*
* IPv4 Forwarding Information Base: semantics.
*
- * Version: $Id: fib_semantics.c,v 1.19 2002/01/12 07:54:56 davem Exp $
- *
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* This program is free software; you can redistribute it and/or
#include <net/tcp.h>
#include <net/sock.h>
#include <net/ip_fib.h>
-#include <net/ip_mp_alg.h>
#include <net/netlink.h>
#include <net/nexthop.h>
#include "fib_lookup.h"
-#define FSprintk(a...)
-
static DEFINE_SPINLOCK(fib_info_lock);
static struct hlist_head *fib_info_hash;
static struct hlist_head *fib_info_laddrhash;
for (nhsel=0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++)
#define change_nexthops(fi) { int nhsel; struct fib_nh * nh; \
-for (nhsel=0, nh = (struct fib_nh*)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nh++, nhsel++)
+for (nhsel=0, nh = (struct fib_nh *)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nh++, nhsel++)
#else /* CONFIG_IP_ROUTE_MULTIPATH */
/* Hope, that gcc will optimize it to get rid of dummy loop */
-#define for_nexthops(fi) { int nhsel=0; const struct fib_nh * nh = (fi)->fib_nh; \
+#define for_nexthops(fi) { int nhsel = 0; const struct fib_nh * nh = (fi)->fib_nh; \
for (nhsel=0; nhsel < 1; nhsel++)
-#define change_nexthops(fi) { int nhsel=0; struct fib_nh * nh = (struct fib_nh*)((fi)->fib_nh); \
+#define change_nexthops(fi) { int nhsel = 0; struct fib_nh * nh = (struct fib_nh *)((fi)->fib_nh); \
for (nhsel=0; nhsel < 1; nhsel++)
#endif /* CONFIG_IP_ROUTE_MULTIPATH */
#define endfor_nexthops(fi) }
-static const struct
+static const struct
{
int error;
u8 scope;
-} fib_props[RTA_MAX + 1] = {
- {
+} fib_props[RTN_MAX + 1] = {
+ {
.error = 0,
.scope = RT_SCOPE_NOWHERE,
}, /* RTN_UNSPEC */
void free_fib_info(struct fib_info *fi)
{
if (fi->fib_dead == 0) {
- printk("Freeing alive fib_info %p\n", fi);
+ printk(KERN_WARNING "Freeing alive fib_info %p\n", fi);
return;
}
change_nexthops(fi) {
nh->nh_dev = NULL;
} endfor_nexthops(fi);
fib_info_cnt--;
+ release_net(fi->fib_net);
kfree(fi);
}
return 0;
}
+static inline unsigned int fib_devindex_hashfn(unsigned int val)
+{
+ unsigned int mask = DEVINDEX_HASHSIZE - 1;
+
+ return (val ^
+ (val >> DEVINDEX_HASHBITS) ^
+ (val >> (DEVINDEX_HASHBITS * 2))) & mask;
+}
+
static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
{
unsigned int mask = (fib_hash_size - 1);
unsigned int val = fi->fib_nhs;
val ^= fi->fib_protocol;
- val ^= fi->fib_prefsrc;
+ val ^= (__force u32)fi->fib_prefsrc;
val ^= fi->fib_priority;
+ for_nexthops(fi) {
+ val ^= fib_devindex_hashfn(nh->nh_oif);
+ } endfor_nexthops(fi)
return (val ^ (val >> 7) ^ (val >> 12)) & mask;
}
head = &fib_info_hash[hash];
hlist_for_each_entry(fi, node, head, fib_hash) {
+ if (!net_eq(fi->fib_net, nfi->fib_net))
+ continue;
if (fi->fib_nhs != nfi->fib_nhs)
continue;
if (nfi->fib_protocol == fi->fib_protocol &&
return NULL;
}
-static inline unsigned int fib_devindex_hashfn(unsigned int val)
-{
- unsigned int mask = DEVINDEX_HASHSIZE - 1;
-
- return (val ^
- (val >> DEVINDEX_HASHBITS) ^
- (val >> (DEVINDEX_HASHBITS * 2))) & mask;
-}
-
/* Check, that the gateway is already configured.
