*
* IPv4 FIB: lookup engine and maintenance routines.
*
- * Version: $Id: fib_hash.c,v 1.13 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 <linux/bitops.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/skbuff.h>
#include <linux/netlink.h>
#include <linux/init.h>
+#include <linux/slab.h>
+#include <net/net_namespace.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
struct hlist_node fn_hash;
struct list_head fn_alias;
__be32 fn_key;
+ struct fib_alias fn_embedded_alias;
};
struct fn_zone {
unsigned long size = divisor * sizeof(struct hlist_head);
if (size <= PAGE_SIZE) {
- return kmalloc(size, GFP_KERNEL);
+ return kzalloc(size, GFP_KERNEL);
} else {
return (struct hlist_head *)
- __get_free_pages(GFP_KERNEL, get_order(size));
+ __get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(size));
}
}
struct hlist_head *ht, *old_ht;
int old_divisor, new_divisor;
u32 new_hashmask;
-
+
old_divisor = fz->fz_divisor;
switch (old_divisor) {
new_hashmask = (new_divisor - 1);
#if RT_CACHE_DEBUG >= 2
- printk("fn_rehash_zone: hash for zone %d grows from %d\n", fz->fz_order, old_divisor);
+ printk(KERN_DEBUG "fn_rehash_zone: hash for zone %d grows from %d\n",
+ fz->fz_order, old_divisor);
#endif
ht = fz_hash_alloc(new_divisor);
if (ht) {
- memset(ht, 0, new_divisor * sizeof(struct hlist_head));
-
write_lock_bh(&fib_hash_lock);
old_ht = fz->fz_hash;
fz->fz_hash = ht;
kmem_cache_free(fn_hash_kmem, f);
}
-static inline void fn_free_alias(struct fib_alias *fa)
+static inline void fn_free_alias(struct fib_alias *fa, struct fib_node *f)
{
fib_release_info(fa->fa_info);
- kmem_cache_free(fn_alias_kmem, fa);
+ if (fa == &f->fn_embedded_alias)
+ fa->fa_info = NULL;
+ else
+ kmem_cache_free(fn_alias_kmem, fa);
}
static struct fn_zone *
kfree(fz);
return NULL;
}
- memset(fz->fz_hash, 0, fz->fz_divisor * sizeof(struct hlist_head *));
fz->fz_order = z;
fz->fz_mask = inet_make_mask(z);
return fz;
}
-static int
-fn_hash_lookup(struct fib_table *tb, const struct flowi *flp, struct fib_result *res)
+int fib_table_lookup(struct fib_table *tb,
+ const struct flowi *flp, struct fib_result *res)
{
int err;
struct fn_zone *fz;
- struct fn_hash *t = (struct fn_hash*)tb->tb_data;
+ struct fn_hash *t = (struct fn_hash *)tb->tb_data;
read_lock(&fib_hash_lock);
for (fz = t->fn_zone_list; fz; fz = fz->fz_next) {
err = fib_semantic_match(&f->fn_alias,
flp, res,
- f->fn_key, fz->fz_mask,
fz->fz_order);
if (err <= 0)
goto out;
return err;
}
-static int fn_hash_last_dflt=-1;
-
-static void
-fn_hash_select_default(struct fib_table *tb, const struct flowi *flp, struct fib_result *res)
+void fib_table_select_default(struct fib_table *tb,
+ const struct flowi *flp, struct fib_result *res)
{
int order, last_idx;
struct hlist_node *node;
struct fib_node *f;
struct fib_info *fi = NULL;
struct fib_info *last_resort;
- struct fn_hash *t = (struct fn_hash*)tb->tb_data;
+ struct fn_hash *t = (struct fn_hash *)tb->tb_data;
struct fn_zone *fz = t->fn_zones[0];
if (fz == NULL)
if (next_fi != res->fi)
break;
} else 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;
- atomic_inc(&fi->fib_clntref);
- fn_hash_last_dflt = order;
+ &last_idx, tb->tb_default)) {
+ fib_result_assign(res, fi);
+ tb->tb_default = order;
goto out;
}
fi = next_fi;
}
if (order <= 0 || fi == NULL) {
- fn_hash_last_dflt = -1;
+ tb->tb_default = -1;
goto out;
}
- 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;
- atomic_inc(&fi->fib_clntref);
- fn_hash_last_dflt = order;
+ if (!fib_detect_death(fi, order, &last_resort, &last_idx,
+ tb->tb_default)) {
+ fib_result_assign(res, fi);
+ tb->tb_default = order;
goto out;
}
- if (last_idx >= 0) {
- if (res->fi)
- fib_info_put(res->fi);
- res->fi = last_resort;
- if (last_resort)
- atomic_inc(&last_resort->fib_clntref);
- }
- fn_hash_last_dflt = last_idx;
+ if (last_idx >= 0)
+ fib_result_assign(res, last_resort);
+ tb->tb_default = last_idx;
out:
read_unlock(&fib_hash_lock);
}
return NULL;
}
-static int fn_hash_insert(struct fib_table *tb, struct fib_config *cfg)
+int fib_table_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_node *new_f = NULL;
+ struct fib_node *f;
struct fib_alias *fa, *new_fa;
struct fn_zone *fz;
struct fib_info *fi;
if (fa && fa->fa_tos == tos &&
fa->fa_info->fib_priority == fi->fib_priority) {
- struct fib_alias *fa_orig;
+ struct fib_alias *fa_first, *fa_match;
err = -EEXIST;
if (cfg->fc_nlflags & NLM_F_EXCL)
goto out;
+ /* We have 2 goals:
+ * 1. Find exact match for type, scope, fib_info to avoid
+ * duplicate routes
+ * 2. Find next 'fa' (or head), NLM_F_APPEND inserts before it
+ */
+ fa_match = NULL;
+ fa_first = fa;
+ fa = list_entry(fa->fa_list.prev, struct fib_alias, fa_list);
+ list_for_each_entry_continue(fa, &f->fn_alias, fa_list) {
+ if (fa->fa_tos != tos)
+ break;
+ if (fa->fa_info->fib_priority != fi->fib_priority)
+ break;
+ if (fa->fa_type == cfg->fc_type &&
+ fa->fa_scope == cfg->fc_scope &&
+ fa->fa_info == fi) {
+ fa_match = fa;
+ break;
+ }
+ }
+
if (cfg->fc_nlflags & NLM_F_REPLACE) {
struct fib_info *fi_drop;
u8 state;
+ fa = fa_first;
+ if (fa_match) {
+ if (fa == fa_match)
+ err = 0;
+ goto out;
+ }
write_lock_bh(&fib_hash_lock);
fi_drop = fa->fa_info;
fa->fa_info = fi;
fib_release_info(fi_drop);
if (state & FA_S_ACCESSED)
- rt_cache_flush(-1);
+ rt_cache_flush(cfg->fc_nlinfo.nl_net, -1);
+ rtmsg_fib(RTM_NEWROUTE, key, fa, cfg->fc_dst_len, tb->tb_id,
+ &cfg->fc_nlinfo, NLM_F_REPLACE);
return 0;
}
* uses the same scope, type, and nexthop
* information.
*/
- fa_orig = fa;
- fa = list_entry(fa->fa_list.prev, struct fib_alias, fa_list);
- list_for_each_entry_continue(fa, &f->fn_alias, fa_list) {
- if (fa->fa_tos != tos)
- break;
- if (fa->fa_info->fib_priority != fi->fib_priority)
- break;
- if (fa->fa_type == cfg->fc_type &&
- fa->fa_scope == cfg->fc_scope &&
- fa->fa_info == fi)
- goto out;
- }
+ if (fa_match)
+ goto out;
+
if (!(cfg->fc_nlflags & NLM_F_APPEND))
- fa = fa_orig;
+ fa = fa_first;
}
err = -ENOENT;
goto out;
err = -ENOBUFS;
- 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, GFP_KERNEL);
+ new_f = kmem_cache_zalloc(fn_hash_kmem, GFP_KERNEL);
if (new_f == NULL)
- goto out_free_new_fa;
+ goto out;
INIT_HLIST_NODE(&new_f->fn_hash);
INIT_LIST_HEAD(&new_f->fn_alias);
f = new_f;
}
+ new_fa = &f->fn_embedded_alias;
+ if (new_fa->fa_info != NULL) {
+ new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL);
+ if (new_fa == NULL)
+ goto out;
+ }
new_fa->fa_info = fi;
new_fa->fa_tos = tos;
new_fa->fa_type = cfg->fc_type;
if (new_f)
fz->fz_nent++;
- rt_cache_flush(-1);
+ rt_cache_flush(cfg->fc_nlinfo.nl_net, -1);
rtmsg_fib(RTM_NEWROUTE, key, new_fa, cfg->fc_dst_len, tb->tb_id,
- &cfg->fc_nlinfo);
+ &cfg->fc_nlinfo, 0);
return 0;
-out_free_new_fa:
- kmem_cache_free(fn_alias_kmem, new_fa);
out:
+ if (new_f)
+ kmem_cache_free(fn_hash_kmem, new_f);
fib_release_info(fi);
return err;
}
-
-static int fn_hash_delete(struct fib_table *tb, struct fib_config *cfg)
+int fib_table_delete(struct fib_table *tb, struct fib_config *cfg)
{
- struct fn_hash *table = (struct fn_hash*)tb->tb_data;
+ struct fn_hash *table = (struct fn_hash *)tb->tb_data;
struct fib_node *f;
struct fib_alias *fa, *fa_to_delete;
struct fn_zone *fz;
fa = fa_to_delete;
rtmsg_fib(RTM_DELROUTE, key, fa, cfg->fc_dst_len,
- tb->tb_id, &cfg->fc_nlinfo);
+ tb->tb_id, &cfg->fc_nlinfo, 0);
kill_fn = 0;
write_lock_bh(&fib_hash_lock);
write_unlock_bh(&fib_hash_lock);
if (fa->fa_state & FA_S_ACCESSED)
- rt_cache_flush(-1);
- fn_free_alias(fa);
+ rt_cache_flush(cfg->fc_nlinfo.nl_net, -1);
+ fn_free_alias(fa, f);
if (kill_fn) {
fn_free_node(f);
fz->fz_nent--;
fib_hash_genid++;
write_unlock_bh(&fib_hash_lock);
- fn_free_alias(fa);
+ fn_free_alias(fa, f);
found++;
}
}
return found;
}
-static int fn_hash_flush(struct fib_table *tb)
+int fib_table_flush(struct fib_table *tb)
{
struct fn_hash *table = (struct fn_hash *) tb->tb_data;
struct fn_zone *fz;
{
int h, s_h;
+ if (fz->fz_hash == NULL)
+ return skb->len;
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[4], 0,
- sizeof(cb->args) - 4*sizeof(cb->args[0]));
- if (fz->fz_hash == NULL ||
- hlist_empty(&fz->fz_hash[h]))
+ for (h = s_h; h < fz->fz_divisor; h++) {
+ if (hlist_empty(&fz->fz_hash[h]))
continue;
- if (fn_hash_dump_bucket(skb, cb, tb, fz, &fz->fz_hash[h])<0) {
+ if (fn_hash_dump_bucket(skb, cb, tb, fz, &fz->fz_hash[h]) < 0) {
cb->args[3] = h;
return -1;
}
+ memset(&cb->args[4], 0,
+ sizeof(cb->args) - 4*sizeof(cb->args[0]));
}
cb->args[3] = h;
return skb->len;
}
-static int fn_hash_dump(struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb)
+int fib_table_dump(struct fib_table *tb, struct sk_buff *skb,
+ struct netlink_callback *cb)
{
int m, s_m;
struct fn_zone *fz;
- struct fn_hash *table = (struct fn_hash*)tb->tb_data;
+ struct fn_hash *table = (struct fn_hash *)tb->tb_data;
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[3], 0,
- sizeof(cb->args) - 3*sizeof(cb->args[0]));
if (fn_hash_dump_zone(skb, cb, tb, fz) < 0) {
cb->args[2] = m;
read_unlock(&fib_hash_lock);
return -1;
}
+ memset(&cb->args[3], 0,
+ sizeof(cb->args) - 3*sizeof(cb->args[0]));
}
read_unlock(&fib_hash_lock);
cb->args[2] = m;
return skb->len;
}
-#ifdef CONFIG_IP_MULTIPLE_TABLES
-struct fib_table * fib_hash_init(u32 id)
-#else
-struct fib_table * __init fib_hash_init(u32 id)
-#endif
+void __init fib_hash_init(void)
{
- struct fib_table *tb;
+ fn_hash_kmem = kmem_cache_create("ip_fib_hash", sizeof(struct fib_node),
+ 0, SLAB_PANIC, NULL);
- if (fn_hash_kmem == NULL)
- fn_hash_kmem = kmem_cache_create("ip_fib_hash",
- sizeof(struct fib_node),
- 0, SLAB_HWCACHE_ALIGN,
- NULL, NULL);
+ fn_alias_kmem = kmem_cache_create("ip_fib_alias", sizeof(struct fib_alias),
+ 0, SLAB_PANIC, NULL);
- if (fn_alias_kmem == NULL)
- fn_alias_kmem = kmem_cache_create("ip_fib_alias",
- sizeof(struct fib_alias),
- 0, SLAB_HWCACHE_ALIGN,
- NULL, NULL);
+}
+
+struct fib_table *fib_hash_table(u32 id)
+{
+ struct fib_table *tb;
tb = kmalloc(sizeof(struct fib_table) + sizeof(struct fn_hash),
GFP_KERNEL);
return NULL;
tb->tb_id = id;
- tb->tb_lookup = fn_hash_lookup;
- tb->tb_insert = fn_hash_insert;
- tb->tb_delete = fn_hash_delete;
- tb->tb_flush = fn_hash_flush;
- tb->tb_select_default = fn_hash_select_default;
- tb->tb_dump = fn_hash_dump;
+ tb->tb_default = -1;
+
memset(tb->tb_data, 0, sizeof(struct fn_hash));
return tb;
}
#ifdef CONFIG_PROC_FS
struct fib_iter_state {
+ struct seq_net_private p;
struct fn_zone *zone;
int bucket;
struct hlist_head *hash_head;
static struct fib_alias *fib_get_first(struct seq_file *seq)
{
struct fib_iter_state *iter = seq->private;
- struct fn_hash *table = (struct fn_hash *) ip_fib_main_table->tb_data;
+ struct fib_table *main_table;
+ struct fn_hash *table;
+
+ main_table = fib_get_table(seq_file_net(seq), RT_TABLE_MAIN);
+ table = (struct fn_hash *)main_table->tb_data;
iter->bucket = 0;
iter->hash_head = NULL;
struct hlist_node *node;
struct fib_node *fn;
- hlist_for_each_entry(fn,node,iter->hash_head,fn_hash) {
+ hlist_for_each_entry(fn, node, iter->hash_head, fn_hash) {
struct fib_alias *fa;
- list_for_each_entry(fa,&fn->fn_alias,fa_list) {
+ list_for_each_entry(fa, &fn->fn_alias, fa_list) {
iter->fn = fn;
iter->fa = fa;
goto out;
if (!iter->zone)
goto out;
-
+
iter->bucket = 0;
iter->hash_head = iter->zone->fz_hash;
{
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;
}
static void *fib_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(fib_hash_lock)
{
void *v = NULL;
read_lock(&fib_hash_lock);
- if (ip_fib_main_table)
+ if (fib_get_table(seq_file_net(seq), RT_TABLE_MAIN))
v = *pos ? fib_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
return v;
}
}
static void fib_seq_stop(struct seq_file *seq, void *v)
+ __releases(fib_hash_lock)
{
read_unlock(&fib_hash_lock);
}
return flags;
}
-/*
+/*
* This outputs /proc/net/route.
*
* It always works in backward compatibility mode.
static int fib_seq_show(struct seq_file *seq, void *v)
{
struct fib_iter_state *iter;
- char bf[128];
+ int len;
__be32 prefix, mask;
unsigned flags;
struct fib_node *f;
mask = FZ_MASK(iter->zone);
flags = fib_flag_trans(fa->fa_type, mask, fi);
if (fi)
- snprintf(bf, sizeof(bf),
- "%s\t%08X\t%08X\t%04X\t%d\t%u\t%d\t%08X\t%d\t%u\t%u",
+ seq_printf(seq,
+ "%s\t%08X\t%08X\t%04X\t%d\t%u\t%d\t%08X\t%d\t%u\t%u%n",
fi->fib_dev ? fi->fib_dev->name : "*", prefix,
fi->fib_nh->nh_gw, flags, 0, 0, fi->fib_priority,
mask, (fi->fib_advmss ? fi->fib_advmss + 40 : 0),
fi->fib_window,
- fi->fib_rtt >> 3);
+ fi->fib_rtt >> 3, &len);
else
- snprintf(bf, sizeof(bf),
- "*\t%08X\t%08X\t%04X\t%d\t%u\t%d\t%08X\t%d\t%u\t%u",
- prefix, 0, flags, 0, 0, 0, mask, 0, 0, 0);
- seq_printf(seq, "%-127s\n", bf);
+ seq_printf(seq,
+ "*\t%08X\t%08X\t%04X\t%d\t%u\t%d\t%08X\t%d\t%u\t%u%n",
+ prefix, 0, flags, 0, 0, 0, mask, 0, 0, 0, &len);
+
+ seq_printf(seq, "%*s\n", 127 - len, "");
out:
return 0;
}
-static struct seq_operations fib_seq_ops = {
+static const struct seq_operations fib_seq_ops = {
.start = fib_seq_start,
.next = fib_seq_next,
.stop = fib_seq_stop,
static int fib_seq_open(struct inode *inode, struct file *file)
{
- struct seq_file *seq;
- int rc = -ENOMEM;
- struct fib_iter_state *s = kzalloc(sizeof(*s), GFP_KERNEL);
-
- if (!s)
- goto out;
-
- rc = seq_open(file, &fib_seq_ops);
- if (rc)
- goto out_kfree;
-
- seq = file->private_data;
- seq->private = s;
-out:
- return rc;
-out_kfree:
- kfree(s);
- goto out;
+ return seq_open_net(inode, file, &fib_seq_ops,
+ sizeof(struct fib_iter_state));
}
-static struct file_operations fib_seq_fops = {
+static const struct file_operations fib_seq_fops = {
.owner = THIS_MODULE,
.open = fib_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = seq_release_net,
};
-int __init fib_proc_init(void)
+int __net_init fib_proc_init(struct net *net)
{
- if (!proc_net_fops_create("route", S_IRUGO, &fib_seq_fops))
+ if (!proc_net_fops_create(net, "route", S_IRUGO, &fib_seq_fops))
return -ENOMEM;
return 0;
}
-void __init fib_proc_exit(void)
+void __net_exit fib_proc_exit(struct net *net)
{
- proc_net_remove("route");
+ proc_net_remove(net, "route");
}
#endif /* CONFIG_PROC_FS */
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff