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
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* BPF JIT compiler
*
* Copyright (C) 2011-2013 Eric Dumazet (eric.dumazet@gmail.com)
* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
*/
#include <linux/netdevice.h>
#include <linux/filter.h>
#include <linux/if_vlan.h>
#include <linux/bpf.h>
#include <linux/memory.h>
#include <linux/sort.h>
#include <asm/extable.h>
#include <asm/set_memory.h>
#include <asm/nospec-branch.h>
#include <asm/text-patching.h>
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); } 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)
#ifdef CONFIG_X86_KERNEL_IBT
#define EMIT_ENDBR() EMIT(gen_endbr(), 4)
#else
#define EMIT_ENDBR()
#endif
static bool is_imm8(int value)
{
return value <= 127 && value >= -128;
}
static bool is_simm32(s64 value)
{
return value == (s64)(s32)value;
}
static bool is_uimm32(u64 value)
{
return value == (u64)(u32)value;
}
/* mov dst, src */
#define EMIT_mov(DST, SRC) \
do { \
if (DST != SRC) \
EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \
} while (0)
static int bpf_size_to_x86_bytes(int bpf_size)
{
if (bpf_size == BPF_W)
return 4;
else if (bpf_size == BPF_H)
return 2;
else if (bpf_size == BPF_B)
return 1;
else if (bpf_size == BPF_DW)
return 4; /* imm32 */
else
return 0;
}
/*
* List of x86 cond jumps opcodes (. + s8)
* Add 0x10 (and an extra 0x0f) to generate far jumps (. + s32)
*/
#define X86_JB 0x72
#define X86_JAE 0x73
#define X86_JE 0x74
#define X86_JNE 0x75
#define X86_JBE 0x76
#define X86_JA 0x77
#define X86_JL 0x7C
#define X86_JGE 0x7D
#define X86_JLE 0x7E
#define X86_JG 0x7F
/* Pick a register outside of BPF range for JIT internal work */
#define AUX_REG (MAX_BPF_JIT_REG + 1)
#define X86_REG_R9 (MAX_BPF_JIT_REG + 2)
/*
* The following table maps BPF registers to x86-64 registers.
*
* x86-64 register R12 is unused, since if used as base address
* register in load/store instructions, it always needs an
* extra byte of encoding and is callee saved.
*
* x86-64 register R9 is not used by BPF programs, but can be used by BPF
* trampoline. x86-64 register R10 is used for blinding (if enabled).
*/
static const int reg2hex[] = {
[BPF_REG_0] = 0, /* RAX */
[BPF_REG_1] = 7, /* RDI */
[BPF_REG_2] = 6, /* RSI */
[BPF_REG_3] = 2, /* RDX */
[BPF_REG_4] = 1, /* RCX */
[BPF_REG_5] = 0, /* R8 */
[BPF_REG_6] = 3, /* RBX callee saved */
[BPF_REG_7] = 5, /* R13 callee saved */
[BPF_REG_8] = 6, /* R14 callee saved */
[BPF_REG_9] = 7, /* R15 callee saved */
[BPF_REG_FP] = 5, /* RBP readonly */
[BPF_REG_AX] = 2, /* R10 temp register */
[AUX_REG] = 3, /* R11 temp register */
[X86_REG_R9] = 1, /* R9 register, 6th function argument */
};
static const int reg2pt_regs[] = {
[BPF_REG_0] = offsetof(struct pt_regs, ax),
[BPF_REG_1] = offsetof(struct pt_regs, di),
[BPF_REG_2] = offsetof(struct pt_regs, si),
[BPF_REG_3] = offsetof(struct pt_regs, dx),
[BPF_REG_4] = offsetof(struct pt_regs, cx),
[BPF_REG_5] = offsetof(struct pt_regs, r8),
[BPF_REG_6] = offsetof(struct pt_regs, bx),
[BPF_REG_7] = offsetof(struct pt_regs, r13),
[BPF_REG_8] = offsetof(struct pt_regs, r14),
[BPF_REG_9] = offsetof(struct pt_regs, r15),
};
/*
* is_ereg() == true if BPF register 'reg' maps to x86-64 r8..r15
* which need extra byte of encoding.
* rax,rcx,...,rbp have simpler encoding
*/
static bool is_ereg(u32 reg)
{
return (1 << reg) & (BIT(BPF_REG_5) |
BIT(AUX_REG) |
BIT(BPF_REG_7) |
BIT(BPF_REG_8) |
BIT(BPF_REG_9) |
BIT(X86_REG_R9) |
BIT(BPF_REG_AX));
}
/*
* is_ereg_8l() == true if BPF register 'reg' is mapped to access x86-64
* lower 8-bit registers dil,sil,bpl,spl,r8b..r15b, which need extra byte
* of encoding. al,cl,dl,bl have simpler encoding.
*/
static bool is_ereg_8l(u32 reg)
{
return is_ereg(reg) ||
(1 << reg) & (BIT(BPF_REG_1) |
BIT(BPF_REG_2) |
BIT(BPF_REG_FP));
}
static bool is_axreg(u32 reg)
{
return reg == BPF_REG_0;
}
/* Add modifiers if 'reg' maps to x86-64 registers R8..R15 */
static u8 add_1mod(u8 byte, u32 reg)
{
if (is_ereg(reg))
byte |= 1;
return byte;
}
static u8 add_2mod(u8 byte, u32 r1, u32 r2)
{
if (is_ereg(r1))
byte |= 1;
if (is_ereg(r2))
byte |= 4;
return byte;
}
/* Encode 'dst_reg' register into x86-64 opcode 'byte' */
static u8 add_1reg(u8 byte, u32 dst_reg)
{
return byte + reg2hex[dst_reg];
}
/* Encode 'dst_reg' and 'src_reg' registers into x86-64 opcode 'byte' */
static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
{
return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3);
}
/* Some 1-byte opcodes for binary ALU operations */
static u8 simple_alu_opcodes[] = {
[BPF_ADD] = 0x01,
[BPF_SUB] = 0x29,
[BPF_AND] = 0x21,
[BPF_OR] = 0x09,
[BPF_XOR] = 0x31,
[BPF_LSH] = 0xE0,
[BPF_RSH] = 0xE8,
[BPF_ARSH] = 0xF8,
};
static void jit_fill_hole(void *area, unsigned int size)
{
/* Fill whole space with INT3 instructions */
memset(area, 0xcc, size);
}
int bpf_arch_text_invalidate(void *dst, size_t len)
{
return IS_ERR_OR_NULL(text_poke_set(dst, 0xcc, len));
}
struct jit_context {
int cleanup_addr; /* Epilogue code offset */
/*
* Program specific offsets of labels in the code; these rely on the
* JIT doing at least 2 passes, recording the position on the first
* pass, only to generate the correct offset on the second pass.
