sock.h

 * 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 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_mem_charge(sk, 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);
	sk_mem_charge(sk, skb->truesize);
}

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 >> 1);
		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 >> 1);
}

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 */