Merge branch 'tcp-cwnd-undo-refactor'
Yuchung Cheng says:
====================
tcp cwnd undo refactor
This patch series consolidate similar cwnd undo functions
implemented by various congestion control by using existing
tcp socket state variable. The first patch fixes a corner
case in of cwnd undo in Reno and HTCP. Since the bug has
existed for many years and is very minor, we consider this
patch set more suitable for net-next as the major change
is the refactor itself.
- v1->v2
Fix trivial compile errors
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index d7389ea..267164a 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -258,7 +258,7 @@ struct tcp_sock {
u32 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */
u32 snd_cwnd_used;
u32 snd_cwnd_stamp;
- u32 prior_cwnd; /* Congestion window at start of Recovery. */
+ u32 prior_cwnd; /* cwnd right before starting loss recovery */
u32 prr_delivered; /* Number of newly delivered packets to
* receiver in Recovery. */
u32 prr_out; /* Total number of pkts sent during Recovery. */
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index 609965f..fc36143 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -49,7 +49,6 @@ MODULE_PARM_DESC(smooth_part, "log(B/(B*Smin))/log(B/(B-1))+B, # of RTT from Wma
struct bictcp {
u32 cnt; /* increase cwnd by 1 after ACKs */
u32 last_max_cwnd; /* last maximum snd_cwnd */
- u32 loss_cwnd; /* congestion window at last loss */
u32 last_cwnd; /* the last snd_cwnd */
u32 last_time; /* time when updated last_cwnd */
u32 epoch_start; /* beginning of an epoch */
@@ -72,7 +71,6 @@ static void bictcp_init(struct sock *sk)
struct bictcp *ca = inet_csk_ca(sk);
bictcp_reset(ca);
- ca->loss_cwnd = 0;
if (initial_ssthresh)
tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
@@ -172,22 +170,12 @@ static u32 bictcp_recalc_ssthresh(struct sock *sk)
else
ca->last_max_cwnd = tp->snd_cwnd;
- ca->loss_cwnd = tp->snd_cwnd;
-
if (tp->snd_cwnd <= low_window)
return max(tp->snd_cwnd >> 1U, 2U);
else
return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U);
}
-static u32 bictcp_undo_cwnd(struct sock *sk)
-{
- const struct tcp_sock *tp = tcp_sk(sk);
- const struct bictcp *ca = inet_csk_ca(sk);
-
- return max(tp->snd_cwnd, ca->loss_cwnd);
-}
-
static void bictcp_state(struct sock *sk, u8 new_state)
{
if (new_state == TCP_CA_Loss)
@@ -214,7 +202,7 @@ static struct tcp_congestion_ops bictcp __read_mostly = {
.ssthresh = bictcp_recalc_ssthresh,
.cong_avoid = bictcp_cong_avoid,
.set_state = bictcp_state,
- .undo_cwnd = bictcp_undo_cwnd,
+ .undo_cwnd = tcp_reno_undo_cwnd,
.pkts_acked = bictcp_acked,
.owner = THIS_MODULE,
.name = "bic",
diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c
index 50a0f3e..66ac69f 100644
--- a/net/ipv4/tcp_cdg.c
+++ b/net/ipv4/tcp_cdg.c
@@ -85,7 +85,6 @@ struct cdg {
u8 state;
u8 delack;
u32 rtt_seq;
- u32 undo_cwnd;
u32 shadow_wnd;
u16 backoff_cnt;
u16 sample_cnt;
@@ -330,8 +329,6 @@ static u32 tcp_cdg_ssthresh(struct sock *sk)
struct cdg *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
- ca->undo_cwnd = tp->snd_cwnd;
-
if (ca->state == CDG_BACKOFF)
return max(2U, (tp->snd_cwnd * min(1024U, backoff_beta)) >> 10);
@@ -344,13 +341,6 @@ static u32 tcp_cdg_ssthresh(struct sock *sk)
return max(2U, tp->snd_cwnd >> 1);
}
-static u32 tcp_cdg_undo_cwnd(struct sock *sk)
-{
- struct cdg *ca = inet_csk_ca(sk);
-
- return max(tcp_sk(sk)->snd_cwnd, ca->undo_cwnd);
-}
-
static void tcp_cdg_cwnd_event(struct sock *sk, const enum tcp_ca_event ev)
{
struct cdg *ca = inet_csk_ca(sk);
@@ -403,7 +393,7 @@ struct tcp_congestion_ops tcp_cdg __read_mostly = {
.cong_avoid = tcp_cdg_cong_avoid,
.cwnd_event = tcp_cdg_cwnd_event,
.pkts_acked = tcp_cdg_acked,
- .undo_cwnd = tcp_cdg_undo_cwnd,
+ .undo_cwnd = tcp_reno_undo_cwnd,
.ssthresh = tcp_cdg_ssthresh,
.release = tcp_cdg_release,
.init = tcp_cdg_init,
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index fde983f..c2b1744 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -456,7 +456,7 @@ u32 tcp_reno_undo_cwnd(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
- return max(tp->snd_cwnd, tp->snd_ssthresh << 1);
+ return max(tp->snd_cwnd, tp->prior_cwnd);
}
EXPORT_SYMBOL_GPL(tcp_reno_undo_cwnd);
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 57ae5b5..78bfadf 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -83,7 +83,6 @@ MODULE_PARM_DESC(hystart_ack_delta, "spacing between ack's indicating train (mse
struct bictcp {
u32 cnt; /* increase cwnd by 1 after ACKs */
u32 last_max_cwnd; /* last maximum snd_cwnd */
- u32 loss_cwnd; /* congestion window at last loss */
u32 last_cwnd; /* the last snd_cwnd */
u32 last_time; /* time when updated last_cwnd */
u32 bic_origin_point;/* origin point of bic function */
@@ -142,7 +141,6 @@ static void bictcp_init(struct sock *sk)
struct bictcp *ca = inet_csk_ca(sk);
bictcp_reset(ca);
- ca->loss_cwnd = 0;
if (hystart)
bictcp_hystart_reset(sk);
@@ -366,18 +364,9 @@ static u32 bictcp_recalc_ssthresh(struct sock *sk)
else
ca->last_max_cwnd = tp->snd_cwnd;
- ca->loss_cwnd = tp->snd_cwnd;
-
return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U);
}
-static u32 bictcp_undo_cwnd(struct sock *sk)
-{
- struct bictcp *ca = inet_csk_ca(sk);
-
- return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
-}
-
static void bictcp_state(struct sock *sk, u8 new_state)
{
if (new_state == TCP_CA_Loss) {
@@ -470,7 +459,7 @@ static struct tcp_congestion_ops cubictcp __read_mostly = {
.ssthresh = bictcp_recalc_ssthresh,
.cong_avoid = bictcp_cong_avoid,
.set_state = bictcp_state,
- .undo_cwnd = bictcp_undo_cwnd,
+ .undo_cwnd = tcp_reno_undo_cwnd,
.cwnd_event = bictcp_cwnd_event,
.pkts_acked = bictcp_acked,
.owner = THIS_MODULE,
diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c
index 6d9879e..d1c33c9 100644
--- a/net/ipv4/tcp_highspeed.c
+++ b/net/ipv4/tcp_highspeed.c
@@ -94,7 +94,6 @@ static const struct hstcp_aimd_val {
struct hstcp {
u32 ai;
- u32 loss_cwnd;
};
static void hstcp_init(struct sock *sk)
@@ -153,22 +152,14 @@ static u32 hstcp_ssthresh(struct sock *sk)
const struct tcp_sock *tp = tcp_sk(sk);
struct hstcp *ca = inet_csk_ca(sk);
- ca->loss_cwnd = tp->snd_cwnd;
/* Do multiplicative decrease */
return max(tp->snd_cwnd - ((tp->snd_cwnd * hstcp_aimd_vals[ca->ai].md) >> 8), 2U);
}
-static u32 hstcp_cwnd_undo(struct sock *sk)
-{
- const struct hstcp *ca = inet_csk_ca(sk);
-
- return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
-}
-
static struct tcp_congestion_ops tcp_highspeed __read_mostly = {
.init = hstcp_init,
.ssthresh = hstcp_ssthresh,
- .undo_cwnd = hstcp_cwnd_undo,
+ .undo_cwnd = tcp_reno_undo_cwnd,
.cong_avoid = hstcp_cong_avoid,
.owner = THIS_MODULE,
diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c
index 3eb78cd..082d479 100644
--- a/net/ipv4/tcp_htcp.c
+++ b/net/ipv4/tcp_htcp.c
@@ -66,7 +66,6 @@ static inline void htcp_reset(struct htcp *ca)
static u32 htcp_cwnd_undo(struct sock *sk)
{
- const struct tcp_sock *tp = tcp_sk(sk);
struct htcp *ca = inet_csk_ca(sk);
if (ca->undo_last_cong) {
@@ -76,7 +75,7 @@ static u32 htcp_cwnd_undo(struct sock *sk)
ca->undo_last_cong = 0;
}
- return max(tp->snd_cwnd, (tp->snd_ssthresh << 7) / ca->beta);
+ return tcp_reno_undo_cwnd(sk);
}
static inline void measure_rtt(struct sock *sk, u32 srtt)
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index 60352ff..7c84357 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -48,7 +48,6 @@ struct illinois {
u32 end_seq; /* right edge of current RTT */
u32 alpha; /* Additive increase */
u32 beta; /* Muliplicative decrease */
- u32 loss_cwnd; /* cwnd on loss */
u16 acked; /* # packets acked by current ACK */
u8 rtt_above; /* average rtt has gone above threshold */
u8 rtt_low; /* # of rtts measurements below threshold */
@@ -297,18 +296,10 @@ static u32 tcp_illinois_ssthresh(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
struct illinois *ca = inet_csk_ca(sk);
- ca->loss_cwnd = tp->snd_cwnd;
/* Multiplicative decrease */
return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->beta) >> BETA_SHIFT), 2U);
}
-static u32 tcp_illinois_cwnd_undo(struct sock *sk)
-{
- const struct illinois *ca = inet_csk_ca(sk);
-
- return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
-}
-
/* Extract info for Tcp socket info provided via netlink. */
static size_t tcp_illinois_info(struct sock *sk, u32 ext, int *attr,
union tcp_cc_info *info)
@@ -336,7 +327,7 @@ static size_t tcp_illinois_info(struct sock *sk, u32 ext, int *attr,
static struct tcp_congestion_ops tcp_illinois __read_mostly = {
.init = tcp_illinois_init,
.ssthresh = tcp_illinois_ssthresh,
- .undo_cwnd = tcp_illinois_cwnd_undo,
+ .undo_cwnd = tcp_reno_undo_cwnd,
.cong_avoid = tcp_illinois_cong_avoid,
.set_state = tcp_illinois_state,
.get_info = tcp_illinois_info,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 99cdf4c..842ed75 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1950,6 +1950,7 @@ void tcp_enter_loss(struct sock *sk)
!after(tp->high_seq, tp->snd_una) ||
(icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) {
tp->prior_ssthresh = tcp_current_ssthresh(sk);
+ tp->prior_cwnd = tp->snd_cwnd;
tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
tcp_ca_event(sk, CA_EVENT_LOSS);
tcp_init_undo(tp);
diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c
index 6d650ed..1ff7398 100644
--- a/net/ipv4/tcp_nv.c
+++ b/net/ipv4/tcp_nv.c
@@ -86,7 +86,6 @@ struct tcpnv {
* < 0 => less than 1 packet/RTT */
u8 available8;
u16 available16;
- u32 loss_cwnd; /* cwnd at last loss */
u8 nv_allow_cwnd_growth:1, /* whether cwnd can grow */
nv_reset:1, /* whether to reset values */
nv_catchup:1; /* whether we are growing because
@@ -121,7 +120,6 @@ static inline void tcpnv_reset(struct tcpnv *ca, struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
ca->nv_reset = 0;
- ca->loss_cwnd = 0;
ca->nv_no_cong_cnt = 0;
ca->nv_rtt_cnt = 0;
ca->nv_last_rtt = 0;
@@ -177,19 +175,10 @@ static void tcpnv_cong_avoid(struct sock *sk, u32 ack, u32 acked)
static u32 tcpnv_recalc_ssthresh(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
- struct tcpnv *ca = inet_csk_ca(sk);
- ca->loss_cwnd = tp->snd_cwnd;
return max((tp->snd_cwnd * nv_loss_dec_factor) >> 10, 2U);
}
-static u32 tcpnv_undo_cwnd(struct sock *sk)
-{
- struct tcpnv *ca = inet_csk_ca(sk);
-
- return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
-}
-
static void tcpnv_state(struct sock *sk, u8 new_state)
{
struct tcpnv *ca = inet_csk_ca(sk);
@@ -446,7 +435,7 @@ static struct tcp_congestion_ops tcpnv __read_mostly = {
.ssthresh = tcpnv_recalc_ssthresh,
.cong_avoid = tcpnv_cong_avoid,
.set_state = tcpnv_state,
- .undo_cwnd = tcpnv_undo_cwnd,
+ .undo_cwnd = tcp_reno_undo_cwnd,
.pkts_acked = tcpnv_acked,
.get_info = tcpnv_get_info,
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index f212307..addc122 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -15,10 +15,6 @@
#define TCP_SCALABLE_AI_CNT 50U
#define TCP_SCALABLE_MD_SCALE 3
-struct scalable {
- u32 loss_cwnd;
-};
-
static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -36,23 +32,13 @@ static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked)
static u32 tcp_scalable_ssthresh(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
- struct scalable *ca = inet_csk_ca(sk);
-
- ca->loss_cwnd = tp->snd_cwnd;
return max(tp->snd_cwnd - (tp->snd_cwnd>>TCP_SCALABLE_MD_SCALE), 2U);
}
-static u32 tcp_scalable_cwnd_undo(struct sock *sk)
-{
- const struct scalable *ca = inet_csk_ca(sk);
-
- return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
-}
-
static struct tcp_congestion_ops tcp_scalable __read_mostly = {
.ssthresh = tcp_scalable_ssthresh,
- .undo_cwnd = tcp_scalable_cwnd_undo,
+ .undo_cwnd = tcp_reno_undo_cwnd,
.cong_avoid = tcp_scalable_cong_avoid,
.owner = THIS_MODULE,
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index 76005d4..6fcf482 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -30,7 +30,6 @@ struct veno {
u32 basertt; /* the min of all Veno rtt measurements seen (in usec) */
u32 inc; /* decide whether to increase cwnd */
u32 diff; /* calculate the diff rate */
- u32 loss_cwnd; /* cwnd when loss occured */
};
/* There are several situations when we must "re-start" Veno:
@@ -194,7 +193,6 @@ static u32 tcp_veno_ssthresh(struct sock *sk)
const struct tcp_sock *tp = tcp_sk(sk);
struct veno *veno = inet_csk_ca(sk);
- veno->loss_cwnd = tp->snd_cwnd;
if (veno->diff < beta)
/* in "non-congestive state", cut cwnd by 1/5 */
return max(tp->snd_cwnd * 4 / 5, 2U);
@@ -203,17 +201,10 @@ static u32 tcp_veno_ssthresh(struct sock *sk)
return max(tp->snd_cwnd >> 1U, 2U);
}
-static u32 tcp_veno_cwnd_undo(struct sock *sk)
-{
- const struct veno *veno = inet_csk_ca(sk);
-
- return max(tcp_sk(sk)->snd_cwnd, veno->loss_cwnd);
-}
-
static struct tcp_congestion_ops tcp_veno __read_mostly = {
.init = tcp_veno_init,
.ssthresh = tcp_veno_ssthresh,
- .undo_cwnd = tcp_veno_cwnd_undo,
+ .undo_cwnd = tcp_reno_undo_cwnd,
.cong_avoid = tcp_veno_cong_avoid,
.pkts_acked = tcp_veno_pkts_acked,
.set_state = tcp_veno_state,
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index e6ff99c..96e829b2 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -37,7 +37,6 @@ struct yeah {
u32 fast_count;
u32 pkts_acked;
- u32 loss_cwnd;
};
static void tcp_yeah_init(struct sock *sk)
@@ -220,22 +219,14 @@ static u32 tcp_yeah_ssthresh(struct sock *sk)
yeah->fast_count = 0;
yeah->reno_count = max(yeah->reno_count>>1, 2U);
- yeah->loss_cwnd = tp->snd_cwnd;
return max_t(int, tp->snd_cwnd - reduction, 2);
}
-static u32 tcp_yeah_cwnd_undo(struct sock *sk)
-{
- const struct yeah *yeah = inet_csk_ca(sk);
-
- return max(tcp_sk(sk)->snd_cwnd, yeah->loss_cwnd);
-}
-
static struct tcp_congestion_ops tcp_yeah __read_mostly = {
.init = tcp_yeah_init,
.ssthresh = tcp_yeah_ssthresh,
- .undo_cwnd = tcp_yeah_cwnd_undo,
+ .undo_cwnd = tcp_reno_undo_cwnd,
.cong_avoid = tcp_yeah_cong_avoid,
.set_state = tcp_vegas_state,
.cwnd_event = tcp_vegas_cwnd_event,