X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fipv4%2Ffib_frontend.c;h=82dbf711d6d0ef2a704e6a636131242f379011c8;hb=d696c7bdaa55e2208e56c6f98e6bc1599f34286d;hp=e787d215115217492ab31bda0ee7df2010bfe82e;hpb=b7c6ba6eb1234e35a74fb8ba8123232a7b1ba9e4;p=safe%2Fjmp%2Flinux-2.6 diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index e787d21..82dbf71 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -5,8 +5,6 @@ * * IPv4 Forwarding Information Base: FIB frontend. * - * Version: $Id: fib_frontend.c,v 1.26 2001/10/31 21:55:54 davem Exp $ - * * Authors: Alexey Kuznetsov, * * This program is free software; you can redistribute it and/or @@ -42,7 +40,6 @@ #include #include #include -#include #include #include #include @@ -116,6 +113,21 @@ struct fib_table *fib_get_table(struct net *net, u32 id) } #endif /* CONFIG_IP_MULTIPLE_TABLES */ +void fib_select_default(struct net *net, + const struct flowi *flp, struct fib_result *res) +{ + struct fib_table *tb; + int table = RT_TABLE_MAIN; +#ifdef CONFIG_IP_MULTIPLE_TABLES + if (res->r == NULL || res->r->action != FR_ACT_TO_TBL) + return; + table = res->r->table; +#endif + tb = fib_get_table(net, table); + if (FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) + fib_table_select_default(tb, flp, res); +} + static void fib_flush(struct net *net) { int flushed = 0; @@ -127,18 +139,18 @@ static void fib_flush(struct net *net) for (h = 0; h < FIB_TABLE_HASHSZ; h++) { head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry(tb, node, head, tb_hlist) - flushed += tb->tb_flush(tb); + flushed += fib_table_flush(tb); } if (flushed) - rt_cache_flush(-1); + rt_cache_flush(net, -1); } /* * Find the first device with a given source address. */ -struct net_device * ip_dev_find(__be32 addr) +struct net_device * ip_dev_find(struct net *net, __be32 addr) { struct flowi fl = { .nl_u = { .ip4_u = { .daddr = addr } } }; struct fib_result res; @@ -149,8 +161,8 @@ struct net_device * ip_dev_find(__be32 addr) res.r = NULL; #endif - local_table = fib_get_table(&init_net, RT_TABLE_LOCAL); - if (!local_table || local_table->tb_lookup(local_table, &fl, &res)) + local_table = fib_get_table(net, RT_TABLE_LOCAL); + if (!local_table || fib_table_lookup(local_table, &fl, &res)) return NULL; if (res.type != RTN_LOCAL) goto out; @@ -176,7 +188,7 @@ static inline unsigned __inet_dev_addr_type(struct net *net, unsigned ret = RTN_BROADCAST; struct fib_table *local_table; - if (ipv4_is_zeronet(addr) || ipv4_is_badclass(addr)) + if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) return RTN_BROADCAST; if (ipv4_is_multicast(addr)) return RTN_MULTICAST; @@ -188,7 +200,7 @@ static inline unsigned __inet_dev_addr_type(struct net *net, local_table = fib_get_table(net, RT_TABLE_LOCAL); if (local_table) { ret = RTN_UNICAST; - if (!local_table->tb_lookup(local_table, &fl, &res)) { + if (!fib_table_lookup(local_table, &fl, &res)) { if (!dev || dev == res.fi->fib_dev) ret = res.type; fib_res_put(&res); @@ -217,34 +229,44 @@ unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, */ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, - struct net_device *dev, __be32 *spec_dst, u32 *itag) + struct net_device *dev, __be32 *spec_dst, + u32 *itag, u32 mark) { struct in_device *in_dev; struct flowi fl = { .nl_u = { .ip4_u = { .daddr = src, .saddr = dst, .tos = tos } }, + .mark = mark, .iif = oif }; + struct fib_result res; - int no_addr, rpf; + int no_addr, rpf, accept_local; int ret; + struct net *net; - no_addr = rpf = 0; + no_addr = rpf = accept_local = 0; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) { no_addr = in_dev->ifa_list == NULL; rpf = IN_DEV_RPFILTER(in_dev); + accept_local = IN_DEV_ACCEPT_LOCAL(in_dev); + if (mark && !IN_DEV_SRC_VMARK(in_dev)) + fl.mark = 