aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2022-12-14drm/amd/pm: add missing SMU13.0.7 mm_dpm feature mappingEvan Quan1-0/+2
Without this, the pp_dpm_vclk and pp_dpm_dclk outputs are not with correct data. Signed-off-by: Evan Quan <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected] # 6.0.x
2022-12-14drm/amd/pm: add missing SMU13.0.0 mm_dpm feature mappingEvan Quan1-0/+2
Without this, the pp_dpm_vclk and pp_dpm_dclk outputs are not with correct data. Signed-off-by: Evan Quan <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected] # 6.0.x
2022-12-14drm/amdgpu: Add notifier lock for KFD userptrsFelix Kuehling6-91/+172
Add a per-process MMU notifier lock for processing notifiers from userptrs. Use that lock to properly synchronize page table updates with MMU notifiers. Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Xiaogang Chen<[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-12-14drm/amd/display: Add DCN314 display SG SupportYifan Zhang1-0/+1
Add display SG support for DCN 3.1.4. Signed-off-by: Yifan Zhang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected]
2022-12-14drm/amdgpu: WARN when freeing kernel memory during suspendChristian König1-0/+2
When buffers are freed during suspend there is no guarantee that they can be re-allocated during resume. The PSP subsystem seems to be quite buggy regarding this, so add a WARN_ON() to point out those bugs. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Tested-by: Guilherme G. Piccoli <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-12-14drm/amdgpu: fixx NULL pointer deref in gmc_v9_0_get_vm_pteChristian König1-1/+3
We not only need to make sure that we have a BO, but also that the BO has some backing store. Fixes: d1a372af1c3d ("drm/amdgpu: Set MTYPE in PTE based on BO flags") Signed-off-by: Christian König <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Luben Tuikov <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-12-14thermal/drivers/imx_sc_thermal: Drop empty platform remove functionUwe Kleine-König1-6/+0
A remove callback just returning 0 is equivalent to no remove callback at all. So drop the useless function. Signed-off-by: Uwe Kleine-König <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/qcom/lmh: Fix irq handler return valueBjorn Andersson1-1/+1
After enough invocations the LMh irq is eventually reported as bad, because the handler doesn't return IRQ_HANDLED, fix this. Fixes: 53bca371cdf7 ("thermal/drivers/qcom: Add support for LMh driver") Reported-by: Daniel Lezcano <[email protected]> Signed-off-by: Bjorn Andersson <[email protected]> Reviewed-by: Dmitry Baryshkov <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14dt-bindings: thermal: qcom-tsens: Add compatible for sm8550Neil Armstrong1-0/+1
The Qualcomm SM8550 platform has three instances of the tsens block, add a compatible for these instances. Signed-off-by: Neil Armstrong <[email protected]> Reviewed-by: Krzysztof Kozlowski <[email protected]> Acked-by: Amit Kucheria <[email protected]> Link: https://lore.kernel.org/r/20221114-narmstrong-sm8550-upstream-tsens-v1-0-0e169822830f@linaro.org Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/st: Use devm_platform_get_and_ioremap_resource()Minghao Chi1-3/+1
Convert platform_get_resource(), devm_ioremap_resource() to a single call to devm_platform_get_and_ioremap_resource(), as this is exactly what this function does. Signed-off-by: Minghao Chi <[email protected]> Signed-off-by: ye xingchen <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14dt-bindings: thermal: rzg2l-thermal: Document RZ/Five SoCLad Prabhakar1-1/+1
The TSU block on the RZ/Five SoC is identical to one found on the RZ/G2UL SoC. "renesas,r9a07g043-tsu" compatible string will be used on the RZ/Five SoC so to make this clear, update the comment to include RZ/Five SoC. No driver changes are required as generic compatible string "renesas,rzg2l-tsu" will be used as a fallback on RZ/Five SoC. Signed-off-by: Lad Prabhakar <[email protected]> Acked-by: Rob Herring <[email protected]> Reviewed-by: Geert Uytterhoeven <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14dt-bindings: thermal: k3-j72xx: conditionally require efuse reg rangeBryan Brattlof1-0/+16
Only some of TI's J721E SoCs will need a eFuse register range mapped to determine if they're affected by TI's i2128 erratum. All other SoC will not need this eFuse range to function properly Update the bindings for the k3_j72xx_bandgap thermal driver so other devices will only need two register ranges Signed-off-by: Bryan Brattlof <[email protected]> Reviewed-by: Krzysztof Kozlowski <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14dt-bindings: thermal: k3-j72xx: elaborate on binding descriptionBryan Brattlof1-1/+18
