summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd
diff options
context:
space:
mode:
authorDavid Francis <David.Francis@amd.com>2026-06-30 09:58:18 -0400
committerAlex Deucher <alexander.deucher@amd.com>2026-07-08 16:44:14 -0400
commit8a93f77aec65574b8152c88eb73613336f92f86b (patch)
tree9a4f7ae3be1f3461e8ae7cd47bdbda67111db607 /drivers/gpu/drm/amd
parent3888a656e8143e4b40f01143648c768fecbfefc6 (diff)
downloadlwn-8a93f77aec65574b8152c88eb73613336f92f86b.tar.gz
lwn-8a93f77aec65574b8152c88eb73613336f92f86b.zip
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 commit 20a5e7ffdfec ("drm/amdkfd: Properly acquire queue buffers in CRIU restore") Fixes: 20a5e7ffdfec ("drm/amdkfd: Properly acquire queue buffers in CRIU restore") Reviewed-by: David Yat Sin <david.yatsin@amd.com> Signed-off-by: David Francis <David.Francis@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> (cherry picked from commit 1cafa8b29e029eac3ddf64604f891b35dbf6262b) Cc: stable@vger.kernel.org
Diffstat (limited to 'drivers/gpu/drm/amd')
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c13
1 files changed, 5 insertions, 8 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 0ac35789b239..b8c36907d536 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -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;
}