| 21 3 3 4 1 4 193 322 96 319 318 89 3 1 2 1 1 3 19 46 39 39 9 9 9 16 9 2 135 135 135 134 131 131 5 135 134 135 135 135 135 194 163 197 18 107 135 135 125 4 1 2 2 2 2 1 2 2 1 8 1 7 110 110 1 1 1 36 58 7 2 28 3 44 135 103 103 103 135 118 118 118 118 14 134 121 12 107 111 107 110 109 12 12 12 12 9 9 9 9 9 295 14 295 294 298 295 294 288 296 122 121 122 123 123 123 120 120 123 119 288 1 186 39 39 39 38 38 84 218 217 32 217 289 85 72 68 69 72 72 15 85 84 85 82 85 297 8 297 8 297 298 299 9 9 27 122 18 4 7 6 1 7 127 191 190 189 184 154 191 185 186 185 151 190 1 190 9 6 190 154 190 154 191 191 191 186 190 154 190 191 191 190 191 191 263 262 262 263 192 191 190 191 262 191 191 189 190 263 2 1 16 16 16 10 58 58 287 287 288 1 299 299 299 297 298 298 22 16 322 322 319 322 320 316 321 319 1 1 319 322 321 322 322 23 1 22 1 321 319 319 25 25 321 320 321 168 162 6 316 201 6 318 318 147 5 142 147 2 320 317 5 315 22 285 94 76 76 76 76 74 76 93 75 285 1 295 256 293 187 154 150 290 133 136 136 104 83 183 109 69 6 4 1 189 106 285 77 296 1 295 290 7 289 296 287 285 287 292 1 291 292 190 138 117 299 198 16 16 199 199 197 156 156 37 30 155 77 149 10 10 10 37 163 1 1 156 106 156 112 7 32 1 156 1 151 10 10 10 10 10 2 2 10 153 156 50 156 10 107 104 104 100 25 81 35 7 7 130 77 48 44 127 55 54 32 4 119 67 1 1 1 1 1 1 1 1 1 67 67 18 18 63 147 63 40 33 63 58 12 3 12 11 10 11 11 11 10 1 11 9 9 6 1 12 94 96 96 96 88 96 67 50 46 30 25 25 24 25 156 155 155 156 154 24 25 155 6 6 6 6 3 156 156 156 155 30 25 155 66 55 8 4 162 155 163 154 156 163 153 10 156 163 155 156 156 156 156 156 37 37 37 37 37 6 35 31 37 37 6 6 6 6 5 5 37 3 37 37 4 4 82 33 11 113 92 74 7 24 81 32 131 32 123 106 98 107 107 107 28 105 46 85 2 108 79 46 1 2 2 2 110 110 79 72 71 72 46 34 34 11 11 11 11 24 8 8 24 7 24 23 11 24 107 3 2 2 1 3 3 3 3 3 3 1 1 3 1 3 3 3 5 5 5 1 5 1 3 5 39 32 28 32 16 16 16 15 14 1 1 1 1 1 1 1 1 1 16 16 16 9 9 7 9 5 30 190 109 11 35 37 39 108 110 110 3 4 1 3 4 1 17 17 1 1 11 11 11 1 10 10 11 210 1 212 1 211 211 151 138 9 8 9 2 2 2 2 2 6 6 6 6 6 114 114 91 91 92 92 22 1 1 1 1 1 1 1 257 12 12 12 12 12 9 6 6 6 221 221 221 194 1 221 6 221 197 199 199 199 199 199 199 13 13 198 13 13 13 199 199 198 13 198 197 196 199 37 37 84 15 83 44 84 3 3 1 3 3 1 1 1 3 3 1 1 3 1 1 1 1 1 1 1 1 7 7 5 111 1 111 111 110 111 110 3 3 3 111 109 110 2 1 1 111 220 221 221 219 220 3 84 3 3 2 2 2 2 2 216 2 2 2 2 2 215 114 18 1 115 114 92 84 70 22 1 22 84 120 111 109 110 9 6 2 1 6 6 3 1 1 1 2 2 1 1 1 2 6 6 31 88 85 84 1 12 12 12 12 12 12 5 5 12 12 12 12 12 12 12 7 2 7 12 7 11 12 43 43 43 42 43 31 7 7 7 7 7 43 36 36 36 36 1 1 1 36 36 3 36 36 36 36 36 44 43 1 1 1 43 1 1 28 28 1 27 27 27 28 26 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 149 105 9 5 4 4 4 2 111 111 19 111 7 111 28 109 7 111 111 6 5 6 106 111 106 9 8 104 106 5 5 5 5 5 5 5 5 113 114 77 1 111 110 4 111 111 1 111 105 105 9 1 1 1 8 8 8 104 8 8 103 50 50 12 12 4 4 4 1 1 1 28 10 18 1 12 12 5 5 5 5 2 2 2 3 5 49 5 1 1 1 1 17 1 3 5 1 3 1 1 1 1 1 1 1 1 1 1 3 3 13 5 1 4 4 1 1 3 1 9 1 148 4 2 149 4 35 149 35 149 149 149 149 148 148 148 148 147 1 149 149 149 149 18 5 3 8 8 8 16 16 16 16 16 16 14 16 16 16 16 16 16 16 16 16 9 16 16 1 1 69 15 1 14 14 14 14 14 14 7 14 14 115 1 4 111 130 127 125 123 122 123 119 29 16 1 1 29 29 2 141 5 5 5 5 1 4 4 4 223 222 222 223 5 5 5 5 219 153 151 1 152 150 152 6 150 1 149 149 149 20 149 149 149 149 149 140 149 45 135 141 135 6 134 8 8 8 8 8 134 5 4 5 1 5 135 135 113 13 12 12 4 12 131 20 135 135 135 12 12 135 135 111 115 120 125 18 10 19 28 19 20 5 2 16 2 12 103 102 103 103 103 1 1 1 125 2 2 2 2 1 2 103 103 103 2 298 1 101 101 2 1 105 105 105 105 1 105 4 4 103 104 1 103 103 103 5 103 102 102 10 10 10 10 10 10 6 5 5 5 1 5 5 5 5 5 3 102 102 100 102 37 35 37 34 33 37 37 35 34 37 33 37 14 13 14 12 1 14 14 13 12 14 1 14 6 7 6 4 1 3 10 7 6 6 6 2 2 2 6 7 2 2 6 2 2 2 2 2 2 2 7 10 13 7 1 1 12 2 10 2 2 10 3 12 12 12 12 2 2 2 1 1 23 22 51 50 50 67 18 67 67 10 66 65 48 34 37 37 14 14 10 10 10 2 2 2 7 7 7 2 2 2 13 1 12 2 2 1 1 61 22 65 127 128 129 68 129 32 1 1 1 31 17 16 18 121 102 18 67 194 192 6 6 5 1 2 2 7 7 7 194 179 131 17 17 120 120 120 1 129 165 181 180 129 120 121 121 120 2 2 2 1 2 2 16 15 5 4 4 4 4 1 1 1 1 1 11 16 165 132 35 132 132 35 3 2 34 123 1 150 130 9 1 127 17 14 14 130 129 194 9 3 6 6 2 9 86 86 23 12 15 12 12 10 10 10 10 17 8 13 8 8 6 6 6 6 16 16 16 16 24 22 27 25 12 8 7 6 18 9 3 2 18 10 2 2 11 11 7 7 2 1 1 1 1 99 11 115 49 19 52 46 5 5 5 86 50 50 43 50 18 5 14 18 18 16 3 5 5 5 1 9 12 12 2 12 1 6 6 5 5 2 6 6 5 29 11 19 28 11 19 23 10 14 23 10 14 50 84 82 50 50 49 50 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 40 37 17 17 2 3 2 9 3 5 4 2 7 7 1 1 1 4 2 2 2 1 8 8 1 1 1 6 4 4 4 8 8 1 1 1 6 1 1 1 1 27 27 117 114 117 1 1 1 1 1 1 115 113 59 59 59 59 52 97 99 115 116 72 69 38 34 33 69 69 41 2 39 3 41 51 1 51 3 84 83 40 69 84 84 40 5 5 84 25 25 82 37 12 46 22 9 64 77 84 11 181 180 180 181 181 88 88 24 24 75 75 3 3 3 3 3 3 2 2 2 2 2 2 2 2 2 2 2 221 220 222 222 222 222 221 222 221 9 8 16 1 70 1 69 69 3 3 66 1 1 299 1 178 1 18 298 298 297 141 299 299 296 298 298 110 24 110 110 162 161 162 162 21 298 180 298 300 300 163 162 1 162 163 22 22 17 5 22 22 126 1 126 126 298 298 297 299 300 297 298 300 295 300 299 298 299 182 1 299 298 322 22 1 21 5 2 2 2 2 2 1 203 1 1 1 1 5 191 5 5 5 5 5 5 5 5 1 1 1 4 4 4 1 4 1 3 3 3 3 3 3 2 2 3 5 2 1 2 322 317 8 1 7 7 204 314 309 5 5 2 28 26 25 25 25 25 28 24 23 32 31 32 13 23 23 15 13 15 15 15 38 38 38 38 26 25 25 38 38 38 43 38 38 38 43 22 22 22 39 38 40 35 35 35 27 27 20 16 15 2 2 2 2 2 10 10 10 10 10 9 16 6 7 7 7 1 7 35 24 8 23 8 8 8 7 7 7 1 1 23 7 7 7 7 7 35 35 1 38 40 35 35 40 40 40 40 2 40 40 40 40 40 39 40 35 39 40 33 30 30 29 33 33 33 33 30 28 33 23 23 6 22 33 33 33 33 22 14 15 3 3 1 15 33 23 5 5 3 3 1 1 3 31 15 33 18 14 18 18 3 3 2 2 188 175 188 127 186 43 28 43 42 18 18 18 1 18 18 3 3 3 3 15 15 38 38 37 33 32 33 33 28 33 27 28 28 7 6 6 6 1 6 27 28 28 28 186 96 94 96 95 96 96 95 96 95 94 96 94 67 29 193 195 29 195 298 291 299 297 188 94 96 33 3 1 299 186 299 298 2 296 3 297 59 22 60 60 298 1 296 297 298 298 193 129 128 129 112 113 104 12 12 99 99 99 99 89 43 43 1 42 42 40 267 158 156 158 16 157 1 154 157 16 152 153 132 241 18 18 18 16 2 2 15 1 240 224 225 224 224 2 223 224 222 224 222 222 15 222 216 218 217 202 118 182 3 180 181 179 180 291 191 90 90 89 90 9 305 307 303 303 5 134 3 305 187 188 188 2 188 92 93 93 79 1 92 1 1 91 91 1 90 89 89 27 27 1 26 26 16 21 4 18 88 8 89 3 228 89 184 298 253 309 58 58 58 58 58 109 109 102 102 102 102 102 102 102 109 109 109 109 109 102 109 21 21 21 6 21 21 21 21 6 21 21 21 21 21 21 21 21 21 198 199 195 196 199 80 11 75 11 198 197 198 199 11 198 11 11 197 198 199 199 21 21 192 189 192 179 6 6 6 1 1 1 95 96 96 96 97 96 190 198 198 111 2 88 89 2 2 198 199 195 195 198 88 2 2 148 77 76 57 76 67 15 15 76 74 22 74 13 11 2 11 13 74 1 74 74 13 191 13 13 13 13 13 13 13 13 13 13 13 13 13 13 5 5 13 13 13 13 13 13 13 13 13 13 13 13 13 13 13 13 13 13 13 13 13 13 13 13 13 192 192 191 190 196 197 197 197 197 197 197 197 4 4 2 4 196 4 197 197 2 2 2 195 10 197 196 111 109 108 1 109 6 109 109 3 3 3 3 3 3 2 2 2 2 1 106 107 92 106 106 106 102 99 97 98 97 97 21 21 5 4 3 3 3 4 2 3 2 1 1 6 3 94 2 2 92 92 90 92 6 89 197 191 196 192 192 192 192 2 2 2 2 192 109 198 198 199 109 198 197 199 288 287 288 289 86 289 298 285 299 299 298 297 298 299 280 289 289 287 189 289 134 298 198 59 59 13 59 310 1 1 3 2 1 1 1 1 1 2 309 14 294 296 1 309 2 3 322 323 324 324 325 323 325 325 325 324 324 323 322 323 325 321 321 315 310 307 300 300 1 299 298 134 197 1 306 199 199 199 199 199 199 199 198 197 192 192 192 193 311 310 162 310 162 304 191 58 58 190 191 58 191 312 253 309 309 312 2 312 311 311 310 | 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 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 11020 11021 11022 11023 11024 11025 11026 11027 11028 11029 11030 11031 11032 11033 11034 11035 11036 11037 11038 11039 11040 11041 11042 11043 11044 11045 11046 11047 11048 11049 11050 11051 11052 11053 11054 11055 11056 11057 11058 11059 11060 11061 11062 11063 11064 11065 11066 11067 11068 11069 11070 11071 11072 11073 11074 11075 11076 11077 11078 11079 11080 11081 11082 11083 11084 11085 11086 11087 11088 11089 11090 11091 11092 11093 11094 11095 11096 11097 11098 11099 11100 11101 11102 11103 11104 11105 11106 11107 11108 11109 11110 11111 11112 11113 11114 11115 11116 11117 11118 11119 11120 11121 11122 11123 11124 11125 11126 11127 11128 11129 11130 11131 11132 11133 11134 11135 11136 11137 11138 11139 11140 11141 11142 11143 11144 11145 11146 11147 11148 11149 11150 11151 11152 11153 11154 11155 11156 11157 11158 11159 11160 11161 11162 11163 11164 11165 11166 11167 11168 11169 11170 11171 11172 11173 11174 11175 11176 11177 11178 11179 11180 11181 11182 11183 11184 11185 11186 11187 11188 11189 11190 11191 11192 11193 11194 11195 11196 11197 11198 11199 11200 11201 11202 11203 11204 11205 11206 11207 11208 11209 11210 11211 11212 11213 11214 11215 11216 11217 11218 11219 11220 11221 11222 11223 11224 11225 11226 11227 11228 11229 11230 11231 11232 11233 11234 11235 11236 11237 11238 11239 11240 11241 11242 11243 11244 11245 11246 11247 11248 11249 11250 11251 11252 11253 11254 11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 11267 11268 11269 11270 11271 11272 11273 11274 11275 11276 11277 11278 11279 11280 11281 11282 11283 11284 11285 11286 11287 11288 11289 11290 11291 11292 11293 11294 11295 11296 11297 11298 11299 11300 11301 11302 11303 11304 11305 11306 11307 11308 11309 11310 11311 11312 11313 11314 11315 11316 11317 11318 11319 11320 11321 11322 11323 11324 11325 11326 11327 11328 11329 11330 11331 11332 11333 11334 11335 11336 11337 11338 11339 11340 11341 11342 11343 11344 11345 11346 11347 11348 11349 11350 11351 11352 11353 11354 11355 11356 11357 11358 11359 11360 11361 11362 11363 11364 11365 11366 11367 11368 11369 11370 11371 11372 11373 11374 11375 11376 11377 11378 11379 11380 11381 11382 11383 11384 11385 11386 11387 11388 11389 11390 11391 11392 11393 11394 11395 11396 11397 11398 11399 11400 11401 11402 11403 11404 11405 11406 11407 11408 11409 11410 11411 11412 11413 11414 11415 11416 11417 11418 11419 11420 11421 11422 11423 11424 11425 11426 11427 11428 11429 11430 11431 11432 11433 11434 11435 11436 11437 11438 11439 11440 11441 11442 11443 11444 11445 11446 11447 11448 11449 11450 11451 11452 11453 11454 11455 11456 11457 11458 11459 11460 11461 11462 11463 11464 11465 11466 11467 11468 11469 11470 11471 11472 11473 11474 11475 11476 11477 11478 11479 11480 11481 11482 11483 11484 11485 11486 11487 11488 11489 11490 11491 11492 11493 11494 11495 11496 11497 11498 11499 11500 11501 11502 11503 11504 11505 11506 11507 11508 11509 11510 11511 11512 11513 11514 11515 11516 11517 11518 11519 11520 11521 11522 11523 11524 11525 11526 11527 11528 11529 11530 11531 11532 11533 11534 11535 11536 11537 11538 11539 11540 11541 11542 11543 11544 11545 11546 11547 11548 11549 11550 11551 11552 11553 11554 11555 11556 11557 11558 11559 11560 11561 11562 11563 11564 11565 11566 11567 11568 11569 11570 11571 11572 11573 11574 11575 11576 11577 11578 11579 11580 11581 11582 11583 11584 11585 11586 11587 11588 11589 11590 11591 11592 11593 11594 11595 11596 11597 11598 11599 11600 11601 11602 11603 11604 11605 11606 11607 11608 11609 11610 11611 11612 11613 11614 11615 11616 11617 11618 11619 11620 11621 11622 11623 11624 11625 11626 11627 11628 11629 11630 11631 11632 11633 11634 11635 11636 11637 11638 11639 11640 11641 11642 11643 11644 11645 11646 11647 11648 11649 11650 11651 11652 11653 11654 11655 11656 11657 11658 11659 11660 11661 11662 11663 11664 11665 11666 11667 11668 11669 11670 11671 11672 11673 11674 11675 11676 11677 11678 11679 11680 11681 11682 11683 11684 11685 11686 11687 11688 11689 11690 11691 11692 11693 11694 11695 11696 11697 11698 11699 11700 11701 11702 11703 11704 11705 11706 11707 11708 11709 11710 11711 11712 11713 11714 11715 11716 11717 11718 11719 11720 11721 11722 11723 11724 11725 11726 11727 11728 11729 11730 11731 11732 11733 11734 11735 11736 11737 11738 11739 11740 11741 11742 11743 11744 11745 11746 11747 11748 11749 11750 11751 11752 11753 11754 11755 11756 11757 11758 11759 11760 11761 11762 11763 11764 11765 11766 11767 11768 11769 11770 11771 11772 11773 11774 11775 11776 11777 11778 11779 11780 11781 11782 11783 11784 11785 11786 11787 11788 11789 11790 11791 11792 11793 11794 11795 11796 11797 11798 11799 11800 11801 11802 11803 11804 11805 11806 11807 11808 11809 11810 11811 11812 11813 11814 11815 11816 11817 11818 11819 11820 11821 11822 11823 11824 11825 11826 11827 11828 11829 11830 11831 11832 11833 11834 11835 11836 11837 11838 11839 11840 11841 11842 11843 11844 11845 11846 11847 11848 11849 11850 11851 11852 11853 11854 11855 11856 11857 11858 11859 11860 11861 11862 11863 11864 11865 11866 11867 11868 11869 11870 11871 11872 11873 11874 11875 11876 11877 11878 11879 11880 11881 11882 11883 11884 11885 11886 11887 11888 11889 11890 11891 11892 11893 11894 11895 11896 11897 11898 11899 11900 11901 11902 11903 11904 11905 11906 11907 11908 11909 11910 11911 11912 11913 11914 11915 11916 11917 11918 11919 11920 11921 11922 11923 11924 11925 11926 11927 11928 11929 11930 11931 11932 11933 11934 11935 11936 11937 11938 11939 11940 11941 11942 11943 11944 11945 11946 11947 11948 11949 11950 11951 11952 11953 11954 11955 11956 11957 11958 11959 11960 11961 11962 11963 11964 11965 11966 11967 11968 11969 11970 11971 11972 11973 11974 11975 11976 11977 11978 11979 11980 11981 11982 11983 11984 11985 11986 11987 11988 11989 11990 11991 11992 11993 11994 11995 11996 11997 11998 11999 12000 12001 12002 12003 12004 12005 12006 12007 12008 12009 12010 12011 12012 12013 12014 12015 12016 12017 12018 12019 12020 12021 12022 12023 12024 12025 12026 12027 12028 12029 12030 12031 12032 12033 12034 12035 12036 12037 12038 12039 12040 12041 12042 12043 12044 12045 12046 12047 12048 12049 12050 12051 12052 12053 12054 12055 12056 12057 12058 12059 12060 12061 12062 12063 12064 12065 12066 12067 12068 12069 12070 12071 12072 12073 12074 12075 12076 12077 12078 12079 12080 12081 12082 12083 12084 12085 12086 12087 12088 12089 12090 12091 12092 12093 12094 12095 12096 12097 12098 12099 12100 12101 12102 12103 12104 12105 12106 12107 12108 12109 12110 12111 12112 12113 12114 12115 12116 12117 12118 12119 12120 12121 12122 12123 12124 12125 12126 12127 12128 12129 12130 12131 12132 12133 12134 12135 12136 12137 12138 12139 12140 12141 12142 12143 12144 12145 12146 12147 12148 12149 12150 12151 12152 12153 12154 12155 12156 12157 12158 12159 12160 12161 12162 12163 12164 12165 12166 12167 12168 12169 12170 12171 12172 12173 12174 12175 12176 12177 12178 12179 12180 12181 12182 12183 12184 12185 12186 12187 12188 12189 12190 12191 12192 12193 12194 12195 12196 12197 12198 12199 12200 12201 12202 12203 12204 12205 12206 12207 12208 12209 12210 12211 12212 12213 12214 12215 12216 12217 12218 12219 12220 12221 12222 12223 12224 12225 12226 12227 12228 12229 12230 12231 12232 12233 12234 12235 12236 12237 12238 12239 12240 12241 12242 12243 12244 12245 12246 12247 12248 12249 12250 12251 12252 12253 12254 12255 12256 12257 12258 12259 12260 12261 12262 12263 12264 12265 12266 12267 12268 12269 12270 12271 12272 12273 12274 12275 12276 12277 12278 12279 12280 12281 12282 12283 12284 12285 12286 12287 12288 12289 12290 12291 12292 12293 12294 12295 12296 12297 12298 12299 12300 12301 12302 12303 12304 12305 12306 12307 12308 12309 12310 12311 12312 12313 12314 12315 12316 12317 12318 12319 12320 12321 12322 12323 12324 12325 12326 12327 12328 12329 12330 12331 12332 12333 12334 12335 12336 12337 12338 12339 12340 12341 12342 12343 12344 12345 12346 12347 12348 12349 12350 12351 12352 12353 12354 12355 12356 12357 12358 12359 12360 12361 12362 12363 12364 12365 12366 12367 12368 12369 12370 12371 12372 12373 12374 12375 12376 12377 12378 12379 12380 12381 12382 12383 12384 12385 12386 12387 12388 12389 12390 12391 12392 12393 12394 12395 12396 12397 12398 12399 12400 12401 12402 12403 12404 12405 12406 12407 12408 12409 12410 12411 12412 12413 12414 12415 12416 12417 12418 12419 12420 12421 12422 12423 12424 12425 12426 12427 12428 12429 12430 12431 12432 12433 12434 12435 12436 12437 12438 12439 12440 12441 12442 12443 12444 12445 12446 12447 12448 12449 12450 12451 12452 12453 12454 12455 12456 12457 12458 12459 12460 12461 12462 12463 12464 12465 12466 12467 12468 12469 12470 12471 12472 12473 12474 12475 12476 12477 12478 12479 12480 12481 12482 12483 12484 12485 12486 12487 12488 12489 12490 12491 12492 12493 12494 12495 12496 12497 12498 12499 12500 12501 12502 12503 12504 12505 12506 12507 12508 12509 12510 12511 12512 12513 12514 12515 12516 12517 12518 12519 12520 12521 12522 12523 12524 12525 12526 12527 12528 12529 12530 12531 12532 12533 12534 12535 12536 12537 12538 12539 12540 12541 12542 12543 12544 12545 12546 12547 12548 12549 12550 12551 12552 12553 12554 12555 12556 12557 12558 12559 12560 12561 12562 12563 12564 12565 12566 12567 12568 12569 12570 12571 12572 12573 12574 12575 12576 12577 12578 12579 12580 12581 12582 12583 12584 12585 12586 12587 12588 12589 12590 12591 12592 12593 12594 12595 12596 12597 12598 12599 12600 12601 12602 12603 12604 12605 12606 12607 12608 12609 12610 12611 12612 12613 12614 12615 12616 12617 12618 12619 12620 12621 12622 12623 12624 12625 12626 12627 12628 12629 12630 12631 12632 12633 12634 12635 12636 12637 12638 12639 12640 12641 12642 12643 12644 12645 12646 12647 12648 12649 12650 12651 12652 12653 12654 12655 12656 12657 12658 12659 12660 12661 12662 12663 12664 12665 12666 12667 12668 12669 12670 12671 12672 12673 12674 12675 12676 12677 12678 12679 12680 12681 12682 12683 12684 12685 12686 12687 12688 12689 12690 12691 12692 12693 12694 12695 12696 12697 12698 12699 12700 12701 12702 12703 12704 12705 12706 12707 12708 12709 12710 12711 12712 12713 12714 12715 12716 12717 12718 12719 12720 12721 12722 12723 12724 12725 12726 12727 12728 12729 12730 12731 12732 12733 12734 12735 12736 12737 12738 12739 12740 12741 12742 12743 12744 12745 12746 12747 12748 12749 12750 12751 12752 12753 12754 12755 12756 12757 12758 12759 12760 12761 12762 12763 12764 12765 12766 12767 12768 12769 12770 12771 12772 12773 12774 12775 12776 12777 12778 12779 12780 12781 12782 12783 12784 12785 12786 12787 12788 12789 12790 12791 12792 12793 12794 12795 12796 12797 12798 12799 12800 12801 12802 12803 12804 12805 12806 12807 12808 12809 12810 12811 12812 12813 12814 12815 12816 12817 12818 12819 12820 12821 12822 12823 12824 12825 12826 12827 12828 12829 12830 12831 12832 12833 12834 12835 12836 12837 12838 12839 12840 12841 12842 12843 12844 12845 12846 12847 12848 12849 12850 12851 12852 12853 12854 12855 12856 12857 12858 12859 12860 12861 12862 12863 12864 12865 12866 12867 12868 12869 12870 12871 12872 12873 12874 12875 12876 12877 12878 12879 12880 12881 12882 12883 12884 12885 12886 12887 12888 12889 12890 12891 12892 12893 12894 12895 12896 12897 12898 12899 12900 12901 12902 12903 12904 12905 12906 12907 12908 12909 12910 12911 12912 12913 12914 12915 12916 12917 12918 12919 12920 12921 12922 12923 12924 12925 12926 12927 12928 12929 12930 12931 12932 12933 12934 12935 12936 12937 12938 12939 12940 12941 12942 12943 12944 12945 12946 12947 12948 12949 12950 12951 12952 12953 12954 12955 12956 12957 12958 12959 12960 12961 12962 12963 12964 12965 12966 12967 12968 12969 12970 12971 12972 12973 12974 12975 12976 12977 12978 12979 12980 12981 12982 12983 12984 12985 12986 12987 12988 12989 12990 12991 12992 12993 12994 12995 12996 12997 12998 12999 13000 13001 13002 13003 13004 13005 13006 13007 13008 13009 13010 13011 13012 13013 13014 13015 13016 13017 13018 13019 13020 13021 13022 13023 13024 13025 13026 13027 13028 13029 13030 13031 13032 13033 13034 13035 13036 13037 13038 13039 13040 13041 13042 13043 13044 13045 13046 13047 13048 13049 13050 13051 13052 13053 13054 13055 13056 13057 13058 13059 13060 13061 13062 13063 13064 13065 13066 13067 13068 13069 13070 13071 13072 13073 13074 13075 13076 13077 13078 13079 13080 13081 13082 13083 13084 13085 13086 13087 13088 13089 13090 13091 13092 13093 13094 13095 13096 13097 13098 13099 13100 13101 13102 13103 13104 13105 13106 13107 13108 13109 13110 13111 13112 13113 13114 13115 13116 13117 13118 13119 13120 13121 13122 13123 13124 13125 13126 13127 13128 13129 13130 13131 13132 13133 13134 13135 13136 13137 13138 13139 13140 13141 13142 13143 13144 13145 13146 13147 13148 13149 13150 13151 13152 13153 13154 13155 13156 13157 13158 13159 13160 13161 13162 13163 13164 13165 13166 13167 13168 13169 13170 13171 13172 13173 13174 13175 13176 13177 13178 13179 13180 13181 13182 13183 13184 13185 13186 13187 13188 13189 13190 13191 13192 13193 13194 13195 13196 13197 13198 13199 13200 13201 13202 13203 13204 13205 13206 13207 13208 13209 13210 13211 13212 13213 13214 13215 13216 13217 13218 13219 13220 13221 13222 13223 13224 13225 13226 13227 13228 13229 13230 13231 13232 13233 13234 13235 13236 13237 13238 13239 13240 13241 13242 13243 13244 13245 13246 13247 13248 13249 13250 13251 13252 13253 13254 13255 13256 13257 13258 13259 13260 13261 13262 13263 13264 13265 13266 13267 13268 13269 13270 13271 13272 13273 13274 13275 13276 13277 13278 13279 13280 13281 13282 13283 13284 13285 13286 13287 13288 13289 13290 13291 13292 13293 13294 13295 13296 13297 13298 13299 13300 13301 13302 13303 13304 13305 13306 13307 13308 13309 13310 13311 13312 13313 13314 13315 13316 13317 13318 13319 13320 13321 13322 13323 13324 13325 13326 13327 13328 13329 13330 13331 13332 13333 13334 13335 13336 13337 13338 13339 13340 13341 13342 13343 13344 13345 13346 13347 13348 13349 13350 13351 13352 13353 13354 13355 13356 13357 13358 13359 13360 13361 13362 13363 13364 13365 13366 13367 13368 13369 13370 13371 13372 13373 13374 13375 13376 13377 13378 13379 13380 13381 13382 13383 13384 13385 13386 13387 13388 13389 13390 13391 13392 13393 13394 13395 13396 13397 13398 13399 13400 13401 13402 13403 13404 13405 13406 13407 13408 13409 13410 13411 13412 13413 13414 13415 13416 13417 13418 13419 13420 13421 13422 13423 13424 13425 13426 13427 13428 13429 13430 13431 13432 13433 13434 13435 13436 13437 13438 13439 13440 13441 13442 13443 13444 13445 13446 13447 13448 13449 13450 13451 13452 13453 13454 13455 13456 13457 13458 13459 13460 13461 13462 13463 13464 13465 13466 13467 13468 13469 13470 13471 13472 13473 13474 13475 13476 13477 13478 13479 13480 13481 13482 13483 13484 13485 13486 13487 13488 13489 13490 13491 13492 13493 13494 13495 13496 13497 13498 13499 13500 13501 13502 13503 13504 13505 13506 13507 13508 13509 13510 13511 13512 13513 13514 13515 13516 13517 13518 13519 13520 13521 13522 13523 13524 13525 13526 13527 13528 13529 13530 13531 13532 13533 13534 13535 13536 13537 13538 13539 13540 13541 13542 13543 13544 13545 13546 13547 13548 13549 13550 13551 13552 13553 13554 13555 13556 13557 13558 13559 13560 13561 13562 13563 13564 13565 13566 13567 13568 13569 13570 13571 13572 13573 13574 13575 13576 13577 13578 13579 13580 13581 13582 13583 13584 13585 13586 13587 13588 13589 13590 13591 13592 13593 13594 13595 13596 13597 13598 13599 13600 13601 13602 13603 13604 13605 13606 13607 13608 13609 13610 13611 13612 13613 13614 13615 13616 13617 13618 13619 13620 13621 13622 13623 13624 13625 13626 13627 13628 13629 13630 13631 13632 13633 13634 13635 13636 13637 13638 13639 13640 13641 13642 13643 13644 13645 13646 13647 13648 13649 13650 13651 13652 13653 13654 13655 13656 13657 13658 13659 13660 13661 13662 13663 13664 13665 13666 13667 13668 13669 13670 13671 13672 13673 13674 13675 13676 13677 13678 13679 13680 13681 13682 13683 13684 13685 13686 13687 13688 13689 13690 13691 13692 13693 13694 13695 13696 13697 13698 13699 13700 13701 13702 13703 13704 13705 13706 13707 13708 13709 13710 13711 13712 13713 13714 13715 13716 13717 13718 13719 13720 13721 13722 13723 13724 13725 13726 13727 13728 13729 13730 13731 13732 13733 13734 13735 13736 13737 13738 13739 13740 13741 13742 13743 13744 13745 13746 13747 13748 13749 13750 13751 13752 13753 13754 13755 13756 13757 13758 13759 13760 13761 13762 13763 13764 13765 13766 13767 13768 13769 13770 13771 13772 13773 13774 13775 13776 13777 13778 13779 13780 13781 13782 13783 13784 13785 13786 13787 13788 13789 13790 13791 13792 13793 13794 13795 13796 13797 13798 13799 13800 13801 13802 13803 13804 13805 13806 13807 13808 13809 13810 13811 13812 13813 13814 13815 13816 13817 13818 13819 13820 13821 13822 13823 13824 13825 13826 13827 13828 13829 13830 13831 13832 13833 13834 13835 13836 13837 13838 13839 13840 13841 13842 13843 13844 13845 13846 13847 13848 13849 13850 13851 13852 13853 13854 13855 13856 13857 13858 13859 13860 13861 13862 13863 13864 13865 13866 13867 13868 13869 13870 13871 13872 13873 13874 13875 13876 13877 13878 13879 13880 13881 13882 13883 13884 13885 13886 13887 13888 13889 13890 13891 13892 13893 13894 13895 13896 13897 13898 13899 13900 13901 13902 13903 13904 13905 13906 13907 13908 13909 13910 13911 13912 13913 13914 13915 13916 13917 13918 13919 13920 13921 13922 13923 13924 13925 13926 13927 13928 13929 13930 13931 13932 13933 13934 13935 13936 13937 13938 13939 13940 13941 13942 13943 13944 13945 13946 13947 13948 13949 13950 13951 13952 13953 13954 13955 13956 13957 13958 13959 13960 13961 13962 13963 13964 13965 13966 13967 13968 13969 13970 13971 13972 13973 13974 13975 13976 13977 13978 13979 13980 13981 13982 13983 13984 13985 13986 13987 13988 13989 13990 13991 13992 13993 13994 13995 13996 13997 13998 13999 14000 14001 14002 14003 14004 14005 14006 14007 14008 14009 14010 14011 14012 14013 14014 14015 14016 14017 14018 14019 14020 14021 14022 14023 14024 14025 14026 14027 14028 14029 14030 14031 14032 14033 14034 14035 14036 14037 14038 14039 14040 14041 14042 14043 14044 14045 14046 14047 14048 14049 14050 14051 14052 14053 14054 14055 14056 14057 14058 14059 14060 14061 14062 14063 14064 14065 14066 14067 14068 14069 14070 14071 14072 14073 14074 14075 14076 14077 14078 14079 14080 14081 14082 14083 14084 14085 14086 14087 14088 14089 14090 14091 14092 14093 14094 14095 14096 14097 14098 14099 14100 14101 14102 14103 14104 14105 14106 14107 14108 14109 14110 14111 14112 14113 14114 14115 14116 14117 14118 14119 14120 14121 14122 14123 14124 14125 14126 14127 14128 14129 14130 14131 14132 14133 14134 14135 14136 14137 14138 14139 14140 14141 14142 14143 14144 14145 14146 14147 14148 14149 14150 14151 14152 14153 14154 14155 14156 14157 14158 14159 14160 14161 14162 14163 14164 14165 14166 14167 14168 14169 14170 14171 14172 14173 14174 14175 14176 14177 14178 14179 14180 14181 14182 14183 14184 14185 14186 14187 14188 14189 14190 14191 14192 14193 14194 14195 14196 14197 14198 14199 14200 14201 14202 14203 14204 14205 14206 14207 14208 14209 14210 14211 14212 14213 14214 14215 14216 14217 14218 14219 14220 14221 14222 14223 14224 14225 14226 14227 14228 14229 14230 14231 14232 14233 14234 14235 14236 14237 14238 14239 14240 14241 14242 14243 14244 14245 14246 14247 14248 14249 14250 14251 14252 14253 14254 14255 14256 14257 14258 14259 14260 14261 14262 14263 14264 14265 14266 14267 14268 14269 14270 14271 14272 14273 14274 14275 14276 14277 14278 14279 14280 14281 14282 14283 14284 14285 14286 14287 14288 14289 14290 14291 14292 14293 14294 14295 14296 14297 14298 14299 14300 14301 14302 14303 14304 14305 14306 14307 14308 14309 14310 14311 14312 14313 14314 14315 14316 14317 14318 14319 14320 14321 14322 14323 14324 14325 14326 14327 14328 14329 14330 14331 14332 14333 14334 14335 14336 14337 14338 14339 14340 14341 14342 14343 14344 14345 14346 14347 14348 14349 14350 14351 14352 14353 14354 14355 14356 14357 14358 14359 14360 14361 14362 14363 14364 14365 14366 14367 14368 14369 14370 14371 14372 14373 14374 14375 14376 14377 14378 14379 14380 14381 14382 14383 14384 14385 14386 14387 14388 14389 14390 14391 14392 14393 14394 14395 14396 14397 14398 14399 14400 14401 14402 14403 14404 14405 14406 14407 14408 14409 14410 14411 14412 14413 14414 14415 14416 14417 14418 14419 14420 14421 14422 14423 14424 14425 14426 14427 14428 14429 14430 14431 14432 14433 14434 14435 14436 14437 14438 14439 14440 14441 14442 14443 14444 14445 14446 14447 14448 14449 14450 14451 14452 14453 14454 14455 14456 14457 14458 14459 14460 14461 14462 14463 14464 14465 14466 14467 14468 14469 14470 14471 14472 14473 14474 14475 14476 14477 14478 14479 14480 14481 14482 14483 14484 14485 14486 14487 14488 14489 14490 14491 14492 14493 14494 14495 14496 14497 14498 14499 14500 14501 14502 14503 14504 14505 14506 14507 14508 14509 14510 14511 14512 14513 14514 14515 14516 14517 14518 14519 14520 14521 14522 14523 14524 14525 14526 14527 14528 14529 14530 14531 14532 14533 14534 14535 14536 14537 14538 14539 14540 14541 14542 14543 14544 14545 14546 14547 14548 14549 14550 14551 14552 14553 14554 14555 14556 14557 14558 14559 14560 14561 14562 14563 14564 14565 14566 14567 14568 14569 14570 14571 14572 14573 14574 14575 14576 14577 14578 14579 14580 14581 14582 14583 14584 14585 14586 14587 14588 14589 14590 14591 14592 14593 14594 14595 14596 14597 14598 14599 14600 14601 14602 14603 14604 14605 14606 14607 14608 14609 14610 14611 14612 14613 14614 14615 14616 14617 14618 14619 14620 14621 14622 14623 14624 14625 14626 14627 14628 14629 14630 14631 14632 14633 14634 14635 14636 14637 14638 14639 14640 14641 14642 14643 14644 14645 14646 14647 14648 14649 14650 14651 14652 14653 14654 14655 14656 14657 14658 14659 14660 14661 14662 14663 14664 14665 14666 14667 14668 14669 14670 14671 14672 14673 14674 14675 14676 14677 14678 14679 14680 14681 14682 14683 14684 14685 14686 14687 14688 14689 14690 14691 14692 14693 14694 14695 14696 14697 14698 14699 14700 14701 14702 14703 14704 14705 14706 14707 14708 14709 14710 14711 14712 14713 14714 14715 14716 14717 14718 14719 14720 14721 14722 14723 14724 14725 14726 14727 14728 14729 14730 14731 14732 14733 14734 14735 14736 14737 14738 14739 14740 14741 14742 14743 14744 14745 14746 14747 14748 14749 14750 14751 14752 14753 14754 14755 14756 14757 14758 14759 14760 14761 14762 14763 14764 14765 14766 14767 14768 14769 14770 14771 14772 14773 14774 14775 14776 14777 14778 14779 14780 14781 14782 14783 14784 14785 14786 14787 14788 14789 14790 14791 14792 14793 14794 14795 14796 14797 14798 14799 14800 14801 14802 14803 14804 14805 14806 14807 14808 14809 14810 14811 14812 14813 14814 14815 14816 14817 14818 14819 14820 14821 14822 14823 14824 14825 14826 14827 14828 14829 14830 14831 14832 14833 14834 14835 14836 14837 14838 14839 14840 14841 14842 14843 14844 14845 14846 14847 14848 14849 14850 14851 14852 14853 14854 14855 14856 14857 14858 14859 14860 14861 14862 14863 14864 14865 14866 14867 14868 14869 14870 14871 14872 14873 14874 14875 14876 14877 14878 14879 14880 14881 14882 14883 14884 14885 14886 14887 14888 14889 14890 14891 14892 14893 14894 14895 14896 14897 14898 14899 14900 14901 14902 14903 14904 14905 14906 14907 14908 14909 14910 14911 14912 14913 14914 14915 14916 14917 14918 14919 14920 14921 14922 14923 14924 14925 14926 14927 14928 14929 14930 14931 14932 14933 14934 14935 14936 14937 14938 14939 14940 14941 14942 14943 14944 14945 14946 14947 14948 14949 14950 14951 14952 14953 14954 14955 14956 14957 14958 14959 14960 14961 14962 14963 14964 14965 14966 14967 14968 14969 14970 14971 14972 14973 14974 14975 14976 14977 14978 14979 14980 14981 14982 14983 14984 14985 14986 14987 14988 14989 14990 14991 14992 14993 14994 14995 14996 14997 14998 14999 15000 15001 15002 15003 15004 15005 15006 15007 15008 15009 15010 15011 15012 15013 15014 15015 15016 15017 15018 15019 15020 15021 15022 15023 15024 15025 15026 15027 15028 15029 15030 15031 15032 15033 15034 15035 15036 15037 15038 15039 15040 15041 15042 15043 15044 15045 15046 15047 15048 15049 15050 15051 15052 15053 15054 15055 15056 15057 15058 15059 15060 15061 15062 15063 15064 15065 15066 15067 15068 15069 15070 15071 15072 15073 15074 15075 15076 15077 15078 15079 15080 15081 15082 15083 15084 15085 15086 15087 15088 15089 15090 15091 15092 15093 15094 15095 15096 15097 15098 15099 15100 15101 15102 15103 15104 15105 15106 15107 15108 15109 15110 15111 15112 15113 15114 15115 15116 15117 15118 15119 15120 15121 15122 15123 15124 15125 15126 15127 15128 15129 15130 15131 15132 15133 15134 15135 15136 15137 15138 15139 15140 15141 15142 15143 15144 15145 15146 15147 15148 15149 15150 15151 15152 15153 15154 15155 15156 15157 15158 15159 15160 15161 15162 15163 15164 15165 15166 15167 15168 15169 15170 15171 15172 15173 15174 15175 15176 15177 15178 15179 15180 15181 15182 15183 15184 15185 15186 15187 15188 15189 15190 15191 15192 15193 15194 15195 15196 15197 15198 15199 15200 15201 15202 15203 15204 15205 15206 15207 15208 15209 15210 15211 15212 15213 15214 15215 15216 15217 15218 15219 15220 15221 15222 15223 15224 15225 15226 15227 15228 15229 15230 15231 15232 15233 15234 15235 15236 15237 15238 15239 15240 15241 15242 15243 15244 15245 15246 15247 15248 15249 15250 15251 15252 15253 15254 15255 15256 15257 15258 15259 15260 15261 15262 15263 15264 15265 15266 15267 15268 15269 15270 15271 15272 15273 15274 15275 15276 15277 15278 15279 15280 15281 15282 15283 15284 15285 15286 15287 15288 15289 15290 15291 15292 15293 15294 15295 15296 15297 15298 15299 15300 15301 15302 15303 15304 15305 15306 15307 15308 15309 15310 15311 15312 15313 15314 15315 15316 15317 15318 15319 15320 15321 15322 15323 15324 15325 15326 15327 15328 15329 15330 15331 15332 15333 15334 15335 15336 15337 15338 15339 15340 15341 15342 15343 15344 15345 15346 15347 15348 15349 15350 15351 15352 15353 15354 15355 15356 15357 15358 15359 15360 15361 15362 15363 15364 15365 15366 15367 15368 15369 15370 15371 15372 15373 15374 15375 15376 15377 15378 15379 15380 15381 15382 15383 15384 15385 15386 15387 15388 15389 15390 15391 15392 15393 15394 15395 15396 15397 15398 15399 15400 15401 15402 15403 15404 15405 15406 15407 15408 15409 15410 15411 15412 15413 15414 15415 15416 15417 15418 15419 15420 15421 15422 15423 15424 15425 15426 15427 15428 15429 15430 15431 15432 15433 15434 15435 15436 15437 15438 15439 15440 15441 15442 15443 15444 15445 15446 15447 15448 15449 15450 15451 15452 15453 15454 15455 15456 15457 15458 15459 15460 15461 15462 15463 15464 15465 15466 15467 15468 15469 15470 15471 15472 15473 15474 15475 15476 15477 15478 15479 15480 15481 15482 15483 15484 15485 15486 15487 15488 15489 15490 15491 15492 15493 15494 15495 15496 15497 15498 15499 15500 15501 15502 15503 15504 15505 15506 15507 15508 15509 15510 15511 15512 15513 15514 15515 15516 15517 15518 15519 15520 15521 15522 15523 15524 15525 15526 15527 15528 15529 15530 15531 15532 15533 15534 15535 15536 15537 15538 15539 15540 15541 15542 15543 15544 15545 15546 15547 15548 15549 15550 15551 15552 15553 15554 15555 15556 15557 15558 15559 15560 15561 15562 15563 15564 15565 15566 15567 15568 15569 15570 15571 15572 15573 15574 15575 15576 15577 15578 15579 15580 15581 15582 15583 15584 15585 15586 15587 15588 15589 15590 15591 15592 15593 15594 15595 15596 15597 15598 15599 15600 15601 15602 15603 15604 15605 15606 15607 15608 15609 15610 15611 15612 15613 15614 15615 15616 15617 15618 15619 15620 15621 15622 15623 15624 15625 15626 15627 15628 15629 15630 15631 15632 15633 15634 15635 15636 15637 15638 15639 15640 15641 15642 15643 15644 15645 15646 15647 15648 15649 15650 15651 15652 15653 15654 15655 15656 15657 15658 15659 15660 15661 15662 15663 15664 15665 15666 15667 15668 15669 15670 15671 15672 15673 15674 15675 15676 15677 15678 15679 15680 15681 15682 15683 15684 15685 15686 15687 15688 15689 15690 15691 15692 15693 15694 15695 15696 15697 15698 15699 15700 15701 15702 15703 15704 15705 15706 15707 15708 15709 15710 15711 15712 15713 15714 15715 15716 15717 15718 15719 15720 15721 15722 15723 15724 15725 15726 15727 15728 15729 15730 15731 15732 15733 15734 15735 15736 15737 15738 15739 15740 15741 15742 15743 15744 15745 15746 15747 15748 15749 15750 15751 15752 15753 15754 15755 15756 15757 15758 15759 15760 15761 15762 15763 15764 15765 15766 15767 15768 15769 15770 15771 15772 15773 15774 15775 15776 15777 15778 15779 15780 15781 15782 15783 15784 15785 15786 15787 15788 15789 15790 15791 15792 15793 15794 15795 15796 15797 15798 15799 15800 15801 15802 15803 15804 15805 15806 15807 15808 15809 15810 15811 15812 15813 15814 15815 15816 15817 15818 15819 15820 15821 15822 15823 15824 15825 15826 15827 15828 15829 15830 15831 15832 15833 15834 15835 15836 15837 15838 15839 15840 15841 15842 15843 15844 15845 15846 15847 15848 15849 15850 15851 15852 15853 15854 15855 15856 15857 15858 15859 15860 15861 15862 15863 15864 15865 15866 15867 15868 15869 15870 15871 15872 15873 15874 15875 15876 15877 15878 15879 15880 15881 15882 15883 15884 15885 15886 15887 15888 15889 15890 15891 15892 15893 15894 15895 15896 15897 15898 15899 15900 15901 15902 15903 15904 15905 15906 15907 15908 15909 15910 15911 15912 15913 15914 15915 15916 15917 15918 15919 15920 15921 15922 15923 15924 15925 15926 15927 15928 15929 15930 15931 15932 15933 15934 15935 15936 15937 15938 15939 15940 15941 15942 15943 15944 15945 15946 15947 15948 15949 15950 15951 15952 15953 15954 15955 15956 15957 15958 15959 15960 15961 15962 15963 15964 15965 15966 15967 15968 15969 15970 15971 15972 15973 15974 15975 15976 15977 15978 15979 15980 15981 15982 15983 15984 15985 15986 15987 15988 15989 15990 15991 15992 15993 15994 15995 15996 15997 15998 15999 16000 16001 16002 16003 16004 16005 16006 16007 16008 16009 16010 16011 16012 16013 16014 16015 16016 16017 16018 16019 16020 16021 16022 16023 16024 16025 16026 16027 16028 16029 16030 16031 16032 16033 16034 16035 16036 16037 16038 16039 16040 16041 16042 16043 16044 16045 16046 16047 16048 16049 16050 16051 16052 16053 16054 16055 16056 16057 16058 16059 16060 16061 16062 16063 16064 16065 16066 16067 16068 16069 16070 16071 16072 16073 16074 16075 16076 16077 16078 16079 16080 16081 16082 16083 16084 16085 16086 16087 16088 16089 16090 16091 16092 16093 16094 16095 16096 16097 16098 16099 16100 16101 16102 16103 16104 16105 16106 16107 16108 16109 16110 16111 16112 16113 16114 16115 16116 16117 16118 16119 16120 16121 16122 16123 16124 16125 16126 16127 16128 16129 16130 16131 16132 16133 16134 16135 16136 16137 16138 16139 16140 16141 16142 16143 16144 16145 16146 16147 16148 16149 16150 16151 16152 16153 16154 16155 16156 16157 16158 16159 16160 16161 16162 16163 16164 16165 16166 16167 16168 16169 16170 16171 16172 16173 16174 16175 16176 16177 16178 16179 16180 16181 16182 16183 16184 16185 16186 16187 16188 16189 16190 16191 16192 16193 16194 16195 16196 16197 16198 16199 16200 16201 16202 16203 16204 16205 16206 16207 16208 16209 16210 16211 16212 16213 16214 16215 16216 16217 16218 16219 16220 16221 16222 16223 16224 16225 16226 16227 16228 16229 16230 16231 16232 16233 16234 16235 16236 16237 16238 16239 16240 16241 16242 16243 16244 16245 16246 16247 16248 16249 16250 16251 16252 16253 16254 16255 16256 16257 16258 16259 16260 16261 16262 16263 16264 16265 16266 16267 16268 16269 16270 16271 16272 16273 16274 16275 16276 16277 16278 16279 16280 16281 16282 16283 16284 16285 16286 16287 16288 16289 16290 16291 16292 16293 16294 16295 16296 16297 16298 16299 16300 16301 16302 16303 16304 16305 16306 16307 16308 16309 16310 16311 16312 16313 16314 16315 16316 16317 16318 16319 16320 16321 16322 16323 16324 16325 16326 16327 16328 16329 16330 16331 16332 16333 16334 16335 16336 16337 16338 16339 16340 16341 16342 16343 16344 16345 16346 16347 16348 16349 16350 16351 16352 16353 16354 16355 16356 16357 16358 16359 16360 16361 16362 16363 16364 16365 16366 16367 16368 16369 16370 16371 16372 16373 16374 16375 16376 16377 16378 16379 16380 16381 16382 16383 16384 16385 16386 16387 16388 16389 16390 16391 16392 16393 16394 16395 16396 16397 16398 16399 16400 16401 16402 16403 16404 16405 16406 16407 16408 16409 16410 16411 16412 16413 16414 16415 16416 16417 16418 16419 16420 16421 16422 16423 16424 16425 16426 16427 16428 16429 16430 16431 16432 16433 16434 16435 16436 16437 16438 16439 16440 16441 16442 16443 16444 16445 16446 16447 16448 16449 16450 16451 16452 16453 16454 16455 16456 16457 16458 16459 16460 16461 16462 16463 16464 16465 16466 16467 16468 16469 16470 16471 16472 16473 16474 16475 16476 16477 16478 16479 16480 16481 16482 16483 16484 16485 16486 16487 16488 16489 16490 16491 16492 16493 16494 16495 16496 16497 16498 16499 16500 16501 16502 16503 16504 16505 16506 16507 16508 16509 16510 16511 16512 16513 16514 16515 16516 16517 16518 16519 16520 16521 16522 16523 16524 16525 16526 16527 16528 16529 16530 16531 16532 16533 16534 16535 16536 16537 16538 16539 16540 16541 16542 16543 16544 16545 16546 16547 16548 16549 16550 16551 16552 16553 16554 16555 16556 16557 16558 16559 16560 16561 16562 16563 16564 16565 16566 16567 16568 16569 16570 16571 16572 16573 16574 16575 16576 16577 16578 16579 16580 16581 16582 16583 16584 16585 16586 16587 16588 16589 16590 16591 16592 16593 16594 16595 16596 16597 16598 16599 16600 16601 16602 16603 16604 16605 16606 16607 16608 16609 16610 16611 16612 16613 16614 16615 16616 16617 16618 16619 16620 16621 16622 16623 16624 16625 16626 16627 16628 16629 16630 16631 16632 16633 16634 16635 16636 16637 16638 16639 16640 16641 16642 16643 16644 16645 16646 16647 16648 16649 16650 16651 16652 16653 16654 16655 16656 16657 16658 16659 16660 16661 16662 16663 16664 16665 16666 16667 16668 16669 16670 16671 16672 16673 16674 16675 16676 16677 16678 16679 16680 16681 16682 16683 16684 16685 16686 16687 16688 16689 16690 16691 16692 16693 16694 16695 16696 16697 16698 16699 16700 16701 16702 16703 16704 16705 16706 16707 16708 16709 16710 16711 16712 16713 16714 16715 16716 16717 16718 16719 16720 16721 16722 16723 16724 16725 16726 16727 16728 16729 16730 16731 16732 16733 16734 16735 16736 16737 16738 16739 16740 16741 16742 16743 16744 16745 16746 16747 16748 16749 16750 16751 16752 16753 16754 16755 16756 16757 16758 16759 16760 16761 16762 16763 16764 16765 16766 16767 16768 16769 16770 16771 16772 16773 16774 16775 16776 16777 16778 16779 16780 16781 16782 16783 16784 16785 16786 16787 16788 16789 16790 16791 16792 16793 16794 16795 16796 16797 16798 16799 16800 16801 16802 16803 16804 16805 16806 16807 16808 16809 16810 16811 16812 16813 16814 16815 16816 16817 16818 16819 16820 16821 16822 16823 16824 16825 16826 16827 16828 16829 16830 16831 16832 16833 16834 16835 16836 16837 16838 16839 16840 16841 16842 16843 16844 16845 16846 16847 16848 16849 16850 16851 16852 16853 16854 16855 16856 16857 16858 16859 16860 16861 16862 16863 16864 16865 16866 16867 16868 16869 16870 16871 16872 16873 16874 16875 16876 16877 16878 16879 16880 16881 16882 16883 16884 16885 16886 16887 16888 16889 16890 16891 16892 16893 16894 16895 16896 16897 16898 16899 16900 16901 16902 16903 16904 16905 16906 16907 16908 16909 16910 16911 16912 16913 16914 16915 16916 16917 16918 16919 16920 16921 16922 16923 16924 16925 16926 16927 16928 16929 16930 16931 16932 16933 16934 16935 16936 16937 16938 16939 16940 16941 16942 16943 16944 16945 16946 16947 16948 16949 16950 16951 16952 16953 16954 16955 16956 16957 16958 16959 16960 16961 16962 16963 16964 16965 16966 16967 16968 16969 16970 16971 16972 16973 16974 16975 16976 16977 16978 16979 16980 16981 16982 16983 16984 16985 16986 16987 16988 16989 16990 16991 16992 16993 16994 16995 16996 16997 16998 16999 17000 17001 17002 17003 17004 17005 17006 17007 17008 17009 17010 17011 17012 17013 17014 17015 17016 17017 17018 17019 17020 17021 17022 17023 17024 17025 17026 17027 17028 17029 17030 17031 17032 17033 17034 17035 17036 17037 17038 17039 17040 17041 17042 17043 17044 17045 17046 17047 17048 17049 17050 17051 17052 17053 17054 17055 17056 17057 17058 17059 17060 17061 17062 17063 17064 17065 17066 17067 17068 17069 17070 17071 17072 17073 17074 17075 17076 17077 17078 17079 17080 17081 17082 17083 17084 17085 17086 17087 17088 17089 17090 17091 17092 17093 17094 17095 17096 17097 17098 17099 17100 17101 17102 17103 17104 17105 17106 17107 17108 17109 17110 17111 17112 17113 17114 17115 17116 17117 17118 17119 17120 17121 17122 17123 17124 17125 17126 17127 17128 17129 17130 17131 17132 17133 17134 17135 17136 17137 17138 17139 17140 17141 17142 17143 17144 17145 17146 17147 17148 17149 17150 17151 17152 17153 17154 17155 17156 17157 17158 17159 17160 17161 17162 17163 17164 17165 17166 17167 17168 17169 17170 17171 17172 17173 17174 17175 17176 17177 17178 17179 17180 17181 17182 17183 17184 17185 17186 17187 17188 17189 17190 17191 17192 17193 17194 17195 17196 17197 17198 17199 17200 17201 17202 17203 17204 17205 17206 17207 17208 17209 17210 17211 17212 17213 17214 17215 17216 17217 17218 17219 17220 17221 17222 17223 17224 17225 17226 17227 17228 17229 17230 17231 17232 17233 17234 17235 17236 17237 17238 17239 17240 17241 17242 17243 17244 17245 17246 17247 17248 17249 17250 17251 17252 17253 17254 17255 17256 17257 17258 17259 17260 17261 17262 17263 17264 17265 17266 17267 17268 17269 17270 17271 17272 17273 17274 17275 17276 17277 17278 17279 17280 17281 17282 17283 17284 17285 17286 17287 17288 17289 17290 17291 17292 17293 17294 17295 17296 17297 17298 17299 17300 17301 17302 17303 17304 17305 17306 17307 17308 17309 17310 17311 17312 17313 17314 17315 17316 17317 17318 17319 17320 17321 17322 17323 17324 17325 17326 17327 17328 17329 17330 17331 17332 17333 17334 17335 17336 17337 17338 17339 17340 17341 17342 17343 17344 17345 17346 17347 17348 17349 17350 17351 17352 17353 17354 17355 17356 17357 17358 17359 17360 17361 17362 17363 17364 17365 17366 17367 17368 17369 17370 17371 17372 17373 17374 17375 17376 17377 17378 17379 17380 17381 17382 17383 17384 17385 17386 17387 17388 17389 17390 17391 17392 17393 17394 17395 17396 17397 17398 17399 17400 17401 17402 17403 17404 17405 17406 17407 17408 17409 17410 17411 17412 17413 17414 17415 17416 17417 17418 17419 17420 17421 17422 17423 17424 17425 17426 17427 17428 17429 17430 17431 17432 17433 17434 17435 17436 17437 17438 17439 17440 17441 17442 17443 17444 17445 17446 17447 17448 17449 17450 17451 17452 17453 17454 17455 17456 17457 17458 17459 17460 17461 17462 17463 17464 17465 17466 17467 17468 17469 17470 17471 17472 17473 17474 17475 17476 17477 17478 17479 17480 17481 17482 17483 17484 17485 17486 17487 17488 17489 17490 17491 17492 17493 17494 17495 17496 17497 17498 17499 17500 17501 17502 17503 17504 17505 17506 17507 17508 17509 17510 17511 17512 17513 17514 17515 17516 17517 17518 17519 17520 17521 17522 17523 17524 17525 17526 17527 17528 17529 17530 17531 17532 17533 17534 17535 17536 17537 17538 17539 17540 17541 17542 17543 17544 17545 17546 17547 17548 17549 17550 17551 17552 17553 17554 17555 17556 17557 17558 17559 17560 17561 17562 17563 17564 17565 17566 17567 17568 17569 17570 17571 17572 17573 17574 17575 17576 17577 17578 17579 17580 17581 17582 17583 17584 17585 17586 17587 17588 17589 17590 17591 17592 17593 17594 17595 17596 17597 17598 17599 17600 17601 17602 17603 17604 17605 17606 17607 17608 17609 17610 17611 17612 17613 17614 17615 17616 17617 17618 17619 17620 17621 17622 17623 17624 17625 17626 17627 17628 17629 17630 17631 17632 17633 17634 17635 17636 17637 17638 17639 17640 17641 17642 17643 17644 17645 17646 17647 17648 17649 17650 17651 17652 17653 17654 17655 17656 17657 17658 17659 17660 17661 17662 17663 17664 17665 17666 17667 17668 17669 17670 17671 17672 17673 17674 17675 17676 17677 17678 17679 17680 17681 17682 17683 17684 17685 17686 17687 17688 17689 17690 17691 17692 17693 17694 17695 17696 17697 17698 17699 17700 17701 17702 17703 17704 17705 17706 17707 17708 17709 17710 17711 17712 17713 17714 17715 17716 17717 17718 17719 17720 17721 17722 17723 17724 17725 17726 17727 17728 17729 17730 17731 17732 17733 17734 17735 17736 17737 17738 17739 17740 17741 17742 17743 17744 17745 17746 17747 17748 17749 17750 17751 17752 17753 17754 17755 17756 17757 17758 17759 17760 17761 17762 17763 17764 17765 17766 17767 17768 17769 17770 17771 17772 17773 17774 17775 17776 17777 17778 17779 17780 17781 17782 17783 17784 17785 17786 17787 17788 17789 17790 17791 17792 17793 17794 17795 17796 17797 17798 17799 17800 17801 17802 17803 17804 17805 17806 17807 17808 17809 17810 17811 17812 17813 17814 17815 17816 17817 17818 17819 17820 17821 17822 17823 17824 17825 17826 17827 17828 17829 17830 17831 17832 17833 17834 17835 17836 17837 17838 17839 17840 17841 17842 17843 17844 17845 17846 17847 17848 17849 17850 17851 17852 17853 17854 17855 17856 17857 17858 17859 17860 17861 17862 17863 17864 17865 17866 17867 17868 17869 17870 17871 17872 17873 17874 17875 17876 17877 17878 17879 17880 17881 17882 17883 17884 17885 17886 17887 17888 17889 17890 17891 17892 17893 17894 17895 17896 17897 17898 17899 17900 17901 17902 17903 17904 17905 17906 17907 17908 17909 17910 17911 17912 17913 17914 17915 17916 17917 17918 17919 17920 17921 17922 17923 17924 17925 17926 17927 17928 17929 17930 17931 17932 17933 17934 17935 17936 17937 17938 17939 17940 17941 17942 17943 17944 17945 17946 17947 17948 17949 17950 17951 17952 17953 17954 17955 17956 17957 17958 17959 17960 17961 17962 17963 17964 17965 17966 17967 17968 17969 17970 17971 17972 17973 17974 17975 17976 17977 17978 17979 17980 17981 17982 17983 17984 17985 17986 17987 17988 17989 17990 17991 17992 17993 17994 17995 17996 17997 17998 17999 18000 18001 18002 18003 18004 18005 18006 18007 18008 18009 18010 18011 18012 18013 18014 18015 18016 18017 18018 18019 18020 18021 18022 18023 18024 18025 18026 18027 18028 18029 18030 18031 18032 18033 18034 18035 18036 18037 18038 18039 18040 18041 18042 18043 18044 18045 18046 18047 18048 18049 18050 18051 18052 18053 18054 18055 18056 18057 18058 18059 18060 18061 18062 18063 18064 18065 18066 18067 18068 18069 18070 18071 18072 18073 18074 18075 18076 18077 18078 18079 18080 18081 18082 18083 18084 18085 18086 18087 18088 18089 18090 18091 18092 18093 18094 18095 18096 18097 18098 18099 18100 18101 18102 18103 18104 18105 18106 18107 18108 18109 18110 18111 18112 18113 18114 18115 18116 18117 18118 18119 18120 18121 18122 18123 18124 18125 18126 18127 18128 18129 18130 18131 18132 18133 18134 18135 18136 18137 18138 18139 18140 18141 18142 18143 18144 18145 18146 18147 18148 18149 18150 18151 18152 18153 18154 18155 18156 18157 18158 18159 18160 18161 18162 18163 18164 18165 18166 18167 18168 18169 18170 18171 18172 18173 18174 18175 18176 18177 18178 18179 18180 18181 18182 18183 18184 18185 18186 18187 18188 18189 18190 18191 18192 18193 18194 18195 18196 18197 18198 18199 18200 18201 18202 18203 18204 18205 18206 18207 18208 18209 18210 18211 18212 18213 18214 18215 18216 18217 18218 18219 18220 18221 18222 18223 18224 18225 18226 18227 18228 18229 18230 18231 18232 18233 18234 18235 18236 18237 18238 18239 18240 18241 18242 18243 18244 18245 18246 18247 18248 18249 18250 18251 18252 18253 18254 18255 18256 18257 18258 18259 18260 18261 18262 18263 18264 18265 18266 18267 18268 18269 18270 18271 18272 18273 18274 18275 18276 18277 18278 18279 18280 18281 18282 18283 18284 18285 18286 18287 18288 18289 18290 18291 18292 18293 18294 18295 18296 18297 18298 18299 18300 18301 18302 18303 18304 18305 18306 18307 18308 18309 18310 18311 18312 18313 18314 18315 18316 18317 18318 18319 18320 18321 18322 18323 18324 18325 18326 18327 18328 18329 18330 18331 18332 18333 18334 18335 18336 18337 18338 18339 18340 18341 18342 18343 18344 18345 18346 18347 18348 18349 18350 18351 18352 18353 18354 18355 18356 18357 18358 18359 18360 18361 18362 18363 18364 18365 18366 18367 18368 18369 18370 18371 18372 18373 18374 18375 18376 18377 18378 18379 18380 18381 18382 18383 18384 18385 18386 18387 18388 18389 18390 18391 18392 18393 18394 18395 18396 18397 18398 18399 18400 18401 18402 18403 18404 18405 18406 18407 18408 18409 18410 18411 18412 18413 18414 18415 18416 18417 18418 18419 18420 18421 18422 18423 18424 18425 18426 18427 18428 18429 18430 18431 18432 18433 18434 18435 18436 18437 18438 18439 18440 18441 18442 18443 18444 18445 18446 18447 18448 18449 18450 18451 18452 18453 18454 18455 18456 18457 18458 18459 18460 18461 18462 18463 18464 18465 18466 18467 18468 18469 18470 18471 18472 18473 18474 18475 18476 18477 18478 18479 18480 18481 18482 18483 18484 18485 18486 18487 18488 18489 18490 18491 18492 18493 18494 18495 18496 18497 18498 18499 18500 18501 18502 18503 18504 18505 18506 18507 18508 18509 18510 18511 18512 18513 18514 18515 18516 18517 18518 18519 18520 18521 18522 18523 18524 18525 18526 18527 18528 18529 18530 18531 18532 18533 18534 18535 18536 18537 18538 18539 18540 18541 18542 18543 18544 18545 18546 18547 18548 18549 18550 18551 18552 18553 18554 18555 18556 18557 18558 18559 18560 18561 18562 18563 18564 18565 18566 18567 18568 18569 18570 18571 18572 18573 18574 18575 18576 18577 18578 18579 18580 18581 18582 18583 18584 18585 18586 18587 18588 18589 18590 18591 18592 18593 18594 18595 18596 18597 18598 18599 18600 18601 18602 18603 18604 18605 18606 18607 18608 18609 18610 18611 18612 18613 18614 18615 18616 18617 18618 18619 18620 18621 18622 18623 18624 18625 18626 18627 18628 18629 18630 18631 18632 18633 18634 18635 18636 18637 18638 18639 18640 18641 18642 18643 18644 18645 18646 18647 18648 18649 18650 18651 18652 18653 18654 18655 18656 18657 18658 18659 18660 18661 18662 18663 18664 18665 18666 18667 18668 18669 18670 18671 18672 18673 18674 18675 18676 18677 18678 18679 18680 18681 18682 18683 18684 18685 18686 18687 18688 18689 18690 18691 18692 18693 18694 18695 18696 18697 18698 18699 18700 18701 18702 18703 18704 18705 18706 18707 18708 18709 18710 18711 18712 18713 18714 18715 18716 18717 18718 18719 18720 18721 18722 18723 18724 18725 18726 18727 18728 18729 18730 18731 18732 18733 18734 18735 18736 18737 18738 18739 18740 18741 18742 18743 18744 18745 18746 18747 18748 18749 18750 18751 18752 18753 18754 18755 18756 18757 18758 18759 18760 18761 18762 18763 18764 18765 18766 18767 18768 18769 18770 18771 18772 18773 18774 18775 18776 18777 18778 18779 18780 18781 18782 18783 18784 18785 18786 18787 18788 18789 18790 18791 18792 18793 18794 18795 18796 18797 18798 18799 18800 18801 18802 18803 18804 18805 18806 18807 18808 18809 18810 18811 18812 18813 18814 18815 18816 18817 18818 18819 18820 18821 18822 18823 18824 18825 18826 18827 18828 18829 18830 18831 18832 18833 18834 18835 18836 18837 18838 18839 18840 18841 18842 18843 18844 18845 18846 18847 18848 18849 18850 18851 18852 18853 18854 18855 18856 18857 18858 18859 18860 18861 18862 18863 18864 18865 18866 18867 18868 18869 18870 18871 18872 18873 18874 18875 18876 18877 18878 18879 18880 18881 18882 18883 18884 18885 18886 18887 18888 18889 18890 18891 18892 18893 18894 18895 18896 18897 18898 18899 18900 18901 18902 18903 18904 18905 18906 18907 18908 18909 18910 18911 18912 18913 18914 18915 18916 18917 18918 18919 18920 18921 18922 18923 18924 18925 18926 18927 18928 18929 18930 18931 18932 18933 18934 18935 18936 18937 18938 18939 18940 18941 18942 18943 18944 18945 18946 18947 18948 18949 18950 18951 18952 18953 18954 18955 18956 18957 18958 18959 18960 18961 18962 18963 18964 18965 18966 18967 18968 18969 18970 18971 18972 18973 18974 18975 18976 18977 18978 18979 18980 18981 18982 18983 18984 18985 18986 18987 18988 18989 18990 18991 18992 18993 18994 18995 18996 18997 18998 18999 19000 19001 19002 19003 19004 19005 19006 19007 19008 19009 19010 19011 19012 19013 19014 19015 19016 19017 19018 19019 19020 19021 19022 19023 19024 19025 19026 19027 19028 19029 19030 19031 19032 19033 19034 19035 19036 19037 19038 19039 19040 19041 19042 19043 19044 19045 19046 19047 19048 19049 19050 19051 19052 19053 19054 19055 19056 19057 19058 19059 19060 19061 19062 19063 19064 19065 19066 19067 19068 19069 19070 19071 19072 19073 19074 19075 19076 19077 19078 19079 19080 19081 19082 19083 19084 19085 19086 19087 19088 19089 19090 19091 19092 19093 19094 19095 19096 19097 19098 19099 19100 19101 19102 19103 19104 19105 19106 19107 19108 19109 19110 19111 19112 19113 19114 19115 19116 19117 19118 19119 19120 19121 19122 19123 19124 19125 19126 19127 19128 19129 19130 19131 19132 19133 19134 19135 19136 19137 19138 19139 19140 19141 19142 19143 19144 19145 19146 19147 19148 19149 19150 19151 19152 19153 19154 19155 19156 19157 19158 19159 19160 19161 19162 19163 19164 19165 19166 19167 19168 19169 19170 19171 19172 19173 19174 19175 19176 19177 19178 19179 19180 19181 19182 19183 19184 19185 19186 19187 19188 19189 19190 19191 19192 19193 19194 19195 19196 19197 19198 19199 19200 19201 19202 19203 19204 19205 19206 19207 19208 19209 19210 19211 19212 19213 19214 19215 19216 19217 19218 19219 19220 19221 19222 19223 19224 19225 19226 19227 19228 19229 19230 19231 19232 19233 19234 19235 19236 19237 19238 19239 19240 19241 19242 19243 19244 19245 19246 19247 19248 19249 19250 19251 19252 19253 19254 19255 19256 19257 19258 19259 19260 19261 19262 19263 19264 19265 19266 19267 19268 19269 19270 19271 19272 19273 19274 19275 19276 19277 19278 19279 19280 19281 19282 19283 19284 19285 19286 19287 19288 19289 19290 19291 19292 19293 19294 19295 19296 19297 19298 19299 19300 19301 19302 19303 19304 19305 19306 19307 19308 19309 19310 19311 19312 19313 19314 19315 19316 19317 19318 19319 19320 19321 19322 19323 19324 19325 19326 19327 19328 19329 19330 19331 19332 19333 19334 19335 19336 19337 19338 19339 19340 19341 19342 19343 19344 19345 19346 19347 19348 19349 19350 19351 19352 19353 19354 19355 19356 19357 19358 19359 19360 19361 19362 19363 19364 19365 19366 19367 19368 19369 19370 19371 19372 19373 19374 19375 19376 19377 19378 19379 19380 19381 19382 19383 19384 19385 19386 19387 19388 19389 19390 19391 19392 19393 19394 19395 19396 19397 19398 19399 19400 19401 19402 19403 19404 19405 19406 19407 19408 19409 19410 19411 19412 19413 19414 19415 19416 19417 19418 19419 19420 19421 19422 19423 19424 19425 19426 19427 19428 19429 19430 19431 19432 19433 19434 19435 19436 19437 19438 19439 19440 19441 19442 19443 19444 19445 19446 19447 19448 19449 19450 19451 19452 19453 19454 19455 19456 19457 19458 19459 19460 19461 19462 19463 19464 19465 19466 19467 19468 19469 19470 19471 19472 19473 19474 19475 19476 19477 19478 19479 19480 19481 19482 19483 19484 19485 19486 19487 19488 19489 19490 19491 19492 19493 19494 19495 19496 19497 19498 19499 19500 19501 19502 19503 19504 19505 19506 19507 19508 19509 19510 19511 19512 19513 19514 19515 19516 19517 19518 19519 19520 19521 19522 19523 19524 19525 19526 19527 19528 19529 19530 19531 19532 19533 19534 19535 19536 19537 19538 19539 19540 19541 19542 19543 19544 19545 19546 19547 19548 19549 19550 19551 19552 19553 19554 19555 19556 19557 19558 19559 19560 19561 19562 19563 19564 19565 19566 19567 19568 19569 19570 19571 19572 19573 19574 19575 19576 19577 19578 19579 19580 19581 19582 19583 19584 19585 19586 19587 19588 19589 19590 19591 19592 19593 19594 19595 19596 19597 19598 19599 19600 19601 19602 19603 19604 19605 19606 19607 19608 19609 19610 19611 19612 19613 19614 19615 19616 19617 19618 19619 19620 19621 19622 19623 19624 19625 19626 19627 19628 19629 19630 19631 19632 19633 19634 19635 19636 19637 19638 19639 19640 19641 19642 19643 19644 19645 19646 19647 19648 19649 19650 19651 19652 19653 19654 19655 19656 19657 19658 19659 19660 19661 19662 19663 19664 19665 19666 19667 19668 19669 19670 19671 19672 19673 19674 19675 19676 19677 19678 19679 19680 19681 19682 19683 19684 19685 19686 19687 19688 19689 19690 19691 19692 19693 19694 19695 19696 19697 19698 19699 19700 19701 19702 19703 19704 19705 19706 19707 19708 19709 19710 19711 19712 19713 19714 19715 19716 19717 19718 19719 19720 19721 19722 19723 19724 19725 19726 19727 19728 19729 19730 19731 19732 19733 19734 19735 19736 19737 19738 19739 19740 19741 19742 19743 19744 19745 19746 19747 19748 19749 19750 19751 19752 19753 19754 19755 19756 19757 19758 19759 19760 19761 19762 19763 19764 19765 19766 19767 19768 19769 19770 19771 19772 19773 19774 19775 19776 19777 19778 19779 19780 19781 19782 19783 19784 19785 19786 19787 19788 19789 19790 19791 19792 19793 19794 19795 19796 19797 19798 19799 19800 19801 19802 19803 19804 19805 19806 19807 19808 19809 19810 19811 19812 19813 19814 19815 19816 19817 19818 19819 19820 19821 19822 19823 19824 19825 19826 19827 19828 19829 19830 19831 19832 19833 19834 19835 19836 19837 19838 19839 19840 19841 19842 19843 19844 19845 19846 19847 19848 19849 19850 19851 19852 19853 19854 19855 19856 19857 19858 19859 19860 19861 19862 19863 19864 19865 19866 19867 19868 19869 19870 19871 19872 19873 19874 19875 19876 19877 19878 19879 19880 19881 19882 19883 19884 19885 19886 19887 19888 19889 19890 19891 19892 19893 19894 19895 19896 19897 19898 19899 19900 19901 19902 19903 19904 19905 19906 19907 19908 19909 19910 19911 19912 19913 19914 19915 19916 19917 19918 19919 19920 19921 19922 19923 19924 19925 19926 19927 19928 19929 19930 19931 19932 19933 19934 19935 19936 19937 19938 19939 19940 19941 19942 19943 19944 19945 19946 19947 19948 19949 19950 19951 19952 19953 19954 19955 19956 19957 19958 19959 19960 19961 19962 19963 19964 19965 19966 19967 19968 19969 19970 19971 19972 19973 19974 19975 19976 19977 19978 19979 19980 19981 19982 19983 19984 19985 19986 19987 19988 19989 19990 19991 19992 19993 19994 19995 19996 19997 19998 19999 20000 20001 20002 20003 20004 20005 20006 20007 20008 20009 20010 20011 20012 20013 20014 20015 20016 20017 20018 20019 20020 20021 20022 20023 20024 20025 20026 20027 20028 20029 20030 20031 20032 20033 20034 20035 20036 20037 20038 20039 20040 20041 20042 20043 20044 20045 20046 20047 20048 20049 20050 20051 20052 20053 20054 20055 20056 20057 20058 20059 20060 20061 20062 20063 20064 20065 20066 20067 20068 20069 20070 20071 20072 20073 20074 20075 20076 20077 20078 20079 20080 20081 20082 20083 20084 20085 20086 20087 20088 20089 20090 20091 20092 20093 20094 20095 20096 20097 20098 20099 20100 20101 20102 20103 20104 20105 20106 20107 20108 20109 20110 20111 20112 20113 20114 20115 20116 20117 20118 20119 20120 20121 20122 20123 20124 20125 20126 20127 20128 20129 20130 20131 20132 20133 20134 20135 20136 20137 20138 20139 20140 20141 20142 20143 20144 20145 20146 20147 20148 20149 20150 20151 20152 20153 20154 20155 20156 20157 20158 20159 20160 20161 20162 20163 20164 20165 20166 20167 20168 20169 20170 20171 20172 20173 20174 20175 20176 20177 20178 20179 20180 20181 20182 20183 20184 20185 20186 20187 20188 20189 20190 20191 20192 20193 20194 20195 20196 20197 20198 20199 20200 20201 20202 20203 20204 20205 20206 20207 20208 20209 20210 20211 20212 20213 20214 20215 20216 20217 20218 20219 20220 20221 20222 20223 20224 20225 20226 20227 20228 20229 20230 20231 20232 20233 20234 20235 20236 20237 20238 20239 20240 20241 20242 20243 20244 20245 20246 20247 20248 20249 20250 20251 20252 20253 20254 20255 20256 20257 20258 20259 20260 20261 20262 20263 20264 20265 20266 20267 20268 20269 20270 20271 20272 20273 20274 20275 20276 20277 20278 20279 20280 20281 20282 20283 20284 20285 20286 20287 20288 20289 20290 20291 20292 20293 20294 20295 20296 20297 20298 20299 20300 20301 20302 20303 20304 20305 20306 20307 20308 20309 20310 20311 20312 20313 20314 20315 20316 20317 20318 20319 20320 20321 20322 20323 20324 20325 20326 20327 20328 20329 20330 20331 20332 20333 20334 20335 20336 20337 20338 20339 20340 20341 20342 20343 20344 20345 20346 20347 20348 20349 20350 20351 20352 20353 20354 20355 20356 20357 20358 20359 20360 20361 20362 20363 20364 20365 20366 20367 20368 20369 20370 20371 20372 20373 20374 20375 20376 20377 20378 20379 20380 20381 20382 20383 20384 20385 20386 20387 20388 20389 20390 20391 20392 20393 20394 20395 20396 20397 20398 20399 20400 20401 20402 20403 20404 20405 20406 20407 20408 20409 20410 20411 20412 20413 20414 20415 20416 20417 20418 20419 20420 20421 20422 20423 20424 20425 20426 20427 20428 20429 20430 20431 20432 20433 20434 20435 20436 20437 20438 20439 20440 20441 20442 20443 20444 20445 20446 20447 20448 20449 20450 20451 20452 20453 20454 20455 20456 20457 20458 20459 20460 20461 20462 20463 20464 20465 20466 20467 20468 20469 20470 20471 20472 20473 20474 20475 20476 20477 20478 20479 20480 20481 20482 20483 20484 20485 20486 20487 20488 20489 20490 20491 20492 20493 20494 20495 20496 20497 20498 20499 20500 20501 20502 20503 20504 20505 20506 20507 20508 20509 20510 20511 20512 20513 20514 20515 20516 20517 20518 20519 20520 20521 20522 20523 20524 20525 20526 20527 20528 20529 20530 20531 20532 20533 20534 20535 20536 20537 20538 20539 20540 20541 20542 20543 20544 20545 20546 20547 20548 20549 20550 20551 20552 20553 20554 20555 20556 20557 20558 20559 20560 20561 20562 20563 20564 20565 20566 20567 20568 20569 20570 20571 20572 20573 20574 20575 20576 20577 20578 20579 20580 20581 20582 20583 20584 20585 20586 20587 20588 20589 20590 20591 20592 20593 20594 20595 20596 20597 20598 20599 20600 20601 20602 20603 20604 20605 20606 20607 20608 20609 20610 20611 20612 20613 20614 20615 20616 20617 20618 20619 20620 20621 20622 20623 20624 20625 20626 20627 20628 20629 20630 20631 20632 20633 20634 20635 20636 20637 20638 20639 20640 20641 20642 20643 20644 20645 20646 20647 20648 20649 20650 20651 20652 20653 20654 20655 20656 20657 20658 20659 20660 20661 20662 20663 20664 20665 20666 20667 20668 20669 20670 20671 20672 20673 20674 20675 20676 20677 20678 20679 20680 20681 20682 20683 20684 20685 20686 20687 20688 20689 20690 20691 20692 20693 20694 20695 20696 20697 20698 20699 20700 20701 20702 20703 20704 20705 20706 20707 20708 20709 20710 20711 20712 20713 20714 20715 20716 20717 20718 20719 20720 20721 20722 20723 20724 20725 20726 20727 20728 20729 20730 20731 20732 20733 20734 20735 20736 20737 20738 20739 20740 20741 20742 20743 20744 20745 20746 20747 20748 20749 20750 20751 20752 20753 20754 20755 20756 20757 20758 20759 20760 20761 20762 20763 20764 20765 20766 20767 20768 20769 20770 20771 20772 20773 20774 20775 20776 20777 20778 20779 20780 20781 20782 20783 20784 20785 20786 20787 20788 20789 20790 20791 20792 20793 20794 20795 20796 20797 20798 20799 20800 20801 20802 20803 20804 20805 20806 20807 20808 20809 20810 20811 20812 20813 20814 20815 20816 20817 20818 20819 20820 20821 20822 20823 20824 20825 20826 20827 20828 20829 20830 20831 20832 20833 20834 20835 20836 20837 20838 20839 20840 20841 20842 20843 20844 20845 20846 20847 20848 20849 20850 20851 20852 20853 20854 20855 20856 20857 20858 20859 20860 20861 20862 20863 20864 20865 20866 20867 20868 20869 20870 20871 20872 20873 20874 20875 20876 20877 20878 20879 20880 20881 20882 20883 20884 20885 20886 20887 20888 20889 20890 20891 20892 20893 20894 20895 20896 20897 20898 20899 20900 20901 20902 20903 20904 20905 20906 20907 20908 20909 20910 20911 20912 20913 20914 20915 20916 20917 20918 20919 20920 20921 20922 20923 20924 20925 20926 20927 20928 20929 20930 20931 20932 20933 20934 20935 20936 20937 20938 20939 20940 20941 20942 20943 20944 20945 20946 20947 20948 20949 20950 20951 20952 20953 20954 20955 20956 20957 20958 20959 20960 20961 20962 20963 20964 20965 20966 20967 20968 20969 20970 20971 20972 20973 20974 20975 20976 20977 20978 20979 20980 20981 20982 20983 20984 20985 20986 20987 20988 20989 20990 20991 20992 20993 20994 20995 20996 20997 20998 20999 21000 21001 21002 21003 21004 21005 21006 21007 21008 21009 21010 21011 21012 21013 21014 21015 21016 21017 21018 21019 21020 21021 21022 21023 21024 21025 21026 21027 21028 21029 21030 21031 21032 21033 21034 21035 21036 21037 21038 21039 21040 21041 21042 21043 21044 21045 21046 21047 21048 21049 21050 21051 21052 21053 21054 21055 21056 21057 21058 21059 21060 21061 21062 21063 21064 21065 21066 21067 21068 21069 21070 21071 21072 21073 21074 21075 21076 21077 21078 21079 21080 21081 21082 21083 21084 21085 21086 21087 21088 21089 21090 21091 21092 21093 21094 21095 21096 21097 21098 21099 21100 21101 21102 21103 21104 21105 21106 21107 21108 21109 21110 21111 21112 21113 21114 21115 21116 21117 21118 21119 21120 21121 21122 21123 21124 21125 21126 21127 21128 21129 21130 21131 21132 21133 21134 21135 21136 21137 21138 21139 21140 21141 21142 21143 21144 21145 21146 21147 21148 21149 21150 21151 21152 21153 21154 21155 21156 21157 21158 21159 21160 21161 21162 21163 21164 21165 21166 21167 21168 21169 21170 21171 21172 21173 21174 21175 21176 21177 21178 21179 21180 21181 21182 21183 21184 21185 21186 21187 21188 21189 21190 21191 21192 21193 21194 21195 21196 21197 21198 21199 21200 21201 21202 21203 21204 21205 21206 21207 21208 21209 21210 21211 21212 21213 21214 21215 21216 21217 21218 21219 21220 21221 21222 21223 21224 21225 21226 21227 21228 21229 21230 21231 21232 21233 21234 21235 21236 21237 21238 21239 21240 21241 21242 21243 21244 21245 21246 21247 21248 21249 21250 21251 21252 21253 21254 21255 21256 21257 21258 21259 21260 21261 21262 21263 21264 21265 21266 21267 21268 21269 21270 21271 21272 21273 21274 21275 21276 21277 21278 21279 21280 21281 21282 21283 21284 21285 21286 21287 21288 21289 21290 21291 21292 21293 21294 21295 21296 21297 21298 21299 21300 21301 21302 21303 21304 21305 21306 21307 21308 21309 21310 21311 21312 21313 21314 21315 21316 21317 21318 21319 21320 21321 21322 21323 21324 21325 21326 21327 21328 21329 21330 21331 21332 21333 21334 21335 21336 21337 21338 21339 21340 21341 21342 21343 21344 21345 21346 21347 21348 21349 21350 21351 21352 21353 21354 21355 21356 21357 21358 21359 21360 21361 21362 21363 21364 21365 21366 21367 21368 21369 21370 21371 21372 21373 21374 21375 21376 21377 21378 21379 21380 21381 21382 21383 21384 21385 21386 21387 21388 21389 21390 21391 21392 21393 21394 21395 21396 21397 21398 21399 21400 21401 21402 21403 21404 21405 21406 21407 21408 21409 21410 21411 21412 21413 21414 21415 21416 21417 21418 21419 21420 21421 21422 21423 21424 21425 21426 21427 21428 21429 21430 21431 21432 21433 21434 21435 21436 21437 21438 21439 21440 21441 21442 21443 21444 21445 21446 21447 21448 21449 21450 21451 21452 21453 21454 21455 21456 21457 21458 21459 21460 21461 21462 21463 21464 21465 21466 21467 21468 21469 21470 21471 21472 21473 21474 21475 21476 21477 21478 21479 21480 21481 21482 21483 21484 21485 21486 21487 21488 21489 21490 21491 21492 21493 21494 21495 21496 21497 21498 21499 21500 21501 21502 21503 21504 21505 21506 21507 21508 21509 21510 21511 21512 21513 21514 21515 21516 21517 21518 21519 21520 21521 21522 21523 21524 21525 21526 21527 21528 21529 21530 21531 21532 21533 21534 21535 21536 21537 21538 21539 21540 21541 21542 21543 21544 21545 21546 21547 21548 21549 21550 21551 21552 21553 21554 21555 21556 21557 21558 21559 21560 21561 21562 21563 21564 21565 21566 21567 21568 21569 21570 21571 21572 21573 21574 21575 21576 21577 21578 21579 21580 21581 21582 21583 21584 21585 21586 21587 21588 21589 21590 21591 21592 21593 21594 21595 21596 21597 21598 21599 21600 21601 21602 21603 21604 21605 21606 21607 21608 21609 21610 21611 21612 21613 21614 21615 21616 21617 21618 21619 21620 21621 21622 21623 21624 21625 21626 21627 21628 21629 21630 21631 21632 21633 21634 21635 21636 21637 21638 21639 21640 21641 21642 21643 21644 21645 21646 21647 21648 21649 21650 21651 21652 21653 21654 21655 21656 21657 21658 21659 21660 21661 21662 21663 21664 21665 21666 21667 21668 21669 21670 21671 21672 21673 21674 21675 21676 21677 21678 21679 21680 21681 21682 21683 21684 21685 21686 21687 21688 21689 21690 21691 21692 21693 21694 21695 21696 21697 21698 21699 21700 21701 21702 21703 21704 21705 21706 21707 21708 21709 21710 21711 21712 21713 21714 21715 21716 21717 21718 21719 21720 21721 21722 21723 21724 21725 21726 21727 21728 21729 21730 21731 21732 21733 21734 21735 21736 21737 21738 21739 21740 21741 21742 21743 21744 21745 21746 21747 21748 21749 21750 21751 21752 21753 21754 21755 21756 21757 21758 21759 21760 21761 21762 21763 21764 21765 21766 21767 21768 21769 21770 21771 21772 21773 21774 21775 21776 21777 21778 21779 21780 21781 21782 21783 21784 21785 21786 21787 21788 21789 21790 21791 21792 21793 21794 21795 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io */ #include <uapi/linux/btf.h> #include <linux/bpf-cgroup.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/bpf_verifier.h> #include <linux/filter.h> #include <net/netlink.h> #include <linux/file.h> #include <linux/vmalloc.h> #include <linux/stringify.h> #include <linux/bsearch.h> #include <linux/sort.h> #include <linux/perf_event.h> #include <linux/ctype.h> #include <linux/error-injection.h> #include <linux/bpf_lsm.h> #include <linux/btf_ids.h> #include <linux/poison.h> #include <linux/module.h> #include <linux/cpumask.h> #include <linux/bpf_mem_alloc.h> #include <net/xdp.h> #include "disasm.h" static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = & _name ## _verifier_ops, #define BPF_MAP_TYPE(_id, _ops) #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE }; struct bpf_mem_alloc bpf_global_percpu_ma; static bool bpf_global_percpu_ma_set; /* bpf_check() is a static code analyzer that walks eBPF program * instruction by instruction and updates register/stack state. * All paths of conditional branches are analyzed until 'bpf_exit' insn. * * The first pass is depth-first-search to check that the program is a DAG. * It rejects the following programs: * - larger than BPF_MAXINSNS insns * - if loop is present (detected via back-edge) * - unreachable insns exist (shouldn't be a forest. program = one function) * - out of bounds or malformed jumps * The second pass is all possible path descent from the 1st insn. * Since it's analyzing all paths through the program, the length of the * analysis is limited to 64k insn, which may be hit even if total number of * insn is less then 4K, but there are too many branches that change stack/regs. * Number of 'branches to be analyzed' is limited to 1k * * On entry to each instruction, each register has a type, and the instruction * changes the types of the registers depending on instruction semantics. * If instruction is BPF_MOV64_REG(BPF_REG_1, BPF_REG_5), then type of R5 is * copied to R1. * * All registers are 64-bit. * R0 - return register * R1-R5 argument passing registers * R6-R9 callee saved registers * R10 - frame pointer read-only * * At the start of BPF program the register R1 contains a pointer to bpf_context * and has type PTR_TO_CTX. * * Verifier tracks arithmetic operations on pointers in case: * BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), * BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -20), * 1st insn copies R10 (which has FRAME_PTR) type into R1 * and 2nd arithmetic instruction is pattern matched to recognize * that it wants to construct a pointer to some element within stack. * So after 2nd insn, the register R1 has type PTR_TO_STACK * (and -20 constant is saved for further stack bounds checking). * Meaning that this reg is a pointer to stack plus known immediate constant. * * Most of the time the registers have SCALAR_VALUE type, which * means the register has some value, but it's not a valid pointer. * (like pointer plus pointer becomes SCALAR_VALUE type) * * When verifier sees load or store instructions the type of base register * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK, PTR_TO_SOCKET. These are * four pointer types recognized by check_mem_access() function. * * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value' * and the range of [ptr, ptr + map's value_size) is accessible. * * registers used to pass values to function calls are checked against * function argument constraints. * * ARG_PTR_TO_MAP_KEY is one of such argument constraints. * It means that the register type passed to this function must be * PTR_TO_STACK and it will be used inside the function as * 'pointer to map element key' * * For example the argument constraints for bpf_map_lookup_elem(): * .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, * .arg1_type = ARG_CONST_MAP_PTR, * .arg2_type = ARG_PTR_TO_MAP_KEY, * * ret_type says that this function returns 'pointer to map elem value or null' * function expects 1st argument to be a const pointer to 'struct bpf_map' and * 2nd argument should be a pointer to stack, which will be used inside * the helper function as a pointer to map element key. * * On the kernel side the helper function looks like: * u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) * { * struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; * void *key = (void *) (unsigned long) r2; * void *value; * * here kernel can access 'key' and 'map' pointers safely, knowing that * [key, key + map->key_size) bytes are valid and were initialized on * the stack of eBPF program. * } * * Corresponding eBPF program may look like: * BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), // after this insn R2 type is FRAME_PTR * BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), // after this insn R2 type is PTR_TO_STACK * BPF_LD_MAP_FD(BPF_REG_1, map_fd), // after this insn R1 type is CONST_PTR_TO_MAP * BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), * here verifier looks at prototype of map_lookup_elem() and sees: * .arg1_type == ARG_CONST_MAP_PTR and R1->type == CONST_PTR_TO_MAP, which is ok, * Now verifier knows that this map has key of R1->map_ptr->key_size bytes * * Then .arg2_type == ARG_PTR_TO_MAP_KEY and R2->type == PTR_TO_STACK, ok so far, * Now verifier checks that [R2, R2 + map's key_size) are within stack limits * and were initialized prior to this call. * If it's ok, then verifier allows this BPF_CALL insn and looks at * .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets * R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function * returns either pointer to map value or NULL. * * When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off' * insn, the register holding that pointer in the true branch changes state to * PTR_TO_MAP_VALUE and the same register changes state to CONST_IMM in the false * branch. See check_cond_jmp_op(). * * After the call R0 is set to return type of the function and registers R1-R5 * are set to NOT_INIT to indicate that they are no longer readable. * * The following reference types represent a potential reference to a kernel * resource which, after first being allocated, must be checked and freed by * the BPF program: * - PTR_TO_SOCKET_OR_NULL, PTR_TO_SOCKET * * When the verifier sees a helper call return a reference type, it allocates a * pointer id for the reference and stores it in the current function state. * Similar to the way that PTR_TO_MAP_VALUE_OR_NULL is converted into * PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL becomes PTR_TO_SOCKET when the type * passes through a NULL-check conditional. For the branch wherein the state is * changed to CONST_IMM, the verifier releases the reference. * * For each helper function that allocates a reference, such as * bpf_sk_lookup_tcp(), there is a corresponding release function, such as * bpf_sk_release(). When a reference type passes into the release function, * the verifier also releases the reference. If any unchecked or unreleased * reference remains at the end of the program, the verifier rejects it. */ /* verifier_state + insn_idx are pushed to stack when branch is encountered */ struct bpf_verifier_stack_elem { /* verifier state is 'st' * before processing instruction 'insn_idx' * and after processing instruction 'prev_insn_idx' */ struct bpf_verifier_state st; int insn_idx; int prev_insn_idx; struct bpf_verifier_stack_elem *next; /* length of verifier log at the time this state was pushed on stack */ u32 log_pos; }; #define BPF_COMPLEXITY_LIMIT_JMP_SEQ 8192 #define BPF_COMPLEXITY_LIMIT_STATES 64 #define BPF_MAP_KEY_POISON (1ULL << 63) #define BPF_MAP_KEY_SEEN (1ULL << 62) #define BPF_GLOBAL_PERCPU_MA_MAX_SIZE 512 static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx); static int release_reference(struct bpf_verifier_env *env, int ref_obj_id); static void invalidate_non_owning_refs(struct bpf_verifier_env *env); static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env); static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state *reg); static void specialize_kfunc(struct bpf_verifier_env *env, u32 func_id, u16 offset, unsigned long *addr); static bool is_trusted_reg(const struct bpf_reg_state *reg); static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux) { return aux->map_ptr_state.poison; } static bool bpf_map_ptr_unpriv(const struct bpf_insn_aux_data *aux) { return aux->map_ptr_state.unpriv; } static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux, struct bpf_map *map, bool unpriv, bool poison) { unpriv |= bpf_map_ptr_unpriv(aux); aux->map_ptr_state.unpriv = unpriv; aux->map_ptr_state.poison = poison; aux->map_ptr_state.map_ptr = map; } static bool bpf_map_key_poisoned(const struct bpf_insn_aux_data *aux) { return aux->map_key_state & BPF_MAP_KEY_POISON; } static bool bpf_map_key_unseen(const struct bpf_insn_aux_data *aux) { return !(aux->map_key_state & BPF_MAP_KEY_SEEN); } static u64 bpf_map_key_immediate(const struct bpf_insn_aux_data *aux) { return aux->map_key_state & ~(BPF_MAP_KEY_SEEN | BPF_MAP_KEY_POISON); } static void bpf_map_key_store(struct bpf_insn_aux_data *aux, u64 state) { bool poisoned = bpf_map_key_poisoned(aux); aux->map_key_state = state | BPF_MAP_KEY_SEEN | (poisoned ? BPF_MAP_KEY_POISON : 0ULL); } static bool bpf_helper_call(const struct bpf_insn *insn) { return insn->code == (BPF_JMP | BPF_CALL) && insn->src_reg == 0; } static bool bpf_pseudo_call(const struct bpf_insn *insn) { return insn->code == (BPF_JMP | BPF_CALL) && insn->src_reg == BPF_PSEUDO_CALL; } static bool bpf_pseudo_kfunc_call(const struct bpf_insn *insn) { return insn->code == (BPF_JMP | BPF_CALL) && insn->src_reg == BPF_PSEUDO_KFUNC_CALL; } struct bpf_call_arg_meta { struct bpf_map *map_ptr; bool raw_mode; bool pkt_access; u8 release_regno; int regno; int access_size; int mem_size; u64 msize_max_value; int ref_obj_id; int dynptr_id; int map_uid; int func_id; struct btf *btf; u32 btf_id; struct btf *ret_btf; u32 ret_btf_id; u32 subprogno; struct btf_field *kptr_field; }; struct bpf_kfunc_call_arg_meta { /* In parameters */ struct btf *btf; u32 func_id; u32 kfunc_flags; const struct btf_type *func_proto; const char *func_name; /* Out parameters */ u32 ref_obj_id; u8 release_regno; bool r0_rdonly; u32 ret_btf_id; u64 r0_size; u32 subprogno; struct { u64 value; bool found; } arg_constant; /* arg_{btf,btf_id,owning_ref} are used by kfunc-specific handling, * generally to pass info about user-defined local kptr types to later * verification logic * bpf_obj_drop/bpf_percpu_obj_drop * Record the local kptr type to be drop'd * bpf_refcount_acquire (via KF_ARG_PTR_TO_REFCOUNTED_KPTR arg type) * Record the local kptr type to be refcount_incr'd and use * arg_owning_ref to determine whether refcount_acquire should be * fallible */ struct btf *arg_btf; u32 arg_btf_id; bool arg_owning_ref; struct { struct btf_field *field; } arg_list_head; struct { struct btf_field *field; } arg_rbtree_root; struct { enum bpf_dynptr_type type; u32 id; u32 ref_obj_id; } initialized_dynptr; struct { u8 spi; u8 frameno; } iter; struct { struct bpf_map *ptr; int uid; } map; u64 mem_size; }; struct btf *btf_vmlinux; static const char *btf_type_name(const struct btf *btf, u32 id) { return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); } static DEFINE_MUTEX(bpf_verifier_lock); static DEFINE_MUTEX(bpf_percpu_ma_lock); __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) { struct bpf_verifier_env *env = private_data; va_list args; if (!bpf_verifier_log_needed(&env->log)) return; va_start(args, fmt); bpf_verifier_vlog(&env->log, fmt, args); va_end(args); } static void verbose_invalid_scalar(struct bpf_verifier_env *env, struct bpf_reg_state *reg, struct bpf_retval_range range, const char *ctx, const char *reg_name) { bool unknown = true; verbose(env, "%s the register %s has", ctx, reg_name); if (reg->smin_value > S64_MIN) { verbose(env, " smin=%lld", reg->smin_value); unknown = false; } if (reg->smax_value < S64_MAX) { verbose(env, " smax=%lld", reg->smax_value); unknown = false; } if (unknown) verbose(env, " unknown scalar value"); verbose(env, " should have been in [%d, %d]\n", range.minval, range.maxval); } static bool type_may_be_null(u32 type) { return type & PTR_MAYBE_NULL; } static bool reg_not_null(const struct bpf_reg_state *reg) { enum bpf_reg_type type; type = reg->type; if (type_may_be_null(type)) return false; type = base_type(type); return type == PTR_TO_SOCKET || type == PTR_TO_TCP_SOCK || type == PTR_TO_MAP_VALUE || type == PTR_TO_MAP_KEY || type == PTR_TO_SOCK_COMMON || (type == PTR_TO_BTF_ID && is_trusted_reg(reg)) || type == PTR_TO_MEM; } static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg) { struct btf_record *rec = NULL; struct btf_struct_meta *meta; if (reg->type == PTR_TO_MAP_VALUE) { rec = reg->map_ptr->record; } else if (type_is_ptr_alloc_obj(reg->type)) { meta = btf_find_struct_meta(reg->btf, reg->btf_id); if (meta) rec = meta->record; } return rec; } static bool subprog_is_global(const struct bpf_verifier_env *env, int subprog) { struct bpf_func_info_aux *aux = env->prog->aux->func_info_aux; return aux && aux[subprog].linkage == BTF_FUNC_GLOBAL; } static const char *subprog_name(const struct bpf_verifier_env *env, int subprog) { struct bpf_func_info *info; if (!env->prog->aux->func_info) return ""; info = &env->prog->aux->func_info[subprog]; return btf_type_name(env->prog->aux->btf, info->type_id); } static void mark_subprog_exc_cb(struct bpf_verifier_env *env, int subprog) { struct bpf_subprog_info *info = subprog_info(env, subprog); info->is_cb = true; info->is_async_cb = true; info->is_exception_cb = true; } static bool subprog_is_exc_cb(struct bpf_verifier_env *env, int subprog) { return subprog_info(env, subprog)->is_exception_cb; } static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK); } static bool type_is_rdonly_mem(u32 type) { return type & MEM_RDONLY; } static bool is_acquire_function(enum bpf_func_id func_id, const struct bpf_map *map) { enum bpf_map_type map_type = map ? map->map_type : BPF_MAP_TYPE_UNSPEC; if (func_id == BPF_FUNC_sk_lookup_tcp || func_id == BPF_FUNC_sk_lookup_udp || func_id == BPF_FUNC_skc_lookup_tcp || func_id == BPF_FUNC_ringbuf_reserve || func_id == BPF_FUNC_kptr_xchg) return true; if (func_id == BPF_FUNC_map_lookup_elem && (map_type == BPF_MAP_TYPE_SOCKMAP || map_type == BPF_MAP_TYPE_SOCKHASH)) return true; return false; } static bool is_ptr_cast_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_tcp_sock || func_id == BPF_FUNC_sk_fullsock || func_id == BPF_FUNC_skc_to_tcp_sock || func_id == BPF_FUNC_skc_to_tcp6_sock || func_id == BPF_FUNC_skc_to_udp6_sock || func_id == BPF_FUNC_skc_to_mptcp_sock || func_id == BPF_FUNC_skc_to_tcp_timewait_sock || func_id == BPF_FUNC_skc_to_tcp_request_sock; } static bool is_dynptr_ref_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_dynptr_data; } static bool is_sync_callback_calling_kfunc(u32 btf_id); static bool is_async_callback_calling_kfunc(u32 btf_id); static bool is_callback_calling_kfunc(u32 btf_id); static bool is_bpf_throw_kfunc(struct bpf_insn *insn); static bool is_bpf_wq_set_callback_impl_kfunc(u32 btf_id); static bool is_sync_callback_calling_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_for_each_map_elem || func_id == BPF_FUNC_find_vma || func_id == BPF_FUNC_loop || func_id == BPF_FUNC_user_ringbuf_drain; } static bool is_async_callback_calling_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_timer_set_callback; } static bool is_callback_calling_function(enum bpf_func_id func_id) { return is_sync_callback_calling_function(func_id) || is_async_callback_calling_function(func_id); } static bool is_sync_callback_calling_insn(struct bpf_insn *insn) { return (bpf_helper_call(insn) && is_sync_callback_calling_function(insn->imm)) || (bpf_pseudo_kfunc_call(insn) && is_sync_callback_calling_kfunc(insn->imm)); } static bool is_async_callback_calling_insn(struct bpf_insn *insn) { return (bpf_helper_call(insn) && is_async_callback_calling_function(insn->imm)) || (bpf_pseudo_kfunc_call(insn) && is_async_callback_calling_kfunc(insn->imm)); } static bool is_may_goto_insn(struct bpf_insn *insn) { return insn->code == (BPF_JMP | BPF_JCOND) && insn->src_reg == BPF_MAY_GOTO; } static bool is_may_goto_insn_at(struct bpf_verifier_env *env, int insn_idx) { return is_may_goto_insn(&env->prog->insnsi[insn_idx]); } static bool is_storage_get_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_sk_storage_get || func_id == BPF_FUNC_inode_storage_get || func_id == BPF_FUNC_task_storage_get || func_id == BPF_FUNC_cgrp_storage_get; } static bool helper_multiple_ref_obj_use(enum bpf_func_id func_id, const struct bpf_map *map) { int ref_obj_uses = 0; if (is_ptr_cast_function(func_id)) ref_obj_uses++; if (is_acquire_function(func_id, map)) ref_obj_uses++; if (is_dynptr_ref_function(func_id)) ref_obj_uses++; return ref_obj_uses > 1; } static bool is_cmpxchg_insn(const struct bpf_insn *insn) { return BPF_CLASS(insn->code) == BPF_STX && BPF_MODE(insn->code) == BPF_ATOMIC && insn->imm == BPF_CMPXCHG; } static int __get_spi(s32 off) { return (-off - 1) / BPF_REG_SIZE; } static struct bpf_func_state *func(struct bpf_verifier_env *env, const struct bpf_reg_state *reg) { struct bpf_verifier_state *cur = env->cur_state; return cur->frame[reg->frameno]; } static bool is_spi_bounds_valid(struct bpf_func_state *state, int spi, int nr_slots) { int allocated_slots = state->allocated_stack / BPF_REG_SIZE; /* We need to check that slots between [spi - nr_slots + 1, spi] are * within [0, allocated_stack). * * Please note that the spi grows downwards. For example, a dynptr * takes the size of two stack slots; the first slot will be at * spi and the second slot will be at spi - 1. */ return spi - nr_slots + 1 >= 0 && spi < allocated_slots; } static int stack_slot_obj_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg, const char *obj_kind, int nr_slots) { int off, spi; if (!tnum_is_const(reg->var_off)) { verbose(env, "%s has to be at a constant offset\n", obj_kind); return -EINVAL; } off = reg->off + reg->var_off.value; if (off % BPF_REG_SIZE) { verbose(env, "cannot pass in %s at an offset=%d\n", obj_kind, off); return -EINVAL; } spi = __get_spi(off); if (spi + 1 < nr_slots) { verbose(env, "cannot pass in %s at an offset=%d\n", obj_kind, off); return -EINVAL; } if (!is_spi_bounds_valid(func(env, reg), spi, nr_slots)) return -ERANGE; return spi; } static int dynptr_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { return stack_slot_obj_get_spi(env, reg, "dynptr", BPF_DYNPTR_NR_SLOTS); } static int iter_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int nr_slots) { return stack_slot_obj_get_spi(env, reg, "iter", nr_slots); } static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type) { switch (arg_type & DYNPTR_TYPE_FLAG_MASK) { case DYNPTR_TYPE_LOCAL: return BPF_DYNPTR_TYPE_LOCAL; case DYNPTR_TYPE_RINGBUF: return BPF_DYNPTR_TYPE_RINGBUF; case DYNPTR_TYPE_SKB: return BPF_DYNPTR_TYPE_SKB; case DYNPTR_TYPE_XDP: return BPF_DYNPTR_TYPE_XDP; default: return BPF_DYNPTR_TYPE_INVALID; } } static enum bpf_type_flag get_dynptr_type_flag(enum bpf_dynptr_type type) { switch (type) { case BPF_DYNPTR_TYPE_LOCAL: return DYNPTR_TYPE_LOCAL; case BPF_DYNPTR_TYPE_RINGBUF: return DYNPTR_TYPE_RINGBUF; case BPF_DYNPTR_TYPE_SKB: return DYNPTR_TYPE_SKB; case BPF_DYNPTR_TYPE_XDP: return DYNPTR_TYPE_XDP; default: return 0; } } static bool dynptr_type_refcounted(enum bpf_dynptr_type type) { return type == BPF_DYNPTR_TYPE_RINGBUF; } static void __mark_dynptr_reg(struct bpf_reg_state *reg, enum bpf_dynptr_type type, bool first_slot, int dynptr_id); static void __mark_reg_not_init(const struct bpf_verifier_env *env, struct bpf_reg_state *reg); static void mark_dynptr_stack_regs(struct bpf_verifier_env *env, struct bpf_reg_state *sreg1, struct bpf_reg_state *sreg2, enum bpf_dynptr_type type) { int id = ++env->id_gen; __mark_dynptr_reg(sreg1, type, true, id); __mark_dynptr_reg(sreg2, type, false, id); } static void mark_dynptr_cb_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, enum bpf_dynptr_type type) { __mark_dynptr_reg(reg, type, true, ++env->id_gen); } static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env, struct bpf_func_state *state, int spi); static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg, enum bpf_arg_type arg_type, int insn_idx, int clone_ref_obj_id) { struct bpf_func_state *state = func(env, reg); enum bpf_dynptr_type type; int spi, i, err; spi = dynptr_get_spi(env, reg); if (spi < 0) return spi; /* We cannot assume both spi and spi - 1 belong to the same dynptr, * hence we need to call destroy_if_dynptr_stack_slot twice for both, * to ensure that for the following example: * [d1][d1][d2][d2] * spi 3 2 1 0 * So marking spi = 2 should lead to destruction of both d1 and d2. In * case they do belong to same dynptr, second call won't see slot_type * as STACK_DYNPTR and will simply skip destruction. */ err = destroy_if_dynptr_stack_slot(env, state, spi); if (err) return err; err = destroy_if_dynptr_stack_slot(env, state, spi - 1); if (err) return err; for (i = 0; i < BPF_REG_SIZE; i++) { state->stack[spi].slot_type[i] = STACK_DYNPTR; state->stack[spi - 1].slot_type[i] = STACK_DYNPTR; } type = arg_to_dynptr_type(arg_type); if (type == BPF_DYNPTR_TYPE_INVALID) return -EINVAL; mark_dynptr_stack_regs(env, &state->stack[spi].spilled_ptr, &state->stack[spi - 1].spilled_ptr, type); if (dynptr_type_refcounted(type)) { /* The id is used to track proper releasing */ int id; if (clone_ref_obj_id) id = clone_ref_obj_id; else id = acquire_reference_state(env, insn_idx); if (id < 0) return id; state->stack[spi].spilled_ptr.ref_obj_id = id; state->stack[spi - 1].spilled_ptr.ref_obj_id = id; } state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; state->stack[spi - 1].spilled_ptr.live |= REG_LIVE_WRITTEN; return 0; } static void invalidate_dynptr(struct bpf_verifier_env *env, struct bpf_func_state *state, int spi) { int i; for (i = 0; i < BPF_REG_SIZE; i++) { state->stack[spi].slot_type[i] = STACK_INVALID; state->stack[spi - 1].slot_type[i] = STACK_INVALID; } __mark_reg_not_init(env, &state->stack[spi].spilled_ptr); __mark_reg_not_init(env, &state->stack[spi - 1].spilled_ptr); /* Why do we need to set REG_LIVE_WRITTEN for STACK_INVALID slot? * * While we don't allow reading STACK_INVALID, it is still possible to * do <8 byte writes marking some but not all slots as STACK_MISC. Then, * helpers or insns can do partial read of that part without failing, * but check_stack_range_initialized, check_stack_read_var_off, and * check_stack_read_fixed_off will do mark_reg_read for all 8-bytes of * the slot conservatively. Hence we need to prevent those liveness * marking walks. * * This was not a problem before because STACK_INVALID is only set by * default (where the default reg state has its reg->parent as NULL), or * in clean_live_states after REG_LIVE_DONE (at which point * mark_reg_read won't walk reg->parent chain), but not randomly during * verifier state exploration (like we did above). Hence, for our case * parentage chain will still be live (i.e. reg->parent may be * non-NULL), while earlier reg->parent was NULL, so we need * REG_LIVE_WRITTEN to screen off read marker propagation when it is * done later on reads or by mark_dynptr_read as well to unnecessary * mark registers in verifier state. */ state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; state->stack[spi - 1].spilled_ptr.live |= REG_LIVE_WRITTEN; } static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); int spi, ref_obj_id, i; spi = dynptr_get_spi(env, reg); if (spi < 0) return spi; if (!dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) { invalidate_dynptr(env, state, spi); return 0; } ref_obj_id = state->stack[spi].spilled_ptr.ref_obj_id; /* If the dynptr has a ref_obj_id, then we need to invalidate * two things: * * 1) Any dynptrs with a matching ref_obj_id (clones) * 2) Any slices derived from this dynptr. */ /* Invalidate any slices associated with this dynptr */ WARN_ON_ONCE(release_reference(env, ref_obj_id)); /* Invalidate any dynptr clones */ for (i = 1; i < state->allocated_stack / BPF_REG_SIZE; i++) { if (state->stack[i].spilled_ptr.ref_obj_id != ref_obj_id) continue; /* it should always be the case that if the ref obj id * matches then the stack slot also belongs to a * dynptr */ if (state->stack[i].slot_type[0] != STACK_DYNPTR) { verbose(env, "verifier internal error: misconfigured ref_obj_id\n"); return -EFAULT; } if (state->stack[i].spilled_ptr.dynptr.first_slot) invalidate_dynptr(env, state, i); } return 0; } static void __mark_reg_unknown(const struct bpf_verifier_env *env, struct bpf_reg_state *reg); static void mark_reg_invalid(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { if (!env->allow_ptr_leaks) __mark_reg_not_init(env, reg); else __mark_reg_unknown(env, reg); } static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env, struct bpf_func_state *state, int spi) { struct bpf_func_state *fstate; struct bpf_reg_state *dreg; int i, dynptr_id; /* We always ensure that STACK_DYNPTR is never set partially, * hence just checking for slot_type[0] is enough. This is * different for STACK_SPILL, where it may be only set for * 1 byte, so code has to use is_spilled_reg. */ if (state->stack[spi].slot_type[0] != STACK_DYNPTR) return 0; /* Reposition spi to first slot */ if (!state->stack[spi].spilled_ptr.dynptr.first_slot) spi = spi + 1; if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) { verbose(env, "cannot overwrite referenced dynptr\n"); return -EINVAL; } mark_stack_slot_scratched(env, spi); mark_stack_slot_scratched(env, spi - 1); /* Writing partially to one dynptr stack slot destroys both. */ for (i = 0; i < BPF_REG_SIZE; i++) { state->stack[spi].slot_type[i] = STACK_INVALID; state->stack[spi - 1].slot_type[i] = STACK_INVALID; } dynptr_id = state->stack[spi].spilled_ptr.id; /* Invalidate any slices associated with this dynptr */ bpf_for_each_reg_in_vstate(env->cur_state, fstate, dreg, ({ /* Dynptr slices are only PTR_TO_MEM_OR_NULL and PTR_TO_MEM */ if (dreg->type != (PTR_TO_MEM | PTR_MAYBE_NULL) && dreg->type != PTR_TO_MEM) continue; if (dreg->dynptr_id == dynptr_id) mark_reg_invalid(env, dreg); })); /* Do not release reference state, we are destroying dynptr on stack, * not using some helper to release it. Just reset register. */ __mark_reg_not_init(env, &state->stack[spi].spilled_ptr); __mark_reg_not_init(env, &state->stack[spi - 1].spilled_ptr); /* Same reason as unmark_stack_slots_dynptr above */ state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; state->stack[spi - 1].spilled_ptr.live |= REG_LIVE_WRITTEN; return 0; } static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { int spi; if (reg->type == CONST_PTR_TO_DYNPTR) return false; spi = dynptr_get_spi(env, reg); /* -ERANGE (i.e. spi not falling into allocated stack slots) isn't an * error because this just means the stack state hasn't been updated yet. * We will do check_mem_access to check and update stack bounds later. */ if (spi < 0 && spi != -ERANGE) return false; /* We don't need to check if the stack slots are marked by previous * dynptr initializations because we allow overwriting existing unreferenced * STACK_DYNPTR slots, see mark_stack_slots_dynptr which calls * destroy_if_dynptr_stack_slot to ensure dynptr objects at the slots we are * touching are completely destructed before we reinitialize them for a new * one. For referenced ones, destroy_if_dynptr_stack_slot returns an error early * instead of delaying it until the end where the user will get "Unreleased * reference" error. */ return true; } static bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); int i, spi; /* This already represents first slot of initialized bpf_dynptr. * * CONST_PTR_TO_DYNPTR already has fixed and var_off as 0 due to * check_func_arg_reg_off's logic, so we don't need to check its * offset and alignment. */ if (reg->type == CONST_PTR_TO_DYNPTR) return true; spi = dynptr_get_spi(env, reg); if (spi < 0) return false; if (!state->stack[spi].spilled_ptr.dynptr.first_slot) return false; for (i = 0; i < BPF_REG_SIZE; i++) { if (state->stack[spi].slot_type[i] != STACK_DYNPTR || state->stack[spi - 1].slot_type[i] != STACK_DYNPTR) return false; } return true; } static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg_state *reg, enum bpf_arg_type arg_type) { struct bpf_func_state *state = func(env, reg); enum bpf_dynptr_type dynptr_type; int spi; /* ARG_PTR_TO_DYNPTR takes any type of dynptr */ if (arg_type == ARG_PTR_TO_DYNPTR) return true; dynptr_type = arg_to_dynptr_type(arg_type); if (reg->type == CONST_PTR_TO_DYNPTR) { return reg->dynptr.type == dynptr_type; } else { spi = dynptr_get_spi(env, reg); if (spi < 0) return false; return state->stack[spi].spilled_ptr.dynptr.type == dynptr_type; } } static void __mark_reg_known_zero(struct bpf_reg_state *reg); static bool in_rcu_cs(struct bpf_verifier_env *env); static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta); static int mark_stack_slots_iter(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta, struct bpf_reg_state *reg, int insn_idx, struct btf *btf, u32 btf_id, int nr_slots) { struct bpf_func_state *state = func(env, reg); int spi, i, j, id; spi = iter_get_spi(env, reg, nr_slots); if (spi < 0) return spi; id = acquire_reference_state(env, insn_idx); if (id < 0) return id; for (i = 0; i < nr_slots; i++) { struct bpf_stack_state *slot = &state->stack[spi - i]; struct bpf_reg_state *st = &slot->spilled_ptr; __mark_reg_known_zero(st); st->type = PTR_TO_STACK; /* we don't have dedicated reg type */ if (is_kfunc_rcu_protected(meta)) { if (in_rcu_cs(env)) st->type |= MEM_RCU; else st->type |= PTR_UNTRUSTED; } st->live |= REG_LIVE_WRITTEN; st->ref_obj_id = i == 0 ? id : 0; st->iter.btf = btf; st->iter.btf_id = btf_id; st->iter.state = BPF_ITER_STATE_ACTIVE; st->iter.depth = 0; for (j = 0; j < BPF_REG_SIZE; j++) slot->slot_type[j] = STACK_ITER; mark_stack_slot_scratched(env, spi - i); } return 0; } static int unmark_stack_slots_iter(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int nr_slots) { struct bpf_func_state *state = func(env, reg); int spi, i, j; spi = iter_get_spi(env, reg, nr_slots); if (spi < 0) return spi; for (i = 0; i < nr_slots; i++) { struct bpf_stack_state *slot = &state->stack[spi - i]; struct bpf_reg_state *st = &slot->spilled_ptr; if (i == 0) WARN_ON_ONCE(release_reference(env, st->ref_obj_id)); __mark_reg_not_init(env, st); /* see unmark_stack_slots_dynptr() for why we need to set REG_LIVE_WRITTEN */ st->live |= REG_LIVE_WRITTEN; for (j = 0; j < BPF_REG_SIZE; j++) slot->slot_type[j] = STACK_INVALID; mark_stack_slot_scratched(env, spi - i); } return 0; } static bool is_iter_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int nr_slots) { struct bpf_func_state *state = func(env, reg); int spi, i, j; /* For -ERANGE (i.e. spi not falling into allocated stack slots), we * will do check_mem_access to check and update stack bounds later, so * return true for that case. */ spi = iter_get_spi(env, reg, nr_slots); if (spi == -ERANGE) return true; if (spi < 0) return false; for (i = 0; i < nr_slots; i++) { struct bpf_stack_state *slot = &state->stack[spi - i]; for (j = 0; j < BPF_REG_SIZE; j++) if (slot->slot_type[j] == STACK_ITER) return false; } return true; } static int is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg, struct btf *btf, u32 btf_id, int nr_slots) { struct bpf_func_state *state = func(env, reg); int spi, i, j; spi = iter_get_spi(env, reg, nr_slots); if (spi < 0) return -EINVAL; for (i = 0; i < nr_slots; i++) { struct bpf_stack_state *slot = &state->stack[spi - i]; struct bpf_reg_state *st = &slot->spilled_ptr; if (st->type & PTR_UNTRUSTED) return -EPROTO; /* only main (first) slot has ref_obj_id set */ if (i == 0 && !st->ref_obj_id) return -EINVAL; if (i != 0 && st->ref_obj_id) return -EINVAL; if (st->iter.btf != btf || st->iter.btf_id != btf_id) return -EINVAL; for (j = 0; j < BPF_REG_SIZE; j++) if (slot->slot_type[j] != STACK_ITER) return -EINVAL; } return 0; } /* Check if given stack slot is "special": * - spilled register state (STACK_SPILL); * - dynptr state (STACK_DYNPTR); * - iter state (STACK_ITER). */ static bool is_stack_slot_special(const struct bpf_stack_state *stack) { enum bpf_stack_slot_type type = stack->slot_type[BPF_REG_SIZE - 1]; switch (type) { case STACK_SPILL: case STACK_DYNPTR: case STACK_ITER: return true; case STACK_INVALID: case STACK_MISC: case STACK_ZERO: return false; default: WARN_ONCE(1, "unknown stack slot type %d\n", type); return true; } } /* The reg state of a pointer or a bounded scalar was saved when * it was spilled to the stack. */ static bool is_spilled_reg(const struct bpf_stack_state *stack) { return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL; } static bool is_spilled_scalar_reg(const struct bpf_stack_state *stack) { return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL && stack->spilled_ptr.type == SCALAR_VALUE; } static bool is_spilled_scalar_reg64(const struct bpf_stack_state *stack) { return stack->slot_type[0] == STACK_SPILL && stack->spilled_ptr.type == SCALAR_VALUE; } /* Mark stack slot as STACK_MISC, unless it is already STACK_INVALID, in which * case they are equivalent, or it's STACK_ZERO, in which case we preserve * more precise STACK_ZERO. * Note, in uprivileged mode leaving STACK_INVALID is wrong, so we take * env->allow_ptr_leaks into account and force STACK_MISC, if necessary. */ static void mark_stack_slot_misc(struct bpf_verifier_env *env, u8 *stype) { if (*stype == STACK_ZERO) return; if (env->allow_ptr_leaks && *stype == STACK_INVALID) return; *stype = STACK_MISC; } static void scrub_spilled_slot(u8 *stype) { if (*stype != STACK_INVALID) *stype = STACK_MISC; } /* copy array src of length n * size bytes to dst. dst is reallocated if it's too * small to hold src. This is different from krealloc since we don't want to preserve * the contents of dst. * * Leaves dst untouched if src is NULL or length is zero. Returns NULL if memory could * not be allocated. */ static void *copy_array(void *dst, const void *src, size_t n, size_t size, gfp_t flags) { size_t alloc_bytes; void *orig = dst; size_t bytes; if (ZERO_OR_NULL_PTR(src)) goto out; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; alloc_bytes = max(ksize(orig), kmalloc_size_roundup(bytes)); dst = krealloc(orig, alloc_bytes, flags); if (!dst) { kfree(orig); return NULL; } memcpy(dst, src, bytes); out: return dst ? dst : ZERO_SIZE_PTR; } /* resize an array from old_n items to new_n items. the array is reallocated if it's too * small to hold new_n items. new items are zeroed out if the array grows. * * Contrary to krealloc_array, does not free arr if new_n is zero. */ static void *realloc_array(void *arr, size_t old_n, size_t new_n, size_t size) { size_t alloc_size; void *new_arr; if (!new_n || old_n == new_n) goto out; alloc_size = kmalloc_size_roundup(size_mul(new_n, size)); new_arr = krealloc(arr, alloc_size, GFP_KERNEL); if (!new_arr) { kfree(arr); return NULL; } arr = new_arr; if (new_n > old_n) memset(arr + old_n * size, 0, (new_n - old_n) * size); out: return arr ? arr : ZERO_SIZE_PTR; } static int copy_reference_state(struct bpf_func_state *dst, const struct bpf_func_state *src) { dst->refs = copy_array(dst->refs, src->refs, src->acquired_refs, sizeof(struct bpf_reference_state), GFP_KERNEL); if (!dst->refs) return -ENOMEM; dst->acquired_refs = src->acquired_refs; return 0; } static int copy_stack_state(struct bpf_func_state *dst, const struct bpf_func_state *src) { size_t n = src->allocated_stack / BPF_REG_SIZE; dst->stack = copy_array(dst->stack, src->stack, n, sizeof(struct bpf_stack_state), GFP_KERNEL); if (!dst->stack) return -ENOMEM; dst->allocated_stack = src->allocated_stack; return 0; } static int resize_reference_state(struct bpf_func_state *state, size_t n) { state->refs = realloc_array(state->refs, state->acquired_refs, n, sizeof(struct bpf_reference_state)); if (!state->refs) return -ENOMEM; state->acquired_refs = n; return 0; } /* Possibly update state->allocated_stack to be at least size bytes. Also * possibly update the function's high-water mark in its bpf_subprog_info. */ static int grow_stack_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int size) { size_t old_n = state->allocated_stack / BPF_REG_SIZE, n; /* The stack size is always a multiple of BPF_REG_SIZE. */ size = round_up(size, BPF_REG_SIZE); n = size / BPF_REG_SIZE; if (old_n >= n) return 0; state->stack = realloc_array(state->stack, old_n, n, sizeof(struct bpf_stack_state)); if (!state->stack) return -ENOMEM; state->allocated_stack = size; /* update known max for given subprogram */ if (env->subprog_info[state->subprogno].stack_depth < size) env->subprog_info[state->subprogno].stack_depth = size; return 0; } /* Acquire a pointer id from the env and update the state->refs to include * this new pointer reference. * On success, returns a valid pointer id to associate with the register * On failure, returns a negative errno. */ static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx) { struct bpf_func_state *state = cur_func(env); int new_ofs = state->acquired_refs; int id, err; err = resize_reference_state(state, state->acquired_refs + 1); if (err) return err; id = ++env->id_gen; state->refs[new_ofs].id = id; state->refs[new_ofs].insn_idx = insn_idx; state->refs[new_ofs].callback_ref = state->in_callback_fn ? state->frameno : 0; return id; } /* release function corresponding to acquire_reference_state(). Idempotent. */ static int release_reference_state(struct bpf_func_state *state, int ptr_id) { int i, last_idx; last_idx = state->acquired_refs - 1; for (i = 0; i < state->acquired_refs; i++) { if (state->refs[i].id == ptr_id) { /* Cannot release caller references in callbacks */ if (state->in_callback_fn && state->refs[i].callback_ref != state->frameno) return -EINVAL; if (last_idx && i != last_idx) memcpy(&state->refs[i], &state->refs[last_idx], sizeof(*state->refs)); memset(&state->refs[last_idx], 0, sizeof(*state->refs)); state->acquired_refs--; return 0; } } return -EINVAL; } static void free_func_state(struct bpf_func_state *state) { if (!state) return; kfree(state->refs); kfree(state->stack); kfree(state); } static void clear_jmp_history(struct bpf_verifier_state *state) { kfree(state->jmp_history); state->jmp_history = NULL; state->jmp_history_cnt = 0; } static void free_verifier_state(struct bpf_verifier_state *state, bool free_self) { int i; for (i = 0; i <= state->curframe; i++) { free_func_state(state->frame[i]); state->frame[i] = NULL; } clear_jmp_history(state); if (free_self) kfree(state); } /* copy verifier state from src to dst growing dst stack space * when necessary to accommodate larger src stack */ static int copy_func_state(struct bpf_func_state *dst, const struct bpf_func_state *src) { int err; memcpy(dst, src, offsetof(struct bpf_func_state, acquired_refs)); err = copy_reference_state(dst, src); if (err) return err; return copy_stack_state(dst, src); } static int copy_verifier_state(struct bpf_verifier_state *dst_state, const struct bpf_verifier_state *src) { struct bpf_func_state *dst; int i, err; dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history, src->jmp_history_cnt, sizeof(*dst_state->jmp_history), GFP_USER); if (!dst_state->jmp_history) return -ENOMEM; dst_state->jmp_history_cnt = src->jmp_history_cnt; /* if dst has more stack frames then src frame, free them, this is also * necessary in case of exceptional exits using bpf_throw. */ for (i = src->curframe + 1; i <= dst_state->curframe; i++) { free_func_state(dst_state->frame[i]); dst_state->frame[i] = NULL; } dst_state->speculative = src->speculative; dst_state->active_rcu_lock = src->active_rcu_lock; dst_state->active_preempt_lock = src->active_preempt_lock; dst_state->in_sleepable = src->in_sleepable; dst_state->curframe = src->curframe; dst_state->active_lock.ptr = src->active_lock.ptr; dst_state->active_lock.id = src->active_lock.id; dst_state->branches = src->branches; dst_state->parent = src->parent; dst_state->first_insn_idx = src->first_insn_idx; dst_state->last_insn_idx = src->last_insn_idx; dst_state->dfs_depth = src->dfs_depth; dst_state->callback_unroll_depth = src->callback_unroll_depth; dst_state->used_as_loop_entry = src->used_as_loop_entry; dst_state->may_goto_depth = src->may_goto_depth; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { dst = kzalloc(sizeof(*dst), GFP_KERNEL); if (!dst) return -ENOMEM; dst_state->frame[i] = dst; } err = copy_func_state(dst, src->frame[i]); if (err) return err; } return 0; } static u32 state_htab_size(struct bpf_verifier_env *env) { return env->prog->len; } static struct bpf_verifier_state_list **explored_state(struct bpf_verifier_env *env, int idx) { struct bpf_verifier_state *cur = env->cur_state; struct bpf_func_state *state = cur->frame[cur->curframe]; return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)]; } static bool same_callsites(struct bpf_verifier_state *a, struct bpf_verifier_state *b) { int fr; if (a->curframe != b->curframe) return false; for (fr = a->curframe; fr >= 0; fr--) if (a->frame[fr]->callsite != b->frame[fr]->callsite) return false; return true; } /* Open coded iterators allow back-edges in the state graph in order to * check unbounded loops that iterators. * * In is_state_visited() it is necessary to know if explored states are * part of some loops in order to decide whether non-exact states * comparison could be used: * - non-exact states comparison establishes sub-state relation and uses * read and precision marks to do so, these marks are propagated from * children states and thus are not guaranteed to be final in a loop; * - exact states comparison just checks if current and explored states * are identical (and thus form a back-edge). * * Paper "A New Algorithm for Identifying Loops in Decompilation" * by Tao Wei, Jian Mao, Wei Zou and Yu Chen [1] presents a convenient * algorithm for loop structure detection and gives an overview of * relevant terminology. It also has helpful illustrations. * * [1] https://api.semanticscholar.org/CorpusID:15784067 * * We use a similar algorithm but because loop nested structure is * irrelevant for verifier ours is significantly simpler and resembles * strongly connected components algorithm from Sedgewick's textbook. * * Define topmost loop entry as a first node of the loop traversed in a * depth first search starting from initial state. The goal of the loop * tracking algorithm is to associate topmost loop entries with states * derived from these entries. * * For each step in the DFS states traversal algorithm needs to identify * the following situations: * * initial initial initial * | | | * V V V * ... ... .---------> hdr * | | | | * V V | V * cur .-> succ | .------... * | | | | | | * V | V | V V * succ '-- cur | ... ... * | | | * | V V * | succ <- cur * | | * | V * | ... * | | * '----' * * (A) successor state of cur (B) successor state of cur or it's entry * not yet traversed are in current DFS path, thus cur and succ * are members of the same outermost loop * * initial initial * | | * V V * ... ... * | | * V V * .------... .------... * | | | | * V V V V * .-> hdr ... ... ... * | | | | | * | V V V V * | succ <- cur succ <- cur * | | | * | V V * | ... ... * | | | * '----' exit * * (C) successor state of cur is a part of some loop but this loop * does not include cur or successor state is not in a loop at all. * * Algorithm could be described as the following python code: * * traversed = set() # Set of traversed nodes * entries = {} # Mapping from node to loop entry * depths = {} # Depth level assigned to graph node * path = set() # Current DFS path * * # Find outermost loop entry known for n * def get_loop_entry(n): * h = entries.get(n, None) * while h in entries and entries[h] != h: * h = entries[h] * return h * * # Update n's loop entry if h's outermost entry comes * # before n's outermost entry in current DFS path. * def update_loop_entry(n, h): * n1 = get_loop_entry(n) or n * h1 = get_loop_entry(h) or h * if h1 in path and depths[h1] <= depths[n1]: * entries[n] = h1 * * def dfs(n, depth): * traversed.add(n) * path.add(n) * depths[n] = depth * for succ in G.successors(n): * if succ not in traversed: * # Case A: explore succ and update cur's loop entry * # only if succ's entry is in current DFS path. * dfs(succ, depth + 1) * h = get_loop_entry(succ) * update_loop_entry(n, h) * else: * # Case B or C depending on `h1 in path` check in update_loop_entry(). * update_loop_entry(n, succ) * path.remove(n) * * To adapt this algorithm for use with verifier: * - use st->branch == 0 as a signal that DFS of succ had been finished * and cur's loop entry has to be updated (case A), handle this in * update_branch_counts(); * - use st->branch > 0 as a signal that st is in the current DFS path; * - handle cases B and C in is_state_visited(); * - update topmost loop entry for intermediate states in get_loop_entry(). */ static struct bpf_verifier_state *get_loop_entry(struct bpf_verifier_state *st) { struct bpf_verifier_state *topmost = st->loop_entry, *old; while (topmost && topmost->loop_entry && topmost != topmost->loop_entry) topmost = topmost->loop_entry; /* Update loop entries for intermediate states to avoid this * traversal in future get_loop_entry() calls. */ while (st && st->loop_entry != topmost) { old = st->loop_entry; st->loop_entry = topmost; st = old; } return topmost; } static void update_loop_entry(struct bpf_verifier_state *cur, struct bpf_verifier_state *hdr) { struct bpf_verifier_state *cur1, *hdr1; cur1 = get_loop_entry(cur) ?: cur; hdr1 = get_loop_entry(hdr) ?: hdr; /* The head1->branches check decides between cases B and C in * comment for get_loop_entry(). If hdr1->branches == 0 then * head's topmost loop entry is not in current DFS path, * hence 'cur' and 'hdr' are not in the same loop and there is * no need to update cur->loop_entry. */ if (hdr1->branches && hdr1->dfs_depth <= cur1->dfs_depth) { cur->loop_entry = hdr; hdr->used_as_loop_entry = true; } } static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { while (st) { u32 br = --st->branches; /* br == 0 signals that DFS exploration for 'st' is finished, * thus it is necessary to update parent's loop entry if it * turned out that st is a part of some loop. * This is a part of 'case A' in get_loop_entry() comment. */ if (br == 0 && st->parent && st->loop_entry) update_loop_entry(st->parent, st->loop_entry); /* WARN_ON(br > 1) technically makes sense here, * but see comment in push_stack(), hence: */ WARN_ONCE((int)br < 0, "BUG update_branch_counts:branches_to_explore=%d\n", br); if (br) break; st = st->parent; } } static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx, int *insn_idx, bool pop_log) { struct bpf_verifier_state *cur = env->cur_state; struct bpf_verifier_stack_elem *elem, *head = env->head; int err; if (env->head == NULL) return -ENOENT; if (cur) { err = copy_verifier_state(cur, &head->st); if (err) return err; } if (pop_log) bpf_vlog_reset(&env->log, head->log_pos); if (insn_idx) *insn_idx = head->insn_idx; if (prev_insn_idx) *prev_insn_idx = head->prev_insn_idx; elem = head->next; free_verifier_state(&head->st, false); kfree(head); env->head = elem; env->stack_size--; return 0; } static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx, bool speculative) { struct bpf_verifier_state *cur = env->cur_state; struct bpf_verifier_stack_elem *elem; int err; elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL); if (!elem) goto err; elem->insn_idx = insn_idx; elem->prev_insn_idx = prev_insn_idx; elem->next = env->head; elem->log_pos = env->log.end_pos; env->head = elem; env->stack_size++; err = copy_verifier_state(&elem->st, cur); if (err) goto err; elem->st.speculative |= speculative; if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) { verbose(env, "The sequence of %d jumps is too complex.\n", env->stack_size); goto err; } if (elem->st.parent) { ++elem->st.parent->branches; /* WARN_ON(branches > 2) technically makes sense here, * but * 1. speculative states will bump 'branches' for non-branch * instructions * 2. is_state_visited() heuristics may decide not to create * a new state for a sequence of branches and all such current * and cloned states will be pointing to a single parent state * which might have large 'branches' count. */ } return &elem->st; err: free_verifier_state(env->cur_state, true); env->cur_state = NULL; /* pop all elements and return */ while (!pop_stack(env, NULL, NULL, false)); return NULL; } #define CALLER_SAVED_REGS 6 static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; /* This helper doesn't clear reg->id */ static void ___mark_reg_known(struct bpf_reg_state *reg, u64 imm) { reg->var_off = tnum_const(imm); reg->smin_value = (s64)imm; reg->smax_value = (s64)imm; reg->umin_value = imm; reg->umax_value = imm; reg->s32_min_value = (s32)imm; reg->s32_max_value = (s32)imm; reg->u32_min_value = (u32)imm; reg->u32_max_value = (u32)imm; } /* Mark the unknown part of a register (variable offset or scalar value) as * known to have the value @imm. */ static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm) { /* Clear off and union(map_ptr, range) */ memset(((u8 *)reg) + sizeof(reg->type), 0, offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type)); reg->id = 0; reg->ref_obj_id = 0; ___mark_reg_known(reg, imm); } static void __mark_reg32_known(struct bpf_reg_state *reg, u64 imm) { reg->var_off = tnum_const_subreg(reg->var_off, imm); reg->s32_min_value = (s32)imm; reg->s32_max_value = (s32)imm; reg->u32_min_value = (u32)imm; reg->u32_max_value = (u32)imm; } /* Mark the 'variable offset' part of a register as zero. This should be * used only on registers holding a pointer type. */ static void __mark_reg_known_zero(struct bpf_reg_state *reg) { __mark_reg_known(reg, 0); } static void __mark_reg_const_zero(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { __mark_reg_known(reg, 0); reg->type = SCALAR_VALUE; /* all scalars are assumed imprecise initially (unless unprivileged, * in which case everything is forced to be precise) */ reg->precise = !env->bpf_capable; } static void mark_reg_known_zero(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { verbose(env, "mark_reg_known_zero(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) __mark_reg_not_init(env, regs + regno); return; } __mark_reg_known_zero(regs + regno); } static void __mark_dynptr_reg(struct bpf_reg_state *reg, enum bpf_dynptr_type type, bool first_slot, int dynptr_id) { /* reg->type has no meaning for STACK_DYNPTR, but when we set reg for * callback arguments, it does need to be CONST_PTR_TO_DYNPTR, so simply * set it unconditionally as it is ignored for STACK_DYNPTR anyway. */ __mark_reg_known_zero(reg); reg->type = CONST_PTR_TO_DYNPTR; /* Give each dynptr a unique id to uniquely associate slices to it. */ reg->id = dynptr_id; reg->dynptr.type = type; reg->dynptr.first_slot = first_slot; } static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) { if (base_type(reg->type) == PTR_TO_MAP_VALUE) { const struct bpf_map *map = reg->map_ptr; if (map->inner_map_meta) { reg->type = CONST_PTR_TO_MAP; reg->map_ptr = map->inner_map_meta; /* transfer reg's id which is unique for every map_lookup_elem * as UID of the inner map. */ if (btf_record_has_field(map->inner_map_meta->record, BPF_TIMER)) reg->map_uid = reg->id; if (btf_record_has_field(map->inner_map_meta->record, BPF_WORKQUEUE)) reg->map_uid = reg->id; } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { reg->type = PTR_TO_XDP_SOCK; } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP || map->map_type == BPF_MAP_TYPE_SOCKHASH) { reg->type = PTR_TO_SOCKET; } else { reg->type = PTR_TO_MAP_VALUE; } return; } reg->type &= ~PTR_MAYBE_NULL; } static void mark_reg_graph_node(struct bpf_reg_state *regs, u32 regno, struct btf_field_graph_root *ds_head) { __mark_reg_known_zero(®s[regno]); regs[regno].type = PTR_TO_BTF_ID | MEM_ALLOC; regs[regno].btf = ds_head->btf; regs[regno].btf_id = ds_head->value_btf_id; regs[regno].off = ds_head->node_offset; } static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg) { return type_is_pkt_pointer(reg->type); } static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg) { return reg_is_pkt_pointer(reg) || reg->type == PTR_TO_PACKET_END; } static bool reg_is_dynptr_slice_pkt(const struct bpf_reg_state *reg) { return base_type(reg->type) == PTR_TO_MEM && (reg->type & DYNPTR_TYPE_SKB || reg->type & DYNPTR_TYPE_XDP); } /* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */ static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg, enum bpf_reg_type which) { /* The register can already have a range from prior markings. * This is fine as long as it hasn't been advanced from its * origin. */ return reg->type == which && reg->id == 0 && reg->off == 0 && tnum_equals_const(reg->var_off, 0); } /* Reset the min/max bounds of a register */ static void __mark_reg_unbounded(struct bpf_reg_state *reg) { reg->smin_value = S64_MIN; reg->smax_value = S64_MAX; reg->umin_value = 0; reg->umax_value = U64_MAX; reg->s32_min_value = S32_MIN; reg->s32_max_value = S32_MAX; reg->u32_min_value = 0; reg->u32_max_value = U32_MAX; } static void __mark_reg64_unbounded(struct bpf_reg_state *reg) { reg->smin_value = S64_MIN; reg->smax_value = S64_MAX; reg->umin_value = 0; reg->umax_value = U64_MAX; } static void __mark_reg32_unbounded(struct bpf_reg_state *reg) { reg->s32_min_value = S32_MIN; reg->s32_max_value = S32_MAX; reg->u32_min_value = 0; reg->u32_max_value = U32_MAX; } static void __update_reg32_bounds(struct bpf_reg_state *reg) { struct tnum var32_off = tnum_subreg(reg->var_off); /* min signed is max(sign bit) | min(other bits) */ reg->s32_min_value = max_t(s32, reg->s32_min_value, var32_off.value | (var32_off.mask & S32_MIN)); /* max signed is min(sign bit) | max(other bits) */ reg->s32_max_value = min_t(s32, reg->s32_max_value, var32_off.value | (var32_off.mask & S32_MAX)); reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)var32_off.value); reg->u32_max_value = min(reg->u32_max_value, (u32)(var32_off.value | var32_off.mask)); } static void __update_reg64_bounds(struct bpf_reg_state *reg) { /* min signed is max(sign bit) | min(other bits) */ reg->smin_value = max_t(s64, reg->smin_value, reg->var_off.value | (reg->var_off.mask & S64_MIN)); /* max signed is min(sign bit) | max(other bits) */ reg->smax_value = min_t(s64, reg->smax_value, reg->var_off.value | (reg->var_off.mask & S64_MAX)); reg->umin_value = max(reg->umin_value, reg->var_off.value); reg->umax_value = min(reg->umax_value, reg->var_off.value | reg->var_off.mask); } static void __update_reg_bounds(struct bpf_reg_state *reg) { __update_reg32_bounds(reg); __update_reg64_bounds(reg); } /* Uses signed min/max values to inform unsigned, and vice-versa */ static void __reg32_deduce_bounds(struct bpf_reg_state *reg) { /* If upper 32 bits of u64/s64 range don't change, we can use lower 32 * bits to improve our u32/s32 boundaries. * * E.g., the case where we have upper 32 bits as zero ([10, 20] in * u64) is pretty trivial, it's obvious that in u32 we'll also have * [10, 20] range. But this property holds for any 64-bit range as * long as upper 32 bits in that entire range of values stay the same. * * E.g., u64 range [0x10000000A, 0x10000000F] ([4294967306, 4294967311] * in decimal) has the same upper 32 bits throughout all the values in * that range. As such, lower 32 bits form a valid [0xA, 0xF] ([10, 15]) * range. * * Note also, that [0xA, 0xF] is a valid range both in u32 and in s32, * following the rules outlined below about u64/s64 correspondence * (which equally applies to u32 vs s32 correspondence). In general it * depends on actual hexadecimal values of 32-bit range. They can form * only valid u32, or only valid s32 ranges in some cases. * * So we use all these insights to derive bounds for subregisters here. */ if ((reg->umin_value >> 32) == (reg->umax_value >> 32)) { /* u64 to u32 casting preserves validity of low 32 bits as * a range, if upper 32 bits are the same */ reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)reg->umin_value); reg->u32_max_value = min_t(u32, reg->u32_max_value, (u32)reg->umax_value); if ((s32)reg->umin_value <= (s32)reg->umax_value) { reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->umin_value); reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->umax_value); } } if ((reg->smin_value >> 32) == (reg->smax_value >> 32)) { /* low 32 bits should form a proper u32 range */ if ((u32)reg->smin_value <= (u32)reg->smax_value) { reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)reg->smin_value); reg->u32_max_value = min_t(u32, reg->u32_max_value, (u32)reg->smax_value); } /* low 32 bits should form a proper s32 range */ if ((s32)reg->smin_value <= (s32)reg->smax_value) { reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->smin_value); reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->smax_value); } } /* Special case where upper bits form a small sequence of two * sequential numbers (in 32-bit unsigned space, so 0xffffffff to * 0x00000000 is also valid), while lower bits form a proper s32 range * going from negative numbers to positive numbers. E.g., let's say we * have s64 range [-1, 1] ([0xffffffffffffffff, 0x0000000000000001]). * Possible s64 values are {-1, 0, 1} ({0xffffffffffffffff, * 0x0000000000000000, 0x00000000000001}). Ignoring upper 32 bits, * we still get a valid s32 range [-1, 1] ([0xffffffff, 0x00000001]). * Note that it doesn't have to be 0xffffffff going to 0x00000000 in * upper 32 bits. As a random example, s64 range * [0xfffffff0fffffff0; 0xfffffff100000010], forms a valid s32 range * [-16, 16] ([0xfffffff0; 0x00000010]) in its 32 bit subregister. */ if ((u32)(reg->umin_value >> 32) + 1 == (u32)(reg->umax_value >> 32) && (s32)reg->umin_value < 0 && (s32)reg->umax_value >= 0) { reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->umin_value); reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->umax_value); } if ((u32)(reg->smin_value >> 32) + 1 == (u32)(reg->smax_value >> 32) && (s32)reg->smin_value < 0 && (s32)reg->smax_value >= 0) { reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->smin_value); reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->smax_value); } /* if u32 range forms a valid s32 range (due to matching sign bit), * try to learn from that */ if ((s32)reg->u32_min_value <= (s32)reg->u32_max_value) { reg->s32_min_value = max_t(s32, reg->s32_min_value, reg->u32_min_value); reg->s32_max_value = min_t(s32, reg->s32_max_value, reg->u32_max_value); } /* If we cannot cross the sign boundary, then signed and unsigned bounds * are the same, so combine. This works even in the negative case, e.g. * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. */ if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) { reg->u32_min_value = max_t(u32, reg->s32_min_value, reg->u32_min_value); reg->u32_max_value = min_t(u32, reg->s32_max_value, reg->u32_max_value); } } static void __reg64_deduce_bounds(struct bpf_reg_state *reg) { /* If u64 range forms a valid s64 range (due to matching sign bit), * try to learn from that. Let's do a bit of ASCII art to see when * this is happening. Let's take u64 range first: * * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX * |-------------------------------|--------------------------------| * * Valid u64 range is formed when umin and umax are anywhere in the * range [0, U64_MAX], and umin <= umax. u64 case is simple and * straightforward. Let's see how s64 range maps onto the same range * of values, annotated below the line for comparison: * * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX * |-------------------------------|--------------------------------| * 0 S64_MAX S64_MIN -1 * * So s64 values basically start in the middle and they are logically * contiguous to the right of it, wrapping around from -1 to 0, and * then finishing as S64_MAX (0x7fffffffffffffff) right before * S64_MIN. We can try drawing the continuity of u64 vs s64 values * more visually as mapped to sign-agnostic range of hex values. * * u64 start u64 end * _______________________________________________________________ * / \ * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX * |-------------------------------|--------------------------------| * 0 S64_MAX S64_MIN -1 * / \ * >------------------------------ -------------------------------> * s64 continues... s64 end s64 start s64 "midpoint" * * What this means is that, in general, we can't always derive * something new about u64 from any random s64 range, and vice versa. * * But we can do that in two particular cases. One is when entire * u64/s64 range is *entirely* contained within left half of the above * diagram or when it is *entirely* contained in the right half. I.e.: * * |-------------------------------|--------------------------------| * ^ ^ ^ ^ * A B C D * * [A, B] and [C, D] are contained entirely in their respective halves * and form valid contiguous ranges as both u64 and s64 values. [A, B] * will be non-negative both as u64 and s64 (and in fact it will be * identical ranges no matter the signedness). [C, D] treated as s64 * will be a range of negative values, while in u64 it will be * non-negative range of values larger than 0x8000000000000000. * * Now, any other range here can't be represented in both u64 and s64 * simultaneously. E.g., [A, C], [A, D], [B, C], [B, D] are valid * contiguous u64 ranges, but they are discontinuous in s64. [B, C] * in s64 would be properly presented as [S64_MIN, C] and [B, S64_MAX], * for example. Similarly, valid s64 range [D, A] (going from negative * to positive values), would be two separate [D, U64_MAX] and [0, A] * ranges as u64. Currently reg_state can't represent two segments per * numeric domain, so in such situations we can only derive maximal * possible range ([0, U64_MAX] for u64, and [S64_MIN, S64_MAX] for s64). * * So we use these facts to derive umin/umax from smin/smax and vice * versa only if they stay within the same "half". This is equivalent * to checking sign bit: lower half will have sign bit as zero, upper * half have sign bit 1. Below in code we simplify this by just * casting umin/umax as smin/smax and checking if they form valid * range, and vice versa. Those are equivalent checks. */ if ((s64)reg->umin_value <= (s64)reg->umax_value) { reg->smin_value = max_t(s64, reg->smin_value, reg->umin_value); reg->smax_value = min_t(s64, reg->smax_value, reg->umax_value); } /* If we cannot cross the sign boundary, then signed and unsigned bounds * are the same, so combine. This works even in the negative case, e.g. * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. */ if ((u64)reg->smin_value <= (u64)reg->smax_value) { reg->umin_value = max_t(u64, reg->smin_value, reg->umin_value); reg->umax_value = min_t(u64, reg->smax_value, reg->umax_value); } } static void __reg_deduce_mixed_bounds(struct bpf_reg_state *reg) { /* Try to tighten 64-bit bounds from 32-bit knowledge, using 32-bit * values on both sides of 64-bit range in hope to have tighter range. * E.g., if r1 is [0x1'00000000, 0x3'80000000], and we learn from * 32-bit signed > 0 operation that s32 bounds are now [1; 0x7fffffff]. * With this, we can substitute 1 as low 32-bits of _low_ 64-bit bound * (0x100000000 -> 0x100000001) and 0x7fffffff as low 32-bits of * _high_ 64-bit bound (0x380000000 -> 0x37fffffff) and arrive at a * better overall bounds for r1 as [0x1'000000001; 0x3'7fffffff]. * We just need to make sure that derived bounds we are intersecting * with are well-formed ranges in respective s64 or u64 domain, just * like we do with similar kinds of 32-to-64 or 64-to-32 adjustments. */ __u64 new_umin, new_umax; __s64 new_smin, new_smax; /* u32 -> u64 tightening, it's always well-formed */ new_umin = (reg->umin_value & ~0xffffffffULL) | reg->u32_min_value; new_umax = (reg->umax_value & ~0xffffffffULL) | reg->u32_max_value; reg->umin_value = max_t(u64, reg->umin_value, new_umin); reg->umax_value = min_t(u64, reg->umax_value, new_umax); /* u32 -> s64 tightening, u32 range embedded into s64 preserves range validity */ new_smin = (reg->smin_value & ~0xffffffffULL) | reg->u32_min_value; new_smax = (reg->smax_value & ~0xffffffffULL) | reg->u32_max_value; reg->smin_value = max_t(s64, reg->smin_value, new_smin); reg->smax_value = min_t(s64, reg->smax_value, new_smax); /* if s32 can be treated as valid u32 range, we can use it as well */ if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) { /* s32 -> u64 tightening */ new_umin = (reg->umin_value & ~0xffffffffULL) | (u32)reg->s32_min_value; new_umax = (reg->umax_value & ~0xffffffffULL) | (u32)reg->s32_max_value; reg->umin_value = max_t(u64, reg->umin_value, new_umin); reg->umax_value = min_t(u64, reg->umax_value, new_umax); /* s32 -> s64 tightening */ new_smin = (reg->smin_value & ~0xffffffffULL) | (u32)reg->s32_min_value; new_smax = (reg->smax_value & ~0xffffffffULL) | (u32)reg->s32_max_value; reg->smin_value = max_t(s64, reg->smin_value, new_smin); reg->smax_value = min_t(s64, reg->smax_value, new_smax); } } static void __reg_deduce_bounds(struct bpf_reg_state *reg) { __reg32_deduce_bounds(reg); __reg64_deduce_bounds(reg); __reg_deduce_mixed_bounds(reg); } /* Attempts to improve var_off based on unsigned min/max information */ static void __reg_bound_offset(struct bpf_reg_state *reg) { struct tnum var64_off = tnum_intersect(reg->var_off, tnum_range(reg->umin_value, reg->umax_value)); struct tnum var32_off = tnum_intersect(tnum_subreg(var64_off), tnum_range(reg->u32_min_value, reg->u32_max_value)); reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off); } static void reg_bounds_sync(struct bpf_reg_state *reg) { /* We might have learned new bounds from the var_off. */ __update_reg_bounds(reg); /* We might have learned something about the sign bit. */ __reg_deduce_bounds(reg); __reg_deduce_bounds(reg); /* We might have learned some bits from the bounds. */ __reg_bound_offset(reg); /* Intersecting with the old var_off might have improved our bounds * slightly, e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), * then new var_off is (0; 0x7f...fc) which improves our umax. */ __update_reg_bounds(reg); } static int reg_bounds_sanity_check(struct bpf_verifier_env *env, struct bpf_reg_state *reg, const char *ctx) { const char *msg; if (reg->umin_value > reg->umax_value || reg->smin_value > reg->smax_value || reg->u32_min_value > reg->u32_max_value || reg->s32_min_value > reg->s32_max_value) { msg = "range bounds violation"; goto out; } if (tnum_is_const(reg->var_off)) { u64 uval = reg->var_off.value; s64 sval = (s64)uval; if (reg->umin_value != uval || reg->umax_value != uval || reg->smin_value != sval || reg->smax_value != sval) { msg = "const tnum out of sync with range bounds"; goto out; } } if (tnum_subreg_is_const(reg->var_off)) { u32 uval32 = tnum_subreg(reg->var_off).value; s32 sval32 = (s32)uval32; if (reg->u32_min_value != uval32 || reg->u32_max_value != uval32 || reg->s32_min_value != sval32 || reg->s32_max_value != sval32) { msg = "const subreg tnum out of sync with range bounds"; goto out; } } return 0; out: verbose(env, "REG INVARIANTS VIOLATION (%s): %s u64=[%#llx, %#llx] " "s64=[%#llx, %#llx] u32=[%#x, %#x] s32=[%#x, %#x] var_off=(%#llx, %#llx)\n", ctx, msg, reg->umin_value, reg->umax_value, reg->smin_value, reg->smax_value, reg->u32_min_value, reg->u32_max_value, reg->s32_min_value, reg->s32_max_value, reg->var_off.value, reg->var_off.mask); if (env->test_reg_invariants) return -EFAULT; __mark_reg_unbounded(reg); return 0; } static bool __reg32_bound_s64(s32 a) { return a >= 0 && a <= S32_MAX; } static void __reg_assign_32_into_64(struct bpf_reg_state *reg) { reg->umin_value = reg->u32_min_value; reg->umax_value = reg->u32_max_value; /* Attempt to pull 32-bit signed bounds into 64-bit bounds but must * be positive otherwise set to worse case bounds and refine later * from tnum. */ if (__reg32_bound_s64(reg->s32_min_value) && __reg32_bound_s64(reg->s32_max_value)) { reg->smin_value = reg->s32_min_value; reg->smax_value = reg->s32_max_value; } else { reg->smin_value = 0; reg->smax_value = U32_MAX; } } /* Mark a register as having a completely unknown (scalar) value. */ static void __mark_reg_unknown_imprecise(struct bpf_reg_state *reg) { /* * Clear type, off, and union(map_ptr, range) and * padding between 'type' and union */ memset(reg, 0, offsetof(struct bpf_reg_state, var_off)); reg->type = SCALAR_VALUE; reg->id = 0; reg->ref_obj_id = 0; reg->var_off = tnum_unknown; reg->frameno = 0; reg->precise = false; __mark_reg_unbounded(reg); } /* Mark a register as having a completely unknown (scalar) value, * initialize .precise as true when not bpf capable. */ static void __mark_reg_unknown(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { __mark_reg_unknown_imprecise(reg); reg->precise = !env->bpf_capable; } static void mark_reg_unknown(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { verbose(env, "mark_reg_unknown(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) __mark_reg_not_init(env, regs + regno); return; } __mark_reg_unknown(env, regs + regno); } static void __mark_reg_not_init(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { __mark_reg_unknown(env, reg); reg->type = NOT_INIT; } static void mark_reg_not_init(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { verbose(env, "mark_reg_not_init(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) __mark_reg_not_init(env, regs + regno); return; } __mark_reg_not_init(env, regs + regno); } static void mark_btf_ld_reg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno, enum bpf_reg_type reg_type, struct btf *btf, u32 btf_id, enum bpf_type_flag flag) { if (reg_type == SCALAR_VALUE) { mark_reg_unknown(env, regs, regno); return; } mark_reg_known_zero(env, regs, regno); regs[regno].type = PTR_TO_BTF_ID | flag; regs[regno].btf = btf; regs[regno].btf_id = btf_id; if (type_may_be_null(flag)) regs[regno].id = ++env->id_gen; } #define DEF_NOT_SUBREG (0) static void init_reg_state(struct bpf_verifier_env *env, struct bpf_func_state *state) { struct bpf_reg_state *regs = state->regs; int i; for (i = 0; i < MAX_BPF_REG; i++) { mark_reg_not_init(env, regs, i); regs[i].live = REG_LIVE_NONE; regs[i].parent = NULL; regs[i].subreg_def = DEF_NOT_SUBREG; } /* frame pointer */ regs[BPF_REG_FP].type = PTR_TO_STACK; mark_reg_known_zero(env, regs, BPF_REG_FP); regs[BPF_REG_FP].frameno = state->frameno; } static struct bpf_retval_range retval_range(s32 minval, s32 maxval) { return (struct bpf_retval_range){ minval, maxval }; } #define BPF_MAIN_FUNC (-1) static void init_func_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int callsite, int frameno, int subprogno) { state->callsite = callsite; state->frameno = frameno; state->subprogno = subprogno; state->callback_ret_range = retval_range(0, 0); init_reg_state(env, state); mark_verifier_state_scratched(env); } /* Similar to push_stack(), but for async callbacks */ static struct bpf_verifier_state *push_async_cb(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx, int subprog, bool is_sleepable) { struct bpf_verifier_stack_elem *elem; struct bpf_func_state *frame; elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL); if (!elem) goto err; elem->insn_idx = insn_idx; elem->prev_insn_idx = prev_insn_idx; elem->next = env->head; elem->log_pos = env->log.end_pos; env->head = elem; env->stack_size++; if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) { verbose(env, "The sequence of %d jumps is too complex for async cb.\n", env->stack_size); goto err; } /* Unlike push_stack() do not copy_verifier_state(). * The caller state doesn't matter. * This is async callback. It starts in a fresh stack. * Initialize it similar to do_check_common(). */ elem->st.branches = 1; elem->st.in_sleepable = is_sleepable; frame = kzalloc(sizeof(*frame), GFP_KERNEL); if (!frame) goto err; init_func_state(env, frame, BPF_MAIN_FUNC /* callsite */, 0 /* frameno within this callchain */, subprog /* subprog number within this prog */); elem->st.frame[0] = frame; return &elem->st; err: free_verifier_state(env->cur_state, true); env->cur_state = NULL; /* pop all elements and return */ while (!pop_stack(env, NULL, NULL, false)); return NULL; } enum reg_arg_type { SRC_OP, /* register is used as source operand */ DST_OP, /* register is used as destination operand */ DST_OP_NO_MARK /* same as above, check only, don't mark */ }; static int cmp_subprogs(const void *a, const void *b) { return ((struct bpf_subprog_info *)a)->start - ((struct bpf_subprog_info *)b)->start; } static int find_subprog(struct bpf_verifier_env *env, int off) { struct bpf_subprog_info *p; p = bsearch(&off, env->subprog_info, env->subprog_cnt, sizeof(env->subprog_info[0]), cmp_subprogs); if (!p) return -ENOENT; return p - env->subprog_info; } static int add_subprog(struct bpf_verifier_env *env, int off) { int insn_cnt = env->prog->len; int ret; if (off >= insn_cnt || off < 0) { verbose(env, "call to invalid destination\n"); return -EINVAL; } ret = find_subprog(env, off); if (ret >= 0) return ret; if (env->subprog_cnt >= BPF_MAX_SUBPROGS) { verbose(env, "too many subprograms\n"); return -E2BIG; } /* determine subprog starts. The end is one before the next starts */ env->subprog_info[env->subprog_cnt++].start = off; sort(env->subprog_info, env->subprog_cnt, sizeof(env->subprog_info[0]), cmp_subprogs, NULL); return env->subprog_cnt - 1; } static int bpf_find_exception_callback_insn_off(struct bpf_verifier_env *env) { struct bpf_prog_aux *aux = env->prog->aux; struct btf *btf = aux->btf; const struct btf_type *t; u32 main_btf_id, id; const char *name; int ret, i; /* Non-zero func_info_cnt implies valid btf */ if (!aux->func_info_cnt) return 0; main_btf_id = aux->func_info[0].type_id; t = btf_type_by_id(btf, main_btf_id); if (!t) { verbose(env, "invalid btf id for main subprog in func_info\n"); return -EINVAL; } name = btf_find_decl_tag_value(btf, t, -1, "exception_callback:"); if (IS_ERR(name)) { ret = PTR_ERR(name); /* If there is no tag present, there is no exception callback */ if (ret == -ENOENT) ret = 0; else if (ret == -EEXIST) verbose(env, "multiple exception callback tags for main subprog\n"); return ret; } ret = btf_find_by_name_kind(btf, name, BTF_KIND_FUNC); if (ret < 0) { verbose(env, "exception callback '%s' could not be found in BTF\n", name); return ret; } id = ret; t = btf_type_by_id(btf, id); if (btf_func_linkage(t) != BTF_FUNC_GLOBAL) { verbose(env, "exception callback '%s' must have global linkage\n", name); return -EINVAL; } ret = 0; for (i = 0; i < aux->func_info_cnt; i++) { if (aux->func_info[i].type_id != id) continue; ret = aux->func_info[i].insn_off; /* Further func_info and subprog checks will also happen * later, so assume this is the right insn_off for now. */ if (!ret) { verbose(env, "invalid exception callback insn_off in func_info: 0\n"); ret = -EINVAL; } } if (!ret) { verbose(env, "exception callback type id not found in func_info\n"); ret = -EINVAL; } return ret; } #define MAX_KFUNC_DESCS 256 #define MAX_KFUNC_BTFS 256 struct bpf_kfunc_desc { struct btf_func_model func_model; u32 func_id; s32 imm; u16 offset; unsigned long addr; }; struct bpf_kfunc_btf { struct btf *btf; struct module *module; u16 offset; }; struct bpf_kfunc_desc_tab { /* Sorted by func_id (BTF ID) and offset (fd_array offset) during * verification. JITs do lookups by bpf_insn, where func_id may not be * available, therefore at the end of verification do_misc_fixups() * sorts this by imm and offset. */ struct bpf_kfunc_desc descs[MAX_KFUNC_DESCS]; u32 nr_descs; }; struct bpf_kfunc_btf_tab { struct bpf_kfunc_btf descs[MAX_KFUNC_BTFS]; u32 nr_descs; }; static int kfunc_desc_cmp_by_id_off(const void *a, const void *b) { const struct bpf_kfunc_desc *d0 = a; const struct bpf_kfunc_desc *d1 = b; /* func_id is not greater than BTF_MAX_TYPE */ return d0->func_id - d1->func_id ?: d0->offset - d1->offset; } static int kfunc_btf_cmp_by_off(const void *a, const void *b) { const struct bpf_kfunc_btf *d0 = a; const struct bpf_kfunc_btf *d1 = b; return d0->offset - d1->offset; } static const struct bpf_kfunc_desc * find_kfunc_desc(const struct bpf_prog *prog, u32 func_id, u16 offset) { struct bpf_kfunc_desc desc = { .func_id = func_id, .offset = offset, }; struct bpf_kfunc_desc_tab *tab; tab = prog->aux->kfunc_tab; return bsearch(&desc, tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_desc_cmp_by_id_off); } int bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id, u16 btf_fd_idx, u8 **func_addr) { const struct bpf_kfunc_desc *desc; desc = find_kfunc_desc(prog, func_id, btf_fd_idx); if (!desc) return -EFAULT; *func_addr = (u8 *)desc->addr; return 0; } static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env, s16 offset) { struct bpf_kfunc_btf kf_btf = { .offset = offset }; struct bpf_kfunc_btf_tab *tab; struct bpf_kfunc_btf *b; struct module *mod; struct btf *btf; int btf_fd; tab = env->prog->aux->kfunc_btf_tab; b = bsearch(&kf_btf, tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_btf_cmp_by_off); if (!b) { if (tab->nr_descs == MAX_KFUNC_BTFS) { verbose(env, "too many different module BTFs\n"); return ERR_PTR(-E2BIG); } if (bpfptr_is_null(env->fd_array)) { verbose(env, "kfunc offset > 0 without fd_array is invalid\n"); return ERR_PTR(-EPROTO); } if (copy_from_bpfptr_offset(&btf_fd, env->fd_array, offset * sizeof(btf_fd), sizeof(btf_fd))) return ERR_PTR(-EFAULT); btf = btf_get_by_fd(btf_fd); if (IS_ERR(btf)) { verbose(env, "invalid module BTF fd specified\n"); return btf; } if (!btf_is_module(btf)) { verbose(env, "BTF fd for kfunc is not a module BTF\n"); btf_put(btf); return ERR_PTR(-EINVAL); } mod = btf_try_get_module(btf); if (!mod) { btf_put(btf); return ERR_PTR(-ENXIO); } b = &tab->descs[tab->nr_descs++]; b->btf = btf; b->module = mod; b->offset = offset; sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_btf_cmp_by_off, NULL); } return b->btf; } void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab) { if (!tab) return; while (tab->nr_descs--) { module_put(tab->descs[tab->nr_descs].module); btf_put(tab->descs[tab->nr_descs].btf); } kfree(tab); } static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env, s16 offset) { if (offset) { if (offset < 0) { /* In the future, this can be allowed to increase limit * of fd index into fd_array, interpreted as u16. */ verbose(env, "negative offset disallowed for kernel module function call\n"); return ERR_PTR(-EINVAL); } return __find_kfunc_desc_btf(env, offset); } return btf_vmlinux ?: ERR_PTR(-ENOENT); } static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset) { const struct btf_type *func, *func_proto; struct bpf_kfunc_btf_tab *btf_tab; struct bpf_kfunc_desc_tab *tab; struct bpf_prog_aux *prog_aux; struct bpf_kfunc_desc *desc; const char *func_name; struct btf *desc_btf; unsigned long call_imm; unsigned long addr; int err; prog_aux = env->prog->aux; tab = prog_aux->kfunc_tab; btf_tab = prog_aux->kfunc_btf_tab; if (!tab) { if (!btf_vmlinux) { verbose(env, "calling kernel function is not supported without CONFIG_DEBUG_INFO_BTF\n"); return -ENOTSUPP; } if (!env->prog->jit_requested) { verbose(env, "JIT is required for calling kernel function\n"); return -ENOTSUPP; } if (!bpf_jit_supports_kfunc_call()) { verbose(env, "JIT does not support calling kernel function\n"); return -ENOTSUPP; } if (!env->prog->gpl_compatible) { verbose(env, "cannot call kernel function from non-GPL compatible program\n"); return -EINVAL; } tab = kzalloc(sizeof(*tab), GFP_KERNEL); if (!tab) return -ENOMEM; prog_aux->kfunc_tab = tab; } /* func_id == 0 is always invalid, but instead of returning an error, be * conservative and wait until the code elimination pass before returning * error, so that invalid calls that get pruned out can be in BPF programs * loaded from userspace. It is also required that offset be untouched * for such calls. */ if (!func_id && !offset) return 0; if (!btf_tab && offset) { btf_tab = kzalloc(sizeof(*btf_tab), GFP_KERNEL); if (!btf_tab) return -ENOMEM; prog_aux->kfunc_btf_tab = btf_tab; } desc_btf = find_kfunc_desc_btf(env, offset); if (IS_ERR(desc_btf)) { verbose(env, "failed to find BTF for kernel function\n"); return PTR_ERR(desc_btf); } if (find_kfunc_desc(env->prog, func_id, offset)) return 0; if (tab->nr_descs == MAX_KFUNC_DESCS) { verbose(env, "too many different kernel function calls\n"); return -E2BIG; } func = btf_type_by_id(desc_btf, func_id); if (!func || !btf_type_is_func(func)) { verbose(env, "kernel btf_id %u is not a function\n", func_id); return -EINVAL; } func_proto = btf_type_by_id(desc_btf, func->type); if (!func_proto || !btf_type_is_func_proto(func_proto)) { verbose(env, "kernel function btf_id %u does not have a valid func_proto\n", func_id); return -EINVAL; } func_name = btf_name_by_offset(desc_btf, func->name_off); addr = kallsyms_lookup_name(func_name); if (!addr) { verbose(env, "cannot find address for kernel function %s\n", func_name); return -EINVAL; } specialize_kfunc(env, func_id, offset, &addr); if (bpf_jit_supports_far_kfunc_call()) { call_imm = func_id; } else { call_imm = BPF_CALL_IMM(addr); /* Check whether the relative offset overflows desc->imm */ if ((unsigned long)(s32)call_imm != call_imm) { verbose(env, "address of kernel function %s is out of range\n", func_name); return -EINVAL; } } if (bpf_dev_bound_kfunc_id(func_id)) { err = bpf_dev_bound_kfunc_check(&env->log, prog_aux); if (err) return err; } desc = &tab->descs[tab->nr_descs++]; desc->func_id = func_id; desc->imm = call_imm; desc->offset = offset; desc->addr = addr; err = btf_distill_func_proto(&env->log, desc_btf, func_proto, func_name, &desc->func_model); if (!err) sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_desc_cmp_by_id_off, NULL); return err; } static int kfunc_desc_cmp_by_imm_off(const void *a, const void *b) { const struct bpf_kfunc_desc *d0 = a; const struct bpf_kfunc_desc *d1 = b; if (d0->imm != d1->imm) return d0->imm < d1->imm ? -1 : 1; if (d0->offset != d1->offset) return d0->offset < d1->offset ? -1 : 1; return 0; } static void sort_kfunc_descs_by_imm_off(struct bpf_prog *prog) { struct bpf_kfunc_desc_tab *tab; tab = prog->aux->kfunc_tab; if (!tab) return; sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_desc_cmp_by_imm_off, NULL); } bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog) { return !!prog->aux->kfunc_tab; } const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn) { const struct bpf_kfunc_desc desc = { .imm = insn->imm, .offset = insn->off, }; const struct bpf_kfunc_desc *res; struct bpf_kfunc_desc_tab *tab; tab = prog->aux->kfunc_tab; res = bsearch(&desc, tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_desc_cmp_by_imm_off); return res ? &res->func_model : NULL; } static int add_subprog_and_kfunc(struct bpf_verifier_env *env) { struct bpf_subprog_info *subprog = env->subprog_info; int i, ret, insn_cnt = env->prog->len, ex_cb_insn; struct bpf_insn *insn = env->prog->insnsi; /* Add entry function. */ ret = add_subprog(env, 0); if (ret) return ret; for (i = 0; i < insn_cnt; i++, insn++) { if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn) && !bpf_pseudo_kfunc_call(insn)) continue; if (!env->bpf_capable) { verbose(env, "loading/calling other bpf or kernel functions are allowed for CAP_BPF and CAP_SYS_ADMIN\n"); return -EPERM; } if (bpf_pseudo_func(insn) || bpf_pseudo_call(insn)) ret = add_subprog(env, i + insn->imm + 1); else ret = add_kfunc_call(env, insn->imm, insn->off); if (ret < 0) return ret; } ret = bpf_find_exception_callback_insn_off(env); if (ret < 0) return ret; ex_cb_insn = ret; /* If ex_cb_insn > 0, this means that the main program has a subprog * marked using BTF decl tag to serve as the exception callback. */ if (ex_cb_insn) { ret = add_subprog(env, ex_cb_insn); if (ret < 0) return ret; for (i = 1; i < env->subprog_cnt; i++) { if (env->subprog_info[i].start != ex_cb_insn) continue; env->exception_callback_subprog = i; mark_subprog_exc_cb(env, i); break; } } /* Add a fake 'exit' subprog which could simplify subprog iteration * logic. 'subprog_cnt' should not be increased. */ subprog[env->subprog_cnt].start = insn_cnt; if (env->log.level & BPF_LOG_LEVEL2) for (i = 0; i < env->subprog_cnt; i++) verbose(env, "func#%d @%d\n", i, subprog[i].start); return 0; } static int check_subprogs(struct bpf_verifier_env *env) { int i, subprog_start, subprog_end, off, cur_subprog = 0; struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; /* now check that all jumps are within the same subprog */ subprog_start = subprog[cur_subprog].start; subprog_end = subprog[cur_subprog + 1].start; for (i = 0; i < insn_cnt; i++) { u8 code = insn[i].code; if (code == (BPF_JMP | BPF_CALL) && insn[i].src_reg == 0 && insn[i].imm == BPF_FUNC_tail_call) subprog[cur_subprog].has_tail_call = true; if (BPF_CLASS(code) == BPF_LD && (BPF_MODE(code) == BPF_ABS || BPF_MODE(code) == BPF_IND)) subprog[cur_subprog].has_ld_abs = true; if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) goto next; if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL) goto next; if (code == (BPF_JMP32 | BPF_JA)) off = i + insn[i].imm + 1; else off = i + insn[i].off + 1; if (off < subprog_start || off >= subprog_end) { verbose(env, "jump out of range from insn %d to %d\n", i, off); return -EINVAL; } next: if (i == subprog_end - 1) { /* to avoid fall-through from one subprog into another * the last insn of the subprog should be either exit * or unconditional jump back or bpf_throw call */ if (code != (BPF_JMP | BPF_EXIT) && code != (BPF_JMP32 | BPF_JA) && code != (BPF_JMP | BPF_JA)) { verbose(env, "last insn is not an exit or jmp\n"); return -EINVAL; } subprog_start = subprog_end; cur_subprog++; if (cur_subprog < env->subprog_cnt) subprog_end = subprog[cur_subprog + 1].start; } } return 0; } /* Parentage chain of this register (or stack slot) should take care of all * issues like callee-saved registers, stack slot allocation time, etc. */ static int mark_reg_read(struct bpf_verifier_env *env, const struct bpf_reg_state *state, struct bpf_reg_state *parent, u8 flag) { bool writes = parent == state->parent; /* Observe write marks */ int cnt = 0; while (parent) { /* if read wasn't screened by an earlier write ... */ if (writes && state->live & REG_LIVE_WRITTEN) break; if (parent->live & REG_LIVE_DONE) { verbose(env, "verifier BUG type %s var_off %lld off %d\n", reg_type_str(env, parent->type), parent->var_off.value, parent->off); return -EFAULT; } /* The first condition is more likely to be true than the * second, checked it first. */ if ((parent->live & REG_LIVE_READ) == flag || parent->live & REG_LIVE_READ64) /* The parentage chain never changes and * this parent was already marked as LIVE_READ. * There is no need to keep walking the chain again and * keep re-marking all parents as LIVE_READ. * This case happens when the same register is read * multiple times without writes into it in-between. * Also, if parent has the stronger REG_LIVE_READ64 set, * then no need to set the weak REG_LIVE_READ32. */ break; /* ... then we depend on parent's value */ parent->live |= flag; /* REG_LIVE_READ64 overrides REG_LIVE_READ32. */ if (flag == REG_LIVE_READ64) parent->live &= ~REG_LIVE_READ32; state = parent; parent = state->parent; writes = true; cnt++; } if (env->longest_mark_read_walk < cnt) env->longest_mark_read_walk = cnt; return 0; } static int mark_dynptr_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); int spi, ret; /* For CONST_PTR_TO_DYNPTR, it must have already been done by * check_reg_arg in check_helper_call and mark_btf_func_reg_size in * check_kfunc_call. */ if (reg->type == CONST_PTR_TO_DYNPTR) return 0; spi = dynptr_get_spi(env, reg); if (spi < 0) return spi; /* Caller ensures dynptr is valid and initialized, which means spi is in * bounds and spi is the first dynptr slot. Simply mark stack slot as * read. */ ret = mark_reg_read(env, &state->stack[spi].spilled_ptr, state->stack[spi].spilled_ptr.parent, REG_LIVE_READ64); if (ret) return ret; return mark_reg_read(env, &state->stack[spi - 1].spilled_ptr, state->stack[spi - 1].spilled_ptr.parent, REG_LIVE_READ64); } static int mark_iter_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int spi, int nr_slots) { struct bpf_func_state *state = func(env, reg); int err, i; for (i = 0; i < nr_slots; i++) { struct bpf_reg_state *st = &state->stack[spi - i].spilled_ptr; err = mark_reg_read(env, st, st->parent, REG_LIVE_READ64); if (err) return err; mark_stack_slot_scratched(env, spi - i); } return 0; } /* This function is supposed to be used by the following 32-bit optimization * code only. It returns TRUE if the source or destination register operates * on 64-bit, otherwise return FALSE. */ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn, u32 regno, struct bpf_reg_state *reg, enum reg_arg_type t) { u8 code, class, op; code = insn->code; class = BPF_CLASS(code); op = BPF_OP(code); if (class == BPF_JMP) { /* BPF_EXIT for "main" will reach here. Return TRUE * conservatively. */ if (op == BPF_EXIT) return true; if (op == BPF_CALL) { /* BPF to BPF call will reach here because of marking * caller saved clobber with DST_OP_NO_MARK for which we * don't care the register def because they are anyway * marked as NOT_INIT already. */ if (insn->src_reg == BPF_PSEUDO_CALL) return false; /* Helper call will reach here because of arg type * check, conservatively return TRUE. */ if (t == SRC_OP) return true; return false; } } if (class == BPF_ALU64 && op == BPF_END && (insn->imm == 16 || insn->imm == 32)) return false; if (class == BPF_ALU64 || class == BPF_JMP || (class == BPF_ALU && op == BPF_END && insn->imm == 64)) return true; if (class == BPF_ALU || class == BPF_JMP32) return false; if (class == BPF_LDX) { if (t != SRC_OP) return BPF_SIZE(code) == BPF_DW || BPF_MODE(code) == BPF_MEMSX; /* LDX source must be ptr. */ return true; } if (class == BPF_STX) { /* BPF_STX (including atomic variants) has multiple source * operands, one of which is a ptr. Check whether the caller is * asking about it. */ if (t == SRC_OP && reg->type != SCALAR_VALUE) return true; return BPF_SIZE(code) == BPF_DW; } if (class == BPF_LD) { u8 mode = BPF_MODE(code); /* LD_IMM64 */ if (mode == BPF_IMM) return true; /* Both LD_IND and LD_ABS return 32-bit data. */ if (t != SRC_OP) return false; /* Implicit ctx ptr. */ if (regno == BPF_REG_6) return true; /* Explicit source could be any width. */ return true; } if (class == BPF_ST) /* The only source register for BPF_ST is a ptr. */ return true; /* Conservatively return true at default. */ return true; } /* Return the regno defined by the insn, or -1. */ static int insn_def_regno(const struct bpf_insn *insn) { switch (BPF_CLASS(insn->code)) { case BPF_JMP: case BPF_JMP32: case BPF_ST: return -1; case BPF_STX: if (BPF_MODE(insn->code) == BPF_ATOMIC && (insn->imm & BPF_FETCH)) { if (insn->imm == BPF_CMPXCHG) return BPF_REG_0; else return insn->src_reg; } else { return -1; } default: return insn->dst_reg; } } /* Return TRUE if INSN has defined any 32-bit value explicitly. */ static bool insn_has_def32(struct bpf_verifier_env *env, struct bpf_insn *insn) { int dst_reg = insn_def_regno(insn); if (dst_reg == -1) return false; return !is_reg64(env, insn, dst_reg, NULL, DST_OP); } static void mark_insn_zext(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { s32 def_idx = reg->subreg_def; if (def_idx == DEF_NOT_SUBREG) return; env->insn_aux_data[def_idx - 1].zext_dst = true; /* The dst will be zero extended, so won't be sub-register anymore. */ reg->subreg_def = DEF_NOT_SUBREG; } static int __check_reg_arg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno, enum reg_arg_type t) { struct bpf_insn *insn = env->prog->insnsi + env->insn_idx; struct bpf_reg_state *reg; bool rw64; if (regno >= MAX_BPF_REG) { verbose(env, "R%d is invalid\n", regno); return -EINVAL; } mark_reg_scratched(env, regno); reg = ®s[regno]; rw64 = is_reg64(env, insn, regno, reg, t); if (t == SRC_OP) { /* check whether register used as source operand can be read */ if (reg->type == NOT_INIT) { verbose(env, "R%d !read_ok\n", regno); return -EACCES; } /* We don't need to worry about FP liveness because it's read-only */ if (regno == BPF_REG_FP) return 0; if (rw64) mark_insn_zext(env, reg); return mark_reg_read(env, reg, reg->parent, rw64 ? REG_LIVE_READ64 : REG_LIVE_READ32); } else { /* check whether register used as dest operand can be written to */ if (regno == BPF_REG_FP) { verbose(env, "frame pointer is read only\n"); return -EACCES; } reg->live |= REG_LIVE_WRITTEN; reg->subreg_def = rw64 ? DEF_NOT_SUBREG : env->insn_idx + 1; if (t == DST_OP) mark_reg_unknown(env, regs, regno); } return 0; } static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, enum reg_arg_type t) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; return __check_reg_arg(env, state->regs, regno, t); } static int insn_stack_access_flags(int frameno, int spi) { return INSN_F_STACK_ACCESS | (spi << INSN_F_SPI_SHIFT) | frameno; } static int insn_stack_access_spi(int insn_flags) { return (insn_flags >> INSN_F_SPI_SHIFT) & INSN_F_SPI_MASK; } static int insn_stack_access_frameno(int insn_flags) { return insn_flags & INSN_F_FRAMENO_MASK; } static void mark_jmp_point(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].jmp_point = true; } static bool is_jmp_point(struct bpf_verifier_env *env, int insn_idx) { return env->insn_aux_data[insn_idx].jmp_point; } /* for any branch, call, exit record the history of jmps in the given state */ static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur, int insn_flags) { u32 cnt = cur->jmp_history_cnt; struct bpf_jmp_history_entry *p; size_t alloc_size; /* combine instruction flags if we already recorded this instruction */ if (env->cur_hist_ent) { /* atomic instructions push insn_flags twice, for READ and * WRITE sides, but they should agree on stack slot */ WARN_ONCE((env->cur_hist_ent->flags & insn_flags) && (env->cur_hist_ent->flags & insn_flags) != insn_flags, "verifier insn history bug: insn_idx %d cur flags %x new flags %x\n", env->insn_idx, env->cur_hist_ent->flags, insn_flags); env->cur_hist_ent->flags |= insn_flags; return 0; } cnt++; alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p))); p = krealloc(cur->jmp_history, alloc_size, GFP_USER); if (!p) return -ENOMEM; cur->jmp_history = p; p = &cur->jmp_history[cnt - 1]; p->idx = env->insn_idx; p->prev_idx = env->prev_insn_idx; p->flags = insn_flags; cur->jmp_history_cnt = cnt; env->cur_hist_ent = p; return 0; } static struct bpf_jmp_history_entry *get_jmp_hist_entry(struct bpf_verifier_state *st, u32 hist_end, int insn_idx) { if (hist_end > 0 && st->jmp_history[hist_end - 1].idx == insn_idx) return &st->jmp_history[hist_end - 1]; return NULL; } /* Backtrack one insn at a time. If idx is not at the top of recorded * history then previous instruction came from straight line execution. * Return -ENOENT if we exhausted all instructions within given state. * * It's legal to have a bit of a looping with the same starting and ending * insn index within the same state, e.g.: 3->4->5->3, so just because current * instruction index is the same as state's first_idx doesn't mean we are * done. If there is still some jump history left, we should keep going. We * need to take into account that we might have a jump history between given * state's parent and itself, due to checkpointing. In this case, we'll have * history entry recording a jump from last instruction of parent state and * first instruction of given state. */ static int get_prev_insn_idx(struct bpf_verifier_state *st, int i, u32 *history) { u32 cnt = *history; if (i == st->first_insn_idx) { if (cnt == 0) return -ENOENT; if (cnt == 1 && st->jmp_history[0].idx == i) return -ENOENT; } if (cnt && st->jmp_history[cnt - 1].idx == i) { i = st->jmp_history[cnt - 1].prev_idx; (*history)--; } else { i--; } return i; } static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn) { const struct btf_type *func; struct btf *desc_btf; if (insn->src_reg != BPF_PSEUDO_KFUNC_CALL) return NULL; desc_btf = find_kfunc_desc_btf(data, insn->off); if (IS_ERR(desc_btf)) return "<error>"; func = btf_type_by_id(desc_btf, insn->imm); return btf_name_by_offset(desc_btf, func->name_off); } static inline void bt_init(struct backtrack_state *bt, u32 frame) { bt->frame = frame; } static inline void bt_reset(struct backtrack_state *bt) { struct bpf_verifier_env *env = bt->env; memset(bt, 0, sizeof(*bt)); bt->env = env; } static inline u32 bt_empty(struct backtrack_state *bt) { u64 mask = 0; int i; for (i = 0; i <= bt->frame; i++) mask |= bt->reg_masks[i] | bt->stack_masks[i]; return mask == 0; } static inline int bt_subprog_enter(struct backtrack_state *bt) { if (bt->frame == MAX_CALL_FRAMES - 1) { verbose(bt->env, "BUG subprog enter from frame %d\n", bt->frame); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } bt->frame++; return 0; } static inline int bt_subprog_exit(struct backtrack_state *bt) { if (bt->frame == 0) { verbose(bt->env, "BUG subprog exit from frame 0\n"); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } bt->frame--; return 0; } static inline void bt_set_frame_reg(struct backtrack_state *bt, u32 frame, u32 reg) { bt->reg_masks[frame] |= 1 << reg; } static inline void bt_clear_frame_reg(struct backtrack_state *bt, u32 frame, u32 reg) { bt->reg_masks[frame] &= ~(1 << reg); } static inline void bt_set_reg(struct backtrack_state *bt, u32 reg) { bt_set_frame_reg(bt, bt->frame, reg); } static inline void bt_clear_reg(struct backtrack_state *bt, u32 reg) { bt_clear_frame_reg(bt, bt->frame, reg); } static inline void bt_set_frame_slot(struct backtrack_state *bt, u32 frame, u32 slot) { bt->stack_masks[frame] |= 1ull << slot; } static inline void bt_clear_frame_slot(struct backtrack_state *bt, u32 frame, u32 slot) { bt->stack_masks[frame] &= ~(1ull << slot); } static inline u32 bt_frame_reg_mask(struct backtrack_state *bt, u32 frame) { return bt->reg_masks[frame]; } static inline u32 bt_reg_mask(struct backtrack_state *bt) { return bt->reg_masks[bt->frame]; } static inline u64 bt_frame_stack_mask(struct backtrack_state *bt, u32 frame) { return bt->stack_masks[frame]; } static inline u64 bt_stack_mask(struct backtrack_state *bt) { return bt->stack_masks[bt->frame]; } static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg) { return bt->reg_masks[bt->frame] & (1 << reg); } static inline bool bt_is_frame_slot_set(struct backtrack_state *bt, u32 frame, u32 slot) { return bt->stack_masks[frame] & (1ull << slot); } /* format registers bitmask, e.g., "r0,r2,r4" for 0x15 mask */ static void fmt_reg_mask(char *buf, ssize_t buf_sz, u32 reg_mask) { DECLARE_BITMAP(mask, 64); bool first = true; int i, n; buf[0] = '\0'; bitmap_from_u64(mask, reg_mask); for_each_set_bit(i, mask, 32) { n = snprintf(buf, buf_sz, "%sr%d", first ? "" : ",", i); first = false; buf += n; buf_sz -= n; if (buf_sz < 0) break; } } /* format stack slots bitmask, e.g., "-8,-24,-40" for 0x15 mask */ static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask) { DECLARE_BITMAP(mask, 64); bool first = true; int i, n; buf[0] = '\0'; bitmap_from_u64(mask, stack_mask); for_each_set_bit(i, mask, 64) { n = snprintf(buf, buf_sz, "%s%d", first ? "" : ",", -(i + 1) * 8); first = false; buf += n; buf_sz -= n; if (buf_sz < 0) break; } } static bool calls_callback(struct bpf_verifier_env *env, int insn_idx); /* For given verifier state backtrack_insn() is called from the last insn to * the first insn. Its purpose is to compute a bitmask of registers and * stack slots that needs precision in the parent verifier state. * * @idx is an index of the instruction we are currently processing; * @subseq_idx is an index of the subsequent instruction that: * - *would be* executed next, if jump history is viewed in forward order; * - *was* processed previously during backtracking. */ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, struct bpf_jmp_history_entry *hist, struct backtrack_state *bt) { const struct bpf_insn_cbs cbs = { .cb_call = disasm_kfunc_name, .cb_print = verbose, .private_data = env, }; struct bpf_insn *insn = env->prog->insnsi + idx; u8 class = BPF_CLASS(insn->code); u8 opcode = BPF_OP(insn->code); u8 mode = BPF_MODE(insn->code); u32 dreg = insn->dst_reg; u32 sreg = insn->src_reg; u32 spi, i, fr; if (insn->code == 0) return 0; if (env->log.level & BPF_LOG_LEVEL2) { fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_reg_mask(bt)); verbose(env, "mark_precise: frame%d: regs=%s ", bt->frame, env->tmp_str_buf); fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_stack_mask(bt)); verbose(env, "stack=%s before ", env->tmp_str_buf); verbose(env, "%d: ", idx); print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); } if (class == BPF_ALU || class == BPF_ALU64) { if (!bt_is_reg_set(bt, dreg)) return 0; if (opcode == BPF_END || opcode == BPF_NEG) { /* sreg is reserved and unused * dreg still need precision before this insn */ return 0; } else if (opcode == BPF_MOV) { if (BPF_SRC(insn->code) == BPF_X) { /* dreg = sreg or dreg = (s8, s16, s32)sreg * dreg needs precision after this insn * sreg needs precision before this insn */ bt_clear_reg(bt, dreg); if (sreg != BPF_REG_FP) bt_set_reg(bt, sreg); } else { /* dreg = K * dreg needs precision after this insn. * Corresponding register is already marked * as precise=true in this verifier state. * No further markings in parent are necessary */ bt_clear_reg(bt, dreg); } } else { if (BPF_SRC(insn->code) == BPF_X) { /* dreg += sreg * both dreg and sreg need precision * before this insn */ if (sreg != BPF_REG_FP) bt_set_reg(bt, sreg); } /* else dreg += K * dreg still needs precision before this insn */ } } else if (class == BPF_LDX) { if (!bt_is_reg_set(bt, dreg)) return 0; bt_clear_reg(bt, dreg); /* scalars can only be spilled into stack w/o losing precision. * Load from any other memory can be zero extended. * The desire to keep that precision is already indicated * by 'precise' mark in corresponding register of this state. * No further tracking necessary. */ if (!hist || !(hist->flags & INSN_F_STACK_ACCESS)) return 0; /* dreg = *(u64 *)[fp - off] was a fill from the stack. * that [fp - off] slot contains scalar that needs to be * tracked with precision */ spi = insn_stack_access_spi(hist->flags); fr = insn_stack_access_frameno(hist->flags); bt_set_frame_slot(bt, fr, spi); } else if (class == BPF_STX || class == BPF_ST) { if (bt_is_reg_set(bt, dreg)) /* stx & st shouldn't be using _scalar_ dst_reg * to access memory. It means backtracking * encountered a case of pointer subtraction. */ return -ENOTSUPP; /* scalars can only be spilled into stack */ if (!hist || !(hist->flags & INSN_F_STACK_ACCESS)) return 0; spi = insn_stack_access_spi(hist->flags); fr = insn_stack_access_frameno(hist->flags); if (!bt_is_frame_slot_set(bt, fr, spi)) return 0; bt_clear_frame_slot(bt, fr, spi); if (class == BPF_STX) bt_set_reg(bt, sreg); } else if (class == BPF_JMP || class == BPF_JMP32) { if (bpf_pseudo_call(insn)) { int subprog_insn_idx, subprog; subprog_insn_idx = idx + insn->imm + 1; subprog = find_subprog(env, subprog_insn_idx); if (subprog < 0) return -EFAULT; if (subprog_is_global(env, subprog)) { /* check that jump history doesn't have any * extra instructions from subprog; the next * instruction after call to global subprog * should be literally next instruction in * caller program */ WARN_ONCE(idx + 1 != subseq_idx, "verifier backtracking bug"); /* r1-r5 are invalidated after subprog call, * so for global func call it shouldn't be set * anymore */ if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } /* global subprog always sets R0 */ bt_clear_reg(bt, BPF_REG_0); return 0; } else { /* static subprog call instruction, which * means that we are exiting current subprog, * so only r1-r5 could be still requested as * precise, r0 and r6-r10 or any stack slot in * the current frame should be zero by now */ if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) { verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } /* we are now tracking register spills correctly, * so any instance of leftover slots is a bug */ if (bt_stack_mask(bt) != 0) { verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt)); WARN_ONCE(1, "verifier backtracking bug (subprog leftover stack slots)"); return -EFAULT; } /* propagate r1-r5 to the caller */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) { if (bt_is_reg_set(bt, i)) { bt_clear_reg(bt, i); bt_set_frame_reg(bt, bt->frame - 1, i); } } if (bt_subprog_exit(bt)) return -EFAULT; return 0; } } else if (is_sync_callback_calling_insn(insn) && idx != subseq_idx - 1) { /* exit from callback subprog to callback-calling helper or * kfunc call. Use idx/subseq_idx check to discern it from * straight line code backtracking. * Unlike the subprog call handling above, we shouldn't * propagate precision of r1-r5 (if any requested), as they are * not actually arguments passed directly to callback subprogs */ if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) { verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } if (bt_stack_mask(bt) != 0) { verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt)); WARN_ONCE(1, "verifier backtracking bug (callback leftover stack slots)"); return -EFAULT; } /* clear r1-r5 in callback subprog's mask */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) bt_clear_reg(bt, i); if (bt_subprog_exit(bt)) return -EFAULT; return 0; } else if (opcode == BPF_CALL) { /* kfunc with imm==0 is invalid and fixup_kfunc_call will * catch this error later. Make backtracking conservative * with ENOTSUPP. */ if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && insn->imm == 0) return -ENOTSUPP; /* regular helper call sets R0 */ bt_clear_reg(bt, BPF_REG_0); if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { /* if backtracing was looking for registers R1-R5 * they should have been found already. */ verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } } else if (opcode == BPF_EXIT) { bool r0_precise; /* Backtracking to a nested function call, 'idx' is a part of * the inner frame 'subseq_idx' is a part of the outer frame. * In case of a regular function call, instructions giving * precision to registers R1-R5 should have been found already. * In case of a callback, it is ok to have R1-R5 marked for * backtracking, as these registers are set by the function * invoking callback. */ if (subseq_idx >= 0 && calls_callback(env, subseq_idx)) for (i = BPF_REG_1; i <= BPF_REG_5; i++) bt_clear_reg(bt, i); if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } /* BPF_EXIT in subprog or callback always returns * right after the call instruction, so by checking * whether the instruction at subseq_idx-1 is subprog * call or not we can distinguish actual exit from * *subprog* from exit from *callback*. In the former * case, we need to propagate r0 precision, if * necessary. In the former we never do that. */ r0_precise = subseq_idx - 1 >= 0 && bpf_pseudo_call(&env->prog->insnsi[subseq_idx - 1]) && bt_is_reg_set(bt, BPF_REG_0); bt_clear_reg(bt, BPF_REG_0); if (bt_subprog_enter(bt)) return -EFAULT; if (r0_precise) bt_set_reg(bt, BPF_REG_0); /* r6-r9 and stack slots will stay set in caller frame * bitmasks until we return back from callee(s) */ return 0; } else if (BPF_SRC(insn->code) == BPF_X) { if (!bt_is_reg_set(bt, dreg) && !bt_is_reg_set(bt, sreg)) return 0; /* dreg <cond> sreg * Both dreg and sreg need precision before * this insn. If only sreg was marked precise * before it would be equally necessary to * propagate it to dreg. */ bt_set_reg(bt, dreg); bt_set_reg(bt, sreg); /* else dreg <cond> K * Only dreg still needs precision before * this insn, so for the K-based conditional * there is nothing new to be marked. */ } } else if (class == BPF_LD) { if (!bt_is_reg_set(bt, dreg)) return 0; bt_clear_reg(bt, dreg); /* It's ld_imm64 or ld_abs or ld_ind. * For ld_imm64 no further tracking of precision * into parent is necessary */ if (mode == BPF_IND || mode == BPF_ABS) /* to be analyzed */ return -ENOTSUPP; } return 0; } /* the scalar precision tracking algorithm: * . at the start all registers have precise=false. * . scalar ranges are tracked as normal through alu and jmp insns. * . once precise value of the scalar register is used in: * . ptr + scalar alu * . if (scalar cond K|scalar) * . helper_call(.., scalar, ...) where ARG_CONST is expected * backtrack through the verifier states and mark all registers and * stack slots with spilled constants that these scalar regisers * should be precise. * . during state pruning two registers (or spilled stack slots) * are equivalent if both are not precise. * * Note the verifier cannot simply walk register parentage chain, * since many different registers and stack slots could have been * used to compute single precise scalar. * * The approach of starting with precise=true for all registers and then * backtrack to mark a register as not precise when the verifier detects * that program doesn't care about specific value (e.g., when helper * takes register as ARG_ANYTHING parameter) is not safe. * * It's ok to walk single parentage chain of the verifier states. * It's possible that this backtracking will go all the way till 1st insn. * All other branches will be explored for needing precision later. * * The backtracking needs to deal with cases like: * R8=map_value(id=0,off=0,ks=4,vs=1952,imm=0) R9_w=map_value(id=0,off=40,ks=4,vs=1952,imm=0) * r9 -= r8 * r5 = r9 * if r5 > 0x79f goto pc+7 * R5_w=inv(id=0,umax_value=1951,var_off=(0x0; 0x7ff)) * r5 += 1 * ... * call bpf_perf_event_output#25 * where .arg5_type = ARG_CONST_SIZE_OR_ZERO * * and this case: * r6 = 1 * call foo // uses callee's r6 inside to compute r0 * r0 += r6 * if r0 == 0 goto * * to track above reg_mask/stack_mask needs to be independent for each frame. * * Also if parent's curframe > frame where backtracking started, * the verifier need to mark registers in both frames, otherwise callees * may incorrectly prune callers. This is similar to * commit 7640ead93924 ("bpf: verifier: make sure callees don't prune with caller differences") * * For now backtracking falls back into conservative marking. */ static void mark_all_scalars_precise(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { struct bpf_func_state *func; struct bpf_reg_state *reg; int i, j; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "mark_precise: frame%d: falling back to forcing all scalars precise\n", st->curframe); } /* big hammer: mark all scalars precise in this path. * pop_stack may still get !precise scalars. * We also skip current state and go straight to first parent state, * because precision markings in current non-checkpointed state are * not needed. See why in the comment in __mark_chain_precision below. */ for (st = st->parent; st; st = st->parent) { for (i = 0; i <= st->curframe; i++) { func = st->frame[i]; for (j = 0; j < BPF_REG_FP; j++) { reg = &func->regs[j]; if (reg->type != SCALAR_VALUE || reg->precise) continue; reg->precise = true; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "force_precise: frame%d: forcing r%d to be precise\n", i, j); } } for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { if (!is_spilled_reg(&func->stack[j])) continue; reg = &func->stack[j].spilled_ptr; if (reg->type != SCALAR_VALUE || reg->precise) continue; reg->precise = true; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "force_precise: frame%d: forcing fp%d to be precise\n", i, -(j + 1) * 8); } } } } } static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { struct bpf_func_state *func; struct bpf_reg_state *reg; int i, j; for (i = 0; i <= st->curframe; i++) { func = st->frame[i]; for (j = 0; j < BPF_REG_FP; j++) { reg = &func->regs[j]; if (reg->type != SCALAR_VALUE) continue; reg->precise = false; } for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { if (!is_spilled_reg(&func->stack[j])) continue; reg = &func->stack[j].spilled_ptr; if (reg->type != SCALAR_VALUE) continue; reg->precise = false; } } } static bool idset_contains(struct bpf_idset *s, u32 id) { u32 i; for (i = 0; i < s->count; ++i) if (s->ids[i] == id) return true; return false; } static int idset_push(struct bpf_idset *s, u32 id) { if (WARN_ON_ONCE(s->count >= ARRAY_SIZE(s->ids))) return -EFAULT; s->ids[s->count++] = id; return 0; } static void idset_reset(struct bpf_idset *s) { s->count = 0; } /* Collect a set of IDs for all registers currently marked as precise in env->bt. * Mark all registers with these IDs as precise. */ static int mark_precise_scalar_ids(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { struct bpf_idset *precise_ids = &env->idset_scratch; struct backtrack_state *bt = &env->bt; struct bpf_func_state *func; struct bpf_reg_state *reg; DECLARE_BITMAP(mask, 64); int i, fr; idset_reset(precise_ids); for (fr = bt->frame; fr >= 0; fr--) { func = st->frame[fr]; bitmap_from_u64(mask, bt_frame_reg_mask(bt, fr)); for_each_set_bit(i, mask, 32) { reg = &func->regs[i]; if (!reg->id || reg->type != SCALAR_VALUE) continue; if (idset_push(precise_ids, reg->id)) return -EFAULT; } bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr)); for_each_set_bit(i, mask, 64) { if (i >= func->allocated_stack / BPF_REG_SIZE) break; if (!is_spilled_scalar_reg(&func->stack[i])) continue; reg = &func->stack[i].spilled_ptr; if (!reg->id) continue; if (idset_push(precise_ids, reg->id)) return -EFAULT; } } for (fr = 0; fr <= st->curframe; ++fr) { func = st->frame[fr]; for (i = BPF_REG_0; i < BPF_REG_10; ++i) { reg = &func->regs[i]; if (!reg->id) continue; if (!idset_contains(precise_ids, reg->id)) continue; bt_set_frame_reg(bt, fr, i); } for (i = 0; i < func->allocated_stack / BPF_REG_SIZE; ++i) { if (!is_spilled_scalar_reg(&func->stack[i])) continue; reg = &func->stack[i].spilled_ptr; if (!reg->id) continue; if (!idset_contains(precise_ids, reg->id)) continue; bt_set_frame_slot(bt, fr, i); } } return 0; } /* * __mark_chain_precision() backtracks BPF program instruction sequence and * chain of verifier states making sure that register *regno* (if regno >= 0) * and/or stack slot *spi* (if spi >= 0) are marked as precisely tracked * SCALARS, as well as any other registers and slots that contribute to * a tracked state of given registers/stack slots, depending on specific BPF * assembly instructions (see backtrack_insns() for exact instruction handling * logic). This backtracking relies on recorded jmp_history and is able to * traverse entire chain of parent states. This process ends only when all the * necessary registers/slots and their transitive dependencies are marked as * precise. * * One important and subtle aspect is that precise marks *do not matter* in * the currently verified state (current state). It is important to understand * why this is the case. * * First, note that current state is the state that is not yet "checkpointed", * i.e., it is not yet put into env->explored_states, and it has no children * states as well. It's ephemeral, and can end up either a) being discarded if * compatible explored state is found at some point or BPF_EXIT instruction is * reached or b) checkpointed and put into env->explored_states, branching out * into one or more children states. * * In the former case, precise markings in current state are completely * ignored by state comparison code (see regsafe() for details). Only * checkpointed ("old") state precise markings are important, and if old * state's register/slot is precise, regsafe() assumes current state's * register/slot as precise and checks value ranges exactly and precisely. If * states turn out to be compatible, current state's necessary precise * markings and any required parent states' precise markings are enforced * after the fact with propagate_precision() logic, after the fact. But it's * important to realize that in this case, even after marking current state * registers/slots as precise, we immediately discard current state. So what * actually matters is any of the precise markings propagated into current * state's parent states, which are always checkpointed (due to b) case above). * As such, for scenario a) it doesn't matter if current state has precise * markings set or not. * * Now, for the scenario b), checkpointing and forking into child(ren) * state(s). Note that before current state gets to checkpointing step, any * processed instruction always assumes precise SCALAR register/slot * knowledge: if precise value or range is useful to prune jump branch, BPF * verifier takes this opportunity enthusiastically. Similarly, when * register's value is used to calculate offset or memory address, exact * knowledge of SCALAR range is assumed, checked, and enforced. So, similar to * what we mentioned above about state comparison ignoring precise markings * during state comparison, BPF verifier ignores and also assumes precise * markings *at will* during instruction verification process. But as verifier * assumes precision, it also propagates any precision dependencies across * parent states, which are not yet finalized, so can be further restricted * based on new knowledge gained from restrictions enforced by their children * states. This is so that once those parent states are finalized, i.e., when * they have no more active children state, state comparison logic in * is_state_visited() would enforce strict and precise SCALAR ranges, if * required for correctness. * * To build a bit more intuition, note also that once a state is checkpointed, * the path we took to get to that state is not important. This is crucial * property for state pruning. When state is checkpointed and finalized at * some instruction index, it can be correctly and safely used to "short * circuit" any *compatible* state that reaches exactly the same instruction * index. I.e., if we jumped to that instruction from a completely different * code path than original finalized state was derived from, it doesn't * matter, current state can be discarded because from that instruction * forward having a compatible state will ensure we will safely reach the * exit. States describe preconditions for further exploration, but completely * forget the history of how we got here. * * This also means that even if we needed precise SCALAR range to get to * finalized state, but from that point forward *that same* SCALAR register is * never used in a precise context (i.e., it's precise value is not needed for * correctness), it's correct and safe to mark such register as "imprecise" * (i.e., precise marking set to false). This is what we rely on when we do * not set precise marking in current state. If no child state requires * precision for any given SCALAR register, it's safe to dictate that it can * be imprecise. If any child state does require this register to be precise, * we'll mark it precise later retroactively during precise markings * propagation from child state to parent states. * * Skipping precise marking setting in current state is a mild version of * relying on the above observation. But we can utilize this property even * more aggressively by proactively forgetting any precise marking in the * current state (which we inherited from the parent state), right before we * checkpoint it and branch off into new child state. This is done by * mark_all_scalars_imprecise() to hopefully get more permissive and generic * finalized states which help in short circuiting more future states. */ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno) { struct backtrack_state *bt = &env->bt; struct bpf_verifier_state *st = env->cur_state; int first_idx = st->first_insn_idx; int last_idx = env->insn_idx; int subseq_idx = -1; struct bpf_func_state *func; struct bpf_reg_state *reg; bool skip_first = true; int i, fr, err; if (!env->bpf_capable) return 0; /* set frame number from which we are starting to backtrack */ bt_init(bt, env->cur_state->curframe); /* Do sanity checks against current state of register and/or stack * slot, but don't set precise flag in current state, as precision * tracking in the current state is unnecessary. */ func = st->frame[bt->frame]; if (regno >= 0) { reg = &func->regs[regno]; if (reg->type != SCALAR_VALUE) { WARN_ONCE(1, "backtracing misuse"); return -EFAULT; } bt_set_reg(bt, regno); } if (bt_empty(bt)) return 0; for (;;) { DECLARE_BITMAP(mask, 64); u32 history = st->jmp_history_cnt; struct bpf_jmp_history_entry *hist; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n", bt->frame, last_idx, first_idx, subseq_idx); } /* If some register with scalar ID is marked as precise, * make sure that all registers sharing this ID are also precise. * This is needed to estimate effect of find_equal_scalars(). * Do this at the last instruction of each state, * bpf_reg_state::id fields are valid for these instructions. * * Allows to track precision in situation like below: * * r2 = unknown value * ... * --- state #0 --- * ... * r1 = r2 // r1 and r2 now share the same ID * ... * --- state #1 {r1.id = A, r2.id = A} --- * ... * if (r2 > 10) goto exit; // find_equal_scalars() assigns range to r1 * ... * --- state #2 {r1.id = A, r2.id = A} --- * r3 = r10 * r3 += r1 // need to mark both r1 and r2 */ if (mark_precise_scalar_ids(env, st)) return -EFAULT; if (last_idx < 0) { /* we are at the entry into subprog, which * is expected for global funcs, but only if * requested precise registers are R1-R5 * (which are global func's input arguments) */ if (st->curframe == 0 && st->frame[0]->subprogno > 0 && st->frame[0]->callsite == BPF_MAIN_FUNC && bt_stack_mask(bt) == 0 && (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) == 0) { bitmap_from_u64(mask, bt_reg_mask(bt)); for_each_set_bit(i, mask, 32) { reg = &st->frame[0]->regs[i]; bt_clear_reg(bt, i); if (reg->type == SCALAR_VALUE) reg->precise = true; } return 0; } verbose(env, "BUG backtracking func entry subprog %d reg_mask %x stack_mask %llx\n", st->frame[0]->subprogno, bt_reg_mask(bt), bt_stack_mask(bt)); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } for (i = last_idx;;) { if (skip_first) { err = 0; skip_first = false; } else { hist = get_jmp_hist_entry(st, history, i); err = backtrack_insn(env, i, subseq_idx, hist, bt); } if (err == -ENOTSUPP) { mark_all_scalars_precise(env, env->cur_state); bt_reset(bt); return 0; } else if (err) { return err; } if (bt_empty(bt)) /* Found assignment(s) into tracked register in this state. * Since this state is already marked, just return. * Nothing to be tracked further in the parent state. */ return 0; subseq_idx = i; i = get_prev_insn_idx(st, i, &history); if (i == -ENOENT) break; if (i >= env->prog->len) { /* This can happen if backtracking reached insn 0 * and there are still reg_mask or stack_mask * to backtrack. * It means the backtracking missed the spot where * particular register was initialized with a constant. */ verbose(env, "BUG backtracking idx %d\n", i); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } } st = st->parent; if (!st) break; for (fr = bt->frame; fr >= 0; fr--) { func = st->frame[fr]; bitmap_from_u64(mask, bt_frame_reg_mask(bt, fr)); for_each_set_bit(i, mask, 32) { reg = &func->regs[i]; if (reg->type != SCALAR_VALUE) { bt_clear_frame_reg(bt, fr, i); continue; } if (reg->precise) bt_clear_frame_reg(bt, fr, i); else reg->precise = true; } bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr)); for_each_set_bit(i, mask, 64) { if (i >= func->allocated_stack / BPF_REG_SIZE) { verbose(env, "BUG backtracking (stack slot %d, total slots %d)\n", i, func->allocated_stack / BPF_REG_SIZE); WARN_ONCE(1, "verifier backtracking bug (stack slot out of bounds)"); return -EFAULT; } if (!is_spilled_scalar_reg(&func->stack[i])) { bt_clear_frame_slot(bt, fr, i); continue; } reg = &func->stack[i].spilled_ptr; if (reg->precise) bt_clear_frame_slot(bt, fr, i); else reg->precise = true; } if (env->log.level & BPF_LOG_LEVEL2) { fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_frame_reg_mask(bt, fr)); verbose(env, "mark_precise: frame%d: parent state regs=%s ", fr, env->tmp_str_buf); fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_frame_stack_mask(bt, fr)); verbose(env, "stack=%s: ", env->tmp_str_buf); print_verifier_state(env, func, true); } } if (bt_empty(bt)) return 0; subseq_idx = first_idx; last_idx = st->last_insn_idx; first_idx = st->first_insn_idx; } /* if we still have requested precise regs or slots, we missed * something (e.g., stack access through non-r10 register), so * fallback to marking all precise */ if (!bt_empty(bt)) { mark_all_scalars_precise(env, env->cur_state); bt_reset(bt); } return 0; } int mark_chain_precision(struct bpf_verifier_env *env, int regno) { return __mark_chain_precision(env, regno); } /* mark_chain_precision_batch() assumes that env->bt is set in the caller to * desired reg and stack masks across all relevant frames */ static int mark_chain_precision_batch(struct bpf_verifier_env *env) { return __mark_chain_precision(env, -1); } static bool is_spillable_regtype(enum bpf_reg_type type) { switch (base_type(type)) { case PTR_TO_MAP_VALUE: case PTR_TO_STACK: case PTR_TO_CTX: case PTR_TO_PACKET: case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: case PTR_TO_FLOW_KEYS: case CONST_PTR_TO_MAP: case PTR_TO_SOCKET: case PTR_TO_SOCK_COMMON: case PTR_TO_TCP_SOCK: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: case PTR_TO_BUF: case PTR_TO_MEM: case PTR_TO_FUNC: case PTR_TO_MAP_KEY: case PTR_TO_ARENA: return true; default: return false; } } /* Does this register contain a constant zero? */ static bool register_is_null(struct bpf_reg_state *reg) { return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0); } /* check if register is a constant scalar value */ static bool is_reg_const(struct bpf_reg_state *reg, bool subreg32) { return reg->type == SCALAR_VALUE && tnum_is_const(subreg32 ? tnum_subreg(reg->var_off) : reg->var_off); } /* assuming is_reg_const() is true, return constant value of a register */ static u64 reg_const_value(struct bpf_reg_state *reg, bool subreg32) { return subreg32 ? tnum_subreg(reg->var_off).value : reg->var_off.value; } static bool __is_pointer_value(bool allow_ptr_leaks, const struct bpf_reg_state *reg) { if (allow_ptr_leaks) return false; return reg->type != SCALAR_VALUE; } static void assign_scalar_id_before_mov(struct bpf_verifier_env *env, struct bpf_reg_state *src_reg) { if (src_reg->type == SCALAR_VALUE && !src_reg->id && !tnum_is_const(src_reg->var_off)) /* Ensure that src_reg has a valid ID that will be copied to * dst_reg and then will be used by find_equal_scalars() to * propagate min/max range. */ src_reg->id = ++env->id_gen; } /* Copy src state preserving dst->parent and dst->live fields */ static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_state *src) { struct bpf_reg_state *parent = dst->parent; enum bpf_reg_liveness live = dst->live; *dst = *src; dst->parent = parent; dst->live = live; } static void save_register_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int spi, struct bpf_reg_state *reg, int size) { int i; copy_register_state(&state->stack[spi].spilled_ptr, reg); if (size == BPF_REG_SIZE) state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; for (i = BPF_REG_SIZE; i > BPF_REG_SIZE - size; i--) state->stack[spi].slot_type[i - 1] = STACK_SPILL; /* size < 8 bytes spill */ for (; i; i--) mark_stack_slot_misc(env, &state->stack[spi].slot_type[i - 1]); } static bool is_bpf_st_mem(struct bpf_insn *insn) { return BPF_CLASS(insn->code) == BPF_ST && BPF_MODE(insn->code) == BPF_MEM; } static int get_reg_width(struct bpf_reg_state *reg) { return fls64(reg->umax_value); } /* check_stack_{read,write}_fixed_off functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, /* stack frame we're writing to */ struct bpf_func_state *state, int off, int size, int value_regno, int insn_idx) { struct bpf_func_state *cur; /* state of the current function */ int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err; struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; struct bpf_reg_state *reg = NULL; int insn_flags = insn_stack_access_flags(state->frameno, spi); /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, * so it's aligned access and [off, off + size) are within stack limits */ if (!env->allow_ptr_leaks && is_spilled_reg(&state->stack[spi]) && size != BPF_REG_SIZE) { verbose(env, "attempt to corrupt spilled pointer on stack\n"); return -EACCES; } cur = env->cur_state->frame[env->cur_state->curframe]; if (value_regno >= 0) reg = &cur->regs[value_regno]; if (!env->bypass_spec_v4) { bool sanitize = reg && is_spillable_regtype(reg->type); for (i = 0; i < size; i++) { u8 type = state->stack[spi].slot_type[i]; if (type != STACK_MISC && type != STACK_ZERO) { sanitize = true; break; } } if (sanitize) env->insn_aux_data[insn_idx].sanitize_stack_spill = true; } err = destroy_if_dynptr_stack_slot(env, state, spi); if (err) return err; mark_stack_slot_scratched(env, spi); if (reg && !(off % BPF_REG_SIZE) && reg->type == SCALAR_VALUE && env->bpf_capable) { bool reg_value_fits; reg_value_fits = get_reg_width(reg) <= BITS_PER_BYTE * size; /* Make sure that reg had an ID to build a relation on spill. */ if (reg_value_fits) assign_scalar_id_before_mov(env, reg); save_register_state(env, state, spi, reg, size); /* Break the relation on a narrowing spill. */ if (!reg_value_fits) state->stack[spi].spilled_ptr.id = 0; } else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) && env->bpf_capable) { struct bpf_reg_state *tmp_reg = &env->fake_reg[0]; memset(tmp_reg, 0, sizeof(*tmp_reg)); __mark_reg_known(tmp_reg, insn->imm); tmp_reg->type = SCALAR_VALUE; save_register_state(env, state, spi, tmp_reg, size); } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { verbose_linfo(env, insn_idx, "; "); verbose(env, "invalid size of register spill\n"); return -EACCES; } if (state != cur && reg->type == PTR_TO_STACK) { verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } save_register_state(env, state, spi, reg, size); } else { u8 type = STACK_MISC; /* regular write of data into stack destroys any spilled ptr */ state->stack[spi].spilled_ptr.type = NOT_INIT; /* Mark slots as STACK_MISC if they belonged to spilled ptr/dynptr/iter. */ if (is_stack_slot_special(&state->stack[spi])) for (i = 0; i < BPF_REG_SIZE; i++) scrub_spilled_slot(&state->stack[spi].slot_type[i]); /* only mark the slot as written if all 8 bytes were written * otherwise read propagation may incorrectly stop too soon * when stack slots are partially written. * This heuristic means that read propagation will be * conservative, since it will add reg_live_read marks * to stack slots all the way to first state when programs * writes+reads less than 8 bytes */ if (size == BPF_REG_SIZE) state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; /* when we zero initialize stack slots mark them as such */ if ((reg && register_is_null(reg)) || (!reg && is_bpf_st_mem(insn) && insn->imm == 0)) { /* STACK_ZERO case happened because register spill * wasn't properly aligned at the stack slot boundary, * so it's not a register spill anymore; force * originating register to be precise to make * STACK_ZERO correct for subsequent states */ err = mark_chain_precision(env, value_regno); if (err) return err; type = STACK_ZERO; } /* Mark slots affected by this stack write. */ for (i = 0; i < size; i++) state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = type; insn_flags = 0; /* not a register spill */ } if (insn_flags) return push_jmp_history(env, env->cur_state, insn_flags); return 0; } /* Write the stack: 'stack[ptr_regno + off] = value_regno'. 'ptr_regno' is * known to contain a variable offset. * This function checks whether the write is permitted and conservatively * tracks the effects of the write, considering that each stack slot in the * dynamic range is potentially written to. * * 'off' includes 'regno->off'. * 'value_regno' can be -1, meaning that an unknown value is being written to * the stack. * * Spilled pointers in range are not marked as written because we don't know * what's going to be actually written. This means that read propagation for * future reads cannot be terminated by this write. * * For privileged programs, uninitialized stack slots are considered * initialized by this write (even though we don't know exactly what offsets * are going to be written to). The idea is that we don't want the verifier to * reject future reads that access slots written to through variable offsets. */ static int check_stack_write_var_off(struct bpf_verifier_env *env, /* func where register points to */ struct bpf_func_state *state, int ptr_regno, int off, int size, int value_regno, int insn_idx) { struct bpf_func_state *cur; /* state of the current function */ int min_off, max_off; int i, err; struct bpf_reg_state *ptr_reg = NULL, *value_reg = NULL; struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; bool writing_zero = false; /* set if the fact that we're writing a zero is used to let any * stack slots remain STACK_ZERO */ bool zero_used = false; cur = env->cur_state->frame[env->cur_state->curframe]; ptr_reg = &cur->regs[ptr_regno]; min_off = ptr_reg->smin_value + off; max_off = ptr_reg->smax_value + off + size; if (value_regno >= 0) value_reg = &cur->regs[value_regno]; if ((value_reg && register_is_null(value_reg)) || (!value_reg && is_bpf_st_mem(insn) && insn->imm == 0)) writing_zero = true; for (i = min_off; i < max_off; i++) { int spi; spi = __get_spi(i); err = destroy_if_dynptr_stack_slot(env, state, spi); if (err) return err; } /* Variable offset writes destroy any spilled pointers in range. */ for (i = min_off; i < max_off; i++) { u8 new_type, *stype; int slot, spi; slot = -i - 1; spi = slot / BPF_REG_SIZE; stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE]; mark_stack_slot_scratched(env, spi); if (!env->allow_ptr_leaks && *stype != STACK_MISC && *stype != STACK_ZERO) { /* Reject the write if range we may write to has not * been initialized beforehand. If we didn't reject * here, the ptr status would be erased below (even * though not all slots are actually overwritten), * possibly opening the door to leaks. * * We do however catch STACK_INVALID case below, and * only allow reading possibly uninitialized memory * later for CAP_PERFMON, as the write may not happen to * that slot. */ verbose(env, "spilled ptr in range of var-offset stack write; insn %d, ptr off: %d", insn_idx, i); return -EINVAL; } /* If writing_zero and the spi slot contains a spill of value 0, * maintain the spill type. */ if (writing_zero && *stype == STACK_SPILL && is_spilled_scalar_reg(&state->stack[spi])) { struct bpf_reg_state *spill_reg = &state->stack[spi].spilled_ptr; if (tnum_is_const(spill_reg->var_off) && spill_reg->var_off.value == 0) { zero_used = true; continue; } } /* Erase all other spilled pointers. */ state->stack[spi].spilled_ptr.type = NOT_INIT; /* Update the slot type. */ new_type = STACK_MISC; if (writing_zero && *stype == STACK_ZERO) { new_type = STACK_ZERO; zero_used = true; } /* If the slot is STACK_INVALID, we check whether it's OK to * pretend that it will be initialized by this write. The slot * might not actually be written to, and so if we mark it as * initialized future reads might leak uninitialized memory. * For privileged programs, we will accept such reads to slots * that may or may not be written because, if we're reject * them, the error would be too confusing. */ if (*stype == STACK_INVALID && !env->allow_uninit_stack) { verbose(env, "uninit stack in range of var-offset write prohibited for !root; insn %d, off: %d", insn_idx, i); return -EINVAL; } *stype = new_type; } if (zero_used) { /* backtracking doesn't work for STACK_ZERO yet. */ err = mark_chain_precision(env, value_regno); if (err) return err; } return 0; } /* When register 'dst_regno' is assigned some values from stack[min_off, * max_off), we set the register's type according to the types of the * respective stack slots. If all the stack values are known to be zeros, then * so is the destination reg. Otherwise, the register is considered to be * SCALAR. This function does not deal with register filling; the caller must * ensure that all spilled registers in the stack range have been marked as * read. */ static void mark_reg_stack_read(struct bpf_verifier_env *env, /* func where src register points to */ struct bpf_func_state *ptr_state, int min_off, int max_off, int dst_regno) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; int i, slot, spi; u8 *stype; int zeros = 0; for (i = min_off; i < max_off; i++) { slot = -i - 1; spi = slot / BPF_REG_SIZE; mark_stack_slot_scratched(env, spi); stype = ptr_state->stack[spi].slot_type; if (stype[slot % BPF_REG_SIZE] != STACK_ZERO) break; zeros++; } if (zeros == max_off - min_off) { /* Any access_size read into register is zero extended, * so the whole register == const_zero. */ __mark_reg_const_zero(env, &state->regs[dst_regno]); } else { /* have read misc data from the stack */ mark_reg_unknown(env, state->regs, dst_regno); } state->regs[dst_regno].live |= REG_LIVE_WRITTEN; } /* Read the stack at 'off' and put the results into the register indicated by * 'dst_regno'. It handles reg filling if the addressed stack slot is a * spilled reg. * * 'dst_regno' can be -1, meaning that the read value is not going to a * register. * * The access is assumed to be within the current stack bounds. */ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, /* func where src register points to */ struct bpf_func_state *reg_state, int off, int size, int dst_regno) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; int i, slot = -off - 1, spi = slot / BPF_REG_SIZE; struct bpf_reg_state *reg; u8 *stype, type; int insn_flags = insn_stack_access_flags(reg_state->frameno, spi); stype = reg_state->stack[spi].slot_type; reg = ®_state->stack[spi].spilled_ptr; mark_stack_slot_scratched(env, spi); if (is_spilled_reg(®_state->stack[spi])) { u8 spill_size = 1; for (i = BPF_REG_SIZE - 1; i > 0 && stype[i - 1] == STACK_SPILL; i--) spill_size++; if (size != BPF_REG_SIZE || spill_size != BPF_REG_SIZE) { if (reg->type != SCALAR_VALUE) { verbose_linfo(env, env->insn_idx, "; "); verbose(env, "invalid size of register fill\n"); return -EACCES; } mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); if (dst_regno < 0) return 0; if (size <= spill_size && bpf_stack_narrow_access_ok(off, size, spill_size)) { /* The earlier check_reg_arg() has decided the * subreg_def for this insn. Save it first. */ s32 subreg_def = state->regs[dst_regno].subreg_def; copy_register_state(&state->regs[dst_regno], reg); state->regs[dst_regno].subreg_def = subreg_def; /* Break the relation on a narrowing fill. * coerce_reg_to_size will adjust the boundaries. */ if (get_reg_width(reg) > size * BITS_PER_BYTE) state->regs[dst_regno].id = 0; } else { int spill_cnt = 0, zero_cnt = 0; for (i = 0; i < size; i++) { type = stype[(slot - i) % BPF_REG_SIZE]; if (type == STACK_SPILL) { spill_cnt++; continue; } if (type == STACK_MISC) continue; if (type == STACK_ZERO) { zero_cnt++; continue; } if (type == STACK_INVALID && env->allow_uninit_stack) continue; verbose(env, "invalid read from stack off %d+%d size %d\n", off, i, size); return -EACCES; } if (spill_cnt == size && tnum_is_const(reg->var_off) && reg->var_off.value == 0) { __mark_reg_const_zero(env, &state->regs[dst_regno]); /* this IS register fill, so keep insn_flags */ } else if (zero_cnt == size) { /* similarly to mark_reg_stack_read(), preserve zeroes */ __mark_reg_const_zero(env, &state->regs[dst_regno]); insn_flags = 0; /* not restoring original register state */ } else { mark_reg_unknown(env, state->regs, dst_regno); insn_flags = 0; /* not restoring original register state */ } } state->regs[dst_regno].live |= REG_LIVE_WRITTEN; } else if (dst_regno >= 0) { /* restore register state from stack */ copy_register_state(&state->regs[dst_regno], reg); /* mark reg as written since spilled pointer state likely * has its liveness marks cleared by is_state_visited() * which resets stack/reg liveness for state transitions */ state->regs[dst_regno].live |= REG_LIVE_WRITTEN; } else if (__is_pointer_value(env->allow_ptr_leaks, reg)) { /* If dst_regno==-1, the caller is asking us whether * it is acceptable to use this value as a SCALAR_VALUE * (e.g. for XADD). * We must not allow unprivileged callers to do that * with spilled pointers. */ verbose(env, "leaking pointer from stack off %d\n", off); return -EACCES; } mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); } else { for (i = 0; i < size; i++) { type = stype[(slot - i) % BPF_REG_SIZE]; if (type == STACK_MISC) continue; if (type == STACK_ZERO) continue; if (type == STACK_INVALID && env->allow_uninit_stack) continue; verbose(env, "invalid read from stack off %d+%d size %d\n", off, i, size); return -EACCES; } mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); if (dst_regno >= 0) mark_reg_stack_read(env, reg_state, off, off + size, dst_regno); insn_flags = 0; /* we are not restoring spilled register */ } if (insn_flags) return push_jmp_history(env, env->cur_state, insn_flags); return 0; } enum bpf_access_src { ACCESS_DIRECT = 1, /* the access is performed by an instruction */ ACCESS_HELPER = 2, /* the access is performed by a helper */ }; static int check_stack_range_initialized(struct bpf_verifier_env *env, int regno, int off, int access_size, bool zero_size_allowed, enum bpf_access_src type, struct bpf_call_arg_meta *meta); static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno) { return cur_regs(env) + regno; } /* Read the stack at 'ptr_regno + off' and put the result into the register * 'dst_regno'. * 'off' includes the pointer register's fixed offset(i.e. 'ptr_regno.off'), * but not its variable offset. * 'size' is assumed to be <= reg size and the access is assumed to be aligned. * * As opposed to check_stack_read_fixed_off, this function doesn't deal with * filling registers (i.e. reads of spilled register cannot be detected when * the offset is not fixed). We conservatively mark 'dst_regno' as containing * SCALAR_VALUE. That's why we assert that the 'ptr_regno' has a variable * offset; for a fixed offset check_stack_read_fixed_off should be used * instead. */ static int check_stack_read_var_off(struct bpf_verifier_env *env, int ptr_regno, int off, int size, int dst_regno) { /* The state of the source register. */ struct bpf_reg_state *reg = reg_state(env, ptr_regno); struct bpf_func_state *ptr_state = func(env, reg); int err; int min_off, max_off; /* Note that we pass a NULL meta, so raw access will not be permitted. */ err = check_stack_range_initialized(env, ptr_regno, off, size, false, ACCESS_DIRECT, NULL); if (err) return err; min_off = reg->smin_value + off; max_off = reg->smax_value + off; mark_reg_stack_read(env, ptr_state, min_off, max_off + size, dst_regno); return 0; } /* check_stack_read dispatches to check_stack_read_fixed_off or * check_stack_read_var_off. * * The caller must ensure that the offset falls within the allocated stack * bounds. * * 'dst_regno' is a register which will receive the value from the stack. It * can be -1, meaning that the read value is not going to a register. */ static int check_stack_read(struct bpf_verifier_env *env, int ptr_regno, int off, int size, int dst_regno) { struct bpf_reg_state *reg = reg_state(env, ptr_regno); struct bpf_func_state *state = func(env, reg); int err; /* Some accesses are only permitted with a static offset. */ bool var_off = !tnum_is_const(reg->var_off); /* The offset is required to be static when reads don't go to a * register, in order to not leak pointers (see * check_stack_read_fixed_off). */ if (dst_regno < 0 && var_off) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "variable offset stack pointer cannot be passed into helper function; var_off=%s off=%d size=%d\n", tn_buf, off, size); return -EACCES; } /* Variable offset is prohibited for unprivileged mode for simplicity * since it requires corresponding support in Spectre masking for stack * ALU. See also retrieve_ptr_limit(). The check in * check_stack_access_for_ptr_arithmetic() called by * adjust_ptr_min_max_vals() prevents users from creating stack pointers * with variable offsets, therefore no check is required here. Further, * just checking it here would be insufficient as speculative stack * writes could still lead to unsafe speculative behaviour. */ if (!var_off) { off += reg->var_off.value; err = check_stack_read_fixed_off(env, state, off, size, dst_regno); } else { /* Variable offset stack reads need more conservative handling * than fixed offset ones. Note that dst_regno >= 0 on this * branch. */ err = check_stack_read_var_off(env, ptr_regno, off, size, dst_regno); } return err; } /* check_stack_write dispatches to check_stack_write_fixed_off or * check_stack_write_var_off. * * 'ptr_regno' is the register used as a pointer into the stack. * 'off' includes 'ptr_regno->off', but not its variable offset (if any). * 'value_regno' is the register whose value we're writing to the stack. It can * be -1, meaning that we're not writing from a register. * * The caller must ensure that the offset falls within the maximum stack size. */ static int check_stack_write(struct bpf_verifier_env *env, int ptr_regno, int off, int size, int value_regno, int insn_idx) { struct bpf_reg_state *reg = reg_state(env, ptr_regno); struct bpf_func_state *state = func(env, reg); int err; if (tnum_is_const(reg->var_off)) { off += reg->var_off.value; err = check_stack_write_fixed_off(env, state, off, size, value_regno, insn_idx); } else { /* Variable offset stack reads need more conservative handling * than fixed offset ones. */ err = check_stack_write_var_off(env, state, ptr_regno, off, size, value_regno, insn_idx); } return err; } static int check_map_access_type(struct bpf_verifier_env *env, u32 regno, int off, int size, enum bpf_access_type type) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_map *map = regs[regno].map_ptr; u32 cap = bpf_map_flags_to_cap(map); if (type == BPF_WRITE && !(cap & BPF_MAP_CAN_WRITE)) { verbose(env, "write into map forbidden, value_size=%d off=%d size=%d\n", map->value_size, off, size); return -EACCES; } if (type == BPF_READ && !(cap & BPF_MAP_CAN_READ)) { verbose(env, "read from map forbidden, value_size=%d off=%d size=%d\n", map->value_size, off, size); return -EACCES; } return 0; } /* check read/write into memory region (e.g., map value, ringbuf sample, etc) */ static int __check_mem_access(struct bpf_verifier_env *env, int regno, int off, int size, u32 mem_size, bool zero_size_allowed) { bool size_ok = size > 0 || (size == 0 && zero_size_allowed); struct bpf_reg_state *reg; if (off >= 0 && size_ok && (u64)off + size <= mem_size) return 0; reg = &cur_regs(env)[regno]; switch (reg->type) { case PTR_TO_MAP_KEY: verbose(env, "invalid access to map key, key_size=%d off=%d size=%d\n", mem_size, off, size); break; case PTR_TO_MAP_VALUE: verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n", mem_size, off, size); break; case PTR_TO_PACKET: case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n", off, size, regno, reg->id, off, mem_size); break; case PTR_TO_MEM: default: verbose(env, "invalid access to memory, mem_size=%u off=%d size=%d\n", mem_size, off, size); } return -EACCES; } /* check read/write into a memory region with possible variable offset */ static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno, int off, int size, u32 mem_size, bool zero_size_allowed) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regno]; int err; /* We may have adjusted the register pointing to memory region, so we * need to try adding each of min_value and max_value to off * to make sure our theoretical access will be safe. * * The minimum value is only important with signed * comparisons where we can't assume the floor of a * value is 0. If we are using signed variables for our * index'es we need to make sure that whatever we use * will have a set floor within our range. */ if (reg->smin_value < 0 && (reg->smin_value == S64_MIN || (off + reg->smin_value != (s64)(s32)(off + reg->smin_value)) || reg->smin_value + off < 0)) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } err = __check_mem_access(env, regno, reg->smin_value + off, size, mem_size, zero_size_allowed); if (err) { verbose(env, "R%d min value is outside of the allowed memory range\n", regno); return err; } /* If we haven't set a max value then we need to bail since we can't be * sure we won't do bad things. * If reg->umax_value + off could overflow, treat that as unbounded too. */ if (reg->umax_value >= BPF_MAX_VAR_OFF) { verbose(env, "R%d unbounded memory access, make sure to bounds check any such access\n", regno); return -EACCES; } err = __check_mem_access(env, regno, reg->umax_value + off, size, mem_size, zero_size_allowed); if (err) { verbose(env, "R%d max value is outside of the allowed memory range\n", regno); return err; } return 0; } static int __check_ptr_off_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, bool fixed_off_ok) { /* Access to this pointer-typed register or passing it to a helper * is only allowed in its original, unmodified form. */ if (reg->off < 0) { verbose(env, "negative offset %s ptr R%d off=%d disallowed\n", reg_type_str(env, reg->type), regno, reg->off); return -EACCES; } if (!fixed_off_ok && reg->off) { verbose(env, "dereference of modified %s ptr R%d off=%d disallowed\n", reg_type_str(env, reg->type), regno, reg->off); return -EACCES; } if (!tnum_is_const(reg->var_off) || reg->var_off.value) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "variable %s access var_off=%s disallowed\n", reg_type_str(env, reg->type), tn_buf); return -EACCES; } return 0; } static int check_ptr_off_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno) { return __check_ptr_off_reg(env, reg, regno, false); } static int map_kptr_match_type(struct bpf_verifier_env *env, struct btf_field *kptr_field, struct bpf_reg_state *reg, u32 regno) { const char *targ_name = btf_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id); int perm_flags; const char *reg_name = ""; if (btf_is_kernel(reg->btf)) { perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED | MEM_RCU; /* Only unreferenced case accepts untrusted pointers */ if (kptr_field->type == BPF_KPTR_UNREF) perm_flags |= PTR_UNTRUSTED; } else { perm_flags = PTR_MAYBE_NULL | MEM_ALLOC; if (kptr_field->type == BPF_KPTR_PERCPU) perm_flags |= MEM_PERCPU; } if (base_type(reg->type) != PTR_TO_BTF_ID || (type_flag(reg->type) & ~perm_flags)) goto bad_type; /* We need to verify reg->type and reg->btf, before accessing reg->btf */ reg_name = btf_type_name(reg->btf, reg->btf_id); /* For ref_ptr case, release function check should ensure we get one * referenced PTR_TO_BTF_ID, and that its fixed offset is 0. For the * normal store of unreferenced kptr, we must ensure var_off is zero. * Since ref_ptr cannot be accessed directly by BPF insns, checks for * reg->off and reg->ref_obj_id are not needed here. */ if (__check_ptr_off_reg(env, reg, regno, true)) return -EACCES; /* A full type match is needed, as BTF can be vmlinux, module or prog BTF, and * we also need to take into account the reg->off. * * We want to support cases like: * * struct foo { * struct bar br; * struct baz bz; * }; * * struct foo *v; * v = func(); // PTR_TO_BTF_ID * val->foo = v; // reg->off is zero, btf and btf_id match type * val->bar = &v->br; // reg->off is still zero, but we need to retry with * // first member type of struct after comparison fails * val->baz = &v->bz; // reg->off is non-zero, so struct needs to be walked * // to match type * * In the kptr_ref case, check_func_arg_reg_off already ensures reg->off * is zero. We must also ensure that btf_struct_ids_match does not walk * the struct to match type against first member of struct, i.e. reject * second case from above. Hence, when type is BPF_KPTR_REF, we set * strict mode to true for type match. */ if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off, kptr_field->kptr.btf, kptr_field->kptr.btf_id, kptr_field->type != BPF_KPTR_UNREF)) goto bad_type; return 0; bad_type: verbose(env, "invalid kptr access, R%d type=%s%s ", regno, reg_type_str(env, reg->type), reg_name); verbose(env, "expected=%s%s", reg_type_str(env, PTR_TO_BTF_ID), targ_name); if (kptr_field->type == BPF_KPTR_UNREF) verbose(env, " or %s%s\n", reg_type_str(env, PTR_TO_BTF_ID | PTR_UNTRUSTED), targ_name); else verbose(env, "\n"); return -EINVAL; } static bool in_sleepable(struct bpf_verifier_env *env) { return env->prog->sleepable || (env->cur_state && env->cur_state->in_sleepable); } /* The non-sleepable programs and sleepable programs with explicit bpf_rcu_read_lock() * can dereference RCU protected pointers and result is PTR_TRUSTED. */ static bool in_rcu_cs(struct bpf_verifier_env *env) { return env->cur_state->active_rcu_lock || env->cur_state->active_lock.ptr || !in_sleepable(env); } /* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */ BTF_SET_START(rcu_protected_types) BTF_ID(struct, prog_test_ref_kfunc) #ifdef CONFIG_CGROUPS BTF_ID(struct, cgroup) #endif #ifdef CONFIG_BPF_JIT BTF_ID(struct, bpf_cpumask) #endif BTF_ID(struct, task_struct) BTF_ID(struct, bpf_crypto_ctx) BTF_SET_END(rcu_protected_types) static bool rcu_protected_object(const struct btf *btf, u32 btf_id) { if (!btf_is_kernel(btf)) return true; return btf_id_set_contains(&rcu_protected_types, btf_id); } static struct btf_record *kptr_pointee_btf_record(struct btf_field *kptr_field) { struct btf_struct_meta *meta; if (btf_is_kernel(kptr_field->kptr.btf)) return NULL; meta = btf_find_struct_meta(kptr_field->kptr.btf, kptr_field->kptr.btf_id); return meta ? meta->record : NULL; } static bool rcu_safe_kptr(const struct btf_field *field) { const struct btf_field_kptr *kptr = &field->kptr; return field->type == BPF_KPTR_PERCPU || (field->type == BPF_KPTR_REF && rcu_protected_object(kptr->btf, kptr->btf_id)); } static u32 btf_ld_kptr_type(struct bpf_verifier_env *env, struct btf_field *kptr_field) { struct btf_record *rec; u32 ret; ret = PTR_MAYBE_NULL; if (rcu_safe_kptr(kptr_field) && in_rcu_cs(env)) { ret |= MEM_RCU; if (kptr_field->type == BPF_KPTR_PERCPU) ret |= MEM_PERCPU; else if (!btf_is_kernel(kptr_field->kptr.btf)) ret |= MEM_ALLOC; rec = kptr_pointee_btf_record(kptr_field); if (rec && btf_record_has_field(rec, BPF_GRAPH_NODE)) ret |= NON_OWN_REF; } else { ret |= PTR_UNTRUSTED; } return ret; } static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, int value_regno, int insn_idx, struct btf_field *kptr_field) { struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; int class = BPF_CLASS(insn->code); struct bpf_reg_state *val_reg; /* Things we already checked for in check_map_access and caller: * - Reject cases where variable offset may touch kptr * - size of access (must be BPF_DW) * - tnum_is_const(reg->var_off) * - kptr_field->offset == off + reg->var_off.value */ /* Only BPF_[LDX,STX,ST] | BPF_MEM | BPF_DW is supported */ if (BPF_MODE(insn->code) != BPF_MEM) { verbose(env, "kptr in map can only be accessed using BPF_MEM instruction mode\n"); return -EACCES; } /* We only allow loading referenced kptr, since it will be marked as * untrusted, similar to unreferenced kptr. */ if (class != BPF_LDX && (kptr_field->type == BPF_KPTR_REF || kptr_field->type == BPF_KPTR_PERCPU)) { verbose(env, "store to referenced kptr disallowed\n"); return -EACCES; } if (class == BPF_LDX) { val_reg = reg_state(env, value_regno); /* We can simply mark the value_regno receiving the pointer * value from map as PTR_TO_BTF_ID, with the correct type. */ mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, kptr_field->kptr.btf, kptr_field->kptr.btf_id, btf_ld_kptr_type(env, kptr_field)); } else if (class == BPF_STX) { val_reg = reg_state(env, value_regno); if (!register_is_null(val_reg) && map_kptr_match_type(env, kptr_field, val_reg, value_regno)) return -EACCES; } else if (class == BPF_ST) { if (insn->imm) { verbose(env, "BPF_ST imm must be 0 when storing to kptr at off=%u\n", kptr_field->offset); return -EACCES; } } else { verbose(env, "kptr in map can only be accessed using BPF_LDX/BPF_STX/BPF_ST\n"); return -EACCES; } return 0; } /* check read/write into a map element with possible variable offset */ static int check_map_access(struct bpf_verifier_env *env, u32 regno, int off, int size, bool zero_size_allowed, enum bpf_access_src src) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regno]; struct bpf_map *map = reg->map_ptr; struct btf_record *rec; int err, i; err = check_mem_region_access(env, regno, off, size, map->value_size, zero_size_allowed); if (err) return err; if (IS_ERR_OR_NULL(map->record)) return 0; rec = map->record; for (i = 0; i < rec->cnt; i++) { struct btf_field *field = &rec->fields[i]; u32 p = field->offset; /* If any part of a field can be touched by load/store, reject * this program. To check that [x1, x2) overlaps with [y1, y2), * it is sufficient to check x1 < y2 && y1 < x2. */ if (reg->smin_value + off < p + btf_field_type_size(field->type) && p < reg->umax_value + off + size) { switch (field->type) { case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: if (src != ACCESS_DIRECT) { verbose(env, "kptr cannot be accessed indirectly by helper\n"); return -EACCES; } if (!tnum_is_const(reg->var_off)) { verbose(env, "kptr access cannot have variable offset\n"); return -EACCES; } if (p != off + reg->var_off.value) { verbose(env, "kptr access misaligned expected=%u off=%llu\n", p, off + reg->var_off.value); return -EACCES; } if (size != bpf_size_to_bytes(BPF_DW)) { verbose(env, "kptr access size must be BPF_DW\n"); return -EACCES; } break; default: verbose(env, "%s cannot be accessed directly by load/store\n", btf_field_type_name(field->type)); return -EACCES; } } } return 0; } #define MAX_PACKET_OFF 0xffff static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, const struct bpf_call_arg_meta *meta, enum bpf_access_type t) { enum bpf_prog_type prog_type = resolve_prog_type(env->prog); switch (prog_type) { /* Program types only with direct read access go here! */ case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_SEG6LOCAL: case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SKB: if (t == BPF_WRITE) return false; fallthrough; /* Program types with direct read + write access go here! */ case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_LWT_XMIT: case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: if (meta) return meta->pkt_access; env->seen_direct_write = true; return true; case BPF_PROG_TYPE_CGROUP_SOCKOPT: if (t == BPF_WRITE) env->seen_direct_write = true; return true; default: return false; } } static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, int size, bool zero_size_allowed) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[regno]; int err; /* We may have added a variable offset to the packet pointer; but any * reg->range we have comes after that. We are only checking the fixed * offset. */ /* We don't allow negative numbers, because we aren't tracking enough * detail to prove they're safe. */ if (reg->smin_value < 0) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } err = reg->range < 0 ? -EINVAL : __check_mem_access(env, regno, off, size, reg->range, zero_size_allowed); if (err) { verbose(env, "R%d offset is outside of the packet\n", regno); return err; } /* __check_mem_access has made sure "off + size - 1" is within u16. * reg->umax_value can't be bigger than MAX_PACKET_OFF which is 0xffff, * otherwise find_good_pkt_pointers would have refused to set range info * that __check_mem_access would have rejected this pkt access. * Therefore, "off + reg->umax_value + size - 1" won't overflow u32. */ env->prog->aux->max_pkt_offset = max_t(u32, env->prog->aux->max_pkt_offset, off + reg->umax_value + size - 1); return err; } /* check access to 'struct bpf_context' fields. Supports fixed offsets only */ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size, enum bpf_access_type t, enum bpf_reg_type *reg_type, struct btf **btf, u32 *btf_id) { struct bpf_insn_access_aux info = { .reg_type = *reg_type, .log = &env->log, }; if (env->ops->is_valid_access && env->ops->is_valid_access(off, size, t, env->prog, &info)) { /* A non zero info.ctx_field_size indicates that this field is a * candidate for later verifier transformation to load the whole * field and then apply a mask when accessed with a narrower * access than actual ctx access size. A zero info.ctx_field_size * will only allow for whole field access and rejects any other * type of narrower access. */ *reg_type = info.reg_type; if (base_type(*reg_type) == PTR_TO_BTF_ID) { *btf = info.btf; *btf_id = info.btf_id; } else { env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; } /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) env->prog->aux->max_ctx_offset = off + size; return 0; } verbose(env, "invalid bpf_context access off=%d size=%d\n", off, size); return -EACCES; } static int check_flow_keys_access(struct bpf_verifier_env *env, int off, int size) { if (size < 0 || off < 0 || (u64)off + size > sizeof(struct bpf_flow_keys)) { verbose(env, "invalid access to flow keys off=%d size=%d\n", off, size); return -EACCES; } return 0; } static int check_sock_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off, int size, enum bpf_access_type t) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[regno]; struct bpf_insn_access_aux info = {}; bool valid; if (reg->smin_value < 0) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } switch (reg->type) { case PTR_TO_SOCK_COMMON: valid = bpf_sock_common_is_valid_access(off, size, t, &info); break; case PTR_TO_SOCKET: valid = bpf_sock_is_valid_access(off, size, t, &info); break; case PTR_TO_TCP_SOCK: valid = bpf_tcp_sock_is_valid_access(off, size, t, &info); break; case PTR_TO_XDP_SOCK: valid = bpf_xdp_sock_is_valid_access(off, size, t, &info); break; default: valid = false; } if (valid) { env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; return 0; } verbose(env, "R%d invalid %s access off=%d size=%d\n", regno, reg_type_str(env, reg->type), off, size); return -EACCES; } static bool is_pointer_value(struct bpf_verifier_env *env, int regno) { return __is_pointer_value(env->allow_ptr_leaks, reg_state(env, regno)); } static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); return reg->type == PTR_TO_CTX; } static bool is_sk_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); return type_is_sk_pointer(reg->type); } static bool is_pkt_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); return type_is_pkt_pointer(reg->type); } static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); /* Separate to is_ctx_reg() since we still want to allow BPF_ST here. */ return reg->type == PTR_TO_FLOW_KEYS; } static bool is_arena_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); return reg->type == PTR_TO_ARENA; } static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { #ifdef CONFIG_NET [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP], #endif [CONST_PTR_TO_MAP] = btf_bpf_map_id, }; static bool is_trusted_reg(const struct bpf_reg_state *reg) { /* A referenced register is always trusted. */ if (reg->ref_obj_id) return true; /* Types listed in the reg2btf_ids are always trusted */ if (reg2btf_ids[base_type(reg->type)] && !bpf_type_has_unsafe_modifiers(reg->type)) return true; /* If a register is not referenced, it is trusted if it has the * MEM_ALLOC or PTR_TRUSTED type modifiers, and no others. Some of the * other type modifiers may be safe, but we elect to take an opt-in * approach here as some (e.g. PTR_UNTRUSTED and PTR_MAYBE_NULL) are * not. * * Eventually, we should make PTR_TRUSTED the single source of truth * for whether a register is trusted. */ return type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS && !bpf_type_has_unsafe_modifiers(reg->type); } static bool is_rcu_reg(const struct bpf_reg_state *reg) { return reg->type & MEM_RCU; } static void clear_trusted_flags(enum bpf_type_flag *flag) { *flag &= ~(BPF_REG_TRUSTED_MODIFIERS | MEM_RCU); } static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict) { struct tnum reg_off; int ip_align; /* Byte size accesses are always allowed. */ if (!strict || size == 1) return 0; /* For platforms that do not have a Kconfig enabling * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS the value of * NET_IP_ALIGN is universally set to '2'. And on platforms * that do set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS, we get * to this code only in strict mode where we want to emulate * the NET_IP_ALIGN==2 checking. Therefore use an * unconditional IP align value of '2'. */ ip_align = 2; reg_off = tnum_add(reg->var_off, tnum_const(ip_align + reg->off + off)); if (!tnum_is_aligned(reg_off, size)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "misaligned packet access off %d+%s+%d+%d size %d\n", ip_align, tn_buf, reg->off, off, size); return -EACCES; } return 0; } static int check_generic_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, const char *pointer_desc, int off, int size, bool strict) { struct tnum reg_off; /* Byte size accesses are always allowed. */ if (!strict || size == 1) return 0; reg_off = tnum_add(reg->var_off, tnum_const(reg->off + off)); if (!tnum_is_aligned(reg_off, size)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "misaligned %saccess off %s+%d+%d size %d\n", pointer_desc, tn_buf, reg->off, off, size); return -EACCES; } return 0; } static int check_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict_alignment_once) { bool strict = env->strict_alignment || strict_alignment_once; const char *pointer_desc = ""; switch (reg->type) { case PTR_TO_PACKET: case PTR_TO_PACKET_META: /* Special case, because of NET_IP_ALIGN. Given metadata sits * right in front, treat it the very same way. */ return check_pkt_ptr_alignment(env, reg, off, size, strict); case PTR_TO_FLOW_KEYS: pointer_desc = "flow keys "; break; case PTR_TO_MAP_KEY: pointer_desc = "key "; break; case PTR_TO_MAP_VALUE: pointer_desc = "value "; break; case PTR_TO_CTX: pointer_desc = "context "; break; case PTR_TO_STACK: pointer_desc = "stack "; /* The stack spill tracking logic in check_stack_write_fixed_off() * and check_stack_read_fixed_off() relies on stack accesses being * aligned. */ strict = true; break; case PTR_TO_SOCKET: pointer_desc = "sock "; break; case PTR_TO_SOCK_COMMON: pointer_desc = "sock_common "; break; case PTR_TO_TCP_SOCK: pointer_desc = "tcp_sock "; break; case PTR_TO_XDP_SOCK: pointer_desc = "xdp_sock "; break; case PTR_TO_ARENA: return 0; default: break; } return check_generic_ptr_alignment(env, reg, pointer_desc, off, size, strict); } static int round_up_stack_depth(struct bpf_verifier_env *env, int stack_depth) { if (env->prog->jit_requested) return round_up(stack_depth, 16); /* round up to 32-bytes, since this is granularity * of interpreter stack size */ return round_up(max_t(u32, stack_depth, 1), 32); } /* starting from main bpf function walk all instructions of the function * and recursively walk all callees that given function can call. * Ignore jump and exit insns. * Since recursion is prevented by check_cfg() this algorithm * only needs a local stack of MAX_CALL_FRAMES to remember callsites */ static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx) { struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; int depth = 0, frame = 0, i, subprog_end; bool tail_call_reachable = false; int ret_insn[MAX_CALL_FRAMES]; int ret_prog[MAX_CALL_FRAMES]; int j; i = subprog[idx].start; process_func: /* protect against potential stack overflow that might happen when * bpf2bpf calls get combined with tailcalls. Limit the caller's stack * depth for such case down to 256 so that the worst case scenario * would result in 8k stack size (32 which is tailcall limit * 256 = * 8k). * * To get the idea what might happen, see an example: * func1 -> sub rsp, 128 * subfunc1 -> sub rsp, 256 * tailcall1 -> add rsp, 256 * func2 -> sub rsp, 192 (total stack size = 128 + 192 = 320) * subfunc2 -> sub rsp, 64 * subfunc22 -> sub rsp, 128 * tailcall2 -> add rsp, 128 * func3 -> sub rsp, 32 (total stack size 128 + 192 + 64 + 32 = 416) * * tailcall will unwind the current stack frame but it will not get rid * of caller's stack as shown on the example above. */ if (idx && subprog[idx].has_tail_call && depth >= 256) { verbose(env, "tail_calls are not allowed when call stack of previous frames is %d bytes. Too large\n", depth); return -EACCES; } depth += round_up_stack_depth(env, subprog[idx].stack_depth); if (depth > MAX_BPF_STACK) { verbose(env, "combined stack size of %d calls is %d. Too large\n", frame + 1, depth); return -EACCES; } continue_func: subprog_end = subprog[idx + 1].start; for (; i < subprog_end; i++) { int next_insn, sidx; if (bpf_pseudo_kfunc_call(insn + i) && !insn[i].off) { bool err = false; if (!is_bpf_throw_kfunc(insn + i)) continue; if (subprog[idx].is_cb) err = true; for (int c = 0; c < frame && !err; c++) { if (subprog[ret_prog[c]].is_cb) { err = true; break; } } if (!err) continue; verbose(env, "bpf_throw kfunc (insn %d) cannot be called from callback subprog %d\n", i, idx); return -EINVAL; } if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i)) continue; /* remember insn and function to return to */ ret_insn[frame] = i + 1; ret_prog[frame] = idx; /* find the callee */ next_insn = i + insn[i].imm + 1; sidx = find_subprog(env, next_insn); if (sidx < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", next_insn); return -EFAULT; } if (subprog[sidx].is_async_cb) { if (subprog[sidx].has_tail_call) { verbose(env, "verifier bug. subprog has tail_call and async cb\n"); return -EFAULT; } /* async callbacks don't increase bpf prog stack size unless called directly */ if (!bpf_pseudo_call(insn + i)) continue; if (subprog[sidx].is_exception_cb) { verbose(env, "insn %d cannot call exception cb directly\n", i); return -EINVAL; } } i = next_insn; idx = sidx; if (subprog[idx].has_tail_call) tail_call_reachable = true; frame++; if (frame >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep !\n", frame); return -E2BIG; } goto process_func; } /* if tail call got detected across bpf2bpf calls then mark each of the * currently present subprog frames as tail call reachable subprogs; * this info will be utilized by JIT so that we will be preserving the * tail call counter throughout bpf2bpf calls combined with tailcalls */ if (tail_call_reachable) for (j = 0; j < frame; j++) { if (subprog[ret_prog[j]].is_exception_cb) { verbose(env, "cannot tail call within exception cb\n"); return -EINVAL; } subprog[ret_prog[j]].tail_call_reachable = true; } if (subprog[0].tail_call_reachable) env->prog->aux->tail_call_reachable = true; /* end of for() loop means the last insn of the 'subprog' * was reached. Doesn't matter whether it was JA or EXIT */ if (frame == 0) return 0; depth -= round_up_stack_depth(env, subprog[idx].stack_depth); frame--; i = ret_insn[frame]; idx = ret_prog[frame]; goto continue_func; } static int check_max_stack_depth(struct bpf_verifier_env *env) { struct bpf_subprog_info *si = env->subprog_info; int ret; for (int i = 0; i < env->subprog_cnt; i++) { if (!i || si[i].is_async_cb) { ret = check_max_stack_depth_subprog(env, i); if (ret < 0) return ret; } continue; } return 0; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON static int get_callee_stack_depth(struct bpf_verifier_env *env, const struct bpf_insn *insn, int idx) { int start = idx + insn->imm + 1, subprog; subprog = find_subprog(env, start); if (subprog < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", start); return -EFAULT; } return env->subprog_info[subprog].stack_depth; } #endif static int __check_buffer_access(struct bpf_verifier_env *env, const char *buf_info, const struct bpf_reg_state *reg, int regno, int off, int size) { if (off < 0) { verbose(env, "R%d invalid %s buffer access: off=%d, size=%d\n", regno, buf_info, off, size); return -EACCES; } if (!tnum_is_const(reg->var_off) || reg->var_off.value) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "R%d invalid variable buffer offset: off=%d, var_off=%s\n", regno, off, tn_buf); return -EACCES; } return 0; } static int check_tp_buffer_access(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, int off, int size) { int err; err = __check_buffer_access(env, "tracepoint", reg, regno, off, size); if (err) return err; if (off + size > env->prog->aux->max_tp_access) env->prog->aux->max_tp_access = off + size; return 0; } static int check_buffer_access(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, int off, int size, bool zero_size_allowed, u32 *max_access) { const char *buf_info = type_is_rdonly_mem(reg->type) ? "rdonly" : "rdwr"; int err; err = __check_buffer_access(env, buf_info, reg, regno, off, size); if (err) return err; if (off + size > *max_access) *max_access = off + size; return 0; } /* BPF architecture zero extends alu32 ops into 64-bit registesr */ static void zext_32_to_64(struct bpf_reg_state *reg) { reg->var_off = tnum_subreg(reg->var_off); __reg_assign_32_into_64(reg); } /* truncate register to smaller size (in bytes) * must be called with size < BPF_REG_SIZE */ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) { u64 mask; /* clear high bits in bit representation */ reg->var_off = tnum_cast(reg->var_off, size); /* fix arithmetic bounds */ mask = ((u64)1 << (size * 8)) - 1; if ((reg->umin_value & ~mask) == (reg->umax_value & ~mask)) { reg->umin_value &= mask; reg->umax_value &= mask; } else { reg->umin_value = 0; reg->umax_value = mask; } reg->smin_value = reg->umin_value; reg->smax_value = reg->umax_value; /* If size is smaller than 32bit register the 32bit register * values are also truncated so we push 64-bit bounds into * 32-bit bounds. Above were truncated < 32-bits already. */ if (size < 4) __mark_reg32_unbounded(reg); reg_bounds_sync(reg); } static void set_sext64_default_val(struct bpf_reg_state *reg, int size) { if (size == 1) { reg->smin_value = reg->s32_min_value = S8_MIN; reg->smax_value = reg->s32_max_value = S8_MAX; } else if (size == 2) { reg->smin_value = reg->s32_min_value = S16_MIN; reg->smax_value = reg->s32_max_value = S16_MAX; } else { /* size == 4 */ reg->smin_value = reg->s32_min_value = S32_MIN; reg->smax_value = reg->s32_max_value = S32_MAX; } reg->umin_value = reg->u32_min_value = 0; reg->umax_value = U64_MAX; reg->u32_max_value = U32_MAX; reg->var_off = tnum_unknown; } static void coerce_reg_to_size_sx(struct bpf_reg_state *reg, int size) { s64 init_s64_max, init_s64_min, s64_max, s64_min, u64_cval; u64 top_smax_value, top_smin_value; u64 num_bits = size * 8; if (tnum_is_const(reg->var_off)) { u64_cval = reg->var_off.value; if (size == 1) reg->var_off = tnum_const((s8)u64_cval); else if (size == 2) reg->var_off = tnum_const((s16)u64_cval); else /* size == 4 */ reg->var_off = tnum_const((s32)u64_cval); u64_cval = reg->var_off.value; reg->smax_value = reg->smin_value = u64_cval; reg->umax_value = reg->umin_value = u64_cval; reg->s32_max_value = reg->s32_min_value = u64_cval; reg->u32_max_value = reg->u32_min_value = u64_cval; return; } top_smax_value = ((u64)reg->smax_value >> num_bits) << num_bits; top_smin_value = ((u64)reg->smin_value >> num_bits) << num_bits; if (top_smax_value != top_smin_value) goto out; /* find the s64_min and s64_min after sign extension */ if (size == 1) { init_s64_max = (s8)reg->smax_value; init_s64_min = (s8)reg->smin_value; } else if (size == 2) { init_s64_max = (s16)reg->smax_value; init_s64_min = (s16)reg->smin_value; } else { init_s64_max = (s32)reg->smax_value; init_s64_min = (s32)reg->smin_value; } s64_max = max(init_s64_max, init_s64_min); s64_min = min(init_s64_max, init_s64_min); /* both of s64_max/s64_min positive or negative */ if ((s64_max >= 0) == (s64_min >= 0)) { reg->smin_value = reg->s32_min_value = s64_min; reg->smax_value = reg->s32_max_value = s64_max; reg->umin_value = reg->u32_min_value = s64_min; reg->umax_value = reg->u32_max_value = s64_max; reg->var_off = tnum_range(s64_min, s64_max); return; } out: set_sext64_default_val(reg, size); } static void set_sext32_default_val(struct bpf_reg_state *reg, int size) { if (size == 1) { reg->s32_min_value = S8_MIN; reg->s32_max_value = S8_MAX; } else { /* size == 2 */ reg->s32_min_value = S16_MIN; reg->s32_max_value = S16_MAX; } reg->u32_min_value = 0; reg->u32_max_value = U32_MAX; reg->var_off = tnum_subreg(tnum_unknown); } static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size) { s32 init_s32_max, init_s32_min, s32_max, s32_min, u32_val; u32 top_smax_value, top_smin_value; u32 num_bits = size * 8; if (tnum_is_const(reg->var_off)) { u32_val = reg->var_off.value; if (size == 1) reg->var_off = tnum_const((s8)u32_val); else reg->var_off = tnum_const((s16)u32_val); u32_val = reg->var_off.value; reg->s32_min_value = reg->s32_max_value = u32_val; reg->u32_min_value = reg->u32_max_value = u32_val; return; } top_smax_value = ((u32)reg->s32_max_value >> num_bits) << num_bits; top_smin_value = ((u32)reg->s32_min_value >> num_bits) << num_bits; if (top_smax_value != top_smin_value) goto out; /* find the s32_min and s32_min after sign extension */ if (size == 1) { init_s32_max = (s8)reg->s32_max_value; init_s32_min = (s8)reg->s32_min_value; } else { /* size == 2 */ init_s32_max = (s16)reg->s32_max_value; init_s32_min = (s16)reg->s32_min_value; } s32_max = max(init_s32_max, init_s32_min); s32_min = min(init_s32_max, init_s32_min); if ((s32_min >= 0) == (s32_max >= 0)) { reg->s32_min_value = s32_min; reg->s32_max_value = s32_max; reg->u32_min_value = (u32)s32_min; reg->u32_max_value = (u32)s32_max; reg->var_off = tnum_subreg(tnum_range(s32_min, s32_max)); return; } out: set_sext32_default_val(reg, size); } static bool bpf_map_is_rdonly(const struct bpf_map *map) { /* A map is considered read-only if the following condition are true: * * 1) BPF program side cannot change any of the map content. The * BPF_F_RDONLY_PROG flag is throughout the lifetime of a map * and was set at map creation time. * 2) The map value(s) have been initialized from user space by a * loader and then "frozen", such that no new map update/delete * operations from syscall side are possible for the rest of * the map's lifetime from that point onwards. * 3) Any parallel/pending map update/delete operations from syscall * side have been completed. Only after that point, it's safe to * assume that map value(s) are immutable. */ return (map->map_flags & BPF_F_RDONLY_PROG) && READ_ONCE(map->frozen) && !bpf_map_write_active(map); } static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val, bool is_ldsx) { void *ptr; u64 addr; int err; err = map->ops->map_direct_value_addr(map, &addr, off); if (err) return err; ptr = (void *)(long)addr + off; switch (size) { case sizeof(u8): *val = is_ldsx ? (s64)*(s8 *)ptr : (u64)*(u8 *)ptr; break; case sizeof(u16): *val = is_ldsx ? (s64)*(s16 *)ptr : (u64)*(u16 *)ptr; break; case sizeof(u32): *val = is_ldsx ? (s64)*(s32 *)ptr : (u64)*(u32 *)ptr; break; case sizeof(u64): *val = *(u64 *)ptr; break; default: return -EINVAL; } return 0; } #define BTF_TYPE_SAFE_RCU(__type) __PASTE(__type, __safe_rcu) #define BTF_TYPE_SAFE_RCU_OR_NULL(__type) __PASTE(__type, __safe_rcu_or_null) #define BTF_TYPE_SAFE_TRUSTED(__type) __PASTE(__type, __safe_trusted) #define BTF_TYPE_SAFE_TRUSTED_OR_NULL(__type) __PASTE(__type, __safe_trusted_or_null) /* * Allow list few fields as RCU trusted or full trusted. * This logic doesn't allow mix tagging and will be removed once GCC supports * btf_type_tag. */ /* RCU trusted: these fields are trusted in RCU CS and never NULL */ BTF_TYPE_SAFE_RCU(struct task_struct) { const cpumask_t *cpus_ptr; struct css_set __rcu *cgroups; struct task_struct __rcu *real_parent; struct task_struct *group_leader; }; BTF_TYPE_SAFE_RCU(struct cgroup) { /* cgrp->kn is always accessible as documented in kernel/cgroup/cgroup.c */ struct kernfs_node *kn; }; BTF_TYPE_SAFE_RCU(struct css_set) { struct cgroup *dfl_cgrp; }; /* RCU trusted: these fields are trusted in RCU CS and can be NULL */ BTF_TYPE_SAFE_RCU_OR_NULL(struct mm_struct) { struct file __rcu *exe_file; }; /* skb->sk, req->sk are not RCU protected, but we mark them as such * because bpf prog accessible sockets are SOCK_RCU_FREE. */ BTF_TYPE_SAFE_RCU_OR_NULL(struct sk_buff) { struct sock *sk; }; BTF_TYPE_SAFE_RCU_OR_NULL(struct request_sock) { struct sock *sk; }; /* full trusted: these fields are trusted even outside of RCU CS and never NULL */ BTF_TYPE_SAFE_TRUSTED(struct bpf_iter_meta) { struct seq_file *seq; }; BTF_TYPE_SAFE_TRUSTED(struct bpf_iter__task) { struct bpf_iter_meta *meta; struct task_struct *task; }; BTF_TYPE_SAFE_TRUSTED(struct linux_binprm) { struct file *file; }; BTF_TYPE_SAFE_TRUSTED(struct file) { struct inode *f_inode; }; BTF_TYPE_SAFE_TRUSTED(struct dentry) { /* no negative dentry-s in places where bpf can see it */ struct inode *d_inode; }; BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket) { struct sock *sk; }; static bool type_is_rcu(struct bpf_verifier_env *env, struct bpf_reg_state *reg, const char *field_name, u32 btf_id) { BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct task_struct)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct cgroup)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct css_set)); return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_rcu"); } static bool type_is_rcu_or_null(struct bpf_verifier_env *env, struct bpf_reg_state *reg, const char *field_name, u32 btf_id) { BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU_OR_NULL(struct mm_struct)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU_OR_NULL(struct sk_buff)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU_OR_NULL(struct request_sock)); return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_rcu_or_null"); } static bool type_is_trusted(struct bpf_verifier_env *env, struct bpf_reg_state *reg, const char *field_name, u32 btf_id) { BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct bpf_iter_meta)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct bpf_iter__task)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct linux_binprm)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct file)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct dentry)); return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_trusted"); } static bool type_is_trusted_or_null(struct bpf_verifier_env *env, struct bpf_reg_state *reg, const char *field_name, u32 btf_id) { BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket)); return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_trusted_or_null"); } static int check_ptr_to_btf_access(struct bpf_verifier_env *env, struct bpf_reg_state *regs, int regno, int off, int size, enum bpf_access_type atype, int value_regno) { struct bpf_reg_state *reg = regs + regno; const struct btf_type *t = btf_type_by_id(reg->btf, reg->btf_id); const char *tname = btf_name_by_offset(reg->btf, t->name_off); const char *field_name = NULL; enum bpf_type_flag flag = 0; u32 btf_id = 0; int ret; if (!env->allow_ptr_leaks) { verbose(env, "'struct %s' access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n", tname); return -EPERM; } if (!env->prog->gpl_compatible && btf_is_kernel(reg->btf)) { verbose(env, "Cannot access kernel 'struct %s' from non-GPL compatible program\n", tname); return -EINVAL; } if (off < 0) { verbose(env, "R%d is ptr_%s invalid negative access: off=%d\n", regno, tname, off); return -EACCES; } if (!tnum_is_const(reg->var_off) || reg->var_off.value) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "R%d is ptr_%s invalid variable offset: off=%d, var_off=%s\n", regno, tname, off, tn_buf); return -EACCES; } if (reg->type & MEM_USER) { verbose(env, "R%d is ptr_%s access user memory: off=%d\n", regno, tname, off); return -EACCES; } if (reg->type & MEM_PERCPU) { verbose(env, "R%d is ptr_%s access percpu memory: off=%d\n", regno, tname, off); return -EACCES; } if (env->ops->btf_struct_access && !type_is_alloc(reg->type) && atype == BPF_WRITE) { if (!btf_is_kernel(reg->btf)) { verbose(env, "verifier internal error: reg->btf must be kernel btf\n"); return -EFAULT; } ret = env->ops->btf_struct_access(&env->log, reg, off, size); } else { /* Writes are permitted with default btf_struct_access for * program allocated objects (which always have ref_obj_id > 0), * but not for untrusted PTR_TO_BTF_ID | MEM_ALLOC. */ if (atype != BPF_READ && !type_is_ptr_alloc_obj(reg->type)) { verbose(env, "only read is supported\n"); return -EACCES; } if (type_is_alloc(reg->type) && !type_is_non_owning_ref(reg->type) && !(reg->type & MEM_RCU) && !reg->ref_obj_id) { verbose(env, "verifier internal error: ref_obj_id for allocated object must be non-zero\n"); return -EFAULT; } ret = btf_struct_access(&env->log, reg, off, size, atype, &btf_id, &flag, &field_name); } if (ret < 0) return ret; if (ret != PTR_TO_BTF_ID) { /* just mark; */ } else if (type_flag(reg->type) & PTR_UNTRUSTED) { /* If this is an untrusted pointer, all pointers formed by walking it * also inherit the untrusted flag. */ flag = PTR_UNTRUSTED; } else if (is_trusted_reg(reg) || is_rcu_reg(reg)) { /* By default any pointer obtained from walking a trusted pointer is no * longer trusted, unless the field being accessed has explicitly been * marked as inheriting its parent's state of trust (either full or RCU). * For example: * 'cgroups' pointer is untrusted if task->cgroups dereference * happened in a sleepable program outside of bpf_rcu_read_lock() * section. In a non-sleepable program it's trusted while in RCU CS (aka MEM_RCU). * Note bpf_rcu_read_unlock() converts MEM_RCU pointers to PTR_UNTRUSTED. * * A regular RCU-protected pointer with __rcu tag can also be deemed * trusted if we are in an RCU CS. Such pointer can be NULL. */ if (type_is_trusted(env, reg, field_name, btf_id)) { flag |= PTR_TRUSTED; } else if (type_is_trusted_or_null(env, reg, field_name, btf_id)) { flag |= PTR_TRUSTED | PTR_MAYBE_NULL; } else if (in_rcu_cs(env) && !type_may_be_null(reg->type)) { if (type_is_rcu(env, reg, field_name, btf_id)) { /* ignore __rcu tag and mark it MEM_RCU */ flag |= MEM_RCU; } else if (flag & MEM_RCU || type_is_rcu_or_null(env, reg, field_name, btf_id)) { /* __rcu tagged pointers can be NULL */ flag |= MEM_RCU | PTR_MAYBE_NULL; /* We always trust them */ if (type_is_rcu_or_null(env, reg, field_name, btf_id) && flag & PTR_UNTRUSTED) flag &= ~PTR_UNTRUSTED; } else if (flag & (MEM_PERCPU | MEM_USER)) { /* keep as-is */ } else { /* walking unknown pointers yields old deprecated PTR_TO_BTF_ID */ clear_trusted_flags(&flag); } } else { /* * If not in RCU CS or MEM_RCU pointer can be NULL then * aggressively mark as untrusted otherwise such * pointers will be plain PTR_TO_BTF_ID without flags * and will be allowed to be passed into helpers for * compat reasons. */ flag = PTR_UNTRUSTED; } } else { /* Old compat. Deprecated */ clear_trusted_flags(&flag); } if (atype == BPF_READ && value_regno >= 0) mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag); return 0; } static int check_ptr_to_map_access(struct bpf_verifier_env *env, struct bpf_reg_state *regs, int regno, int off, int size, enum bpf_access_type atype, int value_regno) { struct bpf_reg_state *reg = regs + regno; struct bpf_map *map = reg->map_ptr; struct bpf_reg_state map_reg; enum bpf_type_flag flag = 0; const struct btf_type *t; const char *tname; u32 btf_id; int ret; if (!btf_vmlinux) { verbose(env, "map_ptr access not supported without CONFIG_DEBUG_INFO_BTF\n"); return -ENOTSUPP; } if (!map->ops->map_btf_id || !*map->ops->map_btf_id) { verbose(env, "map_ptr access not supported for map type %d\n", map->map_type); return -ENOTSUPP; } t = btf_type_by_id(btf_vmlinux, *map->ops->map_btf_id); tname = btf_name_by_offset(btf_vmlinux, t->name_off); if (!env->allow_ptr_leaks) { verbose(env, "'struct %s' access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n", tname); return -EPERM; } if (off < 0) { verbose(env, "R%d is %s invalid negative access: off=%d\n", regno, tname, off); return -EACCES; } if (atype != BPF_READ) { verbose(env, "only read from %s is supported\n", tname); return -EACCES; } /* Simulate access to a PTR_TO_BTF_ID */ memset(&map_reg, 0, sizeof(map_reg)); mark_btf_ld_reg(env, &map_reg, 0, PTR_TO_BTF_ID, btf_vmlinux, *map->ops->map_btf_id, 0); ret = btf_struct_access(&env->log, &map_reg, off, size, atype, &btf_id, &flag, NULL); if (ret < 0) return ret; if (value_regno >= 0) mark_btf_ld_reg(env, regs, value_regno, ret, btf_vmlinux, btf_id, flag); return 0; } /* Check that the stack access at the given offset is within bounds. The * maximum valid offset is -1. * * The minimum valid offset is -MAX_BPF_STACK for writes, and * -state->allocated_stack for reads. */ static int check_stack_slot_within_bounds(struct bpf_verifier_env *env, s64 off, struct bpf_func_state *state, enum bpf_access_type t) { int min_valid_off; if (t == BPF_WRITE || env->allow_uninit_stack) min_valid_off = -MAX_BPF_STACK; else min_valid_off = -state->allocated_stack; if (off < min_valid_off || off > -1) return -EACCES; return 0; } /* Check that the stack access at 'regno + off' falls within the maximum stack * bounds. * * 'off' includes `regno->offset`, but not its dynamic part (if any). */ static int check_stack_access_within_bounds( struct bpf_verifier_env *env, int regno, int off, int access_size, enum bpf_access_src src, enum bpf_access_type type) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; struct bpf_func_state *state = func(env, reg); s64 min_off, max_off; int err; char *err_extra; if (src == ACCESS_HELPER) /* We don't know if helpers are reading or writing (or both). */ err_extra = " indirect access to"; else if (type == BPF_READ) err_extra = " read from"; else err_extra = " write to"; if (tnum_is_const(reg->var_off)) { min_off = (s64)reg->var_off.value + off; max_off = min_off + access_size; } else { if (reg->smax_value >= BPF_MAX_VAR_OFF || reg->smin_value <= -BPF_MAX_VAR_OFF) { verbose(env, "invalid unbounded variable-offset%s stack R%d\n", err_extra, regno); return -EACCES; } min_off = reg->smin_value + off; max_off = reg->smax_value + off + access_size; } err = check_stack_slot_within_bounds(env, min_off, state, type); if (!err && max_off > 0) err = -EINVAL; /* out of stack access into non-negative offsets */ if (!err && access_size < 0) /* access_size should not be negative (or overflow an int); others checks * along the way should have prevented such an access. */ err = -EFAULT; /* invalid negative access size; integer overflow? */ if (err) { if (tnum_is_const(reg->var_off)) { verbose(env, "invalid%s stack R%d off=%d size=%d\n", err_extra, regno, off, access_size); } else { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "invalid variable-offset%s stack R%d var_off=%s off=%d size=%d\n", err_extra, regno, tn_buf, off, access_size); } return err; } /* Note that there is no stack access with offset zero, so the needed stack * size is -min_off, not -min_off+1. */ return grow_stack_state(env, state, -min_off /* size */); } /* check whether memory at (regno + off) is accessible for t = (read | write) * if t==write, value_regno is a register which value is stored into memory * if t==read, value_regno is a register which will receive the value from memory * if t==write && value_regno==-1, some unknown value is stored into memory * if t==read && value_regno==-1, don't care what we read from memory */ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off, int bpf_size, enum bpf_access_type t, int value_regno, bool strict_alignment_once, bool is_ldsx) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; int size, err = 0; size = bpf_size_to_bytes(bpf_size); if (size < 0) return size; /* alignment checks will add in reg->off themselves */ err = check_ptr_alignment(env, reg, off, size, strict_alignment_once); if (err) return err; /* for access checks, reg->off is just part of off */ off += reg->off; if (reg->type == PTR_TO_MAP_KEY) { if (t == BPF_WRITE) { verbose(env, "write to change key R%d not allowed\n", regno); return -EACCES; } err = check_mem_region_access(env, regno, off, size, reg->map_ptr->key_size, false); if (err) return err; if (value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_MAP_VALUE) { struct btf_field *kptr_field = NULL; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into map\n", value_regno); return -EACCES; } err = check_map_access_type(env, regno, off, size, t); if (err) return err; err = check_map_access(env, regno, off, size, false, ACCESS_DIRECT); if (err) return err; if (tnum_is_const(reg->var_off)) kptr_field = btf_record_find(reg->map_ptr->record, off + reg->var_off.value, BPF_KPTR); if (kptr_field) { err = check_map_kptr_access(env, regno, value_regno, insn_idx, kptr_field); } else if (t == BPF_READ && value_regno >= 0) { struct bpf_map *map = reg->map_ptr; /* if map is read-only, track its contents as scalars */ if (tnum_is_const(reg->var_off) && bpf_map_is_rdonly(map) && map->ops->map_direct_value_addr) { int map_off = off + reg->var_off.value; u64 val = 0; err = bpf_map_direct_read(map, map_off, size, &val, is_ldsx); if (err) return err; regs[value_regno].type = SCALAR_VALUE; __mark_reg_known(®s[value_regno], val); } else { mark_reg_unknown(env, regs, value_regno); } } } else if (base_type(reg->type) == PTR_TO_MEM) { bool rdonly_mem = type_is_rdonly_mem(reg->type); if (type_may_be_null(reg->type)) { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str(env, reg->type)); return -EACCES; } if (t == BPF_WRITE && rdonly_mem) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into mem\n", value_regno); return -EACCES; } err = check_mem_region_access(env, regno, off, size, reg->mem_size, false); if (!err && value_regno >= 0 && (t == BPF_READ || rdonly_mem)) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_CTX) { enum bpf_reg_type reg_type = SCALAR_VALUE; struct btf *btf = NULL; u32 btf_id = 0; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into ctx\n", value_regno); return -EACCES; } err = check_ptr_off_reg(env, reg, regno); if (err < 0) return err; err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf, &btf_id); if (err) verbose_linfo(env, insn_idx, "; "); if (!err && t == BPF_READ && value_regno >= 0) { /* ctx access returns either a scalar, or a * PTR_TO_PACKET[_META,_END]. In the latter * case, we know the offset is zero. */ if (reg_type == SCALAR_VALUE) { mark_reg_unknown(env, regs, value_regno); } else { mark_reg_known_zero(env, regs, value_regno); if (type_may_be_null(reg_type)) regs[value_regno].id = ++env->id_gen; /* A load of ctx field could have different * actual load size with the one encoded in the * insn. When the dst is PTR, it is for sure not * a sub-register. */ regs[value_regno].subreg_def = DEF_NOT_SUBREG; if (base_type(reg_type) == PTR_TO_BTF_ID) { regs[value_regno].btf = btf; regs[value_regno].btf_id = btf_id; } } regs[value_regno].type = reg_type; } } else if (reg->type == PTR_TO_STACK) { /* Basic bounds checks. */ err = check_stack_access_within_bounds(env, regno, off, size, ACCESS_DIRECT, t); if (err) return err; if (t == BPF_READ) err = check_stack_read(env, regno, off, size, value_regno); else err = check_stack_write(env, regno, off, size, value_regno, insn_idx); } else if (reg_is_pkt_pointer(reg)) { if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) { verbose(env, "cannot write into packet\n"); return -EACCES; } if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into packet\n", value_regno); return -EACCES; } err = check_packet_access(env, regno, off, size, false); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_FLOW_KEYS) { if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into flow keys\n", value_regno); return -EACCES; } err = check_flow_keys_access(env, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (type_is_sk_pointer(reg->type)) { if (t == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } err = check_sock_access(env, insn_idx, regno, off, size, t); if (!err && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_TP_BUFFER) { err = check_tp_buffer_access(env, reg, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (base_type(reg->type) == PTR_TO_BTF_ID && !type_may_be_null(reg->type)) { err = check_ptr_to_btf_access(env, regs, regno, off, size, t, value_regno); } else if (reg->type == CONST_PTR_TO_MAP) { err = check_ptr_to_map_access(env, regs, regno, off, size, t, value_regno); } else if (base_type(reg->type) == PTR_TO_BUF) { bool rdonly_mem = type_is_rdonly_mem(reg->type); u32 *max_access; if (rdonly_mem) { if (t == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } max_access = &env->prog->aux->max_rdonly_access; } else { max_access = &env->prog->aux->max_rdwr_access; } err = check_buffer_access(env, reg, regno, off, size, false, max_access); if (!err && value_regno >= 0 && (rdonly_mem || t == BPF_READ)) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_ARENA) { if (t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str(env, reg->type)); return -EACCES; } if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ && regs[value_regno].type == SCALAR_VALUE) { if (!is_ldsx) /* b/h/w load zero-extends, mark upper bits as known 0 */ coerce_reg_to_size(®s[value_regno], size); else coerce_reg_to_size_sx(®s[value_regno], size); } return err; } static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type type, bool allow_trust_mismatch); static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn) { int load_reg; int err; switch (insn->imm) { case BPF_ADD: case BPF_ADD | BPF_FETCH: case BPF_AND: case BPF_AND | BPF_FETCH: case BPF_OR: case BPF_OR | BPF_FETCH: case BPF_XOR: case BPF_XOR | BPF_FETCH: case BPF_XCHG: case BPF_CMPXCHG: break; default: verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", insn->imm); return -EINVAL; } if (BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) { verbose(env, "invalid atomic operand size\n"); return -EINVAL; } /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; if (insn->imm == BPF_CMPXCHG) { /* Check comparison of R0 with memory location */ const u32 aux_reg = BPF_REG_0; err = check_reg_arg(env, aux_reg, SRC_OP); if (err) return err; if (is_pointer_value(env, aux_reg)) { verbose(env, "R%d leaks addr into mem\n", aux_reg); return -EACCES; } } if (is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d leaks addr into mem\n", insn->src_reg); return -EACCES; } if (is_ctx_reg(env, insn->dst_reg) || is_pkt_reg(env, insn->dst_reg) || is_flow_key_reg(env, insn->dst_reg) || is_sk_reg(env, insn->dst_reg) || (is_arena_reg(env, insn->dst_reg) && !bpf_jit_supports_insn(insn, true))) { verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n", insn->dst_reg, reg_type_str(env, reg_state(env, insn->dst_reg)->type)); return -EACCES; } if (insn->imm & BPF_FETCH) { if (insn->imm == BPF_CMPXCHG) load_reg = BPF_REG_0; else load_reg = insn->src_reg; /* check and record load of old value */ err = check_reg_arg(env, load_reg, DST_OP); if (err) return err; } else { /* This instruction accesses a memory location but doesn't * actually load it into a register. */ load_reg = -1; } /* Check whether we can read the memory, with second call for fetch * case to simulate the register fill. */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, -1, true, false); if (!err && load_reg >= 0) err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, load_reg, true, false); if (err) return err; if (is_arena_reg(env, insn->dst_reg)) { err = save_aux_ptr_type(env, PTR_TO_ARENA, false); if (err) return err; } /* Check whether we can write into the same memory. */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1, true, false); if (err) return err; return 0; } /* When register 'regno' is used to read the stack (either directly or through * a helper function) make sure that it's within stack boundary and, depending * on the access type and privileges, that all elements of the stack are * initialized. * * 'off' includes 'regno->off', but not its dynamic part (if any). * * All registers that have been spilled on the stack in the slots within the * read offsets are marked as read. */ static int check_stack_range_initialized( struct bpf_verifier_env *env, int regno, int off, int access_size, bool zero_size_allowed, enum bpf_access_src type, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *reg = reg_state(env, regno); struct bpf_func_state *state = func(env, reg); int err, min_off, max_off, i, j, slot, spi; char *err_extra = type == ACCESS_HELPER ? " indirect" : ""; enum bpf_access_type bounds_check_type; /* Some accesses can write anything into the stack, others are * read-only. */ bool clobber = false; if (access_size == 0 && !zero_size_allowed) { verbose(env, "invalid zero-sized read\n"); return -EACCES; } if (type == ACCESS_HELPER) { /* The bounds checks for writes are more permissive than for * reads. However, if raw_mode is not set, we'll do extra * checks below. */ bounds_check_type = BPF_WRITE; clobber = true; } else { bounds_check_type = BPF_READ; } err = check_stack_access_within_bounds(env, regno, off, access_size, type, bounds_check_type); if (err) return err; if (tnum_is_const(reg->var_off)) { min_off = max_off = reg->var_off.value + off; } else { /* Variable offset is prohibited for unprivileged mode for * simplicity since it requires corresponding support in * Spectre masking for stack ALU. * See also retrieve_ptr_limit(). */ if (!env->bypass_spec_v1) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "R%d%s variable offset stack access prohibited for !root, var_off=%s\n", regno, err_extra, tn_buf); return -EACCES; } /* Only initialized buffer on stack is allowed to be accessed * with variable offset. With uninitialized buffer it's hard to * guarantee that whole memory is marked as initialized on * helper return since specific bounds are unknown what may * cause uninitialized stack leaking. */ if (meta && meta->raw_mode) meta = NULL; min_off = reg->smin_value + off; max_off = reg->smax_value + off; } if (meta && meta->raw_mode) { /* Ensure we won't be overwriting dynptrs when simulating byte * by byte access in check_helper_call using meta.access_size. * This would be a problem if we have a helper in the future * which takes: * * helper(uninit_mem, len, dynptr) * * Now, uninint_mem may overlap with dynptr pointer. Hence, it * may end up writing to dynptr itself when touching memory from * arg 1. This can be relaxed on a case by case basis for known * safe cases, but reject due to the possibilitiy of aliasing by * default. */ for (i = min_off; i < max_off + access_size; i++) { int stack_off = -i - 1; spi = __get_spi(i); /* raw_mode may write past allocated_stack */ if (state->allocated_stack <= stack_off) continue; if (state->stack[spi].slot_type[stack_off % BPF_REG_SIZE] == STACK_DYNPTR) { verbose(env, "potential write to dynptr at off=%d disallowed\n", i); return -EACCES; } } meta->access_size = access_size; meta->regno = regno; return 0; } for (i = min_off; i < max_off + access_size; i++) { u8 *stype; slot = -i - 1; spi = slot / BPF_REG_SIZE; if (state->allocated_stack <= slot) { verbose(env, "verifier bug: allocated_stack too small"); return -EFAULT; } stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE]; if (*stype == STACK_MISC) goto mark; if ((*stype == STACK_ZERO) || (*stype == STACK_INVALID && env->allow_uninit_stack)) { if (clobber) { /* helper can write anything into the stack */ *stype = STACK_MISC; } goto mark; } if (is_spilled_reg(&state->stack[spi]) && (state->stack[spi].spilled_ptr.type == SCALAR_VALUE || env->allow_ptr_leaks)) { if (clobber) { __mark_reg_unknown(env, &state->stack[spi].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) scrub_spilled_slot(&state->stack[spi].slot_type[j]); } goto mark; } if (tnum_is_const(reg->var_off)) { verbose(env, "invalid%s read from stack R%d off %d+%d size %d\n", err_extra, regno, min_off, i - min_off, access_size); } else { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "invalid%s read from stack R%d var_off %s+%d size %d\n", err_extra, regno, tn_buf, i - min_off, access_size); } return -EACCES; mark: /* reading any byte out of 8-byte 'spill_slot' will cause * the whole slot to be marked as 'read' */ mark_reg_read(env, &state->stack[spi].spilled_ptr, state->stack[spi].spilled_ptr.parent, REG_LIVE_READ64); /* We do not set REG_LIVE_WRITTEN for stack slot, as we can not * be sure that whether stack slot is written to or not. Hence, * we must still conservatively propagate reads upwards even if * helper may write to the entire memory range. */ } return 0; } static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, int access_size, bool zero_size_allowed, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; u32 *max_access; switch (base_type(reg->type)) { case PTR_TO_PACKET: case PTR_TO_PACKET_META: return check_packet_access(env, regno, reg->off, access_size, zero_size_allowed); case PTR_TO_MAP_KEY: if (meta && meta->raw_mode) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } return check_mem_region_access(env, regno, reg->off, access_size, reg->map_ptr->key_size, false); case PTR_TO_MAP_VALUE: if (check_map_access_type(env, regno, reg->off, access_size, meta && meta->raw_mode ? BPF_WRITE : BPF_READ)) return -EACCES; return check_map_access(env, regno, reg->off, access_size, zero_size_allowed, ACCESS_HELPER); case PTR_TO_MEM: if (type_is_rdonly_mem(reg->type)) { if (meta && meta->raw_mode) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } } return check_mem_region_access(env, regno, reg->off, access_size, reg->mem_size, zero_size_allowed); case PTR_TO_BUF: if (type_is_rdonly_mem(reg->type)) { if (meta && meta->raw_mode) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } max_access = &env->prog->aux->max_rdonly_access; } else { max_access = &env->prog->aux->max_rdwr_access; } return check_buffer_access(env, reg, regno, reg->off, access_size, zero_size_allowed, max_access); case PTR_TO_STACK: return check_stack_range_initialized( env, regno, reg->off, access_size, zero_size_allowed, ACCESS_HELPER, meta); case PTR_TO_BTF_ID: return check_ptr_to_btf_access(env, regs, regno, reg->off, access_size, BPF_READ, -1); case PTR_TO_CTX: /* in case the function doesn't know how to access the context, * (because we are in a program of type SYSCALL for example), we * can not statically check its size. * Dynamically check it now. */ if (!env->ops->convert_ctx_access) { enum bpf_access_type atype = meta && meta->raw_mode ? BPF_WRITE : BPF_READ; int offset = access_size - 1; /* Allow zero-byte read from PTR_TO_CTX */ if (access_size == 0) return zero_size_allowed ? 0 : -EACCES; return check_mem_access(env, env->insn_idx, regno, offset, BPF_B, atype, -1, false, false); } fallthrough; default: /* scalar_value or invalid ptr */ /* Allow zero-byte read from NULL, regardless of pointer type */ if (zero_size_allowed && access_size == 0 && register_is_null(reg)) return 0; verbose(env, "R%d type=%s ", regno, reg_type_str(env, reg->type)); verbose(env, "expected=%s\n", reg_type_str(env, PTR_TO_STACK)); return -EACCES; } } /* verify arguments to helpers or kfuncs consisting of a pointer and an access * size. * * @regno is the register containing the access size. regno-1 is the register * containing the pointer. */ static int check_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, bool zero_size_allowed, struct bpf_call_arg_meta *meta) { int err; /* This is used to refine r0 return value bounds for helpers * that enforce this value as an upper bound on return values. * See do_refine_retval_range() for helpers that can refine * the return value. C type of helper is u32 so we pull register * bound from umax_value however, if negative verifier errors * out. Only upper bounds can be learned because retval is an * int type and negative retvals are allowed. */ meta->msize_max_value = reg->umax_value; /* The register is SCALAR_VALUE; the access check * happens using its boundaries. */ if (!tnum_is_const(reg->var_off)) /* For unprivileged variable accesses, disable raw * mode so that the program is required to * initialize all the memory that the helper could * just partially fill up. */ meta = NULL; if (reg->smin_value < 0) { verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n", regno); return -EACCES; } if (reg->umin_value == 0 && !zero_size_allowed) { verbose(env, "R%d invalid zero-sized read: u64=[%lld,%lld]\n", regno, reg->umin_value, reg->umax_value); return -EACCES; } if (reg->umax_value >= BPF_MAX_VAR_SIZ) { verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", regno); return -EACCES; } err = check_helper_mem_access(env, regno - 1, reg->umax_value, zero_size_allowed, meta); if (!err) err = mark_chain_precision(env, regno); return err; } static int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size) { bool may_be_null = type_may_be_null(reg->type); struct bpf_reg_state saved_reg; struct bpf_call_arg_meta meta; int err; if (register_is_null(reg)) return 0; memset(&meta, 0, sizeof(meta)); /* Assuming that the register contains a value check if the memory * access is safe. Temporarily save and restore the register's state as * the conversion shouldn't be visible to a caller. */ if (may_be_null) { saved_reg = *reg; mark_ptr_not_null_reg(reg); } err = check_helper_mem_access(env, regno, mem_size, true, &meta); /* Check access for BPF_WRITE */ meta.raw_mode = true; err = err ?: check_helper_mem_access(env, regno, mem_size, true, &meta); if (may_be_null) *reg = saved_reg; return err; } static int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno) { struct bpf_reg_state *mem_reg = &cur_regs(env)[regno - 1]; bool may_be_null = type_may_be_null(mem_reg->type); struct bpf_reg_state saved_reg; struct bpf_call_arg_meta meta; int err; WARN_ON_ONCE(regno < BPF_REG_2 || regno > BPF_REG_5); memset(&meta, 0, sizeof(meta)); if (may_be_null) { saved_reg = *mem_reg; mark_ptr_not_null_reg(mem_reg); } err = check_mem_size_reg(env, reg, regno, true, &meta); /* Check access for BPF_WRITE */ meta.raw_mode = true; err = err ?: check_mem_size_reg(env, reg, regno, true, &meta); if (may_be_null) *mem_reg = saved_reg; return err; } /* Implementation details: * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL. * bpf_obj_new returns PTR_TO_BTF_ID | MEM_ALLOC | PTR_MAYBE_NULL. * Two bpf_map_lookups (even with the same key) will have different reg->id. * Two separate bpf_obj_new will also have different reg->id. * For traditional PTR_TO_MAP_VALUE or PTR_TO_BTF_ID | MEM_ALLOC, the verifier * clears reg->id after value_or_null->value transition, since the verifier only * cares about the range of access to valid map value pointer and doesn't care * about actual address of the map element. * For maps with 'struct bpf_spin_lock' inside map value the verifier keeps * reg->id > 0 after value_or_null->value transition. By doing so * two bpf_map_lookups will be considered two different pointers that * point to different bpf_spin_locks. Likewise for pointers to allocated objects * returned from bpf_obj_new. * The verifier allows taking only one bpf_spin_lock at a time to avoid * dead-locks. * Since only one bpf_spin_lock is allowed the checks are simpler than * reg_is_refcounted() logic. The verifier needs to remember only * one spin_lock instead of array of acquired_refs. * cur_state->active_lock remembers which map value element or allocated * object got locked and clears it after bpf_spin_unlock. */ static int process_spin_lock(struct bpf_verifier_env *env, int regno, bool is_lock) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; struct bpf_verifier_state *cur = env->cur_state; bool is_const = tnum_is_const(reg->var_off); u64 val = reg->var_off.value; struct bpf_map *map = NULL; struct btf *btf = NULL; struct btf_record *rec; if (!is_const) { verbose(env, "R%d doesn't have constant offset. bpf_spin_lock has to be at the constant offset\n", regno); return -EINVAL; } if (reg->type == PTR_TO_MAP_VALUE) { map = reg->map_ptr; if (!map->btf) { verbose(env, "map '%s' has to have BTF in order to use bpf_spin_lock\n", map->name); return -EINVAL; } } else { btf = reg->btf; } rec = reg_btf_record(reg); if (!btf_record_has_field(rec, BPF_SPIN_LOCK)) { verbose(env, "%s '%s' has no valid bpf_spin_lock\n", map ? "map" : "local", map ? map->name : "kptr"); return -EINVAL; } if (rec->spin_lock_off != val + reg->off) { verbose(env, "off %lld doesn't point to 'struct bpf_spin_lock' that is at %d\n", val + reg->off, rec->spin_lock_off); return -EINVAL; } if (is_lock) { if (cur->active_lock.ptr) { verbose(env, "Locking two bpf_spin_locks are not allowed\n"); return -EINVAL; } if (map) cur->active_lock.ptr = map; else cur->active_lock.ptr = btf; cur->active_lock.id = reg->id; } else { void *ptr; if (map) ptr = map; else ptr = btf; if (!cur->active_lock.ptr) { verbose(env, "bpf_spin_unlock without taking a lock\n"); return -EINVAL; } if (cur->active_lock.ptr != ptr || cur->active_lock.id != reg->id) { verbose(env, "bpf_spin_unlock of different lock\n"); return -EINVAL; } invalidate_non_owning_refs(env); cur->active_lock.ptr = NULL; cur->active_lock.id = 0; } return 0; } static int process_timer_func(struct bpf_verifier_env *env, int regno, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; bool is_const = tnum_is_const(reg->var_off); struct bpf_map *map = reg->map_ptr; u64 val = reg->var_off.value; if (!is_const) { verbose(env, "R%d doesn't have constant offset. bpf_timer has to be at the constant offset\n", regno); return -EINVAL; } if (!map->btf) { verbose(env, "map '%s' has to have BTF in order to use bpf_timer\n", map->name); return -EINVAL; } if (!btf_record_has_field(map->record, BPF_TIMER)) { verbose(env, "map '%s' has no valid bpf_timer\n", map->name); return -EINVAL; } if (map->record->timer_off != val + reg->off) { verbose(env, "off %lld doesn't point to 'struct bpf_timer' that is at %d\n", val + reg->off, map->record->timer_off); return -EINVAL; } if (meta->map_ptr) { verbose(env, "verifier bug. Two map pointers in a timer helper\n"); return -EFAULT; } meta->map_uid = reg->map_uid; meta->map_ptr = map; return 0; } static int process_wq_func(struct bpf_verifier_env *env, int regno, struct bpf_kfunc_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; struct bpf_map *map = reg->map_ptr; u64 val = reg->var_off.value; if (map->record->wq_off != val + reg->off) { verbose(env, "off %lld doesn't point to 'struct bpf_wq' that is at %d\n", val + reg->off, map->record->wq_off); return -EINVAL; } meta->map.uid = reg->map_uid; meta->map.ptr = map; return 0; } static int process_kptr_func(struct bpf_verifier_env *env, int regno, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; struct bpf_map *map_ptr = reg->map_ptr; struct btf_field *kptr_field; u32 kptr_off; if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d doesn't have constant offset. kptr has to be at the constant offset\n", regno); return -EINVAL; } if (!map_ptr->btf) { verbose(env, "map '%s' has to have BTF in order to use bpf_kptr_xchg\n", map_ptr->name); return -EINVAL; } if (!btf_record_has_field(map_ptr->record, BPF_KPTR)) { verbose(env, "map '%s' has no valid kptr\n", map_ptr->name); return -EINVAL; } meta->map_ptr = map_ptr; kptr_off = reg->off + reg->var_off.value; kptr_field = btf_record_find(map_ptr->record, kptr_off, BPF_KPTR); if (!kptr_field) { verbose(env, "off=%d doesn't point to kptr\n", kptr_off); return -EACCES; } if (kptr_field->type != BPF_KPTR_REF && kptr_field->type != BPF_KPTR_PERCPU) { verbose(env, "off=%d kptr isn't referenced kptr\n", kptr_off); return -EACCES; } meta->kptr_field = kptr_field; return 0; } /* There are two register types representing a bpf_dynptr, one is PTR_TO_STACK * which points to a stack slot, and the other is CONST_PTR_TO_DYNPTR. * * In both cases we deal with the first 8 bytes, but need to mark the next 8 * bytes as STACK_DYNPTR in case of PTR_TO_STACK. In case of * CONST_PTR_TO_DYNPTR, we are guaranteed to get the beginning of the object. * * Mutability of bpf_dynptr is at two levels, one is at the level of struct * bpf_dynptr itself, i.e. whether the helper is receiving a pointer to struct * bpf_dynptr or pointer to const struct bpf_dynptr. In the former case, it can * mutate the view of the dynptr and also possibly destroy it. In the latter * case, it cannot mutate the bpf_dynptr itself but it can still mutate the * memory that dynptr points to. * * The verifier will keep track both levels of mutation (bpf_dynptr's in * reg->type and the memory's in reg->dynptr.type), but there is no support for * readonly dynptr view yet, hence only the first case is tracked and checked. * * This is consistent with how C applies the const modifier to a struct object, * where the pointer itself inside bpf_dynptr becomes const but not what it * points to. * * Helpers which do not mutate the bpf_dynptr set MEM_RDONLY in their argument * type, and declare it as 'const struct bpf_dynptr *' in their prototype. */ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn_idx, enum bpf_arg_type arg_type, int clone_ref_obj_id) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; int err; /* MEM_UNINIT and MEM_RDONLY are exclusive, when applied to an * ARG_PTR_TO_DYNPTR (or ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_*): */ if ((arg_type & (MEM_UNINIT | MEM_RDONLY)) == (MEM_UNINIT | MEM_RDONLY)) { verbose(env, "verifier internal error: misconfigured dynptr helper type flags\n"); return -EFAULT; } /* MEM_UNINIT - Points to memory that is an appropriate candidate for * constructing a mutable bpf_dynptr object. * * Currently, this is only possible with PTR_TO_STACK * pointing to a region of at least 16 bytes which doesn't * contain an existing bpf_dynptr. * * MEM_RDONLY - Points to a initialized bpf_dynptr that will not be * mutated or destroyed. However, the memory it points to * may be mutated. * * None - Points to a initialized dynptr that can be mutated and * destroyed, including mutation of the memory it points * to. */ if (arg_type & MEM_UNINIT) { int i; if (!is_dynptr_reg_valid_uninit(env, reg)) { verbose(env, "Dynptr has to be an uninitialized dynptr\n"); return -EINVAL; } /* we write BPF_DW bits (8 bytes) at a time */ for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) { err = check_mem_access(env, insn_idx, regno, i, BPF_DW, BPF_WRITE, -1, false, false); if (err) return err; } err = mark_stack_slots_dynptr(env, reg, arg_type, insn_idx, clone_ref_obj_id); } else /* MEM_RDONLY and None case from above */ { /* For the reg->type == PTR_TO_STACK case, bpf_dynptr is never const */ if (reg->type == CONST_PTR_TO_DYNPTR && !(arg_type & MEM_RDONLY)) { verbose(env, "cannot pass pointer to const bpf_dynptr, the helper mutates it\n"); return -EINVAL; } if (!is_dynptr_reg_valid_init(env, reg)) { verbose(env, "Expected an initialized dynptr as arg #%d\n", regno); return -EINVAL; } /* Fold modifiers (in this case, MEM_RDONLY) when checking expected type */ if (!is_dynptr_type_expected(env, reg, arg_type & ~MEM_RDONLY)) { verbose(env, "Expected a dynptr of type %s as arg #%d\n", dynptr_type_str(arg_to_dynptr_type(arg_type)), regno); return -EINVAL; } err = mark_dynptr_read(env, reg); } return err; } static u32 iter_ref_obj_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int spi) { struct bpf_func_state *state = func(env, reg); return state->stack[spi].spilled_ptr.ref_obj_id; } static bool is_iter_kfunc(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & (KF_ITER_NEW | KF_ITER_NEXT | KF_ITER_DESTROY); } static bool is_iter_new_kfunc(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_ITER_NEW; } static bool is_iter_next_kfunc(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_ITER_NEXT; } static bool is_iter_destroy_kfunc(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_ITER_DESTROY; } static bool is_kfunc_arg_iter(struct bpf_kfunc_call_arg_meta *meta, int arg) { /* btf_check_iter_kfuncs() guarantees that first argument of any iter * kfunc is iter state pointer */ return arg == 0 && is_iter_kfunc(meta); } static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_idx, struct bpf_kfunc_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; const struct btf_type *t; const struct btf_param *arg; int spi, err, i, nr_slots; u32 btf_id; /* btf_check_iter_kfuncs() ensures we don't need to validate anything here */ arg = &btf_params(meta->func_proto)[0]; t = btf_type_skip_modifiers(meta->btf, arg->type, NULL); /* PTR */ t = btf_type_skip_modifiers(meta->btf, t->type, &btf_id); /* STRUCT */ nr_slots = t->size / BPF_REG_SIZE; if (is_iter_new_kfunc(meta)) { /* bpf_iter_<type>_new() expects pointer to uninit iter state */ if (!is_iter_reg_valid_uninit(env, reg, nr_slots)) { verbose(env, "expected uninitialized iter_%s as arg #%d\n", iter_type_str(meta->btf, btf_id), regno); return -EINVAL; } for (i = 0; i < nr_slots * 8; i += BPF_REG_SIZE) { err = check_mem_access(env, insn_idx, regno, i, BPF_DW, BPF_WRITE, -1, false, false); if (err) return err; } err = mark_stack_slots_iter(env, meta, reg, insn_idx, meta->btf, btf_id, nr_slots); if (err) return err; } else { /* iter_next() or iter_destroy() expect initialized iter state*/ err = is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots); switch (err) { case 0: break; case -EINVAL: verbose(env, "expected an initialized iter_%s as arg #%d\n", iter_type_str(meta->btf, btf_id), regno); return err; case -EPROTO: verbose(env, "expected an RCU CS when using %s\n", meta->func_name); return err; default: return err; } spi = iter_get_spi(env, reg, nr_slots); if (spi < 0) return spi; err = mark_iter_read(env, reg, spi, nr_slots); if (err) return err; /* remember meta->iter info for process_iter_next_call() */ meta->iter.spi = spi; meta->iter.frameno = reg->frameno; meta->ref_obj_id = iter_ref_obj_id(env, reg, spi); if (is_iter_destroy_kfunc(meta)) { err = unmark_stack_slots_iter(env, reg, nr_slots); if (err) return err; } } return 0; } /* Look for a previous loop entry at insn_idx: nearest parent state * stopped at insn_idx with callsites matching those in cur->frame. */ static struct bpf_verifier_state *find_prev_entry(struct bpf_verifier_env *env, struct bpf_verifier_state *cur, int insn_idx) { struct bpf_verifier_state_list *sl; struct bpf_verifier_state *st; /* Explored states are pushed in stack order, most recent states come first */ sl = *explored_state(env, insn_idx); for (; sl; sl = sl->next) { /* If st->branches != 0 state is a part of current DFS verification path, * hence cur & st for a loop. */ st = &sl->state; if (st->insn_idx == insn_idx && st->branches && same_callsites(st, cur) && st->dfs_depth < cur->dfs_depth) return st; } return NULL; } static void reset_idmap_scratch(struct bpf_verifier_env *env); static bool regs_exact(const struct bpf_reg_state *rold, const struct bpf_reg_state *rcur, struct bpf_idmap *idmap); static void maybe_widen_reg(struct bpf_verifier_env *env, struct bpf_reg_state *rold, struct bpf_reg_state *rcur, struct bpf_idmap *idmap) { if (rold->type != SCALAR_VALUE) return; if (rold->type != rcur->type) return; if (rold->precise || rcur->precise || regs_exact(rold, rcur, idmap)) return; __mark_reg_unknown(env, rcur); } static int widen_imprecise_scalars(struct bpf_verifier_env *env, struct bpf_verifier_state *old, struct bpf_verifier_state *cur) { struct bpf_func_state *fold, *fcur; int i, fr; reset_idmap_scratch(env); for (fr = old->curframe; fr >= 0; fr--) { fold = old->frame[fr]; fcur = cur->frame[fr]; for (i = 0; i < MAX_BPF_REG; i++) maybe_widen_reg(env, &fold->regs[i], &fcur->regs[i], &env->idmap_scratch); for (i = 0; i < fold->allocated_stack / BPF_REG_SIZE; i++) { if (!is_spilled_reg(&fold->stack[i]) || !is_spilled_reg(&fcur->stack[i])) continue; maybe_widen_reg(env, &fold->stack[i].spilled_ptr, &fcur->stack[i].spilled_ptr, &env->idmap_scratch); } } return 0; } /* process_iter_next_call() is called when verifier gets to iterator's next * "method" (e.g., bpf_iter_num_next() for numbers iterator) call. We'll refer * to it as just "iter_next()" in comments below. * * BPF verifier relies on a crucial contract for any iter_next() * implementation: it should *eventually* return NULL, and once that happens * it should keep returning NULL. That is, once iterator exhausts elements to * iterate, it should never reset or spuriously return new elements. * * With the assumption of such contract, process_iter_next_call() simulates * a fork in the verifier state to validate loop logic correctness and safety * without having to simulate infinite amount of iterations. * * In current state, we first assume that iter_next() returned NULL and * iterator state is set to DRAINED (BPF_ITER_STATE_DRAINED). In such * conditions we should not form an infinite loop and should eventually reach * exit. * * Besides that, we also fork current state and enqueue it for later * verification. In a forked state we keep iterator state as ACTIVE * (BPF_ITER_STATE_ACTIVE) and assume non-NULL return from iter_next(). We * also bump iteration depth to prevent erroneous infinite loop detection * later on (see iter_active_depths_differ() comment for details). In this * state we assume that we'll eventually loop back to another iter_next() * calls (it could be in exactly same location or in some other instruction, * it doesn't matter, we don't make any unnecessary assumptions about this, * everything revolves around iterator state in a stack slot, not which * instruction is calling iter_next()). When that happens, we either will come * to iter_next() with equivalent state and can conclude that next iteration * will proceed in exactly the same way as we just verified, so it's safe to * assume that loop converges. If not, we'll go on another iteration * simulation with a different input state, until all possible starting states * are validated or we reach maximum number of instructions limit. * * This way, we will either exhaustively discover all possible input states * that iterator loop can start with and eventually will converge, or we'll * effectively regress into bounded loop simulation logic and either reach * maximum number of instructions if loop is not provably convergent, or there * is some statically known limit on number of iterations (e.g., if there is * an explicit `if n > 100 then break;` statement somewhere in the loop). * * Iteration convergence logic in is_state_visited() relies on exact * states comparison, which ignores read and precision marks. * This is necessary because read and precision marks are not finalized * while in the loop. Exact comparison might preclude convergence for * simple programs like below: * * i = 0; * while(iter_next(&it)) * i++; * * At each iteration step i++ would produce a new distinct state and * eventually instruction processing limit would be reached. * * To avoid such behavior speculatively forget (widen) range for * imprecise scalar registers, if those registers were not precise at the * end of the previous iteration and do not match exactly. * * This is a conservative heuristic that allows to verify wide range of programs, * however it precludes verification of programs that conjure an * imprecise value on the first loop iteration and use it as precise on a second. * For example, the following safe program would fail to verify: * * struct bpf_num_iter it; * int arr[10]; * int i = 0, a = 0; * bpf_iter_num_new(&it, 0, 10); * while (bpf_iter_num_next(&it)) { * if (a == 0) { * a = 1; * i = 7; // Because i changed verifier would forget * // it's range on second loop entry. * } else { * arr[i] = 42; // This would fail to verify. * } * } * bpf_iter_num_destroy(&it); */ static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx, struct bpf_kfunc_call_arg_meta *meta) { struct bpf_verifier_state *cur_st = env->cur_state, *queued_st, *prev_st; struct bpf_func_state *cur_fr = cur_st->frame[cur_st->curframe], *queued_fr; struct bpf_reg_state *cur_iter, *queued_iter; int iter_frameno = meta->iter.frameno; int iter_spi = meta->iter.spi; BTF_TYPE_EMIT(struct bpf_iter); cur_iter = &env->cur_state->frame[iter_frameno]->stack[iter_spi].spilled_ptr; if (cur_iter->iter.state != BPF_ITER_STATE_ACTIVE && cur_iter->iter.state != BPF_ITER_STATE_DRAINED) { verbose(env, "verifier internal error: unexpected iterator state %d (%s)\n", cur_iter->iter.state, iter_state_str(cur_iter->iter.state)); return -EFAULT; } if (cur_iter->iter.state == BPF_ITER_STATE_ACTIVE) { /* Because iter_next() call is a checkpoint is_state_visitied() * should guarantee parent state with same call sites and insn_idx. */ if (!cur_st->parent || cur_st->parent->insn_idx != insn_idx || !same_callsites(cur_st->parent, cur_st)) { verbose(env, "bug: bad parent state for iter next call"); return -EFAULT; } /* Note cur_st->parent in the call below, it is necessary to skip * checkpoint created for cur_st by is_state_visited() * right at this instruction. */ prev_st = find_prev_entry(env, cur_st->parent, insn_idx); /* branch out active iter state */ queued_st = push_stack(env, insn_idx + 1, insn_idx, false); if (!queued_st) return -ENOMEM; queued_iter = &queued_st->frame[iter_frameno]->stack[iter_spi].spilled_ptr; queued_iter->iter.state = BPF_ITER_STATE_ACTIVE; queued_iter->iter.depth++; if (prev_st) widen_imprecise_scalars(env, prev_st, queued_st); queued_fr = queued_st->frame[queued_st->curframe]; mark_ptr_not_null_reg(&queued_fr->regs[BPF_REG_0]); } /* switch to DRAINED state, but keep the depth unchanged */ /* mark current iter state as drained and assume returned NULL */ cur_iter->iter.state = BPF_ITER_STATE_DRAINED; __mark_reg_const_zero(env, &cur_fr->regs[BPF_REG_0]); return 0; } static bool arg_type_is_mem_size(enum bpf_arg_type type) { return type == ARG_CONST_SIZE || type == ARG_CONST_SIZE_OR_ZERO; } static bool arg_type_is_release(enum bpf_arg_type type) { return type & OBJ_RELEASE; } static bool arg_type_is_dynptr(enum bpf_arg_type type) { return base_type(type) == ARG_PTR_TO_DYNPTR; } static int int_ptr_type_to_size(enum bpf_arg_type type) { if (type == ARG_PTR_TO_INT) return sizeof(u32); else if (type == ARG_PTR_TO_LONG) return sizeof(u64); return -EINVAL; } static int resolve_map_arg_type(struct bpf_verifier_env *env, const struct bpf_call_arg_meta *meta, enum bpf_arg_type *arg_type) { if (!meta->map_ptr) { /* kernel subsystem misconfigured verifier */ verbose(env, "invalid map_ptr to access map->type\n"); return -EACCES; } switch (meta->map_ptr->map_type) { case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_SOCKHASH: if (*arg_type == ARG_PTR_TO_MAP_VALUE) { *arg_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON; } else { verbose(env, "invalid arg_type for sockmap/sockhash\n"); return -EINVAL; } break; case BPF_MAP_TYPE_BLOOM_FILTER: if (meta->func_id == BPF_FUNC_map_peek_elem) *arg_type = ARG_PTR_TO_MAP_VALUE; break; default: break; } return 0; } struct bpf_reg_types { const enum bpf_reg_type types[10]; u32 *btf_id; }; static const struct bpf_reg_types sock_types = { .types = { PTR_TO_SOCK_COMMON, PTR_TO_SOCKET, PTR_TO_TCP_SOCK, PTR_TO_XDP_SOCK, }, }; #ifdef CONFIG_NET static const struct bpf_reg_types btf_id_sock_common_types = { .types = { PTR_TO_SOCK_COMMON, PTR_TO_SOCKET, PTR_TO_TCP_SOCK, PTR_TO_XDP_SOCK, PTR_TO_BTF_ID, PTR_TO_BTF_ID | PTR_TRUSTED, }, .btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], }; #endif static const struct bpf_reg_types mem_types = { .types = { PTR_TO_STACK, PTR_TO_PACKET, PTR_TO_PACKET_META, PTR_TO_MAP_KEY, PTR_TO_MAP_VALUE, PTR_TO_MEM, PTR_TO_MEM | MEM_RINGBUF, PTR_TO_BUF, PTR_TO_BTF_ID | PTR_TRUSTED, }, }; static const struct bpf_reg_types int_ptr_types = { .types = { PTR_TO_STACK, PTR_TO_PACKET, PTR_TO_PACKET_META, PTR_TO_MAP_KEY, PTR_TO_MAP_VALUE, }, }; static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE, PTR_TO_BTF_ID | MEM_ALLOC, } }; static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } }; static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } }; static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } }; static const struct bpf_reg_types ringbuf_mem_types = { .types = { PTR_TO_MEM | MEM_RINGBUF } }; static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } }; static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID, PTR_TO_BTF_ID | PTR_TRUSTED, PTR_TO_BTF_ID | MEM_RCU, }, }; static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_BTF_ID | MEM_PERCPU, PTR_TO_BTF_ID | MEM_PERCPU | MEM_RCU, PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED, } }; static const struct bpf_reg_types func_ptr_types = { .types = { PTR_TO_FUNC } }; static const struct bpf_reg_types stack_ptr_types = { .types = { PTR_TO_STACK } }; static const struct bpf_reg_types const_str_ptr_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types timer_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types kptr_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types dynptr_types = { .types = { PTR_TO_STACK, CONST_PTR_TO_DYNPTR, } }; static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_MAP_KEY] = &mem_types, [ARG_PTR_TO_MAP_VALUE] = &mem_types, [ARG_CONST_SIZE] = &scalar_types, [ARG_CONST_SIZE_OR_ZERO] = &scalar_types, [ARG_CONST_ALLOC_SIZE_OR_ZERO] = &scalar_types, [ARG_CONST_MAP_PTR] = &const_map_ptr_types, [ARG_PTR_TO_CTX] = &context_types, [ARG_PTR_TO_SOCK_COMMON] = &sock_types, #ifdef CONFIG_NET [ARG_PTR_TO_BTF_ID_SOCK_COMMON] = &btf_id_sock_common_types, #endif [ARG_PTR_TO_SOCKET] = &fullsock_types, [ARG_PTR_TO_BTF_ID] = &btf_ptr_types, [ARG_PTR_TO_SPIN_LOCK] = &spin_lock_types, [ARG_PTR_TO_MEM] = &mem_types, [ARG_PTR_TO_RINGBUF_MEM] = &ringbuf_mem_types, [ARG_PTR_TO_INT] = &int_ptr_types, [ARG_PTR_TO_LONG] = &int_ptr_types, [ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types, [ARG_PTR_TO_FUNC] = &func_ptr_types, [ARG_PTR_TO_STACK] = &stack_ptr_types, [ARG_PTR_TO_CONST_STR] = &const_str_ptr_types, [ARG_PTR_TO_TIMER] = &timer_types, [ARG_PTR_TO_KPTR] = &kptr_types, [ARG_PTR_TO_DYNPTR] = &dynptr_types, }; static int check_reg_type(struct bpf_verifier_env *env, u32 regno, enum bpf_arg_type arg_type, const u32 *arg_btf_id, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; enum bpf_reg_type expected, type = reg->type; const struct bpf_reg_types *compatible; int i, j; compatible = compatible_reg_types[base_type(arg_type)]; if (!compatible) { verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type); return -EFAULT; } /* ARG_PTR_TO_MEM + RDONLY is compatible with PTR_TO_MEM and PTR_TO_MEM + RDONLY, * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM and NOT with PTR_TO_MEM + RDONLY * * Same for MAYBE_NULL: * * ARG_PTR_TO_MEM + MAYBE_NULL is compatible with PTR_TO_MEM and PTR_TO_MEM + MAYBE_NULL, * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM but NOT with PTR_TO_MEM + MAYBE_NULL * * ARG_PTR_TO_MEM is compatible with PTR_TO_MEM that is tagged with a dynptr type. * * Therefore we fold these flags depending on the arg_type before comparison. */ if (arg_type & MEM_RDONLY) type &= ~MEM_RDONLY; if (arg_type & PTR_MAYBE_NULL) type &= ~PTR_MAYBE_NULL; if (base_type(arg_type) == ARG_PTR_TO_MEM) type &= ~DYNPTR_TYPE_FLAG_MASK; if (meta->func_id == BPF_FUNC_kptr_xchg && type_is_alloc(type)) { type &= ~MEM_ALLOC; type &= ~MEM_PERCPU; } for (i = 0; i < ARRAY_SIZE(compatible->types); i++) { expected = compatible->types[i]; if (expected == NOT_INIT) break; if (type == expected) goto found; } verbose(env, "R%d type=%s expected=", regno, reg_type_str(env, reg->type)); for (j = 0; j + 1 < i; j++) verbose(env, "%s, ", reg_type_str(env, compatible->types[j])); verbose(env, "%s\n", reg_type_str(env, compatible->types[j])); return -EACCES; found: if (base_type(reg->type) != PTR_TO_BTF_ID) return 0; if (compatible == &mem_types) { if (!(arg_type & MEM_RDONLY)) { verbose(env, "%s() may write into memory pointed by R%d type=%s\n", func_id_name(meta->func_id), regno, reg_type_str(env, reg->type)); return -EACCES; } return 0; } switch ((int)reg->type) { case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | PTR_TRUSTED: case PTR_TO_BTF_ID | PTR_TRUSTED | PTR_MAYBE_NULL: case PTR_TO_BTF_ID | MEM_RCU: case PTR_TO_BTF_ID | PTR_MAYBE_NULL: case PTR_TO_BTF_ID | PTR_MAYBE_NULL | MEM_RCU: { /* For bpf_sk_release, it needs to match against first member * 'struct sock_common', hence make an exception for it. This * allows bpf_sk_release to work for multiple socket types. */ bool strict_type_match = arg_type_is_release(arg_type) && meta->func_id != BPF_FUNC_sk_release; if (type_may_be_null(reg->type) && (!type_may_be_null(arg_type) || arg_type_is_release(arg_type))) { verbose(env, "Possibly NULL pointer passed to helper arg%d\n", regno); return -EACCES; } if (!arg_btf_id) { if (!compatible->btf_id) { verbose(env, "verifier internal error: missing arg compatible BTF ID\n"); return -EFAULT; } arg_btf_id = compatible->btf_id; } if (meta->func_id == BPF_FUNC_kptr_xchg) { if (map_kptr_match_type(env, meta->kptr_field, reg, regno)) return -EACCES; } else { if (arg_btf_id == BPF_PTR_POISON) { verbose(env, "verifier internal error:"); verbose(env, "R%d has non-overwritten BPF_PTR_POISON type\n", regno); return -EACCES; } if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off, btf_vmlinux, *arg_btf_id, strict_type_match)) { verbose(env, "R%d is of type %s but %s is expected\n", regno, btf_type_name(reg->btf, reg->btf_id), btf_type_name(btf_vmlinux, *arg_btf_id)); return -EACCES; } } break; } case PTR_TO_BTF_ID | MEM_ALLOC: case PTR_TO_BTF_ID | MEM_PERCPU | MEM_ALLOC: if (meta->func_id != BPF_FUNC_spin_lock && meta->func_id != BPF_FUNC_spin_unlock && meta->func_id != BPF_FUNC_kptr_xchg) { verbose(env, "verifier internal error: unimplemented handling of MEM_ALLOC\n"); return -EFAULT; } if (meta->func_id == BPF_FUNC_kptr_xchg) { if (map_kptr_match_type(env, meta->kptr_field, reg, regno)) return -EACCES; } break; case PTR_TO_BTF_ID | MEM_PERCPU: case PTR_TO_BTF_ID | MEM_PERCPU | MEM_RCU: case PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED: /* Handled by helper specific checks */ break; default: verbose(env, "verifier internal error: invalid PTR_TO_BTF_ID register for type match\n"); return -EFAULT; } return 0; } static struct btf_field * reg_find_field_offset(const struct bpf_reg_state *reg, s32 off, u32 fields) { struct btf_field *field; struct btf_record *rec; rec = reg_btf_record(reg); if (!rec) return NULL; field = btf_record_find(rec, off, fields); if (!field) return NULL; return field; } static int check_func_arg_reg_off(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, enum bpf_arg_type arg_type) { u32 type = reg->type; /* When referenced register is passed to release function, its fixed * offset must be 0. * * We will check arg_type_is_release reg has ref_obj_id when storing * meta->release_regno. */ if (arg_type_is_release(arg_type)) { /* ARG_PTR_TO_DYNPTR with OBJ_RELEASE is a bit special, as it * may not directly point to the object being released, but to * dynptr pointing to such object, which might be at some offset * on the stack. In that case, we simply to fallback to the * default handling. */ if (arg_type_is_dynptr(arg_type) && type == PTR_TO_STACK) return 0; /* Doing check_ptr_off_reg check for the offset will catch this * because fixed_off_ok is false, but checking here allows us * to give the user a better error message. */ if (reg->off) { verbose(env, "R%d must have zero offset when passed to release func or trusted arg to kfunc\n", regno); return -EINVAL; } return __check_ptr_off_reg(env, reg, regno, false); } switch (type) { /* Pointer types where both fixed and variable offset is explicitly allowed: */ case PTR_TO_STACK: case PTR_TO_PACKET: case PTR_TO_PACKET_META: case PTR_TO_MAP_KEY: case PTR_TO_MAP_VALUE: case PTR_TO_MEM: case PTR_TO_MEM | MEM_RDONLY: case PTR_TO_MEM | MEM_RINGBUF: case PTR_TO_BUF: case PTR_TO_BUF | MEM_RDONLY: case PTR_TO_ARENA: case SCALAR_VALUE: return 0; /* All the rest must be rejected, except PTR_TO_BTF_ID which allows * fixed offset. */ case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | MEM_ALLOC: case PTR_TO_BTF_ID | PTR_TRUSTED: case PTR_TO_BTF_ID | MEM_RCU: case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF: case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF | MEM_RCU: /* When referenced PTR_TO_BTF_ID is passed to release function, * its fixed offset must be 0. In the other cases, fixed offset * can be non-zero. This was already checked above. So pass * fixed_off_ok as true to allow fixed offset for all other * cases. var_off always must be 0 for PTR_TO_BTF_ID, hence we * still need to do checks instead of returning. */ return __check_ptr_off_reg(env, reg, regno, true); default: return __check_ptr_off_reg(env, reg, regno, false); } } static struct bpf_reg_state *get_dynptr_arg_reg(struct bpf_verifier_env *env, const struct bpf_func_proto *fn, struct bpf_reg_state *regs) { struct bpf_reg_state *state = NULL; int i; for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) if (arg_type_is_dynptr(fn->arg_type[i])) { if (state) { verbose(env, "verifier internal error: multiple dynptr args\n"); return NULL; } state = ®s[BPF_REG_1 + i]; } if (!state) verbose(env, "verifier internal error: no dynptr arg found\n"); return state; } static int dynptr_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); int spi; if (reg->type == CONST_PTR_TO_DYNPTR) return reg->id; spi = dynptr_get_spi(env, reg); if (spi < 0) return spi; return state->stack[spi].spilled_ptr.id; } static int dynptr_ref_obj_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); int spi; if (reg->type == CONST_PTR_TO_DYNPTR) return reg->ref_obj_id; spi = dynptr_get_spi(env, reg); if (spi < 0) return spi; return state->stack[spi].spilled_ptr.ref_obj_id; } static enum bpf_dynptr_type dynptr_get_type(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); int spi; if (reg->type == CONST_PTR_TO_DYNPTR) return reg->dynptr.type; spi = __get_spi(reg->off); if (spi < 0) { verbose(env, "verifier internal error: invalid spi when querying dynptr type\n"); return BPF_DYNPTR_TYPE_INVALID; } return state->stack[spi].spilled_ptr.dynptr.type; } static int check_reg_const_str(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno) { struct bpf_map *map = reg->map_ptr; int err; int map_off; u64 map_addr; char *str_ptr; if (reg->type != PTR_TO_MAP_VALUE) return -EINVAL; if (!bpf_map_is_rdonly(map)) { verbose(env, "R%d does not point to a readonly map'\n", regno); return -EACCES; } if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d is not a constant address'\n", regno); return -EACCES; } if (!map->ops->map_direct_value_addr) { verbose(env, "no direct value access support for this map type\n"); return -EACCES; } err = check_map_access(env, regno, reg->off, map->value_size - reg->off, false, ACCESS_HELPER); if (err) return err; map_off = reg->off + reg->var_off.value; err = map->ops->map_direct_value_addr(map, &map_addr, map_off); if (err) { verbose(env, "direct value access on string failed\n"); return err; } str_ptr = (char *)(long)(map_addr); if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) { verbose(env, "string is not zero-terminated\n"); return -EINVAL; } return 0; } static int check_func_arg(struct bpf_verifier_env *env, u32 arg, struct bpf_call_arg_meta *meta, const struct bpf_func_proto *fn, int insn_idx) { u32 regno = BPF_REG_1 + arg; struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; enum bpf_arg_type arg_type = fn->arg_type[arg]; enum bpf_reg_type type = reg->type; u32 *arg_btf_id = NULL; int err = 0; if (arg_type == ARG_DONTCARE) return 0; err = check_reg_arg(env, regno, SRC_OP); if (err) return err; if (arg_type == ARG_ANYTHING) { if (is_pointer_value(env, regno)) { verbose(env, "R%d leaks addr into helper function\n", regno); return -EACCES; } return 0; } if (type_is_pkt_pointer(type) && !may_access_direct_pkt_data(env, meta, BPF_READ)) { verbose(env, "helper access to the packet is not allowed\n"); return -EACCES; } if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE) { err = resolve_map_arg_type(env, meta, &arg_type); if (err) return err; } if (register_is_null(reg) && type_may_be_null(arg_type)) /* A NULL register has a SCALAR_VALUE type, so skip * type checking. */ goto skip_type_check; /* arg_btf_id and arg_size are in a union. */ if (base_type(arg_type) == ARG_PTR_TO_BTF_ID || base_type(arg_type) == ARG_PTR_TO_SPIN_LOCK) arg_btf_id = fn->arg_btf_id[arg]; err = check_reg_type(env, regno, arg_type, arg_btf_id, meta); if (err) return err; err = check_func_arg_reg_off(env, reg, regno, arg_type); if (err) return err; skip_type_check: if (arg_type_is_release(arg_type)) { if (arg_type_is_dynptr(arg_type)) { struct bpf_func_state *state = func(env, reg); int spi; /* Only dynptr created on stack can be released, thus * the get_spi and stack state checks for spilled_ptr * should only be done before process_dynptr_func for * PTR_TO_STACK. */ if (reg->type == PTR_TO_STACK) { spi = dynptr_get_spi(env, reg); if (spi < 0 || !state->stack[spi].spilled_ptr.ref_obj_id) { verbose(env, "arg %d is an unacquired reference\n", regno); return -EINVAL; } } else { verbose(env, "cannot release unowned const bpf_dynptr\n"); return -EINVAL; } } else if (!reg->ref_obj_id && !register_is_null(reg)) { verbose(env, "R%d must be referenced when passed to release function\n", regno); return -EINVAL; } if (meta->release_regno) { verbose(env, "verifier internal error: more than one release argument\n"); return -EFAULT; } meta->release_regno = regno; } if (reg->ref_obj_id) { if (meta->ref_obj_id) { verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", regno, reg->ref_obj_id, meta->ref_obj_id); return -EFAULT; } meta->ref_obj_id = reg->ref_obj_id; } switch (base_type(arg_type)) { case ARG_CONST_MAP_PTR: /* bpf_map_xxx(map_ptr) call: remember that map_ptr */ if (meta->map_ptr) { /* Use map_uid (which is unique id of inner map) to reject: * inner_map1 = bpf_map_lookup_elem(outer_map, key1) * inner_map2 = bpf_map_lookup_elem(outer_map, key2) * if (inner_map1 && inner_map2) { * timer = bpf_map_lookup_elem(inner_map1); * if (timer) * // mismatch would have been allowed * bpf_timer_init(timer, inner_map2); * } * * Comparing map_ptr is enough to distinguish normal and outer maps. */ if (meta->map_ptr != reg->map_ptr || meta->map_uid != reg->map_uid) { verbose(env, "timer pointer in R1 map_uid=%d doesn't match map pointer in R2 map_uid=%d\n", meta->map_uid, reg->map_uid); return -EINVAL; } } meta->map_ptr = reg->map_ptr; meta->map_uid = reg->map_uid; break; case ARG_PTR_TO_MAP_KEY: /* bpf_map_xxx(..., map_ptr, ..., key) call: * check that [key, key + map->key_size) are within * stack limits and initialized */ if (!meta->map_ptr) { /* in function declaration map_ptr must come before * map_key, so that it's verified and known before * we have to check map_key here. Otherwise it means * that kernel subsystem misconfigured verifier */ verbose(env, "invalid map_ptr to access map->key\n"); return -EACCES; } err = check_helper_mem_access(env, regno, meta->map_ptr->key_size, false, NULL); break; case ARG_PTR_TO_MAP_VALUE: if (type_may_be_null(arg_type) && register_is_null(reg)) return 0; /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity */ if (!meta->map_ptr) { /* kernel subsystem misconfigured verifier */ verbose(env, "invalid map_ptr to access map->value\n"); return -EACCES; } meta->raw_mode = arg_type & MEM_UNINIT; err = check_helper_mem_access(env, regno, meta->map_ptr->value_size, false, meta); break; case ARG_PTR_TO_PERCPU_BTF_ID: if (!reg->btf_id) { verbose(env, "Helper has invalid btf_id in R%d\n", regno); return -EACCES; } meta->ret_btf = reg->btf; meta->ret_btf_id = reg->btf_id; break; case ARG_PTR_TO_SPIN_LOCK: if (in_rbtree_lock_required_cb(env)) { verbose(env, "can't spin_{lock,unlock} in rbtree cb\n"); return -EACCES; } if (meta->func_id == BPF_FUNC_spin_lock) { err = process_spin_lock(env, regno, true); if (err) return err; } else if (meta->func_id == BPF_FUNC_spin_unlock) { err = process_spin_lock(env, regno, false); if (err) return err; } else { verbose(env, "verifier internal error\n"); return -EFAULT; } break; case ARG_PTR_TO_TIMER: err = process_timer_func(env, regno, meta); if (err) return err; break; case ARG_PTR_TO_FUNC: meta->subprogno = reg->subprogno; break; case ARG_PTR_TO_MEM: /* The access to this pointer is only checked when we hit the * next is_mem_size argument below. */ meta->raw_mode = arg_type & MEM_UNINIT; if (arg_type & MEM_FIXED_SIZE) { err = check_helper_mem_access(env, regno, fn->arg_size[arg], false, meta); } break; case ARG_CONST_SIZE: err = check_mem_size_reg(env, reg, regno, false, meta); break; case ARG_CONST_SIZE_OR_ZERO: err = check_mem_size_reg(env, reg, regno, true, meta); break; case ARG_PTR_TO_DYNPTR: err = process_dynptr_func(env, regno, insn_idx, arg_type, 0); if (err) return err; break; case ARG_CONST_ALLOC_SIZE_OR_ZERO: if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d is not a known constant'\n", regno); return -EACCES; } meta->mem_size = reg->var_off.value; err = mark_chain_precision(env, regno); if (err) return err; break; case ARG_PTR_TO_INT: case ARG_PTR_TO_LONG: { int size = int_ptr_type_to_size(arg_type); err = check_helper_mem_access(env, regno, size, false, meta); if (err) return err; err = check_ptr_alignment(env, reg, 0, size, true); break; } case ARG_PTR_TO_CONST_STR: { err = check_reg_const_str(env, reg, regno); if (err) return err; break; } case ARG_PTR_TO_KPTR: err = process_kptr_func(env, regno, meta); if (err) return err; break; } return err; } static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) { enum bpf_attach_type eatype = env->prog->expected_attach_type; enum bpf_prog_type type = resolve_prog_type(env->prog); if (func_id != BPF_FUNC_map_update_elem && func_id != BPF_FUNC_map_delete_elem) return false; /* It's not possible to get access to a locked struct sock in these * contexts, so updating is safe. */ switch (type) { case BPF_PROG_TYPE_TRACING: if (eatype == BPF_TRACE_ITER) return true; break; case BPF_PROG_TYPE_SOCK_OPS: /* map_update allowed only via dedicated helpers with event type checks */ if (func_id == BPF_FUNC_map_delete_elem) return true; break; case BPF_PROG_TYPE_SOCKET_FILTER: case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_SK_LOOKUP: return true; default: break; } verbose(env, "cannot update sockmap in this context\n"); return false; } static bool allow_tail_call_in_subprogs(struct bpf_verifier_env *env) { return env->prog->jit_requested && bpf_jit_supports_subprog_tailcalls(); } static int check_map_func_compatibility(struct bpf_verifier_env *env, struct bpf_map *map, int func_id) { if (!map) return 0; /* We need a two way check, first is from map perspective ... */ switch (map->map_type) { case BPF_MAP_TYPE_PROG_ARRAY: if (func_id != BPF_FUNC_tail_call) goto error; break; case BPF_MAP_TYPE_PERF_EVENT_ARRAY: if (func_id != BPF_FUNC_perf_event_read && func_id != BPF_FUNC_perf_event_output && func_id != BPF_FUNC_skb_output && func_id != BPF_FUNC_perf_event_read_value && func_id != BPF_FUNC_xdp_output) goto error; break; case BPF_MAP_TYPE_RINGBUF: if (func_id != BPF_FUNC_ringbuf_output && func_id != BPF_FUNC_ringbuf_reserve && func_id != BPF_FUNC_ringbuf_query && func_id != BPF_FUNC_ringbuf_reserve_dynptr && func_id != BPF_FUNC_ringbuf_submit_dynptr && func_id != BPF_FUNC_ringbuf_discard_dynptr) goto error; break; case BPF_MAP_TYPE_USER_RINGBUF: if (func_id != BPF_FUNC_user_ringbuf_drain) goto error; break; case BPF_MAP_TYPE_STACK_TRACE: if (func_id != BPF_FUNC_get_stackid) goto error; break; case BPF_MAP_TYPE_CGROUP_ARRAY: if (func_id != BPF_FUNC_skb_under_cgroup && func_id != BPF_FUNC_current_task_under_cgroup) goto error; break; case BPF_MAP_TYPE_CGROUP_STORAGE: case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: if (func_id != BPF_FUNC_get_local_storage) goto error; break; case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: if (func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_elem) goto error; break; /* Restrict bpf side of cpumap and xskmap, open when use-cases * appear. */ case BPF_MAP_TYPE_CPUMAP: if (func_id != BPF_FUNC_redirect_map) goto error; break; case BPF_MAP_TYPE_XSKMAP: if (func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_elem) goto error; break; case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: if (func_id != BPF_FUNC_map_lookup_elem) goto error; break; case BPF_MAP_TYPE_SOCKMAP: if (func_id != BPF_FUNC_sk_redirect_map && func_id != BPF_FUNC_sock_map_update && func_id != BPF_FUNC_msg_redirect_map && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && !may_update_sockmap(env, func_id)) goto error; break; case BPF_MAP_TYPE_SOCKHASH: if (func_id != BPF_FUNC_sk_redirect_hash && func_id != BPF_FUNC_sock_hash_update && func_id != BPF_FUNC_msg_redirect_hash && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && !may_update_sockmap(env, func_id)) goto error; break; case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: if (func_id != BPF_FUNC_sk_select_reuseport) goto error; break; case BPF_MAP_TYPE_QUEUE: case BPF_MAP_TYPE_STACK: if (func_id != BPF_FUNC_map_peek_elem && func_id != BPF_FUNC_map_pop_elem && func_id != BPF_FUNC_map_push_elem) goto error; break; case BPF_MAP_TYPE_SK_STORAGE: if (func_id != BPF_FUNC_sk_storage_get && func_id != BPF_FUNC_sk_storage_delete && func_id != BPF_FUNC_kptr_xchg) goto error; break; case BPF_MAP_TYPE_INODE_STORAGE: if (func_id != BPF_FUNC_inode_storage_get && func_id != BPF_FUNC_inode_storage_delete && func_id != BPF_FUNC_kptr_xchg) goto error; break; case BPF_MAP_TYPE_TASK_STORAGE: if (func_id != BPF_FUNC_task_storage_get && func_id != BPF_FUNC_task_storage_delete && func_id != BPF_FUNC_kptr_xchg) goto error; break; case BPF_MAP_TYPE_CGRP_STORAGE: if (func_id != BPF_FUNC_cgrp_storage_get && func_id != BPF_FUNC_cgrp_storage_delete && func_id != BPF_FUNC_kptr_xchg) goto error; break; case BPF_MAP_TYPE_BLOOM_FILTER: if (func_id != BPF_FUNC_map_peek_elem && func_id != BPF_FUNC_map_push_elem) goto error; break; default: break; } /* ... and second from the function itself. */ switch (func_id) { case BPF_FUNC_tail_call: if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) goto error; if (env->subprog_cnt > 1 && !allow_tail_call_in_subprogs(env)) { verbose(env, "tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls\n"); return -EINVAL; } break; case BPF_FUNC_perf_event_read: case BPF_FUNC_perf_event_output: case BPF_FUNC_perf_event_read_value: case BPF_FUNC_skb_output: case BPF_FUNC_xdp_output: if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) goto error; break; case BPF_FUNC_ringbuf_output: case BPF_FUNC_ringbuf_reserve: case BPF_FUNC_ringbuf_query: case BPF_FUNC_ringbuf_reserve_dynptr: case BPF_FUNC_ringbuf_submit_dynptr: case BPF_FUNC_ringbuf_discard_dynptr: if (map->map_type != BPF_MAP_TYPE_RINGBUF) goto error; break; case BPF_FUNC_user_ringbuf_drain: if (map->map_type != BPF_MAP_TYPE_USER_RINGBUF) goto error; break; case BPF_FUNC_get_stackid: if (map->map_type != BPF_MAP_TYPE_STACK_TRACE) goto error; break; case BPF_FUNC_current_task_under_cgroup: case BPF_FUNC_skb_under_cgroup: if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY) goto error; break; case BPF_FUNC_redirect_map: if (map->map_type != BPF_MAP_TYPE_DEVMAP && map->map_type != BPF_MAP_TYPE_DEVMAP_HASH && map->map_type != BPF_MAP_TYPE_CPUMAP && map->map_type != BPF_MAP_TYPE_XSKMAP) goto error; break; case BPF_FUNC_sk_redirect_map: case BPF_FUNC_msg_redirect_map: case BPF_FUNC_sock_map_update: if (map->map_type != BPF_MAP_TYPE_SOCKMAP) goto error; break; case BPF_FUNC_sk_redirect_hash: case BPF_FUNC_msg_redirect_hash: case BPF_FUNC_sock_hash_update: if (map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; case BPF_FUNC_get_local_storage: if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && map->map_type != BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) goto error; break; case BPF_FUNC_sk_select_reuseport: if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && map->map_type != BPF_MAP_TYPE_SOCKMAP && map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; case BPF_FUNC_map_pop_elem: if (map->map_type != BPF_MAP_TYPE_QUEUE && map->map_type != BPF_MAP_TYPE_STACK) goto error; break; case BPF_FUNC_map_peek_elem: case BPF_FUNC_map_push_elem: if (map->map_type != BPF_MAP_TYPE_QUEUE && map->map_type != BPF_MAP_TYPE_STACK && map->map_type != BPF_MAP_TYPE_BLOOM_FILTER) goto error; break; case BPF_FUNC_map_lookup_percpu_elem: if (map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY && map->map_type != BPF_MAP_TYPE_PERCPU_HASH && map->map_type != BPF_MAP_TYPE_LRU_PERCPU_HASH) goto error; break; case BPF_FUNC_sk_storage_get: case BPF_FUNC_sk_storage_delete: if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) goto error; break; case BPF_FUNC_inode_storage_get: case BPF_FUNC_inode_storage_delete: if (map->map_type != BPF_MAP_TYPE_INODE_STORAGE) goto error; break; case BPF_FUNC_task_storage_get: case BPF_FUNC_task_storage_delete: if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE) goto error; break; case BPF_FUNC_cgrp_storage_get: case BPF_FUNC_cgrp_storage_delete: if (map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) goto error; break; default: break; } return 0; error: verbose(env, "cannot pass map_type %d into func %s#%d\n", map->map_type, func_id_name(func_id), func_id); return -EINVAL; } static bool check_raw_mode_ok(const struct bpf_func_proto *fn) { int count = 0; if (fn->arg1_type == ARG_PTR_TO_UNINIT_MEM) count++; if (fn->arg2_type == ARG_PTR_TO_UNINIT_MEM) count++; if (fn->arg3_type == ARG_PTR_TO_UNINIT_MEM) count++; if (fn->arg4_type == ARG_PTR_TO_UNINIT_MEM) count++; if (fn->arg5_type == ARG_PTR_TO_UNINIT_MEM) count++; /* We only support one arg being in raw mode at the moment, * which is sufficient for the helper functions we have * right now. */ return count <= 1; } static bool check_args_pair_invalid(const struct bpf_func_proto *fn, int arg) { bool is_fixed = fn->arg_type[arg] & MEM_FIXED_SIZE; bool has_size = fn->arg_size[arg] != 0; bool is_next_size = false; if (arg + 1 < ARRAY_SIZE(fn->arg_type)) is_next_size = arg_type_is_mem_size(fn->arg_type[arg + 1]); if (base_type(fn->arg_type[arg]) != ARG_PTR_TO_MEM) return is_next_size; return has_size == is_next_size || is_next_size == is_fixed; } static bool check_arg_pair_ok(const struct bpf_func_proto *fn) { /* bpf_xxx(..., buf, len) call will access 'len' * bytes from memory 'buf'. Both arg types need * to be paired, so make sure there's no buggy * helper function specification. */ if (arg_type_is_mem_size(fn->arg1_type) || check_args_pair_invalid(fn, 0) || check_args_pair_invalid(fn, 1) || check_args_pair_invalid(fn, 2) || check_args_pair_invalid(fn, 3) || check_args_pair_invalid(fn, 4)) return false; return true; } static bool check_btf_id_ok(const struct bpf_func_proto *fn) { int i; for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) { if (base_type(fn->arg_type[i]) == ARG_PTR_TO_BTF_ID) return !!fn->arg_btf_id[i]; if (base_type(fn->arg_type[i]) == ARG_PTR_TO_SPIN_LOCK) return fn->arg_btf_id[i] == BPF_PTR_POISON; if (base_type(fn->arg_type[i]) != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i] && /* arg_btf_id and arg_size are in a union. */ (base_type(fn->arg_type[i]) != ARG_PTR_TO_MEM || !(fn->arg_type[i] & MEM_FIXED_SIZE))) return false; } return true; } static int check_func_proto(const struct bpf_func_proto *fn, int func_id) { return check_raw_mode_ok(fn) && check_arg_pair_ok(fn) && check_btf_id_ok(fn) ? 0 : -EINVAL; } /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] * are now invalid, so turn them into unknown SCALAR_VALUE. * * This also applies to dynptr slices belonging to skb and xdp dynptrs, * since these slices point to packet data. */ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) { struct bpf_func_state *state; struct bpf_reg_state *reg; bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ if (reg_is_pkt_pointer_any(reg) || reg_is_dynptr_slice_pkt(reg)) mark_reg_invalid(env, reg); })); } enum { AT_PKT_END = -1, BEYOND_PKT_END = -2, }; static void mark_pkt_end(struct bpf_verifier_state *vstate, int regn, bool range_open) { struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regn]; if (reg->type != PTR_TO_PACKET) /* PTR_TO_PACKET_META is not supported yet */ return; /* The 'reg' is pkt > pkt_end or pkt >= pkt_end. * How far beyond pkt_end it goes is unknown. * if (!range_open) it's the case of pkt >= pkt_end * if (range_open) it's the case of pkt > pkt_end * hence this pointer is at least 1 byte bigger than pkt_end */ if (range_open) reg->range = BEYOND_PKT_END; else reg->range = AT_PKT_END; } /* The pointer with the specified id has released its reference to kernel * resources. Identify all copies of the same pointer and clear the reference. */ static int release_reference(struct bpf_verifier_env *env, int ref_obj_id) { struct bpf_func_state *state; struct bpf_reg_state *reg; int err; err = release_reference_state(cur_func(env), ref_obj_id); if (err) return err; bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ if (reg->ref_obj_id == ref_obj_id) mark_reg_invalid(env, reg); })); return 0; } static void invalidate_non_owning_refs(struct bpf_verifier_env *env) { struct bpf_func_state *unused; struct bpf_reg_state *reg; bpf_for_each_reg_in_vstate(env->cur_state, unused, reg, ({ if (type_is_non_owning_ref(reg->type)) mark_reg_invalid(env, reg); })); } static void clear_caller_saved_regs(struct bpf_verifier_env *env, struct bpf_reg_state *regs) { int i; /* after the call registers r0 - r5 were scratched */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); __check_reg_arg(env, regs, caller_saved[i], DST_OP_NO_MARK); } } typedef int (*set_callee_state_fn)(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx); static int set_callee_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx); static int setup_func_entry(struct bpf_verifier_env *env, int subprog, int callsite, set_callee_state_fn set_callee_state_cb, struct bpf_verifier_state *state) { struct bpf_func_state *caller, *callee; int err; if (state->curframe + 1 >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep\n", state->curframe + 2); return -E2BIG; } if (state->frame[state->curframe + 1]) { verbose(env, "verifier bug. Frame %d already allocated\n", state->curframe + 1); return -EFAULT; } caller = state->frame[state->curframe]; callee = kzalloc(sizeof(*callee), GFP_KERNEL); if (!callee) return -ENOMEM; state->frame[state->curframe + 1] = callee; /* callee cannot access r0, r6 - r9 for reading and has to write * into its own stack before reading from it. * callee can read/write into caller's stack */ init_func_state(env, callee, /* remember the callsite, it will be used by bpf_exit */ callsite, state->curframe + 1 /* frameno within this callchain */, subprog /* subprog number within this prog */); /* Transfer references to the callee */ err = copy_reference_state(callee, caller); err = err ?: set_callee_state_cb(env, caller, callee, callsite); if (err) goto err_out; /* only increment it after check_reg_arg() finished */ state->curframe++; return 0; err_out: free_func_state(callee); state->frame[state->curframe + 1] = NULL; return err; } static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, const struct btf *btf, struct bpf_reg_state *regs) { struct bpf_subprog_info *sub = subprog_info(env, subprog); struct bpf_verifier_log *log = &env->log; u32 i; int ret; ret = btf_prepare_func_args(env, subprog); if (ret) return ret; /* check that BTF function arguments match actual types that the * verifier sees. */ for (i = 0; i < sub->arg_cnt; i++) { u32 regno = i + 1; struct bpf_reg_state *reg = ®s[regno]; struct bpf_subprog_arg_info *arg = &sub->args[i]; if (arg->arg_type == ARG_ANYTHING) { if (reg->type != SCALAR_VALUE) { bpf_log(log, "R%d is not a scalar\n", regno); return -EINVAL; } } else if (arg->arg_type == ARG_PTR_TO_CTX) { ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE); if (ret < 0) return ret; /* If function expects ctx type in BTF check that caller * is passing PTR_TO_CTX. */ if (reg->type != PTR_TO_CTX) { bpf_log(log, "arg#%d expects pointer to ctx\n", i); return -EINVAL; } } else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) { ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE); if (ret < 0) return ret; if (check_mem_reg(env, reg, regno, arg->mem_size)) return -EINVAL; if (!(arg->arg_type & PTR_MAYBE_NULL) && (reg->type & PTR_MAYBE_NULL)) { bpf_log(log, "arg#%d is expected to be non-NULL\n", i); return -EINVAL; } } else if (base_type(arg->arg_type) == ARG_PTR_TO_ARENA) { /* * Can pass any value and the kernel won't crash, but * only PTR_TO_ARENA or SCALAR make sense. Everything * else is a bug in the bpf program. Point it out to * the user at the verification time instead of * run-time debug nightmare. */ if (reg->type != PTR_TO_ARENA && reg->type != SCALAR_VALUE) { bpf_log(log, "R%d is not a pointer to arena or scalar.\n", regno); return -EINVAL; } } else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) { ret = process_dynptr_func(env, regno, -1, arg->arg_type, 0); if (ret) return ret; } else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) { struct bpf_call_arg_meta meta; int err; if (register_is_null(reg) && type_may_be_null(arg->arg_type)) continue; memset(&meta, 0, sizeof(meta)); /* leave func_id as zero */ err = check_reg_type(env, regno, arg->arg_type, &arg->btf_id, &meta); err = err ?: check_func_arg_reg_off(env, reg, regno, arg->arg_type); if (err) return err; } else { bpf_log(log, "verifier bug: unrecognized arg#%d type %d\n", i, arg->arg_type); return -EFAULT; } } return 0; } /* Compare BTF of a function call with given bpf_reg_state. * Returns: * EFAULT - there is a verifier bug. Abort verification. * EINVAL - there is a type mismatch or BTF is not available. * 0 - BTF matches with what bpf_reg_state expects. * Only PTR_TO_CTX and SCALAR_VALUE states are recognized. */ static int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs) { struct bpf_prog *prog = env->prog; struct btf *btf = prog->aux->btf; u32 btf_id; int err; if (!prog->aux->func_info) return -EINVAL; btf_id = prog->aux->func_info[subprog].type_id; if (!btf_id) return -EFAULT; if (prog->aux->func_info_aux[subprog].unreliable) return -EINVAL; err = btf_check_func_arg_match(env, subprog, btf, regs); /* Compiler optimizations can remove arguments from static functions * or mismatched type can be passed into a global function. * In such cases mark the function as unreliable from BTF point of view. */ if (err) prog->aux->func_info_aux[subprog].unreliable = true; return err; } static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int insn_idx, int subprog, set_callee_state_fn set_callee_state_cb) { struct bpf_verifier_state *state = env->cur_state, *callback_state; struct bpf_func_state *caller, *callee; int err; caller = state->frame[state->curframe]; err = btf_check_subprog_call(env, subprog, caller->regs); if (err == -EFAULT) return err; /* set_callee_state is used for direct subprog calls, but we are * interested in validating only BPF helpers that can call subprogs as * callbacks */ env->subprog_info[subprog].is_cb = true; if (bpf_pseudo_kfunc_call(insn) && !is_callback_calling_kfunc(insn->imm)) { verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n", func_id_name(insn->imm), insn->imm); return -EFAULT; } else if (!bpf_pseudo_kfunc_call(insn) && !is_callback_calling_function(insn->imm)) { /* helper */ verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n", func_id_name(insn->imm), insn->imm); return -EFAULT; } if (is_async_callback_calling_insn(insn)) { struct bpf_verifier_state *async_cb; /* there is no real recursion here. timer and workqueue callbacks are async */ env->subprog_info[subprog].is_async_cb = true; async_cb = push_async_cb(env, env->subprog_info[subprog].start, insn_idx, subprog, is_bpf_wq_set_callback_impl_kfunc(insn->imm)); if (!async_cb) return -EFAULT; callee = async_cb->frame[0]; callee->async_entry_cnt = caller->async_entry_cnt + 1; /* Convert bpf_timer_set_callback() args into timer callback args */ err = set_callee_state_cb(env, caller, callee, insn_idx); if (err) return err; return 0; } /* for callback functions enqueue entry to callback and * proceed with next instruction within current frame. */ callback_state = push_stack(env, env->subprog_info[subprog].start, insn_idx, false); if (!callback_state) return -ENOMEM; err = setup_func_entry(env, subprog, insn_idx, set_callee_state_cb, callback_state); if (err) return err; callback_state->callback_unroll_depth++; callback_state->frame[callback_state->curframe - 1]->callback_depth++; caller->callback_depth = 0; return 0; } static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state; struct bpf_func_state *caller; int err, subprog, target_insn; target_insn = *insn_idx + insn->imm + 1; subprog = find_subprog(env, target_insn); if (subprog < 0) { verbose(env, "verifier bug. No program starts at insn %d\n", target_insn); return -EFAULT; } caller = state->frame[state->curframe]; err = btf_check_subprog_call(env, subprog, caller->regs); if (err == -EFAULT) return err; if (subprog_is_global(env, subprog)) { const char *sub_name = subprog_name(env, subprog); /* Only global subprogs cannot be called with a lock held. */ if (env->cur_state->active_lock.ptr) { verbose(env, "global function calls are not allowed while holding a lock,\n" "use static function instead\n"); return -EINVAL; } /* Only global subprogs cannot be called with preemption disabled. */ if (env->cur_state->active_preempt_lock) { verbose(env, "global function calls are not allowed with preemption disabled,\n" "use static function instead\n"); return -EINVAL; } if (err) { verbose(env, "Caller passes invalid args into func#%d ('%s')\n", subprog, sub_name); return err; } verbose(env, "Func#%d ('%s') is global and assumed valid.\n", subprog, sub_name); /* mark global subprog for verifying after main prog */ subprog_aux(env, subprog)->called = true; clear_caller_saved_regs(env, caller->regs); /* All global functions return a 64-bit SCALAR_VALUE */ mark_reg_unknown(env, caller->regs, BPF_REG_0); caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; /* continue with next insn after call */ return 0; } /* for regular function entry setup new frame and continue * from that frame. */ err = setup_func_entry(env, subprog, *insn_idx, set_callee_state, state); if (err) return err; clear_caller_saved_regs(env, caller->regs); /* and go analyze first insn of the callee */ *insn_idx = env->subprog_info[subprog].start - 1; if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "caller:\n"); print_verifier_state(env, caller, true); verbose(env, "callee:\n"); print_verifier_state(env, state->frame[state->curframe], true); } return 0; } int map_set_for_each_callback_args(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee) { /* bpf_for_each_map_elem(struct bpf_map *map, void *callback_fn, * void *callback_ctx, u64 flags); * callback_fn(struct bpf_map *map, void *key, void *value, * void *callback_ctx); */ callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1]; callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].map_ptr = caller->regs[BPF_REG_1].map_ptr; callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE; __mark_reg_known_zero(&callee->regs[BPF_REG_3]); callee->regs[BPF_REG_3].map_ptr = caller->regs[BPF_REG_1].map_ptr; /* pointer to stack or null */ callee->regs[BPF_REG_4] = caller->regs[BPF_REG_3]; /* unused */ __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); return 0; } static int set_callee_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { int i; /* copy r1 - r5 args that callee can access. The copy includes parent * pointers, which connects us up to the liveness chain */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) callee->regs[i] = caller->regs[i]; return 0; } static int set_map_elem_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { struct bpf_insn_aux_data *insn_aux = &env->insn_aux_data[insn_idx]; struct bpf_map *map; int err; /* valid map_ptr and poison value does not matter */ map = insn_aux->map_ptr_state.map_ptr; if (!map->ops->map_set_for_each_callback_args || !map->ops->map_for_each_callback) { verbose(env, "callback function not allowed for map\n"); return -ENOTSUPP; } err = map->ops->map_set_for_each_callback_args(env, caller, callee); if (err) return err; callee->in_callback_fn = true; callee->callback_ret_range = retval_range(0, 1); return 0; } static int set_loop_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { /* bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, * u64 flags); * callback_fn(u32 index, void *callback_ctx); */ callee->regs[BPF_REG_1].type = SCALAR_VALUE; callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; /* unused */ __mark_reg_not_init(env, &callee->regs[BPF_REG_3]); __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; callee->callback_ret_range = retval_range(0, 1); return 0; } static int set_timer_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { struct bpf_map *map_ptr = caller->regs[BPF_REG_1].map_ptr; /* bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn); * callback_fn(struct bpf_map *map, void *key, void *value); */ callee->regs[BPF_REG_1].type = CONST_PTR_TO_MAP; __mark_reg_known_zero(&callee->regs[BPF_REG_1]); callee->regs[BPF_REG_1].map_ptr = map_ptr; callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].map_ptr = map_ptr; callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE; __mark_reg_known_zero(&callee->regs[BPF_REG_3]); callee->regs[BPF_REG_3].map_ptr = map_ptr; /* unused */ __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_async_callback_fn = true; callee->callback_ret_range = retval_range(0, 1); return 0; } static int set_find_vma_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { /* bpf_find_vma(struct task_struct *task, u64 addr, * void *callback_fn, void *callback_ctx, u64 flags) * (callback_fn)(struct task_struct *task, * struct vm_area_struct *vma, void *callback_ctx); */ callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1]; callee->regs[BPF_REG_2].type = PTR_TO_BTF_ID; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].btf = btf_vmlinux; callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA]; /* pointer to stack or null */ callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4]; /* unused */ __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; callee->callback_ret_range = retval_range(0, 1); return 0; } static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { /* bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void * callback_ctx, u64 flags); * callback_fn(const struct bpf_dynptr_t* dynptr, void *callback_ctx); */ __mark_reg_not_init(env, &callee->regs[BPF_REG_0]); mark_dynptr_cb_reg(env, &callee->regs[BPF_REG_1], BPF_DYNPTR_TYPE_LOCAL); callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; /* unused */ __mark_reg_not_init(env, &callee->regs[BPF_REG_3]); __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; callee->callback_ret_range = retval_range(0, 1); return 0; } static int set_rbtree_add_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { /* void bpf_rbtree_add_impl(struct bpf_rb_root *root, struct bpf_rb_node *node, * bool (less)(struct bpf_rb_node *a, const struct bpf_rb_node *b)); * * 'struct bpf_rb_node *node' arg to bpf_rbtree_add_impl is the same PTR_TO_BTF_ID w/ offset * that 'less' callback args will be receiving. However, 'node' arg was release_reference'd * by this point, so look at 'root' */ struct btf_field *field; field = reg_find_field_offset(&caller->regs[BPF_REG_1], caller->regs[BPF_REG_1].off, BPF_RB_ROOT); if (!field || !field->graph_root.value_btf_id) return -EFAULT; mark_reg_graph_node(callee->regs, BPF_REG_1, &field->graph_root); ref_set_non_owning(env, &callee->regs[BPF_REG_1]); mark_reg_graph_node(callee->regs, BPF_REG_2, &field->graph_root); ref_set_non_owning(env, &callee->regs[BPF_REG_2]); __mark_reg_not_init(env, &callee->regs[BPF_REG_3]); __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; callee->callback_ret_range = retval_range(0, 1); return 0; } static bool is_rbtree_lock_required_kfunc(u32 btf_id); /* Are we currently verifying the callback for a rbtree helper that must * be called with lock held? If so, no need to complain about unreleased * lock */ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env) { struct bpf_verifier_state *state = env->cur_state; struct bpf_insn *insn = env->prog->insnsi; struct bpf_func_state *callee; int kfunc_btf_id; if (!state->curframe) return false; callee = state->frame[state->curframe]; if (!callee->in_callback_fn) return false; kfunc_btf_id = insn[callee->callsite].imm; return is_rbtree_lock_required_kfunc(kfunc_btf_id); } static bool retval_range_within(struct bpf_retval_range range, const struct bpf_reg_state *reg) { return range.minval <= reg->smin_value && reg->smax_value <= range.maxval; } static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state, *prev_st; struct bpf_func_state *caller, *callee; struct bpf_reg_state *r0; bool in_callback_fn; int err; callee = state->frame[state->curframe]; r0 = &callee->regs[BPF_REG_0]; if (r0->type == PTR_TO_STACK) { /* technically it's ok to return caller's stack pointer * (or caller's caller's pointer) back to the caller, * since these pointers are valid. Only current stack * pointer will be invalid as soon as function exits, * but let's be conservative */ verbose(env, "cannot return stack pointer to the caller\n"); return -EINVAL; } caller = state->frame[state->curframe - 1]; if (callee->in_callback_fn) { if (r0->type != SCALAR_VALUE) { verbose(env, "R0 not a scalar value\n"); return -EACCES; } /* we are going to rely on register's precise value */ err = mark_reg_read(env, r0, r0->parent, REG_LIVE_READ64); err = err ?: mark_chain_precision(env, BPF_REG_0); if (err) return err; /* enforce R0 return value range */ if (!retval_range_within(callee->callback_ret_range, r0)) { verbose_invalid_scalar(env, r0, callee->callback_ret_range, "At callback return", "R0"); return -EINVAL; } if (!calls_callback(env, callee->callsite)) { verbose(env, "BUG: in callback at %d, callsite %d !calls_callback\n", *insn_idx, callee->callsite); return -EFAULT; } } else { /* return to the caller whatever r0 had in the callee */ caller->regs[BPF_REG_0] = *r0; } /* callback_fn frame should have released its own additions to parent's * reference state at this point, or check_reference_leak would * complain, hence it must be the same as the caller. There is no need * to copy it back. */ if (!callee->in_callback_fn) { /* Transfer references to the caller */ err = copy_reference_state(caller, callee); if (err) return err; } /* for callbacks like bpf_loop or bpf_for_each_map_elem go back to callsite, * there function call logic would reschedule callback visit. If iteration * converges is_state_visited() would prune that visit eventually. */ in_callback_fn = callee->in_callback_fn; if (in_callback_fn) *insn_idx = callee->callsite; else *insn_idx = callee->callsite + 1; if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "returning from callee:\n"); print_verifier_state(env, callee, true); verbose(env, "to caller at %d:\n", *insn_idx); print_verifier_state(env, caller, true); } /* clear everything in the callee. In case of exceptional exits using * bpf_throw, this will be done by copy_verifier_state for extra frames. */ free_func_state(callee); state->frame[state->curframe--] = NULL; /* for callbacks widen imprecise scalars to make programs like below verify: * * struct ctx { int i; } * void cb(int idx, struct ctx *ctx) { ctx->i++; ... } * ... * struct ctx = { .i = 0; } * bpf_loop(100, cb, &ctx, 0); * * This is similar to what is done in process_iter_next_call() for open * coded iterators. */ prev_st = in_callback_fn ? find_prev_entry(env, state, *insn_idx) : NULL; if (prev_st) { err = widen_imprecise_scalars(env, prev_st, state); if (err) return err; } return 0; } static int do_refine_retval_range(struct bpf_verifier_env *env, struct bpf_reg_state *regs, int ret_type, int func_id, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *ret_reg = ®s[BPF_REG_0]; if (ret_type != RET_INTEGER) return 0; switch (func_id) { case BPF_FUNC_get_stack: case BPF_FUNC_get_task_stack: case BPF_FUNC_probe_read_str: case BPF_FUNC_probe_read_kernel_str: case BPF_FUNC_probe_read_user_str: ret_reg->smax_value = meta->msize_max_value; ret_reg->s32_max_value = meta->msize_max_value; ret_reg->smin_value = -MAX_ERRNO; ret_reg->s32_min_value = -MAX_ERRNO; reg_bounds_sync(ret_reg); break; case BPF_FUNC_get_smp_processor_id: ret_reg->umax_value = nr_cpu_ids - 1; ret_reg->u32_max_value = nr_cpu_ids - 1; ret_reg->smax_value = nr_cpu_ids - 1; ret_reg->s32_max_value = nr_cpu_ids - 1; ret_reg->umin_value = 0; ret_reg->u32_min_value = 0; ret_reg->smin_value = 0; ret_reg->s32_min_value = 0; reg_bounds_sync(ret_reg); break; } return reg_bounds_sanity_check(env, ret_reg, "retval"); } static int record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, int func_id, int insn_idx) { struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; struct bpf_map *map = meta->map_ptr; if (func_id != BPF_FUNC_tail_call && func_id != BPF_FUNC_map_lookup_elem && func_id != BPF_FUNC_map_update_elem && func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_map_push_elem && func_id != BPF_FUNC_map_pop_elem && func_id != BPF_FUNC_map_peek_elem && func_id != BPF_FUNC_for_each_map_elem && func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_percpu_elem) return 0; if (map == NULL) { verbose(env, "kernel subsystem misconfigured verifier\n"); return -EINVAL; } /* In case of read-only, some additional restrictions * need to be applied in order to prevent altering the * state of the map from program side. */ if ((map->map_flags & BPF_F_RDONLY_PROG) && (func_id == BPF_FUNC_map_delete_elem || func_id == BPF_FUNC_map_update_elem || func_id == BPF_FUNC_map_push_elem || func_id == BPF_FUNC_map_pop_elem)) { verbose(env, "write into map forbidden\n"); return -EACCES; } if (!aux->map_ptr_state.map_ptr) bpf_map_ptr_store(aux, meta->map_ptr, !meta->map_ptr->bypass_spec_v1, false); else if (aux->map_ptr_state.map_ptr != meta->map_ptr) bpf_map_ptr_store(aux, meta->map_ptr, !meta->map_ptr->bypass_spec_v1, true); return 0; } static int record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, int func_id, int insn_idx) { struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; struct bpf_reg_state *regs = cur_regs(env), *reg; struct bpf_map *map = meta->map_ptr; u64 val, max; int err; if (func_id != BPF_FUNC_tail_call) return 0; if (!map || map->map_type != BPF_MAP_TYPE_PROG_ARRAY) { verbose(env, "kernel subsystem misconfigured verifier\n"); return -EINVAL; } reg = ®s[BPF_REG_3]; val = reg->var_off.value; max = map->max_entries; if (!(is_reg_const(reg, false) && val < max)) { bpf_map_key_store(aux, BPF_MAP_KEY_POISON); return 0; } err = mark_chain_precision(env, BPF_REG_3); if (err) return err; if (bpf_map_key_unseen(aux)) bpf_map_key_store(aux, val); else if (!bpf_map_key_poisoned(aux) && bpf_map_key_immediate(aux) != val) bpf_map_key_store(aux, BPF_MAP_KEY_POISON); return 0; } static int check_reference_leak(struct bpf_verifier_env *env, bool exception_exit) { struct bpf_func_state *state = cur_func(env); bool refs_lingering = false; int i; if (!exception_exit && state->frameno && !state->in_callback_fn) return 0; for (i = 0; i < state->acquired_refs; i++) { if (!exception_exit && state->in_callback_fn && state->refs[i].callback_ref != state->frameno) continue; verbose(env, "Unreleased reference id=%d alloc_insn=%d\n", state->refs[i].id, state->refs[i].insn_idx); refs_lingering = true; } return refs_lingering ? -EINVAL : 0; } static int check_bpf_snprintf_call(struct bpf_verifier_env *env, struct bpf_reg_state *regs) { struct bpf_reg_state *fmt_reg = ®s[BPF_REG_3]; struct bpf_reg_state *data_len_reg = ®s[BPF_REG_5]; struct bpf_map *fmt_map = fmt_reg->map_ptr; struct bpf_bprintf_data data = {}; int err, fmt_map_off, num_args; u64 fmt_addr; char *fmt; /* data must be an array of u64 */ if (data_len_reg->var_off.value % 8) return -EINVAL; num_args = data_len_reg->var_off.value / 8; /* fmt being ARG_PTR_TO_CONST_STR guarantees that var_off is const * and map_direct_value_addr is set. */ fmt_map_off = fmt_reg->off + fmt_reg->var_off.value; err = fmt_map->ops->map_direct_value_addr(fmt_map, &fmt_addr, fmt_map_off); if (err) { verbose(env, "verifier bug\n"); return -EFAULT; } fmt = (char *)(long)fmt_addr + fmt_map_off; /* We are also guaranteed that fmt+fmt_map_off is NULL terminated, we * can focus on validating the format specifiers. */ err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, num_args, &data); if (err < 0) verbose(env, "Invalid format string\n"); return err; } static int check_get_func_ip(struct bpf_verifier_env *env) { enum bpf_prog_type type = resolve_prog_type(env->prog); int func_id = BPF_FUNC_get_func_ip; if (type == BPF_PROG_TYPE_TRACING) { if (!bpf_prog_has_trampoline(env->prog)) { verbose(env, "func %s#%d supported only for fentry/fexit/fmod_ret programs\n", func_id_name(func_id), func_id); return -ENOTSUPP; } return 0; } else if (type == BPF_PROG_TYPE_KPROBE) { return 0; } verbose(env, "func %s#%d not supported for program type %d\n", func_id_name(func_id), func_id, type); return -ENOTSUPP; } static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env) { return &env->insn_aux_data[env->insn_idx]; } static bool loop_flag_is_zero(struct bpf_verifier_env *env) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[BPF_REG_4]; bool reg_is_null = register_is_null(reg); if (reg_is_null) mark_chain_precision(env, BPF_REG_4); return reg_is_null; } static void update_loop_inline_state(struct bpf_verifier_env *env, u32 subprogno) { struct bpf_loop_inline_state *state = &cur_aux(env)->loop_inline_state; if (!state->initialized) { state->initialized = 1; state->fit_for_inline = loop_flag_is_zero(env); state->callback_subprogno = subprogno; return; } if (!state->fit_for_inline) return; state->fit_for_inline = (loop_flag_is_zero(env) && state->callback_subprogno == subprogno); } static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) { enum bpf_prog_type prog_type = resolve_prog_type(env->prog); bool returns_cpu_specific_alloc_ptr = false; const struct bpf_func_proto *fn = NULL; enum bpf_return_type ret_type; enum bpf_type_flag ret_flag; struct bpf_reg_state *regs; struct bpf_call_arg_meta meta; int insn_idx = *insn_idx_p; bool changes_data; int i, err, func_id; /* find function prototype */ func_id = insn->imm; if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) { verbose(env, "invalid func %s#%d\n", func_id_name(func_id), func_id); return -EINVAL; } if (env->ops->get_func_proto) fn = env->ops->get_func_proto(func_id, env->prog); if (!fn) { verbose(env, "program of this type cannot use helper %s#%d\n", func_id_name(func_id), func_id); return -EINVAL; } /* eBPF programs must be GPL compatible to use GPL-ed functions */ if (!env->prog->gpl_compatible && fn->gpl_only) { verbose(env, "cannot call GPL-restricted function from non-GPL compatible program\n"); return -EINVAL; } if (fn->allowed && !fn->allowed(env->prog)) { verbose(env, "helper call is not allowed in probe\n"); return -EINVAL; } if (!in_sleepable(env) && fn->might_sleep) { verbose(env, "helper call might sleep in a non-sleepable prog\n"); return -EINVAL; } /* With LD_ABS/IND some JITs save/restore skb from r1. */ changes_data = bpf_helper_changes_pkt_data(fn->func); if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) { verbose(env, "kernel subsystem misconfigured func %s#%d: r1 != ctx\n", func_id_name(func_id), func_id); return -EINVAL; } memset(&meta, 0, sizeof(meta)); meta.pkt_access = fn->pkt_access; err = check_func_proto(fn, func_id); if (err) { verbose(env, "kernel subsystem misconfigured func %s#%d\n", func_id_name(func_id), func_id); return err; } if (env->cur_state->active_rcu_lock) { if (fn->might_sleep) { verbose(env, "sleepable helper %s#%d in rcu_read_lock region\n", func_id_name(func_id), func_id); return -EINVAL; } if (in_sleepable(env) && is_storage_get_function(func_id)) env->insn_aux_data[insn_idx].storage_get_func_atomic = true; } if (env->cur_state->active_preempt_lock) { if (fn->might_sleep) { verbose(env, "sleepable helper %s#%d in non-preemptible region\n", func_id_name(func_id), func_id); return -EINVAL; } if (in_sleepable(env) && is_storage_get_function(func_id)) env->insn_aux_data[insn_idx].storage_get_func_atomic = true; } meta.func_id = func_id; /* check args */ for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { err = check_func_arg(env, i, &meta, fn, insn_idx); if (err) return err; } err = record_func_map(env, &meta, func_id, insn_idx); if (err) return err; err = record_func_key(env, &meta, func_id, insn_idx); if (err) return err; /* Mark slots with STACK_MISC in case of raw mode, stack offset * is inferred from register state. */ for (i = 0; i < meta.access_size; i++) { err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, BPF_WRITE, -1, false, false); if (err) return err; } regs = cur_regs(env); if (meta.release_regno) { err = -EINVAL; /* This can only be set for PTR_TO_STACK, as CONST_PTR_TO_DYNPTR cannot * be released by any dynptr helper. Hence, unmark_stack_slots_dynptr * is safe to do directly. */ if (arg_type_is_dynptr(fn->arg_type[meta.release_regno - BPF_REG_1])) { if (regs[meta.release_regno].type == CONST_PTR_TO_DYNPTR) { verbose(env, "verifier internal error: CONST_PTR_TO_DYNPTR cannot be released\n"); return -EFAULT; } err = unmark_stack_slots_dynptr(env, ®s[meta.release_regno]); } else if (func_id == BPF_FUNC_kptr_xchg && meta.ref_obj_id) { u32 ref_obj_id = meta.ref_obj_id; bool in_rcu = in_rcu_cs(env); struct bpf_func_state *state; struct bpf_reg_state *reg; err = release_reference_state(cur_func(env), ref_obj_id); if (!err) { bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ if (reg->ref_obj_id == ref_obj_id) { if (in_rcu && (reg->type & MEM_ALLOC) && (reg->type & MEM_PERCPU)) { reg->ref_obj_id = 0; reg->type &= ~MEM_ALLOC; reg->type |= MEM_RCU; } else { mark_reg_invalid(env, reg); } } })); } } else if (meta.ref_obj_id) { err = release_reference(env, meta.ref_obj_id); } else if (register_is_null(®s[meta.release_regno])) { /* meta.ref_obj_id can only be 0 if register that is meant to be * released is NULL, which must be > R0. */ err = 0; } if (err) { verbose(env, "func %s#%d reference has not been acquired before\n", func_id_name(func_id), func_id); return err; } } switch (func_id) { case BPF_FUNC_tail_call: err = check_reference_leak(env, false); if (err) { verbose(env, "tail_call would lead to reference leak\n"); return err; } break; case BPF_FUNC_get_local_storage: /* check that flags argument in get_local_storage(map, flags) is 0, * this is required because get_local_storage() can't return an error. */ if (!register_is_null(®s[BPF_REG_2])) { verbose(env, "get_local_storage() doesn't support non-zero flags\n"); return -EINVAL; } break; case BPF_FUNC_for_each_map_elem: err = push_callback_call(env, insn, insn_idx, meta.subprogno, set_map_elem_callback_state); break; case BPF_FUNC_timer_set_callback: err = push_callback_call(env, insn, insn_idx, meta.subprogno, set_timer_callback_state); break; case BPF_FUNC_find_vma: err = push_callback_call(env, insn, insn_idx, meta.subprogno, set_find_vma_callback_state); break; case BPF_FUNC_snprintf: err = check_bpf_snprintf_call(env, regs); break; case BPF_FUNC_loop: update_loop_inline_state(env, meta.subprogno); /* Verifier relies on R1 value to determine if bpf_loop() iteration * is finished, thus mark it precise. */ err = mark_chain_precision(env, BPF_REG_1); if (err) return err; if (cur_func(env)->callback_depth < regs[BPF_REG_1].umax_value) { err = push_callback_call(env, insn, insn_idx, meta.subprogno, set_loop_callback_state); } else { cur_func(env)->callback_depth = 0; if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "frame%d bpf_loop iteration limit reached\n", env->cur_state->curframe); } break; case BPF_FUNC_dynptr_from_mem: if (regs[BPF_REG_1].type != PTR_TO_MAP_VALUE) { verbose(env, "Unsupported reg type %s for bpf_dynptr_from_mem data\n", reg_type_str(env, regs[BPF_REG_1].type)); return -EACCES; } break; case BPF_FUNC_set_retval: if (prog_type == BPF_PROG_TYPE_LSM && env->prog->expected_attach_type == BPF_LSM_CGROUP) { if (!env->prog->aux->attach_func_proto->type) { /* Make sure programs that attach to void * hooks don't try to modify return value. */ verbose(env, "BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n"); return -EINVAL; } } break; case BPF_FUNC_dynptr_data: { struct bpf_reg_state *reg; int id, ref_obj_id; reg = get_dynptr_arg_reg(env, fn, regs); if (!reg) return -EFAULT; if (meta.dynptr_id) { verbose(env, "verifier internal error: meta.dynptr_id already set\n"); return -EFAULT; } if (meta.ref_obj_id) { verbose(env, "verifier internal error: meta.ref_obj_id already set\n"); return -EFAULT; } id = dynptr_id(env, reg); if (id < 0) { verbose(env, "verifier internal error: failed to obtain dynptr id\n"); return id; } ref_obj_id = dynptr_ref_obj_id(env, reg); if (ref_obj_id < 0) { verbose(env, "verifier internal error: failed to obtain dynptr ref_obj_id\n"); return ref_obj_id; } meta.dynptr_id = id; meta.ref_obj_id = ref_obj_id; break; } case BPF_FUNC_dynptr_write: { enum bpf_dynptr_type dynptr_type; struct bpf_reg_state *reg; reg = get_dynptr_arg_reg(env, fn, regs); if (!reg) return -EFAULT; dynptr_type = dynptr_get_type(env, reg); if (dynptr_type == BPF_DYNPTR_TYPE_INVALID) return -EFAULT; if (dynptr_type == BPF_DYNPTR_TYPE_SKB) /* this will trigger clear_all_pkt_pointers(), which will * invalidate all dynptr slices associated with the skb */ changes_data = true; break; } case BPF_FUNC_per_cpu_ptr: case BPF_FUNC_this_cpu_ptr: { struct bpf_reg_state *reg = ®s[BPF_REG_1]; const struct btf_type *type; if (reg->type & MEM_RCU) { type = btf_type_by_id(reg->btf, reg->btf_id); if (!type || !btf_type_is_struct(type)) { verbose(env, "Helper has invalid btf/btf_id in R1\n"); return -EFAULT; } returns_cpu_specific_alloc_ptr = true; env->insn_aux_data[insn_idx].call_with_percpu_alloc_ptr = true; } break; } case BPF_FUNC_user_ringbuf_drain: err = push_callback_call(env, insn, insn_idx, meta.subprogno, set_user_ringbuf_callback_state); break; } if (err) return err; /* reset caller saved regs */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } /* helper call returns 64-bit value. */ regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; /* update return register (already marked as written above) */ ret_type = fn->ret_type; ret_flag = type_flag(ret_type); switch (base_type(ret_type)) { case RET_INTEGER: /* sets type to SCALAR_VALUE */ mark_reg_unknown(env, regs, BPF_REG_0); break; case RET_VOID: regs[BPF_REG_0].type = NOT_INIT; break; case RET_PTR_TO_MAP_VALUE: /* There is no offset yet applied, variable or fixed */ mark_reg_known_zero(env, regs, BPF_REG_0); /* remember map_ptr, so that check_map_access() * can check 'value_size' boundary of memory access * to map element returned from bpf_map_lookup_elem() */ if (meta.map_ptr == NULL) { verbose(env, "kernel subsystem misconfigured verifier\n"); return -EINVAL; } regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].map_uid = meta.map_uid; regs[BPF_REG_0].type = PTR_TO_MAP_VALUE | ret_flag; if (!type_may_be_null(ret_type) && btf_record_has_field(meta.map_ptr->record, BPF_SPIN_LOCK)) { regs[BPF_REG_0].id = ++env->id_gen; } break; case RET_PTR_TO_SOCKET: mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_SOCKET | ret_flag; break; case RET_PTR_TO_SOCK_COMMON: mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON | ret_flag; break; case RET_PTR_TO_TCP_SOCK: mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_TCP_SOCK | ret_flag; break; case RET_PTR_TO_MEM: mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag; regs[BPF_REG_0].mem_size = meta.mem_size; break; case RET_PTR_TO_MEM_OR_BTF_ID: { const struct btf_type *t; mark_reg_known_zero(env, regs, BPF_REG_0); t = btf_type_skip_modifiers(meta.ret_btf, meta.ret_btf_id, NULL); if (!btf_type_is_struct(t)) { u32 tsize; const struct btf_type *ret; const char *tname; /* resolve the type size of ksym. */ ret = btf_resolve_size(meta.ret_btf, t, &tsize); if (IS_ERR(ret)) { tname = btf_name_by_offset(meta.ret_btf, t->name_off); verbose(env, "unable to resolve the size of type '%s': %ld\n", tname, PTR_ERR(ret)); return -EINVAL; } regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag; regs[BPF_REG_0].mem_size = tsize; } else { if (returns_cpu_specific_alloc_ptr) { regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC | MEM_RCU; } else { /* MEM_RDONLY may be carried from ret_flag, but it * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise * it will confuse the check of PTR_TO_BTF_ID in * check_mem_access(). */ ret_flag &= ~MEM_RDONLY; regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; } regs[BPF_REG_0].btf = meta.ret_btf; regs[BPF_REG_0].btf_id = meta.ret_btf_id; } break; } case RET_PTR_TO_BTF_ID: { struct btf *ret_btf; int ret_btf_id; mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; if (func_id == BPF_FUNC_kptr_xchg) { ret_btf = meta.kptr_field->kptr.btf; ret_btf_id = meta.kptr_field->kptr.btf_id; if (!btf_is_kernel(ret_btf)) { regs[BPF_REG_0].type |= MEM_ALLOC; if (meta.kptr_field->type == BPF_KPTR_PERCPU) regs[BPF_REG_0].type |= MEM_PERCPU; } } else { if (fn->ret_btf_id == BPF_PTR_POISON) { verbose(env, "verifier internal error:"); verbose(env, "func %s has non-overwritten BPF_PTR_POISON return type\n", func_id_name(func_id)); return -EINVAL; } ret_btf = btf_vmlinux; ret_btf_id = *fn->ret_btf_id; } if (ret_btf_id == 0) { verbose(env, "invalid return type %u of func %s#%d\n", base_type(ret_type), func_id_name(func_id), func_id); return -EINVAL; } regs[BPF_REG_0].btf = ret_btf; regs[BPF_REG_0].btf_id = ret_btf_id; break; } default: verbose(env, "unknown return type %u of func %s#%d\n", base_type(ret_type), func_id_name(func_id), func_id); return -EINVAL; } if (type_may_be_null(regs[BPF_REG_0].type)) regs[BPF_REG_0].id = ++env->id_gen; if (helper_multiple_ref_obj_use(func_id, meta.map_ptr)) { verbose(env, "verifier internal error: func %s#%d sets ref_obj_id more than once\n", func_id_name(func_id), func_id); return -EFAULT; } if (is_dynptr_ref_function(func_id)) regs[BPF_REG_0].dynptr_id = meta.dynptr_id; if (is_ptr_cast_function(func_id) || is_dynptr_ref_function(func_id)) { /* For release_reference() */ regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id; } else if (is_acquire_function(func_id, meta.map_ptr)) { int id = acquire_reference_state(env, insn_idx); if (id < 0) return id; /* For mark_ptr_or_null_reg() */ regs[BPF_REG_0].id = id; /* For release_reference() */ regs[BPF_REG_0].ref_obj_id = id; } err = do_refine_retval_range(env, regs, fn->ret_type, func_id, &meta); if (err) return err; err = check_map_func_compatibility(env, meta.map_ptr, func_id); if (err) return err; if ((func_id == BPF_FUNC_get_stack || func_id == BPF_FUNC_get_task_stack) && !env->prog->has_callchain_buf) { const char *err_str; #ifdef CONFIG_PERF_EVENTS err = get_callchain_buffers(sysctl_perf_event_max_stack); err_str = "cannot get callchain buffer for func %s#%d\n"; #else err = -ENOTSUPP; err_str = "func %s#%d not supported without CONFIG_PERF_EVENTS\n"; #endif if (err) { verbose(env, err_str, func_id_name(func_id), func_id); return err; } env->prog->has_callchain_buf = true; } if (func_id == BPF_FUNC_get_stackid || func_id == BPF_FUNC_get_stack) env->prog->call_get_stack = true; if (func_id == BPF_FUNC_get_func_ip) { if (check_get_func_ip(env)) return -ENOTSUPP; env->prog->call_get_func_ip = true; } if (changes_data) clear_all_pkt_pointers(env); return 0; } /* mark_btf_func_reg_size() is used when the reg size is determined by * the BTF func_proto's return value size and argument. */ static void mark_btf_func_reg_size(struct bpf_verifier_env *env, u32 regno, size_t reg_size) { struct bpf_reg_state *reg = &cur_regs(env)[regno]; if (regno == BPF_REG_0) { /* Function return value */ reg->live |= REG_LIVE_WRITTEN; reg->subreg_def = reg_size == sizeof(u64) ? DEF_NOT_SUBREG : env->insn_idx + 1; } else { /* Function argument */ if (reg_size == sizeof(u64)) { mark_insn_zext(env, reg); mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); } else { mark_reg_read(env, reg, reg->parent, REG_LIVE_READ32); } } } static bool is_kfunc_acquire(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_ACQUIRE; } static bool is_kfunc_release(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_RELEASE; } static bool is_kfunc_trusted_args(struct bpf_kfunc_call_arg_meta *meta) { return (meta->kfunc_flags & KF_TRUSTED_ARGS) || is_kfunc_release(meta); } static bool is_kfunc_sleepable(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_SLEEPABLE; } static bool is_kfunc_destructive(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_DESTRUCTIVE; } static bool is_kfunc_rcu(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_RCU; } static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_RCU_PROTECTED; } static bool is_kfunc_arg_mem_size(const struct btf *btf, const struct btf_param *arg, const struct bpf_reg_state *reg) { const struct btf_type *t; t = btf_type_skip_modifiers(btf, arg->type, NULL); if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) return false; return btf_param_match_suffix(btf, arg, "__sz"); } static bool is_kfunc_arg_const_mem_size(const struct btf *btf, const struct btf_param *arg, const struct bpf_reg_state *reg) { const struct btf_type *t; t = btf_type_skip_modifiers(btf, arg->type, NULL); if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) return false; return btf_param_match_suffix(btf, arg, "__szk"); } static bool is_kfunc_arg_optional(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__opt"); } static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__k"); } static bool is_kfunc_arg_ignore(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__ign"); } static bool is_kfunc_arg_map(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__map"); } static bool is_kfunc_arg_alloc_obj(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__alloc"); } static bool is_kfunc_arg_uninit(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__uninit"); } static bool is_kfunc_arg_refcounted_kptr(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__refcounted_kptr"); } static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__nullable"); } static bool is_kfunc_arg_const_str(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__str"); } static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, const struct btf_param *arg, const char *name) { int len, target_len = strlen(name); const char *param_name; param_name = btf_name_by_offset(btf, arg->name_off); if (str_is_empty(param_name)) return false; len = strlen(param_name); if (len != target_len) return false; if (strcmp(param_name, name)) return false; return true; } enum { KF_ARG_DYNPTR_ID, KF_ARG_LIST_HEAD_ID, KF_ARG_LIST_NODE_ID, KF_ARG_RB_ROOT_ID, KF_ARG_RB_NODE_ID, KF_ARG_WORKQUEUE_ID, }; BTF_ID_LIST(kf_arg_btf_ids) BTF_ID(struct, bpf_dynptr_kern) BTF_ID(struct, bpf_list_head) BTF_ID(struct, bpf_list_node) BTF_ID(struct, bpf_rb_root) BTF_ID(struct, bpf_rb_node) BTF_ID(struct, bpf_wq) static bool __is_kfunc_ptr_arg_type(const struct btf *btf, const struct btf_param *arg, int type) { const struct btf_type *t; u32 res_id; t = btf_type_skip_modifiers(btf, arg->type, NULL); if (!t) return false; if (!btf_type_is_ptr(t)) return false; t = btf_type_skip_modifiers(btf, t->type, &res_id); if (!t) return false; return btf_types_are_same(btf, res_id, btf_vmlinux, kf_arg_btf_ids[type]); } static bool is_kfunc_arg_dynptr(const struct btf *btf, const struct btf_param *arg) { return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_DYNPTR_ID); } static bool is_kfunc_arg_list_head(const struct btf *btf, const struct btf_param *arg) { return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_LIST_HEAD_ID); } static bool is_kfunc_arg_list_node(const struct btf *btf, const struct btf_param *arg) { return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_LIST_NODE_ID); } static bool is_kfunc_arg_rbtree_root(const struct btf *btf, const struct btf_param *arg) { return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_RB_ROOT_ID); } static bool is_kfunc_arg_rbtree_node(const struct btf *btf, const struct btf_param *arg) { return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_RB_NODE_ID); } static bool is_kfunc_arg_wq(const struct btf *btf, const struct btf_param *arg) { return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_WORKQUEUE_ID); } static bool is_kfunc_arg_callback(struct bpf_verifier_env *env, const struct btf *btf, const struct btf_param *arg) { const struct btf_type *t; t = btf_type_resolve_func_ptr(btf, arg->type, NULL); if (!t) return false; return true; } /* Returns true if struct is composed of scalars, 4 levels of nesting allowed */ static bool __btf_type_is_scalar_struct(struct bpf_verifier_env *env, const struct btf *btf, const struct btf_type *t, int rec) { const struct btf_type *member_type; const struct btf_member *member; u32 i; if (!btf_type_is_struct(t)) return false; for_each_member(i, t, member) { const struct btf_array *array; member_type = btf_type_skip_modifiers(btf, member->type, NULL); if (btf_type_is_struct(member_type)) { if (rec >= 3) { verbose(env, "max struct nesting depth exceeded\n"); return false; } if (!__btf_type_is_scalar_struct(env, btf, member_type, rec + 1)) return false; continue; } if (btf_type_is_array(member_type)) { array = btf_array(member_type); if (!array->nelems) return false; member_type = btf_type_skip_modifiers(btf, array->type, NULL); if (!btf_type_is_scalar(member_type)) return false; continue; } if (!btf_type_is_scalar(member_type)) return false; } return true; } enum kfunc_ptr_arg_type { KF_ARG_PTR_TO_CTX, KF_ARG_PTR_TO_ALLOC_BTF_ID, /* Allocated object */ KF_ARG_PTR_TO_REFCOUNTED_KPTR, /* Refcounted local kptr */ KF_ARG_PTR_TO_DYNPTR, KF_ARG_PTR_TO_ITER, KF_ARG_PTR_TO_LIST_HEAD, KF_ARG_PTR_TO_LIST_NODE, KF_ARG_PTR_TO_BTF_ID, /* Also covers reg2btf_ids conversions */ KF_ARG_PTR_TO_MEM, KF_ARG_PTR_TO_MEM_SIZE, /* Size derived from next argument, skip it */ KF_ARG_PTR_TO_CALLBACK, KF_ARG_PTR_TO_RB_ROOT, KF_ARG_PTR_TO_RB_NODE, KF_ARG_PTR_TO_NULL, KF_ARG_PTR_TO_CONST_STR, KF_ARG_PTR_TO_MAP, KF_ARG_PTR_TO_WORKQUEUE, }; enum special_kfunc_type { KF_bpf_obj_new_impl, KF_bpf_obj_drop_impl, KF_bpf_refcount_acquire_impl, KF_bpf_list_push_front_impl, KF_bpf_list_push_back_impl, KF_bpf_list_pop_front, KF_bpf_list_pop_back, KF_bpf_cast_to_kern_ctx, KF_bpf_rdonly_cast, KF_bpf_rcu_read_lock, KF_bpf_rcu_read_unlock, KF_bpf_rbtree_remove, KF_bpf_rbtree_add_impl, KF_bpf_rbtree_first, KF_bpf_dynptr_from_skb, KF_bpf_dynptr_from_xdp, KF_bpf_dynptr_slice, KF_bpf_dynptr_slice_rdwr, KF_bpf_dynptr_clone, KF_bpf_percpu_obj_new_impl, KF_bpf_percpu_obj_drop_impl, KF_bpf_throw, KF_bpf_wq_set_callback_impl, KF_bpf_preempt_disable, KF_bpf_preempt_enable, KF_bpf_iter_css_task_new, KF_bpf_session_cookie, }; BTF_SET_START(special_kfunc_set) BTF_ID(func, bpf_obj_new_impl) BTF_ID(func, bpf_obj_drop_impl) BTF_ID(func, bpf_refcount_acquire_impl) BTF_ID(func, bpf_list_push_front_impl) BTF_ID(func, bpf_list_push_back_impl) BTF_ID(func, bpf_list_pop_front) BTF_ID(func, bpf_list_pop_back) BTF_ID(func, bpf_cast_to_kern_ctx) BTF_ID(func, bpf_rdonly_cast) BTF_ID(func, bpf_rbtree_remove) BTF_ID(func, bpf_rbtree_add_impl) BTF_ID(func, bpf_rbtree_first) BTF_ID(func, bpf_dynptr_from_skb) BTF_ID(func, bpf_dynptr_from_xdp) BTF_ID(func, bpf_dynptr_slice) BTF_ID(func, bpf_dynptr_slice_rdwr) BTF_ID(func, bpf_dynptr_clone) BTF_ID(func, bpf_percpu_obj_new_impl) BTF_ID(func, bpf_percpu_obj_drop_impl) BTF_ID(func, bpf_throw) BTF_ID(func, bpf_wq_set_callback_impl) #ifdef CONFIG_CGROUPS BTF_ID(func, bpf_iter_css_task_new) #endif BTF_SET_END(special_kfunc_set) BTF_ID_LIST(special_kfunc_list) BTF_ID(func, bpf_obj_new_impl) BTF_ID(func, bpf_obj_drop_impl) BTF_ID(func, bpf_refcount_acquire_impl) BTF_ID(func, bpf_list_push_front_impl) BTF_ID(func, bpf_list_push_back_impl) BTF_ID(func, bpf_list_pop_front) BTF_ID(func, bpf_list_pop_back) BTF_ID(func, bpf_cast_to_kern_ctx) BTF_ID(func, bpf_rdonly_cast) BTF_ID(func, bpf_rcu_read_lock) BTF_ID(func, bpf_rcu_read_unlock) BTF_ID(func, bpf_rbtree_remove) BTF_ID(func, bpf_rbtree_add_impl) BTF_ID(func, bpf_rbtree_first) BTF_ID(func, bpf_dynptr_from_skb) BTF_ID(func, bpf_dynptr_from_xdp) BTF_ID(func, bpf_dynptr_slice) BTF_ID(func, bpf_dynptr_slice_rdwr) BTF_ID(func, bpf_dynptr_clone) BTF_ID(func, bpf_percpu_obj_new_impl) BTF_ID(func, bpf_percpu_obj_drop_impl) BTF_ID(func, bpf_throw) BTF_ID(func, bpf_wq_set_callback_impl) BTF_ID(func, bpf_preempt_disable) BTF_ID(func, bpf_preempt_enable) #ifdef CONFIG_CGROUPS BTF_ID(func, bpf_iter_css_task_new) #else BTF_ID_UNUSED #endif #ifdef CONFIG_BPF_EVENTS BTF_ID(func, bpf_session_cookie) #else BTF_ID_UNUSED #endif static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) { if (meta->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl] && meta->arg_owning_ref) { return false; } return meta->kfunc_flags & KF_RET_NULL; } static bool is_kfunc_bpf_rcu_read_lock(struct bpf_kfunc_call_arg_meta *meta) { return meta->func_id == special_kfunc_list[KF_bpf_rcu_read_lock]; } static bool is_kfunc_bpf_rcu_read_unlock(struct bpf_kfunc_call_arg_meta *meta) { return meta->func_id == special_kfunc_list[KF_bpf_rcu_read_unlock]; } static bool is_kfunc_bpf_preempt_disable(struct bpf_kfunc_call_arg_meta *meta) { return meta->func_id == special_kfunc_list[KF_bpf_preempt_disable]; } static bool is_kfunc_bpf_preempt_enable(struct bpf_kfunc_call_arg_meta *meta) { return meta->func_id == special_kfunc_list[KF_bpf_preempt_enable]; } static enum kfunc_ptr_arg_type get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta, const struct btf_type *t, const struct btf_type *ref_t, const char *ref_tname, const struct btf_param *args, int argno, int nargs) { u32 regno = argno + 1; struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[regno]; bool arg_mem_size = false; if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) return KF_ARG_PTR_TO_CTX; /* In this function, we verify the kfunc's BTF as per the argument type, * leaving the rest of the verification with respect to the register * type to our caller. When a set of conditions hold in the BTF type of * arguments, we resolve it to a known kfunc_ptr_arg_type. */ if (btf_is_prog_ctx_type(&env->log, meta->btf, t, resolve_prog_type(env->prog), argno)) return KF_ARG_PTR_TO_CTX; if (is_kfunc_arg_alloc_obj(meta->btf, &args[argno])) return KF_ARG_PTR_TO_ALLOC_BTF_ID; if (is_kfunc_arg_refcounted_kptr(meta->btf, &args[argno])) return KF_ARG_PTR_TO_REFCOUNTED_KPTR; if (is_kfunc_arg_dynptr(meta->btf, &args[argno])) return KF_ARG_PTR_TO_DYNPTR; if (is_kfunc_arg_iter(meta, argno)) return KF_ARG_PTR_TO_ITER; if (is_kfunc_arg_list_head(meta->btf, &args[argno])) return KF_ARG_PTR_TO_LIST_HEAD; if (is_kfunc_arg_list_node(meta->btf, &args[argno])) return KF_ARG_PTR_TO_LIST_NODE; if (is_kfunc_arg_rbtree_root(meta->btf, &args[argno])) return KF_ARG_PTR_TO_RB_ROOT; if (is_kfunc_arg_rbtree_node(meta->btf, &args[argno])) return KF_ARG_PTR_TO_RB_NODE; if (is_kfunc_arg_const_str(meta->btf, &args[argno])) return KF_ARG_PTR_TO_CONST_STR; if (is_kfunc_arg_map(meta->btf, &args[argno])) return KF_ARG_PTR_TO_MAP; if (is_kfunc_arg_wq(meta->btf, &args[argno])) return KF_ARG_PTR_TO_WORKQUEUE; if ((base_type(reg->type) == PTR_TO_BTF_ID || reg2btf_ids[base_type(reg->type)])) { if (!btf_type_is_struct(ref_t)) { verbose(env, "kernel function %s args#%d pointer type %s %s is not supported\n", meta->func_name, argno, btf_type_str(ref_t), ref_tname); return -EINVAL; } return KF_ARG_PTR_TO_BTF_ID; } if (is_kfunc_arg_callback(env, meta->btf, &args[argno])) return KF_ARG_PTR_TO_CALLBACK; if (is_kfunc_arg_nullable(meta->btf, &args[argno]) && register_is_null(reg)) return KF_ARG_PTR_TO_NULL; if (argno + 1 < nargs && (is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1]) || is_kfunc_arg_const_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1]))) arg_mem_size = true; /* This is the catch all argument type of register types supported by * check_helper_mem_access. However, we only allow when argument type is * pointer to scalar, or struct composed (recursively) of scalars. When * arg_mem_size is true, the pointer can be void *. */ if (!btf_type_is_scalar(ref_t) && !__btf_type_is_scalar_struct(env, meta->btf, ref_t, 0) && (arg_mem_size ? !btf_type_is_void(ref_t) : 1)) { verbose(env, "arg#%d pointer type %s %s must point to %sscalar, or struct with scalar\n", argno, btf_type_str(ref_t), ref_tname, arg_mem_size ? "void, " : ""); return -EINVAL; } return arg_mem_size ? KF_ARG_PTR_TO_MEM_SIZE : KF_ARG_PTR_TO_MEM; } static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg, const struct btf_type *ref_t, const char *ref_tname, u32 ref_id, struct bpf_kfunc_call_arg_meta *meta, int argno) { const struct btf_type *reg_ref_t; bool strict_type_match = false; const struct btf *reg_btf; const char *reg_ref_tname; u32 reg_ref_id; if (base_type(reg->type) == PTR_TO_BTF_ID) { reg_btf = reg->btf; reg_ref_id = reg->btf_id; } else { reg_btf = btf_vmlinux; reg_ref_id = *reg2btf_ids[base_type(reg->type)]; } /* Enforce strict type matching for calls to kfuncs that are acquiring * or releasing a reference, or are no-cast aliases. We do _not_ * enforce strict matching for plain KF_TRUSTED_ARGS kfuncs by default, * as we want to enable BPF programs to pass types that are bitwise * equivalent without forcing them to explicitly cast with something * like bpf_cast_to_kern_ctx(). * * For example, say we had a type like the following: * * struct bpf_cpumask { * cpumask_t cpumask; * refcount_t usage; * }; * * Note that as specified in <linux/cpumask.h>, cpumask_t is typedef'ed * to a struct cpumask, so it would be safe to pass a struct * bpf_cpumask * to a kfunc expecting a struct cpumask *. * * The philosophy here is similar to how we allow scalars of different * types to be passed to kfuncs as long as the size is the same. The * only difference here is that we're simply allowing * btf_struct_ids_match() to walk the struct at the 0th offset, and * resolve types. */ if (is_kfunc_acquire(meta) || (is_kfunc_release(meta) && reg->ref_obj_id) || btf_type_ids_nocast_alias(&env->log, reg_btf, reg_ref_id, meta->btf, ref_id)) strict_type_match = true; WARN_ON_ONCE(is_kfunc_trusted_args(meta) && reg->off); reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id, ®_ref_id); reg_ref_tname = btf_name_by_offset(reg_btf, reg_ref_t->name_off); if (!btf_struct_ids_match(&env->log, reg_btf, reg_ref_id, reg->off, meta->btf, ref_id, strict_type_match)) { verbose(env, "kernel function %s args#%d expected pointer to %s %s but R%d has a pointer to %s %s\n", meta->func_name, argno, btf_type_str(ref_t), ref_tname, argno + 1, btf_type_str(reg_ref_t), reg_ref_tname); return -EINVAL; } return 0; } static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_verifier_state *state = env->cur_state; struct btf_record *rec = reg_btf_record(reg); if (!state->active_lock.ptr) { verbose(env, "verifier internal error: ref_set_non_owning w/o active lock\n"); return -EFAULT; } if (type_flag(reg->type) & NON_OWN_REF) { verbose(env, "verifier internal error: NON_OWN_REF already set\n"); return -EFAULT; } reg->type |= NON_OWN_REF; if (rec->refcount_off >= 0) reg->type |= MEM_RCU; return 0; } static int ref_convert_owning_non_owning(struct bpf_verifier_env *env, u32 ref_obj_id) { struct bpf_func_state *state, *unused; struct bpf_reg_state *reg; int i; state = cur_func(env); if (!ref_obj_id) { verbose(env, "verifier internal error: ref_obj_id is zero for " "owning -> non-owning conversion\n"); return -EFAULT; } for (i = 0; i < state->acquired_refs; i++) { if (state->refs[i].id != ref_obj_id) continue; /* Clear ref_obj_id here so release_reference doesn't clobber * the whole reg */ bpf_for_each_reg_in_vstate(env->cur_state, unused, reg, ({ if (reg->ref_obj_id == ref_obj_id) { reg->ref_obj_id = 0; ref_set_non_owning(env, reg); } })); return 0; } verbose(env, "verifier internal error: ref state missing for ref_obj_id\n"); return -EFAULT; } /* Implementation details: * * Each register points to some region of memory, which we define as an * allocation. Each allocation may embed a bpf_spin_lock which protects any * special BPF objects (bpf_list_head, bpf_rb_root, etc.) part of the same * allocation. The lock and the data it protects are colocated in the same * memory region. * * Hence, everytime a register holds a pointer value pointing to such * allocation, the verifier preserves a unique reg->id for it. * * The verifier remembers the lock 'ptr' and the lock 'id' whenever * bpf_spin_lock is called. * * To enable this, lock state in the verifier captures two values: * active_lock.ptr = Register's type specific pointer * active_lock.id = A unique ID for each register pointer value * * Currently, PTR_TO_MAP_VALUE and PTR_TO_BTF_ID | MEM_ALLOC are the two * supported register types. * * The active_lock.ptr in case of map values is the reg->map_ptr, and in case of * allocated objects is the reg->btf pointer. * * The active_lock.id is non-unique for maps supporting direct_value_addr, as we * can establish the provenance of the map value statically for each distinct * lookup into such maps. They always contain a single map value hence unique * IDs for each pseudo load pessimizes the algorithm and rejects valid programs. * * So, in case of global variables, they use array maps with max_entries = 1, * hence their active_lock.ptr becomes map_ptr and id = 0 (since they all point * into the same map value as max_entries is 1, as described above). * * In case of inner map lookups, the inner map pointer has same map_ptr as the * outer map pointer (in verifier context), but each lookup into an inner map * assigns a fresh reg->id to the lookup, so while lookups into distinct inner * maps from the same outer map share the same map_ptr as active_lock.ptr, they * will get different reg->id assigned to each lookup, hence different * active_lock.id. * * In case of allocated objects, active_lock.ptr is the reg->btf, and the * reg->id is a unique ID preserved after the NULL pointer check on the pointer * returned from bpf_obj_new. Each allocation receives a new reg->id. */ static int check_reg_allocation_locked(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { void *ptr; u32 id; switch ((int)reg->type) { case PTR_TO_MAP_VALUE: ptr = reg->map_ptr; break; case PTR_TO_BTF_ID | MEM_ALLOC: ptr = reg->btf; break; default: verbose(env, "verifier internal error: unknown reg type for lock check\n"); return -EFAULT; } id = reg->id; if (!env->cur_state->active_lock.ptr) return -EINVAL; if (env->cur_state->active_lock.ptr != ptr || env->cur_state->active_lock.id != id) { verbose(env, "held lock and object are not in the same allocation\n"); return -EINVAL; } return 0; } static bool is_bpf_list_api_kfunc(u32 btf_id) { return btf_id == special_kfunc_list[KF_bpf_list_push_front_impl] || btf_id == special_kfunc_list[KF_bpf_list_push_back_impl] || btf_id == special_kfunc_list[KF_bpf_list_pop_front] || btf_id == special_kfunc_list[KF_bpf_list_pop_back]; } static bool is_bpf_rbtree_api_kfunc(u32 btf_id) { return btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl] || btf_id == special_kfunc_list[KF_bpf_rbtree_remove] || btf_id == special_kfunc_list[KF_bpf_rbtree_first]; } static bool is_bpf_graph_api_kfunc(u32 btf_id) { return is_bpf_list_api_kfunc(btf_id) || is_bpf_rbtree_api_kfunc(btf_id) || btf_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]; } static bool is_sync_callback_calling_kfunc(u32 btf_id) { return btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl]; } static bool is_async_callback_calling_kfunc(u32 btf_id) { return btf_id == special_kfunc_list[KF_bpf_wq_set_callback_impl]; } static bool is_bpf_throw_kfunc(struct bpf_insn *insn) { return bpf_pseudo_kfunc_call(insn) && insn->off == 0 && insn->imm == special_kfunc_list[KF_bpf_throw]; } static bool is_bpf_wq_set_callback_impl_kfunc(u32 btf_id) { return btf_id == special_kfunc_list[KF_bpf_wq_set_callback_impl]; } static bool is_callback_calling_kfunc(u32 btf_id) { return is_sync_callback_calling_kfunc(btf_id) || is_async_callback_calling_kfunc(btf_id); } static bool is_rbtree_lock_required_kfunc(u32 btf_id) { return is_bpf_rbtree_api_kfunc(btf_id); } static bool check_kfunc_is_graph_root_api(struct bpf_verifier_env *env, enum btf_field_type head_field_type, u32 kfunc_btf_id) { bool ret; switch (head_field_type) { case BPF_LIST_HEAD: ret = is_bpf_list_api_kfunc(kfunc_btf_id); break; case BPF_RB_ROOT: ret = is_bpf_rbtree_api_kfunc(kfunc_btf_id); break; default: verbose(env, "verifier internal error: unexpected graph root argument type %s\n", btf_field_type_name(head_field_type)); return false; } if (!ret) verbose(env, "verifier internal error: %s head arg for unknown kfunc\n", btf_field_type_name(head_field_type)); return ret; } static bool check_kfunc_is_graph_node_api(struct bpf_verifier_env *env, enum btf_field_type node_field_type, u32 kfunc_btf_id) { bool ret; switch (node_field_type) { case BPF_LIST_NODE: ret = (kfunc_btf_id == special_kfunc_list[KF_bpf_list_push_front_impl] || kfunc_btf_id == special_kfunc_list[KF_bpf_list_push_back_impl]); break; case BPF_RB_NODE: ret = (kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_remove] || kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl]); break; default: verbose(env, "verifier internal error: unexpected graph node argument type %s\n", btf_field_type_name(node_field_type)); return false; } if (!ret) verbose(env, "verifier internal error: %s node arg for unknown kfunc\n", btf_field_type_name(node_field_type)); return ret; } static int __process_kf_arg_ptr_to_graph_root(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, struct bpf_kfunc_call_arg_meta *meta, enum btf_field_type head_field_type, struct btf_field **head_field) { const char *head_type_name; struct btf_field *field; struct btf_record *rec; u32 head_off; if (meta->btf != btf_vmlinux) { verbose(env, "verifier internal error: unexpected btf mismatch in kfunc call\n"); return -EFAULT; } if (!check_kfunc_is_graph_root_api(env, head_field_type, meta->func_id)) return -EFAULT; head_type_name = btf_field_type_name(head_field_type); if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d doesn't have constant offset. %s has to be at the constant offset\n", regno, head_type_name); return -EINVAL; } rec = reg_btf_record(reg); head_off = reg->off + reg->var_off.value; field = btf_record_find(rec, head_off, head_field_type); if (!field) { verbose(env, "%s not found at offset=%u\n", head_type_name, head_off); return -EINVAL; } /* All functions require bpf_list_head to be protected using a bpf_spin_lock */ if (check_reg_allocation_locked(env, reg)) { verbose(env, "bpf_spin_lock at off=%d must be held for %s\n", rec->spin_lock_off, head_type_name); return -EINVAL; } if (*head_field) { verbose(env, "verifier internal error: repeating %s arg\n", head_type_name); return -EFAULT; } *head_field = field; return 0; } static int process_kf_arg_ptr_to_list_head(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, struct bpf_kfunc_call_arg_meta *meta) { return __process_kf_arg_ptr_to_graph_root(env, reg, regno, meta, BPF_LIST_HEAD, &meta->arg_list_head.field); } static int process_kf_arg_ptr_to_rbtree_root(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, struct bpf_kfunc_call_arg_meta *meta) { return __process_kf_arg_ptr_to_graph_root(env, reg, regno, meta, BPF_RB_ROOT, &meta->arg_rbtree_root.field); } static int __process_kf_arg_ptr_to_graph_node(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, struct bpf_kfunc_call_arg_meta *meta, enum btf_field_type head_field_type, enum btf_field_type node_field_type, struct btf_field **node_field) { const char *node_type_name; const struct btf_type *et, *t; struct btf_field *field; u32 node_off; if (meta->btf != btf_vmlinux) { verbose(env, "verifier internal error: unexpected btf mismatch in kfunc call\n"); return -EFAULT; } if (!check_kfunc_is_graph_node_api(env, node_field_type, meta->func_id)) return -EFAULT; node_type_name = btf_field_type_name(node_field_type); if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d doesn't have constant offset. %s has to be at the constant offset\n", regno, node_type_name); return -EINVAL; } node_off = reg->off + reg->var_off.value; field = reg_find_field_offset(reg, node_off, node_field_type); if (!field || field->offset != node_off) { verbose(env, "%s not found at offset=%u\n", node_type_name, node_off); return -EINVAL; } field = *node_field; et = btf_type_by_id(field->graph_root.btf, field->graph_root.value_btf_id); t = btf_type_by_id(reg->btf, reg->btf_id); if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, 0, field->graph_root.btf, field->graph_root.value_btf_id, true)) { verbose(env, "operation on %s expects arg#1 %s at offset=%d " "in struct %s, but arg is at offset=%d in struct %s\n", btf_field_type_name(head_field_type), btf_field_type_name(node_field_type), field->graph_root.node_offset, btf_name_by_offset(field->graph_root.btf, et->name_off), node_off, btf_name_by_offset(reg->btf, t->name_off)); return -EINVAL; } meta->arg_btf = reg->btf; meta->arg_btf_id = reg->btf_id; if (node_off != field->graph_root.node_offset) { verbose(env, "arg#1 offset=%d, but expected %s at offset=%d in struct %s\n", node_off, btf_field_type_name(node_field_type), field->graph_root.node_offset, btf_name_by_offset(field->graph_root.btf, et->name_off)); return -EINVAL; } return 0; } static int process_kf_arg_ptr_to_list_node(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, struct bpf_kfunc_call_arg_meta *meta) { return __process_kf_arg_ptr_to_graph_node(env, reg, regno, meta, BPF_LIST_HEAD, BPF_LIST_NODE, &meta->arg_list_head.field); } static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, struct bpf_kfunc_call_arg_meta *meta) { return __process_kf_arg_ptr_to_graph_node(env, reg, regno, meta, BPF_RB_ROOT, BPF_RB_NODE, &meta->arg_rbtree_root.field); } /* * css_task iter allowlist is needed to avoid dead locking on css_set_lock. * LSM hooks and iters (both sleepable and non-sleepable) are safe. * Any sleepable progs are also safe since bpf_check_attach_target() enforce * them can only be attached to some specific hook points. */ static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env) { enum bpf_prog_type prog_type = resolve_prog_type(env->prog); switch (prog_type) { case BPF_PROG_TYPE_LSM: return true; case BPF_PROG_TYPE_TRACING: if (env->prog->expected_attach_type == BPF_TRACE_ITER) return true; fallthrough; default: return in_sleepable(env); } } static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta, int insn_idx) { const char *func_name = meta->func_name, *ref_tname; const struct btf *btf = meta->btf; const struct btf_param *args; struct btf_record *rec; u32 i, nargs; int ret; args = (const struct btf_param *)(meta->func_proto + 1); nargs = btf_type_vlen(meta->func_proto); if (nargs > MAX_BPF_FUNC_REG_ARGS) { verbose(env, "Function %s has %d > %d args\n", func_name, nargs, MAX_BPF_FUNC_REG_ARGS); return -EINVAL; } /* Check that BTF function arguments match actual types that the * verifier sees. */ for (i = 0; i < nargs; i++) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[i + 1]; const struct btf_type *t, *ref_t, *resolve_ret; enum bpf_arg_type arg_type = ARG_DONTCARE; u32 regno = i + 1, ref_id, type_size; bool is_ret_buf_sz = false; int kf_arg_type; t = btf_type_skip_modifiers(btf, args[i].type, NULL); if (is_kfunc_arg_ignore(btf, &args[i])) continue; if (btf_type_is_scalar(t)) { if (reg->type != SCALAR_VALUE) { verbose(env, "R%d is not a scalar\n", regno); return -EINVAL; } if (is_kfunc_arg_constant(meta->btf, &args[i])) { if (meta->arg_constant.found) { verbose(env, "verifier internal error: only one constant argument permitted\n"); return -EFAULT; } if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d must be a known constant\n", regno); return -EINVAL; } ret = mark_chain_precision(env, regno); if (ret < 0) return ret; meta->arg_constant.found = true; meta->arg_constant.value = reg->var_off.value; } else if (is_kfunc_arg_scalar_with_name(btf, &args[i], "rdonly_buf_size")) { meta->r0_rdonly = true; is_ret_buf_sz = true; } else if (is_kfunc_arg_scalar_with_name(btf, &args[i], "rdwr_buf_size")) { is_ret_buf_sz = true; } if (is_ret_buf_sz) { if (meta->r0_size) { verbose(env, "2 or more rdonly/rdwr_buf_size parameters for kfunc"); return -EINVAL; } if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d is not a const\n", regno); return -EINVAL; } meta->r0_size = reg->var_off.value; ret = mark_chain_precision(env, regno); if (ret) return ret; } continue; } if (!btf_type_is_ptr(t)) { verbose(env, "Unrecognized arg#%d type %s\n", i, btf_type_str(t)); return -EINVAL; } if ((is_kfunc_trusted_args(meta) || is_kfunc_rcu(meta)) && (register_is_null(reg) || type_may_be_null(reg->type)) && !is_kfunc_arg_nullable(meta->btf, &args[i])) { verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i); return -EACCES; } if (reg->ref_obj_id) { if (is_kfunc_release(meta) && meta->ref_obj_id) { verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", regno, reg->ref_obj_id, meta->ref_obj_id); return -EFAULT; } meta->ref_obj_id = reg->ref_obj_id; if (is_kfunc_release(meta)) meta->release_regno = regno; } ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id); ref_tname = btf_name_by_offset(btf, ref_t->name_off); kf_arg_type = get_kfunc_ptr_arg_type(env, meta, t, ref_t, ref_tname, args, i, nargs); if (kf_arg_type < 0) return kf_arg_type; switch (kf_arg_type) { case KF_ARG_PTR_TO_NULL: continue; case KF_ARG_PTR_TO_MAP: if (!reg->map_ptr) { verbose(env, "pointer in R%d isn't map pointer\n", regno); return -EINVAL; } if (meta->map.ptr && reg->map_ptr->record->wq_off >= 0) { /* Use map_uid (which is unique id of inner map) to reject: * inner_map1 = bpf_map_lookup_elem(outer_map, key1) * inner_map2 = bpf_map_lookup_elem(outer_map, key2) * if (inner_map1 && inner_map2) { * wq = bpf_map_lookup_elem(inner_map1); * if (wq) * // mismatch would have been allowed * bpf_wq_init(wq, inner_map2); * } * * Comparing map_ptr is enough to distinguish normal and outer maps. */ if (meta->map.ptr != reg->map_ptr || meta->map.uid != reg->map_uid) { verbose(env, "workqueue pointer in R1 map_uid=%d doesn't match map pointer in R2 map_uid=%d\n", meta->map.uid, reg->map_uid); return -EINVAL; } } meta->map.ptr = reg->map_ptr; meta->map.uid = reg->map_uid; fallthrough; case KF_ARG_PTR_TO_ALLOC_BTF_ID: case KF_ARG_PTR_TO_BTF_ID: if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta)) break; if (!is_trusted_reg(reg)) { if (!is_kfunc_rcu(meta)) { verbose(env, "R%d must be referenced or trusted\n", regno); return -EINVAL; } if (!is_rcu_reg(reg)) { verbose(env, "R%d must be a rcu pointer\n", regno); return -EINVAL; } } fallthrough; case KF_ARG_PTR_TO_CTX: /* Trusted arguments have the same offset checks as release arguments */ arg_type |= OBJ_RELEASE; break; case KF_ARG_PTR_TO_DYNPTR: case KF_ARG_PTR_TO_ITER: case KF_ARG_PTR_TO_LIST_HEAD: case KF_ARG_PTR_TO_LIST_NODE: case KF_ARG_PTR_TO_RB_ROOT: case KF_ARG_PTR_TO_RB_NODE: case KF_ARG_PTR_TO_MEM: case KF_ARG_PTR_TO_MEM_SIZE: case KF_ARG_PTR_TO_CALLBACK: case KF_ARG_PTR_TO_REFCOUNTED_KPTR: case KF_ARG_PTR_TO_CONST_STR: case KF_ARG_PTR_TO_WORKQUEUE: /* Trusted by default */ break; default: WARN_ON_ONCE(1); return -EFAULT; } if (is_kfunc_release(meta) && reg->ref_obj_id) arg_type |= OBJ_RELEASE; ret = check_func_arg_reg_off(env, reg, regno, arg_type); if (ret < 0) return ret; switch (kf_arg_type) { case KF_ARG_PTR_TO_CTX: if (reg->type != PTR_TO_CTX) { verbose(env, "arg#%d expected pointer to ctx, but got %s\n", i, btf_type_str(t)); return -EINVAL; } if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) { ret = get_kern_ctx_btf_id(&env->log, resolve_prog_type(env->prog)); if (ret < 0) return -EINVAL; meta->ret_btf_id = ret; } break; case KF_ARG_PTR_TO_ALLOC_BTF_ID: if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC)) { if (meta->func_id != special_kfunc_list[KF_bpf_obj_drop_impl]) { verbose(env, "arg#%d expected for bpf_obj_drop_impl()\n", i); return -EINVAL; } } else if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC | MEM_PERCPU)) { if (meta->func_id != special_kfunc_list[KF_bpf_percpu_obj_drop_impl]) { verbose(env, "arg#%d expected for bpf_percpu_obj_drop_impl()\n", i); return -EINVAL; } } else { verbose(env, "arg#%d expected pointer to allocated object\n", i); return -EINVAL; } if (!reg->ref_obj_id) { verbose(env, "allocated object must be referenced\n"); return -EINVAL; } if (meta->btf == btf_vmlinux) { meta->arg_btf = reg->btf; meta->arg_btf_id = reg->btf_id; } break; case KF_ARG_PTR_TO_DYNPTR: { enum bpf_arg_type dynptr_arg_type = ARG_PTR_TO_DYNPTR; int clone_ref_obj_id = 0; if (reg->type != PTR_TO_STACK && reg->type != CONST_PTR_TO_DYNPTR) { verbose(env, "arg#%d expected pointer to stack or dynptr_ptr\n", i); return -EINVAL; } if (reg->type == CONST_PTR_TO_DYNPTR) dynptr_arg_type |= MEM_RDONLY; if (is_kfunc_arg_uninit(btf, &args[i])) dynptr_arg_type |= MEM_UNINIT; if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb]) { dynptr_arg_type |= DYNPTR_TYPE_SKB; } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_xdp]) { dynptr_arg_type |= DYNPTR_TYPE_XDP; } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_clone] && (dynptr_arg_type & MEM_UNINIT)) { enum bpf_dynptr_type parent_type = meta->initialized_dynptr.type; if (parent_type == BPF_DYNPTR_TYPE_INVALID) { verbose(env, "verifier internal error: no dynptr type for parent of clone\n"); return -EFAULT; } dynptr_arg_type |= (unsigned int)get_dynptr_type_flag(parent_type); clone_ref_obj_id = meta->initialized_dynptr.ref_obj_id; if (dynptr_type_refcounted(parent_type) && !clone_ref_obj_id) { verbose(env, "verifier internal error: missing ref obj id for parent of clone\n"); return -EFAULT; } } ret = process_dynptr_func(env, regno, insn_idx, dynptr_arg_type, clone_ref_obj_id); if (ret < 0) return ret; if (!(dynptr_arg_type & MEM_UNINIT)) { int id = dynptr_id(env, reg); if (id < 0) { verbose(env, "verifier internal error: failed to obtain dynptr id\n"); return id; } meta->initialized_dynptr.id = id; meta->initialized_dynptr.type = dynptr_get_type(env, reg); meta->initialized_dynptr.ref_obj_id = dynptr_ref_obj_id(env, reg); } break; } case KF_ARG_PTR_TO_ITER: if (meta->func_id == special_kfunc_list[KF_bpf_iter_css_task_new]) { if (!check_css_task_iter_allowlist(env)) { verbose(env, "css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs\n"); return -EINVAL; } } ret = process_iter_arg(env, regno, insn_idx, meta); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_LIST_HEAD: if (reg->type != PTR_TO_MAP_VALUE && reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { verbose(env, "arg#%d expected pointer to map value or allocated object\n", i); return -EINVAL; } if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC) && !reg->ref_obj_id) { verbose(env, "allocated object must be referenced\n"); return -EINVAL; } ret = process_kf_arg_ptr_to_list_head(env, reg, regno, meta); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_RB_ROOT: if (reg->type != PTR_TO_MAP_VALUE && reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { verbose(env, "arg#%d expected pointer to map value or allocated object\n", i); return -EINVAL; } if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC) && !reg->ref_obj_id) { verbose(env, "allocated object must be referenced\n"); return -EINVAL; } ret = process_kf_arg_ptr_to_rbtree_root(env, reg, regno, meta); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_LIST_NODE: if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { verbose(env, "arg#%d expected pointer to allocated object\n", i); return -EINVAL; } if (!reg->ref_obj_id) { verbose(env, "allocated object must be referenced\n"); return -EINVAL; } ret = process_kf_arg_ptr_to_list_node(env, reg, regno, meta); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_RB_NODE: if (meta->func_id == special_kfunc_list[KF_bpf_rbtree_remove]) { if (!type_is_non_owning_ref(reg->type) || reg->ref_obj_id) { verbose(env, "rbtree_remove node input must be non-owning ref\n"); return -EINVAL; } if (in_rbtree_lock_required_cb(env)) { verbose(env, "rbtree_remove not allowed in rbtree cb\n"); return -EINVAL; } } else { if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { verbose(env, "arg#%d expected pointer to allocated object\n", i); return -EINVAL; } if (!reg->ref_obj_id) { verbose(env, "allocated object must be referenced\n"); return -EINVAL; } } ret = process_kf_arg_ptr_to_rbtree_node(env, reg, regno, meta); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_MAP: /* If argument has '__map' suffix expect 'struct bpf_map *' */ ref_id = *reg2btf_ids[CONST_PTR_TO_MAP]; ref_t = btf_type_by_id(btf_vmlinux, ref_id); ref_tname = btf_name_by_offset(btf, ref_t->name_off); fallthrough; case KF_ARG_PTR_TO_BTF_ID: /* Only base_type is checked, further checks are done here */ if ((base_type(reg->type) != PTR_TO_BTF_ID || (bpf_type_has_unsafe_modifiers(reg->type) && !is_rcu_reg(reg))) && !reg2btf_ids[base_type(reg->type)]) { verbose(env, "arg#%d is %s ", i, reg_type_str(env, reg->type)); verbose(env, "expected %s or socket\n", reg_type_str(env, base_type(reg->type) | (type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS))); return -EINVAL; } ret = process_kf_arg_ptr_to_btf_id(env, reg, ref_t, ref_tname, ref_id, meta, i); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_MEM: resolve_ret = btf_resolve_size(btf, ref_t, &type_size); if (IS_ERR(resolve_ret)) { verbose(env, "arg#%d reference type('%s %s') size cannot be determined: %ld\n", i, btf_type_str(ref_t), ref_tname, PTR_ERR(resolve_ret)); return -EINVAL; } ret = check_mem_reg(env, reg, regno, type_size); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_MEM_SIZE: { struct bpf_reg_state *buff_reg = ®s[regno]; const struct btf_param *buff_arg = &args[i]; struct bpf_reg_state *size_reg = ®s[regno + 1]; const struct btf_param *size_arg = &args[i + 1]; if (!register_is_null(buff_reg) || !is_kfunc_arg_optional(meta->btf, buff_arg)) { ret = check_kfunc_mem_size_reg(env, size_reg, regno + 1); if (ret < 0) { verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1); return ret; } } if (is_kfunc_arg_const_mem_size(meta->btf, size_arg, size_reg)) { if (meta->arg_constant.found) { verbose(env, "verifier internal error: only one constant argument permitted\n"); return -EFAULT; } if (!tnum_is_const(size_reg->var_off)) { verbose(env, "R%d must be a known constant\n", regno + 1); return -EINVAL; } meta->arg_constant.found = true; meta->arg_constant.value = size_reg->var_off.value; } /* Skip next '__sz' or '__szk' argument */ i++; break; } case KF_ARG_PTR_TO_CALLBACK: if (reg->type != PTR_TO_FUNC) { verbose(env, "arg%d expected pointer to func\n", i); return -EINVAL; } meta->subprogno = reg->subprogno; break; case KF_ARG_PTR_TO_REFCOUNTED_KPTR: if (!type_is_ptr_alloc_obj(reg->type)) { verbose(env, "arg#%d is neither owning or non-owning ref\n", i); return -EINVAL; } if (!type_is_non_owning_ref(reg->type)) meta->arg_owning_ref = true; rec = reg_btf_record(reg); if (!rec) { verbose(env, "verifier internal error: Couldn't find btf_record\n"); return -EFAULT; } if (rec->refcount_off < 0) { verbose(env, "arg#%d doesn't point to a type with bpf_refcount field\n", i); return -EINVAL; } meta->arg_btf = reg->btf; meta->arg_btf_id = reg->btf_id; break; case KF_ARG_PTR_TO_CONST_STR: if (reg->type != PTR_TO_MAP_VALUE) { verbose(env, "arg#%d doesn't point to a const string\n", i); return -EINVAL; } ret = check_reg_const_str(env, reg, regno); if (ret) return ret; break; case KF_ARG_PTR_TO_WORKQUEUE: if (reg->type != PTR_TO_MAP_VALUE) { verbose(env, "arg#%d doesn't point to a map value\n", i); return -EINVAL; } ret = process_wq_func(env, regno, meta); if (ret < 0) return ret; break; } } if (is_kfunc_release(meta) && !meta->release_regno) { verbose(env, "release kernel function %s expects refcounted PTR_TO_BTF_ID\n", func_name); return -EINVAL; } return 0; } static int fetch_kfunc_meta(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_kfunc_call_arg_meta *meta, const char **kfunc_name) { const struct btf_type *func, *func_proto; u32 func_id, *kfunc_flags; const char *func_name; struct btf *desc_btf; if (kfunc_name) *kfunc_name = NULL; if (!insn->imm) return -EINVAL; desc_btf = find_kfunc_desc_btf(env, insn->off); if (IS_ERR(desc_btf)) return PTR_ERR(desc_btf); func_id = insn->imm; func = btf_type_by_id(desc_btf, func_id); func_name = btf_name_by_offset(desc_btf, func->name_off); if (kfunc_name) *kfunc_name = func_name; func_proto = btf_type_by_id(desc_btf, func->type); kfunc_flags = btf_kfunc_id_set_contains(desc_btf, func_id, env->prog); if (!kfunc_flags) { return -EACCES; } memset(meta, 0, sizeof(*meta)); meta->btf = desc_btf; meta->func_id = func_id; meta->kfunc_flags = *kfunc_flags; meta->func_proto = func_proto; meta->func_name = func_name; return 0; } static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name); static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) { bool sleepable, rcu_lock, rcu_unlock, preempt_disable, preempt_enable; u32 i, nargs, ptr_type_id, release_ref_obj_id; struct bpf_reg_state *regs = cur_regs(env); const char *func_name, *ptr_type_name; const struct btf_type *t, *ptr_type; struct bpf_kfunc_call_arg_meta meta; struct bpf_insn_aux_data *insn_aux; int err, insn_idx = *insn_idx_p; const struct btf_param *args; const struct btf_type *ret_t; struct btf *desc_btf; /* skip for now, but return error when we find this in fixup_kfunc_call */ if (!insn->imm) return 0; err = fetch_kfunc_meta(env, insn, &meta, &func_name); if (err == -EACCES && func_name) verbose(env, "calling kernel function %s is not allowed\n", func_name); if (err) return err; desc_btf = meta.btf; insn_aux = &env->insn_aux_data[insn_idx]; insn_aux->is_iter_next = is_iter_next_kfunc(&meta); if (is_kfunc_destructive(&meta) && !capable(CAP_SYS_BOOT)) { verbose(env, "destructive kfunc calls require CAP_SYS_BOOT capability\n"); return -EACCES; } sleepable = is_kfunc_sleepable(&meta); if (sleepable && !in_sleepable(env)) { verbose(env, "program must be sleepable to call sleepable kfunc %s\n", func_name); return -EACCES; } /* Check the arguments */ err = check_kfunc_args(env, &meta, insn_idx); if (err < 0) return err; if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) { err = push_callback_call(env, insn, insn_idx, meta.subprogno, set_rbtree_add_callback_state); if (err) { verbose(env, "kfunc %s#%d failed callback verification\n", func_name, meta.func_id); return err; } } if (meta.func_id == special_kfunc_list[KF_bpf_session_cookie]) { meta.r0_size = sizeof(u64); meta.r0_rdonly = false; } if (is_bpf_wq_set_callback_impl_kfunc(meta.func_id)) { err = push_callback_call(env, insn, insn_idx, meta.subprogno, set_timer_callback_state); if (err) { verbose(env, "kfunc %s#%d failed callback verification\n", func_name, meta.func_id); return err; } } rcu_lock = is_kfunc_bpf_rcu_read_lock(&meta); rcu_unlock = is_kfunc_bpf_rcu_read_unlock(&meta); preempt_disable = is_kfunc_bpf_preempt_disable(&meta); preempt_enable = is_kfunc_bpf_preempt_enable(&meta); if (env->cur_state->active_rcu_lock) { struct bpf_func_state *state; struct bpf_reg_state *reg; u32 clear_mask = (1 << STACK_SPILL) | (1 << STACK_ITER); if (in_rbtree_lock_required_cb(env) && (rcu_lock || rcu_unlock)) { verbose(env, "Calling bpf_rcu_read_{lock,unlock} in unnecessary rbtree callback\n"); return -EACCES; } if (rcu_lock) { verbose(env, "nested rcu read lock (kernel function %s)\n", func_name); return -EINVAL; } else if (rcu_unlock) { bpf_for_each_reg_in_vstate_mask(env->cur_state, state, reg, clear_mask, ({ if (reg->type & MEM_RCU) { reg->type &= ~(MEM_RCU | PTR_MAYBE_NULL); reg->type |= PTR_UNTRUSTED; } })); env->cur_state->active_rcu_lock = false; } else if (sleepable) { verbose(env, "kernel func %s is sleepable within rcu_read_lock region\n", func_name); return -EACCES; } } else if (rcu_lock) { env->cur_state->active_rcu_lock = true; } else if (rcu_unlock) { verbose(env, "unmatched rcu read unlock (kernel function %s)\n", func_name); return -EINVAL; } if (env->cur_state->active_preempt_lock) { if (preempt_disable) { env->cur_state->active_preempt_lock++; } else if (preempt_enable) { env->cur_state->active_preempt_lock--; } else if (sleepable) { verbose(env, "kernel func %s is sleepable within non-preemptible region\n", func_name); return -EACCES; } } else if (preempt_disable) { env->cur_state->active_preempt_lock++; } else if (preempt_enable) { verbose(env, "unmatched attempt to enable preemption (kernel function %s)\n", func_name); return -EINVAL; } /* In case of release function, we get register number of refcounted * PTR_TO_BTF_ID in bpf_kfunc_arg_meta, do the release now. */ if (meta.release_regno) { err = release_reference(env, regs[meta.release_regno].ref_obj_id); if (err) { verbose(env, "kfunc %s#%d reference has not been acquired before\n", func_name, meta.func_id); return err; } } if (meta.func_id == special_kfunc_list[KF_bpf_list_push_front_impl] || meta.func_id == special_kfunc_list[KF_bpf_list_push_back_impl] || meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) { release_ref_obj_id = regs[BPF_REG_2].ref_obj_id; insn_aux->insert_off = regs[BPF_REG_2].off; insn_aux->kptr_struct_meta = btf_find_struct_meta(meta.arg_btf, meta.arg_btf_id); err = ref_convert_owning_non_owning(env, release_ref_obj_id); if (err) { verbose(env, "kfunc %s#%d conversion of owning ref to non-owning failed\n", func_name, meta.func_id); return err; } err = release_reference(env, release_ref_obj_id); if (err) { verbose(env, "kfunc %s#%d reference has not been acquired before\n", func_name, meta.func_id); return err; } } if (meta.func_id == special_kfunc_list[KF_bpf_throw]) { if (!bpf_jit_supports_exceptions()) { verbose(env, "JIT does not support calling kfunc %s#%d\n", func_name, meta.func_id); return -ENOTSUPP; } env->seen_exception = true; /* In the case of the default callback, the cookie value passed * to bpf_throw becomes the return value of the program. */ if (!env->exception_callback_subprog) { err = check_return_code(env, BPF_REG_1, "R1"); if (err < 0) return err; } } for (i = 0; i < CALLER_SAVED_REGS; i++) mark_reg_not_init(env, regs, caller_saved[i]); /* Check return type */ t = btf_type_skip_modifiers(desc_btf, meta.func_proto->type, NULL); if (is_kfunc_acquire(&meta) && !btf_type_is_struct_ptr(meta.btf, t)) { /* Only exception is bpf_obj_new_impl */ if (meta.btf != btf_vmlinux || (meta.func_id != special_kfunc_list[KF_bpf_obj_new_impl] && meta.func_id != special_kfunc_list[KF_bpf_percpu_obj_new_impl] && meta.func_id != special_kfunc_list[KF_bpf_refcount_acquire_impl])) { verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n"); return -EINVAL; } } if (btf_type_is_scalar(t)) { mark_reg_unknown(env, regs, BPF_REG_0); mark_btf_func_reg_size(env, BPF_REG_0, t->size); } else if (btf_type_is_ptr(t)) { ptr_type = btf_type_skip_modifiers(desc_btf, t->type, &ptr_type_id); if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) { if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] || meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) { struct btf_struct_meta *struct_meta; struct btf *ret_btf; u32 ret_btf_id; if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set) return -ENOMEM; if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) { verbose(env, "local type ID argument must be in range [0, U32_MAX]\n"); return -EINVAL; } ret_btf = env->prog->aux->btf; ret_btf_id = meta.arg_constant.value; /* This may be NULL due to user not supplying a BTF */ if (!ret_btf) { verbose(env, "bpf_obj_new/bpf_percpu_obj_new requires prog BTF\n"); return -EINVAL; } ret_t = btf_type_by_id(ret_btf, ret_btf_id); if (!ret_t || !__btf_type_is_struct(ret_t)) { verbose(env, "bpf_obj_new/bpf_percpu_obj_new type ID argument must be of a struct\n"); return -EINVAL; } if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) { if (ret_t->size > BPF_GLOBAL_PERCPU_MA_MAX_SIZE) { verbose(env, "bpf_percpu_obj_new type size (%d) is greater than %d\n", ret_t->size, BPF_GLOBAL_PERCPU_MA_MAX_SIZE); return -EINVAL; } if (!bpf_global_percpu_ma_set) { mutex_lock(&bpf_percpu_ma_lock); if (!bpf_global_percpu_ma_set) { /* Charge memory allocated with bpf_global_percpu_ma to * root memcg. The obj_cgroup for root memcg is NULL. */ err = bpf_mem_alloc_percpu_init(&bpf_global_percpu_ma, NULL); if (!err) bpf_global_percpu_ma_set = true; } mutex_unlock(&bpf_percpu_ma_lock); if (err) return err; } mutex_lock(&bpf_percpu_ma_lock); err = bpf_mem_alloc_percpu_unit_init(&bpf_global_percpu_ma, ret_t->size); mutex_unlock(&bpf_percpu_ma_lock); if (err) return err; } struct_meta = btf_find_struct_meta(ret_btf, ret_btf_id); if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) { if (!__btf_type_is_scalar_struct(env, ret_btf, ret_t, 0)) { verbose(env, "bpf_percpu_obj_new type ID argument must be of a struct of scalars\n"); return -EINVAL; } if (struct_meta) { verbose(env, "bpf_percpu_obj_new type ID argument must not contain special fields\n"); return -EINVAL; } } mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC; regs[BPF_REG_0].btf = ret_btf; regs[BPF_REG_0].btf_id = ret_btf_id; if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) regs[BPF_REG_0].type |= MEM_PERCPU; insn_aux->obj_new_size = ret_t->size; insn_aux->kptr_struct_meta = struct_meta; } else if (meta.func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC; regs[BPF_REG_0].btf = meta.arg_btf; regs[BPF_REG_0].btf_id = meta.arg_btf_id; insn_aux->kptr_struct_meta = btf_find_struct_meta(meta.arg_btf, meta.arg_btf_id); } else if (meta.func_id == special_kfunc_list[KF_bpf_list_pop_front] || meta.func_id == special_kfunc_list[KF_bpf_list_pop_back]) { struct btf_field *field = meta.arg_list_head.field; mark_reg_graph_node(regs, BPF_REG_0, &field->graph_root); } else if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_remove] || meta.func_id == special_kfunc_list[KF_bpf_rbtree_first]) { struct btf_field *field = meta.arg_rbtree_root.field; mark_reg_graph_node(regs, BPF_REG_0, &field->graph_root); } else if (meta.func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_TRUSTED; regs[BPF_REG_0].btf = desc_btf; regs[BPF_REG_0].btf_id = meta.ret_btf_id; } else if (meta.func_id == special_kfunc_list[KF_bpf_rdonly_cast]) { ret_t = btf_type_by_id(desc_btf, meta.arg_constant.value); if (!ret_t || !btf_type_is_struct(ret_t)) { verbose(env, "kfunc bpf_rdonly_cast type ID argument must be of a struct\n"); return -EINVAL; } mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_UNTRUSTED; regs[BPF_REG_0].btf = desc_btf; regs[BPF_REG_0].btf_id = meta.arg_constant.value; } else if (meta.func_id == special_kfunc_list[KF_bpf_dynptr_slice] || meta.func_id == special_kfunc_list[KF_bpf_dynptr_slice_rdwr]) { enum bpf_type_flag type_flag = get_dynptr_type_flag(meta.initialized_dynptr.type); mark_reg_known_zero(env, regs, BPF_REG_0); if (!meta.arg_constant.found) { verbose(env, "verifier internal error: bpf_dynptr_slice(_rdwr) no constant size\n"); return -EFAULT; } regs[BPF_REG_0].mem_size = meta.arg_constant.value; /* PTR_MAYBE_NULL will be added when is_kfunc_ret_null is checked */ regs[BPF_REG_0].type = PTR_TO_MEM | type_flag; if (meta.func_id == special_kfunc_list[KF_bpf_dynptr_slice]) { regs[BPF_REG_0].type |= MEM_RDONLY; } else { /* this will set env->seen_direct_write to true */ if (!may_access_direct_pkt_data(env, NULL, BPF_WRITE)) { verbose(env, "the prog does not allow writes to packet data\n"); return -EINVAL; } } if (!meta.initialized_dynptr.id) { verbose(env, "verifier internal error: no dynptr id\n"); return -EFAULT; } regs[BPF_REG_0].dynptr_id = meta.initialized_dynptr.id; /* we don't need to set BPF_REG_0's ref obj id * because packet slices are not refcounted (see * dynptr_type_refcounted) */ } else { verbose(env, "kernel function %s unhandled dynamic return type\n", meta.func_name); return -EFAULT; } } else if (btf_type_is_void(ptr_type)) { /* kfunc returning 'void *' is equivalent to returning scalar */ mark_reg_unknown(env, regs, BPF_REG_0); } else if (!