aboutsummaryrefslogtreecommitdiff
path: root/net/netfilter/nfnetlink_log.c
blob: e185a5b55913ce8b37af7de85b5e9a9f8b46f2e1 (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
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
/*
 * This is a module which is used for logging packets to userspace via
 * nfetlink.
 *
 * (C) 2005 by Harald Welte <laforge@netfilter.org>
 *
 * Based on the old ipv4-only ipt_ULOG.c:
 * (C) 2000-2004 by Harald Welte <laforge@netfilter.org>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/netdevice.h>
#include <linux/netfilter.h>
#include <linux/netlink.h>
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_log.h>
#include <linux/spinlock.h>
#include <linux/sysctl.h>
#include <linux/proc_fs.h>
#include <linux/security.h>
#include <linux/list.h>
#include <linux/jhash.h>
#include <linux/random.h>
#include <net/sock.h>

#include <asm/atomic.h>

#ifdef CONFIG_BRIDGE_NETFILTER
#include "../bridge/br_private.h"
#endif

#define NFULNL_NLBUFSIZ_DEFAULT	NLMSG_GOODSIZE
#define NFULNL_TIMEOUT_DEFAULT 	100	/* every second */
#define NFULNL_QTHRESH_DEFAULT 	100	/* 100 packets */

#define PRINTR(x, args...)	do { if (net_ratelimit()) \
				     printk(x, ## args); } while (0);

#if 0
#define UDEBUG(x, args ...)	printk(KERN_DEBUG "%s(%d):%s():	" x, 	   \
					__FILE__, __LINE__, __FUNCTION__,  \
					## args)
#else
#define UDEBUG(x, ...)
#endif

struct nfulnl_instance {
	struct hlist_node hlist;	/* global list of instances */
	spinlock_t lock;
	atomic_t use;			/* use count */

	unsigned int qlen;		/* number of nlmsgs in skb */
	struct sk_buff *skb;		/* pre-allocatd skb */
	struct nlmsghdr *lastnlh;	/* netlink header of last msg in skb */
	struct timer_list timer;
	int peer_pid;			/* PID of the peer process */

	/* configurable parameters */
	unsigned int flushtimeout;	/* timeout until queue flush */
	unsigned int nlbufsiz;		/* netlink buffer allocation size */
	unsigned int qthreshold;	/* threshold of the queue */
	u_int32_t copy_range;
	u_int32_t seq;			/* instance-local sequential counter */
	u_int16_t group_num;		/* number of this queue */
	u_int16_t flags;
	u_int8_t copy_mode;
};

static DEFINE_RWLOCK(instances_lock);
static atomic_t global_seq;

#define INSTANCE_BUCKETS	16
static struct hlist_head instance_table[INSTANCE_BUCKETS];
static unsigned int hash_init;

static inline u_int8_t instance_hashfn(u_int16_t group_num)
{
	return ((group_num & 0xff) % INSTANCE_BUCKETS);
}

static struct nfulnl_instance *
__instance_lookup(u_int16_t group_num)
{
	struct hlist_head *head;
	struct hlist_node *pos;
	struct nfulnl_instance *inst;

	UDEBUG("entering (group_num=%u)\n", group_num);

	head = &instance_table[instance_hashfn(group_num)];
	hlist_for_each_entry(inst, pos, head, hlist) {
		if (inst->group_num == group_num)
			return inst;
	}
	return NULL;
}

static inline void
instance_get(struct nfulnl_instance *inst)
{
	atomic_inc(&inst->use);
}

static struct nfulnl_instance *
instance_lookup_get(u_int16_t group_num)
{
	struct nfulnl_instance *inst;

	read_lock_bh(&instances_lock);
	inst = __instance_lookup(group_num);
	if (inst)
		instance_get(inst);
	read_unlock_bh(&instances_lock);

	return inst;
}

static void
instance_put(struct nfulnl_instance *inst)
{
	if (inst && atomic_dec_and_test(&inst->use)) {
		UDEBUG("kfree(inst=%p)\n", inst);
		kfree(inst);
		module_put(THIS_MODULE);
	}
}

static void nfulnl_timer(unsigned long data);

static struct nfulnl_instance *
instance_create(u_int16_t group_num, int pid)
{
	struct nfulnl_instance *inst;

	UDEBUG("entering (group_num=%u, pid=%d)\n", group_num,
		pid);

	write_lock_bh(&instances_lock);
	if (__instance_lookup(group_num)) {
		inst = NULL;
		UDEBUG("aborting, instance already exists\n");
		goto out_unlock;
	}

	inst = kzalloc(sizeof(*inst), GFP_ATOMIC);
	if (!inst)
		goto out_unlock;

	INIT_HLIST_NODE(&inst->hlist);
	spin_lock_init(&inst->lock);
	/* needs to be two, since we _put() after creation */
	atomic_set(&inst->use, 2);

	setup_timer(&inst->timer, nfulnl_timer, (unsigned long)inst);

	inst->peer_pid = pid;
	inst->group_num = group_num;

	inst->qthreshold 	= NFULNL_QTHRESH_DEFAULT;
	inst->flushtimeout 	= NFULNL_TIMEOUT_DEFAULT;
	inst->nlbufsiz 		= NFULNL_NLBUFSIZ_DEFAULT;
	inst->copy_mode 	= NFULNL_COPY_PACKET;
	inst->copy_range 	= 0xffff;

	if (!try_module_get(THIS_MODULE))
		goto out_free;

	hlist_add_head(&inst->hlist,
		       &instance_table[instance_hashfn(group_num)]);

	UDEBUG("newly added node: %p, next=%p\n", &inst->hlist,
		inst->hlist.next);

	write_unlock_bh(&instances_lock);

	return inst;

out_free:
	instance_put(inst);
out_unlock:
	write_unlock_bh(&instances_lock);
	return NULL;
}

static int __nfulnl_send(struct nfulnl_instance *inst);

static void
__instance_destroy(struct nfulnl_instance *inst)
{
	/* first pull it out of the global list */
	UDEBUG("removing instance %p (queuenum=%u) from hash\n",
		inst, inst->group_num);

	hlist_del(&inst->hlist);

	/* then flush all pending packets from skb */

	spin_lock_bh(&inst->lock);
	if (inst->skb) {
		/* timer "holds" one reference (we have one more) */
		if (del_timer(&inst->timer))
			instance_put(inst);
		if (inst->qlen)
			__nfulnl_send(inst);
		if (inst->skb) {
			kfree_skb(inst->skb);
			inst->skb = NULL;
		}
	}
	spin_unlock_bh(&inst->lock);

	/* and finally put the refcount */
	instance_put(inst);
}

static inline void
instance_destroy(struct nfulnl_instance *inst)
{
	write_lock_bh(&instances_lock);
	__instance_destroy(inst);
	write_unlock_bh(&instances_lock);
}

static int
nfulnl_set_mode(struct nfulnl_instance *inst, u_int8_t mode,
		  unsigned int range)
{
	int status = 0;

	spin_lock_bh(&inst->lock);

	switch (mode) {
	case NFULNL_COPY_NONE:
	case NFULNL_COPY_META:
		inst->copy_mode = mode;
		inst->copy_range = 0;
		break;

	case NFULNL_COPY_PACKET:
		inst->copy_mode = mode;
		/* we're using struct nfattr which has 16bit nfa_len */
		if (range > 0xffff)
			inst->copy_range = 0xffff;
		else
			inst->copy_range = range;
		break;

	default:
		status = -EINVAL;
		break;
	}

	spin_unlock_bh(&inst->lock);

	return status;
}

static int
nfulnl_set_nlbufsiz(struct nfulnl_instance *inst, u_int32_t nlbufsiz)
{
	int status;

	spin_lock_bh(&inst->lock);
	if (nlbufsiz < NFULNL_NLBUFSIZ_DEFAULT)
		status = -ERANGE;
	else if (nlbufsiz > 131072)
		status = -ERANGE;
	else {
		inst->nlbufsiz = nlbufsiz;
		status = 0;
	}
	spin_unlock_bh(&inst->lock);

	return status;
}

static int
nfulnl_set_timeout(struct nfulnl_instance *inst, u_int32_t timeout)
{
	spin_lock_bh(&inst->lock);
	inst->flushtimeout = timeout;
	spin_unlock_bh(&inst->lock);

	return 0;
}

static int
nfulnl_set_qthresh(struct nfulnl_instance *inst, u_int32_t qthresh)
{
	spin_lock_bh(&inst->lock);
	inst->qthreshold = qthresh;
	spin_unlock_bh(&inst->lock);

	return 0;
}

static int
nfulnl_set_flags(struct nfulnl_instance *inst, u_int16_t flags)
{
	spin_lock_bh(&inst->lock);
	inst->flags = flags;
	spin_unlock_bh(&inst->lock);

	return 0;
}

static struct sk_buff *nfulnl_alloc_skb(unsigned int inst_size,
					unsigned int pkt_size)
{
	struct sk_buff *skb;
	unsigned int n;

