drm/i915: Fix up locking around dumping requests lists

The debugfs dump of requests was confused about what state requires
the execlist lock versus the GuC lock. There was also a bunch of
duplicated messy code between it and the error capture code.

So refactor the hung request search into a re-usable function. And
reduce the span of the execlist state lock to only the execlist
specific code paths. In order to do that, also move the report of hold
count (which is an execlist only concept) from the top level dump
function to the lower level execlist specific function. Also, move the
execlist specific code into the execlist source file.

v2: Rename some functions and move to more appropriate files (Daniele).
v3: Rename new execlist dump function (Daniele)

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: 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/20230127002842.3169194-4-John.C.Harrison@Intel.com

1 files changed, 3 insertions, 23 deletions

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 9e2d17785a9a..b20bd6365615 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1596,35 +1596,15 @@ capture_engine(struct intel_engine_cs *engine,
 {
 	struct intel_engine_capture_vma *capture = NULL;
 	struct intel_engine_coredump *ee;
-	struct intel_context *ce;
+	struct intel_context *ce = NULL;
 	struct i915_request *rq = NULL;
-	unsigned long flags;
 
 	ee = intel_engine_coredump_alloc(engine, ALLOW_FAIL, dump_flags);
 	if (!ee)
 		return NULL;
 
-	ce = intel_engine_get_hung_context(engine);
-	if (ce) {
-		intel_engine_clear_hung_context(engine);
-		rq = intel_context_get_active_request(ce);
-		if (!rq || !i915_request_started(rq))
-			goto no_request_capture;
-	} else {
-		/*
-		 * Getting here with GuC enabled means it is a forced error capture
-		 * with no actual hang. So, no need to attempt the execlist search.
-		 */
-		if (!intel_uc_uses_guc_submission(&engine->gt->uc)) {
-			spin_lock_irqsave(&engine->sched_engine->lock, flags);
-			rq = intel_engine_execlist_find_hung_request(engine);
-			if (rq)
-				rq = i915_request_get_rcu(rq);
-			spin_unlock_irqrestore(&engine->sched_engine->lock,
-					       flags);
-		}
-	}
-	if (!rq)
+	intel_engine_get_hung_entity(engine, &ce, &rq);
+	if (!rq || !i915_request_started(rq))
 		goto no_request_capture;
 
 	capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL);