@@ -196,6 +196,12 @@ static ssize_t speed_show(struct device *dev,
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 trylock/restart below.
+ */
+ if (!netdev->ethtool_ops->get_link_ksettings)
+ return -EOPNOTSUPP;
+
if (!rtnl_trylock())
return restart_syscall();
@@ -216,6 +222,12 @@ static ssize_t duplex_show(struct device *dev,
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 trylock/restart below.
+ */
+ if (!netdev->ethtool_ops->get_link_ksettings)
+ return -EOPNOTSUPP;
+
if (!rtnl_trylock())
return restart_syscall();
@@ -478,6 +490,12 @@ static ssize_t phys_port_id_show(struct device *dev,
struct net_device *netdev = to_net_dev(dev);
ssize_t ret = -EINVAL;
+ /* The check is also done in dev_get_phys_port_id; this helps returning
+ * early without hitting the trylock/restart below.
+ */
+ if (!netdev->netdev_ops->ndo_get_phys_port_id)
+ return -EOPNOTSUPP;
+
if (!rtnl_trylock())
return restart_syscall();
@@ -500,6 +518,13 @@ static ssize_t phys_port_name_show(struct device *dev,
struct net_device *netdev = to_net_dev(dev);
ssize_t ret = -EINVAL;
+ /* The checks are also done in dev_get_phys_port_name; this helps
+ * returning early without hitting the trylock/restart below.
+ */
+ if (!netdev->netdev_ops->ndo_get_phys_port_name &&
+ !netdev->netdev_ops->ndo_get_devlink_port)
+ return -EOPNOTSUPP;
+
if (!rtnl_trylock())
return restart_syscall();
@@ -522,6 +547,13 @@ static ssize_t phys_switch_id_show(struct device *dev,
struct net_device *netdev = to_net_dev(dev);
ssize_t ret = -EINVAL;
+ /* The checks are also done in dev_get_phys_port_name; this helps
+ * returning early without hitting the trylock/restart below.
+ */
+ if (!netdev->netdev_ops->ndo_get_port_parent_id &&
+ !netdev->netdev_ops->ndo_get_devlink_port)
+ return -EOPNOTSUPP;
+
if (!rtnl_trylock())
return restart_syscall();
@@ -1226,6 +1258,12 @@ static ssize_t tx_maxrate_store(struct netdev_queue *queue,
if (!capable(CAP_NET_ADMIN))
return -EPERM;
+ /* The check is also done later; this helps returning early without
+ * hitting the trylock/restart below.
+ */
+ if (!dev->netdev_ops->ndo_set_tx_maxrate)
+ return -EOPNOTSUPP;
+
err = kstrtou32(buf, 10, &rate);
if (err < 0)
return err;
Due to deadlocks in the networking subsystem spotted 12 years ago[1], a workaround was put in place[2] to avoid taking the rtnl lock when it was not available and restarting the syscall (back to VFS, letting userspace spin). The following construction is found a lot in the net sysfs and sysctl code: if (!rtnl_trylock()) return restart_syscall(); This can be problematic when multiple userspace threads use such interfaces in a short period, making them to spin a lot. This happens for example when adding and moving virtual interfaces: userspace programs listening on events, such as systemd-udevd and NetworkManager, do trigger actions reading files in sysfs. It gets worse when a lot of virtual interfaces are created concurrently, say when creating containers at boot time. Returning early without hitting the above pattern when the syscall will fail eventually does make things better. While it is not a fix for the issue, it does ease things. [1] https://lore.kernel.org/netdev/49A4D5D5.5090602@trash.net/ https://lore.kernel.org/netdev/m14oyhis31.fsf@fess.ebiederm.org/ and https://lore.kernel.org/netdev/20090226084924.16cb3e08@nehalam/ [2] Rightfully, those deadlocks are *hard* to solve. Signed-off-by: Antoine Tenart <atenart@kernel.org> --- net/core/net-sysfs.c | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+)