	UDEBUG("entered (%u, %u)\n", inst_size, pkt_size);

	/* alloc skb which should be big enough for a whole multipart
	 * message.  WARNING: has to be <= 128k due to slab restrictions */

	n = max(inst_size, pkt_size);
	skb = alloc_skb(n, GFP_ATOMIC);
	if (!skb) {
		PRINTR("nfnetlink_log: can't alloc whole buffer (%u bytes)\n",
			inst_size);

		if (n > pkt_size) {
			/* try to allocate only as much as we need for current
			 * packet */

			skb = alloc_skb(pkt_size, GFP_ATOMIC);
			if (!skb)
				PRINTR("nfnetlink_log: can't even alloc %u "
				       "bytes\n", pkt_size);
		}
	}

	return skb;
}

static int
__nfulnl_send(struct nfulnl_instance *inst)
{
	int status;

	if (inst->qlen > 1)
		inst->lastnlh->nlmsg_type = NLMSG_DONE;

	status = nfnetlink_unicast(inst->skb, inst->peer_pid, MSG_DONTWAIT);
	if (status < 0) {
		UDEBUG("netlink_unicast() failed\n");
		/* FIXME: statistics */
	}

	inst->qlen = 0;
	inst->skb = NULL;
	inst->lastnlh = NULL;

	return status;
}

static void nfulnl_timer(unsigned long data)
{
	struct nfulnl_instance *inst = (struct nfulnl_instance *)data;

	UDEBUG("timer function called, flushing buffer\n");

	spin_lock_bh(&inst->lock);
	if (inst->skb)
		__nfulnl_send(inst);
	spin_unlock_bh(&inst->lock);
	instance_put(inst);
}

/* This is an inline function, we don't really care about a long
 * list of arguments */
static inline int
__build_packet_message(struct nfulnl_instance *inst,
			const struct sk_buff *skb,
			unsigned int data_len,
			unsigned int pf,
			unsigned int hooknum,
			const struct net_device *indev,
			const struct net_device *outdev,
			const struct nf_loginfo *li,
			const char *prefix, unsigned int plen)
{
	struct nfulnl_msg_packet_hdr pmsg;
	struct nlmsghdr *nlh;
	struct nfgenmsg *nfmsg;
	__be32 tmp_uint;
	sk_buff_data_t old_tail = inst->skb->tail;

	UDEBUG("entered\n");

	nlh = NLMSG_PUT(inst->skb, 0, 0,
			NFNL_SUBSYS_ULOG << 8 | NFULNL_MSG_PACKET,
			sizeof(struct nfgenmsg));
	nfmsg = NLMSG_DATA(nlh);
	nfmsg->nfgen_family = pf;
	nfmsg->version = NFNETLINK_V0;
	nfmsg->res_id = htons(inst->group_num);

	pmsg.hw_protocol	= skb->protocol;
	pmsg.hook		= hooknum;

	NFA_PUT(inst->skb, NFULA_PACKET_HDR, sizeof(pmsg), &pmsg);

	if (prefix)
		NFA_PUT(inst->skb, NFULA_PREFIX, plen, prefix);

	if (indev) {
		tmp_uint = htonl(indev->ifindex);
#ifndef CONFIG_BRIDGE_NETFILTER
		NFA_PUT(inst->skb, NFULA_IFINDEX_INDEV, sizeof(tmp_uint),
			&tmp_uint);
#else
		if (pf == PF_BRIDGE) {
			/* Case 1: outdev is physical input device, we need to
			 * look for bridge group (when called from
			 * netfilter_bridge) */
			NFA_PUT(inst->skb, NFULA_IFINDEX_PHYSINDEV,
				sizeof(tmp_uint), &tmp_uint);
			/* this is the bridge group "brX" */
			tmp_uint = htonl(indev->br_port->br->dev->ifindex);
			NFA_PUT(inst->skb, NFULA_IFINDEX_INDEV,
				sizeof(tmp_uint), &tmp_uint);
		} else {
			/* Case 2: indev is bridge group, we need to look for
			 * physical device (when called from ipv4) */
			NFA_PUT(inst->skb, NFULA_IFINDEX_INDEV,
				sizeof(tmp_uint), &tmp_uint);
			if (skb->nf_bridge && skb->nf_bridge->physindev) {
				tmp_uint =
				    htonl(skb->nf_bridge->physindev->ifindex);
				NFA_PUT(inst->skb, NFULA_IFINDEX_PHYSINDEV,
					sizeof(tmp_uint), &tmp_uint);
			}
		}
#endif
	}

