| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <1437538896-1330704-2-git-send-email-brakmo@fb.com>
Date: Tue, 21 Jul 2015 21:21:34 -0700
From: Lawrence Brakmo <brakmo@...com>
To: netdev <netdev@...r.kernel.org>
CC: Kernel Team <kernel-team@...com>,
Neal Cardwell <ncardwell@...gle.com>,
Eric Dumazet <eric.dumazet@...il.com>
Subject: [RFC PATCH v2 net-next 1/3] tcp: replace cnt & rtt with struct in pkts_acked()
Replace 2 arguments (cnt and rtt) in the congestion control modules'
pkts_acked() function with a struct. This will allow adding more
information without having to modify existing congestion control
modules (tcp_nv in particular needs bytes in flight when packet
was sent).
This was proposed by Neal Cardwell in his comments to the tcp_nv patch.
Signed-off-by: Lawrence Brakmo <lawrence@...kmo.org>
---
include/net/tcp.h | 7 ++++++-
net/ipv4/tcp_bic.c | 6 +++---
net/ipv4/tcp_cdg.c | 14 +++++++-------
net/ipv4/tcp_cubic.c | 6 +++---
net/ipv4/tcp_htcp.c | 10 +++++-----
net/ipv4/tcp_illinois.c | 20 ++++++++++----------
net/ipv4/tcp_input.c | 7 +++++--
net/ipv4/tcp_lp.c | 6 +++---
net/ipv4/tcp_vegas.c | 6 +++---
net/ipv4/tcp_vegas.h | 2 +-
net/ipv4/tcp_veno.c | 6 +++---
net/ipv4/tcp_westwood.c | 6 +++---
net/ipv4/tcp_yeah.c | 6 +++---
13 files changed, 55 insertions(+), 47 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 364426a..26e7651 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -834,6 +834,11 @@ enum tcp_ca_ack_event_flags {
union tcp_cc_info;
+struct ack_sample {
+ u32 pkts_acked;
+ s32 rtt_us;
+};
+
struct tcp_congestion_ops {
struct list_head list;
u32 key;
@@ -857,7 +862,7 @@ struct tcp_congestion_ops {
/* new value of cwnd after loss (optional) */
u32 (*undo_cwnd)(struct sock *sk);
/* hook for packet ack accounting (optional) */
- void (*pkts_acked)(struct sock *sk, u32 num_acked, s32 rtt_us);
+ void (*pkts_acked)(struct sock *sk, struct ack_sample);
/* get info for inet_diag (optional) */
size_t (*get_info)(struct sock *sk, u32 ext, int *attr,
union tcp_cc_info *info);
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index fd1405d..6a873f7 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -197,15 +197,15 @@ static void bictcp_state(struct sock *sk, u8 new_state)
/* Track delayed acknowledgment ratio using sliding window
* ratio = (15*ratio + sample) / 16
*/
-static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt)
+static void bictcp_acked(struct sock *sk, struct ack_sample sample)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
if (icsk->icsk_ca_state == TCP_CA_Open) {
struct bictcp *ca = inet_csk_ca(sk);
- cnt -= ca->delayed_ack >> ACK_RATIO_SHIFT;
- ca->delayed_ack += cnt;
+ ca->delayed_ack += sample.pkts_acked -
+ (ca->delayed_ack >> ACK_RATIO_SHIFT);
}
}
diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c
index 167b6a3..ef64106 100644
--- a/net/ipv4/tcp_cdg.c
+++ b/net/ipv4/tcp_cdg.c
@@ -294,12 +294,12 @@ static void tcp_cdg_cong_avoid(struct sock *sk, u32 ack, u32 acked)
ca->shadow_wnd = max(ca->shadow_wnd, ca->shadow_wnd + incr);
}
-static void tcp_cdg_acked(struct sock *sk, u32 num_acked, s32 rtt_us)
+static void tcp_cdg_acked(struct sock *sk, struct ack_sample sample)
{
struct cdg *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
- if (rtt_us <= 0)
+ if (sample.rtt_us <= 0)
return;
/* A heuristic for filtering delayed ACKs, adapted from:
@@ -307,20 +307,20 @@ static void tcp_cdg_acked(struct sock *sk, u32 num_acked, s32 rtt_us)
* delay and rate based TCP mechanisms." TR 100219A. CAIA, 2010.
*/
if (tp->sacked_out == 0) {
- if (num_acked == 1 && ca->delack) {
+ if (sample.pkts_acked == 1 && ca->delack) {
/* A delayed ACK is only used for the minimum if it is
* provenly lower than an existing non-zero minimum.
*/
- ca->rtt.min = min(ca->rtt.min, rtt_us);
+ ca->rtt.min = min(ca->rtt.min, sample.rtt_us);
ca->delack--;
return;
- } else if (num_acked > 1 && ca->delack < 5) {
+ } else if (sample.pkts_acked > 1 && ca->delack < 5) {
ca->delack++;
}
}
- ca->rtt.min = min_not_zero(ca->rtt.min, rtt_us);
- ca->rtt.max = max(ca->rtt.max, rtt_us);
+ ca->rtt.min = min_not_zero(ca->rtt.min, sample.rtt_us);
+ ca->rtt.max = max(ca->rtt.max, sample.rtt_us);
}
static u32 tcp_cdg_ssthresh(struct sock *sk)
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 28011fb..070d629 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -416,21 +416,21 @@ static void hystart_update(struct sock *sk, u32 delay)
/* Track delayed acknowledgment ratio using sliding window
* ratio = (15*ratio + sample) / 16
*/
-static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
+static void bictcp_acked(struct sock *sk, struct ack_sample sample)
{
const struct tcp_sock *tp = tcp_sk(sk);
struct bictcp *ca = inet_csk_ca(sk);
u32 delay;
/* Some calls are for duplicates without timetamps */
- if (rtt_us < 0)
+ if (sample.rtt_us < 0)
return;
/* Discard delay samples right after fast recovery */
if (ca->epoch_start && (s32)(tcp_time_stamp - ca->epoch_start) < HZ)
return;
- delay = (rtt_us << 3) / USEC_PER_MSEC;
+ delay = (sample.rtt_us << 3) / USEC_PER_MSEC;
if (delay == 0)
delay = 1;
diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c
index 82f0d9e..4f0fb11 100644
--- a/net/ipv4/tcp_htcp.c
+++ b/net/ipv4/tcp_htcp.c
@@ -99,7 +99,7 @@ static inline void measure_rtt(struct sock *sk, u32 srtt)
}
static void measure_achieved_throughput(struct sock *sk,
- u32 pkts_acked, s32 rtt)
+ struct ack_sample sample)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
const struct tcp_sock *tp = tcp_sk(sk);
@@ -107,10 +107,10 @@ static void measure_achieved_throughput(struct sock *sk,
u32 now = tcp_time_stamp;
if (icsk->icsk_ca_state == TCP_CA_Open)
- ca->pkts_acked = pkts_acked;
+ ca->pkts_acked = sample.pkts_acked;
- if (rtt > 0)
- measure_rtt(sk, usecs_to_jiffies(rtt));
+ if (sample.rtt_us > 0)
+ measure_rtt(sk, usecs_to_jiffies(sample.rtt_us));
if (!use_bandwidth_switch)
return;
@@ -122,7 +122,7 @@ static void measure_achieved_throughput(struct sock *sk,
return;
}
- ca->packetcount += pkts_acked;
+ ca->packetcount += sample.pkts_acked;
if (ca->packetcount >= tp->snd_cwnd - (ca->alpha >> 7 ? : 1) &&
now - ca->lasttime >= ca->minRTT &&
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index 2ab9bbb..7d18b71 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -82,30 +82,30 @@ static void tcp_illinois_init(struct sock *sk)
}
/* Measure RTT for each ack. */
-static void tcp_illinois_acked(struct sock *sk, u32 pkts_acked, s32 rtt)
+static void tcp_illinois_acked(struct sock *sk, struct ack_sample sample)
{
struct illinois *ca = inet_csk_ca(sk);
- ca->acked = pkts_acked;
+ ca->acked = sample.pkts_acked;
/* dup ack, no rtt sample */
- if (rtt < 0)
+ if (sample.rtt_us < 0)
return;
/* ignore bogus values, this prevents wraparound in alpha math */
- if (rtt > RTT_MAX)
- rtt = RTT_MAX;
+ if (sample.rtt_us > RTT_MAX)
+ sample.rtt_us = RTT_MAX;
/* keep track of minimum RTT seen so far */
- if (ca->base_rtt > rtt)
- ca->base_rtt = rtt;
+ if (ca->base_rtt > sample.rtt_us)
+ ca->base_rtt = sample.rtt_us;
/* and max */
- if (ca->max_rtt < rtt)
- ca->max_rtt = rtt;
+ if (ca->max_rtt < sample.rtt_us)
+ ca->max_rtt = sample.rtt_us;
++ca->cnt_rtt;
- ca->sum_rtt += rtt;
+ ca->sum_rtt += sample.rtt_us;
}
/* Maximum queuing delay */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1578fc2..4f641f6 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3195,8 +3195,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
tcp_rearm_rto(sk);
}
- if (icsk->icsk_ca_ops->pkts_acked)
- icsk->icsk_ca_ops->pkts_acked(sk, pkts_acked, ca_rtt_us);
+ if (icsk->icsk_ca_ops->pkts_acked) {
+ struct ack_sample sample = {pkts_acked, ca_rtt_us};
+
+ icsk->icsk_ca_ops->pkts_acked(sk, sample);
+ }
#if FASTRETRANS_DEBUG > 0
WARN_ON((int)tp->sacked_out < 0);
diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c
index 1e70fa8..341c768 100644
--- a/net/ipv4/tcp_lp.c
+++ b/net/ipv4/tcp_lp.c
@@ -260,13 +260,13 @@ static void tcp_lp_rtt_sample(struct sock *sk, u32 rtt)
* newReno in increase case.
* We work it out by following the idea from TCP-LP's paper directly
*/
-static void tcp_lp_pkts_acked(struct sock *sk, u32 num_acked, s32 rtt_us)
+static void tcp_lp_pkts_acked(struct sock *sk, struct ack_sample sample)
{
struct tcp_sock *tp = tcp_sk(sk);
struct lp *lp = inet_csk_ca(sk);
- if (rtt_us > 0)
- tcp_lp_rtt_sample(sk, rtt_us);
+ if (sample.rtt_us > 0)
+ tcp_lp_rtt_sample(sk, sample.rtt_us);
/* calc inference */
if (tcp_time_stamp > tp->rx_opt.rcv_tsecr)
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 13951c4..17d0a84 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -107,16 +107,16 @@ EXPORT_SYMBOL_GPL(tcp_vegas_init);
* o min-filter RTT samples from a much longer window (forever for now)
* to find the propagation delay (baseRTT)
*/
-void tcp_vegas_pkts_acked(struct sock *sk, u32 cnt, s32 rtt_us)
+void tcp_vegas_pkts_acked(struct sock *sk, struct ack_sample sample)
{
struct vegas *vegas = inet_csk_ca(sk);
u32 vrtt;
- if (rtt_us < 0)
+ if (sample.rtt_us < 0)
return;
/* Never allow zero rtt or baseRTT */
- vrtt = rtt_us + 1;
+ vrtt = sample.rtt_us + 1;
/* Filter to find propagation delay: */
if (vrtt < vegas->baseRTT)
diff --git a/net/ipv4/tcp_vegas.h b/net/ipv4/tcp_vegas.h
index ef9da53..469f9ad 100644
--- a/net/ipv4/tcp_vegas.h
+++ b/net/ipv4/tcp_vegas.h
@@ -17,7 +17,7 @@ struct vegas {
void tcp_vegas_init(struct sock *sk);
void tcp_vegas_state(struct sock *sk, u8 ca_state);
-void tcp_vegas_pkts_acked(struct sock *sk, u32 cnt, s32 rtt_us);
+void tcp_vegas_pkts_acked(struct sock *sk, struct ack_sample sample);
void tcp_vegas_cwnd_event(struct sock *sk, enum tcp_ca_event event);
size_t tcp_vegas_get_info(struct sock *sk, u32 ext, int *attr,
union tcp_cc_info *info);
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index 0d094b9..563d8fd 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -69,16 +69,16 @@ static void tcp_veno_init(struct sock *sk)
}
/* Do rtt sampling needed for Veno. */
-static void tcp_veno_pkts_acked(struct sock *sk, u32 cnt, s32 rtt_us)
+static void tcp_veno_pkts_acked(struct sock *sk, struct ack_sample sample)
{
struct veno *veno = inet_csk_ca(sk);
u32 vrtt;
- if (rtt_us < 0)
+ if (sample.rtt_us < 0)
return;
/* Never allow zero rtt or baseRTT */
- vrtt = rtt_us + 1;
+ vrtt = sample.rtt_us + 1;
/* Filter to find propagation delay: */
if (vrtt < veno->basertt)
diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c
index c10732e..d330c3e9 100644
--- a/net/ipv4/tcp_westwood.c
+++ b/net/ipv4/tcp_westwood.c
@@ -99,12 +99,12 @@ static void westwood_filter(struct westwood *w, u32 delta)
* Called after processing group of packets.
* but all westwood needs is the last sample of srtt.
*/
-static void tcp_westwood_pkts_acked(struct sock *sk, u32 cnt, s32 rtt)
+static void tcp_westwood_pkts_acked(struct sock *sk, struct ack_sample sample)
{
struct westwood *w = inet_csk_ca(sk);
- if (rtt > 0)
- w->rtt = usecs_to_jiffies(rtt);
+ if (sample.rtt_us > 0)
+ w->rtt = usecs_to_jiffies(sample.rtt_us);
}
/*
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index 17d3566..66b34c0 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -56,15 +56,15 @@ static void tcp_yeah_init(struct sock *sk)
tp->snd_cwnd_clamp = min_t(u32, tp->snd_cwnd_clamp, 0xffffffff/128);
}
-static void tcp_yeah_pkts_acked(struct sock *sk, u32 pkts_acked, s32 rtt_us)
+static void tcp_yeah_pkts_acked(struct sock *sk, struct ack_sample sample)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct yeah *yeah = inet_csk_ca(sk);
if (icsk->icsk_ca_state == TCP_CA_Open)
- yeah->pkts_acked = pkts_acked;
+ yeah->pkts_acked = sample.pkts_acked;
- tcp_vegas_pkts_acked(sk, pkts_acked, rtt_us);
+ tcp_vegas_pkts_acked(sk, sample);
}
static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked)
--
1.8.1
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists