Skip to contentSkip to conversation

drm/amdkfd: Don't acquire buffers during CRIU queue restore.

PATCH In review David Francis 2 participants 2 messages Jun 30 – Jul 6

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 drm/amdkfd: Don't acquire buffers during CRIU queue restore.

kfd_criu_restore_queue's call of kfd_queue_acquire_buffers was failing for multiple reasons
- The ctl_stack_size set by the CRIU plugin doesn't match what is expected by acquire_buffers
- The svm buffer cannot be acquired at this point because CRIU may not have restored it, or may have restored it to a different address.

The only reason acquire_buffers was necessary here was to avoid a null ptr dereference in init_user_queue.

Just put in a check for that dereference; it doesn't appear to come up in real use cases right now. That is, there is no usage of CRIU with shared MES.

This is a partial revert of d3f670cfb535f (drm/amdkfd: Properly acquire queue buffers in CRIU restore)

---
 .../gpu/drm/amd/amdkfd/kfd_process_queue_manager.c  | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +5 -8
index 071f956f183c..3bbda47a4439 100644
@@ -265,6 +265,11 @@ static int init_user_queue(struct process_queue_manager *pqm,
 	(*q)->process = pqm->process;
 
 	if (dev->kfd->shared_resources.enable_mes) {
+		if (!q_properties->wptr_bo) {
+			pr_debug("Queue initialization with shared MES requires queue buffers to be initialized\n");
+			return -EINVAL;
+		}
+
 		retval = amdgpu_amdkfd_alloc_kernel_mem(dev->adev,
 						AMDGPU_MES_GANG_CTX_SIZE,
 						AMDGPU_GEM_DOMAIN_GTT,
@@ -1042,18 +1047,10 @@ int kfd_criu_restore_queue(struct kfd_process *p,
 	memset(&qp, 0, sizeof(qp));
 	set_queue_properties_from_criu(&qp, q_data, NUM_XCC(pdd->dev->adev->gfx.xcc_mask));
 
-	ret = kfd_queue_acquire_buffers(pdd, &qp);
-	if (ret) {
-		pr_debug("failed to acquire user queue buffers for CRIU\n");
-		goto exit;
-	}
-
 	print_queue_properties(&qp);
 
 	ret = pqm_create_queue(&p->pqm, pdd->dev, &qp, &queue_id, q_data, mqd, ctl_stack, NULL);
 	if (ret) {
-		kfd_queue_unref_bo_vas(pdd, &qp);
-		kfd_queue_release_buffers(pdd, &qp);
 		pr_err("Failed to create new queue err:%d\n", ret);
 		goto exit;
 	}
Signature · 1 line
2.34.1
Reviewed-by on v1 1/1
#1 lore raw

AMD General

Quoted 71 lines

-----Original Message-----
From: amd-gfx <[email protected]> On Behalf Of David Francis
Sent: Tuesday, June 30, 2026 2:37 PM
To: [email protected]
Cc: Francis, David <[email protected]>
Subject: [PATCH] drm/amdkfd: Don't acquire buffers during CRIU queue restore.

kfd_criu_restore_queue's call of kfd_queue_acquire_buffers was failing for multiple reasons
- The ctl_stack_size set by the CRIU plugin doesn't match what is expected by acquire_buffers
- The svm buffer cannot be acquired at this point because CRIU may not have restored it, or may have restored it to a different address.

The only reason acquire_buffers was necessary here was to avoid a null ptr dereference in init_user_queue.

Just put in a check for that dereference; it doesn't appear to come up in real use cases right now. That is, there is no usage of CRIU with shared MES.

This is a partial revert of d3f670cfb535f (drm/amdkfd: Properly acquire queue buffers in CRIU restore)

---
 .../gpu/drm/amd/amdkfd/kfd_process_queue_manager.c  | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +5 -0
index 071f956f183c..3bbda47a4439 100644
@@ -265,6 +265,11 @@ static int init_user_queue(struct process_queue_manager
 *pqm,
      (*q)->process = pqm->process;
 
      if (dev->kfd->shared_resources.enable_mes) {
+             if (!q_properties->wptr_bo) {
+                     pr_debug("Queue initialization with shared MES requires
 queue buffers to be initialized\n");
+                     return -EINVAL;
+             }
+
              retval = amdgpu_amdkfd_alloc_kernel_mem(dev->adev,

AMDGPU_MES_GANG_CTX_SIZE, AMDGPU_GEM_DOMAIN_GTT,

drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +0 -8
@@ -1042,18 +1047,10 @@ int kfd_criu_restore_queue(struct kfd_process *p,
      memset(&qp, 0, sizeof(qp));
      set_queue_properties_from_criu(&qp, q_data, NUM_XCC(pdd->dev->adev-
 >gfx.xcc_mask));
 
-     ret = kfd_queue_acquire_buffers(pdd, &qp);
-     if (ret) {
-             pr_debug("failed to acquire user queue buffers for CRIU\n");
-             goto exit;
-     }
-
      print_queue_properties(&qp);
 
      ret = pqm_create_queue(&p->pqm, pdd->dev, &qp, &queue_id, q_data, mqd,
 ctl_stack, NULL);
      if (ret) {
-             kfd_queue_unref_bo_vas(pdd, &qp);
-             kfd_queue_release_buffers(pdd, &qp);
              pr_err("Failed to create new queue err:%d\n", ret);
              goto exit;
      }

--
2.34.1