1 files changed, 73 insertions, 9 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e51c644..b188e0d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -111,6 +111,25 @@ int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
 #define REXMIT_LOST	1 /* retransmit packets marked lost */
 #define REXMIT_NEW	2 /* FRTO-style transmit of unsent/new packets */
 
+#if IS_ENABLED(CONFIG_TLS_DEVICE)
+static DEFINE_STATIC_KEY_FALSE(clean_acked_data_enabled);
+
+void clean_acked_data_enable(struct inet_connection_sock *icsk,
+			     void (*cad)(struct sock *sk, u32 ack_seq))
+{
+	icsk->icsk_clean_acked = cad;
+	static_branch_inc(&clean_acked_data_enabled);
+}
+EXPORT_SYMBOL_GPL(clean_acked_data_enable);
+
+void clean_acked_data_disable(struct inet_connection_sock *icsk)
+{
+	static_branch_dec(&clean_acked_data_enabled);
+	icsk->icsk_clean_acked = NULL;
+}
+EXPORT_SYMBOL_GPL(clean_acked_data_disable);
+#endif
+
 static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb,
 			     unsigned int len)
 {
@@ -582,6 +601,8 @@ void tcp_rcv_space_adjust(struct sock *sk)
 	u32 copied;
 	int time;
 
+	trace_tcp_rcv_space_adjust(sk);
+
 	tcp_mstamp_refresh(tp);
 	time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time);
 	if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0)
@@ -3496,6 +3517,22 @@ static void tcp_xmit_recovery(struct sock *sk, int rexmit)
 	tcp_xmit_retransmit_queue(sk);
 }
 
+/* Returns the number of packets newly acked or sacked by the current ACK */
+static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered, int flag)
+{
+	const struct net *net = sock_net(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+	u32 delivered;
+
+	delivered = tp->delivered - prior_delivered;
+	NET_ADD_STATS(net, LINUX_MIB_TCPDELIVERED, delivered);
+	if (flag & FLAG_ECE) {
+		tp->delivered_ce += delivered;
+		NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, delivered);
+	}
+	return delivered;
+}
+
 /* This routine deals with incoming acks, but not outgoing ones. */
 static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 {
@@ -3542,6 +3579,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	if (after(ack, prior_snd_una)) {
 		flag |= FLAG_SND_UNA_ADVANCED;
 		icsk->icsk_retransmits = 0;
+
+#if IS_ENABLED(CONFIG_TLS_DEVICE)
+		if (static_branch_unlikely(&clean_acked_data_enabled))
+			if (icsk->icsk_clean_acked)
+				icsk->icsk_clean_acked(sk, ack);
+#endif
 	}
 
 	prior_fack = tcp_is_sack(tp) ? tcp_highest_sack_seq(tp) : tp->snd_una;
@@ -3619,7 +3662,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
 		sk_dst_confirm(sk);
 
-	delivered = tp->delivered - delivered;	/* freshly ACKed or SACKed */
+	delivered = tcp_newly_delivered(sk, delivered, flag);
 	lost = tp->lost - lost;			/* freshly marked lost */
 	rs.is_ack_delayed = !!(flag & FLAG_ACK_MAYBE_DELAYED);
 	tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate);
@@ -3629,9 +3672,11 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 no_queue:
 	/* If data was DSACKed, see if we can undo a cwnd reduction. */
-	if (flag & FLAG_DSACKING_ACK)
+	if (flag & FLAG_DSACKING_ACK) {
 		tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
 				      &rexmit);
+		tcp_newly_delivered(sk, delivered, flag);
+	}
 	/* If this ack opens up a zero window, clear backoff.  It was
 	 * being used to time the probes, and is probably far higher than
 	 * it needs to be for normal retransmission.
@@ -3655,6 +3700,7 @@ old_ack:
 						&sack_state);
 		tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
 				      &rexmit);
+		tcp_newly_delivered(sk, delivered, flag);
 		tcp_xmit_recovery(sk, rexmit);
 	}
 
@@ -4573,6 +4619,17 @@ err:
 
 }
 
+void tcp_data_ready(struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	int avail = tp->rcv_nxt - tp->copied_seq;
+
+	if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE))
+		return;
+
+	sk->sk_data_ready(sk);
+}
+
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -4630,7 +4687,7 @@ queue_and_out:
 		if (eaten > 0)
 			kfree_skb_partial(skb, fragstolen);
 		if (!sock_flag(sk, SOCK_DEAD))
-			sk->sk_data_ready(sk);
+			tcp_data_ready(sk);
 		return;
 	}
 
@@ -5023,9 +5080,12 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
 	    /* More than one full frame received... */
 	if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss &&
 	     /* ... and right edge of window advances far enough.
-	      * (tcp_recvmsg() will send ACK otherwise). Or...
+	      * (tcp_recvmsg() will send ACK otherwise).
+	      * If application uses SO_RCVLOWAT, we want send ack now if
+	      * we have not received enough bytes to satisfy the condition.
 	      */
-	     __tcp_select_window(sk) >= tp->rcv_wnd) ||
+	    (tp->rcv_nxt - tp->copied_seq < sk->sk_rcvlowat ||
+	     __tcp_select_window(sk) >= tp->rcv_wnd)) ||
 	    /* We ACK each frame or... */
 	    tcp_in_quickack_mode(sk) ||
 	    /* We have out of order data. */
@@ -5428,7 +5488,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 no_ack:
 			if (eaten)
 				kfree_skb_partial(skb, fragstolen);
-			sk->sk_data_ready(sk);
+			tcp_data_ready(sk);
 			return;
 		}
 	}
@@ -5550,9 +5610,12 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 		return true;
 	}
 	tp->syn_data_acked = tp->syn_data;
-	if (tp->syn_data_acked)
-		NET_INC_STATS(sock_net(sk),
-				LINUX_MIB_TCPFASTOPENACTIVE);
+	if (tp->syn_data_acked) {
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE);
+		/* SYN-data is counted as two separate packets in tcp_ack() */
+		if (tp->delivered > 1)
+			--tp->delivered;
+	}
 
 	tcp_fastopen_add_skb(sk, synack);
 
@@ -5884,6 +5947,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 	}
 	switch (sk->sk_state) {
 	case TCP_SYN_RECV:
+		tp->delivered++; /* SYN-ACK delivery isn't tracked in tcp_ack */
 		if (!tp->srtt_us)
 			tcp_synack_rtt_meas(sk, req);