drm/i915/guc: Fix locking when searching for a hung request

[ Upstream commit 87b04e53daf806945c415e94de9f90943d434aed ]

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")
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Acked-by: Tvrtko Ursulin <tvrtko.ursulin@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: 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>
Link: https://patchwork.freedesktop.org/patch/msgid/20230127002842.3169194-2-John.C.Harrison@Intel.com
(cherry picked from commit d1c3717501bcf56536e8b8c1bdaf5cd5357f6bb2)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

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 1a23e90..2591620 100644 (file)
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -4587,6 +4587,8 @@ 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;
 
@@ -4603,10 +4605,18 @@ 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... */
@@ -4614,6 +4624,7 @@ 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);