sock.h

来自「linux 内核源代码」· C头文件 代码 · 共 1,417 行 · 第 1/3 页

/*
 * 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, <[e-mail]>
 *		Corey Minyard <wf-rch![e-mail]>
 *		Florian La Roche <[e-mail]>
 *
 * 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/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>
#include <net/net_namespace.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 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_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;
	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);