[Intel-gfx] [PATCH] drm/i915/gt: Check carefully for an idle engine in wait-for-idle

[Intel-gfx] [PATCH] drm/i915/gt: Check carefully for an idle engine in wait-for-idle

[Chris Wilson]

intel_gt_wait_for_idle() tries to wait until all the outstanding requests
are retired and the GPU is idle. As a side effect of retiring requests,
we may submit more work to flush any pm barriers, and so the
wait-for-idle tries to flush the background pm work and catch the new
requests. However, if the work completed in the background before we
were able to flush, it would queue the extra barrier request without us
noticing -- and so we would return from wait-for-idle with one request
remaining. (This breaks e.g. record_default_state where we need to wait
until that barrier is retired, and it may slow suspend down by causing
us to wait on the background retirement worker as opposed to immediately
retiring the barrier.)

However, since we track if there has been a submission since the engine
pm barrier, we can very quickly detect if the idle barrier is still
outstanding.

Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/1763
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_gt_requests.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index dec96a731a77..1781f176886a 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -26,6 +26,11 @@ static bool retire_requests(struct intel_timeline *tl)
 	return !i915_active_fence_isset(&tl->last_request);
 }
 
+static bool engine_active(const struct intel_engine_cs *engine)
+{
+	return READ_ONCE(engine->wakeref_serial) != READ_ONCE(engine->serial);
+}
+
 static bool flush_submission(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
@@ -37,8 +42,13 @@ static bool flush_submission(struct intel_gt *gt)
 
 	for_each_engine(engine, gt, id) {
 		intel_engine_flush_submission(engine);
-		active |= flush_work(&engine->retire_work);
-		active |= flush_delayed_work(&engine->wakeref.work);
+
+		/* Flush the background retirement and idle barriers */
+		flush_work(&engine->retire_work);
+		flush_delayed_work(&engine->wakeref.work);
+
+		/* Is the idle barrier still outstanding? */
+		active |= engine_active(engine);
 	}
 
 	return active;
-- 
2.20.1

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

Re: [Intel-gfx] [PATCH] drm/i915/gt: Check carefully for an idle engine in wait-for-idle

[Chris Wilson]

Quoting Chris Wilson (2020-04-23 07:29:05)
> intel_gt_wait_for_idle() tries to wait until all the outstanding requests
> are retired and the GPU is idle. As a side effect of retiring requests,
> we may submit more work to flush any pm barriers, and so the
> wait-for-idle tries to flush the background pm work and catch the new
> requests. However, if the work completed in the background before we
> were able to flush, it would queue the extra barrier request without us
> noticing -- and so we would return from wait-for-idle with one request
> remaining. (This breaks e.g. record_default_state where we need to wait
> until that barrier is retired, and it may slow suspend down by causing
> us to wait on the background retirement worker as opposed to immediately
> retiring the barrier.)
> 
> However, since we track if there has been a submission since the engine
> pm barrier, we can very quickly detect if the idle barrier is still
> outstanding.
> 
> Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/1763
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Matthew Auld <matthew.auld@intel.com>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> ---
>  drivers/gpu/drm/i915/gt/intel_gt_requests.c | 14 ++++++++++++--
>  1 file changed, 12 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
> index dec96a731a77..1781f176886a 100644
> --- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
> +++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
> @@ -26,6 +26,11 @@ static bool retire_requests(struct intel_timeline *tl)
>         return !i915_active_fence_isset(&tl->last_request);
>  }
>  
> +static bool engine_active(const struct intel_engine_cs *engine)
> +{
> +       return READ_ONCE(engine->wakeref_serial) != READ_ONCE(engine->serial);

This will be false when we have submitted but not yet retired. I was
better with checking the timeline.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH] drm/i915/gt: Check carefully for an idle engine in wait-for-idle

[Chris Wilson]

intel_gt_wait_for_idle() tries to wait until all the outstanding requests
are retired and the GPU is idle. As a side effect of retiring requests,
we may submit more work to flush any pm barriers, and so the
wait-for-idle tries to flush the background pm work and catch the new
requests. However, if the work completed in the background before we
were able to flush, it would queue the extra barrier request without us
noticing -- and so we would return from wait-for-idle with one request
remaining. (This breaks e.g. record_default_state where we need to wait
until that barrier is retired, and it may slow suspend down by causing
us to wait on the background retirement worker as opposed to immediately
retiring the barrier.)

