Merge branch 'tcp-remove-obsolete-rfc3517-rfc6675-code'

Neal Cardwell says:

====================
tcp: remove obsolete RFC3517/RFC6675 code

RACK-TLP loss detection has been enabled as the default loss detection
algorithm for Linux TCP since 2018, in:

 commit b38a51fec1c1 ("tcp: disable RFC6675 loss detection")

In case users ran into unexpected bugs or performance regressions,
that commit allowed Linux system administrators to revert to using
RFC3517/RFC6675 loss recovery by setting net.ipv4.tcp_recovery to 0.

In the seven years since 2018, our team has not heard reports of
anyone reverting Linux TCP to use RFC3517/RFC6675 loss recovery, and
we can't find any record in web searches of such a revert.

RACK-TLP was published as a standards-track RFC, RFC8985, in February
2021.

Several other major TCP implementations have default-enabled RACK-TLP
at this point as well.

RACK-TLP offers several significant performance advantages over
RFC3517/RFC6675 loss recovery, including much better performance in
the common cases of tail drops, lost retransmissions, and reordering.

It is now time to remove the obsolete and unused RFC3517/RFC6675 loss
recovery code. This will allow a substantial simplification of the
Linux TCP code base, and removes 12 bytes of state in every tcp_sock
for 64-bit machines (8 bytes on 32-bit machines).

To arrange the commits in reasonable sizes, this patch series is split
into 3 commits:

(1) Removes the core RFC3517/RFC6675 logic.

(2) Removes the RFC3517/RFC6675 hint state and the first layer of logic that
    updates that state.

(3) Removes the emptied-out tcp_clear_retrans_hints_partial() helper function
    and all of its call sites.
====================

Link: https://patch.msgid.link/20250615001435.2390793-1-ncardwell.sw@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

7 files changed, 16 insertions, 170 deletions

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 0f1251cce314..466bc3f5186e 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -645,9 +645,11 @@ tcp_recovery - INTEGER
 	features.
 
 	=========   =============================================================
-	RACK: 0x1   enables the RACK loss detection for fast detection of lost
-		    retransmissions and tail drops. It also subsumes and disables
-		    RFC6675 recovery for SACK connections.
+	RACK: 0x1   enables RACK loss detection, for fast detection of lost
+		    retransmissions and tail drops, and resilience to
+		    reordering. currently, setting this bit to 0 has no
+		    effect, since RACK is the only supported loss detection
+		    algorithm.
 
 	RACK: 0x2   makes RACK's reordering window static (min_rtt/4).
 
diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst
index bc9b2131bf7a..7bbda5944ee2 100644
--- a/Documentation/networking/net_cachelines/tcp_sock.rst
+++ b/Documentation/networking/net_cachelines/tcp_sock.rst
@@ -115,7 +115,6 @@ u32                           lost_out                read_mostly         read_m
 u32                           sacked_out              read_mostly         read_mostly         tcp_left_out(tx);tcp_packets_in_flight(tx/rx);tcp_clean_rtx_queue(rx)
 struct hrtimer                pacing_timer
 struct hrtimer                compressed_ack_timer
-struct sk_buff*               lost_skb_hint           read_mostly                             tcp_clean_rtx_queue
 struct sk_buff*               retransmit_skb_hint     read_mostly                             tcp_clean_rtx_queue
 struct rb_root                out_of_order_queue                          read_mostly         tcp_data_queue,tcp_fast_path_check
 struct sk_buff*               ooo_last_skb
@@ -123,7 +122,6 @@ struct tcp_sack_block[1]      duplicate_sack
 struct tcp_sack_block[4]      selective_acks
 struct tcp_sack_block[4]      recv_sack_cache
 struct sk_buff*               highest_sack            read_write                              tcp_event_new_data_sent
-int                           lost_cnt_hint
 u32                           prior_ssthresh
 u32                           high_seq
 u32                           retrans_stamp
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 29f59d50dc73..1a5737b3753d 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -208,7 +208,6 @@ struct tcp_sock {
 	u32	notsent_lowat;	/* TCP_NOTSENT_LOWAT */
 	u16	gso_segs;	/* Max number of segs per GSO packet	*/
 	/* from STCP, retrans queue hinting */
-	struct sk_buff *lost_skb_hint;
 	struct sk_buff *retransmit_skb_hint;
 	__cacheline_group_end(tcp_sock_read_tx);
 
@@ -419,8 +418,6 @@ struct tcp_sock {
 
 	struct tcp_sack_block recv_sack_cache[4];
 
-	int     lost_cnt_hint;
-
 	u32	prior_ssthresh; /* ssthresh saved at recovery start	*/
 	u32	high_seq;	/* snd_nxt at onset of congestion	*/
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5078ad868fee..9f852f5f8b95 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1811,14 +1811,8 @@ static inline void tcp_mib_init(struct net *net)
 }
 
 /* from STCP */
-static inline void tcp_clear_retrans_hints_partial(struct tcp_sock *tp)
-{
-	tp->lost_skb_hint = NULL;
-}
-
 static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp)
 {
-	tcp_clear_retrans_hints_partial(tp);
 	tp->retransmit_skb_hint = NULL;
 }
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f64f8276a73c..27d3ef83ce7b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -5053,9 +5053,8 @@ static void __init tcp_struct_check(void)
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, reordering);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, notsent_lowat);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, gso_segs);
-	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, lost_skb_hint);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, retransmit_skb_hint);
-	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_tx, 40);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_tx, 32);
 
 	/* TXRX read-mostly hotpath cache lines */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, tsoffset);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8ec92dec321a..05b9571c9c92 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.
@@ -2381,79 +2340,8 @@ 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)
-{
-	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)
@@ -2881,8 +2769,6 @@ void tcp_simple_retransmit(struct sock *sk)
 			tcp_mark_skb_lost(sk, skb);
 	}
 
-	tcp_clear_retrans_hints_partial(tp);
-
 	if (!tp->lost_out)
 		return;
 
@@ -2990,17 +2876,8 @@ 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);
 
@@ -3025,9 +2902,6 @@ 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;
 }
@@ -3041,7 +2915,7 @@ 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))
@@ -3068,10 +2942,8 @@ 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;
@@ -3120,7 +2992,7 @@ 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))
@@ -3175,11 +3047,8 @@ 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;
 }
 
@@ -3435,8 +3304,6 @@ 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);
 	}
@@ -3494,14 +3361,9 @@ 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,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 3ac8d2d17e1f..eb50746dc482 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1554,11 +1554,6 @@ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int de
 	if (tcp_is_reno(tp) && decr > 0)
 		tp->sacked_out -= min_t(u32, tp->sacked_out, decr);
 
-	if (tp->lost_skb_hint &&
-	    before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) &&
-	    (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
-		tp->lost_cnt_hint -= decr;
-
 	tcp_verify_left_out(tp);
 }
 
@@ -3252,7 +3247,6 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 	TCP_SKB_CB(skb)->eor = TCP_SKB_CB(next_skb)->eor;
 
 	/* changed transmit queue under us so clear hints */
-	tcp_clear_retrans_hints_partial(tp);
 	if (next_skb == tp->retransmit_skb_hint)
 		tp->retransmit_skb_hint = skb;