diff mbox series

[v5,1/8] drm/i915/guc: Fix locking when searching for a hung request

Message ID 20230126005420.160070-2-John.C.Harrison@Intel.com (mailing list archive)
State New, archived
Headers show
Series Allow error capture without a request & fix locking issues | expand

Commit Message

John Harrison Jan. 26, 2023, 12:54 a.m. UTC
From: John Harrison <John.C.Harrison@Intel.com>

intel_guc_find_hung_context() was not acquiring the correct spinlock
before searching the request list. So fix that up. While at it, add
some extra whitespace padding for readability.

Fixes: dc0dad365c5e ("drm/i915/guc: Fix for error capture after full GPU reset with GuC")
Cc: John Harrison <John.C.Harrison@Intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Cc: Michael Cheng <michael.cheng@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Tejas Upadhyay <tejaskumarx.surendrakumar.upadhyay@intel.com>
Cc: Chris Wilson <chris.p.wilson@intel.com>
Cc: Bruce Chang <yu.bruce.chang@intel.com>
Cc: Alan Previn <alan.previn.teres.alexis@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: intel-gfx@lists.freedesktop.org
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
 drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

Comments

Daniele Ceraolo Spurio Jan. 26, 2023, 11:45 p.m. UTC | #1
On 1/25/2023 4:54 PM, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> intel_guc_find_hung_context() was not acquiring the correct spinlock
> before searching the request list. So fix that up. While at it, add
> some extra whitespace padding for readability.
>
> Fixes: dc0dad365c5e ("drm/i915/guc: Fix for error capture after full GPU reset with GuC")
> Cc: John Harrison <John.C.Harrison@Intel.com>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Jani Nikula <jani.nikula@linux.intel.com>
> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
> Cc: Matt Roper <matthew.d.roper@intel.com>
> Cc: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
> Cc: Michael Cheng <michael.cheng@intel.com>
> Cc: Lucas De Marchi <lucas.demarchi@intel.com>
> Cc: Tejas Upadhyay <tejaskumarx.surendrakumar.upadhyay@intel.com>
> Cc: Chris Wilson <chris.p.wilson@intel.com>
> Cc: Bruce Chang <yu.bruce.chang@intel.com>
> Cc: Alan Previn <alan.previn.teres.alexis@intel.com>
> Cc: Matthew Auld <matthew.auld@intel.com>
> Cc: intel-gfx@lists.freedesktop.org
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>

Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>

Daniele

> ---
>   drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 11 +++++++++++
>   1 file changed, 11 insertions(+)
>
> diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> index b436dd7f12e42..3b34a82d692be 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> @@ -4820,6 +4820,8 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine)
>   
>   	xa_lock_irqsave(&guc->context_lookup, flags);
>   	xa_for_each(&guc->context_lookup, index, ce) {
> +		bool found;
> +
>   		if (!kref_get_unless_zero(&ce->ref))
>   			continue;
>   
> @@ -4836,10 +4838,18 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine)
>   				goto next;
>   		}
>   
> +		found = false;
> +		spin_lock(&ce->guc_state.lock);
>   		list_for_each_entry(rq, &ce->guc_state.requests, sched.link) {
>   			if (i915_test_request_state(rq) != I915_REQUEST_ACTIVE)
>   				continue;
>   
> +			found = true;
> +			break;
> +		}
> +		spin_unlock(&ce->guc_state.lock);
> +
> +		if (found) {
>   			intel_engine_set_hung_context(engine, ce);
>   
>   			/* Can only cope with one hang at a time... */
> @@ -4847,6 +4857,7 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine)
>   			xa_lock(&guc->context_lookup);
>   			goto done;
>   		}
> +
>   next:
>   		intel_context_put(ce);
>   		xa_lock(&guc->context_lookup);
diff mbox series

Patch

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index b436dd7f12e42..3b34a82d692be 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -4820,6 +4820,8 @@  void intel_guc_find_hung_context(struct intel_engine_cs *engine)
 
 	xa_lock_irqsave(&guc->context_lookup, flags);
 	xa_for_each(&guc->context_lookup, index, ce) {
+		bool found;
+
 		if (!kref_get_unless_zero(&ce->ref))
 			continue;
 
@@ -4836,10 +4838,18 @@  void intel_guc_find_hung_context(struct intel_engine_cs *engine)
 				goto next;
 		}
 
+		found = false;
+		spin_lock(&ce->guc_state.lock);
 		list_for_each_entry(rq, &ce->guc_state.requests, sched.link) {
 			if (i915_test_request_state(rq) != I915_REQUEST_ACTIVE)
 				continue;
 
+			found = true;
+			break;
+		}
+		spin_unlock(&ce->guc_state.lock);
+
+		if (found) {
 			intel_engine_set_hung_context(engine, ce);
 
 			/* Can only cope with one hang at a time... */
@@ -4847,6 +4857,7 @@  void intel_guc_find_hung_context(struct intel_engine_cs *engine)
 			xa_lock(&guc->context_lookup);
 			goto done;
 		}
+
 next:
 		intel_context_put(ce);
 		xa_lock(&guc->context_lookup);