[IPSEC]: Add ICMP host relookup support

[net-next-2.6.git] / include / net / sock.h

/*
 * 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 AF_INET socket handler.
 *
 * Version:	@(#)sock.h	1.0.4	05/13/93
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Corey Minyard <wf-rch!minyard@relay.EU.net>
 *		Florian La Roche <flla@stud.uni-sb.de>
 *
 * Fixes:
 *		Alan Cox	:	Volatiles in skbuff pointers. See
 *					skbuff comments. May be overdone,
 *					better to prove they can be removed
 *					than the reverse.
 *		Alan Cox	:	Added a zapped field for tcp to note
 *					a socket is reset and must stay shut up
 *		Alan Cox	:	New fields for options
 *	Pauline Middelink	:	identd support
 *		Alan Cox	:	Eliminate low level recv/recvfrom
 *		David S. Miller	:	New socket lookup architecture.
 *              Steve Whitehouse:       Default routines for sock_ops
 *              Arnaldo C. Melo :	removed net_pinfo, tp_pinfo and made
 *              			protinfo be just a void pointer, as the
 *              			protocol specific parts were moved to
 *              			respective headers and ipv4/v6, etc now
 *              			use private slabcaches for its socks
 *              Pedro Hortas	:	New flags field for socket options
 *
 *
 *		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 _SOCK_H
#define _SOCK_H

#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/timer.h>
#include <linux/cache.h>
#include <linux/module.h>
#include <linux/lockdep.h>
#include <linux/netdevice.h>
#include <linux/pcounter.h>
#include <linux/skbuff.h>	/* struct sk_buff */
#include <linux/mm.h>
#include <linux/security.h>

#include <linux/filter.h>

#include <asm/atomic.h>
#include <net/dst.h>
#include <net/checksum.h>

/*
 * This structure really needs to be cleaned up.
 * Most of it is for TCP, and not used by any of
 * the other protocols.
 */

/* Define this to get the SOCK_DBG debugging facility. */
#define SOCK_DEBUGGING
#ifdef SOCK_DEBUGGING
#define SOCK_DEBUG(sk, msg...) do { if ((sk) && sock_flag((sk), SOCK_DBG)) \
					printk(KERN_DEBUG msg); } while (0)
#else
#define SOCK_DEBUG(sk, msg...) do { } while (0)
#endif

/* This is the per-socket lock.  The spinlock provides a synchronization
 * between user contexts and software interrupt processing, whereas the
 * mini-semaphore synchronizes multiple users amongst themselves.
 */
typedef struct {
	spinlock_t		slock;
	int			owned;
	wait_queue_head_t	wq;
	/*
	 * We express the mutex-alike socket_lock semantics
	 * to the lock validator by explicitly managing
	 * the slock as a lock variant (in addition to
	 * the slock itself):
	 */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct lockdep_map dep_map;
#endif
} socket_lock_t;

struct sock;
struct proto;
struct net;

/**
 *	struct sock_common - minimal network layer representation of sockets
 *	@skc_family: network address family
 *	@skc_state: Connection state
 *	@skc_reuse: %SO_REUSEADDR setting
 *	@skc_bound_dev_if: bound device index if != 0
 *	@skc_node: main hash linkage for various protocol lookup tables
 *	@skc_bind_node: bind hash linkage for various protocol lookup tables
 *	@skc_refcnt: reference count
 *	@skc_hash: hash value used with various protocol lookup tables
 *	@skc_prot: protocol handlers inside a network family
 *	@skc_net: reference to the network namespace of this socket
 *
 *	This is the minimal network layer representation of sockets, the header
 *	for struct sock and struct inet_timewait_sock.
 */
struct sock_common {
	unsigned short		skc_family;
	volatile unsigned char	skc_state;
	unsigned char		skc_reuse;
	int			skc_bound_dev_if;
	struct hlist_node	skc_node;
	struct hlist_node	skc_bind_node;
	atomic_t		skc_refcnt;
	unsigned int		skc_hash;
	struct proto		*skc_prot;
	struct net	 	*skc_net;
};

