ip_vs.h 38.8 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5
/*
 *      IP Virtual Server
 *      data structure and functionality definitions
 */

6 7
#ifndef _NET_IP_VS_H
#define _NET_IP_VS_H
L
Linus Torvalds 已提交
8

9
#include <linux/ip_vs.h>                /* definitions shared with userland */
L
Linus Torvalds 已提交
10

11
/* old ipvsadm versions still include this file directly */
L
Linus Torvalds 已提交
12 13
#ifdef __KERNEL__

14 15 16
#include <asm/types.h>                  /* for __uXX types */

#include <linux/sysctl.h>               /* for ctl_path */
L
Linus Torvalds 已提交
17 18 19 20
#include <linux/list.h>                 /* for struct list_head */
#include <linux/spinlock.h>             /* for struct rwlock_t */
#include <asm/atomic.h>                 /* for struct atomic_t */
#include <linux/compiler.h>
21
#include <linux/timer.h>
L
Linus Torvalds 已提交
22

23
#include <net/checksum.h>
24
#include <linux/netfilter.h>		/* for union nf_inet_addr */
25
#include <linux/ip.h>
26 27
#include <linux/ipv6.h>			/* for struct ipv6hdr */
#include <net/ipv6.h>			/* for ipv6_addr_copy */
J
Julian Anastasov 已提交
28
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
29 30
#include <net/netfilter/nf_conntrack.h>
#endif
31 32 33 34 35 36 37 38 39
#include <net/net_namespace.h>		/* Netw namespace */

/*
 * Generic access of ipvs struct
 */
static inline struct netns_ipvs *net_ipvs(struct net* net)
{
	return net->ipvs;
}
40 41 42 43
/*
 * Get net ptr from skb in traffic cases
 * use skb_sknet when call is from userland (ioctl or netlink)
 */
44
static inline struct net *skb_net(const struct sk_buff *skb)
45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71
{
#ifdef CONFIG_NET_NS
#ifdef CONFIG_IP_VS_DEBUG
	/*
	 * This is used for debug only.
	 * Start with the most likely hit
	 * End with BUG
	 */
	if (likely(skb->dev && skb->dev->nd_net))
		return dev_net(skb->dev);
	if (skb_dst(skb)->dev)
		return dev_net(skb_dst(skb)->dev);
	WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n",
		      __func__, __LINE__);
	if (likely(skb->sk && skb->sk->sk_net))
		return sock_net(skb->sk);
	pr_err("There is no net ptr to find in the skb in %s() line:%d\n",
		__func__, __LINE__);
	BUG();
#else
	return dev_net(skb->dev ? : skb_dst(skb)->dev);
#endif
#else
	return &init_net;
#endif
}

72
static inline struct net *skb_sknet(const struct sk_buff *skb)
73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92
{
#ifdef CONFIG_NET_NS
#ifdef CONFIG_IP_VS_DEBUG
	/* Start with the most likely hit */
	if (likely(skb->sk && skb->sk->sk_net))
		return sock_net(skb->sk);
	WARN(skb->dev, "Maybe skb_net should be used instead in %s() line:%d\n",
		       __func__, __LINE__);
	if (likely(skb->dev && skb->dev->nd_net))
		return dev_net(skb->dev);
	pr_err("There is no net ptr to find in the skb in %s() line:%d\n",
		__func__, __LINE__);
	BUG();
#else
	return sock_net(skb->sk);
#endif
#else
	return &init_net;
#endif
}
93 94 95 96 97 98 99 100 101 102 103 104
/*
 * This one needed for single_open_net since net is stored directly in
 * private not as a struct i.e. seq_file_net cant be used.
 */
static inline struct net *seq_file_single_net(struct seq_file *seq)
{
#ifdef CONFIG_NET_NS
	return (struct net *)seq->private;
#else
	return &init_net;
#endif
}
105 106 107 108 109

/* Connections' size value needed by ip_vs_ctl.c */
extern int ip_vs_conn_tab_size;


110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158
struct ip_vs_iphdr {
	int len;
	__u8 protocol;
	union nf_inet_addr saddr;
	union nf_inet_addr daddr;
};

static inline void
ip_vs_fill_iphdr(int af, const void *nh, struct ip_vs_iphdr *iphdr)
{
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6) {
		const struct ipv6hdr *iph = nh;
		iphdr->len = sizeof(struct ipv6hdr);
		iphdr->protocol = iph->nexthdr;
		ipv6_addr_copy(&iphdr->saddr.in6, &iph->saddr);
		ipv6_addr_copy(&iphdr->daddr.in6, &iph->daddr);
	} else
#endif
	{
		const struct iphdr *iph = nh;
		iphdr->len = iph->ihl * 4;
		iphdr->protocol = iph->protocol;
		iphdr->saddr.ip = iph->saddr;
		iphdr->daddr.ip = iph->daddr;
	}
}

static inline void ip_vs_addr_copy(int af, union nf_inet_addr *dst,
				   const union nf_inet_addr *src)
{
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6)
		ipv6_addr_copy(&dst->in6, &src->in6);
	else
#endif
	dst->ip = src->ip;
}

static inline int ip_vs_addr_equal(int af, const union nf_inet_addr *a,
				   const union nf_inet_addr *b)
{
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6)
		return ipv6_addr_equal(&a->in6, &b->in6);
#endif
	return a->ip == b->ip;
}

L
Linus Torvalds 已提交
159
#ifdef CONFIG_IP_VS_DEBUG
160 161
#include <linux/net.h>

L
Linus Torvalds 已提交
162
extern int ip_vs_get_debug_level(void);
163 164 165 166 167 168 169 170

static inline const char *ip_vs_dbg_addr(int af, char *buf, size_t buf_len,
					 const union nf_inet_addr *addr,
					 int *idx)
{
	int len;
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6)
H
Harvey Harrison 已提交
171
		len = snprintf(&buf[*idx], buf_len - *idx, "[%pI6]",
172
			       &addr->in6) + 1;
173 174
	else
#endif
H
Harvey Harrison 已提交
175 176
		len = snprintf(&buf[*idx], buf_len - *idx, "%pI4",
			       &addr->ip) + 1;
177 178 179 180 181 182

	*idx += len;
	BUG_ON(*idx > buf_len + 1);
	return &buf[*idx - len];
}

H
Hannes Eder 已提交
183 184 185 186 187 188 189 190 191 192 193 194 195
#define IP_VS_DBG_BUF(level, msg, ...)					\
	do {								\
		char ip_vs_dbg_buf[160];				\
		int ip_vs_dbg_idx = 0;					\
		if (level <= ip_vs_get_debug_level())			\
			printk(KERN_DEBUG pr_fmt(msg), ##__VA_ARGS__);	\
	} while (0)
#define IP_VS_ERR_BUF(msg...)						\
	do {								\
		char ip_vs_dbg_buf[160];				\
		int ip_vs_dbg_idx = 0;					\
		pr_err(msg);						\
	} while (0)
196 197

