| Message ID | 20200403160951.8271-1-chris@chris-wilson.co.uk (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | drm/i915: Revoke mmap before fence | expand |
On Fri, 3 Apr 2020 at 17:10, Chris Wilson <chris@chris-wilson.co.uk> wrote: > > 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@chris-wilson.co.uk> > Cc: Matthew Auld <matthew.auld@intel.com> Reviewed-by: Matthew Auld <matthew.auld@intel.com>
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)); }
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@chris-wilson.co.uk> Cc: Matthew Auld <matthew.auld@intel.com> --- drivers/gpu/drm/i915/i915_vma.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)