This is a note to let you know that I've just added the patch titled nvme-rdma: add clean action for failed reconnection to the 5.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: nvme-rdma-add-clean-action-for-failed-reconnection.patch and it can be found in the queue-5.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. commit f4edaf81bd1943e0725087bd2069bcf6718141b6 Author: Chao Leng <lengchao@xxxxxxxxxx> Date: Thu Jan 21 11:32:37 2021 +0800 nvme-rdma: add clean action for failed reconnection [ Upstream commit 958dc1d32c80566f58d18f05ef1f05bd32d172c1 ] A crash happens when inject failed reconnection. If reconnect failed after start io queues, the queues will be unquiesced and new requests continue to be delivered. Reconnection error handling process directly free queues without cancel suspend requests. The suppend request will time out, and then crash due to use the queue after free. Add sync queues and cancel suppend requests for reconnection error handling. Signed-off-by: Chao Leng <lengchao@xxxxxxxxxx> Signed-off-by: Christoph Hellwig <hch@xxxxxx> Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 8a62c2fe5a5e..da6030010432 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -835,12 +835,16 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl, error = nvme_init_identify(&ctrl->ctrl); if (error) - goto out_stop_queue; + goto out_quiesce_queue; return 0; +out_quiesce_queue: + blk_mq_quiesce_queue(ctrl->ctrl.admin_q); + blk_sync_queue(ctrl->ctrl.admin_q); out_stop_queue: nvme_rdma_stop_queue(&ctrl->queues[0]); + nvme_cancel_admin_tagset(&ctrl->ctrl); out_cleanup_queue: if (new) blk_cleanup_queue(ctrl->ctrl.admin_q); @@ -917,8 +921,10 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) out_wait_freeze_timed_out: nvme_stop_queues(&ctrl->ctrl); + nvme_sync_io_queues(&ctrl->ctrl); nvme_rdma_stop_io_queues(ctrl); out_cleanup_connect_q: + nvme_cancel_tagset(&ctrl->ctrl); if (new) blk_cleanup_queue(ctrl->ctrl.connect_q); out_free_tag_set: @@ -1054,10 +1060,18 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new) return 0; destroy_io: - if (ctrl->ctrl.queue_count > 1) + if (ctrl->ctrl.queue_count > 1) { + nvme_stop_queues(&ctrl->ctrl); + nvme_sync_io_queues(&ctrl->ctrl); + nvme_rdma_stop_io_queues(ctrl); + nvme_cancel_tagset(&ctrl->ctrl); nvme_rdma_destroy_io_queues(ctrl, new); + } destroy_admin: + blk_mq_quiesce_queue(ctrl->ctrl.admin_q); + blk_sync_queue(ctrl->ctrl.admin_q); nvme_rdma_stop_queue(&ctrl->queues[0]); + nvme_cancel_admin_tagset(&ctrl->ctrl); nvme_rdma_destroy_admin_queue(ctrl, new); return ret; }