Elaborate on the function of this device node as well as some of the properties this node uses. Signed-off-by: Bryan Brattlof <[email protected]> Acked-by: Krzysztof Kozlowski <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/k3_j72xx_bandgap: Map fuse_base only for erratum workaroundBryan Brattlof1-12/+22
Some of TI's J721E SoCs require a software trimming procedure for the temperature monitors to function properly. To determine if a particular J721E is not affected by this erratum, both bits in the WKUP_SPARE_FUSE0 region must be set. Other SoCs, not affected by this erratum, will not need this region. Map the 'fuse_base' region only when the erratum fix is needed. Signed-off-by: Bryan Brattlof <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/k3_j72xx_bandgap: Remove fuse_base from structureBryan Brattlof1-12/+12
'fuse_base' is only needed during the initial probe function to provide data for a software trimming method for some of TI's devices affected by the i2128 erratum. The devices not affected will not use this region Remove fuse_base from the main k3_j72xx_bandgap structure Signed-off-by: Bryan Brattlof <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/k3_j72xx_bandgap: Use bool for i2128 erratum flagBryan Brattlof1-4/+4
Some of TI's J721E SoCs require a software trimming method to report temperatures accurately. Currently we are using a few different data types to indicate when we should apply the erratum. Change the 'workaround_needed' variable's data type to a bool to align with how we are using this variable currently. Signed-off-by: Bryan Brattlof <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/k3_j72xx_bandgap: Simplify k3_thermal_get_temp() functionBryan Brattlof1-8/+1
The k3_thermal_get_temp() function can be simplified to return only the result of k3_bgp_read_temp() without needing the 'ret' variable Signed-off-by: Bryan Brattlof <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/qcom: Demote error log of thermal zone register to debugManivannan Sadhasivam1-1/+1
devm_thermal_of_zone_register() can fail with -ENODEV if thermal zone for the channel is not represented in DT. This is perfectly fine since not all sensors needs to be used for thermal zones but only a few in real world. So demote the error log to debug to avoid spamming users. Signed-off-by: Manivannan Sadhasivam <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/qcom/temp-alarm: Fix inaccurate warning for gen2Luca Weiss1-1/+2
On gen2 chips the stage2 threshold is not 140 degC but 125 degC. Make the warning message clearer by using this variable and also by including the temperature that was checked for. Fixes: aa92b3310c55 ("thermal/drivers/qcom-spmi-temp-alarm: Add support for GEN2 rev 1 PMIC peripherals") Signed-off-by: Luca Weiss <[email protected]> Reviewed-by: Amit Kucheria <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14dt-bindings: thermal: qcom-tsens: narrow interrupts for SC8280XP, SM6350 and ↵Krzysztof Kozlowski1-0/+3
SM8450 Narrow number of interrupts per variants: SC8280XP, SM6350 and SM8450. The compatibles are already used and described. They only missed the constraints of number of interrupts. Signed-off-by: Krzysztof Kozlowski <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/core/power allocator: Remove a useless includeChristophe JAILLET1-1/+0
This file does not use rcu, so there is no point in including <linux/rculist.h>. Remove it. Signed-off-by: Christophe JAILLET <[email protected]> Reviewed-by: Lukasz Luba <[email protected]> Link: https://lore.kernel.org/r/9adeec47cb5a8193016272d5c8bf936235c1711d.1669459337.git.christophe.jaillet@wanadoo.fr Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/imx8mm: Add hwmon supportAlexander Stein1-0/+4
Expose thermal sensors as HWMON devices. Signed-off-by: Alexander Stein <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal: qcom-spmi-adc-tm5: suppress probe-deferral error messageJohan Hovold1-4/+2
Drivers should not be logging errors on probe deferral. Switch to using dev_err_probe() to log failures when parsing the devicetree to avoid errors like: qcom-spmi-adc-tm5 c440000.spmi:pmic@0:adc-tm@3400: get dt data failed: -517 when a channel is not yet available. Signed-off-by: Johan Hovold <[email protected]> Reviewed-by: Manivannan Sadhasivam <[email protected]> Reviewed-by: Andrew Halaney <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14dt-bindings: thermal: mediatek: add compatible string for MT7986 and MT7981 SoCDaniel Golle1-0/+2