	if (outdev) {
		tmp_uint = htonl(outdev->ifindex);
#ifndef CONFIG_BRIDGE_NETFILTER
		NFA_PUT(inst->skb, NFULA_IFINDEX_OUTDEV, sizeof(tmp_uint),
			&tmp_uint);
#else
		if (pf == PF_BRIDGE) {
			/* Case 1: outdev is physical output device, we need to
			 * look for bridge group (when called from
			 * netfilter_bridge) */
			NFA_PUT(inst->skb, NFULA_IFINDEX_PHYSOUTDEV,
				sizeof(tmp_uint), &tmp_uint);
			/* this is the bridge group "brX" */
			tmp_uint = htonl(outdev->br_port->br->dev->ifindex);
			NFA_PUT(inst->skb, NFULA_IFINDEX_OUTDEV,
				sizeof(tmp_uint), &tmp_uint);
		} else {
			/* Case 2: indev is a bridge group, we need to look
			 * for physical device (when called from ipv4) */
			NFA_PUT(inst->skb, NFULA_IFINDEX_OUTDEV,
				sizeof(tmp_uint), &tmp_uint);
			if (skb->nf_bridge && skb->nf_bridge->physoutdev) {
				tmp_uint =
				    htonl(skb->nf_bridge->physoutdev->ifindex);
				NFA_PUT(inst->skb, NFULA_IFINDEX_PHYSOUTDEV,
					sizeof(tmp_uint), &tmp_uint);
			}
		}
#endif
	}

	if (skb->mark) {
		tmp_uint = htonl(skb->mark);
		NFA_PUT(inst->skb, NFULA_MARK, sizeof(tmp_uint), &tmp_uint);
	}

	if (indev && skb->dev && skb->dev->hard_header_parse) {
		struct nfulnl_msg_packet_hw phw;
		int len = skb->dev->hard_header_parse((struct sk_buff *)skb,
						    phw.hw_addr);
		phw.hw_addrlen = htons(len);
		NFA_PUT(inst->skb, NFULA_HWADDR, sizeof(phw), &phw);
	}

	if (skb->tstamp.tv64) {
		struct nfulnl_msg_packet_timestamp ts;
		struct timeval tv = ktime_to_timeval(skb->tstamp);
		ts.sec = cpu_to_be64(tv.tv_sec);
		ts.usec = cpu_to_be64(tv.tv_usec);

		NFA_PUT(inst->skb, NFULA_TIMESTAMP, sizeof(ts), &ts);
	}

	/* UID */
	if (skb->sk) {
		read_lock_bh(&skb->sk->sk_callback_lock);
		if (skb->sk->sk_socket && skb->sk->sk_socket->file) {
			__be32 uid = htonl(skb->sk->sk_socket->file->f_uid);
			/* need to unlock here since NFA_PUT may goto */
			read_unlock_bh(&skb->sk->sk_callback_lock);
			NFA_PUT(inst->skb, NFULA_UID, sizeof(uid), &uid);
		} else
			read_unlock_bh(&skb->sk->sk_callback_lock);
	}

	/* local sequence number */
	if (inst->flags & NFULNL_CFG_F_SEQ) {
		tmp_uint = htonl(inst->seq++);
		NFA_PUT(inst->skb, NFULA_SEQ, sizeof(tmp_uint), &tmp_uint);
	}
	/* global sequence number */
	if (inst->flags & NFULNL_CFG_F_SEQ_GLOBAL) {
		tmp_uint = htonl(atomic_inc_return(&global_seq));
		NFA_PUT(inst->skb, NFULA_SEQ_GLOBAL, sizeof(tmp_uint), &tmp_uint);
	}

	if (data_len) {
		struct nfattr *nfa;
		int size = NFA_LENGTH(data_len);

		if (skb_tailroom(inst->skb) < (int)NFA_SPACE(data_len)) {
			printk(KERN_WARNING "nfnetlink_log: no tailroom!\n");
			goto nlmsg_failure;
		}

		nfa = (struct nfattr *)skb_put(inst->skb, NFA_ALIGN(size));
		nfa->nfa_type = NFULA_PAYLOAD;
		nfa->nfa_len = size;

		if (skb_copy_bits(skb, 0, NFA_DATA(nfa), data_len))
			BUG();
	}

	nlh->nlmsg_len = inst->skb->tail - old_tail;
	inst->lastnlh = nlh;
	return 0;

nlmsg_failure:
	UDEBUG("nlmsg_failure\n");
nfattr_failure:
	PRINTR(KERN_ERR "nfnetlink_log: error creating log nlmsg\n");
	return -1;
}

#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0)

static struct nf_loginfo default_loginfo = {
	.type =		NF_LOG_TYPE_ULOG,
	.u = {
		.ulog = {
			.copy_len	= 0xffff,
			.group		= 0,
			.qthreshold	= 1,
		},
	},
};

/* log handler for internal netfilter logging api */
static void
nfulnl_log_packet(unsigned int pf,
		  unsigned int hooknum,
		  const struct sk_buff *skb,
		  const struct net_device *in,
		  const struct net_device *out,
		  const struct nf_loginfo *li_user,
		  const char *prefix)
{
	unsigned int size, data_len;
	struct nfulnl_instance *inst;
	const struct nf_loginfo *li;
	unsigned int qthreshold;
	unsigned int plen;

	if (li_user && li_user->type == NF_LOG_TYPE_ULOG)
		li = li_user;
	else
		li = &default_loginfo;

	inst = instance_lookup_get(li->u.ulog.group);
	if (!inst)
		return;

	plen = 0;
	if (prefix)
		plen = strlen(prefix) + 1;

	/* all macros expand to constant values at compile time */
	/* FIXME: do we want to make the size calculation conditional based on
	 * what is actually present?  way more branches and checks, but more
	 * memory efficient... */
	size =    NLMSG_SPACE(sizeof(struct nfgenmsg))
		+ NFA_SPACE(sizeof(struct nfulnl_msg_packet_hdr))
		+ NFA_SPACE(sizeof(u_int32_t))	/* ifindex */
		+ NFA_SPACE(sizeof(u_int32_t))	/* ifindex */
#ifdef CONFIG_BRIDGE_NETFILTER
		+ NFA_SPACE(sizeof(u_int32_t))	/* ifindex */
		+ NFA_SPACE(sizeof(u_int32_t))	/* ifindex */
#endif
		+ NFA_SPACE(sizeof(u_int32_t))	/* mark */
		+ NFA_SPACE(sizeof(u_int32_t))	/* uid */
		+ NFA_SPACE(plen)		/* prefix */
		+ NFA_SPACE(sizeof(struct nfulnl_msg_packet_hw))
		+ NFA_SPACE(sizeof(struct nfulnl_msg_packet_timestamp));

	UDEBUG("initial size=%u\n", size);

	spin_lock_bh(&inst->lock);

	if (inst->flags & NFULNL_CFG_F_SEQ)
		size += NFA_SPACE(sizeof(u_int32_t));
	if (inst->flags & NFULNL_CFG_F_SEQ_GLOBAL)
		size += NFA_SPACE(sizeof(u_int32_t));

	qthreshold = inst->qthreshold;
	/* per-rule qthreshold overrides per-instance */
	if (qthreshold > li->u.ulog.qthreshold)
		qthreshold = li->u.ulog.qthreshold;

	switch (inst->copy_mode) {
	case NFULNL_COPY_META:
	case NFULNL_COPY_NONE:
		data_len = 0;
		break;

	case NFULNL_COPY_PACKET:
		if (inst->copy_range == 0
		    || inst->copy_range > skb->len)
			data_len = skb->len;
		else
			data_len = inst->copy_range;

		size += NFA_SPACE(data_len);
		UDEBUG("copy_packet, therefore size now %u\n", size);
		break;

	default:
		goto unlock_and_release;
	}

	if (inst->qlen >= qthreshold ||
	    (inst->skb && size > skb_tailroom(inst->skb))) {
		/* either the queue len is too high or we don't have
		 * enough room in the skb left. flush to userspace. */
		UDEBUG("flushing old skb\n");

		/* timer "holds" one reference (we have another one) */
		if (del_timer(&inst->timer))
			instance_put(inst);
		__nfulnl_send(inst);
	}

	if (!inst->skb) {
		inst->skb = nfulnl_alloc_skb(inst->nlbufsiz, size);
		if (!inst->skb)
			goto alloc_failure;
	}

	UDEBUG("qlen %d, qthreshold %d\n", inst->qlen, qthreshold);
	inst->qlen++;

	__build_packet_message(inst, skb, data_len, pf,
				hooknum, in, out, li, prefix, plen);

	/* timer_pending always called within inst->lock, so there
	 * is no chance of a race here */
	if (!timer_pending(&inst->timer)) {
		instance_get(inst);
		inst->timer.expires = jiffies + (inst->flushtimeout*HZ/100);
		add_timer(&inst->timer);
	}

unlock_and_release:
	spin_unlock_bh(&inst->lock);
	instance_put(inst);
	return;

alloc_failure:
	UDEBUG("error allocating skb\n");
	/* FIXME: statistics */
	goto unlock_and_release;
}

static int
nfulnl_rcv_nl_event(struct notifier_block *this,
		   unsigned long event, void *ptr)
{
	struct netlink_notify *n = ptr;

	if (event == NETLINK_URELEASE &&
	    n->protocol == NETLINK_NETFILTER && n->pid) {
		int i;

		/* destroy all instances for this pid */
		write_lock_bh(&instances_lock);
		for  (i = 0; i < INSTANCE_BUCKETS; i++) {
			struct hlist_node *tmp, *t2;
			struct nfulnl_instance *inst;
			struct hlist_head *head = &instance_table[i];

			hlist_for_each_entry_safe(inst, tmp, t2, head, hlist) {
				UDEBUG("node = %p\n", inst);
				if (n->pid == inst->peer_pid)
					__instance_destroy(inst);
			}
		}
		write_unlock_bh(&instances_lock);
	}
	return NOTIFY_DONE;
}

static struct notifier_block nfulnl_rtnl_notifier = {
	.notifier_call	= nfulnl_rcv_nl_event,
};

static int
nfulnl_recv_unsupp(struct sock *ctnl, struct sk_buff *skb,
		  struct nlmsghdr *nlh, struct nfattr *nfqa[])
{
	return -ENOTSUPP;
}

static struct nf_logger nfulnl_logger = {
	.name	= "nfnetlink_log",
	.logfn	= &nfulnl_log_packet,
	.me	= THIS_MODULE,
};

static const int nfula_min[NFULA_MAX] = {
	[NFULA_PACKET_HDR-1]	= sizeof(struct nfulnl_msg_packet_hdr),
	[NFULA_MARK-1]		= sizeof(u_int32_t),
	[NFULA_TIMESTAMP-1]	= sizeof(struct nfulnl_msg_packet_timestamp),
	[NFULA_IFINDEX_INDEV-1]	= sizeof(u_int32_t),
	[NFULA_IFINDEX_OUTDEV-1]= sizeof(u_int32_t),
	[NFULA_IFINDEX_PHYSINDEV-1]	= sizeof(u_int32_t),
	[NFULA_IFINDEX_PHYSOUTDEV-1]	= sizeof(u_int32_t),
	[NFULA_HWADDR-1]	= sizeof(struct nfulnl_msg_packet_hw),
	[NFULA_PAYLOAD-1]	= 0,
	[NFULA_PREFIX-1]	= 0,
	[NFULA_UID-1]		= sizeof(u_int32_t),
	[NFULA_SEQ-1]		= sizeof(u_int32_t),
	[NFULA_SEQ_GLOBAL-1]	= sizeof(u_int32_t),
};

static const int nfula_cfg_min[NFULA_CFG_MAX] = {
	[NFULA_CFG_CMD-1]	= sizeof(struct nfulnl_msg_config_cmd),
	[NFULA_CFG_MODE-1]	= sizeof(struct nfulnl_msg_config_mode),
	[NFULA_CFG_TIMEOUT-1]	= sizeof(u_int32_t),
	[NFULA_CFG_QTHRESH-1]	= sizeof(u_int32_t),
	[NFULA_CFG_NLBUFSIZ-1]	= sizeof(u_int32_t),
	[NFULA_CFG_FLAGS-1]	= sizeof(u_int16_t),
};

static int
nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb,
		   struct nlmsghdr *nlh, struct nfattr *nfula[])
{
	struct nfgenmsg *nfmsg = NLMSG_DATA(nlh);
	u_int16_t group_num = ntohs(nfmsg->res_id);
	struct nfulnl_instance *inst;
	int ret = 0;

	UDEBUG("entering for msg %u\n", NFNL_MSG_TYPE(nlh->nlmsg_type));

	if (nfattr_bad_size(nfula, NFULA_CFG_MAX, nfula_cfg_min)) {
		UDEBUG("bad attribute size\n");
		return -EINVAL;
	}

	inst = instance_lookup_get(group_num);
	if (nfula[NFULA_CFG_CMD-1]) {
		u_int8_t pf = nfmsg->nfgen_family;
		struct nfulnl_msg_config_cmd *cmd;
		cmd = NFA_DATA(nfula[NFULA_CFG_CMD-1]);
		UDEBUG("found CFG_CMD for\n");

		switch (cmd->command) {
		case NFULNL_CFG_CMD_BIND:
			if (inst) {
				ret = -EBUSY;
				goto out_put;
			}

			inst = instance_create(group_num,
					       NETLINK_CB(skb).pid);
			if (!inst) {
				ret = -EINVAL;
				goto out;
			}
			break;
		case NFULNL_CFG_CMD_UNBIND:
			if (!inst) {
				ret = -ENODEV;
				goto out;
			}

			if (inst->peer_pid != NETLINK_CB(skb).pid) {
				ret = -EPERM;
				goto out_put;
			}

			instance_destroy(inst);
			goto out;
		case NFULNL_CFG_CMD_PF_BIND:
			UDEBUG("registering log handler for pf=%u\n", pf);
			ret = nf_log_register(pf, &nfulnl_logger);
			break;
		case NFULNL_CFG_CMD_PF_UNBIND:
			UDEBUG("unregistering log handler for pf=%u\n", pf);
			/* This is a bug and a feature.  We cannot unregister
			 * other handlers, like nfnetlink_inst can */
			nf_log_unregister_pf(pf);
			break;
		default:
			ret = -EINVAL;
			break;
		}

		if (!inst)
			goto out;
	} else {
		if (!inst) {
			UDEBUG("no config command, and no instance for "
				"group=%u pid=%u =>ENOENT\n",
				group_num, NETLINK_CB(skb).pid);
			ret = -ENOENT;
			goto out;
		}

		if (inst->peer_pid != NETLINK_CB(skb).pid) {
			UDEBUG("no config command, and wrong pid\n");
			ret = -EPERM;
			goto out_put;
		}
	}

	if (nfula[NFULA_CFG_MODE-1]) {
		struct nfulnl_msg_config_mode *params;
		params = NFA_DATA(nfula[NFULA_CFG_MODE-1]);

		nfulnl_set_mode(inst, params->copy_mode,
				ntohl(params->copy_range));
	}

	if (nfula[NFULA_CFG_TIMEOUT-1]) {
		__be32 timeout =
			*(__be32 *)NFA_DATA(nfula[NFULA_CFG_TIMEOUT-1]);

		nfulnl_set_timeout(inst, ntohl(timeout));
	}

	if (nfula[NFULA_CFG_NLBUFSIZ-1]) {
		__be32 nlbufsiz =
			*(__be32 *)NFA_DATA(nfula[NFULA_CFG_NLBUFSIZ-1]);

		nfulnl_set_nlbufsiz(inst, ntohl(nlbufsiz));
	}

	if (nfula[NFULA_CFG_QTHRESH-1]) {
		__be32 qthresh =
			*(__be32 *)NFA_DATA(nfula[NFULA_CFG_QTHRESH-1]);

		nfulnl_set_qthresh(inst, ntohl(qthresh));
	}

	if (nfula[NFULA_CFG_FLAGS-1]) {
		__be16 flags =
			*(__be16 *)NFA_DATA(nfula[NFULA_CFG_FLAGS-1]);
		nfulnl_set_flags(inst, ntohs(flags));
	}

out_put:
	instance_put(inst);
out:
	return ret;
}

static struct nfnl_callback nfulnl_cb[NFULNL_MSG_MAX] = {
	[NFULNL_MSG_PACKET]	= { .call = nfulnl_recv_unsupp,
				    .attr_count = NFULA_MAX, },
	[NFULNL_MSG_CONFIG]	= { .call = nfulnl_recv_config,
				    .attr_count = NFULA_CFG_MAX, },
};

static struct nfnetlink_subsystem nfulnl_subsys = {
	.name		= "log",
	.subsys_id	= NFNL_SUBSYS_ULOG,
	.cb_count	= NFULNL_MSG_MAX,
	.cb		= nfulnl_cb,
};

