TWxSoftware/twx-linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

drm/amdkfd: KFD release_work possible circular locking

Browse Source 
If waiting for gpu reset done in KFD release_work, thers is WARNING:
possible circular locking dependency detected

  #2  kfd_create_process
        kfd_process_mutex
          flush kfd release work

  #1  kfd release work
        wait for amdgpu reset work

  #0  amdgpu_device_gpu_reset
        kgd2kfd_pre_reset
          kfd_process_mutex

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock((work_completion)(&p->release_work));
                  lock((wq_completion)kfd_process_wq);
                  lock((work_completion)(&p->release_work));
   lock((wq_completion)amdgpu-reset-dev);

To fix this, KFD create process move flush release work outside
kfd_process_mutex.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Philip Yang
2025-02-17 20:08:29 -05:00
committed by Alex Deucher
parent ee3ed10066
commit 1b9366c601
1 changed files with 8 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
drivers/gpu/drm/amd/amdkfd/kfd_process.c
+8 -8
View File
@@ -838,6 +838,14 @@ struct kfd_process *kfd_create_process(struct task_struct *thread)
return ERR_PTR(-EINVAL);
}
/* If the process just called exec(3), it is possible that the
* cleanup of the kfd_process (following the release of the mm
* of the old process image) is still in the cleanup work queue.
* Make sure to drain any job before trying to recreate any
* resource for this process.
*/
flush_workqueue(kfd_process_wq);
/*
* take kfd processes mutex before starting of process creation
* so there won't be a case where two threads of the same process
@@ -858,14 +866,6 @@ struct kfd_process *kfd_create_process(struct task_struct *thread)
if (process) {
pr_debug("Process already found\n");
} else {
/* If the process just called exec(3), it is possible that the
* cleanup of the kfd_process (following the release of the mm
* of the old process image) is still in the cleanup work queue.
* Make sure to drain any job before trying to recreate any
* resource for this process.
*/
flush_workqueue(kfd_process_wq);
process = create_process(thread);
if (IS_ERR(process))
goto out;