Merge tag 'amd-drm-next-5.14-2021-06-16' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.14-2021-06-16:

amdgpu:
- Aldebaran fixes
- Expose asic independent throttler status
- BACO fixes for navi1x
- Smartshift fixes
- Misc code cleanups
- RAS fixes for Sienna Cichlid
- Gamma verificaton fixes
- DC LTTPR fixes
- DP AUX timeout handling fixes
- GFX9, 10 powergating fixes

amdkfd:
- TLB flush fixes when using SDMA
- Locking fixes
- SVM fixes

Signed-off-by: Dave Airlie <[email protected]>
From: Alex Deucher <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

1 files changed, 26 insertions, 20 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 edb14e4a9f33..c069fa259b30 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;
 }
 
@@ -1629,7 +1630,7 @@ out:
 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;
@@ -1637,12 +1638,19 @@ 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 */
@@ -1674,29 +1682,27 @@ static int get_wave_state(struct device_queue_manager *dqm,
 			  u32 *save_area_used_size)
 {
 	struct mqd_manager *mqd_mgr;
-	int r;
 
 	dqm_lock(dqm);
 
-	if (q->properties.type != KFD_QUEUE_TYPE_COMPUTE ||
-	    q->properties.is_active || !q->device->cwsr_enabled) {
-		r = -EINVAL;
-		goto dqm_unlock;
-	}
-
 	mqd_mgr = dqm->mqd_mgrs[KFD_MQD_TYPE_CP];
 
-	if (!mqd_mgr->get_wave_state) {
-		r = -EINVAL;
-		goto dqm_unlock;
+	if (q->properties.type != KFD_QUEUE_TYPE_COMPUTE ||
+	    q->properties.is_active || !q->device->cwsr_enabled ||
+	    !mqd_mgr->get_wave_state) {
+		dqm_unlock(dqm);
+		return -EINVAL;
 	}
 
-	r = mqd_mgr->get_wave_state(mqd_mgr, q->mqd, ctl_stack,
-			ctl_stack_used_size, save_area_used_size);
-
-dqm_unlock:
 	dqm_unlock(dqm);
-	return r;
+
+	/*
+	 * get_wave_state is outside the dqm lock to prevent circular locking
+	 * and the queue should be protected against destruction by the process
+	 * lock.
+	 */
+	return mqd_mgr->get_wave_state(mqd_mgr, q->mqd, ctl_stack,
+			ctl_stack_used_size, save_area_used_size);
 }
 
 static int process_termination_cpsch(struct device_queue_manager *dqm,