sock.h

#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;
}

/*
 * Functions for memory accounting
 */
extern int __sk_mem_schedule(struct sock *sk, int size, int kind);
extern void __sk_mem_reclaim(struct sock *sk);

#define SK_MEM_QUANTUM ((int)PAGE_SIZE)
#define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM)
#define SK_MEM_SEND	0
#define SK_MEM_RECV	1

static inline int sk_mem_pages(int amt)
{
	return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT;
}

static inline int sk_has_account(struct sock *sk)
{
	/* return true if protocol supports memory accounting */
	return !!sk->sk_prot->memory_allocated;
}

static inline int sk_wmem_schedule(struct sock *sk, int size)
{
	if (!sk_has_account(sk))
		return 1;
	return size <= sk->sk_forward_alloc ||
		__sk_mem_schedule(sk, size, SK_MEM_SEND);
}

static inline int sk_rmem_schedule(struct sock *sk, int size)
{
	if (!sk_has_account(sk))
		return 1;
	return size <= sk->sk_forward_alloc ||
		__sk_mem_schedule(sk, size, SK_MEM_RECV);
}

static inline void sk_mem_reclaim(struct sock *sk)
{
	if (!sk_has_account(sk))
		return;
	if (sk->sk_forward_alloc >= SK_MEM_QUANTUM)
		__sk_mem_reclaim(sk);
}

static inline void sk_mem_reclaim_partial(struct sock *sk)
{
	if (!sk_has_account(sk))
		return;
	if (sk->sk_forward_alloc > SK_MEM_QUANTUM)
		__sk_mem_reclaim(sk);
}

static inline void sk_mem_charge(struct sock *sk, int size)
{
	if (!sk_has_account(sk))
		return;
	sk->sk_forward_alloc -= size;
}

static inline void sk_mem_uncharge(struct sock *sk, int size)
{
	if (!sk_has_account(sk))
		return;
	sk->sk_forward_alloc += size;
}

static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
{
	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
	sk->sk_wmem_queued -= skb->truesize;
	sk_mem_uncharge(sk, skb->truesize);
	__kfree_skb(skb);
}

/* 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 lock_sock_nested(struct sock *sk, int subclass);

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

extern void 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 bool lock_sock_fast(struct sock *sk);
/**
 * unlock_sock_fast - complement of lock_sock_fast
 * @sk: socket
 * @slow: slow mode
 *
 * fast unlock socket for user context.
 * If slow mode is on, we call regular release_sock()
 */
static inline void unlock_sock_fast(struct sock *sk, bool slow)
{
	if (slow)
		release_sock(sk);
	else
		spin_unlock_bh(&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 void			sk_release_kernel(struct sock *sk);
extern struct sock		*sk_clone_lock(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,
						unsigned 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,
			  gfp_t priority);
extern void sock_kfree_s(struct sock *sk, void *mem, int size);
extern void sk_send_sigurg(struct sock *sk);

#ifdef CONFIG_CGROUPS
extern void sock_update_classid(struct sock *sk);
#else
static inline void sock_update_classid(struct sock *sk)
{
}
#endif

/*
 * 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 *, unsigned 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, unsigned 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, unsigned 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);

extern void sk_filter_release_rcu(struct rcu_head *rcu);

/**
 *	sk_filter_release - release a socket filter
 *	@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))
		call_rcu(&fp->rcu, sk_filter_release_rcu);
}

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);

static inline void sk_tx_queue_set(struct sock *sk, int tx_queue)
{
	sk->sk_tx_queue_mapping = tx_queue;
}

static inline void sk_tx_queue_clear(struct sock *sk)
{
	sk->sk_tx_queue_mapping = -1;
}

static inline int sk_tx_queue_get(const struct sock *sk)
{
	return sk ? sk->sk_tx_queue_mapping : -1;
}

static inline void sk_set_socket(struct sock *sk, struct socket *sock)
{
	sk_tx_queue_clear(sk);
	sk->sk_socket = sock;
}

static inline wait_queue_head_t *sk_sleep(struct sock *sk)
{
	BUILD_BUG_ON(offsetof(struct socket_wq, wait) != 0);
	return &rcu_dereference_raw(sk->sk_wq)->wait;
}
/* 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_set_socket(sk, NULL);
	sk->sk_wq  = 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_wq = parent->wq;
	parent->sk = sk;
	sk_set_socket(sk, 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 rcu_dereference_check(sk->sk_dst_cache, sock_owned_by_user(sk) ||
						       lockdep_is_held(&sk->sk_lock.slock));
}