__btf_type_is_struct(ptr_type)) { if (!meta.r0_size) { __u32 sz; if (!IS_ERR(btf_resolve_size(desc_btf, ptr_type, &sz))) { meta.r0_size = sz; meta.r0_rdonly = true; } } if (!meta.r0_size) { ptr_type_name = btf_name_by_offset(desc_btf, ptr_type->name_off); verbose(env, "kernel function %s returns pointer type %s %s is not supported\n", func_name, btf_type_str(ptr_type), ptr_type_name); return -EINVAL; } mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_MEM; regs[BPF_REG_0].mem_size = meta.r0_size; if (meta.r0_rdonly) regs[BPF_REG_0].type |= MEM_RDONLY; /* Ensures we don't access the memory after a release_reference() */ if (meta.ref_obj_id) regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id; } else { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].btf = desc_btf; regs[BPF_REG_0].type = PTR_TO_BTF_ID; regs[BPF_REG_0].btf_id = ptr_type_id; } if (is_kfunc_ret_null(&meta)) { regs[BPF_REG_0].type |= PTR_MAYBE_NULL; /* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */ regs[BPF_REG_0].id = ++env->id_gen; } mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *)); if (is_kfunc_acquire(&meta)) { int id = acquire_reference_state(env, insn_idx); if (id < 0) return id; if (is_kfunc_ret_null(&meta)) regs[BPF_REG_0].id = id; regs[BPF_REG_0].ref_obj_id = id; } else if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_first]) { ref_set_non_owning(env, ®s[BPF_REG_0]); } if (reg_may_point_to_spin_lock(®s[BPF_REG_0]) && !regs[BPF_REG_0].id) regs[BPF_REG_0].id = ++env->id_gen; } else if (btf_type_is_void(t)) { if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) { if (meta.func_id == special_kfunc_list[KF_bpf_obj_drop_impl] || meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl]) { insn_aux->kptr_struct_meta = btf_find_struct_meta(meta.arg_btf, meta.arg_btf_id); } } } nargs = btf_type_vlen(meta.func_proto); args = (const struct btf_param *)(meta.func_proto + 1); for (i = 0; i < nargs; i++) { u32 regno = i + 1; t = btf_type_skip_modifiers(desc_btf, args[i].type, NULL); if (btf_type_is_ptr(t)) mark_btf_func_reg_size(env, regno, sizeof(void *)); else /* scalar. ensured by btf_check_kfunc_arg_match() */ mark_btf_func_reg_size(env, regno, t->size); } if (is_iter_next_kfunc(&meta)) { err = process_iter_next_call(env, insn_idx, &meta); if (err) return err; } return 0; } static bool signed_add_overflows(s64 a, s64 b) { /* Do the add in u64, where overflow is well-defined */ s64 res = (s64)((u64)a + (u64)b); if (b < 0) return res > a; return res < a; } static bool signed_add32_overflows(s32 a, s32 b) { /* Do the add in u32, where overflow is well-defined */ s32 res = (s32)((u32)a + (u32)b); if (b < 0) return res > a; return res < a; } static bool signed_add16_overflows(s16 a, s16 b) { /* Do the add in u16, where overflow is well-defined */ s16 res = (s16)((u16)a + (u16)b); if (b < 0) return res > a; return res < a; } static bool signed_sub_overflows(s64 a, s64 b) { /* Do the sub in u64, where overflow is well-defined */ s64 res = (s64)((u64)a - (u64)b); if (b < 0) return res < a; return res > a; } static bool signed_sub32_overflows(s32 a, s32 b) { /* Do the sub in u32, where overflow is well-defined */ s32 res = (s32)((u32)a - (u32)b); if (b < 0) return res < a; return res > a; } static bool check_reg_sane_offset(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, enum bpf_reg_type type) { bool known = tnum_is_const(reg->var_off); s64 val = reg->var_off.value; s64 smin = reg->smin_value; if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) { verbose(env, "math between %s pointer and %lld is not allowed\n", reg_type_str(env, type), val); return false; } if (reg->off >= BPF_MAX_VAR_OFF || reg->off <= -BPF_MAX_VAR_OFF) { verbose(env, "%s pointer offset %d is not allowed\n", reg_type_str(env, type), reg->off); return false; } if (smin == S64_MIN) { verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n", reg_type_str(env, type)); return false; } if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) { verbose(env, "value %lld makes %s pointer be out of bounds\n", smin, reg_type_str(env, type)); return false; } return true; } enum { REASON_BOUNDS = -1, REASON_TYPE = -2, REASON_PATHS = -3, REASON_LIMIT = -4, REASON_STACK = -5, }; static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg, u32 *alu_limit, bool mask_to_left) { u32 max = 0, ptr_limit = 0; switch (ptr_reg->type) { case PTR_TO_STACK: /* Offset 0 is out-of-bounds, but acceptable start for the * left direction, see BPF_REG_FP. Also, unknown scalar * offset where we would need to deal with min/max bounds is * currently prohibited for unprivileged. */ max = MAX_BPF_STACK + mask_to_left; ptr_limit = -(ptr_reg->var_off.value + ptr_reg->off); break; case PTR_TO_MAP_VALUE: max = ptr_reg->map_ptr->value_size; ptr_limit = (mask_to_left ? ptr_reg->smin_value : ptr_reg->umax_value) + ptr_reg->off; break; default: return REASON_TYPE; } if (ptr_limit >= max) return REASON_LIMIT; *alu_limit = ptr_limit; return 0; } static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env, const struct bpf_insn *insn) { return env->bypass_spec_v1 || BPF_SRC(insn->code) == BPF_K; } static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux, u32 alu_state, u32 alu_limit) { /* If we arrived here from different branches with different * state or limits to sanitize, then this won't work. */ if (aux->alu_state && (aux->alu_state != alu_state || aux->alu_limit != alu_limit)) return REASON_PATHS; /* Corresponding fixup done in do_misc_fixups(). */ aux->alu_state = alu_state; aux->alu_limit = alu_limit; return 0; } static int sanitize_val_alu(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_insn_aux_data *aux = cur_aux(env); if (can_skip_alu_sanitation(env, insn)) return 0; return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0); } static bool sanitize_needed(u8 opcode) { return opcode == BPF_ADD || opcode == BPF_SUB; } struct bpf_sanitize_info { struct bpf_insn_aux_data aux; bool mask_to_left; }; static struct bpf_verifier_state * sanitize_speculative_path(struct bpf_verifier_env *env, const struct bpf_insn *insn, u32 next_idx, u32 curr_idx) { struct bpf_verifier_state *branch; struct bpf_reg_state *regs; branch = push_stack(env, next_idx, curr_idx, true); if (branch && insn) { regs = branch->frame[branch->curframe]->regs; if (BPF_SRC(insn->code) == BPF_K) { mark_reg_unknown(env, regs, insn->dst_reg); } else if (BPF_SRC(insn->code) == BPF_X) { mark_reg_unknown(env, regs, insn->dst_reg); mark_reg_unknown(env, regs, insn->src_reg); } } return branch; } static int sanitize_ptr_alu(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, const struct bpf_reg_state *off_reg, struct bpf_reg_state *dst_reg, struct bpf_sanitize_info *info, const bool commit_window) { struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : &info->aux; struct bpf_verifier_state *vstate = env->cur_state; bool off_is_imm = tnum_is_const(off_reg->var_off); bool off_is_neg = off_reg->smin_value < 0; bool ptr_is_dst_reg = ptr_reg == dst_reg; u8 opcode = BPF_OP(insn->code); u32 alu_state, alu_limit; struct bpf_reg_state tmp; bool ret; int err; if (can_skip_alu_sanitation(env, insn)) return 0; /* We already marked aux for masking from non-speculative * paths, thus we got here in the first place. We only care * to explore bad access from here. */ if (vstate->speculative) goto do_sim; if (!commit_window) { if (!tnum_is_const(off_reg->var_off) && (off_reg->smin_value < 0) != (off_reg->smax_value < 0)) return REASON_BOUNDS; info->mask_to_left = (opcode == BPF_ADD && off_is_neg) || (opcode == BPF_SUB && !off_is_neg); } err = retrieve_ptr_limit(ptr_reg, &alu_limit, info->mask_to_left); if (err < 0) return err; if (commit_window) { /* In commit phase we narrow the masking window based on * the observed pointer move after the simulated operation. */ alu_state = info->aux.alu_state; alu_limit = abs(info->aux.alu_limit - alu_limit); } else { alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0; alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0; alu_state |= ptr_is_dst_reg ? BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST; /* Limit pruning on unknown scalars to enable deep search for * potential masking differences from other program paths. */ if (!off_is_imm) env->explore_alu_limits = true; } err = update_alu_sanitation_state(aux, alu_state, alu_limit); if (err < 0) return err; do_sim: /* If we're in commit phase, we're done here given we already * pushed the truncated dst_reg into the speculative verification * stack. * * Also, when register is a known constant, we rewrite register-based * operation to immediate-based, and thus do not need masking (and as * a consequence, do not need to simulate the zero-truncation either). */ if (commit_window || off_is_imm) return 0; /* Simulate and find potential out-of-bounds access under * speculative execution from truncation as a result of * masking when off was not within expected range. If off * sits in dst, then we temporarily need to move ptr there * to simulate dst (== 0) +/-= ptr. Needed, for example, * for cases where we use K-based arithmetic in one direction * and truncated reg-based in the other in order to explore * bad access. */ if (!ptr_is_dst_reg) { tmp = *dst_reg; copy_register_state(dst_reg, ptr_reg); } ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1, env->insn_idx); if (!ptr_is_dst_reg && ret) *dst_reg = tmp; return !ret ? REASON_STACK : 0; } static void sanitize_mark_insn_seen(struct bpf_verifier_env *env) { struct bpf_verifier_state *vstate = env->cur_state; /* If we simulate paths under speculation, we don't update the * insn as 'seen' such that when we verify unreachable paths in * the non-speculative domain, sanitize_dead_code() can still * rewrite/sanitize them. */ if (!vstate->speculative) env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; } static int sanitize_err(struct bpf_verifier_env *env, const struct bpf_insn *insn, int reason, const struct bpf_reg_state *off_reg, const struct bpf_reg_state *dst_reg) { static const char *err = "pointer arithmetic with it prohibited for !root"; const char *op = BPF_OP(insn->code) == BPF_ADD ? "add" : "sub"; u32 dst = insn->dst_reg, src = insn->src_reg; switch (reason) { case REASON_BOUNDS: verbose(env, "R%d has unknown scalar with mixed signed bounds, %s\n", off_reg == dst_reg ? dst : src, err); break; case REASON_TYPE: verbose(env, "R%d has pointer with unsupported alu operation, %s\n", off_reg == dst_reg ? src : dst, err); break; case REASON_PATHS: verbose(env, "R%d tried to %s from different maps, paths or scalars, %s\n", dst, op, err); break; case REASON_LIMIT: verbose(env, "R%d tried to %s beyond pointer bounds, %s\n", dst, op, err); break; case REASON_STACK: verbose(env, "R%d could not be pushed for speculative verification, %s\n", dst, err); break; default: verbose(env, "verifier internal error: unknown reason (%d)\n", reason); break; } return -EACCES; } /* check that stack access falls within stack limits and that 'reg' doesn't * have a variable offset. * * Variable offset is prohibited for unprivileged mode for simplicity since it * requires corresponding support in Spectre masking for stack ALU. See also * retrieve_ptr_limit(). * * * 'off' includes 'reg->off'. */ static int check_stack_access_for_ptr_arithmetic( struct bpf_verifier_env *env, int regno, const struct bpf_reg_state *reg, int off) { if (!tnum_is_const(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "R%d variable stack access prohibited for !root, var_off=%s off=%d\n", regno, tn_buf, off); return -EACCES; } if (off >= 0 || off < -MAX_BPF_STACK) { verbose(env, "R%d stack pointer arithmetic goes out of range, " "prohibited for !root; off=%d\n", regno, off); return -EACCES; } return 0; } static int sanitize_check_bounds(struct bpf_verifier_env *env, const struct bpf_insn *insn, const struct bpf_reg_state *dst_reg) { u32 dst = insn->dst_reg; /* For unprivileged we require that resulting offset must be in bounds * in order to be able to sanitize access later on. */ if (env->bypass_spec_v1) return 0; switch (dst_reg->type) { case PTR_TO_STACK: if (check_stack_access_for_ptr_arithmetic(env, dst, dst_reg, dst_reg->off + dst_reg->var_off.value)) return -EACCES; break; case PTR_TO_MAP_VALUE: if (check_map_access(env, dst, dst_reg->off, 1, false, ACCESS_HELPER)) { verbose(env, "R%d pointer arithmetic of map value goes out of range, " "prohibited for !root\n", dst); return -EACCES; } break; default: break; } return 0; } /* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off. * Caller should also handle BPF_MOV case separately. * If we return -EACCES, caller may want to try again treating pointer as a * scalar. So we only emit a diagnostic if !env->allow_ptr_leaks. */ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, const struct bpf_reg_state *off_reg) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *regs = state->regs, *dst_reg; bool known = tnum_is_const(off_reg->var_off); s64 smin_val = off_reg->smin_value, smax_val = off_reg->smax_value, smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value; u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value, umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value; struct bpf_sanitize_info info = {}; u8 opcode = BPF_OP(insn->code); u32 dst = insn->dst_reg; int ret; dst_reg = ®s[dst]; if ((known && (smin_val != smax_val || umin_val != umax_val)) || smin_val > smax_val || umin_val > umax_val) { /* Taint dst register if offset had invalid bounds derived from * e.g. dead branches. */ __mark_reg_unknown(env, dst_reg); return 0; } if (BPF_CLASS(insn->code) != BPF_ALU64) { /* 32-bit ALU ops on pointers produce (meaningless) scalars */ if (opcode == BPF_SUB && env->allow_ptr_leaks) { __mark_reg_unknown(env, dst_reg); return 0; } verbose(env, "R%d 32-bit pointer arithmetic prohibited\n", dst); return -EACCES; } if (ptr_reg->type & PTR_MAYBE_NULL) { verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n", dst, reg_type_str(env, ptr_reg->type)); return -EACCES; } switch (base_type(ptr_reg->type)) { case PTR_TO_CTX: case PTR_TO_MAP_VALUE: case PTR_TO_MAP_KEY: case PTR_TO_STACK: case PTR_TO_PACKET_META: case PTR_TO_PACKET: case PTR_TO_TP_BUFFER: case PTR_TO_BTF_ID: case PTR_TO_MEM: case PTR_TO_BUF: case PTR_TO_FUNC: case CONST_PTR_TO_DYNPTR: break; case PTR_TO_FLOW_KEYS: if (known) break; fallthrough; case CONST_PTR_TO_MAP: /* smin_val represents the known value */ if (known && smin_val == 0 && opcode == BPF_ADD) break; fallthrough; default: verbose(env, "R%d pointer arithmetic on %s prohibited\n", dst, reg_type_str(env, ptr_reg->type)); return -EACCES; } /* In case of 'scalar += pointer', dst_reg inherits pointer type and id. * The id may be overwritten later if we create a new variable offset. */ dst_reg->type = ptr_reg->type; dst_reg->id = ptr_reg->id; if (!check_reg_sane_offset(env, off_reg, ptr_reg->type) || !check_reg_sane_offset(env, ptr_reg, ptr_reg->type)) return -EINVAL; /* pointer types do not carry 32-bit bounds at the moment. */ __mark_reg32_unbounded(dst_reg); if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg, &info, false); if (ret < 0) return sanitize_err(env, insn, ret, off_reg, dst_reg); } switch (opcode) { case BPF_ADD: /* We can take a fixed offset as long as it doesn't overflow * the s32 'off' field */ if (known && (ptr_reg->off + smin_val == (s64)(s32)(ptr_reg->off + smin_val))) { /* pointer += K. Accumulate it into fixed offset */ dst_reg->smin_value = smin_ptr; dst_reg->smax_value = smax_ptr; dst_reg->umin_value = umin_ptr; dst_reg->umax_value = umax_ptr; dst_reg->var_off = ptr_reg->var_off; dst_reg->off = ptr_reg->off + smin_val; dst_reg->raw = ptr_reg->raw; break; } /* A new variable offset is created. Note that off_reg->off * == 0, since it's a scalar. * dst_reg gets the pointer type and since some positive * integer value was added to the pointer, give it a new 'id' * if it's a PTR_TO_PACKET. * this creates a new 'base' pointer, off_reg (variable) gets * added into the variable offset, and we copy the fixed offset * from ptr_reg. */ if (signed_add_overflows(smin_ptr, smin_val) || signed_add_overflows(smax_ptr, smax_val)) { dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { dst_reg->smin_value = smin_ptr + smin_val; dst_reg->smax_value = smax_ptr + smax_val; } if (umin_ptr + umin_val < umin_ptr || umax_ptr + umax_val < umax_ptr) { dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { dst_reg->umin_value = umin_ptr + umin_val; dst_reg->umax_value = umax_ptr + umax_val; } dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; dst_reg->raw = ptr_reg->raw; if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ memset(&dst_reg->raw, 0, sizeof(dst_reg->raw)); } break; case BPF_SUB: if (dst_reg == off_reg) { /* scalar -= pointer. Creates an unknown scalar */ verbose(env, "R%d tried to subtract pointer from scalar\n", dst); return -EACCES; } /* We don't allow subtraction from FP, because (according to * test_verifier.c test "invalid fp arithmetic", JITs might not * be able to deal with it. */ if (ptr_reg->type == PTR_TO_STACK) { verbose(env, "R%d subtraction from stack pointer prohibited\n", dst); return -EACCES; } if (known && (ptr_reg->off - smin_val == (s64)(s32)(ptr_reg->off - smin_val))) { /* pointer -= K. Subtract it from fixed offset */ dst_reg->smin_value = smin_ptr; dst_reg->smax_value = smax_ptr; dst_reg->umin_value = umin_ptr; dst_reg->umax_value = umax_ptr; dst_reg->var_off = ptr_reg->var_off; dst_reg->id = ptr_reg->id; dst_reg->off = ptr_reg->off - smin_val; dst_reg->raw = ptr_reg->raw; break; } /* A new variable offset is created. If the subtrahend is known * nonnegative, then any reg->range we had before is still good. */ if (signed_sub_overflows(smin_ptr, smax_val) || signed_sub_overflows(smax_ptr, smin_val)) { /* Overflow possible, we know nothing */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { dst_reg->smin_value = smin_ptr - smax_val; dst_reg->smax_value = smax_ptr - smin_val; } if (umin_ptr < umax_val) { /* Overflow possible, we know nothing */ dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { /* Cannot overflow (as long as bounds are consistent) */ dst_reg->umin_value = umin_ptr - umax_val; dst_reg->umax_value = umax_ptr - umin_val; } dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; dst_reg->raw = ptr_reg->raw; if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ if (smin_val < 0) memset(&dst_reg->raw, 0, sizeof(dst_reg->raw)); } break; case BPF_AND: case BPF_OR: case BPF_XOR: /* bitwise ops on pointers are troublesome, prohibit. */ verbose(env, "R%d bitwise operator %s on pointer prohibited\n", dst, bpf_alu_string[opcode >> 4]); return -EACCES; default: /* other operators (e.g. MUL,LSH) produce non-pointer results */ verbose(env, "R%d pointer arithmetic with %s operator prohibited\n", dst, bpf_alu_string[opcode >> 4]); return -EACCES; } if (!check_reg_sane_offset(env, dst_reg, ptr_reg->type)) return -EINVAL; reg_bounds_sync(dst_reg); if (sanitize_check_bounds(env, insn, dst_reg) < 0) return -EACCES; if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg, &info, true); if (ret < 0) return sanitize_err(env, insn, ret, off_reg, dst_reg); } return 0; } static void scalar32_min_max_add(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s32 smin_val = src_reg->s32_min_value; s32 smax_val = src_reg->s32_max_value; u32 umin_val = src_reg->u32_min_value; u32 umax_val = src_reg->u32_max_value; if (signed_add32_overflows(dst_reg->s32_min_value, smin_val) || signed_add32_overflows(dst_reg->s32_max_value, smax_val)) { dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } else { dst_reg->s32_min_value += smin_val; dst_reg->s32_max_value += smax_val; } if (dst_reg->u32_min_value + umin_val < umin_val || dst_reg->u32_max_value + umax_val < umax_val) { dst_reg->u32_min_value = 0; dst_reg->u32_max_value = U32_MAX; } else { dst_reg->u32_min_value += umin_val; dst_reg->u32_max_value += umax_val; } } static void scalar_min_max_add(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s64 smin_val = src_reg->smin_value; s64 smax_val = src_reg->smax_value; u64 umin_val = src_reg->umin_value; u64 umax_val = src_reg->umax_value; if (signed_add_overflows(dst_reg->smin_value, smin_val) || signed_add_overflows(dst_reg->smax_value, smax_val)) { dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { dst_reg->smin_value += smin_val; dst_reg->smax_value += smax_val; } if (dst_reg->umin_value + umin_val < umin_val || dst_reg->umax_value + umax_val < umax_val) { dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { dst_reg->umin_value += umin_val; dst_reg->umax_value += umax_val; } } static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s32 smin_val = src_reg->s32_min_value; s32 smax_val = src_reg->s32_max_value; u32 umin_val = src_reg->u32_min_value; u32 umax_val = src_reg->u32_max_value; if (signed_sub32_overflows(dst_reg->s32_min_value, smax_val) || signed_sub32_overflows(dst_reg->s32_max_value, smin_val)) { /* Overflow possible, we know nothing */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } else { dst_reg->s32_min_value -= smax_val; dst_reg->s32_max_value -= smin_val; } if (dst_reg->u32_min_value < umax_val) { /* Overflow possible, we know nothing */ dst_reg->u32_min_value = 0; dst_reg->u32_max_value = U32_MAX; } else { /* Cannot overflow (as long as bounds are consistent) */ dst_reg->u32_min_value -= umax_val; dst_reg->u32_max_value -= umin_val; } } static void scalar_min_max_sub(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s64 smin_val = src_reg->smin_value; s64 smax_val = src_reg->smax_value; u64 umin_val = src_reg->umin_value; u64 umax_val = src_reg->umax_value; if (signed_sub_overflows(dst_reg->smin_value, smax_val) || signed_sub_overflows(dst_reg->smax_value, smin_val)) { /* Overflow possible, we know nothing */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { dst_reg->smin_value -= smax_val; dst_reg->smax_value -= smin_val; } if (dst_reg->umin_value < umax_val) { /* Overflow possible, we know nothing */ dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { /* Cannot overflow (as long as bounds are consistent) */ dst_reg->umin_value -= umax_val; dst_reg->umax_value -= umin_val; } } static void scalar32_min_max_mul(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s32 smin_val = src_reg->s32_min_value; u32 umin_val = src_reg->u32_min_value; u32 umax_val = src_reg->u32_max_value; if (smin_val < 0 || dst_reg->s32_min_value < 0) { /* Ain't nobody got time to multiply that sign */ __mark_reg32_unbounded(dst_reg); return; } /* Both values are positive, so we can work with unsigned and * copy the result to signed (unless it exceeds S32_MAX). */ if (umax_val > U16_MAX || dst_reg->u32_max_value > U16_MAX) { /* Potential overflow, we know nothing */ __mark_reg32_unbounded(dst_reg); return; } dst_reg->u32_min_value *= umin_val; dst_reg->u32_max_value *= umax_val; if (dst_reg->u32_max_value > S32_MAX) { /* Overflow possible, we know nothing */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } else { dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } } static void scalar_min_max_mul(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s64 smin_val = src_reg->smin_value; u64 umin_val = src_reg->umin_value; u64 umax_val = src_reg->umax_value; if (smin_val < 0 || dst_reg->smin_value < 0) { /* Ain't nobody got time to multiply that sign */ __mark_reg64_unbounded(dst_reg); return; } /* Both values are positive, so we can work with unsigned and * copy the result to signed (unless it exceeds S64_MAX). */ if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) { /* Potential overflow, we know nothing */ __mark_reg64_unbounded(dst_reg); return; } dst_reg->umin_value *= umin_val; dst_reg->umax_value *= umax_val; if (dst_reg->umax_value > S64_MAX) { /* Overflow possible, we know nothing */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; } } static void scalar32_min_max_and(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); u32 umax_val = src_reg->u32_max_value; if (src_known && dst_known) { __mark_reg32_known(dst_reg, var32_off.value); return; } /* We get our minimum from the var_off, since that's inherently * bitwise. Our maximum is the minimum of the operands' maxima. */ dst_reg->u32_min_value = var32_off.value; dst_reg->u32_max_value = min(dst_reg->u32_max_value, umax_val); /* Safe to set s32 bounds by casting u32 result into s32 when u32 * doesn't cross sign boundary. Otherwise set s32 bounds to unbounded. */ if ((s32)dst_reg->u32_min_value <= (s32)dst_reg->u32_max_value) { dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } else { dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } } static void scalar_min_max_and(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_is_const(src_reg->var_off); bool dst_known = tnum_is_const(dst_reg->var_off); u64 umax_val = src_reg->umax_value; if (src_known && dst_known) { __mark_reg_known(dst_reg, dst_reg->var_off.value); return; } /* We get our minimum from the var_off, since that's inherently * bitwise. Our maximum is the minimum of the operands' maxima. */ dst_reg->umin_value = dst_reg->var_off.value; dst_reg->umax_value = min(dst_reg->umax_value, umax_val); /* Safe to set s64 bounds by casting u64 result into s64 when u64 * doesn't cross sign boundary. Otherwise set s64 bounds to unbounded. */ if ((s64)dst_reg->umin_value <= (s64)dst_reg->umax_value) { dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; } else { dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); } static void scalar32_min_max_or(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); u32 umin_val = src_reg->u32_min_value; if (src_known && dst_known) { __mark_reg32_known(dst_reg, var32_off.value); return; } /* We get our maximum from the var_off, and our minimum is the * maximum of the operands' minima */ dst_reg->u32_min_value = max(dst_reg->u32_min_value, umin_val); dst_reg->u32_max_value = var32_off.value | var32_off.mask; /* Safe to set s32 bounds by casting u32 result into s32 when u32 * doesn't cross sign boundary. Otherwise set s32 bounds to unbounded. */ if ((s32)dst_reg->u32_min_value <= (s32)dst_reg->u32_max_value) { dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } else { dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } } static void scalar_min_max_or(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_is_const(src_reg->var_off); bool dst_known = tnum_is_const(dst_reg->var_off); u64 umin_val = src_reg->umin_value; if (src_known && dst_known) { __mark_reg_known(dst_reg, dst_reg->var_off.value); return; } /* We get our maximum from the var_off, and our minimum is the * maximum of the operands' minima */ dst_reg->umin_value = max(dst_reg->umin_value, umin_val); dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask; /* Safe to set s64 bounds by casting u64 result into s64 when u64 * doesn't cross sign boundary. Otherwise set s64 bounds to unbounded. */ if ((s64)dst_reg->umin_value <= (s64)dst_reg->umax_value) { dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; } else { dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); } static void scalar32_min_max_xor(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); if (src_known && dst_known) { __mark_reg32_known(dst_reg, var32_off.value); return; } /* We get both minimum and maximum from the var32_off. */ dst_reg->u32_min_value = var32_off.value; dst_reg->u32_max_value = var32_off.value | var32_off.mask; /* Safe to set s32 bounds by casting u32 result into s32 when u32 * doesn't cross sign boundary. Otherwise set s32 bounds to unbounded. */ if ((s32)dst_reg->u32_min_value <= (s32)dst_reg->u32_max_value) { dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } else { dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } } static void scalar_min_max_xor(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_is_const(src_reg->var_off); bool dst_known = tnum_is_const(dst_reg->var_off); if (src_known && dst_known) { /* dst_reg->var_off.value has been updated earlier */ __mark_reg_known(dst_reg, dst_reg->var_off.value); return; } /* We get both minimum and maximum from the var_off. */ dst_reg->umin_value = dst_reg->var_off.value; dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask; /* Safe to set s64 bounds by casting u64 result into s64 when u64 * doesn't cross sign boundary. Otherwise set s64 bounds to unbounded. */ if ((s64)dst_reg->umin_value <= (s64)dst_reg->umax_value) { dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; } else { dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } __update_reg_bounds(dst_reg); } static void __scalar32_min_max_lsh(struct bpf_reg_state *dst_reg, u64 umin_val, u64 umax_val) { /* We lose all sign bit information (except what we can pick * up from var_off) */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; /* If we might shift our top bit out, then we know nothing */ if (umax_val > 31 || dst_reg->u32_max_value > 1ULL << (31 - umax_val)) { dst_reg->u32_min_value = 0; dst_reg->u32_max_value = U32_MAX; } else { dst_reg->u32_min_value <<= umin_val; dst_reg->u32_max_value <<= umax_val; } } static void scalar32_min_max_lsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u32 umax_val = src_reg->u32_max_value; u32 umin_val = src_reg->u32_min_value; /* u32 alu operation will zext upper bits */ struct tnum subreg = tnum_subreg(dst_reg->var_off); __scalar32_min_max_lsh(dst_reg, umin_val, umax_val); dst_reg->var_off = tnum_subreg(tnum_lshift(subreg, umin_val)); /* Not required but being careful mark reg64 bounds as unknown so * that we are forced to pick them up from tnum and zext later and * if some path skips this step we are still safe. */ __mark_reg64_unbounded(dst_reg); __update_reg32_bounds(dst_reg); } static void __scalar64_min_max_lsh(struct bpf_reg_state *dst_reg, u64 umin_val, u64 umax_val) { /* Special case <<32 because it is a common compiler pattern to sign * extend subreg by doing <<32 s>>32. In this case if 32bit bounds are * positive we know this shift will also be positive so we can track * bounds correctly. Otherwise we lose all sign bit information except * what we can pick up from var_off. Perhaps we can generalize this * later to shifts of any length. */ if (umin_val == 32 && umax_val == 32 && dst_reg->s32_max_value >= 0) dst_reg->smax_value = (s64)dst_reg->s32_max_value << 32; else dst_reg->smax_value = S64_MAX; if (umin_val == 32 && umax_val == 32 && dst_reg->s32_min_value >= 0) dst_reg->smin_value = (s64)dst_reg->s32_min_value << 32; else dst_reg->smin_value = S64_MIN; /* If we might shift our top bit out, then we know nothing */ if (dst_reg->umax_value > 1ULL << (63 - umax_val)) { dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { dst_reg->umin_value <<= umin_val; dst_reg->umax_value <<= umax_val; } } static void scalar_min_max_lsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 umax_val = src_reg->umax_value; u64 umin_val = src_reg->umin_value; /* scalar64 calc uses 32bit unshifted bounds so must be called first */ __scalar64_min_max_lsh(dst_reg, umin_val, umax_val); __scalar32_min_max_lsh(dst_reg, umin_val, umax_val); dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val); /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); } static void scalar32_min_max_rsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { struct tnum subreg = tnum_subreg(dst_reg->var_off); u32 umax_val = src_reg->u32_max_value; u32 umin_val = src_reg->u32_min_value; /* BPF_RSH is an unsigned shift. If the value in dst_reg might * be negative, then either: * 1) src_reg might be zero, so the sign bit of the result is * unknown, so we lose our signed bounds * 2) it's known negative, thus the unsigned bounds capture the * signed bounds * 3) the signed bounds cross zero, so they tell us nothing * about the result * If the value in dst_reg is known nonnegative, then again the * unsigned bounds capture the signed bounds. * Thus, in all cases it suffices to blow away our signed bounds * and rely on inferring new ones from the unsigned bounds and * var_off of the result. */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; dst_reg->var_off = tnum_rshift(subreg, umin_val); dst_reg->u32_min_value >>= umax_val; dst_reg->u32_max_value >>= umin_val; __mark_reg64_unbounded(dst_reg); __update_reg32_bounds(dst_reg); } static void scalar_min_max_rsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 umax_val = src_reg->umax_value; u64 umin_val = src_reg->umin_value; /* BPF_RSH is an unsigned shift. If the value in dst_reg might * be negative, then either: * 1) src_reg might be zero, so the sign bit of the result is * unknown, so we lose our signed bounds * 2) it's known negative, thus the unsigned bounds capture the * signed bounds * 3) the signed bounds cross zero, so they tell us nothing * about the result * If the value in dst_reg is known nonnegative, then again the * unsigned bounds capture the signed bounds. * Thus, in all cases it suffices to blow away our signed bounds * and rely on inferring new ones from the unsigned bounds and * var_off of the result. */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val); dst_reg->umin_value >>= umax_val; dst_reg->umax_value >>= umin_val; /* Its not easy to operate on alu32 bounds here because it depends * on bits being shifted in. Take easy way out and mark unbounded * so we can recalculate later from tnum. */ __mark_reg32_unbounded(dst_reg); __update_reg_bounds(dst_reg); } static void scalar32_min_max_arsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 umin_val = src_reg->u32_min_value; /* Upon reaching here, src_known is true and * umax_val is equal to umin_val. */ dst_reg->s32_min_value = (u32)(((s32)dst_reg->s32_min_value) >> umin_val); dst_reg->s32_max_value = (u32)(((s32)dst_reg->s32_max_value) >> umin_val); dst_reg->var_off = tnum_arshift(tnum_subreg(dst_reg->var_off), umin_val, 32); /* blow away the dst_reg umin_value/umax_value and rely on * dst_reg var_off to refine the result. */ dst_reg->u32_min_value = 0; dst_reg->u32_max_value = U32_MAX; __mark_reg64_unbounded(dst_reg); __update_reg32_bounds(dst_reg); } static void scalar_min_max_arsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 umin_val = src_reg->umin_value; /* Upon reaching here, src_known is true and umax_val is equal * to umin_val. */ dst_reg->smin_value >>= umin_val; dst_reg->smax_value >>= umin_val; dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, 64); /* blow away the dst_reg umin_value/umax_value and rely on * dst_reg var_off to refine the result. */ dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; /* Its not easy to operate on alu32 bounds here because it depends * on bits being shifted in from upper 32-bits. Take easy way out * and mark unbounded so we can recalculate later from tnum. */ __mark_reg32_unbounded(dst_reg); __update_reg_bounds(dst_reg); } static bool is_safe_to_compute_dst_reg_range(struct bpf_insn *insn, const struct bpf_reg_state *src_reg) { bool src_is_const = false; u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; if (insn_bitness == 32) { if (tnum_subreg_is_const(src_reg->var_off) && src_reg->s32_min_value == src_reg->s32_max_value && src_reg->u32_min_value == src_reg->u32_max_value) src_is_const = true; } else { if (tnum_is_const(src_reg->var_off) && src_reg->smin_value == src_reg->smax_value && src_reg->umin_value == src_reg->umax_value) src_is_const = true; } switch (BPF_OP(insn->code)) { case BPF_ADD: case BPF_SUB: case BPF_AND: case BPF_XOR: case BPF_OR: case BPF_MUL: return true; /* Shift operators range is only computable if shift dimension operand * is a constant. Shifts greater than 31 or 63 are undefined. This * includes shifts by a negative number. */ case BPF_LSH: case BPF_RSH: case BPF_ARSH: return (src_is_const && src_reg->umax_value < insn_bitness); default: return false; } } /* WARNING: This function does calculations on 64-bit values, but the actual * execution may occur on 32-bit values. Therefore, things like bitshifts * need extra checks in the 32-bit case. */ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_reg_state *dst_reg, struct bpf_reg_state src_reg) { u8 opcode = BPF_OP(insn->code); bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64); int ret; if (!is_safe_to_compute_dst_reg_range(insn, &src_reg)) { __mark_reg_unknown(env, dst_reg); return 0; } if (sanitize_needed(opcode)) { ret = sanitize_val_alu(env, insn); if (ret < 0) return sanitize_err(env, insn, ret, NULL, NULL); } /* Calculate sign/unsigned bounds and tnum for alu32 and alu64 bit ops. * There are two classes of instructions: The first class we track both * alu32 and alu64 sign/unsigned bounds independently this provides the * greatest amount of precision when alu operations are mixed with jmp32 * operations. These operations are BPF_ADD, BPF_SUB, BPF_MUL, BPF_ADD, * and BPF_OR. This is possible because these ops have fairly easy to * understand and calculate behavior in both 32-bit and 64-bit alu ops. * See alu32 verifier tests for examples. The second class of * operations, BPF_LSH, BPF_RSH, and BPF_ARSH, however are not so easy * with regards to tracking sign/unsigned bounds because the bits may * cross subreg boundaries in the alu64 case. When this happens we mark * the reg unbounded in the subreg bound space and use the resulting * tnum to calculate an approximation of the sign/unsigned bounds. */ switch (opcode) { case BPF_ADD: scalar32_min_max_add(dst_reg, &src_reg); scalar_min_max_add(dst_reg, &src_reg); dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off); break; case BPF_SUB: scalar32_min_max_sub(dst_reg, &src_reg); scalar_min_max_sub(dst_reg, &src_reg); dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off); break; case BPF_MUL: dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off); scalar32_min_max_mul(dst_reg, &src_reg); scalar_min_max_mul(dst_reg, &src_reg); break; case BPF_AND: dst_reg->var_off = tnum_and(dst_reg->var_off, src_reg.var_off); scalar32_min_max_and(dst_reg, &src_reg); scalar_min_max_and(dst_reg, &src_reg); break; case BPF_OR: dst_reg->var_off = tnum_or(dst_reg->var_off, src_reg.var_off); scalar32_min_max_or(dst_reg, &src_reg); scalar_min_max_or(dst_reg, &src_reg); break; case BPF_XOR: dst_reg->var_off = tnum_xor(dst_reg->var_off, src_reg.var_off); scalar32_min_max_xor(dst_reg, &src_reg); scalar_min_max_xor(dst_reg, &src_reg); break; case BPF_LSH: if (alu32) scalar32_min_max_lsh(dst_reg, &src_reg); else scalar_min_max_lsh(dst_reg, &src_reg); break; case BPF_RSH: if (alu32) scalar32_min_max_rsh(dst_reg, &src_reg); else scalar_min_max_rsh(dst_reg, &src_reg); break; case BPF_ARSH: if (alu32) scalar32_min_max_arsh(dst_reg, &src_reg); else scalar_min_max_arsh(dst_reg, &src_reg); break; default: break; } /* ALU32 ops are zero extended into 64bit register */ if (alu32) zext_32_to_64(dst_reg); reg_bounds_sync(dst_reg); return 0; } /* Handles ALU ops other than BPF_END, BPF_NEG and BPF_MOV: computes new min/max * and var_off. */ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg; struct bpf_reg_state *ptr_reg = NULL, off_reg = {0}; u8 opcode = BPF_OP(insn->code); int err; dst_reg = ®s[insn->dst_reg]; src_reg = NULL; if (dst_reg->type == PTR_TO_ARENA) { struct bpf_insn_aux_data *aux = cur_aux(env); if (BPF_CLASS(insn->code) == BPF_ALU64) /* * 32-bit operations zero upper bits automatically. * 64-bit operations need to be converted to 32. */ aux->needs_zext = true; /* Any arithmetic operations are allowed on arena pointers */ return 0; } if (dst_reg->type != SCALAR_VALUE) ptr_reg = dst_reg; else /* Make sure ID is cleared otherwise dst_reg min/max could be * incorrectly propagated into other registers by find_equal_scalars() */ dst_reg->id = 0; if (BPF_SRC(insn->code) == BPF_X) { src_reg = ®s[insn->src_reg]; if (src_reg->type != SCALAR_VALUE) { if (dst_reg->type != SCALAR_VALUE) { /* Combining two pointers by any ALU op yields * an arbitrary scalar. Disallow all math except * pointer subtraction */ if (opcode == BPF_SUB && env->allow_ptr_leaks) { mark_reg_unknown(env, regs, insn->dst_reg); return 0; } verbose(env, "R%d pointer %s pointer prohibited\n", insn->dst_reg, bpf_alu_string[opcode >> 4]); return -EACCES; } else { /* scalar += pointer * This is legal, but we have to reverse our * src/dest handling in computing the range */ err = mark_chain_precision(env, insn->dst_reg); if (err) return err; return adjust_ptr_min_max_vals(env, insn, src_reg, dst_reg); } } else if (ptr_reg) { /* pointer += scalar */ err = mark_chain_precision(env, insn->src_reg); if (err) return err; return adjust_ptr_min_max_vals(env, insn, dst_reg, src_reg); } else if (dst_reg->precise) { /* if dst_reg is precise, src_reg should be precise as well */ err = mark_chain_precision(env, insn->src_reg); if (err) return err; } } else { /* Pretend the src is a reg with a known value, since we only * need to be able to read from this state. */ off_reg.type = SCALAR_VALUE; __mark_reg_known(&off_reg, insn->imm); src_reg = &off_reg; if (ptr_reg) /* pointer += K */ return adjust_ptr_min_max_vals(env, insn, ptr_reg, src_reg); } /* Got here implies adding two SCALAR_VALUEs */ if (WARN_ON_ONCE(ptr_reg)) { print_verifier_state(env, state, true); verbose(env, "verifier internal error: unexpected ptr_reg\n"); return -EINVAL; } if (WARN_ON(!src_reg)) { print_verifier_state(env, state, true); verbose(env, "verifier internal error: no src_reg\n"); return -EINVAL; } return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg); } /* check validity of 32-bit and 64-bit arithmetic operations */ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = cur_regs(env); u8 opcode = BPF_OP(insn->code); int err; if (opcode == BPF_END || opcode == BPF_NEG) { if (opcode == BPF_NEG) { if (BPF_SRC(insn->code) != BPF_K || insn->src_reg != BPF_REG_0 || insn->off != 0 || insn->imm != 0) { verbose(env, "BPF_NEG uses reserved fields\n"); return -EINVAL; } } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0 || (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) || (BPF_CLASS(insn->code) == BPF_ALU64 && BPF_SRC(insn->code) != BPF_TO_LE)) { verbose(env, "BPF_END uses reserved fields\n"); return -EINVAL; } } /* check src operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; if (is_pointer_value(env, insn->dst_reg)) { verbose(env, "R%d pointer arithmetic prohibited\n", insn->dst_reg); return -EACCES; } /* check dest operand */ err = check_reg_arg(env, insn->dst_reg, DST_OP); if (err) return err; } else if (opcode == BPF_MOV) { if (BPF_SRC(insn->code) == BPF_X) { if (BPF_CLASS(insn->code) == BPF_ALU) { if ((insn->off != 0 && insn->off != 8 && insn->off != 16) || insn->imm) { verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } } else if (insn->off == BPF_ADDR_SPACE_CAST) { if (insn->imm != 1 && insn->imm != 1u << 16) { verbose(env, "addr_space_cast insn can only convert between address space 1 and 0\n"); return -EINVAL; } if (!env->prog->aux->arena) { verbose(env, "addr_space_cast insn can only be used in a program that has an associated arena\n"); return -EINVAL; } } else { if ((insn->off != 0 && insn->off != 8 && insn->off != 16 && insn->off != 32) || insn->imm) { verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } } /* check src operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0) { verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } } /* check dest operand, mark as required later */ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); if (err) return err; if (BPF_SRC(insn->code) == BPF_X) { struct bpf_reg_state *src_reg = regs + insn->src_reg; struct bpf_reg_state *dst_reg = regs + insn->dst_reg; if (BPF_CLASS(insn->code) == BPF_ALU64) { if (insn->imm) { /* off == BPF_ADDR_SPACE_CAST */ mark_reg_unknown(env, regs, insn->dst_reg); if (insn->imm == 1) { /* cast from as(1) to as(0) */ dst_reg->type = PTR_TO_ARENA; /* PTR_TO_ARENA is 32-bit */ dst_reg->subreg_def = env->insn_idx + 1; } } else if (insn->off == 0) { /* case: R1 = R2 * copy register state to dest reg */ assign_scalar_id_before_mov(env, src_reg); copy_register_state(dst_reg, src_reg); dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = DEF_NOT_SUBREG; } else { /* case: R1 = (s8, s16 s32)R2 */ if (is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d sign-extension part of pointer\n", insn->src_reg); return -EACCES; } else if (src_reg->type == SCALAR_VALUE) { bool no_sext; no_sext = src_reg->umax_value < (1ULL << (insn->off - 1)); if (no_sext) assign_scalar_id_before_mov(env, src_reg); copy_register_state(dst_reg, src_reg); if (!no_sext) dst_reg->id = 0; coerce_reg_to_size_sx(dst_reg, insn->off >> 3); dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = DEF_NOT_SUBREG; } else { mark_reg_unknown(env, regs, insn->dst_reg); } } } else { /* R1 = (u32) R2 */ if (is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d partial copy of pointer\n", insn->src_reg); return -EACCES; } else if (src_reg->type == SCALAR_VALUE) { if (insn->off == 0) { bool is_src_reg_u32 = get_reg_width(src_reg) <= 32; if (is_src_reg_u32) assign_scalar_id_before_mov(env, src_reg); copy_register_state(dst_reg, src_reg); /* Make sure ID is cleared if src_reg is not in u32 * range otherwise dst_reg min/max could be incorrectly * propagated into src_reg by find_equal_scalars() */ if (!is_src_reg_u32) dst_reg->id = 0; dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = env->insn_idx + 1; } else { /* case: W1 = (s8, s16)W2 */ bool no_sext = src_reg->umax_value < (1ULL << (insn->off - 1)); if (no_sext) assign_scalar_id_before_mov(env, src_reg); copy_register_state(dst_reg, src_reg); if (!no_sext) dst_reg->id = 0; dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = env->insn_idx + 1; coerce_subreg_to_size_sx(dst_reg, insn->off >> 3); } } else { mark_reg_unknown(env, regs, insn->dst_reg); } zext_32_to_64(dst_reg); reg_bounds_sync(dst_reg); } } else { /* case: R = imm * remember the value we stored into this reg */ /* clear any state __mark_reg_known doesn't set */ mark_reg_unknown(env, regs, insn->dst_reg); regs[insn->dst_reg].type = SCALAR_VALUE; if (BPF_CLASS(insn->code) == BPF_ALU64) { __mark_reg_known(regs + insn->dst_reg, insn->imm); } else { __mark_reg_known(regs + insn->dst_reg, (u32)insn->imm); } } } else if (opcode > BPF_END) { verbose(env, "invalid BPF_ALU opcode %x\n", opcode); return -EINVAL; } else { /* all other ALU ops: and, sub, xor, add, ... */ if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0 || insn->off > 1 || (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) { verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; } else { if (insn->src_reg != BPF_REG_0 || insn->off > 1 || (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) { verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } } /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; if ((opcode == BPF_MOD || opcode == BPF_DIV) && BPF_SRC(insn->code) == BPF_K && insn->imm == 0) { verbose(env, "div by zero\n"); return -EINVAL; } if ((opcode == BPF_LSH || opcode == BPF_RSH || opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) { int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32; if (insn->imm < 0 || insn->imm >= size) { verbose(env, "invalid shift %d\n", insn->imm); return -EINVAL; } } /* check dest operand */ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); err = err ?: adjust_reg_min_max_vals(env, insn); if (err) return err; } return reg_bounds_sanity_check(env, ®s[insn->dst_reg], "alu"); } static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, struct bpf_reg_state *dst_reg, enum bpf_reg_type type, bool range_right_open) { struct bpf_func_state *state; struct bpf_reg_state *reg; int new_range; if (dst_reg->off < 0 || (dst_reg->off == 0 && range_right_open)) /* This doesn't give us any range */ return; if (dst_reg->umax_value > MAX_PACKET_OFF || dst_reg->umax_value + dst_reg->off > MAX_PACKET_OFF) /* Risk of overflow. For instance, ptr + (1<<63) may be less * than pkt_end, but that's because it's also less than pkt. */ return; new_range = dst_reg->off; if (range_right_open) new_range++; /* Examples for register markings: * * pkt_data in dst register: * * r2 = r3; * r2 += 8; * if (r2 > pkt_end) goto <handle exception> * <access okay> * * r2 = r3; * r2 += 8; * if (r2 < pkt_end) goto <access okay> * <handle exception> * * Where: * r2 == dst_reg, pkt_end == src_reg * r2=pkt(id=n,off=8,r=0) * r3=pkt(id=n,off=0,r=0) * * pkt_data in src register: * * r2 = r3; * r2 += 8; * if (pkt_end >= r2) goto <access okay> * <handle exception> * * r2 = r3; * r2 += 8; * if (pkt_end <= r2) goto <handle exception> * <access okay> * * Where: * pkt_end == dst_reg, r2 == src_reg * r2=pkt(id=n,off=8,r=0) * r3=pkt(id=n,off=0,r=0) * * Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8) * or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8) * and [r3, r3 + 8-1) respectively is safe to access depending on * the check. */ /* If our ids match, then we must have the same max_value. And we * don't care about the other reg's fixed offset, since if it's too big * the range won't allow anything. * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16. */ bpf_for_each_reg_in_vstate(vstate, state, reg, ({ if (reg->type == type && reg->id == dst_reg->id) /* keep the maximum range already checked */ reg->range = max(reg->range, new_range); })); } /* * <reg1> <op> <reg2>, currently assuming reg2 is a constant */ static int is_scalar_branch_taken(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2, u8 opcode, bool is_jmp32) { struct tnum t1 = is_jmp32 ? tnum_subreg(reg1->var_off) : reg1->var_off; struct tnum t2 = is_jmp32 ? tnum_subreg(reg2->var_off) : reg2->var_off; u64 umin1 = is_jmp32 ? (u64)reg1->u32_min_value : reg1->umin_value; u64 umax1 = is_jmp32 ? (u64)reg1->u32_max_value : reg1->umax_value; s64 smin1 = is_jmp32 ? (s64)reg1->s32_min_value : reg1->smin_value; s64 smax1 = is_jmp32 ? (s64)reg1->s32_max_value : reg1->smax_value; u64 umin2 = is_jmp32 ? (u64)reg2->u32_min_value : reg2->umin_value; u64 umax2 = is_jmp32 ? (u64)reg2->u32_max_value : reg2->umax_value; s64 smin2 = is_jmp32 ? (s64)reg2->s32_min_value : reg2->smin_value; s64 smax2 = is_jmp32 ? (s64)reg2->s32_max_value : reg2->smax_value; switch (opcode) { case BPF_JEQ: /* constants, umin/umax and smin/smax checks would be * redundant in this case because they all should match */ if (tnum_is_const(t1) && tnum_is_const(t2)) return t1.value == t2.value; /* non-overlapping ranges */ if (umin1 > umax2 || umax1 < umin2) return 0; if (smin1 > smax2 || smax1 < smin2) return 0; if (!is_jmp32) { /* if 64-bit ranges are inconclusive, see if we can * utilize 32-bit subrange knowledge to eliminate * branches that can't be taken a priori */ if (reg1->u32_min_value > reg2->u32_max_value || reg1->u32_max_value < reg2->u32_min_value) return 0; if (reg1->s32_min_value > reg2->s32_max_value || reg1->s32_max_value < reg2->s32_min_value) return 0; } break; case BPF_JNE: /* constants, umin/umax and smin/smax checks would be * redundant in this case because they all should match */ if (tnum_is_const(t1) && tnum_is_const(t2)) return t1.value != t2.value; /* non-overlapping ranges */ if (umin1 > umax2 || umax1 < umin2) return 1; if (smin1 > smax2 || smax1 < smin2) return 1; if (!is_jmp32) { /* if 64-bit ranges are inconclusive, see if we can * utilize 32-bit subrange knowledge to eliminate * branches that can't be taken a priori */ if (reg1->u32_min_value > reg2->u32_max_value || reg1->u32_max_value < reg2->u32_min_value) return 1; if (reg1->s32_min_value > reg2->s32_max_value || reg1->s32_max_value < reg2->s32_min_value) return 1; } break; case BPF_JSET: if (!is_reg_const(reg2, is_jmp32)) { swap(reg1, reg2); swap(t1, t2); } if (!is_reg_const(reg2, is_jmp32)) return -1; if ((~t1.mask & t1.value) & t2.value) return 1; if (!((t1.mask | t1.value) & t2.value)) return 0; break; case BPF_JGT: if (umin1 > umax2) return 1; else if (umax1 <= umin2) return 0; break; case BPF_JSGT: if (smin1 > smax2) return 1; else if (smax1 <= smin2) return 0; break; case BPF_JLT: if (umax1 < umin2) return 1; else if (umin1 >= umax2) return 0; break; case BPF_JSLT: if (smax1 < smin2) return 1; else if (smin1 >= smax2) return 0; break; case BPF_JGE: if (umin1 >= umax2) return 1; else if (umax1 < umin2) return 0; break; case BPF_JSGE: if (smin1 >= smax2) return 1; else if (smax1 < smin2) return 0; break; case BPF_JLE: if (umax1 <= umin2) return 1; else if (umin1 > umax2) return 0; break; case BPF_JSLE: if (smax1 <= smin2) return 1; else if (smin1 > smax2) return 0; break; } return -1; } static int flip_opcode(u32 opcode) { /* How can we transform "a <op> b" into "b <op> a"? */ static const u8 opcode_flip[16] = { /* these stay the same */ [BPF_JEQ >> 4] = BPF_JEQ, [BPF_JNE >> 4] = BPF_JNE, [BPF_JSET >> 4] = BPF_JSET, /* these swap "lesser" and "greater" (L and G in the opcodes) */ [BPF_JGE >> 4] = BPF_JLE, [BPF_JGT >> 4] = BPF_JLT, [BPF_JLE >> 4] = BPF_JGE, [BPF_JLT >> 4] = BPF_JGT, [BPF_JSGE >> 4] = BPF_JSLE, [BPF_JSGT >> 4] = BPF_JSLT, [BPF_JSLE >> 4] = BPF_JSGE, [BPF_JSLT >> 4] = BPF_JSGT }; return opcode_flip[opcode >> 4]; } static int is_pkt_ptr_branch_taken(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg, u8 opcode) { struct bpf_reg_state *pkt; if (src_reg->type == PTR_TO_PACKET_END) { pkt = dst_reg; } else if (dst_reg->type == PTR_TO_PACKET_END) { pkt = src_reg; opcode = flip_opcode(opcode); } else { return -1; } if (pkt->range >= 0) return -1; switch (opcode) { case BPF_JLE: /* pkt <= pkt_end */ fallthrough; case BPF_JGT: /* pkt > pkt_end */ if (pkt->range == BEYOND_PKT_END) /* pkt has at last one extra byte beyond pkt_end */ return opcode == BPF_JGT; break; case BPF_JLT: /* pkt < pkt_end */ fallthrough; case BPF_JGE: /* pkt >= pkt_end */ if (pkt->range == BEYOND_PKT_END || pkt->range == AT_PKT_END) return opcode == BPF_JGE; break; } return -1; } /* compute branch direction of the expression "if (<reg1> opcode <reg2>) goto target;" * and return: * 1 - branch will be taken and "goto target" will be executed * 0 - branch will not be taken and fall-through to next insn * -1 - unknown. Example: "if (reg1 < 5)" is unknown when register value * range [0,10] */ static int is_branch_taken(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2, u8 opcode, bool is_jmp32) { if (reg_is_pkt_pointer_any(reg1) && reg_is_pkt_pointer_any(reg2) && !is_jmp32) return is_pkt_ptr_branch_taken(reg1, reg2, opcode); if (__is_pointer_value(false, reg1) || __is_pointer_value(false, reg2)) { u64 val; /* arrange that reg2 is a scalar, and reg1 is a pointer */ if (!is_reg_const(reg2, is_jmp32)) { opcode = flip_opcode(opcode); swap(reg1, reg2); } /* and ensure that reg2 is a constant */ if (!is_reg_const(reg2, is_jmp32)) return -1; if (!reg_not_null(reg1)) return -1; /* If pointer is valid tests against zero will fail so we can * use this to direct branch taken. */ val = reg_const_value(reg2, is_jmp32); if (val != 0) return -1; switch (opcode) { case BPF_JEQ: return 0; case BPF_JNE: return 1; default: return -1; } } /* now deal with two scalars, but not necessarily constants */ return is_scalar_branch_taken(reg1, reg2, opcode, is_jmp32); } /* Opcode that corresponds to a *false* branch condition. * E.g., if r1 < r2, then reverse (false) condition is r1 >= r2 */ static u8 rev_opcode(u8 opcode) { switch (opcode) { case BPF_JEQ: return BPF_JNE; case BPF_JNE: return BPF_JEQ; /* JSET doesn't have it's reverse opcode in BPF, so add * BPF_X flag to denote the reverse of that operation */ case BPF_JSET: return BPF_JSET | BPF_X; case BPF_JSET | BPF_X: return BPF_JSET; case BPF_JGE: return BPF_JLT; case BPF_JGT: return BPF_JLE; case BPF_JLE: return BPF_JGT; case BPF_JLT: return BPF_JGE; case BPF_JSGE: return BPF_JSLT; case BPF_JSGT: return BPF_JSLE; case BPF_JSLE: return BPF_JSGT; case BPF_JSLT: return BPF_JSGE; default: return 0; } } /* Refine range knowledge for <reg1> <op> <reg>2 conditional operation. */ static void regs_refine_cond_op(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2, u8 opcode, bool is_jmp32) { struct tnum t; u64 val; /* In case of GE/GT/SGE/JST, reuse LE/LT/SLE/SLT logic from below */ switch (opcode) { case BPF_JGE: case BPF_JGT: case BPF_JSGE: case BPF_JSGT: opcode = flip_opcode(opcode); swap(reg1, reg2); break; default: break; } switch (opcode) { case BPF_JEQ: if (is_jmp32) { reg1->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value); reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value); reg1->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value); reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value); reg2->u32_min_value = reg1->u32_min_value; reg2->u32_max_value = reg1->u32_max_value; reg2->s32_min_value = reg1->s32_min_value; reg2->s32_max_value = reg1->s32_max_value; t = tnum_intersect(tnum_subreg(reg1->var_off), tnum_subreg(reg2->var_off)); reg1->var_off = tnum_with_subreg(reg1->var_off, t); reg2->var_off = tnum_with_subreg(reg2->var_off, t); } else { reg1->umin_value = max(reg1->umin_value, reg2->umin_value); reg1->umax_value = min(reg1->umax_value, reg2->umax_value); reg1->smin_value = max(reg1->smin_value, reg2->smin_value); reg1->smax_value = min(reg1->smax_value, reg2->smax_value); reg2->umin_value = reg1->umin_value; reg2->umax_value = reg1->umax_value; reg2->smin_value = reg1->smin_value; reg2->smax_value = reg1->smax_value; reg1->var_off = tnum_intersect(reg1->var_off, reg2->var_off); reg2->var_off = reg1->var_off; } break; case BPF_JNE: if (!is_reg_const(reg2, is_jmp32)) swap(reg1, reg2); if (!is_reg_const(reg2, is_jmp32)) break; /* try to recompute the bound of reg1 if reg2 is a const and * is exactly the edge of reg1. */ val = reg_const_value(reg2, is_jmp32); if (is_jmp32) { /* u32_min_value is not equal to 0xffffffff at this point, * because otherwise u32_max_value is 0xffffffff as well, * in such a case both reg1 and reg2 would be constants, * jump would be predicted and reg_set_min_max() won't * be called. * * Same reasoning works for all {u,s}{min,max}{32,64} cases * below. */ if (reg1->u32_min_value == (u32)val) reg1->u32_min_value++; if (reg1->u32_max_value == (u32)val) reg1->u32_max_value--; if (reg1->s32_min_value == (s32)val) reg1->s32_min_value++; if (reg1->s32_max_value == (s32)val) reg1->s32_max_value--; } else { if (reg1->umin_value == (u64)val) reg1->umin_value++; if (reg1->umax_value == (u64)val) reg1->umax_value--; if (reg1->smin_value == (s64)val) reg1->smin_value++; if (reg1->smax_value == (s64)val) reg1->smax_value--; } break; case BPF_JSET: if (!is_reg_const(reg2, is_jmp32)) swap(reg1, reg2); if (!is_reg_const(reg2, is_jmp32)) break; val = reg_const_value(reg2, is_jmp32); /* BPF_JSET (i.e., TRUE branch, *not* BPF_JSET | BPF_X) * requires single bit to learn something useful. E.g., if we * know that `r1 & 0x3` is true, then which bits (0, 1, or both) * are actually set? We can learn something definite only if * it's a single-bit value to begin with. * * BPF_JSET | BPF_X (i.e., negation of BPF_JSET) doesn't have * this restriction. I.e., !(r1 & 0x3) means neither bit 0 nor * bit 1 is set, which we can readily use in adjustments. */ if (!is_power_of_2(val)) break; if (is_jmp32) { t = tnum_or(tnum_subreg(reg1->var_off), tnum_const(val)); reg1->var_off = tnum_with_subreg(reg1->var_off, t); } else { reg1->var_off = tnum_or(reg1->var_off, tnum_const(val)); } break; case BPF_JSET | BPF_X: /* reverse of BPF_JSET, see rev_opcode() */ if (!is_reg_const(reg2, is_jmp32)) swap(reg1, reg2); if (!is_reg_const(reg2, is_jmp32)) break; val = reg_const_value(reg2, is_jmp32); if (is_jmp32) { t = tnum_and(tnum_subreg(reg1->var_off), tnum_const(~val)); reg1->var_off = tnum_with_subreg(reg1->var_off, t); } else { reg1->var_off = tnum_and(reg1->var_off, tnum_const(~val)); } break; case BPF_JLE: if (is_jmp32) { reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value); reg2->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value); } else { reg1->umax_value = min(reg1->umax_value, reg2->umax_value); reg2->umin_value = max(reg1->umin_value, reg2->umin_value); } break; case BPF_JLT: if (is_jmp32) { reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value - 1); reg2->u32_min_value = max(reg1->u32_min_value + 1, reg2->u32_min_value); } else { reg1->umax_value = min(reg1->umax_value, reg2->umax_value - 1); reg2->umin_value = max(reg1->umin_value + 1, reg2->umin_value); } break; case BPF_JSLE: if (is_jmp32) { reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value); reg2->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value); } else { reg1->smax_value = min(reg1->smax_value, reg2->smax_value); reg2->smin_value = max(reg1->smin_value, reg2->smin_value); } break; case BPF_JSLT: if (is_jmp32) { reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value - 1); reg2->s32_min_value = max(reg1->s32_min_value + 1, reg2->s32_min_value); } else { reg1->smax_value = min(reg1->smax_value, reg2->smax_value - 1); reg2->smin_value = max(reg1->smin_value + 1, reg2->smin_value); } break; default: return; } } /* Adjusts the register min/max values in the case that the dst_reg and * src_reg are both SCALAR_VALUE registers (or we are simply doing a BPF_K * check, in which case we have a fake SCALAR_VALUE representing insn->imm). * Technically we can do similar adjustments for pointers to the same object, * but we don't support that right now. */ static int reg_set_min_max(struct bpf_verifier_env *env, struct bpf_reg_state *true_reg1, struct bpf_reg_state *true_reg2, struct bpf_reg_state *false_reg1, struct bpf_reg_state *false_reg2, u8 opcode, bool is_jmp32) { int err; /* If either register is a pointer, we can't learn anything about its * variable offset from the compare (unless they were a pointer into * the same object, but we don't bother with that). */ if (false_reg1->type != SCALAR_VALUE || false_reg2->type != SCALAR_VALUE) return 0; /* fallthrough (FALSE) branch */ regs_refine_cond_op(false_reg1, false_reg2, rev_opcode(opcode), is_jmp32); reg_bounds_sync(false_reg1); reg_bounds_sync(false_reg2); /* jump (TRUE) branch */ regs_refine_cond_op(true_reg1, true_reg2, opcode, is_jmp32); reg_bounds_sync(true_reg1); reg_bounds_sync(true_reg2); err = reg_bounds_sanity_check(env, true_reg1, "true_reg1"); err = err ?: reg_bounds_sanity_check(env, true_reg2, "true_reg2"); err = err ?: reg_bounds_sanity_check(env, false_reg1, "false_reg1"); err = err ?: reg_bounds_sanity_check(env, false_reg2, "false_reg2"); return err; } static void mark_ptr_or_null_reg(struct bpf_func_state *state, struct bpf_reg_state *reg, u32 id, bool is_null) { if (type_may_be_null(reg->type) && reg->id == id && (is_rcu_reg(reg) || !WARN_ON_ONCE(!reg->id))) { /* Old offset (both fixed and variable parts) should have been * known-zero, because we don't allow pointer arithmetic on * pointers that might be NULL. If we see this happening, don't * convert the register. * * But in some cases, some helpers that return local kptrs * advance offset for the returned pointer. In those cases, it * is fine to expect to see reg->off. */ if (WARN_ON_ONCE(reg->smin_value || reg->smax_value || !tnum_equals_const(reg->var_off, 0))) return; if (!(type_is_ptr_alloc_obj(reg->type) || type_is_non_owning_ref(reg->type)) && WARN_ON_ONCE(reg->off)) return; if (is_null) { reg->type = SCALAR_VALUE; /* We don't need id and ref_obj_id from this point * onwards anymore, thus we should better reset it, * so that state pruning has chances to take effect. */ reg->id = 0; reg->ref_obj_id = 0; return; } mark_ptr_not_null_reg(reg); if (!reg_may_point_to_spin_lock(reg)) { /* For not-NULL ptr, reg->ref_obj_id will be reset * in release_reference(). * * reg->id is still used by spin_lock ptr. Other * than spin_lock ptr type, reg->id can be reset. */ reg->id = 0; } } } /* The logic is similar to find_good_pkt_pointers(), both could eventually * be folded together at some point. */ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, bool is_null) { struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *regs = state->regs, *reg; u32 ref_obj_id = regs[regno].ref_obj_id; u32 id = regs[regno].id; if (ref_obj_id && ref_obj_id == id && is_null) /* regs[regno] is in the " == NULL" branch. * No one could have freed the reference state before * doing the NULL check. */ WARN_ON_ONCE(release_reference_state(state, id)); bpf_for_each_reg_in_vstate(vstate, state, reg, ({ mark_ptr_or_null_reg(state, reg, id, is_null); })); } static bool try_match_pkt_pointers(const struct bpf_insn *insn, struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg, struct bpf_verifier_state *this_branch, struct bpf_verifier_state *other_branch) { if (BPF_SRC(insn->code) != BPF_X) return false; /* Pointers are always 64-bit. */ if (BPF_CLASS(insn->code) == BPF_JMP32) return false; switch (BPF_OP(insn->code)) { case BPF_JGT: if ((dst_reg->type == PTR_TO_PACKET && src_reg->type == PTR_TO_PACKET_END) || (dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { /* pkt_data' > pkt_end, pkt_meta' > pkt_data */ find_good_pkt_pointers(this_branch, dst_reg, dst_reg->type, false); mark_pkt_end(other_branch, insn->dst_reg, true); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && src_reg->type == PTR_TO_PACKET_META)) { /* pkt_end > pkt_data', pkt_data > pkt_meta' */ find_good_pkt_pointers(other_branch, src_reg, src_reg->type, true); mark_pkt_end(this_branch, insn->src_reg, false); } else { return false; } break; case BPF_JLT: if ((dst_reg->type == PTR_TO_PACKET && src_reg->type == PTR_TO_PACKET_END) || (dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { /* pkt_data' < pkt_end, pkt_meta' < pkt_data */ find_good_pkt_pointers(other_branch, dst_reg, dst_reg->type, true); mark_pkt_end(this_branch, insn->dst_reg, false); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && src_reg->type == PTR_TO_PACKET_META)) { /* pkt_end < pkt_data', pkt_data > pkt_meta' */ find_good_pkt_pointers(this_branch, src_reg, src_reg->type, false); mark_pkt_end(other_branch, insn->src_reg, true); } else { return false; } break; case BPF_JGE: if ((dst_reg->type == PTR_TO_PACKET && src_reg->type == PTR_TO_PACKET_END) || (dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { /* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */ find_good_pkt_pointers(this_branch, dst_reg, dst_reg->type, true); mark_pkt_end(other_branch, insn->dst_reg, false); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && src_reg->type == PTR_TO_PACKET_META)) { /* pkt_end >= pkt_data', pkt_data >= pkt_meta' */ find_good_pkt_pointers(other_branch, src_reg, src_reg->type, false); mark_pkt_end(this_branch, insn->src_reg, true); } else { return false; } break; case BPF_JLE: if ((dst_reg->type == PTR_TO_PACKET && src_reg->type == PTR_TO_PACKET_END) || (dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { /* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */ find_good_pkt_pointers(other_branch, dst_reg, dst_reg->type, false); mark_pkt_end(this_branch, insn->dst_reg, true); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && src_reg->type == PTR_TO_PACKET_META)) { /* pkt_end <= pkt_data', pkt_data <= pkt_meta' */ find_good_pkt_pointers(this_branch, src_reg, src_reg->type, true); mark_pkt_end(other_branch, insn->src_reg, false); } else { return false; } break; default: return false; } return true; } static void find_equal_scalars(struct bpf_verifier_state *vstate, struct bpf_reg_state *known_reg) { struct bpf_func_state *state; struct bpf_reg_state *reg; bpf_for_each_reg_in_vstate(vstate, state, reg, ({ if (reg->type == SCALAR_VALUE && reg->id == known_reg->id) copy_register_state(reg, known_reg); })); } static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { struct bpf_verifier_state *this_branch = env->cur_state; struct bpf_verifier_state *other_branch; struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs; struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL; struct bpf_reg_state *eq_branch_regs; u8 opcode = BPF_OP(insn->code); bool is_jmp32; int pred = -1; int err; /* Only conditional jumps are expected to reach here. */ if (opcode == BPF_JA || opcode > BPF_JCOND) { verbose(env, "invalid BPF_JMP/JMP32 opcode %x\n", opcode); return -EINVAL; } if (opcode == BPF_JCOND) { struct bpf_verifier_state *cur_st = env->cur_state, *queued_st, *prev_st; int idx = *insn_idx; if (insn->code != (BPF_JMP | BPF_JCOND) || insn->src_reg != BPF_MAY_GOTO || insn->dst_reg || insn->imm || insn->off == 0) { verbose(env, "invalid may_goto off %d imm %d\n", insn->off, insn->imm); return -EINVAL; } prev_st = find_prev_entry(env, cur_st->parent, idx); /* branch out 'fallthrough' insn as a new state to explore */ queued_st = push_stack(env, idx + 1, idx, false); if (!queued_st) return -ENOMEM; queued_st->may_goto_depth++; if (prev_st) widen_imprecise_scalars(env, prev_st, queued_st); *insn_idx += insn->off; return 0; } /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; dst_reg = ®s[insn->dst_reg]; if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0) { verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); return -EINVAL; } /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; src_reg = ®s[insn->src_reg]; if (!(reg_is_pkt_pointer_any(dst_reg) && reg_is_pkt_pointer_any(src_reg)) && is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d pointer comparison prohibited\n", insn->src_reg); return -EACCES; } } else { if (insn->src_reg != BPF_REG_0) { verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); return -EINVAL; } src_reg = &env->fake_reg[0]; memset(src_reg, 0, sizeof(*src_reg)); src_reg->type = SCALAR_VALUE; __mark_reg_known(src_reg, insn->imm); } is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; pred = is_branch_taken(dst_reg, src_reg, opcode, is_jmp32); if (pred >= 0) { /* If we get here with a dst_reg pointer type it is because * above is_branch_taken() special cased the 0 comparison. */ if (!__is_pointer_value(false, dst_reg)) err = mark_chain_precision(env, insn->dst_reg); if (BPF_SRC(insn->code) == BPF_X && !err && !__is_pointer_value(false, src_reg)) err = mark_chain_precision(env, insn->src_reg); if (err) return err; } if (pred == 1) { /* Only follow the goto, ignore fall-through. If needed, push * the fall-through branch for simulation under speculative * execution. */ if (!env->bypass_spec_v1 && !sanitize_speculative_path(env, insn, *insn_idx + 1, *insn_idx)) return -EFAULT; if (env->log.level & BPF_LOG_LEVEL) print_insn_state(env, this_branch->frame[this_branch->curframe]); *insn_idx += insn->off; return 0; } else if (pred == 0) { /* Only follow the fall-through branch, since that's where the * program will go. If needed, push the goto branch for * simulation under speculative execution. */ if (!env->bypass_spec_v1 && !sanitize_speculative_path(env, insn, *insn_idx + insn->off + 1, *insn_idx)) return -EFAULT; if (env->log.level & BPF_LOG_LEVEL) print_insn_state(env, this_branch->frame[this_branch->curframe]); return 0; } other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx, false); if (!other_branch) return -EFAULT; other_branch_regs = other_branch->frame[other_branch->curframe]->regs; if (BPF_SRC(insn->code) == BPF_X) { err = reg_set_min_max(env, &other_branch_regs[insn->dst_reg], &other_branch_regs[insn->src_reg], dst_reg, src_reg, opcode, is_jmp32); } else /* BPF_SRC(insn->code) == BPF_K */ { /* reg_set_min_max() can mangle the fake_reg. Make a copy * so that these are two different memory locations. The * src_reg is not used beyond here in context of K. */ memcpy(&env->fake_reg[1], &env->fake_reg[0], sizeof(env->fake_reg[0])); err = reg_set_min_max(env, &other_branch_regs[insn->dst_reg], &env->fake_reg[0], dst_reg, &env->fake_reg[1], opcode, is_jmp32); } if (err) return err; if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id && !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) { find_equal_scalars(this_branch, src_reg); find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]); } if (dst_reg->type == SCALAR_VALUE && dst_reg->id && !WARN_ON_ONCE(dst_reg->id != other_branch_regs[insn->dst_reg].id)) { find_equal_scalars(this_branch, dst_reg); find_equal_scalars(other_branch, &other_branch_regs[insn->dst_reg]); } /* if one pointer register is compared to another pointer * register check if PTR_MAYBE_NULL could be lifted. * E.g. register A - maybe null * register B - not null * for JNE A, B, ... - A is not null in the false branch; * for JEQ A, B, ... - A is not null in the true branch. * * Since PTR_TO_BTF_ID points to a kernel struct that does * not need to be null checked by the BPF program, i.e., * could be null even without PTR_MAYBE_NULL marking, so * only propagate nullness when neither reg is that type. */ if (!is_jmp32 && BPF_SRC(insn->code) == BPF_X && __is_pointer_value(false, src_reg) && __is_pointer_value(false, dst_reg) && type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type) && base_type(src_reg->type) != PTR_TO_BTF_ID && base_type(dst_reg->type) != PTR_TO_BTF_ID) { eq_branch_regs = NULL; switch (opcode) { case BPF_JEQ: eq_branch_regs = other_branch_regs; break; case BPF_JNE: eq_branch_regs = regs; break; default: /* do nothing */ break; } if (eq_branch_regs) { if (type_may_be_null(src_reg->type)) mark_ptr_not_null_reg(&eq_branch_regs[insn->src_reg]); else mark_ptr_not_null_reg(&eq_branch_regs[insn->dst_reg]); } } /* detect if R == 0 where R is returned from bpf_map_lookup_elem(). * NOTE: these optimizations below are related with pointer comparison * which will never be JMP32. */ if (!is_jmp32 && BPF_SRC(insn->code) == BPF_K && insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) && type_may_be_null(dst_reg->type)) { /* Mark all identical registers in each branch as either * safe or unknown depending R == 0 or R != 0 conditional. */ mark_ptr_or_null_regs(this_branch, insn->dst_reg, opcode == BPF_JNE); mark_ptr_or_null_regs(other_branch, insn->dst_reg, opcode == BPF_JEQ); } else if (!try_match_pkt_pointers(insn, dst_reg, ®s[insn->src_reg], this_branch, other_branch) && is_pointer_value(env, insn->dst_reg)) { verbose(env, "R%d pointer comparison prohibited\n", insn->dst_reg); return -EACCES; } if (env->log.level & BPF_LOG_LEVEL) print_insn_state(env, this_branch->frame[this_branch->curframe]); return 0; } /* verify BPF_LD_IMM64 instruction */ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_insn_aux_data *aux = cur_aux(env); struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *dst_reg; struct bpf_map *map; int err; if (BPF_SIZE(insn->code) != BPF_DW) { verbose(env, "invalid BPF_LD_IMM insn\n"); return -EINVAL; } if (insn->off != 0) { verbose(env, "BPF_LD_IMM64 uses reserved fields\n"); return -EINVAL; } err = check_reg_arg(env, insn->dst_reg, DST_OP); if (err) return err; dst_reg = ®s[insn->dst_reg]; if (insn->src_reg == 0) { u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; dst_reg->type = SCALAR_VALUE; __mark_reg_known(®s[insn->dst_reg], imm); return 0; } /* All special src_reg cases are listed below. From this point onwards * we either succeed and assign a corresponding dst_reg->type after * zeroing the offset, or fail and reject the program. */ mark_reg_known_zero(env, regs, insn->dst_reg); if (insn->src_reg == BPF_PSEUDO_BTF_ID) { dst_reg->type = aux->btf_var.reg_type; switch (base_type(dst_reg->type)) { case PTR_TO_MEM: dst_reg->mem_size = aux->btf_var.mem_size; break; case PTR_TO_BTF_ID: dst_reg->btf = aux->btf_var.btf; dst_reg->btf_id = aux->btf_var.btf_id; break; default: verbose(env, "bpf verifier is misconfigured\n"); return -EFAULT; } return 0; } if (insn->src_reg == BPF_PSEUDO_FUNC) { struct bpf_prog_aux *aux = env->prog->aux; u32 subprogno = find_subprog(env, env->insn_idx + insn->imm + 1); if (!aux->func_info) { verbose(env, "missing btf func_info\n"); return -EINVAL; } if (aux->func_info_aux[subprogno].linkage != BTF_FUNC_STATIC) { verbose(env, "callback function not static\n"); return -EINVAL; } dst_reg->type = PTR_TO_FUNC; dst_reg->subprogno = subprogno; return 0; } map = env->used_maps[aux->map_index]; dst_reg->map_ptr = map; if (insn->src_reg == BPF_PSEUDO_MAP_VALUE || insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) { if (map->map_type == BPF_MAP_TYPE_ARENA) { __mark_reg_unknown(env, dst_reg); return 0; } dst_reg->type = PTR_TO_MAP_VALUE; dst_reg->off = aux->map_off; WARN_ON_ONCE(map->max_entries != 1); /* We want reg->id to be same (0) as map_value is not distinct */ } else if (insn->src_reg == BPF_PSEUDO_MAP_FD || insn->src_reg == BPF_PSEUDO_MAP_IDX) { dst_reg->type = CONST_PTR_TO_MAP; } else { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } return 0; } static bool may_access_skb(enum bpf_prog_type type) { switch (type) { case BPF_PROG_TYPE_SOCKET_FILTER: case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: return true; default: return false; } } /* verify safety of LD_ABS|LD_IND instructions: * - they can only appear in the programs where ctx == skb * - since they are wrappers of function calls, they scratch R1-R5 registers, * preserve R6-R9, and store return value into R0 * * Implicit input: * ctx == skb == R6 == CTX * * Explicit input: * SRC == any register * IMM == 32-bit immediate * * Output: * R0 - 8/16/32-bit skb data converted to cpu endianness */ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = cur_regs(env); static const int ctx_reg = BPF_REG_6; u8 mode = BPF_MODE(insn->code); int i, err; if (!may_access_skb(resolve_prog_type(env->prog))) { verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n"); return -EINVAL; } if (!env->ops->gen_ld_abs) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } if (insn->dst_reg != BPF_REG_0 || insn->off != 0 || BPF_SIZE(insn->code) == BPF_DW || (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) { verbose(env, "BPF_LD_[ABS|IND] uses reserved fields\n"); return -EINVAL; } /* check whether implicit source operand (register R6) is readable */ err = check_reg_arg(env, ctx_reg, SRC_OP); if (err) return err; /* Disallow usage of BPF_LD_[ABS|IND] with reference tracking, as * gen_ld_abs() may terminate the program at runtime, leading to * reference leak. */ err = check_reference_leak(env, false); if (err) { verbose(env, "BPF_LD_[ABS|IND] cannot be mixed with socket references\n"); return err; } if (env->cur_state->active_lock.ptr) { verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_spin_lock-ed region\n"); return -EINVAL; } if (env->cur_state->active_rcu_lock) { verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_rcu_read_lock-ed region\n"); return -EINVAL; } if (env->cur_state->active_preempt_lock) { verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_preempt_disable-ed region\n"); return -EINVAL; } if (regs[ctx_reg].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); return -EINVAL; } if (mode == BPF_IND) { /* check explicit source operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; } err = check_ptr_off_reg(env, ®s[ctx_reg], ctx_reg); if (err < 0) return err; /* reset caller saved regs to unreadable */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } /* mark destination R0 register as readable, since it contains * the value fetched from the packet. * Already marked as written above. */ mark_reg_unknown(env, regs, BPF_REG_0); /* ld_abs load up to 32-bit skb data. */ regs[BPF_REG_0].subreg_def = env->insn_idx + 1; return 0; } static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name) { const char *exit_ctx = "At program exit"; struct tnum enforce_attach_type_range = tnum_unknown; const struct bpf_prog *prog = env->prog; struct bpf_reg_state *reg; struct bpf_retval_range range = retval_range(0, 1); enum bpf_prog_type prog_type = resolve_prog_type(env->prog); int err; struct bpf_func_state *frame = env->cur_state->frame[0]; const bool is_subprog = frame->subprogno; /* LSM and struct_ops func-ptr's return type could be "void" */ if (!is_subprog || frame->in_exception_callback_fn) { switch (prog_type) { case BPF_PROG_TYPE_LSM: if (prog->expected_attach_type == BPF_LSM_CGROUP) /* See below, can be 0 or 0-1 depending on hook. */ break; fallthrough; case BPF_PROG_TYPE_STRUCT_OPS: if (!prog->aux->attach_func_proto->type) return 0; break; default: break; } } /* eBPF calling convention is such that R0 is used * to return the value from eBPF program. * Make sure that it's readable at this time * of bpf_exit, which means that program wrote * something into it earlier */ err = check_reg_arg(env, regno, SRC_OP); if (err) return err; if (is_pointer_value(env, regno)) { verbose(env, "R%d leaks addr as return value\n", regno); return -EACCES; } reg = cur_regs(env) + regno; if (frame->in_async_callback_fn) { /* enforce return zero from async callbacks like timer */ exit_ctx = "At async callback return"; range = retval_range(0, 0); goto enforce_retval; } if (is_subprog && !frame->in_exception_callback_fn) { if (reg->type != SCALAR_VALUE) { verbose(env, "At subprogram exit the register R%d is not a scalar value (%s)\n", regno, reg_type_str(env, reg->type)); return -EINVAL; } return 0; } switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_UNIX_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME || env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME || env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETPEERNAME || env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME || env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME || env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETSOCKNAME) range = retval_range(1, 1); if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND || env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND) range = retval_range(0, 3); break; case BPF_PROG_TYPE_CGROUP_SKB: if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) { range = retval_range(0, 3); enforce_attach_type_range = tnum_range(2, 3); } break; case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_CGROUP_SOCKOPT: break; case BPF_PROG_TYPE_RAW_TRACEPOINT: if (!env->prog->aux->attach_btf_id) return 0; range = retval_range(0, 0); break; case BPF_PROG_TYPE_TRACING: switch (env->prog->expected_attach_type) { case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: range = retval_range(0, 0); break; case BPF_TRACE_RAW_TP: case BPF_MODIFY_RETURN: return 0; case BPF_TRACE_ITER: break; default: return -ENOTSUPP; } break; case BPF_PROG_TYPE_SK_LOOKUP: range = retval_range(SK_DROP, SK_PASS); break; case BPF_PROG_TYPE_LSM: if (env->prog->expected_attach_type != BPF_LSM_CGROUP) { /* Regular BPF_PROG_TYPE_LSM programs can return * any value. */ return 0; } if (!env->prog->aux->attach_func_proto->type) { /* Make sure programs that attach to void * hooks don't try to modify return value. */ range = retval_range(1, 1); } break; case BPF_PROG_TYPE_NETFILTER: range = retval_range(NF_DROP, NF_ACCEPT); break; case BPF_PROG_TYPE_EXT: /* freplace program can return anything as its return value * depends on the to-be-replaced kernel func or bpf program. */ default: return 0; } enforce_retval: if (reg->type != SCALAR_VALUE) { verbose(env, "%s the register R%d is not a known value (%s)\n", exit_ctx, regno, reg_type_str(env, reg->type)); return -EINVAL; } err = mark_chain_precision(env, regno); if (err) return err; if (!retval_range_within(range, reg)) { verbose_invalid_scalar(env, reg, range, exit_ctx, reg_name); if (!is_subprog && prog->expected_attach_type == BPF_LSM_CGROUP && prog_type == BPF_PROG_TYPE_LSM && !prog->aux->attach_func_proto->type) verbose(env, "Note, BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n"); return -EINVAL; } if (!tnum_is_unknown(enforce_attach_type_range) && tnum_in(enforce_attach_type_range, reg->var_off)) env->prog->enforce_expected_attach_type = 1; return 0; } /* non-recursive DFS pseudo code * 1 procedure DFS-iterative(G,v): * 2 label v as discovered * 3 let S be a stack * 4 S.push(v) * 5 while S is not empty * 6 t <- S.peek() * 7 if t is what we're looking for: * 8 return t * 9 for all edges e in G.adjacentEdges(t) do * 10 if edge e is already labelled * 11 continue with the next edge * 12 w <- G.adjacentVertex(t,e) * 13 if vertex w is not discovered and not explored * 14 label e as tree-edge * 15 label w as discovered * 16 S.push(w) * 17 continue at 5 * 18 else if vertex w is discovered * 19 label e as back-edge * 20 else * 21 // vertex w is explored * 22 label e as forward- or cross-edge * 23 label t as explored * 24 S.pop() * * convention: * 0x10 - discovered * 0x11 - discovered and fall-through edge labelled * 0x12 - discovered and fall-through and branch edges labelled * 0x20 - explored */ enum { DISCOVERED = 0x10, EXPLORED = 0x20, FALLTHROUGH = 1, BRANCH = 2, }; static void mark_prune_point(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].prune_point = true; } static bool is_prune_point(struct bpf_verifier_env *env, int insn_idx) { return env->insn_aux_data[insn_idx].prune_point; } static void mark_force_checkpoint(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].force_checkpoint = true; } static bool is_force_checkpoint(struct bpf_verifier_env *env, int insn_idx) { return env->insn_aux_data[insn_idx].force_checkpoint; } static void mark_calls_callback(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].calls_callback = true; } static bool calls_callback(struct bpf_verifier_env *env, int insn_idx) { return env->insn_aux_data[insn_idx].calls_callback; } enum { DONE_EXPLORING = 0, KEEP_EXPLORING = 1, }; /* t, w, e - match pseudo-code above: * t - index of current instruction * w - next instruction * e - edge */ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) { int *insn_stack = env->cfg.insn_stack; int *insn_state = env->cfg.insn_state; if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH)) return DONE_EXPLORING; if (e == BRANCH && insn_state[t] >= (DISCOVERED | BRANCH)) return DONE_EXPLORING; if (w < 0 || w >= env->prog->len) { verbose_linfo(env, t, "%d: ", t); verbose(env, "jump out of range from insn %d to %d\n", t, w); return -EINVAL; } if (e == BRANCH) { /* mark branch target for state pruning */ mark_prune_point(env, w); mark_jmp_point(env, w); } if (insn_state[w] == 0) { /* tree-edge */ insn_state[t] = DISCOVERED | e; insn_state[w] = DISCOVERED; if (env->cfg.cur_stack >= env->prog->len) return -E2BIG; insn_stack[env->cfg.cur_stack++] = w; return KEEP_EXPLORING; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { if (env->bpf_capable) return DONE_EXPLORING; verbose_linfo(env, t, "%d: ", t); verbose_linfo(env, w, "%d: ", w); verbose(env, "back-edge from insn %d to %d\n", t, w); return -EINVAL; } else if (insn_state[w] == EXPLORED) { /* forward- or cross-edge */ insn_state[t] = DISCOVERED | e; } else { verbose(env, "insn state internal bug\n"); return -EFAULT; } return DONE_EXPLORING; } static int visit_func_call_insn(int t, struct bpf_insn *insns, struct bpf_verifier_env *env, bool visit_callee) { int ret, insn_sz; insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1; ret = push_insn(t, t + insn_sz, FALLTHROUGH, env); if (ret) return ret; mark_prune_point(env, t + insn_sz); /* when we exit from subprog, we need to record non-linear history */ mark_jmp_point(env, t + insn_sz); if (visit_callee) { mark_prune_point(env, t); ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env); } return ret; } /* Visits the instruction at index t and returns one of the following: * < 0 - an error occurred * DONE_EXPLORING - the instruction was fully explored * KEEP_EXPLORING - there is still work to be done before it is fully explored */ static int visit_insn(int t, struct bpf_verifier_env *env) { struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t]; int ret, off, insn_sz; if (bpf_pseudo_func(insn)) return visit_func_call_insn(t, insns, env, true); /* All non-branch instructions have a single fall-through edge. */ if (BPF_CLASS(insn->code) != BPF_JMP && BPF_CLASS(insn->code) != BPF_JMP32) { insn_sz = bpf_is_ldimm64(insn) ? 2 : 1; return push_insn(t, t + insn_sz, FALLTHROUGH, env); } switch (BPF_OP(insn->code)) { case BPF_EXIT: return DONE_EXPLORING; case BPF_CALL: if (is_async_callback_calling_insn(insn)) /* Mark this call insn as a prune point to trigger * is_state_visited() check before call itself is * processed by __check_func_call(). Otherwise new * async state will be pushed for further exploration. */ mark_prune_point(env, t); /* For functions that invoke callbacks it is not known how many times * callback would be called. Verifier models callback calling functions * by repeatedly visiting callback bodies and returning to origin call * instruction. * In order to stop such iteration verifier needs to identify when a * state identical some state from a previous iteration is reached. * Check below forces creation of checkpoint before callback calling * instruction to allow search for such identical states. */ if (is_sync_callback_calling_insn(insn)) { mark_calls_callback(env, t); mark_force_checkpoint(env, t); mark_prune_point(env, t); mark_jmp_point(env, t); } if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { struct bpf_kfunc_call_arg_meta meta; ret = fetch_kfunc_meta(env, insn, &meta, NULL); if (ret == 0 && is_iter_next_kfunc(&meta)) { mark_prune_point(env, t); /* Checking and saving state checkpoints at iter_next() call * is crucial for fast convergence of open-coded iterator loop * logic, so we need to force it. If we don't do that, * is_state_visited() might skip saving a checkpoint, causing * unnecessarily long sequence of not checkpointed * instructions and jumps, leading to exhaustion of jump * history buffer, and potentially other undesired outcomes. * It is expected that with correct open-coded iterators * convergence will happen quickly, so we don't run a risk of * exhausting memory. */ mark_force_checkpoint(env, t); } } return visit_func_call_insn(t, insns, env, insn->src_reg == BPF_PSEUDO_CALL); case BPF_JA: if (BPF_SRC(insn->code) != BPF_K) return -EINVAL; if (BPF_CLASS(insn->code) == BPF_JMP) off = insn->off; else off = insn->imm; /* unconditional jump with single edge */ ret = push_insn(t, t + off + 1, FALLTHROUGH, env); if (ret) return ret; mark_prune_point(env, t + off + 1); mark_jmp_point(env, t + off + 1); return ret; default: /* conditional jump with two edges */ mark_prune_point(env, t); if (is_may_goto_insn(insn)) mark_force_checkpoint(env, t); ret = push_insn(t, t + 1, FALLTHROUGH, env); if (ret) return ret; return push_insn(t, t + insn->off + 1, BRANCH, env); } } /* non-recursive depth-first-search to detect loops in BPF program * loop == back-edge in directed graph */ static int check_cfg(struct bpf_verifier_env *env) { int insn_cnt = env->prog->len; int *insn_stack, *insn_state; int ex_insn_beg, i, ret = 0; bool ex_done = false; insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_state) return -ENOMEM; insn_stack = env->cfg.insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_stack) { kvfree(insn_state); return -ENOMEM; } insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */ insn_stack[0] = 0; /* 0 is the first instruction */ env->cfg.cur_stack = 1; walk_cfg: while (env->cfg.cur_stack > 0) { int t = insn_stack[env->cfg.cur_stack - 1]; ret = visit_insn(t, env); switch (ret) { case DONE_EXPLORING: insn_state[t] = EXPLORED; env->cfg.cur_stack--; break; case KEEP_EXPLORING: break; default: if (ret > 0) { verbose(env, "visit_insn internal bug\n"); ret = -EFAULT; } goto err_free; } } if (env->cfg.cur_stack < 0) { verbose(env, "pop stack internal bug\n"); ret = -EFAULT; goto err_free; } if (env->exception_callback_subprog && !ex_done) { ex_insn_beg = env->subprog_info[env->exception_callback_subprog].start; insn_state[ex_insn_beg] = DISCOVERED; insn_stack[0] = ex_insn_beg; env->cfg.cur_stack = 1; ex_done = true; goto walk_cfg; } for (i = 0; i < insn_cnt; i++) { struct bpf_insn *insn = &env->prog->insnsi[i]; if (insn_state[i] != EXPLORED) { verbose(env, "unreachable insn %d\n", i); ret = -EINVAL; goto err_free; } if (bpf_is_ldimm64(insn)) { if (insn_state[i + 1] != 0) { verbose(env, "jump into the middle of ldimm64 insn %d\n", i); ret = -EINVAL; goto err_free; } i++; /* skip second half of ldimm64 */ } } ret = 0; /* cfg looks good */ err_free: kvfree(insn_state); kvfree(insn_stack); env->cfg.insn_state = env->cfg.insn_stack = NULL; return ret; } static int check_abnormal_return(struct bpf_verifier_env *env) { int i; for (i = 1; i < env->subprog_cnt; i++) { if (env->subprog_info[i].has_ld_abs) { verbose(env, "LD_ABS is not allowed in subprogs without BTF\n"); return -EINVAL; } if (env->subprog_info[i].has_tail_call) { verbose(env, "tail_call is not allowed in subprogs without BTF\n"); return -EINVAL; } } return 0; } /* The minimum supported BTF func info size */ #define MIN_BPF_FUNCINFO_SIZE 8 #define MAX_FUNCINFO_REC_SIZE 252 static int check_btf_func_early(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) { u32 krec_size = sizeof(struct bpf_func_info); const struct btf_type *type, *func_proto; u32 i, nfuncs, urec_size, min_size; struct bpf_func_info *krecord; struct bpf_prog *prog; const struct btf *btf; u32 prev_offset = 0; bpfptr_t urecord; int ret = -ENOMEM; nfuncs = attr->func_info_cnt; if (!nfuncs) { if (check_abnormal_return(env)) return -EINVAL; return 0; } urec_size = attr->func_info_rec_size; if (urec_size < MIN_BPF_FUNCINFO_SIZE || urec_size > MAX_FUNCINFO_REC_SIZE || urec_size % sizeof(u32)) { verbose(env, "invalid func info rec size %u\n", urec_size); return -EINVAL; } prog = env->prog; btf = prog->aux->btf; urecord = make_bpfptr(attr->func_info, uattr.is_kernel); min_size = min_t(u32, krec_size, urec_size); krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN); if (!krecord) return -ENOMEM; for (i = 0; i < nfuncs; i++) { ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size); if (ret) { if (ret == -E2BIG) { verbose(env, "nonzero tailing record in func info"); /* set the size kernel expects so loader can zero * out the rest of the record. */ if (copy_to_bpfptr_offset(uattr, offsetof(union bpf_attr, func_info_rec_size), &min_size, sizeof(min_size))) ret = -EFAULT; } goto err_free; } if (copy_from_bpfptr(&krecord[i], urecord, min_size)) { ret = -EFAULT; goto err_free; } /* check insn_off */ ret = -EINVAL; if (i == 0) { if (krecord[i].insn_off) { verbose(env, "nonzero insn_off %u for the first func info record", krecord[i].insn_off); goto err_free; } } else if (krecord[i].insn_off <= prev_offset) { verbose(env, "same or smaller insn offset (%u) than previous func info record (%u)", krecord[i].insn_off, prev_offset); goto err_free; } /* check type_id */ type = btf_type_by_id(btf, krecord[i].type_id); if (!type || !btf_type_is_func(type)) { verbose(env, "invalid type id %d in func info", krecord[i].type_id); goto err_free; } func_proto = btf_type_by_id(btf, type->type); if (unlikely(!func_proto || !btf_type_is_func_proto(func_proto))) /* btf_func_check() already verified it during BTF load */ goto err_free; prev_offset = krecord[i].insn_off; bpfptr_add(&urecord, urec_size); } prog->aux->func_info = krecord; prog->aux->func_info_cnt = nfuncs; return 0; err_free: kvfree(krecord); return ret; } static int check_btf_func(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) { const struct btf_type *type, *func_proto, *ret_type; u32 i, nfuncs, urec_size; struct bpf_func_info *krecord; struct bpf_func_info_aux *info_aux = NULL; struct bpf_prog *prog; const struct btf *btf; bpfptr_t urecord; bool scalar_return; int ret = -ENOMEM; nfuncs = attr->func_info_cnt; if (!nfuncs) { if (check_abnormal_return(env)) return -EINVAL; return 0; } if (nfuncs != env->subprog_cnt) { verbose(env, "number of funcs in func_info doesn't match number of subprogs\n"); return -EINVAL; } urec_size = attr->func_info_rec_size; prog = env->prog; btf = prog->aux->btf; urecord = make_bpfptr(attr->func_info, uattr.is_kernel); krecord = prog->aux->func_info; info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN); if (!info_aux) return -ENOMEM; for (i = 0; i < nfuncs; i++) { /* check insn_off */ ret = -EINVAL; if (env->subprog_info[i].start != krecord[i].insn_off) { verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n"); goto err_free; } /* Already checked type_id */ type = btf_type_by_id(btf, krecord[i].type_id); info_aux[i].linkage = BTF_INFO_VLEN(type->info); /* Already checked func_proto */ func_proto = btf_type_by_id(btf, type->type); ret_type = btf_type_skip_modifiers(btf, func_proto->type, NULL); scalar_return = btf_type_is_small_int(ret_type) || btf_is_any_enum(ret_type); if (i && !scalar_return && env->subprog_info[i].has_ld_abs) { verbose(env, "LD_ABS is only allowed in functions that return 'int'.\n"); goto err_free; } if (i && !scalar_return && env->subprog_info[i].has_tail_call) { verbose(env, "tail_call is only allowed in functions that return 'int'.\n"); goto err_free; } bpfptr_add(&urecord, urec_size); } prog->aux->func_info_aux = info_aux; return 0; err_free: kfree(info_aux); return ret; } static void adjust_btf_func(struct bpf_verifier_env *env) { struct bpf_prog_aux *aux = env->prog->aux; int i; if (!aux->func_info) return; /* func_info is not available for hidden subprogs */ for (i = 0; i < env->subprog_cnt - env->hidden_subprog_cnt; i++) aux->func_info[i].insn_off = env->subprog_info[i].start; } #define MIN_BPF_LINEINFO_SIZE offsetofend(struct bpf_line_info, line_col) #define MAX_LINEINFO_REC_SIZE MAX_FUNCINFO_REC_SIZE static int check_btf_line(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) { u32 i, s, nr_linfo, ncopy, expected_size, rec_size, prev_offset = 0; struct bpf_subprog_info *sub; struct bpf_line_info *linfo; struct bpf_prog *prog; const struct btf *btf; bpfptr_t ulinfo; int err; nr_linfo = attr->line_info_cnt; if (!nr_linfo) return 0; if (nr_linfo > INT_MAX / sizeof(struct bpf_line_info)) return -EINVAL; rec_size = attr->line_info_rec_size; if (rec_size < MIN_BPF_LINEINFO_SIZE || rec_size > MAX_LINEINFO_REC_SIZE || rec_size & (sizeof(u32) - 1)) return -EINVAL; /* Need to zero it in case the userspace may * pass in a smaller bpf_line_info object. */ linfo = kvcalloc(nr_linfo, sizeof(struct bpf_line_info), GFP_KERNEL | __GFP_NOWARN); if (!linfo) return -ENOMEM; prog = env->prog; btf = prog->aux->btf; s = 0; sub = env->subprog_info; ulinfo = make_bpfptr(attr->line_info, uattr.is_kernel); expected_size = sizeof(struct bpf_line_info); ncopy = min_t(u32, expected_size, rec_size); for (i = 0; i < nr_linfo; i++) { err = bpf_check_uarg_tail_zero(ulinfo, expected_size, rec_size); if (err) { if (err == -E2BIG) { verbose(env, "nonzero tailing record in line_info"); if (copy_to_bpfptr_offset(uattr, offsetof(union bpf_attr, line_info_rec_size), &expected_size, sizeof(expected_size))) err = -EFAULT; } goto err_free; } if (copy_from_bpfptr(&linfo[i], ulinfo, ncopy)) { err = -EFAULT; goto err_free; } /* * Check insn_off to ensure * 1) strictly increasing AND * 2) bounded by prog->len * * The linfo[0].insn_off == 0 check logically falls into * the later "missing bpf_line_info for func..." case * because the first linfo[0].insn_off must be the * first sub also and the first sub must have * subprog_info[0].start == 0. */ if ((i && linfo[i].insn_off <= prev_offset) || linfo[i].insn_off >= prog->len) { verbose(env, "Invalid line_info[%u].insn_off:%u (prev_offset:%u prog->len:%u)\n", i, linfo[i].insn_off, prev_offset, prog->len); err = -EINVAL; goto err_free; } if (!prog->insnsi[linfo[i].insn_off].code) { verbose(env, "Invalid insn code at line_info[%u].insn_off\n", i); err = -EINVAL; goto err_free; } if (!btf_name_by_offset(btf, linfo[i].line_off) || !btf_name_by_offset(btf, linfo[i].file_name_off)) { verbose(env, "Invalid line_info[%u].line_off or .file_name_off\n", i); err = -EINVAL; goto err_free; } if (s != env->subprog_cnt) { if (linfo[i].insn_off == sub[s].start) { sub[s].linfo_idx = i; s++; } else if (sub[s].start < linfo[i].insn_off) { verbose(env, "missing bpf_line_info for func#%u\n", s); err = -EINVAL; goto err_free; } } prev_offset = linfo[i].insn_off; bpfptr_add(&ulinfo, rec_size); } if (s != env->subprog_cnt) { verbose(env, "missing bpf_line_info for %u funcs starting from func#%u\n", env->subprog_cnt - s, s); err = -EINVAL; goto err_free; } prog->aux->linfo = linfo; prog->aux->nr_linfo = nr_linfo; return 0; err_free: kvfree(linfo); return err; } #define MIN_CORE_RELO_SIZE sizeof(struct bpf_core_relo) #define MAX_CORE_RELO_SIZE MAX_FUNCINFO_REC_SIZE static int check_core_relo(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) { u32 i, nr_core_relo, ncopy, expected_size, rec_size; struct bpf_core_relo core_relo = {}; struct bpf_prog *prog = env->prog; const struct btf *btf = prog->aux->btf; struct bpf_core_ctx ctx = { .log = &env->log, .btf = btf, }; bpfptr_t u_core_relo; int err; nr_core_relo = attr->core_relo_cnt; if (!nr_core_relo) return 0; if (nr_core_relo > INT_MAX / sizeof(struct bpf_core_relo)) return -EINVAL; rec_size = attr->core_relo_rec_size; if (rec_size < MIN_CORE_RELO_SIZE || rec_size > MAX_CORE_RELO_SIZE || rec_size % sizeof(u32)) return -EINVAL; u_core_relo = make_bpfptr(attr->core_relos, uattr.is_kernel); expected_size = sizeof(struct bpf_core_relo); ncopy = min_t(u32, expected_size, rec_size); /* Unlike func_info and line_info, copy and apply each CO-RE * relocation record one at a time. */ for (i = 0; i < nr_core_relo; i++) { /* future proofing when sizeof(bpf_core_relo) changes */ err = bpf_check_uarg_tail_zero(u_core_relo, expected_size, rec_size); if (err) { if (err == -E2BIG) { verbose(env, "nonzero tailing record in core_relo"); if (copy_to_bpfptr_offset(uattr, offsetof(union bpf_attr, core_relo_rec_size), &expected_size, sizeof(expected_size))) err = -EFAULT; } break; } if (copy_from_bpfptr(&core_relo, u_core_relo, ncopy)) { err = -EFAULT; break; } if (core_relo.insn_off % 8 || core_relo.insn_off / 8 >= prog->len) { verbose(env, "Invalid core_relo[%u].insn_off:%u prog->len:%u\n", i, core_relo.insn_off, prog->len); err = -EINVAL; break; } err = bpf_core_apply(&ctx, &core_relo, i, &prog->insnsi[core_relo.insn_off / 8]); if (err) break; bpfptr_add(&u_core_relo, rec_size); } return err; } static int check_btf_info_early(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) { struct btf *btf; int err; if (!attr->func_info_cnt && !attr->line_info_cnt) { if (check_abnormal_return(env)) return -EINVAL; return 0; } btf = btf_get_by_fd(attr->prog_btf_fd); if (IS_ERR(btf)) return PTR_ERR(btf); if (btf_is_kernel(btf)) { btf_put(btf); return -EACCES; } env->prog->aux->btf = btf; err = check_btf_func_early(env, attr, uattr); if (err) return err; return 0; } static int check_btf_info(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) { int err; if (!attr->func_info_cnt && !attr->line_info_cnt) { if (check_abnormal_return(env)) return -EINVAL; return 0; } err = check_btf_func(env, attr, uattr); if (err) return err; err = check_btf_line(env, attr, uattr); if (err) return err; err = check_core_relo(env, attr, uattr); if (err) return err; return 0; } /* check %cur's range satisfies %old's */ static bool range_within(const struct bpf_reg_state *old, const struct bpf_reg_state *cur) { return old->umin_value <= cur->umin_value && old->umax_value >= cur->umax_value && old->smin_value <= cur->smin_value && old->smax_value >= cur->smax_value && old->u32_min_value <= cur->u32_min_value && old->u32_max_value >= cur->u32_max_value && old->s32_min_value <= cur->s32_min_value && old->s32_max_value >= cur->s32_max_value; } /* If in the old state two registers had the same id, then they need to have * the same id in the new state as well. But that id could be different from * the old state, so we need to track the mapping from old to new ids. * Once we have seen that, say, a reg with old id 5 had new id 9, any subsequent * regs with old id 5 must also have new id 9 for the new state to be safe. But * regs with a different old id could still have new id 9, we don't care about * that. * So we look through our idmap to see if this old id has been seen before. If * so, we require the new id to match; otherwise, we add the id pair to the map. */ static bool check_ids(u32 old_id, u32 cur_id, struct bpf_idmap *idmap) { struct bpf_id_pair *map = idmap->map; unsigned int i; /* either both IDs should be set or both should be zero */ if (!!old_id != !!cur_id) return false; if (old_id == 0) /* cur_id == 0 as well */ return true; for (i = 0; i < BPF_ID_MAP_SIZE; i++) { if (!map[i].old) { /* Reached an empty slot; haven't seen this id before */ map[i].old = old_id; map[i].cur = cur_id; return true; } if (map[i].old == old_id) return map[i].cur == cur_id; if (map[i].cur == cur_id) return false; } /* We ran out of idmap slots, which should be impossible */ WARN_ON_ONCE(1); return false; } /* Similar to check_ids(), but allocate a unique temporary ID * for 'old_id' or 'cur_id' of zero. * This makes pairs like '0 vs unique ID', 'unique ID vs 0' valid. */ static bool check_scalar_ids(u32 old_id, u32 cur_id, struct bpf_idmap *idmap) { old_id = old_id ? old_id : ++idmap->tmp_id_gen; cur_id = cur_id ? cur_id : ++idmap->tmp_id_gen; return check_ids(old_id, cur_id, idmap); } static void clean_func_state(struct bpf_verifier_env *env, struct bpf_func_state *st) { enum bpf_reg_liveness live; int i, j; for (i = 0; i < BPF_REG_FP; i++) { live = st->regs[i].live; /* liveness must not touch this register anymore */ st->regs[i].live |= REG_LIVE_DONE; if (!(live & REG_LIVE_READ)) /* since the register is unused, clear its state * to make further comparison simpler */ __mark_reg_not_init(env, &st->regs[i]); } for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) { live = st->stack[i].spilled_ptr.live; /* liveness must not touch this stack slot anymore */ st->stack[i].spilled_ptr.live |= REG_LIVE_DONE; if (!(live & REG_LIVE_READ)) { __mark_reg_not_init(env, &st->stack[i].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) st->stack[i].slot_type[j] = STACK_INVALID; } } } static void clean_verifier_state(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { int i; if (st->frame[0]->regs[0].live & REG_LIVE_DONE) /* all regs in this state in all frames were already marked */ return; for (i = 0; i <= st->curframe; i++) clean_func_state(env, st->frame[i]); } /* the parentage chains form a tree. * the verifier states are added to state lists at given insn and * pushed into state stack for future exploration. * when the verifier reaches bpf_exit insn some of the verifer states * stored in the state lists have their final liveness state already, * but a lot of states will get revised from liveness point of view when * the verifier explores other branches. * Example: * 1: r0 = 1 * 2: if r1 == 100 goto pc+1 * 3: r0 = 2 * 4: exit * when the verifier reaches exit insn the register r0 in the state list of * insn 2 will be seen as !REG_LIVE_READ. Then the verifier pops the other_branch * of insn 2 and goes exploring further. At the insn 4 it will walk the * parentage chain from insn 4 into insn 2 and will mark r0 as REG_LIVE_READ. * * Since the verifier pushes the branch states as it sees them while exploring * the program the condition of walking the branch instruction for the second * time means that all states below this branch were already explored and * their final liveness marks are already propagated. * Hence when the verifier completes the search of state list in is_state_visited() * we can call this clean_live_states() function to mark all liveness states * as REG_LIVE_DONE to indicate that 'parent' pointers of 'struct bpf_reg_state' * will not be used. * This function also clears the registers and stack for states that !READ * to simplify state merging. * * Important note here that walking the same branch instruction in the callee * doesn't meant that the states are DONE. The verifier has to compare * the callsites */ static void clean_live_states(struct bpf_verifier_env *env, int insn, struct bpf_verifier_state *cur) { struct bpf_verifier_state_list *sl; sl = *explored_state(env, insn); while (sl) { if (sl->state.branches) goto next; if (sl->state.insn_idx != insn || !same_callsites(&sl->state, cur)) goto next; clean_verifier_state(env, &sl->state); next: sl = sl->next; } } static bool regs_exact(const struct bpf_reg_state *rold, const struct bpf_reg_state *rcur, struct bpf_idmap *idmap) { return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && check_ids(rold->id, rcur->id, idmap) && check_ids(rold->ref_obj_id, rcur->ref_obj_id, idmap); } enum exact_level { NOT_EXACT, EXACT, RANGE_WITHIN }; /* Returns true if (rold safe implies rcur safe) */ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, struct bpf_reg_state *rcur, struct bpf_idmap *idmap, enum exact_level exact) { if (exact == EXACT) return regs_exact(rold, rcur, idmap); if (!(rold->live & REG_LIVE_READ) && exact == NOT_EXACT) /* explored state didn't use this */ return true; if (rold->type == NOT_INIT) { if (exact == NOT_EXACT || rcur->type == NOT_INIT) /* explored state can't have used this */ return true; } /* Enforce that register types have to match exactly, including their * modifiers (like PTR_MAYBE_NULL, MEM_RDONLY, etc), as a general * rule. * * One can make a point that using a pointer register as unbounded * SCALAR would be technically acceptable, but this could lead to * pointer leaks because scalars are allowed to leak while pointers * are not. We could make this safe in special cases if root is * calling us, but it's probably not worth the hassle. * * Also, register types that are *not* MAYBE_NULL could technically be * safe to use as their MAYBE_NULL variants (e.g., PTR_TO_MAP_VALUE * is safe to be used as PTR_TO_MAP_VALUE_OR_NULL, provided both point * to the same map). * However, if the old MAYBE_NULL register then got NULL checked, * doing so could have affected others with the same id, and we can't * check for that because we lost the id when we converted to * a non-MAYBE_NULL variant. * So, as a general rule we don't allow mixing MAYBE_NULL and * non-MAYBE_NULL registers as well. */ if (rold->type != rcur->type) return false; switch (base_type(rold->type)) { case SCALAR_VALUE: if (env->explore_alu_limits) { /* explore_alu_limits disables tnum_in() and range_within() * logic and requires everything to be strict */ return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && check_scalar_ids(rold->id, rcur->id, idmap); } if (!rold->precise && exact == NOT_EXACT) return true; /* Why check_ids() for scalar registers? * * Consider the following BPF code: * 1: r6 = ... unbound scalar, ID=a ... * 2: r7 = ... unbound scalar, ID=b ... * 3: if (r6 > r7) goto +1 * 4: r6 = r7 * 5: if (r6 > X) goto ... * 6: ... memory operation using r7 ... * * First verification path is [1-6]: * - at (4) same bpf_reg_state::id (b) would be assigned to r6 and r7; * - at (5) r6 would be marked <= X, find_equal_scalars() would also mark * r7 <= X, because r6 and r7 share same id. * Next verification path is [1-4, 6]. * * Instruction (6) would be reached in two states: * I. r6{.id=b}, r7{.id=b} via path 1-6; * II. r6{.id=a}, r7{.id=b} via path 1-4, 6. * * Use check_ids() to distinguish these states. * --- * Also verify that new value satisfies old value range knowledge. */ return range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off) && check_scalar_ids(rold->id, rcur->id, idmap); case PTR_TO_MAP_KEY: case PTR_TO_MAP_VALUE: case PTR_TO_MEM: case PTR_TO_BUF: case PTR_TO_TP_BUFFER: /* If the new min/max/var_off satisfy the old ones and * everything else matches, we are OK. */ return memcmp(rold, rcur, offsetof(struct bpf_reg_state, var_off)) == 0 && range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off) && check_ids(rold->id, rcur->id, idmap) && check_ids(rold->ref_obj_id, rcur->ref_obj_id, idmap); case PTR_TO_PACKET_META: case PTR_TO_PACKET: /* We must have at least as much range as the old ptr * did, so that any accesses which were safe before are * still safe. This is true even if old range < old off, * since someone could have accessed through (ptr - k), or * even done ptr -= k in a register, to get a safe access. */ if (rold->range > rcur->range) return false; /* If the offsets don't match, we can't trust our alignment; * nor can we be sure that we won't fall out of range. */ if (rold->off != rcur->off) return false; /* id relations must be preserved */ if (!check_ids(rold->id, rcur->id, idmap)) return false; /* new val must satisfy old val knowledge */ return range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); case PTR_TO_STACK: /* two stack pointers are equal only if they're pointing to * the same stack frame, since fp-8 in foo != fp-8 in bar */ return regs_exact(rold, rcur, idmap) && rold->frameno == rcur->frameno; case PTR_TO_ARENA: return true; default: return regs_exact(rold, rcur, idmap); } } static struct bpf_reg_state unbound_reg; static __init int unbound_reg_init(void) { __mark_reg_unknown_imprecise(&unbound_reg); unbound_reg.live |= REG_LIVE_READ; return 0; } late_initcall(unbound_reg_init); static bool is_stack_all_misc(struct bpf_verifier_env *env, struct bpf_stack_state *stack) { u32 i; for (i = 0; i < ARRAY_SIZE(stack->slot_type); ++i) { if ((stack->slot_type[i] == STACK_MISC) || (stack->slot_type[i] == STACK_INVALID && env->allow_uninit_stack)) continue; return false; } return true; } static struct bpf_reg_state *scalar_reg_for_stack(struct bpf_verifier_env *env, struct bpf_stack_state *stack) { if (is_spilled_scalar_reg64(stack)) return &stack->spilled_ptr; if (is_stack_all_misc(env, stack)) return &unbound_reg; return NULL; } static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, struct bpf_func_state *cur, struct bpf_idmap *idmap, enum exact_level exact) { int i, spi; /* walk slots of the explored stack and ignore any additional * slots in the current stack, since explored(safe) state * didn't use them */ for (i = 0; i < old->allocated_stack; i++) { struct bpf_reg_state *old_reg, *cur_reg; spi = i / BPF_REG_SIZE; if (exact != NOT_EXACT && old->stack[spi].slot_type[i % BPF_REG_SIZE] != cur->stack[spi].slot_type[i % BPF_REG_SIZE]) return false; if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ) && exact == NOT_EXACT) { i += BPF_REG_SIZE - 1; /* explored state didn't use this */ continue; } if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID) continue; if (env->allow_uninit_stack && old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_MISC) continue; /* explored stack has more populated slots than current stack * and these slots were used */ if (i >= cur->allocated_stack) return false; /* 64-bit scalar spill vs all slots MISC and vice versa. * Load from all slots MISC produces unbound scalar. * Construct a fake register for such stack and call * regsafe() to ensure scalar ids are compared. */ old_reg = scalar_reg_for_stack(env, &old->stack[spi]); cur_reg = scalar_reg_for_stack(env, &cur->stack[spi]); if (old_reg && cur_reg) { if (!regsafe(env, old_reg, cur_reg, idmap, exact)) return false; i += BPF_REG_SIZE - 1; continue; } /* if old state was safe with misc data in the stack * it will be safe with zero-initialized stack. * The opposite is not true */ if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_MISC && cur->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_ZERO) continue; if (old->stack[spi].slot_type[i % BPF_REG_SIZE] != cur->stack[spi].slot_type[i % BPF_REG_SIZE]) /* Ex: old explored (safe) state has STACK_SPILL in * this stack slot, but current has STACK_MISC -> * this verifier states are not equivalent, * return false to continue verification of this path */ return false; if (i % BPF_REG_SIZE != BPF_REG_SIZE - 1) continue; /* Both old and cur are having same slot_type */ switch (old->stack[spi].slot_type[BPF_REG_SIZE - 1]) { case STACK_SPILL: /* when explored and current stack slot are both storing * spilled registers, check that stored pointers types * are the same as well. * Ex: explored safe path could have stored * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -8} * but current path has stored: * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -16} * such verifier states are not equivalent. * return false to continue verification of this path */ if (!regsafe(env, &old->stack[spi].spilled_ptr, &cur->stack[spi].spilled_ptr, idmap, exact)) return false; break; case STACK_DYNPTR: old_reg = &old->stack[spi].spilled_ptr; cur_reg = &cur->stack[spi].spilled_ptr; if (old_reg->dynptr.type != cur_reg->dynptr.type || old_reg->dynptr.first_slot != cur_reg->dynptr.first_slot || !check_ids(old_reg->ref_obj_id, cur_reg->ref_obj_id, idmap)) return false; break; case STACK_ITER: old_reg = &old->stack[spi].spilled_ptr; cur_reg = &cur->stack[spi].spilled_ptr; /* iter.depth is not compared between states as it * doesn't matter for correctness and would otherwise * prevent convergence; we maintain it only to prevent * infinite loop check triggering, see * iter_active_depths_differ() */ if (old_reg->iter.btf != cur_reg->iter.btf || old_reg->iter.btf_id != cur_reg->iter.btf_id || old_reg->iter.state != cur_reg->iter.state || /* ignore {old_reg,cur_reg}->iter.depth, see above */ !check_ids(old_reg->ref_obj_id, cur_reg->ref_obj_id, idmap)) return false; break; case STACK_MISC: case STACK_ZERO: case STACK_INVALID: continue; /* Ensure that new unhandled slot types return false by default */ default: return false; } } return true; } static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur, struct bpf_idmap *idmap) { int i; if (old->acquired_refs != cur->acquired_refs) return false; for (i = 0; i < old->acquired_refs; i++) { if (!check_ids(old->refs[i].id, cur->refs[i].id, idmap)) return false; } return true; } /* compare two verifier states * * all states stored in state_list are known to be valid, since * verifier reached 'bpf_exit' instruction through them * * this function is called when verifier exploring different branches of * execution popped from the state stack. If it sees an old state that has * more strict register state and more strict stack state then this execution * branch doesn't need to be explored further, since verifier already * concluded that more strict state leads to valid finish. * * Therefore two states are equivalent if register state is more conservative * and explored stack state is more conservative than the current one. * Example: * explored current * (slot1=INV slot2=MISC) == (slot1=MISC slot2=MISC) * (slot1=MISC slot2=MISC) != (slot1=INV slot2=MISC) * * In other words if current stack state (one being explored) has more * valid slots than old one that already passed validation, it means * the verifier can stop exploring and conclude that current state is valid too * * Similarly with registers. If explored state has register type as invalid * whereas register type in current state is meaningful, it means that * the current state will reach 'bpf_exit' instruction safely */ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_state *old, struct bpf_func_state *cur, enum exact_level exact) { int i; if (old->callback_depth > cur->callback_depth) return false; for (i = 0; i < MAX_BPF_REG; i++) if (!regsafe(env, &old->regs[i], &cur->regs[i], &env->idmap_scratch, exact)) return false; if (!stacksafe(env, old, cur, &env->idmap_scratch, exact)) return false; if (!refsafe(old, cur, &env->idmap_scratch)) return false; return true; } static void reset_idmap_scratch(struct bpf_verifier_env *env) { env->idmap_scratch.tmp_id_gen = env->id_gen; memset(&env->idmap_scratch.map, 0, sizeof(env->idmap_scratch.map)); } static bool states_equal(struct bpf_verifier_env *env, struct bpf_verifier_state *old, struct bpf_verifier_state *cur, enum exact_level exact) { int i; if (old->curframe != cur->curframe) return false; reset_idmap_scratch(env); /* Verification state from speculative execution simulation * must never prune a non-speculative execution one. */ if (old->speculative && !cur->speculative) return false; if (old->active_lock.ptr != cur->active_lock.ptr) return false; /* Old and cur active_lock's have to be either both present * or both absent. */ if (!!old->active_lock.id != !!cur->active_lock.id) return false; if (old->active_lock.id && !check_ids(old->active_lock.id, cur->active_lock.id, &env->idmap_scratch)) return false; if (old->active_rcu_lock != cur->active_rcu_lock) return false; if (old->active_preempt_lock != cur->active_preempt_lock) return false; if (old->in_sleepable != cur->in_sleepable) return false; /* for states to be equal callsites have to be the same * and all frame states need to be equivalent */ for (i = 0; i <= old->curframe; i++) { if (old->frame[i]->callsite != cur->frame[i]->callsite) return false; if (!func_states_equal(env, old->frame[i], cur->frame[i], exact)) return false; } return true; } /* Return 0 if no propagation happened. Return negative error code if error * happened. Otherwise, return the propagated bit. */ static int propagate_liveness_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, struct bpf_reg_state *parent_reg) { u8 parent_flag = parent_reg->live & REG_LIVE_READ; u8 flag = reg->live & REG_LIVE_READ; int err; /* When comes here, read flags of PARENT_REG or REG could be any of * REG_LIVE_READ64, REG_LIVE_READ32, REG_LIVE_NONE. There is no need * of propagation if PARENT_REG has strongest REG_LIVE_READ64. */ if (parent_flag == REG_LIVE_READ64 || /* Or if there is no read flag from REG. */ !flag || /* Or if the read flag from REG is the same as PARENT_REG. */ parent_flag == flag) return 0; err = mark_reg_read(env, reg, parent_reg, flag); if (err) return err; return flag; } /* A write screens off any subsequent reads; but write marks come from the * straight-line code between a state and its parent. When we arrive at an * equivalent state (jump target or such) we didn't arrive by the straight-line * code, so read marks in the state must propagate to the parent regardless * of the state's write marks. That's what 'parent == state->parent' comparison * in mark_reg_read() is for. */ static int propagate_liveness(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, struct bpf_verifier_state *vparent) { struct bpf_reg_state *state_reg, *parent_reg; struct bpf_func_state *state, *parent; int i, frame, err = 0; if (vparent->curframe != vstate->curframe) { WARN(1, "propagate_live: parent frame %d current frame %d\n", vparent->curframe, vstate->curframe); return -EFAULT; } /* Propagate read liveness of registers... */ BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG); for (frame = 0; frame <= vstate->curframe; frame++) { parent = vparent->frame[frame]; state = vstate->frame[frame]; parent_reg = parent->regs; state_reg = state->regs; /* We don't need to worry about FP liveness, it's read-only */ for (i = frame < vstate->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) { err = propagate_liveness_reg(env, &state_reg[i], &parent_reg[i]); if (err < 0) return err; if (err == REG_LIVE_READ64) mark_insn_zext(env, &parent_reg[i]); } /* Propagate stack slots. */ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE && i < parent->allocated_stack / BPF_REG_SIZE; i++) { parent_reg = &parent->stack[i].spilled_ptr; state_reg = &state->stack[i].spilled_ptr; err = propagate_liveness_reg(env, state_reg, parent_reg); if (err < 0) return err; } } return 0; } /* find precise scalars in the previous equivalent state and * propagate them into the current state */ static int propagate_precision(struct bpf_verifier_env *env, const struct bpf_verifier_state *old) { struct bpf_reg_state *state_reg; struct bpf_func_state *state; int i, err = 0, fr; bool first; for (fr = old->curframe; fr >= 0; fr--) { state = old->frame[fr]; state_reg = state->regs; first = true; for (i = 0; i < BPF_REG_FP; i++, state_reg++) { if (state_reg->type != SCALAR_VALUE || !state_reg->precise || !(state_reg->live & REG_LIVE_READ)) continue; if (env->log.level & BPF_LOG_LEVEL2) { if (first) verbose(env, "frame %d: propagating r%d", fr, i); else verbose(env, ",r%d", i); } bt_set_frame_reg(&env->bt, fr, i); first = false; } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { if (!is_spilled_reg(&state->stack[i])) continue; state_reg = &state->stack[i].spilled_ptr; if (state_reg->type != SCALAR_VALUE || !state_reg->precise || !(state_reg->live & REG_LIVE_READ)) continue; if (env->log.level & BPF_LOG_LEVEL2) { if (first) verbose(env, "frame %d: propagating fp%d", fr, (-i - 1) * BPF_REG_SIZE); else verbose(env, ",fp%d", (-i - 1) * BPF_REG_SIZE); } bt_set_frame_slot(&env->bt, fr, i); first = false; } if (!first) verbose(env, "\n"); } err = mark_chain_precision_batch(env); if (err < 0) return err; return 0; } static bool states_maybe_looping(struct bpf_verifier_state *old, struct bpf_verifier_state *cur) { struct bpf_func_state *fold, *fcur; int i, fr = cur->curframe; if (old->curframe != fr) return false; fold = old->frame[fr]; fcur = cur->frame[fr]; for (i = 0; i < MAX_BPF_REG; i++) if (memcmp(&fold->regs[i], &fcur->regs[i], offsetof(struct bpf_reg_state, parent))) return false; return true; } static bool is_iter_next_insn(struct bpf_verifier_env *env, int insn_idx) { return env->insn_aux_data[insn_idx].is_iter_next; } /* is_state_visited() handles iter_next() (see process_iter_next_call() for * terminology) calls specially: as opposed to bounded BPF loops, it *expects* * states to match, which otherwise would look like an infinite loop. So while * iter_next() calls are taken care of, we still need to be careful and * prevent erroneous and too eager declaration of "ininite loop", when * iterators are involved. * * Here's a situation in pseudo-BPF assembly form: * * 0: again: ; set up iter_next() call args * 1: r1 = &it ; <CHECKPOINT HERE> * 2: call bpf_iter_num_next ; this is iter_next() call * 3: if r0 == 0 goto done * 4: ... something useful here ... * 5: goto again ; another iteration * 6: done: * 7: r1 = &it * 8: call bpf_iter_num_destroy ; clean up iter state * 9: exit * * This is a typical loop. Let's assume that we have a prune point at 1:, * before we get to `call bpf_iter_num_next` (e.g., because of that `goto * again`, assuming other heuristics don't get in a way). * * When we first time come to 1:, let's say we have some state X. We proceed * to 2:, fork states, enqueue ACTIVE, validate NULL case successfully, exit. * Now we come back to validate that forked ACTIVE state. We proceed through * 3-5, come to goto, jump to 1:. Let's assume our state didn't change, so we * are converging. But the problem is that we don't know that yet, as this * convergence has to happen at iter_next() call site only. So if nothing is * done, at 1: verifier will use bounded loop logic and declare infinite * looping (and would be *technically* correct, if not for iterator's * "eventual sticky NULL" contract, see process_iter_next_call()). But we * don't want that. So what we do in process_iter_next_call() when we go on * another ACTIVE iteration, we bump slot->iter.depth, to mark that it's * a different iteration. So when we suspect an infinite loop, we additionally * check if any of the *ACTIVE* iterator states depths differ. If yes, we * pretend we are not looping and wait for next iter_next() call. * * This only applies to ACTIVE state. In DRAINED state we don't expect to * loop, because that would actually mean infinite loop, as DRAINED state is * "sticky", and so we'll keep returning into the same instruction with the * same state (at least in one of possible code paths). * * This approach allows to keep infinite loop heuristic even in the face of * active iterator. E.g., C snippet below is and will be detected as * inifintely looping: * * struct bpf_iter_num it; * int *p, x; * * bpf_iter_num_new(&it, 0, 10); * while ((p = bpf_iter_num_next(&t))) { * x = p; * while (x--) {} // <<-- infinite loop here * } * */ static bool iter_active_depths_differ(struct bpf_verifier_state *old, struct bpf_verifier_state *cur) { struct bpf_reg_state *slot, *cur_slot; struct bpf_func_state *state; int i, fr; for (fr = old->curframe; fr >= 0; fr--) { state = old->frame[fr]; for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { if (state->stack[i].slot_type[0] != STACK_ITER) continue; slot = &state->stack[i].spilled_ptr; if (slot->iter.state != BPF_ITER_STATE_ACTIVE) continue; cur_slot = &cur->frame[fr]->stack[i].spilled_ptr; if (cur_slot->iter.depth != slot->iter.depth) return true; } } return false; } static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state_list *new_sl; struct bpf_verifier_state_list *sl, **pprev; struct bpf_verifier_state *cur = env->cur_state, *new, *loop_entry; int i, j, n, err, states_cnt = 0; bool force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx); bool add_new_state = force_new_state; bool force_exact; /* bpf progs typically have pruning point every 4 instructions * http://vger.kernel.org/bpfconf2019.html#session-1 * Do not add new state for future pruning if the verifier hasn't seen * at least 2 jumps and at least 8 instructions. * This heuristics helps decrease 'total_states' and 'peak_states' metric. * In tests that amounts to up to 50% reduction into total verifier * memory consumption and 20% verifier time speedup. */ if (env->jmps_processed - env->prev_jmps_processed >= 2 && env->insn_processed - env->prev_insn_processed >= 8) add_new_state = true; pprev = explored_state(env, insn_idx); sl = *pprev; clean_live_states(env, insn_idx, cur); while (sl) { states_cnt++; if (sl->state.insn_idx != insn_idx) goto next; if (sl->state.branches) { struct bpf_func_state *frame = sl->state.frame[sl->state.curframe]; if (frame->in_async_callback_fn && frame->async_entry_cnt != cur->frame[cur->curframe]->async_entry_cnt) { /* Different async_entry_cnt means that the verifier is * processing another entry into async callback. * Seeing the same state is not an indication of infinite * loop or infinite recursion. * But finding the same state doesn't mean that it's safe * to stop processing the current state. The previous state * hasn't yet reached bpf_exit, since state.branches > 0. * Checking in_async_callback_fn alone is not enough either. * Since the verifier still needs to catch infinite loops * inside async callbacks. */ goto skip_inf_loop_check; } /* BPF open-coded iterators loop detection is special. * states_maybe_looping() logic is too simplistic in detecting * states that *might* be equivalent, because it doesn't know * about ID remapping, so don't even perform it. * See process_iter_next_call() and iter_active_depths_differ() * for overview of the logic. When current and one of parent * states are detected as equivalent, it's a good thing: we prove * convergence and can stop simulating further iterations. * It's safe to assume that iterator loop will finish, taking into * account iter_next() contract of eventually returning * sticky NULL result. * * Note, that states have to be compared exactly in this case because * read and precision marks might not be finalized inside the loop. * E.g. as in the program below: * * 1. r7 = -16 * 2. r6 = bpf_get_prandom_u32() * 3. while (bpf_iter_num_next(&fp[-8])) { * 4. if (r6 != 42) { * 5. r7 = -32 * 6. r6 = bpf_get_prandom_u32() * 7. continue * 8. } * 9. r0 = r10 * 10. r0 += r7 * 11. r8 = *(u64 *)(r0 + 0) * 12. r6 = bpf_get_prandom_u32() * 13. } * * Here verifier would first visit path 1-3, create a checkpoint at 3 * with r7=-16, continue to 4-7,3. Existing checkpoint at 3 does * not have read or precision mark for r7 yet, thus inexact states * comparison would discard current state with r7=-32 * => unsafe memory access at 11 would not be caught. */ if (is_iter_next_insn(env, insn_idx)) { if (states_equal(env, &sl->state, cur, RANGE_WITHIN)) { struct bpf_func_state *cur_frame; struct bpf_reg_state *iter_state, *iter_reg; int spi; cur_frame = cur->frame[cur->curframe]; /* btf_check_iter_kfuncs() enforces that * iter state pointer is always the first arg */ iter_reg = &cur_frame->regs[BPF_REG_1]; /* current state is valid due to states_equal(), * so we can assume valid iter and reg state, * no need for extra (re-)validations */ spi = __get_spi(iter_reg->off + iter_reg->var_off.value); iter_state = &func(env, iter_reg)->stack[spi].spilled_ptr; if (iter_state->iter.state == BPF_ITER_STATE_ACTIVE) { update_loop_entry(cur, &sl->state); goto hit; } } goto skip_inf_loop_check; } if (is_may_goto_insn_at(env, insn_idx)) { if (sl->state.may_goto_depth != cur->may_goto_depth && states_equal(env, &sl->state, cur, RANGE_WITHIN)) { update_loop_entry(cur, &sl->state); goto hit; } } if (calls_callback(env, insn_idx)) { if (states_equal(env, &sl->state, cur, RANGE_WITHIN)) goto hit; goto skip_inf_loop_check; } /* attempt to detect infinite loop to avoid unnecessary doomed work */ if (states_maybe_looping(&sl->state, cur) && states_equal(env, &sl->state, cur, EXACT) && !iter_active_depths_differ(&sl->state, cur) && sl->state.may_goto_depth == cur->may_goto_depth && sl->state.callback_unroll_depth == cur->callback_unroll_depth) { verbose_linfo(env, insn_idx, "; "); verbose(env, "infinite loop detected at insn %d\n", insn_idx); verbose(env, "cur state:"); print_verifier_state(env, cur->frame[cur->curframe], true); verbose(env, "old state:"); print_verifier_state(env, sl->state.frame[cur->curframe], true); return -EINVAL; } /* if the verifier is processing a loop, avoid adding new state * too often, since different loop iterations have distinct * states and may not help future pruning. * This threshold shouldn't be too low to make sure that * a loop with large bound will be rejected quickly. * The most abusive loop will be: * r1 += 1 * if r1 < 1000000 goto pc-2 * 1M insn_procssed limit / 100 == 10k peak states. * This threshold shouldn't be too high either, since states * at the end of the loop are likely to be useful in pruning. */ skip_inf_loop_check: if (!force_new_state && env->jmps_processed - env->prev_jmps_processed < 20 && env->insn_processed - env->prev_insn_processed < 100) add_new_state = false; goto miss; } /* If sl->state is a part of a loop and this loop's entry is a part of * current verification path then states have to be compared exactly. * 'force_exact' is needed to catch the following case: * * initial Here state 'succ' was processed first, * | it was eventually tracked to produce a * V state identical to 'hdr'. * .---------> hdr All branches from 'succ' had been explored * | | and thus 'succ' has its .branches == 0. * | V * | .------... Suppose states 'cur' and 'succ' correspond * | | | to the same instruction + callsites. * | V V In such case it is necessary to check * | ... ... if 'succ' and 'cur' are states_equal(). * | | | If 'succ' and 'cur' are a part of the * | V V same loop exact flag has to be set. * | succ <- cur To check if that is the case, verify * | | if loop entry of 'succ' is in current * | V DFS path. * | ... * | | * '----' * * Additional details are in the comment before get_loop_entry(). */ loop_entry = get_loop_entry(&sl->state); force_exact = loop_entry && loop_entry->branches > 0; if (states_equal(env, &sl->state, cur, force_exact ? RANGE_WITHIN : NOT_EXACT)) { if (force_exact) update_loop_entry(cur, loop_entry); hit: sl->hit_cnt++; /* reached equivalent register/stack state, * prune the search. * Registers read by the continuation are read by us. * If we have any write marks in env->cur_state, they * will prevent corresponding reads in the continuation * from reaching our parent (an explored_state). Our * own state will get the read marks recorded, but * they'll be immediately forgotten as we're pruning * this state and will pop a new one. */ err = propagate_liveness(env, &sl->state, cur); /* if previous state reached the exit with precision and * current state is equivalent to it (except precision marks) * the precision needs to be propagated back in * the current state. */ if (is_jmp_point(env, env->insn_idx)) err = err ? : push_jmp_history(env, cur, 0); err = err ? : propagate_precision(env, &sl->state); if (err) return err; return 1; } miss: /* when new state is not going to be added do not increase miss count. * Otherwise several loop iterations will remove the state * recorded earlier. The goal of these heuristics is to have * states from some iterations of the loop (some in the beginning * and some at the end) to help pruning. */ if (add_new_state) sl->miss_cnt++; /* heuristic to determine whether this state is beneficial * to keep checking from state equivalence point of view. * Higher numbers increase max_states_per_insn and verification time, * but do not meaningfully decrease insn_processed. * 'n' controls how many times state could miss before eviction. * Use bigger 'n' for checkpoints because evicting checkpoint states * too early would hinder iterator convergence. */ n = is_force_checkpoint(env, insn_idx) && sl->state.branches > 0 ? 64 : 3; if (sl->miss_cnt > sl->hit_cnt * n + n) { /* the state is unlikely to be useful. Remove it to * speed up verification */ *pprev = sl->next; if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE && !sl->state.used_as_loop_entry) { u32 br = sl->state.branches; WARN_ONCE(br, "BUG live_done but branches_to_explore %d\n", br); free_verifier_state(&sl->state, false); kfree(sl); env->peak_states--; } else { /* cannot free this state, since parentage chain may * walk it later. Add it for free_list instead to * be freed at the end of verification */ sl->next = env->free_list; env->free_list = sl; } sl = *pprev; continue; } next: pprev = &sl->next; sl = *pprev; } if (env->max_states_per_insn < states_cnt) env->max_states_per_insn = states_cnt; if (!env->bpf_capable && states_cnt > BPF_COMPLEXITY_LIMIT_STATES) return 0; if (!add_new_state) return 0; /* There were no equivalent states, remember the current one. * Technically the current state is not proven to be safe yet, * but it will either reach outer most bpf_exit (which means it's safe) * or it will be rejected. When there are no loops the verifier won't be * seeing this tuple (frame[0].callsite, frame[1].callsite, .. insn_idx) * again on the way to bpf_exit. * When looping the sl->state.branches will be > 0 and this state * will not be considered for equivalence until branches == 0. */ new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL); if (!new_sl) return -ENOMEM; env->total_states++; env->peak_states++; env->prev_jmps_processed = env->jmps_processed; env->prev_insn_processed = env->insn_processed; /* forget precise markings we inherited, see __mark_chain_precision */ if (env->bpf_capable) mark_all_scalars_imprecise(env, cur); /* add new state to the head of linked list */ new = &new_sl->state; err = copy_verifier_state(new, cur); if (err) { free_verifier_state(new, false); kfree(new_sl); return err; } new->insn_idx = insn_idx; WARN_ONCE(new->branches != 1, "BUG is_state_visited:branches_to_explore=%d insn %d\n", new->branches, insn_idx); cur->parent = new; cur->first_insn_idx = insn_idx; cur->dfs_depth = new->dfs_depth + 1; clear_jmp_history(cur); new_sl->next = *explored_state(env, insn_idx); *explored_state(env, insn_idx) = new_sl; /* connect new state to parentage chain. Current frame needs all * registers connected. Only r6 - r9 of the callers are alive (pushed * to the stack implicitly by JITs) so in callers' frames connect just * r6 - r9 as an optimization. Callers will have r1 - r5 connected to * the state of the call instruction (with WRITTEN set), and r0 comes * from callee with its full parentage chain, anyway. */ /* clear write marks in current state: the writes we did are not writes * our child did, so they don't screen off its reads from us. * (There are no read marks in current state, because reads always mark * their parent and current state never has children yet. Only * explored_states can get read marks.) */ for (j = 0; j <= cur->curframe; j++) { for (i = j < cur->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) cur->frame[j]->regs[i].parent = &new->frame[j]->regs[i]; for (i = 0; i < BPF_REG_FP; i++) cur->frame[j]->regs[i].live = REG_LIVE_NONE; } /* all stack frames are accessible from callee, clear them all */ for (j = 0; j <= cur->curframe; j++) { struct bpf_func_state *frame = cur->frame[j]; struct bpf_func_state *newframe = new->frame[j]; for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++) { frame->stack[i].spilled_ptr.live = REG_LIVE_NONE; frame->stack[i].spilled_ptr.parent = &newframe->stack[i].spilled_ptr; } } return 0; } /* Return true if it's OK to have the same insn return a different type. */ static bool reg_type_mismatch_ok(enum bpf_reg_type type) { switch (base_type(type)) { case PTR_TO_CTX: case PTR_TO_SOCKET: case PTR_TO_SOCK_COMMON: case PTR_TO_TCP_SOCK: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: case PTR_TO_ARENA: return false; default: return true; } } /* If an instruction was previously used with particular pointer types, then we * need to be careful to avoid cases such as the below, where it may be ok * for one branch accessing the pointer, but not ok for the other branch: * * R1 = sock_ptr * goto X; * ... * R1 = some_other_valid_ptr; * goto X; * ... * R2 = *(u32 *)(R1 + 0); */ static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev) { return src != prev && (!reg_type_mismatch_ok(src) || !reg_type_mismatch_ok(prev)); } static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type type, bool allow_trust_mismatch) { enum bpf_reg_type *prev_type = &env->insn_aux_data[env->insn_idx].ptr_type; if (*prev_type == NOT_INIT) { /* Saw a valid insn * dst_reg = *(u32 *)(src_reg + off) * save type to validate intersecting paths */ *prev_type = type; } else if (reg_type_mismatch(type, *prev_type)) { /* Abuser program is trying to use the same insn * dst_reg = *(u32*) (src_reg + off) * with different pointer types: * src_reg == ctx in one branch and * src_reg == stack|map in some other branch. * Reject it. */ if (allow_trust_mismatch && base_type(type) == PTR_TO_BTF_ID && base_type(*prev_type) == PTR_TO_BTF_ID) { /* * Have to support a use case when one path through * the program yields TRUSTED pointer while another * is UNTRUSTED. Fallback to UNTRUSTED to generate * BPF_PROBE_MEM/BPF_PROBE_MEMSX. */ *prev_type = PTR_TO_BTF_ID | PTR_UNTRUSTED; } else { verbose(env, "same insn cannot be used with different pointers\n"); return -EINVAL; } } return 0; } static int do_check(struct bpf_verifier_env *env) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); struct bpf_verifier_state *state = env->cur_state; struct bpf_insn *insns = env->prog->insnsi; struct bpf_reg_state *regs; int insn_cnt = env->prog->len; bool do_print_state = false; int prev_insn_idx = -1; for (;;) { bool exception_exit = false; struct bpf_insn *insn; u8 class; int err; /* reset current history entry on each new instruction */ env->cur_hist_ent = NULL; env->prev_insn_idx = prev_insn_idx; if (env->insn_idx >= insn_cnt) { verbose(env, "invalid insn idx %d insn_cnt %d\n", env->insn_idx, insn_cnt); return -EFAULT; } insn = &insns[env->insn_idx]; class = BPF_CLASS(insn->code); if (++env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) { verbose(env, "BPF program is too large. Processed %d insn\n", env->insn_processed); return -E2BIG; } state->last_insn_idx = env->prev_insn_idx; if (is_prune_point(env, env->insn_idx)) { err = is_state_visited(env, env->insn_idx); if (err < 0) return err; if (err == 1) { /* found equivalent state, can prune the search */ if (env->log.level & BPF_LOG_LEVEL) { if (do_print_state) verbose(env, "\nfrom %d to %d%s: safe\n", env->prev_insn_idx, env->insn_idx, env->cur_state->speculative ? " (speculative execution)" : ""); else verbose(env, "%d: safe\n", env->insn_idx); } goto process_bpf_exit; } } if (is_jmp_point(env, env->insn_idx)) { err = push_jmp_history(env, state, 0); if (err) return err; } if (signal_pending(current)) return -EAGAIN; if (need_resched()) cond_resched(); if (env->log.level & BPF_LOG_LEVEL2 && do_print_state) { verbose(env, "\nfrom %d to %d%s:", env->prev_insn_idx, env->insn_idx, env->cur_state->speculative ? " (speculative execution)" : ""); print_verifier_state(env, state->frame[state->curframe], true); do_print_state = false; } if (env->log.level & BPF_LOG_LEVEL) { const struct bpf_insn_cbs cbs = { .cb_call = disasm_kfunc_name, .cb_print = verbose, .private_data = env, }; if (verifier_state_scratched(env)) print_insn_state(env, state->frame[state->curframe]); verbose_linfo(env, env->insn_idx, "; "); env->prev_log_pos = env->log.end_pos; verbose(env, "%d: ", env->insn_idx); print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); env->prev_insn_print_pos = env->log.end_pos - env->prev_log_pos; env->prev_log_pos = env->log.end_pos; } if (bpf_prog_is_offloaded(env->prog->aux)) { err = bpf_prog_offload_verify_insn(env, env->insn_idx, env->prev_insn_idx); if (err) return err; } regs = cur_regs(env); sanitize_mark_insn_seen(env); prev_insn_idx = env->insn_idx; if (class == BPF_ALU || class == BPF_ALU64) { err = check_alu_op(env, insn); if (err) return err; } else if (class == BPF_LDX) { enum bpf_reg_type src_reg_type; /* check for reserved fields is already done */ /* check src operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); if (err) return err; src_reg_type = regs[insn->src_reg].type; /* check that memory (src_reg + off) is readable, * the state of dst_reg will be updated by this func */ err = check_mem_access(env, env->insn_idx, insn->src_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, insn->dst_reg, false, BPF_MODE(insn->code) == BPF_MEMSX); err = err ?: save_aux_ptr_type(env, src_reg_type, true); err = err ?: reg_bounds_sanity_check(env, ®s[insn->dst_reg], "ldx"); if (err) return err; } else if (class == BPF_STX) { enum bpf_reg_type dst_reg_type; if (BPF_MODE(insn->code) == BPF_ATOMIC) { err = check_atomic(env, env->insn_idx, insn); if (err) return err; env->insn_idx++; continue; } if (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0) { verbose(env, "BPF_STX uses reserved fields\n"); return -EINVAL; } /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; dst_reg_type = regs[insn->dst_reg].type; /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, insn->src_reg, false, false); if (err) return err; err = save_aux_ptr_type(env, dst_reg_type, false); if (err) return err; } else if (class == BPF_ST) { enum bpf_reg_type dst_reg_type; if (BPF_MODE(insn->code) != BPF_MEM || insn->src_reg != BPF_REG_0) { verbose(env, "BPF_ST uses reserved fields\n"); return -EINVAL; } /* check src operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; dst_reg_type = regs[insn->dst_reg].type; /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1, false, false); if (err) return err; err = save_aux_ptr_type(env, dst_reg_type, false); if (err) return err; } else if (class == BPF_JMP || class == BPF_JMP32) { u8 opcode = BPF_OP(insn->code); env->jmps_processed++; if (opcode == BPF_CALL) { if (BPF_SRC(insn->code) != BPF_K || (insn->src_reg != BPF_PSEUDO_KFUNC_CALL && insn->off != 0) || (insn->src_reg != BPF_REG_0 && insn->src_reg != BPF_PSEUDO_CALL && insn->src_reg != BPF_PSEUDO_KFUNC_CALL) || insn->dst_reg != BPF_REG_0 || class == BPF_JMP32) { verbose(env, "BPF_CALL uses reserved fields\n"); return -EINVAL; } if (env->cur_state->active_lock.ptr) { if ((insn->src_reg == BPF_REG_0 && insn->imm != BPF_FUNC_spin_unlock) || (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && (insn->off != 0 || !is_bpf_graph_api_kfunc(insn->imm)))) { verbose(env, "function calls are not allowed while holding a lock\n"); return -EINVAL; } } if (insn->src_reg == BPF_PSEUDO_CALL) { err = check_func_call(env, insn, &env->insn_idx); } else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { err = check_kfunc_call(env, insn, &env->insn_idx); if (!err && is_bpf_throw_kfunc(insn)) { exception_exit = true; goto process_bpf_exit_full; } } else { err = check_helper_call(env, insn, &env->insn_idx); } if (err) return err; mark_reg_scratched(env, BPF_REG_0); } else if (opcode == BPF_JA) { if (BPF_SRC(insn->code) != BPF_K || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0 || (class == BPF_JMP && insn->imm != 0) || (class == BPF_JMP32 && insn->off != 0)) { verbose(env, "BPF_JA uses reserved fields\n"); return -EINVAL; } if (class == BPF_JMP) env->insn_idx += insn->off + 1; else env->insn_idx += insn->imm + 1; continue; } else if (opcode == BPF_EXIT) { if (BPF_SRC(insn->code) != BPF_K || insn->imm != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0 || class == BPF_JMP32) { verbose(env, "BPF_EXIT uses reserved fields\n"); return -EINVAL; } process_bpf_exit_full: if (env->cur_state->active_lock.ptr && !env->cur_state->curframe) { verbose(env, "bpf_spin_unlock is missing\n"); return -EINVAL; } if (env->cur_state->active_rcu_lock && !env->cur_state->curframe) { verbose(env, "bpf_rcu_read_unlock is missing\n"); return -EINVAL; } if (env->cur_state->active_preempt_lock && !env->cur_state->curframe) { verbose(env, "%d bpf_preempt_enable%s missing\n", env->cur_state->active_preempt_lock, env->cur_state->active_preempt_lock == 1 ? " is" : "(s) are"); return -EINVAL; } /* We must do check_reference_leak here before * prepare_func_exit to handle the case when * state->curframe > 0, it may be a callback * function, for which reference_state must * match caller reference state when it exits. */ err = check_reference_leak(env, exception_exit); if (err) return err; /* The side effect of the prepare_func_exit * which is being skipped is that it frees * bpf_func_state. Typically, process_bpf_exit * will only be hit with outermost exit. * copy_verifier_state in pop_stack will handle * freeing of any extra bpf_func_state left over * from not processing all nested function * exits. We also skip return code checks as * they are not needed for exceptional exits. */ if (exception_exit) goto process_bpf_exit; if (state->curframe) { /* exit from nested function */ err = prepare_func_exit(env, &env->insn_idx); if (err) return err; do_print_state = true; continue; } err = check_return_code(env, BPF_REG_0, "R0"); if (err) return err; process_bpf_exit: mark_verifier_state_scratched(env); update_branch_counts(env, env->cur_state); err = pop_stack(env, &prev_insn_idx, &env->insn_idx, pop_log); if (err < 0) { if (err != -ENOENT) return err; break; } else { do_print_state = true; continue; } } else { err = check_cond_jmp_op(env, insn, &env->insn_idx); if (err) return err; } } else if (class == BPF_LD) { u8 mode = BPF_MODE(insn->code); if (mode == BPF_ABS || mode == BPF_IND) { err = check_ld_abs(env, insn); if (err) return err; } else if (mode == BPF_IMM) { err = check_ld_imm(env, insn); if (err) return err; env->insn_idx++; sanitize_mark_insn_seen(env); } else { verbose(env, "invalid BPF_LD mode\n"); return -EINVAL; } } else { verbose(env, "unknown insn class %d\n", class); return -EINVAL; } env->insn_idx++; } return 0; } static int find_btf_percpu_datasec(struct btf *btf) { const struct btf_type *t; const char *tname; int i, n; /* * Both vmlinux and module each have their own ".data..percpu" * DATASECs in BTF. So for module's case, we need to skip vmlinux BTF * types to look at only module's own BTF types. */ n = btf_nr_types(btf); if (btf_is_module(btf)) i = btf_nr_types(btf_vmlinux); else i = 1; for(; i < n; i++) { t = btf_type_by_id(btf, i); if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC) continue; tname = btf_name_by_offset(btf, t->name_off); if (!strcmp(tname, ".data..percpu")) return i; } return -ENOENT; } /* replace pseudo btf_id with kernel symbol address */ static int check_pseudo_btf_id(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_insn_aux_data *aux) { const struct btf_var_secinfo *vsi; const struct btf_type *datasec; struct btf_mod_pair *btf_mod; const struct btf_type *t; const char *sym_name; bool percpu = false; u32 type, id = insn->imm; struct btf *btf; s32 datasec_id; u64 addr; int i, btf_fd, err; btf_fd = insn[1].imm; if (btf_fd) { btf = btf_get_by_fd(btf_fd); if (IS_ERR(btf)) { verbose(env, "invalid module BTF object FD specified.\n"); return -EINVAL; } } else { if (!btf_vmlinux) { verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n"); return -EINVAL; } btf = btf_vmlinux; btf_get(btf); } t = btf_type_by_id(btf, id); if (!t) { verbose(env, "ldimm64 insn specifies invalid btf_id %d.\n", id); err = -ENOENT; goto err_put; } if (!btf_type_is_var(t) && !btf_type_is_func(t)) { verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR or KIND_FUNC\n", id); err = -EINVAL; goto err_put; } sym_name = btf_name_by_offset(btf, t->name_off); addr = kallsyms_lookup_name(sym_name); if (!addr) { verbose(env, "ldimm64 failed to find the address for kernel symbol '%s'.\n", sym_name); err = -ENOENT; goto err_put; } insn[0].imm = (u32)addr; insn[1].imm = addr >> 32; if (btf_type_is_func(t)) { aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY; aux->btf_var.mem_size = 0; goto check_btf; } datasec_id = find_btf_percpu_datasec(btf); if (datasec_id > 0) { datasec = btf_type_by_id(btf, datasec_id); for_each_vsi(i, datasec, vsi) { if (vsi->type == id) { percpu = true; break; } } } type = t->type; t = btf_type_skip_modifiers(btf, type, NULL); if (percpu) { aux->btf_var.reg_type = PTR_TO_BTF_ID | MEM_PERCPU; aux->btf_var.btf = btf; aux->btf_var.btf_id = type; } else if (!btf_type_is_struct(t)) { const struct btf_type *ret; const char *tname; u32 tsize; /* resolve the type size of ksym. */ ret = btf_resolve_size(btf, t, &tsize); if (IS_ERR(ret)) { tname = btf_name_by_offset(btf, t->name_off); verbose(env, "ldimm64 unable to resolve the size of type '%s': %ld\n", tname, PTR_ERR(ret)); err = -EINVAL; goto err_put; } aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY; aux->btf_var.mem_size = tsize; } else { aux->btf_var.reg_type = PTR_TO_BTF_ID; aux->btf_var.btf = btf; aux->btf_var.btf_id = type; } check_btf: /* check whether we recorded this BTF (and maybe module) already */ for (i = 0; i < env->used_btf_cnt; i++) { if (env->used_btfs[i].btf == btf) { btf_put(btf); return 0; } } if (env->used_btf_cnt >= MAX_USED_BTFS) { err = -E2BIG; goto err_put; } btf_mod = &env->used_btfs[env->used_btf_cnt]; btf_mod->btf = btf; btf_mod->module = NULL; /* if we reference variables from kernel module, bump its refcount */ if (btf_is_module(btf)) { btf_mod->module = btf_try_get_module(btf); if (!btf_mod->module) { err = -ENXIO; goto err_put; } } env->used_btf_cnt++; return 0; err_put: btf_put(btf); return err; } static bool is_tracing_prog_type(enum bpf_prog_type type) { switch (type) { case BPF_PROG_TYPE_KPROBE: case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: return true; default: return false; } } static int check_map_prog_compatibility(struct bpf_verifier_env *env, struct bpf_map *map, struct bpf_prog *prog) { enum bpf_prog_type prog_type = resolve_prog_type(prog); if (btf_record_has_field(map->record, BPF_LIST_HEAD) || btf_record_has_field(map->record, BPF_RB_ROOT)) { if (is_tracing_prog_type(prog_type)) { verbose(env, "tracing progs cannot use bpf_{list_head,rb_root} yet\n"); return -EINVAL; } } if (btf_record_has_field(map->record, BPF_SPIN_LOCK)) { if (prog_type == BPF_PROG_TYPE_SOCKET_FILTER) { verbose(env, "socket filter progs cannot use bpf_spin_lock yet\n"); return -EINVAL; } if (is_tracing_prog_type(prog_type)) { verbose(env, "tracing progs cannot use bpf_spin_lock yet\n"); return -EINVAL; } } if (btf_record_has_field(map->record, BPF_TIMER)) { if (is_tracing_prog_type(prog_type)) { verbose(env, "tracing progs cannot use bpf_timer yet\n"); return -EINVAL; } } if (btf_record_has_field(map->record, BPF_WORKQUEUE)) { if (is_tracing_prog_type(prog_type)) { verbose(env, "tracing progs cannot use bpf_wq yet\n"); return -EINVAL; } } if ((bpf_prog_is_offloaded(prog->aux) || bpf_map_is_offloaded(map)) && !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); return -EINVAL; } if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { verbose(env, "bpf_struct_ops map cannot be used in prog\n"); return -EINVAL; } if (prog->sleepable) switch (map->map_type) { case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_LRU_HASH: case BPF_MAP_TYPE_ARRAY: case BPF_MAP_TYPE_PERCPU_HASH: case BPF_MAP_TYPE_PERCPU_ARRAY: case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: case BPF_MAP_TYPE_RINGBUF: case BPF_MAP_TYPE_USER_RINGBUF: case BPF_MAP_TYPE_INODE_STORAGE: case BPF_MAP_TYPE_SK_STORAGE: case BPF_MAP_TYPE_TASK_STORAGE: case BPF_MAP_TYPE_CGRP_STORAGE: case BPF_MAP_TYPE_QUEUE: case BPF_MAP_TYPE_STACK: case BPF_MAP_TYPE_ARENA: break; default: verbose(env, "Sleepable programs can only use array, hash, ringbuf and local storage maps\n"); return -EINVAL; } return 0; } static bool bpf_map_is_cgroup_storage(struct bpf_map *map) { return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); } /* find and rewrite pseudo imm in ld_imm64 instructions: * * 1. if it accesses map FD, replace it with actual map pointer. * 2. if it accesses btf_id of a VAR, replace it with pointer to the var. * * NOTE: btf_vmlinux is required for converting pseudo btf_id. */ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) { struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; int i, j, err; err = bpf_prog_calc_tag(env->prog); if (err) return err; for (i = 0; i < insn_cnt; i++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && ((BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) || insn->imm != 0)) { verbose(env, "BPF_LDX uses reserved fields\n"); return -EINVAL; } if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) { struct bpf_insn_aux_data *aux; struct bpf_map *map; struct fd f; u64 addr; u32 fd; if (i == insn_cnt - 1 || insn[1].code != 0 || insn[1].dst_reg != 0 || insn[1].src_reg != 0 || insn[1].off != 0) { verbose(env, "invalid bpf_ld_imm64 insn\n"); return -EINVAL; } if (insn[0].src_reg == 0) /* valid generic load 64-bit imm */ goto next_insn; if (insn[0].src_reg == BPF_PSEUDO_BTF_ID) { aux = &env->insn_aux_data[i]; err = check_pseudo_btf_id(env, insn, aux); if (err) return err; goto next_insn; } if (insn[0].src_reg == BPF_PSEUDO_FUNC) { aux = &env->insn_aux_data[i]; aux->ptr_type = PTR_TO_FUNC; goto next_insn; } /* In final convert_pseudo_ld_imm64() step, this is * converted into regular 64-bit imm load insn. */ switch (insn[0].src_reg) { case BPF_PSEUDO_MAP_VALUE: case BPF_PSEUDO_MAP_IDX_VALUE: break; case BPF_PSEUDO_MAP_FD: case BPF_PSEUDO_MAP_IDX: if (insn[1].imm == 0) break; fallthrough; default: verbose(env, "unrecognized bpf_ld_imm64 insn\n"); return -EINVAL; } switch (insn[0].src_reg) { case BPF_PSEUDO_MAP_IDX_VALUE: case BPF_PSEUDO_MAP_IDX: if (bpfptr_is_null(env->fd_array)) { verbose(env, "fd_idx without fd_array is invalid\n"); return -EPROTO; } if (copy_from_bpfptr_offset(&fd, env->fd_array, insn[0].imm * sizeof(fd), sizeof(fd))) return -EFAULT; break; default: fd = insn[0].imm; break; } f = fdget(fd); map = __bpf_map_get(f); if (IS_ERR(map)) { verbose(env, "fd %d is not pointing to valid bpf_map\n", fd); return PTR_ERR(map); } err = check_map_prog_compatibility(env, map, env->prog); if (err) { fdput(f); return err; } aux = &env->insn_aux_data[i]; if (insn[0].src_reg == BPF_PSEUDO_MAP_FD || insn[0].src_reg == BPF_PSEUDO_MAP_IDX) { addr = (unsigned long)map; } else { u32 off = insn[1].imm; if (off >= BPF_MAX_VAR_OFF) { verbose(env, "direct value offset of %u is not allowed\n", off); fdput(f); return -EINVAL; } if (!map->ops->map_direct_value_addr) { verbose(env, "no direct value access support for this map type\n"); fdput(f); return -EINVAL; } err = map->ops->map_direct_value_addr(map, &addr, off); if (err) { verbose(env, "invalid access to map value pointer, value_size=%u off=%u\n", map->value_size, off); fdput(f); return err; } aux->map_off = off; addr += off; } insn[0].imm = (u32)addr; insn[1].imm = addr >> 32; /* check whether we recorded this map already */ for (j = 0; j < env->used_map_cnt; j++) { if (env->used_maps[j] == map) { aux->map_index = j; fdput(f); goto next_insn; } } if (env->used_map_cnt >= MAX_USED_MAPS) { verbose(env, "The total number of maps per program has reached the limit of %u\n", MAX_USED_MAPS); fdput(f); return -E2BIG; } if (env->prog->sleepable) atomic64_inc(&map->sleepable_refcnt); /* hold the map. If the program is rejected by verifier, * the map will be released by release_maps() or it * will be used by the valid program until it's unloaded * and all maps are released in bpf_free_used_maps() */ bpf_map_inc(map); aux->map_index = env->used_map_cnt; env->used_maps[env->used_map_cnt++] = map; if (bpf_map_is_cgroup_storage(map) && bpf_cgroup_storage_assign(env->prog->aux, map)) { verbose(env, "only one cgroup storage of each type is allowed\n"); fdput(f); return -EBUSY; } if (map->map_type == BPF_MAP_TYPE_ARENA) { if (env->prog->aux->arena) { verbose(env, "Only one arena per program\n"); fdput(f); return -EBUSY; } if (!env->allow_ptr_leaks || !env->bpf_capable) { verbose(env, "CAP_BPF and CAP_PERFMON are required to use arena\n"); fdput(f); return -EPERM; } if (!env->prog->jit_requested) { verbose(env, "JIT is required to use arena\n"); fdput(f); return -EOPNOTSUPP; } if (!bpf_jit_supports_arena()) { verbose(env, "JIT doesn't support arena\n"); fdput(f); return -EOPNOTSUPP; } env->prog->aux->arena = (void *)map; if (!bpf_arena_get_user_vm_start(env->prog->aux->arena)) { verbose(env, "arena's user address must be set via map_extra or mmap()\n"); fdput(f); return -EINVAL; } } fdput(f); next_insn: insn++; i++; continue; } /* Basic sanity check before we invest more work here. */ if (!bpf_opcode_in_insntable(insn->code)) { verbose(env, "unknown opcode %02x\n", insn->code); return -EINVAL; } } /* now all pseudo BPF_LD_IMM64 instructions load valid * 'struct bpf_map *' into a register instead of user map_fd. * These pointers will be used later by verifier to validate map access. */ return 0; } /* drop refcnt of maps used by the rejected program */ static void release_maps(struct bpf_verifier_env *env) { __bpf_free_used_maps(env->prog->aux, env->used_maps, env->used_map_cnt); } /* drop refcnt of maps used by the rejected program */ static void release_btfs(struct bpf_verifier_env *env) { __bpf_free_used_btfs(env->prog->aux, env->used_btfs, env->used_btf_cnt); } /* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */ static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env) { struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; int i; for (i = 0; i < insn_cnt; i++, insn++) { if (insn->code != (BPF_LD | BPF_IMM | BPF_DW)) continue; if (insn->src_reg == BPF_PSEUDO_FUNC) continue; insn->src_reg = 0; } } /* single env->prog->insni[off] instruction was replaced with the range * insni[off, off + cnt). Adjust corresponding insn_aux_data by copying * [0, off) and [off, end) to new locations, so the patched range stays zero */ static void adjust_insn_aux_data(struct bpf_verifier_env *env, struct bpf_insn_aux_data *new_data, struct bpf_prog *new_prog, u32 off, u32 cnt) { struct bpf_insn_aux_data *old_data = env->insn_aux_data; struct bpf_insn *insn = new_prog->insnsi; u32 old_seen = old_data[off].seen; u32 prog_len; int i; /* aux info at OFF always needs adjustment, no matter fast path * (cnt == 1) is taken or not. There is no guarantee INSN at OFF is the * original insn at old prog. */ old_data[off].zext_dst = insn_has_def32(env, insn + off + cnt - 1); if (cnt == 1) return; prog_len = new_prog->len; memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off); memcpy(new_data + off + cnt - 1, old_data + off, sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); for (i = off; i < off + cnt - 1; i++) { /* Expand insni[off]'s seen count to the patched range. */ new_data[i].seen = old_seen; new_data[i].zext_dst = insn_has_def32(env, insn + i); } env->insn_aux_data = new_data; vfree(old_data); } static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len) { int i; if (len == 1) return; /* NOTE: fake 'exit' subprog should be updated as well. */ for (i = 0; i <= env->subprog_cnt; i++) { if (env->subprog_info[i].start <= off) continue; env->subprog_info[i].start += len - 1; } } static void adjust_poke_descs(struct bpf_prog *prog, u32 off, u32 len) { struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab; int i, sz = prog->aux->size_poke_tab; struct bpf_jit_poke_descriptor *desc; for (i = 0; i < sz; i++) { desc = &tab[i]; if (desc->insn_idx <= off) continue; desc->insn_idx += len - 1; } } static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off, const struct bpf_insn *patch, u32 len) { struct bpf_prog *new_prog; struct bpf_insn_aux_data *new_data = NULL; if (len > 1) { new_data = vzalloc(array_size(env->prog->len + len - 1, sizeof(struct bpf_insn_aux_data))); if (!new_data) return NULL; } new_prog = bpf_patch_insn_single(env->prog, off, patch, len); if (IS_ERR(new_prog)) { if (PTR_ERR(new_prog) == -ERANGE) verbose(env, "insn %d cannot be patched due to 16-bit range\n", env->insn_aux_data[off].orig_idx); vfree(new_data); return NULL; } adjust_insn_aux_data(env, new_data, new_prog, off, len); adjust_subprog_starts(env, off, len); adjust_poke_descs(new_prog, off, len); return new_prog; } /* * For all jmp insns in a given 'prog' that point to 'tgt_idx' insn adjust the * jump offset by 'delta'. */ static int adjust_jmp_off(struct bpf_prog *prog, u32 tgt_idx, u32 delta) { struct bpf_insn *insn = prog->insnsi; u32 insn_cnt = prog->len, i; for (i = 0; i < insn_cnt; i++, insn++) { u8 code = insn->code; if ((BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) || BPF_OP(code) == BPF_CALL || BPF_OP(code) == BPF_EXIT) continue; if (insn->code == (BPF_JMP32 | BPF_JA)) { if (i + 1 + insn->imm != tgt_idx) continue; if (signed_add32_overflows(insn->imm, delta)) return -ERANGE; insn->imm += delta; } else { if (i + 1 + insn->off != tgt_idx) continue; if (signed_add16_overflows(insn->imm, delta)) return -ERANGE; insn->off += delta; } } return 0; } static int adjust_subprog_starts_after_remove(struct bpf_verifier_env *env, u32 off, u32 cnt) { int i, j; /* find first prog starting at or after off (first to remove) */ for (i = 0; i < env->subprog_cnt; i++) if (env->subprog_info[i].start >= off) break; /* find first prog starting at or after off + cnt (first to stay) */ for (j = i; j < env->subprog_cnt; j++) if (env->subprog_info[j].start >= off + cnt) break; /* if j doesn't start exactly at off + cnt, we are just removing * the front of previous prog */ if (env->subprog_info[j].start != off + cnt) j--; if (j > i) { struct bpf_prog_aux *aux = env->prog->aux; int move; /* move fake 'exit' subprog as well */ move = env->subprog_cnt + 1 - j; memmove(env->subprog_info + i, env->subprog_info + j, sizeof(*env->subprog_info) * move); env->subprog_cnt -= j - i; /* remove func_info */ if (aux->func_info) { move = aux->func_info_cnt - j; memmove(aux->func_info + i, aux->func_info + j, sizeof(*aux->func_info) * move); aux->func_info_cnt -= j - i; /* func_info->insn_off is set after all code rewrites, * in adjust_btf_func() - no need to adjust */ } } else { /* convert i from "first prog to remove" to "first to adjust" */ if (env->subprog_info[i].start == off) i++; } /* update fake 'exit' subprog as well */ for (; i <= env->subprog_cnt; i++) env->subprog_info[i].start -= cnt; return 0; } static int bpf_adj_linfo_after_remove(struct bpf_verifier_env *env, u32 off, u32 cnt) { struct bpf_prog *prog = env->prog; u32 i, l_off, l_cnt, nr_linfo; struct bpf_line_info *linfo; nr_linfo = prog->aux->nr_linfo; if (!nr_linfo) return 0; linfo = prog->aux->linfo; /* find first line info to remove, count lines to be removed */ for (i = 0; i < nr_linfo; i++) if (linfo[i].insn_off >= off) break; l_off = i; l_cnt = 0; for (; i < nr_linfo; i++) if (linfo[i].insn_off < off + cnt) l_cnt++; else break; /* First live insn doesn't match first live linfo, it needs to "inherit" * last removed linfo. prog is already modified, so prog->len == off * means no live instructions after (tail of the program was removed). */ if (prog->len != off && l_cnt && (i == nr_linfo || linfo[i].insn_off != off + cnt)) { l_cnt--; linfo[--i].insn_off = off + cnt; } /* remove the line info which refer to the removed instructions */ if (l_cnt) { memmove(linfo + l_off, linfo + i, sizeof(*linfo) * (nr_linfo - i)); prog->aux->nr_linfo -= l_cnt; nr_linfo = prog->aux->nr_linfo; } /* pull all linfo[i].insn_off >= off + cnt in by cnt */ for (i = l_off; i < nr_linfo; i++) linfo[i].insn_off -= cnt; /* fix up all subprogs (incl. 'exit') which start >= off */ for (i = 0; i <= env->subprog_cnt; i++) if (env->subprog_info[i].linfo_idx > l_off) { /* program may have started in the removed region but * may not be fully removed */ if (env->subprog_info[i].linfo_idx >= l_off + l_cnt) env->subprog_info[i].linfo_idx -= l_cnt; else env->subprog_info[i].linfo_idx = l_off; } return 0; } static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; unsigned int orig_prog_len = env->prog->len; int err; if (bpf_prog_is_offloaded(env->prog->aux)) bpf_prog_offload_remove_insns(env, off, cnt); err = bpf_remove_insns(env->prog, off, cnt); if (err) return err; err = adjust_subprog_starts_after_remove(env, off, cnt); if (err) return err; err = bpf_adj_linfo_after_remove(env, off, cnt); if (err) return err; memmove(aux_data + off, aux_data + off + cnt, sizeof(*aux_data) * (orig_prog_len - off - cnt)); return 0; } /* The verifier does more data flow analysis than llvm and will not * explore branches that are dead at run time. Malicious programs can * have dead code too. Therefore replace all dead at-run-time code * with 'ja -1'. * * Just nops are not optimal, e.g. if they would sit at the end of the * program and through another bug we would manage to jump there, then * we'd execute beyond program memory otherwise. Returning exception * code also wouldn't work since we can have subprogs where the dead * code could be located. */ static void sanitize_dead_code(struct bpf_verifier_env *env) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; struct bpf_insn trap = BPF_JMP_IMM(BPF_JA, 0, 0, -1); struct bpf_insn *insn = env->prog->insnsi; const int insn_cnt = env->prog->len; int i; for (i = 0; i < insn_cnt; i++) { if (aux_data[i].seen) continue; memcpy(insn + i, &trap, sizeof(trap)); aux_data[i].zext_dst = false; } } static bool insn_is_cond_jump(u8 code) { u8 op; op = BPF_OP(code); if (BPF_CLASS(code) == BPF_JMP32) return op != BPF_JA; if (BPF_CLASS(code) != BPF_JMP) return false; return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL; } static void opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0); struct bpf_insn *insn = env->prog->insnsi; const int insn_cnt = env->prog->len; int i; for (i = 0; i < insn_cnt; i++, insn++) { if (!insn_is_cond_jump(insn->code)) continue; if (!aux_data[i + 1].seen) ja.off = insn->off; else if (!aux_data[i + 1 + insn->off].seen) ja.off = 0; else continue; if (bpf_prog_is_offloaded(env->prog->aux)) bpf_prog_offload_replace_insn(env, i, &ja); memcpy(insn, &ja, sizeof(ja)); } } static int opt_remove_dead_code(struct bpf_verifier_env *env) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; int insn_cnt = env->prog->len; int i, err; for (i = 0; i < insn_cnt; i++) { int j; j = 0; while (i + j < insn_cnt && !aux_data[i + j].seen) j++; if (!j) continue; err = verifier_remove_insns(env, i, j); if (err) return err; insn_cnt = env->prog->len; } return 0; } static int opt_remove_nops(struct bpf_verifier_env *env) { const struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0); struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; int i, err; for (i = 0; i < insn_cnt; i++) { if (memcmp(&insn[i], &ja, sizeof(ja))) continue; err = verifier_remove_insns(env, i, 1); if (err) return err; insn_cnt--; i--; } return 0; } static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env, const union bpf_attr *attr) { struct bpf_insn *patch, zext_patch[2], rnd_hi32_patch[4]; struct bpf_insn_aux_data *aux = env->insn_aux_data; int i, patch_len, delta = 0, len = env->prog->len; struct bpf_insn *insns = env->prog->insnsi; struct bpf_prog *new_prog; bool rnd_hi32; rnd_hi32 = attr->prog_flags & BPF_F_TEST_RND_HI32; zext_patch[1] = BPF_ZEXT_REG(0); rnd_hi32_patch[1] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, 0); rnd_hi32_patch[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32); rnd_hi32_patch[3] = BPF_ALU64_REG(BPF_OR, 0, BPF_REG_AX); for (i = 0; i < len; i++) { int adj_idx = i + delta; struct bpf_insn insn; int load_reg; insn = insns[adj_idx]; load_reg = insn_def_regno(&insn); if (!aux[adj_idx].zext_dst) { u8 code, class; u32 imm_rnd; if (!rnd_hi32) continue; code = insn.code; class = BPF_CLASS(code); if (load_reg == -1) continue; /* NOTE: arg "reg" (the fourth one) is only used for * BPF_STX + SRC_OP, so it is safe to pass NULL * here. */ if (is_reg64(env, &insn, load_reg, NULL, DST_OP)) { if (class == BPF_LD && BPF_MODE(code) == BPF_IMM) i++; continue; } /* ctx load could be transformed into wider load. */ if (class == BPF_LDX && aux[adj_idx].ptr_type == PTR_TO_CTX) continue; imm_rnd = get_random_u32(); rnd_hi32_patch[0] = insn; rnd_hi32_patch[1].imm = imm_rnd; rnd_hi32_patch[3].dst_reg = load_reg; patch = rnd_hi32_patch; patch_len = 4; goto apply_patch_buffer; } /* Add in an zero-extend instruction if a) the JIT has requested * it or b) it's a CMPXCHG. * * The latter is because: BPF_CMPXCHG always loads a value into * R0, therefore always zero-extends. However some archs' * equivalent instruction only does this load when the * comparison is successful. This detail of CMPXCHG is * orthogonal to the general zero-extension behaviour of the * CPU, so it's treated independently of bpf_jit_needs_zext. */ if (!bpf_jit_needs_zext() && !is_cmpxchg_insn(&insn)) continue; /* Zero-extension is done by the caller. */ if (bpf_pseudo_kfunc_call(&insn)) continue; if (WARN_ON(load_reg == -1)) { verbose(env, "verifier bug. zext_dst is set, but no reg is defined\n"); return -EFAULT; } zext_patch[0] = insn; zext_patch[1].dst_reg = load_reg; zext_patch[1].src_reg = load_reg; patch = zext_patch; patch_len = 2; apply_patch_buffer: new_prog = bpf_patch_insn_data(env, adj_idx, patch, patch_len); if (!new_prog) return -ENOMEM; env->prog = new_prog; insns = new_prog->insnsi; aux = env->insn_aux_data; delta += patch_len - 1; } return 0; } /* convert load instructions that access fields of a context type into a * sequence of instructions that access fields of the underlying structure: * struct __sk_buff -> struct sk_buff * struct bpf_sock_ops -> struct sock */ static int convert_ctx_accesses(struct bpf_verifier_env *env) { const struct bpf_verifier_ops *ops = env->ops; int i, cnt, size, ctx_field_size, delta = 0; const int insn_cnt = env->prog->len; struct bpf_insn insn_buf[16], *insn; u32 target_size, size_default, off; struct bpf_prog *new_prog; enum bpf_access_type type; bool is_narrower_load; if (ops->gen_prologue || env->seen_direct_write) { if (!ops->gen_prologue) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } cnt = ops->gen_prologue(insn_buf, env->seen_direct_write, env->prog); if (cnt >= ARRAY_SIZE(insn_buf)) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } else if (cnt) { new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt); if (!new_prog) return -ENOMEM; env->prog = new_prog; delta += cnt - 1; } } if (bpf_prog_is_offloaded(env->prog->aux)) return 0; insn = env->prog->insnsi + delta; for (i = 0; i < insn_cnt; i++, insn++) { bpf_convert_ctx_access_t convert_ctx_access; u8 mode; if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) || insn->code == (BPF_LDX | BPF_MEM | BPF_H) || insn->code == (BPF_LDX | BPF_MEM | BPF_W) || insn->code == (BPF_LDX | BPF_MEM | BPF_DW) || insn->code == (BPF_LDX | BPF_MEMSX | BPF_B) || insn->code == (BPF_LDX | BPF_MEMSX | BPF_H) || insn->code == (BPF_LDX | BPF_MEMSX | BPF_W)) { type = BPF_READ; } else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) || insn->code == (BPF_STX | BPF_MEM | BPF_H) || insn->code == (BPF_STX | BPF_MEM | BPF_W) || insn->code == (BPF_STX | BPF_MEM | BPF_DW) || insn->code == (BPF_ST | BPF_MEM | BPF_B) || insn->code == (BPF_ST | BPF_MEM | BPF_H) || insn->code == (BPF_ST | BPF_MEM | BPF_W) || insn->code == (BPF_ST | BPF_MEM | BPF_DW)) { type = BPF_WRITE; } else if ((insn->code == (BPF_STX | BPF_ATOMIC | BPF_W) || insn->code == (BPF_STX | BPF_ATOMIC | BPF_DW)) && env->insn_aux_data[i + delta].ptr_type == PTR_TO_ARENA) { insn->code = BPF_STX | BPF_PROBE_ATOMIC | BPF_SIZE(insn->code); env->prog->aux->num_exentries++; continue; } else { continue; } if (type == BPF_WRITE && env->insn_aux_data[i + delta].sanitize_stack_spill) { struct bpf_insn patch[] = { *insn, BPF_ST_NOSPEC(), }; cnt = ARRAY_SIZE(patch); new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } switch ((int)env->insn_aux_data[i + delta].ptr_type) { case PTR_TO_CTX: if (!ops->convert_ctx_access) continue; convert_ctx_access = ops->convert_ctx_access; break; case PTR_TO_SOCKET: case PTR_TO_SOCK_COMMON: convert_ctx_access = bpf_sock_convert_ctx_access; break; case PTR_TO_TCP_SOCK: convert_ctx_access = bpf_tcp_sock_convert_ctx_access; break; case PTR_TO_XDP_SOCK: convert_ctx_access = bpf_xdp_sock_convert_ctx_access; break; case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | PTR_UNTRUSTED: /* PTR_TO_BTF_ID | MEM_ALLOC always has a valid lifetime, unlike * PTR_TO_BTF_ID, and an active ref_obj_id, but the same cannot * be said once it is marked PTR_UNTRUSTED, hence we must handle * any faults for loads into such types. BPF_WRITE is disallowed * for this case. */ case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED: if (type == BPF_READ) { if (BPF_MODE(insn->code) == BPF_MEM) insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code); else insn->code = BPF_LDX | BPF_PROBE_MEMSX | BPF_SIZE((insn)->code); env->prog->aux->num_exentries++; } continue; case PTR_TO_ARENA: if (BPF_MODE(insn->code) == BPF_MEMSX) { verbose(env, "sign extending loads from arena are not supported yet\n"); return -EOPNOTSUPP; } insn->code = BPF_CLASS(insn->code) | BPF_PROBE_MEM32 | BPF_SIZE(insn->code); env->prog->aux->num_exentries++; continue; default: continue; } ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size; size = BPF_LDST_BYTES(insn); mode = BPF_MODE(insn->code); /* If the read access is a narrower load of the field, * convert to a 4/8-byte load, to minimum program type specific * convert_ctx_access changes. If conversion is successful, * we will apply proper mask to the result. */ is_narrower_load = size < ctx_field_size; size_default = bpf_ctx_off_adjust_machine(ctx_field_size); off = insn->off; if (is_narrower_load) { u8 size_code; if (type == BPF_WRITE) { verbose(env, "bpf verifier narrow ctx access misconfigured\n"); return -EINVAL; } size_code = BPF_H; if (ctx_field_size == 4) size_code = BPF_W; else if (ctx_field_size == 8) size_code = BPF_DW; insn->off = off & ~(size_default - 1); insn->code = BPF_LDX | BPF_MEM | size_code; } target_size = 0; cnt = convert_ctx_access(type, insn, insn_buf, env->prog, &target_size); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) || (ctx_field_size && !target_size)) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } if (is_narrower_load && size < target_size) { u8 shift = bpf_ctx_narrow_access_offset( off, size, size_default) * 8; if (shift && cnt + 1 >= ARRAY_SIZE(insn_buf)) { verbose(env, "bpf verifier narrow ctx load misconfigured\n"); return -EINVAL; } if (ctx_field_size <= 4) { if (shift) insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH, insn->dst_reg, shift); insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg, (1 << size * 8) - 1); } else { if (shift) insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH, insn->dst_reg, shift); insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg, (1ULL << size * 8) - 1); } } if (mode == BPF_MEMSX) insn_buf[cnt++] = BPF_RAW_INSN(BPF_ALU64 | BPF_MOV | BPF_X, insn->dst_reg, insn->dst_reg, size * 8, 0); new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; /* keep walking new program and skip insns we just inserted */ env->prog = new_prog; insn = new_prog->insnsi + i + delta; } return 0; } static int jit_subprogs(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog, **func, *tmp; int i, j, subprog_start, subprog_end = 0, len, subprog; struct bpf_map *map_ptr; struct bpf_insn *insn; void *old_bpf_func; int err, num_exentries; if (env->subprog_cnt <= 1) return 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn)) continue; /* Upon error here we cannot fall back to interpreter but * need a hard reject of the program. Thus -EFAULT is * propagated in any case. */ subprog = find_subprog(env, i + insn->imm + 1); if (subprog < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", i + insn->imm + 1); return -EFAULT; } /* temporarily remember subprog id inside insn instead of * aux_data, since next loop will split up all insns into funcs */ insn->off = subprog; /* remember original imm in case JIT fails and fallback * to interpreter will be needed */ env->insn_aux_data[i].call_imm = insn->imm; /* point imm to __bpf_call_base+1 from JITs point of view */ insn->imm = 1; if (bpf_pseudo_func(insn)) { #if defined(MODULES_VADDR) u64 addr = MODULES_VADDR; #else u64 addr = VMALLOC_START; #endif /* jit (e.g. x86_64) may emit fewer instructions * if it learns a u32 imm is the same as a u64 imm. * Set close enough to possible prog address. */ insn[0].imm = (u32)addr; insn[1].imm = addr >> 32; } } err = bpf_prog_alloc_jited_linfo(prog); if (err) goto out_undo_insn; err = -ENOMEM; func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL); if (!func) goto out_undo_insn; for (i = 0; i < env->subprog_cnt; i++) { subprog_start = subprog_end; subprog_end = env->subprog_info[i + 1].start; len = subprog_end - subprog_start; /* bpf_prog_run() doesn't call subprogs directly, * hence main prog stats include the runtime of subprogs. * subprogs don't have IDs and not reachable via prog_get_next_id * func[i]->stats will never be accessed and stays NULL */ func[i] = bpf_prog_alloc_no_stats(bpf_prog_size(len), GFP_USER); if (!func[i]) goto out_free; memcpy(func[i]->insnsi, &prog->insnsi[subprog_start], len * sizeof(struct bpf_insn)); func[i]->type = prog->type; func[i]->len = len; if (bpf_prog_calc_tag(func[i])) goto out_free; func[i]->is_func = 1; func[i]->sleepable = prog->sleepable; func[i]->aux->func_idx = i; /* Below members will be freed only at prog->aux */ func[i]->aux->btf = prog->aux->btf; func[i]->aux->func_info = prog->aux->func_info; func[i]->aux->func_info_cnt = prog->aux->func_info_cnt; func[i]->aux->poke_tab = prog->aux->poke_tab; func[i]->aux->size_poke_tab = prog->aux->size_poke_tab; for (j = 0; j < prog->aux->size_poke_tab; j++) { struct bpf_jit_poke_descriptor *poke; poke = &prog->aux->poke_tab[j]; if (poke->insn_idx < subprog_end && poke->insn_idx >= subprog_start) poke->aux = func[i]->aux; } func[i]->aux->name[0] = 'F'; func[i]->aux->stack_depth = env->subprog_info[i].stack_depth; func[i]->jit_requested = 1; func[i]->blinding_requested = prog->blinding_requested; func[i]->aux->kfunc_tab = prog->aux->kfunc_tab; func[i]->aux->kfunc_btf_tab = prog->aux->kfunc_btf_tab; func[i]->aux->linfo = prog->aux->linfo; func[i]->aux->nr_linfo = prog->aux->nr_linfo; func[i]->aux->jited_linfo = prog->aux->jited_linfo; func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx; func[i]->aux->arena = prog->aux->arena; num_exentries = 0; insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && (BPF_MODE(insn->code) == BPF_PROBE_MEM || BPF_MODE(insn->code) == BPF_PROBE_MEM32 || BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) num_exentries++; if ((BPF_CLASS(insn->code) == BPF_STX || BPF_CLASS(insn->code) == BPF_ST) && BPF_MODE(insn->code) == BPF_PROBE_MEM32) num_exentries++; if (BPF_CLASS(insn->code) == BPF_STX && BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) num_exentries++; } func[i]->aux->num_exentries = num_exentries; func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable; func[i]->aux->exception_cb = env->subprog_info[i].is_exception_cb; if (!i) func[i]->aux->exception_boundary = env->seen_exception; func[i] = bpf_int_jit_compile(func[i]); if (!func[i]->jited) { err = -ENOTSUPP; goto out_free; } cond_resched(); } /* at this point all bpf functions were successfully JITed * now populate all bpf_calls with correct addresses and * run last pass of JIT */ for (i = 0; i < env->subprog_cnt; i++) { insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (bpf_pseudo_func(insn)) { subprog = insn->off; insn[0].imm = (u32)(long)func[subprog]->bpf_func; insn[1].imm = ((u64)(long)func[subprog]->bpf_func) >> 32; continue; } if (!bpf_pseudo_call(insn)) continue; subprog = insn->off; insn->imm = BPF_CALL_IMM(func[subprog]->bpf_func); } /* we use the aux data to keep a list of the start addresses * of the JITed images for each function in the program * * for some architectures, such as powerpc64, the imm field * might not be large enough to hold the offset of the start * address of the callee's JITed image from __bpf_call_base * * in such cases, we can lookup the start address of a callee * by using its subprog id, available from the off field of * the call instruction, as an index for this list */ func[i]->aux->func = func; func[i]->aux->func_cnt = env->subprog_cnt - env->hidden_subprog_cnt; func[i]->aux->real_func_cnt = env->subprog_cnt; } for (i = 0; i < env->subprog_cnt; i++) { old_bpf_func = func[i]->bpf_func; tmp = bpf_int_jit_compile(func[i]); if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) { verbose(env, "JIT doesn't support bpf-to-bpf calls\n"); err = -ENOTSUPP; goto out_free; } cond_resched(); } /* finally lock prog and jit images for all functions and * populate kallsysm. Begin at the first subprogram, since * bpf_prog_load will add the kallsyms for the main program. */ for (i = 1; i < env->subprog_cnt; i++) { err = bpf_prog_lock_ro(func[i]); if (err) goto out_free; } for (i = 1; i < env->subprog_cnt; i++) bpf_prog_kallsyms_add(func[i]); /* Last step: make now unused interpreter insns from main * prog consistent for later dump requests, so they can * later look the same as if they were interpreted only. */ for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { if (bpf_pseudo_func(insn)) { insn[0].imm = env->insn_aux_data[i].call_imm; insn[1].imm = insn->off; insn->off = 0; continue; } if (!bpf_pseudo_call(insn)) continue; insn->off = env->insn_aux_data[i].call_imm; subprog = find_subprog(env, i + insn->off + 1); insn->imm = subprog; } prog->jited = 1; prog->bpf_func = func[0]->bpf_func; prog->jited_len = func[0]->jited_len; prog->aux->extable = func[0]->aux->extable; prog->aux->num_exentries = func[0]->aux->num_exentries; prog->aux->func = func; prog->aux->func_cnt = env->subprog_cnt - env->hidden_subprog_cnt; prog->aux->real_func_cnt = env->subprog_cnt; prog->aux->bpf_exception_cb = (void *)func[env->exception_callback_subprog]->bpf_func; prog->aux->exception_boundary = func[0]->aux->exception_boundary; bpf_prog_jit_attempt_done(prog); return 0; out_free: /* We failed JIT'ing, so at this point we need to unregister poke * descriptors from subprogs, so that kernel is not attempting to * patch it anymore as we're freeing the subprog JIT memory. */ for (i = 0; i < prog->aux->size_poke_tab; i++) { map_ptr = prog->aux->poke_tab[i].tail_call.map; map_ptr->ops->map_poke_untrack(map_ptr, prog->aux); } /* At this point we're guaranteed that poke descriptors are not * live anymore. We can just unlink its descriptor table as it's * released with the main prog. */ for (i = 0; i < env->subprog_cnt; i++) { if (!func[i]) continue; func[i]->aux->poke_tab = NULL; bpf_jit_free(func[i]); } kfree(func); out_undo_insn: /* cleanup main prog to be interpreted */ prog->jit_requested = 0; prog->blinding_requested = 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { if (!bpf_pseudo_call(insn)) continue; insn->off = 0; insn->imm = env->insn_aux_data[i].call_imm; } bpf_prog_jit_attempt_done(prog); return err; } static int fixup_call_args(struct bpf_verifier_env *env) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON struct bpf_prog *prog = env->prog; struct bpf_insn *insn = prog->insnsi; bool has_kfunc_call = bpf_prog_has_kfunc_call(prog); int i, depth; #endif int err = 0; if (env->prog->jit_requested && !bpf_prog_is_offloaded(env->prog->aux)) { err = jit_subprogs(env); if (err == 0) return 0; if (err == -EFAULT) return err; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON if (has_kfunc_call) { verbose(env, "calling kernel functions are not allowed in non-JITed programs\n"); return -EINVAL; } if (env->subprog_cnt > 1 && env->prog->aux->tail_call_reachable) { /* When JIT fails the progs with bpf2bpf calls and tail_calls * have to be rejected, since interpreter doesn't support them yet. */ verbose(env, "tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls\n"); return -EINVAL; } for (i = 0; i < prog->len; i++, insn++) { if (bpf_pseudo_func(insn)) { /* When JIT fails the progs with callback calls * have to be rejected, since interpreter doesn't support them yet. */ verbose(env, "callbacks are not allowed in non-JITed programs\n"); return -EINVAL; } if (!bpf_pseudo_call(insn)) continue; depth = get_callee_stack_depth(env, insn, i); if (depth < 0) return depth; bpf_patch_call_args(insn, depth); } err = 0; #endif return err; } /* replace a generic kfunc with a specialized version if necessary */ static void specialize_kfunc(struct bpf_verifier_env *env, u32 func_id, u16 offset, unsigned long *addr) { struct bpf_prog *prog = env->prog; bool seen_direct_write; void *xdp_kfunc; bool is_rdonly; if (bpf_dev_bound_kfunc_id(func_id)) { xdp_kfunc = bpf_dev_bound_resolve_kfunc(prog, func_id); if (xdp_kfunc) { *addr = (unsigned long)xdp_kfunc; return; } /* fallback to default kfunc when not supported by netdev */ } if (offset) return; if (func_id == special_kfunc_list[KF_bpf_dynptr_from_skb]) { seen_direct_write = env->seen_direct_write; is_rdonly = !may_access_direct_pkt_data(env, NULL, BPF_WRITE); if (is_rdonly) *addr = (unsigned long)bpf_dynptr_from_skb_rdonly; /* restore env->seen_direct_write to its original value, since * may_access_direct_pkt_data mutates it */ env->seen_direct_write = seen_direct_write; } } static void __fixup_collection_insert_kfunc(struct bpf_insn_aux_data *insn_aux, u16 struct_meta_reg, u16 node_offset_reg, struct bpf_insn *insn, struct bpf_insn *insn_buf, int *cnt) { struct btf_struct_meta *kptr_struct_meta = insn_aux->kptr_struct_meta; struct bpf_insn addr[2] = { BPF_LD_IMM64(struct_meta_reg, (long)kptr_struct_meta) }; insn_buf[0] = addr[0]; insn_buf[1] = addr[1]; insn_buf[2] = BPF_MOV64_IMM(node_offset_reg, insn_aux->insert_off); insn_buf[3] = *insn; *cnt = 4; } static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_insn *insn_buf, int insn_idx, int *cnt) { const struct bpf_kfunc_desc *desc; if (!insn->imm) { verbose(env, "invalid kernel function call not eliminated in verifier pass\n"); return -EINVAL; } *cnt = 0; /* insn->imm has the btf func_id. Replace it with an offset relative to * __bpf_call_base, unless the JIT needs to call functions that are * further than 32 bits away (bpf_jit_supports_far_kfunc_call()). */ desc = find_kfunc_desc(env->prog, insn->imm, insn->off); if (!desc) { verbose(env, "verifier internal error: kernel function descriptor not found for func_id %u\n", insn->imm); return -EFAULT; } if (!bpf_jit_supports_far_kfunc_call()) insn->imm = BPF_CALL_IMM(desc->addr); if (insn->off) return 0; if (desc->func_id == special_kfunc_list[KF_bpf_obj_new_impl] || desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) { struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta; struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) }; u64 obj_new_size = env->insn_aux_data[insn_idx].obj_new_size; if (desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl] && kptr_struct_meta) { verbose(env, "verifier internal error: NULL kptr_struct_meta expected at insn_idx %d\n", insn_idx); return -EFAULT; } insn_buf[0] = BPF_MOV64_IMM(BPF_REG_1, obj_new_size); insn_buf[1] = addr[0]; insn_buf[2] = addr[1]; insn_buf[3] = *insn; *cnt = 4; } else if (desc->func_id == special_kfunc_list[KF_bpf_obj_drop_impl] || desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl] || desc->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) { struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta; struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) }; if (desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl] && kptr_struct_meta) { verbose(env, "verifier internal error: NULL kptr_struct_meta expected at insn_idx %d\n", insn_idx); return -EFAULT; } if (desc->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl] && !kptr_struct_meta) { verbose(env, "verifier internal error: kptr_struct_meta expected at insn_idx %d\n", insn_idx); return -EFAULT; } insn_buf[0] = addr[0]; insn_buf[1] = addr[1]; insn_buf[2] = *insn; *cnt = 3; } else if (desc->func_id == special_kfunc_list[KF_bpf_list_push_back_impl] || desc->func_id == special_kfunc_list[KF_bpf_list_push_front_impl] || desc->func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) { struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta; int struct_meta_reg = BPF_REG_3; int node_offset_reg = BPF_REG_4; /* rbtree_add has extra 'less' arg, so args-to-fixup are in diff regs */ if (desc->func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) { struct_meta_reg = BPF_REG_4; node_offset_reg = BPF_REG_5; } if (!kptr_struct_meta) { verbose(env, "verifier internal error: kptr_struct_meta expected at insn_idx %d\n", insn_idx); return -EFAULT; } __fixup_collection_insert_kfunc(&env->insn_aux_data[insn_idx], struct_meta_reg, node_offset_reg, insn, insn_buf, cnt); } else if (desc->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx] || desc->func_id == special_kfunc_list[KF_bpf_rdonly_cast]) { insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1); *cnt = 1; } else if (is_bpf_wq_set_callback_impl_kfunc(desc->func_id)) { struct bpf_insn ld_addrs[2] = { BPF_LD_IMM64(BPF_REG_4, (long)env->prog->aux) }; insn_buf[0] = ld_addrs[0]; insn_buf[1] = ld_addrs[1]; insn_buf[2] = *insn; *cnt = 3; } return 0; } /* The function requires that first instruction in 'patch' is insnsi[prog->len - 1] */ static int add_hidden_subprog(struct bpf_verifier_env *env, struct bpf_insn *patch, int len) { struct bpf_subprog_info *info = env->subprog_info; int cnt = env->subprog_cnt; struct bpf_prog *prog; /* We only reserve one slot for hidden subprogs in subprog_info. */ if (env->hidden_subprog_cnt) { verbose(env, "verifier internal error: only one hidden subprog supported\n"); return -EFAULT; } /* We're not patching any existing instruction, just appending the new * ones for the hidden subprog. Hence all of the adjustment operations * in bpf_patch_insn_data are no-ops. */ prog = bpf_patch_insn_data(env, env->prog->len - 1, patch, len); if (!prog) return -ENOMEM; env->prog = prog; info[cnt + 1].start = info[cnt].start; info[cnt].start = prog->len - len + 1; env->subprog_cnt++; env->hidden_subprog_cnt++; return 0; } /* Do various post-verification rewrites in a single program pass. * These rewrites simplify JIT and interpreter implementations. */ static int do_misc_fixups(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; enum bpf_attach_type eatype = prog->expected_attach_type; enum bpf_prog_type prog_type = resolve_prog_type(prog); struct bpf_insn *insn = prog->insnsi; const struct bpf_func_proto *fn; const int insn_cnt = prog->len; const struct bpf_map_ops *ops; struct bpf_insn_aux_data *aux; struct bpf_insn insn_buf[16]; struct bpf_prog *new_prog; struct bpf_map *map_ptr; int i, ret, cnt, delta = 0, cur_subprog = 0; struct bpf_subprog_info *subprogs = env->subprog_info; u16 stack_depth = subprogs[cur_subprog].stack_depth; u16 stack_depth_extra = 0; if (env->seen_exception && !env->exception_callback_subprog) { struct bpf_insn patch[] = { env->prog->insnsi[insn_cnt - 1], BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), BPF_EXIT_INSN(), }; ret = add_hidden_subprog(env, patch, ARRAY_SIZE(patch)); if (ret < 0) return ret; prog = env->prog; insn = prog->insnsi; env->exception_callback_subprog = env->subprog_cnt - 1; /* Don't update insn_cnt, as add_hidden_subprog always appends insns */ mark_subprog_exc_cb(env, env->exception_callback_subprog); } for (i = 0; i < insn_cnt;) { if (insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->imm) { if ((insn->off == BPF_ADDR_SPACE_CAST && insn->imm == 1) || (((struct bpf_map *)env->prog->aux->arena)->map_flags & BPF_F_NO_USER_CONV)) { /* convert to 32-bit mov that clears upper 32-bit */ insn->code = BPF_ALU | BPF_MOV | BPF_X; /* clear off and imm, so it's a normal 'wX = wY' from JIT pov */ insn->off = 0; insn->imm = 0; } /* cast from as(0) to as(1) should be handled by JIT */ goto next_insn; } if (env->insn_aux_data[i + delta].needs_zext) /* Convert BPF_CLASS(insn->code) == BPF_ALU64 to 32-bit ALU */ insn->code = BPF_ALU | BPF_OP(insn->code) | BPF_SRC(insn->code); /* Make divide-by-zero exceptions impossible. */ if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) || insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) || insn->code == (BPF_ALU | BPF_MOD | BPF_X) || insn->code == (BPF_ALU | BPF_DIV | BPF_X)) { bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; bool isdiv = BPF_OP(insn->code) == BPF_DIV; struct bpf_insn *patchlet; struct bpf_insn chk_and_div[] = { /* [R,W]x div 0 -> 0 */ BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | BPF_JNE | BPF_K, insn->src_reg, 0, 2, 0), BPF_ALU32_REG(BPF_XOR, insn->dst_reg, insn->dst_reg), BPF_JMP_IMM(BPF_JA, 0, 0, 1), *insn, }; struct bpf_insn chk_and_mod[] = { /* [R,W]x mod 0 -> [R,W]x */ BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | BPF_JEQ | BPF_K, insn->src_reg, 0, 1 + (is64 ? 0 : 1), 0), *insn, BPF_JMP_IMM(BPF_JA, 0, 0, 1), BPF_MOV32_REG(insn->dst_reg, insn->dst_reg), }; patchlet = isdiv ? chk_and_div : chk_and_mod; cnt = isdiv ? ARRAY_SIZE(chk_and_div) : ARRAY_SIZE(chk_and_mod) - (is64 ? 2 : 0); new_prog = bpf_patch_insn_data(env, i + delta, patchlet, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Make it impossible to de-reference a userspace address */ if (BPF_CLASS(insn->code) == BPF_LDX && (BPF_MODE(insn->code) == BPF_PROBE_MEM || BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) { struct bpf_insn *patch = &insn_buf[0]; u64 uaddress_limit = bpf_arch_uaddress_limit(); if (!uaddress_limit) goto next_insn; *patch++ = BPF_MOV64_REG(BPF_REG_AX, insn->src_reg); if (insn->off) *patch++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_AX, insn->off); *patch++ = BPF_ALU64_IMM(BPF_RSH, BPF_REG_AX, 32); *patch++ = BPF_JMP_IMM(BPF_JLE, BPF_REG_AX, uaddress_limit >> 32, 2); *patch++ = *insn; *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); *patch++ = BPF_MOV64_IMM(insn->dst_reg, 0); cnt = patch - insn_buf; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Implement LD_ABS and LD_IND with a rewrite, if supported by the program type. */ if (BPF_CLASS(insn->code) == BPF_LD && (BPF_MODE(insn->code) == BPF_ABS || BPF_MODE(insn->code) == BPF_IND)) { cnt = env->ops->gen_ld_abs(insn, insn_buf); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Rewrite pointer arithmetic to mitigate speculation attacks. */ if (insn->code == (BPF_ALU64 | BPF_ADD | BPF_X) || insn->code == (BPF_ALU64 | BPF_SUB | BPF_X)) { const u8 code_add = BPF_ALU64 | BPF_ADD | BPF_X; const u8 code_sub = BPF_ALU64 | BPF_SUB | BPF_X; struct bpf_insn *patch = &insn_buf[0]; bool issrc, isneg, isimm; u32 off_reg; aux = &env->insn_aux_data[i + delta]; if (!aux->alu_state || aux->alu_state == BPF_ALU_NON_POINTER) goto next_insn; isneg = aux->alu_state & BPF_ALU_NEG_VALUE; issrc = (aux->alu_state & BPF_ALU_SANITIZE) == BPF_ALU_SANITIZE_SRC; isimm = aux->alu_state & BPF_ALU_IMMEDIATE; off_reg = issrc ? insn->src_reg : insn->dst_reg; if (isimm) { *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit); } else { if (isneg) *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit); *patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg); *patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg); *patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0); *patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63); *patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX, off_reg); } if (!issrc) *patch++ = BPF_MOV64_REG(insn->dst_reg, insn->src_reg); insn->src_reg = BPF_REG_AX; if (isneg) insn->code = insn->code == code_add ? code_sub : code_add; *patch++ = *insn; if (issrc && isneg && !isimm) *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); cnt = patch - insn_buf; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } if (is_may_goto_insn(insn)) { int stack_off = -stack_depth - 8; stack_depth_extra = 8; insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_AX, BPF_REG_10, stack_off); if (insn->off >= 0) insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 2); else insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off - 1); insn_buf[2] = BPF_ALU64_IMM(BPF_SUB, BPF_REG_AX, 1); insn_buf[3] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_AX, stack_off); cnt = 4; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } if (insn->code != (BPF_JMP | BPF_CALL)) goto next_insn; if (insn->src_reg == BPF_PSEUDO_CALL) goto next_insn; if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { ret = fixup_kfunc_call(env, insn, insn_buf, i + delta, &cnt); if (ret) return ret; if (cnt == 0) goto next_insn; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Skip inlining the helper call if the JIT does it. */ if (bpf_jit_inlines_helper_call(insn->imm)) goto next_insn; if (insn->imm == BPF_FUNC_get_route_realm) prog->dst_needed = 1; if (insn->imm == BPF_FUNC_get_prandom_u32) bpf_user_rnd_init_once(); if (insn->imm == BPF_FUNC_override_return) prog->kprobe_override = 1; if (insn->imm == BPF_FUNC_tail_call) { /* If we tail call into other programs, we * cannot make any assumptions since they can * be replaced dynamically during runtime in * the program array. */ prog->cb_access = 1; if (!allow_tail_call_in_subprogs(env)) prog->aux->stack_depth = MAX_BPF_STACK; prog->aux->max_pkt_offset = MAX_PACKET_OFF; /* mark bpf_tail_call as different opcode to avoid * conditional branch in the interpreter for every normal * call and to prevent accidental JITing by JIT compiler * that doesn't support bpf_tail_call yet */ insn->imm = 0; insn->code = BPF_JMP | BPF_TAIL_CALL; aux = &env->insn_aux_data[i + delta]; if (env->bpf_capable && !prog->blinding_requested && prog->jit_requested && !bpf_map_key_poisoned(aux) && !bpf_map_ptr_poisoned(aux) && !bpf_map_ptr_unpriv(aux)) { struct bpf_jit_poke_descriptor desc = { .reason = BPF_POKE_REASON_TAIL_CALL, .tail_call.map = aux->map_ptr_state.map_ptr, .tail_call.key = bpf_map_key_immediate(aux), .insn_idx = i + delta, }; ret = bpf_jit_add_poke_descriptor(prog, &desc); if (ret < 0) { verbose(env, "adding tail call poke descriptor failed\n"); return ret; } insn->imm = ret + 1; goto next_insn; } if (!bpf_map_ptr_unpriv(aux)) goto next_insn; /* instead of changing every JIT dealing with tail_call * emit two extra insns: * if (index >= max_entries) goto out; * index &= array->index_mask; * to avoid out-of-bounds cpu speculation */ if (bpf_map_ptr_poisoned(aux)) { verbose(env, "tail_call abusing map_ptr\n"); return -EINVAL; } map_ptr = aux->map_ptr_state.map_ptr; insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3, map_ptr->max_entries, 2); insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3, container_of(map_ptr, struct bpf_array, map)->index_mask); insn_buf[2] = *insn; cnt = 3; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } if (insn->imm == BPF_FUNC_timer_set_callback) { /* The verifier will process callback_fn as many times as necessary * with different maps and the register states prepared by * set_timer_callback_state will be accurate. * * The following use case is valid: * map1 is shared by prog1, prog2, prog3. * prog1 calls bpf_timer_init for some map1 elements * prog2 calls bpf_timer_set_callback for some map1 elements. * Those that were not bpf_timer_init-ed will return -EINVAL. * prog3 calls bpf_timer_start for some map1 elements. * Those that were not both bpf_timer_init-ed and * bpf_timer_set_callback-ed will return -EINVAL. */ struct bpf_insn ld_addrs[2] = { BPF_LD_IMM64(BPF_REG_3, (long)prog->aux), }; insn_buf[0] = ld_addrs[0]; insn_buf[1] = ld_addrs[1]; insn_buf[2] = *insn; cnt = 3; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto patch_call_imm; } if (is_storage_get_function(insn->imm)) { if (!in_sleepable(env) || env->insn_aux_data[i + delta].storage_get_func_atomic) insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_ATOMIC); else insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_KERNEL); insn_buf[1] = *insn; cnt = 2; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto patch_call_imm; } /* bpf_per_cpu_ptr() and bpf_this_cpu_ptr() */ if (env->insn_aux_data[i + delta].call_with_percpu_alloc_ptr) { /* patch with 'r1 = *(u64 *)(r1 + 0)' since for percpu data, * bpf_mem_alloc() returns a ptr to the percpu data ptr. */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0); insn_buf[1] = *insn; cnt = 2; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto patch_call_imm; } /* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup * and other inlining handlers are currently limited to 64 bit * only. */ if (prog->jit_requested && BITS_PER_LONG == 64 && (insn->imm == BPF_FUNC_map_lookup_elem || insn->imm == BPF_FUNC_map_update_elem || insn->imm == BPF_FUNC_map_delete_elem || insn->imm == BPF_FUNC_map_push_elem || insn->imm == BPF_FUNC_map_pop_elem || insn->imm == BPF_FUNC_map_peek_elem || insn->imm == BPF_FUNC_redirect_map || insn->imm == BPF_FUNC_for_each_map_elem || insn->imm == BPF_FUNC_map_lookup_percpu_elem)) { aux = &env->insn_aux_data[i + delta]; if (bpf_map_ptr_poisoned(aux)) goto patch_call_imm; map_ptr = aux->map_ptr_state.map_ptr; ops = map_ptr->ops; if (insn->imm == BPF_FUNC_map_lookup_elem && ops->map_gen_lookup) { cnt = ops->map_gen_lookup(map_ptr, insn_buf); if (cnt == -EOPNOTSUPP) goto patch_map_ops_generic; if (cnt <= 0 || cnt >= ARRAY_SIZE(insn_buf)) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } BUILD_BUG_ON(!__same_type(ops->map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); BUILD_BUG_ON(!__same_type(ops->map_delete_elem, (long (*)(struct bpf_map *map, void *key))NULL)); BUILD_BUG_ON(!__same_type(ops->map_update_elem, (long (*)(struct bpf_map *map, void *key, void *value, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_push_elem, (long (*)(struct bpf_map *map, void *value, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_pop_elem, (long (*)(struct bpf_map *map, void *value))NULL)); BUILD_BUG_ON(!__same_type(ops->map_peek_elem, (long (*)(struct bpf_map *map, void *value))NULL)); BUILD_BUG_ON(!__same_type(ops->map_redirect, (long (*)(struct bpf_map *map, u64 index, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_for_each_callback, (long (*)(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_lookup_percpu_elem, (void *(*)(struct bpf_map *map, void *key, u32 cpu))NULL)); patch_map_ops_generic: switch (insn->imm) { case BPF_FUNC_map_lookup_elem: insn->imm = BPF_CALL_IMM(ops->map_lookup_elem); goto next_insn; case BPF_FUNC_map_update_elem: insn->imm = BPF_CALL_IMM(ops->map_update_elem); goto next_insn; case BPF_FUNC_map_delete_elem: insn->imm = BPF_CALL_IMM(ops->map_delete_elem); goto next_insn; case BPF_FUNC_map_push_elem: insn->imm = BPF_CALL_IMM(ops->map_push_elem); goto next_insn; case BPF_FUNC_map_pop_elem: insn->imm = BPF_CALL_IMM(ops->map_pop_elem); goto next_insn; case BPF_FUNC_map_peek_elem: insn->imm = BPF_CALL_IMM(ops->map_peek_elem); goto next_insn; case BPF_FUNC_redirect_map: insn->imm = BPF_CALL_IMM(ops->map_redirect); goto next_insn; case BPF_FUNC_for_each_map_elem: insn->imm = BPF_CALL_IMM(ops->map_for_each_callback); goto next_insn; case BPF_FUNC_map_lookup_percpu_elem: insn->imm = BPF_CALL_IMM(ops->map_lookup_percpu_elem); goto next_insn; } goto patch_call_imm; } /* Implement bpf_jiffies64 inline. */ if (prog->jit_requested && BITS_PER_LONG == 64 && insn->imm == BPF_FUNC_jiffies64) { struct bpf_insn ld_jiffies_addr[2] = { BPF_LD_IMM64(BPF_REG_0, (unsigned long)&jiffies), }; insn_buf[0] = ld_jiffies_addr[0]; insn_buf[1] = ld_jiffies_addr[1]; insn_buf[2] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0); cnt = 3; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } #if defined(CONFIG_X86_64) && !defined(CONFIG_UML) /* Implement bpf_get_smp_processor_id() inline. */ if (insn->imm == BPF_FUNC_get_smp_processor_id && prog->jit_requested && bpf_jit_supports_percpu_insn()) { /* BPF_FUNC_get_smp_processor_id inlining is an * optimization, so if pcpu_hot.cpu_number is ever * changed in some incompatible and hard to support * way, it's fine to back out this inlining logic */ insn_buf[0] = BPF_MOV32_IMM(BPF_REG_0, (u32)(unsigned long)&pcpu_hot.cpu_number); insn_buf[1] = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0); insn_buf[2] = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0); cnt = 3; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } #endif /* Implement bpf_get_func_arg inline. */ if (prog_type == BPF_PROG_TYPE_TRACING && insn->imm == BPF_FUNC_get_func_arg) { /* Load nr_args from ctx - 8 */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); insn_buf[1] = BPF_JMP32_REG(BPF_JGE, BPF_REG_2, BPF_REG_0, 6); insn_buf[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 3); insn_buf[3] = BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1); insn_buf[4] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0); insn_buf[5] = BPF_STX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0); insn_buf[6] = BPF_MOV64_IMM(BPF_REG_0, 0); insn_buf[7] = BPF_JMP_A(1); insn_buf[8] = BPF_MOV64_IMM(BPF_REG_0, -EINVAL); cnt = 9; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Implement bpf_get_func_ret inline. */ if (prog_type == BPF_PROG_TYPE_TRACING && insn->imm == BPF_FUNC_get_func_ret) { if (eatype == BPF_TRACE_FEXIT || eatype == BPF_MODIFY_RETURN) { /* Load nr_args from ctx - 8 */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); insn_buf[1] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3); insn_buf[2] = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1); insn_buf[3] = BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0); insn_buf[4] = BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_3, 0); insn_buf[5] = BPF_MOV64_IMM(BPF_REG_0, 0); cnt = 6; } else { insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, -EOPNOTSUPP); cnt = 1; } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Implement get_func_arg_cnt inline. */ if (prog_type == BPF_PROG_TYPE_TRACING && insn->imm == BPF_FUNC_get_func_arg_cnt) { /* Load nr_args from ctx - 8 */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1); if (!new_prog) return -ENOMEM; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Implement bpf_get_func_ip inline. */ if (prog_type == BPF_PROG_TYPE_TRACING && insn->imm == BPF_FUNC_get_func_ip) { /* Load IP address from ctx - 16 */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -16); new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1); if (!new_prog) return -ENOMEM; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Implement bpf_get_branch_snapshot inline. */ if (IS_ENABLED(CONFIG_PERF_EVENTS) && prog->jit_requested && BITS_PER_LONG == 64 && insn->imm == BPF_FUNC_get_branch_snapshot) { /* We are dealing with the following func protos: * u64 bpf_get_branch_snapshot(void *buf, u32 size, u64 flags); * int perf_snapshot_branch_stack(struct perf_branch_entry *entries, u32 cnt); */ const u32 br_entry_size = sizeof(struct perf_branch_entry); /* struct perf_branch_entry is part of UAPI and is * used as an array element, so extremely unlikely to * ever grow or shrink */ BUILD_BUG_ON(br_entry_size != 24); /* if (unlikely(flags)) return -EINVAL */ insn_buf[0] = BPF_JMP_IMM(BPF_JNE, BPF_REG_3, 0, 7); /* Transform size (bytes) into number of entries (cnt = size / 24). * But to avoid expensive division instruction, we implement * divide-by-3 through multiplication, followed by further * division by 8 through 3-bit right shift. * Refer to book "Hacker's Delight, 2nd ed." by Henry S. Warren, Jr., * p. 227, chapter "Unsigned Division by 3" for details and proofs. * * N / 3 <=> M * N / 2^33, where M = (2^33 + 1) / 3 = 0xaaaaaaab. */ insn_buf[1] = BPF_MOV32_IMM(BPF_REG_0, 0xaaaaaaab); insn_buf[2] = BPF_ALU64_REG(BPF_MUL, BPF_REG_2, BPF_REG_0); insn_buf[3] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 36); /* call perf_snapshot_branch_stack implementation */ insn_buf[4] = BPF_EMIT_CALL(static_call_query(perf_snapshot_branch_stack)); /* if (entry_cnt == 0) return -ENOENT */ insn_buf[5] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4); /* return entry_cnt * sizeof(struct perf_branch_entry) */ insn_buf[6] = BPF_ALU32_IMM(BPF_MUL, BPF_REG_0, br_entry_size); insn_buf[7] = BPF_JMP_A(3); /* return -EINVAL; */ insn_buf[8] = BPF_MOV64_IMM(BPF_REG_0, -EINVAL); insn_buf[9] = BPF_JMP_A(1); /* return -ENOENT; */ insn_buf[10] = BPF_MOV64_IMM(BPF_REG_0, -ENOENT); cnt = 11; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } /* Implement bpf_kptr_xchg inline */ if (prog->jit_requested && BITS_PER_LONG == 64 && insn->imm == BPF_FUNC_kptr_xchg && bpf_jit_supports_ptr_xchg()) { insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_2); insn_buf[1] = BPF_ATOMIC_OP(BPF_DW, BPF_XCHG, BPF_REG_1, BPF_REG_0, 0); cnt = 2; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } patch_call_imm: fn = env->ops->get_func_proto(insn->imm, env->prog); /* all functions that have prototype and verifier allowed * programs to call them, must be real in-kernel functions */ if (!fn->func) { verbose(env, "kernel subsystem misconfigured func %s#%d\n", func_id_name(insn->imm), insn->imm); return -EFAULT; } insn->imm = fn->func - __bpf_call_base; next_insn: if (subprogs[cur_subprog + 1].start == i + delta + 1) { subprogs[cur_subprog].stack_depth += stack_depth_extra; subprogs[cur_subprog].stack_extra = stack_depth_extra; cur_subprog++; stack_depth = subprogs[cur_subprog].stack_depth; stack_depth_extra = 0; } i++; insn++; } env->prog->aux->stack_depth = subprogs[0].stack_depth; for (i = 0; i < env->subprog_cnt; i++) { int subprog_start = subprogs[i].start; int stack_slots = subprogs[i].stack_extra / 8; if (!stack_slots) continue; if (stack_slots > 1) { verbose(env, "verifier bug: stack_slots supports may_goto only\n"); return -EFAULT; } /* Add ST insn to subprog prologue to init extra stack */ insn_buf[0] = BPF_ST_MEM(BPF_DW, BPF_REG_FP, -subprogs[i].stack_depth, BPF_MAX_LOOPS); /* Copy first actual insn to preserve it */ insn_buf[1] = env->prog->insnsi[subprog_start]; new_prog = bpf_patch_insn_data(env, subprog_start, insn_buf, 2); if (!new_prog) return -ENOMEM; env->prog = prog = new_prog; /* * If may_goto is a first insn of a prog there could be a jmp * insn that points to it, hence adjust all such jmps to point * to insn after BPF_ST that inits may_goto count. * Adjustment will succeed because bpf_patch_insn_data() didn't fail. */ WARN_ON(adjust_jmp_off(env->prog, subprog_start, 1)); } /* Since poke tab is now finalized, publish aux to tracker. */ for (i = 0; i < prog->aux->size_poke_tab; i++) { map_ptr = prog->aux->poke_tab[i].tail_call.map; if (!map_ptr->ops->map_poke_track || !map_ptr->ops->map_poke_untrack || !map_ptr->ops->map_poke_run) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } ret = map_ptr->ops->map_poke_track(map_ptr, prog->aux); if (ret < 0) { verbose(env, "tracking tail call prog failed\n"); return ret; } } sort_kfunc_descs_by_imm_off(env->prog); return 0; } static struct bpf_prog *inline_bpf_loop(struct bpf_verifier_env *env, int position, s32 stack_base, u32 callback_subprogno, u32 *cnt) { s32 r6_offset = stack_base + 0 * BPF_REG_SIZE; s32 r7_offset = stack_base + 1 * BPF_REG_SIZE; s32 r8_offset = stack_base + 2 * BPF_REG_SIZE; int reg_loop_max = BPF_REG_6; int reg_loop_cnt = BPF_REG_7; int reg_loop_ctx = BPF_REG_8; struct bpf_prog *new_prog; u32 callback_start; u32 call_insn_offset; s32 callback_offset; /* This represents an inlined version of bpf_iter.c:bpf_loop, * be careful to modify this code in sync. */ struct bpf_insn insn_buf[] = { /* Return error and jump to the end of the patch if * expected number of iterations is too big. */ BPF_JMP_IMM(BPF_JLE, BPF_REG_1, BPF_MAX_LOOPS, 2), BPF_MOV32_IMM(BPF_REG_0, -E2BIG), BPF_JMP_IMM(BPF_JA, 0, 0, 16), /* spill R6, R7, R8 to use these as loop vars */ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, r6_offset), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_7, r7_offset), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_8, r8_offset), /* initialize loop vars */ BPF_MOV64_REG(reg_loop_max, BPF_REG_1), BPF_MOV32_IMM(reg_loop_cnt, 0), BPF_MOV64_REG(reg_loop_ctx, BPF_REG_3), /* loop header, * if reg_loop_cnt >= reg_loop_max skip the loop body */ BPF_JMP_REG(BPF_JGE, reg_loop_cnt, reg_loop_max, 5), /* callback call, * correct callback offset would be set after patching */ BPF_MOV64_REG(BPF_REG_1, reg_loop_cnt), BPF_MOV64_REG(BPF_REG_2, reg_loop_ctx), BPF_CALL_REL(0), /* increment loop counter */ BPF_ALU64_IMM(BPF_ADD, reg_loop_cnt, 1), /* jump to loop header if callback returned 0 */ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -6), /* return value of bpf_loop, * set R0 to the number of iterations */ BPF_MOV64_REG(BPF_REG_0, reg_loop_cnt), /* restore original values of R6, R7, R8 */ BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_10, r6_offset), BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, r7_offset), BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_10, r8_offset), }; *cnt = ARRAY_SIZE(insn_buf); new_prog = bpf_patch_insn_data(env, position, insn_buf, *cnt); if (!new_prog) return new_prog; /* callback start is known only after patching */ callback_start = env->subprog_info[callback_subprogno].start; /* Note: insn_buf[12] is an offset of BPF_CALL_REL instruction */ call_insn_offset = position + 12; callback_offset = callback_start - call_insn_offset - 1; new_prog->insnsi[call_insn_offset].imm = callback_offset; return new_prog; } static bool is_bpf_loop_call(struct bpf_insn *insn) { return insn->code == (BPF_JMP | BPF_CALL) && insn->src_reg == 0 && insn->imm == BPF_FUNC_loop; } /* For all sub-programs in the program (including main) check * insn_aux_data to see if there are bpf_loop calls that require * inlining. If such calls are found the calls are replaced with a * sequence of instructions produced by `inline_bpf_loop` function and * subprog stack_depth is increased by the size of 3 registers. * This stack space is used to spill values of the R6, R7, R8. These * registers are used to store the loop bound, counter and context * variables. */ static int optimize_bpf_loop(struct bpf_verifier_env *env) { struct bpf_subprog_info *subprogs = env->subprog_info; int i, cur_subprog = 0, cnt, delta = 0; struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; u16 stack_depth = subprogs[cur_subprog].stack_depth; u16 stack_depth_roundup = round_up(stack_depth, 8) - stack_depth; u16 stack_depth_extra = 0; for (i = 0; i < insn_cnt; i++, insn++) { struct bpf_loop_inline_state *inline_state = &env->insn_aux_data[i + delta].loop_inline_state; if (is_bpf_loop_call(insn) && inline_state->fit_for_inline) { struct bpf_prog *new_prog; stack_depth_extra = BPF_REG_SIZE * 3 + stack_depth_roundup; new_prog = inline_bpf_loop(env, i + delta, -(stack_depth + stack_depth_extra), inline_state->callback_subprogno, &cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = new_prog; insn = new_prog->insnsi + i + delta; } if (subprogs[cur_subprog + 1].start == i + delta + 1) { subprogs[cur_subprog].stack_depth += stack_depth_extra; cur_subprog++; stack_depth = subprogs[cur_subprog].stack_depth; stack_depth_roundup = round_up(stack_depth, 8) - stack_depth; stack_depth_extra = 0; } } env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return 0; } static void free_states(struct bpf_verifier_env *env) { struct bpf_verifier_state_list *sl, *sln; int i; sl = env->free_list; while (sl) { sln = sl->next; free_verifier_state(&sl->state, false); kfree(sl); sl = sln; } env->free_list = NULL; if (!env->explored_states) return; for (i = 0; i < state_htab_size(env); i++) { sl = env->explored_states[i]; while (sl) { sln = sl->next; free_verifier_state(&sl->state, false); kfree(sl); sl = sln; } env->explored_states[i] = NULL; } } static int do_check_common(struct bpf_verifier_env *env, int subprog) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); struct bpf_subprog_info *sub = subprog_info(env, subprog); struct bpf_verifier_state *state; struct bpf_reg_state *regs; int ret, i; env->prev_linfo = NULL; env->pass_cnt++; state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL); if (!state) return -ENOMEM; state->curframe = 0; state->speculative = false; state->branches = 1; state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL); if (!state->frame[0]) { kfree(state); return -ENOMEM; } env->cur_state = state; init_func_state(env, state->frame[0], BPF_MAIN_FUNC /* callsite */, 0 /* frameno */, subprog); state->first_insn_idx = env->subprog_info[subprog].start; state->last_insn_idx = -1; regs = state->frame[state->curframe]->regs; if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) { const char *sub_name = subprog_name(env, subprog); struct bpf_subprog_arg_info *arg; struct bpf_reg_state *reg; verbose(env, "Validating %s() func#%d...\n", sub_name, subprog); ret = btf_prepare_func_args(env, subprog); if (ret) goto out; if (subprog_is_exc_cb(env, subprog)) { state->frame[0]->in_exception_callback_fn = true; /* We have already ensured that the callback returns an integer, just * like all global subprogs. We need to determine it only has a single * scalar argument. */ if (sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_ANYTHING) { verbose(env, "exception cb only supports single integer argument\n"); ret = -EINVAL; goto out; } } for (i = BPF_REG_1; i <= sub->arg_cnt; i++) { arg = &sub->args[i - BPF_REG_1]; reg = ®s[i]; if (arg->arg_type == ARG_PTR_TO_CTX) { reg->type = PTR_TO_CTX; mark_reg_known_zero(env, regs, i); } else if (arg->arg_type == ARG_ANYTHING) { reg->type = SCALAR_VALUE; mark_reg_unknown(env, regs, i); } else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) { /* assume unspecial LOCAL dynptr type */ __mark_dynptr_reg(reg, BPF_DYNPTR_TYPE_LOCAL, true, ++env->id_gen); } else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) { reg->type = PTR_TO_MEM; if (arg->arg_type & PTR_MAYBE_NULL) reg->type |= PTR_MAYBE_NULL; mark_reg_known_zero(env, regs, i); reg->mem_size = arg->mem_size; reg->id = ++env->id_gen; } else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) { reg->type = PTR_TO_BTF_ID; if (arg->arg_type & PTR_MAYBE_NULL) reg->type |= PTR_MAYBE_NULL; if (arg->arg_type & PTR_UNTRUSTED) reg->type |= PTR_UNTRUSTED; if (arg->arg_type & PTR_TRUSTED) reg->type |= PTR_TRUSTED; mark_reg_known_zero(env, regs, i); reg->btf = bpf_get_btf_vmlinux(); /* can't fail at this point */ reg->btf_id = arg->btf_id; reg->id = ++env->id_gen; } else if (base_type(arg->arg_type) == ARG_PTR_TO_ARENA) { /* caller can pass either PTR_TO_ARENA or SCALAR */ mark_reg_unknown(env, regs, i); } else { WARN_ONCE(1, "BUG: unhandled arg#%d type %d\n", i - BPF_REG_1, arg->arg_type); ret = -EFAULT; goto out; } } } else { /* if main BPF program has associated BTF info, validate that * it's matching expected signature, and otherwise mark BTF * info for main program as unreliable */ if (env->prog->aux->func_info_aux) { ret = btf_prepare_func_args(env, 0); if (ret || sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_PTR_TO_CTX) env->prog->aux->func_info_aux[0].unreliable = true; } /* 1st arg to a function */ regs[BPF_REG_1].type = PTR_TO_CTX; mark_reg_known_zero(env, regs, BPF_REG_1); } ret = do_check(env); out: /* check for NULL is necessary, since cur_state can be freed inside * do_check() under memory pressure. */ if (env->cur_state) { free_verifier_state(env->cur_state, true); env->cur_state = NULL; } while (!pop_stack(env, NULL, NULL, false)); if (!ret && pop_log) bpf_vlog_reset(&env->log, 0); free_states(env); return ret; } /* Lazily verify all global functions based on their BTF, if they are called * from main BPF program or any of subprograms transitively. * BPF global subprogs called from dead code are not validated. * All callable global functions must pass verification. * Otherwise the whole program is rejected. * Consider: * int bar(int); * int foo(int f) * { * return bar(f); * } * int bar(int b) * { * ... * } * foo() will be verified first for R1=any_scalar_value. During verification it * will be assumed that bar() already verified successfully and call to bar() * from foo() will be checked for type match only. Later bar() will be verified * independently to check that it's safe for R1=any_scalar_value. */ static int do_check_subprogs(struct bpf_verifier_env *env) { struct bpf_prog_aux *aux = env->prog->aux; struct bpf_func_info_aux *sub_aux; int i, ret, new_cnt; if (!aux->func_info) return 0; /* exception callback is presumed to be always called */ if (env->exception_callback_subprog) subprog_aux(env, env->exception_callback_subprog)->called = true; again: new_cnt = 0; for (i = 1; i < env->subprog_cnt; i++) { if (!subprog_is_global(env, i)) continue; sub_aux = subprog_aux(env, i); if (!sub_aux->called || sub_aux->verified) continue; env->insn_idx = env->subprog_info[i].start; WARN_ON_ONCE(env->insn_idx == 0); ret = do_check_common(env, i); if (ret) { return ret; } else if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "Func#%d ('%s') is safe for any args that match its prototype\n", i, subprog_name(env, i)); } /* We verified new global subprog, it might have called some * more global subprogs that we haven't verified yet, so we * need to do another pass over subprogs to verify those. */ sub_aux->verified = true; new_cnt++; } /* We can't loop forever as we verify at least one global subprog on * each pass. */ if (new_cnt) goto again; return 0; } static int do_check_main(struct bpf_verifier_env *env) { int ret; env->insn_idx = 0; ret = do_check_common(env, 0); if (!ret) env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return ret; } static void print_verification_stats(struct bpf_verifier_env *env) { int i; if (env->log.level & BPF_LOG_STATS) { verbose(env, "verification time %lld usec\n", div_u64(env->verification_time, 1000)); verbose(env, "stack depth "); for (i = 0; i < env->subprog_cnt; i++) { u32 depth = env->subprog_info[i].stack_depth; verbose(env, "%d", depth); if (i + 1 < env->subprog_cnt) verbose(env, "+"); } verbose(env, "\n"); } verbose(env, "processed %d insns (limit %d) max_states_per_insn %d " "total_states %d peak_states %d mark_read %d\n", env->insn_processed, BPF_COMPLEXITY_LIMIT_INSNS, env->max_states_per_insn, env->total_states, env->peak_states, env->longest_mark_read_walk); } static int check_struct_ops_btf_id(struct bpf_verifier_env *env) { const struct btf_type *t, *func_proto; const struct bpf_struct_ops_desc *st_ops_desc; const struct bpf_struct_ops *st_ops; const struct btf_member *member; struct bpf_prog *prog = env->prog; u32 btf_id, member_idx; struct btf *btf; const char *mname; if (!prog->gpl_compatible) { verbose(env, "struct ops programs must have a GPL compatible license\n"); return -EINVAL; } if (!prog->aux->attach_btf_id) return -ENOTSUPP; btf = prog->aux->attach_btf; if (btf_is_module(btf)) { /* Make sure st_ops is valid through the lifetime of env */ env->attach_btf_mod = btf_try_get_module(btf); if (!env->attach_btf_mod) { verbose(env, "struct_ops module %s is not found\n", btf_get_name(btf)); return -ENOTSUPP; } } btf_id = prog->aux->attach_btf_id; st_ops_desc = bpf_struct_ops_find(btf, btf_id); if (!st_ops_desc) { verbose(env, "attach_btf_id %u is not a supported struct\n", btf_id); return -ENOTSUPP; } st_ops = st_ops_desc->st_ops; t = st_ops_desc->type; member_idx = prog->expected_attach_type; if (member_idx >= btf_type_vlen(t)) { verbose(env, "attach to invalid member idx %u of struct %s\n", member_idx, st_ops->name); return -EINVAL; } member = &btf_type_member(t)[member_idx]; mname = btf_name_by_offset(btf, member->name_off); func_proto = btf_type_resolve_func_ptr(btf, member->type, NULL); if (!func_proto) { verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n", mname, member_idx, st_ops->name); return -EINVAL; } if (st_ops->check_member) { int err = st_ops->check_member(t, member, prog); if (err) { verbose(env, "attach to unsupported member %s of struct %s\n", mname, st_ops->name); return err; } } /* btf_ctx_access() used this to provide argument type info */ prog->aux->ctx_arg_info = st_ops_desc->arg_info[member_idx].info; prog->aux->ctx_arg_info_size = st_ops_desc->arg_info[member_idx].cnt; prog->aux->attach_func_proto = func_proto; prog->aux->attach_func_name = mname; env->ops = st_ops->verifier_ops; return 0; } #define SECURITY_PREFIX "security_" static int check_attach_modify_return(unsigned long addr, const char *func_name) { if (within_error_injection_list(addr) || !strncmp(SECURITY_PREFIX, func_name, sizeof(SECURITY_PREFIX) - 1)) return 0; return -EINVAL; } /* list of non-sleepable functions that are otherwise on * ALLOW_ERROR_INJECTION list */ BTF_SET_START(btf_non_sleepable_error_inject) /* Three functions below can be called from sleepable and non-sleepable context. * Assume non-sleepable from bpf safety point of view. */ BTF_ID(func, __filemap_add_folio) BTF_ID(func, should_fail_alloc_page) BTF_ID(func, should_failslab) BTF_SET_END(btf_non_sleepable_error_inject) static int check_non_sleepable_error_inject(u32 btf_id) { return btf_id_set_contains(&btf_non_sleepable_error_inject, btf_id); } int bpf_check_attach_target(struct bpf_verifier_log *log, const struct bpf_prog *prog, const struct bpf_prog *tgt_prog, u32 btf_id, struct bpf_attach_target_info *tgt_info) { bool prog_extension = prog->type == BPF_PROG_TYPE_EXT; bool prog_tracing = prog->type == BPF_PROG_TYPE_TRACING; const char prefix[] = "btf_trace_"; int ret = 0, subprog = -1, i; const struct btf_type *t; bool conservative = true; const char *tname; struct btf *btf; long addr = 0; struct module *mod = NULL; if (!btf_id) { bpf_log(log, "Tracing programs must provide btf_id\n"); return -EINVAL; } btf = tgt_prog ? tgt_prog->aux->btf : prog->aux->attach_btf; if (!btf) { bpf_log(log, "FENTRY/FEXIT program can only be attached to another program annotated with BTF\n"); return -EINVAL; } t = btf_type_by_id(btf, btf_id); if (!t) { bpf_log(log, "attach_btf_id %u is invalid\n", btf_id); return -EINVAL; } tname = btf_name_by_offset(btf, t->name_off); if (!tname) { bpf_log(log, "attach_btf_id %u doesn't have a name\n", btf_id); return -EINVAL; } if (tgt_prog) { struct bpf_prog_aux *aux = tgt_prog->aux; if (bpf_prog_is_dev_bound(prog->aux) && !bpf_prog_dev_bound_match(prog, tgt_prog)) { bpf_log(log, "Target program bound device mismatch"); return -EINVAL; } for (i = 0; i < aux->func_info_cnt; i++) if (aux->func_info[i].type_id == btf_id) { subprog = i; break; } if (subprog == -1) { bpf_log(log, "Subprog %s doesn't exist\n", tname); return -EINVAL; } if (aux->func && aux->func[subprog]->aux->exception_cb) { bpf_log(log, "%s programs cannot attach to exception callback\n", prog_extension ? "Extension" : "FENTRY/FEXIT"); return -EINVAL; } conservative = aux->func_info_aux[subprog].unreliable; if (prog_extension) { if (conservative) { bpf_log(log, "Cannot replace static functions\n"); return -EINVAL; } if (!prog->jit_requested) { bpf_log(log, "Extension programs should be JITed\n"); return -EINVAL; } } if (!tgt_prog->jited) { bpf_log(log, "Can attach to only JITed progs\n"); return -EINVAL; } if (prog_tracing) { if (aux->attach_tracing_prog) { /* * Target program is an fentry/fexit which is already attached * to another tracing program. More levels of nesting * attachment are not allowed. */ bpf_log(log, "Cannot nest tracing program attach more than once\n"); return -EINVAL; } } else if (tgt_prog->type == prog->type) { /* * To avoid potential call chain cycles, prevent attaching of a * program extension to another extension. It's ok to attach * fentry/fexit to extension program. */ bpf_log(log, "Cannot recursively attach\n"); return -EINVAL; } if (tgt_prog->type == BPF_PROG_TYPE_TRACING && prog_extension && (tgt_prog->expected_attach_type == BPF_TRACE_FENTRY || tgt_prog->expected_attach_type == BPF_TRACE_FEXIT)) { /* Program extensions can extend all program types * except fentry/fexit. The reason is the following. * The fentry/fexit programs are used for performance * analysis, stats and can be attached to any program * type. When extension program is replacing XDP function * it is necessary to allow performance analysis of all * functions. Both original XDP program and its program * extension. Hence attaching fentry/fexit to * BPF_PROG_TYPE_EXT is allowed. If extending of * fentry/fexit was allowed it would be possible to create * long call chain fentry->extension->fentry->extension * beyond reasonable stack size. Hence extending fentry * is not allowed. */ bpf_log(log, "Cannot extend fentry/fexit\n"); return -EINVAL; } } else { if (prog_extension) { bpf_log(log, "Cannot replace kernel functions\n"); return -EINVAL; } } switch (prog->expected_attach_type) { case BPF_TRACE_RAW_TP: if (tgt_prog) { bpf_log(log, "Only FENTRY/FEXIT progs are attachable to another BPF prog\n"); return -EINVAL; } if (!btf_type_is_typedef(t)) { bpf_log(log, "attach_btf_id %u is not a typedef\n", btf_id); return -EINVAL; } if (strncmp(prefix, tname, sizeof(prefix) - 1)) { bpf_log(log, "attach_btf_id %u points to wrong type name %s\n", btf_id, tname); return -EINVAL; } tname += sizeof(prefix) - 1; t = btf_type_by_id(btf, t->type); if (!btf_type_is_ptr(t)) /* should never happen in valid vmlinux build */ return -EINVAL; t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) /* should never happen in valid vmlinux build */ return -EINVAL; break; case BPF_TRACE_ITER: if (!btf_type_is_func(t)) { bpf_log(log, "attach_btf_id %u is not a function\n", btf_id); return -EINVAL; } t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) return -EINVAL; ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel); if (ret) return ret; break; default: if (!prog_extension) return -EINVAL; fallthrough; case BPF_MODIFY_RETURN: case BPF_LSM_MAC: case BPF_LSM_CGROUP: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: if (!btf_type_is_func(t)) { bpf_log(log, "attach_btf_id %u is not a function\n", btf_id); return -EINVAL; } if (prog_extension && btf_check_type_match(log, prog, btf, t)) return -EINVAL; t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) return -EINVAL; if ((prog->aux->saved_dst_prog_type || prog->aux->saved_dst_attach_type) && (!tgt_prog || prog->aux->saved_dst_prog_type != tgt_prog->type || prog->aux->saved_dst_attach_type != tgt_prog->expected_attach_type)) return -EINVAL; if (tgt_prog && conservative) t = NULL; ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel); if (ret < 0) return ret; if (tgt_prog) { if (subprog == 0) addr = (long) tgt_prog->bpf_func; else addr = (long) tgt_prog->aux->func[subprog]->bpf_func; } else { if (btf_is_module(btf)) { mod = btf_try_get_module(btf); if (mod) addr = find_kallsyms_symbol_value(mod, tname); else addr = 0; } else { addr = kallsyms_lookup_name(tname); } if (!addr) { module_put(mod); bpf_log(log, "The address of function %s cannot be found\n", tname); return -ENOENT; } } if (prog->sleepable) { ret = -EINVAL; switch (prog->type) { case BPF_PROG_TYPE_TRACING: /* fentry/fexit/fmod_ret progs can be sleepable if they are * attached to ALLOW_ERROR_INJECTION and are not in denylist. */ if (!check_non_sleepable_error_inject(btf_id) && within_error_injection_list(addr)) ret = 0; /* fentry/fexit/fmod_ret progs can also be sleepable if they are * in the fmodret id set with the KF_SLEEPABLE flag. */ else { u32 *flags = btf_kfunc_is_modify_return(btf, btf_id, prog); if (flags && (*flags & KF_SLEEPABLE)) ret = 0; } break; case BPF_PROG_TYPE_LSM: /* LSM progs check that they are attached to bpf_lsm_*() funcs. * Only some of them are sleepable. */ if (bpf_lsm_is_sleepable_hook(btf_id)) ret = 0; break; default: break; } if (ret) { module_put(mod); bpf_log(log, "%s is not sleepable\n", tname); return ret; } } else if (prog->expected_attach_type == BPF_MODIFY_RETURN) { if (tgt_prog) { module_put(mod); bpf_log(log, "can't modify return codes of BPF programs\n"); return -EINVAL; } ret = -EINVAL; if (btf_kfunc_is_modify_return(btf, btf_id, prog) || !check_attach_modify_return(addr, tname)) ret = 0; if (ret) { module_put(mod); bpf_log(log, "%s() is not modifiable\n", tname); return ret; } } break; } tgt_info->tgt_addr = addr; tgt_info->tgt_name = tname; tgt_info->tgt_type = t; tgt_info->tgt_mod = mod; return 0; } BTF_SET_START(btf_id_deny) BTF_ID_UNUSED #ifdef CONFIG_SMP BTF_ID(func, migrate_disable) BTF_ID(func, migrate_enable) #endif #if !defined CONFIG_PREEMPT_RCU && !defined CONFIG_TINY_RCU BTF_ID(func, rcu_read_unlock_strict) #endif #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_TRACE_PREEMPT_TOGGLE) BTF_ID(func, preempt_count_add) BTF_ID(func, preempt_count_sub) #endif #ifdef CONFIG_PREEMPT_RCU BTF_ID(func, __rcu_read_lock) BTF_ID(func, __rcu_read_unlock) #endif BTF_SET_END(btf_id_deny) static bool can_be_sleepable(struct bpf_prog *prog) { if (prog->type == BPF_PROG_TYPE_TRACING) { switch (prog->expected_attach_type) { case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_MODIFY_RETURN: case BPF_TRACE_ITER: return true; default: return false; } } return prog->type == BPF_PROG_TYPE_LSM || prog->type == BPF_PROG_TYPE_KPROBE /* only for uprobes */ || prog->type == BPF_PROG_TYPE_STRUCT_OPS; } static int check_attach_btf_id(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; struct bpf_prog *tgt_prog = prog->aux->dst_prog; struct bpf_attach_target_info tgt_info = {}; u32 btf_id = prog->aux->attach_btf_id; struct bpf_trampoline *tr; int ret; u64 key; if (prog->type == BPF_PROG_TYPE_SYSCALL) { if (prog->sleepable) /* attach_btf_id checked to be zero already */ return 0; verbose(env, "Syscall programs can only be sleepable\n"); return -EINVAL; } if (prog->sleepable && !can_be_sleepable(prog)) { verbose(env, "Only fentry/fexit/fmod_ret, lsm, iter, uprobe, and struct_ops programs can be sleepable\n"); return -EINVAL; } if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) return check_struct_ops_btf_id(env); if (prog->type != BPF_PROG_TYPE_TRACING && prog->type != BPF_PROG_TYPE_LSM && prog->type != BPF_PROG_TYPE_EXT) return 0; ret = bpf_check_attach_target(&env->log, prog, tgt_prog, btf_id, &tgt_info); if (ret) return ret; if (tgt_prog && prog->type == BPF_PROG_TYPE_EXT) { /* to make freplace equivalent to their targets, they need to * inherit env->ops and expected_attach_type for the rest of the * verification */ env->ops = bpf_verifier_ops[tgt_prog->type]; prog->expected_attach_type = tgt_prog->expected_attach_type; } /* store info about the attachment target that will be used later */ prog->aux->attach_func_proto = tgt_info.tgt_type; prog->aux->attach_func_name = tgt_info.tgt_name; prog->aux->mod = tgt_info.tgt_mod; if (tgt_prog) { prog->aux->saved_dst_prog_type = tgt_prog->type; prog->aux->saved_dst_attach_type = tgt_prog->expected_attach_type; } if (prog->expected_attach_type == BPF_TRACE_RAW_TP) { prog->aux->attach_btf_trace = true; return 0; } else if (prog->expected_attach_type == BPF_TRACE_ITER) { if (!bpf_iter_prog_supported(prog)) return -EINVAL; return 0; } if (prog->type == BPF_PROG_TYPE_LSM) { ret = bpf_lsm_verify_prog(&env->log, prog); if (ret < 0) return ret; } else if (prog->type == BPF_PROG_TYPE_TRACING && btf_id_set_contains(&btf_id_deny, btf_id)) { return -EINVAL; } key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id); tr = bpf_trampoline_get(key, &tgt_info); if (!tr) return -ENOMEM; if (tgt_prog && tgt_prog->aux->tail_call_reachable) tr->flags = BPF_TRAMP_F_TAIL_CALL_CTX; prog->aux->dst_trampoline = tr; return 0; } struct btf *bpf_get_btf_vmlinux(void) { if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { mutex_lock(&bpf_verifier_lock); if (!btf_vmlinux) btf_vmlinux = btf_parse_vmlinux(); mutex_unlock(&bpf_verifier_lock); } return btf_vmlinux; } int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { u64 start_time = ktime_get_ns(); struct bpf_verifier_env *env; int i, len, ret = -EINVAL, err; u32 log_true_size; bool is_priv; /* no program is valid */ if (ARRAY_SIZE(bpf_verifier_ops) == 0) return -EINVAL; /* 'struct bpf_verifier_env' can be global, but since it's not small, * allocate/free it every time bpf_check() is called */ env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL); if (!env) return -ENOMEM; env->bt.env = env; len = (*prog)->len; env->insn_aux_data = vzalloc(array_size(sizeof(struct bpf_insn_aux_data), len)); ret = -ENOMEM; if (!env->insn_aux_data) goto err_free_env; for (i = 0; i < len; i++) env->insn_aux_data[i].orig_idx = i; env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel); env->allow_ptr_leaks = bpf_allow_ptr_leaks(env->prog->aux->token); env->allow_uninit_stack = bpf_allow_uninit_stack(env->prog->aux->token); env->bypass_spec_v1 = bpf_bypass_spec_v1(env->prog->aux->token); env->bypass_spec_v4 = bpf_bypass_spec_v4(env->prog->aux->token); env->bpf_capable = is_priv = bpf_token_capable(env->prog->aux->token, CAP_BPF); bpf_get_btf_vmlinux(); /* grab the mutex to protect few globals used by verifier */ if (!is_priv) mutex_lock(&bpf_verifier_lock); /* user could have requested verbose verifier output * and supplied buffer to store the verification trace */ ret = bpf_vlog_init(&env->log, attr->log_level, (char __user *) (unsigned long) attr->log_buf, attr->log_size); if (ret) goto err_unlock; mark_verifier_state_clean(env); if (IS_ERR(btf_vmlinux)) { /* Either gcc or pahole or kernel are broken. */ verbose(env, "in-kernel BTF is malformed\n"); ret = PTR_ERR(btf_vmlinux); goto skip_full_check; } env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT); if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; if (attr->prog_flags & BPF_F_ANY_ALIGNMENT) env->strict_alignment = false; if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS; env->explored_states = kvcalloc(state_htab_size(env), sizeof(struct bpf_verifier_state_list *), GFP_USER); ret = -ENOMEM; if (!env->explored_states) goto skip_full_check; ret = check_btf_info_early(env, attr, uattr); if (ret < 0) goto skip_full_check; ret = add_subprog_and_kfunc(env); if (ret < 0) goto skip_full_check; ret = check_subprogs(env); if (ret < 0) goto skip_full_check; ret = check_btf_info(env, attr, uattr); if (ret < 0) goto skip_full_check; ret = check_attach_btf_id(env); if (ret) goto skip_full_check; ret = resolve_pseudo_ldimm64(env); if (ret < 0) goto skip_full_check; if (bpf_prog_is_offloaded(env->prog->aux)) { ret = bpf_prog_offload_verifier_prep(env->prog); if (ret) goto skip_full_check; } ret = check_cfg(env); if (ret < 0) goto skip_full_check; ret = do_check_main(env); ret = ret ?: do_check_subprogs(env); if (ret == 0 && bpf_prog_is_offloaded(env->prog->aux)) ret = bpf_prog_offload_finalize(env); skip_full_check: kvfree(env->explored_states); if (ret == 0) ret = check_max_stack_depth(env); /* instruction rewrites happen after this point */ if (ret == 0) ret = optimize_bpf_loop(env); if (is_priv) { if (ret == 0) opt_hard_wire_dead_code_branches(env); if (ret == 0) ret = opt_remove_dead_code(env); if (ret == 0) ret = opt_remove_nops(env); } else { if (ret == 0) sanitize_dead_code(env); } if (ret == 0) /* program is valid, convert *(u32*)(ctx + off) accesses */ ret = convert_ctx_accesses(env); if (ret == 0) ret = do_misc_fixups(env); /* do 32-bit optimization after insn patching has done so those patched * insns could be handled correctly. */ if (ret == 0 && !bpf_prog_is_offloaded(env->prog->aux)) { ret = opt_subreg_zext_lo32_rnd_hi32(env, attr); env->prog->aux->verifier_zext = bpf_jit_needs_zext() ? !ret : false; } if (ret == 0) ret = fixup_call_args(env); env->verification_time = ktime_get_ns() - start_time; print_verification_stats(env); env->prog->aux->verified_insns = env->insn_processed; /* preserve original error even if log finalization is successful */ err = bpf_vlog_finalize(&env->log, &log_true_size); if (err) ret = err; if (uattr_size >= offsetofend(union bpf_attr, log_true_size) && copy_to_bpfptr_offset(uattr, offsetof(union bpf_attr, log_true_size), &log_true_size, sizeof(log_true_size))) { ret = -EFAULT; goto err_release_maps; } if (ret) goto err_release_maps; if (env->used_map_cnt) { /* if program passed verifier, update used_maps in bpf_prog_info */ env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt, sizeof(env->used_maps[0]), GFP_KERNEL); if (!env->prog->aux->used_maps) { ret = -ENOMEM; goto err_release_maps; } memcpy(env->prog->aux->used_maps, env->used_maps, sizeof(env->used_maps[0]) * env->used_map_cnt); env->prog->aux->used_map_cnt = env->used_map_cnt; } if (env->used_btf_cnt) { /* if program passed verifier, update used_btfs in bpf_prog_aux */ env->prog->aux->used_btfs = kmalloc_array(env->used_btf_cnt, sizeof(env->used_btfs[0]), GFP_KERNEL); if (!env->prog->aux->used_btfs) { ret = -ENOMEM; goto err_release_maps; } memcpy(env->prog->aux->used_btfs, env->used_btfs, sizeof(env->used_btfs[0]) * env->used_btf_cnt); env->prog->aux->used_btf_cnt = env->used_btf_cnt; } if (env->used_map_cnt || env->used_btf_cnt) { /* program is valid. Convert pseudo bpf_ld_imm64 into generic * bpf_ld_imm64 instructions */ convert_pseudo_ld_imm64(env); } adjust_btf_func(env); err_release_maps: if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release * them now. Otherwise free_used_maps() will release them. */ release_maps(env); if (!env->prog->aux->used_btfs) release_btfs(env); /* extension progs temporarily inherit the attach_type of their targets for verification purposes, so set it back to zero before returning */ if (env->prog->type == BPF_PROG_TYPE_EXT) env->prog->expected_attach_type = 0; *prog = env->prog; module_put(env->attach_btf_mod); err_unlock: if (!is_priv) mutex_unlock(&bpf_verifier_lock); vfree(env->insn_aux_data); err_free_env: kfree(env); return ret; } |
| 1 1 1 1 1 1 1 6 6 6 1 6 1 1 6 6 2 2 2 1 2 1 1 1 1 1 1 1 1 4 2 2 2 2 4 3 3 3 3 1 6 6 6 3 3 3 4 4 4 4 3 1 1 4 3 3 3 1 1 3 3 6 6 6 6 3 5 3 3 3 3 3 3 3 2 2 3 3 3 3 3 3 3 3 6 6 3 3 9 9 9 9 9 9 2 9 2 2 9 9 9 9 9 9 9 9 5 2 2 2 1 2 9 1 1 1 1 8 8 8 8 8 8 1 2 8 6 6 6 3 4 4 2 2 8 8 1 1 1 1 1 8 2 2 2 2 1 1 1 1 2 2 1 1 1 1 1 1 3 3 3 2 1 1 1 1 5 4 5 2 2 1 1 6 4 3 6 6 2 2 2 2 2 2 2 2 2 2 2 3 3 1 2 1 2 2 1 2 2 2 2 2 2 2 2 2 1 1 1 1 4 4 4 7 3 3 1 1 4 5 4 4 1 3 3 2 2 2 3 3 3 3 4 4 4 2 4 4 4 3 4 4 4 4 1 4 4 1 4 4 4 4 3 3 3 3 3 3 3 3 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Kernel Connection Multiplexor * * Copyright (c) 2016 Tom Herbert <tom@herbertland.com> */ #include <linux/bpf.h> #include <linux/errno.h> #include <linux/errqueue.h> #include <linux/file.h> #include <linux/filter.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/poll.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/uaccess.h> #include <linux/workqueue.h> #include <linux/syscalls.h> #include <linux/sched/signal.h> #include <net/kcm.h> #include <net/netns/generic.h> #include <net/sock.h> #include <uapi/linux/kcm.h> #include <trace/events/sock.h> unsigned int kcm_net_id; static struct kmem_cache *kcm_psockp __read_mostly; static struct kmem_cache *kcm_muxp __read_mostly; static struct workqueue_struct *kcm_wq; static inline struct kcm_sock *kcm_sk(const struct sock *sk) { return (struct kcm_sock *)sk; } static inline struct kcm_tx_msg *kcm_tx_msg(struct sk_buff *skb) { return (struct kcm_tx_msg *)skb->cb; } static void report_csk_error(struct sock *csk, int err) { csk->sk_err = EPIPE; sk_error_report(csk); } static void kcm_abort_tx_psock(struct kcm_psock *psock, int err, bool wakeup_kcm) { struct sock *csk = psock->sk; struct kcm_mux *mux = psock->mux; /* Unrecoverable error in transmit */ spin_lock_bh(&mux->lock); if (psock->tx_stopped) { spin_unlock_bh(&mux->lock); return; } psock->tx_stopped = 1; KCM_STATS_INCR(psock->stats.tx_aborts); if (!psock->tx_kcm) { /* Take off psocks_avail list */ list_del(&psock->psock_avail_list); } else if (wakeup_kcm) { /* In this case psock is being aborted while outside of * write_msgs and psock is reserved. Schedule tx_work * to handle the failure there. Need to commit tx_stopped * before queuing work. */ smp_mb(); queue_work(kcm_wq, &psock->tx_kcm->tx_work); } spin_unlock_bh(&mux->lock); /* Report error on lower socket */ report_csk_error(csk, err); } /* RX mux lock held. */ static void kcm_update_rx_mux_stats(struct kcm_mux *mux, struct kcm_psock *psock) { STRP_STATS_ADD(mux->stats.rx_bytes, psock->strp.stats.bytes - psock->saved_rx_bytes); mux->stats.rx_msgs += psock->strp.stats.msgs - psock->saved_rx_msgs; psock->saved_rx_msgs = psock->strp.stats.msgs; psock->saved_rx_bytes = psock->strp.stats.bytes; } static void kcm_update_tx_mux_stats(struct kcm_mux *mux, struct kcm_psock *psock) { KCM_STATS_ADD(mux->stats.tx_bytes, psock->stats.tx_bytes - psock->saved_tx_bytes); mux->stats.tx_msgs += psock->stats.tx_msgs - psock->saved_tx_msgs; psock->saved_tx_msgs = psock->stats.tx_msgs; psock->saved_tx_bytes = psock->stats.tx_bytes; } static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); /* KCM is ready to receive messages on its queue-- either the KCM is new or * has become unblocked after being blocked on full socket buffer. Queue any * pending ready messages on a psock. RX mux lock held. */ static void kcm_rcv_ready(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; struct kcm_psock *psock; struct sk_buff *skb; if (unlikely(kcm->rx_wait || kcm->rx_psock || kcm->rx_disabled)) return; while (unlikely((skb = __skb_dequeue(&mux->rx_hold_queue)))) { if (kcm_queue_rcv_skb(&kcm->sk, skb)) { /* Assuming buffer limit has been reached */ skb_queue_head(&mux->rx_hold_queue, skb); WARN_ON(!sk_rmem_alloc_get(&kcm->sk)); return; } } while (!list_empty(&mux->psocks_ready)) { psock = list_first_entry(&mux->psocks_ready, struct kcm_psock, psock_ready_list); if (kcm_queue_rcv_skb(&kcm->sk, psock->ready_rx_msg)) { /* Assuming buffer limit has been reached */ WARN_ON(!sk_rmem_alloc_get(&kcm->sk)); return; } /* Consumed the ready message on the psock. Schedule rx_work to * get more messages. */ list_del(&psock->psock_ready_list); psock->ready_rx_msg = NULL; /* Commit clearing of ready_rx_msg for queuing work */ smp_mb(); strp_unpause(&psock->strp); strp_check_rcv(&psock->strp); } /* Buffer limit is okay now, add to ready list */ list_add_tail(&kcm->wait_rx_list, &kcm->mux->kcm_rx_waiters); /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_wait, true); } static void kcm_rfree(struct sk_buff *skb) { struct sock *sk = skb->sk; struct kcm_sock *kcm = kcm_sk(sk); struct kcm_mux *mux = kcm->mux; unsigned int len = skb->truesize; sk_mem_uncharge(sk, len); atomic_sub(len, &sk->sk_rmem_alloc); /* For reading rx_wait and rx_psock without holding lock */ smp_mb__after_atomic(); if (!READ_ONCE(kcm->rx_wait) && !READ_ONCE(kcm->rx_psock) && sk_rmem_alloc_get(sk) < sk->sk_rcvlowat) { spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); spin_unlock_bh(&mux->rx_lock); } } static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct sk_buff_head *list = &sk->sk_receive_queue; if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) return -ENOMEM; if (!sk_rmem_schedule(sk, skb, skb->truesize)) return -ENOBUFS; skb->dev = NULL; skb_orphan(skb); skb->sk = sk; skb->destructor = kcm_rfree; atomic_add(skb->truesize, &sk->sk_rmem_alloc); sk_mem_charge(sk, skb->truesize); skb_queue_tail(list, skb); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); return 0; } /* Requeue received messages for a kcm socket to other kcm sockets. This is * called with a kcm socket is receive disabled. * RX mux lock held. */ static void requeue_rx_msgs(struct kcm_mux *mux, struct sk_buff_head *head) { struct sk_buff *skb; struct kcm_sock *kcm; while ((skb = skb_dequeue(head))) { /* Reset destructor to avoid calling kcm_rcv_ready */ skb->destructor = sock_rfree; skb_orphan(skb); try_again: if (list_empty(&mux->kcm_rx_waiters)) { skb_queue_tail(&mux->rx_hold_queue, skb); continue; } kcm = list_first_entry(&mux->kcm_rx_waiters, struct kcm_sock, wait_rx_list); if (kcm_queue_rcv_skb(&kcm->sk, skb)) { /* Should mean socket buffer full */ list_del(&kcm->wait_rx_list); /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_wait, false); /* Commit rx_wait to read in kcm_free */ smp_wmb(); goto try_again; } } } /* Lower sock lock held */ static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock, struct sk_buff *head) { struct kcm_mux *mux = psock->mux; struct kcm_sock *kcm; WARN_ON(psock->ready_rx_msg); if (psock->rx_kcm) return psock->rx_kcm; spin_lock_bh(&mux->rx_lock); if (psock->rx_kcm) { spin_unlock_bh(&mux->rx_lock); return psock->rx_kcm; } kcm_update_rx_mux_stats(mux, psock); if (list_empty(&mux->kcm_rx_waiters)) { psock->ready_rx_msg = head; strp_pause(&psock->strp); list_add_tail(&psock->psock_ready_list, &mux->psocks_ready); spin_unlock_bh(&mux->rx_lock); return NULL; } kcm = list_first_entry(&mux->kcm_rx_waiters, struct kcm_sock, wait_rx_list); list_del(&kcm->wait_rx_list); /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_wait, false); psock->rx_kcm = kcm; /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_psock, psock); spin_unlock_bh(&mux->rx_lock); return kcm; } static void kcm_done(struct kcm_sock *kcm); static void kcm_done_work(struct work_struct *w) { kcm_done(container_of(w, struct kcm_sock, done_work)); } /* Lower sock held */ static void unreserve_rx_kcm(struct kcm_psock *psock, bool rcv_ready) { struct kcm_sock *kcm = psock->rx_kcm; struct kcm_mux *mux = psock->mux; if (!kcm) return; spin_lock_bh(&mux->rx_lock); psock->rx_kcm = NULL; /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_psock, NULL); /* Commit kcm->rx_psock before sk_rmem_alloc_get to sync with * kcm_rfree */ smp_mb(); if (unlikely(kcm->done)) { spin_unlock_bh(&mux->rx_lock); /* Need to run kcm_done in a task since we need to qcquire * callback locks which may already be held here. */ INIT_WORK(&kcm->done_work, kcm_done_work); schedule_work(&kcm->done_work); return; } if (unlikely(kcm->rx_disabled)) { requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue); } else if (rcv_ready || unlikely(!sk_rmem_alloc_get(&kcm->sk))) { /* Check for degenerative race with rx_wait that all * data was dequeued (accounted for in kcm_rfree). */ kcm_rcv_ready(kcm); } spin_unlock_bh(&mux->rx_lock); } /* Lower sock lock held */ static void psock_data_ready(struct sock *sk) { struct kcm_psock *psock; trace_sk_data_ready(sk); read_lock_bh(&sk->sk_callback_lock); psock = (struct kcm_psock *)sk->sk_user_data; if (likely(psock)) strp_data_ready(&psock->strp); read_unlock_bh(&sk->sk_callback_lock); } /* Called with lower sock held */ static void kcm_rcv_strparser(struct strparser *strp, struct sk_buff *skb) { struct kcm_psock *psock = container_of(strp, struct kcm_psock, strp); struct kcm_sock *kcm; try_queue: kcm = reserve_rx_kcm(psock, skb); if (!kcm) { /* Unable to reserve a KCM, message is held in psock and strp * is paused. */ return; } if (kcm_queue_rcv_skb(&kcm->sk, skb)) { /* Should mean socket buffer full */ unreserve_rx_kcm(psock, false); goto try_queue; } } static int kcm_parse_func_strparser(struct strparser *strp, struct sk_buff *skb) { struct kcm_psock *psock = container_of(strp, struct kcm_psock, strp); struct bpf_prog *prog = psock->bpf_prog; int res; res = bpf_prog_run_pin_on_cpu(prog, skb); return res; } static int kcm_read_sock_done(struct strparser *strp, int err) { struct kcm_psock *psock = container_of(strp, struct kcm_psock, strp); unreserve_rx_kcm(psock, true); return err; } static void psock_state_change(struct sock *sk) { /* TCP only does a EPOLLIN for a half close. Do a EPOLLHUP here * since application will normally not poll with EPOLLIN * on the TCP sockets. */ report_csk_error(sk, EPIPE); } static void psock_write_space(struct sock *sk) { struct kcm_psock *psock; struct kcm_mux *mux; struct kcm_sock *kcm; read_lock_bh(&sk->sk_callback_lock); psock = (struct kcm_psock *)sk->sk_user_data; if (unlikely(!psock)) goto out; mux = psock->mux; spin_lock_bh(&mux->lock); /* Check if the socket is reserved so someone is waiting for sending. */ kcm = psock->tx_kcm; if (kcm && !unlikely(kcm->tx_stopped)) queue_work(kcm_wq, &kcm->tx_work); spin_unlock_bh(&mux->lock); out: read_unlock_bh(&sk->sk_callback_lock); } static void unreserve_psock(struct kcm_sock *kcm); /* kcm sock is locked. */ static struct kcm_psock *reserve_psock(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; struct kcm_psock *psock; psock = kcm->tx_psock; smp_rmb(); /* Must read tx_psock before tx_wait */ if (psock) { WARN_ON(kcm->tx_wait); if (unlikely(psock->tx_stopped)) unreserve_psock(kcm); else return kcm->tx_psock; } spin_lock_bh(&mux->lock); /* Check again under lock to see if psock was reserved for this * psock via psock_unreserve. */ psock = kcm->tx_psock; if (unlikely(psock)) { WARN_ON(kcm->tx_wait); spin_unlock_bh(&mux->lock); return kcm->tx_psock; } if (!list_empty(&mux->psocks_avail)) { psock = list_first_entry(&mux->psocks_avail, struct kcm_psock, psock_avail_list); list_del(&psock->psock_avail_list); if (kcm->tx_wait) { list_del(&kcm->wait_psock_list); kcm->tx_wait = false; } kcm->tx_psock = psock; psock->tx_kcm = kcm; KCM_STATS_INCR(psock->stats.reserved); } else if (!kcm->tx_wait) { list_add_tail(&kcm->wait_psock_list, &mux->kcm_tx_waiters); kcm->tx_wait = true; } spin_unlock_bh(&mux->lock); return psock; } /* mux lock held */ static void psock_now_avail(struct kcm_psock *psock) { struct kcm_mux *mux = psock->mux; struct kcm_sock *kcm; if (list_empty(&mux->kcm_tx_waiters)) { list_add_tail(&psock->psock_avail_list, &mux->psocks_avail); } else { kcm = list_first_entry(&mux->kcm_tx_waiters, struct kcm_sock, wait_psock_list); list_del(&kcm->wait_psock_list); kcm->tx_wait = false; psock->tx_kcm = kcm; /* Commit before changing tx_psock since that is read in * reserve_psock before queuing work. */ smp_mb(); kcm->tx_psock = psock; KCM_STATS_INCR(psock->stats.reserved); queue_work(kcm_wq, &kcm->tx_work); } } /* kcm sock is locked. */ static void unreserve_psock(struct kcm_sock *kcm) { struct kcm_psock *psock; struct kcm_mux *mux = kcm->mux; spin_lock_bh(&mux->lock); psock = kcm->tx_psock; if (WARN_ON(!psock)) { spin_unlock_bh(&mux->lock); return; } smp_rmb(); /* Read tx_psock before tx_wait */ kcm_update_tx_mux_stats(mux, psock); WARN_ON(kcm->tx_wait); kcm->tx_psock = NULL; psock->tx_kcm = NULL; KCM_STATS_INCR(psock->stats.unreserved); if (unlikely(psock->tx_stopped)) { if (psock->done) { /* Deferred free */ list_del(&psock->psock_list); mux->psocks_cnt--; sock_put(psock->sk); fput(psock->sk->sk_socket->file); kmem_cache_free(kcm_psockp, psock); } /* Don't put back on available list */ spin_unlock_bh(&mux->lock); return; } psock_now_avail(psock); spin_unlock_bh(&mux->lock); } static void kcm_report_tx_retry(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; spin_lock_bh(&mux->lock); KCM_STATS_INCR(mux->stats.tx_retries); spin_unlock_bh(&mux->lock); } /* Write any messages ready on the kcm socket. Called with kcm sock lock * held. Return bytes actually sent or error. */ static int kcm_write_msgs(struct kcm_sock *kcm) { unsigned int total_sent = 0; struct sock *sk = &kcm->sk; struct kcm_psock *psock; struct sk_buff *head; int ret = 0; kcm->tx_wait_more = false; psock = kcm->tx_psock; if (unlikely(psock && psock->tx_stopped)) { /* A reserved psock was aborted asynchronously. Unreserve * it and we'll retry the message. */ unreserve_psock(kcm); kcm_report_tx_retry(kcm); if (skb_queue_empty(&sk->sk_write_queue)) return 0; kcm_tx_msg(skb_peek(&sk->sk_write_queue))->started_tx = false; } retry: while ((head = skb_peek(&sk->sk_write_queue))) { struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES, }; struct kcm_tx_msg *txm = kcm_tx_msg(head); struct sk_buff *skb; unsigned int msize; int i; if (!txm->started_tx) { psock = reserve_psock(kcm); if (!psock) goto out; skb = head; txm->frag_offset = 0; txm->sent = 0; txm->started_tx = true; } else { if (WARN_ON(!psock)) { ret = -EINVAL; goto out; } skb = txm->frag_skb; } if (WARN_ON(!skb_shinfo(skb)->nr_frags) || WARN_ON_ONCE(!skb_frag_page(&skb_shinfo(skb)->frags[0]))) { ret = -EINVAL; goto out; } msize = 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) msize += skb_frag_size(&skb_shinfo(skb)->frags[i]); iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, (const struct bio_vec *)skb_shinfo(skb)->frags, skb_shinfo(skb)->nr_frags, msize); iov_iter_advance(&msg.msg_iter, txm->frag_offset); do { ret = sock_sendmsg(psock->sk->sk_socket, &msg); if (ret <= 0) { if (ret == -EAGAIN) { /* Save state to try again when there's * write space on the socket */ txm->frag_skb = skb; ret = 0; goto out; } /* Hard failure in sending message, abort this * psock since it has lost framing * synchronization and retry sending the * message from the beginning. */ kcm_abort_tx_psock(psock, ret ? -ret : EPIPE, true); unreserve_psock(kcm); psock = NULL; txm->started_tx = false; kcm_report_tx_retry(kcm); ret = 0; goto retry; } txm->sent += ret; txm->frag_offset += ret; KCM_STATS_ADD(psock->stats.tx_bytes, ret); } while (msg.msg_iter.count > 0); if (skb == head) { if (skb_has_frag_list(skb)) { txm->frag_skb = skb_shinfo(skb)->frag_list; txm->frag_offset = 0; continue; } } else if (skb->next) { txm->frag_skb = skb->next; txm->frag_offset = 0; continue; } /* Successfully sent the whole packet, account for it. */ sk->sk_wmem_queued -= txm->sent; total_sent += txm->sent; skb_dequeue(&sk->sk_write_queue); kfree_skb(head); KCM_STATS_INCR(psock->stats.tx_msgs); } out: if (!head) { /* Done with all queued messages. */ WARN_ON(!skb_queue_empty(&sk->sk_write_queue)); if (psock) unreserve_psock(kcm); } /* Check if write space is available */ sk->sk_write_space(sk); return total_sent ? : ret; } static void kcm_tx_work(struct work_struct *w) { struct kcm_sock *kcm = container_of(w, struct kcm_sock, tx_work); struct sock *sk = &kcm->sk; int err; lock_sock(sk); /* Primarily for SOCK_DGRAM sockets, also handle asynchronous tx * aborts */ err = kcm_write_msgs(kcm); if (err < 0) { /* Hard failure in write, report error on KCM socket */ pr_warn("KCM: Hard failure on kcm_write_msgs %d\n", err); report_csk_error(&kcm->sk, -err); goto out; } /* Primarily for SOCK_SEQPACKET sockets */ if (likely(sk->sk_socket) && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk->sk_write_space(sk); } out: release_sock(sk); } static void kcm_push(struct kcm_sock *kcm) { if (kcm->tx_wait_more) kcm_write_msgs(kcm); } static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); struct sk_buff *skb = NULL, *head = NULL; size_t copy, copied = 0; long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); int eor = (sock->type == SOCK_DGRAM) ? !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR); int err = -EPIPE; lock_sock(sk); /* Per tcp_sendmsg this should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (sk->sk_err) goto out_error; if (kcm->seq_skb) { /* Previously opened message */ head = kcm->seq_skb; skb = kcm_tx_msg(head)->last_skb; goto start; } /* Call the sk_stream functions to manage the sndbuf mem. */ if (!sk_stream_memory_free(sk)) { kcm_push(kcm); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); err = sk_stream_wait_memory(sk, &timeo); if (err) goto out_error; } if (msg_data_left(msg)) { /* New message, alloc head skb */ head = alloc_skb(0, sk->sk_allocation); while (!head) { kcm_push(kcm); err = sk_stream_wait_memory(sk, &timeo); if (err) goto out_error; head = alloc_skb(0, sk->sk_allocation); } skb = head; /* Set ip_summed to CHECKSUM_UNNECESSARY to avoid calling * csum_and_copy_from_iter from skb_do_copy_data_nocache. */ skb->ip_summed = CHECKSUM_UNNECESSARY; } start: while (msg_data_left(msg)) { bool merge = true; int i = skb_shinfo(skb)->nr_frags; struct page_frag *pfrag = sk_page_frag(sk); if (!sk_page_frag_refill(sk, pfrag)) goto wait_for_memory; if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { if (i == MAX_SKB_FRAGS) { struct sk_buff *tskb; tskb = alloc_skb(0, sk->sk_allocation); if (!tskb) goto wait_for_memory; if (head == skb) skb_shinfo(head)->frag_list = tskb; else skb->next = tskb; skb = tskb; skb->ip_summed = CHECKSUM_UNNECESSARY; continue; } merge = false; } if (msg->msg_flags & MSG_SPLICE_PAGES) { copy = msg_data_left(msg); if (!sk_wmem_schedule(sk, copy)) goto wait_for_memory; err = skb_splice_from_iter(skb, &msg->msg_iter, copy, sk->sk_allocation); if (err < 0) { if (err == -EMSGSIZE) goto wait_for_memory; goto out_error; } copy = err; skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); if (head != skb) head->truesize += copy; } else { copy = min_t(int, msg_data_left(msg), pfrag->size - pfrag->offset); if (!sk_wmem_schedule(sk, copy)) goto wait_for_memory; err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, pfrag->page, pfrag->offset, copy); if (err) goto out_error; /* Update the skb. */ if (merge) { skb_frag_size_add( &skb_shinfo(skb)->frags[i - 1], copy); } else { skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, copy); get_page(pfrag->page); } pfrag->offset += copy; } copied += copy; if (head != skb) { head->len += copy; head->data_len += copy; } continue; wait_for_memory: kcm_push(kcm); err = sk_stream_wait_memory(sk, &timeo); if (err) goto out_error; } if (eor) { bool not_busy = skb_queue_empty(&sk->sk_write_queue); if (head) { /* Message complete, queue it on send buffer */ __skb_queue_tail(&sk->sk_write_queue, head); kcm->seq_skb = NULL; KCM_STATS_INCR(kcm->stats.tx_msgs); } if (msg->msg_flags & MSG_BATCH) { kcm->tx_wait_more = true; } else if (kcm->tx_wait_more || not_busy) { err = kcm_write_msgs(kcm); if (err < 0) { /* We got a hard error in write_msgs but have * already queued this message. Report an error * in the socket, but don't affect return value * from sendmsg */ pr_warn("KCM: Hard failure on kcm_write_msgs\n"); report_csk_error(&kcm->sk, -err); } } } else { /* Message not complete, save state */ partial_message: if (head) { kcm->seq_skb = head; kcm_tx_msg(head)->last_skb = skb; } } KCM_STATS_ADD(kcm->stats.tx_bytes, copied); release_sock(sk); return copied; out_error: kcm_push(kcm); if (sock->type == SOCK_SEQPACKET) { /* Wrote some bytes before encountering an * error, return partial success. */ if (copied) goto partial_message; if (head != kcm->seq_skb) kfree_skb(head); } else { kfree_skb(head); kcm->seq_skb = NULL; } err = sk_stream_error(sk, msg->msg_flags, err); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN)) sk->sk_write_space(sk); release_sock(sk); return err; } static void kcm_splice_eof(struct socket *sock) { struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); if (skb_queue_empty_lockless(&sk->sk_write_queue)) return; lock_sock(sk); kcm_write_msgs(kcm); release_sock(sk); } static int kcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); int err = 0; struct strp_msg *stm; int copied = 0; struct sk_buff *skb; skb = skb_recv_datagram(sk, flags, &err); if (!skb) goto out; /* Okay, have a message on the receive queue */ stm = strp_msg(skb); if (len > stm->full_len) len = stm->full_len; err = skb_copy_datagram_msg(skb, stm->offset, msg, len); if (err < 0) goto out; copied = len; if (likely(!(flags & MSG_PEEK))) { KCM_STATS_ADD(kcm->stats.rx_bytes, copied); if (copied < stm->full_len) { if (sock->type == SOCK_DGRAM) { /* Truncated message */ msg->msg_flags |= MSG_TRUNC; goto msg_finished; } stm->offset += copied; stm->full_len -= copied; } else { msg_finished: /* Finished with message */ msg->msg_flags |= MSG_EOR; KCM_STATS_INCR(kcm->stats.rx_msgs); } } out: skb_free_datagram(sk, skb); return copied ? : err; } static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); struct strp_msg *stm; int err = 0; ssize_t copied; struct sk_buff *skb; /* Only support splice for SOCKSEQPACKET */ skb = skb_recv_datagram(sk, flags, &err); if (!skb) goto err_out; /* Okay, have a message on the receive queue */ stm = strp_msg(skb); if (len > stm->full_len) len = stm->full_len; copied = skb_splice_bits(skb, sk, stm->offset, pipe, len, flags); if (copied < 0) { err = copied; goto err_out; } KCM_STATS_ADD(kcm->stats.rx_bytes, copied); stm->offset += copied; stm->full_len -= copied; /* We have no way to return MSG_EOR. If all the bytes have been * read we still leave the message in the receive socket buffer. * A subsequent recvmsg needs to be done to return MSG_EOR and * finish reading the message. */ skb_free_datagram(sk, skb); return copied; err_out: skb_free_datagram(sk, skb); return err; } /* kcm sock lock held */ static void kcm_recv_disable(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; if (kcm->rx_disabled) return; spin_lock_bh(&mux->rx_lock); kcm->rx_disabled = 1; /* If a psock is reserved we'll do cleanup in unreserve */ if (!kcm->rx_psock) { if (kcm->rx_wait) { list_del(&kcm->wait_rx_list); /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_wait, false); } requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue); } spin_unlock_bh(&mux->rx_lock); } /* kcm sock lock held */ static void kcm_recv_enable(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; if (!kcm->rx_disabled) return; spin_lock_bh(&mux->rx_lock); kcm->rx_disabled = 0; kcm_rcv_ready(kcm); spin_unlock_bh(&mux->rx_lock); } static int kcm_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct kcm_sock *kcm = kcm_sk(sock->sk); int val, valbool; int err = 0; if (level != SOL_KCM) return -ENOPROTOOPT; if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(int))) return -EFAULT; valbool = val ? 1 : 0; switch (optname) { case KCM_RECV_DISABLE: lock_sock(&kcm->sk); if (valbool) kcm_recv_disable(kcm); else kcm_recv_enable(kcm); release_sock(&kcm->sk); break; default: err = -ENOPROTOOPT; } return err; } static int kcm_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct kcm_sock *kcm = kcm_sk(sock->sk); int val, len; if (level != SOL_KCM) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; len = min_t(unsigned int, len, sizeof(int)); switch (optname) { case KCM_RECV_DISABLE: val = kcm->rx_disabled; break; default: return -ENOPROTOOPT; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) { struct kcm_sock *tkcm; struct list_head *head; int index = 0; /* For SOCK_SEQPACKET sock type, datagram_poll checks the sk_state, so * we set sk_state, otherwise epoll_wait always returns right away with * EPOLLHUP */ kcm->sk.sk_state = TCP_ESTABLISHED; /* Add to mux's kcm sockets list */ kcm->mux = mux; spin_lock_bh(&mux->lock); head = &mux->kcm_socks; list_for_each_entry(tkcm, &mux->kcm_socks, kcm_sock_list) { if (tkcm->index != index) break; head = &tkcm->kcm_sock_list; index++; } list_add(&kcm->kcm_sock_list, head); kcm->index = index; mux->kcm_socks_cnt++; spin_unlock_bh(&mux->lock); INIT_WORK(&kcm->tx_work, kcm_tx_work); spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); spin_unlock_bh(&mux->rx_lock); } static int kcm_attach(struct socket *sock, struct socket *csock, struct bpf_prog *prog) { struct kcm_sock *kcm = kcm_sk(sock->sk); struct kcm_mux *mux = kcm->mux; struct sock *csk; struct kcm_psock *psock = NULL, *tpsock; struct list_head *head; int index = 0; static const struct strp_callbacks cb = { .rcv_msg = kcm_rcv_strparser, .parse_msg = kcm_parse_func_strparser, .read_sock_done = kcm_read_sock_done, }; int err = 0; csk = csock->sk; if (!csk) return -EINVAL; lock_sock(csk); /* Only allow TCP sockets to be attached for now */ if ((csk->sk_family != AF_INET && csk->sk_family != AF_INET6) || csk->sk_protocol != IPPROTO_TCP) { err = -EOPNOTSUPP; goto out; } /* Don't allow listeners or closed sockets */ if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE) { err = -EOPNOTSUPP; goto out; } psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL); if (!psock) { err = -ENOMEM; goto out; } psock->mux = mux; psock->sk = csk; psock->bpf_prog = prog; write_lock_bh(&csk->sk_callback_lock); /* Check if sk_user_data is already by KCM or someone else. * Must be done under lock to prevent race conditions. */ if (csk->sk_user_data) { write_unlock_bh(&csk->sk_callback_lock); kmem_cache_free(kcm_psockp, psock); err = -EALREADY; goto out; } err = strp_init(&psock->strp, csk, &cb); if (err) { write_unlock_bh(&csk->sk_callback_lock); kmem_cache_free(kcm_psockp, psock); goto out; } psock->save_data_ready = csk->sk_data_ready; psock->save_write_space = csk->sk_write_space; psock->save_state_change = csk->sk_state_change; csk->sk_user_data = psock; csk->sk_data_ready = psock_data_ready; csk->sk_write_space = psock_write_space; csk->sk_state_change = psock_state_change; write_unlock_bh(&csk->sk_callback_lock); sock_hold(csk); /* Finished initialization, now add the psock to the MUX. */ spin_lock_bh(&mux->lock); head = &mux->psocks; list_for_each_entry(tpsock, &mux->psocks, psock_list) { if (tpsock->index != index) break; head = &tpsock->psock_list; index++; } list_add(&psock->psock_list, head); psock->index = index; KCM_STATS_INCR(mux->stats.psock_attach); mux->psocks_cnt++; psock_now_avail(psock); spin_unlock_bh(&mux->lock); /* Schedule RX work in case there are already bytes queued */ strp_check_rcv(&psock->strp); out: release_sock(csk); return err; } static int kcm_attach_ioctl(struct socket *sock, struct kcm_attach *info) { struct socket *csock; struct bpf_prog *prog; int err; csock = sockfd_lookup(info->fd, &err); if (!csock) return -ENOENT; prog = bpf_prog_get_type(info->bpf_fd, BPF_PROG_TYPE_SOCKET_FILTER); if (IS_ERR(prog)) { err = PTR_ERR(prog); goto out; } err = kcm_attach(sock, csock, prog); if (err) { bpf_prog_put(prog); goto out; } /* Keep reference on file also */ return 0; out: sockfd_put(csock); return err; } static void kcm_unattach(struct kcm_psock *psock) { struct sock *csk = psock->sk; struct kcm_mux *mux = psock->mux; lock_sock(csk); /* Stop getting callbacks from TCP socket. After this there should * be no way to reserve a kcm for this psock. */ write_lock_bh(&csk->sk_callback_lock); csk->sk_user_data = NULL; csk->sk_data_ready = psock->save_data_ready; csk->sk_write_space = psock->save_write_space; csk->sk_state_change = psock->save_state_change; strp_stop(&psock->strp); if (WARN_ON(psock->rx_kcm)) { write_unlock_bh(&csk->sk_callback_lock); release_sock(csk); return; } spin_lock_bh(&mux->rx_lock); /* Stop receiver activities. After this point psock should not be * able to get onto ready list either through callbacks or work. */ if (psock->ready_rx_msg) { list_del(&psock->psock_ready_list); kfree_skb(psock->ready_rx_msg); psock->ready_rx_msg = NULL; KCM_STATS_INCR(mux->stats.rx_ready_drops); } spin_unlock_bh(&mux->rx_lock); write_unlock_bh(&csk->sk_callback_lock); /* Call strp_done without sock lock */ release_sock(csk); strp_done(&psock->strp); lock_sock(csk); bpf_prog_put(psock->bpf_prog); spin_lock_bh(&mux->lock); aggregate_psock_stats(&psock->stats, &mux->aggregate_psock_stats); save_strp_stats(&psock->strp, &mux->aggregate_strp_stats); KCM_STATS_INCR(mux->stats.psock_unattach); if (psock->tx_kcm) { /* psock was reserved. Just mark it finished and we will clean * up in the kcm paths, we need kcm lock which can not be * acquired here. */ KCM_STATS_INCR(mux->stats.psock_unattach_rsvd); spin_unlock_bh(&mux->lock); /* We are unattaching a socket that is reserved. Abort the * socket since we may be out of sync in sending on it. We need * to do this without the mux lock. */ kcm_abort_tx_psock(psock, EPIPE, false); spin_lock_bh(&mux->lock); if (!psock->tx_kcm) { /* psock now unreserved in window mux was unlocked */ goto no_reserved; } psock->done = 1; /* Commit done before queuing work to process it */ smp_mb(); /* Queue tx work to make sure psock->done is handled */ queue_work(kcm_wq, &psock->tx_kcm->tx_work); spin_unlock_bh(&mux->lock); } else { no_reserved: if (!psock->tx_stopped) list_del(&psock->psock_avail_list); list_del(&psock->psock_list); mux->psocks_cnt--; spin_unlock_bh(&mux->lock); sock_put(csk); fput(csk->sk_socket->file); kmem_cache_free(kcm_psockp, psock); } release_sock(csk); } static int kcm_unattach_ioctl(struct socket *sock, struct kcm_unattach *info) { struct kcm_sock *kcm = kcm_sk(sock->sk); struct kcm_mux *mux = kcm->mux; struct kcm_psock *psock; struct socket *csock; struct sock *csk; int err; csock = sockfd_lookup(info->fd, &err); if (!csock) return -ENOENT; csk = csock->sk; if (!csk) { err = -EINVAL; goto out; } err = -ENOENT; spin_lock_bh(&mux->lock); list_for_each_entry(psock, &mux->psocks, psock_list) { if (psock->sk != csk) continue; /* Found the matching psock */ if (psock->unattaching || WARN_ON(psock->done)) { err = -EALREADY; break; } psock->unattaching = 1; spin_unlock_bh(&mux->lock); /* Lower socket lock should already be held */ kcm_unattach(psock); err = 0; goto out; } spin_unlock_bh(&mux->lock); out: sockfd_put(csock); return err; } static struct proto kcm_proto = { .name = "KCM", .owner = THIS_MODULE, .obj_size = sizeof(struct kcm_sock), }; /* Clone a kcm socket. */ static struct file *kcm_clone(struct socket *osock) { struct socket *newsock; struct sock *newsk; newsock = sock_alloc(); if (!newsock) return ERR_PTR(-ENFILE); newsock->type = osock->type; newsock->ops = osock->ops; __module_get(newsock->ops->owner); newsk = sk_alloc(sock_net(osock->sk), PF_KCM, GFP_KERNEL, &kcm_proto, false); if (!newsk) { sock_release(newsock); return ERR_PTR(-ENOMEM); } sock_init_data(newsock, newsk); init_kcm_sock(kcm_sk(newsk), kcm_sk(osock->sk)->mux); return sock_alloc_file(newsock, 0, osock->sk->sk_prot_creator->name); } static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { int err; switch (cmd) { case SIOCKCMATTACH: { struct kcm_attach info; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) return -EFAULT; err = kcm_attach_ioctl(sock, &info); break; } case SIOCKCMUNATTACH: { struct kcm_unattach info; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) return -EFAULT; err = kcm_unattach_ioctl(sock, &info); break; } case SIOCKCMCLONE: { struct kcm_clone info; struct file *file; info.fd = get_unused_fd_flags(0); if (unlikely(info.fd < 0)) return info.fd; file = kcm_clone(sock); if (IS_ERR(file)) { put_unused_fd(info.fd); return PTR_ERR(file); } if (copy_to_user((void __user *)arg, &info, sizeof(info))) { put_unused_fd(info.fd); fput(file); return -EFAULT; } fd_install(info.fd, file); err = 0; break; } default: err = -ENOIOCTLCMD; break; } return err; } static void free_mux(struct rcu_head *rcu) { struct kcm_mux *mux = container_of(rcu, struct kcm_mux, rcu); kmem_cache_free(kcm_muxp, mux); } static void release_mux(struct kcm_mux *mux) { struct kcm_net *knet = mux->knet; struct kcm_psock *psock, *tmp_psock; /* Release psocks */ list_for_each_entry_safe(psock, tmp_psock, &mux->psocks, psock_list) { if (!WARN_ON(psock->unattaching)) kcm_unattach(psock); } if (WARN_ON(mux->psocks_cnt)) return; __skb_queue_purge(&mux->rx_hold_queue); mutex_lock(&knet->mutex); aggregate_mux_stats(&mux->stats, &knet->aggregate_mux_stats); aggregate_psock_stats(&mux->aggregate_psock_stats, &knet->aggregate_psock_stats); aggregate_strp_stats(&mux->aggregate_strp_stats, &knet->aggregate_strp_stats); list_del_rcu(&mux->kcm_mux_list); knet->count--; mutex_unlock(&knet->mutex); call_rcu(&mux->rcu, free_mux); } static void kcm_done(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; struct sock *sk = &kcm->sk; int socks_cnt; spin_lock_bh(&mux->rx_lock); if (kcm->rx_psock) { /* Cleanup in unreserve_rx_kcm */ WARN_ON(kcm->done); kcm->rx_disabled = 1; kcm->done = 1; spin_unlock_bh(&mux->rx_lock); return; } if (kcm->rx_wait) { list_del(&kcm->wait_rx_list); /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_wait, false); } /* Move any pending receive messages to other kcm sockets */ requeue_rx_msgs(mux, &sk->sk_receive_queue); spin_unlock_bh(&mux->rx_lock); if (WARN_ON(sk_rmem_alloc_get(sk))) return; /* Detach from MUX */ spin_lock_bh(&mux->lock); list_del(&kcm->kcm_sock_list); mux->kcm_socks_cnt--; socks_cnt = mux->kcm_socks_cnt; spin_unlock_bh(&mux->lock); if (!socks_cnt) { /* We are done with the mux now. */ release_mux(mux); } WARN_ON(kcm->rx_wait); sock_put(&kcm->sk); } /* Called by kcm_release to close a KCM socket. * If this is the last KCM socket on the MUX, destroy the MUX. */ static int kcm_release(struct socket *sock) { struct sock *sk = sock->sk; struct kcm_sock *kcm; struct kcm_mux *mux; struct kcm_psock *psock; if (!sk) return 0; kcm = kcm_sk(sk); mux = kcm->mux; lock_sock(sk); sock_orphan(sk); kfree_skb(kcm->seq_skb); /* Purge queue under lock to avoid race condition with tx_work trying * to act when queue is nonempty. If tx_work runs after this point * it will just return. */ __skb_queue_purge(&sk->sk_write_queue); /* Set tx_stopped. This is checked when psock is bound to a kcm and we * get a writespace callback. This prevents further work being queued * from the callback (unbinding the psock occurs after canceling work. */ kcm->tx_stopped = 1; release_sock(sk); spin_lock_bh(&mux->lock); if (kcm->tx_wait) { /* Take of tx_wait list, after this point there should be no way * that a psock will be assigned to this kcm. */ list_del(&kcm->wait_psock_list); kcm->tx_wait = false; } spin_unlock_bh(&mux->lock); /* Cancel work. After this point there should be no outside references * to the kcm socket. */ cancel_work_sync(&kcm->tx_work); lock_sock(sk); psock = kcm->tx_psock; if (psock) { /* A psock was reserved, so we need to kill it since it * may already have some bytes queued from a message. We * need to do this after removing kcm from tx_wait list. */ kcm_abort_tx_psock(psock, EPIPE, false); unreserve_psock(kcm); } release_sock(sk); WARN_ON(kcm->tx_wait); WARN_ON(kcm->tx_psock); sock->sk = NULL; kcm_done(kcm); return 0; } static const struct proto_ops kcm_dgram_ops = { .family = PF_KCM, .owner = THIS_MODULE, .release = kcm_release, .bind = sock_no_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, .ioctl = kcm_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = kcm_setsockopt, .getsockopt = kcm_getsockopt, .sendmsg = kcm_sendmsg, .recvmsg = kcm_recvmsg, .mmap = sock_no_mmap, .splice_eof = kcm_splice_eof, }; static const struct proto_ops kcm_seqpacket_ops = { .family = PF_KCM, .owner = THIS_MODULE, .release = kcm_release, .bind = sock_no_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, .ioctl = kcm_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = kcm_setsockopt, .getsockopt = kcm_getsockopt, .sendmsg = kcm_sendmsg, .recvmsg = kcm_recvmsg, .mmap = sock_no_mmap, .splice_eof = kcm_splice_eof, .splice_read = kcm_splice_read, }; /* Create proto operation for kcm sockets */ static int kcm_create(struct net *net, struct socket *sock, int protocol, int kern) { struct kcm_net *knet = net_generic(net, kcm_net_id); struct sock *sk; struct kcm_mux *mux; switch (sock->type) { case SOCK_DGRAM: sock->ops = &kcm_dgram_ops; break; case SOCK_SEQPACKET: sock->ops = &kcm_seqpacket_ops; break; default: return -ESOCKTNOSUPPORT; } if (protocol != KCMPROTO_CONNECTED) return -EPROTONOSUPPORT; sk = sk_alloc(net, PF_KCM, GFP_KERNEL, &kcm_proto, kern); if (!sk) return -ENOMEM; /* Allocate a kcm mux, shared between KCM sockets */ mux = kmem_cache_zalloc(kcm_muxp, GFP_KERNEL); if (!mux) { sk_free(sk); return -ENOMEM; } spin_lock_init(&mux->lock); spin_lock_init(&mux->rx_lock); INIT_LIST_HEAD(&mux->kcm_socks); INIT_LIST_HEAD(&mux->kcm_rx_waiters); INIT_LIST_HEAD(&mux->kcm_tx_waiters); INIT_LIST_HEAD(&mux->psocks); INIT_LIST_HEAD(&mux->psocks_ready); INIT_LIST_HEAD(&mux->psocks_avail); mux->knet = knet; /* Add new MUX to list */ mutex_lock(&knet->mutex); list_add_rcu(&mux->kcm_mux_list, &knet->mux_list); knet->count++; mutex_unlock(&knet->mutex); skb_queue_head_init(&mux->rx_hold_queue); /* Init KCM socket */ sock_init_data(sock, sk); init_kcm_sock(kcm_sk(sk), mux); return 0; } static const struct net_proto_family kcm_family_ops = { .family = PF_KCM, .create = kcm_create, .owner = THIS_MODULE, }; static __net_init int kcm_init_net(struct net *net) { struct kcm_net *knet = net_generic(net, kcm_net_id); INIT_LIST_HEAD_RCU(&knet->mux_list); mutex_init(&knet->mutex); return 0; } static __net_exit void kcm_exit_net(struct net *net) { struct kcm_net *knet = net_generic(net, kcm_net_id); /* All KCM sockets should be closed at this point, which should mean * that all multiplexors and psocks have been destroyed. */ WARN_ON(!list_empty(&knet->mux_list)); mutex_destroy(&knet->mutex); } static struct pernet_operations kcm_net_ops = { .init = kcm_init_net, .exit = kcm_exit_net, .id = &kcm_net_id, .size = sizeof(struct kcm_net), }; static int __init kcm_init(void) { int err = -ENOMEM; kcm_muxp = KMEM_CACHE(kcm_mux, SLAB_HWCACHE_ALIGN); if (!kcm_muxp) goto fail; kcm_psockp = KMEM_CACHE(kcm_psock, SLAB_HWCACHE_ALIGN); if (!kcm_psockp) goto fail; kcm_wq = create_singlethread_workqueue("kkcmd"); if (!kcm_wq) goto fail; err = proto_register(&kcm_proto, 1); if (err) goto fail; err = register_pernet_device(&kcm_net_ops); if (err) goto net_ops_fail; err = sock_register(&kcm_family_ops); if (err) goto sock_register_fail; err = kcm_proc_init(); if (err) goto proc_init_fail; return 0; proc_init_fail: sock_unregister(PF_KCM); sock_register_fail: unregister_pernet_device(&kcm_net_ops); net_ops_fail: proto_unregister(&kcm_proto); fail: kmem_cache_destroy(kcm_muxp); kmem_cache_destroy(kcm_psockp); if (kcm_wq) destroy_workqueue(kcm_wq); return err; } static void __exit kcm_exit(void) { kcm_proc_exit(); sock_unregister(PF_KCM); unregister_pernet_device(&kcm_net_ops); proto_unregister(&kcm_proto); destroy_workqueue(kcm_wq); kmem_cache_destroy(kcm_muxp); kmem_cache_destroy(kcm_psockp); } module_init(kcm_init); module_exit(kcm_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("KCM (Kernel Connection Multiplexor) sockets"); MODULE_ALIAS_NETPROTO(PF_KCM); |
