drm/i915: Apply post-sync write for pipe control invalidates

When invalidating the TLBs it is documentated as requiring a post-sync
write. Failure to do so seems to result in a GPU hang.

Exposure to this hang on IVB seems to be a result of removing the extra
stalls required for SNB pipecontrol workarounds:

commit 6c6cf5aa9c583478b19e23149feaa92d01fb8c2d
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date:   Fri Jul 20 18:02:28 2012 +0100

    drm/i915: Only apply the SNB pipe control w/a to gen6

Note: Manually switch the pipe_control cmd to 4 dwords to avoid a
(silent) functional conflict with -next. This way will get a loud (but
conflict with next (since the scratch_addr has been deleted there).

Reported-and-tested-by: yex.tian@intel.com
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=53322
Acked-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: added note about merge conflict with -next.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -227,31 +227,36 @@ gen6_render_ring_flush(struct intel_ring_buffer *ring,
 	 * number of bits based on the write domains has little performance
 	 * impact.
 	 */
-	flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
-	flags |= PIPE_CONTROL_TLB_INVALIDATE;
-	flags |= PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE;
-	flags |= PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE;
-	flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
-	flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
-	flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
-	flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
-	/*
-	 * Ensure that any following seqno writes only happen when the render
-	 * cache is indeed flushed (but only if the caller actually wants that).
-	 */
-	if (flush_domains)
+	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;
+		flags |= PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
+		/*
+		 * TLB invalidate requires a post-sync write.
+		 */
+		flags |= PIPE_CONTROL_QW_WRITE;
+	}
 
-	ret = intel_ring_begin(ring, 6);
+	ret = intel_ring_begin(ring, 4);
 	if (ret)
 		return ret;
 
-	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(5));
+	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4));
 	intel_ring_emit(ring, flags);
 	intel_ring_emit(ring, scratch_addr | PIPE_CONTROL_GLOBAL_GTT);
-	intel_ring_emit(ring, 0); /* lower dword */
-	intel_ring_emit(ring, 0); /* uppwer dword */
-	intel_ring_emit(ring, MI_NOOP);
+	intel_ring_emit(ring, 0);
 	intel_ring_advance(ring);
 
 	return 0;