*
* 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, <kuznet@ms2.inr.ac.ru>
*
* This program is free software; you can redistribute it and/or
#include <net/route.h>
#include <net/tcp.h>
#include <net/sock.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)
-
-static struct sock *fibnl;
-struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ];
-
#ifndef CONFIG_IP_MULTIPLE_TABLES
static int __net_init fib4_rules_init(struct net *net)
{
struct fib_table *local_table, *main_table;
- local_table = fib_hash_init(RT_TABLE_LOCAL);
+ local_table = fib_hash_table(RT_TABLE_LOCAL);
if (local_table == NULL)
return -ENOMEM;
- main_table = fib_hash_init(RT_TABLE_MAIN);
+ main_table = fib_hash_table(RT_TABLE_MAIN);
if (main_table == NULL)
goto fail;
hlist_add_head_rcu(&local_table->tb_hlist,
- &fib_table_hash[TABLE_LOCAL_INDEX]);
+ &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX]);
hlist_add_head_rcu(&main_table->tb_hlist,
- &fib_table_hash[TABLE_MAIN_INDEX]);
+ &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]);
return 0;
fail:
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 *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)
+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;
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)
- flushed += tb->tb_flush(tb);
+ head = &net->ipv4.fib_table_hash[h];
+ hlist_for_each_entry(tb, node, head, tb_hlist)
+ 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;
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;
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;
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);
*/
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
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;
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(&init_net, 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(&init_net, addr) == RTN_UNICAST)
+ inet_addr_type(net, addr) == RTN_UNICAST)
cfg->fc_scope = RT_SCOPE_UNIVERSE;
}
* 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(&init_net, cfg.fc_table);
+ 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(&init_net, cfg.fc_table);
+ 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;
}
[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 },
};
-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;
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;
- if (net != &init_net)
- return -EINVAL;
-
- err = rtm_to_fib_config(skb, nlh, &cfg);
+ err = rtm_to_fib_config(net, skb, nlh, &cfg);
if (err < 0)
goto errout;
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;
- if (net != &init_net)
- return -EINVAL;
-
- 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(&init_net, cfg.fc_table);
+ tb = fib_new_table(net, cfg.fc_table);
if (tb == NULL) {
err = -ENOBUFS;
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;
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]));
- if (tb->tb_dump(tb, skb, cb) < 0)
+ if (fib_table_dump(tb, skb, cb) < 0)
goto out;
dumped = 1;
next:
static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa)
{
+ struct net *net = dev_net(ifa->ifa_dev->dev);
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(&init_net, RT_TABLE_MAIN);
+ tb = fib_new_table(net, RT_TABLE_MAIN);
else
- tb = fib_new_table(&init_net, RT_TABLE_LOCAL);
+ tb = fib_new_table(net, RT_TABLE_LOCAL);
if (tb == NULL)
return;
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)
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;
}
}
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;
}
}
fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim);
/* Check, that this local address finally disappeared. */
- if (inet_addr_type(&init_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();
+ if (fib_sync_down_addr(dev_net(dev), ifa->ifa_local))
+ fib_flush(dev_net(dev));
}
}
#undef LOCAL_OK
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;
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 = 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)))
nlh = nlmsg_hdr(skb);
frn = (struct fib_result_nl *) NLMSG_DATA(nlh);
- tb = fib_get_table(&init_net, 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)
+static int __net_init nl_fib_lookup_init(struct net *net)
{
- fibnl = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, 0,
- nl_fib_input, NULL, THIS_MODULE);
- if (fibnl == NULL)
+ 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_exit(struct net *net)
{
- sock_put(fibnl);
+ 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();
- 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);
/* 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;
}
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);
+ fib_disable_ip(dev, 2, -1);
return NOTIFY_DONE;
}
#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(
+ 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]);
- 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)
+static void ip_fib_net_exit(struct net *net)
{
unsigned int i;
struct hlist_head *head;
struct hlist_node *node, *tmp;
- head = &fib_table_hash[i];
+ 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);
}
}
+ 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;
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);