sock.h

struct smc_hashinfo;
struct module;

/*
 * caches using SLAB_TYPESAFE_BY_RCU should let .next pointer from nulls nodes
 * un-modified. Special care is taken when initializing object to zero.
 */
static inline void sk_prot_clear_nulls(struct sock *sk, int size)
{
	if (offsetof(struct sock, sk_node.next) != 0)
		memset(sk, 0, offsetof(struct sock, sk_node.next));
	memset(&sk->sk_node.pprev, 0,
	       size - offsetof(struct sock, sk_node.pprev));
}

/* Networking protocol blocks we attach to sockets.
 * socket layer -> transport layer interface
 */
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,
					  bool kern);

	int			(*ioctl)(struct sock *sk, int cmd,
					 unsigned long arg);
	int			(*init)(struct sock *sk);
	void			(*destroy)(struct sock *sk);
	void			(*shutdown)(struct sock *sk, int how);
	int			(*setsockopt)(struct sock *sk, int level,
					int optname, char __user *optval,
					unsigned int optlen);
	int			(*getsockopt)(struct sock *sk, int level,
					int optname, char __user *optval,
					int __user *option);
	void			(*keepalive)(struct sock *sk, int valbool);
#ifdef CONFIG_COMPAT
	int			(*compat_setsockopt)(struct sock *sk,
					int level,
					int optname, char __user *optval,
					unsigned int optlen);
	int			(*compat_getsockopt)(struct sock *sk,
					int level,
					int optname, char __user *optval,
					int __user *option);
	int			(*compat_ioctl)(struct sock *sk,
					unsigned int cmd, unsigned long arg);
#endif
	int			(*sendmsg)(struct sock *sk, struct msghdr *msg,
					   size_t len);
	int			(*recvmsg)(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);

	void		(*release_cb)(struct sock *sk);

	/* Keeping track of sk's, looking them up, and port selection methods. */
	int			(*hash)(struct sock *sk);
	void			(*unhash)(struct sock *sk);
	void			(*rehash)(struct sock *sk);
	int			(*get_port)(struct sock *sk, unsigned short snum);

	/* Keeping track of sockets in use */
#ifdef CONFIG_PROC_FS
	unsigned int		inuse_idx;
#endif

	bool			(*stream_memory_free)(const struct sock *sk);
	/* Memory pressure */
	void			(*enter_memory_pressure)(struct sock *sk);
	atomic_long_t		*memory_allocated;	/* Current allocated memory. */
	struct percpu_counter	*sockets_allocated;	/* Current number of sockets. */
	/*
	 * Pressure flag: try to collapse.
	 * Technical note: it is used by multiple contexts non atomically.
	 * All the __sk_mem_schedule() is of this nature: accounting
	 * is strict, actions are advisory and have some latency.
	 */
	int			*memory_pressure;
	long			*sysctl_mem;
	int			*sysctl_wmem;
	int			*sysctl_rmem;
	int			max_header;
	bool			no_autobind;

	struct kmem_cache	*slab;
	unsigned int		obj_size;
	int			slab_flags;

	struct percpu_counter	*orphan_count;

	struct request_sock_ops	*rsk_prot;
	struct timewait_sock_ops *twsk_prot;

	union {
		struct inet_hashinfo	*hashinfo;
		struct udp_table	*udp_table;
		struct raw_hashinfo	*raw_hash;
		struct smc_hashinfo	*smc_hash;
	} h;

	struct module		*owner;

	char			name[32];

	struct list_head	node;
#ifdef SOCK_REFCNT_DEBUG
	atomic_t		socks;
#endif
	int			(*diag_destroy)(struct sock *sk, int err);
};

int proto_register(struct proto *prot, int alloc_slab);
void proto_unregister(struct proto *prot);

#ifdef SOCK_REFCNT_DEBUG
static inline void sk_refcnt_debug_inc(struct sock *sk)
{
	atomic_inc(&sk->sk_prot->socks);
}

static inline void sk_refcnt_debug_dec(struct sock *sk)
{
	atomic_dec(&sk->sk_prot->socks);
	printk(KERN_DEBUG "%s socket %p released, %d are still alive\n",
	       sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks));
}

static inline void sk_refcnt_debug_release(const struct sock *sk)
{
	if (atomic_read(&sk->sk_refcnt) != 1)
		printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n",
		       sk->sk_prot->name, sk, atomic_read(&sk->sk_refcnt));
}
#else /* SOCK_REFCNT_DEBUG */
#define sk_refcnt_debug_inc(sk) do { } while (0)
#define sk_refcnt_debug_dec(sk) do { } while (0)
#define sk_refcnt_debug_release(sk) do { } while (0)
#endif /* SOCK_REFCNT_DEBUG */

static inline bool sk_stream_memory_free(const struct sock *sk)
{
	if (sk->sk_wmem_queued >= sk->sk_sndbuf)
		return false;

	return sk->sk_prot->stream_memory_free ?
		sk->sk_prot->stream_memory_free(sk) : true;
}

static inline bool sk_stream_is_writeable(const struct sock *sk)
{
	return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) &&
	       sk_stream_memory_free(sk);
}

static inline int sk_under_cgroup_hierarchy(struct sock *sk,
					    struct cgroup *ancestor)
{
#ifdef CONFIG_SOCK_CGROUP_DATA
	return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data),
				    ancestor);
#else
	return -ENOTSUPP;
#endif
}

static inline bool sk_has_memory_pressure(const struct sock *sk)
{
	return sk->sk_prot->memory_pressure != NULL;
}

static inline bool sk_under_memory_pressure(const struct sock *sk)
{
	if (!sk->sk_prot->memory_pressure)
		return false;

	if (mem_cgroup_sockets_enabled && sk->sk_memcg &&
	    mem_cgroup_under_socket_pressure(sk->sk_memcg))
		return true;

	return !!*sk->sk_prot->memory_pressure;
}

static inline void sk_leave_memory_pressure(struct sock *sk)
{
	int *memory_pressure = sk->sk_prot->memory_pressure;

	if (!memory_pressure)
		return;

	if (*memory_pressure)
		*memory_pressure = 0;
}

static inline void sk_enter_memory_pressure(struct sock *sk)
{
	if (!sk->sk_prot->enter_memory_pressure)
		return;

	sk->sk_prot->enter_memory_pressure(sk);
}

static inline long
sk_memory_allocated(const struct sock *sk)
{
	return atomic_long_read(sk->sk_prot->memory_allocated);
}

static inline long
sk_memory_allocated_add(struct sock *sk, int amt)
{
	return atomic_long_add_return(amt, sk->sk_prot->memory_allocated);
}

static inline void
sk_memory_allocated_sub(struct sock *sk, int amt)
{
	atomic_long_sub(amt, sk->sk_prot->memory_allocated);
}

static inline void sk_sockets_allocated_dec(struct sock *sk)
{
	percpu_counter_dec(sk->sk_prot->sockets_allocated);
}

static inline void sk_sockets_allocated_inc(struct sock *sk)
{
	percpu_counter_inc(sk->sk_prot->sockets_allocated);
}

static inline int
sk_sockets_allocated_read_positive(struct sock *sk)
{
	return percpu_counter_read_positive(sk->sk_prot->sockets_allocated);
}

static inline int
proto_sockets_allocated_sum_positive(struct proto *prot)
{
	return percpu_counter_sum_positive(prot->sockets_allocated);
}

static inline long
proto_memory_allocated(struct proto *prot)
{
	return atomic_long_read(prot->memory_allocated);
}

static inline bool
proto_memory_pressure(struct proto *prot)
{
	if (!prot->memory_pressure)
		return false;
	return !!*prot->memory_pressure;
}


#ifdef CONFIG_PROC_FS
/* Called with local bh disabled */
void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc);
int sock_prot_inuse_get(struct net *net, struct proto *proto);
#else
static inline void sock_prot_inuse_add(struct net *net, struct proto *prot,
		int inc)
{
}
#endif


/* With per-bucket locks this operation is not-atomic, so that
 * this version is not worse.
 */
static inline int __sk_prot_rehash(struct sock *sk)
{
	sk->sk_prot->unhash(sk);
	return sk->sk_prot->hash(sk);
}

/* 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

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
 */
int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind);
int __sk_mem_schedule(struct sock *sk, int size, int kind);
void __sk_mem_reduce_allocated(struct sock *sk, int amount);
void __sk_mem_reclaim(struct sock *sk, int amount);

/* We used to have PAGE_SIZE here, but systems with 64KB pages
 * do not necessarily have 16x time more memory than 4KB ones.
 */
#define SK_MEM_QUANTUM 4096
#define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM)
#define SK_MEM_SEND	0
#define SK_MEM_RECV	1

/* sysctl_mem values are in pages, we convert them in SK_MEM_QUANTUM units */
static inline long sk_prot_mem_limits(const struct sock *sk, int index)
{
	long val = sk->sk_prot->sysctl_mem[index];

#if PAGE_SIZE > SK_MEM_QUANTUM
	val <<= PAGE_SHIFT - SK_MEM_QUANTUM_SHIFT;
#elif PAGE_SIZE < SK_MEM_QUANTUM
	val >>= SK_MEM_QUANTUM_SHIFT - PAGE_SHIFT;
#endif
	return val;
}

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

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

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

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

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, sk->sk_forward_alloc);
}

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, sk->sk_forward_alloc - 1);
}

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;

	/* Avoid a possible overflow.
	 * TCP send queues can make this happen, if sk_mem_reclaim()
	 * is not called and more than 2 GBytes are released at once.
	 *
	 * If we reach 2 MBytes, reclaim 1 MBytes right now, there is
	 * no need to hold that much forward allocation anyway.
	 */
	if (unlikely(sk->sk_forward_alloc >= 1 << 21))
		__sk_mem_reclaim(sk, 1 << 20);
}

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);
}

static inline void sock_release_ownership(struct sock *sk)
{
	if (sk->sk_lock.owned) {
		sk->sk_lock.owned = 0;

		/* The sk_lock has mutex_unlock() semantics: */
		mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
	}
}

/*
 * 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)

#ifdef CONFIG_LOCKDEP
static inline bool lockdep_sock_is_held(const struct sock *csk)
{
	struct sock *sk = (struct sock *)csk;

	return lockdep_is_held(&sk->sk_lock) ||
	       lockdep_is_held(&sk->sk_lock.slock);
}
#endif

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

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

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))

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);
}

/* 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.
 */

static inline void sock_owned_by_me(const struct sock *sk)
{
#ifdef CONFIG_LOCKDEP
	WARN_ON_ONCE(!lockdep_sock_is_held(sk) && debug_locks);
#endif
}

static inline bool sock_owned_by_user(const struct sock *sk)
{
	sock_owned_by_me(sk);
	return sk->sk_lock.owned;
}

/* no reclassification while locks are held */
static inline bool sock_allow_reclassification(const struct sock *csk)
{
	struct sock *sk = (struct sock *)csk;

	return !sk->sk_lock.owned && !spin_is_locked(&sk->sk_lock.slock);
}

struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
		      struct proto *prot, int kern);
void sk_free(struct sock *sk);
void sk_destruct(struct sock *sk);
struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority);
void sk_free_unlock_clone(struct sock *sk);

struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
			     gfp_t priority);
void __sock_wfree(struct sk_buff *skb);
void sock_wfree(struct sk_buff *skb);
void skb_orphan_partial(struct sk_buff *skb);
void sock_rfree(struct sk_buff *skb);
void sock_efree(struct sk_buff *skb);
#ifdef CONFIG_INET
void sock_edemux(struct sk_buff *skb);
#else
#define sock_edemux sock_efree
#endif

int sock_setsockopt(struct socket *sock, int level, int op,
		    char __user *optval, unsigned int optlen);

int sock_getsockopt(struct socket *sock, int level, int op,
		    char __user *optval, int __user *optlen);
struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
				    int noblock, int *errcode);
struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
				     unsigned long data_len, int noblock,
				     int *errcode, int max_page_order);
void *sock_kmalloc(struct sock *sk, int size, gfp_t priority);
void sock_kfree_s(struct sock *sk, void *mem, int size);
void sock_kzfree_s(struct sock *sk, void *mem, int size);
void sk_send_sigurg(struct sock *sk);

struct sockcm_cookie {
	u32 mark;
	u16 tsflags;
};

int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
		     struct sockcm_cookie *sockc);
int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
		   struct sockcm_cookie *sockc);

/*
 * Functions to fill in entries in struct proto_ops when a protocol
 * does not implement a particular function.
 */
int sock_no_bind(struct socket *, struct sockaddr *, int);
int sock_no_connect(struct socket *, struct sockaddr *, int, int);
int sock_no_socketpair(struct socket *, struct socket *);
int sock_no_accept(struct socket *, struct socket *, int, bool);
int sock_no_getname(struct socket *, struct sockaddr *, int *, int);
unsigned int sock_no_poll(struct file *, struct socket *,
			  struct poll_table_struct *);
int sock_no_ioctl(struct socket *, unsigned int, unsigned long);
int sock_no_listen(struct socket *, int);
int sock_no_shutdown(struct socket *, int);
int sock_no_getsockopt(struct socket *, int , int, char __user *, int __user *);
int sock_no_setsockopt(struct socket *, int, int, char __user *, unsigned int);
int sock_no_sendmsg(struct socket *, struct msghdr *, size_t);
int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int);
int sock_no_mmap(struct file *file, struct socket *sock,
		 struct vm_area_struct *vma);
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.
 */
int sock_common_getsockopt(struct socket *sock, int level, int optname,
				  char __user *optval, int __user *optlen);
int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
			int flags);
int sock_common_setsockopt(struct socket *sock, int level, int optname,
				  char __user *optval, unsigned int optlen);
int compat_sock_common_getsockopt(struct socket *sock, int level,
		int optname, char __user *optval, int __user *optlen);
int compat_sock_common_setsockopt(struct socket *sock, int level,
		int optname, char __user *optval, unsigned int optlen);

void sk_common_release(struct sock *sk);

/*
 *	Default socket callbacks and setup code
 */

/* Initialise core socket variables */
void sock_init_data(struct socket *sock, struct sock *sk);

/*
 * 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);
}
/* Generic version of sock_put(), dealing with all sockets
 * (TCP_TIMEWAIT, TCP_NEW_SYN_RECV, ESTABLISHED...)
 */
void sock_gen_put(struct sock *sk);

int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested,
		     unsigned int trim_cap, bool refcounted);
static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
				 const int nested)
{
	return __sk_receive_skb(sk, skb, nested, 1, true);
}

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);
	sk->sk_uid = SOCK_INODE(parent)->i_uid;
	security_sock_graft(sk, parent);
	write_unlock_bh(&sk->sk_callback_lock);
}

kuid_t sock_i_uid(struct sock *sk);
unsigned long sock_i_ino(struct sock *sk);

static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk)
{
	return sk ? sk->sk_uid : make_kuid(net->user_ns, 0);
}

static inline u32 net_tx_rndhash(void)
{
	u32 v = prandom_u32();

	return v ?: 1;
}

static inline void sk_set_txhash(struct sock *sk)
{
	sk->sk_txhash = net_tx_rndhash();
}

static inline void sk_rethink_txhash(struct sock *sk)
{
	if (sk->sk_txhash)
		sk_set_txhash(sk);
}

static inline struct dst_entry *
__sk_dst_get(struct sock *sk)
{
	return rcu_dereference_check(sk->sk_dst_cache,
				     lockdep_sock_is_held(sk));
}

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 && !atomic_inc_not_zero(&dst->__refcnt))
		dst = NULL;
	rcu_read_unlock();
	return dst;
}

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

	sk_rethink_txhash(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_tx_queue_clear(sk);
			sk->sk_dst_pending_confirm = 0;
		}
	}
}

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

	sk_tx_queue_clear(sk);
	sk->sk_dst_pending_confirm = 0;
	old_dst = rcu_dereference_protected(sk->sk_dst_cache,
					    lockdep_sock_is_held(sk));
	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)
{
	struct dst_entry *old_dst;

	sk_tx_queue_clear(sk);
	sk->sk_dst_pending_confirm = 0;
	old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst);
	dst_release(old_dst);
}

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

static inline void
sk_dst_reset(struct sock *sk)
{
	sk_dst_set(sk, NULL);
}

struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);

struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie);

static inline void sk_dst_confirm(struct sock *sk)
{
	if (!sk->sk_dst_pending_confirm)
		sk->sk_dst_pending_confirm = 1;
}

static inline void sock_confirm_neigh(struct sk_buff *skb, struct neighbour *n)
{
	if (skb_get_dst_pending_confirm(skb)) {
		struct sock *sk = skb->sk;
		unsigned long now = jiffies;

		/* avoid dirtying neighbour */
		if (n->confirmed != now)
			n->confirmed = now;
		if (sk && sk->sk_dst_pending_confirm)
			sk->sk_dst_pending_confirm = 0;
	}
}

bool sk_mc_loop(struct sock *sk);

static inline bool sk_can_gso(const struct sock *sk)
{
	return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type);
}

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 bool sk_check_csum_caps(struct sock *sk)
{
	return (sk->sk_route_caps & NETIF_F_HW_CSUM) ||
	       (sk->sk_family == PF_INET &&
		(sk->sk_route_caps & NETIF_F_IP_CSUM)) ||
	       (sk->sk_family == PF_INET6 &&
		(sk->sk_route_caps & NETIF_F_IPV6_CSUM));
}

static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb,
					   struct iov_iter *from, char *to,
					   int copy, int offset)
{
	if (skb->ip_summed == CHECKSUM_NONE) {
		__wsum csum = 0;
		if (!csum_and_copy_from_iter_full(to, copy, &csum, from))
			return -EFAULT;
		skb->csum = csum_block_add(skb->csum, csum, offset);
	} else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) {
		if (!copy_from_iter_full_nocache(to, copy, from))
			return -EFAULT;
	} else if (!copy_from_iter_full(to, copy, from))
		return -EFAULT;

	return 0;
}

static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb,
				       struct iov_iter *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, struct iov_iter *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;
}

/**
 * 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 bool sk_has_allocations(const struct sock *sk)
{
	return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk);
}

/**
 * skwq_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 skwq_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 skwq_has_sleeper(struct socket_wq *wq)
{
	return wq && wq_has_sleeper(&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)