drm/i915: Insert a command barrier on BLT/BSD cache flushes

This looked like an odd regression from

commit ec5cc0f9
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date:   Thu Jun 12 10:28:55 2014 +0100

    drm/i915: Restrict GPU boost to the RCS engine

but in reality it undercovered a much older coherency bug. The issue that
boosting the GPU frequency on the BCS ring was masking was that we could
wake the CPU up after completion of a BCS batch and inspect memory prior
to the write cache being fully evicted. In order to serialise the
breadcrumb interrupt (and so ensure that the CPU's view of memory is
coherent) we need to perform a post-sync operation in the MI_FLUSH_DW.

v2: Fix all the MI_FLUSH_DW (bsd plus the duplication in execlists).

Also fix the invalidate_domains mask in gen8_emit_flush() for ring !=
VCS.

Testcase: gpuX-rcs-gpu-read-after-write
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: stable@vger.kernel.org
Acked-by: NDaniel Vetter <daniel@ffwll.ch>
Signed-off-by: NJani Nikula <jani.nikula@intel.com>

drivers/gpu/drm/i915/intel_lrc.c

@@ -1211,15 +1211,17 @@ static int gen8_emit_flush(struct intel_ringbuffer *ringbuf,
 
 	cmd = MI_FLUSH_DW + 1;
 
-	if (ring == &dev_priv->ring[VCS]) {
-		if (invalidate_domains & I915_GEM_GPU_DOMAINS)
-			cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD |
-				MI_FLUSH_DW_STORE_INDEX |
-				MI_FLUSH_DW_OP_STOREDW;
-	} else {
-		if (invalidate_domains & I915_GEM_DOMAIN_RENDER)
-			cmd |= MI_INVALIDATE_TLB | MI_FLUSH_DW_STORE_INDEX |
-				MI_FLUSH_DW_OP_STOREDW;
+	/* We always require a command barrier so that subsequent
+	 * commands, such as breadcrumb interrupts, are strictly ordered
+	 * wrt the contents of the write cache being flushed to memory
+	 * (and thus being coherent from the CPU).
+	 */
+	cmd |= MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+
+	if (invalidate_domains & I915_GEM_GPU_DOMAINS) {
+		cmd |= MI_INVALIDATE_TLB;
+		if (ring == &dev_priv->ring[VCS])
+			cmd |= MI_INVALIDATE_BSD;
 	}
 
 	intel_logical_ring_emit(ringbuf, cmd);

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -2240,6 +2240,14 @@ static int gen6_bsd_ring_flush(struct intel_engine_cs *ring,
 	cmd = MI_FLUSH_DW;
 	if (INTEL_INFO(ring->dev)->gen >= 8)
 		cmd += 1;
+
+	/* We always require a command barrier so that subsequent
+	 * commands, such as breadcrumb interrupts, are strictly ordered
+	 * wrt the contents of the write cache being flushed to memory
+	 * (and thus being coherent from the CPU).
+	 */
+	cmd |= MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+
 	/*
 	 * Bspec vol 1c.5 - video engine command streamer:
 	 * "If ENABLED, all TLBs will be invalidated once the flush
@@ -2247,8 +2255,8 @@ static int gen6_bsd_ring_flush(struct intel_engine_cs *ring,
 	 * Post-Sync Operation field is a value of 1h or 3h."
 	 */
 	if (invalidate & I915_GEM_GPU_DOMAINS)
-		cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD |
-			MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+		cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD;
+
 	intel_ring_emit(ring, cmd);
 	intel_ring_emit(ring, I915_GEM_HWS_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT);
 	if (INTEL_INFO(ring->dev)->gen >= 8) {
@@ -2344,6 +2352,14 @@ static int gen6_ring_flush(struct intel_engine_cs *ring,
 	cmd = MI_FLUSH_DW;
 	if (INTEL_INFO(ring->dev)->gen >= 8)
 		cmd += 1;
+
+	/* We always require a command barrier so that subsequent
+	 * commands, such as breadcrumb interrupts, are strictly ordered
+	 * wrt the contents of the write cache being flushed to memory
+	 * (and thus being coherent from the CPU).
+	 */
+	cmd |= MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+
 	/*
 	 * Bspec vol 1c.3 - blitter engine command streamer:
 	 * "If ENABLED, all TLBs will be invalidated once the flush
@@ -2351,8 +2367,7 @@ static int gen6_ring_flush(struct intel_engine_cs *ring,
 	 * Post-Sync Operation field is a value of 1h or 3h."
 	 */
 	if (invalidate & I915_GEM_DOMAIN_RENDER)
-		cmd |= MI_INVALIDATE_TLB | MI_FLUSH_DW_STORE_INDEX |
-			MI_FLUSH_DW_OP_STOREDW;
+		cmd |= MI_INVALIDATE_TLB;
 	intel_ring_emit(ring, cmd);
 	intel_ring_emit(ring, I915_GEM_HWS_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT);
 	if (INTEL_INFO(ring->dev)->gen >= 8) {