sock.h

来自「Linux Kernel 2.6.9 for OMAP1710」· C头文件 代码 · 共 1,342 行 · 第 1/3 页

{
	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)
{
	sk->sk_queue_shrunk   = 1;
	sk->sk_wmem_queued   -= skb->truesize;
	sk->sk_forward_alloc += skb->truesize;
	__kfree_skb(skb);
}

/* The per-socket spinlock must be held here. */
#define sk_add_backlog(__sk, __skb)				\
do {	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;					\
} while(0)

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

/* 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			(*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);

	/* 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;

	kmem_cache_t		*slab;
	int			slab_obj_size;

	char			name[32];

	struct {
		int inuse;
		u8  __pad[SMP_CACHE_BYTES - sizeof(int)];
	} stats[NR_CPUS];
};

extern int sk_alloc_slab(struct proto *prot, char *name);
extern void sk_free_slab(struct proto *prot);

static inline void sk_alloc_slab_error(struct proto *proto)
{
	printk(KERN_CRIT "%s: Can't create sock SLAB cache!\n", proto->name);
}

static __inline__ void sk_set_owner(struct sock *sk, struct module *owner)
{
	/*
	 * One should use sk_set_owner just once, after struct sock creation,
	 * be it shortly after sk_alloc or after a function that returns a new
	 * struct sock (and that down the call chain called sk_alloc), e.g. the
	 * IPv4 and IPv6 modules share tcp_create_openreq_child, so if
	 * tcp_create_openreq_child called sk_set_owner IPv6 would have to
	 * change the ownership of this struct sock, with one not needed
	 * transient sk_set_owner call.
	 */
	BUG_ON(sk->sk_owner != NULL);

	sk->sk_owner = owner;
	__module_get(owner);
}

/* Called with local bh disabled */
static __inline__ void sock_prot_inc_use(struct proto *prot)
{
	prot->stats[smp_processor_id()].inuse++;
}

static __inline__ void sock_prot_dec_use(struct proto *prot)
{
	prot->stats[smp_processor_id()].inuse--;
}

/* 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 iovec		async_iov;
	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 (amt + SK_STREAM_MEM_QUANTUM - 1) / 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 void sk_stream_writequeue_purge(struct sock *sk)
{
	struct sk_buff *skb;

	while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL)
		sk_stream_free_skb(sk, skb);
	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);
}

/* 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.
 */
extern void __lock_sock(struct sock *sk);
extern void __release_sock(struct sock *sk);
#define sock_owned_by_user(sk)	((sk)->sk_lock.owner)

extern void FASTCALL(lock_sock(struct sock *sk));
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_unlock_sock(__sk)	spin_unlock(&((__sk)->sk_lock.slock))

extern struct sock *		sk_alloc(int family, int priority, int zero_it,
					 kmem_cache_t *slab);
extern void			sk_free(struct sock *sk);

extern struct sk_buff		*sock_wmalloc(struct sock *sk,
					      unsigned long size, int force,
					      int priority);
extern struct sk_buff		*sock_rmalloc(struct sock *sk,
					      unsigned long size, int force,
					      int 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 struct sk_buff 		*sock_alloc_send_pskb(struct sock *sk,
						      unsigned long header_len,
						      unsigned long data_len,
						      int noblock,
						      int *errcode);
extern void *sock_kmalloc(struct sock *sk, int size, int 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_release(struct socket *);
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 void sk_common_release(struct sock *sk);

/*
 *	Default socket callbacks and setup code
 */
 
extern void sock_def_destruct(struct sock *);

/* 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 needlock)
{
	int err;
	
	err = security_sock_rcv_skb(sk, skb);
	if (err)
		return err;
	
	if (sk->sk_filter) {
		struct sk_filter *filter;
		
		if (needlock)
			bh_lock_sock(sk);
		
		filter = sk->sk_filter;
		if (filter) {
			int pkt_len = sk_run_filter(skb, filter->insns,
						    filter->len);
			if (!pkt_len)
				err = -EPERM;
			else
				skb_trim(skb, pkt_len);
		}

		if (needlock)
			bh_unlock_sock(sk);
	}
	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 sock *sk, struct sk_filter *fp)
{
	unsigned int size = sk_filter_len(fp);

	atomic_sub(size, &sk->sk_omem_alloc);

	if (atomic_dec_and_test(&fp->refcnt))
		kfree(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.
 */