diff options
Diffstat (limited to 'net/ipv6/anycast.c')
| -rw-r--r-- | net/ipv6/anycast.c | 279 |
1 files changed, 117 insertions, 162 deletions
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 9c7f83fbc3a..21018324468 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -29,6 +29,7 @@ #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/slab.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -43,96 +44,73 @@ #include <net/checksum.h> -static int ipv6_dev_ac_dec(struct net_device *dev, struct in6_addr *addr); +static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr); /* Big ac list lock for all the sockets */ -static DEFINE_RWLOCK(ipv6_sk_ac_lock); +static DEFINE_SPINLOCK(ipv6_sk_ac_lock); -static int -ip6_onlink(struct in6_addr *addr, struct net_device *dev) -{ - struct inet6_dev *idev; - struct inet6_ifaddr *ifa; - int onlink; - - onlink = 0; - rcu_read_lock(); - idev = __in6_dev_get(dev); - if (idev) { - read_lock_bh(&idev->lock); - for (ifa=idev->addr_list; ifa; ifa=ifa->if_next) { - onlink = ipv6_prefix_equal(addr, &ifa->addr, - ifa->prefix_len); - if (onlink) - break; - } - read_unlock_bh(&idev->lock); - } - rcu_read_unlock(); - return onlink; -} /* * socket join an anycast group */ -int ipv6_sock_ac_join(struct sock *sk, int ifindex, struct in6_addr *addr) +int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); struct net_device *dev = NULL; struct inet6_dev *idev; struct ipv6_ac_socklist *pac; - int ishost = !ipv6_devconf.forwarding; + struct net *net = sock_net(sk); + int ishost = !net->ipv6.devconf_all->forwarding; int err = 0; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (ipv6_addr_is_multicast(addr)) return -EINVAL; - if (ipv6_chk_addr(&init_net, addr, NULL, 0)) + if (ipv6_chk_addr(net, addr, NULL, 0)) return -EINVAL; pac = sock_kmalloc(sk, sizeof(struct ipv6_ac_socklist), GFP_KERNEL); if (pac == NULL) return -ENOMEM; pac->acl_next = NULL; - ipv6_addr_copy(&pac->acl_addr, addr); + pac->acl_addr = *addr; + rcu_read_lock(); if (ifindex == 0) { struct rt6_info *rt; - rt = rt6_lookup(addr, NULL, 0, 0); + rt = rt6_lookup(net, addr, NULL, 0, 0); if (rt) { - dev = rt->rt6i_dev; - dev_hold(dev); - dst_release(&rt->u.dst); + dev = rt->dst.dev; + ip6_rt_put(rt); } else if (ishost) { err = -EADDRNOTAVAIL; - goto out_free_pac; + goto error; } else { /* router, no matching interface: just pick one */ - - dev = dev_get_by_flags(&init_net, IFF_UP, IFF_UP|IFF_LOOPBACK); + dev = dev_get_by_flags_rcu(net, IFF_UP, + IFF_UP | IFF_LOOPBACK); } } else - dev = dev_get_by_index(&init_net, ifindex); + dev = dev_get_by_index_rcu(net, ifindex); if (dev == NULL) { err = -ENODEV; - goto out_free_pac; + goto error; } - idev = in6_dev_get(dev); + idev = __in6_dev_get(dev); if (!idev) { if (ifindex) err = -ENODEV; else err = -EADDRNOTAVAIL; - goto out_dev_put; + goto error; } /* reset ishost, now that we have a specific device */ ishost = !idev->cnf.forwarding; - in6_dev_put(idev); pac->acl_ifindex = dev->ifindex; @@ -141,43 +119,40 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, struct in6_addr *addr) * This obviates the need for propagating anycast routes while * still allowing some non-router anycast participation. */ - if (!ip6_onlink(addr, dev)) { + if (!ipv6_chk_prefix(addr, dev)) { if (ishost) err = -EADDRNOTAVAIL; if (err) - goto out_dev_put; + goto error; } err = ipv6_dev_ac_inc(dev, addr); - if (err) - goto out_dev_put; - - write_lock_bh(&ipv6_sk_ac_lock); - pac->acl_next = np->ipv6_ac_list; - np->ipv6_ac_list = pac; - write_unlock_bh(&ipv6_sk_ac_lock); - - dev_put(dev); - - return 0; + if (!err) { + spin_lock_bh(&ipv6_sk_ac_lock); + pac->acl_next = np->ipv6_ac_list; + np->ipv6_ac_list = pac; + spin_unlock_bh(&ipv6_sk_ac_lock); + pac = NULL; + } -out_dev_put: - dev_put(dev); -out_free_pac: - sock_kfree_s(sk, pac, sizeof(*pac)); +error: + rcu_read_unlock(); + if (pac) + sock_kfree_s(sk, pac, sizeof(*pac)); return err; } /* * socket leave an anycast group */ -int ipv6_sock_ac_drop(struct sock *sk, int ifindex, struct in6_addr *addr) +int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); struct net_device *dev; struct ipv6_ac_socklist *pac, *prev_pac; + struct net *net = sock_net(sk); - write_lock_bh(&ipv6_sk_ac_lock); + spin_lock_bh(&ipv6_sk_ac_lock); prev_pac = NULL; for (pac = np->ipv6_ac_list; pac; pac = pac->acl_next) { if ((ifindex == 0 || pac->acl_ifindex == ifindex) && @@ -186,7 +161,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, struct in6_addr *addr) prev_pac = pac; } if (!pac) { - write_unlock_bh(&ipv6_sk_ac_lock); + spin_unlock_bh(&ipv6_sk_ac_lock); return -ENOENT; } if (prev_pac) @@ -194,13 +169,14 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, struct in6_addr *addr) else np->ipv6_ac_list = pac->acl_next; - write_unlock_bh(&ipv6_sk_ac_lock); + spin_unlock_bh(&ipv6_sk_ac_lock); - dev = dev_get_by_index(&init_net, pac->acl_ifindex); - if (dev) { + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, pac->acl_ifindex); + if (dev) ipv6_dev_ac_dec(dev, &pac->acl_addr); - dev_put(dev); - } + rcu_read_unlock(); + sock_kfree_s(sk, pac, sizeof(*pac)); return 0; } @@ -210,21 +186,24 @@ void ipv6_sock_ac_close(struct sock *sk) struct ipv6_pinfo *np = inet6_sk(sk); struct net_device *dev = NULL; struct ipv6_ac_socklist *pac; + struct net *net = sock_net(sk); int prev_index; - write_lock_bh(&ipv6_sk_ac_lock); + if (!np->ipv6_ac_list) + return; + + spin_lock_bh(&ipv6_sk_ac_lock); pac = np->ipv6_ac_list; np->ipv6_ac_list = NULL; - write_unlock_bh(&ipv6_sk_ac_lock); + spin_unlock_bh(&ipv6_sk_ac_lock); prev_index = 0; + rcu_read_lock(); while (pac) { struct ipv6_ac_socklist *next = pac->acl_next; if (pac->acl_ifindex != prev_index) { - if (dev) - dev_put(dev); - dev = dev_get_by_index(&init_net, pac->acl_ifindex); + dev = dev_get_by_index_rcu(net, pac->acl_ifindex); prev_index = pac->acl_ifindex; } if (dev) @@ -232,44 +211,14 @@ void ipv6_sock_ac_close(struct sock *sk) sock_kfree_s(sk, pac, sizeof(*pac)); pac = next; } - if (dev) - dev_put(dev); -} - -#if 0 -/* The function is not used, which is funny. Apparently, author - * supposed to use it to filter out datagrams inside udp/raw but forgot. - * - * It is OK, anycasts are not special comparing to delivery to unicasts. - */ - -int inet6_ac_check(struct sock *sk, struct in6_addr *addr, int ifindex) -{ - struct ipv6_ac_socklist *pac; - struct ipv6_pinfo *np = inet6_sk(sk); - int found; - - found = 0; - read_lock(&ipv6_sk_ac_lock); - for (pac=np->ipv6_ac_list; pac; pac=pac->acl_next) { - if (ifindex && pac->acl_ifindex != ifindex) - continue; - found = ipv6_addr_equal(&pac->acl_addr, addr); - if (found) - break; - } - read_unlock(&ipv6_sk_ac_lock); - - return found; + rcu_read_unlock(); } -#endif - static void aca_put(struct ifacaddr6 *ac) { if (atomic_dec_and_test(&ac->aca_refcnt)) { in6_dev_put(ac->aca_idev); - dst_release(&ac->aca_rt->u.dst); + dst_release(&ac->aca_rt->dst); kfree(ac); } } @@ -277,7 +226,7 @@ static void aca_put(struct ifacaddr6 *ac) /* * device anycast group inc (add if not found) */ -int ipv6_dev_ac_inc(struct net_device *dev, struct in6_addr *addr) +int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr) { struct ifacaddr6 *aca; struct inet6_dev *idev; @@ -314,14 +263,14 @@ int ipv6_dev_ac_inc(struct net_device *dev, struct in6_addr *addr) goto out; } - rt = addrconf_dst_alloc(idev, addr, 1); + rt = addrconf_dst_alloc(idev, addr, true); if (IS_ERR(rt)) { kfree(aca); err = PTR_ERR(rt); goto out; } - ipv6_addr_copy(&aca->aca_addr, addr); + aca->aca_addr = *addr; aca->aca_idev = idev; aca->aca_rt = rt; aca->aca_users = 1; @@ -334,9 +283,7 @@ int ipv6_dev_ac_inc(struct net_device *dev, struct in6_addr *addr) idev->ac_list = aca; write_unlock_bh(&idev->lock); - dst_hold(&rt->u.dst); - if (ip6_ins_rt(rt)) - dst_release(&rt->u.dst); + ip6_ins_rt(rt); addrconf_join_solict(dev, &aca->aca_addr); @@ -351,7 +298,7 @@ out: /* * device anycast group decrement */ -int __ipv6_dev_ac_dec(struct inet6_dev *idev, struct in6_addr *addr) +int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifacaddr6 *aca, *prev_aca; @@ -377,70 +324,80 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, struct in6_addr *addr) write_unlock_bh(&idev->lock); addrconf_leave_solict(idev, &aca->aca_addr); - dst_hold(&aca->aca_rt->u.dst); - if (ip6_del_rt(aca->aca_rt)) - dst_free(&aca->aca_rt->u.dst); - else - dst_release(&aca->aca_rt->u.dst); + dst_hold(&aca->aca_rt->dst); + ip6_del_rt(aca->aca_rt); aca_put(aca); return 0; } -static int ipv6_dev_ac_dec(struct net_device *dev, struct in6_addr *addr) +/* called with rcu_read_lock() */ +static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr) { - int ret; - struct inet6_dev *idev = in6_dev_get(dev); + struct inet6_dev *idev = __in6_dev_get(dev); + if (idev == NULL) return -ENODEV; - ret = __ipv6_dev_ac_dec(idev, addr); - in6_dev_put(idev); - return ret; + return __ipv6_dev_ac_dec(idev, addr); } /* * check if the interface has this anycast address + * called with rcu_read_lock() */ -static int ipv6_chk_acast_dev(struct net_device *dev, struct in6_addr *addr) +static bool ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *addr) { struct inet6_dev *idev; struct ifacaddr6 *aca; - idev = in6_dev_get(dev); + idev = __in6_dev_get(dev); if (idev) { read_lock_bh(&idev->lock); for (aca = idev->ac_list; aca; aca = aca->aca_next) if (ipv6_addr_equal(&aca->aca_addr, addr)) break; read_unlock_bh(&idev->lock); - in6_dev_put(idev); return aca != NULL; } - return 0; + return false; } /* * check if given interface (or any, if dev==0) has this anycast address */ -int ipv6_chk_acast_addr(struct net_device *dev, struct in6_addr *addr) +bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, + const struct in6_addr *addr) { - int found = 0; + bool found = false; + rcu_read_lock(); if (dev) - return ipv6_chk_acast_dev(dev, addr); - read_lock(&dev_base_lock); - for_each_netdev(&init_net, dev) - if (ipv6_chk_acast_dev(dev, addr)) { - found = 1; - break; - } - read_unlock(&dev_base_lock); + found = ipv6_chk_acast_dev(dev, addr); + else + for_each_netdev_rcu(net, dev) + if (ipv6_chk_acast_dev(dev, addr)) { + found = true; + break; + } + rcu_read_unlock(); return found; } +/* check if this anycast address is link-local on given interface or + * is global + */ +bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev, + const struct in6_addr *addr) +{ + return ipv6_chk_acast_addr(net, + (ipv6_addr_type(addr) & IPV6_ADDR_LINKLOCAL ? + dev : NULL), + addr); +} #ifdef CONFIG_PROC_FS struct ac6_iter_state { + struct seq_net_private p; struct net_device *dev; struct inet6_dev *idev; }; @@ -451,11 +408,12 @@ static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq) { struct ifacaddr6 *im = NULL; struct ac6_iter_state *state = ac6_seq_private(seq); + struct net *net = seq_file_net(seq); state->idev = NULL; - for_each_netdev(&init_net, state->dev) { + for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; - idev = in6_dev_get(state->dev); + idev = __in6_dev_get(state->dev); if (!idev) continue; read_lock_bh(&idev->lock); @@ -465,7 +423,6 @@ static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq) break; } read_unlock_bh(&idev->lock); - in6_dev_put(idev); } return im; } @@ -476,16 +433,15 @@ static struct ifacaddr6 *ac6_get_next(struct seq_file *seq, struct ifacaddr6 *im im = im->aca_next; while (!im) { - if (likely(state->idev != NULL)) { + if (likely(state->idev != NULL)) read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); - } - state->dev = next_net_device(state->dev); + + state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; break; } - state->idev = in6_dev_get(state->dev); + state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; read_lock_bh(&state->idev->lock); @@ -504,29 +460,30 @@ static struct ifacaddr6 *ac6_get_idx(struct seq_file *seq, loff_t pos) } static void *ac6_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(dev_base_lock) + __acquires(RCU) { - read_lock(&dev_base_lock); + rcu_read_lock(); return ac6_get_idx(seq, *pos); } static void *ac6_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct ifacaddr6 *im; - im = ac6_get_next(seq, v); + struct ifacaddr6 *im = ac6_get_next(seq, v); + ++*pos; return im; } static void ac6_seq_stop(struct seq_file *seq, void *v) - __releases(dev_base_lock) + __releases(RCU) { struct ac6_iter_state *state = ac6_seq_private(seq); + if (likely(state->idev != NULL)) { read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); + state->idev = NULL; } - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int ac6_seq_show(struct seq_file *seq, void *v) @@ -534,11 +491,9 @@ static int ac6_seq_show(struct seq_file *seq, void *v) struct ifacaddr6 *im = (struct ifacaddr6 *)v; struct ac6_iter_state *state = ac6_seq_private(seq); - seq_printf(seq, - "%-4d %-15s " NIP6_SEQFMT " %5d\n", + seq_printf(seq, "%-4d %-15s %pi6 %5d\n", state->dev->ifindex, state->dev->name, - NIP6(im->aca_addr), - im->aca_users); + &im->aca_addr, im->aca_users); return 0; } @@ -551,8 +506,8 @@ static const struct seq_operations ac6_seq_ops = { static int ac6_seq_open(struct inode *inode, struct file *file) { - return seq_open_private(file, &ac6_seq_ops, - sizeof(struct ac6_iter_state)); + return seq_open_net(inode, file, &ac6_seq_ops, + sizeof(struct ac6_iter_state)); } static const struct file_operations ac6_seq_fops = { @@ -560,20 +515,20 @@ static const struct file_operations ac6_seq_fops = { .open = ac6_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = seq_release_net, }; -int __init ac6_proc_init(void) +int __net_init ac6_proc_init(struct net *net) { - if (!proc_net_fops_create(&init_net, "anycast6", S_IRUGO, &ac6_seq_fops)) + if (!proc_create("anycast6", S_IRUGO, net->proc_net, &ac6_seq_fops)) return -ENOMEM; return 0; } -void ac6_proc_exit(void) +void ac6_proc_exit(struct net *net) { - proc_net_remove(&init_net, "anycast6"); + remove_proc_entry("anycast6", net->proc_net); } #endif |
