[mirror_ubuntu-bionic-kernel.git] / include / net / inet_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 inet_sock
 *
 * Authors:	Many, reorganised here by
 * 		Arnaldo Carvalho de Melo <acme@mandriva.com>
 *
 *		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 _INET_SOCK_H
#define _INET_SOCK_H

#include <linux/bitops.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/jhash.h>
#include <linux/netdevice.h>

#include <net/flow.h>
#include <net/sock.h>
#include <net/request_sock.h>
#include <net/netns/hash.h>
#include <net/tcp_states.h>
#include <net/l3mdev.h>

/** struct ip_options - IP Options
 *
 * @faddr - Saved first hop address
 * @nexthop - Saved nexthop address in LSRR and SSRR
 * @is_strictroute - Strict source route
 * @srr_is_hit - Packet destination addr was our one
 * @is_changed - IP checksum more not valid
 * @rr_needaddr - Need to record addr of outgoing dev
 * @ts_needtime - Need to record timestamp
 * @ts_needaddr - Need to record addr of outgoing dev
 */
struct ip_options {
	__be32		faddr;
	__be32		nexthop;
	unsigned char	optlen;
	unsigned char	srr;
	unsigned char	rr;
	unsigned char	ts;
	unsigned char	is_strictroute:1,
			srr_is_hit:1,
			is_changed:1,
			rr_needaddr:1,
			ts_needtime:1,
			ts_needaddr:1;
	unsigned char	router_alert;
	unsigned char	cipso;
	unsigned char	__pad2;
	unsigned char	__data[0];
};

struct ip_options_rcu {
	struct rcu_head rcu;
	struct ip_options opt;
};

struct ip_options_data {
	struct ip_options_rcu	opt;
	char			data[40];
};

struct inet_request_sock {
	struct request_sock	req;
#define ir_loc_addr		req.__req_common.skc_rcv_saddr
#define ir_rmt_addr		req.__req_common.skc_daddr
#define ir_num			req.__req_common.skc_num
#define ir_rmt_port		req.__req_common.skc_dport
#define ir_v6_rmt_addr		req.__req_common.skc_v6_daddr
#define ir_v6_loc_addr		req.__req_common.skc_v6_rcv_saddr
#define ir_iif			req.__req_common.skc_bound_dev_if
#define ir_cookie		req.__req_common.skc_cookie
#define ireq_net		req.__req_common.skc_net
#define ireq_state		req.__req_common.skc_state
#define ireq_family		req.__req_common.skc_family

	u16			snd_wscale : 4,
				rcv_wscale : 4,
				tstamp_ok  : 1,
				sack_ok	   : 1,
				wscale_ok  : 1,
				ecn_ok	   : 1,
				acked	   : 1,
				no_srccheck: 1,
				smc_ok	   : 1;
	u32                     ir_mark;
	union {
		struct ip_options_rcu __rcu	*ireq_opt;
#if IS_ENABLED(CONFIG_IPV6)
		struct {
			struct ipv6_txoptions	*ipv6_opt;
			struct sk_buff		*pktopts;
		};
#endif
	};
};

static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
{
	return (struct inet_request_sock *)sk;
}

static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb)
{
	if (!sk->sk_mark && sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept)
		return skb->mark;

	return sk->sk_mark;
}

static inline int inet_request_bound_dev_if(const struct sock *sk,
					    struct sk_buff *skb)
{
#ifdef CONFIG_NET_L3_MASTER_DEV
	struct net *net = sock_net(sk);

	if (!sk->sk_bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept)
		return l3mdev_master_ifindex_by_index(net, skb->skb_iif);
#endif

	return sk->sk_bound_dev_if;
}

struct inet_cork {
	unsigned int		flags;
	__be32			addr;
	struct ip_options	*opt;
	unsigned int		fragsize;
	int			length; /* Total length of all frames */
	struct dst_entry	*dst;
	u8			tx_flags;
	__u8			ttl;
	__s16			tos;
	char			priority;
};

struct inet_cork_full {
	struct inet_cork	base;
	struct flowi		fl;
};

struct ip_mc_socklist;
struct ipv6_pinfo;
struct rtable;

/** struct inet_sock - representation of INET sockets
 *
 * @sk - ancestor class
 * @pinet6 - pointer to IPv6 control block
 * @inet_daddr - Foreign IPv4 addr
 * @inet_rcv_saddr - Bound local IPv4 addr
 * @inet_dport - Destination port
 * @inet_num - Local port
 * @inet_saddr - Sending source
 * @uc_ttl - Unicast TTL
 * @inet_sport - Source port
 * @inet_id - ID counter for DF pkts
 * @tos - TOS
 * @mc_ttl - Multicasting TTL
 * @is_icsk - is this an inet_connection_sock?
 * @uc_index - Unicast outgoing device index
 * @mc_index - Multicast device index
 * @mc_list - Group array
 * @cork - info to build ip hdr on each ip frag while socket is corked
 */
struct inet_sock {
	/* sk and pinet6 has to be the first two members of inet_sock */
	struct sock		sk;
#if IS_ENABLED(CONFIG_IPV6)
	struct ipv6_pinfo	*pinet6;
#endif
	/* Socket demultiplex comparisons on incoming packets. */
#define inet_daddr		sk.__sk_common.skc_daddr
#define inet_rcv_saddr		sk.__sk_common.skc_rcv_saddr
#define inet_dport		sk.__sk_common.skc_dport
#define inet_num		sk.__sk_common.skc_num

	__be32			inet_saddr;
	__s16			uc_ttl;
	__u16			cmsg_flags;
	__be16			inet_sport;
	__u16			inet_id;

	struct ip_options_rcu __rcu	*inet_opt;
	int			rx_dst_ifindex;
	__u8			tos;
	__u8			min_ttl;
	__u8			mc_ttl;
	__u8			pmtudisc;
	__u8			recverr:1,
				is_icsk:1,
				freebind:1,
				hdrincl:1,
				mc_loop:1,
				transparent:1,
				mc_all:1,
				nodefrag:1;
	__u8			bind_address_no_port:1,
				defer_connect:1; /* Indicates that fastopen_connect is set
						  * and cookie exists so we defer connect
						  * until first data frame is written
						  */
	__u8			rcv_tos;
	__u8			convert_csum;
	int			uc_index;
	int			mc_index;
	__be32			mc_addr;
	struct ip_mc_socklist __rcu	*mc_list;
	struct inet_cork_full	cork;
};

#define IPCORK_OPT	1	/* ip-options has been held in ipcork.opt */
#define IPCORK_ALLFRAG	2	/* always fragment (for ipv6 for now) */

/* cmsg flags for inet */
#define IP_CMSG_PKTINFO		BIT(0)
#define IP_CMSG_TTL		BIT(1)
#define IP_CMSG_TOS		BIT(2)
#define IP_CMSG_RECVOPTS	BIT(3)
#define IP_CMSG_RETOPTS		BIT(4)
#define IP_CMSG_PASSSEC		BIT(5)
#define IP_CMSG_ORIGDSTADDR	BIT(6)
#define IP_CMSG_CHECKSUM	BIT(7)
#define IP_CMSG_RECVFRAGSIZE	BIT(8)

/**
 * sk_to_full_sk - Access to a full socket
 * @sk: pointer to a socket
 *
 * SYNACK messages might be attached to request sockets.
 * Some places want to reach the listener in this case.
 */
static inline struct sock *sk_to_full_sk(struct sock *sk)
{
#ifdef CONFIG_INET
	if (sk && sk->sk_state == TCP_NEW_SYN_RECV)
		sk = inet_reqsk(sk)->rsk_listener;
#endif
	return sk;
}

/* sk_to_full_sk() variant with a const argument */
static inline const struct sock *sk_const_to_full_sk(const struct sock *sk)
{
#ifdef CONFIG_INET
	if (sk && sk->sk_state == TCP_NEW_SYN_RECV)
		sk = ((const struct request_sock *)sk)->rsk_listener;
#endif
	return sk;
}

static inline struct sock *skb_to_full_sk(const struct sk_buff *skb)
{
	return sk_to_full_sk(skb->sk);
}

static inline struct inet_sock *inet_sk(const struct sock *sk)
{
	return (struct inet_sock *)sk;
}

static inline void __inet_sk_copy_descendant(struct sock *sk_to,
					     const struct sock *sk_from,
					     const int ancestor_size)
{
	memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1,
	       sk_from->sk_prot->obj_size - ancestor_size);
}
#if !(IS_ENABLED(CONFIG_IPV6))
static inline void inet_sk_copy_descendant(struct sock *sk_to,
					   const struct sock *sk_from)
{
	__inet_sk_copy_descendant(sk_to, sk_from, sizeof(struct inet_sock));
}
#endif

int inet_sk_rebuild_header(struct sock *sk);

static inline unsigned int __inet_ehashfn(const __be32 laddr,
					  const __u16 lport,
					  const __be32 faddr,
					  const __be16 fport,
					  u32 initval)
{
	return jhash_3words((__force __u32) laddr,
			    (__force __u32) faddr,
			    ((__u32) lport) << 16 | (__force __u32)fport,
			    initval);
}

struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
				      struct sock *sk_listener,
				      bool attach_listener);

static inline __u8 inet_sk_flowi_flags(const struct sock *sk)
{
	__u8 flags = 0;

	if (inet_sk(sk)->transparent || inet_sk(sk)->hdrincl)
		flags |= FLOWI_FLAG_ANYSRC;
	return flags;
}

static inline void inet_inc_convert_csum(struct sock *sk)
{
	inet_sk(sk)->convert_csum++;
}

static inline void inet_dec_convert_csum(struct sock *sk)
{
	if (inet_sk(sk)->convert_csum > 0)
		inet_sk(sk)->convert_csum--;
}

static inline bool inet_get_convert_csum(struct sock *sk)
{
	return !!inet_sk(sk)->convert_csum;
}

#endif	/* _INET_SOCK_H */
Commit	Line	Data
	1	/*
	2	* INET An implementation of the TCP/IP protocol suite for the LINUX
	3	* operating system. INET is implemented using the BSD Socket
	4	* interface as the means of communication with the user level.
	5	*
	6	* Definitions for inet_sock
	7	*
	8	* Authors: Many, reorganised here by
	9	* Arnaldo Carvalho de Melo <acme@mandriva.com>
	10	*
	11	* This program is free software; you can redistribute it and/or
	12	* modify it under the terms of the GNU General Public License
	13	* as published by the Free Software Foundation; either version
	14	* 2 of the License, or (at your option) any later version.
	15	*/
	16	#ifndef _INET_SOCK_H
	17	#define _INET_SOCK_H
	18
	19	#include <linux/bitops.h>
	20	#include <linux/string.h>
	21	#include <linux/types.h>
	22	#include <linux/jhash.h>
	23	#include <linux/netdevice.h>
	24
	25	#include <net/flow.h>
	26	#include <net/sock.h>
	27	#include <net/request_sock.h>
	28	#include <net/netns/hash.h>
	29	#include <net/tcp_states.h>
	30	#include <net/l3mdev.h>
	31
	32	/** struct ip_options - IP Options
	33	*
	34	* @faddr - Saved first hop address
	35	* @nexthop - Saved nexthop address in LSRR and SSRR
	36	* @is_strictroute - Strict source route
	37	* @srr_is_hit - Packet destination addr was our one
	38	* @is_changed - IP checksum more not valid
	39	* @rr_needaddr - Need to record addr of outgoing dev
	40	* @ts_needtime - Need to record timestamp
	41	* @ts_needaddr - Need to record addr of outgoing dev
	42	*/
	43	struct ip_options {
	44	__be32 faddr;
	45	__be32 nexthop;
	46	unsigned char optlen;
	47	unsigned char srr;
	48	unsigned char rr;
	49	unsigned char ts;
	50	unsigned char is_strictroute:1,
	51	srr_is_hit:1,
	52	is_changed:1,
	53	rr_needaddr:1,
	54	ts_needtime:1,
	55	ts_needaddr:1;
	56	unsigned char router_alert;
	57	unsigned char cipso;
	58	unsigned char __pad2;
	59	unsigned char __data[0];
	60	};
	61
	62	struct ip_options_rcu {
	63	struct rcu_head rcu;
	64	struct ip_options opt;
	65	};
	66
	67	struct ip_options_data {
	68	struct ip_options_rcu opt;
	69	char data[40];
	70	};
	71
	72	struct inet_request_sock {
	73	struct request_sock req;
	74	#define ir_loc_addr req.__req_common.skc_rcv_saddr
	75	#define ir_rmt_addr req.__req_common.skc_daddr
	76	#define ir_num req.__req_common.skc_num
	77	#define ir_rmt_port req.__req_common.skc_dport
	78	#define ir_v6_rmt_addr req.__req_common.skc_v6_daddr
	79	#define ir_v6_loc_addr req.__req_common.skc_v6_rcv_saddr
	80	#define ir_iif req.__req_common.skc_bound_dev_if
	81	#define ir_cookie req.__req_common.skc_cookie
	82	#define ireq_net req.__req_common.skc_net
	83	#define ireq_state req.__req_common.skc_state
	84	#define ireq_family req.__req_common.skc_family
	85
	86	u16 snd_wscale : 4,
	87	rcv_wscale : 4,
	88	tstamp_ok : 1,
	89	sack_ok : 1,
	90	wscale_ok : 1,
	91	ecn_ok : 1,
	92	acked : 1,
	93	no_srccheck: 1,
	94	smc_ok : 1;
	95	u32 ir_mark;
	96	union {
	97	struct ip_options_rcu __rcu *ireq_opt;
	98	#if IS_ENABLED(CONFIG_IPV6)
	99	struct {
	100	struct ipv6_txoptions *ipv6_opt;
	101	struct sk_buff *pktopts;
	102	};
	103	#endif
	104	};
	105	};
	106
	107	static inline struct inet_request_sock inet_rsk(const struct request_sock sk)
	108	{
	109	return (struct inet_request_sock *)sk;
	110	}
	111
	112	static inline u32 inet_request_mark(const struct sock sk, struct sk_buff skb)
	113	{
	114	if (!sk->sk_mark && sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept)
	115	return skb->mark;
	116
	117	return sk->sk_mark;
	118	}
	119
	120	static inline int inet_request_bound_dev_if(const struct sock *sk,
	121	struct sk_buff *skb)
	122	{
	123	#ifdef CONFIG_NET_L3_MASTER_DEV
	124	struct net *net = sock_net(sk);
	125
	126	if (!sk->sk_bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept)
	127	return l3mdev_master_ifindex_by_index(net, skb->skb_iif);
	128	#endif
	129
	130	return sk->sk_bound_dev_if;
	131	}
	132
	133	struct inet_cork {
	134	unsigned int flags;
	135	__be32 addr;
	136	struct ip_options *opt;
	137	unsigned int fragsize;
	138	int length; /* Total length of all frames */
	139	struct dst_entry *dst;
	140	u8 tx_flags;
	141	__u8 ttl;
	142	__s16 tos;
	143	char priority;
	144	};
	145
	146	struct inet_cork_full {
	147	struct inet_cork base;
	148	struct flowi fl;
	149	};
	150
	151	struct ip_mc_socklist;
	152	struct ipv6_pinfo;
	153	struct rtable;
	154
	155	/** struct inet_sock - representation of INET sockets
	156	*
	157	* @sk - ancestor class
	158	* @pinet6 - pointer to IPv6 control block
	159	* @inet_daddr - Foreign IPv4 addr
	160	* @inet_rcv_saddr - Bound local IPv4 addr
	161	* @inet_dport - Destination port
	162	* @inet_num - Local port
	163	* @inet_saddr - Sending source
	164	* @uc_ttl - Unicast TTL
	165	* @inet_sport - Source port
	166	* @inet_id - ID counter for DF pkts
	167	* @tos - TOS
	168	* @mc_ttl - Multicasting TTL
	169	* @is_icsk - is this an inet_connection_sock?
	170	* @uc_index - Unicast outgoing device index
	171	* @mc_index - Multicast device index
	172	* @mc_list - Group array
	173	* @cork - info to build ip hdr on each ip frag while socket is corked
	174	*/
	175	struct inet_sock {
	176	/* sk and pinet6 has to be the first two members of inet_sock */
	177	struct sock sk;
	178	#if IS_ENABLED(CONFIG_IPV6)
	179	struct ipv6_pinfo *pinet6;
	180	#endif
	181	/* Socket demultiplex comparisons on incoming packets. */
	182	#define inet_daddr sk.__sk_common.skc_daddr
	183	#define inet_rcv_saddr sk.__sk_common.skc_rcv_saddr
	184	#define inet_dport sk.__sk_common.skc_dport
	185	#define inet_num sk.__sk_common.skc_num
	186
	187	__be32 inet_saddr;
	188	__s16 uc_ttl;
	189	__u16 cmsg_flags;
	190	__be16 inet_sport;
	191	__u16 inet_id;
	192
	193	struct ip_options_rcu __rcu *inet_opt;
	194	int rx_dst_ifindex;
	195	__u8 tos;
	196	__u8 min_ttl;
	197	__u8 mc_ttl;
	198	__u8 pmtudisc;
	199	__u8 recverr:1,
	200	is_icsk:1,
	201	freebind:1,
	202	hdrincl:1,
	203	mc_loop:1,
	204	transparent:1,
	205	mc_all:1,
	206	nodefrag:1;
	207	__u8 bind_address_no_port:1,
	208	defer_connect:1; /* Indicates that fastopen_connect is set
	209	* and cookie exists so we defer connect
	210	* until first data frame is written
	211	*/
	212	__u8 rcv_tos;
	213	__u8 convert_csum;
	214	int uc_index;
	215	int mc_index;
	216	__be32 mc_addr;
	217	struct ip_mc_socklist __rcu *mc_list;
	218	struct inet_cork_full cork;
	219	};
	220
	221	#define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */
	222	#define IPCORK_ALLFRAG 2 /* always fragment (for ipv6 for now) */
	223
	224	/* cmsg flags for inet */
	225	#define IP_CMSG_PKTINFO BIT(0)
	226	#define IP_CMSG_TTL BIT(1)
	227	#define IP_CMSG_TOS BIT(2)
	228	#define IP_CMSG_RECVOPTS BIT(3)
	229	#define IP_CMSG_RETOPTS BIT(4)
	230	#define IP_CMSG_PASSSEC BIT(5)
	231	#define IP_CMSG_ORIGDSTADDR BIT(6)
	232	#define IP_CMSG_CHECKSUM BIT(7)
	233	#define IP_CMSG_RECVFRAGSIZE BIT(8)
	234
	235	/**
	236	* sk_to_full_sk - Access to a full socket
	237	* @sk: pointer to a socket
	238	*
	239	* SYNACK messages might be attached to request sockets.
	240	* Some places want to reach the listener in this case.
	241	*/
	242	static inline struct sock sk_to_full_sk(struct sock sk)
	243	{
	244	#ifdef CONFIG_INET
	245	if (sk && sk->sk_state == TCP_NEW_SYN_RECV)
	246	sk = inet_reqsk(sk)->rsk_listener;
	247	#endif
	248	return sk;
	249	}
	250
	251	/* sk_to_full_sk() variant with a const argument */
	252	static inline const struct sock sk_const_to_full_sk(const struct sock sk)
	253	{
	254	#ifdef CONFIG_INET
	255	if (sk && sk->sk_state == TCP_NEW_SYN_RECV)
	256	sk = ((const struct request_sock *)sk)->rsk_listener;
	257	#endif
	258	return sk;
	259	}
	260
	261	static inline struct sock skb_to_full_sk(const struct sk_buff skb)
	262	{
	263	return sk_to_full_sk(skb->sk);
	264	}
	265
	266	static inline struct inet_sock inet_sk(const struct sock sk)
	267	{
	268	return (struct inet_sock *)sk;
	269	}
	270
	271	static inline void __inet_sk_copy_descendant(struct sock *sk_to,
	272	const struct sock *sk_from,
	273	const int ancestor_size)
	274	{
	275	memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1,
	276	sk_from->sk_prot->obj_size - ancestor_size);
	277	}
	278	#if !(IS_ENABLED(CONFIG_IPV6))
	279	static inline void inet_sk_copy_descendant(struct sock *sk_to,
	280	const struct sock *sk_from)
	281	{
	282	__inet_sk_copy_descendant(sk_to, sk_from, sizeof(struct inet_sock));
	283	}
	284	#endif
	285
	286	int inet_sk_rebuild_header(struct sock *sk);
	287
	288	static inline unsigned int __inet_ehashfn(const __be32 laddr,
	289	const __u16 lport,
	290	const __be32 faddr,
	291	const __be16 fport,
	292	u32 initval)
	293	{
	294	return jhash_3words((__force __u32) laddr,
	295	(__force __u32) faddr,
	296	((__u32) lport) << 16 \| (__force __u32)fport,
	297	initval);
	298	}
	299
	300	struct request_sock inet_reqsk_alloc(const struct request_sock_ops ops,
	301	struct sock *sk_listener,
	302	bool attach_listener);
	303
	304	static inline __u8 inet_sk_flowi_flags(const struct sock *sk)
	305	{
	306	__u8 flags = 0;
	307
	308	if (inet_sk(sk)->transparent \|\| inet_sk(sk)->hdrincl)
	309	flags \|= FLOWI_FLAG_ANYSRC;
	310	return flags;
	311	}
	312
	313	static inline void inet_inc_convert_csum(struct sock *sk)
	314	{
	315	inet_sk(sk)->convert_csum++;
	316	}
	317
	318	static inline void inet_dec_convert_csum(struct sock *sk)
	319	{
	320	if (inet_sk(sk)->convert_csum > 0)
	321	inet_sk(sk)->convert_csum--;
	322	}
	323
	324	static inline bool inet_get_convert_csum(struct sock *sk)
	325	{
	326	return !!inet_sk(sk)->convert_csum;
	327	}
	328
	329	#endif /* _INET_SOCK_H */