Used only by redirect accept routine.
*/
-int ip_fib_check_default(u32 gw, struct net_device *dev)
+int ip_fib_check_default(__be32 gw, struct net_device *dev)
{
struct hlist_head *head;
struct hlist_node *node;
return -1;
}
-void rtmsg_fib(int event, u32 key, struct fib_alias *fa,
- int dst_len, u32 tb_id, struct nl_info *info)
+static inline size_t fib_nlmsg_size(struct fib_info *fi)
+{
+ size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg))
+ + nla_total_size(4) /* RTA_TABLE */
+ + nla_total_size(4) /* RTA_DST */
+ + nla_total_size(4) /* RTA_PRIORITY */
+ + nla_total_size(4); /* RTA_PREFSRC */
+
+ /* space for nested metrics */
+ payload += nla_total_size((RTAX_MAX * nla_total_size(4)));
+
+ if (fi->fib_nhs) {
+ /* Also handles the special case fib_nhs == 1 */
+
+ /* each nexthop is packed in an attribute */
+ size_t nhsize = nla_total_size(sizeof(struct rtnexthop));
+
+ /* may contain flow and gateway attribute */
+ nhsize += 2 * nla_total_size(4);
+
+ /* all nexthops are packed in a nested attribute */
+ payload += nla_total_size(fi->fib_nhs * nhsize);
+ }
+
+ return payload;
+}
+
+void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
+ int dst_len, u32 tb_id, struct nl_info *info,
+ unsigned int nlm_flags)
{
struct sk_buff *skb;
- int payload = sizeof(struct rtmsg) + 256;
u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
int err = -ENOBUFS;
- skb = nlmsg_new(nlmsg_total_size(payload), GFP_KERNEL);
+ skb = nlmsg_new(fib_nlmsg_size(fa->fa_info), GFP_KERNEL);
if (skb == NULL)
goto errout;
err = fib_dump_info(skb, info->pid, seq, event, tb_id,
fa->fa_type, fa->fa_scope, key, dst_len,
- fa->fa_tos, fa->fa_info, 0);
+ fa->fa_tos, fa->fa_info, nlm_flags);
if (err < 0) {
+ /* -EMSGSIZE implies BUG in fib_nlmsg_size() */
+ WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout;
}
-
- err = rtnl_notify(skb, info->pid, RTNLGRP_IPV4_ROUTE,
- info->nlh, GFP_KERNEL);
+ rtnl_notify(skb, info->nl_net, info->pid, RTNLGRP_IPV4_ROUTE,
+ info->nlh, GFP_KERNEL);
+ return;
errout:
if (err < 0)
- rtnl_set_sk_err(RTNLGRP_IPV4_ROUTE, err);
+ rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err);
}
/* Return the first fib alias matching TOS with
}
int fib_detect_death(struct fib_info *fi, int order,
- struct fib_info **last_resort, int *last_idx, int *dflt)
+ struct fib_info **last_resort, int *last_idx, int dflt)
{
struct neighbour *n;
int state = NUD_NONE;
state = n->nud_state;
neigh_release(n);
}
- if (state==NUD_REACHABLE)
+ if (state == NUD_REACHABLE)
return 0;
- if ((state&NUD_VALID) && order != *dflt)
+ if ((state&NUD_VALID) && order != dflt)
return 0;
if ((state&NUD_VALID) ||
- (*last_idx<0 && order > *dflt)) {
+ (*last_idx<0 && order > dflt)) {
*last_resort = fi;
*last_idx = order;
}
rtnh = cfg->fc_mp;
remaining = cfg->fc_mp_len;
-
+
for_nexthops(fi) {
int attrlen;
Normally it looks as following.
