/*
- * Linux INET6 implementation
+ * Linux INET6 implementation
* Forwarding Information Database
*
* Authors:
- * Pedro Roque <roque@di.fc.ul.pt>
- *
- * $Id: ip6_fib.c,v 1.25 2001/10/31 21:55:55 davem Exp $
+ * Pedro Roque <roque@di.fc.ul.pt>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* Yuji SEKIYA @USAGI: Support default route on router node;
* remove ip6_null_entry from the top of
* routing table.
+ * Ville Nuorvala: Fixed routing subtrees.
*/
#include <linux/errno.h>
#include <linux/types.h>
#define RT6_TRACE(x...) do { ; } while (0)
#endif
-struct rt6_statistics rt6_stats;
-
-static kmem_cache_t * fib6_node_kmem __read_mostly;
+static struct kmem_cache * fib6_node_kmem __read_mostly;
enum fib_walk_state_t
{
struct fib6_cleaner_t
{
struct fib6_walker_t w;
+ struct net *net;
int (*func)(struct rt6_info *, void *arg);
void *arg;
};
#ifdef CONFIG_IPV6_SUBTREES
#define FWS_INIT FWS_S
-#define SUBTREE(fn) ((fn)->subtree)
#else
#define FWS_INIT FWS_L
-#define SUBTREE(fn) NULL
#endif
-static void fib6_prune_clones(struct fib6_node *fn, struct rt6_info *rt);
-static struct rt6_info * fib6_find_prefix(struct fib6_node *fn);
-static struct fib6_node * fib6_repair_tree(struct fib6_node *fn);
+static void fib6_prune_clones(struct net *net, struct fib6_node *fn,
+ struct rt6_info *rt);
+static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn);
+static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn);
static int fib6_walk(struct fib6_walker_t *w);
static int fib6_walk_continue(struct fib6_walker_t *w);
static __u32 rt_sernum;
-static DEFINE_TIMER(ip6_fib_timer, fib6_run_gc, 0, 0);
+static void fib6_gc_timer_cb(unsigned long arg);
static struct fib6_walker_t fib6_walker_list = {
.prev = &fib6_walker_list,
- .next = &fib6_walker_list,
+ .next = &fib6_walker_list,
};
#define FOR_WALKERS(w) for ((w)=fib6_walker_list.next; (w) != &fib6_walker_list; (w)=(w)->next)
/*
* Auxiliary address test functions for the radix tree.
*
- * These assume a 32bit processor (although it will work on
+ * These assume a 32bit processor (although it will work on
* 64bit processors)
*/
* test bit
*/
-static __inline__ int addr_bit_set(void *token, int fn_bit)
+static __inline__ __be32 addr_bit_set(void *token, int fn_bit)
{
- __u32 *addr = token;
+ __be32 *addr = token;
return htonl(1 << ((~fn_bit)&0x1F)) & addr[fn_bit>>5];
}
{
struct fib6_node *fn;
- if ((fn = kmem_cache_alloc(fib6_node_kmem, SLAB_ATOMIC)) != NULL)
- memset(fn, 0, sizeof(struct fib6_node));
+ fn = kmem_cache_zalloc(fib6_node_kmem, GFP_ATOMIC);
return fn;
}
dst_free(&rt->u.dst);
}
-static struct fib6_table fib6_main_tbl = {
- .tb6_id = RT6_TABLE_MAIN,
- .tb6_lock = RW_LOCK_UNLOCKED,
- .tb6_root = {
- .leaf = &ip6_null_entry,
- .fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO,
- },
-};
-
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
#define FIB_TABLE_HASHSZ 256
#else
#define FIB_TABLE_HASHSZ 1
#endif
-static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ];
-static void fib6_link_table(struct fib6_table *tb)
+static void fib6_link_table(struct net *net, struct fib6_table *tb)
{
unsigned int h;
+ /*
+ * Initialize table lock at a single place to give lockdep a key,
+ * tables aren't visible prior to being linked to the list.
+ */
+ rwlock_init(&tb->tb6_lock);
+
h = tb->tb6_id & (FIB_TABLE_HASHSZ - 1);
/*
* No protection necessary, this is the only list mutatation
* operation, tables never disappear once they exist.
*/
- hlist_add_head_rcu(&tb->tb6_hlist, &fib_table_hash[h]);
+ hlist_add_head_rcu(&tb->tb6_hlist, &net->ipv6.fib_table_hash[h]);
}
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
-static struct fib6_table fib6_local_tbl = {
- .tb6_id = RT6_TABLE_LOCAL,
- .tb6_lock = RW_LOCK_UNLOCKED,
- .tb6_root = {
- .leaf = &ip6_null_entry,
- .fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO,
- },
-};
-static struct fib6_table *fib6_alloc_table(u32 id)
+static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
{
struct fib6_table *table;
table = kzalloc(sizeof(*table), GFP_ATOMIC);
if (table != NULL) {
table->tb6_id = id;
- table->tb6_lock = RW_LOCK_UNLOCKED;
- table->tb6_root.leaf = &ip6_null_entry;
+ table->tb6_root.leaf = net->ipv6.ip6_null_entry;
table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
}
return table;
}
-struct fib6_table *fib6_new_table(u32 id)
+struct fib6_table *fib6_new_table(struct net *net, u32 id)
{
struct fib6_table *tb;
if (id == 0)
id = RT6_TABLE_MAIN;
- tb = fib6_get_table(id);
+ tb = fib6_get_table(net, id);
if (tb)
return tb;
- tb = fib6_alloc_table(id);
+ tb = fib6_alloc_table(net, id);
if (tb != NULL)
- fib6_link_table(tb);
+ fib6_link_table(net, tb);
return tb;
}
-struct fib6_table *fib6_get_table(u32 id)
+struct fib6_table *fib6_get_table(struct net *net, u32 id)
{
struct fib6_table *tb;
+ struct hlist_head *head;
struct hlist_node *node;
unsigned int h;
id = RT6_TABLE_MAIN;
h = id & (FIB_TABLE_HASHSZ - 1);
rcu_read_lock();
- hlist_for_each_entry_rcu(tb, node, &fib_table_hash[h], tb6_hlist) {
+ head = &net->ipv6.fib_table_hash[h];
+ hlist_for_each_entry_rcu(tb, node, head, tb6_hlist) {
if (tb->tb6_id == id) {
rcu_read_unlock();
return tb;
return NULL;
}
-static void __init fib6_tables_init(void)
+static void fib6_tables_init(struct net *net)
{
- fib6_link_table(&fib6_main_tbl);
- fib6_link_table(&fib6_local_tbl);
+ fib6_link_table(net, net->ipv6.fib6_main_tbl);
+ fib6_link_table(net, net->ipv6.fib6_local_tbl);
}
-
#else
-struct fib6_table *fib6_new_table(u32 id)
+struct fib6_table *fib6_new_table(struct net *net, u32 id)
{
- return fib6_get_table(id);
+ return fib6_get_table(net, id);
}
-struct fib6_table *fib6_get_table(u32 id)
+struct fib6_table *fib6_get_table(struct net *net, u32 id)
{
- return &fib6_main_tbl;
+ return net->ipv6.fib6_main_tbl;
}
-struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags,
- pol_lookup_t lookup)
+struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl,
+ int flags, pol_lookup_t lookup)
{
- return (struct dst_entry *) lookup(&fib6_main_tbl, fl, flags);
+ return (struct dst_entry *) lookup(net, net->ipv6.fib6_main_tbl, fl, flags);
}
-static void __init fib6_tables_init(void)
+static void fib6_tables_init(struct net *net)
{
- fib6_link_table(&fib6_main_tbl);
+ fib6_link_table(net, net->ipv6.fib6_main_tbl);
}
#endif
int res;
struct rt6_info *rt;
- for (rt = w->leaf; rt; rt = rt->u.next) {
+ for (rt = w->leaf; rt; rt = rt->u.dst.rt6_next) {
res = rt6_dump_route(rt, w->args);
if (res < 0) {
/* Frame is full, suspend walking */
return res;
}
-int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
+static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
{
+ struct net *net = sock_net(skb->sk);
unsigned int h, s_h;
unsigned int e = 0, s_e;
struct rt6_rtnl_dump_arg arg;
struct fib6_walker_t *w;
struct fib6_table *tb;
struct hlist_node *node;
+ struct hlist_head *head;
int res = 0;
s_h = cb->args[0];
for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) {
e = 0;
- hlist_for_each_entry(tb, node, &fib_table_hash[h], tb6_hlist) {
+ head = &net->ipv6.fib_table_hash[h];
+ hlist_for_each_entry(tb, node, head, tb6_hlist) {
if (e < s_e)
goto next;
res = fib6_dump_table(tb, skb, cb);
struct fib6_node *pn = NULL;
struct rt6key *key;
int bit;
- int dir = 0;
+ __be32 dir = 0;
__u32 sernum = fib6_new_sernum();
RT6_TRACE("fib6_add_1\n");
if (plen < fn->fn_bit ||
!ipv6_prefix_equal(&key->addr, addr, fn->fn_bit))
goto insert_above;
-
+
/*
* Exact match ?
*/
-
+
if (plen == fn->fn_bit) {
/* clean up an intermediate node */
if ((fn->fn_flags & RTN_RTINFO) == 0) {
rt6_release(fn->leaf);
fn->leaf = NULL;
}
-
+
fn->fn_sernum = sernum;
-
+
return fn;
}
/*
* We have more bits to go
*/
-
+
/* Try to walk down on tree. */
fn->fn_sernum = sernum;
dir = addr_bit_set(addr, fn->fn_bit);
if (ln == NULL)
return NULL;
ln->fn_bit = plen;
-
+
ln->parent = pn;
ln->fn_sernum = sernum;
insert_above:
/*
- * split since we don't have a common prefix anymore or
+ * split since we don't have a common prefix anymore or
* we have a less significant route.
* we've to insert an intermediate node on the list
* this new node will point to the one we need to create
See comment in __ipv6_addr_diff: bit may be an invalid value,
but if it is >= plen, the value is ignored in any case.
*/
-
+
bit = __ipv6_addr_diff(addr, &key->addr, addrlen);
- /*
- * (intermediate)[in]
+ /*
+ * (intermediate)[in]
* / \
* (new leaf node)[ln] (old node)[fn]
*/
if (plen > bit) {
in = node_alloc();
ln = node_alloc();
-
+
if (in == NULL || ln == NULL) {
if (in)
node_free(in);
return NULL;
}
- /*
- * new intermediate node.
+ /*
+ * new intermediate node.
* RTN_RTINFO will
* be off since that an address that chooses one of
* the branches would not match less specific routes
}
} else { /* plen <= bit */
- /*
+ /*
* (new leaf node)[ln]
* / \
* (old node)[fn] NULL
ln->parent = pn;
ln->fn_sernum = sernum;
-
+
if (dir)
pn->right = ln;
else
ins = &fn->leaf;
- if (fn->fn_flags&RTN_TL_ROOT &&
- fn->leaf == &ip6_null_entry &&
- !(rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) ){
- fn->leaf = rt;
- rt->u.next = NULL;
- goto out;
- }
-
- for (iter = fn->leaf; iter; iter=iter->u.next) {
+ for (iter = fn->leaf; iter; iter=iter->u.dst.rt6_next) {
/*
* Search for duplicates
*/
if (iter->rt6i_metric > rt->rt6i_metric)
break;
- ins = &iter->u.next;
+ ins = &iter->u.dst.rt6_next;
}
+ /* Reset round-robin state, if necessary */
+ if (ins == &fn->leaf)
+ fn->rr_ptr = NULL;
+
/*
* insert node
*/
-out:
- rt->u.next = iter;
+ rt->u.dst.rt6_next = iter;
*ins = rt;
rt->rt6i_node = fn;
atomic_inc(&rt->rt6i_ref);
inet6_rt_notify(RTM_NEWROUTE, rt, info);
- rt6_stats.fib_rt_entries++;
+ info->nl_net->ipv6.rt6_stats->fib_rt_entries++;
if ((fn->fn_flags & RTN_RTINFO) == 0) {
- rt6_stats.fib_route_nodes++;
+ info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
fn->fn_flags |= RTN_RTINFO;
}
return 0;
}
-static __inline__ void fib6_start_gc(struct rt6_info *rt)
+static __inline__ void fib6_start_gc(struct net *net, struct rt6_info *rt)
{
- if (ip6_fib_timer.expires == 0 &&
+ if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
(rt->rt6i_flags & (RTF_EXPIRES|RTF_CACHE)))
- mod_timer(&ip6_fib_timer, jiffies + ip6_rt_gc_interval);
+ mod_timer(&net->ipv6.ip6_fib_timer,
+ jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
}
-void fib6_force_start_gc(void)
+void fib6_force_start_gc(struct net *net)
{
- if (ip6_fib_timer.expires == 0)
- mod_timer(&ip6_fib_timer, jiffies + ip6_rt_gc_interval);
+ if (!timer_pending(&net->ipv6.ip6_fib_timer))
+ mod_timer(&net->ipv6.ip6_fib_timer,
+ jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
}
/*
if (sfn == NULL)
goto st_failure;
- sfn->leaf = &ip6_null_entry;
- atomic_inc(&ip6_null_entry.rt6i_ref);
+ sfn->leaf = info->nl_net->ipv6.ip6_null_entry;
+ atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref);
sfn->fn_flags = RTN_ROOT;
sfn->fn_sernum = fib6_new_sernum();
err = fib6_add_rt2node(fn, rt, info);
if (err == 0) {
- fib6_start_gc(rt);
+ fib6_start_gc(info->nl_net, rt);
if (!(rt->rt6i_flags&RTF_CACHE))
- fib6_prune_clones(fn, rt);
+ fib6_prune_clones(info->nl_net, pn, rt);
}
out:
* If fib6_add_1 has cleared the old leaf pointer in the
* super-tree leaf node we have to find a new one for it.
*/
+ if (pn != fn && pn->leaf == rt) {
+ pn->leaf = NULL;
+ atomic_dec(&rt->rt6i_ref);
+ }
if (pn != fn && !pn->leaf && !(pn->fn_flags & RTN_RTINFO)) {
- pn->leaf = fib6_find_prefix(pn);
+ pn->leaf = fib6_find_prefix(info->nl_net, pn);
#if RT6_DEBUG >= 2
if (!pn->leaf) {
BUG_TRAP(pn->leaf != NULL);
- pn->leaf = &ip6_null_entry;
+ pn->leaf = info->nl_net->ipv6.ip6_null_entry;
}
#endif
atomic_inc(&pn->leaf->rt6i_ref);
*/
st_failure:
if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)))
- fib6_repair_tree(fn);
+ fib6_repair_tree(info->nl_net, fn);
dst_free(&rt->u.dst);
return err;
#endif
struct lookup_args *args)
{
struct fib6_node *fn;
- int dir;
+ __be32 dir;
+
+ if (unlikely(args->offset == 0))
+ return NULL;
/*
* Descend on a tree
break;
}
- while ((fn->fn_flags & RTN_ROOT) == 0) {
-#ifdef CONFIG_IPV6_SUBTREES
- if (fn->subtree) {
- struct fib6_node *st;
- struct lookup_args *narg;
-
- narg = args + 1;
-
- if (narg->addr) {
- st = fib6_lookup_1(fn->subtree, narg);
-
- if (st && !(st->fn_flags & RTN_ROOT))
- return st;
- }
- }
-#endif
-
- if (fn->fn_flags & RTN_RTINFO) {
+ while(fn) {
+ if (FIB6_SUBTREE(fn) || fn->fn_flags & RTN_RTINFO) {
struct rt6key *key;
key = (struct rt6key *) ((u8 *) fn->leaf +
args->offset);
- if (ipv6_prefix_equal(&key->addr, args->addr, key->plen))
- return fn;
+ if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) {
+#ifdef CONFIG_IPV6_SUBTREES
+ if (fn->subtree)
+ fn = fib6_lookup_1(fn->subtree, args + 1);
+#endif
+ if (!fn || fn->fn_flags & RTN_RTINFO)
+ return fn;
+ }
}
+ if (fn->fn_flags & RTN_ROOT)
