[Intel-gfx] [PATCH 1/2] drm/i915: Record the in-flight requests at the time of a hang

[Chris Wilson]

Being able to tally the list of outstanding requests with the sequence
of commands in the ringbuffer is often useful evidence with respect to
driver corruption.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_debugfs.c |   24 +++++++++----
 drivers/gpu/drm/i915/i915_drv.h     |   17 +++++++---
 drivers/gpu/drm/i915/i915_irq.c     |   63 ++++++++++++++++++++++++++---------
 3 files changed, 75 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 88bda69..28089f7 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -745,7 +745,7 @@ static int i915_error_state(struct seq_file *m, void *unused)
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct drm_i915_error_state *error;
 	unsigned long flags;
-	int i, page, offset, elt;
+	int i, j, page, offset, elt;
 
 	spin_lock_irqsave(&dev_priv->error_lock, flags);
 	error = dev_priv->first_error;
@@ -789,10 +789,10 @@ static int i915_error_state(struct seq_file *m, void *unused)
 				    error->pinned_bo,
 				    error->pinned_bo_count);
 
-	for (i = 0; i < ARRAY_SIZE(error->batchbuffer); i++) {
-		if (error->batchbuffer[i]) {
-			struct drm_i915_error_object *obj = error->batchbuffer[i];
+	for (i = 0; i < ARRAY_SIZE(error->ring); i++) {
+		struct drm_i915_error_object *obj;
 
+		if ((obj = error->ring[i].batchbuffer)) {
 			seq_printf(m, "%s --- gtt_offset = 0x%08x\n",
 				   dev_priv->ring[i].name,
 				   obj->gtt_offset);
@@ -804,11 +804,19 @@ static int i915_error_state(struct seq_file *m, void *unused)
 				}
 			}
 		}
-	}
 
-	for (i = 0; i < ARRAY_SIZE(error->ringbuffer); i++) {
-		if (error->ringbuffer[i]) {
-			struct drm_i915_error_object *obj = error->ringbuffer[i];
+		if (error->ring[i].num_requests) {
+			seq_printf(m, "%s --- %d requests\n",
+				   dev_priv->ring[i].name,
+				   error->ring[i].num_requests);
+			for (j = 0; j < error->ring[i].num_requests; j++) {
+				seq_printf(m, "%d: emitted %ld\n",
+					  error->ring[i].requests[j].seqno,
+					  error->ring[i].requests[j].jiffies);
+			}
+		}
+
+		if ((obj = error->ring[i].ringbuffer)) {
 			seq_printf(m, "%s --- ringbuffer = 0x%08x\n",
 				   dev_priv->ring[i].name,
 				   obj->gtt_offset);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e8e1b85..8f6ae11 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -172,11 +172,18 @@ struct drm_i915_error_state {
 	u32 faddr[I915_NUM_RINGS];
 	u64 fence[I915_MAX_NUM_FENCES];
 	struct timeval time;
-	struct drm_i915_error_object {
-		int page_count;
-		u32 gtt_offset;
-		u32 *pages[0];
-	} *ringbuffer[I915_NUM_RINGS], *batchbuffer[I915_NUM_RINGS];
+	struct drm_i915_error_ring {
+		struct drm_i915_error_object {
+			int page_count;
+			u32 gtt_offset;
+			u32 *pages[0];
+		} *ringbuffer, *batchbuffer;
+		struct drm_i915_error_request {
+			long jiffies;
+			u32 seqno;
+		} *requests;
+		int num_requests;
+	} ring[I915_NUM_RINGS];
 	struct drm_i915_error_buffer {
 		u32 size;
 		u32 name;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 6266f57..24f8928 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -790,11 +790,11 @@ i915_error_state_free(struct kref *error_ref)
 							  typeof(*error), ref);
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(error->batchbuffer); i++)
-		i915_error_object_free(error->batchbuffer[i]);
-
-	for (i = 0; i < ARRAY_SIZE(error->ringbuffer); i++)
-		i915_error_object_free(error->ringbuffer[i]);
+	for (i = 0; i < ARRAY_SIZE(error->ring); i++) {
+		i915_error_object_free(error->ring[i].batchbuffer);
+		i915_error_object_free(error->ring[i].ringbuffer);
+		kfree(error->ring[i].requests);
+	}
 
 	kfree(error->active_bo);
 	kfree(error->overlay);
@@ -929,6 +929,47 @@ static void i915_record_ring_state(struct drm_device *dev,
 	error->tail[ring->id] = I915_READ_TAIL(ring);
 }
 
+static void i915_gem_record_rings(struct drm_device *dev,
+				  struct drm_i915_error_state *error)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_gem_request *request;
+	int i, count;
+
+	for (i = 0; i < I915_NUM_RINGS; i++) {
+		struct intel_ring_buffer *ring = &dev_priv->ring[i];
+
+		error->ring[i].batchbuffer =
+			i915_error_first_batchbuffer(dev_priv, ring);
+
+		error->ring[i].ringbuffer =
+			i915_error_object_create(dev_priv, ring->obj);
+
+		count = 0;
+		list_for_each_entry(request, &ring->request_list, list)
+			count++;
+
+		error->ring[i].num_requests = count;
+		error->ring[i].requests =
+			kcalloc(count,
+				sizeof(struct drm_i915_error_request),
+				GFP_ATOMIC);
+		if (error->ring[i].requests == NULL) {
+			error->ring[i].requests = 0;
+			continue;
+		}
+
+		count = 0;
+		list_for_each_entry(request, &ring->request_list, list) {
+			struct drm_i915_error_request *erq;
+
+			erq = &error->ring[i].requests[count++];
+			erq->seqno = request->seqno;
+			erq->jiffies = request->emitted_jiffies;
+		}
+	}
+}
+
 /**
  * i915_capture_error_state - capture an error record for later analysis
  * @dev: drm device
@@ -980,17 +1021,7 @@ static void i915_capture_error_state(struct drm_device *dev)
 		i915_record_ring_state(dev, error, &dev_priv->ring[VCS]);
 
 	i915_gem_record_fences(dev, error);
-
-	/* Record the active batch and ring buffers */
-	for (i = 0; i < I915_NUM_RINGS; i++) {
-		error->batchbuffer[i] =
-			i915_error_first_batchbuffer(dev_priv,
-						     &dev_priv->ring[i]);
-
-		error->ringbuffer[i] =
-			i915_error_object_create(dev_priv,
-						 dev_priv->ring[i].obj);
-	}
+	i915_gem_record_rings(dev, error);
 
 	/* Record buffers on the active and pinned lists. */
 	error->active_bo = NULL;
-- 
1.7.9