Document compatible string 'mediatek,mt7986-thermal' for V3 thermal unit found in MT7986 SoCs. 'mediatek,mt7981-thermal' is also added as it is identical with the thermal unit of MT7986. Signed-off-by: Daniel Golle <[email protected]> Acked-by: Krzysztof Kozlowski <[email protected]> Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal: ti-soc-thermal: Drop comma after SoC match table sentinelGeert Uytterhoeven1-1/+1
It does not make sense to have a comma after a sentinel, as any new elements must be added before the sentinel. Signed-off-by: Geert Uytterhoeven <[email protected]> Acked-by: Keerthy <[email protected]> Link: https://lore.kernel.org/r/1d6de2a80b919cb11199e56ac06ad21c273ebe57.1669045586.git.geert+renesas@glider.be Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/imx: Add support for loading calibration data from OCOTPMarek Vasut1-0/+164
The TMU TASR, TCALIVn, TRIM registers must be explicitly programmed with calibration values in OCOTP. Add support for reading the OCOTP calibration data and programming those into the TMU hardware. The MX8MM/MX8MN TMUv1 uses only one OCOTP cell, while MX8MP TMUv2 uses 4, the programming differs in each case. Based on U-Boot commits: 70487ff386c ("imx8mm: Load fuse for TMU TCALIV and TASR") ebb9aab318b ("imx: load calibration parameters from fuse for i.MX8MP") Reviewed-by: Peng Fan <[email protected]> Signed-off-by: Marek Vasut <[email protected]> Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14dt-bindings: thermal: imx8mm-thermal: Document optional nvmem-cellsMarek Vasut1-0/+7
The TMU TASR, TCALIVn, TRIM registers must be explicitly programmed with calibration values from OCOTP. Document optional phandle to OCOTP nvmem provider. Acked-by: Krzysztof Kozlowski <[email protected]> Signed-off-by: Marek Vasut <[email protected]> Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/qcom/tsens: Rework debugfs file structureChristian Marangi1-10/+3
The current tsens debugfs structure is composed by: - a tsens dir in debugfs with a version file - a directory for each tsens istance with sensors file to dump all the sensors value. This works on the assumption that we have the same version for each istance but this assumption seems fragile and with more than one tsens istance results in the version file not tracking each of them. A better approach is to just create a subdirectory for each tsens istance and put there version and sensors debugfs file. Using this new implementation results in less code since debugfs entry are created only on successful tsens probe. Signed-off-by: Christian Marangi <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/qcom/tsens: Fix wrong version id dbg_version_showChristian Marangi1-1/+1
For VER_0 the version was incorrectly reported as 0.1.0. Fix that and correctly report the major version for this old tsens revision. Signed-off-by: Christian Marangi <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/qcom/tsens: Init debugfs only with successful probeChristian Marangi1-3/+5
Calibrate and tsens_register can fail or PROBE_DEFER. This will cause a double or a wrong init of the debugfs information. Init debugfs only with successful probe fixing warning about directory already present. Signed-off-by: Christian Marangi <[email protected]> Acked-by: Thara Gopinath <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/tsens: Add IPQ8074 supportRobert Marko3-1/+21
Qualcomm IPQ8074 uses tsens v2.3 IP, however unlike other tsens v2 IP it only has one IRQ, that is used for up/low as well as critical. It also does not support negative trip temperatures. Signed-off-by: Robert Marko <[email protected]> Reviewed-by: Bjorn Andersson <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/tsens: Allow configuring min and max tripsRobert Marko6-2/+14
IPQ8074 and IPQ6018 dont support negative trip temperatures and support up to 204 degrees C as the max trip temperature. So, instead of always setting the -40 as min and 120 degrees C as max allow it to be configured as part of the features. Signed-off-by: Robert Marko <[email protected]> Reviewed-by: Bjorn Andersson <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/tsens: Add support for combined interruptRobert Marko6-6/+38
Despite using tsens v2.3 IP, IPQ8074 and IPQ6018 only have one IRQ for signaling both up/low and critical trips. Signed-off-by: Robert Marko <[email protected]> Reviewed-by: Bjorn Andersson <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14dt-bindings: thermal: tsens: Add ipq8074 compatibleRobert Marko1-11/+65
Qualcomm IPQ8074 has tsens v2.3.0 block, though unlike existing v2 IP it only uses one IRQ, so tsens v2 compatible cannot be used as the fallback. We also have to make sure that correct interrupts are set according to compatibles, so populate interrupt information per compatibles. Signed-off-by: Robert Marko <[email protected]> Reviewed-by: Krzysztof Kozlowski <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/of: Fix memory leak on thermal_of_zone_register() failureIdo Schimmel1-2/+6
The function does not free 'of_ops' upon failure, leading to a memory leak [1]. Fix by freeing 'of_ops' in the error path. [1] unreferenced object 0xffff8ee846198c80 (size 128): comm "swapper/0", pid 1, jiffies 4294699704 (age 70.076s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ d0 3f 6e 8c ff ff ff ff 00 00 00 00 00 00 00 00 .?n............. backtrace: [<00000000d136f562>] __kmalloc_node_track_caller+0x42/0x120 [<0000000063f31678>] kmemdup+0x1d/0x40 [<00000000e6d24096>] thermal_of_zone_register+0x49/0x520 [<000000005e78c755>] devm_thermal_of_zone_register+0x54/0x90 [<00000000ee6b209e>] pmbus_add_sensor+0x1b4/0x1d0 [<00000000896105e3>] pmbus_add_sensor_attrs_one+0x123/0x440 [<0000000049e990a6>] pmbus_add_sensor_attrs+0xfe/0x1d0 [<00000000466b5440>] pmbus_do_probe+0x66b/0x14e0 [<0000000084d42285>] i2c_device_probe+0x13b/0x2f0 [<0000000029e2ae74>] really_probe+0xce/0x2c0 [<00000000692df15c>] driver_probe_device+0x19/0xd0 [<00000000547d9cce>] __device_attach_driver+0x6f/0x100 [<0000000020abd24b>] bus_for_each_drv+0x76/0xc0 [<00000000665d9563>] __device_attach+0xfc/0x180 [<000000008ddd4d6a>] bus_probe_device+0x82/0xa0 [<000000009e61132b>] device_add+0x3fe/0x920 Fixes: 3fd6d6e2b4e8 ("thermal/of: Rework the thermal device tree initialization") Signed-off-by: Ido Schimmel <[email protected]> Reviewed-by: Vadim Pasternak <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/k3_j72xx_bandgap: Fix the debug print messageKeerthy1-1/+1
The debug print message to check the workaround applicability is inverted. Fix the same. Fixes: ffcb2fc86eb7 ("thermal: k3_j72xx_bandgap: Add the bandgap driver support") Reported-by: Bryan Brattlof <[email protected]> Signed-off-by: Keerthy <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14dt-bindings: thermal: Convert generic-adc-thermal to DT schemaRob Herring2-95/+84
Convert the 'generic-adc-thermal' binding to DT schema format. The binding said '#thermal-sensor-cells' should be 1, but all in tree users are 0 and 1 doesn't make sense for a single channel. Drop the example's related providers and consumers of the 'generic-adc-thermal' node as the convention is to not have those in the examples. Signed-off-by: Rob Herring <[email protected]> Reviewed-by: Krzysztof Kozlowski <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/imx8mm_thermal: Validate temperature rangeMarcus Folkesson1-1/+7
Check against the upper temperature limit (125 degrees C) before consider the temperature valid. Fixes: 5eed800a6811 ("thermal: imx8mm: Add support for i.MX8MM thermal monitoring unit") Signed-off-by: Marcus Folkesson <[email protected]> Reviewed-by: Jacky Bai <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14thermal/drivers/imx8mm_thermal: Use GENMASK() when appropriateMarcus Folkesson1-2/+2
GENMASK() is preferred to use for bitmasks. Signed-off-by: Marcus Folkesson <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14dt-bindings: thermal: tsens: Add sm8450 compatibleLuca Weiss1-0/+1
Document the tsens-v2 compatible for sm8450 SoC. Signed-off-by: Luca Weiss <[email protected]> Reviewed-by: Krzysztof Kozlowski <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Daniel Lezcano <[email protected]>
2022-12-14spi: fsl_spi: Don't change speed while chipselect is activeChristophe Leroy1-3/+16
Commit c9bfcb315104 ("spi_mpc83xx: much improved driver") made modifications to the driver to not perform speed changes while chipselect is active. But those changes where lost with the convertion to tranfer_one. Previous implementation was allowing speed changes during message transfer when cs_change flag was set. At the time being, core SPI does not provide any feature to change speed while chipselect is off, so do not allow any speed change during message transfer, and perform the transfer setup in prepare_message in order to set correct speed while chipselect is still off. Reported-by: Herve Codina <[email protected]> Fixes: 64ca1a034f00 ("spi: fsl_spi: Convert to transfer_one") Cc: [email protected] Signed-off-by: Christophe Leroy <[email protected]> Tested-by: Herve Codina <[email protected]> Reviewed-by: Herve Codina <[email protected]> Link: https://lore.kernel.org/r/8aab84c51aa330cf91f4b43782a1c483e150a4e3.1671025244.git.christophe.leroy@csgroup.eu Signed-off-by: Mark Brown <[email protected]>
