Commit 5e514f1c authored by Eric Dumazet's avatar Eric Dumazet Committed by Jakub Kicinski
Browse files

tcp: add tcp_done_with_error() helper 



tcp_reset() ends with a sequence that is carefuly ordered.

We need to fix [e]poll bugs in the following patches,
it makes sense to use a common helper.

Suggested-by: default avatarNeal Cardwell <ncardwell@google.com>
Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Acked-by: default avatarNeal Cardwell <ncardwell@google.com>
Link: https://lore.kernel.org/r/20240528125253.1966136-2-edumazet@google.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent c3390677

include/net/tcp.h

+1 −0
Original line number Diff line number Diff line
@@ -677,6 +677,7 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb, 
/* tcp_input.c */

void tcp_rearm_rto(struct sock *sk);

void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req);

void tcp_done_with_error(struct sock *sk, int err);

void tcp_reset(struct sock *sk, struct sk_buff *skb);

void tcp_fin(struct sock *sk);

void tcp_check_space(struct sock *sk);

net/ipv4/tcp.c

+1 −1
Original line number Diff line number Diff line
@@ -598,7 +598,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) 
		 */

		mask |= EPOLLOUT | EPOLLWRNORM;

	}

	/* This barrier is coupled with smp_wmb() in tcp_reset() */

	/* This barrier is coupled with smp_wmb() in tcp_done_with_error() */

	smp_rmb();

	if (READ_ONCE(sk->sk_err) ||

	    !skb_queue_empty_lockless(&sk->sk_error_queue))

net/ipv4/tcp_input.c

+21 −11
Original line number Diff line number Diff line
@@ -4436,9 +4436,26 @@ static enum skb_drop_reason tcp_sequence(const struct tcp_sock *tp, 
	return SKB_NOT_DROPPED_YET;

}





void tcp_done_with_error(struct sock *sk, int err)

{

	/* This barrier is coupled with smp_rmb() in tcp_poll() */

	WRITE_ONCE(sk->sk_err, err);

	smp_wmb();



	tcp_write_queue_purge(sk);

	tcp_done(sk);



	if (!sock_flag(sk, SOCK_DEAD))

		sk_error_report(sk);

}

EXPORT_SYMBOL(tcp_done_with_error);



/* When we get a reset we do this. */

void tcp_reset(struct sock *sk, struct sk_buff *skb)

{

	int err;



	trace_tcp_receive_reset(sk);



	/* mptcp can't tell us to ignore reset pkts,
@@ -4450,24 +4467,17 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb) 
	/* We want the right error as BSD sees it (and indeed as we do). */

	switch (sk->sk_state) {

	case TCP_SYN_SENT:

		WRITE_ONCE(sk->sk_err, ECONNREFUSED);

		err = ECONNREFUSED;

		break;

	case TCP_CLOSE_WAIT:

		WRITE_ONCE(sk->sk_err, EPIPE);

		err = EPIPE;

		break;

	case TCP_CLOSE:

		return;

	default:

		WRITE_ONCE(sk->sk_err, ECONNRESET);

		err = ECONNRESET;

	}

	/* This barrier is coupled with smp_rmb() in tcp_poll() */

	smp_wmb();



	tcp_write_queue_purge(sk);

	tcp_done(sk);



	if (!sock_flag(sk, SOCK_DEAD))

		sk_error_report(sk);

	tcp_done_with_error(sk, err);

}



/*