Merge branch 'tcp-fix-tcp_poll-races'

Eric Dumazet says:

====================
tcp: fix tcp_poll() races

Flakes in packetdrill tests stressing epoll_wait()
were root caused to bad ordering in tcp_write_err()

Precisely, we have to call sk_error_report() after
tcp_done().

When fixing this issue, we discovered tcp_abort(),
tcp_v4_err() and tcp_v6_err() had similar issues.

Since tcp_reset() has the correct ordering,
first patch takes part of it and creates
tcp_done_with_error() helper.
====================

Link: https://lore.kernel.org/r/20240528125253.1966136-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 31 insertions, 37 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 060e95b331a2..32815a40dea1 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -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);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 681b54e1f3a6..5fa68e7f6ddb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -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))
@@ -4576,14 +4576,10 @@ int tcp_abort(struct sock *sk, int err)
 	bh_lock_sock(sk);
 
 	if (!sock_flag(sk, SOCK_DEAD)) {
-		WRITE_ONCE(sk->sk_err, err);
-		/* This barrier is coupled with smp_rmb() in tcp_poll() */
-		smp_wmb();
-		sk_error_report(sk);
 		if (tcp_need_reset(sk->sk_state))
 			tcp_send_active_reset(sk, GFP_ATOMIC,
 					      SK_RST_REASON_NOT_SPECIFIED);
-		tcp_done(sk);
+		tcp_done_with_error(sk, err);
 	}
 
 	bh_unlock_sock(sk);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9c04a9c8be9d..5aadf64e554d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -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);
 }
 
 /*
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8f70b8d1d1e5..041c7eda9abe 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -611,15 +611,10 @@ int tcp_v4_err(struct sk_buff *skb, u32 info)
 
 		ip_icmp_error(sk, skb, err, th->dest, info, (u8 *)th);
 
-		if (!sock_owned_by_user(sk)) {
-			WRITE_ONCE(sk->sk_err, err);
-
-			sk_error_report(sk);
-
-			tcp_done(sk);
-		} else {
+		if (!sock_owned_by_user(sk))
+			tcp_done_with_error(sk, err);
+		else
 			WRITE_ONCE(sk->sk_err_soft, err);
-		}
 		goto out;
 	}
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 83fe7f62f7f1..3e8604ae7d06 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -74,11 +74,7 @@ u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when)
 
 static void tcp_write_err(struct sock *sk)
 {
-	WRITE_ONCE(sk->sk_err, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT);
-	sk_error_report(sk);
-
-	tcp_write_queue_purge(sk);
-	tcp_done(sk);
+	tcp_done_with_error(sk, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT);
 	__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT);
 }
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 750aa681779c..1ac7502e1bf5 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -490,14 +490,10 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 		ipv6_icmp_error(sk, skb, err, th->dest, ntohl(info), (u8 *)th);
 
-		if (!sock_owned_by_user(sk)) {
-			WRITE_ONCE(sk->sk_err, err);
-			sk_error_report(sk);		/* Wake people up to see the error (see connect in sock.c) */
-
-			tcp_done(sk);
-		} else {
+		if (!sock_owned_by_user(sk))
+			tcp_done_with_error(sk, err);
+		else
 			WRITE_ONCE(sk->sk_err_soft, err);
-		}
 		goto out;
 	case TCP_LISTEN:
 		break;