[PATCHv2 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 | 12 ++++++++++++
 drivers/nvme/host/nvme.h      |  2 ++
 drivers/nvme/host/sysfs.c     |  5 +++++
 3 files changed, 19 insertions(+)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index e0bfbc659963..9984221bcec0 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -545,6 +545,8 @@ 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 =
+				size_add(head->fail_no_available_path, 1);
 	}
 
 	srcu_read_unlock(&head->srcu, srcu_idx);
@@ -1190,6 +1192,16 @@ 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, "%lu\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 39e5b5c7885b..b1ce2857899a 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -509,6 +509,7 @@ struct nvme_ns_head {
 	struct delayed_work	remove_work;
 	unsigned int		delayed_removal_secs;
 	size_t			requeue_no_usable_path;
+	size_t			fail_no_available_path;
 #define NVME_NSHEAD_DISK_LIVE		0
 #define NVME_NSHEAD_QUEUE_IF_NO_PATH	1
 	struct nvme_ns __rcu	*current_path[];
@@ -1006,6 +1007,7 @@ 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 a6b8539074ee..c1e2b93f7ae8 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -283,6 +283,7 @@ 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_command_retries.attr,
@@ -345,6 +346,10 @@ 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_fail_no_available_path.attr) {
+		if (!nvme_disk_is_ns_head(dev_to_disk(dev)))
+			return 0;
+	}
 #endif
 	return a->mode;
 }
-- 
2.52.0