From: "Christian König" <christian.koenig@amd.com>
To: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>,
Alex Deucher <alexander.deucher@amd.com>,
David Airlie <airlied@gmail.com>, Simona Vetter <simona@ffwll.ch>,
Felix Kuehling <Felix.Kuehling@amd.com>,
Harry Wentland <harry.wentland@amd.com>,
Leo Li <sunpeng.li@amd.com>,
Rodrigo Siqueira <siqueira@igalia.com>
Cc: amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v1 12/20] drm/amdgpu: use TTM_FENCES_MAX_SLOT_COUNT
Date: Wed, 5 Nov 2025 09:36:41 +0100 [thread overview]
Message-ID: <23715885-c050-4f19-a964-30cd0e511d8a@amd.com> (raw)
In-Reply-To: <20251104083605.13677-13-pierre-eric.pelloux-prayer@amd.com>
On 11/4/25 09:35, Pierre-Eric Pelloux-Prayer wrote:
> Use TTM_FENCES_MAX_SLOT_COUNT as an upperbound of how many fences
> ttm might need to deal with moves/evictions.
>
> Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 5 ++---
> drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 2 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c | 2 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 3 ++-
> drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 2 +-
> drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c | 2 +-
> drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c | 2 +-
> 7 files changed, 9 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> index ecdfe6cb36cc..b232ed28872b 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> @@ -916,9 +916,8 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
> goto out_free_user_pages;
>
> amdgpu_bo_list_for_each_entry(e, p->bo_list) {
> - /* One fence for TTM and one for each CS job */
> r = drm_exec_prepare_obj(&p->exec, &e->bo->tbo.base,
> - 1 + p->gang_size);
> + TTM_FENCES_MAX_SLOT_COUNT + p->gang_size);
> drm_exec_retry_on_contention(&p->exec);
> if (unlikely(r))
> goto out_free_user_pages;
> @@ -928,7 +927,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
>
> if (p->uf_bo) {
> r = drm_exec_prepare_obj(&p->exec, &p->uf_bo->tbo.base,
> - 1 + p->gang_size);
> + TTM_FENCES_MAX_SLOT_COUNT + p->gang_size);
> drm_exec_retry_on_contention(&p->exec);
> if (unlikely(r))
> goto out_free_user_pages;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> index ce073e894584..f773b06dd135 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> @@ -353,7 +353,7 @@ static void amdgpu_gem_object_close(struct drm_gem_object *obj,
>
> drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES, 0);
> drm_exec_until_all_locked(&exec) {
> - r = drm_exec_prepare_obj(&exec, &bo->tbo.base, 1);
> + r = drm_exec_prepare_obj(&exec, &bo->tbo.base, TTM_FENCES_MAX_SLOT_COUNT);
> drm_exec_retry_on_contention(&exec);
> if (unlikely(r))
> goto out_unlock;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
> index 79bad9cbe2ab..d9bb16186e1f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
> @@ -326,7 +326,7 @@ static int amdgpu_vkms_prepare_fb(struct drm_plane *plane,
> return r;
> }
>
> - r = dma_resv_reserve_fences(rbo->tbo.base.resv, 1);
> + r = dma_resv_reserve_fences(rbo->tbo.base.resv, TTM_FENCES_MAX_SLOT_COUNT);
> if (r) {
> dev_err(adev->dev, "allocating fence slot failed (%d)\n", r);
While at it please also drop this error message. It is absolutely not helpful at all.
> goto error_unlock;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> index 2f8e83f840a8..bc11e212f08c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> @@ -2630,7 +2630,8 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
> }
>
> amdgpu_vm_bo_base_init(&vm->root, vm, root_bo);
> - r = dma_resv_reserve_fences(root_bo->tbo.base.resv, 1);
> + r = dma_resv_reserve_fences(root_bo->tbo.base.resv,
> + TTM_FENCES_MAX_SLOT_COUNT);
> if (r)
> goto error_free_root;
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> index ffb7b36e577c..ea8dd17e2852 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> @@ -627,7 +627,7 @@ svm_range_vram_node_new(struct kfd_node *node, struct svm_range *prange,
> }
> }
>
> - r = dma_resv_reserve_fences(bo->tbo.base.resv, 1);
> + r = dma_resv_reserve_fences(bo->tbo.base.resv, TTM_FENCES_MAX_SLOT_COUNT);
> if (r) {
> pr_debug("failed %d to reserve bo\n", r);
Same here.
> amdgpu_bo_unreserve(bo);
> diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
> index 56cb866ac6f8..1f2a5dcfa3e5 100644
> --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
> +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
> @@ -952,7 +952,7 @@ static int amdgpu_dm_plane_helper_prepare_fb(struct drm_plane *plane,
> return r;
> }
>
> - r = dma_resv_reserve_fences(rbo->tbo.base.resv, 1);
> + r = dma_resv_reserve_fences(rbo->tbo.base.resv, TTM_FENCES_MAX_SLOT_COUNT);
> if (r) {
> drm_err(adev_to_drm(adev), "reserving fence slot failed (%d)\n", r);
And here.
> goto error_unlock;
> diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c
> index d9527c05fc87..60b57d213bdd 100644
> --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c
> +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c
> @@ -106,7 +106,7 @@ static int amdgpu_dm_wb_prepare_job(struct drm_writeback_connector *wb_connector
> return r;
> }
>
> - r = dma_resv_reserve_fences(rbo->tbo.base.resv, 1);
> + r = dma_resv_reserve_fences(rbo->tbo.base.resv, TTM_FENCES_MAX_SLOT_COUNT);
> if (r) {
> drm_err(adev_to_drm(adev), "reserving fence slot failed (%d)\n", r);
And here.
Regards,
Christian.
> goto error_unlock;
next prev parent reply other threads:[~2025-11-05 8:36 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-11-04 8:35 [PATCH v1 00/20] drm/amdgpu: use all SDMA instances for TTM clears and moves Pierre-Eric Pelloux-Prayer
2025-11-04 8:35 ` [PATCH v1 01/20] drm/amdgpu: give each kernel job a unique id Pierre-Eric Pelloux-Prayer
2025-11-04 13:58 ` Christian König
2025-11-04 8:35 ` [PATCH v1 02/20] drm/ttm: rework pipelined eviction fence handling Pierre-Eric Pelloux-Prayer
2025-11-04 14:12 ` Christian König
2025-11-05 10:34 ` Pierre-Eric Pelloux-Prayer
2025-11-05 13:00 ` Christian König
2025-11-04 8:35 ` [PATCH v1 03/20] drm/amdgpu: remove direct_submit arg from amdgpu_copy_buffer Pierre-Eric Pelloux-Prayer
2025-11-04 14:13 ` Christian König
2025-11-04 8:35 ` [PATCH v1 04/20] drm/amdgpu: introduce amdgpu_ttm_entity Pierre-Eric Pelloux-Prayer
2025-11-04 15:13 ` Christian König
2025-11-04 8:35 ` [PATCH v1 05/20] drm/amdgpu: pass the entity to use to ttm functions Pierre-Eric Pelloux-Prayer
2025-11-04 8:35 ` [PATCH v1 06/20] drm/amdgpu: statically assign gart windows to ttm entities Pierre-Eric Pelloux-Prayer
2025-11-04 8:35 ` [PATCH v1 07/20] drm/amdgpu: allocate multiple clear entities Pierre-Eric Pelloux-Prayer
2025-11-04 8:35 ` [PATCH v1 08/20] drm/amdgpu: allocate multiple move entities Pierre-Eric Pelloux-Prayer
2025-11-04 8:35 ` [PATCH v1 09/20] drm/amdgpu: pass optional dependency to amdgpu_fill_buffer Pierre-Eric Pelloux-Prayer
2025-11-04 8:35 ` [PATCH v1 10/20] drm/amdgpu: prepare amdgpu_fill_buffer to use N entities Pierre-Eric Pelloux-Prayer
2025-11-04 8:35 ` [PATCH v1 11/20] drm/amdgpu: use multiple entities in amdgpu_fill_buffer Pierre-Eric Pelloux-Prayer
2025-11-04 16:40 ` Christian König
2025-11-05 10:39 ` Pierre-Eric Pelloux-Prayer
2025-11-05 13:03 ` Christian König
2025-11-12 10:39 ` Pierre-Eric Pelloux-Prayer
2025-11-04 8:35 ` [PATCH v1 12/20] drm/amdgpu: use TTM_FENCES_MAX_SLOT_COUNT Pierre-Eric Pelloux-Prayer
2025-11-05 8:36 ` Christian König [this message]
2025-11-04 8:35 ` [PATCH v1 13/20] drm/amdgpu: use multiple entities in amdgpu_move_blit Pierre-Eric Pelloux-Prayer
2025-11-04 8:35 ` [PATCH v1 14/20] drm/amdgpu: pass all the sdma rings to amdgpu_mman Pierre-Eric Pelloux-Prayer
2025-11-04 8:35 ` [PATCH v1 15/20] drm/amdgpu: introduce amdgpu_sdma_set_vm_pte_scheds Pierre-Eric Pelloux-Prayer
2025-11-05 8:41 ` Christian König
2025-11-04 8:35 ` [PATCH v1 16/20] drm/amdgpu: give ttm entities access to all the sdma scheds Pierre-Eric Pelloux-Prayer
2025-11-05 8:45 ` Christian König
2025-11-05 10:17 ` Pierre-Eric Pelloux-Prayer
2025-11-04 8:35 ` [PATCH v1 17/20] drm/amdgpu: get rid of amdgpu_ttm_clear_buffer Pierre-Eric Pelloux-Prayer
2025-11-05 8:46 ` Christian König
2025-11-05 9:30 ` Pierre-Eric Pelloux-Prayer
2025-11-05 10:07 ` Christian König
2025-11-04 8:35 ` [PATCH v1 18/20] drm/amdgpu: rename amdgpu_fill_buffer as amdgpu_clear_buffer Pierre-Eric Pelloux-Prayer
2025-11-05 8:47 ` Christian König
2025-11-04 8:35 ` [PATCH v1 19/20] drm/amdgpu: use larger gart window when possible Pierre-Eric Pelloux-Prayer
2025-11-04 8:35 ` [PATCH v1 20/20] drm/amdgpu: double AMDGPU_GTT_MAX_TRANSFER_SIZE Pierre-Eric Pelloux-Prayer
2025-11-04 13:56 ` 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=23715885-c050-4f19-a964-30cd0e511d8a@amd.com \
--to=christian.koenig@amd.com \
--cc=Felix.Kuehling@amd.com \
--cc=airlied@gmail.com \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=harry.wentland@amd.com \
--cc=linux-kernel@vger.kernel.org \
--cc=pierre-eric.pelloux-prayer@amd.com \
--cc=simona@ffwll.ch \
--cc=siqueira@igalia.com \
--cc=sunpeng.li@amd.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
all inboxes | Powered by JetHome®