-
Notifications
You must be signed in to change notification settings - Fork 115
/
Copy pathroute.c
3036 lines (2623 loc) · 73.9 KB
/
route.c
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
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* ROUTE - implementation of the IP router.
*
* Version: $Id: route.c,v 1.103 2002/01/12 07:44:09 davem Exp $
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Alan Cox, <gw4pts@gw4pts.ampr.org>
* Linus Torvalds, <Linus.Torvalds@helsinki.fi>
* Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* Fixes:
* Alan Cox : Verify area fixes.
* Alan Cox : cli() protects routing changes
* Rui Oliveira : ICMP routing table updates
* (rco@di.uminho.pt) Routing table insertion and update
* Linus Torvalds : Rewrote bits to be sensible
* Alan Cox : Added BSD route gw semantics
* Alan Cox : Super /proc >4K
* Alan Cox : MTU in route table
* Alan Cox : MSS actually. Also added the window
* clamper.
* Sam Lantinga : Fixed route matching in rt_del()
* Alan Cox : Routing cache support.
* Alan Cox : Removed compatibility cruft.
* Alan Cox : RTF_REJECT support.
* Alan Cox : TCP irtt support.
* Jonathan Naylor : Added Metric support.
* Miquel van Smoorenburg : BSD API fixes.
* Miquel van Smoorenburg : Metrics.
* Alan Cox : Use __u32 properly
* Alan Cox : Aligned routing errors more closely with BSD
* our system is still very different.
* Alan Cox : Faster /proc handling
* Alexey Kuznetsov : Massive rework to support tree based routing,
* routing caches and better behaviour.
*
* Olaf Erb : irtt wasn't being copied right.
* Bjorn Ekwall : Kerneld route support.
* Alan Cox : Multicast fixed (I hope)
* Pavel Krauz : Limited broadcast fixed
* Mike McLagan : Routing by source
* Alexey Kuznetsov : End of old history. Split to fib.c and
* route.c and rewritten from scratch.
* Andi Kleen : Load-limit warning messages.
* Vitaly E. Lavrov : Transparent proxy revived after year coma.
* Vitaly E. Lavrov : Race condition in ip_route_input_slow.
* Tobias Ringstrom : Uninitialized res.type in ip_route_output_slow.
* Vladimir V. Ivanov : IP rule info (flowid) is really useful.
* Marc Boucher : routing by fwmark
* Robert Olsson : Added rt_cache statistics
* Arnaldo C. Melo : Convert proc stuff to seq_file
* Eric Dumazet : hashed spinlocks and rt_check_expire() fixes.
* Ilia Sotnikov : Ignore TOS on PMTUD and Redirect
* Ilia Sotnikov : Removed TOS from hash calculations
*
* 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.
*/
#include <linux/module.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/bootmem.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#include <linux/init.h>
#include <linux/skbuff.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/pkt_sched.h>
#include <linux/mroute.h>
#include <linux/netfilter_ipv4.h>
#include <linux/random.h>
#include <linux/jhash.h>
#include <linux/rcupdate.h>
#include <linux/times.h>
#include <net/protocol.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/inetpeer.h>
#include <net/sock.h>
#include <net/ip_fib.h>
#include <net/arp.h>
#include <net/tcp.h>
#include <net/icmp.h>
#include <net/xfrm.h>
#include <net/netevent.h>
#include <net/rtnetlink.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#define RT_FL_TOS(oldflp) \
((u32)(oldflp->fl4_tos & (IPTOS_RT_MASK | RTO_ONLINK)))
#define IP_MAX_MTU 0xFFF0
#define RT_GC_TIMEOUT (300*HZ)
static int ip_rt_min_delay = 2 * HZ;
static int ip_rt_max_delay = 10 * HZ;
static int ip_rt_max_size;
static int ip_rt_gc_timeout = RT_GC_TIMEOUT;
static int ip_rt_gc_interval = 60 * HZ;
static int ip_rt_gc_min_interval = HZ / 2;
static int ip_rt_redirect_number = 9;
static int ip_rt_redirect_load = HZ / 50;
static int ip_rt_redirect_silence = ((HZ / 50) << (9 + 1));
static int ip_rt_error_cost = HZ;
static int ip_rt_error_burst = 5 * HZ;
static int ip_rt_gc_elasticity = 8;
static int ip_rt_mtu_expires = 10 * 60 * HZ;
static int ip_rt_min_pmtu = 512 + 20 + 20;
static int ip_rt_min_advmss = 256;
static int ip_rt_secret_interval = 10 * 60 * HZ;
static unsigned long rt_deadline;
#define RTprint(a...) printk(KERN_DEBUG a)
static struct timer_list rt_flush_timer;
static struct timer_list rt_periodic_timer;
static struct timer_list rt_secret_timer;
/*
* Interface to generic destination cache.
*/
static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie);
static void ipv4_dst_destroy(struct dst_entry *dst);
static void ipv4_dst_ifdown(struct dst_entry *dst,
struct net_device *dev, int how);
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
static void ipv4_link_failure(struct sk_buff *skb);
static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
static int rt_garbage_collect(void);
static struct dst_ops ipv4_dst_ops = {
.family = AF_INET,
.protocol = __constant_htons(ETH_P_IP),
.gc = rt_garbage_collect,
.check = ipv4_dst_check,
.destroy = ipv4_dst_destroy,
.ifdown = ipv4_dst_ifdown,
.negative_advice = ipv4_negative_advice,
.link_failure = ipv4_link_failure,
.update_pmtu = ip_rt_update_pmtu,
.entry_size = sizeof(struct rtable),
};
#define ECN_OR_COST(class) TC_PRIO_##class
const __u8 ip_tos2prio[16] = {
TC_PRIO_BESTEFFORT,
ECN_OR_COST(FILLER),
TC_PRIO_BESTEFFORT,
ECN_OR_COST(BESTEFFORT),
TC_PRIO_BULK,
ECN_OR_COST(BULK),
TC_PRIO_BULK,
ECN_OR_COST(BULK),
TC_PRIO_INTERACTIVE,
ECN_OR_COST(INTERACTIVE),
TC_PRIO_INTERACTIVE,
ECN_OR_COST(INTERACTIVE),
TC_PRIO_INTERACTIVE_BULK,
ECN_OR_COST(INTERACTIVE_BULK),
TC_PRIO_INTERACTIVE_BULK,
ECN_OR_COST(INTERACTIVE_BULK)
};
/*
* Route cache.
*/
/* The locking scheme is rather straight forward:
*
* 1) Read-Copy Update protects the buckets of the central route hash.
* 2) Only writers remove entries, and they hold the lock
* as they look at rtable reference counts.
* 3) Only readers acquire references to rtable entries,
* they do so with atomic increments and with the
* lock held.
*/
struct rt_hash_bucket {
struct rtable *chain;
};
#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \
defined(CONFIG_PROVE_LOCKING)
/*
* Instead of using one spinlock for each rt_hash_bucket, we use a table of spinlocks
* The size of this table is a power of two and depends on the number of CPUS.
* (on lockdep we have a quite big spinlock_t, so keep the size down there)
*/
#ifdef CONFIG_LOCKDEP
# define RT_HASH_LOCK_SZ 256
#else
# if NR_CPUS >= 32
# define RT_HASH_LOCK_SZ 4096
# elif NR_CPUS >= 16
# define RT_HASH_LOCK_SZ 2048
# elif NR_CPUS >= 8
# define RT_HASH_LOCK_SZ 1024
# elif NR_CPUS >= 4
# define RT_HASH_LOCK_SZ 512
# else
# define RT_HASH_LOCK_SZ 256
# endif
#endif
static spinlock_t *rt_hash_locks;
# define rt_hash_lock_addr(slot) &rt_hash_locks[(slot) & (RT_HASH_LOCK_SZ - 1)]
# define rt_hash_lock_init() { \
int i; \
rt_hash_locks = kmalloc(sizeof(spinlock_t) * RT_HASH_LOCK_SZ, GFP_KERNEL); \
if (!rt_hash_locks) panic("IP: failed to allocate rt_hash_locks\n"); \
for (i = 0; i < RT_HASH_LOCK_SZ; i++) \
spin_lock_init(&rt_hash_locks[i]); \
}
#else
# define rt_hash_lock_addr(slot) NULL
# define rt_hash_lock_init()
#endif
static struct rt_hash_bucket *rt_hash_table;
static unsigned rt_hash_mask;
static int rt_hash_log;
static unsigned int rt_hash_rnd;
static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
#define RT_CACHE_STAT_INC(field) \
(__raw_get_cpu_var(rt_cache_stat).field++)
static int rt_intern_hash(unsigned hash, struct rtable *rth,
struct rtable **res);
static unsigned int rt_hash_code(u32 daddr, u32 saddr)
{
return (jhash_2words(daddr, saddr, rt_hash_rnd)
& rt_hash_mask);
}
#define rt_hash(daddr, saddr, idx) \
rt_hash_code((__force u32)(__be32)(daddr),\
(__force u32)(__be32)(saddr) ^ ((idx) << 5))
#ifdef CONFIG_PROC_FS
struct rt_cache_iter_state {
int bucket;
};
static struct rtable *rt_cache_get_first(struct seq_file *seq)
{
struct rtable *r = NULL;
struct rt_cache_iter_state *st = seq->private;
for (st->bucket = rt_hash_mask; st->bucket >= 0; --st->bucket) {
rcu_read_lock_bh();
r = rt_hash_table[st->bucket].chain;
if (r)
break;
rcu_read_unlock_bh();
}
return r;
}
static struct rtable *rt_cache_get_next(struct seq_file *seq, struct rtable *r)
{
struct rt_cache_iter_state *st = rcu_dereference(seq->private);
r = r->u.dst.rt_next;
while (!r) {
rcu_read_unlock_bh();
if (--st->bucket < 0)
break;
rcu_read_lock_bh();
r = rt_hash_table[st->bucket].chain;
}
return r;
}
static struct rtable *rt_cache_get_idx(struct seq_file *seq, loff_t pos)
{
struct rtable *r = rt_cache_get_first(seq);
if (r)
while (pos && (r = rt_cache_get_next(seq, r)))
--pos;
return pos ? NULL : r;
}
static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
{
return *pos ? rt_cache_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
}
static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct rtable *r = NULL;
if (v == SEQ_START_TOKEN)
r = rt_cache_get_first(seq);
else
r = rt_cache_get_next(seq, v);
++*pos;
return r;
}
static void rt_cache_seq_stop(struct seq_file *seq, void *v)
{
if (v && v != SEQ_START_TOKEN)
rcu_read_unlock_bh();
}
static int rt_cache_seq_show(struct seq_file *seq, void *v)
{
if (v == SEQ_START_TOKEN)
seq_printf(seq, "%-127s\n",
"Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\t"
"Metric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\t"
"HHUptod\tSpecDst");
else {
struct rtable *r = v;
char temp[256];
sprintf(temp, "%s\t%08lX\t%08lX\t%8X\t%d\t%u\t%d\t"
"%08lX\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X",
r->u.dst.dev ? r->u.dst.dev->name : "*",
(unsigned long)r->rt_dst, (unsigned long)r->rt_gateway,
r->rt_flags, atomic_read(&r->u.dst.__refcnt),
r->u.dst.__use, 0, (unsigned long)r->rt_src,
(dst_metric(&r->u.dst, RTAX_ADVMSS) ?
