return READ_ONCE(dev->reg_state) <= NETREG_REGISTERED;
}
+/* There is a possible ABBA deadlock between rtnl_lock and kernfs_node->active,
+ * when unregistering a net device and accessing associated sysfs files. The
+ * potential deadlock is as follow:
+ *
+ * CPU 0 CPU 1
+ *
+ * rtnl_lock vfs_read
+ * unregister_netdevice_many kernfs_seq_start
+ * device_del / kobject_put kernfs_get_active (kn->active++)
+ * kernfs_drain sysfs_kf_seq_show
+ * wait_event( rtnl_lock
+ * kn->active == KN_DEACTIVATED_BIAS) -> waits on CPU 0 to release
+ * -> waits on CPU 1 to decrease kn->active the rtnl lock.
+ *
+ * The historical fix was to use rtnl_trylock with restart_syscall to bail out
+ * of sysfs operations when the lock couldn't be taken. This fixed the above
+ * issue as it allowed CPU 1 to bail out of the ABBA situation.
+ *
+ * But it came with performances issues, as syscalls are being restarted in
+ * loops when there was contention on the rtnl lock, with huge slow downs in
+ * specific scenarios (e.g. lots of virtual interfaces created and userspace
+ * daemons querying their attributes).
+ *
+ * The idea below is to bail out of the active kernfs_node protection
+ * (kn->active) while trying to take the rtnl lock.
+ *
+ * This replaces rtnl_lock() and still has to be used with rtnl_unlock(). The
+ * net device is guaranteed to be alive if this returns successfully.
+ */
+static int sysfs_rtnl_lock(struct kobject *kobj, struct attribute *attr,
+ struct net_device *ndev)
+{
+ struct kernfs_node *kn;
+ int ret = 0;
+
+ /* First, we hold a reference to the net device as the unregistration
+ * path might run in parallel. This will ensure the net device and the
+ * associated sysfs objects won't be freed while we try to take the rtnl
+ * lock.
+ */
+ dev_hold(ndev);
+ /* sysfs_break_active_protection was introduced to allow self-removal of
+ * devices and their associated sysfs files by bailing out of the
+ * sysfs/kernfs protection. We do this here to allow the unregistration
+ * path to complete in parallel. The following takes a reference on the
+ * kobject and the kernfs_node being accessed.
+ *
+ * This works because we hold a reference onto the net device and the
+ * unregistration path will wait for us eventually in netdev_run_todo
+ * (outside an rtnl lock section).
+ */
+ kn = sysfs_break_active_protection(kobj, attr);
+ /* We can now try to take the rtnl lock. This can't deadlock us as the
+ * unregistration path is able to drain sysfs files (kernfs_node) thanks
+ * to the above dance.
+ */
+ if (rtnl_lock_interruptible()) {
+ ret = -ERESTARTSYS;
+ goto unbreak;
+ }
+ /* Check dismantle on the device hasn't started, otherwise deny the
+ * operation.
+ */
+ if (!dev_isalive(ndev)) {
+ rtnl_unlock();
+ ret = -ENODEV;
+ goto unbreak;
+ }
+ /* We are now sure the device dismantle hasn't started nor that it can
+ * start before we exit the locking section as we hold the rtnl lock.
+ * There's no need to keep unbreaking the sysfs protection nor to hold
+ * a net device reference from that point; that was only needed to take
+ * the rtnl lock.
+ */
+unbreak:
+ sysfs_unbreak_active_protection(kn);
+ dev_put(ndev);
+
+ 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,
if (ret)
goto err;
- if (!rtnl_trylock())
- return restart_syscall();
+ ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+ if (ret)
+ goto err;
+
+ ret = (*set)(netdev, new);
+ if (ret == 0)
+ ret = len;
- if (dev_isalive(netdev)) {
- ret = (*set)(netdev, new);
- if (ret == 0)
- ret = len;
- }
rtnl_unlock();
err:
return ret;
struct net_device *netdev = to_net_dev(dev);
/* The check is also done in change_carrier; this helps returning early
- * without hitting the trylock/restart in netdev_store.
+ * without hitting the locking section in netdev_store.
