summaryrefslogtreecommitdiffstats
path: root/arch/arm64/net/bpf_jit_comp.c
blob: 13eac43c632dfe793912ba310f7449d59e3bd9ed (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
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
// SPDX-License-Identifier: GPL-2.0-only
/*
 * BPF JIT compiler for ARM64
 *
 * Copyright (C) 2014-2016 Zi Shen Lim <zlim.lnx@gmail.com>
 */

#define pr_fmt(fmt) "bpf_jit: " fmt

#include <linux/bitfield.h>
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/memory.h>
#include <linux/printk.h>
#include <linux/slab.h>

#include <asm/asm-extable.h>
#include <asm/byteorder.h>
#include <asm/cacheflush.h>
#include <asm/debug-monitors.h>
#include <asm/insn.h>
#include <asm/patching.h>
#include <asm/set_memory.h>

#include "bpf_jit.h"

#define TMP_REG_1 (MAX_BPF_JIT_REG + 0)
#define TMP_REG_2 (MAX_BPF_JIT_REG + 1)
#define TCALL_CNT (MAX_BPF_JIT_REG + 2)
#define TMP_REG_3 (MAX_BPF_JIT_REG + 3)
#define FP_BOTTOM (MAX_BPF_JIT_REG + 4)

#define check_imm(bits, imm) do {				\
	if ((((imm) > 0) && ((imm) >> (bits))) ||		\
	    (((imm) < 0) && (~(imm) >> (bits)))) {		\
		pr_info("[%2d] imm=%d(0x%x) out of range\n",	\
			i, imm, imm);				\
		return -EINVAL;					\
	}							\
} while (0)
#define check_imm19(imm) check_imm(19, imm)
#define check_imm26(imm) check_imm(26, imm)

/* Map BPF registers to A64 registers */
static const int bpf2a64[] = {
	/* return value from in-kernel function, and exit value from eBPF */
	[BPF_REG_0] = A64_R(7),
	/* arguments from eBPF program to in-kernel function */
	[BPF_REG_1] = A64_R(0),
	[BPF_REG_2] = A64_R(1),
	[BPF_REG_3] = A64_R(2),
	[BPF_REG_4] = A64_R(3),
	[BPF_REG_5] = A64_R(4),
	/* callee saved registers that in-kernel function will preserve */
	[BPF_REG_6] = A64_R(19),
	[BPF_REG_7] = A64_R(20),
	[BPF_REG_8] = A64_R(21),
	[BPF_REG_9] = A64_R(22),
	/* read-only frame pointer to access stack */
	[BPF_REG_FP] = A64_R(25),
	/* temporary registers for BPF JIT */
	[TMP_REG_1] = A64_R(10),
	[TMP_REG_2] = A64_R(11),
	[TMP_REG_3] = A64_R(12),
	/* tail_call_cnt */
	[TCALL_CNT] = A64_R(26),
	/* temporary register for blinding constants */
	[BPF_REG_AX] = A64_R(9),
	[FP_BOTTOM] = A64_R(27),
};

struct jit_ctx {
	const struct bpf_prog *prog;
	int idx;
	int epilogue_offset;
	int *offset;
	int exentry_idx;
	__le32 *image;
	__le32 *ro_image;
	u32 stack_size;
	int fpb_offset;
};

struct bpf_plt {
	u32 insn_ldr; /* load target */
	u32 insn_br;  /* branch to target */
	u64 target;   /* target value */
};

#define PLT_TARGET_SIZE   sizeof_field(struct bpf_plt, target)
#define PLT_TARGET_OFFSET offsetof(struct bpf_plt, target)

static inline void emit(const u32 insn, struct jit_ctx *ctx)
{
	if (ctx->image != NULL)
		ctx->image[ctx->idx] = cpu_to_le32(insn);

	ctx->idx++;
}

static inline void emit_a64_mov_i(const int is64, const int reg,
				  const s32 val, struct jit_ctx *ctx)
{
	u16 hi = val >> 16;
	u16 lo = val & 0xffff;

	if (hi & 0x8000) {
		if (hi == 0xffff) {
			emit(A64_MOVN(is64, reg, (u16)~lo, 0), ctx);
		} else {
			emit(A64_MOVN(is64, reg, (u16)~hi, 16), ctx);
			if (lo != 0xffff)
				emit(A64_MOVK(is64, reg, lo, 0), ctx);
		}
	} else {
		emit(A64_MOVZ(is64, reg, lo, 0), ctx);
		if (hi)
			emit(A64_MOVK(is64, reg, hi, 16), ctx);
	}
}

static int i64_i16_blocks(const u64 val, bool inverse)
{
	return (((val >>  0) & 0xffff) != (inverse ? 0xffff : 0x0000)) +
	       (((val >> 16) & 0xffff) != (inverse ? 0xffff : 0x0000)) +
	       (((val >> 32) & 0xffff) != (inverse ? 0xffff : 0x0000)) +
	       (((val >> 48) & 0xffff) != (inverse ? 0xffff : 0x0000));
}

static inline void emit_a64_mov_i64(const int reg, const u64 val,
				    struct jit_ctx *ctx)
{
	u64 nrm_tmp = val, rev_tmp = ~val;
	bool inverse;
	int shift;

	if (!(nrm_tmp >> 32))
		return emit_a64_mov_i(0, reg, (u32)val, ctx);

	inverse = i64_i16_blocks(nrm_tmp, true) < i64_i16_blocks(nrm_tmp, false);
	shift = max(round_down((inverse ? (fls64(rev_tmp) - 1) :
					  (fls64(nrm_tmp) - 1)), 16), 0);
	if (inverse)
		emit(A64_MOVN(1, reg, (rev_tmp >> shift) & 0xffff, shift), ctx);
	else
		emit(A64_MOVZ(1, reg, (nrm_tmp >> shift) & 0xffff, shift), ctx);
	shift -= 16;
	while (shift >= 0) {
		if (((nrm_tmp >> shift) & 0xffff) != (inverse ? 0xffff : 0x0000))
			emit(A64_MOVK(1, reg, (nrm_tmp >> shift) & 0xffff, shift), ctx);
		shift -= 16;
	}
}

static inline void emit_bti(u32 insn, struct jit_ctx *ctx)
{
	if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL))
		emit(insn, ctx);
}

/*
 * Kernel addresses in the vmalloc space use at most 48 bits, and the
 * remaining bits are guaranteed to be 0x1. So we can compose the address
 * with a fixed length movn/movk/movk sequence.
 */
static inline void emit_addr_mov_i64(const int reg, const u64 val,
				     struct jit_ctx *ctx)
{
	u64 tmp = val;
	int shift = 0;

	emit(A64_MOVN(1, reg, ~tmp & 0xffff, shift), ctx);
	while (shift < 32) {
		tmp >>= 16;
		shift += 16;
		emit(A64_MOVK(1, reg, tmp & 0xffff, shift), ctx);
	}
}

static inline void emit_call(u64 target, struct jit_ctx *ctx)
{
	u8 tmp = bpf2a64[TMP_REG_1];

	emit_addr_mov_i64(tmp, target, ctx);
	emit(A64_BLR(tmp), ctx);
}

static inline int bpf2a64_offset(int bpf_insn, int off,
				 const struct jit_ctx *ctx)
{
	/* BPF JMP offset is relative to the next instruction */
	bpf_insn++;
	/*
	 * Whereas arm64 branch instructions encode the offset
	 * from the branch itself, so we must subtract 1 from the
	 * instruction offset.
	 */
	return ctx->offset[bpf_insn + off] - (ctx->offset[bpf_insn] - 1);
}

static void jit_fill_hole(void *area, unsigned int size)
{
	__le32 *ptr;
	/* We are guaranteed to have aligned memory. */
	for (ptr = area; size >= sizeof(u32); size -= sizeof(u32))
		*ptr++ = cpu_to_le32(AARCH64_BREAK_FAULT);
}

int bpf_arch_text_invalidate(void *dst, size_t len)
{
	if (!aarch64_insn_set(dst, AARCH64_BREAK_FAULT, len))
		return -EINVAL;

	return 0;
}

static inline int epilogue_offset(const struct jit_ctx *ctx)
{
	int to = ctx->epilogue_offset;
	int from = ctx->idx;

	return to - from;
}

static bool is_addsub_imm(u32 imm)
{
	/* Either imm12 or shifted imm12. */
	return !(imm & ~0xfff) || !(imm & ~0xfff000);
}

/*
 * There are 3 types of AArch64 LDR/STR (immediate) instruction:
 * Post-index, Pre-index, Unsigned offset.
 *
 * For BPF ldr/str, the "unsigned offset" type is sufficient.
 *
 * "Unsigned offset" type LDR(immediate) format:
 *
 *    3                   2                   1                   0
 *  1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
 * |x x|1 1 1 0 0 1 0 1|         imm12         |    Rn   |    Rt   |
 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
 * scale
 *
 * "Unsigned offset" type STR(immediate) format:
 *    3                   2                   1                   0
 *  1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
 * |x x|1 1 1 0 0 1 0 0|         imm12         |    Rn   |    Rt   |
 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
 * scale
 *
 * The offset is calculated from imm12 and scale in the following way:
 *
 * offset = (u64)imm12 << scale
 */
static bool is_lsi_offset(int offset, int scale)
{
	if (offset < 0)
		return false;

	if (offset > (0xFFF << scale))
		return false;

	if (offset & ((1 << scale) - 1))
		return false;

	return true;
}

/* generated prologue:
 *      bti c // if CONFIG_ARM64_BTI_KERNEL
 *      mov x9, lr
 *      nop  // POKE_OFFSET
 *      paciasp // if CONFIG_ARM64_PTR_AUTH_KERNEL
 *      stp x29, lr, [sp, #-16]!
 *      mov x29, sp
 *      stp x19, x20, [sp, #-16]!
 *      stp x21, x22, [sp, #-16]!
 *      stp x25, x26, [sp, #-16]!
 *      stp x27, x28, [sp, #-16]!
 *      mov x25, sp
 *      mov tcc, #0
 *      // PROLOGUE_OFFSET
 */

#define BTI_INSNS (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) ? 1 : 0)
#define PAC_INSNS (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL) ? 1 : 0)

/* Offset of nop instruction in bpf prog entry to be poked */
#define POKE_OFFSET (BTI_INSNS + 1)

/* Tail call offset to jump into */
#define PROLOGUE_OFFSET (BTI_INSNS + 2 + PAC_INSNS + 8)

static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf,
			  bool is_exception_cb)
{
	const struct bpf_prog *prog = ctx->prog;
	const bool is_main_prog = !bpf_is_subprog(prog);
	const u8 r6 = bpf2a64[BPF_REG_6];
	const u8 r7 = bpf2a64[BPF_REG_7];
	const u8 r8 = bpf2a64[BPF_REG_8];
	const u8 r9 = bpf2a64[BPF_REG_9];
	const u8 fp = bpf2a64[BPF_REG_FP];
	const u8 tcc = bpf2a64[TCALL_CNT];
	const u8 fpb = bpf2a64[FP_BOTTOM];
	const int idx0 = ctx->idx;
	int cur_offset;

	/*
	 * BPF prog stack layout
	 *
	 *                         high
	 * original A64_SP =>   0:+-----+ BPF prologue
	 *                        |FP/LR|
	 * current A64_FP =>  -16:+-----+
	 *                        | ... | callee saved registers
	 * BPF fp register => -64:+-----+ <= (BPF_FP)
	 *                        |     |
	 *                        | ... | BPF prog stack
	 *                        |     |
	 *                        +-----+ <= (BPF_FP - prog->aux->stack_depth)
	 *                        |RSVD | padding
	 * current A64_SP =>      +-----+ <= (BPF_FP - ctx->stack_size)
	 *                        |     |
	 *                        | ... | Function call stack
	 *                        |     |
	 *                        +-----+
	 *                          low
	 *
	 */

	/* bpf function may be invoked by 3 instruction types:
	 * 1. bl, attached via freplace to bpf prog via short jump
	 * 2. br, attached via freplace to bpf prog via long jump
	 * 3. blr, working as a function pointer, used by emit_call.
	 * So BTI_JC should used here to support both br and blr.
	 */
	emit_bti(A64_BTI_JC, ctx);

	emit(A64_MOV(1, A64_R(9), A64_LR), ctx);
	emit(A64_NOP, ctx);

	if (!is_exception_cb) {
		/* Sign lr */
		if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL))
			emit(A64_PACIASP, ctx);
		/* Save FP and LR registers to stay align with ARM64 AAPCS */
		emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
		emit(A64_MOV(1, A64_FP, A64_SP), ctx);

		/* Save callee-saved registers */
		emit(A64_PUSH(r6, r7, A64_SP), ctx);
		emit(A64_PUSH(r8, r9, A64_SP), ctx);
		emit(A64_PUSH(fp, tcc, A64_SP), ctx);
		emit(A64_PUSH(fpb, A64_R(28), A64_SP), ctx);
	} else {
		/*
		 * Exception callback receives FP of Main Program as third
		 * parameter
		 */
		emit(A64_MOV(1, A64_FP, A64_R(2)), ctx);
		/*
		 * Main Program already pushed the frame record and the
		 * callee-saved registers. The exception callback will not push
		 * anything and re-use the main program's stack.
		 *
		 * 10 registers are on the stack
		 */
		emit(A64_SUB_I(1, A64_SP, A64_FP, 80), ctx);
	}

	/* Set up BPF prog stack base register */
	emit(A64_MOV(1, fp, A64_SP), ctx);

	if (!ebpf_from_cbpf && is_main_prog) {
		/* Initialize tail_call_cnt */
		emit(A64_MOVZ(1, tcc, 0, 0), ctx);

		cur_offset = ctx->idx - idx0;
		if (cur_offset != PROLOGUE_OFFSET) {
			pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
				    cur_offset, PROLOGUE_OFFSET);
			return -1;
		}

		/* BTI landing pad for the tail call, done with a BR */
		emit_bti(A64_BTI_J, ctx);
	}

	/*
	 * Program acting as exception boundary should save all ARM64
	 * Callee-saved registers as the exception callback needs to recover
	 * all ARM64 Callee-saved registers in its epilogue.
	 */
	if (prog->aux->exception_boundary) {
		/*
		 * As we are pushing two more registers, BPF_FP should be moved
		 * 16 bytes
		 */
		emit(A64_SUB_I(1, fp, fp, 16), ctx);
		emit(A64_PUSH(A64_R(23), A64_R(24), A64_SP), ctx);
	}

	emit(A64_SUB_I(1, fpb, fp, ctx->fpb_offset), ctx);

	/* Stack must be multiples of 16B */
	ctx->stack_size = round_up(prog->aux->stack_depth, 16);

	/* Set up function call stack */
	emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
	return 0;
}

static int out_offset = -1; /* initialized on the first pass of build_body() */
static int emit_bpf_tail_call(struct jit_ctx *ctx)
{
	/* bpf_tail_call(void *prog_ctx, struct bpf_array *array, u64 index) */
	const u8 r2 = bpf2a64[BPF_REG_2];
	const u8 r3 = bpf2a64[BPF_REG_3];

	const u8 tmp = bpf2a64[TMP_REG_1];
	const u8 prg = bpf2a64[TMP_REG_2];
	const u8 tcc = bpf2a64[TCALL_CNT];
	const int idx0 = ctx->idx;
#define cur_offset (ctx->idx - idx0)
#define jmp_offset (out_offset - (cur_offset))
	size_t off;

	/* if (index >= array->map.max_entries)
	 *     goto out;
	 */
	off = offsetof(struct bpf_array, map.max_entries);
	emit_a64_mov_i64(tmp, off, ctx);
	emit(A64_LDR32(tmp, r2, tmp), ctx);
	emit(A64_MOV(0, r3, r3), ctx);
	emit(A64_CMP(0, r3, tmp), ctx);
	emit(A64_B_(A64_COND_CS, jmp_offset), ctx);

	/*
	 * if (tail_call_cnt >= MAX_TAIL_CALL_CNT)
	 *     goto out;
	 * tail_call_cnt++;
	 */
	emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx);
	emit(A64_CMP(1, tcc, tmp), ctx);
	emit(A64_B_(A64_COND_CS, jmp_offset), ctx);
	emit(A64_ADD_I(1, tcc, tcc, 1), ctx);

	/* prog = array->ptrs[index];
	 * if (prog == NULL)
	 *     goto out;
	 */
	off = offsetof(struct bpf_array, ptrs);
	emit_a64_mov_i64(tmp, off, ctx);
	emit(A64_ADD(1, tmp, r2, tmp), ctx);
	emit(A64_LSL(1, prg, r3, 3), ctx);
	emit(A64_LDR64(prg, tmp, prg), ctx);
	emit(A64_CBZ(1, prg, jmp_offset), ctx);

	/* goto *(prog->bpf_func + prologue_offset); */
	off = offsetof(struct bpf_prog, bpf_func);
	emit_a64_mov_i64(tmp, off, ctx);
	emit(A64_LDR64(tmp, prg, tmp), ctx);
	emit(A64_ADD_I(1, tmp, tmp, sizeof(u32) * PROLOGUE_OFFSET), ctx);
	emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
	emit(A64_BR(tmp), ctx);

	/* out: */
	if (out_offset == -1)
		out_offset = cur_offset;
	if (cur_offset != out_offset) {
		pr_err_once("tail_call out_offset = %d, expected %d!\n",
			    cur_offset, out_offset);
		return -1;
	}
	return 0;
#undef cur_offset
#undef jmp_offset
}

#ifdef CONFIG_ARM64_LSE_ATOMICS
static int emit_lse_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
{
	const u8 code = insn->code;
	const u8 dst = bpf2a64[insn->dst_reg];
	const u8 src = bpf2a64[insn->src_reg];
	const u8 tmp = bpf2a64[TMP_REG_1];
	const u8 tmp2 = bpf2a64[TMP_REG_2];
	const bool isdw = BPF_SIZE(code) == BPF_DW;
	const s16 off = insn->off;
	u8 reg;

	if (!off) {
		reg = dst;
	} else {
		emit_a64_mov_i(1, tmp, off, ctx);
		emit(A64_ADD(1, tmp, tmp, dst), ctx);
		reg = tmp;
	}

	switch (insn->imm) {
	/* lock *(u32/u64 *)(dst_reg + off) <op>= src_reg */
	case BPF_ADD:
		emit(A64_STADD(isdw, reg, src), ctx);
		break;
	case BPF_AND:
		emit(A64_MVN(isdw, tmp2, src), ctx);
		emit(A64_STCLR(isdw, reg, tmp2), ctx);
		break;
	case BPF_OR:
		emit(A64_STSET(isdw, reg, src), ctx);
		break;
	case BPF_XOR:
		emit(A64_STEOR(isdw, reg, src), ctx);
		break;
	/* src_reg = atomic_fetch_<op>(dst_reg + off, src_reg) */
	case BPF_ADD | BPF_FETCH:
		emit(A64_LDADDAL(isdw, src, reg, src), ctx);
		break;
	case BPF_AND | BPF_FETCH:
		emit(A64_MVN(isdw, tmp2, src), ctx);
		emit(A64_LDCLRAL(isdw, src, reg, tmp2), ctx);
		break;
	case BPF_OR | BPF_FETCH:
		emit(A64_LDSETAL(isdw, src, reg, src), ctx);
		break;
	case BPF_XOR | BPF_FETCH:
		emit(A64_LDEORAL(isdw, src, reg, src), ctx);
		break;
	/* src_reg = atomic_xchg(dst_reg + off, src_reg); */
	case BPF_XCHG:
		emit(A64_SWPAL(isdw, src, reg, src), ctx);
		break;
	/* r0 = atomic_cmpxchg(dst_reg + off, r0, src_reg); */
	case BPF_CMPXCHG:
		emit(A64_CASAL(isdw, src, reg, bpf2a64[BPF_REG_0]), ctx);
		break;
	default:
		pr_err_once("unknown atomic op code %02x\n", insn->imm);
		return -EINVAL;
	}

	return 0;
}
#else
static inline int emit_lse_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
{
	return -EINVAL;
}
#endif

static int emit_ll_sc_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
{
	const u8 code = insn->code;
	const u8 dst = bpf2a64[insn->dst_reg];
	const u8 src = bpf2a64[insn->src_reg];
	const u8 tmp = bpf2a64[TMP_REG_1];
	const u8 tmp2 = bpf2a64[TMP_REG_2];
	const u8 tmp3 = bpf2a64[TMP_REG_3];
	const int i = insn - ctx->prog->insnsi;
	const s32 imm = insn->imm;
	const s16 off = insn->off;
	const bool isdw = BPF_SIZE(code) == BPF_DW;
	u8 reg;
	s32 jmp_offset;

	if (!off) {
		reg = dst;
	} else {
		emit_a64_mov_i(1, tmp, off, ctx);
		emit(A64_ADD(1, tmp, tmp, dst), ctx);
		reg = tmp;
	}

	if (imm == BPF_ADD || imm == BPF_AND ||
	    imm == BPF_OR || imm == BPF_XOR) {
		/* lock *(u32/u64 *)(dst_reg + off) <op>= src_reg */
		emit(A64_LDXR(isdw, tmp2, reg), ctx);
		if (imm == BPF_ADD)
			emit(A64_ADD(isdw, tmp2, tmp2, src), ctx);
		else if (imm == BPF_AND)
			emit(A64_AND(isdw, tmp2, tmp2, src), ctx);
		else if (imm == BPF_OR)
			emit(A64_ORR(isdw, tmp2, tmp2, src), ctx);
		else
			emit(A64_EOR(isdw, tmp2, tmp2, src), ctx);
		emit(A64_STXR(isdw, tmp2, reg, tmp3), ctx);
		jmp_offset = -3;
		check_imm19(jmp_offset);
		emit(A64_CBNZ(0, tmp3, jmp_offset), ctx);
	} else if (imm == (BPF_ADD | BPF_FETCH) ||
		   imm == (BPF_AND | BPF_FETCH) ||
		   imm == (BPF_OR | BPF_FETCH) ||
		   imm == (BPF_XOR | BPF_FETCH)) {
		/* src_reg = atomic_fetch_<op>(dst_reg + off, src_reg) */
		const u8 ax = bpf2a64[BPF_REG_AX];

		emit(A64_MOV(isdw, ax, src), ctx);
		emit(A64_LDXR(isdw, src, reg), ctx);
		if (imm == (BPF_ADD | BPF_FETCH))
			emit(A64_ADD(isdw, tmp2, src, ax), ctx);
		else if (imm == (BPF_AND | BPF_FETCH))
			emit(A64_AND(isdw, tmp2, src, ax), ctx);
		else if (imm == (BPF_OR | BPF_FETCH))
			emit(A64_ORR(isdw, tmp2, src, ax), ctx);
		else
			emit(A64_EOR(isdw, tmp2, src, ax), ctx);
		emit(A64_STLXR(isdw, tmp2, reg, tmp3), ctx);
		jmp_offset = -3;
		check_imm19(jmp_offset);
		emit(A64_CBNZ(0, tmp3, jmp_offset), ctx);
		emit(A64_DMB_ISH, ctx);
	} else if (imm == BPF_XCHG) {
		/* src_reg = atomic_xchg(dst_reg + off, src_reg); */
		emit(A64_MOV(isdw, tmp2, src), ctx);
		emit(A64_LDXR(isdw, src, reg), ctx);
		emit(A64_STLXR(isdw, tmp2, reg, tmp3), ctx);
		jmp_offset = -2;
		check_imm19(jmp_offset);
		emit(A64_CBNZ(0, tmp3, jmp_offset), ctx);
		emit(A64_DMB_ISH, ctx);
	} else if (imm == BPF_CMPXCHG) {
		/* r0 = atomic_cmpxchg(dst_reg + off, r0, src_reg); */
		const u8 r0 = bpf2a64[BPF_REG_0];

		emit(A64_MOV(isdw, tmp2, r0), ctx);
		emit(A64_LDXR(isdw, r0, reg), ctx);
		emit(A64_EOR(isdw, tmp3, r0, tmp2), ctx);
		jmp_offset = 4;
		check_imm19(jmp_offset);
		emit(A64_CBNZ(isdw, tmp3, jmp_offset), ctx);
		emit(A64_STLXR(isdw, src, reg, tmp3), ctx);
		jmp_offset = -4;
		check_imm19(jmp_offset);
		emit(A64_CBNZ(0, tmp3, jmp_offset), ctx);
		emit(A64_DMB_ISH, ctx);
	} else {
		pr_err_once("unknown atomic op code %02x\n", imm);
		return -EINVAL;
	}

	return 0;
}

void dummy_tramp(void);

asm (
"	.pushsection .text, \"ax\", @progbits\n"
"	.global dummy_tramp\n"
"	.type dummy_tramp, %function\n"
"dummy_tramp:"
#if IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)
"	bti j\n" /* dummy_tramp is called via "br x10" */
#endif
"	mov x10, x30\n"
"	mov x30, x9\n"
"	ret x10\n"
"	.size dummy_tramp, .-dummy_tramp\n"
"	.popsection\n"
);

/* build a plt initialized like this:
 *
 * plt:
 *      ldr tmp, target
 *      br tmp
 * target:
 *      .quad dummy_tramp
 *
 * when a long jump trampoline is attached, target is filled with the
 * trampoline address, and when the trampoline is removed, target is
 * restored to dummy_tramp address.
 */
static void build_plt(struct jit_ctx *ctx)
{
	const u8 tmp = bpf2a64[TMP_REG_1];
	struct bpf_plt *plt = NULL;

	/* make sure target is 64-bit aligned */
	if ((ctx->idx + PLT_TARGET_OFFSET / AARCH64_INSN_SIZE) % 2)
		emit(A64_NOP, ctx);

	plt = (struct bpf_plt *)(ctx->image + ctx->idx);
	/* plt is called via bl, no BTI needed here */
	emit(A64_LDR64LIT(tmp, 2 * AARCH64_INSN_SIZE), ctx);
	emit(A64_BR(tmp), ctx);

	if (ctx->image)
		plt->target = (u64)&dummy_tramp;
}

static void build_epilogue(struct jit_ctx *ctx, bool is_exception_cb)
{
	const u8 r0 = bpf2a64[BPF_REG_0];
	const u8 r6 = bpf2a64[BPF_REG_6];
	const u8 r7 = bpf2a64[BPF_REG_7];
	const u8 r8 = bpf2a64[BPF_REG_8];
	const u8 r9 = bpf2a64[BPF_REG_9];
	const u8 fp = bpf2a64[BPF_REG_FP];
	const u8 fpb = bpf2a64[FP_BOTTOM];

	/* We're done with BPF stack */
	emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);

	/*
	 * Program acting as exception boundary pushes R23 and R24 in addition
	 * to BPF callee-saved registers. Exception callback uses the boundary
	 * program's stack frame, so recover these extra registers in the above
	 * two cases.
	 */
	if (ctx->prog->aux->exception_boundary || is_exception_cb)
		emit(A64_POP(A64_R(23), A64_R(24), A64_SP), ctx);

	/* Restore x27 and x28 */
	emit(A64_POP(fpb, A64_R(28), A64_SP), ctx);
	/* Restore fs (x25) and x26 */
	emit(A64_POP(fp, A64_R(26), A64_SP), ctx);

	/* Restore callee-saved register */
	emit(A64_POP(r8, r9, A64_SP), ctx);
	emit(A64_POP(r6, r7, A64_SP), ctx);

	/* Restore FP/LR registers */
	emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);

	/* Set return value */
	emit(A64_MOV(1, A64_R(0), r0), ctx);

	/* Authenticate lr */
	if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL))
		emit(A64_AUTIASP, ctx);

	emit(A64_RET(A64_LR), ctx);
}

#define BPF_FIXUP_OFFSET_MASK	GENMASK(26, 0)
#define BPF_FIXUP_REG_MASK	GENMASK(31, 27)

bool ex_handler_bpf(const struct exception_table_entry *ex,
		    struct pt_regs *regs)
{
	off_t offset = FIELD_GET(BPF_FIXUP_OFFSET_MASK, ex->fixup);
	int dst_reg = FIELD_GET(BPF_FIXUP_REG_MASK, ex->fixup);

	regs->regs[dst_reg] = 0;
	regs->pc = (unsigned long)&ex->fixup - offset;
	return true;
}

/* For accesses to BTF pointers, add an entry to the exception table */
static int add_exception_handler(const struct bpf_insn *insn,
				 struct jit_ctx *ctx,
				 int dst_reg)
{
	off_t ins_offset;
	off_t fixup_offset;
	unsigned long pc;
	struct exception_table_entry *ex;

	if (!ctx->image)
		/* First pass */
		return 0;

	if (BPF_MODE(insn->code) != BPF_PROBE_MEM &&
		BPF_MODE(insn->code) != BPF_PROBE_MEMSX)
		return 0;

	if (!ctx->prog->aux->extable ||
	    WARN_ON_ONCE(ctx->exentry_idx >= ctx->prog->aux->num_exentries))
		return -EINVAL;

	ex = &ctx->prog->aux->extable[ctx->exentry_idx];
	pc = (unsigned long)&ctx->ro_image[ctx->idx - 1];

	/*
	 * This is the relative offset of the instruction that may fault from
	 * the exception table itself. This will be written to the exception
	 * table and if this instruction faults, the destination register will
	 * be set to '0' and the execution will jump to the next instruction.
	 */
	ins_offset = pc - (long)&ex->insn;
	if (WARN_ON_ONCE(ins_offset >= 0 || ins_offset < INT_MIN))
		return -ERANGE;

	/*
	 * Since the extable follows the program, the fixup offset is always
	 * negative and limited to BPF_JIT_REGION_SIZE. Store a positive value
	 * to keep things simple, and put the destination register in the upper
	 * bits. We don't need to worry about buildtime or runtime sort
	 * modifying the upper bits because the table is already sorted, and
	 * isn't part of the main exception table.
	 *
	 * The fixup_offset is set to the next instruction from the instruction
	 * that may fault. The execution will jump to this after handling the
	 * fault.
	 */
	fixup_offset = (long)&ex->fixup - (pc + AARCH64_INSN_SIZE);
	if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, fixup_offset))
		return -ERANGE;

	/*
	 * The offsets above have been calculated using the RO buffer but we
	 * need to use the R/W buffer for writes.
	 * switch ex to rw buffer for writing.
	 */
	ex = (void *)ctx->image + ((void *)ex - (void *)ctx->ro_image);

	ex->insn = ins_offset;

	ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, fixup_offset) |
		    FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg);

	ex->type = EX_TYPE_BPF;

	ctx->exentry_idx++;
	return 0;
}

/* JITs an eBPF instruction.
 * Returns:
 * 0  - successfully JITed an 8-byte eBPF instruction.
 * >0 - successfully JITed a 16-byte eBPF instruction.
 * <0 - failed to JIT.
 */
static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
		      bool extra_pass)
{
	const u8 code = insn->code;
	const u8 dst = bpf2a64[insn->dst_reg];
	const u8 src = bpf2a64[insn->src_reg];
	const u8 tmp = bpf2a64[TMP_REG_1];
	const u8 tmp2 = bpf2a64[TMP_REG_2];
	const u8 fp = bpf2a64[BPF_REG_FP];
	const u8 fpb = bpf2a64[FP_BOTTOM];
	const s16 off = insn->off;
	const s32 imm = insn->imm;
	const int i = insn - ctx->prog->insnsi;
	const bool is64 = BPF_CLASS(code) == BPF_ALU64 ||
			  BPF_CLASS(code) == BPF_JMP;
	u8 jmp_cond;
	s32 jmp_offset;
	u32 a64_insn;
	u8 src_adj;
	u8 dst_adj;
	int off_adj;
	int ret;
	bool sign_extend;

	switch (code) {
	/* dst = src */
	case BPF_ALU | BPF_MOV | BPF_X:
	case BPF_ALU64 | BPF_MOV | BPF_X:
		switch (insn->off) {
		case 0:
			emit(A64_MOV(is64, dst, src), ctx);
			break;
		case 8:
			emit(A64_SXTB(is64, dst, src), ctx);
			break;
		case 16:
			emit(A64_SXTH(is64, dst, src), ctx);
			break;
		case 32:
			emit(A64_SXTW(is64, dst, src), ctx);
			break;
		}
		break;
	/* dst = dst OP src */
	case BPF_ALU | BPF_ADD | BPF_X:
	case BPF_ALU64 | BPF_ADD | BPF_X:
		emit(A64_ADD(is64, dst, dst, src), ctx);
		break;
	case BPF_ALU | BPF_SUB | BPF_X:
	case BPF_ALU64 | BPF_SUB | BPF_X:
		emit(A64_SUB(is64, dst, dst, src), ctx);
		break;
	case BPF_ALU | BPF_AND | BPF_X:
	case BPF_ALU64 | BPF_AND | BPF_X:
		emit(A64_AND(is64, dst, dst, src), ctx);
		break;
	case BPF_ALU | BPF_OR | BPF_X:
	case BPF_ALU64 | BPF_OR | BPF_X:
		emit(A64_ORR(is64, dst, dst, src), ctx);
		break;
	case BPF_ALU | BPF_XOR | BPF_X:
	case BPF_ALU64 | BPF_XOR | BPF_X:
		emit(A64_EOR(is64, dst, dst, src), ctx);
		break;
	case BPF_ALU | BPF_MUL | BPF_X:
	case BPF_ALU64 | BPF_MUL | BPF_X:
		emit(A64_MUL(is64, dst, dst, src), ctx);
		break;
	case BPF_ALU | BPF_DIV | BPF_X:
	case BPF_ALU64 | BPF_DIV | BPF_X:
		if (!off)
			emit(A64_UDIV(is64, dst, dst, src), ctx);
		else
			emit(A64_SDIV(is64, dst, dst, src), ctx);
		break;
	case BPF_ALU | BPF_MOD | BPF_X:
	case BPF_ALU64 | BPF_MOD | BPF_X:
		if (!off)
			emit(A64_UDIV(is64, tmp, dst, src), ctx);
		else
			emit(A64_SDIV(is64, tmp, dst, src), ctx);
		emit(A64_MSUB(is64, dst, dst, tmp, src), ctx);
		break;
	case BPF_ALU | BPF_LSH | BPF_X:
	case BPF_ALU64 | BPF_LSH | BPF_X:
		emit(A64_LSLV(is64, dst, dst, src), ctx);
		break;
	case BPF_ALU | BPF_RSH | BPF_X:
	case BPF_ALU64 | BPF_RSH | BPF_X:
		emit(A64_LSRV(is64, dst, dst, src), ctx);
		break;
	case BPF_ALU | BPF_ARSH | BPF_X:
	case BPF_ALU64 | BPF_ARSH | BPF_X:
		emit(A64_ASRV(is64, dst, dst, src), ctx);
		break;
	/* dst = -dst */
	case BPF_ALU | BPF_NEG:
	case BPF_ALU64 | BPF_NEG:
		emit(A64_NEG(is64, dst, dst), ctx);
		break;
	/* dst = BSWAP##imm(dst) */
	case BPF_ALU | BPF_END | BPF_FROM_LE:
	case BPF_ALU | BPF_END | BPF_FROM_BE:
	case BPF_ALU64 | BPF_END | BPF_FROM_LE:
#ifdef CONFIG_CPU_BIG_ENDIAN
		if (BPF_CLASS(code) == BPF_ALU && BPF_SRC(code) == BPF_FROM_BE)
			goto emit_bswap_uxt;
#else /* !CONFIG_CPU_BIG_ENDIAN */
		if (BPF_CLASS(code) == BPF_ALU && BPF_SRC(code) == BPF_FROM_LE)
			goto emit_bswap_uxt;
#endif
		switch (imm) {
		case 16:
			emit(A64_REV16(is64, dst, dst), ctx);
			/* zero-extend 16 bits into 64 bits */
			emit(A64_UXTH(is64, dst, dst), ctx);
			break;
		case 32:
			emit(A64_REV32(0, dst, dst), ctx);
			/* upper 32 bits already cleared */
			break;
		case 64:
			emit(A64_REV64(dst, dst), ctx);
			break;
		}
		break;
emit_bswap_uxt:
		switch (imm) {
		case 16:
			/* zero-extend 16 bits into 64 bits */
			emit(A64_UXTH(is64, dst, dst), ctx);
			break;
		case 32:
			/* zero-extend 32 bits into 64 bits */
			emit(A64_UXTW(is64, dst, dst), ctx);
			break;
		case 64:
			/* nop */
			break;
		}
		break;
	/* dst = imm */
	case BPF_ALU | BPF_MOV | BPF_K:
	case BPF_ALU64 | BPF_MOV | BPF_K:
		emit_a64_mov_i(is64, dst, imm, ctx);
		break;
	/* dst = dst OP imm */
	case BPF_ALU | BPF_ADD | BPF_K:
	case BPF_ALU64 | BPF_ADD | BPF_K:
		if (is_addsub_imm(imm)) {
			emit(A64_ADD_I(is64, dst, dst, imm), ctx);
		} else if (is_addsub_imm(-imm)) {
			emit(A64_SUB_I(is64, dst, dst, -imm), ctx);
		} else {
			emit_a64_mov_i(is64, tmp, imm, ctx);
			emit(A64_ADD(is64, dst, dst, tmp), ctx);
		}
		break;
	case BPF_ALU | BPF_SUB | BPF_K:
	case BPF_ALU64 | BPF_SUB | BPF_K:
		if (is_addsub_imm(imm)) {
			emit(A64_SUB_I(is64, dst, dst, imm), ctx);
		} else if (is_addsub_imm(-imm)) {
			emit(A64_ADD_I(is64, dst, dst, -imm), ctx);
		} else {
			emit_a64_mov_i(is64, tmp, imm, ctx);
			emit(A64_SUB(is64, dst, dst, tmp), ctx);
		}
		break;
	case BPF_ALU | BPF_AND | BPF_K:
	case BPF_ALU64 | BPF_AND | BPF_K:
		a64_insn = A64_AND_I(is64, dst, dst, imm);
		if (a64_insn != AARCH64_BREAK_FAULT) {
			emit(a64_insn, ctx);
		} else {
			emit_a64_mov_i(is64, tmp, imm, ctx);
			emit(A64_AND(is64, dst, dst, tmp), ctx);
		}
		break;
	case BPF_ALU | BPF_OR | BPF_K:
	case BPF_ALU64 | BPF_OR | BPF_K:
		a64_insn = A64_ORR_I(is64, dst, dst, imm);
		if (a64_insn != AARCH64_BREAK_FAULT) {
			emit(a64_insn, ctx);
		} else {
			emit_a64_mov_i(is64, tmp, imm, ctx);
			emit(A64_ORR(is64, dst, dst, tmp), ctx);
		}
		break;
	case BPF_ALU | BPF_XOR | BPF_K:
	case BPF_ALU64 | BPF_XOR | BPF_K:
		a64_insn = A64_EOR_I(is64, dst, dst, imm);
		if (a64_insn != AARCH64_BREAK_FAULT) {
			emit(a64_insn, ctx);
		} else {
			emit_a64_mov_i(is64, tmp, imm, ctx);
			emit(A64_EOR(is64, dst, dst, tmp), ctx);
		}
		break;
	case BPF_ALU | BPF_MUL | BPF_K:
	case BPF_ALU64 | BPF_MUL | BPF_K:
		emit_a64_mov_i(is64, tmp, imm, ctx);
		emit(A64_MUL(is64, dst, dst, tmp), ctx);
		break;
	case BPF_ALU | BPF_DIV | BPF_K:
	case BPF_ALU64 | BPF_DIV | BPF_K:
		emit_a64_mov_i(is64, tmp, imm, ctx);
		if (!off)
			emit(A64_UDIV(is64, dst, dst, tmp), ctx);
		else
			emit(A64_SDIV(is64, dst, dst, tmp), ctx);
		break;
	case BPF_ALU | BPF_MOD | BPF_K:
	case BPF_ALU64 | BPF_MOD | BPF_K:
		emit_a64_mov_i(is64, tmp2, imm, ctx);
		if (!off)
			emit(A64_UDIV(is64, tmp, dst, tmp2), ctx);
		else
			emit(A64_SDIV(is64, tmp, dst, tmp2), ctx);
		emit(A64_MSUB(is64, dst, dst, tmp, tmp2), ctx);
		break;
	case BPF_ALU | BPF_LSH | BPF_K:
	case BPF_ALU64 | BPF_LSH | BPF_K:
		emit(A64_LSL(is64, dst, dst, imm), ctx);
		break;
	case BPF_ALU | BPF_RSH | BPF_K:
	case BPF_ALU64 | BPF_RSH | BPF_K:
		emit(A64_LSR(is64, dst, dst, imm), ctx);
		break;
	case BPF_ALU | BPF_ARSH | BPF_K:
	case BPF_ALU64 | BPF_ARSH | BPF_K:
		emit(A64_ASR(is64, dst, dst, imm), ctx);
		break;

	/* JUMP off */
	case BPF_JMP | BPF_JA:
	case BPF_JMP32 | BPF_JA:
		if (BPF_CLASS(code) == BPF_JMP)
			jmp_offset = bpf2a64_offset(i, off, ctx);
		else
			jmp_offset = bpf2a64_offset(i, imm, ctx);
		check_imm26(jmp_offset);
		emit(A64_B(jmp_offset), ctx);
		break;
	/* IF (dst COND src) JUMP off */
	case BPF_JMP | BPF_JEQ | 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_JNE | 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_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_JNE | 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:
		emit(A64_CMP(is64, dst, src), ctx);
emit_cond_jmp:
		jmp_offset = bpf2a64_offset(i, off, ctx);
		check_imm19(jmp_offset);
		switch (BPF_OP(code)) {
		case BPF_JEQ:
			jmp_cond = A64_COND_EQ;
			break;
		case BPF_JGT:
			jmp_cond = A64_COND_HI;
			break;
		case BPF_JLT:
			jmp_cond = A64_COND_CC;
			break;
		case BPF_JGE:
			jmp_cond = A64_COND_CS;
			break;
		case BPF_JLE:
			jmp_cond = A64_COND_LS;
			break;
		case BPF_JSET:
		case BPF_JNE:
			jmp_cond = A64_COND_NE;
			break;
		case BPF_JSGT:
			jmp_cond = A64_COND_GT;
			break;
		case BPF_JSLT:
			jmp_cond = A64_COND_LT;
			break;
		case BPF_JSGE:
			jmp_cond = A64_COND_GE;
			break;
		case BPF_JSLE:
			jmp_cond = A64_COND_LE;
			break;
		default:
			return -EFAULT;
		}
		emit(A64_B_(jmp_cond, jmp_offset), ctx);
		break;
	case BPF_JMP | BPF_JSET | BPF_X:
	case BPF_JMP32 | BPF_JSET | BPF_X:
		emit(A64_TST(is64, dst, src), ctx);
		goto emit_cond_jmp;
	/* IF (dst COND imm) JUMP off */
	case BPF_JMP | BPF_JEQ | 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_JNE | 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_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_JNE | 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:
		if (is_addsub_imm(imm)) {
			emit(A64_CMP_I(is64, dst, imm), ctx);
		} else if (is_addsub_imm(-imm)) {
			emit(A64_CMN_I(is64, dst, -imm), ctx);
		} else {
			emit_a64_mov_i(is64, tmp, imm, ctx);
			emit(A64_CMP(is64, dst, tmp), ctx);
		}
		goto emit_cond_jmp;
	case BPF_JMP | BPF_JSET | BPF_K:
	case BPF_JMP32 | BPF_JSET | BPF_K:
		a64_insn = A64_TST_I(is64, dst, imm);
		if (a64_insn != AARCH64_BREAK_FAULT) {
			emit(a64_insn, ctx);
		} else {
			emit_a64_mov_i(is64, tmp, imm, ctx);
			emit(A64_TST(is64, dst, tmp), ctx);
		}
		goto emit_cond_jmp;
	/* function call */
	case BPF_JMP | BPF_CALL:
	{
		const u8 r0 = bpf2a64[BPF_REG_0];
		bool func_addr_fixed;
		u64 func_addr;

		ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
					    &func_addr, &func_addr_fixed);
		if (ret < 0)
			return ret;
		emit_call(func_addr, ctx);
		emit(A64_MOV(1, r0, A64_R(0)), ctx);
		break;
	}
	/* tail call */
	case BPF_JMP | BPF_TAIL_CALL:
		if (emit_bpf_tail_call(ctx))
			return -EFAULT;
		break;
	/* function return */
	case BPF_JMP | BPF_EXIT:
		/* Optimization: when last instruction is EXIT,
		   simply fallthrough to epilogue. */
		if (i == ctx->prog->len - 1)
			break;
		jmp_offset = epilogue_offset(ctx);
		check_imm26(jmp_offset);
		emit(A64_B(jmp_offset), ctx);
		break;

	/* dst = imm64 */
	case BPF_LD | BPF_IMM | BPF_DW:
	{
		const struct bpf_insn insn1 = insn[1];
		u64 imm64;

		imm64 = (u64)insn1.imm << 32 | (u32)imm;
		if (bpf_pseudo_func(insn))
			emit_addr_mov_i64(dst, imm64, ctx);
		else
			emit_a64_mov_i64(dst, imm64, ctx);

		return 1;
	}

	/* LDX: dst = (u64)*(unsigned size *)(src + off) */
	case BPF_LDX | BPF_MEM | BPF_W:
	case BPF_LDX | BPF_MEM | BPF_H:
	case BPF_LDX | BPF_MEM | BPF_B:
	case BPF_LDX | BPF_MEM | BPF_DW:
	case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
	case BPF_LDX | BPF_PROBE_MEM | BPF_W:
	case BPF_LDX | BPF_PROBE_MEM | BPF_H:
	case BPF_LDX | BPF_PROBE_MEM | BPF_B:
	/* LDXS: dst_reg = (s64)*(signed size *)(src_reg + off) */
	case BPF_LDX | BPF_MEMSX | BPF_B:
	case BPF_LDX | BPF_MEMSX | BPF_H:
	case BPF_LDX | BPF_MEMSX | BPF_W:
	case BPF_LDX | BPF_PROBE_MEMSX | BPF_B:
	case BPF_LDX | BPF_PROBE_MEMSX | BPF_H:
	case BPF_LDX | BPF_PROBE_MEMSX | BPF_W:
		if (ctx->fpb_offset > 0 && src == fp) {
			src_adj = fpb;
			off_adj = off + ctx->fpb_offset;
		} else {
			src_adj = src;
			off_adj = off;
		}
		sign_extend = (BPF_MODE(insn->code) == BPF_MEMSX ||
				BPF_MODE(insn->code) == BPF_PROBE_MEMSX);
		switch (BPF_SIZE(code)) {
		case BPF_W:
			if (is_lsi_offset(off_adj, 2)) {
				if (sign_extend)
					emit(A64_LDRSWI(dst, src_adj, off_adj), ctx);
				else
					emit(A64_LDR32I(dst, src_adj, off_adj), ctx);
			} else {
				emit_a64_mov_i(1, tmp, off, ctx);
				if (sign_extend)
					emit(A64_LDRSW(dst, src, tmp), ctx);
				else
					emit(A64_LDR32(dst, src, tmp), ctx);
			}
			break;
		case BPF_H:
			if (is_lsi_offset(off_adj, 1)) {
				if (sign_extend)
					emit(A64_LDRSHI(dst, src_adj, off_adj), ctx);
				else
					emit(A64_LDRHI(dst, src_adj, off_adj), ctx);
			} else {
				emit_a64_mov_i(1, tmp, off, ctx);
				if (sign_extend)
					emit(A64_LDRSH(dst, src, tmp), ctx);
				else
					emit(A64_LDRH(dst, src, tmp), ctx);
			}
			break;
		case BPF_B:
			if (is_lsi_offset(off_adj, 0)) {
				if (sign_extend)
					emit(A64_LDRSBI(dst, src_adj, off_adj), ctx);
				else
					emit(A64_LDRBI(dst, src_adj, off_adj), ctx);
			} else {
				emit_a64_mov_i(1, tmp, off, ctx);
				if (sign_extend)
					emit(A64_LDRSB(dst, src, tmp), ctx);
				else
					emit(A64_LDRB(dst, src, tmp), ctx);
			}
			break;
		case BPF_DW:
			if (is_lsi_offset(off_adj, 3)) {
				emit(A64_LDR64I(dst, src_adj, off_adj), ctx);
			} else {
				emit_a64_mov_i(1, tmp, off, ctx);
				emit(A64_LDR64(dst, src, tmp), ctx);
			}
			break;
		}

		ret = add_exception_handler(insn, ctx, dst);
		if (ret)
			return ret;
		break;

	/* speculation barrier */
	case BPF_ST | BPF_NOSPEC:
		/*
		 * Nothing required here.
		 *
		 * In case of arm64, we rely on the firmware mitigation of
		 * Speculative Store Bypass as controlled via the ssbd kernel
		 * parameter. Whenever the mitigation is enabled, it works
		 * for all of the kernel code with no need to provide any
		 * additional instructions.
		 */
		break;

	/* ST: *(size *)(dst + off) = imm */
	case BPF_ST | BPF_MEM | BPF_W:
	case BPF_ST | BPF_MEM | BPF_H:
	case BPF_ST | BPF_MEM | BPF_B:
	case BPF_ST | BPF_MEM | BPF_DW:
		if (ctx->fpb_offset > 0 && dst == fp) {
			dst_adj = fpb;
			off_adj = off + ctx->fpb_offset;
		} else {
			dst_adj = dst;
			off_adj = off;
		}
		/* Load imm to a register then store it */
		emit_a64_mov_i(1, tmp, imm, ctx);
		switch (BPF_SIZE(code)) {
		case BPF_W:
			if (is_lsi_offset(off_adj, 2)) {
				emit(A64_STR32I(tmp, dst_adj, off_adj), ctx);
			} else {
				emit_a64_mov_i(1, tmp2, off, ctx);
				emit(A64_STR32(tmp, dst, tmp2), ctx);
			}
			break;
		case BPF_H:
			if (is_lsi_offset(off_adj, 1)) {
				emit(A64_STRHI(tmp, dst_adj, off_adj), ctx);
			} else {
				emit_a64_mov_i(1, tmp2, off, ctx);
				emit(A64_STRH(tmp, dst, tmp2), ctx);
			}
			break;
		case BPF_B:
			if (is_lsi_offset(off_adj, 0)) {
				emit(A64_STRBI(tmp, dst_adj, off_adj), ctx);
			} else {
				emit_a64_mov_i(1, tmp2, off, ctx);
				emit(A64_STRB(tmp, dst, tmp2), ctx);
			}
			break;
		case BPF_DW:
			if (is_lsi_offset(off_adj, 3)) {
				emit(A64_STR64I(tmp, dst_adj, off_adj), ctx);
			} else {
				emit_a64_mov_i(1, tmp2, off, ctx);
				emit(A64_STR64(tmp, dst, tmp2), ctx);
			}
			break;
		}
		break;

	/* STX: *(size *)(dst + off) = src */
	case BPF_STX | BPF_MEM | BPF_W:
	case BPF_STX | BPF_MEM | BPF_H:
	case BPF_STX | BPF_MEM | BPF_B:
	case BPF_STX | BPF_MEM | BPF_DW:
		if (ctx->fpb_offset > 0 && dst == fp) {
			dst_adj = fpb;
			off_adj = off + ctx->fpb_offset;
		} else {
			dst_adj = dst;
			off_adj = off;
		}
		switch (BPF_SIZE(code)) {
		case BPF_W:
			if (is_lsi_offset(off_adj, 2)) {
				emit(A64_STR32I(src, dst_adj, off_adj), ctx);
			} else {
				emit_a64_mov_i(1, tmp, off, ctx);
				emit(A64_STR32(src, dst, tmp), ctx);
			}
			break;
		case BPF_H:
			if (is_lsi_offset(off_adj, 1)) {
				emit(A64_STRHI(src, dst_adj, off_adj), ctx);
			} else {
				emit_a64_mov_i(1, tmp, off, ctx);
				emit(A64_STRH(src, dst, tmp), ctx);
			}
			break;
		case BPF_B:
			if (is_lsi_offset(off_adj, 0)) {
				emit(A64_STRBI(src, dst_adj, off_adj), ctx);
			} else {
				emit_a64_mov_i(1, tmp, off, ctx);
				emit(A64_STRB(src, dst, tmp), ctx);
			}
			break;
		case BPF_DW:
			if (is_lsi_offset(off_adj, 3)) {
				emit(A64_STR64I(src, dst_adj, off_adj), ctx);
			} else {
				emit_a64_mov_i(1, tmp, off, ctx);
				emit(A64_STR64(src, dst, tmp), ctx);
			}
			break;
		}
		break;

	case BPF_STX | BPF_ATOMIC | BPF_W:
	case BPF_STX | BPF_ATOMIC | BPF_DW:
		if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
			ret = emit_lse_atomic(insn, ctx);
		else
			ret = emit_ll_sc_atomic(insn, ctx);
		if (ret)
			return ret;
		break;

	default:
		pr_err_once("unknown opcode %02x\n", code);
		return -EINVAL;
	}

	return 0;
}

/*
 * Return 0 if FP may change at runtime, otherwise find the minimum negative
 * offset to FP, converts it to positive number, and align down to 8 bytes.
 */
static int find_fpb_offset(struct bpf_prog *prog)
{
	int i;
	int offset = 0;

