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/bitops.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/page_counter.h>
#include <linux/memcontrol.h>
#include <linux/static_key.h>
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/cgroup-defs.h>

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

#include <linux/atomic.h>
#include <linux/refcount.h>
#include <net/dst.h>
#include <net/checksum.h>
#include <net/tcp_states.h>
#include <linux/net_tstamp.h>
#include <net/smc.h>

/*
 * 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(const 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;

typedef __u32 __bitwise __portpair;
typedef __u64 __bitwise __addrpair;

/**
 *	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_dport: placeholder for inet_dport/tw_dport
 *	@skc_num: placeholder for inet_num/tw_num
 *	@skc_family: network address family
 *	@skc_state: Connection state
 *	@skc_reuse: %SO_REUSEADDR setting
 *	@skc_reuseport: %SO_REUSEPORT 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_flags: place holder for sk_flags
 *		%SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
 *		%SO_OOBINLINE settings, %SO_TIMESTAMPING settings
 *	@skc_incoming_cpu: record/match cpu processing incoming packets
 *	@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 on a 8 bytes aligned
	 * address on 64bit arches : cf INET_MATCH()
	 */
	union {
		__addrpair	skc_addrpair;
		struct {
			__be32	skc_daddr;
			__be32	skc_rcv_saddr;
		};
	};
	union  {
		unsigned int	skc_hash;
		__u16		skc_u16hashes[2];
	};
	/* skc_dport && skc_num must be grouped as well */
	union {
		__portpair	skc_portpair;
		struct {
			__be16	skc_dport;
			__u16	skc_num;
		};
	};

	unsigned short		skc_family;
	volatile unsigned char	skc_state;
	unsigned char		skc_reuse:4;
	unsigned char		skc_reuseport:1;
	unsigned char		skc_ipv6only:1;
	unsigned char		skc_net_refcnt:1;
	int			skc_bound_dev_if;
	union {
		struct hlist_node	skc_bind_node;
		struct hlist_node	skc_portaddr_node;
	};
	struct proto		*skc_prot;
	possible_net_t		skc_net;

#if IS_ENABLED(CONFIG_IPV6)
	struct in6_addr		skc_v6_daddr;
	struct in6_addr		skc_v6_rcv_saddr;
#endif

	atomic64_t		skc_cookie;

	/* following fields are padding to force
	 * offset(struct sock, sk_refcnt) == 128 on 64bit arches
	 * assuming IPV6 is enabled. We use this padding differently
	 * for different kind of 'sockets'
	 */
	union {
		unsigned long	skc_flags;
		struct sock	*skc_listener; /* request_sock */
		struct inet_timewait_death_row *skc_tw_dr; /* inet_timewait_sock */
	};
	/*
	 * 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;
	union {
		int		skc_incoming_cpu;
		u32		skc_rcv_wnd;
		u32		skc_tw_rcv_nxt; /* struct tcp_timewait_sock  */
	};

	refcount_t		skc_refcnt;
	/* private: */
	int                     skc_dontcopy_end[0];
	union {
		u32		skc_rxhash;
		u32		skc_window_clamp;
		u32		skc_tw_snd_nxt; /* struct tcp_timewait_sock */
	};
	/* public: */
};

/**
  *	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_kern_sock: True if sock is using kernel lock classes
  *	@sk_rcvbuf: size of receive buffer in bytes
  *	@sk_wq: sock wait queue and async head
  *	@sk_rx_dst: receive input route used by early demux
  *	@sk_dst_cache: destination cache
  *	@sk_dst_pending_confirm: need to confirm neighbour
  *	@sk_policy: flow policy
  *	@sk_receive_queue: incoming packets
  *	@sk_wmem_alloc: transmit queue bytes committed
  *	@sk_tsq_flags: TCP Small Queues flags
  *	@sk_write_queue: Packet sending queue
  *	@sk_omem_alloc: "o" is "option" or "other"
  *	@sk_wmem_queued: persistent queue size
  *	@sk_forward_alloc: space allocated forward
  *	@sk_napi_id: id of the last napi context to receive data for sk
  *	@sk_ll_usec: usecs to busypoll when there is no data
  *	@sk_allocation: allocation mode
  *	@sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
  *	@sk_pacing_status: Pacing status (requested, handled by sch_fq)
  *	@sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE)
  *	@sk_sndbuf: size of send buffer in bytes
  *	@__sk_flags_offset: empty field used to determine location of bitfield
  *	@sk_padding: unused element for alignment
  *	@sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets
  *	@sk_no_check_rx: allow zero checksum in RX 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_gso_max_segs: Maximum number of GSO segments
  *	@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_uid: user id of owner
  *	@sk_priority: %SO_PRIORITY setting
  *	@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_txhash: computed flow hash for use on transmit
  *	@sk_filter: socket filtering instructions
  *	@sk_timer: sock cleanup timer
  *	@sk_stamp: time stamp of last packet received
  *	@sk_tsflags: SO_TIMESTAMPING socket options
  *	@sk_tskey: counter to disambiguate concurrent tstamp requests
  *	@sk_zckey: counter to order MSG_ZEROCOPY notifications
  *	@sk_socket: Identd and reporting IO signals
  *	@sk_user_data: RPC layer private data
  *	@sk_frag: cached page frag
  *	@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_cgrp_data: cgroup data for this cgroup
  *	@sk_memcg: this socket's memory cgroup association
  *	@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
  *	@sk_reuseport_cb: reuseport group container
  *	@sk_rcu: used during RCU grace period
  */
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_portpair		__sk_common.skc_portpair
#define sk_num			__sk_common.skc_num
#define sk_dport		__sk_common.skc_dport
#define sk_addrpair		__sk_common.skc_addrpair
#define sk_daddr		__sk_common.skc_daddr
#define sk_rcv_saddr		__sk_common.skc_rcv_saddr
#define sk_family		__sk_common.skc_family
#define sk_state		__sk_common.skc_state
#define sk_reuse		__sk_common.skc_reuse
#define sk_reuseport		__sk_common.skc_reuseport
#define sk_ipv6only		__sk_common.skc_ipv6only
#define sk_net_refcnt		__sk_common.skc_net_refcnt
#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
#define sk_v6_daddr		__sk_common.skc_v6_daddr
#define sk_v6_rcv_saddr	__sk_common.skc_v6_rcv_saddr
#define sk_cookie		__sk_common.skc_cookie
#define sk_incoming_cpu		__sk_common.skc_incoming_cpu
#define sk_flags		__sk_common.skc_flags
#define sk_rxhash		__sk_common.skc_rxhash

	socket_lock_t		sk_lock;
	atomic_t		sk_drops;
	int			sk_rcvlowat;
	struct sk_buff_head	sk_error_queue;
	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_NET_RX_BUSY_POLL
	unsigned int		sk_ll_usec;
	/* ===== mostly read cache line ===== */
	unsigned int		sk_napi_id;
#endif
	int			sk_rcvbuf;

	struct sk_filter __rcu	*sk_filter;
	union {
		struct socket_wq __rcu	*sk_wq;
		struct socket_wq	*sk_wq_raw;
	};
#ifdef CONFIG_XFRM
	struct xfrm_policy __rcu *sk_policy[2];
#endif
	struct dst_entry	*sk_rx_dst;
	struct dst_entry __rcu	*sk_dst_cache;
	atomic_t		sk_omem_alloc;
	int			sk_sndbuf;

	/* ===== cache line for TX ===== */
	int			sk_wmem_queued;
	refcount_t		sk_wmem_alloc;
	unsigned long		sk_tsq_flags;
	struct sk_buff		*sk_send_head;
	struct sk_buff_head	sk_write_queue;
	__s32			sk_peek_off;
	int			sk_write_pending;
	__u32			sk_dst_pending_confirm;
	u32			sk_pacing_status; /* see enum sk_pacing */
	long			sk_sndtimeo;
	struct timer_list	sk_timer;
	__u32			sk_priority;
	__u32			sk_mark;
	u32			sk_pacing_rate; /* bytes per second */
	u32			sk_max_pacing_rate;
	struct page_frag	sk_frag;
	netdev_features_t	sk_route_caps;
	netdev_features_t	sk_route_nocaps;
	int			sk_gso_type;
	unsigned int		sk_gso_max_size;
	gfp_t			sk_allocation;
	__u32			sk_txhash;

	/*
	 * Because of non atomicity rules, all
	 * changes are protected by socket lock.
	 */
	unsigned int		__sk_flags_offset[0];
#ifdef __BIG_ENDIAN_BITFIELD
#define SK_FL_PROTO_SHIFT  16
#define SK_FL_PROTO_MASK   0x00ff0000

#define SK_FL_TYPE_SHIFT   0
#define SK_FL_TYPE_MASK    0x0000ffff
#else
#define SK_FL_PROTO_SHIFT  8
#define SK_FL_PROTO_MASK   0x0000ff00

#define SK_FL_TYPE_SHIFT   16
#define SK_FL_TYPE_MASK    0xffff0000
#endif

	kmemcheck_bitfield_begin(flags);
	unsigned int		sk_padding : 1,
				sk_kern_sock : 1,
				sk_no_check_tx : 1,
				sk_no_check_rx : 1,
				sk_userlocks : 4,
				sk_protocol  : 8,
				sk_type      : 16;
#define SK_PROTOCOL_MAX U8_MAX
	kmemcheck_bitfield_end(flags);

	u16			sk_gso_max_segs;
	unsigned long	        sk_lingertime;
	struct proto		*sk_prot_creator;
	rwlock_t		sk_callback_lock;
	int			sk_err,
				sk_err_soft;
	u32			sk_ack_backlog;
	u32			sk_max_ack_backlog;
	kuid_t			sk_uid;
	struct pid		*sk_peer_pid;
	const struct cred	*sk_peer_cred;
	long			sk_rcvtimeo;
	ktime_t			sk_stamp;
	u16			sk_tsflags;
	u8			sk_shutdown;
	u32			sk_tskey;
	atomic_t		sk_zckey;
	struct socket		*sk_socket;
	void			*sk_user_data;
#ifdef CONFIG_SECURITY
	void			*sk_security;
#endif
	struct sock_cgroup_data	sk_cgrp_data;
	struct mem_cgroup	*sk_memcg;
	void			(*sk_state_change)(struct sock *sk);
	void			(*sk_data_ready)(struct sock *sk);
	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);
	struct sock_reuseport __rcu	*sk_reuseport_cb;
	struct rcu_head		sk_rcu;
};

enum sk_pacing {
	SK_PACING_NONE		= 0,
	SK_PACING_NEEDED	= 1,
	SK_PACING_FQ		= 2,
};

#define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data)))

#define rcu_dereference_sk_user_data(sk)	rcu_dereference(__sk_user_data((sk)))
#define rcu_assign_sk_user_data(sk, ptr)	rcu_assign_pointer(__sk_user_data((sk)), ptr)

/*
 * 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

int sk_set_peek_off(struct sock *sk, int val);

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

	return 0;
}

static inline void sk_peek_offset_bwd(struct sock *sk, int val)
{
	s32 off = READ_ONCE(sk->sk_peek_off);

	if (unlikely(off >= 0)) {
		off = max_t(s32, off - val, 0);
		WRITE_ONCE(sk->sk_peek_off, off);
	}
}

static inline void sk_peek_offset_fwd(struct sock *sk, int val)
{
	sk_peek_offset_bwd(sk, -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 hlist_entry_safe(sk->sk_node.next, struct sock, sk_node);
}

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

static inline bool 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 bool __sk_del_node_init(struct sock *sk)
{
	if (sk_hashed(sk)) {
		__sk_del_node(sk);
		sk_node_init(&sk->sk_node);
		return true;
	}
	return false;
}

/* 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 __always_inline void sock_hold(struct sock *sk)
{
	refcount_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 __always_inline void __sock_put(struct sock *sk)
{
	refcount_dec(&sk->sk_refcnt);
}

static inline bool sk_del_node_init(struct sock *sk)
{
	bool rc = __sk_del_node_init(sk);

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

static inline bool __sk_nulls_del_node_init_rcu(struct sock *sk)
{
	if (sk_hashed(sk)) {
		hlist_nulls_del_init_rcu(&sk->sk_nulls_node);
		return true;
	}
	return false;
}

static inline bool sk_nulls_del_node_init_rcu(struct sock *sk)
{
	bool rc = __sk_nulls_del_node_init_rcu(sk);

	if (rc) {
		/* paranoid for a while -acme */
		WARN_ON(refcount_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);
	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
	    sk->sk_family == AF_INET6)
		hlist_add_tail_rcu(&sk->sk_node, list);
	else
		hlist_add_head_rcu(&sk->sk_node, list);
}

static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
{
	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
	    sk->sk_family == AF_INET6)
		hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list);
	else
		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, list) \
	hlist_for_each_entry(__sk, list, sk_node)
#define sk_for_each_rcu(__sk, list) \
	hlist_for_each_entry_rcu(__sk, 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) \
	hlist_for_each_entry_from(__sk, 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, tmp, list) \
	hlist_for_each_entry_safe(__sk, tmp, list, sk_node)
#define sk_for_each_bound(__sk, list) \
	hlist_for_each_entry(__sk, list, sk_bind_node)

/**
 * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset
 * @tpos:	the type * to use as a loop cursor.
 * @pos:	the &struct hlist_node to use as a loop cursor.
 * @head:	the head for your list.
 * @offset:	offset of hlist_node within the struct.
 *
 */
#define sk_for_each_entry_offset_rcu(tpos, pos, head, offset)		       \
	for (pos = rcu_dereference((head)->first);			       \
	     pos != NULL &&						       \
		({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;});       \
	     pos = rcu_dereference(pos->next))

static inline struct user_namespace *sk_user_ns(struct sock *sk)
{
	/* Careful only use this in a context where these parameters
	 * can not change and must all be valid, such as recvmsg from
	 * userspace.
	 */
	return sk->sk_socket->file->f_cred->user_ns;
}

/* 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_MEMALLOC, /* VM depends on this socket for swapping */
	SOCK_TIMESTAMPING_RX_SOFTWARE,  /* %SOF_TIMESTAMPING_RX_SOFTWARE */
	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.
		     */
	SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */
	SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
	SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */
};

#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))

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

#ifdef CONFIG_NET
extern struct static_key memalloc_socks;
static inline int sk_memalloc_socks(void)
{
	return static_key_false(&memalloc_socks);
}
#else

static inline int sk_memalloc_socks(void)
{
	return 0;
}

#endif

static inline gfp_t sk_gfp_mask(const struct sock *sk, gfp_t gfp_mask)
{
	return gfp_mask | (sk->sk_allocation & __GFP_MEMALLOC);
}

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 bool sk_acceptq_is_full(const 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(const struct sock *sk)
{
	return sk->sk_wmem_queued >> 1;
}

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

void sk_stream_write_space(struct sock *sk);

/* 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, 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, limit))
		return -ENOBUFS;

	/*
	 * If the skb was allocated from pfmemalloc reserves, only
	 * allow SOCK_MEMALLOC sockets to use it as this socket is
	 * helping free memory
	 */
	if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC))
		return -ENOMEM;

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

int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);

static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
	if (sk_memalloc_socks() && skb_pfmemalloc(skb))
		return __sk_backlog_rcv(sk, skb);

	return sk->sk_backlog_rcv(sk, skb);
}

static inline void sk_incoming_cpu_update(struct sock *sk)
{
	int cpu = raw_smp_processor_id();

	if (unlikely(sk->sk_incoming_cpu != cpu))
		sk->sk_incoming_cpu = cpu;
}

static inline void sock_rps_record_flow_hash(__u32 hash)
{
#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, hash);
	rcu_read_unlock();
#endif
}

static inline void sock_rps_record_flow(const struct sock *sk)
{
#ifdef CONFIG_RPS
	if (static_key_false(&rfs_needed)) {
		/* Reading sk->sk_rxhash might incur an expensive cache line
		 * miss.
		 *
		 * TCP_ESTABLISHED does cover almost all states where RFS
		 * might be useful, and is cheaper [1] than testing :
		 *	IPv4: inet_sk(sk)->inet_daddr
		 * 	IPv6: ipv6_addr_any(&sk->sk_v6_daddr)
		 * OR	an additional socket flag
		 * [1] : sk_state and sk_prot are in the same cache line.
		 */
		if (sk->sk_state == TCP_ESTABLISHED)
			sock_rps_record_flow_hash(sk->sk_rxhash);
	}
#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->hash))
		sk->sk_rxhash = skb->hash;
#endif
}

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

#define sk_wait_event(__sk, __timeo, __condition, __wait)		\
	({	int __rc;						\
		release_sock(__sk);					\
		__rc = __condition;					\
		if (!__rc) {						\
			*(__timeo) = wait_woken(__wait,			\
						TASK_INTERRUPTIBLE,	\
						*(__timeo));		\
		}							\
		sched_annotate_sleep();					\
		lock_sock(__sk);					\
		__rc = __condition;					\
		__rc;							\
	})

int sk_stream_wait_connect(struct sock *sk, long *timeo_p);
int sk_stream_wait_memory(struct sock *sk, long *timeo_p);
void sk_stream_wait_close(struct sock *sk, long timeo_p);
int sk_stream_error(struct sock *sk, int flags, int err);
void sk_stream_kill_queues(struct sock *sk);
void sk_set_memalloc(struct sock *sk);
void sk_clear_memalloc(struct sock *sk);

void __sk_flush_backlog(struct sock *sk);

static inline bool sk_flush_backlog(struct sock *sk)
{
	if (unlikely(READ_ONCE(sk->sk_backlog.tail))) {
		__sk_flush_backlog(sk);
		return true;
	}
	return false;
}

int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb);

struct request_sock_ops;
struct timewait_sock_ops;
struct inet_hashinfo;
struct raw_hashinfo;
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 {