*/
if (!netdev->netdev_ops->ndo_change_carrier)
return -EOPNOTSUPP;
struct net_device *netdev = to_net_dev(dev);
int ret = -EINVAL;
- if (!rtnl_trylock())
- return restart_syscall();
+ ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+ if (ret)
+ return ret;
if (netif_running(netdev)) {
/* Synchronize carrier state with link watch,
ret = sysfs_emit(buf, fmt_dec, !!netif_carrier_ok(netdev));
}
- rtnl_unlock();
+ rtnl_unlock();
return ret;
}
static DEVICE_ATTR_RW(carrier);
int ret = -EINVAL;
/* The check is also done in __ethtool_get_link_ksettings; this helps
- * returning early without hitting the trylock/restart below.
+ * returning early without hitting the locking section below.
*/
if (!netdev->ethtool_ops->get_link_ksettings)
return ret;
- if (!rtnl_trylock())
- return restart_syscall();
+ ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+ if (ret)
+ return ret;
if (netif_running(netdev)) {
struct ethtool_link_ksettings cmd;
int ret = -EINVAL;
/* The check is also done in __ethtool_get_link_ksettings; this helps
- * returning early without hitting the trylock/restart below.
+ * returning early without hitting the locking section below.
*/
if (!netdev->ethtool_ops->get_link_ksettings)
return ret;
- if (!rtnl_trylock())
- return restart_syscall();
+ ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+ if (ret)
+ return ret;
if (netif_running(netdev)) {
struct ethtool_link_ksettings cmd;
if (len > 0 && buf[len - 1] == '\n')
--count;
- if (!rtnl_trylock())
- return restart_syscall();
+ ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+ if (ret)
+ return ret;
- if (dev_isalive(netdev)) {
- ret = dev_set_alias(netdev, buf, count);
- if (ret < 0)
- goto err;
- ret = len;
- netdev_state_change(netdev);
- }
+ ret = dev_set_alias(netdev, buf, count);
+ if (ret < 0)
+ goto err;
+ ret = len;
+ netdev_state_change(netdev);
err:
rtnl_unlock();
struct device_attribute *attr, char *buf)
{
struct net_device *netdev = to_net_dev(dev);
+ struct netdev_phys_item_id ppid;
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.
+ * early without hitting the locking section below.
*/
if (!netdev->netdev_ops->ndo_get_phys_port_id)
return -EOPNOTSUPP;
- if (!rtnl_trylock())
- return restart_syscall();
+ ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+ if (ret)
+ return ret;
- if (dev_isalive(netdev)) {
- struct netdev_phys_item_id ppid;
+ ret = dev_get_phys_port_id(netdev, &ppid);
+ if (!ret)
+ ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id);
- ret = dev_get_phys_port_id(netdev, &ppid);
- if (!ret)
- ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id);
- }
rtnl_unlock();
return ret;
{
struct net_device *netdev = to_net_dev(dev);
ssize_t ret = -EINVAL;
+ char name[IFNAMSIZ];
/* The checks are also done in dev_get_phys_port_name; this helps
- * returning early without hitting the trylock/restart below.
+ * returning early without hitting the locking section below.
*/
if (!netdev->netdev_ops->ndo_get_phys_port_name &&
!netdev->devlink_port)
return -EOPNOTSUPP;
- if (!rtnl_trylock())
- return restart_syscall();
+ ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+ if (ret)
+ return ret;
- if (dev_isalive(netdev)) {
- char name[IFNAMSIZ];
+ ret = dev_get_phys_port_name(netdev, name, sizeof(name));
+ if (!ret)
+ ret = sysfs_emit(buf, "%s\n", name);
- ret = dev_get_phys_port_name(netdev, name, sizeof(name));
- if (!ret)
- ret = sysfs_emit(buf, "%s\n", name);
- }
rtnl_unlock();
return ret;
struct device_attribute *attr, char *buf)
{
struct net_device *netdev = to_net_dev(dev);
+ struct netdev_phys_item_id ppid = { };
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. This works
+ * returning early without hitting the locking section below. This works
* because recurse is false when calling dev_get_port_parent_id.
*/
if (!netdev->netdev_ops->ndo_get_port_parent_id &&
!netdev->devlink_port)
return -EOPNOTSUPP;
- if (!rtnl_trylock())
- return restart_syscall();
+ ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+ if (ret)
+ return ret;
- if (dev_isalive(netdev)) {
- struct netdev_phys_item_id ppid = { };
+ ret = dev_get_port_parent_id(netdev, &ppid, false);
+ if (!ret)
+ ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id);
- ret = dev_get_port_parent_id(netdev, &ppid, false);
- if (!ret)
- ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id);
- }
rtnl_unlock();
return ret;
projects / linux-block.git / commitdiff