drm/i915/guc: Fix for error capture after full GPU reset with GuC

In the case of a full GPU reset (e.g. because GuC has died or because
GuC's hang detection has been disabled), the driver can't rely on GuC
reporting the guilty context. Instead, the driver needs to scan all
active contexts and find one that is currently executing, as per the
execlist mode behaviour. In GuC mode, this scan is different to
execlist mode as the active request list is handled very differently.

Similarly, the request state dump in debugfs needs to be handled
differently when in GuC submission mode.

Also refactured some of the request scanning code to avoid duplication
across the multiple code paths that are now replicating it.

Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210727002348.97202-20-matthew.brost@intel.com

1 files changed, 94 insertions, 46 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 0da7868c5a13..dea0e522c5c7 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1684,6 +1684,98 @@ static void print_properties(struct intel_engine_cs *engine,
 			   read_ul(&engine->defaults, p->offset));
 }
 
+static void engine_dump_request(struct i915_request *rq, struct drm_printer *m, const char *msg)
+{
+	struct intel_timeline *tl = get_timeline(rq);
+
+	i915_request_show(m, rq, msg, 0);
+
+	drm_printf(m, "\t\tring->start:  0x%08x\n",
+		   i915_ggtt_offset(rq->ring->vma));
+	drm_printf(m, "\t\tring->head:   0x%08x\n",
+		   rq->ring->head);
+	drm_printf(m, "\t\tring->tail:   0x%08x\n",
+		   rq->ring->tail);
+	drm_printf(m, "\t\tring->emit:   0x%08x\n",
+		   rq->ring->emit);
+	drm_printf(m, "\t\tring->space:  0x%08x\n",
+		   rq->ring->space);
+
+	if (tl) {
+		drm_printf(m, "\t\tring->hwsp:   0x%08x\n",
+			   tl->hwsp_offset);
+		intel_timeline_put(tl);
+	}
+
+	print_request_ring(m, rq);
+
+	if (rq->context->lrc_reg_state) {
+		drm_printf(m, "Logical Ring Context:\n");
+		hexdump(m, rq->context->lrc_reg_state, PAGE_SIZE);
+	}
+}
+
+void intel_engine_dump_active_requests(struct list_head *requests,
+				       struct i915_request *hung_rq,
+				       struct drm_printer *m)
+{
+	struct i915_request *rq;
+	const char *msg;
+	enum i915_request_state state;
+
+	list_for_each_entry(rq, requests, sched.link) {
+		if (rq == hung_rq)
+			continue;
+
+		state = i915_test_request_state(rq);
+		if (state < I915_REQUEST_QUEUED)
+			continue;
+
+		if (state == I915_REQUEST_ACTIVE)
+			msg = "\t\tactive on engine";
+		else
+			msg = "\t\tactive in queue";
+
+		engine_dump_request(rq, m, msg);
+	}
+}
+
+static void engine_dump_active_requests(struct intel_engine_cs *engine, struct drm_printer *m)
+{
+	struct i915_request *hung_rq = NULL;
+	struct intel_context *ce;
+	bool guc;
+
+	/*
+	 * No need for an engine->irq_seqno_barrier() before the seqno reads.
+	 * The GPU is still running so requests are still executing and any
+	 * hardware reads will be out of date by the time they are reported.
+	 * But the intention here is just to report an instantaneous snapshot
+	 * so that's fine.
+	 */
+	lockdep_assert_held(&engine->sched_engine->lock);
+
+	drm_printf(m, "\tRequests:\n");
+
+	guc = intel_uc_uses_guc_submission(&engine->gt->uc);
+	if (guc) {
+		ce = intel_engine_get_hung_context(engine);
+		if (ce)
+			hung_rq = intel_context_find_active_request(ce);
+	} else {
+		hung_rq = intel_engine_execlist_find_hung_request(engine);
+	}
+
+	if (hung_rq)
+		engine_dump_request(hung_rq, m, "\t\thung");
+
+	if (guc)
+		intel_guc_dump_active_requests(engine, hung_rq, m);
+	else
+		intel_engine_dump_active_requests(&engine->sched_engine->requests,
+						  hung_rq, m);
+}
+
 void intel_engine_dump(struct intel_engine_cs *engine,
 		       struct drm_printer *m,
 		       const char *header, ...)
@@ -1728,39 +1820,9 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		   i915_reset_count(error));
 	print_properties(engine, m);
 
-	drm_printf(m, "\tRequests:\n");
-
 	spin_lock_irqsave(&engine->sched_engine->lock, flags);
-	rq = intel_engine_execlist_find_hung_request(engine);
-	if (rq) {
-		struct intel_timeline *tl = get_timeline(rq);
+	engine_dump_active_requests(engine, m);
 
-		i915_request_show(m, rq, "\t\tactive ", 0);
-
-		drm_printf(m, "\t\tring->start:  0x%08x\n",
-			   i915_ggtt_offset(rq->ring->vma));
-		drm_printf(m, "\t\tring->head:   0x%08x\n",
-			   rq->ring->head);
-		drm_printf(m, "\t\tring->tail:   0x%08x\n",
-			   rq->ring->tail);
-		drm_printf(m, "\t\tring->emit:   0x%08x\n",
-			   rq->ring->emit);
-		drm_printf(m, "\t\tring->space:  0x%08x\n",
-			   rq->ring->space);
-
-		if (tl) {
-			drm_printf(m, "\t\tring->hwsp:   0x%08x\n",
-				   tl->hwsp_offset);
-			intel_timeline_put(tl);
-		}
-
-		print_request_ring(m, rq);
-
-		if (rq->context->lrc_reg_state) {
-			drm_printf(m, "Logical Ring Context:\n");
-			hexdump(m, rq->context->lrc_reg_state, PAGE_SIZE);
-		}
-	}
 	drm_printf(m, "\tOn hold?: %lu\n",
 		   list_count(&engine->sched_engine->hold));
 	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
@@ -1834,13 +1896,6 @@ intel_engine_create_virtual(struct intel_engine_cs **siblings,
 	return siblings[0]->cops->create_virtual(siblings, count);
 }
 
-static bool match_ring(struct i915_request *rq)
-{
-	u32 ring = ENGINE_READ(rq->engine, RING_START);
-
-	return ring == i915_ggtt_offset(rq->ring->vma);
-}
-
 struct i915_request *
 intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine)
 {
@@ -1884,14 +1939,7 @@ intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine)
 
 	list_for_each_entry(request, &engine->sched_engine->requests,
 			    sched.link) {
-		if (__i915_request_is_complete(request))
-			continue;
-
-		if (!__i915_request_has_started(request))
-			continue;
-
-		/* More than one preemptible request may match! */
-		if (!match_ring(request))
+		if (i915_test_request_state(request) != I915_REQUEST_ACTIVE)
 			continue;
 
 		active = request;