	for (i = 0; i < prog->len; i++) {
		const struct bpf_insn *insn = &prog->insnsi[i];
		const u8 class = BPF_CLASS(insn->code);
		const u8 mode = BPF_MODE(insn->code);
		const u8 src = insn->src_reg;
		const u8 dst = insn->dst_reg;
		const s32 imm = insn->imm;
		const s16 off = insn->off;

		switch (class) {
		case BPF_STX:
		case BPF_ST:
			/* fp holds atomic operation result */
			if (class == BPF_STX && mode == BPF_ATOMIC &&
			    ((imm == BPF_XCHG ||
			      imm == (BPF_FETCH | BPF_ADD) ||
			      imm == (BPF_FETCH | BPF_AND) ||
			      imm == (BPF_FETCH | BPF_XOR) ||
			      imm == (BPF_FETCH | BPF_OR)) &&
			     src == BPF_REG_FP))
				return 0;

			if (mode == BPF_MEM && dst == BPF_REG_FP &&
			    off < offset)
				offset = insn->off;
			break;

		case BPF_JMP32:
		case BPF_JMP:
			break;

		case BPF_LDX:
		case BPF_LD:
			/* fp holds load result */
			if (dst == BPF_REG_FP)
				return 0;

			if (class == BPF_LDX && mode == BPF_MEM &&
			    src == BPF_REG_FP && off < offset)
				offset = off;
			break;

		case BPF_ALU:
		case BPF_ALU64:
		default:
			/* fp holds ALU result */
			if (dst == BPF_REG_FP)
				return 0;
		}
	}

	if (offset < 0) {
		/*
		 * safely be converted to a positive 'int', since insn->off
		 * is 's16'
		 */
		offset = -offset;
		/* align down to 8 bytes */
		offset = ALIGN_DOWN(offset, 8);
	}

	return offset;
}

static int build_body(struct jit_ctx *ctx, bool extra_pass)
{
	const struct bpf_prog *prog = ctx->prog;
	int i;

	/*
	 * - offset[0] offset of the end of prologue,
	 *   start of the 1st instruction.
	 * - offset[1] - offset of the end of 1st instruction,
	 *   start of the 2nd instruction
	 * [....]
	 * - offset[3] - offset of the end of 3rd instruction,
	 *   start of 4th instruction
	 */
	for (i = 0; i < prog->len; i++) {
		const struct bpf_insn *insn = &prog->insnsi[i];
		int ret;

		if (ctx->image == NULL)
			ctx->offset[i] = ctx->idx;
		ret = build_insn(insn, ctx, extra_pass);
		if (ret > 0) {
			i++;
			if (ctx->image == NULL)
				ctx->offset[i] = ctx->idx;
			continue;
		}
		if (ret)
			return ret;
	}
	/*
	 * offset is allocated with prog->len + 1 so fill in
	 * the last element with the offset after the last
	 * instruction (end of program)
	 */
	if (ctx->image == NULL)
		ctx->offset[i] = ctx->idx;

	return 0;
}

static int validate_code(struct jit_ctx *ctx)
{
	int i;

	for (i = 0; i < ctx->idx; i++) {
		u32 a64_insn = le32_to_cpu(ctx->image[i]);

		if (a64_insn == AARCH64_BREAK_FAULT)
			return -1;
	}
	return 0;
}

static int validate_ctx(struct jit_ctx *ctx)
{
	if (validate_code(ctx))
		return -1;

	if (WARN_ON_ONCE(ctx->exentry_idx != ctx->prog->aux->num_exentries))
		return -1;

	return 0;
}

static inline void bpf_flush_icache(void *start, void *end)
{
	flush_icache_range((unsigned long)start, (unsigned long)end);
}

struct arm64_jit_data {
	struct bpf_binary_header *header;
	u8 *ro_image;
	struct bpf_binary_header *ro_header;
	struct jit_ctx ctx;
};

struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
{
	int image_size, prog_size, extable_size, extable_align, extable_offset;
	struct bpf_prog *tmp, *orig_prog = prog;
	struct bpf_binary_header *header;
	struct bpf_binary_header *ro_header;
	struct arm64_jit_data *jit_data;
	bool was_classic = bpf_prog_was_classic(prog);
	bool tmp_blinded = false;
	bool extra_pass = false;
	struct jit_ctx ctx;
	u8 *image_ptr;
	u8 *ro_image_ptr;

	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;
	}
	if (jit_data->ctx.offset) {
		ctx = jit_data->ctx;
		ro_image_ptr = jit_data->ro_image;
		ro_header = jit_data->ro_header;
		header = jit_data->header;
		image_ptr = (void *)header + ((void *)ro_image_ptr
						 - (void *)ro_header);
		extra_pass = true;
		prog_size = sizeof(u32) * ctx.idx;
		goto skip_init_ctx;
	}
	memset(&ctx, 0, sizeof(ctx));
	ctx.prog = prog;

	ctx.offset = kvcalloc(prog->len + 1, sizeof(int), GFP_KERNEL);
	if (ctx.offset == NULL) {
		prog = orig_prog;
		goto out_off;
	}

	ctx.fpb_offset = find_fpb_offset(prog);

	/*
	 * 1. Initial fake pass to compute ctx->idx and ctx->offset.
	 *
	 * BPF line info needs ctx->offset[i] to be the offset of
	 * instruction[i] in jited image, so build prologue first.
	 */
	if (build_prologue(&ctx, was_classic, prog->aux->exception_cb)) {
		prog = orig_prog;
		goto out_off;
	}

	if (build_body(&ctx, extra_pass)) {
		prog = orig_prog;
		goto out_off;
	}

	ctx.epilogue_offset = ctx.idx;
	build_epilogue(&ctx, prog->aux->exception_cb);
	build_plt(&ctx);

	extable_align = __alignof__(struct exception_table_entry);
	extable_size = prog->aux->num_exentries *
		sizeof(struct exception_table_entry);

	/* Now we know the actual image size. */
	prog_size = sizeof(u32) * ctx.idx;
	/* also allocate space for plt target */
	extable_offset = round_up(prog_size + PLT_TARGET_SIZE, extable_align);
	image_size = extable_offset + extable_size;
	ro_header = bpf_jit_binary_pack_alloc(image_size, &ro_image_ptr,
					      sizeof(u32), &header, &image_ptr,
					      jit_fill_hole);
	if (!ro_header) {
		prog = orig_prog;
		goto out_off;
	}

	/* 2. Now, the actual pass. */

	/*
	 * Use the image(RW) for writing the JITed instructions. But also save
	 * the ro_image(RX) for calculating the offsets in the image. The RW
	 * image will be later copied to the RX image from where the program
	 * will run. The bpf_jit_binary_pack_finalize() will do this copy in the
	 * final step.
	 */
	ctx.image = (__le32 *)image_ptr;
	ctx.ro_image = (__le32 *)ro_image_ptr;
	if (extable_size)
		prog->aux->extable = (void *)ro_image_ptr + extable_offset;
skip_init_ctx:
	ctx.idx = 0;
	ctx.exentry_idx = 0;

	build_prologue(&ctx, was_classic, prog->aux->exception_cb);

	if (build_body(&ctx, extra_pass)) {
		prog = orig_prog;
		goto out_free_hdr;
	}

	build_epilogue(&ctx, prog->aux->exception_cb);
	build_plt(&ctx);

	/* 3. Extra pass to validate JITed code. */
	if (validate_ctx(&ctx)) {
		prog = orig_prog;
		goto out_free_hdr;
	}

	/* And we're done. */
	if (bpf_jit_enable > 1)
		bpf_jit_dump(prog->len, prog_size, 2, ctx.image);

	if (!prog->is_func || extra_pass) {
		if (extra_pass && ctx.idx != jit_data->ctx.idx) {
			pr_err_once("multi-func JIT bug %d != %d\n",
				    ctx.idx, jit_data->ctx.idx);
			prog->bpf_func = NULL;
			prog->jited = 0;
			prog->jited_len = 0;
			goto out_free_hdr;
		}
		if (WARN_ON(bpf_jit_binary_pack_finalize(prog, ro_header,
							 header))) {
			/* ro_header has been freed */
			ro_header = NULL;
			prog = orig_prog;
			goto out_off;
		}
		/*
		 * The instructions have now been copied to the ROX region from
		 * where they will execute. Now the data cache has to be cleaned to
		 * the PoU and the I-cache has to be invalidated for the VAs.
		 */
		bpf_flush_icache(ro_header, ctx.ro_image + ctx.idx);
	} else {
		jit_data->ctx = ctx;
		jit_data->ro_image = ro_image_ptr;
		jit_data->header = header;
		jit_data->ro_header = ro_header;
	}

	prog->bpf_func = (void *)ctx.ro_image;
	prog->jited = 1;
	prog->jited_len = prog_size;

	if (!prog->is_func || extra_pass) {
		int i;

		/* offset[prog->len] is the size of program */
		for (i = 0; i <= prog->len; i++)
			ctx.offset[i] *= AARCH64_INSN_SIZE;
		bpf_prog_fill_jited_linfo(prog, ctx.offset + 1);
out_off:
		kvfree(ctx.offset);
		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;

out_free_hdr:
	if (header) {
		bpf_arch_text_copy(&ro_header->size, &header->size,
				   sizeof(header->size));
		bpf_jit_binary_pack_free(ro_header, header);
	}
	goto out_off;
}

bool bpf_jit_supports_kfunc_call(void)
{
	return true;
}

void *bpf_arch_text_copy(void *dst, void *src, size_t len)
{
	if (!aarch64_insn_copy(dst, src, len))
		return ERR_PTR(-EINVAL);
	return dst;
}

u64 bpf_jit_alloc_exec_limit(void)
{
	return VMALLOC_END - VMALLOC_START;
}

void *bpf_jit_alloc_exec(unsigned long size)
{
	/* Memory is intended to be executable, reset the pointer tag. */
	return kasan_reset_tag(vmalloc(size));
}

void bpf_jit_free_exec(void *addr)
{
	return vfree(addr);
}

/* Indicate the JIT backend supports mixing bpf2bpf and tailcalls. */
bool bpf_jit_supports_subprog_tailcalls(void)
{
	return true;
}

static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l,
			    int args_off, int retval_off, int run_ctx_off,
			    bool save_ret)
{
	__le32 *branch;
	u64 enter_prog;
	u64 exit_prog;
	struct bpf_prog *p = l->link.prog;
	int cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie);

	enter_prog = (u64)bpf_trampoline_enter(p);
	exit_prog = (u64)bpf_trampoline_exit(p);

	if (l->cookie == 0) {
		/* if cookie is zero, one instruction is enough to store it */
		emit(A64_STR64I(A64_ZR, A64_SP, run_ctx_off + cookie_off), ctx);
	} else {
		emit_a64_mov_i64(A64_R(10), l->cookie, ctx);
		emit(A64_STR64I(A64_R(10), A64_SP, run_ctx_off + cookie_off),
		     ctx);
	}