/* Only use from within IP_VS_DBG_BUF() or IP_VS_ERR_BUF macros */
H
Hannes Eder 已提交
198 199 200 201 202 203 204 205 206 207 208 209 210 211 212
#define IP_VS_DBG_ADDR(af, addr)					\
	ip_vs_dbg_addr(af, ip_vs_dbg_buf,				\
		       sizeof(ip_vs_dbg_buf), addr,			\
		       &ip_vs_dbg_idx)

#define IP_VS_DBG(level, msg, ...)					\
	do {								\
		if (level <= ip_vs_get_debug_level())			\
			printk(KERN_DEBUG pr_fmt(msg), ##__VA_ARGS__);	\
	} while (0)
#define IP_VS_DBG_RL(msg, ...)						\
	do {								\
		if (net_ratelimit())					\
			printk(KERN_DEBUG pr_fmt(msg), ##__VA_ARGS__);	\
	} while (0)
213
#define IP_VS_DBG_PKT(level, af, pp, skb, ofs, msg)			\
H
Hannes Eder 已提交
214 215
	do {								\
		if (level <= ip_vs_get_debug_level())			\
216
			pp->debug_packet(af, pp, skb, ofs, msg);	\
H
Hannes Eder 已提交
217
	} while (0)
218
#define IP_VS_DBG_RL_PKT(level, af, pp, skb, ofs, msg)			\
H
Hannes Eder 已提交
219 220 221
	do {								\
		if (level <= ip_vs_get_debug_level() &&			\
		    net_ratelimit())					\
222
			pp->debug_packet(af, pp, skb, ofs, msg);	\
H
Hannes Eder 已提交
223
	} while (0)
L
Linus Torvalds 已提交
224
#else	/* NO DEBUGGING at ALL */
225 226
#define IP_VS_DBG_BUF(level, msg...)  do {} while (0)
#define IP_VS_ERR_BUF(msg...)  do {} while (0)
L
Linus Torvalds 已提交
227 228
#define IP_VS_DBG(level, msg...)  do {} while (0)
#define IP_VS_DBG_RL(msg...)  do {} while (0)
229 230
#define IP_VS_DBG_PKT(level, af, pp, skb, ofs, msg)	do {} while (0)
#define IP_VS_DBG_RL_PKT(level, af, pp, skb, ofs, msg)	do {} while (0)
L
Linus Torvalds 已提交
231 232 233
#endif

#define IP_VS_BUG() BUG()
234
#define IP_VS_ERR_RL(msg, ...)						\
H
Hannes Eder 已提交
235 236
	do {								\
		if (net_ratelimit())					\
237
			pr_err(msg, ##__VA_ARGS__);			\
H
Hannes Eder 已提交
238
	} while (0)
L
Linus Torvalds 已提交
239 240 241

#ifdef CONFIG_IP_VS_DEBUG
#define EnterFunction(level)						\
H
Hannes Eder 已提交
242 243 244 245 246 247 248 249 250 251 252 253 254
	do {								\
		if (level <= ip_vs_get_debug_level())			\
			printk(KERN_DEBUG				\
			       pr_fmt("Enter: %s, %s line %i\n"),	\
			       __func__, __FILE__, __LINE__);		\
	} while (0)
#define LeaveFunction(level)						\
	do {								\
		if (level <= ip_vs_get_debug_level())			\
			printk(KERN_DEBUG				\
			       pr_fmt("Leave: %s, %s line %i\n"),	\
			       __func__, __FILE__, __LINE__);		\
	} while (0)
L
Linus Torvalds 已提交
255 256 257 258 259 260 261 262 263 264 265
#else
#define EnterFunction(level)   do {} while (0)
#define LeaveFunction(level)   do {} while (0)
#endif

#define	IP_VS_WAIT_WHILE(expr)	while (expr) { cpu_relax(); }


/*
 *      The port number of FTP service (in network order).
 */
266 267
#define FTPPORT  cpu_to_be16(21)
#define FTPDATA  cpu_to_be16(20)
L
Linus Torvalds 已提交
268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302

/*
 *      TCP State Values
 */
enum {
	IP_VS_TCP_S_NONE = 0,
	IP_VS_TCP_S_ESTABLISHED,
	IP_VS_TCP_S_SYN_SENT,
	IP_VS_TCP_S_SYN_RECV,
	IP_VS_TCP_S_FIN_WAIT,
	IP_VS_TCP_S_TIME_WAIT,
	IP_VS_TCP_S_CLOSE,
	IP_VS_TCP_S_CLOSE_WAIT,
	IP_VS_TCP_S_LAST_ACK,
	IP_VS_TCP_S_LISTEN,
	IP_VS_TCP_S_SYNACK,
	IP_VS_TCP_S_LAST
};

/*
 *	UDP State Values
 */
enum {
	IP_VS_UDP_S_NORMAL,
	IP_VS_UDP_S_LAST,
};

/*
 *	ICMP State Values
 */
enum {
	IP_VS_ICMP_S_NORMAL,
	IP_VS_ICMP_S_LAST,
};

303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322
/*
 *	SCTP State Values
 */
enum ip_vs_sctp_states {
	IP_VS_SCTP_S_NONE,
	IP_VS_SCTP_S_INIT_CLI,
	IP_VS_SCTP_S_INIT_SER,
	IP_VS_SCTP_S_INIT_ACK_CLI,
	IP_VS_SCTP_S_INIT_ACK_SER,
	IP_VS_SCTP_S_ECHO_CLI,
	IP_VS_SCTP_S_ECHO_SER,
	IP_VS_SCTP_S_ESTABLISHED,
	IP_VS_SCTP_S_SHUT_CLI,
	IP_VS_SCTP_S_SHUT_SER,
	IP_VS_SCTP_S_SHUT_ACK_CLI,
	IP_VS_SCTP_S_SHUT_ACK_SER,
	IP_VS_SCTP_S_CLOSED,
	IP_VS_SCTP_S_LAST
};

L
Linus Torvalds 已提交
323 324 325 326 327 328 329 330 331 332 333 334
/*
 *	Delta sequence info structure
 *	Each ip_vs_conn has 2 (output AND input seq. changes).
 *      Only used in the VS/NAT.
 */
struct ip_vs_seq {
	__u32			init_seq;	/* Add delta from this seq */
	__u32			delta;		/* Delta in sequence numbers */
	__u32			previous_delta;	/* Delta in sequence numbers
						   before last resized pkt */
};

335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351
/*
 * counters per cpu
 */
struct ip_vs_counters {
	__u32		conns;		/* connections scheduled */
	__u32		inpkts;		/* incoming packets */
	__u32		outpkts;	/* outgoing packets */
	__u64		inbytes;	/* incoming bytes */
	__u64		outbytes;	/* outgoing bytes */
};
/*
 * Stats per cpu
 */
struct ip_vs_cpu_stats {
	struct ip_vs_counters   ustats;
	struct u64_stats_sync   syncp;
};
L
Linus Torvalds 已提交
352 353