/**
  *	struct sock - network layer representation of sockets
  *	@__sk_common: shared layout with inet_timewait_sock
  *	@sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN
  *	@sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings
  *	@sk_lock:	synchronizer
  *	@sk_rcvbuf: size of receive buffer in bytes
  *	@sk_sleep: sock wait queue
  *	@sk_dst_cache: destination cache
  *	@sk_dst_lock: destination cache lock
  *	@sk_policy: flow policy
  *	@sk_rmem_alloc: receive queue bytes committed
  *	@sk_receive_queue: incoming packets
  *	@sk_wmem_alloc: transmit queue bytes committed
  *	@sk_write_queue: Packet sending queue
  *	@sk_async_wait_queue: DMA copied packets
  *	@sk_omem_alloc: "o" is "option" or "other"
  *	@sk_wmem_queued: persistent queue size
  *	@sk_forward_alloc: space allocated forward
  *	@sk_allocation: allocation mode
  *	@sk_sndbuf: size of send buffer in bytes
  *	@sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
  *		   %SO_OOBINLINE settings
  *	@sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets
  *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
  *	@sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
  *	@sk_lingertime: %SO_LINGER l_linger setting
  *	@sk_backlog: always used with the per-socket spinlock held
  *	@sk_callback_lock: used with the callbacks in the end of this struct
  *	@sk_error_queue: rarely used
  *	@sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt,
  *			  IPV6_ADDRFORM for instance)
  *	@sk_err: last error
  *	@sk_err_soft: errors that don't cause failure but are the cause of a
  *		      persistent failure not just 'timed out'
  *	@sk_drops: raw drops counter
  *	@sk_ack_backlog: current listen backlog
  *	@sk_max_ack_backlog: listen backlog set in listen()
  *	@sk_priority: %SO_PRIORITY setting
  *	@sk_type: socket type (%SOCK_STREAM, etc)
  *	@sk_protocol: which protocol this socket belongs in this network family
  *	@sk_peercred: %SO_PEERCRED setting
  *	@sk_rcvlowat: %SO_RCVLOWAT setting
  *	@sk_rcvtimeo: %SO_RCVTIMEO setting
  *	@sk_sndtimeo: %SO_SNDTIMEO setting
  *	@sk_filter: socket filtering instructions
  *	@sk_protinfo: private area, net family specific, when not using slab
  *	@sk_timer: sock cleanup timer
  *	@sk_stamp: time stamp of last packet received
  *	@sk_socket: Identd and reporting IO signals
  *	@sk_user_data: RPC layer private data
  *	@sk_sndmsg_page: cached page for sendmsg
  *	@sk_sndmsg_off: cached offset for sendmsg
  *	@sk_send_head: front of stuff to transmit
  *	@sk_security: used by security modules
  *	@sk_write_pending: a write to stream socket waits to start
  *	@sk_state_change: callback to indicate change in the state of the sock
  *	@sk_data_ready: callback to indicate there is data to be processed
  *	@sk_write_space: callback to indicate there is bf sending space available
  *	@sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
  *	@sk_backlog_rcv: callback to process the backlog
  *	@sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
 */
struct sock {
	/*
	 * Now struct inet_timewait_sock also uses sock_common, so please just
	 * don't add nothing before this first member (__sk_common) --acme
	 */
	struct sock_common	__sk_common;
#define sk_family		__sk_common.skc_family
#define sk_state		__sk_common.skc_state
#define sk_reuse		__sk_common.skc_reuse
#define sk_bound_dev_if		__sk_common.skc_bound_dev_if
#define sk_node			__sk_common.skc_node
#define sk_bind_node		__sk_common.skc_bind_node
#define sk_refcnt		__sk_common.skc_refcnt
#define sk_hash			__sk_common.skc_hash
#define sk_prot			__sk_common.skc_prot
#define sk_net			__sk_common.skc_net
	unsigned char		sk_shutdown : 2,
				sk_no_check : 2,
				sk_userlocks : 4;
	unsigned char		sk_protocol;
	unsigned short		sk_type;
	int			sk_rcvbuf;
	socket_lock_t		sk_lock;
	/*
	 * The backlog queue is special, it is always used with
	 * the per-socket spinlock held and requires low latency
	 * access. Therefore we special case it's implementation.
	 */
	struct {
		struct sk_buff *head;
		struct sk_buff *tail;
	} sk_backlog;
	wait_queue_head_t	*sk_sleep;
	struct dst_entry	*sk_dst_cache;
	struct xfrm_policy	*sk_policy[2];
	rwlock_t		sk_dst_lock;
	atomic_t		sk_rmem_alloc;
	atomic_t		sk_wmem_alloc;
	atomic_t		sk_omem_alloc;
	int			sk_sndbuf;
	struct sk_buff_head	sk_receive_queue;
	struct sk_buff_head	sk_write_queue;
	struct sk_buff_head	sk_async_wait_queue;
	int			sk_wmem_queued;
	int			sk_forward_alloc;
	gfp_t			sk_allocation;
	int			sk_route_caps;
	int			sk_gso_type;
	int			sk_rcvlowat;
	unsigned long 		sk_flags;
	unsigned long	        sk_lingertime;
	struct sk_buff_head	sk_error_queue;
	struct proto		*sk_prot_creator;
	rwlock_t		sk_callback_lock;
	int			sk_err,
				sk_err_soft;
	atomic_t		sk_drops;
	unsigned short		sk_ack_backlog;
	unsigned short		sk_max_ack_backlog;
	__u32			sk_priority;
	struct ucred		sk_peercred;
	long			sk_rcvtimeo;
	long			sk_sndtimeo;
	struct sk_filter      	*sk_filter;
	void			*sk_protinfo;
	struct timer_list	sk_timer;
	ktime_t			sk_stamp;
	struct socket		*sk_socket;
	void			*sk_user_data;
	struct page		*sk_sndmsg_page;
	struct sk_buff		*sk_send_head;
	__u32			sk_sndmsg_off;
	int			sk_write_pending;
	void			*sk_security;
	void			(*sk_state_change)(struct sock *sk);
	void			(*sk_data_ready)(struct sock *sk, int bytes);
	void			(*sk_write_space)(struct sock *sk);
	void			(*sk_error_report)(struct sock *sk);
  	int			(*sk_backlog_rcv)(struct sock *sk,
						  struct sk_buff *skb);  
	void                    (*sk_destruct)(struct sock *sk);
};

/*
 * Hashed lists helper routines
 */
static inline struct sock *__sk_head(const struct hlist_head *head)
{
	return hlist_entry(head->first, struct sock, sk_node);
}

static inline struct sock *sk_head(const struct hlist_head *head)
{
	return hlist_empty(head) ? NULL : __sk_head(head);
}

static inline struct sock *sk_next(const struct sock *sk)
{
	return sk->sk_node.next ?
		hlist_entry(sk->sk_node.next, struct sock, sk_node) : NULL;
}

static inline int sk_unhashed(const struct sock *sk)
{
	return hlist_unhashed(&sk->sk_node);
}

static inline int sk_hashed(const struct sock *sk)
{
	return !sk_unhashed(sk);
}

static __inline__ void sk_node_init(struct hlist_node *node)
{
	node->pprev = NULL;
}

static __inline__ void __sk_del_node(struct sock *sk)
{
	__hlist_del(&sk->sk_node);
}

static __inline__ int __sk_del_node_init(struct sock *sk)
{
	if (sk_hashed(sk)) {
		__sk_del_node(sk);
		sk_node_init(&sk->sk_node);
		return 1;
	}
	return 0;
}

/* Grab socket reference count. This operation is valid only
   when sk is ALREADY grabbed f.e. it is found in hash table
   or a list and the lookup is made under lock preventing hash table
   modifications.
 */

static inline void sock_hold(struct sock *sk)
{
	atomic_inc(&sk->sk_refcnt);
}

/* Ungrab socket in the context, which assumes that socket refcnt
   cannot hit zero, f.e. it is true in context of any socketcall.
 */
static inline void __sock_put(struct sock *sk)
{
	atomic_dec(&sk->sk_refcnt);
}

static __inline__ int sk_del_node_init(struct sock *sk)
{
	int rc = __sk_del_node_init(sk);

	if (rc) {
		/* paranoid for a while -acme */
		WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
		__sock_put(sk);
	}
	return rc;
}

static __inline__ void __sk_add_node(struct sock *sk, struct hlist_head *list)
{
	hlist_add_head(&sk->sk_node, list);
}

static __inline__ void sk_add_node(struct sock *sk, struct hlist_head *list)
{
	sock_hold(sk);
	__sk_add_node(sk, list);
}

static __inline__ void __sk_del_bind_node(struct sock *sk)
{
	__hlist_del(&sk->sk_bind_node);
}

static __inline__ void sk_add_bind_node(struct sock *sk,
					struct hlist_head *list)
{
	hlist_add_head(&sk->sk_bind_node, list);
}

#define sk_for_each(__sk, node, list) \
	hlist_for_each_entry(__sk, node, list, sk_node)
#define sk_for_each_from(__sk, node) \
	if (__sk && ({ node = &(__sk)->sk_node; 1; })) \
		hlist_for_each_entry_from(__sk, node, sk_node)
#define sk_for_each_continue(__sk, node) \
	if (__sk && ({ node = &(__sk)->sk_node; 1; })) \
		hlist_for_each_entry_continue(__sk, node, sk_node)
#define sk_for_each_safe(__sk, node, tmp, list) \
	hlist_for_each_entry_safe(__sk, node, tmp, list, sk_node)
#define sk_for_each_bound(__sk, node, list) \
	hlist_for_each_entry(__sk, node, list, sk_bind_node)

/* Sock flags */
enum sock_flags {
	SOCK_DEAD,
	SOCK_DONE,
	SOCK_URGINLINE,
	SOCK_KEEPOPEN,
	SOCK_LINGER,
	SOCK_DESTROY,
	SOCK_BROADCAST,
	SOCK_TIMESTAMP,
	SOCK_ZAPPED,
	SOCK_USE_WRITE_QUEUE, /* whether to call sk->sk_write_space in sock_wfree */
	SOCK_DBG, /* %SO_DEBUG setting */
	SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */
	SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
	SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
	SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
};

static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)
{
	nsk->sk_flags = osk->sk_flags;
}

static inline void sock_set_flag(struct sock *sk, enum sock_flags flag)
{
	__set_bit(flag, &sk->sk_flags);
}

static inline void sock_reset_flag(struct sock *sk, enum sock_flags flag)
{
	__clear_bit(flag, &sk->sk_flags);
}

static inline int sock_flag(struct sock *sk, enum sock_flags flag)
{
	return test_bit(flag, &sk->sk_flags);
}

static inline void sk_acceptq_removed(struct sock *sk)
{
	sk->sk_ack_backlog--;
}

static inline void sk_acceptq_added(struct sock *sk)
{
	sk->sk_ack_backlog++;
}

static inline int sk_acceptq_is_full(struct sock *sk)
{
	return sk->sk_ack_backlog > sk->sk_max_ack_backlog;
}

/*
 * Compute minimal free write space needed to queue new packets.
 */
static inline int sk_stream_min_wspace(struct sock *sk)
{
	return sk->sk_wmem_queued / 2;
}

static inline int sk_stream_wspace(struct sock *sk)
{
	return sk->sk_sndbuf - sk->sk_wmem_queued;
}

extern void sk_stream_write_space(struct sock *sk);

static inline int sk_stream_memory_free(struct sock *sk)
{
	return sk->sk_wmem_queued < sk->sk_sndbuf;
}

extern void sk_stream_rfree(struct sk_buff *skb);

static inline void sk_stream_set_owner_r(struct sk_buff *skb, struct sock *sk)
{
	skb->sk = sk;
	skb->destructor = sk_stream_rfree;
	atomic_add(skb->truesize, &sk->sk_rmem_alloc);
	sk->sk_forward_alloc -= skb->truesize;
}

static inline void sk_stream_free_skb(struct sock *sk, struct sk_buff *skb)
{
	skb_truesize_check(skb);
	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
	sk->sk_wmem_queued   -= skb->truesize;
	sk->sk_forward_alloc += skb->truesize;
	__kfree_skb(skb);
}

