tcp.h

Linux Kernel 2.6.9 for OMAP1710

/*
 * 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, <[e-mail]>
 *		Fred N. van Kempen, <[e-mail]>
 *
 *		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

/* Cancel timers, when they are not required. */
#undef TCP_CLEAR_TIMERS

#include <linux/config.h>
#include <linux/list.h>
#include <linux/tcp.h>
#include <linux/slab.h>
#include <linux/cache.h>
#include <linux/percpu.h>
#include <net/checksum.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ip.h>
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
#include <linux/ipv6.h>
#endif
#include <linux/seq_file.h>

/* This is for all connections with a full identity, no wildcards.
 * New scheme, half the table is for TIME_WAIT, the other half is
 * for the rest.  I'll experiment with dynamic table growth later.
 */
struct tcp_ehash_bucket {
	rwlock_t	  lock;
	struct hlist_head chain;
} __attribute__((__aligned__(8)));

/* This is for listening sockets, thus all sockets which possess wildcards. */
#define TCP_LHTABLE_SIZE	32	/* Yes, really, this is all you need. */

/* There are a few simple rules, which allow for local port reuse by
 * an application.  In essence:
 *
 *	1) Sockets bound to different interfaces may share a local port.
 *	   Failing that, goto test 2.
 *	2) If all sockets have sk->sk_reuse set, and none of them are in
 *	   TCP_LISTEN state, the port may be shared.
 *	   Failing that, goto test 3.
 *	3) If all sockets are bound to a specific inet_sk(sk)->rcv_saddr local
 *	   address, and none of them are the same, the port may be
 *	   shared.
 *	   Failing this, the port cannot be shared.
 *
 * The interesting point, is test #2.  This is what an FTP server does
 * all day.  To optimize this case we use a specific flag bit defined
 * below.  As we add sockets to a bind bucket list, we perform a
 * check of: (newsk->sk_reuse && (newsk->sk_state != TCP_LISTEN))
 * As long as all sockets added to a bind bucket pass this test,
 * the flag bit will be set.
 * The resulting situation is that tcp_v[46]_verify_bind() can just check
 * for this flag bit, if it is set and the socket trying to bind has
 * sk->sk_reuse set, we don't even have to walk the owners list at all,
 * we return that it is ok to bind this socket to the requested local port.
 *
 * Sounds like a lot of work, but it is worth it.  In a more naive
 * implementation (ie. current FreeBSD etc.) the entire list of ports
 * must be walked for each data port opened by an ftp server.  Needless
 * to say, this does not scale at all.  With a couple thousand FTP
 * users logged onto your box, isn't it nice to know that new data
 * ports are created in O(1) time?  I thought so. ;-)	-DaveM
 */
struct tcp_bind_bucket {
	unsigned short		port;
	signed short		fastreuse;
	struct hlist_node	node;
	struct hlist_head	owners;
};

#define tb_for_each(tb, node, head) hlist_for_each_entry(tb, node, head, node)

struct tcp_bind_hashbucket {
	spinlock_t		lock;
	struct hlist_head	chain;
};

static inline struct tcp_bind_bucket *__tb_head(struct tcp_bind_hashbucket *head)
{
	return hlist_entry(head->chain.first, struct tcp_bind_bucket, node);
}

static inline struct tcp_bind_bucket *tb_head(struct tcp_bind_hashbucket *head)
{
	return hlist_empty(&head->chain) ? NULL : __tb_head(head);
}

extern struct tcp_hashinfo {
	/* This is for sockets with full identity only.  Sockets here will
	 * always be without wildcards and will have the following invariant:
	 *
	 *          TCP_ESTABLISHED <= sk->sk_state < TCP_CLOSE
	 *
	 * First half of the table is for sockets not in TIME_WAIT, second half
	 * is for TIME_WAIT sockets only.
	 */
	struct tcp_ehash_bucket *__tcp_ehash;

	/* Ok, let's try this, I give up, we do need a local binding
	 * TCP hash as well as the others for fast bind/connect.
	 */
	struct tcp_bind_hashbucket *__tcp_bhash;

	int __tcp_bhash_size;
	int __tcp_ehash_size;

	/* All sockets in TCP_LISTEN state will be in here.  This is the only
	 * table where wildcard'd TCP sockets can exist.  Hash function here
	 * is just local port number.
	 */
	struct hlist_head __tcp_listening_hash[TCP_LHTABLE_SIZE];

