summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp_input.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/tcp_input.c')
-rw-r--r--net/ipv4/tcp_input.c84
1 files changed, 46 insertions, 38 deletions
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 45f750e85714..9a1b3c1c1c14 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -97,6 +97,7 @@ int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
#define FLAG_SACK_RENEGING 0x2000 /* snd_una advanced to a sacked seq */
#define FLAG_UPDATE_TS_RECENT 0x4000 /* tcp_replace_ts_recent() */
#define FLAG_NO_CHALLENGE_ACK 0x8000 /* do not call tcp_send_challenge_ack() */
+#define FLAG_ACK_MAYBE_DELAYED 0x10000 /* Likely a delayed ACK */
#define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED)
#define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
@@ -314,7 +315,7 @@ static void tcp_sndbuf_expand(struct sock *sk)
/* Fast Recovery (RFC 5681 3.2) :
* Cubic needs 1.7 factor, rounded to 2 to include
- * extra cushion (application might react slowly to POLLOUT)
+ * extra cushion (application might react slowly to EPOLLOUT)
*/
sndmem = ca_ops->sndbuf_expand ? ca_ops->sndbuf_expand(sk) : 2;
sndmem *= nr_segs * per_mss;
@@ -578,8 +579,8 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
void tcp_rcv_space_adjust(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
+ u32 copied;
int time;
- int copied;
tcp_mstamp_refresh(tp);
time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time);
@@ -602,38 +603,31 @@ void tcp_rcv_space_adjust(struct sock *sk)
if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
- int rcvwin, rcvmem, rcvbuf;
+ int rcvmem, rcvbuf;
+ u64 rcvwin, grow;
/* minimal window to cope with packet losses, assuming
* steady state. Add some cushion because of small variations.
*/
- rcvwin = (copied << 1) + 16 * tp->advmss;
+ rcvwin = ((u64)copied << 1) + 16 * tp->advmss;
- /* If rate increased by 25%,
- * assume slow start, rcvwin = 3 * copied
- * If rate increased by 50%,
- * assume sender can use 2x growth, rcvwin = 4 * copied
- */
- if (copied >=
- tp->rcvq_space.space + (tp->rcvq_space.space >> 2)) {
- if (copied >=
- tp->rcvq_space.space + (tp->rcvq_space.space >> 1))
- rcvwin <<= 1;
- else
- rcvwin += (rcvwin >> 1);
- }
+ /* Accommodate for sender rate increase (eg. slow start) */
+ grow = rcvwin * (copied - tp->rcvq_space.space);
+ do_div(grow, tp->rcvq_space.space);
+ rcvwin += (grow << 1);
rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER);
while (tcp_win_from_space(sk, rcvmem) < tp->advmss)
rcvmem += 128;
- rcvbuf = min(rcvwin / tp->advmss * rcvmem,
- sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+ do_div(rcvwin, tp->advmss);
+ rcvbuf = min_t(u64, rcvwin * rcvmem,
+ sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
if (rcvbuf > sk->sk_rcvbuf) {
sk->sk_rcvbuf = rcvbuf;
/* Make the window clamp follow along. */
- tp->window_clamp = rcvwin;
+ tp->window_clamp = tcp_win_from_space(sk, rcvbuf);
}
}
tp->rcvq_space.space = copied;
@@ -1977,11 +1971,6 @@ void tcp_enter_loss(struct sock *sk)
/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
* loss recovery is underway except recurring timeout(s) on
* the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
- *
- * In theory F-RTO can be used repeatedly during loss recovery.
- * In practice this interacts badly with broken middle-boxes that
- * falsely raise the receive window, which results in repeated
- * timeouts and stop-and-go behavior.
*/
tp->frto = net->ipv4.sysctl_tcp_frto &&
(new_recovery || icsk->icsk_retransmits) &&
@@ -2637,18 +2626,14 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
tcp_try_undo_loss(sk, false))
return;
- /* The ACK (s)acks some never-retransmitted data meaning not all
- * the data packets before the timeout were lost. Therefore we
- * undo the congestion window and state. This is essentially
- * the operation in F-RTO (RFC5682 section 3.1 step 3.b). Since
- * a retransmitted skb is permantly marked, we can apply such an
- * operation even if F-RTO was not used.
- */
- if ((flag & FLAG_ORIG_SACK_ACKED) &&
- tcp_try_undo_loss(sk, tp->undo_marker))
- return;
-
if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
+ /* Step 3.b. A timeout is spurious if not all data are
+ * lost, i.e., never-retransmitted data are (s)acked.
+ */
+ if ((flag & FLAG_ORIG_SACK_ACKED) &&
+ tcp_try_undo_loss(sk, true))
+ return;
+
if (after(tp->snd_nxt, tp->high_seq)) {
if (flag & FLAG_DATA_SACKED || is_dupack)
tp->frto = 0; /* Step 3.a. loss was real */
@@ -2864,11 +2849,18 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
*rexmit = REXMIT_LOST;
}
-static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us)
+static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us, const int flag)
{
u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ;
struct tcp_sock *tp = tcp_sk(sk);
+ if ((flag & FLAG_ACK_MAYBE_DELAYED) && rtt_us > tcp_min_rtt(tp)) {
+ /* If the remote keeps returning delayed ACKs, eventually
+ * the min filter would pick it up and overestimate the
+ * prop. delay when it expires. Skip suspected delayed ACKs.
+ */
+ return;
+ }
minmax_running_min(&tp->rtt_min, wlen, tcp_jiffies32,
rtt_us ? : jiffies_to_usecs(1));
}
@@ -2908,7 +2900,7 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag,
* 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_update_rtt_min(sk, ca_rtt_us, flag);
tcp_rtt_estimator(sk, seq_rtt_us);
tcp_set_rto(sk);
@@ -3132,6 +3124,17 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
if (likely(first_ackt) && !(flag & FLAG_RETRANS_DATA_ACKED)) {
seq_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, first_ackt);
ca_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, last_ackt);
+
+ if (pkts_acked == 1 && last_in_flight < tp->mss_cache &&
+ last_in_flight && !prior_sacked && fully_acked &&
+ sack->rate->prior_delivered + 1 == tp->delivered &&
+ !(flag & (FLAG_CA_ALERT | FLAG_SYN_ACKED))) {
+ /* Conservatively mark a delayed ACK. It's typically
+ * from a lone runt packet over the round trip to
+ * a receiver w/o out-of-order or CE events.
+ */
+ flag |= FLAG_ACK_MAYBE_DELAYED;
+ }
}
if (sack->first_sackt) {
sack_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, sack->first_sackt);
@@ -3621,6 +3624,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */
lost = tp->lost - lost; /* freshly marked lost */
+ rs.is_ack_delayed = !!(flag & FLAG_ACK_MAYBE_DELAYED);
tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate);
tcp_cong_control(sk, ack, delivered, flag, sack_state.rate);
tcp_xmit_recovery(sk, rexmit);
@@ -3988,6 +3992,7 @@ void tcp_reset(struct sock *sk)
/* This barrier is coupled with smp_rmb() in tcp_poll() */
smp_wmb();
+ tcp_write_queue_purge(sk);
tcp_done(sk);
if (!sock_flag(sk, SOCK_DEAD))
@@ -5306,6 +5311,9 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
unsigned int len = skb->len;
struct tcp_sock *tp = tcp_sk(sk);
+ /* TCP congestion window tracking */
+ trace_tcp_probe(sk, skb);
+
tcp_mstamp_refresh(tp);
if (unlikely(!sk->sk_rx_dst))
inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb);
generated by cgit v1.2.3 (git 2.46.0) at 2025-09-09 06:24:20 +0000