[Intel-gfx] [PATCH] drm/i915/pmu: Correct the rc6 offset upon enabling

[Intel-gfx] [PATCH] drm/i915/pmu: Correct the rc6 offset upon enabling

[Chris Wilson]

The rc6 residency starts ticking from 0 from BIOS POST, but the kernel
starts measuring the time from its boot. If we start measuruing
I915_PMU_RC6_RESIDENCY while the GT is idle, we start our sampling from
0 and then upon first activity (park/unpark) add in all the rc6
residency since boot. After the first park with the sampler engaged, the
sleep/active counters are aligned.

Fixes: df6a42053513 ("drm/i915/pmu: Ensure monotonic rc6")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/i915_pmu.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 28a82c849bac..fe0f3e0aa4ce 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -648,6 +648,13 @@ static void i915_pmu_enable(struct perf_event *event)
 	BUILD_BUG_ON(ARRAY_SIZE(pmu->enable_count) != I915_PMU_MASK_BITS);
 	GEM_BUG_ON(bit >= ARRAY_SIZE(pmu->enable_count));
 	GEM_BUG_ON(pmu->enable_count[bit] == ~0);
+
+	if (pmu->enable_count[bit] == 0 &&
+	    config_enabled_mask(I915_PMU_RC6_RESIDENCY) & BIT_ULL(bit)) {
+		pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt);
+		pmu->sleep_last = ktime_get();
+	}
+
 	pmu->enable |= BIT_ULL(bit);
 	pmu->enable_count[bit]++;
 
-- 
2.25.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [Intel-gfx] [PATCH] drm/i915/pmu: Correct the rc6 offset upon enabling

[Chris Wilson]

Quoting Chris Wilson (2020-01-13 22:04:36)
> The rc6 residency starts ticking from 0 from BIOS POST, but the kernel
> starts measuring the time from its boot. If we start measuruing
> I915_PMU_RC6_RESIDENCY while the GT is idle, we start our sampling from
> 0 and then upon first activity (park/unpark) add in all the rc6
> residency since boot. After the first park with the sampler engaged, the
> sleep/active counters are aligned.
> 
> Fixes: df6a42053513 ("drm/i915/pmu: Ensure monotonic rc6")
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> ---
>  drivers/gpu/drm/i915/i915_pmu.c | 7 +++++++
>  1 file changed, 7 insertions(+)
> 
> diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
> index 28a82c849bac..fe0f3e0aa4ce 100644
> --- a/drivers/gpu/drm/i915/i915_pmu.c
> +++ b/drivers/gpu/drm/i915/i915_pmu.c
> @@ -648,6 +648,13 @@ static void i915_pmu_enable(struct perf_event *event)
>         BUILD_BUG_ON(ARRAY_SIZE(pmu->enable_count) != I915_PMU_MASK_BITS);
>         GEM_BUG_ON(bit >= ARRAY_SIZE(pmu->enable_count));
>         GEM_BUG_ON(pmu->enable_count[bit] == ~0);
> +
> +       if (pmu->enable_count[bit] == 0 &&
> +           config_enabled_mask(I915_PMU_RC6_RESIDENCY) & BIT_ULL(bit)) {
> +               pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt);
> +               pmu->sleep_last = ktime_get();

I guess strictly we need with_intel_runtime_pm_get {}

Good exercise for CI ;)
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] ✗ Fi.CI.BAT: failure for drm/i915/pmu: Correct the rc6 offset upon enabling

[Patchwork]

== Series Details ==

Series: drm/i915/pmu: Correct the rc6 offset upon enabling
URL   : https://patchwork.freedesktop.org/series/71982/
State : failure

== Summary ==

CI Bug Log - changes from CI_DRM_7737 -> Patchwork_16085
====================================================

Summary
-------

  **FAILURE**

  Serious unknown changes coming with Patchwork_16085 absolutely need to be
  verified manually.
  
  If you think the reported changes have nothing to do with the changes
  introduced in Patchwork_16085, please notify your bug team to allow them
  to document this new failure mode, which will reduce false positives in CI.

  External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16085/index.html

Possible new issues
-------------------

  Here are the unknown changes that may have been introduced in Patchwork_16085:

### IGT changes ###

#### Possible regressions ####

  * igt@runner@aborted:
    - fi-cfl-guc:         NOTRUN -> [FAIL][1]
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16085/fi-cfl-guc/igt@runner@aborted.html

  
Known issues
------------

  Here are the changes found in Patchwork_16085 that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@i915_module_load@reload-with-fault-injection:
    - fi-cfl-guc:         [PASS][2] -> [INCOMPLETE][3] ([i915#505] / [i915#671])
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7737/fi-cfl-guc/igt@i915_module_load@reload-with-fault-injection.html
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16085/fi-cfl-guc/igt@i915_module_load@reload-with-fault-injection.html
    - fi-skl-6700k2:      [PASS][4] -> [DMESG-WARN][5] ([i915#889])
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7737/fi-skl-6700k2/igt@i915_module_load@reload-with-fault-injection.html
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16085/fi-skl-6700k2/igt@i915_module_load@reload-with-fault-injection.html

  * igt@i915_selftest@live_gem_contexts:
    - fi-cfl-8700k:       [PASS][6] -> [INCOMPLETE][7] ([CI#80] / [i915#424])
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7737/fi-cfl-8700k/igt@i915_selftest@live_gem_contexts.html
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16085/fi-cfl-8700k/igt@i915_selftest@live_gem_contexts.html

  
#### Possible fixes ####

  * igt@gem_exec_fence@basic-wait-default:
    - {fi-ehl-1}:         [INCOMPLETE][8] ([i915#937]) -> [PASS][9]
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7737/fi-ehl-1/igt@gem_exec_fence@basic-wait-default.html
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16085/fi-ehl-1/igt@gem_exec_fence@basic-wait-default.html

  * igt@i915_module_load@reload-with-fault-injection:
    - fi-skl-lmem:        [INCOMPLETE][10] ([i915#671]) -> [PASS][11]
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7737/fi-skl-lmem/igt@i915_module_load@reload-with-fault-injection.html
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16085/fi-skl-lmem/igt@i915_module_load@reload-with-fault-injection.html

  * igt@i915_selftest@live_blt:
    - fi-hsw-4770:        [DMESG-FAIL][12] ([i915#553] / [i915#725]) -> [PASS][13]
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7737/fi-hsw-4770/igt@i915_selftest@live_blt.html
   [13]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16085/fi-hsw-4770/igt@i915_selftest@live_blt.html

  
  {name}: This element is suppressed. This means it is ignored when computing
          the status of the difference (SUCCESS, WARNING, or FAILURE).

  [CI#80]: https://gitlab.freedesktop.org/gfx-ci/i915-infra/issues/80
  [i915#424]: https://gitlab.freedesktop.org/drm/intel/issues/424
  [i915#505]: https://gitlab.freedesktop.org/drm/intel/issues/505
  [i915#553]: https://gitlab.freedesktop.org/drm/intel/issues/553
  [i915#671]: https://gitlab.freedesktop.org/drm/intel/issues/671
  [i915#725]: https://gitlab.freedesktop.org/drm/intel/issues/725
  [i915#889]: https://gitlab.freedesktop.org/drm/intel/issues/889
  [i915#937]: https://gitlab.freedesktop.org/drm/intel/issues/937


Participating hosts (40 -> 43)
------------------------------

  Additional (11): fi-hsw-4770r fi-hsw-peppy fi-skl-6770hq fi-bwr-2160 fi-snb-2520m fi-ilk-650 fi-kbl-7500u fi-gdg-551 fi-ivb-3770 fi-blb-e6850 fi-skl-6600u 
  Missing    (8): fi-hsw-4200u fi-byt-squawks fi-bsw-cyan fi-ctg-p8600 fi-bsw-kefka fi-byt-n2820 fi-byt-clapper fi-bsw-nick 


Build changes
-------------

  * CI: CI-20190529 -> None
  * Linux: CI_DRM_7737 -> Patchwork_16085

  CI-20190529: 20190529
  CI_DRM_7737: 2a331333791d2e499ac843e1dc25cd8ea5bdc81f @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_5364: b7cb6ffdb65cbd233f5ddee2f2dabf97b34fa640 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_16085: 04aa0e368f17908e65b76e04a98dbf65ab891a4d @ git://anongit.freedesktop.org/gfx-ci/linux


== Kernel 32bit build ==

Warning: Kernel 32bit buildtest failed:
https://intel-gfx-ci.01.org/Patchwork_16085/build_32bit.log

  CALL    scripts/checksyscalls.sh
  CALL    scripts/atomic/check-atomics.sh
  CHK     include/generated/compile.h
Kernel: arch/x86/boot/bzImage is ready  (#1)
  Building modules, stage 2.
  MODPOST 122 modules
ERROR: "__udivdi3" [drivers/gpu/drm/amd/amdgpu/amdgpu.ko] undefined!
scripts/Makefile.modpost:93: recipe for target '__modpost' failed
make[1]: *** [__modpost] Error 1
Makefile:1282: recipe for target 'modules' failed
make: *** [modules] Error 2


== Linux commits ==

04aa0e368f17 drm/i915/pmu: Correct the rc6 offset upon enabling

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16085/index.html
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] ✗ Fi.CI.BUILD: warning for drm/i915/pmu: Correct the rc6 offset upon enabling

[Patchwork]

== Series Details ==

Series: drm/i915/pmu: Correct the rc6 offset upon enabling
URL   : https://patchwork.freedesktop.org/series/71982/
State : warning

== Summary ==

CALL    scripts/checksyscalls.sh
  CALL    scripts/atomic/check-atomics.sh
  CHK     include/generated/compile.h
Kernel: arch/x86/boot/bzImage is ready  (#1)
  Building modules, stage 2.
  MODPOST 122 modules
ERROR: "__udivdi3" [drivers/gpu/drm/amd/amdgpu/amdgpu.ko] undefined!
scripts/Makefile.modpost:93: recipe for target '__modpost' failed
make[1]: *** [__modpost] Error 1
Makefile:1282: recipe for target 'modules' failed
make: *** [modules] Error 2

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16085/build_32bit.log
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx