Commit 57dde7f7 authored by Yuchung Cheng's avatar Yuchung Cheng Committed by David S. Miller
Browse files

tcp: add reordering timer in RACK loss detection 



This patch makes RACK install a reordering timer when it suspects
some packets might be lost, but wants to delay the decision
a little bit to accomodate reordering.

It does not create a new timer but instead repurposes the existing
RTO timer, because both are meant to retransmit packets.
Specifically it arms a timer ICSK_TIME_REO_TIMEOUT when
the RACK timing check fails. The wait time is set to

  RACK.RTT + RACK.reo_wnd - (NOW - Packet.xmit_time) + fudge

This translates to expecting a packet (Packet) should take
(RACK.RTT + RACK.reo_wnd + fudge) to deliver after it was sent.

When there are multiple packets that need a timer, we use one timer
with the maximum timeout. Therefore the timer conservatively uses
the maximum window to expire N packets by one timeout, instead of
N timeouts to expire N packets sent at different times.

The fudge factor is 2 jiffies to ensure when the timer fires, all
the suspected packets would exceed the deadline and be marked lost
by tcp_rack_detect_loss(). It has to be at least 1 jiffy because the
clock may tick between calling icsk_reset_xmit_timer(timeout) and
actually hang the timer. The next jiffy is to lower-bound the timeout
to 2 jiffies when reo_wnd is < 1ms.

When the reordering timer fires (tcp_rack_reo_timeout): If we aren't
in Recovery we'll enter fast recovery and force fast retransmit.
This is very similar to the early retransmit (RFC5827) except RACK
is not constrained to only enter recovery for small outstanding
flights.

Signed-off-by: default avatarYuchung Cheng <ycheng@google.com>
Signed-off-by: default avatarNeal Cardwell <ncardwell@google.com>
Acked-by: default avatarEric Dumazet <edumazet@google.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent deed7be7

include/net/inet_connection_sock.h

+3 −1
Original line number Diff line number Diff line
@@ -144,6 +144,7 @@ struct inet_connection_sock { 
#define ICSK_TIME_PROBE0	3	/* Zero window probe timer */

#define ICSK_TIME_EARLY_RETRANS 4	/* Early retransmit timer */

#define ICSK_TIME_LOSS_PROBE	5	/* Tail loss probe timer */

#define ICSK_TIME_REO_TIMEOUT	6	/* Reordering timer */



static inline struct inet_connection_sock *inet_csk(const struct sock *sk)

{
@@ -234,7 +235,8 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, 
	}



	if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 ||

	    what == ICSK_TIME_EARLY_RETRANS || what ==  ICSK_TIME_LOSS_PROBE) {

	    what == ICSK_TIME_EARLY_RETRANS || what == ICSK_TIME_LOSS_PROBE ||

	    what == ICSK_TIME_REO_TIMEOUT) {

		icsk->icsk_pending = what;

		icsk->icsk_timeout = jiffies + when;

		sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);

include/net/tcp.h

+4 −0
Original line number Diff line number Diff line
@@ -143,6 +143,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); 
#define TCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ/2U)) /* Maximal interval between probes

					                 * for local resources.

					                 */

#define TCP_REO_TIMEOUT_MIN	(2000) /* Min RACK reordering timeout in usec */



#define TCP_KEEPALIVE_TIME	(120*60*HZ)	/* two hours */

#define TCP_KEEPALIVE_PROBES	9		/* Max of 9 keepalive probes	*/
@@ -397,6 +398,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, 
int tcp_child_process(struct sock *parent, struct sock *child,

		      struct sk_buff *skb);

void tcp_enter_loss(struct sock *sk);

void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag);

void tcp_clear_retrans(struct tcp_sock *tp);

void tcp_update_metrics(struct sock *sk);

void tcp_init_metrics(struct sock *sk);
@@ -541,6 +543,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); 
void tcp_retransmit_timer(struct sock *sk);

void tcp_xmit_retransmit_queue(struct sock *);

void tcp_simple_retransmit(struct sock *);

void tcp_enter_recovery(struct sock *sk, bool ece_ack);

int tcp_trim_head(struct sock *, struct sk_buff *, u32);

int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int, gfp_t);
@@ -1867,6 +1870,7 @@ extern void tcp_rack_mark_lost(struct sock *sk, const struct skb_mstamp *now); 
extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked,

			     const struct skb_mstamp *xmit_time,

			     const struct skb_mstamp *ack_time);

extern void tcp_rack_reo_timeout(struct sock *sk);



/*

 * Save and compile IPv4 options, return a pointer to it

net/ipv4/inet_diag.c

+1 −0
Original line number Diff line number Diff line
@@ -216,6 +216,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, 


	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||

	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||

	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||

	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {

		r->idiag_timer = 1;

		r->idiag_retrans = icsk->icsk_retransmits;

net/ipv4/tcp_input.c

+3 −3
Original line number Diff line number Diff line
@@ -2522,8 +2522,7 @@ static void tcp_init_cwnd_reduction(struct sock *sk) 
	tcp_ecn_queue_cwr(tp);

}



static void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked,

			       int flag)

void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag)

{

	struct tcp_sock *tp = tcp_sk(sk);

	int sndcnt = 0;
@@ -2691,7 +2690,7 @@ void tcp_simple_retransmit(struct sock *sk) 
}

EXPORT_SYMBOL(tcp_simple_retransmit);



static void tcp_enter_recovery(struct sock *sk, bool ece_ack)

void tcp_enter_recovery(struct sock *sk, bool ece_ack)

{

	struct tcp_sock *tp = tcp_sk(sk);

	int mib_idx;
@@ -3031,6 +3030,7 @@ void tcp_rearm_rto(struct sock *sk) 
		u32 rto = inet_csk(sk)->icsk_rto;

		/* Offset the time elapsed after installing regular RTO */

		if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||

		    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||

		    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {

			struct sk_buff *skb = tcp_write_queue_head(sk);

			const u32 rto_time_stamp =

net/ipv4/tcp_ipv4.c

+1 −0
Original line number Diff line number Diff line
@@ -2230,6 +2230,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) 


	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||

	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||

	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||

	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {

		timer_active	= 1;

		timer_expires	= icsk->icsk_timeout;

CRA Git | Maintained and supported by SUSTech CRA and CCSE