drm/i915: Flush GPU relocs harder for gen3

Adding an extra MI_STORE_DWORD_IMM to the gpu relocation path for gen3
was good, but still not good enough. To survive 24+ hours under test we
needed to perform not one, not two but three extra store-dw. Doing so
for each GPU relocation was a little unsightly and since we need to
worry about userspace hitting the same issues, we should apply the dummy
store-dw into the EMIT_FLUSH.

Fixes: 7dd4f672 ("drm/i915: Async GPU relocation processing")
References: 7fa28e14 ("drm/i915: Write GPU relocs harder with gen3")
Testcase: igt/gem_tiled_fence_blits # blb/pnv
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181207134037.11848-1-chris@chris-wilson.co.uk
(cherry picked from commit a889580c)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

drivers/gpu/drm/i915/i915_gem_execbuffer.c

@@ -1268,7 +1268,7 @@ relocate_entry(struct i915_vma *vma,
 		else if (gen >= 4)
 			len = 4;
 		else
-			len = 6;
+			len = 3;
 
 		batch = reloc_gpu(eb, vma, len);
 		if (IS_ERR(batch))
@@ -1309,11 +1309,6 @@ relocate_entry(struct i915_vma *vma,
 			*batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
 			*batch++ = addr;
 			*batch++ = target_offset;
-
-			/* And again for good measure (blb/pnv) */
-			*batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
-			*batch++ = addr;
-			*batch++ = target_offset;
 		}
 
 		goto out;

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -69,19 +69,28 @@ unsigned int intel_ring_update_space(struct intel_ring *ring)
 static int
 gen2_render_ring_flush(struct i915_request *rq, u32 mode)
 {
+	unsigned int num_store_dw;
 	u32 cmd, *cs;
 
 	cmd = MI_FLUSH;
-
+	num_store_dw = 0;
 	if (mode & EMIT_INVALIDATE)
 		cmd |= MI_READ_FLUSH;
+	if (mode & EMIT_FLUSH)
+		num_store_dw = 4;
 
-	cs = intel_ring_begin(rq, 2);
+	cs = intel_ring_begin(rq, 2 + 3 * num_store_dw);
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
 	*cs++ = cmd;
-	*cs++ = MI_NOOP;
+	while (num_store_dw--) {
+		*cs++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
+		*cs++ = i915_scratch_offset(rq->i915);
+		*cs++ = 0;
+	}
+	*cs++ = MI_FLUSH | MI_NO_WRITE_FLUSH;
+
 	intel_ring_advance(rq, cs);
 
 	return 0;