1 files changed, 281 insertions, 157 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index df7b13f0e5e0..0cbf81bf3d45 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -72,9 +72,10 @@
 #include <linux/prefetch.h>
 #include <net/dst.h>
 #include <net/tcp.h>
+#include <net/proto_memory.h>
 #include <net/inet_common.h>
 #include <linux/ipsec.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 #include <linux/errqueue.h>
 #include <trace/events/tcp.h>
 #include <linux/jump_label_ratelimit.h>
@@ -237,9 +238,20 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
 		 */
 		if (unlikely(len != icsk->icsk_ack.rcv_mss)) {
 			u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE;
+			u8 old_ratio = tcp_sk(sk)->scaling_ratio;
 
 			do_div(val, skb->truesize);
 			tcp_sk(sk)->scaling_ratio = val ? val : 1;
+
+			if (old_ratio != tcp_sk(sk)->scaling_ratio) {
+				struct tcp_sock *tp = tcp_sk(sk);
+
+				val = tcp_win_from_space(sk, sk->sk_rcvbuf);
+				tcp_set_window_clamp(sk, val);
+
+				if (tp->window_clamp < tp->rcvq_space.space)
+					tp->rcvq_space.space = tp->window_clamp;
+			}
 		}
 		icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
 					       tcp_sk(sk)->advmss);
@@ -563,19 +575,20 @@ static void tcp_init_buffer_space(struct sock *sk)
 	maxwin = tcp_full_space(sk);
 
 	if (tp->window_clamp >= maxwin) {
-		tp->window_clamp = maxwin;
+		WRITE_ONCE(tp->window_clamp, maxwin);
 
 		if (tcp_app_win && maxwin > 4 * tp->advmss)
-			tp->window_clamp = max(maxwin -
-					       (maxwin >> tcp_app_win),
-					       4 * tp->advmss);
+			WRITE_ONCE(tp->window_clamp,
+				   max(maxwin - (maxwin >> tcp_app_win),
+				       4 * tp->advmss));
 	}
 
 	/* Force reservation of one segment. */
 	if (tcp_app_win &&
 	    tp->window_clamp > 2 * tp->advmss &&
 	    tp->window_clamp + tp->advmss > maxwin)
-		tp->window_clamp = max(2 * tp->advmss, maxwin - tp->advmss);
+		WRITE_ONCE(tp->window_clamp,
+			   max(2 * tp->advmss, maxwin - tp->advmss));
 
 	tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp);
 	tp->snd_cwnd_stamp = tcp_jiffies32;
@@ -773,7 +786,8 @@ void tcp_rcv_space_adjust(struct sock *sk)
 			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
 
 			/* Make the window clamp follow along.  */
-			tp->window_clamp = tcp_win_from_space(sk, rcvbuf);
+			WRITE_ONCE(tp->window_clamp,
+				   tcp_win_from_space(sk, rcvbuf));
 		}
 	}
 	tp->rcvq_space.space = copied;
@@ -911,7 +925,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
 			tp->rtt_seq = tp->snd_nxt;
 			tp->mdev_max_us = tcp_rto_min_us(sk);
 
-			tcp_bpf_rtt(sk);
+			tcp_bpf_rtt(sk, mrtt_us, srtt);
 		}
 	} else {
 		/* no previous measure. */
@@ -921,7 +935,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
 		tp->mdev_max_us = tp->rttvar_us;
 		tp->rtt_seq = tp->snd_nxt;
 
-		tcp_bpf_rtt(sk);
+		tcp_bpf_rtt(sk, mrtt_us, srtt);
 	}
 	tp->srtt_us = max(1U, srtt);
 }
@@ -1164,7 +1178,7 @@ static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered,
  * L|R	1		- orig is lost, retransmit is in flight.
  * S|R  1		- orig reached receiver, retrans is still in flight.
  * (L|S|R is logically valid, it could occur when L|R is sacked,
- *  but it is equivalent to plain S and code short-curcuits it to S.
+ *  but it is equivalent to plain S and code short-circuits it to S.
  *  L|S is logically invalid, it would mean -1 packet in flight 8))
  *
  * These 6 states form finite state machine, controlled by the following events:
@@ -2126,8 +2140,16 @@ void tcp_clear_retrans(struct tcp_sock *tp)
 static inline void tcp_init_undo(struct tcp_sock *tp)
 {
 	tp->undo_marker = tp->snd_una;
+
 	/* Retransmission still in flight may cause DSACKs later. */
-	tp->undo_retrans = tp->retrans_out ? : -1;
+	/* First, account for regular retransmits in flight: */
+	tp->undo_retrans = tp->retrans_out;
+	/* Next, account for TLP retransmits in flight: */
+	if (tp->tlp_high_seq && tp->tlp_retrans)
+		tp->undo_retrans++;
+	/* Finally, avoid 0, because undo_retrans==0 means "can undo now": */
+	if (!tp->undo_retrans)
+		tp->undo_retrans = -1;
 }
 
