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>

drivers/nvme/host/core.c

@@ -148,6 +148,38 @@ int nvme_try_sched_reset(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_try_sched_reset);
 
+static void nvme_failfast_work(struct work_struct *work)
+{
+	struct nvme_ctrl *ctrl = container_of(to_delayed_work(work),
+			struct nvme_ctrl, failfast_work);
+
+	if (ctrl->state != NVME_CTRL_CONNECTING)
+		return;
+
+	set_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
+	dev_info(ctrl->device, "failfast expired\n");
+	nvme_kick_requeue_lists(ctrl);
+}
+
+static inline void nvme_start_failfast_work(struct nvme_ctrl *ctrl)
+{
+	if (!ctrl->opts || ctrl->opts->fast_io_fail_tmo == -1)
+		return;
+
+	schedule_delayed_work(&ctrl->failfast_work,
+			      ctrl->opts->fast_io_fail_tmo * HZ);
+}
+
+static inline void nvme_stop_failfast_work(struct nvme_ctrl *ctrl)
+{
+	if (!ctrl->opts)
+		return;
+
+	cancel_delayed_work_sync(&ctrl->failfast_work);
+	clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
+}
+
+
 int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
 {
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
@@ -433,8 +465,17 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	}
 
 	spin_unlock_irqrestore(&ctrl->lock, flags);
-	if (changed && ctrl->state == NVME_CTRL_LIVE)
+	if (!changed)
+		return false;
+
+	if (ctrl->state == NVME_CTRL_LIVE) {
+		if (old_state == NVME_CTRL_CONNECTING)
+			nvme_stop_failfast_work(ctrl);
 		nvme_kick_requeue_lists(ctrl);
+	} else if (ctrl->state == NVME_CTRL_CONNECTING &&
+		old_state == NVME_CTRL_RESETTING) {
+		nvme_start_failfast_work(ctrl);
+	}
 	return changed;
 }
 EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
@@ -4372,6 +4413,7 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
 {
 	nvme_mpath_stop(ctrl);
 	nvme_stop_keep_alive(ctrl);
+	nvme_stop_failfast_work(ctrl);
 	flush_work(&ctrl->async_event_work);
 	cancel_work_sync(&ctrl->fw_act_work);
 }
@@ -4437,6 +4479,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	int ret;
 
 	ctrl->state = NVME_CTRL_NEW;
+	clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
 	spin_lock_init(&ctrl->lock);
 	mutex_init(&ctrl->scan_lock);
 	INIT_LIST_HEAD(&ctrl->namespaces);
@@ -4453,6 +4496,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	init_waitqueue_head(&ctrl->state_wq);
 
 	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
+	INIT_DELAYED_WORK(&ctrl->failfast_work, nvme_failfast_work);
 	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
 	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
 

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)

drivers/nvme/host/fabrics.h

@@ -15,6 +15,8 @@
 #define NVMF_DEF_RECONNECT_DELAY	10
 /* default to 600 seconds of reconnect attempts before giving up */
 #define NVMF_DEF_CTRL_LOSS_TMO		600
+/* default is -1: the fail fast mechanism is disabled  */
+#define NVMF_DEF_FAIL_FAST_TMO		-1
 
 /*
  * Define a host as seen by the target.  We allocate one at boot, but also
@@ -56,6 +58,7 @@ enum {
 	NVMF_OPT_NR_WRITE_QUEUES = 1 << 17,
 	NVMF_OPT_NR_POLL_QUEUES = 1 << 18,
 	NVMF_OPT_TOS		= 1 << 19,
+	NVMF_OPT_FAIL_FAST_TMO	= 1 << 20,
 };
 
 /**
@@ -89,6 +92,7 @@ enum {
  * @nr_write_queues: number of queues for write I/O
  * @nr_poll_queues: number of queues for polling I/O
  * @tos: type of service
+ * @fast_io_fail_tmo: Fast I/O fail timeout in seconds
  */
 struct nvmf_ctrl_options {
 	unsigned		mask;
@@ -111,6 +115,7 @@ struct nvmf_ctrl_options {
 	unsigned int		nr_write_queues;
 	unsigned int		nr_poll_queues;
 	int			tos;
+	int			fast_io_fail_tmo;
 };
 
 /*

drivers/nvme/host/multipath.c

@@ -279,6 +279,8 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 	struct nvme_ns *ns;
 
 	list_for_each_entry_rcu(ns, &head->list, siblings) {
+		if (test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ns->ctrl->flags))
+			continue;
 		switch (ns->ctrl->state) {
 		case NVME_CTRL_LIVE:
 		case NVME_CTRL_RESETTING:

drivers/nvme/host/nvme.h

@@ -305,6 +305,7 @@ struct nvme_ctrl {
 	struct work_struct scan_work;
 	struct work_struct async_event_work;
 	struct delayed_work ka_work;
+	struct delayed_work failfast_work;
 	struct nvme_command ka_cmd;
 	struct work_struct fw_act_work;
 	unsigned long events;
@@ -338,6 +339,8 @@ struct nvme_ctrl {
 	u16 icdoff;
 	u16 maxcmd;
 	int nr_reconnects;
+	unsigned long flags;
+#define NVME_CTRL_FAILFAST_EXPIRED	0
 	struct nvmf_ctrl_options *opts;
 
 	struct page *discard_page;