[Intel-gfx] [PATCH v6 10/34] drm/i915: Added scheduler hook into i915_gem_request_notify()

[John.C.Harrison at Intel.com]

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

The scheduler needs to know when requests have completed so that it
can keep its own internal state up to date and can submit new requests
to the hardware from its queue.

v2: Updated due to changes in request handling. The operation is now
reversed from before. Rather than the scheduler being in control of
completion events, it is now the request code itself. The scheduler
merely receives a notification event. It can then optionally request
it's worker thread be woken up after all completion processing is
complete.

v4: Downgraded a BUG_ON to a WARN_ON as the latter is preferred.

v5: Squashed the i915_scheduler.c portions down into the 'start of
scheduler' patch. [Joonas Lahtinen]

v6: Updated to newer nightly (lots of ring -> engine renaming).

Changed an '|=' to an 'if() ='. [review feedback from Joonas Lahtinen]

For: VIZ-1587
Signed-off-by: John Harrison <John.C.Harrison at Intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b7466cb..14dc641 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2918,6 +2918,7 @@ void i915_gem_request_notify(struct intel_engine_cs *engine, bool fence_locked)
 {
 	struct drm_i915_gem_request *req, *req_next;
 	unsigned long flags;
+	bool wake_sched = false;
 	u32 seqno;
 
 	if (list_empty(&engine->fence_signal_list)) {
@@ -2956,6 +2957,15 @@ void i915_gem_request_notify(struct intel_engine_cs *engine, bool fence_locked)
 		 */
 		list_del_init(&req->signal_link);
 
+		/*
+		 * NB: Must notify the scheduler before signalling
+		 * the node. Otherwise the node can get retired first
+		 * and call scheduler_clean() while the scheduler
+		 * thinks it is still active.
+		 */
+		if (i915_scheduler_notify_request(req))
+			wake_sched = true;
+
 		if (!req->cancelled) {
 			fence_signal_locked(&req->fence);
 			trace_i915_gem_request_complete(req);
@@ -2972,6 +2982,13 @@ void i915_gem_request_notify(struct intel_engine_cs *engine, bool fence_locked)
 
 	if (!fence_locked)
 		spin_unlock_irqrestore(&engine->fence_lock, flags);
+
+	/* Necessary? Or does the fence_signal() call do an implicit wakeup? */
+	wake_up_all(&engine->irq_queue);
+
+	/* Final scheduler processing after all individual updates are done. */
+	if (wake_sched)
+		i915_scheduler_wakeup(engine->dev);
 }
 
 static const char *i915_gem_request_get_driver_name(struct fence *req_fence)
-- 
1.9.1