[PATCH 1/2] drm/i915: Dumb down the semaphore logic

[Ben Widawsky <ben@bwidawsk.net>]

While I think the previous code is correct, it was hard to follow and
hard to debug. Since we already have a ring abstraction, might as well
use it to handle the semaphore updates and compares.

I don't expect this code to make semaphores better or worse, but you
never know...

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Eric Anholt <eric@anholt.net>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
---
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |    3 +-
 drivers/gpu/drm/i915/i915_reg.h            |    7 +
 drivers/gpu/drm/i915/intel_ringbuffer.c    |  176 +++++++++++++++++++++-------
 drivers/gpu/drm/i915/intel_ringbuffer.h    |    7 +-
 4 files changed, 145 insertions(+), 48 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 4934cf8..3693e83 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -784,7 +784,8 @@ i915_gem_execbuffer_sync_rings(struct drm_i915_gem_object *obj,
 	}
 
 	from->sync_seqno[idx] = seqno;
-	return intel_ring_sync(to, from, seqno - 1);
+
+	return to->sync_to(to, from, seqno - 1);
 }
 
 static int
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 542453f..f0b5287 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -194,6 +194,13 @@
 #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_INVALID  (1<<0)
 /*
  * 3D instructions used by the kernel
  */
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index c30626e..8f902a1 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -315,79 +315,155 @@ static void render_ring_cleanup(struct intel_ring_buffer *ring)
 }
 
 static void
-update_semaphore(struct intel_ring_buffer *ring, int i, u32 seqno)
+update_mboxes(struct intel_ring_buffer *ring,
+	    u32 seqno,
+	    u32 mmio_offset)
 {
-	struct drm_device *dev = ring->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int id;
-
-	/*
-	 * cs -> 1 = vcs, 0 = bcs
-	 * vcs -> 1 = bcs, 0 = cs,
-	 * bcs -> 1 = cs, 0 = vcs.
-	 */
-	id = ring - dev_priv->ring;
-	id += 2 - i;
-	id %= 3;
-
-	intel_ring_emit(ring,
-			MI_SEMAPHORE_MBOX |
-			MI_SEMAPHORE_REGISTER |
-			MI_SEMAPHORE_UPDATE);
+	intel_ring_emit(ring, MI_SEMAPHORE_MBOX |
+			      MI_SEMAPHORE_GLOBAL_GTT |
+			      MI_SEMAPHORE_REGISTER |
+			      MI_SEMAPHORE_UPDATE);
 	intel_ring_emit(ring, seqno);
-	intel_ring_emit(ring,
-			RING_SYNC_0(dev_priv->ring[id].mmio_base) + 4*i);
+	intel_ring_emit(ring, mmio_offset);
 }
 
-static int
+/**
+ * gen6_add_request - Update the semaphore mailbox registers
+ * 
+ * @ring - ring that is adding a request
+ * @mbox1_reg - mailbox address for RCS or VCS ring
+ * @mbox2_reg - mailbox address for VCS or BCS ring
+ *
+ * Update the mailbox registers in the *other* rings with the current seqno.
+ * This acts like a signal in the canonical semaphore.
+ */
+static u32
 gen6_add_request(struct intel_ring_buffer *ring,
-		 u32 *result)
+		 u32 mbox1_reg,
+		 u32 mbox2_reg)
 {
 	u32 seqno;
 	int ret;
+	seqno = i915_gem_get_seqno(ring->dev);
 
 	ret = intel_ring_begin(ring, 10);
 	if (ret)
 		return ret;
 
-	seqno = i915_gem_get_seqno(ring->dev);
-	update_semaphore(ring, 0, seqno);
-	update_semaphore(ring, 1, seqno);
-
+	update_mboxes(ring, seqno, mbox1_reg);
+	update_mboxes(ring, seqno, mbox2_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);
 	intel_ring_emit(ring, MI_USER_INTERRUPT);
 	intel_ring_advance(ring);
 
-	*result = seqno;
+	return seqno;
+}
+
+static int
+gen6_blt_add_request(struct intel_ring_buffer *ring,
+		     u32 *result)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	*result = gen6_add_request(ring,
+				   dev_priv->ring[RCS].mmio_base + 0x44,
+				   dev_priv->ring[VCS].mmio_base + 0x40);
 	return 0;
 }
 
-int
-intel_ring_sync(struct intel_ring_buffer *ring,
-		struct intel_ring_buffer *to,
+static int
+gen6_bsd_add_request(struct intel_ring_buffer *ring,
+		     u32 *result)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	*result = gen6_add_request(ring,
+				   dev_priv->ring[RCS].mmio_base + 0x40,
+				   dev_priv->ring[BCS].mmio_base + 0x44);
+	return 0;
+}
+
+static int
+gen6_render_add_request(struct intel_ring_buffer *ring,
+		        u32 *result)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	*result = gen6_add_request(ring,
+				   dev_priv->ring[VCS].mmio_base + 0x44,
+				   dev_priv->ring[BCS].mmio_base + 0x40);
+	return 0;
+}
+
+static int
+intel_ring_sync(struct intel_ring_buffer *waiter,
+		struct intel_ring_buffer *signaller,
+		u32 semaphore_register,
 		u32 seqno)
 {
 	int ret;
+	u32 temp = MI_SEMAPHORE_MBOX |
+		   MI_SEMAPHORE_GLOBAL_GTT | /* Not needed */
+		   MI_SEMAPHORE_COMPARE;
 
-	ret = intel_ring_begin(ring, 4);
+	ret = intel_ring_begin(waiter, 4);
 	if (ret)
 		return ret;
 
-	intel_ring_emit(ring,
-			MI_SEMAPHORE_MBOX |
-			MI_SEMAPHORE_REGISTER |
-			intel_ring_sync_index(ring, to) << 17 |
-			MI_SEMAPHORE_COMPARE);
-	intel_ring_emit(ring, seqno);
-	intel_ring_emit(ring, 0);
-	intel_ring_emit(ring, MI_NOOP);
-	intel_ring_advance(ring);
+	temp |= MI_SEMAPHORE_REGISTER;
+
+	intel_ring_emit(waiter, temp | semaphore_register);
+	intel_ring_emit(waiter, seqno);
+	intel_ring_emit(waiter, 0);
+	intel_ring_emit(waiter, MI_NOOP);
+	intel_ring_advance(waiter);
 
 	return 0;
 }
 
+/* VCS->RCS (RVSYNC) or BCS->RCS (RBSYNC) */
+int
+render_ring_sync_to(struct intel_ring_buffer *waiter,
+		    struct intel_ring_buffer *signaller,
+		    u32 seqno)
+{
+	WARN_ON(signaller->semaphore_register[RCS] == MI_SEMAPHORE_SYNC_INVALID);
+	return intel_ring_sync(waiter,
+			       signaller,
+			       signaller->semaphore_register[RCS],
+			       seqno);
+}
+
+/* RCS->VCS (VRSYNC) or BCS->VCS (VBSYNC) */
+int
+gen6_bsd_ring_sync_to(struct intel_ring_buffer *waiter,
+		      struct intel_ring_buffer *signaller,
+		      u32 seqno)
+{
+	WARN_ON(signaller->semaphore_register[VCS] == MI_SEMAPHORE_SYNC_INVALID);
+	return intel_ring_sync(waiter,
+			       signaller,
+			       signaller->semaphore_register[VCS],
+			       seqno);
+}
+
+/* RCS->BCS (BRSYNC) or VCS->BCS (BVSYNC) */
+int
+gen6_blt_ring_sync_to(struct intel_ring_buffer *waiter,
+		      struct intel_ring_buffer *signaller,
+		      u32 seqno)
+{
+	WARN_ON(signaller->semaphore_register[BCS] == MI_SEMAPHORE_SYNC_INVALID);
+	return intel_ring_sync(waiter,
+			       signaller,
+			       signaller->semaphore_register[BCS],
+			       seqno);
+}
+
+
+
 #define PIPE_CONTROL_FLUSH(ring__, addr__)					\
 do {									\
 	intel_ring_emit(ring__, GFX_OP_PIPE_CONTROL | PIPE_CONTROL_QW_WRITE |		\
@@ -1027,6 +1103,10 @@ static const struct intel_ring_buffer render_ring = {
 	.irq_put		= render_ring_put_irq,
 	.dispatch_execbuffer	= render_ring_dispatch_execbuffer,
        .cleanup			= render_ring_cleanup,
+	.sync_to		= render_ring_sync_to,
+	.semaphore_register	= {MI_SEMAPHORE_SYNC_INVALID,
+				   MI_SEMAPHORE_SYNC_RV,
+				   MI_SEMAPHORE_SYNC_RB},
 };
 
