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
|
/*
* net/sched/cls_tcindex.c Packet classifier for skb->tc_index
*
* Written 1998,1999 by Werner Almesberger, EPFL ICA
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <net/act_api.h>
#include <net/netlink.h>
#include <net/pkt_cls.h>
#include <net/sch_generic.h>
/*
* Passing parameters to the root seems to be done more awkwardly than really
* necessary. At least, u32 doesn't seem to use such dirty hacks. To be
* verified. FIXME.
*/
#define PERFECT_HASH_THRESHOLD 64 /* use perfect hash if not bigger */
#define DEFAULT_HASH_SIZE 64 /* optimized for diffserv */
struct tcindex_filter_result {
struct tcf_exts exts;
struct tcf_result res;
struct rcu_work rwork;
};
struct tcindex_filter {
u16 key;
struct tcindex_filter_result result;
struct tcindex_filter __rcu *next;
struct rcu_work rwork;
};
struct tcindex_data {
struct tcindex_filter_result *perfect; /* perfect hash; NULL if none */
struct tcindex_filter __rcu **h; /* imperfect hash; */
struct tcf_proto *tp;
u16 mask; /* AND key with mask */
u32 shift; /* shift ANDed key to the right */
u32 hash; /* hash table size; 0 if undefined */
u32 alloc_hash; /* allocated size */
u32 fall_through; /* 0: only classify if explicit match */
struct rcu_work rwork;
};
static inline int tcindex_filter_is_set(struct tcindex_filter_result *r)
{
return tcf_exts_has_actions(&r->exts) || r->res.classid;
}
static struct tcindex_filter_result *tcindex_lookup(struct tcindex_data *p,
u16 key)
{
if (p->perfect) {
struct tcindex_filter_result *f = p->perfect + key;
return tcindex_filter_is_set(f) ? f : NULL;
} else if (p->h) {
struct tcindex_filter __rcu **fp;
struct tcindex_filter *f;
fp = &p->h[key % p->hash];
for (f = rcu_dereference_bh_rtnl(*fp);
f;
fp = &f->next, f = rcu_dereference_bh_rtnl(*fp))
if (f->key == key)
return &f->result;
}
return NULL;
}
static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
struct tcindex_data *p = rcu_dereference_bh(tp->root);
struct tcindex_filter_result *f;
int key = (skb->tc_index & p->mask) >> p->shift;
pr_debug("tcindex_classify(skb %p,tp %p,res %p),p %p\n",
skb, tp, res, p);
f = tcindex_lookup(p, key);
if (!f) {
struct Qdisc *q = tcf_block_q(tp->chain->block);
if (!p->fall_through)
return -1;
res->classid = TC_H_MAKE(TC_H_MAJ(q->handle), key);
res->class = 0;
pr_debug("alg 0x%x\n", res->classid);
return 0;
}
*res = f->res;
pr_debug("map 0x%x\n", res->classid);
return tcf_exts_exec(skb, &f->exts, res);
}
static void *tcindex_get(struct tcf_proto *tp, u32 handle)
{
struct tcindex_data *p = rtnl_dereference(tp->root);
struct tcindex_filter_result *r;
pr_debug("tcindex_get(tp %p,handle 0x%08x)\n", tp, handle);
if (p->perfect && handle >= p->alloc_hash)
return NULL;
r = tcindex_lookup(p, handle);
return r && tcindex_filter_is_set(r) ? r : NULL;
}
static int tcindex_init(struct tcf_proto *tp)
{
struct tcindex_data *p;
pr_debug("tcindex_init(tp %p)\n", tp);
p = kzalloc(sizeof(struct tcindex_data), GFP_KERNEL);
if (!p)
return -ENOMEM;
p->mask = 0xffff;
p->hash = DEFAULT_HASH_SIZE;
p->fall_through = 1;
rcu_assign_pointer(tp->root, p);
return 0;
}
static void __tcindex_destroy_rexts(struct tcindex_filter_result *r)
{
tcf_exts_destroy(&r->exts);
tcf_exts_put_net(&r->exts);
}
static void tcindex_destroy_rexts_work(struct work_struct *work)
{
struct tcindex_filter_result *r;
r = container_of(to_rcu_work(work),
struct tcindex_filter_result,
rwork);
rtnl_lock();
__tcindex_destroy_rexts(r);
rtnl_unlock();
}
static void __tcindex_destroy_fexts(struct tcindex_filter *f)
{
tcf_exts_destroy(&f->result.exts);
tcf_exts_put_net(&f->result.exts);
kfree(f);
}
static void tcindex_destroy_fexts_work(struct work_struct *work)
{
struct tcindex_filter *f = container_of(to_rcu_work(work),
struct tcindex_filter,
rwork);
rtnl_lock();
__tcindex_destroy_fexts(f);
rtnl_unlock();
}
static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last,
bool rtnl_held, struct netlink_ext_ack *extack)
{
struct tcindex_data *p = rtnl_dereference(tp->root);
struct tcindex_filter_result *r = arg;
struct tcindex_filter __rcu **walk;
struct tcindex_filter *f = NULL;
pr_debug("tcindex_delete(tp %p,arg %p),p %p\n", tp, arg, p);
if (p->perfect) {
if (!r->res.class)
return -ENOENT;
} else {
int i;
for (i = 0; i < p->hash; i++) {
walk = p->h + i;
for (f = rtnl_dereference(*walk); f;
walk = &f->next, f = rtnl_dereference(*walk)) {
if (&f->result == r)
goto found;
}
}
return -ENOENT;
found:
rcu_assign_pointer(*walk, rtnl_dereference(f->next));
}
tcf_unbind_filter(tp, &r->res);
/* all classifiers are required to call tcf_exts_destroy() after rcu
* grace period, since converted-to-rcu actions are relying on that
* in cleanup() callback
*/
if (f) {
if (tcf_exts_get_net(&f->result.exts))
tcf_queue_work(&f->rwork, tcindex_destroy_fexts_work);
else
__tcindex_destroy_fexts(f);
} else {
if (tcf_exts_get_net(&r->exts))
tcf_queue_work(&r->rwork, tcindex_destroy_rexts_work);
else
__tcindex_destroy_rexts(r);
}
*last = false;
return 0;
}
static int tcindex_destroy_element(struct tcf_proto *tp,
void *arg, struct tcf_walker *walker)
{
bool last;
return tcindex_delete(tp, arg, &last, false, NULL);
}
static void tcindex_destroy_work(struct work_struct *work)
{
struct tcindex_data *p = container_of(to_rcu_work(work),
struct tcindex_data,
rwork);
kfree(p->perfect);
kfree(p->h);
kfree(p);
}
static inline int
valid_perfect_hash(struct tcindex_data *p)
{
return p->hash > (p->mask >> p->shift);
}
static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = {
[TCA_TCINDEX_HASH] = { .type = NLA_U32 },
[TCA_TCINDEX_MASK] = { .type = NLA_U16 },
[TCA_TCINDEX_SHIFT] = { .type = NLA_U32 },
[TCA_TCINDEX_FALL_THROUGH] = { .type = NLA_U32 },
[TCA_TCINDEX_CLASSID] = { .type = NLA_U32 },
};
static int tcindex_filter_result_init(struct tcindex_filter_result *r)
{
memset(r, 0, sizeof(*r));
return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
}
static void tcindex_partial_destroy_work(struct work_struct *work)
{
struct tcindex_data *p = container_of(to_rcu_work(work),
struct tcindex_data,
rwork);
kfree(p->perfect);
kfree(p);
}
static void tcindex_free_perfect_hash(struct tcindex_data *cp)
{
int i;
for (i = 0; i < cp->hash; i++)
tcf_exts_destroy(&cp->perfect[i].exts);
kfree(cp->perfect);
}
static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp)
{
int i, err = 0;
cp->perfect = kcalloc(cp->hash, sizeof(struct tcindex_filter_result),
GFP_KERNEL);
if (!cp->perfect)
return -ENOMEM;
for (i = 0; i < cp->hash; i++) {
err = tcf_exts_init(&cp->perfect[i].exts,
TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
if (err < 0)
goto errout;
#ifdef CONFIG_NET_CLS_ACT
cp->perfect[i].exts.net = net;
#endif
}
return 0;
errout:
tcindex_free_perfect_hash(cp);
return err;
}
static int
tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
u32 handle, struct tcindex_data *p,
struct tcindex_filter_result *r, struct nlattr **tb,
struct nlattr *est, bool ovr, struct netlink_ext_ack *extack)
{
struct tcindex_filter_result new_filter_result, *old_r = r;
struct tcindex_data *cp = NULL, *oldp;
struct tcindex_filter *f = NULL; /* make gcc behave */
struct tcf_result cr = {};
int err, balloc = 0;
struct tcf_exts e;
err = tcf_exts_init(&e, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
if (err < 0)
return err;
err = tcf_exts_validate(net, tp, tb, est, &e, ovr, true, extack);
if (err < 0)
goto errout;
err = -ENOMEM;
/* tcindex_data attributes must look atomic to classifier/lookup so
* allocate new tcindex data and RCU assign it onto root. Keeping
* perfect hash and hash pointers from old data.