	/* All the above members are written once at bootup and
	 * never written again _or_ are predominantly read-access.
	 *
	 * Now align to a new cache line as all the following members
	 * are often dirty.
	 */
	rwlock_t __tcp_lhash_lock ____cacheline_aligned;
	atomic_t __tcp_lhash_users;
	wait_queue_head_t __tcp_lhash_wait;
	spinlock_t __tcp_portalloc_lock;
} tcp_hashinfo;

#define tcp_ehash	(tcp_hashinfo.__tcp_ehash)
#define tcp_bhash	(tcp_hashinfo.__tcp_bhash)
#define tcp_ehash_size	(tcp_hashinfo.__tcp_ehash_size)
#define tcp_bhash_size	(tcp_hashinfo.__tcp_bhash_size)
#define tcp_listening_hash (tcp_hashinfo.__tcp_listening_hash)
#define tcp_lhash_lock	(tcp_hashinfo.__tcp_lhash_lock)
#define tcp_lhash_users	(tcp_hashinfo.__tcp_lhash_users)
#define tcp_lhash_wait	(tcp_hashinfo.__tcp_lhash_wait)
#define tcp_portalloc_lock (tcp_hashinfo.__tcp_portalloc_lock)

extern kmem_cache_t *tcp_bucket_cachep;
extern struct tcp_bind_bucket *tcp_bucket_create(struct tcp_bind_hashbucket *head,
						 unsigned short snum);
extern void tcp_bucket_destroy(struct tcp_bind_bucket *tb);
extern void tcp_bucket_unlock(struct sock *sk);
extern int tcp_port_rover;
extern struct sock *tcp_v4_lookup_listener(u32 addr, unsigned short hnum, int dif);

/* These are AF independent. */
static __inline__ int tcp_bhashfn(__u16 lport)
{
	return (lport & (tcp_bhash_size - 1));
}

extern void tcp_bind_hash(struct sock *sk, struct tcp_bind_bucket *tb,
			  unsigned short snum);

#if (BITS_PER_LONG == 64)
#define TCP_ADDRCMP_ALIGN_BYTES 8
#else
#define TCP_ADDRCMP_ALIGN_BYTES 4
#endif

/* This is a TIME_WAIT bucket.  It works around the memory consumption
 * problems of sockets in such a state on heavily loaded servers, but
 * without violating the protocol specification.
 */
struct tcp_tw_bucket {
	/*
	 * Now struct sock also uses sock_common, so please just
	 * don't add nothing before this first member (__tw_common) --acme
	 */
	struct sock_common	__tw_common;
#define tw_family		__tw_common.skc_family
#define tw_state		__tw_common.skc_state
#define tw_reuse		__tw_common.skc_reuse
#define tw_bound_dev_if		__tw_common.skc_bound_dev_if
#define tw_node			__tw_common.skc_node
#define tw_bind_node		__tw_common.skc_bind_node
#define tw_refcnt		__tw_common.skc_refcnt
	volatile unsigned char	tw_substate;
	unsigned char		tw_rcv_wscale;
	__u16			tw_sport;
	/* Socket demultiplex comparisons on incoming packets. */
	/* these five are in inet_opt */
	__u32			tw_daddr
		__attribute__((aligned(TCP_ADDRCMP_ALIGN_BYTES)));
	__u32			tw_rcv_saddr;
	__u16			tw_dport;
	__u16			tw_num;
	/* And these are ours. */
	int			tw_hashent;
	int			tw_timeout;
	__u32			tw_rcv_nxt;
	__u32			tw_snd_nxt;
	__u32			tw_rcv_wnd;
	__u32			tw_ts_recent;
	long			tw_ts_recent_stamp;
	unsigned long		tw_ttd;
	struct tcp_bind_bucket	*tw_tb;
	struct hlist_node	tw_death_node;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
	struct in6_addr		tw_v6_daddr;
	struct in6_addr		tw_v6_rcv_saddr;
	int			tw_v6_ipv6only;
#endif
};

static __inline__ void tw_add_node(struct tcp_tw_bucket *tw,
				   struct hlist_head *list)
{
	hlist_add_head(&tw->tw_node, list);
}

static __inline__ void tw_add_bind_node(struct tcp_tw_bucket *tw,
					struct hlist_head *list)
{
	hlist_add_head(&tw->tw_bind_node, list);
}

static inline int tw_dead_hashed(struct tcp_tw_bucket *tw)
{
	return tw->tw_death_node.pprev != NULL;
}

static __inline__ void tw_dead_node_init(struct tcp_tw_bucket *tw)
{
	tw->tw_death_node.pprev = NULL;
}

static __inline__ void __tw_del_dead_node(struct tcp_tw_bucket *tw)
{
	__hlist_del(&tw->tw_death_node);
	tw_dead_node_init(tw);
}

static __inline__ int tw_del_dead_node(struct tcp_tw_bucket *tw)
{
	if (tw_dead_hashed(tw)) {
		__tw_del_dead_node(tw);
		return 1;
	}
	return 0;
}

#define tw_for_each(tw, node, head) \
	hlist_for_each_entry(tw, node, head, tw_node)

#define tw_for_each_inmate(tw, node, jail) \
	hlist_for_each_entry(tw, node, jail, tw_death_node)

#define tw_for_each_inmate_safe(tw, node, safe, jail) \
	hlist_for_each_entry_safe(tw, node, safe, jail, tw_death_node)

#define tcptw_sk(__sk)	((struct tcp_tw_bucket *)(__sk))

static inline u32 tcp_v4_rcv_saddr(const struct sock *sk)
{
	return likely(sk->sk_state != TCP_TIME_WAIT) ?
		inet_sk(sk)->rcv_saddr : tcptw_sk(sk)->tw_rcv_saddr;
}

#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
static inline struct in6_addr *__tcp_v6_rcv_saddr(const struct sock *sk)
{
	return likely(sk->sk_state != TCP_TIME_WAIT) ?
		&inet6_sk(sk)->rcv_saddr : &tcptw_sk(sk)->tw_v6_rcv_saddr;
}

static inline struct in6_addr *tcp_v6_rcv_saddr(const struct sock *sk)
{
	return sk->sk_family == AF_INET6 ? __tcp_v6_rcv_saddr(sk) : NULL;
}

#define tcptw_sk_ipv6only(__sk)	(tcptw_sk(__sk)->tw_v6_ipv6only)

static inline int tcp_v6_ipv6only(const struct sock *sk)
{
	return likely(sk->sk_state != TCP_TIME_WAIT) ?
		ipv6_only_sock(sk) : tcptw_sk_ipv6only(sk);
}
#else
# define __tcp_v6_rcv_saddr(__sk)	NULL
# define tcp_v6_rcv_saddr(__sk)		NULL
# define tcptw_sk_ipv6only(__sk)	0
# define tcp_v6_ipv6only(__sk)		0
#endif

extern kmem_cache_t *tcp_timewait_cachep;

static inline void tcp_tw_put(struct tcp_tw_bucket *tw)
{
	if (atomic_dec_and_test(&tw->tw_refcnt)) {
#ifdef INET_REFCNT_DEBUG
		printk(KERN_DEBUG "tw_bucket %p released\n", tw);
#endif
		kmem_cache_free(tcp_timewait_cachep, tw);
	}
}

extern atomic_t tcp_orphan_count;
extern int tcp_tw_count;
extern void tcp_time_wait(struct sock *sk, int state, int timeo);
extern void tcp_tw_schedule(struct tcp_tw_bucket *tw, int timeo);
extern void tcp_tw_deschedule(struct tcp_tw_bucket *tw);


/* Socket demux engine toys. */
#ifdef __BIG_ENDIAN
#define TCP_COMBINED_PORTS(__sport, __dport) \
	(((__u32)(__sport)<<16) | (__u32)(__dport))
#else /* __LITTLE_ENDIAN */
#define TCP_COMBINED_PORTS(__sport, __dport) \
	(((__u32)(__dport)<<16) | (__u32)(__sport))
#endif

#if (BITS_PER_LONG == 64)
#ifdef __BIG_ENDIAN
#define TCP_V4_ADDR_COOKIE(__name, __saddr, __daddr) \
	__u64 __name = (((__u64)(__saddr))<<32)|((__u64)(__daddr));
#else /* __LITTLE_ENDIAN */
#define TCP_V4_ADDR_COOKIE(__name, __saddr, __daddr) \
	__u64 __name = (((__u64)(__daddr))<<32)|((__u64)(__saddr));
#endif /* __BIG_ENDIAN */
#define TCP_IPV4_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\
	(((*((__u64 *)&(inet_sk(__sk)->daddr)))== (__cookie))	&&	\
	 ((*((__u32 *)&(inet_sk(__sk)->dport)))== (__ports))	&&	\
	 (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
#define TCP_IPV4_TW_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\
	(((*((__u64 *)&(tcptw_sk(__sk)->tw_daddr))) == (__cookie)) &&	\
	 ((*((__u32 *)&(tcptw_sk(__sk)->tw_dport))) == (__ports)) &&	\
	 (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
#else /* 32-bit arch */
#define TCP_V4_ADDR_COOKIE(__name, __saddr, __daddr)
#define TCP_IPV4_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\
	((inet_sk(__sk)->daddr			== (__saddr))	&&	\
	 (inet_sk(__sk)->rcv_saddr		== (__daddr))	&&	\
	 ((*((__u32 *)&(inet_sk(__sk)->dport)))== (__ports))	&&	\
	 (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
#define TCP_IPV4_TW_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\
	((tcptw_sk(__sk)->tw_daddr		== (__saddr))	&&	\
	 (tcptw_sk(__sk)->tw_rcv_saddr		== (__daddr))	&&	\
	 ((*((__u32 *)&(tcptw_sk(__sk)->tw_dport))) == (__ports)) &&	\
	 (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
#endif /* 64-bit arch */

#define TCP_IPV6_MATCH(__sk, __saddr, __daddr, __ports, __dif)	   \
	(((*((__u32 *)&(inet_sk(__sk)->dport)))== (__ports))   	&& \
	 ((__sk)->sk_family		== AF_INET6)		&& \
	 !ipv6_addr_cmp(&inet6_sk(__sk)->daddr, (__saddr))	&& \
	 !ipv6_addr_cmp(&inet6_sk(__sk)->rcv_saddr, (__daddr))	&& \
	 (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))

/* These can have wildcards, don't try too hard. */
static __inline__ int tcp_lhashfn(unsigned short num)
{
	return num & (TCP_LHTABLE_SIZE - 1);
}

static __inline__ int tcp_sk_listen_hashfn(struct sock *sk)
{
	return tcp_lhashfn(inet_sk(sk)->num);
}

#define MAX_TCP_HEADER	(128 + MAX_HEADER)

/* 
 * 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

/* 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 minumum	*/

#define TCP_SYNACK_RETRIES 5	/* number of times to retry passive opening a
				 * connection: ~180sec is RFC minumum	*/


#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_SYNQ_HSIZE		512	/* Size of SYNACK hash table */

#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.
					 */

#define TCP_TW_RECYCLE_SLOTS_LOG	5
#define TCP_TW_RECYCLE_SLOTS		(1<<TCP_TW_RECYCLE_SLOTS_LOG)

/* If time > 4sec, it is "slow" path, no recycling is required,
   so that we select tick to get range about 4 seconds.
 */

#if HZ <= 16 || HZ > 4096
# error Unsupported: HZ <= 16 or HZ > 4096
#elif HZ <= 32
# define TCP_TW_RECYCLE_TICK (5+2-TCP_TW_RECYCLE_SLOTS_LOG)
#elif HZ <= 64
# define TCP_TW_RECYCLE_TICK (6+2-TCP_TW_RECYCLE_SLOTS_LOG)
#elif HZ <= 128
# define TCP_TW_RECYCLE_TICK (7+2-TCP_TW_RECYCLE_SLOTS_LOG)
#elif HZ <= 256
# define TCP_TW_RECYCLE_TICK (8+2-TCP_TW_RECYCLE_SLOTS_LOG)
#elif HZ <= 512
# define TCP_TW_RECYCLE_TICK (9+2-TCP_TW_RECYCLE_SLOTS_LOG)
#elif HZ <= 1024
# define TCP_TW_RECYCLE_TICK (10+2-TCP_TW_RECYCLE_SLOTS_LOG)
#elif HZ <= 2048
# define TCP_TW_RECYCLE_TICK (11+2-TCP_TW_RECYCLE_SLOTS_LOG)
#else
# define TCP_TW_RECYCLE_TICK (12+2-TCP_TW_RECYCLE_SLOTS_LOG)
#endif

#define BICTCP_1_OVER_BETA	8	/*
					 * Fast recovery
					 * multiplicative decrease factor
					 */
#define BICTCP_MAX_INCREMENT 32		/*
					 * Limit on the amount of
					 * increment allowed during