summaryrefslogtreecommitdiffstats
path: root/net/ipv4/ipvs/ip_vs_sync.c
blob: 60b96823c9aef097302e69bdfbe36507d31356f5 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
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
162
163
164
165
166
167
168
169
170
171
172
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
199
200
201
202
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
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
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
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
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
388
389
390
391
392
393
394
395
396
397
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
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
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
569
570
571
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
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
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
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
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
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
839
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
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
/*
 * IPVS         An implementation of the IP virtual server support for the
 *              LINUX operating system.  IPVS is now implemented as a module
 *              over the NetFilter framework. IPVS can be used to build a
 *              high-performance and highly available server based on a
 *              cluster of servers.
 *
 * Authors:     Wensong Zhang <wensong@linuxvirtualserver.org>
 *
 * ip_vs_sync:  sync connection info from master load balancer to backups
 *              through multicast
 *
 * Changes:
 *	Alexandre Cassen	:	Added master & backup support at a time.
 *	Alexandre Cassen	:	Added SyncID support for incoming sync
 *					messages filtering.
 *	Justin Ossevoort	:	Fix endian problem on sync message size.
 */

#include <linux/module.h>
#include <linux/slab.h>
#include <linux/inetdevice.h>
#include <linux/net.h>
#include <linux/completion.h>
#include <linux/delay.h>
#include <linux/skbuff.h>
#include <linux/in.h>
#include <linux/igmp.h>                 /* for ip_mc_join_group */
#include <linux/udp.h>
#include <linux/err.h>

#include <net/ip.h>
#include <net/sock.h>
#include <asm/uaccess.h>                /* for get_fs and set_fs */

#include <net/ip_vs.h>

#define IP_VS_SYNC_GROUP 0xe0000051    /* multicast addr - 224.0.0.81 */
#define IP_VS_SYNC_PORT  8848          /* multicast port */


/*
 *	IPVS sync connection entry
 */
struct ip_vs_sync_conn {
	__u8			reserved;

	/* Protocol, addresses and port numbers */
	__u8			protocol;       /* Which protocol (TCP/UDP) */
	__be16			cport;
	__be16                  vport;
	__be16                  dport;
	__be32                  caddr;          /* client address */
	__be32                  vaddr;          /* virtual address */
	__be32                  daddr;          /* destination address */

	/* Flags and state transition */
	__be16                  flags;          /* status flags */
	__be16                  state;          /* state info */

	/* The sequence options start here */
};

struct ip_vs_sync_conn_options {
	struct ip_vs_seq        in_seq;         /* incoming seq. struct */
	struct ip_vs_seq        out_seq;        /* outgoing seq. struct */
};

struct ip_vs_sync_thread_data {
	struct completion *startup;
	int state;
};

#define SIMPLE_CONN_SIZE  (sizeof(struct ip_vs_sync_conn))
#define FULL_CONN_SIZE  \
(sizeof(struct ip_vs_sync_conn) + sizeof(struct ip_vs_sync_conn_options))


/*
  The master mulitcasts messages to the backup load balancers in the
  following format.

       0                   1                   2                   3
       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |  Count Conns  |    SyncID     |            Size               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                                                               |
      |                    IPVS Sync Connection (1)                   |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                            .                                  |
      |                            .                                  |
      |                            .                                  |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                                                               |
      |                    IPVS Sync Connection (n)                   |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*/

#define SYNC_MESG_HEADER_LEN	4

struct ip_vs_sync_mesg {
	__u8                    nr_conns;
	__u8                    syncid;
	__u16                   size;

	/* ip_vs_sync_conn entries start here */
};

/* the maximum length of sync (sending/receiving) message */
static int sync_send_mesg_maxlen;
static int sync_recv_mesg_maxlen;

struct ip_vs_sync_buff {
	struct list_head        list;
	unsigned long           firstuse;

	/* pointers for the message data */
	struct ip_vs_sync_mesg  *mesg;
	unsigned char           *head;
	unsigned char           *end;
};