(int)dst_metric(&r->u.dst, RTAX_ADVMSS) + 40 : 0),
dst_metric(&r->u.dst, RTAX_WINDOW),
(int)((dst_metric(&r->u.dst, RTAX_RTT) >> 3) +
dst_metric(&r->u.dst, RTAX_RTTVAR)),
r->fl.fl4_tos,
r->u.dst.hh ? atomic_read(&r->u.dst.hh->hh_refcnt) : -1,
r->u.dst.hh ? (r->u.dst.hh->hh_output ==
dev_queue_xmit) : 0,
r->rt_spec_dst);
seq_printf(seq, "%-127s\n", temp);
}
return 0;
}
static const struct seq_operations rt_cache_seq_ops = {
.start = rt_cache_seq_start,
.next = rt_cache_seq_next,
.stop = rt_cache_seq_stop,
.show = rt_cache_seq_show,
};
static int rt_cache_seq_open(struct inode *inode, struct file *file)
{
struct seq_file *seq;
int rc = -ENOMEM;
struct rt_cache_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL);
if (!s)
goto out;
rc = seq_open(file, &rt_cache_seq_ops);
if (rc)
goto out_kfree;
seq = file->private_data;
seq->private = s;
memset(s, 0, sizeof(*s));
out:
return rc;
out_kfree:
kfree(s);
goto out;
}
static const struct file_operations rt_cache_seq_fops = {
.owner = THIS_MODULE,
.open = rt_cache_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_private,
};
static void *rt_cpu_seq_start(struct seq_file *seq, loff_t *pos)
{
int cpu;
if (*pos == 0)
return SEQ_START_TOKEN;
for (cpu = *pos-1; cpu < NR_CPUS; ++cpu) {
if (!cpu_possible(cpu))
continue;
*pos = cpu+1;
return &per_cpu(rt_cache_stat, cpu);
}
return NULL;
}
static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
int cpu;
for (cpu = *pos; cpu < NR_CPUS; ++cpu) {
if (!cpu_possible(cpu))
continue;
*pos = cpu+1;
return &per_cpu(rt_cache_stat, cpu);
}
return NULL;
}
static void rt_cpu_seq_stop(struct seq_file *seq, void *v)
{
}
static int rt_cpu_seq_show(struct seq_file *seq, void *v)
{
struct rt_cache_stat *st = v;
if (v == SEQ_START_TOKEN) {
seq_printf(seq, "entries in_hit in_slow_tot in_slow_mc in_no_route in_brd in_martian_dst in_martian_src out_hit out_slow_tot out_slow_mc gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n");
return 0;
}
seq_printf(seq,"%08x %08x %08x %08x %08x %08x %08x %08x "
" %08x %08x %08x %08x %08x %08x %08x %08x %08x \n",
atomic_read(&ipv4_dst_ops.entries),
st->in_hit,
st->in_slow_tot,
st->in_slow_mc,
st->in_no_route,
st->in_brd,
st->in_martian_dst,
st->in_martian_src,
st->out_hit,
st->out_slow_tot,
st->out_slow_mc,
st->gc_total,
st->gc_ignored,
st->gc_goal_miss,
st->gc_dst_overflow,
st->in_hlist_search,
st->out_hlist_search
);
return 0;
}
static const struct seq_operations rt_cpu_seq_ops = {
.start = rt_cpu_seq_start,
.next = rt_cpu_seq_next,
.stop = rt_cpu_seq_stop,
.show = rt_cpu_seq_show,
};
static int rt_cpu_seq_open(struct inode *inode, struct file *file)
{
return seq_open(file, &rt_cpu_seq_ops);
}
static const struct file_operations rt_cpu_seq_fops = {
.owner = THIS_MODULE,
.open = rt_cpu_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
#endif /* CONFIG_PROC_FS */
static __inline__ void rt_free(struct rtable *rt)
{
call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free);
}
static __inline__ void rt_drop(struct rtable *rt)
{
ip_rt_put(rt);
call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free);
}
static __inline__ int rt_fast_clean(struct rtable *rth)
{
/* Kill broadcast/multicast entries very aggresively, if they
collide in hash table with more useful entries */
return (rth->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) &&
rth->fl.iif && rth->u.dst.rt_next;
}
static __inline__ int rt_valuable(struct rtable *rth)
{
return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) ||
rth->u.dst.expires;
}
static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2)
{
unsigned long age;
int ret = 0;
if (atomic_read(&rth->u.dst.__refcnt))
goto out;
ret = 1;
if (rth->u.dst.expires &&
time_after_eq(jiffies, rth->u.dst.expires))
goto out;
age = jiffies - rth->u.dst.lastuse;
ret = 0;
if ((age <= tmo1 && !rt_fast_clean(rth)) ||
(age <= tmo2 && rt_valuable(rth)))
goto out;
ret = 1;
out: return ret;
}
/* Bits of score are:
* 31: very valuable
* 30: not quite useless
* 29..0: usage counter
*/
static inline u32 rt_score(struct rtable *rt)
{
u32 score = jiffies - rt->u.dst.lastuse;
score = ~score & ~(3<<30);
if (rt_valuable(rt))
score |= (1<<31);
if (!rt->fl.iif ||
!(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL)))
score |= (1<<30);
return score;
}
static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
{
return ((__force u32)((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) |
(fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr)) |
(fl1->mark ^ fl2->mark) |
(*(u16 *)&fl1->nl_u.ip4_u.tos ^
*(u16 *)&fl2->nl_u.ip4_u.tos) |
(fl1->oif ^ fl2->oif) |
(fl1->iif ^ fl2->iif)) == 0;
}
/* This runs via a timer and thus is always in BH context. */
static void rt_check_expire(unsigned long dummy)
{
static unsigned int rover;
unsigned int i = rover, goal;
struct rtable *rth, **rthp;
unsigned long now = jiffies;
u64 mult;
mult = ((u64)ip_rt_gc_interval) << rt_hash_log;
if (ip_rt_gc_timeout > 1)
do_div(mult, ip_rt_gc_timeout);
goal = (unsigned int)mult;
if (goal > rt_hash_mask) goal = rt_hash_mask + 1;
for (; goal > 0; goal--) {
unsigned long tmo = ip_rt_gc_timeout;
i = (i + 1) & rt_hash_mask;
rthp = &rt_hash_table[i].chain;
if (*rthp == 0)
continue;
spin_lock(rt_hash_lock_addr(i));
while ((rth = *rthp) != NULL) {
if (rth->u.dst.expires) {
/* Entry is expired even if it is in use */
if (time_before_eq(now, rth->u.dst.expires)) {
tmo >>= 1;
rthp = &rth->u.dst.rt_next;
continue;
}
} else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) {
tmo >>= 1;
rthp = &rth->u.dst.rt_next;
continue;
}
/* Cleanup aged off entries. */
*rthp = rth->u.dst.rt_next;
rt_free(rth);
}
spin_unlock(rt_hash_lock_addr(i));
/* Fallback loop breaker. */
if (time_after(jiffies, now))
break;
}
rover = i;
mod_timer(&rt_periodic_timer, jiffies + ip_rt_gc_interval);
}
/* This can run from both BH and non-BH contexts, the latter
* in the case of a forced flush event.
*/
static void rt_run_flush(unsigned long dummy)
{
int i;
struct rtable *rth, *next;
rt_deadline = 0;
get_random_bytes(&rt_hash_rnd, 4);
for (i = rt_hash_mask; i >= 0; i--) {
spin_lock_bh(rt_hash_lock_addr(i));
rth = rt_hash_table[i].chain;
if (rth)
rt_hash_table[i].chain = NULL;
spin_unlock_bh(rt_hash_lock_addr(i));
for (; rth; rth = next) {
next = rth->u.dst.rt_next;
rt_free(rth);
}
}
}
static DEFINE_SPINLOCK(rt_flush_lock);
void rt_cache_flush(int delay)
{
unsigned long now = jiffies;
int user_mode = !in_softirq();
if (delay < 0)
delay = ip_rt_min_delay;
spin_lock_bh(&rt_flush_lock);
if (del_timer(&rt_flush_timer) && delay > 0 && rt_deadline) {
long tmo = (long)(rt_deadline - now);
/* If flush timer is already running
and flush request is not immediate (delay > 0):
if deadline is not achieved, prolongate timer to "delay",
otherwise fire it at deadline time.
*/
if (user_mode && tmo < ip_rt_max_delay-ip_rt_min_delay)
tmo = 0;
if (delay > tmo)
delay = tmo;
}
if (delay <= 0) {
spin_unlock_bh(&rt_flush_lock);
rt_run_flush(0);
return;
}
if (rt_deadline == 0)
rt_deadline = now + ip_rt_max_delay;
mod_timer(&rt_flush_timer, now+delay);
spin_unlock_bh(&rt_flush_lock);
}
static void rt_secret_rebuild(unsigned long dummy)
{
unsigned long now = jiffies;
rt_cache_flush(0);
mod_timer(&rt_secret_timer, now + ip_rt_secret_interval);
}
/*
Short description of GC goals.
We want to build algorithm, which will keep routing cache
at some equilibrium point, when number of aged off entries
is kept approximately equal to newly generated ones.
Current expiration strength is variable "expire".
We try to adjust it dynamically, so that if networking
is idle expires is large enough to keep enough of warm entries,
and when load increases it reduces to limit cache size.
