[Intel-gfx] [PATCH 06/17] drm/i915: Make semaphore updates more precise

[Ben Widawsky]

With the ring mask we now have an easy way to know the number of rings
in the system, and therefore can accurately predict the number of dwords
to emit for semaphore signalling. This was not possible (easily)
previously.

There should be no functional impact, simply fewer instructions emitted.

While we're here, simply do the round up to 2 instead of the fancier
rounding we did before, which rounding up per mbox, ie 4.

Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 43 +++++++++++++++++----------------
 1 file changed, 22 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index b16d11b..cb407a3 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -634,24 +634,20 @@ static void render_ring_cleanup(struct intel_ring_buffer *ring)
 
 static int gen6_signal(struct intel_ring_buffer *signaller)
 {
+#define MBOX_UPDATE_DWORDS 4
 	struct drm_device *dev = signaller->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_ring_buffer *useless;
-	int i, ret, num_dwords = 4;
+	int i, ret, num_rings, num_dwords;
 
-	/* NB: In order to be able to do semaphore MBOX updates for varying
-	 * number of rings, it's easiest if we round up each individual update
-	 * to a multiple of 2 (since ring updates must always be a multiple of
-	 * 2) even though the actual update only requires 3 dwords.
-	 */
-#define MBOX_UPDATE_DWORDS 4
-	if (i915_semaphore_is_enabled(dev))
-		num_dwords += ((I915_NUM_RINGS-1) * MBOX_UPDATE_DWORDS);
+	num_rings = hweight_long(INTEL_INFO(dev)->ring_mask);
+	num_dwords = round_up((num_rings-1) * MBOX_UPDATE_DWORDS, 2);
+#undef MBOX_UPDATE_DWORDS
 
-	ret = intel_ring_begin(signaller, num_dwords);
+	/* XXX: + 4 for the caller */
+	ret = intel_ring_begin(signaller, num_dwords + 4);
 	if (ret)
 		return ret;
-#undef MBOX_UPDATE_DWORDS
 
 	for_each_ring(useless, dev_priv, i) {
 		u32 mbox_reg = signaller->semaphore.signal_mbox[i];
@@ -660,14 +656,11 @@ static int gen6_signal(struct intel_ring_buffer *signaller)
 			intel_ring_emit(signaller, mbox_reg);
 			intel_ring_emit(signaller, signaller->outstanding_lazy_seqno);
 			intel_ring_emit(signaller, MI_NOOP);
-		} else {
-			intel_ring_emit(signaller, MI_NOOP);
-			intel_ring_emit(signaller, MI_NOOP);
-			intel_ring_emit(signaller, MI_NOOP);
-			intel_ring_emit(signaller, MI_NOOP);
 		}
 	}
 
+	WARN_ON(i != num_rings);
+
 	return 0;
 }
 
@@ -687,7 +680,11 @@ gen6_add_request(struct intel_ring_buffer *ring)
 
 	/* XXX: Signal will do ring begin for us. It assumes add_request always
 	 * needs 4 dwords */
-	ret = ring->semaphore.signal(ring);
+	if (ring->semaphore.signal)
+		ret = ring->semaphore.signal(ring);
+	else
+		ret = intel_ring_begin(ring, 4);
+
 	if (ret)
 		return ret;
 
@@ -1878,7 +1875,8 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 		ring->get_seqno = gen6_ring_get_seqno;
 		ring->set_seqno = ring_set_seqno;
 		ring->semaphore.sync_to = gen6_ring_sync;
-		ring->semaphore.signal = gen6_signal;
+		if (i915_semaphore_is_enabled(dev))
+			ring->semaphore.signal = gen6_signal;
 		ring->semaphore.mbox[RCS] = MI_SEMAPHORE_SYNC_INVALID;
 		ring->semaphore.mbox[VCS] = MI_SEMAPHORE_SYNC_RV;
 		ring->semaphore.mbox[BCS] = MI_SEMAPHORE_SYNC_RB;
@@ -2055,7 +2053,8 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 				gen6_ring_dispatch_execbuffer;
 		}
 		ring->semaphore.sync_to = gen6_ring_sync;
-		ring->semaphore.signal = gen6_signal;
+		if (i915_semaphore_is_enabled(dev))
+			ring->semaphore.signal = gen6_signal;
 		ring->semaphore.mbox[RCS] = MI_SEMAPHORE_SYNC_VR;
 		ring->semaphore.mbox[VCS] = MI_SEMAPHORE_SYNC_INVALID;
 		ring->semaphore.mbox[BCS] = MI_SEMAPHORE_SYNC_VB;
@@ -2113,7 +2112,8 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 		ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
 	}
 	ring->semaphore.sync_to = gen6_ring_sync;
-	ring->semaphore.signal = gen6_signal;
+	if (i915_semaphore_is_enabled(dev))
+		ring->semaphore.signal = gen6_signal;
 	ring->semaphore.mbox[RCS] = MI_SEMAPHORE_SYNC_BR;
 	ring->semaphore.mbox[VCS] = MI_SEMAPHORE_SYNC_BV;
 	ring->semaphore.mbox[BCS] = MI_SEMAPHORE_SYNC_INVALID;
@@ -2155,7 +2155,8 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev)
 		ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
 	}
 	ring->semaphore.sync_to = gen6_ring_sync;
-	ring->semaphore.signal = gen6_signal;
+	if (i915_semaphore_is_enabled(dev))
+		ring->semaphore.signal = gen6_signal;
 	ring->semaphore.mbox[RCS] = MI_SEMAPHORE_SYNC_VER;
 	ring->semaphore.mbox[VCS] = MI_SEMAPHORE_SYNC_VEV;
 	ring->semaphore.mbox[BCS] = MI_SEMAPHORE_SYNC_VEB;
-- 
1.8.5.1