/* the sync_buff list head and the lock */
static LIST_HEAD(ip_vs_sync_queue);
static DEFINE_SPINLOCK(ip_vs_sync_lock);

/* current sync_buff for accepting new conn entries */
static struct ip_vs_sync_buff   *curr_sb = NULL;
static DEFINE_SPINLOCK(curr_sb_lock);

/* ipvs sync daemon state */
volatile int ip_vs_sync_state = IP_VS_STATE_NONE;
volatile int ip_vs_master_syncid = 0;
volatile int ip_vs_backup_syncid = 0;

/* multicast interface name */
char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];

/* multicast addr */
static struct sockaddr_in mcast_addr = {
	.sin_family		= AF_INET,
	.sin_port		= __constant_htons(IP_VS_SYNC_PORT),
	.sin_addr.s_addr	= __constant_htonl(IP_VS_SYNC_GROUP),
};


static inline void sb_queue_tail(struct ip_vs_sync_buff *sb)
{
	spin_lock(&ip_vs_sync_lock);
	list_add_tail(&sb->list, &ip_vs_sync_queue);
	spin_unlock(&ip_vs_sync_lock);
}

static inline struct ip_vs_sync_buff * sb_dequeue(void)
{
	struct ip_vs_sync_buff *sb;

	spin_lock_bh(&ip_vs_sync_lock);
	if (list_empty(&ip_vs_sync_queue)) {
		sb = NULL;
	} else {
		sb = list_entry(ip_vs_sync_queue.next,
				struct ip_vs_sync_buff,
				list);
		list_del(&sb->list);
	}
	spin_unlock_bh(&ip_vs_sync_lock);

	return sb;
}

static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create(void)
{
	struct ip_vs_sync_buff *sb;

	if (!(sb=kmalloc(sizeof(struct ip_vs_sync_buff), GFP_ATOMIC)))
		return NULL;

	if (!(sb->mesg=kmalloc(sync_send_mesg_maxlen, GFP_ATOMIC))) {
		kfree(sb);
		return NULL;
	}
	sb->mesg->nr_conns = 0;
	sb->mesg->syncid = ip_vs_master_syncid;
	sb->mesg->size = 4;
	sb->head = (unsigned char *)sb->mesg + 4;
	sb->end = (unsigned char *)sb->mesg + sync_send_mesg_maxlen;
	sb->firstuse = jiffies;
	return sb;
}

static inline void ip_vs_sync_buff_release(struct ip_vs_sync_buff *sb)
{
	kfree(sb->mesg);
	kfree(sb);
}

/*
 *	Get the current sync buffer if it has been created for more
 *	than the specified time or the specified time is zero.
 */
static inline struct ip_vs_sync_buff *
get_curr_sync_buff(unsigned long time)
{
	struct ip_vs_sync_buff *sb;

	spin_lock_bh(&curr_sb_lock);
	if (curr_sb && (time == 0 ||
			time_before(jiffies - curr_sb->firstuse, time))) {
		sb = curr_sb;
		curr_sb = NULL;
	} else
		sb = NULL;
	spin_unlock_bh(&curr_sb_lock);
	return sb;
}


/*
 *      Add an ip_vs_conn information into the current sync_buff.
 *      Called by ip_vs_in.
 */
void ip_vs_sync_conn(struct ip_vs_conn *cp)
{
	struct ip_vs_sync_mesg *m;
	struct ip_vs_sync_conn *s;
	int len;

	spin_lock(&curr_sb_lock);
	if (!curr_sb) {
		if (!(curr_sb=ip_vs_sync_buff_create())) {
			spin_unlock(&curr_sb_lock);
			IP_VS_ERR("ip_vs_sync_buff_create failed.\n");
			return;
		}
	}

	len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE :
		SIMPLE_CONN_SIZE;
	m = curr_sb->mesg;
	s = (struct ip_vs_sync_conn *)curr_sb->head;

	/* copy members */
	s->protocol = cp->protocol;
	s->cport = cp->cport;
	s->vport = cp->vport;
	s->dport = cp->dport;
	s->caddr = cp->caddr;
	s->vaddr = cp->vaddr;
	s->daddr = cp->daddr;
	s->flags = htons(cp->flags & ~IP_VS_CONN_F_HASHED);
	s->state = htons(cp->state);
	if (cp->flags & IP_VS_CONN_F_SEQ_MASK) {
		struct ip_vs_sync_conn_options *opt =
			(struct ip_vs_sync_conn_options *)&s[1];
		memcpy(opt, &cp->in_seq, sizeof(*opt));
	}

	m->nr_conns++;
	m->size += len;
	curr_sb->head += len;

	/* check if there is a space for next one */
	if (curr_sb->head+FULL_CONN_SIZE > curr_sb->end) {
		sb_queue_tail(curr_sb);
		curr_sb = NULL;
	}
	spin_unlock(&curr_sb_lock);

	/* synchronize its controller if it has */
	if (cp->control)
		ip_vs_sync_conn(cp->control);
}


/*
 *      Process received multicast message and create the corresponding
 *      ip_vs_conn entries.
 */
static void ip_vs_process_message(const char *buffer, const size_t buflen)
{
	struct ip_vs_sync_mesg *m = (struct ip_vs_sync_mesg *)buffer;
	struct ip_vs_sync_conn *s;
	struct ip_vs_sync_conn_options *opt;
	struct ip_vs_conn *cp;
	struct ip_vs_protocol *pp;
	struct ip_vs_dest *dest;
	char *p;
	int i;

	if (buflen < sizeof(struct ip_vs_sync_mesg)) {
		IP_VS_ERR_RL("sync message header too short\n");
		return;
	}

	/* Convert size back to host byte order */
	m->size = ntohs(m->size);

	if (buflen != m->size) {
		IP_VS_ERR_RL("bogus sync message size\n");
		return;
	}

	/* SyncID sanity check */
	if (ip_vs_backup_syncid != 0 && m->syncid != ip_vs_backup_syncid) {
		IP_VS_DBG(7, "Ignoring incoming msg with syncid = %d\n",
			  m->syncid);
		return;
	}

	p = (char *)buffer + sizeof(struct ip_vs_sync_mesg);
	for (i=0; i<m->nr_conns; i++) {
		unsigned flags, state;

		if (p + SIMPLE_CONN_SIZE > buffer+buflen) {
			IP_VS_ERR_RL("bogus conn in sync message\n");
			return;
		}
		s = (struct ip_vs_sync_conn *) p;
		flags = ntohs(s->flags) | IP_VS_CONN_F_SYNC;
		flags &= ~IP_VS_CONN_F_HASHED;
		if (flags & IP_VS_CONN_F_SEQ_MASK) {
			opt = (struct ip_vs_sync_conn_options *)&s[1];
			p += FULL_CONN_SIZE;
			if (p > buffer+buflen) {
				IP_VS_ERR_RL("bogus conn options in sync message\n");
				return;
			}
		} else {
			opt = NULL;
			p += SIMPLE_CONN_SIZE;
		}

		state = ntohs(s->state);
		if (!(flags & IP_VS_CONN_F_TEMPLATE)) {
			pp = ip_vs_proto_get(s->protocol);
			if (!pp) {
				IP_VS_ERR_RL("Unsupported protocol %u in sync msg\n",
					s->protocol);
				continue;
			}
			if (state >= pp->num_states) {
				IP_VS_DBG(2, "Invalid %s state %u in sync msg\n",
					pp->name, state);
				continue;
			}
		} else {
			/* protocol in templates is not used for state/timeout */
			pp = NULL;
			if (state > 0) {
				IP_VS_DBG(2, "Invalid template state %u in sync msg\n",
					state);
				state = 0;
			}
		}

		if (!(flags & IP_VS_CONN_F_TEMPLATE))
			cp = ip_vs_conn_in_get(s->protocol,
					       s->caddr, s->cport,
					       s->vaddr, s->vport);
		else
			cp = ip_vs_ct_in_get(s->protocol,
					       s->caddr, s->cport,
					       s->vaddr, s->vport);
		if (!cp) {
			/*
			 * Find the appropriate destination for the connection.
			 * If it is not found the connection will remain unbound
			 * but still handled.
			 */
			dest = ip_vs_find_dest(s->daddr, s->dport,
					       s->vaddr, s->vport,
					       s->protocol);
			/*  Set the approprite ativity flag */
			if (s->protocol == IPPROTO_TCP) {
				if (state != IP_VS_TCP_S_ESTABLISHED)
					flags |= IP_VS_CONN_F_INACTIVE;
				else
					flags &= ~IP_VS_CONN_F_INACTIVE;
			}
			cp = ip_vs_conn_new(s->protocol,
					    s->caddr, s->cport,
					    s->vaddr, s->vport,
					    s->daddr, s->dport,
					    flags, dest);
			if (dest)
				atomic_dec(&dest->refcnt);
			if (!cp) {
				IP_VS_ERR("ip_vs_conn_new failed\n");
				return;
			}
		} else if (!cp->dest) {
			dest = ip_vs_try_bind_dest(cp);
			if (dest)
				atomic_dec(&dest->refcnt);
		} else if ((cp->dest) && (cp->protocol == IPPROTO_TCP) &&
			   (cp->state != state)) {
			/* update active/inactive flag for the connection */
			dest = cp->dest;
			if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
				(state != IP_VS_TCP_S_ESTABLISHED)) {
				atomic_dec(&dest->activeconns);
				atomic_inc(&dest->inactconns);
				cp->flags |= IP_VS_CONN_F_INACTIVE;
			} else if ((cp->flags & IP_VS_CONN_F_INACTIVE) &&
				(state == IP_VS_TCP_S_ESTABLISHED)) {
				atomic_inc(&dest->activeconns);
				atomic_dec(&dest->inactconns);
				cp->flags &= ~IP_VS_CONN_F_INACTIVE;
			}
		}

		if (opt)
			memcpy(&cp->in_seq, opt, sizeof(*opt));
		atomic_set(&cp->in_pkts, sysctl_ip_vs_sync_threshold[0]);
		cp->state = state;
		cp->old_state = cp->state;
		/*
		 * We can not recover the right timeout for templates
		 * in all cases, we can not find the right fwmark
		 * virtual service. If needed, we can do it for
		 * non-fwmark persistent services.
		 */
		if (!(flags & IP_VS_CONN_F_TEMPLATE) && pp->timeout_table)
			cp->timeout = pp->timeout_table[state];
		else
			cp->timeout = (3*60*HZ);
		ip_vs_conn_put(cp);
	}
}


/*
 *      Setup loopback of outgoing multicasts on a sending socket
 */
static void set_mcast_loop(struct sock *sk, u_char loop)
{
	struct inet_sock *inet = inet_sk(sk);

	/* setsockopt(sock, SOL_IP, IP_MULTICAST_LOOP, &loop, sizeof(loop)); */
	lock_sock(sk);
	inet->mc_loop = loop ? 1 : 0;
	release_sock(sk);
}

/*
 *      Specify TTL for outgoing multicasts on a sending socket
 */
static void set_mcast_ttl(struct sock *sk, u_char ttl)
{
	struct inet_sock *inet = inet_sk(sk);

	/* setsockopt(sock, SOL_IP, IP_MULTICAST_TTL, &ttl, sizeof(ttl)); */
	lock_sock(sk);
	inet->mc_ttl = ttl;
	release_sock(sk);
}

/*
 *      Specifiy default interface for outgoing multicasts
 */
static int set_mcast_if(struct sock *sk, char *ifname)
{
	struct net_device *dev;
	struct inet_sock *inet = inet_sk(sk);

	if ((dev = __dev_get_by_name(&init_net, ifname)) == NULL)
		return -ENODEV;

	if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
		return -EINVAL;

	lock_sock(sk);
	inet->mc_index = dev->ifindex;
	/*  inet->mc_addr  = 0; */
	release_sock(sk);

	return 0;
}


/*
 *	Set the maximum length of sync message according to the
 *	specified interface's MTU.
 */
static int set_sync_mesg_maxlen(int sync_state)
{
	struct net_device *dev;
	int num;

	if (sync_state == IP_VS_STATE_MASTER) {
		if ((dev = __dev_get_by_name(&init_net, ip_vs_master_mcast_ifn)) == NULL)
			return -ENODEV;

		num = (dev->mtu - sizeof(struct iphdr) -
		       sizeof(struct udphdr) -
		       SYNC_MESG_HEADER_LEN - 20) / SIMPLE_CONN_SIZE;
		sync_send_mesg_maxlen =
			SYNC_MESG_HEADER_LEN + SIMPLE_CONN_SIZE * num;
		IP_VS_DBG(7, "setting the maximum length of sync sending "
			  "message %d.\n", sync_send_mesg_maxlen);
	} else if (sync_state == IP_VS_STATE_BACKUP) {
		if ((dev = __dev_get_by_name(&init_net, ip_vs_backup_mcast_ifn)) == NULL)
			return -ENODEV;

		sync_recv_mesg_maxlen = dev->mtu -
			sizeof(struct iphdr) - sizeof(struct udphdr);
		IP_VS_DBG(7, "setting the maximum length of sync receiving "
			  "message %d.\n", sync_recv_mesg_maxlen);
	}

	return 0;
}


/*
 *      Join a multicast group.
 *      the group is specified by a class D multicast address 224.0.0.0/8
 *      in the in_addr structure passed in as a parameter.
 */
static int
join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
{
	struct ip_mreqn mreq;
	struct net_device *dev;
	int ret;

	memset(&mreq, 0, sizeof(mreq));
	memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr));

	if ((dev = __dev_get_by_name(&init_net, ifname)) == NULL)
		return -ENODEV;
	if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
		return -EINVAL;

	mreq.imr_ifindex = dev->ifindex;

	lock_sock(sk);
	ret = ip_mc_join_group(sk, &mreq);
	release_sock(sk);

	return ret;
}


static int bind_mcastif_addr(struct socket *sock, char *ifname)
{
	struct net_device *dev;
	__be32 addr;
	struct sockaddr_in sin;

	if ((dev = __dev_get_by_name(&init_net, ifname)) == NULL)
		return -ENODEV;

	addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
	if (!addr)
		IP_VS_ERR("You probably need to specify IP address on "
			  "multicast interface.\n");

	IP_VS_DBG(7, "binding socket with (%s) %u.%u.%u.%u\n",
		  ifname, NIPQUAD(addr));

	/* Now bind the socket with the address of multicast interface */
	sin.sin_family	     = AF_INET;
	sin.sin_addr.s_addr  = addr;
	sin.sin_port         = 0;

	return sock->ops->bind(sock, (struct sockaddr*)&sin, sizeof(sin));
}

/*
 *      Set up sending multicast socket over UDP
 */
static struct socket * make_send_sock(void)
{
	struct socket *sock;
	int result;

	/* First create a socket */
	result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
	if (result < 0) {
		IP_VS_ERR("Error during creation of socket; terminating\n");
		return ERR_PTR(result);
	}

	result = set_mcast_if(sock->sk, ip_vs_master_mcast_ifn);
	if (result < 0) {
		IP_VS_ERR("Error setting outbound mcast interface\n");
		goto error;
	}

	set_mcast_loop(sock->sk, 0);
	set_mcast_ttl(sock->sk, 1);

	result = bind_mcastif_addr(sock, ip_vs_master_mcast_ifn);
	if (result < 0) {
		IP_VS_ERR("Error binding address of the mcast interface\n");
		goto error;
	}

	result = sock->ops->connect(sock, (struct sockaddr *) &mcast_addr,
			sizeof(struct sockaddr), 0);
	if (result < 0) {
		IP_VS_ERR("Error connecting to the multicast addr\n");
		goto error;
	}

	return sock;

  error:
	sock_release(sock);
	return ERR_PTR(result);
}


/*
 *      Set up receiving multicast socket over UDP
 */
static struct socket * make_receive_sock(void)
{
	struct socket *sock;
	int result;

