From: Kuniyuki Iwashima kuniyu@amazon.com
commit d38afeec26ed4739c640bf286c270559aab2ba5f upstream.
Originally, inet6_sk(sk)->XXX were changed under lock_sock(), so we were able to clean them up by calling inet6_destroy_sock() during the IPv6 -> IPv4 conversion by IPV6_ADDRFORM. However, commit 03485f2adcde ("udpv6: Add lockless sendmsg() support") added a lockless memory allocation path, which could cause a memory leak:
setsockopt(IPV6_ADDRFORM) sendmsg() +-----------------------+ +-------+ - do_ipv6_setsockopt(sk, ...) - udpv6_sendmsg(sk, ...) - sockopt_lock_sock(sk) ^._ called via udpv6_prot - lock_sock(sk) before WRITE_ONCE() - WRITE_ONCE(sk->sk_prot, &tcp_prot) - inet6_destroy_sock() - if (!corkreq) - sockopt_release_sock(sk) - ip6_make_skb(sk, ...) - release_sock(sk) ^._ lockless fast path for the non-corking case
- __ip6_append_data(sk, ...) - ipv6_local_rxpmtu(sk, ...) - xchg(&np->rxpmtu, skb) ^._ rxpmtu is never freed.
- goto out_no_dst;
- lock_sock(sk)
For now, rxpmtu is only the case, but not to miss the future change and a similar bug fixed in commit e27326009a3d ("net: ping6: Fix memleak in ipv6_renew_options()."), let's set a new function to IPv6 sk->sk_destruct() and call inet6_cleanup_sock() there. Since the conversion does not change sk->sk_destruct(), we can guarantee that we can clean up IPv6 resources finally.
We can now remove all inet6_destroy_sock() calls from IPv6 protocol specific ->destroy() functions, but such changes are invasive to backport. So they can be posted as a follow-up later for net-next.
Fixes: 03485f2adcde ("udpv6: Add lockless sendmsg() support") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Ziyang Xuan william.xuanziyang@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/ipv6.h | 1 + include/net/udp.h | 2 +- include/net/udplite.h | 8 -------- net/ipv4/udp.c | 9 ++++++--- net/ipv4/udplite.c | 8 ++++++++ net/ipv6/af_inet6.c | 8 +++++++- net/ipv6/udp.c | 15 ++++++++++++++- net/ipv6/udp_impl.h | 1 + net/ipv6/udplite.c | 9 ++++++++- 9 files changed, 46 insertions(+), 15 deletions(-)
--- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1101,6 +1101,7 @@ void ipv6_local_error(struct sock *sk, i void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu);
void inet6_cleanup_sock(struct sock *sk); +void inet6_sock_destruct(struct sock *sk); int inet6_release(struct socket *sock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, --- a/include/net/udp.h +++ b/include/net/udp.h @@ -261,7 +261,7 @@ static inline bool udp_sk_bound_dev_eq(s }
/* net/ipv4/udp.c */ -void udp_destruct_sock(struct sock *sk); +void udp_destruct_common(struct sock *sk); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb); void udp_skb_destructor(struct sock *sk, struct sk_buff *skb); --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -24,14 +24,6 @@ static __inline__ int udplite_getfrag(vo return copy_from_iter_full(to, len, &msg->msg_iter) ? 0 : -EFAULT; }
-/* Designate sk as UDP-Lite socket */ -static inline int udplite_sk_init(struct sock *sk) -{ - udp_init_sock(sk); - udp_sk(sk)->pcflag = UDPLITE_BIT; - return 0; -} - /* * Checksumming routines */ --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1528,7 +1528,7 @@ drop: } EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb);
-void udp_destruct_sock(struct sock *sk) +void udp_destruct_common(struct sock *sk) { /* reclaim completely the forward allocated memory */ struct udp_sock *up = udp_sk(sk); @@ -1541,10 +1541,14 @@ void udp_destruct_sock(struct sock *sk) kfree_skb(skb); } udp_rmem_release(sk, total, 0, true); +} +EXPORT_SYMBOL_GPL(udp_destruct_common);
+static void udp_destruct_sock(struct sock *sk) +{ + udp_destruct_common(sk); inet_sock_destruct(sk); } -EXPORT_SYMBOL_GPL(udp_destruct_sock);
int udp_init_sock(struct sock *sk) { @@ -1552,7 +1556,6 @@ int udp_init_sock(struct sock *sk) sk->sk_destruct = udp_destruct_sock; return 0; } -EXPORT_SYMBOL_GPL(udp_init_sock);
void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) { --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -17,6 +17,14 @@ struct udp_table udplite_table __read_mostly; EXPORT_SYMBOL(udplite_table);
+/* Designate sk as UDP-Lite socket */ +static int udplite_sk_init(struct sock *sk) +{ + udp_init_sock(sk); + udp_sk(sk)->pcflag = UDPLITE_BIT; + return 0; +} + static int udplite_rcv(struct sk_buff *skb) { return __udp4_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE); --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -104,6 +104,12 @@ static __inline__ struct ipv6_pinfo *ine return (struct ipv6_pinfo *)(((u8 *)sk) + offset); }
+void inet6_sock_destruct(struct sock *sk) +{ + inet6_cleanup_sock(sk); + inet_sock_destruct(sk); +} + static int inet6_create(struct net *net, struct socket *sock, int protocol, int kern) { @@ -196,7 +202,7 @@ lookup_protocol: inet->hdrincl = 1; }
- sk->sk_destruct = inet_sock_destruct; + sk->sk_destruct = inet6_sock_destruct; sk->sk_family = PF_INET6; sk->sk_protocol = protocol;
--- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -54,6 +54,19 @@ #include <trace/events/skb.h> #include "udp_impl.h"
+static void udpv6_destruct_sock(struct sock *sk) +{ + udp_destruct_common(sk); + inet6_sock_destruct(sk); +} + +int udpv6_init_sock(struct sock *sk) +{ + skb_queue_head_init(&udp_sk(sk)->reader_queue); + sk->sk_destruct = udpv6_destruct_sock; + return 0; +} + static u32 udp6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, @@ -1665,7 +1678,7 @@ struct proto udpv6_prot = { .connect = ip6_datagram_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, - .init = udp_init_sock, + .init = udpv6_init_sock, .destroy = udpv6_destroy_sock, .setsockopt = udpv6_setsockopt, .getsockopt = udpv6_getsockopt, --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -12,6 +12,7 @@ int __udp6_lib_rcv(struct sk_buff *, str int __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, u8, u8, int, __be32, struct udp_table *);
+int udpv6_init_sock(struct sock *sk); int udp_v6_get_port(struct sock *sk, unsigned short snum); void udp_v6_rehash(struct sock *sk);
--- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -12,6 +12,13 @@ #include <linux/proc_fs.h> #include "udp_impl.h"
+static int udplitev6_sk_init(struct sock *sk) +{ + udpv6_init_sock(sk); + udp_sk(sk)->pcflag = UDPLITE_BIT; + return 0; +} + static int udplitev6_rcv(struct sk_buff *skb) { return __udp6_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE); @@ -38,7 +45,7 @@ struct proto udplitev6_prot = { .connect = ip6_datagram_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, - .init = udplite_sk_init, + .init = udplitev6_sk_init, .destroy = udpv6_destroy_sock, .setsockopt = udpv6_setsockopt, .getsockopt = udpv6_getsockopt,