*/
int tail_call_direct_label;
int tail_call_indirect_label;
};
/* Maximum number of bytes emitted while JITing one eBPF insn */
#define BPF_MAX_INSN_SIZE 128
#define BPF_INSN_SAFETY 64
/* Number of bytes emit_patch() needs to generate instructions */
#define X86_PATCH_SIZE 5
/* Number of bytes that will be skipped on tailcall */
#define X86_TAIL_CALL_OFFSET (11 + ENDBR_INSN_SIZE)
static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
{
u8 *prog = *pprog;
if (callee_regs_used[0])
EMIT1(0x53); /* push rbx */
if (callee_regs_used[1])
EMIT2(0x41, 0x55); /* push r13 */
if (callee_regs_used[2])
EMIT2(0x41, 0x56); /* push r14 */
if (callee_regs_used[3])
EMIT2(0x41, 0x57); /* push r15 */
*pprog = prog;
}
static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
{
u8 *prog = *pprog;
if (callee_regs_used[3])
EMIT2(0x41, 0x5F); /* pop r15 */
if (callee_regs_used[2])
EMIT2(0x41, 0x5E); /* pop r14 */
if (callee_regs_used[1])
EMIT2(0x41, 0x5D); /* pop r13 */
if (callee_regs_used[0])
EMIT1(0x5B); /* pop rbx */
*pprog = prog;
}
/*
* Emit x86-64 prologue code for BPF program.
* bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes
* while jumping to another program
*/
static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
bool tail_call_reachable, bool is_subprog)
{
u8 *prog = *pprog;
/* BPF trampoline can be made to work without these nops,
* but let's waste 5 bytes for now and optimize later
*/
EMIT_ENDBR();
memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
prog += X86_PATCH_SIZE;
if (!ebpf_from_cbpf) {
if (tail_call_reachable && !is_subprog)
EMIT2(0x31, 0xC0); /* xor eax, eax */
else
EMIT2(0x66, 0x90); /* nop2 */
}
EMIT1(0x55); /* push rbp */
EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
/* X86_TAIL_CALL_OFFSET is here */
EMIT_ENDBR();
/* sub rsp, rounded_stack_depth */
if (stack_depth)
EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8));
if (tail_call_reachable)
EMIT1(0x50); /* push rax */
*pprog = prog;
}
static int emit_patch(u8 **pprog, void *func, void *ip, u8 opcode)
{
u8 *prog = *pprog;
s64 offset;
offset = func - (ip + X86_PATCH_SIZE);
if (!is_simm32(offset)) {
pr_err("Target call %p is out of range\n", func);
return -ERANGE;
}
EMIT1_off32(opcode, offset);
*pprog = prog;
return 0;
}
static int emit_call(u8 **pprog, void *func, void *ip)
{
return emit_patch(pprog, func, ip, 0xE8);
}
static int emit_jump(u8 **pprog, void *func, void *ip)
{
return emit_patch(pprog, func, ip, 0xE9);
}
static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
void *old_addr, void *new_addr)
{
const u8 *nop_insn = x86_nops[5];
u8 old_insn[X86_PATCH_SIZE];
u8 new_insn[X86_PATCH_SIZE];
u8 *prog;
int ret;
memcpy(old_insn, nop_insn, X86_PATCH_SIZE);
if (old_addr) {
prog = old_insn;
ret = t == BPF_MOD_CALL ?
emit_call(&prog, old_addr, ip) :
emit_jump(&prog, old_addr, ip);
if (ret)
return ret;
}
memcpy(new_insn, nop_insn, X86_PATCH_SIZE);
if (new_addr) {
prog = new_insn;
ret = t == BPF_MOD_CALL ?
emit_call(&prog, new_addr, ip) :
emit_jump(&prog, new_addr, ip);
if (ret)
return ret;
}
ret = -EBUSY;
mutex_lock(&text_mutex);
if (memcmp(ip, old_insn, X86_PATCH_SIZE))
goto out;
ret = 1;
if (memcmp(ip, new_insn, X86_PATCH_SIZE)) {
text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL);
ret = 0;
}
out:
mutex_unlock(&text_mutex);
return ret;
}
int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
void *old_addr, void *new_addr)
{
if (!is_kernel_text((long)ip) &&
!is_bpf_text_address((long)ip))
/* BPF poking in modules is not supported */
return -EINVAL;
/*
* See emit_prologue(), for IBT builds the trampoline hook is preceded
* with an ENDBR instruction.
*/
if (is_endbr(*(u32 *)ip))
ip += ENDBR_INSN_SIZE;
return __bpf_arch_text_poke(ip, t, old_addr, new_addr);
}
#define EMIT_LFENCE() EMIT3(0x0F, 0xAE, 0xE8)
static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
{
u8 *prog = *pprog;
if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
EMIT_LFENCE();
EMIT2(0xFF, 0xE0 + reg);
} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) {
OPTIMIZER_HIDE_VAR(reg);
emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip);
} else {
EMIT2(0xFF, 0xE0 + reg); /* jmp *%\reg */
if (IS_ENABLED(CONFIG_RETPOLINE) || IS_ENABLED(CONFIG_SLS))
EMIT1(0xCC); /* int3 */
}
*pprog = prog;
}
static void emit_return(u8 **pprog, u8 *ip)
{
u8 *prog = *pprog;
if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
emit_jump(&prog, &__x86_return_thunk, ip);
} else {
EMIT1(0xC3); /* ret */
if (IS_ENABLED(CONFIG_SLS))
EMIT1(0xCC); /* int3 */
}
*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_indirect(u8 **pprog, bool *callee_regs_used,
u32 stack_depth, u8 *ip,
struct jit_context *ctx)
{
int tcc_off = -4 - round_up(stack_depth, 8);
u8 *prog = *pprog, *start = *pprog;
int offset;
/*
* 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));
offset = ctx->tail_call_indirect_label - (prog + 2 - start);
EMIT2(X86_JBE, offset); /* jbe out */
/*
* if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT)
* goto out;
*/
EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */
EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */
offset = ctx->tail_call_indirect_label - (prog + 2 - start);
EMIT2(X86_JAE, offset); /* jae out */
EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */
EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */
/* prog = array->ptrs[index]; */
EMIT4_off32(0x48, 0x8B, 0x8C, 0xD6, /* mov rcx, [rsi + rdx * 8 + offsetof(...)] */
offsetof(struct bpf_array, ptrs));
/*
* if (prog == NULL)
* goto out;
*/
EMIT3(0x48, 0x85, 0xC9); /* test rcx,rcx */
offset = ctx->tail_call_indirect_label - (prog + 2 - start);
EMIT2(X86_JE, offset); /* je out */
pop_callee_regs(&prog, callee_regs_used);
EMIT1(0x58); /* pop rax */
if (stack_depth)
EMIT3_off32(0x48, 0x81, 0xC4, /* add rsp, sd */
round_up(stack_depth, 8));
/* goto *(prog->bpf_func + X86_TAIL_CALL_OFFSET); */
EMIT4(0x48, 0x8B, 0x49, /* mov rcx, qword ptr [rcx + 32] */
offsetof(struct bpf_prog, bpf_func));
EMIT4(0x48, 0x83, 0xC1, /* add rcx, X86_TAIL_CALL_OFFSET */
X86_TAIL_CALL_OFFSET);
/*
* Now we're ready to jump into next BPF program
* rdi == ctx (1st arg)
* rcx == prog->bpf_func + X86_TAIL_CALL_OFFSET
*/
emit_indirect_jump(&prog, 1 /* rcx */, ip + (prog - start));
/* out: */
ctx->tail_call_indirect_label = prog - start;
