summaryrefslogtreecommitdiffstats
path: root/br-nf-bds/patches/bridge-nf-0.0.8-bds-against-2.4.18.diff
blob: ad742c7a6c84715bd141aee11980a37fa1107197 (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
bridge-nf-0.0.8-bds - 26 May

difference between 0.0.7 and 0.0.8:

let iptables mangle table FORWARD chain see the physical out-dev

--- linux/include/linux/netfilter.h	Thu Nov 22 20:47:48 2001
+++ bridge-nf-0.0.8-bds/include/linux/netfilter.h	Sun May 26 12:49:04 2002
@@ -117,17 +117,23 @@
 /* This is gross, but inline doesn't cut it for avoiding the function
    call in fast path: gcc doesn't inline (needs value tracking?). --RR */
 #ifdef CONFIG_NETFILTER_DEBUG
-#define NF_HOOK nf_hook_slow
+#define NF_HOOK(pf, hook, skb, indev, outdev, okfn)			\
+		nf_hook_slow((pf), (hook), (skb), (indev), (outdev), (okfn), INT_MIN)
+#define NF_HOOK_THRESH nf_hook_slow
 #else
 #define NF_HOOK(pf, hook, skb, indev, outdev, okfn)			\
 (list_empty(&nf_hooks[(pf)][(hook)])					\
  ? (okfn)(skb)								\
- : nf_hook_slow((pf), (hook), (skb), (indev), (outdev), (okfn)))
+ : nf_hook_slow((pf), (hook), (skb), (indev), (outdev), (okfn), INT_MIN))
+#define NF_HOOK_THRESH(pf, hook, skb, indev, outdev, okfn, thresh)	\
+(list_empty(&nf_hooks[(pf)][(hook)])					\
+ ? (okfn)(skb)								\
+ : nf_hook_slow((pf), (hook), (skb), (indev), (outdev), (okfn), (thresh)))
 #endif
 
 int nf_hook_slow(int pf, unsigned int hook, struct sk_buff *skb,
 		 struct net_device *indev, struct net_device *outdev,
-		 int (*okfn)(struct sk_buff *));
+		 int (*okfn)(struct sk_buff *), int thresh);
 
 /* Call setsockopt() */
 int nf_setsockopt(struct sock *sk, int pf, int optval, char *opt, 
--- linux/include/linux/netfilter_ipv4.h	Mon Feb 25 20:38:13 2002
+++ bridge-nf-0.0.8-bds/include/linux/netfilter_ipv4.h	Sun May 26 12:52:30 2002
@@ -52,8 +52,10 @@
 enum nf_ip_hook_priorities {
 	NF_IP_PRI_FIRST = INT_MIN,
 	NF_IP_PRI_CONNTRACK = -200,
+	NF_IP_PRI_BRIDGE_SABOTAGE_FORWARD = -175,
 	NF_IP_PRI_MANGLE = -150,
 	NF_IP_PRI_NAT_DST = -100,
+	NF_IP_PRI_BRIDGE_SABOTAGE = -50,
 	NF_IP_PRI_FILTER = 0,
 	NF_IP_PRI_NAT_SRC = 100,
 	NF_IP_PRI_LAST = INT_MAX,
--- linux/include/linux/skbuff.h	Thu Nov 22 20:46:26 2001
+++ bridge-nf-0.0.8-bds/include/linux/skbuff.h	Sun May 26 12:49:04 2002
@@ -135,6 +135,8 @@
 	struct sock	*sk;			/* Socket we are owned by 			*/
 	struct timeval	stamp;			/* Time we arrived				*/
 	struct net_device	*dev;		/* Device we arrived on/are leaving by		*/
+	struct net_device	*physindev;	/* Physical device we arrived on		*/
+	struct net_device	*physoutdev;	/* Physical device we will leave by		*/
 
 	/* Transport layer header */
 	union
--- linux/net/bridge/br.c	Mon Feb 25 20:38:14 2002
+++ bridge-nf-0.0.8-bds/net/bridge/br.c	Sun May 26 12:49:04 2002
@@ -42,6 +42,11 @@
 {
 	printk(KERN_INFO "NET4: Ethernet Bridge 008 for NET4.0\n");
 
+#ifdef CONFIG_BRIDGE_NF
+	if (br_netfilter_init())
+		return 1;
+#endif
+
 	br_handle_frame_hook = br_handle_frame;
 	br_ioctl_hook = br_ioctl_deviceless_stub;
 #if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)
@@ -65,6 +70,9 @@
 
 static void __exit br_deinit(void)
 {
+#ifdef CONFIG_BRIDGE_NF
+	br_netfilter_fini();
+#endif
 	unregister_netdevice_notifier(&br_device_notifier);
 	br_call_ioctl_atomic(__br_clear_ioctl_hook);
 	net_call_rx_atomic(__br_clear_frame_hook);
--- linux/net/bridge/br_forward.c	Wed Aug 15 10:54:35 2001
+++ bridge-nf-0.0.8-bds/net/bridge/br_forward.c	Sun May 26 12:49:04 2002
@@ -30,7 +30,7 @@
 	return 1;
 }
 
