[Intel-gfx] [PATCH 10/12] drm/i915: TLB invalidation with MI_FLUSH_SW requires a post-sync op

[Jesse Barnes]

So store into the scratch space of the HWS to make sure the invalidate
occurs.

Signed-off-by: Jesse Barnes <jbarnes at virtuousgeek.org>
---
 drivers/gpu/drm/i915/i915_reg.h         |    6 ++++--
 drivers/gpu/drm/i915/intel_ringbuffer.c |   22 ++++++++++++++++++----
 2 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 3ceeb68..d98c989 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -241,8 +241,10 @@
  */
 #define MI_LOAD_REGISTER_IMM(x)	MI_INSTR(0x22, 2*x-1)
 #define MI_FLUSH_DW		MI_INSTR(0x26, 1) /* for GEN6 */
-#define   MI_INVALIDATE_TLB	(1<<18)
-#define   MI_INVALIDATE_BSD	(1<<7)
+#define   MI_FLUSH_DW_STORE_INDEX	(1<<21)
+#define   MI_INVALIDATE_TLB		(1<<18)
+#define   MI_FLUSH_DW_OP_STOREDW	(1<<14)
+#define   MI_INVALIDATE_BSD		(1<<7)
 #define MI_BATCH_BUFFER		MI_INSTR(0x30, 1)
 #define   MI_BATCH_NON_SECURE	(1)
 #define   MI_BATCH_NON_SECURE_I965 (1<<8)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 1718c54..d3b7129 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1395,10 +1395,17 @@ static int gen6_ring_flush(struct intel_ring_buffer *ring,
 		return ret;
 
 	cmd = MI_FLUSH_DW;
+	/*
+	 * Bspec vol 1c.5 - video engine command streamer:
+	 * "If ENABLED, all TLBs will be invalidated once the flush
+	 * operation is complete. This bit is only valid when the
+	 * Post-Sync Operation field is a value of 1h or 3h."
+	 */
 	if (invalidate & I915_GEM_GPU_DOMAINS)
-		cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD;
+		cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD |
+			MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
 	intel_ring_emit(ring, cmd);
-	intel_ring_emit(ring, 0);
+	intel_ring_emit(ring, I915_GEM_SCRATCH_INDEX << 3);
 	intel_ring_emit(ring, 0);
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_advance(ring);
@@ -1436,10 +1443,17 @@ static int blt_ring_flush(struct intel_ring_buffer *ring,
 		return ret;
 
 	cmd = MI_FLUSH_DW;
+	/*
+	 * Bspec vol 1c.3 - blitter engine command streamer:
+	 * "If ENABLED, all TLBs will be invalidated once the flush
+	 * operation is complete. This bit is only valid when the
+	 * Post-Sync Operation field is a value of 1h or 3h."
+	 */
 	if (invalidate & I915_GEM_DOMAIN_RENDER)
-		cmd |= MI_INVALIDATE_TLB;
+		cmd |= MI_INVALIDATE_TLB | MI_FLUSH_DW_STORE_INDEX |
+			MI_FLUSH_DW_OP_STOREDW;
 	intel_ring_emit(ring, cmd);
-	intel_ring_emit(ring, 0);
+	intel_ring_emit(ring, I915_GEM_SCRATCH_INDEX << 3);
 	intel_ring_emit(ring, 0);
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_advance(ring);
-- 
1.7.9.5