[Intel-gfx] [PATCH] drm/i915/perf: Fix OA context id overlap with idle context id

[Intel-gfx] [PATCH] drm/i915/perf: Fix OA context id overlap with idle context id

[Umesh Nerlige Ramappa]

Engine context pinned in perf OA was set to same context id as
the idle context. Set the context id to an unused value.

Clear the sw context id field in lrc descriptor before ORing with
ce->tag (Chris)

Fixes: https://gitlab.freedesktop.org/drm/intel/issues/756
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 2 +-
 drivers/gpu/drm/i915/i915_perf.c    | 9 +++++++--
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index a13a8c4b65ab..cf6c43bd540a 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1211,12 +1211,12 @@ __execlists_schedule_in(struct i915_request *rq)
 	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
 		execlists_check_context(ce, engine);
 
+	ce->lrc_desc &= ~GENMASK_ULL(47, 37);
 	if (ce->tag) {
 		/* Use a fixed tag for OA and friends */
 		ce->lrc_desc |= (u64)ce->tag << 32;
 	} else {
 		/* We don't need a strict matching tag, just different values */
-		ce->lrc_desc &= ~GENMASK_ULL(47, 37);
 		ce->lrc_desc |=
 			(u64)(++engine->context_tag % NUM_CONTEXT_TAG) <<
 			GEN11_SW_CTX_ID_SHIFT;
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 3c4647054557..5bd878c64504 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1323,7 +1323,12 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 	case 12: {
 		stream->specific_ctx_id_mask =
 			((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
-		stream->specific_ctx_id = stream->specific_ctx_id_mask;
+		/* Pick an unused context id
+		 * 0 - (NUM_CONTEXT_TAG - 1) are used by other contexts
+		 * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context
+		 */
+		stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
+		BUILD_BUG_ON((GEN12_MAX_CONTEXT_HW_ID - 1) < NUM_CONTEXT_TAG);
 		break;
 	}
 
@@ -1331,7 +1336,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 		MISSING_CASE(INTEL_GEN(ce->engine->i915));
 	}
 
-	ce->tag = stream->specific_ctx_id_mask;
+	ce->tag = stream->specific_ctx_id;
 
 	DRM_DEBUG_DRIVER("filtering on ctx_id=0x%x ctx_id_mask=0x%x\n",
 			 stream->specific_ctx_id,
-- 
2.20.1

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

[Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for drm/i915/perf: Fix OA context id overlap with idle context id

[Patchwork]

== Series Details ==

Series: drm/i915/perf: Fix OA context id overlap with idle context id
URL   : https://patchwork.freedesktop.org/series/72505/
State : warning

== Summary ==

$ dim checkpatch origin/drm-tip
481e30922e7f drm/i915/perf: Fix OA context id overlap with idle context id
-:46: WARNING:LONG_LINE: line over 100 characters
#46: FILE: drivers/gpu/drm/i915/i915_perf.c:1330:
+		stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);

total: 0 errors, 1 warnings, 0 checks, 34 lines checked

_______________________________________________
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/perf: Fix OA context id overlap with idle context id

[Patchwork]

== Series Details ==

Series: drm/i915/perf: Fix OA context id overlap with idle context id
URL   : https://patchwork.freedesktop.org/series/72505/
State : failure

== Summary ==

CI Bug Log - changes from CI_DRM_7806 -> Patchwork_16247
====================================================

Summary
-------

  **FAILURE**

  Serious unknown changes coming with Patchwork_16247 absolutely need to be
  verified manually.
  
  If you think the reported changes have nothing to do with the changes
  introduced in Patchwork_16247, 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_16247/index.html

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

  Here are the unknown changes that may have been introduced in Patchwork_16247:

### IGT changes ###

#### Possible regressions ####

  * igt@gem_exec_suspend@basic-s0:
    - fi-hsw-4770:        [PASS][1] -> [INCOMPLETE][2]
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7806/fi-hsw-4770/igt@gem_exec_suspend@basic-s0.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16247/fi-hsw-4770/igt@gem_exec_suspend@basic-s0.html

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

  Here are the changes found in Patchwork_16247 that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@gem_ctx_param@basic:
    - fi-tgl-y:           [PASS][3] -> [DMESG-WARN][4] ([CI#94] / [i915#402]) +2 similar issues
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7806/fi-tgl-y/igt@gem_ctx_param@basic.html
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16247/fi-tgl-y/igt@gem_ctx_param@basic.html

  * igt@gem_exec_parallel@fds:
    - fi-byt-n2820:       [PASS][5] -> [TIMEOUT][6] ([fdo#112271])
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7806/fi-byt-n2820/igt@gem_exec_parallel@fds.html
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16247/fi-byt-n2820/igt@gem_exec_parallel@fds.html

  * igt@i915_selftest@live_gem_contexts:
    - fi-byt-n2820:       [PASS][7] -> [DMESG-FAIL][8] ([i915#722])
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7806/fi-byt-n2820/igt@i915_selftest@live_gem_contexts.html
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16247/fi-byt-n2820/igt@i915_selftest@live_gem_contexts.html

  
#### Possible fixes ####

  * igt@i915_selftest@live_blt:
    - fi-bsw-nick:        [DMESG-FAIL][9] ([i915#723]) -> [PASS][10]
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7806/fi-bsw-nick/igt@i915_selftest@live_blt.html
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16247/fi-bsw-nick/igt@i915_selftest@live_blt.html
    - fi-hsw-4770r:       [DMESG-FAIL][11] ([i915#563]) -> [PASS][12]
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7806/fi-hsw-4770r/igt@i915_selftest@live_blt.html
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16247/fi-hsw-4770r/igt@i915_selftest@live_blt.html

  * igt@kms_chamelium@hdmi-hpd-fast:
    - fi-kbl-7500u:       [FAIL][13] ([fdo#111407]) -> [PASS][14]
   [13]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7806/fi-kbl-7500u/igt@kms_chamelium@hdmi-hpd-fast.html
   [14]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16247/fi-kbl-7500u/igt@kms_chamelium@hdmi-hpd-fast.html

  * igt@prime_self_import@basic-with_one_bo_two_files:
    - fi-tgl-y:           [DMESG-WARN][15] ([CI#94] / [i915#402]) -> [PASS][16]
   [15]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7806/fi-tgl-y/igt@prime_self_import@basic-with_one_bo_two_files.html
   [16]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16247/fi-tgl-y/igt@prime_self_import@basic-with_one_bo_two_files.html

  
#### Warnings ####

  * igt@gem_close_race@basic-threads:
    - fi-byt-j1900:       [TIMEOUT][17] ([fdo#112271] / [i915#816]) -> [INCOMPLETE][18] ([i915#45])
   [17]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7806/fi-byt-j1900/igt@gem_close_race@basic-threads.html
   [18]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16247/fi-byt-j1900/igt@gem_close_race@basic-threads.html

  
  [CI#94]: https://gitlab.freedesktop.org/gfx-ci/i915-infra/issues/94
  [fdo#111407]: https://bugs.freedesktop.org/show_bug.cgi?id=111407
  [fdo#112271]: https://bugs.freedesktop.org/show_bug.cgi?id=112271
  [i915#402]: https://gitlab.freedesktop.org/drm/intel/issues/402
  [i915#45]: https://gitlab.freedesktop.org/drm/intel/issues/45
  [i915#563]: https://gitlab.freedesktop.org/drm/intel/issues/563
  [i915#722]: https://gitlab.freedesktop.org/drm/intel/issues/722
  [i915#723]: https://gitlab.freedesktop.org/drm/intel/issues/723
  [i915#816]: https://gitlab.freedesktop.org/drm/intel/issues/816


Participating hosts (52 -> 40)
------------------------------

  Missing    (12): fi-ilk-m540 fi-hsw-4200u fi-byt-squawks fi-bsw-cyan fi-bwr-2160 fi-ctg-p8600 fi-gdg-551 fi-ivb-3770 fi-skl-lmem fi-kbl-7560u fi-byt-clapper fi-bdw-samus 


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

  * CI: CI-20190529 -> None
  * Linux: CI_DRM_7806 -> Patchwork_16247

  CI-20190529: 20190529
  CI_DRM_7806: 0b551226df5e5b84044705d5fd76571da70f3163 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_5382: 8dbe5ce61baa2d563d4dd7c56a018bb1e1077467 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_16247: 481e30922e7fd6abb5e640395acce7cacd14a82c @ git://anongit.freedesktop.org/gfx-ci/linux


== Linux commits ==

481e30922e7f drm/i915/perf: Fix OA context id overlap with idle context id

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16247/index.html
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [Intel-gfx] [PATCH] drm/i915/perf: Fix OA context id overlap with idle context id

[Lionel Landwerlin]

On 24/01/2020 03:37, Umesh Nerlige Ramappa wrote:
> Engine context pinned in perf OA was set to same context id as
> the idle context. Set the context id to an unused value.
>
> Clear the sw context id field in lrc descriptor before ORing with
> ce->tag (Chris)
>
> Fixes: https://gitlab.freedesktop.org/drm/intel/issues/756
> Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
> ---
>   drivers/gpu/drm/i915/gt/intel_lrc.c | 2 +-
>   drivers/gpu/drm/i915/i915_perf.c    | 9 +++++++--
>   2 files changed, 8 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
> index a13a8c4b65ab..cf6c43bd540a 100644
> --- a/drivers/gpu/drm/i915/gt/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
> @@ -1211,12 +1211,12 @@ __execlists_schedule_in(struct i915_request *rq)
>   	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
>   		execlists_check_context(ce, engine);
>   
> +	ce->lrc_desc &= ~GENMASK_ULL(47, 37);
>   	if (ce->tag) {
>   		/* Use a fixed tag for OA and friends */
>   		ce->lrc_desc |= (u64)ce->tag << 32;
>   	} else {
>   		/* We don't need a strict matching tag, just different values */
> -		ce->lrc_desc &= ~GENMASK_ULL(47, 37);
I guess you can remove the line just above.
>   		ce->lrc_desc |=
>   			(u64)(++engine->context_tag % NUM_CONTEXT_TAG) <<
>   			GEN11_SW_CTX_ID_SHIFT;
> diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
> index 3c4647054557..5bd878c64504 100644
> --- a/drivers/gpu/drm/i915/i915_perf.c
> +++ b/drivers/gpu/drm/i915/i915_perf.c
> @@ -1323,7 +1323,12 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
>   	case 12: {
>   		stream->specific_ctx_id_mask =
>   			((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
> -		stream->specific_ctx_id = stream->specific_ctx_id_mask;
> +		/* Pick an unused context id
> +		 * 0 - (NUM_CONTEXT_TAG - 1) are used by other contexts
> +		 * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context
> +		 */
> +		stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
> +		BUILD_BUG_ON((GEN12_MAX_CONTEXT_HW_ID - 1) < NUM_CONTEXT_TAG);


Arg yeah, we can't use an id that has all bits to 1 because that matches 
the idle value in the OA reports :/

This also affects gen8-10 cases (afaik).


Thanks for spotting this!


-Lionel


>   		break;
>   	}
>   
> @@ -1331,7 +1336,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
>   		MISSING_CASE(INTEL_GEN(ce->engine->i915));
>   	}
>   
> -	ce->tag = stream->specific_ctx_id_mask;
> +	ce->tag = stream->specific_ctx_id;
>   
>   	DRM_DEBUG_DRIVER("filtering on ctx_id=0x%x ctx_id_mask=0x%x\n",
>   			 stream->specific_ctx_id,


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

Re: [Intel-gfx] [PATCH] drm/i915/perf: Fix OA context id overlap with idle context id

[Lionel Landwerlin]

On 25/01/2020 03:37, Lionel Landwerlin wrote:
> On 24/01/2020 03:37, Umesh Nerlige Ramappa wrote:
>> Engine context pinned in perf OA was set to same context id as
>> the idle context. Set the context id to an unused value.
>>
>> Clear the sw context id field in lrc descriptor before ORing with
>> ce->tag (Chris)
>>
>> Fixes: https://gitlab.freedesktop.org/drm/intel/issues/756

I think the Fixes: tag is to point to another commit. And I think you 
want to point to the commit that you're fixing.

Not sure what you should use gitlab MRs.

-Lionel

>> Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
>> ---
>>   drivers/gpu/drm/i915/gt/intel_lrc.c | 2 +-
>>   drivers/gpu/drm/i915/i915_perf.c    | 9 +++++++--
>>   2 files changed, 8 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c 
>> b/drivers/gpu/drm/i915/gt/intel_lrc.c
>> index a13a8c4b65ab..cf6c43bd540a 100644
>> --- a/drivers/gpu/drm/i915/gt/intel_lrc.c
>> +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
>> @@ -1211,12 +1211,12 @@ __execlists_schedule_in(struct i915_request *rq)
>>       if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
>>           execlists_check_context(ce, engine);
>>   +    ce->lrc_desc &= ~GENMASK_ULL(47, 37);
>>       if (ce->tag) {
>>           /* Use a fixed tag for OA and friends */
>>           ce->lrc_desc |= (u64)ce->tag << 32;
>>       } else {
>>           /* We don't need a strict matching tag, just different 
>> values */
>> -        ce->lrc_desc &= ~GENMASK_ULL(47, 37);
> I guess you can remove the line just above.
>>           ce->lrc_desc |=
>>               (u64)(++engine->context_tag % NUM_CONTEXT_TAG) <<
>>               GEN11_SW_CTX_ID_SHIFT;
>> diff --git a/drivers/gpu/drm/i915/i915_perf.c 
>> b/drivers/gpu/drm/i915/i915_perf.c
>> index 3c4647054557..5bd878c64504 100644
>> --- a/drivers/gpu/drm/i915/i915_perf.c
>> +++ b/drivers/gpu/drm/i915/i915_perf.c
>> @@ -1323,7 +1323,12 @@ static int oa_get_render_ctx_id(struct 
>> i915_perf_stream *stream)
>>       case 12: {
>>           stream->specific_ctx_id_mask =
>>               ((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << 
>> (GEN11_SW_CTX_ID_SHIFT - 32);
>> -        stream->specific_ctx_id = stream->specific_ctx_id_mask;
>> +        /* Pick an unused context id
>> +         * 0 - (NUM_CONTEXT_TAG - 1) are used by other contexts
>> +         * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context
>> +         */
>> +        stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) << 
>> (GEN11_SW_CTX_ID_SHIFT - 32);
>> +        BUILD_BUG_ON((GEN12_MAX_CONTEXT_HW_ID - 1) < NUM_CONTEXT_TAG);
>
>
> Arg yeah, we can't use an id that has all bits to 1 because that 
> matches the idle value in the OA reports :/
>
> This also affects gen8-10 cases (afaik).
>
>
> Thanks for spotting this!
>
>
> -Lionel
>
>
>>           break;
>>       }
>>   @@ -1331,7 +1336,7 @@ static int oa_get_render_ctx_id(struct 
>> i915_perf_stream *stream)
>>           MISSING_CASE(INTEL_GEN(ce->engine->i915));
>>       }
>>   -    ce->tag = stream->specific_ctx_id_mask;
>> +    ce->tag = stream->specific_ctx_id;
>>         DRM_DEBUG_DRIVER("filtering on ctx_id=0x%x ctx_id_mask=0x%x\n",
>>                stream->specific_ctx_id,
>
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx


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

Re: [Intel-gfx] [PATCH] drm/i915/perf: Fix OA context id overlap with idle context id

[Chris Wilson]

Quoting Lionel Landwerlin (2020-01-25 15:02:21)
> On 25/01/2020 03:37, Lionel Landwerlin wrote:
> > On 24/01/2020 03:37, Umesh Nerlige Ramappa wrote:
> >> Engine context pinned in perf OA was set to same context id as
> >> the idle context. Set the context id to an unused value.
> >>
> >> Clear the sw context id field in lrc descriptor before ORing with
> >> ce->tag (Chris)
> >>
> >> Fixes: https://gitlab.freedesktop.org/drm/intel/issues/756
> 
> I think the Fixes: tag is to point to another commit. And I think you 
> want to point to the commit that you're fixing.
> 
> Not sure what you should use gitlab MRs.

We're using Closes: https://gitlab.fd.o/issues/# as a replacement for
Bugzilla:.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for drm/i915/perf: Fix OA context id overlap with idle context id (rev2)

[Patchwork]

== Series Details ==

Series: drm/i915/perf: Fix OA context id overlap with idle context id (rev2)
URL   : https://patchwork.freedesktop.org/series/72505/
State : warning

== Summary ==

$ dim checkpatch origin/drm-tip
e09d05170d36 drm/i915/perf: Fix OA context id overlap with idle context id
-:46: WARNING:LONG_LINE: line over 100 characters
#46: FILE: drivers/gpu/drm/i915/i915_perf.c:1330:
+		stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);

total: 0 errors, 1 warnings, 0 checks, 34 lines checked

_______________________________________________
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/perf: Fix OA context id overlap with idle context id (rev2)

[Patchwork]

== Series Details ==

Series: drm/i915/perf: Fix OA context id overlap with idle context id (rev2)
URL   : https://patchwork.freedesktop.org/series/72505/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_7814 -> Patchwork_16269
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/index.html

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

  Here are the changes found in Patchwork_16269 that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@gem_exec_parallel@fds:
    - fi-byt-n2820:       [PASS][1] -> [TIMEOUT][2] ([fdo#112271])
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/fi-byt-n2820/igt@gem_exec_parallel@fds.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/fi-byt-n2820/igt@gem_exec_parallel@fds.html

  * igt@i915_pm_rpm@module-reload:
    - fi-skl-6600u:       [PASS][3] -> [DMESG-WARN][4] ([i915#889]) +23 similar issues
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/fi-skl-6600u/igt@i915_pm_rpm@module-reload.html
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/fi-skl-6600u/igt@i915_pm_rpm@module-reload.html

  * igt@i915_selftest@live_blt:
    - fi-hsw-peppy:       [PASS][5] -> [DMESG-FAIL][6] ([i915#553] / [i915#725])
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/fi-hsw-peppy/igt@i915_selftest@live_blt.html
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/fi-hsw-peppy/igt@i915_selftest@live_blt.html
    - fi-hsw-4770:        [PASS][7] -> [DMESG-FAIL][8] ([i915#553] / [i915#725])
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/fi-hsw-4770/igt@i915_selftest@live_blt.html
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/fi-hsw-4770/igt@i915_selftest@live_blt.html

  * igt@i915_selftest@live_gem_contexts:
    - fi-cfl-guc:         [PASS][9] -> [INCOMPLETE][10] ([CI#80] / [fdo#106070] / [i915#424])
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/fi-cfl-guc/igt@i915_selftest@live_gem_contexts.html
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/fi-cfl-guc/igt@i915_selftest@live_gem_contexts.html

  * igt@i915_selftest@live_gt_lrc:
    - fi-skl-6600u:       [PASS][11] -> [DMESG-FAIL][12] ([i915#889]) +7 similar issues
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/fi-skl-6600u/igt@i915_selftest@live_gt_lrc.html
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/fi-skl-6600u/igt@i915_selftest@live_gt_lrc.html

  * igt@kms_chamelium@hdmi-hpd-fast:
    - fi-icl-u2:          [PASS][13] -> [FAIL][14] ([i915#217])
   [13]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/fi-icl-u2/igt@kms_chamelium@hdmi-hpd-fast.html
   [14]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/fi-icl-u2/igt@kms_chamelium@hdmi-hpd-fast.html

  
#### Possible fixes ####

  * igt@i915_module_load@reload-with-fault-injection:
    - fi-kbl-x1275:       [INCOMPLETE][15] ([i915#879]) -> [PASS][16]
   [15]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/fi-kbl-x1275/igt@i915_module_load@reload-with-fault-injection.html
   [16]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/fi-kbl-x1275/igt@i915_module_load@reload-with-fault-injection.html

  * igt@kms_frontbuffer_tracking@basic:
    - fi-hsw-peppy:       [DMESG-WARN][17] ([i915#44]) -> [PASS][18]
   [17]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/fi-hsw-peppy/igt@kms_frontbuffer_tracking@basic.html
   [18]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/fi-hsw-peppy/igt@kms_frontbuffer_tracking@basic.html

  
#### Warnings ####

  * igt@gem_exec_parallel@contexts:
    - fi-byt-n2820:       [TIMEOUT][19] ([fdo#112271]) -> [FAIL][20] ([i915#694])
   [19]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/fi-byt-n2820/igt@gem_exec_parallel@contexts.html
   [20]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/fi-byt-n2820/igt@gem_exec_parallel@contexts.html

  
  [CI#80]: https://gitlab.freedesktop.org/gfx-ci/i915-infra/issues/80
  [fdo#106070]: https://bugs.freedesktop.org/show_bug.cgi?id=106070
  [fdo#112271]: https://bugs.freedesktop.org/show_bug.cgi?id=112271
  [i915#217]: https://gitlab.freedesktop.org/drm/intel/issues/217
  [i915#424]: https://gitlab.freedesktop.org/drm/intel/issues/424
  [i915#44]: https://gitlab.freedesktop.org/drm/intel/issues/44
  [i915#553]: https://gitlab.freedesktop.org/drm/intel/issues/553
  [i915#694]: https://gitlab.freedesktop.org/drm/intel/issues/694
  [i915#725]: https://gitlab.freedesktop.org/drm/intel/issues/725
  [i915#879]: https://gitlab.freedesktop.org/drm/intel/issues/879
  [i915#889]: https://gitlab.freedesktop.org/drm/intel/issues/889


Participating hosts (44 -> 41)
------------------------------

  Additional (5): fi-bdw-gvtdvm fi-kbl-7500u fi-blb-e6850 fi-snb-2600 fi-kbl-r 
  Missing    (8): fi-byt-squawks fi-bsw-cyan fi-bwr-2160 fi-kbl-guc fi-ctg-p8600 fi-whl-u fi-byt-clapper fi-bdw-samus 


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

  * CI: CI-20190529 -> None
  * Linux: CI_DRM_7814 -> Patchwork_16269

  CI-20190529: 20190529
  CI_DRM_7814: bc626bbb5b6efa3fb6a90407e85a04ae64461db6 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_5384: fd6896567f7d612c76207970376d4f1e634ded55 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_16269: e09d05170d36fde12bbbdbf997dba5d19f0a970f @ git://anongit.freedesktop.org/gfx-ci/linux


== Linux commits ==

e09d05170d36 drm/i915/perf: Fix OA context id overlap with idle context id

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/index.html
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [Intel-gfx] [PATCH] drm/i915/perf: Fix OA context id overlap with idle context id

[Umesh Nerlige Ramappa]

On Sat, Jan 25, 2020 at 03:37:38AM +0200, Lionel Landwerlin wrote:
>On 24/01/2020 03:37, Umesh Nerlige Ramappa wrote:
>>Engine context pinned in perf OA was set to same context id as
>>the idle context. Set the context id to an unused value.
>>
>>Clear the sw context id field in lrc descriptor before ORing with
>>ce->tag (Chris)
>>
>>Fixes: https://gitlab.freedesktop.org/drm/intel/issues/756
>>Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
>>---
>>  drivers/gpu/drm/i915/gt/intel_lrc.c | 2 +-
>>  drivers/gpu/drm/i915/i915_perf.c    | 9 +++++++--
>>  2 files changed, 8 insertions(+), 3 deletions(-)
>>
>>diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
>>index a13a8c4b65ab..cf6c43bd540a 100644
>>--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
>>+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
>>@@ -1211,12 +1211,12 @@ __execlists_schedule_in(struct i915_request *rq)
>>  	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
>>  		execlists_check_context(ce, engine);
>>+	ce->lrc_desc &= ~GENMASK_ULL(47, 37);
>>  	if (ce->tag) {
>>  		/* Use a fixed tag for OA and friends */
>>  		ce->lrc_desc |= (u64)ce->tag << 32;
>>  	} else {
>>  		/* We don't need a strict matching tag, just different values */
>>-		ce->lrc_desc &= ~GENMASK_ULL(47, 37);
>I guess you can remove the line just above.

Not sure what you mean, the line is moved from here to above the if.

>>  		ce->lrc_desc |=
>>  			(u64)(++engine->context_tag % NUM_CONTEXT_TAG) <<
>>  			GEN11_SW_CTX_ID_SHIFT;
>>diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
>>index 3c4647054557..5bd878c64504 100644
>>--- a/drivers/gpu/drm/i915/i915_perf.c
>>+++ b/drivers/gpu/drm/i915/i915_perf.c
>>@@ -1323,7 +1323,12 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
>>  	case 12: {
>>  		stream->specific_ctx_id_mask =
>>  			((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
>>-		stream->specific_ctx_id = stream->specific_ctx_id_mask;
>>+		/* Pick an unused context id
>>+		 * 0 - (NUM_CONTEXT_TAG - 1) are used by other contexts
>>+		 * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context
>>+		 */
>>+		stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
>>+		BUILD_BUG_ON((GEN12_MAX_CONTEXT_HW_ID - 1) < NUM_CONTEXT_TAG);
>
>
>Arg yeah, we can't use an id that has all bits to 1 because that 
>matches the idle value in the OA reports :/
>
>This also affects gen8-10 cases (afaik).

For gen8-10, I did not see a specific definition for an idle context id.  
The from/to idle context switches are indicated by dedicated bits in the 
CSB instead (from spec).

Thanks,
Umesh

>
>
>Thanks for spotting this!
>
>
>-Lionel
>
>
>>  		break;
>>  	}
>>@@ -1331,7 +1336,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
>>  		MISSING_CASE(INTEL_GEN(ce->engine->i915));
>>  	}
>>-	ce->tag = stream->specific_ctx_id_mask;
>>+	ce->tag = stream->specific_ctx_id;
>>  	DRM_DEBUG_DRIVER("filtering on ctx_id=0x%x ctx_id_mask=0x%x\n",
>>  			 stream->specific_ctx_id,
>
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [Intel-gfx] [PATCH] drm/i915/perf: Fix OA context id overlap with idle context id

[Lionel Landwerlin]

On 27/01/2020 07:30, Umesh Nerlige Ramappa wrote:
> On Sat, Jan 25, 2020 at 03:37:38AM +0200, Lionel Landwerlin wrote:
>> On 24/01/2020 03:37, Umesh Nerlige Ramappa wrote:
>>> Engine context pinned in perf OA was set to same context id as
>>> the idle context. Set the context id to an unused value.
>>>
>>> Clear the sw context id field in lrc descriptor before ORing with
>>> ce->tag (Chris)
>>>
>>> Fixes: https://gitlab.freedesktop.org/drm/intel/issues/756
>>> Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
>>> ---
>>>  drivers/gpu/drm/i915/gt/intel_lrc.c | 2 +-
>>>  drivers/gpu/drm/i915/i915_perf.c    | 9 +++++++--
>>>  2 files changed, 8 insertions(+), 3 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c 
>>> b/drivers/gpu/drm/i915/gt/intel_lrc.c
>>> index a13a8c4b65ab..cf6c43bd540a 100644
>>> --- a/drivers/gpu/drm/i915/gt/intel_lrc.c
>>> +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
>>> @@ -1211,12 +1211,12 @@ __execlists_schedule_in(struct i915_request 
>>> *rq)
>>>      if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
>>>          execlists_check_context(ce, engine);
>>> +    ce->lrc_desc &= ~GENMASK_ULL(47, 37);
>>>      if (ce->tag) {
>>>          /* Use a fixed tag for OA and friends */
>>>          ce->lrc_desc |= (u64)ce->tag << 32;
>>>      } else {
>>>          /* We don't need a strict matching tag, just different 
>>> values */
>>> -        ce->lrc_desc &= ~GENMASK_ULL(47, 37);
>> I guess you can remove the line just above.
>
> Not sure what you mean, the line is moved from here to above the if.


Oh sorry, Looking at the responding email, the '-' didn't appear :(


>
>>>          ce->lrc_desc |=
>>>              (u64)(++engine->context_tag % NUM_CONTEXT_TAG) <<
>>>              GEN11_SW_CTX_ID_SHIFT;
>>> diff --git a/drivers/gpu/drm/i915/i915_perf.c 
>>> b/drivers/gpu/drm/i915/i915_perf.c
>>> index 3c4647054557..5bd878c64504 100644
>>> --- a/drivers/gpu/drm/i915/i915_perf.c
>>> +++ b/drivers/gpu/drm/i915/i915_perf.c
>>> @@ -1323,7 +1323,12 @@ static int oa_get_render_ctx_id(struct 
>>> i915_perf_stream *stream)
>>>      case 12: {
>>>          stream->specific_ctx_id_mask =
>>>              ((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << 
>>> (GEN11_SW_CTX_ID_SHIFT - 32);
>>> -        stream->specific_ctx_id = stream->specific_ctx_id_mask;
>>> +        /* Pick an unused context id
>>> +         * 0 - (NUM_CONTEXT_TAG - 1) are used by other contexts
>>> +         * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context
>>> +         */
>>> +        stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) << 
>>> (GEN11_SW_CTX_ID_SHIFT - 32);
>>> +        BUILD_BUG_ON((GEN12_MAX_CONTEXT_HW_ID - 1) < NUM_CONTEXT_TAG);
>>
>>
>> Arg yeah, we can't use an id that has all bits to 1 because that 
>> matches the idle value in the OA reports :/
>>
>> This also affects gen8-10 cases (afaik).
>
> For gen8-10, I did not see a specific definition for an idle context 
> id.  The from/to idle context switches are indicated by dedicated bits 
> in the CSB instead (from spec).


I meant that I remember the periodic OA reports when HW is idle to have 
the contex_id=0xffffffff.

I could remember wrong :/


-Lionel


>
> Thanks,
> Umesh
>
>>
>>
>> Thanks for spotting this!
>>
>>
>> -Lionel
>>
>>
>>>          break;
>>>      }
>>> @@ -1331,7 +1336,7 @@ static int oa_get_render_ctx_id(struct 
>>> i915_perf_stream *stream)
>>>          MISSING_CASE(INTEL_GEN(ce->engine->i915));
>>>      }
>>> -    ce->tag = stream->specific_ctx_id_mask;
>>> +    ce->tag = stream->specific_ctx_id;
>>>      DRM_DEBUG_DRIVER("filtering on ctx_id=0x%x ctx_id_mask=0x%x\n",
>>>               stream->specific_ctx_id,
>>
>>

_______________________________________________
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/perf: Fix OA context id overlap with idle context id (rev2)

[Patchwork]

== Series Details ==

Series: drm/i915/perf: Fix OA context id overlap with idle context id (rev2)
URL   : https://patchwork.freedesktop.org/series/72505/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_7814_full -> Patchwork_16269_full
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  

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

  Here are the changes found in Patchwork_16269_full that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@gem_ctx_persistence@vcs1-mixed-process:
    - shard-iclb:         [PASS][1] -> [SKIP][2] ([fdo#109276] / [fdo#112080]) +5 similar issues
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-iclb2/igt@gem_ctx_persistence@vcs1-mixed-process.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-iclb7/igt@gem_ctx_persistence@vcs1-mixed-process.html

  * igt@gem_exec_schedule@in-order-bsd:
    - shard-iclb:         [PASS][3] -> [SKIP][4] ([fdo#112146]) +11 similar issues
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-iclb5/igt@gem_exec_schedule@in-order-bsd.html
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-iclb1/igt@gem_exec_schedule@in-order-bsd.html

  * igt@gem_exec_schedule@pi-distinct-iova-bsd:
    - shard-iclb:         [PASS][5] -> [SKIP][6] ([i915#677]) +1 similar issue
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-iclb8/igt@gem_exec_schedule@pi-distinct-iova-bsd.html
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-iclb1/igt@gem_exec_schedule@pi-distinct-iova-bsd.html

  * igt@gem_fence_thrash@bo-write-verify-threaded-y:
    - shard-apl:          [PASS][7] -> [INCOMPLETE][8] ([CI#80] / [fdo#103927])
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-apl8/igt@gem_fence_thrash@bo-write-verify-threaded-y.html
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-apl8/igt@gem_fence_thrash@bo-write-verify-threaded-y.html

  * igt@gem_userptr_blits@sync-unmap-after-close:
    - shard-skl:          [PASS][9] -> [DMESG-WARN][10] ([fdo#111870] / [i915#836])
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-skl10/igt@gem_userptr_blits@sync-unmap-after-close.html
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-skl10/igt@gem_userptr_blits@sync-unmap-after-close.html

  * igt@gen9_exec_parse@allowed-all:
    - shard-glk:          [PASS][11] -> [INCOMPLETE][12] ([i915#58] / [k.org#198133])
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-glk3/igt@gen9_exec_parse@allowed-all.html
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-glk5/igt@gen9_exec_parse@allowed-all.html

  * igt@i915_pm_rps@min-max-config-loaded:
    - shard-skl:          [PASS][13] -> [FAIL][14] ([i915#39])
   [13]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-skl1/igt@i915_pm_rps@min-max-config-loaded.html
   [14]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-skl1/igt@i915_pm_rps@min-max-config-loaded.html

  * igt@i915_selftest@live_blt:
    - shard-hsw:          [PASS][15] -> [DMESG-FAIL][16] ([i915#725])
   [15]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-hsw5/igt@i915_selftest@live_blt.html
   [16]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-hsw7/igt@i915_selftest@live_blt.html

  * igt@i915_suspend@fence-restore-tiled2untiled:
    - shard-apl:          [PASS][17] -> [DMESG-WARN][18] ([i915#180]) +3 similar issues
   [17]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-apl8/igt@i915_suspend@fence-restore-tiled2untiled.html
   [18]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-apl8/igt@i915_suspend@fence-restore-tiled2untiled.html

  * igt@kms_cursor_crc@pipe-a-cursor-suspend:
    - shard-kbl:          [PASS][19] -> [DMESG-WARN][20] ([i915#180]) +5 similar issues
   [19]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-kbl7/igt@kms_cursor_crc@pipe-a-cursor-suspend.html
   [20]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-kbl3/igt@kms_cursor_crc@pipe-a-cursor-suspend.html

  * igt@kms_cursor_crc@pipe-c-cursor-suspend:
    - shard-skl:          [PASS][21] -> [INCOMPLETE][22] ([i915#300])
   [21]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-skl2/igt@kms_cursor_crc@pipe-c-cursor-suspend.html
   [22]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-skl2/igt@kms_cursor_crc@pipe-c-cursor-suspend.html

  * igt@kms_cursor_legacy@flip-vs-cursor-atomic-transitions:
    - shard-glk:          [PASS][23] -> [FAIL][24] ([IGT#5] / [i915#697])
   [23]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-glk1/igt@kms_cursor_legacy@flip-vs-cursor-atomic-transitions.html
   [24]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-glk4/igt@kms_cursor_legacy@flip-vs-cursor-atomic-transitions.html

  * igt@kms_plane_alpha_blend@pipe-a-coverage-7efc:
    - shard-skl:          [PASS][25] -> [FAIL][26] ([fdo#108145])
   [25]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-skl6/igt@kms_plane_alpha_blend@pipe-a-coverage-7efc.html
   [26]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-skl1/igt@kms_plane_alpha_blend@pipe-a-coverage-7efc.html

  * igt@kms_psr@psr2_primary_mmap_cpu:
    - shard-iclb:         [PASS][27] -> [SKIP][28] ([fdo#109441]) +2 similar issues
   [27]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-iclb2/igt@kms_psr@psr2_primary_mmap_cpu.html
   [28]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-iclb6/igt@kms_psr@psr2_primary_mmap_cpu.html

  * igt@perf_pmu@busy-start-vcs1:
    - shard-iclb:         [PASS][29] -> [SKIP][30] ([fdo#112080]) +9 similar issues
   [29]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-iclb4/igt@perf_pmu@busy-start-vcs1.html
   [30]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-iclb7/igt@perf_pmu@busy-start-vcs1.html

  * igt@prime_busy@hang-bsd2:
    - shard-iclb:         [PASS][31] -> [SKIP][32] ([fdo#109276]) +28 similar issues
   [31]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-iclb2/igt@prime_busy@hang-bsd2.html
   [32]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-iclb6/igt@prime_busy@hang-bsd2.html

  
#### Possible fixes ####

  * igt@gem_busy@busy-vcs1:
    - shard-iclb:         [SKIP][33] ([fdo#112080]) -> [PASS][34] +15 similar issues
   [33]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-iclb8/igt@gem_busy@busy-vcs1.html
   [34]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-iclb2/igt@gem_busy@busy-vcs1.html

  * igt@gem_caching@read-writes:
    - shard-hsw:          [FAIL][35] -> [PASS][36]
   [35]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-hsw7/igt@gem_caching@read-writes.html
   [36]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-hsw4/igt@gem_caching@read-writes.html

  * igt@gem_ctx_isolation@vcs1-dirty-create:
    - shard-iclb:         [SKIP][37] ([fdo#109276] / [fdo#112080]) -> [PASS][38] +4 similar issues
   [37]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-iclb6/igt@gem_ctx_isolation@vcs1-dirty-create.html
   [38]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-iclb4/igt@gem_ctx_isolation@vcs1-dirty-create.html

  * igt@gem_exec_schedule@out-order-bsd2:
    - shard-iclb:         [SKIP][39] ([fdo#109276]) -> [PASS][40] +28 similar issues
   [39]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-iclb8/igt@gem_exec_schedule@out-order-bsd2.html
   [40]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-iclb2/igt@gem_exec_schedule@out-order-bsd2.html

  * igt@gem_exec_schedule@pi-userfault-bsd:
    - shard-iclb:         [SKIP][41] ([i915#677]) -> [PASS][42]
   [41]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-iclb1/igt@gem_exec_schedule@pi-userfault-bsd.html
   [42]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-iclb5/igt@gem_exec_schedule@pi-userfault-bsd.html

  * igt@gem_exec_schedule@preemptive-hang-bsd:
    - shard-iclb:         [SKIP][43] ([fdo#112146]) -> [PASS][44] +4 similar issues
   [43]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-iclb1/igt@gem_exec_schedule@preemptive-hang-bsd.html
   [44]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-iclb5/igt@gem_exec_schedule@preemptive-hang-bsd.html

  * igt@gem_exec_whisper@normal:
    - shard-glk:          [DMESG-WARN][45] ([i915#118] / [i915#95]) -> [PASS][46]
   [45]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-glk2/igt@gem_exec_whisper@normal.html
   [46]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-glk8/igt@gem_exec_whisper@normal.html

  * igt@gem_ppgtt@flink-and-close-vma-leak:
    - shard-glk:          [FAIL][47] ([i915#644]) -> [PASS][48]
   [47]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-glk7/igt@gem_ppgtt@flink-and-close-vma-leak.html
   [48]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-glk1/igt@gem_ppgtt@flink-and-close-vma-leak.html
    - shard-kbl:          [FAIL][49] ([i915#644]) -> [PASS][50]
   [49]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-kbl1/igt@gem_ppgtt@flink-and-close-vma-leak.html
   [50]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-kbl6/igt@gem_ppgtt@flink-and-close-vma-leak.html

  * igt@i915_suspend@sysfs-reader:
    - shard-apl:          [DMESG-WARN][51] ([i915#180]) -> [PASS][52] +3 similar issues
   [51]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-apl1/igt@i915_suspend@sysfs-reader.html
   [52]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-apl7/igt@i915_suspend@sysfs-reader.html

  * igt@kms_color@pipe-b-ctm-red-to-blue:
    - shard-skl:          [DMESG-WARN][53] ([i915#109]) -> [PASS][54] +1 similar issue
   [53]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-skl6/igt@kms_color@pipe-b-ctm-red-to-blue.html
   [54]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-skl1/igt@kms_color@pipe-b-ctm-red-to-blue.html

  * igt@kms_flip@flip-vs-suspend-interruptible:
    - shard-hsw:          [INCOMPLETE][55] ([i915#61]) -> [PASS][56]
   [55]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-hsw6/igt@kms_flip@flip-vs-suspend-interruptible.html
   [56]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-hsw6/igt@kms_flip@flip-vs-suspend-interruptible.html

  * igt@kms_frontbuffer_tracking@fbc-suspend:
    - shard-kbl:          [DMESG-WARN][57] ([i915#180]) -> [PASS][58] +6 similar issues
   [57]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-kbl1/igt@kms_frontbuffer_tracking@fbc-suspend.html
   [58]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-kbl6/igt@kms_frontbuffer_tracking@fbc-suspend.html

  * igt@kms_psr2_su@page_flip:
    - shard-iclb:         [SKIP][59] ([fdo#109642] / [fdo#111068]) -> [PASS][60]
   [59]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-iclb6/igt@kms_psr2_su@page_flip.html
   [60]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-iclb2/igt@kms_psr2_su@page_flip.html

  * igt@kms_psr@psr2_sprite_plane_move:
    - shard-iclb:         [SKIP][61] ([fdo#109441]) -> [PASS][62] +1 similar issue
   [61]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-iclb3/igt@kms_psr@psr2_sprite_plane_move.html
   [62]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-iclb2/igt@kms_psr@psr2_sprite_plane_move.html

  * igt@kms_vblank@pipe-b-ts-continuation-dpms-suspend:
    - shard-skl:          [INCOMPLETE][63] ([i915#69]) -> [PASS][64]
   [63]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-skl9/igt@kms_vblank@pipe-b-ts-continuation-dpms-suspend.html
   [64]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-skl9/igt@kms_vblank@pipe-b-ts-continuation-dpms-suspend.html

  * igt@perf@gen12-unprivileged-single-ctx-counters:
    - shard-tglb:         [INCOMPLETE][65] ([i915#472] / [i915#756]) -> [PASS][66]
   [65]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-tglb7/igt@perf@gen12-unprivileged-single-ctx-counters.html
   [66]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-tglb6/igt@perf@gen12-unprivileged-single-ctx-counters.html

  * igt@prime_mmap_coherency@ioctl-errors:
    - shard-hsw:          [FAIL][67] ([i915#831]) -> [PASS][68]
   [67]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-hsw7/igt@prime_mmap_coherency@ioctl-errors.html
   [68]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-hsw2/igt@prime_mmap_coherency@ioctl-errors.html

  
#### Warnings ####

  * igt@gem_ctx_isolation@vcs1-nonpriv:
    - shard-iclb:         [SKIP][69] ([fdo#109276] / [fdo#112080]) -> [FAIL][70] ([IGT#28])
   [69]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-iclb6/igt@gem_ctx_isolation@vcs1-nonpriv.html
   [70]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-iclb4/igt@gem_ctx_isolation@vcs1-nonpriv.html

  * igt@gem_ctx_isolation@vcs1-nonpriv-switch:
    - shard-iclb:         [FAIL][71] ([IGT#28]) -> [SKIP][72] ([fdo#109276] / [fdo#112080])
   [71]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-iclb1/igt@gem_ctx_isolation@vcs1-nonpriv-switch.html
   [72]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-iclb5/igt@gem_ctx_isolation@vcs1-nonpriv-switch.html