-static int __dev_queue_push_xmit(struct sk_buff *skb)
+int br_dev_queue_push_xmit(struct sk_buff *skb)
 {
 	skb_push(skb, ETH_HLEN);
 	dev_queue_xmit(skb);
@@ -38,10 +38,10 @@
 	return 0;
 }
 
-static int __br_forward_finish(struct sk_buff *skb)
+int br_forward_finish(struct sk_buff *skb)
 {
 	NF_HOOK(PF_BRIDGE, NF_BR_POST_ROUTING, skb, NULL, skb->dev,
-			__dev_queue_push_xmit);
+			br_dev_queue_push_xmit);
 
 	return 0;
 }
@@ -54,7 +54,7 @@
 	skb->dev = to->dev;
 
 	NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_OUT, skb, indev, skb->dev,
-			__br_forward_finish);
+			br_forward_finish);
 }
 
 static void __br_forward(struct net_bridge_port *to, struct sk_buff *skb)
@@ -65,7 +65,7 @@
 	skb->dev = to->dev;
 
 	NF_HOOK(PF_BRIDGE, NF_BR_FORWARD, skb, indev, skb->dev,
-			__br_forward_finish);
+			br_forward_finish);
 }
 
 /* called under bridge lock */
--- linux/net/bridge/br_input.c	Mon Feb 25 20:38:14 2002
+++ bridge-nf-0.0.8-bds/net/bridge/br_input.c	Sun May 26 12:49:04 2002
@@ -46,7 +46,7 @@
 			br_pass_frame_up_finish);
 }
 
-static int br_handle_frame_finish(struct sk_buff *skb)
+int br_handle_frame_finish(struct sk_buff *skb)
 {
 	struct net_bridge *br;
 	unsigned char *dest;
--- linux/net/bridge/br_private.h	Mon Feb 25 20:38:14 2002
+++ bridge-nf-0.0.8-bds/net/bridge/br_private.h	Sun May 26 12:49:04 2002
@@ -120,6 +120,7 @@
 extern void br_inc_use_count(void);
 
 /* br_device.c */
+extern int  br_dev_xmit(struct sk_buff *skb, struct net_device *dev);
 extern void br_dev_setup(struct net_device *dev);
 extern int br_dev_xmit(struct sk_buff *skb, struct net_device *dev);
 
@@ -144,8 +145,10 @@
 /* br_forward.c */
 extern void br_deliver(struct net_bridge_port *to,
 		struct sk_buff *skb);
+extern int  br_dev_queue_push_xmit(struct sk_buff *skb);
 extern void br_forward(struct net_bridge_port *to,
 		struct sk_buff *skb);
+extern int  br_forward_finish(struct sk_buff *skb);
 extern void br_flood_deliver(struct net_bridge *br,
 		      struct sk_buff *skb,
 		      int clone);
@@ -166,6 +169,7 @@
 			   int *ifindices);
 
 /* br_input.c */
+extern int  br_handle_frame_finish(struct sk_buff *skb);
 extern void br_handle_frame(struct sk_buff *skb);
 
 /* br_ioctl.c */
@@ -177,6 +181,10 @@
 	     unsigned long arg2);
 extern int br_ioctl_deviceless_stub(unsigned long arg);
 
+/* br_netfilter.c */
+extern int br_netfilter_init(void);
+extern void br_netfilter_fini(void);
+
 /* br_stp.c */
 extern int br_is_root_bridge(struct net_bridge *br);
 extern struct net_bridge_port *br_get_port(struct net_bridge *br,
--- linux/net/bridge/Makefile	Fri Dec 29 23:07:24 2000
+++ bridge-nf-0.0.8-bds/net/bridge/Makefile	Sun May 26 12:49:04 2002
@@ -13,4 +13,6 @@
 			br_stp_if.o br_stp_timer.o
 obj-m		:= $(O_TARGET)
 
+obj-$(CONFIG_BRIDGE_NF) += br_netfilter.o
+
 include $(TOPDIR)/Rules.make
--- linux/net/Config.in	Mon Feb 25 20:38:14 2002
+++ bridge-nf-0.0.8-bds/net/Config.in	Sun May 26 12:49:04 2002
@@ -61,6 +61,9 @@
 fi
 dep_tristate '802.1d Ethernet Bridging' CONFIG_BRIDGE $CONFIG_INET
 if [ "$CONFIG_EXPERIMENTAL" = "y" ]; then
+   if [ "$CONFIG_BRIDGE" != "n" -a "$CONFIG_NETFILTER" != "n" ]; then
+      bool '  netfilter (firewalling) support' CONFIG_BRIDGE_NF
+   fi
    tristate 'CCITT X.25 Packet Layer (EXPERIMENTAL)' CONFIG_X25
    tristate 'LAPB Data Link Driver (EXPERIMENTAL)' CONFIG_LAPB
    bool '802.2 LLC (EXPERIMENTAL)' CONFIG_LLC
--- linux/net/core/netfilter.c	Mon Feb 25 20:38:14 2002
+++ bridge-nf-0.0.8-bds/net/core/netfilter.c	Sun May 26 12:49:04 2002
@@ -343,10 +343,15 @@
 			       const struct net_device *indev,
 			       const struct net_device *outdev,
 			       struct list_head **i,
-			       int (*okfn)(struct sk_buff *))
+			       int (*okfn)(struct sk_buff *),
+			       int hook_thresh)
 {
 	for (*i = (*i)->next; *i != head; *i = (*i)->next) {
 		struct nf_hook_ops *elem = (struct nf_hook_ops *)*i;
+
+		if (hook_thresh > elem->priority)
+			continue;
+
 		switch (elem->hook(hook, skb, indev, outdev, okfn)) {
 		case NF_QUEUE:
 			return NF_QUEUE;
@@ -414,6 +419,8 @@
 {
 	int status;
 	struct nf_info *info;
+	struct net_device *physindev;
+	struct net_device *physoutdev;
 
 	if (!queue_handler[pf].outfn) {
 		kfree_skb(skb);
@@ -436,11 +443,16 @@
 	if (indev) dev_hold(indev);
 	if (outdev) dev_hold(outdev);
 
+	if ((physindev = skb->physindev)) dev_hold(physindev);
+	if ((physoutdev = skb->physoutdev)) dev_hold(physoutdev);
+
 	status = queue_handler[pf].outfn(skb, info, queue_handler[pf].data);
 	if (status < 0) {
 		/* James M doesn't say fuck enough. */
 		if (indev) dev_put(indev);
 		if (outdev) dev_put(outdev);
+		if (physindev) dev_put(physindev);
+		if (physoutdev) dev_put(physoutdev);
 		kfree(info);
 		kfree_skb(skb);
 		return;
@@ -450,7 +462,8 @@
 int nf_hook_slow(int pf, unsigned int hook, struct sk_buff *skb,
 		 struct net_device *indev,
 		 struct net_device *outdev,
-		 int (*okfn)(struct sk_buff *))
+		 int (*okfn)(struct sk_buff *),
+		 int hook_thresh)
 {
 	struct list_head *elem;
 	unsigned int verdict;
@@ -482,7 +495,7 @@
 
 	elem = &nf_hooks[pf][hook];
 	verdict = nf_iterate(&nf_hooks[pf][hook], &skb, hook, indev,
-			     outdev, &elem, okfn);
+			     outdev, &elem, okfn, hook_thresh);
 	if (verdict == NF_QUEUE) {
 		NFDEBUG("nf_hook: Verdict = QUEUE.\n");
 		nf_queue(skb, elem, pf, hook, indev, outdev, okfn);
@@ -531,7 +544,7 @@
 		verdict = nf_iterate(&nf_hooks[info->pf][info->hook],
 				     &skb, info->hook, 
 				     info->indev, info->outdev, &elem,
-				     info->okfn);
+				     info->okfn, INT_MIN);
 	}
 
 	switch (verdict) {
--- linux/net/core/skbuff.c	Fri Dec 21 18:42:05 2001
+++ bridge-nf-0.0.8-bds/net/core/skbuff.c	Sun May 26 12:49:04 2002
@@ -231,6 +231,8 @@
 	skb->sk = NULL;
 	skb->stamp.tv_sec=0;	/* No idea about time */
 	skb->dev = NULL;
+	skb->physindev = NULL;
+	skb->physoutdev = NULL;
 	skb->dst = NULL;
 	memset(skb->cb, 0, sizeof(skb->cb));
 	skb->pkt_type = PACKET_HOST;	/* Default type */
@@ -362,6 +364,8 @@
 	n->sk = NULL;
 	C(stamp);
 	C(dev);
+	C(physindev);
+	C(physoutdev);
 	C(h);
 	C(nh);
 	C(mac);
@@ -417,6 +421,8 @@
 	new->list=NULL;
 	new->sk=NULL;
 	new->dev=old->dev;
+	new->physindev=old->physindev;
+	new->physoutdev=old->physoutdev;
 	new->priority=old->priority;
 	new->protocol=old->protocol;
 	new->dst=dst_clone(old->dst);
--- linux/net/ipv4/ip_output.c	Wed Oct 17 23:16:39 2001
+++ bridge-nf-0.0.8-bds/net/ipv4/ip_output.c	Sun May 26 12:49:04 2002
@@ -819,6 +819,8 @@
 			skb_set_owner_w(skb2, skb->sk);
 		skb2->dst = dst_clone(skb->dst);
 		skb2->dev = skb->dev;
+		skb2->physindev = skb->physindev;
+		skb2->physoutdev = skb->physoutdev;
 
 		/*
 		 *	Copy the packet header into the new buffer.
@@ -882,6 +884,7 @@
 		iph->tot_len = htons(len + hlen);
 
 		ip_send_check(iph);
+		memcpy(skb2->data - 16, skb->data - 16, 16);
 
 		err = output(skb2);
 		if (err)
--- linux/net/ipv4/netfilter/ip_tables.c	Mon Feb 25 20:38:14 2002
+++ bridge-nf-0.0.8-bds/net/ipv4/netfilter/ip_tables.c	Sun May 26 12:49:04 2002
@@ -121,12 +121,15 @@
 static inline int
 ip_packet_match(const struct iphdr *ip,
 		const char *indev,
+		const char *physindev,
 		const char *outdev,
+		const char *physoutdev,
 		const struct ipt_ip *ipinfo,
 		int isfrag)
 {
 	size_t i;
 	unsigned long ret;
+	unsigned long ret2;
 
 #define FWINV(bool,invflg) ((bool) ^ !!(ipinfo->invflags & invflg))
 
@@ -156,7 +159,13 @@
 			& ((const unsigned long *)ipinfo->iniface_mask)[i];
 	}
 
-	if (FWINV(ret != 0, IPT_INV_VIA_IN)) {
+	for (i = 0, ret2 = 0; i < IFNAMSIZ/sizeof(unsigned long); i++) {
+		ret2 |= (((const unsigned long *)physindev)[i]
+			^ ((const unsigned long *)ipinfo->iniface)[i])
+			& ((const unsigned long *)ipinfo->iniface_mask)[i];
+	}
+
+	if (FWINV(ret != 0 && ret2 != 0, IPT_INV_VIA_IN)) {
 		dprintf("VIA in mismatch (%s vs %s).%s\n",
 			indev, ipinfo->iniface,
 			ipinfo->invflags&IPT_INV_VIA_IN ?" (INV)":"");
@@ -169,7 +178,13 @@
 			& ((const unsigned long *)ipinfo->outiface_mask)[i];
 	}
 
-	if (FWINV(ret != 0, IPT_INV_VIA_OUT)) {
+	for (i = 0, ret2 = 0; i < IFNAMSIZ/sizeof(unsigned long); i++) {
+		ret2 |= (((const unsigned long *)physoutdev)[i]
+			^ ((const unsigned long *)ipinfo->outiface)[i])
+			& ((const unsigned long *)ipinfo->outiface_mask)[i];
+	}
+
+	if (FWINV(ret != 0 && ret2 != 0, IPT_INV_VIA_OUT)) {
 		dprintf("VIA out mismatch (%s vs %s).%s\n",
 			outdev, ipinfo->outiface,
 			ipinfo->invflags&IPT_INV_VIA_OUT ?" (INV)":"");
@@ -268,6 +283,7 @@
 	/* Initializing verdict to NF_DROP keeps gcc happy. */
 	unsigned int verdict = NF_DROP;
 	const char *indev, *outdev;
+	const char *physindev, *physoutdev;
 	void *table_base;
 	struct ipt_entry *e, *back;
 
@@ -277,6 +293,9 @@
 	datalen = (*pskb)->len - ip->ihl * 4;
 	indev = in ? in->name : nulldevname;
 	outdev = out ? out->name : nulldevname;
+	physindev = (*pskb)->physindev ? (*pskb)->physindev->name : nulldevname;
+	physoutdev = (*pskb)->physoutdev ? (*pskb)->physoutdev->name : nulldevname;
+
 	/* We handle fragments by dealing with the first fragment as
 	 * if it was a normal packet.  All other fragments are treated
 	 * normally, except that they will NEVER match rules that ask
@@ -312,7 +331,7 @@
 		IP_NF_ASSERT(e);
 		IP_NF_ASSERT(back);
 		(*pskb)->nfcache |= e->nfcache;
-		if (ip_packet_match(ip, indev, outdev, &e->ip, offset)) {
+		if (ip_packet_match(ip, indev, physindev, outdev, physoutdev, &e->ip, offset)) {
 			struct ipt_entry_target *t;
 
 			if (IPT_MATCH_ITERATE(e, do_match,
--- linux/net/ipv4/netfilter/ipt_LOG.c	Mon Feb 25 20:38:14 2002
+++ bridge-nf-0.0.8-bds/net/ipv4/netfilter/ipt_LOG.c	Sun May 26 12:49:04 2002
@@ -285,10 +285,13 @@
 	level_string[1] = '0' + (loginfo->level % 8);
 	spin_lock_bh(&log_lock);
 	printk(level_string);
-	printk("%sIN=%s OUT=%s ",
-	       loginfo->prefix,
-	       in ? in->name : "",
-	       out ? out->name : "");
+	printk("%sIN=%s ", loginfo->prefix, in ? in->name : "");
+	if ((*pskb)->physindev && in != (*pskb)->physindev)
+		printk("PHYSIN=%s ", (*pskb)->physindev->name);
+	printk("OUT=%s ", out ? out->name : "");
+	if ((*pskb)->physoutdev && out != (*pskb)->physoutdev)
+		printk("PHYSOUT=%s ", (*pskb)->physoutdev->name);
+
 	if (in && !out) {
 		/* MAC logging for input chain only. */
 		printk("MAC=");
--- /dev/null	Sat May 18 12:04:21 2002
+++ bridge-nf-0.0.8-bds/net/bridge/br_netfilter.c	Sun May 26 12:59:00 2002
@@ -0,0 +1,567 @@
+/*
+ *	Handle firewalling
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek               <buytenh@gnu.org>
+ *	Bart De Schuymer		<bart.de.schuymer@pandora.be>
+ *
+ *	$Id: bridge-nf-0.0.8-bds-against-2.4.18.diff,v 1.1 2002/06/01 19:24:01 bdschuym Exp $
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ *
+ *	Lennert dedicates this file to Kerstin Wurdinger.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/ip.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/if_ether.h>
+#include <linux/netfilter_bridge.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/in_route.h>
+#include <net/ip.h>
+#include <net/tcp.h>
+#include <asm/uaccess.h>
+#include <asm/checksum.h>
+#include "br_private.h"
+
+
+#ifndef WE_REALLY_INSIST_ON_NOT_HAVING_NAT_SUPPORT
+/* As the original source/destination addresses are variables private to this
+ * file, we store them in unused space at the end of the control buffer.
+ * On 64-bit platforms the TCP control buffer size still leaves us 8 bytes
+ * of space at the end, so that fits.  Usage of the original source address
+ * and the original destination address never overlaps (daddr is needed
+ * around PRE_ROUTING, and saddr around POST_ROUTING), so that's okay as
+ * well.
+ */
+#define skb_origaddr(skb)		(*((u32 *)((skb)->cb + sizeof((skb)->cb) - 4)))
+
+#define store_orig_dstaddr(skb)		(skb_origaddr(skb) = (skb)->nh.iph->daddr)
+#define store_orig_srcaddr(skb)		(skb_origaddr(skb) = (skb)->nh.iph->saddr)
+#define dnat_took_place(skb)		(skb_origaddr(skb) != (skb)->nh.iph->daddr)
+#define snat_took_place(skb)		(skb_origaddr(skb) != (skb)->nh.iph->saddr)
+#else
+#define store_orig_dstaddr(skb)
+#define store_orig_srcaddr(skb)
+#define dnat_took_place(skb)		(0)
+#define snat_took_place(skb)		(0)
+#endif
+
+
+#define has_bridge_parent(device)	((device)->br_port != NULL)
+#define bridge_parent(device)		(&((device)->br_port->br->dev))
+
+
+/* As opposed to the DNAT case, for the SNAT case it's not quite
+ * clear what we should do with ethernet addresses in NAT'ed
+ * packets.  Use this heuristic for now.
+ */
+static inline void __maybe_fixup_src_address(struct sk_buff *skb)
+{
+	if (snat_took_place(skb) &&
+	    inet_addr_type(skb->nh.iph->saddr) == RTN_LOCAL) {
+		memcpy(skb->mac.ethernet->h_source,
+			bridge_parent(skb->dev)->dev_addr,
+			ETH_ALEN);
+	}
+}
+
+
+/* We need these fake structures to make netfilter happy --
+ * lots of places assume that skb->dst != NULL, which isn't
+ * all that unreasonable.
+ *
+ * Currently, we fill in the PMTU entry because netfilter
+ * refragmentation needs it, and the rt_flags entry because
+ * ipt_REJECT needs it.  Future netfilter modules might
+ * require us to fill additional fields.
+ */
+static struct net_device __fake_net_device = {
+	hard_header_len:	ETH_HLEN
+};
+
+static struct rtable __fake_rtable = {
+	u: {
+		dst: {
+			__refcnt:		ATOMIC_INIT(1),
+			dev:			&__fake_net_device,
+			pmtu:			1500
+		}
+	},
+
+	rt_flags:	0
+};
+
+
+/* PF_BRIDGE/PRE_ROUTING *********************************************/
+static void __br_dnat_complain(void)
+{
+	static unsigned long last_complaint = 0;
+
+	if (jiffies - last_complaint >= 5 * HZ) {
+		printk(KERN_WARNING "Performing cross-bridge DNAT requires IP "
+			"forwarding to be enabled\n");
+		last_complaint = jiffies;
+	}
+}
+
+
+static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb)
+{
+	skb->dev = bridge_parent(skb->dev);
+	skb->dst->output(skb);
+	return 0;
+}
+
+/* This requires some explaining.  If DNAT has taken place,
+ * we will need to fix up the destination ethernet address,
+ * and this is a tricky process.
+ *
+ * There are two cases to consider:
+ * 1. The packet was DNAT'ed to a device in the same bridge
+ *    port group as it was received on.  We can still bridge
+ *    the packet.
+ * 2. The packet was DNAT'ed to a different device, either
+ *    a non-bridged device or another bridge port group.
+ *    The packet will need to be routed.
+ *
+ * The way to distinguish between the two is by calling ip_route_input()
+ * and looking at skb->dst->dev, which it changed to the destination device
+ * if ip_route_input() succeeds.
+ *
+ * Let us first consider ip_route_input() succeeds:
+ *
+ * If skb->dst->dev equals the logical bridge device the packet came in on,
+ * we can consider this bridging. We then call skb->dst->output() which will
+ * make the packet enter br_nf_local_out() not much later. In that function
+ * it is assured that the iptables FORWARD chain is traversed for the packet.
+ *
+ * Else, the packet is considered to be routed and we just change the
+ * destination MAC address so that the packet will later be passed up to the ip
+ * stack to be routed.
+ *
+ * Let us now consider ip_route_input() fails:
+ *
+ * After a "echo '0' > /proc/sys/net/ipv4/ip_forward" ip_route_input() will
+ * fail, while ip_route_output() will return success. The source address for
+ * for ip_route_output() is set to zero, so ip_route_output()
+ * thinks we're handling a locally generated packet and won't care if
+ * ip forwarding is allowed. We send a warning message to the users's log
+ * telling her to put ip forwarding on.
+ *
+ * ip_route_input() will also fail if there is no route available. Then we just
+ * drop the packet.
+ *
+ * The other special thing happening here is putting skb->physoutdev on
+ * &__fake_net_device (resp. NULL) for bridged (resp. routed) packets. This is
+ * needed so that br_nf_local_out() can know that it has to give the packets to
+ * the BR_NF_FORWARD (resp. BR_NF_LOCAL_OUT) bridge hook. See that function.
+ * --Lennert, 20020411
+ * --Bart, 20020416 (updated)
+ */
+
+static int br_nf_pre_routing_finish(struct sk_buff *skb)
+{
+	struct net_device *dev = skb->dev;
+	struct iphdr *iph = skb->nh.iph;
+
+	if (dnat_took_place(skb)) {
+		if (ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev)) {
+			struct rtable *rt;
+
+			if (!ip_route_output(&rt, iph->daddr, 0, iph->tos, 0)) {
+				// bridged dnated traffic isn't dependent on
+				// disabled ip_forwarding
+				if (((struct dst_entry *)rt)->dev == dev) {
+					skb->dst = (struct dst_entry *)rt;
+					goto bridged_dnat;
+				}
+				__br_dnat_complain();
+				dst_release((struct dst_entry *)rt);
+			}
+			kfree_skb(skb);
+			return 0;
+		} else {
+			if (skb->dst->dev == dev) {
+bridged_dnat:
+				// tell br_nf_local_out this is a bridged frame
+				skb->physoutdev = &__fake_net_device;
+				skb->dev = skb->physindev;
+				NF_HOOK_THRESH(PF_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
+						br_nf_pre_routing_finish_bridge, 1);
+				return 0;
+			}
+			// tell br_nf_local_out this is a routed frame
+			skb->physoutdev = NULL;
+			memcpy(skb->mac.ethernet->h_dest, dev->dev_addr, ETH_ALEN);
+		}
+	} else {
+		skb->dst = (struct dst_entry *)&__fake_rtable;
+		dst_hold(skb->dst);
+	}
+
+	skb->dev = skb->physindev;
+	NF_HOOK_THRESH(PF_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
+			br_handle_frame_finish, 1);
+
+	return 0;
+}
+
+/* Replicate the checks that IPv4 does on packet reception.
+ * Set skb->dev to the bridge device (i.e. parent of the
+ * receiving device) to make netfilter happy, the REDIRECT
+ * target in particular.  Save the original destination IP
+ * address to be able to detect DNAT afterwards.
+ */
+static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *))
+{
+	struct iphdr *iph;
+	__u32 len;
+	struct sk_buff *skb;
+
+	if ((*pskb)->protocol != __constant_htons(ETH_P_IP))
+		return NF_ACCEPT;
+
+	if ((skb = skb_share_check(*pskb, GFP_ATOMIC)) == NULL)
+		goto out;
+
+	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+		goto inhdr_error;
+
+	iph = skb->nh.iph;
+	if (iph->ihl < 5 || iph->version != 4)
+		goto inhdr_error;
+
+	if (!pskb_may_pull(skb, 4*iph->ihl))
+		goto inhdr_error;
+
+	iph = skb->nh.iph;
+	if (ip_fast_csum((__u8 *)iph, iph->ihl) != 0)
+		goto inhdr_error;
+
+	len = ntohs(iph->tot_len);
+	if (skb->len < len || len < 4*iph->ihl)
+		goto inhdr_error;
+
+	if (skb->len > len) {
+		__pskb_trim(skb, len);
+		if (skb->ip_summed == CHECKSUM_HW)
+			skb->ip_summed = CHECKSUM_NONE;
+	}
+
+	skb->physindev = skb->dev;
+	skb->dev = bridge_parent(skb->dev);
+	if (skb->pkt_type == PACKET_OTHERHOST)
+		skb->pkt_type = PACKET_HOST;
+	store_orig_dstaddr(skb);
+	NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, skb->dev, NULL,
+		br_nf_pre_routing_finish);
+
+	return NF_STOLEN;
