[Intel-gfx] [PATCH] drm/i915: Revoke mmap before fence

[Chris Wilson]

Make sure we revoke the user's mmaps of this vma to force them to take a
pagefault *before* we remove the associated aperture detiling register.

Fixes: 0d86ee35097a ("drm/i915/gt: Make fence revocation unequivocal")
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld at intel.com>
---
 drivers/gpu/drm/i915/i915_vma.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 4cdd883f9d66..42b2f24c8568 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -1258,6 +1258,9 @@ int __i915_vma_unbind(struct i915_vma *vma)
 	GEM_BUG_ON(i915_vma_is_active(vma));
 
 	if (i915_vma_is_map_and_fenceable(vma)) {
+		/* Force a pagefault for domain tracking on next user access */
+		i915_vma_revoke_mmap(vma);
+
 		/*
 		 * Check that we have flushed all writes through the GGTT
 		 * before the unbind, other due to non-strict nature of those
@@ -1276,9 +1279,6 @@ int __i915_vma_unbind(struct i915_vma *vma)
 		/* release the fence reg _after_ flushing */
 		i915_vma_revoke_fence(vma);
 
-		/* Force a pagefault for domain tracking on next user access */
-		i915_vma_revoke_mmap(vma);
-
 		__i915_vma_iounmap(vma);
 		clear_bit(I915_VMA_CAN_FENCE_BIT, __i915_vma_flags(vma));
 	}
-- 
2.20.1