[PATCH v4] drm/i915: clarify semaphore-ring interaction

[Ben Widawsky <ben@bwidawsk.net>]

After Daniel split out this code, I think this makes more sense, and
looks nicer. Also added some comments to help the situation.

v2: Make signal_mbox be all rings for symmetric-ness.
v3: submitted the wrong version of the patch before.
  v2 had an issue with odd number of rings. The fix is to always emit an
  even number of instructions to the ring with mbox updates.
v4: I suck. The code should send out mbox updates for NUM_RINGS-1 *
  number of commands. Instead of NUM_RINGS * number of commands-1.
-ret = intel_ring_begin(ring, round_up((I915_NUM_RINGS) * 3, 2) + 4);
+ret = intel_ring_begin(ring, round_up((I915_NUM_RINGS-1) * 4, 2) + 4);

Reviewed-by (v1): Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
---
 drivers/gpu/drm/i915/i915_reg.h         |   13 ++++----
 drivers/gpu/drm/i915/intel_ringbuffer.c |   54 +++++++++++++++++--------------
 drivers/gpu/drm/i915/intel_ringbuffer.h |    4 +--
 3 files changed, 39 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index fb76b19..d3040d5 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -241,12 +241,12 @@
 #define  MI_SEMAPHORE_UPDATE	    (1<<21)
 #define  MI_SEMAPHORE_COMPARE	    (1<<20)
 #define  MI_SEMAPHORE_REGISTER	    (1<<18)
-#define  MI_SEMAPHORE_SYNC_RV	    (2<<16)
-#define  MI_SEMAPHORE_SYNC_RB	    (0<<16)
-#define  MI_SEMAPHORE_SYNC_VR	    (0<<16)
-#define  MI_SEMAPHORE_SYNC_VB	    (2<<16)
-#define  MI_SEMAPHORE_SYNC_BR	    (2<<16)
-#define  MI_SEMAPHORE_SYNC_BV	    (0<<16)
+#define  MI_SEMAPHORE_SYNC_RB	    (0<<16) /* RCS wait for BCS  (BRSYNC) */
+#define  MI_SEMAPHORE_SYNC_RV	    (2<<16) /* RCS wait for VCS  (VRSYNC) */
+#define  MI_SEMAPHORE_SYNC_VR	    (0<<16) /* VCS wait for RCS  (RVSYNC) */
+#define  MI_SEMAPHORE_SYNC_VB	    (2<<16) /* VCS wait for BCS  (BVSYNC) */
+#define  MI_SEMAPHORE_SYNC_BV	    (0<<16) /* BCS wait for VCS  (VBSYNC) */
+#define  MI_SEMAPHORE_SYNC_BR	    (2<<16) /* BCS wait for RCS  (RBSYNC) */
 #define  MI_SEMAPHORE_SYNC_INVALID  (1<<0)
 /*
  * 3D instructions used by the kernel
@@ -423,6 +423,7 @@
 #define GEN6_VBSYNC (RING_SYNC_0(GEN6_BSD_RING_BASE))
 #define GEN6_BRSYNC (RING_SYNC_0(BLT_RING_BASE))
 #define GEN6_BVSYNC (RING_SYNC_1(BLT_RING_BASE))
+#define GEN6_NOSYNC 0
 #define RING_MAX_IDLE(base)	((base)+0x54)
 #define RING_HWS_PGA(base)	((base)+0x80)
 #define RING_HWS_PGA_GEN6(base)	((base)+0x2080)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index b59b6d5..1d641e3 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -449,6 +449,7 @@ update_mboxes(struct intel_ring_buffer *ring,
 			      MI_SEMAPHORE_UPDATE);
 	intel_ring_emit(ring, seqno);
 	intel_ring_emit(ring, mmio_offset);
+	intel_ring_emit(ring, MI_NOOP);
 }
 
 /**
@@ -464,21 +465,23 @@ static int
 gen6_add_request(struct intel_ring_buffer *ring,
 		 u32 *seqno)
 {
-	u32 mbox1_reg;
-	u32 mbox2_reg;
-	int ret;
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_ring_buffer *useless;
+	int i, ret;
 
-	ret = intel_ring_begin(ring, 10);
+	ret = intel_ring_begin(ring, round_up((I915_NUM_RINGS-1) * 4, 2) + 4);
 	if (ret)
 		return ret;
 
-	mbox1_reg = ring->signal_mbox[0];
-	mbox2_reg = ring->signal_mbox[1];
-
 	*seqno = i915_gem_next_request_seqno(ring);
 
-	update_mboxes(ring, *seqno, mbox1_reg);
-	update_mboxes(ring, *seqno, mbox2_reg);
+	for_each_ring(useless, dev_priv, i) {
+		u32 mbox_reg = ring->signal_mbox[i];
+		if (mbox_reg != GEN6_NOSYNC)
+			update_mboxes(ring, *seqno, mbox_reg);
+	}
+
 	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, *seqno);
@@ -1330,11 +1333,12 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 		ring->irq_enable_mask = GT_USER_INTERRUPT;
 		ring->get_seqno = gen6_ring_get_seqno;
 		ring->sync_to = gen6_ring_sync;
-		ring->semaphore_register[0] = MI_SEMAPHORE_SYNC_INVALID;
-		ring->semaphore_register[1] = MI_SEMAPHORE_SYNC_RV;
-		ring->semaphore_register[2] = MI_SEMAPHORE_SYNC_RB;
-		ring->signal_mbox[0] = GEN6_VRSYNC;
-		ring->signal_mbox[1] = GEN6_BRSYNC;
+		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_INVALID;
+		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_RV;
+		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_RB;
+		ring->signal_mbox[RCS] = GEN6_NOSYNC;
+		ring->signal_mbox[VCS] = GEN6_VRSYNC;
+		ring->signal_mbox[BCS] = GEN6_BRSYNC;
 	} else if (IS_GEN5(dev)) {
 		ring->add_request = pc_render_add_request;
 		ring->flush = gen4_render_ring_flush;
@@ -1465,11 +1469,12 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 		ring->irq_put = gen6_ring_put_irq;
 		ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
 		ring->sync_to = gen6_ring_sync;
-		ring->semaphore_register[0] = MI_SEMAPHORE_SYNC_VR;
-		ring->semaphore_register[1] = MI_SEMAPHORE_SYNC_INVALID;
-		ring->semaphore_register[2] = MI_SEMAPHORE_SYNC_VB;
-		ring->signal_mbox[0] = GEN6_RVSYNC;
-		ring->signal_mbox[1] = GEN6_BVSYNC;
+		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_VR;
+		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_INVALID;
+		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_VB;
+		ring->signal_mbox[RCS] = GEN6_RVSYNC;
+		ring->signal_mbox[VCS] = GEN6_NOSYNC;
+		ring->signal_mbox[BCS] = GEN6_BVSYNC;
 	} else {
 		ring->mmio_base = BSD_RING_BASE;
 		ring->flush = bsd_ring_flush;
@@ -1510,11 +1515,12 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 	ring->irq_put = gen6_ring_put_irq;
 	ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
 	ring->sync_to = gen6_ring_sync;
-	ring->semaphore_register[0] = MI_SEMAPHORE_SYNC_BR;
-	ring->semaphore_register[1] = MI_SEMAPHORE_SYNC_BV;
-	ring->semaphore_register[2] = MI_SEMAPHORE_SYNC_INVALID;
-	ring->signal_mbox[0] = GEN6_RBSYNC;
-	ring->signal_mbox[1] = GEN6_VBSYNC;
+	ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_BR;
+	ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_BV;
+	ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->signal_mbox[RCS] = GEN6_RBSYNC;
+	ring->signal_mbox[VCS] = GEN6_VBSYNC;
+	ring->signal_mbox[BCS] = GEN6_NOSYNC;
 	ring->init = init_ring_common;
 
 	return intel_init_ring_buffer(dev, ring);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 55d3da2..3db4447 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -80,8 +80,8 @@ struct  intel_ring_buffer {
 				   struct intel_ring_buffer *to,
 				   u32 seqno);
 
-	u32		semaphore_register[3]; /*our mbox written by others */
-	u32		signal_mbox[2]; /* mboxes this ring signals to */
+	u32		semaphore_register[I915_NUM_RINGS]; /*our mbox written by others */
+	u32		signal_mbox[I915_NUM_RINGS]; /* mboxes this ring signals to */
 	/**
 	 * List of objects currently involved in rendering from the
 	 * ringbuffer.
-- 
1.7.10.2