[Intel-gfx] [RFC 02/13] drm/i915: Keep a count of requests waiting for a slot on GPU

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin at intel.com>

Keep a per-engine number of runnable (waiting for GPU time) requests.

We choose to mange the runnable counter at the backend level instead of at
the request submit_notify callback. The latter would be more consolidated
and less code, but it would require making the counter either atomic_t or
taking the engine->timeline->lock in submit_notify. So the choice is to do
it at the backend level for the benefit of fewer atomic instructions.

v2:
 * Move queued increment from insert_request to execlist_submit_request to
   avoid bumping when re-ordering for priority.
 * Support the counter on the ringbuffer submission path as well, albeit
   just notionally. (Chris Wilson)

v3:
 * Rebase.

v4:
 * Rename and move the stats into a container structure. (Chris Wilson)

v5:
 * Re-order fields in struct intel_engine_cs. (Chris Wilson)

v6-v8:
 * Rebases.

v9:
 * Fix accounting during wedging.

v10:
 * Improved commit message. (Chris Wilson)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c         | 1 +
 drivers/gpu/drm/i915/i915_request.c     | 7 +++++++
 drivers/gpu/drm/i915/intel_engine_cs.c  | 5 +++--
 drivers/gpu/drm/i915/intel_lrc.c        | 1 +
 drivers/gpu/drm/i915/intel_ringbuffer.h | 9 +++++++++
 5 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 7d45e71100bc..d3a730f6ef65 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3309,6 +3309,7 @@ static void nop_complete_submit_request(struct i915_request *request)
 	dma_fence_set_error(&request->fence, -EIO);
 
 	spin_lock_irqsave(&request->engine->timeline.lock, flags);
+	request->engine->request_stats.runnable++;
 	__i915_request_submit(request);
 	intel_engine_init_global_seqno(request->engine, request->global_seqno);
 	spin_unlock_irqrestore(&request->engine->timeline.lock, flags);
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index abd4dacbab8e..689f838e849c 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -457,6 +457,9 @@ void __i915_request_submit(struct i915_request *request)
 	/* Transfer from per-context onto the global per-engine timeline */
 	move_to_timeline(request, &engine->timeline);
 
+	GEM_BUG_ON(engine->request_stats.runnable == 0);
+	engine->request_stats.runnable--;
+
 	trace_i915_request_execute(request);
 
 	wake_up_all(&request->execute);
@@ -470,6 +473,8 @@ void i915_request_submit(struct i915_request *request)
 	/* Will be called from irq-context when using foreign fences. */
 	spin_lock_irqsave(&engine->timeline.lock, flags);
 
+	engine->request_stats.runnable++;
+
 	__i915_request_submit(request);
 
 	spin_unlock_irqrestore(&engine->timeline.lock, flags);
@@ -507,6 +512,8 @@ void __i915_request_unsubmit(struct i915_request *request)
 	/* Transfer back from the global per-engine timeline to per-context */
 	move_to_timeline(request, request->timeline);
 
+	engine->request_stats.runnable++;
+
 	/*
 	 * We don't need to wake_up any waiters on request->execute, they
 	 * will get woken by any other event or us re-adding this request
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 1c6143bdf5a4..f46ef765aed0 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1460,11 +1460,12 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	if (i915_terminally_wedged(&engine->i915->gpu_error))
 		drm_printf(m, "*** WEDGED ***\n");
 
-	drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms]\n",
+	drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms], runnable %u\n",
 		   intel_engine_get_seqno(engine),
 		   intel_engine_last_submit(engine),
 		   engine->hangcheck.seqno,
-		   jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp));
+		   jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp),
+		   engine->request_stats.runnable);
 	drm_printf(m, "\tReset count: %d (global %d)\n",
 		   i915_reset_engine_count(error, engine),
 		   i915_reset_count(error));
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 28d56387edf5..f0c2673fce49 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1023,6 +1023,7 @@ static void queue_request(struct intel_engine_cs *engine,
 			  int prio)
 {
 	list_add_tail(&node->link, i915_sched_lookup_priolist(engine, prio));
+	engine->request_stats.runnable++;
 }
 
 static void __submit_queue_imm(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 7078132fc631..07491b6c7796 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -380,6 +380,15 @@ struct intel_engine_cs {
 	struct drm_i915_gem_object *default_state;
 	void *pinned_default_state;
 
+	struct {
+		/**
+		 * @runnable: Number of runnable requests sent to the backend.
+		 *
+		 * Count of requests waiting for the GPU to execute them.
+		 */
+		unsigned int runnable;
+	} request_stats;
+
 	unsigned long irq_posted;
 #define ENGINE_IRQ_BREADCRUMB 0
 
-- 
2.17.1