nvme: export I/O requeue count when no path is usable via sysfs

When the NVMe namespace head determines that there is no currently
available path to handle I/O (for example, while a controller is
resetting/connecting or due to a transient link failure), incoming
I/Os are added to the requeue list.

Currently, there is no visibility into how many I/Os have been requeued
in this situation. Add a new ns-head sysfs counter
io_requeue_no_usable_path_count, under diag attribute group to expose
the number of I/Os that were requeued due to the absence of an available
path. This counter is also writable thus allowing user to reset it, if
needed.

This statistic can help users understand I/O slowdowns or stalls caused
by temporary path unavailability, and can be consumed by monitoring
tools such as nvme-top for real-time observability.

Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>

3 files changed, 37 insertions, 0 deletions

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 51c8d928fc80..9021fd44f193 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -538,6 +538,7 @@ static void nvme_ns_head_submit_bio(struct bio *bio)
 		spin_lock_irq(&head->requeue_lock);
 		bio_list_add(&head->requeue_list, bio);
 		spin_unlock_irq(&head->requeue_lock);
+		atomic_long_inc(&head->io_requeue_no_usable_path_count);
 	} else {
 		dev_warn_ratelimited(dev, "no available path - failing I/O\n");
 
@@ -1192,6 +1193,35 @@ static ssize_t multipath_failover_count_store(struct device *dev,
 
 DEVICE_ATTR_RW(multipath_failover_count);
 
+static ssize_t io_requeue_no_usable_path_count_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",
+		    atomic_long_read(&head->io_requeue_no_usable_path_count));
+}
+
+static ssize_t io_requeue_no_usable_path_count_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	int err;
+	unsigned long requeue_cnt;
+	struct gendisk *disk = dev_to_disk(dev);
+	struct nvme_ns_head *head = disk->private_data;
+
+	err = kstrtoul(buf, 0, &requeue_cnt);
+	if (err)
+		return -EINVAL;
+
+	atomic_long_set(&head->io_requeue_no_usable_path_count, requeue_cnt);
+
+	return count;
+}
+
+DEVICE_ATTR_RW(io_requeue_no_usable_path_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 f2734f03682f..bfd427184d69 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -566,6 +566,7 @@ struct nvme_ns_head {
 	unsigned long		flags;
 	struct delayed_work	remove_work;
 	unsigned int		delayed_removal_secs;
+	atomic_long_t		io_requeue_no_usable_path_count;
 #define NVME_NSHEAD_DISK_LIVE		0
 #define NVME_NSHEAD_QUEUE_IF_NO_PATH	1
 	struct nvme_ns __rcu	*current_path[];
@@ -1069,6 +1070,7 @@ 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 dev_attr_io_requeue_no_usable_path_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 a03a22c832d8..7f0575b7cdd0 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -403,6 +403,7 @@ static struct attribute *nvme_ns_diag_attrs[] = {
 	&dev_attr_io_errors.attr,
 #ifdef CONFIG_NVME_MULTIPATH
 	&dev_attr_multipath_failover_count.attr,
+	&dev_attr_io_requeue_no_usable_path_count.attr,
 #endif
 	NULL,
 };
@@ -427,6 +428,10 @@ static umode_t nvme_ns_diag_attrs_are_visible(struct kobject *kobj,
 		if (nvme_disk_is_ns_head(dev_to_disk(dev)))
 			return 0;
 	}
+	if (a == &dev_attr_io_requeue_no_usable_path_count.attr) {
+		if (!nvme_disk_is_ns_head(dev_to_disk(dev)))
+			return 0;
+	}
 #endif
 	return a->mode;
 }