| 789 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/net/dsa.h - Driver for Distributed Switch Architecture switch chips * Copyright (c) 2008-2009 Marvell Semiconductor */ #ifndef __LINUX_NET_DSA_H #define __LINUX_NET_DSA_H #include <linux/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/of.h> #include <linux/ethtool.h> #include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/platform_data/dsa.h> #include <linux/phylink.h> #include <net/devlink.h> #include <net/switchdev.h> struct dsa_8021q_context; struct tc_action; #define DSA_TAG_PROTO_NONE_VALUE 0 #define DSA_TAG_PROTO_BRCM_VALUE 1 #define DSA_TAG_PROTO_BRCM_PREPEND_VALUE 2 #define DSA_TAG_PROTO_DSA_VALUE 3 #define DSA_TAG_PROTO_EDSA_VALUE 4 #define DSA_TAG_PROTO_GSWIP_VALUE 5 #define DSA_TAG_PROTO_KSZ9477_VALUE 6 #define DSA_TAG_PROTO_KSZ9893_VALUE 7 #define DSA_TAG_PROTO_LAN9303_VALUE 8 #define DSA_TAG_PROTO_MTK_VALUE 9 #define DSA_TAG_PROTO_QCA_VALUE 10 #define DSA_TAG_PROTO_TRAILER_VALUE 11 #define DSA_TAG_PROTO_8021Q_VALUE 12 #define DSA_TAG_PROTO_SJA1105_VALUE 13 #define DSA_TAG_PROTO_KSZ8795_VALUE 14 #define DSA_TAG_PROTO_OCELOT_VALUE 15 #define DSA_TAG_PROTO_AR9331_VALUE 16 #define DSA_TAG_PROTO_RTL4_A_VALUE 17 #define DSA_TAG_PROTO_HELLCREEK_VALUE 18 #define DSA_TAG_PROTO_XRS700X_VALUE 19 #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20 #define DSA_TAG_PROTO_SEVILLE_VALUE 21 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 #define DSA_TAG_PROTO_SJA1110_VALUE 23 #define DSA_TAG_PROTO_RTL8_4_VALUE 24 #define DSA_TAG_PROTO_RTL8_4T_VALUE 25 #define DSA_TAG_PROTO_RZN1_A5PSW_VALUE 26 #define DSA_TAG_PROTO_LAN937X_VALUE 27 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, DSA_TAG_PROTO_BRCM = DSA_TAG_PROTO_BRCM_VALUE, DSA_TAG_PROTO_BRCM_LEGACY = DSA_TAG_PROTO_BRCM_LEGACY_VALUE, DSA_TAG_PROTO_BRCM_PREPEND = DSA_TAG_PROTO_BRCM_PREPEND_VALUE, DSA_TAG_PROTO_DSA = DSA_TAG_PROTO_DSA_VALUE, DSA_TAG_PROTO_EDSA = DSA_TAG_PROTO_EDSA_VALUE, DSA_TAG_PROTO_GSWIP = DSA_TAG_PROTO_GSWIP_VALUE, DSA_TAG_PROTO_KSZ9477 = DSA_TAG_PROTO_KSZ9477_VALUE, DSA_TAG_PROTO_KSZ9893 = DSA_TAG_PROTO_KSZ9893_VALUE, DSA_TAG_PROTO_LAN9303 = DSA_TAG_PROTO_LAN9303_VALUE, DSA_TAG_PROTO_MTK = DSA_TAG_PROTO_MTK_VALUE, DSA_TAG_PROTO_QCA = DSA_TAG_PROTO_QCA_VALUE, DSA_TAG_PROTO_TRAILER = DSA_TAG_PROTO_TRAILER_VALUE, DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE, DSA_TAG_PROTO_SJA1105 = DSA_TAG_PROTO_SJA1105_VALUE, DSA_TAG_PROTO_KSZ8795 = DSA_TAG_PROTO_KSZ8795_VALUE, DSA_TAG_PROTO_OCELOT = DSA_TAG_PROTO_OCELOT_VALUE, DSA_TAG_PROTO_AR9331 = DSA_TAG_PROTO_AR9331_VALUE, DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE, DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE, DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE, DSA_TAG_PROTO_RTL8_4T = DSA_TAG_PROTO_RTL8_4T_VALUE, DSA_TAG_PROTO_RZN1_A5PSW = DSA_TAG_PROTO_RZN1_A5PSW_VALUE, DSA_TAG_PROTO_LAN937X = DSA_TAG_PROTO_LAN937X_VALUE, }; struct dsa_switch; struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); int (*connect)(struct dsa_switch *ds); void (*disconnect)(struct dsa_switch *ds); unsigned int needed_headroom; unsigned int needed_tailroom; const char *name; enum dsa_tag_protocol proto; /* Some tagging protocols either mangle or shift the destination MAC * address, in which case the DSA conduit would drop packets on ingress * if what it understands out of the destination MAC address is not in * its RX filter. */ bool promisc_on_conduit; }; struct dsa_lag { struct net_device *dev; unsigned int id; struct mutex fdb_lock; struct list_head fdbs; refcount_t refcount; }; struct dsa_switch_tree { struct list_head list; /* List of switch ports */ struct list_head ports; /* Notifier chain for switch-wide events */ struct raw_notifier_head nh; /* Tree identifier */ unsigned int index; /* Number of switches attached to this tree */ struct kref refcount; /* Maps offloaded LAG netdevs to a zero-based linear ID for * drivers that need it. */ struct dsa_lag **lags; /* Tagging protocol operations */ const struct dsa_device_ops *tag_ops; /* Default tagging protocol preferred by the switches in this * tree. */ enum dsa_tag_protocol default_proto; /* Has this tree been applied to the hardware? */ bool setup; /* * Configuration data for the platform device that owns * this dsa switch tree instance. */ struct dsa_platform_data *pd; /* List of DSA links composing the routing table */ struct list_head rtable; /* Length of "lags" array */ unsigned int lags_len; /* Track the largest switch index within a tree */ unsigned int last_switch; }; /* LAG IDs are one-based, the dst->lags array is zero-based */ #define dsa_lags_foreach_id(_id, _dst) \ for ((_id) = 1; (_id) <= (_dst)->lags_len; (_id)++) \ if ((_dst)->lags[(_id) - 1]) #define dsa_lag_foreach_port(_dp, _dst, _lag) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_offloads_lag((_dp), (_lag))) #define dsa_hsr_foreach_port(_dp, _ds, _hsr) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds) && (_dp)->hsr_dev == (_hsr)) static inline struct dsa_lag *dsa_lag_by_id(struct dsa_switch_tree *dst, unsigned int id) { /* DSA LAG IDs are one-based, dst->lags is zero-based */ return dst->lags[id - 1]; } static inline int dsa_lag_id(struct dsa_switch_tree *dst, struct net_device *lag_dev) { unsigned int id; dsa_lags_foreach_id(id, dst) { struct dsa_lag *lag = dsa_lag_by_id(dst, id); if (lag->dev == lag_dev) return lag->id; } return -ENODEV; } /* TC matchall action types */ enum dsa_port_mall_action_type { DSA_PORT_MALL_MIRROR, DSA_PORT_MALL_POLICER, }; /* TC mirroring entry */ struct dsa_mall_mirror_tc_entry { u8 to_local_port; bool ingress; }; /* TC port policer entry */ struct dsa_mall_policer_tc_entry { u32 burst; u64 rate_bytes_per_sec; }; /* TC matchall entry */ struct dsa_mall_tc_entry { struct list_head list; unsigned long cookie; enum dsa_port_mall_action_type type; union { struct dsa_mall_mirror_tc_entry mirror; struct dsa_mall_policer_tc_entry policer; }; }; struct dsa_bridge { struct net_device *dev; unsigned int num; bool tx_fwd_offload; refcount_t refcount; }; struct dsa_port { /* A CPU port is physically connected to a conduit device. A user port * exposes a network device to user-space, called 'user' here. */ union { struct net_device *conduit; struct net_device *user; }; /* Copy of the tagging protocol operations, for quicker access * in the data path. Valid only for the CPU ports. */ const struct dsa_device_ops *tag_ops; /* Copies for faster access in conduit receive hot path */ struct dsa_switch_tree *dst; struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); struct dsa_switch *ds; unsigned int index; enum { DSA_PORT_TYPE_UNUSED = 0, DSA_PORT_TYPE_CPU, DSA_PORT_TYPE_DSA, DSA_PORT_TYPE_USER, } type; const char *name; struct dsa_port *cpu_dp; u8 mac[ETH_ALEN]; u8 stp_state; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u8 vlan_filtering:1; /* Managed by DSA on user ports and by drivers on CPU and DSA ports */ u8 learning:1; u8 lag_tx_enabled:1; /* conduit state bits, valid only on CPU ports */ u8 conduit_admin_up:1; u8 conduit_oper_up:1; /* Valid only on user ports */ u8 cpu_port_in_lag:1; u8 setup:1; struct device_node *dn; unsigned int ageing_time; struct dsa_bridge *bridge; struct devlink_port devlink_port; struct phylink *pl; struct phylink_config pl_config; struct dsa_lag *lag; struct net_device *hsr_dev; struct list_head list; /* * Original copy of the conduit netdev ethtool_ops */ const struct ethtool_ops *orig_ethtool_ops; /* List of MAC addresses that must be forwarded on this port. * These are only valid on CPU ports and DSA links. */ struct mutex addr_lists_lock; struct list_head fdbs; struct list_head mdbs; struct mutex vlans_lock; union { /* List of VLANs that CPU and DSA ports are members of. * Access to this is serialized by the sleepable @vlans_lock. */ struct list_head vlans; /* List of VLANs that user ports are members of. * Access to this is serialized by netif_addr_lock_bh(). */ struct list_head user_vlans; }; }; static inline struct dsa_port * dsa_phylink_to_port(struct phylink_config *config) { return container_of(config, struct dsa_port, pl_config); } /* TODO: ideally DSA ports would have a single dp->link_dp member, * and no dst->rtable nor this struct dsa_link would be needed, * but this would require some more complex tree walking, * so keep it stupid at the moment and list them all. */ struct dsa_link { struct dsa_port *dp; struct dsa_port *link_dp; struct list_head list; }; enum dsa_db_type { DSA_DB_PORT, DSA_DB_LAG, DSA_DB_BRIDGE, }; struct dsa_db { enum dsa_db_type type; union { const struct dsa_port *dp; struct dsa_lag lag; struct dsa_bridge bridge; }; }; struct dsa_mac_addr { unsigned char addr[ETH_ALEN]; u16 vid; refcount_t refcount; struct list_head list; struct dsa_db db; }; struct dsa_vlan { u16 vid; refcount_t refcount; struct list_head list; }; struct dsa_switch { struct device *dev; /* * Parent switch tree, and switch index. */ struct dsa_switch_tree *dst; unsigned int index; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u32 setup:1; /* Disallow bridge core from requesting different VLAN awareness * settings on ports if not hardware-supported */ u32 vlan_filtering_is_global:1; /* Keep VLAN filtering enabled on ports not offloading any upper */ u32 needs_standalone_vlan_filtering:1; /* Pass .port_vlan_add and .port_vlan_del to drivers even for bridges * that have vlan_filtering=0. All drivers should ideally set this (and * then the option would get removed), but it is unknown whether this * would break things or not. */ u32 configure_vlan_while_not_filtering:1; /* If the switch driver always programs the CPU port as egress tagged * despite the VLAN configuration indicating otherwise, then setting * @untag_bridge_pvid will force the DSA receive path to pop the * bridge's default_pvid VLAN tagged frames to offer a consistent * behavior between a vlan_filtering=0 and vlan_filtering=1 bridge * device. */ u32 untag_bridge_pvid:1; /* Let DSA manage the FDB entries towards the * CPU, based on the software bridge database. */ u32 assisted_learning_on_cpu_port:1; /* In case vlan_filtering_is_global is set, the VLAN awareness state * should be retrieved from here and not from the per-port settings. */ u32 vlan_filtering:1; /* For switches that only have the MRU configurable. To ensure the * configured MTU is not exceeded, normalization of MRU on all bridged * interfaces is needed. */ u32 mtu_enforcement_ingress:1; /* Drivers that isolate the FDBs of multiple bridges must set this * to true to receive the bridge as an argument in .port_fdb_{add,del} * and .port_mdb_{add,del}. Otherwise, the bridge.num will always be * passed as zero. */ u32 fdb_isolation:1; /* Drivers that have global DSCP mapping settings must set this to * true to automatically apply the settings to all ports. */ u32 dscp_prio_mapping_is_global:1; /* Listener for switch fabric events */ struct notifier_block nb; /* * Give the switch driver somewhere to hang its private data * structure. */ void *priv; void *tagger_data; /* * Configuration data for this switch. */ struct dsa_chip_data *cd; /* * The switch operations. */ const struct dsa_switch_ops *ops; /* * Allow a DSA switch driver to override the phylink MAC ops */ const struct phylink_mac_ops *phylink_mac_ops; /* * User mii_bus and devices for the individual ports. */ u32 phys_mii_mask; struct mii_bus *user_mii_bus; /* Ageing Time limits in msecs */ unsigned int ageing_time_min; unsigned int ageing_time_max; /* Storage for drivers using tag_8021q */ struct dsa_8021q_context *tag_8021q_ctx; /* devlink used to represent this switch device */ struct devlink *devlink; /* Number of switch port queues */ unsigned int num_tx_queues; /* Drivers that benefit from having an ID associated with each * offloaded LAG should set this to the maximum number of * supported IDs. DSA will then maintain a mapping of _at * least_ these many IDs, accessible to drivers via * dsa_lag_id(). */ unsigned int num_lag_ids; /* Drivers that support bridge forwarding offload or FDB isolation * should set this to the maximum number of bridges spanning the same * switch tree (or all trees, in the case of cross-tree bridging * support) that can be offloaded. */ unsigned int max_num_bridges; unsigned int num_ports; }; static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p) { struct dsa_switch_tree *dst = ds->dst; struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dp->ds == ds && dp->index == p) return dp; return NULL; } static inline bool dsa_port_is_dsa(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_port_is_cpu(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_port_is_user(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_USER; } static inline bool dsa_port_is_unused(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_port_conduit_is_operational(struct dsa_port *dp) { return dsa_port_is_cpu(dp) && dp->conduit_admin_up && dp->conduit_oper_up; } static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_USER; } #define dsa_tree_for_each_user_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_user_port_continue_reverse(_dp, _dst) \ list_for_each_entry_continue_reverse((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_cpu_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_port(_dp, _ds) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_safe(_dp, _next, _ds) \ list_for_each_entry_safe((_dp), (_next), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_continue_reverse(_dp, _ds) \ list_for_each_entry_continue_reverse((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_available_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (!dsa_port_is_unused((_dp))) #define dsa_switch_for_each_user_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_user_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_cpu_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_cpu_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) static inline u32 dsa_user_ports(struct dsa_switch *ds) { struct dsa_port *dp; u32 mask = 0; dsa_switch_for_each_user_port(dp, ds) mask |= BIT(dp->index); return mask; } static inline u32 dsa_cpu_ports(struct dsa_switch *ds) { struct dsa_port *cpu_dp; u32 mask = 0; dsa_switch_for_each_cpu_port(cpu_dp, ds) mask |= BIT(cpu_dp->index); return mask; } /* Return the local port used to reach an arbitrary switch device */ static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device) { struct dsa_switch_tree *dst = ds->dst; struct dsa_link *dl; list_for_each_entry(dl, &dst->rtable, list) if (dl->dp->ds == ds && dl->link_dp->ds->index == device) return dl->dp->index; return ds->num_ports; } /* Return the local port used to reach an arbitrary switch port */ static inline unsigned int dsa_towards_port(struct dsa_switch *ds, int device, int port) { if (device == ds->index) return port; else return dsa_routing_port(ds, device); } /* Return the local port used to reach the dedicated CPU port */ static inline unsigned int dsa_upstream_port(struct dsa_switch *ds, int port) { const struct dsa_port *dp = dsa_to_port(ds, port); const struct dsa_port *cpu_dp = dp->cpu_dp; if (!cpu_dp) return port; return dsa_towards_port(ds, cpu_dp->ds->index, cpu_dp->index); } /* Return true if this is the local port used to reach the CPU port */ static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port) { if (dsa_is_unused_port(ds, port)) return false; return port == dsa_upstream_port(ds, port); } /* Return true if this is a DSA port leading away from the CPU */ static inline bool dsa_is_downstream_port(struct dsa_switch *ds, int port) { return dsa_is_dsa_port(ds, port) && !dsa_is_upstream_port(ds, port); } /* Return the local port used to reach the CPU port */ static inline unsigned int dsa_switch_upstream_port(struct dsa_switch *ds) { struct dsa_port *dp; dsa_switch_for_each_available_port(dp, ds) { return dsa_upstream_port(ds, dp->index); } return ds->num_ports; } /* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning * that the routing port from @downstream_ds to @upstream_ds is also the port * which @downstream_ds uses to reach its dedicated CPU. */ static inline bool dsa_switch_is_upstream_of(struct dsa_switch *upstream_ds, struct dsa_switch *downstream_ds) { int routing_port; if (upstream_ds == downstream_ds) return true; routing_port = dsa_routing_port(downstream_ds, upstream_ds->index); return dsa_is_upstream_port(downstream_ds, routing_port); } static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) { const struct dsa_switch *ds = dp->ds; if (ds->vlan_filtering_is_global) return ds->vlan_filtering; else return dp->vlan_filtering; } static inline unsigned int dsa_port_lag_id_get(struct dsa_port *dp) { return dp->lag ? dp->lag->id : 0; } static inline struct net_device *dsa_port_lag_dev_get(struct dsa_port *dp) { return dp->lag ? dp->lag->dev : NULL; } static inline bool dsa_port_offloads_lag(struct dsa_port *dp, const struct dsa_lag *lag) { return dsa_port_lag_dev_get(dp) == lag->dev; } static inline struct net_device *dsa_port_to_conduit(const struct dsa_port *dp) { if (dp->cpu_port_in_lag) return dsa_port_lag_dev_get(dp->cpu_dp); return dp->cpu_dp->conduit; } static inline struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) { if (!dp->bridge) return NULL; if (dp->lag) return dp->lag->dev; else if (dp->hsr_dev) return dp->hsr_dev; return dp->user; } static inline struct net_device * dsa_port_bridge_dev_get(const struct dsa_port *dp) { return dp->bridge ? dp->bridge->dev : NULL; } static inline unsigned int dsa_port_bridge_num_get(struct dsa_port *dp) { return dp->bridge ? dp->bridge->num : 0; } static inline bool dsa_port_bridge_same(const struct dsa_port *a, const struct dsa_port *b) { struct net_device *br_a = dsa_port_bridge_dev_get(a); struct net_device *br_b = dsa_port_bridge_dev_get(b); /* Standalone ports are not in the same bridge with one another */ return (!br_a || !br_b) ? false : (br_a == br_b); } static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, const struct net_device *dev) { return dsa_port_to_bridge_port(dp) == dev; } static inline bool dsa_port_offloads_bridge_dev(struct dsa_port *dp, const struct net_device *bridge_dev) { /* DSA ports connected to a bridge, and event was emitted * for the bridge. */ return dsa_port_bridge_dev_get(dp) == bridge_dev; } static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, const struct dsa_bridge *bridge) { return dsa_port_bridge_dev_get(dp) == bridge->dev; } /* Returns true if any port of this tree offloads the given net_device */ static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, const struct net_device *dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_port(dp, dev)) return true; return false; } /* Returns true if any port of this tree offloads the given bridge */ static inline bool dsa_tree_offloads_bridge_dev(struct dsa_switch_tree *dst, const struct net_device *bridge_dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_dev(dp, bridge_dev)) return true; return false; } static inline bool dsa_port_tree_same(const struct dsa_port *a, const struct dsa_port *b) { return a->ds->dst == b->ds->dst; } typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { /* * Tagging protocol helpers called for the CPU ports and DSA links. * @get_tag_protocol retrieves the initial tagging protocol and is * mandatory. Switches which can operate using multiple tagging * protocols should implement @change_tag_protocol and report in * @get_tag_protocol the tagger in current use. */ enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol mprot); int (*change_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); /* * Method for switch drivers to connect to the tagging protocol driver * in current use. The switch driver can provide handlers for certain * types of packets for switch management. */ int (*connect_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); int (*port_change_conduit)(struct dsa_switch *ds, int port, struct net_device *conduit, struct netlink_ext_ack *extack); /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); /* Per-port initialization and destruction methods. Mandatory if the * driver registers devlink port regions, optional otherwise. */ int (*port_setup)(struct dsa_switch *ds, int port); void (*port_teardown)(struct dsa_switch *ds, int port); u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* * Access to the switch's PHY registers. */ int (*phy_read)(struct dsa_switch *ds, int port, int regnum); int (*phy_write)(struct dsa_switch *ds, int port, int regnum, u16 val); /* * PHYLINK integration */ void (*phylink_get_caps)(struct dsa_switch *ds, int port, struct phylink_config *config); struct phylink_pcs *(*phylink_mac_select_pcs)(struct dsa_switch *ds, int port, phy_interface_t iface); int (*phylink_mac_prepare)(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface); void (*phylink_mac_config)(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state); int (*phylink_mac_finish)(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface); void (*phylink_mac_link_down)(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface); void (*phylink_mac_link_up)(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, struct phy_device *phydev, int speed, int duplex, bool tx_pause, bool rx_pause); void (*phylink_fixed_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); /* * Port statistics counters. */ void (*get_strings)(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data); void (*get_ethtool_stats)(struct dsa_switch *ds, int port, uint64_t *data); int (*get_sset_count)(struct dsa_switch *ds, int port, int sset); void (*get_ethtool_phy_stats)(struct dsa_switch *ds, int port, uint64_t *data); void (*get_eth_phy_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_phy_stats *phy_stats); void (*get_eth_mac_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_mac_stats *mac_stats); void (*get_eth_ctrl_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_ctrl_stats *ctrl_stats); void (*get_rmon_stats)(struct dsa_switch *ds, int port, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); void (*get_pause_stats)(struct dsa_switch *ds, int port, struct ethtool_pause_stats *pause_stats); void (*self_test)(struct dsa_switch *ds, int port, struct ethtool_test *etest, u64 *data); /* * ethtool Wake-on-LAN */ void (*get_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); int (*set_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); /* * ethtool timestamp info */ int (*get_ts_info)(struct dsa_switch *ds, int port, struct ethtool_ts_info *ts); /* * ethtool MAC merge layer */ int (*get_mm)(struct dsa_switch *ds, int port, struct ethtool_mm_state *state); int (*set_mm)(struct dsa_switch *ds, int port, struct ethtool_mm_cfg *cfg, struct netlink_ext_ack *extack); void (*get_mm_stats)(struct dsa_switch *ds, int port, struct ethtool_mm_stats *stats); /* * DCB ops */ int (*port_get_default_prio)(struct dsa_switch *ds, int port); int (*port_set_default_prio)(struct dsa_switch *ds, int port, u8 prio); int (*port_get_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp); int (*port_add_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_del_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_set_apptrust)(struct dsa_switch *ds, int port, const u8 *sel, int nsel); int (*port_get_apptrust)(struct dsa_switch *ds, int port, u8 *sel, int *nsel); /* * Suspend and resume */ int (*suspend)(struct dsa_switch *ds); int (*resume)(struct dsa_switch *ds); /* * Port enable/disable */ int (*port_enable)(struct dsa_switch *ds, int port, struct phy_device *phy); void (*port_disable)(struct dsa_switch *ds, int port); /* * Notification for MAC address changes on user ports. Drivers can * currently only veto operations. They should not use the method to * program the hardware, since the operation is not rolled back in case * of other errors. */ int (*port_set_mac_address)(struct dsa_switch *ds, int port, const unsigned char *addr); /* * Compatibility between device trees defining multiple CPU ports and * drivers which are not OK to use by default the numerically smallest * CPU port of a switch for its local ports. This can return NULL, * meaning "don't know/don't care". */ struct dsa_port *(*preferred_default_local_cpu_port)(struct dsa_switch *ds); /* * Port's MAC EEE settings */ int (*set_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_keee *e); int (*get_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_keee *e); /* EEPROM access */ int (*get_eeprom_len)(struct dsa_switch *ds); int (*get_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); int (*set_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); /* * Register access. */ int (*get_regs_len)(struct dsa_switch *ds, int port); void (*get_regs)(struct dsa_switch *ds, int port, struct ethtool_regs *regs, void *p); /* * Upper device tracking. */ int (*port_prechangeupper)(struct dsa_switch *ds, int port, struct netdev_notifier_changeupper_info *info); /* * Bridge integration */ int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); int (*port_bridge_join)(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload, struct netlink_ext_ack *extack); void (*port_bridge_leave)(struct dsa_switch *ds, int port, struct dsa_bridge bridge); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); int (*port_mst_state_set)(struct dsa_switch *ds, int port, const struct switchdev_mst_state *state); void (*port_fast_age)(struct dsa_switch *ds, int port); int (*port_vlan_fast_age)(struct dsa_switch *ds, int port, u16 vid); int (*port_pre_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); int (*port_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); void (*port_set_host_flood)(struct dsa_switch *ds, int port, bool uc, bool mc); /* * VLAN support */ int (*port_vlan_filtering)(struct dsa_switch *ds, int port, bool vlan_filtering, struct netlink_ext_ack *extack); int (*port_vlan_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); int (*vlan_msti_set)(struct dsa_switch *ds, struct dsa_bridge bridge, const struct switchdev_vlan_msti *msti); /* * Forwarding database */ int (*port_fdb_add)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_del)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_dump)(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data); int (*lag_fdb_add)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); int (*lag_fdb_del)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); /* * Multicast database */ int (*port_mdb_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); int (*port_mdb_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); /* * RXNFC */ int (*get_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc, u32 *rule_locs); int (*set_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc); /* * TC integration */ int (*cls_flower_add)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_del)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_stats)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*port_mirror_add)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror, bool ingress, struct netlink_ext_ack *extack); void (*port_mirror_del)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror); int (*port_policer_add)(struct dsa_switch *ds, int port, struct dsa_mall_policer_tc_entry *policer); void (*port_policer_del)(struct dsa_switch *ds, int port); int (*port_setup_tc)(struct dsa_switch *ds, int port, enum tc_setup_type type, void *type_data); /* * Cross-chip operations */ int (*crosschip_bridge_join)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge, struct netlink_ext_ack *extack); void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge); int (*crosschip_lag_change)(struct dsa_switch *ds, int sw_index, int port); int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*crosschip_lag_leave)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag); /* * PTP functionality */ int (*port_hwtstamp_get)(struct dsa_switch *ds, int port, struct ifreq *ifr); int (*port_hwtstamp_set)(struct dsa_switch *ds, int port, struct ifreq *ifr); void (*port_txtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); bool (*port_rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb, unsigned int type); /* Devlink parameters, etc */ int (*devlink_param_get)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_param_set)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_info_get)(struct dsa_switch *ds, struct devlink_info_req *req, struct netlink_ext_ack *extack); int (*devlink_sb_pool_get)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, struct devlink_sb_pool_info *pool_info); int (*devlink_sb_pool_set)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, u32 size, enum devlink_sb_threshold_type threshold_type, struct netlink_ext_ack *extack); int (*devlink_sb_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_threshold); int (*devlink_sb_port_pool_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_tc_pool_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 *p_pool_index, u32 *p_threshold); int (*devlink_sb_tc_pool_bind_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_occ_snapshot)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_max_clear)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_cur, u32 *p_max); int (*devlink_sb_occ_tc_port_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u32 *p_cur, u32 *p_max); /* * MTU change functionality. Switches can also adjust their MRU through * this method. By MTU, one understands the SDU (L2 payload) length. * If the switch needs to account for the DSA tag on the CPU port, this * method needs to do so privately. */ int (*port_change_mtu)(struct dsa_switch *ds, int port, int new_mtu); int (*port_max_mtu)(struct dsa_switch *ds, int port); /* * LAG integration */ int (*port_lag_change)(struct dsa_switch *ds, int port); int (*port_lag_join)(struct dsa_switch *ds, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*port_lag_leave)(struct dsa_switch *ds, int port, struct dsa_lag lag); /* * HSR integration */ int (*port_hsr_join)(struct dsa_switch *ds, int port, struct net_device *hsr, struct netlink_ext_ack *extack); int (*port_hsr_leave)(struct dsa_switch *ds, int port, struct net_device *hsr); /* * MRP integration */ int (*port_mrp_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_add_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); int (*port_mrp_del_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); /* * tag_8021q operations */ int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); /* * DSA conduit tracking operations */ void (*conduit_state_change)(struct dsa_switch *ds, const struct net_device *conduit, bool operational); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes, \ dsa_devlink_param_get, dsa_devlink_param_set, NULL) int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx); int dsa_devlink_param_set(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx, struct netlink_ext_ack *extack); int dsa_devlink_params_register(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); void dsa_devlink_params_unregister(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); int dsa_devlink_resource_register(struct dsa_switch *ds, const char *resource_name, u64 resource_size, u64 resource_id, u64 parent_resource_id, const struct devlink_resource_size_params *size_params); void dsa_devlink_resources_unregister(struct dsa_switch *ds); void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, u64 resource_id, devlink_resource_occ_get_t *occ_get, void *occ_get_priv); void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, u64 resource_id); struct devlink_region * dsa_devlink_region_create(struct dsa_switch *ds, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size); struct devlink_region * dsa_devlink_port_region_create(struct dsa_switch *ds, int port, const struct devlink_port_region_ops *ops, u32 region_max_snapshots, u64 region_size); void dsa_devlink_region_destroy(struct devlink_region *region); struct dsa_port *dsa_port_from_netdev(struct net_device *netdev); struct dsa_devlink_priv { struct dsa_switch *ds; }; static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl) { struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline struct dsa_switch *dsa_devlink_port_to_ds(struct devlink_port *port) { struct devlink *dl = port->devlink; struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline int dsa_devlink_port_to_port(struct devlink_port *port) { return port->index; } struct dsa_switch_driver { struct list_head list; const struct dsa_switch_ops *ops; }; bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); bool dsa_mdb_present_in_other_db(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); /* Keep inline for faster access in hot path */ static inline bool netdev_uses_dsa(const struct net_device *dev) { #if IS_ENABLED(CONFIG_NET_DSA) return dev->dsa_ptr && dev->dsa_ptr->rcv; #endif return false; } /* All DSA tags that push the EtherType to the right (basically all except tail * tags, which don't break dissection) can be treated the same from the * perspective of the flow dissector. * * We need to return: * - offset: the (B - A) difference between: * A. the position of the real EtherType and * B. the current skb->data (aka ETH_HLEN bytes into the frame, aka 2 bytes * after the normal EtherType was supposed to be) * The offset in bytes is exactly equal to the tagger overhead (and half of * that, in __be16 shorts). * * - proto: the value of the real EtherType. */ static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb, __be16 *proto, int *offset) { #if IS_ENABLED(CONFIG_NET_DSA) const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops; int tag_len = ops->needed_headroom; *offset = tag_len; *proto = ((__be16 *)skb->data)[(tag_len / 2) - 1]; #endif } void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); void dsa_switch_shutdown(struct dsa_switch *ds); struct dsa_switch *dsa_switch_find(int tree_index, int sw_index); void dsa_flush_workqueue(void); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); int dsa_switch_resume(struct dsa_switch *ds); #else static inline int dsa_switch_suspend(struct dsa_switch *ds) { return 0; } static inline int dsa_switch_resume(struct dsa_switch *ds) { return 0; } #endif /* CONFIG_PM_SLEEP */ #if IS_ENABLED(CONFIG_NET_DSA) bool dsa_user_dev_check(const struct net_device *dev); #else static inline bool dsa_user_dev_check(const struct net_device *dev) { return false; } #endif netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up); #endif |
| 5 5 2 2 2 2 5 5 1 1 5 5 5 5 1 1 5 5 1 5 5 5 5 5 5 5 4 5 5 5 5 1 5 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "io_uring.h" #include "sqpoll.h" #include "fdinfo.h" #include "cancel.h" #include "rsrc.h" #ifdef CONFIG_PROC_FS static __cold int io_uring_show_cred(struct seq_file *m, unsigned int id, const struct cred *cred) { struct user_namespace *uns = seq_user_ns(m); struct group_info *gi; kernel_cap_t cap; int g; seq_printf(m, "%5d\n", id); seq_put_decimal_ull(m, "\tUid:\t", from_kuid_munged(uns, cred->uid)); seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->euid)); seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->suid)); seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->fsuid)); seq_put_decimal_ull(m, "\n\tGid:\t", from_kgid_munged(uns, cred->gid)); seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->egid)); seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->sgid)); seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->fsgid)); seq_puts(m, "\n\tGroups:\t"); gi = cred->group_info; for (g = 0; g < gi->ngroups; g++) { seq_put_decimal_ull(m, g ? " " : "", from_kgid_munged(uns, gi->gid[g])); } seq_puts(m, "\n\tCapEff:\t"); cap = cred->cap_effective; seq_put_hex_ll(m, NULL, cap.val, 16); seq_putc(m, '\n'); return 0; } /* * Caller holds a reference to the file already, we don't need to do * anything else to get an extra reference. */ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) { struct io_ring_ctx *ctx = file->private_data; struct io_overflow_cqe *ocqe; struct io_rings *r = ctx->rings; struct rusage sq_usage; unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1; unsigned int sq_head = READ_ONCE(r->sq.head); unsigned int sq_tail = READ_ONCE(r->sq.tail); unsigned int cq_head = READ_ONCE(r->cq.head); unsigned int cq_tail = READ_ONCE(r->cq.tail); unsigned int cq_shift = 0; unsigned int sq_shift = 0; unsigned int sq_entries, cq_entries; int sq_pid = -1, sq_cpu = -1; u64 sq_total_time = 0, sq_work_time = 0; bool has_lock; unsigned int i; if (ctx->flags & IORING_SETUP_CQE32) cq_shift = 1; if (ctx->flags & IORING_SETUP_SQE128) sq_shift = 1; /* * we may get imprecise sqe and cqe info if uring is actively running * since we get cached_sq_head and cached_cq_tail without uring_lock * and sq_tail and cq_head are changed by userspace. But it's ok since * we usually use these info when it is stuck. */ seq_printf(m, "SqMask:\t0x%x\n", sq_mask); seq_printf(m, "SqHead:\t%u\n", sq_head); seq_printf(m, "SqTail:\t%u\n", sq_tail); seq_printf(m, "CachedSqHead:\t%u\n", ctx->cached_sq_head); seq_printf(m, "CqMask:\t0x%x\n", cq_mask); seq_printf(m, "CqHead:\t%u\n", cq_head); seq_printf(m, "CqTail:\t%u\n", cq_tail); seq_printf(m, "CachedCqTail:\t%u\n", ctx->cached_cq_tail); seq_printf(m, "SQEs:\t%u\n", sq_tail - sq_head); sq_entries = min(sq_tail - sq_head, ctx->sq_entries); for (i = 0; i < sq_entries; i++) { unsigned int entry = i + sq_head; struct io_uring_sqe *sqe; unsigned int sq_idx; if (ctx->flags & IORING_SETUP_NO_SQARRAY) break; sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]); if (sq_idx > sq_mask) continue; sqe = &ctx->sq_sqes[sq_idx << sq_shift]; seq_printf(m, "%5u: opcode:%s, fd:%d, flags:%x, off:%llu, " "addr:0x%llx, rw_flags:0x%x, buf_index:%d " "user_data:%llu", sq_idx, io_uring_get_opcode(sqe->opcode), sqe->fd, sqe->flags, (unsigned long long) sqe->off, (unsigned long long) sqe->addr, sqe->rw_flags, sqe->buf_index, sqe->user_data); if (sq_shift) { u64 *sqeb = (void *) (sqe + 1); int size = sizeof(struct io_uring_sqe) / sizeof(u64); int j; for (j = 0; j < size; j++) { seq_printf(m, ", e%d:0x%llx", j, (unsigned long long) *sqeb); sqeb++; } } seq_printf(m, "\n"); } seq_printf(m, "CQEs:\t%u\n", cq_tail - cq_head); cq_entries = min(cq_tail - cq_head, ctx->cq_entries); for (i = 0; i < cq_entries; i++) { unsigned int entry = i + cq_head; struct io_uring_cqe *cqe = &r->cqes[(entry & cq_mask) << cq_shift]; seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x", entry & cq_mask, cqe->user_data, cqe->res, cqe->flags); if (cq_shift) seq_printf(m, ", extra1:%llu, extra2:%llu\n", cqe->big_cqe[0], cqe->big_cqe[1]); seq_printf(m, "\n"); } /* * Avoid ABBA deadlock between the seq lock and the io_uring mutex, * since fdinfo case grabs it in the opposite direction of normal use * cases. If we fail to get the lock, we just don't iterate any * structures that could be going away outside the io_uring mutex. */ has_lock = mutex_trylock(&ctx->uring_lock); if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) { struct io_sq_data *sq = ctx->sq_data; /* * sq->thread might be NULL if we raced with the sqpoll * thread termination. */ if (sq->thread) { sq_pid = sq->task_pid; sq_cpu = sq->sq_cpu; getrusage(sq->thread, RUSAGE_SELF, &sq_usage); sq_total_time = (sq_usage.ru_stime.tv_sec * 1000000 + sq_usage.ru_stime.tv_usec); sq_work_time = sq->work_time; } } seq_printf(m, "SqThread:\t%d\n", sq_pid); seq_printf(m, "SqThreadCpu:\t%d\n", sq_cpu); seq_printf(m, "SqTotalTime:\t%llu\n", sq_total_time); seq_printf(m, "SqWorkTime:\t%llu\n", sq_work_time); seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files); for (i = 0; has_lock && i < ctx->nr_user_files; i++) { struct file *f = io_file_from_index(&ctx->file_table, i); if (f) seq_printf(m, "%5u: %s\n", i, file_dentry(f)->d_iname); else seq_printf(m, "%5u: <none>\n", i); } seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs); for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) { struct io_mapped_ubuf *buf = ctx->user_bufs[i]; unsigned int len = buf->ubuf_end - buf->ubuf; seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, len); } if (has_lock && !xa_empty(&ctx->personalities)) { unsigned long index; const struct cred *cred; seq_printf(m, "Personalities:\n"); xa_for_each(&ctx->personalities, index, cred) io_uring_show_cred(m, index, cred); } seq_puts(m, "PollList:\n"); for (i = 0; i < (1U << ctx->cancel_table.hash_bits); i++) { struct io_hash_bucket *hb = &ctx->cancel_table.hbs[i]; struct io_hash_bucket *hbl = &ctx->cancel_table_locked.hbs[i]; struct io_kiocb *req; spin_lock(&hb->lock); hlist_for_each_entry(req, &hb->list, hash_node) seq_printf(m, " op=%d, task_works=%d\n", req->opcode, task_work_pending(req->task)); spin_unlock(&hb->lock); if (!has_lock) continue; hlist_for_each_entry(req, &hbl->list, hash_node) seq_printf(m, " op=%d, task_works=%d\n", req->opcode, task_work_pending(req->task)); } if (has_lock) mutex_unlock(&ctx->uring_lock); seq_puts(m, "CqOverflowList:\n"); spin_lock(&ctx->completion_lock); list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) { struct io_uring_cqe *cqe = &ocqe->cqe; seq_printf(m, " user_data=%llu, res=%d, flags=%x\n", cqe->user_data, cqe->res, cqe->flags); } spin_unlock(&ctx->completion_lock); } #endif |
| 2 2 2 2 2 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * SR-IPv6 implementation * * Author: * David Lebrun <david.lebrun@uclouvain.be> */ #include <linux/types.h> #include <linux/skbuff.h> #include <linux/net.h> #include <linux/module.h> #include <net/ip.h> #include <net/ip_tunnels.h> #include <net/lwtunnel.h> #include <net/netevent.h> #include <net/netns/generic.h> #include <net/ip6_fib.h> #include <net/route.h> #include <net/seg6.h> #include <linux/seg6.h> #include <linux/seg6_iptunnel.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/dst_cache.h> #ifdef CONFIG_IPV6_SEG6_HMAC #include <net/seg6_hmac.h> #endif #include <linux/netfilter.h> static size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo) { int head = 0; switch (tuninfo->mode) { case SEG6_IPTUN_MODE_INLINE: break; case SEG6_IPTUN_MODE_ENCAP: case SEG6_IPTUN_MODE_ENCAP_RED: head = sizeof(struct ipv6hdr); break; case SEG6_IPTUN_MODE_L2ENCAP: case SEG6_IPTUN_MODE_L2ENCAP_RED: return 0; } return ((tuninfo->srh->hdrlen + 1) << 3) + head; } struct seg6_lwt { struct dst_cache cache; struct seg6_iptunnel_encap tuninfo[]; }; static inline struct seg6_lwt *seg6_lwt_lwtunnel(struct lwtunnel_state *lwt) { return (struct seg6_lwt *)lwt->data; } static inline struct seg6_iptunnel_encap * seg6_encap_lwtunnel(struct lwtunnel_state *lwt) { return seg6_lwt_lwtunnel(lwt)->tuninfo; } static const struct nla_policy seg6_iptunnel_policy[SEG6_IPTUNNEL_MAX + 1] = { [SEG6_IPTUNNEL_SRH] = { .type = NLA_BINARY }, }; static int nla_put_srh(struct sk_buff *skb, int attrtype, struct seg6_iptunnel_encap *tuninfo) { struct seg6_iptunnel_encap *data; struct nlattr *nla; int len; len = SEG6_IPTUN_ENCAP_SIZE(tuninfo); nla = nla_reserve(skb, attrtype, len); if (!nla) return -EMSGSIZE; data = nla_data(nla); memcpy(data, tuninfo, len); return 0; } static void set_tun_src(struct net *net, struct net_device *dev, struct in6_addr *daddr, struct in6_addr *saddr) { struct seg6_pernet_data *sdata = seg6_pernet(net); struct in6_addr *tun_src; rcu_read_lock(); tun_src = rcu_dereference(sdata->tun_src); if (!ipv6_addr_any(tun_src)) { memcpy(saddr, tun_src, sizeof(struct in6_addr)); } else { ipv6_dev_get_saddr(net, dev, daddr, IPV6_PREFER_SRC_PUBLIC, saddr); } rcu_read_unlock(); } /* Compute flowlabel for outer IPv6 header */ static __be32 seg6_make_flowlabel(struct net *net, struct sk_buff *skb, struct ipv6hdr *inner_hdr) { int do_flowlabel = net->ipv6.sysctl.seg6_flowlabel; __be32 flowlabel = 0; u32 hash; if (do_flowlabel > 0) { hash = skb_get_hash(skb); hash = rol32(hash, 16); flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; } else if (!do_flowlabel && skb->protocol == htons(ETH_P_IPV6)) { flowlabel = ip6_flowlabel(inner_hdr); } return flowlabel; } /* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) { struct dst_entry *dst = skb_dst(skb); struct net *net = dev_net(dst->dev); struct ipv6hdr *hdr, *inner_hdr; struct ipv6_sr_hdr *isrh; int hdrlen, tot_len, err; __be32 flowlabel; hdrlen = (osrh->hdrlen + 1) << 3; tot_len = hdrlen + sizeof(*hdr); err = skb_cow_head(skb, tot_len + skb->mac_len); if (unlikely(err)) return err; inner_hdr = ipv6_hdr(skb); flowlabel = seg6_make_flowlabel(net, skb, inner_hdr); skb_push(skb, tot_len); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); hdr = ipv6_hdr(skb); /* inherit tc, flowlabel and hlim * hlim will be decremented in ip6_forward() afterwards and * decapsulation will overwrite inner hlim with outer hlim */ if (skb->protocol == htons(ETH_P_IPV6)) { ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)), flowlabel); hdr->hop_limit = inner_hdr->hop_limit; } else { ip6_flow_hdr(hdr, 0, flowlabel); hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); /* the control block has been erased, so we have to set the * iif once again. * We read the receiving interface index directly from the * skb->skb_iif as it is done in the IPv4 receiving path (i.e.: * ip_rcv_core(...)). */ IP6CB(skb)->iif = skb->skb_iif; } hdr->nexthdr = NEXTHDR_ROUTING; isrh = (void *)hdr + sizeof(*hdr); memcpy(isrh, osrh, hdrlen); isrh->nexthdr = proto; hdr->daddr = isrh->segments[isrh->first_segment]; set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(isrh)) { err = seg6_push_hmac(net, &hdr->saddr, isrh); if (unlikely(err)) return err; } #endif hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_postpush_rcsum(skb, hdr, tot_len); return 0; } EXPORT_SYMBOL_GPL(seg6_do_srh_encap); /* encapsulate an IPv6 packet within an outer IPv6 header with reduced SRH */ static int seg6_do_srh_encap_red(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) { __u8 first_seg = osrh->first_segment; struct dst_entry *dst = skb_dst(skb); struct net *net = dev_net(dst->dev); struct ipv6hdr *hdr, *inner_hdr; int hdrlen = ipv6_optlen(osrh); int red_tlv_offset, tlv_offset; struct ipv6_sr_hdr *isrh; bool skip_srh = false; __be32 flowlabel; int tot_len, err; int red_hdrlen; int tlvs_len; if (first_seg > 0) { red_hdrlen = hdrlen - sizeof(struct in6_addr); } else { /* NOTE: if tag/flags and/or other TLVs are introduced in the * seg6_iptunnel infrastructure, they should be considered when * deciding to skip the SRH. */ skip_srh = !sr_has_hmac(osrh); red_hdrlen = skip_srh ? 0 : hdrlen; } tot_len = red_hdrlen + sizeof(struct ipv6hdr); err = skb_cow_head(skb, tot_len + skb->mac_len); if (unlikely(err)) return err; inner_hdr = ipv6_hdr(skb); flowlabel = seg6_make_flowlabel(net, skb, inner_hdr); skb_push(skb, tot_len); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); hdr = ipv6_hdr(skb); /* based on seg6_do_srh_encap() */ if (skb->protocol == htons(ETH_P_IPV6)) { ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)), flowlabel); hdr->hop_limit = inner_hdr->hop_limit; } else { ip6_flow_hdr(hdr, 0, flowlabel); hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); IP6CB(skb)->iif = skb->skb_iif; } /* no matter if we have to skip the SRH or not, the first segment * always comes in the pushed IPv6 header. */ hdr->daddr = osrh->segments[first_seg]; if (skip_srh) { hdr->nexthdr = proto; set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); goto out; } /* we cannot skip the SRH, slow path */ hdr->nexthdr = NEXTHDR_ROUTING; isrh = (void *)hdr + sizeof(struct ipv6hdr); if (unlikely(!first_seg)) { /* this is a very rare case; we have only one SID but * we cannot skip the SRH since we are carrying some * other info. */ memcpy(isrh, osrh, hdrlen); goto srcaddr; } tlv_offset = sizeof(*osrh) + (first_seg + 1) * sizeof(struct in6_addr); red_tlv_offset = tlv_offset - sizeof(struct in6_addr); memcpy(isrh, osrh, red_tlv_offset); tlvs_len = hdrlen - tlv_offset; if (unlikely(tlvs_len > 0)) { const void *s = (const void *)osrh + tlv_offset; void *d = (void *)isrh + red_tlv_offset; memcpy(d, s, tlvs_len); } --isrh->first_segment; isrh->hdrlen -= 2; srcaddr: isrh->nexthdr = proto; set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); #ifdef CONFIG_IPV6_SEG6_HMAC if (unlikely(!skip_srh && sr_has_hmac(isrh))) { err = seg6_push_hmac(net, &hdr->saddr, isrh); if (unlikely(err)) return err; } #endif out: hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_postpush_rcsum(skb, hdr, tot_len); return 0; } /* insert an SRH within an IPv6 packet, just after the IPv6 header */ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) { struct ipv6hdr *hdr, *oldhdr; struct ipv6_sr_hdr *isrh; int hdrlen, err; hdrlen = (osrh->hdrlen + 1) << 3; err = skb_cow_head(skb, hdrlen + skb->mac_len); if (unlikely(err)) return err; oldhdr = ipv6_hdr(skb); skb_pull(skb, sizeof(struct ipv6hdr)); skb_postpull_rcsum(skb, skb_network_header(skb), sizeof(struct ipv6hdr)); skb_push(skb, sizeof(struct ipv6hdr) + hdrlen); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); hdr = ipv6_hdr(skb); memmove(hdr, oldhdr, sizeof(*hdr)); isrh = (void *)hdr + sizeof(*hdr); memcpy(isrh, osrh, hdrlen); isrh->nexthdr = hdr->nexthdr; hdr->nexthdr = NEXTHDR_ROUTING; isrh->segments[0] = hdr->daddr; hdr->daddr = isrh->segments[isrh->first_segment]; #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(isrh)) { struct net *net = dev_net(skb_dst(skb)->dev); err = seg6_push_hmac(net, &hdr->saddr, isrh); if (unlikely(err)) return err; } #endif hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen); return 0; } EXPORT_SYMBOL_GPL(seg6_do_srh_inline); static int seg6_do_srh(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct seg6_iptunnel_encap *tinfo; int proto, err = 0; tinfo = seg6_encap_lwtunnel(dst->lwtstate); switch (tinfo->mode) { case SEG6_IPTUN_MODE_INLINE: if (skb->protocol != htons(ETH_P_IPV6)) return -EINVAL; err = seg6_do_srh_inline(skb, tinfo->srh); if (err) return err; break; case SEG6_IPTUN_MODE_ENCAP: case SEG6_IPTUN_MODE_ENCAP_RED: err = iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6); if (err) return err; if (skb->protocol == htons(ETH_P_IPV6)) proto = IPPROTO_IPV6; else if (skb->protocol == htons(ETH_P_IP)) proto = IPPROTO_IPIP; else return -EINVAL; if (tinfo->mode == SEG6_IPTUN_MODE_ENCAP) err = seg6_do_srh_encap(skb, tinfo->srh, proto); else err = seg6_do_srh_encap_red(skb, tinfo->srh, proto); if (err) return err; skb_set_inner_transport_header(skb, skb_transport_offset(skb)); skb_set_inner_protocol(skb, skb->protocol); skb->protocol = htons(ETH_P_IPV6); break; case SEG6_IPTUN_MODE_L2ENCAP: case SEG6_IPTUN_MODE_L2ENCAP_RED: if (!skb_mac_header_was_set(skb)) return -EINVAL; if (pskb_expand_head(skb, skb->mac_len, 0, GFP_ATOMIC) < 0) return -ENOMEM; skb_mac_header_rebuild(skb); skb_push(skb, skb->mac_len); if (tinfo->mode == SEG6_IPTUN_MODE_L2ENCAP) err = seg6_do_srh_encap(skb, tinfo->srh, IPPROTO_ETHERNET); else err = seg6_do_srh_encap_red(skb, tinfo->srh, IPPROTO_ETHERNET); if (err) return err; skb->protocol = htons(ETH_P_IPV6); break; } skb_set_transport_header(skb, sizeof(struct ipv6hdr)); nf_reset_ct(skb); return 0; } static int seg6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { return dst_input(skb); } static int seg6_input_core(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *orig_dst = skb_dst(skb); struct dst_entry *dst = NULL; struct seg6_lwt *slwt; int err; err = seg6_do_srh(skb); if (unlikely(err)) goto drop; slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); local_bh_disable(); dst = dst_cache_get(&slwt->cache); if (!dst) { ip6_route_input(skb); dst = skb_dst(skb); if (!dst->error) { dst_cache_set_ip6(&slwt->cache, dst, &ipv6_hdr(skb)->saddr); } } else { skb_dst_drop(skb); skb_dst_set(skb, dst); } local_bh_enable(); err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); if (unlikely(err)) goto drop; if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, dev_net(skb->dev), NULL, skb, NULL, skb_dst(skb)->dev, seg6_input_finish); return seg6_input_finish(dev_net(skb->dev), NULL, skb); drop: kfree_skb(skb); return err; } static int seg6_input_nf(struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; struct net *net = dev_net(skb->dev); switch (skb->protocol) { case htons(ETH_P_IP): return NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, NULL, skb, NULL, dev, seg6_input_core); case htons(ETH_P_IPV6): return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, NULL, skb, NULL, dev, seg6_input_core); } return -EINVAL; } static int seg6_input(struct sk_buff *skb) { if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return seg6_input_nf(skb); return seg6_input_core(dev_net(skb->dev), NULL, skb); } static int seg6_output_core(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *orig_dst = skb_dst(skb); struct dst_entry *dst = NULL; struct seg6_lwt *slwt; int err; err = seg6_do_srh(skb); if (unlikely(err)) goto drop; slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); local_bh_disable(); dst = dst_cache_get(&slwt->cache); local_bh_enable(); if (unlikely(!dst)) { struct ipv6hdr *hdr = ipv6_hdr(skb); struct flowi6 fl6; memset(&fl6, 0, sizeof(fl6)); fl6.daddr = hdr->daddr; fl6.saddr = hdr->saddr; fl6.flowlabel = ip6_flowinfo(hdr); fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = hdr->nexthdr; dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { err = dst->error; dst_release(dst); goto drop; } local_bh_disable(); dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr); local_bh_enable(); } skb_dst_drop(skb); skb_dst_set(skb, dst); err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); if (unlikely(err)) goto drop; if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); return dst_output(net, sk, skb); drop: kfree_skb(skb); return err; } static int seg6_output_nf(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; switch (skb->protocol) { case htons(ETH_P_IP): return NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, dev, seg6_output_core); case htons(ETH_P_IPV6): return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, NULL, dev, seg6_output_core); } return -EINVAL; } static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return seg6_output_nf(net, sk, skb); return seg6_output_core(net, sk, skb); } static int seg6_build_state(struct net *net, struct nlattr *nla, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack) { struct nlattr *tb[SEG6_IPTUNNEL_MAX + 1]; struct seg6_iptunnel_encap *tuninfo; struct lwtunnel_state *newts; int tuninfo_len, min_size; struct seg6_lwt *slwt; int err; if (family != AF_INET && family != AF_INET6) return -EINVAL; err = nla_parse_nested_deprecated(tb, SEG6_IPTUNNEL_MAX, nla, seg6_iptunnel_policy, extack); if (err < 0) return err; if (!tb[SEG6_IPTUNNEL_SRH]) return -EINVAL; tuninfo = nla_data(tb[SEG6_IPTUNNEL_SRH]); tuninfo_len = nla_len(tb[SEG6_IPTUNNEL_SRH]); /* tuninfo must contain at least the iptunnel encap structure, * the SRH and one segment */ min_size = sizeof(*tuninfo) + sizeof(struct ipv6_sr_hdr) + sizeof(struct in6_addr); if (tuninfo_len < min_size) return -EINVAL; switch (tuninfo->mode) { case SEG6_IPTUN_MODE_INLINE: if (family != AF_INET6) return -EINVAL; break; case SEG6_IPTUN_MODE_ENCAP: break; case SEG6_IPTUN_MODE_L2ENCAP: break; case SEG6_IPTUN_MODE_ENCAP_RED: break; case SEG6_IPTUN_MODE_L2ENCAP_RED: break; default: return -EINVAL; } /* verify that SRH is consistent */ if (!seg6_validate_srh(tuninfo->srh, tuninfo_len - sizeof(*tuninfo), false)) return -EINVAL; newts = lwtunnel_state_alloc(tuninfo_len + sizeof(*slwt)); if (!newts) return -ENOMEM; slwt = seg6_lwt_lwtunnel(newts); err = dst_cache_init(&slwt->cache, GFP_ATOMIC); if (err) { kfree(newts); return err; } memcpy(&slwt->tuninfo, tuninfo, tuninfo_len); newts->type = LWTUNNEL_ENCAP_SEG6; newts->flags |= LWTUNNEL_STATE_INPUT_REDIRECT; if (tuninfo->mode != SEG6_IPTUN_MODE_L2ENCAP) newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT; newts->headroom = seg6_lwt_headroom(tuninfo); *ts = newts; return 0; } static void seg6_destroy_state(struct lwtunnel_state *lwt) { dst_cache_destroy(&seg6_lwt_lwtunnel(lwt)->cache); } static int seg6_fill_encap_info(struct sk_buff *skb, struct lwtunnel_state *lwtstate) { struct seg6_iptunnel_encap *tuninfo = seg6_encap_lwtunnel(lwtstate); if (nla_put_srh(skb, SEG6_IPTUNNEL_SRH, tuninfo)) return -EMSGSIZE; return 0; } static int seg6_encap_nlsize(struct lwtunnel_state *lwtstate) { struct seg6_iptunnel_encap *tuninfo = seg6_encap_lwtunnel(lwtstate); return nla_total_size(SEG6_IPTUN_ENCAP_SIZE(tuninfo)); } static int seg6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) { struct seg6_iptunnel_encap *a_hdr = seg6_encap_lwtunnel(a); struct seg6_iptunnel_encap *b_hdr = seg6_encap_lwtunnel(b); int len = SEG6_IPTUN_ENCAP_SIZE(a_hdr); if (len != SEG6_IPTUN_ENCAP_SIZE(b_hdr)) return 1; return memcmp(a_hdr, b_hdr, len); } static const struct lwtunnel_encap_ops seg6_iptun_ops = { .build_state = seg6_build_state, .destroy_state = seg6_destroy_state, .output = seg6_output, .input = seg6_input, .fill_encap = seg6_fill_encap_info, .get_encap_size = seg6_encap_nlsize, .cmp_encap = seg6_encap_cmp, .owner = THIS_MODULE, }; int __init seg6_iptunnel_init(void) { return lwtunnel_encap_add_ops(&seg6_iptun_ops, LWTUNNEL_ENCAP_SEG6); } void seg6_iptunnel_exit(void) { lwtunnel_encap_del_ops(&seg6_iptun_ops, LWTUNNEL_ENCAP_SEG6); } |
| 30 3 3 3 3 1 1 1 1 1 3 3 3 2 3 1 1 1 1 1 1 1 1 1 1 1 1 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_TC_PED_H #define __NET_TC_PED_H #include <net/act_api.h> #include <linux/tc_act/tc_pedit.h> #include <linux/types.h> struct tcf_pedit_key_ex { enum pedit_header_type htype; enum pedit_cmd cmd; }; struct tcf_pedit_parms { struct tc_pedit_key *tcfp_keys; struct tcf_pedit_key_ex *tcfp_keys_ex; u32 tcfp_off_max_hint; unsigned char tcfp_nkeys; unsigned char tcfp_flags; struct rcu_head rcu; }; struct tcf_pedit { struct tc_action common; struct tcf_pedit_parms __rcu *parms; }; #define to_pedit(a) ((struct tcf_pedit *)a) #define to_pedit_parms(a) (rcu_dereference(to_pedit(a)->parms)) static inline bool is_tcf_pedit(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT if (a->ops && a->ops->id == TCA_ID_PEDIT) return true; #endif return false; } static inline int tcf_pedit_nkeys(const struct tc_action *a) { struct tcf_pedit_parms *parms; int nkeys; rcu_read_lock(); parms = to_pedit_parms(a); nkeys = parms->tcfp_nkeys; rcu_read_unlock(); return nkeys; } static inline u32 tcf_pedit_htype(const struct tc_action *a, int index) { u32 htype = TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK; struct tcf_pedit_parms *parms; rcu_read_lock(); parms = to_pedit_parms(a); if (parms->tcfp_keys_ex) htype = parms->tcfp_keys_ex[index].htype; rcu_read_unlock(); return htype; } static inline u32 tcf_pedit_cmd(const struct tc_action *a, int index) { struct tcf_pedit_parms *parms; u32 cmd = __PEDIT_CMD_MAX; rcu_read_lock(); parms = to_pedit_parms(a); if (parms->tcfp_keys_ex) cmd = parms->tcfp_keys_ex[index].cmd; rcu_read_unlock(); return cmd; } static inline u32 tcf_pedit_mask(const struct tc_action *a, int index) { struct tcf_pedit_parms *parms; u32 mask; rcu_read_lock(); parms = to_pedit_parms(a); mask = parms->tcfp_keys[index].mask; rcu_read_unlock(); return mask; } static inline u32 tcf_pedit_val(const struct tc_action *a, int index) { struct tcf_pedit_parms *parms; u32 val; rcu_read_lock(); parms = to_pedit_parms(a); val = parms->tcfp_keys[index].val; rcu_read_unlock(); return val; } static inline u32 tcf_pedit_offset(const struct tc_action *a, int index) { struct tcf_pedit_parms *parms; u32 off; rcu_read_lock(); parms = to_pedit_parms(a); off = parms->tcfp_keys[index].off; rcu_read_unlock(); return off; } #endif /* __NET_TC_PED_H */ |
| 4 6 6 6 1 5 2 5 4 5 5 4 4 4 2 5 5 5 5 29 30 31 29 27 31 31 6 6 5 3 3 3 3 3 4 4 4 4 4 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/usb/core/generic.c - generic driver for USB devices (not interfaces) * * (C) Copyright 2005 Greg Kroah-Hartman <gregkh@suse.de> * * based on drivers/usb/usb.c which had the following copyrights: * (C) Copyright Linus Torvalds 1999 * (C) Copyright Johannes Erdfelt 1999-2001 * (C) Copyright Andreas Gal 1999 * (C) Copyright Gregory P. Smith 1999 * (C) Copyright Deti Fliegl 1999 (new USB architecture) * (C) Copyright Randy Dunlap 2000 * (C) Copyright David Brownell 2000-2004 * (C) Copyright Yggdrasil Computing, Inc. 2000 * (usb_device_id matching changes by Adam J. Richter) * (C) Copyright Greg Kroah-Hartman 2002-2003 * * Released under the GPLv2 only. */ #include <linux/usb.h> #include <linux/usb/hcd.h> #include <uapi/linux/usb/audio.h> #include "usb.h" static inline const char *plural(int n) { return (n == 1 ? "" : "s"); } static int is_rndis(struct usb_interface_descriptor *desc) { return desc->bInterfaceClass == USB_CLASS_COMM && desc->bInterfaceSubClass == 2 && desc->bInterfaceProtocol == 0xff; } static int is_activesync(struct usb_interface_descriptor *desc) { return desc->bInterfaceClass == USB_CLASS_MISC && desc->bInterfaceSubClass == 1 && desc->bInterfaceProtocol == 1; } static bool is_audio(struct usb_interface_descriptor *desc) { return desc->bInterfaceClass == USB_CLASS_AUDIO; } static bool is_uac3_config(struct usb_interface_descriptor *desc) { return desc->bInterfaceProtocol == UAC_VERSION_3; } int usb_choose_configuration(struct usb_device *udev) { int i; int num_configs; int insufficient_power = 0; struct usb_host_config *c, *best; struct usb_device_driver *udriver; /* * If a USB device (not an interface) doesn't have a driver then the * kernel has no business trying to select or install a configuration * for it. */ if (!udev->dev.driver) return -1; udriver = to_usb_device_driver(udev->dev.driver); if (usb_device_is_owned(udev)) return 0; if (udriver->choose_configuration) { i = udriver->choose_configuration(udev); if (i >= 0) return i; } best = NULL; c = udev->config; num_configs = udev->descriptor.bNumConfigurations; for (i = 0; i < num_configs; (i++, c++)) { struct usb_interface_descriptor *desc = NULL; /* It's possible that a config has no interfaces! */ if (c->desc.bNumInterfaces > 0) desc = &c->intf_cache[0]->altsetting->desc; /* * HP's USB bus-powered keyboard has only one configuration * and it claims to be self-powered; other devices may have * similar errors in their descriptors. If the next test * were allowed to execute, such configurations would always * be rejected and the devices would not work as expected. * In the meantime, we run the risk of selecting a config * that requires external power at a time when that power * isn't available. It seems to be the lesser of two evils. * * Bugzilla #6448 reports a device that appears to crash * when it receives a GET_DEVICE_STATUS request! We don't * have any other way to tell whether a device is self-powered, * but since we don't use that information anywhere but here, * the call has been removed. * * Maybe the GET_DEVICE_STATUS call and the test below can * be reinstated when device firmwares become more reliable. * Don't hold your breath. */ #if 0 /* Rule out self-powered configs for a bus-powered device */ if (bus_powered && (c->desc.bmAttributes & USB_CONFIG_ATT_SELFPOWER)) continue; #endif /* * The next test may not be as effective as it should be. * Some hubs have errors in their descriptor, claiming * to be self-powered when they are really bus-powered. * We will overestimate the amount of current such hubs * make available for each port. * * This is a fairly benign sort of failure. It won't * cause us to reject configurations that we should have * accepted. */ /* Rule out configs that draw too much bus current */ if (usb_get_max_power(udev, c) > udev->bus_mA) { insufficient_power++; continue; } /* * Select first configuration as default for audio so that * devices that don't comply with UAC3 protocol are supported. * But, still iterate through other configurations and * select UAC3 compliant config if present. */ if (desc && is_audio(desc)) { /* Always prefer the first found UAC3 config */ if (is_uac3_config(desc)) { best = c; break; } /* If there is no UAC3 config, prefer the first config */ else if (i == 0) best = c; /* Unconditional continue, because the rest of the code * in the loop is irrelevant for audio devices, and * because it can reassign best, which for audio devices * we don't want. */ continue; } /* When the first config's first interface is one of Microsoft's * pet nonstandard Ethernet-over-USB protocols, ignore it unless * this kernel has enabled the necessary host side driver. * But: Don't ignore it if it's the only config. */ if (i == 0 && num_configs > 1 && desc && (is_rndis(desc) || is_activesync(desc))) { #if !defined(CONFIG_USB_NET_RNDIS_HOST) && !defined(CONFIG_USB_NET_RNDIS_HOST_MODULE) continue; #else best = c; #endif } /* From the remaining configs, choose the first one whose * first interface is for a non-vendor-specific class. * Reason: Linux is more likely to have a class driver * than a vendor-specific driver. */ else if (udev->descriptor.bDeviceClass != USB_CLASS_VENDOR_SPEC && (desc && desc->bInterfaceClass != USB_CLASS_VENDOR_SPEC)) { best = c; break; } /* If all the remaining configs are vendor-specific, * choose the first one. */ else if (!best) best = c; } if (insufficient_power > 0) dev_info(&udev->dev, "rejected %d configuration%s " "due to insufficient available bus power\n", insufficient_power, plural(insufficient_power)); if (best) { i = best->desc.bConfigurationValue; dev_dbg(&udev->dev, "configuration #%d chosen from %d choice%s\n", i, num_configs, plural(num_configs)); } else { i = -1; dev_warn(&udev->dev, "no configuration chosen from %d choice%s\n", num_configs, plural(num_configs)); } return i; } EXPORT_SYMBOL_GPL(usb_choose_configuration); static int __check_for_non_generic_match(struct device_driver *drv, void *data) { struct usb_device *udev = data; struct usb_device_driver *udrv; if (!is_usb_device_driver(drv)) return 0; udrv = to_usb_device_driver(drv); if (udrv == &usb_generic_driver) return 0; return usb_driver_applicable(udev, udrv); } static bool usb_generic_driver_match(struct usb_device *udev) { if (udev->use_generic_driver) return true; /* * If any other driver wants the device, leave the device to this other * driver. */ if (bus_for_each_drv(&usb_bus_type, NULL, udev, __check_for_non_generic_match)) return false; return true; } int usb_generic_driver_probe(struct usb_device *udev) { int err, c; /* Choose and set the configuration. This registers the interfaces * with the driver core and lets interface drivers bind to them. */ if (udev->authorized == 0) dev_err(&udev->dev, "Device is not authorized for usage\n"); else { c = usb_choose_configuration(udev); if (c >= 0) { err = usb_set_configuration(udev, c); if (err && err != -ENODEV) { dev_err(&udev->dev, "can't set config #%d, error %d\n", c, err); /* This need not be fatal. The user can try to * set other configurations. */ } } } /* USB device state == configured ... usable */ usb_notify_add_device(udev); return 0; } void usb_generic_driver_disconnect(struct usb_device *udev) { usb_notify_remove_device(udev); /* if this is only an unbind, not a physical disconnect, then * unconfigure the device */ if (udev->actconfig) usb_set_configuration(udev, -1); } #ifdef CONFIG_PM int usb_generic_driver_suspend(struct usb_device *udev, pm_message_t msg) { int rc; /* Normal USB devices suspend through their upstream port. * Root hubs don't have upstream ports to suspend, * so we have to shut down their downstream HC-to-USB * interfaces manually by doing a bus (or "global") suspend. */ if (!udev->parent) rc = hcd_bus_suspend(udev, msg); /* * Non-root USB2 devices don't need to do anything for FREEZE * or PRETHAW. USB3 devices don't support global suspend and * needs to be selectively suspended. */ else if ((msg.event == PM_EVENT_FREEZE || msg.event == PM_EVENT_PRETHAW) && (udev->speed < USB_SPEED_SUPER)) rc = 0; else rc = usb_port_suspend(udev, msg); if (rc == 0) usbfs_notify_suspend(udev); return rc; } int usb_generic_driver_resume(struct usb_device *udev, pm_message_t msg) { int rc; /* Normal USB devices resume/reset through their upstream port. * Root hubs don't have upstream ports to resume or reset, * so we have to start up their downstream HC-to-USB * interfaces manually by doing a bus (or "global") resume. */ if (!udev->parent) rc = hcd_bus_resume(udev, msg); else rc = usb_port_resume(udev, msg); if (rc == 0) usbfs_notify_resume(udev); return rc; } #endif /* CONFIG_PM */ struct usb_device_driver usb_generic_driver = { .name = "usb", .match = usb_generic_driver_match, .probe = usb_generic_driver_probe, .disconnect = usb_generic_driver_disconnect, #ifdef CONFIG_PM .suspend = usb_generic_driver_suspend, .resume = usb_generic_driver_resume, #endif .supports_autosuspend = 1, }; |
| 14 15 15 14 10 15 14 1 1 14 7 15 15 9 1 1 15 15 15 15 15 15 15 5 15 15 15 5 5 15 15 15 15 15 15 14 15 15 15 15 2 2 2 2 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 3 3 3 3 1 1 1 3 2 2 2 2 2 2 2 2 2 2 1 1 2 2 2 1 2 2 2 2 2 2 2 2 2 2 2 2 2 3 3 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_fq.c Fair Queue Packet Scheduler (per flow pacing) * * Copyright (C) 2013-2023 Eric Dumazet <edumazet@google.com> * * Meant to be mostly used for locally generated traffic : * Fast classification depends on skb->sk being set before reaching us. * If not, (router workload), we use rxhash as fallback, with 32 bits wide hash. * All packets belonging to a socket are considered as a 'flow'. * * Flows are dynamically allocated and stored in a hash table of RB trees * They are also part of one Round Robin 'queues' (new or old flows) * * Burst avoidance (aka pacing) capability : * * Transport (eg TCP) can set in sk->sk_pacing_rate a rate, enqueue a * bunch of packets, and this packet scheduler adds delay between * packets to respect rate limitation. * * enqueue() : * - lookup one RB tree (out of 1024 or more) to find the flow. * If non existent flow, create it, add it to the tree. * Add skb to the per flow list of skb (fifo). * - Use a special fifo for high prio packets * * dequeue() : serves flows in Round Robin * Note : When a flow becomes empty, we do not immediately remove it from * rb trees, for performance reasons (its expected to send additional packets, * or SLAB cache will reuse socket for another flow) */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/hash.h> #include <linux/prefetch.h> #include <linux/vmalloc.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/sock.h> #include <net/tcp_states.h> #include <net/tcp.h> struct fq_skb_cb { u64 time_to_send; u8 band; }; static inline struct fq_skb_cb *fq_skb_cb(struct sk_buff *skb) { qdisc_cb_private_validate(skb, sizeof(struct fq_skb_cb)); return (struct fq_skb_cb *)qdisc_skb_cb(skb)->data; } /* * Per flow structure, dynamically allocated. * If packets have monotically increasing time_to_send, they are placed in O(1) * in linear list (head,tail), otherwise are placed in a rbtree (t_root). */ struct fq_flow { /* First cache line : used in fq_gc(), fq_enqueue(), fq_dequeue() */ struct rb_root t_root; struct sk_buff *head; /* list of skbs for this flow : first skb */ union { struct sk_buff *tail; /* last skb in the list */ unsigned long age; /* (jiffies | 1UL) when flow was emptied, for gc */ }; union { struct rb_node fq_node; /* anchor in fq_root[] trees */ /* Following field is only used for q->internal, * because q->internal is not hashed in fq_root[] */ u64 stat_fastpath_packets; }; struct sock *sk; u32 socket_hash; /* sk_hash */ int qlen; /* number of packets in flow queue */ /* Second cache line */ int credit; int band; struct fq_flow *next; /* next pointer in RR lists */ struct rb_node rate_node; /* anchor in q->delayed tree */ u64 time_next_packet; }; struct fq_flow_head { struct fq_flow *first; struct fq_flow *last; }; struct fq_perband_flows { struct fq_flow_head new_flows; struct fq_flow_head old_flows; int credit; int quantum; /* based on band nr : 576KB, 192KB, 64KB */ }; #define FQ_PRIO2BAND_CRUMB_SIZE ((TC_PRIO_MAX + 1) >> 2) struct fq_sched_data { /* Read mostly cache line */ u32 quantum; u32 initial_quantum; u32 flow_refill_delay; u32 flow_plimit; /* max packets per flow */ unsigned long flow_max_rate; /* optional max rate per flow */ u64 ce_threshold; u64 horizon; /* horizon in ns */ u32 orphan_mask; /* mask for orphaned skb */ u32 low_rate_threshold; struct rb_root *fq_root; u8 rate_enable; u8 fq_trees_log; u8 horizon_drop; u8 prio2band[FQ_PRIO2BAND_CRUMB_SIZE]; u32 timer_slack; /* hrtimer slack in ns */ /* Read/Write fields. */ unsigned int band_nr; /* band being serviced in fq_dequeue() */ struct fq_perband_flows band_flows[FQ_BANDS]; struct fq_flow internal; /* fastpath queue. */ struct rb_root delayed; /* for rate limited flows */ u64 time_next_delayed_flow; unsigned long unthrottle_latency_ns; u32 band_pkt_count[FQ_BANDS]; u32 flows; u32 inactive_flows; /* Flows with no packet to send. */ u32 throttled_flows; u64 stat_throttled; struct qdisc_watchdog watchdog; u64 stat_gc_flows; /* Seldom used fields. */ u64 stat_band_drops[FQ_BANDS]; u64 stat_ce_mark; u64 stat_horizon_drops; u64 stat_horizon_caps; u64 stat_flows_plimit; u64 stat_pkts_too_long; u64 stat_allocation_errors; }; /* return the i-th 2-bit value ("crumb") */ static u8 fq_prio2band(const u8 *prio2band, unsigned int prio) { return (READ_ONCE(prio2band[prio / 4]) >> (2 * (prio & 0x3))) & 0x3; } /* * f->tail and f->age share the same location. * We can use the low order bit to differentiate if this location points * to a sk_buff or contains a jiffies value, if we force this value to be odd. * This assumes f->tail low order bit must be 0 since alignof(struct sk_buff) >= 2 */ static void fq_flow_set_detached(struct fq_flow *f) { f->age = jiffies | 1UL; } static bool fq_flow_is_detached(const struct fq_flow *f) { return !!(f->age & 1UL); } /* special value to mark a throttled flow (not on old/new list) */ static struct fq_flow throttled; static bool fq_flow_is_throttled(const struct fq_flow *f) { return f->next == &throttled; } enum new_flow { NEW_FLOW, OLD_FLOW }; static void fq_flow_add_tail(struct fq_sched_data *q, struct fq_flow *flow, enum new_flow list_sel) { struct fq_perband_flows *pband = &q->band_flows[flow->band]; struct fq_flow_head *head = (list_sel == NEW_FLOW) ? &pband->new_flows : &pband->old_flows; if (head->first) head->last->next = flow; else head->first = flow; head->last = flow; flow->next = NULL; } static void fq_flow_unset_throttled(struct fq_sched_data *q, struct fq_flow *f) { rb_erase(&f->rate_node, &q->delayed); q->throttled_flows--; fq_flow_add_tail(q, f, OLD_FLOW); } static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f) { struct rb_node **p = &q->delayed.rb_node, *parent = NULL; while (*p) { struct fq_flow *aux; parent = *p; aux = rb_entry(parent, struct fq_flow, rate_node); if (f->time_next_packet >= aux->time_next_packet) p = &parent->rb_right; else p = &parent->rb_left; } rb_link_node(&f->rate_node, parent, p); rb_insert_color(&f->rate_node, &q->delayed); q->throttled_flows++; q->stat_throttled++; f->next = &throttled; if (q->time_next_delayed_flow > f->time_next_packet) q->time_next_delayed_flow = f->time_next_packet; } static struct kmem_cache *fq_flow_cachep __read_mostly; /* limit number of collected flows per round */ #define FQ_GC_MAX 8 #define FQ_GC_AGE (3*HZ) static bool fq_gc_candidate(const struct fq_flow *f) { return fq_flow_is_detached(f) && time_after(jiffies, f->age + FQ_GC_AGE); } static void fq_gc(struct fq_sched_data *q, struct rb_root *root, struct sock *sk) { struct rb_node **p, *parent; void *tofree[FQ_GC_MAX]; struct fq_flow *f; int i, fcnt = 0; p = &root->rb_node; parent = NULL; while (*p) { parent = *p; f = rb_entry(parent, struct fq_flow, fq_node); if (f->sk == sk) break; if (fq_gc_candidate(f)) { tofree[fcnt++] = f; if (fcnt == FQ_GC_MAX) break; } if (f->sk > sk) p = &parent->rb_right; else p = &parent->rb_left; } if (!fcnt) return; for (i = fcnt; i > 0; ) { f = tofree[--i]; rb_erase(&f->fq_node, root); } q->flows -= fcnt; q->inactive_flows -= fcnt; q->stat_gc_flows += fcnt; kmem_cache_free_bulk(fq_flow_cachep, fcnt, tofree); } /* Fast path can be used if : * 1) Packet tstamp is in the past. * 2) FQ qlen == 0 OR * (no flow is currently eligible for transmit, * AND fast path queue has less than 8 packets) * 3) No SO_MAX_PACING_RATE on the socket (if any). * 4) No @maxrate attribute on this qdisc, * * FQ can not use generic TCQ_F_CAN_BYPASS infrastructure. */ static bool fq_fastpath_check(const struct Qdisc *sch, struct sk_buff *skb, u64 now) { const struct fq_sched_data *q = qdisc_priv(sch); const struct sock *sk; if (fq_skb_cb(skb)->time_to_send > now) return false; if (sch->q.qlen != 0) { /* Even if some packets are stored in this qdisc, * we can still enable fast path if all of them are * scheduled in the future (ie no flows are eligible) * or in the fast path queue. */ if (q->flows != q->inactive_flows + q->throttled_flows) return false; /* Do not allow fast path queue to explode, we want Fair Queue mode * under pressure. */ if (q->internal.qlen >= 8) return false; } sk = skb->sk; if (sk && sk_fullsock(sk) && !sk_is_tcp(sk) && sk->sk_max_pacing_rate != ~0UL) return false; if (q->flow_max_rate != ~0UL) return false; return true; } static struct fq_flow *fq_classify(struct Qdisc *sch, struct sk_buff *skb, u64 now) { struct fq_sched_data *q = qdisc_priv(sch); struct rb_node **p, *parent; struct sock *sk = skb->sk; struct rb_root *root; struct fq_flow *f; /* SYNACK messages are attached to a TCP_NEW_SYN_RECV request socket * or a listener (SYNCOOKIE mode) * 1) request sockets are not full blown, * they do not contain sk_pacing_rate * 2) They are not part of a 'flow' yet * 3) We do not want to rate limit them (eg SYNFLOOD attack), * especially if the listener set SO_MAX_PACING_RATE * 4) We pretend they are orphaned */ if (!sk || sk_listener(sk)) { unsigned long hash = skb_get_hash(skb) & q->orphan_mask; /* By forcing low order bit to 1, we make sure to not * collide with a local flow (socket pointers are word aligned) */ sk = (struct sock *)((hash << 1) | 1UL); skb_orphan(skb); } else if (sk->sk_state == TCP_CLOSE) { unsigned long hash = skb_get_hash(skb) & q->orphan_mask; /* * Sockets in TCP_CLOSE are non connected. * Typical use case is UDP sockets, they can send packets * with sendto() to many different destinations. * We probably could use a generic bit advertising * non connected sockets, instead of sk_state == TCP_CLOSE, * if we care enough. */ sk = (struct sock *)((hash << 1) | 1UL); } if (fq_fastpath_check(sch, skb, now)) { q->internal.stat_fastpath_packets++; if (skb->sk == sk && q->rate_enable && READ_ONCE(sk->sk_pacing_status) != SK_PACING_FQ) smp_store_release(&sk->sk_pacing_status, SK_PACING_FQ); return &q->internal; } root = &q->fq_root[hash_ptr(sk, q->fq_trees_log)]; fq_gc(q, root, sk); p = &root->rb_node; parent = NULL; while (*p) { parent = *p; f = rb_entry(parent, struct fq_flow, fq_node); if (f->sk == sk) { /* socket might have been reallocated, so check * if its sk_hash is the same. * It not, we need to refill credit with * initial quantum */ if (unlikely(skb->sk == sk && f->socket_hash != sk->sk_hash)) { f->credit = q->initial_quantum; f->socket_hash = sk->sk_hash; if (q->rate_enable) smp_store_release(&sk->sk_pacing_status, SK_PACING_FQ); if (fq_flow_is_throttled(f)) fq_flow_unset_throttled(q, f); f->time_next_packet = 0ULL; } return f; } if (f->sk > sk) p = &parent->rb_right; else p = &parent->rb_left; } f = kmem_cache_zalloc(fq_flow_cachep, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!f)) { q->stat_allocation_errors++; return &q->internal; } /* f->t_root is already zeroed after kmem_cache_zalloc() */ fq_flow_set_detached(f); f->sk = sk; if (skb->sk == sk) { f->socket_hash = sk->sk_hash; if (q->rate_enable) smp_store_release(&sk->sk_pacing_status, SK_PACING_FQ); } f->credit = q->initial_quantum; rb_link_node(&f->fq_node, parent, p); rb_insert_color(&f->fq_node, root); q->flows++; q->inactive_flows++; return f; } static struct sk_buff *fq_peek(struct fq_flow *flow) { struct sk_buff *skb = skb_rb_first(&flow->t_root); struct sk_buff *head = flow->head; if (!skb) return head; if (!head) return skb; if (fq_skb_cb(skb)->time_to_send < fq_skb_cb(head)->time_to_send) return skb; return head; } static void fq_erase_head(struct Qdisc *sch, struct fq_flow *flow, struct sk_buff *skb) { if (skb == flow->head) { flow->head = skb->next; } else { rb_erase(&skb->rbnode, &flow->t_root); skb->dev = qdisc_dev(sch); } } /* Remove one skb from flow queue. * This skb must be the return value of prior fq_peek(). */ static void fq_dequeue_skb(struct Qdisc *sch, struct fq_flow *flow, struct sk_buff *skb) { fq_erase_head(sch, flow, skb); skb_mark_not_on_list(skb); qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; } static void flow_queue_add(struct fq_flow *flow, struct sk_buff *skb) { struct rb_node **p, *parent; struct sk_buff *head, *aux; head = flow->head; if (!head || fq_skb_cb(skb)->time_to_send >= fq_skb_cb(flow->tail)->time_to_send) { if (!head) flow->head = skb; else flow->tail->next = skb; flow->tail = skb; skb->next = NULL; return; } p = &flow->t_root.rb_node; parent = NULL; while (*p) { parent = *p; aux = rb_to_skb(parent); if (fq_skb_cb(skb)->time_to_send >= fq_skb_cb(aux)->time_to_send) p = &parent->rb_right; else p = &parent->rb_left; } rb_link_node(&skb->rbnode, parent, p); rb_insert_color(&skb->rbnode, &flow->t_root); } static bool fq_packet_beyond_horizon(const struct sk_buff *skb, const struct fq_sched_data *q, u64 now) { return unlikely((s64)skb->tstamp > (s64)(now + q->horizon)); } static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct fq_sched_data *q = qdisc_priv(sch); struct fq_flow *f; u64 now; u8 band; band = fq_prio2band(q->prio2band, skb->priority & TC_PRIO_MAX); if (unlikely(q->band_pkt_count[band] >= sch->limit)) { q->stat_band_drops[band]++; return qdisc_drop(skb, sch, to_free); } now = ktime_get_ns(); if (!skb->tstamp) { fq_skb_cb(skb)->time_to_send = now; } else { /* Check if packet timestamp is too far in the future. */ if (fq_packet_beyond_horizon(skb, q, now)) { if (q->horizon_drop) { q->stat_horizon_drops++; return qdisc_drop(skb, sch, to_free); } q->stat_horizon_caps++; skb->tstamp = now + q->horizon; } fq_skb_cb(skb)->time_to_send = skb->tstamp; } f = fq_classify(sch, skb, now); if (f != &q->internal) { if (unlikely(f->qlen >= q->flow_plimit)) { q->stat_flows_plimit++; return qdisc_drop(skb, sch, to_free); } if (fq_flow_is_detached(f)) { fq_flow_add_tail(q, f, NEW_FLOW); if (time_after(jiffies, f->age + q->flow_refill_delay)) f->credit = max_t(u32, f->credit, q->quantum); } f->band = band; q->band_pkt_count[band]++; fq_skb_cb(skb)->band = band; if (f->qlen == 0) q->inactive_flows--; } f->qlen++; /* Note: this overwrites f->age */ flow_queue_add(f, skb); qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; return NET_XMIT_SUCCESS; } static void fq_check_throttled(struct fq_sched_data *q, u64 now) { unsigned long sample; struct rb_node *p; if (q->time_next_delayed_flow > now) return; /* Update unthrottle latency EWMA. * This is cheap and can help diagnosing timer/latency problems. */ sample = (unsigned long)(now - q->time_next_delayed_flow); q->unthrottle_latency_ns -= q->unthrottle_latency_ns >> 3; q->unthrottle_latency_ns += sample >> 3; q->time_next_delayed_flow = ~0ULL; while ((p = rb_first(&q->delayed)) != NULL) { struct fq_flow *f = rb_entry(p, struct fq_flow, rate_node); if (f->time_next_packet > now) { q->time_next_delayed_flow = f->time_next_packet; break; } fq_flow_unset_throttled(q, f); } } static struct fq_flow_head *fq_pband_head_select(struct fq_perband_flows *pband) { if (pband->credit <= 0) return NULL; if (pband->new_flows.first) return &pband->new_flows; return pband->old_flows.first ? &pband->old_flows : NULL; } static struct sk_buff *fq_dequeue(struct Qdisc *sch) { struct fq_sched_data *q = qdisc_priv(sch); struct fq_perband_flows *pband; struct fq_flow_head *head; struct sk_buff *skb; struct fq_flow *f; unsigned long rate; int retry; u32 plen; u64 now; if (!sch->q.qlen) return NULL; skb = fq_peek(&q->internal); if (unlikely(skb)) { q->internal.qlen--; fq_dequeue_skb(sch, &q->internal, skb); goto out; } now = ktime_get_ns(); fq_check_throttled(q, now); retry = 0; pband = &q->band_flows[q->band_nr]; begin: head = fq_pband_head_select(pband); if (!head) { while (++retry <= FQ_BANDS) { if (++q->band_nr == FQ_BANDS) q->band_nr = 0; pband = &q->band_flows[q->band_nr]; pband->credit = min(pband->credit + pband->quantum, pband->quantum); goto begin; } if (q->time_next_delayed_flow != ~0ULL) qdisc_watchdog_schedule_range_ns(&q->watchdog, q->time_next_delayed_flow, q->timer_slack); return NULL; } f = head->first; retry = 0; if (f->credit <= 0) { f->credit += q->quantum; head->first = f->next; fq_flow_add_tail(q, f, OLD_FLOW); goto begin; } skb = fq_peek(f); if (skb) { u64 time_next_packet = max_t(u64, fq_skb_cb(skb)->time_to_send, f->time_next_packet); if (now < time_next_packet) { head->first = f->next; f->time_next_packet = time_next_packet; fq_flow_set_throttled(q, f); goto begin; } prefetch(&skb->end); if ((s64)(now - time_next_packet - q->ce_threshold) > 0) { INET_ECN_set_ce(skb); q->stat_ce_mark++; } if (--f->qlen == 0) q->inactive_flows++; q->band_pkt_count[fq_skb_cb(skb)->band]--; fq_dequeue_skb(sch, f, skb); } else { head->first = f->next; /* force a pass through old_flows to prevent starvation */ if (head == &pband->new_flows) { fq_flow_add_tail(q, f, OLD_FLOW); } else { fq_flow_set_detached(f); } goto begin; } plen = qdisc_pkt_len(skb); f->credit -= plen; pband->credit -= plen; if (!q->rate_enable) goto out; rate = q->flow_max_rate; /* If EDT time was provided for this skb, we need to * update f->time_next_packet only if this qdisc enforces * a flow max rate. */ if (!skb->tstamp) { if (skb->sk) rate = min(READ_ONCE(skb->sk->sk_pacing_rate), rate); if (rate <= q->low_rate_threshold) { f->credit = 0; } else { plen = max(plen, q->quantum); if (f->credit > 0) goto out; } } if (rate != ~0UL) { u64 len = (u64)plen * NSEC_PER_SEC; if (likely(rate)) len = div64_ul(len, rate); /* Since socket rate can change later, * clamp the delay to 1 second. * Really, providers of too big packets should be fixed ! */ if (unlikely(len > NSEC_PER_SEC)) { len = NSEC_PER_SEC; q->stat_pkts_too_long++; } /* Account for schedule/timers drifts. * f->time_next_packet was set when prior packet was sent, * and current time (@now) can be too late by tens of us. */ if (f->time_next_packet) len -= min(len/2, now - f->time_next_packet); f->time_next_packet = now + len; } out: qdisc_bstats_update(sch, skb); return skb; } static void fq_flow_purge(struct fq_flow *flow) { struct rb_node *p = rb_first(&flow->t_root); while (p) { struct sk_buff *skb = rb_to_skb(p); p = rb_next(p); rb_erase(&skb->rbnode, &flow->t_root); rtnl_kfree_skbs(skb, skb); } rtnl_kfree_skbs(flow->head, flow->tail); flow->head = NULL; flow->qlen = 0; } static void fq_reset(struct Qdisc *sch) { struct fq_sched_data *q = qdisc_priv(sch); struct rb_root *root; struct rb_node *p; struct fq_flow *f; unsigned int idx; sch->q.qlen = 0; sch->qstats.backlog = 0; fq_flow_purge(&q->internal); if (!q->fq_root) return; for (idx = 0; idx < (1U << q->fq_trees_log); idx++) { root = &q->fq_root[idx]; while ((p = rb_first(root)) != NULL) { f = rb_entry(p, struct fq_flow, fq_node); rb_erase(p, root); fq_flow_purge(f); kmem_cache_free(fq_flow_cachep, f); } } for (idx = 0; idx < FQ_BANDS; idx++) { q->band_flows[idx].new_flows.first = NULL; q->band_flows[idx].old_flows.first = NULL; } q->delayed = RB_ROOT; q->flows = 0; q->inactive_flows = 0; q->throttled_flows = 0; } static void fq_rehash(struct fq_sched_data *q, struct rb_root *old_array, u32 old_log, struct rb_root *new_array, u32 new_log) { struct rb_node *op, **np, *parent; struct rb_root *oroot, *nroot; struct fq_flow *of, *nf; int fcnt = 0; u32 idx; for (idx = 0; idx < (1U << old_log); idx++) { oroot = &old_array[idx]; while ((op = rb_first(oroot)) != NULL) { rb_erase(op, oroot); of = rb_entry(op, struct fq_flow, fq_node); if (fq_gc_candidate(of)) { fcnt++; kmem_cache_free(fq_flow_cachep, of); continue; } nroot = &new_array[hash_ptr(of->sk, new_log)]; np = &nroot->rb_node; parent = NULL; while (*np) { parent = *np; nf = rb_entry(parent, struct fq_flow, fq_node); BUG_ON(nf->sk == of->sk); if (nf->sk > of->sk) np = &parent->rb_right; else np = &parent->rb_left; } rb_link_node(&of->fq_node, parent, np); rb_insert_color(&of->fq_node, nroot); } } q->flows -= fcnt; q->inactive_flows -= fcnt; q->stat_gc_flows += fcnt; } static void fq_free(void *addr) { kvfree(addr); } static int fq_resize(struct Qdisc *sch, u32 log) { struct fq_sched_data *q = qdisc_priv(sch); struct rb_root *array; void *old_fq_root; u32 idx; if (q->fq_root && log == q->fq_trees_log) return 0; /* If XPS was setup, we can allocate memory on right NUMA node */ array = kvmalloc_node(sizeof(struct rb_root) << log, GFP_KERNEL | __GFP_RETRY_MAYFAIL, netdev_queue_numa_node_read(sch->dev_queue)); if (!array) return -ENOMEM; for (idx = 0; idx < (1U << log); idx++) array[idx] = RB_ROOT; sch_tree_lock(sch); old_fq_root = q->fq_root; if (old_fq_root) fq_rehash(q, old_fq_root, q->fq_trees_log, array, log); q->fq_root = array; WRITE_ONCE(q->fq_trees_log, log); sch_tree_unlock(sch); fq_free(old_fq_root); return 0; } static const struct netlink_range_validation iq_range = { .max = INT_MAX, }; static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { [TCA_FQ_UNSPEC] = { .strict_start_type = TCA_FQ_TIMER_SLACK }, [TCA_FQ_PLIMIT] = { .type = NLA_U32 }, [TCA_FQ_FLOW_PLIMIT] = { .type = NLA_U32 }, [TCA_FQ_QUANTUM] = { .type = NLA_U32 }, [TCA_FQ_INITIAL_QUANTUM] = NLA_POLICY_FULL_RANGE(NLA_U32, &iq_range), [TCA_FQ_RATE_ENABLE] = { .type = NLA_U32 }, [TCA_FQ_FLOW_DEFAULT_RATE] = { .type = NLA_U32 }, [TCA_FQ_FLOW_MAX_RATE] = { .type = NLA_U32 }, [TCA_FQ_BUCKETS_LOG] = { .type = NLA_U32 }, [TCA_FQ_FLOW_REFILL_DELAY] = { .type = NLA_U32 }, [TCA_FQ_ORPHAN_MASK] = { .type = NLA_U32 }, [TCA_FQ_LOW_RATE_THRESHOLD] = { .type = NLA_U32 }, [TCA_FQ_CE_THRESHOLD] = { .type = NLA_U32 }, [TCA_FQ_TIMER_SLACK] = { .type = NLA_U32 }, [TCA_FQ_HORIZON] = { .type = NLA_U32 }, [TCA_FQ_HORIZON_DROP] = { .type = NLA_U8 }, [TCA_FQ_PRIOMAP] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_prio_qopt)), [TCA_FQ_WEIGHTS] = NLA_POLICY_EXACT_LEN(FQ_BANDS * sizeof(s32)), }; /* compress a u8 array with all elems <= 3 to an array of 2-bit fields */ static void fq_prio2band_compress_crumb(const u8 *in, u8 *out) { const int num_elems = TC_PRIO_MAX + 1; u8 tmp[FQ_PRIO2BAND_CRUMB_SIZE]; int i; memset(tmp, 0, sizeof(tmp)); for (i = 0; i < num_elems; i++) tmp[i / 4] |= in[i] << (2 * (i & 0x3)); for (i = 0; i < FQ_PRIO2BAND_CRUMB_SIZE; i++) WRITE_ONCE(out[i], tmp[i]); } static void fq_prio2band_decompress_crumb(const u8 *in, u8 *out) { const int num_elems = TC_PRIO_MAX + 1; int i; for (i = 0; i < num_elems; i++) out[i] = fq_prio2band(in, i); } static int fq_load_weights(struct fq_sched_data *q, const struct nlattr *attr, struct netlink_ext_ack *extack) { s32 *weights = nla_data(attr); int i; for (i = 0; i < FQ_BANDS; i++) { if (weights[i] < FQ_MIN_WEIGHT) { NL_SET_ERR_MSG_FMT_MOD(extack, "Weight %d less that minimum allowed %d", weights[i], FQ_MIN_WEIGHT); return -EINVAL; } } for (i = 0; i < FQ_BANDS; i++) WRITE_ONCE(q->band_flows[i].quantum, weights[i]); return 0; } static int fq_load_priomap(struct fq_sched_data *q, const struct nlattr *attr, struct netlink_ext_ack *extack) { const struct tc_prio_qopt *map = nla_data(attr); int i; if (map->bands != FQ_BANDS) { NL_SET_ERR_MSG_MOD(extack, "FQ only supports 3 bands"); return -EINVAL; } for (i = 0; i < TC_PRIO_MAX + 1; i++) { if (map->priomap[i] >= FQ_BANDS) { NL_SET_ERR_MSG_FMT_MOD(extack, "FQ priomap field %d maps to a too high band %d", i, map->priomap[i]); return -EINVAL; } } fq_prio2band_compress_crumb(map->priomap, q->prio2band); return 0; } static int fq_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct fq_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_MAX + 1]; int err, drop_count = 0; unsigned drop_len = 0; u32 fq_log; err = nla_parse_nested_deprecated(tb, TCA_FQ_MAX, opt, fq_policy, NULL); if (err < 0) return err; sch_tree_lock(sch); fq_log = q->fq_trees_log; if (tb[TCA_FQ_BUCKETS_LOG]) { u32 nval = nla_get_u32(tb[TCA_FQ_BUCKETS_LOG]); if (nval >= 1 && nval <= ilog2(256*1024)) fq_log = nval; else err = -EINVAL; } if (tb[TCA_FQ_PLIMIT]) WRITE_ONCE(sch->limit, nla_get_u32(tb[TCA_FQ_PLIMIT])); if (tb[TCA_FQ_FLOW_PLIMIT]) WRITE_ONCE(q->flow_plimit, nla_get_u32(tb[TCA_FQ_FLOW_PLIMIT])); if (tb[TCA_FQ_QUANTUM]) { u32 quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]); if (quantum > 0 && quantum <= (1 << 20)) { WRITE_ONCE(q->quantum, quantum); } else { NL_SET_ERR_MSG_MOD(extack, "invalid quantum"); err = -EINVAL; } } if (tb[TCA_FQ_INITIAL_QUANTUM]) WRITE_ONCE(q->initial_quantum, nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM])); if (tb[TCA_FQ_FLOW_DEFAULT_RATE]) pr_warn_ratelimited("sch_fq: defrate %u ignored.\n", nla_get_u32(tb[TCA_FQ_FLOW_DEFAULT_RATE])); if (tb[TCA_FQ_FLOW_MAX_RATE]) { u32 rate = nla_get_u32(tb[TCA_FQ_FLOW_MAX_RATE]); WRITE_ONCE(q->flow_max_rate, (rate == ~0U) ? ~0UL : rate); } if (tb[TCA_FQ_LOW_RATE_THRESHOLD]) WRITE_ONCE(q->low_rate_threshold, nla_get_u32(tb[TCA_FQ_LOW_RATE_THRESHOLD])); if (tb[TCA_FQ_RATE_ENABLE]) { u32 enable = nla_get_u32(tb[TCA_FQ_RATE_ENABLE]); if (enable <= 1) WRITE_ONCE(q->rate_enable, enable); else err = -EINVAL; } if (tb[TCA_FQ_FLOW_REFILL_DELAY]) { u32 usecs_delay = nla_get_u32(tb[TCA_FQ_FLOW_REFILL_DELAY]) ; WRITE_ONCE(q->flow_refill_delay, usecs_to_jiffies(usecs_delay)); } if (!err && tb[TCA_FQ_PRIOMAP]) err = fq_load_priomap(q, tb[TCA_FQ_PRIOMAP], extack); if (!err && tb[TCA_FQ_WEIGHTS]) err = fq_load_weights(q, tb[TCA_FQ_WEIGHTS], extack); if (tb[TCA_FQ_ORPHAN_MASK]) WRITE_ONCE(q->orphan_mask, nla_get_u32(tb[TCA_FQ_ORPHAN_MASK])); if (tb[TCA_FQ_CE_THRESHOLD]) WRITE_ONCE(q->ce_threshold, (u64)NSEC_PER_USEC * nla_get_u32(tb[TCA_FQ_CE_THRESHOLD])); if (tb[TCA_FQ_TIMER_SLACK]) WRITE_ONCE(q->timer_slack, nla_get_u32(tb[TCA_FQ_TIMER_SLACK])); if (tb[TCA_FQ_HORIZON]) WRITE_ONCE(q->horizon, (u64)NSEC_PER_USEC * nla_get_u32(tb[TCA_FQ_HORIZON])); if (tb[TCA_FQ_HORIZON_DROP]) WRITE_ONCE(q->horizon_drop, nla_get_u8(tb[TCA_FQ_HORIZON_DROP])); if (!err) { sch_tree_unlock(sch); err = fq_resize(sch, fq_log); sch_tree_lock(sch); } while (sch->q.qlen > sch->limit) { struct sk_buff *skb = fq_dequeue(sch); if (!skb) break; drop_len += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); drop_count++; } qdisc_tree_reduce_backlog(sch, drop_count, drop_len); sch_tree_unlock(sch); return err; } static void fq_destroy(struct Qdisc *sch) { struct fq_sched_data *q = qdisc_priv(sch); fq_reset(sch); fq_free(q->fq_root); qdisc_watchdog_cancel(&q->watchdog); } static int fq_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct fq_sched_data *q = qdisc_priv(sch); int i, err; sch->limit = 10000; q->flow_plimit = 100; q->quantum = 2 * psched_mtu(qdisc_dev(sch)); q->initial_quantum = 10 * psched_mtu(qdisc_dev(sch)); q->flow_refill_delay = msecs_to_jiffies(40); q->flow_max_rate = ~0UL; q->time_next_delayed_flow = ~0ULL; q->rate_enable = 1; for (i = 0; i < FQ_BANDS; i++) { q->band_flows[i].new_flows.first = NULL; q->band_flows[i].old_flows.first = NULL; } q->band_flows[0].quantum = 9 << 16; q->band_flows[1].quantum = 3 << 16; q->band_flows[2].quantum = 1 << 16; q->delayed = RB_ROOT; q->fq_root = NULL; q->fq_trees_log = ilog2(1024); q->orphan_mask = 1024 - 1; q->low_rate_threshold = 550000 / 8; q->timer_slack = 10 * NSEC_PER_USEC; /* 10 usec of hrtimer slack */ q->horizon = 10ULL * NSEC_PER_SEC; /* 10 seconds */ q->horizon_drop = 1; /* by default, drop packets beyond horizon */ /* Default ce_threshold of 4294 seconds */ q->ce_threshold = (u64)NSEC_PER_USEC * ~0U; fq_prio2band_compress_crumb(sch_default_prio2band, q->prio2band); qdisc_watchdog_init_clockid(&q->watchdog, sch, CLOCK_MONOTONIC); if (opt) err = fq_change(sch, opt, extack); else err = fq_resize(sch, q->fq_trees_log); return err; } static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) { struct fq_sched_data *q = qdisc_priv(sch); struct tc_prio_qopt prio = { .bands = FQ_BANDS, }; struct nlattr *opts; u64 ce_threshold; s32 weights[3]; u64 horizon; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; /* TCA_FQ_FLOW_DEFAULT_RATE is not used anymore */ ce_threshold = READ_ONCE(q->ce_threshold); do_div(ce_threshold, NSEC_PER_USEC); horizon = READ_ONCE(q->horizon); do_div(horizon, NSEC_PER_USEC); if (nla_put_u32(skb, TCA_FQ_PLIMIT, READ_ONCE(sch->limit)) || nla_put_u32(skb, TCA_FQ_FLOW_PLIMIT, READ_ONCE(q->flow_plimit)) || nla_put_u32(skb, TCA_FQ_QUANTUM, READ_ONCE(q->quantum)) || nla_put_u32(skb, TCA_FQ_INITIAL_QUANTUM, READ_ONCE(q->initial_quantum)) || nla_put_u32(skb, TCA_FQ_RATE_ENABLE, READ_ONCE(q->rate_enable)) || nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, min_t(unsigned long, READ_ONCE(q->flow_max_rate), ~0U)) || nla_put_u32(skb, TCA_FQ_FLOW_REFILL_DELAY, jiffies_to_usecs(READ_ONCE(q->flow_refill_delay))) || nla_put_u32(skb, TCA_FQ_ORPHAN_MASK, READ_ONCE(q->orphan_mask)) || nla_put_u32(skb, TCA_FQ_LOW_RATE_THRESHOLD, READ_ONCE(q->low_rate_threshold)) || nla_put_u32(skb, TCA_FQ_CE_THRESHOLD, (u32)ce_threshold) || nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, READ_ONCE(q->fq_trees_log)) || nla_put_u32(skb, TCA_FQ_TIMER_SLACK, READ_ONCE(q->timer_slack)) || nla_put_u32(skb, TCA_FQ_HORIZON, (u32)horizon) || nla_put_u8(skb, TCA_FQ_HORIZON_DROP, READ_ONCE(q->horizon_drop))) goto nla_put_failure; fq_prio2band_decompress_crumb(q->prio2band, prio.priomap); if (nla_put(skb, TCA_FQ_PRIOMAP, sizeof(prio), &prio)) goto nla_put_failure; weights[0] = READ_ONCE(q->band_flows[0].quantum); weights[1] = READ_ONCE(q->band_flows[1].quantum); weights[2] = READ_ONCE(q->band_flows[2].quantum); if (nla_put(skb, TCA_FQ_WEIGHTS, sizeof(weights), &weights)) goto nla_put_failure; return nla_nest_end(skb, opts); nla_put_failure: return -1; } static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct fq_sched_data *q = qdisc_priv(sch); struct tc_fq_qd_stats st; int i; st.pad = 0; sch_tree_lock(sch); st.gc_flows = q->stat_gc_flows; st.highprio_packets = 0; st.fastpath_packets = q->internal.stat_fastpath_packets; st.tcp_retrans = 0; st.throttled = q->stat_throttled; st.flows_plimit = q->stat_flows_plimit; st.pkts_too_long = q->stat_pkts_too_long; st.allocation_errors = q->stat_allocation_errors; st.time_next_delayed_flow = q->time_next_delayed_flow + q->timer_slack - ktime_get_ns(); st.flows = q->flows; st.inactive_flows = q->inactive_flows; st.throttled_flows = q->throttled_flows; st.unthrottle_latency_ns = min_t(unsigned long, q->unthrottle_latency_ns, ~0U); st.ce_mark = q->stat_ce_mark; st.horizon_drops = q->stat_horizon_drops; st.horizon_caps = q->stat_horizon_caps; for (i = 0; i < FQ_BANDS; i++) { st.band_drops[i] = q->stat_band_drops[i]; st.band_pkt_count[i] = q->band_pkt_count[i]; } sch_tree_unlock(sch); return gnet_stats_copy_app(d, &st, sizeof(st)); } static struct Qdisc_ops fq_qdisc_ops __read_mostly = { .id = "fq", .priv_size = sizeof(struct fq_sched_data), .enqueue = fq_enqueue, .dequeue = fq_dequeue, .peek = qdisc_peek_dequeued, .init = fq_init, .reset = fq_reset, .destroy = fq_destroy, .change = fq_change, .dump = fq_dump, .dump_stats = fq_dump_stats, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("fq"); static int __init fq_module_init(void) { int ret; fq_flow_cachep = kmem_cache_create("fq_flow_cache", sizeof(struct fq_flow), 0, SLAB_HWCACHE_ALIGN, NULL); if (!fq_flow_cachep) return -ENOMEM; ret = register_qdisc(&fq_qdisc_ops); if (ret) kmem_cache_destroy(fq_flow_cachep); return ret; } static void __exit fq_module_exit(void) { unregister_qdisc(&fq_qdisc_ops); kmem_cache_destroy(fq_flow_cachep); } module_init(fq_module_init) module_exit(fq_module_exit) MODULE_AUTHOR("Eric Dumazet"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Fair Queue Packet Scheduler"); |
| 6 5 6 1 1 4 12 12 3 3 4 2 2 2 3 9 8 7 9 6 6 6 6 6 6 5 5 5 6 5 1 4 4 1 3 3 3 3 2 3 2 2 8 3 2 2 1 2 1 1 1 1 1 1 3 3 3 3 3 3 3 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 4 4 4 4 4 9 4 4 3 3 2 2 8 3 2 2 2 2 2 2 2 2 2 2 7 8 5 5 5 3 1 3 8 8 8 2 1 1 1 8 7 5 3 1 1 3 2 2 2 1 1 5 5 6 7 6 1 6 6 1 5 1 1 1 1 1 1 11 10 11 10 11 11 11 11 11 10 9 1 10 1 9 8 9 8 8 2 8 1 8 8 1 8 8 7 6 1 6 1 5 11 6 2 11 11 | 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 | /* * Copyright (C) 2014 Red Hat * Copyright (C) 2014 Intel Corp. * Copyright (C) 2018 Intel Corp. * Copyright (c) 2020, The Linux Foundation. All rights reserved. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), * to deal in the Software without restriction, including without limitation * the rights to use, copy, modify, merge, publish, distribute, sublicense, * and/or sell copies of the Software, and to permit persons to whom the * Software is furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice shall be included in * all copies or substantial portions of the Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR * OTHER DEALINGS IN THE SOFTWARE. * * Authors: * Rob Clark <robdclark@gmail.com> * Daniel Vetter <daniel.vetter@ffwll.ch> */ #include <drm/drm_atomic_uapi.h> #include <drm/drm_atomic.h> #include <drm/drm_framebuffer.h> #include <drm/drm_print.h> #include <drm/drm_drv.h> #include <drm/drm_writeback.h> #include <drm/drm_vblank.h> #include <linux/dma-fence.h> #include <linux/uaccess.h> #include <linux/sync_file.h> #include <linux/file.h> #include "drm_crtc_internal.h" /** * DOC: overview * * This file contains the marshalling and demarshalling glue for the atomic UAPI * in all its forms: The monster ATOMIC IOCTL itself, code for GET_PROPERTY and * SET_PROPERTY IOCTLs. Plus interface functions for compatibility helpers and * drivers which have special needs to construct their own atomic updates, e.g. * for load detect or similar. */ /** * drm_atomic_set_mode_for_crtc - set mode for CRTC * @state: the CRTC whose incoming state to update * @mode: kernel-internal mode to use for the CRTC, or NULL to disable * * Set a mode (originating from the kernel) on the desired CRTC state and update * the enable property. * * RETURNS: * Zero on success, error code on failure. Cannot return -EDEADLK. */ int drm_atomic_set_mode_for_crtc(struct drm_crtc_state *state, const struct drm_display_mode *mode) { struct drm_crtc *crtc = state->crtc; struct drm_mode_modeinfo umode; /* Early return for no change. */ if (mode && memcmp(&state->mode, mode, sizeof(*mode)) == 0) return 0; drm_property_blob_put(state->mode_blob); state->mode_blob = NULL; if (mode) { struct drm_property_blob *blob; drm_mode_convert_to_umode(&umode, mode); blob = drm_property_create_blob(crtc->dev, sizeof(umode), &umode); if (IS_ERR(blob)) return PTR_ERR(blob); drm_mode_copy(&state->mode, mode); state->mode_blob = blob; state->enable = true; drm_dbg_atomic(crtc->dev, "Set [MODE:%s] for [CRTC:%d:%s] state %p\n", mode->name, crtc->base.id, crtc->name, state); } else { memset(&state->mode, 0, sizeof(state->mode)); state->enable = false; drm_dbg_atomic(crtc->dev, "Set [NOMODE] for [CRTC:%d:%s] state %p\n", crtc->base.id, crtc->name, state); } return 0; } EXPORT_SYMBOL(drm_atomic_set_mode_for_crtc); /** * drm_atomic_set_mode_prop_for_crtc - set mode for CRTC * @state: the CRTC whose incoming state to update * @blob: pointer to blob property to use for mode * * Set a mode (originating from a blob property) on the desired CRTC state. * This function will take a reference on the blob property for the CRTC state, * and release the reference held on the state's existing mode property, if any * was set. * * RETURNS: * Zero on success, error code on failure. Cannot return -EDEADLK. */ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state, struct drm_property_blob *blob) { struct drm_crtc *crtc = state->crtc; if (blob == state->mode_blob) return 0; drm_property_blob_put(state->mode_blob); state->mode_blob = NULL; memset(&state->mode, 0, sizeof(state->mode)); if (blob) { int ret; if (blob->length != sizeof(struct drm_mode_modeinfo)) { drm_dbg_atomic(crtc->dev, "[CRTC:%d:%s] bad mode blob length: %zu\n", crtc->base.id, crtc->name, blob->length); return -EINVAL; } ret = drm_mode_convert_umode(crtc->dev, &state->mode, blob->data); if (ret) { drm_dbg_atomic(crtc->dev, "[CRTC:%d:%s] invalid mode (%s, %pe): " DRM_MODE_FMT "\n", crtc->base.id, crtc->name, drm_get_mode_status_name(state->mode.status), ERR_PTR(ret), DRM_MODE_ARG(&state->mode)); return -EINVAL; } state->mode_blob = drm_property_blob_get(blob); state->enable = true; drm_dbg_atomic(crtc->dev, "Set [MODE:%s] for [CRTC:%d:%s] state %p\n", state->mode.name, crtc->base.id, crtc->name, state); } else { state->enable = false; drm_dbg_atomic(crtc->dev, "Set [NOMODE] for [CRTC:%d:%s] state %p\n", crtc->base.id, crtc->name, state); } return 0; } EXPORT_SYMBOL(drm_atomic_set_mode_prop_for_crtc); /** * drm_atomic_set_crtc_for_plane - set CRTC for plane * @plane_state: the plane whose incoming state to update * @crtc: CRTC to use for the plane * * Changing the assigned CRTC for a plane requires us to grab the lock and state * for the new CRTC, as needed. This function takes care of all these details * besides updating the pointer in the state object itself. * * Returns: * 0 on success or can fail with -EDEADLK or -ENOMEM. When the error is EDEADLK * then the w/w mutex code has detected a deadlock and the entire atomic * sequence must be restarted. All other errors are fatal. */ int drm_atomic_set_crtc_for_plane(struct drm_plane_state *plane_state, struct drm_crtc *crtc) { struct drm_plane *plane = plane_state->plane; struct drm_crtc_state *crtc_state; /* Nothing to do for same crtc*/ if (plane_state->crtc == crtc) return 0; if (plane_state->crtc) { crtc_state = drm_atomic_get_crtc_state(plane_state->state, plane_state->crtc); if (WARN_ON(IS_ERR(crtc_state))) return PTR_ERR(crtc_state); crtc_state->plane_mask &= ~drm_plane_mask(plane); } plane_state->crtc = crtc; if (crtc) { crtc_state = drm_atomic_get_crtc_state(plane_state->state, crtc); if (IS_ERR(crtc_state)) return PTR_ERR(crtc_state); crtc_state->plane_mask |= drm_plane_mask(plane); } if (crtc) drm_dbg_atomic(plane->dev, "Link [PLANE:%d:%s] state %p to [CRTC:%d:%s]\n", plane->base.id, plane->name, plane_state, crtc->base.id, crtc->name); else drm_dbg_atomic(plane->dev, "Link [PLANE:%d:%s] state %p to [NOCRTC]\n", plane->base.id, plane->name, plane_state); return 0; } EXPORT_SYMBOL(drm_atomic_set_crtc_for_plane); /** * drm_atomic_set_fb_for_plane - set framebuffer for plane * @plane_state: atomic state object for the plane * @fb: fb to use for the plane * * Changing the assigned framebuffer for a plane requires us to grab a reference * to the new fb and drop the reference to the old fb, if there is one. This * function takes care of all these details besides updating the pointer in the * state object itself. */ void drm_atomic_set_fb_for_plane(struct drm_plane_state *plane_state, struct drm_framebuffer *fb) { struct drm_plane *plane = plane_state->plane; if (fb) drm_dbg_atomic(plane->dev, "Set [FB:%d] for [PLANE:%d:%s] state %p\n", fb->base.id, plane->base.id, plane->name, plane_state); else drm_dbg_atomic(plane->dev, "Set [NOFB] for [PLANE:%d:%s] state %p\n", plane->base.id, plane->name, plane_state); drm_framebuffer_assign(&plane_state->fb, fb); } EXPORT_SYMBOL(drm_atomic_set_fb_for_plane); /** * drm_atomic_set_crtc_for_connector - set CRTC for connector * @conn_state: atomic state object for the connector * @crtc: CRTC to use for the connector * * Changing the assigned CRTC for a connector requires us to grab the lock and * state for the new CRTC, as needed. This function takes care of all these * details besides updating the pointer in the state object itself. * * Returns: * 0 on success or can fail with -EDEADLK or -ENOMEM. When the error is EDEADLK * then the w/w mutex code has detected a deadlock and the entire atomic * sequence must be restarted. All other errors are fatal. */ int drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state, struct drm_crtc *crtc) { struct drm_connector *connector = conn_state->connector; struct drm_crtc_state *crtc_state; if (conn_state->crtc == crtc) return 0; if (conn_state->crtc) { crtc_state = drm_atomic_get_new_crtc_state(conn_state->state, conn_state->crtc); crtc_state->connector_mask &= ~drm_connector_mask(conn_state->connector); drm_connector_put(conn_state->connector); conn_state->crtc = NULL; } if (crtc) { crtc_state = drm_atomic_get_crtc_state(conn_state->state, crtc); if (IS_ERR(crtc_state)) return PTR_ERR(crtc_state); crtc_state->connector_mask |= drm_connector_mask(conn_state->connector); drm_connector_get(conn_state->connector); conn_state->crtc = crtc; drm_dbg_atomic(connector->dev, "Link [CONNECTOR:%d:%s] state %p to [CRTC:%d:%s]\n", connector->base.id, connector->name, conn_state, crtc->base.id, crtc->name); } else { drm_dbg_atomic(connector->dev, "Link [CONNECTOR:%d:%s] state %p to [NOCRTC]\n", connector->base.id, connector->name, conn_state); } return 0; } EXPORT_SYMBOL(drm_atomic_set_crtc_for_connector); static void set_out_fence_for_crtc(struct drm_atomic_state *state, struct drm_crtc *crtc, s32 __user *fence_ptr) { state->crtcs[drm_crtc_index(crtc)].out_fence_ptr = fence_ptr; } static s32 __user *get_out_fence_for_crtc(struct drm_atomic_state *state, struct drm_crtc *crtc) { s32 __user *fence_ptr; fence_ptr = state->crtcs[drm_crtc_index(crtc)].out_fence_ptr; state->crtcs[drm_crtc_index(crtc)].out_fence_ptr = NULL; return fence_ptr; } static int set_out_fence_for_connector(struct drm_atomic_state *state, struct drm_connector *connector, s32 __user *fence_ptr) { unsigned int index = drm_connector_index(connector); if (!fence_ptr) return 0; if (put_user(-1, fence_ptr)) return -EFAULT; state->connectors[index].out_fence_ptr = fence_ptr; return 0; } static s32 __user *get_out_fence_for_connector(struct drm_atomic_state *state, struct drm_connector *connector) { unsigned int index = drm_connector_index(connector); s32 __user *fence_ptr; fence_ptr = state->connectors[index].out_fence_ptr; state->connectors[index].out_fence_ptr = NULL; return fence_ptr; } static int drm_atomic_crtc_set_property(struct drm_crtc *crtc, struct drm_crtc_state *state, struct drm_property *property, uint64_t val) { struct drm_device *dev = crtc->dev; struct drm_mode_config *config = &dev->mode_config; bool replaced = false; int ret; if (property == config->prop_active) state->active = val; else if (property == config->prop_mode_id) { struct drm_property_blob *mode = drm_property_lookup_blob(dev, val); ret = drm_atomic_set_mode_prop_for_crtc(state, mode); drm_property_blob_put(mode); return ret; } else if (property == config->prop_vrr_enabled) { state->vrr_enabled = val; } else if (property == config->degamma_lut_property) { ret = drm_property_replace_blob_from_id(dev, &state->degamma_lut, val, -1, sizeof(struct drm_color_lut), &replaced); state->color_mgmt_changed |= replaced; return ret; } else if (property == config->ctm_property) { ret = drm_property_replace_blob_from_id(dev, &state->ctm, val, sizeof(struct drm_color_ctm), -1, &replaced); state->color_mgmt_changed |= replaced; return ret; } else if (property == config->gamma_lut_property) { ret = drm_property_replace_blob_from_id(dev, &state->gamma_lut, val, -1, sizeof(struct drm_color_lut), &replaced); state->color_mgmt_changed |= replaced; return ret; } else if (property == config->prop_out_fence_ptr) { s32 __user *fence_ptr = u64_to_user_ptr(val); if (!fence_ptr) return 0; if (put_user(-1, fence_ptr)) return -EFAULT; set_out_fence_for_crtc(state->state, crtc, fence_ptr); } else if (property == crtc->scaling_filter_property) { state->scaling_filter = val; } else if (crtc->funcs->atomic_set_property) { return crtc->funcs->atomic_set_property(crtc, state, property, val); } else { drm_dbg_atomic(crtc->dev, "[CRTC:%d:%s] unknown property [PROP:%d:%s]\n", crtc->base.id, crtc->name, property->base.id, property->name); return -EINVAL; } return 0; } static int drm_atomic_crtc_get_property(struct drm_crtc *crtc, const struct drm_crtc_state *state, struct drm_property *property, uint64_t *val) { struct drm_device *dev = crtc->dev; struct drm_mode_config *config = &dev->mode_config; if (property == config->prop_active) *val = drm_atomic_crtc_effectively_active(state); else if (property == config->prop_mode_id) *val = (state->mode_blob) ? state->mode_blob->base.id : 0; else if (property == config->prop_vrr_enabled) *val = state->vrr_enabled; else if (property == config->degamma_lut_property) *val = (state->degamma_lut) ? state->degamma_lut->base.id : 0; else if (property == config->ctm_property) *val = (state->ctm) ? state->ctm->base.id : 0; else if (property == config->gamma_lut_property) *val = (state->gamma_lut) ? state->gamma_lut->base.id : 0; else if (property == config->prop_out_fence_ptr) *val = 0; else if (property == crtc->scaling_filter_property) *val = state->scaling_filter; else if (crtc->funcs->atomic_get_property) return crtc->funcs->atomic_get_property(crtc, state, property, val); else { drm_dbg_atomic(dev, "[CRTC:%d:%s] unknown property [PROP:%d:%s]\n", crtc->base.id, crtc->name, property->base.id, property->name); return -EINVAL; } return 0; } static int drm_atomic_plane_set_property(struct drm_plane *plane, struct drm_plane_state *state, struct drm_file *file_priv, struct drm_property *property, uint64_t val) { struct drm_device *dev = plane->dev; struct drm_mode_config *config = &dev->mode_config; bool replaced = false; int ret; if (property == config->prop_fb_id) { struct drm_framebuffer *fb; fb = drm_framebuffer_lookup(dev, file_priv, val); drm_atomic_set_fb_for_plane(state, fb); if (fb) drm_framebuffer_put(fb); } else if (property == config->prop_in_fence_fd) { if (state->fence) return -EINVAL; if (U642I64(val) == -1) return 0; state->fence = sync_file_get_fence(val); if (!state->fence) return -EINVAL; } else if (property == config->prop_crtc_id) { struct drm_crtc *crtc = drm_crtc_find(dev, file_priv, val); if (val && !crtc) { drm_dbg_atomic(dev, "[PROP:%d:%s] cannot find CRTC with ID %llu\n", property->base.id, property->name, val); return -EACCES; } return drm_atomic_set_crtc_for_plane(state, crtc); } else if (property == config->prop_crtc_x) { state->crtc_x = U642I64(val); } else if (property == config->prop_crtc_y) { state->crtc_y = U642I64(val); } else if (property == config->prop_crtc_w) { state->crtc_w = val; } else if (property == config->prop_crtc_h) { state->crtc_h = val; } else if (property == config->prop_src_x) { state->src_x = val; } else if (property == config->prop_src_y) { state->src_y = val; } else if (property == config->prop_src_w) { state->src_w = val; } else if (property == config->prop_src_h) { state->src_h = val; } else if (property == plane->alpha_property) { state->alpha = val; } else if (property == plane->blend_mode_property) { state->pixel_blend_mode = val; } else if (property == plane->rotation_property) { if (!is_power_of_2(val & DRM_MODE_ROTATE_MASK)) { drm_dbg_atomic(plane->dev, "[PLANE:%d:%s] bad rotation bitmask: 0x%llx\n", plane->base.id, plane->name, val); return -EINVAL; } state->rotation = val; } else if (property == plane->zpos_property) { state->zpos = val; } else if (property == plane->color_encoding_property) { state->color_encoding = val; } else if (property == plane->color_range_property) { state->color_range = val; } else if (property == config->prop_fb_damage_clips) { ret = drm_property_replace_blob_from_id(dev, &state->fb_damage_clips, val, -1, sizeof(struct drm_rect), &replaced); return ret; } else if (property == plane->scaling_filter_property) { state->scaling_filter = val; } else if (plane->funcs->atomic_set_property) { return plane->funcs->atomic_set_property(plane, state, property, val); } else if (property == plane->hotspot_x_property) { if (plane->type != DRM_PLANE_TYPE_CURSOR) { drm_dbg_atomic(plane->dev, "[PLANE:%d:%s] is not a cursor plane: 0x%llx\n", plane->base.id, plane->name, val); return -EINVAL; } state->hotspot_x = val; } else if (property == plane->hotspot_y_property) { if (plane->type != DRM_PLANE_TYPE_CURSOR) { drm_dbg_atomic(plane->dev, "[PLANE:%d:%s] is not a cursor plane: 0x%llx\n", plane->base.id, plane->name, val); return -EINVAL; } state->hotspot_y = val; } else { drm_dbg_atomic(plane->dev, "[PLANE:%d:%s] unknown property [PROP:%d:%s]\n", plane->base.id, plane->name, property->base.id, property->name); return -EINVAL; } return 0; } static int drm_atomic_plane_get_property(struct drm_plane *plane, const struct drm_plane_state *state, struct drm_property *property, uint64_t *val) { struct drm_device *dev = plane->dev; struct drm_mode_config *config = &dev->mode_config; if (property == config->prop_fb_id) { *val = (state->fb) ? state->fb->base.id : 0; } else if (property == config->prop_in_fence_fd) { *val = -1; } else if (property == config->prop_crtc_id) { *val = (state->crtc) ? state->crtc->base.id : 0; } else if (property == config->prop_crtc_x) { *val = I642U64(state->crtc_x); } else if (property == config->prop_crtc_y) { *val = I642U64(state->crtc_y); } else if (property == config->prop_crtc_w) { *val = state->crtc_w; } else if (property == config->prop_crtc_h) { *val = state->crtc_h; } else if (property == config->prop_src_x) { *val = state->src_x; } else if (property == config->prop_src_y) { *val = state->src_y; } else if (property == config->prop_src_w) { *val = state->src_w; } else if (property == config->prop_src_h) { *val = state->src_h; } else if (property == plane->alpha_property) { *val = state->alpha; } else if (property == plane->blend_mode_property) { *val = state->pixel_blend_mode; } else if (property == plane->rotation_property) { *val = state->rotation; } else if (property == plane->zpos_property) { *val = state->zpos; } else if (property == plane->color_encoding_property) { *val = state->color_encoding; } else if (property == plane->color_range_property) { *val = state->color_range; } else if (property == config->prop_fb_damage_clips) { *val = (state->fb_damage_clips) ? state->fb_damage_clips->base.id : 0; } else if (property == plane->scaling_filter_property) { *val = state->scaling_filter; } else if (plane->funcs->atomic_get_property) { return plane->funcs->atomic_get_property(plane, state, property, val); } else if (property == plane->hotspot_x_property) { *val = state->hotspot_x; } else if (property == plane->hotspot_y_property) { *val = state->hotspot_y; } else { drm_dbg_atomic(dev, "[PLANE:%d:%s] unknown property [PROP:%d:%s]\n", plane->base.id, plane->name, property->base.id, property->name); return -EINVAL; } return 0; } static int drm_atomic_set_writeback_fb_for_connector( struct drm_connector_state *conn_state, struct drm_framebuffer *fb) { int ret; struct drm_connector *conn = conn_state->connector; ret = drm_writeback_set_fb(conn_state, fb); if (ret < 0) return ret; if (fb) drm_dbg_atomic(conn->dev, "Set [FB:%d] for connector state %p\n", fb->base.id, conn_state); else drm_dbg_atomic(conn->dev, "Set [NOFB] for connector state %p\n", conn_state); return 0; } static int drm_atomic_connector_set_property(struct drm_connector *connector, struct drm_connector_state *state, struct drm_file *file_priv, struct drm_property *property, uint64_t val) { struct drm_device *dev = connector->dev; struct drm_mode_config *config = &dev->mode_config; bool replaced = false; int ret; if (property == config->prop_crtc_id) { struct drm_crtc *crtc = drm_crtc_find(dev, file_priv, val); if (val && !crtc) { drm_dbg_atomic(dev, "[PROP:%d:%s] cannot find CRTC with ID %llu\n", property->base.id, property->name, val); return -EACCES; } return drm_atomic_set_crtc_for_connector(state, crtc); } else if (property == config->dpms_property) { /* setting DPMS property requires special handling, which * is done in legacy setprop path for us. Disallow (for * now?) atomic writes to DPMS property: */ drm_dbg_atomic(dev, "legacy [PROP:%d:%s] can only be set via legacy uAPI\n", property->base.id, property->name); return -EINVAL; } else if (property == config->tv_select_subconnector_property) { state->tv.select_subconnector = val; } else if (property == config->tv_subconnector_property) { state->tv.subconnector = val; } else if (property == config->tv_left_margin_property) { state->tv.margins.left = val; } else if (property == config->tv_right_margin_property) { state->tv.margins.right = val; } else if (property == config->tv_top_margin_property) { state->tv.margins.top = val; } else if (property == config->tv_bottom_margin_property) { state->tv.margins.bottom = val; } else if (property == config->legacy_tv_mode_property) { state->tv.legacy_mode = val; } else if (property == config->tv_mode_property) { state->tv.mode = val; } else if (property == config->tv_brightness_property) { state->tv.brightness = val; } else if (property == config->tv_contrast_property) { state->tv.contrast = val; } else if (property == config->tv_flicker_reduction_property) { state->tv.flicker_reduction = val; } else if (property == config->tv_overscan_property) { state->tv.overscan = val; } else if (property == config->tv_saturation_property) { state->tv.saturation = val; } else if (property == config->tv_hue_property) { state->tv.hue = val; } else if (property == config->link_status_property) { /* Never downgrade from GOOD to BAD on userspace's request here, * only hw issues can do that. * * For an atomic property the userspace doesn't need to be able * to understand all the properties, but needs to be able to * restore the state it wants on VT switch. So if the userspace * tries to change the link_status from GOOD to BAD, driver * silently rejects it and returns a 0. This prevents userspace * from accidentally breaking the display when it restores the * state. */ if (state->link_status != DRM_LINK_STATUS_GOOD) state->link_status = val; } else if (property == config->hdr_output_metadata_property) { ret = drm_property_replace_blob_from_id(dev, &state->hdr_output_metadata, val, sizeof(struct hdr_output_metadata), -1, &replaced); return ret; } else if (property == config->aspect_ratio_property) { state->picture_aspect_ratio = val; } else if (property == config->content_type_property) { state->content_type = val; } else if (property == connector->scaling_mode_property) { state->scaling_mode = val; } else if (property == config->content_protection_property) { if (val == DRM_MODE_CONTENT_PROTECTION_ENABLED) { drm_dbg_kms(dev, "only drivers can set CP Enabled\n"); return -EINVAL; } state->content_protection = val; } else if (property == config->hdcp_content_type_property) { state->hdcp_content_type = val; } else if (property == connector->colorspace_property) { state->colorspace = val; } else if (property == config->writeback_fb_id_property) { struct drm_framebuffer *fb; int ret; fb = drm_framebuffer_lookup(dev, file_priv, val); ret = drm_atomic_set_writeback_fb_for_connector(state, fb); if (fb) drm_framebuffer_put(fb); return ret; } else if (property == config->writeback_out_fence_ptr_property) { s32 __user *fence_ptr = u64_to_user_ptr(val); return set_out_fence_for_connector(state->state, connector, fence_ptr); } else if (property == connector->max_bpc_property) { state->max_requested_bpc = val; } else if (property == connector->privacy_screen_sw_state_property) { state->privacy_screen_sw_state = val; } else if (connector->funcs->atomic_set_property) { return connector->funcs->atomic_set_property(connector, state, property, val); } else { drm_dbg_atomic(connector->dev, "[CONNECTOR:%d:%s] unknown property [PROP:%d:%s]\n", connector->base.id, connector->name, property->base.id, property->name); return -EINVAL; } return 0; } static int drm_atomic_connector_get_property(struct drm_connector *connector, const struct drm_connector_state *state, struct drm_property *property, uint64_t *val) { struct drm_device *dev = connector->dev; struct drm_mode_config *config = &dev->mode_config; if (property == config->prop_crtc_id) { *val = (state->crtc) ? state->crtc->base.id : 0; } else if (property == config->dpms_property) { if (state->crtc && state->crtc->state->self_refresh_active) *val = DRM_MODE_DPMS_ON; else *val = connector->dpms; } else if (property == config->tv_select_subconnector_property) { *val = state->tv.select_subconnector; } else if (property == config->tv_subconnector_property) { *val = state->tv.subconnector; } else if (property == config->tv_left_margin_property) { *val = state->tv.margins.left; } else if (property == config->tv_right_margin_property) { *val = state->tv.margins.right; } else if (property == config->tv_top_margin_property) { *val = state->tv.margins.top; } else if (property == config->tv_bottom_margin_property) { *val = state->tv.margins.bottom; } else if (property == config->legacy_tv_mode_property) { *val = state->tv.legacy_mode; } else if (property == config->tv_mode_property) { *val = state->tv.mode; } else if (property == config->tv_brightness_property) { *val = state->tv.brightness; } else if (property == config->tv_contrast_property) { *val = state->tv.contrast; } else if (property == config->tv_flicker_reduction_property) { *val = state->tv.flicker_reduction; } else if (property == config->tv_overscan_property) { *val = state->tv.overscan; } else if (property == config->tv_saturation_property) { *val = state->tv.saturation; } else if (property == config->tv_hue_property) { *val = state->tv.hue; } else if (property == config->link_status_property) { *val = state->link_status; } else if (property == config->aspect_ratio_property) { *val = state->picture_aspect_ratio; } else if (property == config->content_type_property) { *val = state->content_type; } else if (property == connector->colorspace_property) { *val = state->colorspace; } else if (property == connector->scaling_mode_property) { *val = state->scaling_mode; } else if (property == config->hdr_output_metadata_property) { *val = state->hdr_output_metadata ? state->hdr_output_metadata->base.id : 0; } else if (property == config->content_protection_property) { *val = state->content_protection; } else if (property == config->hdcp_content_type_property) { *val = state->hdcp_content_type; } else if (property == config->writeback_fb_id_property) { /* Writeback framebuffer is one-shot, write and forget */ *val = 0; } else if (property == config->writeback_out_fence_ptr_property) { *val = 0; } else if (property == connector->max_bpc_property) { *val = state->max_requested_bpc; } else if (property == connector->privacy_screen_sw_state_property) { *val = state->privacy_screen_sw_state; } else if (connector->funcs->atomic_get_property) { return connector->funcs->atomic_get_property(connector, state, property, val); } else { drm_dbg_atomic(dev, "[CONNECTOR:%d:%s] unknown property [PROP:%d:%s]\n", connector->base.id, connector->name, property->base.id, property->name); return -EINVAL; } return 0; } int drm_atomic_get_property(struct drm_mode_object *obj, struct drm_property *property, uint64_t *val) { struct drm_device *dev = property->dev; int ret; switch (obj->type) { case DRM_MODE_OBJECT_CONNECTOR: { struct drm_connector *connector = obj_to_connector(obj); WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex)); ret = drm_atomic_connector_get_property(connector, connector->state, property, val); break; } case DRM_MODE_OBJECT_CRTC: { struct drm_crtc *crtc = obj_to_crtc(obj); WARN_ON(!drm_modeset_is_locked(&crtc->mutex)); ret = drm_atomic_crtc_get_property(crtc, crtc->state, property, val); break; } case DRM_MODE_OBJECT_PLANE: { struct drm_plane *plane = obj_to_plane(obj); WARN_ON(!drm_modeset_is_locked(&plane->mutex)); ret = drm_atomic_plane_get_property(plane, plane->state, property, val); break; } default: drm_dbg_atomic(dev, "[OBJECT:%d] has no properties\n", obj->id); ret = -EINVAL; break; } return ret; } /* * The big monster ioctl */ static struct drm_pending_vblank_event *create_vblank_event( struct drm_crtc *crtc, uint64_t user_data) { struct drm_pending_vblank_event *e = NULL; e = kzalloc(sizeof *e, GFP_KERNEL); if (!e) return NULL; e->event.base.type = DRM_EVENT_FLIP_COMPLETE; e->event.base.length = sizeof(e->event); e->event.vbl.crtc_id = crtc->base.id; e->event.vbl.user_data = user_data; return e; } int drm_atomic_connector_commit_dpms(struct drm_atomic_state *state, struct drm_connector *connector, int mode) { struct drm_connector *tmp_connector; struct drm_connector_state *new_conn_state; struct drm_crtc *crtc; struct drm_crtc_state *crtc_state; int i, ret, old_mode = connector->dpms; bool active = false; ret = drm_modeset_lock(&state->dev->mode_config.connection_mutex, state->acquire_ctx); if (ret) return ret; if (mode != DRM_MODE_DPMS_ON) mode = DRM_MODE_DPMS_OFF; connector->dpms = mode; crtc = connector->state->crtc; if (!crtc) goto out; ret = drm_atomic_add_affected_connectors(state, crtc); if (ret) goto out; crtc_state = drm_atomic_get_crtc_state(state, crtc); if (IS_ERR(crtc_state)) { ret = PTR_ERR(crtc_state); goto out; } for_each_new_connector_in_state(state, tmp_connector, new_conn_state, i) { if (new_conn_state->crtc != crtc) continue; if (tmp_connector->dpms == DRM_MODE_DPMS_ON) { active = true; break; } } crtc_state->active = active; ret = drm_atomic_commit(state); out: if (ret != 0) connector->dpms = old_mode; return ret; } static int drm_atomic_check_prop_changes(int ret, uint64_t old_val, uint64_t prop_value, struct drm_property *prop) { if (ret != 0 || old_val != prop_value) { drm_dbg_atomic(prop->dev, "[PROP:%d:%s] No prop can be changed during async flip\n", prop->base.id, prop->name); return -EINVAL; } return 0; } int drm_atomic_set_property(struct drm_atomic_state *state, struct drm_file *file_priv, struct drm_mode_object *obj, struct drm_property *prop, u64 prop_value, bool async_flip) { struct drm_mode_object *ref; u64 old_val; int ret; if (!drm_property_change_valid_get(prop, prop_value, &ref)) return -EINVAL; switch (obj->type) { case DRM_MODE_OBJECT_CONNECTOR: { struct drm_connector *connector = obj_to_connector(obj); struct drm_connector_state *connector_state; connector_state = drm_atomic_get_connector_state(state, connector); if (IS_ERR(connector_state)) { ret = PTR_ERR(connector_state); break; } if (async_flip) { ret = drm_atomic_connector_get_property(connector, connector_state, prop, &old_val); ret = drm_atomic_check_prop_changes(ret, old_val, prop_value, prop); break; } ret = drm_atomic_connector_set_property(connector, connector_state, file_priv, prop, prop_value); break; } case DRM_MODE_OBJECT_CRTC: { struct drm_crtc *crtc = obj_to_crtc(obj); struct drm_crtc_state *crtc_state; crtc_state = drm_atomic_get_crtc_state(state, crtc); if (IS_ERR(crtc_state)) { ret = PTR_ERR(crtc_state); break; } if (async_flip) { ret = drm_atomic_crtc_get_property(crtc, crtc_state, prop, &old_val); ret = drm_atomic_check_prop_changes(ret, old_val, prop_value, prop); break; } ret = drm_atomic_crtc_set_property(crtc, crtc_state, prop, prop_value); break; } case DRM_MODE_OBJECT_PLANE: { struct drm_plane *plane = obj_to_plane(obj); struct drm_plane_state *plane_state; struct drm_mode_config *config = &plane->dev->mode_config; plane_state = drm_atomic_get_plane_state(state, plane); if (IS_ERR(plane_state)) { ret = PTR_ERR(plane_state); break; } if (async_flip && prop != config->prop_fb_id) { ret = drm_atomic_plane_get_property(plane, plane_state, prop, &old_val); ret = drm_atomic_check_prop_changes(ret, old_val, prop_value, prop); break; } if (async_flip && plane_state->plane->type != DRM_PLANE_TYPE_PRIMARY) { drm_dbg_atomic(prop->dev, "[OBJECT:%d] Only primary planes can be changed during async flip\n", obj->id); ret = -EINVAL; break; } ret = drm_atomic_plane_set_property(plane, plane_state, file_priv, prop, prop_value); break; } default: drm_dbg_atomic(prop->dev, "[OBJECT:%d] has no properties\n", obj->id); ret = -EINVAL; break; } drm_property_change_valid_put(prop, ref); return ret; } /** * DOC: explicit fencing properties * * Explicit fencing allows userspace to control the buffer synchronization * between devices. A Fence or a group of fences are transferred to/from * userspace using Sync File fds and there are two DRM properties for that. * IN_FENCE_FD on each DRM Plane to send fences to the kernel and * OUT_FENCE_PTR on each DRM CRTC to receive fences from the kernel. * * As a contrast, with implicit fencing the kernel keeps track of any * ongoing rendering, and automatically ensures that the atomic update waits * for any pending rendering to complete. This is usually tracked in &struct * dma_resv which can also contain mandatory kernel fences. Implicit syncing * is how Linux traditionally worked (e.g. DRI2/3 on X.org), whereas explicit * fencing is what Android wants. * * "IN_FENCE_FD”: * Use this property to pass a fence that DRM should wait on before * proceeding with the Atomic Commit request and show the framebuffer for * the plane on the screen. The fence can be either a normal fence or a * merged one, the sync_file framework will handle both cases and use a * fence_array if a merged fence is received. Passing -1 here means no * fences to wait on. * * If the Atomic Commit request has the DRM_MODE_ATOMIC_TEST_ONLY flag * it will only check if the Sync File is a valid one. * * On the driver side the fence is stored on the @fence parameter of * &struct drm_plane_state. Drivers which also support implicit fencing * should extract the implicit fence using drm_gem_plane_helper_prepare_fb(), * to make sure there's consistent behaviour between drivers in precedence * of implicit vs. explicit fencing. * * "OUT_FENCE_PTR”: * Use this property to pass a file descriptor pointer to DRM. Once the * Atomic Commit request call returns OUT_FENCE_PTR will be filled with * the file descriptor number of a Sync File. This Sync File contains the * CRTC fence that will be signaled when all framebuffers present on the * Atomic Commit * request for that given CRTC are scanned out on the * screen. * * The Atomic Commit request fails if a invalid pointer is passed. If the * Atomic Commit request fails for any other reason the out fence fd * returned will be -1. On a Atomic Commit with the * DRM_MODE_ATOMIC_TEST_ONLY flag the out fence will also be set to -1. * * Note that out-fences don't have a special interface to drivers and are * internally represented by a &struct drm_pending_vblank_event in struct * &drm_crtc_state, which is also used by the nonblocking atomic commit * helpers and for the DRM event handling for existing userspace. */ struct drm_out_fence_state { s32 __user *out_fence_ptr; struct sync_file *sync_file; int fd; }; static int setup_out_fence(struct drm_out_fence_state *fence_state, struct dma_fence *fence) { fence_state->fd = get_unused_fd_flags(O_CLOEXEC); if (fence_state->fd < 0) return fence_state->fd; if (put_user(fence_state->fd, fence_state->out_fence_ptr)) return -EFAULT; fence_state->sync_file = sync_file_create(fence); if (!fence_state->sync_file) return -ENOMEM; return 0; } static int prepare_signaling(struct drm_device *dev, struct drm_atomic_state *state, struct drm_mode_atomic *arg, struct drm_file *file_priv, struct drm_out_fence_state **fence_state, unsigned int *num_fences) { struct drm_crtc *crtc; struct drm_crtc_state *crtc_state; struct drm_connector *conn; struct drm_connector_state *conn_state; int i, c = 0, ret; if (arg->flags & DRM_MODE_ATOMIC_TEST_ONLY) return 0; for_each_new_crtc_in_state(state, crtc, crtc_state, i) { s32 __user *fence_ptr; fence_ptr = get_out_fence_for_crtc(crtc_state->state, crtc); if (arg->flags & DRM_MODE_PAGE_FLIP_EVENT || fence_ptr) { struct drm_pending_vblank_event *e; e = create_vblank_event(crtc, arg->user_data); if (!e) return -ENOMEM; crtc_state->event = e; } if (arg->flags & DRM_MODE_PAGE_FLIP_EVENT) { struct drm_pending_vblank_event *e = crtc_state->event; if (!file_priv) continue; ret = drm_event_reserve_init(dev, file_priv, &e->base, &e->event.base); if (ret) { kfree(e); crtc_state->event = NULL; return ret; } } if (fence_ptr) { struct dma_fence *fence; struct drm_out_fence_state *f; f = krealloc(*fence_state, sizeof(**fence_state) * (*num_fences + 1), GFP_KERNEL); if (!f) return -ENOMEM; memset(&f[*num_fences], 0, sizeof(*f)); f[*num_fences].out_fence_ptr = fence_ptr; *fence_state = f; fence = drm_crtc_create_fence(crtc); if (!fence) return -ENOMEM; ret = setup_out_fence(&f[(*num_fences)++], fence); if (ret) { dma_fence_put(fence); return ret; } crtc_state->event->base.fence = fence; } c++; } for_each_new_connector_in_state(state, conn, conn_state, i) { struct drm_writeback_connector *wb_conn; struct drm_out_fence_state *f; struct dma_fence *fence; s32 __user *fence_ptr; if (!conn_state->writeback_job) continue; fence_ptr = get_out_fence_for_connector(state, conn); if (!fence_ptr) continue; f = krealloc(*fence_state, sizeof(**fence_state) * (*num_fences + 1), GFP_KERNEL); if (!f) return -ENOMEM; memset(&f[*num_fences], 0, sizeof(*f)); f[*num_fences].out_fence_ptr = fence_ptr; *fence_state = f; wb_conn = drm_connector_to_writeback(conn); fence = drm_writeback_get_out_fence(wb_conn); if (!fence) return -ENOMEM; ret = setup_out_fence(&f[(*num_fences)++], fence); if (ret) { dma_fence_put(fence); return ret; } conn_state->writeback_job->out_fence = fence; } /* * Having this flag means user mode pends on event which will never * reach due to lack of at least one CRTC for signaling */ if (c == 0 && (arg->flags & DRM_MODE_PAGE_FLIP_EVENT)) { drm_dbg_atomic(dev, "need at least one CRTC for DRM_MODE_PAGE_FLIP_EVENT"); return -EINVAL; } return 0; } static void complete_signaling(struct drm_device *dev, struct drm_atomic_state *state, struct drm_out_fence_state *fence_state, unsigned int num_fences, bool install_fds) { struct drm_crtc *crtc; struct drm_crtc_state *crtc_state; int i; if (install_fds) { for (i = 0; i < num_fences; i++) fd_install(fence_state[i].fd, fence_state[i].sync_file->file); kfree(fence_state); return; } for_each_new_crtc_in_state(state, crtc, crtc_state, i) { struct drm_pending_vblank_event *event = crtc_state->event; /* * Free the allocated event. drm_atomic_helper_setup_commit * can allocate an event too, so only free it if it's ours * to prevent a double free in drm_atomic_state_clear. */ if (event && (event->base.fence || event->base.file_priv)) { drm_event_cancel_free(dev, &event->base); crtc_state->event = NULL; } } if (!fence_state) return; for (i = 0; i < num_fences; i++) { if (fence_state[i].sync_file) fput(fence_state[i].sync_file->file); if (fence_state[i].fd >= 0) put_unused_fd(fence_state[i].fd); /* If this fails log error to the user */ if (fence_state[i].out_fence_ptr && put_user(-1, fence_state[i].out_fence_ptr)) drm_dbg_atomic(dev, "Couldn't clear out_fence_ptr\n"); } kfree(fence_state); } static void set_async_flip(struct drm_atomic_state *state) { struct drm_crtc *crtc; struct drm_crtc_state *crtc_state; int i; for_each_new_crtc_in_state(state, crtc, crtc_state, i) { crtc_state->async_flip = true; } } int drm_mode_atomic_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_mode_atomic *arg = data; uint32_t __user *objs_ptr = (uint32_t __user *)(unsigned long)(arg->objs_ptr); uint32_t __user *count_props_ptr = (uint32_t __user *)(unsigned long)(arg->count_props_ptr); uint32_t __user *props_ptr = (uint32_t __user *)(unsigned long)(arg->props_ptr); uint64_t __user *prop_values_ptr = (uint64_t __user *)(unsigned long)(arg->prop_values_ptr); unsigned int copied_objs, copied_props; struct drm_atomic_state *state; struct drm_modeset_acquire_ctx ctx; struct drm_out_fence_state *fence_state; int ret = 0; unsigned int i, j, num_fences; bool async_flip = false; /* disallow for drivers not supporting atomic: */ if (!drm_core_check_feature(dev, DRIVER_ATOMIC)) return -EOPNOTSUPP; /* disallow for userspace that has not enabled atomic cap (even * though this may be a bit overkill, since legacy userspace * wouldn't know how to call this ioctl) */ if (!file_priv->atomic) { drm_dbg_atomic(dev, "commit failed: atomic cap not enabled\n"); return -EINVAL; } if (arg->flags & ~DRM_MODE_ATOMIC_FLAGS) { drm_dbg_atomic(dev, "commit failed: invalid flag\n"); return -EINVAL; } if (arg->reserved) { drm_dbg_atomic(dev, "commit failed: reserved field set\n"); return -EINVAL; } if (arg->flags & DRM_MODE_PAGE_FLIP_ASYNC) { if (!dev->mode_config.async_page_flip) { drm_dbg_atomic(dev, "commit failed: DRM_MODE_PAGE_FLIP_ASYNC not supported\n"); return -EINVAL; } async_flip = true; } /* can't test and expect an event at the same time. */ if ((arg->flags & DRM_MODE_ATOMIC_TEST_ONLY) && (arg->flags & DRM_MODE_PAGE_FLIP_EVENT)) { drm_dbg_atomic(dev, "commit failed: page-flip event requested with test-only commit\n"); return -EINVAL; } state = drm_atomic_state_alloc(dev); if (!state) return -ENOMEM; drm_modeset_acquire_init(&ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE); state->acquire_ctx = &ctx; state->allow_modeset = !!(arg->flags & DRM_MODE_ATOMIC_ALLOW_MODESET); retry: copied_objs = 0; copied_props = 0; fence_state = NULL; num_fences = 0; for (i = 0; i < arg->count_objs; i++) { uint32_t obj_id, count_props; struct drm_mode_object *obj; if (get_user(obj_id, objs_ptr + copied_objs)) { ret = -EFAULT; goto out; } obj = drm_mode_object_find(dev, file_priv, obj_id, DRM_MODE_OBJECT_ANY); if (!obj) { drm_dbg_atomic(dev, "cannot find object ID %d", obj_id); ret = -ENOENT; goto out; } if (!obj->properties) { drm_dbg_atomic(dev, "[OBJECT:%d] has no properties", obj_id); drm_mode_object_put(obj); ret = -ENOENT; goto out; } if (get_user(count_props, count_props_ptr + copied_objs)) { drm_mode_object_put(obj); ret = -EFAULT; goto out; } copied_objs++; for (j = 0; j < count_props; j++) { uint32_t prop_id; uint64_t prop_value; struct drm_property *prop; if (get_user(prop_id, props_ptr + copied_props)) { drm_mode_object_put(obj); ret = -EFAULT; goto out; } prop = drm_mode_obj_find_prop_id(obj, prop_id); if (!prop) { drm_dbg_atomic(dev, "[OBJECT:%d] cannot find property ID %d", obj_id, prop_id); drm_mode_object_put(obj); ret = -ENOENT; goto out; } if (copy_from_user(&prop_value, prop_values_ptr + copied_props, sizeof(prop_value))) { drm_mode_object_put(obj); ret = -EFAULT; goto out; } ret = drm_atomic_set_property(state, file_priv, obj, prop, prop_value, async_flip); if (ret) { drm_mode_object_put(obj); goto out; } copied_props++; } drm_mode_object_put(obj); } ret = prepare_signaling(dev, state, arg, file_priv, &fence_state, &num_fences); if (ret) goto out; if (arg->flags & DRM_MODE_PAGE_FLIP_ASYNC) set_async_flip(state); if (arg->flags & DRM_MODE_ATOMIC_TEST_ONLY) { ret = drm_atomic_check_only(state); } else if (arg->flags & DRM_MODE_ATOMIC_NONBLOCK) { ret = drm_atomic_nonblocking_commit(state); } else { ret = drm_atomic_commit(state); } out: complete_signaling(dev, state, fence_state, num_fences, !ret); if (ret == -EDEADLK) { drm_atomic_state_clear(state); ret = drm_modeset_backoff(&ctx); if (!ret) goto retry; } drm_atomic_state_put(state); drm_modeset_drop_locks(&ctx); drm_modeset_acquire_fini(&ctx); return ret; } |
