#define REXMIT_NONE 0/* no loss recovery to do */ #define REXMIT_LOST 1/* retransmit packets marked lost */ #define REXMIT_NEW 2/* FRTO-style transmit of unsent/new packets */
if (likely(!unknown_opt && !parse_all_opt)) return;
/* The skb will be handled in the *bpf_skops_established()or *bpf_skops_write_hdr_opt().
*/ switch (sk->sk_state) { case TCP_SYN_RECV: case TCP_SYN_SENT: case TCP_LISTEN: return;
}
memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
sock_ops.op = bpf_op;
sock_ops.is_fullsock = 1;
sock_ops.is_locked_tcp_sock = 1;
sock_ops.sk = sk; /* sk with TCP_REPAIR_ON does not have skb in tcp_finish_connect */ if (skb)
bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb));
rcu_read_lock();
dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); if (!dev || len >= READ_ONCE(dev->mtu))
pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
dev ? dev->name : "Unknown driver");
rcu_read_unlock();
}
/* Adapt the MSS value used to make delayed ack decision to the *realworld.
*/ staticvoid tcp_measure_rcv_mss(struct sock *sk, conststruct sk_buff *skb)
{ struct inet_connection_sock *icsk = inet_csk(sk); constunsignedint lss = icsk->icsk_ack.last_seg_size; unsignedint len;
icsk->icsk_ack.last_seg_size = 0;
/* skb->len may jitter because of SACKs, even if peer *sendsgoodfull-sizedframes.
*/
len = skb_shinfo(skb)->gso_size ? : skb->len; if (len >= icsk->icsk_ack.rcv_mss) { /* Note: divides are still a bit expensive. *Forthemoment,onlyadjustscaling_ratio *whenweupdateicsk_ack.rcv_mss.
*/ if (unlikely(len != icsk->icsk_ack.rcv_mss)) {
u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE;
u8 old_ratio = tcp_sk(sk)->scaling_ratio;
do_div(val, skb->truesize);
tcp_sk(sk)->scaling_ratio = val ? val : 1;
if (old_ratio != tcp_sk(sk)->scaling_ratio) { struct tcp_sock *tp = tcp_sk(sk);
val = tcp_win_from_space(sk, sk->sk_rcvbuf);
tcp_set_window_clamp(sk, val);
if (tp->window_clamp < tp->rcvq_space.space)
tp->rcvq_space.space = tp->window_clamp;
}
}
icsk->icsk_ack.rcv_mss = min_t(unsignedint, len,
tcp_sk(sk)->advmss); /* Account for possibly-removed options */
DO_ONCE_LITE_IF(len > icsk->icsk_ack.rcv_mss + MAX_TCP_OPTION_SPACE,
tcp_gro_dev_warn, sk, skb, len); /* If the skb has a len of exactly 1*MSS and has the PSH bit *setthenitislikelytheendofanapplicationwrite.So *moredatamaynotbearrivingsoon,andyetthedatasender *maybewaitingforanACKifcwnd-boundorusingTXzero *copy.SowesetICSK_ACK_PUSHEDheresothat *tcp_cleanup_rbuf()willsendanACKimmediatelyiftheapp *readsallofthedataandisnotping-pong.Iflen>MSS *thenthislogicdoesnotmatter(anddoesnothurt)because *tcp_cleanup_rbuf()willalwaysACKimmediatelyiftheapp *readsdataandthereismorethananMSSofunACKeddata.
*/ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_PSH)
icsk->icsk_ack.pending |= ICSK_ACK_PUSHED;
} else { /* Otherwise, we make more careful check taking into account, *thatSACKsblockisvariable. * *"len"isinvariantsegmentlength,includingTCPheader.
*/
len += skb->data - skb_transport_header(skb); if (len >= TCP_MSS_DEFAULT + sizeof(struct tcphdr) || /* If PSH is not set, packet should be *fullsized,providedpeerTCPisnotbadlybroken. *Thisobservation(ifitiscorrect8))allows *tohandlesuper-lowmtulinksfairly.
*/
(len >= TCP_MIN_MSS + sizeof(struct tcphdr) &&
!(tcp_flag_word(tcp_hdr(skb)) & TCP_REMNANT))) { /* Subtract also invariant (if peer is RFC compliant), *tcpheaderplusfixedtimestampoptionlength. *Resulting"len"isMSSfreeofSACKjitter.
*/
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;
}
}
/* If the sender is telling us it has entered CWR, then its *cwndmaybeverylow(evenjust1packet),soweshouldACK *immediately.
*/ if (TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq)
inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
}
}
switch (TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK) { case INET_ECN_NOT_ECT: /* Funny extension: if ECT is not set on a segment, *andwealreadyseenECTonaprevioussegment, *itisprobablyaretransmit.
*/ if (tp->ecn_flags & TCP_ECN_SEEN)
tcp_enter_quickack_mode(sk, 2); break; case INET_ECN_CE: if (tcp_ca_needs_ecn(sk))
tcp_ca_event(sk, CA_EVENT_ECN_IS_CE);
if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) { /* Better not delay acks, sender can have a very low cwnd */
tcp_enter_quickack_mode(sk, 2);
tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
}
tp->ecn_flags |= TCP_ECN_SEEN; break; default: if (tcp_ca_needs_ecn(sk))
tcp_ca_event(sk, CA_EVENT_ECN_NO_CE);
tp->ecn_flags |= TCP_ECN_SEEN; break;
}
}
/* Worst case is non GSO/TSO : each frame consumes one skb *andskb->headiskmallocedusingpoweroftwoareaofmemory
*/
per_mss = max_t(u32, tp->rx_opt.mss_clamp, tp->mss_cache) +
MAX_TCP_HEADER +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
/* Slow part of check#2. */ staticint __tcp_grow_window(conststruct sock *sk, conststruct sk_buff *skb, unsignedint skbtruesize)
{ conststruct tcp_sock *tp = tcp_sk(sk); /* Optimize this! */ int truesize = tcp_win_from_space(sk, skbtruesize) >> 1; int window = tcp_win_from_space(sk, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])) >> 1;
while (tp->rcv_ssthresh <= window) { if (truesize <= skb->len) return2 * inet_csk(sk)->icsk_ack.rcv_mss;
truesize >>= 1;
window >>= 1;
} return0;
}
/* Even if skb appears to have a bad len/truesize ratio, TCP coalescing *canplaynicewithus,assk_buffandskb->headmightbeeither *freedorsharedwithuptoMAX_SKB_FRAGSsegments. *Onlygiveaboosttodriversusingpagefrag(s)toholdtheframe(s), *andifnopayloadwaspulledinskb->headbeforereachingus.
*/ static u32 truesize_adjust(bool adjust, conststruct sk_buff *skb)
{
u32 truesize = skb->truesize;
if (adjust && !skb_headlen(skb)) {
truesize -= SKB_TRUESIZE(skb_end_offset(skb)); /* paranoid check, some drivers might be buggy */ if (unlikely((int)truesize < (int)skb->len))
truesize = skb->truesize;
} return truesize;
}
/* 3. Try to fixup all. It is made immediately after connection enters *establishedstate.
*/ staticvoid tcp_init_buffer_space(struct sock *sk)
{ int tcp_app_win = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_app_win); struct tcp_sock *tp = tcp_sk(sk); int maxwin;
if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK))
tcp_sndbuf_expand(sk);
if (old_sample == 0 || m < old_sample) {
new_sample = m;
} else { /* If we sample in larger samples in the non-timestamp *case,wecouldgrosslyoverestimatetheRTTespecially *withchattyapplicationsorbulktransferappswhich *arestalledonfilesystemI/O. * *Also,sinceweareonlygoingforaminimuminthe *non-timestampcase,wedonotsmooththingsout *elsewithtimestampsdisabledconvergencetakestoo *long.
*/ if (win_dep) return; /* Do not use this sample if receive queue is not empty. */ if (tp->rcv_nxt != tp->copied_seq) return;
new_sample = old_sample - (old_sample >> 3) + sample;
}
if (delta > 0)
tcp_rcv_rtt_update(tp, delta, 0);
}
}
staticvoid tcp_rcvbuf_grow(struct sock *sk)
{ conststruct net *net = sock_net(sk); struct tcp_sock *tp = tcp_sk(sk); int rcvwin, rcvbuf, cap;
if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) ||
(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) return;
/* slow start: allow the sender to double its rate. */
rcvwin = tp->rcvq_space.space << 1;
if (!RB_EMPTY_ROOT(&tp->out_of_order_queue))
rcvwin += TCP_SKB_CB(tp->ooo_last_skb)->end_seq - tp->rcv_nxt;
cap = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]);
rcvbuf = min_t(u32, tcp_space_from_win(sk, rcvwin), cap); if (rcvbuf > sk->sk_rcvbuf) {
WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); /* Make the window clamp follow along. */
WRITE_ONCE(tp->window_clamp,
tcp_win_from_space(sk, rcvbuf));
}
} /* *Thisfunctionshouldbecalledeverytimedataiscopiedtouserspace. *ItcalculatestheappropriateTCPreceivebufferspace.
*/ void tcp_rcv_space_adjust(struct sock *sk)
{ struct tcp_sock *tp = tcp_sk(sk); int time, inq, copied;
trace_tcp_rcv_space_adjust(sk);
tcp_mstamp_refresh(tp);
time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time); if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0) return;
/* Number of bytes copied to user in last RTT */
copied = tp->copied_seq - tp->rcvq_space.seq; /* Number of bytes in receive queue. */
inq = tp->rcv_nxt - tp->copied_seq;
copied -= inq; if (copied <= tp->rcvq_space.space) goto new_measure;
if (skb->protocol == htons(ETH_P_IPV6))
icsk->icsk_ack.lrcv_flowlabel = ntohl(ip6_flowlabel(ipv6_hdr(skb))); #endif
}
/* There is something which you must keep in mind when you analyze the *behaviorofthetp->atodelayedacktimeoutinterval.Whena *connectionstartsup,wewanttoackasquicklyaspossible.The *problemisthat"good"TCP'sdoslowstartatthebeginningofdata *transmission.ThemeansthatuntilwesendthefirstfewACK'sthe *senderwillsitonhisendandonlyqueuemostofhisdata,because *hecanonlysendsnd_cwndunackedpacketsatanygiventime.For *eachACKwesend,heincrementssnd_cwndandtransmitsmoreofhis *queue.-DaveM
*/ staticvoid 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_jiffies32;
if (!icsk->icsk_ack.ato) { /* The _first_ data packet received, initialize *delayedACKengine.
*/
tcp_incr_quickack(sk, TCP_MAX_QUICKACKS);
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;
} elseif (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;
} elseif (m > icsk->icsk_rto) { /* Too long gap. Apparently sender failed to *restartwindow,sothatwesendACKsquickly.
*/
tcp_incr_quickack(sk, TCP_MAX_QUICKACKS);
}
}
icsk->icsk_ack.lrcvtime = now;
tcp_save_lrcv_flowlabel(sk, skb);
tcp_data_ecn_check(sk, skb);
if (skb->len >= 128)
tcp_grow_window(sk, skb, true);
}
/* Called to compute a smoothed rtt estimate. The data fed to this *routineeithercomesfromtimestamps,orfromsegmentsthatwere *known_not_tohavebeenretransmitted[seeKarn/Partridge *ProceedingsSIGCOMM87].ThealgorithmisfromtheSIGCOMM88 *piecebyVanJacobson. *NOTE:thenextthreeroutinesusedtobeonebigroutine. *TosavecyclesintheRFC1323implementationitwasbettertobreak *itupintothreeprocedures.--erics
*/ staticvoid tcp_rtt_estimator(struct sock *sk, long mrtt_us)
{ struct tcp_sock *tp = tcp_sk(sk); long m = mrtt_us; /* RTT */
u32 srtt = tp->srtt_us;
/* The following amusing code comes from Jacobson's *articleinSIGCOMM'88.Notethatrttandmdev *arescaledversionsofrttandmeandeviation. *Thisisdesignedtobeasfastaspossible *mstandsfor"measurement". * *Ona1990paperthertovalueischangedto: *RTO=rtt+4*mdev * *Funny.Thisalgorithmseemstobeverybroken. *TheseformulaeincreaseRTO,whenitshouldbedecreased,increase *tooslowly,whenitshouldbeincreasedquickly,decreasetooquickly *etc.IguessinBSDRTOtakesONEvalue,sothatitisabsolutely *doesnotmatterhowto_calculate_it.Seems,itwastrap *thatVJfailedtoavoid.8)
*/ if (srtt != 0) {
m -= (srtt >> 3); /* m is now error in rtt est */
srtt += m; /* rtt = 7/8 rtt + 1/8 new */ if (m < 0) {
m = -m; /* m is now abs(error) */
m -= (tp->mdev_us >> 2); /* similar update on mdev */ /* This is similar to one of Eifel findings. *Eifelblocksmdevupdateswhenrttdecreases. *Thissolutionisabitdifferent:weusefinergain *formdevinthiscase(alpha*beta). *LikeEifelitalsopreventsgrowthofrto, *butalsoitlimitstoofastrtodecreases, *happeninginpureEifel.
*/ if (m > 0)
m >>= 3;
} else {
m -= (tp->mdev_us >> 2); /* similar update on mdev */
}
tp->mdev_us += m; /* mdev = 3/4 mdev + 1/4 new */ if (tp->mdev_us > tp->mdev_max_us) {
tp->mdev_max_us = tp->mdev_us; if (tp->mdev_max_us > tp->rttvar_us)
tp->rttvar_us = tp->mdev_max_us;
} if (after(tp->snd_una, tp->rtt_seq)) { if (tp->mdev_max_us < tp->rttvar_us)
tp->rttvar_us -= (tp->rttvar_us - tp->mdev_max_us) >> 2;
tp->rtt_seq = tp->snd_nxt;
tp->mdev_max_us = tcp_rto_min_us(sk);
tcp_bpf_rtt(sk, mrtt_us, srtt);
}
} else { /* no previous measure. */
srtt = m << 3; /* take the measured time to be rtt */
tp->mdev_us = m << 1; /* make sure rto = 3*rtt */
tp->rttvar_us = max(tp->mdev_us, tcp_rto_min_us(sk));
tp->mdev_max_us = tp->rttvar_us;
tp->rtt_seq = tp->snd_nxt;
/* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */
rate = (u64)tp->mss_cache * ((USEC_PER_SEC / 100) << 3);
/* current rate is (cwnd * mss) / srtt *InSlowStart[1],setsk_pacing_rateto200%thecurrentrate. *InCongestionAvoidancephase,setitto120%thecurrentrate. * *[1]:NormalSlowStartconditionis(tp->snd_cwnd<tp->snd_ssthresh) *Ifsnd_cwnd>=(tp->snd_ssthresh/2),weareapproaching *endofslowstartandshouldslowdown.
*/ if (tcp_snd_cwnd(tp) < tp->snd_ssthresh / 2)
rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio); else
rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio);
rate *= max(tcp_snd_cwnd(tp), tp->packets_out);
if (likely(tp->srtt_us))
do_div(rate, tp->srtt_us);
/* WRITE_ONCE() is needed because sch_fq fetches sk_pacing_rate *withoutanylock.Wewanttomakesurecompilerwontstore *intermediatevaluesinthislocation.
*/
WRITE_ONCE(sk->sk_pacing_rate,
min_t(u64, rate, READ_ONCE(sk->sk_max_pacing_rate)));
}
/* Calculate rto without backoff. This is the second half of Van Jacobson's *routinereferredtoabove.
*/ staticvoid tcp_set_rto(struct sock *sk)
{ conststruct tcp_sock *tp = tcp_sk(sk); /* Old crap is replaced with new one. 8) * *Moreseriously: *1.Ifrttvariancehappenedtobeless50msec,itishallucination. *ItcannotbelessduetoutterlyerraticACKgenerationmade *atleastbysolarisandfreebsd."ErraticACKs"has_nothing_ *todowithdelayedacks,becauseatcwnd>2truedelacktimeout *isinvisible.Actually,Linux-2.4alsogenerateserratic *ACKsinsomecircumstances.
*/
inet_csk(sk)->icsk_rto = __tcp_set_rto(tp);
/* 2. Fixups made earlier cannot be right. *IfwedonotestimateRTOcorrectlywithoutthem, *allthealgoispureshitandshouldbereplaced *withcorrectone.Itisexactly,whichwepretendtodo.
*/
/* NOTE: clamping at TCP_RTO_MIN is not required, current algo *guaranteesthatrtoishigher.
*/
tcp_bound_rto(sk);
}
if (!cwnd)
cwnd = TCP_INIT_CWND; return min_t(__u32, cwnd, tp->snd_cwnd_clamp);
}
struct tcp_sacktag_state { /* Timestamps for earliest and latest never-retransmitted segment *thatwasSACKed.RTOneedstheearliestRTTtostayconservative, *butcongestioncontrolshouldstillgetanaccuratedelaysignal.
*/
u64 first_sackt;
u64 last_sackt;
u32 reord;
u32 sack_delivered; int flag; unsignedint mss_now; struct rate_sample *rate;
};
/* Take a notice that peer is sending D-SACKs. Skip update of data delivery *andspuriousretransmissioninformationifthisDSACKisunlikelycausedby *sender'saction: *-DSACKedsequencerangeislargerthanmaximumreceiver'swindow. *-Totalno.ofDSACKedsegmentsexceedthetotalno.ofretransmittedsegs.
*/ static u32 tcp_dsack_seen(struct tcp_sock *tp, u32 start_seq,
u32 end_seq, struct tcp_sacktag_state *state)
{
u32 seq_len, dup_segs = 1;
if (!before(start_seq, end_seq)) return0;
seq_len = end_seq - start_seq; /* Dubious DSACK: DSACKed range greater than maximum advertised rwnd */ if (seq_len > tp->max_window) return0; if (seq_len > tp->mss_cache)
dup_segs = DIV_ROUND_UP(seq_len, tp->mss_cache); elseif (tp->tlp_high_seq && tp->tlp_high_seq == end_seq)
state->flag |= FLAG_DSACK_TLP;
tp->dsack_dups += dup_segs; /* Skip the DSACK if dup segs weren't retransmitted by sender */ if (tp->dsack_dups > tp->total_retrans) return0;
tp->rx_opt.sack_ok |= TCP_DSACK_SEEN; /* We increase the RACK ordering window in rounds where we receive *DSACKsthatmayhavebeenduetoreorderingcausingRACKtotrigger *aspuriousfastrecovery.ThusRACKignoresDSACKsthathappen *withouthavingseenreordering,orthatmatchTLPprobes(TLP *istimer-driven,nottriggeredbyRACK).
*/ if (tp->reord_seen && !(state->flag & FLAG_DSACK_TLP))
tp->rack.dsack_seen = 1;
state->flag |= FLAG_DSACKING_ACK; /* A spurious retransmission is delivered */
state->sack_delivered += dup_segs;
/* This exciting event is worth to be remembered. 8) */
tp->reord_seen++;
NET_INC_STATS(sock_net(sk),
ts ? LINUX_MIB_TCPTSREORDER : LINUX_MIB_TCPSACKREORDER);
}
/* This must be called before lost_out or retrans_out are updated *onanewloss,becausewewanttoknowifallskbspreviously *knowntobelosthavealreadybeenretransmitted,indicating *thatthisnewlylostskbisournextskbtoretransmit.
*/ staticvoid tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
{ if ((!tp->retransmit_skb_hint && tp->retrans_out >= tp->lost_out) ||
(tp->retransmit_skb_hint &&
before(TCP_SKB_CB(skb)->seq,
TCP_SKB_CB(tp->retransmit_skb_hint)->seq)))
tp->retransmit_skb_hint = skb;
}
/* Sum the number of packets on the wire we have marked as lost, and *notifythecongestioncontrolmodulethatthegivenskbwasmarkedlost.
*/ staticvoid tcp_notify_skb_loss_event(struct tcp_sock *tp, conststruct sk_buff *skb)
{
tp->lost += tcp_skb_pcount(skb);
}
/* Nasty start_seq wrap-around check (see comments above) */ if (!before(start_seq, tp->snd_nxt)) returnfalse;
/* In outstanding window? ...This is valid exit for D-SACKs too. *start_seq==snd_unaisnon-sensical(seecommentsabove)
*/ if (after(start_seq, tp->snd_una)) returntrue;
if (!is_dsack || !tp->undo_marker) returnfalse;
/* ...Then it's D-SACK, and must reside below snd_una completely */ if (after(end_seq, tp->snd_una)) returnfalse;
if (!before(start_seq, tp->undo_marker)) returntrue;
/* Too old */ if (!after(end_seq, tp->undo_marker)) returnfalse;
/* Undo_marker boundary crossing (overestimates a lot). Known already: *start_seq<undo_markerandend_seq>=undo_marker.
*/ return !before(start_seq, end_seq - tp->max_window);
}
/* Mark the given newly-SACKed range as such, adjusting counters and hints. */ static u8 tcp_sacktag_one(struct sock *sk, struct tcp_sacktag_state *state, u8 sacked,
u32 start_seq, u32 end_seq, int dup_sack, int pcount,
u64 xmit_time)
{ struct tcp_sock *tp = tcp_sk(sk);
/* Nothing to do; acked frame is about to be dropped (was ACKed). */ if (!after(end_seq, tp->snd_una)) return sacked;
if (!(sacked & TCPCB_SACKED_ACKED)) {
tcp_rack_advance(tp, sacked, end_seq, xmit_time);
if (sacked & TCPCB_SACKED_RETRANS) { /* If the segment is not tagged as lost, *wedonotclearRETRANS,believing *thatretransmissionisstillinflight.
*/ if (sacked & TCPCB_LOST) {
sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
tp->lost_out -= pcount;
tp->retrans_out -= pcount;
}
} else { if (!(sacked & TCPCB_RETRANS)) { /* New sack for not retransmitted frame, *whichwasinhole.Itisreordering.
*/ if (before(start_seq,
tcp_highest_sack_seq(tp)) &&
before(start_seq, state->reord))
state->reord = start_seq;
if (!after(end_seq, tp->high_seq))
state->flag |= FLAG_ORIG_SACK_ACKED; if (state->first_sackt == 0)
state->first_sackt = xmit_time;
state->last_sackt = xmit_time;
}
/* D-SACK. We can detect redundant retransmission in S|R and plain R *framesandclearit.undo_retransisdecreasedabove,L|Rframes *areaccountedaboveaswell.
*/ if (dup_sack && (sacked & TCPCB_SACKED_RETRANS)) {
sacked &= ~TCPCB_SACKED_RETRANS;
tp->retrans_out -= pcount;
}
return sacked;
}
/* Shift newly-SACKed bytes from this skb to the immediately previous *already-SACKedsk_buff.Markthenewly-SACKedbytesassuch.
*/ staticbool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev, struct sk_buff *skb, struct tcp_sacktag_state *state, unsignedint pcount, int shifted, int mss, bool dup_sack)
{ struct tcp_sock *tp = tcp_sk(sk);
u32 start_seq = TCP_SKB_CB(skb)->seq; /* start of newly-SACKed */
u32 end_seq = start_seq + shifted; /* end of newly-SACKed */
BUG_ON(!pcount);
/* Adjust counters and hints for the newly sacked sequence *rangebutdiscardthereturnvaluesinceprevisalready *marked.Wemusttagtherangefirstbecausetheseq *advancementbelowimplicitlyadvances *tcp_highest_sack_seq()whenskbishighest_sack.
*/
tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked,
start_seq, end_seq, dup_sack, pcount,
tcp_skb_timestamp_us(skb));
tcp_rate_skb_delivered(sk, skb, state->rate);
/* When we're adding to gso_segs == 1, gso_size will be zero, *intheorythisshouldn'tbenecessarybutaslongasDSACK *codecancomeafterthisskblateronit'sbettertokeep *settinggso_sizetosomething.
*/ if (!TCP_SKB_CB(prev)->tcp_gso_size)
TCP_SKB_CB(prev)->tcp_gso_size = mss;
/* CHECKME: To clear or not to clear? Mimics normal skb currently */ if (tcp_skb_pcount(skb) <= 1)
TCP_SKB_CB(skb)->tcp_gso_size = 0;
/* Difference in this won't matter, both ACKed by the same cumul. ACK */
TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS);
if (skb->len > 0) {
BUG_ON(!tcp_skb_pcount(skb));
NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKSHIFTED); returnfalse;
}
/* Whole SKB was eaten :-) */
if (skb == tp->retransmit_skb_hint)
tp->retransmit_skb_hint = prev;
/* I wish gso_size would have a bit more sane initialization than *something-or-zerowhichcomplicatesthings
*/ staticint tcp_skb_seglen(conststruct sk_buff *skb)
{ return tcp_skb_pcount(skb) == 1 ? skb->len : tcp_skb_mss(skb);
}
/* Shifting pages past head area doesn't work */ staticint skb_can_shift(conststruct sk_buff *skb)
{ return !skb_headlen(skb) && skb_is_nonlinear(skb);
}
int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen)
{ /* TCP min gso_size is 8 bytes (TCP_MIN_GSO_SIZE) *SinceTCP_SKB_CB(skb)->tcp_gso_segsis16bits,weneed *tomakesurenotstoringmorethan65535*8bytesperskb, *evenifcurrentMSSisbigger.
*/ if (unlikely(to->len + shiftlen >= 65535 * TCP_MIN_GSO_SIZE)) return0; if (unlikely(tcp_skb_pcount(to) + pcount > 65535)) return0; return skb_shift(to, from, shiftlen);
}
/* Try collapsing SACK blocks spanning across multiple skbs to a single *skb.
*/ staticstruct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, struct tcp_sacktag_state *state,
u32 start_seq, u32 end_seq, bool dup_sack)
{ struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *prev; int mss; int pcount = 0; int len; int in_sack;
/* Normally R but no L won't result in plain S */ if (!dup_sack &&
(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_RETRANS)) == TCPCB_SACKED_RETRANS) goto fallback; if (!skb_can_shift(skb)) goto fallback; /* This frame is about to be dropped (was ACKed). */ if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) goto fallback;
/* Can only happen with delayed DSACK + discard craziness */
prev = skb_rb_prev(skb); if (!prev) goto fallback;
if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) goto fallback;
if (!tcp_skb_can_collapse(prev, skb)) goto fallback;
if (in_sack) {
len = skb->len;
pcount = tcp_skb_pcount(skb);
mss = tcp_skb_seglen(skb);
/* TODO: Fix DSACKs to not fragment already SACKed and we can *dropthisrestrictionasunnecessary
*/ if (mss != tcp_skb_seglen(prev)) goto fallback;
} else { if (!after(TCP_SKB_CB(skb)->end_seq, start_seq)) goto noop; /* CHECKME: This is non-MSS split case only?, this will *causeskippedskbsduetoadvancingloopbtw,original *hasthatfeaturetoo
*/ if (tcp_skb_pcount(skb) <= 1) goto noop;
in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq); if (!in_sack) { /* TODO: head merge to next could be attempted here *if(!after(TCP_SKB_CB(skb)->end_seq,end_seq)), *thoughitmightnotbeworthoftheadditionalhassle * *...wecanprobablyjustfallbacktowhatwasdone *previously.Wecouldtrymergingnon-SACKedones *aswellbutitprobablyisn'tgoingtobuyoff *becauselaterSACKsmightagainsplitthem,and *itwouldmakeskbtimestamptrackingconsiderably *harderproblem.
*/ goto fallback;
}
/* MSS boundaries should be honoured or else pcount will *severelybreakeventhoughitmakesthingsbittrickier. *Optimizecommoncasetoavoidmostofthedivides
*/
mss = tcp_skb_mss(skb);
/* TODO: Fix DSACKs to not fragment already SACKed and we can *dropthisrestrictionasunnecessary
*/ if (mss != tcp_skb_seglen(prev)) goto fallback;
if (!tcp_skb_shift(prev, skb, pcount, len)) goto fallback; if (!tcp_shifted_skb(sk, prev, skb, state, pcount, len, mss, dup_sack)) goto out;
/* Hole filled allows collapsing with the next as well, this is very *usefulwhenholeoneverynthskbpatternhappens
*/
skb = skb_rb_next(prev); if (!skb) goto out;
skb_rbtree_walk_from(skb) { int in_sack = 0; bool dup_sack = dup_sack_in;
/* queue is in-order => we can short-circuit the walk early */ if (!before(TCP_SKB_CB(skb)->seq, end_seq)) break;
if (next_dup &&
before(TCP_SKB_CB(skb)->seq, next_dup->end_seq)) {
in_sack = tcp_match_skb_to_sack(sk, skb,
next_dup->start_seq,
next_dup->end_seq); if (in_sack > 0)
dup_sack = true;
}
/* skb reference here is a bit tricky to get right, since *shiftingcaneatandfreeboththisskbandthenext, *sonoteven_safevariantoftheloopisenough.
*/ if (in_sack <= 0) {
tmp = tcp_shift_skb_data(sk, skb, state,
start_seq, end_seq, dup_sack); if (tmp) { if (tmp != skb) {
skb = tmp; continue;
}
/* Eliminate too old ACKs, but take into *accountmoreorlessfreshones,theycan *containvalidSACKinfo.
*/ if (before(TCP_SKB_CB(ack_skb)->ack_seq, prior_snd_una - tp->max_window)) return0;
if (!tp->packets_out) goto out;
used_sacks = 0;
first_sack_index = 0; for (i = 0; i < num_sacks; i++) { bool dup_sack = !i && found_dup_sack;
if (!tcp_is_sackblock_valid(tp, dup_sack,
sp[used_sacks].start_seq,
sp[used_sacks].end_seq)) { int mib_idx;
if (dup_sack) { if (!tp->undo_marker)
mib_idx = LINUX_MIB_TCPDSACKIGNOREDNOUNDO; else
mib_idx = LINUX_MIB_TCPDSACKIGNOREDOLD;
} else { /* Don't count olds caused by ACK reordering */ if ((TCP_SKB_CB(ack_skb)->ack_seq != tp->snd_una) &&
!after(sp[used_sacks].end_seq, tp->snd_una)) continue;
mib_idx = LINUX_MIB_TCPSACKDISCARD;
}
NET_INC_STATS(sock_net(sk), mib_idx); if (i == 0)
first_sack_index = -1; continue;
}
/* Ignore very old stuff early */ if (!after(sp[used_sacks].end_seq, prior_snd_una)) { if (i == 0)
first_sack_index = -1; continue;
}
used_sacks++;
}
/* order SACK blocks to allow in order walk of the retrans queue */ for (i = used_sacks - 1; i > 0; i--) { for (j = 0; j < i; j++) { if (after(sp[j].start_seq, sp[j + 1].start_seq)) {
swap(sp[j], sp[j + 1]);
/* Track where the first SACK block goes to */ if (j == first_sack_index)
first_sack_index = j + 1;
}
}
}
state->mss_now = tcp_current_mss(sk);
skb = NULL;
i = 0;
if (!tp->sacked_out) { /* It's already past, so skip checking against it */
cache = tp->recv_sack_cache + ARRAY_SIZE(tp->recv_sack_cache);
} else {
cache = tp->recv_sack_cache; /* Skip empty blocks in at head of the cache */ while (tcp_sack_cache_ok(tp, cache) && !cache->start_seq &&
!cache->end_seq)
cache++;
}
while (i < used_sacks) {
u32 start_seq = sp[i].start_seq;
u32 end_seq = sp[i].end_seq; bool dup_sack = (found_dup_sack && (i == first_sack_index)); struct tcp_sack_block *next_dup = NULL;
/* Clear the head of the cache sack blocks so we can skip it next time */ for (i = 0; i < ARRAY_SIZE(tp->recv_sack_cache) - used_sacks; i++) {
tp->recv_sack_cache[i].start_seq = 0;
tp->recv_sack_cache[i].end_seq = 0;
} for (j = 0; j < used_sacks; j++)
tp->recv_sack_cache[i++] = sp[j];
if (inet_csk(sk)->icsk_ca_state != TCP_CA_Loss || tp->undo_marker)
tcp_check_sack_reordering(sk, state->reord, 0);
/* Limits sacked_out so that sum with lost_out isn't ever larger than *packets_out.Returnsfalseifsacked_outadjustementwasn'tnecessary.
*/ staticbool tcp_limit_reno_sacked(struct tcp_sock *tp)
{
u32 holes;
/* Retransmission still in flight may cause DSACKs later. */ /* First, account for regular retransmits in flight: */
tp->undo_retrans = tp->retrans_out; /* Next, account for TLP retransmits in flight: */ if (tp->tlp_high_seq && tp->tlp_retrans)
tp->undo_retrans++; /* Finally, avoid 0, because undo_retrans==0 means "can undo now": */ if (!tp->undo_retrans)
tp->undo_retrans = -1;
}
/* If we detect SACK reneging, forget all SACK information *andresettagscompletely,otherwisepreserveSACKs.Ifreceiver *droppeditsofoqueue,wewillknowthisduetorenegingdetection.
*/ staticvoid tcp_timeout_mark_lost(struct sock *sk)
{ struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb, *head; bool is_reneg; /* is receiver reneging on SACKs? */
head = tcp_rtx_queue_head(sk);
is_reneg = head && (TCP_SKB_CB(head)->sacked & TCPCB_SACKED_ACKED); if (is_reneg) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
tp->sacked_out = 0; /* Mark SACK reneging until we recover from this loss event. */
tp->is_sack_reneg = 1;
} elseif (tcp_is_reno(tp)) {
tcp_reset_reno_sack(tp);
}
skb = head;
skb_rbtree_walk_from(skb) { if (is_reneg)
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED; elseif (skb != head && tcp_rack_skb_timeout(tp, skb, 0) > 0) continue; /* Don't mark recently sent ones lost yet */
tcp_mark_skb_lost(sk, skb);
}
tcp_verify_left_out(tp);
tcp_clear_all_retrans_hints(tp);
}
/* Linux NewReno/SACK/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 a few algorithms detecting
* lost packets.
*
* If the receiver supports SACK:
*
* RACK (RFC8985): RACK is a newer loss detection algorithm
* (2017-) that checks timing instead of counting DUPACKs.
* Essentially a packet is considered lost if it's not S/ACKed
* after RTT + reordering_window, where both metrics are
* dynamically measured and adjusted. This is implemented in
* tcp_rack_mark_lost.
*
* If the receiver does not support SACK:
*
* NewReno (RFC6582): in Recovery 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.
*
* The really tricky (and requiring careful tuning) part of the algorithm
* is hidden in the RACK code in tcp_recovery.c 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 bool tcp_time_to_recover(const struct tcp_sock *tp)
{
/* Has loss detection marked at least one packet lost? */
return tp->lost_out != 0;
}
/* skb is spurious retransmitted if the returned timestamp echo
* reply is prior to the skb transmission time
*/
static bool tcp_skb_spurious_retrans(const struct tcp_sock *tp,
const struct sk_buff *skb)
{
return (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) &&
tcp_tsopt_ecr_before(tp, tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb));
}
/* Nothing was retransmitted or returned timestamp is less
* than timestamp of the first retransmission.
*/
static inline bool tcp_packet_delayed(const struct tcp_sock *tp)
{
const struct sock *sk = (const struct sock *)tp;
/* Received an echoed timestamp before the first retransmission? */
if (tp->retrans_stamp)
return tcp_tsopt_ecr_before(tp, tp->retrans_stamp);
/* We set tp->retrans_stamp upon the first retransmission of a loss
* recovery episode, so normally if tp->retrans_stamp is 0 then no
* retransmission has happened yet (likely due to TSQ, which can cause
* fast retransmits to be delayed). So if snd_una advanced while
* (tp->retrans_stamp is 0 then apparently a packet was merely delayed,
* not lost. But there are exceptions where we retransmit but then
* clear tp->retrans_stamp, so we check for those exceptions.
*/
/* (1) For non-SACK connections, tcp_is_non_sack_preventing_reopen()
* clears tp->retrans_stamp when snd_una == high_seq.
*/
if (!tcp_is_sack(tp) && !before(tp->snd_una, tp->high_seq))
return false;
/* (2) In TCP_SYN_SENT tcp_clean_rtx_queue() clears tp->retrans_stamp
* when setting FLAG_SYN_ACKED is set, even if the SYN was
* retransmitted.
*/
if (sk->sk_state == TCP_SYN_SENT)
return false;
return true; /* tp->retrans_stamp is zero; no retransmit yet */
}
/* Undo procedures. */
/* We can clear retrans_stamp when there are no retransmissions in the
* window. It would seem that it is trivially available for us in
* tp->retrans_out, however, that kind of assumptions doesn't consider
* what will happen if errors occur when sending retransmission for the
* second time. ...It could the that such segment has only
* TCPCB_EVER_RETRANS set at the present time. It seems that checking
* the head skb is enough except for some reneging corner cases that
* are not worth the effort.
*
* Main reason for all this complexity is the fact that connection dying
* time now depends on the validity of the retrans_stamp, in particular,
* that successive retransmissions of a segment must not advance
* retrans_stamp under any conditions.
*/
static bool tcp_any_retrans_done(const struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
/* If loss recovery is finished and there are no retransmits out in the
* network, then we clear retrans_stamp so that upon the next loss recovery
* retransmits_timed_out() and timestamp-undo are using the correct value.
*/
static void tcp_retrans_stamp_cleanup(struct sock *sk)
{
if (!tcp_any_retrans_done(sk))
tcp_sk(sk)->retrans_stamp = 0;
}
if (tp->snd_una == tp->high_seq && tcp_is_reno(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. */
if (!tcp_any_retrans_done(sk))
tp->retrans_stamp = 0;
return true;
}
return false;
}
/* People celebrate: "We love our President!" */
static bool tcp_try_undo_recovery(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
if (tcp_may_undo(tp)) {
int mib_idx;
/* 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_cwnd_reduction(sk, false);
if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
mib_idx = LINUX_MIB_TCPLOSSUNDO;
else
mib_idx = LINUX_MIB_TCPFULLUNDO;
/* Undo during loss recovery after partial ACK or using F-RTO. */
static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
{
struct tcp_sock *tp = tcp_sk(sk);
if (frto_undo || tcp_may_undo(tp)) {
tcp_undo_cwnd_reduction(sk, true);
/* The cwnd reduction in CWR and Recovery uses the PRR algorithm in RFC 6937.
* It computes the number of packets to send (sndcnt) based on packets newly
* delivered:
* 1) If the packets in flight is larger than ssthresh, PRR spreads the
* cwnd reductions across a full RTT.
* 2) Otherwise PRR uses packet conservation to send as much as delivered.
* But when SND_UNA is acked without further losses,
* slow starts cwnd up to ssthresh to speed up the recovery.
*/
static void tcp_init_cwnd_reduction(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
/* Sometimes we deduce that packets have been dropped due to reasons other than
* congestion, like path MTU reductions or failed client TFO attempts. In these
* cases we call this function to retransmit as many packets as cwnd allows,
* without reducing cwnd. Given that retransmits will set retrans_stamp to a
* non-zero value (and may do so in a later calling context due to TSQ), we
* also enter CA_Loss so that we track when all retransmitted packets are ACKed
* and clear retrans_stamp when that happens (to ensure later recurring RTOs
* are using the correct retrans_stamp and don't declare ETIMEDOUT
* prematurely).
*/
static void tcp_non_congestion_loss_retransmit(struct sock *sk)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
/* Do a simple retransmit without using the backoff mechanisms in
* tcp_timer. This is used for path mtu discovery.
* The socket is already locked here.
*/
void tcp_simple_retransmit(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
int mss;
/* A fastopen SYN request is stored as two separate packets within
* the retransmit queue, this is done by tcp_send_syn_data().
* As a result simply checking the MSS of the frames in the queue
* will not work for the SYN packet.
*
* Us being here is an indication of a path MTU issue so we can
* assume that the fastopen SYN was lost and just mark all the
* frames in the retransmit queue as lost. We will use an MSS of
* -1 to mark all frames as lost, otherwise compute the current MSS.
*/
if (tp->syn_data && sk->sk_state == TCP_SYN_SENT)
mss = -1;
else
mss = tcp_current_mss(sk);
skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
if (tcp_skb_seglen(skb) > mss)
tcp_mark_skb_lost(sk, skb);
}
if (!tp->lost_out)
return;
if (tcp_is_reno(tp))
tcp_limit_reno_sacked(tp);
tcp_verify_left_out(tp);
/* Don't muck with the congestion window here.
* Reason is that we do not increase amount of _data_
* in network, but units changed and effective
* cwnd/ssthresh really reduced now.
*/
tcp_non_congestion_loss_retransmit(sk);
}
EXPORT_IPV6_MOD(tcp_simple_retransmit);
/* Process an ACK in CA_Loss state. Move to CA_Open if lost data are
* recovered or spurious. Otherwise retransmits more on partial ACKs.
*/
static void tcp_process_loss(struct sock *sk, int flag, int num_dupack,
int *rexmit)
{
struct tcp_sock *tp = tcp_sk(sk);
bool recovered = !before(tp->snd_una, tp->high_seq);
if ((flag & FLAG_SND_UNA_ADVANCED || rcu_access_pointer(tp->fastopen_rsk)) &&
tcp_try_undo_loss(sk, false))
return;
if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
/* Step 3.b. A timeout is spurious if not all data are
* lost, i.e., never-retransmitted data are (s)acked.
*/
if ((flag & FLAG_ORIG_SACK_ACKED) &&
tcp_try_undo_loss(sk, true))
return;
if (after(tp->snd_nxt, tp->high_seq)) {
if (flag & FLAG_DATA_SACKED || num_dupack)
tp->frto = 0; /* Step 3.a. loss was real */
} else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) {
tp->high_seq = tp->snd_nxt;
/* Step 2.b. Try send new data (but deferred until cwnd
* is updated in tcp_ack()). Otherwise fall back to
* the conventional recovery.
*/
if (!tcp_write_queue_empty(sk) &&
after(tcp_wnd_end(tp), tp->snd_nxt)) {
*rexmit = REXMIT_NEW;
return;
}
tp->frto = 0;
}
}
if (recovered) {
/* F-RTO RFC5682 sec 3.1 step 2.a and 1st part of step 3.a */
tcp_try_undo_recovery(sk);
return;
}
if (tcp_is_reno(tp)) {
/* A Reno DUPACK means new data in F-RTO step 2.b above are
* delivered. Lower inflight to clock out (re)transmissions.
*/
if (after(tp->snd_nxt, tp->high_seq) && num_dupack)
tcp_add_reno_sack(sk, num_dupack, flag & FLAG_ECE);
else if (flag & FLAG_SND_UNA_ADVANCED)
tcp_reset_reno_sack(tp);
}
*rexmit = REXMIT_LOST;
}
/* Undo during fast recovery after partial ACK. */
static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una)
{
struct tcp_sock *tp = tcp_sk(sk);
if (tp->undo_marker && tcp_packet_delayed(tp)) {
/* Plain luck! Hole if filled with delayed
* packet, rather than with a retransmit. Check reordering.
*/
tcp_check_sack_reordering(sk, prior_snd_una, 1);
/* We are getting evidence that the reordering degree is higher
* than we realized. If there are no retransmits out then we
* can undo. Otherwise we clock out new packets but do not
* mark more packets lost or retransmit more.
*/
if (tp->retrans_out)
return true;
if (!tcp_any_retrans_done(sk))
tp->retrans_stamp = 0;
if (tcp_rack_mark_lost(sk))
*ack_flag &= ~FLAG_SET_XMIT_TIMER;
if (prior_retrans > tp->retrans_out)
*ack_flag |= FLAG_LOST_RETRANS;
}
}
/* 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 updates the congestion state when packet loss or ECN
* is detected. But it does not reduce the cwnd, it is done by the
* congestion control later.
*
* It does _not_ decide what to send, it is made in function
* tcp_xmit_retransmit_queue().
*/
static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
int num_dupack, int *ack_flag, int *rexmit)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
int flag = *ack_flag;
bool ece_ack = flag & FLAG_ECE;
if (!tp->packets_out && tp->sacked_out)
tp->sacked_out = 0;
/* Now state machine starts.
* A. ECE, hence prohibit cwnd undoing, the reduction is required. */
if (ece_ack)
tp->prior_ssthresh = 0;
/* B. In all the states check for reneging SACKs. */
if (tcp_check_sack_reneging(sk, ack_flag))
return;
/* C. Check consistency of the current state. */
tcp_verify_left_out(tp);
/* D. Check state exit conditions. State can be terminated
* when high_seq is ACKed. */
if (icsk->icsk_ca_state == TCP_CA_Open) {
WARN_ON(tp->retrans_out != 0 && !tp->syn_data);
tp->retrans_stamp = 0;
} else if (!before(tp->snd_una, tp->high_seq)) {
switch (icsk->icsk_ca_state) {
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_end_cwnd_reduction(sk);
tcp_set_ca_state(sk, TCP_CA_Open);
}
break;
case TCP_CA_Recovery:
if (tcp_is_reno(tp))
tcp_reset_reno_sack(tp);
if (tcp_try_undo_recovery(sk))
return;
tcp_end_cwnd_reduction(sk);
break;
}
}
/* E. Process state. */
switch (icsk->icsk_ca_state) {
case TCP_CA_Recovery:
if (!(flag & FLAG_SND_UNA_ADVANCED)) {
if (tcp_is_reno(tp))
tcp_add_reno_sack(sk, num_dupack, ece_ack);
} else if (tcp_try_undo_partial(sk, prior_snd_una))
return;
if (tcp_try_undo_dsack(sk))
tcp_try_to_open(sk, flag);
tcp_identify_packet_loss(sk, ack_flag);
if (icsk->icsk_ca_state != TCP_CA_Recovery) {
if (!tcp_time_to_recover(tp))
return;
/* Undo reverts the recovery state. If loss is evident,
* starts a new recovery (e.g. reordering then loss);
*/
tcp_enter_recovery(sk, ece_ack);
}
break;
case TCP_CA_Loss:
tcp_process_loss(sk, flag, num_dupack, rexmit);
if (icsk->icsk_ca_state != TCP_CA_Loss)
tcp_update_rto_time(tp);
tcp_identify_packet_loss(sk, ack_flag);
if (!(icsk->icsk_ca_state == TCP_CA_Open ||
(*ack_flag & FLAG_LOST_RETRANS)))
return;
/* Change state if cwnd is undone or retransmits are lost */
fallthrough;
default:
if (tcp_is_reno(tp)) {
if (flag & FLAG_SND_UNA_ADVANCED)
tcp_reset_reno_sack(tp);
tcp_add_reno_sack(sk, num_dupack, ece_ack);
}
if (icsk->icsk_ca_state <= TCP_CA_Disorder)
tcp_try_undo_dsack(sk);
tcp_identify_packet_loss(sk, ack_flag);
if (!tcp_time_to_recover(tp)) {
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() */
tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) + 1);
tcp_simple_retransmit(sk);
return;
}
/* Otherwise enter Recovery state */
tcp_enter_recovery(sk, ece_ack);
}
if ((flag & FLAG_ACK_MAYBE_DELAYED) && rtt_us > tcp_min_rtt(tp)) {
/* If the remote keeps returning delayed ACKs, eventually
* the min filter would pick it up and overestimate the
* prop. delay when it expires. Skip suspected delayed ACKs.
*/
return;
}
minmax_running_min(&tp->rtt_min, wlen, tcp_jiffies32,
rtt_us ? : jiffies_to_usecs(1));
}
static bool tcp_ack_update_rtt(struct sock *sk, const int flag,
long seq_rtt_us, long sack_rtt_us,
long ca_rtt_us, struct rate_sample *rs)
{
const struct tcp_sock *tp = tcp_sk(sk);
/* Prefer RTT measured from ACK's timing to TS-ECR. This is because
* broken middle-boxes or peers may corrupt TS-ECR fields. But
* Karn's algorithm forbids taking RTT if some retransmitted data
* is acked (RFC6298).
*/
if (seq_rtt_us < 0)
seq_rtt_us = sack_rtt_us;
/* 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.
*/
if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp &&
tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED)
seq_rtt_us = ca_rtt_us = tcp_rtt_tsopt_us(tp, 1);
rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */
if (seq_rtt_us < 0)
return false;
/* ca_rtt_us >= 0 is counting on the invariant that ca_rtt_us is
* always taken together with ACK, SACK, or TS-opts. Any negative
* values will be skipped with the seq_rtt_us < 0 check above.
*/
tcp_update_rtt_min(sk, ca_rtt_us, flag);
tcp_rtt_estimator(sk, seq_rtt_us);
tcp_set_rto(sk);
/* RFC6298: only reset backoff on valid RTT measurement. */
inet_csk(sk)->icsk_backoff = 0;
return true;
}
/* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */
void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req)
{
struct rate_sample rs;
long rtt_us = -1L;
if (req && !req->num_retrans && tcp_rsk(req)->snt_synack)
rtt_us = tcp_stamp_us_delta(tcp_clock_us(), tcp_rsk(req)->snt_synack);
/* Restart timer after forward progress on connection.
* RFC2988 recommends to restart timer to now+rto.
*/
void tcp_rearm_rto(struct sock *sk)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
/* If the retrans timer is currently being used by Fast Open
* for SYN-ACK retrans purpose, stay put.
*/
if (rcu_access_pointer(tp->fastopen_rsk))
return;
if (!tp->packets_out) {
inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
} else {
u32 rto = inet_csk(sk)->icsk_rto;
/* Offset the time elapsed after installing regular RTO */
if (icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
s64 delta_us = tcp_rto_delta_us(sk);
/* delta_us may not be positive if the socket is locked
* when the retrans timer fires and is rescheduled.
*/
rto = usecs_to_jiffies(max_t(int, delta_us, 1));
}
tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto, true);
}
}
/* Try to schedule a loss probe; if that doesn't work, then schedule an RTO. */
static void tcp_set_xmit_timer(struct sock *sk)
{
if (!tcp_schedule_loss_probe(sk, true))
tcp_rearm_rto(sk);
}
/* If we get here, the whole TSO packet has not been acked. */
static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 packets_acked;
/* Determine how many packets and what bytes were acked, tso and else */
if (after(scb->end_seq, tp->snd_una)) {
if (tcp_skb_pcount(skb) == 1 ||
!after(tp->snd_una, scb->seq))
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 ata, we will erroneously exit
* connection startup slow start one packet too
* quickly. This is severely frowned upon behavior.
*/
if (likely(!(scb->tcp_flags & TCPHDR_SYN))) {
flag |= FLAG_DATA_ACKED;
} else {
flag |= FLAG_SYN_ACKED;
tp->retrans_stamp = 0;
}
if (!fully_acked)
break;
tcp_ack_tstamp(sk, skb, ack_skb, prior_snd_una);
next = skb_rb_next(skb);
if (unlikely(skb == tp->retransmit_skb_hint))
tp->retransmit_skb_hint = NULL;
tcp_highest_sack_replace(sk, skb, next);
tcp_rtx_queue_unlink_and_free(skb, sk);
}
if (!skb)
tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
if (likely(between(tp->snd_up, prior_snd_una, tp->snd_una)))
tp->snd_up = tp->snd_una;
if (skb) {
tcp_ack_tstamp(sk, skb, ack_skb, prior_snd_una);
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
flag |= FLAG_SACK_RENEGING;
}
if (pkts_acked == 1 && fully_acked && !prior_sacked &&
(tp->snd_una - prior_snd_una) < tp->mss_cache &&
sack->rate->prior_delivered + 1 == tp->delivered &&
!(flag & (FLAG_CA_ALERT | FLAG_SYN_ACKED))) {
/* Conservatively mark a delayed ACK. It's typically
* from a lone runt packet over the round trip to
* a receiver w/o out-of-order or CE events.
*/
flag |= FLAG_ACK_MAYBE_DELAYED;
}
}
if (sack->first_sackt) {
sack_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, sack->first_sackt);
ca_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, sack->last_sackt);
}
rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us,
ca_rtt_us, sack->rate);
if (flag & FLAG_ACKED) {
flag |= FLAG_SET_XMIT_TIMER; /* set TLP or RTO timer */
if (unlikely(icsk->icsk_mtup.probe_size &&
!after(tp->mtu_probe.probe_seq_end, tp->snd_una))) {
tcp_mtup_probe_success(sk);
}
if (tcp_is_reno(tp)) {
tcp_remove_reno_sacks(sk, pkts_acked, ece_ack);
/* If any of the cumulatively ACKed segments was
* retransmitted, non-SACK case cannot confirm that
* progress was due to original transmission due to
* lack of TCPCB_SACKED_ACKED bits even if some of
* the packets may have been never retransmitted.
*/
if (flag & FLAG_RETRANS_DATA_ACKED)
flag &= ~FLAG_ORIG_SACK_ACKED;
} else {
/* Non-retransmitted hole got filled? That's reordering */
if (before(reord, prior_fack))
tcp_check_sack_reordering(sk, reord, 0);
}
} else if (skb && rtt_update && sack_rtt_us >= 0 &&
sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp,
tcp_skb_timestamp_us(skb))) {
/* Do not re-arm RTO if the sack RTT is measured from data sent
* after when the head was last (re)transmitted. Otherwise the
* timeout may continue to extend in loss recovery.
*/
flag |= FLAG_SET_XMIT_TIMER; /* set TLP or RTO timer */
}
/* Was it a usable window open? */
if (!head)
return;
if (!after(TCP_SKB_CB(head)->end_seq, tcp_wnd_end(tp))) {
icsk->icsk_backoff = 0;
icsk->icsk_probes_tstamp = 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 {
unsigned long when = tcp_probe0_when(sk, tcp_rto_max(sk));
when = tcp_clamp_probe0_to_user_timeout(sk, when);
tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, when, true);
}
}
/* Decide wheather to run the increase function of congestion control. */
static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag)
{
/* If reordering is high then always grow cwnd whenever data is
* delivered regardless of its ordering. Otherwise stay conservative
* and only grow cwnd on in-order delivery (RFC5681). A stretched ACK w/
* new SACK or ECE mark may first advance cwnd here and later reduce
* cwnd in tcp_fastretrans_alert() based on more states.
*/
if (tcp_sk(sk)->reordering >
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering))
return flag & FLAG_FORWARD_PROGRESS;
return flag & FLAG_DATA_ACKED;
}
/* The "ultimate" congestion control function that aims to replace the rigid
* cwnd increase and decrease control (tcp_cong_avoid,tcp_*cwnd_reduction).
* It's called toward the end of processing an ACK with precise rate
* information. All transmission or retransmission are delayed afterwards.
*/
static void tcp_cong_control(struct sock *sk, u32 ack, u32 acked_sacked,
int flag, const struct rate_sample *rs)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
if (icsk->icsk_ca_ops->cong_control) {
icsk->icsk_ca_ops->cong_control(sk, ack, flag, rs);
return;
}
if (tcp_in_cwnd_reduction(sk)) {
/* Reduce cwnd if state mandates */
tcp_cwnd_reduction(sk, acked_sacked, rs->losses, flag);
} else if (tcp_may_raise_cwnd(sk, flag)) {
/* Advance cwnd if state allows */
tcp_cong_avoid(sk, ack, acked_sacked);
}
tcp_update_pacing_rate(sk);
}
/* Check that window update is acceptable.
* The function assumes that snd_una<=ack<=snd_next.
*/
static inline bool 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 || !nwin));
}
/* 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, const 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_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 (!tcp_write_queue_empty(sk))
tcp_slow_start_after_idle_check(sk);
static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
u32 *last_oow_ack_time)
{
/* Paired with the WRITE_ONCE() in this function. */
u32 val = READ_ONCE(*last_oow_ack_time);
if (val) {
s32 elapsed = (s32)(tcp_jiffies32 - val);
/* Paired with the prior READ_ONCE() and with itself,
* as we might be lockless.
*/
WRITE_ONCE(*last_oow_ack_time, tcp_jiffies32);
return false; /* not rate-limited: go ahead, send dupack now! */
}
/* Return true if we're currently rate-limiting out-of-window ACKs and
* thus shouldn't send a dupack right now. We rate-limit dupacks in
* response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS
* attacks that send repeated SYNs or ACKs for the same connection. To
* do this, we do not send a duplicate SYNACK or ACK if the remote
* endpoint is sending out-of-window SYNs or pure ACKs at a high rate.
*/
bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb,
int mib_idx, u32 *last_oow_ack_time)
{
/* Data packets without SYNs are not likely part of an ACK loop. */
if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) &&
!tcp_hdr(skb)->syn)
return false;
static int tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
{
s32 delta;
if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) {
/* PAWS bug workaround wrt. ACK frames, the PAWS discard
* extra check below makes sure this can only happen
* for pure ACK frames. -DaveM
*
* Not only, also it occurs for expired timestamps.
*/
/* This routine deals with acks during a TLP episode and ends an episode by
* resetting tlp_high_seq. Ref: TLP algorithm in RFC8985
*/
static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
if (before(ack, tp->tlp_high_seq))
return;
if (!tp->tlp_retrans) {
/* TLP of new data has been acknowledged */
tp->tlp_high_seq = 0;
} else if (flag & FLAG_DSACK_TLP) {
/* This DSACK means original and TLP probe arrived; no loss */
tp->tlp_high_seq = 0;
} else if (after(ack, tp->tlp_high_seq)) {
/* ACK advances: there was a loss, so reduce cwnd. Reset
* tlp_high_seq in tcp_init_cwnd_reduction()
*/
tcp_init_cwnd_reduction(sk);
tcp_set_ca_state(sk, TCP_CA_CWR);
tcp_end_cwnd_reduction(sk);
tcp_try_keep_open(sk);
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPLOSSPROBERECOVERY);
} else if (!(flag & (FLAG_SND_UNA_ADVANCED |
FLAG_NOT_DUP | FLAG_DATA_SACKED))) {
/* Pure dupack: original and TLP probe arrived; no loss */
tp->tlp_high_seq = 0;
}
}
/* Congestion control has updated the cwnd already. So if we're in
* loss recovery then now we do any new sends (for FRTO) or
* retransmits (for CA_Loss or CA_recovery) that make sense.
*/
static void tcp_xmit_recovery(struct sock *sk, int rexmit)
{
struct tcp_sock *tp = tcp_sk(sk);
if (rexmit == REXMIT_NONE || sk->sk_state == TCP_SYN_SENT)
return;
if (unlikely(rexmit == REXMIT_NEW)) {
__tcp_push_pending_frames(sk, tcp_current_mss(sk),
TCP_NAGLE_OFF);
if (after(tp->snd_nxt, tp->high_seq))
return;
tp->frto = 0;
}
tcp_xmit_retransmit_queue(sk);
}
/* Returns the number of packets newly acked or sacked by the current ACK */
static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered, int flag)
{
const struct net *net = sock_net(sk);
struct tcp_sock *tp = tcp_sk(sk);
u32 delivered;
/* We very likely will need to access rtx queue. */
prefetch(sk->tcp_rtx_queue.rb_node);
/* If the ack is older than previous acks
* then we can probably ignore it.
*/
if (before(ack, prior_snd_una)) {
u32 max_window;
/* do not accept ACK for bytes we never sent. */
max_window = min_t(u64, tp->max_window, tp->bytes_acked);
/* RFC 59615.2 [Blind Data Injection Attack].[Mitigation] */
if (before(ack, prior_snd_una - max_window)) {
if (!(flag & FLAG_NO_CHALLENGE_ACK))
tcp_send_challenge_ack(sk);
return -SKB_DROP_REASON_TCP_TOO_OLD_ACK;
}
goto old_ack;
}
/* If the ack includes data we haven't sent yet, discard
* this segment (RFC793 Section 3.9).
*/
if (after(ack, tp->snd_nxt))
return -SKB_DROP_REASON_TCP_ACK_UNSENT_DATA;
if (after(ack, prior_snd_una)) {
flag |= FLAG_SND_UNA_ADVANCED;
icsk->icsk_retransmits = 0;
#if IS_ENABLED(CONFIG_TLS_DEVICE)
if (static_branch_unlikely(&clean_acked_data_enabled.key))
if (tp->tcp_clean_acked)
tp->tcp_clean_acked(sk, ack);
#endif
}
/* ts_recent update must be made after we are sure that the packet
* is in window.
*/
if (flag & FLAG_UPDATE_TS_RECENT)
flag |= tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
if ((flag & (FLAG_SLOWPATH | FLAG_SND_UNA_ADVANCED)) ==
FLAG_SND_UNA_ADVANCED) {
/* Window is constant, pure forward advance.
* No more checks are required.
* Note, we use the fact that SND.UNA>=SND.WL2.
*/
tcp_update_wl(tp, ack_seq);
tcp_snd_una_update(tp, ack);
flag |= FLAG_WIN_UPDATE;
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPACKS);
} else {
if (ack_seq != TCP_SKB_CB(skb)->end_seq)
flag |= FLAG_DATA;
else
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPUREACKS);
flag |= tcp_ack_update_window(sk, skb, ack, ack_seq);
if (TCP_SKB_CB(skb)->sacked)
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
&sack_state);
if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb)))
flag |= FLAG_ECE;
if (sack_state.sack_delivered)
tcp_count_delivered(tp, sack_state.sack_delivered,
flag & FLAG_ECE);
}
/* This is a deviation from RFC3168 since it states that:
* "When the TCP data sender is ready to set the CWR bit after reducing
* the congestion window, it SHOULD set the CWR bit only on the first
* new data packet that it transmits."
* We accept CWR on pure ACKs to be more robust
* with widely-deployed TCP implementations that do this.
*/
tcp_ecn_accept_cwr(sk, skb);
/* We passed data and got it acked, remove any soft error
* log. Something worked...
*/
WRITE_ONCE(sk->sk_err_soft, 0);
icsk->icsk_probes_out = 0;
tp->rcv_tstamp = tcp_jiffies32;
if (!prior_packets)
goto no_queue;
/* See if we can take anything off of the retransmit queue. */
flag |= tcp_clean_rtx_queue(sk, skb, prior_fack, prior_snd_una,
&sack_state, flag & FLAG_ECE);
tcp_rack_update_reo_wnd(sk, &rs);
tcp_in_ack_event(sk, flag);
if (tp->tlp_high_seq)
tcp_process_tlp_ack(sk, ack, flag);
if (tcp_ack_is_dubious(sk, flag)) {
if (!(flag & (FLAG_SND_UNA_ADVANCED |
FLAG_NOT_DUP | FLAG_DSACKING_ACK))) {
num_dupack = 1;
/* Consider if pure acks were aggregated in tcp_add_backlog() */
if (!(flag & FLAG_DATA))
num_dupack = max_t(u16, 1, skb_shinfo(skb)->gso_segs);
}
tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag,
&rexmit);
}
/* If needed, reset TLP/RTO timer when RACK doesn't set. */
if (flag & FLAG_SET_XMIT_TIMER)
tcp_set_xmit_timer(sk);
if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
sk_dst_confirm(sk);
no_queue:
tcp_in_ack_event(sk, flag);
/* If data was DSACKed, see if we can undo a cwnd reduction. */
if (flag & FLAG_DSACKING_ACK) {
tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag,
&rexmit);
tcp_newly_delivered(sk, delivered, flag);
}
/* If this ack opens up a zero window, clear backoff. It was
* being used to time the probes, and is probably far higher than
* it needs to be for normal retransmission.
*/
tcp_ack_probe(sk);
if (tp->tlp_high_seq)
tcp_process_tlp_ack(sk, ack, flag);
return 1;
old_ack:
/* If data was SACKed, tag it and see if we should send more data.
* If data was DSACKed, see if we can undo a cwnd reduction.
*/
if (TCP_SKB_CB(skb)->sacked) {
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
&sack_state);
tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag,
&rexmit);
tcp_newly_delivered(sk, delivered, flag);
tcp_xmit_recovery(sk, rexmit);
}
return 0;
}
static void tcp_parse_fastopen_option(int len, const unsigned char *cookie,
bool syn, struct tcp_fastopen_cookie *foc,
bool exp_opt)
{
/* Valid only in SYN or SYN-ACK with an even length. */
if (!foc || !syn || len < 0 || (len & 1))
return;
if (len >= TCP_FASTOPEN_COOKIE_MIN &&
len <= TCP_FASTOPEN_COOKIE_MAX)
memcpy(foc->val, cookie, len);
else if (len != 0)
len = -1;
foc->len = len;
foc->exp = exp_opt;
}
/* Look for tcp options. Normally only called on SYN and SYNACK packets.
* But, this can also be called on packets in the established flow when
* the fast version below fails.
*/
void tcp_parse_options(const struct net *net,
const struct sk_buff *skb,
struct tcp_options_received *opt_rx, int estab,
struct tcp_fastopen_cookie *foc)
{
const unsigned char *ptr;
const struct tcphdr *th = tcp_hdr(skb);
int length = (th->doff * 4) - sizeof(struct tcphdr);
/* Fast parse options. This hopes to only see timestamps.
* If it is wrong it falls back on tcp_parse_options().
*/
static bool tcp_fast_parse_options(const struct net *net,
const struct sk_buff *skb,
const struct tcphdr *th, struct tcp_sock *tp)
{
/* In the spirit of fast parsing, compare doff directly to constant
* values. Because equality is used, short doff can be ignored here.
*/
if (th->doff == (sizeof(*th) / 4)) {
tp->rx_opt.saw_tstamp = 0;
return false;
} else if (tp->rx_opt.tstamp_ok &&
th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4)) {
if (tcp_parse_aligned_timestamp(tp, th))
return true;
}
if (IS_ENABLED(CONFIG_TCP_AO))
minlen = sizeof(struct tcp_ao_hdr) + 1;
*md5_hash = NULL;
*ao_hash = NULL;
/* If not enough data remaining, we can short cut */
while (length >= minlen) {
int opcode = *ptr++;
int opsize;
switch (opcode) {
case TCPOPT_EOL:
return 0;
case TCPOPT_NOP:
length--;
continue;
default:
opsize = *ptr++;
if (opsize < 2 || opsize > length)
return -EINVAL;
if (opcode == TCPOPT_MD5SIG) {
if (opsize != TCPOLEN_MD5SIG)
return -EINVAL;
if (unlikely(*md5_hash || *ao_hash))
return -EEXIST;
*md5_hash = ptr;
} else if (opcode == TCPOPT_AO) {
if (opsize <= sizeof(struct tcp_ao_hdr))
return -EINVAL;
if (unlikely(*md5_hash || *ao_hash))
return -EEXIST;
*ao_hash = ptr;
}
}
ptr += opsize - 2;
length -= opsize;
}
return 0;
}
EXPORT_SYMBOL(tcp_do_parse_auth_options);
#endif
/* Sorry, PAWS as specified is broken wrt. pure-ACKs -DaveM
*
* It is not fatal. If this ACK does _not_ change critical state (seqs, window)
* it can pass through stack. So, the following predicate verifies that
* this segment is not used for anything but congestion avoidance or
* fast retransmit. Moreover, we even are able to eliminate most of such
* second order effects, if we apply some small "replay" window (~RTO)
* to timestamp space.
*
* All these measures still do not guarantee that we reject wrapped ACKs
* on networks with high bandwidth, when sequence space is recycled fastly,
* but it guarantees that such events will be very rare and do not affect
* connection seriously. This doesn't look nice, but alas, PAWS is really
* buggy extension.
*
* [ Later note. Even worse! It is buggy for segments _with_ data. RFC
* states that events when retransmit arrives after original data are rare.
* It is a blatant lie. VJ forgot about fast retransmit! 8)8) It is
* the biggest problem on large power networks even with minor reordering.
* OK, let's give it small replay window. If peer clock is even 1hz, it is safe
* up to bandwidth of 18Gigabit/sec. 8) ]
*/
/* Estimates max number of increments of remote peer TSval in
* a replay window (based on our current RTO estimation).
*/
static u32 tcp_tsval_replay(const struct sock *sk)
{
/* If we use usec TS resolution,
* then expect the remote peer to use the same resolution.
*/
if (tcp_sk(sk)->tcp_usec_ts)
return inet_csk(sk)->icsk_rto * (USEC_PER_SEC / HZ);
/* RFC 7323 recommends a TSval clock between 1ms and 1sec.
* We know that some OS (including old linux) can use 1200 Hz.
*/
return inet_csk(sk)->icsk_rto * 1200 / HZ;
}
/* 1. Is this not a pure ACK ? */
if (!th->ack || seq != TCP_SKB_CB(skb)->end_seq)
return reason;
/* 2. Is its sequence not the expected one ? */
if (seq != tp->rcv_nxt)
return before(seq, tp->rcv_nxt) ?
SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK :
reason;
/* 3. Is this not a duplicate ACK ? */
if (ack != tp->snd_una)
return reason;
/* 4. Is this updating the window ? */
if (tcp_may_update_window(tp, ack, seq, ntohs(th->window) <<
tp->rx_opt.snd_wscale))
return reason;
/* 5. Is this not in the replay window ? */
if ((s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) >
tcp_tsval_replay(sk))
return reason;
return 0;
}
/* Check segment sequence number for validity.
*
* Segment controls are considered valid, if the segment
* fits to the window after truncation to the window. Acceptability
* of data (and SYN, FIN, of course) is checked separately.
* See tcp_data_queue(), for example.
*
* Also, controls (RST is main one) are accepted using RCV.WUP instead
* of RCV.NXT. Peer still did not advance his SND.UNA when we
* delayed ACK, so that hisSND.UNA<=ourRCV.WUP.
* (borrowed from freebsd)
*/
if (before(end_seq, tp->rcv_wup))
return SKB_DROP_REASON_TCP_OLD_SEQUENCE;
if (after(end_seq, tp->rcv_nxt + tcp_receive_window(tp))) {
if (after(seq, tp->rcv_nxt + tcp_receive_window(tp)))
return SKB_DROP_REASON_TCP_INVALID_SEQUENCE;
/* Only accept this packet if receive queue is empty. */
if (skb_queue_len(&sk->sk_receive_queue))
return SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE;
}
return SKB_NOT_DROPPED_YET;
}
void tcp_done_with_error(struct sock *sk, int err)
{
/* This barrier is coupled with smp_rmb() in tcp_poll() */
WRITE_ONCE(sk->sk_err, err);
smp_wmb();
tcp_write_queue_purge(sk);
tcp_done(sk);
if (!sock_flag(sk, SOCK_DEAD))
sk_error_report(sk);
}
EXPORT_IPV6_MOD(tcp_done_with_error);
/* When we get a reset we do this. */
void tcp_reset(struct sock *sk, struct sk_buff *skb)
{
int err;
trace_tcp_receive_reset(sk);
/* mptcp can't tell us to ignore reset pkts,
* so just ignore the return value of mptcp_incoming_options().
*/
if (sk_is_mptcp(sk))
mptcp_incoming_options(sk, skb);
/* We want the right error as BSD sees it (and indeed as we do). */
switch (sk->sk_state) {
case TCP_SYN_SENT:
err = ECONNREFUSED;
break;
case TCP_CLOSE_WAIT:
err = EPIPE;
break;
case TCP_CLOSE:
return;
default:
err = ECONNRESET;
}
tcp_done_with_error(sk, err);
}
/*
* Process the FIN bit. This now behaves as it is supposed to work
* and the FIN takes effect when it is validly part of sequence
* space. Not before when we get holes.
*
* If we are ESTABLISHED, a received fin moves us to CLOSE-WAIT
* (and thence onto LAST-ACK and finally, CLOSE, we never enter
* TIME-WAIT)
*
* If we are in FINWAIT-1, a received FIN indicates simultaneous
* close and we go into CLOSING (and later onto TIME-WAIT)
*
* If we are in FINWAIT-2, a received FIN moves us to TIME-WAIT.
*/
void tcp_fin(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
switch (sk->sk_state) {
case TCP_SYN_RECV:
case TCP_ESTABLISHED:
/* Move to CLOSE_WAIT */
tcp_set_state(sk, TCP_CLOSE_WAIT);
inet_csk_enter_pingpong_mode(sk);
break;
case TCP_CLOSE_WAIT:
case TCP_CLOSING:
/* Received a retransmission of the FIN, do
* nothing.
*/
break;
case TCP_LAST_ACK:
/* RFC793: Remain in the LAST-ACK state. */
break;
case TCP_FIN_WAIT1:
/* This case occurs when a simultaneous close
* happens, we must ack the received FIN and
* enter the CLOSING state.
*/
tcp_send_ack(sk);
tcp_set_state(sk, TCP_CLOSING);
break;
case TCP_FIN_WAIT2:
/* Received a FIN -- send ACK and enter TIME_WAIT. */
tcp_send_ack(sk);
tcp_time_wait(sk, TCP_TIME_WAIT, 0);
break;
default:
/* Only TCP_LISTEN and TCP_CLOSE are left, in these
* cases we should never reach this piece of code.
*/
pr_err("%s: Impossible, sk->sk_state=%d\n",
__func__, sk->sk_state);
break;
}
/* It _is_ possible, that we have something out-of-order _after_ FIN.
* Probably, we should reset in this case. For now drop them.
*/
skb_rbtree_purge(&tp->out_of_order_queue);
if (tcp_is_sack(tp))
tcp_sack_reset(&tp->rx_opt);
if (!sock_flag(sk, SOCK_DEAD)) {
sk->sk_state_change(sk);
/* Do not send POLL_HUP for half duplex close. */
if (sk->sk_shutdown == SHUTDOWN_MASK ||
sk->sk_state == TCP_CLOSE)
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
else
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
}
}
if (!tp->rx_opt.dsack)
tcp_dsack_set(sk, seq, end_seq);
else
tcp_sack_extend(tp->duplicate_sack, seq, end_seq);
}
static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb)
{
/* When the ACK path fails or drops most ACKs, the sender would
* timeout and spuriously retransmit the same segment repeatedly.
* If it seems our ACKs are not reaching the other side,
* based on receiving a duplicate data segment with new flowlabel
* (suggesting the sender suffered an RTO), and we are not already
* repathing due to our own RTO, then rehash the socket to repath our
* packets.
*/
#if IS_ENABLED(CONFIG_IPV6)
if (inet_csk(sk)->icsk_ca_state != TCP_CA_Loss &&
skb->protocol == htons(ETH_P_IPV6) &&
(tcp_sk(sk)->inet_conn.icsk_ack.lrcv_flowlabel !=
ntohl(ip6_flowlabel(ipv6_hdr(skb)))) &&
sk_rethink_txhash(sk))
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDUPLICATEDATAREHASH);
/* Save last flowlabel after a spurious retrans. */
tcp_save_lrcv_flowlabel(sk, skb);
#endif
}
/* These routines update the SACK block as out-of-order packets arrive or
* in-order packets close up the sequence space.
*/
static void tcp_sack_maybe_coalesce(struct tcp_sock *tp)
{
int this_sack;
struct tcp_sack_block *sp = &tp->selective_acks[0];
struct tcp_sack_block *swalk = sp + 1;
/* See if the recent change to the first SACK eats into
* or hits the sequence space of other SACK blocks, if so coalesce.
*/
for (this_sack = 1; this_sack < tp->rx_opt.num_sacks;) {
if (tcp_sack_extend(sp, swalk->start_seq, swalk->end_seq)) {
int i;
/* Zap SWALK, by moving every further SACK up by one slot.
* Decrease num_sacks.
*/
tp->rx_opt.num_sacks--;
for (i = this_sack; i < tp->rx_opt.num_sacks; i++)
sp[i] = sp[i + 1];
continue;
}
this_sack++;
swalk++;
}
}
if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1)
__sock_put(sk);
/* Since we have to send one ack finally,
* substract one from tp->compressed_ack to keep
* LINUX_MIB_TCPACKCOMPRESSED accurate.
*/
NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED,
tp->compressed_ack - 1);
tp->compressed_ack = 0;
tcp_send_ack(sk);
}
/* Reasonable amount of sack blocks included in TCP SACK option
* The max is 4, but this becomes 3 if TCP timestamps are there.
* Given that SACK packets might be lost, be conservative and use 2.
*/
#define TCP_SACK_BLOCKS_EXPECTED 2
for (this_sack = 0; this_sack < cur_sacks; this_sack++, sp++) {
if (tcp_sack_extend(sp, seq, end_seq)) {
if (this_sack >= TCP_SACK_BLOCKS_EXPECTED)
tcp_sack_compress_send_ack(sk);
/* Rotate this_sack to the first one. */
for (; this_sack > 0; this_sack--, sp--)
swap(*sp, *(sp - 1));
if (cur_sacks > 1)
tcp_sack_maybe_coalesce(tp);
return;
}
}
if (this_sack >= TCP_SACK_BLOCKS_EXPECTED)
tcp_sack_compress_send_ack(sk);
/* Could not find an adjacent existing SACK, build a new one,
* put it at the front, and shift everyone else down. We
* always know there is at least one SACK present already here.
*
* If the sack array is full, forget about the last one.
*/
if (this_sack >= TCP_NUM_SACKS) {
this_sack--;
tp->rx_opt.num_sacks--;
sp--;
}
for (; this_sack > 0; this_sack--, sp--)
*sp = *(sp - 1);
new_sack:
/* Build the new head SACK, and we're done. */
sp->start_seq = seq;
sp->end_seq = end_seq;
tp->rx_opt.num_sacks++;
}
/* RCV.NXT advances, some SACKs should be eaten. */
static void tcp_sack_remove(struct tcp_sock *tp)
{
struct tcp_sack_block *sp = &tp->selective_acks[0];
int num_sacks = tp->rx_opt.num_sacks;
int this_sack;
/* Empty ofo queue, hence, all the SACKs are eaten. Clear. */
if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) {
tp->rx_opt.num_sacks = 0;
return;
}
for (this_sack = 0; this_sack < num_sacks;) {
/* Check if the start of the sack is covered by RCV.NXT. */
if (!before(tp->rcv_nxt, sp->start_seq)) {
int i;
/* RCV.NXT must cover all the block! */
WARN_ON(before(tp->rcv_nxt, sp->end_seq));
/* Zap this SACK, by moving forward any other SACKS. */
for (i = this_sack+1; i < num_sacks; i++)
tp->selective_acks[i-1] = tp->selective_acks[i];
num_sacks--;
continue;
}
this_sack++;
sp++;
}
tp->rx_opt.num_sacks = num_sacks;
}
/**
* tcp_try_coalesce - try to merge skb to prior one
* @sk: socket
* @to: prior buffer
* @from: buffer to add in queue
* @fragstolen: pointer to boolean
*
* Before queueing skb @from after @to, try to merge them
* to reduce overall memory use and queue lengths, if cost is small.
* Packets in ofo or receive queues can stay a long time.
* Better try to coalesce them right now to avoid future collapses.
* Returns true if caller should free @from instead of queueing it
*/
static bool tcp_try_coalesce(struct sock *sk,
struct sk_buff *to,
struct sk_buff *from,
bool *fragstolen)
{
int delta;
*fragstolen = false;
/* Its possible this segment overlaps with prior segment in queue */
if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
return false;
if (!tcp_skb_can_collapse_rx(to, from))
return false;
if (!skb_try_coalesce(to, from, fragstolen, &delta))
return false;
/* In case tcp_drop_reason() is called later, update to->gso_segs */
if (res) {
u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) +
max_t(u16, 1, skb_shinfo(from)->gso_segs);
/* This one checks to see if we can put data from the
* out_of_order queue into the receive_queue.
*/
static void tcp_ofo_queue(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
__u32 dsack_high = tp->rcv_nxt;
bool fin, fragstolen, eaten;
struct sk_buff *skb, *tail;
struct rb_node *p;
p = rb_first(&tp->out_of_order_queue);
while (p) {
skb = rb_to_skb(p);
if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
break;
if (before(TCP_SKB_CB(skb)->seq, dsack_high)) {
__u32 dsack = dsack_high;
if (before(TCP_SKB_CB(skb)->end_seq, dsack_high))
dsack = TCP_SKB_CB(skb)->end_seq;
tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack);
}
p = rb_next(p);
rb_erase(&skb->rbnode, &tp->out_of_order_queue);
if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) {
tcp_drop_reason(sk, skb, SKB_DROP_REASON_TCP_OFO_DROP);
continue;
}
/* Check if this incoming skb can be added to socket receive queues
* while satisfying sk->sk_rcvbuf limit.
*
* In theory we should use skb->truesize, but this can cause problems
* when applications use too small SO_RCVBUF values.
* When LRO / hw gro is used, the socket might have a high tp->scaling_ratio,
* allowing RWIN to be close to available space.
* Whenever the receive queue gets full, we can receive a small packet
* filling RWIN, but with a high skb->truesize, because most NIC use 4K page
* plus sk_buff metadata even when receiving less than 1500 bytes of payload.
*
* Note that we use skb->len to decide to accept or drop this packet,
* but sk->sk_rmem_alloc is the sum of all skb->truesize.
*/
static bool tcp_can_ingest(const struct sock *sk, const struct sk_buff *skb)
{
unsigned int rmem = atomic_read(&sk->sk_rmem_alloc);
return rmem + skb->len <= sk->sk_rcvbuf;
}
static int tcp_try_rmem_schedule(struct sock *sk, const struct sk_buff *skb,
unsigned int size)
{
if (!tcp_can_ingest(sk, skb) ||
!sk_rmem_schedule(sk, skb, size)) {
if (tcp_prune_queue(sk, skb) < 0)
return -1;
while (!sk_rmem_schedule(sk, skb, size)) {
if (!tcp_prune_ofo_queue(sk, skb))
return -1;
}
}
return 0;
}
p = &tp->out_of_order_queue.rb_node;
if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) {
/* Initial out of order segment, build 1 SACK. */
if (tcp_is_sack(tp)) {
tp->rx_opt.num_sacks = 1;
tp->selective_acks[0].start_seq = seq;
tp->selective_acks[0].end_seq = end_seq;
}
rb_link_node(&skb->rbnode, NULL, p);
rb_insert_color(&skb->rbnode, &tp->out_of_order_queue);
tp->ooo_last_skb = skb;
goto end;
}
/* In the typical case, we are adding an skb to the end of the list.
* Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
*/
if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
skb, &fragstolen)) {
coalesce_done:
/* For non sack flows, do not grow window to force DUPACK
* and trigger fast retransmit.
*/
if (tcp_is_sack(tp))
tcp_grow_window(sk, skb, true);
kfree_skb_partial(skb, fragstolen);
skb = NULL;
goto add_sack;
}
/* Can avoid an rbtree lookup if we are adding skb after ooo_last_skb */
if (!before(seq, TCP_SKB_CB(tp->ooo_last_skb)->end_seq)) {
parent = &tp->ooo_last_skb->rbnode;
p = &parent->rb_right;
goto insert;
}
/* Find place to insert this segment. Handle overlaps on the way. */
parent = NULL;
while (*p) {
parent = *p;
skb1 = rb_to_skb(parent);
if (before(seq, TCP_SKB_CB(skb1)->seq)) {
p = &parent->rb_left;
continue;
}
if (before(seq, TCP_SKB_CB(skb1)->end_seq)) {
if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
/* All the bits are present. Drop. */
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPOFOMERGE);
tcp_drop_reason(sk, skb,
SKB_DROP_REASON_TCP_OFOMERGE);
skb = NULL;
tcp_dsack_set(sk, seq, end_seq);
goto add_sack;
}
if (after(seq, TCP_SKB_CB(skb1)->seq)) {
/* Partial overlap. */
tcp_dsack_set(sk, seq, TCP_SKB_CB(skb1)->end_seq);
} else {
/* skb's seq == skb1's seq and skb covers skb1.
* Replace skb1 with skb.
*/
rb_replace_node(&skb1->rbnode, &skb->rbnode,
&tp->out_of_order_queue);
tcp_dsack_extend(sk,
TCP_SKB_CB(skb1)->seq,
TCP_SKB_CB(skb1)->end_seq);
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPOFOMERGE);
tcp_drop_reason(sk, skb1,
SKB_DROP_REASON_TCP_OFOMERGE);
goto merge_right;
}
} else if (tcp_ooo_try_coalesce(sk, skb1,
skb, &fragstolen)) {
goto coalesce_done;
}
p = &parent->rb_right;
}
insert:
/* Insert segment into RB tree. */
rb_link_node(&skb->rbnode, parent, p);
rb_insert_color(&skb->rbnode, &tp->out_of_order_queue);
merge_right:
/* Remove other segments covered by skb. */
while ((skb1 = skb_rb_next(skb)) != NULL) {
if (!after(end_seq, TCP_SKB_CB(skb1)->seq))
break;
if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq,
end_seq);
break;
}
rb_erase(&skb1->rbnode, &tp->out_of_order_queue);
tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq,
TCP_SKB_CB(skb1)->end_seq);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE);
tcp_drop_reason(sk, skb1, SKB_DROP_REASON_TCP_OFOMERGE);
}
/* If there is no skb after us, we are the last_skb ! */
if (!skb1)
tp->ooo_last_skb = skb;
add_sack:
if (tcp_is_sack(tp))
tcp_sack_new_ofo_skb(sk, seq, end_seq);
end:
if (skb) {
/* For non sack flows, do not grow window to force DUPACK
* and trigger fast retransmit.
*/
if (tcp_is_sack(tp))
tcp_grow_window(sk, skb, false);
skb_condense(skb);
skb_set_owner_r(skb, sk);
}
/* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */
if (sk->sk_socket)
tcp_rcvbuf_grow(sk);
}
static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb,
bool *fragstolen)
{
int eaten;
struct sk_buff *tail = skb_peek_tail(&sk->sk_receive_queue);
/* If a subflow has been reset, the packet should not continue
* to be processed, drop the packet.
*/
if (sk_is_mptcp(sk) && !mptcp_incoming_options(sk, skb)) {
__kfree_skb(skb);
return;
}
/* Queue data for delivery to the user.
* Packets in sequence go to the receive queue.
* Out of sequence packets to the out_of_order_queue.
*/
if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) {
if (tcp_receive_window(tp) == 0) {
/* Some stacks are known to send bare FIN packets
* in a loop even if we send RWIN 0 in our ACK.
* Accepting this FIN does not hurt memory pressure
* because the FIN flag will simply be merged to the
* receive queue tail skb in most cases.
*/
if (!skb->len &&
(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN))
goto queue_and_out;
eaten = tcp_queue_rcv(sk, skb, &fragstolen);
if (skb->len)
tcp_event_data_recv(sk, skb);
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
tcp_fin(sk);
if (!RB_EMPTY_ROOT(&tp->out_of_order_queue)) {
tcp_ofo_queue(sk);
/* RFC5681. 4.2. SHOULD send immediate ACK, when
* gap in queue is filled.
*/
if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
}
if (tp->rx_opt.num_sacks)
tcp_sack_remove(tp);
tcp_fast_path_check(sk);
if (eaten > 0)
kfree_skb_partial(skb, fragstolen);
if (!sock_flag(sk, SOCK_DEAD))
tcp_data_ready(sk);
return;
}
if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
tcp_rcv_spurious_retrans(sk, skb);
/* A retransmit, 2nd most common case. Force an immediate ack. */
reason = SKB_DROP_REASON_TCP_OLD_DATA;
NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
/* If window is closed, drop tail of packet. But after
* remembering D-SACK for its head made in previous line.
*/
if (!tcp_receive_window(tp)) {
reason = SKB_DROP_REASON_TCP_ZEROWINDOW;
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP);
goto out_of_window;
}
goto queue_and_out;
}
while (*p) {
parent = *p;
skb1 = rb_to_skb(parent);
if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq))
p = &parent->rb_left;
else
p = &parent->rb_right;
}
rb_link_node(&skb->rbnode, parent, p);
rb_insert_color(&skb->rbnode, root);
}
/* Collapse contiguous sequence of skbs head..tail with
* sequence numbers start..end.
*
* If tail is NULL, this means until the end of the queue.
*
* Segments with FIN/SYN are not collapsed (only because this
* simplifies code)
*/
static void
tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
struct sk_buff *head, struct sk_buff *tail, u32 start, u32 end)
{
struct sk_buff *skb = head, *n;
struct sk_buff_head tmp;
bool end_of_skbs;
/* First, check that queue is collapsible and find
* the point where collapsing can be useful.
*/
restart:
for (end_of_skbs = true; skb != NULL && skb != tail; skb = n) {
n = tcp_skb_next(skb, list);
if (!skb_frags_readable(skb))
goto skip_this;
/* No new bits? It is possible on ofo queue. */
if (!before(start, TCP_SKB_CB(skb)->end_seq)) {
skb = tcp_collapse_one(sk, skb, list, root);
if (!skb)
break;
goto restart;
}
/* The first skb to collapse is:
* - not SYN/FIN and
* - bloated or contains data before "start" or
* overlaps to the next one and mptcp allow collapsing.
*/
if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) &&
(tcp_win_from_space(sk, skb->truesize) > skb->len ||
before(TCP_SKB_CB(skb)->seq, start))) {
end_of_skbs = false;
break;
}
/* Range is terminated when we see a gap or when
* we are at the queue end.
*/
if (!skb ||
after(TCP_SKB_CB(skb)->seq, end) ||
before(TCP_SKB_CB(skb)->end_seq, start)) {
/* Do not attempt collapsing tiny skbs */
if (range_truesize != head->truesize ||
end - start >= SKB_WITH_OVERHEAD(PAGE_SIZE)) {
tcp_collapse(sk, NULL, &tp->out_of_order_queue,
head, skb, start, end);
} else {
sum_tiny += range_truesize;
if (sum_tiny > sk->sk_rcvbuf >> 3)
return;
}
goto new_range;
}
range_truesize += skb->truesize;
if (unlikely(before(TCP_SKB_CB(skb)->seq, start)))
start = TCP_SKB_CB(skb)->seq;
if (after(TCP_SKB_CB(skb)->end_seq, end))
end = TCP_SKB_CB(skb)->end_seq;
}
}
/*
* Clean the out-of-order queue to make room.
* We drop high sequences packets to :
* 1) Let a chance for holes to be filled.
* This means we do not drop packets from ooo queue if their sequence
* is before incoming packet sequence.
* 2) not add too big latencies if thousands of packets sit there.
* (But if application shrinks SO_RCVBUF, we could still end up
* freeing whole queue here)
* 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks.
*
* Return true if queue has shrunk.
*/
static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb)
{
struct tcp_sock *tp = tcp_sk(sk);
struct rb_node *node, *prev;
bool pruned = false;
int goal;
if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
return false;
/* If incoming skb would land last in ofo queue, stop pruning. */
if (after(TCP_SKB_CB(in_skb)->seq, TCP_SKB_CB(skb)->seq))
break;
pruned = true;
prev = rb_prev(node);
rb_erase(node, &tp->out_of_order_queue);
goal -= skb->truesize;
tcp_drop_reason(sk, skb, SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE);
tp->ooo_last_skb = rb_to_skb(prev);
if (!prev || goal <= 0) {
if (tcp_can_ingest(sk, in_skb) &&
!tcp_under_memory_pressure(sk))
break;
goal = sk->sk_rcvbuf >> 3;
}
node = prev;
} while (node);
if (pruned) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED);
/* Reset SACK state. A conforming SACK implementation will
* do the same at a timeout based retransmit. When a connection
* is in a sad state like this, we care only about integrity
* of the connection not performance.
*/
if (tp->rx_opt.sack_ok)
tcp_sack_reset(&tp->rx_opt);
}
return pruned;
}
/* Reduce allocated memory if we can, trying to get
* the socket within its memory limits again.
*
* Return less than zero if we should start dropping frames
* until the socket owning process reads some of the data
* to stabilize the situation.
*/
static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb)
{
struct tcp_sock *tp = tcp_sk(sk);
/* Do nothing if our queues are empty. */
if (!atomic_read(&sk->sk_rmem_alloc))
return -1;
if (!tcp_can_ingest(sk, in_skb))
tcp_clamp_window(sk);
else if (tcp_under_memory_pressure(sk))
tcp_adjust_rcv_ssthresh(sk);
if (tcp_can_ingest(sk, in_skb))
return 0;
tcp_collapse_ofo_queue(sk);
if (!skb_queue_empty(&sk->sk_receive_queue))
tcp_collapse(sk, &sk->sk_receive_queue, NULL,
skb_peek(&sk->sk_receive_queue),
NULL,
tp->copied_seq, tp->rcv_nxt);
if (tcp_can_ingest(sk, in_skb))
return 0;
/* Collapsing did not help, destructive actions follow.
* This must not ever occur. */
tcp_prune_ofo_queue(sk, in_skb);
if (tcp_can_ingest(sk, in_skb))
return 0;
/* If we are really being abused, tell the caller to silently
* drop receive data on the floor. It will get retransmitted
* and hopefully then we'll have sufficient space.
*/
NET_INC_STATS(sock_net(sk), LINUX_MIB_RCVPRUNED);
/* If the user specified a specific send buffer setting, do
* not modify it.
*/
if (sk->sk_userlocks & SOCK_SNDBUF_LOCK)
return false;
/* If we are under global TCP memory pressure, do not expand. */
if (tcp_under_memory_pressure(sk)) {
int unused_mem = sk_unused_reserved_mem(sk);
/* Adjust sndbuf according to reserved mem. But make sure
* it never goes below SOCK_MIN_SNDBUF.
* See sk_stream_moderate_sndbuf() for more details.
*/
if (unused_mem > SOCK_MIN_SNDBUF)
WRITE_ONCE(sk->sk_sndbuf, unused_mem);
return false;
}
/* If we are under soft global TCP memory pressure, do not expand. */
if (sk_memory_allocated(sk) >= sk_prot_mem_limits(sk, 0))
return false;
/* If we filled the congestion window, do not expand. */
if (tcp_packets_in_flight(tp) >= tcp_snd_cwnd(tp))
return false;
/* Caller made space either from:
* 1) Freeing skbs in rtx queues (after tp->snd_una has advanced)
* 2) Sent skbs from output queue (and thus advancing tp->snd_nxt)
*
* We might be able to generate EPOLLOUT to the application if:
* 1) Space consumed in output/rtx queues is below sk->sk_sndbuf/2
* 2) notsent amount (tp->write_seq - tp->snd_nxt) became
* small enough that tcp_stream_memory_free() decides it
* is time to generate EPOLLOUT.
*/
void tcp_check_space(struct sock *sk)
{
/* pairs with tcp_poll() */
smp_mb();
if (sk->sk_socket &&
test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
tcp_new_space(sk);
if (!test_bit(SOCK_NOSPACE, &sk->sk_socket->flags))
tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
}
}
/*
* Check if sending an ack is needed.
*/
static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
{
struct tcp_sock *tp = tcp_sk(sk);
unsigned long rtt, delay;
/* More than one full frame received... */
if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss &&
/* ... and right edge of window advances far enough.
* (tcp_recvmsg() will send ACK otherwise).
* If application uses SO_RCVLOWAT, we want send ack now if
* we have not received enough bytes to satisfy the condition.
*/
(tp->rcv_nxt - tp->copied_seq < sk->sk_rcvlowat ||
__tcp_select_window(sk) >= tp->rcv_wnd)) ||
/* We ACK each frame or... */
tcp_in_quickack_mode(sk) ||
/* Protocol state mandates a one-time immediate ACK */
inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOW) {
/* If we are running from __release_sock() in user context,
* Defer the ack until tcp_release_cb().
*/
if (sock_owned_by_user_nocheck(sk) &&
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_backlog_ack_defer)) {
set_bit(TCP_ACK_DEFERRED, &sk->sk_tsq_flags);
return;
}
send_now:
tcp_send_ack(sk);
return;
}
if (!ofo_possible || RB_EMPTY_ROOT(&tp->out_of_order_queue)) {
tcp_send_delayed_ack(sk);
return;
}
if (!tcp_is_sack(tp) ||
tp->compressed_ack >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr))
goto send_now;
if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) {
tp->compressed_ack_rcv_nxt = tp->rcv_nxt;
tp->dup_ack_counter = 0;
}
if (tp->dup_ack_counter < TCP_FASTRETRANS_THRESH) {
tp->dup_ack_counter++;
goto send_now;
}
tp->compressed_ack++;
if (hrtimer_is_queued(&tp->compressed_ack_timer))
return;
/* compress ack timer : 5 % of rtt, but no more than tcp_comp_sack_delay_ns */
static inline void tcp_ack_snd_check(struct sock *sk)
{
if (!inet_csk_ack_scheduled(sk)) {
/* We sent a data segment already. */
return;
}
__tcp_ack_snd_check(sk, 1);
}
/*
* This routine is only called when we have urgent data
* signaled. Its the 'slow' part of tcp_urg. It could be
* moved inline now as tcp_urg is only called from one
* place. We handle URGent data wrong. We have to - as
* BSD still doesn't use the correction from RFC961.
* For 1003.1g we should support a new option TCP_STDURG to permit
* either form (or just set the sysctl tcp_stdurg).
*/
if (ptr && !READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_stdurg))
ptr--;
ptr += ntohl(th->seq);
/* Ignore urgent data that we've already seen and read. */
if (after(tp->copied_seq, ptr))
return;
/* Do not replay urg ptr.
*
* NOTE: interesting situation not covered by specs.
* Misbehaving sender may send urg ptr, pointing to segment,
* which we already have in ofo queue. We are not able to fetch
* such data and will stay in TCP_URG_NOTYET until will be eaten
* by recvmsg(). Seems, we are not obliged to handle such wicked
* situations. But it is worth to think about possibility of some
* DoSes using some hypothetical application level deadlock.
*/
if (before(ptr, tp->rcv_nxt))
return;
/* Do we already have a newer (or duplicate) urgent pointer? */
if (tp->urg_data && !after(ptr, tp->urg_seq))
return;
/* Tell the world about our new urgent pointer. */
sk_send_sigurg(sk);
/* We may be adding urgent data when the last byte read was
* urgent. To do this requires some care. We cannot just ignore
* tp->copied_seq since we would read the last urgent byte again
* as data, nor can we alter copied_seq until this data arrives
* or we break the semantics of SIOCATMARK (and thus sockatmark())
*
* NOTE. Double Dutch. Rendering to plain English: author of comment
* above did something sort of send("A", MSG_OOB); send("B", MSG_OOB);
* and expect that both A and B disappear from stream. This is _wrong_.
* Though this happens in BSD with high probability, this is occasional.
* Any application relying on this is buggy. Note also, that fix "works"
* only in this artificial test. Insert some normal data between A and B and we will
* decline of BSD again. Verdict: it is better to remove to trap
* buggy users.
*/
if (tp->urg_seq == tp->copied_seq && tp->urg_data &&
!sock_flag(sk, SOCK_URGINLINE) && tp->copied_seq != tp->rcv_nxt) {
struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
tp->copied_seq++;
if (skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq)) {
__skb_unlink(skb, &sk->sk_receive_queue);
__kfree_skb(skb);
}
}
/* This is the 'fast' part of urgent handling. */
static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th)
{
struct tcp_sock *tp = tcp_sk(sk);
/* Check if we get a new urgent pointer - normally not. */
if (unlikely(th->urg))
tcp_check_urg(sk, th);
/* Do we wait for any urgent data? - normally not... */
if (unlikely(tp->urg_data == TCP_URG_NOTYET)) {
u32 ptr = tp->urg_seq - ntohl(th->seq) + (th->doff * 4) -
th->syn;
/* Is the urgent pointer pointing into this packet? */
if (ptr < skb->len) {
u8 tmp;
if (skb_copy_bits(skb, ptr, &tmp, 1))
BUG();
WRITE_ONCE(tp->urg_data, TCP_URG_VALID | tmp);
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_data_ready(sk);
}
}
}
/* Accept RST for rcv_nxt - 1 after a FIN.
* When tcp connections are abruptly terminated from Mac OSX (via ^C), a
* FIN is sent followed by a RST packet. The RST is sent with the same
* sequence number as the FIN, and thus according to RFC 5961 a challenge
* ACK should be sent. However, Mac OSX rate limits replies to challenge
* ACKs on the closed socket. In addition middleboxes can drop either the
* challenge ACK or a subsequent RST.
*/
static bool tcp_reset_check(const struct sock *sk, const struct sk_buff *skb)
{
const struct tcp_sock *tp = tcp_sk(sk);
/* Does PAWS and seqno based validation of an incoming segment, flags will
* play significant role here.
*/
static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
const struct tcphdr *th, int syn_inerr)
{
struct tcp_sock *tp = tcp_sk(sk);
SKB_DR(reason);
reason = tcp_disordered_ack_check(sk, skb);
if (!reason)
goto step1;
/* Reset is accepted even if it did not pass PAWS. */
if (th->rst)
goto step1;
if (unlikely(th->syn))
goto syn_challenge;
/* Old ACK are common, increment PAWS_OLD_ACK
* and do not send a dupack.
*/
if (reason == SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWS_OLD_ACK);
goto discard;
}
NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
if (!tcp_oow_rate_limited(sock_net(sk), skb,
LINUX_MIB_TCPACKSKIPPEDPAWS,
&tp->last_oow_ack_time))
tcp_send_dupack(sk, skb);
goto discard;
step1:
/* Step 1: check sequence number */
reason = tcp_sequence(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
if (reason) {
/* RFC793, page 37: "In all states except SYN-SENT, all reset
* (RST) segments are validated by checking their SEQ-fields."
* And page 69: "If an incoming segment is not acceptable,
* an acknowledgment should be sent in reply (unless the RST
* bit is set, if so drop the segment and return)".
*/
if (!th->rst) {
if (th->syn)
goto syn_challenge;
if (reason == SKB_DROP_REASON_TCP_INVALID_SEQUENCE ||
reason == SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE)
NET_INC_STATS(sock_net(sk),
LINUX_MIB_BEYOND_WINDOW);
if (!tcp_oow_rate_limited(sock_net(sk), skb,
LINUX_MIB_TCPACKSKIPPEDSEQ,
&tp->last_oow_ack_time))
tcp_send_dupack(sk, skb);
} else if (tcp_reset_check(sk, skb)) {
goto reset;
}
goto discard;
}
/* Step 2: check RST bit */
if (th->rst) {
/* RFC 59613.2 (extend to match against (RCV.NXT - 1) after a
* FIN and SACK too if available):
* If seq num matches RCV.NXT or (RCV.NXT - 1) after a FIN, or
* the right-most SACK block,
* then
* RESET the connection
* else
* Send a challenge ACK
*/
if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt ||
tcp_reset_check(sk, skb))
goto reset;
if (tcp_is_sack(tp) && tp->rx_opt.num_sacks > 0) {
struct tcp_sack_block *sp = &tp->selective_acks[0];
int max_sack = sp[0].end_seq;
int this_sack;
if (TCP_SKB_CB(skb)->seq == max_sack)
goto reset;
}
/* Disable TFO if RST is out-of-order
* and no data has been received
* for current active TFO socket
*/
if (tp->syn_fastopen && !tp->data_segs_in &&
sk->sk_state == TCP_ESTABLISHED)
tcp_fastopen_active_disable(sk);
tcp_send_challenge_ack(sk);
SKB_DR_SET(reason, TCP_RESET);
goto discard;
}
/* step 3: check security and precedence [ignored] */
/* step 4: Check for a SYN
* RFC 59614.2 : Send a challenge ack
*/
if (th->syn) {
if (sk->sk_state == TCP_SYN_RECV && sk->sk_socket && th->ack &&
TCP_SKB_CB(skb)->seq + 1 == TCP_SKB_CB(skb)->end_seq &&
TCP_SKB_CB(skb)->seq + 1 == tp->rcv_nxt &&
TCP_SKB_CB(skb)->ack_seq == tp->snd_nxt)
goto pass;
syn_challenge:
if (syn_inerr)
TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNCHALLENGE);
tcp_send_challenge_ack(sk);
SKB_DR_SET(reason, TCP_INVALID_SYN);
goto discard;
}
/*
* TCP receive function for the ESTABLISHED state.
*
* It is split into a fast path and a slow path. The fast path is
* disabled when:
* - A zero window was announced from us - zero window probing
* is only handled properly in the slow path.
* - Out of order segments arrived.
* - Urgent data is expected.
* - There is no buffer space left
* - Unexpected TCP flags/window values/header lengths are received
* (detected by checking the TCP header against pred_flags)
* - Data is sent in both directions. Fast path only supports pure senders
* or pure receivers (this means either the sequence number or the ack
* value must stay constant)
* - Unexpected TCP option.
*
* When these conditions are not satisfied it drops into a standard
* receive procedure patterned after RFC793 to handle all cases.
* The first three cases are guaranteed by proper pred_flags setting,
* the rest is checked inline. Fast processing is turned on in
* tcp_data_queue when everything is OK.
*/
void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
{
enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
const struct tcphdr *th = (const struct tcphdr *)skb->data;
struct tcp_sock *tp = tcp_sk(sk);
unsigned int len = skb->len;
tcp_mstamp_refresh(tp);
if (unlikely(!rcu_access_pointer(sk->sk_rx_dst)))
inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb);
/*
* Header prediction.
* The code loosely follows the one in the famous
* "30 instruction TCP receive" Van Jacobson mail.
*
* Van's trick is to deposit buffers into socket queue
* on a device interrupt, to call tcp_recv function
* on the receive process context and checksum and copy
* the buffer to user space. smart...
*
* Our current scheme is not silly either but we take the
* extra cost of the net_bh soft interrupt processing...
* We do checksum and copy also but from device to kernel.
*/
tp->rx_opt.saw_tstamp = 0;
/* pred_flags is 0xS?10 << 16 + snd_wnd
* if header_prediction is to be made
* 'S' will always be tp->tcp_header_len >> 2
* '?' will be 0 for the fast path, otherwise pred_flags is 0 to
* turn it off (when there are holes in the receive
* space for instance)
* PSH flag is ignored.
*/
if ((tcp_flag_word(th) & TCP_HP_BITS) == tp->pred_flags &&
TCP_SKB_CB(skb)->seq == tp->rcv_nxt &&
!after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) {
int tcp_header_len = tp->tcp_header_len;
s32 delta = 0;
int flag = 0;
/* Timestamp header prediction: tcp_header_len
* is automatically equal to th->doff*4 due to pred_flags
* match.
*/
delta = tp->rx_opt.rcv_tsval -
tp->rx_opt.ts_recent;
/* If PAWS failed, check it more carefully in slow path */
if (delta < 0)
goto slow_path;
/* DO NOT update ts_recent here, if checksum fails
* and timestamp was corrupted part, it will result
* in a hung connection since we will drop all
* future packets due to the PAWS test.
*/
}
if (len <= tcp_header_len) {
/* Bulk data transfer: sender */
if (len == tcp_header_len) {
/* Predicted packet is in window by definition.
* seq == rcv_nxt and rcv_wup <= rcv_nxt.
* Hence, check seq<=rcv_wup reduces to:
*/
if (tcp_header_len ==
(sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
tp->rcv_nxt == tp->rcv_wup)
flag |= __tcp_replace_ts_recent(tp,
delta);
/* We know that such packets are checksummed
* on entry.
*/
tcp_ack(sk, skb, flag);
__kfree_skb(skb);
tcp_data_snd_check(sk);
/* When receiving pure ack in fast path, update
* last ts ecr directly instead of calling
* tcp_rcv_rtt_measure_ts()
*/
tp->rcv_rtt_last_tsecr = tp->rx_opt.rcv_tsecr;
return;
} else { /* Header too small */
reason = SKB_DROP_REASON_PKT_TOO_SMALL;
TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
goto discard;
}
} else {
int eaten = 0;
bool fragstolen = false;
if (tcp_checksum_complete(skb))
goto csum_error;
if (after(TCP_SKB_CB(skb)->end_seq,
tp->rcv_nxt + tcp_receive_window(tp)))
goto validate;
if ((int)skb->truesize > sk->sk_forward_alloc)
goto step5;
/* Predicted packet is in window by definition.
* seq == rcv_nxt and rcv_wup <= rcv_nxt.
* Hence, check seq<=rcv_wup reduces to:
*/
if (tcp_header_len ==
(sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
tp->rcv_nxt == tp->rcv_wup)
flag |= __tcp_replace_ts_recent(tp,
delta);
if (TCP_SKB_CB(skb)->ack_seq != tp->snd_una) {
/* Well, only one small jumplet in fast path... */
tcp_ack(sk, skb, flag | FLAG_DATA);
tcp_data_snd_check(sk);
if (!inet_csk_ack_scheduled(sk))
goto no_ack;
} else {
tcp_update_wl(tp, TCP_SKB_CB(skb)->seq);
}
/* Initialize the congestion window to start the transfer.
* 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->undo_marker)
tcp_snd_cwnd_set(tp, 1);
else
tcp_snd_cwnd_set(tp, tcp_init_cwnd(tp, __sk_dst_get(sk)));
tp->snd_cwnd_stamp = tcp_jiffies32;
bpf_skops_established(sk, bpf_op, skb);
/* Initialize congestion control unless BPF initialized it already: */
if (!icsk->icsk_ca_initialized)
tcp_init_congestion_control(sk);
tcp_init_buffer_space(sk);
}
if (mss == tp->rx_opt.user_mss) {
struct tcp_options_received opt;
/* Get original SYNACK MSS value if user MSS sets mss_clamp */
tcp_clear_options(&opt);
opt.user_mss = opt.mss_clamp = 0;
tcp_parse_options(sock_net(sk), synack, &opt, 0, NULL);
mss = opt.mss_clamp;
}
if (!tp->syn_fastopen) {
/* Ignore an unsolicited cookie */
cookie->len = -1;
} else if (tp->total_retrans) {
/* SYN timed out and the SYN-ACK neither has a cookie nor
* acknowledges data. Presumably the remote received only
* the retransmitted (regular) SYNs: either the original
* SYN-data or the corresponding SYN-ACK was dropped.
*/
syn_drop = (cookie->len < 0 && data);
} else if (cookie->len < 0 && !tp->syn_data) {
/* We requested a cookie but didn't get it. If we did not use
* the (old) exp opt format then try so next time (try_exp=1).
* Otherwise we go back to use the RFC7413 opt (try_exp=2).
*/
try_exp = tp->syn_fastopen_exp ? 2 : 1;
}
if (data) { /* Retransmit unacked data in SYN */
if (tp->total_retrans)
tp->fastopen_client_fail = TFO_SYN_RETRANSMITTED;
else
tp->fastopen_client_fail = TFO_DATA_NOT_ACKED;
skb_rbtree_walk_from(data)
tcp_mark_skb_lost(sk, data);
tcp_non_congestion_loss_retransmit(sk);
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPFASTOPENACTIVEFAIL);
return true;
}
tp->syn_data_acked = tp->syn_data;
if (tp->syn_data_acked) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE);
/* SYN-data is counted as two separate packets in tcp_ack() */
if (tp->delivered > 1)
--tp->delivered;
}
/* undo_marker is set when SYN or SYNACK times out. The timeout is
* spurious if the ACK's timestamp option echo value matches the
* original SYN timestamp.
*/
syn_stamp = tp->retrans_stamp;
if (tp->undo_marker && syn_stamp && tp->rx_opt.saw_tstamp &&
syn_stamp == tp->rx_opt.rcv_tsecr)
tp->undo_marker = 0;
}
if (th->ack) {
/* rfc793:
* "If the state is SYN-SENT then
* first check the ACK bit
* If the ACK bit is set
* If SEG.ACK =< ISS, or SEG.ACK > SND.NXT, send
* a reset (unless the RST bit is set, if so drop
* the segment and return)"
*/
if (!after(TCP_SKB_CB(skb)->ack_seq, tp->snd_una) ||
after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) {
/* Previous FIN/ACK or RST/ACK might be ignored. */
if (icsk->icsk_retransmits == 0)
tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
TCP_TIMEOUT_MIN, false);
SKB_DR_SET(reason, TCP_INVALID_ACK_SEQUENCE);
goto reset_and_undo;
}
/* Now ACK is acceptable.
*
* "If the RST bit is set
* If the ACK was acceptable then signal the user "error:
* connection reset", drop the segment, enter CLOSED state,
* delete TCB, and return."
*/
if (th->rst) {
tcp_reset(sk, skb);
consume:
__kfree_skb(skb); return0;
}
/* Remember, tcp_poll() does not lock socket! *ChangestatefromSYN-SENTonlyaftercopied_seq
* is initialized. */
WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
/* PAWS check. */ if (tp->rx_opt.ts_recent_stamp && tp->rx_opt.saw_tstamp &&
tcp_paws_reject(&tp->rx_opt, 0)) {
SKB_DR_SET(reason, TCP_RFC7323_PAWS); goto discard_and_undo;
} if (th->syn) { /* We see SYN without ACK. It is attempt of *simultaneousconnectwithcrossedSYNs. *Particularly,itcanbeconnecttoself.
*/ #ifdef CONFIG_TCP_AO struct tcp_ao_info *ao;
ao = rcu_dereference_protected(tp->ao_info,
lockdep_sock_is_held(sk)); if ( *
WRITE_ONCE(ao->risn, th->seq);
ao->rcv_sne = 0;
} #endif
tcp_set_state(sk, TCP_SYN_RECV);
tcp_send_synack(sk); #if0 /* Note, we could accept data and URG from this segment. *Therearenoobstaclestomakethis(exceptthatwemust *eitherchangetcp_recvmsg()topreventitfromreturningdata *before3WHScompletesperRFC793,oremployTCPFastOpen). * *However,ifweignoredatainACKlesssegmentssometimes, *wehavenoreasonstoacceptitsometimes. *Also,seemsthecodedoingitinstep6oftcp_rcv_state_process *isnotflawless.So,discardpacketforsanity. *Uncommentthisreturntoprocessthedata.
*/ return -1; #else goto consume; #endif
} /* "fifth, if neither of the SYN or RST bits is set then *dropthesegmentandreturn."
*/
reset_and_undo:
tcp_clear_options(&tp->rx_opt);
tp->rx_opt.mss_clamp = saved_clamp; /* we can reuse/return @reason to its caller to handle the exception */ return reason;
}
/* If we are still handling the SYNACK RTO, see if timestamp ECR allows *undo.IfpeerSACKstriggeredfastrecovery,wecan'tundohere.
*/ if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss && !tp->packets_out)
tcp_try_undo_recovery(sk);
tcp_update_rto_time(tp);
inet_csk(sk)->icsk_retransmits = 0; /* In tcp_fastopen_synack_timer() on the first SYNACK RTO we set *retrans_stampbutdon'tenterCA_Loss,soincasethathappenedwe *needtozeroretrans_stampheretopreventspurious *retransmits_timed_out().However,iftheACKofourSYNACKcausedus *toenterCA_Recoverythenweneedtoleaveretrans_stampasitwas *setenteringCA_Recovery,forcorrectretransmits_timed_out()and *undobehavior.
*/
tcp_retrans_stamp_cleanup(sk);
/* Once we leave TCP_SYN_RECV or TCP_FIN_WAIT_1, *wenolongerneedreqsoreleaseit.
*/
req = rcu_dereference_protected(tp->fastopen_rsk,
lockdep_sock_is_held(sk));
reqsk_fastopen_remove(sk, req, false);
/* Re-arm the timer because data may have been sent out. *Thisissimilartotheregulardatatransmissioncase *whennewdatahasjustbeenack'ed. * *(TFO)-wecouldtrytobemoreaggressiveand *retransmittinganydatasoonerbasedonwhenthey *aresentout.
*/
tcp_rearm_rto(sk);
}
switch (sk->sk_state) { case TCP_CLOSE:
SKB_DR_SET(reason, TCP_CLOSE); goto discard;
case TCP_LISTEN: if (th->ack) return SKB_DROP_REASON_TCP_FLAGS;
if (th->rst) {
SKB_DR_SET(reason, TCP_RESET); goto discard;
} if (th->syn) { if (th->fin) {
SKB_DR_SET(reason, TCP_FLAGS); goto discard;
} /* It is possible that we process SYN packets from backlog, *soweneedtomakesuretodisableBHandRCUrightthere.
*/
rcu_read_lock();
local_bh_disable();
icsk->icsk_af_ops->conn_request(sk, skb);
local_bh_enable();
rcu_read_unlock();
/* Note, that this wakeup is only for marginal crossed SYN case. *Passivelyopensocketsarenotwakedup,because *sk->sk_sleep==NULLandsk->sk_socket==NULL.
*/ if (sk->sk_socket)
sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT);
if (!sock_flag(sk, SOCK_DEAD)) { /* Wake up lingering close() */
sk->sk_state_change(sk); break;
}
if (READ_ONCE(tp->linger2) < 0) {
tcp_done(sk);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); return SKB_DROP_REASON_TCP_ABORT_ON_DATA;
} if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) { /* Receive out of order FIN after close() */ if (tp->syn_fastopen && th->fin)
tcp_fastopen_active_disable(sk);
tcp_done(sk);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); return SKB_DROP_REASON_TCP_ABORT_ON_DATA;
}
tmo = tcp_fin_time(sk); if (tmo > TCP_TIMEWAIT_LEN) {
tcp_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN);
} elseif (th->fin || sock_owned_by_user(sk)) { /* Bad case. We could lose such FIN otherwise. *Itisnotabigproblem,butitlooksconfusing *andnotsorareevent.Westillcanloseitnow, *ifitspinsinbh_lock_sock(),butitisreally *marginalcase.
*/
tcp_reset_keepalive_timer(sk, tmo);
} else {
tcp_time_wait(sk, TCP_FIN_WAIT2, tmo); goto consume;
} break;
}
case TCP_CLOSING: if (tp->snd_una == tp->write_seq) {
tcp_time_wait(sk, TCP_TIME_WAIT, 0); goto consume;
} break;
case TCP_LAST_ACK: if (tp->snd_una == tp->write_seq) {
tcp_update_metrics(sk);
tcp_done(sk); goto consume;
} break;
}
/* step 6: check the URG bit */
tcp_urg(sk, skb, th);
/* step 7: process the segment text */ switch (sk->sk_state) { case TCP_CLOSE_WAIT: case TCP_CLOSING: case TCP_LAST_ACK: if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { /* If a subflow has been reset, the packet should not *continuetobeprocessed,dropthepacket.
*/ if (sk_is_mptcp(sk) && !mptcp_incoming_options(sk, skb)) goto discard; break;
}
fallthrough; case TCP_FIN_WAIT1: case TCP_FIN_WAIT2: /* RFC 793 says to queue data in these states, *RFC1122saysweMUSTsendareset. *BSD4.4alsodoesreset.
*/ if (sk->sk_shutdown & RCV_SHUTDOWN) { if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
tcp_reset(sk, skb); return SKB_DROP_REASON_TCP_ABORT_ON_DATA;
}
}
fallthrough; case TCP_ESTABLISHED:
tcp_data_queue(sk, skb);
queued = 1; break;
}
/* tcp_data could move socket to TIME-WAIT */ if (sk->sk_state != TCP_CLOSE) {
tcp_data_snd_check(sk);
tcp_ack_snd_check(sk);
}
if (!queued) {
discard:
tcp_drop_reason(sk, skb, reason);
} return0;
if (!READ_ONCE(queue->synflood_warned) && syncookies != 2 &&
xchg(&queue->synflood_warned, 1) == 0) { if (IS_ENABLED(CONFIG_IPV6) && sk->sk_family == AF_INET6) {
net_info_ratelimited("%s: Possible SYN flooding on port [%pI6c]:%u. %s.\n",
proto, inet6_rcv_saddr(sk),
sk->sk_num, msg);
} else {
net_info_ratelimited("%s: Possible SYN flooding on port %pI4:%u. %s.\n",
proto, &sk->sk_rcv_saddr,
sk->sk_num, msg);
}
}
if (tcp_sk(sk)->save_syn == 2) { /* Save full header. */
base = skb_mac_header(skb);
mac_hdrlen = skb_mac_header_len(skb);
len += mac_hdrlen;
} else {
base = skb_network_header(skb);
mac_hdrlen = 0;
}
/* If a SYN cookie is required and supported, returns a clamped MSS value to be *usedforSYNcookiegeneration.
*/
u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, conststruct tcp_request_sock_ops *af_ops, struct sock *sk, struct tcphdr *th)
{ struct tcp_sock *tp = tcp_sk(sk);
u16 mss;
if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) != 2 &&
!inet_csk_reqsk_queue_is_full(sk)) return0;
if (!tcp_syn_flood_action(sk, rsk_ops->slab_name)) return0;
if (sk_acceptq_is_full(sk)) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); return0;
}
mss = tcp_parse_mss_option(th, tp->rx_opt.user_mss); if (!mss)
mss = af_ops->mss_clamp;
if (tmp_opt.tstamp_ok) {
tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst);
tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb);
}
if (!want_cookie && !isn) {
int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog);
/* Kill the following clause, if you dislike this way. */
if (!syncookies &&
(max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
(max_syn_backlog >> 2)) &&
!tcp_peer_is_proven(req, dst)) {
/* Without syncookies last quarter of
* backlog is filled with destinations,
* proven to be alive.
* It means that we continue to communicate
* to destinations, already remembered
* to the moment of synflood.
*/
pr_drop_req(req, ntohs(tcp_hdr(skb)->source),
rsk_ops->family);
goto drop_and_release;
}
isn = af_ops->init_seq(skb);
}
tcp_ecn_create_request(req, skb, sk, dst);
if (want_cookie) {
isn = cookie_init_sequence(af_ops, sk, skb, &req->mss);
if (!tmp_opt.tstamp_ok)
inet_rsk(req)->ecn_ok = 0;
}
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.