2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
|
* 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.
|
|
|
|
|
*
|
|
|
|
|
* Definitions for the TCP module.
|
|
|
|
|
*
|
|
|
|
|
* Version: @(#)tcp.h 1.0.5 05/23/93
|
|
|
|
|
*
|
2005-05-06 07:16:16 +08:00
|
|
|
* Authors: Ross Biro
|
2005-04-17 06:20:36 +08:00
|
|
|
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
|
|
|
|
|
*
|
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
|
* modify it under the terms of the GNU General Public License
|
|
|
|
|
* as published by the Free Software Foundation; either version
|
|
|
|
|
* 2 of the License, or (at your option) any later version.
|
|
|
|
|
*/
|
|
|
|
|
#ifndef _TCP_H
|
|
|
|
|
#define _TCP_H
|
|
|
|
|
|
|
|
|
|
#define TCP_DEBUG 1
|
|
|
|
|
#define FASTRETRANS_DEBUG 1
|
|
|
|
|
|
|
|
|
|
#include <linux/list.h>
|
|
|
|
|
#include <linux/tcp.h>
|
|
|
|
|
#include <linux/slab.h>
|
|
|
|
|
#include <linux/cache.h>
|
|
|
|
|
#include <linux/percpu.h>
|
2005-11-11 05:01:24 +08:00
|
|
|
#include <linux/skbuff.h>
|
2006-05-24 08:55:33 +08:00
|
|
|
#include <linux/dmaengine.h>
|
2006-11-15 11:07:45 +08:00
|
|
|
#include <linux/crypto.h>
|
2008-02-08 13:49:26 +08:00
|
|
|
#include <linux/cryptohash.h>
|
2005-08-10 11:11:08 +08:00
|
|
|
|
|
|
|
|
#include <net/inet_connection_sock.h>
|
2005-08-10 11:44:40 +08:00
|
|
|
#include <net/inet_timewait_sock.h>
|
2005-08-10 11:00:51 +08:00
|
|
|
#include <net/inet_hashtables.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <net/checksum.h>
|
[NET] Generalise TCP's struct open_request minisock infrastructure
Kept this first changeset minimal, without changing existing names to
ease peer review.
Basicaly tcp_openreq_alloc now receives the or_calltable, that in turn
has two new members:
->slab, that replaces tcp_openreq_cachep
->obj_size, to inform the size of the openreq descendant for
a specific protocol
The protocol specific fields in struct open_request were moved to a
class hierarchy, with the things that are common to all connection
oriented PF_INET protocols in struct inet_request_sock, the TCP ones
in tcp_request_sock, that is an inet_request_sock, that is an
open_request.
I.e. this uses the same approach used for the struct sock class
hierarchy, with sk_prot indicating if the protocol wants to use the
open_request infrastructure by filling in sk_prot->rsk_prot with an
or_calltable.
Results? Performance is improved and TCP v4 now uses only 64 bytes per
open request minisock, down from 96 without this patch :-)
Next changeset will rename some of the structs, fields and functions
mentioned above, struct or_calltable is way unclear, better name it
struct request_sock_ops, s/struct open_request/struct request_sock/g,
etc.
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-19 13:46:52 +08:00
|
|
|
#include <net/request_sock.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <net/sock.h>
|
|
|
|
|
#include <net/snmp.h>
|
|
|
|
|
#include <net/ip.h>
|
2005-08-10 11:08:28 +08:00
|
|
|
#include <net/tcp_states.h>
|
2007-05-27 17:04:16 +08:00
|
|
|
#include <net/inet_ecn.h>
|
2005-08-10 11:08:28 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/seq_file.h>
|
|
|
|
|
|
2005-08-10 11:07:35 +08:00
|
|
|
extern struct inet_hashinfo tcp_hashinfo;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-11-26 13:17:14 +08:00
|
|
|
extern struct percpu_counter tcp_orphan_count;
|
2005-04-17 06:20:36 +08:00
|
|
|
extern void tcp_time_wait(struct sock *sk, int state, int timeo);
|
|
|
|
|
|
|
|
|
|
#define MAX_TCP_HEADER (128 + MAX_HEADER)
|
2008-07-19 15:04:31 +08:00
|
|
|
#define MAX_TCP_OPTION_SPACE 40
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Never offer a window over 32767 without using window scaling. Some
|
|
|
|
|
* poor stacks do signed 16bit maths!
|
|
|
|
|
*/
|
|
|
|
|
#define MAX_TCP_WINDOW 32767U
|
|
|
|
|
|
|
|
|
|
/* Minimal accepted MSS. It is (60+60+8) - (20+20). */
|
|
|
|
|
#define TCP_MIN_MSS 88U
|
|
|
|
|
|
|
|
|
|
/* Minimal RCV_MSS. */
|
|
|
|
|
#define TCP_MIN_RCVMSS 536U
|
|
|
|
|
|
2006-03-21 09:53:41 +08:00
|
|
|
/* The least MTU to use for probing */
|
|
|
|
|
#define TCP_BASE_MSS 512
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* After receiving this amount of duplicate ACKs fast retransmit starts. */
|
|
|
|
|
#define TCP_FASTRETRANS_THRESH 3
|
|
|
|
|
|
|
|
|
|
/* Maximal reordering. */
|
|
|
|
|
#define TCP_MAX_REORDERING 127
|
|
|
|
|
|
|
|
|
|
/* Maximal number of ACKs sent quickly to accelerate slow-start. */
|
|
|
|
|
#define TCP_MAX_QUICKACKS 16U
|
|
|
|
|
|
|
|
|
|
/* urg_data states */
|
|
|
|
|
#define TCP_URG_VALID 0x0100
|
|
|
|
|
#define TCP_URG_NOTYET 0x0200
|
|
|
|
|
#define TCP_URG_READ 0x0400
|
|
|
|
|
|
|
|
|
|
#define TCP_RETR1 3 /*
|
|
|
|
|
* This is how many retries it does before it
|
|
|
|
|
* tries to figure out if the gateway is
|
|
|
|
|
* down. Minimal RFC value is 3; it corresponds
|
|
|
|
|
* to ~3sec-8min depending on RTO.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#define TCP_RETR2 15 /*
|
|
|
|
|
* This should take at least
|
|
|
|
|
* 90 minutes to time out.
|
|
|
|
|
* RFC1122 says that the limit is 100 sec.
|
|
|
|
|
* 15 is ~13-30min depending on RTO.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#define TCP_SYN_RETRIES 5 /* number of times to retry active opening a
|
2005-11-11 09:13:47 +08:00
|
|
|
* connection: ~180sec is RFC minimum */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
#define TCP_SYNACK_RETRIES 5 /* number of times to retry passive opening a
|
2005-11-11 09:13:47 +08:00
|
|
|
* connection: ~180sec is RFC minimum */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
#define TCP_ORPHAN_RETRIES 7 /* number of times to retry on an orphaned
|
|
|
|
|
* socket. 7 is ~50sec-16min.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#define TCP_TIMEWAIT_LEN (60*HZ) /* how long to wait to destroy TIME-WAIT
|
|
|
|
|
* state, about 60 seconds */
|
|
|
|
|
#define TCP_FIN_TIMEOUT TCP_TIMEWAIT_LEN
|
|
|
|
|
/* BSD style FIN_WAIT2 deadlock breaker.
|
|
|
|
|
* It used to be 3min, new value is 60sec,
|
|
|
|
|
* to combine FIN-WAIT-2 timeout with
|
|
|
|
|
* TIME-WAIT timer.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#define TCP_DELACK_MAX ((unsigned)(HZ/5)) /* maximal time to delay before sending an ACK */
|
|
|
|
|
#if HZ >= 100
|
|
|
|
|
#define TCP_DELACK_MIN ((unsigned)(HZ/25)) /* minimal time to delay before sending an ACK */
|
|
|
|
|
#define TCP_ATO_MIN ((unsigned)(HZ/25))
|
|
|
|
|
#else
|
|
|
|
|
#define TCP_DELACK_MIN 4U
|
|
|
|
|
#define TCP_ATO_MIN 4U
|
|
|
|
|
#endif
|
|
|
|
|
#define TCP_RTO_MAX ((unsigned)(120*HZ))
|
|
|
|
|
#define TCP_RTO_MIN ((unsigned)(HZ/5))
|
|
|
|
|
#define TCP_TIMEOUT_INIT ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value */
|
|
|
|
|
|
|
|
|
|
#define TCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ/2U)) /* Maximal interval between probes
|
|
|
|
|
* for local resources.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#define TCP_KEEPALIVE_TIME (120*60*HZ) /* two hours */
|
|
|
|
|
#define TCP_KEEPALIVE_PROBES 9 /* Max of 9 keepalive probes */
|
|
|
|
|
#define TCP_KEEPALIVE_INTVL (75*HZ)
|
|
|
|
|
|
|
|
|
|
#define MAX_TCP_KEEPIDLE 32767
|
|
|
|
|
#define MAX_TCP_KEEPINTVL 32767
|
|
|
|
|
#define MAX_TCP_KEEPCNT 127
|
|
|
|
|
#define MAX_TCP_SYNCNT 127
|
|
|
|
|
|
|
|
|
|
#define TCP_SYNQ_INTERVAL (HZ/5) /* Period of SYNACK timer */
|
|
|
|
|
|
|
|
|
|
#define TCP_PAWS_24DAYS (60 * 60 * 24 * 24)
|
|
|
|
|
#define TCP_PAWS_MSL 60 /* Per-host timestamps are invalidated
|
|
|
|
|
* after this time. It should be equal
|
|
|
|
|
* (or greater than) TCP_TIMEWAIT_LEN
|
|
|
|
|
* to provide reliability equal to one
|
|
|
|
|
* provided by timewait state.
|
|
|
|
|
*/
|
|
|
|
|
#define TCP_PAWS_WINDOW 1 /* Replay window for per-host
|
|
|
|
|
* timestamps. It must be less than
|
|
|
|
|
* minimal timewait lifetime.