*pprog = prog;
}
static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
u8 **pprog, u8 *ip,
bool *callee_regs_used, u32 stack_depth,
struct jit_context *ctx)
{
int tcc_off = -4 - round_up(stack_depth, 8);
u8 *prog = *pprog, *start = *pprog;
int offset;
/*
* if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT)
* goto out;
*/
EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */
EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */
offset = ctx->tail_call_direct_label - (prog + 2 - start);
EMIT2(X86_JAE, offset); /* jae out */
EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */
EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */
poke->tailcall_bypass = ip + (prog - start);
poke->adj_off = X86_TAIL_CALL_OFFSET;
poke->tailcall_target = ip + ctx->tail_call_direct_label - X86_PATCH_SIZE;
poke->bypass_addr = (u8 *)poke->tailcall_target + X86_PATCH_SIZE;
emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE,
poke->tailcall_bypass);
pop_callee_regs(&prog, callee_regs_used);
EMIT1(0x58); /* pop rax */
if (stack_depth)
EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
prog += X86_PATCH_SIZE;
/* out: */
ctx->tail_call_direct_label = prog - start;
*pprog = prog;
}
static void bpf_tail_call_direct_fixup(struct bpf_prog *prog)
{
struct bpf_jit_poke_descriptor *poke;
struct bpf_array *array;
struct bpf_prog *target;
int i, ret;
for (i = 0; i < prog->aux->size_poke_tab; i++) {
poke = &prog->aux->poke_tab[i];
if (poke->aux && poke->aux != prog->aux)
continue;
WARN_ON_ONCE(READ_ONCE(poke->tailcall_target_stable));
if (poke->reason != BPF_POKE_REASON_TAIL_CALL)
continue;
array = container_of(poke->tail_call.map, struct bpf_array, map);
mutex_lock(&array->aux->poke_mutex);
target = array->ptrs[poke->tail_call.key];
if (target) {
ret = __bpf_arch_text_poke(poke->tailcall_target,
BPF_MOD_JUMP, NULL,
(u8 *)target->bpf_func +
poke->adj_off);
BUG_ON(ret < 0);
ret = __bpf_arch_text_poke(poke->tailcall_bypass,
BPF_MOD_JUMP,
(u8 *)poke->tailcall_target +
X86_PATCH_SIZE, NULL);
BUG_ON(ret < 0);
}
WRITE_ONCE(poke->tailcall_target_stable, true);
mutex_unlock(&array->aux->poke_mutex);
}
}
static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
u32 dst_reg, const u32 imm32)
{
u8 *prog = *pprog;
u8 b1, b2, b3;
/*
* 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;
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;
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;
}
/* Emit the suffix (ModR/M etc) for addressing *(ptr_reg + off) and val_reg */
static void emit_insn_suffix(u8 **pprog, u32 ptr_reg, u32 val_reg, int off)
{
u8 *prog = *pprog;
if (is_imm8(off)) {
/* 1-byte signed displacement.
*
* If off == 0 we could skip this and save one extra byte, but
* special case of x86 R13 which always needs an offset is not
* worth the hassle
*/
EMIT2(add_2reg(0x40, ptr_reg, val_reg), off);
} else {
/* 4-byte signed displacement */
EMIT1_off32(add_2reg(0x80, ptr_reg, val_reg), off);
}
*pprog = prog;
}
/*
* Emit a REX byte if it will be necessary to address these registers
*/
static void maybe_emit_mod(u8 **pprog, u32 dst_reg, u32 src_reg, bool is64)
{
u8 *prog = *pprog;
if (is64)
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));
*pprog = prog;
}
/*
* Similar version of maybe_emit_mod() for a single register
*/
static void maybe_emit_1mod(u8 **pprog, u32 reg, bool is64)
{
u8 *prog = *pprog;
if (is64)
EMIT1(add_1mod(0x48, reg));
else if (is_ereg(reg))
EMIT1(add_1mod(0x40, 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;
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;
}
emit_insn_suffix(&prog, 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;
switch (size) {
case BPF_B:
/* Emit 'mov byte ptr [rax + off], al' */
if (is_ereg(dst_reg) || is_ereg_8l(src_reg))
/* Add extra byte for eregs or SIL,DIL,BPL in src_reg */
EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88);
else
EMIT1(0x88);
break;
case BPF_H:
if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT3(0x66, add_2mod(0x40, dst_reg, src_reg), 0x89);
else
EMIT2(0x66, 0x89);
break;
case BPF_W:
if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x89);
else
EMIT1(0x89);
break;
case BPF_DW:
EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89);
break;
}
emit_insn_suffix(&prog, dst_reg, src_reg, off);
*pprog = prog;
}
static int emit_atomic(u8 **pprog, u8 atomic_op,
u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size)
{
u8 *prog = *pprog;
EMIT1(0xF0); /* lock prefix */
maybe_emit_mod(&prog, dst_reg, src_reg, bpf_size == BPF_DW);
/* emit opcode */
switch (atomic_op) {
case BPF_ADD:
case BPF_AND:
case BPF_OR:
case BPF_XOR:
/* lock *(u32/u64*)(dst_reg + off) <op>= src_reg */
EMIT1(simple_alu_opcodes[atomic_op]);
break;
case BPF_ADD | BPF_FETCH:
/* src_reg = atomic_fetch_add(dst_reg + off, src_reg); */
EMIT2(0x0F, 0xC1);
break;
case BPF_XCHG:
/* src_reg = atomic_xchg(dst_reg + off, src_reg); */
EMIT1(0x87);
break;
case BPF_CMPXCHG:
/* r0 = atomic_cmpxchg(dst_reg + off, r0, src_reg); */
EMIT2(0x0F, 0xB1);
break;
default:
pr_err("bpf_jit: unknown atomic opcode %02x\n", atomic_op);
return -EFAULT;
}
emit_insn_suffix(&prog, dst_reg, src_reg, off);
*pprog = prog;
return 0;
}
bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs)
{
u32 reg = x->fixup >> 8;
/* jump over faulting load and clear dest register */
*(unsigned long *)((void *)regs + reg) = 0;
regs->ip += x->fixup & 0xff;
return true;
}
static void detect_reg_usage(struct bpf_insn *insn, int insn_cnt,
bool *regs_used, bool *tail_call_seen)
{
int i;
for (i = 1; i <= insn_cnt; i++, insn++) {
if (insn->code == (BPF_JMP | BPF_TAIL_CALL))
*tail_call_seen = true;
if (insn->dst_reg == BPF_REG_6 || insn->src_reg == BPF_REG_6)
regs_used[0] = true;
if (insn->dst_reg == BPF_REG_7 || insn->src_reg == BPF_REG_7)
regs_used[1] = true;
if (insn->dst_reg == BPF_REG_8 || insn->src_reg == BPF_REG_8)
regs_used[2] = true;
if (insn->dst_reg == BPF_REG_9 || insn->src_reg == BPF_REG_9)
regs_used[3] = true;
}
}
static void emit_nops(u8 **pprog, int len)
{
u8 *prog = *pprog;
int i, noplen;
while (len > 0) {
noplen = len;
if (noplen > ASM_NOP_MAX)
noplen = ASM_NOP_MAX;
for (i = 0; i < noplen; i++)
EMIT1(x86_nops[noplen][i]);
len -= noplen;
}
*pprog = prog;
}
/* emit the 3-byte VEX prefix
*
