int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
int sysctl_tcp_early_retrans __read_mostly = 3;
+int sysctl_tcp_default_init_rwnd __read_mostly = TCP_DEFAULT_INIT_RCVWND;
#define FLAG_DATA 0x01 /* Incoming frame contained data. */
#define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */
static void tcp_fixup_rcvbuf(struct sock *sk)
{
u32 mss = tcp_sk(sk)->advmss;
- u32 icwnd = TCP_DEFAULT_INIT_RCVWND;
+ u32 icwnd = sysctl_tcp_default_init_rwnd;
int rcvmem;
/* Limit to 10 segments if mss <= 1460,
* or 14600/mss segments, with a minimum of two segments.
*/
if (mss > 1460)
- icwnd = max_t(u32, (1460 * TCP_DEFAULT_INIT_RCVWND) / mss, 2);
+ icwnd = max_t(u32, (1460 * icwnd) / mss, 2);
rcvmem = SKB_TRUESIZE(mss + MAX_TCP_HEADER);
while (tcp_win_from_space(rcvmem) < mss)
}
}
+/* Set the sk_pacing_rate to allow proper sizing of TSO packets.
+ * Note: TCP stack does not yet implement pacing.
+ * FQ packet scheduler can be used to implement cheap but effective
+ * TCP pacing, to smooth the burst on large writes when packets
+ * in flight is significantly lower than cwnd (or rwin)
+ */
+static void tcp_update_pacing_rate(struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ u64 rate;
+
+ /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */
+ rate = (u64)tp->mss_cache * 2 * (HZ << 3);
+
+ rate *= max(tp->snd_cwnd, tp->packets_out);
+
+ /* Correction for small srtt : minimum srtt being 8 (1 jiffy << 3),
+ * be conservative and assume srtt = 1 (125 us instead of 1.25 ms)
+ * We probably need usec resolution in the future.
+ * Note: This also takes care of possible srtt=0 case,
+ * when tcp_rtt_estimator() was not yet called.
+ */
+ if (tp->srtt > 8 + 2)
+ do_div(rate, tp->srtt);
+
+ sk->sk_pacing_rate = min_t(u64, rate, ~0U);
+}
+
/* Calculate rto without backoff. This is the second half of Van Jacobson's
* routine referred to above.
*/
}
/* D-SACK for already forgotten data... Do dumb counting. */
- if (dup_sack && tp->undo_marker && tp->undo_retrans &&
+ if (dup_sack && tp->undo_marker && tp->undo_retrans > 0 &&
!after(end_seq_0, prior_snd_una) &&
after(end_seq_0, tp->undo_marker))
tp->undo_retrans--;
unsigned int new_len = (pkt_len / mss) * mss;
if (!in_sack && new_len < pkt_len) {
new_len += mss;
- if (new_len > skb->len)
+ if (new_len >= skb->len)
return 0;
}
pkt_len = new_len;
/* Account D-SACK for retransmitted packet. */
if (dup_sack && (sacked & TCPCB_RETRANS)) {
- if (tp->undo_marker && tp->undo_retrans &&
+ if (tp->undo_marker && tp->undo_retrans > 0 &&
after(end_seq, tp->undo_marker))
tp->undo_retrans--;
if (sacked & TCPCB_SACKED_ACKED)
tp->lost_cnt_hint -= tcp_skb_pcount(prev);
}
- TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(prev)->tcp_flags;
+ TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+ TCP_SKB_CB(prev)->end_seq++;
+
if (skb == tcp_highest_sack(sk))
tcp_advance_highest_sack(sk, skb);
tp->lost_out = 0;
tp->undo_marker = 0;
- tp->undo_retrans = 0;
+ tp->undo_retrans = -1;
}
void tcp_clear_retrans(struct tcp_sock *tp)
tp->prior_ssthresh = 0;
tp->undo_marker = tp->snd_una;
- tp->undo_retrans = tp->retrans_out;
+ tp->undo_retrans = tp->retrans_out ? : -1;
if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
if (!ece_ack)
bool recovered = !before(tp->snd_una, tp->high_seq);
if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
- if (flag & FLAG_ORIG_SACK_ACKED) {
- /* Step 3.b. A timeout is spurious if not all data are
- * lost, i.e., never-retransmitted data are (s)acked.
- */
- tcp_try_undo_loss(sk, true);
+ /* Step 3.b. A timeout is spurious if not all data are
+ * lost, i.e., never-retransmitted data are (s)acked.
+ */
+ if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED))
return;
- }
+
if (after(tp->snd_nxt, tp->high_seq) &&
(flag & FLAG_DATA_SACKED || is_dupack)) {
tp->frto = 0; /* Loss was real: 2nd part of step 3.a */
if (seq_rtt < 0) {
seq_rtt = ca_seq_rtt;
}
- if (!(sacked & TCPCB_SACKED_ACKED))
+ if (!(sacked & TCPCB_SACKED_ACKED)) {
reord = min(pkts_acked, reord);
- if (!after(scb->end_seq, tp->high_seq))
- flag |= FLAG_ORIG_SACK_ACKED;
+ if (!after(scb->end_seq, tp->high_seq))
+ flag |= FLAG_ORIG_SACK_ACKED;
+ }
}
if (sacked & TCPCB_SACKED_ACKED)
tcp_init_cwnd_reduction(sk, true);
tcp_set_ca_state(sk, TCP_CA_CWR);
tcp_end_cwnd_reduction(sk);
- tcp_set_ca_state(sk, TCP_CA_Open);
+ tcp_try_keep_open(sk);
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPLOSSPROBERECOVERY);
}
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
bool is_dupack = false;
- u32 prior_in_flight;
+ u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt;
u32 prior_fackets;
int prior_packets = tp->packets_out;
int prior_sacked = tp->sacked_out;
if (icsk->icsk_pending == ICSK_TIME_RETRANS)
tcp_schedule_loss_probe(sk);
+ if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd)
+ tcp_update_pacing_rate(sk);
return 1;
no_queue:
} else
tcp_init_metrics(sk);
+ tcp_update_pacing_rate(sk);
+
/* Prevent spurious tcp_cwnd_restart() on
* first data packet.
*/