1// SPDX-License-Identifier: GPL-2.0
2#include <linux/tcp.h>
3#include <net/tcp.h>
4
5static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2)
6{
7	return t1 > t2 || (t1 == t2 && after(seq1, seq2));
8}
9
10static u32 tcp_rack_reo_wnd(const struct sock *sk)
11{
12	struct tcp_sock *tp = tcp_sk(sk);
13
14	if (!tp->reord_seen) {
15		/* If reordering has not been observed, be aggressive during
16		 * the recovery or starting the recovery by DUPACK threshold.
17		 */
18		if (inet_csk(sk)->icsk_ca_state >= TCP_CA_Recovery)
19			return 0;
20
21		if (tp->sacked_out >= tp->reordering &&
22		    !(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) &
23		      TCP_RACK_NO_DUPTHRESH))
24			return 0;
25	}
26
27	/* To be more reordering resilient, allow min_rtt/4 settling delay.
28	 * Use min_rtt instead of the smoothed RTT because reordering is
29	 * often a path property and less related to queuing or delayed ACKs.
30	 * Upon receiving DSACKs, linearly increase the window up to the
31	 * smoothed RTT.
32	 */
33	return min((tcp_min_rtt(tp) >> 2) * tp->rack.reo_wnd_steps,
34		   tp->srtt_us >> 3);
35}
36
37s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb, u32 reo_wnd)
38{
39	return tp->rack.rtt_us + reo_wnd -
40	       tcp_stamp_us_delta(tp->tcp_mstamp, tcp_skb_timestamp_us(skb));
41}
42
43/* RACK loss detection (IETF draft draft-ietf-tcpm-rack-01):
44 *
45 * Marks a packet lost, if some packet sent later has been (s)acked.
46 * The underlying idea is similar to the traditional dupthresh and FACK
47 * but they look at different metrics:
48 *
49 * dupthresh: 3 OOO packets delivered (packet count)
50 * FACK: sequence delta to highest sacked sequence (sequence space)
51 * RACK: sent time delta to the latest delivered packet (time domain)
52 *
53 * The advantage of RACK is it applies to both original and retransmitted
54 * packet and therefore is robust against tail losses. Another advantage
55 * is being more resilient to reordering by simply allowing some
56 * "settling delay", instead of tweaking the dupthresh.
57 *
58 * When tcp_rack_detect_loss() detects some packets are lost and we
59 * are not already in the CA_Recovery state, either tcp_rack_reo_timeout()
60 * or tcp_time_to_recover()'s "Trick#1: the loss is proven" code path will
61 * make us enter the CA_Recovery state.
62 */
63static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
64{
65	struct tcp_sock *tp = tcp_sk(sk);
66	struct sk_buff *skb, *n;
67	u32 reo_wnd;
68
69	*reo_timeout = 0;
70	reo_wnd = tcp_rack_reo_wnd(sk);
71	list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue,
72				 tcp_tsorted_anchor) {
73		struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
74		s32 remaining;
75
76		/* Skip ones marked lost but not yet retransmitted */
77		if ((scb->sacked & TCPCB_LOST) &&
78		    !(scb->sacked & TCPCB_SACKED_RETRANS))
79			continue;
80
81		if (!tcp_rack_sent_after(tp->rack.mstamp,
82					 tcp_skb_timestamp_us(skb),
83					 tp->rack.end_seq, scb->end_seq))
84			break;
85
86		/* A packet is lost if it has not been s/acked beyond
87		 * the recent RTT plus the reordering window.
88		 */
89		remaining = tcp_rack_skb_timeout(tp, skb, reo_wnd);
90		if (remaining <= 0) {
91			tcp_mark_skb_lost(sk, skb);
92			list_del_init(&skb->tcp_tsorted_anchor);
93		} else {
94			/* Record maximum wait time */
95			*reo_timeout = max_t(u32, *reo_timeout, remaining);
96		}
97	}
98}
99
100bool tcp_rack_mark_lost(struct sock *sk)
101{
102	struct tcp_sock *tp = tcp_sk(sk);
103	u32 timeout;
104
105	if (!tp->rack.advanced)
106		return false;
107
108	/* Reset the advanced flag to avoid unnecessary queue scanning */
109	tp->rack.advanced = 0;
110	tcp_rack_detect_loss(sk, &timeout);
111	if (timeout) {
112		timeout = usecs_to_jiffies(timeout + TCP_TIMEOUT_MIN_US);
113		inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT,
114					  timeout, inet_csk(sk)->icsk_rto);
115	}
116	return !!timeout;
117}
118
119/* Record the most recently (re)sent time among the (s)acked packets
120 * This is "Step 3: Advance RACK.xmit_time and update RACK.RTT" from
121 * draft-cheng-tcpm-rack-00.txt
122 */
123void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq,
124		      u64 xmit_time)
125{
126	u32 rtt_us;
127
128	rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, xmit_time);
129	if (rtt_us < tcp_min_rtt(tp) && (sacked & TCPCB_RETRANS)) {
130		/* If the sacked packet was retransmitted, it's ambiguous
131		 * whether the retransmission or the original (or the prior
132		 * retransmission) was sacked.
133		 *
134		 * If the original is lost, there is no ambiguity. Otherwise
135		 * we assume the original can be delayed up to aRTT + min_rtt.
136		 * the aRTT term is bounded by the fast recovery or timeout,
137		 * so it's at least one RTT (i.e., retransmission is at least
138		 * an RTT later).
139		 */
140		return;
141	}
142	tp->rack.advanced = 1;
143	tp->rack.rtt_us = rtt_us;
144	if (tcp_rack_sent_after(xmit_time, tp->rack.mstamp,
145				end_seq, tp->rack.end_seq)) {
146		tp->rack.mstamp = xmit_time;
147		tp->rack.end_seq = end_seq;
148	}
149}
150
151/* We have waited long enough to accommodate reordering. Mark the expired
152 * packets lost and retransmit them.
153 */
154void tcp_rack_reo_timeout(struct sock *sk)
155{
156	struct tcp_sock *tp = tcp_sk(sk);
157	u32 timeout, prior_inflight;
158
159	prior_inflight = tcp_packets_in_flight(tp);
160	tcp_rack_detect_loss(sk, &timeout);
161	if (prior_inflight != tcp_packets_in_flight(tp)) {
162		if (inet_csk(sk)->icsk_ca_state != TCP_CA_Recovery) {
163			tcp_enter_recovery(sk, false);
164			if (!inet_csk(sk)->icsk_ca_ops->cong_control)
165				tcp_cwnd_reduction(sk, 1, 0);
166		}
167		tcp_xmit_retransmit_queue(sk);
168	}
169	if (inet_csk(sk)->icsk_pending != ICSK_TIME_RETRANS)
170		tcp_rearm_rto(sk);
171}
172
173/* Updates the RACK's reo_wnd based on DSACK and no. of recoveries.
174 *
175 * If DSACK is received, increment reo_wnd by min_rtt/4 (upper bounded
176 * by srtt), since there is possibility that spurious retransmission was
177 * due to reordering delay longer than reo_wnd.
178 *
179 * Persist the current reo_wnd value for TCP_RACK_RECOVERY_THRESH (16)
180 * no. of successful recoveries (accounts for full DSACK-based loss
181 * recovery undo). After that, reset it to default (min_rtt/4).
182 *
183 * At max, reo_wnd is incremented only once per rtt. So that the new
184 * DSACK on which we are reacting, is due to the spurious retx (approx)
185 * after the reo_wnd has been updated last time.
186 *
187 * reo_wnd is tracked in terms of steps (of min_rtt/4), rather than
188 * absolute value to account for change in rtt.
189 */
190void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs)
191{
192	struct tcp_sock *tp = tcp_sk(sk);
193
194	if ((READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) &
195	     TCP_RACK_STATIC_REO_WND) ||
196	    !rs->prior_delivered)
197		return;
198
199	/* Disregard DSACK if a rtt has not passed since we adjusted reo_wnd */
200	if (before(rs->prior_delivered, tp->rack.last_delivered))
201		tp->rack.dsack_seen = 0;
202
203	/* Adjust the reo_wnd if update is pending */
204	if (tp->rack.dsack_seen) {
205		tp->rack.reo_wnd_steps = min_t(u32, 0xFF,
206					       tp->rack.reo_wnd_steps + 1);
207		tp->rack.dsack_seen = 0;
208		tp->rack.last_delivered = tp->delivered;
209		tp->rack.reo_wnd_persist = TCP_RACK_RECOVERY_THRESH;
210	} else if (!tp->rack.reo_wnd_persist) {
211		tp->rack.reo_wnd_steps = 1;
212	}
213}
214
215/* RFC6582 NewReno recovery for non-SACK connection. It simply retransmits
216 * the next unacked packet upon receiving
217 * a) three or more DUPACKs to start the fast recovery
218 * b) an ACK acknowledging new data during the fast recovery.
219 */
220void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced)
221{
222	const u8 state = inet_csk(sk)->icsk_ca_state;
223	struct tcp_sock *tp = tcp_sk(sk);
224
225	if ((state < TCP_CA_Recovery && tp->sacked_out >= tp->reordering) ||
226	    (state == TCP_CA_Recovery && snd_una_advanced)) {
227		struct sk_buff *skb = tcp_rtx_queue_head(sk);
228		u32 mss;
229
230		if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST)
231			return;
232
233		mss = tcp_skb_mss(skb);
234		if (tcp_skb_pcount(skb) > 1 && skb->len > mss)
235			tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
236				     mss, mss, GFP_ATOMIC);
237
238		tcp_mark_skb_lost(sk, skb);
239	}
240}
241