[PATCH AUTOSEL 5.12 096/160] drm/amdkfd: Fix circular lock in nocpsch path
From: Sasha Levin <sashal@kernel.org>
Date: 2021-07-06 11:39:03
Also in:
amd-gfx, dri-devel, lkml
Subsystem:
amd kfd, drm drivers, radeon and amdgpu drm drivers, the rest · Maintainers:
Felix Kuehling, David Airlie, Simona Vetter, Alex Deucher, Christian König, Linus Torvalds
From: Amber Lin <redacted> [ Upstream commit a7b2451d31cfa2e8aeccf3b35612ce33f02371fc ] Calling free_mqd inside of destroy_queue_nocpsch_locked can cause a circular lock. destroy_queue_nocpsch_locked is called under a DQM lock, which is taken in MMU notifiers, potentially in FS reclaim context. Taking another lock, which is BO reservation lock from free_mqd, while causing an FS reclaim inside the DQM lock creates a problematic circular lock dependency. Therefore move free_mqd out of destroy_queue_nocpsch_locked and call it after unlocking DQM. Signed-off-by: Amber Lin <redacted> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org> --- .../drm/amd/amdkfd/kfd_device_queue_manager.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 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 df05eca73275..3d66565a618f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c@@ -486,9 +486,6 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm, if (retval == -ETIME) qpd->reset_wavefronts = true; - - mqd_mgr->free_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj); - list_del(&q->list); if (list_empty(&qpd->queues_list)) { if (qpd->reset_wavefronts) {
@@ -523,6 +520,8 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm, int retval; uint64_t sdma_val = 0; struct kfd_process_device *pdd = qpd_to_pdd(qpd); + struct mqd_manager *mqd_mgr = + dqm->mqd_mgrs[get_mqd_type_from_queue_type(q->properties.type)]; /* Get the SDMA queue stats */ if ((q->properties.type == KFD_QUEUE_TYPE_SDMA) ||
@@ -540,6 +539,8 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm, pdd->sdma_past_activity_counter += sdma_val; dqm_unlock(dqm); + mqd_mgr->free_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj); + return retval; }
@@ -1632,7 +1633,7 @@ static int set_trap_handler(struct device_queue_manager *dqm, static int process_termination_nocpsch(struct device_queue_manager *dqm, struct qcm_process_device *qpd) { - struct queue *q, *next; + struct queue *q; struct device_process_node *cur, *next_dpn; int retval = 0; bool found = false;
@@ -1640,12 +1641,19 @@ static int process_termination_nocpsch(struct device_queue_manager *dqm, dqm_lock(dqm); /* Clear all user mode queues */ - list_for_each_entry_safe(q, next, &qpd->queues_list, list) { + while (!list_empty(&qpd->queues_list)) { + struct mqd_manager *mqd_mgr; int ret; + q = list_first_entry(&qpd->queues_list, struct queue, list); + mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type( + q->properties.type)]; ret = destroy_queue_nocpsch_locked(dqm, qpd, q); if (ret) retval = ret; + dqm_unlock(dqm); + mqd_mgr->free_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj); + dqm_lock(dqm); } /* Unregister process */
--
2.30.2