forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathcore.c
1835 lines (1622 loc) · 45.4 KB
/
core.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
/*
* Linux Socket Filter - Kernel level socket filtering
*
* Based on the design of the Berkeley Packet Filter. The new
* internal format has been designed by PLUMgrid:
*
* Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com
*
* Authors:
*
* Jay Schulist <[email protected]>
* Alexei Starovoitov <[email protected]>
* Daniel Borkmann <[email protected]>
*
* 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.
*
* Andi Kleen - Fix a few bad bugs and races.
* Kris Katterjohn - Added many additional checks in bpf_check_classic()
*/
#include <linux/filter.h>
#include <linux/skbuff.h>
#include <linux/vmalloc.h>
#include <linux/random.h>
#include <linux/moduleloader.h>
#include <linux/bpf.h>
#include <linux/frame.h>
#include <linux/rbtree_latch.h>
#include <linux/kallsyms.h>
#include <linux/rcupdate.h>
#include <asm/unaligned.h>
/* Registers */
#define BPF_R0 regs[BPF_REG_0]
#define BPF_R1 regs[BPF_REG_1]
#define BPF_R2 regs[BPF_REG_2]
#define BPF_R3 regs[BPF_REG_3]
#define BPF_R4 regs[BPF_REG_4]
#define BPF_R5 regs[BPF_REG_5]
#define BPF_R6 regs[BPF_REG_6]
#define BPF_R7 regs[BPF_REG_7]
#define BPF_R8 regs[BPF_REG_8]
#define BPF_R9 regs[BPF_REG_9]
#define BPF_R10 regs[BPF_REG_10]
/* Named registers */
#define DST regs[insn->dst_reg]
#define SRC regs[insn->src_reg]
#define FP regs[BPF_REG_FP]
#define ARG1 regs[BPF_REG_ARG1]
#define CTX regs[BPF_REG_CTX]
#define IMM insn->imm
/* No hurry in this branch
*
* Exported for the bpf jit load helper.
*/
void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size)
{
u8 *ptr = NULL;
if (k >= SKF_NET_OFF)
ptr = skb_network_header(skb) + k - SKF_NET_OFF;
else if (k >= SKF_LL_OFF)
ptr = skb_mac_header(skb) + k - SKF_LL_OFF;
if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb))
return ptr;
return NULL;
}
struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
{
gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog_aux *aux;
struct bpf_prog *fp;
size = round_up(size, PAGE_SIZE);
fp = __vmalloc(size, gfp_flags, PAGE_KERNEL);
if (fp == NULL)
return NULL;
aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags);
if (aux == NULL) {
vfree(fp);
return NULL;
}
fp->pages = size / PAGE_SIZE;
fp->aux = aux;
fp->aux->prog = fp;
fp->jit_requested = ebpf_jit_enabled();
INIT_LIST_HEAD_RCU(&fp->aux->ksym_lnode);
return fp;
}
EXPORT_SYMBOL_GPL(bpf_prog_alloc);
struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
gfp_t gfp_extra_flags)
{
gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog *fp;
u32 pages, delta;
int ret;
BUG_ON(fp_old == NULL);
size = round_up(size, PAGE_SIZE);
pages = size / PAGE_SIZE;
if (pages <= fp_old->pages)
return fp_old;
delta = pages - fp_old->pages;
ret = __bpf_prog_charge(fp_old->aux->user, delta);
if (ret)
return NULL;
fp = __vmalloc(size, gfp_flags, PAGE_KERNEL);
if (fp == NULL) {
__bpf_prog_uncharge(fp_old->aux->user, delta);
} else {
memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE);
fp->pages = pages;
fp->aux->prog = fp;
/* We keep fp->aux from fp_old around in the new
* reallocated structure.
*/
fp_old->aux = NULL;
__bpf_prog_free(fp_old);
}
return fp;
}
void __bpf_prog_free(struct bpf_prog *fp)
{
kfree(fp->aux);
vfree(fp);
}
int bpf_prog_calc_tag(struct bpf_prog *fp)
{
const u32 bits_offset = SHA_MESSAGE_BYTES - sizeof(__be64);
u32 raw_size = bpf_prog_tag_scratch_size(fp);
u32 digest[SHA_DIGEST_WORDS];
u32 ws[SHA_WORKSPACE_WORDS];
u32 i, bsize, psize, blocks;
struct bpf_insn *dst;
bool was_ld_map;
u8 *raw, *todo;
__be32 *result;
__be64 *bits;
raw = vmalloc(raw_size);
if (!raw)
return -ENOMEM;
sha_init(digest);
memset(ws, 0, sizeof(ws));
/* We need to take out the map fd for the digest calculation
* since they are unstable from user space side.
*/
dst = (void *)raw;
for (i = 0, was_ld_map = false; i < fp->len; i++) {
dst[i] = fp->insnsi[i];
if (!was_ld_map &&
dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) &&
dst[i].src_reg == BPF_PSEUDO_MAP_FD) {
was_ld_map = true;
dst[i].imm = 0;
} else if (was_ld_map &&
dst[i].code == 0 &&
dst[i].dst_reg == 0 &&
dst[i].src_reg == 0 &&
dst[i].off == 0) {
was_ld_map = false;
dst[i].imm = 0;
} else {
was_ld_map = false;
}
}
psize = bpf_prog_insn_size(fp);
memset(&raw[psize], 0, raw_size - psize);
raw[psize++] = 0x80;
bsize = round_up(psize, SHA_MESSAGE_BYTES);
blocks = bsize / SHA_MESSAGE_BYTES;
todo = raw;
if (bsize - psize >= sizeof(__be64)) {
bits = (__be64 *)(todo + bsize - sizeof(__be64));
} else {
bits = (__be64 *)(todo + bsize + bits_offset);
blocks++;
}
*bits = cpu_to_be64((psize - 1) << 3);
while (blocks--) {
sha_transform(digest, todo, ws);
todo += SHA_MESSAGE_BYTES;
}
result = (__force __be32 *)digest;
for (i = 0; i < SHA_DIGEST_WORDS; i++)
result[i] = cpu_to_be32(digest[i]);
memcpy(fp->tag, result, sizeof(fp->tag));
vfree(raw);
return 0;
}
static void bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta)
{
struct bpf_insn *insn = prog->insnsi;
u32 i, insn_cnt = prog->len;
bool pseudo_call;
u8 code;
int off;
for (i = 0; i < insn_cnt; i++, insn++) {
code = insn->code;
if (BPF_CLASS(code) != BPF_JMP)
continue;
if (BPF_OP(code) == BPF_EXIT)
continue;
if (BPF_OP(code) == BPF_CALL) {
if (insn->src_reg == BPF_PSEUDO_CALL)
pseudo_call = true;
else
continue;
} else {
pseudo_call = false;
}
off = pseudo_call ? insn->imm : insn->off;
/* Adjust offset of jmps if we cross boundaries. */
if (i < pos && i + off + 1 > pos)
off += delta;
else if (i > pos + delta && i + off + 1 <= pos + delta)
off -= delta;
if (pseudo_call)
insn->imm = off;
else
insn->off = off;
}
}
struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
const struct bpf_insn *patch, u32 len)
{
u32 insn_adj_cnt, insn_rest, insn_delta = len - 1;
struct bpf_prog *prog_adj;
/* Since our patchlet doesn't expand the image, we're done. */
if (insn_delta == 0) {
memcpy(prog->insnsi + off, patch, sizeof(*patch));
return prog;
}
insn_adj_cnt = prog->len + insn_delta;
/* Several new instructions need to be inserted. Make room
* for them. Likely, there's no need for a new allocation as
* last page could have large enough tailroom.
*/
prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt),
GFP_USER);
if (!prog_adj)
return NULL;
prog_adj->len = insn_adj_cnt;
/* Patching happens in 3 steps:
*
* 1) Move over tail of insnsi from next instruction onwards,
* so we can patch the single target insn with one or more
* new ones (patching is always from 1 to n insns, n > 0).
* 2) Inject new instructions at the target location.
* 3) Adjust branch offsets if necessary.
*/
insn_rest = insn_adj_cnt - off - len;
memmove(prog_adj->insnsi + off + len, prog_adj->insnsi + off + 1,
sizeof(*patch) * insn_rest);
memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len);
bpf_adj_branches(prog_adj, off, insn_delta);
return prog_adj;
}
#ifdef CONFIG_BPF_JIT
/* All BPF JIT sysctl knobs here. */
int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON);
int bpf_jit_harden __read_mostly;
int bpf_jit_kallsyms __read_mostly;
static __always_inline void
bpf_get_prog_addr_region(const struct bpf_prog *prog,
unsigned long *symbol_start,
unsigned long *symbol_end)
{
const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(prog);
unsigned long addr = (unsigned long)hdr;
WARN_ON_ONCE(!bpf_prog_ebpf_jited(prog));
*symbol_start = addr;
*symbol_end = addr + hdr->pages * PAGE_SIZE;
}
static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
{
const char *end = sym + KSYM_NAME_LEN;
BUILD_BUG_ON(sizeof("bpf_prog_") +
sizeof(prog->tag) * 2 +
/* name has been null terminated.
* We should need +1 for the '_' preceding
* the name. However, the null character
* is double counted between the name and the
* sizeof("bpf_prog_") above, so we omit
* the +1 here.
*/
sizeof(prog->aux->name) > KSYM_NAME_LEN);
sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_");
sym = bin2hex(sym, prog->tag, sizeof(prog->tag));
if (prog->aux->name[0])
snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name);
else
*sym = 0;
}
static __always_inline unsigned long
bpf_get_prog_addr_start(struct latch_tree_node *n)
{
unsigned long symbol_start, symbol_end;
const struct bpf_prog_aux *aux;
aux = container_of(n, struct bpf_prog_aux, ksym_tnode);
bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);
return symbol_start;
}
static __always_inline bool bpf_tree_less(struct latch_tree_node *a,
struct latch_tree_node *b)
{
return bpf_get_prog_addr_start(a) < bpf_get_prog_addr_start(b);
}
static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n)
{
unsigned long val = (unsigned long)key;
unsigned long symbol_start, symbol_end;
const struct bpf_prog_aux *aux;
aux = container_of(n, struct bpf_prog_aux, ksym_tnode);
bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);
if (val < symbol_start)
return -1;
if (val >= symbol_end)
return 1;
return 0;
}
static const struct latch_tree_ops bpf_tree_ops = {
.less = bpf_tree_less,
.comp = bpf_tree_comp,
};
static DEFINE_SPINLOCK(bpf_lock);
static LIST_HEAD(bpf_kallsyms);
static struct latch_tree_root bpf_tree __cacheline_aligned;
static void bpf_prog_ksym_node_add(struct bpf_prog_aux *aux)
{
WARN_ON_ONCE(!list_empty(&aux->ksym_lnode));
list_add_tail_rcu(&aux->ksym_lnode, &bpf_kallsyms);
latch_tree_insert(&aux->ksym_tnode, &bpf_tree, &bpf_tree_ops);
}
static void bpf_prog_ksym_node_del(struct bpf_prog_aux *aux)
{
if (list_empty(&aux->ksym_lnode))
return;
latch_tree_erase(&aux->ksym_tnode, &bpf_tree, &bpf_tree_ops);
list_del_rcu(&aux->ksym_lnode);
}
static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp)
{
return fp->jited && !bpf_prog_was_classic(fp);
}
static bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp)
{
return list_empty(&fp->aux->ksym_lnode) ||
fp->aux->ksym_lnode.prev == LIST_POISON2;
}
void bpf_prog_kallsyms_add(struct bpf_prog *fp)
{
if (!bpf_prog_kallsyms_candidate(fp) ||
!capable(CAP_SYS_ADMIN))
return;
spin_lock_bh(&bpf_lock);
bpf_prog_ksym_node_add(fp->aux);
spin_unlock_bh(&bpf_lock);
}
void bpf_prog_kallsyms_del(struct bpf_prog *fp)
{
if (!bpf_prog_kallsyms_candidate(fp))
return;
spin_lock_bh(&bpf_lock);
bpf_prog_ksym_node_del(fp->aux);
spin_unlock_bh(&bpf_lock);
}
static struct bpf_prog *bpf_prog_kallsyms_find(unsigned long addr)
{
struct latch_tree_node *n;
if (!bpf_jit_kallsyms_enabled())
return NULL;
n = latch_tree_find((void *)addr, &bpf_tree, &bpf_tree_ops);
return n ?
container_of(n, struct bpf_prog_aux, ksym_tnode)->prog :
NULL;
}
const char *__bpf_address_lookup(unsigned long addr, unsigned long *size,
unsigned long *off, char *sym)
{
unsigned long symbol_start, symbol_end;
struct bpf_prog *prog;
char *ret = NULL;
rcu_read_lock();
prog = bpf_prog_kallsyms_find(addr);
if (prog) {
bpf_get_prog_addr_region(prog, &symbol_start, &symbol_end);
bpf_get_prog_name(prog, sym);
ret = sym;
if (size)
*size = symbol_end - symbol_start;
if (off)
*off = addr - symbol_start;
}
rcu_read_unlock();
return ret;
}
bool is_bpf_text_address(unsigned long addr)
{
bool ret;
rcu_read_lock();
ret = bpf_prog_kallsyms_find(addr) != NULL;
rcu_read_unlock();
return ret;
}
int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
char *sym)
{
unsigned long symbol_start, symbol_end;
struct bpf_prog_aux *aux;
unsigned int it = 0;
int ret = -ERANGE;
if (!bpf_jit_kallsyms_enabled())
return ret;
rcu_read_lock();
list_for_each_entry_rcu(aux, &bpf_kallsyms, ksym_lnode) {
if (it++ != symnum)
continue;
bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);
bpf_get_prog_name(aux->prog, sym);
*value = symbol_start;
*type = BPF_SYM_ELF_TYPE;
ret = 0;
break;
}
rcu_read_unlock();
return ret;
}
struct bpf_binary_header *
bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
unsigned int alignment,
bpf_jit_fill_hole_t bpf_fill_ill_insns)
{
struct bpf_binary_header *hdr;
unsigned int size, hole, start;
/* Most of BPF filters are really small, but if some of them
* fill a page, allow at least 128 extra bytes to insert a
* random section of illegal instructions.
*/
size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE);
hdr = module_alloc(size);
if (hdr == NULL)
return NULL;
/* Fill space with illegal/arch-dep instructions. */
bpf_fill_ill_insns(hdr, size);
hdr->pages = size / PAGE_SIZE;
hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
PAGE_SIZE - sizeof(*hdr));
start = (get_random_int() % hole) & ~(alignment - 1);
/* Leave a random number of instructions before BPF code. */
*image_ptr = &hdr->image[start];
return hdr;
}
void bpf_jit_binary_free(struct bpf_binary_header *hdr)
{
module_memfree(hdr);
}
/* This symbol is only overridden by archs that have different
* requirements than the usual eBPF JITs, f.e. when they only
* implement cBPF JIT, do not set images read-only, etc.
*/
void __weak bpf_jit_free(struct bpf_prog *fp)
{
if (fp->jited) {
struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
bpf_jit_binary_unlock_ro(hdr);
bpf_jit_binary_free(hdr);
WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp));
}
bpf_prog_unlock_free(fp);
}
static int bpf_jit_blind_insn(const struct bpf_insn *from,
const struct bpf_insn *aux,
struct bpf_insn *to_buff)
{
struct bpf_insn *to = to_buff;
u32 imm_rnd = get_random_int();
s16 off;
BUILD_BUG_ON(BPF_REG_AX + 1 != MAX_BPF_JIT_REG);
BUILD_BUG_ON(MAX_BPF_REG + 1 != MAX_BPF_JIT_REG);
if (from->imm == 0 &&
(from->code == (BPF_ALU | BPF_MOV | BPF_K) ||
from->code == (BPF_ALU64 | BPF_MOV | BPF_K))) {
*to++ = BPF_ALU64_REG(BPF_XOR, from->dst_reg, from->dst_reg);
goto out;
}
switch (from->code) {
case BPF_ALU | BPF_ADD | BPF_K:
case BPF_ALU | BPF_SUB | BPF_K:
case BPF_ALU | BPF_AND | BPF_K:
case BPF_ALU | BPF_OR | BPF_K:
case BPF_ALU | BPF_XOR | BPF_K:
case BPF_ALU | BPF_MUL | BPF_K:
case BPF_ALU | BPF_MOV | BPF_K:
case BPF_ALU | BPF_DIV | BPF_K:
case BPF_ALU | BPF_MOD | BPF_K:
*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
*to++ = BPF_ALU32_REG(from->code, from->dst_reg, BPF_REG_AX);
break;
case BPF_ALU64 | BPF_ADD | BPF_K:
case BPF_ALU64 | BPF_SUB | BPF_K:
case BPF_ALU64 | BPF_AND | BPF_K:
case BPF_ALU64 | BPF_OR | BPF_K:
case BPF_ALU64 | BPF_XOR | BPF_K:
case BPF_ALU64 | BPF_MUL | BPF_K:
case BPF_ALU64 | BPF_MOV | BPF_K:
case BPF_ALU64 | BPF_DIV | BPF_K:
case BPF_ALU64 | BPF_MOD | BPF_K:
*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
