* 2 of the License, or (at your option) any later version.
*/
-#include <linux/config.h>
#include <asm/uaccess.h>
#include <asm/system.h>
-#include <asm/bitops.h>
+#include <linux/bitops.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/in.h>
#include <linux/inet.h>
+#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/proc_fs.h>
#include <linux/skbuff.h>
#include <linux/netlink.h>
#include <linux/init.h>
+#include <linux/vs_context.h>
#include <net/ip.h>
#include <net/protocol.h>
#include "fib_lookup.h"
-static kmem_cache_t *fn_hash_kmem;
-static kmem_cache_t *fn_alias_kmem;
+static struct kmem_cache *fn_hash_kmem __read_mostly;
+static struct kmem_cache *fn_alias_kmem __read_mostly;
struct fib_node {
struct hlist_node fn_hash;
struct list_head fn_alias;
- u32 fn_key;
+ __be32 fn_key;
};
struct fn_zone {
#define FZ_HASHMASK(fz) ((fz)->fz_hashmask)
int fz_order; /* Zone order */
- u32 fz_mask;
+ __be32 fz_mask;
#define FZ_MASK(fz) ((fz)->fz_mask)
};
struct fn_zone *fn_zone_list;
};
-static inline u32 fn_hash(u32 key, struct fn_zone *fz)
+static inline u32 fn_hash(__be32 key, struct fn_zone *fz)
{
u32 h = ntohl(key)>>(32 - fz->fz_order);
h ^= (h>>20);
return h;
}
-static inline u32 fz_key(u32 dst, struct fn_zone *fz)
+static inline __be32 fz_key(__be32 dst, struct fn_zone *fz)
{
return dst & FZ_MASK(fz);
}
-static rwlock_t fib_hash_lock = RW_LOCK_UNLOCKED;
+static DEFINE_RWLOCK(fib_hash_lock);
+static unsigned int fib_hash_genid;
#define FZ_MAX_DIVISOR ((PAGE_SIZE<<MAX_ORDER) / sizeof(struct hlist_head))
fz->fz_hashmask = new_hashmask;
fz->fz_divisor = new_divisor;
fn_rebuild_zone(fz, old_ht, old_divisor);
+ fib_hash_genid++;
write_unlock_bh(&fib_hash_lock);
fz_hash_free(old_ht, old_divisor);
fn_new_zone(struct fn_hash *table, int z)
{
int i;
- struct fn_zone *fz = kmalloc(sizeof(struct fn_zone), GFP_KERNEL);
+ struct fn_zone *fz = kzalloc(sizeof(struct fn_zone), GFP_KERNEL);
if (!fz)
return NULL;
- memset(fz, 0, sizeof(struct fn_zone));
if (z) {
fz->fz_divisor = 16;
} else {
table->fn_zones[i]->fz_next = fz;
}
table->fn_zones[z] = fz;
+ fib_hash_genid++;
write_unlock_bh(&fib_hash_lock);
return fz;
}
struct hlist_head *head;
struct hlist_node *node;
struct fib_node *f;
- u32 k = fz_key(flp->fl4_dst, fz);
+ __be32 k = fz_key(flp->fl4_dst, fz);
head = &fz->fz_hash[fn_hash(k, fz)];
hlist_for_each_entry(f, node, head, fn_hash) {
err = fib_semantic_match(&f->fn_alias,
flp, res,
+ f->fn_key, fz->fz_mask,
fz->fz_order);
if (err <= 0)
goto out;
static int fn_hash_last_dflt=-1;
-static int fib_detect_death(struct fib_info *fi, int order,
- struct fib_info **last_resort, int *last_idx)
-{
- struct neighbour *n;
- int state = NUD_NONE;
-
- n = neigh_lookup(&arp_tbl, &fi->fib_nh[0].nh_gw, fi->fib_dev);
- if (n) {
- state = n->nud_state;
- neigh_release(n);
- }
- if (state==NUD_REACHABLE)
- return 0;
- if ((state&NUD_VALID) && order != fn_hash_last_dflt)
- return 0;
- if ((state&NUD_VALID) ||
- (*last_idx<0 && order > fn_hash_last_dflt)) {
- *last_resort = fi;
- *last_idx = order;
- }
- return 1;
-}
-
static void
fn_hash_select_default(struct fib_table *tb, const struct flowi *flp, struct fib_result *res)
{
if (next_fi != res->fi)
break;
} else if (!fib_detect_death(fi, order, &last_resort,
- &last_idx)) {
+ &last_idx, &fn_hash_last_dflt)) {
if (res->fi)
fib_info_put(res->fi);
res->fi = fi;
goto out;
}
- if (!fib_detect_death(fi, order, &last_resort, &last_idx)) {
+ if (!fib_detect_death(fi, order, &last_resort, &last_idx, &fn_hash_last_dflt)) {
if (res->fi)
fib_info_put(res->fi);
res->fi = fi;
read_unlock(&fib_hash_lock);
}
-static void rtmsg_fib(int, struct fib_node *, struct fib_alias *,
- int, int,
- struct nlmsghdr *n,
- struct netlink_skb_parms *);
-
/* Insert node F to FZ. */
static inline void fib_insert_node(struct fn_zone *fz, struct fib_node *f)
{
}
/* Return the node in FZ matching KEY. */
-static struct fib_node *fib_find_node(struct fn_zone *fz, u32 key)
+static struct fib_node *fib_find_node(struct fn_zone *fz, __be32 key)
{
struct hlist_head *head = &fz->fz_hash[fn_hash(key, fz)];
struct hlist_node *node;
return NULL;
}
-/* Return the first fib alias matching TOS with
- * priority less than or equal to PRIO.
- */
-static struct fib_alias *fib_find_alias(struct fib_node *fn, u8 tos, u32 prio)
-{
- if (fn) {
- struct list_head *head = &fn->fn_alias;
- struct fib_alias *fa;
-
- list_for_each_entry(fa, head, fa_list) {
- if (fa->fa_tos > tos)
- continue;
- if (fa->fa_info->fib_priority >= prio ||
- fa->fa_tos < tos)
- return fa;
- }
- }
- return NULL;
-}
-
-static int
-fn_hash_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta,
- struct nlmsghdr *n, struct netlink_skb_parms *req)
+static int fn_hash_insert(struct fib_table *tb, struct fib_config *cfg)
{
struct fn_hash *table = (struct fn_hash *) tb->tb_data;
struct fib_node *new_f, *f;
struct fib_alias *fa, *new_fa;
struct fn_zone *fz;
struct fib_info *fi;
- int z = r->rtm_dst_len;
- int type = r->rtm_type;
- u8 tos = r->rtm_tos;
- u32 key;
+ u8 tos = cfg->fc_tos;
+ __be32 key;
int err;
- if (z > 32)
+ if (cfg->fc_dst_len > 32)
return -EINVAL;
- fz = table->fn_zones[z];
- if (!fz && !(fz = fn_new_zone(table, z)))
+
+ fz = table->fn_zones[cfg->fc_dst_len];
+ if (!fz && !(fz = fn_new_zone(table, cfg->fc_dst_len)))
return -ENOBUFS;
key = 0;
- if (rta->rta_dst) {
- u32 dst;
- memcpy(&dst, rta->rta_dst, 4);
- if (dst & ~FZ_MASK(fz))
+ if (cfg->fc_dst) {
+ if (cfg->fc_dst & ~FZ_MASK(fz))
return -EINVAL;
- key = fz_key(dst, fz);
+ key = fz_key(cfg->fc_dst, fz);
}
- if ((fi = fib_create_info(r, rta, n, &err)) == NULL)
- return err;
+ fi = fib_create_info(cfg);
+ if (IS_ERR(fi))
+ return PTR_ERR(fi);
if (fz->fz_nent > (fz->fz_divisor<<1) &&
fz->fz_divisor < FZ_MAX_DIVISOR &&
- (z==32 || (1<<z) > fz->fz_divisor))
+ (cfg->fc_dst_len == 32 ||
+ (1 << cfg->fc_dst_len) > fz->fz_divisor))
fn_rehash_zone(fz);
f = fib_find_node(fz, key);
- fa = fib_find_alias(f, tos, fi->fib_priority);
+
+ if (!f)
+ fa = NULL;
+ else
+ fa = fib_find_alias(&f->fn_alias, tos, fi->fib_priority);
/* Now fa, if non-NULL, points to the first fib alias
* with the same keys [prefix,tos,priority], if such key already
struct fib_alias *fa_orig;
err = -EEXIST;
- if (n->nlmsg_flags & NLM_F_EXCL)
+ if (cfg->fc_nlflags & NLM_F_EXCL)
goto out;
- if (n->nlmsg_flags & NLM_F_REPLACE) {
+ if (cfg->fc_nlflags & NLM_F_REPLACE) {
struct fib_info *fi_drop;
u8 state;
write_lock_bh(&fib_hash_lock);
fi_drop = fa->fa_info;
fa->fa_info = fi;
- fa->fa_type = type;
- fa->fa_scope = r->rtm_scope;
+ fa->fa_type = cfg->fc_type;
+ fa->fa_scope = cfg->fc_scope;
state = fa->fa_state;
fa->fa_state &= ~FA_S_ACCESSED;
+ fib_hash_genid++;
write_unlock_bh(&fib_hash_lock);
fib_release_info(fi_drop);
break;
if (fa->fa_info->fib_priority != fi->fib_priority)
break;
- if (fa->fa_type == type &&
- fa->fa_scope == r->rtm_scope &&
+ if (fa->fa_type == cfg->fc_type &&
+ fa->fa_scope == cfg->fc_scope &&
fa->fa_info == fi)
goto out;
}
- if (!(n->nlmsg_flags & NLM_F_APPEND))
+ if (!(cfg->fc_nlflags & NLM_F_APPEND))
fa = fa_orig;
}
err = -ENOENT;
- if (!(n->nlmsg_flags&NLM_F_CREATE))
+ if (!(cfg->fc_nlflags & NLM_F_CREATE))
goto out;
err = -ENOBUFS;
- new_fa = kmem_cache_alloc(fn_alias_kmem, SLAB_KERNEL);
+ new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL);
if (new_fa == NULL)
goto out;
new_f = NULL;
if (!f) {
- new_f = kmem_cache_alloc(fn_hash_kmem, SLAB_KERNEL);
+ new_f = kmem_cache_alloc(fn_hash_kmem, GFP_KERNEL);
if (new_f == NULL)
goto out_free_new_fa;
new_fa->fa_info = fi;
new_fa->fa_tos = tos;
- new_fa->fa_type = type;
- new_fa->fa_scope = r->rtm_scope;
+ new_fa->fa_type = cfg->fc_type;
+ new_fa->fa_scope = cfg->fc_scope;
new_fa->fa_state = 0;
/*
fib_insert_node(fz, new_f);
list_add_tail(&new_fa->fa_list,
(fa ? &fa->fa_list : &f->fn_alias));
+ fib_hash_genid++;
write_unlock_bh(&fib_hash_lock);
if (new_f)
fz->fz_nent++;
rt_cache_flush(-1);
- rtmsg_fib(RTM_NEWROUTE, f, new_fa, z, tb->tb_id, n, req);
+ rtmsg_fib(RTM_NEWROUTE, key, new_fa, cfg->fc_dst_len, tb->tb_id,
+ &cfg->fc_nlinfo);
return 0;
out_free_new_fa:
}
-static int
-fn_hash_delete(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta,
- struct nlmsghdr *n, struct netlink_skb_parms *req)
+static int fn_hash_delete(struct fib_table *tb, struct fib_config *cfg)
{
struct fn_hash *table = (struct fn_hash*)tb->tb_data;
struct fib_node *f;
struct fib_alias *fa, *fa_to_delete;
- int z = r->rtm_dst_len;
struct fn_zone *fz;
- u32 key;
- u8 tos = r->rtm_tos;
+ __be32 key;
- if (z > 32)
+ if (cfg->fc_dst_len > 32)
return -EINVAL;
- if ((fz = table->fn_zones[z]) == NULL)
+
+ if ((fz = table->fn_zones[cfg->fc_dst_len]) == NULL)
return -ESRCH;
key = 0;
- if (rta->rta_dst) {
- u32 dst;
- memcpy(&dst, rta->rta_dst, 4);
- if (dst & ~FZ_MASK(fz))
+ if (cfg->fc_dst) {
+ if (cfg->fc_dst & ~FZ_MASK(fz))
return -EINVAL;
- key = fz_key(dst, fz);
+ key = fz_key(cfg->fc_dst, fz);
}
f = fib_find_node(fz, key);
- fa = fib_find_alias(f, tos, 0);
+