	/* First create a socket */
	result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
	if (result < 0) {
		IP_VS_ERR("Error during creation of socket; terminating\n");
		return ERR_PTR(result);
	}

	/* it is equivalent to the REUSEADDR option in user-space */
	sock->sk->sk_reuse = 1;

	result = sock->ops->bind(sock, (struct sockaddr *) &mcast_addr,
			sizeof(struct sockaddr));
	if (result < 0) {
		IP_VS_ERR("Error binding to the multicast addr\n");
		goto error;
	}

	/* join the multicast group */
	result = join_mcast_group(sock->sk,
			(struct in_addr *) &mcast_addr.sin_addr,
			ip_vs_backup_mcast_ifn);
	if (result < 0) {
		IP_VS_ERR("Error joining to the multicast group\n");
		goto error;
	}

	return sock;

  error:
	sock_release(sock);
	return ERR_PTR(result);
}


static int
ip_vs_send_async(struct socket *sock, const char *buffer, const size_t length)
{
	struct msghdr	msg = {.msg_flags = MSG_DONTWAIT|MSG_NOSIGNAL};
	struct kvec	iov;
	int		len;

	EnterFunction(7);
	iov.iov_base     = (void *)buffer;
	iov.iov_len      = length;

	len = kernel_sendmsg(sock, &msg, &iov, 1, (size_t)(length));

	LeaveFunction(7);
	return len;
}

static void
ip_vs_send_sync_msg(struct socket *sock, struct ip_vs_sync_mesg *msg)
{
	int msize;

	msize = msg->size;

	/* Put size in network byte order */
	msg->size = htons(msg->size);

	if (ip_vs_send_async(sock, (char *)msg, msize) != msize)
		IP_VS_ERR("ip_vs_send_async error\n");
}

static int
ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen)
{
	struct msghdr		msg = {NULL,};
	struct kvec		iov;
	int			len;

	EnterFunction(7);

	/* Receive a packet */
	iov.iov_base     = buffer;
	iov.iov_len      = (size_t)buflen;

	len = kernel_recvmsg(sock, &msg, &iov, 1, buflen, 0);

	if (len < 0)
		return -1;

	LeaveFunction(7);
	return len;
}


static DECLARE_WAIT_QUEUE_HEAD(sync_wait);
static pid_t sync_master_pid = 0;
static pid_t sync_backup_pid = 0;

static DECLARE_WAIT_QUEUE_HEAD(stop_sync_wait);
static int stop_master_sync = 0;
static int stop_backup_sync = 0;

static void sync_master_loop(void)
{
	struct socket *sock;
	struct ip_vs_sync_buff *sb;

	/* create the sending multicast socket */
	sock = make_send_sock();
	if (IS_ERR(sock))
		return;

	IP_VS_INFO("sync thread started: state = MASTER, mcast_ifn = %s, "
		   "syncid = %d\n",
		   ip_vs_master_mcast_ifn, ip_vs_master_syncid);

	for (;;) {
		while ((sb=sb_dequeue())) {
			ip_vs_send_sync_msg(sock, sb->mesg);
			ip_vs_sync_buff_release(sb);
		}

		/* check if entries stay in curr_sb for 2 seconds */
		if ((sb = get_curr_sync_buff(2*HZ))) {
			ip_vs_send_sync_msg(sock, sb->mesg);
			ip_vs_sync_buff_release(sb);
		}

		if (stop_master_sync)
			break;

		msleep_interruptible(1000);
	}

	/* clean up the sync_buff queue */
	while ((sb=sb_dequeue())) {
		ip_vs_sync_buff_release(sb);
	}

