NVMe: Start all requests

Once the nvme callback is set for a request, the driver can start it
and make it available for timeout handling. For timed out commands on a
device that is not initialized, this fixes potential deadlocks that can
occur on startup and shutdown when a device is unresponsive since they
can now be cancelled.

Asynchronous requests do not have any expected timeout, so these are
using the new "REQ_NO_TIMEOUT" request flags.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index f7d083bb3bd5c0e437e6ce8cb6f640b2c65b7dda..286fa4cfc9372d832093914b0dbf37051d75c85b 100644 (file)
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -215,6 +215,7 @@ static void nvme_set_info(struct nvme_cmd_info *cmd, void *ctx,
        cmd->fn = handler;
        cmd->ctx = ctx;
        cmd->aborted = 0;
+       blk_mq_start_request(blk_mq_rq_from_pdu(cmd));
 }
 
 /* Special values must be less than 0x1000 */
@@ -664,8 +665,6 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
                }
        }
 
-       blk_mq_start_request(req);
-
        nvme_set_info(cmd, iod, req_completion);
        spin_lock_irq(&nvmeq->q_lock);
        if (req->cmd_flags & REQ_DISCARD)
@@ -835,6 +834,7 @@ static int nvme_submit_async_admin_req(struct nvme_dev *dev)
        if (IS_ERR(req))
                return PTR_ERR(req);
 
+       req->cmd_flags |= REQ_NO_TIMEOUT;
        cmd_info = blk_mq_rq_to_pdu(req);
        nvme_set_info(cmd_info, req, async_req_completion);
 
@@ -1086,8 +1086,16 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 
        dev_warn(nvmeq->q_dmadev, "Timeout I/O %d QID %d\n", req->tag,
                                                        nvmeq->qid);
-       if (nvmeq->dev->initialized)
-               nvme_abort_req(req);
+
+       if (!nvmeq->dev->initialized) {
+               /*
+                * Force cancelled command frees the request, which requires we
+                * return BLK_EH_NOT_HANDLED.
+                */
+               nvme_cancel_queue_ios(nvmeq->hctx, req, nvmeq, reserved);
+               return BLK_EH_NOT_HANDLED;
+       }
+       nvme_abort_req(req);
 
        /*
         * The aborted req will be completed on receiving the abort req.