/*
* Hook inserted to be called before each receive packet.
* Note: arguments must match tcp_rcv_established()!
*/
static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
struct tcphdr *th, unsigned len)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct inet_sock *inet = inet_sk(sk);
/* Only update if port matches */
if ((port == 0 || ntohs(inet->dport) == port || ntohs(inet->sport) == port)
&& (full || tp->snd_cwnd != tcp_probe.lastcwnd)) {
spin_lock(&tcp_probe.lock);
/* If log fills, just silently drop */
if (tcp_probe_avail() > 1) {
struct tcp_log *p = tcp_probe.log + tcp_probe.head;
p->tstamp = ktime_get();
p->saddr = inet->saddr;
p->sport = inet->sport;
p->daddr = inet->daddr;
p->dport = inet->dport;
p->length = skb->len;
p->snd_nxt = tp->snd_nxt;
p->snd_una = tp->snd_una;
p->snd_cwnd = tp->snd_cwnd;
p->snd_wnd = tp->snd_wnd;
p->ssthresh = tcp_current_ssthresh(sk);
p->srtt = tp->srtt >> 3;
tcp_probe.head = (tcp_probe.head + 1) % bufsize;
}
tcp_probe.lastcwnd = tp->snd_cwnd;
spin_unlock(&tcp_probe.lock);
wake_up(&tcp_probe.wait);
}
/*
* Hook inserted to be called before each receive packet.
* Note: arguments must match tcp_rcv_established()!
*/
static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
const struct tcphdr *th, unsigned int len)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct inet_sock *inet = inet_sk(sk);
/* Only update if port or skb mark matches */
if (((port == 0 && fwmark == 0) ||
ntohs(inet->inet_dport) == port ||
ntohs(inet->inet_sport) == port ||
(fwmark > 0 && skb->mark == fwmark)) &&
(full || tp->snd_cwnd != tcp_probe.lastcwnd)) {
spin_lock(&tcp_probe.lock);
/* If log fills, just silently drop */
if (tcp_probe_avail() > 1) {
struct tcp_log *p = tcp_probe.log + tcp_probe.head;
p->tstamp = ktime_get();
switch (sk->sk_family) {
case AF_INET:
tcp_probe_copy_fl_to_si4(inet, p->src.v4, s);
tcp_probe_copy_fl_to_si4(inet, p->dst.v4, d);
break;
case AF_INET6:
memset(&p->src.v6, 0, sizeof(p->src.v6));
memset(&p->dst.v6, 0, sizeof(p->dst.v6));
#if IS_ENABLED(CONFIG_IPV6)
p->src.v6.sin6_family = AF_INET6;
p->src.v6.sin6_port = inet->inet_sport;
p->src.v6.sin6_addr = inet6_sk(sk)->saddr;
p->dst.v6.sin6_family = AF_INET6;
p->dst.v6.sin6_port = inet->inet_dport;
p->dst.v6.sin6_addr = sk->sk_v6_daddr;
#endif
break;
default:
BUG();
}
p->length = skb->len;
p->snd_nxt = tp->snd_nxt;
p->snd_una = tp->snd_una;
p->snd_cwnd = tp->snd_cwnd;
p->snd_wnd = tp->snd_wnd;
p->rcv_wnd = tp->rcv_wnd;
p->ssthresh = tcp_current_ssthresh(sk);
p->srtt = tp->srtt_us >> 3;
tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1);
}
tcp_probe.lastcwnd = tp->snd_cwnd;
spin_unlock(&tcp_probe.lock);
wake_up(&tcp_probe.wait);
}
/*
* Hook inserted to be called before each receive packet.
* Note: arguments must match tcp_rcv_established()!
*/
static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
struct tcphdr *th, unsigned len)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct inet_sock *inet = inet_sk(sk);
/* Only update if port matches */
if ((port == 0 || ntohs(inet->dport) == port || ntohs(inet->sport) == port)
&& (full || tp->snd_cwnd != tcpw.lastcwnd)) {
printl("%d.%d.%d.%d:%u %d.%d.%d.%d:%u %d %#x %#x %u %u %u %u\n",
NIPQUAD(inet->saddr), ntohs(inet->sport),
NIPQUAD(inet->daddr), ntohs(inet->dport),
skb->len, tp->snd_nxt, tp->snd_una,
tp->snd_cwnd, tcp_current_ssthresh(sk),
tp->snd_wnd, tp->srtt >> 3);
tcpw.lastcwnd = tp->snd_cwnd;
}
static int jtcp_sendmsg(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg, size_t size)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct inet_sock *inet = inet_sk(sk);
if (port == 0 || ntohs(inet->dport) == port ||
ntohs(inet->sport) == port) {
printl("%d.%d.%d.%d:%u %d.%d.%d.%d:%u %d %#x %#x %u %u %u\n",
NIPQUAD(inet->saddr), ntohs(inet->sport),
NIPQUAD(inet->daddr), ntohs(inet->dport),
size, tp->snd_nxt, tp->snd_una,
tp->snd_cwnd, tcp_current_ssthresh(sk),
tp->snd_wnd);
}
jprobe_return();
return 0;
}
static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked)
{
struct tcp_sock *tp = tcp_sk(sk);
struct vegas *vegas = inet_csk_ca(sk);
if (!vegas->doing_vegas_now) {
tcp_reno_cong_avoid(sk, ack, acked);
return;
}
if (after(ack, vegas->beg_snd_nxt)) {
/* Do the Vegas once-per-RTT cwnd adjustment. */
/* Save the extent of the current window so we can use this
* at the end of the next RTT.
*/
vegas->beg_snd_nxt = tp->snd_nxt;
/* We do the Vegas calculations only if we got enough RTT
* samples that we can be reasonably sure that we got
* at least one RTT sample that wasn't from a delayed ACK.
* If we only had 2 samples total,
* then that means we're getting only 1 ACK per RTT, which
* means they're almost certainly delayed ACKs.
* If we have 3 samples, we should be OK.
*/
if (vegas->cntRTT <= 2) {
/* We don't have enough RTT samples to do the Vegas
* calculation, so we'll behave like Reno.
*/
tcp_reno_cong_avoid(sk, ack, acked);
} else {
u32 rtt, diff;
u64 target_cwnd;
/* We have enough RTT samples, so, using the Vegas
* algorithm, we determine if we should increase or
* decrease cwnd, and by how much.
*/
/* Pluck out the RTT we are using for the Vegas
* calculations. This is the min RTT seen during the
* last RTT. Taking the min filters out the effects
* of delayed ACKs, at the cost of noticing congestion
* a bit later.
*/
rtt = vegas->minRTT;
/* Calculate the cwnd we should have, if we weren't
* going too fast.
*
* This is:
* (actual rate in segments) * baseRTT
*/
target_cwnd = (u64)tp->snd_cwnd * vegas->baseRTT;
do_div(target_cwnd, rtt);
/* Calculate the difference between the window we had,
* and the window we would like to have. This quantity
* is the "Diff" from the Arizona Vegas papers.
*/
diff = tp->snd_cwnd * (rtt-vegas->baseRTT) / vegas->baseRTT;
if (diff > gamma && tcp_in_slow_start(tp)) {
/* Going too fast. Time to slow down
* and switch to congestion avoidance.
*/
/* Set cwnd to match the actual rate
* exactly:
* cwnd = (actual rate) * baseRTT
* Then we add 1 because the integer
* truncation robs us of full link
* utilization.
*/
tp->snd_cwnd = min(tp->snd_cwnd, (u32)target_cwnd+1);
tp->snd_ssthresh = tcp_vegas_ssthresh(tp);
} else if (tcp_in_slow_start(tp)) {
/* Slow start. */
tcp_slow_start(tp, acked);
} else {
/* Congestion avoidance. */
/* Figure out where we would like cwnd
* to be.
*/
if (diff > beta) {
/* The old window was too fast, so
* we slow down.
*/
tp->snd_cwnd--;
tp->snd_ssthresh
= tcp_vegas_ssthresh(tp);
} else if (diff < alpha) {
/* We don't have enough extra packets
* in the network, so speed up.
*/
tp->snd_cwnd++;
} else {
/* Sending just as fast as we
* should be.
*/
}
}
if (tp->snd_cwnd < 2)
tp->snd_cwnd = 2;
else if (tp->snd_cwnd > tp->snd_cwnd_clamp)
tp->snd_cwnd = tp->snd_cwnd_clamp;
tp->snd_ssthresh = tcp_current_ssthresh(sk);
}
/* Wipe the slate clean for the next RTT. */
vegas->cntRTT = 0;
vegas->minRTT = 0x7fffffff;
}
/* Use normal slow start */
else if (tcp_in_slow_start(tp))
tcp_slow_start(tp, acked);
}