/* The per-socket spinlock must be held here. */
static inline void sk_add_backlog(struct sock *sk, struct sk_buff *skb)
{
	if (!sk->sk_backlog.tail) {
		sk->sk_backlog.head = sk->sk_backlog.tail = skb;
	} else {
		sk->sk_backlog.tail->next = skb;
		sk->sk_backlog.tail = skb;
	}
	skb->next = NULL;
}

#define sk_wait_event(__sk, __timeo, __condition)			\
	({	int __rc;						\
		release_sock(__sk);					\
		__rc = __condition;					\
		if (!__rc) {						\
			*(__timeo) = schedule_timeout(*(__timeo));	\
		}							\
		lock_sock(__sk);					\
		__rc = __condition;					\
		__rc;							\
	})

extern int sk_stream_wait_connect(struct sock *sk, long *timeo_p);
extern int sk_stream_wait_memory(struct sock *sk, long *timeo_p);
extern void sk_stream_wait_close(struct sock *sk, long timeo_p);
extern int sk_stream_error(struct sock *sk, int flags, int err);
extern void sk_stream_kill_queues(struct sock *sk);

extern int sk_wait_data(struct sock *sk, long *timeo);

struct request_sock_ops;
struct timewait_sock_ops;

/* Networking protocol blocks we attach to sockets.
 * socket layer -> transport layer interface
 * transport -> network interface is defined by struct inet_proto
 */
struct proto {
	void			(*close)(struct sock *sk, 
					long timeout);
	int			(*connect)(struct sock *sk,
				        struct sockaddr *uaddr, 
					int addr_len);
	int			(*disconnect)(struct sock *sk, int flags);

	struct sock *		(*accept) (struct sock *sk, int flags, int *err);

	int			(*ioctl)(struct sock *sk, int cmd,
					 unsigned long arg);
	int			(*init)(struct sock *sk);
	int			(*destroy)(struct sock *sk);
	void			(*shutdown)(struct sock *sk, int how);
	int			(*setsockopt)(struct sock *sk, int level, 
					int optname, char __user *optval,
					int optlen);
	int			(*getsockopt)(struct sock *sk, int level, 
					int optname, char __user *optval, 
					int __user *option);  	 
	int			(*compat_setsockopt)(struct sock *sk,
					int level,
					int optname, char __user *optval,
					int optlen);
	int			(*compat_getsockopt)(struct sock *sk,
					int level,
					int optname, char __user *optval,
					int __user *option);
	int			(*sendmsg)(struct kiocb *iocb, struct sock *sk,
					   struct msghdr *msg, size_t len);
	int			(*recvmsg)(struct kiocb *iocb, struct sock *sk,
					   struct msghdr *msg,
					size_t len, int noblock, int flags, 
					int *addr_len);
	int			(*sendpage)(struct sock *sk, struct page *page,
					int offset, size_t size, int flags);
	int			(*bind)(struct sock *sk, 
					struct sockaddr *uaddr, int addr_len);

	int			(*backlog_rcv) (struct sock *sk, 
						struct sk_buff *skb);

	/* Keeping track of sk's, looking them up, and port selection methods. */
	void			(*hash)(struct sock *sk);
	void			(*unhash)(struct sock *sk);
	int			(*get_port)(struct sock *sk, unsigned short snum);

	/* Keeping track of sockets in use */
	struct pcounter		inuse;

	/* Memory pressure */
	void			(*enter_memory_pressure)(void);
	atomic_t		*memory_allocated;	/* Current allocated memory. */
	atomic_t		*sockets_allocated;	/* Current number of sockets. */
	/*
	 * Pressure flag: try to collapse.
	 * Technical note: it is used by multiple contexts non atomically.
	 * All the sk_stream_mem_schedule() is of this nature: accounting
	 * is strict, actions are advisory and have some latency.
	 */
	int			*memory_pressure;
	int			*sysctl_mem;
	int			*sysctl_wmem;
	int			*sysctl_rmem;
	int			max_header;

	struct kmem_cache		*slab;
	unsigned int		obj_size;

	atomic_t		*orphan_count;

	struct request_sock_ops	*rsk_prot;
	struct timewait_sock_ops *twsk_prot;

	struct module		*owner;

	char			name[32];

	struct list_head	node;
#ifdef SOCK_REFCNT_DEBUG
	atomic_t		socks;
#endif
};

#define DEFINE_PROTO_INUSE(NAME) DEFINE_PCOUNTER(NAME)
#define REF_PROTO_INUSE(NAME) PCOUNTER_MEMBER_INITIALIZER(NAME, .inuse)

extern int proto_register(struct proto *prot, int alloc_slab);
extern void proto_unregister(struct proto *prot);

#ifdef SOCK_REFCNT_DEBUG
static inline void sk_refcnt_debug_inc(struct sock *sk)
{
	atomic_inc(&sk->sk_prot->socks);
}

static inline void sk_refcnt_debug_dec(struct sock *sk)
{
	atomic_dec(&sk->sk_prot->socks);
	printk(KERN_DEBUG "%s socket %p released, %d are still alive\n",
	       sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks));
}

static inline void sk_refcnt_debug_release(const struct sock *sk)
{
	if (atomic_read(&sk->sk_refcnt) != 1)
		printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n",
		       sk->sk_prot->name, sk, atomic_read(&sk->sk_refcnt));
}
#else /* SOCK_REFCNT_DEBUG */
#define sk_refcnt_debug_inc(sk) do { } while (0)
#define sk_refcnt_debug_dec(sk) do { } while (0)
#define sk_refcnt_debug_release(sk) do { } while (0)
#endif /* SOCK_REFCNT_DEBUG */

/* Called with local bh disabled */
static __inline__ void sock_prot_inc_use(struct proto *prot)
{
	pcounter_add(&prot->inuse, 1);
}

static __inline__ void sock_prot_dec_use(struct proto *prot)
{
	pcounter_add(&prot->inuse, -1);
}

static __inline__ int sock_prot_inuse(struct proto *proto)
{
	return pcounter_getval(&proto->inuse);
}

/* With per-bucket locks this operation is not-atomic, so that
 * this version is not worse.
 */
static inline void __sk_prot_rehash(struct sock *sk)
{
	sk->sk_prot->unhash(sk);
	sk->sk_prot->hash(sk);
}

/* About 10 seconds */
#define SOCK_DESTROY_TIME (10*HZ)

/* Sockets 0-1023 can't be bound to unless you are superuser */
#define PROT_SOCK	1024

#define SHUTDOWN_MASK	3
#define RCV_SHUTDOWN	1
#define SEND_SHUTDOWN	2

#define SOCK_SNDBUF_LOCK	1
#define SOCK_RCVBUF_LOCK	2
#define SOCK_BINDADDR_LOCK	4
#define SOCK_BINDPORT_LOCK	8

/* sock_iocb: used to kick off async processing of socket ios */
struct sock_iocb {
	struct list_head	list;

	int			flags;
	int			size;
	struct socket		*sock;
	struct sock		*sk;
	struct scm_cookie	*scm;
	struct msghdr		*msg, async_msg;
	struct kiocb		*kiocb;
};

static inline struct sock_iocb *kiocb_to_siocb(struct kiocb *iocb)
{
	return (struct sock_iocb *)iocb->private;
}

static inline struct kiocb *siocb_to_kiocb(struct sock_iocb *si)
{
	return si->kiocb;
}

struct socket_alloc {
	struct socket socket;
	struct inode vfs_inode;
};

static inline struct socket *SOCKET_I(struct inode *inode)
{
	return &container_of(inode, struct socket_alloc, vfs_inode)->socket;
}

static inline struct inode *SOCK_INODE(struct socket *socket)
{
	return &container_of(socket, struct socket_alloc, socket)->vfs_inode;
}

extern void __sk_stream_mem_reclaim(struct sock *sk);
extern int sk_stream_mem_schedule(struct sock *sk, int size, int kind);

#define SK_STREAM_MEM_QUANTUM ((int)PAGE_SIZE)

static inline int sk_stream_pages(int amt)
{
	return DIV_ROUND_UP(amt, SK_STREAM_MEM_QUANTUM);
}

static inline void sk_stream_mem_reclaim(struct sock *sk)
{
	if (sk->sk_forward_alloc >= SK_STREAM_MEM_QUANTUM)
		__sk_stream_mem_reclaim(sk);
}

static inline int sk_stream_rmem_schedule(struct sock *sk, struct sk_buff *skb)
{
	return (int)skb->truesize <= sk->sk_forward_alloc ||
		sk_stream_mem_schedule(sk, skb->truesize, 1);
}

static inline int sk_stream_wmem_schedule(struct sock *sk, int size)
{
	return size <= sk->sk_forward_alloc ||
	       sk_stream_mem_schedule(sk, size, 0);
}

/* Used by processes to "lock" a socket state, so that
 * interrupts and bottom half handlers won't change it
 * from under us. It essentially blocks any incoming
 * packets, so that we won't get any new data or any
 * packets that change the state of the socket.
 *
 * While locked, BH processing will add new packets to
 * the backlog queue.  This queue is processed by the
 * owner of the socket lock right before it is released.
 *
 * Since ~2.3.5 it is also exclusive sleep lock serializing
 * accesses from user process context.
 */
#define sock_owned_by_user(sk)	((sk)->sk_lock.owned)

/*
 * Macro so as to not evaluate some arguments when
 * lockdep is not enabled.
 *
 * Mark both the sk_lock and the sk_lock.slock as a
 * per-address-family lock class.
 */
#define sock_lock_init_class_and_name(sk, sname, skey, name, key) 	\
do {									\
	sk->sk_lock.owned = 0;					\
	init_waitqueue_head(&sk->sk_lock.wq);				\
	spin_lock_init(&(sk)->sk_lock.slock);				\
	debug_check_no_locks_freed((void *)&(sk)->sk_lock,		\
			sizeof((sk)->sk_lock));				\
	lockdep_set_class_and_name(&(sk)->sk_lock.slock,		\
		       	(skey), (sname));				\
	lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0);	\
} while (0)

extern void FASTCALL(lock_sock_nested(struct sock *sk, int subclass));

static inline void lock_sock(struct sock *sk)
{
	lock_sock_nested(sk, 0);
}

extern void FASTCALL(release_sock(struct sock *sk));

/* BH context may only use the following locking interface. */
#define bh_lock_sock(__sk)	spin_lock(&((__sk)->sk_lock.slock))
#define bh_lock_sock_nested(__sk) \
				spin_lock_nested(&((__sk)->sk_lock.slock), \
				SINGLE_DEPTH_NESTING)
#define bh_unlock_sock(__sk)	spin_unlock(&((__sk)->sk_lock.slock))

extern struct sock		*sk_alloc(struct net *net, int family,
					  gfp_t priority,
					  struct proto *prot);
extern void			sk_free(struct sock *sk);
extern struct sock		*sk_clone(const struct sock *sk,
					  const gfp_t priority);

extern struct sk_buff		*sock_wmalloc(struct sock *sk,
					      unsigned long size, int force,
					      gfp_t priority);
extern struct sk_buff		*sock_rmalloc(struct sock *sk,
					      unsigned long size, int force,
					      gfp_t priority);
extern void			sock_wfree(struct sk_buff *skb);
extern void			sock_rfree(struct sk_buff *skb);

extern int			sock_setsockopt(struct socket *sock, int level,
						int op, char __user *optval,
						int optlen);

extern int			sock_getsockopt(struct socket *sock, int level,
						int op, char __user *optval, 
						int __user *optlen);
extern struct sk_buff 		*sock_alloc_send_skb(struct sock *sk,
						     unsigned long size,
						     int noblock,
						     int *errcode);
extern void *sock_kmalloc(struct sock *sk, int size,
			  gfp_t priority);
extern void sock_kfree_s(struct sock *sk, void *mem, int size);
extern void sk_send_sigurg(struct sock *sk);

/*
 * Functions to fill in entries in struct proto_ops when a protocol
 * does not implement a particular function.
 */
extern int                      sock_no_bind(struct socket *, 
					     struct sockaddr *, int);
extern int                      sock_no_connect(struct socket *,
						struct sockaddr *, int, int);
extern int                      sock_no_socketpair(struct socket *,
						   struct socket *);
extern int                      sock_no_accept(struct socket *,
					       struct socket *, int);
extern int                      sock_no_getname(struct socket *,
						struct sockaddr *, int *, int);
extern unsigned int             sock_no_poll(struct file *, struct socket *,
					     struct poll_table_struct *);
extern int                      sock_no_ioctl(struct socket *, unsigned int,
					      unsigned long);
extern int			sock_no_listen(struct socket *, int);
extern int                      sock_no_shutdown(struct socket *, int);
extern int			sock_no_getsockopt(struct socket *, int , int,
						   char __user *, int __user *);
extern int			sock_no_setsockopt(struct socket *, int, int,
						   char __user *, int);
extern int                      sock_no_sendmsg(struct kiocb *, struct socket *,
						struct msghdr *, size_t);
extern int                      sock_no_recvmsg(struct kiocb *, struct socket *,
						struct msghdr *, size_t, int);
extern int			sock_no_mmap(struct file *file,
					     struct socket *sock,
					     struct vm_area_struct *vma);
extern ssize_t			sock_no_sendpage(struct socket *sock,
						struct page *page,
						int offset, size_t size, 
						int flags);

/*
 * Functions to fill in entries in struct proto_ops when a protocol
 * uses the inet style.
 */
extern int sock_common_getsockopt(struct socket *sock, int level, int optname,
				  char __user *optval, int __user *optlen);
extern int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock,
			       struct msghdr *msg, size_t size, int flags);
extern int sock_common_setsockopt(struct socket *sock, int level, int optname,
				  char __user *optval, int optlen);
extern int compat_sock_common_getsockopt(struct socket *sock, int level,
		int optname, char __user *optval, int __user *optlen);
extern int compat_sock_common_setsockopt(struct socket *sock, int level,
		int optname, char __user *optval, int optlen);

extern void sk_common_release(struct sock *sk);

/*
 *	Default socket callbacks and setup code
 */
 
/* Initialise core socket variables */
extern void sock_init_data(struct socket *sock, struct sock *sk);

/**
 *	sk_filter - run a packet through a socket filter
 *	@sk: sock associated with &sk_buff
 *	@skb: buffer to filter
 *	@needlock: set to 1 if the sock is not locked by caller.
 *
 * Run the filter code and then cut skb->data to correct size returned by
 * sk_run_filter. If pkt_len is 0 we toss packet. If skb->len is smaller
 * than pkt_len we keep whole skb->data. This is the socket level
 * wrapper to sk_run_filter. It returns 0 if the packet should
 * be accepted or -EPERM if the packet should be tossed.
 *
 */

static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
{
	int err;
	struct sk_filter *filter;
	
	err = security_sock_rcv_skb(sk, skb);
	if (err)
		return err;
	
	rcu_read_lock_bh();
	filter = rcu_dereference(sk->sk_filter);
	if (filter) {
		unsigned int pkt_len = sk_run_filter(skb, filter->insns,
				filter->len);
		err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM;
	}
 	rcu_read_unlock_bh();

	return err;
}

/**
 *	sk_filter_release: Release a socket filter
 *	@sk: socket
 *	@fp: filter to remove
 *
 *	Remove a filter from a socket and release its resources.
 */

static inline void sk_filter_release(struct sk_filter *fp)
{
	if (atomic_dec_and_test(&fp->refcnt))
		kfree(fp);
}

static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
{
	unsigned int size = sk_filter_len(fp);

	atomic_sub(size, &sk->sk_omem_alloc);
	sk_filter_release(fp);
}

static inline void sk_filter_charge(struct sock *sk, struct sk_filter *fp)
{
	atomic_inc(&fp->refcnt);
	atomic_add(sk_filter_len(fp), &sk->sk_omem_alloc);
}

