[PATCHv3 6/7] nvme: export controller reset event count via sysfs

[Nilay Shroff]

The NVMe controller transitions into the RESETTING state during error
recovery, link instability, firmware activation, or when a reset is
explicitly triggered by the user.

Expose a controller reset event count via sysfs attribute named
"reset_events" to provide visibility into these RESETTING state
transitions. Observing the frequency of reset events can help users
identify issues such as PCIe errors or unstable fabric links. This
counter is also writable thus allowing user to reset its value, if
needed.

This counter can also be consumed by monitoring tools such as nvme-top
to improve controller-level observability.

Signed-off-by: Nilay Shroff <nilay at linux.ibm.com>
---
 drivers/nvme/host/core.c  |  2 ++
 drivers/nvme/host/nvme.h  |  1 +
 drivers/nvme/host/sysfs.c | 27 +++++++++++++++++++++++++++
 3 files changed, 30 insertions(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index d07e2ed9e494..1cba460d8563 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -593,6 +593,8 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		case NVME_CTRL_NEW:
 		case NVME_CTRL_LIVE:
 			changed = true;
+			WRITE_ONCE(ctrl->nr_reset,
+				size_add(READ_ONCE(ctrl->nr_reset), 1));
 			fallthrough;
 		default:
 			break;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index b1ce2857899a..5d90e5fa7298 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -360,6 +360,7 @@ struct nvme_ctrl {
 	struct work_struct fw_act_work;
 	unsigned long events;
 	size_t errors;
+	size_t nr_reset;
 #ifdef CONFIG_NVME_MULTIPATH
 	/* asymmetric namespace access: */
 	u8 anacap;
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index 790bf875dd1b..f3e6c7208315 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -710,6 +710,32 @@ struct device_attribute dev_attr_adm_errors =
 	__ATTR(command_error_count, 0644,
 			nvme_adm_errors_show, nvme_adm_errors_store);
 
+static ssize_t reset_events_show(struct device *dev,
+		   struct device_attribute *attr, char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%lu\n", READ_ONCE(ctrl->nr_reset));
+}
+
+static ssize_t reset_events_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	int err;
+	unsigned long reset_cnt;
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	err = kstrtoul(buf, 0, &reset_cnt);
+	if (err)
+		return -EINVAL;
+
+	WRITE_ONCE(ctrl->nr_reset, reset_cnt);
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(reset_events);
+
 #ifdef CONFIG_NVME_HOST_AUTH
 static ssize_t nvme_ctrl_dhchap_secret_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -857,6 +883,7 @@ static struct attribute *nvme_dev_attrs[] = {
 #endif
 	&dev_attr_adm_passthru_err_log_enabled.attr,
 	&dev_attr_adm_errors.attr,
+	&dev_attr_reset_events.attr,
 	NULL
 };
 
-- 
2.52.0