0; } rcu_read_unlock(); if (in_dev == NULL) goto e_inval; - if (fib_lookup(&fl, &res)) + net = dev_net(dev); + if (fib_lookup(net, &fl, &res)) goto last_resort; - if (res.type != RTN_UNICAST) - goto e_inval_res; + if (res.type != RTN_UNICAST) { + if (res.type != RTN_LOCAL || !accept_local) + goto e_inval_res; + } *spec_dst = FIB_RES_PREFSRC(res); fib_combine_itag(itag, &res); #ifdef CONFIG_IP_ROUTE_MULTIPATH @@ -260,12 +282,12 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, fib_res_put(&res); if (no_addr) goto last_resort; - if (rpf) + if (rpf == 1) goto e_inval; fl.oif = dev->ifindex; ret = 0; - if (fib_lookup(&fl, &res) == 0) { + if (fib_lookup(net, &fl, &res) == 0) { if (res.type == RTN_UNICAST) { *spec_dst = FIB_RES_PREFSRC(res); ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST; @@ -459,13 +481,13 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (cmd == SIOCDELRT) { tb = fib_get_table(net, cfg.fc_table); if (tb) - err = tb->tb_delete(tb, &cfg); + err = fib_table_delete(tb, &cfg); else err = -ESRCH; } else { tb = fib_new_table(net, cfg.fc_table); if (tb) - err = tb->tb_insert(tb, &cfg); + err = fib_table_insert(tb, &cfg); else err = -ENOBUFS; } @@ -489,7 +511,6 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX+1] = { [RTA_PREFSRC] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, - [RTA_PROTOINFO] = { .type = NLA_U32 }, [RTA_FLOW] = { .type = NLA_U32 }, }; @@ -564,9 +585,9 @@ errout: return err; } -static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct fib_config cfg; struct fib_table *tb; int err; @@ -581,14 +602,14 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *ar goto errout; } - err = tb->tb_delete(tb, &cfg); + err = fib_table_delete(tb, &cfg); errout: return err; } -static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct fib_config cfg; struct fib_table *tb; int err; @@ -603,14 +624,14 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *ar goto errout; } - err = tb->tb_insert(tb, &cfg); + err = fib_table_insert(tb, &cfg); errout: return err; } static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); unsigned int h, s_h; unsigned int e = 0, s_e; struct fib_table *tb; @@ -634,7 +655,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (dumped) memset(&cb->args[2], 0, sizeof(cb->args) - 2 * sizeof(cb->args[0])); - if (tb->tb_dump(tb, skb, cb) < 0) + if (fib_table_dump(tb, skb, cb) < 0) goto out; dumped = 1; next: @@ -657,7 +678,7 @@ out: static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa) { - struct net *net = ifa->ifa_dev->dev->nd_net; + struct net *net = dev_net(ifa->ifa_dev->dev); struct fib_table *tb; struct fib_config cfg = { .fc_protocol = RTPROT_KERNEL, @@ -688,9 +709,9 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad cfg.fc_scope = RT_SCOPE_HOST; if (cmd == RTM_NEWROUTE) - tb->tb_insert(tb, &cfg); + fib_table_insert(tb, &cfg); else - tb->tb_delete(tb, &cfg); + fib_table_delete(tb, &cfg); } void fib_add_ifaddr(struct in_ifaddr *ifa) @@ -784,15 +805,15 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim); /* Check, that this local address finally disappeared. */ - if (inet_addr_type(dev->nd_net, ifa->ifa_local) != RTN_LOCAL) { + if (inet_addr_type(dev_net(dev), ifa->ifa_local) != RTN_LOCAL) { /* And the last, but not the least thing. We must flush stray FIB entries. First of all, we scan fib_info list searching for stray nexthop entries, then ignite fib_flush. */ - if (fib_sync_down(ifa->ifa_local, NULL, 0)) - fib_flush(dev->nd_net); + if (fib_sync_down_addr(dev_net(dev), ifa->ifa_local)) + fib_flush(dev_net(dev)); } } #undef LOCAL_OK @@ -819,7 +840,7 @@ static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb ) local_bh_disable(); frn->tb_id = tb->tb_id; - frn->err = tb->tb_lookup(tb, &fl, &res); + frn->err = fib_table_lookup(tb, &fl, &res); if (!frn->err) { frn->prefixlen = res.prefixlen; @@ -840,7 +861,7 @@ static void nl_fib_input(struct sk_buff *skb) struct fib_table *tb; u32 pid; - net = skb->sk->sk_net; + net = sock_net(skb->sk); nlh = nlmsg_hdr(skb); if (skb->len < NLMSG_SPACE(0) || skb->len < nlh->nlmsg_len || nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*frn))) @@ -869,40 +890,36 @@ static int nl_fib_lookup_init(struct net *net) nl_fib_input, NULL, THIS_MODULE); if (sk == NULL) return -EAFNOSUPPORT; - /* Don't hold an extra reference on the namespace */ - put_net(sk->sk_net); net->ipv4.fibnl = sk; return 0; } static void nl_fib_lookup_exit(struct net *net) { - /* At the last minute lie and say this is a socket for the - * initial network namespace. So the socket will be safe to free. - */ - net->ipv4.fibnl->sk_net = get_net(&init_net); netlink_kernel_release(net->ipv4.fibnl); + net->ipv4.fibnl = NULL; } -static void fib_disable_ip(struct net_device *dev, int force) +static void fib_disable_ip(struct net_device *dev, int force, int delay) { - if (fib_sync_down(0, dev, force)) - fib_flush(dev->nd_net); - rt_cache_flush(0); + if (fib_sync_down_dev(dev, force)) + fib_flush(dev_net(dev)); + rt_cache_flush(dev_net(dev), delay); arp_ifdown(dev); } static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct in_ifaddr *ifa = (struct in_ifaddr*)ptr; + struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; + struct net_device *dev = ifa->ifa_dev->dev; switch (event) { case NETDEV_UP: fib_add_ifaddr(ifa); #ifdef CONFIG_IP_ROUTE_MULTIPATH - fib_sync_up(ifa->ifa_dev->dev); + fib_sync_up(dev); #endif - rt_cache_flush(-1); + rt_cache_flush(dev_net(dev), -1); break; case NETDEV_DOWN: fib_del_ifaddr(ifa); @@ -910,9 +927,9 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, /* Last address was deleted from this interface. Disable IP. */ - fib_disable_ip(ifa->ifa_dev->dev, 1); + fib_disable_ip(dev, 1, 0); } else { - rt_cache_flush(-1); + rt_cache_flush(dev_net(dev), -1); } break; } @@ -925,7 +942,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo struct in_device *in_dev = __in_dev_get_rtnl(dev); if (event == NETDEV_UNREGISTER) { - fib_disable_ip(dev, 2); + fib_disable_ip(dev, 2, -1); return NOTIFY_DONE; } @@ -940,29 +957,33 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo #ifdef CONFIG_IP_ROUTE_MULTIPATH fib_sync_up(dev); #endif - rt_cache_flush(-1); + rt_cache_flush(dev_net(dev), -1); break; case NETDEV_DOWN: - fib_disable_ip(dev, 0); + fib_disable_ip(dev, 0, 0); break; case NETDEV_CHANGEMTU: case NETDEV_CHANGE: - rt_cache_flush(0); + rt_cache_flush(dev_net(dev), 0); + break; + case NETDEV_UNREGISTER_BATCH: + rt_cache_flush_batch(); break; } return NOTIFY_DONE; } static struct notifier_block fib_inetaddr_notifier = { - .notifier_call =fib_inetaddr_event, + .notifier_call = fib_inetaddr_event, }; static struct notifier_block fib_netdev_notifier = { - .notifier_call =fib_netdev_event, + .notifier_call = fib_netdev_event, }; static int __net_init ip_fib_net_init(struct net *net) { + int err; unsigned int i; net->ipv4.fib_table_hash = kzalloc( @@ -973,7 +994,14 @@ static int __net_init ip_fib_net_init(struct net *net) for (i = 0; i < FIB_TABLE_HASHSZ; i++) INIT_HLIST_HEAD(&net->ipv4.fib_table_hash[i]); - return fib4_rules_init(net); + err = fib4_rules_init(net); + if (err < 0) + goto fail; + return 0; + +fail: + kfree(net->ipv4.fib_table_hash); + return err; } static void __net_exit ip_fib_net_exit(struct net *net) @@ -992,7 +1020,7 @@ static void __net_exit ip_fib_net_exit(struct net *net) head = &net->ipv4.fib_table_hash[i]; hlist_for_each_entry_safe(tb, node, tmp, head, tb_hlist) { hlist_del(node); - tb->tb_flush(tb); + fib_table_flush(tb); kfree(tb); } }