	/* save p to callee saved register x19 to avoid loading p with mov_i64
	 * each time.
	 */
	emit_addr_mov_i64(A64_R(19), (const u64)p, ctx);

	/* arg1: prog */
	emit(A64_MOV(1, A64_R(0), A64_R(19)), ctx);
	/* arg2: &run_ctx */
	emit(A64_ADD_I(1, A64_R(1), A64_SP, run_ctx_off), ctx);

	emit_call(enter_prog, ctx);

	/* save return value to callee saved register x20 */
	emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx);

	/* if (__bpf_prog_enter(prog) == 0)
	 *         goto skip_exec_of_prog;
	 */
	branch = ctx->image + ctx->idx;
	emit(A64_NOP, ctx);

	emit(A64_ADD_I(1, A64_R(0), A64_SP, args_off), ctx);
	if (!p->jited)
		emit_addr_mov_i64(A64_R(1), (const u64)p->insnsi, ctx);

	emit_call((const u64)p->bpf_func, ctx);

	if (save_ret)
		emit(A64_STR64I(A64_R(0), A64_SP, retval_off), ctx);

	if (ctx->image) {
		int offset = &ctx->image[ctx->idx] - branch;
		*branch = cpu_to_le32(A64_CBZ(1, A64_R(0), offset));
	}

	/* arg1: prog */
	emit(A64_MOV(1, A64_R(0), A64_R(19)), ctx);
	/* arg2: start time */
	emit(A64_MOV(1, A64_R(1), A64_R(20)), ctx);
	/* arg3: &run_ctx */
	emit(A64_ADD_I(1, A64_R(2), A64_SP, run_ctx_off), ctx);

	emit_call(exit_prog, ctx);
}

static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_links *tl,
			       int args_off, int retval_off, int run_ctx_off,
			       __le32 **branches)
{
	int i;

	/* The first fmod_ret program will receive a garbage return value.
	 * Set this to 0 to avoid confusing the program.
	 */
	emit(A64_STR64I(A64_ZR, A64_SP, retval_off), ctx);
	for (i = 0; i < tl->nr_links; i++) {
		invoke_bpf_prog(ctx, tl->links[i], args_off, retval_off,
				run_ctx_off, true);
		/* if (*(u64 *)(sp + retval_off) !=  0)
		 *	goto do_fexit;
		 */
		emit(A64_LDR64I(A64_R(10), A64_SP, retval_off), ctx);
		/* Save the location of branch, and generate a nop.
		 * This nop will be replaced with a cbnz later.
		 */
		branches[i] = ctx->image + ctx->idx;
		emit(A64_NOP, ctx);
	}
}

static void save_args(struct jit_ctx *ctx, int args_off, int nregs)
{
	int i;

	for (i = 0; i < nregs; i++) {
		emit(A64_STR64I(i, A64_SP, args_off), ctx);
		args_off += 8;
	}
}

static void restore_args(struct jit_ctx *ctx, int args_off, int nregs)
{
	int i;

	for (i = 0; i < nregs; i++) {
		emit(A64_LDR64I(i, A64_SP, args_off), ctx);
		args_off += 8;
	}
}

/* Based on the x86's implementation of arch_prepare_bpf_trampoline().
 *
 * bpf prog and function entry before bpf trampoline hooked:
 *   mov x9, lr
 *   nop
 *
 * bpf prog and function entry after bpf trampoline hooked:
 *   mov x9, lr
 *   bl  <bpf_trampoline or plt>
 *
 */
static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
			      struct bpf_tramp_links *tlinks, void *func_addr,
			      int nregs, u32 flags)
{
	int i;
	int stack_size;
	int retaddr_off;
	int regs_off;
	int retval_off;
	int args_off;
	int nregs_off;
	int ip_off;
	int run_ctx_off;
	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
	bool save_ret;
	__le32 **branches = NULL;

	/* trampoline stack layout:
	 *                  [ parent ip         ]
	 *                  [ FP                ]
	 * SP + retaddr_off [ self ip           ]
	 *                  [ FP                ]
	 *
	 *                  [ padding           ] align SP to multiples of 16
	 *
	 *                  [ x20               ] callee saved reg x20
	 * SP + regs_off    [ x19               ] callee saved reg x19
	 *
	 * SP + retval_off  [ return value      ] BPF_TRAMP_F_CALL_ORIG or
	 *                                        BPF_TRAMP_F_RET_FENTRY_RET
	 *
	 *                  [ arg reg N         ]
	 *                  [ ...               ]
	 * SP + args_off    [ arg reg 1         ]
	 *
	 * SP + nregs_off   [ arg regs count    ]
	 *
	 * SP + ip_off      [ traced function   ] BPF_TRAMP_F_IP_ARG flag
	 *
	 * SP + run_ctx_off [ bpf_tramp_run_ctx ]
	 */

	stack_size = 0;
	run_ctx_off = stack_size;
	/* room for bpf_tramp_run_ctx */
	stack_size += round_up(sizeof(struct bpf_tramp_run_ctx), 8);

	ip_off = stack_size;
	/* room for IP address argument */
	if (flags & BPF_TRAMP_F_IP_ARG)
		stack_size += 8;

	nregs_off = stack_size;
	/* room for args count */
	stack_size += 8;

	args_off = stack_size;
	/* room for args */
	stack_size += nregs * 8;

	/* room for return value */
	retval_off = stack_size;
	save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET);
	if (save_ret)
		stack_size += 8;

	/* room for callee saved registers, currently x19 and x20 are used */
	regs_off = stack_size;
	stack_size += 16;

	/* round up to multiples of 16 to avoid SPAlignmentFault */
	stack_size = round_up(stack_size, 16);

	/* return address locates above FP */
	retaddr_off = stack_size + 8;

	/* bpf trampoline may be invoked by 3 instruction types:
	 * 1. bl, attached to bpf prog or kernel function via short jump
	 * 2. br, attached to bpf prog or kernel function via long jump
	 * 3. blr, working as a function pointer, used by struct_ops.
	 * So BTI_JC should used here to support both br and blr.
	 */
	emit_bti(A64_BTI_JC, ctx);

	/* frame for parent function */
	emit(A64_PUSH(A64_FP, A64_R(9), A64_SP), ctx);
	emit(A64_MOV(1, A64_FP, A64_SP), ctx);

	/* frame for patched function */
	emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
	emit(A64_MOV(1, A64_FP, A64_SP), ctx);

	/* allocate stack space */
	emit(A64_SUB_I(1, A64_SP, A64_SP, stack_size), ctx);

	if (flags & BPF_TRAMP_F_IP_ARG) {
		/* save ip address of the traced function */
		emit_addr_mov_i64(A64_R(10), (const u64)func_addr, ctx);
		emit(A64_STR64I(A64_R(10), A64_SP, ip_off), ctx);
	}

	/* save arg regs count*/
	emit(A64_MOVZ(1, A64_R(10), nregs, 0), ctx);
	emit(A64_STR64I(A64_R(10), A64_SP, nregs_off), ctx);

	/* save arg regs */
	save_args(ctx, args_off, nregs);

	/* save callee saved registers */
	emit(A64_STR64I(A64_R(19), A64_SP, regs_off), ctx);
	emit(A64_STR64I(A64_R(20), A64_SP, regs_off + 8), ctx);

	if (flags & BPF_TRAMP_F_CALL_ORIG) {
		emit_addr_mov_i64(A64_R(0), (const u64)im, ctx);
		emit_call((const u64)__bpf_tramp_enter, ctx);
	}

	for (i = 0; i < fentry->nr_links; i++)
		invoke_bpf_prog(ctx, fentry->links[i], args_off,
				retval_off, run_ctx_off,
				flags & BPF_TRAMP_F_RET_FENTRY_RET);

	if (fmod_ret->nr_links) {
		branches = kcalloc(fmod_ret->nr_links, sizeof(__le32 *),
				   GFP_KERNEL);
		if (!branches)
			return -ENOMEM;

		invoke_bpf_mod_ret(ctx, fmod_ret, args_off, retval_off,
				   run_ctx_off, branches);
	}

	if (flags & BPF_TRAMP_F_CALL_ORIG) {
		restore_args(ctx, args_off, nregs);
		/* call original func */
		emit(A64_LDR64I(A64_R(10), A64_SP, retaddr_off), ctx);
		emit(A64_ADR(A64_LR, AARCH64_INSN_SIZE * 2), ctx);
		emit(A64_RET(A64_R(10)), ctx);
		/* store return value */
		emit(A64_STR64I(A64_R(0), A64_SP, retval_off), ctx);
		/* reserve a nop for bpf_tramp_image_put */
		im->ip_after_call = ctx->ro_image + ctx->idx;
		emit(A64_NOP, ctx);
	}

	/* update the branches saved in invoke_bpf_mod_ret with cbnz */
	for (i = 0; i < fmod_ret->nr_links && ctx->image != NULL; i++) {
		int offset = &ctx->image[ctx->idx] - branches[i];
		*branches[i] = cpu_to_le32(A64_CBNZ(1, A64_R(10), offset));
	}

	for (i = 0; i < fexit->nr_links; i++)
		invoke_bpf_prog(ctx, fexit->links[i], args_off, retval_off,
				run_ctx_off, false);

	if (flags & BPF_TRAMP_F_CALL_ORIG) {
		im->ip_epilogue = ctx->ro_image + ctx->idx;
		emit_addr_mov_i64(A64_R(0), (const u64)im, ctx);
		emit_call((const u64)__bpf_tramp_exit, ctx);
	}

	if (flags & BPF_TRAMP_F_RESTORE_REGS)
		restore_args(ctx, args_off, nregs);

	/* restore callee saved register x19 and x20 */
	emit(A64_LDR64I(A64_R(19), A64_SP, regs_off), ctx);
	emit(A64_LDR64I(A64_R(20), A64_SP, regs_off + 8), ctx);

	if (save_ret)
		emit(A64_LDR64I(A64_R(0), A64_SP, retval_off), ctx);

	/* reset SP  */
	emit(A64_MOV(1, A64_SP, A64_FP), ctx);

	/* pop frames  */
	emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);
	emit(A64_POP(A64_FP, A64_R(9), A64_SP), ctx);

	if (flags & BPF_TRAMP_F_SKIP_FRAME) {
		/* skip patched function, return to parent */
		emit(A64_MOV(1, A64_LR, A64_R(9)), ctx);
		emit(A64_RET(A64_R(9)), ctx);
	} else {
		/* return to patched function */
		emit(A64_MOV(1, A64_R(10), A64_LR), ctx);
		emit(A64_MOV(1, A64_LR, A64_R(9)), ctx);
		emit(A64_RET(A64_R(10)), ctx);
	}

	kfree(branches);

	return ctx->idx;
}

static int btf_func_model_nregs(const struct btf_func_model *m)
{
	int nregs = m->nr_args;
	int i;

