[Intel-gfx] [RFC 09/37] drm/i915/error: track, capture & print ringbuffer submission activity

[John.C.Harrison at Intel.com]

From: Dave Gordon <david.s.gordon at intel.com>

For: VIZ-2021
Signed-off-by: Dave Gordon <david.s.gordon at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h         |  2 ++
 drivers/gpu/drm/i915/i915_gem.c         | 11 +++++++++--
 drivers/gpu/drm/i915/i915_gpu_error.c   |  9 +++++++++
 drivers/gpu/drm/i915/intel_ringbuffer.h | 14 ++++++++++++++
 4 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 779fc70..9b4ab5d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -567,6 +567,8 @@ struct drm_i915_error_state {
 
 		u64 ctx_desc;
 
+		struct intel_ringbuffer req_ring;
+
 		struct drm_i915_error_object {
 			int page_count;
 			u64 gtt_offset;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ab6064e..785310c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2634,8 +2634,15 @@ void __i915_add_request(struct drm_i915_gem_request *request,
 	 */
 	request->batch_obj = obj;
 
-	request->emitted_jiffies = jiffies;
-	ring->last_submitted_seqno = request->seqno;
+	if (ring->last_submitted_ringbuf == ringbuf)
+		ringbuf->resubmission_count += 1;
+	else
+		ringbuf->resubmission_count = 1;
+	ring->last_submitted_ringbuf = ringbuf;
+	ringbuf->total_submission_count += 1;
+	ringbuf->last_submitted_tail = request->tail;
+	ringbuf->last_submitted_seqno = ring->last_submitted_seqno = request->seqno;
+	ringbuf->last_submitted_jiffies = request->emitted_jiffies = jiffies;
 	list_add_tail(&request->list, &ring->request_list);
 
 	trace_i915_gem_request_add(request);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index bafaadd..0697fc3 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -522,12 +522,20 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 		}
 
 		if ((obj = error->ring[i].req_ringbuffer)) {
+			struct intel_ringbuffer *irb = &error->ring[i].req_ring;
+
 			err_printf(m, "%s --- ringbuffer = 0x%08x; %d pages (ctx_desc 0x%08x_%08x)\n",
 				   dev_priv->ring[i].name,
 				   lower_32_bits(obj->gtt_offset),
 				   obj->page_count,
 				   upper_32_bits(error->ring[i].ctx_desc),
 				   lower_32_bits(error->ring[i].ctx_desc));
+			err_printf(m, "\t\tringbuffer head 0x%08x tail 0x%08x space 0x%08x lrh 0x%08x\n",
+				   irb->head, irb->tail, irb->space, irb->last_retired_head);
+			err_printf(m, "\t\t%llu submission(s), %d consecutive, last at %ld: tail 0x%08x seqno %08x (%d)\n",
+				   irb->total_submission_count, irb->resubmission_count,
+				   irb->last_submitted_jiffies, irb->last_submitted_tail,
+				   irb->last_submitted_seqno, irb->last_submitted_seqno);
 			print_error_obj(m, obj);
 		}
 
@@ -1163,6 +1171,7 @@ static void i915_gem_record_rings(struct drm_device *dev,
 		error->ring[i].ctx_desc = ctx_desc;
 		error->ring[i].req_ringbuffer =
 			i915_error_ggtt_object_create(dev_priv, rbuf->obj);
+		error->ring[i].req_ring = *rbuf;
 
 		error->ring[i].hws_page =
 			i915_error_ggtt_object_create(dev_priv, ring->status_page.obj);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index c472f8a..6bdc1ad 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -126,6 +126,19 @@ struct intel_ringbuffer {
 	 * we can detect new retirements.
 	 */
 	u32 last_retired_head;
+
+	/*
+	 * Consecutive resubmissions are opportunities for the h/w to do
+	 * a 'lite restore' rather than a full context switch. Let's note
+	 * when that happens, in case it's useful for hang diagnosis.
+	 */
+	u32 resubmission_count;
+	u64 total_submission_count;
+
+	/* Info about last time this ringbuffer was submitted (to GuC) */
+	unsigned long last_submitted_jiffies;
+	u32 last_submitted_seqno;
+	u32 last_submitted_tail;
 };
 
 struct	intel_context;
@@ -306,6 +319,7 @@ struct  intel_engine_cs {
 	 * inspecting request list.
 	 */
 	u32 last_submitted_seqno;
+	struct intel_ringbuffer *last_submitted_ringbuf;
 
 	/* deferred free list to allow unreferencing requests outside the driver */
 	struct list_head delayed_free_list;
-- 
1.9.1