A circular locking dependency was detected between the global
`adev->userq_mutex` and per-file `userq_mgr->userq_mutex` when
creating user queues. The issue occurs because:

1. `amdgpu_userq_suspend()` and `amdgpu_userq_resume` take `adev->userq_mutex` 
first, then
   `userq_mgr->userq_mutex`
2. While `amdgpu_userq_create()` takes them in reverse order

This patch resolves the issue by:
1. Moving the `adev->userq_mutex` lock earlier in `amdgpu_userq_create()`
   to cover the `amdgpu_userq_ensure_ev_fence()` call
2. Releasing it after we're done with both queue creation and the
   scheduling halt check

v2: remove unused adev->userq_mutex lock (Prike)

Signed-off-by: Jesse Zhang <[email protected]>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index 697dd3cbd114..2ee63b33724d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -531,6 +531,7 @@ amdgpu_userq_create(struct drm_file *filp, union 
drm_amdgpu_userq *args)
         *
         * This will also make sure we have a valid eviction fence ready to be 
used.
         */
+       mutex_lock(&adev->userq_mutex);
        amdgpu_userq_ensure_ev_fence(&fpriv->userq_mgr, &fpriv->evf_mgr);
 
        uq_funcs = adev->userq_funcs[args->in.ip_type];
@@ -594,7 +595,6 @@ amdgpu_userq_create(struct drm_file *filp, union 
drm_amdgpu_userq *args)
        }
 
        /* don't map the queue if scheduling is halted */
-       mutex_lock(&adev->userq_mutex);
        if (adev->userq_halt_for_enforce_isolation &&
            ((queue->queue_type == AMDGPU_HW_IP_GFX) ||
             (queue->queue_type == AMDGPU_HW_IP_COMPUTE)))
@@ -604,7 +604,6 @@ amdgpu_userq_create(struct drm_file *filp, union 
drm_amdgpu_userq *args)
        if (!skip_map_queue) {
                r = amdgpu_userq_map_helper(uq_mgr, queue);
                if (r) {
-                       mutex_unlock(&adev->userq_mutex);
                        drm_file_err(uq_mgr->file, "Failed to map Queue\n");
                        idr_remove(&uq_mgr->userq_idr, qid);
                        amdgpu_userq_fence_driver_free(queue);
@@ -613,13 +612,13 @@ amdgpu_userq_create(struct drm_file *filp, union 
drm_amdgpu_userq *args)
                        goto unlock;
                }
        }
-       mutex_unlock(&adev->userq_mutex);
 
 
        args->out.queue_id = qid;
 
 unlock:
        mutex_unlock(&uq_mgr->userq_mutex);
+       mutex_unlock(&adev->userq_mutex);
 
        return r;
 }
-- 
2.49.0

Reply via email to