From 3b49f11cc92dc10a3587c9c982cbab6fa8ba91c9 Mon Sep 17 00:00:00 2001 From: Quanye Yang Date: Fri, 25 Sep 2026 05:47:56 -0700 Subject: [PATCH 1/2] tcp: annotate lockless access to sk->sk_err BUG: KCSAN: data-race in do_recvmmsg / mptcp_recvmsg read-write (marked) to 0xffff8880134d391c of 4 bytes by task 2619 on cpu 1: instrument_atomic_read_write include/linux/instrumented.h:113 [inline] sock_error include/net/sock.h:2565 [inline] do_recvmmsg+0x50c/0x580 net/socket.c:3049 __sys_recvmmsg net/socket.c:3144 [inline] __do_sys_recvmmsg net/socket.c:3167 [inline] __se_sys_recvmmsg net/socket.c:3160 [inline] __x64_sys_recvmmsg+0x161/0x180 net/socket.c:3160 x64_sys_call+0x19c7/0x1ca0 arch/x86/include/generated/asm/syscalls_64.h:300 do_syscall_x64 arch/x86/entry/syscall_64.c:61 [inline] do_syscall_64+0xde/0x3d0 arch/x86/entry/syscall_64.c:84 entry_SYSCALL_64_after_hwframe+0x77/0x7f read to 0xffff8880134d391c of 4 bytes by task 2620 on cpu 0: tcp_recv_should_stop include/net/tcp.h:3086 [inline] mptcp_recvmsg+0x54d/0xd50 net/mptcp/protocol.c:2466 inet_recvmsg+0x204/0x210 net/ipv4/af_inet.c:894 sock_recvmsg_nosec net/socket.c:1151 [inline] sock_recvmsg+0x11a/0x140 net/socket.c:1173 ____sys_recvmsg+0x14b/0x3c0 net/socket.c:2933 ___sys_recvmsg+0x116/0x160 net/socket.c:2975 __sys_recvmsg net/socket.c:3008 [inline] __do_sys_recvmsg net/socket.c:3014 [inline] __se_sys_recvmsg net/socket.c:3011 [inline] __x64_sys_recvmsg+0xeb/0x160 net/socket.c:3011 x64_sys_call+0x1319/0x1ca0 arch/x86/include/generated/asm/syscalls_64.h:48 do_syscall_x64 arch/x86/entry/syscall_64.c:61 [inline] do_syscall_64+0xde/0x3d0 arch/x86/entry/syscall_64.c:84 entry_SYSCALL_64_after_hwframe+0x77/0x7f value changed: 0x0000006b -> 0x00000000 Reported by Kernel Concurrency Sanitizer on: CPU: 0 UID: 0 PID: 2620 Comm: syz.2.33 Not tainted 7.2.0-g39d4f32c5d53 #76 PREEMPT(full) Hardware name: QEMU Ubuntu 26.04 PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1ubuntu1 04/01/2014 do_recvmmsg() and getsockopt(SO_ERROR) call sock_error() without the socket lock. sock_error() clears sk_err with xchg(), which races with unmarked loads of the same field. KCSAN reported the unmarked peek in tcp_recv_should_stop(). Annotate that helper and the other send-side peeks with READ_ONCE(). On the no-data recv and splice paths, if (sk_err) followed by sock_error() and an unconditional break can return 0 after another thread consumes the error. Call sock_error() once and only stop when it returns a non-zero error. tcp_bpf_sendmsg() read sk_err twice; fold those unmarked loads into one READ_ONCE() and use that value as the returned errno. The field is still not consumed. MPTCP is handled in the next patch. Suggested-by: Jiayuan Chen Link: https://lore.kernel.org/netdev/8bbee583-6f21-4817-bfeb-2d60057380a3@linux.dev/ Reported-by: Matthieu Baerts (NGI0) Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/632 Signed-off-by: Quanye Yang Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260925-mptcp-sk-err-net-v5-1-0cac04d6ea48@proton.me Signed-off-by: Paolo Abeni --- include/net/tcp.h | 2 +- net/core/stream.c | 2 +- net/ipv4/tcp.c | 12 +++++------- net/ipv4/tcp_bpf.c | 10 ++++------ 4 files changed, 11 insertions(+), 15 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 96a1a23e47fa..74f54bfa51f1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -3093,7 +3093,7 @@ enum skb_drop_reason tcp_inbound_hash(struct sock *sk, static inline int tcp_recv_should_stop(struct sock *sk) { - return sk->sk_err || + return READ_ONCE(sk->sk_err) || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || signal_pending(current); diff --git a/net/core/stream.c b/net/core/stream.c index 2d748581862d..5c0adc3077f0 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -133,7 +133,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) while (1) { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); - if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) + if (READ_ONCE(sk->sk_err) || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; if (!*timeo_p) goto do_eagain; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3ac485685279..7c9d8305094c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -846,10 +846,9 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, break; if (sock_flag(sk, SOCK_DONE)) break; - if (sk->sk_err) { - ret = sock_error(sk); + ret = sock_error(sk); + if (ret) break; - } if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_state == TCP_CLOSE) { @@ -1230,7 +1229,7 @@ restart: mss_now = tcp_send_mss(sk, &size_goal, flags); err = -EPIPE; - if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) + if (READ_ONCE(sk->sk_err) || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; while (msg_data_left(msg)) { @@ -2762,10 +2761,9 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, if (sock_flag(sk, SOCK_DONE)) break; - if (sk->sk_err) { - copied = sock_error(sk); + copied = sock_error(sk); + if (copied) break; - } if (sk->sk_shutdown & RCV_SHUTDOWN) break; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 2e234d155b5e..338c5d90e550 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -286,10 +286,9 @@ msg_bytes_ready: if (sock_flag(sk, SOCK_DONE)) goto out; - if (sk->sk_err) { - copied = sock_error(sk); + copied = sock_error(sk); + if (copied) goto out; - } if (sk->sk_shutdown & RCV_SHUTDOWN) goto out; @@ -553,10 +552,9 @@ static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) bool enospc = false; u32 copy, osize; - if (sk->sk_err) { - err = -sk->sk_err; + err = -READ_ONCE(sk->sk_err); + if (err) goto out_err; - } copy = msg_data_left(msg); if (!sk_stream_memory_free(sk)) From 97870870b7dd7970d4e6090b63627abf2ee3e6a5 Mon Sep 17 00:00:00 2001 From: Quanye Yang Date: Fri, 25 Sep 2026 05:47:57 -0700 Subject: [PATCH 2/2] mptcp: annotate lockless access to sk->sk_err sock_error() can clear sk_err with xchg() without the socket lock. On the no-data msk recv and splice paths, call sock_error() once and only stop when it returns a non-zero error. Annotate the remaining msk send and subflow error-report peeks with READ_ONCE(). Signed-off-by: Quanye Yang Reviewed-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260925-mptcp-sk-err-net-v5-2-0cac04d6ea48@proton.me Signed-off-by: Paolo Abeni --- net/mptcp/protocol.c | 14 ++++++-------- net/mptcp/subflow.c | 4 ++-- 2 files changed, 8 insertions(+), 10 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e89a69ab927c..b543eb245136 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -970,7 +970,7 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) moved = __mptcp_move_skbs_from_subflow(msk, ssk, true); __mptcp_ofo_queue(msk); - if (unlikely(ssk->sk_err)) + if (unlikely(READ_ONCE(ssk->sk_err))) __mptcp_subflow_error_report(sk, ssk); /* If the moves have caught up with the DATA_FIN sequence number @@ -2033,7 +2033,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } ret = -EPIPE; - if (unlikely(sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))) + if (unlikely(READ_ONCE(sk->sk_err) || (sk->sk_shutdown & SEND_SHUTDOWN))) goto do_error; pfrag = sk_page_frag(sk); @@ -2434,10 +2434,9 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, !timeo) break; } else { - if (sk->sk_err) { - copied = sock_error(sk); + copied = sock_error(sk); + if (copied) break; - } if (sk->sk_shutdown & RCV_SHUTDOWN) break; @@ -4671,10 +4670,9 @@ static ssize_t mptcp_splice_read(struct socket *sock, loff_t *ppos, break; if (sock_flag(sk, SOCK_DONE)) break; - if (sk->sk_err) { - ret = sock_error(sk); + ret = sock_error(sk); + if (ret) break; - } if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_state == TCP_CLOSE) { diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 14aa82647c3d..e9cb19188069 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1545,7 +1545,7 @@ static void subflow_data_ready(struct sock *sk) if (mptcp_data_avail(msk) < parent->sk_rcvlowat && (tcp_sk(sk)->rcv_nxt - tcp_sk(sk)->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss) inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; - } else if (unlikely(sk->sk_err)) { + } else if (unlikely(READ_ONCE(sk->sk_err))) { subflow_error_report(sk); } } @@ -1900,7 +1900,7 @@ static void subflow_state_change(struct sock *sk) */ if (mptcp_subflow_data_available(sk)) mptcp_data_ready(parent, sk); - else if (unlikely(sk->sk_err)) + else if (unlikely(READ_ONCE(sk->sk_err))) subflow_error_report(sk); subflow_sched_work_if_closed(mptcp_sk(parent), sk);