 static bool tcp_is_rack(const struct sock *sk)
@@ -2206,6 +2228,7 @@ void tcp_enter_loss(struct sock *sk)
 
 	tcp_set_ca_state(sk, TCP_CA_Loss);
 	tp->high_seq = tp->snd_nxt;
+	tp->tlp_high_seq = 0;
 	tcp_ecn_queue_cwr(tp);
 
 	/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
@@ -2456,8 +2479,22 @@ static bool tcp_skb_spurious_retrans(const struct tcp_sock *tp,
  */
 static inline bool tcp_packet_delayed(const struct tcp_sock *tp)
 {
-	return tp->retrans_stamp &&
-	       tcp_tsopt_ecr_before(tp, tp->retrans_stamp);
+	const struct sock *sk = (const struct sock *)tp;
+
+	if (tp->retrans_stamp &&
+	    tcp_tsopt_ecr_before(tp, tp->retrans_stamp))
+		return true;  /* got echoed TS before first retransmission */
+
+	/* Check if nothing was retransmitted (retrans_stamp==0), which may
+	 * happen in fast recovery due to TSQ. But we ignore zero retrans_stamp
+	 * in TCP_SYN_SENT, since when we set FLAG_SYN_ACKED we also clear
+	 * retrans_stamp even if we had retransmitted the SYN.
+	 */
+	if (!tp->retrans_stamp &&	   /* no record of a retransmit/SYN? */
+	    sk->sk_state != TCP_SYN_SENT)  /* not the FLAG_SYN_ACKED case? */
+		return true;  /* nothing was retransmitted */
+
+	return false;
 }
 
 /* Undo procedures. */
@@ -2491,6 +2528,16 @@ static bool tcp_any_retrans_done(const struct sock *sk)
 	return false;
 }
 
+/* If loss recovery is finished and there are no retransmits out in the
+ * network, then we clear retrans_stamp so that upon the next loss recovery
+ * retransmits_timed_out() and timestamp-undo are using the correct value.
+ */
+static void tcp_retrans_stamp_cleanup(struct sock *sk)
+{
+	if (!tcp_any_retrans_done(sk))
+		tcp_sk(sk)->retrans_stamp = 0;
+}
+
 static void DBGUNDO(struct sock *sk, const char *msg)
 {
 #if FASTRETRANS_DEBUG > 1
@@ -2779,13 +2826,37 @@ static void tcp_mtup_probe_success(struct sock *sk)
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMTUPSUCCESS);
 }
 
+/* Sometimes we deduce that packets have been dropped due to reasons other than
+ * congestion, like path MTU reductions or failed client TFO attempts. In these
+ * cases we call this function to retransmit as many packets as cwnd allows,
+ * without reducing cwnd. Given that retransmits will set retrans_stamp to a
+ * non-zero value (and may do so in a later calling context due to TSQ), we
+ * also enter CA_Loss so that we track when all retransmitted packets are ACKed
+ * and clear retrans_stamp when that happens (to ensure later recurring RTOs
+ * are using the correct retrans_stamp and don't declare ETIMEDOUT
+ * prematurely).
+ */
+static void tcp_non_congestion_loss_retransmit(struct sock *sk)
+{
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (icsk->icsk_ca_state != TCP_CA_Loss) {
+		tp->high_seq = tp->snd_nxt;
+		tp->snd_ssthresh = tcp_current_ssthresh(sk);
+		tp->prior_ssthresh = 0;
+		tp->undo_marker = 0;
+		tcp_set_ca_state(sk, TCP_CA_Loss);
+	}
+	tcp_xmit_retransmit_queue(sk);
+}
+
 /* Do a simple retransmit without using the backoff mechanisms in
  * tcp_timer. This is used for path mtu discovery.
  * The socket is already locked here.
  */
 void tcp_simple_retransmit(struct sock *sk)
 {
-	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 	int mss;
@@ -2825,14 +2896,7 @@ void tcp_simple_retransmit(struct sock *sk)
 	 * in network, but units changed and effective
 	 * cwnd/ssthresh really reduced now.
 	 */
-	if (icsk->icsk_ca_state != TCP_CA_Loss) {
-		tp->high_seq = tp->snd_nxt;
-		tp->snd_ssthresh = tcp_current_ssthresh(sk);
-		tp->prior_ssthresh = 0;
-		tp->undo_marker = 0;
-		tcp_set_ca_state(sk, TCP_CA_Loss);
-	}
-	tcp_xmit_retransmit_queue(sk);
+	tcp_non_congestion_loss_retransmit(sk);
 }
 EXPORT_SYMBOL(tcp_simple_retransmit);
 
@@ -2841,6 +2905,9 @@ void tcp_enter_recovery(struct sock *sk, bool ece_ack)
 	struct tcp_sock *tp = tcp_sk(sk);
 	int mib_idx;
 
+	/* Start the clock with our fast retransmit, for undo and ETIMEDOUT. */
+	tcp_retrans_stamp_cleanup(sk);
+
 	if (tcp_is_reno(tp))
 		mib_idx = LINUX_MIB_TCPRENORECOVERY;
 	else
@@ -3057,7 +3124,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 			return;
 
 		if (tcp_try_undo_dsack(sk))
-			tcp_try_keep_open(sk);
+			tcp_try_to_open(sk, flag);
 
 		tcp_identify_packet_loss(sk, ack_flag);
 		if (icsk->icsk_ca_state != TCP_CA_Recovery) {
@@ -3539,7 +3606,7 @@ static void tcp_cong_control(struct sock *sk, u32 ack, u32 acked_sacked,
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 
 	if (icsk->icsk_ca_ops->cong_control) {
-		icsk->icsk_ca_ops->cong_control(sk, rs);
+		icsk->icsk_ca_ops->cong_control(sk, ack, flag, rs);
 		return;
 	}
 
@@ -3575,8 +3642,10 @@ static void tcp_snd_sne_update(struct tcp_sock *tp, u32 ack)
 
 	ao = rcu_dereference_protected(tp->ao_info,
 				       lockdep_sock_is_held((struct sock *)tp));
-	if (ao && ack < tp->snd_una)
+	if (ao && ack < tp->snd_una) {
 		ao->snd_sne++;
+		trace_tcp_ao_snd_sne_update((struct sock *)tp, ao->snd_sne);
+	}
 #endif
 }
 
@@ -3601,8 +3670,10 @@ static void tcp_rcv_sne_update(struct tcp_sock *tp, u32 seq)
 
 	ao = rcu_dereference_protected(tp->ao_info,
 				       lockdep_sock_is_held((struct sock *)tp));
-	if (ao && seq < tp->rcv_nxt)
+	if (ao && seq < tp->rcv_nxt) {
 		ao->rcv_sne++;
+		trace_tcp_ao_rcv_sne_update((struct sock *)tp, ao->rcv_sne);
+	}
 #endif
 }
 
@@ -4204,6 +4275,13 @@ void tcp_parse_options(const struct net *net,
 				 */
 				break;
 #endif
+#ifdef CONFIG_TCP_AO
+			case TCPOPT_AO:
+				/* TCP AO has already been checked
+				 * (see tcp_inbound_ao_hash()).
+				 */
+				break;
+#endif
 			case TCPOPT_FASTOPEN:
 				tcp_parse_fastopen_option(
 					opsize - TCPOLEN_FASTOPEN_BASE,
@@ -4378,34 +4456,40 @@ static u32 tcp_tsval_replay(const struct sock *sk)
 	return inet_csk(sk)->icsk_rto * 1200 / HZ;
 }
 
-static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
+static enum skb_drop_reason tcp_disordered_ack_check(const struct sock *sk,
+						     const struct sk_buff *skb)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	const struct tcphdr *th = tcp_hdr(skb);
-	u32 seq = TCP_SKB_CB(skb)->seq;
+	SKB_DR_INIT(reason, TCP_RFC7323_PAWS);
 	u32 ack = TCP_SKB_CB(skb)->ack_seq;
+	u32 seq = TCP_SKB_CB(skb)->seq;
 
-	return	/* 1. Pure ACK with correct sequence number. */
-		(th->ack && seq == TCP_SKB_CB(skb)->end_seq && seq == tp->rcv_nxt) &&
+	/* 1. Is this not a pure ACK ? */
+	if (!th->ack || seq != TCP_SKB_CB(skb)->end_seq)
+		return reason;
 
-		/* 2. ... and duplicate ACK. */
-		ack == tp->snd_una &&
+	/* 2. Is its sequence not the expected one ? */
+	if (seq != tp->rcv_nxt)
+		return before(seq, tp->rcv_nxt) ?
+			SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK :
+			reason;
 
-		/* 3. ... and does not update window. */
-		!tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) &&
+	/* 3. Is this not a duplicate ACK ? */
+	if (ack != tp->snd_una)
+		return reason;
 
-		/* 4. ... and sits in replay window. */
-		(s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <=
-		tcp_tsval_replay(sk);
-}
+	/* 4. Is this updating the window ? */
+	if (tcp_may_update_window(tp, ack, seq, ntohs(th->window) <<
+						tp->rx_opt.snd_wscale))
+		return reason;
 
-static inline bool tcp_paws_discard(const struct sock *sk,
-				   const struct sk_buff *skb)
-{
-	const struct tcp_sock *tp = tcp_sk(sk);
+	/* 5. Is this not in the replay window ? */
+	if ((s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) >
+	    tcp_tsval_replay(sk))
+		return reason;
 
-	return !tcp_paws_check(&tp->rx_opt, TCP_PAWS_WINDOW) &&
-	       !tcp_disordered_ack(sk, skb);
+	return 0;
 }
 
 /* Check segment sequence number for validity.
@@ -4433,9 +4517,26 @@ static enum skb_drop_reason tcp_sequence(const struct tcp_sock *tp,
 	return SKB_NOT_DROPPED_YET;
 }
 
+
+void tcp_done_with_error(struct sock *sk, int err)
+{
+	/* This barrier is coupled with smp_rmb() in tcp_poll() */
+	WRITE_ONCE(sk->sk_err, err);
+	smp_wmb();
+
+	tcp_write_queue_purge(sk);
+	tcp_done(sk);
+
+	if (!sock_flag(sk, SOCK_DEAD))
+		sk_error_report(sk);
+}
+EXPORT_SYMBOL(tcp_done_with_error);
+
 /* When we get a reset we do this. */
 void tcp_reset(struct sock *sk, struct sk_buff *skb)
 {
+	int err;
+
 	trace_tcp_receive_reset(sk);
 
 	/* mptcp can't tell us to ignore reset pkts,
@@ -4447,24 +4548,17 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb)
 	/* We want the right error as BSD sees it (and indeed as we do). */
 	switch (sk->sk_state) {
 	case TCP_SYN_SENT:
-		WRITE_ONCE(sk->sk_err, ECONNREFUSED);
+		err = ECONNREFUSED;
 		break;
 	case TCP_CLOSE_WAIT:
-		WRITE_ONCE(sk->sk_err, EPIPE);
+		err = EPIPE;
 		break;
 	case TCP_CLOSE:
 		return;
 	default:
-		WRITE_ONCE(sk->sk_err, ECONNRESET);
+		err = ECONNRESET;
 	}
-	/* This barrier is coupled with smp_rmb() in tcp_poll() */
-	smp_wmb();
-
-	tcp_write_queue_purge(sk);
-	tcp_done(sk);
-
-	if (!sock_flag(sk, SOCK_DEAD))
-		sk_error_report(sk);
+	tcp_done_with_error(sk, err);
 }
 
 /*
@@ -4800,14 +4894,9 @@ static bool tcp_try_coalesce(struct sock *sk,
 	if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
 		return false;
 
-	if (!mptcp_skb_can_collapse(to, from))
+	if (!tcp_skb_can_collapse_rx(to, from))
 		return false;
 
-#ifdef CONFIG_TLS_DEVICE
-	if (from->decrypted != to->decrypted)
-		return false;
-#endif
-
 	if (!skb_try_coalesce(to, from, fragstolen, &delta))
 		return false;
 
@@ -4844,11 +4933,11 @@ static bool tcp_ooo_try_coalesce(struct sock *sk,
 	return res;
 }
 
-static void tcp_drop_reason(struct sock *sk, struct sk_buff *skb,
-			    enum skb_drop_reason reason)
+noinline_for_tracing static void
+tcp_drop_reason(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason)
 {
 	sk_drops_add(sk, skb);
-	kfree_skb_reason(skb, reason);
+	sk_skb_reason_drop(sk, skb, reason);
 }
 
 /* This one checks to see if we can put data from the
@@ -4887,7 +4976,7 @@ static void tcp_ofo_queue(struct sock *sk)
 		tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
 		fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
 		if (!eaten)
-			__skb_queue_tail(&sk->sk_receive_queue, skb);
+			tcp_add_receive_queue(sk, skb);
 		else
 			kfree_skb_partial(skb, fragstolen);
 
@@ -5079,7 +5168,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb,
 				  skb, fragstolen)) ? 1 : 0;
 	tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq);
 	if (!eaten) {
-		__skb_queue_tail(&sk->sk_receive_queue, skb);
+		tcp_add_receive_queue(sk, skb);
 		skb_set_owner_r(skb, sk);
 	}
 	return eaten;
@@ -5162,7 +5251,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 		__kfree_skb(skb);
 		return;
 	}
-	skb_dst_drop(skb);
+	tcp_cleanup_skb(skb);
 	__skb_pull(skb, tcp_hdr(skb)->doff * 4);
 
 	reason = SKB_DROP_REASON_NOT_SPECIFIED;
@@ -5174,6 +5263,16 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	 */
 	if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) {
 		if (tcp_receive_window(tp) == 0) {
+			/* Some stacks are known to send bare FIN packets
+			 * in a loop even if we send RWIN 0 in our ACK.
+			 * Accepting this FIN does not hurt memory pressure
+			 * because the FIN flag will simply be merged to the
+			 * receive queue tail skb in most cases.
+			 */
+			if (!skb->len &&
+			    (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN))
+				goto queue_and_out;
+
 			reason = SKB_DROP_REASON_TCP_ZEROWINDOW;
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP);
 			goto out_of_window;
@@ -5188,7 +5287,7 @@ queue_and_out:
 			inet_csk_schedule_ack(sk);
 			sk->sk_data_ready(sk);
 
-			if (skb_queue_len(&sk->sk_receive_queue)) {
+			if (skb_queue_len(&sk->sk_receive_queue) && skb->len) {
 				reason = SKB_DROP_REASON_PROTO_MEM;
 				NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
 				goto drop;
@@ -5331,6 +5430,9 @@ restart:
 	for (end_of_skbs = true; skb != NULL && skb != tail; skb = n) {
 		n = tcp_skb_next(skb, list);
 
+		if (!skb_frags_readable(skb))
+			goto skip_this;
+
 		/* No new bits? It is possible on ofo queue. */
 		if (!before(start, TCP_SKB_CB(skb)->end_seq)) {
 			skb = tcp_collapse_one(sk, skb, list, root);
@@ -5351,17 +5453,20 @@ restart:
 			break;
 		}
 
-		if (n && n != tail && mptcp_skb_can_collapse(skb, n) &&
+		if (n && n != tail && skb_frags_readable(n) &&
+		    tcp_skb_can_collapse_rx(skb, n) &&
 		    TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) {
 			end_of_skbs = false;
 			break;
 		}
 
+skip_this:
 		/* Decided to skip this, advance start seq. */
 		start = TCP_SKB_CB(skb)->end_seq;
 	}
 	if (end_of_skbs ||
-	    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
+	    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) ||
+	    !skb_frags_readable(skb))
 		return;
 
 	__skb_queue_head_init(&tmp);
@@ -5375,9 +5480,7 @@ restart:
 			break;
 
 		memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
-#ifdef CONFIG_TLS_DEVICE
-		nskb->decrypted = skb->decrypted;
-#endif
+		skb_copy_decrypted(nskb, skb);
 		TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start;
 		if (list)
 			__skb_queue_before(list, skb, nskb);
@@ -5404,13 +5507,10 @@ restart:
 				skb = tcp_collapse_one(sk, skb, list, root);
 				if (!skb ||
 				    skb == tail ||
-				    !mptcp_skb_can_collapse(nskb, skb) ||
-				    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
+				    !tcp_skb_can_collapse_rx(nskb, skb) ||
+				    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) ||
+				    !skb_frags_readable(skb))
 					goto end;
-#ifdef CONFIG_TLS_DEVICE
-				if (skb->decrypted != nskb->decrypted)
-					goto end;
-#endif
 			}
 		}
 	}
@@ -5861,23 +5961,35 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 	SKB_DR(reason);
 
 	/* RFC1323: H1. Apply PAWS check first. */
-	if (tcp_fast_parse_options(sock_net(sk), skb, th, tp) &&
-	    tp->rx_opt.saw_tstamp &&
-	    tcp_paws_discard(sk, skb)) {
-		if (!th->rst) {
-			if (unlikely(th->syn))
-				goto syn_challenge;
-			NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
-			if (!tcp_oow_rate_limited(sock_net(sk), skb,
-						  LINUX_MIB_TCPACKSKIPPEDPAWS,
-						  &tp->last_oow_ack_time))
-				tcp_send_dupack(sk, skb);
-			SKB_DR_SET(reason, TCP_RFC7323_PAWS);
-			goto discard;
-		}
-		/* Reset is accepted even if it did not pass PAWS. */
+	if (!tcp_fast_parse_options(sock_net(sk), skb, th, tp) ||
+	    !tp->rx_opt.saw_tstamp ||
+	    tcp_paws_check(&tp->rx_opt, TCP_PAWS_WINDOW))
+		goto step1;
+
+	reason = tcp_disordered_ack_check(sk, skb);
+	if (!reason)
+		goto step1;
+	/* Reset is accepted even if it did not pass PAWS. */
+	if (th->rst)
+		goto step1;
+	if (unlikely(th->syn))
+		goto syn_challenge;
+
+	/* Old ACK are common, increment PAWS_OLD_ACK
+	 * and do not send a dupack.
+	 */
+	if (reason == SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK) {
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWS_OLD_ACK);
+		goto discard;
 	}
+	NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
+	if (!tcp_oow_rate_limited(sock_net(sk), skb,
+				  LINUX_MIB_TCPACKSKIPPEDPAWS,
+				  &tp->last_oow_ack_time))
+		tcp_send_dupack(sk, skb);
+	goto discard;
 
+step1:
 	/* Step 1: check sequence number */
 	reason = tcp_sequence(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
 	if (reason) {
@@ -5949,6 +6061,11 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 	 * RFC 5961 4.2 : Send a challenge ack
 	 */
 	if (th->syn) {
+		if (sk->sk_state == TCP_SYN_RECV && sk->sk_socket && th->ack &&
+		    TCP_SKB_CB(skb)->seq + 1 == TCP_SKB_CB(skb)->end_seq &&
+		    TCP_SKB_CB(skb)->seq + 1 == tp->rcv_nxt &&
+		    TCP_SKB_CB(skb)->ack_seq == tp->snd_nxt)
+			goto pass;
 syn_challenge:
 		if (syn_inerr)
 			TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
@@ -5958,6 +6075,7 @@ syn_challenge:
 		goto discard;
 	}
 
+pass:
 	bpf_skops_parse_hdr(sk, skb);
 
 	return true;
@@ -6114,7 +6232,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS);
 
 			/* Bulk data transfer: receiver */
-			skb_dst_drop(skb);
+			tcp_cleanup_skb(skb);
 			__skb_pull(skb, tcp_header_len);
 			eaten = tcp_queue_rcv(sk, skb, &fragstolen);
 
@@ -6288,7 +6406,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 			tp->fastopen_client_fail = TFO_DATA_NOT_ACKED;
 		skb_rbtree_walk_from(data)
 			 tcp_mark_skb_lost(sk, data);
-		tcp_xmit_retransmit_queue(sk);
+		tcp_non_congestion_loss_retransmit(sk);
 		NET_INC_STATS(sock_net(sk),
 				LINUX_MIB_TCPFASTOPENACTIVEFAIL);
 		return true;
@@ -6361,6 +6479,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 				inet_csk_reset_xmit_timer(sk,
 						ICSK_TIME_RETRANS,
 						TCP_TIMEOUT_MIN, TCP_RTO_MAX);
+			SKB_DR_SET(reason, TCP_INVALID_ACK_SEQUENCE);
 			goto reset_and_undo;
 		}
 
@@ -6369,6 +6488,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 			     tcp_time_stamp_ts(tp))) {
 			NET_INC_STATS(sock_net(sk),
 					LINUX_MIB_PAWSACTIVEREJECTED);
+			SKB_DR_SET(reason, TCP_RFC7323_PAWS);
 			goto reset_and_undo;
 		}
 
@@ -6424,7 +6544,8 @@ consume:
 
 		if (!tp->rx_opt.wscale_ok) {
 			tp->rx_opt.snd_wscale = tp->rx_opt.rcv_wscale = 0;
-			tp->window_clamp = min(tp->window_clamp, 65535U);
+			WRITE_ONCE(tp->window_clamp,
+				   min(tp->window_clamp, 65535U));
 		}
 
 		if (tp->rx_opt.saw_tstamp) {
@@ -6572,7 +6693,8 @@ discard_and_undo:
 reset_and_undo:
 	tcp_clear_options(&tp->rx_opt);
 	tp->rx_opt.mss_clamp = saved_clamp;
-	return 1;
+	/* we can reuse/return @reason to its caller to handle the exception */
+	return reason;
 }
 
 static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
@@ -6586,10 +6708,17 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
 	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_update_rto_time(tp);
-	tp->retrans_stamp = 0;
 	inet_csk(sk)->icsk_retransmits = 0;
+	/* In tcp_fastopen_synack_timer() on the first SYNACK RTO we set
+	 * retrans_stamp but don't enter CA_Loss, so in case that happened we
+	 * need to zero retrans_stamp here to prevent spurious
+	 * retransmits_timed_out(). However, if the ACK of our SYNACK caused us
+	 * to enter CA_Recovery then we need to leave retrans_stamp as it was
+	 * set entering CA_Recovery, for correct retransmits_timed_out() and
+	 * undo behavior.
+	 */
+	tcp_retrans_stamp_cleanup(sk);
 
 	/* Once we leave TCP_SYN_RECV or TCP_FIN_WAIT_1,
 	 * we no longer need req so release it.
@@ -6616,14 +6745,14 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
  *	address independent.
  */
 
-int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
+enum skb_drop_reason
+tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcphdr *th = tcp_hdr(skb);
 	struct request_sock *req;
 	int queued = 0;
-	bool acceptable;
 	SKB_DR(reason);
 
 	switch (sk->sk_state) {
@@ -6633,7 +6762,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 
 	case TCP_LISTEN:
 		if (th->ack)
-			return 1;
+			return SKB_DROP_REASON_TCP_FLAGS;
 
 		if (th->rst) {
 			SKB_DR_SET(reason, TCP_RESET);
@@ -6649,12 +6778,10 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			 */
 			rcu_read_lock();
 			local_bh_disable();
-			acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0;
+			icsk->icsk_af_ops->conn_request(sk, skb);
 			local_bh_enable();
 			rcu_read_unlock();
 
-			if (!acceptable)
-				return 1;
 			consume_skb(skb);
 			return 0;
 		}
@@ -6699,17 +6826,25 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		return 0;
 
 	/* step 5: check the ACK field */
-	acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH |
-				      FLAG_UPDATE_TS_RECENT |
-				      FLAG_NO_CHALLENGE_ACK) > 0;
-
-	if (!acceptable) {
-		if (sk->sk_state == TCP_SYN_RECV)
-			return 1;	/* send one RST */
-		tcp_send_challenge_ack(sk);
-		SKB_DR_SET(reason, TCP_OLD_ACK);
-		goto discard;
+	reason = tcp_ack(sk, skb, FLAG_SLOWPATH |
+				  FLAG_UPDATE_TS_RECENT |
+				  FLAG_NO_CHALLENGE_ACK);
+
+	if ((int)reason <= 0) {
+		if (sk->sk_state == TCP_SYN_RECV) {
+			/* send one RST */
+			if (!reason)
+				return SKB_DROP_REASON_TCP_OLD_ACK;
+			return -reason;
+		}
+		/* accept old ack during closing */
+		if ((int)reason < 0) {
+			tcp_send_challenge_ack(sk);
+			reason = -reason;
+			goto discard;
+		}
 	}
+	SKB_DR_SET(reason, NOT_SPECIFIED);
 	switch (sk->sk_state) {
 	case TCP_SYN_RECV:
 		tp->delivered++; /* SYN-ACK delivery isn't tracked in tcp_ack */
@@ -6752,6 +6887,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 
 		tcp_initialize_rcv_mss(sk);
 		tcp_fast_path_on(tp);
+		if (sk->sk_shutdown & SEND_SHUTDOWN)
+			tcp_shutdown(sk, SEND_SHUTDOWN);
 		break;
 
 	case TCP_FIN_WAIT1: {
@@ -6777,7 +6914,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		if (READ_ONCE(tp->linger2) < 0) {
 			tcp_done(sk);
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
-			return 1;
+			return SKB_DROP_REASON_TCP_ABORT_ON_DATA;
 		}
 		if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
 		    after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) {
@@ -6786,7 +6923,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 				tcp_fastopen_active_disable(sk);
 			tcp_done(sk);
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
-			return 1;
+			return SKB_DROP_REASON_TCP_ABORT_ON_DATA;
 		}
 
 		tmo = tcp_fin_time(sk);
@@ -6851,7 +6988,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			    after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) {
 				NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
 				tcp_reset(sk, skb);
-				return 1;
+				return SKB_DROP_REASON_TCP_ABORT_ON_DATA;
 			}
 		}
 		fallthrough;
@@ -6962,35 +7099,10 @@ static void tcp_openreq_init(struct request_sock *req,
 #endif
 }
 
-struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
-				      struct sock *sk_listener,
-				      bool attach_listener)
-{
-	struct request_sock *req = reqsk_alloc(ops, sk_listener,
-					       attach_listener);
-
-	if (req) {
-		struct inet_request_sock *ireq = inet_rsk(req);
-
-		ireq->ireq_opt = NULL;
-#if IS_ENABLED(CONFIG_IPV6)
-		ireq->pktopts = NULL;
-#endif
-		atomic64_set(&ireq->ir_cookie, 0);
-		ireq->ireq_state = TCP_NEW_SYN_RECV;
-		write_pnet(&ireq->ireq_net, sock_net(sk_listener));
-		ireq->ireq_family = sk_listener->sk_family;
-		req->timeout = TCP_TIMEOUT_INIT;
-	}
-
-	return req;
-}
-EXPORT_SYMBOL(inet_reqsk_alloc);
-
 /*
  * Return true if a syncookie should be sent
  */
-static bool tcp_syn_flood_action(const struct sock *sk, const char *proto)
+static bool tcp_syn_flood_action(struct sock *sk, const char *proto)
 {
 	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
 	const char *msg = "Dropping request";
@@ -7091,7 +7203,6 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		     struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_fastopen_cookie foc = { .len = -1 };
-	__u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn;
 	struct tcp_options_received tmp_opt;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
@@ -7101,21 +7212,28 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	struct dst_entry *dst;
 	struct flowi fl;
 	u8 syncookies;
+	u32 isn;
 
 #ifdef CONFIG_TCP_AO
 	const struct tcp_ao_hdr *aoh;
 #endif
 
-	syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies);
+	isn = __this_cpu_read(tcp_tw_isn);
+	if (isn) {
+		/* TW buckets are converted to open requests without
+		 * limitations, they conserve resources and peer is
+		 * evidently real one.
+		 */
+		__this_cpu_write(tcp_tw_isn, 0);
+	} else {
+		syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies);
 
-	/* TW buckets are converted to open requests without
-	 * limitations, they conserve resources and peer is
-	 * evidently real one.
-	 */
-	if ((syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) && !isn) {
-		want_cookie = tcp_syn_flood_action(sk, rsk_ops->slab_name);
-		if (!want_cookie)
-			goto drop;
+		if (syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) {
+			want_cookie = tcp_syn_flood_action(sk,
+							   rsk_ops->slab_name);
+			if (!want_cookie)
+				goto drop;
+		}
 	}
 
 	if (sk_acceptq_is_full(sk)) {
@@ -7154,7 +7272,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	/* Note: tcp_v6_init_req() might override ir_iif for link locals */
 	inet_rsk(req)->ir_iif = inet_request_bound_dev_if(sk, skb);
 
-	dst = af_ops->route_req(sk, skb, &fl, req);
+	dst = af_ops->route_req(sk, skb, &fl, req, isn);
 	if (!dst)
 		goto drop_and_free;
 
@@ -7231,7 +7349,13 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		tcp_rsk(req)->tfo_listener = false;
 		if (!want_cookie) {
 			req->timeout = tcp_timeout_init((struct sock *)req);
-			inet_csk_reqsk_queue_hash_add(sk, req, req->timeout);
+			if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req,
+								    req->timeout))) {
+				reqsk_free(req);
+				dst_release(dst);
+				return 0;
+			}
+
 		}
 		af_ops->send_synack(sk, dst, &fl, req, &foc,
 				    !want_cookie ? TCP_SYNACK_NORMAL :