  * igt@i915_pm_rpm@modeset-pc8-residency-stress:
    - shard-snb:          [SKIP][73] ([fdo#109271]) -> [INCOMPLETE][74] ([i915#82])
   [73]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-snb4/igt@i915_pm_rpm@modeset-pc8-residency-stress.html
   [74]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-snb6/igt@i915_pm_rpm@modeset-pc8-residency-stress.html

  * igt@kms_dp_dsc@basic-dsc-enable-edp:
    - shard-iclb:         [SKIP][75] ([fdo#109349]) -> [DMESG-WARN][76] ([fdo#107724])
   [75]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-iclb3/igt@kms_dp_dsc@basic-dsc-enable-edp.html
   [76]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-iclb2/igt@kms_dp_dsc@basic-dsc-enable-edp.html

  * igt@perf@gen12-mi-rpc:
    - shard-tglb:         [INCOMPLETE][77] ([i915#472] / [i915#756]) -> [TIMEOUT][78] ([fdo#112271] / [i915#472])
   [77]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7814/shard-tglb7/igt@perf@gen12-mi-rpc.html
   [78]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16269/shard-tglb1/igt@perf@gen12-mi-rpc.html

  
  [CI#80]: https://gitlab.freedesktop.org/gfx-ci/i915-infra/issues/80
  [IGT#28]: https://gitlab.freedesktop.org/drm/igt-gpu-tools/issues/28
  [IGT#5]: https://gitlab.freedesktop.org/drm/igt-gpu-tools/issues/5
  [fdo#103927]: https://bugs.freedesktop.org/show_bug.cgi?id=103927
  [fdo#107724]: https://bugs.freedesktop.org/show_bug.cgi?id=107724
  [fdo#108145]: https://bugs.freedesktop.org/show_bug.cgi?id=108145
  [fdo#109271]: https://bugs.freedesktop.org/show_bug.cgi?id=109271
  [fdo#109276]: https://bugs.freedesktop.org/show_bug.cgi?id=109276
  [fdo#109349]: https://bugs.freedesktop.org/show_bug.cgi?id=109349
  [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
  [fdo#111870]: https://bugs.freedesktop.org/show_bug.cgi?id=111870
  [fdo#112080]: https://bugs.freedesktop.org/show_bug.cgi?id=112080
  [fdo#112146]: https://bugs.freedesktop.org/show_bug.cgi?id=112146
  [fdo#112271]: https://bugs.freedesktop.org/show_bug.cgi?id=112271
  [i915#109]: https://gitlab.freedesktop.org/drm/intel/issues/109
  [i915#118]: https://gitlab.freedesktop.org/drm/intel/issues/118
  [i915#180]: https://gitlab.freedesktop.org/drm/intel/issues/180
  [i915#300]: https://gitlab.freedesktop.org/drm/intel/issues/300
  [i915#39]: https://gitlab.freedesktop.org/drm/intel/issues/39
  [i915#472]: https://gitlab.freedesktop.org/drm/intel/issues/472
  [i915#58]: https://gitlab.freedesktop.org/drm/intel/issues/58
  [i915#61]: https://gitlab.freedesktop.org/drm/intel/issues/61
  [i915#644]: https://gitlab.freedesktop.org/drm/intel/issues/644
  [i915#677]: https://gitlab.freedesktop.org/drm/intel/issues/677
  [i915#69]: https://gitlab.freedesktop.org/drm/intel/issues/69
  [i915#697]: https://gitlab.freedesktop.org/drm/intel/issues/697
  [i915#725]: https://gitlab.freedesktop.org/drm/intel/issues/725
  [i915#756]: https://gitlab.freedesktop.org/drm/intel/issues/756
  [i915#82]: https://gitlab.freedesktop.org/drm/intel/issues/82
  [i915#831]: https://gitlab.freedesktop.org/drm/intel/issues/831
  [i915#836]: https://gitlab.freedesktop.org/drm/intel/issues/836
  [i915#95]: https://gitlab.freedesktop.org/drm/intel/issues/95
  [k.org#198133]: https://bugzilla.kernel.org/show_bug.cgi?id=198133


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

  No changes in participating hosts


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

  * CI: CI-20190529 -> None
  * Linux: CI_DRM_7814 -> Patchwork_16269

  CI-20190529: 20190529
  CI_DRM_7814: bc626bbb5b6efa3fb6a90407e85a04ae64461db6 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_5384: fd6896567f7d612c76207970376d4f1e634ded55 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_16269: e09d05170d36fde12bbbdbf997dba5d19f0a970f @ 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_16269/index.html
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [Intel-gfx] [PATCH] drm/i915/perf: Fix OA context id overlap with idle context id

[Umesh Nerlige Ramappa]

On Mon, Jan 27, 2020 at 11:16:32AM +0200, Lionel Landwerlin wrote:

[snip]

>>>>--- a/drivers/gpu/drm/i915/i915_perf.c
>>>>+++ b/drivers/gpu/drm/i915/i915_perf.c
>>>>@@ -1323,7 +1323,12 @@ static int oa_get_render_ctx_id(struct 
>>>>i915_perf_stream *stream)
>>>>     case 12: {
>>>>         stream->specific_ctx_id_mask =
>>>>             ((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << 
>>>>(GEN11_SW_CTX_ID_SHIFT - 32);
>>>>-        stream->specific_ctx_id = stream->specific_ctx_id_mask;
>>>>+        /* Pick an unused context id
>>>>+         * 0 - (NUM_CONTEXT_TAG - 1) are used by other contexts
>>>>+         * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context
>>>>+         */
>>>>+        stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) 
>>>><< (GEN11_SW_CTX_ID_SHIFT - 32);
>>>>+        BUILD_BUG_ON((GEN12_MAX_CONTEXT_HW_ID - 1) < NUM_CONTEXT_TAG);
>>>
>>>
>>>Arg yeah, we can't use an id that has all bits to 1 because that 
>>>matches the idle value in the OA reports :/
>>>
>>>This also affects gen8-10 cases (afaik).
>>
>>For gen8-10, I did not see a specific definition for an idle context 
>>id.  The from/to idle context switches are indicated by dedicated 
>>bits in the CSB instead (from spec).
>
>
>I meant that I remember the periodic OA reports when HW is idle to 
>have the contex_id=0xffffffff.

For these gens we use 0x1fffff as the context id. Before we return 
reports to the user, we are setting context id to 0xffffffff for invalid 
and irrelevant contexts.

