[PATCH] drm/i915/selftests: Check for hangs mid context execution tests

[PATCH] drm/i915/selftests: Check for hangs mid context execution tests

[Chris Wilson]

Use the live_test struct to record the reset count before and compare it
at the end of the test to assert that no mystery hang occurred during the
test.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../gpu/drm/i915/selftests/i915_gem_context.c | 22 ++++++++++++++-----
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 913c0f83f86a..ea165a644d79 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -531,10 +531,11 @@ static int igt_ctx_exec(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct drm_i915_gem_object *obj = NULL;
+	unsigned long ncontexts, ndwords, dw;
 	struct drm_file *file;
 	IGT_TIMEOUT(end_time);
 	LIST_HEAD(objects);
-	unsigned long ncontexts, ndwords, dw;
+	struct live_test t;
 	int err = -ENODEV;
 
 	/*
@@ -552,6 +553,10 @@ static int igt_ctx_exec(void *arg)
 
 	mutex_lock(&i915->drm.struct_mutex);
 
+	err = begin_live_test(&t, i915, __func__, "");
+	if (err)
+		goto out_unlock;
+
 	ncontexts = 0;
 	ndwords = 0;
 	dw = 0;
@@ -616,7 +621,7 @@ static int igt_ctx_exec(void *arg)
 	}
 
 out_unlock:
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (end_live_test(&t))
 		err = -EIO;
 	mutex_unlock(&i915->drm.struct_mutex);
 
@@ -628,13 +633,14 @@ static int igt_ctx_readonly(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct drm_i915_gem_object *obj = NULL;
+	struct i915_gem_context *ctx;
+	struct i915_hw_ppgtt *ppgtt;
+	unsigned long ndwords, dw;
 	struct drm_file *file;
 	I915_RND_STATE(prng);
 	IGT_TIMEOUT(end_time);
 	LIST_HEAD(objects);
-	struct i915_gem_context *ctx;
-	struct i915_hw_ppgtt *ppgtt;
-	unsigned long ndwords, dw;
+	struct live_test t;
 	int err = -ENODEV;
 
 	/*
@@ -649,6 +655,10 @@ static int igt_ctx_readonly(void *arg)
 
 	mutex_lock(&i915->drm.struct_mutex);
 
+	err = begin_live_test(&t, i915, __func__, "");
+	if (err)
+		goto out_unlock;
+
 	ctx = i915_gem_create_context(i915, file->driver_priv);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
@@ -721,7 +731,7 @@ static int igt_ctx_readonly(void *arg)
 	}
 
 out_unlock:
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (end_live_test(&t))
 		err = -EIO;
 	mutex_unlock(&i915->drm.struct_mutex);
 
-- 
2.19.1

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

✓ Fi.CI.BAT: success for drm/i915/selftests: Check for hangs mid context execution tests

[Patchwork]

== Series Details ==

Series: drm/i915/selftests: Check for hangs mid context execution tests
URL   : https://patchwork.freedesktop.org/series/50801/
State : success

== Summary ==

= CI Bug Log - changes from CI_DRM_4961 -> Patchwork_10413 =

== Summary - SUCCESS ==

  No regressions found.

  External URL: https://patchwork.freedesktop.org/api/1.0/series/50801/revisions/1/mbox/

== Known issues ==

  Here are the changes found in Patchwork_10413 that come from known issues:

  === IGT changes ===

    ==== Issues hit ====

    igt@kms_pipe_crc_basic@read-crc-pipe-b-frame-sequence:
      fi-ilk-650:         PASS -> DMESG-WARN (fdo#106387) +1

    
    ==== Possible fixes ====

    igt@gem_exec_suspend@basic-s3:
      fi-cfl-8109u:       DMESG-WARN (fdo#107345) -> PASS +1

    igt@kms_chamelium@dp-crc-fast:
      fi-kbl-7500u:       FAIL (fdo#103841) -> PASS +2

    igt@kms_chamelium@dp-hpd-fast:
      fi-skl-6700k2:      FAIL (fdo#103841) -> SKIP +4

    igt@kms_chamelium@hdmi-crc-fast:
      fi-skl-6700k2:      FAIL (fdo#103841) -> PASS +3

    igt@kms_chamelium@vga-hpd-fast:
      fi-kbl-7500u:       FAIL (fdo#103841) -> SKIP +4

    igt@kms_pipe_crc_basic@hang-read-crc-pipe-a:
      fi-byt-clapper:     FAIL (fdo#103191, fdo#107362) -> PASS

