1 files changed, 60 insertions, 167 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 68bc79eb9019..71b76e98371a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1451,11 +1451,6 @@ static u8 tcp_sacktag_one(struct sock *sk,
 		tp->sacked_out += pcount;
 		/* Out-of-order packets delivered */
 		state->sack_delivered += pcount;
-
-		/* Lost marker hint past SACKed? Tweak RFC3517 cnt */
-		if (tp->lost_skb_hint &&
-		    before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq))
-			tp->lost_cnt_hint += pcount;
 	}
 
 	/* D-SACK. We can detect redundant retransmission in S|R and plain R
@@ -1496,9 +1491,6 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
 			tcp_skb_timestamp_us(skb));
 	tcp_rate_skb_delivered(sk, skb, state->rate);
 
-	if (skb == tp->lost_skb_hint)
-		tp->lost_cnt_hint += pcount;
-
 	TCP_SKB_CB(prev)->end_seq += shifted;
 	TCP_SKB_CB(skb)->seq += shifted;
 
@@ -1531,10 +1523,6 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
 
 	if (skb == tp->retransmit_skb_hint)
 		tp->retransmit_skb_hint = prev;
-	if (skb == tp->lost_skb_hint) {
-		tp->lost_skb_hint = prev;
-		tp->lost_cnt_hint -= tcp_skb_pcount(prev);
-	}
 
 	TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
 	TCP_SKB_CB(prev)->eor = TCP_SKB_CB(skb)->eor;
@@ -2151,12 +2139,6 @@ static inline void tcp_init_undo(struct tcp_sock *tp)
 		tp->undo_retrans = -1;
 }
 
-static bool tcp_is_rack(const struct sock *sk)
-{
-	return READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) &
-		TCP_RACK_LOSS_DETECTION;
-}
-
 /* If we detect SACK reneging, forget all SACK information
  * and reset tags completely, otherwise preserve SACKs. If receiver
  * dropped its ofo queue, we will know this due to reneging detection.
@@ -2182,8 +2164,7 @@ static void tcp_timeout_mark_lost(struct sock *sk)
 	skb_rbtree_walk_from(skb) {
 		if (is_reneg)
 			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
-		else if (tcp_is_rack(sk) && skb != head &&
-			 tcp_rack_skb_timeout(tp, skb, 0) > 0)
+		else if (skb != head && tcp_rack_skb_timeout(tp, skb, 0) > 0)
 			continue; /* Don't mark recently sent ones lost yet */
 		tcp_mark_skb_lost(sk, skb);
 	}
@@ -2264,22 +2245,6 @@ static bool tcp_check_sack_reneging(struct sock *sk, int *ack_flag)
 	return false;
 }
 
-/* Heurestics to calculate number of duplicate ACKs. There's no dupACKs
- * counter when SACK is enabled (without SACK, sacked_out is used for
- * that purpose).
- *
- * With reordering, holes may still be in flight, so RFC3517 recovery
- * uses pure sacked_out (total number of SACKed segments) even though
- * it violates the RFC that uses duplicate ACKs, often these are equal
- * but when e.g. out-of-window ACKs or packet duplication occurs,
- * they differ. Since neither occurs due to loss, TCP should really
- * ignore them.
- */
-static inline int tcp_dupack_heuristics(const struct tcp_sock *tp)
-{
-	return tp->sacked_out + 1;
-}
-
 /* Linux NewReno/SACK/ECN state machine.
  * --------------------------------------
  *
@@ -2332,13 +2297,7 @@ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp)
  *
  *		If the receiver supports SACK:
  *
- *		RFC6675/3517: It is the conventional algorithm. A packet is
- *		considered lost if the number of higher sequence packets
- *		SACKed is greater than or equal the DUPACK thoreshold
- *		(reordering). This is implemented in tcp_mark_head_lost and
- *		tcp_update_scoreboard.
- *
- *		RACK (draft-ietf-tcpm-rack-01): it is a newer algorithm
+ *		RACK (RFC8985): RACK is a newer loss detection algorithm
  *		(2017-) that checks timing instead of counting DUPACKs.
  *		Essentially a packet is considered lost if it's not S/ACKed
  *		after RTT + reordering_window, where both metrics are
@@ -2353,8 +2312,8 @@ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp)
  *		is lost (NewReno). This heuristics are the same in NewReno
  *		and SACK.
  *
- * Really tricky (and requiring careful tuning) part of algorithm
- * is hidden in functions tcp_time_to_recover() and tcp_xmit_retransmit_queue().
+ * The really tricky (and requiring careful tuning) part of the algorithm
+ * is hidden in the RACK code in tcp_recovery.c and tcp_xmit_retransmit_queue().
  * The first determines the moment _when_ we should reduce CWND and,
  * hence, slow down forward transmission. In fact, it determines the moment
  * when we decide that hole is caused by loss, rather than by a reorder.
@@ -2377,83 +2336,10 @@ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp)
  * Main question: may we further continue forward transmission
  * with the same cwnd?
  */
-static bool tcp_time_to_recover(struct sock *sk, int flag)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	/* Trick#1: The loss is proven. */
-	if (tp->lost_out)
-		return true;
-
-	/* Not-A-Trick#2 : Classic rule... */
-	if (!tcp_is_rack(sk) && tcp_dupack_heuristics(tp) > tp->reordering)
-		return true;
-
-	return false;
-}
-
-/* Detect loss in event "A" above by marking head of queue up as lost.
- * For RFC3517 SACK, a segment is considered lost if it
- * has at least tp->reordering SACKed seqments above it; "packets" refers to
- * the maximum SACKed segments to pass before reaching this limit.
- */
-static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb;
-	int cnt;
-	/* Use SACK to deduce losses of new sequences sent during recovery */
-	const u32 loss_high = tp->snd_nxt;
-
-	WARN_ON(packets > tp->packets_out);
-	skb = tp->lost_skb_hint;
-	if (skb) {
-		/* Head already handled? */
-		if (mark_head && after(TCP_SKB_CB(skb)->seq, tp->snd_una))
-			return;
-		cnt = tp->lost_cnt_hint;
-	} else {
-		skb = tcp_rtx_queue_head(sk);
-		cnt = 0;
-	}
-
-	skb_rbtree_walk_from(skb) {
-		/* TODO: do this better */
-		/* this is not the most efficient way to do this... */
-		tp->lost_skb_hint = skb;
-		tp->lost_cnt_hint = cnt;
-
-		if (after(TCP_SKB_CB(skb)->end_seq, loss_high))
-			break;
-
-		if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
-			cnt += tcp_skb_pcount(skb);
-
-		if (cnt > packets)
-			break;
-
-		if (!(TCP_SKB_CB(skb)->sacked & TCPCB_LOST))
-			tcp_mark_skb_lost(sk, skb);
-
-		if (mark_head)
-			break;
-	}
-	tcp_verify_left_out(tp);
-}
-
-/* Account newly detected lost packet(s) */
-
-static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit)
+static bool tcp_time_to_recover(const struct tcp_sock *tp)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (tcp_is_sack(tp)) {
-		int sacked_upto = tp->sacked_out - tp->reordering;
-		if (sacked_upto >= 0)
-			tcp_mark_head_lost(sk, sacked_upto, 0);
-		else if (fast_rexmit)
-			tcp_mark_head_lost(sk, 1, 1);
-	}
+	/* Has loss detection marked at least one packet lost? */
+	return tp->lost_out != 0;
 }
 
 static bool tcp_tsopt_ecr_before(const struct tcp_sock *tp, u32 when)
@@ -2894,8 +2780,6 @@ void tcp_simple_retransmit(struct sock *sk)
 			tcp_mark_skb_lost(sk, skb);
 	}
 
-	tcp_clear_retrans_hints_partial(tp);
-
 	if (!tp->lost_out)
 		return;
 
@@ -3003,17 +2887,8 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack,
 	*rexmit = REXMIT_LOST;
 }
 
-static bool tcp_force_fast_retransmit(struct sock *sk)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	return after(tcp_highest_sack_seq(tp),
-		     tp->snd_una + tp->reordering * tp->mss_cache);
-}
-
 /* Undo during fast recovery after partial ACK. */
-static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una,
-				 bool *do_lost)
+static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -3038,9 +2913,6 @@ static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una,
 		tcp_undo_cwnd_reduction(sk, true);
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO);
 		tcp_try_keep_open(sk);
-	} else {
-		/* Partial ACK arrived. Force fast retransmit. */
-		*do_lost = tcp_force_fast_retransmit(sk);
 	}
 	return false;
 }
@@ -3054,7 +2926,7 @@ static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag)
 
 	if (unlikely(tcp_is_reno(tp))) {
 		tcp_newreno_mark_lost(sk, *ack_flag & FLAG_SND_UNA_ADVANCED);
-	} else if (tcp_is_rack(sk)) {
+	} else {
 		u32 prior_retrans = tp->retrans_out;
 
 		if (tcp_rack_mark_lost(sk))
@@ -3081,10 +2953,8 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	int fast_rexmit = 0, flag = *ack_flag;
+	int flag = *ack_flag;
 	bool ece_ack = flag & FLAG_ECE;
-	bool do_lost = num_dupack || ((flag & FLAG_DATA_SACKED) &&
-				      tcp_force_fast_retransmit(sk));
 
 	if (!tp->packets_out && tp->sacked_out)
 		tp->sacked_out = 0;
@@ -3133,7 +3003,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 		if (!(flag & FLAG_SND_UNA_ADVANCED)) {
 			if (tcp_is_reno(tp))
 				tcp_add_reno_sack(sk, num_dupack, ece_ack);
-		} else if (tcp_try_undo_partial(sk, prior_snd_una, &do_lost))
+		} else if (tcp_try_undo_partial(sk, prior_snd_una))
 			return;
 
 		if (tcp_try_undo_dsack(sk))
@@ -3141,7 +3011,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 
 		tcp_identify_packet_loss(sk, ack_flag);
 		if (icsk->icsk_ca_state != TCP_CA_Recovery) {
-			if (!tcp_time_to_recover(sk, flag))
+			if (!tcp_time_to_recover(tp))
 				return;
 			/* Undo reverts the recovery state. If loss is evident,
 			 * starts a new recovery (e.g. reordering then loss);
@@ -3170,7 +3040,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 			tcp_try_undo_dsack(sk);
 
 		tcp_identify_packet_loss(sk, ack_flag);
-		if (!tcp_time_to_recover(sk, flag)) {
+		if (!tcp_time_to_recover(tp)) {
 			tcp_try_to_open(sk, flag);
 			return;
 		}
@@ -3188,11 +3058,8 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 
 		/* Otherwise enter Recovery state */
 		tcp_enter_recovery(sk, ece_ack);
-		fast_rexmit = 1;
 	}
 
-	if (!tcp_is_rack(sk) && do_lost)
-		tcp_update_scoreboard(sk, fast_rexmit);
 	*rexmit = REXMIT_LOST;
 }
 
@@ -3448,8 +3315,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb,
 		next = skb_rb_next(skb);
 		if (unlikely(skb == tp->retransmit_skb_hint))
 			tp->retransmit_skb_hint = NULL;
-		if (unlikely(skb == tp->lost_skb_hint))
-			tp->lost_skb_hint = NULL;
 		tcp_highest_sack_replace(sk, skb, next);
 		tcp_rtx_queue_unlink_and_free(skb, sk);
 	}
@@ -3507,14 +3372,9 @@ static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb,
 			if (flag & FLAG_RETRANS_DATA_ACKED)
 				flag &= ~FLAG_ORIG_SACK_ACKED;
 		} else {
-			int delta;
-
 			/* Non-retransmitted hole got filled? That's reordering */
 			if (before(reord, prior_fack))
 				tcp_check_sack_reordering(sk, reord, 0);
-
-			delta = prior_sacked - tp->sacked_out;
-			tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta);
 		}
 	} else if (skb && rtt_update && sack_rtt_us >= 0 &&
 		   sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp,
@@ -3854,7 +3714,7 @@ static int tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
 }
 
 /* This routine deals with acks during a TLP episode and ends an episode by
- * resetting tlp_high_seq. Ref: TLP algorithm in draft-ietf-tcpm-rack
+ * resetting tlp_high_seq. Ref: TLP algorithm in RFC8985
  */
 static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 {
@@ -4531,14 +4391,22 @@ static enum skb_drop_reason tcp_disordered_ack_check(const struct sock *sk,
  * (borrowed from freebsd)
  */
 
-static enum skb_drop_reason tcp_sequence(const struct tcp_sock *tp,
+static enum skb_drop_reason tcp_sequence(const struct sock *sk,
 					 u32 seq, u32 end_seq)
 {
+	const struct tcp_sock *tp = tcp_sk(sk);
+
 	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;
+	if (after(end_seq, tp->rcv_nxt + tcp_receive_window(tp))) {
+		if (after(seq, tp->rcv_nxt + tcp_receive_window(tp)))
+			return SKB_DROP_REASON_TCP_INVALID_SEQUENCE;
+
+		/* Only accept this packet if receive queue is empty. */
+		if (skb_queue_len(&sk->sk_receive_queue))
+			return SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE;
+	}
 
 	return SKB_NOT_DROPPED_YET;
 }
@@ -4985,8 +4853,9 @@ static void tcp_ofo_queue(struct sock *sk)
 
 		if (before(TCP_SKB_CB(skb)->seq, dsack_high)) {
 			__u32 dsack = dsack_high;
+
 			if (before(TCP_SKB_CB(skb)->end_seq, dsack_high))
-				dsack_high = TCP_SKB_CB(skb)->end_seq;
+				dsack = TCP_SKB_CB(skb)->end_seq;
 			tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack);
 		}
 		p = rb_next(p);
@@ -5019,10 +4888,20 @@ static void tcp_ofo_queue(struct sock *sk)
 static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb);
 static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb);
 
-static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb,
+/* Check if this incoming skb can be added to socket receive queues
+ * while satisfying sk->sk_rcvbuf limit.
+ */
+static bool tcp_can_ingest(const struct sock *sk, const struct sk_buff *skb)
+{
+	unsigned int new_mem = atomic_read(&sk->sk_rmem_alloc) + skb->truesize;
+
+	return new_mem <= sk->sk_rcvbuf;
+}
+
+static int tcp_try_rmem_schedule(struct sock *sk, const struct sk_buff *skb,
 				 unsigned int size)
 {
-	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
+	if (!tcp_can_ingest(sk, skb) ||
 	    !sk_rmem_schedule(sk, skb, size)) {
 
 		if (tcp_prune_queue(sk, skb) < 0)
@@ -5054,6 +4933,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 		return;
 	}
 
+	tcp_measure_rcv_mss(sk, skb);
 	/* Disable header prediction. */
 	tp->pred_flags = 0;
 	inet_csk_schedule_ack(sk);
@@ -5637,7 +5517,7 @@ static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb)
 		tcp_drop_reason(sk, skb, SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE);
 		tp->ooo_last_skb = rb_to_skb(prev);
 		if (!prev || goal <= 0) {
-			if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+			if (tcp_can_ingest(sk, in_skb) &&
 			    !tcp_under_memory_pressure(sk))
 				break;
 			goal = sk->sk_rcvbuf >> 3;
@@ -5669,14 +5549,18 @@ static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	/* Do nothing if our queues are empty. */
+	if (!atomic_read(&sk->sk_rmem_alloc))
+		return -1;
+
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_PRUNECALLED);
 
-	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
+	if (!tcp_can_ingest(sk, in_skb))
 		tcp_clamp_window(sk);
 	else if (tcp_under_memory_pressure(sk))
 		tcp_adjust_rcv_ssthresh(sk);
 
-	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+	if (tcp_can_ingest(sk, in_skb))
 		return 0;
 
 	tcp_collapse_ofo_queue(sk);
@@ -5686,7 +5570,7 @@ static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb)
 			     NULL,
 			     tp->copied_seq, tp->rcv_nxt);
 
-	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+	if (tcp_can_ingest(sk, in_skb))
 		return 0;
 
 	/* Collapsing did not help, destructive actions follow.
@@ -5694,7 +5578,7 @@ static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb)
 
 	tcp_prune_ofo_queue(sk, in_skb);
 
-	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+	if (tcp_can_ingest(sk, in_skb))
 		return 0;
 
 	/* If we are really being abused, tell the caller to silently
@@ -6020,7 +5904,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 
 step1:
 	/* Step 1: check sequence number */
-	reason = tcp_sequence(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
+	reason = tcp_sequence(sk, 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."
@@ -6031,6 +5915,11 @@ step1:
 		if (!th->rst) {
 			if (th->syn)
 				goto syn_challenge;
+
+			if (reason == SKB_DROP_REASON_TCP_INVALID_SEQUENCE ||
+			    reason == SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE)
+				NET_INC_STATS(sock_net(sk),
+					      LINUX_MIB_BEYOND_WINDOW);
 			if (!tcp_oow_rate_limited(sock_net(sk), skb,
 						  LINUX_MIB_TCPACKSKIPPEDSEQ,
 						  &tp->last_oow_ack_time))
@@ -6249,6 +6138,10 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 			if (tcp_checksum_complete(skb))
 				goto csum_error;
 
+			if (after(TCP_SKB_CB(skb)->end_seq,
+				  tp->rcv_nxt + tcp_receive_window(tp)))
+				goto validate;
+
 			if ((int)skb->truesize > sk->sk_forward_alloc)
 				goto step5;
 
@@ -6304,7 +6197,7 @@ slow_path:
 	/*
 	 *	Standard slow path.
 	 */
-
+validate:
 	if (!tcp_validate_incoming(sk, skb, th, 1))
 		return;