Thanks,
Umesh
>
>I could remember wrong :/
>
>
>-Lionel
>
>
>>
>>Thanks,
>>Umesh
>>
>>>
>>>
>>>Thanks for spotting this!
>>>
>>>
>>>-Lionel
>>>
>>>
>>>>         break;
>>>>     }
>>>>@@ -1331,7 +1336,7 @@ static int oa_get_render_ctx_id(struct 
>>>>i915_perf_stream *stream)
>>>>         MISSING_CASE(INTEL_GEN(ce->engine->i915));
>>>>     }
>>>>-    ce->tag = stream->specific_ctx_id_mask;
>>>>+    ce->tag = stream->specific_ctx_id;
>>>>     DRM_DEBUG_DRIVER("filtering on ctx_id=0x%x ctx_id_mask=0x%x\n",
>>>>              stream->specific_ctx_id,
>>>
>>>
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [Intel-gfx] [PATCH] drm/i915/perf: Fix OA context id overlap with idle context id

[Lionel Landwerlin]

On 31/01/2020 01:54, Umesh Nerlige Ramappa wrote:
> On Mon, Jan 27, 2020 at 11:16:32AM +0200, Lionel Landwerlin wrote:
>
> [snip]
>
>>>>> --- a/drivers/gpu/drm/i915/i915_perf.c
>>>>> +++ b/drivers/gpu/drm/i915/i915_perf.c
>>>>> @@ -1323,7 +1323,12 @@ static int oa_get_render_ctx_id(struct 
>>>>> i915_perf_stream *stream)
>>>>>      case 12: {
>>>>>          stream->specific_ctx_id_mask =
>>>>>              ((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << 
>>>>> (GEN11_SW_CTX_ID_SHIFT - 32);
>>>>> -        stream->specific_ctx_id = stream->specific_ctx_id_mask;
>>>>> +        /* Pick an unused context id
>>>>> +         * 0 - (NUM_CONTEXT_TAG - 1) are used by other contexts
>>>>> +         * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context
>>>>> +         */
>>>>> +        stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) 
>>>>> << (GEN11_SW_CTX_ID_SHIFT - 32);
>>>>> +        BUILD_BUG_ON((GEN12_MAX_CONTEXT_HW_ID - 1) < 
>>>>> NUM_CONTEXT_TAG);
>>>>
>>>>
>>>> Arg yeah, we can't use an id that has all bits to 1 because that 
>>>> matches the idle value in the OA reports :/
>>>>
>>>> This also affects gen8-10 cases (afaik).
>>>
>>> For gen8-10, I did not see a specific definition for an idle context 
>>> id.  The from/to idle context switches are indicated by dedicated 
>>> bits in the CSB instead (from spec).
>>
>>
>> I meant that I remember the periodic OA reports when HW is idle to 
>> have the contex_id=0xffffffff.
>
> For these gens we use 0x1fffff as the context id. Before we return 
> reports to the user, we are setting context id to 0xffffffff for 
> invalid and irrelevant contexts.
>
> Thanks,
> Umesh


Sorry, I've been a bit out of the loop on OA reports lately.

I just noticed that the context valid bit is not checked on gen12 anymore.

The documentation is really horrible, but BSpec 52198 seems to indicate 
the bit is still around.


Could it be the source of the issue?


Thanks for your help :)


-Lionel


>>
>> I could remember wrong :/
>>
>>
>> -Lionel
>>
>>
>>>
>>> Thanks,
>>> Umesh
>>>
>>>>
>>>>
>>>> Thanks for spotting this!
>>>>
>>>>
>>>> -Lionel
>>>>
>>>>
>>>>>          break;
>>>>>      }
>>>>> @@ -1331,7 +1336,7 @@ static int oa_get_render_ctx_id(struct 
>>>>> i915_perf_stream *stream)
>>>>>          MISSING_CASE(INTEL_GEN(ce->engine->i915));
>>>>>      }
>>>>> -    ce->tag = stream->specific_ctx_id_mask;
>>>>> +    ce->tag = stream->specific_ctx_id;
>>>>>      DRM_DEBUG_DRIVER("filtering on ctx_id=0x%x ctx_id_mask=0x%x\n",
>>>>>               stream->specific_ctx_id,
>>>>
>>>>
>>

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

Re: [Intel-gfx] [PATCH] drm/i915/perf: Fix OA context id overlap with idle context id

[Umesh Nerlige Ramappa]

On Fri, Jan 31, 2020 at 01:00:54PM +0200, Lionel Landwerlin wrote:
>On 31/01/2020 01:54, Umesh Nerlige Ramappa wrote:
>>On Mon, Jan 27, 2020 at 11:16:32AM +0200, Lionel Landwerlin wrote:
>>
>>[snip]
>>
>>>>>>--- a/drivers/gpu/drm/i915/i915_perf.c
>>>>>>+++ b/drivers/gpu/drm/i915/i915_perf.c
>>>>>>@@ -1323,7 +1323,12 @@ static int 
>>>>>>oa_get_render_ctx_id(struct i915_perf_stream *stream)
>>>>>>     case 12: {
>>>>>>         stream->specific_ctx_id_mask =
>>>>>>             ((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << 
>>>>>>(GEN11_SW_CTX_ID_SHIFT - 32);
>>>>>>-        stream->specific_ctx_id = stream->specific_ctx_id_mask;
>>>>>>+        /* Pick an unused context id
>>>>>>+         * 0 - (NUM_CONTEXT_TAG - 1) are used by other contexts
>>>>>>+         * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context
>>>>>>+         */
>>>>>>+        stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID 
>>>>>>- 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
>>>>>>+        BUILD_BUG_ON((GEN12_MAX_CONTEXT_HW_ID - 1) < 
>>>>>>NUM_CONTEXT_TAG);
>>>>>
>>>>>
>>>>>Arg yeah, we can't use an id that has all bits to 1 because 
>>>>>that matches the idle value in the OA reports :/
>>>>>
>>>>>This also affects gen8-10 cases (afaik).
>>>>
>>>>For gen8-10, I did not see a specific definition for an idle 
>>>>context id.  The from/to idle context switches are indicated by 
>>>>dedicated bits in the CSB instead (from spec).
>>>
>>>
>>>I meant that I remember the periodic OA reports when HW is idle to 
>>>have the contex_id=0xffffffff.
>>
>>For these gens we use 0x1fffff as the context id. Before we return 
>>reports to the user, we are setting context id to 0xffffffff for 
>>invalid and irrelevant contexts.
>>
>>Thanks,
>>Umesh
>
>
>Sorry, I've been a bit out of the loop on OA reports lately.
>
>I just noticed that the context valid bit is not checked on gen12 anymore.
>
>The documentation is really horrible, but BSpec 52198 seems to 
>indicate the bit is still around.

I am looking at the first table describing the report ID in 52198 which 
has TGL next to it. I don't see a definition for this bit.

I will try to ask around to see if that's not the case.
>
>
>Could it be the source of the issue?
You mean - seeing 0xffffffff during idle in periodic reports?

Thanks,
Umesh

>
>
>Thanks for your help :)
>
>
>-Lionel
>
>
>>>
>>>I could remember wrong :/
>>>
>>>
>>>-Lionel
>>>
>>>
>>>>
>>>>Thanks,
>>>>Umesh
>>>>
>>>>>
>>>>>
>>>>>Thanks for spotting this!
>>>>>
>>>>>
>>>>>-Lionel
>>>>>
>>>>>
>>>>>>         break;
>>>>>>     }
>>>>>>@@ -1331,7 +1336,7 @@ static int oa_get_render_ctx_id(struct 
>>>>>>i915_perf_stream *stream)
>>>>>>         MISSING_CASE(INTEL_GEN(ce->engine->i915));
>>>>>>     }
>>>>>>-    ce->tag = stream->specific_ctx_id_mask;
>>>>>>+    ce->tag = stream->specific_ctx_id;
>>>>>>     DRM_DEBUG_DRIVER("filtering on ctx_id=0x%x ctx_id_mask=0x%x\n",
>>>>>>              stream->specific_ctx_id,
>>>>>
>>>>>
>>>
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx