On 5/9/25 17:33, Tvrtko Ursulin wrote:
> With the goal of reducing the need for drivers to touch (and dereference)
> fence->ops, we change the prototype of __dma_fence_is_later() to take
> fence instead of fence->ops.
>
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursu...@igalia.com>
Reviewed-by: Christian König <christian.koe...@amd.com>
> ---
> drivers/dma-buf/dma-fence-chain.c | 2 +-
> drivers/dma-buf/sw_sync.c | 2 +-
> drivers/gpu/drm/xe/xe_hw_fence.c | 2 +-
> drivers/gpu/drm/xe/xe_sched_job.c | 14 ++++++++------
> include/linux/dma-fence.h | 9 ++++-----
> 5 files changed, 15 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/dma-buf/dma-fence-chain.c
> b/drivers/dma-buf/dma-fence-chain.c
> index 9663ba1bb6ac..90424f23fd73 100644
> --- a/drivers/dma-buf/dma-fence-chain.c
> +++ b/drivers/dma-buf/dma-fence-chain.c
> @@ -252,7 +252,7 @@ void dma_fence_chain_init(struct dma_fence_chain *chain,
> chain->prev_seqno = 0;
>
> /* Try to reuse the context of the previous chain node. */
> - if (prev_chain && __dma_fence_is_later(seqno, prev->seqno, prev->ops)) {
> + if (prev_chain && __dma_fence_is_later(prev, seqno, prev->seqno)) {
> context = prev->context;
> chain->prev_seqno = prev->seqno;
> } else {
> diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c
> index 4f27ee93a00c..3c20f1d31cf5 100644
> --- a/drivers/dma-buf/sw_sync.c
> +++ b/drivers/dma-buf/sw_sync.c
> @@ -170,7 +170,7 @@ static bool timeline_fence_signaled(struct dma_fence
> *fence)
> {
> struct sync_timeline *parent = dma_fence_parent(fence);
>
> - return !__dma_fence_is_later(fence->seqno, parent->value, fence->ops);
> + return !__dma_fence_is_later(fence, fence->seqno, parent->value);
> }
>
> static void timeline_fence_set_deadline(struct dma_fence *fence, ktime_t
> deadline)
> diff --git a/drivers/gpu/drm/xe/xe_hw_fence.c
> b/drivers/gpu/drm/xe/xe_hw_fence.c
> index 0b4f12be3692..03eb8c6d1616 100644
> --- a/drivers/gpu/drm/xe/xe_hw_fence.c
> +++ b/drivers/gpu/drm/xe/xe_hw_fence.c
> @@ -165,7 +165,7 @@ static bool xe_hw_fence_signaled(struct dma_fence
> *dma_fence)
> u32 seqno = xe_map_rd(xe, &fence->seqno_map, 0, u32);
>
> return dma_fence->error ||
> - !__dma_fence_is_later(dma_fence->seqno, seqno, dma_fence->ops);
> + !__dma_fence_is_later(dma_fence, dma_fence->seqno, seqno);
> }
>
> static bool xe_hw_fence_enable_signaling(struct dma_fence *dma_fence)
> diff --git a/drivers/gpu/drm/xe/xe_sched_job.c
> b/drivers/gpu/drm/xe/xe_sched_job.c
> index 1905ca590965..f0a6ce610948 100644
> --- a/drivers/gpu/drm/xe/xe_sched_job.c
> +++ b/drivers/gpu/drm/xe/xe_sched_job.c
> @@ -216,15 +216,17 @@ void xe_sched_job_set_error(struct xe_sched_job *job,
> int error)
>
> bool xe_sched_job_started(struct xe_sched_job *job)
> {
> + struct dma_fence *fence = dma_fence_chain_contained(job->fence);
> struct xe_lrc *lrc = job->q->lrc[0];
>
> - return !__dma_fence_is_later(xe_sched_job_lrc_seqno(job),
> - xe_lrc_start_seqno(lrc),
> -
> dma_fence_chain_contained(job->fence)->ops);
> + return !__dma_fence_is_later(fence,
> + xe_sched_job_lrc_seqno(job),
> + xe_lrc_start_seqno(lrc));
> }
>
> bool xe_sched_job_completed(struct xe_sched_job *job)
> {
> + struct dma_fence *fence = dma_fence_chain_contained(job->fence);
> struct xe_lrc *lrc = job->q->lrc[0];
>
> /*
> @@ -232,9 +234,9 @@ bool xe_sched_job_completed(struct xe_sched_job *job)
> * parallel handshake is done.
> */
>
> - return !__dma_fence_is_later(xe_sched_job_lrc_seqno(job),
> - xe_lrc_seqno(lrc),
> -
> dma_fence_chain_contained(job->fence)->ops);
> + return !__dma_fence_is_later(fence,
> + xe_sched_job_lrc_seqno(job),
> + xe_lrc_seqno(lrc));
> }
>
> void xe_sched_job_arm(struct xe_sched_job *job)
> diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
> index b12776883d14..48b5202c531d 100644
> --- a/include/linux/dma-fence.h
> +++ b/include/linux/dma-fence.h
> @@ -441,21 +441,20 @@ dma_fence_is_signaled(struct dma_fence *fence)
>
> /**
> * __dma_fence_is_later - return if f1 is chronologically later than f2
> + * @fence: fence in whose context to do the comparison
> * @f1: the first fence's seqno
> * @f2: the second fence's seqno from the same context
> - * @ops: dma_fence_ops associated with the seqno
> *
> * Returns true if f1 is chronologically later than f2. Both fences must be
> * from the same context, since a seqno is not common across contexts.
> */
> -static inline bool __dma_fence_is_later(u64 f1, u64 f2,
> - const struct dma_fence_ops *ops)
> +static inline bool __dma_fence_is_later(struct dma_fence *fence, u64 f1, u64
> f2)
> {
> /* This is for backward compatibility with drivers which can only handle
> * 32bit sequence numbers. Use a 64bit compare when the driver says to
> * do so.
> */
> - if (ops->use_64bit_seqno)
> + if (fence->ops->use_64bit_seqno)
> return f1 > f2;
>
> return (int)(lower_32_bits(f1) - lower_32_bits(f2)) > 0;
> @@ -475,7 +474,7 @@ static inline bool dma_fence_is_later(struct dma_fence
> *f1,
> if (WARN_ON(f1->context != f2->context))
> return false;
>
> - return __dma_fence_is_later(f1->seqno, f2->seqno, f1->ops);
> + return __dma_fence_is_later(f1, f1->seqno, f2->seqno);
> }
>
> /**