|
|
|
|
|
*/
|
|
|
|
|
/*
|
|
|
|
|
* TCP option
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#define TCPOPT_NOP 1 /* Padding */
|
|
|
|
|
#define TCPOPT_EOL 0 /* End of options */
|
|
|
|
|
#define TCPOPT_MSS 2 /* Segment size negotiating */
|
|
|
|
|
#define TCPOPT_WINDOW 3 /* Window scaling */
|
|
|
|
|
#define TCPOPT_SACK_PERM 4 /* SACK Permitted */
|
|
|
|
|
#define TCPOPT_SACK 5 /* SACK Block */
|
|
|
|
|
#define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */
|
2006-11-15 11:07:45 +08:00
|
|
|
#define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* TCP option lengths
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#define TCPOLEN_MSS 4
|
|
|
|
|
#define TCPOLEN_WINDOW 3
|
|
|
|
|
#define TCPOLEN_SACK_PERM 2
|
|
|
|
|
#define TCPOLEN_TIMESTAMP 10
|
2006-11-15 11:07:45 +08:00
|
|
|
#define TCPOLEN_MD5SIG 18
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
/* But this is what stacks really send out. */
|
|
|
|
|
#define TCPOLEN_TSTAMP_ALIGNED 12
|
|
|
|
|
#define TCPOLEN_WSCALE_ALIGNED 4
|
|
|
|
|
#define TCPOLEN_SACKPERM_ALIGNED 4
|
|
|
|
|
#define TCPOLEN_SACK_BASE 2
|
|
|
|
|
#define TCPOLEN_SACK_BASE_ALIGNED 4
|
|
|
|
|
#define TCPOLEN_SACK_PERBLOCK 8
|
2006-11-15 11:07:45 +08:00
|
|
|
#define TCPOLEN_MD5SIG_ALIGNED 20
|
2008-07-19 15:04:31 +08:00
|
|
|
#define TCPOLEN_MSS_ALIGNED 4
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
/* Flags in tp->nonagle */
|
|
|
|
|
#define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */
|
|
|
|
|
#define TCP_NAGLE_CORK 2 /* Socket is corked */
|
2005-11-11 09:13:47 +08:00
|
|
|
#define TCP_NAGLE_PUSH 4 /* Cork is overridden for already queued data */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-08-10 11:44:40 +08:00
|
|
|
extern struct inet_timewait_death_row tcp_death_row;
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* sysctl variables for tcp */
|
|
|
|
|
extern int sysctl_tcp_timestamps;
|
|
|
|
|
extern int sysctl_tcp_window_scaling;
|
|
|
|
|
extern int sysctl_tcp_sack;
|
|
|
|
|
extern int sysctl_tcp_fin_timeout;
|
|
|
|
|
extern int sysctl_tcp_keepalive_time;
|
|
|
|
|
extern int sysctl_tcp_keepalive_probes;
|
|
|
|
|
extern int sysctl_tcp_keepalive_intvl;
|
|
|
|
|
extern int sysctl_tcp_syn_retries;
|
|
|
|
|
extern int sysctl_tcp_synack_retries;
|
|
|
|
|
extern int sysctl_tcp_retries1;
|
|
|
|
|
extern int sysctl_tcp_retries2;
|
|
|
|
|
extern int sysctl_tcp_orphan_retries;
|
|
|
|
|
extern int sysctl_tcp_syncookies;
|
|
|
|
|
extern int sysctl_tcp_retrans_collapse;
|
|
|
|
|
extern int sysctl_tcp_stdurg;
|
|
|
|
|
extern int sysctl_tcp_rfc1337;
|
|
|
|
|
extern int sysctl_tcp_abort_on_overflow;
|
|
|
|
|
extern int sysctl_tcp_max_orphans;
|
|
|
|
|
extern int sysctl_tcp_fack;
|
|
|
|
|
extern int sysctl_tcp_reordering;
|
|
|
|
|
extern int sysctl_tcp_ecn;
|
|
|
|
|
extern int sysctl_tcp_dsack;
|
|
|
|
|
extern int sysctl_tcp_mem[3];
|
|
|
|
|
extern int sysctl_tcp_wmem[3];
|
|
|
|
|
extern int sysctl_tcp_rmem[3];
|
|
|
|
|
extern int sysctl_tcp_app_win;
|
|
|
|
|
extern int sysctl_tcp_adv_win_scale;
|
|
|
|
|
extern int sysctl_tcp_tw_reuse;
|
|
|
|
|
extern int sysctl_tcp_frto;
|
2007-02-28 02:09:49 +08:00
|
|
|
extern int sysctl_tcp_frto_response;
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int sysctl_tcp_low_latency;
|
2006-05-24 09:02:55 +08:00
|
|
|
extern int sysctl_tcp_dma_copybreak;
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int sysctl_tcp_nometrics_save;
|
|
|
|
|
extern int sysctl_tcp_moderate_rcvbuf;
|
|
|
|
|
extern int sysctl_tcp_tso_win_divisor;
|
2005-11-11 09:09:53 +08:00
|
|
|
extern int sysctl_tcp_abc;
|
2006-03-21 09:53:41 +08:00
|
|
|
extern int sysctl_tcp_mtu_probing;
|
|
|
|
|
extern int sysctl_tcp_base_mss;
|
2006-03-21 14:40:29 +08:00
|
|
|
extern int sysctl_tcp_workaround_signed_windows;
|
2006-06-14 13:33:04 +08:00
|
|
|
extern int sysctl_tcp_slow_start_after_idle;
|
2007-03-26 10:21:45 +08:00
|
|
|
extern int sysctl_tcp_max_ssthresh;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
extern atomic_t tcp_memory_allocated;
|
2008-11-26 13:16:35 +08:00
|
|
|
extern struct percpu_counter tcp_sockets_allocated;
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int tcp_memory_pressure;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* The next routines deal with comparing 32 bit unsigned ints
|
|
|
|
|
* and worry about wraparound (automatic with unsigned arithmetic).
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
static inline int before(__u32 seq1, __u32 seq2)
|
|
|
|
|
{
|
2007-01-05 04:25:16 +08:00
|
|
|
return (__s32)(seq1-seq2) < 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
[TCP]: Fix ambiguity in the `before' relation.
While looking at DCCP sequence numbers, I stumbled over a problem with
the following definition of before in tcp.h:
static inline int before(__u32 seq1, __u32 seq2)
{
return (__s32)(seq1-seq2) < 0;
}
Problem: This definition suffers from an an ambiguity, i.e. always
before(a, (a + 2^31) % 2^32)) = 1
before((a + 2^31) % 2^32), a) = 1
In text: when the difference between a and b amounts to 2^31,
a is always considered `before' b, the function can not decide.
The reason is that implicitly 0 is `before' 1 ... 2^31-1 ... 2^31
Solution: There is a simple fix, by defining before in such a way that
0 is no longer `before' 2^31, i.e. 0 `before' 1 ... 2^31-1
By not using the middle between 0 and 2^32, before can be made
unambiguous.
This is achieved by testing whether seq2-seq1 > 0 (using signed
32-bit arithmetic).
I attach a patch to codify this. Also the `after' relation is basically
a redefinition of `before', it is now defined as a macro after before.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-12-21 02:25:55 +08:00
|
|
|
#define after(seq2, seq1) before(seq1, seq2)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
/* is s2<=s1<=s3 ? */
|
|
|
|
|
static inline int between(__u32 seq1, __u32 seq2, __u32 seq3)
|
|
|
|
|
{
|
|
|
|
|
return seq3 - seq2 >= seq1 - seq2;
|
|
|
|
|
}
|
|
|
|
|
|
2007-05-30 04:19:18 +08:00
|
|
|
static inline int tcp_too_many_orphans(struct sock *sk, int num)
|
|
|
|
|
{
|
|
|
|
|
return (num > sysctl_tcp_max_orphans) ||
|
|
|
|
|
(sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
|
|
|
|
|
atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2]);
|
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
extern struct proto tcp_prot;
|
|
|
|
|
|
2008-07-18 19:02:08 +08:00
|
|
|
#define TCP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.tcp_statistics, field)
|
|
|
|
|
#define TCP_INC_STATS_BH(net, field) SNMP_INC_STATS_BH((net)->mib.tcp_statistics, field)
|
|
|
|
|
#define TCP_DEC_STATS(net, field) SNMP_DEC_STATS((net)->mib.tcp_statistics, field)
|
|
|
|
|
#define TCP_ADD_STATS_USER(net, field, val) SNMP_ADD_STATS_USER((net)->mib.tcp_statistics, field, val)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
extern void tcp_v4_err(struct sk_buff *skb, u32);
|
|
|
|
|
|
|
|
|
|
extern void tcp_shutdown (struct sock *sk, int how);
|
|
|
|
|
|
|
|
|
|
extern int tcp_v4_rcv(struct sk_buff *skb);
|
|
|
|
|
|
|
|
|
|
extern int tcp_v4_remember_stamp(struct sock *sk);
|
|
|
|
|
|
2005-08-10 11:09:30 +08:00
|
|
|
extern int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-08-03 10:23:56 +08:00
|
|
|
extern int tcp_sendmsg(struct kiocb *iocb, struct socket *sock,
|
2005-04-17 06:20:36 +08:00
|
|
|
struct msghdr *msg, size_t size);
|
|
|
|
|
extern ssize_t tcp_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags);
|
|
|
|
|
|
|
|
|
|
extern int tcp_ioctl(struct sock *sk,
|
|
|
|
|
int cmd,
|
|
|
|
|
unsigned long arg);
|
|
|
|
|
|
|
|
|
|
extern int tcp_rcv_state_process(struct sock *sk,
|
|
|
|
|
struct sk_buff *skb,
|
|
|
|
|
struct tcphdr *th,
|
|
|
|
|
unsigned len);
|
|
|
|
|
|
|
|
|
|
extern int tcp_rcv_established(struct sock *sk,
|
|
|
|
|
struct sk_buff *skb,
|
|
|
|
|
struct tcphdr *th,
|
|
|
|
|
unsigned len);
|
|
|
|
|
|
|
|
|
|
extern void tcp_rcv_space_adjust(struct sock *sk);
|
|
|
|
|
|
2006-05-24 09:00:16 +08:00
|
|
|
extern void tcp_cleanup_rbuf(struct sock *sk, int copied);
|
|
|
|
|
|
2005-12-14 15:25:19 +08:00
|
|
|
extern int tcp_twsk_unique(struct sock *sk,
|
|
|
|
|
struct sock *sktw, void *twp);
|
|
|
|
|
|
2006-11-15 11:07:45 +08:00
|
|
|
extern void tcp_twsk_destructor(struct sock *sk);
|
|
|
|
|
|
2007-11-07 15:30:13 +08:00
|
|
|
extern ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
|
|
|
|
|
struct pipe_inode_info *pipe, size_t len, unsigned int flags);
|
|
|
|
|
|
2005-08-10 11:10:42 +08:00
|
|
|
static inline void tcp_dec_quickack_mode(struct sock *sk,
|
|
|
|
|
const unsigned int pkts)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2005-08-10 11:10:42 +08:00
|
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
2005-07-06 06:17:45 +08:00
|
|
|
|
2005-08-10 11:10:42 +08:00
|
|
|
if (icsk->icsk_ack.quick) {
|
|
|
|
|
if (pkts >= icsk->icsk_ack.quick) {
|
|
|
|
|
icsk->icsk_ack.quick = 0;
|
2005-07-06 06:17:45 +08:00
|
|
|
/* Leaving quickack mode we deflate ATO. */
|
2005-08-10 11:10:42 +08:00
|
|
|
icsk->icsk_ack.ato = TCP_ATO_MIN;
|
2005-07-06 06:17:45 +08:00
|
|
|
} else
|
2005-08-10 11:10:42 +08:00
|
|
|
icsk->icsk_ack.quick -= pkts;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2005-08-10 11:10:42 +08:00
|
|
|
extern void tcp_enter_quickack_mode(struct sock *sk);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
|
|
|
|
|
{
|
|
|
|
|
rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
|
|
|
|
|
}
|
|
|
|
|
|
2007-05-27 17:04:16 +08:00
|
|
|
#define TCP_ECN_OK 1
|
|
|
|
|
#define TCP_ECN_QUEUE_CWR 2
|
|
|
|
|
#define TCP_ECN_DEMAND_CWR 4
|
|
|
|
|
|
|
|
|
|
static __inline__ void
|
|
|
|
|
TCP_ECN_create_request(struct request_sock *req, struct tcphdr *th)
|
|
|
|
|
{
|
|
|
|
|
if (sysctl_tcp_ecn && th->ece && th->cwr)
|
|
|
|
|
inet_rsk(req)->ecn_ok = 1;
|
|
|
|
|
}
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
enum tcp_tw_status
|
|
|
|
|
{
|
|
|
|
|
TCP_TW_SUCCESS = 0,
|
|
|
|
|
TCP_TW_RST = 1,
|
|
|
|
|
TCP_TW_ACK = 2,
|
|
|
|
|
TCP_TW_SYN = 3
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
|
2005-08-10 11:09:30 +08:00
|
|
|
extern enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw,
|
2005-04-17 06:20:36 +08:00
|
|
|
struct sk_buff *skb,
|
2005-08-10 11:09:30 +08:00
|
|
|
const struct tcphdr *th);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
extern struct sock * tcp_check_req(struct sock *sk,struct sk_buff *skb,
|
2005-06-19 13:47:21 +08:00
|
|
|
struct request_sock *req,
|
|
|
|
|
struct request_sock **prev);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int tcp_child_process(struct sock *parent,
|
|
|
|
|
struct sock *child,
|
|
|
|
|
struct sk_buff *skb);
|
[TCP] FRTO: Entry is allowed only during (New)Reno like recovery
This interpretation comes from RFC4138:
"If the sender implements some loss recovery algorithm other
than Reno or NewReno [FHG04], the F-RTO algorithm SHOULD
NOT be entered when earlier fast recovery is underway."
I think the RFC means to say (especially in the light of
Appendix B) that ...recovery is underway (not just fast recovery)
or was underway when it was interrupted by an earlier (F-)RTO
that hasn't yet been resolved (snd_una has not advanced enough).