+ if (!f)
+ fa = NULL;
+ else
+ fa = fib_find_alias(&f->fn_alias, cfg->fc_tos, 0);
if (!fa)
return -ESRCH;
list_for_each_entry_continue(fa, &f->fn_alias, fa_list) {
struct fib_info *fi = fa->fa_info;
- if (fa->fa_tos != tos)
+ if (fa->fa_tos != cfg->fc_tos)
break;
- if ((!r->rtm_type ||
- fa->fa_type == r->rtm_type) &&
- (r->rtm_scope == RT_SCOPE_NOWHERE ||
- fa->fa_scope == r->rtm_scope) &&
- (!r->rtm_protocol ||
- fi->fib_protocol == r->rtm_protocol) &&
- fib_nh_match(r, n, rta, fi) == 0) {
+ if ((!cfg->fc_type ||
+ fa->fa_type == cfg->fc_type) &&
+ (cfg->fc_scope == RT_SCOPE_NOWHERE ||
+ fa->fa_scope == cfg->fc_scope) &&
+ (!cfg->fc_protocol ||
+ fi->fib_protocol == cfg->fc_protocol) &&
+ fib_nh_match(cfg, fi) == 0) {
fa_to_delete = fa;
break;
}
int kill_fn;
fa = fa_to_delete;
- rtmsg_fib(RTM_DELROUTE, f, fa, z, tb->tb_id, n, req);
+ rtmsg_fib(RTM_DELROUTE, key, fa, cfg->fc_dst_len,
+ tb->tb_id, &cfg->fc_nlinfo);
kill_fn = 0;
write_lock_bh(&fib_hash_lock);
hlist_del(&f->fn_hash);
kill_fn = 1;
}
+ fib_hash_genid++;
write_unlock_bh(&fib_hash_lock);
if (fa->fa_state & FA_S_ACCESSED)
hlist_del(&f->fn_hash);
kill_f = 1;
}
+ fib_hash_genid++;
write_unlock_bh(&fib_hash_lock);
fn_free_alias(fa);
struct fib_node *f;
int i, s_i;
- s_i = cb->args[3];
+ s_i = cb->args[4];
i = 0;
hlist_for_each_entry(f, node, head, fn_hash) {
struct fib_alias *fa;
list_for_each_entry(fa, &f->fn_alias, fa_list) {
if (i < s_i)
- continue;
+ goto next;
if (fib_dump_info(skb, NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq,
tb->tb_id,
fa->fa_type,
fa->fa_scope,
- &f->fn_key,
+ f->fn_key,
fz->fz_order,
fa->fa_tos,
- fa->fa_info) < 0) {
- cb->args[3] = i;
+ fa->fa_info,
+ NLM_F_MULTI) < 0) {
+ cb->args[4] = i;
return -1;
}
-
+ next:
i++;
}
}
- cb->args[3] = i;
+ cb->args[4] = i;
return skb->len;
}
{
int h, s_h;
- s_h = cb->args[2];
+ s_h = cb->args[3];
for (h=0; h < fz->fz_divisor; h++) {
if (h < s_h) continue;
if (h > s_h)
- memset(&cb->args[3], 0,
- sizeof(cb->args) - 3*sizeof(cb->args[0]));
+ memset(&cb->args[4], 0,
+ sizeof(cb->args) - 4*sizeof(cb->args[0]));
if (fz->fz_hash == NULL ||
hlist_empty(&fz->fz_hash[h]))
continue;
if (fn_hash_dump_bucket(skb, cb, tb, fz, &fz->fz_hash[h])<0) {
- cb->args[2] = h;
+ cb->args[3] = h;
return -1;
}
}
- cb->args[2] = h;
+ cb->args[3] = h;
return skb->len;
}
struct fn_zone *fz;
struct fn_hash *table = (struct fn_hash*)tb->tb_data;
- s_m = cb->args[1];
+ s_m = cb->args[2];
read_lock(&fib_hash_lock);
for (fz = table->fn_zone_list, m=0; fz; fz = fz->fz_next, m++) {
if (m < s_m) continue;
if (m > s_m)
- memset(&cb->args[2], 0,
- sizeof(cb->args) - 2*sizeof(cb->args[0]));
+ memset(&cb->args[3], 0,
+ sizeof(cb->args) - 3*sizeof(cb->args[0]));
if (fn_hash_dump_zone(skb, cb, tb, fz) < 0) {
- cb->args[1] = m;
+ cb->args[2] = m;
read_unlock(&fib_hash_lock);
return -1;
}
}
read_unlock(&fib_hash_lock);
- cb->args[1] = m;
+ cb->args[2] = m;
return skb->len;
}
-static void rtmsg_fib(int event, struct fib_node *f, struct fib_alias *fa,
- int z, int tb_id,
- struct nlmsghdr *n, struct netlink_skb_parms *req)
-{
- struct sk_buff *skb;
- u32 pid = req ? req->pid : 0;
- int size = NLMSG_SPACE(sizeof(struct rtmsg)+256);
-
- skb = alloc_skb(size, GFP_KERNEL);
- if (!skb)
- return;
-
- if (fib_dump_info(skb, pid, n->nlmsg_seq, event, tb_id,
- fa->fa_type, fa->fa_scope, &f->fn_key, z,
- fa->fa_tos,
- fa->fa_info) < 0) {
- kfree_skb(skb);
- return;
- }
- NETLINK_CB(skb).dst_groups = RTMGRP_IPV4_ROUTE;
- if (n->nlmsg_flags&NLM_F_ECHO)
- atomic_inc(&skb->users);
- netlink_broadcast(rtnl, skb, pid, RTMGRP_IPV4_ROUTE, GFP_KERNEL);
- if (n->nlmsg_flags&NLM_F_ECHO)
- netlink_unicast(rtnl, skb, pid, MSG_DONTWAIT);
-}
-
#ifdef CONFIG_IP_MULTIPLE_TABLES
-struct fib_table * fib_hash_init(int id)
+struct fib_table * fib_hash_init(u32 id)
#else
-struct fib_table * __init fib_hash_init(int id)
+struct fib_table * __init fib_hash_init(u32 id)
#endif
{
struct fib_table *tb;
struct hlist_head *hash_head;
struct fib_node *fn;
struct fib_alias *fa;
+ loff_t pos;
+ unsigned int genid;
+ int valid;
};
static struct fib_alias *fib_get_first(struct seq_file *seq)
iter->hash_head = NULL;
iter->fn = NULL;
iter->fa = NULL;
+ iter->pos = 0;
+ iter->genid = fib_hash_genid;
+ iter->valid = 1;
for (iter->zone = table->fn_zone_list; iter->zone;
iter->zone = iter->zone->fz_next) {
}
}
out:
+ iter->pos++;
return fa;
}
+static struct fib_alias *fib_get_idx(struct seq_file *seq, loff_t pos)
+{
+ struct fib_iter_state *iter = seq->private;
+ struct fib_alias *fa;
+
+ if (iter->valid && pos >= iter->pos && iter->genid == fib_hash_genid) {
+ fa = iter->fa;
+ pos -= iter->pos;
+ } else
+ fa = fib_get_first(seq);
+
+ if (fa)
+ while (pos && (fa = fib_get_next(seq)))
+ --pos;
+ return pos ? NULL : fa;
+}
+
static void *fib_seq_start(struct seq_file *seq, loff_t *pos)
{
void *v = NULL;
read_lock(&fib_hash_lock);
if (ip_fib_main_table)
- v = *pos ? fib_get_next(seq) : SEQ_START_TOKEN;
+ v = *pos ? fib_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
return v;
}
read_unlock(&fib_hash_lock);
}
-static unsigned fib_flag_trans(int type, u32 mask, struct fib_info *fi)
+static unsigned fib_flag_trans(int type, __be32 mask, struct fib_info *fi)
{
- static unsigned type2flags[RTN_MAX + 1] = {
+ static const unsigned type2flags[RTN_MAX + 1] = {
[7] = RTF_REJECT, [8] = RTF_REJECT,
};
unsigned flags = type2flags[type];
if (fi && fi->fib_nh->nh_gw)
flags |= RTF_GATEWAY;
- if (mask == 0xFFFFFFFF)
+ if (mask == htonl(0xFFFFFFFF))
flags |= RTF_HOST;
flags |= RTF_UP;
return flags;
{
struct fib_iter_state *iter;
char bf[128];
- u32 prefix, mask;
+ __be32 prefix, mask;
unsigned flags;
struct fib_node *f;
struct fib_alias *fa;
{
struct seq_file *seq;
int rc = -ENOMEM;
- struct fib_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL);
+ struct fib_iter_state *s = kzalloc(sizeof(*s), GFP_KERNEL);
if (!s)
goto out;
seq = file->private_data;
seq->private = s;
- memset(s, 0, sizeof(*s));
out:
return rc;
out_kfree: