1 files changed, 72 insertions, 34 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c151c4dd4ae6..61243531a7f4 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -178,6 +178,19 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
 		if (unlikely(len > icsk->icsk_ack.rcv_mss +
 				   MAX_TCP_OPTION_SPACE))
 			tcp_gro_dev_warn(sk, skb, len);
+		/* If the skb has a len of exactly 1*MSS and has the PSH bit
+		 * set then it is likely the end of an application write. So
+		 * more data may not be arriving soon, and yet the data sender
+		 * may be waiting for an ACK if cwnd-bound or using TX zero
+		 * copy. So we set ICSK_ACK_PUSHED here so that
+		 * tcp_cleanup_rbuf() will send an ACK immediately if the app
+		 * reads all of the data and is not ping-pong. If len > MSS
+		 * then this logic does not matter (and does not hurt) because
+		 * tcp_cleanup_rbuf() will always ACK immediately if the app
+		 * reads data and there is more than an MSS of unACKed data.
+		 */
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_PSH)
+			icsk->icsk_ack.pending |= ICSK_ACK_PUSHED;
 	} else {
 		/* Otherwise, we make more careful check taking into account,
 		 * that SACKs block is variable.
@@ -222,7 +235,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks)
 		icsk->icsk_ack.quick = quickacks;
 }
 
-void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
+static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -230,7 +243,6 @@ void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
 	inet_csk_exit_pingpong_mode(sk);
 	icsk->icsk_ack.ato = TCP_ATO_MIN;
 }
-EXPORT_SYMBOL(tcp_enter_quickack_mode);
 
 /* Send ACKs quickly, if "quick" count is not exhausted
  * and the session is not interactive.
@@ -439,7 +451,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
  */
 void tcp_init_buffer_space(struct sock *sk)
 {
-	int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win;
+	int tcp_app_win = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_app_win);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int maxwin;
 
@@ -2030,7 +2042,7 @@ void tcp_enter_loss(struct sock *sk)
 	 * loss recovery is underway except recurring timeout(s) on
 	 * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
 	 */
-	tp->frto = net->ipv4.sysctl_tcp_frto &&
+	tp->frto = READ_ONCE(net->ipv4.sysctl_tcp_frto) &&
 		   (new_recovery || icsk->icsk_retransmits) &&
 		   !inet_csk(sk)->icsk_mtup.probe_size;
 }
@@ -2045,15 +2057,17 @@ void tcp_enter_loss(struct sock *sk)
  * restore sanity to the SACK scoreboard. If the apparent reneging
  * persists until this RTO then we'll clear the SACK scoreboard.
  */
-static bool tcp_check_sack_reneging(struct sock *sk, int flag)
+static bool tcp_check_sack_reneging(struct sock *sk, int *ack_flag)
 {
-	if (flag & FLAG_SACK_RENEGING) {
+	if (*ack_flag & FLAG_SACK_RENEGING &&
+	    *ack_flag & FLAG_SND_UNA_ADVANCED) {
 		struct tcp_sock *tp = tcp_sk(sk);
 		unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4),
 					  msecs_to_jiffies(10));
 
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
 					  delay, TCP_RTO_MAX);
+		*ack_flag &= ~FLAG_SET_XMIT_TIMER;
 		return true;
 	}
 	return false;
@@ -2384,6 +2398,21 @@ static inline bool tcp_may_undo(const struct tcp_sock *tp)
 	return tp->undo_marker && (!tp->undo_retrans || tcp_packet_delayed(tp));
 }
 
+static bool tcp_is_non_sack_preventing_reopen(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
+		/* Hold old state until something *above* high_seq
+		 * is ACKed. For Reno it is MUST to prevent false
+		 * fast retransmits (RFC2582). SACK TCP is safe. */
+		if (!tcp_any_retrans_done(sk))
+			tp->retrans_stamp = 0;
+		return true;
+	}
+	return false;
+}
+
 /* People celebrate: "We love our President!" */
 static bool tcp_try_undo_recovery(struct sock *sk)
 {
@@ -2406,14 +2435,8 @@ static bool tcp_try_undo_recovery(struct sock *sk)
 	} else if (tp->rack.reo_wnd_persist) {
 		tp->rack.reo_wnd_persist--;
 	}
-	if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
-		/* Hold old state until something *above* high_seq
-		 * is ACKed. For Reno it is MUST to prevent false
-		 * fast retransmits (RFC2582). SACK TCP is safe. */
-		if (!tcp_any_retrans_done(sk))
-			tp->retrans_stamp = 0;
+	if (tcp_is_non_sack_preventing_reopen(sk))
 		return true;
-	}
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
 	return false;
@@ -2449,6 +2472,8 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
 			NET_INC_STATS(sock_net(sk),
 					LINUX_MIB_TCPSPURIOUSRTOS);
 		inet_csk(sk)->icsk_retransmits = 0;
+		if (tcp_is_non_sack_preventing_reopen(sk))
+			return true;
 		if (frto_undo || tcp_is_sack(tp)) {
 			tcp_set_ca_state(sk, TCP_CA_Open);
 			tp->is_sack_reneg = 0;
@@ -2816,7 +2841,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 		tp->prior_ssthresh = 0;
 
 	/* B. In all the states check for reneging SACKs. */
-	if (tcp_check_sack_reneging(sk, flag))
+	if (tcp_check_sack_reneging(sk, ack_flag))
 		return;
 
 	/* C. Check consistency of the current state. */
@@ -2914,7 +2939,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 
 static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us, const int flag)
 {
-	u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ;
+	u32 wlen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen) * HZ;
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	if ((flag & FLAG_ACK_MAYBE_DELAYED) && rtt_us > tcp_min_rtt(tp)) {
@@ -3433,16 +3458,23 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32
 static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
 				   u32 *last_oow_ack_time)
 {
-	if (*last_oow_ack_time) {
-		s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time);
+	/* Paired with the WRITE_ONCE() in this function. */
+	u32 val = READ_ONCE(*last_oow_ack_time);
+
+	if (val) {
+		s32 elapsed = (s32)(tcp_jiffies32 - val);
 
-		if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) {
+		if (0 <= elapsed &&
+		    elapsed < READ_ONCE(net->ipv4.sysctl_tcp_invalid_ratelimit)) {
 			NET_INC_STATS(net, mib_idx);
 			return true;	/* rate-limited: don't send yet! */
 		}
 	}
 
-	*last_oow_ack_time = tcp_jiffies32;
+	/* Paired with the prior READ_ONCE() and with itself,
+	 * as we might be lockless.
+	 */
+	WRITE_ONCE(*last_oow_ack_time, tcp_jiffies32);
 
 	return false;	/* not rate-limited: go ahead, send dupack now! */
 }
@@ -3483,11 +3515,11 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 
 	/* Then check host-wide RFC 5961 rate limit. */
 	now = jiffies / HZ;
-	if (now != challenge_timestamp) {
-		u32 ack_limit = net->ipv4.sysctl_tcp_challenge_ack_limit;
+	if (now != READ_ONCE(challenge_timestamp)) {
+		u32 ack_limit = READ_ONCE(net->ipv4.sysctl_tcp_challenge_ack_limit);
 		u32 half = (ack_limit + 1) >> 1;
 
-		challenge_timestamp = now;
+		WRITE_ONCE(challenge_timestamp, now);
 		WRITE_ONCE(challenge_count, half + prandom_u32_max(ack_limit));
 	}
 	count = READ_ONCE(challenge_count);
@@ -3625,8 +3657,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	 * then we can probably ignore it.
 	 */
 	if (before(ack, prior_snd_una)) {
+		u32 max_window;
+
+		/* do not accept ACK for bytes we never sent. */
+		max_window = min_t(u64, tp->max_window, tp->bytes_acked);
 		/* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */
-		if (before(ack, prior_snd_una - tp->max_window)) {
+		if (before(ack, prior_snd_una - max_window)) {
 			if (!(flag & FLAG_NO_CHALLENGE_ACK))
 				tcp_send_challenge_ack(sk, skb);
 			return -1;
@@ -4180,7 +4216,7 @@ void tcp_fin(struct sock *sk)
 
 	inet_csk_schedule_ack(sk);
 
-	sk->sk_shutdown |= RCV_SHUTDOWN;
+	WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN);
 	sock_set_flag(sk, SOCK_DONE);
 
 	switch (sk->sk_state) {
@@ -4260,7 +4296,7 @@ static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
+	if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) {
 		int mib_idx;
 
 		if (before(seq, tp->rcv_nxt))
@@ -4306,7 +4342,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
 		tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
 
-		if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
+		if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) {
 			u32 end_seq = TCP_SKB_CB(skb)->end_seq;
 
 			tcp_rcv_spurious_retrans(sk, skb);
@@ -5302,7 +5338,7 @@ send_now:
 	}
 
 	if (!tcp_is_sack(tp) ||
-	    tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)
+	    tp->compressed_ack >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr))
 		goto send_now;
 
 	if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) {
@@ -5325,7 +5361,8 @@ send_now:
 	if (tp->srtt_us && tp->srtt_us < rtt)
 		rtt = tp->srtt_us;
 
-	delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns,
+	delay = min_t(unsigned long,
+		      READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns),
 		      rtt * (NSEC_PER_USEC >> 3)/20);
 	sock_hold(sk);
 	hrtimer_start(&tp->compressed_ack_timer, ns_to_ktime(delay),
@@ -5603,7 +5640,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 	trace_tcp_probe(sk, skb);
 
 	tcp_mstamp_refresh(tp);
-	if (unlikely(!sk->sk_rx_dst))
+	if (unlikely(!rcu_access_pointer(sk->sk_rx_dst)))
 		inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb);
 	/*
 	 *	Header prediction.
@@ -6143,22 +6180,23 @@ reset_and_undo:
 
 static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
 	struct request_sock *req;
 
 	/* If we are still handling the SYNACK RTO, see if timestamp ECR allows
 	 * undo. If peer SACKs triggered fast recovery, we can't undo here.
 	 */
-	if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
-		tcp_try_undo_loss(sk, false);
+	if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss && !tp->packets_out)
+		tcp_try_undo_recovery(sk);
 
 	/* Reset rtx states to prevent spurious retransmits_timed_out() */
-	tcp_sk(sk)->retrans_stamp = 0;
+	tp->retrans_stamp = 0;
 	inet_csk(sk)->icsk_retransmits = 0;
 
 	/* Once we leave TCP_SYN_RECV or TCP_FIN_WAIT_1,
 	 * we no longer need req so release it.
 	 */
-	req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk,
+	req = rcu_dereference_protected(tp->fastopen_rsk,
 					lockdep_sock_is_held(sk));
 	reqsk_fastopen_remove(sk, req, false);
 
@@ -6316,7 +6354,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			break;
 
 		tcp_set_state(sk, TCP_FIN_WAIT2);
-		sk->sk_shutdown |= SEND_SHUTDOWN;
+		WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | SEND_SHUTDOWN);
 
 		sk_dst_confirm(sk);