From 17edde520927070a6bf14a6a75027c0b843443e5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 22 Feb 2009 00:11:09 -0800 Subject: netns: Remove net_alive It turns out that net_alive is unnecessary, and the original problem that led to it being added was simply that the icmp code thought it was a network device and wound up being unable to handle packets while there were still packets in the network namespace. Now that icmp and tcp have been fixed to properly register themselves this problem is no longer present and we have a stronger guarantee that packets will not arrive in a network namespace then that provided by net_alive in netif_receive_skb. So remove net_alive allowing packet reception run a little faster. Additionally document the strong reason why network namespace cleanup is safe so that if something happens again someone else will have a chance of figuring it out. Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- include/net/net_namespace.h | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 6fc13d905c5..ded434b032a 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -109,11 +109,6 @@ extern struct list_head net_namespace_list; #ifdef CONFIG_NET_NS extern void __put_net(struct net *net); -static inline int net_alive(struct net *net) -{ - return net && atomic_read(&net->count); -} - static inline struct net *get_net(struct net *net) { atomic_inc(&net->count); @@ -145,11 +140,6 @@ int net_eq(const struct net *net1, const struct net *net2) } #else -static inline int net_alive(struct net *net) -{ - return 1; -} - static inline struct net *get_net(struct net *net) { return net; @@ -234,6 +224,23 @@ struct pernet_operations { void (*exit)(struct net *net); }; +/* + * Use these carefully. If you implement a network device and it + * needs per network namespace operations use device pernet operations, + * otherwise use pernet subsys operations. + * + * This is critically important. Most of the network code cleanup + * runs with the assumption that dev_remove_pack has been called so no + * new packets will arrive during and after the cleanup functions have + * been called. dev_remove_pack is not per namespace so instead the + * guarantee of no more packets arriving in a network namespace is + * provided by ensuring that all network devices and all sockets have + * left the network namespace before the cleanup methods are called. + * + * For the longest time the ipv4 icmp code was registered as a pernet + * device which caused kernel oops, and panics during network + * namespace cleanup. So please don't get this wrong. + */ extern int register_pernet_subsys(struct pernet_operations *); extern void unregister_pernet_subsys(struct pernet_operations *); extern int register_pernet_gen_subsys(int *id, struct pernet_operations *); -- cgit v1.2.3-70-g09d2 From 9d40bbda599def1e1d155d7f7dca14fe8744bd2b Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 4 Mar 2009 23:46:25 -0800 Subject: vlan: Fix vlan-in-vlan crashes. As analyzed by Patrick McHardy, vlan needs to reset it's netdev_ops pointer in it's ->init() function but this leaves the compat method pointers stale. Add a netdev_resync_ops() and call it from the vlan code. Any other driver which changes ->netdev_ops after register_netdevice() will need to call this new function after doing so too. With help from Patrick McHardy. Tested-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + net/8021q/vlan_dev.c | 3 ++- net/core/dev.c | 56 ++++++++++++++++++++++++++++------------------- 3 files changed, 37 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ec54785d34f..659366734f3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1079,6 +1079,7 @@ extern void synchronize_net(void); extern int register_netdevice_notifier(struct notifier_block *nb); extern int unregister_netdevice_notifier(struct notifier_block *nb); extern int init_dummy_netdev(struct net_device *dev); +extern void netdev_resync_ops(struct net_device *dev); extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev); extern struct net_device *dev_get_by_index(struct net *net, int ifindex); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 4a19acd3a32..1b34135cf99 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -553,7 +553,7 @@ static int vlan_dev_neigh_setup(struct net_device *dev, struct neigh_parms *pa) int err = 0; if (netif_device_present(real_dev) && ops->ndo_neigh_setup) - err = ops->ndo_neigh_setup(dev, pa); + err = ops->ndo_neigh_setup(real_dev, pa); return err; } @@ -639,6 +639,7 @@ static int vlan_dev_init(struct net_device *dev) dev->hard_header_len = real_dev->hard_header_len + VLAN_HLEN; dev->netdev_ops = &vlan_netdev_ops; } + netdev_resync_ops(dev); if (is_vlan_dev(real_dev)) subclass = 1; diff --git a/net/core/dev.c b/net/core/dev.c index 2dd484ed3db..f1129706ce7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4282,6 +4282,39 @@ unsigned long netdev_fix_features(unsigned long features, const char *name) } EXPORT_SYMBOL(netdev_fix_features); +/* Some devices need to (re-)set their netdev_ops inside + * ->init() or similar. If that happens, we have to setup + * the compat pointers again. + */ +void netdev_resync_ops(struct net_device *dev) +{ +#ifdef CONFIG_COMPAT_NET_DEV_OPS + const struct net_device_ops *ops = dev->netdev_ops; + + dev->init = ops->ndo_init; + dev->uninit = ops->ndo_uninit; + dev->open = ops->ndo_open; + dev->change_rx_flags = ops->ndo_change_rx_flags; + dev->set_rx_mode = ops->ndo_set_rx_mode; + dev->set_multicast_list = ops->ndo_set_multicast_list; + dev->set_mac_address = ops->ndo_set_mac_address; + dev->validate_addr = ops->ndo_validate_addr; + dev->do_ioctl = ops->ndo_do_ioctl; + dev->set_config = ops->ndo_set_config; + dev->change_mtu = ops->ndo_change_mtu; + dev->neigh_setup = ops->ndo_neigh_setup; + dev->tx_timeout = ops->ndo_tx_timeout; + dev->get_stats = ops->ndo_get_stats; + dev->vlan_rx_register = ops->ndo_vlan_rx_register; + dev->vlan_rx_add_vid = ops->ndo_vlan_rx_add_vid; + dev->vlan_rx_kill_vid = ops->ndo_vlan_rx_kill_vid; +#ifdef CONFIG_NET_POLL_CONTROLLER + dev->poll_controller = ops->ndo_poll_controller; +#endif +#endif +} +EXPORT_SYMBOL(netdev_resync_ops); + /** * register_netdevice - register a network device * @dev: device to register @@ -4326,28 +4359,7 @@ int register_netdevice(struct net_device *dev) * This is temporary until all network devices are converted. */ if (dev->netdev_ops) { - const struct net_device_ops *ops = dev->netdev_ops; - - dev->init = ops->ndo_init; - dev->uninit = ops->ndo_uninit; - dev->open = ops->ndo_open; - dev->change_rx_flags = ops->ndo_change_rx_flags; - dev->set_rx_mode = ops->ndo_set_rx_mode; - dev->set_multicast_list = ops->ndo_set_multicast_list; - dev->set_mac_address = ops->ndo_set_mac_address; - dev->validate_addr = ops->ndo_validate_addr; - dev->do_ioctl = ops->ndo_do_ioctl; - dev->set_config = ops->ndo_set_config; - dev->change_mtu = ops->ndo_change_mtu; - dev->neigh_setup = ops->ndo_neigh_setup; - dev->tx_timeout = ops->ndo_tx_timeout; - dev->get_stats = ops->ndo_get_stats; - dev->vlan_rx_register = ops->ndo_vlan_rx_register; - dev->vlan_rx_add_vid = ops->ndo_vlan_rx_add_vid; - dev->vlan_rx_kill_vid = ops->ndo_vlan_rx_kill_vid; -#ifdef CONFIG_NET_POLL_CONTROLLER - dev->poll_controller = ops->ndo_poll_controller; -#endif + netdev_resync_ops(dev); } else { char drivername[64]; pr_info("%s (%s): not using net_device_ops yet\n", -- cgit v1.2.3-70-g09d2