/*
354
 *	IPVS statistics objects
L
Linus Torvalds 已提交
355
 */
356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371
struct ip_vs_estimator {
	struct list_head	list;

	u64			last_inbytes;
	u64			last_outbytes;
	u32			last_conns;
	u32			last_inpkts;
	u32			last_outpkts;

	u32			cps;
	u32			inpps;
	u32			outpps;
	u32			inbps;
	u32			outbps;
};

E
Eric Dumazet 已提交
372
struct ip_vs_stats {
373
	struct ip_vs_stats_user	ustats;		/* statistics */
374
	struct ip_vs_estimator	est;		/* estimator */
375 376
	struct ip_vs_cpu_stats	*cpustats;	/* per cpu counters */
	spinlock_t		lock;		/* spin lock */
377
	struct ip_vs_stats_user	ustats0;	/* reset values */
L
Linus Torvalds 已提交
378 379
};

380 381
struct dst_entry;
struct iphdr;
L
Linus Torvalds 已提交
382 383
struct ip_vs_conn;
struct ip_vs_app;
384
struct sk_buff;
H
Hans Schillstrom 已提交
385
struct ip_vs_proto_data;
L
Linus Torvalds 已提交
386 387 388 389

struct ip_vs_protocol {
	struct ip_vs_protocol	*next;
	char			*name;
390 391
	u16			protocol;
	u16			num_states;
L
Linus Torvalds 已提交
392 393 394 395 396 397
	int			dont_defrag;

	void (*init)(struct ip_vs_protocol *pp);

	void (*exit)(struct ip_vs_protocol *pp);

H
Hans Schillstrom 已提交
398 399 400 401
	void (*init_netns)(struct net *net, struct ip_vs_proto_data *pd);

	void (*exit_netns)(struct net *net, struct ip_vs_proto_data *pd);

402
	int (*conn_schedule)(int af, struct sk_buff *skb,
403
			     struct ip_vs_proto_data *pd,
L
Linus Torvalds 已提交
404 405 406
			     int *verdict, struct ip_vs_conn **cpp);

	struct ip_vs_conn *
407 408 409
	(*conn_in_get)(int af,
		       const struct sk_buff *skb,
		       const struct ip_vs_iphdr *iph,
L
Linus Torvalds 已提交
410 411 412 413
		       unsigned int proto_off,
		       int inverse);

	struct ip_vs_conn *
414 415 416
	(*conn_out_get)(int af,
			const struct sk_buff *skb,
			const struct ip_vs_iphdr *iph,
L
Linus Torvalds 已提交
417 418 419
			unsigned int proto_off,
			int inverse);

420
	int (*snat_handler)(struct sk_buff *skb,
L
Linus Torvalds 已提交
421 422
			    struct ip_vs_protocol *pp, struct ip_vs_conn *cp);

423
	int (*dnat_handler)(struct sk_buff *skb,
L
Linus Torvalds 已提交
424 425
			    struct ip_vs_protocol *pp, struct ip_vs_conn *cp);

426 427
	int (*csum_check)(int af, struct sk_buff *skb,
			  struct ip_vs_protocol *pp);
L
Linus Torvalds 已提交
428 429 430 431 432

	const char *(*state_name)(int state);

	int (*state_transition)(struct ip_vs_conn *cp, int direction,
				const struct sk_buff *skb,
433
				struct ip_vs_proto_data *pd);
L
Linus Torvalds 已提交
434

435
	int (*register_app)(struct net *net, struct ip_vs_app *inc);
L
Linus Torvalds 已提交
436

437
	void (*unregister_app)(struct net *net, struct ip_vs_app *inc);
L
Linus Torvalds 已提交
438 439 440

	int (*app_conn_bind)(struct ip_vs_conn *cp);

441
	void (*debug_packet)(int af, struct ip_vs_protocol *pp,
L
Linus Torvalds 已提交
442 443 444 445
			     const struct sk_buff *skb,
			     int offset,
			     const char *msg);

446
	void (*timeout_change)(struct ip_vs_proto_data *pd, int flags);
L
Linus Torvalds 已提交
447 448
};

H
Hans Schillstrom 已提交
449 450 451 452 453 454 455 456 457 458 459 460 461 462
/*
 * protocol data per netns
 */
struct ip_vs_proto_data {
	struct ip_vs_proto_data	*next;
	struct ip_vs_protocol	*pp;
	int			*timeout_table;	/* protocol timeout table */
	atomic_t		appcnt;		/* counter of proto app incs. */
	struct tcp_states_t	*tcp_state_table;
};

extern struct ip_vs_protocol   *ip_vs_proto_get(unsigned short proto);
extern struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net,
						     unsigned short proto);
L
Linus Torvalds 已提交
463

S
Simon Horman 已提交
464
struct ip_vs_conn_param {
465
	struct net			*net;
S
Simon Horman 已提交
466 467 468 469 470 471
	const union nf_inet_addr	*caddr;
	const union nf_inet_addr	*vaddr;
	__be16				cport;
	__be16				vport;
	__u16				protocol;
	u16				af;
S
Simon Horman 已提交
472 473 474 475

	const struct ip_vs_pe		*pe;
	char				*pe_data;
	__u8				pe_data_len;
S
Simon Horman 已提交
476 477
};

L
Linus Torvalds 已提交
478 479 480 481
/*
 *	IP_VS structure allocated for each dynamically scheduled connection
 */
struct ip_vs_conn {
C
Changli Gao 已提交
482
	struct hlist_node	c_list;         /* hashed list heads */
483 484 485
#ifdef CONFIG_NET_NS
	struct net              *net;           /* Name space */
#endif
L
Linus Torvalds 已提交
486
	/* Protocol, addresses and port numbers */
487 488 489 490 491 492 493 494 495
	u16                     af;             /* address family */
	__be16                  cport;
	__be16                  vport;
	__be16                  dport;
	__u32                   fwmark;         /* Fire wall mark from skb */
	union nf_inet_addr      caddr;          /* client address */
	union nf_inet_addr      vaddr;          /* virtual address */
	union nf_inet_addr      daddr;          /* destination address */
	volatile __u32          flags;          /* status flags */
L
Linus Torvalds 已提交
496 497 498 499 500 501 502 503 504 505
	__u16                   protocol;       /* Which protocol (TCP/UDP) */

	/* counter and timer */
	atomic_t		refcnt;		/* reference count */
	struct timer_list	timer;		/* Expiration timer */
	volatile unsigned long	timeout;	/* timeout */

	/* Flags and state transition */
	spinlock_t              lock;           /* lock for state transition */
	volatile __u16          state;          /* state info */
506 507 508 509
	volatile __u16          old_state;      /* old state, to be used for
						 * state transition triggerd
						 * synchronization
						 */
L
Linus Torvalds 已提交
510 511 512 513 514 515 516 517 518 519

	/* Control members */
	struct ip_vs_conn       *control;       /* Master control connection */
	atomic_t                n_control;      /* Number of controlled ones */
	struct ip_vs_dest       *dest;          /* real server */
	atomic_t                in_pkts;        /* incoming packet counter */

