[Intel-gfx] [PATCH 03/13] drm/i915: Move ring_begin to signal()

[Ben Widawsky]

Add_request has always contained both the semaphore mailbox updates as
well as the breadcrumb writes. Since the semaphore signal is the one
which actually knows about the number of dwords it needs to emit to the
ring, we move the ring_begin to that function. This allows us to remove
the hideously shared #define

On a related not, gen8 will use a different number of dwords for
semaphores, but not for add request.

v2: Make number of dwords an explicit part of signalling (via function
argument). (Chris)

v3: very slight comment change

Reviewed-by: Ville Syrjälä <ville.syrjala at linux.intel.com>
Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 39 +++++++++++++++++++--------------
 drivers/gpu/drm/i915/intel_ringbuffer.h |  4 +++-
 2 files changed, 25 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 558bddf..06d849a 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -634,18 +634,28 @@ static void render_ring_cleanup(struct intel_ring_buffer *ring)
 	ring->scratch.obj = NULL;
 }
 
-static void gen6_signal(struct intel_ring_buffer *signaller)
+static int gen6_signal(struct intel_ring_buffer *signaller,
+		       unsigned int num_dwords)
 {
-	struct drm_i915_private *dev_priv = signaller->dev->dev_private;
+	struct drm_device *dev = signaller->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_ring_buffer *useless;
-	int i;
+	int i, ret;
 
-/* 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.
- */
+	/* 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);
+
+	ret = intel_ring_begin(signaller, num_dwords);
+	if (ret)
+		return ret;
+#undef MBOX_UPDATE_DWORDS
+
 	for_each_ring(useless, dev_priv, i) {
 		u32 mbox_reg = signaller->semaphore.mbox.signal[i];
 		if (mbox_reg != GEN6_NOSYNC) {
@@ -660,6 +670,8 @@ static void gen6_signal(struct intel_ring_buffer *signaller)
 			intel_ring_emit(signaller, MI_NOOP);
 		}
 	}
+
+	return 0;
 }
 
 /**
@@ -674,19 +686,12 @@ static void gen6_signal(struct intel_ring_buffer *signaller)
 static int
 gen6_add_request(struct intel_ring_buffer *ring)
 {
-	struct drm_device *dev = ring->dev;
-	int ret, num_dwords = 4;
-
-	if (i915_semaphore_is_enabled(dev))
-		num_dwords += ((I915_NUM_RINGS-1) * MBOX_UPDATE_DWORDS);
-#undef MBOX_UPDATE_DWORDS
+	int ret;
 
-	ret = intel_ring_begin(ring, num_dwords);
+	ret = ring->semaphore.signal(ring, 4);
 	if (ret)
 		return ret;
 
-	ring->semaphore.signal(ring);
-
 	intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
 	intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
 	intel_ring_emit(ring, ring->outstanding_lazy_seqno);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index d270323..36b4462 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -127,7 +127,9 @@ struct  intel_ring_buffer {
 		int	(*sync_to)(struct intel_ring_buffer *ring,
 				   struct intel_ring_buffer *to,
 				   u32 seqno);
-		void	(*signal)(struct intel_ring_buffer *signaller);
+		int	(*signal)(struct intel_ring_buffer *signaller,
+				  /* num_dwords needed by caller */
+				  unsigned int num_dwords);
 	} semaphore;
 
 	/**
-- 
1.9.0