[Intel-gfx] [PATCH v6 7/7] drm/i915: Cache last IRQ seqno to reduce IRQ overhead

[John.C.Harrison at Intel.com]

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

The notify function can be called many times without the seqno
changing. A large number of duplicates are to prevent races due to the
requirement of not enabling interrupts until requested. However, when
interrupts are enabled the IRQ handle can be called multiple times
without the ring's seqno value changing. This patch reduces the
overhead of these extra calls by caching the last processed seqno
value and early exiting if it has not changed.

v3: New patch for series.

v5: Added comment about last_irq_seqno usage due to code review
feedback (Tvrtko Ursulin).

v6: Minor update to resolve a race condition with the wait_request
optimisation.

For: VIZ-5190
Signed-off-by: John Harrison <John.C.Harrison at Intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c         | 21 +++++++++++++++++++--
 drivers/gpu/drm/i915/intel_ringbuffer.h |  1 +
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index f7858ea..72a37d6 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1386,6 +1386,7 @@ out:
 			 * request has not actually been fully processed yet.
 			 */
 			spin_lock_irq(&req->ring->fence_lock);
+			req->ring->last_irq_seqno = 0;
 			i915_gem_request_notify(req->ring, true);
 			spin_unlock_irq(&req->ring->fence_lock);
 		}
@@ -2543,6 +2544,8 @@ i915_gem_init_seqno(struct drm_device *dev, u32 seqno)
 
 		for (j = 0; j < ARRAY_SIZE(ring->semaphore.sync_seqno); j++)
 			ring->semaphore.sync_seqno[j] = 0;
+
+		ring->last_irq_seqno = 0;
 	}
 
 	return 0;
@@ -2875,11 +2878,22 @@ void i915_gem_request_notify(struct intel_engine_cs *ring, bool fence_locked)
 		return;
 	}
 
+	/*
+	 * Check for a new seqno. If it hasn't actually changed then early
+	 * exit without even grabbing the spinlock. Note that this is safe
+	 * because any corruption of last_irq_seqno merely results in doing
+	 * the full processing when there is potentially no work to be done.
+	 * It can never lead to not processing work that does need to happen.
+	 */
+	seqno = ring->get_seqno(ring, false);
+	trace_i915_gem_request_notify(ring, seqno);
+	if (seqno == ring->last_irq_seqno)
+		return;
+
 	if (!fence_locked)
 		spin_lock_irqsave(&ring->fence_lock, flags);
 
-	seqno = ring->get_seqno(ring, false);
-	trace_i915_gem_request_notify(ring, seqno);
+	ring->last_irq_seqno = seqno;
 
 	list_for_each_entry_safe(req, req_next, &ring->fence_signal_list, signal_link) {
 		if (!req->cancelled) {
@@ -3167,7 +3181,10 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
 	 * Tidy up anything left over. This includes a call to
 	 * i915_gem_request_notify() which will make sure that any requests
 	 * that were on the signal pending list get also cleaned up.
+	 * NB: The seqno cache must be cleared otherwise the notify call will
+	 * simply return immediately.
 	 */
+	ring->last_irq_seqno = 0;
 	i915_gem_retire_requests_ring(ring);
 
 	/* Having flushed all requests from all queues, we know that all
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 6a7968b..ada93a9 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -363,6 +363,7 @@ struct  intel_engine_cs {
 	spinlock_t fence_lock;
 	struct list_head fence_signal_list;
 	struct list_head fence_unsignal_list;
+	uint32_t last_irq_seqno;
 };
 
 static inline bool
-- 
1.9.1