Commit e337e24d authored by Christoph Paasch's avatar Christoph Paasch Committed by David S. Miller

inet: Fix kmemleak in tcp_v4/6_syn_recv_sock and dccp_v4/6_request_recv_sock

If in either of the above functions inet_csk_route_child_sock() or
__inet_inherit_port() fails, the newsk will not be freed:

unreferenced object 0xffff88022e8a92c0 (size 1592):
  comm "softirq", pid 0, jiffies 4294946244 (age 726.160s)
  hex dump (first 32 bytes):
    0a 01 01 01 0a 01 01 02 00 00 00 00 a7 cc 16 00  ................
    02 00 03 01 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<ffffffff8153d190>] kmemleak_alloc+0x21/0x3e
    [<ffffffff810ab3e7>] kmem_cache_alloc+0xb5/0xc5
    [<ffffffff8149b65b>] sk_prot_alloc.isra.53+0x2b/0xcd
    [<ffffffff8149b784>] sk_clone_lock+0x16/0x21e
    [<ffffffff814d711a>] inet_csk_clone_lock+0x10/0x7b
    [<ffffffff814ebbc3>] tcp_create_openreq_child+0x21/0x481
    [<ffffffff814e8fa5>] tcp_v4_syn_recv_sock+0x3a/0x23b
    [<ffffffff814ec5ba>] tcp_check_req+0x29f/0x416
    [<ffffffff814e8e10>] tcp_v4_do_rcv+0x161/0x2bc
    [<ffffffff814eb917>] tcp_v4_rcv+0x6c9/0x701
    [<ffffffff814cea9f>] ip_local_deliver_finish+0x70/0xc4
    [<ffffffff814cec20>] ip_local_deliver+0x4e/0x7f
    [<ffffffff814ce9f8>] ip_rcv_finish+0x1fc/0x233
    [<ffffffff814cee68>] ip_rcv+0x217/0x267
    [<ffffffff814a7bbe>] __netif_receive_skb+0x49e/0x553
    [<ffffffff814a7cc3>] netif_receive_skb+0x50/0x82

This happens, because sk_clone_lock initializes sk_refcnt to 2, and thus
a single sock_put() is not enough to free the memory. Additionally, things
like xfrm, memcg, cookie_values,... may have been initialized.
We have to free them properly.

This is fixed by forcing a call to tcp_done(), ending up in
inet_csk_destroy_sock, doing the final sock_put(). tcp_done() is necessary,
because it ends up doing all the cleanup on xfrm, memcg, cookie_values,
xfrm,...

Before calling tcp_done, we have to set the socket to SOCK_DEAD, to
force it entering inet_csk_destroy_sock. To avoid the warning in
inet_csk_destroy_sock, inet_num has to be set to 0.
As inet_csk_destroy_sock does a dec on orphan_count, we first have to
increase it.

Calling tcp_done() allows us to remove the calls to
tcp_clear_xmit_timer() and tcp_cleanup_congestion_control().

A similar approach is taken for dccp by calling dccp_done().

This is in the kernel since 093d2823 (tproxy: fix hash locking issue
when using port redirection in __inet_inherit_port()), thus since
version >= 2.6.37.
Signed-off-by: default avatarChristoph Paasch <christoph.paasch@uclouvain.be>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 093d04d4
...@@ -318,6 +318,7 @@ extern void inet_csk_reqsk_queue_prune(struct sock *parent, ...@@ -318,6 +318,7 @@ extern void inet_csk_reqsk_queue_prune(struct sock *parent,
const unsigned long max_rto); const unsigned long max_rto);
extern void inet_csk_destroy_sock(struct sock *sk); extern void inet_csk_destroy_sock(struct sock *sk);
extern void inet_csk_prepare_forced_close(struct sock *sk);
/* /*
* LISTEN is a special case for poll.. * LISTEN is a special case for poll..
......
...@@ -439,8 +439,8 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, ...@@ -439,8 +439,8 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb,
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
return NULL; return NULL;
put_and_exit: put_and_exit:
bh_unlock_sock(newsk); inet_csk_prepare_forced_close(newsk);
sock_put(newsk); dccp_done(newsk);
goto exit; goto exit;
} }
......
...@@ -585,7 +585,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, ...@@ -585,7 +585,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
newinet->inet_rcv_saddr = LOOPBACK4_IPV6; newinet->inet_rcv_saddr = LOOPBACK4_IPV6;
if (__inet_inherit_port(sk, newsk) < 0) { if (__inet_inherit_port(sk, newsk) < 0) {
sock_put(newsk); inet_csk_prepare_forced_close(newsk);
dccp_done(newsk);
goto out; goto out;
} }
__inet6_hash(newsk, NULL); __inet6_hash(newsk, NULL);
......
...@@ -710,6 +710,22 @@ void inet_csk_destroy_sock(struct sock *sk) ...@@ -710,6 +710,22 @@ void inet_csk_destroy_sock(struct sock *sk)
} }
EXPORT_SYMBOL(inet_csk_destroy_sock); EXPORT_SYMBOL(inet_csk_destroy_sock);
/* This function allows to force a closure of a socket after the call to
* tcp/dccp_create_openreq_child().
*/
void inet_csk_prepare_forced_close(struct sock *sk)
{
/* sk_clone_lock locked the socket and set refcnt to 2 */
bh_unlock_sock(sk);
sock_put(sk);
/* The below has to be done to allow calling inet_csk_destroy_sock */
sock_set_flag(sk, SOCK_DEAD);
percpu_counter_inc(sk->sk_prot->orphan_count);
inet_sk(sk)->inet_num = 0;
}
EXPORT_SYMBOL(inet_csk_prepare_forced_close);
int inet_csk_listen_start(struct sock *sk, const int nr_table_entries) int inet_csk_listen_start(struct sock *sk, const int nr_table_entries)
{ {
struct inet_sock *inet = inet_sk(sk); struct inet_sock *inet = inet_sk(sk);
......
...@@ -1767,10 +1767,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, ...@@ -1767,10 +1767,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
return NULL; return NULL;
put_and_exit: put_and_exit:
tcp_clear_xmit_timers(newsk); inet_csk_prepare_forced_close(newsk);
tcp_cleanup_congestion_control(newsk); tcp_done(newsk);
bh_unlock_sock(newsk);
sock_put(newsk);
goto exit; goto exit;
} }
EXPORT_SYMBOL(tcp_v4_syn_recv_sock); EXPORT_SYMBOL(tcp_v4_syn_recv_sock);
......
...@@ -1288,7 +1288,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, ...@@ -1288,7 +1288,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
#endif #endif
if (__inet_inherit_port(sk, newsk) < 0) { if (__inet_inherit_port(sk, newsk) < 0) {
sock_put(newsk); inet_csk_prepare_forced_close(newsk);
tcp_done(newsk);
goto out; goto out;
} }
__inet6_hash(newsk, NULL); __inet6_hash(newsk, NULL);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment