[PATCH net-next v4 1/2] tcp: annotate lockless access to sk->sk_err
From: Quanye Yang via B4 Relay
Date: Thu Sep 17 2026 - 10:34:31 EST
From: Quanye Yang <quanyeyang@xxxxxxxxx>
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(). The same
lockless writer races with the other plain sk_err reads on the TCP
send, recv and splice paths.
Annotate those peeks with READ_ONCE(). No extra ordering is needed:
the value is only used to decide whether I/O should stop. This does
not consume sk_err; the check-then-sock_error() TOCTOU on the no-data
paths is a separate issue. MPTCP peeks are handled in the next patch.
Suggested-by: Jiayuan Chen <jiayuan.chen@xxxxxxxxx>
Link: https://lore.kernel.org/netdev/8bbee583-6f21-4817-bfeb-2d60057380a3@xxxxxxxxx/
Reported-by: Matthieu Baerts (NGI0) <matttbe@xxxxxxxxxx>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/632
Signed-off-by: Quanye Yang <quanyeyang@xxxxxxxxx>
---
include/net/tcp.h | 3 ++-
net/core/stream.c | 2 +-
net/ipv4/tcp.c | 6 +++---
net/ipv4/tcp_bpf.c | 7 +++----
4 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5e5f5f9b89a3..6ee513bdb503 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -3093,7 +3093,8 @@ enum skb_drop_reason tcp_inbound_hash(struct sock *sk,
static inline int tcp_recv_should_stop(struct sock *sk)
{
- return sk->sk_err ||
+ /* sk_err can be cleared locklessly by sock_error(). */
+ 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 1c867a302444..9e7fa7e39726 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -843,7 +843,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
break;
if (sock_flag(sk, SOCK_DONE))
break;
- if (sk->sk_err) {
+ if (READ_ONCE(sk->sk_err)) {
ret = sock_error(sk);
break;
}
@@ -1228,7 +1228,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
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)) {
@@ -2760,7 +2760,7 @@ 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) {
+ if (READ_ONCE(sk->sk_err)) {
copied = sock_error(sk);
break;
}
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 2e234d155b5e..a96323e65758 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -286,7 +286,7 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,
if (sock_flag(sk, SOCK_DONE))
goto out;
- if (sk->sk_err) {
+ if (READ_ONCE(sk->sk_err)) {
copied = sock_error(sk);
goto out;
}
@@ -553,10 +553,9 @@ 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))
--
2.55.0