On resume, amdgpu_userq_vm_validate_and_restore_queue() updates each queue's
wptr GPU address via amdgpu_bo_gpu_offset().

WPTR BOs are VM-mapped, but each BO has its own reservation object and is not
implicitly covered by the VM validation path here. This can leave offset reads
without proper BO locking/placement state and trigger WARN_ONs.
  ------------[ cut here ]------------
  WARNING: amdgpu_object.c:1486 at amdgpu_bo_gpu_offset+0x75/0xa0 [amdgpu], 
CPU#3: kworker/3:1/116
  Workqueue: events amdgpu_userq_restore_worker [amdgpu]
  RIP: 0010:amdgpu_bo_gpu_offset+0x75/0xa0 [amdgpu]
  Call Trace:
   <TASK>
   amdgpu_userq_vm_validate_and_restore_queue+0x629/0x960 [amdgpu]
   amdgpu_userq_restore_worker+0xa6/0x180 [amdgpu]
   process_scheduled_works+0xa6/0x460
   worker_thread+0x13c/0x290
   kthread+0xfb/0x140
   ret_from_fork+0x1b6/0x2b0
   ret_from_fork_asm+0x1a/0x30
   </TASK>
  ---[ end trace 0000000000000000 ]---
  ------------[ cut here ]------------
  WARNING: amdgpu_object.c:1485 at amdgpu_bo_gpu_offset+0x9a/0xa0 [amdgpu], 
CPU#2: kworker/2:1/127
  Workqueue: events amdgpu_userq_restore_worker [amdgpu]
  RIP: 0010:amdgpu_bo_gpu_offset+0x9a/0xa0 [amdgpu]

Add each queue's WPTR BO to the drm_exec ww context and validate it to its
allowed placement before the later offset update.

Signed-off-by: Jesse Zhang <[email protected]>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c | 24 +++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index 17cc48d87c4d..ab8fc14a235b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -1054,6 +1054,30 @@ amdgpu_userq_vm_validate_and_restore_queue(struct 
amdgpu_userq_mgr *uq_mgr)
                drm_exec_retry_on_contention(&exec);
                if (unlikely(ret))
                        goto unlock_all;
+
+               /*
+                * WPTR BOs are VM-mapped, but each BO has its own reservation
+                * object. Lock them into this drm_exec ww context so the later
+                * amdgpu_bo_gpu_offset() reads are done with the BO resv 
locked.
+                */
+               xa_for_each(&uq_mgr->userq_xa, tmp_key, queue) {
+                       struct ttm_operation_ctx wptr_ctx = { false, false };
+
+                       bo = queue->wptr_obj.obj;
+                       if (!bo)
+                               continue;
+
+                       ret = drm_exec_prepare_obj(&exec, &bo->tbo.base,
+                                                  TTM_NUM_MOVE_FENCES + 1);
+                       drm_exec_retry_on_contention(&exec);
+                       if (unlikely(ret))
+                               goto unlock_all;
+
+                       amdgpu_bo_placement_from_domain(bo, 
bo->allowed_domains);
+                       ret = ttm_bo_validate(&bo->tbo, &bo->placement, 
&wptr_ctx);
+                       if (unlikely(ret))
+                               goto unlock_all;
+               }
        }
 
        if (invalidated) {
-- 
2.49.0

Reply via email to