[PATCHv2 2/7] nvme: export multipath failover count via sysfs

[Nilay Shroff]

When an NVMe command completes with a path-specific error, the NVMe
driver may retry the command on an alternate controller or path if one
is available. These failover events indicate that I/O was redirected
away from the original path.

Currently, the number of times requests are failed over to another
available path is not visible to userspace. Exposing this information
can be useful for diagnosing path health and stability.

Export the multipath failover count through sysfs to provide visibility
into path failover behavior. This statistic can be consumed by
monitoring tools such as nvme-top to help identify paths that
consistently trigger failovers under load.

Signed-off-by: Nilay Shroff <nilay at linux.ibm.com>
---
 drivers/nvme/host/multipath.c | 10 ++++++++++
 drivers/nvme/host/nvme.h      |  2 ++
 drivers/nvme/host/sysfs.c     |  5 +++++
 3 files changed, 17 insertions(+)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 174027d1cc19..792385477211 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -142,6 +142,7 @@ void nvme_failover_req(struct request *req)
 	struct bio *bio;
 
 	nvme_mpath_clear_current_path(ns);
+	ns->failover = size_add(ns->failover, 1);
 
 	/*
 	 * If we got back an ANA error, we know the controller is alive but not
@@ -1168,6 +1169,15 @@ static ssize_t delayed_removal_secs_store(struct device *dev,
 
 DEVICE_ATTR_RW(delayed_removal_secs);
 
+static ssize_t multipath_failover_count_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
+
+	return sysfs_emit(buf, "%lu\n", ns->failover);
+}
+DEVICE_ATTR_RO(multipath_failover_count);
+
 static int nvme_lookup_ana_group_desc(struct nvme_ctrl *ctrl,
 		struct nvme_ana_group_desc *desc, void *data)
 {
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 237829cdc151..6307243fd216 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -533,6 +533,7 @@ struct nvme_ns {
 #ifdef CONFIG_NVME_MULTIPATH
 	enum nvme_ana_state ana_state;
 	u32 ana_grpid;
+	size_t failover;
 #endif
 	size_t retries;
 	struct list_head siblings;
@@ -1000,6 +1001,7 @@ extern struct device_attribute dev_attr_ana_state;
 extern struct device_attribute dev_attr_queue_depth;
 extern struct device_attribute dev_attr_numa_nodes;
 extern struct device_attribute dev_attr_delayed_removal_secs;
+extern struct device_attribute dev_attr_multipath_failover_count;
 extern struct device_attribute subsys_attr_iopolicy;
 
 static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index 174d099246b4..34dcb6db9b5c 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -270,6 +270,7 @@ static struct attribute *nvme_ns_attrs[] = {
 	&dev_attr_queue_depth.attr,
 	&dev_attr_numa_nodes.attr,
 	&dev_attr_delayed_removal_secs.attr,
+	&dev_attr_multipath_failover_count.attr,
 #endif
 	&dev_attr_io_passthru_err_log_enabled.attr,
 	&dev_attr_command_retries.attr,
@@ -317,6 +318,10 @@ static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj,
 		if (!nvme_disk_is_ns_head(disk))
 			return 0;
 	}
+	if (a == &dev_attr_multipath_failover_count.attr) {
+		if (nvme_disk_is_ns_head(dev_to_disk(dev)))
+			return 0;
+	}
 #endif
 	return a->mode;
 }
-- 
2.52.0