From: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>
To: Matthew Brost <matthew.brost@intel.com>, intel-xe@lists.freedesktop.org
Subject: Re: [PATCH v5 6/6] drm/xe: Remove last fence dependency check from binds
Date: Thu, 30 Oct 2025 09:43:47 +0100 [thread overview]
Message-ID: <fbd6f305c5650ccd43721ee6fe4fd1ee87a8d611.camel@linux.intel.com> (raw)
In-Reply-To: <20251029205719.2746501-7-matthew.brost@intel.com>
On Wed, 2025-10-29 at 13:57 -0700, Matthew Brost wrote:
> Eliminate redundant last fence dependency checks in bind jobs, as
> they
> are now equivalent to xe_exec_queue_is_idle. Simplify the code by
> removing this dead logic.
>
> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> ---
> drivers/gpu/drm/xe/xe_exec_queue.c | 23 -----------------------
> drivers/gpu/drm/xe/xe_exec_queue.h | 2 --
> drivers/gpu/drm/xe/xe_pt.c | 7 -------
> 3 files changed, 32 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c
> b/drivers/gpu/drm/xe/xe_exec_queue.c
> index b7551592fe3f..3486744a8dfd 100644
> --- a/drivers/gpu/drm/xe/xe_exec_queue.c
> +++ b/drivers/gpu/drm/xe/xe_exec_queue.c
> @@ -1122,29 +1122,6 @@ void xe_exec_queue_last_fence_set(struct
> xe_exec_queue *q, struct xe_vm *vm,
> q->last_fence = dma_fence_get(fence);
> }
>
> -/**
> - * xe_exec_queue_last_fence_test_dep - Test last fence dependency of
> queue
> - * @q: The exec queue
> - * @vm: The VM the engine does a bind or exec for
> - *
> - * Returns:
> - * -ETIME if there exists an unsignalled last fence dependency, zero
> otherwise.
> - */
> -int xe_exec_queue_last_fence_test_dep(struct xe_exec_queue *q,
> struct xe_vm *vm)
> -{
> - struct dma_fence *fence;
> - int err = 0;
> -
> - fence = xe_exec_queue_last_fence_get(q, vm);
> - if (fence) {
> - err = test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence-
> >flags) ?
> - 0 : -ETIME;
> - dma_fence_put(fence);
> - }
> -
> - return err;
> -}
> -
> /**
> * xe_exec_queue_tlb_inval_last_fence_put() - Drop ref to last TLB
> invalidation fence
> * @q: The exec queue
> diff --git a/drivers/gpu/drm/xe/xe_exec_queue.h
> b/drivers/gpu/drm/xe/xe_exec_queue.h
> index 1ba7354b33d1..fda4d4f9bda8 100644
> --- a/drivers/gpu/drm/xe/xe_exec_queue.h
> +++ b/drivers/gpu/drm/xe/xe_exec_queue.h
> @@ -88,8 +88,6 @@ struct dma_fence
> *xe_exec_queue_last_fence_get_for_resume(struct xe_exec_queue *
> struct
> xe_vm *vm);
> void xe_exec_queue_last_fence_set(struct xe_exec_queue *e, struct
> xe_vm *vm,
> struct dma_fence *fence);
> -int xe_exec_queue_last_fence_test_dep(struct xe_exec_queue *q,
> - struct xe_vm *vm);
>
> void xe_exec_queue_tlb_inval_last_fence_put(struct xe_exec_queue *q,
> struct xe_vm *vm,
> diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
> index a4b9cdf016d9..01056b51ac9f 100644
> --- a/drivers/gpu/drm/xe/xe_pt.c
> +++ b/drivers/gpu/drm/xe/xe_pt.c
> @@ -1338,13 +1338,6 @@ static int xe_pt_vm_dependencies(struct
> xe_sched_job *job,
> return err;
> }
>
> - if (!(pt_update_ops->q->flags & EXEC_QUEUE_FLAG_KERNEL)) {
> - if (job)
> - err = xe_sched_job_last_fence_add_dep(job,
> vm);
> - else
> - err =
> xe_exec_queue_last_fence_test_dep(pt_update_ops->q, vm);
> - }
> -
> for (i = 0; job && !err && i < vops->num_syncs; i++)
> err = xe_sync_entry_add_deps(&vops->syncs[i], job);
>
next prev parent reply other threads:[~2025-10-30 8:43 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-29 20:57 [PATCH v5 0/6] Fix serialization on burst of unbinds - v2 Matthew Brost
2025-10-29 20:57 ` [PATCH v5 1/6] drm/xe: Enforce correct user fence signaling order using drm_syncobjs Matthew Brost
2025-10-30 7:58 ` Thomas Hellström
2025-10-30 12:54 ` Matthew Brost
2025-10-29 20:57 ` [PATCH v5 2/6] drm/xe: Attach last fence to TLB invalidation job queues Matthew Brost
2025-10-30 8:24 ` Thomas Hellström
2025-10-29 20:57 ` [PATCH v5 3/6] drm/xe: Decouple bind queue last fence from TLB invalidations Matthew Brost
2025-10-30 9:52 ` Thomas Hellström
2025-10-29 20:57 ` [PATCH v5 4/6] drm/xe: Skip TLB invalidation waits in page fault binds Matthew Brost
2025-11-03 15:19 ` Thomas Hellström
2025-10-29 20:57 ` [PATCH v5 5/6] drm/xe: Disallow input fences on zero batch execs and zero binds Matthew Brost
2025-11-03 15:21 ` Thomas Hellström
2025-11-03 15:22 ` Thomas Hellström
2025-10-29 20:57 ` [PATCH v5 6/6] drm/xe: Remove last fence dependency check from binds Matthew Brost
2025-10-30 8:43 ` Thomas Hellström [this message]
2025-11-03 15:24 ` Thomas Hellström
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=fbd6f305c5650ccd43721ee6fe4fd1ee87a8d611.camel@linux.intel.com \
--to=thomas.hellstrom@linux.intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=matthew.brost@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox