*iph), &_iph);
@@ -30,8 +30,10 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt)
return -1;
len = iph_totlen(pkt->skb, iph);
- thoff = skb_network_offset(pkt->skb) + (iph->ihl * 4);
- if (pkt->skb->len < len)
+ thoff = iph->ihl * 4;
+ skb_len = pkt->skb->len - skb_network_offset(pkt->skb);
+
+ if (skb_len < len)
return -1;
else if (len < thoff)
return -1;
@@ -40,7 +42,7 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt)
pkt->flags = NFT_PKTINFO_L4PROTO;
pkt->tprot = iph->protocol;
- pkt->thoff = thoff;
+ pkt->thoff = skb_network_offset(pkt->skb) + thoff;
pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET;
return 0;
diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h
index 467d59b..a0633ee 100644
--- a/include/net/netfilter/nf_tables_ipv6.h
+++ b/include/net/netfilter/nf_tables_ipv6.h
@@ -31,8 +31,8 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt)
struct ipv6hdr *ip6h, _ip6h;
unsigned int thoff = 0;
unsigned short frag_off;
+ u32 pkt_len, skb_len;
int protohdr;
- u32 pkt_len;
ip6h = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb),
sizeof(*ip6h), &_ip6h);
@@ -43,7 +43,8 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt)
return -1;
pkt_len = ntohs(ip6h->payload_len);
- if (pkt_len + sizeof(*ip6h) > pkt->skb->len)
+ skb_len = pkt->skb->len - skb_network_offset(pkt->skb);
+ if (pkt_len + sizeof(*ip6h) > skb_len)
return -1;
protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags);
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index 45c40d2..8ecfb94 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -234,7 +234,7 @@ static inline sector_t scsi_get_lba(struct scsi_cmnd *scmd)
static inline unsigned int scsi_logical_block_count(struct scsi_cmnd *scmd)
{
- unsigned int shift = ilog2(scmd->device->sector_size) - SECTOR_SHIFT;
+ unsigned int shift = ilog2(scmd->device->sector_size);
return blk_rq_bytes(scsi_cmd_to_rq(scmd)) >> shift;
}
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 6a37b29..462c653 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -813,6 +813,9 @@ struct ocelot {
const u32 *const *map;
struct list_head stats_regions;
+ spinlock_t inj_lock;
+ spinlock_t xtr_lock;
+
u32 pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM];
int packet_buffer_size;
int num_frame_refs;
@@ -966,10 +969,17 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target,
u32 val, u32 reg, u32 offset);
/* Packet I/O */
+void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp);
+void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp);
+void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp);
+void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp);
+void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp);
+void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp);
bool ocelot_can_inject(struct ocelot *ocelot, int grp);
void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp,
u32 rew_op, struct sk_buff *skb);
-void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag);
+void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port,
+ u32 rew_op, struct sk_buff *skb);
int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **skb);
void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp);
void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb,
diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h
index c601a45..eb19668 100644
--- a/include/soc/mscc/ocelot_vcap.h
+++ b/include/soc/mscc/ocelot_vcap.h
@@ -13,6 +13,7 @@
*/
#define OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port, upstream) ((upstream) << 16 | (port))
#define OCELOT_VCAP_IS1_TAG_8021Q_TXVLAN(ocelot, port) (port)
+#define OCELOT_VCAP_IS1_VLAN_RECLASSIFY(ocelot, port) ((ocelot)->num_phys_ports + (port))
#define OCELOT_VCAP_IS2_TAG_8021Q_TXVLAN(ocelot, port) (port)
#define OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port) ((ocelot)->num_phys_ports + (port))
#define OCELOT_VCAP_IS2_MRP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2)
@@ -499,6 +500,7 @@ struct ocelot_vcap_key_vlan {
struct ocelot_vcap_u8 pcp; /* PCP (3 bit) */
enum ocelot_vcap_bit dei; /* DEI */
enum ocelot_vcap_bit tagged; /* Tagged/untagged frame */
+ enum ocelot_vcap_bit tpid;
};
struct ocelot_vcap_key_etype {
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index da23484..606b4a0 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -51,6 +51,7 @@
EM(netfs_rreq_trace_resubmit, "RESUBMT") \
EM(netfs_rreq_trace_set_pause, "PAUSE ") \
EM(netfs_rreq_trace_unlock, "UNLOCK ") \
+ EM(netfs_rreq_trace_unlock_pgpriv2, "UNLCK-2") \
EM(netfs_rreq_trace_unmark, "UNMARK ") \
EM(netfs_rreq_trace_wait_ip, "WAIT-IP") \
EM(netfs_rreq_trace_wait_pause, "WT-PAUS") \
@@ -145,6 +146,7 @@
EM(netfs_folio_trace_clear_g, "clear-g") \
EM(netfs_folio_trace_clear_s, "clear-s") \
EM(netfs_folio_trace_copy_to_cache, "mark-copy") \
+ EM(netfs_folio_trace_end_copy, "end-copy") \
EM(netfs_folio_trace_filled_gaps, "filled-gaps") \
EM(netfs_folio_trace_kill, "kill") \
EM(netfs_folio_trace_kill_cc, "kill-cc") \
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index ba2d6a0..a96a985 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -2277,6 +2277,42 @@ DEFINE_CLIENT_DEVICE_EVENT(rpcrdma_client_remove_one);
DEFINE_CLIENT_DEVICE_EVENT(rpcrdma_client_wait_on);
DEFINE_CLIENT_DEVICE_EVENT(rpcrdma_client_remove_one_done);
+DECLARE_EVENT_CLASS(rpcrdma_client_register_class,
+ TP_PROTO(
+ const struct ib_device *device,
+ const struct rpcrdma_notification *rn
+ ),
+
+ TP_ARGS(device, rn),
+
+ TP_STRUCT__entry(
+ __string(name, device->name)
+ __field(void *, callback)
+ __field(u32, index)
+ ),
+
+ TP_fast_assign(
+ __assign_str(name);
+ __entry->callback = rn->rn_done;
+ __entry->index = rn->rn_index;
+ ),
+
+ TP_printk("device=%s index=%u done callback=%pS\n",
+ __get_str(name), __entry->index, __entry->callback
+ )
+);
+
+#define DEFINE_CLIENT_REGISTER_EVENT(name) \
+ DEFINE_EVENT(rpcrdma_client_register_class, name, \
+ TP_PROTO( \
+ const struct ib_device *device, \
+ const struct rpcrdma_notification *rn \
+ ), \
+ TP_ARGS(device, rn))
+
+DEFINE_CLIENT_REGISTER_EVENT(rpcrdma_client_register);
+DEFINE_CLIENT_REGISTER_EVENT(rpcrdma_client_unregister);
+
#endif /* _TRACE_RPCRDMA_H */
#include <trace/define_trace.h>
diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index 19619d4..db232a2 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -1590,10 +1590,10 @@ enum drm_xe_oa_property_id {
* b. Counter select c. Counter size and d. BC report. Also refer to the
* oa_formats array in drivers/gpu/drm/xe/xe_oa.c.
*/
-#define DRM_XE_OA_FORMAT_MASK_FMT_TYPE (0xff << 0)
-#define DRM_XE_OA_FORMAT_MASK_COUNTER_SEL (0xff << 8)
-#define DRM_XE_OA_FORMAT_MASK_COUNTER_SIZE (0xff << 16)
-#define DRM_XE_OA_FORMAT_MASK_BC_REPORT (0xff << 24)
+#define DRM_XE_OA_FORMAT_MASK_FMT_TYPE (0xffu << 0)
+#define DRM_XE_OA_FORMAT_MASK_COUNTER_SEL (0xffu << 8)
+#define DRM_XE_OA_FORMAT_MASK_COUNTER_SIZE (0xffu << 16)
+#define DRM_XE_OA_FORMAT_MASK_BC_REPORT (0xffu << 24)
/**
* @DRM_XE_OA_PROPERTY_OA_PERIOD_EXPONENT: Requests periodic OA unit
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 2aaf7ee..adc2524 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -421,7 +421,7 @@ enum io_uring_msg_ring_flags {
* IO completion data structure (Completion Queue Entry)
*/
struct io_uring_cqe {
- __u64 user_data; /* sqe->data submission passed back */
+ __u64 user_data; /* sqe->user_data value passed back */
__s32 res; /* result code for this event */
__u32 flags;
diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h
index b133211..5fad3d0 100644
--- a/include/uapi/linux/nsfs.h
+++ b/include/uapi/linux/nsfs.h
@@ -3,6 +3,7 @@
#define __LINUX_NSFS_H
#include <linux/ioctl.h>
+#include <linux/types.h>
#define NSIO 0xb7
@@ -16,7 +17,7 @@
/* Get owner UID (in the caller's user namespace) for a user namespace */
#define NS_GET_OWNER_UID _IO(NSIO, 0x4)
/* Get the id for a mount namespace */
-#define NS_GET_MNTNS_ID _IO(NSIO, 0x5)
+#define NS_GET_MNTNS_ID _IOR(NSIO, 0x5, __u64)
/* Translate pid from target pid namespace into the caller's pid namespace. */
#define NS_GET_PID_FROM_PIDNS _IOR(NSIO, 0x6, int)
/* Return thread-group leader id of pid in the callers pid namespace. */
diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h
index 2289b7c..832c15d 100644
--- a/include/uapi/linux/psp-sev.h
+++ b/include/uapi/linux/psp-sev.h
@@ -51,6 +51,7 @@ typedef enum {
SEV_RET_INVALID_PLATFORM_STATE,
SEV_RET_INVALID_GUEST_STATE,
SEV_RET_INAVLID_CONFIG,
+ SEV_RET_INVALID_CONFIG = SEV_RET_INAVLID_CONFIG,
SEV_RET_INVALID_LEN,
SEV_RET_ALREADY_OWNED,
SEV_RET_INVALID_CERTIFICATE,
diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h
index 9158369..f33d914 100644
--- a/include/uapi/misc/fastrpc.h
+++ b/include/uapi/misc/fastrpc.h
@@ -8,14 +8,11 @@
#define FASTRPC_IOCTL_ALLOC_DMA_BUFF _IOWR('R', 1, struct fastrpc_alloc_dma_buf)
#define FASTRPC_IOCTL_FREE_DMA_BUFF _IOWR('R', 2, __u32)
#define FASTRPC_IOCTL_INVOKE _IOWR('R', 3, struct fastrpc_invoke)
-/* This ioctl is only supported with secure device nodes */
#define FASTRPC_IOCTL_INIT_ATTACH _IO('R', 4)
#define FASTRPC_IOCTL_INIT_CREATE _IOWR('R', 5, struct fastrpc_init_create)
#define FASTRPC_IOCTL_MMAP _IOWR('R', 6, struct fastrpc_req_mmap)
#define FASTRPC_IOCTL_MUNMAP _IOWR('R', 7, struct fastrpc_req_munmap)
-/* This ioctl is only supported with secure device nodes */
#define FASTRPC_IOCTL_INIT_ATTACH_SNS _IO('R', 8)
-/* This ioctl is only supported with secure device nodes */
#define FASTRPC_IOCTL_INIT_CREATE_STATIC _IOWR('R', 9, struct fastrpc_init_create_static)
#define FASTRPC_IOCTL_MEM_MAP _IOWR('R', 10, struct fastrpc_mem_map)
#define FASTRPC_IOCTL_MEM_UNMAP _IOWR('R', 11, struct fastrpc_mem_unmap)
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index cac0cdb..0fd2aeb 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -676,6 +676,14 @@ enum ufshcd_quirks {
* the standard best practice for managing keys).
*/
UFSHCD_QUIRK_KEYS_IN_PRDT = 1 << 24,
+
+ /*
+ * This quirk indicates that the controller reports the value 1 (not
+ * supported) in the Legacy Single DoorBell Support (LSDBS) bit of the
+ * Controller Capabilities register although it supports the legacy
+ * single doorbell mode.
+ */
+ UFSHCD_QUIRK_BROKEN_LSDBS_CAP = 1 << 25,
};
enum ufshcd_caps {
diff --git a/init/Kconfig b/init/Kconfig
index 37260d1..5783a0b 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1920,7 +1920,7 @@
config RUSTC_VERSION_TEXT
string
depends on RUST
- default $(shell,command -v $(RUSTC) >/dev/null 2>&1 && $(RUSTC) --version || echo n)
+ default "$(shell,$(RUSTC) --version 2>/dev/null)"
config BINDGEN_VERSION_TEXT
string
@@ -1928,7 +1928,7 @@
# The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0
# (https://github.com/rust-lang/rust-bindgen/pull/2678). It can be removed when
# the minimum version is upgraded past that (0.69.1 already fixed the issue).
- default $(shell,command -v $(BINDGEN) >/dev/null 2>&1 && $(BINDGEN) --version workaround-for-0.69.0 || echo n)
+ default "$(shell,$(BINDGEN) --version workaround-for-0.69.0 2>/dev/null)"
#
# Place an empty function call at each tracepoint site. Can be
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index c95dc17..bdfa30b 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -129,7 +129,7 @@ static int io_provided_buffers_select(struct io_kiocb *req, size_t *len,
iov[0].iov_base = buf;
iov[0].iov_len = *len;
- return 0;
+ return 1;
}
static struct io_uring_buf *io_ring_head_to_buf(struct io_uring_buf_ring *br,
@@ -218,10 +218,13 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg,
buf = io_ring_head_to_buf(br, head, bl->mask);
if (arg->max_len) {
- int needed;
+ u32 len = READ_ONCE(buf->len);
+ size_t needed;
- needed = (arg->max_len + buf->len - 1) / buf->len;
- needed = min(needed, PEEK_MAX_IMPORT);
+ if (unlikely(!len))
+ return -ENOBUFS;
+ needed = (arg->max_len + len - 1) / len;
+ needed = min_not_zero(needed, (size_t) PEEK_MAX_IMPORT);
if (nr_avail > needed)
nr_avail = needed;
}
diff --git a/io_uring/napi.c b/io_uring/napi.c
index a3dc376..1de1d4d 100644
--- a/io_uring/napi.c
+++ b/io_uring/napi.c
@@ -26,7 +26,6 @@ static struct io_napi_entry *io_napi_hash_find(struct hlist_head *hash_list,
hlist_for_each_entry_rcu(e, hash_list, node) {
if (e->napi_id != napi_id)
continue;
- e->timeout = jiffies + NAPI_TIMEOUT;
return e;
}
@@ -302,7 +301,7 @@ void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq)
{
iowq->napi_prefer_busy_poll = READ_ONCE(ctx->napi_prefer_busy_poll);
- if (!(ctx->flags & IORING_SETUP_SQPOLL) && ctx->napi_enabled)
+ if (!(ctx->flags & IORING_SETUP_SQPOLL))
io_napi_blocking_busy_loop(ctx, iowq);
}
diff --git a/io_uring/napi.h b/io_uring/napi.h
index 88f1c21..27b88c3 100644
--- a/io_uring/napi.h
+++ b/io_uring/napi.h
@@ -55,7 +55,7 @@ static inline void io_napi_add(struct io_kiocb *req)
struct io_ring_ctx *ctx = req->ctx;
struct socket *sock;
- if (!READ_ONCE(ctx->napi_busy_poll_dt))
+ if (!READ_ONCE(ctx->napi_enabled))
return;
sock = sock_from_file(req->file);
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index a860516..453867a 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -394,10 +394,11 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx,
struct io_uring_rsrc_update2 *up,
unsigned int nr_args)
{
- struct iovec __user *uvec = u64_to_user_ptr(up->data);
u64 __user *tags = u64_to_user_ptr(up->tags);
struct iovec fast_iov, *iov;
struct page *last_hpage = NULL;
+ struct iovec __user *uvec;
+ u64 user_data = up->data;
__u32 done;
int i, err;
@@ -410,7 +411,8 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx,
struct io_mapped_ubuf *imu;
u64 tag = 0;
- iov = iovec_from_user(&uvec[done], 1, 1, &fast_iov, ctx->compat);
+ uvec = u64_to_user_ptr(user_data);
+ iov = iovec_from_user(uvec, 1, 1, &fast_iov, ctx->compat);
if (IS_ERR(iov)) {
err = PTR_ERR(iov);
break;
@@ -443,6 +445,10 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx,
ctx->user_bufs[i] = imu;
*io_get_tag_slot(ctx->buf_data, i) = tag;
+ if (ctx->compat)
+ user_data += sizeof(struct compat_iovec);
+ else
+ user_data += sizeof(struct iovec);
}
return done ? done : err;
}
@@ -949,7 +955,7 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
struct page *last_hpage = NULL;
struct io_rsrc_data *data;
struct iovec fast_iov, *iov = &fast_iov;
- const struct iovec __user *uvec = (struct iovec * __user) arg;
+ const struct iovec __user *uvec;
int i, ret;
BUILD_BUG_ON(IORING_MAX_REG_BUFFERS >= (1u << 16));
@@ -972,7 +978,8 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) {
if (arg) {
- iov = iovec_from_user(&uvec[i], 1, 1, &fast_iov, ctx->compat);
+ uvec = (struct iovec __user *) arg;
+ iov = iovec_from_user(uvec, 1, 1, &fast_iov, ctx->compat);
if (IS_ERR(iov)) {
ret = PTR_ERR(iov);
break;
@@ -980,6 +987,10 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
ret = io_buffer_validate(iov);
if (ret)
break;
+ if (ctx->compat)
+ arg += sizeof(struct compat_iovec);
+ else
+ arg += sizeof(struct iovec);
}
if (!iov->iov_base && *io_get_tag_slot(data, i)) {
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index b3722e5..3b50dc9 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -44,7 +44,7 @@ void io_sq_thread_unpark(struct io_sq_data *sqd)
void io_sq_thread_park(struct io_sq_data *sqd)
__acquires(&sqd->lock)
{
- WARN_ON_ONCE(sqd->thread == current);
+ WARN_ON_ONCE(data_race(sqd->thread) == current);
atomic_inc(&sqd->park_pending);
set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 4cb5441..d852009 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -16884,8 +16884,9 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
spi = i / BPF_REG_SIZE;
if (exact != NOT_EXACT &&
- old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
- cur->stack[spi].slot_type[i % BPF_REG_SIZE])
+ (i >= cur->allocated_stack ||
+ old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
+ cur->stack[spi].slot_type[i % BPF_REG_SIZE]))
return false;
if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 40ec4ab..4bd9e50 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -233,6 +233,13 @@ static cpumask_var_t isolated_cpus;
static struct list_head remote_children;
/*
+ * A flag to force sched domain rebuild at the end of an operation while
+ * inhibiting it in the intermediate stages when set. Currently it is only
+ * set in hotplug code.
+ */
+static bool force_sd_rebuild;
+
+/*
* Partition root states:
*
* 0 - member (not a partition root)
@@ -1475,7 +1482,7 @@ static void update_partition_sd_lb(struct cpuset *cs, int old_prs)
clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
}
- if (rebuild_domains)
+ if (rebuild_domains && !force_sd_rebuild)
rebuild_sched_domains_locked();
}
@@ -1833,7 +1840,7 @@ static void remote_partition_check(struct cpuset *cs, struct cpumask *newmask,
remote_partition_disable(child, tmp);
disable_cnt++;
}
- if (disable_cnt)
+ if (disable_cnt && !force_sd_rebuild)
rebuild_sched_domains_locked();
}
@@ -1991,6 +1998,8 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
part_error = PERR_CPUSEMPTY;
goto write_error;
}
+ /* Check newmask again, whether cpus are available for parent/cs */
+ nocpu |= tasks_nocpu_error(parent, cs, newmask);
/*
* partcmd_update with newmask:
@@ -2440,7 +2449,8 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
}
rcu_read_unlock();
- if (need_rebuild_sched_domains && !(flags & HIER_NO_SD_REBUILD))
+ if (need_rebuild_sched_domains && !(flags & HIER_NO_SD_REBUILD) &&
+ !force_sd_rebuild)
rebuild_sched_domains_locked();
}
@@ -2523,7 +2533,8 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
*/
if (!*buf) {
cpumask_clear(trialcs->cpus_allowed);
- cpumask_clear(trialcs->effective_xcpus);
+ if (cpumask_empty(trialcs->exclusive_cpus))
+ cpumask_clear(trialcs->effective_xcpus);
} else {
retval = cpulist_parse(buf, trialcs->cpus_allowed);
if (retval < 0)
@@ -3101,7 +3112,8 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
cs->flags = trialcs->flags;
spin_unlock_irq(&callback_lock);
- if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed)
+ if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed &&
+ !force_sd_rebuild)
rebuild_sched_domains_locked();
if (spread_flag_changed)
@@ -4498,11 +4510,9 @@ hotplug_update_tasks(struct cpuset *cs,
update_tasks_nodemask(cs);
}
-static bool force_rebuild;
-
void cpuset_force_rebuild(void)
{
- force_rebuild = true;
+ force_sd_rebuild = true;
}
/**
@@ -4650,15 +4660,9 @@ static void cpuset_handle_hotplug(void)
!cpumask_empty(subpartitions_cpus);
mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems);
- /*
- * In the rare case that hotplug removes all the cpus in
- * subpartitions_cpus, we assumed that cpus are updated.
- */
- if (!cpus_updated && !cpumask_empty(subpartitions_cpus))
- cpus_updated = true;
-
/* For v1, synchronize cpus_allowed to cpu_active_mask */
if (cpus_updated) {
+ cpuset_force_rebuild();
spin_lock_irq(&callback_lock);
if (!on_dfl)
cpumask_copy(top_cpuset.cpus_allowed, &new_cpus);
@@ -4714,8 +4718,8 @@ static void cpuset_handle_hotplug(void)
}
/* rebuild sched domains if cpus_allowed has changed */
- if (cpus_updated || force_rebuild) {
- force_rebuild = false;
+ if (force_sd_rebuild) {
+ force_sd_rebuild = false;
rebuild_sched_domains_cpuslocked();
}
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 1209dda..b1fd2a3 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -2689,6 +2689,16 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
return ret;
}
+/**
+ * Check if the core a CPU belongs to is online
+ */
+#if !defined(topology_is_core_online)
+static inline bool topology_is_core_online(unsigned int cpu)
+{
+ return true;
+}
+#endif
+
int cpuhp_smt_enable(void)
{
int cpu, ret = 0;
@@ -2699,7 +2709,7 @@ int cpuhp_smt_enable(void)
/* Skip online CPUs and CPUs on offline nodes */
if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
continue;
- if (!cpu_smt_thread_allowed(cpu))
+ if (!cpu_smt_thread_allowed(cpu) || !topology_is_core_online(cpu))
continue;
ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
if (ret)
diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c
index d3b4cd1..64d44a5 100644
--- a/kernel/crash_reserve.c
+++ b/kernel/crash_reserve.c
@@ -423,7 +423,8 @@ void __init reserve_crashkernel_generic(char *cmdline,
if (high && search_end == CRASH_ADDR_HIGH_MAX) {
search_end = CRASH_ADDR_LOW_MAX;
search_base = 0;
- goto retry;
+ if (search_end != CRASH_ADDR_HIGH_MAX)
+ goto retry;
}
pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
crash_size);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index aa3450b..c973e3c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9706,7 +9706,8 @@ static int __perf_event_overflow(struct perf_event *event,
ret = __perf_event_account_interrupt(event, throttle);
- if (event->prog && !bpf_overflow_handler(event, data, regs))
+ if (event->prog && event->prog->type == BPF_PROG_TYPE_PERF_EVENT &&
+ !bpf_overflow_handler(event, data, regs))
return ret;
/*
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index fb2c773..a9a0ca6 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -160,38 +160,6 @@ unsigned long kallsyms_sym_address(int idx)
return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
}
-static void cleanup_symbol_name(char *s)
-{
- char *res;
-
- if (!IS_ENABLED(CONFIG_LTO_CLANG))
- return;
-
- /*
- * LLVM appends various suffixes for local functions and variables that
- * must be promoted to global scope as part of LTO. This can break
- * hooking of static functions with kprobes. '.' is not a valid
- * character in an identifier in C. Suffixes only in LLVM LTO observed:
- * - foo.llvm.[0-9a-f]+
- */
- res = strstr(s, ".llvm.");
- if (res)
- *res = '\0';
-
- return;
-}
-
-static int compare_symbol_name(const char *name, char *namebuf)
-{
- /* The kallsyms_seqs_of_names is sorted based on names after
- * cleanup_symbol_name() (see scripts/kallsyms.c) if clang lto is enabled.
- * To ensure correct bisection in kallsyms_lookup_names(), do
- * cleanup_symbol_name(namebuf) before comparing name and namebuf.
- */
- cleanup_symbol_name(namebuf);
- return strcmp(name, namebuf);
-}
-
static unsigned int get_symbol_seq(int index)
{
unsigned int i, seq = 0;
@@ -219,7 +187,7 @@ static int kallsyms_lookup_names(const char *name,
seq = get_symbol_seq(mid);
off = get_symbol_offset(seq);
kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
- ret = compare_symbol_name(name, namebuf);
+ ret = strcmp(name, namebuf);
if (ret > 0)
low = mid + 1;
else if (ret < 0)
@@ -236,7 +204,7 @@ static int kallsyms_lookup_names(const char *name,
seq = get_symbol_seq(low - 1);
off = get_symbol_offset(seq);
kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
- if (compare_symbol_name(name, namebuf))
+ if (strcmp(name, namebuf))
break;
low--;
}
@@ -248,7 +216,7 @@ static int kallsyms_lookup_names(const char *name,
seq = get_symbol_seq(high + 1);
off = get_symbol_offset(seq);
kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
- if (compare_symbol_name(name, namebuf))
+ if (strcmp(name, namebuf))
break;
high++;
}
@@ -407,8 +375,7 @@ static int kallsyms_lookup_buildid(unsigned long addr,
if (modbuildid)
*modbuildid = NULL;
- ret = strlen(namebuf);
- goto found;
+ return strlen(namebuf);
}
/* See if it's in a module or a BPF JITed image. */
@@ -422,8 +389,6 @@ static int kallsyms_lookup_buildid(unsigned long addr,
ret = ftrace_mod_address_lookup(addr, symbolsize,
offset, modname, namebuf);
-found:
- cleanup_symbol_name(namebuf);
return ret;
}
@@ -450,8 +415,6 @@ const char *kallsyms_lookup(unsigned long addr,
int lookup_symbol_name(unsigned long addr, char *symname)
{
- int res;
-
symname[0] = '\0';
symname[KSYM_NAME_LEN - 1] = '\0';
@@ -462,16 +425,10 @@ int lookup_symbol_name(unsigned long addr, char *symname)
/* Grab name */
kallsyms_expand_symbol(get_symbol_offset(pos),
symname, KSYM_NAME_LEN);
- goto found;
+ return 0;
}
/* See if it's in a module. */
- res = lookup_module_symbol_name(addr, symname);
- if (res)
- return res;
-
-found:
- cleanup_symbol_name(symname);
- return 0;
+ return lookup_module_symbol_name(addr, symname);
}
/* Look up a kernel symbol and return it in a text buffer. */
diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c
index 2f84896..873f7c4 100644
--- a/kernel/kallsyms_selftest.c
+++ b/kernel/kallsyms_selftest.c
@@ -187,31 +187,11 @@ static void test_perf_kallsyms_lookup_name(void)
stat.min, stat.max, div_u64(stat.sum, stat.real_cnt));
}
-static bool match_cleanup_name(const char *s, const char *name)
-{
- char *p;
- int len;
-
- if (!IS_ENABLED(CONFIG_LTO_CLANG))
- return false;
-
- p = strstr(s, ".llvm.");
- if (!p)
- return false;
-
- len = strlen(name);
- if (p - s != len)
- return false;
-
- return !strncmp(s, name, len);
-}
-
static int find_symbol(void *data, const char *name, unsigned long addr)
{
struct test_stat *stat = (struct test_stat *)data;
- if (strcmp(name, stat->name) == 0 ||
- (!stat->perf && match_cleanup_name(name, stat->name))) {
+ if (!strcmp(name, stat->name)) {
stat->real_cnt++;
stat->addr = addr;
diff --git a/kernel/panic.c b/kernel/panic.c
index f861bed..2a04491 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -64,6 +64,8 @@ unsigned long panic_on_taint;
bool panic_on_taint_nousertaint = false;
static unsigned int warn_limit __read_mostly;
+bool panic_triggering_all_cpu_backtrace;
+
int panic_timeout = CONFIG_PANIC_TIMEOUT;
EXPORT_SYMBOL_GPL(panic_timeout);
@@ -253,8 +255,12 @@ void check_panic_on_warn(const char *origin)
*/
static void panic_other_cpus_shutdown(bool crash_kexec)
{
- if (panic_print & PANIC_PRINT_ALL_CPU_BT)
+ if (panic_print & PANIC_PRINT_ALL_CPU_BT) {
+ /* Temporary allow non-panic CPUs to write their backtraces. */
+ panic_triggering_all_cpu_backtrace = true;
trigger_all_cpu_backtrace();
+ panic_triggering_all_cpu_backtrace = false;
+ }
/*
* Note that smp_send_stop() is the usual SMP shutdown function,
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 054c0e7..c22b0704 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2316,7 +2316,7 @@ asmlinkage int vprintk_emit(int facility, int level,
* non-panic CPUs are generating any messages, they will be
* silently dropped.
*/
- if (other_cpu_in_panic())
+ if (other_cpu_in_panic() && !panic_triggering_all_cpu_backtrace)
return 0;
if (level == LOGLEVEL_SCHED) {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 10cd38b..ebe7ce2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7956,7 +7956,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
trace_access_unlock(iter->cpu_file);
if (ret < 0) {
- if (trace_empty(iter)) {
+ if (trace_empty(iter) && !iter->closed) {
if ((filp->f_flags & O_NONBLOCK))
return -EAGAIN;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 1745ca7..e7b005f 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -377,7 +377,7 @@ struct workqueue_struct {
/* hot fields used during command issue, aligned to cacheline */
unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */
- struct pool_workqueue __percpu __rcu **cpu_pwq; /* I: per-cpu pwqs */
+ struct pool_workqueue __rcu * __percpu *cpu_pwq; /* I: per-cpu pwqs */
struct wq_node_nr_active *node_nr_active[]; /* I: per-node nr_active */
};
@@ -897,7 +897,7 @@ static struct worker_pool *get_work_pool(struct work_struct *work)
static unsigned long shift_and_mask(unsigned long v, u32 shift, u32 bits)
{
- return (v >> shift) & ((1 << bits) - 1);
+ return (v >> shift) & ((1U << bits) - 1);
}
static void work_offqd_unpack(struct work_offq_data *offqd, unsigned long data)
@@ -3351,7 +3351,6 @@ static int worker_thread(void *__worker)
set_pf_worker(false);
ida_free(&pool->worker_ida, worker->id);
- WARN_ON_ONCE(!list_empty(&worker->entry));
return 0;
}
@@ -4167,7 +4166,6 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
static bool __flush_work(struct work_struct *work, bool from_cancel)
{
struct wq_barrier barr;
- unsigned long data;
if (WARN_ON(!wq_online))
return false;
@@ -4185,29 +4183,35 @@ static bool __flush_work(struct work_struct *work, bool from_cancel)
* was queued on a BH workqueue, we also know that it was running in the
* BH context and thus can be busy-waited.
*/
- data = *work_data_bits(work);
- if (from_cancel &&
- !WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_BH)) {
- /*
- * On RT, prevent a live lock when %current preempted soft
- * interrupt processing or prevents ksoftirqd from running by
- * keeping flipping BH. If the BH work item runs on a different
- * CPU then this has no effect other than doing the BH
- * disable/enable dance for nothing. This is copied from
- * kernel/softirq.c::tasklet_unlock_spin_wait().
- */
- while (!try_wait_for_completion(&barr.done)) {
- if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
- local_bh_disable();
- local_bh_enable();
- } else {
- cpu_relax();
+ if (from_cancel) {
+ unsigned long data = *work_data_bits(work);
+
+ if (!WARN_ON_ONCE(data & WORK_STRUCT_PWQ) &&
+ (data & WORK_OFFQ_BH)) {
+ /*
+ * On RT, prevent a live lock when %current preempted
+ * soft interrupt processing or prevents ksoftirqd from
+ * running by keeping flipping BH. If the BH work item
+ * runs on a different CPU then this has no effect other
+ * than doing the BH disable/enable dance for nothing.
+ * This is copied from
+ * kernel/softirq.c::tasklet_unlock_spin_wait().
+ */
+ while (!try_wait_for_completion(&barr.done)) {
+ if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+ local_bh_disable();
+ local_bh_enable();
+ } else {
+ cpu_relax();
+ }
}
+ goto out_destroy;
}
- } else {
- wait_for_completion(&barr.done);
}
+ wait_for_completion(&barr.done);
+
+out_destroy:
destroy_work_on_stack(&barr.work);
return true;
}
diff --git a/lib/generic-radix-tree.c b/lib/generic-radix-tree.c
index aaefb9b..fa692c8 100644
--- a/lib/generic-radix-tree.c
+++ b/lib/generic-radix-tree.c
@@ -121,6 +121,8 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset,
if ((v = cmpxchg_release(&radix->root, r, new_root)) == r) {
v = new_root;
new_node = NULL;
+ } else {
+ new_node->children[0] = NULL;
}
}
diff --git a/lib/overflow_kunit.c b/lib/overflow_kunit.c
index f314a0c..2abc783 100644
--- a/lib/overflow_kunit.c
+++ b/lib/overflow_kunit.c
@@ -668,7 +668,6 @@ DEFINE_TEST_ALLOC(devm_kzalloc, devm_kfree, 1, 1, 0);
static void overflow_allocation_test(struct kunit *test)
{
- const char device_name[] = "overflow-test";
struct device *dev;
int count = 0;
@@ -678,7 +677,7 @@ static void overflow_allocation_test(struct kunit *test)
} while (0)
/* Create dummy device for devm_kmalloc()-family tests. */
- dev = kunit_device_register(test, device_name);
+ dev = kunit_device_register(test, "overflow-test");
KUNIT_ASSERT_FALSE_MSG(test, IS_ERR(dev),
"Cannot register test device\n");
diff --git a/lib/vdso/getrandom.c b/lib/vdso/getrandom.c
index b230f0b..e1db228 100644
--- a/lib/vdso/getrandom.c
+++ b/lib/vdso/getrandom.c
@@ -85,6 +85,10 @@ __cvdso_getrandom_data(const struct vdso_rng_data *rng_info, void *buffer, size_
if (unlikely(((unsigned long)opaque_state & ~PAGE_MASK) + sizeof(*state) > PAGE_SIZE))
return -EFAULT;
+ /* Handle unexpected flags by falling back to the kernel. */
+ if (unlikely(flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE)))
+ goto fallback_syscall;
+
/* If the caller passes the wrong size, which might happen due to CRIU, fallback. */
if (unlikely(opaque_len != sizeof(*state)))
goto fallback_syscall;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f4be468..67c86a5d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1685,7 +1685,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
spin_unlock(vmf->ptl);
- goto out;
+ return 0;
}
pmd = pmd_modify(oldpmd, vma->vm_page_prot);
@@ -1728,22 +1728,16 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
if (!migrate_misplaced_folio(folio, vma, target_nid)) {
flags |= TNF_MIGRATED;
nid = target_nid;
- } else {
- flags |= TNF_MIGRATE_FAIL;
- vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
- if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
- spin_unlock(vmf->ptl);
- goto out;
- }
- goto out_map;
+ task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags);
+ return 0;
}
-out:
- if (nid != NUMA_NO_NODE)
- task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags);
-
- return 0;
-
+ flags |= TNF_MIGRATE_FAIL;
+ vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+ if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
+ spin_unlock(vmf->ptl);
+ return 0;
+ }
out_map:
/* Restore the PMD */
pmd = pmd_modify(oldpmd, vma->vm_page_prot);
@@ -1753,7 +1747,10 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd);
update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
spin_unlock(vmf->ptl);
- goto out;
+
+ if (nid != NUMA_NO_NODE)
+ task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags);
+ return 0;
}
/*
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 829112b..0c3f56b 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -185,11 +185,11 @@ static int vmemmap_remap_range(unsigned long start, unsigned long end,
static inline void free_vmemmap_page(struct page *page)
{
if (PageReserved(page)) {
+ memmap_boot_pages_add(-1);
free_bootmem_page(page);
- mod_node_page_state(page_pgdat(page), NR_MEMMAP_BOOT, -1);
} else {
+ memmap_pages_add(-1);
__free_page(page);
- mod_node_page_state(page_pgdat(page), NR_MEMMAP, -1);
}
}
@@ -341,7 +341,7 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end,
copy_page(page_to_virt(walk.reuse_page),
(void *)walk.reuse_addr);
list_add(&walk.reuse_page->lru, vmemmap_pages);
- mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, 1);
+ memmap_pages_add(1);
}
/*
@@ -392,14 +392,11 @@ static int alloc_vmemmap_page_list(unsigned long start, unsigned long end,
for (i = 0; i < nr_pages; i++) {
page = alloc_pages_node(nid, gfp_mask, 0);
- if (!page) {
- mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, i);
+ if (!page)
goto out;
- }
list_add(&page->lru, list);
}
-
- mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, nr_pages);
+ memmap_pages_add(nr_pages);
return 0;
out:
diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c
index 2aeea4d..417c96f 100644
--- a/mm/memcontrol-v1.c
+++ b/mm/memcontrol-v1.c
@@ -1842,9 +1842,12 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
buf = endp + 1;
cfd = simple_strtoul(buf, &endp, 10);
- if ((*endp != ' ') && (*endp != '\0'))
+ if (*endp == '\0')
+ buf = endp;
+ else if (*endp == ' ')
+ buf = endp + 1;
+ else
return -EINVAL;
- buf = endp + 1;
event = kzalloc(sizeof(*event), GFP_KERNEL);
if (!event)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 581d3e5..7066fc8 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -2417,7 +2417,7 @@ struct memory_failure_entry {
struct memory_failure_cpu {
DECLARE_KFIFO(fifo, struct memory_failure_entry,
MEMORY_FAILURE_FIFO_SIZE);
- spinlock_t lock;
+ raw_spinlock_t lock;
struct work_struct work;
};
@@ -2443,20 +2443,22 @@ void memory_failure_queue(unsigned long pfn, int flags)
{
struct memory_failure_cpu *mf_cpu;
unsigned long proc_flags;
+ bool buffer_overflow;
struct memory_failure_entry entry = {
.pfn = pfn,
.flags = flags,
};
mf_cpu = &get_cpu_var(memory_failure_cpu);
- spin_lock_irqsave(&mf_cpu->lock, proc_flags);
- if (kfifo_put(&mf_cpu->fifo, entry))
+ raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags);
+ buffer_overflow = !kfifo_put(&mf_cpu->fifo, entry);
+ if (!buffer_overflow)
schedule_work_on(smp_processor_id(), &mf_cpu->work);
- else
+ raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
+ put_cpu_var(memory_failure_cpu);
+ if (buffer_overflow)
pr_err("buffer overflow when queuing memory failure at %#lx\n",
pfn);
- spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
- put_cpu_var(memory_failure_cpu);
}
EXPORT_SYMBOL_GPL(memory_failure_queue);
@@ -2469,9 +2471,9 @@ static void memory_failure_work_func(struct work_struct *work)
mf_cpu = container_of(work, struct memory_failure_cpu, work);
for (;;) {
- spin_lock_irqsave(&mf_cpu->lock, proc_flags);
+ raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags);
gotten = kfifo_get(&mf_cpu->fifo, &entry);
- spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
+ raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
if (!gotten)
break;
if (entry.flags & MF_SOFT_OFFLINE)
@@ -2501,7 +2503,7 @@ static int __init memory_failure_init(void)
for_each_possible_cpu(cpu) {
mf_cpu = &per_cpu(memory_failure_cpu, cpu);
- spin_lock_init(&mf_cpu->lock);
+ raw_spin_lock_init(&mf_cpu->lock);
INIT_KFIFO(mf_cpu->fifo);
INIT_WORK(&mf_cpu->work, memory_failure_work_func);
}
diff --git a/mm/memory.c b/mm/memory.c
index 34f8402..3c01d68 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5295,7 +5295,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
if (unlikely(!pte_same(old_pte, vmf->orig_pte))) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
- goto out;
+ return 0;
}
pte = pte_modify(old_pte, vma->vm_page_prot);
@@ -5358,23 +5358,19 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
if (!migrate_misplaced_folio(folio, vma, target_nid)) {
nid = target_nid;
flags |= TNF_MIGRATED;
- } else {
- flags |= TNF_MIGRATE_FAIL;
- vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
- vmf->address, &vmf->ptl);
- if (unlikely(!vmf->pte))
- goto out;
- if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) {
- pte_unmap_unlock(vmf->pte, vmf->ptl);
- goto out;
- }
- goto out_map;
+ task_numa_fault(last_cpupid, nid, nr_pages, flags);
+ return 0;
}
-out:
- if (nid != NUMA_NO_NODE)
- task_numa_fault(last_cpupid, nid, nr_pages, flags);
- return 0;
+ flags |= TNF_MIGRATE_FAIL;
+ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
+ vmf->address, &vmf->ptl);
+ if (unlikely(!vmf->pte))
+ return 0;
+ if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) {
+ pte_unmap_unlock(vmf->pte, vmf->ptl);
+ return 0;
+ }
out_map:
/*
* Make it present again, depending on how arch implements
@@ -5387,7 +5383,10 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
numa_rebuild_single_mapping(vmf, vma, vmf->address, vmf->pte,
writable);
pte_unmap_unlock(vmf->pte, vmf->ptl);
- goto out;
+
+ if (nid != NUMA_NO_NODE)
+ task_numa_fault(last_cpupid, nid, nr_pages, flags);
+ return 0;
}
static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
diff --git a/mm/migrate.c b/mm/migrate.c
index e7296c0..923ea80 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1479,11 +1479,17 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio,
return rc;
}
-static inline int try_split_folio(struct folio *folio, struct list_head *split_folios)
+static inline int try_split_folio(struct folio *folio, struct list_head *split_folios,
+ enum migrate_mode mode)
{
int rc;
- folio_lock(folio);
+ if (mode == MIGRATE_ASYNC) {
+ if (!folio_trylock(folio))
+ return -EAGAIN;
+ } else {
+ folio_lock(folio);
+ }
rc = split_folio_to_list(folio, split_folios);
folio_unlock(folio);
if (!rc)
@@ -1677,7 +1683,7 @@ static int migrate_pages_batch(struct list_head *from,
*/
if (nr_pages > 2 &&
!list_empty(&folio->_deferred_list)) {
- if (try_split_folio(folio, split_folios) == 0) {
+ if (!try_split_folio(folio, split_folios, mode)) {
nr_failed++;
stats->nr_thp_failed += is_thp;
stats->nr_thp_split += is_thp;
@@ -1699,7 +1705,7 @@ static int migrate_pages_batch(struct list_head *from,
if (!thp_migration_supported() && is_thp) {
nr_failed++;
stats->nr_thp_failed++;
- if (!try_split_folio(folio, split_folios)) {
+ if (!try_split_folio(folio, split_folios, mode)) {
stats->nr_thp_split++;
stats->nr_split++;
continue;
@@ -1731,7 +1737,7 @@ static int migrate_pages_batch(struct list_head *from,
stats->nr_thp_failed += is_thp;
/* Large folio NUMA faulting doesn't split to retry. */
if (is_large && !nosplit) {
- int ret = try_split_folio(folio, split_folios);
+ int ret = try_split_folio(folio, split_folios, mode);
if (!ret) {
stats->nr_thp_split += is_thp;
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 75c3bd4..5196007 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1623,8 +1623,7 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat)
panic("Failed to allocate %ld bytes for node %d memory map\n",
size, pgdat->node_id);
pgdat->node_mem_map = map + offset;
- mod_node_early_perpage_metadata(pgdat->node_id,
- DIV_ROUND_UP(size, PAGE_SIZE));
+ memmap_boot_pages_add(DIV_ROUND_UP(size, PAGE_SIZE));
pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n",
__func__, pgdat->node_id, (unsigned long)pgdat,
(unsigned long)pgdat->node_mem_map);
@@ -2245,6 +2244,8 @@ void __init init_cma_reserved_pageblock(struct page *page)
set_pageblock_migratetype(page, MIGRATE_CMA);
set_page_refcounted(page);
+ /* pages were reserved and not allocated */
+ clear_page_tag_ref(page);
__free_pages(page, pageblock_order);
adjust_managed_page_count(page, pageblock_nr_pages);
@@ -2460,15 +2461,7 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn,
}
/* pages were reserved and not allocated */
- if (mem_alloc_profiling_enabled()) {
- union codetag_ref *ref = get_page_tag_ref(page);
-
- if (ref) {
- set_codetag_empty(ref);
- put_page_tag_ref(ref);
- }
- }
-
+ clear_page_tag_ref(page);
__free_pages_core(page, order, MEMINIT_EARLY);
}
diff --git a/mm/mseal.c b/mm/mseal.c
index bf783bb..15bba28 100644
--- a/mm/mseal.c
+++ b/mm/mseal.c
@@ -40,9 +40,17 @@ static bool can_modify_vma(struct vm_area_struct *vma)
static bool is_madv_discard(int behavior)
{
- return behavior &
- (MADV_FREE | MADV_DONTNEED | MADV_DONTNEED_LOCKED |
- MADV_REMOVE | MADV_DONTFORK | MADV_WIPEONFORK);
+ switch (behavior) {
+ case MADV_FREE:
+ case MADV_DONTNEED:
+ case MADV_DONTNEED_LOCKED:
+ case MADV_REMOVE:
+ case MADV_DONTFORK:
+ case MADV_WIPEONFORK:
+ return true;
+ }
+
+ return false;
}
static bool is_ro_anon(struct vm_area_struct *vma)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 28f80da..c565de8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -287,7 +287,7 @@ EXPORT_SYMBOL(nr_online_nodes);
static bool page_contains_unaccepted(struct page *page, unsigned int order);
static void accept_page(struct page *page, unsigned int order);
-static bool try_to_accept_memory(struct zone *zone, unsigned int order);
+static bool cond_accept_memory(struct zone *zone, unsigned int order);
static inline bool has_unaccepted_memory(void);
static bool __free_unaccepted(struct page *page);
@@ -3072,9 +3072,6 @@ static inline long __zone_watermark_unusable_free(struct zone *z,
if (!(alloc_flags & ALLOC_CMA))
unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES);
#endif
-#ifdef CONFIG_UNACCEPTED_MEMORY
- unusable_free += zone_page_state(z, NR_UNACCEPTED);
-#endif
return unusable_free;
}
@@ -3368,6 +3365,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
}
}
+ cond_accept_memory(zone, order);
+
/*
* Detect whether the number of free pages is below high
* watermark. If so, we will decrease pcp->high and free
@@ -3393,10 +3392,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
gfp_mask)) {
int ret;
- if (has_unaccepted_memory()) {
- if (try_to_accept_memory(zone, order))
- goto try_this_zone;
- }
+ if (cond_accept_memory(zone, order))
+ goto try_this_zone;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/*
@@ -3450,10 +3447,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
return page;
} else {
- if (has_unaccepted_memory()) {
- if (try_to_accept_memory(zone, order))
- goto try_this_zone;
- }
+ if (cond_accept_memory(zone, order))
+ goto try_this_zone;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/* Try again if zone has deferred pages */
@@ -5755,7 +5750,6 @@ void __init setup_per_cpu_pageset(void)
for_each_online_pgdat(pgdat)
pgdat->per_cpu_nodestats =
alloc_percpu(struct per_cpu_nodestat);
- store_early_perpage_metadata();
}
__meminit void zone_pcp_init(struct zone *zone)
@@ -5821,14 +5815,7 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char
void free_reserved_page(struct page *page)
{
- if (mem_alloc_profiling_enabled()) {
- union codetag_ref *ref = get_page_tag_ref(page);
-
- if (ref) {
- set_codetag_empty(ref);
- put_page_tag_ref(ref);
- }
- }
+ clear_page_tag_ref(page);
ClearPageReserved(page);
init_page_count(page);
__free_page(page);
@@ -6951,9 +6938,6 @@ static bool try_to_accept_memory_one(struct zone *zone)
struct page *page;
bool last;
- if (list_empty(&zone->unaccepted_pages))
- return false;
-
spin_lock_irqsave(&zone->lock, flags);
page = list_first_entry_or_null(&zone->unaccepted_pages,
struct page, lru);
@@ -6979,23 +6963,29 @@ static bool try_to_accept_memory_one(struct zone *zone)
return true;
}
-static bool try_to_accept_memory(struct zone *zone, unsigned int order)
+static bool cond_accept_memory(struct zone *zone, unsigned int order)
{
long to_accept;
- int ret = false;
+ bool ret = false;
+
+ if (!has_unaccepted_memory())
+ return false;
+
+ if (list_empty(&zone->unaccepted_pages))
+ return false;
/* How much to accept to get to high watermark? */
to_accept = high_wmark_pages(zone) -
(zone_page_state(zone, NR_FREE_PAGES) -
- __zone_watermark_unusable_free(zone, order, 0));
+ __zone_watermark_unusable_free(zone, order, 0) -
+ zone_page_state(zone, NR_UNACCEPTED));
- /* Accept at least one page */
- do {
+ while (to_accept > 0) {
if (!try_to_accept_memory_one(zone))
break;
ret = true;
to_accept -= MAX_ORDER_NR_PAGES;
- } while (to_accept > 0);
+ }
return ret;
}
@@ -7038,7 +7028,7 @@ static void accept_page(struct page *page, unsigned int order)
{
}
-static bool try_to_accept_memory(struct zone *zone, unsigned int order)
+static bool cond_accept_memory(struct zone *zone, unsigned int order)
{
return false;
}
diff --git a/mm/page_ext.c b/mm/page_ext.c
index c191e49..641d93f 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -214,8 +214,7 @@ static int __init alloc_node_page_ext(int nid)
return -ENOMEM;
NODE_DATA(nid)->node_page_ext = base;
total_usage += table_size;
- mod_node_page_state(NODE_DATA(nid), NR_MEMMAP_BOOT,
- DIV_ROUND_UP(table_size, PAGE_SIZE));
+ memmap_boot_pages_add(DIV_ROUND_UP(table_size, PAGE_SIZE));
return 0;
}
@@ -275,10 +274,8 @@ static void *__meminit alloc_page_ext(size_t size, int nid)
else
addr = vzalloc_node(size, nid);
- if (addr) {
- mod_node_page_state(NODE_DATA(nid), NR_MEMMAP,
- DIV_ROUND_UP(size, PAGE_SIZE));
- }
+ if (addr)
+ memmap_pages_add(DIV_ROUND_UP(size, PAGE_SIZE));
return addr;
}
@@ -323,25 +320,18 @@ static void free_page_ext(void *addr)
{
size_t table_size;
struct page *page;
- struct pglist_data *pgdat;
table_size = page_ext_size * PAGES_PER_SECTION;
+ memmap_pages_add(-1L * (DIV_ROUND_UP(table_size, PAGE_SIZE)));
if (is_vmalloc_addr(addr)) {
- page = vmalloc_to_page(addr);
- pgdat = page_pgdat(page);
vfree(addr);
} else {
page = virt_to_page(addr);
- pgdat = page_pgdat(page);
BUG_ON(PageReserved(page));
kmemleak_free(addr);
free_pages_exact(addr, table_size);
}
-
- mod_node_page_state(pgdat, NR_MEMMAP,
- -1L * (DIV_ROUND_UP(table_size, PAGE_SIZE)));
-
}
static void __free_page_ext(unsigned long pfn)
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 1dda6c5..edcc7a6 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -469,13 +469,10 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn,
if (r < 0)
return NULL;
- if (system_state == SYSTEM_BOOTING) {
- mod_node_early_perpage_metadata(nid, DIV_ROUND_UP(end - start,
- PAGE_SIZE));
- } else {
- mod_node_page_state(NODE_DATA(nid), NR_MEMMAP,
- DIV_ROUND_UP(end - start, PAGE_SIZE));
- }
+ if (system_state == SYSTEM_BOOTING)
+ memmap_boot_pages_add(DIV_ROUND_UP(end - start, PAGE_SIZE));
+ else
+ memmap_pages_add(DIV_ROUND_UP(end - start, PAGE_SIZE));
return pfn_to_page(pfn);
}
diff --git a/mm/sparse.c b/mm/sparse.c
index e4b8300..0f018c6 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -463,7 +463,7 @@ static void __init sparse_buffer_init(unsigned long size, int nid)
sparsemap_buf = memmap_alloc(size, section_map_size(), addr, nid, true);
sparsemap_buf_end = sparsemap_buf + size;
#ifndef CONFIG_SPARSEMEM_VMEMMAP
- mod_node_early_perpage_metadata(nid, DIV_ROUND_UP(size, PAGE_SIZE));
+ memmap_boot_pages_add(DIV_ROUND_UP(size, PAGE_SIZE));
#endif
}
@@ -643,8 +643,7 @@ static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
unsigned long start = (unsigned long) pfn_to_page(pfn);
unsigned long end = start + nr_pages * sizeof(struct page);
- mod_node_page_state(page_pgdat(pfn_to_page(pfn)), NR_MEMMAP,
- -1L * (DIV_ROUND_UP(end - start, PAGE_SIZE)));
+ memmap_pages_add(-1L * (DIV_ROUND_UP(end - start, PAGE_SIZE)));
vmemmap_free(start, end, altmap);
}
static void free_map_bootmem(struct page *memmap)
diff --git a/mm/truncate.c b/mm/truncate.c
index 4d61fbd..0668cd3 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -157,7 +157,7 @@ static void truncate_cleanup_folio(struct folio *folio)
if (folio_mapped(folio))
unmap_mapping_folio(folio);
- if (folio_has_private(folio))
+ if (folio_needs_release(folio))
folio_invalidate(folio, 0, folio_size(folio));
/*
@@ -219,7 +219,7 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
if (!mapping_inaccessible(folio->mapping))
folio_zero_range(folio, offset, length);
- if (folio_has_private(folio))
+ if (folio_needs_release(folio))
folio_invalidate(folio, offset, length);
if (!folio_test_large(folio))
return true;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 6b783ba..af2de36 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3584,15 +3584,8 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
page = alloc_pages_noprof(alloc_gfp, order);
else
page = alloc_pages_node_noprof(nid, alloc_gfp, order);
- if (unlikely(!page)) {
- if (!nofail)
- break;
-
- /* fall back to the zero order allocations */
- alloc_gfp |= __GFP_NOFAIL;
- order = 0;
- continue;
- }
+ if (unlikely(!page))
+ break;
/*
* Higher order allocations must be able to be treated as
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 04a1cb6..e875f2a 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1033,6 +1033,24 @@ unsigned long node_page_state(struct pglist_data *pgdat,
}
#endif
+/*
+ * Count number of pages "struct page" and "struct page_ext" consume.
+ * nr_memmap_boot_pages: # of pages allocated by boot allocator
+ * nr_memmap_pages: # of pages that were allocated by buddy allocator
+ */
+static atomic_long_t nr_memmap_boot_pages = ATOMIC_LONG_INIT(0);
+static atomic_long_t nr_memmap_pages = ATOMIC_LONG_INIT(0);
+
+void memmap_boot_pages_add(long delta)
+{
+ atomic_long_add(delta, &nr_memmap_boot_pages);
+}
+
+void memmap_pages_add(long delta)
+{
+ atomic_long_add(delta, &nr_memmap_pages);
+}
+
#ifdef CONFIG_COMPACTION
struct contig_page_info {
@@ -1255,11 +1273,11 @@ const char * const vmstat_text[] = {
"pgdemote_kswapd",
"pgdemote_direct",
"pgdemote_khugepaged",
- "nr_memmap",
- "nr_memmap_boot",
- /* enum writeback_stat_item counters */
+ /* system-wide enum vm_stat_item counters */
"nr_dirty_threshold",
"nr_dirty_background_threshold",
+ "nr_memmap_pages",
+ "nr_memmap_boot_pages",
#if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG)
/* enum vm_event_item counters */
@@ -1790,7 +1808,7 @@ static const struct seq_operations zoneinfo_op = {
#define NR_VMSTAT_ITEMS (NR_VM_ZONE_STAT_ITEMS + \
NR_VM_NUMA_EVENT_ITEMS + \
NR_VM_NODE_STAT_ITEMS + \
- NR_VM_WRITEBACK_STAT_ITEMS + \
+ NR_VM_STAT_ITEMS + \
(IS_ENABLED(CONFIG_VM_EVENT_COUNTERS) ? \
NR_VM_EVENT_ITEMS : 0))
@@ -1827,7 +1845,9 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos)
global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD,
v + NR_DIRTY_THRESHOLD);
- v += NR_VM_WRITEBACK_STAT_ITEMS;
+ v[NR_MEMMAP_PAGES] = atomic_long_read(&nr_memmap_pages);
+ v[NR_MEMMAP_BOOT_PAGES] = atomic_long_read(&nr_memmap_boot_pages);
+ v += NR_VM_STAT_ITEMS;
#ifdef CONFIG_VM_EVENT_COUNTERS
all_vm_events(v);
@@ -2285,25 +2305,3 @@ static int __init extfrag_debug_init(void)
module_init(extfrag_debug_init);
#endif
-
-/*
- * Page metadata size (struct page and page_ext) in pages
- */
-static unsigned long early_perpage_metadata[MAX_NUMNODES] __meminitdata;
-
-void __meminit mod_node_early_perpage_metadata(int nid, long delta)
-{
- early_perpage_metadata[nid] += delta;
-}
-
-void __meminit store_early_perpage_metadata(void)
-{
- int nid;
- struct pglist_data *pgdat;
-
- for_each_online_pgdat(pgdat) {
- nid = pgdat->node_id;
- mod_node_page_state(NODE_DATA(nid), NR_MEMMAP_BOOT,
- early_perpage_metadata[nid]);
- }
-}
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 06da8ac..d6976db 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2406,10 +2406,16 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action,
/* To avoid a potential race with hci_unregister_dev. */
hci_dev_hold(hdev);
- if (action == PM_SUSPEND_PREPARE)
+ switch (action) {
+ case PM_HIBERNATION_PREPARE:
+ case PM_SUSPEND_PREPARE:
ret = hci_suspend_dev(hdev);
- else if (action == PM_POST_SUSPEND)
+ break;
+ case PM_POST_HIBERNATION:
+ case PM_POST_SUSPEND:
ret = hci_resume_dev(hdev);
+ break;
+ }
if (ret)
bt_dev_err(hdev, "Suspend notifier action (%lu) failed: %d",
@@ -3664,19 +3670,19 @@ static void hci_sched_le(struct hci_dev *hdev)
{
struct hci_chan *chan;
struct sk_buff *skb;
- int quote, cnt, tmp;
+ int quote, *cnt, tmp;
BT_DBG("%s", hdev->name);
if (!hci_conn_num(hdev, LE_LINK))
return;
- cnt = hdev->le_pkts ? hdev->le_cnt : hdev->acl_cnt;
+ cnt = hdev->le_pkts ? &hdev->le_cnt : &hdev->acl_cnt;
- __check_timeout(hdev, cnt, LE_LINK);
+ __check_timeout(hdev, *cnt, LE_LINK);
- tmp = cnt;
- while (cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) {
+ tmp = *cnt;
+ while (*cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) {
u32 priority = (skb_peek(&chan->data_q))->priority;
while (quote-- && (skb = skb_peek(&chan->data_q))) {
BT_DBG("chan %p skb %p len %d priority %u", chan, skb,
@@ -3691,7 +3697,7 @@ static void hci_sched_le(struct hci_dev *hdev)
hci_send_frame(hdev, skb);
hdev->le_last_tx = jiffies;
- cnt--;
+ (*cnt)--;
chan->sent++;
chan->conn->sent++;
@@ -3701,12 +3707,7 @@ static void hci_sched_le(struct hci_dev *hdev)
}
}
- if (hdev->le_pkts)
- hdev->le_cnt = cnt;
- else
- hdev->acl_cnt = cnt;
-
- if (cnt != tmp)
+ if (*cnt != tmp)
hci_prio_recalculate(hdev, LE_LINK);
}
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index d0c118c..1c82dcd 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -5920,7 +5920,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev,
* while we have an existing one in peripheral role.
*/
if (hdev->conn_hash.le_num_peripheral > 0 &&
- (!test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) ||
+ (test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) ||
!(hdev->le_states[3] & 0x10)))
return NULL;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 40d4887..25979f4 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3456,6 +3456,10 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data,
* will be kept and this function does nothing.
*/
p = hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type);
+ if (!p) {
+ err = -EIO;
+ goto unlock;
+ }
if (p->auto_connect == HCI_AUTO_CONN_EXPLICIT)
p->auto_connect = HCI_AUTO_CONN_DISABLED;
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 1e7ea3a..4f9fdf4 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -914,7 +914,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
* Confirms and the responder Enters the passkey.
*/
if (smp->method == OVERLAP) {
- if (hcon->role == HCI_ROLE_MASTER)
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
smp->method = CFM_PASSKEY;
else
smp->method = REQ_PASSKEY;
@@ -964,7 +964,7 @@ static u8 smp_confirm(struct smp_chan *smp)
smp_send_cmd(smp->conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp);
- if (conn->hcon->out)
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM);
else
SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);
@@ -980,7 +980,8 @@ static u8 smp_random(struct smp_chan *smp)
int ret;
bt_dev_dbg(conn->hcon->hdev, "conn %p %s", conn,
- conn->hcon->out ? "initiator" : "responder");
+ test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" :
+ "responder");
ret = smp_c1(smp->tk, smp->rrnd, smp->preq, smp->prsp,
hcon->init_addr_type, &hcon->init_addr,
@@ -994,7 +995,7 @@ static u8 smp_random(struct smp_chan *smp)
return SMP_CONFIRM_FAILED;
}
- if (hcon->out) {
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
u8 stk[16];
__le64 rand = 0;
__le16 ediv = 0;
@@ -1256,14 +1257,15 @@ static void smp_distribute_keys(struct smp_chan *smp)
rsp = (void *) &smp->prsp[1];
/* The responder sends its keys first */
- if (hcon->out && (smp->remote_key_dist & KEY_DIST_MASK)) {
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags) &&
+ (smp->remote_key_dist & KEY_DIST_MASK)) {
smp_allow_key_dist(smp);
return;
}
req = (void *) &smp->preq[1];
- if (hcon->out) {
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
keydist = &rsp->init_key_dist;
*keydist &= req->init_key_dist;
} else {
@@ -1432,7 +1434,7 @@ static int sc_mackey_and_ltk(struct smp_chan *smp, u8 mackey[16], u8 ltk[16])
struct hci_conn *hcon = smp->conn->hcon;
u8 *na, *nb, a[7], b[7];
- if (hcon->out) {
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
na = smp->prnd;
nb = smp->rrnd;
} else {
@@ -1460,7 +1462,7 @@ static void sc_dhkey_check(struct smp_chan *smp)
a[6] = hcon->init_addr_type;
b[6] = hcon->resp_addr_type;
- if (hcon->out) {
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
local_addr = a;
remote_addr = b;
memcpy(io_cap, &smp->preq[1], 3);
@@ -1539,7 +1541,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op)
/* The round is only complete when the initiator
* receives pairing random.
*/
- if (!hcon->out) {
+ if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM,
sizeof(smp->prnd), smp->prnd);
if (smp->passkey_round == 20)
@@ -1567,7 +1569,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op)
SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);
- if (hcon->out) {
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM,
sizeof(smp->prnd), smp->prnd);
return 0;
@@ -1578,7 +1580,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op)
case SMP_CMD_PUBLIC_KEY:
default:
/* Initiating device starts the round */
- if (!hcon->out)
+ if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags))
return 0;
bt_dev_dbg(hdev, "Starting passkey round %u",
@@ -1623,7 +1625,7 @@ static int sc_user_reply(struct smp_chan *smp, u16 mgmt_op, __le32 passkey)
}
/* Initiator sends DHKey check first */
- if (hcon->out) {
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
sc_dhkey_check(smp);
SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK);
} else if (test_and_clear_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags)) {
@@ -1746,7 +1748,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
struct smp_cmd_pairing rsp, *req = (void *) skb->data;
struct l2cap_chan *chan = conn->smp;
struct hci_dev *hdev = conn->hcon->hdev;
- struct smp_chan *smp;
+ struct smp_chan *smp = chan->data;
u8 key_size, auth, sec_level;
int ret;
@@ -1755,16 +1757,14 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
if (skb->len < sizeof(*req))
return SMP_INVALID_PARAMS;
- if (conn->hcon->role != HCI_ROLE_SLAVE)
+ if (smp && test_bit(SMP_FLAG_INITIATOR, &smp->flags))
return SMP_CMD_NOTSUPP;
- if (!chan->data)
+ if (!smp) {
smp = smp_chan_create(conn);
- else
- smp = chan->data;
-
- if (!smp)
- return SMP_UNSPECIFIED;
+ if (!smp)
+ return SMP_UNSPECIFIED;
+ }
/* We didn't start the pairing, so match remote */
auth = req->auth_req & AUTH_REQ_MASK(hdev);
@@ -1946,7 +1946,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb)
if (skb->len < sizeof(*rsp))
return SMP_INVALID_PARAMS;
- if (conn->hcon->role != HCI_ROLE_MASTER)
+ if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags))
return SMP_CMD_NOTSUPP;
skb_pull(skb, sizeof(*rsp));
@@ -2041,7 +2041,7 @@ static u8 sc_check_confirm(struct smp_chan *smp)
if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY)
return sc_passkey_round(smp, SMP_CMD_PAIRING_CONFIRM);
- if (conn->hcon->out) {
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd),
smp->prnd);
SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);
@@ -2063,7 +2063,7 @@ static int fixup_sc_false_positive(struct smp_chan *smp)
u8 auth;
/* The issue is only observed when we're in responder role */
- if (hcon->out)
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
return SMP_UNSPECIFIED;
if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) {
@@ -2099,7 +2099,8 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb)
struct hci_dev *hdev = hcon->hdev;
bt_dev_dbg(hdev, "conn %p %s", conn,
- hcon->out ? "initiator" : "responder");
+ test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" :
+ "responder");
if (skb->len < sizeof(smp->pcnf))
return SMP_INVALID_PARAMS;
@@ -2121,7 +2122,7 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb)
return ret;
}
- if (conn->hcon->out) {
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd),
smp->prnd);
SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);
@@ -2156,7 +2157,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
if (!test_bit(SMP_FLAG_SC, &smp->flags))
return smp_random(smp);
- if (hcon->out) {
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
pkax = smp->local_pk;
pkbx = smp->remote_pk;
na = smp->prnd;
@@ -2169,7 +2170,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
}
if (smp->method == REQ_OOB) {
- if (!hcon->out)
+ if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags))
smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM,
sizeof(smp->prnd), smp->prnd);
SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK);
@@ -2180,7 +2181,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY)
return sc_passkey_round(smp, SMP_CMD_PAIRING_RANDOM);
- if (hcon->out) {
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
u8 cfm[16];
err = smp_f4(smp->tfm_cmac, smp->remote_pk, smp->local_pk,
@@ -2221,7 +2222,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
return SMP_UNSPECIFIED;
if (smp->method == REQ_OOB) {
- if (hcon->out) {
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
sc_dhkey_check(smp);
SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK);
}
@@ -2295,10 +2296,27 @@ bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level,
return false;
}
+static void smp_send_pairing_req(struct smp_chan *smp, __u8 auth)
+{
+ struct smp_cmd_pairing cp;
+
+ if (smp->conn->hcon->type == ACL_LINK)
+ build_bredr_pairing_cmd(smp, &cp, NULL);
+ else
+ build_pairing_cmd(smp->conn, &cp, NULL, auth);
+
+ smp->preq[0] = SMP_CMD_PAIRING_REQ;
+ memcpy(&smp->preq[1], &cp, sizeof(cp));
+
+ smp_send_cmd(smp->conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp);
+ SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP);
+
+ set_bit(SMP_FLAG_INITIATOR, &smp->flags);
+}
+
static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
{
struct smp_cmd_security_req *rp = (void *) skb->data;
- struct smp_cmd_pairing cp;
struct hci_conn *hcon = conn->hcon;
struct hci_dev *hdev = hcon->hdev;
struct smp_chan *smp;
@@ -2347,18 +2365,22 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
skb_pull(skb, sizeof(*rp));
- memset(&cp, 0, sizeof(cp));
- build_pairing_cmd(conn, &cp, NULL, auth);
-
- smp->preq[0] = SMP_CMD_PAIRING_REQ;
- memcpy(&smp->preq[1], &cp, sizeof(cp));
-
- smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp);
- SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP);
+ smp_send_pairing_req(smp, auth);
return 0;
}
+static void smp_send_security_req(struct smp_chan *smp, __u8 auth)
+{
+ struct smp_cmd_security_req cp;
+
+ cp.auth_req = auth;
+ smp_send_cmd(smp->conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp);
+ SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ);
+
+ clear_bit(SMP_FLAG_INITIATOR, &smp->flags);
+}
+
int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
{
struct l2cap_conn *conn = hcon->l2cap_data;
@@ -2427,23 +2449,11 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
authreq |= SMP_AUTH_MITM;
}
- if (hcon->role == HCI_ROLE_MASTER) {
- struct smp_cmd_pairing cp;
+ if (hcon->role == HCI_ROLE_MASTER)
+ smp_send_pairing_req(smp, authreq);
+ else
+ smp_send_security_req(smp, authreq);
- build_pairing_cmd(conn, &cp, NULL, authreq);
- smp->preq[0] = SMP_CMD_PAIRING_REQ;
- memcpy(&smp->preq[1], &cp, sizeof(cp));
-
- smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp);
- SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP);
- } else {
- struct smp_cmd_security_req cp;
- cp.auth_req = authreq;
- smp_send_cmd(conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp);
- SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ);
- }
-
- set_bit(SMP_FLAG_INITIATOR, &smp->flags);
ret = 0;
unlock:
@@ -2694,8 +2704,6 @@ static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb)
static u8 sc_select_method(struct smp_chan *smp)
{
- struct l2cap_conn *conn = smp->conn;
- struct hci_conn *hcon = conn->hcon;
struct smp_cmd_pairing *local, *remote;
u8 local_mitm, remote_mitm, local_io, remote_io, method;
@@ -2708,7 +2716,7 @@ static u8 sc_select_method(struct smp_chan *smp)
* the "struct smp_cmd_pairing" from them we need to skip the
* first byte which contains the opcode.
*/
- if (hcon->out) {
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
local = (void *) &smp->preq[1];
remote = (void *) &smp->prsp[1];
} else {
@@ -2777,7 +2785,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
/* Non-initiating device sends its public key after receiving
* the key from the initiating device.
*/
- if (!hcon->out) {
+ if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
err = sc_send_public_key(smp);
if (err)
return err;
@@ -2839,7 +2847,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
}
if (smp->method == REQ_OOB) {
- if (hcon->out)
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM,
sizeof(smp->prnd), smp->prnd);
@@ -2848,7 +2856,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
return 0;
}
- if (hcon->out)
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM);
if (smp->method == REQ_PASSKEY) {
@@ -2863,7 +2871,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
/* The Initiating device waits for the non-initiating device to
* send the confirm value.
*/
- if (conn->hcon->out)
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
return 0;
err = smp_f4(smp->tfm_cmac, smp->local_pk, smp->remote_pk, smp->prnd,
@@ -2897,7 +2905,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb)
a[6] = hcon->init_addr_type;
b[6] = hcon->resp_addr_type;
- if (hcon->out) {
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
local_addr = a;
remote_addr = b;
memcpy(io_cap, &smp->prsp[1], 3);
@@ -2922,7 +2930,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb)
if (crypto_memneq(check->e, e, 16))
return SMP_DHKEY_CHECK_FAILED;
- if (!hcon->out) {
+ if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
if (test_bit(SMP_FLAG_WAIT_USER, &smp->flags)) {
set_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags);
return 0;
@@ -2934,7 +2942,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb)
sc_add_ltk(smp);
- if (hcon->out) {
+ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
hci_le_start_enc(hcon, 0, 0, smp->tk, smp->enc_key_size);
hcon->enc_key_size = smp->enc_key_size;
}
@@ -3083,7 +3091,6 @@ static void bredr_pairing(struct l2cap_chan *chan)
struct l2cap_conn *conn = chan->conn;
struct hci_conn *hcon = conn->hcon;
struct hci_dev *hdev = hcon->hdev;
- struct smp_cmd_pairing req;
struct smp_chan *smp;
bt_dev_dbg(hdev, "chan %p", chan);
@@ -3135,14 +3142,7 @@ static void bredr_pairing(struct l2cap_chan *chan)
bt_dev_dbg(hdev, "starting SMP over BR/EDR");
- /* Prepare and send the BR/EDR SMP Pairing Request */
- build_bredr_pairing_cmd(smp, &req, NULL);
-
- smp->preq[0] = SMP_CMD_PAIRING_REQ;
- memcpy(&smp->preq[1], &req, sizeof(req));
-
- smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(req), &req);
- SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP);
+ smp_send_pairing_req(smp, 0x00);
}
static void smp_resume_cb(struct l2cap_chan *chan)
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 09f6a77..8f9c19d 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -622,8 +622,12 @@ static unsigned int br_nf_local_in(void *priv,
if (likely(nf_ct_is_confirmed(ct)))
return NF_ACCEPT;
+ if (WARN_ON_ONCE(refcount_read(&nfct->use) != 1)) {
+ nf_reset_ct(skb);
+ return NF_ACCEPT;
+ }
+
WARN_ON_ONCE(skb_shared(skb));
- WARN_ON_ONCE(refcount_read(&nfct->use) != 1);
/* We can't call nf_confirm here, it would create a dependency
* on nf_conntrack module.
diff --git a/net/core/dev.c b/net/core/dev.c
index 751d9b7..f66e614 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9912,6 +9912,15 @@ static void netdev_sync_lower_features(struct net_device *upper,
}
}
+static bool netdev_has_ip_or_hw_csum(netdev_features_t features)
+{
+ netdev_features_t ip_csum_mask = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+ bool ip_csum = (features & ip_csum_mask) == ip_csum_mask;
+ bool hw_csum = features & NETIF_F_HW_CSUM;
+
+ return ip_csum || hw_csum;
+}
+
static netdev_features_t netdev_fix_features(struct net_device *dev,
netdev_features_t features)
{
@@ -9993,15 +10002,9 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
features &= ~NETIF_F_LRO;
}
- if (features & NETIF_F_HW_TLS_TX) {
- bool ip_csum = (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) ==
- (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
- bool hw_csum = features & NETIF_F_HW_CSUM;
-
- if (!ip_csum && !hw_csum) {
- netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
- features &= ~NETIF_F_HW_TLS_TX;
- }
+ if ((features & NETIF_F_HW_TLS_TX) && !netdev_has_ip_or_hw_csum(features)) {
+ netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
+ features &= ~NETIF_F_HW_TLS_TX;
}
if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) {
@@ -10009,6 +10012,11 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
features &= ~NETIF_F_HW_TLS_RX;
}
+ if ((features & NETIF_F_GSO_UDP_L4) && !netdev_has_ip_or_hw_csum(features)) {
+ netdev_dbg(dev, "Dropping USO feature since no CSUM feature.\n");
+ features &= ~NETIF_F_GSO_UDP_L4;
+ }
+
return features;
}
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 0e2084c..444f23e 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -235,7 +235,7 @@ static ssize_t speed_show(struct device *dev,
if (!rtnl_trylock())
return restart_syscall();
- if (netif_running(netdev) && netif_device_present(netdev)) {
+ if (netif_running(netdev)) {
struct ethtool_link_ksettings cmd;
if (!__ethtool_get_link_ksettings(netdev, &cmd))
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 55bcacf..d657b04 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -228,7 +228,6 @@ void netpoll_poll_disable(struct net_device *dev)
down(&ni->dev_lock);
srcu_read_unlock(&netpoll_srcu, idx);
}
-EXPORT_SYMBOL(netpoll_poll_disable);
void netpoll_poll_enable(struct net_device *dev)
{
@@ -239,7 +238,6 @@ void netpoll_poll_enable(struct net_device *dev)
up(&ni->dev_lock);
rcu_read_unlock();
}
-EXPORT_SYMBOL(netpoll_poll_enable);
static void refill_skbs(void)
{
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index ea55a75..197a50e 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3654,7 +3654,7 @@ static int pktgen_thread_worker(void *arg)
struct pktgen_dev *pkt_dev = NULL;
int cpu = t->cpu;
- WARN_ON(smp_processor_id() != cpu);
+ WARN_ON_ONCE(smp_processor_id() != cpu);
init_waitqueue_head(&t->queue);
complete(&t->start_done);
@@ -3989,6 +3989,7 @@ static int __net_init pg_net_init(struct net *net)
goto remove;
}
+ cpus_read_lock();
for_each_online_cpu(cpu) {
int err;
@@ -3997,6 +3998,7 @@ static int __net_init pg_net_init(struct net *net)
pr_warn("Cannot create thread for cpu %d (%d)\n",
cpu, err);
}
+ cpus_read_unlock();
if (list_empty(&pn->pktgen_threads)) {
pr_err("Initialization failed for all threads\n");
diff --git a/net/dsa/tag.c b/net/dsa/tag.c
index 6e402d4..79ad105 100644
--- a/net/dsa/tag.c
+++ b/net/dsa/tag.c
@@ -105,8 +105,9 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
p = netdev_priv(skb->dev);
- if (unlikely(cpu_dp->ds->untag_bridge_pvid)) {
- nskb = dsa_untag_bridge_pvid(skb);
+ if (unlikely(cpu_dp->ds->untag_bridge_pvid ||
+ cpu_dp->ds->untag_vlan_aware_bridge_pvid)) {
+ nskb = dsa_software_vlan_untag(skb);
if (!nskb) {
kfree_skb(skb);
return 0;
diff --git a/net/dsa/tag.h b/net/dsa/tag.h
index f6b9c73..d570787 100644
--- a/net/dsa/tag.h
+++ b/net/dsa/tag.h
@@ -44,46 +44,81 @@ static inline struct net_device *dsa_conduit_find_user(struct net_device *dev,
return NULL;
}
-/* If under a bridge with vlan_filtering=0, make sure to send pvid-tagged
- * frames as untagged, since the bridge will not untag them.
+/**
+ * dsa_software_untag_vlan_aware_bridge: Software untagging for VLAN-aware bridge
+ * @skb: Pointer to received socket buffer (packet)
+ * @br: Pointer to bridge upper interface of ingress port
+ * @vid: Parsed VID from packet
+ *
+ * The bridge can process tagged packets. Software like STP/PTP may not. The
+ * bridge can also process untagged packets, to the same effect as if they were
+ * tagged with the PVID of the ingress port. So packets tagged with the PVID of
+ * the bridge port must be software-untagged, to support both use cases.
*/
-static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb)
+static inline void dsa_software_untag_vlan_aware_bridge(struct sk_buff *skb,
+ struct net_device *br,
+ u16 vid)
{
- struct dsa_port *dp = dsa_user_to_port(skb->dev);
- struct net_device *br = dsa_port_bridge_dev_get(dp);
- struct net_device *dev = skb->dev;
- struct net_device *upper_dev;
- u16 vid, pvid, proto;
+ u16 pvid, proto;
int err;
- if (!br || br_vlan_enabled(br))
- return skb;
-
err = br_vlan_get_proto(br, &proto);
if (err)
- return skb;
+ return;
- /* Move VLAN tag from data to hwaccel */
- if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) {
- skb = skb_vlan_untag(skb);
- if (!skb)
- return NULL;
- }
-
- if (!skb_vlan_tag_present(skb))
- return skb;
-
- vid = skb_vlan_tag_get_id(skb);
-
- /* We already run under an RCU read-side critical section since
- * we are called from netif_receive_skb_list_internal().
- */
- err = br_vlan_get_pvid_rcu(dev, &pvid);
+ err = br_vlan_get_pvid_rcu(skb->dev, &pvid);
if (err)
- return skb;
+ return;
- if (vid != pvid)
- return skb;
+ if (vid == pvid && skb->vlan_proto == htons(proto))
+ __vlan_hwaccel_clear_tag(skb);
+}
+
+/**
+ * dsa_software_untag_vlan_unaware_bridge: Software untagging for VLAN-unaware bridge
+ * @skb: Pointer to received socket buffer (packet)
+ * @br: Pointer to bridge upper interface of ingress port
+ * @vid: Parsed VID from packet
+ *
+ * The bridge ignores all VLAN tags. Software like STP/PTP may not (it may run
+ * on the plain port, or on a VLAN upper interface). Maybe packets are coming
+ * to software as tagged with a driver-defined VID which is NOT equal to the
+ * PVID of the bridge port (since the bridge is VLAN-unaware, its configuration
+ * should NOT be committed to hardware). DSA needs a method for this private
+ * VID to be communicated by software to it, and if packets are tagged with it,
+ * software-untag them. Note: the private VID may be different per bridge, to
+ * support the FDB isolation use case.
+ *
+ * FIXME: this is currently implemented based on the broken assumption that
+ * the "private VID" used by the driver in VLAN-unaware mode is equal to the
+ * bridge PVID. It should not be, except for a coincidence; the bridge PVID is
+ * irrelevant to the data path in the VLAN-unaware mode. Thus, the VID that
+ * this function removes is wrong.
+ *
+ * All users of ds->untag_bridge_pvid should fix their drivers, if necessary,
+ * to make the two independent. Only then, if there still remains a need to
+ * strip the private VID from packets, then a new ds->ops->get_private_vid()
+ * API shall be introduced to communicate to DSA what this VID is, which needs
+ * to be stripped here.
+ */
+static inline void dsa_software_untag_vlan_unaware_bridge(struct sk_buff *skb,
+ struct net_device *br,
+ u16 vid)
+{
+ struct net_device *upper_dev;
+ u16 pvid, proto;
+ int err;
+
+ err = br_vlan_get_proto(br, &proto);
+ if (err)
+ return;
+
+ err = br_vlan_get_pvid_rcu(skb->dev, &pvid);
+ if (err)
+ return;
+
+ if (vid != pvid || skb->vlan_proto != htons(proto))
+ return;
/* The sad part about attempting to untag from DSA is that we
* don't know, unless we check, if the skb will end up in
@@ -95,10 +130,50 @@ static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb)
* definitely keep the tag, to make sure it keeps working.
*/
upper_dev = __vlan_find_dev_deep_rcu(br, htons(proto), vid);
- if (upper_dev)
+ if (!upper_dev)
+ __vlan_hwaccel_clear_tag(skb);
+}
+
+/**
+ * dsa_software_vlan_untag: Software VLAN untagging in DSA receive path
+ * @skb: Pointer to socket buffer (packet)
+ *
+ * Receive path method for switches which cannot avoid tagging all packets
+ * towards the CPU port. Called when ds->untag_bridge_pvid (legacy) or
+ * ds->untag_vlan_aware_bridge_pvid is set to true.
+ *
+ * As a side effect of this method, any VLAN tag from the skb head is moved
+ * to hwaccel.
+ */
+static inline struct sk_buff *dsa_software_vlan_untag(struct sk_buff *skb)
+{
+ struct dsa_port *dp = dsa_user_to_port(skb->dev);
+ struct net_device *br = dsa_port_bridge_dev_get(dp);
+ u16 vid;
+
+ /* software untagging for standalone ports not yet necessary */
+ if (!br)
return skb;
- __vlan_hwaccel_clear_tag(skb);
+ /* Move VLAN tag from data to hwaccel */
+ if (!skb_vlan_tag_present(skb)) {
+ skb = skb_vlan_untag(skb);
+ if (!skb)
+ return NULL;
+ }
+
+ if (!skb_vlan_tag_present(skb))
+ return skb;
+
+ vid = skb_vlan_tag_get_id(skb);
+
+ if (br_vlan_enabled(br)) {
+ if (dp->ds->untag_vlan_aware_bridge_pvid)
+ dsa_software_untag_vlan_aware_bridge(skb, br, vid);
+ } else {
+ if (dp->ds->untag_bridge_pvid)
+ dsa_software_untag_vlan_unaware_bridge(skb, br, vid);
+ }
return skb;
}
diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c
index e0e4300..bf6608f 100644
--- a/net/dsa/tag_ocelot.c
+++ b/net/dsa/tag_ocelot.c
@@ -8,40 +8,6 @@
#define OCELOT_NAME "ocelot"
#define SEVILLE_NAME "seville"
-/* If the port is under a VLAN-aware bridge, remove the VLAN header from the
- * payload and move it into the DSA tag, which will make the switch classify
- * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero,
- * which is the pvid of standalone and VLAN-unaware bridge ports.
- */
-static void ocelot_xmit_get_vlan_info(struct sk_buff *skb, struct dsa_port *dp,
- u64 *vlan_tci, u64 *tag_type)
-{
- struct net_device *br = dsa_port_bridge_dev_get(dp);
- struct vlan_ethhdr *hdr;
- u16 proto, tci;
-
- if (!br || !br_vlan_enabled(br)) {
- *vlan_tci = 0;
- *tag_type = IFH_TAG_TYPE_C;
- return;
- }
-
- hdr = skb_vlan_eth_hdr(skb);
- br_vlan_get_proto(br, &proto);
-
- if (ntohs(hdr->h_vlan_proto) == proto) {
- vlan_remove_tag(skb, &tci);
- *vlan_tci = tci;
- } else {
- rcu_read_lock();
- br_vlan_get_pvid_rcu(br, &tci);
- rcu_read_unlock();
- *vlan_tci = tci;
- }
-
- *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C;
-}
-
static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev,
__be32 ifh_prefix, void **ifh)
{
@@ -53,7 +19,8 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev,
u32 rew_op = 0;
u64 qos_class;
- ocelot_xmit_get_vlan_info(skb, dp, &vlan_tci, &tag_type);
+ ocelot_xmit_get_vlan_info(skb, dsa_port_bridge_dev_get(dp), &vlan_tci,
+ &tag_type);
qos_class = netdev_get_num_tc(netdev) ?
netdev_get_prio_tc_map(netdev, skb->priority) : skb->priority;
diff --git a/net/ethtool/cmis_fw_update.c b/net/ethtool/cmis_fw_update.c
index ae4b4b2..655ff52 100644
--- a/net/ethtool/cmis_fw_update.c
+++ b/net/ethtool/cmis_fw_update.c
@@ -35,7 +35,10 @@ struct cmis_cdb_fw_mng_features_rpl {
__be16 resv7;
};
-#define CMIS_CDB_FW_WRITE_MECHANISM_LPL 0x01
+enum cmis_cdb_fw_write_mechanism {
+ CMIS_CDB_FW_WRITE_MECHANISM_LPL = 0x01,
+ CMIS_CDB_FW_WRITE_MECHANISM_BOTH = 0x11,
+};
static int
cmis_fw_update_fw_mng_features_get(struct ethtool_cmis_cdb *cdb,
@@ -64,7 +67,8 @@ cmis_fw_update_fw_mng_features_get(struct ethtool_cmis_cdb *cdb,
}
rpl = (struct cmis_cdb_fw_mng_features_rpl *)args.req.payload;
- if (!(rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_LPL)) {
+ if (!(rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_LPL ||
+ rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_BOTH)) {
ethnl_module_fw_flash_ntf_err(dev, ntf_params,
"Write LPL is not supported",
NULL);
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index e18823b..ae041f5 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -442,6 +442,9 @@ int __ethtool_get_link_ksettings(struct net_device *dev,
if (!dev->ethtool_ops->get_link_ksettings)
return -EOPNOTSUPP;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+
memset(link_ksettings, 0, sizeof(*link_ksettings));
return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings);
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e03a342..831a18d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -4637,6 +4637,13 @@ int tcp_abort(struct sock *sk, int err)
/* Don't race with userspace socket closes such as tcp_close. */
lock_sock(sk);
+ /* Avoid closing the same socket twice. */
+ if (sk->sk_state == TCP_CLOSE) {
+ if (!has_current_bpf_ctx())
+ release_sock(sk);
+ return -ENOENT;
+ }
+
if (sk->sk_state == TCP_LISTEN) {
tcp_set_state(sk, TCP_CLOSE);
inet_csk_listen_stop(sk);
@@ -4646,16 +4653,13 @@ int tcp_abort(struct sock *sk, int err)
local_bh_disable();
bh_lock_sock(sk);
- if (!sock_flag(sk, SOCK_DEAD)) {
- if (tcp_need_reset(sk->sk_state))
- tcp_send_active_reset(sk, GFP_ATOMIC,
- SK_RST_REASON_NOT_SPECIFIED);
- tcp_done_with_error(sk, err);
- }
+ if (tcp_need_reset(sk->sk_state))
+ tcp_send_active_reset(sk, GFP_ATOMIC,
+ SK_RST_REASON_NOT_SPECIFIED);
+ tcp_done_with_error(sk, err);
bh_unlock_sock(sk);
local_bh_enable();
- tcp_write_queue_purge(sk);
if (!has_current_bpf_ctx())
release_sock(sk);
return 0;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e2b9583..e37488d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -238,9 +238,14 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
*/
if (unlikely(len != icsk->icsk_ack.rcv_mss)) {
u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE;
+ u8 old_ratio = tcp_sk(sk)->scaling_ratio;
do_div(val, skb->truesize);
tcp_sk(sk)->scaling_ratio = val ? val : 1;
+
+ if (old_ratio != tcp_sk(sk)->scaling_ratio)
+ WRITE_ONCE(tcp_sk(sk)->window_clamp,
+ tcp_win_from_space(sk, sk->sk_rcvbuf));
}
icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
tcp_sk(sk)->advmss);
@@ -754,7 +759,8 @@ void tcp_rcv_space_adjust(struct sock *sk)
* <prev RTT . ><current RTT .. ><next RTT .... >
*/
- if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)) {
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
+ !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
u64 rcvwin, grow;
int rcvbuf;
@@ -770,22 +776,12 @@ void tcp_rcv_space_adjust(struct sock *sk)
rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin),
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
- if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
- if (rcvbuf > sk->sk_rcvbuf) {
- WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
+ if (rcvbuf > sk->sk_rcvbuf) {
+ WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
- /* Make the window clamp follow along. */
- WRITE_ONCE(tp->window_clamp,
- tcp_win_from_space(sk, rcvbuf));
- }
- } else {
- /* Make the window clamp follow along while being bounded
- * by SO_RCVBUF.
- */
- int clamp = tcp_win_from_space(sk, min(rcvbuf, sk->sk_rcvbuf));
-
- if (clamp > tp->window_clamp)
- WRITE_ONCE(tp->window_clamp, clamp);
+ /* Make the window clamp follow along. */
+ WRITE_ONCE(tp->window_clamp,
+ tcp_win_from_space(sk, rcvbuf));
}
}
tp->rcvq_space.space = copied;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fd17f25f..a4e5108 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -97,6 +97,8 @@ static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = {
.bh_lock = INIT_LOCAL_LOCK(bh_lock),
};
+static DEFINE_MUTEX(tcp_exit_batch_mutex);
+
static u32 tcp_v4_init_seq(const struct sk_buff *skb)
{
return secure_tcp_seq(ip_hdr(skb)->daddr,
@@ -3514,6 +3516,16 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
{
struct net *net;
+ /* make sure concurrent calls to tcp_sk_exit_batch from net_cleanup_work
+ * and failed setup_net error unwinding path are serialized.
+ *
+ * tcp_twsk_purge() handles twsk in any dead netns, not just those in
+ * net_exit_list, the thread that dismantles a particular twsk must
+ * do so without other thread progressing to refcount_dec_and_test() of
+ * tcp_death_row.tw_refcount.
+ */
+ mutex_lock(&tcp_exit_batch_mutex);
+
tcp_twsk_purge(net_exit_list);
list_for_each_entry(net, net_exit_list, exit_list) {
@@ -3521,6 +3533,8 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount));
tcp_fastopen_ctx_destroy(net);
}
+
+ mutex_unlock(&tcp_exit_batch_mutex);
}
static struct pernet_operations __net_initdata tcp_sk_ops = {
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index bc8a9da..d842303 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -279,9 +279,16 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
return ERR_PTR(-EINVAL);
if (unlikely(skb_checksum_start(gso_skb) !=
- skb_transport_header(gso_skb)))
+ skb_transport_header(gso_skb) &&
+ !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST)))
return ERR_PTR(-EINVAL);
+ /* We don't know if egress device can segment and checksum the packet
+ * when IPv6 extension headers are present. Fall back to software GSO.