	/* clean up the current sync_buff */
	if ((sb = get_curr_sync_buff(0))) {
		ip_vs_sync_buff_release(sb);
	}

	/* release the sending multicast socket */
	sock_release(sock);
}


static void sync_backup_loop(void)
{
	struct socket *sock;
	char *buf;
	int len;

	if (!(buf = kmalloc(sync_recv_mesg_maxlen, GFP_ATOMIC))) {
		IP_VS_ERR("sync_backup_loop: kmalloc error\n");
		return;
	}

	/* create the receiving multicast socket */
	sock = make_receive_sock();
	if (IS_ERR(sock))
		goto out;

	IP_VS_INFO("sync thread started: state = BACKUP, mcast_ifn = %s, "
		   "syncid = %d\n",
		   ip_vs_backup_mcast_ifn, ip_vs_backup_syncid);

	for (;;) {
		/* do you have data now? */
		while (!skb_queue_empty(&(sock->sk->sk_receive_queue))) {
			if ((len =
			     ip_vs_receive(sock, buf,
					   sync_recv_mesg_maxlen)) <= 0) {
				IP_VS_ERR("receiving message error\n");
				break;
			}
			/* disable bottom half, because it accessed the data
			   shared by softirq while getting/creating conns */
			local_bh_disable();
			ip_vs_process_message(buf, len);
			local_bh_enable();
		}

		if (stop_backup_sync)
			break;

		msleep_interruptible(1000);
	}

	/* release the sending multicast socket */
	sock_release(sock);

  out:
	kfree(buf);
}


static void set_sync_pid(int sync_state, pid_t sync_pid)
{
	if (sync_state == IP_VS_STATE_MASTER)
		sync_master_pid = sync_pid;
	else if (sync_state == IP_VS_STATE_BACKUP)
		sync_backup_pid = sync_pid;
}

static void set_stop_sync(int sync_state, int set)
{
	if (sync_state == IP_VS_STATE_MASTER)
		stop_master_sync = set;
	else if (sync_state == IP_VS_STATE_BACKUP)
		stop_backup_sync = set;
	else {
		stop_master_sync = set;
		stop_backup_sync = set;
	}
}

static int sync_thread(void *startup)
{
	DECLARE_WAITQUEUE(wait, current);
	mm_segment_t oldmm;
	int state;
	const char *name;
	struct ip_vs_sync_thread_data *tinfo = startup;

	/* increase the module use count */
	ip_vs_use_count_inc();

	if (ip_vs_sync_state & IP_VS_STATE_MASTER && !sync_master_pid) {
		state = IP_VS_STATE_MASTER;
		name = "ipvs_syncmaster";
	} else if (ip_vs_sync_state & IP_VS_STATE_BACKUP && !sync_backup_pid) {
		state = IP_VS_STATE_BACKUP;
		name = "ipvs_syncbackup";
	} else {
		IP_VS_BUG();
		ip_vs_use_count_dec();
		return -EINVAL;
	}

	daemonize(name);

	oldmm = get_fs();
	set_fs(KERNEL_DS);

	/* Block all signals */
	spin_lock_irq(&current->sighand->siglock);
	siginitsetinv(&current->blocked, 0);
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);

	/* set the maximum length of sync message */
	set_sync_mesg_maxlen(state);

	add_wait_queue(&sync_wait, &wait);

	set_sync_pid(state, task_pid_nr(current));
	complete(tinfo->startup);

	/*
	 * once we call the completion queue above, we should
	 * null out that reference, since its allocated on the
	 * stack of the creating kernel thread
	 */
	tinfo->startup = NULL;

	/* processing master/backup loop here */
	if (state == IP_VS_STATE_MASTER)
		sync_master_loop();
	else if (state == IP_VS_STATE_BACKUP)
		sync_backup_loop();
	else IP_VS_BUG();

	remove_wait_queue(&sync_wait, &wait);

	/* thread exits */

	/*
	 * If we weren't explicitly stopped, then we
	 * exited in error, and should undo our state
	 */
	if ((!stop_master_sync) && (!stop_backup_sync))
		ip_vs_sync_state -= tinfo->state;

	set_sync_pid(state, 0);
	IP_VS_INFO("sync thread stopped!\n");

	set_fs(oldmm);

	/* decrease the module use count */
	ip_vs_use_count_dec();

	set_stop_sync(state, 0);
	wake_up(&stop_sync_wait);

	/*
	 * we need to free the structure that was allocated
	 * for us in start_sync_thread
	 */
	kfree(tinfo);
	return 0;
}


static int fork_sync_thread(void *startup)
{
	pid_t pid;

	/* fork the sync thread here, then the parent process of the
	   sync thread is the init process after this thread exits. */
  repeat:
	if ((pid = kernel_thread(sync_thread, startup, 0)) < 0) {
		IP_VS_ERR("could not create sync_thread due to %d... "
			  "retrying.\n", pid);
		msleep_interruptible(1000);
		goto repeat;
	}

	return 0;
}


int start_sync_thread(int state, char *mcast_ifn, __u8 syncid)
{
	DECLARE_COMPLETION_ONSTACK(startup);
	pid_t pid;
	struct ip_vs_sync_thread_data *tinfo;

	if ((state == IP_VS_STATE_MASTER && sync_master_pid) ||
	    (state == IP_VS_STATE_BACKUP && sync_backup_pid))
		return -EEXIST;

	/*
	 * Note that tinfo will be freed in sync_thread on exit
	 */
	tinfo = kmalloc(sizeof(struct ip_vs_sync_thread_data), GFP_KERNEL);
	if (!tinfo)
		return -ENOMEM;

	IP_VS_DBG(7, "%s: pid %d\n", __func__, task_pid_nr(current));
	IP_VS_DBG(7, "Each ip_vs_sync_conn entry need %Zd bytes\n",
		  sizeof(struct ip_vs_sync_conn));

	ip_vs_sync_state |= state;
	if (state == IP_VS_STATE_MASTER) {
		strlcpy(ip_vs_master_mcast_ifn, mcast_ifn,
			sizeof(ip_vs_master_mcast_ifn));
		ip_vs_master_syncid = syncid;
	} else {
		strlcpy(ip_vs_backup_mcast_ifn, mcast_ifn,
			sizeof(ip_vs_backup_mcast_ifn));
		ip_vs_backup_syncid = syncid;
	}

	tinfo->state = state;
	tinfo->startup = &startup;

  repeat:
	if ((pid = kernel_thread(fork_sync_thread, tinfo, 0)) < 0) {
		IP_VS_ERR("could not create fork_sync_thread due to %d... "
			  "retrying.\n", pid);
		msleep_interruptible(1000);
		goto repeat;
	}

	wait_for_completion(&startup);

	return 0;
}


int stop_sync_thread(int state)
{
	DECLARE_WAITQUEUE(wait, current);

	if ((state == IP_VS_STATE_MASTER && !sync_master_pid) ||
	    (state == IP_VS_STATE_BACKUP && !sync_backup_pid))
		return -ESRCH;

	IP_VS_DBG(7, "%s: pid %d\n", __func__, task_pid_nr(current));
	IP_VS_INFO("stopping sync thread %d ...\n",
		   (state == IP_VS_STATE_MASTER) ?
		   sync_master_pid : sync_backup_pid);

	__set_current_state(TASK_UNINTERRUPTIBLE);
	add_wait_queue(&stop_sync_wait, &wait);
	set_stop_sync(state, 1);
	ip_vs_sync_state -= state;
	wake_up(&sync_wait);
	schedule();
	__set_current_state(TASK_RUNNING);
	remove_wait_queue(&stop_sync_wait, &wait);

	/* Note: no need to reap the sync thread, because its parent
	   process is the init process */

	if ((state == IP_VS_STATE_MASTER && stop_master_sync) ||
	    (state == IP_VS_STATE_BACKUP && stop_backup_sync))
		IP_VS_BUG();

	return 0;
}