#include <linux/capability.h>
#include <linux/types.h>
#include <linux/kernel.h>
-#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/if_addr.h>
#include <linux/if_arp.h>
#include <linux/skbuff.h>
-#include <linux/netlink.h>
#include <linux/init.h>
#include <linux/list.h>
#include <net/icmp.h>
#include <net/arp.h>
#include <net/ip_fib.h>
+#include <net/rtnetlink.h>
#define FFprint(a...) printk(KERN_DEBUG a)
#ifndef CONFIG_IP_MULTIPLE_TABLES
-struct fib_table *ip_fib_local_table;
-struct fib_table *ip_fib_main_table;
+static int __net_init fib4_rules_init(struct net *net)
+{
+ struct fib_table *local_table, *main_table;
-#define FIB_TABLE_HASHSZ 1
-static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ];
+ local_table = fib_hash_init(RT_TABLE_LOCAL);
+ if (local_table == NULL)
+ return -ENOMEM;
-#else
+ main_table = fib_hash_init(RT_TABLE_MAIN);
+ if (main_table == NULL)
+ goto fail;
+
+ 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;
-#define FIB_TABLE_HASHSZ 256
-static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ];
+fail:
+ kfree(local_table);
+ return -ENOMEM;
+}
+#else
-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);
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;
}
#endif /* CONFIG_IP_MULTIPLE_TABLES */
-static void fib_flush(void)
+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);
}
struct flowi fl = { .nl_u = { .ip4_u = { .daddr = addr } } };
struct fib_result res;
struct net_device *dev = NULL;
+ struct fib_table *local_table;
#ifdef CONFIG_IP_MULTIPLE_TABLES
res.r = NULL;
#endif
- if (!ip_fib_local_table ||
- ip_fib_local_table->tb_lookup(ip_fib_local_table, &fl, &res))
+ local_table = fib_get_table(&init_net, RT_TABLE_LOCAL);
+ if (!local_table || local_table->tb_lookup(local_table, &fl, &res))
return NULL;
if (res.type != RTN_LOCAL)
goto 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_badclass(addr))
return RTN_BROADCAST;
- if (MULTICAST(addr))
+ if (ipv4_is_multicast(addr))
return RTN_MULTICAST;
#ifdef CONFIG_IP_MULTIPLE_TABLES
res.r = NULL;
#endif
-
- if (ip_fib_local_table) {
+
+ local_table = fib_get_table(net, RT_TABLE_LOCAL);
+ if (local_table) {
ret = RTN_UNICAST;
- if (!ip_fib_local_table->tb_lookup(ip_fib_local_table,
- &fl, &res)) {
- ret = res.type;
+ if (!local_table->tb_lookup(local_table, &fl, &res)) {
+ 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.
return -EINVAL;
}
-#ifndef CONFIG_IP_NOSIOCRT
-
static inline __be32 sk_extract_addr(struct sockaddr *addr)
{
return ((struct sockaddr_in *) addr)->sin_addr.s_addr;
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;
colon = strchr(devname, ':');
if (colon)
*colon = 0;
- dev = __dev_get_by_name(devname);
+ dev = __dev_get_by_name(net, devname);
if (!dev)
return -ENODEV;
cfg->fc_oif = dev->ifindex;
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;
}
int len = 0;
mx = kzalloc(3 * nla_total_size(4), GFP_KERNEL);
- if (mx == NULL)
+ if (mx == NULL)
return -ENOMEM;
if (rt->rt_flags & RTF_MTU)
/*
* 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;
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
return -EINVAL;
}
-#else
-
-int ip_rt_ioctl(unsigned int cmd, void *arg)
-{
- return -EINVAL;
-}
-
-#endif
-
-struct nla_policy rtm_ipv4_policy[RTA_MAX+1] __read_mostly = {
+const struct nla_policy rtm_ipv4_policy[RTA_MAX+1] = {
[RTA_DST] = { .type = NLA_U32 },
[RTA_SRC] = { .type = NLA_U32 },
[RTA_IIF] = { .type = NLA_U32 },
[RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) },
[RTA_PROTOINFO] = { .type = NLA_U32 },
[RTA_FLOW] = { .type = NLA_U32 },
- [RTA_MP_ALGO] = { .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;
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;
+ goto errout;
+ }
nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), remaining) {
- switch (attr->nla_type) {
+ switch (nla_type(attr)) {
case RTA_DST:
cfg->fc_dst = nla_get_be32(attr);
break;
case RTA_FLOW:
cfg->fc_flow = nla_get_u32(attr);
break;
- case RTA_MP_ALGO:
- cfg->fc_mp_alg = nla_get_u32(attr);
- break;
case RTA_TABLE:
cfg->fc_table = nla_get_u32(attr);
