// SPDX-License-Identifier: GPL-2.0 /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Implementation of the Transmission Control Protocol(TCP). * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche, <flla@stud.uni-sb.de> * Charles Hedrick, <hedrick@klinzhai.rutgers.edu> * Linus Torvalds, <torvalds@cs.helsinki.fi> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Matthew Dillon, <dillon@apollo.west.oic.com> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Jorge Cwik, <jorge@laser.satlink.net>
*/
/* * Changes: * Pedro Roque : Fast Retransmit/Recovery. * Two receive queues. * Retransmit queue handled by TCP. * Better retransmit timer handling. * New congestion avoidance. * Header prediction. * Variable renaming. * * Eric : Fast Retransmit. * Randy Scott : MSS option defines. * Eric Schenk : Fixes to slow start algorithm. * Eric Schenk : Yet another double ACK bug. * Eric Schenk : Delayed ACK bug fixes. * Eric Schenk : Floyd style fast retrans war avoidance. * David S. Miller : Don't allow zero congestion window. * Eric Schenk : Fix retransmitter so that it sends * next packet on ack of previous packet. * Andi Kleen : Moved open_request checking here * and process RSTs for open_requests. * Andi Kleen : Better prune_queue, and other fixes. * Andrey Savochkin: Fix RTT measurements in the presence of * timestamps. * Andrey Savochkin: Check sequence numbers correctly when * removing SACKs due to in sequence incoming * data segments. * Andi Kleen: Make sure we never ack data there is not * enough room for. Also make this condition * a fatal error if it might still happen. * Andi Kleen: Add tcp_measure_rcv_mss to make * connections with MSS<min(MTU,ann. MSS) * work without delayed acks. * Andi Kleen: Process packets with PSH set in the * fast path. * J Hadi Salim: ECN support * Andrei Gurtov, * Pasi Sarolahti, * Panu Kuhlberg: Experimental audit of TCP (re)transmission * engine. Lots of bugs are found. * Pasi Sarolahti: F-RTO for dealing with spurious RTOs
*/
#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 * real world.
*/ 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 * sends good full-sized frames.
*/
len = skb_shinfo(skb)->gso_size ? : skb->len; if (len >= icsk->icsk_ack.rcv_mss) { /* Note: divides are still a bit expensive. * For the moment, only adjust scaling_ratio * when we update icsk_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 * set then it is likely the end of an application write. So * more data may not be arriving soon, and yet the data sender * may be waiting for an ACK if cwnd-bound or using TX zero * copy. So we set ICSK_ACK_PUSHED here so that * tcp_cleanup_rbuf() will send an ACK immediately if the app * reads all of the data and is not ping-pong. If len > MSS * then this logic does not matter (and does not hurt) because * tcp_cleanup_rbuf() will always ACK immediately if the app * reads data and there is more than an MSS of unACKed data.
*/ 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, * that SACKs block is variable. * * "len" is invariant segment length, including TCP header.
*/
len += skb->data - skb_transport_header(skb); if (len >= TCP_MSS_DEFAULT + sizeof(struct tcphdr) || /* If PSH is not set, packet should be * full sized, provided peer TCP is not badly broken. * This observation (if it is correct 8)) allows * to handle super-low mtu links fairly.
*/
(len >= TCP_MIN_MSS + sizeof(struct tcphdr) &&
!(tcp_flag_word(tcp_hdr(skb)) & TCP_REMNANT))) { /* Subtract also invariant (if peer is RFC compliant), * tcp header plus fixed timestamp option length. * Resulting "len" is MSS free of SACK jitter.
*/
len -= tcp_sk(sk)->tcp_header_len;
icsk->icsk_ack.last_seg_size = len; if (len == lss) {
icsk->icsk_ack.rcv_mss = len; return;
}
} if (icsk->icsk_ack.pending & ICSK_ACK_PUSHED)
icsk->icsk_ack.pending |= ICSK_ACK_PUSHED2;
icsk->icsk_ack.pending |= ICSK_ACK_PUSHED;
}
}
/* If the sender is telling us it has entered CWR, then its * cwnd may be very low (even just 1 packet), so we should ACK * 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, * and we already seen ECT on a previous segment, * it is probably a retransmit.
*/ 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 * and skb->head is kmalloced using power of two area of memory
*/
per_mss = max_t(u32, tp->rx_opt.mss_clamp, tp->mss_cache) +
MAX_TCP_HEADER +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
/* Fast Recovery (RFC 5681 3.2) : * Cubic needs 1.7 factor, rounded to 2 to include * extra cushion (application might react slowly to EPOLLOUT)
*/
sndmem = ca_ops->sndbuf_expand ? ca_ops->sndbuf_expand(sk) : 2;
sndmem *= nr_segs * per_mss;
if (sk->sk_sndbuf < sndmem)
WRITE_ONCE(sk->sk_sndbuf,
min(sndmem, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[2])));
}
/* 2. Tuning advertised window (window_clamp, rcv_ssthresh) * * All tcp_full_space() is split to two parts: "network" buffer, allocated * forward and advertised in receiver window (tp->rcv_wnd) and * "application buffer", required to isolate scheduling/application * latencies from network. * window_clamp is maximal advertised window. It can be less than * tcp_full_space(), in this case tcp_full_space() - window_clamp * is reserved for "application" buffer. The less window_clamp is * the smoother our behaviour from viewpoint of network, but the lower * throughput and the higher sensitivity of the connection to losses. 8) * * rcv_ssthresh is more strict window_clamp used at "slow start" * phase to predict further behaviour of this connection. * It is used for two goals: * - to enforce header prediction at sender, even when application * requires some significant "application buffer". It is check #1. * - to prevent pruning of receive queue because of misprediction * of receiver window. Check #2. * * The scheme does not work when sender sends good segments opening * window and then starts to feed us spaghetti. But it should work * in common situations. Otherwise, we have to rely on queue collapsing.
*/
/* Slow part of check#2. */ 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) return 2 * inet_csk(sk)->icsk_ack.rcv_mss;
truesize >>= 1;
window >>= 1;
} return 0;
}
/* Even if skb appears to have a bad len/truesize ratio, TCP coalescing * can play nice with us, as sk_buff and skb->head might be either * freed or shared with up to MAX_SKB_FRAGS segments. * Only give a boost to drivers using page frag(s) to hold the frame(s), * and if no payload was pulled in skb->head before reaching us.
*/ 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;
}
/* Check #1 */ if (!tcp_under_memory_pressure(sk)) { unsignedint truesize = truesize_adjust(adjust, skb); int incr;
/* Check #2. Increase window, if skb with such overhead * will fit to rcvbuf in future.
*/ if (tcp_win_from_space(sk, truesize) <= skb->len)
incr = 2 * tp->advmss; else
incr = __tcp_grow_window(sk, skb, truesize);
if (incr) {
incr = max_t(int, incr, 2 * skb->len);
tp->rcv_ssthresh += min(room, incr);
inet_csk(sk)->icsk_ack.quick |= 1;
}
} else { /* Under pressure: * Adjust rcv_ssthresh according to reserved mem
*/
tcp_adjust_rcv_ssthresh(sk);
}
}
/* 3. Try to fixup all. It is made immediately after connection enters * established state.
*/ 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);
/* Initialize RCV_MSS value. * RCV_MSS is an our guess about MSS used by the peer. * We haven't any direct information about the MSS. * It's better to underestimate the RCV_MSS rather than overestimate. * Overestimations make us ACKing less frequently than needed. * Underestimations are more easy to detect and fix by tcp_measure_rcv_mss().
*/ void tcp_initialize_rcv_mss(struct sock *sk)
{ conststruct tcp_sock *tp = tcp_sk(sk); unsignedint hint = min_t(unsignedint, tp->advmss, tp->mss_cache);
hint = min(hint, tp->rcv_wnd / 2);
hint = min(hint, TCP_MSS_DEFAULT);
hint = max(hint, TCP_MIN_MSS);
/* Receiver "autotuning" code. * * The algorithm for RTT estimation w/o timestamps is based on * Dynamic Right-Sizing (DRS) by Wu Feng and Mike Fisk of LANL. * <https://public.lanl.gov/radiant/pubs.html#DRS> * * More detail on this code can be found at * <http://staff.psc.edu/jheffner/>, * though this reference is out of date. A new paper * is pending.
*/ staticvoid tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
{
u32 new_sample, old_sample = tp->rcv_rtt_est.rtt_us; long m = sample << 3;
if (old_sample == 0 || m < old_sample) {
new_sample = m;
} else { /* If we sample in larger samples in the non-timestamp * case, we could grossly overestimate the RTT especially * with chatty applications or bulk transfer apps which * are stalled on filesystem I/O. * * Also, since we are only going for a minimum in the * non-timestamp case, we do not smooth things out * else with timestamps disabled convergence takes too * long.
*/ if (win_dep) 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));
}
} /* * This function should be called every time data is copied to user space. * It calculates the appropriate TCP receive buffer space.
*/ void tcp_rcv_space_adjust(struct sock *sk)
{ struct tcp_sock *tp = tcp_sk(sk); int time, 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 * behavior of the tp->ato delayed ack timeout interval. When a * connection starts up, we want to ack as quickly as possible. The * problem is that "good" TCP's do slow start at the beginning of data * transmission. The means that until we send the first few ACK's the * sender will sit on his end and only queue most of his data, because * he can only send snd_cwnd unacked packets at any given time. For * each ACK we send, he increments snd_cwnd and transmits more of his * queue. -DaveM
*/ 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 * delayed ACK engine.
*/
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 * restart window, so that we send ACKs quickly.
*/
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 * routine either comes from timestamps, or from segments that were * known _not_ to have been retransmitted [see Karn/Partridge * Proceedings SIGCOMM 87]. The algorithm is from the SIGCOMM 88 * piece by Van Jacobson. * NOTE: the next three routines used to be one big routine. * To save cycles in the RFC 1323 implementation it was better to break * it up into three procedures. -- erics
*/ 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 * article in SIGCOMM '88. Note that rtt and mdev * are scaled versions of rtt and mean deviation. * This is designed to be as fast as possible * m stands for "measurement". * * On a 1990 paper the rto value is changed to: * RTO = rtt + 4 * mdev * * Funny. This algorithm seems to be very broken. * These formulae increase RTO, when it should be decreased, increase * too slowly, when it should be increased quickly, decrease too quickly * etc. I guess in BSD RTO takes ONE value, so that it is absolutely * does not matter how to _calculate_ it. Seems, it was trap * that VJ failed to avoid. 8)
*/ if (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. * Eifel blocks mdev updates when rtt decreases. * This solution is a bit different: we use finer gain * for mdev in this case (alpha*beta). * Like Eifel it also prevents growth of rto, * but also it limits too fast rto decreases, * happening in pure Eifel.
*/ if (m > 0)
m >>= 3;
} else {
m -= (tp->mdev_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 * In Slow Start [1], set sk_pacing_rate to 200 % the current rate. * In Congestion Avoidance phase, set it to 120 % the current rate. * * [1] : Normal Slow Start condition is (tp->snd_cwnd < tp->snd_ssthresh) * If snd_cwnd >= (tp->snd_ssthresh / 2), we are approaching * end of slow start and should slow down.
*/ 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 * without any lock. We want to make sure compiler wont store * intermediate values in this location.
*/
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 * routine referred to above.
*/ staticvoid tcp_set_rto(struct sock *sk)
{ conststruct tcp_sock *tp = tcp_sk(sk); /* Old crap is replaced with new one. 8) * * More seriously: * 1. If rtt variance happened to be less 50msec, it is hallucination. * It cannot be less due to utterly erratic ACK generation made * at least by solaris and freebsd. "Erratic ACKs" has _nothing_ * to do with delayed acks, because at cwnd>2 true delack timeout * is invisible. Actually, Linux-2.4 also generates erratic * ACKs in some circumstances.
*/
inet_csk(sk)->icsk_rto = __tcp_set_rto(tp);
/* 2. Fixups made earlier cannot be right. * If we do not estimate RTO correctly without them, * all the algo is pure shit and should be replaced * with correct one. It is exactly, which we pretend to do.
*/
/* NOTE: clamping at TCP_RTO_MIN is not required, current algo * guarantees that rto is higher.
*/
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 * that was SACKed. RTO needs the earliest RTT to stay conservative, * but congestion control should still get an accurate delay signal.
*/
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 * and spurious retransmission information if this DSACK is unlikely caused by * sender's action: * - DSACKed sequence range is larger than maximum receiver's window. * - Total no. of DSACKed segments exceed the total no. of retransmitted segs.
*/ 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)) return 0;
seq_len = end_seq - start_seq; /* Dubious DSACK: DSACKed range greater than maximum advertised rwnd */ if (seq_len > tp->max_window) return 0; 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) return 0;
tp->rx_opt.sack_ok |= TCP_DSACK_SEEN; /* We increase the RACK ordering window in rounds where we receive * DSACKs that may have been due to reordering causing RACK to trigger * a spurious fast recovery. Thus RACK ignores DSACKs that happen * without having seen reordering, or that match TLP probes (TLP * is timer-driven, not triggered by RACK).
*/ 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;
return dup_segs;
}
/* It's reordering when higher sequence was delivered (i.e. sacked) before * some lower never-retransmitted sequence ("low_seq"). The maximum reordering * distance is approximated in full-mss packet distance ("reordering").
*/ staticvoid tcp_check_sack_reordering(struct sock *sk, const u32 low_seq, constint ts)
{ struct tcp_sock *tp = tcp_sk(sk); const u32 mss = tp->mss_cache;
u32 fack, metric;
fack = tcp_highest_sack_seq(tp); if (!before(low_seq, fack)) return;
/* 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 * on a new loss, because we want to know if all skbs previously * known to be lost have already been retransmitted, indicating * that this newly lost skb is our next skb to retransmit.
*/ 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 * notify the congestion control module that the given skb was marked lost.
*/ staticvoid tcp_notify_skb_loss_event(struct tcp_sock *tp, conststruct sk_buff *skb)
{
tp->lost += tcp_skb_pcount(skb);
}
tcp_verify_retransmit_hint(tp, skb); if (sacked & TCPCB_LOST) { if (sacked & TCPCB_SACKED_RETRANS) { /* Account for retransmits that are lost again */
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
tp->retrans_out -= tcp_skb_pcount(skb);
NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT,
tcp_skb_pcount(skb));
tcp_notify_skb_loss_event(tp, skb);
}
} else {
tp->lost_out += tcp_skb_pcount(skb);
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tcp_notify_skb_loss_event(tp, skb);
}
}
/* This procedure tags the retransmission queue when SACKs arrive. * * We have three tag bits: SACKED(S), RETRANS(R) and LOST(L). * Packets in queue with these bits set are counted in variables * sacked_out, retrans_out and lost_out, correspondingly. * * Valid combinations are: * Tag InFlight Description * 0 1 - orig segment is in flight. * S 0 - nothing flies, orig reached receiver. * L 0 - nothing flies, orig lost by net. * R 2 - both orig and retransmit are in flight. * L|R 1 - orig is lost, retransmit is in flight. * S|R 1 - orig reached receiver, retrans is still in flight. * (L|S|R is logically valid, it could occur when L|R is sacked, * but it is equivalent to plain S and code short-circuits it to S. * L|S is logically invalid, it would mean -1 packet in flight 8)) * * These 6 states form finite state machine, controlled by the following events: * 1. New ACK (+SACK) arrives. (tcp_sacktag_write_queue()) * 2. Retransmission. (tcp_retransmit_skb(), tcp_xmit_retransmit_queue()) * 3. Loss detection event of two flavors: * A. Scoreboard estimator decided the packet is lost. * A'. Reno "three dupacks" marks head of queue lost. * B. SACK arrives sacking SND.NXT at the moment, when the * segment was retransmitted. * 4. D-SACK added new rule: D-SACK changes any tag to S. * * It is pleasant to note, that state diagram turns out to be commutative, * so that we are allowed not to be bothered by order of our actions, * when multiple events arrive simultaneously. (see the function below). * * Reordering detection. * -------------------- * Reordering metric is maximal distance, which a packet can be displaced * in packet stream. With SACKs we can estimate it: * * 1. SACK fills old hole and the corresponding segment was not * ever retransmitted -> reordering. Alas, we cannot use it * when segment was retransmitted. * 2. The last flaw is solved with D-SACK. D-SACK arrives * for retransmitted and already SACKed segment -> reordering.. * Both of these heuristics are not used in Loss state, when we cannot * account for retransmits accurately. * * SACK block validation. * ---------------------- * * SACK block range validation checks that the received SACK block fits to * the expected sequence limits, i.e., it is between SND.UNA and SND.NXT. * Note that SND.UNA is not included to the range though being valid because * it means that the receiver is rather inconsistent with itself reporting * SACK reneging when it should advance SND.UNA. Such SACK block this is * perfectly valid, however, in light of RFC2018 which explicitly states * that "SACK block MUST reflect the newest segment. Even if the newest * segment is going to be discarded ...", not that it looks very clever * in case of head skb. Due to potentional receiver driven attacks, we * choose to avoid immediate execution of a walk in write queue due to * reneging and defer head skb's loss recovery to standard loss recovery * procedure that will eventually trigger (nothing forbids us doing this). * * Implements also blockage to start_seq wrap-around. Problem lies in the * fact that though start_seq (s) is before end_seq (i.e., not reversed), * there's no guarantee that it will be before snd_nxt (n). The problem * happens when start_seq resides between end_seq wrap (e_w) and snd_nxt * wrap (s_w): * * <- outs wnd -> <- wrapzone -> * u e n u_w e_w s n_w * | | | | | | | * |<------------+------+----- TCP seqno space --------------+---------->| * ...-- <2^31 ->| |<--------... * ...---- >2^31 ------>| |<--------... * * Current code wouldn't be vulnerable but it's better still to discard such * crazy SACK blocks. Doing this check for start_seq alone closes somewhat * similar case (end_seq after snd_nxt wrap) as earlier reversed check in * snd_nxt wrap -> snd_una region will then become "well defined", i.e., * equal to the ideal case (infinite seqno space without wrap caused issues). * * With D-SACK the lower bound is extended to cover sequence space below * SND.UNA down to undo_marker, which is the last point of interest. Yet * again, D-SACK block must not to go across snd_una (for the same reason as * for the normal SACK blocks, explained above). But there all simplicity * ends, TCP might receive valid D-SACKs below that. As long as they reside * fully below undo_marker they do not affect behavior in anyway and can * therefore be safely ignored. In rare cases (which are more or less * theoretical ones), the D-SACK will nicely cross that boundary due to skb * fragmentation and packet reordering past skb's retransmission. To consider * them correctly, the acceptable range must be extended even more though * the exact amount is rather hard to quantify. However, tp->max_window can * be used as an exaggerated estimate.
*/ staticbool tcp_is_sackblock_valid(struct tcp_sock *tp, bool is_dsack,
u32 start_seq, u32 end_seq)
{ /* Too far in future, or reversed (interpretation is ambiguous) */ if (after(end_seq, tp->snd_nxt) || !before(start_seq, end_seq)) returnfalse;
/* 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_una is non-sensical (see comments above)
*/ 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_marker and end_seq >= undo_marker.
*/ return !before(start_seq, end_seq - tp->max_window);
}
/* D-SACK for already forgotten data... Do dumb counting. */ if (tp->undo_marker && tp->undo_retrans > 0 &&
!after(end_seq_0, prior_snd_una) &&
after(end_seq_0, tp->undo_marker))
tp->undo_retrans = max_t(int, 0, tp->undo_retrans - dup_segs);
returntrue;
}
/* Check if skb is fully within the SACK block. In presence of GSO skbs, * the incoming SACK may not exactly match but we can find smaller MSS * aligned portion of it that matches. Therefore we might need to fragment * which may fail and creates some hassle (caller must handle error case * returns). * * FIXME: this could be merged to shift decision code
*/ staticint tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
u32 start_seq, u32 end_seq)
{ int err; bool in_sack; unsignedint pkt_len; unsignedint mss;
/* 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, * we do not clear RETRANS, believing * that retransmission is still in flight.
*/ 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, * which was in hole. It is reordering.
*/ 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 * frames and clear it. undo_retrans is decreased above, L|R frames * are accounted above as well.
*/ 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-SACKed sk_buff. Mark the newly-SACKed bytes as such.
*/ 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 * range but discard the return value since prev is already * marked. We must tag the range first because the seq * advancement below implicitly advances * tcp_highest_sack_seq() when skb is highest_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, * in theory this shouldn't be necessary but as long as DSACK * code can come after this skb later on it's better to keep * setting gso_size to something.
*/ 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-zero which complicates things
*/ 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) * Since TCP_SKB_CB(skb)->tcp_gso_segs is 16 bits, we need * to make sure not storing more than 65535 * 8 bytes per skb, * even if current MSS is bigger.
*/ if (unlikely(to->len + shiftlen >= 65535 * TCP_MIN_GSO_SIZE)) return 0; if (unlikely(tcp_skb_pcount(to) + pcount > 65535)) return 0; 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 * drop this restriction as unnecessary
*/ 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 * cause skipped skbs due to advancing loop btw, original * has that feature too
*/ 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)), * though it might not be worth of the additional hassle * * ...we can probably just fallback to what was done * previously. We could try merging non-SACKed ones * as well but it probably isn't going to buy off * because later SACKs might again split them, and * it would make skb timestamp tracking considerably * harder problem.
*/ goto fallback;
}
/* MSS boundaries should be honoured or else pcount will * severely break even though it makes things bit trickier. * Optimize common case to avoid most of the divides
*/
mss = tcp_skb_mss(skb);
/* TODO: Fix DSACKs to not fragment already SACKed and we can * drop this restriction as unnecessary
*/ 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 * useful when hole on every nth skb pattern happens
*/
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 * shifting can eat and free both this skb and the next, * so not even _safe variant of the loop is enough.
*/ 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 * account more or less fresh ones, they can * contain valid SACK info.
*/ if (before(TCP_SKB_CB(ack_skb)->ack_seq, prior_snd_una - tp->max_window)) return 0;
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. Returns false if sacked_out adjustement wasn't necessary.
*/ staticbool tcp_limit_reno_sacked(struct tcp_sock *tp)
{
u32 holes;
/* If we receive more dupacks than we expected counting segments * in assumption of absent reordering, interpret this as reordering. * The only another reason could be bug in receiver TCP.
*/ staticvoid tcp_check_reno_reordering(struct sock *sk, constint addend)
{ struct tcp_sock *tp = tcp_sk(sk);
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.
