1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
|
// SPDX-License-Identifier: GPL-2.0
#include <linux/tcp.h>
#include <net/tcp.h>
static u32 tcp_rack_reo_wnd(const struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
if (!tp->reord_seen) {
/* If reordering has not been observed, be aggressive during
* the recovery or starting the recovery by DUPACK threshold.
*/
if (inet_csk(sk)->icsk_ca_state >= TCP_CA_Recovery)
return 0;
if (tp->sacked_out >= tp->reordering &&
!(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) &
TCP_RACK_NO_DUPTHRESH))
return 0;
}
/* To be more reordering resilient, allow min_rtt/4 settling delay.
* Use min_rtt instead of the smoothed RTT because reordering is
* often a path property and less related to queuing or delayed ACKs.
* Upon receiving DSACKs, linearly increase the window up to the
* smoothed RTT.
*/
return min((tcp_min_rtt(tp) >> 2) * tp->rack.reo_wnd_steps,
tp->srtt_us >> 3);
}
s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb, u32 reo_wnd)
{
return tp->rack.rtt_us + reo_wnd -
tcp_stamp_us_delta(tp->tcp_mstamp, tcp_skb_timestamp_us(skb));
}
/* RACK loss detection (IETF RFC8985):
*
* Marks a packet lost, if some packet sent later has been (s)acked.
* The underlying idea is similar to the traditional dupthresh and FACK
* but they look at different metrics:
*
* dupthresh: 3 OOO packets delivered (packet count)
* FACK: sequence delta to highest sacked sequence (sequence space)
* RACK: sent time delta to the latest delivered packet (time domain)
*
* The advantage of RACK is it applies to both original and retransmitted
* packet and therefore is robust against tail losses. Another advantage
* is being more resilient to reordering by simply allowing some
* "settling delay", instead of tweaking the dupthresh.
*
* When tcp_rack_detect_loss() detects some packets are lost and we
* are not already in the CA_Recovery state, either tcp_rack_reo_timeout()
* or tcp_time_to_recover()'s "Trick#1: the loss is proven" code path will
* make us enter the CA_Recovery state.
*/
static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb, *n;
u32 reo_wnd;
*reo_timeout = 0;
reo_wnd = tcp_rack_reo_wnd(sk);
list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue,
tcp_tsorted_anchor) {
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
s32 remaining;
/* Skip ones marked lost but not yet retransmitted */
if ((scb->sacked & TCPCB_LOST) &&
!(scb->sacked & TCPCB_SACKED_RETRANS))
continue;
if (!tcp_skb_sent_after(tp->rack.mstamp,
tcp_skb_timestamp_us(skb),
tp->rack.end_seq, scb->end_seq))
break;
/* A packet is lost if it has not been s/acked beyond
* the recent RTT plus the reordering window.
*/
remaining = tcp_rack_skb_timeout(tp, skb, reo_wnd);
if (remaining <= 0) {
tcp_mark_skb_lost(sk, skb);
list_del_init(&skb->tcp_tsorted_anchor);
} else {
/* Record maximum wait time */
*reo_timeout = max_t(u32, *reo_timeout, remaining);
}
}
}
bool tcp_rack_mark_lost(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 timeout;
if (!tp->rack.advanced)
return false;
/* Reset the advanced flag to avoid unnecessary queue scanning */
tp->rack.advanced = 0;
tcp_rack_detect_loss(sk, &timeout);
if (timeout) {
timeout = usecs_to_jiffies(timeout + TCP_TIMEOUT_MIN_US);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT,
timeout, inet_csk(sk)->icsk_rto);
}
return !!timeout;
}
/* We have waited long enough to accommodate reordering. Mark the expired
* packets lost and retransmit them.
*/
void tcp_rack_reo_timeout(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 timeout, prior_inflight;
u32 lost = tp->lost;
prior_inflight = tcp_packets_in_flight(tp);
tcp_rack_detect_loss(sk, &timeout);
if (prior_inflight != tcp_packets_in_flight(tp)) {
if (inet_csk(sk)->icsk_ca_state != TCP_CA_Recovery) {
tcp_enter_recovery(sk, false);
if (!inet_csk(sk)->icsk_ca_ops->cong_control)
tcp_cwnd_reduction(sk, 1, tp->lost - lost, 0);
}
tcp_xmit_retransmit_queue(sk);
}
if (inet_csk(sk)->icsk_pending != ICSK_TIME_RETRANS)
tcp_rearm_rto(sk);
}
/* RFC6582 NewReno recovery for non-SACK connection. It simply retransmits
* the next unacked packet upon receiving
* a) three or more DUPACKs to start the fast recovery
* b) an ACK acknowledging new data during the fast recovery.
*/
void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced)
{
const u8 state = inet_csk(sk)->icsk_ca_state;
struct tcp_sock *tp = tcp_sk(sk);
if ((state < TCP_CA_Recovery && tp->sacked_out >= tp->reordering) ||
(state == TCP_CA_Recovery && snd_una_advanced)) {
struct sk_buff *skb = tcp_rtx_queue_head(sk);
u32 mss;
if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST)
return;
mss = tcp_skb_mss(skb);
if (tcp_skb_pcount(skb) > 1 && skb->len > mss)
tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
mss, mss, GFP_ATOMIC);
tcp_mark_skb_lost(sk, skb);
}
}
|