diff options
author | Matthew Auld <matthew.auld@intel.com> | 2021-10-27 17:18:10 +0100 |
---|---|---|
committer | Matthew Auld <matthew.auld@intel.com> | 2021-11-02 09:43:10 +0000 |
commit | 3ea355b234d7d3e543b89e55c66d57db50ef1581 (patch) | |
tree | 44b99c866e0ca63b9cb2320b66573ecfce0704fd /drivers/gpu/drm/i915/gem/i915_gem_clflush.c | |
parent | drm/i915: Introduce refcounted sg-tables (diff) | |
download | linux-dev-3ea355b234d7d3e543b89e55c66d57db50ef1581.tar.xz linux-dev-3ea355b234d7d3e543b89e55c66d57db50ef1581.zip |
drm/i915/clflush: fixup handling of cache_dirty
In theory if clflush_work_create() somehow fails here, and we don't yet
have mm.pages populated then we end up resetting cache_dirty, which is
likely wrong, since that will potentially skip the flush-on-acquire, if
it was needed.
It looks like intel_user_framebuffer_dirty() can arrive here before the
pages are populated.
v2(Thomas):
- Move setting cache_dirty out of the async portion, also add a
comment for why that should still be safe.
v3:
- Add Thomas' irc r-b
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211027161813.3094681-1-matthew.auld@intel.com
Diffstat (limited to '')
-rw-r--r-- | drivers/gpu/drm/i915/gem/i915_gem_clflush.c | 10 |
1 files changed, 9 insertions, 1 deletions
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c index f0435c6feb68..47586a8a1b73 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c @@ -109,12 +109,20 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, I915_FENCE_GFP); dma_resv_add_excl_fence(obj->base.resv, &clflush->base.dma); dma_fence_work_commit(&clflush->base); + /* + * We must have successfully populated the pages(since we are + * holding a pin on the pages as per the flush worker) to reach + * this point, which must mean we have already done the required + * flush-on-acquire, hence resetting cache_dirty here should be + * safe. + */ + obj->cache_dirty = false; } else if (obj->mm.pages) { __do_clflush(obj); + obj->cache_dirty = false; } else { GEM_BUG_ON(obj->write_domain != I915_GEM_DOMAIN_CPU); } - obj->cache_dirty = false; return true; } |