+ */
+ if (gso_skb->ip_summed != CHECKSUM_PARTIAL)
+ features &= ~(NETIF_F_GSO_UDP_L4 | NETIF_F_CSUM_MASK);
+
if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) {
/* Packet is from an untrusted source, reset gso_segs. */
skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh),
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ab504d3..f26841f 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -70,11 +70,15 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
/* Be paranoid, rather than too clever. */
if (unlikely(hh_len > skb_headroom(skb)) && dev->header_ops) {
+ /* Make sure idev stays alive */
+ rcu_read_lock();
skb = skb_expand_head(skb, hh_len);
if (!skb) {
IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+ rcu_read_unlock();
return -ENOMEM;
}
+ rcu_read_unlock();
}
hdr = ipv6_hdr(skb);
@@ -283,11 +287,15 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
head_room += opt->opt_nflen + opt->opt_flen;
if (unlikely(head_room > skb_headroom(skb))) {
+ /* Make sure idev stays alive */
+ rcu_read_lock();
skb = skb_expand_head(skb, head_room);
if (!skb) {
IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+ rcu_read_unlock();
return -ENOBUFS;
}
+ rcu_read_unlock();
}
if (opt) {
@@ -1956,6 +1964,7 @@ int ip6_send_skb(struct sk_buff *skb)
struct rt6_info *rt = dst_rt6_info(skb_dst(skb));
int err;
+ rcu_read_lock();
err = ip6_local_out(net, skb->sk, skb);
if (err) {
if (err > 0)
@@ -1965,6 +1974,7 @@ int ip6_send_skb(struct sk_buff *skb)
IPSTATS_MIB_OUTDISCARDS);
}
+ rcu_read_unlock();
return err;
}
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 9dee0c1..87dfb56 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1507,7 +1507,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
tdev = __dev_get_by_index(t->net, p->link);
if (tdev) {
- dev->hard_header_len = tdev->hard_header_len + t_hlen;
+ dev->needed_headroom = tdev->hard_header_len +
+ tdev->needed_headroom + t_hlen;
mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU);
mtu = mtu - t_hlen;
@@ -1731,7 +1732,9 @@ ip6_tnl_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
{
struct ip6_tnl *tnl = netdev_priv(dev);
+ int t_hlen;
+ t_hlen = tnl->hlen + sizeof(struct ipv6hdr);
if (tnl->parms.proto == IPPROTO_IPV6) {
if (new_mtu < IPV6_MIN_MTU)
return -EINVAL;
@@ -1740,10 +1743,10 @@ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
return -EINVAL;
}
if (tnl->parms.proto == IPPROTO_IPV6 || tnl->parms.proto == 0) {
- if (new_mtu > IP6_MAX_MTU - dev->hard_header_len)
+ if (new_mtu > IP6_MAX_MTU - dev->hard_header_len - t_hlen)
return -EINVAL;
} else {
- if (new_mtu > IP_MAX_MTU - dev->hard_header_len)
+ if (new_mtu > IP_MAX_MTU - dev->hard_header_len - t_hlen)
return -EINVAL;
}
WRITE_ONCE(dev->mtu, new_mtu);
@@ -1887,12 +1890,11 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
t_hlen = t->hlen + sizeof(struct ipv6hdr);
dev->type = ARPHRD_TUNNEL6;
- dev->hard_header_len = LL_MAX_HEADER + t_hlen;
dev->mtu = ETH_DATA_LEN - t_hlen;
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
dev->mtu -= 8;
dev->min_mtu = ETH_MIN_MTU;
- dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len;
+ dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len - t_hlen;
netdev_hold(dev, &t->dev_tracker, GFP_KERNEL);
netdev_lockdep_set_classes(dev);
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 6f0844c..4120e67 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -154,6 +154,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
};
struct inet_frag_queue *q;
+ if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
+ IPV6_ADDR_LINKLOCAL)))
+ key.iif = 0;
+
q = inet_frag_find(nf_frag->fqdir, &key);
if (!q)
return NULL;
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index 1e42e13..d3e9efa 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -86,13 +86,15 @@ struct device *iucv_alloc_device(const struct attribute_group **attrs,
{
struct device *dev;
va_list vargs;
+ char buf[20];
int rc;
dev = kzalloc(sizeof(*dev), GFP_KERNEL);
if (!dev)
goto out_error;
va_start(vargs, fmt);
- rc = dev_set_name(dev, fmt, vargs);
+ vsnprintf(buf, sizeof(buf), fmt, vargs);
+ rc = dev_set_name(dev, "%s", buf);
va_end(vargs);
if (rc)
goto out_error;
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 2f191e5..d4118c7 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -755,6 +755,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
!(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR);
int err = -EPIPE;
+ mutex_lock(&kcm->tx_mutex);
lock_sock(sk);
/* Per tcp_sendmsg this should be in poll */
@@ -926,6 +927,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
KCM_STATS_ADD(kcm->stats.tx_bytes, copied);
release_sock(sk);
+ mutex_unlock(&kcm->tx_mutex);
return copied;
out_error:
@@ -951,6 +953,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
sk->sk_write_space(sk);
release_sock(sk);
+ mutex_unlock(&kcm->tx_mutex);
return err;
}
@@ -1204,6 +1207,7 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux)
spin_unlock_bh(&mux->lock);
INIT_WORK(&kcm->tx_work, kcm_tx_work);
+ mutex_init(&kcm->tx_mutex);
spin_lock_bh(&mux->rx_lock);
kcm_rcv_ready(kcm);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 4779a18..f9526bb 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -6664,7 +6664,7 @@ static bool ieee80211_mgd_ssid_mismatch(struct ieee80211_sub_if_data *sdata,
return true;
/* hidden SSID: zeroed out */
- if (memcmp(elems->ssid, zero_ssid, elems->ssid_len))
+ if (!memcmp(elems->ssid, zero_ssid, elems->ssid_len))
return false;
return memcmp(elems->ssid, cfg->ssid, cfg->ssid_len);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index edba4a3..bca7b34 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -5348,8 +5348,10 @@ ieee80211_beacon_get_ap(struct ieee80211_hw *hw,
if (beacon->tail)
skb_put_data(skb, beacon->tail, beacon->tail_len);
- if (ieee80211_beacon_protect(skb, local, sdata, link) < 0)
+ if (ieee80211_beacon_protect(skb, local, sdata, link) < 0) {
+ dev_kfree_skb(skb);
return NULL;
+ }
ieee80211_beacon_get_finish(hw, vif, link, offs, beacon, skb,
chanctx_conf, csa_off_base);
diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c
index 77e5dd4..8551dab 100644
--- a/net/mctp/test/route-test.c
+++ b/net/mctp/test/route-test.c
@@ -366,7 +366,7 @@ static void mctp_test_route_input_sk(struct kunit *test)
skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2);
- KUNIT_EXPECT_EQ(test, skb->len, 1);
+ KUNIT_EXPECT_EQ(test, skb2->len, 1);
skb_free_datagram(sock->sk, skb2);
diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c
index 3ae46b5..2d3efb4 100644
--- a/net/mptcp/diag.c
+++ b/net/mptcp/diag.c
@@ -94,7 +94,7 @@ static size_t subflow_get_info_size(const struct sock *sk)
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */
nla_total_size_64bit(8) + /* MPTCP_SUBFLOW_ATTR_MAP_SEQ */
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */
- nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */
+ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */
nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_FLAGS */
nla_total_size(1) + /* MPTCP_SUBFLOW_ATTR_ID_REM */
diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
index ad28da6..a29ff90 100644
--- a/net/mptcp/fastopen.c
+++ b/net/mptcp/fastopen.c
@@ -68,12 +68,12 @@ void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflo
skb = skb_peek_tail(&sk->sk_receive_queue);
if (skb) {
WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq);
- pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx", sk,
+ pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx\n", sk,
MPTCP_SKB_CB(skb)->map_seq, MPTCP_SKB_CB(skb)->map_seq + msk->ack_seq,
MPTCP_SKB_CB(skb)->end_seq, MPTCP_SKB_CB(skb)->end_seq + msk->ack_seq);
MPTCP_SKB_CB(skb)->map_seq += msk->ack_seq;
MPTCP_SKB_CB(skb)->end_seq += msk->ack_seq;
}
- pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq);
+ pr_debug("msk=%p ack_seq=%llx\n", msk, msk->ack_seq);
}
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index ac2f1a5..370c383 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -117,7 +117,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD;
ptr += 2;
}
- pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u",
+ pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u\n",
version, flags, opsize, mp_opt->sndr_key,
mp_opt->rcvr_key, mp_opt->data_len, mp_opt->csum);
break;
@@ -131,7 +131,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
ptr += 4;
mp_opt->nonce = get_unaligned_be32(ptr);
ptr += 4;
- pr_debug("MP_JOIN bkup=%u, id=%u, token=%u, nonce=%u",
+ pr_debug("MP_JOIN bkup=%u, id=%u, token=%u, nonce=%u\n",
mp_opt->backup, mp_opt->join_id,
mp_opt->token, mp_opt->nonce);
} else if (opsize == TCPOLEN_MPTCP_MPJ_SYNACK) {
@@ -142,19 +142,19 @@ static void mptcp_parse_option(const struct sk_buff *skb,
ptr += 8;
mp_opt->nonce = get_unaligned_be32(ptr);
ptr += 4;
- pr_debug("MP_JOIN bkup=%u, id=%u, thmac=%llu, nonce=%u",
+ pr_debug("MP_JOIN bkup=%u, id=%u, thmac=%llu, nonce=%u\n",
mp_opt->backup, mp_opt->join_id,
mp_opt->thmac, mp_opt->nonce);
} else if (opsize == TCPOLEN_MPTCP_MPJ_ACK) {
mp_opt->suboptions |= OPTION_MPTCP_MPJ_ACK;
ptr += 2;
memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN);
- pr_debug("MP_JOIN hmac");
+ pr_debug("MP_JOIN hmac\n");
}
break;
case MPTCPOPT_DSS:
- pr_debug("DSS");
+ pr_debug("DSS\n");
ptr++;
/* we must clear 'mpc_map' be able to detect MP_CAPABLE
@@ -169,7 +169,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
mp_opt->ack64 = (flags & MPTCP_DSS_ACK64) != 0;
mp_opt->use_ack = (flags & MPTCP_DSS_HAS_ACK);
- pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d",
+ pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d\n",
mp_opt->data_fin, mp_opt->dsn64,
mp_opt->use_map, mp_opt->ack64,
mp_opt->use_ack);
@@ -207,7 +207,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
ptr += 4;
}
- pr_debug("data_ack=%llu", mp_opt->data_ack);
+ pr_debug("data_ack=%llu\n", mp_opt->data_ack);
}
if (mp_opt->use_map) {
@@ -231,7 +231,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
ptr += 2;
}
- pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u",
+ pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u\n",
mp_opt->data_seq, mp_opt->subflow_seq,
mp_opt->data_len, !!(mp_opt->suboptions & OPTION_MPTCP_CSUMREQD),
mp_opt->csum);
@@ -293,7 +293,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
mp_opt->ahmac = get_unaligned_be64(ptr);
ptr += 8;
}
- pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d",
+ pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d\n",
(mp_opt->addr.family == AF_INET6) ? "6" : "",
mp_opt->addr.id, mp_opt->ahmac, mp_opt->echo, ntohs(mp_opt->addr.port));
break;
@@ -309,7 +309,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
mp_opt->rm_list.nr = opsize - TCPOLEN_MPTCP_RM_ADDR_BASE;
for (i = 0; i < mp_opt->rm_list.nr; i++)
mp_opt->rm_list.ids[i] = *ptr++;
- pr_debug("RM_ADDR: rm_list_nr=%d", mp_opt->rm_list.nr);
+ pr_debug("RM_ADDR: rm_list_nr=%d\n", mp_opt->rm_list.nr);
break;
case MPTCPOPT_MP_PRIO:
@@ -318,7 +318,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
mp_opt->suboptions |= OPTION_MPTCP_PRIO;
mp_opt->backup = *ptr++ & MPTCP_PRIO_BKUP;
- pr_debug("MP_PRIO: prio=%d", mp_opt->backup);
+ pr_debug("MP_PRIO: prio=%d\n", mp_opt->backup);
break;
case MPTCPOPT_MP_FASTCLOSE:
@@ -329,7 +329,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
mp_opt->rcvr_key = get_unaligned_be64(ptr);
ptr += 8;
mp_opt->suboptions |= OPTION_MPTCP_FASTCLOSE;
- pr_debug("MP_FASTCLOSE: recv_key=%llu", mp_opt->rcvr_key);
+ pr_debug("MP_FASTCLOSE: recv_key=%llu\n", mp_opt->rcvr_key);
break;
case MPTCPOPT_RST:
@@ -343,7 +343,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
flags = *ptr++;
mp_opt->reset_transient = flags & MPTCP_RST_TRANSIENT;
mp_opt->reset_reason = *ptr;
- pr_debug("MP_RST: transient=%u reason=%u",
+ pr_debug("MP_RST: transient=%u reason=%u\n",
mp_opt->reset_transient, mp_opt->reset_reason);
break;
@@ -354,7 +354,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
ptr += 2;
mp_opt->suboptions |= OPTION_MPTCP_FAIL;
mp_opt->fail_seq = get_unaligned_be64(ptr);
- pr_debug("MP_FAIL: data_seq=%llu", mp_opt->fail_seq);
+ pr_debug("MP_FAIL: data_seq=%llu\n", mp_opt->fail_seq);
break;
default:
@@ -417,7 +417,7 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
*size = TCPOLEN_MPTCP_MPC_SYN;
return true;
} else if (subflow->request_join) {
- pr_debug("remote_token=%u, nonce=%u", subflow->remote_token,
+ pr_debug("remote_token=%u, nonce=%u\n", subflow->remote_token,
subflow->local_nonce);
opts->suboptions = OPTION_MPTCP_MPJ_SYN;
opts->join_id = subflow->local_id;
@@ -500,7 +500,7 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
*size = TCPOLEN_MPTCP_MPC_ACK;
}
- pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d",
+ pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d\n",
subflow, subflow->local_key, subflow->remote_key,
data_len);
@@ -509,7 +509,7 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
opts->suboptions = OPTION_MPTCP_MPJ_ACK;
memcpy(opts->hmac, subflow->hmac, MPTCPOPT_HMAC_LEN);
*size = TCPOLEN_MPTCP_MPJ_ACK;
- pr_debug("subflow=%p", subflow);
+ pr_debug("subflow=%p\n", subflow);
/* we can use the full delegate action helper only from BH context
* If we are in process context - sk is flushing the backlog at
@@ -675,7 +675,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
*size = len;
if (drop_other_suboptions) {
- pr_debug("drop other suboptions");
+ pr_debug("drop other suboptions\n");
opts->suboptions = 0;
/* note that e.g. DSS could have written into the memory
@@ -695,7 +695,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
} else {
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX);
}
- pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d",
+ pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d\n",
opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port));
return true;
@@ -726,7 +726,7 @@ static bool mptcp_established_options_rm_addr(struct sock *sk,
opts->rm_list = rm_list;
for (i = 0; i < opts->rm_list.nr; i++)
- pr_debug("rm_list_ids[%d]=%d", i, opts->rm_list.ids[i]);
+ pr_debug("rm_list_ids[%d]=%d\n", i, opts->rm_list.ids[i]);
MPTCP_ADD_STATS(sock_net(sk), MPTCP_MIB_RMADDRTX, opts->rm_list.nr);
return true;
}
@@ -752,7 +752,7 @@ static bool mptcp_established_options_mp_prio(struct sock *sk,
opts->suboptions |= OPTION_MPTCP_PRIO;
opts->backup = subflow->request_bkup;
- pr_debug("prio=%d", opts->backup);
+ pr_debug("prio=%d\n", opts->backup);
return true;
}
@@ -794,7 +794,7 @@ static bool mptcp_established_options_fastclose(struct sock *sk,
opts->suboptions |= OPTION_MPTCP_FASTCLOSE;
opts->rcvr_key = READ_ONCE(msk->remote_key);
- pr_debug("FASTCLOSE key=%llu", opts->rcvr_key);
+ pr_debug("FASTCLOSE key=%llu\n", opts->rcvr_key);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX);
return true;
}
@@ -816,7 +816,7 @@ static bool mptcp_established_options_mp_fail(struct sock *sk,
opts->suboptions |= OPTION_MPTCP_FAIL;
opts->fail_seq = subflow->map_seq;
- pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq);
+ pr_debug("MP_FAIL fail_seq=%llu\n", opts->fail_seq);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX);
return true;
@@ -904,7 +904,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
opts->csum_reqd = subflow_req->csum_reqd;
opts->allow_join_id0 = subflow_req->allow_join_id0;
*size = TCPOLEN_MPTCP_MPC_SYNACK;
- pr_debug("subflow_req=%p, local_key=%llu",
+ pr_debug("subflow_req=%p, local_key=%llu\n",
subflow_req, subflow_req->local_key);
return true;
} else if (subflow_req->mp_join) {
@@ -913,7 +913,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
opts->join_id = subflow_req->local_id;
opts->thmac = subflow_req->thmac;
opts->nonce = subflow_req->local_nonce;
- pr_debug("req=%p, bkup=%u, id=%u, thmac=%llu, nonce=%u",
+ pr_debug("req=%p, bkup=%u, id=%u, thmac=%llu, nonce=%u\n",
subflow_req, opts->backup, opts->join_id,
opts->thmac, opts->nonce);
*size = TCPOLEN_MPTCP_MPJ_SYNACK;
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 23bb89c..37f6dbc 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -19,7 +19,7 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk,
{
u8 add_addr = READ_ONCE(msk->pm.addr_signal);
- pr_debug("msk=%p, local_id=%d, echo=%d", msk, addr->id, echo);
+ pr_debug("msk=%p, local_id=%d, echo=%d\n", msk, addr->id, echo);
lockdep_assert_held(&msk->pm.lock);
@@ -45,7 +45,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
{
u8 rm_addr = READ_ONCE(msk->pm.addr_signal);
- pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr);
+ pr_debug("msk=%p, rm_list_nr=%d\n", msk, rm_list->nr);
if (rm_addr) {
MPTCP_ADD_STATS(sock_net((struct sock *)msk),
@@ -60,23 +60,13 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
return 0;
}
-int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list)
-{
- pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr);
-
- spin_lock_bh(&msk->pm.lock);
- mptcp_pm_nl_rm_subflow_received(msk, rm_list);
- spin_unlock_bh(&msk->pm.lock);
- return 0;
-}
-
/* path manager event handlers */
void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side)
{
struct mptcp_pm_data *pm = &msk->pm;
- pr_debug("msk=%p, token=%u side=%d", msk, READ_ONCE(msk->token), server_side);
+ pr_debug("msk=%p, token=%u side=%d\n", msk, READ_ONCE(msk->token), server_side);
WRITE_ONCE(pm->server_side, server_side);
mptcp_event(MPTCP_EVENT_CREATED, msk, ssk, GFP_ATOMIC);
@@ -100,7 +90,7 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk)
subflows_max = mptcp_pm_get_subflows_max(msk);
- pr_debug("msk=%p subflows=%d max=%d allow=%d", msk, pm->subflows,
+ pr_debug("msk=%p subflows=%d max=%d allow=%d\n", msk, pm->subflows,
subflows_max, READ_ONCE(pm->accept_subflow));
/* try to avoid acquiring the lock below */
@@ -124,7 +114,7 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk)
static bool mptcp_pm_schedule_work(struct mptcp_sock *msk,
enum mptcp_pm_status new_status)
{
- pr_debug("msk=%p status=%x new=%lx", msk, msk->pm.status,
+ pr_debug("msk=%p status=%x new=%lx\n", msk, msk->pm.status,
BIT(new_status));
if (msk->pm.status & BIT(new_status))
return false;
@@ -139,7 +129,7 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk)
struct mptcp_pm_data *pm = &msk->pm;
bool announce = false;
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
spin_lock_bh(&pm->lock);
@@ -163,14 +153,14 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk)
void mptcp_pm_connection_closed(struct mptcp_sock *msk)
{
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
}
void mptcp_pm_subflow_established(struct mptcp_sock *msk)
{
struct mptcp_pm_data *pm = &msk->pm;
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
if (!READ_ONCE(pm->work_pending))
return;
@@ -222,7 +212,7 @@ void mptcp_pm_add_addr_received(const struct sock *ssk,
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
struct mptcp_pm_data *pm = &msk->pm;
- pr_debug("msk=%p remote_id=%d accept=%d", msk, addr->id,
+ pr_debug("msk=%p remote_id=%d accept=%d\n", msk, addr->id,
READ_ONCE(pm->accept_addr));
mptcp_event_addr_announced(ssk, addr);
@@ -236,7 +226,9 @@ void mptcp_pm_add_addr_received(const struct sock *ssk,
} else {
__MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_ADDADDRDROP);
}
- } else if (!READ_ONCE(pm->accept_addr)) {
+ /* id0 should not have a different address */
+ } else if ((addr->id == 0 && !mptcp_pm_nl_is_init_remote_addr(msk, addr)) ||
+ (addr->id > 0 && !READ_ONCE(pm->accept_addr))) {
mptcp_pm_announce_addr(msk, addr, true);
mptcp_pm_add_addr_send_ack(msk);
} else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) {
@@ -253,7 +245,7 @@ void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,
{
struct mptcp_pm_data *pm = &msk->pm;
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
spin_lock_bh(&pm->lock);
@@ -277,7 +269,7 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
struct mptcp_pm_data *pm = &msk->pm;
u8 i;
- pr_debug("msk=%p remote_ids_nr=%d", msk, rm_list->nr);
+ pr_debug("msk=%p remote_ids_nr=%d\n", msk, rm_list->nr);
for (i = 0; i < rm_list->nr; i++)
mptcp_event_addr_removed(msk, rm_list->ids[i]);
@@ -309,19 +301,19 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq)
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
- pr_debug("fail_seq=%llu", fail_seq);
+ pr_debug("fail_seq=%llu\n", fail_seq);
if (!READ_ONCE(msk->allow_infinite_fallback))
return;
if (!subflow->fail_tout) {
- pr_debug("send MP_FAIL response and infinite map");
+ pr_debug("send MP_FAIL response and infinite map\n");
subflow->send_mp_fail = 1;
subflow->send_infinite_map = 1;
tcp_send_ack(sk);
} else {
- pr_debug("MP_FAIL response received");
+ pr_debug("MP_FAIL response received\n");
WRITE_ONCE(subflow->fail_tout, 0);
}
}
@@ -444,9 +436,6 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id
*flags = 0;
*ifindex = 0;
- if (!id)
- return 0;
-
if (mptcp_pm_is_userspace(msk))
return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk, id, flags, ifindex);
return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 4cae2aa..f891bc7 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -130,12 +130,15 @@ static bool lookup_subflow_by_daddr(const struct list_head *list,
{
struct mptcp_subflow_context *subflow;
struct mptcp_addr_info cur;
- struct sock_common *skc;
list_for_each_entry(subflow, list, node) {
- skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow);
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
- remote_address(skc, &cur);
+ if (!((1 << inet_sk_state_load(ssk)) &
+ (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_SYN_RECV)))
+ continue;
+
+ remote_address((struct sock_common *)ssk, &cur);
if (mptcp_addresses_equal(&cur, daddr, daddr->port))
return true;
}
@@ -143,11 +146,13 @@ static bool lookup_subflow_by_daddr(const struct list_head *list,
return false;
}
-static struct mptcp_pm_addr_entry *
+static bool
select_local_address(const struct pm_nl_pernet *pernet,
- const struct mptcp_sock *msk)
+ const struct mptcp_sock *msk,
+ struct mptcp_pm_addr_entry *new_entry)
{
- struct mptcp_pm_addr_entry *entry, *ret = NULL;
+ struct mptcp_pm_addr_entry *entry;
+ bool found = false;
msk_owned_by_me(msk);
@@ -159,17 +164,21 @@ select_local_address(const struct pm_nl_pernet *pernet,
if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
continue;
- ret = entry;
+ *new_entry = *entry;
+ found = true;
break;
}
rcu_read_unlock();
- return ret;
+
+ return found;
}
-static struct mptcp_pm_addr_entry *
-select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk)
+static bool
+select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk,
+ struct mptcp_pm_addr_entry *new_entry)
{
- struct mptcp_pm_addr_entry *entry, *ret = NULL;
+ struct mptcp_pm_addr_entry *entry;
+ bool found = false;
rcu_read_lock();
/* do not keep any additional per socket state, just signal
@@ -184,11 +193,13 @@ select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk)
if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL))
continue;
- ret = entry;
+ *new_entry = *entry;
+ found = true;
break;
}
rcu_read_unlock();
- return ret;
+
+ return found;
}
unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk)
@@ -279,7 +290,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
struct mptcp_sock *msk = entry->sock;
struct sock *sk = (struct sock *)msk;
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
if (!msk)
return;
@@ -298,7 +309,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
spin_lock_bh(&msk->pm.lock);
if (!mptcp_pm_should_add_signal_addr(msk)) {
- pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id);
+ pr_debug("retransmit ADD_ADDR id=%d\n", entry->addr.id);
mptcp_pm_announce_addr(msk, &entry->addr, false);
mptcp_pm_add_addr_send_ack(msk);
entry->retrans_times++;
@@ -379,7 +390,7 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
struct sock *sk = (struct sock *)msk;
LIST_HEAD(free_list);
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
spin_lock_bh(&msk->pm.lock);
list_splice_init(&msk->pm.anno_list, &free_list);
@@ -465,7 +476,7 @@ static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_con
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
bool slow;
- pr_debug("send ack for %s",
+ pr_debug("send ack for %s\n",
prio ? "mp_prio" : (mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr"));
slow = lock_sock_fast(ssk);
@@ -512,9 +523,10 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info)
static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
{
- struct mptcp_pm_addr_entry *local, *signal_and_subflow = NULL;
struct sock *sk = (struct sock *)msk;
+ struct mptcp_pm_addr_entry local;
unsigned int add_addr_signal_max;
+ bool signal_and_subflow = false;
unsigned int local_addr_max;
struct pm_nl_pernet *pernet;
unsigned int subflows_max;
@@ -565,23 +577,27 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL))
return;
- local = select_signal_address(pernet, msk);
- if (!local)
+ if (!select_signal_address(pernet, msk, &local))
goto subflow;
/* If the alloc fails, we are on memory pressure, not worth
* continuing, and trying to create subflows.
*/
- if (!mptcp_pm_alloc_anno_list(msk, &local->addr))
+ if (!mptcp_pm_alloc_anno_list(msk, &local.addr))
return;
- __clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
+ __clear_bit(local.addr.id, msk->pm.id_avail_bitmap);
msk->pm.add_addr_signaled++;
- mptcp_pm_announce_addr(msk, &local->addr, false);
+
+ /* Special case for ID0: set the correct ID */
+ if (local.addr.id == msk->mpc_endpoint_id)
+ local.addr.id = 0;
+
+ mptcp_pm_announce_addr(msk, &local.addr, false);
mptcp_pm_nl_addr_send_ack(msk);
- if (local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
- signal_and_subflow = local;
+ if (local.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
+ signal_and_subflow = true;
}
subflow:
@@ -592,26 +608,28 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
bool fullmesh;
int i, nr;
- if (signal_and_subflow) {
- local = signal_and_subflow;
- signal_and_subflow = NULL;
- } else {
- local = select_local_address(pernet, msk);
- if (!local)
- break;
- }
+ if (signal_and_subflow)
+ signal_and_subflow = false;
+ else if (!select_local_address(pernet, msk, &local))
+ break;
- fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
+ fullmesh = !!(local.flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
- msk->pm.local_addr_used++;
- __clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
- nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs);
+ __clear_bit(local.addr.id, msk->pm.id_avail_bitmap);
+
+ /* Special case for ID0: set the correct ID */
+ if (local.addr.id == msk->mpc_endpoint_id)
+ local.addr.id = 0;
+ else /* local_addr_used is not decr for ID 0 */
+ msk->pm.local_addr_used++;
+
+ nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh, addrs);
if (nr == 0)
continue;
spin_unlock_bh(&msk->pm.lock);
for (i = 0; i < nr; i++)
- __mptcp_subflow_connect(sk, &local->addr, &addrs[i]);
+ __mptcp_subflow_connect(sk, &local.addr, &addrs[i]);
spin_lock_bh(&msk->pm.lock);
}
mptcp_pm_nl_check_work_pending(msk);
@@ -636,6 +654,7 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
{
struct sock *sk = (struct sock *)msk;
struct mptcp_pm_addr_entry *entry;
+ struct mptcp_addr_info mpc_addr;
struct pm_nl_pernet *pernet;
unsigned int subflows_max;
int i = 0;
@@ -643,6 +662,8 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
pernet = pm_nl_get_pernet_from_msk(msk);
subflows_max = mptcp_pm_get_subflows_max(msk);
+ mptcp_local_address((struct sock_common *)msk, &mpc_addr);
+
rcu_read_lock();
list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH))
@@ -653,7 +674,13 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
if (msk->pm.subflows < subflows_max) {
msk->pm.subflows++;
- addrs[i++] = entry->addr;
+ addrs[i] = entry->addr;
+
+ /* Special case for ID0: set the correct ID */
+ if (mptcp_addresses_equal(&entry->addr, &mpc_addr, entry->addr.port))
+ addrs[i].id = 0;
+
+ i++;
}
}
rcu_read_unlock();
@@ -695,7 +722,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk);
subflows_max = mptcp_pm_get_subflows_max(msk);
- pr_debug("accepted %d:%d remote family %d",
+ pr_debug("accepted %d:%d remote family %d\n",
msk->pm.add_addr_accepted, add_addr_accept_max,
msk->pm.remote.family);
@@ -724,13 +751,24 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
spin_lock_bh(&msk->pm.lock);
if (sf_created) {
- msk->pm.add_addr_accepted++;
+ /* add_addr_accepted is not decr for ID 0 */
+ if (remote.id)
+ msk->pm.add_addr_accepted++;
if (msk->pm.add_addr_accepted >= add_addr_accept_max ||
msk->pm.subflows >= subflows_max)
WRITE_ONCE(msk->pm.accept_addr, false);
}
}
+bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk,
+ const struct mptcp_addr_info *remote)
+{
+ struct mptcp_addr_info mpc_remote;
+
+ remote_address((struct sock_common *)msk, &mpc_remote);
+ return mptcp_addresses_equal(&mpc_remote, remote, remote->port);
+}
+
void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
{
struct mptcp_subflow_context *subflow;
@@ -742,9 +780,12 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
!mptcp_pm_should_rm_signal(msk))
return;
- subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node);
- if (subflow)
- mptcp_pm_send_ack(msk, subflow, false, false);
+ mptcp_for_each_subflow(msk, subflow) {
+ if (__mptcp_subflow_active(subflow)) {
+ mptcp_pm_send_ack(msk, subflow, false, false);
+ break;
+ }
+ }
}
int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
@@ -754,7 +795,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
{
struct mptcp_subflow_context *subflow;
- pr_debug("bkup=%d", bkup);
+ pr_debug("bkup=%d\n", bkup);
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
@@ -777,11 +818,6 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
return -EINVAL;
}
-static bool mptcp_local_id_match(const struct mptcp_sock *msk, u8 local_id, u8 id)
-{
- return local_id == id || (!local_id && msk->mpc_endpoint_id == id);
-}
-
static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
const struct mptcp_rm_list *rm_list,
enum linux_mptcp_mib_field rm_type)
@@ -790,7 +826,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
struct sock *sk = (struct sock *)msk;
u8 i;
- pr_debug("%s rm_list_nr %d",
+ pr_debug("%s rm_list_nr %d\n",
rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", rm_list->nr);
msk_owned_by_me(msk);
@@ -814,12 +850,14 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
u8 id = subflow_get_local_id(subflow);
+ if (inet_sk_state_load(ssk) == TCP_CLOSE)
+ continue;
if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id)
continue;
- if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id))
+ if (rm_type == MPTCP_MIB_RMSUBFLOW && id != rm_id)
continue;
- pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u",
+ pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u\n",
rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow",
i, rm_id, id, remote_id, msk->mpc_endpoint_id);
spin_unlock_bh(&msk->pm.lock);
@@ -829,25 +867,27 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
mptcp_close_ssk(sk, ssk, subflow);
spin_lock_bh(&msk->pm.lock);
- removed = true;
+ removed |= subflow->request_join;
if (rm_type == MPTCP_MIB_RMSUBFLOW)
__MPTCP_INC_STATS(sock_net(sk), rm_type);
}
- if (rm_type == MPTCP_MIB_RMSUBFLOW)
- __set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap);
- else if (rm_type == MPTCP_MIB_RMADDR)
+
+ if (rm_type == MPTCP_MIB_RMADDR)
__MPTCP_INC_STATS(sock_net(sk), rm_type);
+
if (!removed)
continue;
if (!mptcp_pm_is_kernel(msk))
continue;
- if (rm_type == MPTCP_MIB_RMADDR) {
- msk->pm.add_addr_accepted--;
- WRITE_ONCE(msk->pm.accept_addr, true);
- } else if (rm_type == MPTCP_MIB_RMSUBFLOW) {
- msk->pm.local_addr_used--;
+ if (rm_type == MPTCP_MIB_RMADDR && rm_id &&
+ !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) {
+ /* Note: if the subflow has been closed before, this
+ * add_addr_accepted counter will not be decremented.
+ */
+ if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk))
+ WRITE_ONCE(msk->pm.accept_addr, true);
}
}
}
@@ -857,8 +897,8 @@ static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk)
mptcp_pm_nl_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR);
}
-void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
- const struct mptcp_rm_list *rm_list)
+static void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
+ const struct mptcp_rm_list *rm_list)
{
mptcp_pm_nl_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW);
}
@@ -874,7 +914,7 @@ void mptcp_pm_nl_work(struct mptcp_sock *msk)
spin_lock_bh(&msk->pm.lock);
- pr_debug("msk=%p status=%x", msk, pm->status);
+ pr_debug("msk=%p status=%x\n", msk, pm->status);
if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) {
pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED);
mptcp_pm_nl_add_addr_received(msk);
@@ -1292,20 +1332,27 @@ static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info)
return pm_nl_get_pernet(genl_info_net(info));
}
-static int mptcp_nl_add_subflow_or_signal_addr(struct net *net)
+static int mptcp_nl_add_subflow_or_signal_addr(struct net *net,
+ struct mptcp_addr_info *addr)
{
struct mptcp_sock *msk;
long s_slot = 0, s_num = 0;
while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
struct sock *sk = (struct sock *)msk;
+ struct mptcp_addr_info mpc_addr;
if (!READ_ONCE(msk->fully_established) ||
mptcp_pm_is_userspace(msk))
goto next;
+ /* if the endp linked to the init sf is re-added with a != ID */
+ mptcp_local_address((struct sock_common *)msk, &mpc_addr);
+
lock_sock(sk);
spin_lock_bh(&msk->pm.lock);
+ if (mptcp_addresses_equal(addr, &mpc_addr, addr->port))
+ msk->mpc_endpoint_id = addr->id;
mptcp_pm_create_subflow_or_signal_addr(msk);
spin_unlock_bh(&msk->pm.lock);
release_sock(sk);
@@ -1378,7 +1425,7 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
goto out_free;
}
- mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk));
+ mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk), &entry->addr);
return 0;
out_free:
@@ -1393,6 +1440,10 @@ int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int
struct sock *sk = (struct sock *)msk;
struct net *net = sock_net(sk);
+ /* No entries with ID 0 */
+ if (id == 0)
+ return 0;
+
rcu_read_lock();
entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id);
if (entry) {
@@ -1419,6 +1470,12 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk,
return false;
}
+static u8 mptcp_endp_get_local_id(struct mptcp_sock *msk,
+ const struct mptcp_addr_info *addr)
+{
+ return msk->mpc_endpoint_id == addr->id ? 0 : addr->id;
+}
+
static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr,
bool force)
@@ -1426,29 +1483,38 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
struct mptcp_rm_list list = { .nr = 0 };
bool ret;
- list.ids[list.nr++] = addr->id;
+ list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr);
ret = remove_anno_list_by_saddr(msk, addr);
if (ret || force) {
spin_lock_bh(&msk->pm.lock);
- msk->pm.add_addr_signaled -= ret;
+ if (ret) {
+ __set_bit(addr->id, msk->pm.id_avail_bitmap);
+ msk->pm.add_addr_signaled--;
+ }
mptcp_pm_remove_addr(msk, &list);
spin_unlock_bh(&msk->pm.lock);
}
return ret;
}
+static void __mark_subflow_endp_available(struct mptcp_sock *msk, u8 id)
+{
+ /* If it was marked as used, and not ID 0, decrement local_addr_used */
+ if (!__test_and_set_bit(id ? : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap) &&
+ id && !WARN_ON_ONCE(msk->pm.local_addr_used == 0))
+ msk->pm.local_addr_used--;
+}
+
static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
const struct mptcp_pm_addr_entry *entry)
{
const struct mptcp_addr_info *addr = &entry->addr;
- struct mptcp_rm_list list = { .nr = 0 };
+ struct mptcp_rm_list list = { .nr = 1 };
long s_slot = 0, s_num = 0;
struct mptcp_sock *msk;
- pr_debug("remove_id=%d", addr->id);
-
- list.ids[list.nr++] = addr->id;
+ pr_debug("remove_id=%d\n", addr->id);
while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
struct sock *sk = (struct sock *)msk;
@@ -1466,8 +1532,22 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr);
mptcp_pm_remove_anno_addr(msk, addr, remove_subflow &&
!(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT));
- if (remove_subflow)
- mptcp_pm_remove_subflow(msk, &list);
+
+ list.ids[0] = mptcp_endp_get_local_id(msk, addr);
+ if (remove_subflow) {
+ spin_lock_bh(&msk->pm.lock);
+ mptcp_pm_nl_rm_subflow_received(msk, &list);
+ spin_unlock_bh(&msk->pm.lock);
+ }
+
+ if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
+ spin_lock_bh(&msk->pm.lock);
+ __mark_subflow_endp_available(msk, list.ids[0]);
+ spin_unlock_bh(&msk->pm.lock);
+ }
+
+ if (msk->mpc_endpoint_id == entry->addr.id)
+ msk->mpc_endpoint_id = 0;
release_sock(sk);
next:
@@ -1502,6 +1582,7 @@ static int mptcp_nl_remove_id_zero_address(struct net *net,
spin_lock_bh(&msk->pm.lock);
mptcp_pm_remove_addr(msk, &list);
mptcp_pm_nl_rm_subflow_received(msk, &list);
+ __mark_subflow_endp_available(msk, 0);
spin_unlock_bh(&msk->pm.lock);
release_sock(sk);
@@ -1561,6 +1642,7 @@ int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info)
return ret;
}
+/* Called from the userspace PM only */
void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list)
{
struct mptcp_rm_list alist = { .nr = 0 };
@@ -1589,6 +1671,7 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list)
}
}
+/* Called from the in-kernel PM only */
static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
struct list_head *rm_list)
{
@@ -1598,21 +1681,24 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
list_for_each_entry(entry, rm_list, list) {
if (slist.nr < MPTCP_RM_IDS_MAX &&
lookup_subflow_by_saddr(&msk->conn_list, &entry->addr))
- slist.ids[slist.nr++] = entry->addr.id;
+ slist.ids[slist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr);
if (alist.nr < MPTCP_RM_IDS_MAX &&
remove_anno_list_by_saddr(msk, &entry->addr))
- alist.ids[alist.nr++] = entry->addr.id;
+ alist.ids[alist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr);
}
+ spin_lock_bh(&msk->pm.lock);
if (alist.nr) {
- spin_lock_bh(&msk->pm.lock);
msk->pm.add_addr_signaled -= alist.nr;
mptcp_pm_remove_addr(msk, &alist);
- spin_unlock_bh(&msk->pm.lock);
}
if (slist.nr)
- mptcp_pm_remove_subflow(msk, &slist);
+ mptcp_pm_nl_rm_subflow_received(msk, &slist);
+ /* Reset counters: maybe some subflows have been removed before */
+ bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
+ msk->pm.local_addr_used = 0;
+ spin_unlock_bh(&msk->pm.lock);
}
static void mptcp_nl_remove_addrs_list(struct net *net,
@@ -1896,10 +1982,11 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
{
struct mptcp_rm_list list = { .nr = 0 };
- list.ids[list.nr++] = addr->id;
+ list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr);
spin_lock_bh(&msk->pm.lock);
mptcp_pm_nl_rm_subflow_received(msk, &list);
+ __mark_subflow_endp_available(msk, list.ids[0]);
mptcp_pm_create_subflow_or_signal_addr(msk);
spin_unlock_bh(&msk->pm.lock);
}
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 0d536b1..37ebcb7 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -139,7 +139,7 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
!skb_try_coalesce(to, from, &fragstolen, &delta))
return false;
- pr_debug("colesced seq %llx into %llx new len %d new end seq %llx",
+ pr_debug("colesced seq %llx into %llx new len %d new end seq %llx\n",
MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq,
to->len, MPTCP_SKB_CB(from)->end_seq);
MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq;
@@ -217,7 +217,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
end_seq = MPTCP_SKB_CB(skb)->end_seq;
max_seq = atomic64_read(&msk->rcv_wnd_sent);
- pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq,
+ pr_debug("msk=%p seq=%llx limit=%llx empty=%d\n", msk, seq, max_seq,
RB_EMPTY_ROOT(&msk->out_of_order_queue));
if (after64(end_seq, max_seq)) {
/* out of window */
@@ -643,7 +643,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
}
}
- pr_debug("msk=%p ssk=%p", msk, ssk);
+ pr_debug("msk=%p ssk=%p\n", msk, ssk);
tp = tcp_sk(ssk);
do {
u32 map_remaining, offset;
@@ -724,7 +724,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
u64 end_seq;
p = rb_first(&msk->out_of_order_queue);
- pr_debug("msk=%p empty=%d", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue));
+ pr_debug("msk=%p empty=%d\n", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue));
while (p) {
skb = rb_to_skb(p);
if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq))
@@ -746,7 +746,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
int delta = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq;
/* skip overlapping data, if any */
- pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d",
+ pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d\n",
MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq,
delta);
MPTCP_SKB_CB(skb)->offset += delta;
@@ -1240,7 +1240,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
size_t copy;
int i;
- pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u",
+ pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u\n",
msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent);
if (WARN_ON_ONCE(info->sent > info->limit ||
@@ -1341,7 +1341,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
mpext->use_map = 1;
mpext->dsn64 = 1;
- pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d",
+ pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d\n",
mpext->data_seq, mpext->subflow_seq, mpext->data_len,
mpext->dsn64);
@@ -1892,7 +1892,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (!msk->first_pending)
WRITE_ONCE(msk->first_pending, dfrag);
}
- pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d", msk,
+ pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d\n", msk,
dfrag->data_seq, dfrag->data_len, dfrag->already_sent,
!dfrag_collapsed);
@@ -2248,7 +2248,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
}
}
- pr_debug("block timeout %ld", timeo);
+ pr_debug("block timeout %ld\n", timeo);
sk_wait_data(sk, &timeo, NULL);
}
@@ -2264,7 +2264,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
}
}
- pr_debug("msk=%p rx queue empty=%d:%d copied=%d",
+ pr_debug("msk=%p rx queue empty=%d:%d copied=%d\n",
msk, skb_queue_empty_lockless(&sk->sk_receive_queue),
skb_queue_empty(&msk->receive_queue), copied);
if (!(flags & MSG_PEEK))
@@ -2326,7 +2326,7 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
continue;
}
- if (subflow->backup) {
+ if (subflow->backup || subflow->request_bkup) {
if (!backup)
backup = ssk;
continue;
@@ -2508,6 +2508,12 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
struct mptcp_subflow_context *subflow)
{
+ /* The first subflow can already be closed and still in the list */
+ if (subflow->close_event_done)
+ return;
+
+ subflow->close_event_done = true;
+
if (sk->sk_state == TCP_ESTABLISHED)
mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL);
@@ -2533,8 +2539,11 @@ static void __mptcp_close_subflow(struct sock *sk)
mptcp_for_each_subflow_safe(msk, subflow, tmp) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ int ssk_state = inet_sk_state_load(ssk);
- if (inet_sk_state_load(ssk) != TCP_CLOSE)
+ if (ssk_state != TCP_CLOSE &&
+ (ssk_state != TCP_CLOSE_WAIT ||
+ inet_sk_state_load(sk) != TCP_ESTABLISHED))
continue;
/* 'subflow_data_ready' will re-sched once rx queue is empty */
@@ -2714,7 +2723,7 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk)
if (!ssk)
return;
- pr_debug("MP_FAIL doesn't respond, reset the subflow");
+ pr_debug("MP_FAIL doesn't respond, reset the subflow\n");
slow = lock_sock_fast(ssk);
mptcp_subflow_reset(ssk);
@@ -2888,7 +2897,7 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
break;
default:
if (__mptcp_check_fallback(mptcp_sk(sk))) {
- pr_debug("Fallback");
+ pr_debug("Fallback\n");
ssk->sk_shutdown |= how;
tcp_shutdown(ssk, how);
@@ -2898,7 +2907,7 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt);
mptcp_schedule_work(sk);
} else {
- pr_debug("Sending DATA_FIN on subflow %p", ssk);
+ pr_debug("Sending DATA_FIN on subflow %p\n", ssk);
tcp_send_ack(ssk);
if (!mptcp_rtx_timer_pending(sk))
mptcp_reset_rtx_timer(sk);
@@ -2964,7 +2973,7 @@ static void mptcp_check_send_data_fin(struct sock *sk)
struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk = mptcp_sk(sk);
- pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu",
+ pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu\n",
msk, msk->snd_data_fin_enable, !!mptcp_send_head(sk),
msk->snd_nxt, msk->write_seq);
@@ -2988,7 +2997,7 @@ static void __mptcp_wr_shutdown(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d",
+ pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d\n",
msk, msk->snd_data_fin_enable, sk->sk_shutdown, sk->sk_state,
!!mptcp_send_head(sk));
@@ -3003,7 +3012,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
might_sleep();
@@ -3111,7 +3120,7 @@ bool __mptcp_close(struct sock *sk, long timeout)
mptcp_set_state(sk, TCP_CLOSE);
sock_hold(sk);
- pr_debug("msk=%p state=%d", sk, sk->sk_state);
+ pr_debug("msk=%p state=%d\n", sk, sk->sk_state);
if (msk->token)
mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);
@@ -3543,7 +3552,7 @@ static int mptcp_get_port(struct sock *sk, unsigned short snum)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- pr_debug("msk=%p, ssk=%p", msk, msk->first);
+ pr_debug("msk=%p, ssk=%p\n", msk, msk->first);
if (WARN_ON_ONCE(!msk->first))
return -EINVAL;
@@ -3560,7 +3569,7 @@ void mptcp_finish_connect(struct sock *ssk)
sk = subflow->conn;
msk = mptcp_sk(sk);
- pr_debug("msk=%p, token=%u", sk, subflow->token);
+ pr_debug("msk=%p, token=%u\n", sk, subflow->token);
subflow->map_seq = subflow->iasn;
subflow->map_subflow_seq = 1;
@@ -3589,7 +3598,7 @@ bool mptcp_finish_join(struct sock *ssk)
struct sock *parent = (void *)msk;
bool ret = true;
- pr_debug("msk=%p, subflow=%p", msk, subflow);
+ pr_debug("msk=%p, subflow=%p\n", msk, subflow);
/* mptcp socket already closing? */
if (!mptcp_is_fully_established(parent)) {
@@ -3635,7 +3644,7 @@ bool mptcp_finish_join(struct sock *ssk)
static void mptcp_shutdown(struct sock *sk, int how)
{
- pr_debug("sk=%p, how=%d", sk, how);
+ pr_debug("sk=%p, how=%d\n", sk, how);
if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk))
__mptcp_wr_shutdown(sk);
@@ -3856,7 +3865,7 @@ static int mptcp_listen(struct socket *sock, int backlog)
struct sock *ssk;
int err;
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
lock_sock(sk);
@@ -3895,7 +3904,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
struct mptcp_sock *msk = mptcp_sk(sock->sk);
struct sock *ssk, *newsk;
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
/* Buggy applications can call accept on socket states other then LISTEN
* but no need to allocate the first subflow just to error out.