* r: same as rex.r, extra bit for ModRM reg field
* x: same as rex.x, extra bit for SIB index field
* b: same as rex.b, extra bit for ModRM r/m, or SIB base
* m: opcode map select, encoding escape bytes e.g. 0x0f38
* w: same as rex.w (32 bit or 64 bit) or opcode specific
* src_reg2: additional source reg (encoded as BPF reg)
* l: vector length (128 bit or 256 bit) or reserved
* pp: opcode prefix (none, 0x66, 0xf2 or 0xf3)
*/
static void emit_3vex(u8 **pprog, bool r, bool x, bool b, u8 m,
bool w, u8 src_reg2, bool l, u8 pp)
{
u8 *prog = *pprog;
const u8 b0 = 0xc4; /* first byte of 3-byte VEX prefix */
u8 b1, b2;
u8 vvvv = reg2hex[src_reg2];
/* reg2hex gives only the lower 3 bit of vvvv */
if (is_ereg(src_reg2))
vvvv |= 1 << 3;
/*
* 2nd byte of 3-byte VEX prefix
* ~ means bit inverted encoding
*
* 7 0
* +---+---+---+---+---+---+---+---+
* |~R |~X |~B | m |
* +---+---+---+---+---+---+---+---+
*/
b1 = (!r << 7) | (!x << 6) | (!b << 5) | (m & 0x1f);
/*
* 3rd byte of 3-byte VEX prefix
*
* 7 0
* +---+---+---+---+---+---+---+---+
* | W | ~vvvv | L | pp |
* +---+---+---+---+---+---+---+---+
*/
b2 = (w << 7) | ((~vvvv & 0xf) << 3) | (l << 2) | (pp & 3);
EMIT3(b0, b1, b2);
*pprog = prog;
}
/* emit BMI2 shift instruction */
static void emit_shiftx(u8 **pprog, u32 dst_reg, u8 src_reg, bool is64, u8 op)
{
u8 *prog = *pprog;
bool r = is_ereg(dst_reg);
u8 m = 2; /* escape code 0f38 */
emit_3vex(&prog, r, false, r, m, is64, src_reg, false, op);
EMIT2(0xf7, add_2reg(0xC0, dst_reg, dst_reg));
*pprog = prog;
}
#define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp)))
static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image,
int oldproglen, struct jit_context *ctx, bool jmp_padding)
{
bool tail_call_reachable = bpf_prog->aux->tail_call_reachable;
struct bpf_insn *insn = bpf_prog->insnsi;
bool callee_regs_used[4] = {};
int insn_cnt = bpf_prog->len;
bool tail_call_seen = false;
bool seen_exit = false;
u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
int i, excnt = 0;
int ilen, proglen = 0;
u8 *prog = temp;
int err;
detect_reg_usage(insn, insn_cnt, callee_regs_used,
&tail_call_seen);
/* tail call's presence in current prog implies it is reachable */
tail_call_reachable |= tail_call_seen;
emit_prologue(&prog, bpf_prog->aux->stack_depth,
bpf_prog_was_classic(bpf_prog), tail_call_reachable,
bpf_prog->aux->func_idx != 0);
push_callee_regs(&prog, callee_regs_used);
ilen = prog - temp;
if (rw_image)
memcpy(rw_image + proglen, temp, ilen);
proglen += ilen;
addrs[0] = proglen;
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;
u8 *start_of_ldx;
s64 jmp_offset;
u8 jmp_cond;
u8 *func;
int nops;
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:
maybe_emit_mod(&prog, dst_reg, src_reg,
BPF_CLASS(insn->code) == BPF_ALU64);
b2 = simple_alu_opcodes[BPF_OP(insn->code)];
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:
maybe_emit_1mod(&prog, dst_reg,
BPF_CLASS(insn->code) == BPF_ALU64);
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:
maybe_emit_1mod(&prog, dst_reg,
BPF_CLASS(insn->code) == BPF_ALU64);
/*
* 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: {
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 */
if (BPF_SRC(insn->code) == BPF_X) {
if (src_reg == BPF_REG_0 ||
src_reg == BPF_REG_3) {
/* mov r11, src_reg */
EMIT_mov(AUX_REG, src_reg);
src_reg = AUX_REG;
}
} else {
/* mov r11, imm32 */
EMIT3_off32(0x49, 0xC7, 0xC3, imm32);
src_reg = AUX_REG;
}
if (dst_reg != BPF_REG_0)
/* mov rax, dst_reg */
emit_mov_reg(&prog, is64, BPF_REG_0, dst_reg);
/*
* xor edx, edx
* equivalent to 'xor rdx, rdx', but one byte less
*/
EMIT2(0x31, 0xd2);
/* div src_reg */
maybe_emit_1mod(&prog, src_reg, is64);
EMIT2(0xF7, add_1reg(0xF0, src_reg));
if (BPF_OP(insn->code) == BPF_MOD &&
dst_reg != BPF_REG_3)
/* mov dst_reg, rdx */
emit_mov_reg(&prog, is64, dst_reg, BPF_REG_3);
else if (BPF_OP(insn->code) == BPF_DIV &&
dst_reg != BPF_REG_0)
/* mov dst_reg, rax */
emit_mov_reg(&prog, is64, dst_reg, BPF_REG_0);
if (dst_reg != BPF_REG_3)
EMIT1(0x5A); /* pop rdx */
if (dst_reg != BPF_REG_0)
EMIT1(0x58); /* pop rax */
break;
}
case BPF_ALU | BPF_MUL | BPF_K:
case BPF_ALU64 | BPF_MUL | BPF_K:
maybe_emit_mod(&prog, dst_reg, dst_reg,
BPF_CLASS(insn->code) == BPF_ALU64);
if (is_imm8(imm32))
/* imul dst_reg, dst_reg, imm8 */
EMIT3(0x6B, add_2reg(0xC0, dst_reg, dst_reg),
imm32);
else
/* imul dst_reg, dst_reg, imm32 */
EMIT2_off32(0x69,
add_2reg(0xC0, dst_reg, dst_reg),
imm32);
break;
case BPF_ALU | BPF_MUL | BPF_X:
case BPF_ALU64 | BPF_MUL | BPF_X:
maybe_emit_mod(&prog, src_reg, dst_reg,
BPF_CLASS(insn->code) == BPF_ALU64);
/* imul dst_reg, src_reg */
EMIT3(0x0F, 0xAF, add_2reg(0xC0, src_reg, dst_reg));
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:
maybe_emit_1mod(&prog, dst_reg,
BPF_CLASS(insn->code) == BPF_ALU64);
b3 = simple_alu_opcodes[BPF_OP(insn->code)];
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:
/* BMI2 shifts aren't better when shift count is already in rcx */
if (boot_cpu_has(X86_FEATURE_BMI2) && src_reg != BPF_REG_4) {
/* shrx/sarx/shlx dst_reg, dst_reg, src_reg */
bool w = (BPF_CLASS(insn->code) == BPF_ALU64);
u8 op;
switch (BPF_OP(insn->code)) {
case BPF_LSH:
op = 1; /* prefix 0x66 */
break;
case BPF_RSH:
op = 3; /* prefix 0xf2 */
break;
case BPF_ARSH:
op = 2; /* prefix 0xf3 */
break;
}
emit_shiftx(&prog, dst_reg, src_reg, w, op);
break;
}
if (src_reg != BPF_REG_4) { /* common case */
/* 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;
} else {
EMIT1(0x51); /* push rcx */
}
/* mov rcx, src_reg */
EMIT_mov(BPF_REG_4, src_reg);
}
/* shl %rax, %cl | shr %rax, %cl | sar %rax, %cl */
maybe_emit_1mod(&prog, dst_reg,
BPF_CLASS(insn->code) == BPF_ALU64);
b3 = simple_alu_opcodes[BPF_OP(insn->code)];
EMIT2(0xD3, add_1reg(b3, dst_reg));
if (src_reg != BPF_REG_4) {
if (insn->dst_reg == BPF_REG_4)
/* mov dst_reg, r11 */
EMIT_mov(insn->dst_reg, AUX_REG);
else
EMIT1(0x59); /* pop rcx */
}
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;
/* speculation barrier */
case BPF_ST | BPF_NOSPEC:
EMIT_LFENCE();
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:
if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
/* Though the verifier prevents negative insn->off in BPF_PROBE_MEM
* add abs(insn->off) to the limit to make sure that negative
* offset won't be an issue.
* insn->off is s16, so it won't affect valid pointers.
*/
u64 limit = TASK_SIZE_MAX + PAGE_SIZE + abs(insn->off);
u8 *end_of_jmp1, *end_of_jmp2;
/* Conservatively check that src_reg + insn->off is a kernel address:
* 1. src_reg + insn->off >= limit
* 2. src_reg + insn->off doesn't become small positive.
* Cannot do src_reg + insn->off >= limit in one branch,
* since it needs two spare registers, but JIT has only one.
*/
/* movabsq r11, limit */
EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG));
EMIT((u32)limit, 4);
EMIT(limit >> 32, 4);
/* cmp src_reg, r11 */
maybe_emit_mod(&prog, src_reg, AUX_REG, true);
EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG));
/* if unsigned '<' goto end_of_jmp2 */
EMIT2(X86_JB, 0);
end_of_jmp1 = prog;
/* mov r11, src_reg */
emit_mov_reg(&prog, true, AUX_REG, src_reg);
/* add r11, insn->off */
maybe_emit_1mod(&prog, AUX_REG, true);
EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off);
/* jmp if not carry to start_of_ldx
* Otherwise ERR_PTR(-EINVAL) + 128 will be the user addr
* that has to be rejected.
*/
EMIT2(0x73 /* JNC */, 0);
end_of_jmp2 = prog;
/* xor dst_reg, dst_reg */
emit_mov_imm32(&prog, false, dst_reg, 0);
/* jmp byte_after_ldx */
EMIT2(0xEB, 0);
/* populate jmp_offset for JB above to jump to xor dst_reg */
end_of_jmp1[-1] = end_of_jmp2 - end_of_jmp1;
/* populate jmp_offset for JNC above to jump to start_of_ldx */
start_of_ldx = prog;
end_of_jmp2[-1] = start_of_ldx - end_of_jmp2;
}
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 + (start_of_ldx - temp);
s64 delta;
/* populate jmp_offset for JMP above */
start_of_ldx[-1] = prog - start_of_ldx;
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;
}
/* switch ex to rw buffer for writes */
ex = (void *)rw_image + ((void *)ex - (void *)image);
ex->insn = delta;
ex->data = EX_TYPE_BPF;
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 - start_of_ldx) | (reg2pt_regs[dst_reg] << 8);
}
break;
case BPF_STX | BPF_ATOMIC | BPF_W:
case BPF_STX | BPF_ATOMIC | BPF_DW:
if (insn->imm == (BPF_AND | BPF_FETCH) ||
insn->imm == (BPF_OR | BPF_FETCH) ||
insn->imm == (BPF_XOR | BPF_FETCH)) {
bool is64 = BPF_SIZE(insn->code) == BPF_DW;
u32 real_src_reg = src_reg;
u32 real_dst_reg = dst_reg;
u8 *branch_target;
/*
* Can't be implemented with a single x86 insn.
* Need to do a CMPXCHG loop.
*/
/* Will need RAX as a CMPXCHG operand so save R0 */
emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0);
if (src_reg == BPF_REG_0)
real_src_reg = BPF_REG_AX;
if (dst_reg == BPF_REG_0)
real_dst_reg = BPF_REG_AX;
branch_target = prog;
/* Load old value */
emit_ldx(&prog, BPF_SIZE(insn->code),
BPF_REG_0, real_dst_reg, insn->off);
/*
* Perform the (commutative) operation locally,
* put the result in the AUX_REG.
*/
emit_mov_reg(&prog, is64, AUX_REG, BPF_REG_0);
maybe_emit_mod(&prog, AUX_REG, real_src_reg, is64);
EMIT2(simple_alu_opcodes[BPF_OP(insn->imm)],
add_2reg(0xC0, AUX_REG, real_src_reg));
/* Attempt to swap in new value */
err = emit_atomic(&prog, BPF_CMPXCHG,
real_dst_reg, AUX_REG,
insn->off,
BPF_SIZE(insn->code));
if (WARN_ON(err))
return err;
/*
* ZF tells us whether we won the race. If it's
* cleared we need to try again.
*/
EMIT2(X86_JNE, -(prog - branch_target) - 2);
/* Return the pre-modification value */
emit_mov_reg(&prog, is64, real_src_reg, BPF_REG_0);
/* Restore R0 after clobbering RAX */
emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX);
break;
}
err = emit_atomic(&prog, insn->imm, dst_reg, src_reg,
insn->off, BPF_SIZE(insn->code));
if (err)
return err;
break;
/* call */
case BPF_JMP | BPF_CALL:
func = (u8 *) __bpf_call_base + imm32;
if (tail_call_reachable) {
/* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */
EMIT3_off32(0x48, 0x8B, 0x85,
-round_up(bpf_prog->aux->stack_depth, 8) - 8);
if (!imm32 || emit_call(&prog, func, image + addrs[i - 1] + 7))
return -EINVAL;
} else {
if (!imm32 || emit_call(&prog, func, image + addrs[i - 1]))
return -EINVAL;
}
break;
case BPF_JMP | BPF_TAIL_CALL:
if (imm32)
emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1],
&prog, image + addrs[i - 1],
callee_regs_used,
bpf_prog->aux->stack_depth,
ctx);
else
emit_bpf_tail_call_indirect(&prog,
callee_regs_used,
bpf_prog->aux->stack_depth,
image + addrs[i - 1],
ctx);
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 */
maybe_emit_mod(&prog, dst_reg, src_reg,
BPF_CLASS(insn->code) == BPF_JMP);
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 */
maybe_emit_mod(&prog, dst_reg, src_reg,
BPF_CLASS(insn->code) == BPF_JMP);
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 */
maybe_emit_1mod(&prog, dst_reg,
BPF_CLASS(insn->code) == BPF_JMP);
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) {
maybe_emit_mod(&prog, dst_reg, dst_reg,
BPF_CLASS(insn->code) == BPF_JMP);
EMIT2(0x85, add_2reg(0xC0, dst_reg, dst_reg));
goto emit_cond_jmp;
}
/* cmp dst_reg, imm8/32 */
maybe_emit_1mod(&prog, dst_reg,
BPF_CLASS(insn->code) == BPF_JMP);
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)) {
if (jmp_padding) {
/* To keep the jmp_offset valid, the extra bytes are
* padded before the jump insn, so we subtract the
* 2 bytes of jmp_cond insn from INSN_SZ_DIFF.
*
* If the previous pass already emits an imm8
* jmp_cond, then this BPF insn won't shrink, so
* "nops" is 0.
*
* On the other hand, if the previous pass emits an
* imm32 jmp_cond, the extra 4 bytes(*) is padded to
* keep the image from shrinking further.
*
* (*) imm32 jmp_cond is 6 bytes, and imm8 jmp_cond
* is 2 bytes, so the size difference is 4 bytes.
*/
nops = INSN_SZ_DIFF - 2;
if (nops != 0 && nops != 4) {
pr_err("unexpected jmp_cond padding: %d bytes\n",
nops);
return -EFAULT;
}
emit_nops(&prog, nops);
}
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) {
/*
* If jmp_padding is enabled, the extra nops will
* be inserted. Otherwise, optimize out nop jumps.
*/
if (jmp_padding) {
/* There are 3 possible conditions.
* (1) This BPF_JA is already optimized out in
* the previous run, so there is no need
* to pad any extra byte (0 byte).
* (2) The previous pass emits an imm8 jmp,
* so we pad 2 bytes to match the previous
* insn size.
* (3) Similarly, the previous pass emits an
* imm32 jmp, and 5 bytes is padded.
*/
nops = INSN_SZ_DIFF;
if (nops != 0 && nops != 2 && nops != 5) {
pr_err("unexpected nop jump padding: %d bytes\n",
nops);
return -EFAULT;
}
emit_nops(&prog, nops);
}
break;
}
emit_jmp:
if (is_imm8(jmp_offset)) {
if (jmp_padding) {
/* To avoid breaking jmp_offset, the extra bytes
* are padded before the actual jmp insn, so
* 2 bytes is subtracted from INSN_SZ_DIFF.
*
* If the previous pass already emits an imm8
* jmp, there is nothing to pad (0 byte).
*
* If it emits an imm32 jmp (5 bytes) previously
* and now an imm8 jmp (2 bytes), then we pad
* (5 - 2 = 3) bytes to stop the image from
* shrinking further.
*/
nops = INSN_SZ_DIFF - 2;
if (nops != 0 && nops != 3) {
pr_err("unexpected jump padding: %d bytes\n",
nops);
return -EFAULT;
}
emit_nops(&prog, INSN_SZ_DIFF - 2);
}
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;
pop_callee_regs(&prog, callee_regs_used);
EMIT1(0xC9); /* leave */
emit_return(&prog, image + addrs[i - 1] + (prog - temp));
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) {
/*
* When populating the image, assert that:
*
* i) We do not write beyond the allocated space, and
* ii) addrs[i] did not change from the prior run, in order
* to validate assumptions made for computing branch
* displacements.
*/
if (unlikely(proglen + ilen > oldproglen ||
proglen + ilen != addrs[i])) {
pr_err("bpf_jit: fatal error\n");
return -EFAULT;
}
memcpy(rw_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(const struct btf_func_model *m, u8 **prog, int nr_args,
int stack_size)
{
int i, j, arg_size, nr_regs;
/* 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, j = 0; i < min(nr_args, 6); i++) {
if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) {
nr_regs = (m->arg_size[i] + 7) / 8;
arg_size = 8;
} else {
nr_regs = 1;
arg_size = m->arg_size[i];
}
while (nr_regs) {
emit_stx(prog, bytes_to_bpf_size(arg_size),
BPF_REG_FP,
j == 5 ? X86_REG_R9 : BPF_REG_1 + j,
-(stack_size - j * 8));
nr_regs--;
j++;
}
}
}
static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args,
int stack_size)
{
int i, j, arg_size, nr_regs;
/* 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, j = 0; i < min(nr_args, 6); i++) {
if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) {
nr_regs = (m->arg_size[i] + 7) / 8;
arg_size = 8;
} else {
nr_regs = 1;
arg_size = m->arg_size[i];
}
while (nr_regs) {
emit_ldx(prog, bytes_to_bpf_size(arg_size),
j == 5 ? X86_REG_R9 : BPF_REG_1 + j,
BPF_REG_FP,
-(stack_size - j * 8));
nr_regs--;
j++;
}
}
}
static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
struct bpf_tramp_link *l, int stack_size,
int run_ctx_off, bool save_ret)
{
void (*exit)(struct bpf_prog *prog, u64 start,
struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_exit;
u64 (*enter)(struct bpf_prog *prog,
struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_enter;
u8 *prog = *pprog;
u8 *jmp_insn;
int ctx_cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie);
struct bpf_prog *p = l->link.prog;
u64 cookie = l->cookie;
/* mov rdi, cookie */
emit_mov_imm64(&prog, BPF_REG_1, (long) cookie >> 32, (u32) (long) cookie);
/* Prepare struct bpf_tramp_run_ctx.
*
* bpf_tramp_run_ctx is already preserved by
* arch_prepare_bpf_trampoline().
*
* mov QWORD PTR [rbp - run_ctx_off + ctx_cookie_off], rdi
*/
emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_1, -run_ctx_off + ctx_cookie_off);
if (p->aux->sleepable) {
enter = __bpf_prog_enter_sleepable;
exit = __bpf_prog_exit_sleepable;
} else if (p->type == BPF_PROG_TYPE_STRUCT_OPS) {
enter = __bpf_prog_enter_struct_ops;
exit = __bpf_prog_exit_struct_ops;
} else if (p->expected_attach_type == BPF_LSM_CGROUP) {
enter = __bpf_prog_enter_lsm_cgroup;
exit = __bpf_prog_exit_lsm_cgroup;
}
/* arg1: mov rdi, progs[i] */
emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
/* arg2: lea rsi, [rbp - ctx_cookie_off] */
EMIT4(0x48, 0x8D, 0x75, -run_ctx_off);
if (emit_call(&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);
/* if (__bpf_prog_enter*(prog) == 0)
* goto skip_exec_of_prog;
*/
EMIT3(0x48, 0x85, 0xC0); /* test rax,rax */
/* emit 2 nops that will be replaced with JE insn */
jmp_insn = prog;
emit_nops(&prog, 2);
/* arg1: lea rdi, [rbp - stack_size] */
EMIT4(0x48, 0x8D, 0x7D, -stack_size);
/* arg2: progs[i]->insnsi for interpreter */
if (!p->jited)
emit_mov_imm64(&prog, BPF_REG_2,
(long) p->insnsi >> 32,
(u32) (long) p->insnsi);
/* call JITed bpf program or interpreter */
if (emit_call(&prog, p->bpf_func, prog))
return -EINVAL;
/*
* BPF_TRAMP_MODIFY_RETURN trampolines can modify the return
* of the previous call which is then passed on the stack to
* the next BPF program.
