ip_vs.h 22.8 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>
L
Linus Torvalds 已提交
24 25

#ifdef CONFIG_IP_VS_DEBUG
26 27
#include <linux/net.h>

L
Linus Torvalds 已提交
28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161
extern int ip_vs_get_debug_level(void);
#define IP_VS_DBG(level, msg...)			\
    do {						\
	    if (level <= ip_vs_get_debug_level())	\
		    printk(KERN_DEBUG "IPVS: " msg);	\
    } while (0)
#define IP_VS_DBG_RL(msg...)				\
    do {						\
	    if (net_ratelimit())			\
		    printk(KERN_DEBUG "IPVS: " msg);	\
    } while (0)
#define IP_VS_DBG_PKT(level, pp, skb, ofs, msg)		\
    do {						\
	    if (level <= ip_vs_get_debug_level())	\
		pp->debug_packet(pp, skb, ofs, msg);	\
    } while (0)
#define IP_VS_DBG_RL_PKT(level, pp, skb, ofs, msg)	\
    do {						\
	    if (level <= ip_vs_get_debug_level() &&	\
		net_ratelimit())			\
		pp->debug_packet(pp, skb, ofs, msg);	\
    } while (0)
#else	/* NO DEBUGGING at ALL */
#define IP_VS_DBG(level, msg...)  do {} while (0)
#define IP_VS_DBG_RL(msg...)  do {} while (0)
#define IP_VS_DBG_PKT(level, pp, skb, ofs, msg)		do {} while (0)
#define IP_VS_DBG_RL_PKT(level, pp, skb, ofs, msg)	do {} while (0)
#endif

#define IP_VS_BUG() BUG()
#define IP_VS_ERR(msg...) printk(KERN_ERR "IPVS: " msg)
#define IP_VS_INFO(msg...) printk(KERN_INFO "IPVS: " msg)
#define IP_VS_WARNING(msg...) \
	printk(KERN_WARNING "IPVS: " msg)
#define IP_VS_ERR_RL(msg...)				\
    do {						\
	    if (net_ratelimit())			\
		    printk(KERN_ERR "IPVS: " msg);	\
    } while (0)

#ifdef CONFIG_IP_VS_DEBUG
#define EnterFunction(level)						\
    do {								\
	    if (level <= ip_vs_get_debug_level())			\
		    printk(KERN_DEBUG "Enter: %s, %s line %i\n",	\
			   __FUNCTION__, __FILE__, __LINE__);		\
    } while (0)
#define LeaveFunction(level)                                            \
    do {                                                                \
	    if (level <= ip_vs_get_debug_level())                       \
			printk(KERN_DEBUG "Leave: %s, %s line %i\n",    \
			       __FUNCTION__, __FILE__, __LINE__);       \
    } while (0)
#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).
 */
#define FTPPORT  __constant_htons(21)
#define FTPDATA  __constant_htons(20)

/*
 *      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,
};

/*
 *	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 */
};


/*
 *	IPVS statistics object
 */
struct ip_vs_stats
{
	__u32                   conns;          /* connections scheduled */
	__u32                   inpkts;         /* incoming packets */
	__u32                   outpkts;        /* outgoing packets */
	__u64                   inbytes;        /* incoming bytes */
	__u64                   outbytes;       /* outgoing bytes */

	__u32			cps;		/* current connection rate */
	__u32			inpps;		/* current in packet rate */
	__u32			outpps;		/* current out packet rate */
	__u32			inbps;		/* current in byte rate */
	__u32			outbps;		/* current out byte rate */

	spinlock_t              lock;           /* spin lock */
};

162 163
struct dst_entry;
struct iphdr;
L
Linus Torvalds 已提交
164 165
struct ip_vs_conn;
struct ip_vs_app;
166
struct sk_buff;
L
Linus Torvalds 已提交
167 168 169 170

struct ip_vs_protocol {
	struct ip_vs_protocol	*next;
	char			*name;
171 172
	u16			protocol;
	u16			num_states;
L
Linus Torvalds 已提交
173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198
	int			dont_defrag;
	atomic_t		appcnt;		/* counter of proto app incs */
	int			*timeout_table;	/* protocol timeout table */

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

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

	int (*conn_schedule)(struct sk_buff *skb,
			     struct ip_vs_protocol *pp,
			     int *verdict, struct ip_vs_conn **cpp);

	struct ip_vs_conn *
	(*conn_in_get)(const struct sk_buff *skb,
		       struct ip_vs_protocol *pp,
		       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_protocol *pp,
			const struct iphdr *iph,
			unsigned int proto_off,
			int inverse);

199
	int (*snat_handler)(struct sk_buff *skb,
L
Linus Torvalds 已提交
200 201
			    struct ip_vs_protocol *pp, struct ip_vs_conn *cp);

202
	int (*dnat_handler)(struct sk_buff *skb,
L
Linus Torvalds 已提交
203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237
			    struct ip_vs_protocol *pp, struct ip_vs_conn *cp);

	int (*csum_check)(struct sk_buff *skb, struct ip_vs_protocol *pp);

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

	int (*state_transition)(struct ip_vs_conn *cp, int direction,
				const struct sk_buff *skb,
				struct ip_vs_protocol *pp);

	int (*register_app)(struct ip_vs_app *inc);

	void (*unregister_app)(struct ip_vs_app *inc);

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

	void (*debug_packet)(struct ip_vs_protocol *pp,
			     const struct sk_buff *skb,
			     int offset,
			     const char *msg);

	void (*timeout_change)(struct ip_vs_protocol *pp, int flags);

	int (*set_state_timeout)(struct ip_vs_protocol *pp, char *sname, int to);
};

extern struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto);

/*
 *	IP_VS structure allocated for each dynamically scheduled connection
 */
struct ip_vs_conn {
	struct list_head        c_list;         /* hashed list heads */

	/* Protocol, addresses and port numbers */
A
Al Viro 已提交
238 239 240 241 242 243
	__be32                   caddr;          /* client address */
	__be32                   vaddr;          /* virtual address */
	__be32                   daddr;          /* destination address */
	__be16                   cport;
	__be16                   vport;
	__be16                   dport;
L
Linus Torvalds 已提交
244 245 246 247 248 249 250 251 252 253 254
	__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          flags;          /* status flags */
	volatile __u16          state;          /* state info */
255 256 257 258
	volatile __u16          old_state;      /* old state, to be used for
						 * state transition triggerd
						 * synchronization
						 */
L
Linus Torvalds 已提交
259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293

	/* 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 **.
	 */
	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 */
};


/*
 *	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 */

	__u16			protocol; /* which protocol (TCP/UDP) */
A
Al Viro 已提交
294 295
	__be32			addr;	  /* IP address for virtual service */
	__be16			port;	  /* port number for the service */
L
Linus Torvalds 已提交
296 297 298
	__u32                   fwmark;   /* firewall mark of the service */
	unsigned		flags;	  /* service status flags */
	unsigned		timeout;  /* persistent timeout in ticks */
A
Al Viro 已提交
299
	__be32			netmask;  /* grouping granularity */
L
Linus Torvalds 已提交
300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320

	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 */
};


/*
 *	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 */

A
Al Viro 已提交
321 322
	__be32			addr;		/* IP address of the server */
	__be16			port;		/* port number of the server */
L
Linus Torvalds 已提交
323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344
	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 */

	/* for virtual service */
	struct ip_vs_service	*svc;		/* service it belongs to */
	__u16			protocol;	/* which protocol (TCP/UDP) */
A
Al Viro 已提交
345 346
	__be32			vaddr;		/* virtual IP address */
	__be16			vport;		/* virtual port number */
L
Linus Torvalds 已提交
347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387
	__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);
};


/*
 *	The application module object (a.k.a. app incarnation)
 */
struct ip_vs_app
{
	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
388
	__be16			port;		/* port number in net order */
L
Linus Torvalds 已提交
389 390 391 392
	atomic_t		usecnt;		/* usage counter */

	/* output hook: return false if can't linearize. diff set for TCP.  */
	int (*pkt_out)(struct ip_vs_app *, struct ip_vs_conn *,
393
		       struct sk_buff *, int *diff);
L
Linus Torvalds 已提交
394 395 396

	/* input hook: return false if can't linearize. diff set for TCP. */
	int (*pkt_in)(struct ip_vs_app *, struct ip_vs_conn *,
397
		      struct sk_buff *, int *diff);
L
Linus Torvalds 已提交
398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478

	/* 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);
};


/*
 *      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);
#define IP_VS_INIT_HASH_TABLE(t) ip_vs_init_hash_table(t, sizeof(t)/sizeof(t[0]))

