AMD-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Philipp Stanner <phasta@mailbox.org>
To: "Christian König" <ckoenig.leichtzumerken@gmail.com>,
	alexdeucher@gmail.com, simona.vetter@ffwll.ch,
	tursulin@ursulin.net, matthew.brost@intel.com,
	dri-devel@lists.freedesktop.org, amd-gfx@lists.freedesktop.org,
	linaro-mm-sig@lists.linaro.org, sumit.semwal@linaro.org
Subject: Re: [PATCH 09/18] drm/amdgpu: fix KFD eviction fence enable_signaling path
Date: Thu, 27 Nov 2025 11:57:25 +0100	[thread overview]
Message-ID: <cbf607a647ab40ef800b3deb23f7b9c14f0b38e7.camel@mailbox.org> (raw)
In-Reply-To: <20251113145332.16805-10-christian.koenig@amd.com>

On Thu, 2025-11-13 at 15:51 +0100, Christian König wrote:
> Calling dma_fence_is_signaled() here is illegal!

OK, but why is that patch in this series?

P.

> 
> Signed-off-by: Christian König <christian.koenig@amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c | 6 ------
>  1 file changed, 6 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c
> index 1ef758ac5076..09c919f72b6c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c
> @@ -120,12 +120,6 @@ static bool amdkfd_fence_enable_signaling(struct dma_fence *f)
>  {
>  	struct amdgpu_amdkfd_fence *fence = to_amdgpu_amdkfd_fence(f);
>  
> -	if (!fence)
> -		return false;
> -
> -	if (dma_fence_is_signaled(f))
> -		return true;
> -
>  	if (!fence->svm_bo) {
>  		if (!kgd2kfd_schedule_evict_and_restore_process(fence->mm, f))
>  			return true;


  reply	other threads:[~2025-11-28  8:35 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-11-13 14:51 Independence for dma_fences! v3 Christian König
2025-11-13 14:51 ` [PATCH 01/18] dma-buf: cleanup dma_fence_describe v3 Christian König
2025-11-20 14:09   ` Tvrtko Ursulin
2025-11-27 10:17   ` Philipp Stanner
2025-11-13 14:51 ` [PATCH 02/18] dma-buf: protected fence ops by RCU v3 Christian König
2025-11-14 10:50   ` Tvrtko Ursulin
2025-11-18 14:28     ` Christian König
2025-11-18 16:03       ` Tvrtko Ursulin
2025-11-20 14:03         ` Christian König
2025-11-20 14:08           ` Tvrtko Ursulin
2025-11-13 14:51 ` [PATCH 03/18] dma-buf: detach fence ops on signal v2 Christian König
2025-11-20 14:14   ` Tvrtko Ursulin
2025-11-27 10:29   ` Philipp Stanner
2025-11-13 14:51 ` [PATCH 04/18] dma-buf: inline spinlock for fence protection v2 Christian König
2025-11-13 20:49   ` kernel test robot
2025-11-14  7:30   ` kernel test robot
2025-11-14 11:49   ` Tvrtko Ursulin
2025-11-27 10:44   ` Philipp Stanner
2025-11-13 14:51 ` [PATCH 05/18] dma-buf: use inline lock for the stub fence Christian König
2025-11-27 10:50   ` Philipp Stanner
2025-11-28 12:31     ` Christian König
2025-11-13 14:51 ` [PATCH 06/18] dma-buf: use inline lock for the dma-fence-array Christian König
2025-11-27 10:51   ` Philipp Stanner
2025-11-13 14:51 ` [PATCH 07/18] dma-buf: use inline lock for the dma-fence-chain Christian König
2025-11-27 10:52   ` Philipp Stanner
2025-11-13 14:51 ` [PATCH 08/18] drm/sched: use inline locks for the drm-sched-fence Christian König
2025-11-13 16:23   ` Philipp Stanner
2025-11-17 15:32     ` Christian König
2025-11-18  7:10       ` Philipp Stanner
2025-11-20 14:17   ` Tvrtko Ursulin
2025-11-13 14:51 ` [PATCH 09/18] drm/amdgpu: fix KFD eviction fence enable_signaling path Christian König
2025-11-27 10:57   ` Philipp Stanner [this message]
2025-11-28 10:01     ` Christian König
2025-11-13 14:51 ` [PATCH 10/18] drm/amdgpu: independence for the amdgpu_fence! Christian König
2025-11-20 14:42   ` Tvrtko Ursulin
2025-11-13 14:51 ` [PATCH 11/18] drm/amdgpu: independence for the amdgpu_eviction_fence! Christian König
2025-11-27 11:02   ` Philipp Stanner
2025-11-13 14:51 ` [PATCH 12/18] drm/amdgpu: independence for the amdgpu_vm_tlb_fence! Christian König
2025-11-13 14:51 ` [PATCH 13/18] drm/amdgpu: independence for the amdkfd_fence! v2 Christian König
2025-11-14 11:43   ` kernel test robot
2025-11-27 11:10   ` Philipp Stanner
2025-11-28 10:06     ` Christian König
2025-11-28 10:10       ` Philipp Stanner
2025-11-28 10:12         ` Christian König
2025-11-13 14:51 ` [PATCH 14/18] drm/amdgpu: independence for the amdgpu_userq__fence! Christian König
2025-11-13 14:51 ` [PATCH 15/18] drm/xe: Disconnect the low hanging fences from Xe module Christian König
2025-11-13 14:51 ` [PATCH 16/18] drm/xe: Drop HW fence slab Christian König
2025-11-13 14:51 ` [PATCH 17/18] drm/xe: Promote xe_hw_fence_irq to an ref counted object Christian König
2025-11-13 14:51 ` [PATCH 18/18] drm/xe: Finish disconnect HW fences from module Christian König
2025-11-27 11:17   ` Philipp Stanner
2025-11-13 16:20 ` Independence for dma_fences! v3 Philipp Stanner
2025-11-17 15:28   ` Christian König

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=cbf607a647ab40ef800b3deb23f7b9c14f0b38e7.camel@mailbox.org \
    --to=phasta@mailbox.org \
    --cc=alexdeucher@gmail.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=ckoenig.leichtzumerken@gmail.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=linaro-mm-sig@lists.linaro.org \
    --cc=matthew.brost@intel.com \
    --cc=phasta@kernel.org \
    --cc=simona.vetter@ffwll.ch \
    --cc=sumit.semwal@linaro.org \
    --cc=tursulin@ursulin.net \
    /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