[PATCHv4 2/8] nvme: export command retry count via sysfs

[Nilay Shroff]

When Advanced Command Retry Enable (ACRE) is configured, a controller
may interrupt command execution and return a completion status
indicating command interrupted with the DNR bit cleared. In this case,
the driver retries the command based on the Command Retry Delay (CRD)
value provided in the completion status.

Currently, these command retries are handled entirely within the NVMe
driver and are not visible to userspace. As a result, there is no
observability into retry behavior, which can be a useful diagnostic
signal.

Expose a per-namespace sysfs attribute command_retries_count, under
diag attribute group to provide visibility into retry activity. This
information can help identify controller-side congestion under load
and enables comparison across paths in multipath setups (for example,
detecting cases where one path experiences significantly more retries
than another under identical workloads).

This exported metric is intended for diagnostics and monitoring tools
such as nvme-top, and does not change command retry behavior. A new
sysfs attribute named "command_retries_count" is added for this purpose.
This attribute is both readable as well as writable. So user could
reset this counter if needed.

Signed-off-by: Nilay Shroff <nilay at linux.ibm.com>
---
 drivers/nvme/host/core.c  |  4 ++++
 drivers/nvme/host/nvme.h  |  1 +
 drivers/nvme/host/sysfs.c | 33 +++++++++++++++++++++++++++++++++
 3 files changed, 38 insertions(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index dc388e24caad..bacd5e45c322 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -323,6 +323,7 @@ static void nvme_retry_req(struct request *req)
 {
 	unsigned long delay = 0;
 	u16 crd;
+	struct nvme_ns *ns = req->q->queuedata;
 
 	/* The mask and shift result must be <= 3 */
 	crd = (nvme_req(req)->status & NVME_STATUS_CRD) >> 11;
@@ -330,6 +331,9 @@ static void nvme_retry_req(struct request *req)
 		delay = nvme_req(req)->ctrl->crdt[crd - 1] * 100;
 
 	nvme_req(req)->retries++;
+	if (ns)
+		atomic_long_inc(&ns->retries);
+
 	blk_mq_requeue_request(req, false);
 	blk_mq_delay_kick_requeue_list(req->q, delay);
 }
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index c8225d594252..7538153fa61c 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -590,6 +590,7 @@ struct nvme_ns {
 	enum nvme_ana_state ana_state;
 	u32 ana_grpid;
 #endif
+	atomic_long_t retries;
 	struct list_head siblings;
 	struct kref kref;
 	struct nvme_ns_head *head;
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index cc569c8556f3..46071e87079f 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -351,13 +351,46 @@ const struct attribute_group nvme_ns_mpath_attr_group = {
 };
 #endif
 
+static ssize_t command_retries_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", atomic_long_read(&ns->retries));
+}
+
+static ssize_t command_retries_count_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	unsigned long retries;
+	int err;
+	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
+
+	err = kstrtoul(buf, 0, &retries);
+	if (err)
+		return -EINVAL;
+
+	atomic_long_set(&ns->retries, retries);
+
+	return count;
+}
+static DEVICE_ATTR_RW(command_retries_count);
+
 static struct attribute *nvme_ns_diag_attrs[] = {
+	&dev_attr_command_retries_count.attr,
 	NULL,
 };
 
 static umode_t nvme_ns_diag_attrs_are_visible(struct kobject *kobj,
 		struct attribute *a, int n)
 {
+	struct device *dev = container_of(kobj, struct device, kobj);
+
+	if (a == &dev_attr_command_retries_count.attr) {
+		if (nvme_disk_is_ns_head(dev_to_disk(dev)))
+			return 0;
+	}
+
 	return a->mode;
 }
 
-- 
2.53.0