#ifdef CONFIG_PROC_FS
struct iter_state {
	unsigned int bucket;
};

static struct hlist_node *get_first(struct iter_state *st)
{
	if (!st)
		return NULL;

	for (st->bucket = 0; st->bucket < INSTANCE_BUCKETS; st->bucket++) {
		if (!hlist_empty(&instance_table[st->bucket]))
			return instance_table[st->bucket].first;
	}
	return NULL;
}

static struct hlist_node *get_next(struct iter_state *st, struct hlist_node *h)
{
	h = h->next;
	while (!h) {
		if (++st->bucket >= INSTANCE_BUCKETS)
			return NULL;

		h = instance_table[st->bucket].first;
	}
	return h;
}

static struct hlist_node *get_idx(struct iter_state *st, loff_t pos)
{
	struct hlist_node *head;
	head = get_first(st);

	if (head)
		while (pos && (head = get_next(st, head)))
			pos--;
	return pos ? NULL : head;
}

static void *seq_start(struct seq_file *seq, loff_t *pos)
{
	read_lock_bh(&instances_lock);
	return get_idx(seq->private, *pos);
}

static void *seq_next(struct seq_file *s, void *v, loff_t *pos)
{
	(*pos)++;
	return get_next(s->private, v);
}

static void seq_stop(struct seq_file *s, void *v)
{
	read_unlock_bh(&instances_lock);
}

static int seq_show(struct seq_file *s, void *v)
{
	const struct nfulnl_instance *inst = v;

	return seq_printf(s, "%5d %6d %5d %1d %5d %6d %2d\n",
			  inst->group_num,
			  inst->peer_pid, inst->qlen,
			  inst->copy_mode, inst->copy_range,
			  inst->flushtimeout, atomic_read(&inst->use));
}

static const struct seq_operations nful_seq_ops = {
	.start	= seq_start,
	.next	= seq_next,
	.stop	= seq_stop,
	.show	= seq_show,
};

static int nful_open(struct inode *inode, struct file *file)
{
	struct seq_file *seq;
	struct iter_state *is;
	int ret;

	is = kzalloc(sizeof(*is), GFP_KERNEL);
	if (!is)
		return -ENOMEM;
	ret = seq_open(file, &nful_seq_ops);
	if (ret < 0)
		goto out_free;
	seq = file->private_data;
	seq->private = is;
	return ret;
out_free:
	kfree(is);
	return ret;
}

static const struct file_operations nful_file_ops = {
	.owner	 = THIS_MODULE,
	.open	 = nful_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = seq_release_private,
};

#endif /* PROC_FS */

static int __init nfnetlink_log_init(void)
{
	int i, status = -ENOMEM;
#ifdef CONFIG_PROC_FS
	struct proc_dir_entry *proc_nful;
#endif

	for (i = 0; i < INSTANCE_BUCKETS; i++)
		INIT_HLIST_HEAD(&instance_table[i]);

	/* it's not really all that important to have a random value, so
	 * we can do this from the init function, even if there hasn't
	 * been that much entropy yet */
	get_random_bytes(&hash_init, sizeof(hash_init));

	netlink_register_notifier(&nfulnl_rtnl_notifier);
	status = nfnetlink_subsys_register(&nfulnl_subsys);
	if (status < 0) {
		printk(KERN_ERR "log: failed to create netlink socket\n");
		goto cleanup_netlink_notifier;
	}

#ifdef CONFIG_PROC_FS
	proc_nful = create_proc_entry("nfnetlink_log", 0440,
				      proc_net_netfilter);
	if (!proc_nful)
		goto cleanup_subsys;
	proc_nful->proc_fops = &nful_file_ops;
#endif
	return status;

#ifdef CONFIG_PROC_FS
cleanup_subsys:
	nfnetlink_subsys_unregister(&nfulnl_subsys);
#endif
cleanup_netlink_notifier:
	netlink_unregister_notifier(&nfulnl_rtnl_notifier);
	return status;
}

static void __exit nfnetlink_log_fini(void)
{
	nf_log_unregister(&nfulnl_logger);
#ifdef CONFIG_PROC_FS
	remove_proc_entry("nfnetlink_log", proc_net_netfilter);
#endif
	nfnetlink_subsys_unregister(&nfulnl_subsys);
	netlink_unregister_notifier(&nfulnl_rtnl_notifier);
}

MODULE_DESCRIPTION("netfilter userspace logging");
MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
MODULE_LICENSE("GPL");
MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_ULOG);

module_init(nfnetlink_log_init);
module_exit(nfnetlink_log_fini);