int sysctl_tcp_rfc1337 __read_mostly;
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
int sysctl_tcp_frto __read_mostly = 2;
+int sysctl_tcp_min_rtt_wlen __read_mostly = 300;
int sysctl_tcp_thin_dupack __read_mostly;
return !before(start_seq, end_seq - tp->max_window);
}
-/* Check for lost retransmit. This superb idea is borrowed from "ratehalving".
- * Event "B". Later note: FACK people cheated me again 8), we have to account
- * for reordering! Ugly, but should help.
- *
- * Search retransmitted skbs from write_queue that were sent when snd_nxt was
- * less than what is now known to be received by the other end (derived from
- * highest SACK block). Also calculate the lowest snd_nxt among the remaining
- * retransmitted skbs to avoid some costly processing per ACKs.
- */
-static void tcp_mark_lost_retrans(struct sock *sk, int *flag)
-{
- const struct inet_connection_sock *icsk = inet_csk(sk);
- struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb;
- int cnt = 0;
- u32 new_low_seq = tp->snd_nxt;
- u32 received_upto = tcp_highest_sack_seq(tp);
-
- if (!tcp_is_fack(tp) || !tp->retrans_out ||
- !after(received_upto, tp->lost_retrans_low) ||
- icsk->icsk_ca_state != TCP_CA_Recovery)
- return;
-
- tcp_for_write_queue(skb, sk) {
- u32 ack_seq = TCP_SKB_CB(skb)->ack_seq;
-
- if (skb == tcp_send_head(sk))
- break;
- if (cnt == tp->retrans_out)
- break;
- if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
- continue;
-
- if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS))
- continue;
-
- /* TODO: We would like to get rid of tcp_is_fack(tp) only
- * constraint here (see above) but figuring out that at
- * least tp->reordering SACK blocks reside between ack_seq
- * and received_upto is not easy task to do cheaply with
- * the available datastructures.
- *
- * Whether FACK should check here for tp->reordering segs
- * in-between one could argue for either way (it would be
- * rather simple to implement as we could count fack_count
- * during the walk and do tp->fackets_out - fack_count).
- */
- if (after(received_upto, ack_seq)) {
- TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
- tp->retrans_out -= tcp_skb_pcount(skb);
- *flag |= FLAG_LOST_RETRANS;
- tcp_skb_mark_lost_uncond_verify(tp, skb);
- NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT);
- } else {
- if (before(ack_seq, new_low_seq))
- new_low_seq = ack_seq;
- cnt += tcp_skb_pcount(skb);
- }
- }
-
- if (tp->retrans_out)
- tp->lost_retrans_low = new_low_seq;
-}
-
static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb,
struct tcp_sack_block_wire *sp, int num_sacks,
u32 prior_snd_una)
((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker))
tcp_update_reordering(sk, tp->fackets_out - state->reord, 0);
- tcp_mark_lost_retrans(sk, &state->flag);
tcp_verify_left_out(tp);
out:
tp->snd_cwnd_stamp = tcp_time_stamp;
}
+static bool tcp_tsopt_ecr_before(const struct tcp_sock *tp, u32 when)
+{
+ return tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
+ before(tp->rx_opt.rcv_tsecr, when);
+}
+
/* Nothing was retransmitted or returned timestamp is less
* than timestamp of the first retransmission.
*/
static inline bool tcp_packet_delayed(const struct tcp_sock *tp)
{
return !tp->retrans_stamp ||
- (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
- before(tp->rx_opt.rcv_tsecr, tp->retrans_stamp));
+ tcp_tsopt_ecr_before(tp, tp->retrans_stamp);
}
/* Undo procedures. */
tcp_xmit_retransmit_queue(sk);
}
+/* Kathleen Nichols' algorithm for tracking the minimum value of
+ * a data stream over some fixed time interval. (E.g., the minimum
+ * RTT over the past five minutes.) It uses constant space and constant
+ * time per update yet almost always delivers the same minimum as an
+ * implementation that has to keep all the data in the window.
+ *
+ * The algorithm keeps track of the best, 2nd best & 3rd best min
+ * values, maintaining an invariant that the measurement time of the
+ * n'th best >= n-1'th best. It also makes sure that the three values
+ * are widely separated in the time window since that bounds the worse
+ * case error when that data is monotonically increasing over the window.
+ *
+ * Upon getting a new min, we can forget everything earlier because it
+ * has no value - the new min is <= everything else in the window by
+ * definition and it's the most recent. So we restart fresh on every new min
+ * and overwrites 2nd & 3rd choices. The same property holds for 2nd & 3rd
+ * best.
+ */
+static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us)
+{
+ const u32 now = tcp_time_stamp, wlen = sysctl_tcp_min_rtt_wlen * HZ;
+ struct rtt_meas *m = tcp_sk(sk)->rtt_min;
+ struct rtt_meas rttm = { .rtt = (rtt_us ? : 1), .ts = now };
+ u32 elapsed;
+
+ /* Check if the new measurement updates the 1st, 2nd, or 3rd choices */
+ if (unlikely(rttm.rtt <= m[0].rtt))
+ m[0] = m[1] = m[2] = rttm;
+ else if (rttm.rtt <= m[1].rtt)
+ m[1] = m[2] = rttm;
+ else if (rttm.rtt <= m[2].rtt)
+ m[2] = rttm;
+
+ elapsed = now - m[0].ts;
+ if (unlikely(elapsed > wlen)) {
+ /* Passed entire window without a new min so make 2nd choice
+ * the new min & 3rd choice the new 2nd. So forth and so on.
+ */
+ m[0] = m[1];
+ m[1] = m[2];
+ m[2] = rttm;
+ if (now - m[0].ts > wlen) {
+ m[0] = m[1];
+ m[1] = rttm;
+ if (now - m[0].ts > wlen)
+ m[0] = rttm;
+ }
+ } else if (m[1].ts == m[0].ts && elapsed > wlen / 4) {
+ /* Passed a quarter of the window without a new min so
+ * take 2nd choice from the 2nd quarter of the window.
+ */
+ m[2] = m[1] = rttm;
+ } else if (m[2].ts == m[1].ts && elapsed > wlen / 2) {
+ /* Passed half the window without a new min so take the 3rd
+ * choice from the last half of the window.
+ */
+ m[2] = rttm;
+ }
+}
+
static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
- long seq_rtt_us, long sack_rtt_us)
+ long seq_rtt_us, long sack_rtt_us,
+ long ca_rtt_us)
{
const struct tcp_sock *tp = tcp_sk(sk);
* Karn's algorithm forbids taking RTT if some retransmitted data
* is acked (RFC6298).
*/
- if (flag & FLAG_RETRANS_DATA_ACKED)
- seq_rtt_us = -1L;
-
if (seq_rtt_us < 0)
seq_rtt_us = sack_rtt_us;
*/
if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
flag & FLAG_ACKED)
- seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - tp->rx_opt.rcv_tsecr);
-
+ seq_rtt_us = ca_rtt_us = jiffies_to_usecs(tcp_time_stamp -
+ tp->rx_opt.rcv_tsecr);
if (seq_rtt_us < 0)
return false;
+ /* ca_rtt_us >= 0 is counting on the invariant that ca_rtt_us is
+ * always taken together with ACK, SACK, or TS-opts. Any negative
+ * values will be skipped with the seq_rtt_us < 0 check above.
+ */
+ tcp_update_rtt_min(sk, ca_rtt_us);
tcp_rtt_estimator(sk, seq_rtt_us);
tcp_set_rto(sk);
rtt_us = skb_mstamp_us_delta(&now, &tcp_rsk(req)->snt_synack);
}
- tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L);
+ tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L, rtt_us);
}
flag |= FLAG_SACK_RENEGING;
skb_mstamp_get(&now);
- if (likely(first_ackt.v64)) {
+ if (likely(first_ackt.v64) && !(flag & FLAG_RETRANS_DATA_ACKED)) {
seq_rtt_us = skb_mstamp_us_delta(&now, &first_ackt);
ca_rtt_us = skb_mstamp_us_delta(&now, &last_ackt);
}
ca_rtt_us = skb_mstamp_us_delta(&now, &sack->last_sackt);
}
- rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us);
+ rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us,
+ ca_rtt_us);
if (flag & FLAG_ACKED) {
tcp_rearm_rto(sk);
{
struct inet_request_sock *ireq = inet_rsk(req);
- req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */
+ req->rsk_rcv_wnd = 0; /* So that tcp_send_synack() knows! */
req->cookie_ts = 0;
tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq;
tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
}
if (fastopen_sk) {
af_ops->send_synack(fastopen_sk, dst, &fl, req,
- skb_get_queue_mapping(skb), &foc, false);
+ &foc, false);
/* Add the child socket directly into the accept queue */
inet_csk_reqsk_queue_add(sk, req, fastopen_sk);
sk->sk_data_ready(sk);
if (!want_cookie)
inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
af_ops->send_synack(sk, dst, &fl, req,
- skb_get_queue_mapping(skb), &foc, !want_cookie);
+ &foc, !want_cookie);
if (want_cookie)
goto drop_and_free;
}