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

	rcu_read_lock();
	dst = rcu_dereference(sk->sk_dst_cache);
	if (dst)
		dst_hold(dst);
	rcu_read_unlock();
	return dst;
}

extern void sk_reset_txq(struct sock *sk);

static inline void dst_negative_advice(struct sock *sk)
{
	struct dst_entry *ndst, *dst = __sk_dst_get(sk);

	if (dst && dst->ops->negative_advice) {
		ndst = dst->ops->negative_advice(dst);

		if (ndst != dst) {
			rcu_assign_pointer(sk->sk_dst_cache, ndst);
			sk_reset_txq(sk);
		}
	}
}

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

	sk_tx_queue_clear(sk);
	/*
	 * This can be called while sk is owned by the caller only,
	 * with no state that can be checked in a rcu_dereference_check() cond
	 */
	old_dst = rcu_dereference_raw(sk->sk_dst_cache);
	rcu_assign_pointer(sk->sk_dst_cache, dst);
	dst_release(old_dst);
}

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

static inline void
__sk_dst_reset(struct sock *sk)
{
	__sk_dst_set(sk, NULL);
}

static inline void
sk_dst_reset(struct sock *sk)
{
	spin_lock(&sk->sk_dst_lock);
	__sk_dst_reset(sk);
	spin_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_nocaps_add(struct sock *sk, netdev_features_t flags)
{
	sk->sk_route_nocaps |= flags;
	sk->sk_route_caps &= ~flags;
}

static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb,
					   char __user *from, char *to,
					   int copy, int offset)
{
	if (skb->ip_summed == CHECKSUM_NONE) {
		int err = 0;
		__wsum csum = csum_and_copy_from_user(from, to, copy, 0, &err);
		if (err)
			return err;
		skb->csum = csum_block_add(skb->csum, csum, offset);
	} else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) {
		if (!access_ok(VERIFY_READ, from, copy) ||
		    __copy_from_user_nocache(to, from, copy))
			return -EFAULT;
	} else if (copy_from_user(to, from, copy))
		return -EFAULT;

	return 0;
}

static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb,
				       char __user *from, int copy)
{
	int err, offset = skb->len;

	err = skb_do_copy_data_nocache(sk, skb, from, skb_put(skb, copy),
				       copy, offset);
	if (err)
		__skb_trim(skb, offset);

	return err;
}

static inline int skb_copy_to_page_nocache(struct sock *sk, char __user *from,
					   struct sk_buff *skb,
					   struct page *page,
					   int off, int copy)
{
	int err;

	err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) + off,
				       copy, skb->len);
	if (err)
		return err;

	skb->len	     += copy;
	skb->data_len	     += copy;
	skb->truesize	     += copy;
	sk->sk_wmem_queued   += copy;
	sk_mem_charge(sk, copy);
	return 0;
}

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;
}

/**
 * sk_wmem_alloc_get - returns write allocations
 * @sk: socket
 *
 * Returns sk_wmem_alloc minus initial offset of one
 */
static inline int sk_wmem_alloc_get(const struct sock *sk)
{
	return atomic_read(&sk->sk_wmem_alloc) - 1;
}

/**
 * sk_rmem_alloc_get - returns read allocations
 * @sk: socket
 *
 * Returns sk_rmem_alloc
 */
static inline int sk_rmem_alloc_get(const struct sock *sk)
{
	return atomic_read(&sk->sk_rmem_alloc);
}

/**
 * sk_has_allocations - check if allocations are outstanding
 * @sk: socket
 *
 * Returns true if socket has write or read allocations
 */
static inline int sk_has_allocations(const struct sock *sk)
{
	return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk);
}

/**
 * wq_has_sleeper - check if there are any waiting processes
 * @wq: struct socket_wq
 *
 * Returns true if socket_wq has waiting processes
 *
 * The purpose of the wq_has_sleeper and sock_poll_wait is to wrap the memory
 * barrier call. They were added due to the race found within the tcp code.
 *
 * Consider following tcp code paths:
 *
 * CPU1                  CPU2
 *
 * sys_select            receive packet
 *   ...                 ...
 *   __add_wait_queue    update tp->rcv_nxt
 *   ...                 ...
 *   tp->rcv_nxt check   sock_def_readable
 *   ...                 {
 *   schedule               rcu_read_lock();
 *                          wq = rcu_dereference(sk->sk_wq);
 *                          if (wq && waitqueue_active(&wq->wait))
 *                              wake_up_interruptible(&wq->wait)
 *                          ...
 *                       }
 *
 * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay
 * in its cache, and so does the tp->rcv_nxt update on CPU2 side.  The CPU1
 * could then endup calling schedule and sleep forever if there are no more
 * data on the socket.
 *
 */
static inline bool wq_has_sleeper(struct socket_wq *wq)
{

	/*
	 * We need to be sure we are in sync with the
	 * add_wait_queue modifications to the wait queue.
	 *
	 * This memory barrier is paired in the sock_poll_wait.
	 */
	smp_mb();
	return wq && waitqueue_active(&wq->wait);
}

/**
 * sock_poll_wait - place memory barrier behind the poll_wait call.
 * @filp:           file
 * @wait_address:   socket wait queue
 * @p:              poll_table
 *
 * See the comments in the wq_has_sleeper function.
 */
static inline void sock_poll_wait(struct file *filp,
		wait_queue_head_t *wait_address, poll_table *p)
{
	if (p && wait_address) {
		poll_wait(filp, wait_address, p);
		/*
		 * We need to be sure we are in sync with the
		 * socket flags modification.
		 *
		 * This memory barrier is paired in the wq_has_sleeper.
		*/
		smp_mb();
	}
}

/*
 * 	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)
{
	skb_orphan(skb);
	skb->sk = sk;
	skb->destructor = sock_wfree;
	/*
	 * We used to take a refcount on sk, but following operation
	 * is enough to guarantee sk_free() wont free this sock until
	 * all in-flight packets are completed
	 */
	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
}

static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
{
	skb_orphan(skb);
	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);

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

/*
 *	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 (sock_flag(sk, SOCK_FASYNC))
		sock_wake_async(sk->sk_socket, how, band);
}

#define SOCK_MIN_SNDBUF 2048
/*
 * Since sk_rmem_alloc sums skb->truesize, even a small frame might need
 * sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak
 */
#define SOCK_MIN_RCVBUF (2048 + sizeof(struct sk_buff))

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_enter_memory_pressure(sk);
		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_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;
}

extern void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
	struct sk_buff *skb);
extern void __sock_recv_wifi_status(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;
	struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb);

	/*
	 * generate control messages if
	 * - receive time stamping in software requested (SOCK_RCVTSTAMP
	 *   or SOCK_TIMESTAMPING_RX_SOFTWARE)
	 * - software time stamp available and wanted
	 *   (SOCK_TIMESTAMPING_SOFTWARE)
	 * - hardware time stamps available and wanted
	 *   (SOCK_TIMESTAMPING_SYS_HARDWARE or
	 *   SOCK_TIMESTAMPING_RAW_HARDWARE)
	 */
	if (sock_flag(sk, SOCK_RCVTSTAMP) ||
	    sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE) ||
	    (kt.tv64 && sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) ||
	    (hwtstamps->hwtstamp.tv64 &&
	     sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE)) ||
	    (hwtstamps->syststamp.tv64 &&
	     sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE)))
		__sock_recv_timestamp(msg, sk, skb);
	else
		sk->sk_stamp = kt;

	if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid)
		__sock_recv_wifi_status(msg, sk, skb);
}

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

static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
					  struct sk_buff *skb)
{
#define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL)			| \
			   (1UL << SOCK_RCVTSTAMP)			| \
			   (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)	| \
			   (1UL << SOCK_TIMESTAMPING_SOFTWARE)		| \
			   (1UL << SOCK_TIMESTAMPING_RAW_HARDWARE) 	| \
			   (1UL << SOCK_TIMESTAMPING_SYS_HARDWARE))

	if (sk->sk_flags & FLAGS_TS_OR_DROPS)
		__sock_recv_ts_and_drops(msg, sk, skb);
	else
		sk->sk_stamp = skb->tstamp;
}

/**
 * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped
 * @sk:		socket sending this packet
 * @tx_flags:	filled with instructions for time stamping
 *
 * Currently only depends on SOCK_TIMESTAMPING* flags. Returns error code if
 * parameters are invalid.
 */
extern int sock_tx_timestamp(struct sock *sk, __u8 *tx_flags);

/**
 * 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

static inline
struct net *sock_net(const struct sock *sk)
{
	return read_pnet(&sk->sk_net);
}

static inline
void sock_net_set(struct sock *sk, struct net *net)
{
	write_pnet(&sk->sk_net, net);
}

/*
 * Kernel sockets, f.e. rtnl or icmp_socket, are a part of a namespace.
 * They should not hold a reference to a namespace in order to allow
 * to stop it.
 * Sockets after sk_change_net should be released using sk_release_kernel
 */
static inline void sk_change_net(struct sock *sk, struct net *net)
{
	put_net(sock_net(sk));
	sock_net_set(sk, hold_net(net));
}

static inline struct sock *skb_steal_sock(struct sk_buff *skb)
{
	if (unlikely(skb->sk)) {
		struct sock *sk = skb->sk;

		skb->destructor = NULL;
		skb->sk = NULL;
		return sk;
	}
	return NULL;
}

extern void sock_enable_timestamp(struct sock *sk, int flag);
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)

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 */