linux-stable.git/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c, branch linux-7.2.y Linux kernel stable tree drm/amdgpu/userq: serialize queue map against GPU reset 2026-08-06T18:32:23+00:00 Jesse Zhang Jesse.Zhang@amd.com 2026-08-03T09:19:46+00:00 b77a725e50c87c091f51affc8e46710badea0d49 Creating a user queue can race with a GPU reset. While recovery holds reset_domain->sem for write, MES is unresponsive, so the ADD_QUEUE from amdgpu_userq_map_helper() times out (-110) and an otherwise valid queue create fails: amdgpu: MES(0) failed to respond to msg=ADD_QUEUE [drm:mes_userq_map [amdgpu]] *ERROR* Failed to map queue in HW, err (-110) amdgpu: [drm] *ERROR* ... Failed to map Queue amdgpu: [drm] *ERROR* ... Failed to create usermode queue Take reset_domain->sem for read around the map so it runs only once MES is back up. This mirrors amdgpu_userq_cleanup() and honors the userq_mutex -> reset_domain->sem order; the reset path never takes userq_mutex, so there is no deadlock. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> (cherry picked from commit a8e151fe629c63b0eb08aa57de0d434614db3e1b) Cc: stable@vger.kernel.org 
Creating a user queue can race with a GPU reset. While recovery holds
reset_domain->sem for write, MES is unresponsive, so the ADD_QUEUE from
amdgpu_userq_map_helper() times out (-110) and an otherwise valid queue
create fails:

  amdgpu: MES(0) failed to respond to msg=ADD_QUEUE
  [drm:mes_userq_map [amdgpu]] *ERROR* Failed to map queue in HW, err (-110)
  amdgpu: [drm] *ERROR* ... Failed to map Queue
  amdgpu: [drm] *ERROR* ... Failed to create usermode queue

Take reset_domain->sem for read around the map so it runs only once MES
is back up. This mirrors amdgpu_userq_cleanup() and honors the
userq_mutex -> reset_domain->sem order; the reset path never takes
userq_mutex, so there is no deadlock.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit a8e151fe629c63b0eb08aa57de0d434614db3e1b)
Cc: stable@vger.kernel.org
drm/amdgpu: dont pin wptr bo instead use eviction fence 2026-07-28T23:59:08+00:00 Sunil Khatri sunil.khatri@amd.com 2026-07-15T14:02:56+00:00 17da8410554906a95bb9ef30acbdf0c5abc1a4ef Instead of pinning the wptr bo attach the eviction fence to the bo to make sure it remains valid all the time. Signed-off-by: Sunil Khatri <sunil.khatri@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> (cherry picked from commit 7264bc10c7c657a54603c7fc058bf8e15f18ce12) 
Instead of pinning the wptr bo attach the eviction fence to
the bo to make sure it remains valid all the time.

Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 7264bc10c7c657a54603c7fc058bf8e15f18ce12)
drm/amdgpu/userq: fix indefinite fence wait during GPU reset 2026-07-17T21:38:16+00:00 Jesse Zhang Jesse.Zhang@amd.com 2026-07-10T08:45:42+00:00 5d75ec2e5f1736c2f10c7d6f4565bf1bf29f29a7 pre_reset only force-completes fences of MAPPED queues. A queue in any other state (e.g. mid-eviction) keeps its last_fence pending; after a GPU reset that fence never signals, so the eviction/suspend worker and process teardown (amdgpu_evf_mgr_flush_suspend) wait on it forever and wedge the machine: INFO: task kworker/6:28 blocked for more than 120 seconds. Workqueue: events amdgpu_eviction_fence_suspend_worker [amdgpu] Call Trace: dma_fence_wait_timeout+0x7e/0x130 amdgpu_userq_evict+0x67/0x140 [amdgpu] amdgpu_eviction_fence_suspend_worker+0xd8/0x160 [amdgpu] process_scheduled_works+0xa6/0x420 Force-complete every queue's fence regardless of state. The unmap and mark-hung step stays gated on MAPPED, since unmapping a queue that is not mapped is invalid. Fixes: 290f46cf5726 ("drm/amdgpu: Implement user queue reset functionality") Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> (cherry picked from commit 9102b39fa924dcc3dc75a3137bfa9633c40b88c0) Cc: stable@vger.kernel.org 
pre_reset only force-completes fences of MAPPED queues. A queue in any
other state (e.g. mid-eviction) keeps its last_fence pending; after a
GPU reset that fence never signals, so the eviction/suspend worker and
process teardown (amdgpu_evf_mgr_flush_suspend) wait on it forever and
wedge the machine:

  INFO: task kworker/6:28 blocked for more than 120 seconds.
  Workqueue: events amdgpu_eviction_fence_suspend_worker [amdgpu]
  Call Trace:
   dma_fence_wait_timeout+0x7e/0x130
   amdgpu_userq_evict+0x67/0x140 [amdgpu]
   amdgpu_eviction_fence_suspend_worker+0xd8/0x160 [amdgpu]
   process_scheduled_works+0xa6/0x420

Force-complete every queue's fence regardless of state. The unmap and
mark-hung step stays gated on MAPPED, since unmapping a queue that is
not mapped is invalid.

Fixes: 290f46cf5726 ("drm/amdgpu: Implement user queue reset functionality")
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 9102b39fa924dcc3dc75a3137bfa9633c40b88c0)
Cc: stable@vger.kernel.org
drm/amdgpu: trigger GPU recovery when userq destroy fails to unmap a hung queue 2026-07-08T20:29:11+00:00 Jesse Zhang Jesse.Zhang@amd.com 2026-07-01T10:17:03+00:00 614e8a989d462876c4f6a659f56e1075e72ad515 Destroying a hung user queue issues a MES REMOVE_QUEUE that times out, The destroy path only logged the error and freed the queue, so the next userq submission failed and forced a GPU reset attributed to an innocent workload. Kick the userq reset work when unmap fails so the GPU is recovered at destroy time. Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> (cherry picked from commit 8396b9de4198a54ec4760a94a179347540a9764d) Cc: stable@vger.kernel.org 
Destroying a hung user queue issues a MES REMOVE_QUEUE that times out,
The destroy path only logged the error and freed the queue, so the
next userq submission failed and forced a GPU reset attributed to an innocent workload.

Kick the userq reset work when unmap fails so the GPU is recovered at
destroy time.

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 8396b9de4198a54ec4760a94a179347540a9764d)
Cc: stable@vger.kernel.org
drm/amdgpu: reject mapping a reserved doorbell to a new queue 2026-07-01T17:00:10+00:00 Zhu Lingshan lingshan.zhu@amd.com 2026-06-24T07:52:35+00:00 a609b6278bf3cde17eeee6620091465521e4b02c When creating an user-queue, the user space provides a doorbell BO handle and an offset within the bo to obtain a doorbell. However current implementation using xa_store_irq() to store a doorbell, which allows a later queue created with the same BO and offset parameters to overwrite an existing queue and doorbell mapping. This can cause problems like misrouting fence IRQ processing to a wrong queue, and mislead the cleanup process of one queue erasing the mapping of another queue. This commit fixes this issue by replacing xa_store_irq with xa_insert_irq, which rejects mapping a reserved doorbell to a newly created queue Signed-off-by: Zhu Lingshan <lingshan.zhu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> (cherry picked from commit 6244eae22966350db52faf9c1369d3b2ffc5de4e) Cc: stable@vger.kernel.org 
When creating an user-queue, the user space
provides a doorbell BO handle and an offset within
the bo to obtain a doorbell.

However current implementation using xa_store_irq()
to store a doorbell, which allows a later queue created
with the same BO and offset parameters to overwrite an
existing queue and doorbell mapping.

This can cause problems like misrouting fence IRQ
processing to a wrong queue, and mislead the cleanup
process of one queue erasing the mapping of another queue.

This commit fixes this issue by replacing xa_store_irq with
xa_insert_irq, which rejects mapping a reserved
doorbell to a newly created queue

Signed-off-by: Zhu Lingshan <lingshan.zhu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 6244eae22966350db52faf9c1369d3b2ffc5de4e)
Cc: stable@vger.kernel.org
drm/amdgpu/userq: move wptr_obj cleanup in mqd_destroy 2026-06-03T17:58:51+00:00 Sunil Khatri sunil.khatri@amd.com 2026-05-25T04:26:23+00:00 43355f62cd2ef5386c2693df537c232ea0f2ce6c In case when queue_create fails and mqd has already been allocated and hence wptr_obj is not cleaned up. So moving that cleanup part to mqd_destroy so it takes care of all the cases of clean up and during tear down of the queue. Signed-off-by: Sunil Khatri <sunil.khatri@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
In case when queue_create fails and mqd has already been
allocated and hence wptr_obj is not cleaned up.

So moving that cleanup part to mqd_destroy so it takes
care of all the cases of clean up and during tear down of
the queue.

Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu/userq: remove the vital queue unmap logging 2026-06-03T17:55:33+00:00 Sunil Khatri sunil.khatri@amd.com 2026-05-25T07:48:00+00:00 758a868043dcb07eca923bc451c16da3e73dc47c Mesa userqueues free does not wait for the free to complete and go ahead in unmapping the vital bos while kernel is still in queue free and corresponding cleanup. So ideally we don't need the logging for that and hence remove the warn message as this is expected behaviour and functionally, we are making sure to wait for the required fences before unmap. Signed-off-by: Sunil Khatri <sunil.khatri@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Mesa userqueues free does not wait for the free to complete and go ahead
in unmapping the vital bos while kernel is still in queue free and
corresponding cleanup.

So ideally we don't need the logging for that and hence remove the warn
message as this is expected behaviour and functionally, we are making
sure to wait for the required fences before unmap.

Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: unmap userq for evicting user queue 2026-06-03T17:49:41+00:00 Prike Liang Prike.Liang@amd.com 2026-05-14T09:21:09+00:00 d87c9d86727a0bcc95c3009a213a1b27a11b691e If the driver only preempts queues, there can still be inflight waves, pending dispatch state, or resume/redispatch possibility tied to the same queue. Then the VM/TTM side may proceed to move/unmap queue related BOs during evicting userq objects while shader TCP clients still need to access them. So for eviction, unmap is safer because it makes the queue nonrunnable before memory backing is invalidated. Meanwhile, for a idle queue it's more sutiable for unmapping it rather preempt and unmapping also can save more processing time than preempt. Signed-off-by: Prike Liang <Prike.Liang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
If the driver only preempts queues, there can still be inflight waves,
pending dispatch state, or resume/redispatch possibility tied to the
same queue. Then the VM/TTM side may proceed to move/unmap queue related
BOs during evicting userq objects while shader TCP clients still need to
access them.

So for eviction, unmap is safer because it makes the queue nonrunnable
before memory backing is invalidated. Meanwhile, for a idle queue it's
more sutiable for unmapping it rather preempt and unmapping also can
save more processing time than preempt.

Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: reserve TTM move fences slot for rearming eviction fences 2026-06-03T17:49:29+00:00 Prike Liang Prike.Liang@amd.com 2026-05-26T08:42:14+00:00 113fa3ca614a865776f81759bb245dabf99859a7 The eviction rearming does not cover possible TTM move fences. If TTM moves the BO and consumes move fence slots, the later eviction fence add can hit the dma_resv_add_fence() BUG. Signed-off-by: Prike Liang <Prike.Liang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
The eviction rearming does not cover possible TTM move fences. If TTM
moves the BO and consumes move fence slots, the later eviction fence
add can hit the dma_resv_add_fence() BUG.

Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu/userq: use array instead of list for userq_vas 2026-05-27T14:50:02+00:00 Sunil Khatri sunil.khatri@amd.com 2026-05-20T11:09:49+00:00 ef7dc711a664b0c548ecfdf13a00436b7446b8e7 Use arrays instead of list for userq_vas since we have fixed no of bos. Also, we dont have to worry to free that memory later since this array would be free along with queue only. Signed-off-by: Sunil Khatri <sunil.khatri@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Use arrays instead of list for userq_vas since we have fixed no
of bos. Also, we dont have to worry to free that memory later
since this array would be free along with queue only.

Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>