[PATCH AUTOSEL 5.10 096/137] drm/amdkfd: Walk through list with dqm lock hold

From: Sasha Levin
Date: Tue Jul 06 2021 - 07:54:37 EST


From: xinhui pan <xinhui.pan@xxxxxxx>

[ Upstream commit 56f221b6389e7ab99c30bbf01c71998ae92fc584 ]

To avoid any list corruption.

Signed-off-by: xinhui pan <xinhui.pan@xxxxxxx>
Reviewed-by: Felix Kuehling <Felix.Kuehling@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 22 ++++++++++---------
1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index ffb3d37881a8..352a32dc609b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1712,7 +1712,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
struct qcm_process_device *qpd)
{
int retval;
- struct queue *q, *next;
+ struct queue *q;
struct kernel_queue *kq, *kq_next;
struct mqd_manager *mqd_mgr;
struct device_process_node *cur, *next_dpn;
@@ -1769,24 +1769,26 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
qpd->reset_wavefronts = false;
}

- dqm_unlock(dqm);
-
- /* Outside the DQM lock because under the DQM lock we can't do
- * reclaim or take other locks that others hold while reclaiming.
- */
- if (found)
- kfd_dec_compute_active(dqm->dev);
-
/* Lastly, free mqd resources.
* Do free_mqd() after dqm_unlock to avoid circular locking.
*/
- list_for_each_entry_safe(q, next, &qpd->queues_list, list) {
+ while (!list_empty(&qpd->queues_list)) {
+ q = list_first_entry(&qpd->queues_list, struct queue, list);
mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type(
q->properties.type)];
list_del(&q->list);
qpd->queue_count--;
+ dqm_unlock(dqm);
mqd_mgr->free_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
+ dqm_lock(dqm);
}
+ dqm_unlock(dqm);
+
+ /* Outside the DQM lock because under the DQM lock we can't do
+ * reclaim or take other locks that others hold while reclaiming.
+ */
+ if (found)
+ kfd_dec_compute_active(dqm->dev);

return retval;
}
--
2.30.2