dma-buf: Relax the write-seqlock for reallocating the shared fence list

As the set of shared fences is not being changed during reallocation of
the reservation list, we can skip updating the write_seqlock.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20190712080314.21018-2-chris@chris-wilson.co.uk
This commit is contained in:
Chris Wilson 2019-07-12 09:03:14 +01:00
parent 45b2fda3d8
commit 30fe7b07f6

View file

@ -157,15 +157,15 @@ int reservation_object_reserve_shared(struct reservation_object *obj,
(ksize(new) - offsetof(typeof(*new), shared)) / (ksize(new) - offsetof(typeof(*new), shared)) /
sizeof(*new->shared); sizeof(*new->shared);
preempt_disable();
write_seqcount_begin(&obj->seq);
/* /*
* RCU_INIT_POINTER can be used here, * We are not changing the effective set of fences here so can
* seqcount provides the necessary barriers * merely update the pointer to the new array; both existing
* readers and new readers will see exactly the same set of
* active (unsignaled) shared fences. Individual fences and the
* old array are protected by RCU and so will not vanish under
* the gaze of the rcu_read_lock() readers.
*/ */
RCU_INIT_POINTER(obj->fence, new); rcu_assign_pointer(obj->fence, new);
write_seqcount_end(&obj->seq);
preempt_enable();
if (!old) if (!old)
return 0; return 0;