2022-12-14perf build: Fix python/perf.so library's nameIan Rogers2-2/+4
Since Python 3.3 extensions have a suffix encoding platform and version information. For example, the perf extension was previously perf.so but now maybe perf.cpython-310-x86_64-linux-gnu.so. Compute the extension using Python and then use this in the target name. Doing this avoids the "perf.so" target always being rebuilt. Signed-off-by: Ian Rogers <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Alexey Bayduraev <[email protected]> Cc: Andi Kleen <[email protected]> Cc: Anshuman Khandual <[email protected]> Cc: Athira Jajeev <[email protected]> Cc: Eelco Chaudron <[email protected]> Cc: German Gomez <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: James Clark <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Kan Liang <[email protected]> Cc: Kim Phillips <[email protected]> Cc: Leo Yan <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Riccardo Mancini <[email protected]> Cc: Sandipan Das <[email protected]> Cc: Sean Christopherson <[email protected]> Cc: Shaomin Deng <[email protected]> Cc: Stephane Eranian <[email protected]> Cc: Timothy Hayes <[email protected]> Cc: Xing Zhengjun <[email protected]> Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2022-12-14perf test arm64: Add attr tests for new VG registerJames Clark3-0/+33
Ensure that the availability of the VG register behaves as expected depending on the kernel version and SVE support. Signed-off-by: James Clark <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2022-12-14perf test: Add mechanism for skipping attr tests on kernel versionsJames Clark1-1/+27
The first two version numbers are used since that is where the ABI changes happen, so seems to be the most useful for now. 'Until' is exclusive and 'since' is inclusive so that the same version number can be used to mark a point where the change comes into effect. This allows keeping the tests in a state where new tests will also pass on older kernels if the existence of a new feature isn't explicitly broadcast by the kernel. For example extended user regs are currently discovered by trial and error calls to perf_event_open. Signed-off-by: James Clark <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2022-12-14perf test: Add mechanism for skipping attr tests on auxiliary vector valuesJames Clark1-2/+31
This can be used to skip tests or provide different test values on different platforms. For example to run a test only where Arm SVE is present add this to the config section: auxv = auxv["AT_HWCAP"] & 0x200000 == 0x200000 The value is a freeform Python expression that is evaled in the context of a map called "auxv" that contains the decoded auxiliary vector. Signed-off-by: James Clark <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2022-12-14perf test: Add ability to test exit code for attr testsJames Clark1-2/+8
Currently the return value is used to skip the test, but sometimes it can be useful to test if a certain command should return a certain exit code. Signed-off-by: James Clark <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2022-12-14perf test: add new task-analyzer testsPetar Gligoric1-0/+151
Provide task-analyzer test cases for all possible arguments and a subset of possible combinations. 12 Tests in total. test_basic: - cmd:"perf script report task-analyzer" - Fundamental test of script without arguments. - Check for standard output. test_ns_rename: - cmd:"perf script report task-analyzer --ns --rename-comms-by-tids 0:random" - Standard task with timestamps in nanoseconds and comm renamed. - Check for standard output. test_ms_filtertasks_highlight: - cmd:"perf script report task-analyzer --ms --filter-tasks perf --highlight-tasks perf" - Standard task with timestamps in milliseconds, task filtered out and highlighted. - Check for standard output. test_extended_times_timelimit_limittasks: - cmd "perf script report task-analyzer --extended-times --time-limit :99999" - Standard task with additional schedule out/in info and timlimit active at 99999. - Check for extended table output. test_summary: - cmd:"perf script report task-analyzer --summary" - Standard task with additional summary output. - Check for summary print. test_summary_extended: - cmd:"perf script report task-analyzer --summary-extended" - Standard task with summary and additional schedule in/out info. - Chceck for extended table print. test_summaryonly: - cmd:"perf script report task-analyzer --summary-only" - Only summary should be printed. - Check for summary print. test_extended_times_summary_ns: - cmd:"perf script report task-analyzer --extended-times --summary --ns" - Standard task with extended schedule in/out information and summary in ns. - Check for extended table and summary. test_csv: - cmd:"perf script report task-analyzer --csv csv" - Print standard task to csv file in csv format. - Check for csv format. test_csv_extended_times: - cmd:"perf script report task-analyzer --csv csv --extended-times" - Print standard task to csv file in csv format with additional schedule in/out information. - Check for additional information and csv format. test_csvsummary: - cmd:"perf script report task-analyzer --csv-summary csvsummary" - Print summary to csvsummary file in csv format. - Check for csv format. test_csvsummary_extended: - cmd:"perf script report task-analyzer --csv-summary csvsummary --summary-extended" - Print summary to csvsummary file in csv format with additional schedule in/out information. - Check for additional information and csv format. Suggested-by: Ian Rogers <[email protected]> Signed-off-by: Petar Gligoric <[email protected]> Cc: Andi Kleen <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Namhyung Kim <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Hagen Paul Pfeifer <[email protected]> Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2022-12-14perf script: task-analyzer add csv supportPetar Gligoric1-89/+185
This patch adds the possibility to write the trace and the summary as csv files to a user specified file. A format as such simplifies further data processing. This is achieved by having ";" as separators instead of spaces and solely one header per file. Additional parameters are being considered, like in the normal usage of the script. Colors are turned off in the case of a csv output, thus the highlight option is also being ignored. Usage: Write standard task to csv file: $ perf script report tasks-analyzer --csv <file> write limited output to csv file in nanoseconds: $ perf script report tasks-analyzer --csv <file> --ns --limit-to-tasks 1337 Write summary to a csv file: $ perf script report tasks-analyzer --csv-summary <file> Write summary to csv file with additional schedule information: $ perf script report tasks-analyzer --csv-summary <file> --summary-extended Write both summary and standard task to a csv file: $ perf script report tasks-analyzer --csv --csv-summary The following examples illustrate what is possible with the CSV output. The first command sequence will record all scheduler switch events for 10 seconds, the task-analyzer calculates task information like runtimes as CSV. A small python snippet using pandas and matplotlib will visualize the most frequent task (e.g. kworker/1:1) runtimes - each runtime as a bar in a bar chart: $ perf record -e sched:sched_switch -a -- sleep 10 $ perf script report tasks-analyzer --ns --csv tasks.csv $ cat << EOF > /tmp/freq-comm-runtimes-bar.py import pandas as pd import matplotlib.pyplot as plt df = pd.read_csv("tasks.csv", sep=';') most_freq_comm = df["COMM"].value_counts().idxmax() most_freq_runtimes = df[df["COMM"]==most_freq_comm]["Runtime"] plt.title(f"Runtimes for Task {most_freq_comm} in Nanoseconds") plt.bar(range(len(most_freq_runtimes)), most_freq_runtimes) plt.show() $ python3 /tmp/freq-comm-runtimes-bar.py As a seconds example, the subsequent script generates a pie chart of all accumulated tasks runtimes for 10 seconds of system recordings: $ perf record -e sched:sched_switch -a -- sleep 10 $ perf script report tasks-analyzer --csv-summary task-summary.csv $ cat << EOF > /tmp/accumulated-task-pie.py import pandas as pd from matplotlib.pyplot import pie, axis, show df = pd.read_csv("task-summary.csv", sep=';') sums = df.groupby(df["Comm"])["Accumulated"].sum() axis("equal") pie(sums, labels=sums.index); show() EOF $ python3 /tmp/accumulated-task-pie.py A variety of other visualizations are possible in matplotlib and other environments. Of course, pandas, numpy and co. also allow easy statistical analysis of the data! Signed-off-by: Petar Gligoric <[email protected]> Cc: Andi Kleen <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Namhyung Kim <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Hagen Paul Pfeifer <[email protected]> Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2022-12-14perf script: Introduce task analyzer python scriptHagen Paul Pfeifer3-0/+843
Introduce a new 'perf script' to analyze task scheduling behavior. During the task analysis, some data is always needed - which goes beyond the simple time of switching on and off a task (process/thread). This concerns for example the runtime of a process or the frequency with which the process was called. This script serves to simplify this recurring analyze process. It immediately provides the user with helpful task characteristic information about the tasks runtimes. Usage: Recorded can be in two ways: $ perf script record tasks-analyzer -- sleep 10 $ perf record -e sched:sched_switch -a -- sleep 10 The script can parse all perf.data files, most important: sched:sched_switch events are mandatory, other events will be ignored. Most simple report use case is to just call the script without arguments: $ perf script report tasks-analyzer Switched-In Switched-Out CPU PID TID Comm Runtime Time Out-In 15576.658891407 15576.659156086 4 2412 2428 gdbus 265 1949 15576.659111320 15576.659455410 0 2412 2412 gnome-shell 344 2267 15576.659491326 15576.659506173 2 74 74 kworker/2:1 15 13145 15576.659506173 15576.659825748 2 2858 2858 gnome-terminal- 320 63263 15576.659871270 15576.659902872 6 20932 20932 kworker/u16:0 32 2314582 15576.659909951 15576.659945501 3 27264 27264 sh 36 -1 15576.659853285 15576.659971052 7 27265 27265 perf 118 5050741 [...] What is not shown here are the ASCII color sequences. For example, if the task consists of only one thread, the TID is grayed out. Runtime is the time the task was running on the CPU, Time Out-In is the time between the process being scheduled *out* and scheduled back *in*. So the last time span between two executions. If -1 is printed, then the task simply ran the first time in the measurements - a Out-In delta could not be calculated. In addition to the chronological representation, there is a summary on task level. This output can be additionally switched on via the --summary option and provides information such as max, min & average runtime per process. The maximum runtime is often important for debugging. The call looks like this: $ perf script report tasks-analyzer --summary Summary Task Information Runtime Information PID TID Comm Runs Accumulated Mean Median Min Max Max At 14 14 ksoftirqd/0 13 334 26 15 9 127 15571.621211956 15 15 rcu_preempt 133 1778 13 13 2 33 15572.581176024 16 16 migration/0 3 49 16 13 12 24 15571.608915425 20 20 migration/1 3 34 11 13 8 13 15571.639101555 25 25 migration/2 3 32 11 12 9 12 15575.639239896 [...] Besides these two options, there are a number of other options that change the output and behavior. This can be queried via --help. Options worth mentioning include: - filter-tasks - filter out unneeded tasks, --filter-task 1337,/sbin/init - highlight-tasks - more pleasant focusing, --highlight-tasks 1:red,mutt:yellow - extended-times - show combinations of elapsed times between schedule in/schedule out - summary-extended - summary with additional information, like maximum delta time statistics - rename-comms-by-tids - handy for inexpressive processnames like python, --rename 1337:my-python-app - ms - show timestamps in milliseconds, nanoseconds is also possible (--ns) - time-limit - limit the analyzer to a time range, --time-limit 15576.0:15576.1 Script is tested and prime time ready for python2 & python3: - make PYTHON=python3 prefix=/usr/local install - make PYTHON=python2 prefix=/usr/local install Signed-off-by: Hagen Paul Pfeifer <[email protected]> Cc: Andi Kleen <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Namhyung Kim <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Petar Gligoric <[email protected]> Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2022-12-14perf cs-etm: Print auxtrace info even if OpenCSD isn't linkedJames Clark4-166/+191
Printing the info doesn't have any dependency on OpenCSD, and neither does recording Coresight data. Because it's sometimes useful to look at the info for debugging, it makes sense to be able to see it on the same platform that the recording was made on. So pull the auxtrace info printing parts into a new file that is always compiled into Perf. Signed-off-by: James Clark <[email protected]> Cc: Al Grant <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Leo Yan <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mathieu Poirier <[email protected]> Cc: Mike Leach <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Suzuki Poulouse <[email protected]> Cc: Will Deacon <[email protected]> Cc: [email protected] Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>