*/
static int rt_garbage_collect(void)
{
static unsigned long expire = RT_GC_TIMEOUT;
static unsigned long last_gc;
static int rover;
static int equilibrium;
struct rtable *rth, **rthp;
unsigned long now = jiffies;
int goal;
/*
* Garbage collection is pretty expensive,
* do not make it too frequently.
*/
RT_CACHE_STAT_INC(gc_total);
if (now - last_gc < ip_rt_gc_min_interval &&
atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size) {
RT_CACHE_STAT_INC(gc_ignored);
goto out;
}
/* Calculate number of entries, which we want to expire now. */
goal = atomic_read(&ipv4_dst_ops.entries) -
(ip_rt_gc_elasticity << rt_hash_log);
if (goal <= 0) {
if (equilibrium < ipv4_dst_ops.gc_thresh)
equilibrium = ipv4_dst_ops.gc_thresh;
goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium;
if (goal > 0) {
equilibrium += min_t(unsigned int, goal / 2, rt_hash_mask + 1);
goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium;
}
} else {
/* We are in dangerous area. Try to reduce cache really
* aggressively.
*/
goal = max_t(unsigned int, goal / 2, rt_hash_mask + 1);
equilibrium = atomic_read(&ipv4_dst_ops.entries) - goal;
}
if (now - last_gc >= ip_rt_gc_min_interval)
last_gc = now;
if (goal <= 0) {
equilibrium += goal;
goto work_done;
}
do {
int i, k;
for (i = rt_hash_mask, k = rover; i >= 0; i--) {
unsigned long tmo = expire;
k = (k + 1) & rt_hash_mask;
rthp = &rt_hash_table[k].chain;
spin_lock_bh(rt_hash_lock_addr(k));
while ((rth = *rthp) != NULL) {
if (!rt_may_expire(rth, tmo, expire)) {
tmo >>= 1;
rthp = &rth->u.dst.rt_next;
continue;
}
*rthp = rth->u.dst.rt_next;
rt_free(rth);
goal--;
}
spin_unlock_bh(rt_hash_lock_addr(k));
if (goal <= 0)
break;
}
rover = k;
if (goal <= 0)
goto work_done;
/* Goal is not achieved. We stop process if:
- if expire reduced to zero. Otherwise, expire is halfed.
- if table is not full.
- if we are called from interrupt.
- jiffies check is just fallback/debug loop breaker.
We will not spin here for long time in any case.
*/
RT_CACHE_STAT_INC(gc_goal_miss);
if (expire == 0)
break;
expire >>= 1;
#if RT_CACHE_DEBUG >= 2
printk(KERN_DEBUG "expire>> %u %d %d %d\n", expire,
atomic_read(&ipv4_dst_ops.entries), goal, i);
#endif
if (atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size)
goto out;
} while (!in_softirq() && time_before_eq(jiffies, now));
if (atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size)
goto out;
if (net_ratelimit())
printk(KERN_WARNING "dst cache overflow\n");
RT_CACHE_STAT_INC(gc_dst_overflow);
return 1;
work_done:
expire += ip_rt_gc_min_interval;
if (expire > ip_rt_gc_timeout ||
atomic_read(&ipv4_dst_ops.entries) < ipv4_dst_ops.gc_thresh)
expire = ip_rt_gc_timeout;
#if RT_CACHE_DEBUG >= 2
printk(KERN_DEBUG "expire++ %u %d %d %d\n", expire,
atomic_read(&ipv4_dst_ops.entries), goal, rover);
#endif
out: return 0;
}
static int rt_intern_hash(unsigned hash, struct rtable *rt, struct rtable **rp)
{
struct rtable *rth, **rthp;
unsigned long now;
struct rtable *cand, **candp;
u32 min_score;
int chain_length;
int attempts = !in_softirq();
restart:
chain_length = 0;
min_score = ~(u32)0;
cand = NULL;
candp = NULL;
now = jiffies;
rthp = &rt_hash_table[hash].chain;
spin_lock_bh(rt_hash_lock_addr(hash));
while ((rth = *rthp) != NULL) {
if (compare_keys(&rth->fl, &rt->fl)) {
/* Put it first */
*rthp = rth->u.dst.rt_next;
/*
* Since lookup is lockfree, the deletion
* must be visible to another weakly ordered CPU before
* the insertion at the start of the hash chain.
*/
rcu_assign_pointer(rth->u.dst.rt_next,
rt_hash_table[hash].chain);
/*
* Since lookup is lockfree, the update writes
* must be ordered for consistency on SMP.
*/
rcu_assign_pointer(rt_hash_table[hash].chain, rth);
rth->u.dst.__use++;
dst_hold(&rth->u.dst);
rth->u.dst.lastuse = now;
spin_unlock_bh(rt_hash_lock_addr(hash));
rt_drop(rt);
*rp = rth;
return 0;
}
if (!atomic_read(&rth->u.dst.__refcnt)) {
u32 score = rt_score(rth);
if (score <= min_score) {
cand = rth;
candp = rthp;
min_score = score;
}
}
chain_length++;
rthp = &rth->u.dst.rt_next;
}
if (cand) {
/* ip_rt_gc_elasticity used to be average length of chain
* length, when exceeded gc becomes really aggressive.
*
* The second limit is less certain. At the moment it allows
* only 2 entries per bucket. We will see.
*/
if (chain_length > ip_rt_gc_elasticity) {
*candp = cand->u.dst.rt_next;
rt_free(cand);
}
}
/* Try to bind route to arp only if it is output
route or unicast forwarding path.
*/
if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) {
int err = arp_bind_neighbour(&rt->u.dst);
if (err) {
spin_unlock_bh(rt_hash_lock_addr(hash));
if (err != -ENOBUFS) {
rt_drop(rt);
return err;
}
/* Neighbour tables are full and nothing
can be released. Try to shrink route cache,
it is most likely it holds some neighbour records.
*/
if (attempts-- > 0) {
int saved_elasticity = ip_rt_gc_elasticity;
int saved_int = ip_rt_gc_min_interval;
ip_rt_gc_elasticity = 1;
ip_rt_gc_min_interval = 0;
rt_garbage_collect();
ip_rt_gc_min_interval = saved_int;
ip_rt_gc_elasticity = saved_elasticity;
goto restart;
}
if (net_ratelimit())
printk(KERN_WARNING "Neighbour table overflow.\n");
rt_drop(rt);
return -ENOBUFS;
}
}
rt->u.dst.rt_next = rt_hash_table[hash].chain;
#if RT_CACHE_DEBUG >= 2
if (rt->u.dst.rt_next) {
struct rtable *trt;
printk(KERN_DEBUG "rt_cache @%02x: %u.%u.%u.%u", hash,
NIPQUAD(rt->rt_dst));
for (trt = rt->u.dst.rt_next; trt; trt = trt->u.dst.rt_next)
printk(" . %u.%u.%u.%u", NIPQUAD(trt->rt_dst));
printk("\n");
}
#endif
rt_hash_table[hash].chain = rt;
spin_unlock_bh(rt_hash_lock_addr(hash));
*rp = rt;
return 0;
}
void rt_bind_peer(struct rtable *rt, int create)
{
static DEFINE_SPINLOCK(rt_peer_lock);
struct inet_peer *peer;
peer = inet_getpeer(rt->rt_dst, create);
spin_lock_bh(&rt_peer_lock);
if (rt->peer == NULL) {
rt->peer = peer;
peer = NULL;
}
spin_unlock_bh(&rt_peer_lock);
if (peer)
inet_putpeer(peer);
}
/*
* Peer allocation may fail only in serious out-of-memory conditions. However
* we still can generate some output.
* Random ID selection looks a bit dangerous because we have no chances to
* select ID being unique in a reasonable period of time.
* But broken packet identifier may be better than no packet at all.
*/
static void ip_select_fb_ident(struct iphdr *iph)
{
static DEFINE_SPINLOCK(ip_fb_id_lock);
static u32 ip_fallback_id;
u32 salt;
spin_lock_bh(&ip_fb_id_lock);
salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr);
iph->id = htons(salt & 0xFFFF);
ip_fallback_id = salt;
spin_unlock_bh(&ip_fb_id_lock);
}
void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
{
struct rtable *rt = (struct rtable *) dst;