sock.h

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);
}

static inline void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
{
	__sk_dst_set(sk, dst);
	sk->sk_route_caps = dst->dev->features;
	if (sk->sk_route_caps & NETIF_F_GSO)
		sk->sk_route_caps |= NETIF_F_GSO_MASK;
	if (sk_can_gso(sk)) {
		if (dst->header_len)
			sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
		else 
			sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
	}
}

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;
		unsigned int 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);
	}
}

static inline struct sk_buff *sk_stream_alloc_pskb(struct sock *sk,
						   int size, int mem,
						   gfp_t gfp)
{
	struct sk_buff *skb;
	int hdr_len;

	hdr_len = SKB_DATA_ALIGN(sk->sk_prot->max_header);
	skb = alloc_skb_fclone(size + hdr_len, gfp);
	if (skb) {
		skb->truesize += mem;
		if (sk_stream_wmem_schedule(sk, skb->truesize)) {
			skb_reserve(skb, hdr_len);
			return skb;
		}
		__kfree_skb(skb);
	} else {
		sk->sk_prot->enter_memory_pressure();
		sk_stream_moderate_sndbuf(sk);
	}
	return NULL;
}

static inline struct sk_buff *sk_stream_alloc_skb(struct sock *sk,
						  int size,
						  gfp_t gfp)
{
	return sk_stream_alloc_pskb(sk, size, 0, 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;
}

#define sk_stream_for_retrans_queue(skb, sk)				\
		for (skb = (sk)->sk_write_queue.next;			\
		     (skb != (sk)->sk_send_head) &&			\
		     (skb != (struct sk_buff *)&(sk)->sk_write_queue);	\
		     skb = skb->next)

/*from STCP for fast SACK Process*/
#define sk_stream_for_retrans_queue_from(skb, sk)			\
		for (; (skb != (sk)->sk_send_head) &&                   \
		     (skb != (struct sk_buff *)&(sk)->sk_write_queue);	\
		     skb = skb->next)

/*
 *	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_softirq() ? 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;
}

static __inline__ void
sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
{
	struct timeval stamp;

	skb_get_timestamp(skb, &stamp);
	if (sock_flag(sk, SOCK_RCVTSTAMP)) {
		/* Race occurred between timestamp enabling and packet
		   receiving.  Fill in the current time for now. */
		if (stamp.tv_sec == 0)
			do_gettimeofday(&stamp);
		skb_set_timestamp(skb, &stamp);
		put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP, sizeof(struct timeval),
			 &stamp);
	} else
		sk->sk_stamp = stamp;
}

/**
 * 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 *);

/* 
 *	Enable debug/info messages 
 */

#ifdef CONFIG_NETDEBUG
#define NETDEBUG(fmt, args...)	printk(fmt,##args)
#define LIMIT_NETDEBUG(fmt, args...) do { if (net_ratelimit()) printk(fmt,##args); } while(0)
#else
#define NETDEBUG(fmt, args...)	do { } while (0)
#define LIMIT_NETDEBUG(fmt, args...) do { } while(0)
#endif

/*
 * 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); \
				}

static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
{
	if (valbool)
		sock_set_flag(sk, bit);
	else
		sock_reset_flag(sk, bit);
}

extern __u32 sysctl_wmem_max;
extern __u32 sysctl_rmem_max;

#ifdef CONFIG_NET
int siocdevprivate_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg);
#else
static inline int siocdevprivate_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg)
{
	return -ENODEV;
}
#endif

extern void sk_init(void);

#ifdef CONFIG_SYSCTL
extern struct ctl_table core_table[];
#endif

extern int sysctl_optmem_max;

extern __u32 sysctl_wmem_default;
extern __u32 sysctl_rmem_default;

#endif	/* _SOCK_H */