sock.h

/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Definitions for the AF_INET socket handler.
 *
 * Version:	@(#)sock.h	1.0.4	05/13/93
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Corey Minyard <wf-rch!minyard@relay.EU.net>
 *		Florian La Roche <flla@stud.uni-sb.de>
 *
 * Fixes:
 *		Alan Cox	:	Volatiles in skbuff pointers. See
 *					skbuff comments. May be overdone,
 *					better to prove they can be removed
 *					than the reverse.
 *		Alan Cox	:	Added a zapped field for tcp to note
 *					a socket is reset and must stay shut up
 *		Alan Cox	:	New fields for options
 *	Pauline Middelink	:	identd support
 *		Alan Cox	:	Eliminate low level recv/recvfrom
 *		David S. Miller	:	New socket lookup architecture.
 *              Steve Whitehouse:       Default routines for sock_ops
 *              Arnaldo C. Melo :	removed net_pinfo, tp_pinfo and made
 *              			protinfo be just a void pointer, as the
 *              			protocol specific parts were moved to
 *              			respective headers and ipv4/v6, etc now
 *              			use private slabcaches for its socks
 *              Pedro Hortas	:	New flags field for socket options
 *
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 */
#ifndef _SOCK_H
#define _SOCK_H

#include <linux/hardirq.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/list_nulls.h>
#include <linux/timer.h>
#include <linux/cache.h>
#include <linux/lockdep.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>	/* struct sk_buff */
#include <linux/mm.h>
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/memcontrol.h>
#include <linux/res_counter.h>
#include <linux/static_key.h>
#include <linux/aio.h>
#include <linux/sched.h>

#include <linux/filter.h>
#include <linux/rculist_nulls.h>
#include <linux/poll.h>

#include <linux/atomic.h>
#include <net/dst.h>
#include <net/checksum.h>

struct cgroup;
struct cgroup_subsys;
#ifdef CONFIG_NET
int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss);
void mem_cgroup_sockets_destroy(struct cgroup *cgrp);
#else
static inline
int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss)
{
	return 0;
}
static inline
void mem_cgroup_sockets_destroy(struct cgroup *cgrp)
{
}
#endif
/*
 * This structure really needs to be cleaned up.
 * Most of it is for TCP, and not used by any of
 * the other protocols.
 */

/* Define this to get the SOCK_DBG debugging facility. */
#define SOCK_DEBUGGING
#ifdef SOCK_DEBUGGING
#define SOCK_DEBUG(sk, msg...) do { if ((sk) && sock_flag((sk), SOCK_DBG)) \
					printk(KERN_DEBUG msg); } while (0)
#else
/* Validate arguments and do nothing */
static inline __printf(2, 3)
void SOCK_DEBUG(struct sock *sk, const char *msg, ...)
{
}
#endif

/* This is the per-socket lock.  The spinlock provides a synchronization
 * between user contexts and software interrupt processing, whereas the
 * mini-semaphore synchronizes multiple users amongst themselves.
 */
typedef struct {
	spinlock_t		slock;
	int			owned;
	wait_queue_head_t	wq;
	/*
	 * We express the mutex-alike socket_lock semantics
	 * to the lock validator by explicitly managing
	 * the slock as a lock variant (in addition to
	 * the slock itself):
	 */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct lockdep_map dep_map;
#endif
} socket_lock_t;

struct sock;
struct proto;
struct net;

/**
 *	struct sock_common - minimal network layer representation of sockets
 *	@skc_daddr: Foreign IPv4 addr
 *	@skc_rcv_saddr: Bound local IPv4 addr
 *	@skc_hash: hash value used with various protocol lookup tables
 *	@skc_u16hashes: two u16 hash values used by UDP lookup tables
 *	@skc_family: network address family
 *	@skc_state: Connection state
 *	@skc_reuse: %SO_REUSEADDR setting
 *	@skc_bound_dev_if: bound device index if != 0
 *	@skc_bind_node: bind hash linkage for various protocol lookup tables
 *	@skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol
 *	@skc_prot: protocol handlers inside a network family
 *	@skc_net: reference to the network namespace of this socket
 *	@skc_node: main hash linkage for various protocol lookup tables
 *	@skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
 *	@skc_tx_queue_mapping: tx queue number for this connection
 *	@skc_refcnt: reference count
 *
 *	This is the minimal network layer representation of sockets, the header
 *	for struct sock and struct inet_timewait_sock.
 */
struct sock_common {
	/* skc_daddr and skc_rcv_saddr must be grouped :
	 * cf INET_MATCH() and INET_TW_MATCH()
	 */
	__be32			skc_daddr;
	__be32			skc_rcv_saddr;

	union  {
		unsigned int	skc_hash;
		__u16		skc_u16hashes[2];
	};
	unsigned short		skc_family;
	volatile unsigned char	skc_state;
	unsigned char		skc_reuse;
	int			skc_bound_dev_if;
	union {
		struct hlist_node	skc_bind_node;
		struct hlist_nulls_node skc_portaddr_node;
	};
	struct proto		*skc_prot;
#ifdef CONFIG_NET_NS
	struct net	 	*skc_net;
#endif
	/*
	 * fields between dontcopy_begin/dontcopy_end
	 * are not copied in sock_copy()
	 */
	/* private: */
	int			skc_dontcopy_begin[0];
	/* public: */
	union {
		struct hlist_node	skc_node;
		struct hlist_nulls_node skc_nulls_node;
	};
	int			skc_tx_queue_mapping;
	atomic_t		skc_refcnt;
	/* private: */
	int                     skc_dontcopy_end[0];
	/* public: */
};

struct cg_proto;
/**
  *	struct sock - network layer representation of sockets
  *	@__sk_common: shared layout with inet_timewait_sock
  *	@sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN
  *	@sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings
  *	@sk_lock:	synchronizer
  *	@sk_rcvbuf: size of receive buffer in bytes
  *	@sk_wq: sock wait queue and async head
  *	@sk_dst_cache: destination cache
  *	@sk_dst_lock: destination cache lock
  *	@sk_policy: flow policy
  *	@sk_receive_queue: incoming packets
  *	@sk_wmem_alloc: transmit queue bytes committed
  *	@sk_write_queue: Packet sending queue
  *	@sk_async_wait_queue: DMA copied packets
  *	@sk_omem_alloc: "o" is "option" or "other"
  *	@sk_wmem_queued: persistent queue size
  *	@sk_forward_alloc: space allocated forward
  *	@sk_allocation: allocation mode
  *	@sk_sndbuf: size of send buffer in bytes
  *	@sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
  *		   %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
  *	@sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets
  *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
  *	@sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
  *	@sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
  *	@sk_gso_max_size: Maximum GSO segment size to build
  *	@sk_lingertime: %SO_LINGER l_linger setting
  *	@sk_backlog: always used with the per-socket spinlock held
  *	@sk_callback_lock: used with the callbacks in the end of this struct
  *	@sk_error_queue: rarely used
  *	@sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt,
  *			  IPV6_ADDRFORM for instance)
  *	@sk_err: last error
  *	@sk_err_soft: errors that don't cause failure but are the cause of a
  *		      persistent failure not just 'timed out'
  *	@sk_drops: raw/udp drops counter
  *	@sk_ack_backlog: current listen backlog
  *	@sk_max_ack_backlog: listen backlog set in listen()
  *	@sk_priority: %SO_PRIORITY setting
  *	@sk_cgrp_prioidx: socket group's priority map index
  *	@sk_type: socket type (%SOCK_STREAM, etc)
  *	@sk_protocol: which protocol this socket belongs in this network family
  *	@sk_peer_pid: &struct pid for this socket's peer
  *	@sk_peer_cred: %SO_PEERCRED setting
  *	@sk_rcvlowat: %SO_RCVLOWAT setting
  *	@sk_rcvtimeo: %SO_RCVTIMEO setting
  *	@sk_sndtimeo: %SO_SNDTIMEO setting
  *	@sk_rxhash: flow hash received from netif layer
  *	@sk_filter: socket filtering instructions
  *	@sk_protinfo: private area, net family specific, when not using slab
  *	@sk_timer: sock cleanup timer
  *	@sk_stamp: time stamp of last packet received
  *	@sk_socket: Identd and reporting IO signals
  *	@sk_user_data: RPC layer private data
  *	@sk_sndmsg_page: cached page for sendmsg
  *	@sk_sndmsg_off: cached offset for sendmsg
  *	@sk_peek_off: current peek_offset value
  *	@sk_send_head: front of stuff to transmit
  *	@sk_security: used by security modules
  *	@sk_mark: generic packet mark
  *	@sk_classid: this socket's cgroup classid
  *	@sk_cgrp: this socket's cgroup-specific proto data
  *	@sk_write_pending: a write to stream socket waits to start
  *	@sk_state_change: callback to indicate change in the state of the sock
  *	@sk_data_ready: callback to indicate there is data to be processed
  *	@sk_write_space: callback to indicate there is bf sending space available
  *	@sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
  *	@sk_backlog_rcv: callback to process the backlog
  *	@sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
 */
struct sock {
	/*
	 * Now struct inet_timewait_sock also uses sock_common, so please just
	 * don't add nothing before this first member (__sk_common) --acme
	 */
	struct sock_common	__sk_common;
#define sk_node			__sk_common.skc_node
#define sk_nulls_node		__sk_common.skc_nulls_node
#define sk_refcnt		__sk_common.skc_refcnt
#define sk_tx_queue_mapping	__sk_common.skc_tx_queue_mapping

#define sk_dontcopy_begin	__sk_common.skc_dontcopy_begin
#define sk_dontcopy_end		__sk_common.skc_dontcopy_end
#define sk_hash			__sk_common.skc_hash
#define sk_family		__sk_common.skc_family
#define sk_state		__sk_common.skc_state
#define sk_reuse		__sk_common.skc_reuse
#define sk_bound_dev_if		__sk_common.skc_bound_dev_if
#define sk_bind_node		__sk_common.skc_bind_node
#define sk_prot			__sk_common.skc_prot
#define sk_net			__sk_common.skc_net
	socket_lock_t		sk_lock;
	struct sk_buff_head	sk_receive_queue;
	/*
	 * The backlog queue is special, it is always used with
	 * the per-socket spinlock held and requires low latency
	 * access. Therefore we special case it's implementation.
	 * Note : rmem_alloc is in this structure to fill a hole
	 * on 64bit arches, not because its logically part of
	 * backlog.
	 */
	struct {
		atomic_t	rmem_alloc;
		int		len;
		struct sk_buff	*head;
		struct sk_buff	*tail;
	} sk_backlog;
#define sk_rmem_alloc sk_backlog.rmem_alloc
	int			sk_forward_alloc;
#ifdef CONFIG_RPS
	__u32			sk_rxhash;
#endif
	atomic_t		sk_drops;
	int			sk_rcvbuf;

	struct sk_filter __rcu	*sk_filter;
	struct socket_wq __rcu	*sk_wq;

