[PATCH 5/7] nvme: export I/O failure count when no path is available via sysfs

[Nilay Shroff]

When I/O is submitted to the NVMe namespace head and no available path
can handle the request, the driver fails the I/O immediately. Currently,
such failures are only reported via kernel log messages, which may be
lost over time since dmesg is a circular buffer.

Add a new sysfs counter, fail_no_available_path, to expose the number of
I/Os that failed due to the absence of an available path. This provides
persistent visibility into path-related I/O failures and can help users
diagnose the cause of I/O errors.

This counter can also be consumed by monitoring tools such as nvme-top.

Signed-off-by: Nilay Shroff <nilay at linux.ibm.com>
---
 drivers/nvme/host/multipath.c | 11 +++++++++++
 drivers/nvme/host/nvme.h      |  2 ++
 drivers/nvme/host/sysfs.c     |  1 +
 3 files changed, 14 insertions(+)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 4e5f8523ca40..85641e8852ad 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -544,6 +544,7 @@ static void nvme_ns_head_submit_bio(struct bio *bio)
 		dev_warn_ratelimited(dev, "no available path - failing I/O\n");
 
 		bio_io_error(bio);
+		head->fail_no_available_path++;
 	}
 
 	srcu_read_unlock(&head->srcu, srcu_idx);
@@ -1189,6 +1190,16 @@ static ssize_t requeue_no_usable_path_show(struct device *dev,
 }
 DEVICE_ATTR_RO(requeue_no_usable_path);
 
+static ssize_t fail_no_available_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, "%llu\n", head->fail_no_available_path);
+}
+DEVICE_ATTR_RO(fail_no_available_path);
+
 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 5836e4c557a2..66bd4db1fe0f 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -510,6 +510,7 @@ struct nvme_ns_head {
 	struct delayed_work	remove_work;
 	unsigned int		delayed_removal_secs;
 	u64			requeue_no_usable_path;
+	u64			fail_no_available_path;
 #define NVME_NSHEAD_DISK_LIVE		0
 #define NVME_NSHEAD_QUEUE_IF_NO_PATH	1
 	struct nvme_ns __rcu	*current_path[];
@@ -1007,6 +1008,7 @@ 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 dev_attr_requeue_no_usable_path;
+extern struct device_attribute dev_attr_fail_no_available_path;
 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 84d33445a578..c23d9a0ba3f4 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -285,6 +285,7 @@ static struct attribute *nvme_ns_attrs[] = {
 	&dev_attr_delayed_removal_secs.attr,
 	&dev_attr_multipath_failover_count.attr,
 	&dev_attr_requeue_no_usable_path.attr,
+	&dev_attr_fail_no_available_path.attr,
 #endif
 	&dev_attr_io_passthru_err_log_enabled.attr,
 	&dev_attr_io_command_retries.attr,
-- 
2.52.0