Newer
Older
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Implementation of the Transmission Control Protocol(TCP).
*
* Version: $Id: tcp_output.c,v 1.146 2002/02/01 22:01:04 davem Exp $
*
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
* 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 : Retransmit queue handled by TCP.
* : Fragmentation on mtu decrease
* : Segment collapse on retransmit
* : AF independence
*
* Linus Torvalds : send_delayed_ack
* David S. Miller : Charge memory using the right skb
* during syn/ack processing.
* David S. Miller : Output engine completely rewritten.
* Andrea Arcangeli: SYNACK carry ts_recent in tsecr.
* Cacophonix Gaul : draft-minshall-nagle-01
* J Hadi Salim : ECN support
*
*/
#include <net/tcp.h>
#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/smp_lock.h>
/* People can turn this off for buggy TCP's found in printers etc. */
int sysctl_tcp_retrans_collapse __read_mostly = 1;
/* People can turn this on to work with those rare, broken TCPs that
* interpret the window field as a signed quantity.
*/
int sysctl_tcp_workaround_signed_windows __read_mostly = 0;
/* This limits the percentage of the congestion window which we
* will allow a single TSO frame to consume. Building TSO frames
* which are too large can cause TCP streams to be bursty.
*/
int sysctl_tcp_tso_win_divisor __read_mostly = 3;
int sysctl_tcp_mtu_probing __read_mostly = 0;
int sysctl_tcp_base_mss __read_mostly = 512;
/* By default, RFC2861 behavior. */
int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
static void update_send_head(struct sock *sk, struct tcp_sock *tp,
struct sk_buff *skb)
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
{
sk->sk_send_head = skb->next;
if (sk->sk_send_head == (struct sk_buff *)&sk->sk_write_queue)
sk->sk_send_head = NULL;
tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
tcp_packets_out_inc(sk, tp, skb);
}
/* SND.NXT, if window was not shrunk.
* If window has been shrunk, what should we make? It is not clear at all.
* Using SND.UNA we will fail to open window, SND.NXT is out of window. :-(
* Anything in between SND.UNA...SND.UNA+SND.WND also can be already
* invalid. OK, let's make this for now:
*/
static inline __u32 tcp_acceptable_seq(struct sock *sk, struct tcp_sock *tp)
{
if (!before(tp->snd_una+tp->snd_wnd, tp->snd_nxt))
return tp->snd_nxt;
else
return tp->snd_una+tp->snd_wnd;
}
/* Calculate mss to advertise in SYN segment.
* RFC1122, RFC1063, draft-ietf-tcpimpl-pmtud-01 state that:
*
* 1. It is independent of path mtu.
* 2. Ideally, it is maximal possible segment size i.e. 65535-40.
* 3. For IPv4 it is reasonable to calculate it from maximal MTU of
* attached devices, because some buggy hosts are confused by
* large MSS.
* 4. We do not make 3, we advertise MSS, calculated from first
* hop device mtu, but allow to raise it to ip_rt_min_advmss.
* This may be overridden via information stored in routing table.
* 5. Value 65535 for MSS is valid in IPv6 and means "as large as possible,
* probably even Jumbo".
*/
static __u16 tcp_advertise_mss(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct dst_entry *dst = __sk_dst_get(sk);
int mss = tp->advmss;
if (dst && dst_metric(dst, RTAX_ADVMSS) < mss) {
mss = dst_metric(dst, RTAX_ADVMSS);
tp->advmss = mss;
}
return (__u16)mss;
}
/* RFC2861. Reset CWND after idle period longer RTO to "restart window".
* This is the first part of cwnd validation mechanism. */
static void tcp_cwnd_restart(struct sock *sk, struct dst_entry *dst)
struct tcp_sock *tp = tcp_sk(sk);
s32 delta = tcp_time_stamp - tp->lsndtime;
u32 restart_cwnd = tcp_init_cwnd(tp, dst);
u32 cwnd = tp->snd_cwnd;
tcp_ca_event(sk, CA_EVENT_CWND_RESTART);
tp->snd_ssthresh = tcp_current_ssthresh(sk);
while ((delta -= inet_csk(sk)->icsk_rto) > 0 && cwnd > restart_cwnd)
cwnd >>= 1;
tp->snd_cwnd = max(cwnd, restart_cwnd);
tp->snd_cwnd_stamp = tcp_time_stamp;
tp->snd_cwnd_used = 0;
}
static void tcp_event_data_sent(struct tcp_sock *tp,
struct sk_buff *skb, struct sock *sk)
struct inet_connection_sock *icsk = inet_csk(sk);
const u32 now = tcp_time_stamp;
if (sysctl_tcp_slow_start_after_idle &&
(!tp->packets_out && (s32)(now - tp->lsndtime) > icsk->icsk_rto))
tcp_cwnd_restart(sk, __sk_dst_get(sk));
tp->lsndtime = now;
/* If it is a reply for ato after last received
* packet, enter pingpong mode.
*/
if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
icsk->icsk_ack.pingpong = 1;
static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
tcp_dec_quickack_mode(sk, pkts);
inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
}
/* Determine a window scaling and initial window to offer.
* Based on the assumption that the given amount of space
* will be offered. Store the results in the tp structure.
* NOTE: for smooth operation initial space offering should
* be a multiple of mss if possible. We assume here that mss >= 1.
* This MUST be enforced by all callers.
*/
void tcp_select_initial_window(int __space, __u32 mss,
__u32 *rcv_wnd, __u32 *window_clamp,
int wscale_ok, __u8 *rcv_wscale)
{
unsigned int space = (__space < 0 ? 0 : __space);
/* If no clamp set the clamp to the max possible scaled window */
if (*window_clamp == 0)
(*window_clamp) = (65535 << 14);
space = min(*window_clamp, space);
/* Quantize space offering to a multiple of mss if possible. */
if (space > mss)
space = (space / mss) * mss;
/* NOTE: offering an initial window larger than 32767
* will break some buggy TCP stacks. If the admin tells us
* it is likely we could be speaking with such a buggy stack
* we will truncate our initial window offering to 32K-1
* unless the remote has sent us a window scaling option,
* which we interpret as a sign the remote TCP is not
* misinterpreting the window field as a signed quantity.
if (sysctl_tcp_workaround_signed_windows)
(*rcv_wnd) = min(space, MAX_TCP_WINDOW);
else
(*rcv_wnd) = space;
(*rcv_wscale) = 0;
if (wscale_ok) {
/* Set window scaling on max possible window
* See RFC1323 for an explanation of the limit to 14
*/
space = max_t(u32, sysctl_tcp_rmem[2], sysctl_rmem_max);
space = min_t(u32, space, *window_clamp);
while (space > 65535 && (*rcv_wscale) < 14) {
space >>= 1;
(*rcv_wscale)++;
}
}
/* Set initial window to value enough for senders,
* following RFC2414. Senders, not following this RFC,
* will be satisfied with 2.
*/
if (mss > (1<<*rcv_wscale)) {
int init_cwnd = 4;
if (mss > 1460*3)
else if (mss > 1460)
init_cwnd = 3;
if (*rcv_wnd > init_cwnd*mss)
*rcv_wnd = init_cwnd*mss;
}
/* Set the clamp no higher than max representable value */
(*window_clamp) = min(65535U << (*rcv_wscale), *window_clamp);
}
/* Chose a new window to advertise, update state in tcp_sock for the
* socket, and return result with RFC1323 scaling applied. The return
* value can be stuffed directly into th->window for an outgoing
* frame.
*/
{
struct tcp_sock *tp = tcp_sk(sk);
u32 cur_win = tcp_receive_window(tp);
u32 new_win = __tcp_select_window(sk);
/* Never shrink the offered window */
if(new_win < cur_win) {
/* Danger Will Robinson!
* Don't update rcv_wup/rcv_wnd here or else
* we will not be able to advertise a zero
* window in time. --DaveM
*
* Relax Will Robinson.
*/
new_win = cur_win;
}
tp->rcv_wnd = new_win;
tp->rcv_wup = tp->rcv_nxt;
/* Make sure we do not exceed the maximum possible
* scaled window.
*/
if (!tp->rx_opt.rcv_wscale && sysctl_tcp_workaround_signed_windows)
new_win = min(new_win, MAX_TCP_WINDOW);
else
new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
/* RFC1323 scaling applied */
new_win >>= tp->rx_opt.rcv_wscale;
/* If we advertise zero window, disable fast path. */
if (new_win == 0)
tp->pred_flags = 0;
return new_win;
}
static void tcp_build_and_update_options(__be32 *ptr, struct tcp_sock *tp,
__u32 tstamp, __u8 **md5_hash)
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_TIMESTAMP << 8) |
TCPOLEN_TIMESTAMP);
*ptr++ = htonl(tstamp);
*ptr++ = htonl(tp->rx_opt.ts_recent);
}
if (tp->rx_opt.eff_sacks) {
struct tcp_sack_block *sp = tp->rx_opt.dsack ? tp->duplicate_sack : tp->selective_acks;
int this_sack;
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_SACK << 8) |
(TCPOLEN_SACK_BASE + (tp->rx_opt.eff_sacks *
TCPOLEN_SACK_PERBLOCK)));
for(this_sack = 0; this_sack < tp->rx_opt.eff_sacks; this_sack++) {
*ptr++ = htonl(sp[this_sack].start_seq);
*ptr++ = htonl(sp[this_sack].end_seq);
}
if (tp->rx_opt.dsack) {
tp->rx_opt.dsack = 0;
tp->rx_opt.eff_sacks--;
}
}
#ifdef CONFIG_TCP_MD5SIG
if (md5_hash) {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_MD5SIG << 8) |
TCPOLEN_MD5SIG);
*md5_hash = (__u8 *)ptr;
}
#endif
}
/* Construct a tcp options header for a SYN or SYN_ACK packet.
* If this is every changed make sure to change the definition of
* MAX_SYN_SIZE to match the new maximum number of options that you
* can generate.
*
* Note - that with the RFC2385 TCP option, we make room for the
* 16 byte MD5 hash. This will be filled in later, so the pointer for the
* location to be filled is passed back up.
static void tcp_syn_build_options(__be32 *ptr, int mss, int ts, int sack,
__u32 ts_recent, __u8 **md5_hash)
{
/* We always get an MSS option.
* The option bytes which will be seen in normal data
* packets should timestamps be used, must be in the MSS
* advertised. But we subtract them from tp->mss_cache so
* that calculations in tcp_sendmsg are simpler etc.
* So account for this fact here if necessary. If we
* don't do this correctly, as a receiver we won't
* recognize data packets as being full sized when we
* should, and thus we won't abide by the delayed ACK
* rules correctly.
* SACKs don't matter, we never delay an ACK when we
* have any of those going out.
*/
*ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | mss);
if (ts) {
if(sack)
*ptr++ = htonl((TCPOPT_SACK_PERM << 24) |
(TCPOLEN_SACK_PERM << 16) |
(TCPOPT_TIMESTAMP << 8) |
TCPOLEN_TIMESTAMP);
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_TIMESTAMP << 8) |
TCPOLEN_TIMESTAMP);
*ptr++ = htonl(tstamp); /* TSVAL */
*ptr++ = htonl(ts_recent); /* TSECR */
} else if(sack)
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_SACK_PERM << 8) |
TCPOLEN_SACK_PERM);
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_WINDOW << 16) |
(TCPOLEN_WINDOW << 8) |
(wscale));
#ifdef CONFIG_TCP_MD5SIG
/*
* If MD5 is enabled, then we set the option, and include the size
* (always 18). The actual MD5 hash is added just before the
* packet is sent.
*/
if (md5_hash) {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_MD5SIG << 8) |
TCPOLEN_MD5SIG);
*md5_hash = (__u8 *) ptr;
}
#endif
/* This routine actually transmits TCP packets queued in by
* tcp_do_sendmsg(). This is used by both the initial
* transmission and possible later retransmissions.
* All SKB's seen here are completely headerless. It is our
* job to build the TCP header, and pass the packet down to
* IP so it can do the same plus pass the packet off to the
* device.
*
* We are working here with either a clone of the original
* SKB, or a fresh unique copy made by the retransmit engine.
*/
static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, gfp_t gfp_mask)
const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet;
struct tcp_sock *tp;
struct tcp_skb_cb *tcb;
int tcp_header_size;
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *md5;
__u8 *md5_hash_location;
#endif
struct tcphdr *th;
int sysctl_flags;
int err;
BUG_ON(!skb || !tcp_skb_pcount(skb));
/* If congestion control is doing timestamping, we must
* take such a timestamp before we potentially clone/copy.
*/
if (icsk->icsk_ca_ops->rtt_sample)
__net_timestamp(skb);
if (likely(clone_it)) {
if (unlikely(skb_cloned(skb)))
skb = pskb_copy(skb, gfp_mask);
else
skb = skb_clone(skb, gfp_mask);
if (unlikely(!skb))
return -ENOBUFS;
}
inet = inet_sk(sk);
tp = tcp_sk(sk);
tcb = TCP_SKB_CB(skb);
tcp_header_size = tp->tcp_header_len;
#define SYSCTL_FLAG_TSTAMPS 0x1
#define SYSCTL_FLAG_WSCALE 0x2
#define SYSCTL_FLAG_SACK 0x4
sysctl_flags = 0;
if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) {
tcp_header_size = sizeof(struct tcphdr) + TCPOLEN_MSS;
if(sysctl_tcp_timestamps) {
tcp_header_size += TCPOLEN_TSTAMP_ALIGNED;
sysctl_flags |= SYSCTL_FLAG_TSTAMPS;
if (sysctl_tcp_window_scaling) {
tcp_header_size += TCPOLEN_WSCALE_ALIGNED;
sysctl_flags |= SYSCTL_FLAG_WSCALE;
if (sysctl_tcp_sack) {
sysctl_flags |= SYSCTL_FLAG_SACK;
if (!(sysctl_flags & SYSCTL_FLAG_TSTAMPS))
tcp_header_size += TCPOLEN_SACKPERM_ALIGNED;
} else if (unlikely(tp->rx_opt.eff_sacks)) {
/* A SACK is 2 pad bytes, a 2 byte header, plus
* 2 32-bit sequence numbers for each SACK block.
*/
tcp_header_size += (TCPOLEN_SACK_BASE_ALIGNED +
(tp->rx_opt.eff_sacks *
TCPOLEN_SACK_PERBLOCK));
}
if (tcp_packets_in_flight(tp) == 0)
tcp_ca_event(sk, CA_EVENT_TX_START);
#ifdef CONFIG_TCP_MD5SIG
/*
* Are we doing MD5 on this segment? If so - make
* room for it.
*/
md5 = tp->af_specific->md5_lookup(sk, sk);
if (md5)
tcp_header_size += TCPOLEN_MD5SIG_ALIGNED;
#endif
th = (struct tcphdr *) skb_push(skb, tcp_header_size);
skb->h.th = th;
skb_set_owner_w(skb, sk);
/* Build TCP header and checksum it. */
th->source = inet->sport;
th->dest = inet->dport;
th->seq = htonl(tcb->seq);
th->ack_seq = htonl(tp->rcv_nxt);
*(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) |
tcb->flags);
if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) {
/* RFC1323: The window in SYN & SYN/ACK segments
* is never scaled.
*/
th->window = htons(tp->rcv_wnd);
} else {
th->window = htons(tcp_select_window(sk));
}
th->check = 0;
th->urg_ptr = 0;
if (unlikely(tp->urg_mode &&
between(tp->snd_up, tcb->seq+1, tcb->seq+0xFFFF))) {
th->urg_ptr = htons(tp->snd_up-tcb->seq);
th->urg = 1;
}
if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) {
tcp_syn_build_options((__be32 *)(th + 1),
tcp_advertise_mss(sk),
(sysctl_flags & SYSCTL_FLAG_TSTAMPS),
(sysctl_flags & SYSCTL_FLAG_SACK),
(sysctl_flags & SYSCTL_FLAG_WSCALE),
tp->rx_opt.rcv_wscale,
tcb->when,
tp->rx_opt.ts_recent,
#ifdef CONFIG_TCP_MD5SIG
md5 ? &md5_hash_location :
#endif
NULL);
tcp_build_and_update_options((__be32 *)(th + 1),
tp, tcb->when,
#ifdef CONFIG_TCP_MD5SIG
md5 ? &md5_hash_location :
#endif
NULL);
TCP_ECN_send(sk, tp, skb, tcp_header_size);
}
#ifdef CONFIG_TCP_MD5SIG
/* Calculate the MD5 hash, as we have all we need now */
if (md5) {
tp->af_specific->calc_md5_hash(md5_hash_location,
md5,
sk, NULL, NULL,
skb->h.th,
sk->sk_protocol,
skb->len);
}
#endif
Arnaldo Carvalho de Melo
committed
icsk->icsk_af_ops->send_check(sk, skb->len, skb);
if (likely(tcb->flags & TCPCB_FLAG_ACK))
tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
if (skb->len != tcp_header_size)
tcp_event_data_sent(tp, skb, sk);
if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)
TCP_INC_STATS(TCP_MIB_OUTSEGS);
err = icsk->icsk_af_ops->queue_xmit(skb, 0);
return err;
tcp_enter_cwr(sk);
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
#undef SYSCTL_FLAG_TSTAMPS
#undef SYSCTL_FLAG_WSCALE
#undef SYSCTL_FLAG_SACK
}
/* This routine just queue's the buffer
*
* NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
* otherwise socket can stall.
*/
static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
/* Advance write_seq and place onto the write_queue. */
tp->write_seq = TCP_SKB_CB(skb)->end_seq;
skb_header_release(skb);
__skb_queue_tail(&sk->sk_write_queue, skb);
sk_charge_skb(sk, skb);
/* Queue it, remembering where we must start sending. */
if (sk->sk_send_head == NULL)
sk->sk_send_head = skb;
}
static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now)
if (skb->len <= mss_now || !sk_can_gso(sk)) {
/* Avoid the costly divide in the normal
* non-TSO case.
*/
skb_shinfo(skb)->gso_segs = 1;
skb_shinfo(skb)->gso_size = 0;
skb_shinfo(skb)->gso_type = 0;
} else {
unsigned int factor;
factor = skb->len + (mss_now - 1);
factor /= mss_now;
skb_shinfo(skb)->gso_segs = factor;
skb_shinfo(skb)->gso_size = mss_now;
skb_shinfo(skb)->gso_type = sk->sk_gso_type;
}
}
/* Function to create two new TCP segments. Shrinks the given segment
* to the specified size and appends a new segment with the rest of the
* packet to the list. This won't be called frequently, I hope.
* Remember, these are still headerless SKBs at this point.
*/
int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss_now)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *buff;
int nsize, old_factor;
nsize = skb_headlen(skb) - len;
if (nsize < 0)
nsize = 0;
if (skb_cloned(skb) &&
skb_is_nonlinear(skb) &&
pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
return -ENOMEM;
/* Get a new skb... force flag on. */
buff = sk_stream_alloc_skb(sk, nsize, GFP_ATOMIC);
if (buff == NULL)
return -ENOMEM; /* We'll just try again later. */
sk_charge_skb(sk, buff);
nlen = skb->len - len - nsize;
buff->truesize += nlen;
skb->truesize -= nlen;
/* Correct the sequence numbers. */
TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len;
TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq;
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq;
/* PSH and FIN should only be set in the second packet. */
flags = TCP_SKB_CB(skb)->flags;
TCP_SKB_CB(skb)->flags = flags & ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH);
TCP_SKB_CB(buff)->flags = flags;
TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked;
if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_PARTIAL) {
/* Copy and checksum data tail into the new buffer. */
buff->csum = csum_partial_copy_nocheck(skb->data + len, skb_put(buff, nsize),
nsize, 0);
skb_trim(skb, len);
skb->csum = csum_block_sub(skb->csum, buff->csum, len);
} else {
skb->ip_summed = CHECKSUM_PARTIAL;
skb_split(skb, buff, len);
}
buff->ip_summed = skb->ip_summed;
/* Looks stupid, but our code really uses when of
* skbs, which it never sent before. --ANK
*/
TCP_SKB_CB(buff)->when = TCP_SKB_CB(skb)->when;
buff->tstamp = skb->tstamp;
old_factor = tcp_skb_pcount(skb);
/* Fix up tso_factor for both original and new SKB. */
tcp_set_skb_tso_segs(sk, skb, mss_now);
tcp_set_skb_tso_segs(sk, buff, mss_now);
/* If this packet has been sent out already, we must
* adjust the various packet counters.
*/
if (!before(tp->snd_nxt, TCP_SKB_CB(buff)->end_seq)) {
int diff = old_factor - tcp_skb_pcount(skb) -
tcp_skb_pcount(buff);
tp->packets_out -= diff;
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
tp->sacked_out -= diff;
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
tp->retrans_out -= diff;
if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) {
tp->lost_out -= diff;
tp->left_out -= diff;
}
/* Adjust Reno SACK estimate. */
if (!tp->rx_opt.sack_ok) {
tp->sacked_out -= diff;
if ((int)tp->sacked_out < 0)
tp->sacked_out = 0;
tcp_sync_left_out(tp);
}
tp->fackets_out -= diff;
if ((int)tp->fackets_out < 0)
tp->fackets_out = 0;
}
skb_header_release(buff);
return 0;
}
/* This is similar to __pskb_pull_head() (it will go to core/skbuff.c
* eventually). The difference is that pulled data not copied, but
* immediately discarded.
*/
static void __pskb_trim_head(struct sk_buff *skb, int len)
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
{
int i, k, eat;
eat = len;
k = 0;
for (i=0; i<skb_shinfo(skb)->nr_frags; i++) {
if (skb_shinfo(skb)->frags[i].size <= eat) {
put_page(skb_shinfo(skb)->frags[i].page);
eat -= skb_shinfo(skb)->frags[i].size;
} else {
skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i];
if (eat) {
skb_shinfo(skb)->frags[k].page_offset += eat;
skb_shinfo(skb)->frags[k].size -= eat;
eat = 0;
}
k++;
}
}
skb_shinfo(skb)->nr_frags = k;
skb->tail = skb->data;
skb->data_len -= len;
skb->len = skb->data_len;
}
int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
{
if (skb_cloned(skb) &&
pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
return -ENOMEM;
/* If len == headlen, we avoid __skb_pull to preserve alignment. */
if (unlikely(len < skb_headlen(skb)))
else
__pskb_trim_head(skb, len - skb_headlen(skb));
skb->ip_summed = CHECKSUM_PARTIAL;
skb->truesize -= len;
sk->sk_wmem_queued -= len;
sk->sk_forward_alloc += len;
sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
/* Any change of skb->len requires recalculation of tso
* factor and mss.
*/
if (tcp_skb_pcount(skb) > 1)
tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk, 1));
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
/* Not accounting for SACKs here. */
int tcp_mtu_to_mss(struct sock *sk, int pmtu)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
int mss_now;
/* Calculate base mss without TCP options:
It is MMS_S - sizeof(tcphdr) of rfc1122
*/
mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr);
/* Clamp it (mss_clamp does not include tcp options) */
if (mss_now > tp->rx_opt.mss_clamp)
mss_now = tp->rx_opt.mss_clamp;
/* Now subtract optional transport overhead */
mss_now -= icsk->icsk_ext_hdr_len;
/* Then reserve room for full set of TCP options and 8 bytes of data */
if (mss_now < 48)
mss_now = 48;
/* Now subtract TCP options size, not including SACKs */
mss_now -= tp->tcp_header_len - sizeof(struct tcphdr);
return mss_now;
}
/* Inverse of above */
int tcp_mss_to_mtu(struct sock *sk, int mss)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
int mtu;
mtu = mss +
tp->tcp_header_len +
icsk->icsk_ext_hdr_len +
icsk->icsk_af_ops->net_header_len;
return mtu;
}
void tcp_mtup_init(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
icsk->icsk_mtup.enabled = sysctl_tcp_mtu_probing > 1;
icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) +
icsk->icsk_af_ops->net_header_len;
icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, sysctl_tcp_base_mss);
icsk->icsk_mtup.probe_size = 0;
}
/* This function synchronize snd mss to current pmtu/exthdr set.
tp->rx_opt.user_mss is mss set by user by TCP_MAXSEG. It does NOT counts
for TCP options, but includes only bare TCP header.
tp->rx_opt.mss_clamp is mss negotiated at connection setup.
It is minimum of user_mss and mss received with SYN.
inet_csk(sk)->icsk_pmtu_cookie is last pmtu, seen by this function.
tp->mss_cache is current effective sending mss, including
all tcp options except for SACKs. It is evaluated,
taking into account current pmtu, but never exceeds
tp->rx_opt.mss_clamp.
NOTE1. rfc1122 clearly states that advertised MSS
DOES NOT include either tcp or ip options.
NOTE2. inet_csk(sk)->icsk_pmtu_cookie and tp->mss_cache
are READ ONLY outside this function. --ANK (980731)
*/
unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
if (icsk->icsk_mtup.search_high > pmtu)
icsk->icsk_mtup.search_high = pmtu;
/* Bound mss with half of window */
if (tp->max_window && mss_now > (tp->max_window>>1))
mss_now = max((tp->max_window>>1), 68U - tp->tcp_header_len);
/* And store cached results */
icsk->icsk_pmtu_cookie = pmtu;
if (icsk->icsk_mtup.enabled)
mss_now = min(mss_now, tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low));
return mss_now;
}
/* Compute the current effective MSS, taking SACKs and IP options,
* and even PMTU discovery events into account.
*
* LARGESEND note: !urg_mode is overkill, only frames up to snd_up
* cannot be large. However, taking into account rare use of URG, this
* is not a big flaw.
*/
unsigned int tcp_current_mss(struct sock *sk, int large_allowed)
{
struct tcp_sock *tp = tcp_sk(sk);
struct dst_entry *dst = __sk_dst_get(sk);
u32 mss_now;
u16 xmit_size_goal;
int doing_tso = 0;
mss_now = tp->mss_cache;
if (large_allowed && sk_can_gso(sk) && !tp->urg_mode)
if (mtu != inet_csk(sk)->icsk_pmtu_cookie)
if (tp->rx_opt.eff_sacks)
mss_now -= (TCPOLEN_SACK_BASE_ALIGNED +
(tp->rx_opt.eff_sacks * TCPOLEN_SACK_PERBLOCK));
#ifdef CONFIG_TCP_MD5SIG
if (tp->af_specific->md5_lookup(sk, sk))
mss_now -= TCPOLEN_MD5SIG_ALIGNED;
#endif
Arnaldo Carvalho de Melo
committed
xmit_size_goal = (65535 -
inet_csk(sk)->icsk_af_ops->net_header_len -
inet_csk(sk)->icsk_ext_hdr_len -
tp->tcp_header_len);
if (tp->max_window &&
(xmit_size_goal > (tp->max_window >> 1)))
xmit_size_goal = max((tp->max_window >> 1),
68U - tp->tcp_header_len);
xmit_size_goal -= (xmit_size_goal % mss_now);
tp->xmit_size_goal = xmit_size_goal;
/* Congestion window validation. (RFC2861) */
static void tcp_cwnd_validate(struct sock *sk, struct tcp_sock *tp)
{
__u32 packets_out = tp->packets_out;
if (packets_out >= tp->snd_cwnd) {
/* Network is feed fully. */
tp->snd_cwnd_used = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
} else {
/* Network starves. */
if (tp->packets_out > tp->snd_cwnd_used)
tp->snd_cwnd_used = tp->packets_out;
if ((s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto)
tcp_cwnd_application_limited(sk);
}
}
static unsigned int tcp_window_allows(struct tcp_sock *tp, struct sk_buff *skb, unsigned int mss_now, unsigned int cwnd)
{
u32 window, cwnd_len;
window = (tp->snd_una + tp->snd_wnd - TCP_SKB_CB(skb)->seq);
cwnd_len = mss_now * cwnd;
return min(window, cwnd_len);
}
/* Can at least one segment of SKB be sent right now, according to the
* congestion window rules? If so, return how many segments are allowed.
*/
static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp, struct sk_buff *skb)
{
u32 in_flight, cwnd;
/* Don't be strict about the congestion window for the final FIN. */
if ((TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) &&
tcp_skb_pcount(skb) == 1)
return 1;
in_flight = tcp_packets_in_flight(tp);
cwnd = tp->snd_cwnd;
if (in_flight < cwnd)
return (cwnd - in_flight);
return 0;
}
/* This must be invoked the first time we consider transmitting
* SKB onto the wire.
*/
static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now)
{
int tso_segs = tcp_skb_pcount(skb);
if (!tso_segs ||
(tso_segs > 1 &&
tcp_set_skb_tso_segs(sk, skb, mss_now);
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
tso_segs = tcp_skb_pcount(skb);
}
return tso_segs;
}
static inline int tcp_minshall_check(const struct tcp_sock *tp)
{
return after(tp->snd_sml,tp->snd_una) &&
!after(tp->snd_sml, tp->snd_nxt);
}
/* Return 0, if packet can be sent now without violation Nagle's rules:
* 1. It is full sized.
* 2. Or it contains FIN. (already checked by caller)
* 3. Or TCP_NODELAY was set.
* 4. Or TCP_CORK is not set, and all sent packets are ACKed.
* With Minshall's modification: all sent small packets are ACKed.
*/
static inline int tcp_nagle_check(const struct tcp_sock *tp,
const struct sk_buff *skb,
unsigned mss_now, int nonagle)
{
return (skb->len < mss_now &&
((nonagle&TCP_NAGLE_CORK) ||
(!nonagle &&
tp->packets_out &&
tcp_minshall_check(tp))));
}
/* Return non-zero if the Nagle test allows this packet to be
* sent now.
*/
static inline int tcp_nagle_test(struct tcp_sock *tp, struct sk_buff *skb,
unsigned int cur_mss, int nonagle)
{
/* Nagle rule does not apply to frames, which sit in the middle of the
* write_queue (they have no chances to get new data).
*
* This is implemented in the callers, where they modify the 'nonagle'
* argument based upon the location of SKB in the send queue.
*/
if (nonagle & TCP_NAGLE_PUSH)
return 1;
/* Don't use the nagle rule for urgent data (or for the final FIN). */
if (tp->urg_mode ||
(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN))
return 1;
if (!tcp_nagle_check(tp, skb, cur_mss, nonagle))
return 1;
return 0;
}
/* Does at least the first segment of SKB fit into the send window? */
static inline int tcp_snd_wnd_test(struct tcp_sock *tp, struct sk_buff *skb, unsigned int cur_mss)
{
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
if (skb->len > cur_mss)
end_seq = TCP_SKB_CB(skb)->seq + cur_mss;
return !after(end_seq, tp->snd_una + tp->snd_wnd);
}
/* This checks if the data bearing packet SKB (usually sk->sk_send_head)
* should be put on the wire right now. If so, it returns the number of
* packets allowed by the congestion window.
*/
static unsigned int tcp_snd_test(struct sock *sk, struct sk_buff *skb,
unsigned int cur_mss, int nonagle)
{
struct tcp_sock *tp = tcp_sk(sk);
unsigned int cwnd_quota;
tcp_init_tso_segs(sk, skb, cur_mss);
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
if (!tcp_nagle_test(tp, skb, cur_mss, nonagle))
return 0;
cwnd_quota = tcp_cwnd_test(tp, skb);
if (cwnd_quota &&
!tcp_snd_wnd_test(tp, skb, cur_mss))
cwnd_quota = 0;
return cwnd_quota;
}
static inline int tcp_skb_is_last(const struct sock *sk,
const struct sk_buff *skb)
{
return skb->next == (struct sk_buff *)&sk->sk_write_queue;
}
int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp)
{
struct sk_buff *skb = sk->sk_send_head;
return (skb &&
tcp_snd_test(sk, skb, tcp_current_mss(sk, 1),
(tcp_skb_is_last(sk, skb) ?
TCP_NAGLE_PUSH :
tp->nonagle)));
}
/* Trim TSO SKB to LEN bytes, put the remaining data into a new packet
* which is put after SKB on the list. It is very much like
* tcp_fragment() except that it may make several kinds of assumptions
* in order to speed up the splitting operation. In particular, we
* know that all the data is in scatter-gather pages, and that the
* packet has never been sent out before (and thus is not cloned).
*/
static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, unsigned int mss_now)
{
struct sk_buff *buff;
int nlen = skb->len - len;
u16 flags;
/* All of a TSO frame must be composed of paged data. */
if (skb->len != skb->data_len)
return tcp_fragment(sk, skb, len, mss_now);
buff = sk_stream_alloc_pskb(sk, 0, 0, GFP_ATOMIC);
if (unlikely(buff == NULL))
return -ENOMEM;
sk_charge_skb(sk, buff);
buff->truesize += nlen;
skb->truesize -= nlen;
/* Correct the sequence numbers. */
TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len;
TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq;
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq;
/* PSH and FIN should only be set in the second packet. */
flags = TCP_SKB_CB(skb)->flags;
TCP_SKB_CB(skb)->flags = flags & ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH);
TCP_SKB_CB(buff)->flags = flags;
/* This packet was never sent out yet, so no SACK bits. */
TCP_SKB_CB(buff)->sacked = 0;
buff->ip_summed = skb->ip_summed = CHECKSUM_PARTIAL;
skb_split(skb, buff, len);
/* Fix up tso_factor for both original and new SKB. */
tcp_set_skb_tso_segs(sk, skb, mss_now);
tcp_set_skb_tso_segs(sk, buff, mss_now);
/* Link BUFF into the send queue. */
skb_header_release(buff);
return 0;
}
/* Try to defer sending, if possible, in order to minimize the amount
* of TSO splitting we do. View it as a kind of TSO Nagle test.
*
* This algorithm is from John Heffner.
*/
static int tcp_tso_should_defer(struct sock *sk, struct tcp_sock *tp, struct sk_buff *skb)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 send_win, cong_win, limit, in_flight;
if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)
if (icsk->icsk_ca_state != TCP_CA_Open)
goto send_now;
/* Defer for less than two clock ticks. */
if (!tp->tso_deferred && ((jiffies<<1)>>1) - (tp->tso_deferred>>1) > 1)
goto send_now;
in_flight = tcp_packets_in_flight(tp);
BUG_ON(tcp_skb_pcount(skb) <= 1 ||
(tp->snd_cwnd <= in_flight));
send_win = (tp->snd_una + tp->snd_wnd) - TCP_SKB_CB(skb)->seq;
/* From in_flight test above, we know that cwnd > in_flight. */
cong_win = (tp->snd_cwnd - in_flight) * tp->mss_cache;
limit = min(send_win, cong_win);
/* If a full-sized TSO skb can be sent, do it. */
if (limit >= 65536)
if (sysctl_tcp_tso_win_divisor) {
u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
/* If at least some fraction of a window is available,
* just use it.
*/
chunk /= sysctl_tcp_tso_win_divisor;
if (limit >= chunk)
} else {
/* Different approach, try not to defer past a single
* ACK. Receiver should ACK every other full sized
* frame, so if we have space for more than 3 frames
* then send now.
*/
if (limit > tcp_max_burst(tp) * tp->mss_cache)
}
/* Ok, it looks like it is advisable to defer. */
send_now:
tp->tso_deferred = 0;
return 0;
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
/* Create a new MTU probe if we are ready.
* Returns 0 if we should wait to probe (no cwnd available),
* 1 if a probe was sent,
* -1 otherwise */
static int tcp_mtu_probe(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct sk_buff *skb, *nskb, *next;
int len;
int probe_size;
unsigned int pif;
int copy;
int mss_now;
/* Not currently probing/verifying,
* not in recovery,
* have enough cwnd, and
* not SACKing (the variable headers throw things off) */
if (!icsk->icsk_mtup.enabled ||
icsk->icsk_mtup.probe_size ||
inet_csk(sk)->icsk_ca_state != TCP_CA_Open ||
tp->snd_cwnd < 11 ||
tp->rx_opt.eff_sacks)
return -1;
/* Very simple search strategy: just double the MSS. */
mss_now = tcp_current_mss(sk, 0);
probe_size = 2*tp->mss_cache;
if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high)) {
/* TODO: set timer for probe_converge_event */
return -1;
}
/* Have enough data in the send queue to probe? */
len = 0;
if ((skb = sk->sk_send_head) == NULL)
return -1;
while ((len += skb->len) < probe_size && !tcp_skb_is_last(sk, skb))
skb = skb->next;
if (len < probe_size)
return -1;
/* Receive window check. */
if (after(TCP_SKB_CB(skb)->seq + probe_size, tp->snd_una + tp->snd_wnd)) {
if (tp->snd_wnd < probe_size)
return -1;
else
return 0;
}
/* Do we need to wait to drain cwnd? */
pif = tcp_packets_in_flight(tp);
if (pif + 2 > tp->snd_cwnd) {
/* With no packets in flight, don't stall. */
if (pif == 0)
return -1;
else
return 0;
}
/* We're allowed to probe. Build it now. */
if ((nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC)) == NULL)
return -1;
sk_charge_skb(sk, nskb);
skb = sk->sk_send_head;
__skb_insert(nskb, skb->prev, skb, &sk->sk_write_queue);
sk->sk_send_head = nskb;
TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
TCP_SKB_CB(nskb)->flags = TCPCB_FLAG_ACK;
TCP_SKB_CB(nskb)->sacked = 0;
nskb->csum = 0;
nskb->ip_summed = skb->ip_summed;
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
len = 0;
while (len < probe_size) {
next = skb->next;
copy = min_t(int, skb->len, probe_size - len);
if (nskb->ip_summed)
skb_copy_bits(skb, 0, skb_put(nskb, copy), copy);
else
nskb->csum = skb_copy_and_csum_bits(skb, 0,
skb_put(nskb, copy), copy, nskb->csum);
if (skb->len <= copy) {
/* We've eaten all the data from this skb.
* Throw it away. */
TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags;
__skb_unlink(skb, &sk->sk_write_queue);
sk_stream_free_skb(sk, skb);
} else {
TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags &
~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH);
if (!skb_shinfo(skb)->nr_frags) {
skb_pull(skb, copy);
if (skb->ip_summed != CHECKSUM_PARTIAL)
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
skb->csum = csum_partial(skb->data, skb->len, 0);
} else {
__pskb_trim_head(skb, copy);
tcp_set_skb_tso_segs(sk, skb, mss_now);
}
TCP_SKB_CB(skb)->seq += copy;
}
len += copy;
skb = next;
}
tcp_init_tso_segs(sk, nskb, nskb->len);
/* We're ready to send. If this fails, the probe will
* be resegmented into mss-sized pieces by tcp_write_xmit(). */
TCP_SKB_CB(nskb)->when = tcp_time_stamp;
if (!tcp_transmit_skb(sk, nskb, 1, GFP_ATOMIC)) {
/* Decrement cwnd here because we are sending
* effectively two packets. */
tp->snd_cwnd--;
update_send_head(sk, tp, nskb);
icsk->icsk_mtup.probe_size = tcp_mss_to_mtu(sk, nskb->len);
tp->mtu_probe.probe_seq_start = TCP_SKB_CB(nskb)->seq;
tp->mtu_probe.probe_seq_end = TCP_SKB_CB(nskb)->end_seq;
return 1;
}
return -1;
}
/* This routine writes packets to the network. It advances the
* send_head. This happens as incoming acks open up the remote
* window for us.
*
* Returns 1, if no segments are in flight and we have queued segments, but
* cannot send anything now because of SWS or another problem.
*/
static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle)
unsigned int tso_segs, sent_pkts;
int cwnd_quota;
/* If we are closed, the bytes will have to remain here.
* In time closedown will finish, we empty the write queue and all
* will be happy.
*/
if (unlikely(sk->sk_state == TCP_CLOSE))
return 0;
/* Do MTU probing. */
if ((result = tcp_mtu_probe(sk)) == 0) {
return 0;
} else if (result > 0) {
sent_pkts = 1;
}
unsigned int limit;
tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
cwnd_quota = tcp_cwnd_test(tp, skb);
if (!cwnd_quota)
break;
if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now)))
break;
if (tso_segs == 1) {
if (unlikely(!tcp_nagle_test(tp, skb, mss_now,
(tcp_skb_is_last(sk, skb) ?
nonagle : TCP_NAGLE_PUSH))))
break;
} else {
if (tcp_tso_should_defer(sk, tp, skb))
break;
}
limit = mss_now;
limit = tcp_window_allows(tp, skb,
mss_now, cwnd_quota);
if (skb->len < limit) {
unsigned int trim = skb->len % mss_now;
if (trim)
limit = skb->len - trim;
}
if (skb->len > limit &&
unlikely(tso_fragment(sk, skb, limit, mss_now)))
break;
TCP_SKB_CB(skb)->when = tcp_time_stamp;
if (unlikely(tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC)))
/* Advance the send_head. This one is sent out.
* This call will increment packets_out.
*/
update_send_head(sk, tp, skb);
tcp_minshall_update(tp, mss_now, skb);
sent_pkts++;
if (likely(sent_pkts)) {
tcp_cwnd_validate(sk, tp);
return 0;
return !tp->packets_out && sk->sk_send_head;
/* Push out any pending frames which were held back due to
* TCP_CORK or attempt at coalescing tiny packets.
* The socket must be locked by the caller.
*/
void __tcp_push_pending_frames(struct sock *sk, struct tcp_sock *tp,
unsigned int cur_mss, int nonagle)
{
struct sk_buff *skb = sk->sk_send_head;
if (skb) {
if (tcp_write_xmit(sk, cur_mss, nonagle))
tcp_check_probe_timer(sk, tp);
}
}
/* Send _single_ skb sitting at the send head. This function requires
* true push pending frames to setup probe timer etc.
*/
void tcp_push_one(struct sock *sk, unsigned int mss_now)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb = sk->sk_send_head;
unsigned int tso_segs, cwnd_quota;
BUG_ON(!skb || skb->len < mss_now);
tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
cwnd_quota = tcp_snd_test(sk, skb, mss_now, TCP_NAGLE_PUSH);
if (likely(cwnd_quota)) {
unsigned int limit;
limit = mss_now;
limit = tcp_window_allows(tp, skb,
mss_now, cwnd_quota);
if (skb->len < limit) {
unsigned int trim = skb->len % mss_now;
if (trim)
limit = skb->len - trim;
}
}
if (skb->len > limit &&
unlikely(tso_fragment(sk, skb, limit, mss_now)))
return;
/* Send it out now. */
TCP_SKB_CB(skb)->when = tcp_time_stamp;
if (likely(!tcp_transmit_skb(sk, skb, 1, sk->sk_allocation))) {
update_send_head(sk, tp, skb);
tcp_cwnd_validate(sk, tp);
return;
}
}
}
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
/* This function returns the amount that we can raise the
* usable window based on the following constraints
*
* 1. The window can never be shrunk once it is offered (RFC 793)
* 2. We limit memory per socket
*
* RFC 1122:
* "the suggested [SWS] avoidance algorithm for the receiver is to keep
* RECV.NEXT + RCV.WIN fixed until:
* RCV.BUFF - RCV.USER - RCV.WINDOW >= min(1/2 RCV.BUFF, MSS)"
*
* i.e. don't raise the right edge of the window until you can raise
* it at least MSS bytes.
*
* Unfortunately, the recommended algorithm breaks header prediction,
* since header prediction assumes th->window stays fixed.
*
* Strictly speaking, keeping th->window fixed violates the receiver
* side SWS prevention criteria. The problem is that under this rule
* a stream of single byte packets will cause the right side of the
* window to always advance by a single byte.
*
* Of course, if the sender implements sender side SWS prevention
* then this will not be a problem.
*
* BSD seems to make the following compromise:
*
* If the free space is less than the 1/4 of the maximum
* space available and the free space is less than 1/2 mss,
* then set the window to 0.
* [ Actually, bsd uses MSS and 1/4 of maximal _window_ ]
* Otherwise, just prevent the window from shrinking
* and from being larger than the largest representable value.
*
* This prevents incremental opening of the window in the regime
* where TCP is limited by the speed of the reader side taking
* data out of the TCP receive queue. It does nothing about
* those cases where the window is constrained on the sender side
* because the pipeline is full.
*
* BSD also seems to "accidentally" limit itself to windows that are a
* multiple of MSS, at least until the free space gets quite small.
* This would appear to be a side effect of the mbuf implementation.
* Combining these two algorithms results in the observed behavior
* of having a fixed window size at almost all times.
*
* Below we obtain similar behavior by forcing the offered window to
* a multiple of the mss when it is feasible to do so.
*
* Note, we don't "adjust" for TIMESTAMP or SACK option bytes.
* Regular options like TIMESTAMP are taken into account.
*/
u32 __tcp_select_window(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
/* MSS for the peer's data. Previous versions used mss_clamp
* here. I don't know if the value based on our guesses
* of peer's MSS is better for the performance. It's more correct
* but may be worse for the performance because of rcv_mss
* fluctuations. --SAW 1998/11/1
*/
int mss = icsk->icsk_ack.rcv_mss;
int free_space = tcp_space(sk);
int full_space = min_t(int, tp->window_clamp, tcp_full_space(sk));
int window;
if (mss > full_space)
mss = full_space;
if (free_space < full_space/2) {
icsk->icsk_ack.quick = 0;
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
if (tcp_memory_pressure)
tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U*tp->advmss);
if (free_space < mss)
return 0;
}
if (free_space > tp->rcv_ssthresh)
free_space = tp->rcv_ssthresh;
/* Don't do rounding if we are using window scaling, since the
* scaled window will not line up with the MSS boundary anyway.
*/
window = tp->rcv_wnd;
if (tp->rx_opt.rcv_wscale) {
window = free_space;
/* Advertise enough space so that it won't get scaled away.
* Import case: prevent zero window announcement if
* 1<<rcv_wscale > mss.
*/
if (((window >> tp->rx_opt.rcv_wscale) << tp->rx_opt.rcv_wscale) != window)
window = (((window >> tp->rx_opt.rcv_wscale) + 1)
<< tp->rx_opt.rcv_wscale);
} else {
/* Get the largest window that is a nice multiple of mss.
* Window clamp already applied above.
* If our current window offering is within 1 mss of the
* free space we just keep it. This prevents the divide
* and multiply from happening most of the time.
* We also don't do any window rounding when the free space
* is too small.
*/
if (window <= free_space - mss || window > free_space)
window = (free_space/mss)*mss;
}
return window;
}
/* Attempt to collapse two adjacent SKB's during retransmission. */
static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb, int mss_now)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *next_skb = skb->next;
/* The first test we must make is that neither of these two
* SKB's are still referenced by someone else.
*/
if (!skb_cloned(skb) && !skb_cloned(next_skb)) {
int skb_size = skb->len, next_skb_size = next_skb->len;
u16 flags = TCP_SKB_CB(skb)->flags;
/* Also punt if next skb has been SACK'd. */
if(TCP_SKB_CB(next_skb)->sacked & TCPCB_SACKED_ACKED)
return;
/* Next skb is out of window. */
if (after(TCP_SKB_CB(next_skb)->end_seq, tp->snd_una+tp->snd_wnd))
return;
/* Punt if not enough space exists in the first SKB for
* the data in the second, or the total combined payload
* would exceed the MSS.
*/
if ((next_skb_size > skb_tailroom(skb)) ||
((skb_size + next_skb_size) > mss_now))
return;
BUG_ON(tcp_skb_pcount(skb) != 1 ||
tcp_skb_pcount(next_skb) != 1);
/* changing transmit queue under us so clear hints */
clear_all_retrans_hints(tp);
/* Ok. We will be able to collapse the packet. */
memcpy(skb_put(skb, next_skb_size), next_skb->data, next_skb_size);
if (next_skb->ip_summed == CHECKSUM_PARTIAL)
skb->ip_summed = CHECKSUM_PARTIAL;
if (skb->ip_summed != CHECKSUM_PARTIAL)
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
skb->csum = csum_block_add(skb->csum, next_skb->csum, skb_size);
/* Update sequence range on original skb. */
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq;
/* Merge over control information. */
flags |= TCP_SKB_CB(next_skb)->flags; /* This moves PSH/FIN etc. over */
TCP_SKB_CB(skb)->flags = flags;
/* All done, get rid of second SKB and account for it so
* packet counting does not break.
*/
TCP_SKB_CB(skb)->sacked |= TCP_SKB_CB(next_skb)->sacked&(TCPCB_EVER_RETRANS|TCPCB_AT_TAIL);
if (TCP_SKB_CB(next_skb)->sacked&TCPCB_SACKED_RETRANS)
tp->retrans_out -= tcp_skb_pcount(next_skb);
if (TCP_SKB_CB(next_skb)->sacked&TCPCB_LOST) {
tp->lost_out -= tcp_skb_pcount(next_skb);
tp->left_out -= tcp_skb_pcount(next_skb);
}
/* Reno case is special. Sigh... */
if (!tp->rx_opt.sack_ok && tp->sacked_out) {
tcp_dec_pcount_approx(&tp->sacked_out, next_skb);
tp->left_out -= tcp_skb_pcount(next_skb);
}
/* Not quite right: it can be > snd.fack, but
* it is better to underestimate fackets.
*/
tcp_dec_pcount_approx(&tp->fackets_out, next_skb);
tcp_packets_out_dec(tp, next_skb);
sk_stream_free_skb(sk, next_skb);
}
}
/* 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)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
unsigned int mss = tcp_current_mss(sk, 0);
int lost = 0;
sk_stream_for_retrans_queue(skb, sk) {
if (skb->len > mss &&
!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED)) {
if (TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_RETRANS) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
tp->retrans_out -= tcp_skb_pcount(skb);
}
if (!(TCP_SKB_CB(skb)->sacked&TCPCB_LOST)) {
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
lost = 1;
}
}
}
if (!lost)
return;
tcp_sync_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.
*/
if (icsk->icsk_ca_state != TCP_CA_Loss) {
tp->snd_ssthresh = tcp_current_ssthresh(sk);
tcp_set_ca_state(sk, TCP_CA_Loss);
}
tcp_xmit_retransmit_queue(sk);
}
/* This retransmits one SKB. Policy decisions and retransmit queue
* state updates are done by the caller. Returns non-zero if an
* error occurred which prevented the send.
*/
int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
unsigned int cur_mss = tcp_current_mss(sk, 0);
int err;
/* Inconslusive MTU probe */
if (icsk->icsk_mtup.probe_size) {
icsk->icsk_mtup.probe_size = 0;
}
/* Do not sent more than we queued. 1/4 is reserved for possible
* copying overhead: fragmentation, tunneling, mangling etc.
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
*/
if (atomic_read(&sk->sk_wmem_alloc) >
min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf))
return -EAGAIN;
if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
BUG();
if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq))
return -ENOMEM;
}
/* If receiver has shrunk his window, and skb is out of
* new window, do not retransmit it. The exception is the
* case, when window is shrunk to zero. In this case
* our retransmit serves as a zero window probe.
*/
if (!before(TCP_SKB_CB(skb)->seq, tp->snd_una+tp->snd_wnd)
&& TCP_SKB_CB(skb)->seq != tp->snd_una)
return -EAGAIN;
if (skb->len > cur_mss) {
if (tcp_fragment(sk, skb, cur_mss, cur_mss))
return -ENOMEM; /* We'll try again later. */
}
/* Collapse two adjacent packets if worthwhile and we can. */
if(!(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_SYN) &&
(skb->len < (cur_mss >> 1)) &&
(skb->next != sk->sk_send_head) &&
(skb->next != (struct sk_buff *)&sk->sk_write_queue) &&
(skb_shinfo(skb)->nr_frags == 0 && skb_shinfo(skb->next)->nr_frags == 0) &&
(tcp_skb_pcount(skb) == 1 && tcp_skb_pcount(skb->next) == 1) &&
(sysctl_tcp_retrans_collapse != 0))
tcp_retrans_try_collapse(sk, skb, cur_mss);
Arnaldo Carvalho de Melo
committed
if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
return -EHOSTUNREACH; /* Routing failure or similar. */
/* Some Solaris stacks overoptimize and ignore the FIN on a
* retransmit when old data is attached. So strip it off
* since it is cheap to do so and saves bytes on the network.
*/
if(skb->len > 0 &&
(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) &&
tp->snd_una == (TCP_SKB_CB(skb)->end_seq - 1)) {
if (!pskb_trim(skb, 0)) {
TCP_SKB_CB(skb)->seq = TCP_SKB_CB(skb)->end_seq - 1;
skb_shinfo(skb)->gso_segs = 1;
skb_shinfo(skb)->gso_size = 0;
skb_shinfo(skb)->gso_type = 0;
skb->ip_summed = CHECKSUM_NONE;
skb->csum = 0;
}
}
/* Make a copy, if the first transmission SKB clone we made
* is still in somebody's hands, else make a clone.
*/
TCP_SKB_CB(skb)->when = tcp_time_stamp;
err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
if (err == 0) {
/* Update global TCP statistics. */
TCP_INC_STATS(TCP_MIB_RETRANSSEGS);
tp->total_retrans++;
#if FASTRETRANS_DEBUG > 0
if (TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_RETRANS) {
if (net_ratelimit())
printk(KERN_DEBUG "retrans_out leaked.\n");
}
#endif
TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS;
tp->retrans_out += tcp_skb_pcount(skb);
/* Save stamp of the first retransmit. */
if (!tp->retrans_stamp)
tp->retrans_stamp = TCP_SKB_CB(skb)->when;
tp->undo_retrans++;
/* snd_nxt is stored to detect loss of retransmitted segment,
* see tcp_input.c tcp_sacktag_write_queue().
*/
TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt;
}
return err;
}
/* This gets called after a retransmit timeout, and the initially
* retransmitted data is acknowledged. It tries to continue
* resending the rest of the retransmit queue, until either
* we've sent it all or the congestion window limit is reached.
* If doing SACK, the first ACK which comes back for a timeout
* based retransmit packet might feed us FACK information again.
* If so, we use it to avoid unnecessarily retransmissions.
*/
void tcp_xmit_retransmit_queue(struct sock *sk)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
int packet_cnt;
if (tp->retransmit_skb_hint) {
skb = tp->retransmit_skb_hint;
packet_cnt = tp->retransmit_cnt_hint;
}else{
skb = sk->sk_write_queue.next;
packet_cnt = 0;
}
if (tp->lost_out) {
sk_stream_for_retrans_queue_from(skb, sk) {
/* we could do better than to assign each time */
tp->retransmit_skb_hint = skb;
tp->retransmit_cnt_hint = packet_cnt;
/* Assume this retransmit will generate
* only one packet for congestion window
* calculation purposes. This works because
* tcp_retransmit_skb() will chop up the
* packet to be MSS sized and all the
* packet counting works out.
*/
if (tcp_packets_in_flight(tp) >= tp->snd_cwnd)
return;
if (!(sacked&(TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS))) {
if (tcp_retransmit_skb(sk, skb)) {
tp->retransmit_skb_hint = NULL;
if (icsk->icsk_ca_state != TCP_CA_Loss)
NET_INC_STATS_BH(LINUX_MIB_TCPFASTRETRANS);
else
NET_INC_STATS_BH(LINUX_MIB_TCPSLOWSTARTRETRANS);
if (skb ==
skb_peek(&sk->sk_write_queue))
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
Arnaldo Carvalho de Melo
committed
inet_csk(sk)->icsk_rto,
TCP_RTO_MAX);
packet_cnt += tcp_skb_pcount(skb);
if (packet_cnt >= tp->lost_out)
break;
}
}
}
/* OK, demanded retransmission is finished. */
/* Forward retransmissions are possible only during Recovery. */
if (icsk->icsk_ca_state != TCP_CA_Recovery)
return;
/* No forward retransmissions in Reno are possible. */
if (!tp->rx_opt.sack_ok)
return;
/* Yeah, we have to make difficult choice between forward transmission
* and retransmission... Both ways have their merits...
*
* For now we do not retransmit anything, while we have some new
* segments to send.
*/
if (tcp_may_send_now(sk, tp))
return;
if (tp->forward_skb_hint) {
skb = tp->forward_skb_hint;
packet_cnt = tp->forward_cnt_hint;
} else{
skb = sk->sk_write_queue.next;
packet_cnt = 0;
}
sk_stream_for_retrans_queue_from(skb, sk) {
tp->forward_cnt_hint = packet_cnt;
tp->forward_skb_hint = skb;
/* Similar to the retransmit loop above we
* can pretend that the retransmitted SKB
* we send out here will be composed of one
* real MSS sized packet because tcp_retransmit_skb()
* will fragment it if necessary.
*/
if (++packet_cnt > tp->fackets_out)
break;
if (tcp_packets_in_flight(tp) >= tp->snd_cwnd)
break;
if (TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS)
continue;
/* Ok, retransmit it. */
if (tcp_retransmit_skb(sk, skb)) {
tp->forward_skb_hint = NULL;
Arnaldo Carvalho de Melo
committed
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
inet_csk(sk)->icsk_rto,
TCP_RTO_MAX);
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
NET_INC_STATS_BH(LINUX_MIB_TCPFORWARDRETRANS);
}
}
/* Send a fin. The caller locks the socket for us. This cannot be
* allowed to fail queueing a FIN frame under any circumstances.
*/
void tcp_send_fin(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb = skb_peek_tail(&sk->sk_write_queue);
int mss_now;
/* Optimization, tack on the FIN if we have a queue of
* unsent frames. But be careful about outgoing SACKS
* and IP options.
*/
mss_now = tcp_current_mss(sk, 1);
if (sk->sk_send_head != NULL) {
TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_FIN;
TCP_SKB_CB(skb)->end_seq++;
tp->write_seq++;
} else {
/* Socket is locked, keep trying until memory is available. */
for (;;) {
skb = alloc_skb_fclone(MAX_TCP_HEADER, GFP_KERNEL);
if (skb)
break;
yield();
}
/* Reserve space for headers and prepare control bits. */
skb_reserve(skb, MAX_TCP_HEADER);
skb->csum = 0;
TCP_SKB_CB(skb)->flags = (TCPCB_FLAG_ACK | TCPCB_FLAG_FIN);
TCP_SKB_CB(skb)->sacked = 0;
skb_shinfo(skb)->gso_segs = 1;
skb_shinfo(skb)->gso_size = 0;
skb_shinfo(skb)->gso_type = 0;
/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
TCP_SKB_CB(skb)->seq = tp->write_seq;
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + 1;
tcp_queue_skb(sk, skb);
}
__tcp_push_pending_frames(sk, tp, mss_now, TCP_NAGLE_OFF);
}
/* We get here when a process closes a file descriptor (either due to
* an explicit close() or as a byproduct of exit()'ing) and there
* was unread data in the receive queue. This behavior is recommended
* by draft-ietf-tcpimpl-prob-03.txt section 3.10. -DaveM
*/
void tcp_send_active_reset(struct sock *sk, gfp_t priority)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
/* NOTE: No TCP options attached and we never retransmit this. */
skb = alloc_skb(MAX_TCP_HEADER, priority);
if (!skb) {
NET_INC_STATS(LINUX_MIB_TCPABORTFAILED);
return;
}
/* Reserve space for headers and prepare control bits. */
skb_reserve(skb, MAX_TCP_HEADER);
skb->csum = 0;
TCP_SKB_CB(skb)->flags = (TCPCB_FLAG_ACK | TCPCB_FLAG_RST);
TCP_SKB_CB(skb)->sacked = 0;
skb_shinfo(skb)->gso_segs = 1;
skb_shinfo(skb)->gso_size = 0;
skb_shinfo(skb)->gso_type = 0;
/* Send it off. */
TCP_SKB_CB(skb)->seq = tcp_acceptable_seq(sk, tp);
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq;
TCP_SKB_CB(skb)->when = tcp_time_stamp;
if (tcp_transmit_skb(sk, skb, 0, priority))
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
NET_INC_STATS(LINUX_MIB_TCPABORTFAILED);
}
/* WARNING: This routine must only be called when we have already sent
* a SYN packet that crossed the incoming SYN that caused this routine
* to get called. If this assumption fails then the initial rcv_wnd
* and rcv_wscale values will not be correct.
*/
int tcp_send_synack(struct sock *sk)
{
struct sk_buff* skb;
skb = skb_peek(&sk->sk_write_queue);
if (skb == NULL || !(TCP_SKB_CB(skb)->flags&TCPCB_FLAG_SYN)) {
printk(KERN_DEBUG "tcp_send_synack: wrong queue state\n");
return -EFAULT;
}
if (!(TCP_SKB_CB(skb)->flags&TCPCB_FLAG_ACK)) {
if (skb_cloned(skb)) {
struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC);
if (nskb == NULL)
return -ENOMEM;
__skb_unlink(skb, &sk->sk_write_queue);
skb_header_release(nskb);
__skb_queue_head(&sk->sk_write_queue, nskb);
sk_stream_free_skb(sk, skb);
sk_charge_skb(sk, nskb);
skb = nskb;
}
TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_ACK;
TCP_ECN_send_synack(tcp_sk(sk), skb);
}
TCP_SKB_CB(skb)->when = tcp_time_stamp;
return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
}
/*
* Prepare a SYN-ACK.
*/
struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst,
struct request_sock *req)
Arnaldo Carvalho de Melo
committed
struct inet_request_sock *ireq = inet_rsk(req);
struct tcp_sock *tp = tcp_sk(sk);
struct tcphdr *th;
int tcp_header_size;
struct sk_buff *skb;
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *md5;
__u8 *md5_hash_location;
#endif
skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC);
if (skb == NULL)
return NULL;
/* Reserve space for headers. */
skb_reserve(skb, MAX_TCP_HEADER);
skb->dst = dst_clone(dst);
tcp_header_size = (sizeof(struct tcphdr) + TCPOLEN_MSS +
Arnaldo Carvalho de Melo
committed
(ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0) +
(ireq->wscale_ok ? TCPOLEN_WSCALE_ALIGNED : 0) +
Arnaldo Carvalho de Melo
committed
((ireq->sack_ok && !ireq->tstamp_ok) ? TCPOLEN_SACKPERM_ALIGNED : 0));
#ifdef CONFIG_TCP_MD5SIG
/* Are we doing MD5 on this segment? If so - make room for it */
md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req);
if (md5)
tcp_header_size += TCPOLEN_MD5SIG_ALIGNED;
#endif
skb->h.th = th = (struct tcphdr *) skb_push(skb, tcp_header_size);
memset(th, 0, sizeof(struct tcphdr));
th->syn = 1;
th->ack = 1;
TCP_ECN_make_synack(req, th);
th->source = inet_sk(sk)->sport;
Arnaldo Carvalho de Melo
committed
th->dest = ireq->rmt_port;
TCP_SKB_CB(skb)->seq = tcp_rsk(req)->snt_isn;
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + 1;
TCP_SKB_CB(skb)->sacked = 0;
skb_shinfo(skb)->gso_segs = 1;
skb_shinfo(skb)->gso_size = 0;
skb_shinfo(skb)->gso_type = 0;
Arnaldo Carvalho de Melo
committed
th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1);
if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */
__u8 rcv_wscale;
/* Set this up on the first call only */
req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW);
/* tcp_full_space because it is guaranteed to be the first packet */
tcp_select_initial_window(tcp_full_space(sk),
Arnaldo Carvalho de Melo
committed
dst_metric(dst, RTAX_ADVMSS) - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
Arnaldo Carvalho de Melo
committed
ireq->wscale_ok,
Arnaldo Carvalho de Melo
committed
ireq->rcv_wscale = rcv_wscale;
}
/* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
th->window = htons(req->rcv_wnd);
TCP_SKB_CB(skb)->when = tcp_time_stamp;
tcp_syn_build_options((__be32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), ireq->tstamp_ok,
Arnaldo Carvalho de Melo
committed
ireq->sack_ok, ireq->wscale_ok, ireq->rcv_wscale,
req->ts_recent,
(
#ifdef CONFIG_TCP_MD5SIG
md5 ? &md5_hash_location :
#endif
NULL)
);
skb->csum = 0;
th->doff = (tcp_header_size >> 2);
TCP_INC_STATS(TCP_MIB_OUTSEGS);
#ifdef CONFIG_TCP_MD5SIG
/* Okay, we have all we need - do the md5 hash if needed */
if (md5) {
tp->af_specific->calc_md5_hash(md5_hash_location,
md5,
NULL, dst, req,
skb->h.th, sk->sk_protocol,
skb->len);
}
#endif
return skb;
}
/*
* Do all connect socket setups that can be done AF independent.
*/
Loading
Loading full blame...