github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-07-28 10:09:10 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

nvme: export controller reset event count via sysfs

Browse Source 
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>
This commit is contained in:
Nilay Shroff 2026-05-17 00:06:54 +05:30 committed by Keith Busch
parent a8e434cb03
commit 29aafaaf58
3 changed files with 29 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
drivers/nvme/host/core.c
View File

@ -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;

1
drivers/nvme/host/nvme.h
View File

@ -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: */

27
drivers/nvme/host/sysfs.c
View File

@ -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,
};