[PATCH] drm/i915: Park before resetting the submission backend

[PATCH] drm/i915: Park before resetting the submission backend

[Chris Wilson]

As different backends may have different park/unpark callbacks, we
should only ever switch backends (reset_default_submission on wedge
recovery, or on enabling the guc) while parked.

v2: Remove the assert from the guc code, as we are currently trying to
modify the engine vfuncs pointer on a live system after reset (not just
wedging). We will just have to hope that the system is balanced.
v3: Rebase onto __i915_gem_park and improve grammar.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c        | 15 ++++++++++++---
 drivers/gpu/drm/i915/intel_engine_cs.c |  3 +++
 2 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 28ab0beff86c..dd3e292ba243 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -144,8 +144,6 @@ static u32 __i915_gem_park(struct drm_i915_private *i915)
 	if (!i915->gt.awake)
 		return I915_EPOCH_INVALID;
 
-	GEM_BUG_ON(i915->gt.epoch == I915_EPOCH_INVALID);
-
 	/*
 	 * Be paranoid and flush a concurrent interrupt to make sure
 	 * we don't reactivate any irq tasklets after parking.
@@ -173,6 +171,7 @@ static u32 __i915_gem_park(struct drm_i915_private *i915)
 
 	intel_runtime_pm_put(i915);
 
+	GEM_BUG_ON(i915->gt.epoch == I915_EPOCH_INVALID);
 	return i915->gt.epoch;
 }
 
@@ -3435,7 +3434,17 @@ bool i915_gem_unset_wedged(struct drm_i915_private *i915)
 		}
 	}
 	i915_retire_requests(i915);
-	GEM_BUG_ON(i915->gt.active_requests);
+
+	/*
+	 * Park before disengaging the old submit mechanism as different
+	 * backends may have different park/unpack callbacks.
+	 *
+	 * We are idle; the idle-worker will be queued, but we need to run
+	 * it now. As we already hold the struct mutex, we can park the GPU
+	 * right away, letting the lazy worker see that we are already active
+	 * again by the time it acquires the mutex.
+	 */
+	__i915_gem_park(i915);
 
 	/*
 	 * Undo nop_submit_request. We prevent all new i915 requests from
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 12486d8f534b..b4ea77a2896c 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1651,6 +1651,9 @@ void intel_engines_reset_default_submission(struct drm_i915_private *i915)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
+	/* Must be parked first! */
+	GEM_BUG_ON(i915->gt.awake);
+
 	for_each_engine(engine, i915, id)
 		engine->set_default_submission(engine);
 }
-- 
2.17.0

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

Re: [PATCH] drm/i915: Park before resetting the submission backend

[Sagar Arun Kamble]

On 4/9/2018 3:48 PM, Chris Wilson wrote:
> As different backends may have different park/unpark callbacks, we
> should only ever switch backends (reset_default_submission on wedge
> recovery, or on enabling the guc) while parked.
>
> v2: Remove the assert from the guc code, as we are currently trying to
> modify the engine vfuncs pointer on a live system after reset (not just
> wedging). We will just have to hope that the system is balanced.
> v3: Rebase onto __i915_gem_park and improve grammar.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
> Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Sagar Arun Kamble <sagar.a.kamble@intel.com>
> ---
>   drivers/gpu/drm/i915/i915_gem.c        | 15 ++++++++++++---
>   drivers/gpu/drm/i915/intel_engine_cs.c |  3 +++
>   2 files changed, 15 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 28ab0beff86c..dd3e292ba243 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -144,8 +144,6 @@ static u32 __i915_gem_park(struct drm_i915_private *i915)
>   	if (!i915->gt.awake)
>   		return I915_EPOCH_INVALID;
>   
> -	GEM_BUG_ON(i915->gt.epoch == I915_EPOCH_INVALID);
> -
>   	/*
>   	 * Be paranoid and flush a concurrent interrupt to make sure
>   	 * we don't reactivate any irq tasklets after parking.
> @@ -173,6 +171,7 @@ static u32 __i915_gem_park(struct drm_i915_private *i915)
>   
>   	intel_runtime_pm_put(i915);
>   
> +	GEM_BUG_ON(i915->gt.epoch == I915_EPOCH_INVALID);
>   	return i915->gt.epoch;
>   }
>   
> @@ -3435,7 +3434,17 @@ bool i915_gem_unset_wedged(struct drm_i915_private *i915)
>   		}
>   	}
>   	i915_retire_requests(i915);
> -	GEM_BUG_ON(i915->gt.active_requests);
> +
> +	/*
> +	 * Park before disengaging the old submit mechanism as different
> +	 * backends may have different park/unpack callbacks.
> +	 *
> +	 * We are idle; the idle-worker will be queued, but we need to run
> +	 * it now. As we already hold the struct mutex, we can park the GPU
> +	 * right away, letting the lazy worker see that we are already active
> +	 * again by the time it acquires the mutex.
> +	 */
> +	__i915_gem_park(i915);
>   
>   	/*
>   	 * Undo nop_submit_request. We prevent all new i915 requests from
> diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
> index 12486d8f534b..b4ea77a2896c 100644
> --- a/drivers/gpu/drm/i915/intel_engine_cs.c
> +++ b/drivers/gpu/drm/i915/intel_engine_cs.c
> @@ -1651,6 +1651,9 @@ void intel_engines_reset_default_submission(struct drm_i915_private *i915)
>   	struct intel_engine_cs *engine;
>   	enum intel_engine_id id;
>   
> +	/* Must be parked first! */
> +	GEM_BUG_ON(i915->gt.awake);
> +
>   	for_each_engine(engine, i915, id)
>   		engine->set_default_submission(engine);
>   }

-- 
Thanks,
Sagar

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

Re: [PATCH] drm/i915: Park before resetting the submission backend

[Chris Wilson]

Quoting Sagar Arun Kamble (2018-04-09 11:38:34)
> 
> 
> On 4/9/2018 3:48 PM, Chris Wilson wrote:
> > As different backends may have different park/unpark callbacks, we
> > should only ever switch backends (reset_default_submission on wedge
> > recovery, or on enabling the guc) while parked.
> >
> > v2: Remove the assert from the guc code, as we are currently trying to
> > modify the engine vfuncs pointer on a live system after reset (not just
> > wedging). We will just have to hope that the system is balanced.
> > v3: Rebase onto __i915_gem_park and improve grammar.
> >
> > Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> > Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
> > Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
> > Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> > Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
> Reviewed-by: Sagar Arun Kamble <sagar.a.kamble@intel.com>

Michal, do you want to take this and merge it into your series?
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Park before resetting the submission backend

[Michal Wajdeczko]

On Mon, 09 Apr 2018 12:41:22 +0200, Chris Wilson  
<chris@chris-wilson.co.uk> wrote:

> Quoting Sagar Arun Kamble (2018-04-09 11:38:34)
>>
>>
>> On 4/9/2018 3:48 PM, Chris Wilson wrote:
>> > As different backends may have different park/unpark callbacks, we
>> > should only ever switch backends (reset_default_submission on wedge
>> > recovery, or on enabling the guc) while parked.
>> >
>> > v2: Remove the assert from the guc code, as we are currently trying to
>> > modify the engine vfuncs pointer on a live system after reset (not  
>> just
>> > wedging). We will just have to hope that the system is balanced.
>> > v3: Rebase onto __i915_gem_park and improve grammar.
>> >
>> > Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
>> > Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
>> > Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
>> > Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>> > Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
>> Reviewed-by: Sagar Arun Kamble <sagar.a.kamble@intel.com>
>
> Michal, do you want to take this and merge it into your series?

Yes, I can take it.
Then we will see results from CI.IGT with GuC enabled.

/Michal

ps. this patch is also

Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✗ Fi.CI.BAT: warning for drm/i915: Park before resetting the submission backend (rev2)

[Patchwork]

== Series Details ==

Series: drm/i915: Park before resetting the submission backend (rev2)
URL   : https://patchwork.freedesktop.org/series/41202/
State : warning

== Summary ==

Series 41202v2 drm/i915: Park before resetting the submission backend
https://patchwork.freedesktop.org/api/1.0/series/41202/revisions/2/mbox/

---- Possible new issues:

Test gem_exec_gttfill:
        Subgroup basic:
                pass       -> SKIP       (fi-pnv-d510)

---- Known issues:

Test debugfs_test:
        Subgroup read_all_entries:
                incomplete -> PASS       (fi-snb-2520m) fdo#103713 +1
Test gem_ctx_param:
        Subgroup basic-default:
                incomplete -> PASS       (fi-cnl-y3) fdo#105086
Test kms_chamelium:
        Subgroup dp-edid-read:
                fail       -> PASS       (fi-kbl-7500u) fdo#102505
Test kms_flip:
        Subgroup basic-flip-vs-wf_vblank:
                fail       -> PASS       (fi-cfl-s3) fdo#100368

fdo#103713 https://bugs.freedesktop.org/show_bug.cgi?id=103713
fdo#105086 https://bugs.freedesktop.org/show_bug.cgi?id=105086
fdo#102505 https://bugs.freedesktop.org/show_bug.cgi?id=102505
fdo#100368 https://bugs.freedesktop.org/show_bug.cgi?id=100368

fi-bdw-5557u     total:285  pass:264  dwarn:0   dfail:0   fail:0   skip:21  time:434s
fi-bdw-gvtdvm    total:285  pass:261  dwarn:0   dfail:0   fail:0   skip:24  time:444s
fi-blb-e6850     total:285  pass:220  dwarn:1   dfail:0   fail:0   skip:64  time:383s
fi-bsw-n3050     total:285  pass:239  dwarn:0   dfail:0   fail:0   skip:46  time:543s
fi-bwr-2160      total:285  pass:180  dwarn:0   dfail:0   fail:0   skip:105 time:296s
fi-bxt-dsi       total:285  pass:255  dwarn:0   dfail:0   fail:0   skip:30  time:513s
fi-bxt-j4205     total:285  pass:256  dwarn:0   dfail:0   fail:0   skip:29  time:514s
fi-byt-j1900     total:285  pass:250  dwarn:0   dfail:0   fail:0   skip:35  time:518s
fi-byt-n2820     total:285  pass:246  dwarn:0   dfail:0   fail:0   skip:39  time:505s
fi-cfl-8700k     total:285  pass:257  dwarn:0   dfail:0   fail:0   skip:28  time:412s
fi-cfl-s3        total:285  pass:259  dwarn:0   dfail:0   fail:0   skip:26  time:562s
fi-cfl-u         total:285  pass:259  dwarn:0   dfail:0   fail:0   skip:26  time:512s
fi-cnl-y3        total:285  pass:259  dwarn:0   dfail:0   fail:0   skip:26  time:590s
fi-elk-e7500     total:285  pass:226  dwarn:0   dfail:0   fail:0   skip:59  time:426s
fi-gdg-551       total:285  pass:176  dwarn:0   dfail:0   fail:1   skip:108 time:314s
fi-glk-1         total:285  pass:257  dwarn:0   dfail:0   fail:0   skip:28  time:535s
fi-glk-j4005     total:285  pass:256  dwarn:0   dfail:0   fail:0   skip:29  time:485s
fi-hsw-4770      total:285  pass:258  dwarn:0   dfail:0   fail:0   skip:27  time:405s
fi-ilk-650       total:285  pass:225  dwarn:0   dfail:0   fail:0   skip:60  time:422s
fi-ivb-3520m     total:285  pass:256  dwarn:0   dfail:0   fail:0   skip:29  time:464s
fi-ivb-3770      total:285  pass:252  dwarn:0   dfail:0   fail:0   skip:33  time:438s
fi-kbl-7500u     total:285  pass:260  dwarn:1   dfail:0   fail:0   skip:24  time:474s
fi-kbl-7567u     total:285  pass:265  dwarn:0   dfail:0   fail:0   skip:20  time:466s
fi-kbl-r         total:285  pass:258  dwarn:0   dfail:0   fail:0   skip:27  time:507s
fi-pnv-d510      total:285  pass:219  dwarn:1   dfail:0   fail:0   skip:65  time:644s
fi-skl-6260u     total:285  pass:265  dwarn:0   dfail:0   fail:0   skip:20  time:442s
fi-skl-6600u     total:285  pass:258  dwarn:0   dfail:0   fail:0   skip:27  time:532s
fi-skl-6700k2    total:285  pass:261  dwarn:0   dfail:0   fail:0   skip:24  time:500s
fi-skl-6770hq    total:285  pass:265  dwarn:0   dfail:0   fail:0   skip:20  time:506s
fi-skl-guc       total:285  pass:257  dwarn:0   dfail:0   fail:0   skip:28  time:426s
fi-skl-gvtdvm    total:285  pass:262  dwarn:0   dfail:0   fail:0   skip:23  time:444s
fi-snb-2520m     total:242  pass:208  dwarn:0   dfail:0   fail:0   skip:33 
fi-snb-2600      total:285  pass:245  dwarn:0   dfail:0   fail:0   skip:40  time:408s

1be073153147c5c39cdcbdfdeb4e2595ba595bf7 drm-tip: 2018y-04m-07d-22h-26m-31s UTC integration manifest
03338d1167d7 drm/i915: Park before resetting the submission backend

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_8637/issues.html
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Park before resetting the submission backend

[Chris Wilson]

Quoting Chris Wilson (2018-04-05 11:57:22)
> As different backends may have different park/unpark callbacks, we
> should only ever switch backends (reset_default_submission on wedge
> recovery, or on enabling the guc) while parked.

Last in series, missing the series... Sorry for the noise,
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH] drm/i915: Park before resetting the submission backend

[Chris Wilson]

As different backends may have different park/unpark callbacks, we
should only ever switch backends (reset_default_submission on wedge
recovery, or on enabling the guc) while parked.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c             | 11 +++++++++++
 drivers/gpu/drm/i915/intel_engine_cs.c      |  3 +++
 drivers/gpu/drm/i915/intel_guc_submission.c |  1 +
 3 files changed, 15 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index e148db310ea6..e2880de2fc7e 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3380,6 +3380,17 @@ bool i915_gem_unset_wedged(struct drm_i915_private *i915)
 	i915_retire_requests(i915);
 	GEM_BUG_ON(i915->gt.active_requests);
 
+	/*
+	 * Park before disengaging the old submit mechanism as different
+	 * backends may have different park/unpack callbacks.
+	 *
+	 * We are idle; the idle-worker will be queued, but we need to run
+	 * it now. As we already hold the struct mutex, we can get park
+	 * the GPU right away, letting the lazy worker see that we are
+	 * already active again by the time it acquires the mutex.
+	 */
+	i915_gem_park(i915);
+
 	/*
 	 * Undo nop_submit_request. We prevent all new i915 requests from
 	 * being queued (by disallowing execbuf whilst wedged) so having
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 12486d8f534b..b4ea77a2896c 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1651,6 +1651,9 @@ void intel_engines_reset_default_submission(struct drm_i915_private *i915)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
+	/* Must be parked first! */
+	GEM_BUG_ON(i915->gt.awake);
+
 	for_each_engine(engine, i915, id)
 		engine->set_default_submission(engine);
 }
diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 97121230656c..225fa3927a02 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -1243,6 +1243,7 @@ int intel_guc_submission_enable(struct intel_guc *guc)
 	/* Take over from manual control of ELSP (execlists) */
 	guc_interrupts_capture(dev_priv);
 
+	GEM_BUG_ON(dev_priv->gt.awake); /* Must be idle switching park/unpark */
 	for_each_engine(engine, dev_priv, id) {
 		struct intel_engine_execlists * const execlists =
 			&engine->execlists;
-- 
2.16.3

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