 /* ring buffer for bit-stream decoder */
@@ -1149,11 +1229,15 @@ static const struct intel_ring_buffer gen6_bsd_ring = {
 	.init			= init_ring_common,
 	.write_tail		= gen6_bsd_ring_write_tail,
 	.flush			= gen6_ring_flush,
-	.add_request		= gen6_add_request,
+	.add_request		= gen6_bsd_add_request,
 	.get_seqno		= ring_get_seqno,
 	.irq_get		= gen6_bsd_ring_get_irq,
 	.irq_put		= gen6_bsd_ring_put_irq,
 	.dispatch_execbuffer	= gen6_ring_dispatch_execbuffer,
+	.sync_to		= gen6_bsd_ring_sync_to,
+	.semaphore_register	= {MI_SEMAPHORE_SYNC_VR,
+				   MI_SEMAPHORE_SYNC_INVALID,
+				   MI_SEMAPHORE_SYNC_VB},
 };
 
 /* Blitter support (SandyBridge+) */
@@ -1279,12 +1363,16 @@ static const struct intel_ring_buffer gen6_blt_ring = {
        .init			= blt_ring_init,
        .write_tail		= ring_write_tail,
        .flush			= blt_ring_flush,
-       .add_request		= gen6_add_request,
+       .add_request		= gen6_blt_add_request,
        .get_seqno		= ring_get_seqno,
        .irq_get			= blt_ring_get_irq,
        .irq_put			= blt_ring_put_irq,
        .dispatch_execbuffer	= gen6_ring_dispatch_execbuffer,
        .cleanup			= blt_ring_cleanup,
+       .sync_to			= gen6_blt_ring_sync_to,
+       .semaphore_register	= {MI_SEMAPHORE_SYNC_BR,
+				   MI_SEMAPHORE_SYNC_BV,
+				   MI_SEMAPHORE_SYNC_INVALID},
 };
 
 int intel_init_render_ring_buffer(struct drm_device *dev)
@@ -1294,7 +1382,7 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 
 	*ring = render_ring;
 	if (INTEL_INFO(dev)->gen >= 6) {
-		ring->add_request = gen6_add_request;
+		ring->add_request = gen6_render_add_request;
 		ring->irq_get = gen6_render_ring_get_irq;
 		ring->irq_put = gen6_render_ring_put_irq;
 	} else if (IS_GEN5(dev)) {
@@ -1317,7 +1405,7 @@ int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size)
 
 	*ring = render_ring;
 	if (INTEL_INFO(dev)->gen >= 6) {
-		ring->add_request = gen6_add_request;
+		ring->add_request = gen6_render_add_request;
 		ring->irq_get = gen6_render_ring_get_irq;
 		ring->irq_put = gen6_render_ring_put_irq;
 	} else if (IS_GEN5(dev)) {
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 39ac2b6..98052fd 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -75,7 +75,11 @@ struct  intel_ring_buffer {
 	int		(*dispatch_execbuffer)(struct intel_ring_buffer *ring,
 					       u32 offset, u32 length);
 	void		(*cleanup)(struct intel_ring_buffer *ring);
+	int		(*sync_to)(struct intel_ring_buffer *ring,
+				   struct intel_ring_buffer *to,
+				   u32 seqno);
 
+	u32		semaphore_register[3];
 	/**
 	 * List of objects currently involved in rendering from the
 	 * ringbuffer.
@@ -180,9 +184,6 @@ static inline void intel_ring_emit(struct intel_ring_buffer *ring,
 void intel_ring_advance(struct intel_ring_buffer *ring);
 
 u32 intel_ring_get_seqno(struct intel_ring_buffer *ring);
-int intel_ring_sync(struct intel_ring_buffer *ring,
-		    struct intel_ring_buffer *to,
-		    u32 seqno);
 
 int intel_init_render_ring_buffer(struct drm_device *dev);
 int intel_init_bsd_ring_buffer(struct drm_device *dev);
-- 
1.7.6.1