Merge branch 'next' into for-linus

Prepare first round of input updates for 3.20.

1 files changed, 36 insertions, 34 deletions

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index df90cd1ce37f..1829c7fbc77e 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -52,7 +52,7 @@ static void tcp_write_err(struct sock *sk)
  *    limit.
  * 2. If we have strong memory pressure.
  */
-static int tcp_out_of_resources(struct sock *sk, int do_reset)
+static int tcp_out_of_resources(struct sock *sk, bool do_reset)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int shift = 0;
@@ -72,7 +72,7 @@ static int tcp_out_of_resources(struct sock *sk, int do_reset)
 		if ((s32)(tcp_time_stamp - tp->lsndtime) <= TCP_TIMEWAIT_LEN ||
 		    /*  2. Window is closed. */
 		    (!tp->snd_wnd && !tp->packets_out))
-			do_reset = 1;
+			do_reset = true;
 		if (do_reset)
 			tcp_send_active_reset(sk, GFP_ATOMIC);
 		tcp_done(sk);
@@ -135,10 +135,9 @@ static bool retransmits_timed_out(struct sock *sk,
 	if (!inet_csk(sk)->icsk_retransmits)
 		return false;
 
-	if (unlikely(!tcp_sk(sk)->retrans_stamp))
-		start_ts = TCP_SKB_CB(tcp_write_queue_head(sk))->when;
-	else
-		start_ts = tcp_sk(sk)->retrans_stamp;
+	start_ts = tcp_sk(sk)->retrans_stamp;
+	if (unlikely(!start_ts))
+		start_ts = tcp_skb_timestamp(tcp_write_queue_head(sk));
 
 	if (likely(timeout == 0)) {
 		linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base);
@@ -181,7 +180,7 @@ static int tcp_write_timeout(struct sock *sk)
 
 		retry_until = sysctl_tcp_retries2;
 		if (sock_flag(sk, SOCK_DEAD)) {
-			const int alive = (icsk->icsk_rto < TCP_RTO_MAX);
+			const int alive = icsk->icsk_rto < TCP_RTO_MAX;
 
 			retry_until = tcp_orphan_retries(sk, alive);
 			do_reset = alive ||
@@ -271,40 +270,41 @@ static void tcp_probe_timer(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int max_probes;
+	u32 start_ts;
 
 	if (tp->packets_out || !tcp_send_head(sk)) {
 		icsk->icsk_probes_out = 0;
 		return;
 	}
 
-	/* *WARNING* RFC 1122 forbids this
-	 *
-	 * It doesn't AFAIK, because we kill the retransmit timer -AK
-	 *
-	 * FIXME: We ought not to do it, Solaris 2.5 actually has fixing
-	 * this behaviour in Solaris down as a bug fix. [AC]
-	 *
-	 * Let me to explain. icsk_probes_out is zeroed by incoming ACKs
-	 * even if they advertise zero window. Hence, connection is killed only
-	 * if we received no ACKs for normal connection timeout. It is not killed
-	 * only because window stays zero for some time, window may be zero
-	 * until armageddon and even later. We are in full accordance
-	 * with RFCs, only probe timer combines both retransmission timeout
-	 * and probe timeout in one bottle.				--ANK
+	/* RFC 1122 4.2.2.17 requires the sender to stay open indefinitely as
+	 * long as the receiver continues to respond probes. We support this by
+	 * default and reset icsk_probes_out with incoming ACKs. But if the
+	 * socket is orphaned or the user specifies TCP_USER_TIMEOUT, we
+	 * kill the socket when the retry count and the time exceeds the
+	 * corresponding system limit. We also implement similar policy when
+	 * we use RTO to probe window in tcp_retransmit_timer().
 	 */
-	max_probes = sysctl_tcp_retries2;
+	start_ts = tcp_skb_timestamp(tcp_send_head(sk));
+	if (!start_ts)
+		skb_mstamp_get(&tcp_send_head(sk)->skb_mstamp);
+	else if (icsk->icsk_user_timeout &&
+		 (s32)(tcp_time_stamp - start_ts) > icsk->icsk_user_timeout)
+		goto abort;
 
+	max_probes = sysctl_tcp_retries2;
 	if (sock_flag(sk, SOCK_DEAD)) {
-		const int alive = ((icsk->icsk_rto << icsk->icsk_backoff) < TCP_RTO_MAX);
+		const int alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX;
 
 		max_probes = tcp_orphan_retries(sk, alive);
-
-		if (tcp_out_of_resources(sk, alive || icsk->icsk_probes_out <= max_probes))
+		if (!alive && icsk->icsk_backoff >= max_probes)
+			goto abort;
+		if (tcp_out_of_resources(sk, true))
 			return;
 	}
 
 	if (icsk->icsk_probes_out > max_probes) {
-		tcp_write_err(sk);
+abort:		tcp_write_err(sk);
 	} else {
 		/* Only send another probe if we didn't close things up. */
 		tcp_send_probe0(sk);
@@ -374,17 +374,19 @@ void tcp_retransmit_timer(struct sock *sk)
 		 */
 		struct inet_sock *inet = inet_sk(sk);
 		if (sk->sk_family == AF_INET) {
-			LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"),
-				       &inet->inet_daddr,
-				       ntohs(inet->inet_dport), inet->inet_num,
-				       tp->snd_una, tp->snd_nxt);
+			net_dbg_ratelimited("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
+					    &inet->inet_daddr,
+					    ntohs(inet->inet_dport),
+					    inet->inet_num,
+					    tp->snd_una, tp->snd_nxt);
 		}
 #if IS_ENABLED(CONFIG_IPV6)
 		else if (sk->sk_family == AF_INET6) {
-			LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"),
-				       &sk->sk_v6_daddr,
-				       ntohs(inet->inet_dport), inet->inet_num,
-				       tp->snd_una, tp->snd_nxt);
+			net_dbg_ratelimited("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
+					    &sk->sk_v6_daddr,
+					    ntohs(inet->inet_dport),
+					    inet->inet_num,
+					    tp->snd_una, tp->snd_nxt);
 		}
 #endif
 		if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) {