1 files changed, 47 insertions, 45 deletions

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 9d5d5a397b64..904f21e1380c 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1370,14 +1370,14 @@ static void engine_record_execlists(struct intel_engine_coredump *ee)
 }
 
 static bool record_context(struct i915_gem_context_coredump *e,
-			   const struct i915_request *rq)
+			   struct intel_context *ce)
 {
 	struct i915_gem_context *ctx;
 	struct task_struct *task;
 	bool simulated;
 
 	rcu_read_lock();
-	ctx = rcu_dereference(rq->context->gem_context);
+	ctx = rcu_dereference(ce->gem_context);
 	if (ctx && !kref_get_unless_zero(&ctx->ref))
 		ctx = NULL;
 	rcu_read_unlock();
@@ -1396,8 +1396,8 @@ static bool record_context(struct i915_gem_context_coredump *e,
 	e->guilty = atomic_read(&ctx->guilty_count);
 	e->active = atomic_read(&ctx->active_count);
 
-	e->total_runtime = intel_context_get_total_runtime_ns(rq->context);
-	e->avg_runtime = intel_context_get_avg_runtime_ns(rq->context);
+	e->total_runtime = intel_context_get_total_runtime_ns(ce);
+	e->avg_runtime = intel_context_get_avg_runtime_ns(ce);
 
 	simulated = i915_gem_context_no_error_capture(ctx);
 
@@ -1532,15 +1532,37 @@ intel_engine_coredump_alloc(struct intel_engine_cs *engine, gfp_t gfp, u32 dump_
 	return ee;
 }
 
+static struct intel_engine_capture_vma *
+engine_coredump_add_context(struct intel_engine_coredump *ee,
+			    struct intel_context *ce,
+			    gfp_t gfp)
+{
+	struct intel_engine_capture_vma *vma = NULL;
+
+	ee->simulated |= record_context(&ee->context, ce);
+	if (ee->simulated)
+		return NULL;
+
+	/*
+	 * We need to copy these to an anonymous buffer
+	 * as the simplest method to avoid being overwritten
+	 * by userspace.
+	 */
+	vma = capture_vma(vma, ce->ring->vma, "ring", gfp);
+	vma = capture_vma(vma, ce->state, "HW context", gfp);
+
+	return vma;
+}
+
 struct intel_engine_capture_vma *
 intel_engine_coredump_add_request(struct intel_engine_coredump *ee,
 				  struct i915_request *rq,
 				  gfp_t gfp)
 {
-	struct intel_engine_capture_vma *vma = NULL;
+	struct intel_engine_capture_vma *vma;
 
-	ee->simulated |= record_context(&ee->context, rq);
-	if (ee->simulated)
+	vma = engine_coredump_add_context(ee, rq->context, gfp);
+	if (!vma)
 		return NULL;
 
 	/*
@@ -1550,8 +1572,6 @@ intel_engine_coredump_add_request(struct intel_engine_coredump *ee,
 	 */
 	vma = capture_vma_snapshot(vma, rq->batch_res, gfp, "batch");
 	vma = capture_user(vma, rq, gfp);
-	vma = capture_vma(vma, rq->ring->vma, "ring", gfp);
-	vma = capture_vma(vma, rq->context->state, "HW context", gfp);
 
 	ee->rq_head = rq->head;
 	ee->rq_post = rq->postfix;
@@ -1596,54 +1616,36 @@ 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_find_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);
-			spin_unlock_irqrestore(&engine->sched_engine->lock,
-					       flags);
-		}
-	}
-	if (rq)
-		rq = i915_request_get_rcu(rq);
+	intel_engine_get_hung_entity(engine, &ce, &rq);
+	if (rq && !i915_request_started(rq))
+		drm_info(&engine->gt->i915->drm, "Got hung context on %s with active request %lld:%lld [0x%04X] not yet started\n",
+			 engine->name, rq->fence.context, rq->fence.seqno, ce->guc_id.id);
 
-	if (!rq)
-		goto no_request_capture;
-
-	capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL);
-	if (!capture) {
+	if (rq) {
+		capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL);
 		i915_request_put(rq);
-		goto no_request_capture;
+	} else if (ce) {
+		capture = engine_coredump_add_context(ee, ce, ATOMIC_MAYFAIL);
 	}
-	if (dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE)
-		intel_guc_capture_get_matching_node(engine->gt, ee, ce);
 
-	intel_engine_coredump_add_vma(ee, capture, compress);
-	i915_request_put(rq);
+	if (capture) {
+		intel_engine_coredump_add_vma(ee, capture, compress);
 
-	return ee;
+		if (dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE)
+			intel_guc_capture_get_matching_node(engine->gt, ee, ce);
+	} else {
+		kfree(ee);
+		ee = NULL;
+	}
 
-no_request_capture:
-	kfree(ee);
-	return NULL;
+	return ee;
 }
 
 static void