+
+inhdr_error:
+//	IP_INC_STATS_BH(IpInHdrErrors);
+out:
+	return NF_DROP;
+}
+
+
+/* PF_BRIDGE/LOCAL_IN ************************************************/
+/* The packet is locally destined, which requires a real
+ * dst_entry, so detach the fake one.  On the way up, the
+ * packet would pass through PRE_ROUTING again (which already
+ * took place when the packet entered the bridge), but we
+ * register an IPv4 PRE_ROUTING 'sabotage' hook that will
+ * prevent this from happening.
+ */
+static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *))
+{
+	struct sk_buff *skb = *pskb;
+
+	if (skb->protocol != __constant_htons(ETH_P_IP))
+		return NF_ACCEPT;
+
+	if (skb->dst == (struct dst_entry *)&__fake_rtable) {
+		dst_release(skb->dst);
+		skb->dst = NULL;
+	}
+
+	return NF_ACCEPT;
+}
+
+
+/* PF_BRIDGE/FORWARD *************************************************/
+static int br_nf_forward_finish(struct sk_buff *skb)
+{
+	NF_HOOK_THRESH(PF_BRIDGE, NF_BR_FORWARD, skb, skb->physindev,
+			skb->dev, br_forward_finish, 1);
+
+	return 0;
+}
+
+/* This is the 'purely bridged' case.  We pass the packet to
+ * netfilter with indev and outdev set to the bridge device,
+ * but we are still able to filter on the 'real' indev/outdev
+ * because another bit of the bridge-nf patch overloads the
+ * '-i' and '-o' iptables interface checks to take
+ * skb->phys{in,out}dev into account as well (so both the real
+ * device and the bridge device will match).
+ */
+static unsigned int br_nf_forward(unsigned int hook, struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *))
+{
+	struct sk_buff *skb = *pskb;
+
+	// don't mess with non-ip frames, also don't mess with the ip-packets
+	// when br_nf_local_out_finish explicitly says so.
+	if (skb->protocol != __constant_htons(ETH_P_IP) || skb->physindev == NULL)
+		return NF_ACCEPT;
+
+	skb->physoutdev = skb->dev;
+	NF_HOOK(PF_INET, NF_IP_FORWARD, skb, bridge_parent(skb->physindev),
+			bridge_parent(skb->dev), br_nf_forward_finish);
+
+	return NF_STOLEN;
+}
+
+
+/* PF_BRIDGE/LOCAL_OUT ***********************************************/
+static int br_nf_local_out_finish_forward(struct sk_buff *skb)
+{
+	struct net_device *dev;
+
+	dev = skb->physindev;
+	// tell br_nf_forward to stay away
+	skb->physindev = NULL;
+	NF_HOOK(PF_BRIDGE, NF_BR_FORWARD, skb, dev, skb->dev,
+		br_forward_finish);
+
+	return 0;
+}
+
+static int br_nf_local_out_finish(struct sk_buff *skb)
+{
+	NF_HOOK_THRESH(PF_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
+			br_forward_finish, INT_MIN + 1);
+
+	return 0;
+}
+
+
+/* This hook sees both locally originated IP packets and forwarded
+ * IP packets (in both cases the destination device is a bridge
+ * device).  For the sake of interface transparency (i.e. properly
+ * overloading the '-o' option), we steal packets destined to
+ * a bridge device away from the IPv4 FORWARD and OUTPUT hooks,
+ * and reinject them later, when we have determined the real
+ * output device.  This reinjecting happens here.
+ *
+ * If skb->physindev is NULL, the bridge-nf code never touched
+ * this packet before, and so the packet was locally originated.
+ * We call the IPv4 LOCAL_OUT hook.
+ *
+ * If skb->physindev isn't NULL, there are two cases:
+ * 1. The packet was IP routed.
+ * 2. The packet was cross-bridge DNAT'ed (see the comment near
+ *    PF_BRIDGE/PRE_ROUTING).
+ * In both cases, we call the IPv4 FORWARD hook.  In case 1,
+ * if the packet originally came from a bridge device, and in
+ * case 2, skb->physindev will have a bridge device as parent,
+ * so we use that parent device as indev.  Otherwise, we just
+ * use physindev.
+ *
+ * If skb->physoutdev == NULL the bridge code never touched the
+ * packet or the packet was routed in br_nf_pre_routing_finish().
+ * We give the packet to the bridge NF_BR_LOCAL_OUT hook.
+ * If not, the packet is actually a bridged one so we give it to
+ * the NF_BR_FORWARD hook.
+ */
+
+static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, int (*_okfn)(struct sk_buff *))
+{
+	int hookno, prio;
+	int (*okfn)(struct sk_buff *skb);
+	struct net_device *realindev;
+	struct sk_buff *skb = *pskb;
+
+	if (skb->protocol != __constant_htons(ETH_P_IP))
+		return NF_ACCEPT;
+
+	/* Sometimes we get packets with NULL ->dst here (for example,
+	 * running a dhcp client daemon triggers this).
+	 */
+	if (skb->dst == NULL)
+		return NF_ACCEPT;
+
+	// bridged, take forward
+	// (see big note in front of br_nf_pre_routing_finish)
+	if (skb->physoutdev == &__fake_net_device) {
+		okfn = br_nf_local_out_finish_forward;
+	} else if (skb->physoutdev == NULL) {
+		// non-bridged: routed or locally generated traffic, take local_out