{universe prefix} -> (gw, oif) [scope link]
- |
+ |
|-> {link prefix} -> (gw, oif) [scope local]
- |
+ |
|-> {local prefix} (terminal node)
*/
struct fib_nh *nh)
{
int err;
+ struct net *net;
+ net = cfg->fc_nlinfo.nl_net;
if (nh->nh_gw) {
struct fib_result res;
if (cfg->fc_scope >= RT_SCOPE_LINK)
return -EINVAL;
- if (inet_addr_type(nh->nh_gw) != RTN_UNICAST)
+ if (inet_addr_type(net, nh->nh_gw) != RTN_UNICAST)
return -EINVAL;
- if ((dev = __dev_get_by_index(nh->nh_oif)) == NULL)
+ if ((dev = __dev_get_by_index(net, nh->nh_oif)) == NULL)
return -ENODEV;
if (!(dev->flags&IFF_UP))
return -ENETDOWN;
/* It is not necessary, but requires a bit of thinking */
if (fl.fl4_scope < RT_SCOPE_LINK)
fl.fl4_scope = RT_SCOPE_LINK;
- if ((err = fib_lookup(&fl, &res)) != 0)
+ if ((err = fib_lookup(net, &fl, &res)) != 0)
return err;
}
err = -EINVAL;
if (nh->nh_flags&(RTNH_F_PERVASIVE|RTNH_F_ONLINK))
return -EINVAL;
- in_dev = inetdev_by_index(nh->nh_oif);
+ in_dev = inetdev_by_index(net, nh->nh_oif);
if (in_dev == NULL)
return -ENODEV;
if (!(in_dev->dev->flags&IFF_UP)) {
return 0;
}
-static inline unsigned int fib_laddr_hashfn(u32 val)
+static inline unsigned int fib_laddr_hashfn(__be32 val)
{
unsigned int mask = (fib_hash_size - 1);
- return (val ^ (val >> 7) ^ (val >> 14)) & mask;
+ return ((__force u32)val ^ ((__force u32)val >> 7) ^ ((__force u32)val >> 14)) & mask;
}
static struct hlist_head *fib_hash_alloc(int bytes)
{
if (bytes <= PAGE_SIZE)
- return kmalloc(bytes, GFP_KERNEL);
+ return kzalloc(bytes, GFP_KERNEL);
else
return (struct hlist_head *)
- __get_free_pages(GFP_KERNEL, get_order(bytes));
+ __get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(bytes));
}
static void fib_hash_free(struct hlist_head *hash, int bytes)
struct fib_info *fi = NULL;
struct fib_info *ofi;
int nhs = 1;
+ struct net *net = cfg->fc_nlinfo.nl_net;
/* Fast check to catch the most weird cases */
if (fib_props[cfg->fc_type].scope > cfg->fc_scope)
goto err_inval;
}
#endif
-#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
- if (cfg->fc_mp_alg) {
- if (cfg->fc_mp_alg < IP_MP_ALG_NONE ||
- cfg->fc_mp_alg > IP_MP_ALG_MAX)
- goto err_inval;
- }
-#endif
err = -ENOBUFS;
if (fib_info_cnt >= fib_hash_size) {
if (!new_info_hash || !new_laddrhash) {
fib_hash_free(new_info_hash, bytes);
fib_hash_free(new_laddrhash, bytes);
- } else {
- memset(new_info_hash, 0, bytes);
- memset(new_laddrhash, 0, bytes);
-
+ } else
fib_hash_move(new_info_hash, new_laddrhash, new_size);
- }
if (!fib_hash_size)
goto failure;
goto failure;
fib_info_cnt++;
+ fi->fib_net = hold_net(net);
fi->fib_protocol = cfg->fc_protocol;
fi->fib_flags = cfg->fc_flags;
fi->fib_priority = cfg->fc_priority;
int remaining;
nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
- int type = nla->nla_type;
+ int type = nla_type(nla);
if (type) {
if (type > RTAX_MAX)
#endif
}
-#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
- fi->fib_mp_alg = cfg->fc_mp_alg;
-#endif
-
if (fib_props[cfg->fc_type].error) {
if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp)
goto err_inval;
if (nhs != 1 || nh->nh_gw)
goto err_inval;
nh->nh_scope = RT_SCOPE_NOWHERE;
- nh->nh_dev = dev_get_by_index(fi->fib_nh->nh_oif);
+ nh->nh_dev = dev_get_by_index(net, fi->fib_nh->nh_oif);
err = -ENODEV;
if (nh->nh_dev == NULL)
goto failure;
if (fi->fib_prefsrc) {
if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst ||
fi->fib_prefsrc != cfg->fc_dst)
- if (inet_addr_type(fi->fib_prefsrc) != RTN_LOCAL)
+ if (inet_addr_type(net, fi->fib_prefsrc) != RTN_LOCAL)
goto err_inval;
}
err = -EINVAL;
failure:
- if (fi) {
+ if (fi) {
fi->fib_dead = 1;
free_fib_info(fi);
}
/* Note! fib_semantic_match intentionally uses RCU list functions. */
int fib_semantic_match(struct list_head *head, const struct flowi *flp,
- struct fib_result *res, __u32 zone, __u32 mask,
- int prefixlen)
+ struct fib_result *res, int prefixlen)
{
struct fib_alias *fa;
int nh_sel = 0;
continue;
default:
- printk(KERN_DEBUG "impossible 102\n");
+ printk(KERN_WARNING "fib_semantic_match bad type %#x\n",
+ fa->fa_type);
return -EINVAL;
- };
+ }
}
return err;
}
res->type = fa->fa_type;
res->scope = fa->fa_scope;
res->fi = fa->fa_info;
-#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
- res->netmask = mask;
- res->network = zone &
- (0xFFFFFFFF >> (32 - prefixlen));
-#endif
atomic_inc(&res->fi->fib_clntref);
return 0;
}
}
int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
- u32 tb_id, u8 type, u8 scope, u32 dst, int dst_len, u8 tos,
+ u32 tb_id, u8 type, u8 scope, __be32 dst, int dst_len, u8 tos,
struct fib_info *fi, unsigned int flags)
{
struct nlmsghdr *nlh;
nlh = nlmsg_put(skb, pid, seq, event, sizeof(*rtm), flags);
if (nlh == NULL)
- return -ENOBUFS;
+ return -EMSGSIZE;
rtm = nlmsg_data(nlh);
rtm->rtm_family = AF_INET;
rtm->rtm_dst_len = dst_len;
rtm->rtm_src_len = 0;
rtm->rtm_tos = tos;
- rtm->rtm_table = tb_id;
+ if (tb_id < 256)
+ rtm->rtm_table = tb_id;
+ else
+ rtm->rtm_table = RT_TABLE_COMPAT;
NLA_PUT_U32(skb, RTA_TABLE, tb_id);
rtm->rtm_type = type;
rtm->rtm_flags = fi->fib_flags;
return nlmsg_end(skb, nlh);
nla_put_failure:
- return nlmsg_cancel(skb, nlh);
+ nlmsg_cancel(skb, nlh);
+ return -EMSGSIZE;
}
/*
referring to it.
- device went down -> we must shutdown all nexthops going via it.
*/
-
-int fib_sync_down(u32 local, struct net_device *dev, int force)
+int fib_sync_down_addr(struct net *net, __be32 local)
{
int ret = 0;
- int scope = RT_SCOPE_NOWHERE;
-
- if (force)
- scope = -1;
+ unsigned int hash = fib_laddr_hashfn(local);
+ struct hlist_head *head = &fib_info_laddrhash[hash];
+ struct hlist_node *node;
+ struct fib_info *fi;
- if (local && fib_info_laddrhash) {
- unsigned int hash = fib_laddr_hashfn(local);
- struct hlist_head *head = &fib_info_laddrhash[hash];
- struct hlist_node *node;
- struct fib_info *fi;
+ if (fib_info_laddrhash == NULL || local == 0)
+ return 0;
- hlist_for_each_entry(fi, node, head, fib_lhash) {
- if (fi->fib_prefsrc == local) {
- fi->fib_flags |= RTNH_F_DEAD;
- ret++;
- }
+ hlist_for_each_entry(fi, node, head, fib_lhash) {
+ if (!net_eq(fi->fib_net, net))
+ continue;
+ if (fi->fib_prefsrc == local) {
+ fi->fib_flags |= RTNH_F_DEAD;
+ ret++;
}
}
+ return ret;
+}
+
+int fib_sync_down_dev(struct net_device *dev, int force)
+{
+ int ret = 0;
+ int scope = RT_SCOPE_NOWHERE;
+ struct fib_info *prev_fi = NULL;
+ unsigned int hash = fib_devindex_hashfn(dev->ifindex);
+ struct hlist_head *head = &fib_info_devhash[hash];
+ struct hlist_node *node;
+ struct fib_nh *nh;
- if (dev) {
- struct fib_info *prev_fi = NULL;
- unsigned int hash = fib_devindex_hashfn(dev->ifindex);
- struct hlist_head *head = &fib_info_devhash[hash];
- struct hlist_node *node;
- struct fib_nh *nh;
+ if (force)
+ scope = -1;
- hlist_for_each_entry(nh, node, head, nh_hash) {
- struct fib_info *fi = nh->nh_parent;
- int dead;
+ hlist_for_each_entry(nh, node, head, nh_hash) {
+ struct fib_info *fi = nh->nh_parent;
+ int dead;
- BUG_ON(!fi->fib_nhs);
- if (nh->nh_dev != dev || fi == prev_fi)
- continue;
- prev_fi = fi;
- dead = 0;
- change_nexthops(fi) {
- if (nh->nh_flags&RTNH_F_DEAD)
- dead++;
- else if (nh->nh_dev == dev &&
- nh->nh_scope != scope) {
- nh->nh_flags |= RTNH_F_DEAD;
+ BUG_ON(!fi->fib_nhs);
+ if (nh->nh_dev != dev || fi == prev_fi)
+ continue;
+ prev_fi = fi;
+ dead = 0;
+ change_nexthops(fi) {
+ if (nh->nh_flags&RTNH_F_DEAD)
+ dead++;
+ else if (nh->nh_dev == dev &&
+ nh->nh_scope != scope) {
+ nh->nh_flags |= RTNH_F_DEAD;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
- spin_lock_bh(&fib_multipath_lock);
- fi->fib_power -= nh->nh_power;
- nh->nh_power = 0;
- spin_unlock_bh(&fib_multipath_lock);
+ spin_lock_bh(&fib_multipath_lock);
+ fi->fib_power -= nh->nh_power;
+ nh->nh_power = 0;
+ spin_unlock_bh(&fib_multipath_lock);
#endif
- dead++;
- }
+ dead++;
+ }
#ifdef CONFIG_IP_ROUTE_MULTIPATH
- if (force > 1 && nh->nh_dev == dev) {
- dead = fi->fib_nhs;
- break;
- }
-#endif
- } endfor_nexthops(fi)
- if (dead == fi->fib_nhs) {
- fi->fib_flags |= RTNH_F_DEAD;
- ret++;
+ if (force > 1 && nh->nh_dev == dev) {
+ dead = fi->fib_nhs;
+ break;
}
+#endif
+ } endfor_nexthops(fi)
+ if (dead == fi->fib_nhs) {
+ fi->fib_flags |= RTNH_F_DEAD;
+ ret++;
}
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff