Currently, we only allow ourselves to prune the fences so long as
all the waits completed (i.e. all the fences we checked were signaled),
and that the reservation snapshot did not change across the wait.
However, if we only waited for a subset of the reservation object, i.e.
just waiting for the last writer to complete as opposed to all readers
as well, then we would erroneously conclude we could prune the fences as
indeed although all of our waits were successful, they did not represent
the totality of the reservation object.
Fixes: e54ca9774777 ("drm/i915: Remove completed fences after a wait")
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx>
Cc: Matthew Auld <matthew.auld@xxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gem.c | 9 +++------
1 file changed, 3 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index a5bd07338b46..e3e52b9a74e9 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -407,7 +407,7 @@ i915_gem_object_wait_reservation(struct reservation_object *resv,
{
unsigned int seq = __read_seqcount_begin(&resv->seq);
struct dma_fence *excl;
- bool prune_fences = false;
+ bool prune_fences;
if (flags & I915_WAIT_ALL) {
struct dma_fence **shared;
@@ -432,17 +432,13 @@ i915_gem_object_wait_reservation(struct reservation_object *resv,
for (; i < count; i++)
dma_fence_put(shared[i]);
kfree(shared);
-
- prune_fences = count && timeout >= 0;
} else {
excl = reservation_object_get_excl_rcu(resv);
}
- if (excl && timeout >= 0) {
+ if (excl && timeout >= 0)
timeout = i915_gem_object_wait_fence(excl, flags, timeout,
rps_client);
- prune_fences = timeout >= 0;
- }
dma_fence_put(excl);
@@ -450,6 +446,7 @@ i915_gem_object_wait_reservation(struct reservation_object *resv,
* signaled and that the reservation object has not been changed (i.e.
* no new fences have been added).
*/
+ prune_fences = flags & I915_WAIT_ALL && timeout >= 0;
if (prune_fences && !__read_seqcount_retry(&resv->seq, seq)) {
if (reservation_object_trylock(resv)) {
if (!__read_seqcount_retry(&resv->seq, seq))
--
2.16.2
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
