[Intel-gfx] [PATCH 13/13] 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.

For: VIZ-5190
Signed-off-by: John Harrison <John.C.Harrison at Intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c         | 14 +++++++++++---
 drivers/gpu/drm/i915/intel_ringbuffer.h |  1 +
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 279d79f..3c88678 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2457,6 +2457,8 @@ 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;
@@ -2788,11 +2790,14 @@ void i915_gem_request_notify(struct intel_engine_cs *ring, bool fence_locked)
 		return;
 	}
 
-	if (!fence_locked)
-		spin_lock_irqsave(&ring->fence_lock, flags);
-
 	seqno = ring->get_seqno(ring, false);
 	trace_i915_gem_request_notify(ring, seqno);
+	if (seqno == ring->last_irq_seqno)
+		return;
+	ring->last_irq_seqno = seqno;
+
+	if (!fence_locked)
+		spin_lock_irqsave(&ring->fence_lock, flags);
 
 	list_for_each_entry_safe(req, req_next, &ring->fence_signal_list, signal_link) {
 		if (!req->cancelled) {
@@ -3163,7 +3168,10 @@ 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 9d09edb..1987abd 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -356,6 +356,7 @@ 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;
 };
 
 bool intel_ring_initialized(struct intel_engine_cs *ring);
-- 
1.9.1