	/* packet transmitter for different forwarding methods.  If it
	   mangles the packet, it must return NF_DROP or better NF_STOLEN,
	   otherwise this must be changed to a sk_buff **.
520
	   NF_ACCEPT can be returned when destination is local.
L
Linus Torvalds 已提交
521 522 523 524 525 526 527 528 529 530 531
	 */
	int (*packet_xmit)(struct sk_buff *skb, struct ip_vs_conn *cp,
			   struct ip_vs_protocol *pp);

	/* Note: we can group the following members into a structure,
	   in order to save more space, and the following members are
	   only used in VS/NAT anyway */
	struct ip_vs_app        *app;           /* bound ip_vs_app object */
	void                    *app_data;      /* Application private data */
	struct ip_vs_seq        in_seq;         /* incoming seq. struct */
	struct ip_vs_seq        out_seq;        /* outgoing seq. struct */
S
Simon Horman 已提交
532

533
	const struct ip_vs_pe	*pe;
S
Simon Horman 已提交
534 535
	char			*pe_data;
	__u8			pe_data_len;
L
Linus Torvalds 已提交
536 537
};

538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564
/*
 *  To save some memory in conn table when name space is disabled.
 */
static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp)
{
#ifdef CONFIG_NET_NS
	return cp->net;
#else
	return &init_net;
#endif
}
static inline void ip_vs_conn_net_set(struct ip_vs_conn *cp, struct net *net)
{
#ifdef CONFIG_NET_NS
	cp->net = net;
#endif
}

static inline int ip_vs_conn_net_eq(const struct ip_vs_conn *cp,
				    struct net *net)
{
#ifdef CONFIG_NET_NS
	return cp->net == net;
#else
	return 1;
#endif
}
L
Linus Torvalds 已提交
565

566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583
/*
 *	Extended internal versions of struct ip_vs_service_user and
 *	ip_vs_dest_user for IPv6 support.
 *
 *	We need these to conveniently pass around service and destination
 *	options, but unfortunately, we also need to keep the old definitions to
 *	maintain userspace backwards compatibility for the setsockopt interface.
 */
struct ip_vs_service_user_kern {
	/* virtual service addresses */
	u16			af;
	u16			protocol;
	union nf_inet_addr	addr;		/* virtual ip address */
	u16			port;
	u32			fwmark;		/* firwall mark of service */

	/* virtual service options */
	char			*sched_name;
584
	char			*pe_name;
585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605
	unsigned		flags;		/* virtual service flags */
	unsigned		timeout;	/* persistent timeout in sec */
	u32			netmask;	/* persistent netmask */
};


struct ip_vs_dest_user_kern {
	/* destination server address */
	union nf_inet_addr	addr;
	u16			port;

	/* real server options */
	unsigned		conn_flags;	/* connection flags */
	int			weight;		/* destination weight */

	/* thresholds for active connections */
	u32			u_threshold;	/* upper threshold */
	u32			l_threshold;	/* lower threshold */
};


L
Linus Torvalds 已提交
606 607 608 609 610 611 612 613 614 615
/*
 *	The information about the virtual service offered to the net
 *	and the forwarding entries
 */
struct ip_vs_service {
	struct list_head	s_list;   /* for normal service table */
	struct list_head	f_list;   /* for fwmark-based service table */
	atomic_t		refcnt;   /* reference counter */
	atomic_t		usecnt;   /* use counter */

616
	u16			af;       /* address family */
L
Linus Torvalds 已提交
617
	__u16			protocol; /* which protocol (TCP/UDP) */
618
	union nf_inet_addr	addr;	  /* IP address for virtual service */
A
Al Viro 已提交
619
	__be16			port;	  /* port number for the service */
L
Linus Torvalds 已提交
620 621 622
	__u32                   fwmark;   /* firewall mark of the service */
	unsigned		flags;	  /* service status flags */
	unsigned		timeout;  /* persistent timeout in ticks */
A
Al Viro 已提交
623
	__be32			netmask;  /* grouping granularity */
624
	struct net		*net;
L
Linus Torvalds 已提交
625 626 627 628 629 630 631 632 633 634

	struct list_head	destinations;  /* real server d-linked list */
	__u32			num_dests;     /* number of servers */
	struct ip_vs_stats      stats;         /* statistics for the service */
	struct ip_vs_app	*inc;	  /* bind conns to this app inc */

	/* for scheduling */
	struct ip_vs_scheduler	*scheduler;    /* bound scheduler object */
	rwlock_t		sched_lock;    /* lock sched_data */
	void			*sched_data;   /* scheduler application data */
S
Simon Horman 已提交
635 636 637

	/* alternate persistence engine */
	struct ip_vs_pe		*pe;
L
Linus Torvalds 已提交
638 639 640 641 642 643 644 645 646 647 648
};


/*
 *	The real server destination forwarding entry
 *	with ip address, port number, and so on.
 */
struct ip_vs_dest {
	struct list_head	n_list;   /* for the dests in the service */
	struct list_head	d_list;   /* for table with all the dests */

649
	u16			af;		/* address family */
A
Al Viro 已提交
650
	__be16			port;		/* port number of the server */
H
Hans Schillstrom 已提交
651
	union nf_inet_addr	addr;		/* IP address of the server */
L
Linus Torvalds 已提交
652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669
	volatile unsigned	flags;		/* dest status flags */
	atomic_t		conn_flags;	/* flags to copy to conn */
	atomic_t		weight;		/* server weight */

	atomic_t		refcnt;		/* reference counter */
	struct ip_vs_stats      stats;          /* statistics */

	/* connection counters and thresholds */
	atomic_t		activeconns;	/* active connections */
	atomic_t		inactconns;	/* inactive connections */
	atomic_t		persistconns;	/* persistent connections */
	__u32			u_threshold;	/* upper threshold */
	__u32			l_threshold;	/* lower threshold */

	/* for destination cache */
	spinlock_t		dst_lock;	/* lock of dst_cache */
	struct dst_entry	*dst_cache;	/* destination cache entry */
	u32			dst_rtos;	/* RT_TOS(tos) for dst */
H
Hans Schillstrom 已提交
670 671 672 673
	u32			dst_cookie;
#ifdef CONFIG_IP_VS_IPV6
	struct in6_addr		dst_saddr;
#endif
L
Linus Torvalds 已提交
674 675 676 677

	/* for virtual service */
	struct ip_vs_service	*svc;		/* service it belongs to */
	__u16			protocol;	/* which protocol (TCP/UDP) */
A
Al Viro 已提交
678
	__be16			vport;		/* virtual port number */
H
Hans Schillstrom 已提交
679
	union nf_inet_addr	vaddr;		/* virtual IP address */
L
Linus Torvalds 已提交
680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704
	__u32			vfwmark;	/* firewall mark of service */
};


/*
 *	The scheduler object
 */
struct ip_vs_scheduler {
	struct list_head	n_list;		/* d-linked list head */
	char			*name;		/* scheduler name */
	atomic_t		refcnt;		/* reference counter */
	struct module		*module;	/* THIS_MODULE/NULL */

