From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 30 Jan 2018 16:44:57 +0000
Subject: drm/i915: Flush ggtt writes through the old fenced vma before
 changing fences
Git-commit: 5b364bec5cbfd6c23505952a40150b053ec551d1
Patch-mainline: v4.17-rc1
References: FATE#326289 FATE#326079 FATE#326049 FATE#322398 FATE#326166

This is a precautionary measure as I have no evidence to suggest we've
hit a bug here (I was hoping this might explain gdg's odd behaviour, but
alas), but given that we have a function to flush the ggtt writes it
seems prudent to use it prior to changing the fence register. Due to the
intrinsic nature of the GTT often operating as an independent mmio path,
we should not just rely on the write to the fence acting as a full flush
for GTT writes.

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/20180130164457.14037-1-chris@chris-wilson.co.uk

Acked-by: Petr Tesarik <ptesarik@suse.com>
---
 drivers/gpu/drm/i915/i915_gem_fence_reg.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

--- a/drivers/gpu/drm/i915/i915_gem_fence_reg.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
@@ -230,10 +230,14 @@ static int fence_update(struct drm_i915_
 	}
 
 	if (fence->vma) {
-		ret = i915_gem_active_retire(&fence->vma->last_fence,
-				      &fence->vma->obj->base.dev->struct_mutex);
+		struct i915_vma *old = fence->vma;
+
+		ret = i915_gem_active_retire(&old->last_fence,
+					     &old->obj->base.dev->struct_mutex);
 		if (ret)
 			return ret;
+
+		i915_vma_flush_writes(old);
 	}
 
 	if (fence->vma && fence->vma != vma) {