blob: 38cb25b48bf3b9961e1ba737db9ea194c448c3b1 [file] [log] [blame]
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Implementation of the Transmission Control Protocol(TCP).
*
* Version: $Id: tcp_input.c,v 1.243 2002/02/01 22:01:04 davem Exp $
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
* Corey Minyard <wf-rch!minyard@relay.EU.net>
* Florian La Roche, <flla@stud.uni-sb.de>
* Charles Hedrick, <hedrick@klinzhai.rutgers.edu>
* Linus Torvalds, <torvalds@cs.helsinki.fi>
* Alan Cox, <gw4pts@gw4pts.ampr.org>
* Matthew Dillon, <dillon@apollo.west.oic.com>
* Arnt Gulbrandsen, <agulbra@nvg.unit.no>
* Jorge Cwik, <jorge@laser.satlink.net>
*/
/*
* Changes:
* Pedro Roque : Fast Retransmit/Recovery.
* Two receive queues.
* Retransmit queue handled by TCP.
* Better retransmit timer handling.
* New congestion avoidance.
* Header prediction.
* Variable renaming.
*
* Eric : Fast Retransmit.
* Randy Scott : MSS option defines.
* Eric Schenk : Fixes to slow start algorithm.
* Eric Schenk : Yet another double ACK bug.
* Eric Schenk : Delayed ACK bug fixes.
* Eric Schenk : Floyd style fast retrans war avoidance.
* David S. Miller : Don't allow zero congestion window.
* Eric Schenk : Fix retransmitter so that it sends
* next packet on ack of previous packet.
* Andi Kleen : Moved open_request checking here
* and process RSTs for open_requests.
* Andi Kleen : Better prune_queue, and other fixes.
* Andrey Savochkin: Fix RTT measurements in the presence of
* timestamps.
* Andrey Savochkin: Check sequence numbers correctly when
* removing SACKs due to in sequence incoming
* data segments.
* Andi Kleen: Make sure we never ack data there is not
* enough room for. Also make this condition
* a fatal error if it might still happen.
* Andi Kleen: Add tcp_measure_rcv_mss to make
* connections with MSS<min(MTU,ann. MSS)
* work without delayed acks.
* Andi Kleen: Process packets with PSH set in the
* fast path.
* J Hadi Salim: ECN support
* Andrei Gurtov,
* Pasi Sarolahti,
* Panu Kuhlberg: Experimental audit of TCP (re)transmission
* engine. Lots of bugs are found.
* Pasi Sarolahti: F-RTO for dealing with spurious RTOs
*/
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <net/tcp.h>
#include <net/inet_common.h>
#include <linux/ipsec.h>
#include <asm/unaligned.h>
#include <net/netdma.h>
int sysctl_tcp_timestamps __read_mostly = 1;
int sysctl_tcp_window_scaling __read_mostly = 1;
int sysctl_tcp_sack __read_mostly = 1;
int sysctl_tcp_fack __read_mostly = 1;
int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH;
int sysctl_tcp_ecn __read_mostly;
int sysctl_tcp_dsack __read_mostly = 1;
int sysctl_tcp_app_win __read_mostly = 31;
int sysctl_tcp_adv_win_scale __read_mostly = 2;
int sysctl_tcp_stdurg __read_mostly;
int sysctl_tcp_rfc1337 __read_mostly;
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
int sysctl_tcp_frto __read_mostly;
int sysctl_tcp_frto_response __read_mostly;
int sysctl_tcp_nometrics_save __read_mostly;
int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
int sysctl_tcp_abc __read_mostly;
#define FLAG_DATA 0x01 /* Incoming frame contained data. */
#define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */
#define FLAG_DATA_ACKED 0x04 /* This ACK acknowledged new data. */
#define FLAG_RETRANS_DATA_ACKED 0x08 /* "" "" some of which was retransmitted. */
#define FLAG_SYN_ACKED 0x10 /* This ACK acknowledged SYN. */
#define FLAG_DATA_SACKED 0x20 /* New SACK. */
#define FLAG_ECE 0x40 /* ECE in this ACK */
#define FLAG_DATA_LOST 0x80 /* SACK detected data lossage. */
#define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/
#define FLAG_ONLY_ORIG_SACKED 0x200 /* SACKs only non-rexmit sent before RTO */
#define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED)
#define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
#define FLAG_CA_ALERT (FLAG_DATA_SACKED|FLAG_ECE)
#define FLAG_FORWARD_PROGRESS (FLAG_ACKED|FLAG_DATA_SACKED)
#define IsReno(tp) ((tp)->rx_opt.sack_ok == 0)
#define IsFack(tp) ((tp)->rx_opt.sack_ok & 2)
#define IsDSack(tp) ((tp)->rx_opt.sack_ok & 4)
#define IsSackFrto() (sysctl_tcp_frto == 0x2)
#define TCP_REMNANT (TCP_FLAG_FIN|TCP_FLAG_URG|TCP_FLAG_SYN|TCP_FLAG_PSH)
/* Adapt the MSS value used to make delayed ack decision to the
* real world.
*/
static void tcp_measure_rcv_mss(struct sock *sk,
const struct sk_buff *skb)
{
struct inet_connection_sock *icsk = inet_csk(sk);
const unsigned int lss = icsk->icsk_ack.last_seg_size;
unsigned int len;
icsk->icsk_ack.last_seg_size = 0;
/* skb->len may jitter because of SACKs, even if peer
* sends good full-sized frames.
*/
len = skb_shinfo(skb)->gso_size ?: skb->len;
if (len >= icsk->icsk_ack.rcv_mss) {
icsk->icsk_ack.rcv_mss = len;
} else {
/* Otherwise, we make more careful check taking into account,
* that SACKs block is variable.
*
* "len" is invariant segment length, including TCP header.
*/
len += skb->data - skb_transport_header(skb);
if (len >= TCP_MIN_RCVMSS + sizeof(struct tcphdr) ||
/* If PSH is not set, packet should be
* full sized, provided peer TCP is not badly broken.
* This observation (if it is correct 8)) allows
* to handle super-low mtu links fairly.
*/
(len >= TCP_MIN_MSS + sizeof(struct tcphdr) &&
!(tcp_flag_word(tcp_hdr(skb)) & TCP_REMNANT))) {
/* Subtract also invariant (if peer is RFC compliant),
* tcp header plus fixed timestamp option length.
* Resulting "len" is MSS free of SACK jitter.
*/
len -= tcp_sk(sk)->tcp_header_len;
icsk->icsk_ack.last_seg_size = len;
if (len == lss) {
icsk->icsk_ack.rcv_mss = len;
return;
}
}
if (icsk->icsk_ack.pending & ICSK_ACK_PUSHED)
icsk->icsk_ack.pending |= ICSK_ACK_PUSHED2;
icsk->icsk_ack.pending |= ICSK_ACK_PUSHED;
}
}
static void tcp_incr_quickack(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
unsigned quickacks = tcp_sk(sk)->rcv_wnd / (2 * icsk->icsk_ack.rcv_mss);
if (quickacks==0)
quickacks=2;
if (quickacks > icsk->icsk_ack.quick)
icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS);
}
void tcp_enter_quickack_mode(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
tcp_incr_quickack(sk);
icsk->icsk_ack.pingpong = 0;
icsk->icsk_ack.ato = TCP_ATO_MIN;
}
/* Send ACKs quickly, if "quick" count is not exhausted
* and the session is not interactive.
*/
static inline int tcp_in_quickack_mode(const struct sock *sk)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
return icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong;
}
/* Buffer size and advertised window tuning.
*
* 1. Tuning sk->sk_sndbuf, when connection enters established state.
*/
static void tcp_fixup_sndbuf(struct sock *sk)
{
int sndmem = tcp_sk(sk)->rx_opt.mss_clamp + MAX_TCP_HEADER + 16 +
sizeof(struct sk_buff);
if (sk->sk_sndbuf < 3 * sndmem)
sk->sk_sndbuf = min(3 * sndmem, sysctl_tcp_wmem[2]);
}
/* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
*
* All tcp_full_space() is split to two parts: "network" buffer, allocated
* forward and advertised in receiver window (tp->rcv_wnd) and
* "application buffer", required to isolate scheduling/application
* latencies from network.
* window_clamp is maximal advertised window. It can be less than
* tcp_full_space(), in this case tcp_full_space() - window_clamp
* is reserved for "application" buffer. The less window_clamp is
* the smoother our behaviour from viewpoint of network, but the lower
* throughput and the higher sensitivity of the connection to losses. 8)
*
* rcv_ssthresh is more strict window_clamp used at "slow start"
* phase to predict further behaviour of this connection.
* It is used for two goals:
* - to enforce header prediction at sender, even when application
* requires some significant "application buffer". It is check #1.
* - to prevent pruning of receive queue because of misprediction
* of receiver window. Check #2.
*
* The scheme does not work when sender sends good segments opening
* window and then starts to feed us spaghetti. But it should work
* in common situations. Otherwise, we have to rely on queue collapsing.
*/
/* Slow part of check#2. */
static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
/* Optimize this! */
int truesize = tcp_win_from_space(skb->truesize)/2;
int window = tcp_win_from_space(sysctl_tcp_rmem[2])/2;
while (tp->rcv_ssthresh <= window) {
if (truesize <= skb->len)
return 2 * inet_csk(sk)->icsk_ack.rcv_mss;
truesize >>= 1;
window >>= 1;
}
return 0;
}
static void tcp_grow_window(struct sock *sk,
struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
/* Check #1 */
if (tp->rcv_ssthresh < tp->window_clamp &&
(int)tp->rcv_ssthresh < tcp_space(sk) &&
!tcp_memory_pressure) {
int incr;
/* Check #2. Increase window, if skb with such overhead
* will fit to rcvbuf in future.
*/
if (tcp_win_from_space(skb->truesize) <= skb->len)
incr = 2*tp->advmss;
else
incr = __tcp_grow_window(sk, skb);
if (incr) {
tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr, tp->window_clamp);
inet_csk(sk)->icsk_ack.quick |= 1;
}
}
}
/* 3. Tuning rcvbuf, when connection enters established state. */
static void tcp_fixup_rcvbuf(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
int rcvmem = tp->advmss + MAX_TCP_HEADER + 16 + sizeof(struct sk_buff);
/* Try to select rcvbuf so that 4 mss-sized segments
* will fit to window and corresponding skbs will fit to our rcvbuf.
* (was 3; 4 is minimum to allow fast retransmit to work.)
*/
while (tcp_win_from_space(rcvmem) < tp->advmss)
rcvmem += 128;
if (sk->sk_rcvbuf < 4 * rcvmem)
sk->sk_rcvbuf = min(4 * rcvmem, sysctl_tcp_rmem[2]);
}
/* 4. Try to fixup all. It is made immediately after connection enters
* established state.
*/
static void tcp_init_buffer_space(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
int maxwin;
if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK))
tcp_fixup_rcvbuf(sk);
if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK))
tcp_fixup_sndbuf(sk);
tp->rcvq_space.space = tp->rcv_wnd;
maxwin = tcp_full_space(sk);
if (tp->window_clamp >= maxwin) {
tp->window_clamp = maxwin;
if (sysctl_tcp_app_win && maxwin > 4 * tp->advmss)
tp->window_clamp = max(maxwin -
(maxwin >> sysctl_tcp_app_win),
4 * tp->advmss);
}
/* Force reservation of one segment. */
if (sysctl_tcp_app_win &&
tp->window_clamp > 2 * tp->advmss &&
tp->window_clamp + tp->advmss > maxwin)
tp->window_clamp = max(2 * tp->advmss, maxwin - tp->advmss);
tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp);
tp->snd_cwnd_stamp = tcp_time_stamp;
}
/* 5. Recalculate window clamp after socket hit its memory bounds. */
static void tcp_clamp_window(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
icsk->icsk_ack.quick = 0;
if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
!tcp_memory_pressure &&
atomic_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) {
sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
sysctl_tcp_rmem[2]);
}
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
tp->rcv_ssthresh = min(tp->window_clamp, 2U*tp->advmss);
}
/* Initialize RCV_MSS value.
* RCV_MSS is an our guess about MSS used by the peer.
* We haven't any direct information about the MSS.
* It's better to underestimate the RCV_MSS rather than overestimate.
* Overestimations make us ACKing less frequently than needed.
* Underestimations are more easy to detect and fix by tcp_measure_rcv_mss().
*/
void tcp_initialize_rcv_mss(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache);
hint = min(hint, tp->rcv_wnd/2);
hint = min(hint, TCP_MIN_RCVMSS);
hint = max(hint, TCP_MIN_MSS);
inet_csk(sk)->icsk_ack.rcv_mss = hint;
}
/* Receiver "autotuning" code.
*
* The algorithm for RTT estimation w/o timestamps is based on
* Dynamic Right-Sizing (DRS) by Wu Feng and Mike Fisk of LANL.
* <http://www.lanl.gov/radiant/website/pubs/drs/lacsi2001.ps>
*
* More detail on this code can be found at
* <http://www.psc.edu/~jheffner/senior_thesis.ps>,
* though this reference is out of date. A new paper
* is pending.
*/
static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
{
u32 new_sample = tp->rcv_rtt_est.rtt;
long m = sample;
if (m == 0)
m = 1;
if (new_sample != 0) {
/* If we sample in larger samples in the non-timestamp
* case, we could grossly overestimate the RTT especially
* with chatty applications or bulk transfer apps which
* are stalled on filesystem I/O.
*
* Also, since we are only going for a minimum in the
* non-timestamp case, we do not smooth things out
* else with timestamps disabled convergence takes too
* long.
*/
if (!win_dep) {
m -= (new_sample >> 3);
new_sample += m;
} else if (m < new_sample)
new_sample = m << 3;
} else {
/* No previous measure. */
new_sample = m << 3;
}
if (tp->rcv_rtt_est.rtt != new_sample)
tp->rcv_rtt_est.rtt = new_sample;
}
static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp)
{
if (tp->rcv_rtt_est.time == 0)
goto new_measure;
if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq))
return;
tcp_rcv_rtt_update(tp,
jiffies - tp->rcv_rtt_est.time,
1);
new_measure:
tp->rcv_rtt_est.seq = tp->rcv_nxt + tp->rcv_wnd;
tp->rcv_rtt_est.time = tcp_time_stamp;
}
static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, const struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
if (tp->rx_opt.rcv_tsecr &&
(TCP_SKB_CB(skb)->end_seq -
TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss))
tcp_rcv_rtt_update(tp, tcp_time_stamp - tp->rx_opt.rcv_tsecr, 0);
}
/*
* This function should be called every time data is copied to user space.
* It calculates the appropriate TCP receive buffer space.
*/
void tcp_rcv_space_adjust(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
int time;
int space;
if (tp->rcvq_space.time == 0)
goto new_measure;
time = tcp_time_stamp - tp->rcvq_space.time;
if (time < (tp->rcv_rtt_est.rtt >> 3) ||
tp->rcv_rtt_est.rtt == 0)
return;
space = 2 * (tp->copied_seq - tp->rcvq_space.seq);
space = max(tp->rcvq_space.space, space);
if (tp->rcvq_space.space != space) {
int rcvmem;
tp->rcvq_space.space = space;
if (sysctl_tcp_moderate_rcvbuf &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
int new_clamp = space;
/* Receive space grows, normalize in order to
* take into account packet headers and sk_buff
* structure overhead.
*/
space /= tp->advmss;
if (!space)
space = 1;
rcvmem = (tp->advmss + MAX_TCP_HEADER +
16 + sizeof(struct sk_buff));
while (tcp_win_from_space(rcvmem) < tp->advmss)
rcvmem += 128;
space *= rcvmem;
space = min(space, sysctl_tcp_rmem[2]);
if (space > sk->sk_rcvbuf) {
sk->sk_rcvbuf = space;
/* Make the window clamp follow along. */
tp->window_clamp = new_clamp;
}
}
}
new_measure:
tp->rcvq_space.seq = tp->copied_seq;
tp->rcvq_space.time = tcp_time_stamp;
}
/* There is something which you must keep in mind when you analyze the
* behavior of the tp->ato delayed ack timeout interval. When a
* connection starts up, we want to ack as quickly as possible. The
* problem is that "good" TCP's do slow start at the beginning of data
* transmission. The means that until we send the first few ACK's the
* sender will sit on his end and only queue most of his data, because
* he can only send snd_cwnd unacked packets at any given time. For
* each ACK we send, he increments snd_cwnd and transmits more of his
* queue. -DaveM
*/
static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
u32 now;
inet_csk_schedule_ack(sk);
tcp_measure_rcv_mss(sk, skb);
tcp_rcv_rtt_measure(tp);
now = tcp_time_stamp;
if (!icsk->icsk_ack.ato) {
/* The _first_ data packet received, initialize
* delayed ACK engine.
*/
tcp_incr_quickack(sk);
icsk->icsk_ack.ato = TCP_ATO_MIN;
} else {
int m = now - icsk->icsk_ack.lrcvtime;
if (m <= TCP_ATO_MIN/2) {
/* The fastest case is the first. */
icsk->icsk_ack.ato = (icsk->icsk_ack.ato >> 1) + TCP_ATO_MIN / 2;
} else if (m < icsk->icsk_ack.ato) {
icsk->icsk_ack.ato = (icsk->icsk_ack.ato >> 1) + m;
if (icsk->icsk_ack.ato > icsk->icsk_rto)
icsk->icsk_ack.ato = icsk->icsk_rto;
} else if (m > icsk->icsk_rto) {
/* Too long gap. Apparently sender failed to
* restart window, so that we send ACKs quickly.
*/
tcp_incr_quickack(sk);
sk_stream_mem_reclaim(sk);
}
}
icsk->icsk_ack.lrcvtime = now;
TCP_ECN_check_ce(tp, skb);
if (skb->len >= 128)
tcp_grow_window(sk, skb);
}
/* Called to compute a smoothed rtt estimate. The data fed to this
* routine either comes from timestamps, or from segments that were
* known _not_ to have been retransmitted [see Karn/Partridge
* Proceedings SIGCOMM 87]. The algorithm is from the SIGCOMM 88
* piece by Van Jacobson.
* NOTE: the next three routines used to be one big routine.
* To save cycles in the RFC 1323 implementation it was better to break
* it up into three procedures. -- erics
*/
static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
{
struct tcp_sock *tp = tcp_sk(sk);
long m = mrtt; /* RTT */
/* The following amusing code comes from Jacobson's
* article in SIGCOMM '88. Note that rtt and mdev
* are scaled versions of rtt and mean deviation.
* This is designed to be as fast as possible
* m stands for "measurement".
*
* On a 1990 paper the rto value is changed to:
* RTO = rtt + 4 * mdev
*
* Funny. This algorithm seems to be very broken.
* These formulae increase RTO, when it should be decreased, increase
* too slowly, when it should be increased quickly, decrease too quickly
* etc. I guess in BSD RTO takes ONE value, so that it is absolutely
* does not matter how to _calculate_ it. Seems, it was trap
* that VJ failed to avoid. 8)
*/
if (m == 0)
m = 1;
if (tp->srtt != 0) {
m -= (tp->srtt >> 3); /* m is now error in rtt est */
tp->srtt += m; /* rtt = 7/8 rtt + 1/8 new */
if (m < 0) {
m = -m; /* m is now abs(error) */
m -= (tp->mdev >> 2); /* similar update on mdev */
/* This is similar to one of Eifel findings.
* Eifel blocks mdev updates when rtt decreases.
* This solution is a bit different: we use finer gain
* for mdev in this case (alpha*beta).
* Like Eifel it also prevents growth of rto,
* but also it limits too fast rto decreases,
* happening in pure Eifel.
*/
if (m > 0)
m >>= 3;
} else {
m -= (tp->mdev >> 2); /* similar update on mdev */
}
tp->mdev += m; /* mdev = 3/4 mdev + 1/4 new */
if (tp->mdev > tp->mdev_max) {
tp->mdev_max = tp->mdev;
if (tp->mdev_max > tp->rttvar)
tp->rttvar = tp->mdev_max;
}
if (after(tp->snd_una, tp->rtt_seq)) {
if (tp->mdev_max < tp->rttvar)
tp->rttvar -= (tp->rttvar-tp->mdev_max)>>2;
tp->rtt_seq = tp->snd_nxt;
tp->mdev_max = TCP_RTO_MIN;
}
} else {
/* no previous measure. */
tp->srtt = m<<3; /* take the measured time to be rtt */
tp->mdev = m<<1; /* make sure rto = 3*rtt */
tp->mdev_max = tp->rttvar = max(tp->mdev, TCP_RTO_MIN);
tp->rtt_seq = tp->snd_nxt;
}
}
/* Calculate rto without backoff. This is the second half of Van Jacobson's
* routine referred to above.
*/
static inline void tcp_set_rto(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
/* Old crap is replaced with new one. 8)
*
* More seriously:
* 1. If rtt variance happened to be less 50msec, it is hallucination.
* It cannot be less due to utterly erratic ACK generation made
* at least by solaris and freebsd. "Erratic ACKs" has _nothing_
* to do with delayed acks, because at cwnd>2 true delack timeout
* is invisible. Actually, Linux-2.4 also generates erratic
* ACKs in some circumstances.
*/
inet_csk(sk)->icsk_rto = (tp->srtt >> 3) + tp->rttvar;
/* 2. Fixups made earlier cannot be right.
* If we do not estimate RTO correctly without them,
* all the algo is pure shit and should be replaced
* with correct one. It is exactly, which we pretend to do.
*/
}
/* NOTE: clamping at TCP_RTO_MIN is not required, current algo
* guarantees that rto is higher.
*/
static inline void tcp_bound_rto(struct sock *sk)
{
if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX)
inet_csk(sk)->icsk_rto = TCP_RTO_MAX;
}
/* 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;
dst_confirm(dst);
if (dst && (dst->flags&DST_HOST)) {
const struct inet_connection_sock *icsk = inet_csk(sk);
int m;
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->metrics[RTAX_RTT-1] = 0;
return;
}
m = dst_metric(dst, RTAX_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)
dst->metrics[RTAX_RTT-1] = tp->srtt;
else
dst->metrics[RTAX_RTT-1] -= (m>>3);
}
if (!(dst_metric_locked(dst, RTAX_RTTVAR))) {
if (m < 0)
m = -m;
/* Scale deviation to rttvar fixed point */
m >>= 1;
if (m < tp->mdev)
m = tp->mdev;
if (m >= dst_metric(dst, RTAX_RTTVAR))
dst->metrics[RTAX_RTTVAR-1] = m;
else
dst->metrics[RTAX_RTTVAR-1] -=
(dst->metrics[RTAX_RTTVAR-1] - m)>>2;
}
if (tp->snd_ssthresh >= 0xFFFF) {
/* 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->metrics[RTAX_SSTHRESH-1] = tp->snd_cwnd >> 1;
if (!dst_metric_locked(dst, RTAX_CWND) &&
tp->snd_cwnd > dst_metric(dst, RTAX_CWND))
dst->metrics[RTAX_CWND-1] = 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->metrics[RTAX_SSTHRESH-1] =
max(tp->snd_cwnd >> 1, tp->snd_ssthresh);
if (!dst_metric_locked(dst, RTAX_CWND))
dst->metrics[RTAX_CWND-1] = (dst->metrics[RTAX_CWND-1] + 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->metrics[RTAX_CWND-1] = (dst->metrics[RTAX_CWND-1] + tp->snd_ssthresh) >> 1;
if (dst->metrics[RTAX_SSTHRESH-1] &&
!dst_metric_locked(dst, RTAX_SSTHRESH) &&
tp->snd_ssthresh > dst->metrics[RTAX_SSTHRESH-1])
dst->metrics[RTAX_SSTHRESH-1] = tp->snd_ssthresh;
}
if (!dst_metric_locked(dst, RTAX_REORDERING)) {
if (dst->metrics[RTAX_REORDERING-1] < tp->reordering &&
tp->reordering != sysctl_tcp_reordering)
dst->metrics[RTAX_REORDERING-1] = tp->reordering;
}
}
}
/* Numbers are taken from RFC2414. */
__u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst)
{
__u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0);
if (!cwnd) {
if (tp->mss_cache > 1460)
cwnd = 2;
else
cwnd = (tp->mss_cache > 1095) ? 3 : 4;
}
return min_t(__u32, cwnd, tp->snd_cwnd_clamp);
}
/* Set slow start threshold and cwnd not falling to slow start */
void tcp_enter_cwr(struct sock *sk, const int set_ssthresh)
{
struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
tp->prior_ssthresh = 0;
tp->bytes_acked = 0;
if (icsk->icsk_ca_state < TCP_CA_CWR) {
tp->undo_marker = 0;
if (set_ssthresh)
tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
tp->snd_cwnd = min(tp->snd_cwnd,
tcp_packets_in_flight(tp) + 1U);
tp->snd_cwnd_cnt = 0;
tp->high_seq = tp->snd_nxt;
tp->snd_cwnd_stamp = tcp_time_stamp;
TCP_ECN_queue_cwr(tp);
tcp_set_ca_state(sk, TCP_CA_CWR);
}
}
/* 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;
}
if (dst_metric(dst, RTAX_REORDERING) &&
tp->reordering != dst_metric(dst, RTAX_REORDERING)) {
tp->rx_opt.sack_ok &= ~2;
tp->reordering = dst_metric(dst, RTAX_REORDERING);
}
if (dst_metric(dst, RTAX_RTT) == 0)
goto reset;
if (!tp->srtt && dst_metric(dst, RTAX_RTT) < (TCP_TIMEOUT_INIT << 3))
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(dst, RTAX_RTT) > tp->srtt) {
tp->srtt = dst_metric(dst, RTAX_RTT);
tp->rtt_seq = tp->snd_nxt;
}
if (dst_metric(dst, RTAX_RTTVAR) > tp->mdev) {
tp->mdev = dst_metric(dst, RTAX_RTTVAR);
tp->mdev_max = tp->rttvar = max(tp->mdev, TCP_RTO_MIN);
}
tcp_set_rto(sk);
tcp_bound_rto(sk);
if (inet_csk(sk)->icsk_rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp)
goto reset;
tp->snd_cwnd = tcp_init_cwnd(tp, dst);
tp->snd_cwnd_stamp = tcp_time_stamp;
return;
reset:
/* Play conservative. If timestamps are not
* supported, TCP will fail to recalculate correct
* rtt, if initial rto is too small. FORGET ALL AND RESET!
*/
if (!tp->rx_opt.saw_tstamp && tp->srtt) {
tp->srtt = 0;
tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_INIT;
inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
}
}
static void tcp_update_reordering(struct sock *sk, const int metric,
const int ts)
{
struct tcp_sock *tp = tcp_sk(sk);
if (metric > tp->reordering) {
tp->reordering = min(TCP_MAX_REORDERING, metric);
/* This exciting event is worth to be remembered. 8) */
if (ts)
NET_INC_STATS_BH(LINUX_MIB_TCPTSREORDER);
else if (IsReno(tp))
NET_INC_STATS_BH(LINUX_MIB_TCPRENOREORDER);
else if (IsFack(tp))
NET_INC_STATS_BH(LINUX_MIB_TCPFACKREORDER);
else
NET_INC_STATS_BH(LINUX_MIB_TCPSACKREORDER);
#if FASTRETRANS_DEBUG > 1
printk(KERN_DEBUG "Disorder%d %d %u f%u s%u rr%d\n",
tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state,
tp->reordering,
tp->fackets_out,
tp->sacked_out,
tp->undo_marker ? tp->undo_retrans : 0);
#endif
/* Disable FACK yet. */
tp->rx_opt.sack_ok &= ~2;
}
}
/* This procedure tags the retransmission queue when SACKs arrive.
*
* We have three tag bits: SACKED(S), RETRANS(R) and LOST(L).
* Packets in queue with these bits set are counted in variables
* sacked_out, retrans_out and lost_out, correspondingly.
*
* Valid combinations are:
* Tag InFlight Description
* 0 1 - orig segment is in flight.
* S 0 - nothing flies, orig reached receiver.
* L 0 - nothing flies, orig lost by net.
* R 2 - both orig and retransmit are in flight.
* L|R 1 - orig is lost, retransmit is in flight.
* S|R 1 - orig reached receiver, retrans is still in flight.
* (L|S|R is logically valid, it could occur when L|R is sacked,
* but it is equivalent to plain S and code short-curcuits it to S.
* L|S is logically invalid, it would mean -1 packet in flight 8))
*
* These 6 states form finite state machine, controlled by the following events:
* 1. New ACK (+SACK) arrives. (tcp_sacktag_write_queue())
* 2. Retransmission. (tcp_retransmit_skb(), tcp_xmit_retransmit_queue())
* 3. Loss detection event of one of three flavors:
* A. Scoreboard estimator decided the packet is lost.
* A'. Reno "three dupacks" marks head of queue lost.
* A''. Its FACK modfication, head until snd.fack is lost.
* B. SACK arrives sacking data transmitted after never retransmitted
* hole was sent out.
* C. SACK arrives sacking SND.NXT at the moment, when the
* segment was retransmitted.
* 4. D-SACK added new rule: D-SACK changes any tag to S.
*
* It is pleasant to note, that state diagram turns out to be commutative,
* so that we are allowed not to be bothered by order of our actions,
* when multiple events arrive simultaneously. (see the function below).
*
* Reordering detection.
* --------------------
* Reordering metric is maximal distance, which a packet can be displaced
* in packet stream. With SACKs we can estimate it:
*
* 1. SACK fills old hole and the corresponding segment was not
* ever retransmitted -> reordering. Alas, we cannot use it
* when segment was retransmitted.
* 2. The last flaw is solved with D-SACK. D-SACK arrives
* for retransmitted and already SACKed segment -> reordering..
* Both of these heuristics are not used in Loss state, when we cannot
* account for retransmits accurately.
*/
static int
tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_una)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
unsigned char *ptr = (skb_transport_header(ack_skb) +
TCP_SKB_CB(ack_skb)->sacked);
struct tcp_sack_block_wire *sp = (struct tcp_sack_block_wire *)(ptr+2);
struct sk_buff *cached_skb;
int num_sacks = (ptr[1] - TCPOLEN_SACK_BASE)>>3;
int reord = tp->packets_out;
int prior_fackets;
u32 lost_retrans = 0;
int flag = 0;
int dup_sack = 0;
int cached_fack_count;
int i;
int first_sack_index;
if (!tp->sacked_out)
tp->fackets_out = 0;
prior_fackets = tp->fackets_out;
/* Check for D-SACK. */
if (before(ntohl(sp[0].start_seq), TCP_SKB_CB(ack_skb)->ack_seq)) {
dup_sack = 1;
tp->rx_opt.sack_ok |= 4;
NET_INC_STATS_BH(LINUX_MIB_TCPDSACKRECV);
} else if (num_sacks > 1 &&
!after(ntohl(sp[0].end_seq), ntohl(sp[1].end_seq)) &&
!before(ntohl(sp[0].start_seq), ntohl(sp[1].start_seq))) {
dup_sack = 1;
tp->rx_opt.sack_ok |= 4;
NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFORECV);
}
/* D-SACK for already forgotten data...
* Do dumb counting. */
if (dup_sack &&
!after(ntohl(sp[0].end_seq), prior_snd_una) &&
after(ntohl(sp[0].end_seq), tp->undo_marker))
tp->undo_retrans--;
/* Eliminate too old ACKs, but take into
* account more or less fresh ones, they can
* contain valid SACK info.
*/
if (before(TCP_SKB_CB(ack_skb)->ack_seq, prior_snd_una - tp->max_window))
return 0;
/* SACK fastpath:
* if the only SACK change is the increase of the end_seq of
* the first block then only apply that SACK block
* and use retrans queue hinting otherwise slowpath */
flag = 1;
for (i = 0; i < num_sacks; i++) {
__be32 start_seq = sp[i].start_seq;
__be32 end_seq = sp[i].end_seq;
if (i == 0) {
if (tp->recv_sack_cache[i].start_seq != start_seq)
flag = 0;
} else {
if ((tp->recv_sack_cache[i].start_seq != start_seq) ||
(tp->recv_sack_cache[i].end_seq != end_seq))
flag = 0;
}
tp->recv_sack_cache[i].start_seq = start_seq;
tp->recv_sack_cache[i].end_seq = end_seq;
}
/* Clear the rest of the cache sack blocks so they won't match mistakenly. */
for (; i < ARRAY_SIZE(tp->recv_sack_cache); i++) {
tp->recv_sack_cache[i].start_seq = 0;
tp->recv_sack_cache[i].end_seq = 0;
}
first_sack_index = 0;
if (flag)
num_sacks = 1;
else {
int j;
tp->fastpath_skb_hint = NULL;
/* order SACK blocks to allow in order walk of the retrans queue */
for (i = num_sacks-1; i > 0; i--) {
for (j = 0; j < i; j++){
if (after(ntohl(sp[j].start_seq),
ntohl(sp[j+1].start_seq))){
struct tcp_sack_block_wire tmp;
tmp = sp[j];
sp[j] = sp[j+1];
sp[j+1] = tmp;
/* Track where the first SACK block goes to */
if (j == first_sack_index)
first_sack_index = j+1;
}
}
}
}
/* clear flag as used for different purpose in following code */
flag = 0;
/* Use SACK fastpath hint if valid */
cached_skb = tp->fastpath_skb_hint;
cached_fack_count = tp->fastpath_cnt_hint;
if (!cached_skb) {
cached_skb = tcp_write_queue_head(sk);
cached_fack_count = 0;
}
for (i=0; i<num_sacks; i++, sp++) {
struct sk_buff *skb;
__u32 start_seq = ntohl(sp->start_seq);
__u32 end_seq = ntohl(sp->end_seq);
int fack_count;
skb = cached_skb;
fack_count = cached_fack_count;
/* Event "B" in the comment above. */
if (after(end_seq, tp->high_seq))
flag |= FLAG_DATA_LOST;
tcp_for_write_queue_from(skb, sk) {
int in_sack, pcount;
u8 sacked;
if (skb == tcp_send_head(sk))
break;
cached_skb = skb;
cached_fack_count = fack_count;
if (i == first_sack_index) {
tp->fastpath_skb_hint = skb;
tp->fastpath_cnt_hint = fack_count;
}
/* The retransmission queue is always in order, so
* we can short-circuit the walk early.
*/
if (!before(TCP_SKB_CB(skb)->seq, end_seq))
break;
in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
!before(end_seq, TCP_SKB_CB(skb)->end_seq);
pcount = tcp_skb_pcount(skb);
if (pcount > 1 && !in_sack &&
after(TCP_SKB_CB(skb)->end_seq, start_seq)) {
unsigned int pkt_len;
in_sack = !after(start_seq,
TCP_SKB_CB(skb)->seq);
if (!in_sack)
pkt_len = (start_seq -
TCP_SKB_CB(skb)->seq);
else
pkt_len = (end_seq -
TCP_SKB_CB(skb)->seq);
if (tcp_fragment(sk, skb, pkt_len, skb_shinfo(skb)->gso_size))
break;
pcount = tcp_skb_pcount(skb);
}
fack_count += pcount;
sacked = TCP_SKB_CB(skb)->sacked;
/* Account D-SACK for retransmitted packet. */
if ((dup_sack && in_sack) &&
(sacked & TCPCB_RETRANS) &&
after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker))
tp->undo_retrans--;
/* The frame is ACKed. */
if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) {
if (sacked&TCPCB_RETRANS) {
if ((dup_sack && in_sack) &&
(sacked&TCPCB_SACKED_ACKED))
reord = min(fack_count, reord);
} else {
/* If it was in a hole, we detected reordering. */
if (fack_count < prior_fackets &&
!(sacked&TCPCB_SACKED_ACKED))
reord = min(fack_count, reord);
}
/* Nothing to do; acked frame is about to be dropped. */
continue;
}
if ((sacked&TCPCB_SACKED_RETRANS) &&
after(end_seq, TCP_SKB_CB(skb)->ack_seq) &&
(!lost_retrans || after(end_seq, lost_retrans)))
lost_retrans = end_seq;
if (!in_sack)
continue;
if (!(sacked&TCPCB_SACKED_ACKED)) {
if (sacked & TCPCB_SACKED_RETRANS) {
/* If the segment is not tagged as lost,
* we do not clear RETRANS, believing
* that retransmission is still in flight.
*/
if (sacked & TCPCB_LOST) {
TCP_SKB_CB(skb)->sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
tp->lost_out -= tcp_skb_pcount(skb);
tp->retrans_out -= tcp_skb_pcount(skb);
/* clear lost hint */
tp->retransmit_skb_hint = NULL;
}
} else {
/* New sack for not retransmitted frame,
* which was in hole. It is reordering.
*/
if (!(sacked & TCPCB_RETRANS) &&
fack_count < prior_fackets)
reord = min(fack_count, reord);
if (sacked & TCPCB_LOST) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
tp->lost_out -= tcp_skb_pcount(skb);
/* clear lost hint */
tp->retransmit_skb_hint = NULL;
}
/* SACK enhanced F-RTO detection.
* Set flag if and only if non-rexmitted
* segments below frto_highmark are
* SACKed (RFC4138; Appendix B).
* Clearing correct due to in-order walk
*/
if (after(end_seq, tp->frto_highmark)) {
flag &= ~FLAG_ONLY_ORIG_SACKED;
} else {
if (!(sacked & TCPCB_RETRANS))
flag |= FLAG_ONLY_ORIG_SACKED;
}
}
TCP_SKB_CB(skb)->sacked |= TCPCB_SACKED_ACKED;
flag |= FLAG_DATA_SACKED;
tp->sacked_out += tcp_skb_pcount(skb);
if (fack_count > tp->fackets_out)
tp->fackets_out = fack_count;
} else {
if (dup_sack && (sacked&TCPCB_RETRANS))
reord = min(fack_count, reord);
}
/* D-SACK. We can detect redundant retransmission
* in S|R and plain R frames and clear it.
* undo_retrans is decreased above, L|R frames
* are accounted above as well.
*/
if (dup_sack &&
(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_RETRANS)) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
tp->retrans_out -= tcp_skb_pcount(skb);
tp->retransmit_skb_hint = NULL;
}
}
}
/* Check for lost retransmit. This superb idea is
* borrowed from "ratehalving". Event "C".
* Later note: FACK people cheated me again 8),
* we have to account for reordering! Ugly,
* but should help.
*/
if (lost_retrans && icsk->icsk_ca_state == TCP_CA_Recovery) {
struct sk_buff *skb;
tcp_for_write_queue(skb, sk) {
if (skb == tcp_send_head(sk))
break;
if (after(TCP_SKB_CB(skb)->seq, lost_retrans))
break;
if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
continue;
if ((TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_RETRANS) &&
after(lost_retrans, TCP_SKB_CB(skb)->ack_seq) &&
(IsFack(tp) ||
!before(lost_retrans,
TCP_SKB_CB(skb)->ack_seq + tp->reordering *
tp->mss_cache))) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
tp->retrans_out -= tcp_skb_pcount(skb);
/* clear lost hint */
tp->retransmit_skb_hint = NULL;
if (!(TCP_SKB_CB(skb)->sacked&(TCPCB_LOST|TCPCB_SACKED_ACKED))) {
tp->lost_out += tcp_skb_pcount(skb);
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
flag |= FLAG_DATA_SACKED;
NET_INC_STATS_BH(LINUX_MIB_TCPLOSTRETRANSMIT);
}
}
}
}
tp->left_out = tp->sacked_out + tp->lost_out;
if ((reord < tp->fackets_out) && icsk->icsk_ca_state != TCP_CA_Loss &&
(!tp->frto_highmark || after(tp->snd_una, tp->frto_highmark)))
tcp_update_reordering(sk, ((tp->fackets_out + 1) - reord), 0);
#if FASTRETRANS_DEBUG > 0
BUG_TRAP((int)tp->sacked_out >= 0);
BUG_TRAP((int)tp->lost_out >= 0);
BUG_TRAP((int)tp->retrans_out >= 0);
BUG_TRAP((int)tcp_packets_in_flight(tp) >= 0);
#endif
return flag;
}
/* F-RTO can only be used if TCP has never retransmitted anything other than
* head (SACK enhanced variant from Appendix B of RFC4138 is more robust here)
*/
int tcp_use_frto(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
if (!sysctl_tcp_frto)
return 0;
if (IsSackFrto())
return 1;
/* Avoid expensive walking of rexmit queue if possible */
if (tp->retrans_out > 1)
return 0;
skb = tcp_write_queue_head(sk);
skb = tcp_write_queue_next(sk, skb); /* Skips head */
tcp_for_write_queue_from(skb, sk) {
if (skb == tcp_send_head(sk))
break;
if (TCP_SKB_CB(skb)->sacked&TCPCB_RETRANS)
return 0;
/* Short-circuit when first non-SACKed skb has been checked */
if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED))
break;
}
return 1;
}
/* RTO occurred, but do not yet enter Loss state. Instead, defer RTO
* recovery a bit and use heuristics in tcp_process_frto() to detect if
* the RTO was spurious. Only clear SACKED_RETRANS of the head here to
* keep retrans_out counting accurate (with SACK F-RTO, other than head
* may still have that bit set); TCPCB_LOST and remaining SACKED_RETRANS
* bits are handled if the Loss state is really to be entered (in
* tcp_enter_frto_loss).
*
* Do like tcp_enter_loss() would; when RTO expires the second time it
* does:
* "Reduce ssthresh if it has not yet been made inside this window."
*/
void tcp_enter_frto(struct sock *sk)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
if ((!tp->frto_counter && icsk->icsk_ca_state <= TCP_CA_Disorder) ||
tp->snd_una == tp->high_seq ||
((icsk->icsk_ca_state == TCP_CA_Loss || tp->frto_counter) &&
!icsk->icsk_retransmits)) {
tp->prior_ssthresh = tcp_current_ssthresh(sk);
/* Our state is too optimistic in ssthresh() call because cwnd
* is not reduced until tcp_enter_frto_loss() when previous FRTO
* recovery has not yet completed. Pattern would be this: RTO,
* Cumulative ACK, RTO (2xRTO for the same segment does not end
* up here twice).
* RFC4138 should be more specific on what to do, even though
* RTO is quite unlikely to occur after the first Cumulative ACK
* due to back-off and complexity of triggering events ...
*/
if (tp->frto_counter) {
u32 stored_cwnd;
stored_cwnd = tp->snd_cwnd;
tp->snd_cwnd = 2;
tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
tp->snd_cwnd = stored_cwnd;
} else {
tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
}
/* ... in theory, cong.control module could do "any tricks" in
* ssthresh(), which means that ca_state, lost bits and lost_out
* counter would have to be faked before the call occurs. We
* consider that too expensive, unlikely and hacky, so modules
* using these in ssthresh() must deal these incompatibility
* issues if they receives CA_EVENT_FRTO and frto_counter != 0
*/
tcp_ca_event(sk, CA_EVENT_FRTO);
}
tp->undo_marker = tp->snd_una;
tp->undo_retrans = 0;
skb = tcp_write_queue_head(sk);
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
tp->retrans_out -= tcp_skb_pcount(skb);
}
tcp_sync_left_out(tp);
/* Earlier loss recovery underway (see RFC4138; Appendix B).
* The last condition is necessary at least in tp->frto_counter case.
*/
if (IsSackFrto() && (tp->frto_counter ||
((1 << icsk->icsk_ca_state) & (TCPF_CA_Recovery|TCPF_CA_Loss))) &&
after(tp->high_seq, tp->snd_una)) {
tp->frto_highmark = tp->high_seq;
} else {
tp->frto_highmark = tp->snd_nxt;
}
tcp_set_ca_state(sk, TCP_CA_Disorder);
tp->high_seq = tp->snd_nxt;
tp->frto_counter = 1;
}
/* Enter Loss state after F-RTO was applied. Dupack arrived after RTO,
* which indicates that we should follow the traditional RTO recovery,
* i.e. mark everything lost and do go-back-N retransmission.
*/
static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
int cnt = 0;
tp->sacked_out = 0;
tp->lost_out = 0;
tp->fackets_out = 0;
tp->retrans_out = 0;
tcp_for_write_queue(skb, sk) {
if (skb == tcp_send_head(sk))
break;
cnt += tcp_skb_pcount(skb);
/*
* Count the retransmission made on RTO correctly (only when
* waiting for the first ACK and did not get it)...
*/
if ((tp->frto_counter == 1) && !(flag&FLAG_DATA_ACKED)) {
tp->retrans_out += tcp_skb_pcount(skb);
/* ...enter this if branch just for the first segment */
flag |= FLAG_DATA_ACKED;
} else {
TCP_SKB_CB(skb)->sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
}
if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED)) {
/* Do not mark those segments lost that were
* forward transmitted after RTO
*/
if (!after(TCP_SKB_CB(skb)->end_seq,
tp->frto_highmark)) {
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
}
} else {
tp->sacked_out += tcp_skb_pcount(skb);
tp->fackets_out = cnt;
}
}
tcp_sync_left_out(tp);
tp->snd_cwnd = tcp_packets_in_flight(tp) + allowed_segments;
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
tp->undo_marker = 0;
tp->frto_counter = 0;
tp->reordering = min_t(unsigned int, tp->reordering,
sysctl_tcp_reordering);
tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->frto_highmark;
TCP_ECN_queue_cwr(tp);
clear_all_retrans_hints(tp);
}
void tcp_clear_retrans(struct tcp_sock *tp)
{
tp->left_out = 0;
tp->retrans_out = 0;
tp->fackets_out = 0;
tp->sacked_out = 0;
tp->lost_out = 0;
tp->undo_marker = 0;
tp->undo_retrans = 0;
}
/* Enter Loss state. If "how" is not zero, forget all SACK information
* and reset tags completely, otherwise preserve SACKs. If receiver
* dropped its ofo queue, we will know this due to reneging detection.
*/
void tcp_enter_loss(struct sock *sk, int how)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
int cnt = 0;
/* Reduce ssthresh if it has not yet been made inside this window. */
if (icsk->icsk_ca_state <= TCP_CA_Disorder || tp->snd_una == tp->high_seq ||
(icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) {
tp->prior_ssthresh = tcp_current_ssthresh(sk);
tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
tcp_ca_event(sk, CA_EVENT_LOSS);
}
tp->snd_cwnd = 1;
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
tp->bytes_acked = 0;
tcp_clear_retrans(tp);
/* Push undo marker, if it was plain RTO and nothing
* was retransmitted. */
if (!how)
tp->undo_marker = tp->snd_una;
tcp_for_write_queue(skb, sk) {
if (skb == tcp_send_head(sk))
break;
cnt += tcp_skb_pcount(skb);
if (TCP_SKB_CB(skb)->sacked&TCPCB_RETRANS)
tp->undo_marker = 0;
TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || how) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
} else {
tp->sacked_out += tcp_skb_pcount(skb);
tp->fackets_out = cnt;
}
}
tcp_sync_left_out(tp);
tp->reordering = min_t(unsigned int, tp->reordering,
sysctl_tcp_reordering);
tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->snd_nxt;
TCP_ECN_queue_cwr(tp);
/* Abort FRTO algorithm if one is in progress */
tp->frto_counter = 0;
clear_all_retrans_hints(tp);
}
static int tcp_check_sack_reneging(struct sock *sk)
{
struct sk_buff *skb;
/* If ACK arrived pointing to a remembered SACK,
* it means that our remembered SACKs do not reflect
* real state of receiver i.e.
* receiver _host_ is heavily congested (or buggy).
* Do processing similar to RTO timeout.
*/
if ((skb = tcp_write_queue_head(sk)) != NULL &&
(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
struct inet_connection_sock *icsk = inet_csk(sk);
NET_INC_STATS_BH(LINUX_MIB_TCPSACKRENEGING);
tcp_enter_loss(sk, 1);
icsk->icsk_retransmits++;
tcp_retransmit_skb(sk, tcp_write_queue_head(sk));
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
icsk->icsk_rto, TCP_RTO_MAX);
return 1;
}
return 0;
}
static inline int tcp_fackets_out(struct tcp_sock *tp)
{
return IsReno(tp) ? tp->sacked_out+1 : tp->fackets_out;
}
static inline int tcp_skb_timedout(struct sock *sk, struct sk_buff *skb)
{
return (tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto);
}
static inline int tcp_head_timedout(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
return tp->packets_out &&
tcp_skb_timedout(sk, tcp_write_queue_head(sk));
}
/* Linux NewReno/SACK/FACK/ECN state machine.
* --------------------------------------
*
* "Open" Normal state, no dubious events, fast path.
* "Disorder" In all the respects it is "Open",
* but requires a bit more attention. It is entered when
* we see some SACKs or dupacks. It is split of "Open"
* mainly to move some processing from fast path to slow one.
* "CWR" CWND was reduced due to some Congestion Notification event.
* It can be ECN, ICMP source quench, local device congestion.
* "Recovery" CWND was reduced, we are fast-retransmitting.
* "Loss" CWND was reduced due to RTO timeout or SACK reneging.
*
* tcp_fastretrans_alert() is entered:
* - each incoming ACK, if state is not "Open"
* - when arrived ACK is unusual, namely:
* * SACK
* * Duplicate ACK.
* * ECN ECE.
*
* Counting packets in flight is pretty simple.
*
* in_flight = packets_out - left_out + retrans_out
*
* packets_out is SND.NXT-SND.UNA counted in packets.
*
* retrans_out is number of retransmitted segments.
*
* left_out is number of segments left network, but not ACKed yet.
*
* left_out = sacked_out + lost_out
*
* sacked_out: Packets, which arrived to receiver out of order
* and hence not ACKed. With SACKs this number is simply
* amount of SACKed data. Even without SACKs
* it is easy to give pretty reliable estimate of this number,
* counting duplicate ACKs.
*
* lost_out: Packets lost by network. TCP has no explicit
* "loss notification" feedback from network (for now).
* It means that this number can be only _guessed_.
* Actually, it is the heuristics to predict lossage that
* distinguishes different algorithms.
*
* F.e. after RTO, when all the queue is considered as lost,
* lost_out = packets_out and in_flight = retrans_out.
*
* Essentially, we have now two algorithms counting
* lost packets.
*
* FACK: It is the simplest heuristics. As soon as we decided
* that something is lost, we decide that _all_ not SACKed
* packets until the most forward SACK are lost. I.e.
* lost_out = fackets_out - sacked_out and left_out = fackets_out.
* It is absolutely correct estimate, if network does not reorder
* packets. And it loses any connection to reality when reordering
* takes place. We use FACK by default until reordering
* is suspected on the path to this destination.
*
* NewReno: when Recovery is entered, we assume that one segment
* is lost (classic Reno). While we are in Recovery and
* a partial ACK arrives, we assume that one more packet
* is lost (NewReno). This heuristics are the same in NewReno
* and SACK.
*
* Imagine, that's all! Forget about all this shamanism about CWND inflation
* deflation etc. CWND is real congestion window, never inflated, changes
* only according to classic VJ rules.
*
* Really tricky (and requiring careful tuning) part of algorithm
* is hidden in functions tcp_time_to_recover() and tcp_xmit_retransmit_queue().
* The first determines the moment _when_ we should reduce CWND and,
* hence, slow down forward transmission. In fact, it determines the moment
* when we decide that hole is caused by loss, rather than by a reorder.
*
* tcp_xmit_retransmit_queue() decides, _what_ we should retransmit to fill
* holes, caused by lost packets.
*
* And the most logically complicated part of algorithm is undo
* heuristics. We detect false retransmits due to both too early
* fast retransmit (reordering) and underestimated RTO, analyzing
* timestamps and D-SACKs. When we detect that some segments were
* retransmitted by mistake and CWND reduction was wrong, we undo
* window reduction and abort recovery phase. This logic is hidden
* inside several functions named tcp_try_undo_<something>.
*/
/* This function decides, when we should leave Disordered state
* and enter Recovery phase, reducing congestion window.
*
* Main question: may we further continue forward transmission
* with the same cwnd?
*/
static int tcp_time_to_recover(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
__u32 packets_out;
/* Do not perform any recovery during FRTO algorithm */
if (tp->frto_counter)
return 0;
/* Trick#1: The loss is proven. */
if (tp->lost_out)
return 1;
/* Not-A-Trick#2 : Classic rule... */
if (tcp_fackets_out(tp) > tp->reordering)
return 1;
/* Trick#3 : when we use RFC2988 timer restart, fast
* retransmit can be triggered by timeout of queue head.
*/
if (tcp_head_timedout(sk))
return 1;
/* Trick#4: It is still not OK... But will it be useful to delay
* recovery more?
*/
packets_out = tp->packets_out;
if (packets_out <= tp->reordering &&
tp->sacked_out >= max_t(__u32, packets_out/2, sysctl_tcp_reordering) &&
!tcp_may_send_now(sk)) {
/* We have nothing to send. This connection is limited
* either by receiver window or by application.
*/
return 1;
}
return 0;
}
/* If we receive more dupacks than we expected counting segments
* in assumption of absent reordering, interpret this as reordering.
* The only another reason could be bug in receiver TCP.
*/
static void tcp_check_reno_reordering(struct sock *sk, const int addend)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 holes;
holes = max(tp->lost_out, 1U);
holes = min(holes, tp->packets_out);
if ((tp->sacked_out + holes) > tp->packets_out) {
tp->sacked_out = tp->packets_out - holes;
tcp_update_reordering(sk, tp->packets_out + addend, 0);
}
}
/* Emulate SACKs for SACKless connection: account for a new dupack. */
static void tcp_add_reno_sack(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
tp->sacked_out++;
tcp_check_reno_reordering(sk, 0);
tcp_sync_left_out(tp);
}
/* Account for ACK, ACKing some data in Reno Recovery phase. */
static void tcp_remove_reno_sacks(struct sock *sk, int acked)
{
struct tcp_sock *tp = tcp_sk(sk);
if (acked > 0) {
/* One ACK acked hole. The rest eat duplicate ACKs. */
if (acked-1 >= tp->sacked_out)
tp->sacked_out = 0;
else
tp->sacked_out -= acked-1;
}
tcp_check_reno_reordering(sk, acked);
tcp_sync_left_out(tp);
}
static inline void tcp_reset_reno_sack(struct tcp_sock *tp)
{
tp->sacked_out = 0;
tp->left_out = tp->lost_out;
}
/* Mark head of queue up as lost. */
static void tcp_mark_head_lost(struct sock *sk,
int packets, u32 high_seq)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
int cnt;
BUG_TRAP(packets <= tp->packets_out);
if (tp->lost_skb_hint) {
skb = tp->lost_skb_hint;
cnt = tp->lost_cnt_hint;
} else {
skb = tcp_write_queue_head(sk);
cnt = 0;
}
tcp_for_write_queue_from(skb, sk) {
if (skb == tcp_send_head(sk))
break;
/* TODO: do this better */
/* this is not the most efficient way to do this... */
tp->lost_skb_hint = skb;
tp->lost_cnt_hint = cnt;
cnt += tcp_skb_pcount(skb);
if (cnt > packets || after(TCP_SKB_CB(skb)->end_seq, high_seq))
break;
if (!(TCP_SKB_CB(skb)->sacked&TCPCB_TAGBITS)) {
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
/* clear xmit_retransmit_queue hints
* if this is beyond hint */
if (tp->retransmit_skb_hint != NULL &&
before(TCP_SKB_CB(skb)->seq,
TCP_SKB_CB(tp->retransmit_skb_hint)->seq))
tp->retransmit_skb_hint = NULL;
}
}
tcp_sync_left_out(tp);
}
/* Account newly detected lost packet(s) */
static void tcp_update_scoreboard(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
if (IsFack(tp)) {
int lost = tp->fackets_out - tp->reordering;
if (lost <= 0)
lost = 1;
tcp_mark_head_lost(sk, lost, tp->high_seq);
} else {
tcp_mark_head_lost(sk, 1, tp->high_seq);
}
/* New heuristics: it is possible only after we switched
* to restart timer each time when something is ACKed.
* Hence, we can detect timed out packets during fast
* retransmit without falling to slow start.
*/
if (!IsReno(tp) && tcp_head_timedout(sk)) {
struct sk_buff *skb;
skb = tp->scoreboard_skb_hint ? tp->scoreboard_skb_hint
: tcp_write_queue_head(sk);
tcp_for_write_queue_from(skb, sk) {
if (skb == tcp_send_head(sk))
break;
if (!tcp_skb_timedout(sk, skb))
break;
if (!(TCP_SKB_CB(skb)->sacked&TCPCB_TAGBITS)) {
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
/* clear xmit_retrans hint */
if (tp->retransmit_skb_hint &&
before(TCP_SKB_CB(skb)->seq,
TCP_SKB_CB(tp->retransmit_skb_hint)->seq))
tp->retransmit_skb_hint = NULL;
}
}
tp->scoreboard_skb_hint = skb;
tcp_sync_left_out(tp);
}
}
/* CWND moderation, preventing bursts due to too big ACKs
* in dubious situations.
*/
static inline void tcp_moderate_cwnd(struct tcp_sock *tp)
{
tp->snd_cwnd = min(tp->snd_cwnd,
tcp_packets_in_flight(tp)+tcp_max_burst(tp));
tp->snd_cwnd_stamp = tcp_time_stamp;
}
/* Lower bound on congestion window is slow start threshold
* unless congestion avoidance choice decides to overide it.
*/
static inline u32 tcp_cwnd_min(const struct sock *sk)
{
const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
return ca_ops->min_cwnd ? ca_ops->min_cwnd(sk) : tcp_sk(sk)->snd_ssthresh;
}
/* Decrease cwnd each second ack. */
static void tcp_cwnd_down(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
int decr = tp->snd_cwnd_cnt + 1;
tp->snd_cwnd_cnt = decr&1;
decr >>= 1;
if (decr && tp->snd_cwnd > tcp_cwnd_min(sk))
tp->snd_cwnd -= decr;
tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp)+1);
tp->snd_cwnd_stamp = tcp_time_stamp;
}
/* Nothing was retransmitted or returned timestamp is less
* than timestamp of the first retransmission.
*/
static inline int tcp_packet_delayed(struct tcp_sock *tp)
{
return !tp->retrans_stamp ||
(tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
(__s32)(tp->rx_opt.rcv_tsecr - tp->retrans_stamp) < 0);
}
/* Undo procedures. */
#if FASTRETRANS_DEBUG > 1
static void DBGUNDO(struct sock *sk, const char *msg)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_sock *inet = inet_sk(sk);
printk(KERN_DEBUG "Undo %s %u.%u.%u.%u/%u c%u l%u ss%u/%u p%u\n",
msg,
NIPQUAD(inet->daddr), ntohs(inet->dport),
tp->snd_cwnd, tp->left_out,
tp->snd_ssthresh, tp->prior_ssthresh,
tp->packets_out);
}
#else
#define DBGUNDO(x...) do { } while (0)
#endif
static void tcp_undo_cwr(struct sock *sk, const int undo)
{
struct tcp_sock *tp = tcp_sk(sk);
if (tp->prior_ssthresh) {
const struct inet_connection_sock *icsk = inet_csk(sk);
if (icsk->icsk_ca_ops->undo_cwnd)
tp->snd_cwnd = icsk->icsk_ca_ops->undo_cwnd(sk);
else
tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh<<1);
if (undo && tp->prior_ssthresh > tp->snd_ssthresh) {
tp->snd_ssthresh = tp->prior_ssthresh;
TCP_ECN_withdraw_cwr(tp);
}
} else {
tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh);
}
tcp_moderate_cwnd(tp);
tp->snd_cwnd_stamp = tcp_time_stamp;
/* There is something screwy going on with the retrans hints after
an undo */
clear_all_retrans_hints(tp);
}
static inline int tcp_may_undo(struct tcp_sock *tp)
{
return tp->undo_marker &&
(!tp->undo_retrans || tcp_packet_delayed(tp));
}
/* People celebrate: "We love our President!" */
static int tcp_try_undo_recovery(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
if (tcp_may_undo(tp)) {
/* Happy end! We did not retransmit anything
* or our original transmission succeeded.
*/
DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans");
tcp_undo_cwr(sk, 1);
if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
NET_INC_STATS_BH(LINUX_MIB_TCPLOSSUNDO);
else
NET_INC_STATS_BH(LINUX_MIB_TCPFULLUNDO);
tp->undo_marker = 0;
}
if (tp->snd_una == tp->high_seq && IsReno(tp)) {
/* Hold old state until something *above* high_seq
* is ACKed. For Reno it is MUST to prevent false
* fast retransmits (RFC2582). SACK TCP is safe. */
tcp_moderate_cwnd(tp);
return 1;
}
tcp_set_ca_state(sk, TCP_CA_Open);
return 0;
}
/* Try to undo cwnd reduction, because D-SACKs acked all retransmitted data */
static void tcp_try_undo_dsack(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
if (tp->undo_marker && !tp->undo_retrans) {
DBGUNDO(sk, "D-SACK");
tcp_undo_cwr(sk, 1);
tp->undo_marker = 0;
NET_INC_STATS_BH(LINUX_MIB_TCPDSACKUNDO);
}
}
/* Undo during fast recovery after partial ACK. */
static int tcp_try_undo_partial(struct sock *sk, int acked)
{
struct tcp_sock *tp = tcp_sk(sk);
/* Partial ACK arrived. Force Hoe's retransmit. */
int failed = IsReno(tp) || tp->fackets_out>tp->reordering;
if (tcp_may_undo(tp)) {
/* Plain luck! Hole if filled with delayed
* packet, rather than with a retransmit.
*/
if (tp->retrans_out == 0)
tp->retrans_stamp = 0;
tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
DBGUNDO(sk, "Hoe");
tcp_undo_cwr(sk, 0);
NET_INC_STATS_BH(LINUX_MIB_TCPPARTIALUNDO);
/* So... Do not make Hoe's retransmit yet.
* If the first packet was delayed, the rest
* ones are most probably delayed as well.
*/
failed = 0;
}
return failed;
}
/* Undo during loss recovery after partial ACK. */
static int tcp_try_undo_loss(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
if (tcp_may_undo(tp)) {
struct sk_buff *skb;
tcp_for_write_queue(skb, sk) {
if (skb == tcp_send_head(sk))
break;
TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
}
clear_all_retrans_hints(tp);
DBGUNDO(sk, "partial loss");
tp->lost_out = 0;
tp->left_out = tp->sacked_out;
tcp_undo_cwr(sk, 1);
NET_INC_STATS_BH(LINUX_MIB_TCPLOSSUNDO);
inet_csk(sk)->icsk_retransmits = 0;
tp->undo_marker = 0;
if (!IsReno(tp))
tcp_set_ca_state(sk, TCP_CA_Open);
return 1;
}
return 0;
}
static inline void tcp_complete_cwr(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
tp->snd_cwnd_stamp = tcp_time_stamp;
tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR);
}
static void tcp_try_to_open(struct sock *sk, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
tp->left_out = tp->sacked_out;
if (tp->retrans_out == 0)
tp->retrans_stamp = 0;
if (flag&FLAG_ECE)
tcp_enter_cwr(sk, 1);
if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) {
int state = TCP_CA_Open;
if (tp->left_out || tp->retrans_out || tp->undo_marker)
state = TCP_CA_Disorder;
if (inet_csk(sk)->icsk_ca_state != state) {
tcp_set_ca_state(sk, state);
tp->high_seq = tp->snd_nxt;
}
tcp_moderate_cwnd(tp);
} else {
tcp_cwnd_down(sk);
}
}
static void tcp_mtup_probe_failed(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
icsk->icsk_mtup.search_high = icsk->icsk_mtup.probe_size - 1;
icsk->icsk_mtup.probe_size = 0;
}
static void tcp_mtup_probe_success(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
/* FIXME: breaks with very large cwnd */
tp->prior_ssthresh = tcp_current_ssthresh(sk);
tp->snd_cwnd = tp->snd_cwnd *
tcp_mss_to_mtu(sk, tp->mss_cache) /
icsk->icsk_mtup.probe_size;
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
tp->rcv_ssthresh = tcp_current_ssthresh(sk);
icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size;
icsk->icsk_mtup.probe_size = 0;
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
}
/* Process an event, which can update packets-in-flight not trivially.
* Main goal of this function is to calculate new estimate for left_out,
* taking into account both packets sitting in receiver's buffer and
* packets lost by network.
*
* Besides that it does CWND reduction, when packet loss is detected
* and changes state of machine.
*
* It does _not_ decide what to send, it is made in function
* tcp_xmit_retransmit_queue().
*/
static void
tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una,
int prior_packets, int flag)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
int is_dupack = (tp->snd_una == prior_snd_una && !(flag&FLAG_NOT_DUP));
/* Some technical things:
* 1. Reno does not count dupacks (sacked_out) automatically. */
if (!tp->packets_out)
tp->sacked_out = 0;
/* 2. SACK counts snd_fack in packets inaccurately. */
if (tp->sacked_out == 0)
tp->fackets_out = 0;
/* Now state machine starts.
* A. ECE, hence prohibit cwnd undoing, the reduction is required. */
if (flag&FLAG_ECE)
tp->prior_ssthresh = 0;
/* B. In all the states check for reneging SACKs. */
if (tp->sacked_out && tcp_check_sack_reneging(sk))
return;
/* C. Process data loss notification, provided it is valid. */
if ((flag&FLAG_DATA_LOST) &&
before(tp->snd_una, tp->high_seq) &&
icsk->icsk_ca_state != TCP_CA_Open &&
tp->fackets_out > tp->reordering) {
tcp_mark_head_lost(sk, tp->fackets_out-tp->reordering, tp->high_seq);
NET_INC_STATS_BH(LINUX_MIB_TCPLOSS);
}
/* D. Synchronize left_out to current state. */
tcp_sync_left_out(tp);
/* E. Check state exit conditions. State can be terminated
* when high_seq is ACKed. */
if (icsk->icsk_ca_state == TCP_CA_Open) {
BUG_TRAP(tp->retrans_out == 0);
tp->retrans_stamp = 0;
} else if (!before(tp->snd_una, tp->high_seq)) {
switch (icsk->icsk_ca_state) {
case TCP_CA_Loss:
icsk->icsk_retransmits = 0;
if (tcp_try_undo_recovery(sk))
return;
break;
case TCP_CA_CWR:
/* CWR is to be held something *above* high_seq
* is ACKed for CWR bit to reach receiver. */
if (tp->snd_una != tp->high_seq) {
tcp_complete_cwr(sk);
tcp_set_ca_state(sk, TCP_CA_Open);
}
break;
case TCP_CA_Disorder:
tcp_try_undo_dsack(sk);
if (!tp->undo_marker ||
/* For SACK case do not Open to allow to undo
* catching for all duplicate ACKs. */
IsReno(tp) || tp->snd_una != tp->high_seq) {
tp->undo_marker = 0;
tcp_set_ca_state(sk, TCP_CA_Open);
}
break;
case TCP_CA_Recovery:
if (IsReno(tp))
tcp_reset_reno_sack(tp);
if (tcp_try_undo_recovery(sk))
return;
tcp_complete_cwr(sk);
break;
}
}
/* F. Process state. */
switch (icsk->icsk_ca_state) {
case TCP_CA_Recovery:
if (prior_snd_una == tp->snd_una) {
if (IsReno(tp) && is_dupack)
tcp_add_reno_sack(sk);
} else {
int acked = prior_packets - tp->packets_out;
if (IsReno(tp))
tcp_remove_reno_sacks(sk, acked);
is_dupack = tcp_try_undo_partial(sk, acked);
}
break;
case TCP_CA_Loss:
if (flag&FLAG_DATA_ACKED)
icsk->icsk_retransmits = 0;
if (!tcp_try_undo_loss(sk)) {
tcp_moderate_cwnd(tp);
tcp_xmit_retransmit_queue(sk);
return;
}
if (icsk->icsk_ca_state != TCP_CA_Open)
return;
/* Loss is undone; fall through to processing in Open state. */
default:
if (IsReno(tp)) {
if (tp->snd_una != prior_snd_una)
tcp_reset_reno_sack(tp);
if (is_dupack)
tcp_add_reno_sack(sk);
}
if (icsk->icsk_ca_state == TCP_CA_Disorder)
tcp_try_undo_dsack(sk);
if (!tcp_time_to_recover(sk)) {
tcp_try_to_open(sk, flag);
return;
}
/* MTU probe failure: don't reduce cwnd */
if (icsk->icsk_ca_state < TCP_CA_CWR &&
icsk->icsk_mtup.probe_size &&
tp->snd_una == tp->mtu_probe.probe_seq_start) {
tcp_mtup_probe_failed(sk);
/* Restores the reduction we did in tcp_mtup_probe() */
tp->snd_cwnd++;
tcp_simple_retransmit(sk);
return;
}
/* Otherwise enter Recovery state */
if (IsReno(tp))
NET_INC_STATS_BH(LINUX_MIB_TCPRENORECOVERY);
else
NET_INC_STATS_BH(LINUX_MIB_TCPSACKRECOVERY);
tp->high_seq = tp->snd_nxt;
tp->prior_ssthresh = 0;
tp->undo_marker = tp->snd_una;
tp->undo_retrans = tp->retrans_out;
if (icsk->icsk_ca_state < TCP_CA_CWR) {
if (!(flag&FLAG_ECE))
tp->prior_ssthresh = tcp_current_ssthresh(sk);
tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
TCP_ECN_queue_cwr(tp);
}
tp->bytes_acked = 0;
tp->snd_cwnd_cnt = 0;
tcp_set_ca_state(sk, TCP_CA_Recovery);
}
if (is_dupack || tcp_head_timedout(sk))
tcp_update_scoreboard(sk);
tcp_cwnd_down(sk);
tcp_xmit_retransmit_queue(sk);
}
/* Read draft-ietf-tcplw-high-performance before mucking
* with this code. (Supersedes RFC1323)
*/
static void tcp_ack_saw_tstamp(struct sock *sk, int flag)
{
/* RTTM Rule: A TSecr value received in a segment is used to
* update the averaged RTT measurement only if the segment
* acknowledges some new data, i.e., only if it advances the
* left edge of the send window.
*
* See draft-ietf-tcplw-high-performance-00, section 3.3.
* 1998/04/10 Andrey V. Savochkin <saw@msu.ru>
*
* Changed: reset backoff as soon as we see the first valid sample.
* If we do not, we get strongly overestimated rto. With timestamps
* samples are accepted even from very old segments: f.e., when rtt=1
* increases to 8, we retransmit 5 times and after 8 seconds delayed
* answer arrives rto becomes 120 seconds! If at least one of segments
* in window is lost... Voila. --ANK (010210)
*/
struct tcp_sock *tp = tcp_sk(sk);
const __u32 seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr;
tcp_rtt_estimator(sk, seq_rtt);
tcp_set_rto(sk);
inet_csk(sk)->icsk_backoff = 0;
tcp_bound_rto(sk);
}
static void tcp_ack_no_tstamp(struct sock *sk, u32 seq_rtt, int flag)
{
/* We don't have a timestamp. Can only use
* packets that are not retransmitted to determine
* rtt estimates. Also, we must not reset the
* backoff for rto until we get a non-retransmitted
* packet. This allows us to deal with a situation
* where the network delay has increased suddenly.
* I.e. Karn's algorithm. (SIGCOMM '87, p5.)
*/
if (flag & FLAG_RETRANS_DATA_ACKED)
return;
tcp_rtt_estimator(sk, seq_rtt);
tcp_set_rto(sk);
inet_csk(sk)->icsk_backoff = 0;
tcp_bound_rto(sk);
}
static inline void tcp_ack_update_rtt(struct sock *sk, const int flag,
const s32 seq_rtt)
{
const struct tcp_sock *tp = tcp_sk(sk);
/* Note that peer MAY send zero echo. In this case it is ignored. (rfc1323) */
if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
tcp_ack_saw_tstamp(sk, flag);
else if (seq_rtt >= 0)
tcp_ack_no_tstamp(sk, seq_rtt, flag);
}
static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 rtt,
u32 in_flight, int good)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
icsk->icsk_ca_ops->cong_avoid(sk, ack, rtt, in_flight, good);
tcp_sk(sk)->snd_cwnd_stamp = tcp_time_stamp;
}
/* Restart timer after forward progress on connection.
* RFC2988 recommends to restart timer to now+rto.
*/
static void tcp_ack_packets_out(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
if (!tp->packets_out) {
inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
} else {
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
}
}
static int tcp_tso_acked(struct sock *sk, struct sk_buff *skb,
__u32 now, __s32 *seq_rtt)
{
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
__u32 seq = tp->snd_una;
__u32 packets_acked;
int acked = 0;
/* If we get here, the whole TSO packet has not been
* acked.
*/
BUG_ON(!after(scb->end_seq, seq));
packets_acked = tcp_skb_pcount(skb);
if (tcp_trim_head(sk, skb, seq - scb->seq))
return 0;
packets_acked -= tcp_skb_pcount(skb);
if (packets_acked) {
__u8 sacked = scb->sacked;
acked |= FLAG_DATA_ACKED;
if (sacked) {
if (sacked & TCPCB_RETRANS) {
if (sacked & TCPCB_SACKED_RETRANS)
tp->retrans_out -= packets_acked;
acked |= FLAG_RETRANS_DATA_ACKED;
*seq_rtt = -1;
} else if (*seq_rtt < 0)
*seq_rtt = now - scb->when;
if (sacked & TCPCB_SACKED_ACKED)
tp->sacked_out -= packets_acked;
if (sacked & TCPCB_LOST)
tp->lost_out -= packets_acked;
if (sacked & TCPCB_URG) {
if (tp->urg_mode &&
!before(seq, tp->snd_up))
tp->urg_mode = 0;
}
} else if (*seq_rtt < 0)
*seq_rtt = now - scb->when;
if (tp->fackets_out) {
__u32 dval = min(tp->fackets_out, packets_acked);
tp->fackets_out -= dval;
}
tp->packets_out -= packets_acked;
BUG_ON(tcp_skb_pcount(skb) == 0);
BUG_ON(!before(scb->seq, scb->end_seq));
}
return acked;
}
/* Remove acknowledged frames from the retransmission queue. */
static int tcp_clean_rtx_queue(struct sock *sk, __s32 *seq_rtt_p)
{
struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
struct sk_buff *skb;
__u32 now = tcp_time_stamp;
int acked = 0;
__s32 seq_rtt = -1;
u32 pkts_acked = 0;
ktime_t last_ackt = ktime_set(0,0);
while ((skb = tcp_write_queue_head(sk)) &&
skb != tcp_send_head(sk)) {
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
__u8 sacked = scb->sacked;
/* If our packet is before the ack sequence we can
* discard it as it's confirmed to have arrived at
* the other end.
*/
if (after(scb->end_seq, tp->snd_una)) {
if (tcp_skb_pcount(skb) > 1 &&
after(tp->snd_una, scb->seq))
acked |= tcp_tso_acked(sk, skb,
now, &seq_rtt);
break;
}
/* Initial outgoing SYN's get put onto the write_queue
* just like anything else we transmit. It is not
* true data, and if we misinform our callers that
* this ACK acks real data, we will erroneously exit
* connection startup slow start one packet too
* quickly. This is severely frowned upon behavior.
*/
if (!(scb->flags & TCPCB_FLAG_SYN)) {
acked |= FLAG_DATA_ACKED;
++pkts_acked;
} else {
acked |= FLAG_SYN_ACKED;
tp->retrans_stamp = 0;
}
/* MTU probing checks */
if (icsk->icsk_mtup.probe_size) {
if (!after(tp->mtu_probe.probe_seq_end, TCP_SKB_CB(skb)->end_seq)) {
tcp_mtup_probe_success(sk, skb);
}
}
if (sacked) {
if (sacked & TCPCB_RETRANS) {
if (sacked & TCPCB_SACKED_RETRANS)
tp->retrans_out -= tcp_skb_pcount(skb);
acked |= FLAG_RETRANS_DATA_ACKED;
seq_rtt = -1;
} else if (seq_rtt < 0) {
seq_rtt = now - scb->when;
last_ackt = skb->tstamp;
}
if (sacked & TCPCB_SACKED_ACKED)
tp->sacked_out -= tcp_skb_pcount(skb);
if (sacked & TCPCB_LOST)
tp->lost_out -= tcp_skb_pcount(skb);
if (sacked & TCPCB_URG) {
if (tp->urg_mode &&
!before(scb->end_seq, tp->snd_up))
tp->urg_mode = 0;
}
} else if (seq_rtt < 0) {
seq_rtt = now - scb->when;
last_ackt = skb->tstamp;
}
tcp_dec_pcount_approx(&tp->fackets_out, skb);
tcp_packets_out_dec(tp, skb);
tcp_unlink_write_queue(skb, sk);
sk_stream_free_skb(sk, skb);
clear_all_retrans_hints(tp);
}
if (acked&FLAG_ACKED) {
const struct tcp_congestion_ops *ca_ops
= inet_csk(sk)->icsk_ca_ops;
tcp_ack_update_rtt(sk, acked, seq_rtt);
tcp_ack_packets_out(sk);
if (ca_ops->pkts_acked)
ca_ops->pkts_acked(sk, pkts_acked, last_ackt);
}
#if FASTRETRANS_DEBUG > 0
BUG_TRAP((int)tp->sacked_out >= 0);
BUG_TRAP((int)tp->lost_out >= 0);
BUG_TRAP((int)tp->retrans_out >= 0);
if (!tp->packets_out && tp->rx_opt.sack_ok) {
const struct inet_connection_sock *icsk = inet_csk(sk);
if (tp->lost_out) {
printk(KERN_DEBUG "Leak l=%u %d\n",
tp->lost_out, icsk->icsk_ca_state);
tp->lost_out = 0;
}
if (tp->sacked_out) {
printk(KERN_DEBUG "Leak s=%u %d\n",
tp->sacked_out, icsk->icsk_ca_state);
tp->sacked_out = 0;
}
if (tp->retrans_out) {
printk(KERN_DEBUG "Leak r=%u %d\n",
tp->retrans_out, icsk->icsk_ca_state);
tp->retrans_out = 0;
}
}
#endif
*seq_rtt_p = seq_rtt;
return acked;
}
static void tcp_ack_probe(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
/* Was it a usable window open? */
if (!after(TCP_SKB_CB(tcp_send_head(sk))->end_seq,
tp->snd_una + tp->snd_wnd)) {
icsk->icsk_backoff = 0;
inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0);
/* Socket must be waked up by subsequent tcp_data_snd_check().
* This function is not for random using!
*/
} else {
inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
min(icsk->icsk_rto << icsk->icsk_backoff, TCP_RTO_MAX),
TCP_RTO_MAX);
}
}
static inline int tcp_ack_is_dubious(const struct sock *sk, const int flag)
{
return (!(flag & FLAG_NOT_DUP) || (flag & FLAG_CA_ALERT) ||
inet_csk(sk)->icsk_ca_state != TCP_CA_Open);
}
static inline int tcp_may_raise_cwnd(const struct sock *sk, const int flag)
{
const struct tcp_sock *tp = tcp_sk(sk);
return (!(flag & FLAG_ECE) || tp->snd_cwnd < tp->snd_ssthresh) &&
!((1 << inet_csk(sk)->icsk_ca_state) & (TCPF_CA_Recovery | TCPF_CA_CWR));
}
/* Check that window update is acceptable.
* The function assumes that snd_una<=ack<=snd_next.
*/
static inline int tcp_may_update_window(const struct tcp_sock *tp, const u32 ack,
const u32 ack_seq, const u32 nwin)
{
return (after(ack, tp->snd_una) ||
after(ack_seq, tp->snd_wl1) ||
(ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd));
}
/* Update our send window.
*
* Window update algorithm, described in RFC793/RFC1122 (used in linux-2.2
* and in FreeBSD. NetBSD's one is even worse.) is wrong.
*/
static int tcp_ack_update_window(struct sock *sk, struct sk_buff *skb, u32 ack,
u32 ack_seq)
{
struct tcp_sock *tp = tcp_sk(sk);
int flag = 0;
u32 nwin = ntohs(tcp_hdr(skb)->window);
if (likely(!tcp_hdr(skb)->syn))
nwin <<= tp->rx_opt.snd_wscale;
if (tcp_may_update_window(tp, ack, ack_seq, nwin)) {
flag |= FLAG_WIN_UPDATE;
tcp_update_wl(tp, ack, ack_seq);
if (tp->snd_wnd != nwin) {
tp->snd_wnd = nwin;
/* Note, it is the only place, where
* fast path is recovered for sending TCP.
*/
tp->pred_flags = 0;
tcp_fast_path_check(sk);
if (nwin > tp->max_window) {
tp->max_window = nwin;
tcp_sync_mss(sk, inet_csk(sk)->icsk_pmtu_cookie);
}
}
}
tp->snd_una = ack;
return flag;
}
/* A very conservative spurious RTO response algorithm: reduce cwnd and
* continue in congestion avoidance.
*/
static void tcp_conservative_spur_to_response(struct tcp_sock *tp)
{
tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
tp->snd_cwnd_cnt = 0;
TCP_ECN_queue_cwr(tp);
tcp_moderate_cwnd(tp);
}
/* A conservative spurious RTO response algorithm: reduce cwnd using
* rate halving and continue in congestion avoidance.
*/
static void tcp_ratehalving_spur_to_response(struct sock *sk)
{
tcp_enter_cwr(sk, 0);
}
static void tcp_undo_spur_to_response(struct sock *sk, int flag)
{
if (flag&FLAG_ECE)
tcp_ratehalving_spur_to_response(sk);
else
tcp_undo_cwr(sk, 1);
}
/* F-RTO spurious RTO detection algorithm (RFC4138)
*
* F-RTO affects during two new ACKs following RTO (well, almost, see inline
* comments). State (ACK number) is kept in frto_counter. When ACK advances
* window (but not to or beyond highest sequence sent before RTO):
* On First ACK, send two new segments out.
* On Second ACK, RTO was likely spurious. Do spurious response (response
* algorithm is not part of the F-RTO detection algorithm
* given in RFC4138 but can be selected separately).
* Otherwise (basically on duplicate ACK), RTO was (likely) caused by a loss
* and TCP falls back to conventional RTO recovery. F-RTO allows overriding
* of Nagle, this is done using frto_counter states 2 and 3, when a new data
* segment of any size sent during F-RTO, state 2 is upgraded to 3.
*
* Rationale: if the RTO was spurious, new ACKs should arrive from the
* original window even after we transmit two new data segments.
*
* SACK version:
* on first step, wait until first cumulative ACK arrives, then move to
* the second step. In second step, the next ACK decides.
*
* F-RTO is implemented (mainly) in four functions:
* - tcp_use_frto() is used to determine if TCP is can use F-RTO
* - tcp_enter_frto() prepares TCP state on RTO if F-RTO is used, it is
* called when tcp_use_frto() showed green light
* - tcp_process_frto() handles incoming ACKs during F-RTO algorithm
* - tcp_enter_frto_loss() is called if there is not enough evidence
* to prove that the RTO is indeed spurious. It transfers the control
* from F-RTO to the conventional RTO recovery
*/
static int tcp_process_frto(struct sock *sk, u32 prior_snd_una, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
tcp_sync_left_out(tp);
/* Duplicate the behavior from Loss state (fastretrans_alert) */
if (flag&FLAG_DATA_ACKED)
inet_csk(sk)->icsk_retransmits = 0;
if (!before(tp->snd_una, tp->frto_highmark)) {
tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3), flag);
return 1;
}
if (!IsSackFrto() || IsReno(tp)) {
/* RFC4138 shortcoming in step 2; should also have case c):
* ACK isn't duplicate nor advances window, e.g., opposite dir
* data, winupdate
*/
if ((tp->snd_una == prior_snd_una) && (flag&FLAG_NOT_DUP) &&
!(flag&FLAG_FORWARD_PROGRESS))
return 1;
if (!(flag&FLAG_DATA_ACKED)) {
tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 0 : 3),
flag);
return 1;
}
} else {
if (!(flag&FLAG_DATA_ACKED) && (tp->frto_counter == 1)) {
/* Prevent sending of new data. */
tp->snd_cwnd = min(tp->snd_cwnd,
tcp_packets_in_flight(tp));
return 1;
}
if ((tp->frto_counter >= 2) &&
(!(flag&FLAG_FORWARD_PROGRESS) ||
((flag&FLAG_DATA_SACKED) && !(flag&FLAG_ONLY_ORIG_SACKED)))) {
/* RFC4138 shortcoming (see comment above) */
if (!(flag&FLAG_FORWARD_PROGRESS) && (flag&FLAG_NOT_DUP))
return 1;
tcp_enter_frto_loss(sk, 3, flag);
return 1;
}
}
if (tp->frto_counter == 1) {
/* Sending of the next skb must be allowed or no FRTO */
if (!tcp_send_head(sk) ||
after(TCP_SKB_CB(tcp_send_head(sk))->end_seq,
tp->snd_una + tp->snd_wnd)) {
tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3),
flag);
return 1;
}
tp->snd_cwnd = tcp_packets_in_flight(tp) + 2;
tp->frto_counter = 2;
return 1;
} else {
switch (sysctl_tcp_frto_response) {
case 2:
tcp_undo_spur_to_response(sk, flag);
break;
case 1:
tcp_conservative_spur_to_response(tp);
break;
default:
tcp_ratehalving_spur_to_response(sk);
break;
}
tp->frto_counter = 0;
}
return 0;
}
/* This routine deals with incoming acks, but not outgoing ones. */
static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
u32 prior_snd_una = tp->snd_una;
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
u32 prior_in_flight;
s32 seq_rtt;
int prior_packets;