1 files changed, 42 insertions, 27 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 57c8af1859c1..06fe1cf645d5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -237,6 +237,16 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
 	 */
 	len = skb_shinfo(skb)->gso_size ? : skb->len;
 	if (len >= icsk->icsk_ack.rcv_mss) {
+		/* Note: divides are still a bit expensive.
+		 * For the moment, only adjust scaling_ratio
+		 * when we update icsk_ack.rcv_mss.
+		 */
+		if (unlikely(len != icsk->icsk_ack.rcv_mss)) {
+			u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE;
+
+			do_div(val, skb->truesize);
+			tcp_sk(sk)->scaling_ratio = val ? val : 1;
+		}
 		icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
 					       tcp_sk(sk)->advmss);
 		/* Account for possibly-removed options */
@@ -287,7 +297,7 @@ 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);
 
@@ -295,7 +305,6 @@ 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.
@@ -727,8 +736,8 @@ void tcp_rcv_space_adjust(struct sock *sk)
 
 	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
-		int rcvmem, rcvbuf;
 		u64 rcvwin, grow;
+		int rcvbuf;
 
 		/* minimal window to cope with packet losses, assuming
 		 * steady state. Add some cushion because of small variations.
@@ -740,12 +749,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 		do_div(grow, tp->rcvq_space.space);
 		rcvwin += (grow << 1);
 
-		rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER);
-		while (tcp_win_from_space(sk, rcvmem) < tp->advmss)
-			rcvmem += 128;
-
-		do_div(rcvwin, tp->advmss);
-		rcvbuf = min_t(u64, rcvwin * rcvmem,
+		rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin),
 			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
 		if (rcvbuf > sk->sk_rcvbuf) {
 			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
@@ -3521,7 +3525,7 @@ static inline bool tcp_may_update_window(const struct tcp_sock *tp,
 {
 	return	after(ack, tp->snd_una) ||
 		after(ack_seq, tp->snd_wl1) ||
-		(ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd);
+		(ack_seq == tp->snd_wl1 && (nwin > tp->snd_wnd || !nwin));
 }
 
 /* If we update tp->snd_una, also update tp->bytes_acked */
@@ -4122,9 +4126,8 @@ void tcp_parse_options(const struct net *net,
 				break;
 #ifdef CONFIG_TCP_MD5SIG
 			case TCPOPT_MD5SIG:
-				/*
-				 * The MD5 Hash has already been
-				 * checked (see tcp_v{4,6}_do_rcv()).
+				/* The MD5 Hash has already been
+				 * checked (see tcp_v{4,6}_rcv()).
 				 */
 				break;
 #endif
@@ -4308,10 +4311,16 @@ static inline bool tcp_paws_discard(const struct sock *sk,
  * (borrowed from freebsd)
  */
 
-static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq)
+static enum skb_drop_reason tcp_sequence(const struct tcp_sock *tp,
+					 u32 seq, u32 end_seq)
 {
-	return	!before(end_seq, tp->rcv_wup) &&
-		!after(seq, tp->rcv_nxt + tcp_receive_window(tp));
+	if (before(end_seq, tp->rcv_wup))
+		return SKB_DROP_REASON_TCP_OLD_SEQUENCE;
+
+	if (after(seq, tp->rcv_nxt + tcp_receive_window(tp)))
+		return SKB_DROP_REASON_TCP_INVALID_SEQUENCE;
+
+	return SKB_NOT_DROPPED_YET;
 }
 
 /* When we get a reset we do this. */
@@ -5050,13 +5059,19 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 
 		/* Ok. In sequence. In window. */
 queue_and_out:
-		if (skb_queue_len(&sk->sk_receive_queue) == 0)
-			sk_forced_mem_schedule(sk, skb->truesize);
-		else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
-			reason = SKB_DROP_REASON_PROTO_MEM;
-			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
+		if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
+			/* TODO: maybe ratelimit these WIN 0 ACK ? */
+			inet_csk(sk)->icsk_ack.pending |=
+					(ICSK_ACK_NOMEM | ICSK_ACK_NOW);
+			inet_csk_schedule_ack(sk);
 			sk->sk_data_ready(sk);
-			goto drop;
+
+			if (skb_queue_len(&sk->sk_receive_queue)) {
+				reason = SKB_DROP_REASON_PROTO_MEM;
+				NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
+				goto drop;
+			}
+			sk_forced_mem_schedule(sk, skb->truesize);
 		}
 
 		eaten = tcp_queue_rcv(sk, skb, &fragstolen);
@@ -5734,7 +5749,8 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 	}
 
 	/* Step 1: check sequence number */
-	if (!tcp_sequence(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq)) {
+	reason = tcp_sequence(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
+	if (reason) {
 		/* RFC793, page 37: "In all states except SYN-SENT, all reset
 		 * (RST) segments are validated by checking their SEQ-fields."
 		 * And page 69: "If an incoming segment is not acceptable,
@@ -5751,7 +5767,6 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 		} else if (tcp_reset_check(sk, skb)) {
 			goto reset;
 		}
-		SKB_DR_SET(reason, TCP_INVALID_SEQUENCE);
 		goto discard;
 	}
 
@@ -6315,7 +6330,7 @@ consume:
 		if (fastopen_fail)
 			return -1;
 		if (sk->sk_write_pending ||
-		    icsk->icsk_accept_queue.rskq_defer_accept ||
+		    READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept) ||
 		    inet_csk_in_pingpong_mode(sk)) {
 			/* Save one ACK. Data will be ready after
 			 * several ticks, if write_pending is set.
@@ -6615,7 +6630,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			break;
 		}
 
-		if (tp->linger2 < 0) {
+		if (READ_ONCE(tp->linger2) < 0) {
 			tcp_done(sk);
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
 			return 1;
@@ -6985,7 +7000,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 
 	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
 	tcp_openreq_init(req, &tmp_opt, skb, sk);
-	inet_rsk(req)->no_srccheck = inet_sk(sk)->transparent;
+	inet_rsk(req)->no_srccheck = inet_test_bit(TRANSPARENT, sk);
 
 	/* Note: tcp_v6_init_req() might override ir_iif for link locals */
 	inet_rsk(req)->ir_iif = inet_request_bound_dev_if(sk, skb);