From: Nilay Shroff <nilay@linux.ibm.com>
Date: Sat, 16 May 2026 18:36:54 +0000 (+0530)
Subject: nvme: export controller reset event count via sysfs
X-Git-Url: http://git.ipfire.org/gitweb/?a=commitdiff_plain;h=29aafaaf582b342ef3e2182cefd0c2aac6e9f3a8;p=thirdparty%2Fkernel%2Flinux.git

nvme: export controller reset event count via sysfs

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 per-ctrl sysfs attribute reset_count, under diag attribute
group 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.

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>
---

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 5f885e0ab9308..efaddab8296e0 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -596,6 +596,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		case NVME_CTRL_NEW:
 		case NVME_CTRL_LIVE:
 			changed = true;
+			atomic_long_inc(&ctrl->nr_reset);
 			fallthrough;
 		default:
 			break;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 249f1f8dde404..81f297e995e4a 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -416,6 +416,7 @@ struct nvme_ctrl {
 	struct work_struct fw_act_work;
 	unsigned long events;
 	atomic_long_t errors;
+	atomic_long_t nr_reset;
 
 #ifdef CONFIG_NVME_MULTIPATH
 	/* asymmetric namespace access: */
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index d2c7d943b23fc..ff603a9d7b8ca 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -1151,8 +1151,35 @@ struct device_attribute dev_attr_adm_errors =
 	__ATTR(command_error_count, 0644,
 		nvme_adm_errors_show, nvme_adm_errors_store);
 
+static ssize_t reset_count_show(struct device *dev,
+		   struct device_attribute *attr, char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%lu\n", atomic_long_read(&ctrl->nr_reset));
+}
+
+static ssize_t reset_count_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;
+
+	atomic_long_set(&ctrl->nr_reset, reset_cnt);
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(reset_count);
+
 static struct attribute *nvme_dev_diag_attrs[] = {
 	&dev_attr_adm_errors.attr,
+	&dev_attr_reset_count.attr,
 	NULL,
 };