nvme-rdma: avoid race between time out and tear down

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>

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 40a0a3b..83dbf22 100644 (file)
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -122,7 +122,6 @@ struct nvme_rdma_ctrl {
        struct sockaddr_storage src_addr;
 
        struct nvme_ctrl        ctrl;
-       struct mutex            teardown_lock;
        bool                    use_inline_data;
        u32                     io_queues[HCTX_MAX_TYPES];
 };
@@ -1010,8 +1009,8 @@ out_free_io_queues:
 static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
                bool remove)
 {
-       mutex_lock(&ctrl->teardown_lock);
        blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+       blk_sync_queue(ctrl->ctrl.admin_q);
        nvme_rdma_stop_queue(&ctrl->queues[0]);
        if (ctrl->ctrl.admin_tagset) {
                blk_mq_tagset_busy_iter(ctrl->ctrl.admin_tagset,
@@ -1021,16 +1020,15 @@ static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
        if (remove)
                blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
        nvme_rdma_destroy_admin_queue(ctrl, remove);
-       mutex_unlock(&ctrl->teardown_lock);
 }
 
 static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
                bool remove)
 {
-       mutex_lock(&ctrl->teardown_lock);
        if (ctrl->ctrl.queue_count > 1) {
                nvme_start_freeze(&ctrl->ctrl);
                nvme_stop_queues(&ctrl->ctrl);
+               nvme_sync_io_queues(&ctrl->ctrl);
                nvme_rdma_stop_io_queues(ctrl);
                if (ctrl->ctrl.tagset) {
                        blk_mq_tagset_busy_iter(ctrl->ctrl.tagset,
@@ -1041,7 +1039,6 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
                        nvme_start_queues(&ctrl->ctrl);
                nvme_rdma_destroy_io_queues(ctrl, remove);
        }
-       mutex_unlock(&ctrl->teardown_lock);
 }
 
 static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
@@ -1976,16 +1973,12 @@ static void nvme_rdma_complete_timed_out(struct request *rq)
 {
        struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
        struct nvme_rdma_queue *queue = req->queue;
-       struct nvme_rdma_ctrl *ctrl = queue->ctrl;
 
-       /* fence other contexts that may complete the command */
-       mutex_lock(&ctrl->teardown_lock);
        nvme_rdma_stop_queue(queue);
        if (!blk_mq_request_completed(rq)) {
                nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
                blk_mq_complete_request(rq);
        }
-       mutex_unlock(&ctrl->teardown_lock);
 }
 
 static enum blk_eh_timer_return
@@ -2320,7 +2313,6 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
                return ERR_PTR(-ENOMEM);
        ctrl->ctrl.opts = opts;
        INIT_LIST_HEAD(&ctrl->list);
-       mutex_init(&ctrl->teardown_lock);
 
        if (!(opts->mask & NVMF_OPT_TRSVCID)) {
                opts->trsvcid =