drm/i915: TLB invalidation with MI_FLUSH_DW requires a post-sync op v3

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

v2: use GTT address space for store, clean up #defines (Chris)
v3: use correct #define in blt ring flush (Chris)
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NAntti Koskipää <antti.koskipaa@intel.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
References: https://bugs.launchpad.net/ubuntu/+source/xserver-xorg-video-intel/+bug/1063252Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/i915_reg.h

@@ -242,8 +242,12 @@
  */
 #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_FLUSH_DW_USE_GTT		(1<<2)
+#define   MI_FLUSH_DW_USE_PPGTT		(0<<2)
 #define MI_BATCH_BUFFER		MI_INSTR(0x30, 1)
 #define   MI_BATCH_NON_SECURE		(1)
 /* for snb/ivb/vlv this also means "batch in ppgtt" when ppgtt is enabled. */

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_HWS_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT);
 	intel_ring_emit(ring, 0);
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_advance(ring);
@@ -1460,10 +1467,17 @@ 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 | MI_FLUSH_DW_OP_STOREDW;
 	intel_ring_emit(ring, cmd);
-	intel_ring_emit(ring, 0);
+	intel_ring_emit(ring, I915_GEM_HWS_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT);
 	intel_ring_emit(ring, 0);
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_advance(ring);

drivers/gpu/drm/i915/intel_ringbuffer.h

@@ -183,6 +183,8 @@ intel_read_status_page(struct intel_ring_buffer *ring,
  * The area from dword 0x20 to 0x3ff is available for driver usage.
  */
 #define I915_GEM_HWS_INDEX		0x20
+#define I915_GEM_HWS_SCRATCH_INDEX	0x30
+#define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT)
 
 void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring);