linux/include/net/tcp.h

1540 lines
46 KiB
C
Raw Normal View History

/*
* 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
*
* Authors: Ross Biro
* 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>
#include <linux/skbuff.h>
#include <linux/dmaengine.h>
#include <linux/crypto.h>
#include <linux/cryptohash.h>
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 02:17:05 +08:00
#include <linux/kref.h>
#include <net/inet_connection_sock.h>
#include <net/inet_timewait_sock.h>
#include <net/inet_hashtables.h>
#include <net/checksum.h>
#include <net/request_sock.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ip.h>
#include <net/tcp_states.h>
#include <net/inet_ecn.h>
#include <net/dst.h>
#include <linux/seq_file.h>
extern struct inet_hashinfo tcp_hashinfo;
extern struct percpu_counter tcp_orphan_count;
extern void tcp_time_wait(struct sock *sk, int state, int timeo);
#define MAX_TCP_HEADER (128 + MAX_HEADER)
#define MAX_TCP_OPTION_SPACE 40
/*
* Never offer a window over 32767 without using window scaling. Some
* poor stacks do signed 16bit maths!
*/
#define MAX_TCP_WINDOW 32767U
TCP: increase default initial receive window. This patch changes the default initial receive window to 10 mss (defined constant). The default window is limited to the maximum of 10*1460 and 2*mss (when mss > 1460). draft-ietf-tcpm-initcwnd-00 is a proposal to the IETF that recommends increasing TCP's initial congestion window to 10 mss or about 15KB. Leading up to this proposal were several large-scale live Internet experiments with an initial congestion window of 10 mss (IW10), where we showed that the average latency of HTTP responses improved by approximately 10%. This was accompanied by a slight increase in retransmission rate (0.5%), most of which is coming from applications opening multiple simultaneous connections. To understand the extreme worst case scenarios, and fairness issues (IW10 versus IW3), we further conducted controlled testbed experiments. We came away finding minimal negative impact even under low link bandwidths (dial-ups) and small buffers. These results are extremely encouraging to adopting IW10. However, an initial congestion window of 10 mss is useless unless a TCP receiver advertises an initial receive window of at least 10 mss. Fortunately, in the large-scale Internet experiments we found that most widely used operating systems advertised large initial receive windows of 64KB, allowing us to experiment with a wide range of initial congestion windows. Linux systems were among the few exceptions that advertised a small receive window of 6KB. The purpose of this patch is to fix this shortcoming. References: 1. A comprehensive list of all IW10 references to date. http://code.google.com/speed/protocols/tcpm-IW10.html 2. Paper describing results from large-scale Internet experiments with IW10. http://ccr.sigcomm.org/drupal/?q=node/621 3. Controlled testbed experiments under worst case scenarios and a fairness study. http://www.ietf.org/proceedings/79/slides/tcpm-0.pdf 4. Raw test data from testbed experiments (Linux senders/receivers) with initial congestion and receive windows of both 10 mss. http://research.csc.ncsu.edu/netsrv/?q=content/iw10 5. Internet-Draft. Increasing TCP's Initial Window. https://datatracker.ietf.org/doc/draft-ietf-tcpm-initcwnd/ Signed-off-by: Nandita Dukkipati <nanditad@google.com> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-20 22:15:56 +08:00
/* Offer an initial receive window of 10 mss. */
#define TCP_DEFAULT_INIT_RCVWND 10
/* Minimal accepted MSS. It is (60+60+8) - (20+20). */
#define TCP_MIN_MSS 88U
/* The least MTU to use for probing */
#define TCP_BASE_MSS 512
/* 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
* connection: ~180sec is RFC minimum */
#define TCP_SYNACK_RETRIES 5 /* number of times to retry passive opening a
* connection: ~180sec is RFC minimum */
#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)(1*HZ)) /* RFC2988bis initial RTO value */
#define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value, now
* used as a fallback RTO for the
* initial data transmission if no
* valid RTT sample has been acquired,
* most likely due to retrans in 3WHS.
*/
#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 */
#define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 02:17:05 +08:00
#define TCPOPT_COOKIE 253 /* Cookie extension (experimental) */
/*
* TCP option lengths
*/
#define TCPOLEN_MSS 4
#define TCPOLEN_WINDOW 3
#define TCPOLEN_SACK_PERM 2
#define TCPOLEN_TIMESTAMP 10
#define TCPOLEN_MD5SIG 18
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 02:17:05 +08:00
#define TCPOLEN_COOKIE_BASE 2 /* Cookie-less header extension */
#define TCPOLEN_COOKIE_PAIR 3 /* Cookie pair header extension */
#define TCPOLEN_COOKIE_MIN (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MIN)
#define TCPOLEN_COOKIE_MAX (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MAX)
/* 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
#define TCPOLEN_MD5SIG_ALIGNED 20
#define TCPOLEN_MSS_ALIGNED 4
/* Flags in tp->nonagle */
#define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */
#define TCP_NAGLE_CORK 2 /* Socket is corked */
#define TCP_NAGLE_PUSH 4 /* Cork is overridden for already queued data */
/* TCP thin-stream limits */
#define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */
/* TCP initial congestion window as per draft-hkchu-tcpm-initcwnd-01 */
#define TCP_INIT_CWND 10
extern struct inet_timewait_death_row tcp_death_row;
/* 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 long 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;
extern int sysctl_tcp_frto_response;
extern int sysctl_tcp_low_latency;
extern int sysctl_tcp_dma_copybreak;
extern int sysctl_tcp_nometrics_save;
extern int sysctl_tcp_moderate_rcvbuf;
extern int sysctl_tcp_tso_win_divisor;
extern int sysctl_tcp_abc;
extern int sysctl_tcp_mtu_probing;
extern int sysctl_tcp_base_mss;
extern int sysctl_tcp_workaround_signed_windows;
extern int sysctl_tcp_slow_start_after_idle;
extern int sysctl_tcp_max_ssthresh;
extern int sysctl_tcp_cookie_size;
extern int sysctl_tcp_thin_linear_timeouts;
extern int sysctl_tcp_thin_dupack;
extern atomic_long_t tcp_memory_allocated;
extern struct percpu_counter tcp_sockets_allocated;
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)
{
return (__s32)(seq1-seq2) < 0;
}
#define after(seq2, seq1) before(seq1, seq2)
/* is s2<=s1<=s3 ? */
static inline int between(__u32 seq1, __u32 seq2, __u32 seq3)
{
return seq3 - seq2 >= seq1 - seq2;
}
static inline bool tcp_too_many_orphans(struct sock *sk, int shift)
{
struct percpu_counter *ocp = sk->sk_prot->orphan_count;
int orphans = percpu_counter_read_positive(ocp);
if (orphans << shift > sysctl_tcp_max_orphans) {
orphans = percpu_counter_sum_positive(ocp);
if (orphans << shift > sysctl_tcp_max_orphans)
return true;
}
if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
atomic_long_read(&tcp_memory_allocated) > sysctl_tcp_mem[2])
return true;
return false;
}
/* syncookies: remember time of last synqueue overflow */
static inline void tcp_synq_overflow(struct sock *sk)
{
tcp_sk(sk)->rx_opt.ts_recent_stamp = jiffies;
}
/* syncookies: no recent synqueue overflow on this listening socket? */
static inline int tcp_synq_no_recent_overflow(const struct sock *sk)
{
unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
return time_after(jiffies, last_overflow + TCP_TIMEOUT_FALLBACK);
}
extern struct proto tcp_prot;
#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)
#define TCP_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val)
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 struct inet_peer *tcp_v4_get_peer(struct sock *sk, bool *release_it);
extern void *tcp_v4_tw_get_peer(struct sock *sk);
extern int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t size);
extern int tcp_sendpage(struct sock *sk, 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);
extern void tcp_cleanup_rbuf(struct sock *sk, int copied);
extern int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp);
extern void tcp_twsk_destructor(struct sock *sk);
extern ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags);
static inline void tcp_dec_quickack_mode(struct sock *sk,
const unsigned int pkts)
{
struct inet_connection_sock *icsk = inet_csk(sk);
if (icsk->icsk_ack.quick) {
if (pkts >= icsk->icsk_ack.quick) {
icsk->icsk_ack.quick = 0;
/* Leaving quickack mode we deflate ATO. */
icsk->icsk_ack.ato = TCP_ATO_MIN;
} else
icsk->icsk_ack.quick -= pkts;
}
}
#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;
}
enum tcp_tw_status {
TCP_TW_SUCCESS = 0,
TCP_TW_RST = 1,
TCP_TW_ACK = 2,