Thus, my interpretation is that whenever TCP has ever
retransmitted other than head, basic version cannot be used
because then the order assumptions which are used as FRTO basis
do not hold.
NewReno has only the head segment retransmitted at a time.
Therefore, walk up to the segment that has not been SACKed, if
that segment is not retransmitted nor anything before it, we know
for sure, that nothing after the non-SACKed segment should be
either. This assumption is valid because TCPCB_EVER_RETRANS does
not leave holes but each non-SACKed segment is rexmitted
in-order.
Check for retrans_out > 1 avoids more expensive walk through the
skb list, as we can know the result beforehand: F-RTO will not be
allowed.
SACKed skb can turn into non-SACked only in the extremely rare
case of SACK reneging, in this case we might fail to detect
retransmissions if there were them for any other than head. To
get rid of that feature, whole rexmit queue would have to be
walked (always) or FRTO should be prevented when SACK reneging
happens. Of course RTO should still trigger after reneging which
makes this issue even less likely to show up. And as long as the
response is as conservative as it's now, nothing bad happens even
then.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-02-22 15:10:39 +08:00
|
|
|
extern int tcp_use_frto(struct sock *sk);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern void tcp_enter_frto(struct sock *sk);
|
|
|
|
|
extern void tcp_enter_loss(struct sock *sk, int how);
|
|
|
|
|
extern void tcp_clear_retrans(struct tcp_sock *tp);
|
|
|
|
|
extern void tcp_update_metrics(struct sock *sk);
|
|
|
|
|
|
|
|
|
|
extern void tcp_close(struct sock *sk,
|
|
|
|
|
long timeout);
|
|
|
|
|
extern unsigned int tcp_poll(struct file * file, struct socket *sock, struct poll_table_struct *wait);
|
|
|
|
|
|
|
|
|
|
extern int tcp_getsockopt(struct sock *sk, int level,
|
|
|
|
|
int optname,
|
|
|
|
|
char __user *optval,
|
|
|
|
|
int __user *optlen);
|
|
|
|
|
extern int tcp_setsockopt(struct sock *sk, int level,
|
|
|
|
|
int optname, char __user *optval,
|
|
|
|
|
int optlen);
|
2006-03-21 14:45:21 +08:00
|
|
|
extern int compat_tcp_getsockopt(struct sock *sk,
|
|
|
|
|
int level, int optname,
|
|
|
|
|
char __user *optval, int __user *optlen);
|
|
|
|
|
extern int compat_tcp_setsockopt(struct sock *sk,
|
|
|
|
|
int level, int optname,
|
|
|
|
|
char __user *optval, int optlen);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern void tcp_set_keepalive(struct sock *sk, int val);
|
|
|
|
|
extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk,
|
|
|
|
|
struct msghdr *msg,
|
|
|
|
|
size_t len, int nonblock,
|
|
|
|
|
int flags, int *addr_len);
|
|
|
|
|
|
|
|
|
|
extern void tcp_parse_options(struct sk_buff *skb,
|
|
|
|
|
struct tcp_options_received *opt_rx,
|
|
|
|
|
int estab);
|
|
|
|
|
|
2008-04-17 11:29:53 +08:00
|
|
|
extern u8 *tcp_parse_md5sig_option(struct tcphdr *th);
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
|
* TCP v4 functions exported for the inet6 API
|
|
|
|
|
*/
|
|
|
|
|
|
2005-12-14 15:15:52 +08:00
|
|
|
extern void tcp_v4_send_check(struct sock *sk, int len,
|
2005-04-17 06:20:36 +08:00
|
|
|
struct sk_buff *skb);
|
|
|
|
|
|
|
|
|
|
extern int tcp_v4_conn_request(struct sock *sk,
|
|
|
|
|
struct sk_buff *skb);
|
|
|
|
|
|
|
|
|
|
extern struct sock * tcp_create_openreq_child(struct sock *sk,
|
2005-06-19 13:47:21 +08:00
|
|
|
struct request_sock *req,
|
2005-04-17 06:20:36 +08:00
|
|
|
struct sk_buff *skb);
|
|
|
|
|
|
|
|
|
|
extern struct sock * tcp_v4_syn_recv_sock(struct sock *sk,
|
|
|
|
|
struct sk_buff *skb,
|
2005-06-19 13:47:21 +08:00
|
|
|
struct request_sock *req,
|
2005-04-17 06:20:36 +08:00
|
|
|
struct dst_entry *dst);
|
|
|
|
|
|
|
|
|
|
extern int tcp_v4_do_rcv(struct sock *sk,
|
|
|
|
|
struct sk_buff *skb);
|
|
|
|
|
|
|
|
|
|
extern int tcp_v4_connect(struct sock *sk,
|
|
|
|
|
struct sockaddr *uaddr,
|
|
|
|
|
int addr_len);
|
|
|
|
|
|
|
|
|
|
extern int tcp_connect(struct sock *sk);
|
|
|
|
|
|
|
|
|
|
extern struct sk_buff * tcp_make_synack(struct sock *sk,
|
|
|
|
|
struct dst_entry *dst,
|
2005-06-19 13:47:21 +08:00
|
|
|
struct request_sock *req);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
extern int tcp_disconnect(struct sock *sk, int flags);
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/* From syncookies.c */
|
2008-03-24 13:21:28 +08:00
|
|
|
extern __u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS];
|
2005-04-17 06:20:36 +08:00
|
|
|
extern struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
|
|
|
|
|
struct ip_options *opt);
|
|
|
|
|
extern __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb,
|
|
|
|
|
__u16 *mss);
|
|
|
|
|
|
2008-04-10 18:12:40 +08:00
|
|
|
extern __u32 cookie_init_timestamp(struct request_sock *req);
|
|
|
|
|
extern void cookie_check_timestamp(struct tcp_options_received *tcp_opt);
|
|
|
|
|
|
2008-02-08 13:49:26 +08:00
|
|
|
/* From net/ipv6/syncookies.c */
|
|
|
|
|
extern struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb);
|
|
|
|
|
extern __u32 cookie_v6_init_sequence(struct sock *sk, struct sk_buff *skb,
|
|
|
|
|
__u16 *mss);
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* tcp_output.c */
|
|
|
|
|
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-21 13:18:02 +08:00
|
|
|
extern void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
|
|
|
|
|
int nonagle);
|
|
|
|
|
extern int tcp_may_send_now(struct sock *sk);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int tcp_retransmit_skb(struct sock *, struct sk_buff *);
|
|
|
|
|
extern void tcp_xmit_retransmit_queue(struct sock *);
|
|
|
|
|
extern void tcp_simple_retransmit(struct sock *);
|
|
|
|
|
extern int tcp_trim_head(struct sock *, struct sk_buff *, u32);
|
2005-09-02 13:47:01 +08:00
|
|
|
extern int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
extern void tcp_send_probe0(struct sock *);
|
|
|
|
|
extern void tcp_send_partial(struct sock *);
|
|
|
|
|
extern int tcp_write_wakeup(struct sock *);
|
|
|
|
|
extern void tcp_send_fin(struct sock *sk);
|
2005-10-07 14:46:04 +08:00
|
|
|
extern void tcp_send_active_reset(struct sock *sk, gfp_t priority);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern int tcp_send_synack(struct sock *);
|
2005-07-06 06:24:38 +08:00
|
|
|
extern void tcp_push_one(struct sock *, unsigned int mss_now);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern void tcp_send_ack(struct sock *sk);
|
|
|
|
|
extern void tcp_send_delayed_ack(struct sock *sk);
|
|
|
|
|
|
2005-07-06 06:18:51 +08:00
|
|
|
/* tcp_input.c */
|
|
|
|
|
extern void tcp_cwnd_application_limited(struct sock *sk);
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* tcp_timer.c */
|
|
|
|
|
extern void tcp_init_xmit_timers(struct sock *);
|
2005-08-10 11:10:42 +08:00
|
|
|
static inline void tcp_clear_xmit_timers(struct sock *sk)
|
|
|
|
|
{
|
|
|
|
|
inet_csk_clear_xmit_timers(sk);
|
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
extern unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
|
|
|
|
|
extern unsigned int tcp_current_mss(struct sock *sk, int large);
|
|
|
|
|
|
[INET_DIAG]: Move the tcp_diag interface to the proper place
With this the previous setup is back, i.e. tcp_diag can be built as a module,
as dccp_diag and both share the infrastructure available in inet_diag.
If one selects CONFIG_INET_DIAG as module CONFIG_INET_TCP_DIAG will also be
built as a module, as will CONFIG_INET_DCCP_DIAG, if CONFIG_IP_DCCP was
selected static or as a module, if CONFIG_INET_DIAG is y, being statically
linked CONFIG_INET_TCP_DIAG will follow suit and CONFIG_INET_DCCP_DIAG will be
built in the same manner as CONFIG_IP_DCCP.
Now to aim at UDP, converting it to use inet_hashinfo, so that we can use
iproute2 for UDP sockets as well.
Ah, just to show an example of this new infrastructure working for DCCP :-)
[root@qemu ~]# ./ss -dane
State Recv-Q Send-Q Local Address:Port Peer Address:Port
LISTEN 0 0 *:5001 *:* ino:942 sk:cfd503a0
ESTAB 0 0 127.0.0.1:5001 127.0.0.1:32770 ino:943 sk:cfd50a60
ESTAB 0 0 127.0.0.1:32770 127.0.0.1:5001 ino:947 sk:cfd50700
TIME-WAIT 0 0 127.0.0.1:32769 127.0.0.1:5001 timer:(timewait,3.430ms,0) ino:0 sk:cf209620
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-12 23:59:17 +08:00
|
|
|
/* tcp.c */
|
2005-04-17 06:20:36 +08:00
|
|
|
extern void tcp_get_info(struct sock *, struct tcp_info *);
|
|
|
|
|
|
|
|
|
|
/* Read 'sendfile()'-style from a TCP socket */
|
|
|
|
|
typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *,
|
|
|
|
|
unsigned int, size_t);
|
|
|
|
|
extern int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
|
|
|
|
|
sk_read_actor_t recv_actor);
|
|
|
|
|
|
2006-01-04 08:03:49 +08:00
|
|
|
extern void tcp_initialize_rcv_mss(struct sock *sk);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-03-21 09:53:41 +08:00
|
|
|
extern int tcp_mtu_to_mss(struct sock *sk, int pmtu);
|
|
|
|
|
extern int tcp_mss_to_mtu(struct sock *sk, int mss);
|
|
|
|
|
extern void tcp_mtup_init(struct sock *sk);
|
|
|
|
|
|
2006-01-04 08:03:49 +08:00
|
|
|
static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
tp->pred_flags = htonl((tp->tcp_header_len << 26) |
|
|
|
|
|
ntohl(TCP_FLAG_ACK) |
|
|
|
|
|
snd_wnd);
|
|
|
|
|
}
|
|
|
|
|
|
2006-01-04 08:03:49 +08:00
|
|
|
static inline void tcp_fast_path_on(struct tcp_sock *tp)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
__tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale);
|
|
|
|
|
}
|
|
|
|
|
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-21 13:18:02 +08:00
|
|
|
static inline void tcp_fast_path_check(struct sock *sk)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-21 13:18:02 +08:00
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
|
|
2005-07-09 05:57:23 +08:00
|
|
|
if (skb_queue_empty(&tp->out_of_order_queue) &&
|
2005-04-17 06:20:36 +08:00
|
|
|
tp->rcv_wnd &&
|
|
|
|
|
atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
|
|
|
|
|
!tp->urg_data)
|
|
|
|
|
tcp_fast_path_on(tp);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Compute the actual receive window we are currently advertising.
|
|
|
|
|
* Rcv_nxt can be after the window if our peer push more data
|
|
|
|
|
* than the offered window.
|
|
|
|
|
*/
|
2006-01-04 08:03:49 +08:00
|
|
|
static inline u32 tcp_receive_window(const struct tcp_sock *tp)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
s32 win = tp->rcv_wup + tp->rcv_wnd - tp->rcv_nxt;
|
|
|
|
|
|
|
|
|
|
if (win < 0)
|
|
|
|
|
win = 0;
|
|
|
|
|
return (u32) win;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Choose a new window, without checks for shrinking, and without
|
|
|
|
|
* scaling applied to the result. The caller does these things
|
|
|
|
|
* if necessary. This is a "raw" window selection.
|
|
|
|
|
*/
|
|
|
|
|
extern u32 __tcp_select_window(struct sock *sk);
|
|
|
|
|
|
|
|
|
|
/* TCP timestamps are only 32-bits, this causes a slight
|
|
|
|
|
* complication on 64-bit systems since we store a snapshot
|
2005-11-16 07:17:10 +08:00
|
|
|
* of jiffies in the buffer control blocks below. We decided
|
|
|
|
|
* to use only the low 32-bits of jiffies and hide the ugly
|
2005-04-17 06:20:36 +08:00
|
|
|
* casts with the following macro.
|
|
|
|
|
*/
|
|
|
|
|
#define tcp_time_stamp ((__u32)(jiffies))
|
|
|
|
|
|
2005-11-11 09:13:47 +08:00
|
|
|
/* This is what the send packet queuing engine uses to pass
|
2005-04-17 06:20:36 +08:00
|
|
|
* TCP per-packet control information to the transmission
|
|
|
|
|
* code. We also store the host-order sequence numbers in
|
|
|
|
|
* here too. This is 36 bytes on 32-bit architectures,
|
|
|
|
|
* 40 bytes on 64-bit machines, if this grows please adjust
|
|
|
|
|
* skbuff.h:skbuff->cb[xxx] size appropriately.
|
|
|
|
|
*/
|
|
|
|
|
struct tcp_skb_cb {
|
|
|
|
|
union {
|
|
|
|
|
struct inet_skb_parm h4;
|
|
|
|
|
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
|
|
|
|
|
struct inet6_skb_parm h6;
|
|
|
|
|
#endif
|
|
|
|
|
} header; /* For incoming frames */
|
|
|
|
|
__u32 seq; /* Starting sequence number */
|
|
|
|
|
__u32 end_seq; /* SEQ + FIN + SYN + datalen */
|
|
|
|
|
__u32 when; /* used to compute rtt's */
|
|
|
|
|
__u8 flags; /* TCP header flags. */
|
|
|
|
|
|
|
|
|
|
/* NOTE: These must match up to the flags byte in a
|
|
|
|
|
* real TCP header.
|
|
|
|
|
*/
|
|
|
|
|
#define TCPCB_FLAG_FIN 0x01
|
|
|
|
|
#define TCPCB_FLAG_SYN 0x02
|
|
|
|
|
#define TCPCB_FLAG_RST 0x04
|
|
|
|
|
#define TCPCB_FLAG_PSH 0x08
|
|
|
|
|
#define TCPCB_FLAG_ACK 0x10
|
|
|
|
|
#define TCPCB_FLAG_URG 0x20
|
|
|
|
|
#define TCPCB_FLAG_ECE 0x40
|
|
|
|
|
#define TCPCB_FLAG_CWR 0x80
|
|
|
|
|
|
|
|
|
|
__u8 sacked; /* State flags for SACK/FACK. */
|
|
|
|
|
#define TCPCB_SACKED_ACKED 0x01 /* SKB ACK'd by a SACK block */
|
|
|
|
|
#define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */
|
|
|
|
|
#define TCPCB_LOST 0x04 /* SKB is lost */
|
|
|
|
|
#define TCPCB_TAGBITS 0x07 /* All tag bits */
|
|
|
|
|
|
|
|
|
|
#define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */
|
|
|
|
|
#define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS)
|
|
|
|
|
|
|
|
|
|
__u32 ack_seq; /* Sequence number ACK'd */
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
#define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0]))
|
|
|
|
|
|
|
|
|
|
/* Due to TSO, an SKB can be composed of multiple actual
|
|
|
|
|
* packets. To keep these tracked properly, we use this.
|
|
|
|
|
*/
|
|
|
|
|
static inline int tcp_skb_pcount(const struct sk_buff *skb)
|
|
|
|
|
{
|
2006-06-22 17:40:14 +08:00
|
|
|
return skb_shinfo(skb)->gso_segs;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* This is valid iff tcp_skb_pcount() > 1. */
|
|
|
|
|
static inline int tcp_skb_mss(const struct sk_buff *skb)
|
|
|
|
|
{
|
2006-06-22 17:40:14 +08:00
|
|
|
return skb_shinfo(skb)->gso_size;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2007-06-15 17:58:38 +08:00
|
|
|
static inline void tcp_dec_pcount_approx_int(__u32 *count, const int decr)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
if (*count) {
|
2007-06-15 17:58:38 +08:00
|
|
|
*count -= decr;
|
2005-04-17 06:20:36 +08:00
|
|
|
if ((int)*count < 0)
|
|
|
|
|
*count = 0;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2007-06-15 17:58:38 +08:00
|
|
|
static inline void tcp_dec_pcount_approx(__u32 *count,
|
|
|
|
|
const struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
tcp_dec_pcount_approx_int(count, tcp_skb_pcount(skb));
|
|
|
|
|
}
|
|
|
|
|
|
2005-06-24 03:19:55 +08:00
|
|
|
/* Events passed to congestion control interface */
|
|
|
|
|
enum tcp_ca_event {
|
|
|
|
|
CA_EVENT_TX_START, /* first transmit when no packets in flight */
|
|
|
|
|
CA_EVENT_CWND_RESTART, /* congestion window restart */
|
|
|
|
|
CA_EVENT_COMPLETE_CWR, /* end of congestion recovery */
|
|
|
|
|
CA_EVENT_FRTO, /* fast recovery timeout */
|
|
|
|
|
CA_EVENT_LOSS, /* loss timeout */
|
|
|
|
|
CA_EVENT_FAST_ACK, /* in sequence ack */
|
|
|
|
|
CA_EVENT_SLOW_ACK, /* other ack */
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Interface for adding new TCP congestion control handlers
|
|
|
|
|
*/
|
|
|
|
|
#define TCP_CA_NAME_MAX 16
|
2006-11-10 08:32:06 +08:00
|
|
|
#define TCP_CA_MAX 128
|
|
|
|
|
#define TCP_CA_BUF_MAX (TCP_CA_NAME_MAX*TCP_CA_MAX)
|
|
|
|
|
|
2007-04-24 13:26:16 +08:00
|
|
|
#define TCP_CONG_NON_RESTRICTED 0x1
|
|
|
|
|
#define TCP_CONG_RTT_STAMP 0x2
|
|
|
|
|
|
2005-06-24 03:19:55 +08:00
|
|
|
struct tcp_congestion_ops {
|
|
|
|
|
struct list_head list;
|
2007-04-24 13:26:16 +08:00
|
|
|
unsigned long flags;
|
2005-06-24 03:19:55 +08:00
|
|
|
|
|
|
|
|
/* initialize private data (optional) */
|
2005-08-10 15:03:31 +08:00
|
|
|
void (*init)(struct sock *sk);
|
2005-06-24 03:19:55 +08:00
|
|
|
/* cleanup private data (optional) */
|
2005-08-10 15:03:31 +08:00
|
|
|
void (*release)(struct sock *sk);
|
2005-06-24 03:19:55 +08:00
|
|
|
|
|
|
|
|
/* return slow start threshold (required) */
|
2005-08-10 15:03:31 +08:00
|
|
|
u32 (*ssthresh)(struct sock *sk);
|
2005-06-24 03:19:55 +08:00
|
|
|
/* lower bound for congestion window (optional) */
|
2006-06-06 08:30:08 +08:00
|
|
|
u32 (*min_cwnd)(const struct sock *sk);
|
2005-06-24 03:19:55 +08:00
|
|
|
/* do new cwnd calculation (required) */
|
2007-12-02 06:47:59 +08:00
|
|
|
void (*cong_avoid)(struct sock *sk, u32 ack, u32 in_flight);
|
2005-06-24 03:19:55 +08:00
|
|
|
/* call before changing ca_state (optional) */
|
2005-08-10 15:03:31 +08:00
|
|
|
void (*set_state)(struct sock *sk, u8 new_state);
|
2005-06-24 03:19:55 +08:00
|
|
|
/* call when cwnd event occurs (optional) */
|
2005-08-10 15:03:31 +08:00
|
|
|
void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);
|
2005-06-24 03:19:55 +08:00
|
|
|
/* new value of cwnd after loss (optional) */
|
2005-08-10 15:03:31 +08:00
|
|
|
u32 (*undo_cwnd)(struct sock *sk);
|
2005-06-24 03:19:55 +08:00
|
|
|
/* hook for packet ack accounting (optional) */
|
2007-07-26 14:49:34 +08:00
|
|
|
void (*pkts_acked)(struct sock *sk, u32 num_acked, s32 rtt_us);
|
2005-08-12 23:51:49 +08:00
|
|
|
/* get info for inet_diag (optional) */
|
2005-08-10 15:03:31 +08:00
|
|
|
void (*get_info)(struct sock *sk, u32 ext, struct sk_buff *skb);
|
2005-06-24 03:19:55 +08:00
|
|
|
|
|
|
|
|
char name[TCP_CA_NAME_MAX];
|
|
|
|
|
struct module *owner;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
extern int tcp_register_congestion_control(struct tcp_congestion_ops *type);
|
|
|
|
|
extern void tcp_unregister_congestion_control(struct tcp_congestion_ops *type);
|
|
|
|
|
|
2005-08-10 15:03:31 +08:00
|
|
|
extern void tcp_init_congestion_control(struct sock *sk);
|
|
|
|
|
extern void tcp_cleanup_congestion_control(struct sock *sk);
|
2005-06-24 03:19:55 +08:00
|
|
|
extern int tcp_set_default_congestion_control(const char *name);
|
|
|
|
|
extern void tcp_get_default_congestion_control(char *name);
|
2006-11-10 08:32:06 +08:00
|
|
|
extern void tcp_get_available_congestion_control(char *buf, size_t len);
|
2006-11-10 08:35:15 +08:00
|
|
|
extern void tcp_get_allowed_congestion_control(char *buf, size_t len);
|
|
|
|
|
extern int tcp_set_allowed_congestion_control(char *allowed);
|
2005-08-10 15:03:31 +08:00
|
|
|
extern int tcp_set_congestion_control(struct sock *sk, const char *name);
|
2006-01-04 08:03:49 +08:00
|
|
|
extern void tcp_slow_start(struct tcp_sock *tp);
|
2005-06-24 03:19:55 +08:00
|
|
|
|
2005-06-24 11:37:36 +08:00
|
|
|
extern struct tcp_congestion_ops tcp_init_congestion_ops;
|
2005-08-10 15:03:31 +08:00
|
|
|
extern u32 tcp_reno_ssthresh(struct sock *sk);
|
2007-12-02 06:47:59 +08:00
|
|
|
extern void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight);
|
2006-06-06 08:30:08 +08:00
|
|
|
extern u32 tcp_reno_min_cwnd(const struct sock *sk);
|
2005-06-24 14:45:02 +08:00
|
|
|
extern struct tcp_congestion_ops tcp_reno;
|
2005-06-24 03:19:55 +08:00
|
|
|
|
2005-08-10 15:03:31 +08:00
|
|
|
static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
|
2005-06-24 03:19:55 +08:00
|
|
|
{
|
2005-08-10 15:03:31 +08:00
|
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
|
|
|
|
|
|
|
|
|
if (icsk->icsk_ca_ops->set_state)
|
|
|
|
|
icsk->icsk_ca_ops->set_state(sk, ca_state);
|
|
|
|
|
icsk->icsk_ca_state = ca_state;
|
2005-06-24 03:19:55 +08:00
|
|
|
}
|
|
|
|
|
|
2005-08-10 15:03:31 +08:00
|
|
|
static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
|
2005-06-24 03:19:55 +08:00
|
|
|
{
|
2005-08-10 15:03:31 +08:00
|
|
|
const struct inet_connection_sock *icsk = inet_csk(sk);
|
|
|
|
|
|
|
|
|
|
if (icsk->icsk_ca_ops->cwnd_event)
|
|
|
|
|
icsk->icsk_ca_ops->cwnd_event(sk, event);
|
2005-06-24 03:19:55 +08:00
|
|
|
}
|
|
|
|
|
|
2007-08-09 20:14:46 +08:00
|
|
|
/* These functions determine how the current flow behaves in respect of SACK
|
|
|
|
|
* handling. SACK is negotiated with the peer, and therefore it can vary
|
|
|
|
|
* between different flows.
|
|
|
|
|
*
|
|
|
|
|
* tcp_is_sack - SACK enabled
|
|
|
|
|
* tcp_is_reno - No SACK
|
|
|
|
|
* tcp_is_fack - FACK enabled, implies SACK enabled
|
|
|
|
|
*/
|
|
|
|
|
static inline int tcp_is_sack(const struct tcp_sock *tp)
|
|
|
|
|
{
|
|
|
|
|
return tp->rx_opt.sack_ok;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline int tcp_is_reno(const struct tcp_sock *tp)
|
|
|
|
|
{
|
|
|
|
|
return !tcp_is_sack(tp);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline int tcp_is_fack(const struct tcp_sock *tp)
|
|
|
|
|
{
|
|
|
|
|
return tp->rx_opt.sack_ok & 2;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void tcp_enable_fack(struct tcp_sock *tp)
|
|
|
|
|
{
|
|
|
|
|
tp->rx_opt.sack_ok |= 2;
|
|
|
|
|
}
|
|
|
|
|
|
2007-08-09 19:37:30 +08:00
|
|
|
static inline unsigned int tcp_left_out(const struct tcp_sock *tp)
|
|
|
|
|
{
|
|
|
|
|
return tp->sacked_out + tp->lost_out;
|
|
|
|
|
}
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* This determines how many packets are "in the network" to the best
|
|
|
|
|
* of our knowledge. In many cases it is conservative, but where
|
|
|
|
|
* detailed information is available from the receiver (via SACK
|
|
|
|
|
* blocks etc.) we can make more aggressive calculations.
|
|
|
|
|
*
|
|
|
|
|
* Use this for decisions involving congestion control, use just
|
|
|
|
|
* tp->packets_out to determine if the send queue is empty or not.
|
|
|
|
|
*
|
|
|
|
|
* Read this equation as:
|
|
|
|
|
*
|
|
|
|
|
* "Packets sent once on transmission queue" MINUS
|
|
|
|
|
* "Packets left network, but not honestly ACKed yet" PLUS
|
|
|
|
|
* "Packets fast retransmitted"
|
|
|
|
|
*/
|
2006-01-04 08:03:49 +08:00
|
|
|
static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2007-08-09 19:37:30 +08:00
|
|
|
return tp->packets_out - tcp_left_out(tp) + tp->retrans_out;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* If cwnd > ssthresh, we may raise ssthresh to be half-way to cwnd.
|
|
|
|
|
* The exception is rate halving phase, when cwnd is decreasing towards
|
|
|
|
|
* ssthresh.
|
|
|
|
|
*/
|
2005-08-10 15:03:31 +08:00
|
|
|
static inline __u32 tcp_current_ssthresh(const struct sock *sk)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2005-08-10 15:03:31 +08:00
|
|
|
const struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
|
if ((1 << inet_csk(sk)->icsk_ca_state) & (TCPF_CA_CWR | TCPF_CA_Recovery))
|
2005-04-17 06:20:36 +08:00
|
|
|
return tp->snd_ssthresh;
|
|
|
|
|
else
|
|
|
|
|
return max(tp->snd_ssthresh,
|
|
|
|
|
((tp->snd_cwnd >> 1) +
|
|
|
|
|
(tp->snd_cwnd >> 2)));
|
|
|
|
|
}
|
|
|
|
|
|
2007-07-27 21:36:17 +08:00
|
|
|
/* Use define here intentionally to get WARN_ON location shown at the caller */
|
|
|
|
|
#define tcp_verify_left_out(tp) WARN_ON(tcp_left_out(tp) > tp->packets_out)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-02-28 02:09:49 +08:00
|
|
|
extern void tcp_enter_cwr(struct sock *sk, const int set_ssthresh);
|
2005-04-17 06:20:36 +08:00
|
|
|
extern __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst);
|
|
|
|
|
|
|
|
|
|
/* Slow start with delack produces 3 packets of burst, so that
|
2008-04-16 06:26:39 +08:00
|
|
|
* it is safe "de facto". This will be the default - same as
|
|
|
|
|
* the default reordering threshold - but if reordering increases,
|
|
|
|
|
* we must be able to allow cwnd to burst at least this much in order
|
|
|
|
|
* to not pull it back when holes are filled.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
|
static __inline__ __u32 tcp_max_burst(const struct tcp_sock *tp)
|
|
|
|
|
{
|
2008-04-16 06:26:39 +08:00
|
|
|
return tp->reordering;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2007-12-31 20:48:41 +08:00
|
|
|
/* Returns end sequence number of the receiver's advertised window */
|
|
|
|
|
static inline u32 tcp_wnd_end(const struct tcp_sock *tp)
|
|
|
|
|
{
|
|
|
|
|
return tp->snd_una + tp->snd_wnd;
|
|
|
|
|
}
|
[TCP]: Uninline tcp_is_cwnd_limited
net/ipv4/tcp_cong.c:
tcp_reno_cong_avoid | -65
1 function changed, 65 bytes removed, diff: -65
net/ipv4/arp.c:
arp_ignore | -5
1 function changed, 5 bytes removed, diff: -5
net/ipv4/tcp_bic.c:
bictcp_cong_avoid | -57
1 function changed, 57 bytes removed, diff: -57
net/ipv4/tcp_cubic.c:
bictcp_cong_avoid | -61
1 function changed, 61 bytes removed, diff: -61
net/ipv4/tcp_highspeed.c:
hstcp_cong_avoid | -63
1 function changed, 63 bytes removed, diff: -63
net/ipv4/tcp_hybla.c:
hybla_cong_avoid | -85
1 function changed, 85 bytes removed, diff: -85
net/ipv4/tcp_htcp.c:
htcp_cong_avoid | -57
1 function changed, 57 bytes removed, diff: -57
net/ipv4/tcp_veno.c:
tcp_veno_cong_avoid | -52
1 function changed, 52 bytes removed, diff: -52
net/ipv4/tcp_scalable.c:
tcp_scalable_cong_avoid | -61
1 function changed, 61 bytes removed, diff: -61
net/ipv4/tcp_yeah.c:
tcp_yeah_cong_avoid | -75
1 function changed, 75 bytes removed, diff: -75
net/ipv4/tcp_illinois.c:
tcp_illinois_cong_avoid | -54
1 function changed, 54 bytes removed, diff: -54
net/dccp/ccids/ccid3.c:
ccid3_update_send_interval | -7
ccid3_hc_tx_packet_recv | +7
2 functions changed, 7 bytes added, 7 bytes removed, diff: +0
net/ipv4/tcp_cong.c:
tcp_is_cwnd_limited | +88
1 function changed, 88 bytes added, diff: +88
built-in.o:
14 functions changed, 95 bytes added, 642 bytes removed, diff: -547
...Again some gcc artifacts visible as well.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-12 19:19:12 +08:00
|
|
|
extern int tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight);
|
2005-11-11 08:53:30 +08:00
|
|
|
|
2007-10-24 12:08:54 +08:00
|
|
|
static inline void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss,
|
2006-01-04 08:03:49 +08:00
|
|
|
const struct sk_buff *skb)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
if (skb->len < mss)
|
|
|
|
|
tp->snd_sml = TCP_SKB_CB(skb)->end_seq;
|
|
|
|
|
}
|
|
|
|
|
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-21 13:18:02 +08:00
|
|
|
static inline void tcp_check_probe_timer(struct sock *sk)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-21 13:18:02 +08:00
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
2005-08-10 11:10:42 +08:00
|
|
|
const struct inet_connection_sock *icsk = inet_csk(sk);
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-21 13:18:02 +08:00
|
|
|
|
2005-08-10 11:10:42 +08:00
|
|
|
if (!tp->packets_out && !icsk->icsk_pending)
|
2005-08-10 11:11:08 +08:00
|
|
|
inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
|
|
|
|
|
icsk->icsk_rto, TCP_RTO_MAX);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-21 13:18:02 +08:00
|
|
|
static inline void tcp_push_pending_frames(struct sock *sk)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-21 13:18:02 +08:00
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
|
|
|
|
|
|
__tcp_push_pending_frames(sk, tcp_current_mss(sk, 1), tp->nonagle);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2006-01-04 08:03:49 +08:00
|
|
|
static inline void tcp_init_wl(struct tcp_sock *tp, u32 ack, u32 seq)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
tp->snd_wl1 = seq;
|
|
|
|
|
}
|
|
|
|
|
|
2006-01-04 08:03:49 +08:00
|
|
|
static inline void tcp_update_wl(struct tcp_sock *tp, u32 ack, u32 seq)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
tp->snd_wl1 = seq;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Calculate(/check) TCP checksum
|
|
|
|
|
*/
|
2007-02-05 12:15:27 +08:00
|
|
|
static inline __sum16 tcp_v4_check(int len, __be32 saddr,
|
|
|
|
|
__be32 daddr, __wsum base)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
return csum_tcpudp_magic(saddr,daddr,len,IPPROTO_TCP,base);
|
|
|
|
|
}
|
|
|
|
|
|
2006-11-15 13:40:42 +08:00
|
|
|
static inline __sum16 __tcp_checksum_complete(struct sk_buff *skb)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2005-11-11 05:01:24 +08:00
|
|
|
return __skb_checksum_complete(skb);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2006-01-04 08:03:49 +08:00
|
|
|
static inline int tcp_checksum_complete(struct sk_buff *skb)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2007-04-10 02:59:39 +08:00
|
|
|
return !skb_csum_unnecessary(skb) &&
|
2005-04-17 06:20:36 +08:00
|
|
|
__tcp_checksum_complete(skb);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Prequeue for VJ style copy to user, combined with checksumming. */
|
|
|
|
|
|
2006-01-04 08:03:49 +08:00
|
|
|
static inline void tcp_prequeue_init(struct tcp_sock *tp)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
tp->ucopy.task = NULL;
|
|
|
|
|
tp->ucopy.len = 0;
|
|
|
|
|
tp->ucopy.memory = 0;
|
|
|
|
|
skb_queue_head_init(&tp->ucopy.prequeue);
|
2006-05-24 08:55:33 +08:00
|
|
|
#ifdef CONFIG_NET_DMA
|
|
|
|
|
tp->ucopy.dma_chan = NULL;
|
|
|
|
|
tp->ucopy.wakeup = 0;
|
|
|
|
|
tp->ucopy.pinned_list = NULL;
|
|
|
|
|
tp->ucopy.dma_cookie = 0;
|
|
|
|
|
#endif
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Packet is added to VJ-style prequeue for processing in process
|
|
|
|
|
* context, if a reader task is waiting. Apparently, this exciting
|
|
|
|
|
* idea (VJ's mail "Re: query about TCP header on tcp-ip" of 07 Sep 93)
|
|
|
|
|
* failed somewhere. Latency? Burstiness? Well, at least now we will
|
|
|
|
|
* see, why it failed. 8)8) --ANK
|
|
|
|
|
*
|
|
|
|
|
* NOTE: is this not too big to inline?
|
|
|
|
|
*/
|
2006-01-04 08:03:49 +08:00
|
|
|
static inline int tcp_prequeue(struct sock *sk, struct sk_buff *skb)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
|
|
|
|
|
|
if (!sysctl_tcp_low_latency && tp->ucopy.task) {
|
|
|
|
|
__skb_queue_tail(&tp->ucopy.prequeue, skb);
|
|
|
|
|
tp->ucopy.memory += skb->truesize;
|
|
|
|
|
if (tp->ucopy.memory > sk->sk_rcvbuf) {
|
|
|
|
|
struct sk_buff *skb1;
|
|
|
|
|
|
|
|
|
|
BUG_ON(sock_owned_by_user(sk));
|
|
|
|
|
|
|
|
|
|
while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) {
|
2008-10-08 05:18:42 +08:00
|
|
|
sk_backlog_rcv(sk, skb1);
|
2008-07-17 11:31:16 +08:00
|
|
|
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPREQUEUEDROPPED);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
tp->ucopy.memory = 0;
|
|
|
|
|
} else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
|
|
|
|
|
wake_up_interruptible(sk->sk_sleep);
|
2005-08-10 11:10:42 +08:00
|
|
|
if (!inet_csk_ack_scheduled(sk))
|
|
|
|
|
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
|
2005-08-10 11:11:08 +08:00
|
|
|
(3 * TCP_RTO_MIN) / 4,
|
|
|
|
|
TCP_RTO_MAX);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
return 1;
|
|
|
|
|
}
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#undef STATE_TRACE
|
|
|
|
|
|
|
|
|
|
#ifdef STATE_TRACE
|
|
|
|
|
static const char *statename[]={
|
|
|
|
|
"Unused","Established","Syn Sent","Syn Recv",
|
|
|
|
|
"Fin Wait 1","Fin Wait 2","Time Wait", "Close",
|
|
|
|
|
"Close Wait","Last ACK","Listen","Closing"
|
|
|
|
|
};
|
|
|
|
|
#endif
|
[TCP]: Uninline tcp_set_state
net/ipv4/tcp.c:
tcp_close_state | -226
tcp_done | -145
tcp_close | -564
tcp_disconnect | -141
4 functions changed, 1076 bytes removed, diff: -1076
net/ipv4/tcp_input.c:
tcp_fin | -86
tcp_rcv_state_process | -164
2 functions changed, 250 bytes removed, diff: -250
net/ipv4/tcp_ipv4.c:
tcp_v4_connect | -209
1 function changed, 209 bytes removed, diff: -209
net/ipv4/arp.c:
arp_ignore | +5
1 function changed, 5 bytes added, diff: +5
net/ipv6/tcp_ipv6.c:
tcp_v6_connect | -158
1 function changed, 158 bytes removed, diff: -158
net/sunrpc/xprtsock.c:
xs_sendpages | -2
1 function changed, 2 bytes removed, diff: -2
net/dccp/ccids/ccid3.c:
ccid3_update_send_interval | +7
1 function changed, 7 bytes added, diff: +7
net/ipv4/tcp.c:
tcp_set_state | +238
1 function changed, 238 bytes added, diff: +238
built-in.o:
12 functions changed, 250 bytes added, 1695 bytes removed, diff: -1445
I've no explanation why some unrelated changes seem to occur
consistently as well (arp_ignore, ccid3_update_send_interval;
I checked the arp_ignore asm and it seems to be due to some
reordered of operation order causing some extra opcodes to be
generated). Still, the benefits are pretty obvious from the
codiff's results.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-12 19:17:20 +08:00
|
|
|
extern void tcp_set_state(struct sock *sk, int state);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-04-21 08:11:46 +08:00
|
|
|
extern void tcp_done(struct sock *sk);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-01-04 08:03:49 +08:00
|
|
|
static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
rx_opt->dsack = 0;
|
|
|
|
|
rx_opt->eff_sacks = 0;
|
|
|
|
|
rx_opt->num_sacks = 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Determine a window scaling and initial window to offer. */
|
|
|
|
|
extern void tcp_select_initial_window(int __space, __u32 mss,
|
|
|
|
|
__u32 *rcv_wnd, __u32 *window_clamp,
|
|
|
|
|
int wscale_ok, __u8 *rcv_wscale);
|
|
|
|
|
|
|
|
|
|
static inline int tcp_win_from_space(int space)
|
|
|
|
|
{
|
|
|
|
|
return sysctl_tcp_adv_win_scale<=0 ?
|
|
|
|
|
(space>>(-sysctl_tcp_adv_win_scale)) :
|
|
|
|
|
space - (space>>sysctl_tcp_adv_win_scale);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Note: caller must be prepared to deal with negative returns */
|
|
|
|
|
static inline int tcp_space(const struct sock *sk)
|
|
|
|
|
{
|
|
|
|
|
return tcp_win_from_space(sk->sk_rcvbuf -
|
|
|
|
|
atomic_read(&sk->sk_rmem_alloc));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline int tcp_full_space(const struct sock *sk)
|
|
|
|
|
{
|
|
|
|
|
return tcp_win_from_space(sk->sk_rcvbuf);
|
|
|
|
|
}
|
|
|
|
|
|
2006-01-04 08:03:49 +08:00
|
|
|
static inline void tcp_openreq_init(struct request_sock *req,
|
|
|
|
|
struct tcp_options_received *rx_opt,
|
|
|
|
|
struct sk_buff *skb)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
[NET] Generalise TCP's struct open_request minisock infrastructure
Kept this first changeset minimal, without changing existing names to
ease peer review.
Basicaly tcp_openreq_alloc now receives the or_calltable, that in turn
has two new members:
->slab, that replaces tcp_openreq_cachep
->obj_size, to inform the size of the openreq descendant for
a specific protocol
The protocol specific fields in struct open_request were moved to a
class hierarchy, with the things that are common to all connection
oriented PF_INET protocols in struct inet_request_sock, the TCP ones
in tcp_request_sock, that is an inet_request_sock, that is an
open_request.
I.e. this uses the same approach used for the struct sock class
hierarchy, with sk_prot indicating if the protocol wants to use the
open_request infrastructure by filling in sk_prot->rsk_prot with an
or_calltable.
Results? Performance is improved and TCP v4 now uses only 64 bytes per
open request minisock, down from 96 without this patch :-)
Next changeset will rename some of the structs, fields and functions
mentioned above, struct or_calltable is way unclear, better name it
struct request_sock_ops, s/struct open_request/struct request_sock/g,
etc.
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-19 13:46:52 +08:00
|
|
|
struct inet_request_sock *ireq = inet_rsk(req);
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */
|
2008-04-10 18:12:40 +08:00
|
|
|
req->cookie_ts = 0;
|
[NET] Generalise TCP's struct open_request minisock infrastructure
Kept this first changeset minimal, without changing existing names to
ease peer review.
Basicaly tcp_openreq_alloc now receives the or_calltable, that in turn
has two new members:
->slab, that replaces tcp_openreq_cachep
->obj_size, to inform the size of the openreq descendant for
a specific protocol
The protocol specific fields in struct open_request were moved to a
class hierarchy, with the things that are common to all connection
oriented PF_INET protocols in struct inet_request_sock, the TCP ones
in tcp_request_sock, that is an inet_request_sock, that is an
open_request.
I.e. this uses the same approach used for the struct sock class
hierarchy, with sk_prot indicating if the protocol wants to use the
open_request infrastructure by filling in sk_prot->rsk_prot with an
or_calltable.
Results? Performance is improved and TCP v4 now uses only 64 bytes per
open request minisock, down from 96 without this patch :-)
Next changeset will rename some of the structs, fields and functions
mentioned above, struct or_calltable is way unclear, better name it
struct request_sock_ops, s/struct open_request/struct request_sock/g,
etc.
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-19 13:46:52 +08:00
|
|
|
tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq;
|
2005-04-17 06:20:36 +08:00
|
|
|
req->mss = rx_opt->mss_clamp;
|
|
|
|
|
req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0;
|
[NET] Generalise TCP's struct open_request minisock infrastructure
Kept this first changeset minimal, without changing existing names to
ease peer review.
Basicaly tcp_openreq_alloc now receives the or_calltable, that in turn
has two new members:
->slab, that replaces tcp_openreq_cachep
->obj_size, to inform the size of the openreq descendant for
a specific protocol
The protocol specific fields in struct open_request were moved to a
class hierarchy, with the things that are common to all connection
oriented PF_INET protocols in struct inet_request_sock, the TCP ones
in tcp_request_sock, that is an inet_request_sock, that is an
open_request.
I.e. this uses the same approach used for the struct sock class
hierarchy, with sk_prot indicating if the protocol wants to use the
open_request infrastructure by filling in sk_prot->rsk_prot with an
or_calltable.
Results? Performance is improved and TCP v4 now uses only 64 bytes per
open request minisock, down from 96 without this patch :-)
Next changeset will rename some of the structs, fields and functions
mentioned above, struct or_calltable is way unclear, better name it
struct request_sock_ops, s/struct open_request/struct request_sock/g,
etc.
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-19 13:46:52 +08:00
|
|
|
ireq->tstamp_ok = rx_opt->tstamp_ok;
|
|
|
|
|
ireq->sack_ok = rx_opt->sack_ok;
|
|
|
|
|
ireq->snd_wscale = rx_opt->snd_wscale;
|
|
|
|
|
ireq->wscale_ok = rx_opt->wscale_ok;
|
|
|
|
|
ireq->acked = 0;
|
|
|
|
|
ireq->ecn_ok = 0;
|
2007-04-11 12:04:22 +08:00
|
|
|
ireq->rmt_port = tcp_hdr(skb)->source;
|
2008-10-01 22:46:49 +08:00
|
|
|
ireq->loc_port = tcp_hdr(skb)->dest;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2008-07-17 11:28:10 +08:00
|
|
|
extern void tcp_enter_memory_pressure(struct sock *sk);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
static inline int keepalive_intvl_when(const struct tcp_sock *tp)
|
|
|
|
|
{
|
|
|
|
|
return tp->keepalive_intvl ? : sysctl_tcp_keepalive_intvl;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline int keepalive_time_when(const struct tcp_sock *tp)
|
|
|
|
|
{
|
|
|
|
|
return tp->keepalive_time ? : sysctl_tcp_keepalive_time;
|
|
|
|
|
}
|
|
|
|
|
|
2005-08-10 11:10:42 +08:00
|
|
|
static inline int tcp_fin_time(const struct sock *sk)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2005-08-10 11:10:42 +08:00
|
|
|
int fin_timeout = tcp_sk(sk)->linger2 ? : sysctl_tcp_fin_timeout;
|
|
|
|
|
const int rto = inet_csk(sk)->icsk_rto;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-08-10 11:10:42 +08:00
|
|
|
if (fin_timeout < (rto << 2) - (rto >> 1))
|
|
|
|
|
fin_timeout = (rto << 2) - (rto >> 1);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
return fin_timeout;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline int tcp_paws_check(const struct tcp_options_received *rx_opt, int rst)
|
|
|
|
|
{
|
|
|
|
|
if ((s32)(rx_opt->rcv_tsval - rx_opt->ts_recent) >= 0)
|
|
|
|
|
return 0;
|
2007-03-05 08:12:44 +08:00
|
|
|
if (get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS)
|
2005-04-17 06:20:36 +08:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
|
|
/* RST segments are not recommended to carry timestamp,
|
|
|
|
|
and, if they do, it is recommended to ignore PAWS because
|
|
|
|
|
"their cleanup function should take precedence over timestamps."
|
|
|
|
|
Certainly, it is mistake. It is necessary to understand the reasons
|
|
|
|
|
of this constraint to relax it: if peer reboots, clock may go
|
|
|
|
|
out-of-sync and half-open connections will not be reset.
|
|
|
|
|
Actually, the problem would be not existing if all
|
|
|
|
|
the implementations followed draft about maintaining clock
|
|
|
|
|
via reboots. Linux-2.2 DOES NOT!
|
|
|
|
|
|
|
|
|
|
However, we can relax time bounds for RST segments to MSL.
|
|
|
|
|
*/
|
2007-03-05 08:12:44 +08:00
|
|
|
if (rst && get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_MSL)
|
2005-04-17 06:20:36 +08:00
|
|
|
return 0;
|
|
|
|
|
return 1;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#define TCP_CHECK_TIMER(sk) do { } while (0)
|
|
|
|
|
|
2008-07-17 11:21:42 +08:00
|
|
|
static inline void tcp_mib_init(struct net *net)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
/* See RFC 2012 */
|
2008-07-17 11:27:38 +08:00
|
|
|
TCP_ADD_STATS_USER(net, TCP_MIB_RTOALGORITHM, 1);
|
|
|
|
|
TCP_ADD_STATS_USER(net, TCP_MIB_RTOMIN, TCP_RTO_MIN*1000/HZ);
|
|
|
|
|
TCP_ADD_STATS_USER(net, TCP_MIB_RTOMAX, TCP_RTO_MAX*1000/HZ);
|
|
|
|
|
TCP_ADD_STATS_USER(net, TCP_MIB_MAXCONN, -1);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2007-09-21 02:30:48 +08:00
|
|
|
/* from STCP */
|
2008-09-21 12:25:15 +08:00
|
|
|
static inline void tcp_clear_retrans_hints_partial(struct tcp_sock *tp)
|
2007-09-21 02:40:37 +08:00
|
|
|
{
|
2005-11-11 09:14:59 +08:00
|
|
|
tp->lost_skb_hint = NULL;
|
|
|
|
|
tp->scoreboard_skb_hint = NULL;
|
2008-09-21 12:25:15 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp)
|
|
|
|
|
{
|
|
|
|
|
tcp_clear_retrans_hints_partial(tp);
|
2005-11-11 09:14:59 +08:00
|
|
|
tp->retransmit_skb_hint = NULL;
|
2007-09-21 02:37:19 +08:00
|
|
|
}
|
|
|
|
|
|
2006-11-15 11:07:45 +08:00
|
|
|
/* MD5 Signature */
|
|
|
|
|
struct crypto_hash;
|
|
|
|
|
|
|
|
|
|
/* - key database */
|
|
|
|
|
struct tcp_md5sig_key {
|
|
|
|
|
u8 *key;
|
|
|
|
|
u8 keylen;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct tcp4_md5sig_key {
|
2007-09-29 06:18:35 +08:00
|
|
|
struct tcp_md5sig_key base;
|
2006-11-15 11:07:45 +08:00
|
|
|
__be32 addr;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct tcp6_md5sig_key {
|
2007-09-29 06:18:35 +08:00
|
|
|
struct tcp_md5sig_key base;
|
2006-11-15 11:07:45 +08:00
|
|
|
#if 0
|
|
|
|
|
u32 scope_id; /* XXX */
|
|
|
|
|
#endif
|
|
|
|
|
struct in6_addr addr;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
/* - sock block */
|
|
|
|
|
struct tcp_md5sig_info {
|
|
|
|
|
struct tcp4_md5sig_key *keys4;
|
|
|
|
|
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
|
|
|
|
|
struct tcp6_md5sig_key *keys6;
|
|
|
|
|
u32 entries6;
|
|
|
|
|
u32 alloced6;
|
|
|
|
|
#endif
|
|
|
|
|
u32 entries4;
|
|
|
|
|
u32 alloced4;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
/* - pseudo header */
|
|
|
|
|
struct tcp4_pseudohdr {
|
|
|
|
|
__be32 saddr;
|
|
|
|
|
__be32 daddr;
|
|
|
|
|
__u8 pad;
|
|
|
|
|
__u8 protocol;
|
|
|
|
|
__be16 len;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct tcp6_pseudohdr {
|
|
|
|
|
struct in6_addr saddr;
|
|
|
|
|
struct in6_addr daddr;
|
|
|
|
|
__be32 len;
|
|
|
|
|
__be32 protocol; /* including padding */
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
union tcp_md5sum_block {
|
|
|
|
|
struct tcp4_pseudohdr ip4;
|
|
|
|
|
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
|
|
|
|
|
struct tcp6_pseudohdr ip6;
|
|
|
|
|
#endif
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
/* - pool: digest algorithm, hash description and scratch buffer */
|
|
|
|
|
struct tcp_md5sig_pool {
|
|
|
|
|
struct hash_desc md5_desc;
|
|
|
|
|
union tcp_md5sum_block md5_blk;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
#define TCP_MD5SIG_MAXKEYS (~(u32)0) /* really?! */
|
|
|
|
|
|
|
|
|
|
/* - functions */
|
2008-07-19 15:01:42 +08:00
|
|
|
extern int tcp_v4_md5_hash_skb(char *md5_hash,
|
|
|
|
|
struct tcp_md5sig_key *key,
|
|
|
|
|
struct sock *sk,
|
|
|
|
|
struct request_sock *req,
|
|
|
|
|
struct sk_buff *skb);
|
|
|
|
|
|
2006-11-15 11:07:45 +08:00
|
|
|
extern struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
|
|
|
|
|
struct sock *addr_sk);
|
|
|
|
|
|
|
|
|
|
extern int tcp_v4_md5_do_add(struct sock *sk,
|
|
|
|
|
__be32 addr,
|
|
|
|
|
u8 *newkey,
|
|
|
|
|
u8 newkeylen);
|
|
|
|
|
|
|
|
|
|
extern int tcp_v4_md5_do_del(struct sock *sk,
|
2006-11-21 10:06:37 +08:00
|
|
|
__be32 addr);
|
2006-11-15 11:07:45 +08:00
|
|
|
|
2008-04-18 11:45:16 +08:00
|
|
|
#ifdef CONFIG_TCP_MD5SIG
|
|
|
|
|
#define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_keylen ? \
|
|
|
|
|
&(struct tcp_md5sig_key) { \
|
|
|
|
|
.key = (twsk)->tw_md5_key, \
|
|
|
|
|
.keylen = (twsk)->tw_md5_keylen, \
|
|
|
|
|
} : NULL)
|
|
|
|
|
#else
|
|
|
|
|
#define tcp_twsk_md5_key(twsk) NULL
|
|
|
|
|
#endif
|
|
|
|
|
|
2006-11-15 11:07:45 +08:00
|
|
|
extern struct tcp_md5sig_pool **tcp_alloc_md5sig_pool(void);
|
|
|
|
|
extern void tcp_free_md5sig_pool(void);
|
|
|
|
|
|
|
|
|
|
extern struct tcp_md5sig_pool *__tcp_get_md5sig_pool(int cpu);
|
|
|
|
|
extern void __tcp_put_md5sig_pool(void);
|
2008-07-19 15:01:42 +08:00
|
|
|
extern int tcp_md5_hash_header(struct tcp_md5sig_pool *, struct tcphdr *);
|
|
|
|
|
extern int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, struct sk_buff *,
|
|
|
|
|
unsigned header_len);
|
|
|
|
|
extern int tcp_md5_hash_key(struct tcp_md5sig_pool *hp,
|
|
|
|
|
struct tcp_md5sig_key *key);
|
2006-11-15 11:07:45 +08:00
|
|
|
|
|
|
|
|
static inline
|
|
|
|
|
struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
|
|
|
|
|
{
|
|
|
|
|
int cpu = get_cpu();
|
|
|
|
|
struct tcp_md5sig_pool *ret = __tcp_get_md5sig_pool(cpu);
|
|
|
|
|
if (!ret)
|
|
|
|
|
put_cpu();
|
|
|
|
|
return ret;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void tcp_put_md5sig_pool(void)
|
|
|
|
|
{
|
|
|
|
|
__tcp_put_md5sig_pool();
|
|
|
|
|
put_cpu();
|
|
|
|
|
}
|
|
|
|
|
|
2007-03-08 04:12:44 +08:00
|
|
|
/* write queue abstraction */
|
|
|
|
|
static inline void tcp_write_queue_purge(struct sock *sk)
|
|
|
|
|
{
|
|
|
|
|
struct sk_buff *skb;
|
|
|
|
|
|
|
|
|
|
while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL)
|
2007-12-31 16:11:19 +08:00
|
|
|
sk_wmem_free_skb(sk, skb);
|
|
|
|
|
sk_mem_reclaim(sk);
|
2007-03-08 04:12:44 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline struct sk_buff *tcp_write_queue_head(struct sock *sk)
|
|
|
|
|
{
|
2008-09-23 15:50:13 +08:00
|
|
|
return skb_peek(&sk->sk_write_queue);
|
2007-03-08 04:12:44 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline struct sk_buff *tcp_write_queue_tail(struct sock *sk)
|
|
|
|
|
{
|
2008-09-23 15:50:13 +08:00
|
|
|
return skb_peek_tail(&sk->sk_write_queue);
|
2007-03-08 04:12:44 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline struct sk_buff *tcp_write_queue_next(struct sock *sk, struct sk_buff *skb)
|
|
|
|
|
{
|
2008-09-23 15:50:13 +08:00
|
|
|
return skb_queue_next(&sk->sk_write_queue, skb);
|
2007-03-08 04:12:44 +08:00
|
|
|
}
|
|
|
|
|
|
tcp: Try to restore large SKBs while SACK processing
During SACK processing, most of the benefits of TSO are eaten by
the SACK blocks that one-by-one fragment SKBs to MSS sized chunks.
Then we're in problems when cleanup work for them has to be done
when a large cumulative ACK comes. Try to return back to pre-split
state already while more and more SACK info gets discovered by
combining newly discovered SACK areas with the previous skb if
that's SACKed as well.
This approach has a number of benefits:
1) The processing overhead is spread more equally over the RTT
2) Write queue has less skbs to process (affect everything
which has to walk in the queue past the sacked areas)
3) Write queue is consistent whole the time, so no other parts
of TCP has to be aware of this (this was not the case with
some other approach that was, well, quite intrusive all
around).
4) Clean_rtx_queue can release most of the pages using single
put_page instead of previous PAGE_SIZE/mss+1 calls
In case a hole is fully filled by the new SACK block, we attempt
to combine the next skb too which allows construction of skbs
that are even larger than what tso split them to and it handles
hole per on every nth patterns that often occur during slow start
overshoot pretty nicely. Though this to be really useful also
a retransmission would have to get lost since cumulative ACKs
advance one hole at a time in the most typical case.
TODO: handle upwards only merging. That should be rather easy
when segment is fully sacked but I'm leaving that as future
work item (it won't make very large difference anyway since
this current approach already covers quite a lot of normal
cases).
I was earlier thinking of some sophisticated way of tracking
timestamps of the first and the last segment but later on
realized that it won't be that necessary at all to store the
timestamp of the last segment. The cases that can occur are
basically either:
1) ambiguous => no sensible measurement can be taken anyway
2) non-ambiguous is due to reordering => having the timestamp
of the last segment there is just skewing things more off
than does some good since the ack got triggered by one of
the holes (besides some substle issues that would make
determining right hole/skb even harder problem). Anyway,
it has nothing to do with this change then.
I choose to route some abnormal looking cases with goto noop,
some could be handled differently (eg., by stopping the
walking at that skb but again). In general, they either
shouldn't happen at all or are rare enough to make no difference
in practice.
In theory this change (as whole) could cause some macroscale
regression (global) because of cache misses that are taken over
the round-trip time but it gets very likely better because of much
less (local) cache misses per other write queue walkers and the
big recovery clearing cumulative ack.
Worth to note that these benefits would be very easy to get also
without TSO/GSO being on as long as the data is in pages so that
we can merge them. Currently I won't let that happen because
DSACK splitting at fragment that would mess up pcounts due to
sk_can_gso in tcp_set_skb_tso_segs. Once DSACKs fragments gets
avoided, we have some conditions that can be made less strict.
TODO: I will probably have to convert the excessive pointer
passing to struct sacktag_state... :-)
My testing revealed that considerable amount of skbs couldn't
be shifted because they were cloned (most likely still awaiting
tx reclaim)...
[The rest is considering future work instead since I got
repeatably EFAULT to tcpdump's recvfrom when I added
pskb_expand_head to deal with clones, so I separated that
into another, later patch]
...To counter that, I gave up on the fifth advantage:
5) When growing previous SACK block, less allocs for new skbs
are done, basically a new alloc is needed only when new hole
is detected and when the previous skb runs out of frags space
...which now only happens of if reclaim is fast enough to dispose
the clone before the SACK block comes in (the window is RTT long),
otherwise we'll have to alloc some.
With clones being handled I got these numbers (will be somewhat
worse without that), taken with fine-grained mibs:
TCPSackShifted 398
TCPSackMerged 877
TCPSackShiftFallback 320
TCPSACKCOLLAPSEFALLBACKGSO 0
TCPSACKCOLLAPSEFALLBACKSKBBITS 0
TCPSACKCOLLAPSEFALLBACKSKBDATA 0
TCPSACKCOLLAPSEFALLBACKBELOW 0
TCPSACKCOLLAPSEFALLBACKFIRST 1
TCPSACKCOLLAPSEFALLBACKPREVBITS 318
TCPSACKCOLLAPSEFALLBACKMSS 1
TCPSACKCOLLAPSEFALLBACKNOHEAD 0
TCPSACKCOLLAPSEFALLBACKSHIFT 0
TCPSACKCOLLAPSENOOPSEQ 0
TCPSACKCOLLAPSENOOPSMALLPCOUNT 0
TCPSACKCOLLAPSENOOPSMALLLEN 0
TCPSACKCOLLAPSEHOLE 12
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-25 13:20:15 +08:00
|
|
|
static inline struct sk_buff *tcp_write_queue_prev(struct sock *sk, struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
return skb_queue_prev(&sk->sk_write_queue, skb);
|
|
|
|
|
}
|
|
|
|
|
|
2007-03-08 04:12:44 +08:00
|
|
|
#define tcp_for_write_queue(skb, sk) \
|
2008-09-23 15:50:13 +08:00
|
|
|
skb_queue_walk(&(sk)->sk_write_queue, skb)
|
2007-03-08 04:12:44 +08:00
|
|
|
|
|
|
|
|
#define tcp_for_write_queue_from(skb, sk) \
|
2008-09-23 15:50:13 +08:00
|
|
|
skb_queue_walk_from(&(sk)->sk_write_queue, skb)
|
2007-03-08 04:12:44 +08:00
|
|
|
|
2007-12-02 06:48:02 +08:00
|
|
|
#define tcp_for_write_queue_from_safe(skb, tmp, sk) \
|
2008-09-23 15:50:13 +08:00
|
|
|
skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp)
|
2007-12-02 06:48:02 +08:00
|
|
|
|
2007-03-08 04:12:44 +08:00
|
|
|
static inline struct sk_buff *tcp_send_head(struct sock *sk)
|
|
|
|
|
{
|
|
|
|
|
return sk->sk_send_head;
|
|
|
|
|
}
|
|
|
|
|
|
2008-09-23 15:50:13 +08:00
|
|
|
static inline bool tcp_skb_is_last(const struct sock *sk,
|
|
|
|
|
const struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
return skb_queue_is_last(&sk->sk_write_queue, skb);
|
|
|
|
|
}
|
|
|
|
|
|
2007-03-08 04:12:44 +08:00
|
|
|
static inline void tcp_advance_send_head(struct sock *sk, struct sk_buff *skb)
|
|
|
|
|
{
|
2008-09-23 15:50:13 +08:00
|
|
|
if (tcp_skb_is_last(sk, skb))
|
2007-03-08 04:12:44 +08:00
|
|
|
sk->sk_send_head = NULL;
|
2008-09-23 15:50:13 +08:00
|
|
|
else
|
|
|
|
|
sk->sk_send_head = tcp_write_queue_next(sk, skb);
|
2007-03-08 04:12:44 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unlinked)
|
|
|
|
|
{
|
|
|
|
|
if (sk->sk_send_head == skb_unlinked)
|
|
|
|
|
sk->sk_send_head = NULL;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void tcp_init_send_head(struct sock *sk)
|
|
|
|
|
{
|
|
|
|
|
sk->sk_send_head = NULL;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void __tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
__skb_queue_tail(&sk->sk_write_queue, skb);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
__tcp_add_write_queue_tail(sk, skb);
|
|
|
|
|
|
|
|
|
|
/* Queue it, remembering where we must start sending. */
|
2007-12-02 06:48:06 +08:00
|
|
|
if (sk->sk_send_head == NULL) {
|
2007-03-08 04:12:44 +08:00
|
|
|
sk->sk_send_head = skb;
|
2007-12-02 06:48:06 +08:00
|
|
|
|
|
|
|
|
if (tcp_sk(sk)->highest_sack == NULL)
|
|
|
|
|
tcp_sk(sk)->highest_sack = skb;
|
|
|
|
|
}
|
2007-03-08 04:12:44 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void __tcp_add_write_queue_head(struct sock *sk, struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
__skb_queue_head(&sk->sk_write_queue, skb);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Insert buff after skb on the write queue of sk. */
|
|
|
|
|
static inline void tcp_insert_write_queue_after(struct sk_buff *skb,
|
|
|
|
|
struct sk_buff *buff,
|
|
|
|
|
struct sock *sk)
|
|
|
|
|
{
|
2008-04-14 15:05:09 +08:00
|
|
|
__skb_queue_after(&sk->sk_write_queue, skb, buff);
|
2007-03-08 04:12:44 +08:00
|
|
|
}
|
|
|
|
|
|
2008-09-22 12:28:51 +08:00
|
|
|
/* Insert new before skb on the write queue of sk. */
|
2007-03-08 04:12:44 +08:00
|
|
|
static inline void tcp_insert_write_queue_before(struct sk_buff *new,
|
|
|
|
|
struct sk_buff *skb,
|
|
|
|
|
struct sock *sk)
|
|
|
|
|
{
|
2008-09-22 12:28:51 +08:00
|
|
|
__skb_queue_before(&sk->sk_write_queue, skb, new);
|
2007-11-20 15:24:09 +08:00
|
|
|
|
|
|
|
|
if (sk->sk_send_head == skb)
|
|
|
|
|
sk->sk_send_head = new;
|
2007-03-08 04:12:44 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk)
|
|
|
|
|
{
|
|
|
|
|
__skb_unlink(skb, &sk->sk_write_queue);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline int tcp_write_queue_empty(struct sock *sk)
|
|
|
|
|
{
|
|
|
|
|
return skb_queue_empty(&sk->sk_write_queue);
|
|
|
|
|
}
|
|
|
|
|
|
2007-11-16 11:41:46 +08:00
|
|
|
/* Start sequence of the highest skb with SACKed bit, valid only if
|
|
|
|
|
* sacked > 0 or when the caller has ensured validity by itself.
|
|
|
|
|
*/
|
|
|
|
|
static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp)
|
|
|
|
|
{
|
|
|
|
|
if (!tp->sacked_out)
|
|
|
|
|
return tp->snd_una;
|
2007-12-02 06:48:06 +08:00
|
|
|
|
|
|
|
|
if (tp->highest_sack == NULL)
|
|
|
|
|
return tp->snd_nxt;
|
|
|
|
|
|
2007-11-16 11:41:46 +08:00
|
|
|
return TCP_SKB_CB(tp->highest_sack)->seq;
|
|
|
|
|
}
|
|
|
|
|
|
2007-12-02 06:48:06 +08:00
|
|
|
static inline void tcp_advance_highest_sack(struct sock *sk, struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
tcp_sk(sk)->highest_sack = tcp_skb_is_last(sk, skb) ? NULL :
|
|
|
|
|
tcp_write_queue_next(sk, skb);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline struct sk_buff *tcp_highest_sack(struct sock *sk)
|
|
|
|
|
{
|
|
|
|
|
return tcp_sk(sk)->highest_sack;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void tcp_highest_sack_reset(struct sock *sk)
|
|
|
|
|
{
|
|
|
|
|
tcp_sk(sk)->highest_sack = tcp_write_queue_head(sk);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Called when old skb is about to be deleted (to be combined with new skb) */
|
|
|
|
|
static inline void tcp_highest_sack_combine(struct sock *sk,
|
|
|
|
|
struct sk_buff *old,
|
|
|
|
|
struct sk_buff *new)
|
|
|
|
|
{
|
|
|
|
|
if (tcp_sk(sk)->sacked_out && (old == tcp_sk(sk)->highest_sack))
|
|
|
|
|
tcp_sk(sk)->highest_sack = new;
|
|
|
|
|
}
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* /proc */
|
|
|
|
|
enum tcp_seq_states {
|
|
|
|
|
TCP_SEQ_STATE_LISTENING,
|
|
|
|
|
TCP_SEQ_STATE_OPENREQ,
|
|
|
|
|
TCP_SEQ_STATE_ESTABLISHED,
|
|
|
|
|
TCP_SEQ_STATE_TIME_WAIT,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct tcp_seq_afinfo {
|
|
|
|
|
char *name;
|
|
|
|
|
sa_family_t family;
|
2008-04-14 13:13:30 +08:00
|
|
|
struct file_operations seq_fops;
|
2008-04-14 13:12:13 +08:00
|
|
|
struct seq_operations seq_ops;
|
2005-04-17 06:20:36 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct tcp_iter_state {
|
2008-04-14 13:11:14 +08:00
|
|
|
struct seq_net_private p;
|
2005-04-17 06:20:36 +08:00
|
|
|
sa_family_t family;
|
|
|
|
|
enum tcp_seq_states state;
|
|
|
|
|
struct sock *syn_wait_sk;
|
|
|
|
|
int bucket, sbucket, num, uid;
|
|
|
|
|
};
|
|
|
|
|
|
2008-03-21 19:14:45 +08:00
|
|
|
extern int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo);
|
|
|
|
|
extern void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-08-16 13:18:02 +08:00
|
|
|
extern struct request_sock_ops tcp_request_sock_ops;
|
2008-02-08 13:49:26 +08:00
|
|
|
extern struct request_sock_ops tcp6_request_sock_ops;
|
2005-08-16 13:18:02 +08:00
|
|
|
|
2008-06-15 08:04:49 +08:00
|
|
|
extern void tcp_v4_destroy_sock(struct sock *sk);
|
2005-08-16 13:18:02 +08:00
|
|
|
|
2006-07-09 04:34:56 +08:00
|
|
|
extern int tcp_v4_gso_send_check(struct sk_buff *skb);
|
2006-06-28 04:22:38 +08:00
|
|
|
extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features);
|
2008-12-16 15:43:36 +08:00
|
|
|
extern struct sk_buff **tcp_gro_receive(struct sk_buff **head,
|
|
|
|
|
struct sk_buff *skb);
|
|
|
|
|
extern struct sk_buff **tcp4_gro_receive(struct sk_buff **head,
|
|
|
|
|
struct sk_buff *skb);
|
|
|
|
|
extern int tcp_gro_complete(struct sk_buff *skb);
|
|
|
|
|
extern int tcp4_gro_complete(struct sk_buff *skb);
|
2006-06-22 18:02:40 +08:00
|
|
|
|
2005-08-16 13:18:02 +08:00
|
|
|
#ifdef CONFIG_PROC_FS
|
|
|
|
|
extern int tcp4_proc_init(void);
|
|
|
|
|
extern void tcp4_proc_exit(void);
|
|
|
|
|
#endif
|
|
|
|
|
|
2006-11-15 11:07:45 +08:00
|
|
|
/* TCP af-specific functions */
|
|
|
|
|
struct tcp_sock_af_ops {
|
|
|
|
|
#ifdef CONFIG_TCP_MD5SIG
|
|
|
|
|
struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk,
|
|
|
|
|
struct sock *addr_sk);
|
|
|
|
|
int (*calc_md5_hash) (char *location,
|
|
|
|
|
struct tcp_md5sig_key *md5,
|
|
|
|
|
struct sock *sk,
|
|
|
|
|
struct request_sock *req,
|
2008-07-19 15:01:42 +08:00
|
|
|
struct sk_buff *skb);
|
2006-11-15 11:07:45 +08:00
|
|
|
int (*md5_add) (struct sock *sk,
|
|
|
|
|
struct sock *addr_sk,
|
|
|
|
|
u8 *newkey,
|
|
|
|
|
u8 len);
|
|
|
|
|
int (*md5_parse) (struct sock *sk,
|
|
|
|
|
char __user *optval,
|
|
|
|
|
int optlen);
|
|
|
|
|
#endif
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct tcp_request_sock_ops {
|
|
|
|
|
#ifdef CONFIG_TCP_MD5SIG
|
|
|
|
|
struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk,
|
|
|
|
|
struct request_sock *req);
|
|
|
|
|
#endif
|
|
|
|
|
};
|
|
|
|
|
|
2008-03-01 03:13:15 +08:00
|
|
|
extern void tcp_v4_init(void);
|
2005-08-16 13:18:02 +08:00
|
|
|
extern void tcp_init(void);
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif /* _TCP_H */
|