*/
cp = kzalloc(sizeof(*cp), GFP_KERNEL);
if (!cp)
goto errout;
cp->mask = p->mask;
cp->shift = p->shift;
cp->hash = p->hash;
cp->alloc_hash = p->alloc_hash;
cp->fall_through = p->fall_through;
cp->tp = tp;
if (p->perfect) {
int i;
if (tcindex_alloc_perfect_hash(net, cp) < 0)
goto errout;
for (i = 0; i < cp->hash; i++)
cp->perfect[i].res = p->perfect[i].res;
balloc = 1;
}
cp->h = p->h;
err = tcindex_filter_result_init(&new_filter_result);
if (err < 0)
goto errout1;
if (old_r)
cr = r->res;
if (tb[TCA_TCINDEX_HASH])
cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
if (tb[TCA_TCINDEX_MASK])
cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]);
if (tb[TCA_TCINDEX_SHIFT])
cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]);
err = -EBUSY;
/* Hash already allocated, make sure that we still meet the
* requirements for the allocated hash.
*/
if (cp->perfect) {
if (!valid_perfect_hash(cp) ||
cp->hash > cp->alloc_hash)
goto errout_alloc;
} else if (cp->h && cp->hash != cp->alloc_hash) {
goto errout_alloc;
}
err = -EINVAL;
if (tb[TCA_TCINDEX_FALL_THROUGH])
cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]);
if (!cp->hash) {
/* Hash not specified, use perfect hash if the upper limit
* of the hashing index is below the threshold.
*/
if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD)
cp->hash = (cp->mask >> cp->shift) + 1;
else
cp->hash = DEFAULT_HASH_SIZE;
}
if (!cp->perfect && !cp->h)
cp->alloc_hash = cp->hash;
/* Note: this could be as restrictive as if (handle & ~(mask >> shift))
* but then, we'd fail handles that may become valid after some future
* mask change. While this is extremely unlikely to ever matter,
* the check below is safer (and also more backwards-compatible).
*/
if (cp->perfect || valid_perfect_hash(cp))
if (handle >= cp->alloc_hash)
goto errout_alloc;
err = -ENOMEM;
if (!cp->perfect && !cp->h) {
if (valid_perfect_hash(cp)) {
if (tcindex_alloc_perfect_hash(net, cp) < 0)
goto errout_alloc;
balloc = 1;
} else {
struct tcindex_filter __rcu **hash;
hash = kcalloc(cp->hash,
sizeof(struct tcindex_filter *),
GFP_KERNEL);
if (!hash)
goto errout_alloc;
cp->h = hash;
balloc = 2;
}
}
if (cp->perfect)
r = cp->perfect + handle;
else
r = tcindex_lookup(cp, handle) ? : &new_filter_result;
if (r == &new_filter_result) {
f = kzalloc(sizeof(*f), GFP_KERNEL);
if (!f)
goto errout_alloc;
f->key = handle;
f->next = NULL;
err = tcindex_filter_result_init(&f->result);
if (err < 0) {
kfree(f);
goto errout_alloc;
}
}
if (tb[TCA_TCINDEX_CLASSID]) {
cr.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]);
tcf_bind_filter(tp, &cr, base);
}
if (old_r && old_r != r) {
err = tcindex_filter_result_init(old_r);
if (err < 0) {
kfree(f);
goto errout_alloc;
}
}
oldp = p;
r->res = cr;
tcf_exts_change(&r->exts, &e);
rcu_assign_pointer(tp->root, cp);
if (r == &new_filter_result) {
struct tcindex_filter *nfp;
struct tcindex_filter __rcu **fp;
f->result.res = r->res;
tcf_exts_change(&f->result.exts, &r->exts);
fp = cp->h + (handle % cp->hash);
for (nfp = rtnl_dereference(*fp);
nfp;
fp = &nfp->next, nfp = rtnl_dereference(*fp))
; /* nothing */
rcu_assign_pointer(*fp, f);
} else {
tcf_exts_destroy(&new_filter_result.exts);
}
if (oldp)
tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work);
return 0;
errout_alloc:
if (balloc == 1)
tcindex_free_perfect_hash(cp);
else if (balloc == 2)
kfree(cp->h);
errout1:
tcf_exts_destroy(&new_filter_result.exts);
errout:
kfree(cp);
tcf_exts_destroy(&e);
return err;
}
static int
tcindex_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base, u32 handle,
struct nlattr **tca, void **arg, bool ovr,
bool rtnl_held, struct netlink_ext_ack *extack)
{
struct nlattr *opt = tca[TCA_OPTIONS];
struct nlattr *tb[TCA_TCINDEX_MAX + 1];
struct tcindex_data *p = rtnl_dereference(tp->root);
struct tcindex_filter_result *r = *arg;
int err;
pr_debug("tcindex_change(tp %p,handle 0x%08x,tca %p,arg %p),opt %p,"
"p %p,r %p,*arg %p\n",
tp, handle, tca, arg, opt, p, r, arg ? *arg : NULL);
if (!opt)
return 0;
err = nla_parse_nested(tb, TCA_TCINDEX_MAX, opt, tcindex_policy, NULL);
if (err < 0)
return err;
return tcindex_set_parms(net, tp, base, handle, p, r, tb,
tca[TCA_RATE], ovr, extack);
}
static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker,
bool rtnl_held)
{
struct tcindex_data *p = rtnl_dereference(tp->root);
struct tcindex_filter *f, *next;
int i;
pr_debug("tcindex_walk(tp %p,walker %p),p %p\n", tp, walker, p);
if (p->perfect) {
for (i = 0; i < p->hash; i++) {
if (!p->perfect[i].res.class)
continue;
if (walker->count >= walker->skip) {
if (walker->fn(tp, p->perfect + i, walker) < 0) {
walker->stop = 1;
return;
}
}
walker->count++;
}
}
if (!p->h)
return;
for (i = 0; i < p->hash; i++) {
for (f = rtnl_dereference(p->h[i]); f; f = next) {
next = rtnl_dereference(f->next);
if (walker->count >= walker->skip) {
if (walker->fn(tp, &f->result, walker) < 0) {
walker->stop = 1;
return;
}
}
walker->count++;
}
}
}
static void tcindex_destroy(struct tcf_proto *tp, bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct tcindex_data *p = rtnl_dereference(tp->root);
struct tcf_walker walker;
pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p);
walker.count = 0;
walker.skip = 0;
walker.fn = tcindex_destroy_element;
tcindex_walk(tp, &walker, true);
tcf_queue_work(&p->rwork, tcindex_destroy_work);
}
static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh,
struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
{
struct tcindex_data *p = rtnl_dereference(tp->root);
struct tcindex_filter_result *r = fh;
struct nlattr *nest;
pr_debug("tcindex_dump(tp %p,fh %p,skb %p,t %p),p %p,r %p\n",
tp, fh, skb, t, p, r);
pr_debug("p->perfect %p p->h %p\n", p->perfect, p->h);
nest = nla_nest_start(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
if (!fh) {
t->tcm_handle = ~0; /* whatever ... */
if (nla_put_u32(skb, TCA_TCINDEX_HASH, p->hash) ||
nla_put_u16(skb, TCA_TCINDEX_MASK, p->mask) ||
nla_put_u32(skb, TCA_TCINDEX_SHIFT, p->shift) ||
nla_put_u32(skb, TCA_TCINDEX_FALL_THROUGH, p->fall_through))
goto nla_put_failure;
nla_nest_end(skb, nest);
} else {
if (p->perfect) {
t->tcm_handle = r - p->perfect;
} else {
struct tcindex_filter *f;
struct tcindex_filter __rcu **fp;
int i;
t->tcm_handle = 0;
for (i = 0; !t->tcm_handle && i < p->hash; i++) {
fp = &p->h[i];
for (f = rtnl_dereference(*fp);
!t->tcm_handle && f;
fp = &f->next, f = rtnl_dereference(*fp)) {
if (&f->result == r)
t->tcm_handle = f->key;
}
}
}
pr_debug("handle = %d\n", t->tcm_handle);
if (r->res.class &&
nla_put_u32(skb, TCA_TCINDEX_CLASSID, r->res.classid))
goto nla_put_failure;
if (tcf_exts_dump(skb, &r->exts) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
if (tcf_exts_dump_stats(skb, &r->exts) < 0)
goto nla_put_failure;
}
return skb->len;
nla_put_failure:
nla_nest_cancel(skb, nest);
return -1;
}
static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl)
{
struct tcindex_filter_result *r = fh;
if (r && r->res.classid == classid)
r->res.class = cl;
}
static struct tcf_proto_ops cls_tcindex_ops __read_mostly = {
.kind = "tcindex",
.classify = tcindex_classify,
.init = tcindex_init,
.destroy = tcindex_destroy,
.get = tcindex_get,
.change = tcindex_change,
.delete = tcindex_delete,
.walk = tcindex_walk,
.dump = tcindex_dump,
.bind_class = tcindex_bind_class,
.owner = THIS_MODULE,
};
static int __init init_tcindex(void)
{
return register_tcf_proto_ops(&cls_tcindex_ops);
}
static void __exit exit_tcindex(void)
{
unregister_tcf_proto_ops(&cls_tcindex_ops);
}
module_init(init_tcindex)
module_exit(exit_tcindex)
MODULE_LICENSE("GPL");
|