*to++ = BPF_ALU64_REG(from->code, from->dst_reg, BPF_REG_AX);
break;
case BPF_JMP | BPF_JEQ | BPF_K:
case BPF_JMP | BPF_JNE | BPF_K:
case BPF_JMP | BPF_JGT | BPF_K:
case BPF_JMP | BPF_JLT | BPF_K:
case BPF_JMP | BPF_JGE | BPF_K:
case BPF_JMP | BPF_JLE | BPF_K:
case BPF_JMP | BPF_JSGT | BPF_K:
case BPF_JMP | BPF_JSLT | BPF_K:
case BPF_JMP | BPF_JSGE | BPF_K:
case BPF_JMP | BPF_JSLE | BPF_K:
case BPF_JMP | BPF_JSET | BPF_K:
/* Accommodate for extra offset in case of a backjump. */
off = from->off;
if (off < 0)
off -= 2;
*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
*to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off);
break;
case BPF_LD | BPF_ABS | BPF_W:
case BPF_LD | BPF_ABS | BPF_H:
case BPF_LD | BPF_ABS | BPF_B:
*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
*to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0);
break;
case BPF_LD | BPF_IND | BPF_W:
case BPF_LD | BPF_IND | BPF_H:
case BPF_LD | BPF_IND | BPF_B:
*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
*to++ = BPF_ALU32_REG(BPF_ADD, BPF_REG_AX, from->src_reg);
*to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0);
break;
case BPF_LD | BPF_IMM | BPF_DW:
*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm);
*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
*to++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32);
*to++ = BPF_ALU64_REG(BPF_MOV, aux[0].dst_reg, BPF_REG_AX);
break;
case 0: /* Part 2 of BPF_LD | BPF_IMM | BPF_DW. */
*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[0].imm);
*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
*to++ = BPF_ALU64_REG(BPF_OR, aux[0].dst_reg, BPF_REG_AX);
break;
case BPF_ST | BPF_MEM | BPF_DW:
case BPF_ST | BPF_MEM | BPF_W:
case BPF_ST | BPF_MEM | BPF_H:
case BPF_ST | BPF_MEM | BPF_B:
*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
*to++ = BPF_STX_MEM(from->code, from->dst_reg, BPF_REG_AX, from->off);
break;
}
out:
return to - to_buff;
}
static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other,
gfp_t gfp_extra_flags)
{
gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog *fp;
fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags, PAGE_KERNEL);
if (fp != NULL) {
/* aux->prog still points to the fp_other one, so
* when promoting the clone to the real program,
* this still needs to be adapted.
*/
memcpy(fp, fp_other, fp_other->pages * PAGE_SIZE);
}
return fp;
}
static void bpf_prog_clone_free(struct bpf_prog *fp)
{
/* aux was stolen by the other clone, so we cannot free
* it from this path! It will be freed eventually by the
* other program on release.
*
* At this point, we don't need a deferred release since
* clone is guaranteed to not be locked.
*/
fp->aux = NULL;
__bpf_prog_free(fp);
}
void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other)
{
/* We have to repoint aux->prog to self, as we don't
* know whether fp here is the clone or the original.
*/
fp->aux->prog = fp;
bpf_prog_clone_free(fp_other);
}
struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog)
{
struct bpf_insn insn_buff[16], aux[2];
struct bpf_prog *clone, *tmp;
int insn_delta, insn_cnt;
struct bpf_insn *insn;
int i, rewritten;
if (!bpf_jit_blinding_enabled(prog) || prog->blinded)
return prog;
clone = bpf_prog_clone_create(prog, GFP_USER);
if (!clone)
return ERR_PTR(-ENOMEM);
insn_cnt = clone->len;
insn = clone->insnsi;
for (i = 0; i < insn_cnt; i++, insn++) {
/* We temporarily need to hold the original ld64 insn
* so that we can still access the first part in the
* second blinding run.
*/
if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW) &&
insn[1].code == 0)
memcpy(aux, insn, sizeof(aux));
rewritten = bpf_jit_blind_insn(insn, aux, insn_buff);
if (!rewritten)
continue;
tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten);
if (!tmp) {
/* Patching may have repointed aux->prog during
* realloc from the original one, so we need to
* fix it up here on error.
