1 files changed, 36 insertions, 2 deletions

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index b8a7a014d46d..87eebc13c0d8 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -91,6 +91,7 @@ static int
 gen4_render_ring_flush(struct i915_request *rq, u32 mode)
 {
         u32 cmd, *cs;
+        int i;
 
         /*
          * read/write caches:
@@ -127,12 +128,45 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode)
                         cmd |= MI_INVALIDATE_ISP;
         }
 
-        cs = intel_ring_begin(rq, 2);
+        i = 2;
+        if (mode & EMIT_INVALIDATE)
+                i += 20;
+
+        cs = intel_ring_begin(rq, i);
         if (IS_ERR(cs))
                 return PTR_ERR(cs);
 
         *cs++ = cmd;
-        *cs++ = MI_NOOP;
+
+        /*
+         * A random delay to let the CS invalidate take effect? Without this
+         * delay, the GPU relocation path fails as the CS does not see
+         * the updated contents. Just as important, if we apply the flushes
+         * to the EMIT_FLUSH branch (i.e. immediately after the relocation
+         * write and before the invalidate on the next batch), the relocations
+         * still fail. This implies that is a delay following invalidation
+         * that is required to reset the caches as opposed to a delay to
+         * ensure the memory is written.
+         */
+        if (mode & EMIT_INVALIDATE) {
+                *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE;
+                *cs++ = i915_ggtt_offset(rq->engine->scratch) |
+                        PIPE_CONTROL_GLOBAL_GTT;
+                *cs++ = 0;
+                *cs++ = 0;
+
+                for (i = 0; i < 12; i++)
+                        *cs++ = MI_FLUSH;
+
+                *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE;
+                *cs++ = i915_ggtt_offset(rq->engine->scratch) |
+                        PIPE_CONTROL_GLOBAL_GTT;
+                *cs++ = 0;
+                *cs++ = 0;
+        }
+
+        *cs++ = cmd;
+
         intel_ring_advance(rq, cs);
 
         return 0;