[PATCH 04/10] drm/i915/bdw: implement semaphore wait

[Ben Widawsky <benjamin.widawsky@intel.com>]

Semaphore waits use a new instruction, MI_SEMAPHORE_WAIT. The seqno to
wait on is all well defined by the table in the previous patch. There is
nothing else different from previous GEN's semaphore synchronization
code.

v2: Update macros to not require the other ring's ring->id (Chris)

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
---
 drivers/gpu/drm/i915/i915_reg.h         |  3 +++
 drivers/gpu/drm/i915/intel_ringbuffer.c | 33 +++++++++++++++++++++++++++++----
 drivers/gpu/drm/i915/intel_ringbuffer.h |  4 ++--
 3 files changed, 34 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index dc25084..532f62b 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -260,6 +260,9 @@
 #define   MI_RESTORE_INHIBIT		(1<<0)
 #define MI_SEMAPHORE_SIGNAL	MI_INSTR(0x1b, 0) /* GEN8+ */
 #define   MI_SEMAPHORE_TARGET(engine)	((engine)<<15)
+#define MI_SEMAPHORE_WAIT	MI_INSTR(0x1c, 2) /* GEN8+ */
+#define   MI_SEMAPHORE_POLL		(1<<15)
+#define   MI_SEMAPHORE_SAD_GTE_SDD	(1<<12)
 #define MI_STORE_DWORD_IMM	MI_INSTR(0x20, 1)
 #define   MI_MEM_VIRTUAL	(1 << 22) /* 965+ only */
 #define MI_STORE_DWORD_INDEX	MI_INSTR(0x21, 1)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index b69eceb..20fc2b1 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -827,6 +827,31 @@ static inline bool i915_gem_has_seqno_wrapped(struct drm_device *dev,
  * @signaller - ring which has, or will signal
  * @seqno - seqno which the waiter will block on
  */
+
+static int
+gen8_ring_sync(struct intel_ring_buffer *waiter,
+	       struct intel_ring_buffer *signaller,
+	       u32 seqno)
+{
+	struct drm_i915_private *dev_priv = waiter->dev->dev_private;
+	int ret;
+
+	ret = intel_ring_begin(waiter, 4);
+	if (ret)
+		return ret;
+
+	intel_ring_emit(waiter, MI_SEMAPHORE_WAIT |
+				MI_SEMAPHORE_GLOBAL_GTT |
+				MI_SEMAPHORE_SAD_GTE_SDD);
+	intel_ring_emit(waiter, seqno);
+	intel_ring_emit(waiter,
+			lower_32_bits(GEN8_WAIT_OFFSET(waiter, signaller->id)));
+	intel_ring_emit(waiter,
+			upper_32_bits(GEN8_WAIT_OFFSET(waiter, signaller->id)));
+	intel_ring_advance(waiter);
+	return 0;
+}
+
 static int
 gen6_ring_sync(struct intel_ring_buffer *waiter,
 	       struct intel_ring_buffer *signaller,
@@ -2023,7 +2048,7 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 		ring->set_seqno = ring_set_seqno;
 		if (i915_semaphore_is_enabled(dev)) {
 			BUG_ON(!dev_priv->semaphore_obj);
-			ring->semaphore.sync_to = gen6_ring_sync;
+			ring->semaphore.sync_to = gen8_ring_sync;
 			ring->semaphore.signal = gen8_rcs_signal;
 			GEN8_RING_SEMAPHORE_INIT;
 		}
@@ -2217,7 +2242,7 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 			ring->dispatch_execbuffer =
 				gen8_ring_dispatch_execbuffer;
 			if (i915_semaphore_is_enabled(dev)) {
-				ring->semaphore.sync_to = gen6_ring_sync;
+				ring->semaphore.sync_to = gen8_ring_sync;
 				ring->semaphore.signal = gen8_xcs_signal;
 				GEN8_RING_SEMAPHORE_INIT;
 			}
@@ -2337,7 +2362,7 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 		ring->irq_put = gen8_ring_put_irq;
 		ring->dispatch_execbuffer = gen8_ring_dispatch_execbuffer;
 		if (i915_semaphore_is_enabled(dev)) {
-			ring->semaphore.sync_to = gen6_ring_sync;
+			ring->semaphore.sync_to = gen8_ring_sync;
 			ring->semaphore.signal = gen8_xcs_signal;
 			GEN8_RING_SEMAPHORE_INIT;
 		}
@@ -2395,7 +2420,7 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev)
 		ring->irq_put = gen8_ring_put_irq;
 		ring->dispatch_execbuffer = gen8_ring_dispatch_execbuffer;
 		if (i915_semaphore_is_enabled(dev)) {
-			ring->semaphore.sync_to = gen6_ring_sync;
+			ring->semaphore.sync_to = gen8_ring_sync;
 			ring->semaphore.signal = gen8_xcs_signal;
 			GEN8_RING_SEMAPHORE_INIT;
 		}
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 3bbdf26..ff20d11 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -45,10 +45,10 @@ struct  intel_hw_status_page {
 	(ring->id * I915_NUM_RINGS * i915_semaphore_seqno_size) + \
 	(i915_semaphore_seqno_size * (to)))
 
-#define GEN8_WAIT_OFFSET(from) \
+#define GEN8_WAIT_OFFSET(__ring, from) \
 	(i915_gem_obj_ggtt_offset(dev_priv->semaphore_obj) + \
 	((from) * I915_NUM_RINGS * i915_semaphore_seqno_size) + \
-	(i915_semaphore_seqno_size * ring->id))
+	(i915_semaphore_seqno_size * (__ring)->id))
 
 #define GEN8_RING_SEMAPHORE_INIT do { \
 	if (!dev_priv->semaphore_obj) { \
-- 
1.9.2