+		// (see big note in front of br_nf_pre_routing_finish)
+		okfn = br_nf_local_out_finish;
+	} else {
+		printk("ARGH: bridge_or_routed hack doesn't work\n");
+		okfn = br_nf_local_out_finish;
+	}
+
+	skb->physoutdev = skb->dev;
+
+	hookno = NF_IP_LOCAL_OUT;
+	prio = NF_IP_PRI_BRIDGE_SABOTAGE;
+	if ((realindev = skb->physindev) != NULL) {
+		hookno = NF_IP_FORWARD;
+		// there is an iptables mangle table FORWARD chain with
+		// priority -150. This chain should see the physical out-dev.
+		prio = NF_IP_PRI_BRIDGE_SABOTAGE_FORWARD;
+		if (has_bridge_parent(realindev))
+			realindev = bridge_parent(realindev);
+	}
+
+	NF_HOOK_THRESH(PF_INET, hookno, skb, realindev,
+			bridge_parent(skb->dev), okfn, prio + 1);
+
+	return NF_STOLEN;
+}
+
+
+/* PF_BRIDGE/POST_ROUTING ********************************************/
+static int br_nf_post_routing_finish(struct sk_buff *skb)
+{
+	__maybe_fixup_src_address(skb);
+	NF_HOOK_THRESH(PF_BRIDGE, NF_BR_POST_ROUTING, skb, NULL,
+			bridge_parent(skb->dev), br_dev_queue_push_xmit, 1);
+
+	return 0;
+}
+
+static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *))
+{
+	struct sk_buff *skb = *pskb;
+
+	/* Be very paranoid.  */
+	if (skb->mac.raw < skb->head || skb->mac.raw + ETH_HLEN > skb->data) {
+		printk(KERN_CRIT "Argh!! Fuck me harder with a chainsaw. ");
+		if (skb->dev != NULL) {
+			printk("[%s]", skb->dev->name);
+			if (has_bridge_parent(skb->dev))
+				printk("[%s]", bridge_parent(skb->dev)->name);
+		}
+		printk("\n");
+		return NF_ACCEPT;
+	}
+
+	if (skb->protocol != __constant_htons(ETH_P_IP))
+		return NF_ACCEPT;
+
+	/* Sometimes we get packets with NULL ->dst here (for example,
+	 * running a dhcp client daemon triggers this).
+	 */
+	if (skb->dst == NULL)
+		return NF_ACCEPT;
+
+	store_orig_srcaddr(skb);
+	NF_HOOK(PF_INET, NF_IP_POST_ROUTING, skb, NULL,
+		bridge_parent(skb->dev), br_nf_post_routing_finish);
+
+	return NF_STOLEN;
+}
+
+
+/* IPv4/SABOTAGE *****************************************************/
+/* Don't hand locally destined packets to PF_INET/PRE_ROUTING
+ * for the second time.  */
+static unsigned int ipv4_sabotage_in(unsigned int hook, struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *))
+{
+	if (in->hard_start_xmit == br_dev_xmit &&
+	    okfn != br_nf_pre_routing_finish) {
+		okfn(*pskb);
+		return NF_STOLEN;
+	}
+
+	return NF_ACCEPT;
+}
+
+/* Postpone execution of PF_INET/FORWARD, PF_INET/LOCAL_OUT
+ * and PF_INET/POST_ROUTING until we have done the forwarding
+ * decision in the bridge code and have determined skb->physoutdev.
+ */
+static unsigned int ipv4_sabotage_out(unsigned int hook, struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *))
+{
+	if (out->hard_start_xmit == br_dev_xmit &&
+	    okfn != br_nf_forward_finish &&
+	    okfn != br_nf_local_out_finish &&
+	    okfn != br_nf_post_routing_finish) {
+		struct sk_buff *skb = *pskb;
+
+		if (hook == NF_IP_FORWARD && skb->physindev == NULL)
+			skb->physindev = (struct net_device *)in;
+		okfn(skb);
+		return NF_STOLEN;
+	}
+
+	return NF_ACCEPT;
+}
+
+
+static struct nf_hook_ops br_nf_ops[] = {
+	{ { NULL, NULL }, br_nf_pre_routing, PF_BRIDGE, NF_BR_PRE_ROUTING, 0 },
+	{ { NULL, NULL }, br_nf_local_in, PF_BRIDGE, NF_BR_LOCAL_IN, 0 },
+	{ { NULL, NULL }, br_nf_forward, PF_BRIDGE, NF_BR_FORWARD, 0 },
+	// we need INT_MIN, so innocent NF_BR_LOCAL_OUT functions don't
+	// get bridged traffic as input
+	{ { NULL, NULL }, br_nf_local_out, PF_BRIDGE, NF_BR_LOCAL_OUT, INT_MIN },
+	{ { NULL, NULL }, br_nf_post_routing, PF_BRIDGE, NF_BR_POST_ROUTING, 0 },
+
+	{ { NULL, NULL }, ipv4_sabotage_in, PF_INET, NF_IP_PRE_ROUTING, NF_IP_PRI_FIRST },
+
+	{ { NULL, NULL }, ipv4_sabotage_out, PF_INET, NF_IP_FORWARD, NF_IP_PRI_BRIDGE_SABOTAGE_FORWARD },
+	{ { NULL, NULL }, ipv4_sabotage_out, PF_INET, NF_IP_LOCAL_OUT, NF_IP_PRI_BRIDGE_SABOTAGE },
+	{ { NULL, NULL }, ipv4_sabotage_out, PF_INET, NF_IP_POST_ROUTING, NF_IP_PRI_FIRST },
+};
+
+#define NUMHOOKS (sizeof(br_nf_ops)/sizeof(br_nf_ops[0]))
+
+
+int br_netfilter_init(void)
+{
+	int i;
+
+#ifndef WE_REALLY_INSIST_ON_NOT_HAVING_NAT_SUPPORT
+	if (sizeof(struct tcp_skb_cb) + 4 >= sizeof(((struct sk_buff *)NULL)->cb)) {
+		extern int __too_little_space_in_control_buffer(void);
+		__too_little_space_in_control_buffer();
+	}
+#endif
+
+	for (i=0;i<NUMHOOKS;i++) {
+		int ret;
+
+		if ((ret = nf_register_hook(&br_nf_ops[i])) >= 0)
+			continue;
+
+		while (i--)
+			nf_unregister_hook(&br_nf_ops[i]);
+
+		return ret;
+	}
+
+	printk(KERN_NOTICE "Bridge firewalling registered\n");
+
+	return 0;
+}
+
+void br_netfilter_fini(void)
+{
+	int i;
+
+	for (i=NUMHOOKS-1;i>=0;i--)
+		nf_unregister_hook(&br_nf_ops[i]);
+}