	/* extra registers needed for struct argument */
	for (i = 0; i < MAX_BPF_FUNC_ARGS; i++) {
		/* The arg_size is at most 16 bytes, enforced by the verifier. */
		if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG)
			nregs += (m->arg_size[i] + 7) / 8 - 1;
	}

	return nregs;
}

int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
			     struct bpf_tramp_links *tlinks, void *func_addr)
{
	struct jit_ctx ctx = {
		.image = NULL,
		.idx = 0,
	};
	struct bpf_tramp_image im;
	int nregs, ret;

	nregs = btf_func_model_nregs(m);
	/* the first 8 registers are used for arguments */
	if (nregs > 8)
		return -ENOTSUPP;

	ret = prepare_trampoline(&ctx, &im, tlinks, func_addr, nregs, flags);
	if (ret < 0)
		return ret;

	return ret < 0 ? ret : ret * AARCH64_INSN_SIZE;
}

void *arch_alloc_bpf_trampoline(unsigned int size)
{
	return bpf_prog_pack_alloc(size, jit_fill_hole);
}

void arch_free_bpf_trampoline(void *image, unsigned int size)
{
	bpf_prog_pack_free(image, size);
}

void arch_protect_bpf_trampoline(void *image, unsigned int size)
{
}

void arch_unprotect_bpf_trampoline(void *image, unsigned int size)
{
}

int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image,
				void *ro_image_end, const struct btf_func_model *m,
				u32 flags, struct bpf_tramp_links *tlinks,
				void *func_addr)
{
	int ret, nregs;
	void *image, *tmp;
	u32 size = ro_image_end - ro_image;

	/* image doesn't need to be in module memory range, so we can
	 * use kvmalloc.
	 */
	image = kvmalloc(size, GFP_KERNEL);
	if (!image)
		return -ENOMEM;

	struct jit_ctx ctx = {
		.image = image,
		.ro_image = ro_image,
		.idx = 0,
	};

	nregs = btf_func_model_nregs(m);
	/* the first 8 registers are used for arguments */
	if (nregs > 8)
		return -ENOTSUPP;

	jit_fill_hole(image, (unsigned int)(ro_image_end - ro_image));
	ret = prepare_trampoline(&ctx, im, tlinks, func_addr, nregs, flags);

	if (ret > 0 && validate_code(&ctx) < 0) {
		ret = -EINVAL;
		goto out;
	}

	if (ret > 0)
		ret *= AARCH64_INSN_SIZE;

	tmp = bpf_arch_text_copy(ro_image, image, size);
	if (IS_ERR(tmp)) {
		ret = PTR_ERR(tmp);
		goto out;
	}

	bpf_flush_icache(ro_image, ro_image + size);
out:
	kvfree(image);
	return ret;
}

static bool is_long_jump(void *ip, void *target)
{
	long offset;

	/* NULL target means this is a NOP */
	if (!target)
		return false;

	offset = (long)target - (long)ip;
	return offset < -SZ_128M || offset >= SZ_128M;
}

static int gen_branch_or_nop(enum aarch64_insn_branch_type type, void *ip,
			     void *addr, void *plt, u32 *insn)
{
	void *target;

	if (!addr) {
		*insn = aarch64_insn_gen_nop();
		return 0;
	}

	if (is_long_jump(ip, addr))
		target = plt;
	else
		target = addr;

	*insn = aarch64_insn_gen_branch_imm((unsigned long)ip,
					    (unsigned long)target,
					    type);

	return *insn != AARCH64_BREAK_FAULT ? 0 : -EFAULT;
}

/* Replace the branch instruction from @ip to @old_addr in a bpf prog or a bpf
 * trampoline with the branch instruction from @ip to @new_addr. If @old_addr
 * or @new_addr is NULL, the old or new instruction is NOP.
 *
 * When @ip is the bpf prog entry, a bpf trampoline is being attached or
 * detached. Since bpf trampoline and bpf prog are allocated separately with
 * vmalloc, the address distance may exceed 128MB, the maximum branch range.
 * So long jump should be handled.
 *
 * When a bpf prog is constructed, a plt pointing to empty trampoline
 * dummy_tramp is placed at the end:
 *
 *      bpf_prog:
 *              mov x9, lr
 *              nop // patchsite
 *              ...
 *              ret
 *
 *      plt:
 *              ldr x10, target
 *              br x10
 *      target:
 *              .quad dummy_tramp // plt target
 *
 * This is also the state when no trampoline is attached.
 *
 * When a short-jump bpf trampoline is attached, the patchsite is patched
 * to a bl instruction to the trampoline directly:
 *
 *      bpf_prog:
 *              mov x9, lr
 *              bl <short-jump bpf trampoline address> // patchsite
 *              ...
 *              ret
 *
 *      plt:
 *              ldr x10, target
 *              br x10
 *      target:
 *              .quad dummy_tramp // plt target
 *
 * When a long-jump bpf trampoline is attached, the plt target is filled with
 * the trampoline address and the patchsite is patched to a bl instruction to
 * the plt:
 *
 *      bpf_prog:
 *              mov x9, lr
 *              bl plt // patchsite
 *              ...
 *              ret
 *
 *      plt:
 *              ldr x10, target
 *              br x10
 *      target:
 *              .quad <long-jump bpf trampoline address> // plt target
 *
 * The dummy_tramp is used to prevent another CPU from jumping to unknown
 * locations during the patching process, making the patching process easier.
 */
int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
		       void *old_addr, void *new_addr)
{
	int ret;
	u32 old_insn;
	u32 new_insn;
	u32 replaced;
	struct bpf_plt *plt = NULL;
	unsigned long size = 0UL;
	unsigned long offset = ~0UL;
	enum aarch64_insn_branch_type branch_type;
	char namebuf[KSYM_NAME_LEN];
	void *image = NULL;
	u64 plt_target = 0ULL;
	bool poking_bpf_entry;

	if (!__bpf_address_lookup((unsigned long)ip, &size, &offset, namebuf))
		/* Only poking bpf text is supported. Since kernel function
		 * entry is set up by ftrace, we reply on ftrace to poke kernel
		 * functions.
		 */
		return -ENOTSUPP;

	image = ip - offset;
	/* zero offset means we're poking bpf prog entry */
	poking_bpf_entry = (offset == 0UL);

	/* bpf prog entry, find plt and the real patchsite */
	if (poking_bpf_entry) {
		/* plt locates at the end of bpf prog */
		plt = image + size - PLT_TARGET_OFFSET;

		/* skip to the nop instruction in bpf prog entry:
		 * bti c // if BTI enabled
		 * mov x9, x30
		 * nop
		 */
		ip = image + POKE_OFFSET * AARCH64_INSN_SIZE;
	}

	/* long jump is only possible at bpf prog entry */
	if (WARN_ON((is_long_jump(ip, new_addr) || is_long_jump(ip, old_addr)) &&
		    !poking_bpf_entry))
		return -EINVAL;

	if (poke_type == BPF_MOD_CALL)
		branch_type = AARCH64_INSN_BRANCH_LINK;
	else
		branch_type = AARCH64_INSN_BRANCH_NOLINK;

	if (gen_branch_or_nop(branch_type, ip, old_addr, plt, &old_insn) < 0)
		return -EFAULT;

	if (gen_branch_or_nop(branch_type, ip, new_addr, plt, &new_insn) < 0)
		return -EFAULT;

	if (is_long_jump(ip, new_addr))
		plt_target = (u64)new_addr;
	else if (is_long_jump(ip, old_addr))
		/* if the old target is a long jump and the new target is not,
		 * restore the plt target to dummy_tramp, so there is always a
		 * legal and harmless address stored in plt target, and we'll
		 * never jump from plt to an unknown place.
		 */
		plt_target = (u64)&dummy_tramp;

	if (plt_target) {
		/* non-zero plt_target indicates we're patching a bpf prog,
		 * which is read only.
		 */
		if (set_memory_rw(PAGE_MASK & ((uintptr_t)&plt->target), 1))
			return -EFAULT;
		WRITE_ONCE(plt->target, plt_target);
		set_memory_ro(PAGE_MASK & ((uintptr_t)&plt->target), 1);
		/* since plt target points to either the new trampoline
		 * or dummy_tramp, even if another CPU reads the old plt
		 * target value before fetching the bl instruction to plt,
		 * it will be brought back by dummy_tramp, so no barrier is
		 * required here.
		 */
	}

	/* if the old target and the new target are both long jumps, no
	 * patching is required
	 */
	if (old_insn == new_insn)
		return 0;

	mutex_lock(&text_mutex);
	if (aarch64_insn_read(ip, &replaced)) {
		ret = -EFAULT;
		goto out;
	}

	if (replaced != old_insn) {
		ret = -EFAULT;
		goto out;
	}

	/* We call aarch64_insn_patch_text_nosync() to replace instruction
	 * atomically, so no other CPUs will fetch a half-new and half-old
	 * instruction. But there is chance that another CPU executes the
	 * old instruction after the patching operation finishes (e.g.,
	 * pipeline not flushed, or icache not synchronized yet).
	 *
	 * 1. when a new trampoline is attached, it is not a problem for
	 *    different CPUs to jump to different trampolines temporarily.
	 *
	 * 2. when an old trampoline is freed, we should wait for all other
	 *    CPUs to exit the trampoline and make sure the trampoline is no
	 *    longer reachable, since bpf_tramp_image_put() function already
	 *    uses percpu_ref and task-based rcu to do the sync, no need to call
	 *    the sync version here, see bpf_tramp_image_put() for details.
	 */
	ret = aarch64_insn_patch_text_nosync(ip, new_insn);
out:
	mutex_unlock(&text_mutex);

	return ret;
}

bool bpf_jit_supports_ptr_xchg(void)
{
	return true;
}

bool bpf_jit_supports_exceptions(void)
{
	/* We unwind through both kernel frames starting from within bpf_throw
	 * call and BPF frames. Therefore we require FP unwinder to be enabled
	 * to walk kernel frames and reach BPF frames in the stack trace.
	 * ARM64 kernel is aways compiled with CONFIG_FRAME_POINTER=y
	 */
	return true;
}

void bpf_jit_free(struct bpf_prog *prog)
{
	if (prog->jited) {
		struct arm64_jit_data *jit_data = prog->aux->jit_data;
		struct bpf_binary_header *hdr;

		/*
		 * If we fail the final pass of JIT (from jit_subprogs),
		 * the program may not be finalized yet. Call finalize here
		 * before freeing it.
		 */
		if (jit_data) {
			bpf_arch_text_copy(&jit_data->ro_header->size, &jit_data->header->size,
					   sizeof(jit_data->header->size));
			kfree(jit_data);
		}
		hdr = bpf_jit_binary_pack_hdr(prog);
		bpf_jit_binary_pack_free(hdr, NULL);
		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog));
	}

	bpf_prog_unlock_free(prog);
}