However, since we track if there has been a submission since the engine
pm barrier, we can very quickly detect if the idle barrier is still
outstanding.

Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/1763
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_gt_requests.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index dec96a731a77..03e2438f4ba1 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -26,6 +26,11 @@ static bool retire_requests(struct intel_timeline *tl)
 	return !i915_active_fence_isset(&tl->last_request);
 }
 
+static bool engine_active(const struct intel_engine_cs *engine)
+{
+	return !list_empty(&engine->kernel_context->timeline->requests);
+}
+
 static bool flush_submission(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
@@ -37,8 +42,13 @@ static bool flush_submission(struct intel_gt *gt)
 
 	for_each_engine(engine, gt, id) {
 		intel_engine_flush_submission(engine);
-		active |= flush_work(&engine->retire_work);
-		active |= flush_delayed_work(&engine->wakeref.work);
+
+		/* Flush the background retirement and idle barriers */
+		flush_work(&engine->retire_work);
+		flush_delayed_work(&engine->wakeref.work);
+
+		/* Is the idle barrier still outstanding? */
+		active |= engine_active(engine);
 	}
 
 	return active;
-- 
2.20.1

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

[Intel-gfx] ✓ Fi.CI.BAT: success for drm/i915/gt: Check carefully for an idle engine in wait-for-idle

[Patchwork]

== Series Details ==

Series: drm/i915/gt: Check carefully for an idle engine in wait-for-idle
URL   : https://patchwork.freedesktop.org/series/76362/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_8350 -> Patchwork_17433
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/index.html

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

  Here are the changes found in Patchwork_17433 that come from known issues:

### IGT changes ###

#### Warnings ####

  * igt@i915_pm_rpm@module-reload:
    - fi-kbl-x1275:       [FAIL][1] ([i915#62]) -> [SKIP][2] ([fdo#109271])
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/fi-kbl-x1275/igt@i915_pm_rpm@module-reload.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/fi-kbl-x1275/igt@i915_pm_rpm@module-reload.html

  
  [fdo#109271]: https://bugs.freedesktop.org/show_bug.cgi?id=109271
  [i915#62]: https://gitlab.freedesktop.org/drm/intel/issues/62


Participating hosts (48 -> 42)
------------------------------

  Additional (1): fi-icl-dsi 
  Missing    (7): fi-cml-u2 fi-hsw-4200u fi-byt-squawks fi-bsw-cyan fi-kbl-7500u fi-byt-clapper fi-bdw-samus 


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

  * CI: CI-20190529 -> None
  * Linux: CI_DRM_8350 -> Patchwork_17433

  CI-20190529: 20190529
  CI_DRM_8350: 018bab6d1c4ac37bff9306384383fab59750e140 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_5606: 678afb3954bec6227c8762756a0ad6d9946d49b2 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_17433: f4f991b2acc57f880fd995d3c1ba6a732d55b600 @ git://anongit.freedesktop.org/gfx-ci/linux


== Linux commits ==

f4f991b2acc5 drm/i915/gt: Check carefully for an idle engine in wait-for-idle

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/index.html
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] ✓ Fi.CI.IGT: success for drm/i915/gt: Check carefully for an idle engine in wait-for-idle

[Patchwork]

== Series Details ==

Series: drm/i915/gt: Check carefully for an idle engine in wait-for-idle
URL   : https://patchwork.freedesktop.org/series/76362/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_8350_full -> Patchwork_17433_full
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  

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

  Here are the changes found in Patchwork_17433_full that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@kms_pipe_crc_basic@suspend-read-crc-pipe-a:
    - shard-kbl:          [PASS][1] -> [DMESG-WARN][2] ([i915#180]) +2 similar issues
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/shard-kbl1/igt@kms_pipe_crc_basic@suspend-read-crc-pipe-a.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/shard-kbl1/igt@kms_pipe_crc_basic@suspend-read-crc-pipe-a.html

  * igt@kms_plane@plane-panning-bottom-right-suspend-pipe-b-planes:
    - shard-apl:          [PASS][3] -> [DMESG-WARN][4] ([i915#180]) +1 similar issue
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/shard-apl1/igt@kms_plane@plane-panning-bottom-right-suspend-pipe-b-planes.html
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/shard-apl6/igt@kms_plane@plane-panning-bottom-right-suspend-pipe-b-planes.html

  * igt@kms_plane_alpha_blend@pipe-c-coverage-7efc:
    - shard-skl:          [PASS][5] -> [FAIL][6] ([fdo#108145] / [i915#265]) +1 similar issue
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/shard-skl6/igt@kms_plane_alpha_blend@pipe-c-coverage-7efc.html
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/shard-skl4/igt@kms_plane_alpha_blend@pipe-c-coverage-7efc.html

  * igt@kms_psr2_su@frontbuffer:
    - shard-iclb:         [PASS][7] -> [SKIP][8] ([fdo#109642] / [fdo#111068])
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/shard-iclb2/igt@kms_psr2_su@frontbuffer.html
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/shard-iclb4/igt@kms_psr2_su@frontbuffer.html

  * igt@kms_psr@psr2_primary_mmap_cpu:
    - shard-iclb:         [PASS][9] -> [SKIP][10] ([fdo#109441])
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/shard-iclb2/igt@kms_psr@psr2_primary_mmap_cpu.html
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/shard-iclb6/igt@kms_psr@psr2_primary_mmap_cpu.html

  
#### Possible fixes ####

  * igt@i915_pm_rc6_residency@rc6-idle:
    - shard-iclb:         [WARN][11] ([i915#1515]) -> [PASS][12]
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/shard-iclb6/igt@i915_pm_rc6_residency@rc6-idle.html
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/shard-iclb2/igt@i915_pm_rc6_residency@rc6-idle.html

  * igt@i915_pm_rpm@system-suspend:
    - shard-skl:          [INCOMPLETE][13] ([i915#151] / [i915#69]) -> [PASS][14]
   [13]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/shard-skl10/igt@i915_pm_rpm@system-suspend.html
   [14]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/shard-skl10/igt@i915_pm_rpm@system-suspend.html

  * {igt@kms_flip@flip-vs-expired-vblank-interruptible@a-edp1}:
    - shard-skl:          [FAIL][15] ([i915#46]) -> [PASS][16]
   [15]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/shard-skl1/igt@kms_flip@flip-vs-expired-vblank-interruptible@a-edp1.html
   [16]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/shard-skl1/igt@kms_flip@flip-vs-expired-vblank-interruptible@a-edp1.html

  * {igt@kms_flip@flip-vs-expired-vblank-interruptible@c-edp1}:
    - shard-skl:          [FAIL][17] ([i915#79]) -> [PASS][18]
   [17]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/shard-skl1/igt@kms_flip@flip-vs-expired-vblank-interruptible@c-edp1.html
   [18]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/shard-skl1/igt@kms_flip@flip-vs-expired-vblank-interruptible@c-edp1.html

  * {igt@kms_flip@flip-vs-suspend-interruptible@a-dp1}:
    - shard-kbl:          [DMESG-WARN][19] ([i915#180]) -> [PASS][20] +3 similar issues
   [19]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/shard-kbl6/igt@kms_flip@flip-vs-suspend-interruptible@a-dp1.html
   [20]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/shard-kbl6/igt@kms_flip@flip-vs-suspend-interruptible@a-dp1.html