#ifdef CONFIG_NET_DMA
	struct sk_buff_head	sk_async_wait_queue;
#endif

#ifdef CONFIG_XFRM
	struct xfrm_policy	*sk_policy[2];
#endif
	unsigned long 		sk_flags;
	struct dst_entry	*sk_dst_cache;
	spinlock_t		sk_dst_lock;
	atomic_t		sk_wmem_alloc;
	atomic_t		sk_omem_alloc;
	int			sk_sndbuf;
	struct sk_buff_head	sk_write_queue;
	kmemcheck_bitfield_begin(flags);
	unsigned int		sk_shutdown  : 2,
				sk_no_check  : 2,
				sk_userlocks : 4,
				sk_protocol  : 8,
				sk_type      : 16;
	kmemcheck_bitfield_end(flags);
	int			sk_wmem_queued;
	gfp_t			sk_allocation;
	netdev_features_t	sk_route_caps;
	netdev_features_t	sk_route_nocaps;
	int			sk_gso_type;
	unsigned int		sk_gso_max_size;
	int			sk_rcvlowat;
	unsigned long	        sk_lingertime;
	struct sk_buff_head	sk_error_queue;
	struct proto		*sk_prot_creator;
	rwlock_t		sk_callback_lock;
	int			sk_err,
				sk_err_soft;
	unsigned short		sk_ack_backlog;
	unsigned short		sk_max_ack_backlog;
	__u32			sk_priority;
#ifdef CONFIG_CGROUPS
	__u32			sk_cgrp_prioidx;
#endif
	struct pid		*sk_peer_pid;
	const struct cred	*sk_peer_cred;
	long			sk_rcvtimeo;
	long			sk_sndtimeo;
	void			*sk_protinfo;
	struct timer_list	sk_timer;
	ktime_t			sk_stamp;
	struct socket		*sk_socket;
	void			*sk_user_data;
	struct page		*sk_sndmsg_page;
	struct sk_buff		*sk_send_head;
	__u32			sk_sndmsg_off;
	__s32			sk_peek_off;
	int			sk_write_pending;
#ifdef CONFIG_SECURITY
	void			*sk_security;
#endif
	__u32			sk_mark;
	u32			sk_classid;
	struct cg_proto		*sk_cgrp;
	void			(*sk_state_change)(struct sock *sk);
	void			(*sk_data_ready)(struct sock *sk, int bytes);
	void			(*sk_write_space)(struct sock *sk);
	void			(*sk_error_report)(struct sock *sk);
  	int			(*sk_backlog_rcv)(struct sock *sk,
						  struct sk_buff *skb);  
	void                    (*sk_destruct)(struct sock *sk);
};

/*
 * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK
 * or not whether his port will be reused by someone else. SK_FORCE_REUSE
 * on a socket means that the socket will reuse everybody else's port
 * without looking at the other's sk_reuse value.
 */

#define SK_NO_REUSE	0
#define SK_CAN_REUSE	1
#define SK_FORCE_REUSE	2

static inline int sk_peek_offset(struct sock *sk, int flags)
{
	if ((flags & MSG_PEEK) && (sk->sk_peek_off >= 0))
		return sk->sk_peek_off;
	else
		return 0;
}

static inline void sk_peek_offset_bwd(struct sock *sk, int val)
{
	if (sk->sk_peek_off >= 0) {
		if (sk->sk_peek_off >= val)
			sk->sk_peek_off -= val;
		else
			sk->sk_peek_off = 0;
	}
}

static inline void sk_peek_offset_fwd(struct sock *sk, int val)
{
	if (sk->sk_peek_off >= 0)
		sk->sk_peek_off += val;
}

/*
 * Hashed lists helper routines
 */
static inline struct sock *sk_entry(const struct hlist_node *node)
{
	return hlist_entry(node, struct sock, sk_node);
}

static inline struct sock *__sk_head(const struct hlist_head *head)
{
	return hlist_entry(head->first, struct sock, sk_node);
}

static inline struct sock *sk_head(const struct hlist_head *head)
{
	return hlist_empty(head) ? NULL : __sk_head(head);
}

static inline struct sock *__sk_nulls_head(const struct hlist_nulls_head *head)
{
	return hlist_nulls_entry(head->first, struct sock, sk_nulls_node);
}

static inline struct sock *sk_nulls_head(const struct hlist_nulls_head *head)
{
	return hlist_nulls_empty(head) ? NULL : __sk_nulls_head(head);
}

static inline struct sock *sk_next(const struct sock *sk)
{
	return sk->sk_node.next ?
		hlist_entry(sk->sk_node.next, struct sock, sk_node) : NULL;
}

static inline struct sock *sk_nulls_next(const struct sock *sk)
{
	return (!is_a_nulls(sk->sk_nulls_node.next)) ?
		hlist_nulls_entry(sk->sk_nulls_node.next,
				  struct sock, sk_nulls_node) :
		NULL;
}

static inline int sk_unhashed(const struct sock *sk)
{
	return hlist_unhashed(&sk->sk_node);
}

static inline int sk_hashed(const struct sock *sk)
{
	return !sk_unhashed(sk);
}

static __inline__ void sk_node_init(struct hlist_node *node)
{
	node->pprev = NULL;
}

static __inline__ void sk_nulls_node_init(struct hlist_nulls_node *node)
{
	node->pprev = NULL;
}

static __inline__ void __sk_del_node(struct sock *sk)
{
	__hlist_del(&sk->sk_node);
}

/* NB: equivalent to hlist_del_init_rcu */
static __inline__ int __sk_del_node_init(struct sock *sk)
{
	if (sk_hashed(sk)) {
		__sk_del_node(sk);
		sk_node_init(&sk->sk_node);
		return 1;
	}
	return 0;
}

/* Grab socket reference count. This operation is valid only
   when sk is ALREADY grabbed f.e. it is found in hash table
   or a list and the lookup is made under lock preventing hash table
   modifications.
 */

static inline void sock_hold(struct sock *sk)
{
	atomic_inc(&sk->sk_refcnt);
}

/* Ungrab socket in the context, which assumes that socket refcnt
   cannot hit zero, f.e. it is true in context of any socketcall.
 */
static inline void __sock_put(struct sock *sk)
{
	atomic_dec(&sk->sk_refcnt);
}

static __inline__ int sk_del_node_init(struct sock *sk)
{
	int rc = __sk_del_node_init(sk);

	if (rc) {
		/* paranoid for a while -acme */
		WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
		__sock_put(sk);
	}
	return rc;
}
#define sk_del_node_init_rcu(sk)	sk_del_node_init(sk)

static __inline__ int __sk_nulls_del_node_init_rcu(struct sock *sk)
{
	if (sk_hashed(sk)) {
		hlist_nulls_del_init_rcu(&sk->sk_nulls_node);
		return 1;
	}
	return 0;
}

static __inline__ int sk_nulls_del_node_init_rcu(struct sock *sk)
{
	int rc = __sk_nulls_del_node_init_rcu(sk);

	if (rc) {
		/* paranoid for a while -acme */
		WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
		__sock_put(sk);
	}
	return rc;
}

static __inline__ void __sk_add_node(struct sock *sk, struct hlist_head *list)
{
	hlist_add_head(&sk->sk_node, list);
}

static __inline__ void sk_add_node(struct sock *sk, struct hlist_head *list)
{
	sock_hold(sk);
	__sk_add_node(sk, list);
}

static __inline__ void sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
{
	sock_hold(sk);
	hlist_add_head_rcu(&sk->sk_node, list);
}

static __inline__ void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
{
	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
}

static __inline__ void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
{
	sock_hold(sk);
	__sk_nulls_add_node_rcu(sk, list);
}

static __inline__ void __sk_del_bind_node(struct sock *sk)
{
	__hlist_del(&sk->sk_bind_node);
}

static __inline__ void sk_add_bind_node(struct sock *sk,
					struct hlist_head *list)
{
	hlist_add_head(&sk->sk_bind_node, list);
}

#define sk_for_each(__sk, node, list) \
	hlist_for_each_entry(__sk, node, list, sk_node)
#define sk_for_each_rcu(__sk, node, list) \
	hlist_for_each_entry_rcu(__sk, node, list, sk_node)
#define sk_nulls_for_each(__sk, node, list) \
	hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node)
#define sk_nulls_for_each_rcu(__sk, node, list) \
	hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node)
#define sk_for_each_from(__sk, node) \
	if (__sk && ({ node = &(__sk)->sk_node; 1; })) \
		hlist_for_each_entry_from(__sk, node, sk_node)
#define sk_nulls_for_each_from(__sk, node) \
	if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \
		hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node)
#define sk_for_each_safe(__sk, node, tmp, list) \
	hlist_for_each_entry_safe(__sk, node, tmp, list, sk_node)
#define sk_for_each_bound(__sk, node, list) \
	hlist_for_each_entry(__sk, node, list, sk_bind_node)

/* Sock flags */
enum sock_flags {
	SOCK_DEAD,
	SOCK_DONE,
	SOCK_URGINLINE,
	SOCK_KEEPOPEN,
	SOCK_LINGER,
	SOCK_DESTROY,
	SOCK_BROADCAST,
	SOCK_TIMESTAMP,
	SOCK_ZAPPED,
	SOCK_USE_WRITE_QUEUE, /* whether to call sk->sk_write_space in sock_wfree */
	SOCK_DBG, /* %SO_DEBUG setting */
	SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */
	SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
	SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
	SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
	SOCK_TIMESTAMPING_TX_HARDWARE,  /* %SOF_TIMESTAMPING_TX_HARDWARE */
	SOCK_TIMESTAMPING_TX_SOFTWARE,  /* %SOF_TIMESTAMPING_TX_SOFTWARE */
	SOCK_TIMESTAMPING_RX_HARDWARE,  /* %SOF_TIMESTAMPING_RX_HARDWARE */
	SOCK_TIMESTAMPING_RX_SOFTWARE,  /* %SOF_TIMESTAMPING_RX_SOFTWARE */
	SOCK_TIMESTAMPING_SOFTWARE,     /* %SOF_TIMESTAMPING_SOFTWARE */
	SOCK_TIMESTAMPING_RAW_HARDWARE, /* %SOF_TIMESTAMPING_RAW_HARDWARE */
	SOCK_TIMESTAMPING_SYS_HARDWARE, /* %SOF_TIMESTAMPING_SYS_HARDWARE */
	SOCK_FASYNC, /* fasync() active */
	SOCK_RXQ_OVFL,
	SOCK_ZEROCOPY, /* buffers from userspace */
	SOCK_WIFI_STATUS, /* push wifi status to userspace */
	SOCK_NOFCS, /* Tell NIC not to do the Ethernet FCS.
		     * Will use last 4 bytes of packet sent from
		     * user-space instead.
		     */
};

static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)
{
	nsk->sk_flags = osk->sk_flags;
}

static inline void sock_set_flag(struct sock *sk, enum sock_flags flag)
{
	__set_bit(flag, &sk->sk_flags);
}

static inline void sock_reset_flag(struct sock *sk, enum sock_flags flag)
{
	__clear_bit(flag, &sk->sk_flags);
}

static inline int sock_flag(struct sock *sk, enum sock_flags flag)
{
	return test_bit(flag, &sk->sk_flags);
}

static inline void sk_acceptq_removed(struct sock *sk)
{
	sk->sk_ack_backlog--;
}

static inline void sk_acceptq_added(struct sock *sk)
{
	sk->sk_ack_backlog++;
}

static inline int sk_acceptq_is_full(struct sock *sk)
{
	return sk->sk_ack_backlog > sk->sk_max_ack_backlog;
}

/*
 * Compute minimal free write space needed to queue new packets.
 */
static inline int sk_stream_min_wspace(struct sock *sk)
{
	return sk->sk_wmem_queued >> 1;
}

static inline int sk_stream_wspace(struct sock *sk)
{
	return sk->sk_sndbuf - sk->sk_wmem_queued;
}

extern void sk_stream_write_space(struct sock *sk);

static inline int sk_stream_memory_free(struct sock *sk)
{
	return sk->sk_wmem_queued < sk->sk_sndbuf;
}

/* OOB backlog add */
static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
{
	/* dont let skb dst not refcounted, we are going to leave rcu lock */
	skb_dst_force(skb);

	if (!sk->sk_backlog.tail)
		sk->sk_backlog.head = skb;
	else
		sk->sk_backlog.tail->next = skb;

	sk->sk_backlog.tail = skb;
	skb->next = NULL;
}

/*
 * Take into account size of receive queue and backlog queue
 * Do not take into account this skb truesize,
 * to allow even a single big packet to come.
 */
static inline bool sk_rcvqueues_full(const struct sock *sk, const struct sk_buff *skb,
				     unsigned int limit)
{
	unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc);

	return qsize > limit;
}

/* The per-socket spinlock must be held here. */
static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb,
					      unsigned int limit)
{
	if (sk_rcvqueues_full(sk, skb, limit))
		return -ENOBUFS;

	__sk_add_backlog(sk, skb);
	sk->sk_backlog.len += skb->truesize;
	return 0;
}

static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
	return sk->sk_backlog_rcv(sk, skb);
}

static inline void sock_rps_record_flow(const struct sock *sk)
{
#ifdef CONFIG_RPS
	struct rps_sock_flow_table *sock_flow_table;

	rcu_read_lock();
	sock_flow_table = rcu_dereference(rps_sock_flow_table);
	rps_record_sock_flow(sock_flow_table, sk->sk_rxhash);
	rcu_read_unlock();
#endif
}

static inline void sock_rps_reset_flow(const struct sock *sk)
{
#ifdef CONFIG_RPS
	struct rps_sock_flow_table *sock_flow_table;

	rcu_read_lock();
	sock_flow_table = rcu_dereference(rps_sock_flow_table);
	rps_reset_sock_flow(sock_flow_table, sk->sk_rxhash);
	rcu_read_unlock();
#endif
}

static inline void sock_rps_save_rxhash(struct sock *sk,
					const struct sk_buff *skb)
{
#ifdef CONFIG_RPS
	if (unlikely(sk->sk_rxhash != skb->rxhash)) {
		sock_rps_reset_flow(sk);
		sk->sk_rxhash = skb->rxhash;
	}
#endif
}

static inline void sock_rps_reset_rxhash(struct sock *sk)
{
#ifdef CONFIG_RPS
	sock_rps_reset_flow(sk);
	sk->sk_rxhash = 0;
#endif
}

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

struct request_sock_ops;
struct timewait_sock_ops;
struct inet_hashinfo;
struct raw_hashinfo;
struct module;

/* 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);
	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);  	 
#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 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);
	void			(*rehash)(struct sock *sk);
	int			(*get_port)(struct sock *sk, unsigned short snum);
	void			(*clear_sk)(struct sock *sk, int size);

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

	/* 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;
	} h;

	struct module		*owner;

	char			name[32];

	struct list_head	node;
#ifdef SOCK_REFCNT_DEBUG
	atomic_t		socks;
#endif
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
	/*
	 * cgroup specific init/deinit functions. Called once for all
	 * protocols that implement it, from cgroups populate function.
	 * This function has to setup any files the protocol want to
	 * appear in the kmem cgroup filesystem.
	 */
	int			(*init_cgroup)(struct cgroup *cgrp,
					       struct cgroup_subsys *ss);
	void			(*destroy_cgroup)(struct cgroup *cgrp);
	struct cg_proto		*(*proto_cgroup)(struct mem_cgroup *memcg);
#endif
};

struct cg_proto {
	void			(*enter_memory_pressure)(struct sock *sk);
	struct res_counter	*memory_allocated;	/* Current allocated memory. */
	struct percpu_counter	*sockets_allocated;	/* Current number of sockets. */
	int			*memory_pressure;
	long			*sysctl_mem;
	/*
	 * memcg field is used to find which memcg we belong directly
	 * Each memcg struct can hold more than one cg_proto, so container_of
	 * won't really cut.
	 *
	 * The elegant solution would be having an inverse function to
	 * proto_cgroup in struct proto, but that means polluting the structure
	 * for everybody, instead of just for memcg users.
	 */
	struct mem_cgroup	*memcg;
};

extern int proto_register(struct proto *prot, int alloc_slab);
extern 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));
}

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 */

#if defined(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) && defined(CONFIG_NET)
extern struct static_key memcg_socket_limit_enabled;
static inline struct cg_proto *parent_cg_proto(struct proto *proto,
					       struct cg_proto *cg_proto)
{
	return proto->proto_cgroup(parent_mem_cgroup(cg_proto->memcg));
}
#define mem_cgroup_sockets_enabled static_key_false(&memcg_socket_limit_enabled)
#else
#define mem_cgroup_sockets_enabled 0
static inline struct cg_proto *parent_cg_proto(struct proto *proto,
					       struct cg_proto *cg_proto)
{
	return NULL;
}
#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_cgrp)
		return !!*sk->sk_cgrp->memory_pressure;

	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;

	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
		struct cg_proto *cg_proto = sk->sk_cgrp;
		struct proto *prot = sk->sk_prot;

		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
			if (*cg_proto->memory_pressure)
				*cg_proto->memory_pressure = 0;
	}

}

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

	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
		struct cg_proto *cg_proto = sk->sk_cgrp;
		struct proto *prot = sk->sk_prot;

		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
			cg_proto->enter_memory_pressure(sk);
	}

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

static inline long sk_prot_mem_limits(const struct sock *sk, int index)
{
	long *prot = sk->sk_prot->sysctl_mem;
	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
		prot = sk->sk_cgrp->sysctl_mem;
	return prot[index];
}

static inline void memcg_memory_allocated_add(struct cg_proto *prot,
					      unsigned long amt,
					      int *parent_status)
{
	struct res_counter *fail;
	int ret;

	ret = res_counter_charge_nofail(prot->memory_allocated,
					amt << PAGE_SHIFT, &fail);
	if (ret < 0)
		*parent_status = OVER_LIMIT;
}

static inline void memcg_memory_allocated_sub(struct cg_proto *prot,
					      unsigned long amt)
{
	res_counter_uncharge(prot->memory_allocated, amt << PAGE_SHIFT);
}

static inline u64 memcg_memory_allocated_read(struct cg_proto *prot)
{
	u64 ret;
	ret = res_counter_read_u64(prot->memory_allocated, RES_USAGE);
	return ret >> PAGE_SHIFT;
}

static inline long
sk_memory_allocated(const struct sock *sk)
{
	struct proto *prot = sk->sk_prot;
	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
		return memcg_memory_allocated_read(sk->sk_cgrp);

	return atomic_long_read(prot->memory_allocated);
}

static inline long
sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status)
{
	struct proto *prot = sk->sk_prot;

	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
		memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status);
		/* update the root cgroup regardless */
		atomic_long_add_return(amt, prot->memory_allocated);
		return memcg_memory_allocated_read(sk->sk_cgrp);
	}

	return atomic_long_add_return(amt, prot->memory_allocated);
}

static inline void
sk_memory_allocated_sub(struct sock *sk, int amt)
{
	struct proto *prot = sk->sk_prot;

	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
		memcg_memory_allocated_sub(sk->sk_cgrp, amt);

	atomic_long_sub(amt, prot->memory_allocated);
}

static inline void sk_sockets_allocated_dec(struct sock *sk)
{
	struct proto *prot = sk->sk_prot;

	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
		struct cg_proto *cg_proto = sk->sk_cgrp;

		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
			percpu_counter_dec(cg_proto->sockets_allocated);
	}

	percpu_counter_dec(prot->sockets_allocated);
}

static inline void sk_sockets_allocated_inc(struct sock *sk)
{
	struct proto *prot = sk->sk_prot;

	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
		struct cg_proto *cg_proto = sk->sk_cgrp;

		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
			percpu_counter_inc(cg_proto->sockets_allocated);
	}

	percpu_counter_inc(prot->sockets_allocated);
}

static inline int
sk_sockets_allocated_read_positive(struct sock *sk)
{
	struct proto *prot = sk->sk_prot;

	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
		return percpu_counter_read_positive(sk->sk_cgrp->sockets_allocated);

	return percpu_counter_read_positive(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 */
extern void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc);
extern int sock_prot_inuse_get(struct net *net, struct proto *proto);
#else
static void inline 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 void __sk_prot_rehash(struct sock *sk)
{
	sk->sk_prot->unhash(sk);
	sk->sk_prot->hash(sk);
}

void sk_prot_clear_portaddr_nulls(struct sock *sk, int size);

/* 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 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,