linux/net/ipv6/ip6_fib.c

1714 lines
36 KiB
C
Raw Normal View History

/*
* Linux INET6 implementation
* Forwarding Information Database
*
* Authors:
* 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
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
/*
* Changes:
* 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>
#include <linux/net.h>
#include <linux/route.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/init.h>
#include <linux/list.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <net/ipv6.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#define RT6_DEBUG 2
#if RT6_DEBUG >= 3
#define RT6_TRACE(x...) printk(KERN_DEBUG x)
#else
#define RT6_TRACE(x...) do { ; } while (0)
#endif
static struct kmem_cache * fib6_node_kmem __read_mostly;
enum fib_walk_state_t
{
#ifdef CONFIG_IPV6_SUBTREES
FWS_S,
#endif
FWS_L,
FWS_R,
FWS_C,
FWS_U
};
struct fib6_cleaner_t
{
struct fib6_walker_t w;
struct net *net;
int (*func)(struct rt6_info *, void *arg);
void *arg;
};
static DEFINE_RWLOCK(fib6_walker_lock);
#ifdef CONFIG_IPV6_SUBTREES
#define FWS_INIT FWS_S
#else
#define FWS_INIT FWS_L
#endif
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);
/*
* A routing update causes an increase of the serial number on the
* affected subtree. This allows for cached routes to be asynchronously
* tested when modifications are made to the destination cache as a
* result of redirects, path MTU changes, etc.
*/
static __u32 rt_sernum;
static void fib6_gc_timer_cb(unsigned long arg);
static LIST_HEAD(fib6_walkers);
#define FOR_WALKERS(w) list_for_each_entry(w, &fib6_walkers, lh)
static inline void fib6_walker_link(struct fib6_walker_t *w)
{
write_lock_bh(&fib6_walker_lock);
list_add(&w->lh, &fib6_walkers);
write_unlock_bh(&fib6_walker_lock);
}
static inline void fib6_walker_unlink(struct fib6_walker_t *w)
{
write_lock_bh(&fib6_walker_lock);
list_del(&w->lh);
write_unlock_bh(&fib6_walker_lock);
}
static __inline__ u32 fib6_new_sernum(void)
{
u32 n = ++rt_sernum;
if ((__s32)n <= 0)
rt_sernum = n = 1;
return n;
}
/*
* Auxiliary address test functions for the radix tree.
*
* These assume a 32bit processor (although it will work on
* 64bit processors)
*/
/*
* test bit
*/
#if defined(__LITTLE_ENDIAN)
# define BITOP_BE32_SWIZZLE (0x1F & ~7)
#else
# define BITOP_BE32_SWIZZLE 0
#endif
static __inline__ __be32 addr_bit_set(const void *token, int fn_bit)
{
const __be32 *addr = token;
/*
* Here,
* 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)
* is optimized version of
* htonl(1 << ((~fn_bit)&0x1F))
* See include/asm-generic/bitops/le.h.
*/
return (__force __be32)(1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)) &
addr[fn_bit >> 5];
}
static __inline__ struct fib6_node * node_alloc(void)
{
struct fib6_node *fn;
fn = kmem_cache_zalloc(fib6_node_kmem, GFP_ATOMIC);
return fn;
}
static __inline__ void node_free(struct fib6_node * fn)
{
kmem_cache_free(fib6_node_kmem, fn);
}
static __inline__ void rt6_release(struct rt6_info *rt)
{
if (atomic_dec_and_test(&rt->rt6i_ref))
dst_free(&rt->dst);
}
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 & (FIB6_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, &net->ipv6.fib_table_hash[h]);
}
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
{
struct fib6_table *table;
table = kzalloc(sizeof(*table), GFP_ATOMIC);
if (table) {
table->tb6_id = id;
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(struct net *net, u32 id)
{
struct fib6_table *tb;
if (id == 0)
id = RT6_TABLE_MAIN;
tb = fib6_get_table(net, id);
if (tb)
return tb;
tb = fib6_alloc_table(net, id);
if (tb)
fib6_link_table(net, tb);
return tb;
}
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;
if (id == 0)
id = RT6_TABLE_MAIN;
h = id & (FIB6_TABLE_HASHSZ - 1);
rcu_read_lock();
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;
}
}
rcu_read_unlock();
return NULL;
}
static void __net_init fib6_tables_init(struct net *net)
{
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(struct net *net, u32 id)
{
return fib6_get_table(net, id);
}
struct fib6_table *fib6_get_table(struct net *net, u32 id)
{
return net->ipv6.fib6_main_tbl;
}
struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
int flags, pol_lookup_t lookup)
{
return (struct dst_entry *) lookup(net, net->ipv6.fib6_main_tbl, fl6, flags);
}
static void __net_init fib6_tables_init(struct net *net)
{
fib6_link_table(net, net->ipv6.fib6_main_tbl);
}
#endif
static int fib6_dump_node(struct fib6_walker_t *w)
{
int res;
struct rt6_info *rt;
for (rt = w->leaf; rt; rt = rt->dst.rt6_next) {
res = rt6_dump_route(rt, w->args);
if (res < 0) {
/* Frame is full, suspend walking */
w->leaf = rt;
return 1;
}
WARN_ON(res == 0);
}
w->leaf = NULL;
return 0;
}
static void fib6_dump_end(struct netlink_callback *cb)
{
struct fib6_walker_t *w = (void*)cb->args[2];
if (w) {
if (cb->args[4]) {
cb->args[4] = 0;
fib6_walker_unlink(w);
}
cb->args[2] = 0;
kfree(w);
}
cb->done = (void*)cb->args[3];
cb->args[1] = 3;
}
static int fib6_dump_done(struct netlink_callback *cb)
{
fib6_dump_end(cb);
return cb->done ? cb->done(cb) : 0;
}
static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb,
struct netlink_callback *cb)
{
struct fib6_walker_t *w;
int res;
w = (void *)cb->args[2];
w->root = &table->tb6_root;
if (cb->args[4] == 0) {
ipv6: fib: fix crash when changing large fib while dumping it When the fib size exceeds what can be dumped in a single skb, the dump is suspended and resumed once the last skb has been received by userspace. When the fib is changed while the dump is suspended, the walker might contain stale pointers, causing a crash when the dump is resumed. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] PGD 5347a067 PUD 65c7067 PMD 0 Oops: 0000 [#1] PREEMPT SMP ... RIP: 0010:[<ffffffffa01bce04>] [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] ... Call Trace: [<ffffffff8104aca3>] ? mutex_spin_on_owner+0x59/0x71 [<ffffffffa01bd105>] inet6_dump_fib+0x11b/0x1b9 [ipv6] [<ffffffff81371af4>] netlink_dump+0x5b/0x19e [<ffffffff8134f288>] ? consume_skb+0x28/0x2a [<ffffffff81373b69>] netlink_recvmsg+0x1ab/0x2c6 [<ffffffff81372781>] ? netlink_unicast+0xfa/0x151 [<ffffffff813483e0>] __sock_recvmsg+0x6d/0x79 [<ffffffff81348a53>] sock_recvmsg+0xca/0xe3 [<ffffffff81066d4b>] ? autoremove_wake_function+0x0/0x38 [<ffffffff811ed1f8>] ? radix_tree_lookup_slot+0xe/0x10 [<ffffffff810b3ed7>] ? find_get_page+0x90/0xa5 [<ffffffff810b5dc5>] ? filemap_fault+0x201/0x34f [<ffffffff810ef152>] ? fget_light+0x2f/0xac [<ffffffff813519e7>] ? verify_iovec+0x4f/0x94 [<ffffffff81349a65>] sys_recvmsg+0x14d/0x223 Store the serial number when beginning to walk the fib and reload pointers when continuing to walk after a change occured. Similar to other dumping functions, this might cause unrelated entries to be missed when entries are deleted. Tested-by: Ben Greear <greearb@candelatech.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-08 05:19:03 +00:00
w->count = 0;
w->skip = 0;
read_lock_bh(&table->tb6_lock);
res = fib6_walk(w);
read_unlock_bh(&table->tb6_lock);
ipv6: fib: fix crash when changing large fib while dumping it When the fib size exceeds what can be dumped in a single skb, the dump is suspended and resumed once the last skb has been received by userspace. When the fib is changed while the dump is suspended, the walker might contain stale pointers, causing a crash when the dump is resumed. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] PGD 5347a067 PUD 65c7067 PMD 0 Oops: 0000 [#1] PREEMPT SMP ... RIP: 0010:[<ffffffffa01bce04>] [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] ... Call Trace: [<ffffffff8104aca3>] ? mutex_spin_on_owner+0x59/0x71 [<ffffffffa01bd105>] inet6_dump_fib+0x11b/0x1b9 [ipv6] [<ffffffff81371af4>] netlink_dump+0x5b/0x19e [<ffffffff8134f288>] ? consume_skb+0x28/0x2a [<ffffffff81373b69>] netlink_recvmsg+0x1ab/0x2c6 [<ffffffff81372781>] ? netlink_unicast+0xfa/0x151 [<ffffffff813483e0>] __sock_recvmsg+0x6d/0x79 [<ffffffff81348a53>] sock_recvmsg+0xca/0xe3 [<ffffffff81066d4b>] ? autoremove_wake_function+0x0/0x38 [<ffffffff811ed1f8>] ? radix_tree_lookup_slot+0xe/0x10 [<ffffffff810b3ed7>] ? find_get_page+0x90/0xa5 [<ffffffff810b5dc5>] ? filemap_fault+0x201/0x34f [<ffffffff810ef152>] ? fget_light+0x2f/0xac [<ffffffff813519e7>] ? verify_iovec+0x4f/0x94 [<ffffffff81349a65>] sys_recvmsg+0x14d/0x223 Store the serial number when beginning to walk the fib and reload pointers when continuing to walk after a change occured. Similar to other dumping functions, this might cause unrelated entries to be missed when entries are deleted. Tested-by: Ben Greear <greearb@candelatech.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-08 05:19:03 +00:00
if (res > 0) {
cb->args[4] = 1;
ipv6: fib: fix crash when changing large fib while dumping it When the fib size exceeds what can be dumped in a single skb, the dump is suspended and resumed once the last skb has been received by userspace. When the fib is changed while the dump is suspended, the walker might contain stale pointers, causing a crash when the dump is resumed. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] PGD 5347a067 PUD 65c7067 PMD 0 Oops: 0000 [#1] PREEMPT SMP ... RIP: 0010:[<ffffffffa01bce04>] [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] ... Call Trace: [<ffffffff8104aca3>] ? mutex_spin_on_owner+0x59/0x71 [<ffffffffa01bd105>] inet6_dump_fib+0x11b/0x1b9 [ipv6] [<ffffffff81371af4>] netlink_dump+0x5b/0x19e [<ffffffff8134f288>] ? consume_skb+0x28/0x2a [<ffffffff81373b69>] netlink_recvmsg+0x1ab/0x2c6 [<ffffffff81372781>] ? netlink_unicast+0xfa/0x151 [<ffffffff813483e0>] __sock_recvmsg+0x6d/0x79 [<ffffffff81348a53>] sock_recvmsg+0xca/0xe3 [<ffffffff81066d4b>] ? autoremove_wake_function+0x0/0x38 [<ffffffff811ed1f8>] ? radix_tree_lookup_slot+0xe/0x10 [<ffffffff810b3ed7>] ? find_get_page+0x90/0xa5 [<ffffffff810b5dc5>] ? filemap_fault+0x201/0x34f [<ffffffff810ef152>] ? fget_light+0x2f/0xac [<ffffffff813519e7>] ? verify_iovec+0x4f/0x94 [<ffffffff81349a65>] sys_recvmsg+0x14d/0x223 Store the serial number when beginning to walk the fib and reload pointers when continuing to walk after a change occured. Similar to other dumping functions, this might cause unrelated entries to be missed when entries are deleted. Tested-by: Ben Greear <greearb@candelatech.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-08 05:19:03 +00:00
cb->args[5] = w->root->fn_sernum;
}
} else {
ipv6: fib: fix crash when changing large fib while dumping it When the fib size exceeds what can be dumped in a single skb, the dump is suspended and resumed once the last skb has been received by userspace. When the fib is changed while the dump is suspended, the walker might contain stale pointers, causing a crash when the dump is resumed. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] PGD 5347a067 PUD 65c7067 PMD 0 Oops: 0000 [#1] PREEMPT SMP ... RIP: 0010:[<ffffffffa01bce04>] [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] ... Call Trace: [<ffffffff8104aca3>] ? mutex_spin_on_owner+0x59/0x71 [<ffffffffa01bd105>] inet6_dump_fib+0x11b/0x1b9 [ipv6] [<ffffffff81371af4>] netlink_dump+0x5b/0x19e [<ffffffff8134f288>] ? consume_skb+0x28/0x2a [<ffffffff81373b69>] netlink_recvmsg+0x1ab/0x2c6 [<ffffffff81372781>] ? netlink_unicast+0xfa/0x151 [<ffffffff813483e0>] __sock_recvmsg+0x6d/0x79 [<ffffffff81348a53>] sock_recvmsg+0xca/0xe3 [<ffffffff81066d4b>] ? autoremove_wake_function+0x0/0x38 [<ffffffff811ed1f8>] ? radix_tree_lookup_slot+0xe/0x10 [<ffffffff810b3ed7>] ? find_get_page+0x90/0xa5 [<ffffffff810b5dc5>] ? filemap_fault+0x201/0x34f [<ffffffff810ef152>] ? fget_light+0x2f/0xac [<ffffffff813519e7>] ? verify_iovec+0x4f/0x94 [<ffffffff81349a65>] sys_recvmsg+0x14d/0x223 Store the serial number when beginning to walk the fib and reload pointers when continuing to walk after a change occured. Similar to other dumping functions, this might cause unrelated entries to be missed when entries are deleted. Tested-by: Ben Greear <greearb@candelatech.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-08 05:19:03 +00:00
if (cb->args[5] != w->root->fn_sernum) {
/* Begin at the root if the tree changed */
cb->args[5] = w->root->fn_sernum;
w->state = FWS_INIT;
w->node = w->root;
w->skip = w->count;
} else
w->skip = 0;
read_lock_bh(&table->tb6_lock);
res = fib6_walk_continue(w);
read_unlock_bh(&table->tb6_lock);
if (res <= 0) {
fib6_walker_unlink(w);
cb->args[4] = 0;
}
}
return res;
}
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];
s_e = cb->args[1];
w = (void *)cb->args[2];
if (!w) {
/* New dump:
*
* 1. hook callback destructor.
*/
cb->args[3] = (long)cb->done;
cb->done = fib6_dump_done;
/*
* 2. allocate and initialize walker.
*/
w = kzalloc(sizeof(*w), GFP_ATOMIC);
if (!w)
return -ENOMEM;
w->func = fib6_dump_node;
cb->args[2] = (long)w;
}
arg.skb = skb;
arg.cb = cb;
arg.net = net;
w->args = &arg;
rcu_read_lock();
for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) {
e = 0;
head = &net->ipv6.fib_table_hash[h];
hlist_for_each_entry_rcu(tb, node, head, tb6_hlist) {
if (e < s_e)
goto next;
res = fib6_dump_table(tb, skb, cb);
if (res != 0)
goto out;
next:
e++;
}
}
out:
rcu_read_unlock();
cb->args[1] = e;
cb->args[0] = h;
res = res < 0 ? res : skb->len;
if (res <= 0)
fib6_dump_end(cb);
return res;
}
/*
* Routing Table
*
* return the appropriate node for a routing tree "add" operation
* by either creating and inserting or by returning an existing
* node.
*/
static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr,
int addrlen, int plen,
int offset, int allow_create,
int replace_required)
{
struct fib6_node *fn, *in, *ln;
struct fib6_node *pn = NULL;
struct rt6key *key;
int bit;
__be32 dir = 0;
__u32 sernum = fib6_new_sernum();
RT6_TRACE("fib6_add_1\n");
/* insert node in tree */
fn = root;
do {
key = (struct rt6key *)((u8 *)fn->leaf + offset);
/*
* Prefix match
*/
if (plen < fn->fn_bit ||
!ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) {
if (!allow_create) {
if (replace_required) {
pr_warn("IPv6: Can't replace route, "
"no match found\n");
return ERR_PTR(-ENOENT);
}
pr_warn("IPv6: NLM_F_CREATE should be set "
"when creating new route\n");
}
goto insert_above;
}
/*
* Exact match ?
*/
if (plen == fn->fn_bit) {
/* clean up an intermediate node */
if (!(fn->fn_flags & RTN_RTINFO)) {
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);
pn = fn;
fn = dir ? fn->right: fn->left;
} while (fn);
if (!allow_create) {
/* We should not create new node because
* NLM_F_REPLACE was specified without NLM_F_CREATE
* I assume it is safe to require NLM_F_CREATE when
* REPLACE flag is used! Later we may want to remove the
* check for replace_required, because according
* to netlink specification, NLM_F_CREATE
* MUST be specified if new route is created.
* That would keep IPv6 consistent with IPv4
*/
if (replace_required) {
pr_warn("IPv6: Can't replace route, no match found\n");
return ERR_PTR(-ENOENT);
}
pr_warn("IPv6: NLM_F_CREATE should be set "
"when creating new route\n");
}
/*
* We walked to the bottom of tree.
* Create new leaf node without children.
*/
ln = node_alloc();
if (!ln)
return NULL;
ln->fn_bit = plen;
ln->parent = pn;
ln->fn_sernum = sernum;
if (dir)
pn->right = ln;
else
pn->left = ln;
return ln;
insert_above:
/*
* 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
* and the current
*/
pn = fn->parent;
/* find 1st bit in difference between the 2 addrs.
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]
* / \
* (new leaf node)[ln] (old node)[fn]
*/
if (plen > bit) {
in = node_alloc();
ln = node_alloc();
if (!in || !ln) {
if (in)
node_free(in);
if (ln)
node_free(ln);
return NULL;
}
/*
* new intermediate node.
* RTN_RTINFO will
* be off since that an address that chooses one of
* the branches would not match less specific routes
* in the other branch
*/
in->fn_bit = bit;
in->parent = pn;
in->leaf = fn->leaf;
atomic_inc(&in->leaf->rt6i_ref);
in->fn_sernum = sernum;
/* update parent pointer */
if (dir)
pn->right = in;
else
pn->left = in;
ln->fn_bit = plen;
ln->parent = in;
fn->parent = in;
ln->fn_sernum = sernum;
if (addr_bit_set(addr, bit)) {
in->right = ln;
in->left = fn;
} else {
in->left = ln;
in->right = fn;
}
} else { /* plen <= bit */
/*
* (new leaf node)[ln]
* / \
* (old node)[fn] NULL
*/
ln = node_alloc();
if (!ln)
return NULL;
ln->fn_bit = plen;
ln->parent = pn;
ln->fn_sernum = sernum;
if (dir)
pn->right = ln;
else
pn->left = ln;
if (addr_bit_set(&key->addr, plen))
ln->right = fn;
else
ln->left = fn;
fn->parent = ln;
}
return ln;
}
/*
* Insert routing information in a node.
*/
static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
struct nl_info *info)
{
struct rt6_info *iter = NULL;
struct rt6_info **ins;
int replace = (info->nlh &&
(info->nlh->nlmsg_flags & NLM_F_REPLACE));
int add = (!info->nlh ||
(info->nlh->nlmsg_flags & NLM_F_CREATE));
int found = 0;
ins = &fn->leaf;
for (iter = fn->leaf; iter; iter = iter->dst.rt6_next) {
/*
* Search for duplicates
*/
if (iter->rt6i_metric == rt->rt6i_metric) {
/*
* Same priority level
*/
if (info->nlh &&
(info->nlh->nlmsg_flags & NLM_F_EXCL))
return -EEXIST;
if (replace) {
found++;
break;
}
if (iter->dst.dev == rt->dst.dev &&
iter->rt6i_idev == rt->rt6i_idev &&
ipv6_addr_equal(&iter->rt6i_gateway,
&rt->rt6i_gateway)) {
if (!(iter->rt6i_flags & RTF_EXPIRES))
return -EEXIST;
if (!(rt->rt6i_flags & RTF_EXPIRES))
rt6_clean_expires(iter);
else
rt6_set_expires(iter, rt->dst.expires);
return -EEXIST;
}
}
if (iter->rt6i_metric > rt->rt6i_metric)
break;
ins = &iter->dst.rt6_next;
}
[IPV6]: Fix routing round-robin locking. As per RFC2461, section 6.3.6, item #2, when no routers on the matching list are known to be reachable or probably reachable we do round robin on those available routes so that we make sure to probe as many of them as possible to detect when one becomes reachable faster. Each routing table has a rwlock protecting the tree and the linked list of routes at each leaf. The round robin code executes during lookup and thus with the rwlock taken as a reader. A small local spinlock tries to provide protection but this does not work at all for two reasons: 1) The round-robin list manipulation, as coded, goes like this (with read lock held): walk routes finding head and tail spin_lock(); rotate list using head and tail spin_unlock(); While one thread is rotating the list, another thread can end up with stale values of head and tail and then proceed to corrupt the list when it gets the lock. This ends up causing the OOPS in fib6_add() later onthat many people have been hitting. 2) All the other code paths that run with the rwlock held as a reader do not expect the list to change on them, they expect it to remain completely fixed while they hold the lock in that way. So, simply stated, it is impossible to implement this correctly using a manipulation of the list without violating the rwlock locking semantics. Reimplement using a per-fib6_node round-robin pointer. This way we don't need to manipulate the list at all, and since the round-robin pointer can only ever point to real existing entries we don't need to perform any locking on the changing of the round-robin pointer itself. We only need to reset the round-robin pointer to NULL when the entry it is pointing to is removed. The idea is from Thomas Graf and it is very similar to how this was implemented before the advanced router selection code when in. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-25 03:36:25 +00:00
/* Reset round-robin state, if necessary */
if (ins == &fn->leaf)
fn->rr_ptr = NULL;
/*
* insert node
*/
if (!replace) {
if (!add)
pr_warn("IPv6: NLM_F_CREATE should be set when creating new route\n");
add:
rt->dst.rt6_next = iter;
*ins = rt;
rt->rt6i_node = fn;
atomic_inc(&rt->rt6i_ref);
inet6_rt_notify(RTM_NEWROUTE, rt, info);
info->nl_net->ipv6.rt6_stats->fib_rt_entries++;
if (!(fn->fn_flags & RTN_RTINFO)) {
info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
fn->fn_flags |= RTN_RTINFO;
}
} else {
if (!found) {
if (add)
goto add;
pr_warn("IPv6: NLM_F_REPLACE set, but no existing node found!\n");
return -ENOENT;
}
*ins = rt;
rt->rt6i_node = fn;
rt->dst.rt6_next = iter->dst.rt6_next;
atomic_inc(&rt->rt6i_ref);
inet6_rt_notify(RTM_NEWROUTE, rt, info);
rt6_release(iter);
if (!(fn->fn_flags & RTN_RTINFO)) {
info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
fn->fn_flags |= RTN_RTINFO;
}
}
return 0;
}
static __inline__ void fib6_start_gc(struct net *net, struct rt6_info *rt)
{
if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
(rt->rt6i_flags & (RTF_EXPIRES | RTF_CACHE)))
mod_timer(&net->ipv6.ip6_fib_timer,
jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
}
void fib6_force_start_gc(struct net *net)
{
if (!timer_pending(&net->ipv6.ip6_fib_timer))
mod_timer(&net->ipv6.ip6_fib_timer,
jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
}
/*
* Add routing information to the routing tree.
* <destination addr>/<source addr>
* with source addr info in sub-trees
*/
int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info)
{
struct fib6_node *fn, *pn = NULL;
int err = -ENOMEM;
int allow_create = 1;
int replace_required = 0;
if (info->nlh) {
if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
allow_create = 0;
if (info->nlh->nlmsg_flags & NLM_F_REPLACE)
replace_required = 1;
}
if (!allow_create && !replace_required)
pr_warn("IPv6: RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n");
fn = fib6_add_1(root, &rt->rt6i_dst.addr, sizeof(struct in6_addr),
rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst),
allow_create, replace_required);
if (IS_ERR(fn)) {
err = PTR_ERR(fn);
fn = NULL;
}
if (!fn)
goto out;
pn = fn;
#ifdef CONFIG_IPV6_SUBTREES
if (rt->rt6i_src.plen) {
struct fib6_node *sn;
if (!fn->subtree) {
struct fib6_node *sfn;
/*
* Create subtree.
*
* fn[main tree]
* |
* sfn[subtree root]
* \
* sn[new leaf node]
*/
/* Create subtree root node */
sfn = node_alloc();
if (!sfn)
goto st_failure;
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();
/* Now add the first leaf node to new subtree */
sn = fib6_add_1(sfn, &rt->rt6i_src.addr,
sizeof(struct in6_addr), rt->rt6i_src.plen,
offsetof(struct rt6_info, rt6i_src),
allow_create, replace_required);
if (!sn) {
/* If it is failed, discard just allocated
root, and then (in st_failure) stale node
in main tree.
