forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
bpf_jit_comp.c
2121 lines (1894 loc) · 55.7 KB
/
bpf_jit_comp.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
// SPDX-License-Identifier: GPL-2.0-only
/*
* bpf_jit_comp.c: BPF JIT compiler
*
* Copyright (C) 2011-2013 Eric Dumazet ([email protected])
* Internal BPF Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
*/
#include <linux/netdevice.h>
#include <linux/filter.h>
#include <linux/if_vlan.h>
#include <linux/bpf.h>
#include <linux/memory.h>
#include <linux/sort.h>
#include <asm/extable.h>
#include <asm/set_memory.h>
#include <asm/nospec-branch.h>
#include <asm/text-patching.h>
#include <asm/asm-prototypes.h>
static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
{
if (len == 1)
*ptr = bytes;
else if (len == 2)
*(u16 *)ptr = bytes;
else {
*(u32 *)ptr = bytes;
barrier();
}
return ptr + len;
}
#define EMIT(bytes, len) \
do { prog = emit_code(prog, bytes, len); cnt += len; } while (0)
#define EMIT1(b1) EMIT(b1, 1)
#define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2)
#define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3)
#define EMIT4(b1, b2, b3, b4) EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4)
#define EMIT1_off32(b1, off) \
do { EMIT1(b1); EMIT(off, 4); } while (0)
#define EMIT2_off32(b1, b2, off) \
do { EMIT2(b1, b2); EMIT(off, 4); } while (0)
#define EMIT3_off32(b1, b2, b3, off) \
do { EMIT3(b1, b2, b3); EMIT(off, 4); } while (0)
#define EMIT4_off32(b1, b2, b3, b4, off) \
do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
static bool is_imm8(int value)
{
return value <= 127 && value >= -128;
}
static bool is_simm32(s64 value)
{
return value == (s64)(s32)value;
}
static bool is_uimm32(u64 value)
{
return value == (u64)(u32)value;
}
/* mov dst, src */
#define EMIT_mov(DST, SRC) \
do { \
if (DST != SRC) \
EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \
} while (0)
static int bpf_size_to_x86_bytes(int bpf_size)
{
if (bpf_size == BPF_W)
return 4;
else if (bpf_size == BPF_H)
return 2;
else if (bpf_size == BPF_B)
return 1;
else if (bpf_size == BPF_DW)
return 4; /* imm32 */
else
return 0;
}
/*
* List of x86 cond jumps opcodes (. + s8)
* Add 0x10 (and an extra 0x0f) to generate far jumps (. + s32)
*/
#define X86_JB 0x72
#define X86_JAE 0x73
#define X86_JE 0x74
#define X86_JNE 0x75
#define X86_JBE 0x76
#define X86_JA 0x77
#define X86_JL 0x7C
#define X86_JGE 0x7D
#define X86_JLE 0x7E
#define X86_JG 0x7F
/* Pick a register outside of BPF range for JIT internal work */
#define AUX_REG (MAX_BPF_JIT_REG + 1)
#define X86_REG_R9 (MAX_BPF_JIT_REG + 2)
/*
* The following table maps BPF registers to x86-64 registers.
*
* x86-64 register R12 is unused, since if used as base address
* register in load/store instructions, it always needs an
* extra byte of encoding and is callee saved.
*
* x86-64 register R9 is not used by BPF programs, but can be used by BPF
* trampoline. x86-64 register R10 is used for blinding (if enabled).
