linux/net/ipv4/inet_timewait_sock.c
Eric Dumazet 3099a52918 soreuseport: initialise timewait reuseport field
syzbot reported an uninit-value in inet_csk_bind_conflict() [1]

It turns out we never propagated sk->sk_reuseport into timewait socket.

[1]
BUG: KMSAN: uninit-value in inet_csk_bind_conflict+0x5f9/0x990 net/ipv4/inet_connection_sock.c:151
CPU: 1 PID: 3589 Comm: syzkaller008242 Not tainted 4.16.0+ #82
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
 inet_csk_bind_conflict+0x5f9/0x990 net/ipv4/inet_connection_sock.c:151
 inet_csk_get_port+0x1d28/0x1e40 net/ipv4/inet_connection_sock.c:320
 inet6_bind+0x121c/0x1820 net/ipv6/af_inet6.c:399
 SYSC_bind+0x3f2/0x4b0 net/socket.c:1474
 SyS_bind+0x54/0x80 net/socket.c:1460
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x4416e9
RSP: 002b:00007ffce6d15c88 EFLAGS: 00000217 ORIG_RAX: 0000000000000031
RAX: ffffffffffffffda RBX: 0100000000000000 RCX: 00000000004416e9
RDX: 000000000000001c RSI: 0000000020402000 RDI: 0000000000000004
RBP: 0000000000000000 R08: 00000000e6d15e08 R09: 00000000e6d15e08
R10: 0000000000000004 R11: 0000000000000217 R12: 0000000000009478
R13: 00000000006cd448 R14: 0000000000000000 R15: 0000000000000000

Uninit was stored to memory at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
 kmsan_save_stack mm/kmsan/kmsan.c:293 [inline]
 kmsan_internal_chain_origin+0x12b/0x210 mm/kmsan/kmsan.c:684
 __msan_chain_origin+0x69/0xc0 mm/kmsan/kmsan_instr.c:521
 tcp_time_wait+0xf17/0xf50 net/ipv4/tcp_minisocks.c:283
 tcp_rcv_state_process+0xebe/0x6490 net/ipv4/tcp_input.c:6003
 tcp_v6_do_rcv+0x11dd/0x1d90 net/ipv6/tcp_ipv6.c:1331
 sk_backlog_rcv include/net/sock.h:908 [inline]
 __release_sock+0x2d6/0x680 net/core/sock.c:2271
 release_sock+0x97/0x2a0 net/core/sock.c:2786
 tcp_close+0x277/0x18f0 net/ipv4/tcp.c:2269
 inet_release+0x240/0x2a0 net/ipv4/af_inet.c:427
 inet6_release+0xaf/0x100 net/ipv6/af_inet6.c:435
 sock_release net/socket.c:595 [inline]
 sock_close+0xe0/0x300 net/socket.c:1149
 __fput+0x49e/0xa10 fs/file_table.c:209
 ____fput+0x37/0x40 fs/file_table.c:243
 task_work_run+0x243/0x2c0 kernel/task_work.c:113
 exit_task_work include/linux/task_work.h:22 [inline]
 do_exit+0x10e1/0x38d0 kernel/exit.c:867
 do_group_exit+0x1a0/0x360 kernel/exit.c:970
 SYSC_exit_group+0x21/0x30 kernel/exit.c:981
 SyS_exit_group+0x25/0x30 kernel/exit.c:979
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
Uninit was stored to memory at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
 kmsan_save_stack mm/kmsan/kmsan.c:293 [inline]
 kmsan_internal_chain_origin+0x12b/0x210 mm/kmsan/kmsan.c:684
 __msan_chain_origin+0x69/0xc0 mm/kmsan/kmsan_instr.c:521
 inet_twsk_alloc+0xaef/0xc00 net/ipv4/inet_timewait_sock.c:182
 tcp_time_wait+0xd9/0xf50 net/ipv4/tcp_minisocks.c:258
 tcp_rcv_state_process+0xebe/0x6490 net/ipv4/tcp_input.c:6003
 tcp_v6_do_rcv+0x11dd/0x1d90 net/ipv6/tcp_ipv6.c:1331
 sk_backlog_rcv include/net/sock.h:908 [inline]
 __release_sock+0x2d6/0x680 net/core/sock.c:2271
 release_sock+0x97/0x2a0 net/core/sock.c:2786
 tcp_close+0x277/0x18f0 net/ipv4/tcp.c:2269
 inet_release+0x240/0x2a0 net/ipv4/af_inet.c:427
 inet6_release+0xaf/0x100 net/ipv6/af_inet6.c:435
 sock_release net/socket.c:595 [inline]
 sock_close+0xe0/0x300 net/socket.c:1149
 __fput+0x49e/0xa10 fs/file_table.c:209
 ____fput+0x37/0x40 fs/file_table.c:243
 task_work_run+0x243/0x2c0 kernel/task_work.c:113
 exit_task_work include/linux/task_work.h:22 [inline]
 do_exit+0x10e1/0x38d0 kernel/exit.c:867
 do_group_exit+0x1a0/0x360 kernel/exit.c:970
 SYSC_exit_group+0x21/0x30 kernel/exit.c:981
 SyS_exit_group+0x25/0x30 kernel/exit.c:979
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
 kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188
 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314
 kmem_cache_alloc+0xaab/0xb90 mm/slub.c:2756
 inet_twsk_alloc+0x13b/0xc00 net/ipv4/inet_timewait_sock.c:163
 tcp_time_wait+0xd9/0xf50 net/ipv4/tcp_minisocks.c:258
 tcp_rcv_state_process+0xebe/0x6490 net/ipv4/tcp_input.c:6003
 tcp_v6_do_rcv+0x11dd/0x1d90 net/ipv6/tcp_ipv6.c:1331
 sk_backlog_rcv include/net/sock.h:908 [inline]
 __release_sock+0x2d6/0x680 net/core/sock.c:2271
 release_sock+0x97/0x2a0 net/core/sock.c:2786
 tcp_close+0x277/0x18f0 net/ipv4/tcp.c:2269
 inet_release+0x240/0x2a0 net/ipv4/af_inet.c:427
 inet6_release+0xaf/0x100 net/ipv6/af_inet6.c:435
 sock_release net/socket.c:595 [inline]
 sock_close+0xe0/0x300 net/socket.c:1149
 __fput+0x49e/0xa10 fs/file_table.c:209
 ____fput+0x37/0x40 fs/file_table.c:243
 task_work_run+0x243/0x2c0 kernel/task_work.c:113
 exit_task_work include/linux/task_work.h:22 [inline]
 do_exit+0x10e1/0x38d0 kernel/exit.c:867
 do_group_exit+0x1a0/0x360 kernel/exit.c:970
 SYSC_exit_group+0x21/0x30 kernel/exit.c:981
 SyS_exit_group+0x25/0x30 kernel/exit.c:979
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: da5e36308d ("soreuseport: TCP/IPv4 implementation")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-07 22:32:32 -04:00

302 lines
8.8 KiB
C

/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Generic TIME_WAIT sockets functions
*
* From code orinally in TCP
*/
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <net/inet_hashtables.h>
#include <net/inet_timewait_sock.h>
#include <net/ip.h>
/**
* inet_twsk_bind_unhash - unhash a timewait socket from bind hash
* @tw: timewait socket
* @hashinfo: hashinfo pointer
*
* unhash a timewait socket from bind hash, if hashed.
* bind hash lock must be held by caller.
* Returns 1 if caller should call inet_twsk_put() after lock release.
*/
void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
struct inet_hashinfo *hashinfo)
{
struct inet_bind_bucket *tb = tw->tw_tb;
if (!tb)
return;
__hlist_del(&tw->tw_bind_node);
tw->tw_tb = NULL;
inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
__sock_put((struct sock *)tw);
}
/* Must be called with locally disabled BHs. */
static void inet_twsk_kill(struct inet_timewait_sock *tw)
{
struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo;
spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
struct inet_bind_hashbucket *bhead;
spin_lock(lock);
sk_nulls_del_node_init_rcu((struct sock *)tw);
spin_unlock(lock);
/* Disassociate with bind bucket. */
bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num,
hashinfo->bhash_size)];
spin_lock(&bhead->lock);
inet_twsk_bind_unhash(tw, hashinfo);
spin_unlock(&bhead->lock);
atomic_dec(&tw->tw_dr->tw_count);
inet_twsk_put(tw);
}
void inet_twsk_free(struct inet_timewait_sock *tw)
{
struct module *owner = tw->tw_prot->owner;
twsk_destructor((struct sock *)tw);
#ifdef SOCK_REFCNT_DEBUG
pr_debug("%s timewait_sock %p released\n", tw->tw_prot->name, tw);
#endif
kmem_cache_free(tw->tw_prot->twsk_prot->twsk_slab, tw);
module_put(owner);
}
void inet_twsk_put(struct inet_timewait_sock *tw)
{
if (refcount_dec_and_test(&tw->tw_refcnt))
inet_twsk_free(tw);
}
EXPORT_SYMBOL_GPL(inet_twsk_put);
static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
struct hlist_nulls_head *list)
{
hlist_nulls_add_head_rcu(&tw->tw_node, list);
}
static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
struct hlist_head *list)
{
hlist_add_head(&tw->tw_bind_node, list);
}
/*
* Enter the time wait state. This is called with locally disabled BH.
* Essentially we whip up a timewait bucket, copy the relevant info into it
* from the SK, and mess with hash chains and list linkage.
*/
void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
struct inet_hashinfo *hashinfo)
{
const struct inet_sock *inet = inet_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash);
spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
struct inet_bind_hashbucket *bhead;
/* Step 1: Put TW into bind hash. Original socket stays there too.
Note, that any socket with inet->num != 0 MUST be bound in
binding cache, even if it is closed.
*/
bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
hashinfo->bhash_size)];
spin_lock(&bhead->lock);
tw->tw_tb = icsk->icsk_bind_hash;
WARN_ON(!icsk->icsk_bind_hash);
inet_twsk_add_bind_node(tw, &tw->tw_tb->owners);
spin_unlock(&bhead->lock);
spin_lock(lock);
inet_twsk_add_node_rcu(tw, &ehead->chain);
/* Step 3: Remove SK from hash chain */
if (__sk_nulls_del_node_init_rcu(sk))
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
spin_unlock(lock);
/* tw_refcnt is set to 3 because we have :
* - one reference for bhash chain.
* - one reference for ehash chain.
* - one reference for timer.
* We can use atomic_set() because prior spin_lock()/spin_unlock()
* committed into memory all tw fields.
* Also note that after this point, we lost our implicit reference
* so we are not allowed to use tw anymore.
*/
refcount_set(&tw->tw_refcnt, 3);
}
EXPORT_SYMBOL_GPL(inet_twsk_hashdance);
static void tw_timer_handler(struct timer_list *t)
{
struct inet_timewait_sock *tw = from_timer(tw, t, tw_timer);
if (tw->tw_kill)
__NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED);
else
__NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITED);
inet_twsk_kill(tw);
}
struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
struct inet_timewait_death_row *dr,
const int state)
{
struct inet_timewait_sock *tw;
if (atomic_read(&dr->tw_count) >= dr->sysctl_max_tw_buckets)
return NULL;
tw = kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab,
GFP_ATOMIC);
if (tw) {
const struct inet_sock *inet = inet_sk(sk);
tw->tw_dr = dr;
/* Give us an identity. */
tw->tw_daddr = inet->inet_daddr;
tw->tw_rcv_saddr = inet->inet_rcv_saddr;
tw->tw_bound_dev_if = sk->sk_bound_dev_if;
tw->tw_tos = inet->tos;
tw->tw_num = inet->inet_num;
tw->tw_state = TCP_TIME_WAIT;
tw->tw_substate = state;
tw->tw_sport = inet->inet_sport;
tw->tw_dport = inet->inet_dport;
tw->tw_family = sk->sk_family;
tw->tw_reuse = sk->sk_reuse;
tw->tw_reuseport = sk->sk_reuseport;
tw->tw_hash = sk->sk_hash;
tw->tw_ipv6only = 0;
tw->tw_transparent = inet->transparent;
tw->tw_prot = sk->sk_prot_creator;
atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie));
twsk_net_set(tw, sock_net(sk));
timer_setup(&tw->tw_timer, tw_timer_handler, TIMER_PINNED);
/*
* Because we use RCU lookups, we should not set tw_refcnt
* to a non null value before everything is setup for this
* timewait socket.
*/
refcount_set(&tw->tw_refcnt, 0);
__module_get(tw->tw_prot->owner);
}
return tw;
}
EXPORT_SYMBOL_GPL(inet_twsk_alloc);
/* These are always called from BH context. See callers in
* tcp_input.c to verify this.
*/
/* This is for handling early-kills of TIME_WAIT sockets.
* Warning : consume reference.
* Caller should not access tw anymore.
*/
void inet_twsk_deschedule_put(struct inet_timewait_sock *tw)
{
if (del_timer_sync(&tw->tw_timer))
inet_twsk_kill(tw);
inet_twsk_put(tw);
}
EXPORT_SYMBOL(inet_twsk_deschedule_put);
void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm)
{
/* timeout := RTO * 3.5
*
* 3.5 = 1+2+0.5 to wait for two retransmits.
*
* RATIONALE: if FIN arrived and we entered TIME-WAIT state,
* our ACK acking that FIN can be lost. If N subsequent retransmitted
* FINs (or previous seqments) are lost (probability of such event
* is p^(N+1), where p is probability to lose single packet and
* time to detect the loss is about RTO*(2^N - 1) with exponential
* backoff). Normal timewait length is calculated so, that we
* waited at least for one retransmitted FIN (maximal RTO is 120sec).
* [ BTW Linux. following BSD, violates this requirement waiting
* only for 60sec, we should wait at least for 240 secs.
* Well, 240 consumes too much of resources 8)
* ]
* This interval is not reduced to catch old duplicate and
* responces to our wandering segments living for two MSLs.
* However, if we use PAWS to detect
* old duplicates, we can reduce the interval to bounds required
* by RTO, rather than MSL. So, if peer understands PAWS, we
* kill tw bucket after 3.5*RTO (it is important that this number
* is greater than TS tick!) and detect old duplicates with help
* of PAWS.
*/
tw->tw_kill = timeo <= 4*HZ;
if (!rearm) {
BUG_ON(mod_timer(&tw->tw_timer, jiffies + timeo));
atomic_inc(&tw->tw_dr->tw_count);
} else {
mod_timer_pending(&tw->tw_timer, jiffies + timeo);
}
}
EXPORT_SYMBOL_GPL(__inet_twsk_schedule);
void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family)
{
struct inet_timewait_sock *tw;
struct sock *sk;
struct hlist_nulls_node *node;
unsigned int slot;
for (slot = 0; slot <= hashinfo->ehash_mask; slot++) {
struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
restart_rcu:
cond_resched();
rcu_read_lock();
restart:
sk_nulls_for_each_rcu(sk, node, &head->chain) {
if (sk->sk_state != TCP_TIME_WAIT)
continue;
tw = inet_twsk(sk);
if ((tw->tw_family != family) ||
refcount_read(&twsk_net(tw)->count))
continue;
if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt)))
continue;
if (unlikely((tw->tw_family != family) ||
refcount_read(&twsk_net(tw)->count))) {
inet_twsk_put(tw);
goto restart;
}
rcu_read_unlock();
local_bh_disable();
inet_twsk_deschedule_put(tw);
local_bh_enable();
goto restart_rcu;
}
/* If the nulls value we got at the end of this lookup is
* not the expected one, we must restart lookup.
* We probably met an item that was moved to another chain.
*/
if (get_nulls_value(node) != slot)
goto restart;
rcu_read_unlock();
}
}
EXPORT_SYMBOL_GPL(inet_twsk_purge);