/*
 * Socket reference counting postulates.
 *
 * * Each user of socket SHOULD hold a reference count.
 * * Each access point to socket (an hash table bucket, reference from a list,
 *   running timer, skb in flight MUST hold a reference count.
 * * When reference count hits 0, it means it will never increase back.
 * * When reference count hits 0, it means that no references from
 *   outside exist to this socket and current process on current CPU
 *   is last user and may/should destroy this socket.
 * * sk_free is called from any context: process, BH, IRQ. When
 *   it is called, socket has no references from outside -> sk_free
 *   may release descendant resources allocated by the socket, but
 *   to the time when it is called, socket is NOT referenced by any
 *   hash tables, lists etc.
 * * Packets, delivered from outside (from network or from another process)
 *   and enqueued on receive/error queues SHOULD NOT grab reference count,
 *   when they sit in queue. Otherwise, packets will leak to hole, when
 *   socket is looked up by one cpu and unhasing is made by another CPU.
 *   It is true for udp/raw, netlink (leak to receive and error queues), tcp
 *   (leak to backlog). Packet socket does all the processing inside
 *   BR_NETPROTO_LOCK, so that it has not this race condition. UNIX sockets
 *   use separate SMP lock, so that they are prone too.
 */

/* Ungrab socket and destroy it, if it was the last reference. */
static inline void sock_put(struct sock *sk)
{
	if (atomic_dec_and_test(&sk->sk_refcnt))
		sk_free(sk);
}

extern int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
			  const int nested);

/* Detach socket from process context.
 * Announce socket dead, detach it from wait queue and inode.
 * Note that parent inode held reference count on this struct sock,
 * we do not release it in this function, because protocol
 * probably wants some additional cleanups or even continuing
 * to work with this socket (TCP).
 */
static inline void sock_orphan(struct sock *sk)
{
	write_lock_bh(&sk->sk_callback_lock);
	sock_set_flag(sk, SOCK_DEAD);
	sk->sk_socket = NULL;
	sk->sk_sleep  = NULL;
	write_unlock_bh(&sk->sk_callback_lock);
}

static inline void sock_graft(struct sock *sk, struct socket *parent)
{
	write_lock_bh(&sk->sk_callback_lock);
	sk->sk_sleep = &parent->wait;
	parent->sk = sk;
	sk->sk_socket = parent;
	security_sock_graft(sk, parent);
	write_unlock_bh(&sk->sk_callback_lock);
}

extern int sock_i_uid(struct sock *sk);
extern unsigned long sock_i_ino(struct sock *sk);

static inline struct dst_entry *
__sk_dst_get(struct sock *sk)
{
	return sk->sk_dst_cache;
}

static inline struct dst_entry *
sk_dst_get(struct sock *sk)
{
	struct dst_entry *dst;

	read_lock(&sk->sk_dst_lock);
	dst = sk->sk_dst_cache;
	if (dst)
		dst_hold(dst);
	read_unlock(&sk->sk_dst_lock);
	return dst;
}

static inline void
__sk_dst_set(struct sock *sk, struct dst_entry *dst)
{
	struct dst_entry *old_dst;

	old_dst = sk->sk_dst_cache;
	sk->sk_dst_cache = dst;
	dst_release(old_dst);
}

static inline void
sk_dst_set(struct sock *sk, struct dst_entry *dst)
{
	write_lock(&sk->sk_dst_lock);
	__sk_dst_set(sk, dst);
	write_unlock(&sk->sk_dst_lock);
}

static inline void
__sk_dst_reset(struct sock *sk)
{
	struct dst_entry *old_dst;

	old_dst = sk->sk_dst_cache;
	sk->sk_dst_cache = NULL;
	dst_release(old_dst);
}

static inline void
sk_dst_reset(struct sock *sk)
{
	write_lock(&sk->sk_dst_lock);
	__sk_dst_reset(sk);
	write_unlock(&sk->sk_dst_lock);
}

extern struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);

extern struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie);

static inline int sk_can_gso(const struct sock *sk)
{
	return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type);
}

extern void sk_setup_caps(struct sock *sk, struct dst_entry *dst);

static inline void sk_charge_skb(struct sock *sk, struct sk_buff *skb)
{
	sk->sk_wmem_queued   += skb->truesize;
	sk->sk_forward_alloc -= skb->truesize;
}

static inline int skb_copy_to_page(struct sock *sk, char __user *from,
				   struct sk_buff *skb, struct page *page,
				   int off, int copy)
{
	if (skb->ip_summed == CHECKSUM_NONE) {
		int err = 0;
		__wsum csum = csum_and_copy_from_user(from,
						     page_address(page) + off,
							    copy, 0, &err);
		if (err)
			return err;
		skb->csum = csum_block_add(skb->csum, csum, skb->len);
	} else if (copy_from_user(page_address(page) + off, from, copy))
		return -EFAULT;

	skb->len	     += copy;
	skb->data_len	     += copy;
	skb->truesize	     += copy;
	sk->sk_wmem_queued   += copy;
	sk->sk_forward_alloc -= copy;
	return 0;
}

/*
 * 	Queue a received datagram if it will fit. Stream and sequenced
 *	protocols can't normally use this as they need to fit buffers in
 *	and play with them.
 *
 * 	Inlined as it's very short and called for pretty much every
 *	packet ever received.
 */

static inline void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
{
	sock_hold(sk);
	skb->sk = sk;
	skb->destructor = sock_wfree;
	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
}

static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
{
	skb->sk = sk;
	skb->destructor = sock_rfree;
	atomic_add(skb->truesize, &sk->sk_rmem_alloc);
}

extern void sk_reset_timer(struct sock *sk, struct timer_list* timer,
			   unsigned long expires);

extern void sk_stop_timer(struct sock *sk, struct timer_list* timer);

extern int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);

static inline int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
{
	/* Cast skb->rcvbuf to unsigned... It's pointless, but reduces
	   number of warnings when compiling with -W --ANK
	 */
	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
	    (unsigned)sk->sk_rcvbuf)
		return -ENOMEM;
	skb_set_owner_r(skb, sk);
	skb_queue_tail(&sk->sk_error_queue, skb);
	if (!sock_flag(sk, SOCK_DEAD))
		sk->sk_data_ready(sk, skb->len);
	return 0;
}

/*
 *	Recover an error report and clear atomically
 */
 
static inline int sock_error(struct sock *sk)
{
	int err;
	if (likely(!sk->sk_err))
		return 0;
	err = xchg(&sk->sk_err, 0);
	return -err;
}

static inline unsigned long sock_wspace(struct sock *sk)
{
	int amt = 0;

	if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
		amt = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc);
		if (amt < 0) 
			amt = 0;
	}
	return amt;
}

static inline void sk_wake_async(struct sock *sk, int how, int band)
{
	if (sk->sk_socket && sk->sk_socket->fasync_list)
		sock_wake_async(sk->sk_socket, how, band);
}

#define SOCK_MIN_SNDBUF 2048
#define SOCK_MIN_RCVBUF 256

static inline void sk_stream_moderate_sndbuf(struct sock *sk)
{
	if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) {
		sk->sk_sndbuf = min(sk->sk_sndbuf, sk->sk_wmem_queued / 2);
		sk->sk_sndbuf = max(sk->sk_sndbuf, SOCK_MIN_SNDBUF);
	}
}

struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp);

static inline struct page *sk_stream_alloc_page(struct sock *sk)
{
	struct page *page = NULL;

	page = alloc_pages(sk->sk_allocation, 0);
	if (!page) {
		sk->sk_prot->enter_memory_pressure();
		sk_stream_moderate_sndbuf(sk);
	}
	return page;
}

/*
 *	Default write policy as shown to user space via poll/select/SIGIO
 */
static inline int sock_writeable(const struct sock *sk) 
{
	return atomic_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf / 2);
}

static inline gfp_t gfp_any(void)
{
	return in_atomic() ? GFP_ATOMIC : GFP_KERNEL;
}

static inline long sock_rcvtimeo(const struct sock *sk, int noblock)
{
	return noblock ? 0 : sk->sk_rcvtimeo;
}

static inline long sock_sndtimeo(const struct sock *sk, int noblock)
{
	return noblock ? 0 : sk->sk_sndtimeo;
}

static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len)
{
	return (waitall ? len : min_t(int, sk->sk_rcvlowat, len)) ? : 1;
}

/* Alas, with timeout socket operations are not restartable.
 * Compare this to poll().
 */
static inline int sock_intr_errno(long timeo)
{
	return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR;
}

extern void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
	struct sk_buff *skb);

static __inline__ void
sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
{
	ktime_t kt = skb->tstamp;

	if (sock_flag(sk, SOCK_RCVTSTAMP))
		__sock_recv_timestamp(msg, sk, skb);
	else
		sk->sk_stamp = kt;
}

/**
 * sk_eat_skb - Release a skb if it is no longer needed
 * @sk: socket to eat this skb from
 * @skb: socket buffer to eat
 * @copied_early: flag indicating whether DMA operations copied this data early
 *
 * This routine must be called with interrupts disabled or with the socket
 * locked so that the sk_buff queue operation is ok.
*/
#ifdef CONFIG_NET_DMA
static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, int copied_early)
{
	__skb_unlink(skb, &sk->sk_receive_queue);
	if (!copied_early)
		__kfree_skb(skb);
	else
		__skb_queue_tail(&sk->sk_async_wait_queue, skb);
}
#else
static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, int copied_early)
{
	__skb_unlink(skb, &sk->sk_receive_queue);
	__kfree_skb(skb);
}
#endif

extern void sock_enable_timestamp(struct sock *sk);
extern int sock_get_timestamp(struct sock *, struct timeval __user *);
extern int sock_get_timestampns(struct sock *, struct timespec __user *);

/* 
 *	Enable debug/info messages 
 */
extern int net_msg_warn;
#define NETDEBUG(fmt, args...) \
	do { if (net_msg_warn) printk(fmt,##args); } while (0)

#define LIMIT_NETDEBUG(fmt, args...) \
	do { if (net_msg_warn && net_ratelimit()) printk(fmt,##args); } while(0)

/*
 * Macros for sleeping on a socket. Use them like this:
 *
 * SOCK_SLEEP_PRE(sk)
 * if (condition)
 * 	schedule();
 * SOCK_SLEEP_POST(sk)
 *
 * N.B. These are now obsolete and were, afaik, only ever used in DECnet
 * and when the last use of them in DECnet has gone, I'm intending to
 * remove them.
 */

#define SOCK_SLEEP_PRE(sk) 	{ struct task_struct *tsk = current; \
				DECLARE_WAITQUEUE(wait, tsk); \
				tsk->state = TASK_INTERRUPTIBLE; \
				add_wait_queue((sk)->sk_sleep, &wait); \
				release_sock(sk);

#define SOCK_SLEEP_POST(sk)	tsk->state = TASK_RUNNING; \
				remove_wait_queue((sk)->sk_sleep, &wait); \
				lock_sock(sk); \
				}

extern __u32 sysctl_wmem_max;
extern __u32 sysctl_rmem_max;

extern void sk_init(void);

extern int sysctl_optmem_max;

extern __u32 sysctl_wmem_default;
extern __u32 sysctl_rmem_default;

#endif	/* _SOCK_H */