*
* BPF_TRAMP_FENTRY trampoline may need to return the return
* value of BPF_PROG_TYPE_STRUCT_OPS prog.
*/
if (save_ret)
emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
/* replace 2 nops with JE insn, since jmp target is known */
jmp_insn[0] = X86_JE;
jmp_insn[1] = prog - jmp_insn - 2;
/* arg1: mov rdi, progs[i] */
emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
/* arg2: mov rsi, rbx <- start time in nsec */
emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
/* arg3: lea rdx, [rbp - run_ctx_off] */
EMIT4(0x48, 0x8D, 0x55, -run_ctx_off);
if (emit_call(&prog, exit, prog))
return -EINVAL;
*pprog = prog;
return 0;
}
static void emit_align(u8 **pprog, u32 align)
{
u8 *target, *prog = *pprog;
target = PTR_ALIGN(prog, align);
if (target != prog)
emit_nops(&prog, target - prog);
*pprog = prog;
}
static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond)
{
u8 *prog = *pprog;
s64 offset;
offset = func - (ip + 2 + 4);
if (!is_simm32(offset)) {
pr_err("Target %p is out of range\n", func);
return -EINVAL;
}
EMIT2_off32(0x0F, jmp_cond + 0x10, offset);
*pprog = prog;
return 0;
}
static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
struct bpf_tramp_links *tl, int stack_size,
int run_ctx_off, bool save_ret)
{
int i;
u8 *prog = *pprog;
for (i = 0; i < tl->nr_links; i++) {
if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size,
run_ctx_off, save_ret))
return -EINVAL;
}
*pprog = prog;
return 0;
}
static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
struct bpf_tramp_links *tl, int stack_size,
int run_ctx_off, u8 **branches)
{
u8 *prog = *pprog;
int i;
/* The first fmod_ret program will receive a garbage return value.
* Set this to 0 to avoid confusing the program.
*/
emit_mov_imm32(&prog, false, BPF_REG_0, 0);
emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
for (i = 0; i < tl->nr_links; i++) {
if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, run_ctx_off, true))
return -EINVAL;
/* mod_ret prog stored return value into [rbp - 8]. Emit:
* if (*(u64 *)(rbp - 8) != 0)
* goto do_fexit;
*/
/* cmp QWORD PTR [rbp - 0x8], 0x0 */
EMIT4(0x48, 0x83, 0x7d, 0xf8); EMIT1(0x00);
/* Save the location of the branch and Generate 6 nops
* (4 bytes for an offset and 2 bytes for the jump) These nops
* are replaced with a conditional jump once do_fexit (i.e. the
* start of the fexit invocation) is finalized.
*/
branches[i] = prog;
emit_nops(&prog, 4 + 2);
}
*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(struct bpf_tramp_image *im, void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
struct bpf_tramp_links *tlinks,
void *func_addr)
{
int ret, i, nr_args = m->nr_args, extra_nregs = 0;
int regs_off, ip_off, args_off, stack_size = nr_args * 8, 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];
void *orig_call = func_addr;
u8 **branches = NULL;
u8 *prog;
bool save_ret;
/* x86-64 supports up to 6 arguments. 7+ can be added in the future */
if (nr_args > 6)
return -ENOTSUPP;
for (i = 0; i < MAX_BPF_FUNC_ARGS; i++) {
if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG)
extra_nregs += (m->arg_size[i] + 7) / 8 - 1;
}
if (nr_args + extra_nregs > 6)
return -ENOTSUPP;
stack_size += extra_nregs * 8;
/* Generated trampoline stack layout:
*
* RBP + 8 [ return address ]
* RBP + 0 [ RBP ]
*
* RBP - 8 [ return value ] BPF_TRAMP_F_CALL_ORIG or
* BPF_TRAMP_F_RET_FENTRY_RET flags
*
* [ reg_argN ] always
* [ ... ]
* RBP - regs_off [ reg_arg1 ] program's ctx pointer
*
* RBP - args_off [ arg regs count ] always
*
* RBP - ip_off [ traced function ] BPF_TRAMP_F_IP_ARG flag
*
* RBP - run_ctx_off [ bpf_tramp_run_ctx ]
*/
/* room for return value of orig_call or fentry prog */
save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET);
if (save_ret)
stack_size += 8;
regs_off = stack_size;
/* args count */
stack_size += 8;
args_off = stack_size;
if (flags & BPF_TRAMP_F_IP_ARG)
stack_size += 8; /* room for IP address argument */
ip_off = stack_size;
stack_size += (sizeof(struct bpf_tramp_run_ctx) + 7) & ~0x7;
run_ctx_off = stack_size;
if (flags & BPF_TRAMP_F_SKIP_FRAME) {
/* skip patched call instruction and point orig_call to actual
* body of the kernel function.
*/
if (is_endbr(*(u32 *)orig_call))
orig_call += ENDBR_INSN_SIZE;
orig_call += X86_PATCH_SIZE;
}
prog = image;
EMIT_ENDBR();
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 */
/* Store number of argument registers of the traced function:
* mov rax, nr_args + extra_nregs
* mov QWORD PTR [rbp - args_off], rax
*/
emit_mov_imm64(&prog, BPF_REG_0, 0, (u32) nr_args + extra_nregs);
emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -args_off);
if (flags & BPF_TRAMP_F_IP_ARG) {
/* Store IP address of the traced function:
* movabsq rax, func_addr
* mov QWORD PTR [rbp - ip_off], rax
*/
emit_mov_imm64(&prog, BPF_REG_0, (long) func_addr >> 32, (u32) (long) func_addr);
emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -ip_off);
}
save_regs(m, &prog, nr_args, regs_off);
if (flags & BPF_TRAMP_F_CALL_ORIG) {
/* arg1: mov rdi, im */
emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im);
if (emit_call(&prog, __bpf_tramp_enter, prog)) {
ret = -EINVAL;
goto cleanup;
}
}
if (fentry->nr_links)
if (invoke_bpf(m, &prog, fentry, regs_off, run_ctx_off,
flags & BPF_TRAMP_F_RET_FENTRY_RET))
return -EINVAL;
if (fmod_ret->nr_links) {
branches = kcalloc(fmod_ret->nr_links, sizeof(u8 *),
GFP_KERNEL);
if (!branches)
return -ENOMEM;
if (invoke_bpf_mod_ret(m, &prog, fmod_ret, regs_off,
run_ctx_off, branches)) {
ret = -EINVAL;
goto cleanup;
}
}
if (flags & BPF_TRAMP_F_CALL_ORIG) {
restore_regs(m, &prog, nr_args, regs_off);
if (flags & BPF_TRAMP_F_ORIG_STACK) {
emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8);
EMIT2(0xff, 0xd0); /* call *rax */
} else {
/* call original function */
if (emit_call(&prog, orig_call, prog)) {
ret = -EINVAL;
goto cleanup;
}
}
/* remember return value in a stack for bpf prog to access */
emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
im->ip_after_call = prog;
memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
prog += X86_PATCH_SIZE;
}
if (fmod_ret->nr_links) {
/* From Intel 64 and IA-32 Architectures Optimization
* Reference Manual, 3.4.1.4 Code Alignment, Assembly/Compiler
* Coding Rule 11: All branch targets should be 16-byte
* aligned.
*/
emit_align(&prog, 16);
/* Update the branches saved in invoke_bpf_mod_ret with the
* aligned address of do_fexit.
*/
for (i = 0; i < fmod_ret->nr_links; i++)
emit_cond_near_jump(&branches[i], prog, branches[i],
X86_JNE);
}
if (fexit->nr_links)
if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off, false)) {
ret = -EINVAL;
goto cleanup;
}
if (flags & BPF_TRAMP_F_RESTORE_REGS)
restore_regs(m, &prog, nr_args, regs_off);
/* This needs to be done regardless. If there were fmod_ret programs,
* the return value is only updated on the stack and still needs to be
* restored to R0.
*/
if (flags & BPF_TRAMP_F_CALL_ORIG) {
im->ip_epilogue = prog;
/* arg1: mov rdi, im */
emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im);
if (emit_call(&prog, __bpf_tramp_exit, prog)) {
ret = -EINVAL;
goto cleanup;
}
}
/* restore return value of orig_call or fentry prog back into RAX */
if (save_ret)
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 */
emit_return(&prog, prog);
/* Make sure the trampoline generation logic doesn't overflow */
if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) {
ret = -EFAULT;
goto cleanup;
}
ret = prog - (u8 *)image;
cleanup:
kfree(branches);
return ret;
}
static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs, u8 *image, u8 *buf)
{
u8 *jg_reloc, *prog = *pprog;
int pivot, err, jg_bytes = 1;
s64 jg_offset;
if (a == b) {
/* Leaf node of recursion, i.e. not a range of indices
* anymore.
*/
EMIT1(add_1mod(0x48, BPF_REG_3)); /* cmp rdx,func */
if (!is_simm32(progs[a]))
return -1;
EMIT2_off32(0x81, add_1reg(0xF8, BPF_REG_3),
progs[a]);
err = emit_cond_near_jump(&prog, /* je func */
(void *)progs[a], image + (prog - buf),
X86_JE);
if (err)
return err;
emit_indirect_jump(&prog, 2 /* rdx */, image + (prog - buf));
*pprog = prog;
return 0;
}
/* Not a leaf node, so we pivot, and recursively descend into
* the lower and upper ranges.
*/
pivot = (b - a) / 2;
EMIT1(add_1mod(0x48, BPF_REG_3)); /* cmp rdx,func */
if (!is_simm32(progs[a + pivot]))
return -1;
EMIT2_off32(0x81, add_1reg(0xF8, BPF_REG_3), progs[a + pivot]);
if (pivot > 2) { /* jg upper_part */
/* Require near jump. */
jg_bytes = 4;
EMIT2_off32(0x0F, X86_JG + 0x10, 0);
} else {
EMIT2(X86_JG, 0);
}
jg_reloc = prog;
err = emit_bpf_dispatcher(&prog, a, a + pivot, /* emit lower_part */
progs, image, buf);
if (err)
return err;
/* From Intel 64 and IA-32 Architectures Optimization
* Reference Manual, 3.4.1.4 Code Alignment, Assembly/Compiler
* Coding Rule 11: All branch targets should be 16-byte
* aligned.
*/
emit_align(&prog, 16);
jg_offset = prog - jg_reloc;
emit_code(jg_reloc - jg_bytes, jg_offset, jg_bytes);
err = emit_bpf_dispatcher(&prog, a + pivot + 1, /* emit upper_part */
b, progs, image, buf);
if (err)
return err;
*pprog = prog;
return 0;
}
static int cmp_ips(const void *a, const void *b)
{
const s64 *ipa = a;
const s64 *ipb = b;
if (*ipa > *ipb)
return 1;
if (*ipa < *ipb)
return -1;
return 0;
}
int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs)
{
u8 *prog = buf;
sort(funcs, num_funcs, sizeof(funcs[0]), cmp_ips, NULL);
return emit_bpf_dispatcher(&prog, 0, num_funcs - 1, funcs, image, buf);
}
struct x64_jit_data {
struct bpf_binary_header *rw_header;
struct bpf_binary_header *header;
int *addrs;
u8 *image;
int proglen;
struct jit_context ctx;
};
#define MAX_PASSES 20
#define PADDING_PASSES (MAX_PASSES - 5)
struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
{
struct bpf_binary_header *rw_header = NULL;
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;
bool padding = false;
u8 *rw_image = NULL;
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;
rw_header = jit_data->rw_header;
rw_image = (void *)rw_header + ((void *)image - (void *)header);
extra_pass = true;
padding = true;
goto skip_init_addrs;
}
addrs = kvmalloc_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 < MAX_PASSES || image; pass++) {
if (!padding && pass >= PADDING_PASSES)
padding = true;
proglen = do_jit(prog, addrs, image, rw_image, oldproglen, &ctx, padding);
if (proglen <= 0) {
out_image:
image = NULL;
if (header) {
bpf_arch_text_copy(&header->size, &rw_header->size,
sizeof(rw_header->size));
bpf_jit_binary_pack_free(header, rw_header);
}
/* Fall back to interpreter mode */
prog = orig_prog;
if (extra_pass) {
prog->bpf_func = NULL;
prog->jited = 0;
prog->jited_len = 0;
}
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_pack_alloc(roundup(proglen, align) + extable_size,
&image, align, &rw_header, &rw_image,
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_pack_finalize fails in two scenarios:
* 1) header is not pointing to proper module memory;
* 2) the arch doesn't support bpf_arch_text_copy().
*
* Both cases are serious bugs and justify WARN_ON.
*/
if (WARN_ON(bpf_jit_binary_pack_finalize(prog, header, rw_header))) {
/* header has been freed */
header = NULL;
goto out_image;
}
bpf_tail_call_direct_fixup(prog);
} else {
jit_data->addrs = addrs;
jit_data->ctx = ctx;
jit_data->proglen = proglen;
jit_data->image = image;
jit_data->header = header;
jit_data->rw_header = rw_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:
kvfree(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;
}
bool bpf_jit_supports_kfunc_call(void)
{
return true;
}
void *bpf_arch_text_copy(void *dst, void *src, size_t len)
{
if (text_poke_copy(dst, src, len) == NULL)
return ERR_PTR(-EINVAL);
return dst;
}
/* Indicate the JIT backend supports mixing bpf2bpf and tailcalls. */
bool bpf_jit_supports_subprog_tailcalls(void)
{
return true;
}
void bpf_jit_free(struct bpf_prog *prog)
{
if (prog->jited) {
struct x64_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_jit_binary_pack_finalize(prog, jit_data->header,
jit_data->rw_header);
kvfree(jit_data->addrs);
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);
}
|