summaryrefslogtreecommitdiff
path: root/arch/x86/net/bpf_jit_comp.c
blob: 2e586f5799453f8f6fdbae197460c19f2e348e55 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
// SPDX-License-Identifier: GPL-2.0-only
/*
 * bpf_jit_comp.c: BPF JIT compiler
 *
 * Copyright (C) 2011-2013 Eric Dumazet (eric.dumazet@gmail.com)
 * 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 <asm/extable.h>
#include <asm/set_memory.h>
#include <asm/nospec-branch.h>
#include <asm/text-patching.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));
}

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_call() needs to generate call instruction */
#define X86_CALL_SIZE		5

#define PROLOGUE_SIZE		25

/*
 * Emit x86-64 prologue code for BPF program and check its size.
 * bpf_tail_call helper will skip it while jumping into another program
 */
static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
{
	u8 *prog = *pprog;
	int cnt = X86_CALL_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;
	EMIT1(0x55);             /* push rbp */
	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
	/* sub rsp, rounded_stack_depth */
	EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8));
	EMIT1(0x53);             /* push rbx */
	EMIT2(0x41, 0x55);       /* push r13 */
	EMIT2(0x41, 0x56);       /* push r14 */
	EMIT2(0x41, 0x57);       /* push r15 */
	if (!ebpf_from_cbpf) {
		/* zero init tail_call_cnt */
		EMIT2(0x6a, 0x00);
		BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
	}
	*pprog = prog;
}

/*
 * 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(u8 **pprog)
{
	u8 *prog = *pprog;
	int label1, label2, label3;
	int cnt = 0;

	/*
	 * 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 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* Number of bytes to jump */
	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
	label1 = cnt;

	/*
	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
	 *	goto out;
	 */
	EMIT2_off32(0x8B, 0x85, -36 - MAX_BPF_STACK); /* mov eax, dword ptr [rbp - 548] */
	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
#define OFFSET2 (30 + RETPOLINE_RAX_BPF_JIT_SIZE)
	EMIT2(X86_JA, OFFSET2);                   /* ja out */
	label2 = cnt;
	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
	EMIT2_off32(0x89, 0x85, -36 - MAX_BPF_STACK); /* mov dword ptr [rbp -548], eax */

	/* prog = array->ptrs[index]; */
	EMIT4_off32(0x48, 0x8B, 0x84, 0xD6,       /* mov rax, [rsi + rdx * 8 + offsetof(...)] */
		    offsetof(struct bpf_array, ptrs));

	/*
	 * if (prog == NULL)
	 *	goto out;
	 */
	EMIT3(0x48, 0x85, 0xC0);		  /* test rax,rax */
#define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE)
	EMIT2(X86_JE, OFFSET3);                   /* je out */
	label3 = cnt;

	/* goto *(prog->bpf_func + prologue_size); */
	EMIT4(0x48, 0x8B, 0x40,                   /* mov rax, qword ptr [rax + 32] */
	      offsetof(struct bpf_prog, bpf_func));
	EMIT4(0x48, 0x83, 0xC0, PROLOGUE_SIZE);   /* add rax, prologue_size */

	/*
	 * Wow we're ready to jump into next BPF program
	 * rdi == ctx (1st arg)
	 * rax == prog->bpf_func + prologue_size
	 */
	RETPOLINE_RAX_BPF_JIT();

	/* out: */
	BUILD_BUG_ON(cnt - label1 != OFFSET1);
	BUILD_BUG_ON(cnt - label2 != OFFSET2);
	BUILD_BUG_ON(cnt - label3 != OFFSET3);
	*pprog = prog;
}

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(src_reg) ||
		    /* We have to add extra byte for x86 SIL, DIL regs */
		    src_reg == BPF_REG_1 || src_reg == BPF_REG_2)
			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 int emit_call(u8 **pprog, void *func, void *ip)
{
	u8 *prog = *pprog;
	int cnt = 0;
	s64 offset;

	offset = func - (ip + X86_CALL_SIZE);
	if (!is_simm32(offset)) {
		pr_err("Target call %p is out of range\n", func);
		return -EINVAL;
	}
	EMIT1_off32(0xE8, offset);
	*pprog = prog;
	return 0;
}

int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
		       void *old_addr, void *new_addr)
{
	u8 old_insn[X86_CALL_SIZE] = {};
	u8 new_insn[X86_CALL_SIZE] = {};
	u8 *prog;
	int ret;

	if (!is_kernel_text((long)ip) &&
	    !is_bpf_text_address((long)ip))
		/* BPF trampoline in modules is not supported */
		return -EINVAL;

	if (old_addr) {
		prog = old_insn;
		ret = emit_call(&prog, old_addr, (void *)ip);
		if (ret)
			return ret;
	}
	if (new_addr) {
		prog = new_insn;
		ret = emit_call(&prog, new_addr, (void *)ip);
		if (ret)
			return ret;
	}
	ret = -EBUSY;
	mutex_lock(&text_mutex);
	switch (t) {
	case BPF_MOD_NOP_TO_CALL:
		if (memcmp(ip, ideal_nops[NOP_ATOMIC5], X86_CALL_SIZE))
			goto out;
		text_poke_bp(ip, new_insn, X86_CALL_SIZE, NULL);
		break;
	case BPF_MOD_CALL_TO_CALL:
		if (memcmp(ip, old_insn, X86_CALL_SIZE))
			goto out;
		text_poke_bp(ip, new_insn, X86_CALL_SIZE, NULL);
		break;
	case BPF_MOD_CALL_TO_NOP:
		if (memcmp(ip, old_insn, X86_CALL_SIZE))
			goto out;
		text_poke_bp(ip, ideal_nops[NOP_ATOMIC5], X86_CALL_SIZE, NULL);
		break;
	}
	ret = 0;
out:
	mutex_unlock(&text_mutex);
	return ret;
}

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 int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
		  int oldproglen, struct jit_context *ctx)
{
	struct bpf_insn *insn = bpf_prog->insnsi;
	int insn_cnt = bpf_prog->len;
	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;

	emit_prologue(&prog, bpf_prog->aux->stack_depth,
		      bpf_prog_was_classic(bpf_prog));
	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);

			if (is64)
				EMIT1(add_1mod(0x48, AUX_REG));
			else if (is_ereg(AUX_REG))
				EMIT1(add_1mod(0x40, AUX_REG));
			/* mul(q) r11 */
			EMIT2(0xF7, add_1reg(0xE0, AUX_REG));

			if (dst_reg != BPF_REG_3)
				EMIT1(0x5A); /* pop rdx */
			if (dst_reg != BPF_REG_0) {
				/* mov dst_reg, rax */
				EMIT_mov(dst_reg, BPF_REG_0);
				EMIT1(0x58); /* pop rax */
			}
			break;
		}
			/* Shifts */
		case BPF_ALU | BPF_LSH | BPF_K:
		case BPF_ALU | BPF_RSH | BPF_K:
		case BPF_ALU | BPF_ARSH | BPF_K:
		case BPF_ALU64 | BPF_LSH | BPF_K:
		case BPF_ALU64 | BPF_RSH | BPF_K:
		case BPF_ALU64 | BPF_ARSH | 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));

			switch (BPF_OP(insn->code)) {
			case BPF_LSH: b3 = 0xE0; break;
			case BPF_RSH: b3 = 0xE8; break;
			case BPF_ARSH: b3 = 0xF8; break;
			}

			if (imm32 == 1)
				EMIT2(0xD1, add_1reg(b3, dst_reg));
			else
				EMIT3(0xC1, add_1reg(b3, dst_reg), imm32);
			break;

		case BPF_ALU | BPF_LSH | BPF_X:
		case BPF_ALU | BPF_RSH | BPF_X:
		case BPF_ALU | BPF_ARSH | BPF_X:
		case BPF_ALU64 | BPF_LSH | BPF_X:
		case BPF_ALU64 | BPF_RSH | BPF_X:
		case BPF_ALU64 | BPF_ARSH | BPF_X:

			/* Check for bad case when dst_reg == rcx */
			if (dst_reg == BPF_REG_4) {
				/* mov r11, dst_reg */
				EMIT_mov(AUX_REG, dst_reg);
				dst_reg = AUX_REG;
			}

			if (src_reg != BPF_REG_4) { /* common case */
				EMIT1(0x51); /* push rcx */

				/* mov rcx, src_reg */
				EMIT_mov(BPF_REG_4, src_reg);
			}

			/* shl %rax, %cl | shr %rax, %cl | sar %rax, %cl */
			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));

			switch (BPF_OP(insn->code)) {
			case BPF_LSH: b3 = 0xE0; break;
			case BPF_RSH: b3 = 0xE8; break;
			case BPF_ARSH: b3 = 0xF8; break;
			}
			EMIT2(0xD3, add_1reg(b3, dst_reg));

			if (src_reg != BPF_REG_4)
				EMIT1(0x59); /* pop rcx */

			if (insn->dst_reg == BPF_REG_4)
				/* mov dst_reg, r11 */
				EMIT_mov(insn->dst_reg, AUX_REG);
			break;

		case BPF_ALU | BPF_END | BPF_FROM_BE:
			switch (imm32) {
			case 16:
				/* Emit 'ror %ax, 8' to swap lower 2 bytes */
				EMIT1(0x66);
				if (is_ereg(dst_reg))
					EMIT1(0x41);
				EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8);

				/* Emit 'movzwl eax, ax' */
				if (is_ereg(dst_reg))
					EMIT3(0x45, 0x0F, 0xB7);
				else
					EMIT2(0x0F, 0xB7);
				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
				break;
			case 32:
				/* Emit 'bswap eax' to swap lower 4 bytes */
				if (is_ereg(dst_reg))
					EMIT2(0x41, 0x0F);
				else
					EMIT1(0x0F);
				EMIT1(add_1reg(0xC8, dst_reg));
				break;
			case 64:
				/* Emit 'bswap rax' to swap 8 bytes */
				EMIT3(add_1mod(0x48, dst_reg), 0x0F,
				      add_1reg(0xC8, dst_reg));
				break;
			}
			break;

		case BPF_ALU | BPF_END | BPF_FROM_LE:
			switch (imm32) {
			case 16:
				/*
				 * Emit 'movzwl eax, ax' to zero extend 16-bit
				 * into 64 bit
				 */
				if (is_ereg(dst_reg))
					EMIT3(0x45, 0x0F, 0xB7);
				else
					EMIT2(0x0F, 0xB7);
				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
				break;
			case 32:
				/* Emit 'mov eax, eax' to clear upper 32-bits */
				if (is_ereg(dst_reg))
					EMIT1(0x45);
				EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg));
				break;
			case 64:
				/* nop */
				break;
			}
			break;

			/* ST: *(u8*)(dst_reg + off) = imm */
		case BPF_ST | BPF_MEM | BPF_B:
			if (is_ereg(dst_reg))
				EMIT2(0x41, 0xC6);
			else
				EMIT1(0xC6);
			goto st;
		case BPF_ST | BPF_MEM | BPF_H:
			if (is_ereg(dst_reg))
				EMIT3(0x66, 0x41, 0xC7);
			else
				EMIT2(0x66, 0xC7);
			goto st;
		case BPF_ST | BPF_MEM | BPF_W:
			if (is_ereg(dst_reg))
				EMIT2(0x41, 0xC7);
			else
				EMIT1(0xC7);
			goto st;
		case BPF_ST | BPF_MEM | BPF_DW:
			EMIT2(add_1mod(0x48, dst_reg), 0xC7);

st:			if (is_imm8(insn->off))
				EMIT2(add_1reg(0x40, dst_reg), insn->off);
			else
				EMIT1_off32(add_1reg(0x80, dst_reg), insn->off);

			EMIT(imm32, bpf_size_to_x86_bytes(BPF_SIZE(insn->code)));
			break;

			/* STX: *(u8*)(dst_reg + off) = src_reg */
		case BPF_STX | BPF_MEM | BPF_B:
		case BPF_STX | BPF_MEM | BPF_H:
		case BPF_STX | BPF_MEM | BPF_W:
		case BPF_STX | BPF_MEM | BPF_DW:
			emit_stx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off);
			break;

			/* LDX: dst_reg = *(u8*)(src_reg + off) */
		case BPF_LDX | BPF_MEM | BPF_B:
		case BPF_LDX | BPF_PROBE_MEM | BPF_B:
		case BPF_LDX | BPF_MEM | BPF_H:
		case BPF_LDX | BPF_PROBE_MEM | BPF_H:
		case BPF_LDX | BPF_MEM | BPF_W:
		case BPF_LDX | BPF_PROBE_MEM | BPF_W:
		case BPF_LDX | BPF_MEM | BPF_DW:
		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
			emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off);
			if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
				struct exception_table_entry *ex;
				u8 *_insn = image + proglen;
				s64 delta;

				if (!bpf_prog->aux->extable)
					break;

				if (excnt >= bpf_prog->aux->num_exentries) {
					pr_err("ex gen bug\n");
					return -EFAULT;
				}
				ex = &bpf_prog->aux->extable[excnt++];

				delta = _insn - (u8 *)&ex->insn;
				if (!is_simm32(delta)) {
					pr_err("extable->insn doesn't fit into 32-bit\n");
					return -EFAULT;
				}
				ex->insn = delta;

				delta = (u8 *)ex_handler_bpf - (u8 *)&ex->handler;
				if (!is_simm32(delta)) {
					pr_err("extable->handler doesn't fit into 32-bit\n");
					return -EFAULT;
				}
				ex->handler = delta;

				if (dst_reg > BPF_REG_9) {
					pr_err("verifier error\n");
					return -EFAULT;
				}
				/*
				 * Compute size of x86 insn and its target dest x86 register.
				 * ex_handler_bpf() will use lower 8 bits to adjust
				 * pt_regs->ip to jump over this x86 instruction
				 * and upper bits to figure out which pt_regs to zero out.
				 * End result: x86 insn "mov rbx, qword ptr [rax+0x14]"
				 * of 4 bytes will be ignored and rbx will be zero inited.
				 */
				ex->fixup = (prog - temp) | (reg2pt_regs[dst_reg] << 8);
			}
			break;

			/* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */
		case BPF_STX | BPF_XADD | BPF_W:
			/* Emit 'lock add dword ptr [rax + off], eax' */
			if (is_ereg(dst_reg) || is_ereg(src_reg))
				EMIT3(0xF0, add_2mod(0x40, dst_reg, src_reg), 0x01);
			else
				EMIT2(0xF0, 0x01);
			goto xadd;
		case BPF_STX | BPF_XADD | BPF_DW:
			EMIT3(0xF0, add_2mod(0x48, dst_reg, src_reg), 0x01);
xadd:			if (is_imm8(insn->off))
				EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off);
			else
				EMIT1_off32(add_2reg(0x80, dst_reg, src_reg),
					    insn->off);
			break;

			/* call */
		case BPF_JMP | BPF_CALL:
			func = (u8 *) __bpf_call_base + imm32;
			if (!imm32 || emit_call(&prog, func, image + addrs[i - 1]))
				return -EINVAL;
			break;

		case BPF_JMP | BPF_TAIL_CALL:
			emit_bpf_tail_call(&prog);
			break;

			/* cond jump */
		case BPF_JMP | BPF_JEQ | BPF_X:
		case BPF_JMP | BPF_JNE | BPF_X:
		case BPF_JMP | BPF_JGT | BPF_X:
		case BPF_JMP | BPF_JLT | BPF_X:
		case BPF_JMP | BPF_JGE | BPF_X:
		case BPF_JMP | BPF_JLE | BPF_X:
		case BPF_JMP | BPF_JSGT | BPF_X:
		case BPF_JMP | BPF_JSLT | BPF_X:
		case BPF_JMP | BPF_JSGE | BPF_X:
		case BPF_JMP | BPF_JSLE | BPF_X:
		case BPF_JMP32 | BPF_JEQ | BPF_X:
		case BPF_JMP32 | BPF_JNE | BPF_X:
		case BPF_JMP32 | BPF_JGT | BPF_X:
		case BPF_JMP32 | BPF_JLT | BPF_X:
		case BPF_JMP32 | BPF_JGE | BPF_X:
		case BPF_JMP32 | BPF_JLE | BPF_X:
		case BPF_JMP32 | BPF_JSGT | BPF_X:
		case BPF_JMP32 | BPF_JSLT | BPF_X:
		case BPF_JMP32 | BPF_JSGE | BPF_X:
		case BPF_JMP32 | BPF_JSLE | BPF_X:
			/* cmp dst_reg, src_reg */
			if (BPF_CLASS(insn->code) == BPF_JMP)
				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(0x39, add_2reg(0xC0, dst_reg, src_reg));
			goto emit_cond_jmp;

		case BPF_JMP | BPF_JSET | BPF_X:
		case BPF_JMP32 | BPF_JSET | BPF_X:
			/* test dst_reg, src_reg */
			if (BPF_CLASS(insn->code) == BPF_JMP)
				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(0x85, add_2reg(0xC0, dst_reg, src_reg));
			goto emit_cond_jmp;

		case BPF_JMP | BPF_JSET | BPF_K:
		case BPF_JMP32 | BPF_JSET | BPF_K:
			/* test dst_reg, imm32 */
			if (BPF_CLASS(insn->code) == BPF_JMP)
				EMIT1(add_1mod(0x48, dst_reg));
			else if (is_ereg(dst_reg))
				EMIT1(add_1mod(0x40, dst_reg));
			EMIT2_off32(0xF7, add_1reg(0xC0, dst_reg), imm32);
			goto emit_cond_jmp;

		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_JMP32 | BPF_JEQ | BPF_K:
		case BPF_JMP32 | BPF_JNE | BPF_K:
		case BPF_JMP32 | BPF_JGT | BPF_K:
		case BPF_JMP32 | BPF_JLT | BPF_K:
		case BPF_JMP32 | BPF_JGE | BPF_K:
		case BPF_JMP32 | BPF_JLE | BPF_K:
		case BPF_JMP32 | BPF_JSGT | BPF_K:
		case BPF_JMP32 | BPF_JSLT | BPF_K:
		case BPF_JMP32 | BPF_JSGE | BPF_K:
		case BPF_JMP32 | BPF_JSLE | BPF_K:
			/* test dst_reg, dst_reg to save one extra byte */
			if (imm32 == 0) {
				if (BPF_CLASS(insn->code) == BPF_JMP)
					EMIT1(add_2mod(0x48, dst_reg, dst_reg));
				else if (is_ereg(dst_reg))
					EMIT1(add_2mod(0x40, dst_reg, dst_reg));
				EMIT2(0x85, add_2reg(0xC0, dst_reg, dst_reg));
				goto emit_cond_jmp;
			}

			/* cmp dst_reg, imm8/32 */
			if (BPF_CLASS(insn->code) == BPF_JMP)
				EMIT1(add_1mod(0x48, dst_reg));
			else if (is_ereg(dst_reg))
				EMIT1(add_1mod(0x40, dst_reg));

			if (is_imm8(imm32))
				EMIT3(0x83, add_1reg(0xF8, dst_reg), imm32);
			else
				EMIT2_off32(0x81, add_1reg(0xF8, dst_reg), imm32);

emit_cond_jmp:		/* Convert BPF opcode to x86 */
			switch (BPF_OP(insn->code)) {
			case BPF_JEQ:
				jmp_cond = X86_JE;
				break;
			case BPF_JSET:
			case BPF_JNE:
				jmp_cond = X86_JNE;
				break;
			case BPF_JGT:
				/* GT is unsigned '>', JA in x86 */
				jmp_cond = X86_JA;
				break;
			case BPF_JLT:
				/* LT is unsigned '<', JB in x86 */
				jmp_cond = X86_JB;
				break;
			case BPF_JGE:
				/* GE is unsigned '>=', JAE in x86 */
				jmp_cond = X86_JAE;
				break;
			case BPF_JLE:
				/* LE is unsigned '<=', JBE in x86 */
				jmp_cond = X86_JBE;
				break;
			case BPF_JSGT:
				/* Signed '>', GT in x86 */
				jmp_cond = X86_JG;
				break;
			case BPF_JSLT:
				/* Signed '<', LT in x86 */
				jmp_cond = X86_JL;
				break;
			case BPF_JSGE:
				/* Signed '>=', GE in x86 */
				jmp_cond = X86_JGE;
				break;
			case BPF_JSLE:
				/* Signed '<=', LE in x86 */
				jmp_cond = X86_JLE;
				break;
			default: /* to silence GCC warning */
				return -EFAULT;
			}
			jmp_offset = addrs[i + insn->off] - addrs[i];
			if (is_imm8(jmp_offset)) {
				EMIT2(jmp_cond, jmp_offset);
			} else if (is_simm32(jmp_offset)) {
				EMIT2_off32(0x0F, jmp_cond + 0x10, jmp_offset);
			} else {
				pr_err("cond_jmp gen bug %llx\n", jmp_offset);
				return -EFAULT;
			}

			break;

		case BPF_JMP | BPF_JA:
			if (insn->off == -1)
				/* -1 jmp instructions will always jump
				 * backwards two bytes. Explicitly handling
				 * this case avoids wasting too many passes
				 * when there are long sequences of replaced
				 * dead code.
				 */
				jmp_offset = -2;
			else
				jmp_offset = addrs[i + insn->off] - addrs[i];

			if (!jmp_offset)
				/* Optimize out nop jumps */
				break;
emit_jmp:
			if (is_imm8(jmp_offset)) {
				EMIT2(0xEB, jmp_offset);
			} else if (is_simm32(jmp_offset)) {
				EMIT1_off32(0xE9, jmp_offset);
			} else {
				pr_err("jmp gen bug %llx\n", jmp_offset);
				return -EFAULT;
			}
			break;

		case BPF_JMP | BPF_EXIT:
			if (seen_exit) {
				jmp_offset = ctx->cleanup_addr - addrs[i];
				goto emit_jmp;
			}
			seen_exit = true;
			/* Update cleanup_addr */
			ctx->cleanup_addr = proglen;
			if (!bpf_prog_was_classic(bpf_prog))
				EMIT1(0x5B); /* get rid of tail_call_cnt */
			EMIT2(0x41, 0x5F);   /* pop r15 */
			EMIT2(0x41, 0x5E);   /* pop r14 */
			EMIT2(0x41, 0x5D);   /* pop r13 */
			EMIT1(0x5B);         /* pop rbx */
			EMIT1(0xC9);         /* leave */
			EMIT1(0xC3);         /* ret */
			break;

		default:
			/*
			 * By design x86-64 JIT should support all BPF instructions.
			 * This error will be seen if new instruction was added
			 * to the interpreter, but not to the JIT, or if there is
			 * junk in bpf_prog.
			 */
			pr_err("bpf_jit: unknown opcode %02x\n", insn->code);
			return -EINVAL;
		}

		ilen = prog - temp;
		if (ilen > BPF_MAX_INSN_SIZE) {
			pr_err("bpf_jit: fatal insn size error\n");
			return -EFAULT;
		}

		if (image) {
			if (unlikely(proglen + ilen > oldproglen)) {
				pr_err("bpf_jit: fatal error\n");
				return -EFAULT;
			}
			memcpy(image + proglen, temp, ilen);
		}
		proglen += ilen;
		addrs[i] = proglen;
		prog = temp;
	}

	if (image && excnt != bpf_prog->aux->num_exentries) {
		pr_err("extable is not populated\n");
		return -EFAULT;
	}
	return proglen;
}

static void save_regs(struct btf_func_model *m, u8 **prog, int nr_args,
		      int stack_size)
{
	int i;
	/* Store function arguments to stack.
	 * For a function that accepts two pointers the sequence will be:
	 * mov QWORD PTR [rbp-0x10],rdi
	 * mov QWORD PTR [rbp-0x8],rsi
	 */
	for (i = 0; i < min(nr_args, 6); i++)
		emit_stx(prog, bytes_to_bpf_size(m->arg_size[i]),
			 BPF_REG_FP,
			 i == 5 ? X86_REG_R9 : BPF_REG_1 + i,
			 -(stack_size - i * 8));
}

static void restore_regs(struct btf_func_model *m, u8 **prog, int nr_args,
			 int stack_size)
{
	int i;

	/* Restore function arguments from stack.
	 * For a function that accepts two pointers the sequence will be:
	 * EMIT4(0x48, 0x8B, 0x7D, 0xF0); mov rdi,QWORD PTR [rbp-0x10]
	 * EMIT4(0x48, 0x8B, 0x75, 0xF8); mov rsi,QWORD PTR [rbp-0x8]
	 */
	for (i = 0; i < min(nr_args, 6); i++)
		emit_ldx(prog, bytes_to_bpf_size(m->arg_size[i]),
			 i == 5 ? X86_REG_R9 : BPF_REG_1 + i,
			 BPF_REG_FP,
			 -(stack_size - i * 8));
}

static int invoke_bpf(struct btf_func_model *m, u8 **pprog,
		      struct bpf_prog **progs, int prog_cnt, int stack_size)
{
	u8 *prog = *pprog;
	int cnt = 0, i;

	for (i = 0; i < prog_cnt; i++) {
		if (emit_call(&prog, __bpf_prog_enter, prog))
			return -EINVAL;
		/* remember prog start time returned by __bpf_prog_enter */
		emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);

		/* arg1: lea rdi, [rbp - stack_size] */
		EMIT4(0x48, 0x8D, 0x7D, -stack_size);
		/* arg2: progs[i]->insnsi for interpreter */
		if (!progs[i]->jited)
			emit_mov_imm64(&prog, BPF_REG_2,
				       (long) progs[i]->insnsi >> 32,
				       (u32) (long) progs[i]->insnsi);
		/* call JITed bpf program or interpreter */
		if (emit_call(&prog, progs[i]->bpf_func, prog))
			return -EINVAL;

		/* arg1: mov rdi, progs[i] */
		emit_mov_imm64(&prog, BPF_REG_1, (long) progs[i] >> 32,
			       (u32) (long) progs[i]);
		/* arg2: mov rsi, rbx <- start time in nsec */
		emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
		if (emit_call(&prog, __bpf_prog_exit, prog))
			return -EINVAL;
	}
	*pprog = prog;
	return 0;
}

/* Example:
 * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
 * its 'struct btf_func_model' will be nr_args=2
 * The assembly code when eth_type_trans is executing after trampoline:
 *
 * push rbp
 * mov rbp, rsp
 * sub rsp, 16                     // space for skb and dev
 * push rbx                        // temp regs to pass start time
 * mov qword ptr [rbp - 16], rdi   // save skb pointer to stack
 * mov qword ptr [rbp - 8], rsi    // save dev pointer to stack
 * call __bpf_prog_enter           // rcu_read_lock and preempt_disable
 * mov rbx, rax                    // remember start time in bpf stats are enabled
 * lea rdi, [rbp - 16]             // R1==ctx of bpf prog
 * call addr_of_jited_FENTRY_prog
 * movabsq rdi, 64bit_addr_of_struct_bpf_prog  // unused if bpf stats are off
 * mov rsi, rbx                    // prog start time
 * call __bpf_prog_exit            // rcu_read_unlock, preempt_enable and stats math
 * mov rdi, qword ptr [rbp - 16]   // restore skb pointer from stack
 * mov rsi, qword ptr [rbp - 8]    // restore dev pointer from stack
 * pop rbx
 * leave
 * ret
 *
 * eth_type_trans has 5 byte nop at the beginning. These 5 bytes will be
 * replaced with 'call generated_bpf_trampoline'. When it returns
 * eth_type_trans will continue executing with original skb and dev pointers.
 *
 * The assembly code when eth_type_trans is called from trampoline:
 *
 * push rbp
 * mov rbp, rsp
 * sub rsp, 24                     // space for skb, dev, return value
 * push rbx                        // temp regs to pass start time
 * mov qword ptr [rbp - 24], rdi   // save skb pointer to stack
 * mov qword ptr [rbp - 16], rsi   // save dev pointer to stack
 * call __bpf_prog_enter           // rcu_read_lock and preempt_disable
 * mov rbx, rax                    // remember start time if bpf stats are enabled
 * lea rdi, [rbp - 24]             // R1==ctx of bpf prog
 * call addr_of_jited_FENTRY_prog  // bpf prog can access skb and dev
 * movabsq rdi, 64bit_addr_of_struct_bpf_prog  // unused if bpf stats are off
 * mov rsi, rbx                    // prog start time
 * call __bpf_prog_exit            // rcu_read_unlock, preempt_enable and stats math
 * mov rdi, qword ptr [rbp - 24]   // restore skb pointer from stack
 * mov rsi, qword ptr [rbp - 16]   // restore dev pointer from stack
 * call eth_type_trans+5           // execute body of eth_type_trans
 * mov qword ptr [rbp - 8], rax    // save return value
 * call __bpf_prog_enter           // rcu_read_lock and preempt_disable
 * mov rbx, rax                    // remember start time in bpf stats are enabled
 * lea rdi, [rbp - 24]             // R1==ctx of bpf prog
 * call addr_of_jited_FEXIT_prog   // bpf prog can access skb, dev, return value
 * movabsq rdi, 64bit_addr_of_struct_bpf_prog  // unused if bpf stats are off
 * mov rsi, rbx                    // prog start time
 * call __bpf_prog_exit            // rcu_read_unlock, preempt_enable and stats math
 * mov rax, qword ptr [rbp - 8]    // restore eth_type_trans's return value
 * pop rbx
 * leave
 * add rsp, 8                      // skip eth_type_trans's frame
 * ret                             // return to its caller
 */
int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags,
				struct bpf_prog **fentry_progs, int fentry_cnt,
				struct bpf_prog **fexit_progs, int fexit_cnt,
				void *orig_call)
{
	int cnt = 0, nr_args = m->nr_args;
	int stack_size = nr_args * 8;
	u8 *prog;

	/* x86-64 supports up to 6 arguments. 7+ can be added in the future */
	if (nr_args > 6)
		return -ENOTSUPP;

	if ((flags & BPF_TRAMP_F_RESTORE_REGS) &&
	    (flags & BPF_TRAMP_F_SKIP_FRAME))
		return -EINVAL;

	if (flags & BPF_TRAMP_F_CALL_ORIG)
		stack_size += 8; /* room for return value of orig_call */

	if (flags & BPF_TRAMP_F_SKIP_FRAME)
		/* skip patched call instruction and point orig_call to actual
		 * body of the kernel function.
		 */
		orig_call += X86_CALL_SIZE;

	prog = image;

	EMIT1(0x55);		 /* push rbp */
	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
	EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */
	EMIT1(0x53);		 /* push rbx */

	save_regs(m, &prog, nr_args, stack_size);

	if (fentry_cnt)
		if (invoke_bpf(m, &prog, fentry_progs, fentry_cnt, stack_size))
			return -EINVAL;

	if (flags & BPF_TRAMP_F_CALL_ORIG) {
		if (fentry_cnt)
			restore_regs(m, &prog, nr_args, stack_size);

		/* call original function */
		if (emit_call(&prog, orig_call, prog))
			return -EINVAL;
		/* remember return value in a stack for bpf prog to access */
		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
	}

	if (fexit_cnt)
		if (invoke_bpf(m, &prog, fexit_progs, fexit_cnt, stack_size))
			return -EINVAL;

	if (flags & BPF_TRAMP_F_RESTORE_REGS)
		restore_regs(m, &prog, nr_args, stack_size);

	if (flags & BPF_TRAMP_F_CALL_ORIG)
		/* restore original return value back into RAX */
		emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8);

	EMIT1(0x5B); /* pop rbx */
	EMIT1(0xC9); /* leave */
	if (flags & BPF_TRAMP_F_SKIP_FRAME)
		/* skip our return address and return to parent */
		EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */
	EMIT1(0xC3); /* ret */
	/* One half of the page has active running trampoline.
	 * Another half is an area for next trampoline.
	 * Make sure the trampoline generation logic doesn't overflow.
	 */
	if (WARN_ON_ONCE(prog - (u8 *)image > PAGE_SIZE / 2 - BPF_INSN_SAFETY))
		return -EFAULT;
	return 0;
}

struct x64_jit_data {
	struct bpf_binary_header *header;
	int *addrs;
	u8 *image;
	int proglen;
	struct jit_context ctx;
};

struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
{
	struct bpf_binary_header *header = NULL;
	struct bpf_prog *tmp, *orig_prog = prog;
	struct x64_jit_data *jit_data;
	int proglen, oldproglen = 0;
	struct jit_context ctx = {};
	bool tmp_blinded = false;
	bool extra_pass = false;
	u8 *image = NULL;
	int *addrs;
	int pass;
	int i;

	if (!prog->jit_requested)
		return orig_prog;

	tmp = bpf_jit_blind_constants(prog);
	/*
	 * If blinding was requested and we failed during blinding,
	 * we must fall back to the interpreter.
	 */
	if (IS_ERR(tmp))
		return orig_prog;
	if (tmp != prog) {
		tmp_blinded = true;
		prog = tmp;
	}

	jit_data = prog->aux->jit_data;
	if (!jit_data) {
		jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
		if (!jit_data) {
			prog = orig_prog;
			goto out;
		}
		prog->aux->jit_data = jit_data;
	}
	addrs = jit_data->addrs;
	if (addrs) {
		ctx = jit_data->ctx;
		oldproglen = jit_data->proglen;
		image = jit_data->image;
		header = jit_data->header;
		extra_pass = true;
		goto skip_init_addrs;
	}
	addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
	if (!addrs) {
		prog = orig_prog;
		goto out_addrs;
	}

	/*
	 * Before first pass, make a rough estimation of addrs[]
	 * each BPF instruction is translated to less than 64 bytes
	 */
	for (proglen = 0, i = 0; i <= prog->len; i++) {
		proglen += 64;
		addrs[i] = proglen;
	}
	ctx.cleanup_addr = proglen;
skip_init_addrs:

	/*
	 * JITed image shrinks with every pass and the loop iterates
	 * until the image stops shrinking. Very large BPF programs
	 * may converge on the last pass. In such case do one more
	 * pass to emit the final image.
	 */
	for (pass = 0; pass < 20 || image; pass++) {
		proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
		if (proglen <= 0) {
out_image:
			image = NULL;
			if (header)
				bpf_jit_binary_free(header);
			prog = orig_prog;
			goto out_addrs;
		}
		if (image) {
			if (proglen != oldproglen) {
				pr_err("bpf_jit: proglen=%d != oldproglen=%d\n",
				       proglen, oldproglen);
				goto out_image;
			}
			break;
		}
		if (proglen == oldproglen) {
			/*
			 * The number of entries in extable is the number of BPF_LDX
			 * insns that access kernel memory via "pointer to BTF type".
			 * The verifier changed their opcode from LDX|MEM|size
			 * to LDX|PROBE_MEM|size to make JITing easier.
			 */
			u32 align = __alignof__(struct exception_table_entry);
			u32 extable_size = prog->aux->num_exentries *
				sizeof(struct exception_table_entry);

			/* allocate module memory for x86 insns and extable */
			header = bpf_jit_binary_alloc(roundup(proglen, align) + extable_size,
						      &image, align, jit_fill_hole);
			if (!header) {
				prog = orig_prog;
				goto out_addrs;
			}
			prog->aux->extable = (void *) image + roundup(proglen, align);
		}
		oldproglen = proglen;
		cond_resched();
	}

	if (bpf_jit_enable > 1)
		bpf_jit_dump(prog->len, proglen, pass + 1, image);

	if (image) {
		if (!prog->is_func || extra_pass) {
			bpf_jit_binary_lock_ro(header);
		} else {
			jit_data->addrs = addrs;
			jit_data->ctx = ctx;
			jit_data->proglen = proglen;
			jit_data->image = image;
			jit_data->header = header;
		}
		prog->bpf_func = (void *)image;
		prog->jited = 1;
		prog->jited_len = proglen;
	} else {
		prog = orig_prog;
	}

	if (!image || !prog->is_func || extra_pass) {
		if (image)
			bpf_prog_fill_jited_linfo(prog, addrs + 1);
out_addrs:
		kfree(addrs);
		kfree(jit_data);
		prog->aux->jit_data = NULL;
	}
out:
	if (tmp_blinded)
		bpf_jit_prog_release_other(prog, prog == orig_prog ?
					   tmp : orig_prog);
	return prog;
}