From: Quanye Yang 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 --- 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 e1f08f71cdb1..e37a8642a4b0 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -969,7 +969,7 @@ 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 @@ -2028,7 +2028,7 @@ 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); @@ -2429,10 +2429,9 @@ 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; @@ -4655,10 +4654,9 @@ 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 af81ad5e699d..ec9668fe8d5b 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1541,7 +1541,7 @@ 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); } } @@ -1889,7 +1889,7 @@ 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); -- 2.55.0