[PATCH net-next] net: sysfs: use ops lock for speed and duplex
From: Wang Zhan <hidden>
Date: 2026-08-31 08:06:35
Subsystem:
networking [general], the rest · Maintainers:
"David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Linus Torvalds
Reading /sys/class/net/<dev>/{speed,duplex} takes rtnl_lock() before
calling __ethtool_get_link_ksettings(). For ops-locked devices whose
callbacks do not require RTNL, this unnecessarily serializes sysfs
readers with rtnetlink users. On CPU-throttled hosts, a periodic reader
such as node-exporter can keep RTNL held for hundreds of milliseconds
while an mlx5 callback runs.
Ops-locked devices can run ethtool operations under the netdev instance
lock. The ethtool netlink and ioctl paths use
ETHTOOL_OP_NEEDS_RTNL_LINKSETTINGS to identify callbacks that still need
RTNL, but the sysfs path currently does not. Apply the same rule to sysfs
reads: call netif_get_link_ksettings() under netdev_lock_ops() when the
callback does not require RTNL, and keep sysfs_rtnl_lock() for legacy
devices and callbacks that opt in to RTNL.
Preserve the existing speed and duplex sysfs ABI, including -EINVAL for
devices that are down or callbacks that fail.
Assisted-by: LLM
Signed-off-by: Wang Zhan <redacted>
---
net/core/net-sysfs.c | 122 +++++++++++++++++++++++++------------------
1 file changed, 71 insertions(+), 51 deletions(-)
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 352173df75785..3e01e7f3cac79 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c@@ -118,6 +118,55 @@ static int sysfs_rtnl_lock(struct kobject *kobj, struct attribute *attr, return ret; } +/* + * Use the per-device ops lock without RTNL when the device supports it. + * Legacy devices and callbacks which explicitly require RTNL retain the + * existing locking. + */ +static int sysfs_get_link_ksettings(struct device *dev, + struct device_attribute *attr, + struct ethtool_link_ksettings *cmd) +{ + struct net_device *netdev = to_net_dev(dev); + int ret = -EINVAL; + bool need_rtnl; + + /* + * The check is also done in netif_get_link_ksettings(); this helps + * returning early without hitting the locking section below. + */ + if (!netdev->ethtool_ops->get_link_ksettings) + return ret; + + need_rtnl = !netdev_need_ops_lock(netdev) || + (netdev->ethtool_ops->op_needs_rtnl & + ETHTOOL_OP_NEEDS_RTNL_LINKSETTINGS); + if (need_rtnl) { + ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); + if (ret) + return ret; + } + netdev_lock_ops(netdev); + + ret = -EINVAL; + if (!dev_isalive(netdev)) { + ret = -ENODEV; + } else if (netif_running(netdev)) { + /* + * Keep the sysfs ABI: report any callback error as -EINVAL + * instead of propagating the driver's error code. + */ + if (!netif_get_link_ksettings(netdev, cmd)) + ret = 0; + } + + netdev_unlock_ops(netdev); + if (need_rtnl) + rtnl_unlock(); + + return ret; +} + /* use same locking rules as GIF* ioctl's */ static ssize_t netdev_show(const struct device *dev, struct device_attribute *attr, char *buf,
@@ -332,27 +381,13 @@ static DEVICE_ATTR_RW(carrier); static ssize_t speed_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct net_device *netdev = to_net_dev(dev); - int ret = -EINVAL; - - /* The check is also done in __ethtool_get_link_ksettings; this helps - * returning early without hitting the locking section below. - */ - if (!netdev->ethtool_ops->get_link_ksettings) - return ret; - - ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); - if (ret) - return ret; + struct ethtool_link_ksettings cmd; + int ret; - ret = -EINVAL; - if (netif_running(netdev)) { - struct ethtool_link_ksettings cmd; + ret = sysfs_get_link_ksettings(dev, attr, &cmd); + if (!ret) + ret = sysfs_emit(buf, fmt_dec, cmd.base.speed); - if (!__ethtool_get_link_ksettings(netdev, &cmd)) - ret = sysfs_emit(buf, fmt_dec, cmd.base.speed); - } - rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(speed);
@@ -360,41 +395,26 @@ static DEVICE_ATTR_RO(speed); static ssize_t duplex_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct net_device *netdev = to_net_dev(dev); - int ret = -EINVAL; - - /* The check is also done in __ethtool_get_link_ksettings; this helps - * returning early without hitting the locking section below. - */ - if (!netdev->ethtool_ops->get_link_ksettings) - return ret; - - ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); - if (ret) - return ret; - - ret = -EINVAL; - if (netif_running(netdev)) { - struct ethtool_link_ksettings cmd; - - if (!__ethtool_get_link_ksettings(netdev, &cmd)) { - const char *duplex; + struct ethtool_link_ksettings cmd; + const char *duplex; + int ret; - switch (cmd.base.duplex) { - case DUPLEX_HALF: - duplex = "half"; - break; - case DUPLEX_FULL: - duplex = "full"; - break; - default: - duplex = "unknown"; - break; - } - ret = sysfs_emit(buf, "%s\n", duplex); + ret = sysfs_get_link_ksettings(dev, attr, &cmd); + if (!ret) { + switch (cmd.base.duplex) { + case DUPLEX_HALF: + duplex = "half"; + break; + case DUPLEX_FULL: + duplex = "full"; + break; + default: + duplex = "unknown"; + break; } + ret = sysfs_emit(buf, "%s\n", duplex); } - rtnl_unlock(); + return ret; } static DEVICE_ATTR_RO(duplex);
base-commit: 1bb784eb6e38fd73143f021608e4ef3095d0c0d7 -- 2.47.3