*/
node_free(sfn);
goto st_failure;
}
/* Now link new subtree to main tree */
sfn->parent = fn;
fn->subtree = sfn;
} else {
sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr,
sizeof(struct in6_addr), rt->rt6i_src.plen,
offsetof(struct rt6_info, rt6i_src),
allow_create, replace_required);
if (IS_ERR(sn)) {
err = PTR_ERR(sn);
sn = NULL;
}
if (!sn)
goto st_failure;
}
if (!fn->leaf) {
fn->leaf = rt;
atomic_inc(&rt->rt6i_ref);
}
fn = sn;
}
#endif
err = fib6_add_rt2node(fn, rt, info);
if (!err) {
fib6_start_gc(info->nl_net, rt);
if (!(rt->rt6i_flags & RTF_CACHE))
fib6_prune_clones(info->nl_net, pn, rt);
}
out:
if (err) {
#ifdef CONFIG_IPV6_SUBTREES
/*
* 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(info->nl_net, pn);
#if RT6_DEBUG >= 2
if (!pn->leaf) {
WARN_ON(pn->leaf == NULL);
pn->leaf = info->nl_net->ipv6.ip6_null_entry;
}
#endif
atomic_inc(&pn->leaf->rt6i_ref);
}
#endif
dst_free(&rt->dst);
}
return err;
#ifdef CONFIG_IPV6_SUBTREES
/* Subtree creation failed, probably main tree node
is orphan. If it is, shoot it.
*/
st_failure:
if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)))
fib6_repair_tree(info->nl_net, fn);
dst_free(&rt->dst);
return err;
#endif
}
/*
* Routing tree lookup
*
*/
struct lookup_args {
int offset; /* key offset on rt6_info */
const struct in6_addr *addr; /* search key */
};
static struct fib6_node * fib6_lookup_1(struct fib6_node *root,
struct lookup_args *args)
{
struct fib6_node *fn;
__be32 dir;
if (unlikely(args->offset == 0))
return NULL;
/*
* Descend on a tree
*/
fn = root;
for (;;) {
struct fib6_node *next;
dir = addr_bit_set(args->addr, fn->fn_bit);
next = dir ? fn->right : fn->left;
if (next) {
fn = next;
continue;
}
break;
}
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)) {
#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;
}
return NULL;
}
struct fib6_node * fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
struct fib6_node *fn;
struct lookup_args args[] = {
{
.offset = offsetof(struct rt6_info, rt6i_dst),
.addr = daddr,
},
#ifdef CONFIG_IPV6_SUBTREES
{
.offset = offsetof(struct rt6_info, rt6i_src),
.addr = saddr,
},
#endif
{
.offset = 0, /* sentinel */
}
};
fn = fib6_lookup_1(root, daddr ? args : args + 1);
if (!fn || fn->fn_flags & RTN_TL_ROOT)
fn = root;
return fn;
}
/*
* Get node with specified destination prefix (and source prefix,
* if subtrees are used)
*/
static struct fib6_node * fib6_locate_1(struct fib6_node *root,
const struct in6_addr *addr,
int plen, int offset)
{
struct fib6_node *fn;
for (fn = root; fn ; ) {
struct rt6key *key = (struct rt6key *)((u8 *)fn->leaf + offset);
/*
* Prefix match
*/
if (plen < fn->fn_bit ||
!ipv6_prefix_equal(&key->addr, addr, fn->fn_bit))
return NULL;
if (plen == fn->fn_bit)
return fn;
/*
* We have more bits to go
*/
if (addr_bit_set(addr, fn->fn_bit))
fn = fn->right;
else
fn = fn->left;
}
return NULL;
}
struct fib6_node * fib6_locate(struct fib6_node *root,
const struct in6_addr *daddr, int dst_len,
const struct in6_addr *saddr, int src_len)
{
struct fib6_node *fn;
fn = fib6_locate_1(root, daddr, dst_len,
offsetof(struct rt6_info, rt6i_dst));
#ifdef CONFIG_IPV6_SUBTREES
if (src_len) {
WARN_ON(saddr == NULL);
if (fn && fn->subtree)
fn = fib6_locate_1(fn->subtree, saddr, src_len,
offsetof(struct rt6_info, rt6i_src));
}
#endif
if (fn && fn->fn_flags & RTN_RTINFO)
return fn;
return NULL;
}
/*
* Deletion
*
*/
static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn)
{
if (fn->fn_flags & RTN_ROOT)
return net->ipv6.ip6_null_entry;
while (fn) {
if (fn->left)
return fn->left->leaf;
if (fn->right)
return fn->right->leaf;
fn = FIB6_SUBTREE(fn);
}
return NULL;
}
/*
* Called to trim the tree of intermediate nodes when possible. "fn"
* is the node we want to try and remove.
*/
static struct fib6_node *fib6_repair_tree(struct net *net,
struct fib6_node *fn)
{
int children;
int nstate;
struct fib6_node *child, *pn;
struct fib6_walker_t *w;
int iter = 0;
for (;;) {
RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter);
iter++;
WARN_ON(fn->fn_flags & RTN_RTINFO);
WARN_ON(fn->fn_flags & RTN_TL_ROOT);
WARN_ON(fn->leaf != NULL);
children = 0;
child = NULL;
if (fn->right) child = fn->right, children |= 1;
if (fn->left) child = fn->left, children |= 2;
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(net, fn);
#if RT6_DEBUG >= 2
if (!fn->leaf) {
WARN_ON(!fn->leaf);
fn->leaf = net->ipv6.ip6_null_entry;
}
#endif
atomic_inc(&fn->leaf->rt6i_ref);
return fn->parent;
}
pn = fn->parent;
#ifdef CONFIG_IPV6_SUBTREES
if (FIB6_SUBTREE(pn) == fn) {
WARN_ON(!(fn->fn_flags & RTN_ROOT));
FIB6_SUBTREE(pn) = NULL;
nstate = FWS_L;
} else {
WARN_ON(fn->fn_flags & RTN_ROOT);
#endif
if (pn->right == fn) pn->right = child;
else if (pn->left == fn) pn->left = child;
#if RT6_DEBUG >= 2
else
WARN_ON(1);
#endif
if (child)
child->parent = pn;
nstate = FWS_R;
#ifdef CONFIG_IPV6_SUBTREES
}
#endif
read_lock(&fib6_walker_lock);
FOR_WALKERS(w) {
if (!child) {
if (w->root == fn) {
w->root = w->node = NULL;
RT6_TRACE("W %p adjusted by delroot 1\n", w);
} else if (w->node == fn) {
RT6_TRACE("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate);
w->node = pn;
w->state = nstate;
}
} else {
if (w->root == fn) {
w->root = child;
RT6_TRACE("W %p adjusted by delroot 2\n", w);
}
if (w->node == fn) {
w->node = child;
if (children&2) {
RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state);
w->state = w->state>=FWS_R ? FWS_U : FWS_INIT;
} else {
RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state);
w->state = w->state>=FWS_C ? FWS_U : FWS_INIT;
}
}
}
}
read_unlock(&fib6_walker_lock);
node_free(fn);
if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn))
return pn;
rt6_release(pn->leaf);
pn->leaf = NULL;
fn = pn;
}
}
static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
struct nl_info *info)
{
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->dst.rt6_next;
rt->rt6i_node = NULL;
net->ipv6.rt6_stats->fib_rt_entries--;
net->ipv6.rt6_stats->fib_discarded_routes++;
[IPV6]: Fix routing round-robin locking. As per RFC2461, section 6.3.6, item #2, when no routers on the matching list are known to be reachable or probably reachable we do round robin on those available routes so that we make sure to probe as many of them as possible to detect when one becomes reachable faster. Each routing table has a rwlock protecting the tree and the linked list of routes at each leaf. The round robin code executes during lookup and thus with the rwlock taken as a reader. A small local spinlock tries to provide protection but this does not work at all for two reasons: 1) The round-robin list manipulation, as coded, goes like this (with read lock held): walk routes finding head and tail spin_lock(); rotate list using head and tail spin_unlock(); While one thread is rotating the list, another thread can end up with stale values of head and tail and then proceed to corrupt the list when it gets the lock. This ends up causing the OOPS in fib6_add() later onthat many people have been hitting. 2) All the other code paths that run with the rwlock held as a reader do not expect the list to change on them, they expect it to remain completely fixed while they hold the lock in that way. So, simply stated, it is impossible to implement this correctly using a manipulation of the list without violating the rwlock locking semantics. Reimplement using a per-fib6_node round-robin pointer. This way we don't need to manipulate the list at all, and since the round-robin pointer can only ever point to real existing entries we don't need to perform any locking on the changing of the round-robin pointer itself. We only need to reset the round-robin pointer to NULL when the entry it is pointing to is removed. The idea is from Thomas Graf and it is very similar to how this was implemented before the advanced router selection code when in. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-25 03:36:25 +00:00
/* 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->dst.rt6_next;
if (!w->leaf)
w->state = FWS_U;
}
}
read_unlock(&fib6_walker_lock);
rt->dst.rt6_next = NULL;
/* If it was last route, expunge its radix tree node */
if (!fn->leaf) {
fn->fn_flags &= ~RTN_RTINFO;
net->ipv6.rt6_stats->fib_route_nodes--;
fn = fib6_repair_tree(net, fn);
}
if (atomic_read(&rt->rt6i_ref) != 1) {
/* This route is used as dummy address holder in some split
* nodes. It is not leaked, but it still holds other resources,
* which must be released in time. So, scan ascendant nodes
* and replace dummy references to this route with references
* to still alive ones.
*/
while (fn) {
if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) {
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. */
BUG_ON(atomic_read(&rt->rt6i_ref) != 1);
}
inet6_rt_notify(RTM_DELROUTE, rt, info);
rt6_release(rt);
}
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;
#if RT6_DEBUG >= 2
if (rt->dst.obsolete>0) {
WARN_ON(fn != NULL);
return -ENOENT;
}
#endif
if (!fn || rt == net->ipv6.ip6_null_entry)
return -ENOENT;
WARN_ON(!(fn->fn_flags & RTN_RTINFO));
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)->dst.rt6_next) {
if (*rtp == rt) {
fib6_del_route(fn, rtp, info);
return 0;
}
}
return -ENOENT;
}
/*
* Tree traversal function.
*
* Certainly, it is not interrupt safe.
* 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.
*
* It guarantees that every node will be traversed,
* and that it will be traversed only once.
*
* Callback function w->func may return:
* 0 -> continue walking.
* positive value -> walking is suspended (used by tree dumps,
* and probably by gc, if it will be split to several slices)
* negative value -> terminate walking.
*
* The function itself returns:
* 0 -> walk is complete.
* >0 -> walk is incomplete (i.e. suspended)
* <0 -> walk is terminated by an error.
*/
static int fib6_walk_continue(struct fib6_walker_t *w)
{
struct fib6_node *fn, *pn;
for (;;) {
fn = w->node;
if (!fn)
return 0;
if (w->prune && fn != w->root &&
fn->fn_flags & RTN_RTINFO && w->state < FWS_C) {
w->state = FWS_C;
w->leaf = fn->leaf;
}
switch (w->state) {
#ifdef CONFIG_IPV6_SUBTREES
case FWS_S:
if (FIB6_SUBTREE(fn)) {
w->node = FIB6_SUBTREE(fn);
continue;
}
w->state = FWS_L;
#endif
case FWS_L:
if (fn->left) {
w->node = fn->left;
w->state = FWS_INIT;
continue;
}
w->state = FWS_R;
case FWS_R:
if (fn->right) {
w->node = fn->right;
w->state = FWS_INIT;
continue;
}
w->state = FWS_C;
w->leaf = fn->leaf;
case FWS_C:
if (w->leaf && fn->fn_flags & RTN_RTINFO) {
ipv6: fib: fix crash when changing large fib while dumping it When the fib size exceeds what can be dumped in a single skb, the dump is suspended and resumed once the last skb has been received by userspace. When the fib is changed while the dump is suspended, the walker might contain stale pointers, causing a crash when the dump is resumed. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] PGD 5347a067 PUD 65c7067 PMD 0 Oops: 0000 [#1] PREEMPT SMP ... RIP: 0010:[<ffffffffa01bce04>] [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] ... Call Trace: [<ffffffff8104aca3>] ? mutex_spin_on_owner+0x59/0x71 [<ffffffffa01bd105>] inet6_dump_fib+0x11b/0x1b9 [ipv6] [<ffffffff81371af4>] netlink_dump+0x5b/0x19e [<ffffffff8134f288>] ? consume_skb+0x28/0x2a [<ffffffff81373b69>] netlink_recvmsg+0x1ab/0x2c6 [<ffffffff81372781>] ? netlink_unicast+0xfa/0x151 [<ffffffff813483e0>] __sock_recvmsg+0x6d/0x79 [<ffffffff81348a53>] sock_recvmsg+0xca/0xe3 [<ffffffff81066d4b>] ? autoremove_wake_function+0x0/0x38 [<ffffffff811ed1f8>] ? radix_tree_lookup_slot+0xe/0x10 [<ffffffff810b3ed7>] ? find_get_page+0x90/0xa5 [<ffffffff810b5dc5>] ? filemap_fault+0x201/0x34f [<ffffffff810ef152>] ? fget_light+0x2f/0xac [<ffffffff813519e7>] ? verify_iovec+0x4f/0x94 [<ffffffff81349a65>] sys_recvmsg+0x14d/0x223 Store the serial number when beginning to walk the fib and reload pointers when continuing to walk after a change occured. Similar to other dumping functions, this might cause unrelated entries to be missed when entries are deleted. Tested-by: Ben Greear <greearb@candelatech.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-08 05:19:03 +00:00
int err;
if (w->count < w->skip) {
w->count++;
continue;
}
err = w->func(w);
if (err)
return err;
ipv6: fib: fix crash when changing large fib while dumping it When the fib size exceeds what can be dumped in a single skb, the dump is suspended and resumed once the last skb has been received by userspace. When the fib is changed while the dump is suspended, the walker might contain stale pointers, causing a crash when the dump is resumed. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] PGD 5347a067 PUD 65c7067 PMD 0 Oops: 0000 [#1] PREEMPT SMP ... RIP: 0010:[<ffffffffa01bce04>] [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] ... Call Trace: [<ffffffff8104aca3>] ? mutex_spin_on_owner+0x59/0x71 [<ffffffffa01bd105>] inet6_dump_fib+0x11b/0x1b9 [ipv6] [<ffffffff81371af4>] netlink_dump+0x5b/0x19e [<ffffffff8134f288>] ? consume_skb+0x28/0x2a [<ffffffff81373b69>] netlink_recvmsg+0x1ab/0x2c6 [<ffffffff81372781>] ? netlink_unicast+0xfa/0x151 [<ffffffff813483e0>] __sock_recvmsg+0x6d/0x79 [<ffffffff81348a53>] sock_recvmsg+0xca/0xe3 [<ffffffff81066d4b>] ? autoremove_wake_function+0x0/0x38 [<ffffffff811ed1f8>] ? radix_tree_lookup_slot+0xe/0x10 [<ffffffff810b3ed7>] ? find_get_page+0x90/0xa5 [<ffffffff810b5dc5>] ? filemap_fault+0x201/0x34f [<ffffffff810ef152>] ? fget_light+0x2f/0xac [<ffffffff813519e7>] ? verify_iovec+0x4f/0x94 [<ffffffff81349a65>] sys_recvmsg+0x14d/0x223 Store the serial number when beginning to walk the fib and reload pointers when continuing to walk after a change occured. Similar to other dumping functions, this might cause unrelated entries to be missed when entries are deleted. Tested-by: Ben Greear <greearb@candelatech.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-08 05:19:03 +00:00
w->count++;
continue;
}
w->state = FWS_U;
case FWS_U:
if (fn == w->root)
return 0;
pn = fn->parent;
w->node = pn;
#ifdef CONFIG_IPV6_SUBTREES
if (FIB6_SUBTREE(pn) == fn) {
WARN_ON(!(fn->fn_flags & RTN_ROOT));
w->state = FWS_L;
continue;
}
#endif
if (pn->left == fn) {
w->state = FWS_R;
continue;
}
if (pn->right == fn) {
w->state = FWS_C;
w->leaf = w->node->leaf;
continue;
}
#if RT6_DEBUG >= 2
WARN_ON(1);
#endif
}
}
}
static int fib6_walk(struct fib6_walker_t *w)
{
int res;
w->state = FWS_INIT;
w->node = w->root;
fib6_walker_link(w);
res = fib6_walk_continue(w);
if (res <= 0)
fib6_walker_unlink(w);
return res;
}
static int fib6_clean_node(struct fib6_walker_t *w)
{
int res;
struct rt6_info *rt;
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->dst.rt6_next) {
res = c->func(rt, c->arg);
if (res < 0) {
w->leaf = rt;
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);
#endif
continue;
}
return 0;
}
WARN_ON(res != 0);
}
w->leaf = rt;
return 0;
}
/*
* Convenient frontend to tree walker.
*
* func is called on each route.
* It may return -1 -> delete this route.
* 0 -> continue walking
*
* prune==1 -> only immediate children of node (certainly,
* ignoring pure split nodes) will be scanned.
*/
static void fib6_clean_tree(struct net *net, struct fib6_node *root,
int (*func)(struct rt6_info *, void *arg),
int prune, void *arg)
{
struct fib6_cleaner_t c;
c.w.root = root;
c.w.func = fib6_clean_node;
c.w.prune = prune;
ipv6: fib: fix crash when changing large fib while dumping it When the fib size exceeds what can be dumped in a single skb, the dump is suspended and resumed once the last skb has been received by userspace. When the fib is changed while the dump is suspended, the walker might contain stale pointers, causing a crash when the dump is resumed. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] PGD 5347a067 PUD 65c7067 PMD 0 Oops: 0000 [#1] PREEMPT SMP ... RIP: 0010:[<ffffffffa01bce04>] [<ffffffffa01bce04>] fib6_walk_continue+0xbb/0x124 [ipv6] ... Call Trace: [<ffffffff8104aca3>] ? mutex_spin_on_owner+0x59/0x71 [<ffffffffa01bd105>] inet6_dump_fib+0x11b/0x1b9 [ipv6] [<ffffffff81371af4>] netlink_dump+0x5b/0x19e [<ffffffff8134f288>] ? consume_skb+0x28/0x2a [<ffffffff81373b69>] netlink_recvmsg+0x1ab/0x2c6 [<ffffffff81372781>] ? netlink_unicast+0xfa/0x151 [<ffffffff813483e0>] __sock_recvmsg+0x6d/0x79 [<ffffffff81348a53>] sock_recvmsg+0xca/0xe3 [<ffffffff81066d4b>] ? autoremove_wake_function+0x0/0x38 [<ffffffff811ed1f8>] ? radix_tree_lookup_slot+0xe/0x10 [<ffffffff810b3ed7>] ? find_get_page+0x90/0xa5 [<ffffffff810b5dc5>] ? filemap_fault+0x201/0x34f [<ffffffff810ef152>] ? fget_light+0x2f/0xac [<ffffffff813519e7>] ? verify_iovec+0x4f/0x94 [<ffffffff81349a65>] sys_recvmsg+0x14d/0x223 Store the serial number when beginning to walk the fib and reload pointers when continuing to walk after a change occured. Similar to other dumping functions, this might cause unrelated entries to be missed when entries are deleted. Tested-by: Ben Greear <greearb@candelatech.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-02-08 05:19:03 +00:00
c.w.count = 0;
c.w.skip = 0;
c.func = func;
c.arg = arg;
c.net = net;
fib6_walk(&c.w);
}
IPv6: Avoid taking write lock for /proc/net/ipv6_route During some debugging I needed to look into how /proc/net/ipv6_route operated and in my digging I found its calling fib6_clean_all() which uses "write_lock_bh(&table->tb6_lock)" before doing the walk of the table. I found this on 2.6.32, but reading the code I believe the same basic idea exists currently. Looking at the rtnetlink code they are only calling "read_lock_bh(&table->tb6_lock);" via fib6_dump_table(). While I realize reading from proc isn't the recommended way of fetching the ipv6 route table; taking a write lock seems unnecessary and would probably cause network performance issues. To verify this I loaded up the ipv6 route table and then ran iperf in 3 cases: * doing nothing * reading ipv6 route table via proc (while :; do cat /proc/net/ipv6_route > /dev/null; done) * reading ipv6 route table via rtnetlink (while :; do ip -6 route show table all > /dev/null; done) * Load the ipv6 route table up with: * for ((i = 0;i < 4000;i++)); do ip route add unreachable 2000::$i; done * iperf commands: * client: iperf -i 1 -V -c <ipv6 addr> * server: iperf -V -s * iperf results - 3 runs each (in Mbits/sec) * nothing: client: 927,927,927 server: 927,927,927 * proc: client: 179,97,96,113 server: 142,112,133 * iproute: client: 928,927,928 server: 927,927,927 lock_stat shows taking the write lock is causing the slowdown. Using this info I decided to write a version of fib6_clean_all() which replaces write_lock_bh(&table->tb6_lock) with read_lock_bh(&table->tb6_lock). With this new function I see the same results as with my rtnetlink iperf test. Signed-off-by: Josh Hunt <joshhunt00@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-28 13:23:07 +00:00
void fib6_clean_all_ro(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 < FIB6_TABLE_HASHSZ; h++) {
head = &net->ipv6.fib_table_hash[h];
hlist_for_each_entry_rcu(table, node, head, tb6_hlist) {
read_lock_bh(&table->tb6_lock);
fib6_clean_tree(net, &table->tb6_root,
func, prune, arg);
read_unlock_bh(&table->tb6_lock);
}
}
rcu_read_unlock();
}
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 < FIB6_TABLE_HASHSZ; h++) {
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(net, &table->tb6_root,
func, prune, arg);
write_unlock_bh(&table->tb6_lock);
}
}
rcu_read_unlock();
}
static int fib6_prune_clone(struct rt6_info *rt, void *arg)
{
if (rt->rt6i_flags & RTF_CACHE) {
RT6_TRACE("pruning clone %p\n", rt);
return -1;
}
return 0;
}
static void fib6_prune_clones(struct net *net, struct fib6_node *fn,
struct rt6_info *rt)
{
fib6_clean_tree(net, fn, fib6_prune_clone, 1, rt);
}
/*
* Garbage collection
*/
static struct fib6_gc_args
{
int timeout;
int more;
} gc_args;
static int fib6_age(struct rt6_info *rt, void *arg)
{
unsigned long now = jiffies;
/*
* check addrconf expiration here.
* Routes are expired even if they are in use.
*
* Also age clones. Note, that clones are aged out
* only if they are not in use now.
*/
if (rt->rt6i_flags & RTF_EXPIRES && rt->dst.expires) {
if (time_after(now, rt->dst.expires)) {
RT6_TRACE("expiring %p\n", rt);
return -1;
}
gc_args.more++;
} else if (rt->rt6i_flags & RTF_CACHE) {
if (atomic_read(&rt->dst.__refcnt) == 0 &&
time_after_eq(now, rt->dst.lastuse + gc_args.timeout)) {
RT6_TRACE("aging clone %p\n", rt);
return -1;
} else if (rt->rt6i_flags & RTF_GATEWAY) {
struct neighbour *neigh;
__u8 neigh_flags = 0;
neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway);
if (neigh) {
neigh_flags = neigh->flags;
neigh_release(neigh);
}
if (neigh_flags & NTF_ROUTER) {
RT6_TRACE("purging route %p via non-router but gateway\n",
rt);
return -1;
}
}
gc_args.more++;
}
return 0;
}
static DEFINE_SPINLOCK(fib6_gc_lock);
void fib6_run_gc(unsigned long expires, struct net *net)
{
if (expires != ~0UL) {
spin_lock_bh(&fib6_gc_lock);
gc_args.timeout = expires ? (int)expires :
net->ipv6.sysctl.ip6_rt_gc_interval;
} else {
if (!spin_trylock_bh(&fib6_gc_lock)) {
mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ);
return;
}
gc_args.timeout = net->ipv6.sysctl.ip6_rt_gc_interval;
}
gc_args.more = icmp6_dst_gc();
fib6_clean_all(net, fib6_age, 0, NULL);
if (gc_args.more)
mod_timer(&net->ipv6.ip6_fib_timer,
round_jiffies(jiffies
+ net->ipv6.sysctl.ip6_rt_gc_interval));
else
del_timer(&net->ipv6.ip6_fib_timer);
spin_unlock_bh(&fib6_gc_lock);
}
static void fib6_gc_timer_cb(unsigned long arg)
{
fib6_run_gc(0, (struct net *)arg);
}
static int __net_init fib6_net_init(struct net *net)
{
size_t size = sizeof(struct hlist_head) * FIB6_TABLE_HASHSZ;
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;
/* Avoid false sharing : Use at least a full cache line */
size = max_t(size_t, size, L1_CACHE_BYTES);
net->ipv6.fib_table_hash = kzalloc(size, 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);
if (!fib6_node_kmem)
goto out;
ret = register_pernet_subsys(&fib6_net_ops);
if (ret)
goto out_kmem_cache_create;
ret = __rtnl_register(PF_INET6, RTM_GETROUTE, NULL, inet6_dump_fib,
NULL);
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)
{
unregister_pernet_subsys(&fib6_net_ops);
kmem_cache_destroy(fib6_node_kmem);
}