  * igt@kms_psr@psr2_primary_page_flip:
    - shard-iclb:         [SKIP][21] ([fdo#109441]) -> [PASS][22] +1 similar issue
   [21]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/shard-iclb6/igt@kms_psr@psr2_primary_page_flip.html
   [22]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/shard-iclb2/igt@kms_psr@psr2_primary_page_flip.html

  * {igt@perf@polling-small-buf}:
    - shard-iclb:         [FAIL][23] ([i915#1722]) -> [PASS][24]
   [23]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/shard-iclb2/igt@perf@polling-small-buf.html
   [24]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/shard-iclb4/igt@perf@polling-small-buf.html

  
#### Warnings ####

  * igt@gem_workarounds@suspend-resume-context:
    - shard-kbl:          [INCOMPLETE][25] ([i915#155] / [i915#1687]) -> [INCOMPLETE][26] ([i915#155] / [i915#1687] / [i915#180])
   [25]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/shard-kbl7/igt@gem_workarounds@suspend-resume-context.html
   [26]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/shard-kbl2/igt@gem_workarounds@suspend-resume-context.html

  * igt@i915_pm_dc@dc3co-vpb-simulation:
    - shard-snb:          [SKIP][27] ([fdo#109271]) -> [INCOMPLETE][28] ([i915#82])
   [27]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/shard-snb5/igt@i915_pm_dc@dc3co-vpb-simulation.html
   [28]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/shard-snb5/igt@i915_pm_dc@dc3co-vpb-simulation.html

  * igt@i915_pm_dc@dc6-psr:
    - shard-tglb:         [FAIL][29] ([i915#454]) -> [SKIP][30] ([i915#468])
   [29]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/shard-tglb5/igt@i915_pm_dc@dc6-psr.html
   [30]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/shard-tglb2/igt@i915_pm_dc@dc6-psr.html

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

  [fdo#108145]: https://bugs.freedesktop.org/show_bug.cgi?id=108145
  [fdo#109271]: https://bugs.freedesktop.org/show_bug.cgi?id=109271
  [fdo#109441]: https://bugs.freedesktop.org/show_bug.cgi?id=109441
  [fdo#109642]: https://bugs.freedesktop.org/show_bug.cgi?id=109642
  [fdo#111068]: https://bugs.freedesktop.org/show_bug.cgi?id=111068
  [i915#151]: https://gitlab.freedesktop.org/drm/intel/issues/151
  [i915#1515]: https://gitlab.freedesktop.org/drm/intel/issues/1515
  [i915#155]: https://gitlab.freedesktop.org/drm/intel/issues/155
  [i915#1687]: https://gitlab.freedesktop.org/drm/intel/issues/1687
  [i915#1722]: https://gitlab.freedesktop.org/drm/intel/issues/1722
  [i915#180]: https://gitlab.freedesktop.org/drm/intel/issues/180
  [i915#265]: https://gitlab.freedesktop.org/drm/intel/issues/265
  [i915#454]: https://gitlab.freedesktop.org/drm/intel/issues/454
  [i915#46]: https://gitlab.freedesktop.org/drm/intel/issues/46
  [i915#468]: https://gitlab.freedesktop.org/drm/intel/issues/468
  [i915#69]: https://gitlab.freedesktop.org/drm/intel/issues/69
  [i915#79]: https://gitlab.freedesktop.org/drm/intel/issues/79
  [i915#82]: https://gitlab.freedesktop.org/drm/intel/issues/82


Participating hosts (10 -> 10)
------------------------------

  No changes in participating hosts


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

  * CI: CI-20190529 -> None
  * Linux: CI_DRM_8350 -> Patchwork_17433

  CI-20190529: 20190529
  CI_DRM_8350: 018bab6d1c4ac37bff9306384383fab59750e140 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_5606: 678afb3954bec6227c8762756a0ad6d9946d49b2 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_17433: f4f991b2acc57f880fd995d3c1ba6a732d55b600 @ git://anongit.freedesktop.org/gfx-ci/linux
  piglit_4509: fdc5a4ca11124ab8413c7988896eec4c97336694 @ git://anongit.freedesktop.org/piglit

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17433/index.html
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx