From 5b2c5540b8110eea0d67a78fb0ddb9654c58daeb Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 4 Jan 2022 12:59:18 -0800 Subject: bpf, sockmap: Fix return codes from tcp_bpf_recvmsg_parser() Applications can be confused slightly because we do not always return the same error code as expected, e.g. what the TCP stack normally returns. For example on a sock err sk->sk_err instead of returning the sock_error we return EAGAIN. This usually means the application will 'try again' instead of aborting immediately. Another example, when a shutdown event is received we should immediately abort instead of waiting for data when the user provides a timeout. These tend to not be fatal, applications usually recover, but introduces bogus errors to the user or introduces unexpected latency. Before 'c5d2177a72a16' we fell back to the TCP stack when no data was available so we managed to catch many of the cases here, although with the extra latency cost of calling tcp_msg_wait_data() first. To fix lets duplicate the error handling in TCP stack into tcp_bpf so that we get the same error codes. These were found in our CI tests that run applications against sockmap and do longer lived testing, at least compared to test_sockmap that does short-lived ping/pong tests, and in some of our test clusters we deploy. Its non-trivial to do these in a shorter form CI tests that would be appropriate for BPF selftests, but we are looking into it so we can ensure this keeps working going forward. As a preview one idea is to pull in the packetdrill testing which catches some of this. Fixes: c5d2177a72a16 ("bpf, sockmap: Fix race in ingress receive verdict with redirect to self") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20220104205918.286416-1-john.fastabend@gmail.com --- net/ipv4/tcp_bpf.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index f70aa0932bd6..9b9b02052fd3 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -196,12 +196,39 @@ msg_bytes_ready: long timeo; int data; + if (sock_flag(sk, SOCK_DONE)) + goto out; + + if (sk->sk_err) { + copied = sock_error(sk); + goto out; + } + + if (sk->sk_shutdown & RCV_SHUTDOWN) + goto out; + + if (sk->sk_state == TCP_CLOSE) { + copied = -ENOTCONN; + goto out; + } + timeo = sock_rcvtimeo(sk, nonblock); + if (!timeo) { + copied = -EAGAIN; + goto out; + } + + if (signal_pending(current)) { + copied = sock_intr_errno(timeo); + goto out; + } + data = tcp_msg_wait_data(sk, psock, timeo); if (data && !sk_psock_queue_empty(psock)) goto msg_bytes_ready; copied = -EAGAIN; } +out: release_sock(sk); sk_psock_put(sk, psock); return copied; -- cgit v1.2.3-73-gaa49b From 91a760b26926265a60c77ddf016529bcf3e17a04 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Thu, 6 Jan 2022 21:20:20 +0800 Subject: 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 Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220106132022.3470772-2-imagedong@tencent.com --- 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(+) (limited to 'net/ipv4') diff --git a/include/net/sock.h b/include/net/sock.h index 7b4b4237e6e0..ff9b508d9c5f 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1209,6 +1209,7 @@ 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); #ifdef CONFIG_BPF_SYSCALL int (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock, diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f53184767ee7..9c465bac1eb0 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -531,6 +531,8 @@ 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 e540b0dcf085..0e56df3a45e2 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -994,6 +994,7 @@ 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 ac10e4cdd8d0..9861786b8336 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3076,6 +3076,7 @@ struct proto tcp_prot = { .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, + .put_port = inet_put_port, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = tcp_bpf_update_proto, #endif diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 7b18a6f42f18..c2a4411d2b04 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2927,6 +2927,7 @@ struct proto udp_prot = { .unhash = udp_lib_unhash, .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, + .put_port = udp_lib_unhash, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = udp_bpf_update_proto, #endif diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index d1636425654e..8fe7900f1949 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -413,6 +413,8 @@ 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 6ac88fe24a8e..9256f6ba87ef 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -177,6 +177,7 @@ 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 1ac243d18c2b..075ee8a2df3b 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2181,6 +2181,7 @@ struct proto tcpv6_prot = { .hash = inet6_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, + .put_port = inet_put_port, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = tcp_bpf_update_proto, #endif diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1accc06abc54..90718a924ca8 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1732,6 +1732,7 @@ struct proto udpv6_prot = { .unhash = udp_lib_unhash, .rehash = udp_v6_rehash, .get_port = udp_v6_get_port, + .put_port = udp_lib_unhash, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = udp_bpf_update_proto, #endif -- cgit v1.2.3-73-gaa49b