From: Chao Leng <lengchao@huawei.com>
Date: Thu, 22 Oct 2020 10:15:15 +0800
Subject: [PATCH] nvme-tcp: avoid race between time out and tear down
Git-commit: d6f66210f4b1aa2f5944f0e34e0f8db44f499f92
Patch-Mainline: v5.10-rc3
References: bsc#1179519

Now use teardown_lock to serialize for time out and tear down. This may
cause abnormal: first cancel all request in tear down, then time out may
complete the request again, but the request may already be freed or
restarted.

To avoid race between time out and tear down, in tear down process,
first we quiesce the queue, and then delete the timer and cancel
the time out work for the queue. At the same time we need to delete
teardown_lock.

Signed-off-by: Chao Leng <lengchao@huawei.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 drivers/nvme/host/tcp.c | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index d6a3e1487354..19f86ea547bb 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -124,7 +124,6 @@ struct nvme_tcp_ctrl {
 	struct sockaddr_storage src_addr;
 	struct nvme_ctrl	ctrl;
 
-	struct mutex		teardown_lock;
 	struct work_struct	err_work;
 	struct delayed_work	connect_work;
 	struct nvme_tcp_request async_req;
@@ -1886,8 +1885,8 @@ static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new)
 static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
 		bool remove)
 {
-	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	blk_mq_quiesce_queue(ctrl->admin_q);
+	blk_sync_queue(ctrl->admin_q);
 	nvme_tcp_stop_queue(ctrl, 0);
 	if (ctrl->admin_tagset) {
 		blk_mq_tagset_busy_iter(ctrl->admin_tagset,
@@ -1897,18 +1896,17 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
 	if (remove)
 		blk_mq_unquiesce_queue(ctrl->admin_q);
 	nvme_tcp_destroy_admin_queue(ctrl, remove);
-	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 		bool remove)
 {
-	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	if (ctrl->queue_count <= 1)
-		goto out;
+		return;
 	blk_mq_quiesce_queue(ctrl->admin_q);
 	nvme_start_freeze(ctrl);
 	nvme_stop_queues(ctrl);
+	nvme_sync_io_queues(ctrl);
 	nvme_tcp_stop_io_queues(ctrl);
 	if (ctrl->tagset) {
 		blk_mq_tagset_busy_iter(ctrl->tagset,
@@ -1918,8 +1916,6 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 	if (remove)
 		nvme_start_queues(ctrl);
 	nvme_tcp_destroy_io_queues(ctrl, remove);
-out:
-	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
@@ -2171,14 +2167,11 @@ static void nvme_tcp_complete_timed_out(struct request *rq)
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
 
-	/* fence other contexts that may complete the command */
-	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue));
 	if (!blk_mq_request_completed(rq)) {
 		nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
 		blk_mq_complete_request(rq);
 	}
-	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static enum blk_eh_timer_return
@@ -2455,7 +2448,6 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 			nvme_tcp_reconnect_ctrl_work);
 	INIT_WORK(&ctrl->err_work, nvme_tcp_error_recovery_work);
 	INIT_WORK(&ctrl->ctrl.reset_work, nvme_reset_ctrl_work);
-	mutex_init(&ctrl->teardown_lock);
 
 	if (!(opts->mask & NVMF_OPT_TRSVCID)) {
 		opts->trsvcid =
-- 
2.16.4