tcp: fix stretch ACK bugs in CUBIC
Change CUBIC to properly handle stretch ACKs in additive increase mode
by passing in the count of ACKed packets to tcp_cong_avoid_ai().
In addition, because we are now precisely accounting for stretch ACKs,
including delayed ACKs, we can now remove the delayed ACK tracking and
estimation code that tracked recent delayed ACK behavior in
ca->delayed_ack.
Reported-by: Eyal Perry <eyalpe@mellanox.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index df4bc4d..ffc045d 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -93,9 +93,7 @@
u32 epoch_start; /* beginning of an epoch */
u32 ack_cnt; /* number of acks */
u32 tcp_cwnd; /* estimated tcp cwnd */
-#define ACK_RATIO_SHIFT 4
-#define ACK_RATIO_LIMIT (32u << ACK_RATIO_SHIFT)
- u16 delayed_ack; /* estimate the ratio of Packets/ACKs << 4 */
+ u16 unused;
u8 sample_cnt; /* number of samples to decide curr_rtt */
u8 found; /* the exit point is found? */
u32 round_start; /* beginning of each round */
@@ -114,7 +112,6 @@
ca->bic_K = 0;
ca->delay_min = 0;
ca->epoch_start = 0;
- ca->delayed_ack = 2 << ACK_RATIO_SHIFT;
ca->ack_cnt = 0;
ca->tcp_cwnd = 0;
ca->found = 0;
@@ -205,12 +202,12 @@
/*
* Compute congestion window to use.
*/
-static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
+static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked)
{
u32 delta, bic_target, max_cnt;
u64 offs, t;
- ca->ack_cnt++; /* count the number of ACKs */
+ ca->ack_cnt += acked; /* count the number of ACKed packets */
if (ca->last_cwnd == cwnd &&
(s32)(tcp_time_stamp - ca->last_time) <= HZ / 32)
@@ -221,7 +218,7 @@
if (ca->epoch_start == 0) {
ca->epoch_start = tcp_time_stamp; /* record beginning */
- ca->ack_cnt = 1; /* start counting */
+ ca->ack_cnt = acked; /* start counting */
ca->tcp_cwnd = cwnd; /* syn with cubic */
if (ca->last_max_cwnd <= cwnd) {
@@ -301,7 +298,6 @@
}
}
- ca->cnt = (ca->cnt << ACK_RATIO_SHIFT) / ca->delayed_ack;
if (ca->cnt == 0) /* cannot be zero */
ca->cnt = 1;
}
@@ -317,11 +313,12 @@
if (tp->snd_cwnd <= tp->snd_ssthresh) {
if (hystart && after(ack, ca->end_seq))
bictcp_hystart_reset(sk);
- tcp_slow_start(tp, acked);
- } else {
- bictcp_update(ca, tp->snd_cwnd);
- tcp_cong_avoid_ai(tp, ca->cnt, 1);
+ acked = tcp_slow_start(tp, acked);
+ if (!acked)
+ return;
}
+ bictcp_update(ca, tp->snd_cwnd, acked);
+ tcp_cong_avoid_ai(tp, ca->cnt, acked);
}
static u32 bictcp_recalc_ssthresh(struct sock *sk)
@@ -411,20 +408,10 @@
*/
static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
{
- const struct inet_connection_sock *icsk = inet_csk(sk);
const struct tcp_sock *tp = tcp_sk(sk);
struct bictcp *ca = inet_csk_ca(sk);
u32 delay;
- if (icsk->icsk_ca_state == TCP_CA_Open) {
- u32 ratio = ca->delayed_ack;
-
- ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT;
- ratio += cnt;
-
- ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT);
- }
-
/* Some calls are for duplicates without timetamps */
if (rtt_us < 0)
return;