From: "Christian König" <ckoenig.leichtzumerken@gmail.com>
To: thomas.hellstrom@linux.intel.com, dakr@kernel.org,
ecourtney@nvidia.com, simona@ffwll.ch, matthew.brost@intel.com,
nat@pixelcluster.dev, airlied@gmail.com,
dri-devel@lists.freedesktop.org, linux-kernel@vger.kernel.org,
intel-gfx@lists.freedesktop.org, intel-xe@lists.freedesktop.org,
amd-gfx@lists.freedesktop.org
Subject: [PATCH 12/12] drm/amdgpu: use drm_exec during BO validation
Date: Fri, 10 Jul 2026 20:52:52 +0200 [thread overview]
Message-ID: <20260710190752.2355-13-christian.koenig@amd.com> (raw)
In-Reply-To: <20260710190752.2355-1-christian.koenig@amd.com>
This allows to detect deadlocks happening because of resource
constraints.
Especially submissions which want to use all of GDS doesn't result in
sporadic -ENOMEM any more.
Signed-off-by: Christian König <christian.koenig@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 82 ++++++++++++++------------
1 file changed, 44 insertions(+), 38 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index c2e6495a28bc5..17223e295ff25 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -793,7 +793,7 @@ static int amdgpu_cs_bo_validate(void *param, struct amdgpu_bo *bo)
struct ttm_operation_ctx ctx = {
.interruptible = true,
.no_wait_gpu = false,
- .resv = bo->tbo.base.resv
+ .exec = &p->exec,
};
uint32_t domain;
int r;
@@ -845,7 +845,10 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
union drm_amdgpu_cs *cs)
{
struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
- struct ttm_operation_ctx ctx = { true, false };
+ struct ttm_operation_ctx ctx = {
+ .interruptible =true,
+ .exec = &p->exec
+ };
struct amdgpu_vm *vm = &fpriv->vm;
struct amdgpu_bo_list_entry *e;
struct drm_gem_object *obj;
@@ -899,6 +902,11 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
e->user_invalidated = userpage_invalidated;
}
+ amdgpu_cs_get_threshold_for_moves(p->adev, &p->bytes_moved_threshold,
+ &p->bytes_moved_vis_threshold);
+ p->bytes_moved = 0;
+ p->bytes_moved_vis = 0;
+
drm_exec_until_all_locked(&p->exec) {
r = amdgpu_vm_lock_pd(&fpriv->vm, &p->exec, 1 + p->gang_size);
drm_exec_retry_on_contention(&p->exec);
@@ -922,47 +930,48 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
if (unlikely(r))
goto out_free_user_pages;
}
- }
- amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
- struct mm_struct *usermm;
+ amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
+ struct mm_struct *usermm;
- usermm = amdgpu_ttm_tt_get_usermm(e->bo->tbo.ttm);
- if (usermm && usermm != current->mm) {
- r = -EPERM;
- goto out_free_user_pages;
- }
-
- if (amdgpu_ttm_tt_is_userptr(e->bo->tbo.ttm) &&
- e->user_invalidated) {
- amdgpu_bo_placement_from_domain(e->bo,
- AMDGPU_GEM_DOMAIN_CPU);
- r = ttm_bo_validate(&e->bo->tbo, &e->bo->placement,
- &ctx);
- if (r)
+ usermm = amdgpu_ttm_tt_get_usermm(e->bo->tbo.ttm);
+ if (usermm && usermm != current->mm) {
+ r = -EPERM;
goto out_free_user_pages;
+ }
- amdgpu_ttm_tt_set_user_pages(e->bo->tbo.ttm,
- e->range);
+ if (amdgpu_ttm_tt_is_userptr(e->bo->tbo.ttm) &&
+ e->user_invalidated) {
+ amdgpu_bo_placement_from_domain(e->bo,
+ AMDGPU_GEM_DOMAIN_CPU);
+ r = ttm_bo_validate(&e->bo->tbo, &e->bo->placement,
+ &ctx);
+ drm_exec_retry_on_contention(&p->exec);
+ if (r)
+ goto out_free_user_pages;
+
+ amdgpu_ttm_tt_set_user_pages(e->bo->tbo.ttm,
+ e->range);
+ }
}
- }
- amdgpu_cs_get_threshold_for_moves(p->adev, &p->bytes_moved_threshold,
- &p->bytes_moved_vis_threshold);
- p->bytes_moved = 0;
- p->bytes_moved_vis = 0;
+ r = amdgpu_vm_validate(p->adev, &fpriv->vm, NULL,
+ amdgpu_cs_bo_validate, p);
+ drm_exec_retry_on_contention(&p->exec);
+ if (r) {
+ drm_err(adev_to_drm(p->adev), "amdgpu_vm_validate() failed.\n");
+ goto out_free_user_pages;
+ }
- r = amdgpu_vm_validate(p->adev, &fpriv->vm, NULL,
- amdgpu_cs_bo_validate, p);
- if (r) {
- drm_err(adev_to_drm(p->adev), "amdgpu_vm_validate() failed.\n");
- goto out_free_user_pages;
- }
+ drm_exec_for_each_locked_object(&p->exec, obj) {
+ r = amdgpu_cs_bo_validate(p, gem_to_amdgpu_bo(obj));
+ drm_exec_retry_on_contention(&p->exec);
+ if (unlikely(r))
+ goto out_free_user_pages;
- drm_exec_for_each_locked_object(&p->exec, obj) {
- r = amdgpu_cs_bo_validate(p, gem_to_amdgpu_bo(obj));
- if (unlikely(r))
- goto out_free_user_pages;
+ amdgpu_cs_report_moved_bytes(p->adev, p->bytes_moved,
+ p->bytes_moved_vis);
+ }
}
if (p->uf_bo) {
@@ -973,9 +982,6 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
p->gang_leader->uf_addr += amdgpu_bo_gpu_offset(p->uf_bo);
}
- amdgpu_cs_report_moved_bytes(p->adev, p->bytes_moved,
- p->bytes_moved_vis);
-
for (i = 0; i < p->gang_size; ++i)
amdgpu_job_set_resources(p->jobs[i], p->bo_list->gds_obj,
p->bo_list->gws_obj,
--
2.43.0
next prev parent reply other threads:[~2026-07-10 19:08 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-10 18:52 Refcounting dma_resv and using that for drm_exec support in TTM Christian König
2026-07-10 18:52 ` [PATCH 01/12] dma-buf: Add reference counting to dma_resv Christian König
2026-07-11 1:27 ` Matthew Brost
2026-07-11 13:10 ` Danilo Krummrich
2026-07-12 19:51 ` Matthew Brost
2026-07-13 9:25 ` Christian König
2026-07-13 14:57 ` Matthew Brost
2026-07-10 18:52 ` [PATCH 02/12] dma-buf/tests: Convert st-dma-resv tests to use dma_resv_alloc Christian König
2026-07-10 18:52 ` [PATCH 03/12] drm/gem: Add helper for drm_gem_object resv assignment Christian König
2026-07-10 18:52 ` [PATCH 04/12] drm/ttm: Switch LRU cursor to track dma_resv instead of buffer objects Christian König
2026-07-13 13:40 ` Thomas Hellström
2026-07-13 15:15 ` Matthew Brost
2026-07-10 18:52 ` [PATCH 05/12] drm/ttm: switch to ttm_bo_lru_for_each_reserved_guarded for swapout Christian König
2026-07-10 18:52 ` [PATCH 06/12] drm/ttm: move delete handling into ttm_bo_evict Christian König
2026-07-10 18:52 ` [PATCH 07/12] drm/ttm: use ttm_bo_lru_for_each_reserved_guarded in evict_all Christian König
2026-07-10 18:52 ` [PATCH 08/12] drm/ttm: use dma_resv reference in ttm_device_clear_lru_dma_mappings Christian König
2026-07-10 18:52 ` [PATCH 09/12] drm/ttm: nuke buffer refcounting Christian König
2026-07-11 13:26 ` Danilo Krummrich
2026-07-13 15:06 ` Matthew Brost
2026-07-10 18:52 ` [PATCH 10/12] drm/exec: add drm_exec_lock_resv function Christian König
2026-07-13 11:57 ` Thomas Hellström
2026-07-13 12:07 ` Christian König
2026-07-13 12:19 ` Thomas Hellström
2026-07-13 13:14 ` Christian König
2026-07-13 13:37 ` Thomas Hellström
2026-07-10 18:52 ` [PATCH 11/12] drm/ttm: support using drm_exec during eviction v4 Christian König
2026-07-13 11:59 ` Thomas Hellström
2026-07-10 18:52 ` Christian König [this message]
2026-07-13 11:32 ` Refcounting dma_resv and using that for drm_exec support in TTM Thomas Hellström
2026-07-13 15:03 ` Matthew Brost
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=20260710190752.2355-13-christian.koenig@amd.com \
--to=ckoenig.leichtzumerken@gmail.com \
--cc=airlied@gmail.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=christian.koenig@amd.com \
--cc=dakr@kernel.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=ecourtney@nvidia.com \
--cc=intel-gfx@lists.freedesktop.org \
--cc=intel-xe@lists.freedesktop.org \
--cc=linux-kernel@vger.kernel.org \
--cc=matthew.brost@intel.com \
--cc=nat@pixelcluster.dev \
--cc=simona@ffwll.ch \
--cc=thomas.hellstrom@linux.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
all inboxes | Powered by JetHome®