[Intel-gfx] [RFC 9/9] drm/i915: Add sync support to the scheduler statistics and status dump

[John.C.Harrison at Intel.com]

From: John Harrison <John.C.Harrison at Intel.com>

There are useful statistics and debug information about fences that
can be returned via the scheduler's existing reporting mechanisms
(sysfs and debug output). These changes were previously part of the
patches that originally added those mechanisms. However, as the sync
framework has now been rebased to after the scheduler patches, they
must now be done as a separate patch on top.

For: VIZ-1587
Signed-off-by: John Harrison <John.C.Harrison at Intel.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c        |  4 ++++
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |  8 +++++++-
 drivers/gpu/drm/i915/i915_scheduler.c      | 20 ++++++++++++++++----
 drivers/gpu/drm/i915/i915_scheduler.h      |  5 +++++
 4 files changed, 32 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index a99f9c5..c1e1bcd 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3712,6 +3712,10 @@ static int i915_scheduler_info(struct seq_file *m, void *unused)
 	PRINT_VAR("  ExecEarly retry",      "u", stats[r].exec_early);
 	PRINT_VAR("  ExecFinal requeue",    "u", stats[r].exec_again);
 	PRINT_VAR("  ExecFinal killed",     "u", stats[r].exec_dead);
+	PRINT_VAR("  Fence wait",           "u", stats[r].fence_wait);
+	PRINT_VAR("  Fence wait again",     "u", stats[r].fence_again);
+	PRINT_VAR("  Fence wait ignore",    "u", stats[r].fence_ignore);
+	PRINT_VAR("  Fence supplied",       "u", stats[r].fence_got);
 	PRINT_VAR("  Hung flying",          "u", stats[r].kill_flying);
 	PRINT_VAR("  Hung queued",          "u", stats[r].kill_queued);
 	seq_putc(m, '\n');
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 8232a02..252532b 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1418,6 +1418,8 @@ eb_get_batch(struct eb_vmas *eb)
  */
 static int i915_early_fence_wait(struct intel_engine_cs *ring, int fence_fd)
 {
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	struct i915_scheduler *scheduler = dev_priv->scheduler;
 	struct sync_fence *fence;
 	int ret = 0;
 
@@ -1439,8 +1441,12 @@ static int i915_early_fence_wait(struct intel_engine_cs *ring, int fence_fd)
 	 * because the the mutex lock has not yet been acquired and
 	 * the wait is interruptible.
 	 */
-	if (!i915_safe_to_ignore_fence(ring, fence))
+	if (i915_safe_to_ignore_fence(ring, fence))
+		scheduler->stats[ring->id].fence_ignore++;
+	else {
+		scheduler->stats[ring->id].fence_wait++;
 		ret = sync_fence_wait(fence, -1);
+	}
 
 	sync_fence_put(fence);
 	return ret;
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 5228df7..5e3e85a 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -274,6 +274,9 @@ int i915_scheduler_queue_execbuffer(struct i915_scheduler_queue_entry *qe)
 
 	WARN_ON(!scheduler);
 
+	if (qe->params.fence_wait)
+		scheduler->stats[ring->id].fence_got++;
+
 	if (i915.scheduler_override & i915_so_direct_submit) {
 		int ret;
 
@@ -912,7 +915,7 @@ static int i915_scheduler_dump_locked(struct intel_engine_cs *ring,
 					deps++;
 
 			DRM_DEBUG_DRIVER("<%s>   %c:%02d> uniq = %d, seqno"
-					 " = %d/%s, deps = %d / %d, %s [pri = "
+					 " = %d/%s, deps = %d / %d, fence = %p/%d, %s [pri = "
 					 "%4d]\n", ring->name,
 					 i915_scheduler_queue_status_chr(node->status),
 					 count,
@@ -920,6 +923,8 @@ static int i915_scheduler_dump_locked(struct intel_engine_cs *ring,
 					 node->params.request->seqno,
 					 node->params.ring->name,
 					 deps, node->num_deps,
+					 node->params.fence_wait,
+					 node->params.fence_wait ? sync_fence_is_signaled(node->params.fence_wait) : 0,
 					 i915_qe_state_str(node),
 					 node->priority);
 
@@ -1205,15 +1210,20 @@ static void i915_scheduler_wait_fence_signaled(struct sync_fence *fence,
 static bool i915_scheduler_async_fence_wait(struct drm_device *dev,
 				     struct i915_scheduler_queue_entry *node)
 {
+	struct drm_i915_private         *dev_priv = node->params.ring->dev->dev_private;
+	struct i915_scheduler           *scheduler = dev_priv->scheduler;
 	struct i915_sync_fence_waiter	*fence_waiter;
 	struct sync_fence		*fence = node->params.fence_wait;
 	int				signaled;
 	bool				success = true;
 
-	if ((node->flags & i915_qef_fence_waiting) == 0)
+	if ((node->flags & i915_qef_fence_waiting) == 0) {
 		node->flags |= i915_qef_fence_waiting;
-	else
+		scheduler->stats[node->params.ring->id].fence_wait++;
+	} else {
+		scheduler->stats[node->params.ring->id].fence_again++;
 		return true;
+	}
 
 	if (fence == NULL)
 		return false;
@@ -1280,8 +1290,10 @@ static int i915_scheduler_pop_from_queue_locked(struct intel_engine_cs *ring,
 		else
 			signalled = true;
 
-		if (!signalled)
+		if (!signalled) {
 			signalled = i915_safe_to_ignore_fence(ring, node->params.fence_wait);
+			scheduler->stats[node->params.ring->id].fence_ignore++;
+		}
 
 		has_local  = false;
 		has_remote = false;
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index 408958f..7622963 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -100,6 +100,11 @@ struct i915_scheduler_stats {
 	uint32_t            exec_dead;
 	uint32_t            kill_flying;
 	uint32_t            kill_queued;
+
+	uint32_t            fence_wait;
+	uint32_t            fence_again;
+	uint32_t            fence_ignore;
+	uint32_t            fence_got;
 };
 
 struct i915_scheduler {
-- 
1.9.1