+ break;
+
fn = fn->parent;
}
struct fib6_node * fib6_lookup(struct fib6_node *root, struct in6_addr *daddr,
struct in6_addr *saddr)
{
- struct lookup_args args[2];
struct fib6_node *fn;
-
- args[0].offset = offsetof(struct rt6_info, rt6i_dst);
- args[0].addr = daddr;
-
+ struct lookup_args args[] = {
+ {
+ .offset = offsetof(struct rt6_info, rt6i_dst),
+ .addr = daddr,
+ },
#ifdef CONFIG_IPV6_SUBTREES
- args[1].offset = offsetof(struct rt6_info, rt6i_src);
- args[1].addr = saddr;
+ {
+ .offset = offsetof(struct rt6_info, rt6i_src),
+ .addr = saddr,
+ },
#endif
+ {
+ .offset = 0, /* sentinel */
+ }
+ };
- fn = fib6_lookup_1(root, args);
+ fn = fib6_lookup_1(root, daddr ? args : args + 1);
if (fn == NULL || fn->fn_flags & RTN_TL_ROOT)
fn = root;
#ifdef CONFIG_IPV6_SUBTREES
if (src_len) {
BUG_TRAP(saddr!=NULL);
- if (fn == NULL)
- fn = fn->subtree;
- if (fn)
- fn = fib6_locate_1(fn, saddr, src_len,
+ if (fn && fn->subtree)
+ fn = fib6_locate_1(fn->subtree, saddr, src_len,
offsetof(struct rt6_info, rt6i_src));
}
#endif
*
*/
-static struct rt6_info * fib6_find_prefix(struct fib6_node *fn)
+static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn)
{
if (fn->fn_flags&RTN_ROOT)
- return &ip6_null_entry;
+ return net->ipv6.ip6_null_entry;
while(fn) {
if(fn->left)
if(fn->right)
return fn->right->leaf;
- fn = SUBTREE(fn);
+ fn = FIB6_SUBTREE(fn);
}
return NULL;
}
* is the node we want to try and remove.
*/
-static struct fib6_node * fib6_repair_tree(struct fib6_node *fn)
+static struct fib6_node *fib6_repair_tree(struct net *net,
+ struct fib6_node *fn)
{
int children;
int nstate;
if (fn->right) child = fn->right, children |= 1;
if (fn->left) child = fn->left, children |= 2;
- if (children == 3 || SUBTREE(fn)
+ if (children == 3 || FIB6_SUBTREE(fn)
#ifdef CONFIG_IPV6_SUBTREES
/* Subtree root (i.e. fn) may have one child */
|| (children && fn->fn_flags&RTN_ROOT)
#endif
) {
- fn->leaf = fib6_find_prefix(fn);
+ fn->leaf = fib6_find_prefix(net, fn);
#if RT6_DEBUG >= 2
if (fn->leaf==NULL) {
BUG_TRAP(fn->leaf);
- fn->leaf = &ip6_null_entry;
+ fn->leaf = net->ipv6.ip6_null_entry;
}
#endif
atomic_inc(&fn->leaf->rt6i_ref);
pn = fn->parent;
#ifdef CONFIG_IPV6_SUBTREES
- if (SUBTREE(pn) == fn) {
+ if (FIB6_SUBTREE(pn) == fn) {
BUG_TRAP(fn->fn_flags&RTN_ROOT);
- SUBTREE(pn) = NULL;
+ FIB6_SUBTREE(pn) = NULL;
nstate = FWS_L;
} else {
BUG_TRAP(!(fn->fn_flags&RTN_ROOT));
read_unlock(&fib6_walker_lock);
node_free(fn);
- if (pn->fn_flags&RTN_RTINFO || SUBTREE(pn))
+ if (pn->fn_flags&RTN_RTINFO || FIB6_SUBTREE(pn))
return pn;
rt6_release(pn->leaf);
{
struct fib6_walker_t *w;
struct rt6_info *rt = *rtp;
+ struct net *net = info->nl_net;
RT6_TRACE("fib6_del_route\n");
/* Unlink it */
- *rtp = rt->u.next;
+ *rtp = rt->u.dst.rt6_next;
rt->rt6i_node = NULL;
- rt6_stats.fib_rt_entries--;
- rt6_stats.fib_discarded_routes++;
+ net->ipv6.rt6_stats->fib_rt_entries--;
+ net->ipv6.rt6_stats->fib_discarded_routes++;
+
+ /* Reset round-robin state, if necessary */
+ if (fn->rr_ptr == rt)
+ fn->rr_ptr = NULL;
/* Adjust walkers */
read_lock(&fib6_walker_lock);
FOR_WALKERS(w) {
if (w->state == FWS_C && w->leaf == rt) {
RT6_TRACE("walker %p adjusted by delroute\n", w);
- w->leaf = rt->u.next;
+ w->leaf = rt->u.dst.rt6_next;
if (w->leaf == NULL)
w->state = FWS_U;
}
}
read_unlock(&fib6_walker_lock);
- rt->u.next = NULL;
-
- if (fn->leaf == NULL && fn->fn_flags&RTN_TL_ROOT)
- fn->leaf = &ip6_null_entry;
+ rt->u.dst.rt6_next = NULL;
/* If it was last route, expunge its radix tree node */
if (fn->leaf == NULL) {
fn->fn_flags &= ~RTN_RTINFO;
- rt6_stats.fib_route_nodes--;
- fn = fib6_repair_tree(fn);
+ net->ipv6.rt6_stats->fib_route_nodes--;
+ fn = fib6_repair_tree(net, fn);
}
if (atomic_read(&rt->rt6i_ref) != 1) {
*/
while (fn) {
if (!(fn->fn_flags&RTN_RTINFO) && fn->leaf == rt) {
- fn->leaf = fib6_find_prefix(fn);
+ fn->leaf = fib6_find_prefix(net, fn);
atomic_inc(&fn->leaf->rt6i_ref);
rt6_release(rt);
}
fn = fn->parent;
}
/* No more references are possible at this point. */
- if (atomic_read(&rt->rt6i_ref) != 1) BUG();
+ BUG_ON(atomic_read(&rt->rt6i_ref) != 1);
}
inet6_rt_notify(RTM_DELROUTE, rt, info);
int fib6_del(struct rt6_info *rt, struct nl_info *info)
{
+ struct net *net = info->nl_net;
struct fib6_node *fn = rt->rt6i_node;
struct rt6_info **rtp;
return -ENOENT;
}
#endif
- if (fn == NULL || rt == &ip6_null_entry)
+ if (fn == NULL || rt == net->ipv6.ip6_null_entry)
return -ENOENT;
BUG_TRAP(fn->fn_flags&RTN_RTINFO);
- if (!(rt->rt6i_flags&RTF_CACHE))
- fib6_prune_clones(fn, rt);
+ if (!(rt->rt6i_flags&RTF_CACHE)) {
+ struct fib6_node *pn = fn;
+#ifdef CONFIG_IPV6_SUBTREES
+ /* clones of this route might be in another subtree */
+ if (rt->rt6i_src.plen) {
+ while (!(pn->fn_flags&RTN_ROOT))
+ pn = pn->parent;
+ pn = pn->parent;
+ }
+#endif
+ fib6_prune_clones(info->nl_net, pn, rt);
+ }
/*
* Walk the leaf entries looking for ourself
*/
- for (rtp = &fn->leaf; *rtp; rtp = &(*rtp)->u.next) {
+ for (rtp = &fn->leaf; *rtp; rtp = &(*rtp)->u.dst.rt6_next) {
if (*rtp == rt) {
fib6_del_route(fn, rtp, info);
return 0;
* However, it is internally reenterable wrt itself and fib6_add/fib6_del.
* It means, that we can modify tree during walking
* and use this function for garbage collection, clone pruning,
- * cleaning tree when a device goes down etc. etc.
+ * cleaning tree when a device goes down etc. etc.
*
* It guarantees that every node will be traversed,
* and that it will be traversed only once.
switch (w->state) {
#ifdef CONFIG_IPV6_SUBTREES
case FWS_S:
- if (SUBTREE(fn)) {
- w->node = SUBTREE(fn);
+ if (FIB6_SUBTREE(fn)) {
+ w->node = FIB6_SUBTREE(fn);
continue;
}
w->state = FWS_L;
-#endif
+#endif
case FWS_L:
if (fn->left) {
w->node = fn->left;
pn = fn->parent;
w->node = pn;
#ifdef CONFIG_IPV6_SUBTREES
- if (SUBTREE(pn) == fn) {
+ if (FIB6_SUBTREE(pn) == fn) {
BUG_TRAP(fn->fn_flags&RTN_ROOT);
w->state = FWS_L;
continue;
{
int res;
struct rt6_info *rt;
- struct fib6_cleaner_t *c = (struct fib6_cleaner_t*)w;
+ struct fib6_cleaner_t *c = container_of(w, struct fib6_cleaner_t, w);
+ struct nl_info info = {
+ .nl_net = c->net,
+ };
- for (rt = w->leaf; rt; rt = rt->u.next) {
+ for (rt = w->leaf; rt; rt = rt->u.dst.rt6_next) {
res = c->func(rt, c->arg);
if (res < 0) {
w->leaf = rt;
- res = fib6_del(rt, NULL);
+ res = fib6_del(rt, &info);
if (res) {
#if RT6_DEBUG >= 2
printk(KERN_DEBUG "fib6_clean_node: del failed: rt=%p@%p err=%d\n", rt, rt->rt6i_node, res);
/*
* Convenient frontend to tree walker.
- *
+ *
* func is called on each route.
* It may return -1 -> delete this route.
* 0 -> continue walking
* ignoring pure split nodes) will be scanned.
*/
-static void fib6_clean_tree(struct fib6_node *root,
+static void fib6_clean_tree(struct net *net, struct fib6_node *root,
int (*func)(struct rt6_info *, void *arg),
int prune, void *arg)
{
c.w.prune = prune;
c.func = func;
c.arg = arg;
+ c.net = net;
fib6_walk(&c.w);
}
-void fib6_clean_all(int (*func)(struct rt6_info *, void *arg),
+void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
int prune, void *arg)
{
struct fib6_table *table;
struct hlist_node *node;
+ struct hlist_head *head;
unsigned int h;
rcu_read_lock();
for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
- hlist_for_each_entry_rcu(table, node, &fib_table_hash[h],
- tb6_hlist) {
+ head = &net->ipv6.fib_table_hash[h];
+ hlist_for_each_entry_rcu(table, node, head, tb6_hlist) {
write_lock_bh(&table->tb6_lock);
- fib6_clean_tree(&table->tb6_root, func, prune, arg);
+ fib6_clean_tree(net, &table->tb6_root,
+ func, prune, arg);
write_unlock_bh(&table->tb6_lock);
}
}
return 0;
}
-static void fib6_prune_clones(struct fib6_node *fn, struct rt6_info *rt)
+static void fib6_prune_clones(struct net *net, struct fib6_node *fn,
+ struct rt6_info *rt)
{
- fib6_clean_tree(fn, fib6_prune_clone, 1, rt);
+ fib6_clean_tree(net, fn, fib6_prune_clone, 1, rt);
}
/*
static DEFINE_SPINLOCK(fib6_gc_lock);
-void fib6_run_gc(unsigned long dummy)
+void fib6_run_gc(unsigned long expires, struct net *net)
{
- if (dummy != ~0UL) {
+ if (expires != ~0UL) {
spin_lock_bh(&fib6_gc_lock);
- gc_args.timeout = dummy ? (int)dummy : ip6_rt_gc_interval;
+ gc_args.timeout = expires ? (int)expires :
+ net->ipv6.sysctl.ip6_rt_gc_interval;
} else {
local_bh_disable();
if (!spin_trylock(&fib6_gc_lock)) {
- mod_timer(&ip6_fib_timer, jiffies + HZ);
+ mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ);
local_bh_enable();
return;
}
- gc_args.timeout = ip6_rt_gc_interval;
+ gc_args.timeout = net->ipv6.sysctl.ip6_rt_gc_interval;
}
gc_args.more = 0;
- ndisc_dst_gc(&gc_args.more);
- fib6_clean_all(fib6_age, 0, NULL);
+ icmp6_dst_gc(&gc_args.more);
+
+ fib6_clean_all(net, fib6_age, 0, NULL);
if (gc_args.more)
- mod_timer(&ip6_fib_timer, jiffies + ip6_rt_gc_interval);
- else {
- del_timer(&ip6_fib_timer);
- ip6_fib_timer.expires = 0;
- }
+ mod_timer(&net->ipv6.ip6_fib_timer, jiffies +
+ net->ipv6.sysctl.ip6_rt_gc_interval);
+ else
+ del_timer(&net->ipv6.ip6_fib_timer);
spin_unlock_bh(&fib6_gc_lock);
}
-void __init fib6_init(void)
+static void fib6_gc_timer_cb(unsigned long arg)
+{
+ fib6_run_gc(0, (struct net *)arg);
+}
+
+static int fib6_net_init(struct net *net)
+{
+ setup_timer(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, (unsigned long)net);
+
+ net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL);
+ if (!net->ipv6.rt6_stats)
+ goto out_timer;
+
+ net->ipv6.fib_table_hash =
+ kzalloc(sizeof(*net->ipv6.fib_table_hash)*FIB_TABLE_HASHSZ,
+ GFP_KERNEL);
+ if (!net->ipv6.fib_table_hash)
+ goto out_rt6_stats;
+
+ net->ipv6.fib6_main_tbl = kzalloc(sizeof(*net->ipv6.fib6_main_tbl),
+ GFP_KERNEL);
+ if (!net->ipv6.fib6_main_tbl)
+ goto out_fib_table_hash;
+
+ net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN;
+ net->ipv6.fib6_main_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry;
+ net->ipv6.fib6_main_tbl->tb6_root.fn_flags =
+ RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
+
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+ net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl),
+ GFP_KERNEL);
+ if (!net->ipv6.fib6_local_tbl)
+ goto out_fib6_main_tbl;
+ net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL;
+ net->ipv6.fib6_local_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry;
+ net->ipv6.fib6_local_tbl->tb6_root.fn_flags =
+ RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
+#endif
+ fib6_tables_init(net);
+
+ return 0;
+
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+out_fib6_main_tbl:
+ kfree(net->ipv6.fib6_main_tbl);
+#endif
+out_fib_table_hash:
+ kfree(net->ipv6.fib_table_hash);
+out_rt6_stats:
+ kfree(net->ipv6.rt6_stats);
+out_timer:
+ return -ENOMEM;
+ }
+
+static void fib6_net_exit(struct net *net)
+{
+ rt6_ifdown(net, NULL);
+ del_timer_sync(&net->ipv6.ip6_fib_timer);
+
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+ kfree(net->ipv6.fib6_local_tbl);
+#endif
+ kfree(net->ipv6.fib6_main_tbl);
+ kfree(net->ipv6.fib_table_hash);
+ kfree(net->ipv6.rt6_stats);
+}
+
+static struct pernet_operations fib6_net_ops = {
+ .init = fib6_net_init,
+ .exit = fib6_net_exit,
+};
+
+int __init fib6_init(void)
{
+ int ret = -ENOMEM;
+
fib6_node_kmem = kmem_cache_create("fib6_nodes",
sizeof(struct fib6_node),
0, SLAB_HWCACHE_ALIGN,
- NULL, NULL);
+ NULL);
if (!fib6_node_kmem)
- panic("cannot create fib6_nodes cache");
+ goto out;
+
+ ret = register_pernet_subsys(&fib6_net_ops);
+ if (ret)
+ goto out_kmem_cache_create;
- fib6_tables_init();
+ ret = __rtnl_register(PF_INET6, RTM_GETROUTE, NULL, inet6_dump_fib);
+ if (ret)
+ goto out_unregister_subsys;
+out:
+ return ret;
+
+out_unregister_subsys:
+ unregister_pernet_subsys(&fib6_net_ops);
+out_kmem_cache_create:
+ kmem_cache_destroy(fib6_node_kmem);
+ goto out;
}
void fib6_gc_cleanup(void)
{
- del_timer(&ip6_fib_timer);
+ unregister_pernet_subsys(&fib6_net_ops);
kmem_cache_destroy(fib6_node_kmem);
}