On 12/14/2021 11:59, Matthew Brost wrote:
Increment composite fence seqno on each fence creation.
Fixes: 544460c33821 ("drm/i915: Multi-BB execbuf")
Signed-off-by: Matthew Brost <[email protected]>
---
drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 2213f7b613da..96cf8361b017 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -3113,7 +3113,7 @@ eb_composite_fence_create(struct i915_execbuffer *eb, int
out_fence_fd)
fence_array = dma_fence_array_create(eb->num_batches,
fences,
eb->context->parallel.fence_context,
- eb->context->parallel.seqno,
+ eb->context->parallel.seqno++,
As is, this change looks good. So:
Reviewed-by: John Harrison <[email protected]>
However, just spotted that dma_fence_array_create() takes the seqno
value as an 'unsigned' even though it passes it on to an underlying
dma-fence as a u64 (and all other dma-fence code uses u64 seqnos). That
should probably be fixed (and our context::parallel::seqno changed from
u32 to u64).
John.
false);
if (!fence_array) {
kfree(fences);
