From: "Christian König" <ckoenig.leichtzumerken@gmail.com>
To: srinivasan.shanmugam@amd.com, amd-gfx@lists.freedesktop.org
Subject: [PATCH 2/8] drm/amdgpu: use GFP_NOWAIT for memory allocations
Date: Tue, 18 Feb 2025 17:13:55 +0100 [thread overview]
Message-ID: <20250218161401.2155-2-christian.koenig@amd.com> (raw)
In-Reply-To: <20250218161401.2155-1-christian.koenig@amd.com>
In the critical submission path memory allocations can't wait for
reclaim since that can potentially wait for submissions to finish.
Finally clean that up and mark most memory allocations in the critical
path with GFP_NOWAIT. The only exception left is the dma_fence_array()
used when no VMID is available, but that will be cleaned up later on.
Signed-off-by: Christian König <christian.koenig@amd.com>
---
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 8 ++++----
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 18 +++++++++++-------
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 11 +++++++----
drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 4 ++--
drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c | 11 ++++++-----
drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h | 3 ++-
drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c | 4 ++--
7 files changed, 34 insertions(+), 25 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 2b4d3840e5bc..cb819919192a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -499,7 +499,7 @@ static int vm_update_pds(struct amdgpu_vm *vm, struct amdgpu_sync *sync)
if (ret)
return ret;
- return amdgpu_sync_fence(sync, vm->last_update);
+ return amdgpu_sync_fence(sync, vm->last_update, GFP_KERNEL);
}
static uint64_t get_pte_flags(struct amdgpu_device *adev, struct kgd_mem *mem)
@@ -1263,7 +1263,7 @@ static int unmap_bo_from_gpuvm(struct kgd_mem *mem,
(void)amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update);
- (void)amdgpu_sync_fence(sync, bo_va->last_pt_update);
+ (void)amdgpu_sync_fence(sync, bo_va->last_pt_update, GFP_KERNEL);
return 0;
}
@@ -1287,7 +1287,7 @@ static int update_gpuvm_pte(struct kgd_mem *mem,
return ret;
}
- return amdgpu_sync_fence(sync, bo_va->last_pt_update);
+ return amdgpu_sync_fence(sync, bo_va->last_pt_update, GFP_KERNEL);
}
static int map_bo_to_gpuvm(struct kgd_mem *mem,
@@ -2948,7 +2948,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
}
dma_resv_for_each_fence(&cursor, bo->tbo.base.resv,
DMA_RESV_USAGE_KERNEL, fence) {
- ret = amdgpu_sync_fence(&sync_obj, fence);
+ ret = amdgpu_sync_fence(&sync_obj, fence, GFP_KERNEL);
if (ret) {
pr_debug("Memory eviction: Sync BO fence failed. Try again\n");
goto validate_map_fail;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 5df21529b3b1..2ce0c6a152a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -428,7 +428,7 @@ static int amdgpu_cs_p2_dependencies(struct amdgpu_cs_parser *p,
dma_fence_put(old);
}
- r = amdgpu_sync_fence(&p->sync, fence);
+ r = amdgpu_sync_fence(&p->sync, fence, GFP_KERNEL);
dma_fence_put(fence);
if (r)
return r;
@@ -450,7 +450,7 @@ static int amdgpu_syncobj_lookup_and_add(struct amdgpu_cs_parser *p,
return r;
}
- r = amdgpu_sync_fence(&p->sync, fence);
+ r = amdgpu_sync_fence(&p->sync, fence, GFP_KERNEL);
dma_fence_put(fence);
return r;
}
@@ -1124,7 +1124,8 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
if (r)
return r;
- r = amdgpu_sync_fence(&p->sync, fpriv->prt_va->last_pt_update);
+ r = amdgpu_sync_fence(&p->sync, fpriv->prt_va->last_pt_update,
+ GFP_KERNEL);
if (r)
return r;
@@ -1135,7 +1136,8 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
if (r)
return r;
- r = amdgpu_sync_fence(&p->sync, bo_va->last_pt_update);
+ r = amdgpu_sync_fence(&p->sync, bo_va->last_pt_update,
+ GFP_KERNEL);
if (r)
return r;
}
@@ -1154,7 +1156,8 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
if (r)
return r;
- r = amdgpu_sync_fence(&p->sync, bo_va->last_pt_update);
+ r = amdgpu_sync_fence(&p->sync, bo_va->last_pt_update,
+ GFP_KERNEL);
if (r)
return r;
}
@@ -1167,7 +1170,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
if (r)
return r;
- r = amdgpu_sync_fence(&p->sync, vm->last_update);
+ r = amdgpu_sync_fence(&p->sync, vm->last_update, GFP_KERNEL);
if (r)
return r;
@@ -1248,7 +1251,8 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p)
continue;
}
- r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence);
+ r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence,
+ GFP_KERNEL);
dma_fence_put(fence);
if (r)
return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index 8e712a11aba5..56d27cea052e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -209,7 +209,7 @@ static int amdgpu_vmid_grab_idle(struct amdgpu_ring *ring,
return 0;
}
- fences = kmalloc_array(id_mgr->num_ids, sizeof(void *), GFP_KERNEL);
+ fences = kmalloc_array(id_mgr->num_ids, sizeof(void *), GFP_NOWAIT);
if (!fences)
return -ENOMEM;
@@ -326,7 +326,8 @@ static int amdgpu_vmid_grab_reserved(struct amdgpu_vm *vm,
/* Good we can use this VMID. Remember this submission as
* user of the VMID.
*/
- r = amdgpu_sync_fence(&(*id)->active, &job->base.s_fence->finished);
+ r = amdgpu_sync_fence(&(*id)->active, &job->base.s_fence->finished,
+ GFP_NOWAIT);
if (r)
return r;
@@ -385,7 +386,8 @@ static int amdgpu_vmid_grab_used(struct amdgpu_vm *vm,
* user of the VMID.
*/
r = amdgpu_sync_fence(&(*id)->active,
- &job->base.s_fence->finished);
+ &job->base.s_fence->finished,
+ GFP_NOWAIT);
if (r)
return r;
@@ -437,7 +439,8 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
/* Remember this submission as user of the VMID */
r = amdgpu_sync_fence(&id->active,
- &job->base.s_fence->finished);
+ &job->base.s_fence->finished,
+ GFP_NOWAIT);
if (r)
goto error;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index cee38bb6cfaf..597476c441bc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -1332,14 +1332,14 @@ int amdgpu_mes_ctx_map_meta_data(struct amdgpu_device *adev,
DRM_ERROR("failed to do vm_bo_update on meta data\n");
goto error_del_bo_va;
}
- amdgpu_sync_fence(&sync, bo_va->last_pt_update);
+ amdgpu_sync_fence(&sync, bo_va->last_pt_update, GFP_KERNEL);
r = amdgpu_vm_update_pdes(adev, vm, false);
if (r) {
DRM_ERROR("failed to update pdes on meta data\n");
goto error_del_bo_va;
}
- amdgpu_sync_fence(&sync, vm->last_update);
+ amdgpu_sync_fence(&sync, vm->last_update, GFP_KERNEL);
amdgpu_sync_wait(&sync, false);
drm_exec_fini(&exec);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
index c586ab4c911b..86c17a8946f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -152,7 +152,8 @@ static bool amdgpu_sync_add_later(struct amdgpu_sync *sync, struct dma_fence *f)
*
* Add the fence to the sync object.
*/
-int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f)
+int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f,
+ gfp_t flags)
{
struct amdgpu_sync_entry *e;
@@ -162,7 +163,7 @@ int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f)
if (amdgpu_sync_add_later(sync, f))
return 0;
- e = kmem_cache_alloc(amdgpu_sync_slab, GFP_KERNEL);
+ e = kmem_cache_alloc(amdgpu_sync_slab, flags);
if (!e)
return -ENOMEM;
@@ -249,7 +250,7 @@ int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync,
struct dma_fence *tmp = dma_fence_chain_contained(f);
if (amdgpu_sync_test_fence(adev, mode, owner, tmp)) {
- r = amdgpu_sync_fence(sync, f);
+ r = amdgpu_sync_fence(sync, f, GFP_KERNEL);
dma_fence_put(f);
if (r)
return r;
@@ -281,7 +282,7 @@ int amdgpu_sync_kfd(struct amdgpu_sync *sync, struct dma_resv *resv)
if (fence_owner != AMDGPU_FENCE_OWNER_KFD)
continue;
- r = amdgpu_sync_fence(sync, f);
+ r = amdgpu_sync_fence(sync, f, GFP_KERNEL);
if (r)
break;
}
@@ -388,7 +389,7 @@ int amdgpu_sync_clone(struct amdgpu_sync *source, struct amdgpu_sync *clone)
hash_for_each_safe(source->fences, i, tmp, e, node) {
f = e->fence;
if (!dma_fence_is_signaled(f)) {
- r = amdgpu_sync_fence(clone, f);
+ r = amdgpu_sync_fence(clone, f, GFP_KERNEL);
if (r)
return r;
} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
index e3272dce798d..1504f5e7fc46 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
@@ -47,7 +47,8 @@ struct amdgpu_sync {
};
void amdgpu_sync_create(struct amdgpu_sync *sync);
-int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f);
+int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f,
+ gfp_t flags);
int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync,
struct dma_resv *resv, enum amdgpu_sync_mode mode,
void *owner);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
index ba550c7e2118..3e1587c6cf34 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
@@ -120,13 +120,13 @@ static int map_ring_data(struct amdgpu_device *adev, struct amdgpu_vm *vm,
if (r)
goto error_del_bo_va;
- amdgpu_sync_fence(&sync, (*bo_va)->last_pt_update);
+ amdgpu_sync_fence(&sync, (*bo_va)->last_pt_update, GFP_KERNEL);
r = amdgpu_vm_update_pdes(adev, vm, false);
if (r)
goto error_del_bo_va;
- amdgpu_sync_fence(&sync, vm->last_update);
+ amdgpu_sync_fence(&sync, vm->last_update, GFP_KERNEL);
amdgpu_sync_wait(&sync, false);
drm_exec_fini(&exec);
--
2.34.1
next prev parent reply other threads:[~2025-02-18 16:14 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-18 16:13 [PATCH 1/8] drm/amdgpu: grab an additional reference on the gang fence Christian König
2025-02-18 16:13 ` Christian König [this message]
2025-02-18 16:13 ` [PATCH 3/8] drm/amdgpu: overwrite signaled fence in amdgpu_sync Christian König
2025-02-18 16:13 ` [PATCH 4/8] drm/amdgpu: rework how isolation is enforced v2 Christian König
2025-02-18 16:13 ` [PATCH 5/8] drm/amdgpu: rework how the cleaner shader is emitted v3 Christian König
2025-03-14 4:18 ` SRINIVASAN SHANMUGAM
2025-02-18 16:13 ` [PATCH 6/8] drm/amdgpu: stop reserving VMIDs to enforce isolation Christian König
2025-02-18 16:14 ` [PATCH 7/8] drm/amdgpu: add isolation trace point Christian König
2025-02-18 16:14 ` [PATCH 8/8] drm/amdgpu: add cleaner shader " Christian König
-- strict thread matches above, loose matches on Subject: below --
2025-03-07 13:48 [PATCH 1/8] drm/amdgpu: grab an additional reference on the gang fence v2 Christian König
2025-03-07 13:48 ` [PATCH 2/8] drm/amdgpu: use GFP_NOWAIT for memory allocations 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=20250218161401.2155-2-christian.koenig@amd.com \
--to=ckoenig.leichtzumerken@gmail.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=srinivasan.shanmugam@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;
as well as URLs for NNTP newsgroup(s).