Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Sasha Levin <sashal@kernel.org>
To:     linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc:     xinhui pan <xinhui.pan@amd.com>,
        Felix Kuehling <Felix.Kuehling@amd.com>,
        Alex Deucher <alexander.deucher@amd.com>,
        Sasha Levin <sashal@kernel.org>, amd-gfx@lists.freedesktop.org,
        dri-devel@lists.freedesktop.org
Subject: [PATCH AUTOSEL 5.13 129/189] drm/amdkfd: Walk through list with dqm lock hold
Date:   Tue,  6 Jul 2021 07:13:09 -0400
Message-Id: <20210706111409.2058071-129-sashal@kernel.org>
In-Reply-To: <20210706111409.2058071-1-sashal@kernel.org>
References: <20210706111409.2058071-1-sashal@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: xinhui pan <xinhui.pan@amd.com>

[ Upstream commit 56f221b6389e7ab99c30bbf01c71998ae92fc584 ]

To avoid any list corruption.

Signed-off-by: xinhui pan <xinhui.pan@amd.com>
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 | 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 e9b3e2e32bf8..f0bad74af230 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1709,7 +1709,7 @@ 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;
@@ -1766,24 +1766,26 @@ 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