break;
return err;
}
-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 fib_config cfg;
struct fib_table *tb;
int err;
- err = rtm_to_fib_config(skb, nlh, &cfg);
+ if (net != &init_net)
+ return -EINVAL;
+
+ 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;
return err;
}
-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 fib_config cfg;
struct fib_table *tb;
int err;
- err = rtm_to_fib_config(skb, nlh, &cfg);
+ if (net != &init_net)
+ return -EINVAL;
+
+ 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(&init_net, cfg.fc_table);
if (tb == NULL) {
err = -ENOBUFS;
goto errout;
return err;
}
-int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
+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 (net != &init_net)
+ return 0;
+
if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) &&
((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED)
return ip_rt_dump(skb, 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)
memset(&cb->args[2], 0, sizeof(cb->args) -
- 2 * sizeof(cb->args[0]));
+ 2 * sizeof(cb->args[0]));
if (tb->tb_dump(tb, skb, cb) < 0)
goto out;
dumped = 1;
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,
.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;
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);
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(&init_net, ifa->ifa_local) != RTN_LOCAL) {
/* And the last, but not the least thing.
We must flush stray FIB entries.
for stray nexthop entries, then ignite fib_flush.
*/
if (fib_sync_down(ifa->ifa_local, NULL, 0))
- fib_flush();
+ fib_flush(&init_net);
}
}
#undef LOCAL_OK
static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb )
{
-
+
struct fib_result res;
struct flowi fl = { .mark = frn->fl_mark,
.nl_u = { .ip4_u = { .daddr = frn->fl_addr,
.tos = frn->fl_tos,
.scope = frn->fl_scope } } };
+
+#ifdef CONFIG_IP_MULTIPLE_TABLES
+ res.r = NULL;
+#endif
+
+ frn->err = -ENOENT;
if (tb) {
local_bh_disable();
frn->nh_sel = res.nh_sel;
frn->type = res.type;
frn->scope = res.scope;
+ fib_res_put(&res);
}
local_bh_enable();
}
}
-static void nl_fib_input(struct sock *sk, int len)
+static void nl_fib_input(struct sk_buff *skb)
{
- struct sk_buff *skb = NULL;
- struct nlmsghdr *nlh = NULL;
+ struct net *net;
struct fib_result_nl *frn;
- u32 pid;
+ struct nlmsghdr *nlh;
struct fib_table *tb;
-
- skb = skb_dequeue(&sk->sk_receive_queue);
- nlh = (struct nlmsghdr *)skb->data;
+ 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))) {
- kfree_skb(skb);
+ nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*frn)))
return;
- }
-
+
+ skb = skb_clone(skb, GFP_KERNEL);
+ if (skb == NULL)
+ return;
+ 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 = nlh->nlmsg_pid; /*pid of sending process */
+
+ pid = NETLINK_CB(skb).pid; /* pid of sending process */
NETLINK_CB(skb).pid = 0; /* from kernel */
- NETLINK_CB(skb).dst_pid = pid;
NETLINK_CB(skb).dst_group = 0; /* unicast */
- netlink_unicast(sk, 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;
+ /* 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_init(void)
+static void nl_fib_lookup_exit(struct net *net)
{
- netlink_kernel_create(NETLINK_FIB_LOOKUP, 0, nl_fib_input, THIS_MODULE);
+ /* 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);
+ sock_put(net->ipv4.fibnl);
}
static void fib_disable_ip(struct net_device *dev, int force)
{
if (fib_sync_down(0, dev, force))
- fib_flush();
+ fib_flush(&init_net);
rt_cache_flush(0);
arp_ifdown(dev);
}
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;
.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]);
-#ifndef CONFIG_IP_MULTIPLE_TABLES
- 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]);
-#else
- fib4_rules_init();
+ INIT_HLIST_HEAD(&net->ipv4.fib_table_hash[i]);
+
+ return fib4_rules_init(net);
+}
+
+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 = 0;
+ if (net != &init_net)
+ goto out;
+
+ 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);
- nl_fib_lookup_init();
}
EXPORT_SYMBOL(inet_addr_type);
+EXPORT_SYMBOL(inet_dev_addr_type);
EXPORT_SYMBOL(ip_dev_find);