nvme-fabrics: reject I/O to offline device

Commands get stuck while Host NVMe-oF controller is in reconnect state.
The controller enters into reconnect state when it loses connection with
the target.  It tries to reconnect every 10 seconds (default) until
a successful reconnect or until the reconnect time-out is reached.
The default reconnect time out is 10 minutes.

Applications are expecting commands to complete with success or error
within a certain timeout (30 seconds by default).  The NVMe host is
enforcing that timeout while it is connected, but during reconnect the
timeout is not enforced and commands may get stuck for a long period or
even forever.

To fix this long delay due to the default timeout, introduce new
"fast_io_fail_tmo" session parameter.  The timeout is measured in seconds
from the controller reconnect and any command beyond that timeout is
rejected.  The new parameter value may be passed during 'connect'.
The default value of -1 means no timeout (similar to current behavior).

Signed-off-by: Victor Gladkov <victor.gladkov@kioxia.com>
Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chao Leng <lengchao@huawei.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

1 files changed, 22 insertions, 3 deletions

diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 8575724734e0..72ac00173500 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -549,6 +549,7 @@ blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
 {
 	if (ctrl->state != NVME_CTRL_DELETING_NOIO &&
 	    ctrl->state != NVME_CTRL_DEAD &&
+	    !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
 	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
 		return BLK_STS_RESOURCE;
 
@@ -615,6 +616,7 @@ static const match_table_t opt_tokens = {
 	{ NVMF_OPT_NR_WRITE_QUEUES,	"nr_write_queues=%d"	},
 	{ NVMF_OPT_NR_POLL_QUEUES,	"nr_poll_queues=%d"	},
 	{ NVMF_OPT_TOS,			"tos=%d"		},
+	{ NVMF_OPT_FAIL_FAST_TMO,	"fast_io_fail_tmo=%d"	},
 	{ NVMF_OPT_ERR,			NULL			}
 };
 
@@ -634,6 +636,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 	opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY;
 	opts->kato = NVME_DEFAULT_KATO;
 	opts->duplicate_connect = false;
+	opts->fast_io_fail_tmo = NVMF_DEF_FAIL_FAST_TMO;
 	opts->hdr_digest = false;
 	opts->data_digest = false;
 	opts->tos = -1; /* < 0 == use transport default */
@@ -754,6 +757,17 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 				pr_warn("ctrl_loss_tmo < 0 will reconnect forever\n");
 			ctrl_loss_tmo = token;
 			break;
+		case NVMF_OPT_FAIL_FAST_TMO:
+			if (match_int(args, &token)) {
+				ret = -EINVAL;
+				goto out;
+			}
+
+			if (token >= 0)
+				pr_warn("I/O fail on reconnect controller after %d sec\n",
+					token);
+			opts->fast_io_fail_tmo = token;
+			break;
 		case NVMF_OPT_HOSTNQN:
 			if (opts->host) {
 				pr_err("hostnqn already user-assigned: %s\n",
@@ -884,11 +898,15 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 		opts->nr_poll_queues = 0;
 		opts->duplicate_connect = true;
 	}
-	if (ctrl_loss_tmo < 0)
+	if (ctrl_loss_tmo < 0) {
 		opts->max_reconnects = -1;
-	else
+	} else {
 		opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo,
 						opts->reconnect_delay);
+		if (ctrl_loss_tmo < opts->fast_io_fail_tmo)
+			pr_warn("failfast tmo (%d) larger than controller loss tmo (%d)\n",
+				opts->fast_io_fail_tmo, ctrl_loss_tmo);
+	}
 
 	if (!opts->host) {
 		kref_get(&nvmf_default_host->ref);
@@ -988,7 +1006,8 @@ EXPORT_SYMBOL_GPL(nvmf_free_options);
 #define NVMF_ALLOWED_OPTS	(NVMF_OPT_QUEUE_SIZE | NVMF_OPT_NR_IO_QUEUES | \
 				 NVMF_OPT_KATO | NVMF_OPT_HOSTNQN | \
 				 NVMF_OPT_HOST_ID | NVMF_OPT_DUP_CONNECT |\
-				 NVMF_OPT_DISABLE_SQFLOW)
+				 NVMF_OPT_DISABLE_SQFLOW |\
+				 NVMF_OPT_FAIL_FAST_TMO)
 
 static struct nvme_ctrl *
 nvmf_create_ctrl(struct device *dev, const char *buf)