1 files changed, 190 insertions, 45 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 06fe1cf645d5..50aaa1527150 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -253,6 +253,19 @@ 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.
@@ -680,6 +693,23 @@ new_measure:
 	tp->rcv_rtt_est.time = tp->tcp_mstamp;
 }
 
+static s32 tcp_rtt_tsopt_us(const struct tcp_sock *tp)
+{
+	u32 delta, delta_us;
+
+	delta = tcp_time_stamp_ts(tp) - tp->rx_opt.rcv_tsecr;
+	if (tp->tcp_usec_ts)
+		return delta;
+
+	if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
+		if (!delta)
+			delta = 1;
+		delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
+		return delta_us;
+	}
+	return -1;
+}
+
 static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
 					  const struct sk_buff *skb)
 {
@@ -691,15 +721,10 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
 
 	if (TCP_SKB_CB(skb)->end_seq -
 	    TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss) {
-		u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
-		u32 delta_us;
-
-		if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
-			if (!delta)
-				delta = 1;
-			delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
-			tcp_rcv_rtt_update(tp, delta_us, 0);
-		}
+		s32 delta = tcp_rtt_tsopt_us(tp);
+
+		if (delta >= 0)
+			tcp_rcv_rtt_update(tp, delta, 0);
 	}
 }
 
@@ -765,6 +790,16 @@ new_measure:
 	tp->rcvq_space.time = tp->tcp_mstamp;
 }
 
+static void tcp_save_lrcv_flowlabel(struct sock *sk, const struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	if (skb->protocol == htons(ETH_P_IPV6))
+		icsk->icsk_ack.lrcv_flowlabel = ntohl(ip6_flowlabel(ipv6_hdr(skb)));
+#endif
+}
+
 /* There is something which you must keep in mind when you analyze the
  * behavior of the tp->ato delayed ack timeout interval.  When a
  * connection starts up, we want to ack as quickly as possible.  The
@@ -813,6 +848,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
 		}
 	}
 	icsk->icsk_ack.lrcvtime = now;
+	tcp_save_lrcv_flowlabel(sk, skb);
 
 	tcp_ecn_check_ce(sk, skb);
 
@@ -927,8 +963,8 @@ static void tcp_update_pacing_rate(struct sock *sk)
 	 * without any lock. We want to make sure compiler wont store
 	 * intermediate values in this location.
 	 */
-	WRITE_ONCE(sk->sk_pacing_rate, min_t(u64, rate,
-					     sk->sk_max_pacing_rate));
+	WRITE_ONCE(sk->sk_pacing_rate,
+		   min_t(u64, rate, READ_ONCE(sk->sk_max_pacing_rate)));
 }
 
 /* Calculate rto without backoff.  This is the second half of Van Jacobson's
@@ -2088,6 +2124,10 @@ void tcp_clear_retrans(struct tcp_sock *tp)
 	tp->undo_marker = 0;
 	tp->undo_retrans = -1;
 	tp->sacked_out = 0;
+	tp->rto_stamp = 0;
+	tp->total_rto = 0;
+	tp->total_rto_recoveries = 0;
+	tp->total_rto_time = 0;
 }
 
 static inline void tcp_init_undo(struct tcp_sock *tp)
@@ -2194,16 +2234,17 @@ 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 &&
-	    flag & FLAG_SND_UNA_ADVANCED) {
+	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;
@@ -2414,7 +2455,7 @@ static bool tcp_skb_spurious_retrans(const struct tcp_sock *tp,
 				     const struct sk_buff *skb)
 {
 	return (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) &&
-	       tcp_tsopt_ecr_before(tp, tcp_skb_timestamp(skb));
+	       tcp_tsopt_ecr_before(tp, tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb));
 }
 
 /* Nothing was retransmitted or returned timestamp is less
@@ -2825,6 +2866,14 @@ void tcp_enter_recovery(struct sock *sk, bool ece_ack)
 	tcp_set_ca_state(sk, TCP_CA_Recovery);
 }
 
+static void tcp_update_rto_time(struct tcp_sock *tp)
+{
+	if (tp->rto_stamp) {
+		tp->total_rto_time += tcp_time_stamp_ms(tp) - tp->rto_stamp;
+		tp->rto_stamp = 0;
+	}
+}
+
 /* Process an ACK in CA_Loss state. Move to CA_Open if lost data are
  * recovered or spurious. Otherwise retransmits more on partial ACKs.
  */
@@ -2973,7 +3022,7 @@ 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. */
@@ -3029,6 +3078,8 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 		break;
 	case TCP_CA_Loss:
 		tcp_process_loss(sk, flag, num_dupack, rexmit);
+		if (icsk->icsk_ca_state != TCP_CA_Loss)
+			tcp_update_rto_time(tp);
 		tcp_identify_packet_loss(sk, ack_flag);
 		if (!(icsk->icsk_ca_state == TCP_CA_Open ||
 		      (*ack_flag & FLAG_LOST_RETRANS)))
@@ -3108,17 +3159,10 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 	 * left edge of the send window.
 	 * See draft-ietf-tcplw-high-performance-00, section 3.3.
 	 */
-	if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
-	    flag & FLAG_ACKED) {
-		u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
-
-		if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
-			if (!delta)
-				delta = 1;
-			seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
-			ca_rtt_us = seq_rtt_us;
-		}
-	}
+	if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp &&
+	    tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED)
+		seq_rtt_us = ca_rtt_us = tcp_rtt_tsopt_us(tp);
+
 	rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */
 	if (seq_rtt_us < 0)
 		return false;
@@ -3528,6 +3572,21 @@ static inline bool tcp_may_update_window(const struct tcp_sock *tp,
 		(ack_seq == tp->snd_wl1 && (nwin > tp->snd_wnd || !nwin));
 }
 
+static void tcp_snd_sne_update(struct tcp_sock *tp, u32 ack)
+{
+#ifdef CONFIG_TCP_AO
+	struct tcp_ao_info *ao;
+
+	if (!static_branch_unlikely(&tcp_ao_needed.key))
+		return;
+
+	ao = rcu_dereference_protected(tp->ao_info,
+				       lockdep_sock_is_held((struct sock *)tp));
+	if (ao && ack < tp->snd_una)
+		ao->snd_sne++;
+#endif
+}
+
 /* If we update tp->snd_una, also update tp->bytes_acked */
 static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack)
 {
@@ -3535,9 +3594,25 @@ static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack)
 
 	sock_owned_by_me((struct sock *)tp);
 	tp->bytes_acked += delta;
+	tcp_snd_sne_update(tp, ack);
 	tp->snd_una = ack;
 }
 
+static void tcp_rcv_sne_update(struct tcp_sock *tp, u32 seq)
+{
+#ifdef CONFIG_TCP_AO
+	struct tcp_ao_info *ao;
+
+	if (!static_branch_unlikely(&tcp_ao_needed.key))
+		return;
+
+	ao = rcu_dereference_protected(tp->ao_info,
+				       lockdep_sock_is_held((struct sock *)tp));
+	if (ao && seq < tp->rcv_nxt)
+		ao->rcv_sne++;
+#endif
+}
+
 /* If we update tp->rcv_nxt, also update tp->bytes_received */
 static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq)
 {
@@ -3545,6 +3620,7 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq)
 
 	sock_owned_by_me((struct sock *)tp);
 	tp->bytes_received += delta;
+	tcp_rcv_sne_update(tp, seq);
 	WRITE_ONCE(tp->rcv_nxt, seq);
 }
 
@@ -4211,39 +4287,58 @@ static bool tcp_fast_parse_options(const struct net *net,
 	return true;
 }
 
-#ifdef CONFIG_TCP_MD5SIG
+#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO)
 /*
- * Parse MD5 Signature option
+ * Parse Signature options
  */
-const u8 *tcp_parse_md5sig_option(const struct tcphdr *th)
+int tcp_do_parse_auth_options(const struct tcphdr *th,
+			      const u8 **md5_hash, const u8 **ao_hash)
 {
 	int length = (th->doff << 2) - sizeof(*th);
 	const u8 *ptr = (const u8 *)(th + 1);
+	unsigned int minlen = TCPOLEN_MD5SIG;
+
+	if (IS_ENABLED(CONFIG_TCP_AO))
+		minlen = sizeof(struct tcp_ao_hdr) + 1;
+
+	*md5_hash = NULL;
+	*ao_hash = NULL;
 
 	/* If not enough data remaining, we can short cut */
-	while (length >= TCPOLEN_MD5SIG) {
+	while (length >= minlen) {
 		int opcode = *ptr++;
 		int opsize;
 
 		switch (opcode) {
 		case TCPOPT_EOL:
-			return NULL;
+			return 0;
 		case TCPOPT_NOP:
 			length--;
 			continue;
 		default:
 			opsize = *ptr++;
 			if (opsize < 2 || opsize > length)
-				return NULL;
-			if (opcode == TCPOPT_MD5SIG)
-				return opsize == TCPOLEN_MD5SIG ? ptr : NULL;
+				return -EINVAL;
+			if (opcode == TCPOPT_MD5SIG) {
+				if (opsize != TCPOLEN_MD5SIG)
+					return -EINVAL;
+				if (unlikely(*md5_hash || *ao_hash))
+					return -EEXIST;
+				*md5_hash = ptr;
+			} else if (opcode == TCPOPT_AO) {
+				if (opsize <= sizeof(struct tcp_ao_hdr))
+					return -EINVAL;
+				if (unlikely(*md5_hash || *ao_hash))
+					return -EEXIST;
+				*ao_hash = ptr;
+			}
 		}
 		ptr += opsize - 2;
 		length -= opsize;
 	}
-	return NULL;
+	return 0;
 }
-EXPORT_SYMBOL(tcp_parse_md5sig_option);
+EXPORT_SYMBOL(tcp_do_parse_auth_options);
 #endif
 
 /* Sorry, PAWS as specified is broken wrt. pure-ACKs -DaveM
@@ -4486,12 +4581,23 @@ static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb)
 {
 	/* When the ACK path fails or drops most ACKs, the sender would
 	 * timeout and spuriously retransmit the same segment repeatedly.
-	 * The receiver remembers and reflects via DSACKs. Leverage the
-	 * DSACK state and change the txhash to re-route speculatively.
+	 * If it seems our ACKs are not reaching the other side,
+	 * based on receiving a duplicate data segment with new flowlabel
+	 * (suggesting the sender suffered an RTO), and we are not already
+	 * repathing due to our own RTO, then rehash the socket to repath our
+	 * packets.
 	 */
-	if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq &&
+#if IS_ENABLED(CONFIG_IPV6)
+	if (inet_csk(sk)->icsk_ca_state != TCP_CA_Loss &&
+	    skb->protocol == htons(ETH_P_IPV6) &&
+	    (tcp_sk(sk)->inet_conn.icsk_ack.lrcv_flowlabel !=
+	     ntohl(ip6_flowlabel(ipv6_hdr(skb)))) &&
 	    sk_rethink_txhash(sk))
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDUPLICATEDATAREHASH);
+
+	/* Save last flowlabel after a spurious retrans. */
+	tcp_save_lrcv_flowlabel(sk, skb);
+#endif
 }
 
 static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
@@ -4808,6 +4914,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	u32 seq, end_seq;
 	bool fragstolen;
 
+	tcp_save_lrcv_flowlabel(sk, skb);
 	tcp_ecn_check_ce(sk, skb);
 
 	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
@@ -5553,6 +5660,14 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
 	    tcp_in_quickack_mode(sk) ||
 	    /* Protocol state mandates a one-time immediate ACK */
 	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOW) {
+		/* If we are running from __release_sock() in user context,
+		 * Defer the ack until tcp_release_cb().
+		 */
+		if (sock_owned_by_user_nocheck(sk) &&
+		    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_backlog_ack_defer)) {
+			set_bit(TCP_ACK_DEFERRED, &sk->sk_tsq_flags);
+			return;
+		}
 send_now:
 		tcp_send_ack(sk);
 		return;
@@ -6087,6 +6202,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
+	tcp_ao_finish_connect(sk, skb);
 	tcp_set_state(sk, TCP_ESTABLISHED);
 	icsk->icsk_ack.lrcvtime = tcp_jiffies32;
 
@@ -6235,7 +6351,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 
 		if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
 		    !between(tp->rx_opt.rcv_tsecr, tp->retrans_stamp,
-			     tcp_time_stamp(tp))) {
+			     tcp_time_stamp_ts(tp))) {
 			NET_INC_STATS(sock_net(sk),
 					LINUX_MIB_PAWSACTIVEREJECTED);
 			goto reset_and_undo;
@@ -6372,6 +6488,16 @@ consume:
 		 * simultaneous connect with crossed SYNs.
 		 * Particularly, it can be connect to self.
 		 */
+#ifdef CONFIG_TCP_AO
+		struct tcp_ao_info *ao;
+
+		ao = rcu_dereference_protected(tp->ao_info,
+					       lockdep_sock_is_held(sk));
+		if (ao) {
+			WRITE_ONCE(ao->risn, th->seq);
+			ao->rcv_sne = 0;
+		}
+#endif
 		tcp_set_state(sk, TCP_SYN_RECV);
 
 		if (tp->rx_opt.saw_tstamp) {
@@ -6436,22 +6562,24 @@ 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;
+	tcp_update_rto_time(tp);
+	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);
 
@@ -6582,6 +6710,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 					  skb);
 			WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 		}
+		tcp_ao_established(sk);
 		smp_mb();
 		tcp_set_state(sk, TCP_ESTABLISHED);
 		sk->sk_state_change(sk);
@@ -6958,6 +7087,10 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	struct flowi fl;
 	u8 syncookies;
 
+#ifdef CONFIG_TCP_AO
+	const struct tcp_ao_hdr *aoh;
+#endif
+
 	syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies);
 
 	/* TW buckets are converted to open requests without
@@ -6982,6 +7115,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	req->syncookie = want_cookie;
 	tcp_rsk(req)->af_specific = af_ops;
 	tcp_rsk(req)->ts_off = 0;
+	tcp_rsk(req)->req_usec_ts = -1;
 #if IS_ENABLED(CONFIG_MPTCP)
 	tcp_rsk(req)->is_mptcp = 0;
 #endif
@@ -7043,6 +7177,17 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			inet_rsk(req)->ecn_ok = 0;
 	}
 
+#ifdef CONFIG_TCP_AO
+	if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh))
+		goto drop_and_release; /* Invalid TCP options */
+	if (aoh) {
+		tcp_rsk(req)->maclen = aoh->length - sizeof(struct tcp_ao_hdr);
+		tcp_rsk(req)->ao_rcv_next = aoh->keyid;
+		tcp_rsk(req)->ao_keyid = aoh->rnext_keyid;
+	} else {
+		tcp_rsk(req)->maclen = 0;
+	}
+#endif
 	tcp_rsk(req)->snt_isn = isn;
 	tcp_rsk(req)->txhash = net_tx_rndhash();
 	tcp_rsk(req)->syn_tos = TCP_SKB_CB(skb)->ip_dsfield;