tcp: Move dynamnic metrics handling into seperate file.
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller
parent
ad7eee98be
commit
4aabd8ef8c
|
|
@ -388,6 +388,8 @@ extern void tcp_enter_frto(struct sock *sk);
|
||||||
extern void tcp_enter_loss(struct sock *sk, int how);
|
extern void tcp_enter_loss(struct sock *sk, int how);
|
||||||
extern void tcp_clear_retrans(struct tcp_sock *tp);
|
extern void tcp_clear_retrans(struct tcp_sock *tp);
|
||||||
extern void tcp_update_metrics(struct sock *sk);
|
extern void tcp_update_metrics(struct sock *sk);
|
||||||
|
extern void tcp_init_metrics(struct sock *sk);
|
||||||
|
extern void tcp_disable_fack(struct tcp_sock *tp);
|
||||||
extern void tcp_close(struct sock *sk, long timeout);
|
extern void tcp_close(struct sock *sk, long timeout);
|
||||||
extern void tcp_init_sock(struct sock *sk);
|
extern void tcp_init_sock(struct sock *sk);
|
||||||
extern unsigned int tcp_poll(struct file * file, struct socket *sock,
|
extern unsigned int tcp_poll(struct file * file, struct socket *sock,
|
||||||
|
|
@ -556,6 +558,8 @@ static inline u32 __tcp_set_rto(const struct tcp_sock *tp)
|
||||||
return (tp->srtt >> 3) + tp->rttvar;
|
return (tp->srtt >> 3) + tp->rttvar;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
extern void tcp_set_rto(struct sock *sk);
|
||||||
|
|
||||||
static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
|
static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
|
||||||
{
|
{
|
||||||
tp->pred_flags = htonl((tp->tcp_header_len << 26) |
|
tp->pred_flags = htonl((tp->tcp_header_len << 26) |
|
||||||
|
|
|
||||||
|
|
@ -7,7 +7,7 @@ obj-y := route.o inetpeer.o protocol.o \
|
||||||
ip_output.o ip_sockglue.o inet_hashtables.o \
|
ip_output.o ip_sockglue.o inet_hashtables.o \
|
||||||
inet_timewait_sock.o inet_connection_sock.o \
|
inet_timewait_sock.o inet_connection_sock.o \
|
||||||
tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \
|
tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \
|
||||||
tcp_minisocks.o tcp_cong.o \
|
tcp_minisocks.o tcp_cong.o tcp_metrics.o \
|
||||||
datagram.o raw.o udp.o udplite.o \
|
datagram.o raw.o udp.o udplite.o \
|
||||||
arp.o icmp.o devinet.o af_inet.o igmp.o \
|
arp.o icmp.o devinet.o af_inet.o igmp.o \
|
||||||
fib_frontend.o fib_semantics.o fib_trie.o \
|
fib_frontend.o fib_semantics.o fib_trie.o \
|
||||||
|
|
|
||||||
|
|
@ -93,7 +93,6 @@ int sysctl_tcp_rfc1337 __read_mostly;
|
||||||
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
|
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
|
||||||
int sysctl_tcp_frto __read_mostly = 2;
|
int sysctl_tcp_frto __read_mostly = 2;
|
||||||
int sysctl_tcp_frto_response __read_mostly;
|
int sysctl_tcp_frto_response __read_mostly;
|
||||||
int sysctl_tcp_nometrics_save __read_mostly;
|
|
||||||
|
|
||||||
int sysctl_tcp_thin_dupack __read_mostly;
|
int sysctl_tcp_thin_dupack __read_mostly;
|
||||||
|
|
||||||
|
|
@ -701,7 +700,7 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
|
||||||
/* Calculate rto without backoff. This is the second half of Van Jacobson's
|
/* Calculate rto without backoff. This is the second half of Van Jacobson's
|
||||||
* routine referred to above.
|
* routine referred to above.
|
||||||
*/
|
*/
|
||||||
static inline void tcp_set_rto(struct sock *sk)
|
void tcp_set_rto(struct sock *sk)
|
||||||
{
|
{
|
||||||
const struct tcp_sock *tp = tcp_sk(sk);
|
const struct tcp_sock *tp = tcp_sk(sk);
|
||||||
/* Old crap is replaced with new one. 8)
|
/* Old crap is replaced with new one. 8)
|
||||||
|
|
@ -728,109 +727,6 @@ static inline void tcp_set_rto(struct sock *sk)
|
||||||
tcp_bound_rto(sk);
|
tcp_bound_rto(sk);
|
||||||
}
|
}
|
||||||
|
|
||||||
/* Save metrics learned by this TCP session.
|
|
||||||
This function is called only, when TCP finishes successfully
|
|
||||||
i.e. when it enters TIME-WAIT or goes from LAST-ACK to CLOSE.
|
|
||||||
*/
|
|
||||||
void tcp_update_metrics(struct sock *sk)
|
|
||||||
{
|
|
||||||
struct tcp_sock *tp = tcp_sk(sk);
|
|
||||||
struct dst_entry *dst = __sk_dst_get(sk);
|
|
||||||
|
|
||||||
if (sysctl_tcp_nometrics_save)
|
|
||||||
return;
|
|
||||||
|
|
||||||
if (dst && (dst->flags & DST_HOST)) {
|
|
||||||
const struct inet_connection_sock *icsk = inet_csk(sk);
|
|
||||||
int m;
|
|
||||||
unsigned long rtt;
|
|
||||||
|
|
||||||
dst_confirm(dst);
|
|
||||||
|
|
||||||
if (icsk->icsk_backoff || !tp->srtt) {
|
|
||||||
/* This session failed to estimate rtt. Why?
|
|
||||||
* Probably, no packets returned in time.
|
|
||||||
* Reset our results.
|
|
||||||
*/
|
|
||||||
if (!(dst_metric_locked(dst, RTAX_RTT)))
|
|
||||||
dst_metric_set(dst, RTAX_RTT, 0);
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
|
|
||||||
rtt = dst_metric_rtt(dst, RTAX_RTT);
|
|
||||||
m = rtt - tp->srtt;
|
|
||||||
|
|
||||||
/* If newly calculated rtt larger than stored one,
|
|
||||||
* store new one. Otherwise, use EWMA. Remember,
|
|
||||||
* rtt overestimation is always better than underestimation.
|
|
||||||
*/
|
|
||||||
if (!(dst_metric_locked(dst, RTAX_RTT))) {
|
|
||||||
if (m <= 0)
|
|
||||||
set_dst_metric_rtt(dst, RTAX_RTT, tp->srtt);
|
|
||||||
else
|
|
||||||
set_dst_metric_rtt(dst, RTAX_RTT, rtt - (m >> 3));
|
|
||||||
}
|
|
||||||
|
|
||||||
if (!(dst_metric_locked(dst, RTAX_RTTVAR))) {
|
|
||||||
unsigned long var;
|
|
||||||
if (m < 0)
|
|
||||||
m = -m;
|
|
||||||
|
|
||||||
/* Scale deviation to rttvar fixed point */
|
|
||||||
m >>= 1;
|
|
||||||
if (m < tp->mdev)
|
|
||||||
m = tp->mdev;
|
|
||||||
|
|
||||||
var = dst_metric_rtt(dst, RTAX_RTTVAR);
|
|
||||||
if (m >= var)
|
|
||||||
var = m;
|
|
||||||
else
|
|
||||||
var -= (var - m) >> 2;
|
|
||||||
|
|
||||||
set_dst_metric_rtt(dst, RTAX_RTTVAR, var);
|
|
||||||
}
|
|
||||||
|
|
||||||
if (tcp_in_initial_slowstart(tp)) {
|
|
||||||
/* Slow start still did not finish. */
|
|
||||||
if (dst_metric(dst, RTAX_SSTHRESH) &&
|
|
||||||
!dst_metric_locked(dst, RTAX_SSTHRESH) &&
|
|
||||||
(tp->snd_cwnd >> 1) > dst_metric(dst, RTAX_SSTHRESH))
|
|
||||||
dst_metric_set(dst, RTAX_SSTHRESH, tp->snd_cwnd >> 1);
|
|
||||||
if (!dst_metric_locked(dst, RTAX_CWND) &&
|
|
||||||
tp->snd_cwnd > dst_metric(dst, RTAX_CWND))
|
|
||||||
dst_metric_set(dst, RTAX_CWND, tp->snd_cwnd);
|
|
||||||
} else if (tp->snd_cwnd > tp->snd_ssthresh &&
|
|
||||||
icsk->icsk_ca_state == TCP_CA_Open) {
|
|
||||||
/* Cong. avoidance phase, cwnd is reliable. */
|
|
||||||
if (!dst_metric_locked(dst, RTAX_SSTHRESH))
|
|
||||||
dst_metric_set(dst, RTAX_SSTHRESH,
|
|
||||||
max(tp->snd_cwnd >> 1, tp->snd_ssthresh));
|
|
||||||
if (!dst_metric_locked(dst, RTAX_CWND))
|
|
||||||
dst_metric_set(dst, RTAX_CWND,
|
|
||||||
(dst_metric(dst, RTAX_CWND) +
|
|
||||||
tp->snd_cwnd) >> 1);
|
|
||||||
} else {
|
|
||||||
/* Else slow start did not finish, cwnd is non-sense,
|
|
||||||
ssthresh may be also invalid.
|
|
||||||
*/
|
|
||||||
if (!dst_metric_locked(dst, RTAX_CWND))
|
|
||||||
dst_metric_set(dst, RTAX_CWND,
|
|
||||||
(dst_metric(dst, RTAX_CWND) +
|
|
||||||
tp->snd_ssthresh) >> 1);
|
|
||||||
if (dst_metric(dst, RTAX_SSTHRESH) &&
|
|
||||||
!dst_metric_locked(dst, RTAX_SSTHRESH) &&
|
|
||||||
tp->snd_ssthresh > dst_metric(dst, RTAX_SSTHRESH))
|
|
||||||
dst_metric_set(dst, RTAX_SSTHRESH, tp->snd_ssthresh);
|
|
||||||
}
|
|
||||||
|
|
||||||
if (!dst_metric_locked(dst, RTAX_REORDERING)) {
|
|
||||||
if (dst_metric(dst, RTAX_REORDERING) < tp->reordering &&
|
|
||||||
tp->reordering != sysctl_tcp_reordering)
|
|
||||||
dst_metric_set(dst, RTAX_REORDERING, tp->reordering);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
__u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst)
|
__u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst)
|
||||||
{
|
{
|
||||||
__u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0);
|
__u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0);
|
||||||
|
|
@ -867,7 +763,7 @@ void tcp_enter_cwr(struct sock *sk, const int set_ssthresh)
|
||||||
* Packet counting of FACK is based on in-order assumptions, therefore TCP
|
* Packet counting of FACK is based on in-order assumptions, therefore TCP
|
||||||
* disables it when reordering is detected
|
* disables it when reordering is detected
|
||||||
*/
|
*/
|
||||||
static void tcp_disable_fack(struct tcp_sock *tp)
|
void tcp_disable_fack(struct tcp_sock *tp)
|
||||||
{
|
{
|
||||||
/* RFC3517 uses different metric in lost marker => reset on change */
|
/* RFC3517 uses different metric in lost marker => reset on change */
|
||||||
if (tcp_is_fack(tp))
|
if (tcp_is_fack(tp))
|
||||||
|
|
@ -881,86 +777,6 @@ static void tcp_dsack_seen(struct tcp_sock *tp)
|
||||||
tp->rx_opt.sack_ok |= TCP_DSACK_SEEN;
|
tp->rx_opt.sack_ok |= TCP_DSACK_SEEN;
|
||||||
}
|
}
|
||||||
|
|
||||||
/* Initialize metrics on socket. */
|
|
||||||
|
|
||||||
static void tcp_init_metrics(struct sock *sk)
|
|
||||||
{
|
|
||||||
struct tcp_sock *tp = tcp_sk(sk);
|
|
||||||
struct dst_entry *dst = __sk_dst_get(sk);
|
|
||||||
|
|
||||||
if (dst == NULL)
|
|
||||||
goto reset;
|
|
||||||
|
|
||||||
dst_confirm(dst);
|
|
||||||
|
|
||||||
if (dst_metric_locked(dst, RTAX_CWND))
|
|
||||||
tp->snd_cwnd_clamp = dst_metric(dst, RTAX_CWND);
|
|
||||||
if (dst_metric(dst, RTAX_SSTHRESH)) {
|
|
||||||
tp->snd_ssthresh = dst_metric(dst, RTAX_SSTHRESH);
|
|
||||||
if (tp->snd_ssthresh > tp->snd_cwnd_clamp)
|
|
||||||
tp->snd_ssthresh = tp->snd_cwnd_clamp;
|
|
||||||
} else {
|
|
||||||
/* ssthresh may have been reduced unnecessarily during.
|
|
||||||
* 3WHS. Restore it back to its initial default.
|
|
||||||
*/
|
|
||||||
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
|
|
||||||
}
|
|
||||||
if (dst_metric(dst, RTAX_REORDERING) &&
|
|
||||||
tp->reordering != dst_metric(dst, RTAX_REORDERING)) {
|
|
||||||
tcp_disable_fack(tp);
|
|
||||||
tcp_disable_early_retrans(tp);
|
|
||||||
tp->reordering = dst_metric(dst, RTAX_REORDERING);
|
|
||||||
}
|
|
||||||
|
|
||||||
if (dst_metric(dst, RTAX_RTT) == 0 || tp->srtt == 0)
|
|
||||||
goto reset;
|
|
||||||
|
|
||||||
/* Initial rtt is determined from SYN,SYN-ACK.
|
|
||||||
* The segment is small and rtt may appear much
|
|
||||||
* less than real one. Use per-dst memory
|
|
||||||
* to make it more realistic.
|
|
||||||
*
|
|
||||||
* A bit of theory. RTT is time passed after "normal" sized packet
|
|
||||||
* is sent until it is ACKed. In normal circumstances sending small
|
|
||||||
* packets force peer to delay ACKs and calculation is correct too.
|
|
||||||
* The algorithm is adaptive and, provided we follow specs, it
|
|
||||||
* NEVER underestimate RTT. BUT! If peer tries to make some clever
|
|
||||||
* tricks sort of "quick acks" for time long enough to decrease RTT
|
|
||||||
* to low value, and then abruptly stops to do it and starts to delay
|
|
||||||
* ACKs, wait for troubles.
|
|
||||||
*/
|
|
||||||
if (dst_metric_rtt(dst, RTAX_RTT) > tp->srtt) {
|
|
||||||
tp->srtt = dst_metric_rtt(dst, RTAX_RTT);
|
|
||||||
tp->rtt_seq = tp->snd_nxt;
|
|
||||||
}
|
|
||||||
if (dst_metric_rtt(dst, RTAX_RTTVAR) > tp->mdev) {
|
|
||||||
tp->mdev = dst_metric_rtt(dst, RTAX_RTTVAR);
|
|
||||||
tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
|
|
||||||
}
|
|
||||||
tcp_set_rto(sk);
|
|
||||||
reset:
|
|
||||||
if (tp->srtt == 0) {
|
|
||||||
/* RFC6298: 5.7 We've failed to get a valid RTT sample from
|
|
||||||
* 3WHS. This is most likely due to retransmission,
|
|
||||||
* including spurious one. Reset the RTO back to 3secs
|
|
||||||
* from the more aggressive 1sec to avoid more spurious
|
|
||||||
* retransmission.
|
|
||||||
*/
|
|
||||||
tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK;
|
|
||||||
inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK;
|
|
||||||
}
|
|
||||||
/* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been
|
|
||||||
* retransmitted. In light of RFC6298 more aggressive 1sec
|
|
||||||
* initRTO, we only reset cwnd when more than 1 SYN/SYN-ACK
|
|
||||||
* retransmission has occurred.
|
|
||||||
*/
|
|
||||||
if (tp->total_retrans > 1)
|
|
||||||
tp->snd_cwnd = 1;
|
|
||||||
else
|
|
||||||
tp->snd_cwnd = tcp_init_cwnd(tp, dst);
|
|
||||||
tp->snd_cwnd_stamp = tcp_time_stamp;
|
|
||||||
}
|
|
||||||
|
|
||||||
static void tcp_update_reordering(struct sock *sk, const int metric,
|
static void tcp_update_reordering(struct sock *sk, const int metric,
|
||||||
const int ts)
|
const int ts)
|
||||||
{
|
{
|
||||||
|
|
|
||||||
|
|
@ -0,0 +1,192 @@
|
||||||
|
#include <linux/cache.h>
|
||||||
|
#include <linux/tcp.h>
|
||||||
|
|
||||||
|
#include <net/inet_connection_sock.h>
|
||||||
|
#include <net/sock.h>
|
||||||
|
#include <net/dst.h>
|
||||||
|
#include <net/tcp.h>
|
||||||
|
|
||||||
|
int sysctl_tcp_nometrics_save __read_mostly;
|
||||||
|
|
||||||
|
/* Save metrics learned by this TCP session. This function is called
|
||||||
|
* only, when TCP finishes successfully i.e. when it enters TIME-WAIT
|
||||||
|
* or goes from LAST-ACK to CLOSE.
|
||||||
|
*/
|
||||||
|
void tcp_update_metrics(struct sock *sk)
|
||||||
|
{
|
||||||
|
struct tcp_sock *tp = tcp_sk(sk);
|
||||||
|
struct dst_entry *dst = __sk_dst_get(sk);
|
||||||
|
|
||||||
|
if (sysctl_tcp_nometrics_save)
|
||||||
|
return;
|
||||||
|
|
||||||
|
if (dst && (dst->flags & DST_HOST)) {
|
||||||
|
const struct inet_connection_sock *icsk = inet_csk(sk);
|
||||||
|
int m;
|
||||||
|
unsigned long rtt;
|
||||||
|
|
||||||
|
dst_confirm(dst);
|
||||||
|
|
||||||
|
if (icsk->icsk_backoff || !tp->srtt) {
|
||||||
|
/* This session failed to estimate rtt. Why?
|
||||||
|
* Probably, no packets returned in time.
|
||||||
|
* Reset our results.
|
||||||
|
*/
|
||||||
|
if (!(dst_metric_locked(dst, RTAX_RTT)))
|
||||||
|
dst_metric_set(dst, RTAX_RTT, 0);
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
|
||||||
|
rtt = dst_metric_rtt(dst, RTAX_RTT);
|
||||||
|
m = rtt - tp->srtt;
|
||||||
|
|
||||||
|
/* If newly calculated rtt larger than stored one,
|
||||||
|
* store new one. Otherwise, use EWMA. Remember,
|
||||||
|
* rtt overestimation is always better than underestimation.
|
||||||
|
*/
|
||||||
|
if (!(dst_metric_locked(dst, RTAX_RTT))) {
|
||||||
|
if (m <= 0)
|
||||||
|
set_dst_metric_rtt(dst, RTAX_RTT, tp->srtt);
|
||||||
|
else
|
||||||
|
set_dst_metric_rtt(dst, RTAX_RTT, rtt - (m >> 3));
|
||||||
|
}
|
||||||
|
|
||||||
|
if (!(dst_metric_locked(dst, RTAX_RTTVAR))) {
|
||||||
|
unsigned long var;
|
||||||
|
if (m < 0)
|
||||||
|
m = -m;
|
||||||
|
|
||||||
|
/* Scale deviation to rttvar fixed point */
|
||||||
|
m >>= 1;
|
||||||
|
if (m < tp->mdev)
|
||||||
|
m = tp->mdev;
|
||||||
|
|
||||||
|
var = dst_metric_rtt(dst, RTAX_RTTVAR);
|
||||||
|
if (m >= var)
|
||||||
|
var = m;
|
||||||
|
else
|
||||||
|
var -= (var - m) >> 2;
|
||||||
|
|
||||||
|
set_dst_metric_rtt(dst, RTAX_RTTVAR, var);
|
||||||
|
}
|
||||||
|
|
||||||
|
if (tcp_in_initial_slowstart(tp)) {
|
||||||
|
/* Slow start still did not finish. */
|
||||||
|
if (dst_metric(dst, RTAX_SSTHRESH) &&
|
||||||
|
!dst_metric_locked(dst, RTAX_SSTHRESH) &&
|
||||||
|
(tp->snd_cwnd >> 1) > dst_metric(dst, RTAX_SSTHRESH))
|
||||||
|
dst_metric_set(dst, RTAX_SSTHRESH, tp->snd_cwnd >> 1);
|
||||||
|
if (!dst_metric_locked(dst, RTAX_CWND) &&
|
||||||
|
tp->snd_cwnd > dst_metric(dst, RTAX_CWND))
|
||||||
|
dst_metric_set(dst, RTAX_CWND, tp->snd_cwnd);
|
||||||
|
} else if (tp->snd_cwnd > tp->snd_ssthresh &&
|
||||||
|
icsk->icsk_ca_state == TCP_CA_Open) {
|
||||||
|
/* Cong. avoidance phase, cwnd is reliable. */
|
||||||
|
if (!dst_metric_locked(dst, RTAX_SSTHRESH))
|
||||||
|
dst_metric_set(dst, RTAX_SSTHRESH,
|
||||||
|
max(tp->snd_cwnd >> 1, tp->snd_ssthresh));
|
||||||
|
if (!dst_metric_locked(dst, RTAX_CWND))
|
||||||
|
dst_metric_set(dst, RTAX_CWND,
|
||||||
|
(dst_metric(dst, RTAX_CWND) +
|
||||||
|
tp->snd_cwnd) >> 1);
|
||||||
|
} else {
|
||||||
|
/* Else slow start did not finish, cwnd is non-sense,
|
||||||
|
ssthresh may be also invalid.
|
||||||
|
*/
|
||||||
|
if (!dst_metric_locked(dst, RTAX_CWND))
|
||||||
|
dst_metric_set(dst, RTAX_CWND,
|
||||||
|
(dst_metric(dst, RTAX_CWND) +
|
||||||
|
tp->snd_ssthresh) >> 1);
|
||||||
|
if (dst_metric(dst, RTAX_SSTHRESH) &&
|
||||||
|
!dst_metric_locked(dst, RTAX_SSTHRESH) &&
|
||||||
|
tp->snd_ssthresh > dst_metric(dst, RTAX_SSTHRESH))
|
||||||
|
dst_metric_set(dst, RTAX_SSTHRESH, tp->snd_ssthresh);
|
||||||
|
}
|
||||||
|
|
||||||
|
if (!dst_metric_locked(dst, RTAX_REORDERING)) {
|
||||||
|
if (dst_metric(dst, RTAX_REORDERING) < tp->reordering &&
|
||||||
|
tp->reordering != sysctl_tcp_reordering)
|
||||||
|
dst_metric_set(dst, RTAX_REORDERING, tp->reordering);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Initialize metrics on socket. */
|
||||||
|
|
||||||
|
void tcp_init_metrics(struct sock *sk)
|
||||||
|
{
|
||||||
|
struct tcp_sock *tp = tcp_sk(sk);
|
||||||
|
struct dst_entry *dst = __sk_dst_get(sk);
|
||||||
|
|
||||||
|
if (dst == NULL)
|
||||||
|
goto reset;
|
||||||
|
|
||||||
|
dst_confirm(dst);
|
||||||
|
|
||||||
|
if (dst_metric_locked(dst, RTAX_CWND))
|
||||||
|
tp->snd_cwnd_clamp = dst_metric(dst, RTAX_CWND);
|
||||||
|
if (dst_metric(dst, RTAX_SSTHRESH)) {
|
||||||
|
tp->snd_ssthresh = dst_metric(dst, RTAX_SSTHRESH);
|
||||||
|
if (tp->snd_ssthresh > tp->snd_cwnd_clamp)
|
||||||
|
tp->snd_ssthresh = tp->snd_cwnd_clamp;
|
||||||
|
} else {
|
||||||
|
/* ssthresh may have been reduced unnecessarily during.
|
||||||
|
* 3WHS. Restore it back to its initial default.
|
||||||
|
*/
|
||||||
|
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
|
||||||
|
}
|
||||||
|
if (dst_metric(dst, RTAX_REORDERING) &&
|
||||||
|
tp->reordering != dst_metric(dst, RTAX_REORDERING)) {
|
||||||
|
tcp_disable_fack(tp);
|
||||||
|
tcp_disable_early_retrans(tp);
|
||||||
|
tp->reordering = dst_metric(dst, RTAX_REORDERING);
|
||||||
|
}
|
||||||
|
|
||||||
|
if (dst_metric(dst, RTAX_RTT) == 0 || tp->srtt == 0)
|
||||||
|
goto reset;
|
||||||
|
|
||||||
|
/* Initial rtt is determined from SYN,SYN-ACK.
|
||||||
|
* The segment is small and rtt may appear much
|
||||||
|
* less than real one. Use per-dst memory
|
||||||
|
* to make it more realistic.
|
||||||
|
*
|
||||||
|
* A bit of theory. RTT is time passed after "normal" sized packet
|
||||||
|
* is sent until it is ACKed. In normal circumstances sending small
|
||||||
|
* packets force peer to delay ACKs and calculation is correct too.
|
||||||
|
* The algorithm is adaptive and, provided we follow specs, it
|
||||||
|
* NEVER underestimate RTT. BUT! If peer tries to make some clever
|
||||||
|
* tricks sort of "quick acks" for time long enough to decrease RTT
|
||||||
|
* to low value, and then abruptly stops to do it and starts to delay
|
||||||
|
* ACKs, wait for troubles.
|
||||||
|
*/
|
||||||
|
if (dst_metric_rtt(dst, RTAX_RTT) > tp->srtt) {
|
||||||
|
tp->srtt = dst_metric_rtt(dst, RTAX_RTT);
|
||||||
|
tp->rtt_seq = tp->snd_nxt;
|
||||||
|
}
|
||||||
|
if (dst_metric_rtt(dst, RTAX_RTTVAR) > tp->mdev) {
|
||||||
|
tp->mdev = dst_metric_rtt(dst, RTAX_RTTVAR);
|
||||||
|
tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
|
||||||
|
}
|
||||||
|
tcp_set_rto(sk);
|
||||||
|
reset:
|
||||||
|
if (tp->srtt == 0) {
|
||||||
|
/* RFC6298: 5.7 We've failed to get a valid RTT sample from
|
||||||
|
* 3WHS. This is most likely due to retransmission,
|
||||||
|
* including spurious one. Reset the RTO back to 3secs
|
||||||
|
* from the more aggressive 1sec to avoid more spurious
|
||||||
|
* retransmission.
|
||||||
|
*/
|
||||||
|
tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK;
|
||||||
|
inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK;
|
||||||
|
}
|
||||||
|
/* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been
|
||||||
|
* retransmitted. In light of RFC6298 more aggressive 1sec
|
||||||
|
* initRTO, we only reset cwnd when more than 1 SYN/SYN-ACK
|
||||||
|
* retransmission has occurred.
|
||||||
|
*/
|
||||||
|
if (tp->total_retrans > 1)
|
||||||
|
tp->snd_cwnd = 1;
|
||||||
|
else
|
||||||
|
tp->snd_cwnd = tcp_init_cwnd(tp, dst);
|
||||||
|
tp->snd_cwnd_stamp = tcp_time_stamp;
|
||||||
|
}
|
||||||
Loading…
Reference in New Issue