TCP_TW_SYN = 3
};
extern enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw,
struct sk_buff *skb,
const struct tcphdr *th);
extern struct sock * tcp_check_req(struct sock *sk,struct sk_buff *skb,
struct request_sock *req,
struct request_sock **prev);
extern int tcp_child_process(struct sock *parent, struct sock *child,
struct sk_buff *skb);
extern int tcp_use_frto(struct sock *sk);
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, unsigned int optlen);
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, unsigned int optlen);
extern void tcp_set_keepalive(struct sock *sk, int val);
extern void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req);
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, u8 **hvpp,
int estab);
extern u8 *tcp_parse_md5sig_option(struct tcphdr *th);
/*
* TCP v4 functions exported for the inet6 API
*/
extern void tcp_v4_send_check(struct sock *sk, 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,
struct request_sock *req,
struct sk_buff *skb);
extern struct sock * tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
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,
struct request_sock *req,
struct request_values *rvp);
extern int tcp_disconnect(struct sock *sk, int flags);
/* From syncookies.c */
extern __u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS];
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);
extern __u32 cookie_init_timestamp(struct request_sock *req);
extern bool cookie_check_timestamp(struct tcp_options_received *opt, bool *);
/* 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);
/* 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);
extern int tcp_retransmit_skb(struct sock *, struct sk_buff *);
extern void tcp_retransmit_timer(struct sock *sk);
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);
extern int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int);
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);
extern void tcp_send_active_reset(struct sock *sk, gfp_t priority);
extern int tcp_send_synack(struct sock *);
extern void tcp_push_one(struct sock *, unsigned int mss_now);
extern void tcp_send_ack(struct sock *sk);
extern void tcp_send_delayed_ack(struct sock *sk);
/* tcp_input.c */
extern void tcp_cwnd_application_limited(struct sock *sk);
/* tcp_timer.c */
extern void tcp_init_xmit_timers(struct sock *);
static inline void tcp_clear_xmit_timers(struct sock *sk)
{
inet_csk_clear_xmit_timers(sk);
}
extern unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
extern unsigned int tcp_current_mss(struct sock *sk);
/* Bound MSS / TSO packet size with the half of the window */
static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize)
{
int cutoff;
/* When peer uses tiny windows, there is no use in packetizing
* to sub-MSS pieces for the sake of SWS or making sure there
* are enough packets in the pipe for fast recovery.
*
* On the other hand, for extremely large MSS devices, handling
* smaller than MSS windows in this way does make sense.
*/
if (tp->max_window >= 512)
cutoff = (tp->max_window >> 1);
else
cutoff = tp->max_window;
if (cutoff && pktsize > cutoff)
return max_t(int, cutoff, 68U - tp->tcp_header_len);
else
return pktsize;
}
/* tcp.c */
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);
extern void tcp_initialize_rcv_mss(struct sock *sk);
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);
extern void tcp_valid_rtt_meas(struct sock *sk, u32 seq_rtt);
static inline void tcp_bound_rto(const struct sock *sk)
{
if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX)
inet_csk(sk)->icsk_rto = TCP_RTO_MAX;
}
static inline u32 __tcp_set_rto(const struct tcp_sock *tp)
{
return (tp->srtt >> 3) + tp->rttvar;
}
static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
{
tp->pred_flags = htonl((tp->tcp_header_len << 26) |
ntohl(TCP_FLAG_ACK) |
snd_wnd);
}
static inline void tcp_fast_path_on(struct tcp_sock *tp)
{
__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)
{
[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);
if (skb_queue_empty(&tp->out_of_order_queue) &&
tp->rcv_wnd &&
atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
!tp->urg_data)
tcp_fast_path_on(tp);
}
/* Compute the actual rto_min value */
static inline u32 tcp_rto_min(struct sock *sk)
{
struct dst_entry *dst = __sk_dst_get(sk);
u32 rto_min = TCP_RTO_MIN;
if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
return rto_min;
}
/* 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.
*/
static inline u32 tcp_receive_window(const struct tcp_sock *tp)
{
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
* of jiffies in the buffer control blocks below. We decided
* to use only the low 32-bits of jiffies and hide the ugly
* casts with the following macro.
*/
#define tcp_time_stamp ((__u32)(jiffies))
#define tcp_flag_byte(th) (((u_int8_t *)th)[13])
#define TCPHDR_FIN 0x01
#define TCPHDR_SYN 0x02
#define TCPHDR_RST 0x04
#define TCPHDR_PSH 0x08
#define TCPHDR_ACK 0x10
#define TCPHDR_URG 0x20
#define TCPHDR_ECE 0x40
#define TCPHDR_CWR 0x80
/* This is what the send packet queuing engine uses to pass
* TCP per-packet control information to the transmission code.
* We also store the host-order sequence numbers in here too.
* This is 44 bytes if IPV6 is enabled.
* 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. */
__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)
{
return skb_shinfo(skb)->gso_segs;
}
/* This is valid iff tcp_skb_pcount() > 1. */
static inline int tcp_skb_mss(const struct sk_buff *skb)
{
return skb_shinfo(skb)->gso_size;
}
/* 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
#define TCP_CA_MAX 128
#define TCP_CA_BUF_MAX (TCP_CA_NAME_MAX*TCP_CA_MAX)
#define TCP_CONG_NON_RESTRICTED 0x1
#define TCP_CONG_RTT_STAMP 0x2
struct tcp_congestion_ops {
struct list_head list;
unsigned long flags;
/* initialize private data (optional) */
void (*init)(struct sock *sk);
/* cleanup private data (optional) */
void (*release)(struct sock *sk);
/* return slow start threshold (required) */
u32 (*ssthresh)(struct sock *sk);
/* lower bound for congestion window (optional) */
u32 (*min_cwnd)(const struct sock *sk);
/* do new cwnd calculation (required) */
void (*cong_avoid)(struct sock *sk, u32 ack, u32 in_flight);
/* call before changing ca_state (optional) */
void (*set_state)(struct sock *sk, u8 new_state);
/* call when cwnd event occurs (optional) */
void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);
/* new value of cwnd after loss (optional) */
u32 (*undo_cwnd)(struct sock *sk);
/* hook for packet ack accounting (optional) */
void (*pkts_acked)(struct sock *sk, u32 num_acked, s32 rtt_us);
/* get info for inet_diag (optional) */
void (*get_info)(struct sock *sk, u32 ext, struct sk_buff *skb);
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);
extern void tcp_init_congestion_control(struct sock *sk);
extern void tcp_cleanup_congestion_control(struct sock *sk);
extern int tcp_set_default_congestion_control(const char *name);
extern void tcp_get_default_congestion_control(char *name);
extern void tcp_get_available_congestion_control(char *buf, size_t len);
extern void tcp_get_allowed_congestion_control(char *buf, size_t len);
extern int tcp_set_allowed_congestion_control(char *allowed);
extern int tcp_set_congestion_control(struct sock *sk, const char *name);
extern void tcp_slow_start(struct tcp_sock *tp);
extern void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w);
extern struct tcp_congestion_ops tcp_init_congestion_ops;
extern u32 tcp_reno_ssthresh(struct sock *sk);
extern void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight);
extern u32 tcp_reno_min_cwnd(const struct sock *sk);
extern struct tcp_congestion_ops tcp_reno;
static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
{
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;
}
static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
if (icsk->icsk_ca_ops->cwnd_event)
icsk->icsk_ca_ops->cwnd_event(sk, event);
}
/* 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;
}
static inline unsigned int tcp_left_out(const struct tcp_sock *tp)
{
return tp->sacked_out + tp->lost_out;
}
/* 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"
*/
static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
{
return tp->packets_out - tcp_left_out(tp) + tp->retrans_out;
}
#define TCP_INFINITE_SSTHRESH 0x7fffffff
static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp)
{
return tp->snd_ssthresh >= TCP_INFINITE_SSTHRESH;
}
/* 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.
*/
static inline __u32 tcp_current_ssthresh(const struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
if ((1 << inet_csk(sk)->icsk_ca_state) & (TCPF_CA_CWR | TCPF_CA_Recovery))
return tp->snd_ssthresh;
else
return max(tp->snd_ssthresh,
((tp->snd_cwnd >> 1) +
(tp->snd_cwnd >> 2)));
}
/* 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)
extern void tcp_enter_cwr(struct sock *sk, const int set_ssthresh);
extern __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst);
/* Slow start with delack produces 3 packets of burst, so that
* 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.
*/
static __inline__ __u32 tcp_max_burst(const struct tcp_sock *tp)
{
return tp->reordering;
}
/* 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);
static inline void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss,
const struct sk_buff *skb)
{
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)
{
[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);
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
if (!tp->packets_out && !icsk->icsk_pending)
inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
icsk->icsk_rto, TCP_RTO_MAX);
}
static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq)
{
tp->snd_wl1 = seq;
}
static inline void tcp_update_wl(struct tcp_sock *tp, u32 seq)
{
tp->snd_wl1 = seq;
}
/*
* Calculate(/check) TCP checksum
*/
static inline __sum16 tcp_v4_check(int len, __be32 saddr,
__be32 daddr, __wsum base)
{
return csum_tcpudp_magic(saddr,daddr,len,IPPROTO_TCP,base);
}
static inline __sum16 __tcp_checksum_complete(struct sk_buff *skb)
{
return __skb_checksum_complete(skb);
}
static inline int tcp_checksum_complete(struct sk_buff *skb)
{
return !skb_csum_unnecessary(skb) &&
__tcp_checksum_complete(skb);
}
/* Prequeue for VJ style copy to user, combined with checksumming. */
static inline void tcp_prequeue_init(struct tcp_sock *tp)
{
tp->ucopy.task = NULL;
tp->ucopy.len = 0;
tp->ucopy.memory = 0;
skb_queue_head_init(&tp->ucopy.prequeue);
#ifdef CONFIG_NET_DMA
tp->ucopy.dma_chan = NULL;
tp->ucopy.wakeup = 0;
tp->ucopy.pinned_list = NULL;
tp->ucopy.dma_cookie = 0;
#endif
}
/* 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?
*/
static inline int tcp_prequeue(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
if (sysctl_tcp_low_latency || !tp->ucopy.task)
return 0;
__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) {
sk_backlog_rcv(sk, skb1);
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPPREQUEUEDROPPED);
}
tp->ucopy.memory = 0;
} else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
wake_up_interruptible_sync_poll(sk_sleep(sk),
POLLIN | POLLRDNORM | POLLRDBAND);
if (!inet_csk_ack_scheduled(sk))
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
(3 * tcp_rto_min(sk)) / 4,
TCP_RTO_MAX);
}
return 1;
}
#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
extern void tcp_set_state(struct sock *sk, int state);
extern void tcp_done(struct sock *sk);
static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
{
rx_opt->dsack = 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,
__u32 init_rcv_wnd);
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);
}
static inline void tcp_openreq_init(struct request_sock *req,
struct tcp_options_received *rx_opt,
struct sk_buff *skb)
{
struct inet_request_sock *ireq = inet_rsk(req);
req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */
req->cookie_ts = 0;
tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq;
req->mss = rx_opt->mss_clamp;
req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0;
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;
ireq->rmt_port = tcp_hdr(skb)->source;
ireq->loc_port = tcp_hdr(skb)->dest;
}
extern void tcp_enter_memory_pressure(struct sock *sk);
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;
}
static inline int keepalive_probes(const struct tcp_sock *tp)
{
return tp->keepalive_probes ? : sysctl_tcp_keepalive_probes;
}
static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp)
{
const struct inet_connection_sock *icsk = &tp->inet_conn;
return min_t(u32, tcp_time_stamp - icsk->icsk_ack.lrcvtime,
tcp_time_stamp - tp->rcv_tstamp);
}
static inline int tcp_fin_time(const struct sock *sk)
{
int fin_timeout = tcp_sk(sk)->linger2 ? : sysctl_tcp_fin_timeout;
const int rto = inet_csk(sk)->icsk_rto;
if (fin_timeout < (rto << 2) - (rto >> 1))
fin_timeout = (rto << 2) - (rto >> 1);
return fin_timeout;
}
static inline int tcp_paws_check(const struct tcp_options_received *rx_opt,
int paws_win)
{
if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win)
return 1;
if (unlikely(get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS))
return 1;
/*
* Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0,
* then following tcp messages have valid values. Ignore 0 value,
* or else 'negative' tsval might forbid us to accept their packets.
*/
if (!rx_opt->ts_recent)
return 1;
return 0;
}
static inline int tcp_paws_reject(const struct tcp_options_received *rx_opt,
int rst)
{
if (tcp_paws_check(rx_opt, 0))
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.
*/
if (rst && get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_MSL)
return 0;
return 1;
}
static inline void tcp_mib_init(struct net *net)
{
/* See RFC 2012 */
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);
}
/* from STCP */
static inline void tcp_clear_retrans_hints_partial(struct tcp_sock *tp)
{
tp->lost_skb_hint = NULL;
tp->scoreboard_skb_hint = NULL;
}
static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp)
{
tcp_clear_retrans_hints_partial(tp);
tp->retransmit_skb_hint = NULL;
}
/* MD5 Signature */
struct crypto_hash;
/* - key database */
struct tcp_md5sig_key {
u8 *key;
u8 keylen;
};
struct tcp4_md5sig_key {
struct tcp_md5sig_key base;
__be32 addr;
};
struct tcp6_md5sig_key {
struct tcp_md5sig_key base;
#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;
};
/* - functions */
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);
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, __be32 addr);
#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
extern struct tcp_md5sig_pool * __percpu *tcp_alloc_md5sig_pool(struct sock *);
extern void tcp_free_md5sig_pool(void);
extern struct tcp_md5sig_pool *tcp_get_md5sig_pool(void);
extern void tcp_put_md5sig_pool(void);
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);
/* 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)
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 16:11:19 +08:00
sk_wmem_free_skb(sk, skb);
sk_mem_reclaim(sk);
tcp_clear_all_retrans_hints(tcp_sk(sk));
}
static inline struct sk_buff *tcp_write_queue_head(struct sock *sk)
{
return skb_peek(&sk->sk_write_queue);
}
static inline struct sk_buff *tcp_write_queue_tail(struct sock *sk)
{
return skb_peek_tail(&sk->sk_write_queue);
}
static inline struct sk_buff *tcp_write_queue_next(struct sock *sk, struct sk_buff *skb)
{
return skb_queue_next(&sk->sk_write_queue, skb);
}
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);
}
#define tcp_for_write_queue(skb, sk) \
skb_queue_walk(&(sk)->sk_write_queue, skb)
#define tcp_for_write_queue_from(skb, sk) \
skb_queue_walk_from(&(sk)->sk_write_queue, skb)
#define tcp_for_write_queue_from_safe(skb, tmp, sk) \
skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp)
static inline struct sk_buff *tcp_send_head(struct sock *sk)
{
return sk->sk_send_head;
}
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);
}
static inline void tcp_advance_send_head(struct sock *sk, struct sk_buff *skb)
{
if (tcp_skb_is_last(sk, skb))
sk->sk_send_head = NULL;
else
sk->sk_send_head = tcp_write_queue_next(sk, skb);
}
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. */
if (sk->sk_send_head == NULL) {
sk->sk_send_head = skb;
if (tcp_sk(sk)->highest_sack == NULL)
tcp_sk(sk)->highest_sack = skb;
}
}
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)
{
__skb_queue_after(&sk->sk_write_queue, skb, buff);
}
/* Insert new before skb on the write queue of sk. */
static inline void tcp_insert_write_queue_before(struct sk_buff *new,
struct sk_buff *skb,
struct sock *sk)
{
__skb_queue_before(&sk->sk_write_queue, skb, new);
if (sk->sk_send_head == skb)
sk->sk_send_head = new;
}
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);
}
static inline void tcp_push_pending_frames(struct sock *sk)
{
if (tcp_send_head(sk)) {
struct tcp_sock *tp = tcp_sk(sk);
__tcp_push_pending_frames(sk, tcp_current_mss(sk), tp->nonagle);
}
}
/* 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;
if (tp->highest_sack == NULL)
return tp->snd_nxt;
return TCP_SKB_CB(tp->highest_sack)->seq;
}
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;
}
/* Determines whether this is a thin stream (which may suffer from
* increased latency). Used to trigger latency-reducing mechanisms.
*/
static inline unsigned int tcp_stream_is_thin(struct tcp_sock *tp)
{
return tp->packets_out < 4 && !tcp_in_initial_slowstart(tp);
}
/* /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;
struct file_operations seq_fops;
struct seq_operations seq_ops;
};
struct tcp_iter_state {
struct seq_net_private p;
sa_family_t family;
enum tcp_seq_states state;
struct sock *syn_wait_sk;
int bucket, offset, sbucket, num, uid;
loff_t last_pos;
};
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);
extern struct request_sock_ops tcp_request_sock_ops;
extern struct request_sock_ops tcp6_request_sock_ops;
extern void tcp_v4_destroy_sock(struct sock *sk);
extern int tcp_v4_gso_send_check(struct sk_buff *skb);
extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features);
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);
#ifdef CONFIG_PROC_FS
extern int tcp4_proc_init(void);
extern void tcp4_proc_exit(void);
#endif
/* 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,
struct sk_buff *skb);
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);
int (*calc_md5_hash) (char *location,
struct tcp_md5sig_key *md5,
struct sock *sk,
struct request_sock *req,
struct sk_buff *skb);
#endif
};
/* Using SHA1 for now, define some constants.
*/
#define COOKIE_DIGEST_WORDS (SHA_DIGEST_WORDS)
#define COOKIE_MESSAGE_WORDS (SHA_MESSAGE_BYTES / 4)
#define COOKIE_WORKSPACE_WORDS (COOKIE_DIGEST_WORDS + COOKIE_MESSAGE_WORDS)
extern int tcp_cookie_generator(u32 *bakery);
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 02:17:05 +08:00
/**
* struct tcp_cookie_values - each socket needs extra space for the
* cookies, together with (optional) space for any SYN data.
*
* A tcp_sock contains a pointer to the current value, and this is
* cloned to the tcp_timewait_sock.
*
* @cookie_pair: variable data from the option exchange.
*
* @cookie_desired: user specified tcpct_cookie_desired. Zero
* indicates default (sysctl_tcp_cookie_size).
* After cookie sent, remembers size of cookie.
* Range 0, TCP_COOKIE_MIN to TCP_COOKIE_MAX.
*
* @s_data_desired: user specified tcpct_s_data_desired. When the
* constant payload is specified (@s_data_constant),
* holds its length instead.
* Range 0 to TCP_MSS_DESIRED.
*
* @s_data_payload: constant data that is to be included in the
* payload of SYN or SYNACK segments when the
* cookie option is present.
*/
struct tcp_cookie_values {
struct kref kref;
u8 cookie_pair[TCP_COOKIE_PAIR_SIZE];
u8 cookie_pair_size;
u8 cookie_desired;
u16 s_data_desired:11,
s_data_constant:1,
s_data_in:1,
s_data_out:1,
s_data_unused:2;
u8 s_data_payload[0];
};
static inline void tcp_cookie_values_release(struct kref *kref)
{
kfree(container_of(kref, struct tcp_cookie_values, kref));
}
/* The length of constant payload data. Note that s_data_desired is
* overloaded, depending on s_data_constant: either the length of constant
* data (returned here) or the limit on variable data.
*/
static inline int tcp_s_data_size(const struct tcp_sock *tp)
{
return (tp->cookie_values != NULL && tp->cookie_values->s_data_constant)
? tp->cookie_values->s_data_desired
: 0;
}
/**
* struct tcp_extend_values - tcp_ipv?.c to tcp_output.c workspace.
*
* As tcp_request_sock has already been extended in other places, the
* only remaining method is to pass stack values along as function
* parameters. These parameters are not needed after sending SYNACK.
*
* @cookie_bakery: cryptographic secret and message workspace.
*
* @cookie_plus: bytes in authenticator/cookie option, copied from
* struct tcp_options_received (above).
*/
struct tcp_extend_values {
struct request_values rv;
u32 cookie_bakery[COOKIE_WORKSPACE_WORDS];
u8 cookie_plus:6,
cookie_out_never:1,
cookie_in_always:1;
};
static inline struct tcp_extend_values *tcp_xv(struct request_values *rvp)
{
return (struct tcp_extend_values *)rvp;
}
extern void tcp_v4_init(void);
extern void tcp_init(void);
#endif /* _TCP_H */