[PATCH v4 2/2] nvme-multipath: add fail_if_no_path sysfs attribute

[Krishna Iyer]

When no usable path exists, I/O on a multipath namespace is queued
until a path returns. With ctrl_loss_tmo=-1 that can be forever:
during a long fabric outage any process waiting on the I/O is stuck in
D state. We hit this on virtualization hosts, where a SIGKILLed VM
process cannot exit while draining I/O to an unreachable NVMe/TCP
target.

Nothing can fail this I/O without tearing something down: controller
deletion takes every namespace on the controller with it.

Add a fail_if_no_path attribute on the ns-head disk: a persistent
per-namespace policy to fail parked and newly arriving I/O instead of
queueing it when no usable path exists. It is the namespace-scoped
counterpart to the controller-scoped fast_io_fail_tmo: the trigger is
an event userspace observes (a consumer known to be gone, for us a
SIGKILLed VM the host must reap), not a duration picked up front, and
sibling namespaces behind the same controllers keep queueing and ride
out the outage.

A CONNECTING controller stops counting as an available path, and with
no controllers left the policy overrides the delayed_removal_secs
queue-if-no-path window; the two are opposites, so fail_if_no_path takes
precedence when both are set. ANA change and controller resetting still
queue, since both are transient. Controller state is untouched and
reconnects continue. Like dm's fail_if_no_path, the policy is transport
agnostic.

Assisted-by: Claude:claude-fable-5
Signed-off-by: Krishna Iyer <kiyer@xxxxxxxxx>
---
 Documentation/ABI/stable/sysfs-nvme | 16 +++++++++
 drivers/nvme/host/multipath.c       | 50 +++++++++++++++++++++++++++--
 drivers/nvme/host/nvme.h            |  2 ++
 drivers/nvme/host/sysfs.c           |  4 ++-
 4 files changed, 69 insertions(+), 3 deletions(-)

diff --git a/Documentation/ABI/stable/sysfs-nvme b/Documentation/ABI/stable/sysfs-nvme
index a0bb88ca1694..448692dcb117 100644
--- a/Documentation/ABI/stable/sysfs-nvme
+++ b/Documentation/ABI/stable/sysfs-nvme
@@ -358,6 +358,22 @@ Description:
 		is deferred. Only visible on multipath head devices.
 		Requires CONFIG_NVME_MULTIPATH.
 
+What:		/sys/block/nvmeXnY/fail_if_no_path
+Date:		October 2026
+KernelVersion:	7.4
+Contact:	Krishna Iyer <kiyer@xxxxxxxxx>
+Description:
+		Shows or sets the fail-if-no-path policy of the multipath
+		head device ("on" or "off", default "off"). When on, I/O
+		queued or arriving while no usable path exists is failed
+		immediately instead of being queued. This is the opposite of
+		the queue-if-no-path behavior enabled by a nonzero
+		delayed_removal_secs: when both are set fail_if_no_path takes
+		precedence and the parked I/O is failed rather than held for
+		the delayed_removal_secs window. Reconnect attempts are not
+		affected. Only visible on multipath head devices.
+		Requires CONFIG_NVME_MULTIPATH.
+
 What:		/sys/block/nvmeXnY/csi
 What:		/sys/block/nvmeXnY/metadata_bytes
 What:		/sys/block/nvmeXnY/nuse
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 0d6c05f0808b..e43b0f43e73e 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -517,6 +517,8 @@ static inline bool nvme_state_is_live(enum nvme_ana_state state)
 static bool nvme_available_path(struct nvme_ns_head *head)
 	__must_hold_shared(&head->srcu)
 {
+	bool fail_if_no_path = test_bit(NVME_NSHEAD_FAIL_IF_NO_PATH,
+					&head->flags);
 	bool failfast = false;
 	struct nvme_ns *ns;
 
@@ -536,14 +538,17 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 				continue;
 			return true;
 		case NVME_CTRL_RESETTING:
-		case NVME_CTRL_CONNECTING:
 			return true;
+		case NVME_CTRL_CONNECTING:
+			if (!fail_if_no_path)
+				return true;
+			continue;
 		default:
 			break;
 		}
 	}
 
-	if (failfast)
+	if (failfast || fail_if_no_path)
 		return false;
 
 	/*
@@ -1242,6 +1247,47 @@ static ssize_t delayed_removal_secs_store(struct device *dev,
 
 DEVICE_ATTR_RW(delayed_removal_secs);
 
+static ssize_t fail_if_no_path_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	struct nvme_ns_head *head = disk->private_data;
+
+	return sysfs_emit(buf, test_bit(NVME_NSHEAD_FAIL_IF_NO_PATH,
+			&head->flags) ? "on\n" : "off\n");
+}
+
+static ssize_t fail_if_no_path_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	struct nvme_ns_head *head = disk->private_data;
+	bool enable;
+	int ret;
+
+	ret = kstrtobool(buf, &enable);
+	if (ret < 0)
+		return ret;
+
+	if (enable) {
+		if (test_and_set_bit(NVME_NSHEAD_FAIL_IF_NO_PATH, &head->flags))
+			return count;
+	} else {
+		if (!test_and_clear_bit(NVME_NSHEAD_FAIL_IF_NO_PATH,
+					&head->flags))
+			return count;
+	}
+
+	synchronize_srcu(&head->srcu);
+
+	if (enable)
+		kblockd_schedule_work(&head->requeue_work);
+
+	return count;
+}
+
+DEVICE_ATTR_RW(fail_if_no_path);
+
 static ssize_t multipath_failover_count_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index bac25b287d25..71ec72306c9c 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -589,6 +589,7 @@ struct nvme_ns_head {
 #define NVME_NSHEAD_DISK_LIVE		0
 #define NVME_NSHEAD_QUEUE_IF_NO_PATH	1
 #define NVME_NSHEAD_CDEV_LIVE		2
+#define NVME_NSHEAD_FAIL_IF_NO_PATH	3
 	struct nvme_ns __rcu_guarded	*current_path[];
 #endif
 };
@@ -1097,6 +1098,7 @@ extern struct device_attribute dev_attr_queue_depth;
 extern struct device_attribute dev_attr_numa_nodes;
 extern struct device_attribute dev_attr_path_state;
 extern struct device_attribute dev_attr_delayed_removal_secs;
+extern struct device_attribute dev_attr_fail_if_no_path;
 extern struct device_attribute dev_attr_multipath_failover_count;
 extern struct device_attribute dev_attr_io_requeue_no_usable_path_count;
 extern struct device_attribute dev_attr_io_fail_no_available_path_count;
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index 4ac3ea3a86fd..fe1e5305880e 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -265,6 +265,7 @@ static struct attribute *nvme_ns_attrs[] = {
 	&dev_attr_numa_nodes.attr,
 	&dev_attr_path_state.attr,
 	&dev_attr_delayed_removal_secs.attr,
+	&dev_attr_fail_if_no_path.attr,
 #endif
 	&dev_attr_io_passthru_err_log_enabled.attr,
 	NULL,
@@ -302,7 +303,8 @@ static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj,
 		if (nvme_disk_is_ns_head(dev_to_disk(dev)))
 			return 0;
 	}
-	if (a == &dev_attr_delayed_removal_secs.attr) {
+	if (a == &dev_attr_delayed_removal_secs.attr ||
+	    a == &dev_attr_fail_if_no_path.attr) {
 		struct gendisk *disk = dev_to_disk(dev);
 
 		if (!nvme_disk_is_ns_head(disk))
-- 
2.54.0