#define IP_VS_APP_TYPE_FTP	1

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

/*
 *     IPVS connection entry hash table
 */
#ifndef CONFIG_IP_VS_TAB_BITS
#define CONFIG_IP_VS_TAB_BITS   12
#endif
/* make sure that IP_VS_CONN_TAB_BITS is located in [8, 20] */
#if CONFIG_IP_VS_TAB_BITS < 8
#define IP_VS_CONN_TAB_BITS	8
#endif
#if CONFIG_IP_VS_TAB_BITS > 20
#define IP_VS_CONN_TAB_BITS	20
#endif
#if 8 <= CONFIG_IP_VS_TAB_BITS && CONFIG_IP_VS_TAB_BITS <= 20
#define IP_VS_CONN_TAB_BITS	CONFIG_IP_VS_TAB_BITS
#endif
#define IP_VS_CONN_TAB_SIZE     (1 << IP_VS_CONN_TAB_BITS)
#define IP_VS_CONN_TAB_MASK     (IP_VS_CONN_TAB_SIZE - 1)

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

extern struct ip_vs_conn *ip_vs_conn_in_get
A
Al Viro 已提交
479
(int protocol, __be32 s_addr, __be16 s_port, __be32 d_addr, __be16 d_port);
480
extern struct ip_vs_conn *ip_vs_ct_in_get
A
Al Viro 已提交
481
(int protocol, __be32 s_addr, __be16 s_port, __be32 d_addr, __be16 d_port);
L
Linus Torvalds 已提交
482
extern struct ip_vs_conn *ip_vs_conn_out_get
A
Al Viro 已提交
483
(int protocol, __be32 s_addr, __be16 s_port, __be32 d_addr, __be16 d_port);
L
Linus Torvalds 已提交
484 485 486 487 488 489 490

/* 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
491
extern void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport);
L
Linus Torvalds 已提交
492 493

extern struct ip_vs_conn *
A
Al Viro 已提交
494 495
ip_vs_conn_new(int proto, __be32 caddr, __be16 cport, __be32 vaddr, __be16 vport,
	       __be32 daddr, __be16 dport, unsigned flags,
L
Linus Torvalds 已提交
496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568
	       struct ip_vs_dest *dest);
extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp);

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

extern void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp);
extern int ip_vs_check_template(struct ip_vs_conn *ct);
extern void ip_vs_random_dropentry(void);
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) {
		IP_VS_ERR("request control DEL for uncontrolled: "
			  "%d.%d.%d.%d:%d to %d.%d.%d.%d:%d\n",
			  NIPQUAD(cp->caddr),ntohs(cp->cport),
			  NIPQUAD(cp->vaddr),ntohs(cp->vport));
		return;
	}

	IP_VS_DBG(7, "DELeting control for: "
		  "cp.dst=%d.%d.%d.%d:%d ctl_cp.dst=%d.%d.%d.%d:%d\n",
		  NIPQUAD(cp->caddr),ntohs(cp->cport),
		  NIPQUAD(ctl_cp->caddr),ntohs(ctl_cp->cport));

	cp->control = NULL;
	if (atomic_read(&ctl_cp->n_control) == 0) {
		IP_VS_ERR("BUG control DEL with n=0 : "
			  "%d.%d.%d.%d:%d to %d.%d.%d.%d:%d\n",
			  NIPQUAD(cp->caddr),ntohs(cp->cport),
			  NIPQUAD(cp->vaddr),ntohs(cp->vport));
		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) {
		IP_VS_ERR("request control ADD for already controlled: "
			  "%d.%d.%d.%d:%d to %d.%d.%d.%d:%d\n",
			  NIPQUAD(cp->caddr),ntohs(cp->cport),
			  NIPQUAD(cp->vaddr),ntohs(cp->vport));
		ip_vs_control_del(cp);
	}

	IP_VS_DBG(7, "ADDing control for: "
		  "cp.dst=%d.%d.%d.%d:%d ctl_cp.dst=%d.%d.%d.%d:%d\n",
		  NIPQUAD(cp->caddr),ntohs(cp->cport),
		  NIPQUAD(ctl_cp->caddr),ntohs(ctl_cp->cport));

	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
extern int register_ip_vs_app(struct ip_vs_app *app);
extern void unregister_ip_vs_app(struct ip_vs_app *app);
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);
extern int
register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port);
extern int ip_vs_app_inc_get(struct ip_vs_app *inc);
extern void ip_vs_app_inc_put(struct ip_vs_app *inc);

569 570
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);
A
Al Viro 已提交
571
extern int ip_vs_skb_replace(struct sk_buff *skb, gfp_t pri,
L
Linus Torvalds 已提交
572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622
			     char *o_buf, int o_len, char *n_buf, int n_len);
extern int ip_vs_app_init(void);
extern void ip_vs_app_cleanup(void);


/*
 *	IPVS protocol functions (from ip_vs_proto.c)
 */
extern int ip_vs_protocol_init(void);
extern void ip_vs_protocol_cleanup(void);
extern void ip_vs_protocol_timeout_change(int flags);
extern int *ip_vs_create_timeout_table(int *table, int size);
extern int
ip_vs_set_state_timeout(int *table, int num, char **names, char *name, int to);
extern void
ip_vs_tcpudp_debug_packet(struct ip_vs_protocol *pp, const struct sk_buff *skb,
			  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;


/*
 *      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 *
ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb);
extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
			struct ip_vs_protocol *pp);


/*
 *      IPVS control data and functions (from ip_vs_ctl.c)
 */
extern int sysctl_ip_vs_cache_bypass;
extern int sysctl_ip_vs_expire_nodest_conn;
extern int sysctl_ip_vs_expire_quiescent_template;
extern int sysctl_ip_vs_sync_threshold[2];
extern int sysctl_ip_vs_nat_icmp_send;
extern struct ip_vs_stats ip_vs_stats;
623
extern struct ctl_path net_vs_ctl_path[];
L
Linus Torvalds 已提交
624 625

extern struct ip_vs_service *
A
Al Viro 已提交
626
ip_vs_service_get(__u32 fwmark, __u16 protocol, __be32 vaddr, __be16 vport);
L
Linus Torvalds 已提交
627 628 629 630 631 632 633

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

extern struct ip_vs_dest *
A
Al Viro 已提交
634
ip_vs_lookup_real_service(__u16 protocol, __be32 daddr, __be16 dport);
L
Linus Torvalds 已提交
635 636 637 638
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);
639 640 641 642
extern struct ip_vs_dest *
ip_vs_find_dest(__be32 daddr, __be16 dport,
		 __be32 vaddr, __be16 vport, __u16 protocol);
extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
L
Linus Torvalds 已提交
643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704


/*
 *      IPVS sync daemon data and function prototypes
 *      (from ip_vs_sync.c)
 */
extern volatile int ip_vs_sync_state;
extern volatile int ip_vs_master_syncid;
extern volatile int ip_vs_backup_syncid;
extern char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid);
extern int stop_sync_thread(int state);
extern void ip_vs_sync_conn(struct ip_vs_conn *cp);


/*
 *      IPVS rate estimator prototypes (from ip_vs_est.c)
 */
extern int ip_vs_new_estimator(struct ip_vs_stats *stats);
extern void ip_vs_kill_estimator(struct ip_vs_stats *stats);
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);


/*
 *	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
 */
extern int ip_vs_drop_rate;
extern int ip_vs_drop_counter;

static __inline__ int ip_vs_todrop(void)
{
	if (!ip_vs_drop_rate) return 0;
	if (--ip_vs_drop_counter > 0) return 0;
	ip_vs_drop_counter = ip_vs_drop_rate;
	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)

705
static inline char ip_vs_fwd_tag(struct ip_vs_conn *cp)
L
Linus Torvalds 已提交
706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728
{
	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,
		struct ip_vs_conn *cp, int dir);

729
extern __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset);
L
Linus Torvalds 已提交
730

A
Al Viro 已提交
731
static inline __wsum ip_vs_check_diff4(__be32 old, __be32 new, __wsum oldsum)
L
Linus Torvalds 已提交
732
{
A
Al Viro 已提交
733
	__be32 diff[2] = { ~old, new };
L
Linus Torvalds 已提交
734

A
Al Viro 已提交
735 736 737 738 739 740 741 742
	return csum_partial((char *) diff, sizeof(diff), oldsum);
}

static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum)
{
	__be16 diff[2] = { ~old, new };

	return csum_partial((char *) diff, sizeof(diff), oldsum);
L
Linus Torvalds 已提交
743 744 745 746
}

#endif /* __KERNEL__ */

747
#endif	/* _NET_IP_VS_H */