*/
bpf_jit_prog_release_other(prog, clone);
return ERR_PTR(-ENOMEM);
}
clone = tmp;
insn_delta = rewritten - 1;
/* Walk new program and skip insns we just inserted. */
insn = clone->insnsi + i + insn_delta;
insn_cnt += insn_delta;
i += insn_delta;
}
clone->blinded = 1;
return clone;
}
#endif /* CONFIG_BPF_JIT */
/* Base function for offset calculation. Needs to go into .text section,
* therefore keeping it non-static as well; will also be used by JITs
* anyway later on, so do not let the compiler omit it. This also needs
* to go into kallsyms for correlation from e.g. bpftool, so naming
* must not change.
*/
noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
return 0;
}
EXPORT_SYMBOL_GPL(__bpf_call_base);
/* All UAPI available opcodes. */
#define BPF_INSN_MAP(INSN_2, INSN_3) \
/* 32 bit ALU operations. */ \
/* Register based. */ \
INSN_3(ALU, ADD, X), \
INSN_3(ALU, SUB, X), \
INSN_3(ALU, AND, X), \
INSN_3(ALU, OR, X), \
INSN_3(ALU, LSH, X), \
INSN_3(ALU, RSH, X), \
INSN_3(ALU, XOR, X), \
INSN_3(ALU, MUL, X), \
INSN_3(ALU, MOV, X), \
INSN_3(ALU, DIV, X), \
INSN_3(ALU, MOD, X), \
INSN_2(ALU, NEG), \
INSN_3(ALU, END, TO_BE), \
INSN_3(ALU, END, TO_LE), \
/* Immediate based. */ \
INSN_3(ALU, ADD, K), \
INSN_3(ALU, SUB, K), \
INSN_3(ALU, AND, K), \
INSN_3(ALU, OR, K), \
INSN_3(ALU, LSH, K), \
INSN_3(ALU, RSH, K), \
INSN_3(ALU, XOR, K), \
INSN_3(ALU, MUL, K), \
INSN_3(ALU, MOV, K), \
INSN_3(ALU, DIV, K), \
INSN_3(ALU, MOD, K), \
/* 64 bit ALU operations. */ \
/* Register based. */ \
INSN_3(ALU64, ADD, X), \
INSN_3(ALU64, SUB, X), \
INSN_3(ALU64, AND, X), \
INSN_3(ALU64, OR, X), \
INSN_3(ALU64, LSH, X), \
INSN_3(ALU64, RSH, X), \
INSN_3(ALU64, XOR, X), \
INSN_3(ALU64, MUL, X), \
INSN_3(ALU64, MOV, X), \
INSN_3(ALU64, ARSH, X), \
INSN_3(ALU64, DIV, X), \
INSN_3(ALU64, MOD, X), \
INSN_2(ALU64, NEG), \
/* Immediate based. */ \
INSN_3(ALU64, ADD, K), \
INSN_3(ALU64, SUB, K), \
INSN_3(ALU64, AND, K), \
INSN_3(ALU64, OR, K), \
INSN_3(ALU64, LSH, K), \
INSN_3(ALU64, RSH, K), \
INSN_3(ALU64, XOR, K), \
INSN_3(ALU64, MUL, K), \
INSN_3(ALU64, MOV, K), \
INSN_3(ALU64, ARSH, K), \
INSN_3(ALU64, DIV, K), \
INSN_3(ALU64, MOD, K), \
/* Call instruction. */ \
INSN_2(JMP, CALL), \
/* Exit instruction. */ \
INSN_2(JMP, EXIT), \
/* Jump instructions. */ \
/* Register based. */ \
INSN_3(JMP, JEQ, X), \
INSN_3(JMP, JNE, X), \
INSN_3(JMP, JGT, X), \
INSN_3(JMP, JLT, X), \
INSN_3(JMP, JGE, X), \
INSN_3(JMP, JLE, X), \
INSN_3(JMP, JSGT, X), \
INSN_3(JMP, JSLT, X), \
INSN_3(JMP, JSGE, X), \
INSN_3(JMP, JSLE, X), \
INSN_3(JMP, JSET, X), \
/* Immediate based. */ \
INSN_3(JMP, JEQ, K), \
INSN_3(JMP, JNE, K), \
INSN_3(JMP, JGT, K), \
INSN_3(JMP, JLT, K), \
INSN_3(JMP, JGE, K), \
INSN_3(JMP, JLE, K), \
INSN_3(JMP, JSGT, K), \
INSN_3(JMP, JSLT, K), \
INSN_3(JMP, JSGE, K), \
INSN_3(JMP, JSLE, K), \
INSN_3(JMP, JSET, K), \
INSN_2(JMP, JA), \
/* Store instructions. */ \
/* Register based. */ \
INSN_3(STX, MEM, B), \
INSN_3(STX, MEM, H), \
INSN_3(STX, MEM, W), \
INSN_3(STX, MEM, DW), \
INSN_3(STX, XADD, W), \
INSN_3(STX, XADD, DW), \
/* Immediate based. */ \
INSN_3(ST, MEM, B), \
INSN_3(ST, MEM, H), \
INSN_3(ST, MEM, W), \
INSN_3(ST, MEM, DW), \
/* Load instructions. */ \
/* Register based. */ \
INSN_3(LDX, MEM, B), \
INSN_3(LDX, MEM, H), \
INSN_3(LDX, MEM, W), \
INSN_3(LDX, MEM, DW), \
/* Immediate based. */ \
INSN_3(LD, IMM, DW), \
/* Misc (old cBPF carry-over). */ \
INSN_3(LD, ABS, B), \
INSN_3(LD, ABS, H), \
INSN_3(LD, ABS, W), \
INSN_3(LD, IND, B), \
INSN_3(LD, IND, H), \
INSN_3(LD, IND, W)
bool bpf_opcode_in_insntable(u8 code)
{
#define BPF_INSN_2_TBL(x, y) [BPF_##x | BPF_##y] = true
#define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true
static const bool public_insntable[256] = {
[0 ... 255] = false,
/* Now overwrite non-defaults ... */
BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
};
#undef BPF_INSN_3_TBL
#undef BPF_INSN_2_TBL
return public_insntable[code];
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
/**
* __bpf_prog_run - run eBPF program on a given context
* @ctx: is the data we are operating on
* @insn: is the array of eBPF instructions
*
* Decode and execute eBPF instructions.
*/
static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
{
u64 tmp;
#define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y
#define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z
static const void *jumptable[256] = {
[0 ... 255] = &&default_label,
/* Now overwrite non-defaults ... */
BPF_INSN_MAP(BPF_INSN_2_LBL, BPF_INSN_3_LBL),
/* Non-UAPI available opcodes. */
[BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS,
[BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL,
};
#undef BPF_INSN_3_LBL
#undef BPF_INSN_2_LBL
u32 tail_call_cnt = 0;
void *ptr;
int off;
#define CONT ({ insn++; goto select_insn; })
#define CONT_JMP ({ insn++; goto select_insn; })
select_insn:
goto *jumptable[insn->code];
/* ALU */
#define ALU(OPCODE, OP) \
ALU64_##OPCODE##_X: \
DST = DST OP SRC; \
CONT; \
ALU_##OPCODE##_X: \
DST = (u32) DST OP (u32) SRC; \
CONT; \
ALU64_##OPCODE##_K: \
DST = DST OP IMM; \
CONT; \
ALU_##OPCODE##_K: \
DST = (u32) DST OP (u32) IMM; \
CONT;
ALU(ADD, +)
ALU(SUB, -)
ALU(AND, &)
ALU(OR, |)
ALU(LSH, <<)
ALU(RSH, >>)
ALU(XOR, ^)
ALU(MUL, *)
#undef ALU
ALU_NEG:
DST = (u32) -DST;
CONT;
ALU64_NEG:
DST = -DST;
CONT;
ALU_MOV_X:
DST = (u32) SRC;
CONT;
ALU_MOV_K:
DST = (u32) IMM;
CONT;
ALU64_MOV_X:
DST = SRC;
CONT;
ALU64_MOV_K:
DST = IMM;
CONT;
LD_IMM_DW:
DST = (u64) (u32) insn[0].imm | ((u64) (u32) insn[1].imm) << 32;
insn++;
CONT;
ALU64_ARSH_X:
(*(s64 *) &DST) >>= SRC;
CONT;
ALU64_ARSH_K:
(*(s64 *) &DST) >>= IMM;
CONT;