mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-08-30 16:53:20 -04:00
drm/amdgpu/userq: serialize queue map against GPU reset
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 a8e151fe62)
Cc: stable@vger.kernel.org
This commit is contained in:
committed by
Alex Deucher
parent
384c1d907e
commit
b77a725e50
@@ -700,7 +700,12 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
|
||||
if (!adev->userq_halt_for_enforce_isolation ||
|
||||
((queue->queue_type != AMDGPU_HW_IP_GFX) &&
|
||||
(queue->queue_type != AMDGPU_HW_IP_COMPUTE))) {
|
||||
/* Serialize the map against an in-progress GPU reset (MES is
|
||||
* unresponsive during recovery), matching amdgpu_userq_cleanup().
|
||||
*/
|
||||
down_read(&adev->reset_domain->sem);
|
||||
r = amdgpu_userq_map_helper(queue);
|
||||
up_read(&adev->reset_domain->sem);
|
||||
if (r) {
|
||||
drm_file_err(uq_mgr->file, "Failed to map Queue\n");
|
||||
mutex_unlock(&uq_mgr->userq_mutex);
|
||||
|
||||
Reference in New Issue
Block a user