diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2008-01-29 22:54:01 +1100 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2008-01-29 22:54:01 +1100 |
commit | 0ba6c33bcddc64a54b5f1c25a696c4767dc76292 (patch) | |
tree | 62e616f97a4762d8e75bf732e4827af2d15d52c5 /net/ipv4/fib_frontend.c | |
parent | 21af0297c7e56024a5ccc4d8ad2a590f9ec371ba (diff) | |
parent | 85040bcb4643cba578839e953f25e2d1965d83d0 (diff) | |
download | op-kernel-dev-0ba6c33bcddc64a54b5f1c25a696c4767dc76292.zip op-kernel-dev-0ba6c33bcddc64a54b5f1c25a696c4767dc76292.tar.gz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6.25
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6.25: (1470 commits)
[IPV6] ADDRLABEL: Fix double free on label deletion.
[PPP]: Sparse warning fixes.
[IPV4] fib_trie: remove unneeded NULL check
[IPV4] fib_trie: More whitespace cleanup.
[NET_SCHED]: Use nla_policy for attribute validation in ematches
[NET_SCHED]: Use nla_policy for attribute validation in actions
[NET_SCHED]: Use nla_policy for attribute validation in classifiers
[NET_SCHED]: Use nla_policy for attribute validation in packet schedulers
[NET_SCHED]: sch_api: introduce constant for rate table size
[NET_SCHED]: Use typeful attribute parsing helpers
[NET_SCHED]: Use typeful attribute construction helpers
[NET_SCHED]: Use NLA_PUT_STRING for string dumping
[NET_SCHED]: Use nla_nest_start/nla_nest_end
[NET_SCHED]: Propagate nla_parse return value
[NET_SCHED]: act_api: use PTR_ERR in tcf_action_init/tcf_action_get
[NET_SCHED]: act_api: use nlmsg_parse
[NET_SCHED]: act_api: fix netlink API conversion bug
[NET_SCHED]: sch_netem: use nla_parse_nested_compat
[NET_SCHED]: sch_atm: fix format string warning
[NETNS]: Add namespace for ICMP replying code.
...
Diffstat (limited to 'net/ipv4/fib_frontend.c')
-rw-r--r-- | net/ipv4/fib_frontend.c | 271 |
1 files changed, 202 insertions, 69 deletions
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 97abf93..d282618 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -47,59 +47,65 @@ #include <net/ip_fib.h> #include <net/rtnetlink.h> -#define FFprint(a...) printk(KERN_DEBUG a) +#ifndef CONFIG_IP_MULTIPLE_TABLES -static struct sock *fibnl; +static int __net_init fib4_rules_init(struct net *net) +{ + struct fib_table *local_table, *main_table; -#ifndef CONFIG_IP_MULTIPLE_TABLES + local_table = fib_hash_table(RT_TABLE_LOCAL); + if (local_table == NULL) + return -ENOMEM; -struct fib_table *ip_fib_local_table; -struct fib_table *ip_fib_main_table; + main_table = fib_hash_table(RT_TABLE_MAIN); + if (main_table == NULL) + goto fail; -#define FIB_TABLE_HASHSZ 1 -static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ]; + hlist_add_head_rcu(&local_table->tb_hlist, + &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX]); + hlist_add_head_rcu(&main_table->tb_hlist, + &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]); + return 0; -static void __init fib4_rules_init(void) -{ - ip_fib_local_table = fib_hash_init(RT_TABLE_LOCAL); - hlist_add_head_rcu(&ip_fib_local_table->tb_hlist, &fib_table_hash[0]); - ip_fib_main_table = fib_hash_init(RT_TABLE_MAIN); - hlist_add_head_rcu(&ip_fib_main_table->tb_hlist, &fib_table_hash[0]); +fail: + kfree(local_table); + return -ENOMEM; } #else -#define FIB_TABLE_HASHSZ 256 -static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ]; - -struct fib_table *fib_new_table(u32 id) +struct fib_table *fib_new_table(struct net *net, u32 id) { struct fib_table *tb; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; - tb = fib_get_table(id); + tb = fib_get_table(net, id); if (tb) return tb; - tb = fib_hash_init(id); + + tb = fib_hash_table(id); if (!tb) return NULL; h = id & (FIB_TABLE_HASHSZ - 1); - hlist_add_head_rcu(&tb->tb_hlist, &fib_table_hash[h]); + hlist_add_head_rcu(&tb->tb_hlist, &net->ipv4.fib_table_hash[h]); return tb; } -struct fib_table *fib_get_table(u32 id) +struct fib_table *fib_get_table(struct net *net, u32 id) { struct fib_table *tb; struct hlist_node *node; + struct hlist_head *head; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; h = id & (FIB_TABLE_HASHSZ - 1); + rcu_read_lock(); - hlist_for_each_entry_rcu(tb, node, &fib_table_hash[h], tb_hlist) { + head = &net->ipv4.fib_table_hash[h]; + hlist_for_each_entry_rcu(tb, node, head, tb_hlist) { if (tb->tb_id == id) { rcu_read_unlock(); return tb; @@ -110,15 +116,32 @@ struct fib_table *fib_get_table(u32 id) } #endif /* CONFIG_IP_MULTIPLE_TABLES */ -static void fib_flush(void) +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) + tb->tb_select_default(tb, flp, res); +} + +static void fib_flush(struct net *net) { int flushed = 0; struct fib_table *tb; struct hlist_node *node; + struct hlist_head *head; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { - hlist_for_each_entry(tb, node, &fib_table_hash[h], tb_hlist) + head = &net->ipv4.fib_table_hash[h]; + hlist_for_each_entry(tb, node, head, tb_hlist) flushed += tb->tb_flush(tb); } @@ -130,7 +153,7 @@ static void fib_flush(void) * 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; @@ -141,7 +164,7 @@ struct net_device * ip_dev_find(__be32 addr) res.r = NULL; #endif - local_table = fib_get_table(RT_TABLE_LOCAL); + local_table = fib_get_table(net, RT_TABLE_LOCAL); if (!local_table || local_table->tb_lookup(local_table, &fl, &res)) return NULL; if (res.type != RTN_LOCAL) @@ -155,33 +178,51 @@ out: return dev; } -unsigned inet_addr_type(__be32 addr) +/* + * Find address type as if only "dev" was present in the system. If + * on_dev is NULL then all interfaces are taken into consideration. + */ +static inline unsigned __inet_dev_addr_type(struct net *net, + const struct net_device *dev, + __be32 addr) { struct flowi fl = { .nl_u = { .ip4_u = { .daddr = addr } } }; struct fib_result res; unsigned ret = RTN_BROADCAST; struct fib_table *local_table; - if (ZERONET(addr) || BADCLASS(addr)) + if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) return RTN_BROADCAST; - if (MULTICAST(addr)) + if (ipv4_is_multicast(addr)) return RTN_MULTICAST; #ifdef CONFIG_IP_MULTIPLE_TABLES res.r = NULL; #endif - local_table = fib_get_table(RT_TABLE_LOCAL); + local_table = fib_get_table(net, RT_TABLE_LOCAL); if (local_table) { ret = RTN_UNICAST; if (!local_table->tb_lookup(local_table, &fl, &res)) { - ret = res.type; + if (!dev || dev == res.fi->fib_dev) + ret = res.type; fib_res_put(&res); } } return ret; } +unsigned int inet_addr_type(struct net *net, __be32 addr) +{ + return __inet_dev_addr_type(net, NULL, addr); +} + +unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, + __be32 addr) +{ + return __inet_dev_addr_type(net, dev, addr); +} + /* Given (packet source, input interface) and optional (dst, oif, tos): - (main) check, that source is valid i.e. not broadcast or our local address. @@ -202,6 +243,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, struct fib_result res; int no_addr, rpf; int ret; + struct net *net; no_addr = rpf = 0; rcu_read_lock(); @@ -215,7 +257,8 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, if (in_dev == NULL) goto e_inval; - if (fib_lookup(&fl, &res)) + net = dev->nd_net; + if (fib_lookup(net, &fl, &res)) goto last_resort; if (res.type != RTN_UNICAST) goto e_inval_res; @@ -239,7 +282,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, 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; @@ -278,13 +321,14 @@ static int put_rtax(struct nlattr *mx, int len, int type, u32 value) return len + nla_total_size(4); } -static int rtentry_to_fib_config(int cmd, struct rtentry *rt, +static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, struct fib_config *cfg) { __be32 addr; int plen; memset(cfg, 0, sizeof(*cfg)); + cfg->fc_nlinfo.nl_net = net; if (rt->rt_dst.sa_family != AF_INET) return -EAFNOSUPPORT; @@ -345,7 +389,7 @@ static int rtentry_to_fib_config(int cmd, struct rtentry *rt, colon = strchr(devname, ':'); if (colon) *colon = 0; - dev = __dev_get_by_name(&init_net, devname); + dev = __dev_get_by_name(net, devname); if (!dev) return -ENODEV; cfg->fc_oif = dev->ifindex; @@ -368,7 +412,7 @@ static int rtentry_to_fib_config(int cmd, struct rtentry *rt, if (rt->rt_gateway.sa_family == AF_INET && addr) { cfg->fc_gw = addr; if (rt->rt_flags & RTF_GATEWAY && - inet_addr_type(addr) == RTN_UNICAST) + inet_addr_type(net, addr) == RTN_UNICAST) cfg->fc_scope = RT_SCOPE_UNIVERSE; } @@ -409,7 +453,7 @@ static int rtentry_to_fib_config(int cmd, struct rtentry *rt, * Handle IP routing ioctl calls. These are used to manipulate the routing tables */ -int ip_rt_ioctl(unsigned int cmd, void __user *arg) +int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg) { struct fib_config cfg; struct rtentry rt; @@ -425,18 +469,18 @@ int ip_rt_ioctl(unsigned int cmd, void __user *arg) return -EFAULT; rtnl_lock(); - err = rtentry_to_fib_config(cmd, &rt, &cfg); + err = rtentry_to_fib_config(net, cmd, &rt, &cfg); if (err == 0) { struct fib_table *tb; if (cmd == SIOCDELRT) { - tb = fib_get_table(cfg.fc_table); + tb = fib_get_table(net, cfg.fc_table); if (tb) err = tb->tb_delete(tb, &cfg); else err = -ESRCH; } else { - tb = fib_new_table(cfg.fc_table); + tb = fib_new_table(net, cfg.fc_table); if (tb) err = tb->tb_insert(tb, &cfg); else @@ -466,8 +510,8 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX+1] = { [RTA_FLOW] = { .type = NLA_U32 }, }; -static int rtm_to_fib_config(struct sk_buff *skb, struct nlmsghdr *nlh, - struct fib_config *cfg) +static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, + struct nlmsghdr *nlh, struct fib_config *cfg) { struct nlattr *attr; int err, remaining; @@ -491,6 +535,7 @@ static int rtm_to_fib_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid; cfg->fc_nlinfo.nlh = nlh; + cfg->fc_nlinfo.nl_net = net; if (cfg->fc_type > RTN_MAX) { err = -EINVAL; @@ -538,15 +583,16 @@ errout: static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { + struct net *net = skb->sk->sk_net; struct fib_config cfg; struct fib_table *tb; int err; - err = rtm_to_fib_config(skb, nlh, &cfg); + err = rtm_to_fib_config(net, skb, nlh, &cfg); if (err < 0) goto errout; - tb = fib_get_table(cfg.fc_table); + tb = fib_get_table(net, cfg.fc_table); if (tb == NULL) { err = -ESRCH; goto errout; @@ -559,15 +605,16 @@ errout: static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { + struct net *net = skb->sk->sk_net; struct fib_config cfg; struct fib_table *tb; int err; - err = rtm_to_fib_config(skb, nlh, &cfg); + err = rtm_to_fib_config(net, skb, nlh, &cfg); if (err < 0) goto errout; - tb = fib_new_table(cfg.fc_table); + tb = fib_new_table(net, cfg.fc_table); if (tb == NULL) { err = -ENOBUFS; goto errout; @@ -580,10 +627,12 @@ errout: static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = skb->sk->sk_net; unsigned int h, s_h; unsigned int e = 0, s_e; struct fib_table *tb; struct hlist_node *node; + struct hlist_head *head; int dumped = 0; if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) && @@ -595,7 +644,8 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { e = 0; - hlist_for_each_entry(tb, node, &fib_table_hash[h], tb_hlist) { + head = &net->ipv4.fib_table_hash[h]; + hlist_for_each_entry(tb, node, head, tb_hlist) { if (e < s_e) goto next; if (dumped) @@ -624,6 +674,7 @@ 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 fib_table *tb; struct fib_config cfg = { .fc_protocol = RTPROT_KERNEL, @@ -633,12 +684,15 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad .fc_prefsrc = ifa->ifa_local, .fc_oif = ifa->ifa_dev->dev->ifindex, .fc_nlflags = NLM_F_CREATE | NLM_F_APPEND, + .fc_nlinfo = { + .nl_net = net, + }, }; if (type == RTN_UNICAST) - tb = fib_new_table(RT_TABLE_MAIN); + tb = fib_new_table(net, RT_TABLE_MAIN); else - tb = fib_new_table(RT_TABLE_LOCAL); + tb = fib_new_table(net, RT_TABLE_LOCAL); if (tb == NULL) return; @@ -668,7 +722,7 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) if (ifa->ifa_flags&IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, prefix, mask); if (prim == NULL) { - printk(KERN_DEBUG "fib_add_ifaddr: bug: prim == NULL\n"); + printk(KERN_WARNING "fib_add_ifaddr: bug: prim == NULL\n"); return; } } @@ -682,7 +736,7 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF)) fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim); - if (!ZERONET(prefix) && !(ifa->ifa_flags&IFA_F_SECONDARY) && + if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags&IFA_F_SECONDARY) && (prefix != addr || ifa->ifa_prefixlen < 32)) { fib_magic(RTM_NEWROUTE, dev->flags&IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, prefix, ifa->ifa_prefixlen, prim); @@ -715,7 +769,7 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) else { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); if (prim == NULL) { - printk(KERN_DEBUG "fib_del_ifaddr: bug: prim == NULL\n"); + printk(KERN_WARNING "fib_del_ifaddr: bug: prim == NULL\n"); return; } } @@ -747,7 +801,7 @@ 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(ifa->ifa_local) != RTN_LOCAL) { + if (inet_addr_type(dev->nd_net, ifa->ifa_local) != RTN_LOCAL) { /* And the last, but not the least thing. We must flush stray FIB entries. @@ -755,7 +809,7 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) for stray nexthop entries, then ignite fib_flush. */ if (fib_sync_down(ifa->ifa_local, NULL, 0)) - fib_flush(); + fib_flush(dev->nd_net); } } #undef LOCAL_OK @@ -797,11 +851,13 @@ static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb ) static void nl_fib_input(struct sk_buff *skb) { + struct net *net; struct fib_result_nl *frn; struct nlmsghdr *nlh; struct fib_table *tb; u32 pid; + net = skb->sk->sk_net; nlh = nlmsg_hdr(skb); if (skb->len < NLMSG_SPACE(0) || skb->len < nlh->nlmsg_len || nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*frn))) @@ -813,26 +869,37 @@ static void nl_fib_input(struct sk_buff *skb) nlh = nlmsg_hdr(skb); frn = (struct fib_result_nl *) NLMSG_DATA(nlh); - tb = fib_get_table(frn->tb_id_in); + tb = fib_get_table(net, frn->tb_id_in); nl_fib_lookup(frn, tb); pid = NETLINK_CB(skb).pid; /* pid of sending process */ NETLINK_CB(skb).pid = 0; /* from kernel */ NETLINK_CB(skb).dst_group = 0; /* unicast */ - netlink_unicast(fibnl, skb, pid, MSG_DONTWAIT); + netlink_unicast(net->ipv4.fibnl, skb, pid, MSG_DONTWAIT); +} + +static int nl_fib_lookup_init(struct net *net) +{ + struct sock *sk; + sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, 0, + nl_fib_input, NULL, THIS_MODULE); + if (sk == NULL) + return -EAFNOSUPPORT; + net->ipv4.fibnl = sk; + return 0; } -static void nl_fib_lookup_init(void) +static void nl_fib_lookup_exit(struct net *net) { - fibnl = netlink_kernel_create(&init_net, NETLINK_FIB_LOOKUP, 0, - nl_fib_input, NULL, THIS_MODULE); + netlink_kernel_release(net->ipv4.fibnl); + net->ipv4.fibnl = NULL; } static void fib_disable_ip(struct net_device *dev, int force) { if (fib_sync_down(0, dev, force)) - fib_flush(); + fib_flush(dev->nd_net); rt_cache_flush(0); arp_ifdown(dev); } @@ -869,9 +936,6 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo struct net_device *dev = ptr; struct in_device *in_dev = __in_dev_get_rtnl(dev); - if (dev->nd_net != &init_net) - return NOTIFY_DONE; - if (event == NETDEV_UNREGISTER) { fib_disable_ip(dev, 2); return NOTIFY_DONE; @@ -909,23 +973,92 @@ static struct notifier_block fib_netdev_notifier = { .notifier_call =fib_netdev_event, }; -void __init ip_fib_init(void) +static int __net_init ip_fib_net_init(struct net *net) { unsigned int i; + net->ipv4.fib_table_hash = kzalloc( + sizeof(struct hlist_head)*FIB_TABLE_HASHSZ, GFP_KERNEL); + if (net->ipv4.fib_table_hash == NULL) + return -ENOMEM; + for (i = 0; i < FIB_TABLE_HASHSZ; i++) - INIT_HLIST_HEAD(&fib_table_hash[i]); + INIT_HLIST_HEAD(&net->ipv4.fib_table_hash[i]); - fib4_rules_init(); + return fib4_rules_init(net); +} - register_netdevice_notifier(&fib_netdev_notifier); - register_inetaddr_notifier(&fib_inetaddr_notifier); - nl_fib_lookup_init(); +static void __net_exit ip_fib_net_exit(struct net *net) +{ + unsigned int i; + +#ifdef CONFIG_IP_MULTIPLE_TABLES + fib4_rules_exit(net); +#endif + for (i = 0; i < FIB_TABLE_HASHSZ; i++) { + struct fib_table *tb; + struct hlist_head *head; + struct hlist_node *node, *tmp; + + 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); + kfree(tb); + } + } + kfree(net->ipv4.fib_table_hash); +} + +static int __net_init fib_net_init(struct net *net) +{ + int error; + + error = ip_fib_net_init(net); + if (error < 0) + goto out; + error = nl_fib_lookup_init(net); + if (error < 0) + goto out_nlfl; + error = fib_proc_init(net); + if (error < 0) + goto out_proc; +out: + return error; + +out_proc: + nl_fib_lookup_exit(net); +out_nlfl: + ip_fib_net_exit(net); + goto out; +} + +static void __net_exit fib_net_exit(struct net *net) +{ + fib_proc_exit(net); + nl_fib_lookup_exit(net); + ip_fib_net_exit(net); +} + +static struct pernet_operations fib_net_ops = { + .init = fib_net_init, + .exit = fib_net_exit, +}; + +void __init ip_fib_init(void) +{ rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL); rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL); rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib); + + register_pernet_subsys(&fib_net_ops); + register_netdevice_notifier(&fib_netdev_notifier); + register_inetaddr_notifier(&fib_inetaddr_notifier); + + fib_hash_init(); } EXPORT_SYMBOL(inet_addr_type); +EXPORT_SYMBOL(inet_dev_addr_type); EXPORT_SYMBOL(ip_dev_find); |