From 4ab848ee2ee32f902ccda3482fc7dce59a9caf09 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Tue, 11 Jan 2022 16:58:43 +0800 Subject: [PATCH] net: bpf: handle return value of BPF_CGROUP_RUN_PROG_INET{4,6}_POST_BIND() The return value of BPF_CGROUP_RUN_PROG_INET{4,6}_POST_BIND() in __inet_bind() is not handled properly. While the return value is non-zero, it will set inet_saddr and inet_rcv_saddr to 0 and exit: err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk); if (err) { inet->inet_saddr = inet->inet_rcv_saddr = 0; goto out_release_sock; } Let's take UDP for example and see what will happen. For UDP socket, it will be added to 'udp_prot.h.udp_table->hash' and 'udp_prot.h.udp_table->hash2' after the sk->sk_prot->get_port() called success. If 'inet->inet_rcv_saddr' is specified here, then 'sk' will be in the 'hslot2' of 'hash2' that it don't belong to (because inet_saddr is changed to 0), and UDP packet received will not be passed to this sock. If 'inet->inet_rcv_saddr' is not specified here, the sock will work fine, as it can receive packet properly, which is wired, as the 'bind()' is already failed. To undo the get_port() operation, introduce the 'put_port' field for 'struct proto'. For TCP proto, it is inet_put_port(); For UDP proto, it is udp_lib_unhash(); For icmp proto, it is ping_unhash(). Therefore, after sys_bind() fail caused by BPF_CGROUP_RUN_PROG_INET4_POST_BIND(), it will be unbinded, which means that it can try to be binded to another port. Signed-off-by: Menglong Dong --- include/net/sock.h | 1 + net/ipv4/af_inet.c | 2 ++ net/ipv4/ping.c | 1 + net/ipv4/tcp_ipv4.c | 1 + net/ipv4/udp.c | 1 + net/ipv6/af_inet6.c | 2 ++ net/ipv6/ping.c | 1 + net/ipv6/tcp_ipv6.c | 1 + net/ipv6/udp.c | 1 + 9 files changed, 11 insertions(+) diff --git a/include/net/sock.h b/include/net/sock.h index df1db867b..a778a8a14 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1138,6 +1138,7 @@ struct proto { void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); + void (*put_port)(struct sock *sk); /* Keeping track of sockets in use */ #ifdef CONFIG_PROC_FS diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 0a25205ee..ea0dd193d 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -530,6 +530,8 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk); if (err) { inet->inet_saddr = inet->inet_rcv_saddr = 0; + if (sk->sk_prot->put_port) + sk->sk_prot->put_port(sk); goto out_release_sock; } } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index df6fbefe4..d9493987b 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -1005,6 +1005,7 @@ struct proto ping_prot = { .hash = ping_hash, .unhash = ping_unhash, .get_port = ping_get_port, + .put_port = ping_unhash, .obj_size = sizeof(struct inet_sock), }; EXPORT_SYMBOL(ping_prot); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1171b0ed1..fc99a82fa 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2626,6 +2626,7 @@ struct proto tcp_prot = { .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, + .put_port = inet_put_port, .enter_memory_pressure = tcp_enter_memory_pressure, .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 5e72ae2ab..55ed53bb4 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2802,6 +2802,7 @@ struct proto udp_prot = { .unhash = udp_lib_unhash, .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, + .put_port = udp_lib_unhash, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 7a976aad3..ce876b848 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -411,6 +411,8 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, if (err) { sk->sk_ipv6only = saved_ipv6only; inet_reset_saddr(sk); + if (sk->sk_prot->put_port) + sk->sk_prot->put_port(sk); goto out; } } diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 98ac32b49..7853791a3 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -176,6 +176,7 @@ struct proto pingv6_prot = { .hash = ping_hash, .unhash = ping_unhash, .get_port = ping_get_port, + .put_port = ping_unhash, .obj_size = sizeof(struct raw6_sock), }; EXPORT_SYMBOL_GPL(pingv6_prot); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b7ea65255..58b376541 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2033,6 +2033,7 @@ struct proto tcpv6_prot = { .hash = inet6_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, + .put_port = inet_put_port, .enter_memory_pressure = tcp_enter_memory_pressure, .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 676243028..95bc7d894 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1673,6 +1673,7 @@ struct proto udpv6_prot = { .unhash = udp_lib_unhash, .rehash = udp_v6_rehash, .get_port = udp_v6_get_port, + .put_port = udp_lib_unhash, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min),