@@ -3904,12 +3913,12 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
if (!ssk)
return -EINVAL;
- pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk));
+ pr_debug("ssk=%p, listener=%p\n", ssk, mptcp_subflow_ctx(ssk));
newsk = inet_csk_accept(ssk, arg);
if (!newsk)
return arg->err;
- pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk));
+ pr_debug("newsk=%p, subflow is mptcp=%d\n", newsk, sk_is_mptcp(newsk));
if (sk_is_mptcp(newsk)) {
struct mptcp_subflow_context *subflow;
struct sock *new_mptcp_sock;
@@ -4002,7 +4011,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
sock_poll_wait(file, sock, wait);
state = inet_sk_state_load(sk);
- pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags);
+ pr_debug("msk=%p state=%d flags=%lx\n", msk, state, msk->flags);
if (state == TCP_LISTEN) {
struct sock *ssk = READ_ONCE(msk->first);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 60c6b07..3b22313 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -524,7 +524,8 @@ struct mptcp_subflow_context {
stale : 1, /* unable to snd/rcv data, do not use for xmit */
valid_csum_seen : 1, /* at least one csum validated */
is_mptfo : 1, /* subflow is doing TFO */
- __unused : 10;
+ close_event_done : 1, /* has done the post-closed part */
+ __unused : 9;
bool data_avail;
bool scheduled;
u32 remote_nonce;
@@ -992,6 +993,8 @@ void mptcp_pm_add_addr_received(const struct sock *ssk,
void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr);
void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk);
+bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk,
+ const struct mptcp_addr_info *remote);
void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk);
void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
const struct mptcp_rm_list *rm_list);
@@ -1026,7 +1029,6 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr,
bool echo);
int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);
-int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);
void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list);
void mptcp_free_local_addr_list(struct mptcp_sock *msk);
@@ -1133,8 +1135,6 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo
void __init mptcp_pm_nl_init(void);
void mptcp_pm_nl_work(struct mptcp_sock *msk);
-void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
- const struct mptcp_rm_list *rm_list);
unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk);
unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk);
unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk);
@@ -1180,7 +1180,7 @@ static inline bool mptcp_check_fallback(const struct sock *sk)
static inline void __mptcp_do_fallback(struct mptcp_sock *msk)
{
if (__mptcp_check_fallback(msk)) {
- pr_debug("TCP fallback already done (msk=%p)", msk);
+ pr_debug("TCP fallback already done (msk=%p)\n", msk);
return;
}
set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
@@ -1216,7 +1216,7 @@ static inline void mptcp_do_fallback(struct sock *ssk)
}
}
-#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a)
+#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)\n", __func__, a)
static inline bool mptcp_check_infinite_map(struct sk_buff *skb)
{
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 4a7fd05..78ed508 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -86,7 +86,7 @@ int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
list_add_tail_rcu(&sched->list, &mptcp_sched_list);
spin_unlock(&mptcp_sched_list_lock);
- pr_debug("%s registered", sched->name);
+ pr_debug("%s registered\n", sched->name);
return 0;
}
@@ -118,7 +118,7 @@ int mptcp_init_sched(struct mptcp_sock *msk,
if (msk->sched->init)
msk->sched->init(msk);
- pr_debug("sched=%s", msk->sched->name);
+ pr_debug("sched=%s\n", msk->sched->name);
return 0;
}
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 2026a9a..505445a 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -873,7 +873,7 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname,
struct mptcp_sock *msk = mptcp_sk(sk);
struct sock *ssk;
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
if (level == SOL_SOCKET)
return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen);
@@ -1453,7 +1453,7 @@ int mptcp_getsockopt(struct sock *sk, int level, int optname,
struct mptcp_sock *msk = mptcp_sk(sk);
struct sock *ssk;
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
/* @@ the meaning of setsockopt() when the socket is connected and
* there are multiple subflows is not yet defined. It is up to the
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index a21c712..064ab32 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -39,7 +39,7 @@ static void subflow_req_destructor(struct request_sock *req)
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
- pr_debug("subflow_req=%p", subflow_req);
+ pr_debug("subflow_req=%p\n", subflow_req);
if (subflow_req->msk)
sock_put((struct sock *)subflow_req->msk);
@@ -146,7 +146,7 @@ static int subflow_check_req(struct request_sock *req,
struct mptcp_options_received mp_opt;
bool opt_mp_capable, opt_mp_join;
- pr_debug("subflow_req=%p, listener=%p", subflow_req, listener);
+ pr_debug("subflow_req=%p, listener=%p\n", subflow_req, listener);
#ifdef CONFIG_TCP_MD5SIG
/* no MPTCP if MD5SIG is enabled on this socket or we may run out of
@@ -221,7 +221,7 @@ static int subflow_check_req(struct request_sock *req,
}
if (subflow_use_different_sport(subflow_req->msk, sk_listener)) {
- pr_debug("syn inet_sport=%d %d",
+ pr_debug("syn inet_sport=%d %d\n",
ntohs(inet_sk(sk_listener)->inet_sport),
ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport));
if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) {
@@ -243,7 +243,7 @@ static int subflow_check_req(struct request_sock *req,
subflow_init_req_cookie_join_save(subflow_req, skb);
}
- pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token,
+ pr_debug("token=%u, remote_nonce=%u msk=%p\n", subflow_req->token,
subflow_req->remote_nonce, subflow_req->msk);
}
@@ -527,7 +527,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
subflow->rel_write_seq = 1;
subflow->conn_finished = 1;
subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
- pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset);
+ pr_debug("subflow=%p synack seq=%x\n", subflow, subflow->ssn_offset);
mptcp_get_options(skb, &mp_opt);
if (subflow->request_mptcp) {
@@ -559,7 +559,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
subflow->thmac = mp_opt.thmac;
subflow->remote_nonce = mp_opt.nonce;
WRITE_ONCE(subflow->remote_id, mp_opt.join_id);
- pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d",
+ pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d\n",
subflow, subflow->thmac, subflow->remote_nonce,
subflow->backup);
@@ -585,7 +585,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX);
if (subflow_use_different_dport(msk, sk)) {
- pr_debug("synack inet_dport=%d %d",
+ pr_debug("synack inet_dport=%d %d\n",
ntohs(inet_sk(sk)->inet_dport),
ntohs(inet_sk(parent)->inet_dport));
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINPORTSYNACKRX);
@@ -655,7 +655,7 @@ static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
- pr_debug("subflow=%p", subflow);
+ pr_debug("subflow=%p\n", subflow);
/* Never answer to SYNs sent to broadcast or multicast */
if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
@@ -686,7 +686,7 @@ static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
- pr_debug("subflow=%p", subflow);
+ pr_debug("subflow=%p\n", subflow);
if (skb->protocol == htons(ETH_P_IP))
return subflow_v4_conn_request(sk, skb);
@@ -807,7 +807,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
struct mptcp_sock *owner;
struct sock *child;
- pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn);
+ pr_debug("listener=%p, req=%p, conn=%p\n", listener, req, listener->conn);
/* After child creation we must look for MPC even when options
* are not parsed
@@ -898,7 +898,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
ctx->conn = (struct sock *)owner;
if (subflow_use_different_sport(owner, sk)) {
- pr_debug("ack inet_sport=%d %d",
+ pr_debug("ack inet_sport=%d %d\n",
ntohs(inet_sk(sk)->inet_sport),
ntohs(inet_sk((struct sock *)owner)->inet_sport));
if (!mptcp_pm_sport_in_anno_list(owner, sk)) {
@@ -961,7 +961,7 @@ enum mapping_status {
static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
{
- pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d",
+ pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d\n",
ssn, subflow->map_subflow_seq, subflow->map_data_len);
}
@@ -1121,7 +1121,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
data_len = mpext->data_len;
if (data_len == 0) {
- pr_debug("infinite mapping received");
+ pr_debug("infinite mapping received\n");
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
subflow->map_data_len = 0;
return MAPPING_INVALID;
@@ -1133,7 +1133,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
if (data_len == 1) {
bool updated = mptcp_update_rcv_data_fin(msk, mpext->data_seq,
mpext->dsn64);
- pr_debug("DATA_FIN with no payload seq=%llu", mpext->data_seq);
+ pr_debug("DATA_FIN with no payload seq=%llu\n", mpext->data_seq);
if (subflow->map_valid) {
/* A DATA_FIN might arrive in a DSS
* option before the previous mapping
@@ -1159,7 +1159,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
data_fin_seq &= GENMASK_ULL(31, 0);
mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64);
- pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d",
+ pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d\n",
data_fin_seq, mpext->dsn64);
/* Adjust for DATA_FIN using 1 byte of sequence space */
@@ -1205,7 +1205,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
if (unlikely(subflow->map_csum_reqd != csum_reqd))
return MAPPING_INVALID;
- pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u",
+ pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u\n",
subflow->map_seq, subflow->map_subflow_seq,
subflow->map_data_len, subflow->map_csum_reqd,
subflow->map_data_csum);
@@ -1240,7 +1240,7 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
avail_len = skb->len - offset;
incr = limit >= avail_len ? avail_len + fin : limit;
- pr_debug("discarding=%d len=%d offset=%d seq=%d", incr, skb->len,
+ pr_debug("discarding=%d len=%d offset=%d seq=%d\n", incr, skb->len,
offset, subflow->map_subflow_seq);
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA);
tcp_sk(ssk)->copied_seq += incr;
@@ -1255,12 +1255,16 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
/* sched mptcp worker to remove the subflow if no more data is pending */
static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk)
{
- if (likely(ssk->sk_state != TCP_CLOSE))
+ struct sock *sk = (struct sock *)msk;
+
+ if (likely(ssk->sk_state != TCP_CLOSE &&
+ (ssk->sk_state != TCP_CLOSE_WAIT ||
+ inet_sk_state_load(sk) != TCP_ESTABLISHED)))
return;
if (skb_queue_empty(&ssk->sk_receive_queue) &&
!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
- mptcp_schedule_work((struct sock *)msk);
+ mptcp_schedule_work(sk);
}
static bool subflow_can_fallback(struct mptcp_subflow_context *subflow)
@@ -1337,7 +1341,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
old_ack = READ_ONCE(msk->ack_seq);
ack_seq = mptcp_subflow_get_mapped_dsn(subflow);
- pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack,
+ pr_debug("msk ack_seq=%llx subflow ack_seq=%llx\n", old_ack,
ack_seq);
if (unlikely(before64(ack_seq, old_ack))) {
mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq);
@@ -1409,7 +1413,7 @@ bool mptcp_subflow_data_available(struct sock *sk)
subflow->map_valid = 0;
WRITE_ONCE(subflow->data_avail, false);
- pr_debug("Done with mapping: seq=%u data_len=%u",
+ pr_debug("Done with mapping: seq=%u data_len=%u\n",
subflow->map_subflow_seq,
subflow->map_data_len);
}
@@ -1519,7 +1523,7 @@ void mptcpv6_handle_mapped(struct sock *sk, bool mapped)
target = mapped ? &subflow_v6m_specific : subflow_default_af_ops(sk);
- pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d",
+ pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d\n",
subflow, sk->sk_family, icsk->icsk_af_ops, target, mapped);
if (likely(icsk->icsk_af_ops == target))
@@ -1612,7 +1616,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
goto failed;
mptcp_crypto_key_sha(subflow->remote_key, &remote_token, NULL);
- pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk,
+ pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d\n", msk,
remote_token, local_id, remote_id);
subflow->remote_token = remote_token;
WRITE_ONCE(subflow->remote_id, remote_id);
@@ -1747,7 +1751,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
SOCK_INODE(sf)->i_gid = SOCK_INODE(sk->sk_socket)->i_gid;
subflow = mptcp_subflow_ctx(sf->sk);
- pr_debug("subflow=%p", subflow);
+ pr_debug("subflow=%p\n", subflow);
*new_sock = sf;
sock_hold(sk);
@@ -1776,7 +1780,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk,
INIT_LIST_HEAD(&ctx->node);
INIT_LIST_HEAD(&ctx->delegated_node);
- pr_debug("subflow=%p", ctx);
+ pr_debug("subflow=%p\n", ctx);
ctx->tcp_sock = sk;
WRITE_ONCE(ctx->local_id, -1);
@@ -1927,7 +1931,7 @@ static int subflow_ulp_init(struct sock *sk)
goto out;
}
- pr_debug("subflow=%p, family=%d", ctx, sk->sk_family);
+ pr_debug("subflow=%p, family=%d\n", ctx, sk->sk_family);
tp->is_mptcp = 1;
ctx->icsk_af_ops = icsk->icsk_af_ops;
diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c
index 88787b4..8b541a08 100644
--- a/net/netfilter/nf_flow_table_inet.c
+++ b/net/netfilter/nf_flow_table_inet.c
@@ -17,6 +17,9 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb,
switch (skb->protocol) {
case htons(ETH_P_8021Q):
+ if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth)))
+ return NF_ACCEPT;
+
veth = (struct vlan_ethhdr *)skb_mac_header(skb);
proto = veth->h_vlan_encapsulated_proto;
break;
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index c2c0052..98edcaa 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -281,6 +281,9 @@ static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto,
switch (skb->protocol) {
case htons(ETH_P_8021Q):
+ if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth)))
+ return false;
+
veth = (struct vlan_ethhdr *)skb_mac_header(skb);
if (veth->h_vlan_encapsulated_proto == proto) {
*offset += VLAN_HLEN;
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index ff1a4e3..e06bc36 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -841,8 +841,8 @@ static int nf_flow_offload_tuple(struct nf_flowtable *flowtable,
struct list_head *block_cb_list)
{
struct flow_cls_offload cls_flow = {};
+ struct netlink_ext_ack extack = {};
struct flow_block_cb *block_cb;
- struct netlink_ext_ack extack;
__be16 proto = ETH_P_ALL;
int err, i = 0;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 481ee78..0a2f793 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -8020,6 +8020,19 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
return skb->len;
}
+static int nf_tables_dumpreset_obj(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk));
+ int ret;
+
+ mutex_lock(&nft_net->commit_mutex);
+ ret = nf_tables_dump_obj(skb, cb);
+ mutex_unlock(&nft_net->commit_mutex);
+
+ return ret;
+}
+
static int nf_tables_dump_obj_start(struct netlink_callback *cb)
{
struct nft_obj_dump_ctx *ctx = (void *)cb->ctx;
@@ -8036,12 +8049,18 @@ static int nf_tables_dump_obj_start(struct netlink_callback *cb)
if (nla[NFTA_OBJ_TYPE])
ctx->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
- if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET)
- ctx->reset = true;
-
return 0;
}
+static int nf_tables_dumpreset_obj_start(struct netlink_callback *cb)
+{
+ struct nft_obj_dump_ctx *ctx = (void *)cb->ctx;
+
+ ctx->reset = true;
+
+ return nf_tables_dump_obj_start(cb);
+}
+
static int nf_tables_dump_obj_done(struct netlink_callback *cb)
{
struct nft_obj_dump_ctx *ctx = (void *)cb->ctx;
@@ -8052,8 +8071,9 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb)
}
/* called with rcu_read_lock held */
-static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,
- const struct nlattr * const nla[])
+static struct sk_buff *
+nf_tables_getobj_single(u32 portid, const struct nfnl_info *info,
+ const struct nlattr * const nla[], bool reset)
{
struct netlink_ext_ack *extack = info->extack;
u8 genmask = nft_genmask_cur(info->net);
@@ -8062,10 +8082,47 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,
struct net *net = info->net;
struct nft_object *obj;
struct sk_buff *skb2;
- bool reset = false;
u32 objtype;
int err;
+ if (!nla[NFTA_OBJ_NAME] ||
+ !nla[NFTA_OBJ_TYPE])
+ return ERR_PTR(-EINVAL);
+
+ table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]);
+ return ERR_CAST(table);
+ }
+
+ objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
+ obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask);
+ if (IS_ERR(obj)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]);
+ return ERR_CAST(obj);
+ }
+
+ skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC);
+ if (!skb2)
+ return ERR_PTR(-ENOMEM);
+
+ err = nf_tables_fill_obj_info(skb2, net, portid,
+ info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0,
+ family, table, obj, reset);
+ if (err < 0) {
+ kfree_skb(skb2);
+ return ERR_PTR(err);
+ }
+
+ return skb2;
+}
+
+static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,
+ const struct nlattr * const nla[])
+{
+ u32 portid = NETLINK_CB(skb).portid;
+ struct sk_buff *skb2;
+
if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
.start = nf_tables_dump_obj_start,
@@ -8078,56 +8135,56 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,
return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c);
}
- if (!nla[NFTA_OBJ_NAME] ||
- !nla[NFTA_OBJ_TYPE])
+ skb2 = nf_tables_getobj_single(portid, info, nla, false);
+ if (IS_ERR(skb2))
+ return PTR_ERR(skb2);
+
+ return nfnetlink_unicast(skb2, info->net, portid);
+}
+
+static int nf_tables_getobj_reset(struct sk_buff *skb,
+ const struct nfnl_info *info,
+ const struct nlattr * const nla[])
+{
+ struct nftables_pernet *nft_net = nft_pernet(info->net);
+ u32 portid = NETLINK_CB(skb).portid;
+ struct net *net = info->net;
+ struct sk_buff *skb2;
+ char *buf;
+
+ if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
+ struct netlink_dump_control c = {
+ .start = nf_tables_dumpreset_obj_start,
+ .dump = nf_tables_dumpreset_obj,
+ .done = nf_tables_dump_obj_done,
+ .module = THIS_MODULE,
+ .data = (void *)nla,
+ };
+
+ return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c);
+ }
+
+ if (!try_module_get(THIS_MODULE))
return -EINVAL;
+ rcu_read_unlock();
+ mutex_lock(&nft_net->commit_mutex);
+ skb2 = nf_tables_getobj_single(portid, info, nla, true);
+ mutex_unlock(&nft_net->commit_mutex);
+ rcu_read_lock();
+ module_put(THIS_MODULE);
- table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0);
- if (IS_ERR(table)) {
- NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]);
- return PTR_ERR(table);
- }
+ if (IS_ERR(skb2))
+ return PTR_ERR(skb2);
- objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
- obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask);
- if (IS_ERR(obj)) {
- NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]);
- return PTR_ERR(obj);
- }
+ buf = kasprintf(GFP_ATOMIC, "%.*s:%u",
+ nla_len(nla[NFTA_OBJ_TABLE]),
+ (char *)nla_data(nla[NFTA_OBJ_TABLE]),
+ nft_net->base_seq);
+ audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1,
+ AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC);
+ kfree(buf);
- skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC);
- if (!skb2)
- return -ENOMEM;
-
- if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET)
- reset = true;
-
- if (reset) {
- const struct nftables_pernet *nft_net;
- char *buf;
-
- nft_net = nft_pernet(net);
- buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, nft_net->base_seq);
-
- audit_log_nfcfg(buf,
- family,
- 1,
- AUDIT_NFT_OP_OBJ_RESET,
- GFP_ATOMIC);
- kfree(buf);
- }
-
- err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid,
- info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0,
- family, table, obj, reset);
- if (err < 0)
- goto err_fill_obj_info;
-
- return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid);
-
-err_fill_obj_info:
- kfree_skb(skb2);
- return err;
+ return nfnetlink_unicast(skb2, net, portid);
}
static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj)
@@ -9410,7 +9467,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
.policy = nft_obj_policy,
},
[NFT_MSG_GETOBJ_RESET] = {
- .call = nf_tables_getobj,
+ .call = nf_tables_getobj_reset,
.type = NFNL_CB_RCU,
.attr_count = NFTA_OBJ_MAX,
.policy = nft_obj_policy,
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 4abf660..932b3dd 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -427,8 +427,10 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
nfnl_unlock(subsys_id);
- if (nlh->nlmsg_flags & NLM_F_ACK)
+ if (nlh->nlmsg_flags & NLM_F_ACK) {
+ memset(&extack, 0, sizeof(extack));
nfnl_err_add(&err_list, nlh, 0, &extack);
+ }
while (skb->len >= nlmsg_total_size(0)) {
int msglen, type;
@@ -577,6 +579,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
ss->abort(net, oskb, NFNL_ABORT_NONE);
netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL);
} else if (nlh->nlmsg_flags & NLM_F_ACK) {
+ memset(&extack, 0, sizeof(extack));
nfnl_err_add(&err_list, nlh, 0, &extack);
}
} else {
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 55e28e1..e0716da 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -820,10 +820,41 @@ static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry)
{
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
static const unsigned long flags = IPS_CONFIRMED | IPS_DYING;
- const struct nf_conn *ct = (void *)skb_nfct(entry->skb);
+ struct nf_conn *ct = (void *)skb_nfct(entry->skb);
+ unsigned long status;
+ unsigned int use;
- if (ct && ((ct->status & flags) == IPS_DYING))
+ if (!ct)
+ return false;
+
+ status = READ_ONCE(ct->status);
+ if ((status & flags) == IPS_DYING)
return true;
+
+ if (status & IPS_CONFIRMED)
+ return false;
+
+ /* in some cases skb_clone() can occur after initial conntrack
+ * pickup, but conntrack assumes exclusive skb->_nfct ownership for
+ * unconfirmed entries.
+ *
+ * This happens for br_netfilter and with ip multicast routing.
+ * We can't be solved with serialization here because one clone could
+ * have been queued for local delivery.
+ */
+ use = refcount_read(&ct->ct_general.use);
+ if (likely(use == 1))
+ return false;
+
+ /* Can't decrement further? Exclusive ownership. */
+ if (!refcount_dec_not_one(&ct->ct_general.use))
+ return false;
+
+ skb_set_nfct(entry->skb, 0);
+ /* No nf_ct_put(): we already decremented .use and it cannot
+ * drop down to 0.
+ */
+ return true;
#endif
return false;
}
diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c
index 291ed20..eab0dc6 100644
--- a/net/netfilter/nft_counter.c
+++ b/net/netfilter/nft_counter.c
@@ -107,11 +107,16 @@ static void nft_counter_reset(struct nft_counter_percpu_priv *priv,
struct nft_counter *total)
{
struct nft_counter *this_cpu;
+ seqcount_t *myseq;
local_bh_disable();
this_cpu = this_cpu_ptr(priv->counter);
+ myseq = this_cpu_ptr(&nft_counter_seq);
+
+ write_seqcount_begin(myseq);
this_cpu->packets -= total->packets;
this_cpu->bytes -= total->bytes;
+ write_seqcount_end(myseq);
local_bh_enable();
}
@@ -265,7 +270,7 @@ static void nft_counter_offload_stats(struct nft_expr *expr,
struct nft_counter *this_cpu;
seqcount_t *myseq;
- preempt_disable();
+ local_bh_disable();
this_cpu = this_cpu_ptr(priv->counter);
myseq = this_cpu_ptr(&nft_counter_seq);
@@ -273,7 +278,7 @@ static void nft_counter_offload_stats(struct nft_expr *expr,
this_cpu->packets += stats->pkts;
this_cpu->bytes += stats->bytes;
write_seqcount_end(myseq);
- preempt_enable();
+ local_bh_enable();
}
void nft_counter_init_seqcount(void)
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 99d7254..78d9961 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -2706,7 +2706,7 @@ static struct pernet_operations ovs_net_ops = {
};
static const char * const ovs_drop_reasons[] = {
-#define S(x) (#x),
+#define S(x) [(x) & ~SKB_DROP_REASON_SUBSYS_MASK] = (#x),
OVS_DROP_REASONS(S)
#undef S
};
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 2389747..19a49af 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -663,7 +663,9 @@ static struct sk_buff *fq_dequeue(struct Qdisc *sch)
pband = &q->band_flows[q->band_nr];
pband->credit = min(pband->credit + pband->quantum,
pband->quantum);
- goto begin;
+ if (pband->credit > 0)
+ goto begin;
+ retry = 0;
}
if (q->time_next_delayed_flow != ~0ULL)
qdisc_watchdog_schedule_range_ns(&q->watchdog,
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index edc7296..0f8d581 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -446,12 +446,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct netem_sched_data *q = qdisc_priv(sch);
/* We don't fill cb now as skb_unshare() may invalidate it */
struct netem_skb_cb *cb;
- struct sk_buff *skb2;
+ struct sk_buff *skb2 = NULL;
struct sk_buff *segs = NULL;
unsigned int prev_len = qdisc_pkt_len(skb);
int count = 1;
- int rc = NET_XMIT_SUCCESS;
- int rc_drop = NET_XMIT_DROP;
/* Do not fool qdisc_drop_all() */
skb->prev = NULL;
@@ -480,19 +478,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
skb_orphan_partial(skb);
/*
- * If we need to duplicate packet, then re-insert at top of the
- * qdisc tree, since parent queuer expects that only one
- * skb will be queued.
+ * If we need to duplicate packet, then clone it before
+ * original is modified.
*/
- if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) {
- struct Qdisc *rootq = qdisc_root_bh(sch);
- u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
-
- q->duplicate = 0;
- rootq->enqueue(skb2, rootq, to_free);
- q->duplicate = dupsave;
- rc_drop = NET_XMIT_SUCCESS;
- }
+ if (count > 1)
+ skb2 = skb_clone(skb, GFP_ATOMIC);
/*
* Randomized packet corruption.
@@ -504,7 +494,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
if (skb_is_gso(skb)) {
skb = netem_segment(skb, sch, to_free);
if (!skb)
- return rc_drop;
+ goto finish_segs;
+
segs = skb->next;
skb_mark_not_on_list(skb);
qdisc_skb_cb(skb)->pkt_len = skb->len;
@@ -530,7 +521,24 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
/* re-link segs, so that qdisc_drop_all() frees them all */
skb->next = segs;
qdisc_drop_all(skb, sch, to_free);
- return rc_drop;
+ if (skb2)
+ __qdisc_drop(skb2, to_free);
+ return NET_XMIT_DROP;
+ }
+
+ /*
+ * If doing duplication then re-insert at top of the
+ * qdisc tree, since parent queuer expects that only one
+ * skb will be queued.
+ */
+ if (skb2) {
+ struct Qdisc *rootq = qdisc_root_bh(sch);
+ u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
+
+ q->duplicate = 0;
+ rootq->enqueue(skb2, rootq, to_free);
+ q->duplicate = dupsave;
+ skb2 = NULL;
}
qdisc_qstats_backlog_inc(sch, skb);
@@ -601,9 +609,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
}
finish_segs:
+ if (skb2)
+ __qdisc_drop(skb2, to_free);
+
if (segs) {
unsigned int len, last_len;
- int nb;
+ int rc, nb;
len = skb ? skb->len : 0;
nb = skb ? 1 : 0;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 5adf0c0..7d315a1 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -2260,12 +2260,6 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook(
}
}
- /* Update socket peer label if first association. */
- if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) {
- sctp_association_free(new_asoc);
- return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
- }
-
/* Set temp so that it won't be added into hashtable */
new_asoc->temp = 1;
@@ -2274,6 +2268,22 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook(
*/
action = sctp_tietags_compare(new_asoc, asoc);
+ /* In cases C and E the association doesn't enter the ESTABLISHED
+ * state, so there is no need to call security_sctp_assoc_request().
+ */
+ switch (action) {
+ case 'A': /* Association restart. */
+ case 'B': /* Collision case B. */
+ case 'D': /* Collision case D. */
+ /* Update socket peer label if first association. */
+ if (security_sctp_assoc_request((struct sctp_association *)asoc,
+ chunk->head_skb ?: chunk->skb)) {
+ sctp_association_free(new_asoc);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+ }
+ break;
+ }
+
switch (action) {
case 'A': /* Association restart. */
retval = sctp_sf_do_dupcook_a(net, ep, asoc, chunk, commands,
diff --git a/net/sunrpc/xprtrdma/ib_client.c b/net/sunrpc/xprtrdma/ib_client.c
index a938c19..8507cd4 100644
--- a/net/sunrpc/xprtrdma/ib_client.c
+++ b/net/sunrpc/xprtrdma/ib_client.c
@@ -62,10 +62,11 @@ int rpcrdma_rn_register(struct ib_device *device,
if (!rd || test_bit(RPCRDMA_RD_F_REMOVING, &rd->rd_flags))
return -ENETUNREACH;
- kref_get(&rd->rd_kref);
if (xa_alloc(&rd->rd_xa, &rn->rn_index, rn, xa_limit_32b, GFP_KERNEL) < 0)
return -ENOMEM;
+ kref_get(&rd->rd_kref);
rn->rn_done = done;
+ trace_rpcrdma_client_register(device, rn);
return 0;
}
@@ -91,6 +92,7 @@ void rpcrdma_rn_unregister(struct ib_device *device,
if (!rd)
return;
+ trace_rpcrdma_client_unregister(device, rn);
xa_erase(&rd->rd_xa, rn->rn_index);
kref_put(&rd->rd_kref, rpcrdma_rn_release);
}
@@ -111,7 +113,7 @@ static int rpcrdma_add_one(struct ib_device *device)
return -ENOMEM;
kref_init(&rd->rd_kref);
- xa_init_flags(&rd->rd_xa, XA_FLAGS_ALLOC1);
+ xa_init_flags(&rd->rd_xa, XA_FLAGS_ALLOC);
rd->rd_device = device;
init_completion(&rd->rd_done);
ib_set_client_data(device, &rpcrdma_ib_client, rd);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 4b04028..0ff9b2d 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1270,25 +1270,28 @@ static int vsock_dgram_connect(struct socket *sock,
return err;
}
+int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
+ size_t len, int flags)
+{
+ struct sock *sk = sock->sk;
+ struct vsock_sock *vsk = vsock_sk(sk);
+
+ return vsk->transport->dgram_dequeue(vsk, msg, len, flags);
+}
+
int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
size_t len, int flags)
{
#ifdef CONFIG_BPF_SYSCALL
+ struct sock *sk = sock->sk;
const struct proto *prot;
-#endif
- struct vsock_sock *vsk;
- struct sock *sk;
- sk = sock->sk;
- vsk = vsock_sk(sk);
-
-#ifdef CONFIG_BPF_SYSCALL
prot = READ_ONCE(sk->sk_prot);
if (prot != &vsock_proto)
return prot->recvmsg(sk, msg, len, flags, NULL);
#endif
- return vsk->transport->dgram_dequeue(vsk, msg, len, flags);
+ return __vsock_dgram_recvmsg(sock, msg, len, flags);
}
EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg);
@@ -2174,15 +2177,12 @@ static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg,
}
int
-vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
- int flags)
+__vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+ int flags)
{
struct sock *sk;
struct vsock_sock *vsk;
const struct vsock_transport *transport;
-#ifdef CONFIG_BPF_SYSCALL
- const struct proto *prot;
-#endif
int err;
sk = sock->sk;
@@ -2233,14 +2233,6 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
goto out;
}
-#ifdef CONFIG_BPF_SYSCALL
- prot = READ_ONCE(sk->sk_prot);
- if (prot != &vsock_proto) {
- release_sock(sk);
- return prot->recvmsg(sk, msg, len, flags, NULL);
- }
-#endif
-
if (sk->sk_type == SOCK_STREAM)
err = __vsock_stream_recvmsg(sk, msg, len, flags);
else
@@ -2250,6 +2242,22 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
release_sock(sk);
return err;
}
+
+int
+vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+ int flags)
+{
+#ifdef CONFIG_BPF_SYSCALL
+ struct sock *sk = sock->sk;
+ const struct proto *prot;
+
+ prot = READ_ONCE(sk->sk_prot);
+ if (prot != &vsock_proto)
+ return prot->recvmsg(sk, msg, len, flags, NULL);
+#endif
+
+ return __vsock_connectible_recvmsg(sock, msg, len, flags);
+}
EXPORT_SYMBOL_GPL(vsock_connectible_recvmsg);
static int vsock_set_rcvlowat(struct sock *sk, int val)
diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c
index a3c9754..c42c5cc1 100644
--- a/net/vmw_vsock/vsock_bpf.c
+++ b/net/vmw_vsock/vsock_bpf.c
@@ -64,9 +64,9 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int
int err;
if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)
- err = vsock_connectible_recvmsg(sock, msg, len, flags);
+ err = __vsock_connectible_recvmsg(sock, msg, len, flags);
else if (sk->sk_type == SOCK_DGRAM)
- err = vsock_dgram_recvmsg(sock, msg, len, flags);
+ err = __vsock_dgram_recvmsg(sock, msg, len, flags);
else
err = -EPROTOTYPE;
diff --git a/rust/Makefile b/rust/Makefile
index 1f10f92..8de3ebb 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -227,7 +227,7 @@
-fno-reorder-blocks -fno-allow-store-data-races -fasan-shadow-offset=% \
-fzero-call-used-regs=% -fno-stack-clash-protection \
-fno-inline-functions-called-once -fsanitize=bounds-strict \
- -fstrict-flex-arrays=% \
+ -fstrict-flex-arrays=% -fmin-function-alignment=% \
--param=% --param asan-%
# Derived from `scripts/Makefile.clang`.
@@ -350,12 +350,12 @@
$(Q)$(srctree)/scripts/generate_rust_analyzer.py \
--cfgs='core=$(core-cfgs)' --cfgs='alloc=$(alloc-cfgs)' \
$(realpath $(srctree)) $(realpath $(objtree)) \
- $(RUST_LIB_SRC) $(KBUILD_EXTMOD) > \
+ $(rustc_sysroot) $(RUST_LIB_SRC) $(KBUILD_EXTMOD) > \
$(if $(KBUILD_EXTMOD),$(extmod_prefix),$(objtree))/rust-project.json
redirect-intrinsics = \
- __addsf3 __eqsf2 __gesf2 __lesf2 __ltsf2 __mulsf3 __nesf2 __unordsf2 \
- __adddf3 __ledf2 __ltdf2 __muldf3 __unorddf2 \
+ __addsf3 __eqsf2 __extendsfdf2 __gesf2 __lesf2 __ltsf2 __mulsf3 __nesf2 __truncdfsf2 __unordsf2 \
+ __adddf3 __eqdf2 __ledf2 __ltdf2 __muldf3 __unorddf2 \
__muloti4 __multi3 \
__udivmodti4 __udivti3 __umodti3
diff --git a/rust/compiler_builtins.rs b/rust/compiler_builtins.rs
index bba2922..f14b8d7 100644
--- a/rust/compiler_builtins.rs
+++ b/rust/compiler_builtins.rs
@@ -40,16 +40,19 @@ pub extern "C" fn $ident() {
define_panicking_intrinsics!("`f32` should not be used", {
__addsf3,
__eqsf2,
+ __extendsfdf2,
__gesf2,
__lesf2,
__ltsf2,
__mulsf3,
__nesf2,
+ __truncdfsf2,
__unordsf2,
});
define_panicking_intrinsics!("`f64` should not be used", {
__adddf3,
+ __eqdf2,
__ledf2,
__ltdf2,
__muldf3,
diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs
index 159e752..5be0cb9 100644
--- a/rust/macros/lib.rs
+++ b/rust/macros/lib.rs
@@ -94,7 +94,7 @@
/// - `license`: ASCII string literal of the license of the kernel module (required).
/// - `alias`: array of ASCII string literals of the alias names of the kernel module.
/// - `firmware`: array of ASCII string literals of the firmware files of
-/// the kernel module.
+/// the kernel module.
#[proc_macro]
pub fn module(ts: TokenStream) -> TokenStream {
module::module(ts)
diff --git a/samples/trace_events/trace_custom_sched.c b/samples/trace_events/trace_custom_sched.c
index b99d9ab..dd409b7 100644
--- a/samples/trace_events/trace_custom_sched.c
+++ b/samples/trace_events/trace_custom_sched.c
@@ -8,7 +8,6 @@
#define pr_fmt(fmt) fmt
#include <linux/trace_events.h>
-#include <linux/version.h>
#include <linux/module.h>
#include <linux/sched.h>
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index efacca6..a5ac8ed 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -487,7 +487,7 @@
need-modorder=$(if $(filter $@/modules.order, $(subdir-modorder)),1) \
$(filter $@/%, $(single-subdir-goals))
-# Add FORCE to the prequisites of a target to force it to be always rebuilt.
+# Add FORCE to the prerequisites of a target to force it to be always rebuilt.
# ---------------------------------------------------------------------------
PHONY += FORCE
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index fe3668d..207325e 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -400,26 +400,23 @@
$(obj)/%.dtbo.S: $(obj)/%.dtbo FORCE
$(call if_changed,wrap_S_dtb)
-quiet_cmd_dtc = DTC $@
+quiet_dtb_check_tag = $(if $(dtb-check-enabled),[C], )
+cmd_dtb_check = $(if $(dtb-check-enabled),; $(DT_CHECKER) $(DT_CHECKER_FLAGS) -u $(srctree)/$(DT_BINDING_DIR) -p $(DT_TMP_SCHEMA) $@ || true)
+
+quiet_cmd_dtc = DTC $(quiet_dtb_check_tag) $@
cmd_dtc = $(HOSTCC) -E $(dtc_cpp_flags) -x assembler-with-cpp -o $(dtc-tmp) $< ; \
$(DTC) -o $@ -b 0 \
$(addprefix -i,$(dir $<) $(DTC_INCLUDE)) $(DTC_FLAGS) \
-d $(depfile).dtc.tmp $(dtc-tmp) ; \
- cat $(depfile).pre.tmp $(depfile).dtc.tmp > $(depfile)
-
-DT_CHECK_CMD = $(DT_CHECKER) $(DT_CHECKER_FLAGS) -u $(srctree)/$(DT_BINDING_DIR) -p $(DT_TMP_SCHEMA)
+ cat $(depfile).pre.tmp $(depfile).dtc.tmp > $(depfile) \
+ $(cmd_dtb_check)
# NOTE:
# Do not replace $(filter %.dtb %.dtbo, $^) with $(real-prereqs). When a single
# DTB is turned into a multi-blob DTB, $^ will contain header file dependencies
# recorded in the .*.cmd file.
-ifneq ($(CHECK_DTBS),)
-quiet_cmd_fdtoverlay = DTOVLCH $@
- cmd_fdtoverlay = $(objtree)/scripts/dtc/fdtoverlay -o $@ -i $(filter %.dtb %.dtbo, $^) ; $(DT_CHECK_CMD) $@ || true
-else
-quiet_cmd_fdtoverlay = DTOVL $@
- cmd_fdtoverlay = $(objtree)/scripts/dtc/fdtoverlay -o $@ -i $(filter %.dtb %.dtbo, $^)
-endif
+quiet_cmd_fdtoverlay = OVL $(quiet_dtb_check_tag) $@
+ cmd_fdtoverlay = $(objtree)/scripts/dtc/fdtoverlay -o $@ -i $(filter %.dtb %.dtbo, $^) $(cmd_dtb_check)
$(multi-dtb-y): FORCE
$(call if_changed,fdtoverlay)
@@ -430,16 +427,11 @@
DT_CHECKER_FLAGS ?= $(if $(DT_SCHEMA_FILES),-l $(DT_SCHEMA_FILES),-m)
DT_BINDING_DIR := Documentation/devicetree/bindings
DT_TMP_SCHEMA := $(objtree)/$(DT_BINDING_DIR)/processed-schema.json
-
-quiet_cmd_dtb = DTC_CHK $@
- cmd_dtb = $(cmd_dtc) ; $(DT_CHECK_CMD) $@ || true
-else
-quiet_cmd_dtb = $(quiet_cmd_dtc)
- cmd_dtb = $(cmd_dtc)
+dtb-check-enabled = $(if $(filter %.dtb, $@),y)
endif
$(obj)/%.dtb: $(obj)/%.dts $(DTC) $(DT_TMP_SCHEMA) FORCE
- $(call if_changed_dep,dtb)
+ $(call if_changed_dep,dtc)
$(obj)/%.dtbo: $(src)/%.dtso $(DTC) FORCE
$(call if_changed_dep,dtc)
diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
index 1fa98b5..306a6bb 100644
--- a/scripts/Makefile.modfinal
+++ b/scripts/Makefile.modfinal
@@ -62,7 +62,7 @@
targets += $(modules:%.o=%.ko) $(modules:%.o=%.mod.o)
-# Add FORCE to the prequisites of a target to force it to be always rebuilt.
+# Add FORCE to the prerequisites of a target to force it to be always rebuilt.
# ---------------------------------------------------------------------------
PHONY += FORCE
diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
index 49946cb9..5ceecbe 100644
--- a/scripts/Makefile.vmlinux
+++ b/scripts/Makefile.vmlinux
@@ -33,7 +33,7 @@
vmlinux: scripts/link-vmlinux.sh vmlinux.o $(KBUILD_LDS) FORCE
+$(call if_changed_dep,link_vmlinux)
-# Add FORCE to the prequisites of a target to force it to be always rebuilt.
+# Add FORCE to the prerequisites of a target to force it to be always rebuilt.
# ---------------------------------------------------------------------------
PHONY += FORCE
diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o
index 6de2979..d64070b 100644
--- a/scripts/Makefile.vmlinux_o
+++ b/scripts/Makefile.vmlinux_o
@@ -87,7 +87,7 @@
modules.builtin: modules.builtin.modinfo FORCE
$(call if_changed,modules_builtin)
-# Add FORCE to the prequisites of a target to force it to be always rebuilt.
+# Add FORCE to the prerequisites of a target to force it to be always rebuilt.
# ---------------------------------------------------------------------------
PHONY += FORCE
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 39032224..4427572 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -4015,16 +4015,6 @@
}
}
-# Block comment styles
-# Networking with an initial /*
- if ($realfile =~ m@^(drivers/net/|net/)@ &&
- $prevrawline =~ /^\+[ \t]*\/\*[ \t]*$/ &&
- $rawline =~ /^\+[ \t]*\*/ &&
- $realline > 3) { # Do not warn about the initial copyright comment block after SPDX-License-Identifier
- WARN("NETWORKING_BLOCK_COMMENT_STYLE",
- "networking block comments don't use an empty /* line, use /* Comment...\n" . $hereprev);
- }
-
# Block comments use * on subsequent lines
if ($prevline =~ /$;[ \t]*$/ && #ends in comment
$prevrawline =~ /^\+.*?\/\*/ && #starting /*
diff --git a/scripts/gcc-plugins/randomize_layout_plugin.c b/scripts/gcc-plugins/randomize_layout_plugin.c
index 746ff2d..5694df3 100644
--- a/scripts/gcc-plugins/randomize_layout_plugin.c
+++ b/scripts/gcc-plugins/randomize_layout_plugin.c
@@ -19,10 +19,6 @@
#include "gcc-common.h"
#include "randomize_layout_seed.h"
-#if BUILDING_GCC_MAJOR < 4 || (BUILDING_GCC_MAJOR == 4 && BUILDING_GCC_MINOR < 7)
-#error "The RANDSTRUCT plugin requires GCC 4.7 or newer."
-#endif
-
#define ORIG_TYPE_NAME(node) \
(TYPE_NAME(TYPE_MAIN_VARIANT(node)) != NULL_TREE ? ((const unsigned char *)IDENTIFIER_POINTER(TYPE_NAME(TYPE_MAIN_VARIANT(node)))) : (const unsigned char *)"anonymous")
diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py
index f270c7b..d2bc63c 100755
--- a/scripts/generate_rust_analyzer.py
+++ b/scripts/generate_rust_analyzer.py
@@ -145,6 +145,7 @@
parser.add_argument('--cfgs', action='append', default=[])
parser.add_argument("srctree", type=pathlib.Path)
parser.add_argument("objtree", type=pathlib.Path)
+ parser.add_argument("sysroot", type=pathlib.Path)
parser.add_argument("sysroot_src", type=pathlib.Path)
parser.add_argument("exttree", type=pathlib.Path, nargs="?")
args = parser.parse_args()
@@ -154,9 +155,12 @@
level=logging.INFO if args.verbose else logging.WARNING
)
+ # Making sure that the `sysroot` and `sysroot_src` belong to the same toolchain.
+ assert args.sysroot in args.sysroot_src.parents
+
rust_project = {
"crates": generate_crates(args.srctree, args.objtree, args.sysroot_src, args.exttree, args.cfgs),
- "sysroot_src": str(args.sysroot_src),
+ "sysroot": str(args.sysroot),
}
json.dump(rust_project, sys.stdout, sort_keys=True, indent=4)
diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs
index 87f3492..404edf7 100644
--- a/scripts/generate_rust_target.rs
+++ b/scripts/generate_rust_target.rs
@@ -162,7 +162,7 @@ fn main() {
"data-layout",
"e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128",
);
- let mut features = "-3dnow,-3dnowa,-mmx,+soft-float".to_string();
+ let mut features = "-mmx,+soft-float".to_string();
if cfg.has("MITIGATION_RETPOLINE") {
features += ",+retpoline-external-thunk";
}
@@ -179,7 +179,7 @@ fn main() {
"data-layout",
"e-m:e-p:32:32-p270:32:32-p271:32:32-p272:64:64-i128:128-f64:32:64-f80:32-n8:16:32-S128",
);
- let mut features = "-3dnow,-3dnowa,-mmx,+soft-float".to_string();
+ let mut features = "-mmx,+soft-float".to_string();
if cfg.has("MITIGATION_RETPOLINE") {
features += ",+retpoline-external-thunk";
}
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 0ed8734..123dab0 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -5,8 +5,7 @@
* This software may be used and distributed according to the terms
* of the GNU General Public License, incorporated herein by reference.
*
- * Usage: kallsyms [--all-symbols] [--absolute-percpu]
- * [--lto-clang] in.map > out.S
+ * Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S
*
* Table compression uses all the unused char codes on the symbols and
* maps these to the most used substrings (tokens). For instance, it might
@@ -62,7 +61,6 @@ static struct sym_entry **table;
static unsigned int table_size, table_cnt;
static int all_symbols;
static int absolute_percpu;
-static int lto_clang;
static int token_profit[0x10000];
@@ -73,8 +71,7 @@ static unsigned char best_table_len[256];
static void usage(void)
{
- fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] "
- "[--lto-clang] in.map > out.S\n");
+ fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S\n");
exit(1);
}
@@ -344,25 +341,6 @@ static bool symbol_absolute(const struct sym_entry *s)
return s->percpu_absolute;
}
-static void cleanup_symbol_name(char *s)
-{
- char *p;
-
- /*
- * ASCII[.] = 2e
- * ASCII[0-9] = 30,39
- * ASCII[A-Z] = 41,5a
- * ASCII[_] = 5f
- * ASCII[a-z] = 61,7a
- *
- * As above, replacing the first '.' in ".llvm." with '\0' does not
- * affect the main sorting, but it helps us with subsorting.
- */
- p = strstr(s, ".llvm.");
- if (p)
- *p = '\0';
-}
-
static int compare_names(const void *a, const void *b)
{
int ret;
@@ -526,10 +504,6 @@ static void write_src(void)
output_address(relative_base);
printf("\n");
- if (lto_clang)
- for (i = 0; i < table_cnt; i++)
- cleanup_symbol_name((char *)table[i]->sym);
-
sort_symbols_by_name();
output_label("kallsyms_seqs_of_names");
for (i = 0; i < table_cnt; i++)
@@ -807,7 +781,6 @@ int main(int argc, char **argv)
static const struct option long_options[] = {
{"all-symbols", no_argument, &all_symbols, 1},
{"absolute-percpu", no_argument, &absolute_percpu, 1},
- {"lto-clang", no_argument, <o_clang, 1},
{},
};
diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh
index 902eb42..0b79524 100755
--- a/scripts/kconfig/merge_config.sh
+++ b/scripts/kconfig/merge_config.sh
@@ -167,6 +167,8 @@
sed -i "/$CFG[ =]/d" $MERGE_FILE
fi
done
+ # In case the previous file lacks a new line at the end
+ echo >> $TMP_FILE
cat $MERGE_FILE >> $TMP_FILE
done
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index f7b2503..070a319 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -156,10 +156,6 @@
kallsymopt="${kallsymopt} --absolute-percpu"
fi
- if is_enabled CONFIG_LTO_CLANG; then
- kallsymopt="${kallsymopt} --lto-clang"
- fi
-
info KSYMS "${2}.S"
scripts/kallsyms ${kallsymopt} "${1}" > "${2}.S"
@@ -219,7 +215,8 @@
strip_debug=
if is_enabled CONFIG_KALLSYMS; then
- kallsyms /dev/null .tmp_vmlinux0.kallsyms
+ truncate -s0 .tmp_vmlinux.kallsyms0.syms
+ kallsyms .tmp_vmlinux.kallsyms0.syms .tmp_vmlinux0.kallsyms
fi
if is_enabled CONFIG_KALLSYMS || is_enabled CONFIG_DEBUG_INFO_BTF; then
diff --git a/security/apparmor/policy_unpack_test.c b/security/apparmor/policy_unpack_test.c
index 874fcf9..c64733d 100644
--- a/security/apparmor/policy_unpack_test.c
+++ b/security/apparmor/policy_unpack_test.c
@@ -80,14 +80,14 @@ static struct aa_ext *build_aa_ext_struct(struct policy_unpack_fixture *puf,
*(buf + 1) = strlen(TEST_U32_NAME) + 1;
strscpy(buf + 3, TEST_U32_NAME, e->end - (void *)(buf + 3));
*(buf + 3 + strlen(TEST_U32_NAME) + 1) = AA_U32;
- *((u32 *)(buf + 3 + strlen(TEST_U32_NAME) + 2)) = TEST_U32_DATA;
+ *((__le32 *)(buf + 3 + strlen(TEST_U32_NAME) + 2)) = cpu_to_le32(TEST_U32_DATA);
buf = e->start + TEST_NAMED_U64_BUF_OFFSET;
*buf = AA_NAME;
*(buf + 1) = strlen(TEST_U64_NAME) + 1;
strscpy(buf + 3, TEST_U64_NAME, e->end - (void *)(buf + 3));
*(buf + 3 + strlen(TEST_U64_NAME) + 1) = AA_U64;
- *((u64 *)(buf + 3 + strlen(TEST_U64_NAME) + 2)) = TEST_U64_DATA;
+ *((__le64 *)(buf + 3 + strlen(TEST_U64_NAME) + 2)) = cpu_to_le64(TEST_U64_DATA);
buf = e->start + TEST_NAMED_BLOB_BUF_OFFSET;
*buf = AA_NAME;
@@ -103,7 +103,7 @@ static struct aa_ext *build_aa_ext_struct(struct policy_unpack_fixture *puf,
*(buf + 1) = strlen(TEST_ARRAY_NAME) + 1;
strscpy(buf + 3, TEST_ARRAY_NAME, e->end - (void *)(buf + 3));
*(buf + 3 + strlen(TEST_ARRAY_NAME) + 1) = AA_ARRAY;
- *((u16 *)(buf + 3 + strlen(TEST_ARRAY_NAME) + 2)) = TEST_ARRAY_SIZE;
+ *((__le16 *)(buf + 3 + strlen(TEST_ARRAY_NAME) + 2)) = cpu_to_le16(TEST_ARRAY_SIZE);
return e;
}
diff --git a/security/keys/trusted-keys/trusted_dcp.c b/security/keys/trusted-keys/trusted_dcp.c
index b5f81a0..4edc5bb 100644
--- a/security/keys/trusted-keys/trusted_dcp.c
+++ b/security/keys/trusted-keys/trusted_dcp.c
@@ -186,20 +186,21 @@ static int do_aead_crypto(u8 *in, u8 *out, size_t len, u8 *key, u8 *nonce,
return ret;
}
-static int decrypt_blob_key(u8 *key)
+static int decrypt_blob_key(u8 *encrypted_key, u8 *plain_key)
{
- return do_dcp_crypto(key, key, false);
+ return do_dcp_crypto(encrypted_key, plain_key, false);
}
-static int encrypt_blob_key(u8 *key)
+static int encrypt_blob_key(u8 *plain_key, u8 *encrypted_key)
{
- return do_dcp_crypto(key, key, true);
+ return do_dcp_crypto(plain_key, encrypted_key, true);
}
static int trusted_dcp_seal(struct trusted_key_payload *p, char *datablob)
{
struct dcp_blob_fmt *b = (struct dcp_blob_fmt *)p->blob;
int blen, ret;
+ u8 plain_blob_key[AES_KEYSIZE_128];
blen = calc_blob_len(p->key_len);
if (blen > MAX_BLOB_SIZE)
@@ -207,30 +208,36 @@ static int trusted_dcp_seal(struct trusted_key_payload *p, char *datablob)
b->fmt_version = DCP_BLOB_VERSION;
get_random_bytes(b->nonce, AES_KEYSIZE_128);
- get_random_bytes(b->blob_key, AES_KEYSIZE_128);
+ get_random_bytes(plain_blob_key, AES_KEYSIZE_128);
- ret = do_aead_crypto(p->key, b->payload, p->key_len, b->blob_key,
+ ret = do_aead_crypto(p->key, b->payload, p->key_len, plain_blob_key,
b->nonce, true);
if (ret) {
pr_err("Unable to encrypt blob payload: %i\n", ret);
- return ret;
+ goto out;
}
- ret = encrypt_blob_key(b->blob_key);
+ ret = encrypt_blob_key(plain_blob_key, b->blob_key);
if (ret) {
pr_err("Unable to encrypt blob key: %i\n", ret);
- return ret;
+ goto out;
}
- b->payload_len = get_unaligned_le32(&p->key_len);
+ put_unaligned_le32(p->key_len, &b->payload_len);
p->blob_len = blen;
- return 0;
+ ret = 0;
+
+out:
+ memzero_explicit(plain_blob_key, sizeof(plain_blob_key));
+
+ return ret;
}
static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob)
{
struct dcp_blob_fmt *b = (struct dcp_blob_fmt *)p->blob;
int blen, ret;
+ u8 plain_blob_key[AES_KEYSIZE_128];
if (b->fmt_version != DCP_BLOB_VERSION) {
pr_err("DCP blob has bad version: %i, expected %i\n",
@@ -248,14 +255,14 @@ static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob)
goto out;
}
- ret = decrypt_blob_key(b->blob_key);
+ ret = decrypt_blob_key(b->blob_key, plain_blob_key);
if (ret) {
pr_err("Unable to decrypt blob key: %i\n", ret);
goto out;
}
ret = do_aead_crypto(b->payload, p->key, p->key_len + DCP_BLOB_AUTHLEN,
- b->blob_key, b->nonce, false);
+ plain_blob_key, b->nonce, false);
if (ret) {
pr_err("Unwrap of DCP payload failed: %i\n", ret);
goto out;
@@ -263,6 +270,8 @@ static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob)
ret = 0;
out:
+ memzero_explicit(plain_blob_key, sizeof(plain_blob_key));
+
return ret;
}
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index 32eb67f..b49c448 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -330,12 +330,12 @@ static int avc_add_xperms_decision(struct avc_node *node,
{
struct avc_xperms_decision_node *dest_xpd;
- node->ae.xp_node->xp.len++;
dest_xpd = avc_xperms_decision_alloc(src->used);
if (!dest_xpd)
return -ENOMEM;
avc_copy_xperms_decision(&dest_xpd->xpd, src);
list_add(&dest_xpd->xpd_list, &node->ae.xp_node->xpd_head);
+ node->ae.xp_node->xp.len++;
return 0;
}
@@ -907,7 +907,11 @@ static int avc_update_node(u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid,
node->ae.avd.auditdeny &= ~perms;
break;
case AVC_CALLBACK_ADD_XPERMS:
- avc_add_xperms_decision(node, xpd);
+ rc = avc_add_xperms_decision(node, xpd);
+ if (rc) {
+ avc_node_kill(node);
+ goto out_unlock;
+ }
break;
}
avc_node_replace(node, orig);
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 55c78c3..400eca4 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3852,7 +3852,17 @@ static int selinux_file_mprotect(struct vm_area_struct *vma,
if (default_noexec &&
(prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) {
int rc = 0;
- if (vma_is_initial_heap(vma)) {
+ /*
+ * We don't use the vma_is_initial_heap() helper as it has
+ * a history of problems and is currently broken on systems
+ * where there is no heap, e.g. brk == start_brk. Before
+ * replacing the conditional below with vma_is_initial_heap(),
+ * or something similar, please ensure that the logic is the
+ * same as what we have below or you have tested every possible
+ * corner case you can think to test.
+ */
+ if (vma->vm_start >= vma->vm_mm->start_brk &&
+ vma->vm_end <= vma->vm_mm->brk) {
rc = avc_has_perm(sid, sid, SECCLASS_PROCESS,
PROCESS__EXECHEAP, NULL);
} else if (!vma->vm_file && (vma_is_initial_stack(vma) ||
@@ -6650,8 +6660,8 @@ static int selinux_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen
*/
static int selinux_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen)
{
- return __vfs_setxattr_noperm(&nop_mnt_idmap, dentry, XATTR_NAME_SELINUX,
- ctx, ctxlen, 0);
+ return __vfs_setxattr_locked(&nop_mnt_idmap, dentry, XATTR_NAME_SELINUX,
+ ctx, ctxlen, 0, NULL);
}
static int selinux_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen)
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 4164699..002a1b9 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -4880,8 +4880,8 @@ static int smack_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen)
static int smack_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen)
{
- return __vfs_setxattr_noperm(&nop_mnt_idmap, dentry, XATTR_NAME_SMACK,
- ctx, ctxlen, 0);
+ return __vfs_setxattr_locked(&nop_mnt_idmap, dentry, XATTR_NAME_SMACK,
+ ctx, ctxlen, 0, NULL);
}
static int smack_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen)
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 8c4ee50..6be548b 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -537,6 +537,9 @@ static struct snd_seq_client *get_event_dest_client(struct snd_seq_event *event,
return NULL;
if (! dest->accept_input)
goto __not_avail;
+ if (snd_seq_ev_is_ump(event))
+ return dest; /* ok - no filter checks */
+
if ((dest->filter & SNDRV_SEQ_FILTER_USE_EVENT) &&
! test_bit(event->type, dest->event_filter))
goto __not_avail;
diff --git a/sound/core/timer.c b/sound/core/timer.c
index d104adc..71a07c1 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -547,7 +547,7 @@ static int snd_timer_start1(struct snd_timer_instance *timeri,
/* check the actual time for the start tick;
* bail out as error if it's way too low (< 100us)
*/
- if (start) {
+ if (start && !(timer->hw.flags & SNDRV_TIMER_HW_SLAVE)) {
if ((u64)snd_timer_hw_resolution(timer) * ticks < 100000)
return -EINVAL;
}
diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c
index 3a92e98..d68bf75 100644
--- a/sound/pci/hda/cs35l41_hda.c
+++ b/sound/pci/hda/cs35l41_hda.c
@@ -134,7 +134,7 @@ static const struct reg_sequence cs35l41_hda_mute[] = {
};
static const struct cs_dsp_client_ops client_ops = {
- .control_remove = hda_cs_dsp_control_remove,
+ /* cs_dsp requires the client to provide this even if it is empty */
};
static int cs35l41_request_tuning_param_file(struct cs35l41_hda *cs35l41, char *tuning_filename,
diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c
index 31cc92b..e3ac0e2 100644
--- a/sound/pci/hda/cs35l56_hda.c
+++ b/sound/pci/hda/cs35l56_hda.c
@@ -413,7 +413,7 @@ static void cs35l56_hda_remove_controls(struct cs35l56_hda *cs35l56)
}
static const struct cs_dsp_client_ops cs35l56_hda_client_ops = {
- .control_remove = hda_cs_dsp_control_remove,
+ /* cs_dsp requires the client to provide this even if it is empty */
};
static int cs35l56_hda_request_firmware_file(struct cs35l56_hda *cs35l56,
@@ -1003,7 +1003,7 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int hid, int id)
goto err;
}
- cs35l56->base.cal_index = cs35l56->index;
+ cs35l56->base.cal_index = -1;
cs35l56_init_cs_dsp(&cs35l56->base, &cs35l56->cs_dsp);
cs35l56->cs_dsp.client_ops = &cs35l56_hda_client_ops;
diff --git a/sound/pci/hda/hda_component.c b/sound/pci/hda/hda_component.c
index 7b19cb3..b7dfdb1 100644
--- a/sound/pci/hda/hda_component.c
+++ b/sound/pci/hda/hda_component.c
@@ -141,8 +141,7 @@ int hda_component_manager_bind(struct hda_codec *cdc,
int ret;
/* Init shared and component specific data */
- memset(parent, 0, sizeof(*parent));
- mutex_init(&parent->mutex);
+ memset(parent->comps, 0, sizeof(parent->comps));
parent->codec = cdc;
mutex_lock(&parent->mutex);
@@ -164,6 +163,8 @@ int hda_component_manager_init(struct hda_codec *cdc,
struct hda_scodec_match *sm;
int ret, i;
+ mutex_init(&parent->mutex);
+
for (i = 0; i < count; i++) {
sm = devm_kmalloc(dev, sizeof(*sm), GFP_KERNEL);
if (!sm)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 480e82d..588738c 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -11,15 +11,18 @@
*/
#include <linux/acpi.h>
+#include <linux/cleanup.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/slab.h>
#include <linux/pci.h>
#include <linux/dmi.h>
#include <linux/module.h>
+#include <linux/i2c.h>
#include <linux/input.h>
#include <linux/leds.h>
#include <linux/ctype.h>
+#include <linux/spi/spi.h>
#include <sound/core.h>
#include <sound/jack.h>
#include <sound/hda_codec.h>
@@ -583,7 +586,6 @@ static void alc_shutup_pins(struct hda_codec *codec)
switch (codec->core.vendor_id) {
case 0x10ec0236:
case 0x10ec0256:
- case 0x10ec0257:
case 0x19e58326:
case 0x10ec0283:
case 0x10ec0285:
@@ -4928,6 +4930,30 @@ static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec,
}
}
+static void alc_hp_mute_disable(struct hda_codec *codec, unsigned int delay)
+{
+ if (delay <= 0)
+ delay = 75;
+ snd_hda_codec_write(codec, 0x21, 0,
+ AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
+ msleep(delay);
+ snd_hda_codec_write(codec, 0x21, 0,
+ AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0);
+ msleep(delay);
+}
+
+static void alc_hp_enable_unmute(struct hda_codec *codec, unsigned int delay)
+{
+ if (delay <= 0)
+ delay = 75;
+ snd_hda_codec_write(codec, 0x21, 0,
+ AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
+ msleep(delay);
+ snd_hda_codec_write(codec, 0x21, 0,
+ AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
+ msleep(delay);
+}
+
static const struct coef_fw alc225_pre_hsmode[] = {
UPDATE_COEF(0x4a, 1<<8, 0),
UPDATE_COEFEX(0x57, 0x05, 1<<14, 0),
@@ -5029,6 +5055,7 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
case 0x10ec0236:
case 0x10ec0256:
case 0x19e58326:
+ alc_hp_mute_disable(codec, 75);
alc_process_coef_fw(codec, coef0256);
break;
case 0x10ec0234:
@@ -5063,6 +5090,7 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
case 0x10ec0295:
case 0x10ec0289:
case 0x10ec0299:
+ alc_hp_mute_disable(codec, 75);
alc_process_coef_fw(codec, alc225_pre_hsmode);
alc_process_coef_fw(codec, coef0225);
break;
@@ -5288,6 +5316,7 @@ static void alc_headset_mode_default(struct hda_codec *codec)
case 0x10ec0299:
alc_process_coef_fw(codec, alc225_pre_hsmode);
alc_process_coef_fw(codec, coef0225);
+ alc_hp_enable_unmute(codec, 75);
break;
case 0x10ec0255:
alc_process_coef_fw(codec, coef0255);
@@ -5300,6 +5329,7 @@ static void alc_headset_mode_default(struct hda_codec *codec)
alc_write_coef_idx(codec, 0x45, 0xc089);
msleep(50);
alc_process_coef_fw(codec, coef0256);
+ alc_hp_enable_unmute(codec, 75);
break;
case 0x10ec0234:
case 0x10ec0274:
@@ -5397,6 +5427,7 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
case 0x10ec0256:
case 0x19e58326:
alc_process_coef_fw(codec, coef0256);
+ alc_hp_enable_unmute(codec, 75);
break;
case 0x10ec0234:
case 0x10ec0274:
@@ -5445,6 +5476,7 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
alc_process_coef_fw(codec, coef0225_2);
else
alc_process_coef_fw(codec, coef0225_1);
+ alc_hp_enable_unmute(codec, 75);
break;
case 0x10ec0867:
alc_update_coefex_idx(codec, 0x57, 0x5, 1<<14, 0);
@@ -5512,6 +5544,7 @@ static void alc_headset_mode_omtp(struct hda_codec *codec)
case 0x10ec0256:
case 0x19e58326:
alc_process_coef_fw(codec, coef0256);
+ alc_hp_enable_unmute(codec, 75);
break;
case 0x10ec0234:
case 0x10ec0274:
@@ -5549,6 +5582,7 @@ static void alc_headset_mode_omtp(struct hda_codec *codec)
case 0x10ec0289:
case 0x10ec0299:
alc_process_coef_fw(codec, coef0225);
+ alc_hp_enable_unmute(codec, 75);
break;
}
codec_dbg(codec, "Headset jack set to Nokia-style headset mode.\n");
@@ -5617,25 +5651,21 @@ static void alc_determine_headset_type(struct hda_codec *codec)
alc_write_coef_idx(codec, 0x06, 0x6104);
alc_write_coefex_idx(codec, 0x57, 0x3, 0x09a3);
- snd_hda_codec_write(codec, 0x21, 0,
- AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
- msleep(80);
- snd_hda_codec_write(codec, 0x21, 0,
- AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0);
-
alc_process_coef_fw(codec, coef0255);
msleep(300);
val = alc_read_coef_idx(codec, 0x46);
is_ctia = (val & 0x0070) == 0x0070;
-
+ if (!is_ctia) {
+ alc_write_coef_idx(codec, 0x45, 0xe089);
+ msleep(100);
+ val = alc_read_coef_idx(codec, 0x46);
+ if ((val & 0x0070) == 0x0070)
+ is_ctia = false;
+ else
+ is_ctia = true;
+ }
alc_write_coefex_idx(codec, 0x57, 0x3, 0x0da3);
alc_update_coefex_idx(codec, 0x57, 0x5, 1<<14, 0);
-
- snd_hda_codec_write(codec, 0x21, 0,
- AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
- msleep(80);
- snd_hda_codec_write(codec, 0x21, 0,
- AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
break;
case 0x10ec0234:
case 0x10ec0274:
@@ -5712,12 +5742,6 @@ static void alc_determine_headset_type(struct hda_codec *codec)
case 0x10ec0295:
case 0x10ec0289:
case 0x10ec0299:
- snd_hda_codec_write(codec, 0x21, 0,
- AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
- msleep(80);
- snd_hda_codec_write(codec, 0x21, 0,
- AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0);
-
alc_process_coef_fw(codec, alc225_pre_hsmode);
alc_update_coef_idx(codec, 0x67, 0xf000, 0x1000);
val = alc_read_coef_idx(codec, 0x45);
@@ -5734,15 +5758,19 @@ static void alc_determine_headset_type(struct hda_codec *codec)
val = alc_read_coef_idx(codec, 0x46);
is_ctia = (val & 0x00f0) == 0x00f0;
}
+ if (!is_ctia) {
+ alc_update_coef_idx(codec, 0x45, 0x3f<<10, 0x38<<10);
+ alc_update_coef_idx(codec, 0x49, 3<<8, 1<<8);
+ msleep(100);
+ val = alc_read_coef_idx(codec, 0x46);
+ if ((val & 0x00f0) == 0x00f0)
+ is_ctia = false;
+ else
+ is_ctia = true;
+ }
alc_update_coef_idx(codec, 0x4a, 7<<6, 7<<6);
alc_update_coef_idx(codec, 0x4a, 3<<4, 3<<4);
alc_update_coef_idx(codec, 0x67, 0xf000, 0x3000);
-
- snd_hda_codec_write(codec, 0x21, 0,
- AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
- msleep(80);
- snd_hda_codec_write(codec, 0x21, 0,
- AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
break;
case 0x10ec0867:
is_ctia = true;
@@ -6856,6 +6884,86 @@ static void comp_generic_fixup(struct hda_codec *cdc, int action, const char *bu
}
}
+static void cs35lxx_autodet_fixup(struct hda_codec *cdc,
+ const struct hda_fixup *fix,
+ int action)
+{
+ struct device *dev = hda_codec_dev(cdc);
+ struct acpi_device *adev;
+ struct fwnode_handle *fwnode __free(fwnode_handle) = NULL;
+ const char *bus = NULL;
+ static const struct {
+ const char *hid;
+ const char *name;
+ } acpi_ids[] = {{ "CSC3554", "cs35l54-hda" },
+ { "CSC3556", "cs35l56-hda" },
+ { "CSC3557", "cs35l57-hda" }};
+ char *match;
+ int i, count = 0, count_devindex = 0;
+
+ switch (action) {
+ case HDA_FIXUP_ACT_PRE_PROBE:
+ for (i = 0; i < ARRAY_SIZE(acpi_ids); ++i) {
+ adev = acpi_dev_get_first_match_dev(acpi_ids[i].hid, NULL, -1);
+ if (adev)
+ break;
+ }
+ if (!adev) {
+ dev_err(dev, "Failed to find ACPI entry for a Cirrus Amp\n");
+ return;
+ }
+
+ count = i2c_acpi_client_count(adev);
+ if (count > 0) {
+ bus = "i2c";
+ } else {
+ count = acpi_spi_count_resources(adev);
+ if (count > 0)
+ bus = "spi";
+ }
+
+ fwnode = fwnode_handle_get(acpi_fwnode_handle(adev));
+ acpi_dev_put(adev);
+
+ if (!bus) {
+ dev_err(dev, "Did not find any buses for %s\n", acpi_ids[i].hid);
+ return;
+ }
+
+ if (!fwnode) {
+ dev_err(dev, "Could not get fwnode for %s\n", acpi_ids[i].hid);
+ return;
+ }
+
+ /*
+ * When available the cirrus,dev-index property is an accurate
+ * count of the amps in a system and is used in preference to
+ * the count of bus devices that can contain additional address
+ * alias entries.
+ */
+ count_devindex = fwnode_property_count_u32(fwnode, "cirrus,dev-index");
+ if (count_devindex > 0)
+ count = count_devindex;
+
+ match = devm_kasprintf(dev, GFP_KERNEL, "-%%s:00-%s.%%d", acpi_ids[i].name);
+ if (!match)
+ return;
+ dev_info(dev, "Found %d %s on %s (%s)\n", count, acpi_ids[i].hid, bus, match);
+ comp_generic_fixup(cdc, action, bus, acpi_ids[i].hid, match, count);
+
+ break;
+ case HDA_FIXUP_ACT_FREE:
+ /*
+ * Pass the action on to comp_generic_fixup() so that
+ * hda_component_manager functions can be called in just once
+ * place. In this context the bus, hid, match_str or count
+ * values do not need to be calculated.
+ */
+ comp_generic_fixup(cdc, action, NULL, NULL, NULL, 0);
+ break;
+ }
+}
+
static void cs35l41_fixup_i2c_two(struct hda_codec *cdc, const struct hda_fixup *fix, int action)
{
comp_generic_fixup(cdc, action, "i2c", "CSC3551", "-%s:00-cs35l41-hda.%d", 2);
@@ -7528,6 +7636,7 @@ enum {
ALC256_FIXUP_CHROME_BOOK,
ALC287_FIXUP_LENOVO_14ARP8_LEGION_IAH7,
ALC287_FIXUP_LENOVO_SSID_17AA3820,
+ ALCXXX_FIXUP_CS35LXX,
};
/* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -9857,6 +9966,10 @@ static const struct hda_fixup alc269_fixups[] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc287_fixup_lenovo_ssid_17aa3820,
},
+ [ALCXXX_FIXUP_CS35LXX] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = cs35lxx_autodet_fixup,
+ },
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -10228,6 +10341,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x8c15, "HP Spectre x360 2-in-1 Laptop 14-eu0xxx", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX),
SND_PCI_QUIRK(0x103c, 0x8c16, "HP Spectre 16", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x103c, 0x8c17, "HP Spectre 16", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x103c, 0x8c21, "HP Pavilion Plus Laptop 14-ey0XXX", ALC245_FIXUP_HP_X360_MUTE_LEDS),
SND_PCI_QUIRK(0x103c, 0x8c46, "HP EliteBook 830 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8c47, "HP EliteBook 840 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8c48, "HP EliteBook 860 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
@@ -10266,11 +10380,23 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x8ca2, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8cbd, "HP Pavilion Aero Laptop 13-bg0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS),
SND_PCI_QUIRK(0x103c, 0x8cdd, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x103c, 0x8cde, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x103c, 0x8cdf, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8ce0, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8d01, "HP ZBook Power 14 G12", ALCXXX_FIXUP_CS35LXX),
+ SND_PCI_QUIRK(0x103c, 0x8d08, "HP EliteBook 1045 14 G12", ALCXXX_FIXUP_CS35LXX),
+ SND_PCI_QUIRK(0x103c, 0x8d85, "HP EliteBook 1040 14 G12", ALCXXX_FIXUP_CS35LXX),
+ SND_PCI_QUIRK(0x103c, 0x8d86, "HP Elite x360 1040 14 G12", ALCXXX_FIXUP_CS35LXX),
+ SND_PCI_QUIRK(0x103c, 0x8d8c, "HP EliteBook 830 13 G12", ALCXXX_FIXUP_CS35LXX),
+ SND_PCI_QUIRK(0x103c, 0x8d8d, "HP Elite x360 830 13 G12", ALCXXX_FIXUP_CS35LXX),
+ SND_PCI_QUIRK(0x103c, 0x8d8e, "HP EliteBook 840 14 G12", ALCXXX_FIXUP_CS35LXX),
+ SND_PCI_QUIRK(0x103c, 0x8d8f, "HP EliteBook 840 14 G12", ALCXXX_FIXUP_CS35LXX),
+ SND_PCI_QUIRK(0x103c, 0x8d90, "HP EliteBook 860 16 G12", ALCXXX_FIXUP_CS35LXX),
+ SND_PCI_QUIRK(0x103c, 0x8d91, "HP ZBook Firefly 14 G12", ALCXXX_FIXUP_CS35LXX),
+ SND_PCI_QUIRK(0x103c, 0x8d92, "HP ZBook Firefly 16 G12", ALCXXX_FIXUP_CS35LXX),
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),
@@ -10415,6 +10541,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x144d, 0xca03, "Samsung Galaxy Book2 Pro 360 (NP930QED)", ALC298_FIXUP_SAMSUNG_AMP),
SND_PCI_QUIRK(0x144d, 0xc868, "Samsung Galaxy Book2 Pro (NP930XED)", ALC298_FIXUP_SAMSUNG_AMP),
SND_PCI_QUIRK(0x144d, 0xc1ca, "Samsung Galaxy Book3 Pro 360 (NP960QFG-KB1US)", ALC298_FIXUP_SAMSUNG_AMP2),
+ SND_PCI_QUIRK(0x144d, 0xc1cc, "Samsung Galaxy Book3 Ultra (NT960XFH-XD92G))", ALC298_FIXUP_SAMSUNG_AMP2),
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),
diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c
index 49bd709..89d8235 100644
--- a/sound/pci/hda/tas2781_hda_i2c.c
+++ b/sound/pci/hda/tas2781_hda_i2c.c
@@ -2,10 +2,12 @@
//
// TAS2781 HDA I2C driver
//
-// Copyright 2023 Texas Instruments, Inc.
+// Copyright 2023 - 2024 Texas Instruments, Inc.
//
// Author: Shenghao Ding <shenghao-ding@ti.com>
+// Current maintainer: Baojun Xu <baojun.xu@ti.com>
+#include <asm/unaligned.h>
#include <linux/acpi.h>
#include <linux/crc8.h>
#include <linux/crc32.h>
@@ -519,20 +521,22 @@ static void tas2781_apply_calib(struct tasdevice_priv *tas_priv)
static const unsigned char rgno_array[CALIB_MAX] = {
0x74, 0x0c, 0x14, 0x70, 0x7c,
};
- unsigned char *data;
+ int offset = 0;
int i, j, rc;
+ __be32 data;
for (i = 0; i < tas_priv->ndev; i++) {
- data = tas_priv->cali_data.data +
- i * TASDEVICE_SPEAKER_CALIBRATION_SIZE;
for (j = 0; j < CALIB_MAX; j++) {
+ data = cpu_to_be32(
+ *(uint32_t *)&tas_priv->cali_data.data[offset]);
rc = tasdevice_dev_bulk_write(tas_priv, i,
TASDEVICE_REG(0, page_array[j], rgno_array[j]),
- &(data[4 * j]), 4);
+ (unsigned char *)&data, 4);
if (rc < 0)
dev_err(tas_priv->dev,
"chn %d calib %d bulk_wr err = %d\n",
i, j, rc);
+ offset += 4;
}
}
}
diff --git a/sound/soc/amd/acp/acp-legacy-mach.c b/sound/soc/amd/acp/acp-legacy-mach.c
index 47c3b5f..0d529e3 100644
--- a/sound/soc/amd/acp/acp-legacy-mach.c
+++ b/sound/soc/amd/acp/acp-legacy-mach.c
@@ -227,6 +227,8 @@ static const struct platform_device_id board_ids[] = {
},
{ }
};
+MODULE_DEVICE_TABLE(platform, board_ids);
+
static struct platform_driver acp_asoc_audio = {
.driver = {
.pm = &snd_soc_pm_ops,
diff --git a/sound/soc/amd/acp/acp-sof-mach.c b/sound/soc/amd/acp/acp-sof-mach.c
index fc59ea3..b3a702d 100644
--- a/sound/soc/amd/acp/acp-sof-mach.c
+++ b/sound/soc/amd/acp/acp-sof-mach.c
@@ -158,6 +158,8 @@ static const struct platform_device_id board_ids[] = {
},
{ }
};
+MODULE_DEVICE_TABLE(platform, board_ids);
+
static struct platform_driver acp_asoc_audio = {
.driver = {
.name = "sof_mach",
diff --git a/sound/soc/au1x/db1200.c b/sound/soc/au1x/db1200.c
index 83a75a3..81abe2e 100644
--- a/sound/soc/au1x/db1200.c
+++ b/sound/soc/au1x/db1200.c
@@ -44,6 +44,7 @@ static const struct platform_device_id db1200_pids[] = {
},
{},
};
+MODULE_DEVICE_TABLE(platform, db1200_pids);
/*------------------------- AC97 PART ---------------------------*/
diff --git a/sound/soc/codecs/cs-amp-lib-test.c b/sound/soc/codecs/cs-amp-lib-test.c
index 15f991b..8169ec8 100644
--- a/sound/soc/codecs/cs-amp-lib-test.c
+++ b/sound/soc/codecs/cs-amp-lib-test.c
@@ -38,6 +38,7 @@ static void cs_amp_lib_test_init_dummy_cal_blob(struct kunit *test, int num_amps
{
struct cs_amp_lib_test_priv *priv = test->priv;
unsigned int blob_size;
+ int i;
blob_size = offsetof(struct cirrus_amp_efi_data, data) +
sizeof(struct cirrus_amp_cal_data) * num_amps;
@@ -49,6 +50,14 @@ static void cs_amp_lib_test_init_dummy_cal_blob(struct kunit *test, int num_amps
priv->cal_blob->count = num_amps;
get_random_bytes(priv->cal_blob->data, sizeof(struct cirrus_amp_cal_data) * num_amps);
+
+ /* Ensure all timestamps are non-zero to mark the entry valid. */
+ for (i = 0; i < num_amps; i++)
+ priv->cal_blob->data[i].calTime[0] |= 1;
+
+ /* Ensure that all UIDs are non-zero and unique. */
+ for (i = 0; i < num_amps; i++)
+ *(u8 *)&priv->cal_blob->data[i].calTarget[0] = i + 1;
}
static u64 cs_amp_lib_test_get_target_uid(struct kunit *test)
diff --git a/sound/soc/codecs/cs-amp-lib.c b/sound/soc/codecs/cs-amp-lib.c
index 605964a..51b128c 100644
--- a/sound/soc/codecs/cs-amp-lib.c
+++ b/sound/soc/codecs/cs-amp-lib.c
@@ -182,6 +182,10 @@ static int _cs_amp_get_efi_calibration_data(struct device *dev, u64 target_uid,
for (i = 0; i < efi_data->count; ++i) {
u64 cal_target = cs_amp_cal_target_u64(&efi_data->data[i]);
+ /* Skip empty entries */
+ if (!efi_data->data[i].calTime[0] && !efi_data->data[i].calTime[1])
+ continue;
+
/* Skip entries with unpopulated silicon ID */
if (cal_target == 0)
continue;
@@ -193,7 +197,8 @@ static int _cs_amp_get_efi_calibration_data(struct device *dev, u64 target_uid,
}
}
- if (!cal && (amp_index >= 0) && (amp_index < efi_data->count)) {
+ if (!cal && (amp_index >= 0) && (amp_index < efi_data->count) &&
+ (efi_data->data[amp_index].calTime[0] || efi_data->data[amp_index].calTime[1])) {
u64 cal_target = cs_amp_cal_target_u64(&efi_data->data[amp_index]);
/*
diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c
index 60d366e..6400ac8 100644
--- a/sound/soc/codecs/cs42l42.c
+++ b/sound/soc/codecs/cs42l42.c
@@ -11,7 +11,6 @@
#include <linux/module.h>
#include <linux/moduleparam.h>
-#include <linux/version.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/delay.h>
diff --git a/sound/soc/codecs/lpass-macro-common.h b/sound/soc/codecs/lpass-macro-common.h
index 21cb30a..fb4b96c 100644
--- a/sound/soc/codecs/lpass-macro-common.h
+++ b/sound/soc/codecs/lpass-macro-common.h
@@ -49,6 +49,12 @@ static inline void lpass_macro_pds_exit_action(void *pds)
static inline const char *lpass_macro_get_codec_version_string(int version)
{
switch (version) {
+ case LPASS_CODEC_VERSION_1_0:
+ return "v1.0";
+ case LPASS_CODEC_VERSION_1_1:
+ return "v1.1";
+ case LPASS_CODEC_VERSION_1_2:
+ return "v1.2";
case LPASS_CODEC_VERSION_2_0:
return "v2.0";
case LPASS_CODEC_VERSION_2_1:
diff --git a/sound/soc/codecs/lpass-va-macro.c b/sound/soc/codecs/lpass-va-macro.c
index a62ccd0..8454193 100644
--- a/sound/soc/codecs/lpass-va-macro.c
+++ b/sound/soc/codecs/lpass-va-macro.c
@@ -1485,6 +1485,10 @@ static void va_macro_set_lpass_codec_version(struct va_macro *va)
if ((core_id_0 == 0x02) && (core_id_1 == 0x0F) && (core_id_2 == 0x80 || core_id_2 == 0x81))
version = LPASS_CODEC_VERSION_2_8;
+ if (version == LPASS_CODEC_VERSION_UNKNOWN)
+ dev_warn(va->dev, "Unknown Codec version, ID: %02x / %02x / %02x\n",
+ core_id_0, core_id_1, core_id_2);
+
lpass_macro_set_codec_version(version);
dev_dbg(va->dev, "LPASS Codec Version %s\n", lpass_macro_get_codec_version_string(version));
diff --git a/sound/soc/codecs/wcd937x.c b/sound/soc/codecs/wcd937x.c
index 13926f4..af296b7 100644
--- a/sound/soc/codecs/wcd937x.c
+++ b/sound/soc/codecs/wcd937x.c
@@ -242,10 +242,9 @@ static const struct regmap_irq_chip wcd937x_regmap_irq_chip = {
static void wcd937x_reset(struct wcd937x_priv *wcd937x)
{
- usleep_range(20, 30);
-
gpiod_set_value(wcd937x->reset_gpio, 1);
-
+ usleep_range(20, 30);
+ gpiod_set_value(wcd937x->reset_gpio, 0);
usleep_range(20, 30);
}
diff --git a/sound/soc/mediatek/mt8188/mt8188-afe-pcm.c b/sound/soc/mediatek/mt8188/mt8188-afe-pcm.c
index ccb6c1f..73e5c63 100644
--- a/sound/soc/mediatek/mt8188/mt8188-afe-pcm.c
+++ b/sound/soc/mediatek/mt8188/mt8188-afe-pcm.c
@@ -2748,6 +2748,7 @@ static bool mt8188_is_volatile_reg(struct device *dev, unsigned int reg)
case AFE_ASRC12_NEW_CON9:
case AFE_LRCK_CNT:
case AFE_DAC_MON0:
+ case AFE_DAC_CON0:
case AFE_DL2_CUR:
case AFE_DL3_CUR:
case AFE_DL6_CUR:
diff --git a/sound/soc/sof/amd/acp-dsp-offset.h b/sound/soc/sof/amd/acp-dsp-offset.h
index 59afbe2..072b703 100644
--- a/sound/soc/sof/amd/acp-dsp-offset.h
+++ b/sound/soc/sof/amd/acp-dsp-offset.h
@@ -76,13 +76,15 @@
#define DSP_SW_INTR_CNTL_OFFSET 0x0
#define DSP_SW_INTR_STAT_OFFSET 0x4
#define DSP_SW_INTR_TRIG_OFFSET 0x8
-#define ACP_ERROR_STATUS 0x18C4
+#define ACP3X_ERROR_STATUS 0x18C4
+#define ACP6X_ERROR_STATUS 0x1A4C
#define ACP3X_AXI2DAGB_SEM_0 0x1880
#define ACP5X_AXI2DAGB_SEM_0 0x1884
#define ACP6X_AXI2DAGB_SEM_0 0x1874
/* ACP common registers to report errors related to I2S & SoundWire interfaces */
-#define ACP_SW0_I2S_ERROR_REASON 0x18B4
+#define ACP3X_SW_I2S_ERROR_REASON 0x18C8
+#define ACP6X_SW0_I2S_ERROR_REASON 0x18B4
#define ACP_SW1_I2S_ERROR_REASON 0x1A50
/* Registers from ACP_SHA block */
diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c
index 74fd5f2..85b58c8 100644
--- a/sound/soc/sof/amd/acp.c
+++ b/sound/soc/sof/amd/acp.c
@@ -92,6 +92,7 @@ static int config_dma_channel(struct acp_dev_data *adata, unsigned int ch,
unsigned int idx, unsigned int dscr_count)
{
struct snd_sof_dev *sdev = adata->dev;
+ const struct sof_amd_acp_desc *desc = get_chip_info(sdev->pdata);
unsigned int val, status;
int ret;
@@ -102,7 +103,7 @@ static int config_dma_channel(struct acp_dev_data *adata, unsigned int ch,
val & (1 << ch), ACP_REG_POLL_INTERVAL,
ACP_REG_POLL_TIMEOUT_US);
if (ret < 0) {
- status = snd_sof_dsp_read(sdev, ACP_DSP_BAR, ACP_ERROR_STATUS);
+ status = snd_sof_dsp_read(sdev, ACP_DSP_BAR, desc->acp_error_stat);
val = snd_sof_dsp_read(sdev, ACP_DSP_BAR, ACP_DMA_ERR_STS_0 + ch * sizeof(u32));
dev_err(sdev->dev, "ACP_DMA_ERR_STS :0x%x ACP_ERROR_STATUS :0x%x\n", val, status);
@@ -263,6 +264,17 @@ int configure_and_run_sha_dma(struct acp_dev_data *adata, void *image_addr,
snd_sof_dsp_write(sdev, ACP_DSP_BAR, ACP_SHA_DMA_STRT_ADDR, start_addr);
snd_sof_dsp_write(sdev, ACP_DSP_BAR, ACP_SHA_DMA_DESTINATION_ADDR, dest_addr);
snd_sof_dsp_write(sdev, ACP_DSP_BAR, ACP_SHA_MSG_LENGTH, image_length);
+
+ /* psp_send_cmd only required for vangogh platform (rev - 5) */
+ if (desc->rev == 5 && !(adata->quirks && adata->quirks->skip_iram_dram_size_mod)) {
+ /* Modify IRAM and DRAM size */
+ ret = psp_send_cmd(adata, MBOX_ACP_IRAM_DRAM_FENCE_COMMAND | IRAM_DRAM_FENCE_2);
+ if (ret)
+ return ret;
+ ret = psp_send_cmd(adata, MBOX_ACP_IRAM_DRAM_FENCE_COMMAND | MBOX_ISREADY_FLAG);
+ if (ret)
+ return ret;
+ }
snd_sof_dsp_write(sdev, ACP_DSP_BAR, ACP_SHA_DMA_CMD, ACP_SHA_RUN);
ret = snd_sof_dsp_read_poll_timeout(sdev, ACP_DSP_BAR, ACP_SHA_TRANSFER_BYTE_CNT,
@@ -280,17 +292,6 @@ int configure_and_run_sha_dma(struct acp_dev_data *adata, void *image_addr,
return ret;
}
- /* psp_send_cmd only required for vangogh platform (rev - 5) */
- if (desc->rev == 5 && !(adata->quirks && adata->quirks->skip_iram_dram_size_mod)) {
- /* Modify IRAM and DRAM size */
- ret = psp_send_cmd(adata, MBOX_ACP_IRAM_DRAM_FENCE_COMMAND | IRAM_DRAM_FENCE_2);
- if (ret)
- return ret;
- ret = psp_send_cmd(adata, MBOX_ACP_IRAM_DRAM_FENCE_COMMAND | MBOX_ISREADY_FLAG);
- if (ret)
- return ret;
- }
-
ret = snd_sof_dsp_read_poll_timeout(sdev, ACP_DSP_BAR, ACP_SHA_DSP_FW_QUALIFIER,
fw_qualifier, fw_qualifier & DSP_FW_RUN_ENABLE,
ACP_REG_POLL_INTERVAL, ACP_DMA_COMPLETE_TIMEOUT_US);
@@ -402,9 +403,11 @@ static irqreturn_t acp_irq_handler(int irq, void *dev_id)
if (val & ACP_ERROR_IRQ_MASK) {
snd_sof_dsp_write(sdev, ACP_DSP_BAR, desc->ext_intr_stat, ACP_ERROR_IRQ_MASK);
- snd_sof_dsp_write(sdev, ACP_DSP_BAR, base + ACP_SW0_I2S_ERROR_REASON, 0);
- snd_sof_dsp_write(sdev, ACP_DSP_BAR, base + ACP_SW1_I2S_ERROR_REASON, 0);
- snd_sof_dsp_write(sdev, ACP_DSP_BAR, base + ACP_ERROR_STATUS, 0);
+ snd_sof_dsp_write(sdev, ACP_DSP_BAR, desc->acp_sw0_i2s_err_reason, 0);
+ /* ACP_SW1_I2S_ERROR_REASON is newly added register from rmb platform onwards */
+ if (desc->rev >= 6)
+ snd_sof_dsp_write(sdev, ACP_DSP_BAR, ACP_SW1_I2S_ERROR_REASON, 0);
+ snd_sof_dsp_write(sdev, ACP_DSP_BAR, desc->acp_error_stat, 0);
irq_flag = 1;
}
@@ -430,6 +433,7 @@ static int acp_power_on(struct snd_sof_dev *sdev)
const struct sof_amd_acp_desc *desc = get_chip_info(sdev->pdata);
unsigned int base = desc->pgfsm_base;
unsigned int val;
+ unsigned int acp_pgfsm_status_mask, acp_pgfsm_cntl_mask;
int ret;
val = snd_sof_dsp_read(sdev, ACP_DSP_BAR, base + PGFSM_STATUS_OFFSET);
@@ -437,9 +441,23 @@ static int acp_power_on(struct snd_sof_dev *sdev)
if (val == ACP_POWERED_ON)
return 0;
- if (val & ACP_PGFSM_STATUS_MASK)
+ switch (desc->rev) {
+ case 3:
+ case 5:
+ acp_pgfsm_status_mask = ACP3X_PGFSM_STATUS_MASK;
+ acp_pgfsm_cntl_mask = ACP3X_PGFSM_CNTL_POWER_ON_MASK;
+ break;
+ case 6:
+ acp_pgfsm_status_mask = ACP6X_PGFSM_STATUS_MASK;
+ acp_pgfsm_cntl_mask = ACP6X_PGFSM_CNTL_POWER_ON_MASK;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (val & acp_pgfsm_status_mask)
snd_sof_dsp_write(sdev, ACP_DSP_BAR, base + PGFSM_CONTROL_OFFSET,
- ACP_PGFSM_CNTL_POWER_ON_MASK);
+ acp_pgfsm_cntl_mask);
ret = snd_sof_dsp_read_poll_timeout(sdev, ACP_DSP_BAR, base + PGFSM_STATUS_OFFSET, val,
!val, ACP_REG_POLL_INTERVAL, ACP_REG_POLL_TIMEOUT_US);
diff --git a/sound/soc/sof/amd/acp.h b/sound/soc/sof/amd/acp.h
index 87e79d5..61b28df8 100644
--- a/sound/soc/sof/amd/acp.h
+++ b/sound/soc/sof/amd/acp.h
@@ -25,8 +25,11 @@
#define ACP_REG_POLL_TIMEOUT_US 2000
#define ACP_DMA_COMPLETE_TIMEOUT_US 5000
-#define ACP_PGFSM_CNTL_POWER_ON_MASK 0x01
-#define ACP_PGFSM_STATUS_MASK 0x03
+#define ACP3X_PGFSM_CNTL_POWER_ON_MASK 0x01
+#define ACP3X_PGFSM_STATUS_MASK 0x03
+#define ACP6X_PGFSM_CNTL_POWER_ON_MASK 0x07
+#define ACP6X_PGFSM_STATUS_MASK 0x0F
+
#define ACP_POWERED_ON 0x00
#define ACP_ASSERT_RESET 0x01
#define ACP_RELEASE_RESET 0x00
@@ -203,6 +206,8 @@ struct sof_amd_acp_desc {
u32 probe_reg_offset;
u32 reg_start_addr;
u32 reg_end_addr;
+ u32 acp_error_stat;
+ u32 acp_sw0_i2s_err_reason;
u32 sdw_max_link_count;
u64 sdw_acpi_dev_addr;
};
diff --git a/sound/soc/sof/amd/pci-acp63.c b/sound/soc/sof/amd/pci-acp63.c
index fc89844..986f592 100644
--- a/sound/soc/sof/amd/pci-acp63.c
+++ b/sound/soc/sof/amd/pci-acp63.c
@@ -35,6 +35,8 @@ static const struct sof_amd_acp_desc acp63_chip_info = {
.ext_intr_cntl = ACP6X_EXTERNAL_INTR_CNTL,
.ext_intr_stat = ACP6X_EXT_INTR_STAT,
.ext_intr_stat1 = ACP6X_EXT_INTR_STAT1,
+ .acp_error_stat = ACP6X_ERROR_STATUS,
+ .acp_sw0_i2s_err_reason = ACP6X_SW0_I2S_ERROR_REASON,
.dsp_intr_base = ACP6X_DSP_SW_INTR_BASE,
.sram_pte_offset = ACP6X_SRAM_PTE_OFFSET,
.hw_semaphore_offset = ACP6X_AXI2DAGB_SEM_0,
diff --git a/sound/soc/sof/amd/pci-rmb.c b/sound/soc/sof/amd/pci-rmb.c
index 4bc3095..a366f90 100644
--- a/sound/soc/sof/amd/pci-rmb.c
+++ b/sound/soc/sof/amd/pci-rmb.c
@@ -33,6 +33,8 @@ static const struct sof_amd_acp_desc rembrandt_chip_info = {
.pgfsm_base = ACP6X_PGFSM_BASE,
.ext_intr_stat = ACP6X_EXT_INTR_STAT,
.dsp_intr_base = ACP6X_DSP_SW_INTR_BASE,
+ .acp_error_stat = ACP6X_ERROR_STATUS,
+ .acp_sw0_i2s_err_reason = ACP6X_SW0_I2S_ERROR_REASON,
.sram_pte_offset = ACP6X_SRAM_PTE_OFFSET,
.hw_semaphore_offset = ACP6X_AXI2DAGB_SEM_0,
.fusion_dsp_offset = ACP6X_DSP_FUSION_RUNSTALL,
diff --git a/sound/soc/sof/amd/pci-rn.c b/sound/soc/sof/amd/pci-rn.c
index e08875b..2b7c534 100644
--- a/sound/soc/sof/amd/pci-rn.c
+++ b/sound/soc/sof/amd/pci-rn.c
@@ -33,6 +33,8 @@ static const struct sof_amd_acp_desc renoir_chip_info = {
.pgfsm_base = ACP3X_PGFSM_BASE,
.ext_intr_stat = ACP3X_EXT_INTR_STAT,
.dsp_intr_base = ACP3X_DSP_SW_INTR_BASE,
+ .acp_error_stat = ACP3X_ERROR_STATUS,
+ .acp_sw0_i2s_err_reason = ACP3X_SW_I2S_ERROR_REASON,
.sram_pte_offset = ACP3X_SRAM_PTE_OFFSET,
.hw_semaphore_offset = ACP3X_AXI2DAGB_SEM_0,
.acp_clkmux_sel = ACP3X_CLKMUX_SEL,
diff --git a/sound/soc/sof/mediatek/mt8195/mt8195.c b/sound/soc/sof/mediatek/mt8195/mt8195.c
index 1c6e035..82d221f 100644
--- a/sound/soc/sof/mediatek/mt8195/mt8195.c
+++ b/sound/soc/sof/mediatek/mt8195/mt8195.c
@@ -575,6 +575,9 @@ static struct snd_sof_of_mach sof_mt8195_machs[] = {
.compatible = "google,tomato",
.sof_tplg_filename = "sof-mt8195-mt6359-rt1019-rt5682.tplg"
}, {
+ .compatible = "google,dojo",
+ .sof_tplg_filename = "sof-mt8195-mt6359-max98390-rt5682.tplg"
+ }, {
.compatible = "mediatek,mt8195",
.sof_tplg_filename = "sof-mt8195.tplg"
}, {
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index f13a8d6..aaa6a51 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -273,6 +273,7 @@ YAMAHA_DEVICE(0x105a, NULL),
YAMAHA_DEVICE(0x105b, NULL),
YAMAHA_DEVICE(0x105c, NULL),
YAMAHA_DEVICE(0x105d, NULL),
+YAMAHA_DEVICE(0x1718, "P-125"),
{
USB_DEVICE(0x0499, 0x1503),
.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index ea063a14..e7b68c6 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2221,6 +2221,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
QUIRK_FLAG_GENERIC_IMPLICIT_FB),
DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */
QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+ DEVICE_FLG(0x2d95, 0x8021, /* VIVO USB-C-XE710 HEADSET */
+ QUIRK_FLAG_CTL_MSG_DELAY_1M),
DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */
QUIRK_FLAG_IGNORE_CTL_ERROR),
DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
index 7b32b99..5fd7cae 100644
--- a/tools/arch/arm64/include/asm/cputype.h
+++ b/tools/arch/arm64/include/asm/cputype.h
@@ -86,9 +86,14 @@
#define ARM_CPU_PART_CORTEX_X2 0xD48
#define ARM_CPU_PART_NEOVERSE_N2 0xD49
#define ARM_CPU_PART_CORTEX_A78C 0xD4B
+#define ARM_CPU_PART_CORTEX_X1C 0xD4C
+#define ARM_CPU_PART_CORTEX_X3 0xD4E
#define ARM_CPU_PART_NEOVERSE_V2 0xD4F
+#define ARM_CPU_PART_CORTEX_A720 0xD81
#define ARM_CPU_PART_CORTEX_X4 0xD82
#define ARM_CPU_PART_NEOVERSE_V3 0xD84
+#define ARM_CPU_PART_CORTEX_X925 0xD85
+#define ARM_CPU_PART_CORTEX_A725 0xD87
#define APM_CPU_PART_XGENE 0x000
#define APM_CPU_VAR_POTENZA 0x00
@@ -162,9 +167,14 @@
#define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
#define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2)
#define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C)
+#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C)
+#define MIDR_CORTEX_X3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X3)
#define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2)
+#define MIDR_CORTEX_A720 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A720)
#define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4)
#define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3)
+#define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925)
+#define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725)
#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)
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 1691297..eaeda00 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -645,6 +645,9 @@ struct kvm_ppc_cpu_char {
#define KVM_REG_PPC_SIER3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc3)
#define KVM_REG_PPC_DAWR1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc4)
#define KVM_REG_PPC_DAWRX1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc5)
+#define KVM_REG_PPC_DEXCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc6)
+#define KVM_REG_PPC_HASHKEYR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc7)
+#define KVM_REG_PPC_HASHPKEYR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc8)
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 3c74343..dd468285 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -18,170 +18,170 @@
/*
* Note: If the comment begins with a quoted string, that string is used
- * in /proc/cpuinfo instead of the macro name. If the string is "",
- * this feature bit is not displayed in /proc/cpuinfo at all.
+ * in /proc/cpuinfo instead of the macro name. Otherwise, this feature
+ * bit is not displayed in /proc/cpuinfo at all.
*
* When adding new features here that depend on other features,
* please update the table in kernel/cpu/cpuid-deps.c as well.
*/
/* Intel-defined CPU features, CPUID level 0x00000001 (EDX), word 0 */
-#define X86_FEATURE_FPU ( 0*32+ 0) /* Onboard FPU */
-#define X86_FEATURE_VME ( 0*32+ 1) /* Virtual Mode Extensions */
-#define X86_FEATURE_DE ( 0*32+ 2) /* Debugging Extensions */
-#define X86_FEATURE_PSE ( 0*32+ 3) /* Page Size Extensions */
-#define X86_FEATURE_TSC ( 0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR ( 0*32+ 5) /* Model-Specific Registers */
-#define X86_FEATURE_PAE ( 0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE ( 0*32+ 7) /* Machine Check Exception */
-#define X86_FEATURE_CX8 ( 0*32+ 8) /* CMPXCHG8 instruction */
-#define X86_FEATURE_APIC ( 0*32+ 9) /* Onboard APIC */
-#define X86_FEATURE_SEP ( 0*32+11) /* SYSENTER/SYSEXIT */
-#define X86_FEATURE_MTRR ( 0*32+12) /* Memory Type Range Registers */
-#define X86_FEATURE_PGE ( 0*32+13) /* Page Global Enable */
-#define X86_FEATURE_MCA ( 0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV ( 0*32+15) /* CMOV instructions (plus FCMOVcc, FCOMI with FPU) */
-#define X86_FEATURE_PAT ( 0*32+16) /* Page Attribute Table */
-#define X86_FEATURE_PSE36 ( 0*32+17) /* 36-bit PSEs */
-#define X86_FEATURE_PN ( 0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLUSH ( 0*32+19) /* CLFLUSH instruction */
+#define X86_FEATURE_FPU ( 0*32+ 0) /* "fpu" Onboard FPU */
+#define X86_FEATURE_VME ( 0*32+ 1) /* "vme" Virtual Mode Extensions */
+#define X86_FEATURE_DE ( 0*32+ 2) /* "de" Debugging Extensions */
+#define X86_FEATURE_PSE ( 0*32+ 3) /* "pse" Page Size Extensions */
+#define X86_FEATURE_TSC ( 0*32+ 4) /* "tsc" Time Stamp Counter */
+#define X86_FEATURE_MSR ( 0*32+ 5) /* "msr" Model-Specific Registers */
+#define X86_FEATURE_PAE ( 0*32+ 6) /* "pae" Physical Address Extensions */
+#define X86_FEATURE_MCE ( 0*32+ 7) /* "mce" Machine Check Exception */
+#define X86_FEATURE_CX8 ( 0*32+ 8) /* "cx8" CMPXCHG8 instruction */
+#define X86_FEATURE_APIC ( 0*32+ 9) /* "apic" Onboard APIC */
+#define X86_FEATURE_SEP ( 0*32+11) /* "sep" SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR ( 0*32+12) /* "mtrr" Memory Type Range Registers */
+#define X86_FEATURE_PGE ( 0*32+13) /* "pge" Page Global Enable */
+#define X86_FEATURE_MCA ( 0*32+14) /* "mca" Machine Check Architecture */
+#define X86_FEATURE_CMOV ( 0*32+15) /* "cmov" CMOV instructions (plus FCMOVcc, FCOMI with FPU) */
+#define X86_FEATURE_PAT ( 0*32+16) /* "pat" Page Attribute Table */
+#define X86_FEATURE_PSE36 ( 0*32+17) /* "pse36" 36-bit PSEs */
+#define X86_FEATURE_PN ( 0*32+18) /* "pn" Processor serial number */
+#define X86_FEATURE_CLFLUSH ( 0*32+19) /* "clflush" CLFLUSH instruction */
#define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */
-#define X86_FEATURE_ACPI ( 0*32+22) /* ACPI via MSR */
-#define X86_FEATURE_MMX ( 0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_ACPI ( 0*32+22) /* "acpi" ACPI via MSR */
+#define X86_FEATURE_MMX ( 0*32+23) /* "mmx" Multimedia Extensions */
+#define X86_FEATURE_FXSR ( 0*32+24) /* "fxsr" FXSAVE/FXRSTOR, CR4.OSFXSR */
#define X86_FEATURE_XMM ( 0*32+25) /* "sse" */
#define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */
#define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */
-#define X86_FEATURE_HT ( 0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_HT ( 0*32+28) /* "ht" Hyper-Threading */
#define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */
-#define X86_FEATURE_IA64 ( 0*32+30) /* IA-64 processor */
-#define X86_FEATURE_PBE ( 0*32+31) /* Pending Break Enable */
+#define X86_FEATURE_IA64 ( 0*32+30) /* "ia64" IA-64 processor */
+#define X86_FEATURE_PBE ( 0*32+31) /* "pbe" Pending Break Enable */
/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
/* Don't duplicate feature flags which are redundant with Intel! */
-#define X86_FEATURE_SYSCALL ( 1*32+11) /* SYSCALL/SYSRET */
-#define X86_FEATURE_MP ( 1*32+19) /* MP Capable */
-#define X86_FEATURE_NX ( 1*32+20) /* Execute Disable */
-#define X86_FEATURE_MMXEXT ( 1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_SYSCALL ( 1*32+11) /* "syscall" SYSCALL/SYSRET */
+#define X86_FEATURE_MP ( 1*32+19) /* "mp" MP Capable */
+#define X86_FEATURE_NX ( 1*32+20) /* "nx" Execute Disable */
+#define X86_FEATURE_MMXEXT ( 1*32+22) /* "mmxext" AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* "fxsr_opt" FXSAVE/FXRSTOR optimizations */
#define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */
-#define X86_FEATURE_RDTSCP ( 1*32+27) /* RDTSCP */
-#define X86_FEATURE_LM ( 1*32+29) /* Long Mode (x86-64, 64-bit support) */
-#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* AMD 3DNow extensions */
-#define X86_FEATURE_3DNOW ( 1*32+31) /* 3DNow */
+#define X86_FEATURE_RDTSCP ( 1*32+27) /* "rdtscp" RDTSCP */
+#define X86_FEATURE_LM ( 1*32+29) /* "lm" Long Mode (x86-64, 64-bit support) */
+#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* "3dnowext" AMD 3DNow extensions */
+#define X86_FEATURE_3DNOW ( 1*32+31) /* "3dnow" 3DNow */
/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
-#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* CPU in recovery mode */
-#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* Longrun power control */
-#define X86_FEATURE_LRTI ( 2*32+ 3) /* LongRun table interface */
+#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* "recovery" CPU in recovery mode */
+#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* "longrun" Longrun power control */
+#define X86_FEATURE_LRTI ( 2*32+ 3) /* "lrti" LongRun table interface */
/* Other features, Linux-defined mapping, word 3 */
/* This range is used for feature bits which conflict or are synthesized */
-#define X86_FEATURE_CXMMX ( 3*32+ 0) /* Cyrix MMX extensions */
-#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
-#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
-#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
-#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */
-#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* "" CPU based on Zen5 microarchitecture */
-#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */
-#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */
-#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
-#define X86_FEATURE_UP ( 3*32+ 9) /* SMP kernel running on UP */
-#define X86_FEATURE_ART ( 3*32+10) /* Always running timer (ART) */
-#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_PEBS ( 3*32+12) /* Precise-Event Based Sampling */
-#define X86_FEATURE_BTS ( 3*32+13) /* Branch Trace Store */
-#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 */
-#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */
-#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* "" Clear CPU buffers using VERW */
-#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */
-#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */
-#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* CPU topology enum extensions */
-#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
-#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */
-#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */
-#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* Extended APICID (8 bits) */
-#define X86_FEATURE_AMD_DCM ( 3*32+27) /* AMD multi-node processor */
-#define X86_FEATURE_APERFMPERF ( 3*32+28) /* P-State hardware coordination feedback capability (APERF/MPERF MSRs) */
-#define X86_FEATURE_RAPL ( 3*32+29) /* AMD/Hygon RAPL interface */
-#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
-#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */
+#define X86_FEATURE_CXMMX ( 3*32+ 0) /* "cxmmx" Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* "k6_mtrr" AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* "cyrix_arr" Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */
+#define X86_FEATURE_K8 ( 3*32+ 4) /* Opteron, Athlon64 */
+#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* CPU based on Zen5 microarchitecture */
+#define X86_FEATURE_P3 ( 3*32+ 6) /* P3 */
+#define X86_FEATURE_P4 ( 3*32+ 7) /* P4 */
+#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */
+#define X86_FEATURE_UP ( 3*32+ 9) /* "up" SMP kernel running on UP */
+#define X86_FEATURE_ART ( 3*32+10) /* "art" Always running timer (ART) */
+#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* "arch_perfmon" Intel Architectural PerfMon */
+#define X86_FEATURE_PEBS ( 3*32+12) /* "pebs" Precise-Event Based Sampling */
+#define X86_FEATURE_BTS ( 3*32+13) /* "bts" Branch Trace Store */
+#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_good" REP microcode works well */
+#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* "amd_lbr_v2" AMD Last Branch Record Extension Version 2 */
+#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* Clear CPU buffers using VERW */
+#define X86_FEATURE_ACC_POWER ( 3*32+19) /* "acc_power" AMD Accumulated Power Mechanism */
+#define X86_FEATURE_NOPL ( 3*32+20) /* "nopl" The NOPL (0F 1F) instructions */
+#define X86_FEATURE_ALWAYS ( 3*32+21) /* Always-present feature */
+#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* "xtopology" CPU topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* "tsc_reliable" TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* "nonstop_tsc" TSC does not stop in C states */
+#define X86_FEATURE_CPUID ( 3*32+25) /* "cpuid" CPU has CPUID instruction itself */
+#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* "extd_apicid" Extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM ( 3*32+27) /* "amd_dcm" AMD multi-node processor */
+#define X86_FEATURE_APERFMPERF ( 3*32+28) /* "aperfmperf" P-State hardware coordination feedback capability (APERF/MPERF MSRs) */
+#define X86_FEATURE_RAPL ( 3*32+29) /* "rapl" AMD/Hygon RAPL interface */
+#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* "nonstop_tsc_s3" TSC doesn't stop in S3 state */
+#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* "tsc_known_freq" TSC has known frequency */
/* Intel-defined CPU features, CPUID level 0x00000001 (ECX), word 4 */
#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */
-#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* PCLMULQDQ instruction */
-#define X86_FEATURE_DTES64 ( 4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* "pclmulqdq" PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64 ( 4*32+ 2) /* "dtes64" 64-bit Debug Store */
#define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" MONITOR/MWAIT support */
#define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL-qualified (filtered) Debug Store */
-#define X86_FEATURE_VMX ( 4*32+ 5) /* Hardware virtualization */
-#define X86_FEATURE_SMX ( 4*32+ 6) /* Safer Mode eXtensions */
-#define X86_FEATURE_EST ( 4*32+ 7) /* Enhanced SpeedStep */
-#define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */
-#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */
-#define X86_FEATURE_CID ( 4*32+10) /* Context ID */
-#define X86_FEATURE_SDBG ( 4*32+11) /* Silicon Debug */
-#define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */
-#define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B instruction */
-#define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */
-#define X86_FEATURE_PDCM ( 4*32+15) /* Perf/Debug Capabilities MSR */
-#define X86_FEATURE_PCID ( 4*32+17) /* Process Context Identifiers */
-#define X86_FEATURE_DCA ( 4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_VMX ( 4*32+ 5) /* "vmx" Hardware virtualization */
+#define X86_FEATURE_SMX ( 4*32+ 6) /* "smx" Safer Mode eXtensions */
+#define X86_FEATURE_EST ( 4*32+ 7) /* "est" Enhanced SpeedStep */
+#define X86_FEATURE_TM2 ( 4*32+ 8) /* "tm2" Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* "ssse3" Supplemental SSE-3 */
+#define X86_FEATURE_CID ( 4*32+10) /* "cid" Context ID */
+#define X86_FEATURE_SDBG ( 4*32+11) /* "sdbg" Silicon Debug */
+#define X86_FEATURE_FMA ( 4*32+12) /* "fma" Fused multiply-add */
+#define X86_FEATURE_CX16 ( 4*32+13) /* "cx16" CMPXCHG16B instruction */
+#define X86_FEATURE_XTPR ( 4*32+14) /* "xtpr" Send Task Priority Messages */
+#define X86_FEATURE_PDCM ( 4*32+15) /* "pdcm" Perf/Debug Capabilities MSR */
+#define X86_FEATURE_PCID ( 4*32+17) /* "pcid" Process Context Identifiers */
+#define X86_FEATURE_DCA ( 4*32+18) /* "dca" Direct Cache Access */
#define X86_FEATURE_XMM4_1 ( 4*32+19) /* "sse4_1" SSE-4.1 */
#define X86_FEATURE_XMM4_2 ( 4*32+20) /* "sse4_2" SSE-4.2 */
-#define X86_FEATURE_X2APIC ( 4*32+21) /* X2APIC */
-#define X86_FEATURE_MOVBE ( 4*32+22) /* MOVBE instruction */
-#define X86_FEATURE_POPCNT ( 4*32+23) /* POPCNT instruction */
-#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* TSC deadline timer */
-#define X86_FEATURE_AES ( 4*32+25) /* AES instructions */
-#define X86_FEATURE_XSAVE ( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV instructions */
-#define X86_FEATURE_OSXSAVE ( 4*32+27) /* "" XSAVE instruction enabled in the OS */
-#define X86_FEATURE_AVX ( 4*32+28) /* Advanced Vector Extensions */
-#define X86_FEATURE_F16C ( 4*32+29) /* 16-bit FP conversions */
-#define X86_FEATURE_RDRAND ( 4*32+30) /* RDRAND instruction */
-#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* Running on a hypervisor */
+#define X86_FEATURE_X2APIC ( 4*32+21) /* "x2apic" X2APIC */
+#define X86_FEATURE_MOVBE ( 4*32+22) /* "movbe" MOVBE instruction */
+#define X86_FEATURE_POPCNT ( 4*32+23) /* "popcnt" POPCNT instruction */
+#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* "tsc_deadline_timer" TSC deadline timer */
+#define X86_FEATURE_AES ( 4*32+25) /* "aes" AES instructions */
+#define X86_FEATURE_XSAVE ( 4*32+26) /* "xsave" XSAVE/XRSTOR/XSETBV/XGETBV instructions */
+#define X86_FEATURE_OSXSAVE ( 4*32+27) /* XSAVE instruction enabled in the OS */
+#define X86_FEATURE_AVX ( 4*32+28) /* "avx" Advanced Vector Extensions */
+#define X86_FEATURE_F16C ( 4*32+29) /* "f16c" 16-bit FP conversions */
+#define X86_FEATURE_RDRAND ( 4*32+30) /* "rdrand" RDRAND instruction */
+#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* "hypervisor" Running on a hypervisor */
/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
#define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */
#define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */
#define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
#define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
-#define X86_FEATURE_ACE2 ( 5*32+ 8) /* Advanced Cryptography Engine v2 */
-#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* ACE v2 enabled */
-#define X86_FEATURE_PHE ( 5*32+10) /* PadLock Hash Engine */
-#define X86_FEATURE_PHE_EN ( 5*32+11) /* PHE enabled */
-#define X86_FEATURE_PMM ( 5*32+12) /* PadLock Montgomery Multiplier */
-#define X86_FEATURE_PMM_EN ( 5*32+13) /* PMM enabled */
+#define X86_FEATURE_ACE2 ( 5*32+ 8) /* "ace2" Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* "ace2_en" ACE v2 enabled */
+#define X86_FEATURE_PHE ( 5*32+10) /* "phe" PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN ( 5*32+11) /* "phe_en" PHE enabled */
+#define X86_FEATURE_PMM ( 5*32+12) /* "pmm" PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN ( 5*32+13) /* "pmm_en" PMM enabled */
/* More extended AMD flags: CPUID level 0x80000001, ECX, word 6 */
-#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* LAHF/SAHF in long mode */
-#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* If yes HyperThreading not valid */
-#define X86_FEATURE_SVM ( 6*32+ 2) /* Secure Virtual Machine */
-#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* Extended APIC space */
-#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* CR8 in 32-bit mode */
-#define X86_FEATURE_ABM ( 6*32+ 5) /* Advanced bit manipulation */
-#define X86_FEATURE_SSE4A ( 6*32+ 6) /* SSE-4A */
-#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
-#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
-#define X86_FEATURE_OSVW ( 6*32+ 9) /* OS Visible Workaround */
-#define X86_FEATURE_IBS ( 6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_XOP ( 6*32+11) /* extended AVX instructions */
-#define X86_FEATURE_SKINIT ( 6*32+12) /* SKINIT/STGI instructions */
-#define X86_FEATURE_WDT ( 6*32+13) /* Watchdog timer */
-#define X86_FEATURE_LWP ( 6*32+15) /* Light Weight Profiling */
-#define X86_FEATURE_FMA4 ( 6*32+16) /* 4 operands MAC instructions */
-#define X86_FEATURE_TCE ( 6*32+17) /* Translation Cache Extension */
-#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* NodeId MSR */
-#define X86_FEATURE_TBM ( 6*32+21) /* Trailing Bit Manipulations */
-#define X86_FEATURE_TOPOEXT ( 6*32+22) /* Topology extensions CPUID leafs */
-#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* Core performance counter extensions */
-#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */
-#define X86_FEATURE_BPEXT ( 6*32+26) /* Data breakpoint extension */
-#define X86_FEATURE_PTSC ( 6*32+27) /* Performance time-stamp counter */
-#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */
-#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX instructions) */
+#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* "lahf_lm" LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* "cmp_legacy" If yes HyperThreading not valid */
+#define X86_FEATURE_SVM ( 6*32+ 2) /* "svm" Secure Virtual Machine */
+#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* "extapic" Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* "cr8_legacy" CR8 in 32-bit mode */
+#define X86_FEATURE_ABM ( 6*32+ 5) /* "abm" Advanced bit manipulation */
+#define X86_FEATURE_SSE4A ( 6*32+ 6) /* "sse4a" SSE-4A */
+#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* "misalignsse" Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* "3dnowprefetch" 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW ( 6*32+ 9) /* "osvw" OS Visible Workaround */
+#define X86_FEATURE_IBS ( 6*32+10) /* "ibs" Instruction Based Sampling */
+#define X86_FEATURE_XOP ( 6*32+11) /* "xop" Extended AVX instructions */
+#define X86_FEATURE_SKINIT ( 6*32+12) /* "skinit" SKINIT/STGI instructions */
+#define X86_FEATURE_WDT ( 6*32+13) /* "wdt" Watchdog timer */
+#define X86_FEATURE_LWP ( 6*32+15) /* "lwp" Light Weight Profiling */
+#define X86_FEATURE_FMA4 ( 6*32+16) /* "fma4" 4 operands MAC instructions */
+#define X86_FEATURE_TCE ( 6*32+17) /* "tce" Translation Cache Extension */
+#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* "nodeid_msr" NodeId MSR */
+#define X86_FEATURE_TBM ( 6*32+21) /* "tbm" Trailing Bit Manipulations */
+#define X86_FEATURE_TOPOEXT ( 6*32+22) /* "topoext" Topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* "perfctr_core" Core performance counter extensions */
+#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* "perfctr_nb" NB performance counter extensions */
+#define X86_FEATURE_BPEXT ( 6*32+26) /* "bpext" Data breakpoint extension */
+#define X86_FEATURE_PTSC ( 6*32+27) /* "ptsc" Performance time-stamp counter */
+#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* "perfctr_llc" Last Level Cache performance counter extensions */
+#define X86_FEATURE_MWAITX ( 6*32+29) /* "mwaitx" MWAIT extension (MONITORX/MWAITX instructions) */
/*
* Auxiliary flags: Linux defined - For features scattered in various
@@ -189,93 +189,93 @@
*
* Reuse free bits when adding new feature flags!
*/
-#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT instructions */
-#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */
-#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */
-#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
-#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */
-#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */
-#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */
-#define X86_FEATURE_TDX_HOST_PLATFORM ( 7*32+ 7) /* Platform supports being a TDX host */
-#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
-#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
-#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */
-#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */
-#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */
-#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* "" Fill RSB on VM-Exit */
-#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
-#define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */
-#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
-#define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */
-#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */
-#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */
-#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* AMD Performance Monitoring Version 2 */
-#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
-#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */
-#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */
-#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* "" AMD SSBD implementation via LS_CFG MSR */
-#define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */
-#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */
-#define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */
-#define X86_FEATURE_ZEN ( 7*32+28) /* "" Generic flag for all Zen and newer */
-#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */
-#define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */
-#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */
+#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* "ring3mwait" Ring 3 MONITOR/MWAIT instructions */
+#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* "cpuid_fault" Intel CPUID faulting */
+#define X86_FEATURE_CPB ( 7*32+ 2) /* "cpb" AMD Core Performance Boost */
+#define X86_FEATURE_EPB ( 7*32+ 3) /* "epb" IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* "cat_l3" Cache Allocation Technology L3 */
+#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* "cat_l2" Cache Allocation Technology L2 */
+#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* "cdp_l3" Code and Data Prioritization L3 */
+#define X86_FEATURE_TDX_HOST_PLATFORM ( 7*32+ 7) /* "tdx_host_platform" Platform supports being a TDX host */
+#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* "hw_pstate" AMD HW-PState */
+#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* "proc_feedback" AMD ProcFeedbackInterface */
+#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* Use compacted XSTATE (XSAVES or XSAVEC) */
+#define X86_FEATURE_PTI ( 7*32+11) /* "pti" Kernel Page Table Isolation enabled */
+#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* Set/clear IBRS on kernel entry/exit */
+#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* Fill RSB on VM-Exit */
+#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* "intel_ppin" Intel Processor Inventory Number */
+#define X86_FEATURE_CDP_L2 ( 7*32+15) /* "cdp_l2" Code and Data Prioritization L2 */
+#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* MSR SPEC_CTRL is implemented */
+#define X86_FEATURE_SSBD ( 7*32+17) /* "ssbd" Speculative Store Bypass Disable */
+#define X86_FEATURE_MBA ( 7*32+18) /* "mba" Memory Bandwidth Allocation */
+#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */
+#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* "perfmon_v2" AMD Performance Monitoring Version 2 */
+#define X86_FEATURE_USE_IBPB ( 7*32+21) /* Indirect Branch Prediction Barrier enabled */
+#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* Use IBRS during runtime firmware calls */
+#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* Disable Speculative Store Bypass. */
+#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* AMD SSBD implementation via LS_CFG MSR */
+#define X86_FEATURE_IBRS ( 7*32+25) /* "ibrs" Indirect Branch Restricted Speculation */
+#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier */
+#define X86_FEATURE_STIBP ( 7*32+27) /* "stibp" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ZEN ( 7*32+28) /* Generic flag for all Zen and newer */
+#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* L1TF workaround PTE inversion */
+#define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* "ibrs_enhanced" Enhanced IBRS */
+#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* MSR IA32_FEAT_CTL configured */
/* Virtualization flags: Linux defined, word 8 */
-#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
-#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* Intel FlexPriority */
-#define X86_FEATURE_EPT ( 8*32+ 2) /* Intel Extended Page Table */
-#define X86_FEATURE_VPID ( 8*32+ 3) /* Intel Virtual Processor ID */
+#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* "tpr_shadow" Intel TPR Shadow */
+#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* "flexpriority" Intel FlexPriority */
+#define X86_FEATURE_EPT ( 8*32+ 2) /* "ept" Intel Extended Page Table */
+#define X86_FEATURE_VPID ( 8*32+ 3) /* "vpid" Intel Virtual Processor ID */
-#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */
-#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */
-#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_PVUNLOCK ( 8*32+20) /* "" PV unlock function */
-#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */
-#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* Intel Trust Domain Extensions Guest */
+#define X86_FEATURE_VMMCALL ( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */
+#define X86_FEATURE_XENPV ( 8*32+16) /* Xen paravirtual guest */
+#define X86_FEATURE_EPT_AD ( 8*32+17) /* "ept_ad" 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_PVUNLOCK ( 8*32+20) /* PV unlock function */
+#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* PV vcpu_is_preempted function */
+#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* "tdx_guest" Intel Trust Domain Extensions Guest */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
-#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
-#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3B */
-#define X86_FEATURE_SGX ( 9*32+ 2) /* Software Guard Extensions */
-#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */
-#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */
-#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */
-#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* "" FPU data pointer updated only on x87 exceptions */
-#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */
-#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */
-#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */
-#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */
-#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */
-#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */
-#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* "" Zero out FPU CS and FPU DS */
-#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */
-#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */
-#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */
-#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
-#define X86_FEATURE_RDSEED ( 9*32+18) /* RDSEED instruction */
-#define X86_FEATURE_ADX ( 9*32+19) /* ADCX and ADOX instructions */
-#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */
-#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
-#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */
-#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */
-#define X86_FEATURE_INTEL_PT ( 9*32+25) /* Intel Processor Trace */
-#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */
-#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */
-#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */
-#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
-#define X86_FEATURE_AVX512BW ( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */
-#define X86_FEATURE_AVX512VL ( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */
+#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* "fsgsbase" RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
+#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* "tsc_adjust" TSC adjustment MSR 0x3B */
+#define X86_FEATURE_SGX ( 9*32+ 2) /* "sgx" Software Guard Extensions */
+#define X86_FEATURE_BMI1 ( 9*32+ 3) /* "bmi1" 1st group bit manipulation extensions */
+#define X86_FEATURE_HLE ( 9*32+ 4) /* "hle" Hardware Lock Elision */
+#define X86_FEATURE_AVX2 ( 9*32+ 5) /* "avx2" AVX2 instructions */
+#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* FPU data pointer updated only on x87 exceptions */
+#define X86_FEATURE_SMEP ( 9*32+ 7) /* "smep" Supervisor Mode Execution Protection */
+#define X86_FEATURE_BMI2 ( 9*32+ 8) /* "bmi2" 2nd group bit manipulation extensions */
+#define X86_FEATURE_ERMS ( 9*32+ 9) /* "erms" Enhanced REP MOVSB/STOSB instructions */
+#define X86_FEATURE_INVPCID ( 9*32+10) /* "invpcid" Invalidate Processor Context ID */
+#define X86_FEATURE_RTM ( 9*32+11) /* "rtm" Restricted Transactional Memory */
+#define X86_FEATURE_CQM ( 9*32+12) /* "cqm" Cache QoS Monitoring */
+#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* Zero out FPU CS and FPU DS */
+#define X86_FEATURE_MPX ( 9*32+14) /* "mpx" Memory Protection Extension */
+#define X86_FEATURE_RDT_A ( 9*32+15) /* "rdt_a" Resource Director Technology Allocation */
+#define X86_FEATURE_AVX512F ( 9*32+16) /* "avx512f" AVX-512 Foundation */
+#define X86_FEATURE_AVX512DQ ( 9*32+17) /* "avx512dq" AVX-512 DQ (Double/Quad granular) Instructions */
+#define X86_FEATURE_RDSEED ( 9*32+18) /* "rdseed" RDSEED instruction */
+#define X86_FEATURE_ADX ( 9*32+19) /* "adx" ADCX and ADOX instructions */
+#define X86_FEATURE_SMAP ( 9*32+20) /* "smap" Supervisor Mode Access Prevention */
+#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* "avx512ifma" AVX-512 Integer Fused Multiply-Add instructions */
+#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* "clflushopt" CLFLUSHOPT instruction */
+#define X86_FEATURE_CLWB ( 9*32+24) /* "clwb" CLWB instruction */
+#define X86_FEATURE_INTEL_PT ( 9*32+25) /* "intel_pt" Intel Processor Trace */
+#define X86_FEATURE_AVX512PF ( 9*32+26) /* "avx512pf" AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER ( 9*32+27) /* "avx512er" AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD ( 9*32+28) /* "avx512cd" AVX-512 Conflict Detection */
+#define X86_FEATURE_SHA_NI ( 9*32+29) /* "sha_ni" SHA1/SHA256 Instruction Extensions */
+#define X86_FEATURE_AVX512BW ( 9*32+30) /* "avx512bw" AVX-512 BW (Byte/Word granular) Instructions */
+#define X86_FEATURE_AVX512VL ( 9*32+31) /* "avx512vl" AVX-512 VL (128/256 Vector Length) Extensions */
/* Extended state features, CPUID level 0x0000000d:1 (EAX), word 10 */
-#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT instruction */
-#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC instruction */
-#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */
-#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */
-#define X86_FEATURE_XFD (10*32+ 4) /* "" eXtended Feature Disabling */
+#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* "xsaveopt" XSAVEOPT instruction */
+#define X86_FEATURE_XSAVEC (10*32+ 1) /* "xsavec" XSAVEC instruction */
+#define X86_FEATURE_XGETBV1 (10*32+ 2) /* "xgetbv1" XGETBV with ECX = 1 instruction */
+#define X86_FEATURE_XSAVES (10*32+ 3) /* "xsaves" XSAVES/XRSTORS instructions */
+#define X86_FEATURE_XFD (10*32+ 4) /* eXtended Feature Disabling */
/*
* Extended auxiliary flags: Linux defined - for features scattered in various
@@ -283,181 +283,183 @@
*
* Reuse free bits when adding new feature flags!
*/
-#define X86_FEATURE_CQM_LLC (11*32+ 0) /* LLC QoS if 1 */
-#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* LLC occupancy monitoring */
-#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* LLC Total MBM monitoring */
-#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */
-#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 */
-#define X86_FEATURE_SGX1 (11*32+ 8) /* "" Basic SGX */
-#define X86_FEATURE_SGX2 (11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */
-#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* "" Issue an IBPB on kernel entry */
-#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* "" RET prediction control */
-#define X86_FEATURE_RETPOLINE (11*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
-#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */
-#define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */
-#define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */
-#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */
-#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */
-#define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* "" SGX EDECCSSA user leaf function */
-#define X86_FEATURE_CALL_DEPTH (11*32+19) /* "" Call depth tracking for RSB stuffing */
-#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */
-#define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */
-#define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */
-#define X86_FEATURE_USER_SHSTK (11*32+23) /* Shadow stack support for user mode applications */
-#define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */
-#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */
-#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */
-#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */
-#define X86_FEATURE_ZEN2 (11*32+28) /* "" CPU based on Zen2 microarchitecture */
-#define X86_FEATURE_ZEN3 (11*32+29) /* "" CPU based on Zen3 microarchitecture */
-#define X86_FEATURE_ZEN4 (11*32+30) /* "" CPU based on Zen4 microarchitecture */
-#define X86_FEATURE_ZEN1 (11*32+31) /* "" CPU based on Zen1 microarchitecture */
+#define X86_FEATURE_CQM_LLC (11*32+ 0) /* "cqm_llc" LLC QoS if 1 */
+#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* "cqm_occup_llc" LLC occupancy monitoring */
+#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* "cqm_mbm_total" LLC Total MBM monitoring */
+#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* "cqm_mbm_local" LLC Local MBM monitoring */
+#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) /* "split_lock_detect" #AC for split lock */
+#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* Per-thread Memory Bandwidth Allocation */
+#define X86_FEATURE_SGX1 (11*32+ 8) /* Basic SGX */
+#define X86_FEATURE_SGX2 (11*32+ 9) /* SGX Enclave Dynamic Memory Management (EDMM) */
+#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* Issue an IBPB on kernel entry */
+#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* RET prediction control */
+#define X86_FEATURE_RETPOLINE (11*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* Use LFENCE for Spectre variant 2 */
+#define X86_FEATURE_RETHUNK (11*32+14) /* Use REturn THUNK */
+#define X86_FEATURE_UNRET (11*32+15) /* AMD BTB untrain return */
+#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* Use IBPB during runtime firmware calls */
+#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* Fill RSB on VM exit when EIBRS is enabled */
+#define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* SGX EDECCSSA user leaf function */
+#define X86_FEATURE_CALL_DEPTH (11*32+19) /* Call depth tracking for RSB stuffing */
+#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* MSR IA32_TSX_CTRL (Intel) implemented */
+#define X86_FEATURE_SMBA (11*32+21) /* Slow Memory Bandwidth Allocation */
+#define X86_FEATURE_BMEC (11*32+22) /* Bandwidth Monitoring Event Configuration */
+#define X86_FEATURE_USER_SHSTK (11*32+23) /* "user_shstk" Shadow stack support for user mode applications */
+#define X86_FEATURE_SRSO (11*32+24) /* AMD BTB untrain RETs */
+#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* AMD BTB untrain RETs through aliasing */
+#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* Issue an IBPB only on VMEXIT */
+#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* IA32_TSC_DEADLINE and X2APIC MSRs need fencing */
+#define X86_FEATURE_ZEN2 (11*32+28) /* CPU based on Zen2 microarchitecture */
+#define X86_FEATURE_ZEN3 (11*32+29) /* CPU based on Zen3 microarchitecture */
+#define X86_FEATURE_ZEN4 (11*32+30) /* CPU based on Zen4 microarchitecture */
+#define X86_FEATURE_ZEN1 (11*32+31) /* CPU based on Zen1 microarchitecture */
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
-#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */
-#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
-#define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */
-#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* "" Intel Architectural PerfMon Extension */
-#define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */
-#define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */
-#define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */
-#define X86_FEATURE_FRED (12*32+17) /* Flexible Return and Event Delivery */
-#define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */
-#define X86_FEATURE_WRMSRNS (12*32+19) /* "" Non-serializing WRMSR */
-#define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */
-#define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */
-#define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */
+#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* "avx_vnni" AVX VNNI instructions */
+#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* "avx512_bf16" AVX512 BFLOAT16 instructions */
+#define X86_FEATURE_CMPCCXADD (12*32+ 7) /* CMPccXADD instructions */
+#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* Intel Architectural PerfMon Extension */
+#define X86_FEATURE_FZRM (12*32+10) /* Fast zero-length REP MOVSB */
+#define X86_FEATURE_FSRS (12*32+11) /* Fast short REP STOSB */
+#define X86_FEATURE_FSRC (12*32+12) /* Fast short REP {CMPSB,SCASB} */
+#define X86_FEATURE_FRED (12*32+17) /* "fred" Flexible Return and Event Delivery */
+#define X86_FEATURE_LKGS (12*32+18) /* Load "kernel" (userspace) GS */
+#define X86_FEATURE_WRMSRNS (12*32+19) /* Non-serializing WRMSR */
+#define X86_FEATURE_AMX_FP16 (12*32+21) /* AMX fp16 Support */
+#define X86_FEATURE_AVX_IFMA (12*32+23) /* Support for VPMADD52[H,L]UQ */
+#define X86_FEATURE_LAM (12*32+26) /* "lam" Linear Address Masking */
/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
-#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
-#define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */
-#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */
-#define X86_FEATURE_RDPRU (13*32+ 4) /* Read processor register at user level */
-#define X86_FEATURE_WBNOINVD (13*32+ 9) /* WBNOINVD instruction */
-#define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */
-#define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */
-#define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */
-#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */
-#define X86_FEATURE_AMD_PPIN (13*32+23) /* Protected Processor Inventory Number */
-#define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */
-#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */
-#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
-#define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */
-#define X86_FEATURE_AMD_PSFD (13*32+28) /* "" Predictive Store Forwarding Disable */
-#define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */
-#define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */
+#define X86_FEATURE_CLZERO (13*32+ 0) /* "clzero" CLZERO instruction */
+#define X86_FEATURE_IRPERF (13*32+ 1) /* "irperf" Instructions Retired Count */
+#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* "xsaveerptr" Always save/restore FP error pointers */
+#define X86_FEATURE_RDPRU (13*32+ 4) /* "rdpru" Read processor register at user level */
+#define X86_FEATURE_WBNOINVD (13*32+ 9) /* "wbnoinvd" WBNOINVD instruction */
+#define X86_FEATURE_AMD_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_AMD_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_AMD_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* Single Thread Indirect Branch Predictors always-on preferred */
+#define X86_FEATURE_AMD_PPIN (13*32+23) /* "amd_ppin" Protected Processor Inventory Number */
+#define X86_FEATURE_AMD_SSBD (13*32+24) /* Speculative Store Bypass Disable */
+#define X86_FEATURE_VIRT_SSBD (13*32+25) /* "virt_ssbd" Virtualized Speculative Store Bypass Disable */
+#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* Speculative Store Bypass is fixed in hardware. */
+#define X86_FEATURE_CPPC (13*32+27) /* "cppc" Collaborative Processor Performance Control */
+#define X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */
+#define X86_FEATURE_BTC_NO (13*32+29) /* Not vulnerable to Branch Type Confusion */
+#define X86_FEATURE_BRS (13*32+31) /* "brs" Branch Sampling available */
/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
-#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */
-#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */
-#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */
-#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */
-#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */
-#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */
-#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */
-#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */
-#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */
-#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */
-#define X86_FEATURE_HFI (14*32+19) /* Hardware Feedback Interface */
+#define X86_FEATURE_DTHERM (14*32+ 0) /* "dtherm" Digital Thermal Sensor */
+#define X86_FEATURE_IDA (14*32+ 1) /* "ida" Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT (14*32+ 2) /* "arat" Always Running APIC Timer */
+#define X86_FEATURE_PLN (14*32+ 4) /* "pln" Intel Power Limit Notification */
+#define X86_FEATURE_PTS (14*32+ 6) /* "pts" Intel Package Thermal Status */
+#define X86_FEATURE_HWP (14*32+ 7) /* "hwp" Intel Hardware P-states */
+#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* "hwp_notify" HWP Notification */
+#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* "hwp_act_window" HWP Activity Window */
+#define X86_FEATURE_HWP_EPP (14*32+10) /* "hwp_epp" HWP Energy Perf. Preference */
+#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* "hwp_pkg_req" HWP Package Level Request */
+#define X86_FEATURE_HWP_HIGHEST_PERF_CHANGE (14*32+15) /* HWP Highest perf change */
+#define X86_FEATURE_HFI (14*32+19) /* "hfi" Hardware Feedback Interface */
/* AMD SVM Feature Identification, CPUID level 0x8000000a (EDX), word 15 */
-#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */
-#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */
+#define X86_FEATURE_NPT (15*32+ 0) /* "npt" Nested Page Table support */
+#define X86_FEATURE_LBRV (15*32+ 1) /* "lbrv" LBR Virtualization support */
#define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */
#define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */
#define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */
#define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
-#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */
-#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */
-#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
-#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
-#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */
-#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
-#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */
-#define X86_FEATURE_X2AVIC (15*32+18) /* Virtual x2apic */
-#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */
-#define X86_FEATURE_VNMI (15*32+25) /* Virtual NMI */
-#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */
+#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* "flushbyasid" Flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* "decodeassists" Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER (15*32+10) /* "pausefilter" Filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* "pfthreshold" Pause filter threshold */
+#define X86_FEATURE_AVIC (15*32+13) /* "avic" Virtual Interrupt Controller */
+#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* "v_vmsave_vmload" Virtual VMSAVE VMLOAD */
+#define X86_FEATURE_VGIF (15*32+16) /* "vgif" Virtual GIF */
+#define X86_FEATURE_X2AVIC (15*32+18) /* "x2avic" Virtual x2apic */
+#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* "v_spec_ctrl" Virtual SPEC_CTRL */
+#define X86_FEATURE_VNMI (15*32+25) /* "vnmi" Virtual NMI */
+#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* SVME addr check */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
-#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
-#define X86_FEATURE_UMIP (16*32+ 2) /* User Mode Instruction Protection */
-#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */
-#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */
-#define X86_FEATURE_WAITPKG (16*32+ 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */
-#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
-#define X86_FEATURE_SHSTK (16*32+ 7) /* "" Shadow stack */
-#define X86_FEATURE_GFNI (16*32+ 8) /* Galois Field New Instructions */
-#define X86_FEATURE_VAES (16*32+ 9) /* Vector AES */
-#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* Carry-Less Multiplication Double Quadword */
-#define X86_FEATURE_AVX512_VNNI (16*32+11) /* Vector Neural Network Instructions */
-#define X86_FEATURE_AVX512_BITALG (16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */
-#define X86_FEATURE_TME (16*32+13) /* Intel Total Memory Encryption */
-#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
-#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */
-#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */
-#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* Bus Lock detect */
-#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 */
-#define X86_FEATURE_SGX_LC (16*32+30) /* Software Guard Extensions Launch Control */
+#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* "avx512vbmi" AVX512 Vector Bit Manipulation instructions*/
+#define X86_FEATURE_UMIP (16*32+ 2) /* "umip" User Mode Instruction Protection */
+#define X86_FEATURE_PKU (16*32+ 3) /* "pku" Protection Keys for Userspace */
+#define X86_FEATURE_OSPKE (16*32+ 4) /* "ospke" OS Protection Keys Enable */
+#define X86_FEATURE_WAITPKG (16*32+ 5) /* "waitpkg" UMONITOR/UMWAIT/TPAUSE Instructions */
+#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* "avx512_vbmi2" Additional AVX512 Vector Bit Manipulation Instructions */
+#define X86_FEATURE_SHSTK (16*32+ 7) /* Shadow stack */
+#define X86_FEATURE_GFNI (16*32+ 8) /* "gfni" Galois Field New Instructions */
+#define X86_FEATURE_VAES (16*32+ 9) /* "vaes" Vector AES */
+#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* "vpclmulqdq" Carry-Less Multiplication Double Quadword */
+#define X86_FEATURE_AVX512_VNNI (16*32+11) /* "avx512_vnni" Vector Neural Network Instructions */
+#define X86_FEATURE_AVX512_BITALG (16*32+12) /* "avx512_bitalg" Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */
+#define X86_FEATURE_TME (16*32+13) /* "tme" Intel Total Memory Encryption */
+#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* "avx512_vpopcntdq" POPCNT for vectors of DW/QW */
+#define X86_FEATURE_LA57 (16*32+16) /* "la57" 5-level page tables */
+#define X86_FEATURE_RDPID (16*32+22) /* "rdpid" RDPID instruction */
+#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* "bus_lock_detect" Bus Lock detect */
+#define X86_FEATURE_CLDEMOTE (16*32+25) /* "cldemote" CLDEMOTE instruction */
+#define X86_FEATURE_MOVDIRI (16*32+27) /* "movdiri" MOVDIRI instruction */
+#define X86_FEATURE_MOVDIR64B (16*32+28) /* "movdir64b" MOVDIR64B instruction */
+#define X86_FEATURE_ENQCMD (16*32+29) /* "enqcmd" ENQCMD and ENQCMDS instructions */
+#define X86_FEATURE_SGX_LC (16*32+30) /* "sgx_lc" Software Guard Extensions Launch Control */
/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
-#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */
-#define X86_FEATURE_SUCCOR (17*32+ 1) /* Uncorrectable error containment and recovery */
-#define X86_FEATURE_SMCA (17*32+ 3) /* Scalable MCA */
+#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* "overflow_recov" MCA overflow recovery support */
+#define X86_FEATURE_SUCCOR (17*32+ 1) /* "succor" Uncorrectable error containment and recovery */
+#define X86_FEATURE_SMCA (17*32+ 3) /* "smca" Scalable MCA */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
-#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */
-#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
-#define X86_FEATURE_FSRM (18*32+ 4) /* Fast Short Rep Mov */
-#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
-#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* "" SRBDS mitigation MSR available */
-#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */
-#define X86_FEATURE_RTM_ALWAYS_ABORT (18*32+11) /* "" RTM transaction always aborts */
-#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
-#define X86_FEATURE_SERIALIZE (18*32+14) /* SERIALIZE instruction */
-#define X86_FEATURE_HYBRID_CPU (18*32+15) /* "" This part has CPUs of more than one type */
-#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_IBT (18*32+20) /* Indirect Branch Tracking */
-#define X86_FEATURE_AMX_BF16 (18*32+22) /* AMX bf16 Support */
-#define X86_FEATURE_AVX512_FP16 (18*32+23) /* AVX512 FP16 */
-#define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */
-#define X86_FEATURE_AMX_INT8 (18*32+25) /* AMX int8 Support */
-#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
-#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */
-#define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */
-#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
-#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */
-#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */
+#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* "avx512_4vnniw" AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* "avx512_4fmaps" AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_FSRM (18*32+ 4) /* "fsrm" Fast Short Rep Mov */
+#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* "avx512_vp2intersect" AVX-512 Intersect for D/Q */
+#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* SRBDS mitigation MSR available */
+#define X86_FEATURE_MD_CLEAR (18*32+10) /* "md_clear" VERW clears CPU buffers */
+#define X86_FEATURE_RTM_ALWAYS_ABORT (18*32+11) /* RTM transaction always aborts */
+#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* TSX_FORCE_ABORT */
+#define X86_FEATURE_SERIALIZE (18*32+14) /* "serialize" SERIALIZE instruction */
+#define X86_FEATURE_HYBRID_CPU (18*32+15) /* This part has CPUs of more than one type */
+#define X86_FEATURE_TSXLDTRK (18*32+16) /* "tsxldtrk" TSX Suspend Load Address Tracking */
+#define X86_FEATURE_PCONFIG (18*32+18) /* "pconfig" Intel PCONFIG */
+#define X86_FEATURE_ARCH_LBR (18*32+19) /* "arch_lbr" Intel ARCH LBR */
+#define X86_FEATURE_IBT (18*32+20) /* "ibt" Indirect Branch Tracking */
+#define X86_FEATURE_AMX_BF16 (18*32+22) /* "amx_bf16" AMX bf16 Support */
+#define X86_FEATURE_AVX512_FP16 (18*32+23) /* "avx512_fp16" AVX512 FP16 */
+#define X86_FEATURE_AMX_TILE (18*32+24) /* "amx_tile" AMX tile Support */
+#define X86_FEATURE_AMX_INT8 (18*32+25) /* "amx_int8" AMX int8 Support */
+#define X86_FEATURE_SPEC_CTRL (18*32+26) /* Speculation Control (IBRS + IBPB) */
+#define X86_FEATURE_INTEL_STIBP (18*32+27) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_FLUSH_L1D (18*32+28) /* "flush_l1d" Flush L1D cache */
+#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* "arch_capabilities" IA32_ARCH_CAPABILITIES MSR (Intel) */
+#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* IA32_CORE_CAPABILITIES MSR */
+#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* Speculative Store Bypass Disable */
/* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */
-#define X86_FEATURE_SME (19*32+ 0) /* AMD Secure Memory Encryption */
-#define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */
-#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */
-#define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */
-#define X86_FEATURE_SEV_SNP (19*32+ 4) /* AMD Secure Encrypted Virtualization - Secure Nested Paging */
-#define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */
-#define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */
-#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* AMD SEV-ES full debug state swap support */
+#define X86_FEATURE_SME (19*32+ 0) /* "sme" AMD Secure Memory Encryption */
+#define X86_FEATURE_SEV (19*32+ 1) /* "sev" AMD Secure Encrypted Virtualization */
+#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* VM Page Flush MSR is supported */
+#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" AMD Secure Encrypted Virtualization - Encrypted State */
+#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" AMD Secure Encrypted Virtualization - Secure Nested Paging */
+#define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* Virtual TSC_AUX */
+#define X86_FEATURE_SME_COHERENT (19*32+10) /* AMD hardware-enforced cache coherency */
+#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" AMD SEV-ES full debug state swap support */
+#define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */
/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
-#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */
-#define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* "" WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */
-#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */
-#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* "" Null Selector Clears Base */
-#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */
-#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* "" SMM_CTL MSR is not present */
+#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */
+#define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */
+#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */
+#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* Null Selector Clears Base */
+#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* Automatic IBRS */
+#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* SMM_CTL MSR is not present */
-#define X86_FEATURE_SBPB (20*32+27) /* "" Selective Branch Prediction Barrier */
-#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */
-#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */
+#define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */
+#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */
+#define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */
/*
* Extended auxiliary flags: Linux defined - for features scattered in various
@@ -465,59 +467,60 @@
*
* Reuse free bits when adding new feature flags!
*/
-#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */
-#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */
-#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */
-#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */
-#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */
+#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* "amd_lbr_pmc_freeze" AMD LBR and PMC Freeze */
+#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* Clear branch history at syscall entry using SW loop */
+#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* BHI_DIS_S HW control available */
+#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* BHI_DIS_S HW control enabled */
+#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */
+#define X86_FEATURE_FAST_CPPC (21*32 + 5) /* AMD Fast CPPC */
/*
* BUG word(s)
*/
#define X86_BUG(x) (NCAPINTS*32 + (x))
-#define X86_BUG_F00F X86_BUG(0) /* Intel F00F */
-#define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */
-#define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */
+#define X86_BUG_F00F X86_BUG(0) /* "f00f" Intel F00F */
+#define X86_BUG_FDIV X86_BUG(1) /* "fdiv" FPU FDIV */
+#define X86_BUG_COMA X86_BUG(2) /* "coma" Cyrix 6x86 coma */
#define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
#define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
-#define X86_BUG_11AP X86_BUG(5) /* Bad local APIC aka 11AP */
-#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
-#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
-#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
+#define X86_BUG_11AP X86_BUG(5) /* "11ap" Bad local APIC aka 11AP */
+#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* "fxsave_leak" FXSAVE leaks FOP/FIP/FOP */
+#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* "clflush_monitor" AAI65, CLFLUSH required before MONITOR */
+#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* "sysret_ss_attrs" SYSRET doesn't fix up SS attrs */
#ifdef CONFIG_X86_32
/*
* 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional
* to avoid confusion.
*/
-#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
+#define X86_BUG_ESPFIX X86_BUG(9) /* IRET to 16-bit SS corrupts ESP/RSP high bits */
#endif
-#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */
-#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */
-#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */
-#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */
-#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
-#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
-#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
-#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */
-#define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
-#define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */
-#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */
-#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */
-#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */
-#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
-#define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
-#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */
-#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */
-#define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */
-#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
-#define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
-#define X86_BUG_GDS X86_BUG(30) /* CPU is affected by Gather Data Sampling */
-#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* CPU may incur #MC if non-TD software does partial write to TDX private memory */
+#define X86_BUG_NULL_SEG X86_BUG(10) /* "null_seg" Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* "swapgs_fence" SWAPGS without input dep on GS */
+#define X86_BUG_MONITOR X86_BUG(12) /* "monitor" IPI required to wake up remote CPU */
+#define X86_BUG_AMD_E400 X86_BUG(13) /* "amd_e400" CPU is among the affected by Erratum 400 */
+#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* "cpu_meltdown" CPU is affected by meltdown attack and needs kernel page table isolation */
+#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* "spectre_v1" CPU is affected by Spectre variant 1 attack with conditional branches */
+#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* "spectre_v2" CPU is affected by Spectre variant 2 attack with indirect branches */
+#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* "spec_store_bypass" CPU is affected by speculative store bypass attack */
+#define X86_BUG_L1TF X86_BUG(18) /* "l1tf" CPU is affected by L1 Terminal Fault */
+#define X86_BUG_MDS X86_BUG(19) /* "mds" CPU is affected by Microarchitectural data sampling */
+#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* "msbds_only" CPU is only affected by the MSDBS variant of BUG_MDS */
+#define X86_BUG_SWAPGS X86_BUG(21) /* "swapgs" CPU is affected by speculation through SWAPGS */
+#define X86_BUG_TAA X86_BUG(22) /* "taa" CPU is affected by TSX Async Abort(TAA) */
+#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* "itlb_multihit" CPU may incur MCE during certain page attribute changes */
+#define X86_BUG_SRBDS X86_BUG(24) /* "srbds" CPU may leak RNG bits if not mitigated */
+#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* "mmio_stale_data" CPU is affected by Processor MMIO Stale Data vulnerabilities */
+#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* "mmio_unknown" CPU is too old and its MMIO Stale Data status is unknown */
+#define X86_BUG_RETBLEED X86_BUG(27) /* "retbleed" CPU is affected by RETBleed */
+#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* "eibrs_pbrsb" EIBRS is vulnerable to Post Barrier RSB Predictions */
+#define X86_BUG_SMT_RSB X86_BUG(29) /* "smt_rsb" CPU is vulnerable to Cross-Thread Return Address Predictions */
+#define X86_BUG_GDS X86_BUG(30) /* "gds" CPU is affected by Gather Data Sampling */
+#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* "tdx_pw_mce" CPU may incur #MC if non-TD software does partial write to TDX private memory */
/* BUG word 2 */
-#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */
-#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */
-#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */
-#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */
+#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* "srso" AMD SRSO bug */
+#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* "div0" AMD DIV0 speculation bug */
+#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
+#define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index e022e6e..82c6a4d 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -566,6 +566,12 @@
#define MSR_RELOAD_PMC0 0x000014c1
#define MSR_RELOAD_FIXED_CTR0 0x00001309
+/* V6 PMON MSR range */
+#define MSR_IA32_PMC_V6_GP0_CTR 0x1900
+#define MSR_IA32_PMC_V6_GP0_CFG_A 0x1901
+#define MSR_IA32_PMC_V6_FX0_CTR 0x1980
+#define MSR_IA32_PMC_V6_STEP 4
+
/* KeyID partitioning between MKTME and TDX */
#define MSR_IA32_MKTME_KEYID_PARTITIONING 0x00000087
@@ -660,6 +666,8 @@
#define MSR_AMD64_RMP_BASE 0xc0010132
#define MSR_AMD64_RMP_END 0xc0010133
+#define MSR_SVSM_CAA 0xc001f000
+
/* AMD Collaborative Processor Performance Control MSRs */
#define MSR_AMD_CPPC_CAP1 0xc00102b0
#define MSR_AMD_CPPC_ENABLE 0xc00102b1
@@ -781,6 +789,8 @@
#define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT)
#define MSR_K7_FID_VID_CTL 0xc0010041
#define MSR_K7_FID_VID_STATUS 0xc0010042
+#define MSR_K7_HWCR_CPB_DIS_BIT 25
+#define MSR_K7_HWCR_CPB_DIS BIT_ULL(MSR_K7_HWCR_CPB_DIS_BIT)
/* K6 MSRs */
#define MSR_K6_WHCR 0xc0000082
@@ -1164,6 +1174,7 @@
#define MSR_IA32_QM_CTR 0xc8e
#define MSR_IA32_PQR_ASSOC 0xc8f
#define MSR_IA32_L3_CBM_BASE 0xc90
+#define MSR_RMID_SNC_CONFIG 0xca0
#define MSR_IA32_L2_CBM_BASE 0xd10
#define MSR_IA32_MBA_THRTL_BASE 0xd50
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 9fae1b7..bf57a82 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -106,6 +106,7 @@ struct kvm_ioapic_state {
#define KVM_RUN_X86_SMM (1 << 0)
#define KVM_RUN_X86_BUS_LOCK (1 << 1)
+#define KVM_RUN_X86_GUEST_MODE (1 << 2)
/* for KVM_GET_REGS and KVM_SET_REGS */
struct kvm_regs {
@@ -697,6 +698,11 @@ enum sev_cmd_id {
/* Second time is the charm; improved versions of the above ioctls. */
KVM_SEV_INIT2,
+ /* SNP-specific commands */
+ KVM_SEV_SNP_LAUNCH_START = 100,
+ KVM_SEV_SNP_LAUNCH_UPDATE,
+ KVM_SEV_SNP_LAUNCH_FINISH,
+
KVM_SEV_NR_MAX,
};
@@ -824,6 +830,48 @@ struct kvm_sev_receive_update_data {
__u32 pad2;
};
+struct kvm_sev_snp_launch_start {
+ __u64 policy;
+ __u8 gosvw[16];
+ __u16 flags;
+ __u8 pad0[6];
+ __u64 pad1[4];
+};
+
+/* Kept in sync with firmware values for simplicity. */
+#define KVM_SEV_SNP_PAGE_TYPE_NORMAL 0x1
+#define KVM_SEV_SNP_PAGE_TYPE_ZERO 0x3
+#define KVM_SEV_SNP_PAGE_TYPE_UNMEASURED 0x4
+#define KVM_SEV_SNP_PAGE_TYPE_SECRETS 0x5
+#define KVM_SEV_SNP_PAGE_TYPE_CPUID 0x6
+
+struct kvm_sev_snp_launch_update {
+ __u64 gfn_start;
+ __u64 uaddr;
+ __u64 len;
+ __u8 type;
+ __u8 pad0;
+ __u16 flags;
+ __u32 pad1;
+ __u64 pad2[4];
+};
+
+#define KVM_SEV_SNP_ID_BLOCK_SIZE 96
+#define KVM_SEV_SNP_ID_AUTH_SIZE 4096
+#define KVM_SEV_SNP_FINISH_DATA_SIZE 32
+
+struct kvm_sev_snp_launch_finish {
+ __u64 id_block_uaddr;
+ __u64 id_auth_uaddr;
+ __u8 id_block_en;
+ __u8 auth_key_en;
+ __u8 vcek_disabled;
+ __u8 host_data[KVM_SEV_SNP_FINISH_DATA_SIZE];
+ __u8 pad0[3];
+ __u16 flags;
+ __u64 pad1[4];
+};
+
#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1)
@@ -874,5 +922,6 @@ struct kvm_hyperv_eventfd {
#define KVM_X86_SW_PROTECTED_VM 1
#define KVM_X86_SEV_VM 2
#define KVM_X86_SEV_ES_VM 3
+#define KVM_X86_SNP_VM 4
#endif /* _ASM_X86_KVM_H */
diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
index 80e1df48..1814b41 100644
--- a/tools/arch/x86/include/uapi/asm/svm.h
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -115,6 +115,7 @@
#define SVM_VMGEXIT_AP_CREATE_ON_INIT 0
#define SVM_VMGEXIT_AP_CREATE 1
#define SVM_VMGEXIT_AP_DESTROY 2
+#define SVM_VMGEXIT_SNP_RUN_VMPL 0x80000018
#define SVM_VMGEXIT_HV_FEATURES 0x8000fffd
#define SVM_VMGEXIT_TERM_REQUEST 0x8000fffe
#define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code) \
diff --git a/tools/include/uapi/README b/tools/include/uapi/README
new file mode 100644
index 0000000..7147b1b
--- /dev/null
+++ b/tools/include/uapi/README
@@ -0,0 +1,73 @@
+Why we want a copy of kernel headers in tools?
+==============================================
+
+There used to be no copies, with tools/ code using kernel headers
+directly. From time to time tools/perf/ broke due to legitimate kernel
+hacking. At some point Linus complained about such direct usage. Then we
+adopted the current model.
+
+The way these headers are used in perf are not restricted to just
+including them to compile something.
+
+There are sometimes used in scripts that convert defines into string
+tables, etc, so some change may break one of these scripts, or new MSRs
+may use some different #define pattern, etc.
+
+E.g.:
+
+ $ ls -1 tools/perf/trace/beauty/*.sh | head -5
+ tools/perf/trace/beauty/arch_errno_names.sh
+ tools/perf/trace/beauty/drm_ioctl.sh
+ tools/perf/trace/beauty/fadvise.sh
+ tools/perf/trace/beauty/fsconfig.sh
+ tools/perf/trace/beauty/fsmount.sh
+ $
+ $ tools/perf/trace/beauty/fadvise.sh
+ static const char *fadvise_advices[] = {
+ [0] = "NORMAL",
+ [1] = "RANDOM",
+ [2] = "SEQUENTIAL",
+ [3] = "WILLNEED",
+ [4] = "DONTNEED",
+ [5] = "NOREUSE",
+ };
+ $
+
+The tools/perf/check-headers.sh script, part of the tools/ build
+process, points out changes in the original files.
+
+So its important not to touch the copies in tools/ when doing changes in
+the original kernel headers, that will be done later, when
+check-headers.sh inform about the change to the perf tools hackers.
+
+Another explanation from Ingo Molnar:
+It's better than all the alternatives we tried so far:
+
+ - Symbolic links and direct #includes: this was the original approach but
+ was pushed back on from the kernel side, when tooling modified the
+ headers and broke them accidentally for kernel builds.
+
+ - Duplicate self-defined ABI headers like glibc: double the maintenance
+ burden, double the chance for mistakes, plus there's no tech-driven
+ notification mechanism to look at new kernel side changes.
+
+What we are doing now is a third option:
+
+ - A software-enforced copy-on-write mechanism of kernel headers to
+ tooling, driven by non-fatal warnings on the tooling side build when
+ kernel headers get modified:
+
+ Warning: Kernel ABI header differences:
+ diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h
+ diff -u tools/include/uapi/linux/fs.h include/uapi/linux/fs.h
+ diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h
+ ...
+
+ The tooling policy is to always pick up the kernel side headers as-is,
+ and integate them into the tooling build. The warnings above serve as a
+ notification to tooling maintainers that there's changes on the kernel
+ side.
+
+We've been using this for many years now, and it might seem hacky, but
+works surprisingly well.
+
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index a00d53d..5bf6148 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -737,7 +737,7 @@ __SC_COMP(__NR_pselect6_time64, sys_pselect6, compat_sys_pselect6_time64)
#define __NR_ppoll_time64 414
__SC_COMP(__NR_ppoll_time64, sys_ppoll, compat_sys_ppoll_time64)
#define __NR_io_pgetevents_time64 416
-__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents)
+__SC_COMP(__NR_io_pgetevents_time64, sys_io_pgetevents, compat_sys_io_pgetevents_time64)
#define __NR_recvmmsg_time64 417
__SC_COMP(__NR_recvmmsg_time64, sys_recvmmsg, compat_sys_recvmmsg_time64)
#define __NR_mq_timedsend_time64 418
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index d4d86e5..535cb68 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -2163,6 +2163,15 @@ struct drm_i915_gem_context_param {
* supports this per context flag.
*/
#define I915_CONTEXT_PARAM_LOW_LATENCY 0xe
+
+/*
+ * I915_CONTEXT_PARAM_CONTEXT_IMAGE:
+ *
+ * Allows userspace to provide own context images.
+ *
+ * Note that this is a debug API not available on production kernel builds.
+ */
+#define I915_CONTEXT_PARAM_CONTEXT_IMAGE 0xf
/* Must be kept compact -- no holes and well documented */
/** @value: Context parameter value to be set or queried */
@@ -2564,6 +2573,24 @@ struct i915_context_param_engines {
struct i915_engine_class_instance engines[N__]; \
} __attribute__((packed)) name__
+struct i915_gem_context_param_context_image {
+ /** @engine: Engine class & instance to be configured. */
+ struct i915_engine_class_instance engine;
+
+ /** @flags: One of the supported flags or zero. */
+ __u32 flags;
+#define I915_CONTEXT_IMAGE_FLAG_ENGINE_INDEX (1u << 0)
+
+ /** @size: Size of the image blob pointed to by @image. */
+ __u32 size;
+
+ /** @mbz: Must be zero. */
+ __u32 mbz;
+
+ /** @image: Userspace memory containing the context image. */
+ __u64 image;
+} __attribute__((packed));
+
/**
* struct drm_i915_gem_context_create_ext_setparam - Context parameter
* to set or query during context creation.
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index e682ab6..d358add 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -81,6 +81,8 @@ enum {
#define IPPROTO_ETHERNET IPPROTO_ETHERNET
IPPROTO_RAW = 255, /* Raw IP packets */
#define IPPROTO_RAW IPPROTO_RAW
+ IPPROTO_SMC = 256, /* Shared Memory Communications */
+#define IPPROTO_SMC IPPROTO_SMC
IPPROTO_MPTCP = 262, /* Multipath TCP connection */
#define IPPROTO_MPTCP IPPROTO_MPTCP
IPPROTO_MAX
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index e5af8c6..637efc0 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -192,11 +192,24 @@ struct kvm_xen_exit {
/* Flags that describe what fields in emulation_failure hold valid data. */
#define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0)
+/*
+ * struct kvm_run can be modified by userspace at any time, so KVM must be
+ * careful to avoid TOCTOU bugs. In order to protect KVM, HINT_UNSAFE_IN_KVM()
+ * renames fields in struct kvm_run from <symbol> to <symbol>__unsafe when
+ * compiled into the kernel, ensuring that any use within KVM is obvious and
+ * gets extra scrutiny.
+ */
+#ifdef __KERNEL__
+#define HINT_UNSAFE_IN_KVM(_symbol) _symbol##__unsafe
+#else
+#define HINT_UNSAFE_IN_KVM(_symbol) _symbol
+#endif
+
/* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
struct kvm_run {
/* in */
__u8 request_interrupt_window;
- __u8 immediate_exit;
+ __u8 HINT_UNSAFE_IN_KVM(immediate_exit);
__u8 padding1[6];
/* out */
@@ -918,6 +931,8 @@ struct kvm_enable_cap {
#define KVM_CAP_GUEST_MEMFD 234
#define KVM_CAP_VM_TYPES 235
#define KVM_CAP_PRE_FAULT_MEMORY 236
+#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237
+#define KVM_CAP_X86_GUEST_MODE 238
struct kvm_irq_routing_irqchip {
__u32 irqchip;
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 3a64499..4842c36 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -1349,12 +1349,14 @@ union perf_mem_data_src {
#define PERF_MEM_LVLNUM_L2 0x02 /* L2 */
#define PERF_MEM_LVLNUM_L3 0x03 /* L3 */
#define PERF_MEM_LVLNUM_L4 0x04 /* L4 */
-/* 5-0x7 available */
+#define PERF_MEM_LVLNUM_L2_MHB 0x05 /* L2 Miss Handling Buffer */
+#define PERF_MEM_LVLNUM_MSC 0x06 /* Memory-side Cache */
+/* 0x7 available */
#define PERF_MEM_LVLNUM_UNC 0x08 /* Uncached */
#define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */
#define PERF_MEM_LVLNUM_IO 0x0a /* I/O */
#define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
-#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */
+#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB / L1 Miss Handling Buffer */
#define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */
#define PERF_MEM_LVLNUM_PMEM 0x0e /* PMEM */
#define PERF_MEM_LVLNUM_NA 0x0f /* N/A */
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index 67626d5..887a252 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -126,9 +126,15 @@ struct statx {
__u64 stx_mnt_id;
__u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */
__u32 stx_dio_offset_align; /* File offset alignment for direct I/O */
- __u64 stx_subvol; /* Subvolume identifier */
/* 0xa0 */
- __u64 __spare3[11]; /* Spare space for future expansion */
+ __u64 stx_subvol; /* Subvolume identifier */
+ __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */
+ __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */
+ /* 0xb0 */
+ __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */
+ __u32 __spare1[1];
+ /* 0xb8 */
+ __u64 __spare3[9]; /* Spare space for future expansion */
/* 0x100 */
};
@@ -157,6 +163,7 @@ struct statx {
#define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */
#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */
#define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */
+#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */
#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
@@ -192,6 +199,7 @@ struct statx {
#define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */
#define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */
#define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */
+#define STATX_ATTR_WRITE_ATOMIC 0x00400000 /* File supports atomic write operations */
#endif /* _UAPI_LINUX_STAT_H */
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 3656f1c..ebae841 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -230,8 +230,10 @@
178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend
179 32 pread64 sys_ppc_pread64 compat_sys_ppc_pread64
179 64 pread64 sys_pread64
+179 spu pread64 sys_pread64
180 32 pwrite64 sys_ppc_pwrite64 compat_sys_ppc_pwrite64
180 64 pwrite64 sys_pwrite64
+180 spu pwrite64 sys_pwrite64
181 common chown sys_chown
182 common getcwd sys_getcwd
183 common capget sys_capget
@@ -246,6 +248,7 @@
190 common ugetrlimit sys_getrlimit compat_sys_getrlimit
191 32 readahead sys_ppc_readahead compat_sys_ppc_readahead
191 64 readahead sys_readahead
+191 spu readahead sys_readahead
192 32 mmap2 sys_mmap2 compat_sys_mmap2
193 32 truncate64 sys_ppc_truncate64 compat_sys_ppc_truncate64
194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64
@@ -293,6 +296,7 @@
232 nospu set_tid_address sys_set_tid_address
233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64
233 64 fadvise64 sys_fadvise64
+233 spu fadvise64 sys_fadvise64
234 nospu exit_group sys_exit_group
235 nospu lookup_dcookie sys_ni_syscall
236 common epoll_create sys_epoll_create
@@ -502,7 +506,7 @@
412 32 utimensat_time64 sys_utimensat sys_utimensat
413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64
414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64
-416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents
+416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64
417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64
418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend
419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index bd0fee2..0107118 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -418,7 +418,7 @@
412 32 utimensat_time64 - sys_utimensat
413 32 pselect6_time64 - compat_sys_pselect6_time64
414 32 ppoll_time64 - compat_sys_ppoll_time64
-416 32 io_pgetevents_time64 - sys_io_pgetevents
+416 32 io_pgetevents_time64 - compat_sys_io_pgetevents_time64
417 32 recvmmsg_time64 - compat_sys_recvmmsg_time64
418 32 mq_timedsend_time64 - sys_mq_timedsend
419 32 mq_timedreceive_time64 - sys_mq_timedreceive
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index a396f6e..7093ee2 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -1,8 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
#
# 64-bit system call numbers and entry vectors
#
# The format is:
-# <number> <abi> <name> <entry point>
+# <number> <abi> <name> <entry point> [<compat entry point> [noreturn]]
#
# The __x64_sys_*() stubs are created on-the-fly for sys_*() system calls
#
@@ -68,7 +69,7 @@
57 common fork sys_fork
58 common vfork sys_vfork
59 64 execve sys_execve
-60 common exit sys_exit
+60 common exit sys_exit - noreturn
61 common wait4 sys_wait4
62 common kill sys_kill
63 common uname sys_newuname
@@ -239,7 +240,7 @@
228 common clock_gettime sys_clock_gettime
229 common clock_getres sys_clock_getres
230 common clock_nanosleep sys_clock_nanosleep
-231 common exit_group sys_exit_group
+231 common exit_group sys_exit_group - noreturn
232 common epoll_wait sys_epoll_wait
233 common epoll_ctl sys_epoll_ctl
234 common tgkill sys_tgkill
@@ -343,6 +344,7 @@
332 common statx sys_statx
333 common io_pgetevents sys_io_pgetevents
334 common rseq sys_rseq
+335 common uretprobe sys_uretprobe
# don't use numbers 387 through 423, add new calls after the last
# 'common' entry
424 common pidfd_send_signal sys_pidfd_send_signal
diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c
index de76bbc..5c9335f 100644
--- a/tools/perf/builtin-daemon.c
+++ b/tools/perf/builtin-daemon.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <internal/lib.h>
+#include <inttypes.h>
#include <subcmd/parse-options.h>
#include <api/fd/array.h>
#include <api/fs/fs.h>
@@ -688,7 +689,7 @@ static int cmd_session_list(struct daemon *daemon, union cmd *cmd, FILE *out)
/* lock */
csv_sep, daemon->base, "lock");
- fprintf(out, "%c%lu",
+ fprintf(out, "%c%" PRIu64,
/* session up time */
csv_sep, (curr - daemon->start) / 60);
@@ -700,7 +701,7 @@ static int cmd_session_list(struct daemon *daemon, union cmd *cmd, FILE *out)
daemon->base, SESSION_OUTPUT);
fprintf(out, " lock: %s/lock\n",
daemon->base);
- fprintf(out, " up: %lu minutes\n",
+ fprintf(out, " up: %" PRIu64 " minutes\n",
(curr - daemon->start) / 60);
}
}
@@ -727,7 +728,7 @@ static int cmd_session_list(struct daemon *daemon, union cmd *cmd, FILE *out)
/* session ack */
csv_sep, session->base, SESSION_ACK);
- fprintf(out, "%c%lu",
+ fprintf(out, "%c%" PRIu64,
/* session up time */
csv_sep, (curr - session->start) / 60);
@@ -745,7 +746,7 @@ static int cmd_session_list(struct daemon *daemon, union cmd *cmd, FILE *out)
session->base, SESSION_CONTROL);
fprintf(out, " ack: %s/%s\n",
session->base, SESSION_ACK);
- fprintf(out, " up: %lu minutes\n",
+ fprintf(out, " up: %" PRIu64 " minutes\n",
(curr - session->start) / 60);
}
}
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index 89d16b90..df9cdb8 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -76,7 +76,7 @@ struct msghdr {
__kernel_size_t msg_controllen; /* ancillary data buffer length */
struct kiocb *msg_iocb; /* ptr to iocb for async requests */
struct ubuf_info *msg_ubuf;
- int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb,
+ int (*sg_from_iter)(struct sk_buff *skb,
struct iov_iter *from, size_t length);
};
@@ -442,11 +442,14 @@ extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
extern int __sys_socket(int family, int type, int protocol);
extern struct file *__sys_socket_file(int family, int type, int protocol);
extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
+extern int __sys_bind_socket(struct socket *sock, struct sockaddr_storage *address,
+ int addrlen);
extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr,
int addrlen, int file_flags);
extern int __sys_connect(int fd, struct sockaddr __user *uservaddr,
int addrlen);
extern int __sys_listen(int fd, int backlog);
+extern int __sys_listen_socket(struct socket *sock, int backlog);
extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr,
int __user *usockaddr_len);
extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h
index 45e4e64..7539717 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fs.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h
@@ -329,12 +329,17 @@ typedef int __bitwise __kernel_rwf_t;
/* per-IO negation of O_APPEND */
#define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020)
+/* Atomic Write */
+#define RWF_ATOMIC ((__force __kernel_rwf_t)0x00000040)
+
/* mask of flags supported by the kernel */
#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
- RWF_APPEND | RWF_NOAPPEND)
+ RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC)
+
+#define PROCFS_IOCTL_MAGIC 'f'
/* Pagemap ioctl */
-#define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg)
+#define PAGEMAP_SCAN _IOWR(PROCFS_IOCTL_MAGIC, 16, struct pm_scan_arg)
/* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */
#define PAGE_IS_WPALLOWED (1 << 0)
@@ -393,4 +398,158 @@ struct pm_scan_arg {
__u64 return_mask;
};
+/* /proc/<pid>/maps ioctl */
+#define PROCMAP_QUERY _IOWR(PROCFS_IOCTL_MAGIC, 17, struct procmap_query)
+
+enum procmap_query_flags {
+ /*
+ * VMA permission flags.
+ *
+ * Can be used as part of procmap_query.query_flags field to look up
+ * only VMAs satisfying specified subset of permissions. E.g., specifying
+ * PROCMAP_QUERY_VMA_READABLE only will return both readable and read/write VMAs,
+ * while having PROCMAP_QUERY_VMA_READABLE | PROCMAP_QUERY_VMA_WRITABLE will only
+ * return read/write VMAs, though both executable/non-executable and
+ * private/shared will be ignored.
+ *
+ * PROCMAP_QUERY_VMA_* flags are also returned in procmap_query.vma_flags
+ * field to specify actual VMA permissions.
+ */
+ PROCMAP_QUERY_VMA_READABLE = 0x01,
+ PROCMAP_QUERY_VMA_WRITABLE = 0x02,
+ PROCMAP_QUERY_VMA_EXECUTABLE = 0x04,
+ PROCMAP_QUERY_VMA_SHARED = 0x08,
+ /*
+ * Query modifier flags.
+ *
+ * By default VMA that covers provided address is returned, or -ENOENT
+ * is returned. With PROCMAP_QUERY_COVERING_OR_NEXT_VMA flag set, closest
+ * VMA with vma_start > addr will be returned if no covering VMA is
+ * found.
+ *
+ * PROCMAP_QUERY_FILE_BACKED_VMA instructs query to consider only VMAs that
+ * have file backing. Can be combined with PROCMAP_QUERY_COVERING_OR_NEXT_VMA
+ * to iterate all VMAs with file backing.
+ */
+ PROCMAP_QUERY_COVERING_OR_NEXT_VMA = 0x10,
+ PROCMAP_QUERY_FILE_BACKED_VMA = 0x20,
+};
+
+/*
+ * Input/output argument structured passed into ioctl() call. It can be used
+ * to query a set of VMAs (Virtual Memory Areas) of a process.
+ *
+ * Each field can be one of three kinds, marked in a short comment to the
+ * right of the field:
+ * - "in", input argument, user has to provide this value, kernel doesn't modify it;
+ * - "out", output argument, kernel sets this field with VMA data;
+ * - "in/out", input and output argument; user provides initial value (used
+ * to specify maximum allowable buffer size), and kernel sets it to actual
+ * amount of data written (or zero, if there is no data).
+ *
+ * If matching VMA is found (according to criterias specified by
+ * query_addr/query_flags, all the out fields are filled out, and ioctl()
+ * returns 0. If there is no matching VMA, -ENOENT will be returned.
+ * In case of any other error, negative error code other than -ENOENT is
+ * returned.
+ *
+ * Most of the data is similar to the one returned as text in /proc/<pid>/maps
+ * file, but procmap_query provides more querying flexibility. There are no
+ * consistency guarantees between subsequent ioctl() calls, but data returned
+ * for matched VMA is self-consistent.
+ */
+struct procmap_query {
+ /* Query struct size, for backwards/forward compatibility */
+ __u64 size;
+ /*
+ * Query flags, a combination of enum procmap_query_flags values.
+ * Defines query filtering and behavior, see enum procmap_query_flags.
+ *
+ * Input argument, provided by user. Kernel doesn't modify it.
+ */
+ __u64 query_flags; /* in */
+ /*
+ * Query address. By default, VMA that covers this address will
+ * be looked up. PROCMAP_QUERY_* flags above modify this default
+ * behavior further.
+ *
+ * Input argument, provided by user. Kernel doesn't modify it.
+ */
+ __u64 query_addr; /* in */
+ /* VMA starting (inclusive) and ending (exclusive) address, if VMA is found. */
+ __u64 vma_start; /* out */
+ __u64 vma_end; /* out */
+ /* VMA permissions flags. A combination of PROCMAP_QUERY_VMA_* flags. */
+ __u64 vma_flags; /* out */
+ /* VMA backing page size granularity. */
+ __u64 vma_page_size; /* out */
+ /*
+ * VMA file offset. If VMA has file backing, this specifies offset
+ * within the file that VMA's start address corresponds to.
+ * Is set to zero if VMA has no backing file.
+ */
+ __u64 vma_offset; /* out */
+ /* Backing file's inode number, or zero, if VMA has no backing file. */
+ __u64 inode; /* out */
+ /* Backing file's device major/minor number, or zero, if VMA has no backing file. */
+ __u32 dev_major; /* out */
+ __u32 dev_minor; /* out */
+ /*
+ * If set to non-zero value, signals the request to return VMA name
+ * (i.e., VMA's backing file's absolute path, with " (deleted)" suffix
+ * appended, if file was unlinked from FS) for matched VMA. VMA name
+ * can also be some special name (e.g., "[heap]", "[stack]") or could
+ * be even user-supplied with prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME).
+ *
+ * Kernel will set this field to zero, if VMA has no associated name.
+ * Otherwise kernel will return actual amount of bytes filled in
+ * user-supplied buffer (see vma_name_addr field below), including the
+ * terminating zero.
+ *
+ * If VMA name is longer that user-supplied maximum buffer size,
+ * -E2BIG error is returned.
+ *
+ * If this field is set to non-zero value, vma_name_addr should point
+ * to valid user space memory buffer of at least vma_name_size bytes.
+ * If set to zero, vma_name_addr should be set to zero as well
+ */
+ __u32 vma_name_size; /* in/out */
+ /*
+ * If set to non-zero value, signals the request to extract and return
+ * VMA's backing file's build ID, if the backing file is an ELF file
+ * and it contains embedded build ID.
+ *
+ * Kernel will set this field to zero, if VMA has no backing file,
+ * backing file is not an ELF file, or ELF file has no build ID
+ * embedded.
+ *
+ * Build ID is a binary value (not a string). Kernel will set
+ * build_id_size field to exact number of bytes used for build ID.
+ * If build ID is requested and present, but needs more bytes than
+ * user-supplied maximum buffer size (see build_id_addr field below),
+ * -E2BIG error will be returned.
+ *
+ * If this field is set to non-zero value, build_id_addr should point
+ * to valid user space memory buffer of at least build_id_size bytes.
+ * If set to zero, build_id_addr should be set to zero as well
+ */
+ __u32 build_id_size; /* in/out */
+ /*
+ * User-supplied address of a buffer of at least vma_name_size bytes
+ * for kernel to fill with matched VMA's name (see vma_name_size field
+ * description above for details).
+ *
+ * Should be set to zero if VMA name should not be returned.
+ */
+ __u64 vma_name_addr; /* in */
+ /*
+ * User-supplied address of a buffer of at least build_id_size bytes
+ * for kernel to fill with matched VMA's ELF build ID, if available
+ * (see build_id_size field description above for details).
+ *
+ * Should be set to zero if build ID should not be returned.
+ */
+ __u64 build_id_addr; /* in */
+};
+
#endif /* _UAPI_LINUX_FS_H */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h
index ad5478d..225bc36 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/mount.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h
@@ -154,7 +154,7 @@ struct mount_attr {
*/
struct statmount {
__u32 size; /* Total size, including strings */
- __u32 __spare1;
+ __u32 mnt_opts; /* [str] Mount options of the mount */
__u64 mask; /* What results were written */
__u32 sb_dev_major; /* Device ID */
__u32 sb_dev_minor;
@@ -172,7 +172,8 @@ struct statmount {
__u64 propagate_from; /* Propagation from in current namespace */
__u32 mnt_root; /* [str] Root of mount relative to root of fs */
__u32 mnt_point; /* [str] Mountpoint relative to current root */
- __u64 __spare2[50];
+ __u64 mnt_ns_id; /* ID of the mount namespace */
+ __u64 __spare2[49];
char str[]; /* Variable size part containing strings */
};
@@ -188,10 +189,12 @@ struct mnt_id_req {
__u32 spare;
__u64 mnt_id;
__u64 param;
+ __u64 mnt_ns_id;
};
/* List of all mnt_id_req versions. */
#define MNT_ID_REQ_SIZE_VER0 24 /* sizeof first published struct */
+#define MNT_ID_REQ_SIZE_VER1 32 /* sizeof second published struct */
/*
* @mask bits for statmount(2)
@@ -202,10 +205,13 @@ struct mnt_id_req {
#define STATMOUNT_MNT_ROOT 0x00000008U /* Want/got mnt_root */
#define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */
#define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */
+#define STATMOUNT_MNT_NS_ID 0x00000040U /* Want/got mnt_ns_id */
+#define STATMOUNT_MNT_OPTS 0x00000080U /* Want/got mnt_opts */
/*
* Special @mnt_id values that can be passed to listmount
*/
#define LSMT_ROOT 0xffffffffffffffff /* root mount */
+#define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */
#endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/stat.h b/tools/perf/trace/beauty/include/uapi/linux/stat.h
index 67626d5..887a252 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/stat.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/stat.h
@@ -126,9 +126,15 @@ struct statx {
__u64 stx_mnt_id;
__u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */
__u32 stx_dio_offset_align; /* File offset alignment for direct I/O */
- __u64 stx_subvol; /* Subvolume identifier */
/* 0xa0 */
- __u64 __spare3[11]; /* Spare space for future expansion */
+ __u64 stx_subvol; /* Subvolume identifier */
+ __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */
+ __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */
+ /* 0xb0 */
+ __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */
+ __u32 __spare1[1];
+ /* 0xb8 */
+ __u64 __spare3[9]; /* Spare space for future expansion */
/* 0x100 */
};
@@ -157,6 +163,7 @@ struct statx {
#define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */
#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */
#define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */
+#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */
#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
@@ -192,6 +199,7 @@ struct statx {
#define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */
#define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */
#define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */
+#define STATX_ATTR_WRITE_ATOMIC 0x00400000 /* File supports atomic write operations */
#endif /* _UAPI_LINUX_STAT_H */
diff --git a/tools/perf/trace/beauty/include/uapi/sound/asound.h b/tools/perf/trace/beauty/include/uapi/sound/asound.h
index 628d46a..8bf7e8a 100644
--- a/tools/perf/trace/beauty/include/uapi/sound/asound.h
+++ b/tools/perf/trace/beauty/include/uapi/sound/asound.h
@@ -142,7 +142,7 @@ struct snd_hwdep_dsp_image {
* *
*****************************************************************************/
-#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 17)
+#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 18)
typedef unsigned long snd_pcm_uframes_t;
typedef signed long snd_pcm_sframes_t;
@@ -334,7 +334,7 @@ union snd_pcm_sync_id {
unsigned char id[16];
unsigned short id16[8];
unsigned int id32[4];
-};
+} __attribute__((deprecated));
struct snd_pcm_info {
unsigned int device; /* RO/WR (control): device number */
@@ -348,7 +348,7 @@ struct snd_pcm_info {
int dev_subclass; /* SNDRV_PCM_SUBCLASS_* */
unsigned int subdevices_count;
unsigned int subdevices_avail;
- union snd_pcm_sync_id sync; /* hardware synchronization ID */
+ unsigned char pad1[16]; /* was: hardware synchronization ID */
unsigned char reserved[64]; /* reserved for future... */
};
@@ -420,7 +420,8 @@ struct snd_pcm_hw_params {
unsigned int rate_num; /* R: rate numerator */
unsigned int rate_den; /* R: rate denominator */
snd_pcm_uframes_t fifo_size; /* R: chip FIFO size in frames */
- unsigned char reserved[64]; /* reserved for future */
+ unsigned char sync[16]; /* R: synchronization ID (perfect sync - one clock source) */
+ unsigned char reserved[48]; /* reserved for future */
};
enum {
diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild
index 030b388..3d1ca9e 100644
--- a/tools/testing/cxl/Kbuild
+++ b/tools/testing/cxl/Kbuild
@@ -14,6 +14,7 @@
ldflags-y += --wrap=devm_cxl_add_rch_dport
ldflags-y += --wrap=cxl_rcd_component_reg_phys
ldflags-y += --wrap=cxl_endpoint_parse_cdat
+ldflags-y += --wrap=cxl_setup_parent_dport
DRIVERS := ../../../drivers
CXL_SRC := $(DRIVERS)/cxl
diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c
index 6f73794..d619672 100644
--- a/tools/testing/cxl/test/mock.c
+++ b/tools/testing/cxl/test/mock.c
@@ -299,6 +299,18 @@ void __wrap_cxl_endpoint_parse_cdat(struct cxl_port *port)
}
EXPORT_SYMBOL_NS_GPL(__wrap_cxl_endpoint_parse_cdat, CXL);
+void __wrap_cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport)
+{
+ int index;
+ struct cxl_mock_ops *ops = get_cxl_mock_ops(&index);
+
+ if (!ops || !ops->is_mock_port(dport->dport_dev))
+ cxl_setup_parent_dport(host, dport);
+
+ put_cxl_mock_ops(index);
+}
+EXPORT_SYMBOL_NS_GPL(__wrap_cxl_setup_parent_dport, CXL);
+
MODULE_LICENSE("GPL v2");
MODULE_IMPORT_NS(ACPI);
MODULE_IMPORT_NS(CXL);
diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
index 16bdc3e..ef70b88 100644
--- a/tools/testing/selftests/bpf/progs/iters.c
+++ b/tools/testing/selftests/bpf/progs/iters.c
@@ -1432,4 +1432,58 @@ int iter_arr_with_actual_elem_count(const void *ctx)
return sum;
}
+__u32 upper, select_n, result;
+__u64 global;
+
+static __noinline bool nest_2(char *str)
+{
+ /* some insns (including branch insns) to ensure stacksafe() is triggered
+ * in nest_2(). This way, stacksafe() can compare frame associated with nest_1().
+ */
+ if (str[0] == 't')
+ return true;
+ if (str[1] == 'e')
+ return true;
+ if (str[2] == 's')
+ return true;
+ if (str[3] == 't')
+ return true;
+ return false;
+}
+
+static __noinline bool nest_1(int n)
+{
+ /* case 0: allocate stack, case 1: no allocate stack */
+ switch (n) {
+ case 0: {
+ char comm[16];
+
+ if (bpf_get_current_comm(comm, 16))
+ return false;
+ return nest_2(comm);
+ }
+ case 1:
+ return nest_2((char *)&global);
+ default:
+ return false;
+ }
+}
+
+SEC("raw_tp")
+__success
+int iter_subprog_check_stacksafe(const void *ctx)
+{
+ long i;
+
+ bpf_for(i, 0, upper) {
+ if (!nest_1(select_n)) {
+ result = 1;
+ return 0;
+ }
+ }
+
+ result = 2;
+ return 0;
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c
index 991c473..12b4eb9 100644
--- a/tools/testing/selftests/core/close_range_test.c
+++ b/tools/testing/selftests/core/close_range_test.c
@@ -589,4 +589,39 @@ TEST(close_range_cloexec_unshare_syzbot)
EXPECT_EQ(close(fd3), 0);
}
+TEST(close_range_bitmap_corruption)
+{
+ pid_t pid;
+ int status;
+ struct __clone_args args = {
+ .flags = CLONE_FILES,
+ .exit_signal = SIGCHLD,
+ };
+
+ /* get the first 128 descriptors open */
+ for (int i = 2; i < 128; i++)
+ EXPECT_GE(dup2(0, i), 0);
+
+ /* get descriptor table shared */
+ pid = sys_clone3(&args, sizeof(args));
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* unshare and truncate descriptor table down to 64 */
+ if (sys_close_range(64, ~0U, CLOSE_RANGE_UNSHARE))
+ exit(EXIT_FAILURE);
+
+ ASSERT_EQ(fcntl(64, F_GETFD), -1);
+ /* ... and verify that the range 64..127 is not
+ stuck "fully used" according to secondary bitmap */
+ EXPECT_EQ(dup(0), 64)
+ exit(EXIT_FAILURE);
+ exit(EXIT_SUCCESS);
+ }
+
+ EXPECT_EQ(waitpid(pid, &status, 0), pid);
+ EXPECT_EQ(true, WIFEXITED(status));
+ EXPECT_EQ(0, WEXITSTATUS(status));
+}
+
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh b/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh
index 877cd6d..fe905a7 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh
@@ -2,6 +2,7 @@
# SPDX-License-Identifier: GPL-2.0
lib_dir=$(dirname $0)/../../../net/forwarding
+ethtool_lib_dir=$(dirname $0)/../hw
ALL_TESTS="
autoneg
@@ -11,7 +12,7 @@
NUM_NETIFS=2
: ${TIMEOUT:=30000} # ms
source $lib_dir/lib.sh
-source $lib_dir/ethtool_lib.sh
+source $ethtool_lib_dir/ethtool_lib.sh
setup_prepare()
{
diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c
index 6343f40..4927b9a 100644
--- a/tools/testing/selftests/iommu/iommufd.c
+++ b/tools/testing/selftests/iommu/iommufd.c
@@ -825,7 +825,7 @@ TEST_F(iommufd_ioas, copy_area)
{
struct iommu_ioas_copy copy_cmd = {
.size = sizeof(copy_cmd),
- .flags = IOMMU_IOAS_MAP_FIXED_IOVA,
+ .flags = IOMMU_IOAS_MAP_FIXED_IOVA | IOMMU_IOAS_MAP_WRITEABLE,
.dst_ioas_id = self->ioas_id,
.src_ioas_id = self->ioas_id,
.length = PAGE_SIZE,
@@ -1318,7 +1318,7 @@ TEST_F(iommufd_ioas, copy_sweep)
{
struct iommu_ioas_copy copy_cmd = {
.size = sizeof(copy_cmd),
- .flags = IOMMU_IOAS_MAP_FIXED_IOVA,
+ .flags = IOMMU_IOAS_MAP_FIXED_IOVA | IOMMU_IOAS_MAP_WRITEABLE,
.src_ioas_id = self->ioas_id,
.dst_iova = MOCK_APERTURE_START,
.length = MOCK_PAGE_SIZE,
@@ -1608,7 +1608,7 @@ TEST_F(iommufd_mock_domain, user_copy)
};
struct iommu_ioas_copy copy_cmd = {
.size = sizeof(copy_cmd),
- .flags = IOMMU_IOAS_MAP_FIXED_IOVA,
+ .flags = IOMMU_IOAS_MAP_FIXED_IOVA | IOMMU_IOAS_MAP_WRITEABLE,
.dst_ioas_id = self->ioas_id,
.dst_iova = MOCK_APERTURE_START,
.length = BUFFER_SIZE,
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index 709d7d7..4abebde 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -32,13 +32,13 @@ static struct feature_id_reg feat_id_regs[] = {
{
ARM64_SYS_REG(3, 0, 10, 2, 2), /* PIRE0_EL1 */
ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */
- 4,
+ 8,
1
},
{
ARM64_SYS_REG(3, 0, 10, 2, 3), /* PIR_EL1 */
ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */
- 4,
+ 8,
1
}
};
diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
index 69849ac..618cd24 100644
--- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
@@ -184,6 +184,33 @@ static void test_apic_id(void)
kvm_vm_free(vm);
}
+static void test_x2apic_id(void)
+{
+ struct kvm_lapic_state lapic = {};
+ struct kvm_vcpu *vcpu;
+ struct kvm_vm *vm;
+ int i;
+
+ vm = vm_create_with_one_vcpu(&vcpu, NULL);
+ vcpu_set_msr(vcpu, MSR_IA32_APICBASE, MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
+
+ /*
+ * Try stuffing a modified x2APIC ID, KVM should ignore the value and
+ * always return the vCPU's default/readonly x2APIC ID.
+ */
+ for (i = 0; i <= 0xff; i++) {
+ *(u32 *)(lapic.regs + APIC_ID) = i << 24;
+ *(u32 *)(lapic.regs + APIC_SPIV) = APIC_SPIV_APIC_ENABLED;
+ vcpu_ioctl(vcpu, KVM_SET_LAPIC, &lapic);
+
+ vcpu_ioctl(vcpu, KVM_GET_LAPIC, &lapic);
+ TEST_ASSERT(*((u32 *)&lapic.regs[APIC_ID]) == vcpu->id << 24,
+ "x2APIC ID should be fully readonly");
+ }
+
+ kvm_vm_free(vm);
+}
+
int main(int argc, char *argv[])
{
struct xapic_vcpu x = {
@@ -211,4 +238,5 @@ int main(int argc, char *argv[])
kvm_vm_free(vm);
test_apic_id();
+ test_x2apic_id();
}
diff --git a/tools/testing/selftests/livepatch/test-livepatch.sh b/tools/testing/selftests/livepatch/test-livepatch.sh
index 65c9c05..bd13257 100755
--- a/tools/testing/selftests/livepatch/test-livepatch.sh
+++ b/tools/testing/selftests/livepatch/test-livepatch.sh
@@ -139,11 +139,8 @@
grep 'live patched' /proc/cmdline > /dev/kmsg
grep 'live patched' /proc/meminfo > /dev/kmsg
-mods=(/sys/kernel/livepatch/*)
-nmods=${#mods[@]}
-if [ "$nmods" -ne 1 ]; then
- die "Expecting only one moduled listed, found $nmods"
-fi
+loop_until 'mods=(/sys/kernel/livepatch/*); nmods=${#mods[@]}; [[ "$nmods" -eq 1 ]]' ||
+ die "Expecting only one moduled listed, found $nmods"
# These modules were disabled by the atomic replace
for mod in $MOD_LIVEPATCH3 $MOD_LIVEPATCH2 $MOD_LIVEPATCH1; do
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index 7b8a5de..cfad627 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -53,7 +53,9 @@
TEST_GEN_FILES += map_fixed_noreplace
TEST_GEN_FILES += map_hugetlb
TEST_GEN_FILES += map_populate
+ifneq (,$(filter $(ARCH),arm64 riscv riscv64 x86 x86_64))
TEST_GEN_FILES += memfd_secret
+endif
TEST_GEN_FILES += migration
TEST_GEN_FILES += mkdirty
TEST_GEN_FILES += mlock-random-test
diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c
index e140558..2c3a0eb 100644
--- a/tools/testing/selftests/mm/compaction_test.c
+++ b/tools/testing/selftests/mm/compaction_test.c
@@ -89,9 +89,10 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size,
int fd, ret = -1;
int compaction_index = 0;
char nr_hugepages[20] = {0};
- char init_nr_hugepages[20] = {0};
+ char init_nr_hugepages[24] = {0};
- sprintf(init_nr_hugepages, "%lu", initial_nr_hugepages);
+ snprintf(init_nr_hugepages, sizeof(init_nr_hugepages),
+ "%lu", initial_nr_hugepages);
/* We want to test with 80% of available memory. Else, OOM killer comes
in to play */
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index 03ac4f2..36045ed 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -374,8 +374,11 @@
# MADV_POPULATE_READ and MADV_POPULATE_WRITE tests
CATEGORY="madv_populate" run_test ./madv_populate
+if [ -x ./memfd_secret ]
+then
(echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope 2>&1) | tap_prefix
CATEGORY="memfd_secret" run_test ./memfd_secret
+fi
# KSM KSM_MERGE_TIME_HUGE_PAGES test with size of 100
CATEGORY="ksm" run_test ./ksm_tests -H -s 100
diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c
index 16d0c17..535eb2c 100644
--- a/tools/testing/selftests/net/af_unix/msg_oob.c
+++ b/tools/testing/selftests/net/af_unix/msg_oob.c
@@ -209,7 +209,7 @@ static void __sendpair(struct __test_metadata *_metadata,
static void __recvpair(struct __test_metadata *_metadata,
FIXTURE_DATA(msg_oob) *self,
- const void *expected_buf, int expected_len,
+ const char *expected_buf, int expected_len,
int buf_len, int flags)
{
int i, ret[2], recv_errno[2], expected_errno = 0;
diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
index 64bd00f..90f8a24 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
@@ -1,7 +1,7 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn"
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn other_tpid"
NUM_NETIFS=4
CHECK_TC="yes"
source lib.sh
@@ -142,6 +142,58 @@
bridge fdb del de:ad:be:ef:13:37 dev $swp1 master vlan 1 &> /dev/null
}
+other_tpid()
+{
+ local mac=de:ad:be:ef:13:37
+
+ # Test that packets with TPID 802.1ad VID 3 + TPID 802.1Q VID 5 are
+ # classified as untagged by a bridge with vlan_protocol 802.1Q, and
+ # are processed in the PVID of the ingress port (here 1). Not VID 3,
+ # and not VID 5.
+ RET=0
+
+ tc qdisc add dev $h2 clsact
+ tc filter add dev $h2 ingress protocol all pref 1 handle 101 \
+ flower dst_mac $mac action drop
+ ip link set $h2 promisc on
+ ethtool -K $h2 rx-vlan-filter off rx-vlan-stag-filter off
+
+ $MZ -q $h1 -c 1 -b $mac -a own "88:a8 00:03 81:00 00:05 08:00 aa-aa-aa-aa-aa-aa-aa-aa-aa"
+ sleep 1
+
+ # Match on 'self' addresses as well, for those drivers which
+ # do not push their learned addresses to the bridge software
+ # database
+ bridge -j fdb show $swp1 | \
+ jq -e ".[] | select(.mac == \"$(mac_get $h1)\") | select(.vlan == 1)" &> /dev/null
+ check_err $? "FDB entry was not learned when it should"
+
+ log_test "FDB entry in PVID for VLAN-tagged with other TPID"
+
+ RET=0
+ tc -j -s filter show dev $h2 ingress \
+ | jq -e ".[] | select(.options.handle == 101) \
+ | select(.options.actions[0].stats.packets == 1)" &> /dev/null
+ check_err $? "Packet was not forwarded when it should"
+ log_test "Reception of VLAN with other TPID as untagged"
+
+ bridge vlan del dev $swp1 vid 1
+
+ $MZ -q $h1 -c 1 -b $mac -a own "88:a8 00:03 81:00 00:05 08:00 aa-aa-aa-aa-aa-aa-aa-aa-aa"
+ sleep 1
+
+ RET=0
+ tc -j -s filter show dev $h2 ingress \
+ | jq -e ".[] | select(.options.handle == 101) \
+ | select(.options.actions[0].stats.packets == 1)" &> /dev/null
+ check_err $? "Packet was forwarded when should not"
+ log_test "Reception of VLAN with other TPID as untagged (no PVID)"
+
+ bridge vlan add dev $swp1 vid 1 pvid untagged
+ ip link set $h2 promisc off
+ tc qdisc del dev $h2 clsact
+}
+
trap cleanup EXIT
setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index ff96bb7..718d04a 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -500,6 +500,11 @@
fi
}
+xfail()
+{
+ FAIL_TO_XFAIL=yes "$@"
+}
+
xfail_on_slow()
{
if [[ $KSFT_MACHINE_SLOW = yes ]]; then
@@ -1113,6 +1118,39 @@
ip -j link show dev $if_name | jq -r '.[]["address"]'
}
+ether_addr_to_u64()
+{
+ local addr="$1"
+ local order="$((1 << 40))"
+ local val=0
+ local byte
+
+ addr="${addr//:/ }"
+
+ for byte in $addr; do
+ byte="0x$byte"
+ val=$((val + order * byte))
+ order=$((order >> 8))
+ done
+
+ printf "0x%x" $val
+}
+
+u64_to_ether_addr()
+{
+ local val=$1
+ local byte
+ local i
+
+ for ((i = 40; i >= 0; i -= 8)); do
+ byte=$(((val & (0xff << i)) >> i))
+ printf "%02x" $byte
+ if [ $i -ne 0 ]; then
+ printf ":"
+ fi
+ done
+}
+
ipv6_lladdr_get()
{
local if_name=$1
@@ -2229,3 +2267,22 @@
echo $((v > 0 ? v : -v))
}
+
+has_unicast_flt()
+{
+ local dev=$1; shift
+ local mac_addr=$(mac_get $dev)
+ local tmp=$(ether_addr_to_u64 $mac_addr)
+ local promisc
+
+ ip link set $dev up
+ ip link add link $dev name macvlan-tmp type macvlan mode private
+ ip link set macvlan-tmp address $(u64_to_ether_addr $((tmp + 1)))
+ ip link set macvlan-tmp up
+
+ promisc=$(ip -j -d link show dev $dev | jq -r '.[].promiscuity')
+
+ ip link del macvlan-tmp
+
+ [[ $promisc == 1 ]] && echo "no" || echo "yes"
+}
diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh
index 4b364cd..c3554876 100755
--- a/tools/testing/selftests/net/forwarding/local_termination.sh
+++ b/tools/testing/selftests/net/forwarding/local_termination.sh
@@ -1,7 +1,9 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-ALL_TESTS="standalone bridge"
+ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge test_vlan \
+ vlan_over_vlan_unaware_bridged_port vlan_over_vlan_aware_bridged_port \
+ vlan_over_vlan_unaware_bridge vlan_over_vlan_aware_bridge"
NUM_NETIFS=2
PING_COUNT=1
REQUIRE_MTOOLS=yes
@@ -37,9 +39,68 @@
UNKNOWN_MACV6_MC_ADDR2="33:33:01:02:03:06"
UNKNOWN_MACV6_MC_ADDR3="33:33:01:02:03:07"
-NON_IP_MC="01:02:03:04:05:06"
-NON_IP_PKT="00:04 48:45:4c:4f"
-BC="ff:ff:ff:ff:ff:ff"
+PTP_1588_L2_SYNC=" \
+01:1b:19:00:00:00 00:00:de:ad:be:ef 88:f7 00 02 \
+00 2c 00 00 02 00 00 00 00 00 00 00 00 00 00 00 \
+00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 00 00 \
+00 00 00 00 00 00 00 00 00 00"
+PTP_1588_L2_FOLLOW_UP=" \
+01:1b:19:00:00:00 00:00:de:ad:be:ef 88:f7 08 02 \
+00 2c 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \
+00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 02 00 \
+00 00 66 83 c5 f1 17 97 ed f0"
+PTP_1588_L2_PDELAY_REQ=" \
+01:80:c2:00:00:0e 00:00:de:ad:be:ef 88:f7 02 02 \
+00 36 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \
+00 00 3e 37 63 ff fe cf 17 0e 00 01 00 06 05 7f \
+00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \
+00 00 00 00"
+PTP_1588_IPV4_SYNC=" \
+01:00:5e:00:01:81 00:00:de:ad:be:ef 08:00 45 00 \
+00 48 0a 9a 40 00 01 11 cb 88 c0 00 02 01 e0 00 \
+01 81 01 3f 01 3f 00 34 a3 c8 00 02 00 2c 00 00 \
+02 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \
+63 ff fe cf 17 0e 00 01 00 00 00 00 00 00 00 00 \
+00 00 00 00 00 00"
+PTP_1588_IPV4_FOLLOW_UP="
+01:00:5e:00:01:81 00:00:de:ad:be:ef 08:00 45 00 \
+00 48 0a 9b 40 00 01 11 cb 87 c0 00 02 01 e0 00 \
+01 81 01 40 01 40 00 34 a3 c8 08 02 00 2c 00 00 \
+00 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \
+63 ff fe cf 17 0e 00 01 00 00 02 00 00 00 66 83 \
+c6 0f 1d 9a 61 87"
+PTP_1588_IPV4_PDELAY_REQ=" \
+01:00:5e:00:00:6b 00:00:de:ad:be:ef 08:00 45 00 \
+00 52 35 a9 40 00 01 11 a1 85 c0 00 02 01 e0 00 \
+00 6b 01 3f 01 3f 00 3e a2 bc 02 02 00 36 00 00 \
+00 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \
+63 ff fe cf 17 0e 00 01 00 01 05 7f 00 00 00 00 \
+00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00"
+PTP_1588_IPV6_SYNC=" \
+33:33:00:00:01:81 00:00:de:ad:be:ef 86:dd 60 06 \
+7c 2f 00 36 11 01 20 01 0d b8 00 01 00 00 00 00 \
+00 00 00 00 00 01 ff 0e 00 00 00 00 00 00 00 00 \
+00 00 00 00 01 81 01 3f 01 3f 00 36 2e 92 00 02 \
+00 2c 00 00 02 00 00 00 00 00 00 00 00 00 00 00 \
+00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 00 00 \
+00 00 00 00 00 00 00 00 00 00 00 00"
+PTP_1588_IPV6_FOLLOW_UP=" \
+33:33:00:00:01:81 00:00:de:ad:be:ef 86:dd 60 0a \
+00 bc 00 36 11 01 20 01 0d b8 00 01 00 00 00 00 \
+00 00 00 00 00 01 ff 0e 00 00 00 00 00 00 00 00 \
+00 00 00 00 01 81 01 40 01 40 00 36 2e 92 08 02 \
+00 2c 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \
+00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 02 00 \
+00 00 66 83 c6 2a 32 09 bd 74 00 00"
+PTP_1588_IPV6_PDELAY_REQ=" \
+33:33:00:00:00:6b 00:00:de:ad:be:ef 86:dd 60 0c \
+5c fd 00 40 11 01 fe 80 00 00 00 00 00 00 3c 37 \
+63 ff fe cf 17 0e ff 02 00 00 00 00 00 00 00 00 \
+00 00 00 00 00 6b 01 3f 01 3f 00 40 b4 54 02 02 \
+00 36 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \
+00 00 3e 37 63 ff fe cf 17 0e 00 01 00 01 05 7f \
+00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \
+00 00 00 00 00 00"
# Disable promisc to ensure we don't receive unknown MAC DA packets
export TCPDUMP_EXTRA_FLAGS="-pl"
@@ -47,13 +108,15 @@
h1=${NETIFS[p1]}
h2=${NETIFS[p2]}
-send_non_ip()
+send_raw()
{
- local if_name=$1
- local smac=$2
- local dmac=$3
+ local if_name=$1; shift
+ local pkt="$1"; shift
+ local smac=$(mac_get $if_name)
- $MZ -q $if_name "$dmac $smac $NON_IP_PKT"
+ pkt="${pkt/00:00:de:ad:be:ef/$smac}"
+
+ $MZ -q $if_name "$pkt"
}
send_uc_ipv4()
@@ -68,10 +131,11 @@
check_rcv()
{
- local if_name=$1
- local type=$2
- local pattern=$3
- local should_receive=$4
+ local if_name=$1; shift
+ local type=$1; shift
+ local pattern=$1; shift
+ local should_receive=$1; shift
+ local test_name="$1"; shift
local should_fail=
[ $should_receive = true ] && should_fail=0 || should_fail=1
@@ -81,7 +145,7 @@
check_err_fail "$should_fail" "$?" "reception"
- log_test "$if_name: $type"
+ log_test "$test_name: $type"
}
mc_route_prepare()
@@ -104,44 +168,78 @@
run_test()
{
- local rcv_if_name=$1
- local smac=$(mac_get $h1)
+ local send_if_name=$1; shift
+ local rcv_if_name=$1; shift
+ local skip_ptp=$1; shift
+ local no_unicast_flt=$1; shift
+ local test_name="$1"; shift
+ local smac=$(mac_get $send_if_name)
local rcv_dmac=$(mac_get $rcv_if_name)
+ local should_receive
tcpdump_start $rcv_if_name
- mc_route_prepare $h1
+ mc_route_prepare $send_if_name
mc_route_prepare $rcv_if_name
- send_uc_ipv4 $h1 $rcv_dmac
- send_uc_ipv4 $h1 $MACVLAN_ADDR
- send_uc_ipv4 $h1 $UNKNOWN_UC_ADDR1
+ send_uc_ipv4 $send_if_name $rcv_dmac
+ send_uc_ipv4 $send_if_name $MACVLAN_ADDR
+ send_uc_ipv4 $send_if_name $UNKNOWN_UC_ADDR1
ip link set dev $rcv_if_name promisc on
- send_uc_ipv4 $h1 $UNKNOWN_UC_ADDR2
- mc_send $h1 $UNKNOWN_IPV4_MC_ADDR2
- mc_send $h1 $UNKNOWN_IPV6_MC_ADDR2
+ send_uc_ipv4 $send_if_name $UNKNOWN_UC_ADDR2
+ mc_send $send_if_name $UNKNOWN_IPV4_MC_ADDR2
+ mc_send $send_if_name $UNKNOWN_IPV6_MC_ADDR2
ip link set dev $rcv_if_name promisc off
mc_join $rcv_if_name $JOINED_IPV4_MC_ADDR
- mc_send $h1 $JOINED_IPV4_MC_ADDR
+ mc_send $send_if_name $JOINED_IPV4_MC_ADDR
mc_leave
mc_join $rcv_if_name $JOINED_IPV6_MC_ADDR
- mc_send $h1 $JOINED_IPV6_MC_ADDR
+ mc_send $send_if_name $JOINED_IPV6_MC_ADDR
mc_leave
- mc_send $h1 $UNKNOWN_IPV4_MC_ADDR1
- mc_send $h1 $UNKNOWN_IPV6_MC_ADDR1
+ mc_send $send_if_name $UNKNOWN_IPV4_MC_ADDR1
+ mc_send $send_if_name $UNKNOWN_IPV6_MC_ADDR1
ip link set dev $rcv_if_name allmulticast on
- send_uc_ipv4 $h1 $UNKNOWN_UC_ADDR3
- mc_send $h1 $UNKNOWN_IPV4_MC_ADDR3
- mc_send $h1 $UNKNOWN_IPV6_MC_ADDR3
+ send_uc_ipv4 $send_if_name $UNKNOWN_UC_ADDR3
+ mc_send $send_if_name $UNKNOWN_IPV4_MC_ADDR3
+ mc_send $send_if_name $UNKNOWN_IPV6_MC_ADDR3
ip link set dev $rcv_if_name allmulticast off
mc_route_destroy $rcv_if_name
- mc_route_destroy $h1
+ mc_route_destroy $send_if_name
+
+ if [ $skip_ptp = false ]; then
+ ip maddress add 01:1b:19:00:00:00 dev $rcv_if_name
+ send_raw $send_if_name "$PTP_1588_L2_SYNC"
+ send_raw $send_if_name "$PTP_1588_L2_FOLLOW_UP"
+ ip maddress del 01:1b:19:00:00:00 dev $rcv_if_name
+
+ ip maddress add 01:80:c2:00:00:0e dev $rcv_if_name
+ send_raw $send_if_name "$PTP_1588_L2_PDELAY_REQ"
+ ip maddress del 01:80:c2:00:00:0e dev $rcv_if_name
+
+ mc_join $rcv_if_name 224.0.1.129
+ send_raw $send_if_name "$PTP_1588_IPV4_SYNC"
+ send_raw $send_if_name "$PTP_1588_IPV4_FOLLOW_UP"
+ mc_leave
+
+ mc_join $rcv_if_name 224.0.0.107
+ send_raw $send_if_name "$PTP_1588_IPV4_PDELAY_REQ"
+ mc_leave
+
+ mc_join $rcv_if_name ff0e::181
+ send_raw $send_if_name "$PTP_1588_IPV6_SYNC"
+ send_raw $send_if_name "$PTP_1588_IPV6_FOLLOW_UP"
+ mc_leave
+
+ mc_join $rcv_if_name ff02::6b
+ send_raw $send_if_name "$PTP_1588_IPV6_PDELAY_REQ"
+ mc_leave
+ fi
sleep 1
@@ -149,61 +247,99 @@
check_rcv $rcv_if_name "Unicast IPv4 to primary MAC address" \
"$smac > $rcv_dmac, ethertype IPv4 (0x0800)" \
- true
+ true "$test_name"
check_rcv $rcv_if_name "Unicast IPv4 to macvlan MAC address" \
"$smac > $MACVLAN_ADDR, ethertype IPv4 (0x0800)" \
- true
+ true "$test_name"
- xfail_on_veth $h1 \
- check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address" \
- "$smac > $UNKNOWN_UC_ADDR1, ethertype IPv4 (0x0800)" \
- false
+ [ $no_unicast_flt = true ] && should_receive=true || should_receive=false
+ check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address" \
+ "$smac > $UNKNOWN_UC_ADDR1, ethertype IPv4 (0x0800)" \
+ $should_receive "$test_name"
check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address, promisc" \
"$smac > $UNKNOWN_UC_ADDR2, ethertype IPv4 (0x0800)" \
- true
+ true "$test_name"
- xfail_on_veth $h1 \
- check_rcv $rcv_if_name \
- "Unicast IPv4 to unknown MAC address, allmulti" \
- "$smac > $UNKNOWN_UC_ADDR3, ethertype IPv4 (0x0800)" \
- false
+ [ $no_unicast_flt = true ] && should_receive=true || should_receive=false
+ check_rcv $rcv_if_name \
+ "Unicast IPv4 to unknown MAC address, allmulti" \
+ "$smac > $UNKNOWN_UC_ADDR3, ethertype IPv4 (0x0800)" \
+ $should_receive "$test_name"
check_rcv $rcv_if_name "Multicast IPv4 to joined group" \
"$smac > $JOINED_MACV4_MC_ADDR, ethertype IPv4 (0x0800)" \
- true
+ true "$test_name"
- xfail_on_veth $h1 \
+ xfail \
check_rcv $rcv_if_name \
"Multicast IPv4 to unknown group" \
"$smac > $UNKNOWN_MACV4_MC_ADDR1, ethertype IPv4 (0x0800)" \
- false
+ false "$test_name"
check_rcv $rcv_if_name "Multicast IPv4 to unknown group, promisc" \
"$smac > $UNKNOWN_MACV4_MC_ADDR2, ethertype IPv4 (0x0800)" \
- true
+ true "$test_name"
check_rcv $rcv_if_name "Multicast IPv4 to unknown group, allmulti" \
"$smac > $UNKNOWN_MACV4_MC_ADDR3, ethertype IPv4 (0x0800)" \
- true
+ true "$test_name"
check_rcv $rcv_if_name "Multicast IPv6 to joined group" \
"$smac > $JOINED_MACV6_MC_ADDR, ethertype IPv6 (0x86dd)" \
- true
+ true "$test_name"
- xfail_on_veth $h1 \
+ xfail \
check_rcv $rcv_if_name "Multicast IPv6 to unknown group" \
"$smac > $UNKNOWN_MACV6_MC_ADDR1, ethertype IPv6 (0x86dd)" \
- false
+ false "$test_name"
check_rcv $rcv_if_name "Multicast IPv6 to unknown group, promisc" \
"$smac > $UNKNOWN_MACV6_MC_ADDR2, ethertype IPv6 (0x86dd)" \
- true
+ true "$test_name"
check_rcv $rcv_if_name "Multicast IPv6 to unknown group, allmulti" \
"$smac > $UNKNOWN_MACV6_MC_ADDR3, ethertype IPv6 (0x86dd)" \
- true
+ true "$test_name"
+
+ if [ $skip_ptp = false ]; then
+ check_rcv $rcv_if_name "1588v2 over L2 transport, Sync" \
+ "ethertype PTP (0x88f7).* PTPv2.* msg type : sync msg" \
+ true "$test_name"
+
+ check_rcv $rcv_if_name "1588v2 over L2 transport, Follow-Up" \
+ "ethertype PTP (0x88f7).* PTPv2.* msg type : follow up msg" \
+ true "$test_name"
+
+ check_rcv $rcv_if_name "1588v2 over L2 transport, Peer Delay Request" \
+ "ethertype PTP (0x88f7).* PTPv2.* msg type : peer delay req msg" \
+ true "$test_name"
+
+ check_rcv $rcv_if_name "1588v2 over IPv4, Sync" \
+ "ethertype IPv4 (0x0800).* PTPv2.* msg type : sync msg" \
+ true "$test_name"
+
+ check_rcv $rcv_if_name "1588v2 over IPv4, Follow-Up" \
+ "ethertype IPv4 (0x0800).* PTPv2.* msg type : follow up msg" \
+ true "$test_name"
+
+ check_rcv $rcv_if_name "1588v2 over IPv4, Peer Delay Request" \
+ "ethertype IPv4 (0x0800).* PTPv2.* msg type : peer delay req msg" \
+ true "$test_name"
+
+ check_rcv $rcv_if_name "1588v2 over IPv6, Sync" \
+ "ethertype IPv6 (0x86dd).* PTPv2.* msg type : sync msg" \
+ true "$test_name"
+
+ check_rcv $rcv_if_name "1588v2 over IPv6, Follow-Up" \
+ "ethertype IPv6 (0x86dd).* PTPv2.* msg type : follow up msg" \
+ true "$test_name"
+
+ check_rcv $rcv_if_name "1588v2 over IPv6, Peer Delay Request" \
+ "ethertype IPv6 (0x86dd).* PTPv2.* msg type : peer delay req msg" \
+ true "$test_name"
+ fi
tcpdump_cleanup $rcv_if_name
}
@@ -228,62 +364,217 @@
simple_if_fini $h2 $H2_IPV4/24 $H2_IPV6/64
}
+h1_vlan_create()
+{
+ simple_if_init $h1
+ vlan_create $h1 100 v$h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h1_vlan_destroy()
+{
+ vlan_destroy $h1 100
+ simple_if_fini $h1
+}
+
+h2_vlan_create()
+{
+ simple_if_init $h2
+ vlan_create $h2 100 v$h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+h2_vlan_destroy()
+{
+ vlan_destroy $h2 100
+ simple_if_fini $h2
+}
+
bridge_create()
{
- ip link add br0 type bridge
+ local vlan_filtering=$1
+
+ ip link add br0 type bridge vlan_filtering $vlan_filtering
ip link set br0 address $BRIDGE_ADDR
ip link set br0 up
ip link set $h2 master br0
ip link set $h2 up
-
- simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64
}
bridge_destroy()
{
- simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64
-
ip link del br0
}
+macvlan_create()
+{
+ local lower=$1
+
+ ip link add link $lower name macvlan0 type macvlan mode private
+ ip link set macvlan0 address $MACVLAN_ADDR
+ ip link set macvlan0 up
+}
+
+macvlan_destroy()
+{
+ ip link del macvlan0
+}
+
standalone()
{
+ local no_unicast_flt=true
+ local skip_ptp=false
+
+ if [ $(has_unicast_flt $h2) = yes ]; then
+ no_unicast_flt=false
+ fi
+
h1_create
h2_create
+ macvlan_create $h2
- ip link add link $h2 name macvlan0 type macvlan mode private
- ip link set macvlan0 address $MACVLAN_ADDR
- ip link set macvlan0 up
+ run_test $h1 $h2 $skip_ptp $no_unicast_flt "$h2"
- run_test $h2
-
- ip link del macvlan0
-
+ macvlan_destroy
h2_destroy
h1_destroy
}
-bridge()
+test_bridge()
{
+ local no_unicast_flt=true
+ local vlan_filtering=$1
+ local skip_ptp=true
+
h1_create
- bridge_create
+ bridge_create $vlan_filtering
+ simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64
+ macvlan_create br0
- ip link add link br0 name macvlan0 type macvlan mode private
- ip link set macvlan0 address $MACVLAN_ADDR
- ip link set macvlan0 up
+ run_test $h1 br0 $skip_ptp $no_unicast_flt \
+ "vlan_filtering=$vlan_filtering bridge"
- run_test br0
-
- ip link del macvlan0
-
+ macvlan_destroy
+ simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64
bridge_destroy
h1_destroy
}
+vlan_unaware_bridge()
+{
+ test_bridge 0
+}
+
+vlan_aware_bridge()
+{
+ test_bridge 1
+}
+
+test_vlan()
+{
+ local no_unicast_flt=true
+ local skip_ptp=false
+
+ if [ $(has_unicast_flt $h2) = yes ]; then
+ no_unicast_flt=false
+ fi
+
+ h1_vlan_create
+ h2_vlan_create
+ macvlan_create $h2.100
+
+ run_test $h1.100 $h2.100 $skip_ptp $no_unicast_flt "VLAN upper"
+
+ macvlan_destroy
+ h2_vlan_destroy
+ h1_vlan_destroy
+}
+
+vlan_over_bridged_port()
+{
+ local no_unicast_flt=true
+ local vlan_filtering=$1
+ local skip_ptp=false
+
+ # br_manage_promisc() will not force a single vlan_filtering port to
+ # promiscuous mode, so we should still expect unicast filtering to take
+ # place if the device can do it.
+ if [ $(has_unicast_flt $h2) = yes ] && [ $vlan_filtering = 1 ]; then
+ no_unicast_flt=false
+ fi
+
+ h1_vlan_create
+ h2_vlan_create
+ bridge_create $vlan_filtering
+ macvlan_create $h2.100
+
+ run_test $h1.100 $h2.100 $skip_ptp $no_unicast_flt \
+ "VLAN over vlan_filtering=$vlan_filtering bridged port"
+
+ macvlan_destroy
+ bridge_destroy
+ h2_vlan_destroy
+ h1_vlan_destroy
+}
+
+vlan_over_vlan_unaware_bridged_port()
+{
+ vlan_over_bridged_port 0
+}
+
+vlan_over_vlan_aware_bridged_port()
+{
+ vlan_over_bridged_port 1
+}
+
+vlan_over_bridge()
+{
+ local no_unicast_flt=true
+ local vlan_filtering=$1
+ local skip_ptp=true
+
+ h1_vlan_create
+ bridge_create $vlan_filtering
+ simple_if_init br0
+ vlan_create br0 100 vbr0 $H2_IPV4/24 $H2_IPV6/64
+ macvlan_create br0.100
+
+ if [ $vlan_filtering = 1 ]; then
+ bridge vlan add dev $h2 vid 100 master
+ bridge vlan add dev br0 vid 100 self
+ fi
+
+ run_test $h1.100 br0.100 $skip_ptp $no_unicast_flt \
+ "VLAN over vlan_filtering=$vlan_filtering bridge"
+
+ if [ $vlan_filtering = 1 ]; then
+ bridge vlan del dev br0 vid 100 self
+ bridge vlan del dev $h2 vid 100 master
+ fi
+
+ macvlan_destroy
+ vlan_destroy br0 100
+ simple_if_fini br0
+ bridge_destroy
+ h1_vlan_destroy
+}
+
+vlan_over_vlan_unaware_bridge()
+{
+ vlan_over_bridge 0
+}
+
+vlan_over_vlan_aware_bridge()
+{
+ vlan_over_bridge 1
+}
+
cleanup()
{
pre_cleanup
+
+ ip link set $h2 down
+ ip link set $h1 down
+
vrf_cleanup
}
diff --git a/tools/testing/selftests/net/forwarding/no_forwarding.sh b/tools/testing/selftests/net/forwarding/no_forwarding.sh
index af3b398..9e677aa 100755
--- a/tools/testing/selftests/net/forwarding/no_forwarding.sh
+++ b/tools/testing/selftests/net/forwarding/no_forwarding.sh
@@ -233,6 +233,9 @@
{
pre_cleanup
+ ip link set dev $swp2 down
+ ip link set dev $swp1 down
+
h2_destroy
h1_destroy
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index d021903..8ee4489 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -146,6 +146,7 @@
for ns in "$@"; do
[ -z "${ns}" ] && continue
+ ip netns pids "${ns}" 2> /dev/null | xargs -r kill || true
ip netns delete "${ns}" &> /dev/null || true
if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then
echo "Warn: Failed to remove namespace $ns"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 9ea6d69..a4762c4 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -420,12 +420,17 @@
fi
}
+start_events()
+{
+ mptcp_lib_events "${ns1}" "${evts_ns1}" evts_ns1_pid
+ mptcp_lib_events "${ns2}" "${evts_ns2}" evts_ns2_pid
+}
+
reset_with_events()
{
reset "${1}" || return 1
- mptcp_lib_events "${ns1}" "${evts_ns1}" evts_ns1_pid
- mptcp_lib_events "${ns2}" "${evts_ns2}" evts_ns2_pid
+ start_events
}
reset_with_tcp_filter()
@@ -436,9 +441,10 @@
local ns="${!1}"
local src="${2}"
local target="${3}"
+ local chain="${4:-INPUT}"
if ! ip netns exec "${ns}" ${iptables} \
- -A INPUT \
+ -A "${chain}" \
-s "${src}" \
-p tcp \
-j "${target}"; then
@@ -1111,26 +1117,26 @@
print_check "sum"
count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtDataCsumErr")
- if [ "$count" != "$csum_ns1" ]; then
+ if [ -n "$count" ] && [ "$count" != "$csum_ns1" ]; then
extra_msg+=" ns1=$count"
fi
if [ -z "$count" ]; then
print_skip
elif { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } ||
- { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then
+ { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then
fail_test "got $count data checksum error[s] expected $csum_ns1"
else
print_ok
fi
print_check "csum"
count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtDataCsumErr")
- if [ "$count" != "$csum_ns2" ]; then
+ if [ -n "$count" ] && [ "$count" != "$csum_ns2" ]; then
extra_msg+=" ns2=$count"
fi
if [ -z "$count" ]; then
print_skip
elif { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } ||
- { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then
+ { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then
fail_test "got $count data checksum error[s] expected $csum_ns2"
else
print_ok
@@ -1168,13 +1174,13 @@
print_check "ftx"
count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFailTx")
- if [ "$count" != "$fail_tx" ]; then
+ if [ -n "$count" ] && [ "$count" != "$fail_tx" ]; then
extra_msg+=",tx=$count"
fi
if [ -z "$count" ]; then
print_skip
elif { [ "$count" != "$fail_tx" ] && [ $allow_tx_lost -eq 0 ]; } ||
- { [ "$count" -gt "$fail_tx" ] && [ $allow_tx_lost -eq 1 ]; }; then
+ { [ "$count" -gt "$fail_tx" ] && [ $allow_tx_lost -eq 1 ]; }; then
fail_test "got $count MP_FAIL[s] TX expected $fail_tx"
else
print_ok
@@ -1182,13 +1188,13 @@
print_check "failrx"
count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFailRx")
- if [ "$count" != "$fail_rx" ]; then
+ if [ -n "$count" ] && [ "$count" != "$fail_rx" ]; then
extra_msg+=",rx=$count"
fi
if [ -z "$count" ]; then
print_skip
elif { [ "$count" != "$fail_rx" ] && [ $allow_rx_lost -eq 0 ]; } ||
- { [ "$count" -gt "$fail_rx" ] && [ $allow_rx_lost -eq 1 ]; }; then
+ { [ "$count" -gt "$fail_rx" ] && [ $allow_rx_lost -eq 1 ]; }; then
fail_test "got $count MP_FAIL[s] RX expected $fail_rx"
else
print_ok
@@ -3058,6 +3064,7 @@
pm_nl_set_limits $ns1 1 3
pm_nl_set_limits $ns2 1 3
pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+ pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,fullmesh
fullmesh=1 speed=slow \
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 3 3 3
@@ -3331,6 +3338,36 @@
fi
}
+# $1: ns ; $2: event type ; $3: count
+chk_evt_nr()
+{
+ local ns=${1}
+ local evt_name="${2}"
+ local exp="${3}"
+
+ local evts="${evts_ns1}"
+ local evt="${!evt_name}"
+ local count
+
+ evt_name="${evt_name:16}" # without MPTCP_LIB_EVENT_
+ [ "${ns}" == "ns2" ] && evts="${evts_ns2}"
+
+ print_check "event ${ns} ${evt_name} (${exp})"
+
+ if [[ "${evt_name}" = "LISTENER_"* ]] &&
+ ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then
+ print_skip "event not supported"
+ return
+ fi
+
+ count=$(grep -cw "type:${evt}" "${evts}")
+ if [ "${count}" != "${exp}" ]; then
+ fail_test "got ${count} events, expected ${exp}"
+ else
+ print_ok
+ fi
+}
+
userspace_tests()
{
# userspace pm type prevents add_addr
@@ -3427,14 +3464,12 @@
"signal"
userspace_pm_chk_get_addr "${ns1}" "10" "id 10 flags signal 10.0.2.1"
userspace_pm_chk_get_addr "${ns1}" "20" "id 20 flags signal 10.0.3.1"
- userspace_pm_rm_addr $ns1 10
userspace_pm_rm_sf $ns1 "::ffff:10.0.2.1" $MPTCP_LIB_EVENT_SUB_ESTABLISHED
userspace_pm_chk_dump_addr "${ns1}" \
- "id 20 flags signal 10.0.3.1" "after rm_addr 10"
+ "id 20 flags signal 10.0.3.1" "after rm_sf 10"
userspace_pm_rm_addr $ns1 20
- userspace_pm_rm_sf $ns1 10.0.3.1 $MPTCP_LIB_EVENT_SUB_ESTABLISHED
userspace_pm_chk_dump_addr "${ns1}" "" "after rm_addr 20"
- chk_rm_nr 2 2 invert
+ chk_rm_nr 1 1 invert
chk_mptcp_info subflows 0 subflows 0
chk_subflows_total 1 1
kill_events_pids
@@ -3458,12 +3493,11 @@
"id 20 flags subflow 10.0.3.2" \
"subflow"
userspace_pm_chk_get_addr "${ns2}" "20" "id 20 flags subflow 10.0.3.2"
- userspace_pm_rm_addr $ns2 20
userspace_pm_rm_sf $ns2 10.0.3.2 $MPTCP_LIB_EVENT_SUB_ESTABLISHED
userspace_pm_chk_dump_addr "${ns2}" \
"" \
- "after rm_addr 20"
- chk_rm_nr 1 1
+ "after rm_sf 20"
+ chk_rm_nr 0 1
chk_mptcp_info subflows 0 subflows 0
chk_subflows_total 1 1
kill_events_pids
@@ -3571,40 +3605,90 @@
mptcp_lib_kill_wait $tests_pid
fi
- if reset "delete and re-add" &&
+ if reset_with_tcp_filter "delete and re-add" ns2 10.0.3.2 REJECT OUTPUT &&
mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
- pm_nl_set_limits $ns1 1 1
- pm_nl_set_limits $ns2 1 1
+ start_events
+ pm_nl_set_limits $ns1 0 3
+ pm_nl_set_limits $ns2 0 3
+ pm_nl_add_endpoint $ns2 10.0.1.2 id 1 dev ns2eth1 flags subflow
pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
- test_linkfail=4 speed=20 \
+ test_linkfail=4 speed=5 \
run_tests $ns1 $ns2 10.0.1.1 &
local tests_pid=$!
wait_mpj $ns2
pm_nl_check_endpoint "creation" \
$ns2 10.0.2.2 id 2 flags subflow dev ns2eth2
- chk_subflow_nr "before delete" 2
+ chk_subflow_nr "before delete id 2" 2
chk_mptcp_info subflows 1 subflows 1
pm_nl_del_endpoint $ns2 2 10.0.2.2
sleep 0.5
- chk_subflow_nr "after delete" 1
+ chk_subflow_nr "after delete id 2" 1
chk_mptcp_info subflows 0 subflows 0
- pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow
+ pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
wait_mpj $ns2
- chk_subflow_nr "after re-add" 2
+ chk_subflow_nr "after re-add id 2" 2
chk_mptcp_info subflows 1 subflows 1
+
+ pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
+ wait_attempt_fail $ns2
+ chk_subflow_nr "after new reject" 2
+ chk_mptcp_info subflows 1 subflows 1
+
+ ip netns exec "${ns2}" ${iptables} -D OUTPUT -s "10.0.3.2" -p tcp -j REJECT
+ pm_nl_del_endpoint $ns2 3 10.0.3.2
+ pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
+ wait_mpj $ns2
+ chk_subflow_nr "after no reject" 3
+ chk_mptcp_info subflows 2 subflows 2
+
+ local i
+ for i in $(seq 3); do
+ pm_nl_del_endpoint $ns2 1 10.0.1.2
+ sleep 0.5
+ chk_subflow_nr "after delete id 0 ($i)" 2
+ chk_mptcp_info subflows 2 subflows 2 # only decr for additional sf
+
+ pm_nl_add_endpoint $ns2 10.0.1.2 id 1 dev ns2eth1 flags subflow
+ wait_mpj $ns2
+ chk_subflow_nr "after re-add id 0 ($i)" 3
+ chk_mptcp_info subflows 3 subflows 3
+ done
+
mptcp_lib_kill_wait $tests_pid
+
+ kill_events_pids
+ chk_evt_nr ns1 MPTCP_LIB_EVENT_LISTENER_CREATED 1
+ chk_evt_nr ns1 MPTCP_LIB_EVENT_CREATED 1
+ chk_evt_nr ns1 MPTCP_LIB_EVENT_ESTABLISHED 1
+ chk_evt_nr ns1 MPTCP_LIB_EVENT_ANNOUNCED 0
+ chk_evt_nr ns1 MPTCP_LIB_EVENT_REMOVED 4
+ chk_evt_nr ns1 MPTCP_LIB_EVENT_SUB_ESTABLISHED 6
+ chk_evt_nr ns1 MPTCP_LIB_EVENT_SUB_CLOSED 4
+
+ chk_evt_nr ns2 MPTCP_LIB_EVENT_CREATED 1
+ chk_evt_nr ns2 MPTCP_LIB_EVENT_ESTABLISHED 1
+ chk_evt_nr ns2 MPTCP_LIB_EVENT_ANNOUNCED 0
+ chk_evt_nr ns2 MPTCP_LIB_EVENT_REMOVED 0
+ chk_evt_nr ns2 MPTCP_LIB_EVENT_SUB_ESTABLISHED 6
+ chk_evt_nr ns2 MPTCP_LIB_EVENT_SUB_CLOSED 5 # one has been closed before estab
+
+ chk_join_nr 6 6 6
+ chk_rm_nr 4 4
fi
# remove and re-add
- if reset "delete re-add signal" &&
+ if reset_with_events "delete re-add signal" &&
mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
- pm_nl_set_limits $ns1 1 1
- pm_nl_set_limits $ns2 1 1
+ pm_nl_set_limits $ns1 0 3
+ pm_nl_set_limits $ns2 3 3
pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal
- test_linkfail=4 speed=20 \
+ # broadcast IP: no packet for this address will be received on ns1
+ pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal
+ pm_nl_add_endpoint $ns1 10.0.1.1 id 42 flags signal
+ test_linkfail=4 speed=5 \
run_tests $ns1 $ns2 10.0.1.1 &
local tests_pid=$!
@@ -3615,17 +3699,89 @@
chk_mptcp_info subflows 1 subflows 1
pm_nl_del_endpoint $ns1 1 10.0.2.1
+ pm_nl_del_endpoint $ns1 2 224.0.0.1
sleep 0.5
chk_subflow_nr "after delete" 1
chk_mptcp_info subflows 0 subflows 0
- pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+ pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal
+ pm_nl_add_endpoint $ns1 10.0.3.1 id 2 flags signal
wait_mpj $ns2
- chk_subflow_nr "after re-add" 2
- chk_mptcp_info subflows 1 subflows 1
+ chk_subflow_nr "after re-add" 3
+ chk_mptcp_info subflows 2 subflows 2
+
+ pm_nl_del_endpoint $ns1 42 10.0.1.1
+ sleep 0.5
+ chk_subflow_nr "after delete ID 0" 2
+ chk_mptcp_info subflows 2 subflows 2
+
+ pm_nl_add_endpoint $ns1 10.0.1.1 id 99 flags signal
+ wait_mpj $ns2
+ chk_subflow_nr "after re-add ID 0" 3
+ chk_mptcp_info subflows 3 subflows 3
+
+ pm_nl_del_endpoint $ns1 99 10.0.1.1
+ sleep 0.5
+ chk_subflow_nr "after re-delete ID 0" 2
+ chk_mptcp_info subflows 2 subflows 2
+
+ pm_nl_add_endpoint $ns1 10.0.1.1 id 88 flags signal
+ wait_mpj $ns2
+ chk_subflow_nr "after re-re-add ID 0" 3
+ chk_mptcp_info subflows 3 subflows 3
mptcp_lib_kill_wait $tests_pid
+
+ kill_events_pids
+ chk_evt_nr ns1 MPTCP_LIB_EVENT_LISTENER_CREATED 1
+ chk_evt_nr ns1 MPTCP_LIB_EVENT_CREATED 1
+ chk_evt_nr ns1 MPTCP_LIB_EVENT_ESTABLISHED 1
+ chk_evt_nr ns1 MPTCP_LIB_EVENT_ANNOUNCED 0
+ chk_evt_nr ns1 MPTCP_LIB_EVENT_REMOVED 0
+ chk_evt_nr ns1 MPTCP_LIB_EVENT_SUB_ESTABLISHED 5
+ chk_evt_nr ns1 MPTCP_LIB_EVENT_SUB_CLOSED 3
+
+ chk_evt_nr ns2 MPTCP_LIB_EVENT_CREATED 1
+ chk_evt_nr ns2 MPTCP_LIB_EVENT_ESTABLISHED 1
+ chk_evt_nr ns2 MPTCP_LIB_EVENT_ANNOUNCED 6
+ chk_evt_nr ns2 MPTCP_LIB_EVENT_REMOVED 4
+ chk_evt_nr ns2 MPTCP_LIB_EVENT_SUB_ESTABLISHED 5
+ chk_evt_nr ns2 MPTCP_LIB_EVENT_SUB_CLOSED 3
+
+ chk_join_nr 5 5 5
+ chk_add_nr 6 6
+ chk_rm_nr 4 3 invert
fi
+ # flush and re-add
+ if reset_with_tcp_filter "flush re-add" ns2 10.0.3.2 REJECT OUTPUT &&
+ mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
+ pm_nl_set_limits $ns1 0 2
+ pm_nl_set_limits $ns2 1 2
+ # broadcast IP: no packet for this address will be received on ns1
+ pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal
+ pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
+ test_linkfail=4 speed=20 \
+ run_tests $ns1 $ns2 10.0.1.1 &
+ local tests_pid=$!
+
+ wait_attempt_fail $ns2
+ chk_subflow_nr "before flush" 1
+ chk_mptcp_info subflows 0 subflows 0
+
+ pm_nl_flush_endpoint $ns2
+ pm_nl_flush_endpoint $ns1
+ wait_rm_addr $ns2 0
+ ip netns exec "${ns2}" ${iptables} -D OUTPUT -s "10.0.3.2" -p tcp -j REJECT
+ pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
+ wait_mpj $ns2
+ pm_nl_add_endpoint $ns1 10.0.3.1 id 2 flags signal
+ wait_mpj $ns2
+ mptcp_lib_kill_wait $tests_pid
+
+ chk_join_nr 2 2 2
+ chk_add_nr 2 2
+ chk_rm_nr 1 0 invert
+ fi
}
# [$1: error message]
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index 438280e..4578a33 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -12,10 +12,14 @@
readonly KSFT_TEST="${MPTCP_LIB_KSFT_TEST:-$(basename "${0}" .sh)}"
# These variables are used in some selftests, read-only
+declare -rx MPTCP_LIB_EVENT_CREATED=1 # MPTCP_EVENT_CREATED
+declare -rx MPTCP_LIB_EVENT_ESTABLISHED=2 # MPTCP_EVENT_ESTABLISHED
+declare -rx MPTCP_LIB_EVENT_CLOSED=3 # MPTCP_EVENT_CLOSED
declare -rx MPTCP_LIB_EVENT_ANNOUNCED=6 # MPTCP_EVENT_ANNOUNCED
declare -rx MPTCP_LIB_EVENT_REMOVED=7 # MPTCP_EVENT_REMOVED
declare -rx MPTCP_LIB_EVENT_SUB_ESTABLISHED=10 # MPTCP_EVENT_SUB_ESTABLISHED
declare -rx MPTCP_LIB_EVENT_SUB_CLOSED=11 # MPTCP_EVENT_SUB_CLOSED
+declare -rx MPTCP_LIB_EVENT_SUB_PRIORITY=13 # MPTCP_EVENT_SUB_PRIORITY
declare -rx MPTCP_LIB_EVENT_LISTENER_CREATED=15 # MPTCP_EVENT_LISTENER_CREATED
declare -rx MPTCP_LIB_EVENT_LISTENER_CLOSED=16 # MPTCP_EVENT_LISTENER_CLOSED
diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile
index 47945b2..d13fb5e 100644
--- a/tools/testing/selftests/net/netfilter/Makefile
+++ b/tools/testing/selftests/net/netfilter/Makefile
@@ -7,6 +7,7 @@
MNL_LDLIBS := $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl)
TEST_PROGS := br_netfilter.sh bridge_brouter.sh
+TEST_PROGS += br_netfilter_queue.sh
TEST_PROGS += conntrack_icmp_related.sh
TEST_PROGS += conntrack_ipip_mtu.sh
TEST_PROGS += conntrack_tcp_unreplied.sh
diff --git a/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh b/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh
new file mode 100755
index 0000000..6a764d7
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh
@@ -0,0 +1,78 @@
+#!/bin/bash
+
+source lib.sh
+
+checktool "nft --version" "run test without nft tool"
+
+cleanup() {
+ cleanup_all_ns
+}
+
+setup_ns c1 c2 c3 sender
+
+trap cleanup EXIT
+
+nf_queue_wait()
+{
+ grep -q "^ *$1 " "/proc/self/net/netfilter/nfnetlink_queue"
+}
+
+port_add() {
+ ns="$1"
+ dev="$2"
+ a="$3"
+
+ ip link add name "$dev" type veth peer name "$dev" netns "$ns"
+
+ ip -net "$ns" addr add 192.168.1."$a"/24 dev "$dev"
+ ip -net "$ns" link set "$dev" up
+
+ ip link set "$dev" master br0
+ ip link set "$dev" up
+}
+
+[ "${1}" != "run" ] && { unshare -n "${0}" run; exit $?; }
+
+ip link add br0 type bridge
+ip addr add 192.168.1.254/24 dev br0
+
+port_add "$c1" "c1" 1
+port_add "$c2" "c2" 2
+port_add "$c3" "c3" 3
+port_add "$sender" "sender" 253
+
+ip link set br0 up
+
+modprobe -q br_netfilter
+
+sysctl net.bridge.bridge-nf-call-iptables=1 || exit 1
+
+ip netns exec "$sender" ping -I sender -c1 192.168.1.1 || exit 1
+ip netns exec "$sender" ping -I sender -c1 192.168.1.2 || exit 2
+ip netns exec "$sender" ping -I sender -c1 192.168.1.3 || exit 3
+
+nft -f /dev/stdin <<EOF
+table ip filter {
+ chain forward {
+ type filter hook forward priority 0; policy accept;
+ ct state new counter
+ ip protocol icmp counter queue num 0 bypass
+ }
+}
+EOF
+./nf_queue -t 5 > /dev/null &
+
+busywait 5000 nf_queue_wait
+
+for i in $(seq 1 5); do conntrack -F > /dev/null 2> /dev/null; sleep 0.1 ; done &
+ip netns exec "$sender" ping -I sender -f -c 50 -b 192.168.1.255
+
+read t < /proc/sys/kernel/tainted
+if [ "$t" -eq 0 ];then
+ echo PASS: kernel not tainted
+else
+ echo ERROR: kernel is tainted
+ exit 1
+fi
+
+exit 0
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index 11a1ebd..d5ffd8c 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -7,8 +7,6 @@
readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
-BPF_FILE="xdp_dummy.bpf.o"
-
# set global exit status, but never reset nonzero one.
check_err()
{
@@ -38,7 +36,7 @@
ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24
ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad
ip -netns "${PEER_NS}" link set dev veth1 up
- ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp
+ ip netns exec "${PEER_NS}" ethtool -K veth1 gro on
}
run_one() {
@@ -46,17 +44,19 @@
local -r all="$@"
local -r tx_args=${all%rx*}
local -r rx_args=${all#*rx}
+ local ret=0
cfg_veth
- ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} && \
- echo "ok" || \
- echo "failed" &
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} &
+ local PID1=$!
wait_local_port_listen ${PEER_NS} 8000 udp
./udpgso_bench_tx ${tx_args}
- ret=$?
- wait $(jobs -p)
+ check_err $?
+ wait ${PID1}
+ check_err $?
+ [ "$ret" -eq 0 ] && echo "ok" || echo "failed"
return $ret
}
@@ -73,6 +73,7 @@
local -r all="$@"
local -r tx_args=${all%rx*}
local -r rx_args=${all#*rx}
+ local ret=0
if [[ ${tx_args} = *-4* ]]; then
ipt_cmd=iptables
@@ -93,16 +94,17 @@
# ... so that GRO will match the UDP_GRO enabled socket, but packets
# will land on the 'plain' one
ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 &
- pid=$!
- ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} && \
- echo "ok" || \
- echo "failed"&
+ local PID1=$!
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} &
+ local PID2=$!
wait_local_port_listen "${PEER_NS}" 8000 udp
./udpgso_bench_tx ${tx_args}
- ret=$?
- kill -INT $pid
- wait $(jobs -p)
+ check_err $?
+ kill -INT ${PID1}
+ wait ${PID2}
+ check_err $?
+ [ "$ret" -eq 0 ] && echo "ok" || echo "failed"
return $ret
}
@@ -111,20 +113,26 @@
local -r all="$@"
local -r tx_args=${all%rx*}
local -r rx_args=${all#*rx}
+ local ret=0
cfg_veth
ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} -p 12345 &
- ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} && \
- echo "ok" || \
- echo "failed" &
+ local PID1=$!
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} &
+ local PID2=$!
wait_local_port_listen "${PEER_NS}" 12345 udp
./udpgso_bench_tx ${tx_args} -p 12345
+ check_err $?
wait_local_port_listen "${PEER_NS}" 8000 udp
./udpgso_bench_tx ${tx_args}
- ret=$?
- wait $(jobs -p)
+ check_err $?
+ wait ${PID1}
+ check_err $?
+ wait ${PID2}
+ check_err $?
+ [ "$ret" -eq 0 ] && echo "ok" || echo "failed"
return $ret
}
@@ -196,11 +204,6 @@
return $ret
}
-if [ ! -f ${BPF_FILE} ]; then
- echo "Missing ${BPF_FILE}. Run 'make' first"
- exit -1
-fi
-
if [[ $# -eq 0 ]]; then
run_all
elif [[ $1 == "__subprocess" ]]; then
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
index 3e74cfa1..3f2fca0 100644
--- a/tools/testing/selftests/net/udpgso.c
+++ b/tools/testing/selftests/net/udpgso.c
@@ -67,6 +67,7 @@ struct testcase {
int gso_len; /* mss after applying gso */
int r_num_mss; /* recv(): number of calls of full mss */
int r_len_last; /* recv(): size of last non-mss dgram, if any */
+ bool v6_ext_hdr; /* send() dgrams with IPv6 extension headers */
};
const struct in6_addr addr6 = {
@@ -77,6 +78,8 @@ const struct in_addr addr4 = {
__constant_htonl(0x0a000001), /* 10.0.0.1 */
};
+static const char ipv6_hopopts_pad1[8] = { 0 };
+
struct testcase testcases_v4[] = {
{
/* no GSO: send a single byte */
@@ -256,6 +259,13 @@ struct testcase testcases_v6[] = {
.r_num_mss = 2,
},
{
+ /* send 2 1B segments with extension headers */
+ .tlen = 2,
+ .gso_len = 1,
+ .r_num_mss = 2,
+ .v6_ext_hdr = true,
+ },
+ {
/* send 2B + 2B + 1B segments */
.tlen = 5,
.gso_len = 2,
@@ -396,11 +406,18 @@ static void run_one(struct testcase *test, int fdt, int fdr,
int i, ret, val, mss;
bool sent;
- fprintf(stderr, "ipv%d tx:%d gso:%d %s\n",
+ fprintf(stderr, "ipv%d tx:%d gso:%d %s%s\n",
addr->sa_family == AF_INET ? 4 : 6,
test->tlen, test->gso_len,
+ test->v6_ext_hdr ? "ext-hdr " : "",
test->tfail ? "(fail)" : "");
+ if (test->v6_ext_hdr) {
+ if (setsockopt(fdt, IPPROTO_IPV6, IPV6_HOPOPTS,
+ ipv6_hopopts_pad1, sizeof(ipv6_hopopts_pad1)))
+ error(1, errno, "setsockopt ipv6 hopopts");
+ }
+
val = test->gso_len;
if (cfg_do_setsockopt) {
if (setsockopt(fdt, SOL_UDP, UDP_SEGMENT, &val, sizeof(val)))
@@ -412,6 +429,12 @@ static void run_one(struct testcase *test, int fdt, int fdr,
error(1, 0, "send succeeded while expecting failure");
if (!sent && !test->tfail)
error(1, 0, "send failed while expecting success");
+
+ if (test->v6_ext_hdr) {
+ if (setsockopt(fdt, IPPROTO_IPV6, IPV6_HOPOPTS, NULL, 0))
+ error(1, errno, "setsockopt ipv6 hopopts clear");
+ }
+
if (!sent)
return;
diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index ee34918..4f255ce 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -143,7 +143,6 @@
except Exception as ee:
print('exception {} in call to pre_case for {} plugin'.
format(ee, pgn_inst.__class__))
- print('test_ordinal is {}'.format(test_ordinal))
print('testid is {}'.format(caseinfo['id']))
raise
diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c
index f594a44..2f75662 100644
--- a/tools/tracing/rtla/src/osnoise_top.c
+++ b/tools/tracing/rtla/src/osnoise_top.c
@@ -651,8 +651,10 @@ struct osnoise_tool *osnoise_init_top(struct osnoise_top_params *params)
return NULL;
tool->data = osnoise_alloc_top(nr_cpus);
- if (!tool->data)
- goto out_err;
+ if (!tool->data) {
+ osnoise_destroy_tool(tool);
+ return NULL;
+ }
tool->params = params;
@@ -660,11 +662,6 @@ struct osnoise_tool *osnoise_init_top(struct osnoise_top_params *params)
osnoise_top_handler, NULL);
return tool;
-
-out_err:
- osnoise_free_top(tool->data);
- osnoise_destroy_tool(tool);
- return NULL;
}
static int stop_tracing;
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 2295700..992f9be 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -97,18 +97,19 @@ irqfd_resampler_shutdown(struct kvm_kernel_irqfd *irqfd)
mutex_lock(&kvm->irqfds.resampler_lock);
list_del_rcu(&irqfd->resampler_link);
- synchronize_srcu(&kvm->irq_srcu);
if (list_empty(&resampler->list)) {
list_del_rcu(&resampler->link);
kvm_unregister_irq_ack_notifier(kvm, &resampler->notifier);
/*
- * synchronize_srcu(&kvm->irq_srcu) already called
+ * synchronize_srcu_expedited(&kvm->irq_srcu) already called
* in kvm_unregister_irq_ack_notifier().
*/
kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
resampler->notifier.gsi, 0, false);
kfree(resampler);
+ } else {
+ synchronize_srcu_expedited(&kvm->irq_srcu);
}
mutex_unlock(&kvm->irqfds.resampler_lock);
@@ -126,7 +127,7 @@ irqfd_shutdown(struct work_struct *work)
u64 cnt;
/* Make sure irqfd has been initialized in assign path. */
- synchronize_srcu(&kvm->irq_srcu);
+ synchronize_srcu_expedited(&kvm->irq_srcu);
/*
* Synchronize with the wait-queue and unhook ourselves to prevent
@@ -384,7 +385,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
}
list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list);
- synchronize_srcu(&kvm->irq_srcu);
+ synchronize_srcu_expedited(&kvm->irq_srcu);
mutex_unlock(&kvm->irqfds.resampler_lock);
}
@@ -523,7 +524,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
mutex_lock(&kvm->irq_lock);
hlist_del_init_rcu(&kian->link);
mutex_unlock(&kvm->irq_lock);
- synchronize_srcu(&kvm->irq_srcu);
+ synchronize_srcu_expedited(&kvm->irq_srcu);
kvm_arch_post_irq_ack_notifier_list_update(kvm);
}
@@ -608,7 +609,7 @@ kvm_irqfd_release(struct kvm *kvm)
/*
* Take note of a change in irq routing.
- * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards.
+ * Caller must invoke synchronize_srcu_expedited(&kvm->irq_srcu) afterwards.
*/
void kvm_irq_routing_update(struct kvm *kvm)
{
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9290165..cb2b78e 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1578,15 +1578,14 @@ static int check_memory_region_flags(struct kvm *kvm,
if (mem->flags & KVM_MEM_GUEST_MEMFD)
valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
-#ifdef CONFIG_HAVE_KVM_READONLY_MEM
/*
* GUEST_MEMFD is incompatible with read-only memslots, as writes to
* read-only memslots have emulated MMIO, not page fault, semantics,
* and KVM doesn't allow emulated MMIO for private memory.
*/
- if (!(mem->flags & KVM_MEM_GUEST_MEMFD))
+ if (kvm_arch_has_readonly_mem(kvm) &&
+ !(mem->flags & KVM_MEM_GUEST_MEMFD))
valid_flags |= KVM_MEM_READONLY;
-#endif
if (mem->flags & ~valid_flags)
return -EINVAL;