*/
static const int reg2hex[] = {
[BPF_REG_0] = 0, /* RAX */
[BPF_REG_1] = 7, /* RDI */
[BPF_REG_2] = 6, /* RSI */
[BPF_REG_3] = 2, /* RDX */
[BPF_REG_4] = 1, /* RCX */
[BPF_REG_5] = 0, /* R8 */
[BPF_REG_6] = 3, /* RBX callee saved */
[BPF_REG_7] = 5, /* R13 callee saved */
[BPF_REG_8] = 6, /* R14 callee saved */
[BPF_REG_9] = 7, /* R15 callee saved */
[BPF_REG_FP] = 5, /* RBP readonly */
[BPF_REG_AX] = 2, /* R10 temp register */
[AUX_REG] = 3, /* R11 temp register */
[X86_REG_R9] = 1, /* R9 register, 6th function argument */
};
static const int reg2pt_regs[] = {
[BPF_REG_0] = offsetof(struct pt_regs, ax),
[BPF_REG_1] = offsetof(struct pt_regs, di),
[BPF_REG_2] = offsetof(struct pt_regs, si),
[BPF_REG_3] = offsetof(struct pt_regs, dx),
[BPF_REG_4] = offsetof(struct pt_regs, cx),
[BPF_REG_5] = offsetof(struct pt_regs, r8),
[BPF_REG_6] = offsetof(struct pt_regs, bx),
[BPF_REG_7] = offsetof(struct pt_regs, r13),
[BPF_REG_8] = offsetof(struct pt_regs, r14),
[BPF_REG_9] = offsetof(struct pt_regs, r15),
};
/*
* is_ereg() == true if BPF register 'reg' maps to x86-64 r8..r15
* which need extra byte of encoding.
* rax,rcx,...,rbp have simpler encoding
*/
static bool is_ereg(u32 reg)
{
return (1 << reg) & (BIT(BPF_REG_5) |
BIT(AUX_REG) |
BIT(BPF_REG_7) |
BIT(BPF_REG_8) |
BIT(BPF_REG_9) |
BIT(X86_REG_R9) |
BIT(BPF_REG_AX));
}
/*
* is_ereg_8l() == true if BPF register 'reg' is mapped to access x86-64
* lower 8-bit registers dil,sil,bpl,spl,r8b..r15b, which need extra byte
* of encoding. al,cl,dl,bl have simpler encoding.
*/
static bool is_ereg_8l(u32 reg)
{
return is_ereg(reg) ||
(1 << reg) & (BIT(BPF_REG_1) |
BIT(BPF_REG_2) |
BIT(BPF_REG_FP));
}
static bool is_axreg(u32 reg)
{
return reg == BPF_REG_0;
}
/* Add modifiers if 'reg' maps to x86-64 registers R8..R15 */
static u8 add_1mod(u8 byte, u32 reg)
{
if (is_ereg(reg))
byte |= 1;
return byte;
}
static u8 add_2mod(u8 byte, u32 r1, u32 r2)
{
if (is_ereg(r1))
byte |= 1;
if (is_ereg(r2))
byte |= 4;
return byte;
}
/* Encode 'dst_reg' register into x86-64 opcode 'byte' */
static u8 add_1reg(u8 byte, u32 dst_reg)
{
return byte + reg2hex[dst_reg];
}
/* Encode 'dst_reg' and 'src_reg' registers into x86-64 opcode 'byte' */
static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
{
return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3);
}
static void jit_fill_hole(void *area, unsigned int size)
{
/* Fill whole space with INT3 instructions */
memset(area, 0xcc, size);
}
struct jit_context {
int cleanup_addr; /* Epilogue code offset */
};
/* Maximum number of bytes emitted while JITing one eBPF insn */
#define BPF_MAX_INSN_SIZE 128
#define BPF_INSN_SAFETY 64
/* Number of bytes emit_patch() needs to generate instructions */
#define X86_PATCH_SIZE 5
/* Number of bytes that will be skipped on tailcall */
#define X86_TAIL_CALL_OFFSET 11
static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
{
u8 *prog = *pprog;
int cnt = 0;
if (callee_regs_used[0])
EMIT1(0x53); /* push rbx */
if (callee_regs_used[1])
EMIT2(0x41, 0x55); /* push r13 */
if (callee_regs_used[2])
EMIT2(0x41, 0x56); /* push r14 */
if (callee_regs_used[3])
EMIT2(0x41, 0x57); /* push r15 */
*pprog = prog;
}
static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
{
u8 *prog = *pprog;
int cnt = 0;
if (callee_regs_used[3])
EMIT2(0x41, 0x5F); /* pop r15 */
if (callee_regs_used[2])
EMIT2(0x41, 0x5E); /* pop r14 */
if (callee_regs_used[1])
EMIT2(0x41, 0x5D); /* pop r13 */
if (callee_regs_used[0])
EMIT1(0x5B); /* pop rbx */
*pprog = prog;
}
/*
* Emit x86-64 prologue code for BPF program.
* bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes
* while jumping to another program
*/
static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
bool tail_call_reachable, bool is_subprog)
{
u8 *prog = *pprog;
int cnt = X86_PATCH_SIZE;
/* BPF trampoline can be made to work without these nops,
* but let's waste 5 bytes for now and optimize later
*/
memcpy(prog, ideal_nops[NOP_ATOMIC5], cnt);
prog += cnt;
if (!ebpf_from_cbpf) {
if (tail_call_reachable && !is_subprog)
EMIT2(0x31, 0xC0); /* xor eax, eax */
else
EMIT2(0x66, 0x90); /* nop2 */
}
EMIT1(0x55); /* push rbp */
EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
/* sub rsp, rounded_stack_depth */
if (stack_depth)
EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8));
if (tail_call_reachable)
EMIT1(0x50); /* push rax */
*pprog = prog;
}
static int emit_patch(u8 **pprog, void *func, void *ip, u8 opcode)
{
u8 *prog = *pprog;
int cnt = 0;
s64 offset;
offset = func - (ip + X86_PATCH_SIZE);
if (!is_simm32(offset)) {
pr_err("Target call %p is out of range\n", func);
return -ERANGE;
}
EMIT1_off32(opcode, offset);
*pprog = prog;
return 0;
}
static int emit_call(u8 **pprog, void *func, void *ip)
{
return emit_patch(pprog, func, ip, 0xE8);
}
static int emit_jump(u8 **pprog, void *func, void *ip)
{
return emit_patch(pprog, func, ip, 0xE9);
}
static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
void *old_addr, void *new_addr,
const bool text_live)
{
const u8 *nop_insn = ideal_nops[NOP_ATOMIC5];
u8 old_insn[X86_PATCH_SIZE];
u8 new_insn[X86_PATCH_SIZE];
u8 *prog;
int ret;
memcpy(old_insn, nop_insn, X86_PATCH_SIZE);
if (old_addr) {
prog = old_insn;
ret = t == BPF_MOD_CALL ?
emit_call(&prog, old_addr, ip) :
emit_jump(&prog, old_addr, ip);
if (ret)
return ret;
}
memcpy(new_insn, nop_insn, X86_PATCH_SIZE);
if (new_addr) {
prog = new_insn;
ret = t == BPF_MOD_CALL ?
emit_call(&prog, new_addr, ip) :
emit_jump(&prog, new_addr, ip);
if (ret)
return ret;
}
ret = -EBUSY;
mutex_lock(&text_mutex);
if (memcmp(ip, old_insn, X86_PATCH_SIZE))
goto out;
ret = 1;
if (memcmp(ip, new_insn, X86_PATCH_SIZE)) {
if (text_live)
text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL);
else
memcpy(ip, new_insn, X86_PATCH_SIZE);
ret = 0;
}
out:
mutex_unlock(&text_mutex);
return ret;
}
int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
void *old_addr, void *new_addr)
{
if (!is_kernel_text((long)ip) &&
!is_bpf_text_address((long)ip))
/* BPF poking in modules is not supported */
return -EINVAL;
return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true);
}
static int get_pop_bytes(bool *callee_regs_used)
{
int bytes = 0;
if (callee_regs_used[3])
bytes += 2;
if (callee_regs_used[2])
bytes += 2;
if (callee_regs_used[1])
bytes += 2;
if (callee_regs_used[0])
bytes += 1;
return bytes;
}
/*
* Generate the following code:
*
* ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ...
* if (index >= array->map.max_entries)
* goto out;
* if (++tail_call_cnt > MAX_TAIL_CALL_CNT)
* goto out;
* prog = array->ptrs[index];
* if (prog == NULL)
* goto out;
* goto *(prog->bpf_func + prologue_size);
* out:
*/
static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
u32 stack_depth)
{
int tcc_off = -4 - round_up(stack_depth, 8);
u8 *prog = *pprog;
int pop_bytes = 0;
int off1 = 42;
int off2 = 31;
int off3 = 9;
int cnt = 0;
/* count the additional bytes used for popping callee regs from stack
* that need to be taken into account for each of the offsets that
* are used for bailing out of the tail call
*/
pop_bytes = get_pop_bytes(callee_regs_used);
off1 += pop_bytes;
off2 += pop_bytes;
off3 += pop_bytes;
if (stack_depth) {
off1 += 7;
off2 += 7;
off3 += 7;
}
/*
* rdi - pointer to ctx
* rsi - pointer to bpf_array
* rdx - index in bpf_array
*/
/*
* if (index >= array->map.max_entries)
* goto out;
*/
EMIT2(0x89, 0xD2); /* mov edx, edx */
EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */
offsetof(struct bpf_array, map.max_entries));
#define OFFSET1 (off1 + RETPOLINE_RCX_BPF_JIT_SIZE) /* Number of bytes to jump */
EMIT2(X86_JBE, OFFSET1); /* jbe out */
/*
* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
* goto out;
*/
EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */
EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */
#define OFFSET2 (off2 + RETPOLINE_RCX_BPF_JIT_SIZE)
EMIT2(X86_JA, OFFSET2); /* ja out */
EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */
EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */
/* prog = array->ptrs[index]; */
EMIT4_off32(0x48, 0x8B, 0x8C, 0xD6, /* mov rcx, [rsi + rdx * 8 + offsetof(...)] */
offsetof(struct bpf_array, ptrs));
/*
* if (prog == NULL)
* goto out;
*/
EMIT3(0x48, 0x85, 0xC9); /* test rcx,rcx */
#define OFFSET3 (off3 + RETPOLINE_RCX_BPF_JIT_SIZE)
EMIT2(X86_JE, OFFSET3); /* je out */
*pprog = prog;
pop_callee_regs(pprog, callee_regs_used);
prog = *pprog;
EMIT1(0x58); /* pop rax */
if (stack_depth)
EMIT3_off32(0x48, 0x81, 0xC4, /* add rsp, sd */
round_up(stack_depth, 8));
/* goto *(prog->bpf_func + X86_TAIL_CALL_OFFSET); */
EMIT4(0x48, 0x8B, 0x49, /* mov rcx, qword ptr [rcx + 32] */
offsetof(struct bpf_prog, bpf_func));
EMIT4(0x48, 0x83, 0xC1, /* add rcx, X86_TAIL_CALL_OFFSET */
X86_TAIL_CALL_OFFSET);
/*
* Now we're ready to jump into next BPF program
* rdi == ctx (1st arg)
* rcx == prog->bpf_func + X86_TAIL_CALL_OFFSET
*/
RETPOLINE_RCX_BPF_JIT();
/* out: */
*pprog = prog;
}
static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
u8 **pprog, int addr, u8 *image,
bool *callee_regs_used, u32 stack_depth)
{
int tcc_off = -4 - round_up(stack_depth, 8);
u8 *prog = *pprog;
int pop_bytes = 0;
int off1 = 20;
int poke_off;
int cnt = 0;
/* count the additional bytes used for popping callee regs to stack
* that need to be taken into account for jump offset that is used for
* bailing out from of the tail call when limit is reached
*/
pop_bytes = get_pop_bytes(callee_regs_used);
off1 += pop_bytes;
/*
* total bytes for:
* - nop5/ jmpq $off
* - pop callee regs
* - sub rsp, $val if depth > 0
* - pop rax
*/
poke_off = X86_PATCH_SIZE + pop_bytes + 1;
if (stack_depth) {
poke_off += 7;
off1 += 7;
}
/*
* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
* goto out;
*/
EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */
EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */
EMIT2(X86_JA, off1); /* ja out */
EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */
EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */
poke->tailcall_bypass = image + (addr - poke_off - X86_PATCH_SIZE);
poke->adj_off = X86_TAIL_CALL_OFFSET;
poke->tailcall_target = image + (addr - X86_PATCH_SIZE);
poke->bypass_addr = (u8 *)poke->tailcall_target + X86_PATCH_SIZE;
emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE,
poke->tailcall_bypass);
*pprog = prog;
pop_callee_regs(pprog, callee_regs_used);
prog = *pprog;
EMIT1(0x58); /* pop rax */
if (stack_depth)
EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE);
prog += X86_PATCH_SIZE;
/* out: */
*pprog = prog;
}
static void bpf_tail_call_direct_fixup(struct bpf_prog *prog)
{
struct bpf_jit_poke_descriptor *poke;
struct bpf_array *array;
struct bpf_prog *target;
int i, ret;
for (i = 0; i < prog->aux->size_poke_tab; i++) {
poke = &prog->aux->poke_tab[i];
WARN_ON_ONCE(READ_ONCE(poke->tailcall_target_stable));
if (poke->reason != BPF_POKE_REASON_TAIL_CALL)
continue;
array = container_of(poke->tail_call.map, struct bpf_array, map);
mutex_lock(&array->aux->poke_mutex);
target = array->ptrs[poke->tail_call.key];
if (target) {
/* Plain memcpy is used when image is not live yet
* and still not locked as read-only. Once poke
* location is active (poke->tailcall_target_stable),
* any parallel bpf_arch_text_poke() might occur
* still on the read-write image until we finally
* locked it as read-only. Both modifications on
* the given image are under text_mutex to avoid
* interference.
*/
ret = __bpf_arch_text_poke(poke->tailcall_target,
BPF_MOD_JUMP, NULL,
(u8 *)target->bpf_func +
poke->adj_off, false);
BUG_ON(ret < 0);
ret = __bpf_arch_text_poke(poke->tailcall_bypass,
BPF_MOD_JUMP,
(u8 *)poke->tailcall_target +
X86_PATCH_SIZE, NULL, false);
BUG_ON(ret < 0);
}
WRITE_ONCE(poke->tailcall_target_stable, true);
mutex_unlock(&array->aux->poke_mutex);
}
}
static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
u32 dst_reg, const u32 imm32)
{
u8 *prog = *pprog;
u8 b1, b2, b3;
int cnt = 0;
/*
* Optimization: if imm32 is positive, use 'mov %eax, imm32'
* (which zero-extends imm32) to save 2 bytes.
*/
if (sign_propagate && (s32)imm32 < 0) {
/* 'mov %rax, imm32' sign extends imm32 */
b1 = add_1mod(0x48, dst_reg);
b2 = 0xC7;
b3 = 0xC0;
EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32);
goto done;
}
/*
* Optimization: if imm32 is zero, use 'xor %eax, %eax'
* to save 3 bytes.
*/
if (imm32 == 0) {
if (is_ereg(dst_reg))
EMIT1(add_2mod(0x40, dst_reg, dst_reg));
b2 = 0x31; /* xor */
b3 = 0xC0;
EMIT2(b2, add_2reg(b3, dst_reg, dst_reg));
goto done;
}
/* mov %eax, imm32 */
if (is_ereg(dst_reg))
EMIT1(add_1mod(0x40, dst_reg));
EMIT1_off32(add_1reg(0xB8, dst_reg), imm32);
done:
*pprog = prog;
}
static void emit_mov_imm64(u8 **pprog, u32 dst_reg,
const u32 imm32_hi, const u32 imm32_lo)
{
u8 *prog = *pprog;
int cnt = 0;
if (is_uimm32(((u64)imm32_hi << 32) | (u32)imm32_lo)) {
/*
* For emitting plain u32, where sign bit must not be
* propagated LLVM tends to load imm64 over mov32
* directly, so save couple of bytes by just doing
* 'mov %eax, imm32' instead.
*/
emit_mov_imm32(&prog, false, dst_reg, imm32_lo);
} else {
/* movabsq %rax, imm64 */
EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg));
EMIT(imm32_lo, 4);
EMIT(imm32_hi, 4);
}
*pprog = prog;
}
static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg)
{
u8 *prog = *pprog;
int cnt = 0;
if (is64) {
/* mov dst, src */
EMIT_mov(dst_reg, src_reg);
} else {
/* mov32 dst, src */
if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT1(add_2mod(0x40, dst_reg, src_reg));
EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg));
}
*pprog = prog;
}
/* LDX: dst_reg = *(u8*)(src_reg + off) */
static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
{
u8 *prog = *pprog;
int cnt = 0;
switch (size) {
case BPF_B:
/* Emit 'movzx rax, byte ptr [rax + off]' */
EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6);
break;
case BPF_H:
/* Emit 'movzx rax, word ptr [rax + off]' */
EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7);
break;
case BPF_W:
/* Emit 'mov eax, dword ptr [rax+0x14]' */
if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B);
else
EMIT1(0x8B);
break;
case BPF_DW:
/* Emit 'mov rax, qword ptr [rax+0x14]' */
EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B);
break;
}
/*
* If insn->off == 0 we can save one extra byte, but
* special case of x86 R13 which always needs an offset
* is not worth the hassle
*/
if (is_imm8(off))
EMIT2(add_2reg(0x40, src_reg, dst_reg), off);
else
EMIT1_off32(add_2reg(0x80, src_reg, dst_reg), off);
*pprog = prog;
}
/* STX: *(u8*)(dst_reg + off) = src_reg */
static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
{
u8 *prog = *pprog;
int cnt = 0;
switch (size) {
case BPF_B:
/* Emit 'mov byte ptr [rax + off], al' */
if (is_ereg(dst_reg) || is_ereg_8l(src_reg))
/* Add extra byte for eregs or SIL,DIL,BPL in src_reg */
EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88);
else
EMIT1(0x88);
break;
case BPF_H:
if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT3(0x66, add_2mod(0x40, dst_reg, src_reg), 0x89);
else
EMIT2(0x66, 0x89);
break;
case BPF_W:
if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x89);
else
EMIT1(0x89);
break;
case BPF_DW:
EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89);
break;
}
if (is_imm8(off))
EMIT2(add_2reg(0x40, dst_reg, src_reg), off);
else
EMIT1_off32(add_2reg(0x80, dst_reg, src_reg), off);
*pprog = prog;
}
static bool ex_handler_bpf(const struct exception_table_entry *x,
struct pt_regs *regs, int trapnr,
unsigned long error_code, unsigned long fault_addr)
{
u32 reg = x->fixup >> 8;
/* jump over faulting load and clear dest register */
*(unsigned long *)((void *)regs + reg) = 0;
regs->ip += x->fixup & 0xff;
return true;
}
static void detect_reg_usage(struct bpf_insn *insn, int insn_cnt,
bool *regs_used, bool *tail_call_seen)
{
int i;
for (i = 1; i <= insn_cnt; i++, insn++) {
if (insn->code == (BPF_JMP | BPF_TAIL_CALL))
*tail_call_seen = true;
if (insn->dst_reg == BPF_REG_6 || insn->src_reg == BPF_REG_6)
regs_used[0] = true;
if (insn->dst_reg == BPF_REG_7 || insn->src_reg == BPF_REG_7)
regs_used[1] = true;
if (insn->dst_reg == BPF_REG_8 || insn->src_reg == BPF_REG_8)
regs_used[2] = true;
if (insn->dst_reg == BPF_REG_9 || insn->src_reg == BPF_REG_9)
regs_used[3] = true;
}
}
static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
int oldproglen, struct jit_context *ctx)
{
bool tail_call_reachable = bpf_prog->aux->tail_call_reachable;
struct bpf_insn *insn = bpf_prog->insnsi;
bool callee_regs_used[4] = {};
int insn_cnt = bpf_prog->len;
bool tail_call_seen = false;
bool seen_exit = false;
u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
int i, cnt = 0, excnt = 0;
int proglen = 0;
u8 *prog = temp;
detect_reg_usage(insn, insn_cnt, callee_regs_used,
&tail_call_seen);
/* tail call's presence in current prog implies it is reachable */
tail_call_reachable |= tail_call_seen;
emit_prologue(&prog, bpf_prog->aux->stack_depth,
bpf_prog_was_classic(bpf_prog), tail_call_reachable,
bpf_prog->aux->func_idx != 0);
push_callee_regs(&prog, callee_regs_used);
addrs[0] = prog - temp;
for (i = 1; i <= insn_cnt; i++, insn++) {
const s32 imm32 = insn->imm;
u32 dst_reg = insn->dst_reg;
u32 src_reg = insn->src_reg;
u8 b2 = 0, b3 = 0;
s64 jmp_offset;
u8 jmp_cond;
int ilen;
u8 *func;
switch (insn->code) {
/* ALU */
case BPF_ALU | BPF_ADD | BPF_X:
case BPF_ALU | BPF_SUB | BPF_X:
case BPF_ALU | BPF_AND | BPF_X:
case BPF_ALU | BPF_OR | BPF_X:
case BPF_ALU | BPF_XOR | BPF_X:
case BPF_ALU64 | BPF_ADD | BPF_X:
case BPF_ALU64 | BPF_SUB | BPF_X:
case BPF_ALU64 | BPF_AND | BPF_X:
case BPF_ALU64 | BPF_OR | BPF_X:
case BPF_ALU64 | BPF_XOR | BPF_X:
switch (BPF_OP(insn->code)) {
case BPF_ADD: b2 = 0x01; break;
case BPF_SUB: b2 = 0x29; break;
case BPF_AND: b2 = 0x21; break;
case BPF_OR: b2 = 0x09; break;
case BPF_XOR: b2 = 0x31; break;
}
if (BPF_CLASS(insn->code) == BPF_ALU64)
EMIT1(add_2mod(0x48, dst_reg, src_reg));
else if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT1(add_2mod(0x40, dst_reg, src_reg));
EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg));
break;
case BPF_ALU64 | BPF_MOV | BPF_X:
case BPF_ALU | BPF_MOV | BPF_X:
emit_mov_reg(&prog,
BPF_CLASS(insn->code) == BPF_ALU64,
dst_reg, src_reg);
break;
/* neg dst */
case BPF_ALU | BPF_NEG:
case BPF_ALU64 | BPF_NEG:
if (BPF_CLASS(insn->code) == BPF_ALU64)
EMIT1(add_1mod(0x48, dst_reg));
else if (is_ereg(dst_reg))
EMIT1(add_1mod(0x40, dst_reg));
EMIT2(0xF7, add_1reg(0xD8, dst_reg));
break;
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_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:
if (BPF_CLASS(insn->code) == BPF_ALU64)
EMIT1(add_1mod(0x48, dst_reg));
else if (is_ereg(dst_reg))
EMIT1(add_1mod(0x40, dst_reg));
/*
* b3 holds 'normal' opcode, b2 short form only valid
* in case dst is eax/rax.
*/
switch (BPF_OP(insn->code)) {
case BPF_ADD:
b3 = 0xC0;
b2 = 0x05;
break;
case BPF_SUB:
b3 = 0xE8;
b2 = 0x2D;
break;
case BPF_AND:
b3 = 0xE0;
b2 = 0x25;
break;
case BPF_OR:
b3 = 0xC8;
b2 = 0x0D;
break;
case BPF_XOR:
b3 = 0xF0;
b2 = 0x35;
break;
}
if (is_imm8(imm32))
EMIT3(0x83, add_1reg(b3, dst_reg), imm32);
else if (is_axreg(dst_reg))
EMIT1_off32(b2, imm32);
else
EMIT2_off32(0x81, add_1reg(b3, dst_reg), imm32);
break;
case BPF_ALU64 | BPF_MOV | BPF_K:
case BPF_ALU | BPF_MOV | BPF_K:
emit_mov_imm32(&prog, BPF_CLASS(insn->code) == BPF_ALU64,
dst_reg, imm32);
break;
case BPF_LD | BPF_IMM | BPF_DW:
emit_mov_imm64(&prog, dst_reg, insn[1].imm, insn[0].imm);
insn++;
i++;
break;
/* dst %= src, dst /= src, dst %= imm32, dst /= imm32 */
case BPF_ALU | BPF_MOD | BPF_X:
case BPF_ALU | BPF_DIV | BPF_X:
case BPF_ALU | BPF_MOD | BPF_K:
case BPF_ALU | BPF_DIV | BPF_K:
case BPF_ALU64 | BPF_MOD | BPF_X:
case BPF_ALU64 | BPF_DIV | BPF_X:
case BPF_ALU64 | BPF_MOD | BPF_K:
case BPF_ALU64 | BPF_DIV | BPF_K:
EMIT1(0x50); /* push rax */
EMIT1(0x52); /* push rdx */
if (BPF_SRC(insn->code) == BPF_X)
/* mov r11, src_reg */
EMIT_mov(AUX_REG, src_reg);
else
/* mov r11, imm32 */
EMIT3_off32(0x49, 0xC7, 0xC3, imm32);
/* mov rax, dst_reg */
EMIT_mov(BPF_REG_0, dst_reg);
/*
* xor edx, edx
* equivalent to 'xor rdx, rdx', but one byte less
*/
EMIT2(0x31, 0xd2);
if (BPF_CLASS(insn->code) == BPF_ALU64)
/* div r11 */
EMIT3(0x49, 0xF7, 0xF3);
else
/* div r11d */
EMIT3(0x41, 0xF7, 0xF3);
if (BPF_OP(insn->code) == BPF_MOD)
/* mov r11, rdx */
EMIT3(0x49, 0x89, 0xD3);
else
/* mov r11, rax */
EMIT3(0x49, 0x89, 0xC3);
EMIT1(0x5A); /* pop rdx */
EMIT1(0x58); /* pop rax */
/* mov dst_reg, r11 */
EMIT_mov(dst_reg, AUX_REG);
break;
case BPF_ALU | BPF_MUL | BPF_K:
case BPF_ALU | BPF_MUL | BPF_X:
case BPF_ALU64 | BPF_MUL | BPF_K:
case BPF_ALU64 | BPF_MUL | BPF_X:
{
bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
if (dst_reg != BPF_REG_0)
EMIT1(0x50); /* push rax */
if (dst_reg != BPF_REG_3)
EMIT1(0x52); /* push rdx */
/* mov r11, dst_reg */
EMIT_mov(AUX_REG, dst_reg);
if (BPF_SRC(insn->code) == BPF_X)
emit_mov_reg(&prog, is64, BPF_REG_0, src_reg);
else
emit_mov_imm32(&prog, is64, BPF_REG_0, imm32);