[Intel-gfx] [PATCH 4/4] drm/i915: add one more workaround to gen7_render_ring_flush

[Paulo Zanoni]

From: Paulo Zanoni <paulo.r.zanoni at intel.com>

The combination of this commit + the previous one prevents the dozens
of GPU hangs I'm seeing on my gen 7.5 machine.

Signed-off-by: Paulo Zanoni <paulo.r.zanoni at intel.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 9895a6e..7c0bc96 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -290,6 +290,15 @@ gen7_render_ring_flush(struct intel_ring_buffer *ring,
 	u32 scratch_addr = pc->gtt_offset + 128;
 	int ret;
 
+	/*
+	 * Ensure that any following seqno writes only happen when the render
+	 * cache is indeed flushed.
+	 * The documentation also mentions that every 4th PIPE_CONTROL command
+	 * (except the ones with only read-cache invalidate bits set) must have
+	 * the CS_STALL bit set.
+	 */
+	flags |= PIPE_CONTROL_CS_STALL;
+
 	/* Just flush everything.  Experiments have shown that reducing the
 	 * number of bits based on the write domains has little performance
 	 * impact.
@@ -297,11 +306,6 @@ gen7_render_ring_flush(struct intel_ring_buffer *ring,
 	if (flush_domains) {
 		flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
 		flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
-		/*
-		 * Ensure that any following seqno writes only happen
-		 * when the render cache is indeed flushed.
-		 */
-		flags |= PIPE_CONTROL_CS_STALL;
 	}
 	if (invalidate_domains) {
 		flags |= PIPE_CONTROL_TLB_INVALIDATE;
-- 
1.7.11.2