    
    ==== Warnings ====

    igt@kms_chamelium@common-hpd-after-suspend:
      fi-kbl-7500u:       FAIL (fdo#103841) -> DMESG-WARN (fdo#102505, fdo#105079, fdo#105602)

    
  fdo#102505 https://bugs.freedesktop.org/show_bug.cgi?id=102505
  fdo#103191 https://bugs.freedesktop.org/show_bug.cgi?id=103191
  fdo#103841 https://bugs.freedesktop.org/show_bug.cgi?id=103841
  fdo#105079 https://bugs.freedesktop.org/show_bug.cgi?id=105079
  fdo#105602 https://bugs.freedesktop.org/show_bug.cgi?id=105602
  fdo#106387 https://bugs.freedesktop.org/show_bug.cgi?id=106387
  fdo#107345 https://bugs.freedesktop.org/show_bug.cgi?id=107345
  fdo#107362 https://bugs.freedesktop.org/show_bug.cgi?id=107362


== Participating hosts (48 -> 41) ==

  Missing    (7): fi-ilk-m540 fi-hsw-4200u fi-byt-squawks fi-icl-u2 fi-bsw-cyan fi-ctg-p8600 fi-pnv-d510 


== Build changes ==

    * Linux: CI_DRM_4961 -> Patchwork_10413

  CI_DRM_4961: 1b9d983587107509e70d14509fcd304b19ae0ce0 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_4673: 54cb1aeb4e50dea9f3abae632e317875d147c4ab @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_10413: 2f79f218c3ba344e17eb939a94f45b144070967d @ git://anongit.freedesktop.org/gfx-ci/linux


== Linux commits ==

2f79f218c3ba drm/i915/selftests: Check for hangs mid context execution tests

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_10413/issues.html
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✓ Fi.CI.IGT: success for drm/i915/selftests: Check for hangs mid context execution tests

[Patchwork]

== Series Details ==

Series: drm/i915/selftests: Check for hangs mid context execution tests
URL   : https://patchwork.freedesktop.org/series/50801/
State : success

== Summary ==

= CI Bug Log - changes from CI_DRM_4961_full -> Patchwork_10413_full =

== Summary - WARNING ==

  Minor unknown changes coming with Patchwork_10413_full need to be verified
  manually.
  
  If you think the reported changes have nothing to do with the changes
  introduced in Patchwork_10413_full, please notify your bug team to allow them
  to document this new failure mode, which will reduce false positives in CI.

  

== Possible new issues ==

  Here are the unknown changes that may have been introduced in Patchwork_10413_full:

  === IGT changes ===

    ==== Warnings ====

    igt@kms_frontbuffer_tracking@fbc-1p-offscren-pri-shrfb-draw-render:
      shard-snb:          SKIP -> PASS

    igt@perf_pmu@rc6:
      shard-kbl:          PASS -> SKIP

    
== Known issues ==

  Here are the changes found in Patchwork_10413_full that come from known issues:

  === IGT changes ===

    ==== Issues hit ====

    igt@gem_exec_schedule@pi-ringfull-vebox:
      shard-skl:          NOTRUN -> FAIL (fdo#103158)

    igt@gem_ppgtt@blt-vs-render-ctxn:
      shard-skl:          NOTRUN -> TIMEOUT (fdo#108039)

    igt@kms_busy@extended-modeset-hang-newfb-render-a:
      shard-skl:          NOTRUN -> DMESG-WARN (fdo#107956)

    igt@kms_frontbuffer_tracking@fbc-1p-offscren-pri-shrfb-draw-render:
      shard-glk:          PASS -> FAIL (fdo#103167)

    igt@kms_panel_fitting@legacy:
      shard-skl:          NOTRUN -> FAIL (fdo#105456)

    {igt@kms_plane_alpha_blend@pipe-a-alpha-transparant-fb}:
      shard-skl:          NOTRUN -> FAIL (fdo#108145) +1

    {igt@kms_plane_alpha_blend@pipe-b-coverage-7efc}:
      shard-skl:          NOTRUN -> FAIL (fdo#108146)

    igt@kms_setmode@basic:
      shard-hsw:          PASS -> FAIL (fdo#99912)

    igt@pm_rpm@debugfs-forcewake-user:
      shard-skl:          PASS -> INCOMPLETE (fdo#107807)

    igt@pm_rpm@gem-idle:
      shard-skl:          NOTRUN -> INCOMPLETE (fdo#107807)

    
    ==== Possible fixes ====

    igt@drv_suspend@debugfs-reader:
      shard-skl:          INCOMPLETE (fdo#104108, fdo#107773) -> PASS

    igt@kms_busy@extended-modeset-hang-newfb-render-a:
      shard-snb:          DMESG-WARN (fdo#107956) -> PASS

    igt@kms_frontbuffer_tracking@fbc-1p-primscrn-spr-indfb-move:
      shard-apl:          FAIL (fdo#103167) -> PASS

    igt@kms_plane_multiple@atomic-pipe-b-tiling-y:
      shard-glk:          FAIL (fdo#103166) -> PASS

    igt@kms_setmode@basic:
      shard-kbl:          FAIL (fdo#99912) -> PASS

    igt@pm_rpm@gem-mmap-cpu:
      shard-skl:          INCOMPLETE (fdo#107807) -> PASS

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

  fdo#103158 https://bugs.freedesktop.org/show_bug.cgi?id=103158
  fdo#103166 https://bugs.freedesktop.org/show_bug.cgi?id=103166
  fdo#103167 https://bugs.freedesktop.org/show_bug.cgi?id=103167
  fdo#104108 https://bugs.freedesktop.org/show_bug.cgi?id=104108
  fdo#105456 https://bugs.freedesktop.org/show_bug.cgi?id=105456
  fdo#107773 https://bugs.freedesktop.org/show_bug.cgi?id=107773
  fdo#107807 https://bugs.freedesktop.org/show_bug.cgi?id=107807
  fdo#107956 https://bugs.freedesktop.org/show_bug.cgi?id=107956
  fdo#108039 https://bugs.freedesktop.org/show_bug.cgi?id=108039
  fdo#108145 https://bugs.freedesktop.org/show_bug.cgi?id=108145
  fdo#108146 https://bugs.freedesktop.org/show_bug.cgi?id=108146
  fdo#99912 https://bugs.freedesktop.org/show_bug.cgi?id=99912


== Participating hosts (6 -> 6) ==

  No changes in participating hosts


== Build changes ==

    * Linux: CI_DRM_4961 -> Patchwork_10413

  CI_DRM_4961: 1b9d983587107509e70d14509fcd304b19ae0ce0 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_4673: 54cb1aeb4e50dea9f3abae632e317875d147c4ab @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_10413: 2f79f218c3ba344e17eb939a94f45b144070967d @ 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_10413/shards.html
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH v2] drm/i915/selftests: Check for hangs mid context execution tests

[Chris Wilson]

Use the live_test struct to record the reset count before and compare it
at the end of the test to assert that no mystery hang occurred during the
test.

v2: Check per-engine resets as well

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 .../gpu/drm/i915/selftests/i915_gem_context.c | 51 +++++++++++++++----
 1 file changed, 41 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 913c0f83f86a..1be3b67a7c48 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -39,7 +39,8 @@ struct live_test {
 	const char *func;
 	const char *name;
 
-	unsigned int reset_count;
+	unsigned int reset_global;
+	unsigned int reset_engine[I915_NUM_ENGINES];
 };
 
 static int begin_live_test(struct live_test *t,
@@ -47,6 +48,8 @@ static int begin_live_test(struct live_test *t,
 			   const char *func,
 			   const char *name)
 {
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int err;
 
 	t->i915 = i915;
@@ -63,7 +66,11 @@ static int begin_live_test(struct live_test *t,
 	}
 
 	i915->gpu_error.missed_irq_rings = 0;
-	t->reset_count = i915_reset_count(&i915->gpu_error);
+	t->reset_global = i915_reset_count(&i915->gpu_error);
+
+	for_each_engine(engine, i915, id)
+		t->reset_engine[id] =
+			i915_reset_engine_count(&i915->gpu_error, engine);
 
 	return 0;
 }
@@ -71,14 +78,28 @@ static int begin_live_test(struct live_test *t,
 static int end_live_test(struct live_test *t)
 {
 	struct drm_i915_private *i915 = t->i915;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
 	if (igt_flush_test(i915, I915_WAIT_LOCKED))
 		return -EIO;
 
-	if (t->reset_count != i915_reset_count(&i915->gpu_error)) {
+	if (t->reset_global != i915_reset_count(&i915->gpu_error)) {
 		pr_err("%s(%s): GPU was reset %d times!\n",
 		       t->func, t->name,
-		       i915_reset_count(&i915->gpu_error) - t->reset_count);
+		       i915_reset_count(&i915->gpu_error) - t->reset_global);
+		return -EIO;
+	}
+
+	for_each_engine(engine, i915, id) {
+		if (t->reset_engine[id] ==
+		    i915_reset_engine_count(&i915->gpu_error, engine))
+			continue;
+
+		pr_err("%s(%s): engine '%s' was reset %d times!\n",
+		       t->func, t->name, engine->name,
+		       i915_reset_engine_count(&i915->gpu_error, engine) -
+		       t->reset_engine[id]);
 		return -EIO;
 	}
 
@@ -531,10 +552,11 @@ static int igt_ctx_exec(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct drm_i915_gem_object *obj = NULL;
+	unsigned long ncontexts, ndwords, dw;
 	struct drm_file *file;
 	IGT_TIMEOUT(end_time);
 	LIST_HEAD(objects);
-	unsigned long ncontexts, ndwords, dw;
+	struct live_test t;
 	int err = -ENODEV;
 
 	/*
@@ -552,6 +574,10 @@ static int igt_ctx_exec(void *arg)
 
 	mutex_lock(&i915->drm.struct_mutex);
 
+	err = begin_live_test(&t, i915, __func__, "");
+	if (err)
+		goto out_unlock;
+
 	ncontexts = 0;
 	ndwords = 0;
 	dw = 0;
@@ -616,7 +642,7 @@ static int igt_ctx_exec(void *arg)
 	}
 
 out_unlock:
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (end_live_test(&t))
 		err = -EIO;
 	mutex_unlock(&i915->drm.struct_mutex);
 
@@ -628,13 +654,14 @@ static int igt_ctx_readonly(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct drm_i915_gem_object *obj = NULL;
+	struct i915_gem_context *ctx;
+	struct i915_hw_ppgtt *ppgtt;
+	unsigned long ndwords, dw;
 	struct drm_file *file;
 	I915_RND_STATE(prng);
 	IGT_TIMEOUT(end_time);
 	LIST_HEAD(objects);
-	struct i915_gem_context *ctx;
-	struct i915_hw_ppgtt *ppgtt;
-	unsigned long ndwords, dw;
+	struct live_test t;
 	int err = -ENODEV;
 
 	/*
@@ -649,6 +676,10 @@ static int igt_ctx_readonly(void *arg)
 
 	mutex_lock(&i915->drm.struct_mutex);
 
+	err = begin_live_test(&t, i915, __func__, "");
+	if (err)
+		goto out_unlock;
+
 	ctx = i915_gem_create_context(i915, file->driver_priv);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
@@ -721,7 +752,7 @@ static int igt_ctx_readonly(void *arg)
 	}
 
 out_unlock:
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (end_live_test(&t))
 		err = -EIO;
 	mutex_unlock(&i915->drm.struct_mutex);
 
-- 
2.19.1

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

✗ Fi.CI.BAT: failure for drm/i915/selftests: Check for hangs mid context execution tests (rev2)

[Patchwork]

== Series Details ==

Series: drm/i915/selftests: Check for hangs mid context execution tests (rev2)
URL   : https://patchwork.freedesktop.org/series/50801/
State : failure

== Summary ==

= CI Bug Log - changes from CI_DRM_4976 -> Patchwork_10437 =

== Summary - FAILURE ==

  Serious unknown changes coming with Patchwork_10437 absolutely need to be
  verified manually.
  
  If you think the reported changes have nothing to do with the changes
  introduced in Patchwork_10437, please notify your bug team to allow them
  to document this new failure mode, which will reduce false positives in CI.

  External URL: https://patchwork.freedesktop.org/api/1.0/series/50801/revisions/2/mbox/

== Possible new issues ==

  Here are the unknown changes that may have been introduced in Patchwork_10437:

  === IGT changes ===

    ==== Possible regressions ====

    igt@drv_selftest@live_contexts:
      fi-icl-u2:          PASS -> DMESG-FAIL
      fi-icl-u:           PASS -> DMESG-FAIL

    
== Known issues ==

  Here are the changes found in Patchwork_10437 that come from known issues:

  === IGT changes ===

    ==== Issues hit ====

    igt@debugfs_test@read_all_entries:
      fi-icl-u:           PASS -> DMESG-WARN (fdo#107724) +1

    igt@drv_selftest@live_gem:
      {fi-apl-guc}:       NOTRUN -> INCOMPLETE (fdo#106693)

    igt@kms_frontbuffer_tracking@basic:
      fi-hsw-peppy:       PASS -> DMESG-WARN (fdo#102614)

    igt@kms_pipe_crc_basic@suspend-read-crc-pipe-b:
      fi-blb-e6850:       PASS -> INCOMPLETE (fdo#107718)

    
    ==== Possible fixes ====

    igt@kms_flip@basic-flip-vs-modeset:
      fi-glk-j4005:       DMESG-WARN (fdo#106097) -> PASS

    igt@kms_frontbuffer_tracking@basic:
      fi-byt-clapper:     FAIL (fdo#103167) -> PASS

    igt@kms_pipe_crc_basic@read-crc-pipe-c:
      fi-skl-6700k2:      FAIL (fdo#107362, fdo#103191) -> PASS

    igt@pm_rpm@module-reload:
      fi-skl-6600u:       INCOMPLETE (fdo#107807) -> PASS
      fi-glk-j4005:       FAIL (fdo#108338) -> PASS

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

  fdo#102614 https://bugs.freedesktop.org/show_bug.cgi?id=102614
  fdo#103167 https://bugs.freedesktop.org/show_bug.cgi?id=103167
  fdo#103191 https://bugs.freedesktop.org/show_bug.cgi?id=103191
  fdo#106097 https://bugs.freedesktop.org/show_bug.cgi?id=106097
  fdo#106693 https://bugs.freedesktop.org/show_bug.cgi?id=106693
  fdo#107362 https://bugs.freedesktop.org/show_bug.cgi?id=107362
  fdo#107718 https://bugs.freedesktop.org/show_bug.cgi?id=107718
  fdo#107724 https://bugs.freedesktop.org/show_bug.cgi?id=107724
  fdo#107807 https://bugs.freedesktop.org/show_bug.cgi?id=107807
  fdo#108338 https://bugs.freedesktop.org/show_bug.cgi?id=108338


== Participating hosts (45 -> 42) ==

  Additional (1): fi-apl-guc 
  Missing    (4): fi-ctg-p8600 fi-ilk-m540 fi-byt-squawks fi-bsw-cyan 


== Build changes ==

    * Linux: CI_DRM_4976 -> Patchwork_10437

  CI_DRM_4976: dec9886eff39d38332bb5ea438b9b053d6b2177c @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_4674: 93871c6fb3c25e5d350c9faf36ded917174214de @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_10437: c7def2543d8b7ead4a76b3ea8d3a2b6dc6a770c4 @ git://anongit.freedesktop.org/gfx-ci/linux


== Linux commits ==

c7def2543d8b drm/i915/selftests: Check for hangs mid context execution tests

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_10437/issues.html
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH v2] drm/i915/selftests: Check for hangs mid context execution tests

[Tvrtko Ursulin]

On 12/10/2018 13:24, Chris Wilson wrote:
> Use the live_test struct to record the reset count before and compare it
> at the end of the test to assert that no mystery hang occurred during the
> test.
> 
> v2: Check per-engine resets as well
> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
> ---
>   .../gpu/drm/i915/selftests/i915_gem_context.c | 51 +++++++++++++++----
>   1 file changed, 41 insertions(+), 10 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
> index 913c0f83f86a..1be3b67a7c48 100644
> --- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
> @@ -39,7 +39,8 @@ struct live_test {
>   	const char *func;
>   	const char *name;
>   
> -	unsigned int reset_count;
> +	unsigned int reset_global;
> +	unsigned int reset_engine[I915_NUM_ENGINES];
>   };
>   
>   static int begin_live_test(struct live_test *t,
> @@ -47,6 +48,8 @@ static int begin_live_test(struct live_test *t,
>   			   const char *func,
>   			   const char *name)
>   {
> +	struct intel_engine_cs *engine;
> +	enum intel_engine_id id;
>   	int err;
>   
>   	t->i915 = i915;
> @@ -63,7 +66,11 @@ static int begin_live_test(struct live_test *t,
>   	}
>   
>   	i915->gpu_error.missed_irq_rings = 0;
> -	t->reset_count = i915_reset_count(&i915->gpu_error);
> +	t->reset_global = i915_reset_count(&i915->gpu_error);
> +
> +	for_each_engine(engine, i915, id)
> +		t->reset_engine[id] =
> +			i915_reset_engine_count(&i915->gpu_error, engine);
>   
>   	return 0;
>   }
> @@ -71,14 +78,28 @@ static int begin_live_test(struct live_test *t,
>   static int end_live_test(struct live_test *t)
>   {
>   	struct drm_i915_private *i915 = t->i915;
> +	struct intel_engine_cs *engine;
> +	enum intel_engine_id id;
>   
>   	if (igt_flush_test(i915, I915_WAIT_LOCKED))
>   		return -EIO;
>   
> -	if (t->reset_count != i915_reset_count(&i915->gpu_error)) {
> +	if (t->reset_global != i915_reset_count(&i915->gpu_error)) {
>   		pr_err("%s(%s): GPU was reset %d times!\n",
>   		       t->func, t->name,
> -		       i915_reset_count(&i915->gpu_error) - t->reset_count);
> +		       i915_reset_count(&i915->gpu_error) - t->reset_global);
> +		return -EIO;
> +	}
> +
> +	for_each_engine(engine, i915, id) {
> +		if (t->reset_engine[id] ==
> +		    i915_reset_engine_count(&i915->gpu_error, engine))
> +			continue;
> +
> +		pr_err("%s(%s): engine '%s' was reset %d times!\n",
> +		       t->func, t->name, engine->name,
> +		       i915_reset_engine_count(&i915->gpu_error, engine) -
> +		       t->reset_engine[id]);
>   		return -EIO;
>   	}
>   
> @@ -531,10 +552,11 @@ static int igt_ctx_exec(void *arg)
>   {
>   	struct drm_i915_private *i915 = arg;
>   	struct drm_i915_gem_object *obj = NULL;
> +	unsigned long ncontexts, ndwords, dw;
>   	struct drm_file *file;
>   	IGT_TIMEOUT(end_time);
>   	LIST_HEAD(objects);
> -	unsigned long ncontexts, ndwords, dw;
> +	struct live_test t;
>   	int err = -ENODEV;
>   
>   	/*
> @@ -552,6 +574,10 @@ static int igt_ctx_exec(void *arg)
>   
>   	mutex_lock(&i915->drm.struct_mutex);
>   
> +	err = begin_live_test(&t, i915, __func__, "");
> +	if (err)
> +		goto out_unlock;
> +
>   	ncontexts = 0;
>   	ndwords = 0;
>   	dw = 0;
> @@ -616,7 +642,7 @@ static int igt_ctx_exec(void *arg)
>   	}
>   
>   out_unlock:
> -	if (igt_flush_test(i915, I915_WAIT_LOCKED))
> +	if (end_live_test(&t))
>   		err = -EIO;
>   	mutex_unlock(&i915->drm.struct_mutex);
>   
> @@ -628,13 +654,14 @@ static int igt_ctx_readonly(void *arg)
>   {
>   	struct drm_i915_private *i915 = arg;
>   	struct drm_i915_gem_object *obj = NULL;
> +	struct i915_gem_context *ctx;
> +	struct i915_hw_ppgtt *ppgtt;
> +	unsigned long ndwords, dw;
>   	struct drm_file *file;
>   	I915_RND_STATE(prng);
>   	IGT_TIMEOUT(end_time);
>   	LIST_HEAD(objects);
> -	struct i915_gem_context *ctx;
> -	struct i915_hw_ppgtt *ppgtt;
> -	unsigned long ndwords, dw;
> +	struct live_test t;
>   	int err = -ENODEV;
>   
>   	/*
> @@ -649,6 +676,10 @@ static int igt_ctx_readonly(void *arg)
>   
>   	mutex_lock(&i915->drm.struct_mutex);
>   
> +	err = begin_live_test(&t, i915, __func__, "");
> +	if (err)
> +		goto out_unlock;
> +
>   	ctx = i915_gem_create_context(i915, file->driver_priv);
>   	if (IS_ERR(ctx)) {
>   		err = PTR_ERR(ctx);
> @@ -721,7 +752,7 @@ static int igt_ctx_readonly(void *arg)
>   	}
>   
>   out_unlock:
> -	if (igt_flush_test(i915, I915_WAIT_LOCKED))
> +	if (end_live_test(&t))
>   		err = -EIO;
>   	mutex_unlock(&i915->drm.struct_mutex);
>   
> 

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Regards,

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

Re: [PATCH v2] drm/i915/selftests: Check for hangs mid context execution tests

[Chris Wilson]

Quoting Tvrtko Ursulin (2018-10-26 12:14:31)
> 
> On 12/10/2018 13:24, Chris Wilson wrote:
> > Use the live_test struct to record the reset count before and compare it
> > at the end of the test to assert that no mystery hang occurred during the
> > test.
> > 
> > v2: Check per-engine resets as well
> > 
> > Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> > Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
> > ---
> >   .../gpu/drm/i915/selftests/i915_gem_context.c | 51 +++++++++++++++----
> >   1 file changed, 41 insertions(+), 10 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
> > index 913c0f83f86a..1be3b67a7c48 100644
> > --- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
> > +++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
> > @@ -39,7 +39,8 @@ struct live_test {
> >       const char *func;
> >       const char *name;
> >   
> > -     unsigned int reset_count;
> > +     unsigned int reset_global;
> > +     unsigned int reset_engine[I915_NUM_ENGINES];
> >   };
> >   
> >   static int begin_live_test(struct live_test *t,
> > @@ -47,6 +48,8 @@ static int begin_live_test(struct live_test *t,
> >                          const char *func,
> >                          const char *name)
> >   {
> > +     struct intel_engine_cs *engine;
> > +     enum intel_engine_id id;
> >       int err;
> >   
> >       t->i915 = i915;
> > @@ -63,7 +66,11 @@ static int begin_live_test(struct live_test *t,
> >       }
> >   
> >       i915->gpu_error.missed_irq_rings = 0;
> > -     t->reset_count = i915_reset_count(&i915->gpu_error);
> > +     t->reset_global = i915_reset_count(&i915->gpu_error);
> > +
> > +     for_each_engine(engine, i915, id)
> > +             t->reset_engine[id] =
> > +                     i915_reset_engine_count(&i915->gpu_error, engine);
> >   
> >       return 0;
> >   }
> > @@ -71,14 +78,28 @@ static int begin_live_test(struct live_test *t,
> >   static int end_live_test(struct live_test *t)
> >   {
> >       struct drm_i915_private *i915 = t->i915;
> > +     struct intel_engine_cs *engine;
> > +     enum intel_engine_id id;
> >   
> >       if (igt_flush_test(i915, I915_WAIT_LOCKED))
> >               return -EIO;
> >   
> > -     if (t->reset_count != i915_reset_count(&i915->gpu_error)) {
> > +     if (t->reset_global != i915_reset_count(&i915->gpu_error)) {
> >               pr_err("%s(%s): GPU was reset %d times!\n",
> >                      t->func, t->name,
> > -                    i915_reset_count(&i915->gpu_error) - t->reset_count);
> > +                    i915_reset_count(&i915->gpu_error) - t->reset_global);
> > +             return -EIO;
> > +     }
> > +
> > +     for_each_engine(engine, i915, id) {
> > +             if (t->reset_engine[id] ==
> > +                 i915_reset_engine_count(&i915->gpu_error, engine))
> > +                     continue;
> > +
> > +             pr_err("%s(%s): engine '%s' was reset %d times!\n",
> > +                    t->func, t->name, engine->name,
> > +                    i915_reset_engine_count(&i915->gpu_error, engine) -
> > +                    t->reset_engine[id]);
> >               return -EIO;
> >       }
> >   
> > @@ -531,10 +552,11 @@ static int igt_ctx_exec(void *arg)
> >   {
> >       struct drm_i915_private *i915 = arg;
> >       struct drm_i915_gem_object *obj = NULL;
> > +     unsigned long ncontexts, ndwords, dw;
> >       struct drm_file *file;
> >       IGT_TIMEOUT(end_time);
> >       LIST_HEAD(objects);
> > -     unsigned long ncontexts, ndwords, dw;
> > +     struct live_test t;
> >       int err = -ENODEV;
> >   
> >       /*
> > @@ -552,6 +574,10 @@ static int igt_ctx_exec(void *arg)
> >   
> >       mutex_lock(&i915->drm.struct_mutex);
> >   
> > +     err = begin_live_test(&t, i915, __func__, "");
> > +     if (err)
> > +             goto out_unlock;
> > +
> >       ncontexts = 0;
> >       ndwords = 0;
> >       dw = 0;
> > @@ -616,7 +642,7 @@ static int igt_ctx_exec(void *arg)
> >       }
> >   
> >   out_unlock:
> > -     if (igt_flush_test(i915, I915_WAIT_LOCKED))
> > +     if (end_live_test(&t))
> >               err = -EIO;
> >       mutex_unlock(&i915->drm.struct_mutex);
> >   
> > @@ -628,13 +654,14 @@ static int igt_ctx_readonly(void *arg)
> >   {
> >       struct drm_i915_private *i915 = arg;
> >       struct drm_i915_gem_object *obj = NULL;
> > +     struct i915_gem_context *ctx;
> > +     struct i915_hw_ppgtt *ppgtt;
> > +     unsigned long ndwords, dw;
> >       struct drm_file *file;
> >       I915_RND_STATE(prng);
> >       IGT_TIMEOUT(end_time);
> >       LIST_HEAD(objects);
> > -     struct i915_gem_context *ctx;
> > -     struct i915_hw_ppgtt *ppgtt;
> > -     unsigned long ndwords, dw;
> > +     struct live_test t;
> >       int err = -ENODEV;
> >   
> >       /*
> > @@ -649,6 +676,10 @@ static int igt_ctx_readonly(void *arg)
> >   
> >       mutex_lock(&i915->drm.struct_mutex);
> >   
> > +     err = begin_live_test(&t, i915, __func__, "");
> > +     if (err)
> > +             goto out_unlock;
> > +
> >       ctx = i915_gem_create_context(i915, file->driver_priv);
> >       if (IS_ERR(ctx)) {
> >               err = PTR_ERR(ctx);
> > @@ -721,7 +752,7 @@ static int igt_ctx_readonly(void *arg)
> >       }
> >   
> >   out_unlock:
> > -     if (igt_flush_test(i915, I915_WAIT_LOCKED))
> > +     if (end_live_test(&t))
> >               err = -EIO;
> >       mutex_unlock(&i915->drm.struct_mutex);
> >   
> > 
> 
> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Ta, with any luck this will cause a deluge of bug reports about icl
being broken.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx