From 7db814465395f3196ee98c8bd40d214d63e4f708 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 23 Oct 2017 16:04:11 +0300 Subject: nvme-rdma: fix possible hang when issuing commands during ctrl removal nvme_rdma_queue_is_ready() fails requests in case a queue is not LIVE. If the controller is in RECONNECTING state, we might be in this state for a long time (until we successfully reconnect) and we are better off with failing the request fast. Otherwise, we fail with BLK_STS_RESOURCE to have the block layer try again soon. In case we are removing the controller when the admin queue is not LIVE, we will terminate the request with BLK_STS_RESOURCE but it happens before we call blk_mq_start_request() so the request timeout never expires, and the queue will never get back to LIVE (because we are removing the controller). This causes the removal operation to block infinitly [1]. Thus, if we are removing (state DELETING), and the queue is not LIVE, we need to fail the request permanently as there is no chance for it to ever complete successfully. [1] -- sysrq: SysRq : Show Blocked State task PC stack pid father kworker/u66:2 D 0 440 2 0x80000000 Workqueue: nvme-wq nvme_rdma_del_ctrl_work [nvme_rdma] Call Trace: __schedule+0x3e9/0xb00 schedule+0x40/0x90 schedule_timeout+0x221/0x580 io_schedule_timeout+0x1e/0x50 wait_for_completion_io_timeout+0x118/0x180 blk_execute_rq+0x86/0xc0 __nvme_submit_sync_cmd+0x89/0xf0 nvmf_reg_write32+0x4b/0x90 [nvme_fabrics] nvme_shutdown_ctrl+0x41/0xe0 nvme_rdma_shutdown_ctrl+0xca/0xd0 [nvme_rdma] nvme_rdma_remove_ctrl+0x2b/0x40 [nvme_rdma] nvme_rdma_del_ctrl_work+0x25/0x30 [nvme_rdma] process_one_work+0x1fd/0x630 worker_thread+0x1db/0x3b0 kthread+0x11e/0x150 ret_from_fork+0x27/0x40 01 D 0 2868 2862 0x00000000 Call Trace: __schedule+0x3e9/0xb00 schedule+0x40/0x90 schedule_timeout+0x260/0x580 wait_for_completion+0x108/0x170 flush_work+0x1e0/0x270 nvme_rdma_del_ctrl+0x5a/0x80 [nvme_rdma] nvme_sysfs_delete+0x2a/0x40 dev_attr_store+0x18/0x30 sysfs_kf_write+0x45/0x60 kernfs_fop_write+0x124/0x1c0 __vfs_write+0x28/0x150 vfs_write+0xc7/0x1b0 SyS_write+0x49/0xa0 entry_SYSCALL_64_fastpath+0x18/0xad -- Reported-by: Bart Van Assche Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/rdma.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 87bac27ec64b..0ebb539f3bd3 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1614,12 +1614,15 @@ nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue, struct request *rq) /* * reconnecting state means transport disruption, which * can take a long time and even might fail permanently, - * so we can't let incoming I/O be requeued forever. - * fail it fast to allow upper layers a chance to - * failover. + * fail fast to give upper layers a chance to failover. + * deleting state means that the ctrl will never accept + * commands again, fail it permanently. */ - if (queue->ctrl->ctrl.state == NVME_CTRL_RECONNECTING) + if (queue->ctrl->ctrl.state == NVME_CTRL_RECONNECTING || + queue->ctrl->ctrl.state == NVME_CTRL_DELETING) { + nvme_req(rq)->status = NVME_SC_ABORT_REQ; return BLK_STS_IOERR; + } return BLK_STS_RESOURCE; /* try again later */ } } -- cgit v1.2.3