3.6.11.1 stable review patch. If anyone has any objections, please let me know. ------------------ From: Christoph Paasch [ Upstream commit e337e24d6624e74a558aa69071e112a65f7b5758 ] 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: [] kmemleak_alloc+0x21/0x3e [] kmem_cache_alloc+0xb5/0xc5 [] sk_prot_alloc.isra.53+0x2b/0xcd [] sk_clone_lock+0x16/0x21e [] inet_csk_clone_lock+0x10/0x7b [] tcp_create_openreq_child+0x21/0x481 [] tcp_v4_syn_recv_sock+0x3a/0x23b [] tcp_check_req+0x29f/0x416 [] tcp_v4_do_rcv+0x161/0x2bc [] tcp_v4_rcv+0x6c9/0x701 [] ip_local_deliver_finish+0x70/0xc4 [] ip_local_deliver+0x4e/0x7f [] ip_rcv_finish+0x1fc/0x233 [] ip_rcv+0x217/0x267 [] __netif_receive_skb+0x49e/0x553 [] 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 093d282321 (tproxy: fix hash locking issue when using port redirection in __inet_inherit_port()), thus since version >= 2.6.37. Signed-off-by: Christoph Paasch Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 1 + net/dccp/ipv4.c | 4 ++-- net/dccp/ipv6.c | 3 ++- net/ipv4/inet_connection_sock.c | 16 ++++++++++++++++ net/ipv4/tcp_ipv4.c | 6 ++---- net/ipv6/tcp_ipv6.c | 3 ++- 6 files changed, 25 insertions(+), 8 deletions(-) diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index ba1d361..1832927 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -318,6 +318,7 @@ extern void inet_csk_reqsk_queue_prune(struct sock *parent, const unsigned long max_rto); 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.. diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 176ecdb..4f9f5eb 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -439,8 +439,8 @@ exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; put_and_exit: - bh_unlock_sock(newsk); - sock_put(newsk); + inet_csk_prepare_forced_close(newsk); + dccp_done(newsk); goto exit; } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 56840b2..6e05981 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -585,7 +585,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, newinet->inet_rcv_saddr = LOOPBACK4_IPV6; if (__inet_inherit_port(sk, newsk) < 0) { - sock_put(newsk); + inet_csk_prepare_forced_close(newsk); + dccp_done(newsk); goto out; } __inet6_hash(newsk, NULL); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 0405cc8..567c31f 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -679,6 +679,22 @@ void inet_csk_destroy_sock(struct sock *sk) } 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) { struct inet_sock *inet = inet_sk(sk); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index db7bfad..4705caf 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1537,10 +1537,8 @@ exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; put_and_exit: - tcp_clear_xmit_timers(newsk); - tcp_cleanup_congestion_control(newsk); - bh_unlock_sock(newsk); - sock_put(newsk); + inet_csk_prepare_forced_close(newsk); + tcp_done(newsk); goto exit; } EXPORT_SYMBOL(tcp_v4_syn_recv_sock); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7e32d42..8b45fb4 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1371,7 +1371,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, #endif if (__inet_inherit_port(sk, newsk) < 0) { - sock_put(newsk); + inet_csk_prepare_forced_close(newsk); + tcp_done(newsk); goto out; } __inet6_hash(newsk, NULL); -- 1.7.10.4 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/