#include <linux/module.h>
#include <linux/sysctl.h>
#include <linux/kernel.h>
+#include <linux/reciprocal_div.h>
#include <net/dst.h>
#include <net/tcp.h>
#include <net/inet_common.h>
EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
/* rfc5961 challenge ack rate limiting */
-int sysctl_tcp_challenge_ack_limit = 100;
+int sysctl_tcp_challenge_ack_limit = 1000;
int sysctl_tcp_stdurg __read_mostly;
int sysctl_tcp_rfc1337 __read_mostly;
#define FLAG_ORIG_SACK_ACKED 0x200 /* Never retransmitted data are (s)acked */
#define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */
#define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */
+#define FLAG_SET_XMIT_TIMER 0x1000 /* Set TLP or RTO timer */
#define FLAG_SACK_RENEGING 0x2000 /* snd_una advanced to a sacked seq */
#define FLAG_UPDATE_TS_RECENT 0x4000 /* tcp_replace_ts_recent() */
}
}
+/* 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)
struct tcp_sock *tp = tcp_sk(sk);
/* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */
- if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR ||
- (tp->undo_marker && tp->snd_ssthresh < TCP_INFINITE_SSTHRESH)) {
+ if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH &&
+ (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || tp->undo_marker)) {
tp->snd_cwnd = tp->snd_ssthresh;
tp->snd_cwnd_stamp = tcp_time_stamp;
}
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 */
/* Offset the time elapsed after installing regular RTO */
if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
- struct sk_buff *skb = tcp_write_queue_head(sk);
- const u32 rto_time_stamp = TCP_SKB_CB(skb)->when + rto;
- s32 delta = (s32)(rto_time_stamp - tcp_time_stamp);
+ s32 delta = tcp_rto_delta(sk);
/* delta may not be positive if the socket is locked
* when the retrans timer fires and is rescheduled.
*/
- if (delta > 0)
- rto = delta;
+ rto = max_t(int, delta, 1);
}
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
TCP_RTO_MAX);
tcp_xmit_retransmit_queue(sk);
}
+/* Try to schedule a loss probe; if that doesn't work, then schedule an RTO. */
+static void tcp_set_xmit_timer(struct sock *sk)
+{
+ if (!tcp_schedule_loss_probe(sk))
+ tcp_rearm_rto(sk);
+}
+
/* If we get here, the whole TSO packet has not been acked. */
static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb)
{
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_ack_update_rtt(sk, flag, seq_rtt);
- tcp_rearm_rto(sk);
+ flag |= FLAG_SET_XMIT_TIMER; /* set TLP or RTO timer */
if (tcp_is_reno(tp)) {
tcp_remove_reno_sacks(sk, pkts_acked);
static u32 challenge_timestamp;
static unsigned int challenge_count;
u32 now = jiffies / HZ;
+ u32 count;
if (now != challenge_timestamp) {
+ u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1;
+
challenge_timestamp = now;
- challenge_count = 0;
+ ACCESS_ONCE(challenge_count) = half +
+ reciprocal_divide(prandom_u32(),
+ sysctl_tcp_challenge_ack_limit);
}
- if (++challenge_count <= sysctl_tcp_challenge_ack_limit) {
+ count = ACCESS_ONCE(challenge_count);
+ if (count > 0) {
+ ACCESS_ONCE(challenge_count) = count - 1;
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK);
tcp_send_ack(sk);
}
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 (after(ack, tp->snd_nxt))
goto invalid_ack;
- if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
- icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
- tcp_rearm_rto(sk);
-
if (after(ack, prior_snd_una))
flag |= FLAG_SND_UNA_ADVANCED;
pkts_acked = previous_packets_out - tp->packets_out;
+ if (tp->tlp_high_seq)
+ tcp_process_tlp_ack(sk, ack, flag);
+ /* If needed, reset TLP/RTO timer; RACK may later override this. */
+ if (flag & FLAG_SET_XMIT_TIMER)
+ tcp_set_xmit_timer(sk);
+
if (tcp_ack_is_dubious(sk, flag)) {
/* Advance CWND, if state allows this. */
if ((flag & FLAG_DATA_ACKED) && tcp_may_raise_cwnd(sk, flag))
tcp_cong_avoid(sk, ack, prior_in_flight);
}
- if (tp->tlp_high_seq)
- tcp_process_tlp_ack(sk, ack, flag);
-
if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) {
struct dst_entry *dst = __sk_dst_get(sk);
if (dst)
dst_confirm(dst);
}
- 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:
++ptr;
tp->rx_opt.rcv_tsval = ntohl(*ptr);
++ptr;
- tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset;
+ if (*ptr)
+ tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset;
+ else
+ tp->rx_opt.rcv_tsecr = 0;
return true;
}
return false;
}
tcp_parse_options(skb, &tp->rx_opt, 1, NULL);
- if (tp->rx_opt.saw_tstamp)
+ if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
tp->rx_opt.rcv_tsecr -= tp->tsoffset;
return true;
struct inet_connection_sock *icsk = inet_csk(sk);
tcp_set_state(sk, TCP_ESTABLISHED);
+ icsk->icsk_ack.lrcvtime = tcp_time_stamp;
if (skb != NULL) {
icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
int saved_clamp = tp->rx_opt.mss_clamp;
tcp_parse_options(skb, &tp->rx_opt, 0, &foc);
- if (tp->rx_opt.saw_tstamp)
+ if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
tp->rx_opt.rcv_tsecr -= tp->tsoffset;
if (th->ack) {
* to stand against the temptation 8) --ANK
*/
inet_csk_schedule_ack(sk);
- icsk->icsk_ack.lrcvtime = tcp_time_stamp;
tcp_enter_quickack_mode(sk);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
TCP_DELACK_MAX, TCP_RTO_MAX);
}
tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+ tp->copied_seq = tp->rcv_nxt;
tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
/* RFC1323: The window in SYN & SYN/ACK segments is
} else
tcp_init_metrics(sk);
+ tcp_update_pacing_rate(sk);
+
/* Prevent spurious tcp_cwnd_restart() on
* first data packet.
*/