	/* scheduler initializing service */
	int (*init_service)(struct ip_vs_service *svc);
	/* scheduling service finish */
	int (*done_service)(struct ip_vs_service *svc);
	/* scheduler updating service */
	int (*update_service)(struct ip_vs_service *svc);

	/* selecting a server from the given service */
	struct ip_vs_dest* (*schedule)(struct ip_vs_service *svc,
				       const struct sk_buff *skb);
};

S
Simon Horman 已提交
705 706 707 708 709 710 711 712 713 714 715 716 717
/* The persistence engine object */
struct ip_vs_pe {
	struct list_head	n_list;		/* d-linked list head */
	char			*name;		/* scheduler name */
	atomic_t		refcnt;		/* reference counter */
	struct module		*module;	/* THIS_MODULE/NULL */

	/* get the connection template, if any */
	int (*fill_param)(struct ip_vs_conn_param *p, struct sk_buff *skb);
	bool (*ct_match)(const struct ip_vs_conn_param *p,
			 struct ip_vs_conn *ct);
	u32 (*hashkey_raw)(const struct ip_vs_conn_param *p, u32 initval,
			   bool inverse);
718
	int (*show_pe_data)(const struct ip_vs_conn *cp, char *buf);
S
Simon Horman 已提交
719
};
L
Linus Torvalds 已提交
720 721 722 723

/*
 *	The application module object (a.k.a. app incarnation)
 */
E
Eric Dumazet 已提交
724
struct ip_vs_app {
L
Linus Torvalds 已提交
725 726 727 728 729 730 731 732 733 734
	struct list_head	a_list;		/* member in app list */
	int			type;		/* IP_VS_APP_TYPE_xxx */
	char			*name;		/* application module name */
	__u16			protocol;
	struct module		*module;	/* THIS_MODULE/NULL */
	struct list_head	incs_list;	/* list of incarnations */

	/* members for application incarnations */
	struct list_head	p_list;		/* member in proto app list */
	struct ip_vs_app	*app;		/* its real application */
A
Al Viro 已提交
735
	__be16			port;		/* port number in net order */
L
Linus Torvalds 已提交
736 737
	atomic_t		usecnt;		/* usage counter */

738 739 740 741 742
	/*
	 * output hook: Process packet in inout direction, diff set for TCP.
	 * Return: 0=Error, 1=Payload Not Mangled/Mangled but checksum is ok,
	 *	   2=Mangled but checksum was not updated
	 */
L
Linus Torvalds 已提交
743
	int (*pkt_out)(struct ip_vs_app *, struct ip_vs_conn *,
744
		       struct sk_buff *, int *diff);
L
Linus Torvalds 已提交
745

746 747 748 749 750
	/*
	 * input hook: Process packet in outin direction, diff set for TCP.
	 * Return: 0=Error, 1=Payload Not Mangled/Mangled but checksum is ok,
	 *	   2=Mangled but checksum was not updated
	 */
L
Linus Torvalds 已提交
751
	int (*pkt_in)(struct ip_vs_app *, struct ip_vs_conn *,
752
		      struct sk_buff *, int *diff);
L
Linus Torvalds 已提交
753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790

	/* ip_vs_app initializer */
	int (*init_conn)(struct ip_vs_app *, struct ip_vs_conn *);

	/* ip_vs_app finish */
	int (*done_conn)(struct ip_vs_app *, struct ip_vs_conn *);


	/* not used now */
	int (*bind_conn)(struct ip_vs_app *, struct ip_vs_conn *,
			 struct ip_vs_protocol *);

	void (*unbind_conn)(struct ip_vs_app *, struct ip_vs_conn *);

	int *			timeout_table;
	int *			timeouts;
	int			timeouts_size;

	int (*conn_schedule)(struct sk_buff *skb, struct ip_vs_app *app,
			     int *verdict, struct ip_vs_conn **cpp);

	struct ip_vs_conn *
	(*conn_in_get)(const struct sk_buff *skb, struct ip_vs_app *app,
		       const struct iphdr *iph, unsigned int proto_off,
		       int inverse);

	struct ip_vs_conn *
	(*conn_out_get)(const struct sk_buff *skb, struct ip_vs_app *app,
			const struct iphdr *iph, unsigned int proto_off,
			int inverse);

	int (*state_transition)(struct ip_vs_conn *cp, int direction,
				const struct sk_buff *skb,
				struct ip_vs_app *app);

	void (*timeout_change)(struct ip_vs_app *app, int flags);
};

J
Julian Anastasov 已提交
791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838
/* IPVS in network namespace */
struct netns_ipvs {
	int			gen;		/* Generation */
	/*
	 *	Hash table: for real service lookups
	 */
	#define IP_VS_RTAB_BITS 4
	#define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS)
	#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)

	struct list_head	rs_table[IP_VS_RTAB_SIZE];
	/* ip_vs_app */
	struct list_head	app_list;
	struct mutex		app_mutex;
	struct lock_class_key	app_key;	/* mutex debuging */

	/* ip_vs_proto */
	#define IP_VS_PROTO_TAB_SIZE	32	/* must be power of 2 */
	struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE];
	/* ip_vs_proto_tcp */
#ifdef CONFIG_IP_VS_PROTO_TCP
	#define	TCP_APP_TAB_BITS	4
	#define	TCP_APP_TAB_SIZE	(1 << TCP_APP_TAB_BITS)
	#define	TCP_APP_TAB_MASK	(TCP_APP_TAB_SIZE - 1)
	struct list_head	tcp_apps[TCP_APP_TAB_SIZE];
	spinlock_t		tcp_app_lock;
#endif
	/* ip_vs_proto_udp */
#ifdef CONFIG_IP_VS_PROTO_UDP
	#define	UDP_APP_TAB_BITS	4
	#define	UDP_APP_TAB_SIZE	(1 << UDP_APP_TAB_BITS)
	#define	UDP_APP_TAB_MASK	(UDP_APP_TAB_SIZE - 1)
	struct list_head	udp_apps[UDP_APP_TAB_SIZE];
	spinlock_t		udp_app_lock;
#endif
	/* ip_vs_proto_sctp */
#ifdef CONFIG_IP_VS_PROTO_SCTP
	#define SCTP_APP_TAB_BITS	4
	#define SCTP_APP_TAB_SIZE	(1 << SCTP_APP_TAB_BITS)
	#define SCTP_APP_TAB_MASK	(SCTP_APP_TAB_SIZE - 1)
	/* Hash table for SCTP application incarnations	 */
	struct list_head	sctp_apps[SCTP_APP_TAB_SIZE];
	spinlock_t		sctp_app_lock;
#endif
	/* ip_vs_conn */
	atomic_t		conn_count;      /*  connection counter */

	/* ip_vs_ctl */
J
Julian Anastasov 已提交
839
	struct ip_vs_stats		tot_stats;  /* Statistics & est. */
J
Julian Anastasov 已提交
840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910

	int			num_services;    /* no of virtual services */
	/* 1/rate drop and drop-entry variables */
	struct delayed_work	defense_work;   /* Work handler */
	int			drop_rate;
	int			drop_counter;
	atomic_t		dropentry;
	/* locks in ctl.c */
	spinlock_t		dropentry_lock;  /* drop entry handling */
	spinlock_t		droppacket_lock; /* drop packet handling */
	spinlock_t		securetcp_lock;  /* state and timeout tables */
	rwlock_t		rs_lock;         /* real services table */
	/* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
	struct lock_class_key	ctl_key;	/* ctl_mutex debuging */
	/* Trash for destinations */
	struct list_head	dest_trash;
	/* Service counters */
	atomic_t		ftpsvc_counter;
	atomic_t		nullsvc_counter;

	/* sys-ctl struct */
	struct ctl_table_header	*sysctl_hdr;
	struct ctl_table	*sysctl_tbl;
	/* sysctl variables */
	int			sysctl_amemthresh;
	int			sysctl_am_droprate;
	int			sysctl_drop_entry;
	int			sysctl_drop_packet;
	int			sysctl_secure_tcp;
#ifdef CONFIG_IP_VS_NFCT
	int			sysctl_conntrack;
#endif
	int			sysctl_snat_reroute;
	int			sysctl_sync_ver;
	int			sysctl_cache_bypass;
	int			sysctl_expire_nodest_conn;
	int			sysctl_expire_quiescent_template;
	int			sysctl_sync_threshold[2];
	int			sysctl_nat_icmp_send;

	/* ip_vs_lblc */
	int			sysctl_lblc_expiration;
	struct ctl_table_header	*lblc_ctl_header;
	struct ctl_table	*lblc_ctl_table;
	/* ip_vs_lblcr */
	int			sysctl_lblcr_expiration;
	struct ctl_table_header	*lblcr_ctl_header;
	struct ctl_table	*lblcr_ctl_table;
	/* ip_vs_est */
	struct list_head	est_list;	/* estimator list */
	spinlock_t		est_lock;
	struct timer_list	est_timer;	/* Estimation timer */
	/* ip_vs_sync */
	struct list_head	sync_queue;
	spinlock_t		sync_lock;
	struct ip_vs_sync_buff  *sync_buff;
	spinlock_t		sync_buff_lock;
	struct sockaddr_in	sync_mcast_addr;
	struct task_struct	*master_thread;
	struct task_struct	*backup_thread;
	int			send_mesg_maxlen;
	int			recv_mesg_maxlen;
	volatile int		sync_state;
	volatile int		master_syncid;
	volatile int		backup_syncid;
	/* multicast interface name */
	char			master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
	char			backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
	/* net name space ptr */
	struct net		*net;            /* Needed by timer routines */
};
L
Linus Torvalds 已提交
911 912 913 914 915 916 917

/*
 *      IPVS core functions
 *      (from ip_vs_core.c)
 */
extern const char *ip_vs_proto_name(unsigned proto);
extern void ip_vs_init_hash_table(struct list_head *table, int rows);
S
Sven Wegener 已提交
918
#define IP_VS_INIT_HASH_TABLE(t) ip_vs_init_hash_table((t), ARRAY_SIZE((t)))
L
Linus Torvalds 已提交
919 920 921 922 923 924 925 926 927 928 929 930 931 932 933

#define IP_VS_APP_TYPE_FTP	1

/*
 *     ip_vs_conn handling functions
 *     (from ip_vs_conn.c)
 */

enum {
	IP_VS_DIR_INPUT = 0,
	IP_VS_DIR_OUTPUT,
	IP_VS_DIR_INPUT_ONLY,
	IP_VS_DIR_LAST,
};

934
static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol,
S
Simon Horman 已提交
935 936 937 938 939 940
					 const union nf_inet_addr *caddr,
					 __be16 cport,
					 const union nf_inet_addr *vaddr,
					 __be16 vport,
					 struct ip_vs_conn_param *p)
{
941
	p->net = net;
S
Simon Horman 已提交
942 943 944 945 946 947
	p->af = af;
	p->protocol = protocol;
	p->caddr = caddr;
	p->cport = cport;
	p->vaddr = vaddr;
	p->vport = vport;
S
Simon Horman 已提交
948 949
	p->pe = NULL;
	p->pe_data = NULL;
S
Simon Horman 已提交
950
}
951

S
Simon Horman 已提交
952 953
struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p);
struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p);
954

955 956 957 958 959
struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
					    const struct ip_vs_iphdr *iph,
					    unsigned int proto_off,
					    int inverse);

S
Simon Horman 已提交
960
struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p);
L
Linus Torvalds 已提交
961

962 963 964 965 966
struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
					     const struct ip_vs_iphdr *iph,
					     unsigned int proto_off,
					     int inverse);

L
Linus Torvalds 已提交
967 968 969 970 971 972
/* put back the conn without restarting its timer */
static inline void __ip_vs_conn_put(struct ip_vs_conn *cp)
{
	atomic_dec(&cp->refcnt);
}
extern void ip_vs_conn_put(struct ip_vs_conn *cp);
A
Al Viro 已提交
973
extern void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport);
L
Linus Torvalds 已提交
974

S
Simon Horman 已提交
975 976 977
struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p,
				  const union nf_inet_addr *daddr,
				  __be16 dport, unsigned flags,
978
				  struct ip_vs_dest *dest, __u32 fwmark);
L
Linus Torvalds 已提交
979 980 981 982
extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp);

extern const char * ip_vs_state_name(__u16 proto, int state);

983
extern void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp);
L
Linus Torvalds 已提交
984
extern int ip_vs_check_template(struct ip_vs_conn *ct);
985
extern void ip_vs_random_dropentry(struct net *net);
L
Linus Torvalds 已提交
986 987 988 989 990 991 992
extern int ip_vs_conn_init(void);
extern void ip_vs_conn_cleanup(void);

static inline void ip_vs_control_del(struct ip_vs_conn *cp)
{
	struct ip_vs_conn *ctl_cp = cp->control;
	if (!ctl_cp) {
993 994 995 996 997 998 999
		IP_VS_ERR_BUF("request control DEL for uncontrolled: "
			      "%s:%d to %s:%d\n",
			      IP_VS_DBG_ADDR(cp->af, &cp->caddr),
			      ntohs(cp->cport),
			      IP_VS_DBG_ADDR(cp->af, &cp->vaddr),
			      ntohs(cp->vport));

L
Linus Torvalds 已提交
1000 1001 1002
		return;
	}

1003 1004 1005 1006 1007 1008
	IP_VS_DBG_BUF(7, "DELeting control for: "
		      "cp.dst=%s:%d ctl_cp.dst=%s:%d\n",
		      IP_VS_DBG_ADDR(cp->af, &cp->caddr),
		      ntohs(cp->cport),
		      IP_VS_DBG_ADDR(cp->af, &ctl_cp->caddr),
		      ntohs(ctl_cp->cport));
L
Linus Torvalds 已提交
1009 1010 1011

	cp->control = NULL;
	if (atomic_read(&ctl_cp->n_control) == 0) {
1012 1013 1014 1015 1016 1017 1018
		IP_VS_ERR_BUF("BUG control DEL with n=0 : "
			      "%s:%d to %s:%d\n",
			      IP_VS_DBG_ADDR(cp->af, &cp->caddr),
			      ntohs(cp->cport),
			      IP_VS_DBG_ADDR(cp->af, &cp->vaddr),
			      ntohs(cp->vport));

L
Linus Torvalds 已提交
1019 1020 1021 1022 1023 1024 1025 1026 1027
		return;
	}
	atomic_dec(&ctl_cp->n_control);
}

static inline void
ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp)
{
	if (cp->control) {
1028 1029 1030 1031 1032 1033 1034
		IP_VS_ERR_BUF("request control ADD for already controlled: "
			      "%s:%d to %s:%d\n",
			      IP_VS_DBG_ADDR(cp->af, &cp->caddr),
			      ntohs(cp->cport),
			      IP_VS_DBG_ADDR(cp->af, &cp->vaddr),
			      ntohs(cp->vport));

L
Linus Torvalds 已提交
1035 1036 1037
		ip_vs_control_del(cp);
	}

1038 1039 1040 1041 1042 1043
	IP_VS_DBG_BUF(7, "ADDing control for: "
		      "cp.dst=%s:%d ctl_cp.dst=%s:%d\n",
		      IP_VS_DBG_ADDR(cp->af, &cp->caddr),
		      ntohs(cp->cport),
		      IP_VS_DBG_ADDR(cp->af, &ctl_cp->caddr),
		      ntohs(ctl_cp->cport));
L
Linus Torvalds 已提交
1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054

	cp->control = ctl_cp;
	atomic_inc(&ctl_cp->n_control);
}


/*
 *      IPVS application functions
 *      (from ip_vs_app.c)
 */
#define IP_VS_APP_MAX_PORTS  8
1055 1056
extern int register_ip_vs_app(struct net *net, struct ip_vs_app *app);
extern void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app);
L
Linus Torvalds 已提交
1057 1058
extern int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern void ip_vs_unbind_app(struct ip_vs_conn *cp);
1059 1060
extern int register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app,
				  __u16 proto, __u16 port);
L
Linus Torvalds 已提交
1061 1062 1063
extern int ip_vs_app_inc_get(struct ip_vs_app *inc);
extern void ip_vs_app_inc_put(struct ip_vs_app *inc);

1064 1065
extern int ip_vs_app_pkt_out(struct ip_vs_conn *, struct sk_buff *skb);
extern int ip_vs_app_pkt_in(struct ip_vs_conn *, struct sk_buff *skb);
L
Linus Torvalds 已提交
1066 1067 1068
extern int ip_vs_app_init(void);
extern void ip_vs_app_cleanup(void);

1069 1070 1071 1072
void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe);
void ip_vs_unbind_pe(struct ip_vs_service *svc);
int register_ip_vs_pe(struct ip_vs_pe *pe);
int unregister_ip_vs_pe(struct ip_vs_pe *pe);
1073
struct ip_vs_pe *ip_vs_pe_getbyname(const char *name);
1074
struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name);
1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086

static inline void ip_vs_pe_get(const struct ip_vs_pe *pe)
{
	if (pe && pe->module)
		__module_get(pe->module);
}

static inline void ip_vs_pe_put(const struct ip_vs_pe *pe)
{
	if (pe && pe->module)
		module_put(pe->module);
}
L
Linus Torvalds 已提交
1087 1088 1089 1090 1091 1092

/*
 *	IPVS protocol functions (from ip_vs_proto.c)
 */
extern int ip_vs_protocol_init(void);
extern void ip_vs_protocol_cleanup(void);
1093
extern void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags);
L
Linus Torvalds 已提交
1094 1095
extern int *ip_vs_create_timeout_table(int *table, int size);
extern int
1096 1097
ip_vs_set_state_timeout(int *table, int num, const char *const *names,
			const char *name, int to);
L
Linus Torvalds 已提交
1098
extern void
1099 1100
ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp,
			  const struct sk_buff *skb,
L
Linus Torvalds 已提交
1101 1102 1103 1104 1105 1106 1107
			  int offset, const char *msg);

extern struct ip_vs_protocol ip_vs_protocol_tcp;
extern struct ip_vs_protocol ip_vs_protocol_udp;
extern struct ip_vs_protocol ip_vs_protocol_icmp;
extern struct ip_vs_protocol ip_vs_protocol_esp;
extern struct ip_vs_protocol ip_vs_protocol_ah;
1108
extern struct ip_vs_protocol ip_vs_protocol_sctp;
L
Linus Torvalds 已提交
1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121

/*
 *      Registering/unregistering scheduler functions
 *      (from ip_vs_sched.c)
 */
extern int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
extern int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
extern int ip_vs_bind_scheduler(struct ip_vs_service *svc,
				struct ip_vs_scheduler *scheduler);
extern int ip_vs_unbind_scheduler(struct ip_vs_service *svc);
extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name);
extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler);
extern struct ip_vs_conn *
1122
ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
1123
	       struct ip_vs_proto_data *pd, int *ignored);
L
Linus Torvalds 已提交
1124
extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
1125
			struct ip_vs_proto_data *pd);
L
Linus Torvalds 已提交
1126

1127 1128
extern void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg);

L
Linus Torvalds 已提交
1129 1130 1131 1132 1133

/*
 *      IPVS control data and functions (from ip_vs_ctl.c)
 */
extern struct ip_vs_stats ip_vs_stats;
S
Sven Wegener 已提交
1134
extern const struct ctl_path net_vs_ctl_path[];
1135
extern int sysctl_ip_vs_sync_ver;
L
Linus Torvalds 已提交
1136

1137
extern void ip_vs_sync_switch_mode(struct net *net, int mode);
L
Linus Torvalds 已提交
1138
extern struct ip_vs_service *
1139
ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
1140
		  const union nf_inet_addr *vaddr, __be16 vport);
L
Linus Torvalds 已提交
1141 1142 1143 1144 1145 1146 1147

static inline void ip_vs_service_put(struct ip_vs_service *svc)
{
	atomic_dec(&svc->usecnt);
}

extern struct ip_vs_dest *
1148
ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol,
1149 1150
			  const union nf_inet_addr *daddr, __be16 dport);

L
Linus Torvalds 已提交
1151 1152 1153 1154
extern int ip_vs_use_count_inc(void);
extern void ip_vs_use_count_dec(void);
extern int ip_vs_control_init(void);
extern void ip_vs_control_cleanup(void);
1155
extern struct ip_vs_dest *
1156 1157 1158
ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr,
		__be16 dport, const union nf_inet_addr *vaddr, __be16 vport,
		__u16 protocol, __u32 fwmark);
1159
extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
L
Linus Torvalds 已提交
1160 1161 1162 1163 1164 1165


/*
 *      IPVS sync daemon data and function prototypes
 *      (from ip_vs_sync.c)
 */
1166 1167 1168 1169
extern int start_sync_thread(struct net *net, int state, char *mcast_ifn,
			     __u8 syncid);
extern int stop_sync_thread(struct net *net, int state);
extern void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp);
1170 1171
extern int ip_vs_sync_init(void);
extern void ip_vs_sync_cleanup(void);
L
Linus Torvalds 已提交
1172 1173 1174 1175 1176


/*
 *      IPVS rate estimator prototypes (from ip_vs_est.c)
 */
1177 1178
extern int ip_vs_estimator_init(void);
extern void ip_vs_estimator_cleanup(void);
1179 1180
extern void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats);
extern void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats);
L
Linus Torvalds 已提交
1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199
extern void ip_vs_zero_estimator(struct ip_vs_stats *stats);

/*
 *	Various IPVS packet transmitters (from ip_vs_xmit.c)
 */
extern int ip_vs_null_xmit
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern int ip_vs_bypass_xmit
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern int ip_vs_nat_xmit
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern int ip_vs_tunnel_xmit
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern int ip_vs_dr_xmit
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern int ip_vs_icmp_xmit
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, int offset);
extern void ip_vs_dst_reset(struct ip_vs_dest *dest);

1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212
#ifdef CONFIG_IP_VS_IPV6
extern int ip_vs_bypass_xmit_v6
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern int ip_vs_nat_xmit_v6
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern int ip_vs_tunnel_xmit_v6
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern int ip_vs_dr_xmit_v6
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern int ip_vs_icmp_xmit_v6
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp,
 int offset);
#endif
L
Linus Torvalds 已提交
1213 1214 1215 1216 1217 1218 1219

/*
 *	This is a simple mechanism to ignore packets when
 *	we are loaded. Just set ip_vs_drop_rate to 'n' and
 *	we start to drop 1/rate of the packets
 */

1220
static inline int ip_vs_todrop(struct netns_ipvs *ipvs)
L
Linus Torvalds 已提交
1221
{
1222 1223 1224 1225 1226
	if (!ipvs->drop_rate)
		return 0;
	if (--ipvs->drop_counter > 0)
		return 0;
	ipvs->drop_counter = ipvs->drop_rate;
L
Linus Torvalds 已提交
1227 1228 1229 1230 1231 1232 1233 1234
	return 1;
}

/*
 *      ip_vs_fwd_tag returns the forwarding tag of the connection
 */
#define IP_VS_FWD_METHOD(cp)  (cp->flags & IP_VS_CONN_F_FWD_MASK)

1235
static inline char ip_vs_fwd_tag(struct ip_vs_conn *cp)
L
Linus Torvalds 已提交
1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256
{
	char fwd;

	switch (IP_VS_FWD_METHOD(cp)) {
	case IP_VS_CONN_F_MASQ:
		fwd = 'M'; break;
	case IP_VS_CONN_F_LOCALNODE:
		fwd = 'L'; break;
	case IP_VS_CONN_F_TUNNEL:
		fwd = 'T'; break;
	case IP_VS_CONN_F_DROUTE:
		fwd = 'R'; break;
	case IP_VS_CONN_F_BYPASS:
		fwd = 'B'; break;
	default:
		fwd = '?'; break;
	}
	return fwd;
}

extern void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
1257 1258 1259 1260 1261 1262
			   struct ip_vs_conn *cp, int dir);

#ifdef CONFIG_IP_VS_IPV6
extern void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
			      struct ip_vs_conn *cp, int dir);
#endif
L
Linus Torvalds 已提交
1263

1264
extern __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset);
L
Linus Torvalds 已提交
1265

A
Al Viro 已提交
1266
static inline __wsum ip_vs_check_diff4(__be32 old, __be32 new, __wsum oldsum)
L
Linus Torvalds 已提交
1267
{
A
Al Viro 已提交
1268
	__be32 diff[2] = { ~old, new };
L
Linus Torvalds 已提交
1269

1270
	return csum_partial(diff, sizeof(diff), oldsum);
A
Al Viro 已提交
1271 1272
}

1273 1274 1275 1276 1277 1278 1279
#ifdef CONFIG_IP_VS_IPV6
static inline __wsum ip_vs_check_diff16(const __be32 *old, const __be32 *new,
					__wsum oldsum)
{
	__be32 diff[8] = { ~old[3], ~old[2], ~old[1], ~old[0],
			    new[3],  new[2],  new[1],  new[0] };

1280
	return csum_partial(diff, sizeof(diff), oldsum);
1281 1282 1283
}
#endif

A
Al Viro 已提交
1284 1285 1286 1287
static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum)
{
	__be16 diff[2] = { ~old, new };

1288
	return csum_partial(diff, sizeof(diff), oldsum);
L
Linus Torvalds 已提交
1289 1290
}

J
Julian Anastasov 已提交
1291 1292 1293 1294 1295 1296 1297
/*
 * Forget current conntrack (unconfirmed) and attach notrack entry
 */
static inline void ip_vs_notrack(struct sk_buff *skb)
{
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
	enum ip_conntrack_info ctinfo;
1298
	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
J
Julian Anastasov 已提交
1299 1300 1301 1302 1303 1304 1305 1306 1307 1308

	if (!ct || !nf_ct_is_untracked(ct)) {
		nf_reset(skb);
		skb->nfct = &nf_ct_untracked_get()->ct_general;
		skb->nfctinfo = IP_CT_NEW;
		nf_conntrack_get(skb->nfct);
	}
#endif
}

1309 1310 1311 1312 1313
#ifdef CONFIG_IP_VS_NFCT
/*
 *      Netfilter connection tracking
 *      (from ip_vs_nfct.c)
 */
1314
static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)
1315
{
1316
	return ipvs->sysctl_conntrack;
1317 1318
}

J
Julian Anastasov 已提交
1319 1320
extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp,
				   int outin);
1321 1322 1323 1324 1325 1326 1327 1328
extern int ip_vs_confirm_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp);
extern void ip_vs_nfct_expect_related(struct sk_buff *skb, struct nf_conn *ct,
				      struct ip_vs_conn *cp, u_int8_t proto,
				      const __be16 port, int from_rs);
extern void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp);

#else

1329
static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)
1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349
{
	return 0;
}

static inline void ip_vs_update_conntrack(struct sk_buff *skb,
					  struct ip_vs_conn *cp, int outin)
{
}

static inline int ip_vs_confirm_conntrack(struct sk_buff *skb,
					  struct ip_vs_conn *cp)
{
	return NF_ACCEPT;
}

static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
{
}
/* CONFIG_IP_VS_NFCT */
#endif
J
Julian Anastasov 已提交
1350

1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364
static inline unsigned int
ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
{
	/*
	 * We think the overhead of processing active connections is 256
	 * times higher than that of inactive connections in average. (This
	 * 256 times might not be accurate, we will change it later) We
	 * use the following formula to estimate the overhead now:
	 *		  dest->activeconns*256 + dest->inactconns
	 */
	return (atomic_read(&dest->activeconns) << 8) +
		atomic_read(&dest->inactconns);
}

L
Linus Torvalds 已提交
1365 1366
#endif /* __KERNEL__ */

1367
#endif	/* _NET_IP_VS_H */