[PATCH 36/36] drm/i915/execlists: Reduce lock context between schedule/submit_request

[Chris Wilson]

If we do not require to perform priority bumping, and we haven't yet
submitted the request, we can update its priority in situ and skip
acquiring the engine locks -- thus avoiding any contention between us
and submit/execute.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_lrc.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 062f309a5c61..42c776c42212 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -768,6 +768,17 @@ static void execlists_schedule(struct drm_i915_gem_request *request, int prio)
 		list_safe_reset_next(dep, p, dfs_link);
 	}
 
+	/* If we didn't need to bump any existing priorites, and we haven't
+	 * yet submitted this request (i..e there is no porential race with
+	 * execlists_submit_request()), we can set our own priority and skip
+	 * acquiring the engine locks.
+	 */
+	if (request->priotree.priority == INT_MIN) {
+		request->priotree.priority = prio;
+		if (stack.dfs_link.next == stack.dfs_link.prev)
+			return;
+	}
+
 	engine = request->engine;
 	spin_lock_irq(&engine->timeline->lock);
 
-- 
2.11.0