| 4 1 3 4 4 4 2 4 2 2 2 2 1 1 1 1 1 1 1 1 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/module.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_socket.h> #include <net/inet_sock.h> #include <net/tcp.h> struct nft_socket { enum nft_socket_keys key:8; u8 level; u8 len; union { u8 dreg; }; }; static void nft_socket_wildcard(const struct nft_pktinfo *pkt, struct nft_regs *regs, struct sock *sk, u32 *dest) { switch (nft_pf(pkt)) { case NFPROTO_IPV4: nft_reg_store8(dest, inet_sk(sk)->inet_rcv_saddr == 0); break; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case NFPROTO_IPV6: nft_reg_store8(dest, ipv6_addr_any(&sk->sk_v6_rcv_saddr)); break; #endif default: regs->verdict.code = NFT_BREAK; return; } } #ifdef CONFIG_SOCK_CGROUP_DATA static noinline bool nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo *pkt, u32 level) { struct cgroup *cgrp; u64 cgid; if (!sk_fullsock(sk)) return false; cgrp = cgroup_ancestor(sock_cgroup_ptr(&sk->sk_cgrp_data), level); if (!cgrp) return false; cgid = cgroup_id(cgrp); memcpy(dest, &cgid, sizeof(u64)); return true; } #endif static struct sock *nft_socket_do_lookup(const struct nft_pktinfo *pkt) { const struct net_device *indev = nft_in(pkt); const struct sk_buff *skb = pkt->skb; struct sock *sk = NULL; if (!indev) return NULL; switch (nft_pf(pkt)) { case NFPROTO_IPV4: sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, indev); break; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case NFPROTO_IPV6: sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, indev); break; #endif default: WARN_ON_ONCE(1); break; } return sk; } static void nft_socket_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_socket *priv = nft_expr_priv(expr); struct sk_buff *skb = pkt->skb; struct sock *sk = skb->sk; u32 *dest = ®s->data[priv->dreg]; if (sk && !net_eq(nft_net(pkt), sock_net(sk))) sk = NULL; if (!sk) sk = nft_socket_do_lookup(pkt); if (!sk) { regs->verdict.code = NFT_BREAK; return; } switch(priv->key) { case NFT_SOCKET_TRANSPARENT: nft_reg_store8(dest, inet_sk_transparent(sk)); break; case NFT_SOCKET_MARK: if (sk_fullsock(sk)) { *dest = READ_ONCE(sk->sk_mark); } else { regs->verdict.code = NFT_BREAK; return; } break; case NFT_SOCKET_WILDCARD: if (!sk_fullsock(sk)) { regs->verdict.code = NFT_BREAK; return; } nft_socket_wildcard(pkt, regs, sk, dest); break; #ifdef CONFIG_SOCK_CGROUP_DATA case NFT_SOCKET_CGROUPV2: if (!nft_sock_get_eval_cgroupv2(dest, sk, pkt, priv->level)) { regs->verdict.code = NFT_BREAK; return; } break; #endif default: WARN_ON(1); regs->verdict.code = NFT_BREAK; } if (sk != skb->sk) sock_gen_put(sk); } static const struct nla_policy nft_socket_policy[NFTA_SOCKET_MAX + 1] = { [NFTA_SOCKET_KEY] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_SOCKET_DREG] = { .type = NLA_U32 }, [NFTA_SOCKET_LEVEL] = NLA_POLICY_MAX(NLA_BE32, 255), }; static int nft_socket_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_socket *priv = nft_expr_priv(expr); unsigned int len; if (!tb[NFTA_SOCKET_DREG] || !tb[NFTA_SOCKET_KEY]) return -EINVAL; switch(ctx->family) { case NFPROTO_IPV4: #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case NFPROTO_IPV6: #endif case NFPROTO_INET: break; default: return -EOPNOTSUPP; } priv->key = ntohl(nla_get_be32(tb[NFTA_SOCKET_KEY])); switch(priv->key) { case NFT_SOCKET_TRANSPARENT: case NFT_SOCKET_WILDCARD: len = sizeof(u8); break; case NFT_SOCKET_MARK: len = sizeof(u32); break; #ifdef CONFIG_CGROUPS case NFT_SOCKET_CGROUPV2: { unsigned int level; if (!tb[NFTA_SOCKET_LEVEL]) return -EINVAL; level = ntohl(nla_get_be32(tb[NFTA_SOCKET_LEVEL])); if (level > 255) return -EOPNOTSUPP; priv->level = level; len = sizeof(u64); break; } #endif default: return -EOPNOTSUPP; } priv->len = len; return nft_parse_register_store(ctx, tb[NFTA_SOCKET_DREG], &priv->dreg, NULL, NFT_DATA_VALUE, len); } static int nft_socket_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_socket *priv = nft_expr_priv(expr); if (nla_put_be32(skb, NFTA_SOCKET_KEY, htonl(priv->key))) return -1; if (nft_dump_register(skb, NFTA_SOCKET_DREG, priv->dreg)) return -1; if (priv->key == NFT_SOCKET_CGROUPV2 && nla_put_be32(skb, NFTA_SOCKET_LEVEL, htonl(priv->level))) return -1; return 0; } static bool nft_socket_reduce(struct nft_regs_track *track, const struct nft_expr *expr) { const struct nft_socket *priv = nft_expr_priv(expr); const struct nft_socket *socket; if (!nft_reg_track_cmp(track, expr, priv->dreg)) { nft_reg_track_update(track, expr, priv->dreg, priv->len); return false; } socket = nft_expr_priv(track->regs[priv->dreg].selector); if (priv->key != socket->key || priv->dreg != socket->dreg || priv->level != socket->level) { nft_reg_track_update(track, expr, priv->dreg, priv->len); return false; } if (!track->regs[priv->dreg].bitwise) return true; return nft_expr_reduce_bitwise(track, expr); } static int nft_socket_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && ctx->family != NFPROTO_INET) return -EOPNOTSUPP; return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT)); } static struct nft_expr_type nft_socket_type; static const struct nft_expr_ops nft_socket_ops = { .type = &nft_socket_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_socket)), .eval = nft_socket_eval, .init = nft_socket_init, .dump = nft_socket_dump, .validate = nft_socket_validate, .reduce = nft_socket_reduce, }; static struct nft_expr_type nft_socket_type __read_mostly = { .name = "socket", .ops = &nft_socket_ops, .policy = nft_socket_policy, .maxattr = NFTA_SOCKET_MAX, .owner = THIS_MODULE, }; static int __init nft_socket_module_init(void) { return nft_register_expr(&nft_socket_type); } static void __exit nft_socket_module_exit(void) { nft_unregister_expr(&nft_socket_type); } module_init(nft_socket_module_init); module_exit(nft_socket_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Máté Eckl"); MODULE_DESCRIPTION("nf_tables socket match module"); MODULE_ALIAS_NFT_EXPR("socket"); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * 32-bit compatibility support for ELF format executables and core dumps. * * Copyright (C) 2007 Red Hat, Inc. All rights reserved. * * Red Hat Author: Roland McGrath. * * This file is used in a 64-bit kernel that wants to support 32-bit ELF. * asm/elf.h is responsible for defining the compat_* and COMPAT_* macros * used below, with definitions appropriate for 32-bit ABI compatibility. * * We use macros to rename the ABI types and machine-dependent * functions used in binfmt_elf.c to compat versions. */ #include <linux/elfcore-compat.h> #include <linux/time.h> #define ELF_COMPAT 1 /* * Rename the basic ELF layout types to refer to the 32-bit class of files. */ #undef ELF_CLASS #define ELF_CLASS ELFCLASS32 #undef elfhdr #undef elf_phdr #undef elf_shdr #undef elf_note #undef elf_addr_t #undef ELF_GNU_PROPERTY_ALIGN #define elfhdr elf32_hdr #define elf_phdr elf32_phdr #define elf_shdr elf32_shdr #define elf_note elf32_note #define elf_addr_t Elf32_Addr #define ELF_GNU_PROPERTY_ALIGN ELF32_GNU_PROPERTY_ALIGN /* * Some data types as stored in coredump. */ #define user_long_t compat_long_t #define user_siginfo_t compat_siginfo_t #define copy_siginfo_to_external copy_siginfo_to_external32 /* * The machine-dependent core note format types are defined in elfcore-compat.h, * which requires asm/elf.h to define compat_elf_gregset_t et al. */ #define elf_prstatus compat_elf_prstatus #define elf_prstatus_common compat_elf_prstatus_common #define elf_prpsinfo compat_elf_prpsinfo #undef ns_to_kernel_old_timeval #define ns_to_kernel_old_timeval ns_to_old_timeval32 /* * To use this file, asm/elf.h must define compat_elf_check_arch. * The other following macros can be defined if the compat versions * differ from the native ones, or omitted when they match. */ #undef elf_check_arch #define elf_check_arch compat_elf_check_arch #ifdef COMPAT_ELF_PLATFORM #undef ELF_PLATFORM #define ELF_PLATFORM COMPAT_ELF_PLATFORM #endif #ifdef COMPAT_ELF_HWCAP #undef ELF_HWCAP #define ELF_HWCAP COMPAT_ELF_HWCAP #endif #ifdef COMPAT_ELF_HWCAP2 #undef ELF_HWCAP2 #define ELF_HWCAP2 COMPAT_ELF_HWCAP2 #endif #ifdef COMPAT_ARCH_DLINFO #undef ARCH_DLINFO #define ARCH_DLINFO COMPAT_ARCH_DLINFO #endif #ifdef COMPAT_ELF_ET_DYN_BASE #undef ELF_ET_DYN_BASE #define ELF_ET_DYN_BASE COMPAT_ELF_ET_DYN_BASE #endif #ifdef COMPAT_ELF_PLAT_INIT #undef ELF_PLAT_INIT #define ELF_PLAT_INIT COMPAT_ELF_PLAT_INIT #endif #ifdef COMPAT_SET_PERSONALITY #undef SET_PERSONALITY #define SET_PERSONALITY COMPAT_SET_PERSONALITY #endif #ifdef compat_start_thread #define COMPAT_START_THREAD(ex, regs, new_ip, new_sp) \ compat_start_thread(regs, new_ip, new_sp) #endif #ifdef COMPAT_START_THREAD #undef START_THREAD #define START_THREAD COMPAT_START_THREAD #endif #ifdef compat_arch_setup_additional_pages #define COMPAT_ARCH_SETUP_ADDITIONAL_PAGES(bprm, ex, interpreter) \ compat_arch_setup_additional_pages(bprm, interpreter) #endif #ifdef COMPAT_ARCH_SETUP_ADDITIONAL_PAGES #undef ARCH_HAS_SETUP_ADDITIONAL_PAGES #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 #undef ARCH_SETUP_ADDITIONAL_PAGES #define ARCH_SETUP_ADDITIONAL_PAGES COMPAT_ARCH_SETUP_ADDITIONAL_PAGES #endif #ifdef compat_elf_read_implies_exec #undef elf_read_implies_exec #define elf_read_implies_exec compat_elf_read_implies_exec #endif /* * Rename a few of the symbols that binfmt_elf.c will define. * These are all local so the names don't really matter, but it * might make some debugging less confusing not to duplicate them. */ #define elf_format compat_elf_format #define init_elf_binfmt init_compat_elf_binfmt #define exit_elf_binfmt exit_compat_elf_binfmt #define binfmt_elf_test_cases compat_binfmt_elf_test_cases #define binfmt_elf_test_suite compat_binfmt_elf_test_suite /* * We share all the actual code with the native (64-bit) version. */ #include "binfmt_elf.c" |
| 5 4 4 4 4 4 1 4 4 4 1 4 4 4 4 4 4 4 2 4 4 | 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 | /* * Copyright (c) 2016 Intel Corporation * * Permission to use, copy, modify, distribute, and sell this software and its * documentation for any purpose is hereby granted without fee, provided that * the above copyright notice appear in all copies and that both that copyright * notice and this permission notice appear in supporting documentation, and * that the name of the copyright holders not be used in advertising or * publicity pertaining to distribution of the software without specific, * written prior permission. The copyright holders make no representations * about the suitability of this software for any purpose. It is provided "as * is" without express or implied warranty. * * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE * OF THIS SOFTWARE. */ #include <linux/uaccess.h> #include <drm/drm_drv.h> #include <drm/drm_encoder.h> #include <drm/drm_file.h> #include <drm/drm_framebuffer.h> #include <drm/drm_managed.h> #include <drm/drm_mode_config.h> #include <drm/drm_print.h> #include <linux/dma-resv.h> #include "drm_crtc_internal.h" #include "drm_internal.h" int drm_modeset_register_all(struct drm_device *dev) { int ret; ret = drm_plane_register_all(dev); if (ret) goto err_plane; ret = drm_crtc_register_all(dev); if (ret) goto err_crtc; ret = drm_encoder_register_all(dev); if (ret) goto err_encoder; ret = drm_connector_register_all(dev); if (ret) goto err_connector; return 0; err_connector: drm_encoder_unregister_all(dev); err_encoder: drm_crtc_unregister_all(dev); err_crtc: drm_plane_unregister_all(dev); err_plane: return ret; } void drm_modeset_unregister_all(struct drm_device *dev) { drm_connector_unregister_all(dev); drm_encoder_unregister_all(dev); drm_crtc_unregister_all(dev); drm_plane_unregister_all(dev); } /** * drm_mode_getresources - get graphics configuration * @dev: drm device for the ioctl * @data: data pointer for the ioctl * @file_priv: drm file for the ioctl call * * Construct a set of configuration description structures and return * them to the user, including CRTC, connector and framebuffer configuration. * * Called by the user via ioctl. * * Returns: * Zero on success, negative errno on failure. */ int drm_mode_getresources(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_mode_card_res *card_res = data; struct drm_framebuffer *fb; struct drm_connector *connector; struct drm_crtc *crtc; struct drm_encoder *encoder; int count, ret = 0; uint32_t __user *fb_id; uint32_t __user *crtc_id; uint32_t __user *connector_id; uint32_t __user *encoder_id; struct drm_connector_list_iter conn_iter; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EOPNOTSUPP; mutex_lock(&file_priv->fbs_lock); count = 0; fb_id = u64_to_user_ptr(card_res->fb_id_ptr); list_for_each_entry(fb, &file_priv->fbs, filp_head) { if (count < card_res->count_fbs && put_user(fb->base.id, fb_id + count)) { mutex_unlock(&file_priv->fbs_lock); return -EFAULT; } count++; } card_res->count_fbs = count; mutex_unlock(&file_priv->fbs_lock); card_res->max_height = dev->mode_config.max_height; card_res->min_height = dev->mode_config.min_height; card_res->max_width = dev->mode_config.max_width; card_res->min_width = dev->mode_config.min_width; count = 0; crtc_id = u64_to_user_ptr(card_res->crtc_id_ptr); drm_for_each_crtc(crtc, dev) { if (drm_lease_held(file_priv, crtc->base.id)) { if (count < card_res->count_crtcs && put_user(crtc->base.id, crtc_id + count)) return -EFAULT; count++; } } card_res->count_crtcs = count; count = 0; encoder_id = u64_to_user_ptr(card_res->encoder_id_ptr); drm_for_each_encoder(encoder, dev) { if (count < card_res->count_encoders && put_user(encoder->base.id, encoder_id + count)) return -EFAULT; count++; } card_res->count_encoders = count; drm_connector_list_iter_begin(dev, &conn_iter); count = 0; connector_id = u64_to_user_ptr(card_res->connector_id_ptr); drm_for_each_connector_iter(connector, &conn_iter) { /* only expose writeback connectors if userspace understands them */ if (!file_priv->writeback_connectors && (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK)) continue; if (drm_lease_held(file_priv, connector->base.id)) { if (count < card_res->count_connectors && put_user(connector->base.id, connector_id + count)) { drm_connector_list_iter_end(&conn_iter); return -EFAULT; } count++; } } card_res->count_connectors = count; drm_connector_list_iter_end(&conn_iter); return ret; } /** * drm_mode_config_reset - call ->reset callbacks * @dev: drm device * * This functions calls all the crtc's, encoder's and connector's ->reset * callback. Drivers can use this in e.g. their driver load or resume code to * reset hardware and software state. */ void drm_mode_config_reset(struct drm_device *dev) { struct drm_crtc *crtc; struct drm_plane *plane; struct drm_encoder *encoder; struct drm_connector *connector; struct drm_connector_list_iter conn_iter; drm_for_each_plane(plane, dev) if (plane->funcs->reset) plane->funcs->reset(plane); drm_for_each_crtc(crtc, dev) if (crtc->funcs->reset) crtc->funcs->reset(crtc); drm_for_each_encoder(encoder, dev) if (encoder->funcs && encoder->funcs->reset) encoder->funcs->reset(encoder); drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) if (connector->funcs->reset) connector->funcs->reset(connector); drm_connector_list_iter_end(&conn_iter); } EXPORT_SYMBOL(drm_mode_config_reset); /* * Global properties */ static const struct drm_prop_enum_list drm_plane_type_enum_list[] = { { DRM_PLANE_TYPE_OVERLAY, "Overlay" }, { DRM_PLANE_TYPE_PRIMARY, "Primary" }, { DRM_PLANE_TYPE_CURSOR, "Cursor" }, }; static int drm_mode_create_standard_properties(struct drm_device *dev) { struct drm_property *prop; int ret; ret = drm_connector_create_standard_properties(dev); if (ret) return ret; prop = drm_property_create_enum(dev, DRM_MODE_PROP_IMMUTABLE, "type", drm_plane_type_enum_list, ARRAY_SIZE(drm_plane_type_enum_list)); if (!prop) return -ENOMEM; dev->mode_config.plane_type_property = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, "SRC_X", 0, UINT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_src_x = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, "SRC_Y", 0, UINT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_src_y = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, "SRC_W", 0, UINT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_src_w = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, "SRC_H", 0, UINT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_src_h = prop; prop = drm_property_create_signed_range(dev, DRM_MODE_PROP_ATOMIC, "CRTC_X", INT_MIN, INT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_crtc_x = prop; prop = drm_property_create_signed_range(dev, DRM_MODE_PROP_ATOMIC, "CRTC_Y", INT_MIN, INT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_crtc_y = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, "CRTC_W", 0, INT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_crtc_w = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, "CRTC_H", 0, INT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_crtc_h = prop; prop = drm_property_create_object(dev, DRM_MODE_PROP_ATOMIC, "FB_ID", DRM_MODE_OBJECT_FB); if (!prop) return -ENOMEM; dev->mode_config.prop_fb_id = prop; prop = drm_property_create_signed_range(dev, DRM_MODE_PROP_ATOMIC, "IN_FENCE_FD", -1, INT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_in_fence_fd = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, "OUT_FENCE_PTR", 0, U64_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_out_fence_ptr = prop; prop = drm_property_create_object(dev, DRM_MODE_PROP_ATOMIC, "CRTC_ID", DRM_MODE_OBJECT_CRTC); if (!prop) return -ENOMEM; dev->mode_config.prop_crtc_id = prop; prop = drm_property_create(dev, DRM_MODE_PROP_ATOMIC | DRM_MODE_PROP_BLOB, "FB_DAMAGE_CLIPS", 0); if (!prop) return -ENOMEM; dev->mode_config.prop_fb_damage_clips = prop; prop = drm_property_create_bool(dev, DRM_MODE_PROP_ATOMIC, "ACTIVE"); if (!prop) return -ENOMEM; dev->mode_config.prop_active = prop; prop = drm_property_create(dev, DRM_MODE_PROP_ATOMIC | DRM_MODE_PROP_BLOB, "MODE_ID", 0); if (!prop) return -ENOMEM; dev->mode_config.prop_mode_id = prop; prop = drm_property_create_bool(dev, 0, "VRR_ENABLED"); if (!prop) return -ENOMEM; dev->mode_config.prop_vrr_enabled = prop; prop = drm_property_create(dev, DRM_MODE_PROP_BLOB, "DEGAMMA_LUT", 0); if (!prop) return -ENOMEM; dev->mode_config.degamma_lut_property = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_IMMUTABLE, "DEGAMMA_LUT_SIZE", 0, UINT_MAX); if (!prop) return -ENOMEM; dev->mode_config.degamma_lut_size_property = prop; prop = drm_property_create(dev, DRM_MODE_PROP_BLOB, "CTM", 0); if (!prop) return -ENOMEM; dev->mode_config.ctm_property = prop; prop = drm_property_create(dev, DRM_MODE_PROP_BLOB, "GAMMA_LUT", 0); if (!prop) return -ENOMEM; dev->mode_config.gamma_lut_property = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_IMMUTABLE, "GAMMA_LUT_SIZE", 0, UINT_MAX); if (!prop) return -ENOMEM; dev->mode_config.gamma_lut_size_property = prop; prop = drm_property_create(dev, DRM_MODE_PROP_IMMUTABLE | DRM_MODE_PROP_BLOB, "IN_FORMATS", 0); if (!prop) return -ENOMEM; dev->mode_config.modifiers_property = prop; prop = drm_property_create(dev, DRM_MODE_PROP_IMMUTABLE | DRM_MODE_PROP_BLOB, "SIZE_HINTS", 0); if (!prop) return -ENOMEM; dev->mode_config.size_hints_property = prop; return 0; } static void drm_mode_config_init_release(struct drm_device *dev, void *ptr) { drm_mode_config_cleanup(dev); } /** * drmm_mode_config_init - managed DRM mode_configuration structure * initialization * @dev: DRM device * * Initialize @dev's mode_config structure, used for tracking the graphics * configuration of @dev. * * Since this initializes the modeset locks, no locking is possible. Which is no * problem, since this should happen single threaded at init time. It is the * driver's problem to ensure this guarantee. * * Cleanup is automatically handled through registering drm_mode_config_cleanup * with drmm_add_action(). * * Returns: 0 on success, negative error value on failure. */ int drmm_mode_config_init(struct drm_device *dev) { int ret; mutex_init(&dev->mode_config.mutex); drm_modeset_lock_init(&dev->mode_config.connection_mutex); mutex_init(&dev->mode_config.idr_mutex); mutex_init(&dev->mode_config.fb_lock); mutex_init(&dev->mode_config.blob_lock); INIT_LIST_HEAD(&dev->mode_config.fb_list); INIT_LIST_HEAD(&dev->mode_config.crtc_list); INIT_LIST_HEAD(&dev->mode_config.connector_list); INIT_LIST_HEAD(&dev->mode_config.encoder_list); INIT_LIST_HEAD(&dev->mode_config.property_list); INIT_LIST_HEAD(&dev->mode_config.property_blob_list); INIT_LIST_HEAD(&dev->mode_config.plane_list); INIT_LIST_HEAD(&dev->mode_config.privobj_list); idr_init_base(&dev->mode_config.object_idr, 1); idr_init_base(&dev->mode_config.tile_idr, 1); ida_init(&dev->mode_config.connector_ida); spin_lock_init(&dev->mode_config.connector_list_lock); init_llist_head(&dev->mode_config.connector_free_list); INIT_WORK(&dev->mode_config.connector_free_work, drm_connector_free_work_fn); ret = drm_mode_create_standard_properties(dev); if (ret) { drm_mode_config_cleanup(dev); return ret; } /* Just to be sure */ dev->mode_config.num_fb = 0; dev->mode_config.num_connector = 0; dev->mode_config.num_crtc = 0; dev->mode_config.num_encoder = 0; dev->mode_config.num_total_plane = 0; if (IS_ENABLED(CONFIG_LOCKDEP)) { struct drm_modeset_acquire_ctx modeset_ctx; struct ww_acquire_ctx resv_ctx; struct dma_resv resv; int ret; dma_resv_init(&resv); drm_modeset_acquire_init(&modeset_ctx, 0); ret = drm_modeset_lock(&dev->mode_config.connection_mutex, &modeset_ctx); if (ret == -EDEADLK) ret = drm_modeset_backoff(&modeset_ctx); ww_acquire_init(&resv_ctx, &reservation_ww_class); ret = dma_resv_lock(&resv, &resv_ctx); if (ret == -EDEADLK) dma_resv_lock_slow(&resv, &resv_ctx); dma_resv_unlock(&resv); ww_acquire_fini(&resv_ctx); drm_modeset_drop_locks(&modeset_ctx); drm_modeset_acquire_fini(&modeset_ctx); dma_resv_fini(&resv); } return drmm_add_action_or_reset(dev, drm_mode_config_init_release, NULL); } EXPORT_SYMBOL(drmm_mode_config_init); /** * drm_mode_config_cleanup - free up DRM mode_config info * @dev: DRM device * * Free up all the connectors and CRTCs associated with this DRM device, then * free up the framebuffers and associated buffer objects. * * Note that since this /should/ happen single-threaded at driver/device * teardown time, no locking is required. It's the driver's job to ensure that * this guarantee actually holds true. * * FIXME: With the managed drmm_mode_config_init() it is no longer necessary for * drivers to explicitly call this function. */ void drm_mode_config_cleanup(struct drm_device *dev) { struct drm_connector *connector; struct drm_connector_list_iter conn_iter; struct drm_crtc *crtc, *ct; struct drm_encoder *encoder, *enct; struct drm_framebuffer *fb, *fbt; struct drm_property *property, *pt; struct drm_property_blob *blob, *bt; struct drm_plane *plane, *plt; list_for_each_entry_safe(encoder, enct, &dev->mode_config.encoder_list, head) { encoder->funcs->destroy(encoder); } drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) { /* drm_connector_list_iter holds an full reference to the * current connector itself, which means it is inherently safe * against unreferencing the current connector - but not against * deleting it right away. */ drm_connector_put(connector); } drm_connector_list_iter_end(&conn_iter); /* connector_iter drops references in a work item. */ flush_work(&dev->mode_config.connector_free_work); if (WARN_ON(!list_empty(&dev->mode_config.connector_list))) { drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) DRM_ERROR("connector %s leaked!\n", connector->name); drm_connector_list_iter_end(&conn_iter); } list_for_each_entry_safe(property, pt, &dev->mode_config.property_list, head) { drm_property_destroy(dev, property); } list_for_each_entry_safe(plane, plt, &dev->mode_config.plane_list, head) { plane->funcs->destroy(plane); } list_for_each_entry_safe(crtc, ct, &dev->mode_config.crtc_list, head) { crtc->funcs->destroy(crtc); } list_for_each_entry_safe(blob, bt, &dev->mode_config.property_blob_list, head_global) { drm_property_blob_put(blob); } /* * Single-threaded teardown context, so it's not required to grab the * fb_lock to protect against concurrent fb_list access. Contrary, it * would actually deadlock with the drm_framebuffer_cleanup function. * * Also, if there are any framebuffers left, that's a driver leak now, * so politely WARN about this. */ WARN_ON(!list_empty(&dev->mode_config.fb_list)); list_for_each_entry_safe(fb, fbt, &dev->mode_config.fb_list, head) { struct drm_printer p = drm_dbg_printer(dev, DRM_UT_KMS, "[leaked fb]"); drm_printf(&p, "framebuffer[%u]:\n", fb->base.id); drm_framebuffer_print_info(&p, 1, fb); drm_framebuffer_free(&fb->base.refcount); } ida_destroy(&dev->mode_config.connector_ida); idr_destroy(&dev->mode_config.tile_idr); idr_destroy(&dev->mode_config.object_idr); drm_modeset_lock_fini(&dev->mode_config.connection_mutex); } EXPORT_SYMBOL(drm_mode_config_cleanup); static u32 full_encoder_mask(struct drm_device *dev) { struct drm_encoder *encoder; u32 encoder_mask = 0; drm_for_each_encoder(encoder, dev) encoder_mask |= drm_encoder_mask(encoder); return encoder_mask; } /* * For some reason we want the encoder itself included in * possible_clones. Make life easy for drivers by allowing them * to leave possible_clones unset if no cloning is possible. */ static void fixup_encoder_possible_clones(struct drm_encoder *encoder) { if (encoder->possible_clones == 0) encoder->possible_clones = drm_encoder_mask(encoder); } static void validate_encoder_possible_clones(struct drm_encoder *encoder) { struct drm_device *dev = encoder->dev; u32 encoder_mask = full_encoder_mask(dev); struct drm_encoder *other; drm_for_each_encoder(other, dev) { WARN(!!(encoder->possible_clones & drm_encoder_mask(other)) != !!(other->possible_clones & drm_encoder_mask(encoder)), "possible_clones mismatch: " "[ENCODER:%d:%s] mask=0x%x possible_clones=0x%x vs. " "[ENCODER:%d:%s] mask=0x%x possible_clones=0x%x\n", encoder->base.id, encoder->name, drm_encoder_mask(encoder), encoder->possible_clones, other->base.id, other->name, drm_encoder_mask(other), other->possible_clones); } WARN((encoder->possible_clones & drm_encoder_mask(encoder)) == 0 || (encoder->possible_clones & ~encoder_mask) != 0, "Bogus possible_clones: " "[ENCODER:%d:%s] possible_clones=0x%x (full encoder mask=0x%x)\n", encoder->base.id, encoder->name, encoder->possible_clones, encoder_mask); } static u32 full_crtc_mask(struct drm_device *dev) { struct drm_crtc *crtc; u32 crtc_mask = 0; drm_for_each_crtc(crtc, dev) crtc_mask |= drm_crtc_mask(crtc); return crtc_mask; } static void validate_encoder_possible_crtcs(struct drm_encoder *encoder) { u32 crtc_mask = full_crtc_mask(encoder->dev); WARN((encoder->possible_crtcs & crtc_mask) == 0 || (encoder->possible_crtcs & ~crtc_mask) != 0, "Bogus possible_crtcs: " "[ENCODER:%d:%s] possible_crtcs=0x%x (full crtc mask=0x%x)\n", encoder->base.id, encoder->name, encoder->possible_crtcs, crtc_mask); } void drm_mode_config_validate(struct drm_device *dev) { struct drm_encoder *encoder; struct drm_crtc *crtc; struct drm_plane *plane; u32 primary_with_crtc = 0, cursor_with_crtc = 0; unsigned int num_primary = 0; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return; drm_for_each_encoder(encoder, dev) fixup_encoder_possible_clones(encoder); drm_for_each_encoder(encoder, dev) { validate_encoder_possible_clones(encoder); validate_encoder_possible_crtcs(encoder); } drm_for_each_crtc(crtc, dev) { WARN(!crtc->primary, "Missing primary plane on [CRTC:%d:%s]\n", crtc->base.id, crtc->name); WARN(crtc->cursor && crtc->funcs->cursor_set, "[CRTC:%d:%s] must not have both a cursor plane and a cursor_set func", crtc->base.id, crtc->name); WARN(crtc->cursor && crtc->funcs->cursor_set2, "[CRTC:%d:%s] must not have both a cursor plane and a cursor_set2 func", crtc->base.id, crtc->name); WARN(crtc->cursor && crtc->funcs->cursor_move, "[CRTC:%d:%s] must not have both a cursor plane and a cursor_move func", crtc->base.id, crtc->name); if (crtc->primary) { WARN(!(crtc->primary->possible_crtcs & drm_crtc_mask(crtc)), "Bogus primary plane possible_crtcs: [PLANE:%d:%s] must be compatible with [CRTC:%d:%s]\n", crtc->primary->base.id, crtc->primary->name, crtc->base.id, crtc->name); WARN(primary_with_crtc & drm_plane_mask(crtc->primary), "Primary plane [PLANE:%d:%s] used for multiple CRTCs", crtc->primary->base.id, crtc->primary->name); primary_with_crtc |= drm_plane_mask(crtc->primary); } if (crtc->cursor) { WARN(!(crtc->cursor->possible_crtcs & drm_crtc_mask(crtc)), "Bogus cursor plane possible_crtcs: [PLANE:%d:%s] must be compatible with [CRTC:%d:%s]\n", crtc->cursor->base.id, crtc->cursor->name, crtc->base.id, crtc->name); WARN(cursor_with_crtc & drm_plane_mask(crtc->cursor), "Cursor plane [PLANE:%d:%s] used for multiple CRTCs", crtc->cursor->base.id, crtc->cursor->name); cursor_with_crtc |= drm_plane_mask(crtc->cursor); } } drm_for_each_plane(plane, dev) { if (plane->type == DRM_PLANE_TYPE_PRIMARY) num_primary++; } WARN(num_primary != dev->mode_config.num_crtc, "Must have as many primary planes as there are CRTCs, but have %u primary planes and %u CRTCs", num_primary, dev->mode_config.num_crtc); } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2000-2001 Vojtech Pavlik * Copyright (c) 2006-2010 Jiri Kosina * * HID to Linux Input mapping */ /* * * Should you need to contact me, the author, you can do so either by * e-mail - mail your message to <vojtech@ucw.cz>, or by paper mail: * Vojtech Pavlik, Simunkova 1594, Prague 8, 182 00 Czech Republic */ #include <linux/module.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/hid.h> #include <linux/hid-debug.h> #include "hid-ids.h" #define unk KEY_UNKNOWN static const unsigned char hid_keyboard[256] = { 0, 0, 0, 0, 30, 48, 46, 32, 18, 33, 34, 35, 23, 36, 37, 38, 50, 49, 24, 25, 16, 19, 31, 20, 22, 47, 17, 45, 21, 44, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 28, 1, 14, 15, 57, 12, 13, 26, 27, 43, 43, 39, 40, 41, 51, 52, 53, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 87, 88, 99, 70,119,110,102,104,111,107,109,106, 105,108,103, 69, 98, 55, 74, 78, 96, 79, 80, 81, 75, 76, 77, 71, 72, 73, 82, 83, 86,127,116,117,183,184,185,186,187,188,189,190, 191,192,193,194,134,138,130,132,128,129,131,137,133,135,136,113, 115,114,unk,unk,unk,121,unk, 89, 93,124, 92, 94, 95,unk,unk,unk, 122,123, 90, 91, 85,unk,unk,unk,unk,unk,unk,unk,111,unk,unk,unk, unk,unk,unk,unk,unk,unk,unk,unk,unk,unk,unk,unk,unk,unk,unk,unk, unk,unk,unk,unk,unk,unk,179,180,unk,unk,unk,unk,unk,unk,unk,unk, unk,unk,unk,unk,unk,unk,unk,unk,unk,unk,unk,unk,unk,unk,unk,unk, unk,unk,unk,unk,unk,unk,unk,unk,111,unk,unk,unk,unk,unk,unk,unk, 29, 42, 56,125, 97, 54,100,126,164,166,165,163,161,115,114,113, 150,158,159,128,136,177,178,176,142,152,173,140,unk,unk,unk,unk }; static const struct { __s32 x; __s32 y; } hid_hat_to_axis[] = {{ 0, 0}, { 0,-1}, { 1,-1}, { 1, 0}, { 1, 1}, { 0, 1}, {-1, 1}, {-1, 0}, {-1,-1}}; struct usage_priority { __u32 usage; /* the HID usage associated */ bool global; /* we assume all usages to be slotted, * unless global */ unsigned int slot_overwrite; /* for globals: allows to set the usage * before or after the slots */ }; /* * hid-input will convert this list into priorities: * the first element will have the highest priority * (the length of the following array) and the last * element the lowest (1). * * hid-input will then shift the priority by 8 bits to leave some space * in case drivers want to interleave other fields. * * To accommodate slotted devices, the slot priority is * defined in the next 8 bits (defined by 0xff - slot). * * If drivers want to add fields before those, hid-input will * leave out the first 8 bits of the priority value. * * This still leaves us 65535 individual priority values. */ static const struct usage_priority hidinput_usages_priorities[] = { { /* Eraser (eraser touching) must always come before tipswitch */ .usage = HID_DG_ERASER, }, { /* Invert must always come before In Range */ .usage = HID_DG_INVERT, }, { /* Is the tip of the tool touching? */ .usage = HID_DG_TIPSWITCH, }, { /* Tip Pressure might emulate tip switch */ .usage = HID_DG_TIPPRESSURE, }, { /* In Range needs to come after the other tool states */ .usage = HID_DG_INRANGE, }, }; #define map_abs(c) hid_map_usage(hidinput, usage, &bit, &max, EV_ABS, (c)) #define map_rel(c) hid_map_usage(hidinput, usage, &bit, &max, EV_REL, (c)) #define map_key(c) hid_map_usage(hidinput, usage, &bit, &max, EV_KEY, (c)) #define map_led(c) hid_map_usage(hidinput, usage, &bit, &max, EV_LED, (c)) #define map_msc(c) hid_map_usage(hidinput, usage, &bit, &max, EV_MSC, (c)) #define map_abs_clear(c) hid_map_usage_clear(hidinput, usage, &bit, \ &max, EV_ABS, (c)) #define map_key_clear(c) hid_map_usage_clear(hidinput, usage, &bit, \ &max, EV_KEY, (c)) static bool match_scancode(struct hid_usage *usage, unsigned int cur_idx, unsigned int scancode) { return (usage->hid & (HID_USAGE_PAGE | HID_USAGE)) == scancode; } static bool match_keycode(struct hid_usage *usage, unsigned int cur_idx, unsigned int keycode) { /* * We should exclude unmapped usages when doing lookup by keycode. */ return (usage->type == EV_KEY && usage->code == keycode); } static bool match_index(struct hid_usage *usage, unsigned int cur_idx, unsigned int idx) { return cur_idx == idx; } typedef bool (*hid_usage_cmp_t)(struct hid_usage *usage, unsigned int cur_idx, unsigned int val); static struct hid_usage *hidinput_find_key(struct hid_device *hid, hid_usage_cmp_t match, unsigned int value, unsigned int *usage_idx) { unsigned int i, j, k, cur_idx = 0; struct hid_report *report; struct hid_usage *usage; for (k = HID_INPUT_REPORT; k <= HID_OUTPUT_REPORT; k++) { list_for_each_entry(report, &hid->report_enum[k].report_list, list) { for (i = 0; i < report->maxfield; i++) { for (j = 0; j < report->field[i]->maxusage; j++) { usage = report->field[i]->usage + j; if (usage->type == EV_KEY || usage->type == 0) { if (match(usage, cur_idx, value)) { if (usage_idx) *usage_idx = cur_idx; return usage; } cur_idx++; } } } } } return NULL; } static struct hid_usage *hidinput_locate_usage(struct hid_device *hid, const struct input_keymap_entry *ke, unsigned int *index) { struct hid_usage *usage; unsigned int scancode; if (ke->flags & INPUT_KEYMAP_BY_INDEX) usage = hidinput_find_key(hid, match_index, ke->index, index); else if (input_scancode_to_scalar(ke, &scancode) == 0) usage = hidinput_find_key(hid, match_scancode, scancode, index); else usage = NULL; return usage; } static int hidinput_getkeycode(struct input_dev *dev, struct input_keymap_entry *ke) { struct hid_device *hid = input_get_drvdata(dev); struct hid_usage *usage; unsigned int scancode, index; usage = hidinput_locate_usage(hid, ke, &index); if (usage) { ke->keycode = usage->type == EV_KEY ? usage->code : KEY_RESERVED; ke->index = index; scancode = usage->hid & (HID_USAGE_PAGE | HID_USAGE); ke->len = sizeof(scancode); memcpy(ke->scancode, &scancode, sizeof(scancode)); return 0; } return -EINVAL; } static int hidinput_setkeycode(struct input_dev *dev, const struct input_keymap_entry *ke, unsigned int *old_keycode) { struct hid_device *hid = input_get_drvdata(dev); struct hid_usage *usage; usage = hidinput_locate_usage(hid, ke, NULL); if (usage) { *old_keycode = usage->type == EV_KEY ? usage->code : KEY_RESERVED; usage->type = EV_KEY; usage->code = ke->keycode; clear_bit(*old_keycode, dev->keybit); set_bit(usage->code, dev->keybit); dbg_hid("Assigned keycode %d to HID usage code %x\n", usage->code, usage->hid); /* * Set the keybit for the old keycode if the old keycode is used * by another key */ if (hidinput_find_key(hid, match_keycode, *old_keycode, NULL)) set_bit(*old_keycode, dev->keybit); return 0; } return -EINVAL; } /** * hidinput_calc_abs_res - calculate an absolute axis resolution * @field: the HID report field to calculate resolution for * @code: axis code * * The formula is: * (logical_maximum - logical_minimum) * resolution = ---------------------------------------------------------- * (physical_maximum - physical_minimum) * 10 ^ unit_exponent * * as seen in the HID specification v1.11 6.2.2.7 Global Items. * * Only exponent 1 length units are processed. Centimeters and inches are * converted to millimeters. Degrees are converted to radians. */ __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code) { __s32 unit_exponent = field->unit_exponent; __s32 logical_extents = field->logical_maximum - field->logical_minimum; __s32 physical_extents = field->physical_maximum - field->physical_minimum; __s32 prev; /* Check if the extents are sane */ if (logical_extents <= 0 || physical_extents <= 0) return 0; /* * Verify and convert units. * See HID specification v1.11 6.2.2.7 Global Items for unit decoding */ switch (code) { case ABS_X: case ABS_Y: case ABS_Z: case ABS_MT_POSITION_X: case ABS_MT_POSITION_Y: case ABS_MT_TOOL_X: case ABS_MT_TOOL_Y: case ABS_MT_TOUCH_MAJOR: case ABS_MT_TOUCH_MINOR: if (field->unit == 0x11) { /* If centimeters */ /* Convert to millimeters */ unit_exponent += 1; } else if (field->unit == 0x13) { /* If inches */ /* Convert to millimeters */ prev = physical_extents; physical_extents *= 254; if (physical_extents < prev) return 0; unit_exponent -= 1; } else { return 0; } break; case ABS_RX: case ABS_RY: case ABS_RZ: case ABS_WHEEL: case ABS_TILT_X: case ABS_TILT_Y: if (field->unit == 0x14) { /* If degrees */ /* Convert to radians */ prev = logical_extents; logical_extents *= 573; if (logical_extents < prev) return 0; unit_exponent += 1; } else if (field->unit != 0x12) { /* If not radians */ return 0; } break; default: return 0; } /* Apply negative unit exponent */ for (; unit_exponent < 0; unit_exponent++) { prev = logical_extents; logical_extents *= 10; if (logical_extents < prev) return 0; } /* Apply positive unit exponent */ for (; unit_exponent > 0; unit_exponent--) { prev = physical_extents; physical_extents *= 10; if (physical_extents < prev) return 0; } /* Calculate resolution */ return DIV_ROUND_CLOSEST(logical_extents, physical_extents); } EXPORT_SYMBOL_GPL(hidinput_calc_abs_res); #ifdef CONFIG_HID_BATTERY_STRENGTH static enum power_supply_property hidinput_battery_props[] = { POWER_SUPPLY_PROP_PRESENT, POWER_SUPPLY_PROP_ONLINE, POWER_SUPPLY_PROP_CAPACITY, POWER_SUPPLY_PROP_MODEL_NAME, POWER_SUPPLY_PROP_STATUS, POWER_SUPPLY_PROP_SCOPE, }; #define HID_BATTERY_QUIRK_PERCENT (1 << 0) /* always reports percent */ #define HID_BATTERY_QUIRK_FEATURE (1 << 1) /* ask for feature report */ #define HID_BATTERY_QUIRK_IGNORE (1 << 2) /* completely ignore the battery */ #define HID_BATTERY_QUIRK_AVOID_QUERY (1 << 3) /* do not query the battery */ static const struct hid_device_id hid_battery_quirks[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO), HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI), HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI), HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO), HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI), HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGICTRACKPAD), HID_BATTERY_QUIRK_IGNORE }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_BM084), HID_BATTERY_QUIRK_IGNORE }, { HID_USB_DEVICE(USB_VENDOR_ID_SYMBOL, USB_DEVICE_ID_SYMBOL_SCANNER_3), HID_BATTERY_QUIRK_IGNORE }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_T100CHI_KEYBOARD), HID_BATTERY_QUIRK_IGNORE }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_ASUS_TP420IA_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_ASUS_GV301RA_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_ASUS_UX3402_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_ASUS_UX6404_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_L), HID_BATTERY_QUIRK_AVOID_QUERY }, { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_PRO_MW), HID_BATTERY_QUIRK_AVOID_QUERY }, { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_PRO_SW), HID_BATTERY_QUIRK_AVOID_QUERY }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_ENVY_X360_15), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_ENVY_X360_15T_DR100), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_ENVY_X360_EU0009NV), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_15), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_13_AW0020NG), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_SURFACE_GO2_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_LENOVO_YOGA_C630_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_13T_AW100), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_14T_EA100_V1), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_14T_EA100_V2), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_ENVY_X360_15_EU0556NG), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_CHROMEBOOK_TROGDOR_POMPOM), HID_BATTERY_QUIRK_AVOID_QUERY }, {} }; static unsigned find_battery_quirk(struct hid_device *hdev) { unsigned quirks = 0; const struct hid_device_id *match; match = hid_match_id(hdev, hid_battery_quirks); if (match != NULL) quirks = match->driver_data; return quirks; } static int hidinput_scale_battery_capacity(struct hid_device *dev, int value) { if (dev->battery_min < dev->battery_max && value >= dev->battery_min && value <= dev->battery_max) value = ((value - dev->battery_min) * 100) / (dev->battery_max - dev->battery_min); return value; } static int hidinput_query_battery_capacity(struct hid_device *dev) { u8 *buf; int ret; buf = kmalloc(4, GFP_KERNEL); if (!buf) return -ENOMEM; ret = hid_hw_raw_request(dev, dev->battery_report_id, buf, 4, dev->battery_report_type, HID_REQ_GET_REPORT); if (ret < 2) { kfree(buf); return -ENODATA; } ret = hidinput_scale_battery_capacity(dev, buf[1]); kfree(buf); return ret; } static int hidinput_get_battery_property(struct power_supply *psy, enum power_supply_property prop, union power_supply_propval *val) { struct hid_device *dev = power_supply_get_drvdata(psy); int value; int ret = 0; switch (prop) { case POWER_SUPPLY_PROP_PRESENT: case POWER_SUPPLY_PROP_ONLINE: val->intval = 1; break; case POWER_SUPPLY_PROP_CAPACITY: if (dev->battery_status != HID_BATTERY_REPORTED && !dev->battery_avoid_query) { value = hidinput_query_battery_capacity(dev); if (value < 0) return value; } else { value = dev->battery_capacity; } val->intval = value; break; case POWER_SUPPLY_PROP_MODEL_NAME: val->strval = dev->name; break; case POWER_SUPPLY_PROP_STATUS: if (dev->battery_status != HID_BATTERY_REPORTED && !dev->battery_avoid_query) { value = hidinput_query_battery_capacity(dev); if (value < 0) return value; dev->battery_capacity = value; dev->battery_status = HID_BATTERY_QUERIED; } if (dev->battery_status == HID_BATTERY_UNKNOWN) val->intval = POWER_SUPPLY_STATUS_UNKNOWN; else val->intval = dev->battery_charge_status; break; case POWER_SUPPLY_PROP_SCOPE: val->intval = POWER_SUPPLY_SCOPE_DEVICE; break; default: ret = -EINVAL; break; } return ret; } static int hidinput_setup_battery(struct hid_device *dev, unsigned report_type, struct hid_field *field, bool is_percentage) { struct power_supply_desc *psy_desc; struct power_supply_config psy_cfg = { .drv_data = dev, }; unsigned quirks; s32 min, max; int error; if (dev->battery) return 0; /* already initialized? */ quirks = find_battery_quirk(dev); hid_dbg(dev, "device %x:%x:%x %d quirks %d\n", dev->bus, dev->vendor, dev->product, dev->version, quirks); if (quirks & HID_BATTERY_QUIRK_IGNORE) return 0; psy_desc = kzalloc(sizeof(*psy_desc), GFP_KERNEL); if (!psy_desc) return -ENOMEM; psy_desc->name = kasprintf(GFP_KERNEL, "hid-%s-battery", strlen(dev->uniq) ? dev->uniq : dev_name(&dev->dev)); if (!psy_desc->name) { error = -ENOMEM; goto err_free_mem; } psy_desc->type = POWER_SUPPLY_TYPE_BATTERY; psy_desc->properties = hidinput_battery_props; psy_desc->num_properties = ARRAY_SIZE(hidinput_battery_props); psy_desc->use_for_apm = 0; psy_desc->get_property = hidinput_get_battery_property; min = field->logical_minimum; max = field->logical_maximum; if (is_percentage || (quirks & HID_BATTERY_QUIRK_PERCENT)) { min = 0; max = 100; } if (quirks & HID_BATTERY_QUIRK_FEATURE) report_type = HID_FEATURE_REPORT; dev->battery_min = min; dev->battery_max = max; dev->battery_report_type = report_type; dev->battery_report_id = field->report->id; dev->battery_charge_status = POWER_SUPPLY_STATUS_DISCHARGING; /* * Stylus is normally not connected to the device and thus we * can't query the device and get meaningful battery strength. * We have to wait for the device to report it on its own. */ dev->battery_avoid_query = report_type == HID_INPUT_REPORT && field->physical == HID_DG_STYLUS; if (quirks & HID_BATTERY_QUIRK_AVOID_QUERY) dev->battery_avoid_query = true; dev->battery = power_supply_register(&dev->dev, psy_desc, &psy_cfg); if (IS_ERR(dev->battery)) { error = PTR_ERR(dev->battery); hid_warn(dev, "can't register power supply: %d\n", error); goto err_free_name; } power_supply_powers(dev->battery, &dev->dev); return 0; err_free_name: kfree(psy_desc->name); err_free_mem: kfree(psy_desc); dev->battery = NULL; return error; } static void hidinput_cleanup_battery(struct hid_device *dev) { const struct power_supply_desc *psy_desc; if (!dev->battery) return; psy_desc = dev->battery->desc; power_supply_unregister(dev->battery); kfree(psy_desc->name); kfree(psy_desc); dev->battery = NULL; } static void hidinput_update_battery(struct hid_device *dev, int value) { int capacity; if (!dev->battery) return; if (value == 0 || value < dev->battery_min || value > dev->battery_max) return; capacity = hidinput_scale_battery_capacity(dev, value); if (dev->battery_status != HID_BATTERY_REPORTED || capacity != dev->battery_capacity || ktime_after(ktime_get_coarse(), dev->battery_ratelimit_time)) { dev->battery_capacity = capacity; dev->battery_status = HID_BATTERY_REPORTED; dev->battery_ratelimit_time = ktime_add_ms(ktime_get_coarse(), 30 * 1000); power_supply_changed(dev->battery); } } static bool hidinput_set_battery_charge_status(struct hid_device *dev, unsigned int usage, int value) { switch (usage) { case HID_BAT_CHARGING: dev->battery_charge_status = value ? POWER_SUPPLY_STATUS_CHARGING : POWER_SUPPLY_STATUS_DISCHARGING; return true; } return false; } #else /* !CONFIG_HID_BATTERY_STRENGTH */ static int hidinput_setup_battery(struct hid_device *dev, unsigned report_type, struct hid_field *field, bool is_percentage) { return 0; } static void hidinput_cleanup_battery(struct hid_device *dev) { } static void hidinput_update_battery(struct hid_device *dev, int value) { } static bool hidinput_set_battery_charge_status(struct hid_device *dev, unsigned int usage, int value) { return false; } #endif /* CONFIG_HID_BATTERY_STRENGTH */ static bool hidinput_field_in_collection(struct hid_device *device, struct hid_field *field, unsigned int type, unsigned int usage) { struct hid_collection *collection; collection = &device->collection[field->usage->collection_index]; return collection->type == type && collection->usage == usage; } static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_field *field, struct hid_usage *usage, unsigned int usage_index) { struct input_dev *input = hidinput->input; struct hid_device *device = input_get_drvdata(input); const struct usage_priority *usage_priority = NULL; int max = 0, code; unsigned int i = 0; unsigned long *bit = NULL; field->hidinput = hidinput; if (field->flags & HID_MAIN_ITEM_CONSTANT) goto ignore; /* Ignore if report count is out of bounds. */ if (field->report_count < 1) goto ignore; /* only LED usages are supported in output fields */ if (field->report_type == HID_OUTPUT_REPORT && (usage->hid & HID_USAGE_PAGE) != HID_UP_LED) { goto ignore; } /* assign a priority based on the static list declared here */ for (i = 0; i < ARRAY_SIZE(hidinput_usages_priorities); i++) { if (usage->hid == hidinput_usages_priorities[i].usage) { usage_priority = &hidinput_usages_priorities[i]; field->usages_priorities[usage_index] = (ARRAY_SIZE(hidinput_usages_priorities) - i) << 8; break; } } /* * For slotted devices, we need to also add the slot index * in the priority. */ if (usage_priority && usage_priority->global) field->usages_priorities[usage_index] |= usage_priority->slot_overwrite; else field->usages_priorities[usage_index] |= (0xff - field->slot_idx) << 16; if (device->driver->input_mapping) { int ret = device->driver->input_mapping(device, hidinput, field, usage, &bit, &max); if (ret > 0) goto mapped; if (ret < 0) goto ignore; } switch (usage->hid & HID_USAGE_PAGE) { case HID_UP_UNDEFINED: goto ignore; case HID_UP_KEYBOARD: set_bit(EV_REP, input->evbit); if ((usage->hid & HID_USAGE) < 256) { if (!hid_keyboard[usage->hid & HID_USAGE]) goto ignore; map_key_clear(hid_keyboard[usage->hid & HID_USAGE]); } else map_key(KEY_UNKNOWN); break; case HID_UP_BUTTON: code = ((usage->hid - 1) & HID_USAGE); switch (field->application) { case HID_GD_MOUSE: case HID_GD_POINTER: code += BTN_MOUSE; break; case HID_GD_JOYSTICK: if (code <= 0xf) code += BTN_JOYSTICK; else code += BTN_TRIGGER_HAPPY - 0x10; break; case HID_GD_GAMEPAD: if (code <= 0xf) code += BTN_GAMEPAD; else code += BTN_TRIGGER_HAPPY - 0x10; break; case HID_CP_CONSUMER_CONTROL: if (hidinput_field_in_collection(device, field, HID_COLLECTION_NAMED_ARRAY, HID_CP_PROGRAMMABLEBUTTONS)) { if (code <= 0x1d) code += KEY_MACRO1; else code += BTN_TRIGGER_HAPPY - 0x1e; break; } fallthrough; default: switch (field->physical) { case HID_GD_MOUSE: case HID_GD_POINTER: code += BTN_MOUSE; break; case HID_GD_JOYSTICK: code += BTN_JOYSTICK; break; case HID_GD_GAMEPAD: code += BTN_GAMEPAD; break; default: code += BTN_MISC; } } map_key(code); break; case HID_UP_SIMULATION: switch (usage->hid & 0xffff) { case 0xba: map_abs(ABS_RUDDER); break; case 0xbb: map_abs(ABS_THROTTLE); break; case 0xc4: map_abs(ABS_GAS); break; case 0xc5: map_abs(ABS_BRAKE); break; case 0xc8: map_abs(ABS_WHEEL); break; default: goto ignore; } break; case HID_UP_GENDESK: if ((usage->hid & 0xf0) == 0x80) { /* SystemControl */ switch (usage->hid & 0xf) { case 0x1: map_key_clear(KEY_POWER); break; case 0x2: map_key_clear(KEY_SLEEP); break; case 0x3: map_key_clear(KEY_WAKEUP); break; case 0x4: map_key_clear(KEY_CONTEXT_MENU); break; case 0x5: map_key_clear(KEY_MENU); break; case 0x6: map_key_clear(KEY_PROG1); break; case 0x7: map_key_clear(KEY_HELP); break; case 0x8: map_key_clear(KEY_EXIT); break; case 0x9: map_key_clear(KEY_SELECT); break; case 0xa: map_key_clear(KEY_RIGHT); break; case 0xb: map_key_clear(KEY_LEFT); break; case 0xc: map_key_clear(KEY_UP); break; case 0xd: map_key_clear(KEY_DOWN); break; case 0xe: map_key_clear(KEY_POWER2); break; case 0xf: map_key_clear(KEY_RESTART); break; default: goto unknown; } break; } if ((usage->hid & 0xf0) == 0x90) { /* SystemControl*/ switch (usage->hid & 0xf) { case 0xb: map_key_clear(KEY_DO_NOT_DISTURB); break; default: goto ignore; } break; } if ((usage->hid & 0xf0) == 0xa0) { /* SystemControl */ switch (usage->hid & 0xf) { case 0x9: map_key_clear(KEY_MICMUTE); break; case 0xa: map_key_clear(KEY_ACCESSIBILITY); break; default: goto ignore; } break; } if ((usage->hid & 0xf0) == 0xb0) { /* SC - Display */ switch (usage->hid & 0xf) { case 0x05: map_key_clear(KEY_SWITCHVIDEOMODE); break; default: goto ignore; } break; } /* * Some lazy vendors declare 255 usages for System Control, * leading to the creation of ABS_X|Y axis and too many others. * It wouldn't be a problem if joydev doesn't consider the * device as a joystick then. */ if (field->application == HID_GD_SYSTEM_CONTROL) goto ignore; if ((usage->hid & 0xf0) == 0x90) { /* D-pad */ switch (usage->hid) { case HID_GD_UP: usage->hat_dir = 1; break; case HID_GD_DOWN: usage->hat_dir = 5; break; case HID_GD_RIGHT: usage->hat_dir = 3; break; case HID_GD_LEFT: usage->hat_dir = 7; break; default: goto unknown; } if (field->dpad) { map_abs(field->dpad); goto ignore; } map_abs(ABS_HAT0X); break; } switch (usage->hid) { /* These usage IDs map directly to the usage codes. */ case HID_GD_X: case HID_GD_Y: case HID_GD_Z: case HID_GD_RX: case HID_GD_RY: case HID_GD_RZ: if (field->flags & HID_MAIN_ITEM_RELATIVE) map_rel(usage->hid & 0xf); else map_abs_clear(usage->hid & 0xf); break; case HID_GD_WHEEL: if (field->flags & HID_MAIN_ITEM_RELATIVE) { set_bit(REL_WHEEL, input->relbit); map_rel(REL_WHEEL_HI_RES); } else { map_abs(usage->hid & 0xf); } break; case HID_GD_SLIDER: case HID_GD_DIAL: if (field->flags & HID_MAIN_ITEM_RELATIVE) map_rel(usage->hid & 0xf); else map_abs(usage->hid & 0xf); break; case HID_GD_HATSWITCH: usage->hat_min = field->logical_minimum; usage->hat_max = field->logical_maximum; map_abs(ABS_HAT0X); break; case HID_GD_START: map_key_clear(BTN_START); break; case HID_GD_SELECT: map_key_clear(BTN_SELECT); break; case HID_GD_RFKILL_BTN: /* MS wireless radio ctl extension, also check CA */ if (field->application == HID_GD_WIRELESS_RADIO_CTLS) { map_key_clear(KEY_RFKILL); /* We need to simulate the btn release */ field->flags |= HID_MAIN_ITEM_RELATIVE; break; } goto unknown; default: goto unknown; } break; case HID_UP_LED: switch (usage->hid & 0xffff) { /* HID-Value: */ case 0x01: map_led (LED_NUML); break; /* "Num Lock" */ case 0x02: map_led (LED_CAPSL); break; /* "Caps Lock" */ case 0x03: map_led (LED_SCROLLL); break; /* "Scroll Lock" */ case 0x04: map_led (LED_COMPOSE); break; /* "Compose" */ case 0x05: map_led (LED_KANA); break; /* "Kana" */ case 0x27: map_led (LED_SLEEP); break; /* "Stand-By" */ case 0x4c: map_led (LED_SUSPEND); break; /* "System Suspend" */ case 0x09: map_led (LED_MUTE); break; /* "Mute" */ case 0x4b: map_led (LED_MISC); break; /* "Generic Indicator" */ case 0x19: map_led (LED_MAIL); break; /* "Message Waiting" */ case 0x4d: map_led (LED_CHARGING); break; /* "External Power Connected" */ default: goto ignore; } break; case HID_UP_DIGITIZER: if ((field->application & 0xff) == 0x01) /* Digitizer */ __set_bit(INPUT_PROP_POINTER, input->propbit); else if ((field->application & 0xff) == 0x02) /* Pen */ __set_bit(INPUT_PROP_DIRECT, input->propbit); switch (usage->hid & 0xff) { case 0x00: /* Undefined */ goto ignore; case 0x30: /* TipPressure */ if (!test_bit(BTN_TOUCH, input->keybit)) { device->quirks |= HID_QUIRK_NOTOUCH; set_bit(EV_KEY, input->evbit); set_bit(BTN_TOUCH, input->keybit); } map_abs_clear(ABS_PRESSURE); break; case 0x32: /* InRange */ switch (field->physical) { case HID_DG_PUCK: map_key(BTN_TOOL_MOUSE); break; case HID_DG_FINGER: map_key(BTN_TOOL_FINGER); break; default: /* * If the physical is not given, * rely on the application. */ if (!field->physical) { switch (field->application) { case HID_DG_TOUCHSCREEN: case HID_DG_TOUCHPAD: map_key_clear(BTN_TOOL_FINGER); break; default: map_key_clear(BTN_TOOL_PEN); } } else { map_key(BTN_TOOL_PEN); } break; } break; case 0x3b: /* Battery Strength */ hidinput_setup_battery(device, HID_INPUT_REPORT, field, false); usage->type = EV_PWR; return; case 0x3c: /* Invert */ device->quirks &= ~HID_QUIRK_NOINVERT; map_key_clear(BTN_TOOL_RUBBER); break; case 0x3d: /* X Tilt */ map_abs_clear(ABS_TILT_X); break; case 0x3e: /* Y Tilt */ map_abs_clear(ABS_TILT_Y); break; case 0x33: /* Touch */ case 0x42: /* TipSwitch */ case 0x43: /* TipSwitch2 */ device->quirks &= ~HID_QUIRK_NOTOUCH; map_key_clear(BTN_TOUCH); break; case 0x44: /* BarrelSwitch */ map_key_clear(BTN_STYLUS); break; case 0x45: /* ERASER */ /* * This event is reported when eraser tip touches the surface. * Actual eraser (BTN_TOOL_RUBBER) is set and released either * by Invert if tool reports proximity or by Eraser directly. */ if (!test_bit(BTN_TOOL_RUBBER, input->keybit)) { device->quirks |= HID_QUIRK_NOINVERT; set_bit(BTN_TOOL_RUBBER, input->keybit); } map_key_clear(BTN_TOUCH); break; case 0x46: /* TabletPick */ case 0x5a: /* SecondaryBarrelSwitch */ map_key_clear(BTN_STYLUS2); break; case 0x5b: /* TransducerSerialNumber */ case 0x6e: /* TransducerSerialNumber2 */ map_msc(MSC_SERIAL); break; default: goto unknown; } break; case HID_UP_TELEPHONY: switch (usage->hid & HID_USAGE) { case 0x2f: map_key_clear(KEY_MICMUTE); break; case 0xb0: map_key_clear(KEY_NUMERIC_0); break; case 0xb1: map_key_clear(KEY_NUMERIC_1); break; case 0xb2: map_key_clear(KEY_NUMERIC_2); break; case 0xb3: map_key_clear(KEY_NUMERIC_3); break; case 0xb4: map_key_clear(KEY_NUMERIC_4); break; case 0xb5: map_key_clear(KEY_NUMERIC_5); break; case 0xb6: map_key_clear(KEY_NUMERIC_6); break; case 0xb7: map_key_clear(KEY_NUMERIC_7); break; case 0xb8: map_key_clear(KEY_NUMERIC_8); break; case 0xb9: map_key_clear(KEY_NUMERIC_9); break; case 0xba: map_key_clear(KEY_NUMERIC_STAR); break; case 0xbb: map_key_clear(KEY_NUMERIC_POUND); break; case 0xbc: map_key_clear(KEY_NUMERIC_A); break; case 0xbd: map_key_clear(KEY_NUMERIC_B); break; case 0xbe: map_key_clear(KEY_NUMERIC_C); break; case 0xbf: map_key_clear(KEY_NUMERIC_D); break; default: goto ignore; } break; case HID_UP_CONSUMER: /* USB HUT v1.12, pages 75-84 */ switch (usage->hid & HID_USAGE) { case 0x000: goto ignore; case 0x030: map_key_clear(KEY_POWER); break; case 0x031: map_key_clear(KEY_RESTART); break; case 0x032: map_key_clear(KEY_SLEEP); break; case 0x034: map_key_clear(KEY_SLEEP); break; case 0x035: map_key_clear(KEY_KBDILLUMTOGGLE); break; case 0x036: map_key_clear(BTN_MISC); break; case 0x040: map_key_clear(KEY_MENU); break; /* Menu */ case 0x041: map_key_clear(KEY_SELECT); break; /* Menu Pick */ case 0x042: map_key_clear(KEY_UP); break; /* Menu Up */ case 0x043: map_key_clear(KEY_DOWN); break; /* Menu Down */ case 0x044: map_key_clear(KEY_LEFT); break; /* Menu Left */ case 0x045: map_key_clear(KEY_RIGHT); break; /* Menu Right */ case 0x046: map_key_clear(KEY_ESC); break; /* Menu Escape */ case 0x047: map_key_clear(KEY_KPPLUS); break; /* Menu Value Increase */ case 0x048: map_key_clear(KEY_KPMINUS); break; /* Menu Value Decrease */ case 0x060: map_key_clear(KEY_INFO); break; /* Data On Screen */ case 0x061: map_key_clear(KEY_SUBTITLE); break; /* Closed Caption */ case 0x063: map_key_clear(KEY_VCR); break; /* VCR/TV */ case 0x065: map_key_clear(KEY_CAMERA); break; /* Snapshot */ case 0x069: map_key_clear(KEY_RED); break; case 0x06a: map_key_clear(KEY_GREEN); break; case 0x06b: map_key_clear(KEY_BLUE); break; case 0x06c: map_key_clear(KEY_YELLOW); break; case 0x06d: map_key_clear(KEY_ASPECT_RATIO); break; case 0x06f: map_key_clear(KEY_BRIGHTNESSUP); break; case 0x070: map_key_clear(KEY_BRIGHTNESSDOWN); break; case 0x072: map_key_clear(KEY_BRIGHTNESS_TOGGLE); break; case 0x073: map_key_clear(KEY_BRIGHTNESS_MIN); break; case 0x074: map_key_clear(KEY_BRIGHTNESS_MAX); break; case 0x075: map_key_clear(KEY_BRIGHTNESS_AUTO); break; case 0x076: map_key_clear(KEY_CAMERA_ACCESS_ENABLE); break; case 0x077: map_key_clear(KEY_CAMERA_ACCESS_DISABLE); break; case 0x078: map_key_clear(KEY_CAMERA_ACCESS_TOGGLE); break; case 0x079: map_key_clear(KEY_KBDILLUMUP); break; case 0x07a: map_key_clear(KEY_KBDILLUMDOWN); break; case 0x07c: map_key_clear(KEY_KBDILLUMTOGGLE); break; case 0x082: map_key_clear(KEY_VIDEO_NEXT); break; case 0x083: map_key_clear(KEY_LAST); break; case 0x084: map_key_clear(KEY_ENTER); break; case 0x088: map_key_clear(KEY_PC); break; case 0x089: map_key_clear(KEY_TV); break; case 0x08a: map_key_clear(KEY_WWW); break; case 0x08b: map_key_clear(KEY_DVD); break; case 0x08c: map_key_clear(KEY_PHONE); break; case 0x08d: map_key_clear(KEY_PROGRAM); break; case 0x08e: map_key_clear(KEY_VIDEOPHONE); break; case 0x08f: map_key_clear(KEY_GAMES); break; case 0x090: map_key_clear(KEY_MEMO); break; case 0x091: map_key_clear(KEY_CD); break; case 0x092: map_key_clear(KEY_VCR); break; case 0x093: map_key_clear(KEY_TUNER); break; case 0x094: map_key_clear(KEY_EXIT); break; case 0x095: map_key_clear(KEY_HELP); break; case 0x096: map_key_clear(KEY_TAPE); break; case 0x097: map_key_clear(KEY_TV2); break; case 0x098: map_key_clear(KEY_SAT); break; case 0x09a: map_key_clear(KEY_PVR); break; case 0x09c: map_key_clear(KEY_CHANNELUP); break; case 0x09d: map_key_clear(KEY_CHANNELDOWN); break; case 0x0a0: map_key_clear(KEY_VCR2); break; case 0x0b0: map_key_clear(KEY_PLAY); break; case 0x0b1: map_key_clear(KEY_PAUSE); break; case 0x0b2: map_key_clear(KEY_RECORD); break; case 0x0b3: map_key_clear(KEY_FASTFORWARD); break; case 0x0b4: map_key_clear(KEY_REWIND); break; case 0x0b5: map_key_clear(KEY_NEXTSONG); break; case 0x0b6: map_key_clear(KEY_PREVIOUSSONG); break; case 0x0b7: map_key_clear(KEY_STOPCD); break; case 0x0b8: map_key_clear(KEY_EJECTCD); break; case 0x0bc: map_key_clear(KEY_MEDIA_REPEAT); break; case 0x0b9: map_key_clear(KEY_SHUFFLE); break; case 0x0bf: map_key_clear(KEY_SLOW); break; case 0x0cd: map_key_clear(KEY_PLAYPAUSE); break; case 0x0cf: map_key_clear(KEY_VOICECOMMAND); break; case 0x0d8: map_key_clear(KEY_DICTATE); break; case 0x0d9: map_key_clear(KEY_EMOJI_PICKER); break; case 0x0e0: map_abs_clear(ABS_VOLUME); break; case 0x0e2: map_key_clear(KEY_MUTE); break; case 0x0e5: map_key_clear(KEY_BASSBOOST); break; case 0x0e9: map_key_clear(KEY_VOLUMEUP); break; case 0x0ea: map_key_clear(KEY_VOLUMEDOWN); break; case 0x0f5: map_key_clear(KEY_SLOW); break; case 0x181: map_key_clear(KEY_BUTTONCONFIG); break; case 0x182: map_key_clear(KEY_BOOKMARKS); break; case 0x183: map_key_clear(KEY_CONFIG); break; case 0x184: map_key_clear(KEY_WORDPROCESSOR); break; case 0x185: map_key_clear(KEY_EDITOR); break; case 0x186: map_key_clear(KEY_SPREADSHEET); break; case 0x187: map_key_clear(KEY_GRAPHICSEDITOR); break; case 0x188: map_key_clear(KEY_PRESENTATION); break; case 0x189: map_key_clear(KEY_DATABASE); break; case 0x18a: map_key_clear(KEY_MAIL); break; case 0x18b: map_key_clear(KEY_NEWS); break; case 0x18c: map_key_clear(KEY_VOICEMAIL); break; case 0x18d: map_key_clear(KEY_ADDRESSBOOK); break; case 0x18e: map_key_clear(KEY_CALENDAR); break; case 0x18f: map_key_clear(KEY_TASKMANAGER); break; case 0x190: map_key_clear(KEY_JOURNAL); break; case 0x191: map_key_clear(KEY_FINANCE); break; case 0x192: map_key_clear(KEY_CALC); break; case 0x193: map_key_clear(KEY_PLAYER); break; case 0x194: map_key_clear(KEY_FILE); break; case 0x196: map_key_clear(KEY_WWW); break; case 0x199: map_key_clear(KEY_CHAT); break; case 0x19c: map_key_clear(KEY_LOGOFF); break; case 0x19e: map_key_clear(KEY_COFFEE); break; case 0x19f: map_key_clear(KEY_CONTROLPANEL); break; case 0x1a2: map_key_clear(KEY_APPSELECT); break; case 0x1a3: map_key_clear(KEY_NEXT); break; case 0x1a4: map_key_clear(KEY_PREVIOUS); break; case 0x1a6: map_key_clear(KEY_HELP); break; case 0x1a7: map_key_clear(KEY_DOCUMENTS); break; case 0x1ab: map_key_clear(KEY_SPELLCHECK); break; case 0x1ae: map_key_clear(KEY_KEYBOARD); break; case 0x1b1: map_key_clear(KEY_SCREENSAVER); break; case 0x1b4: map_key_clear(KEY_FILE); break; case 0x1b6: map_key_clear(KEY_IMAGES); break; case 0x1b7: map_key_clear(KEY_AUDIO); break; case 0x1b8: map_key_clear(KEY_VIDEO); break; case 0x1bc: map_key_clear(KEY_MESSENGER); break; case 0x1bd: map_key_clear(KEY_INFO); break; case 0x1cb: map_key_clear(KEY_ASSISTANT); break; case 0x201: map_key_clear(KEY_NEW); break; case 0x202: map_key_clear(KEY_OPEN); break; case 0x203: map_key_clear(KEY_CLOSE); break; case 0x204: map_key_clear(KEY_EXIT); break; case 0x207: map_key_clear(KEY_SAVE); break; case 0x208: map_key_clear(KEY_PRINT); break; case 0x209: map_key_clear(KEY_PROPS); break; case 0x21a: map_key_clear(KEY_UNDO); break; case 0x21b: map_key_clear(KEY_COPY); break; case 0x21c: map_key_clear(KEY_CUT); break; case 0x21d: map_key_clear(KEY_PASTE); break; case 0x21f: map_key_clear(KEY_FIND); break; case 0x221: map_key_clear(KEY_SEARCH); break; case 0x222: map_key_clear(KEY_GOTO); break; case 0x223: map_key_clear(KEY_HOMEPAGE); break; case 0x224: map_key_clear(KEY_BACK); break; case 0x225: map_key_clear(KEY_FORWARD); break; case 0x226: map_key_clear(KEY_STOP); break; case 0x227: map_key_clear(KEY_REFRESH); break; case 0x22a: map_key_clear(KEY_BOOKMARKS); break; case 0x22d: map_key_clear(KEY_ZOOMIN); break; case 0x22e: map_key_clear(KEY_ZOOMOUT); break; case 0x22f: map_key_clear(KEY_ZOOMRESET); break; case 0x232: map_key_clear(KEY_FULL_SCREEN); break; case 0x233: map_key_clear(KEY_SCROLLUP); break; case 0x234: map_key_clear(KEY_SCROLLDOWN); break; case 0x238: /* AC Pan */ set_bit(REL_HWHEEL, input->relbit); map_rel(REL_HWHEEL_HI_RES); break; case 0x23d: map_key_clear(KEY_EDIT); break; case 0x25f: map_key_clear(KEY_CANCEL); break; case 0x269: map_key_clear(KEY_INSERT); break; case 0x26a: map_key_clear(KEY_DELETE); break; case 0x279: map_key_clear(KEY_REDO); break; case 0x289: map_key_clear(KEY_REPLY); break; case 0x28b: map_key_clear(KEY_FORWARDMAIL); break; case 0x28c: map_key_clear(KEY_SEND); break; case 0x29d: map_key_clear(KEY_KBD_LAYOUT_NEXT); break; case 0x2a2: map_key_clear(KEY_ALL_APPLICATIONS); break; case 0x2c7: map_key_clear(KEY_KBDINPUTASSIST_PREV); break; case 0x2c8: map_key_clear(KEY_KBDINPUTASSIST_NEXT); break; case 0x2c9: map_key_clear(KEY_KBDINPUTASSIST_PREVGROUP); break; case 0x2ca: map_key_clear(KEY_KBDINPUTASSIST_NEXTGROUP); break; case 0x2cb: map_key_clear(KEY_KBDINPUTASSIST_ACCEPT); break; case 0x2cc: map_key_clear(KEY_KBDINPUTASSIST_CANCEL); break; case 0x29f: map_key_clear(KEY_SCALE); break; default: map_key_clear(KEY_UNKNOWN); } break; case HID_UP_GENDEVCTRLS: switch (usage->hid) { case HID_DC_BATTERYSTRENGTH: hidinput_setup_battery(device, HID_INPUT_REPORT, field, false); usage->type = EV_PWR; return; } goto unknown; case HID_UP_BATTERY: switch (usage->hid) { case HID_BAT_ABSOLUTESTATEOFCHARGE: hidinput_setup_battery(device, HID_INPUT_REPORT, field, true); usage->type = EV_PWR; return; case HID_BAT_CHARGING: usage->type = EV_PWR; return; } goto unknown; case HID_UP_CAMERA: switch (usage->hid & HID_USAGE) { case 0x020: map_key_clear(KEY_CAMERA_FOCUS); break; case 0x021: map_key_clear(KEY_CAMERA); break; default: goto ignore; } break; case HID_UP_HPVENDOR: /* Reported on a Dutch layout HP5308 */ set_bit(EV_REP, input->evbit); switch (usage->hid & HID_USAGE) { case 0x021: map_key_clear(KEY_PRINT); break; case 0x070: map_key_clear(KEY_HP); break; case 0x071: map_key_clear(KEY_CAMERA); break; case 0x072: map_key_clear(KEY_SOUND); break; case 0x073: map_key_clear(KEY_QUESTION); break; case 0x080: map_key_clear(KEY_EMAIL); break; case 0x081: map_key_clear(KEY_CHAT); break; case 0x082: map_key_clear(KEY_SEARCH); break; case 0x083: map_key_clear(KEY_CONNECT); break; case 0x084: map_key_clear(KEY_FINANCE); break; case 0x085: map_key_clear(KEY_SPORT); break; case 0x086: map_key_clear(KEY_SHOP); break; default: goto ignore; } break; case HID_UP_HPVENDOR2: set_bit(EV_REP, input->evbit); switch (usage->hid & HID_USAGE) { case 0x001: map_key_clear(KEY_MICMUTE); break; case 0x003: map_key_clear(KEY_BRIGHTNESSDOWN); break; case 0x004: map_key_clear(KEY_BRIGHTNESSUP); break; default: goto ignore; } break; case HID_UP_MSVENDOR: goto ignore; case HID_UP_CUSTOM: /* Reported on Logitech and Apple USB keyboards */ set_bit(EV_REP, input->evbit); goto ignore; case HID_UP_LOGIVENDOR: /* intentional fallback */ case HID_UP_LOGIVENDOR2: /* intentional fallback */ case HID_UP_LOGIVENDOR3: goto ignore; case HID_UP_PID: switch (usage->hid & HID_USAGE) { case 0xa4: map_key_clear(BTN_DEAD); break; default: goto ignore; } break; default: unknown: if (field->report_size == 1) { if (field->report->type == HID_OUTPUT_REPORT) { map_led(LED_MISC); break; } map_key(BTN_MISC); break; } if (field->flags & HID_MAIN_ITEM_RELATIVE) { map_rel(REL_MISC); break; } map_abs(ABS_MISC); break; } mapped: /* Mapping failed, bail out */ if (!bit) return; if (device->driver->input_mapped && device->driver->input_mapped(device, hidinput, field, usage, &bit, &max) < 0) { /* * The driver indicated that no further generic handling * of the usage is desired. */ return; } set_bit(usage->type, input->evbit); /* * This part is *really* controversial: * - HID aims at being generic so we should do our best to export * all incoming events * - HID describes what events are, so there is no reason for ABS_X * to be mapped to ABS_Y * - HID is using *_MISC+N as a default value, but nothing prevents * *_MISC+N to overwrite a legitimate even, which confuses userspace * (for instance ABS_MISC + 7 is ABS_MT_SLOT, which has a different * processing) * * If devices still want to use this (at their own risk), they will * have to use the quirk HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE, but * the default should be a reliable mapping. */ while (usage->code <= max && test_and_set_bit(usage->code, bit)) { if (device->quirks & HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE) { usage->code = find_next_zero_bit(bit, max + 1, usage->code); } else { device->status |= HID_STAT_DUP_DETECTED; goto ignore; } } if (usage->code > max) goto ignore; if (usage->type == EV_ABS) { int a = field->logical_minimum; int b = field->logical_maximum; if ((device->quirks & HID_QUIRK_BADPAD) && (usage->code == ABS_X || usage->code == ABS_Y)) { a = field->logical_minimum = 0; b = field->logical_maximum = 255; } if (field->application == HID_GD_GAMEPAD || field->application == HID_GD_JOYSTICK) input_set_abs_params(input, usage->code, a, b, (b - a) >> 8, (b - a) >> 4); else input_set_abs_params(input, usage->code, a, b, 0, 0); input_abs_set_res(input, usage->code, hidinput_calc_abs_res(field, usage->code)); /* use a larger default input buffer for MT devices */ if (usage->code == ABS_MT_POSITION_X && input->hint_events_per_packet == 0) input_set_events_per_packet(input, 60); } if (usage->type == EV_ABS && (usage->hat_min < usage->hat_max || usage->hat_dir)) { int i; for (i = usage->code; i < usage->code + 2 && i <= max; i++) { input_set_abs_params(input, i, -1, 1, 0, 0); set_bit(i, input->absbit); } if (usage->hat_dir && !field->dpad) field->dpad = usage->code; } /* for those devices which produce Consumer volume usage as relative, * we emulate pressing volumeup/volumedown appropriate number of times * in hidinput_hid_event() */ if ((usage->type == EV_ABS) && (field->flags & HID_MAIN_ITEM_RELATIVE) && (usage->code == ABS_VOLUME)) { set_bit(KEY_VOLUMEUP, input->keybit); set_bit(KEY_VOLUMEDOWN, input->keybit); } if (usage->type == EV_KEY) { set_bit(EV_MSC, input->evbit); set_bit(MSC_SCAN, input->mscbit); } return; ignore: usage->type = 0; usage->code = 0; } static void hidinput_handle_scroll(struct hid_usage *usage, struct input_dev *input, __s32 value) { int code; int hi_res, lo_res; if (value == 0) return; if (usage->code == REL_WHEEL_HI_RES) code = REL_WHEEL; else code = REL_HWHEEL; /* * Windows reports one wheel click as value 120. Where a high-res * scroll wheel is present, a fraction of 120 is reported instead. * Our REL_WHEEL_HI_RES axis does the same because all HW must * adhere to the 120 expectation. */ hi_res = value * 120/usage->resolution_multiplier; usage->wheel_accumulated += hi_res; lo_res = usage->wheel_accumulated/120; if (lo_res) usage->wheel_accumulated -= lo_res * 120; input_event(input, EV_REL, code, lo_res); input_event(input, EV_REL, usage->code, hi_res); } static void hid_report_release_tool(struct hid_report *report, struct input_dev *input, unsigned int tool) { /* if the given tool is not currently reported, ignore */ if (!test_bit(tool, input->key)) return; /* * if the given tool was previously set, release it, * release any TOUCH and send an EV_SYN */ input_event(input, EV_KEY, BTN_TOUCH, 0); input_event(input, EV_KEY, tool, 0); input_event(input, EV_SYN, SYN_REPORT, 0); report->tool = 0; } static void hid_report_set_tool(struct hid_report *report, struct input_dev *input, unsigned int new_tool) { if (report->tool != new_tool) hid_report_release_tool(report, input, report->tool); input_event(input, EV_KEY, new_tool, 1); report->tool = new_tool; } void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct hid_usage *usage, __s32 value) { struct input_dev *input; struct hid_report *report = field->report; unsigned *quirks = &hid->quirks; if (!usage->type) return; if (usage->type == EV_PWR) { bool handled = hidinput_set_battery_charge_status(hid, usage->hid, value); if (!handled) hidinput_update_battery(hid, value); return; } if (!field->hidinput) return; input = field->hidinput->input; if (usage->hat_min < usage->hat_max || usage->hat_dir) { int hat_dir = usage->hat_dir; if (!hat_dir) hat_dir = (value - usage->hat_min) * 8 / (usage->hat_max - usage->hat_min + 1) + 1; if (hat_dir < 0 || hat_dir > 8) hat_dir = 0; input_event(input, usage->type, usage->code , hid_hat_to_axis[hat_dir].x); input_event(input, usage->type, usage->code + 1, hid_hat_to_axis[hat_dir].y); return; } /* * Ignore out-of-range values as per HID specification, * section 5.10 and 6.2.25, when NULL state bit is present. * When it's not, clamp the value to match Microsoft's input * driver as mentioned in "Required HID usages for digitizers": * https://msdn.microsoft.com/en-us/library/windows/hardware/dn672278(v=vs.85).asp * * The logical_minimum < logical_maximum check is done so that we * don't unintentionally discard values sent by devices which * don't specify logical min and max. */ if ((field->flags & HID_MAIN_ITEM_VARIABLE) && field->logical_minimum < field->logical_maximum) { if (field->flags & HID_MAIN_ITEM_NULL_STATE && (value < field->logical_minimum || value > field->logical_maximum)) { dbg_hid("Ignoring out-of-range value %x\n", value); return; } value = clamp(value, field->logical_minimum, field->logical_maximum); } switch (usage->hid) { case HID_DG_ERASER: report->tool_active |= !!value; /* * if eraser is set, we must enforce BTN_TOOL_RUBBER * to accommodate for devices not following the spec. */ if (value) hid_report_set_tool(report, input, BTN_TOOL_RUBBER); else if (report->tool != BTN_TOOL_RUBBER) /* value is off, tool is not rubber, ignore */ return; else if (*quirks & HID_QUIRK_NOINVERT && !test_bit(BTN_TOUCH, input->key)) { /* * There is no invert to release the tool, let hid_input * send BTN_TOUCH with scancode and release the tool after. */ hid_report_release_tool(report, input, BTN_TOOL_RUBBER); return; } /* let hid-input set BTN_TOUCH */ break; case HID_DG_INVERT: report->tool_active |= !!value; /* * If invert is set, we store BTN_TOOL_RUBBER. */ if (value) hid_report_set_tool(report, input, BTN_TOOL_RUBBER); else if (!report->tool_active) /* tool_active not set means Invert and Eraser are not set */ hid_report_release_tool(report, input, BTN_TOOL_RUBBER); /* no further processing */ return; case HID_DG_INRANGE: report->tool_active |= !!value; if (report->tool_active) { /* * if tool is not set but is marked as active, * assume ours */ if (!report->tool) report->tool = usage->code; /* drivers may have changed the value behind our back, resend it */ hid_report_set_tool(report, input, report->tool); } else { hid_report_release_tool(report, input, usage->code); } /* reset tool_active for the next event */ report->tool_active = false; /* no further processing */ return; case HID_DG_TIPSWITCH: report->tool_active |= !!value; /* if tool is set to RUBBER we should ignore the current value */ if (report->tool == BTN_TOOL_RUBBER) return; break; case HID_DG_TIPPRESSURE: if (*quirks & HID_QUIRK_NOTOUCH) { int a = field->logical_minimum; int b = field->logical_maximum; if (value > a + ((b - a) >> 3)) { input_event(input, EV_KEY, BTN_TOUCH, 1); report->tool_active = true; } } break; case HID_UP_PID | 0x83UL: /* Simultaneous Effects Max */ dbg_hid("Maximum Effects - %d\n",value); return; case HID_UP_PID | 0x7fUL: dbg_hid("PID Pool Report\n"); return; } switch (usage->type) { case EV_KEY: if (usage->code == 0) /* Key 0 is "unassigned", not KEY_UNKNOWN */ return; break; case EV_REL: if (usage->code == REL_WHEEL_HI_RES || usage->code == REL_HWHEEL_HI_RES) { hidinput_handle_scroll(usage, input, value); return; } break; case EV_ABS: if ((field->flags & HID_MAIN_ITEM_RELATIVE) && usage->code == ABS_VOLUME) { int count = abs(value); int direction = value > 0 ? KEY_VOLUMEUP : KEY_VOLUMEDOWN; int i; for (i = 0; i < count; i++) { input_event(input, EV_KEY, direction, 1); input_sync(input); input_event(input, EV_KEY, direction, 0); input_sync(input); } return; } else if (((*quirks & HID_QUIRK_X_INVERT) && usage->code == ABS_X) || ((*quirks & HID_QUIRK_Y_INVERT) && usage->code == ABS_Y)) value = field->logical_maximum - value; break; } /* * Ignore reports for absolute data if the data didn't change. This is * not only an optimization but also fixes 'dead' key reports. Some * RollOver implementations for localized keys (like BACKSLASH/PIPE; HID * 0x31 and 0x32) report multiple keys, even though a localized keyboard * can only have one of them physically available. The 'dead' keys * report constant 0. As all map to the same keycode, they'd confuse * the input layer. If we filter the 'dead' keys on the HID level, we * skip the keycode translation and only forward real events. */ if (!(field->flags & (HID_MAIN_ITEM_RELATIVE | HID_MAIN_ITEM_BUFFERED_BYTE)) && (field->flags & HID_MAIN_ITEM_VARIABLE) && usage->usage_index < field->maxusage && value == field->value[usage->usage_index]) return; /* report the usage code as scancode if the key status has changed */ if (usage->type == EV_KEY && (!test_bit(usage->code, input->key)) == value) input_event(input, EV_MSC, MSC_SCAN, usage->hid); input_event(input, usage->type, usage->code, value); if ((field->flags & HID_MAIN_ITEM_RELATIVE) && usage->type == EV_KEY && value) { input_sync(input); input_event(input, usage->type, usage->code, 0); } } void hidinput_report_event(struct hid_device *hid, struct hid_report *report) { struct hid_input *hidinput; if (hid->quirks & HID_QUIRK_NO_INPUT_SYNC) return; list_for_each_entry(hidinput, &hid->inputs, list) input_sync(hidinput->input); } EXPORT_SYMBOL_GPL(hidinput_report_event); static int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int code, struct hid_field **field) { struct hid_report *report; int i, j; list_for_each_entry(report, &hid->report_enum[HID_OUTPUT_REPORT].report_list, list) { for (i = 0; i < report->maxfield; i++) { *field = report->field[i]; for (j = 0; j < (*field)->maxusage; j++) if ((*field)->usage[j].type == type && (*field)->usage[j].code == code) return j; } } return -1; } struct hid_field *hidinput_get_led_field(struct hid_device *hid) { struct hid_report *report; struct hid_field *field; int i, j; list_for_each_entry(report, &hid->report_enum[HID_OUTPUT_REPORT].report_list, list) { for (i = 0; i < report->maxfield; i++) { field = report->field[i]; for (j = 0; j < field->maxusage; j++) if (field->usage[j].type == EV_LED) return field; } } return NULL; } EXPORT_SYMBOL_GPL(hidinput_get_led_field); unsigned int hidinput_count_leds(struct hid_device *hid) { struct hid_report *report; struct hid_field *field; int i, j; unsigned int count = 0; list_for_each_entry(report, &hid->report_enum[HID_OUTPUT_REPORT].report_list, list) { for (i = 0; i < report->maxfield; i++) { field = report->field[i]; for (j = 0; j < field->maxusage; j++) if (field->usage[j].type == EV_LED && field->value[j]) count += 1; } } return count; } EXPORT_SYMBOL_GPL(hidinput_count_leds); static void hidinput_led_worker(struct work_struct *work) { struct hid_device *hid = container_of(work, struct hid_device, led_work); struct hid_field *field; struct hid_report *report; int ret; u32 len; __u8 *buf; field = hidinput_get_led_field(hid); if (!field) return; /* * field->report is accessed unlocked regarding HID core. So there might * be another incoming SET-LED request from user-space, which changes * the LED state while we assemble our outgoing buffer. However, this * doesn't matter as hid_output_report() correctly converts it into a * boolean value no matter what information is currently set on the LED * field (even garbage). So the remote device will always get a valid * request. * And in case we send a wrong value, a next led worker is spawned * for every SET-LED request so the following worker will send the * correct value, guaranteed! */ report = field->report; /* use custom SET_REPORT request if possible (asynchronous) */ if (hid->ll_driver->request) return hid->ll_driver->request(hid, report, HID_REQ_SET_REPORT); /* fall back to generic raw-output-report */ len = hid_report_len(report); buf = hid_alloc_report_buf(report, GFP_KERNEL); if (!buf) return; hid_output_report(report, buf); /* synchronous output report */ ret = hid_hw_output_report(hid, buf, len); if (ret == -ENOSYS) hid_hw_raw_request(hid, report->id, buf, len, HID_OUTPUT_REPORT, HID_REQ_SET_REPORT); kfree(buf); } static int hidinput_input_event(struct input_dev *dev, unsigned int type, unsigned int code, int value) { struct hid_device *hid = input_get_drvdata(dev); struct hid_field *field; int offset; if (type == EV_FF) return input_ff_event(dev, type, code, value); if (type != EV_LED) return -1; if ((offset = hidinput_find_field(hid, type, code, &field)) == -1) { hid_warn(dev, "event field not found\n"); return -1; } hid_set_field(field, offset, value); schedule_work(&hid->led_work); return 0; } static int hidinput_open(struct input_dev *dev) { struct hid_device *hid = input_get_drvdata(dev); return hid_hw_open(hid); } static void hidinput_close(struct input_dev *dev) { struct hid_device *hid = input_get_drvdata(dev); hid_hw_close(hid); } static bool __hidinput_change_resolution_multipliers(struct hid_device *hid, struct hid_report *report, bool use_logical_max) { struct hid_usage *usage; bool update_needed = false; bool get_report_completed = false; int i, j; if (report->maxfield == 0) return false; for (i = 0; i < report->maxfield; i++) { __s32 value = use_logical_max ? report->field[i]->logical_maximum : report->field[i]->logical_minimum; /* There is no good reason for a Resolution * Multiplier to have a count other than 1. * Ignore that case. */ if (report->field[i]->report_count != 1) continue; for (j = 0; j < report->field[i]->maxusage; j++) { usage = &report->field[i]->usage[j]; if (usage->hid != HID_GD_RESOLUTION_MULTIPLIER) continue; /* * If we have more than one feature within this * report we need to fill in the bits from the * others before we can overwrite the ones for the * Resolution Multiplier. * * But if we're not allowed to read from the device, * we just bail. Such a device should not exist * anyway. */ if (!get_report_completed && report->maxfield > 1) { if (hid->quirks & HID_QUIRK_NO_INIT_REPORTS) return update_needed; hid_hw_request(hid, report, HID_REQ_GET_REPORT); hid_hw_wait(hid); get_report_completed = true; } report->field[i]->value[j] = value; update_needed = true; } } return update_needed; } static void hidinput_change_resolution_multipliers(struct hid_device *hid) { struct hid_report_enum *rep_enum; struct hid_report *rep; int ret; rep_enum = &hid->report_enum[HID_FEATURE_REPORT]; list_for_each_entry(rep, &rep_enum->report_list, list) { bool update_needed = __hidinput_change_resolution_multipliers(hid, rep, true); if (update_needed) { ret = __hid_request(hid, rep, HID_REQ_SET_REPORT); if (ret) { __hidinput_change_resolution_multipliers(hid, rep, false); return; } } } /* refresh our structs */ hid_setup_resolution_multiplier(hid); } static void report_features(struct hid_device *hid) { struct hid_driver *drv = hid->driver; struct hid_report_enum *rep_enum; struct hid_report *rep; struct hid_usage *usage; int i, j; rep_enum = &hid->report_enum[HID_FEATURE_REPORT]; list_for_each_entry(rep, &rep_enum->report_list, list) for (i = 0; i < rep->maxfield; i++) { /* Ignore if report count is out of bounds. */ if (rep->field[i]->report_count < 1) continue; for (j = 0; j < rep->field[i]->maxusage; j++) { usage = &rep->field[i]->usage[j]; /* Verify if Battery Strength feature is available */ if (usage->hid == HID_DC_BATTERYSTRENGTH) hidinput_setup_battery(hid, HID_FEATURE_REPORT, rep->field[i], false); if (drv->feature_mapping) drv->feature_mapping(hid, rep->field[i], usage); } } } static struct hid_input *hidinput_allocate(struct hid_device *hid, unsigned int application) { struct hid_input *hidinput = kzalloc(sizeof(*hidinput), GFP_KERNEL); struct input_dev *input_dev = input_allocate_device(); const char *suffix = NULL; size_t suffix_len, name_len; if (!hidinput || !input_dev) goto fail; if ((hid->quirks & HID_QUIRK_INPUT_PER_APP) && hid->maxapplication > 1) { switch (application) { case HID_GD_KEYBOARD: suffix = "Keyboard"; break; case HID_GD_KEYPAD: suffix = "Keypad"; break; case HID_GD_MOUSE: suffix = "Mouse"; break; case HID_DG_PEN: /* * yes, there is an issue here: * DG_PEN -> "Stylus" * DG_STYLUS -> "Pen" * But changing this now means users with config snippets * will have to change it and the test suite will not be happy. */ suffix = "Stylus"; break; case HID_DG_STYLUS: suffix = "Pen"; break; case HID_DG_TOUCHSCREEN: suffix = "Touchscreen"; break; case HID_DG_TOUCHPAD: suffix = "Touchpad"; break; case HID_GD_SYSTEM_CONTROL: suffix = "System Control"; break; case HID_CP_CONSUMER_CONTROL: suffix = "Consumer Control"; break; case HID_GD_WIRELESS_RADIO_CTLS: suffix = "Wireless Radio Control"; break; case HID_GD_SYSTEM_MULTIAXIS: suffix = "System Multi Axis"; break; default: break; } } if (suffix) { name_len = strlen(hid->name); suffix_len = strlen(suffix); if ((name_len < suffix_len) || strcmp(hid->name + name_len - suffix_len, suffix)) { hidinput->name = kasprintf(GFP_KERNEL, "%s %s", hid->name, suffix); if (!hidinput->name) goto fail; } } input_set_drvdata(input_dev, hid); input_dev->event = hidinput_input_event; input_dev->open = hidinput_open; input_dev->close = hidinput_close; input_dev->setkeycode = hidinput_setkeycode; input_dev->getkeycode = hidinput_getkeycode; input_dev->name = hidinput->name ? hidinput->name : hid->name; input_dev->phys = hid->phys; input_dev->uniq = hid->uniq; input_dev->id.bustype = hid->bus; input_dev->id.vendor = hid->vendor; input_dev->id.product = hid->product; input_dev->id.version = hid->version; input_dev->dev.parent = &hid->dev; hidinput->input = input_dev; hidinput->application = application; list_add_tail(&hidinput->list, &hid->inputs); INIT_LIST_HEAD(&hidinput->reports); return hidinput; fail: kfree(hidinput); input_free_device(input_dev); hid_err(hid, "Out of memory during hid input probe\n"); return NULL; } static bool hidinput_has_been_populated(struct hid_input *hidinput) { int i; unsigned long r = 0; for (i = 0; i < BITS_TO_LONGS(EV_CNT); i++) r |= hidinput->input->evbit[i]; for (i = 0; i < BITS_TO_LONGS(KEY_CNT); i++) r |= hidinput->input->keybit[i]; for (i = 0; i < BITS_TO_LONGS(REL_CNT); i++) r |= hidinput->input->relbit[i]; for (i = 0; i < BITS_TO_LONGS(ABS_CNT); i++) r |= hidinput->input->absbit[i]; for (i = 0; i < BITS_TO_LONGS(MSC_CNT); i++) r |= hidinput->input->mscbit[i]; for (i = 0; i < BITS_TO_LONGS(LED_CNT); i++) r |= hidinput->input->ledbit[i]; for (i = 0; i < BITS_TO_LONGS(SND_CNT); i++) r |= hidinput->input->sndbit[i]; for (i = 0; i < BITS_TO_LONGS(FF_CNT); i++) r |= hidinput->input->ffbit[i]; for (i = 0; i < BITS_TO_LONGS(SW_CNT); i++) r |= hidinput->input->swbit[i]; return !!r; } static void hidinput_cleanup_hidinput(struct hid_device *hid, struct hid_input *hidinput) { struct hid_report *report; int i, k; list_del(&hidinput->list); input_free_device(hidinput->input); kfree(hidinput->name); for (k = HID_INPUT_REPORT; k <= HID_OUTPUT_REPORT; k++) { if (k == HID_OUTPUT_REPORT && hid->quirks & HID_QUIRK_SKIP_OUTPUT_REPORTS) continue; list_for_each_entry(report, &hid->report_enum[k].report_list, list) { for (i = 0; i < report->maxfield; i++) if (report->field[i]->hidinput == hidinput) report->field[i]->hidinput = NULL; } } kfree(hidinput); } static struct hid_input *hidinput_match(struct hid_report *report) { struct hid_device *hid = report->device; struct hid_input *hidinput; list_for_each_entry(hidinput, &hid->inputs, list) { if (hidinput->report && hidinput->report->id == report->id) return hidinput; } return NULL; } static struct hid_input *hidinput_match_application(struct hid_report *report) { struct hid_device *hid = report->device; struct hid_input *hidinput; list_for_each_entry(hidinput, &hid->inputs, list) { if (hidinput->application == report->application) return hidinput; /* * Keep SystemControl and ConsumerControl applications together * with the main keyboard, if present. */ if ((report->application == HID_GD_SYSTEM_CONTROL || report->application == HID_CP_CONSUMER_CONTROL) && hidinput->application == HID_GD_KEYBOARD) { return hidinput; } } return NULL; } static inline void hidinput_configure_usages(struct hid_input *hidinput, struct hid_report *report) { int i, j, k; int first_field_index = 0; int slot_collection_index = -1; int prev_collection_index = -1; unsigned int slot_idx = 0; struct hid_field *field; /* * First tag all the fields that are part of a slot, * a slot needs to have one Contact ID in the collection */ for (i = 0; i < report->maxfield; i++) { field = report->field[i]; /* ignore fields without usage */ if (field->maxusage < 1) continue; /* * janitoring when collection_index changes */ if (prev_collection_index != field->usage->collection_index) { prev_collection_index = field->usage->collection_index; first_field_index = i; } /* * if we already found a Contact ID in the collection, * tag and continue to the next. */ if (slot_collection_index == field->usage->collection_index) { field->slot_idx = slot_idx; continue; } /* check if the current field has Contact ID */ for (j = 0; j < field->maxusage; j++) { if (field->usage[j].hid == HID_DG_CONTACTID) { slot_collection_index = field->usage->collection_index; slot_idx++; /* * mark all previous fields and this one in the * current collection to be slotted. */ for (k = first_field_index; k <= i; k++) report->field[k]->slot_idx = slot_idx; break; } } } for (i = 0; i < report->maxfield; i++) for (j = 0; j < report->field[i]->maxusage; j++) hidinput_configure_usage(hidinput, report->field[i], report->field[i]->usage + j, j); } /* * Register the input device; print a message. * Configure the input layer interface * Read all reports and initialize the absolute field values. */ int hidinput_connect(struct hid_device *hid, unsigned int force) { struct hid_driver *drv = hid->driver; struct hid_report *report; struct hid_input *next, *hidinput = NULL; unsigned int application; int i, k; INIT_LIST_HEAD(&hid->inputs); INIT_WORK(&hid->led_work, hidinput_led_worker); hid->status &= ~HID_STAT_DUP_DETECTED; if (!force) { for (i = 0; i < hid->maxcollection; i++) { struct hid_collection *col = &hid->collection[i]; if (col->type == HID_COLLECTION_APPLICATION || col->type == HID_COLLECTION_PHYSICAL) if (IS_INPUT_APPLICATION(col->usage)) break; } if (i == hid->maxcollection) return -1; } report_features(hid); for (k = HID_INPUT_REPORT; k <= HID_OUTPUT_REPORT; k++) { if (k == HID_OUTPUT_REPORT && hid->quirks & HID_QUIRK_SKIP_OUTPUT_REPORTS) continue; list_for_each_entry(report, &hid->report_enum[k].report_list, list) { if (!report->maxfield) continue; application = report->application; /* * Find the previous hidinput report attached * to this report id. */ if (hid->quirks & HID_QUIRK_MULTI_INPUT) hidinput = hidinput_match(report); else if (hid->maxapplication > 1 && (hid->quirks & HID_QUIRK_INPUT_PER_APP)) hidinput = hidinput_match_application(report); if (!hidinput) { hidinput = hidinput_allocate(hid, application); if (!hidinput) goto out_unwind; } hidinput_configure_usages(hidinput, report); if (hid->quirks & HID_QUIRK_MULTI_INPUT) hidinput->report = report; list_add_tail(&report->hidinput_list, &hidinput->reports); } } hidinput_change_resolution_multipliers(hid); list_for_each_entry_safe(hidinput, next, &hid->inputs, list) { if (drv->input_configured && drv->input_configured(hid, hidinput)) goto out_unwind; if (!hidinput_has_been_populated(hidinput)) { /* no need to register an input device not populated */ hidinput_cleanup_hidinput(hid, hidinput); continue; } if (input_register_device(hidinput->input)) goto out_unwind; hidinput->registered = true; } if (list_empty(&hid->inputs)) { hid_err(hid, "No inputs registered, leaving\n"); goto out_unwind; } if (hid->status & HID_STAT_DUP_DETECTED) hid_dbg(hid, "Some usages could not be mapped, please use HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE if this is legitimate.\n"); return 0; out_unwind: /* unwind the ones we already registered */ hidinput_disconnect(hid); return -1; } EXPORT_SYMBOL_GPL(hidinput_connect); void hidinput_disconnect(struct hid_device *hid) { struct hid_input *hidinput, *next; hidinput_cleanup_battery(hid); list_for_each_entry_safe(hidinput, next, &hid->inputs, list) { list_del(&hidinput->list); if (hidinput->registered) input_unregister_device(hidinput->input); else input_free_device(hidinput->input); kfree(hidinput->name); kfree(hidinput); } /* led_work is spawned by input_dev callbacks, but doesn't access the * parent input_dev at all. Once all input devices are removed, we * know that led_work will never get restarted, so we can cancel it * synchronously and are safe. */ cancel_work_sync(&hid->led_work); } EXPORT_SYMBOL_GPL(hidinput_disconnect); #ifdef CONFIG_HID_KUNIT_TEST #include "hid-input-test.c" #endif |
| 2 2 2 2 2 2 | 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 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Basic Transport Functions exploiting Infiniband API * * Copyright IBM Corp. 2016 * * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com> */ #include <linux/socket.h> #include <linux/if_vlan.h> #include <linux/random.h> #include <linux/workqueue.h> #include <linux/wait.h> #include <linux/reboot.h> #include <linux/mutex.h> #include <linux/list.h> #include <linux/smc.h> #include <net/tcp.h> #include <net/sock.h> #include <rdma/ib_verbs.h> #include <rdma/ib_cache.h> #include "smc.h" #include "smc_clc.h" #include "smc_core.h" #include "smc_ib.h" #include "smc_wr.h" #include "smc_llc.h" #include "smc_cdc.h" #include "smc_close.h" #include "smc_ism.h" #include "smc_netlink.h" #include "smc_stats.h" #include "smc_tracepoint.h" #define SMC_LGR_NUM_INCR 256 #define SMC_LGR_FREE_DELAY_SERV (600 * HZ) #define SMC_LGR_FREE_DELAY_CLNT (SMC_LGR_FREE_DELAY_SERV + 10 * HZ) struct smc_lgr_list smc_lgr_list = { /* established link groups */ .lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock), .list = LIST_HEAD_INIT(smc_lgr_list.list), .num = 0, }; static atomic_t lgr_cnt = ATOMIC_INIT(0); /* number of existing link groups */ static DECLARE_WAIT_QUEUE_HEAD(lgrs_deleted); static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, struct smc_buf_desc *buf_desc); static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft); static void smc_link_down_work(struct work_struct *work); /* return head of link group list and its lock for a given link group */ static inline struct list_head *smc_lgr_list_head(struct smc_link_group *lgr, spinlock_t **lgr_lock) { if (lgr->is_smcd) { *lgr_lock = &lgr->smcd->lgr_lock; return &lgr->smcd->lgr_list; } *lgr_lock = &smc_lgr_list.lock; return &smc_lgr_list.list; } static void smc_ibdev_cnt_inc(struct smc_link *lnk) { atomic_inc(&lnk->smcibdev->lnk_cnt_by_port[lnk->ibport - 1]); } static void smc_ibdev_cnt_dec(struct smc_link *lnk) { atomic_dec(&lnk->smcibdev->lnk_cnt_by_port[lnk->ibport - 1]); } static void smc_lgr_schedule_free_work(struct smc_link_group *lgr) { /* client link group creation always follows the server link group * creation. For client use a somewhat higher removal delay time, * otherwise there is a risk of out-of-sync link groups. */ if (!lgr->freeing) { mod_delayed_work(system_wq, &lgr->free_work, (!lgr->is_smcd && lgr->role == SMC_CLNT) ? SMC_LGR_FREE_DELAY_CLNT : SMC_LGR_FREE_DELAY_SERV); } } /* Register connection's alert token in our lookup structure. * To use rbtrees we have to implement our own insert core. * Requires @conns_lock * @smc connection to register * Returns 0 on success, != otherwise. */ static void smc_lgr_add_alert_token(struct smc_connection *conn) { struct rb_node **link, *parent = NULL; u32 token = conn->alert_token_local; link = &conn->lgr->conns_all.rb_node; while (*link) { struct smc_connection *cur = rb_entry(*link, struct smc_connection, alert_node); parent = *link; if (cur->alert_token_local > token) link = &parent->rb_left; else link = &parent->rb_right; } /* Put the new node there */ rb_link_node(&conn->alert_node, parent, link); rb_insert_color(&conn->alert_node, &conn->lgr->conns_all); } /* assign an SMC-R link to the connection */ static int smcr_lgr_conn_assign_link(struct smc_connection *conn, bool first) { enum smc_link_state expected = first ? SMC_LNK_ACTIVATING : SMC_LNK_ACTIVE; int i, j; /* do link balancing */ conn->lnk = NULL; /* reset conn->lnk first */ for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &conn->lgr->lnk[i]; if (lnk->state != expected || lnk->link_is_asym) continue; if (conn->lgr->role == SMC_CLNT) { conn->lnk = lnk; /* temporary, SMC server assigns link*/ break; } if (conn->lgr->conns_num % 2) { for (j = i + 1; j < SMC_LINKS_PER_LGR_MAX; j++) { struct smc_link *lnk2; lnk2 = &conn->lgr->lnk[j]; if (lnk2->state == expected && !lnk2->link_is_asym) { conn->lnk = lnk2; break; } } } if (!conn->lnk) conn->lnk = lnk; break; } if (!conn->lnk) return SMC_CLC_DECL_NOACTLINK; atomic_inc(&conn->lnk->conn_cnt); return 0; } /* Register connection in link group by assigning an alert token * registered in a search tree. * Requires @conns_lock * Note that '0' is a reserved value and not assigned. */ static int smc_lgr_register_conn(struct smc_connection *conn, bool first) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); static atomic_t nexttoken = ATOMIC_INIT(0); int rc; if (!conn->lgr->is_smcd) { rc = smcr_lgr_conn_assign_link(conn, first); if (rc) { conn->lgr = NULL; return rc; } } /* find a new alert_token_local value not yet used by some connection * in this link group */ sock_hold(&smc->sk); /* sock_put in smc_lgr_unregister_conn() */ while (!conn->alert_token_local) { conn->alert_token_local = atomic_inc_return(&nexttoken); if (smc_lgr_find_conn(conn->alert_token_local, conn->lgr)) conn->alert_token_local = 0; } smc_lgr_add_alert_token(conn); conn->lgr->conns_num++; return 0; } /* Unregister connection and reset the alert token of the given connection< */ static void __smc_lgr_unregister_conn(struct smc_connection *conn) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); struct smc_link_group *lgr = conn->lgr; rb_erase(&conn->alert_node, &lgr->conns_all); if (conn->lnk) atomic_dec(&conn->lnk->conn_cnt); lgr->conns_num--; conn->alert_token_local = 0; sock_put(&smc->sk); /* sock_hold in smc_lgr_register_conn() */ } /* Unregister connection from lgr */ static void smc_lgr_unregister_conn(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; if (!smc_conn_lgr_valid(conn)) return; write_lock_bh(&lgr->conns_lock); if (conn->alert_token_local) { __smc_lgr_unregister_conn(conn); } write_unlock_bh(&lgr->conns_lock); } int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); char hostname[SMC_MAX_HOSTNAME_LEN + 1]; char smc_seid[SMC_MAX_EID_LEN + 1]; struct nlattr *attrs; u8 *seid = NULL; u8 *host = NULL; void *nlh; nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_GET_SYS_INFO); if (!nlh) goto errmsg; if (cb_ctx->pos[0]) goto errout; attrs = nla_nest_start(skb, SMC_GEN_SYS_INFO); if (!attrs) goto errout; if (nla_put_u8(skb, SMC_NLA_SYS_VER, SMC_V2)) goto errattr; if (nla_put_u8(skb, SMC_NLA_SYS_REL, SMC_RELEASE)) goto errattr; if (nla_put_u8(skb, SMC_NLA_SYS_IS_ISM_V2, smc_ism_is_v2_capable())) goto errattr; if (nla_put_u8(skb, SMC_NLA_SYS_IS_SMCR_V2, true)) goto errattr; smc_clc_get_hostname(&host); if (host) { memcpy(hostname, host, SMC_MAX_HOSTNAME_LEN); hostname[SMC_MAX_HOSTNAME_LEN] = 0; if (nla_put_string(skb, SMC_NLA_SYS_LOCAL_HOST, hostname)) goto errattr; } if (smc_ism_is_v2_capable()) { smc_ism_get_system_eid(&seid); memcpy(smc_seid, seid, SMC_MAX_EID_LEN); smc_seid[SMC_MAX_EID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_SYS_SEID, smc_seid)) goto errattr; } nla_nest_end(skb, attrs); genlmsg_end(skb, nlh); cb_ctx->pos[0] = 1; return skb->len; errattr: nla_nest_cancel(skb, attrs); errout: genlmsg_cancel(skb, nlh); errmsg: return skb->len; } /* Fill SMC_NLA_LGR_D_V2_COMMON/SMC_NLA_LGR_R_V2_COMMON nested attributes */ static int smc_nl_fill_lgr_v2_common(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb, struct nlattr *v2_attrs) { char smc_host[SMC_MAX_HOSTNAME_LEN + 1]; char smc_eid[SMC_MAX_EID_LEN + 1]; if (nla_put_u8(skb, SMC_NLA_LGR_V2_VER, lgr->smc_version)) goto errv2attr; if (nla_put_u8(skb, SMC_NLA_LGR_V2_REL, lgr->peer_smc_release)) goto errv2attr; if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os)) goto errv2attr; memcpy(smc_host, lgr->peer_hostname, SMC_MAX_HOSTNAME_LEN); smc_host[SMC_MAX_HOSTNAME_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host)) goto errv2attr; memcpy(smc_eid, lgr->negotiated_eid, SMC_MAX_EID_LEN); smc_eid[SMC_MAX_EID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid)) goto errv2attr; nla_nest_end(skb, v2_attrs); return 0; errv2attr: nla_nest_cancel(skb, v2_attrs); return -EMSGSIZE; } static int smc_nl_fill_smcr_lgr_v2(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *v2_attrs; v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2); if (!v2_attrs) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_DIRECT, !lgr->uses_gateway)) goto errv2attr; if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_MAX_CONNS, lgr->max_conns)) goto errv2attr; if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_MAX_LINKS, lgr->max_links)) goto errv2attr; nla_nest_end(skb, v2_attrs); return 0; errv2attr: nla_nest_cancel(skb, v2_attrs); errattr: return -EMSGSIZE; } static int smc_nl_fill_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { char smc_target[SMC_MAX_PNETID_LEN + 1]; struct nlattr *attrs, *v2_attrs; attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCR); if (!attrs) goto errout; if (nla_put_u32(skb, SMC_NLA_LGR_R_ID, *((u32 *)&lgr->id))) goto errattr; if (nla_put_u32(skb, SMC_NLA_LGR_R_CONNS_NUM, lgr->conns_num)) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_ROLE, lgr->role)) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_TYPE, lgr->type)) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_BUF_TYPE, lgr->buf_type)) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_VLAN_ID, lgr->vlan_id)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_LGR_R_NET_COOKIE, lgr->net->net_cookie, SMC_NLA_LGR_R_PAD)) goto errattr; memcpy(smc_target, lgr->pnet_id, SMC_MAX_PNETID_LEN); smc_target[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target)) goto errattr; if (lgr->smc_version > SMC_V1) { v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2_COMMON); if (!v2_attrs) goto errattr; if (smc_nl_fill_lgr_v2_common(lgr, skb, cb, v2_attrs)) goto errattr; if (smc_nl_fill_smcr_lgr_v2(lgr, skb, cb)) goto errattr; } nla_nest_end(skb, attrs); return 0; errattr: nla_nest_cancel(skb, attrs); errout: return -EMSGSIZE; } static int smc_nl_fill_lgr_link(struct smc_link_group *lgr, struct smc_link *link, struct sk_buff *skb, struct netlink_callback *cb) { char smc_ibname[IB_DEVICE_NAME_MAX]; u8 smc_gid_target[41]; struct nlattr *attrs; u32 link_uid = 0; void *nlh; nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_GET_LINK_SMCR); if (!nlh) goto errmsg; attrs = nla_nest_start(skb, SMC_GEN_LINK_SMCR); if (!attrs) goto errout; if (nla_put_u8(skb, SMC_NLA_LINK_ID, link->link_id)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LINK_STATE, link->state)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LINK_CONN_CNT, atomic_read(&link->conn_cnt))) goto errattr; if (nla_put_u8(skb, SMC_NLA_LINK_IB_PORT, link->ibport)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LINK_NET_DEV, link->ndev_ifidx)) goto errattr; snprintf(smc_ibname, sizeof(smc_ibname), "%s", link->ibname); if (nla_put_string(skb, SMC_NLA_LINK_IB_DEV, smc_ibname)) goto errattr; memcpy(&link_uid, link->link_uid, sizeof(link_uid)); if (nla_put_u32(skb, SMC_NLA_LINK_UID, link_uid)) goto errattr; memcpy(&link_uid, link->peer_link_uid, sizeof(link_uid)); if (nla_put_u32(skb, SMC_NLA_LINK_PEER_UID, link_uid)) goto errattr; memset(smc_gid_target, 0, sizeof(smc_gid_target)); smc_gid_be16_convert(smc_gid_target, link->gid); if (nla_put_string(skb, SMC_NLA_LINK_GID, smc_gid_target)) goto errattr; memset(smc_gid_target, 0, sizeof(smc_gid_target)); smc_gid_be16_convert(smc_gid_target, link->peer_gid); if (nla_put_string(skb, SMC_NLA_LINK_PEER_GID, smc_gid_target)) goto errattr; nla_nest_end(skb, attrs); genlmsg_end(skb, nlh); return 0; errattr: nla_nest_cancel(skb, attrs); errout: genlmsg_cancel(skb, nlh); errmsg: return -EMSGSIZE; } static int smc_nl_handle_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb, bool list_links) { void *nlh; int i; nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_GET_LGR_SMCR); if (!nlh) goto errmsg; if (smc_nl_fill_lgr(lgr, skb, cb)) goto errout; genlmsg_end(skb, nlh); if (!list_links) goto out; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_usable(&lgr->lnk[i])) continue; if (smc_nl_fill_lgr_link(lgr, &lgr->lnk[i], skb, cb)) goto errout; } out: return 0; errout: genlmsg_cancel(skb, nlh); errmsg: return -EMSGSIZE; } static void smc_nl_fill_lgr_list(struct smc_lgr_list *smc_lgr, struct sk_buff *skb, struct netlink_callback *cb, bool list_links) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); struct smc_link_group *lgr; int snum = cb_ctx->pos[0]; int num = 0; spin_lock_bh(&smc_lgr->lock); list_for_each_entry(lgr, &smc_lgr->list, list) { if (num < snum) goto next; if (smc_nl_handle_lgr(lgr, skb, cb, list_links)) goto errout; next: num++; } errout: spin_unlock_bh(&smc_lgr->lock); cb_ctx->pos[0] = num; } static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { char smc_pnet[SMC_MAX_PNETID_LEN + 1]; struct smcd_dev *smcd = lgr->smcd; struct smcd_gid smcd_gid; struct nlattr *attrs; void *nlh; nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_GET_LGR_SMCD); if (!nlh) goto errmsg; attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCD); if (!attrs) goto errout; if (nla_put_u32(skb, SMC_NLA_LGR_D_ID, *((u32 *)&lgr->id))) goto errattr; smcd->ops->get_local_gid(smcd, &smcd_gid); if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_GID, smcd_gid.gid, SMC_NLA_LGR_D_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_EXT_GID, smcd_gid.gid_ext, SMC_NLA_LGR_D_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_GID, lgr->peer_gid.gid, SMC_NLA_LGR_D_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_EXT_GID, lgr->peer_gid.gid_ext, SMC_NLA_LGR_D_PAD)) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_D_VLAN_ID, lgr->vlan_id)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LGR_D_CONNS_NUM, lgr->conns_num)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LGR_D_CHID, smc_ism_get_chid(lgr->smcd))) goto errattr; memcpy(smc_pnet, lgr->smcd->pnetid, SMC_MAX_PNETID_LEN); smc_pnet[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet)) goto errattr; if (lgr->smc_version > SMC_V1) { struct nlattr *v2_attrs; v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_D_V2_COMMON); if (!v2_attrs) goto errattr; if (smc_nl_fill_lgr_v2_common(lgr, skb, cb, v2_attrs)) goto errattr; } nla_nest_end(skb, attrs); genlmsg_end(skb, nlh); return 0; errattr: nla_nest_cancel(skb, attrs); errout: genlmsg_cancel(skb, nlh); errmsg: return -EMSGSIZE; } static int smc_nl_handle_smcd_lgr(struct smcd_dev *dev, struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); struct smc_link_group *lgr; int snum = cb_ctx->pos[1]; int rc = 0, num = 0; spin_lock_bh(&dev->lgr_lock); list_for_each_entry(lgr, &dev->lgr_list, list) { if (!lgr->is_smcd) continue; if (num < snum) goto next; rc = smc_nl_fill_smcd_lgr(lgr, skb, cb); if (rc) goto errout; next: num++; } errout: spin_unlock_bh(&dev->lgr_lock); cb_ctx->pos[1] = num; return rc; } static int smc_nl_fill_smcd_dev(struct smcd_dev_list *dev_list, struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); struct smcd_dev *smcd_dev; int snum = cb_ctx->pos[0]; int rc = 0, num = 0; mutex_lock(&dev_list->mutex); list_for_each_entry(smcd_dev, &dev_list->list, list) { if (list_empty(&smcd_dev->lgr_list)) continue; if (num < snum) goto next; rc = smc_nl_handle_smcd_lgr(smcd_dev, skb, cb); if (rc) goto errout; next: num++; } errout: mutex_unlock(&dev_list->mutex); cb_ctx->pos[0] = num; return rc; } int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb) { bool list_links = false; smc_nl_fill_lgr_list(&smc_lgr_list, skb, cb, list_links); return skb->len; } int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb) { bool list_links = true; smc_nl_fill_lgr_list(&smc_lgr_list, skb, cb, list_links); return skb->len; } int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb) { smc_nl_fill_smcd_dev(&smcd_dev_list, skb, cb); return skb->len; } void smc_lgr_cleanup_early(struct smc_link_group *lgr) { spinlock_t *lgr_lock; if (!lgr) return; smc_lgr_list_head(lgr, &lgr_lock); spin_lock_bh(lgr_lock); /* do not use this link group for new connections */ if (!list_empty(&lgr->list)) list_del_init(&lgr->list); spin_unlock_bh(lgr_lock); __smc_lgr_terminate(lgr, true); } static void smcr_lgr_link_deactivate_all(struct smc_link_group *lgr) { int i; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &lgr->lnk[i]; if (smc_link_sendable(lnk)) lnk->state = SMC_LNK_INACTIVE; } wake_up_all(&lgr->llc_msg_waiter); wake_up_all(&lgr->llc_flow_waiter); } static void smc_lgr_free(struct smc_link_group *lgr); static void smc_lgr_free_work(struct work_struct *work) { struct smc_link_group *lgr = container_of(to_delayed_work(work), struct smc_link_group, free_work); spinlock_t *lgr_lock; bool conns; smc_lgr_list_head(lgr, &lgr_lock); spin_lock_bh(lgr_lock); if (lgr->freeing) { spin_unlock_bh(lgr_lock); return; } read_lock_bh(&lgr->conns_lock); conns = RB_EMPTY_ROOT(&lgr->conns_all); read_unlock_bh(&lgr->conns_lock); if (!conns) { /* number of lgr connections is no longer zero */ spin_unlock_bh(lgr_lock); return; } list_del_init(&lgr->list); /* remove from smc_lgr_list */ lgr->freeing = 1; /* this instance does the freeing, no new schedule */ spin_unlock_bh(lgr_lock); cancel_delayed_work(&lgr->free_work); if (!lgr->is_smcd && !lgr->terminating) smc_llc_send_link_delete_all(lgr, true, SMC_LLC_DEL_PROG_INIT_TERM); if (lgr->is_smcd && !lgr->terminating) smc_ism_signal_shutdown(lgr); if (!lgr->is_smcd) smcr_lgr_link_deactivate_all(lgr); smc_lgr_free(lgr); } static void smc_lgr_terminate_work(struct work_struct *work) { struct smc_link_group *lgr = container_of(work, struct smc_link_group, terminate_work); __smc_lgr_terminate(lgr, true); } /* return next unique link id for the lgr */ static u8 smcr_next_link_id(struct smc_link_group *lgr) { u8 link_id; int i; while (1) { again: link_id = ++lgr->next_link_id; if (!link_id) /* skip zero as link_id */ link_id = ++lgr->next_link_id; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (smc_link_usable(&lgr->lnk[i]) && lgr->lnk[i].link_id == link_id) goto again; } break; } return link_id; } static void smcr_copy_dev_info_to_link(struct smc_link *link) { struct smc_ib_device *smcibdev = link->smcibdev; snprintf(link->ibname, sizeof(link->ibname), "%s", smcibdev->ibdev->name); link->ndev_ifidx = smcibdev->ndev_ifidx[link->ibport - 1]; } int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, u8 link_idx, struct smc_init_info *ini) { struct smc_ib_device *smcibdev; u8 rndvec[3]; int rc; if (lgr->smc_version == SMC_V2) { lnk->smcibdev = ini->smcrv2.ib_dev_v2; lnk->ibport = ini->smcrv2.ib_port_v2; } else { lnk->smcibdev = ini->ib_dev; lnk->ibport = ini->ib_port; } get_device(&lnk->smcibdev->ibdev->dev); atomic_inc(&lnk->smcibdev->lnk_cnt); refcount_set(&lnk->refcnt, 1); /* link refcnt is set to 1 */ lnk->clearing = 0; lnk->path_mtu = lnk->smcibdev->pattr[lnk->ibport - 1].active_mtu; lnk->link_id = smcr_next_link_id(lgr); lnk->lgr = lgr; smc_lgr_hold(lgr); /* lgr_put in smcr_link_clear() */ lnk->link_idx = link_idx; lnk->wr_rx_id_compl = 0; smc_ibdev_cnt_inc(lnk); smcr_copy_dev_info_to_link(lnk); atomic_set(&lnk->conn_cnt, 0); smc_llc_link_set_uid(lnk); INIT_WORK(&lnk->link_down_wrk, smc_link_down_work); if (!lnk->smcibdev->initialized) { rc = (int)smc_ib_setup_per_ibdev(lnk->smcibdev); if (rc) goto out; } get_random_bytes(rndvec, sizeof(rndvec)); lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) + (rndvec[2] << 16); rc = smc_ib_determine_gid(lnk->smcibdev, lnk->ibport, ini->vlan_id, lnk->gid, &lnk->sgid_index, lgr->smc_version == SMC_V2 ? &ini->smcrv2 : NULL); if (rc) goto out; rc = smc_llc_link_init(lnk); if (rc) goto out; rc = smc_wr_alloc_link_mem(lnk); if (rc) goto clear_llc_lnk; rc = smc_ib_create_protection_domain(lnk); if (rc) goto free_link_mem; rc = smc_ib_create_queue_pair(lnk); if (rc) goto dealloc_pd; rc = smc_wr_create_link(lnk); if (rc) goto destroy_qp; lnk->state = SMC_LNK_ACTIVATING; return 0; destroy_qp: smc_ib_destroy_queue_pair(lnk); dealloc_pd: smc_ib_dealloc_protection_domain(lnk); free_link_mem: smc_wr_free_link_mem(lnk); clear_llc_lnk: smc_llc_link_clear(lnk, false); out: smc_ibdev_cnt_dec(lnk); put_device(&lnk->smcibdev->ibdev->dev); smcibdev = lnk->smcibdev; memset(lnk, 0, sizeof(struct smc_link)); lnk->state = SMC_LNK_UNUSED; if (!atomic_dec_return(&smcibdev->lnk_cnt)) wake_up(&smcibdev->lnks_deleted); smc_lgr_put(lgr); /* lgr_hold above */ return rc; } /* create a new SMC link group */ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) { struct smc_link_group *lgr; struct list_head *lgr_list; struct smcd_dev *smcd; struct smc_link *lnk; spinlock_t *lgr_lock; u8 link_idx; int rc = 0; int i; if (ini->is_smcd && ini->vlan_id) { if (smc_ism_get_vlan(ini->ism_dev[ini->ism_selected], ini->vlan_id)) { rc = SMC_CLC_DECL_ISMVLANERR; goto out; } } lgr = kzalloc(sizeof(*lgr), GFP_KERNEL); if (!lgr) { rc = SMC_CLC_DECL_MEM; goto ism_put_vlan; } lgr->tx_wq = alloc_workqueue("smc_tx_wq-%*phN", 0, 0, SMC_LGR_ID_SIZE, &lgr->id); if (!lgr->tx_wq) { rc = -ENOMEM; goto free_lgr; } lgr->is_smcd = ini->is_smcd; lgr->sync_err = 0; lgr->terminating = 0; lgr->freeing = 0; lgr->vlan_id = ini->vlan_id; refcount_set(&lgr->refcnt, 1); /* set lgr refcnt to 1 */ init_rwsem(&lgr->sndbufs_lock); init_rwsem(&lgr->rmbs_lock); rwlock_init(&lgr->conns_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { INIT_LIST_HEAD(&lgr->sndbufs[i]); INIT_LIST_HEAD(&lgr->rmbs[i]); } lgr->next_link_id = 0; smc_lgr_list.num += SMC_LGR_NUM_INCR; memcpy(&lgr->id, (u8 *)&smc_lgr_list.num, SMC_LGR_ID_SIZE); INIT_DELAYED_WORK(&lgr->free_work, smc_lgr_free_work); INIT_WORK(&lgr->terminate_work, smc_lgr_terminate_work); lgr->conns_all = RB_ROOT; if (ini->is_smcd) { /* SMC-D specific settings */ smcd = ini->ism_dev[ini->ism_selected]; get_device(smcd->ops->get_dev(smcd)); lgr->peer_gid.gid = ini->ism_peer_gid[ini->ism_selected].gid; lgr->peer_gid.gid_ext = ini->ism_peer_gid[ini->ism_selected].gid_ext; lgr->smcd = ini->ism_dev[ini->ism_selected]; lgr_list = &ini->ism_dev[ini->ism_selected]->lgr_list; lgr_lock = &lgr->smcd->lgr_lock; lgr->smc_version = ini->smcd_version; lgr->peer_shutdown = 0; atomic_inc(&ini->ism_dev[ini->ism_selected]->lgr_cnt); } else { /* SMC-R specific settings */ struct smc_ib_device *ibdev; int ibport; lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT; lgr->smc_version = ini->smcr_version; memcpy(lgr->peer_systemid, ini->peer_systemid, SMC_SYSTEMID_LEN); if (lgr->smc_version == SMC_V2) { ibdev = ini->smcrv2.ib_dev_v2; ibport = ini->smcrv2.ib_port_v2; lgr->saddr = ini->smcrv2.saddr; lgr->uses_gateway = ini->smcrv2.uses_gateway; memcpy(lgr->nexthop_mac, ini->smcrv2.nexthop_mac, ETH_ALEN); lgr->max_conns = ini->max_conns; lgr->max_links = ini->max_links; } else { ibdev = ini->ib_dev; ibport = ini->ib_port; lgr->max_conns = SMC_CONN_PER_LGR_MAX; lgr->max_links = SMC_LINKS_ADD_LNK_MAX; } memcpy(lgr->pnet_id, ibdev->pnetid[ibport - 1], SMC_MAX_PNETID_LEN); rc = smc_wr_alloc_lgr_mem(lgr); if (rc) goto free_wq; smc_llc_lgr_init(lgr, smc); link_idx = SMC_SINGLE_LINK; lnk = &lgr->lnk[link_idx]; rc = smcr_link_init(lgr, lnk, link_idx, ini); if (rc) { smc_wr_free_lgr_mem(lgr); goto free_wq; } lgr->net = smc_ib_net(lnk->smcibdev); lgr_list = &smc_lgr_list.list; lgr_lock = &smc_lgr_list.lock; lgr->buf_type = lgr->net->smc.sysctl_smcr_buf_type; atomic_inc(&lgr_cnt); } smc->conn.lgr = lgr; spin_lock_bh(lgr_lock); list_add_tail(&lgr->list, lgr_list); spin_unlock_bh(lgr_lock); return 0; free_wq: destroy_workqueue(lgr->tx_wq); free_lgr: kfree(lgr); ism_put_vlan: if (ini->is_smcd && ini->vlan_id) smc_ism_put_vlan(ini->ism_dev[ini->ism_selected], ini->vlan_id); out: if (rc < 0) { if (rc == -ENOMEM) rc = SMC_CLC_DECL_MEM; else rc = SMC_CLC_DECL_INTERR; } return rc; } static int smc_write_space(struct smc_connection *conn) { int buffer_len = conn->peer_rmbe_size; union smc_host_cursor prod; union smc_host_cursor cons; int space; smc_curs_copy(&prod, &conn->local_tx_ctrl.prod, conn); smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn); /* determine rx_buf space */ space = buffer_len - smc_curs_diff(buffer_len, &cons, &prod); return space; } static int smc_switch_cursor(struct smc_sock *smc, struct smc_cdc_tx_pend *pend, struct smc_wr_buf *wr_buf) { struct smc_connection *conn = &smc->conn; union smc_host_cursor cons, fin; int rc = 0; int diff; smc_curs_copy(&conn->tx_curs_sent, &conn->tx_curs_fin, conn); smc_curs_copy(&fin, &conn->local_tx_ctrl_fin, conn); /* set prod cursor to old state, enforce tx_rdma_writes() */ smc_curs_copy(&conn->local_tx_ctrl.prod, &fin, conn); smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn); if (smc_curs_comp(conn->peer_rmbe_size, &cons, &fin) < 0) { /* cons cursor advanced more than fin, and prod was set * fin above, so now prod is smaller than cons. Fix that. */ diff = smc_curs_diff(conn->peer_rmbe_size, &fin, &cons); smc_curs_add(conn->sndbuf_desc->len, &conn->tx_curs_sent, diff); smc_curs_add(conn->sndbuf_desc->len, &conn->tx_curs_fin, diff); smp_mb__before_atomic(); atomic_add(diff, &conn->sndbuf_space); smp_mb__after_atomic(); smc_curs_add(conn->peer_rmbe_size, &conn->local_tx_ctrl.prod, diff); smc_curs_add(conn->peer_rmbe_size, &conn->local_tx_ctrl_fin, diff); } /* recalculate, value is used by tx_rdma_writes() */ atomic_set(&smc->conn.peer_rmbe_space, smc_write_space(conn)); if (smc->sk.sk_state != SMC_INIT && smc->sk.sk_state != SMC_CLOSED) { rc = smcr_cdc_msg_send_validation(conn, pend, wr_buf); if (!rc) { queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work, 0); smc->sk.sk_data_ready(&smc->sk); } } else { smc_wr_tx_put_slot(conn->lnk, (struct smc_wr_tx_pend_priv *)pend); } return rc; } void smc_switch_link_and_count(struct smc_connection *conn, struct smc_link *to_lnk) { atomic_dec(&conn->lnk->conn_cnt); /* link_hold in smc_conn_create() */ smcr_link_put(conn->lnk); conn->lnk = to_lnk; atomic_inc(&conn->lnk->conn_cnt); /* link_put in smc_conn_free() */ smcr_link_hold(conn->lnk); } struct smc_link *smc_switch_conns(struct smc_link_group *lgr, struct smc_link *from_lnk, bool is_dev_err) { struct smc_link *to_lnk = NULL; struct smc_cdc_tx_pend *pend; struct smc_connection *conn; struct smc_wr_buf *wr_buf; struct smc_sock *smc; struct rb_node *node; int i, rc = 0; /* link is inactive, wake up tx waiters */ smc_wr_wakeup_tx_wait(from_lnk); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_active(&lgr->lnk[i]) || i == from_lnk->link_idx) continue; if (is_dev_err && from_lnk->smcibdev == lgr->lnk[i].smcibdev && from_lnk->ibport == lgr->lnk[i].ibport) { continue; } to_lnk = &lgr->lnk[i]; break; } if (!to_lnk || !smc_wr_tx_link_hold(to_lnk)) { smc_lgr_terminate_sched(lgr); return NULL; } again: read_lock_bh(&lgr->conns_lock); for (node = rb_first(&lgr->conns_all); node; node = rb_next(node)) { conn = rb_entry(node, struct smc_connection, alert_node); if (conn->lnk != from_lnk) continue; smc = container_of(conn, struct smc_sock, conn); /* conn->lnk not yet set in SMC_INIT state */ if (smc->sk.sk_state == SMC_INIT) continue; if (smc->sk.sk_state == SMC_CLOSED || smc->sk.sk_state == SMC_PEERCLOSEWAIT1 || smc->sk.sk_state == SMC_PEERCLOSEWAIT2 || smc->sk.sk_state == SMC_APPFINCLOSEWAIT || smc->sk.sk_state == SMC_APPCLOSEWAIT1 || smc->sk.sk_state == SMC_APPCLOSEWAIT2 || smc->sk.sk_state == SMC_PEERFINCLOSEWAIT || smc->sk.sk_state == SMC_PEERABORTWAIT || smc->sk.sk_state == SMC_PROCESSABORT) { spin_lock_bh(&conn->send_lock); smc_switch_link_and_count(conn, to_lnk); spin_unlock_bh(&conn->send_lock); continue; } sock_hold(&smc->sk); read_unlock_bh(&lgr->conns_lock); /* pre-fetch buffer outside of send_lock, might sleep */ rc = smc_cdc_get_free_slot(conn, to_lnk, &wr_buf, NULL, &pend); if (rc) goto err_out; /* avoid race with smcr_tx_sndbuf_nonempty() */ spin_lock_bh(&conn->send_lock); smc_switch_link_and_count(conn, to_lnk); rc = smc_switch_cursor(smc, pend, wr_buf); spin_unlock_bh(&conn->send_lock); sock_put(&smc->sk); if (rc) goto err_out; goto again; } read_unlock_bh(&lgr->conns_lock); smc_wr_tx_link_put(to_lnk); return to_lnk; err_out: smcr_link_down_cond_sched(to_lnk); smc_wr_tx_link_put(to_lnk); return NULL; } static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, struct smc_link_group *lgr) { struct rw_semaphore *lock; /* lock buffer list */ int rc; if (is_rmb && buf_desc->is_conf_rkey && !list_empty(&lgr->list)) { /* unregister rmb with peer */ rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY); if (!rc) { /* protect against smc_llc_cli_rkey_exchange() */ down_read(&lgr->llc_conf_mutex); smc_llc_do_delete_rkey(lgr, buf_desc); buf_desc->is_conf_rkey = false; up_read(&lgr->llc_conf_mutex); smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl); } } if (buf_desc->is_reg_err) { /* buf registration failed, reuse not possible */ lock = is_rmb ? &lgr->rmbs_lock : &lgr->sndbufs_lock; down_write(lock); list_del(&buf_desc->list); up_write(lock); smc_buf_free(lgr, is_rmb, buf_desc); } else { /* memzero_explicit provides potential memory barrier semantics */ memzero_explicit(buf_desc->cpu_addr, buf_desc->len); WRITE_ONCE(buf_desc->used, 0); } } static void smcd_buf_detach(struct smc_connection *conn) { struct smcd_dev *smcd = conn->lgr->smcd; u64 peer_token = conn->peer_token; if (!conn->sndbuf_desc) return; smc_ism_detach_dmb(smcd, peer_token); kfree(conn->sndbuf_desc); conn->sndbuf_desc = NULL; } static void smc_buf_unuse(struct smc_connection *conn, struct smc_link_group *lgr) { if (conn->sndbuf_desc) { if (!lgr->is_smcd && conn->sndbuf_desc->is_vm) { smcr_buf_unuse(conn->sndbuf_desc, false, lgr); } else { memzero_explicit(conn->sndbuf_desc->cpu_addr, conn->sndbuf_desc->len); WRITE_ONCE(conn->sndbuf_desc->used, 0); } } if (conn->rmb_desc) { if (!lgr->is_smcd) { smcr_buf_unuse(conn->rmb_desc, true, lgr); } else { memzero_explicit(conn->rmb_desc->cpu_addr, conn->rmb_desc->len + sizeof(struct smcd_cdc_msg)); WRITE_ONCE(conn->rmb_desc->used, 0); } } } /* remove a finished connection from its link group */ void smc_conn_free(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; if (!lgr || conn->freed) /* Connection has never been registered in a * link group, or has already been freed. */ return; conn->freed = 1; if (!smc_conn_lgr_valid(conn)) /* Connection has already unregistered from * link group. */ goto lgr_put; if (lgr->is_smcd) { if (!list_empty(&lgr->list)) smc_ism_unset_conn(conn); if (smc_ism_support_dmb_nocopy(lgr->smcd)) smcd_buf_detach(conn); tasklet_kill(&conn->rx_tsklet); } else { smc_cdc_wait_pend_tx_wr(conn); if (current_work() != &conn->abort_work) cancel_work_sync(&conn->abort_work); } if (!list_empty(&lgr->list)) { smc_buf_unuse(conn, lgr); /* allow buffer reuse */ smc_lgr_unregister_conn(conn); } if (!lgr->conns_num) smc_lgr_schedule_free_work(lgr); lgr_put: if (!lgr->is_smcd) smcr_link_put(conn->lnk); /* link_hold in smc_conn_create() */ smc_lgr_put(lgr); /* lgr_hold in smc_conn_create() */ } /* unregister a link from a buf_desc */ static void smcr_buf_unmap_link(struct smc_buf_desc *buf_desc, bool is_rmb, struct smc_link *lnk) { if (is_rmb || buf_desc->is_vm) buf_desc->is_reg_mr[lnk->link_idx] = false; if (!buf_desc->is_map_ib[lnk->link_idx]) return; if ((is_rmb || buf_desc->is_vm) && buf_desc->mr[lnk->link_idx]) { smc_ib_put_memory_region(buf_desc->mr[lnk->link_idx]); buf_desc->mr[lnk->link_idx] = NULL; } if (is_rmb) smc_ib_buf_unmap_sg(lnk, buf_desc, DMA_FROM_DEVICE); else smc_ib_buf_unmap_sg(lnk, buf_desc, DMA_TO_DEVICE); sg_free_table(&buf_desc->sgt[lnk->link_idx]); buf_desc->is_map_ib[lnk->link_idx] = false; } /* unmap all buffers of lgr for a deleted link */ static void smcr_buf_unmap_lgr(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; struct smc_buf_desc *buf_desc, *bf; int i; for (i = 0; i < SMC_RMBE_SIZES; i++) { down_write(&lgr->rmbs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) smcr_buf_unmap_link(buf_desc, true, lnk); up_write(&lgr->rmbs_lock); down_write(&lgr->sndbufs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) smcr_buf_unmap_link(buf_desc, false, lnk); up_write(&lgr->sndbufs_lock); } } static void smcr_rtoken_clear_link(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; int i; for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) { lgr->rtokens[i][lnk->link_idx].rkey = 0; lgr->rtokens[i][lnk->link_idx].dma_addr = 0; } } static void __smcr_link_clear(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; struct smc_ib_device *smcibdev; smc_wr_free_link_mem(lnk); smc_ibdev_cnt_dec(lnk); put_device(&lnk->smcibdev->ibdev->dev); smcibdev = lnk->smcibdev; memset(lnk, 0, sizeof(struct smc_link)); lnk->state = SMC_LNK_UNUSED; if (!atomic_dec_return(&smcibdev->lnk_cnt)) wake_up(&smcibdev->lnks_deleted); smc_lgr_put(lgr); /* lgr_hold in smcr_link_init() */ } /* must be called under lgr->llc_conf_mutex lock */ void smcr_link_clear(struct smc_link *lnk, bool log) { if (!lnk->lgr || lnk->clearing || lnk->state == SMC_LNK_UNUSED) return; lnk->clearing = 1; lnk->peer_qpn = 0; smc_llc_link_clear(lnk, log); smcr_buf_unmap_lgr(lnk); smcr_rtoken_clear_link(lnk); smc_ib_modify_qp_error(lnk); smc_wr_free_link(lnk); smc_ib_destroy_queue_pair(lnk); smc_ib_dealloc_protection_domain(lnk); smcr_link_put(lnk); /* theoretically last link_put */ } void smcr_link_hold(struct smc_link *lnk) { refcount_inc(&lnk->refcnt); } void smcr_link_put(struct smc_link *lnk) { if (refcount_dec_and_test(&lnk->refcnt)) __smcr_link_clear(lnk); } static void smcr_buf_free(struct smc_link_group *lgr, bool is_rmb, struct smc_buf_desc *buf_desc) { int i; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) smcr_buf_unmap_link(buf_desc, is_rmb, &lgr->lnk[i]); if (!buf_desc->is_vm && buf_desc->pages) __free_pages(buf_desc->pages, buf_desc->order); else if (buf_desc->is_vm && buf_desc->cpu_addr) vfree(buf_desc->cpu_addr); kfree(buf_desc); } static void smcd_buf_free(struct smc_link_group *lgr, bool is_dmb, struct smc_buf_desc *buf_desc) { if (is_dmb) { /* restore original buf len */ buf_desc->len += sizeof(struct smcd_cdc_msg); smc_ism_unregister_dmb(lgr->smcd, buf_desc); } else { kfree(buf_desc->cpu_addr); } kfree(buf_desc); } static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, struct smc_buf_desc *buf_desc) { if (lgr->is_smcd) smcd_buf_free(lgr, is_rmb, buf_desc); else smcr_buf_free(lgr, is_rmb, buf_desc); } static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb) { struct smc_buf_desc *buf_desc, *bf_desc; struct list_head *buf_list; int i; for (i = 0; i < SMC_RMBE_SIZES; i++) { if (is_rmb) buf_list = &lgr->rmbs[i]; else buf_list = &lgr->sndbufs[i]; list_for_each_entry_safe(buf_desc, bf_desc, buf_list, list) { list_del(&buf_desc->list); smc_buf_free(lgr, is_rmb, buf_desc); } } } static void smc_lgr_free_bufs(struct smc_link_group *lgr) { /* free send buffers */ __smc_lgr_free_bufs(lgr, false); /* free rmbs */ __smc_lgr_free_bufs(lgr, true); } /* won't be freed until no one accesses to lgr anymore */ static void __smc_lgr_free(struct smc_link_group *lgr) { smc_lgr_free_bufs(lgr); if (lgr->is_smcd) { if (!atomic_dec_return(&lgr->smcd->lgr_cnt)) wake_up(&lgr->smcd->lgrs_deleted); } else { smc_wr_free_lgr_mem(lgr); if (!atomic_dec_return(&lgr_cnt)) wake_up(&lgrs_deleted); } kfree(lgr); } /* remove a link group */ static void smc_lgr_free(struct smc_link_group *lgr) { int i; if (!lgr->is_smcd) { down_write(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (lgr->lnk[i].state != SMC_LNK_UNUSED) smcr_link_clear(&lgr->lnk[i], false); } up_write(&lgr->llc_conf_mutex); smc_llc_lgr_clear(lgr); } destroy_workqueue(lgr->tx_wq); if (lgr->is_smcd) { smc_ism_put_vlan(lgr->smcd, lgr->vlan_id); put_device(lgr->smcd->ops->get_dev(lgr->smcd)); } smc_lgr_put(lgr); /* theoretically last lgr_put */ } void smc_lgr_hold(struct smc_link_group *lgr) { refcount_inc(&lgr->refcnt); } void smc_lgr_put(struct smc_link_group *lgr) { if (refcount_dec_and_test(&lgr->refcnt)) __smc_lgr_free(lgr); } static void smc_sk_wake_ups(struct smc_sock *smc) { smc->sk.sk_write_space(&smc->sk); smc->sk.sk_data_ready(&smc->sk); smc->sk.sk_state_change(&smc->sk); } /* kill a connection */ static void smc_conn_kill(struct smc_connection *conn, bool soft) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); if (conn->lgr->is_smcd && conn->lgr->peer_shutdown) conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; else smc_close_abort(conn); conn->killed = 1; smc->sk.sk_err = ECONNABORTED; smc_sk_wake_ups(smc); if (conn->lgr->is_smcd) { smc_ism_unset_conn(conn); if (smc_ism_support_dmb_nocopy(conn->lgr->smcd)) smcd_buf_detach(conn); if (soft) tasklet_kill(&conn->rx_tsklet); else tasklet_unlock_wait(&conn->rx_tsklet); } else { smc_cdc_wait_pend_tx_wr(conn); } smc_lgr_unregister_conn(conn); smc_close_active_abort(smc); } static void smc_lgr_cleanup(struct smc_link_group *lgr) { if (lgr->is_smcd) { smc_ism_signal_shutdown(lgr); } else { u32 rsn = lgr->llc_termination_rsn; if (!rsn) rsn = SMC_LLC_DEL_PROG_INIT_TERM; smc_llc_send_link_delete_all(lgr, false, rsn); smcr_lgr_link_deactivate_all(lgr); } } /* terminate link group * @soft: true if link group shutdown can take its time * false if immediate link group shutdown is required */ static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft) { struct smc_connection *conn; struct smc_sock *smc; struct rb_node *node; if (lgr->terminating) return; /* lgr already terminating */ /* cancel free_work sync, will terminate when lgr->freeing is set */ cancel_delayed_work(&lgr->free_work); lgr->terminating = 1; /* kill remaining link group connections */ read_lock_bh(&lgr->conns_lock); node = rb_first(&lgr->conns_all); while (node) { read_unlock_bh(&lgr->conns_lock); conn = rb_entry(node, struct smc_connection, alert_node); smc = container_of(conn, struct smc_sock, conn); sock_hold(&smc->sk); /* sock_put below */ lock_sock(&smc->sk); smc_conn_kill(conn, soft); release_sock(&smc->sk); sock_put(&smc->sk); /* sock_hold above */ read_lock_bh(&lgr->conns_lock); node = rb_first(&lgr->conns_all); } read_unlock_bh(&lgr->conns_lock); smc_lgr_cleanup(lgr); smc_lgr_free(lgr); } /* unlink link group and schedule termination */ void smc_lgr_terminate_sched(struct smc_link_group *lgr) { spinlock_t *lgr_lock; smc_lgr_list_head(lgr, &lgr_lock); spin_lock_bh(lgr_lock); if (list_empty(&lgr->list) || lgr->terminating || lgr->freeing) { spin_unlock_bh(lgr_lock); return; /* lgr already terminating */ } list_del_init(&lgr->list); lgr->freeing = 1; spin_unlock_bh(lgr_lock); schedule_work(&lgr->terminate_work); } /* Called when peer lgr shutdown (regularly or abnormally) is received */ void smc_smcd_terminate(struct smcd_dev *dev, struct smcd_gid *peer_gid, unsigned short vlan) { struct smc_link_group *lgr, *l; LIST_HEAD(lgr_free_list); /* run common cleanup function and build free list */ spin_lock_bh(&dev->lgr_lock); list_for_each_entry_safe(lgr, l, &dev->lgr_list, list) { if ((!peer_gid->gid || (lgr->peer_gid.gid == peer_gid->gid && !smc_ism_is_emulated(dev) ? 1 : lgr->peer_gid.gid_ext == peer_gid->gid_ext)) && (vlan == VLAN_VID_MASK || lgr->vlan_id == vlan)) { if (peer_gid->gid) /* peer triggered termination */ lgr->peer_shutdown = 1; list_move(&lgr->list, &lgr_free_list); lgr->freeing = 1; } } spin_unlock_bh(&dev->lgr_lock); /* cancel the regular free workers and actually free lgrs */ list_for_each_entry_safe(lgr, l, &lgr_free_list, list) { list_del_init(&lgr->list); schedule_work(&lgr->terminate_work); } } /* Called when an SMCD device is removed or the smc module is unloaded */ void smc_smcd_terminate_all(struct smcd_dev *smcd) { struct smc_link_group *lgr, *lg; LIST_HEAD(lgr_free_list); spin_lock_bh(&smcd->lgr_lock); list_splice_init(&smcd->lgr_list, &lgr_free_list); list_for_each_entry(lgr, &lgr_free_list, list) lgr->freeing = 1; spin_unlock_bh(&smcd->lgr_lock); list_for_each_entry_safe(lgr, lg, &lgr_free_list, list) { list_del_init(&lgr->list); __smc_lgr_terminate(lgr, false); } if (atomic_read(&smcd->lgr_cnt)) wait_event(smcd->lgrs_deleted, !atomic_read(&smcd->lgr_cnt)); } /* Called when an SMCR device is removed or the smc module is unloaded. * If smcibdev is given, all SMCR link groups using this device are terminated. * If smcibdev is NULL, all SMCR link groups are terminated. */ void smc_smcr_terminate_all(struct smc_ib_device *smcibdev) { struct smc_link_group *lgr, *lg; LIST_HEAD(lgr_free_list); int i; spin_lock_bh(&smc_lgr_list.lock); if (!smcibdev) { list_splice_init(&smc_lgr_list.list, &lgr_free_list); list_for_each_entry(lgr, &lgr_free_list, list) lgr->freeing = 1; } else { list_for_each_entry_safe(lgr, lg, &smc_lgr_list.list, list) { for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (lgr->lnk[i].smcibdev == smcibdev) smcr_link_down_cond_sched(&lgr->lnk[i]); } } } spin_unlock_bh(&smc_lgr_list.lock); list_for_each_entry_safe(lgr, lg, &lgr_free_list, list) { list_del_init(&lgr->list); smc_llc_set_termination_rsn(lgr, SMC_LLC_DEL_OP_INIT_TERM); __smc_lgr_terminate(lgr, false); } if (smcibdev) { if (atomic_read(&smcibdev->lnk_cnt)) wait_event(smcibdev->lnks_deleted, !atomic_read(&smcibdev->lnk_cnt)); } else { if (atomic_read(&lgr_cnt)) wait_event(lgrs_deleted, !atomic_read(&lgr_cnt)); } } /* set new lgr type and clear all asymmetric link tagging */ void smcr_lgr_set_type(struct smc_link_group *lgr, enum smc_lgr_type new_type) { char *lgr_type = ""; int i; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) if (smc_link_usable(&lgr->lnk[i])) lgr->lnk[i].link_is_asym = false; if (lgr->type == new_type) return; lgr->type = new_type; switch (lgr->type) { case SMC_LGR_NONE: lgr_type = "NONE"; break; case SMC_LGR_SINGLE: lgr_type = "SINGLE"; break; case SMC_LGR_SYMMETRIC: lgr_type = "SYMMETRIC"; break; case SMC_LGR_ASYMMETRIC_PEER: lgr_type = "ASYMMETRIC_PEER"; break; case SMC_LGR_ASYMMETRIC_LOCAL: lgr_type = "ASYMMETRIC_LOCAL"; break; } pr_warn_ratelimited("smc: SMC-R lg %*phN net %llu state changed: " "%s, pnetid %.16s\n", SMC_LGR_ID_SIZE, &lgr->id, lgr->net->net_cookie, lgr_type, lgr->pnet_id); } /* set new lgr type and tag a link as asymmetric */ void smcr_lgr_set_type_asym(struct smc_link_group *lgr, enum smc_lgr_type new_type, int asym_lnk_idx) { smcr_lgr_set_type(lgr, new_type); lgr->lnk[asym_lnk_idx].link_is_asym = true; } /* abort connection, abort_work scheduled from tasklet context */ static void smc_conn_abort_work(struct work_struct *work) { struct smc_connection *conn = container_of(work, struct smc_connection, abort_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn); lock_sock(&smc->sk); smc_conn_kill(conn, true); release_sock(&smc->sk); sock_put(&smc->sk); /* sock_hold done by schedulers of abort_work */ } void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport) { struct smc_link_group *lgr, *n; spin_lock_bh(&smc_lgr_list.lock); list_for_each_entry_safe(lgr, n, &smc_lgr_list.list, list) { struct smc_link *link; if (strncmp(smcibdev->pnetid[ibport - 1], lgr->pnet_id, SMC_MAX_PNETID_LEN) || lgr->type == SMC_LGR_SYMMETRIC || lgr->type == SMC_LGR_ASYMMETRIC_PEER || !rdma_dev_access_netns(smcibdev->ibdev, lgr->net)) continue; if (lgr->type == SMC_LGR_SINGLE && lgr->max_links <= 1) continue; /* trigger local add link processing */ link = smc_llc_usable_link(lgr); if (link) smc_llc_add_link_local(link); } spin_unlock_bh(&smc_lgr_list.lock); } /* link is down - switch connections to alternate link, * must be called under lgr->llc_conf_mutex lock */ static void smcr_link_down(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; struct smc_link *to_lnk; int del_link_id; if (!lgr || lnk->state == SMC_LNK_UNUSED || list_empty(&lgr->list)) return; to_lnk = smc_switch_conns(lgr, lnk, true); if (!to_lnk) { /* no backup link available */ smcr_link_clear(lnk, true); return; } smcr_lgr_set_type(lgr, SMC_LGR_SINGLE); del_link_id = lnk->link_id; if (lgr->role == SMC_SERV) { /* trigger local delete link processing */ smc_llc_srv_delete_link_local(to_lnk, del_link_id); } else { if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { /* another llc task is ongoing */ up_write(&lgr->llc_conf_mutex); wait_event_timeout(lgr->llc_flow_waiter, (list_empty(&lgr->list) || lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE), SMC_LLC_WAIT_TIME); down_write(&lgr->llc_conf_mutex); } if (!list_empty(&lgr->list)) { smc_llc_send_delete_link(to_lnk, del_link_id, SMC_LLC_REQ, true, SMC_LLC_DEL_LOST_PATH); smcr_link_clear(lnk, true); } wake_up(&lgr->llc_flow_waiter); /* wake up next waiter */ } } /* must be called under lgr->llc_conf_mutex lock */ void smcr_link_down_cond(struct smc_link *lnk) { if (smc_link_downing(&lnk->state)) { trace_smcr_link_down(lnk, __builtin_return_address(0)); smcr_link_down(lnk); } } /* will get the lgr->llc_conf_mutex lock */ void smcr_link_down_cond_sched(struct smc_link *lnk) { if (smc_link_downing(&lnk->state)) { trace_smcr_link_down(lnk, __builtin_return_address(0)); schedule_work(&lnk->link_down_wrk); } } void smcr_port_err(struct smc_ib_device *smcibdev, u8 ibport) { struct smc_link_group *lgr, *n; int i; list_for_each_entry_safe(lgr, n, &smc_lgr_list.list, list) { if (strncmp(smcibdev->pnetid[ibport - 1], lgr->pnet_id, SMC_MAX_PNETID_LEN)) continue; /* lgr is not affected */ if (list_empty(&lgr->list)) continue; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &lgr->lnk[i]; if (smc_link_usable(lnk) && lnk->smcibdev == smcibdev && lnk->ibport == ibport) smcr_link_down_cond_sched(lnk); } } } static void smc_link_down_work(struct work_struct *work) { struct smc_link *link = container_of(work, struct smc_link, link_down_wrk); struct smc_link_group *lgr = link->lgr; if (list_empty(&lgr->list)) return; wake_up_all(&lgr->llc_msg_waiter); down_write(&lgr->llc_conf_mutex); smcr_link_down(link); up_write(&lgr->llc_conf_mutex); } static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev, struct netdev_nested_priv *priv) { unsigned short *vlan_id = (unsigned short *)priv->data; if (is_vlan_dev(lower_dev)) { *vlan_id = vlan_dev_vlan_id(lower_dev); return 1; } return 0; } /* Determine vlan of internal TCP socket. */ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(clcsock->sk); struct netdev_nested_priv priv; struct net_device *ndev; int rc = 0; ini->vlan_id = 0; if (!dst) { rc = -ENOTCONN; goto out; } if (!dst->dev) { rc = -ENODEV; goto out_rel; } ndev = dst->dev; if (is_vlan_dev(ndev)) { ini->vlan_id = vlan_dev_vlan_id(ndev); goto out_rel; } priv.data = (void *)&ini->vlan_id; rtnl_lock(); netdev_walk_all_lower_dev(ndev, smc_vlan_by_tcpsk_walk, &priv); rtnl_unlock(); out_rel: dst_release(dst); out: return rc; } static bool smcr_lgr_match(struct smc_link_group *lgr, u8 smcr_version, u8 peer_systemid[], u8 peer_gid[], u8 peer_mac_v1[], enum smc_lgr_role role, u32 clcqpn, struct net *net) { struct smc_link *lnk; int i; if (memcmp(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN) || lgr->role != role) return false; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { lnk = &lgr->lnk[i]; if (!smc_link_active(lnk)) continue; /* use verbs API to check netns, instead of lgr->net */ if (!rdma_dev_access_netns(lnk->smcibdev->ibdev, net)) return false; if ((lgr->role == SMC_SERV || lnk->peer_qpn == clcqpn) && !memcmp(lnk->peer_gid, peer_gid, SMC_GID_SIZE) && (smcr_version == SMC_V2 || !memcmp(lnk->peer_mac, peer_mac_v1, ETH_ALEN))) return true; } return false; } static bool smcd_lgr_match(struct smc_link_group *lgr, struct smcd_dev *smcismdev, struct smcd_gid *peer_gid) { if (lgr->peer_gid.gid != peer_gid->gid || lgr->smcd != smcismdev) return false; if (smc_ism_is_emulated(smcismdev) && lgr->peer_gid.gid_ext != peer_gid->gid_ext) return false; return true; } /* create a new SMC connection (and a new link group if necessary) */ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) { struct smc_connection *conn = &smc->conn; struct net *net = sock_net(&smc->sk); struct list_head *lgr_list; struct smc_link_group *lgr; enum smc_lgr_role role; spinlock_t *lgr_lock; int rc = 0; lgr_list = ini->is_smcd ? &ini->ism_dev[ini->ism_selected]->lgr_list : &smc_lgr_list.list; lgr_lock = ini->is_smcd ? &ini->ism_dev[ini->ism_selected]->lgr_lock : &smc_lgr_list.lock; ini->first_contact_local = 1; role = smc->listen_smc ? SMC_SERV : SMC_CLNT; if (role == SMC_CLNT && ini->first_contact_peer) /* create new link group as well */ goto create; /* determine if an existing link group can be reused */ spin_lock_bh(lgr_lock); list_for_each_entry(lgr, lgr_list, list) { write_lock_bh(&lgr->conns_lock); if ((ini->is_smcd ? smcd_lgr_match(lgr, ini->ism_dev[ini->ism_selected], &ini->ism_peer_gid[ini->ism_selected]) : smcr_lgr_match(lgr, ini->smcr_version, ini->peer_systemid, ini->peer_gid, ini->peer_mac, role, ini->ib_clcqpn, net)) && !lgr->sync_err && (ini->smcd_version == SMC_V2 || lgr->vlan_id == ini->vlan_id) && (role == SMC_CLNT || ini->is_smcd || (lgr->conns_num < lgr->max_conns && !bitmap_full(lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX)))) { /* link group found */ ini->first_contact_local = 0; conn->lgr = lgr; rc = smc_lgr_register_conn(conn, false); write_unlock_bh(&lgr->conns_lock); if (!rc && delayed_work_pending(&lgr->free_work)) cancel_delayed_work(&lgr->free_work); break; } write_unlock_bh(&lgr->conns_lock); } spin_unlock_bh(lgr_lock); if (rc) return rc; if (role == SMC_CLNT && !ini->first_contact_peer && ini->first_contact_local) { /* Server reuses a link group, but Client wants to start * a new one * send out_of_sync decline, reason synchr. error */ return SMC_CLC_DECL_SYNCERR; } create: if (ini->first_contact_local) { rc = smc_lgr_create(smc, ini); if (rc) goto out; lgr = conn->lgr; write_lock_bh(&lgr->conns_lock); rc = smc_lgr_register_conn(conn, true); write_unlock_bh(&lgr->conns_lock); if (rc) { smc_lgr_cleanup_early(lgr); goto out; } } smc_lgr_hold(conn->lgr); /* lgr_put in smc_conn_free() */ if (!conn->lgr->is_smcd) smcr_link_hold(conn->lnk); /* link_put in smc_conn_free() */ conn->freed = 0; conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE; conn->local_tx_ctrl.len = SMC_WR_TX_SIZE; conn->urg_state = SMC_URG_READ; init_waitqueue_head(&conn->cdc_pend_tx_wq); INIT_WORK(&smc->conn.abort_work, smc_conn_abort_work); if (ini->is_smcd) { conn->rx_off = sizeof(struct smcd_cdc_msg); smcd_cdc_rx_init(conn); /* init tasklet for this conn */ } else { conn->rx_off = 0; } #ifndef KERNEL_HAS_ATOMIC64 spin_lock_init(&conn->acurs_lock); #endif out: return rc; } #define SMCD_DMBE_SIZES 6 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ #define SMCR_RMBE_SIZES 5 /* 0 -> 16KB, 1 -> 32KB, .. 5 -> 512KB */ /* convert the RMB size into the compressed notation (minimum 16K, see * SMCD/R_DMBE_SIZES. * In contrast to plain ilog2, this rounds towards the next power of 2, * so the socket application gets at least its desired sndbuf / rcvbuf size. */ static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb) { const unsigned int max_scat = SG_MAX_SINGLE_ALLOC * PAGE_SIZE; u8 compressed; if (size <= SMC_BUF_MIN_SIZE) return 0; size = (size - 1) >> 14; /* convert to 16K multiple */ compressed = min_t(u8, ilog2(size) + 1, is_smcd ? SMCD_DMBE_SIZES : SMCR_RMBE_SIZES); if (!is_smcd && is_rmb) /* RMBs are backed by & limited to max size of scatterlists */ compressed = min_t(u8, compressed, ilog2(max_scat >> 14)); return compressed; } /* convert the RMB size from compressed notation into integer */ int smc_uncompress_bufsize(u8 compressed) { u32 size; size = 0x00000001 << (((int)compressed) + 14); return (int)size; } /* try to reuse a sndbuf or rmb description slot for a certain * buffer size; if not available, return NULL */ static struct smc_buf_desc *smc_buf_get_slot(int compressed_bufsize, struct rw_semaphore *lock, struct list_head *buf_list) { struct smc_buf_desc *buf_slot; down_read(lock); list_for_each_entry(buf_slot, buf_list, list) { if (cmpxchg(&buf_slot->used, 0, 1) == 0) { up_read(lock); return buf_slot; } } up_read(lock); return NULL; } /* one of the conditions for announcing a receiver's current window size is * that it "results in a minimum increase in the window size of 10% of the * receive buffer space" [RFC7609] */ static inline int smc_rmb_wnd_update_limit(int rmbe_size) { return max_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2); } /* map an buf to a link */ static int smcr_buf_map_link(struct smc_buf_desc *buf_desc, bool is_rmb, struct smc_link *lnk) { int rc, i, nents, offset, buf_size, size, access_flags; struct scatterlist *sg; void *buf; if (buf_desc->is_map_ib[lnk->link_idx]) return 0; if (buf_desc->is_vm) { buf = buf_desc->cpu_addr; buf_size = buf_desc->len; offset = offset_in_page(buf_desc->cpu_addr); nents = PAGE_ALIGN(buf_size + offset) / PAGE_SIZE; } else { nents = 1; } rc = sg_alloc_table(&buf_desc->sgt[lnk->link_idx], nents, GFP_KERNEL); if (rc) return rc; if (buf_desc->is_vm) { /* virtually contiguous buffer */ for_each_sg(buf_desc->sgt[lnk->link_idx].sgl, sg, nents, i) { size = min_t(int, PAGE_SIZE - offset, buf_size); sg_set_page(sg, vmalloc_to_page(buf), size, offset); buf += size / sizeof(*buf); buf_size -= size; offset = 0; } } else { /* physically contiguous buffer */ sg_set_buf(buf_desc->sgt[lnk->link_idx].sgl, buf_desc->cpu_addr, buf_desc->len); } /* map sg table to DMA address */ rc = smc_ib_buf_map_sg(lnk, buf_desc, is_rmb ? DMA_FROM_DEVICE : DMA_TO_DEVICE); /* SMC protocol depends on mapping to one DMA address only */ if (rc != nents) { rc = -EAGAIN; goto free_table; } buf_desc->is_dma_need_sync |= smc_ib_is_sg_need_sync(lnk, buf_desc) << lnk->link_idx; if (is_rmb || buf_desc->is_vm) { /* create a new memory region for the RMB or vzalloced sndbuf */ access_flags = is_rmb ? IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE : IB_ACCESS_LOCAL_WRITE; rc = smc_ib_get_memory_region(lnk->roce_pd, access_flags, buf_desc, lnk->link_idx); if (rc) goto buf_unmap; smc_ib_sync_sg_for_device(lnk, buf_desc, is_rmb ? DMA_FROM_DEVICE : DMA_TO_DEVICE); } buf_desc->is_map_ib[lnk->link_idx] = true; return 0; buf_unmap: smc_ib_buf_unmap_sg(lnk, buf_desc, is_rmb ? DMA_FROM_DEVICE : DMA_TO_DEVICE); free_table: sg_free_table(&buf_desc->sgt[lnk->link_idx]); return rc; } /* register a new buf on IB device, rmb or vzalloced sndbuf * must be called under lgr->llc_conf_mutex lock */ int smcr_link_reg_buf(struct smc_link *link, struct smc_buf_desc *buf_desc) { if (list_empty(&link->lgr->list)) return -ENOLINK; if (!buf_desc->is_reg_mr[link->link_idx]) { /* register memory region for new buf */ if (buf_desc->is_vm) buf_desc->mr[link->link_idx]->iova = (uintptr_t)buf_desc->cpu_addr; if (smc_wr_reg_send(link, buf_desc->mr[link->link_idx])) { buf_desc->is_reg_err = true; return -EFAULT; } buf_desc->is_reg_mr[link->link_idx] = true; } return 0; } static int _smcr_buf_map_lgr(struct smc_link *lnk, struct rw_semaphore *lock, struct list_head *lst, bool is_rmb) { struct smc_buf_desc *buf_desc, *bf; int rc = 0; down_write(lock); list_for_each_entry_safe(buf_desc, bf, lst, list) { if (!buf_desc->used) continue; rc = smcr_buf_map_link(buf_desc, is_rmb, lnk); if (rc) goto out; } out: up_write(lock); return rc; } /* map all used buffers of lgr for a new link */ int smcr_buf_map_lgr(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; int i, rc = 0; for (i = 0; i < SMC_RMBE_SIZES; i++) { rc = _smcr_buf_map_lgr(lnk, &lgr->rmbs_lock, &lgr->rmbs[i], true); if (rc) return rc; rc = _smcr_buf_map_lgr(lnk, &lgr->sndbufs_lock, &lgr->sndbufs[i], false); if (rc) return rc; } return 0; } /* register all used buffers of lgr for a new link, * must be called under lgr->llc_conf_mutex lock */ int smcr_buf_reg_lgr(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; struct smc_buf_desc *buf_desc, *bf; int i, rc = 0; /* reg all RMBs for a new link */ down_write(&lgr->rmbs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) { if (!buf_desc->used) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { up_write(&lgr->rmbs_lock); return rc; } } } up_write(&lgr->rmbs_lock); if (lgr->buf_type == SMCR_PHYS_CONT_BUFS) return rc; /* reg all vzalloced sndbufs for a new link */ down_write(&lgr->sndbufs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) { if (!buf_desc->used || !buf_desc->is_vm) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { up_write(&lgr->sndbufs_lock); return rc; } } } up_write(&lgr->sndbufs_lock); return rc; } static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr, bool is_rmb, int bufsize) { struct smc_buf_desc *buf_desc; /* try to alloc a new buffer */ buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL); if (!buf_desc) return ERR_PTR(-ENOMEM); switch (lgr->buf_type) { case SMCR_PHYS_CONT_BUFS: case SMCR_MIXED_BUFS: buf_desc->order = get_order(bufsize); buf_desc->pages = alloc_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_NOMEMALLOC | __GFP_COMP | __GFP_NORETRY | __GFP_ZERO, buf_desc->order); if (buf_desc->pages) { buf_desc->cpu_addr = (void *)page_address(buf_desc->pages); buf_desc->len = bufsize; buf_desc->is_vm = false; break; } if (lgr->buf_type == SMCR_PHYS_CONT_BUFS) goto out; fallthrough; // try virtually continguous buf case SMCR_VIRT_CONT_BUFS: buf_desc->order = get_order(bufsize); buf_desc->cpu_addr = vzalloc(PAGE_SIZE << buf_desc->order); if (!buf_desc->cpu_addr) goto out; buf_desc->pages = NULL; buf_desc->len = bufsize; buf_desc->is_vm = true; break; } return buf_desc; out: kfree(buf_desc); return ERR_PTR(-EAGAIN); } /* map buf_desc on all usable links, * unused buffers stay mapped as long as the link is up */ static int smcr_buf_map_usable_links(struct smc_link_group *lgr, struct smc_buf_desc *buf_desc, bool is_rmb) { int i, rc = 0, cnt = 0; /* protect against parallel link reconfiguration */ down_read(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &lgr->lnk[i]; if (!smc_link_usable(lnk)) continue; if (smcr_buf_map_link(buf_desc, is_rmb, lnk)) { rc = -ENOMEM; goto out; } cnt++; } out: up_read(&lgr->llc_conf_mutex); if (!rc && !cnt) rc = -EINVAL; return rc; } static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr, bool is_dmb, int bufsize) { struct smc_buf_desc *buf_desc; int rc; /* try to alloc a new DMB */ buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL); if (!buf_desc) return ERR_PTR(-ENOMEM); if (is_dmb) { rc = smc_ism_register_dmb(lgr, bufsize, buf_desc); if (rc) { kfree(buf_desc); if (rc == -ENOMEM) return ERR_PTR(-EAGAIN); if (rc == -ENOSPC) return ERR_PTR(-ENOSPC); return ERR_PTR(-EIO); } buf_desc->pages = virt_to_page(buf_desc->cpu_addr); /* CDC header stored in buf. So, pretend it was smaller */ buf_desc->len = bufsize - sizeof(struct smcd_cdc_msg); } else { buf_desc->cpu_addr = kzalloc(bufsize, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC); if (!buf_desc->cpu_addr) { kfree(buf_desc); return ERR_PTR(-EAGAIN); } buf_desc->len = bufsize; } return buf_desc; } static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) { struct smc_buf_desc *buf_desc = ERR_PTR(-ENOMEM); struct smc_connection *conn = &smc->conn; struct smc_link_group *lgr = conn->lgr; struct list_head *buf_list; int bufsize, bufsize_comp; struct rw_semaphore *lock; /* lock buffer list */ bool is_dgraded = false; if (is_rmb) /* use socket recv buffer size (w/o overhead) as start value */ bufsize = smc->sk.sk_rcvbuf / 2; else /* use socket send buffer size (w/o overhead) as start value */ bufsize = smc->sk.sk_sndbuf / 2; for (bufsize_comp = smc_compress_bufsize(bufsize, is_smcd, is_rmb); bufsize_comp >= 0; bufsize_comp--) { if (is_rmb) { lock = &lgr->rmbs_lock; buf_list = &lgr->rmbs[bufsize_comp]; } else { lock = &lgr->sndbufs_lock; buf_list = &lgr->sndbufs[bufsize_comp]; } bufsize = smc_uncompress_bufsize(bufsize_comp); /* check for reusable slot in the link group */ buf_desc = smc_buf_get_slot(bufsize_comp, lock, buf_list); if (buf_desc) { buf_desc->is_dma_need_sync = 0; SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); SMC_STAT_BUF_REUSE(smc, is_smcd, is_rmb); break; /* found reusable slot */ } if (is_smcd) buf_desc = smcd_new_buf_create(lgr, is_rmb, bufsize); else buf_desc = smcr_new_buf_create(lgr, is_rmb, bufsize); if (PTR_ERR(buf_desc) == -ENOMEM) break; if (IS_ERR(buf_desc)) { if (!is_dgraded) { is_dgraded = true; SMC_STAT_RMB_DOWNGRADED(smc, is_smcd, is_rmb); } continue; } SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb); SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); buf_desc->used = 1; down_write(lock); list_add(&buf_desc->list, buf_list); up_write(lock); break; /* found */ } if (IS_ERR(buf_desc)) return PTR_ERR(buf_desc); if (!is_smcd) { if (smcr_buf_map_usable_links(lgr, buf_desc, is_rmb)) { smcr_buf_unuse(buf_desc, is_rmb, lgr); return -ENOMEM; } } if (is_rmb) { conn->rmb_desc = buf_desc; conn->rmbe_size_comp = bufsize_comp; smc->sk.sk_rcvbuf = bufsize * 2; atomic_set(&conn->bytes_to_rcv, 0); conn->rmbe_update_limit = smc_rmb_wnd_update_limit(buf_desc->len); if (is_smcd) smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */ } else { conn->sndbuf_desc = buf_desc; smc->sk.sk_sndbuf = bufsize * 2; atomic_set(&conn->sndbuf_space, bufsize); } return 0; } void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn) { if (!conn->sndbuf_desc->is_dma_need_sync) return; if (!smc_conn_lgr_valid(conn) || conn->lgr->is_smcd || !smc_link_active(conn->lnk)) return; smc_ib_sync_sg_for_device(conn->lnk, conn->sndbuf_desc, DMA_TO_DEVICE); } void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn) { int i; if (!conn->rmb_desc->is_dma_need_sync) return; if (!smc_conn_lgr_valid(conn) || conn->lgr->is_smcd) return; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_active(&conn->lgr->lnk[i])) continue; smc_ib_sync_sg_for_cpu(&conn->lgr->lnk[i], conn->rmb_desc, DMA_FROM_DEVICE); } } /* create the send and receive buffer for an SMC socket; * receive buffers are called RMBs; * (even though the SMC protocol allows more than one RMB-element per RMB, * the Linux implementation uses just one RMB-element per RMB, i.e. uses an * extra RMB for every connection in a link group */ int smc_buf_create(struct smc_sock *smc, bool is_smcd) { int rc; /* create send buffer */ if (is_smcd && smc_ism_support_dmb_nocopy(smc->conn.lgr->smcd)) goto create_rmb; rc = __smc_buf_create(smc, is_smcd, false); if (rc) return rc; create_rmb: /* create rmb */ rc = __smc_buf_create(smc, is_smcd, true); if (rc && smc->conn.sndbuf_desc) { down_write(&smc->conn.lgr->sndbufs_lock); list_del(&smc->conn.sndbuf_desc->list); up_write(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); smc->conn.sndbuf_desc = NULL; } return rc; } int smcd_buf_attach(struct smc_sock *smc) { struct smc_connection *conn = &smc->conn; struct smcd_dev *smcd = conn->lgr->smcd; u64 peer_token = conn->peer_token; struct smc_buf_desc *buf_desc; int rc; buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL); if (!buf_desc) return -ENOMEM; /* The ghost sndbuf_desc describes the same memory region as * peer RMB. Its lifecycle is consistent with the connection's * and it will be freed with the connections instead of the * link group. */ rc = smc_ism_attach_dmb(smcd, peer_token, buf_desc); if (rc) goto free; smc->sk.sk_sndbuf = buf_desc->len; buf_desc->cpu_addr = (u8 *)buf_desc->cpu_addr + sizeof(struct smcd_cdc_msg); buf_desc->len -= sizeof(struct smcd_cdc_msg); conn->sndbuf_desc = buf_desc; conn->sndbuf_desc->used = 1; atomic_set(&conn->sndbuf_space, conn->sndbuf_desc->len); return 0; free: kfree(buf_desc); return rc; } static inline int smc_rmb_reserve_rtoken_idx(struct smc_link_group *lgr) { int i; for_each_clear_bit(i, lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX) { if (!test_and_set_bit(i, lgr->rtokens_used_mask)) return i; } return -ENOSPC; } static int smc_rtoken_find_by_link(struct smc_link_group *lgr, int lnk_idx, u32 rkey) { int i; for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) { if (test_bit(i, lgr->rtokens_used_mask) && lgr->rtokens[i][lnk_idx].rkey == rkey) return i; } return -ENOENT; } /* set rtoken for a new link to an existing rmb */ void smc_rtoken_set(struct smc_link_group *lgr, int link_idx, int link_idx_new, __be32 nw_rkey_known, __be64 nw_vaddr, __be32 nw_rkey) { int rtok_idx; rtok_idx = smc_rtoken_find_by_link(lgr, link_idx, ntohl(nw_rkey_known)); if (rtok_idx == -ENOENT) return; lgr->rtokens[rtok_idx][link_idx_new].rkey = ntohl(nw_rkey); lgr->rtokens[rtok_idx][link_idx_new].dma_addr = be64_to_cpu(nw_vaddr); } /* set rtoken for a new link whose link_id is given */ void smc_rtoken_set2(struct smc_link_group *lgr, int rtok_idx, int link_id, __be64 nw_vaddr, __be32 nw_rkey) { u64 dma_addr = be64_to_cpu(nw_vaddr); u32 rkey = ntohl(nw_rkey); bool found = false; int link_idx; for (link_idx = 0; link_idx < SMC_LINKS_PER_LGR_MAX; link_idx++) { if (lgr->lnk[link_idx].link_id == link_id) { found = true; break; } } if (!found) return; lgr->rtokens[rtok_idx][link_idx].rkey = rkey; lgr->rtokens[rtok_idx][link_idx].dma_addr = dma_addr; } /* add a new rtoken from peer */ int smc_rtoken_add(struct smc_link *lnk, __be64 nw_vaddr, __be32 nw_rkey) { struct smc_link_group *lgr = smc_get_lgr(lnk); u64 dma_addr = be64_to_cpu(nw_vaddr); u32 rkey = ntohl(nw_rkey); int i; for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) { if (lgr->rtokens[i][lnk->link_idx].rkey == rkey && lgr->rtokens[i][lnk->link_idx].dma_addr == dma_addr && test_bit(i, lgr->rtokens_used_mask)) { /* already in list */ return i; } } i = smc_rmb_reserve_rtoken_idx(lgr); if (i < 0) return i; lgr->rtokens[i][lnk->link_idx].rkey = rkey; lgr->rtokens[i][lnk->link_idx].dma_addr = dma_addr; return i; } /* delete an rtoken from all links */ int smc_rtoken_delete(struct smc_link *lnk, __be32 nw_rkey) { struct smc_link_group *lgr = smc_get_lgr(lnk); u32 rkey = ntohl(nw_rkey); int i, j; for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) { if (lgr->rtokens[i][lnk->link_idx].rkey == rkey && test_bit(i, lgr->rtokens_used_mask)) { for (j = 0; j < SMC_LINKS_PER_LGR_MAX; j++) { lgr->rtokens[i][j].rkey = 0; lgr->rtokens[i][j].dma_addr = 0; } clear_bit(i, lgr->rtokens_used_mask); return 0; } } return -ENOENT; } /* save rkey and dma_addr received from peer during clc handshake */ int smc_rmb_rtoken_handling(struct smc_connection *conn, struct smc_link *lnk, struct smc_clc_msg_accept_confirm *clc) { conn->rtoken_idx = smc_rtoken_add(lnk, clc->r0.rmb_dma_addr, clc->r0.rmb_rkey); if (conn->rtoken_idx < 0) return conn->rtoken_idx; return 0; } static void smc_core_going_away(void) { struct smc_ib_device *smcibdev; struct smcd_dev *smcd; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(smcibdev, &smc_ib_devices.list, list) { int i; for (i = 0; i < SMC_MAX_PORTS; i++) set_bit(i, smcibdev->ports_going_away); } mutex_unlock(&smc_ib_devices.mutex); mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) { smcd->going_away = 1; } mutex_unlock(&smcd_dev_list.mutex); } /* Clean up all SMC link groups */ static void smc_lgrs_shutdown(void) { struct smcd_dev *smcd; smc_core_going_away(); smc_smcr_terminate_all(NULL); mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) smc_smcd_terminate_all(smcd); mutex_unlock(&smcd_dev_list.mutex); } static int smc_core_reboot_event(struct notifier_block *this, unsigned long event, void *ptr) { smc_lgrs_shutdown(); smc_ib_unregister_client(); smc_ism_exit(); return 0; } static struct notifier_block smc_reboot_notifier = { .notifier_call = smc_core_reboot_event, }; int __init smc_core_init(void) { return register_reboot_notifier(&smc_reboot_notifier); } /* Called (from smc_exit) when module is removed */ void smc_core_exit(void) { unregister_reboot_notifier(&smc_reboot_notifier); smc_lgrs_shutdown(); } |
| 7 1 1 7 1 | 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 | #ifndef IOU_REQ_REF_H #define IOU_REQ_REF_H #include <linux/atomic.h> #include <linux/io_uring_types.h> /* * Shamelessly stolen from the mm implementation of page reference checking, * see commit f958d7b528b1 for details. */ #define req_ref_zero_or_close_to_overflow(req) \ ((unsigned int) atomic_read(&(req->refs)) + 127u <= 127u) static inline bool req_ref_inc_not_zero(struct io_kiocb *req) { WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT)); return atomic_inc_not_zero(&req->refs); } static inline bool req_ref_put_and_test(struct io_kiocb *req) { if (likely(!(req->flags & REQ_F_REFCOUNT))) return true; WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); return atomic_dec_and_test(&req->refs); } static inline void req_ref_get(struct io_kiocb *req) { WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT)); WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); atomic_inc(&req->refs); } static inline void req_ref_put(struct io_kiocb *req) { WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT)); WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); atomic_dec(&req->refs); } static inline void __io_req_set_refcount(struct io_kiocb *req, int nr) { if (!(req->flags & REQ_F_REFCOUNT)) { req->flags |= REQ_F_REFCOUNT; atomic_set(&req->refs, nr); } } static inline void io_req_set_refcount(struct io_kiocb *req) { __io_req_set_refcount(req, 1); } #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 OR MIT */ #ifndef _CRYPTO_BLAKE2B_H #define _CRYPTO_BLAKE2B_H #include <linux/bug.h> #include <linux/types.h> #include <linux/string.h> enum blake2b_lengths { BLAKE2B_BLOCK_SIZE = 128, BLAKE2B_HASH_SIZE = 64, BLAKE2B_KEY_SIZE = 64, BLAKE2B_160_HASH_SIZE = 20, BLAKE2B_256_HASH_SIZE = 32, BLAKE2B_384_HASH_SIZE = 48, BLAKE2B_512_HASH_SIZE = 64, }; struct blake2b_state { /* 'h', 't', and 'f' are used in assembly code, so keep them as-is. */ u64 h[8]; u64 t[2]; u64 f[2]; u8 buf[BLAKE2B_BLOCK_SIZE]; unsigned int buflen; unsigned int outlen; }; enum blake2b_iv { BLAKE2B_IV0 = 0x6A09E667F3BCC908ULL, BLAKE2B_IV1 = 0xBB67AE8584CAA73BULL, BLAKE2B_IV2 = 0x3C6EF372FE94F82BULL, BLAKE2B_IV3 = 0xA54FF53A5F1D36F1ULL, BLAKE2B_IV4 = 0x510E527FADE682D1ULL, BLAKE2B_IV5 = 0x9B05688C2B3E6C1FULL, BLAKE2B_IV6 = 0x1F83D9ABFB41BD6BULL, BLAKE2B_IV7 = 0x5BE0CD19137E2179ULL, }; static inline void __blake2b_init(struct blake2b_state *state, size_t outlen, const void *key, size_t keylen) { state->h[0] = BLAKE2B_IV0 ^ (0x01010000 | keylen << 8 | outlen); state->h[1] = BLAKE2B_IV1; state->h[2] = BLAKE2B_IV2; state->h[3] = BLAKE2B_IV3; state->h[4] = BLAKE2B_IV4; state->h[5] = BLAKE2B_IV5; state->h[6] = BLAKE2B_IV6; state->h[7] = BLAKE2B_IV7; state->t[0] = 0; state->t[1] = 0; state->f[0] = 0; state->f[1] = 0; state->buflen = 0; state->outlen = outlen; if (keylen) { memcpy(state->buf, key, keylen); memset(&state->buf[keylen], 0, BLAKE2B_BLOCK_SIZE - keylen); state->buflen = BLAKE2B_BLOCK_SIZE; } } #endif /* _CRYPTO_BLAKE2B_H */ |
| 422 13 1 8 1 345 1 1 1 1 1 230 263 263 263 60 5 10 1 1 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_INETDEVICE_H #define _LINUX_INETDEVICE_H #ifdef __KERNEL__ #include <linux/bitmap.h> #include <linux/if.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> #include <linux/timer.h> #include <linux/sysctl.h> #include <linux/rtnetlink.h> #include <linux/refcount.h> struct ipv4_devconf { void *sysctl; int data[IPV4_DEVCONF_MAX]; DECLARE_BITMAP(state, IPV4_DEVCONF_MAX); }; #define MC_HASH_SZ_LOG 9 struct in_device { struct net_device *dev; netdevice_tracker dev_tracker; refcount_t refcnt; int dead; struct in_ifaddr __rcu *ifa_list;/* IP ifaddr chain */ struct ip_mc_list __rcu *mc_list; /* IP multicast filter chain */ struct ip_mc_list __rcu * __rcu *mc_hash; int mc_count; /* Number of installed mcasts */ spinlock_t mc_tomb_lock; struct ip_mc_list *mc_tomb; unsigned long mr_v1_seen; unsigned long mr_v2_seen; unsigned long mr_maxdelay; unsigned long mr_qi; /* Query Interval */ unsigned long mr_qri; /* Query Response Interval */ unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; u32 mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ struct timer_list mr_ifc_timer; /* interface change timer */ struct neigh_parms *arp_parms; struct ipv4_devconf cnf; struct rcu_head rcu_head; }; #define IPV4_DEVCONF(cnf, attr) ((cnf).data[IPV4_DEVCONF_ ## attr - 1]) #define IPV4_DEVCONF_RO(cnf, attr) READ_ONCE(IPV4_DEVCONF(cnf, attr)) #define IPV4_DEVCONF_ALL(net, attr) \ IPV4_DEVCONF((*(net)->ipv4.devconf_all), attr) #define IPV4_DEVCONF_ALL_RO(net, attr) READ_ONCE(IPV4_DEVCONF_ALL(net, attr)) static inline int ipv4_devconf_get(const struct in_device *in_dev, int index) { index--; return READ_ONCE(in_dev->cnf.data[index]); } static inline void ipv4_devconf_set(struct in_device *in_dev, int index, int val) { index--; set_bit(index, in_dev->cnf.state); WRITE_ONCE(in_dev->cnf.data[index], val); } static inline void ipv4_devconf_setall(struct in_device *in_dev) { bitmap_fill(in_dev->cnf.state, IPV4_DEVCONF_MAX); } #define IN_DEV_CONF_GET(in_dev, attr) \ ipv4_devconf_get((in_dev), IPV4_DEVCONF_ ## attr) #define IN_DEV_CONF_SET(in_dev, attr, val) \ ipv4_devconf_set((in_dev), IPV4_DEVCONF_ ## attr, (val)) #define IN_DEV_ANDCONF(in_dev, attr) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr) && \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_NET_ORCONF(in_dev, net, attr) \ (IPV4_DEVCONF_ALL_RO(net, attr) || \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_ORCONF(in_dev, attr) \ IN_DEV_NET_ORCONF(in_dev, dev_net(in_dev->dev), attr) #define IN_DEV_MAXCONF(in_dev, attr) \ (max(IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr), \ IN_DEV_CONF_GET((in_dev), attr))) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) #define IN_DEV_BFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), BC_FORWARDING) #define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) #define IN_DEV_SRC_VMARK(in_dev) IN_DEV_ORCONF((in_dev), SRC_VMARK) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ ACCEPT_SOURCE_ROUTE) #define IN_DEV_ACCEPT_LOCAL(in_dev) IN_DEV_ORCONF((in_dev), ACCEPT_LOCAL) #define IN_DEV_BOOTP_RELAY(in_dev) IN_DEV_ANDCONF((in_dev), BOOTP_RELAY) #define IN_DEV_LOG_MARTIANS(in_dev) IN_DEV_ORCONF((in_dev), LOG_MARTIANS) #define IN_DEV_PROXY_ARP(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP) #define IN_DEV_PROXY_ARP_PVLAN(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP_PVLAN) #define IN_DEV_SHARED_MEDIA(in_dev) IN_DEV_ORCONF((in_dev), SHARED_MEDIA) #define IN_DEV_TX_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), SEND_REDIRECTS) #define IN_DEV_SEC_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), \ SECURE_REDIRECTS) #define IN_DEV_IDTAG(in_dev) IN_DEV_CONF_GET(in_dev, TAG) #define IN_DEV_MEDIUM_ID(in_dev) IN_DEV_CONF_GET(in_dev, MEDIUM_ID) #define IN_DEV_PROMOTE_SECONDARIES(in_dev) \ IN_DEV_ORCONF((in_dev), \ PROMOTE_SECONDARIES) #define IN_DEV_ROUTE_LOCALNET(in_dev) IN_DEV_ORCONF(in_dev, ROUTE_LOCALNET) #define IN_DEV_NET_ROUTE_LOCALNET(in_dev, net) \ IN_DEV_NET_ORCONF(in_dev, net, ROUTE_LOCALNET) #define IN_DEV_RX_REDIRECTS(in_dev) \ ((IN_DEV_FORWARD(in_dev) && \ IN_DEV_ANDCONF((in_dev), ACCEPT_REDIRECTS)) \ || (!IN_DEV_FORWARD(in_dev) && \ IN_DEV_ORCONF((in_dev), ACCEPT_REDIRECTS))) #define IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) \ IN_DEV_ORCONF((in_dev), IGNORE_ROUTES_WITH_LINKDOWN) #define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER) #define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ACCEPT) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) #define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) #define IN_DEV_ARP_EVICT_NOCARRIER(in_dev) IN_DEV_ANDCONF((in_dev), \ ARP_EVICT_NOCARRIER) struct in_ifaddr { struct hlist_node hash; struct in_ifaddr __rcu *ifa_next; struct in_device *ifa_dev; struct rcu_head rcu_head; __be32 ifa_local; __be32 ifa_address; __be32 ifa_mask; __u32 ifa_rt_priority; __be32 ifa_broadcast; unsigned char ifa_scope; unsigned char ifa_prefixlen; unsigned char ifa_proto; __u32 ifa_flags; char ifa_label[IFNAMSIZ]; /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 ifa_valid_lft; __u32 ifa_preferred_lft; unsigned long ifa_cstamp; /* created timestamp */ unsigned long ifa_tstamp; /* updated timestamp */ }; struct in_validator_info { __be32 ivi_addr; struct in_device *ivi_dev; struct netlink_ext_ack *extack; }; int register_inetaddr_notifier(struct notifier_block *nb); int unregister_inetaddr_notifier(struct notifier_block *nb); int register_inetaddr_validator_notifier(struct notifier_block *nb); int unregister_inetaddr_validator_notifier(struct notifier_block *nb); void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf); struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref); static inline struct net_device *ip_dev_find(struct net *net, __be32 addr) { return __ip_dev_find(net, addr, true); } int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b); int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *); #ifdef CONFIG_INET int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size); #else static inline int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { return 0; } #endif void devinet_init(void); struct in_device *inetdev_by_index(struct net *, int); __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr); static inline bool inet_ifa_match(__be32 addr, const struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); } /* * Check if a mask is acceptable. */ static __inline__ bool bad_mask(__be32 mask, __be32 addr) { __u32 hmask; if (addr & (mask = ~mask)) return true; hmask = ntohl(mask); if (hmask & (hmask+1)) return true; return false; } #define in_dev_for_each_ifa_rtnl(ifa, in_dev) \ for (ifa = rtnl_dereference((in_dev)->ifa_list); ifa; \ ifa = rtnl_dereference(ifa->ifa_next)) #define in_dev_for_each_ifa_rcu(ifa, in_dev) \ for (ifa = rcu_dereference((in_dev)->ifa_list); ifa; \ ifa = rcu_dereference(ifa->ifa_next)) static inline struct in_device *__in_dev_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->ip_ptr); } static inline struct in_device *in_dev_get(const struct net_device *dev) { struct in_device *in_dev; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) refcount_inc(&in_dev->refcnt); rcu_read_unlock(); return in_dev; } static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->ip_ptr); } /* called with rcu_read_lock or rtnl held */ static inline bool ip_ignore_linkdown(const struct net_device *dev) { struct in_device *in_dev; bool rc = false; in_dev = rcu_dereference_rtnl(dev->ip_ptr); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) rc = true; return rc; } static inline struct neigh_parms *__in_dev_arp_parms_get_rcu(const struct net_device *dev) { struct in_device *in_dev = __in_dev_get_rcu(dev); return in_dev ? in_dev->arp_parms : NULL; } void in_dev_finish_destroy(struct in_device *idev); static inline void in_dev_put(struct in_device *idev) { if (refcount_dec_and_test(&idev->refcnt)) in_dev_finish_destroy(idev); } #define __in_dev_put(idev) refcount_dec(&(idev)->refcnt) #define in_dev_hold(idev) refcount_inc(&(idev)->refcnt) #endif /* __KERNEL__ */ static __inline__ __be32 inet_make_mask(int logmask) { if (logmask) return htonl(~((1U<<(32-logmask))-1)); return 0; } static __inline__ int inet_mask_len(__be32 mask) { __u32 hmask = ntohl(mask); if (!hmask) return 0; return 32 - ffz(~hmask); } #endif /* _LINUX_INETDEVICE_H */ |
| 2 2 2 2 2 2 2 43 43 43 42 2 42 43 2 2 2 29 29 29 29 28 109 110 110 110 110 109 110 109 109 107 110 7 7 8 54 53 26 26 54 28 28 1 27 1 26 27 27 27 1 67 66 67 67 52 52 52 22 21 22 7 16 67 7 67 13 67 58 13 67 66 15 15 14 9 7 8 7 24 24 13 13 24 1 1 1 1 1 1 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Task credentials management - see Documentation/security/credentials.rst * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) "CRED: " fmt #include <linux/export.h> #include <linux/cred.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/coredump.h> #include <linux/key.h> #include <linux/keyctl.h> #include <linux/init_task.h> #include <linux/security.h> #include <linux/binfmts.h> #include <linux/cn_proc.h> #include <linux/uidgid.h> #if 0 #define kdebug(FMT, ...) \ printk("[%-5.5s%5u] " FMT "\n", \ current->comm, current->pid, ##__VA_ARGS__) #else #define kdebug(FMT, ...) \ do { \ if (0) \ no_printk("[%-5.5s%5u] " FMT "\n", \ current->comm, current->pid, ##__VA_ARGS__); \ } while (0) #endif static struct kmem_cache *cred_jar; /* init to 2 - one for init_task, one to ensure it is never freed */ static struct group_info init_groups = { .usage = REFCOUNT_INIT(2) }; /* * The initial credentials for the initial task */ struct cred init_cred = { .usage = ATOMIC_INIT(4), .uid = GLOBAL_ROOT_UID, .gid = GLOBAL_ROOT_GID, .suid = GLOBAL_ROOT_UID, .sgid = GLOBAL_ROOT_GID, .euid = GLOBAL_ROOT_UID, .egid = GLOBAL_ROOT_GID, .fsuid = GLOBAL_ROOT_UID, .fsgid = GLOBAL_ROOT_GID, .securebits = SECUREBITS_DEFAULT, .cap_inheritable = CAP_EMPTY_SET, .cap_permitted = CAP_FULL_SET, .cap_effective = CAP_FULL_SET, .cap_bset = CAP_FULL_SET, .user = INIT_USER, .user_ns = &init_user_ns, .group_info = &init_groups, .ucounts = &init_ucounts, }; /* * The RCU callback to actually dispose of a set of credentials */ static void put_cred_rcu(struct rcu_head *rcu) { struct cred *cred = container_of(rcu, struct cred, rcu); kdebug("put_cred_rcu(%p)", cred); if (atomic_long_read(&cred->usage) != 0) panic("CRED: put_cred_rcu() sees %p with usage %ld\n", cred, atomic_long_read(&cred->usage)); security_cred_free(cred); key_put(cred->session_keyring); key_put(cred->process_keyring); key_put(cred->thread_keyring); key_put(cred->request_key_auth); if (cred->group_info) put_group_info(cred->group_info); free_uid(cred->user); if (cred->ucounts) put_ucounts(cred->ucounts); put_user_ns(cred->user_ns); kmem_cache_free(cred_jar, cred); } /** * __put_cred - Destroy a set of credentials * @cred: The record to release * * Destroy a set of credentials on which no references remain. */ void __put_cred(struct cred *cred) { kdebug("__put_cred(%p{%ld})", cred, atomic_long_read(&cred->usage)); BUG_ON(atomic_long_read(&cred->usage) != 0); BUG_ON(cred == current->cred); BUG_ON(cred == current->real_cred); if (cred->non_rcu) put_cred_rcu(&cred->rcu); else call_rcu(&cred->rcu, put_cred_rcu); } EXPORT_SYMBOL(__put_cred); /* * Clean up a task's credentials when it exits */ void exit_creds(struct task_struct *tsk) { struct cred *real_cred, *cred; kdebug("exit_creds(%u,%p,%p,{%ld})", tsk->pid, tsk->real_cred, tsk->cred, atomic_long_read(&tsk->cred->usage)); real_cred = (struct cred *) tsk->real_cred; tsk->real_cred = NULL; cred = (struct cred *) tsk->cred; tsk->cred = NULL; if (real_cred == cred) { put_cred_many(cred, 2); } else { put_cred(real_cred); put_cred(cred); } #ifdef CONFIG_KEYS_REQUEST_CACHE key_put(tsk->cached_requested_key); tsk->cached_requested_key = NULL; #endif } /** * get_task_cred - Get another task's objective credentials * @task: The task to query * * Get the objective credentials of a task, pinning them so that they can't go * away. Accessing a task's credentials directly is not permitted. * * The caller must also make sure task doesn't get deleted, either by holding a * ref on task or by holding tasklist_lock to prevent it from being unlinked. */ const struct cred *get_task_cred(struct task_struct *task) { const struct cred *cred; rcu_read_lock(); do { cred = __task_cred((task)); BUG_ON(!cred); } while (!get_cred_rcu(cred)); rcu_read_unlock(); return cred; } EXPORT_SYMBOL(get_task_cred); /* * Allocate blank credentials, such that the credentials can be filled in at a * later date without risk of ENOMEM. */ struct cred *cred_alloc_blank(void) { struct cred *new; new = kmem_cache_zalloc(cred_jar, GFP_KERNEL); if (!new) return NULL; atomic_long_set(&new->usage, 1); if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0) goto error; return new; error: abort_creds(new); return NULL; } /** * prepare_creds - Prepare a new set of credentials for modification * * Prepare a new set of task credentials for modification. A task's creds * shouldn't generally be modified directly, therefore this function is used to * prepare a new copy, which the caller then modifies and then commits by * calling commit_creds(). * * Preparation involves making a copy of the objective creds for modification. * * Returns a pointer to the new creds-to-be if successful, NULL otherwise. * * Call commit_creds() or abort_creds() to clean up. */ struct cred *prepare_creds(void) { struct task_struct *task = current; const struct cred *old; struct cred *new; new = kmem_cache_alloc(cred_jar, GFP_KERNEL); if (!new) return NULL; kdebug("prepare_creds() alloc %p", new); old = task->cred; memcpy(new, old, sizeof(struct cred)); new->non_rcu = 0; atomic_long_set(&new->usage, 1); get_group_info(new->group_info); get_uid(new->user); get_user_ns(new->user_ns); #ifdef CONFIG_KEYS key_get(new->session_keyring); key_get(new->process_keyring); key_get(new->thread_keyring); key_get(new->request_key_auth); #endif #ifdef CONFIG_SECURITY new->security = NULL; #endif new->ucounts = get_ucounts(new->ucounts); if (!new->ucounts) goto error; if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; return new; error: abort_creds(new); return NULL; } EXPORT_SYMBOL(prepare_creds); /* * Prepare credentials for current to perform an execve() * - The caller must hold ->cred_guard_mutex */ struct cred *prepare_exec_creds(void) { struct cred *new; new = prepare_creds(); if (!new) return new; #ifdef CONFIG_KEYS /* newly exec'd tasks don't get a thread keyring */ key_put(new->thread_keyring); new->thread_keyring = NULL; /* inherit the session keyring; new process keyring */ key_put(new->process_keyring); new->process_keyring = NULL; #endif new->suid = new->fsuid = new->euid; new->sgid = new->fsgid = new->egid; return new; } /* * Copy credentials for the new process created by fork() * * We share if we can, but under some circumstances we have to generate a new * set. * * The new process gets the current process's subjective credentials as its * objective and subjective credentials */ int copy_creds(struct task_struct *p, unsigned long clone_flags) { struct cred *new; int ret; #ifdef CONFIG_KEYS_REQUEST_CACHE p->cached_requested_key = NULL; #endif if ( #ifdef CONFIG_KEYS !p->cred->thread_keyring && #endif clone_flags & CLONE_THREAD ) { p->real_cred = get_cred_many(p->cred, 2); kdebug("share_creds(%p{%ld})", p->cred, atomic_long_read(&p->cred->usage)); inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); return 0; } new = prepare_creds(); if (!new) return -ENOMEM; if (clone_flags & CLONE_NEWUSER) { ret = create_user_ns(new); if (ret < 0) goto error_put; ret = set_cred_ucounts(new); if (ret < 0) goto error_put; } #ifdef CONFIG_KEYS /* new threads get their own thread keyrings if their parent already * had one */ if (new->thread_keyring) { key_put(new->thread_keyring); new->thread_keyring = NULL; if (clone_flags & CLONE_THREAD) install_thread_keyring_to_cred(new); } /* The process keyring is only shared between the threads in a process; * anything outside of those threads doesn't inherit. */ if (!(clone_flags & CLONE_THREAD)) { key_put(new->process_keyring); new->process_keyring = NULL; } #endif p->cred = p->real_cred = get_cred(new); inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); return 0; error_put: put_cred(new); return ret; } static bool cred_cap_issubset(const struct cred *set, const struct cred *subset) { const struct user_namespace *set_ns = set->user_ns; const struct user_namespace *subset_ns = subset->user_ns; /* If the two credentials are in the same user namespace see if * the capabilities of subset are a subset of set. */ if (set_ns == subset_ns) return cap_issubset(subset->cap_permitted, set->cap_permitted); /* The credentials are in a different user namespaces * therefore one is a subset of the other only if a set is an * ancestor of subset and set->euid is owner of subset or one * of subsets ancestors. */ for (;subset_ns != &init_user_ns; subset_ns = subset_ns->parent) { if ((set_ns == subset_ns->parent) && uid_eq(subset_ns->owner, set->euid)) return true; } return false; } /** * commit_creds - Install new credentials upon the current task * @new: The credentials to be assigned * * Install a new set of credentials to the current task, using RCU to replace * the old set. Both the objective and the subjective credentials pointers are * updated. This function may not be called if the subjective credentials are * in an overridden state. * * This function eats the caller's reference to the new credentials. * * Always returns 0 thus allowing this function to be tail-called at the end * of, say, sys_setgid(). */ int commit_creds(struct cred *new) { struct task_struct *task = current; const struct cred *old = task->real_cred; kdebug("commit_creds(%p{%ld})", new, atomic_long_read(&new->usage)); BUG_ON(task->cred != old); BUG_ON(atomic_long_read(&new->usage) < 1); get_cred(new); /* we will require a ref for the subj creds too */ /* dumpability changes */ if (!uid_eq(old->euid, new->euid) || !gid_eq(old->egid, new->egid) || !uid_eq(old->fsuid, new->fsuid) || !gid_eq(old->fsgid, new->fsgid) || !cred_cap_issubset(old, new)) { if (task->mm) set_dumpable(task->mm, suid_dumpable); task->pdeath_signal = 0; /* * If a task drops privileges and becomes nondumpable, * the dumpability change must become visible before * the credential change; otherwise, a __ptrace_may_access() * racing with this change may be able to attach to a task it * shouldn't be able to attach to (as if the task had dropped * privileges without becoming nondumpable). * Pairs with a read barrier in __ptrace_may_access(). */ smp_wmb(); } /* alter the thread keyring */ if (!uid_eq(new->fsuid, old->fsuid)) key_fsuid_changed(new); if (!gid_eq(new->fsgid, old->fsgid)) key_fsgid_changed(new); /* do it * RLIMIT_NPROC limits on user->processes have already been checked * in set_user(). */ if (new->user != old->user || new->user_ns != old->user_ns) inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1); rcu_assign_pointer(task->real_cred, new); rcu_assign_pointer(task->cred, new); if (new->user != old->user || new->user_ns != old->user_ns) dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1); /* send notifications */ if (!uid_eq(new->uid, old->uid) || !uid_eq(new->euid, old->euid) || !uid_eq(new->suid, old->suid) || !uid_eq(new->fsuid, old->fsuid)) proc_id_connector(task, PROC_EVENT_UID); if (!gid_eq(new->gid, old->gid) || !gid_eq(new->egid, old->egid) || !gid_eq(new->sgid, old->sgid) || !gid_eq(new->fsgid, old->fsgid)) proc_id_connector(task, PROC_EVENT_GID); /* release the old obj and subj refs both */ put_cred_many(old, 2); return 0; } EXPORT_SYMBOL(commit_creds); /** * abort_creds - Discard a set of credentials and unlock the current task * @new: The credentials that were going to be applied * * Discard a set of credentials that were under construction and unlock the * current task. */ void abort_creds(struct cred *new) { kdebug("abort_creds(%p{%ld})", new, atomic_long_read(&new->usage)); BUG_ON(atomic_long_read(&new->usage) < 1); put_cred(new); } EXPORT_SYMBOL(abort_creds); /** * override_creds - Override the current process's subjective credentials * @new: The credentials to be assigned * * Install a set of temporary override subjective credentials on the current * process, returning the old set for later reversion. */ const struct cred *override_creds(const struct cred *new) { const struct cred *old = current->cred; kdebug("override_creds(%p{%ld})", new, atomic_long_read(&new->usage)); /* * NOTE! This uses 'get_new_cred()' rather than 'get_cred()'. * * That means that we do not clear the 'non_rcu' flag, since * we are only installing the cred into the thread-synchronous * '->cred' pointer, not the '->real_cred' pointer that is * visible to other threads under RCU. */ get_new_cred((struct cred *)new); rcu_assign_pointer(current->cred, new); kdebug("override_creds() = %p{%ld}", old, atomic_long_read(&old->usage)); return old; } EXPORT_SYMBOL(override_creds); /** * revert_creds - Revert a temporary subjective credentials override * @old: The credentials to be restored * * Revert a temporary set of override subjective credentials to an old set, * discarding the override set. */ void revert_creds(const struct cred *old) { const struct cred *override = current->cred; kdebug("revert_creds(%p{%ld})", old, atomic_long_read(&old->usage)); rcu_assign_pointer(current->cred, old); put_cred(override); } EXPORT_SYMBOL(revert_creds); /** * cred_fscmp - Compare two credentials with respect to filesystem access. * @a: The first credential * @b: The second credential * * cred_cmp() will return zero if both credentials have the same * fsuid, fsgid, and supplementary groups. That is, if they will both * provide the same access to files based on mode/uid/gid. * If the credentials are different, then either -1 or 1 will * be returned depending on whether @a comes before or after @b * respectively in an arbitrary, but stable, ordering of credentials. * * Return: -1, 0, or 1 depending on comparison */ int cred_fscmp(const struct cred *a, const struct cred *b) { struct group_info *ga, *gb; int g; if (a == b) return 0; if (uid_lt(a->fsuid, b->fsuid)) return -1; if (uid_gt(a->fsuid, b->fsuid)) return 1; if (gid_lt(a->fsgid, b->fsgid)) return -1; if (gid_gt(a->fsgid, b->fsgid)) return 1; ga = a->group_info; gb = b->group_info; if (ga == gb) return 0; if (ga == NULL) return -1; if (gb == NULL) return 1; if (ga->ngroups < gb->ngroups) return -1; if (ga->ngroups > gb->ngroups) return 1; for (g = 0; g < ga->ngroups; g++) { if (gid_lt(ga->gid[g], gb->gid[g])) return -1; if (gid_gt(ga->gid[g], gb->gid[g])) return 1; } return 0; } EXPORT_SYMBOL(cred_fscmp); int set_cred_ucounts(struct cred *new) { struct ucounts *new_ucounts, *old_ucounts = new->ucounts; /* * This optimization is needed because alloc_ucounts() uses locks * for table lookups. */ if (old_ucounts->ns == new->user_ns && uid_eq(old_ucounts->uid, new->uid)) return 0; if (!(new_ucounts = alloc_ucounts(new->user_ns, new->uid))) return -EAGAIN; new->ucounts = new_ucounts; put_ucounts(old_ucounts); return 0; } /* * initialise the credentials stuff */ void __init cred_init(void) { /* allocate a slab in which we can store credentials */ cred_jar = KMEM_CACHE(cred, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); } /** * prepare_kernel_cred - Prepare a set of credentials for a kernel service * @daemon: A userspace daemon to be used as a reference * * Prepare a set of credentials for a kernel service. This can then be used to * override a task's own credentials so that work can be done on behalf of that * task that requires a different subjective context. * * @daemon is used to provide a base cred, with the security data derived from * that; if this is "&init_task", they'll be set to 0, no groups, full * capabilities, and no keys. * * The caller may change these controls afterwards if desired. * * Returns the new credentials or NULL if out of memory. */ struct cred *prepare_kernel_cred(struct task_struct *daemon) { const struct cred *old; struct cred *new; if (WARN_ON_ONCE(!daemon)) return NULL; new = kmem_cache_alloc(cred_jar, GFP_KERNEL); if (!new) return NULL; kdebug("prepare_kernel_cred() alloc %p", new); old = get_task_cred(daemon); *new = *old; new->non_rcu = 0; atomic_long_set(&new->usage, 1); get_uid(new->user); get_user_ns(new->user_ns); get_group_info(new->group_info); #ifdef CONFIG_KEYS new->session_keyring = NULL; new->process_keyring = NULL; new->thread_keyring = NULL; new->request_key_auth = NULL; new->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING; #endif #ifdef CONFIG_SECURITY new->security = NULL; #endif new->ucounts = get_ucounts(new->ucounts); if (!new->ucounts) goto error; if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; put_cred(old); return new; error: put_cred(new); put_cred(old); return NULL; } EXPORT_SYMBOL(prepare_kernel_cred); /** * set_security_override - Set the security ID in a set of credentials * @new: The credentials to alter * @secid: The LSM security ID to set * * Set the LSM security ID in a set of credentials so that the subjective * security is overridden when an alternative set of credentials is used. */ int set_security_override(struct cred *new, u32 secid) { return security_kernel_act_as(new, secid); } EXPORT_SYMBOL(set_security_override); /** * set_security_override_from_ctx - Set the security ID in a set of credentials * @new: The credentials to alter * @secctx: The LSM security context to generate the security ID from. * * Set the LSM security ID in a set of credentials so that the subjective * security is overridden when an alternative set of credentials is used. The * security ID is specified in string form as a security context to be * interpreted by the LSM. */ int set_security_override_from_ctx(struct cred *new, const char *secctx) { u32 secid; int ret; ret = security_secctx_to_secid(secctx, strlen(secctx), &secid); if (ret < 0) return ret; return set_security_override(new, secid); } EXPORT_SYMBOL(set_security_override_from_ctx); /** * set_create_files_as - Set the LSM file create context in a set of credentials * @new: The credentials to alter * @inode: The inode to take the context from * * Change the LSM file creation context in a set of credentials to be the same * as the object context of the specified inode, so that the new inodes have * the same MAC context as that inode. */ int set_create_files_as(struct cred *new, struct inode *inode) { if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid)) return -EINVAL; new->fsuid = inode->i_uid; new->fsgid = inode->i_gid; return security_kernel_create_files_as(new, inode); } EXPORT_SYMBOL(set_create_files_as); |
| 2 2 2 2 3 3 3 3 3 3 3 3 2 2 3 3 2 3 2 3 2 2 2 2 2 2 2 1 1 1 1 2 2 2 2 1 2 2 2 2 2 2 1 3 3 2 2 2 2 2 2 3 3 3 2 2 2 2 3 3 2 3 3 3 3 3 1 1 1 1 1 1 1 1 1 3 3 3 3 1 3 2 2 2 2 2 3 3 3 3 3 3 3 3 2 2 2 | 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 | /* * Copyright (c) 2004 Topspin Communications. All rights reserved. * Copyright (c) 2005 Intel Corporation. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2005 Voltaire, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include <linux/if_vlan.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/netdevice.h> #include <net/addrconf.h> #include <rdma/ib_cache.h> #include "core_priv.h" struct ib_pkey_cache { int table_len; u16 table[] __counted_by(table_len); }; struct ib_update_work { struct work_struct work; struct ib_event event; bool enforce_security; }; union ib_gid zgid; EXPORT_SYMBOL(zgid); enum gid_attr_find_mask { GID_ATTR_FIND_MASK_GID = 1UL << 0, GID_ATTR_FIND_MASK_NETDEV = 1UL << 1, GID_ATTR_FIND_MASK_DEFAULT = 1UL << 2, GID_ATTR_FIND_MASK_GID_TYPE = 1UL << 3, }; enum gid_table_entry_state { GID_TABLE_ENTRY_INVALID = 1, GID_TABLE_ENTRY_VALID = 2, /* * Indicates that entry is pending to be removed, there may * be active users of this GID entry. * When last user of the GID entry releases reference to it, * GID entry is detached from the table. */ GID_TABLE_ENTRY_PENDING_DEL = 3, }; struct roce_gid_ndev_storage { struct rcu_head rcu_head; struct net_device *ndev; }; struct ib_gid_table_entry { struct kref kref; struct work_struct del_work; struct ib_gid_attr attr; void *context; /* Store the ndev pointer to release reference later on in * call_rcu context because by that time gid_table_entry * and attr might be already freed. So keep a copy of it. * ndev_storage is freed by rcu callback. */ struct roce_gid_ndev_storage *ndev_storage; enum gid_table_entry_state state; }; struct ib_gid_table { int sz; /* In RoCE, adding a GID to the table requires: * (a) Find if this GID is already exists. * (b) Find a free space. * (c) Write the new GID * * Delete requires different set of operations: * (a) Find the GID * (b) Delete it. * **/ /* Any writer to data_vec must hold this lock and the write side of * rwlock. Readers must hold only rwlock. All writers must be in a * sleepable context. */ struct mutex lock; /* rwlock protects data_vec[ix]->state and entry pointer. */ rwlock_t rwlock; struct ib_gid_table_entry **data_vec; /* bit field, each bit indicates the index of default GID */ u32 default_gid_indices; }; static void dispatch_gid_change_event(struct ib_device *ib_dev, u32 port) { struct ib_event event; event.device = ib_dev; event.element.port_num = port; event.event = IB_EVENT_GID_CHANGE; ib_dispatch_event_clients(&event); } static const char * const gid_type_str[] = { /* IB/RoCE v1 value is set for IB_GID_TYPE_IB and IB_GID_TYPE_ROCE for * user space compatibility reasons. */ [IB_GID_TYPE_IB] = "IB/RoCE v1", [IB_GID_TYPE_ROCE] = "IB/RoCE v1", [IB_GID_TYPE_ROCE_UDP_ENCAP] = "RoCE v2", }; const char *ib_cache_gid_type_str(enum ib_gid_type gid_type) { if (gid_type < ARRAY_SIZE(gid_type_str) && gid_type_str[gid_type]) return gid_type_str[gid_type]; return "Invalid GID type"; } EXPORT_SYMBOL(ib_cache_gid_type_str); /** rdma_is_zero_gid - Check if given GID is zero or not. * @gid: GID to check * Returns true if given GID is zero, returns false otherwise. */ bool rdma_is_zero_gid(const union ib_gid *gid) { return !memcmp(gid, &zgid, sizeof(*gid)); } EXPORT_SYMBOL(rdma_is_zero_gid); /** is_gid_index_default - Check if a given index belongs to * reserved default GIDs or not. * @table: GID table pointer * @index: Index to check in GID table * Returns true if index is one of the reserved default GID index otherwise * returns false. */ static bool is_gid_index_default(const struct ib_gid_table *table, unsigned int index) { return index < 32 && (BIT(index) & table->default_gid_indices); } int ib_cache_gid_parse_type_str(const char *buf) { unsigned int i; size_t len; int err = -EINVAL; len = strlen(buf); if (len == 0) return -EINVAL; if (buf[len - 1] == '\n') len--; for (i = 0; i < ARRAY_SIZE(gid_type_str); ++i) if (gid_type_str[i] && !strncmp(buf, gid_type_str[i], len) && len == strlen(gid_type_str[i])) { err = i; break; } return err; } EXPORT_SYMBOL(ib_cache_gid_parse_type_str); static struct ib_gid_table *rdma_gid_table(struct ib_device *device, u32 port) { return device->port_data[port].cache.gid; } static bool is_gid_entry_free(const struct ib_gid_table_entry *entry) { return !entry; } static bool is_gid_entry_valid(const struct ib_gid_table_entry *entry) { return entry && entry->state == GID_TABLE_ENTRY_VALID; } static void schedule_free_gid(struct kref *kref) { struct ib_gid_table_entry *entry = container_of(kref, struct ib_gid_table_entry, kref); queue_work(ib_wq, &entry->del_work); } static void put_gid_ndev(struct rcu_head *head) { struct roce_gid_ndev_storage *storage = container_of(head, struct roce_gid_ndev_storage, rcu_head); WARN_ON(!storage->ndev); /* At this point its safe to release netdev reference, * as all callers working on gid_attr->ndev are done * using this netdev. */ dev_put(storage->ndev); kfree(storage); } static void free_gid_entry_locked(struct ib_gid_table_entry *entry) { struct ib_device *device = entry->attr.device; u32 port_num = entry->attr.port_num; struct ib_gid_table *table = rdma_gid_table(device, port_num); dev_dbg(&device->dev, "%s port=%u index=%u gid %pI6\n", __func__, port_num, entry->attr.index, entry->attr.gid.raw); write_lock_irq(&table->rwlock); /* * The only way to avoid overwriting NULL in table is * by comparing if it is same entry in table or not! * If new entry in table is added by the time we free here, * don't overwrite the table entry. */ if (entry == table->data_vec[entry->attr.index]) table->data_vec[entry->attr.index] = NULL; /* Now this index is ready to be allocated */ write_unlock_irq(&table->rwlock); if (entry->ndev_storage) call_rcu(&entry->ndev_storage->rcu_head, put_gid_ndev); kfree(entry); } static void free_gid_entry(struct kref *kref) { struct ib_gid_table_entry *entry = container_of(kref, struct ib_gid_table_entry, kref); free_gid_entry_locked(entry); } /** * free_gid_work - Release reference to the GID entry * @work: Work structure to refer to GID entry which needs to be * deleted. * * free_gid_work() frees the entry from the HCA's hardware table * if provider supports it. It releases reference to netdevice. */ static void free_gid_work(struct work_struct *work) { struct ib_gid_table_entry *entry = container_of(work, struct ib_gid_table_entry, del_work); struct ib_device *device = entry->attr.device; u32 port_num = entry->attr.port_num; struct ib_gid_table *table = rdma_gid_table(device, port_num); mutex_lock(&table->lock); free_gid_entry_locked(entry); mutex_unlock(&table->lock); } static struct ib_gid_table_entry * alloc_gid_entry(const struct ib_gid_attr *attr) { struct ib_gid_table_entry *entry; struct net_device *ndev; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return NULL; ndev = rcu_dereference_protected(attr->ndev, 1); if (ndev) { entry->ndev_storage = kzalloc(sizeof(*entry->ndev_storage), GFP_KERNEL); if (!entry->ndev_storage) { kfree(entry); return NULL; } dev_hold(ndev); entry->ndev_storage->ndev = ndev; } kref_init(&entry->kref); memcpy(&entry->attr, attr, sizeof(*attr)); INIT_WORK(&entry->del_work, free_gid_work); entry->state = GID_TABLE_ENTRY_INVALID; return entry; } static void store_gid_entry(struct ib_gid_table *table, struct ib_gid_table_entry *entry) { entry->state = GID_TABLE_ENTRY_VALID; dev_dbg(&entry->attr.device->dev, "%s port=%u index=%u gid %pI6\n", __func__, entry->attr.port_num, entry->attr.index, entry->attr.gid.raw); lockdep_assert_held(&table->lock); write_lock_irq(&table->rwlock); table->data_vec[entry->attr.index] = entry; write_unlock_irq(&table->rwlock); } static void get_gid_entry(struct ib_gid_table_entry *entry) { kref_get(&entry->kref); } static void put_gid_entry(struct ib_gid_table_entry *entry) { kref_put(&entry->kref, schedule_free_gid); } static void put_gid_entry_locked(struct ib_gid_table_entry *entry) { kref_put(&entry->kref, free_gid_entry); } static int add_roce_gid(struct ib_gid_table_entry *entry) { const struct ib_gid_attr *attr = &entry->attr; int ret; if (!attr->ndev) { dev_err(&attr->device->dev, "%s NULL netdev port=%u index=%u\n", __func__, attr->port_num, attr->index); return -EINVAL; } if (rdma_cap_roce_gid_table(attr->device, attr->port_num)) { ret = attr->device->ops.add_gid(attr, &entry->context); if (ret) { dev_err(&attr->device->dev, "%s GID add failed port=%u index=%u\n", __func__, attr->port_num, attr->index); return ret; } } return 0; } /** * del_gid - Delete GID table entry * * @ib_dev: IB device whose GID entry to be deleted * @port: Port number of the IB device * @table: GID table of the IB device for a port * @ix: GID entry index to delete * */ static void del_gid(struct ib_device *ib_dev, u32 port, struct ib_gid_table *table, int ix) { struct roce_gid_ndev_storage *ndev_storage; struct ib_gid_table_entry *entry; lockdep_assert_held(&table->lock); dev_dbg(&ib_dev->dev, "%s port=%u index=%d gid %pI6\n", __func__, port, ix, table->data_vec[ix]->attr.gid.raw); write_lock_irq(&table->rwlock); entry = table->data_vec[ix]; entry->state = GID_TABLE_ENTRY_PENDING_DEL; /* * For non RoCE protocol, GID entry slot is ready to use. */ if (!rdma_protocol_roce(ib_dev, port)) table->data_vec[ix] = NULL; write_unlock_irq(&table->rwlock); if (rdma_cap_roce_gid_table(ib_dev, port)) ib_dev->ops.del_gid(&entry->attr, &entry->context); ndev_storage = entry->ndev_storage; if (ndev_storage) { entry->ndev_storage = NULL; rcu_assign_pointer(entry->attr.ndev, NULL); call_rcu(&ndev_storage->rcu_head, put_gid_ndev); } put_gid_entry_locked(entry); } /** * add_modify_gid - Add or modify GID table entry * * @table: GID table in which GID to be added or modified * @attr: Attributes of the GID * * Returns 0 on success or appropriate error code. It accepts zero * GID addition for non RoCE ports for HCA's who report them as valid * GID. However such zero GIDs are not added to the cache. */ static int add_modify_gid(struct ib_gid_table *table, const struct ib_gid_attr *attr) { struct ib_gid_table_entry *entry; int ret = 0; /* * Invalidate any old entry in the table to make it safe to write to * this index. */ if (is_gid_entry_valid(table->data_vec[attr->index])) del_gid(attr->device, attr->port_num, table, attr->index); /* * Some HCA's report multiple GID entries with only one valid GID, and * leave other unused entries as the zero GID. Convert zero GIDs to * empty table entries instead of storing them. */ if (rdma_is_zero_gid(&attr->gid)) return 0; entry = alloc_gid_entry(attr); if (!entry) return -ENOMEM; if (rdma_protocol_roce(attr->device, attr->port_num)) { ret = add_roce_gid(entry); if (ret) goto done; } store_gid_entry(table, entry); return 0; done: put_gid_entry(entry); return ret; } /* rwlock should be read locked, or lock should be held */ static int find_gid(struct ib_gid_table *table, const union ib_gid *gid, const struct ib_gid_attr *val, bool default_gid, unsigned long mask, int *pempty) { int i = 0; int found = -1; int empty = pempty ? -1 : 0; while (i < table->sz && (found < 0 || empty < 0)) { struct ib_gid_table_entry *data = table->data_vec[i]; struct ib_gid_attr *attr; int curr_index = i; i++; /* find_gid() is used during GID addition where it is expected * to return a free entry slot which is not duplicate. * Free entry slot is requested and returned if pempty is set, * so lookup free slot only if requested. */ if (pempty && empty < 0) { if (is_gid_entry_free(data) && default_gid == is_gid_index_default(table, curr_index)) { /* * Found an invalid (free) entry; allocate it. * If default GID is requested, then our * found slot must be one of the DEFAULT * reserved slots or we fail. * This ensures that only DEFAULT reserved * slots are used for default property GIDs. */ empty = curr_index; } } /* * Additionally find_gid() is used to find valid entry during * lookup operation; so ignore the entries which are marked as * pending for removal and the entries which are marked as * invalid. */ if (!is_gid_entry_valid(data)) continue; if (found >= 0) continue; attr = &data->attr; if (mask & GID_ATTR_FIND_MASK_GID_TYPE && attr->gid_type != val->gid_type) continue; if (mask & GID_ATTR_FIND_MASK_GID && memcmp(gid, &data->attr.gid, sizeof(*gid))) continue; if (mask & GID_ATTR_FIND_MASK_NETDEV && attr->ndev != val->ndev) continue; if (mask & GID_ATTR_FIND_MASK_DEFAULT && is_gid_index_default(table, curr_index) != default_gid) continue; found = curr_index; } if (pempty) *pempty = empty; return found; } static void make_default_gid(struct net_device *dev, union ib_gid *gid) { gid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL); addrconf_ifid_eui48(&gid->raw[8], dev); } static int __ib_cache_gid_add(struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *attr, unsigned long mask, bool default_gid) { struct ib_gid_table *table; int ret = 0; int empty; int ix; /* Do not allow adding zero GID in support of * IB spec version 1.3 section 4.1.1 point (6) and * section 12.7.10 and section 12.7.20 */ if (rdma_is_zero_gid(gid)) return -EINVAL; table = rdma_gid_table(ib_dev, port); mutex_lock(&table->lock); ix = find_gid(table, gid, attr, default_gid, mask, &empty); if (ix >= 0) goto out_unlock; if (empty < 0) { ret = -ENOSPC; goto out_unlock; } attr->device = ib_dev; attr->index = empty; attr->port_num = port; attr->gid = *gid; ret = add_modify_gid(table, attr); if (!ret) dispatch_gid_change_event(ib_dev, port); out_unlock: mutex_unlock(&table->lock); if (ret) pr_warn("%s: unable to add gid %pI6 error=%d\n", __func__, gid->raw, ret); return ret; } int ib_cache_gid_add(struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *attr) { unsigned long mask = GID_ATTR_FIND_MASK_GID | GID_ATTR_FIND_MASK_GID_TYPE | GID_ATTR_FIND_MASK_NETDEV; return __ib_cache_gid_add(ib_dev, port, gid, attr, mask, false); } static int _ib_cache_gid_del(struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *attr, unsigned long mask, bool default_gid) { struct ib_gid_table *table; int ret = 0; int ix; table = rdma_gid_table(ib_dev, port); mutex_lock(&table->lock); ix = find_gid(table, gid, attr, default_gid, mask, NULL); if (ix < 0) { ret = -EINVAL; goto out_unlock; } del_gid(ib_dev, port, table, ix); dispatch_gid_change_event(ib_dev, port); out_unlock: mutex_unlock(&table->lock); if (ret) pr_debug("%s: can't delete gid %pI6 error=%d\n", __func__, gid->raw, ret); return ret; } int ib_cache_gid_del(struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *attr) { unsigned long mask = GID_ATTR_FIND_MASK_GID | GID_ATTR_FIND_MASK_GID_TYPE | GID_ATTR_FIND_MASK_DEFAULT | GID_ATTR_FIND_MASK_NETDEV; return _ib_cache_gid_del(ib_dev, port, gid, attr, mask, false); } int ib_cache_gid_del_all_netdev_gids(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { struct ib_gid_table *table; int ix; bool deleted = false; table = rdma_gid_table(ib_dev, port); mutex_lock(&table->lock); for (ix = 0; ix < table->sz; ix++) { if (is_gid_entry_valid(table->data_vec[ix]) && table->data_vec[ix]->attr.ndev == ndev) { del_gid(ib_dev, port, table, ix); deleted = true; } } mutex_unlock(&table->lock); if (deleted) dispatch_gid_change_event(ib_dev, port); return 0; } /** * rdma_find_gid_by_port - Returns the GID entry attributes when it finds * a valid GID entry for given search parameters. It searches for the specified * GID value in the local software cache. * @ib_dev: The device to query. * @gid: The GID value to search for. * @gid_type: The GID type to search for. * @port: The port number of the device where the GID value should be searched. * @ndev: In RoCE, the net device of the device. NULL means ignore. * * Returns sgid attributes if the GID is found with valid reference or * returns ERR_PTR for the error. * The caller must invoke rdma_put_gid_attr() to release the reference. */ const struct ib_gid_attr * rdma_find_gid_by_port(struct ib_device *ib_dev, const union ib_gid *gid, enum ib_gid_type gid_type, u32 port, struct net_device *ndev) { int local_index; struct ib_gid_table *table; unsigned long mask = GID_ATTR_FIND_MASK_GID | GID_ATTR_FIND_MASK_GID_TYPE; struct ib_gid_attr val = {.ndev = ndev, .gid_type = gid_type}; const struct ib_gid_attr *attr; unsigned long flags; if (!rdma_is_port_valid(ib_dev, port)) return ERR_PTR(-ENOENT); table = rdma_gid_table(ib_dev, port); if (ndev) mask |= GID_ATTR_FIND_MASK_NETDEV; read_lock_irqsave(&table->rwlock, flags); local_index = find_gid(table, gid, &val, false, mask, NULL); if (local_index >= 0) { get_gid_entry(table->data_vec[local_index]); attr = &table->data_vec[local_index]->attr; read_unlock_irqrestore(&table->rwlock, flags); return attr; } read_unlock_irqrestore(&table->rwlock, flags); return ERR_PTR(-ENOENT); } EXPORT_SYMBOL(rdma_find_gid_by_port); /** * rdma_find_gid_by_filter - Returns the GID table attribute where a * specified GID value occurs * @ib_dev: The device to query. * @gid: The GID value to search for. * @port: The port number of the device where the GID value could be * searched. * @filter: The filter function is executed on any matching GID in the table. * If the filter function returns true, the corresponding index is returned, * otherwise, we continue searching the GID table. It's guaranteed that * while filter is executed, ndev field is valid and the structure won't * change. filter is executed in an atomic context. filter must not be NULL. * @context: Private data to pass into the call-back. * * rdma_find_gid_by_filter() searches for the specified GID value * of which the filter function returns true in the port's GID table. * */ const struct ib_gid_attr *rdma_find_gid_by_filter( struct ib_device *ib_dev, const union ib_gid *gid, u32 port, bool (*filter)(const union ib_gid *gid, const struct ib_gid_attr *, void *), void *context) { const struct ib_gid_attr *res = ERR_PTR(-ENOENT); struct ib_gid_table *table; unsigned long flags; unsigned int i; if (!rdma_is_port_valid(ib_dev, port)) return ERR_PTR(-EINVAL); table = rdma_gid_table(ib_dev, port); read_lock_irqsave(&table->rwlock, flags); for (i = 0; i < table->sz; i++) { struct ib_gid_table_entry *entry = table->data_vec[i]; if (!is_gid_entry_valid(entry)) continue; if (memcmp(gid, &entry->attr.gid, sizeof(*gid))) continue; if (filter(gid, &entry->attr, context)) { get_gid_entry(entry); res = &entry->attr; break; } } read_unlock_irqrestore(&table->rwlock, flags); return res; } static struct ib_gid_table *alloc_gid_table(int sz) { struct ib_gid_table *table = kzalloc(sizeof(*table), GFP_KERNEL); if (!table) return NULL; table->data_vec = kcalloc(sz, sizeof(*table->data_vec), GFP_KERNEL); if (!table->data_vec) goto err_free_table; mutex_init(&table->lock); table->sz = sz; rwlock_init(&table->rwlock); return table; err_free_table: kfree(table); return NULL; } static void release_gid_table(struct ib_device *device, struct ib_gid_table *table) { bool leak = false; int i; if (!table) return; for (i = 0; i < table->sz; i++) { if (is_gid_entry_free(table->data_vec[i])) continue; if (kref_read(&table->data_vec[i]->kref) > 1) { dev_err(&device->dev, "GID entry ref leak for index %d ref=%u\n", i, kref_read(&table->data_vec[i]->kref)); leak = true; } } if (leak) return; mutex_destroy(&table->lock); kfree(table->data_vec); kfree(table); } static void cleanup_gid_table_port(struct ib_device *ib_dev, u32 port, struct ib_gid_table *table) { int i; if (!table) return; mutex_lock(&table->lock); for (i = 0; i < table->sz; ++i) { if (is_gid_entry_valid(table->data_vec[i])) del_gid(ib_dev, port, table, i); } mutex_unlock(&table->lock); } void ib_cache_gid_set_default_gid(struct ib_device *ib_dev, u32 port, struct net_device *ndev, unsigned long gid_type_mask, enum ib_cache_gid_default_mode mode) { union ib_gid gid = { }; struct ib_gid_attr gid_attr; unsigned int gid_type; unsigned long mask; mask = GID_ATTR_FIND_MASK_GID_TYPE | GID_ATTR_FIND_MASK_DEFAULT | GID_ATTR_FIND_MASK_NETDEV; memset(&gid_attr, 0, sizeof(gid_attr)); gid_attr.ndev = ndev; for (gid_type = 0; gid_type < IB_GID_TYPE_SIZE; ++gid_type) { if (1UL << gid_type & ~gid_type_mask) continue; gid_attr.gid_type = gid_type; if (mode == IB_CACHE_GID_DEFAULT_MODE_SET) { make_default_gid(ndev, &gid); __ib_cache_gid_add(ib_dev, port, &gid, &gid_attr, mask, true); } else if (mode == IB_CACHE_GID_DEFAULT_MODE_DELETE) { _ib_cache_gid_del(ib_dev, port, &gid, &gid_attr, mask, true); } } } static void gid_table_reserve_default(struct ib_device *ib_dev, u32 port, struct ib_gid_table *table) { unsigned int i; unsigned long roce_gid_type_mask; unsigned int num_default_gids; roce_gid_type_mask = roce_gid_type_mask_support(ib_dev, port); num_default_gids = hweight_long(roce_gid_type_mask); /* Reserve starting indices for default GIDs */ for (i = 0; i < num_default_gids && i < table->sz; i++) table->default_gid_indices |= BIT(i); } static void gid_table_release_one(struct ib_device *ib_dev) { u32 p; rdma_for_each_port (ib_dev, p) { release_gid_table(ib_dev, ib_dev->port_data[p].cache.gid); ib_dev->port_data[p].cache.gid = NULL; } } static int _gid_table_setup_one(struct ib_device *ib_dev) { struct ib_gid_table *table; u32 rdma_port; rdma_for_each_port (ib_dev, rdma_port) { table = alloc_gid_table( ib_dev->port_data[rdma_port].immutable.gid_tbl_len); if (!table) goto rollback_table_setup; gid_table_reserve_default(ib_dev, rdma_port, table); ib_dev->port_data[rdma_port].cache.gid = table; } return 0; rollback_table_setup: gid_table_release_one(ib_dev); return -ENOMEM; } static void gid_table_cleanup_one(struct ib_device *ib_dev) { u32 p; rdma_for_each_port (ib_dev, p) cleanup_gid_table_port(ib_dev, p, ib_dev->port_data[p].cache.gid); } static int gid_table_setup_one(struct ib_device *ib_dev) { int err; err = _gid_table_setup_one(ib_dev); if (err) return err; rdma_roce_rescan_device(ib_dev); return err; } /** * rdma_query_gid - Read the GID content from the GID software cache * @device: Device to query the GID * @port_num: Port number of the device * @index: Index of the GID table entry to read * @gid: Pointer to GID where to store the entry's GID * * rdma_query_gid() only reads the GID entry content for requested device, * port and index. It reads for IB, RoCE and iWarp link layers. It doesn't * hold any reference to the GID table entry in the HCA or software cache. * * Returns 0 on success or appropriate error code. * */ int rdma_query_gid(struct ib_device *device, u32 port_num, int index, union ib_gid *gid) { struct ib_gid_table *table; unsigned long flags; int res; if (!rdma_is_port_valid(device, port_num)) return -EINVAL; table = rdma_gid_table(device, port_num); read_lock_irqsave(&table->rwlock, flags); if (index < 0 || index >= table->sz) { res = -EINVAL; goto done; } if (!is_gid_entry_valid(table->data_vec[index])) { res = -ENOENT; goto done; } memcpy(gid, &table->data_vec[index]->attr.gid, sizeof(*gid)); res = 0; done: read_unlock_irqrestore(&table->rwlock, flags); return res; } EXPORT_SYMBOL(rdma_query_gid); /** * rdma_read_gid_hw_context - Read the HW GID context from GID attribute * @attr: Potinter to the GID attribute * * rdma_read_gid_hw_context() reads the drivers GID HW context corresponding * to the SGID attr. Callers are required to already be holding the reference * to an existing GID entry. * * Returns the HW GID context * */ void *rdma_read_gid_hw_context(const struct ib_gid_attr *attr) { return container_of(attr, struct ib_gid_table_entry, attr)->context; } EXPORT_SYMBOL(rdma_read_gid_hw_context); /** * rdma_find_gid - Returns SGID attributes if the matching GID is found. * @device: The device to query. * @gid: The GID value to search for. * @gid_type: The GID type to search for. * @ndev: In RoCE, the net device of the device. NULL means ignore. * * rdma_find_gid() searches for the specified GID value in the software cache. * * Returns GID attributes if a valid GID is found or returns ERR_PTR for the * error. The caller must invoke rdma_put_gid_attr() to release the reference. * */ const struct ib_gid_attr *rdma_find_gid(struct ib_device *device, const union ib_gid *gid, enum ib_gid_type gid_type, struct net_device *ndev) { unsigned long mask = GID_ATTR_FIND_MASK_GID | GID_ATTR_FIND_MASK_GID_TYPE; struct ib_gid_attr gid_attr_val = {.ndev = ndev, .gid_type = gid_type}; u32 p; if (ndev) mask |= GID_ATTR_FIND_MASK_NETDEV; rdma_for_each_port(device, p) { struct ib_gid_table *table; unsigned long flags; int index; table = device->port_data[p].cache.gid; read_lock_irqsave(&table->rwlock, flags); index = find_gid(table, gid, &gid_attr_val, false, mask, NULL); if (index >= 0) { const struct ib_gid_attr *attr; get_gid_entry(table->data_vec[index]); attr = &table->data_vec[index]->attr; read_unlock_irqrestore(&table->rwlock, flags); return attr; } read_unlock_irqrestore(&table->rwlock, flags); } return ERR_PTR(-ENOENT); } EXPORT_SYMBOL(rdma_find_gid); int ib_get_cached_pkey(struct ib_device *device, u32 port_num, int index, u16 *pkey) { struct ib_pkey_cache *cache; unsigned long flags; int ret = 0; if (!rdma_is_port_valid(device, port_num)) return -EINVAL; read_lock_irqsave(&device->cache_lock, flags); cache = device->port_data[port_num].cache.pkey; if (!cache || index < 0 || index >= cache->table_len) ret = -EINVAL; else *pkey = cache->table[index]; read_unlock_irqrestore(&device->cache_lock, flags); return ret; } EXPORT_SYMBOL(ib_get_cached_pkey); void ib_get_cached_subnet_prefix(struct ib_device *device, u32 port_num, u64 *sn_pfx) { unsigned long flags; read_lock_irqsave(&device->cache_lock, flags); *sn_pfx = device->port_data[port_num].cache.subnet_prefix; read_unlock_irqrestore(&device->cache_lock, flags); } EXPORT_SYMBOL(ib_get_cached_subnet_prefix); int ib_find_cached_pkey(struct ib_device *device, u32 port_num, u16 pkey, u16 *index) { struct ib_pkey_cache *cache; unsigned long flags; int i; int ret = -ENOENT; int partial_ix = -1; if (!rdma_is_port_valid(device, port_num)) return -EINVAL; read_lock_irqsave(&device->cache_lock, flags); cache = device->port_data[port_num].cache.pkey; if (!cache) { ret = -EINVAL; goto err; } *index = -1; for (i = 0; i < cache->table_len; ++i) if ((cache->table[i] & 0x7fff) == (pkey & 0x7fff)) { if (cache->table[i] & 0x8000) { *index = i; ret = 0; break; } else { partial_ix = i; } } if (ret && partial_ix >= 0) { *index = partial_ix; ret = 0; } err: read_unlock_irqrestore(&device->cache_lock, flags); return ret; } EXPORT_SYMBOL(ib_find_cached_pkey); int ib_find_exact_cached_pkey(struct ib_device *device, u32 port_num, u16 pkey, u16 *index) { struct ib_pkey_cache *cache; unsigned long flags; int i; int ret = -ENOENT; if (!rdma_is_port_valid(device, port_num)) return -EINVAL; read_lock_irqsave(&device->cache_lock, flags); cache = device->port_data[port_num].cache.pkey; if (!cache) { ret = -EINVAL; goto err; } *index = -1; for (i = 0; i < cache->table_len; ++i) if (cache->table[i] == pkey) { *index = i; ret = 0; break; } err: read_unlock_irqrestore(&device->cache_lock, flags); return ret; } EXPORT_SYMBOL(ib_find_exact_cached_pkey); int ib_get_cached_lmc(struct ib_device *device, u32 port_num, u8 *lmc) { unsigned long flags; int ret = 0; if (!rdma_is_port_valid(device, port_num)) return -EINVAL; read_lock_irqsave(&device->cache_lock, flags); *lmc = device->port_data[port_num].cache.lmc; read_unlock_irqrestore(&device->cache_lock, flags); return ret; } EXPORT_SYMBOL(ib_get_cached_lmc); int ib_get_cached_port_state(struct ib_device *device, u32 port_num, enum ib_port_state *port_state) { unsigned long flags; int ret = 0; if (!rdma_is_port_valid(device, port_num)) return -EINVAL; read_lock_irqsave(&device->cache_lock, flags); *port_state = device->port_data[port_num].cache.port_state; read_unlock_irqrestore(&device->cache_lock, flags); return ret; } EXPORT_SYMBOL(ib_get_cached_port_state); /** * rdma_get_gid_attr - Returns GID attributes for a port of a device * at a requested gid_index, if a valid GID entry exists. * @device: The device to query. * @port_num: The port number on the device where the GID value * is to be queried. * @index: Index of the GID table entry whose attributes are to * be queried. * * rdma_get_gid_attr() acquires reference count of gid attributes from the * cached GID table. Caller must invoke rdma_put_gid_attr() to release * reference to gid attribute regardless of link layer. * * Returns pointer to valid gid attribute or ERR_PTR for the appropriate error * code. */ const struct ib_gid_attr * rdma_get_gid_attr(struct ib_device *device, u32 port_num, int index) { const struct ib_gid_attr *attr = ERR_PTR(-ENODATA); struct ib_gid_table *table; unsigned long flags; if (!rdma_is_port_valid(device, port_num)) return ERR_PTR(-EINVAL); table = rdma_gid_table(device, port_num); if (index < 0 || index >= table->sz) return ERR_PTR(-EINVAL); read_lock_irqsave(&table->rwlock, flags); if (!is_gid_entry_valid(table->data_vec[index])) goto done; get_gid_entry(table->data_vec[index]); attr = &table->data_vec[index]->attr; done: read_unlock_irqrestore(&table->rwlock, flags); return attr; } EXPORT_SYMBOL(rdma_get_gid_attr); /** * rdma_query_gid_table - Reads GID table entries of all the ports of a device up to max_entries. * @device: The device to query. * @entries: Entries where GID entries are returned. * @max_entries: Maximum number of entries that can be returned. * Entries array must be allocated to hold max_entries number of entries. * * Returns number of entries on success or appropriate error code. */ ssize_t rdma_query_gid_table(struct ib_device *device, struct ib_uverbs_gid_entry *entries, size_t max_entries) { const struct ib_gid_attr *gid_attr; ssize_t num_entries = 0, ret; struct ib_gid_table *table; u32 port_num, i; struct net_device *ndev; unsigned long flags; rdma_for_each_port(device, port_num) { table = rdma_gid_table(device, port_num); read_lock_irqsave(&table->rwlock, flags); for (i = 0; i < table->sz; i++) { if (!is_gid_entry_valid(table->data_vec[i])) continue; if (num_entries >= max_entries) { ret = -EINVAL; goto err; } gid_attr = &table->data_vec[i]->attr; memcpy(&entries->gid, &gid_attr->gid, sizeof(gid_attr->gid)); entries->gid_index = gid_attr->index; entries->port_num = gid_attr->port_num; entries->gid_type = gid_attr->gid_type; ndev = rcu_dereference_protected( gid_attr->ndev, lockdep_is_held(&table->rwlock)); if (ndev) entries->netdev_ifindex = ndev->ifindex; num_entries++; entries++; } read_unlock_irqrestore(&table->rwlock, flags); } return num_entries; err: read_unlock_irqrestore(&table->rwlock, flags); return ret; } EXPORT_SYMBOL(rdma_query_gid_table); /** * rdma_put_gid_attr - Release reference to the GID attribute * @attr: Pointer to the GID attribute whose reference * needs to be released. * * rdma_put_gid_attr() must be used to release reference whose * reference is acquired using rdma_get_gid_attr() or any APIs * which returns a pointer to the ib_gid_attr regardless of link layer * of IB or RoCE. * */ void rdma_put_gid_attr(const struct ib_gid_attr *attr) { struct ib_gid_table_entry *entry = container_of(attr, struct ib_gid_table_entry, attr); put_gid_entry(entry); } EXPORT_SYMBOL(rdma_put_gid_attr); /** * rdma_hold_gid_attr - Get reference to existing GID attribute * * @attr: Pointer to the GID attribute whose reference * needs to be taken. * * Increase the reference count to a GID attribute to keep it from being * freed. Callers are required to already be holding a reference to attribute. * */ void rdma_hold_gid_attr(const struct ib_gid_attr *attr) { struct ib_gid_table_entry *entry = container_of(attr, struct ib_gid_table_entry, attr); get_gid_entry(entry); } EXPORT_SYMBOL(rdma_hold_gid_attr); /** * rdma_read_gid_attr_ndev_rcu - Read GID attribute netdevice * which must be in UP state. * * @attr:Pointer to the GID attribute * * Returns pointer to netdevice if the netdevice was attached to GID and * netdevice is in UP state. Caller must hold RCU lock as this API * reads the netdev flags which can change while netdevice migrates to * different net namespace. Returns ERR_PTR with error code otherwise. * */ struct net_device *rdma_read_gid_attr_ndev_rcu(const struct ib_gid_attr *attr) { struct ib_gid_table_entry *entry = container_of(attr, struct ib_gid_table_entry, attr); struct ib_device *device = entry->attr.device; struct net_device *ndev = ERR_PTR(-EINVAL); u32 port_num = entry->attr.port_num; struct ib_gid_table *table; unsigned long flags; bool valid; table = rdma_gid_table(device, port_num); read_lock_irqsave(&table->rwlock, flags); valid = is_gid_entry_valid(table->data_vec[attr->index]); if (valid) { ndev = rcu_dereference(attr->ndev); if (!ndev) ndev = ERR_PTR(-ENODEV); } read_unlock_irqrestore(&table->rwlock, flags); return ndev; } EXPORT_SYMBOL(rdma_read_gid_attr_ndev_rcu); static int get_lower_dev_vlan(struct net_device *lower_dev, struct netdev_nested_priv *priv) { u16 *vlan_id = (u16 *)priv->data; if (is_vlan_dev(lower_dev)) *vlan_id = vlan_dev_vlan_id(lower_dev); /* We are interested only in first level vlan device, so * always return 1 to stop iterating over next level devices. */ return 1; } /** * rdma_read_gid_l2_fields - Read the vlan ID and source MAC address * of a GID entry. * * @attr: GID attribute pointer whose L2 fields to be read * @vlan_id: Pointer to vlan id to fill up if the GID entry has * vlan id. It is optional. * @smac: Pointer to smac to fill up for a GID entry. It is optional. * * rdma_read_gid_l2_fields() returns 0 on success and returns vlan id * (if gid entry has vlan) and source MAC, or returns error. */ int rdma_read_gid_l2_fields(const struct ib_gid_attr *attr, u16 *vlan_id, u8 *smac) { struct netdev_nested_priv priv = { .data = (void *)vlan_id, }; struct net_device *ndev; rcu_read_lock(); ndev = rcu_dereference(attr->ndev); if (!ndev) { rcu_read_unlock(); return -ENODEV; } if (smac) ether_addr_copy(smac, ndev->dev_addr); if (vlan_id) { *vlan_id = 0xffff; if (is_vlan_dev(ndev)) { *vlan_id = vlan_dev_vlan_id(ndev); } else { /* If the netdev is upper device and if it's lower * device is vlan device, consider vlan id of * the lower vlan device for this gid entry. */ netdev_walk_all_lower_dev_rcu(attr->ndev, get_lower_dev_vlan, &priv); } } rcu_read_unlock(); return 0; } EXPORT_SYMBOL(rdma_read_gid_l2_fields); static int config_non_roce_gid_cache(struct ib_device *device, u32 port, struct ib_port_attr *tprops) { struct ib_gid_attr gid_attr = {}; struct ib_gid_table *table; int ret = 0; int i; gid_attr.device = device; gid_attr.port_num = port; table = rdma_gid_table(device, port); mutex_lock(&table->lock); for (i = 0; i < tprops->gid_tbl_len; ++i) { if (!device->ops.query_gid) continue; ret = device->ops.query_gid(device, port, i, &gid_attr.gid); if (ret) { dev_warn(&device->dev, "query_gid failed (%d) for index %d\n", ret, i); goto err; } if (rdma_protocol_iwarp(device, port)) { struct net_device *ndev; ndev = ib_device_get_netdev(device, port); if (!ndev) continue; RCU_INIT_POINTER(gid_attr.ndev, ndev); dev_put(ndev); } gid_attr.index = i; tprops->subnet_prefix = be64_to_cpu(gid_attr.gid.global.subnet_prefix); add_modify_gid(table, &gid_attr); } err: mutex_unlock(&table->lock); return ret; } static int ib_cache_update(struct ib_device *device, u32 port, bool update_gids, bool update_pkeys, bool enforce_security) { struct ib_port_attr *tprops = NULL; struct ib_pkey_cache *pkey_cache = NULL; struct ib_pkey_cache *old_pkey_cache = NULL; int i; int ret; if (!rdma_is_port_valid(device, port)) return -EINVAL; tprops = kmalloc(sizeof *tprops, GFP_KERNEL); if (!tprops) return -ENOMEM; ret = ib_query_port(device, port, tprops); if (ret) { dev_warn(&device->dev, "ib_query_port failed (%d)\n", ret); goto err; } if (!rdma_protocol_roce(device, port) && update_gids) { ret = config_non_roce_gid_cache(device, port, tprops); if (ret) goto err; } update_pkeys &= !!tprops->pkey_tbl_len; if (update_pkeys) { pkey_cache = kmalloc(struct_size(pkey_cache, table, tprops->pkey_tbl_len), GFP_KERNEL); if (!pkey_cache) { ret = -ENOMEM; goto err; } pkey_cache->table_len = tprops->pkey_tbl_len; for (i = 0; i < pkey_cache->table_len; ++i) { ret = ib_query_pkey(device, port, i, pkey_cache->table + i); if (ret) { dev_warn(&device->dev, "ib_query_pkey failed (%d) for index %d\n", ret, i); goto err; } } } write_lock_irq(&device->cache_lock); if (update_pkeys) { old_pkey_cache = device->port_data[port].cache.pkey; device->port_data[port].cache.pkey = pkey_cache; } device->port_data[port].cache.lmc = tprops->lmc; device->port_data[port].cache.port_state = tprops->state; device->port_data[port].cache.subnet_prefix = tprops->subnet_prefix; write_unlock_irq(&device->cache_lock); if (enforce_security) ib_security_cache_change(device, port, tprops->subnet_prefix); kfree(old_pkey_cache); kfree(tprops); return 0; err: kfree(pkey_cache); kfree(tprops); return ret; } static void ib_cache_event_task(struct work_struct *_work) { struct ib_update_work *work = container_of(_work, struct ib_update_work, work); int ret; /* Before distributing the cache update event, first sync * the cache. */ ret = ib_cache_update(work->event.device, work->event.element.port_num, work->event.event == IB_EVENT_GID_CHANGE, work->event.event == IB_EVENT_PKEY_CHANGE, work->enforce_security); /* GID event is notified already for individual GID entries by * dispatch_gid_change_event(). Hence, notifiy for rest of the * events. */ if (!ret && work->event.event != IB_EVENT_GID_CHANGE) ib_dispatch_event_clients(&work->event); kfree(work); } static void ib_generic_event_task(struct work_struct *_work) { struct ib_update_work *work = container_of(_work, struct ib_update_work, work); ib_dispatch_event_clients(&work->event); kfree(work); } static bool is_cache_update_event(const struct ib_event *event) { return (event->event == IB_EVENT_PORT_ERR || event->event == IB_EVENT_PORT_ACTIVE || event->event == IB_EVENT_LID_CHANGE || event->event == IB_EVENT_PKEY_CHANGE || event->event == IB_EVENT_CLIENT_REREGISTER || event->event == IB_EVENT_GID_CHANGE); } /** * ib_dispatch_event - Dispatch an asynchronous event * @event:Event to dispatch * * Low-level drivers must call ib_dispatch_event() to dispatch the * event to all registered event handlers when an asynchronous event * occurs. */ void ib_dispatch_event(const struct ib_event *event) { struct ib_update_work *work; work = kzalloc(sizeof(*work), GFP_ATOMIC); if (!work) return; if (is_cache_update_event(event)) INIT_WORK(&work->work, ib_cache_event_task); else INIT_WORK(&work->work, ib_generic_event_task); work->event = *event; if (event->event == IB_EVENT_PKEY_CHANGE || event->event == IB_EVENT_GID_CHANGE) work->enforce_security = true; queue_work(ib_wq, &work->work); } EXPORT_SYMBOL(ib_dispatch_event); int ib_cache_setup_one(struct ib_device *device) { u32 p; int err; err = gid_table_setup_one(device); if (err) return err; rdma_for_each_port (device, p) { err = ib_cache_update(device, p, true, true, true); if (err) return err; } return 0; } void ib_cache_release_one(struct ib_device *device) { u32 p; /* * The release function frees all the cache elements. * This function should be called as part of freeing * all the device's resources when the cache could no * longer be accessed. */ rdma_for_each_port (device, p) kfree(device->port_data[p].cache.pkey); gid_table_release_one(device); } void ib_cache_cleanup_one(struct ib_device *device) { /* The cleanup function waits for all in-progress workqueue * elements and cleans up the GID cache. This function should be * called after the device was removed from the devices list and * all clients were removed, so the cache exists but is * non-functional and shouldn't be updated anymore. */ flush_workqueue(ib_wq); gid_table_cleanup_one(device); /* * Flush the wq second time for any pending GID delete work. */ flush_workqueue(ib_wq); } |
| 1554 1552 6 4 10 4 4 6 6 1557 1552 1564 1553 8 6 6 6 6 6 8 6 6 6 6 6 6 6 6 6 6 2 2 2 2 12 1 13 13 12 13 13 13 13 13 6 13 4 4 4 3 4 4 4 4 4 4 13 4 4 5 4 4 4 13 10 4 4 4 32 32 31 31 32 32 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic helpers for smp ipi calls * * (C) Jens Axboe <jens.axboe@oracle.com> 2008 */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/irq_work.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/gfp.h> #include <linux/smp.h> #include <linux/cpu.h> #include <linux/sched.h> #include <linux/sched/idle.h> #include <linux/hypervisor.h> #include <linux/sched/clock.h> #include <linux/nmi.h> #include <linux/sched/debug.h> #include <linux/jump_label.h> #include <trace/events/ipi.h> #define CREATE_TRACE_POINTS #include <trace/events/csd.h> #undef CREATE_TRACE_POINTS #include "smpboot.h" #include "sched/smp.h" #define CSD_TYPE(_csd) ((_csd)->node.u_flags & CSD_FLAG_TYPE_MASK) struct call_function_data { call_single_data_t __percpu *csd; cpumask_var_t cpumask; cpumask_var_t cpumask_ipi; }; static DEFINE_PER_CPU_ALIGNED(struct call_function_data, cfd_data); static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue); static DEFINE_PER_CPU(atomic_t, trigger_backtrace) = ATOMIC_INIT(1); static void __flush_smp_call_function_queue(bool warn_cpu_offline); int smpcfd_prepare_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, cpu_to_node(cpu))) return -ENOMEM; if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL, cpu_to_node(cpu))) { free_cpumask_var(cfd->cpumask); return -ENOMEM; } cfd->csd = alloc_percpu(call_single_data_t); if (!cfd->csd) { free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); return -ENOMEM; } return 0; } int smpcfd_dead_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); free_percpu(cfd->csd); return 0; } int smpcfd_dying_cpu(unsigned int cpu) { /* * The IPIs for the smp-call-function callbacks queued by other * CPUs might arrive late, either due to hardware latencies or * because this CPU disabled interrupts (inside stop-machine) * before the IPIs were sent. So flush out any pending callbacks * explicitly (without waiting for the IPIs to arrive), to * ensure that the outgoing CPU doesn't go offline with work * still pending. */ __flush_smp_call_function_queue(false); irq_work_run(); return 0; } void __init call_function_init(void) { int i; for_each_possible_cpu(i) init_llist_head(&per_cpu(call_single_queue, i)); smpcfd_prepare_cpu(smp_processor_id()); } static __always_inline void send_call_function_single_ipi(int cpu) { if (call_function_single_prep_ipi(cpu)) { trace_ipi_send_cpu(cpu, _RET_IP_, generic_smp_call_function_single_interrupt); arch_send_call_function_single_ipi(cpu); } } static __always_inline void send_call_function_ipi_mask(struct cpumask *mask) { trace_ipi_send_cpumask(mask, _RET_IP_, generic_smp_call_function_single_interrupt); arch_send_call_function_ipi_mask(mask); } static __always_inline void csd_do_func(smp_call_func_t func, void *info, call_single_data_t *csd) { trace_csd_function_entry(func, csd); func(info); trace_csd_function_exit(func, csd); } #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG static DEFINE_STATIC_KEY_MAYBE(CONFIG_CSD_LOCK_WAIT_DEBUG_DEFAULT, csdlock_debug_enabled); /* * Parse the csdlock_debug= kernel boot parameter. * * If you need to restore the old "ext" value that once provided * additional debugging information, reapply the following commits: * * de7b09ef658d ("locking/csd_lock: Prepare more CSD lock debugging") * a5aabace5fb8 ("locking/csd_lock: Add more data to CSD lock debugging") */ static int __init csdlock_debug(char *str) { int ret; unsigned int val = 0; ret = get_option(&str, &val); if (ret) { if (val) static_branch_enable(&csdlock_debug_enabled); else static_branch_disable(&csdlock_debug_enabled); } return 1; } __setup("csdlock_debug=", csdlock_debug); static DEFINE_PER_CPU(call_single_data_t *, cur_csd); static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func); static DEFINE_PER_CPU(void *, cur_csd_info); static ulong csd_lock_timeout = 5000; /* CSD lock timeout in milliseconds. */ module_param(csd_lock_timeout, ulong, 0444); static int panic_on_ipistall; /* CSD panic timeout in milliseconds, 300000 for five minutes. */ module_param(panic_on_ipistall, int, 0444); static atomic_t csd_bug_count = ATOMIC_INIT(0); /* Record current CSD work for current CPU, NULL to erase. */ static void __csd_lock_record(call_single_data_t *csd) { if (!csd) { smp_mb(); /* NULL cur_csd after unlock. */ __this_cpu_write(cur_csd, NULL); return; } __this_cpu_write(cur_csd_func, csd->func); __this_cpu_write(cur_csd_info, csd->info); smp_wmb(); /* func and info before csd. */ __this_cpu_write(cur_csd, csd); smp_mb(); /* Update cur_csd before function call. */ /* Or before unlock, as the case may be. */ } static __always_inline void csd_lock_record(call_single_data_t *csd) { if (static_branch_unlikely(&csdlock_debug_enabled)) __csd_lock_record(csd); } static int csd_lock_wait_getcpu(call_single_data_t *csd) { unsigned int csd_type; csd_type = CSD_TYPE(csd); if (csd_type == CSD_TYPE_ASYNC || csd_type == CSD_TYPE_SYNC) return csd->node.dst; /* Other CSD_TYPE_ values might not have ->dst. */ return -1; } /* * Complain if too much time spent waiting. Note that only * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU, * so waiting on other types gets much less information. */ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id) { int cpu = -1; int cpux; bool firsttime; u64 ts2, ts_delta; call_single_data_t *cpu_cur_csd; unsigned int flags = READ_ONCE(csd->node.u_flags); unsigned long long csd_lock_timeout_ns = csd_lock_timeout * NSEC_PER_MSEC; if (!(flags & CSD_FLAG_LOCK)) { if (!unlikely(*bug_id)) return true; cpu = csd_lock_wait_getcpu(csd); pr_alert("csd: CSD lock (#%d) got unstuck on CPU#%02d, CPU#%02d released the lock.\n", *bug_id, raw_smp_processor_id(), cpu); return true; } ts2 = sched_clock(); /* How long since we last checked for a stuck CSD lock.*/ ts_delta = ts2 - *ts1; if (likely(ts_delta <= csd_lock_timeout_ns || csd_lock_timeout_ns == 0)) return false; firsttime = !*bug_id; if (firsttime) *bug_id = atomic_inc_return(&csd_bug_count); cpu = csd_lock_wait_getcpu(csd); if (WARN_ONCE(cpu < 0 || cpu >= nr_cpu_ids, "%s: cpu = %d\n", __func__, cpu)) cpux = 0; else cpux = cpu; cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux)); /* Before func and info. */ /* How long since this CSD lock was stuck. */ ts_delta = ts2 - ts0; pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %llu ns for CPU#%02d %pS(%ps).\n", firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), ts_delta, cpu, csd->func, csd->info); /* * If the CSD lock is still stuck after 5 minutes, it is unlikely * to become unstuck. Use a signed comparison to avoid triggering * on underflows when the TSC is out of sync between sockets. */ BUG_ON(panic_on_ipistall > 0 && (s64)ts_delta > ((s64)panic_on_ipistall * NSEC_PER_MSEC)); if (cpu_cur_csd && csd != cpu_cur_csd) { pr_alert("\tcsd: CSD lock (#%d) handling prior %pS(%ps) request.\n", *bug_id, READ_ONCE(per_cpu(cur_csd_func, cpux)), READ_ONCE(per_cpu(cur_csd_info, cpux))); } else { pr_alert("\tcsd: CSD lock (#%d) %s.\n", *bug_id, !cpu_cur_csd ? "unresponsive" : "handling this request"); } if (cpu >= 0) { if (atomic_cmpxchg_acquire(&per_cpu(trigger_backtrace, cpu), 1, 0)) dump_cpu_task(cpu); if (!cpu_cur_csd) { pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu); arch_send_call_function_single_ipi(cpu); } } if (firsttime) dump_stack(); *ts1 = ts2; return false; } /* * csd_lock/csd_unlock used to serialize access to per-cpu csd resources * * For non-synchronous ipi calls the csd can still be in use by the * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ static void __csd_lock_wait(call_single_data_t *csd) { int bug_id = 0; u64 ts0, ts1; ts1 = ts0 = sched_clock(); for (;;) { if (csd_lock_wait_toolong(csd, ts0, &ts1, &bug_id)) break; cpu_relax(); } smp_acquire__after_ctrl_dep(); } static __always_inline void csd_lock_wait(call_single_data_t *csd) { if (static_branch_unlikely(&csdlock_debug_enabled)) { __csd_lock_wait(csd); return; } smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK)); } #else static void csd_lock_record(call_single_data_t *csd) { } static __always_inline void csd_lock_wait(call_single_data_t *csd) { smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK)); } #endif static __always_inline void csd_lock(call_single_data_t *csd) { csd_lock_wait(csd); csd->node.u_flags |= CSD_FLAG_LOCK; /* * prevent CPU from reordering the above assignment * to ->flags with any subsequent assignments to other * fields of the specified call_single_data_t structure: */ smp_wmb(); } static __always_inline void csd_unlock(call_single_data_t *csd) { WARN_ON(!(csd->node.u_flags & CSD_FLAG_LOCK)); /* * ensure we're all done before releasing data: */ smp_store_release(&csd->node.u_flags, 0); } static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); void __smp_call_single_queue(int cpu, struct llist_node *node) { /* * We have to check the type of the CSD before queueing it, because * once queued it can have its flags cleared by * flush_smp_call_function_queue() * even if we haven't sent the smp_call IPI yet (e.g. the stopper * executes migration_cpu_stop() on the remote CPU). */ if (trace_csd_queue_cpu_enabled()) { call_single_data_t *csd; smp_call_func_t func; csd = container_of(node, call_single_data_t, node.llist); func = CSD_TYPE(csd) == CSD_TYPE_TTWU ? sched_ttwu_pending : csd->func; trace_csd_queue_cpu(cpu, _RET_IP_, func, csd); } /* * The list addition should be visible to the target CPU when it pops * the head of the list to pull the entry off it in the IPI handler * because of normal cache coherency rules implied by the underlying * llist ops. * * If IPIs can go out of order to the cache coherency protocol * in an architecture, sufficient synchronisation should be added * to arch code to make it appear to obey cache coherency WRT * locking and barrier primitives. Generic code isn't really * equipped to do the right thing... */ if (llist_add(node, &per_cpu(call_single_queue, cpu))) send_call_function_single_ipi(cpu); } /* * Insert a previously allocated call_single_data_t element * for execution on the given CPU. data must already have * ->func, ->info, and ->flags set. */ static int generic_exec_single(int cpu, call_single_data_t *csd) { if (cpu == smp_processor_id()) { smp_call_func_t func = csd->func; void *info = csd->info; unsigned long flags; /* * We can unlock early even for the synchronous on-stack case, * since we're doing this from the same CPU.. */ csd_lock_record(csd); csd_unlock(csd); local_irq_save(flags); csd_do_func(func, info, NULL); csd_lock_record(NULL); local_irq_restore(flags); return 0; } if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu)) { csd_unlock(csd); return -ENXIO; } __smp_call_single_queue(cpu, &csd->node.llist); return 0; } /** * generic_smp_call_function_single_interrupt - Execute SMP IPI callbacks * * Invoked by arch to handle an IPI for call function single. * Must be called with interrupts disabled. */ void generic_smp_call_function_single_interrupt(void) { __flush_smp_call_function_queue(true); } /** * __flush_smp_call_function_queue - Flush pending smp-call-function callbacks * * @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an * offline CPU. Skip this check if set to 'false'. * * Flush any pending smp-call-function callbacks queued on this CPU. This is * invoked by the generic IPI handler, as well as by a CPU about to go offline, * to ensure that all pending IPI callbacks are run before it goes completely * offline. * * Loop through the call_single_queue and run all the queued callbacks. * Must be called with interrupts disabled. */ static void __flush_smp_call_function_queue(bool warn_cpu_offline) { call_single_data_t *csd, *csd_next; struct llist_node *entry, *prev; struct llist_head *head; static bool warned; atomic_t *tbt; lockdep_assert_irqs_disabled(); /* Allow waiters to send backtrace NMI from here onwards */ tbt = this_cpu_ptr(&trigger_backtrace); atomic_set_release(tbt, 1); head = this_cpu_ptr(&call_single_queue); entry = llist_del_all(head); entry = llist_reverse_order(entry); /* There shouldn't be any pending callbacks on an offline CPU. */ if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) && !warned && entry != NULL)) { warned = true; WARN(1, "IPI on offline CPU %d\n", smp_processor_id()); /* * We don't have to use the _safe() variant here * because we are not invoking the IPI handlers yet. */ llist_for_each_entry(csd, entry, node.llist) { switch (CSD_TYPE(csd)) { case CSD_TYPE_ASYNC: case CSD_TYPE_SYNC: case CSD_TYPE_IRQ_WORK: pr_warn("IPI callback %pS sent to offline CPU\n", csd->func); break; case CSD_TYPE_TTWU: pr_warn("IPI task-wakeup sent to offline CPU\n"); break; default: pr_warn("IPI callback, unknown type %d, sent to offline CPU\n", CSD_TYPE(csd)); break; } } } /* * First; run all SYNC callbacks, people are waiting for us. */ prev = NULL; llist_for_each_entry_safe(csd, csd_next, entry, node.llist) { /* Do we wait until *after* callback? */ if (CSD_TYPE(csd) == CSD_TYPE_SYNC) { smp_call_func_t func = csd->func; void *info = csd->info; if (prev) { prev->next = &csd_next->node.llist; } else { entry = &csd_next->node.llist; } csd_lock_record(csd); csd_do_func(func, info, csd); csd_unlock(csd); csd_lock_record(NULL); } else { prev = &csd->node.llist; } } if (!entry) return; /* * Second; run all !SYNC callbacks. */ prev = NULL; llist_for_each_entry_safe(csd, csd_next, entry, node.llist) { int type = CSD_TYPE(csd); if (type != CSD_TYPE_TTWU) { if (prev) { prev->next = &csd_next->node.llist; } else { entry = &csd_next->node.llist; } if (type == CSD_TYPE_ASYNC) { smp_call_func_t func = csd->func; void *info = csd->info; csd_lock_record(csd); csd_unlock(csd); csd_do_func(func, info, csd); csd_lock_record(NULL); } else if (type == CSD_TYPE_IRQ_WORK) { irq_work_single(csd); } } else { prev = &csd->node.llist; } } /* * Third; only CSD_TYPE_TTWU is left, issue those. */ if (entry) { csd = llist_entry(entry, typeof(*csd), node.llist); csd_do_func(sched_ttwu_pending, entry, csd); } } /** * flush_smp_call_function_queue - Flush pending smp-call-function callbacks * from task context (idle, migration thread) * * When TIF_POLLING_NRFLAG is supported and a CPU is in idle and has it * set, then remote CPUs can avoid sending IPIs and wake the idle CPU by * setting TIF_NEED_RESCHED. The idle task on the woken up CPU has to * handle queued SMP function calls before scheduling. * * The migration thread has to ensure that an eventually pending wakeup has * been handled before it migrates a task. */ void flush_smp_call_function_queue(void) { unsigned int was_pending; unsigned long flags; if (llist_empty(this_cpu_ptr(&call_single_queue))) return; local_irq_save(flags); /* Get the already pending soft interrupts for RT enabled kernels */ was_pending = local_softirq_pending(); __flush_smp_call_function_queue(true); if (local_softirq_pending()) do_softirq_post_smp_call_flush(was_pending); local_irq_restore(flags); } /* * smp_call_function_single - Run a function on a specific CPU * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed on other CPUs. * * Returns 0 on success, else a negative status code. */ int smp_call_function_single(int cpu, smp_call_func_t func, void *info, int wait) { call_single_data_t *csd; call_single_data_t csd_stack = { .node = { .u_flags = CSD_FLAG_LOCK | CSD_TYPE_SYNC, }, }; int this_cpu; int err; /* * prevent preemption and reschedule on another processor, * as well as CPU removal */ this_cpu = get_cpu(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled() && !oops_in_progress); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); csd = &csd_stack; if (!wait) { csd = this_cpu_ptr(&csd_data); csd_lock(csd); } csd->func = func; csd->info = info; #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG csd->node.src = smp_processor_id(); csd->node.dst = cpu; #endif err = generic_exec_single(cpu, csd); if (wait) csd_lock_wait(csd); put_cpu(); return err; } EXPORT_SYMBOL(smp_call_function_single); /** * smp_call_function_single_async() - Run an asynchronous function on a * specific CPU. * @cpu: The CPU to run on. * @csd: Pre-allocated and setup data structure * * Like smp_call_function_single(), but the call is asynchonous and * can thus be done from contexts with disabled interrupts. * * The caller passes his own pre-allocated data structure * (ie: embedded in an object) and is responsible for synchronizing it * such that the IPIs performed on the @csd are strictly serialized. * * If the function is called with one csd which has not yet been * processed by previous call to smp_call_function_single_async(), the * function will return immediately with -EBUSY showing that the csd * object is still in progress. * * NOTE: Be careful, there is unfortunately no current debugging facility to * validate the correctness of this serialization. * * Return: %0 on success or negative errno value on error */ int smp_call_function_single_async(int cpu, call_single_data_t *csd) { int err = 0; preempt_disable(); if (csd->node.u_flags & CSD_FLAG_LOCK) { err = -EBUSY; goto out; } csd->node.u_flags = CSD_FLAG_LOCK; smp_wmb(); err = generic_exec_single(cpu, csd); out: preempt_enable(); return err; } EXPORT_SYMBOL_GPL(smp_call_function_single_async); /* * smp_call_function_any - Run a function on any of the given cpus * @mask: The mask of cpus it can run on. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed. * * Returns 0 on success, else a negative status code (if no cpus were online). * * Selection preference: * 1) current cpu if in @mask * 2) any cpu of current node if in @mask * 3) any other online cpu in @mask */ int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, void *info, int wait) { unsigned int cpu; const struct cpumask *nodemask; int ret; /* Try for same CPU (cheapest) */ cpu = get_cpu(); if (cpumask_test_cpu(cpu, mask)) goto call; /* Try for same node. */ nodemask = cpumask_of_node(cpu_to_node(cpu)); for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids; cpu = cpumask_next_and(cpu, nodemask, mask)) { if (cpu_online(cpu)) goto call; } /* Any online will do: smp_call_function_single handles nr_cpu_ids. */ cpu = cpumask_any_and(mask, cpu_online_mask); call: ret = smp_call_function_single(cpu, func, info, wait); put_cpu(); return ret; } EXPORT_SYMBOL_GPL(smp_call_function_any); /* * Flags to be used as scf_flags argument of smp_call_function_many_cond(). * * %SCF_WAIT: Wait until function execution is completed * %SCF_RUN_LOCAL: Run also locally if local cpu is set in cpumask */ #define SCF_WAIT (1U << 0) #define SCF_RUN_LOCAL (1U << 1) static void smp_call_function_many_cond(const struct cpumask *mask, smp_call_func_t func, void *info, unsigned int scf_flags, smp_cond_func_t cond_func) { int cpu, last_cpu, this_cpu = smp_processor_id(); struct call_function_data *cfd; bool wait = scf_flags & SCF_WAIT; int nr_cpus = 0; bool run_remote = false; bool run_local = false; lockdep_assert_preemption_disabled(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ if (cpu_online(this_cpu) && !oops_in_progress && !early_boot_irqs_disabled) lockdep_assert_irqs_enabled(); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); /* Check if we need local execution. */ if ((scf_flags & SCF_RUN_LOCAL) && cpumask_test_cpu(this_cpu, mask)) run_local = true; /* Check if we need remote execution, i.e., any CPU excluding this one. */ cpu = cpumask_first_and(mask, cpu_online_mask); if (cpu == this_cpu) cpu = cpumask_next_and(cpu, mask, cpu_online_mask); if (cpu < nr_cpu_ids) run_remote = true; if (run_remote) { cfd = this_cpu_ptr(&cfd_data); cpumask_and(cfd->cpumask, mask, cpu_online_mask); __cpumask_clear_cpu(this_cpu, cfd->cpumask); cpumask_clear(cfd->cpumask_ipi); for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu); if (cond_func && !cond_func(cpu, info)) { __cpumask_clear_cpu(cpu, cfd->cpumask); continue; } csd_lock(csd); if (wait) csd->node.u_flags |= CSD_TYPE_SYNC; csd->func = func; csd->info = info; #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG csd->node.src = smp_processor_id(); csd->node.dst = cpu; #endif trace_csd_queue_cpu(cpu, _RET_IP_, func, csd); if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu))) { __cpumask_set_cpu(cpu, cfd->cpumask_ipi); nr_cpus++; last_cpu = cpu; } } /* * Choose the most efficient way to send an IPI. Note that the * number of CPUs might be zero due to concurrent changes to the * provided mask. */ if (nr_cpus == 1) send_call_function_single_ipi(last_cpu); else if (likely(nr_cpus > 1)) send_call_function_ipi_mask(cfd->cpumask_ipi); } if (run_local && (!cond_func || cond_func(this_cpu, info))) { unsigned long flags; local_irq_save(flags); csd_do_func(func, info, NULL); local_irq_restore(flags); } if (run_remote && wait) { for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd; csd = per_cpu_ptr(cfd->csd, cpu); csd_lock_wait(csd); } } } /** * smp_call_function_many(): Run a function on a set of CPUs. * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: Bitmask that controls the operation. If %SCF_WAIT is set, wait * (atomically) until function has completed on other CPUs. If * %SCF_RUN_LOCAL is set, the function will also be run locally * if the local CPU is set in the @cpumask. * * If @wait is true, then returns once @func has returned. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. Preemption * must be disabled when calling this function. */ void smp_call_function_many(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { smp_call_function_many_cond(mask, func, info, wait * SCF_WAIT, NULL); } EXPORT_SYMBOL(smp_call_function_many); /** * smp_call_function(): Run a function on all other CPUs. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * Returns 0. * * If @wait is true, then returns once @func has returned; otherwise * it returns just before the target cpu calls @func. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. */ void smp_call_function(smp_call_func_t func, void *info, int wait) { preempt_disable(); smp_call_function_many(cpu_online_mask, func, info, wait); preempt_enable(); } EXPORT_SYMBOL(smp_call_function); /* Setup configured maximum number of CPUs to activate */ unsigned int setup_max_cpus = NR_CPUS; EXPORT_SYMBOL(setup_max_cpus); /* * Setup routine for controlling SMP activation * * Command-line option of "nosmp" or "maxcpus=0" will disable SMP * activation entirely (the MPS table probe still happens, though). * * Command-line option of "maxcpus=<NUM>", where <NUM> is an integer * greater than 0, limits the maximum number of CPUs activated in * SMP mode to <NUM>. */ void __weak __init arch_disable_smp_support(void) { } static int __init nosmp(char *str) { setup_max_cpus = 0; arch_disable_smp_support(); return 0; } early_param("nosmp", nosmp); /* this is hard limit */ static int __init nrcpus(char *str) { int nr_cpus; if (get_option(&str, &nr_cpus) && nr_cpus > 0 && nr_cpus < nr_cpu_ids) set_nr_cpu_ids(nr_cpus); return 0; } early_param("nr_cpus", nrcpus); static int __init maxcpus(char *str) { get_option(&str, &setup_max_cpus); if (setup_max_cpus == 0) arch_disable_smp_support(); return 0; } early_param("maxcpus", maxcpus); #if (NR_CPUS > 1) && !defined(CONFIG_FORCE_NR_CPUS) /* Setup number of possible processor ids */ unsigned int nr_cpu_ids __read_mostly = NR_CPUS; EXPORT_SYMBOL(nr_cpu_ids); #endif /* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */ void __init setup_nr_cpu_ids(void) { set_nr_cpu_ids(find_last_bit(cpumask_bits(cpu_possible_mask), NR_CPUS) + 1); } /* Called by boot processor to activate the rest. */ void __init smp_init(void) { int num_nodes, num_cpus; idle_threads_init(); cpuhp_threads_init(); pr_info("Bringing up secondary CPUs ...\n"); bringup_nonboot_cpus(setup_max_cpus); num_nodes = num_online_nodes(); num_cpus = num_online_cpus(); pr_info("Brought up %d node%s, %d CPU%s\n", num_nodes, (num_nodes > 1 ? "s" : ""), num_cpus, (num_cpus > 1 ? "s" : "")); /* Any cleanup work */ smp_cpus_done(setup_max_cpus); } /* * on_each_cpu_cond(): Call a function on each processor for which * the supplied function cond_func returns true, optionally waiting * for all the required CPUs to finish. This may include the local * processor. * @cond_func: A callback function that is passed a cpu id and * the info parameter. The function is called * with preemption disabled. The function should * return a blooean value indicating whether to IPI * the specified CPU. * @func: The function to run on all applicable CPUs. * This must be fast and non-blocking. * @info: An arbitrary pointer to pass to both functions. * @wait: If true, wait (atomically) until function has * completed on other CPUs. * * Preemption is disabled to protect against CPUs going offline but not online. * CPUs going online during the call will not be seen or sent an IPI. * * You must not call this function with disabled interrupts or * from a hardware interrupt handler or from a bottom half handler. */ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait, const struct cpumask *mask) { unsigned int scf_flags = SCF_RUN_LOCAL; if (wait) scf_flags |= SCF_WAIT; preempt_disable(); smp_call_function_many_cond(mask, func, info, scf_flags, cond_func); preempt_enable(); } EXPORT_SYMBOL(on_each_cpu_cond_mask); static void do_nothing(void *unused) { } /** * kick_all_cpus_sync - Force all cpus out of idle * * Used to synchronize the update of pm_idle function pointer. It's * called after the pointer is updated and returns after the dummy * callback function has been executed on all cpus. The execution of * the function can only happen on the remote cpus after they have * left the idle function which had been called via pm_idle function * pointer. So it's guaranteed that nothing uses the previous pointer * anymore. */ void kick_all_cpus_sync(void) { /* Make sure the change is visible before we kick the cpus */ smp_mb(); smp_call_function(do_nothing, NULL, 1); } EXPORT_SYMBOL_GPL(kick_all_cpus_sync); /** * wake_up_all_idle_cpus - break all cpus out of idle * wake_up_all_idle_cpus try to break all cpus which is in idle state even * including idle polling cpus, for non-idle cpus, we will do nothing * for them. */ void wake_up_all_idle_cpus(void) { int cpu; for_each_possible_cpu(cpu) { preempt_disable(); if (cpu != smp_processor_id() && cpu_online(cpu)) wake_up_if_idle(cpu); preempt_enable(); } } EXPORT_SYMBOL_GPL(wake_up_all_idle_cpus); /** * struct smp_call_on_cpu_struct - Call a function on a specific CPU * @work: &work_struct * @done: &completion to signal * @func: function to call * @data: function's data argument * @ret: return value from @func * @cpu: target CPU (%-1 for any CPU) * * Used to call a function on a specific cpu and wait for it to return. * Optionally make sure the call is done on a specified physical cpu via vcpu * pinning in order to support virtualized environments. */ struct smp_call_on_cpu_struct { struct work_struct work; struct completion done; int (*func)(void *); void *data; int ret; int cpu; }; static void smp_call_on_cpu_callback(struct work_struct *work) { struct smp_call_on_cpu_struct *sscs; sscs = container_of(work, struct smp_call_on_cpu_struct, work); if (sscs->cpu >= 0) hypervisor_pin_vcpu(sscs->cpu); sscs->ret = sscs->func(sscs->data); if (sscs->cpu >= 0) hypervisor_pin_vcpu(-1); complete(&sscs->done); } int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys) { struct smp_call_on_cpu_struct sscs = { .done = COMPLETION_INITIALIZER_ONSTACK(sscs.done), .func = func, .data = par, .cpu = phys ? cpu : -1, }; INIT_WORK_ONSTACK(&sscs.work, smp_call_on_cpu_callback); if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; queue_work_on(cpu, system_wq, &sscs.work); wait_for_completion(&sscs.done); return sscs.ret; } EXPORT_SYMBOL_GPL(smp_call_on_cpu); |
| 14 8 17 17 14 12 13 5 2 2 6 11 11 11 11 11 2 11 11 11 7 11 11 11 11 4 7 11 10 9 10 11 5 5 5 1 5 11 11 11 5 6 5 1 11 8 8 8 8 7 5 7 8 8 3 1 1 1 1 15 4 15 2 1 2 1 4 1 1 1 1 1 1 1 1 1 1 1 1 21 7 6 2 2 1 1 2 5 1 5 1 1 21 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * * Modified by Fred N. van Kempen, 01/29/93, to add line disciplines * which can be dynamically activated and de-activated by the line * discipline handling modules (like SLIP). */ #include <linux/bits.h> #include <linux/types.h> #include <linux/termios.h> #include <linux/errno.h> #include <linux/sched/signal.h> #include <linux/kernel.h> #include <linux/major.h> #include <linux/tty.h> #include <linux/fcntl.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/bitops.h> #include <linux/mutex.h> #include <linux/compat.h> #include <linux/termios_internal.h> #include "tty.h" #include <asm/io.h> #include <linux/uaccess.h> #undef DEBUG /* * Internal flag options for termios setting behavior */ #define TERMIOS_FLUSH BIT(0) #define TERMIOS_WAIT BIT(1) #define TERMIOS_TERMIO BIT(2) #define TERMIOS_OLD BIT(3) /** * tty_chars_in_buffer - characters pending * @tty: terminal * * Returns: the number of bytes of data in the device private output queue. If * no private method is supplied there is assumed to be no queue on the device. */ unsigned int tty_chars_in_buffer(struct tty_struct *tty) { if (tty->ops->chars_in_buffer) return tty->ops->chars_in_buffer(tty); return 0; } EXPORT_SYMBOL(tty_chars_in_buffer); /** * tty_write_room - write queue space * @tty: terminal * * Returns: the number of bytes that can be queued to this device at the present * time. The result should be treated as a guarantee and the driver cannot * offer a value it later shrinks by more than the number of bytes written. If * no method is provided, 2K is always returned and data may be lost as there * will be no flow control. */ unsigned int tty_write_room(struct tty_struct *tty) { if (tty->ops->write_room) return tty->ops->write_room(tty); return 2048; } EXPORT_SYMBOL(tty_write_room); /** * tty_driver_flush_buffer - discard internal buffer * @tty: terminal * * Discard the internal output buffer for this device. If no method is provided, * then either the buffer cannot be hardware flushed or there is no buffer * driver side. */ void tty_driver_flush_buffer(struct tty_struct *tty) { if (tty->ops->flush_buffer) tty->ops->flush_buffer(tty); } EXPORT_SYMBOL(tty_driver_flush_buffer); /** * tty_unthrottle - flow control * @tty: terminal * * Indicate that a @tty may continue transmitting data down the stack. Takes * the &tty_struct->termios_rwsem to protect against parallel * throttle/unthrottle and also to ensure the driver can consistently reference * its own termios data at this point when implementing software flow control. * * Drivers should however remember that the stack can issue a throttle, then * change flow control method, then unthrottle. */ void tty_unthrottle(struct tty_struct *tty) { down_write(&tty->termios_rwsem); if (test_and_clear_bit(TTY_THROTTLED, &tty->flags) && tty->ops->unthrottle) tty->ops->unthrottle(tty); tty->flow_change = TTY_FLOW_NO_CHANGE; up_write(&tty->termios_rwsem); } EXPORT_SYMBOL(tty_unthrottle); /** * tty_throttle_safe - flow control * @tty: terminal * * Indicate that a @tty should stop transmitting data down the stack. * tty_throttle_safe() will only attempt throttle if @tty->flow_change is * %TTY_THROTTLE_SAFE. Prevents an accidental throttle due to race conditions * when throttling is conditional on factors evaluated prior to throttling. * * Returns: %true if @tty is throttled (or was already throttled) */ bool tty_throttle_safe(struct tty_struct *tty) { bool ret = true; mutex_lock(&tty->throttle_mutex); if (!tty_throttled(tty)) { if (tty->flow_change != TTY_THROTTLE_SAFE) ret = false; else { set_bit(TTY_THROTTLED, &tty->flags); if (tty->ops->throttle) tty->ops->throttle(tty); } } mutex_unlock(&tty->throttle_mutex); return ret; } /** * tty_unthrottle_safe - flow control * @tty: terminal * * Similar to tty_unthrottle() but will only attempt unthrottle if * @tty->flow_change is %TTY_UNTHROTTLE_SAFE. Prevents an accidental unthrottle * due to race conditions when unthrottling is conditional on factors evaluated * prior to unthrottling. * * Returns: %true if @tty is unthrottled (or was already unthrottled) */ bool tty_unthrottle_safe(struct tty_struct *tty) { bool ret = true; mutex_lock(&tty->throttle_mutex); if (tty_throttled(tty)) { if (tty->flow_change != TTY_UNTHROTTLE_SAFE) ret = false; else { clear_bit(TTY_THROTTLED, &tty->flags); if (tty->ops->unthrottle) tty->ops->unthrottle(tty); } } mutex_unlock(&tty->throttle_mutex); return ret; } /** * tty_wait_until_sent - wait for I/O to finish * @tty: tty we are waiting for * @timeout: how long we will wait * * Wait for characters pending in a tty driver to hit the wire, or for a * timeout to occur (eg due to flow control). * * Locking: none */ void tty_wait_until_sent(struct tty_struct *tty, long timeout) { if (!timeout) timeout = MAX_SCHEDULE_TIMEOUT; timeout = wait_event_interruptible_timeout(tty->write_wait, !tty_chars_in_buffer(tty), timeout); if (timeout <= 0) return; if (timeout == MAX_SCHEDULE_TIMEOUT) timeout = 0; if (tty->ops->wait_until_sent) tty->ops->wait_until_sent(tty, timeout); } EXPORT_SYMBOL(tty_wait_until_sent); /* * Termios Helper Methods */ static void unset_locked_termios(struct tty_struct *tty, const struct ktermios *old) { struct ktermios *termios = &tty->termios; struct ktermios *locked = &tty->termios_locked; int i; #define NOSET_MASK(x, y, z) (x = ((x) & ~(z)) | ((y) & (z))) NOSET_MASK(termios->c_iflag, old->c_iflag, locked->c_iflag); NOSET_MASK(termios->c_oflag, old->c_oflag, locked->c_oflag); NOSET_MASK(termios->c_cflag, old->c_cflag, locked->c_cflag); NOSET_MASK(termios->c_lflag, old->c_lflag, locked->c_lflag); termios->c_line = locked->c_line ? old->c_line : termios->c_line; for (i = 0; i < NCCS; i++) termios->c_cc[i] = locked->c_cc[i] ? old->c_cc[i] : termios->c_cc[i]; /* FIXME: What should we do for i/ospeed */ } /** * tty_termios_copy_hw - copy hardware settings * @new: new termios * @old: old termios * * Propagate the hardware specific terminal setting bits from the @old termios * structure to the @new one. This is used in cases where the hardware does not * support reconfiguration or as a helper in some cases where only minimal * reconfiguration is supported. */ void tty_termios_copy_hw(struct ktermios *new, const struct ktermios *old) { /* The bits a dumb device handles in software. Smart devices need to always provide a set_termios method */ new->c_cflag &= HUPCL | CREAD | CLOCAL; new->c_cflag |= old->c_cflag & ~(HUPCL | CREAD | CLOCAL); new->c_ispeed = old->c_ispeed; new->c_ospeed = old->c_ospeed; } EXPORT_SYMBOL(tty_termios_copy_hw); /** * tty_termios_hw_change - check for setting change * @a: termios * @b: termios to compare * * Check if any of the bits that affect a dumb device have changed between the * two termios structures, or a speed change is needed. * * Returns: %true if change is needed */ bool tty_termios_hw_change(const struct ktermios *a, const struct ktermios *b) { if (a->c_ispeed != b->c_ispeed || a->c_ospeed != b->c_ospeed) return true; if ((a->c_cflag ^ b->c_cflag) & ~(HUPCL | CREAD | CLOCAL)) return true; return false; } EXPORT_SYMBOL(tty_termios_hw_change); /** * tty_get_char_size - get size of a character * @cflag: termios cflag value * * Returns: size (in bits) of a character depending on @cflag's %CSIZE setting */ unsigned char tty_get_char_size(unsigned int cflag) { switch (cflag & CSIZE) { case CS5: return 5; case CS6: return 6; case CS7: return 7; case CS8: default: return 8; } } EXPORT_SYMBOL_GPL(tty_get_char_size); /** * tty_get_frame_size - get size of a frame * @cflag: termios cflag value * * Get the size (in bits) of a frame depending on @cflag's %CSIZE, %CSTOPB, and * %PARENB setting. The result is a sum of character size, start and stop bits * -- one bit each -- second stop bit (if set), and parity bit (if set). * * Returns: size (in bits) of a frame depending on @cflag's setting. */ unsigned char tty_get_frame_size(unsigned int cflag) { unsigned char bits = 2 + tty_get_char_size(cflag); if (cflag & CSTOPB) bits++; if (cflag & PARENB) bits++; if (cflag & ADDRB) bits++; return bits; } EXPORT_SYMBOL_GPL(tty_get_frame_size); /** * tty_set_termios - update termios values * @tty: tty to update * @new_termios: desired new value * * Perform updates to the termios values set on this @tty. A master pty's * termios should never be set. * * Locking: &tty_struct->termios_rwsem */ int tty_set_termios(struct tty_struct *tty, struct ktermios *new_termios) { struct ktermios old_termios; struct tty_ldisc *ld; WARN_ON(tty->driver->type == TTY_DRIVER_TYPE_PTY && tty->driver->subtype == PTY_TYPE_MASTER); /* * Perform the actual termios internal changes under lock. */ /* FIXME: we need to decide on some locking/ordering semantics for the set_termios notification eventually */ down_write(&tty->termios_rwsem); old_termios = tty->termios; tty->termios = *new_termios; unset_locked_termios(tty, &old_termios); /* Reset any ADDRB changes, ADDRB is changed through ->rs485_config() */ tty->termios.c_cflag ^= (tty->termios.c_cflag ^ old_termios.c_cflag) & ADDRB; if (tty->ops->set_termios) tty->ops->set_termios(tty, &old_termios); else tty_termios_copy_hw(&tty->termios, &old_termios); ld = tty_ldisc_ref(tty); if (ld != NULL) { if (ld->ops->set_termios) ld->ops->set_termios(tty, &old_termios); tty_ldisc_deref(ld); } up_write(&tty->termios_rwsem); return 0; } EXPORT_SYMBOL_GPL(tty_set_termios); /* * Translate a "termio" structure into a "termios". Ugh. */ __weak int user_termio_to_kernel_termios(struct ktermios *termios, struct termio __user *termio) { struct termio v; if (copy_from_user(&v, termio, sizeof(struct termio))) return -EFAULT; termios->c_iflag = (0xffff0000 & termios->c_iflag) | v.c_iflag; termios->c_oflag = (0xffff0000 & termios->c_oflag) | v.c_oflag; termios->c_cflag = (0xffff0000 & termios->c_cflag) | v.c_cflag; termios->c_lflag = (0xffff0000 & termios->c_lflag) | v.c_lflag; termios->c_line = (0xffff0000 & termios->c_lflag) | v.c_line; memcpy(termios->c_cc, v.c_cc, NCC); return 0; } /* * Translate a "termios" structure into a "termio". Ugh. */ __weak int kernel_termios_to_user_termio(struct termio __user *termio, struct ktermios *termios) { struct termio v; memset(&v, 0, sizeof(struct termio)); v.c_iflag = termios->c_iflag; v.c_oflag = termios->c_oflag; v.c_cflag = termios->c_cflag; v.c_lflag = termios->c_lflag; v.c_line = termios->c_line; memcpy(v.c_cc, termios->c_cc, NCC); return copy_to_user(termio, &v, sizeof(struct termio)); } #ifdef TCGETS2 __weak int user_termios_to_kernel_termios(struct ktermios *k, struct termios2 __user *u) { return copy_from_user(k, u, sizeof(struct termios2)); } __weak int kernel_termios_to_user_termios(struct termios2 __user *u, struct ktermios *k) { return copy_to_user(u, k, sizeof(struct termios2)); } __weak int user_termios_to_kernel_termios_1(struct ktermios *k, struct termios __user *u) { return copy_from_user(k, u, sizeof(struct termios)); } __weak int kernel_termios_to_user_termios_1(struct termios __user *u, struct ktermios *k) { return copy_to_user(u, k, sizeof(struct termios)); } #else __weak int user_termios_to_kernel_termios(struct ktermios *k, struct termios __user *u) { return copy_from_user(k, u, sizeof(struct termios)); } __weak int kernel_termios_to_user_termios(struct termios __user *u, struct ktermios *k) { return copy_to_user(u, k, sizeof(struct termios)); } #endif /* TCGETS2 */ /** * set_termios - set termios values for a tty * @tty: terminal device * @arg: user data * @opt: option information * * Helper function to prepare termios data and run necessary other functions * before using tty_set_termios() to do the actual changes. * * Locking: called functions take &tty_struct->ldisc_sem and * &tty_struct->termios_rwsem locks * * Returns: 0 on success, an error otherwise */ static int set_termios(struct tty_struct *tty, void __user *arg, int opt) { struct ktermios tmp_termios; struct tty_ldisc *ld; int retval = tty_check_change(tty); if (retval) return retval; down_read(&tty->termios_rwsem); tmp_termios = tty->termios; up_read(&tty->termios_rwsem); if (opt & TERMIOS_TERMIO) { if (user_termio_to_kernel_termios(&tmp_termios, (struct termio __user *)arg)) return -EFAULT; #ifdef TCGETS2 } else if (opt & TERMIOS_OLD) { if (user_termios_to_kernel_termios_1(&tmp_termios, (struct termios __user *)arg)) return -EFAULT; } else { if (user_termios_to_kernel_termios(&tmp_termios, (struct termios2 __user *)arg)) return -EFAULT; } #else } else if (user_termios_to_kernel_termios(&tmp_termios, (struct termios __user *)arg)) return -EFAULT; #endif /* If old style Bfoo values are used then load c_ispeed/c_ospeed * with the real speed so its unconditionally usable */ tmp_termios.c_ispeed = tty_termios_input_baud_rate(&tmp_termios); tmp_termios.c_ospeed = tty_termios_baud_rate(&tmp_termios); if (opt & (TERMIOS_FLUSH|TERMIOS_WAIT)) { retry_write_wait: retval = wait_event_interruptible(tty->write_wait, !tty_chars_in_buffer(tty)); if (retval < 0) return retval; if (tty_write_lock(tty, false) < 0) goto retry_write_wait; /* Racing writer? */ if (tty_chars_in_buffer(tty)) { tty_write_unlock(tty); goto retry_write_wait; } ld = tty_ldisc_ref(tty); if (ld != NULL) { if ((opt & TERMIOS_FLUSH) && ld->ops->flush_buffer) ld->ops->flush_buffer(tty); tty_ldisc_deref(ld); } if ((opt & TERMIOS_WAIT) && tty->ops->wait_until_sent) { tty->ops->wait_until_sent(tty, 0); if (signal_pending(current)) { tty_write_unlock(tty); return -ERESTARTSYS; } } tty_set_termios(tty, &tmp_termios); tty_write_unlock(tty); } else { tty_set_termios(tty, &tmp_termios); } /* FIXME: Arguably if tmp_termios == tty->termios AND the actual requested termios was not tmp_termios then we may want to return an error as no user requested change has succeeded */ return 0; } static void copy_termios(struct tty_struct *tty, struct ktermios *kterm) { down_read(&tty->termios_rwsem); *kterm = tty->termios; up_read(&tty->termios_rwsem); } static void copy_termios_locked(struct tty_struct *tty, struct ktermios *kterm) { down_read(&tty->termios_rwsem); *kterm = tty->termios_locked; up_read(&tty->termios_rwsem); } static int get_termio(struct tty_struct *tty, struct termio __user *termio) { struct ktermios kterm; copy_termios(tty, &kterm); if (kernel_termios_to_user_termio(termio, &kterm)) return -EFAULT; return 0; } #ifdef TIOCGETP /* * These are deprecated, but there is limited support.. * * The "sg_flags" translation is a joke.. */ static int get_sgflags(struct tty_struct *tty) { int flags = 0; if (!L_ICANON(tty)) { if (L_ISIG(tty)) flags |= 0x02; /* cbreak */ else flags |= 0x20; /* raw */ } if (L_ECHO(tty)) flags |= 0x08; /* echo */ if (O_OPOST(tty)) if (O_ONLCR(tty)) flags |= 0x10; /* crmod */ return flags; } static int get_sgttyb(struct tty_struct *tty, struct sgttyb __user *sgttyb) { struct sgttyb tmp; down_read(&tty->termios_rwsem); tmp.sg_ispeed = tty->termios.c_ispeed; tmp.sg_ospeed = tty->termios.c_ospeed; tmp.sg_erase = tty->termios.c_cc[VERASE]; tmp.sg_kill = tty->termios.c_cc[VKILL]; tmp.sg_flags = get_sgflags(tty); up_read(&tty->termios_rwsem); return copy_to_user(sgttyb, &tmp, sizeof(tmp)) ? -EFAULT : 0; } static void set_sgflags(struct ktermios *termios, int flags) { termios->c_iflag = ICRNL | IXON; termios->c_oflag = 0; termios->c_lflag = ISIG | ICANON; if (flags & 0x02) { /* cbreak */ termios->c_iflag = 0; termios->c_lflag &= ~ICANON; } if (flags & 0x08) { /* echo */ termios->c_lflag |= ECHO | ECHOE | ECHOK | ECHOCTL | ECHOKE | IEXTEN; } if (flags & 0x10) { /* crmod */ termios->c_oflag |= OPOST | ONLCR; } if (flags & 0x20) { /* raw */ termios->c_iflag = 0; termios->c_lflag &= ~(ISIG | ICANON); } if (!(termios->c_lflag & ICANON)) { termios->c_cc[VMIN] = 1; termios->c_cc[VTIME] = 0; } } /** * set_sgttyb - set legacy terminal values * @tty: tty structure * @sgttyb: pointer to old style terminal structure * * Updates a terminal from the legacy BSD style terminal information structure. * * Locking: &tty_struct->termios_rwsem * * Returns: 0 on success, an error otherwise */ static int set_sgttyb(struct tty_struct *tty, struct sgttyb __user *sgttyb) { int retval; struct sgttyb tmp; struct ktermios termios; retval = tty_check_change(tty); if (retval) return retval; if (copy_from_user(&tmp, sgttyb, sizeof(tmp))) return -EFAULT; down_write(&tty->termios_rwsem); termios = tty->termios; termios.c_cc[VERASE] = tmp.sg_erase; termios.c_cc[VKILL] = tmp.sg_kill; set_sgflags(&termios, tmp.sg_flags); /* Try and encode into Bfoo format */ tty_termios_encode_baud_rate(&termios, termios.c_ispeed, termios.c_ospeed); up_write(&tty->termios_rwsem); tty_set_termios(tty, &termios); return 0; } #endif #ifdef TIOCGETC static int get_tchars(struct tty_struct *tty, struct tchars __user *tchars) { struct tchars tmp; down_read(&tty->termios_rwsem); tmp.t_intrc = tty->termios.c_cc[VINTR]; tmp.t_quitc = tty->termios.c_cc[VQUIT]; tmp.t_startc = tty->termios.c_cc[VSTART]; tmp.t_stopc = tty->termios.c_cc[VSTOP]; tmp.t_eofc = tty->termios.c_cc[VEOF]; tmp.t_brkc = tty->termios.c_cc[VEOL2]; /* what is brkc anyway? */ up_read(&tty->termios_rwsem); return copy_to_user(tchars, &tmp, sizeof(tmp)) ? -EFAULT : 0; } static int set_tchars(struct tty_struct *tty, struct tchars __user *tchars) { struct tchars tmp; if (copy_from_user(&tmp, tchars, sizeof(tmp))) return -EFAULT; down_write(&tty->termios_rwsem); tty->termios.c_cc[VINTR] = tmp.t_intrc; tty->termios.c_cc[VQUIT] = tmp.t_quitc; tty->termios.c_cc[VSTART] = tmp.t_startc; tty->termios.c_cc[VSTOP] = tmp.t_stopc; tty->termios.c_cc[VEOF] = tmp.t_eofc; tty->termios.c_cc[VEOL2] = tmp.t_brkc; /* what is brkc anyway? */ up_write(&tty->termios_rwsem); return 0; } #endif #ifdef TIOCGLTC static int get_ltchars(struct tty_struct *tty, struct ltchars __user *ltchars) { struct ltchars tmp; down_read(&tty->termios_rwsem); tmp.t_suspc = tty->termios.c_cc[VSUSP]; /* what is dsuspc anyway? */ tmp.t_dsuspc = tty->termios.c_cc[VSUSP]; tmp.t_rprntc = tty->termios.c_cc[VREPRINT]; /* what is flushc anyway? */ tmp.t_flushc = tty->termios.c_cc[VEOL2]; tmp.t_werasc = tty->termios.c_cc[VWERASE]; tmp.t_lnextc = tty->termios.c_cc[VLNEXT]; up_read(&tty->termios_rwsem); return copy_to_user(ltchars, &tmp, sizeof(tmp)) ? -EFAULT : 0; } static int set_ltchars(struct tty_struct *tty, struct ltchars __user *ltchars) { struct ltchars tmp; if (copy_from_user(&tmp, ltchars, sizeof(tmp))) return -EFAULT; down_write(&tty->termios_rwsem); tty->termios.c_cc[VSUSP] = tmp.t_suspc; /* what is dsuspc anyway? */ tty->termios.c_cc[VEOL2] = tmp.t_dsuspc; tty->termios.c_cc[VREPRINT] = tmp.t_rprntc; /* what is flushc anyway? */ tty->termios.c_cc[VEOL2] = tmp.t_flushc; tty->termios.c_cc[VWERASE] = tmp.t_werasc; tty->termios.c_cc[VLNEXT] = tmp.t_lnextc; up_write(&tty->termios_rwsem); return 0; } #endif /** * tty_change_softcar - carrier change ioctl helper * @tty: tty to update * @enable: enable/disable %CLOCAL * * Perform a change to the %CLOCAL state and call into the driver layer to make * it visible. * * Locking: &tty_struct->termios_rwsem. * * Returns: 0 on success, an error otherwise */ static int tty_change_softcar(struct tty_struct *tty, bool enable) { int ret = 0; struct ktermios old; tcflag_t bit = enable ? CLOCAL : 0; down_write(&tty->termios_rwsem); old = tty->termios; tty->termios.c_cflag &= ~CLOCAL; tty->termios.c_cflag |= bit; if (tty->ops->set_termios) tty->ops->set_termios(tty, &old); if (C_CLOCAL(tty) != bit) ret = -EINVAL; up_write(&tty->termios_rwsem); return ret; } /** * tty_mode_ioctl - mode related ioctls * @tty: tty for the ioctl * @cmd: command * @arg: ioctl argument * * Perform non-line discipline specific mode control ioctls. This is designed * to be called by line disciplines to ensure they provide consistent mode * setting. */ int tty_mode_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct tty_struct *real_tty; void __user *p = (void __user *)arg; int ret = 0; struct ktermios kterm; if (tty->driver->type == TTY_DRIVER_TYPE_PTY && tty->driver->subtype == PTY_TYPE_MASTER) real_tty = tty->link; else real_tty = tty; switch (cmd) { #ifdef TIOCGETP case TIOCGETP: return get_sgttyb(real_tty, (struct sgttyb __user *) arg); case TIOCSETP: case TIOCSETN: return set_sgttyb(real_tty, (struct sgttyb __user *) arg); #endif #ifdef TIOCGETC case TIOCGETC: return get_tchars(real_tty, p); case TIOCSETC: return set_tchars(real_tty, p); #endif #ifdef TIOCGLTC case TIOCGLTC: return get_ltchars(real_tty, p); case TIOCSLTC: return set_ltchars(real_tty, p); #endif case TCSETSF: return set_termios(real_tty, p, TERMIOS_FLUSH | TERMIOS_WAIT | TERMIOS_OLD); case TCSETSW: return set_termios(real_tty, p, TERMIOS_WAIT | TERMIOS_OLD); case TCSETS: return set_termios(real_tty, p, TERMIOS_OLD); #ifndef TCGETS2 case TCGETS: copy_termios(real_tty, &kterm); if (kernel_termios_to_user_termios((struct termios __user *)arg, &kterm)) ret = -EFAULT; return ret; #else case TCGETS: copy_termios(real_tty, &kterm); if (kernel_termios_to_user_termios_1((struct termios __user *)arg, &kterm)) ret = -EFAULT; return ret; case TCGETS2: copy_termios(real_tty, &kterm); if (kernel_termios_to_user_termios((struct termios2 __user *)arg, &kterm)) ret = -EFAULT; return ret; case TCSETSF2: return set_termios(real_tty, p, TERMIOS_FLUSH | TERMIOS_WAIT); case TCSETSW2: return set_termios(real_tty, p, TERMIOS_WAIT); case TCSETS2: return set_termios(real_tty, p, 0); #endif case TCGETA: return get_termio(real_tty, p); case TCSETAF: return set_termios(real_tty, p, TERMIOS_FLUSH | TERMIOS_WAIT | TERMIOS_TERMIO); case TCSETAW: return set_termios(real_tty, p, TERMIOS_WAIT | TERMIOS_TERMIO); case TCSETA: return set_termios(real_tty, p, TERMIOS_TERMIO); #ifndef TCGETS2 case TIOCGLCKTRMIOS: copy_termios_locked(real_tty, &kterm); if (kernel_termios_to_user_termios((struct termios __user *)arg, &kterm)) ret = -EFAULT; return ret; case TIOCSLCKTRMIOS: if (!checkpoint_restore_ns_capable(&init_user_ns)) return -EPERM; copy_termios_locked(real_tty, &kterm); if (user_termios_to_kernel_termios(&kterm, (struct termios __user *) arg)) return -EFAULT; down_write(&real_tty->termios_rwsem); real_tty->termios_locked = kterm; up_write(&real_tty->termios_rwsem); return 0; #else case TIOCGLCKTRMIOS: copy_termios_locked(real_tty, &kterm); if (kernel_termios_to_user_termios_1((struct termios __user *)arg, &kterm)) ret = -EFAULT; return ret; case TIOCSLCKTRMIOS: if (!checkpoint_restore_ns_capable(&init_user_ns)) return -EPERM; copy_termios_locked(real_tty, &kterm); if (user_termios_to_kernel_termios_1(&kterm, (struct termios __user *) arg)) return -EFAULT; down_write(&real_tty->termios_rwsem); real_tty->termios_locked = kterm; up_write(&real_tty->termios_rwsem); return ret; #endif #ifdef TCGETX case TCGETX: case TCSETX: case TCSETXW: case TCSETXF: return -ENOTTY; #endif case TIOCGSOFTCAR: copy_termios(real_tty, &kterm); ret = put_user((kterm.c_cflag & CLOCAL) ? 1 : 0, (int __user *)arg); return ret; case TIOCSSOFTCAR: if (get_user(arg, (unsigned int __user *) arg)) return -EFAULT; return tty_change_softcar(real_tty, arg); default: return -ENOIOCTLCMD; } } EXPORT_SYMBOL_GPL(tty_mode_ioctl); /* Caller guarantees ldisc reference is held */ static int __tty_perform_flush(struct tty_struct *tty, unsigned long arg) { struct tty_ldisc *ld = tty->ldisc; switch (arg) { case TCIFLUSH: if (ld && ld->ops->flush_buffer) { ld->ops->flush_buffer(tty); tty_unthrottle(tty); } break; case TCIOFLUSH: if (ld && ld->ops->flush_buffer) { ld->ops->flush_buffer(tty); tty_unthrottle(tty); } fallthrough; case TCOFLUSH: tty_driver_flush_buffer(tty); break; default: return -EINVAL; } return 0; } int tty_perform_flush(struct tty_struct *tty, unsigned long arg) { struct tty_ldisc *ld; int retval = tty_check_change(tty); if (retval) return retval; ld = tty_ldisc_ref_wait(tty); retval = __tty_perform_flush(tty, arg); if (ld) tty_ldisc_deref(ld); return retval; } EXPORT_SYMBOL_GPL(tty_perform_flush); int n_tty_ioctl_helper(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { int retval; switch (cmd) { case TCXONC: retval = tty_check_change(tty); if (retval) return retval; switch (arg) { case TCOOFF: spin_lock_irq(&tty->flow.lock); if (!tty->flow.tco_stopped) { tty->flow.tco_stopped = true; __stop_tty(tty); } spin_unlock_irq(&tty->flow.lock); break; case TCOON: spin_lock_irq(&tty->flow.lock); if (tty->flow.tco_stopped) { tty->flow.tco_stopped = false; __start_tty(tty); } spin_unlock_irq(&tty->flow.lock); break; case TCIOFF: if (STOP_CHAR(tty) != __DISABLED_CHAR) retval = tty_send_xchar(tty, STOP_CHAR(tty)); break; case TCION: if (START_CHAR(tty) != __DISABLED_CHAR) retval = tty_send_xchar(tty, START_CHAR(tty)); break; default: return -EINVAL; } return retval; case TCFLSH: retval = tty_check_change(tty); if (retval) return retval; return __tty_perform_flush(tty, arg); default: /* Try the mode commands */ return tty_mode_ioctl(tty, cmd, arg); } } EXPORT_SYMBOL(n_tty_ioctl_helper); |
| 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * mount.c - operations for initializing and mounting configfs. * * Based on sysfs: * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel * * configfs Copyright (C) 2005 Oracle. All rights reserved. */ #include <linux/fs.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/configfs.h> #include "configfs_internal.h" /* Random magic number */ #define CONFIGFS_MAGIC 0x62656570 static struct vfsmount *configfs_mount = NULL; struct kmem_cache *configfs_dir_cachep; static int configfs_mnt_count = 0; static void configfs_free_inode(struct inode *inode) { if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); free_inode_nonrcu(inode); } static const struct super_operations configfs_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .free_inode = configfs_free_inode, }; static struct config_group configfs_root_group = { .cg_item = { .ci_namebuf = "root", .ci_name = configfs_root_group.cg_item.ci_namebuf, }, }; int configfs_is_root(struct config_item *item) { return item == &configfs_root_group.cg_item; } static struct configfs_dirent configfs_root = { .s_sibling = LIST_HEAD_INIT(configfs_root.s_sibling), .s_children = LIST_HEAD_INIT(configfs_root.s_children), .s_element = &configfs_root_group.cg_item, .s_type = CONFIGFS_ROOT, .s_iattr = NULL, }; static int configfs_fill_super(struct super_block *sb, struct fs_context *fc) { struct inode *inode; struct dentry *root; sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = CONFIGFS_MAGIC; sb->s_op = &configfs_ops; sb->s_time_gran = 1; inode = configfs_new_inode(S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO, &configfs_root, sb); if (inode) { inode->i_op = &configfs_root_inode_operations; inode->i_fop = &configfs_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); } else { pr_debug("could not get root inode\n"); return -ENOMEM; } root = d_make_root(inode); if (!root) { pr_debug("%s: could not get root dentry!\n",__func__); return -ENOMEM; } config_group_init(&configfs_root_group); configfs_root_group.cg_item.ci_dentry = root; root->d_fsdata = &configfs_root; sb->s_root = root; sb->s_d_op = &configfs_dentry_ops; /* the rest get that */ return 0; } static int configfs_get_tree(struct fs_context *fc) { return get_tree_single(fc, configfs_fill_super); } static const struct fs_context_operations configfs_context_ops = { .get_tree = configfs_get_tree, }; static int configfs_init_fs_context(struct fs_context *fc) { fc->ops = &configfs_context_ops; return 0; } static struct file_system_type configfs_fs_type = { .owner = THIS_MODULE, .name = "configfs", .init_fs_context = configfs_init_fs_context, .kill_sb = kill_litter_super, }; MODULE_ALIAS_FS("configfs"); struct dentry *configfs_pin_fs(void) { int err = simple_pin_fs(&configfs_fs_type, &configfs_mount, &configfs_mnt_count); return err ? ERR_PTR(err) : configfs_mount->mnt_root; } void configfs_release_fs(void) { simple_release_fs(&configfs_mount, &configfs_mnt_count); } static int __init configfs_init(void) { int err = -ENOMEM; configfs_dir_cachep = kmem_cache_create("configfs_dir_cache", sizeof(struct configfs_dirent), 0, 0, NULL); if (!configfs_dir_cachep) goto out; err = sysfs_create_mount_point(kernel_kobj, "config"); if (err) goto out2; err = register_filesystem(&configfs_fs_type); if (err) goto out3; return 0; out3: pr_err("Unable to register filesystem!\n"); sysfs_remove_mount_point(kernel_kobj, "config"); out2: kmem_cache_destroy(configfs_dir_cachep); configfs_dir_cachep = NULL; out: return err; } static void __exit configfs_exit(void) { unregister_filesystem(&configfs_fs_type); sysfs_remove_mount_point(kernel_kobj, "config"); kmem_cache_destroy(configfs_dir_cachep); configfs_dir_cachep = NULL; } MODULE_AUTHOR("Oracle"); MODULE_LICENSE("GPL"); MODULE_VERSION("0.0.2"); MODULE_DESCRIPTION("Simple RAM filesystem for user driven kernel subsystem configuration."); core_initcall(configfs_init); module_exit(configfs_exit); |
| 5 5 3 5 5 5 3 3 3 3 3 3 1 3 3 3 2 2 218 215 5 2 2 2 2 1 2 1 2 1 2 3 3 2 3 1 3 3 3 2 3 2 3 1 2 2 3 3 4 1 3 3 3 3 3 3 3 2 2 1 1 3 3 3 3 3 3 3 3 2 3 3 3 4 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Directory notifications for Linux. * * Copyright (C) 2000,2001,2002 Stephen Rothwell * * Copyright (C) 2009 Eric Paris <Red Hat Inc> * dnotify was largly rewritten to use the new fsnotify infrastructure */ #include <linux/fs.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/sched/signal.h> #include <linux/dnotify.h> #include <linux/init.h> #include <linux/security.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/fdtable.h> #include <linux/fsnotify_backend.h> static int dir_notify_enable __read_mostly = 1; #ifdef CONFIG_SYSCTL static struct ctl_table dnotify_sysctls[] = { { .procname = "dir-notify-enable", .data = &dir_notify_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static void __init dnotify_sysctl_init(void) { register_sysctl_init("fs", dnotify_sysctls); } #else #define dnotify_sysctl_init() do { } while (0) #endif static struct kmem_cache *dnotify_struct_cache __ro_after_init; static struct kmem_cache *dnotify_mark_cache __ro_after_init; static struct fsnotify_group *dnotify_group __ro_after_init; /* * dnotify will attach one of these to each inode (i_fsnotify_marks) which * is being watched by dnotify. If multiple userspace applications are watching * the same directory with dnotify their information is chained in dn */ struct dnotify_mark { struct fsnotify_mark fsn_mark; struct dnotify_struct *dn; }; /* * When a process starts or stops watching an inode the set of events which * dnotify cares about for that inode may change. This function runs the * list of everything receiving dnotify events about this directory and calculates * the set of all those events. After it updates what dnotify is interested in * it calls the fsnotify function so it can update the set of all events relevant * to this inode. */ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark) { __u32 new_mask = 0; struct dnotify_struct *dn; struct dnotify_mark *dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); assert_spin_locked(&fsn_mark->lock); for (dn = dn_mark->dn; dn != NULL; dn = dn->dn_next) new_mask |= (dn->dn_mask & ~FS_DN_MULTISHOT); if (fsn_mark->mask == new_mask) return; fsn_mark->mask = new_mask; fsnotify_recalc_mask(fsn_mark->connector); } /* * Mains fsnotify call where events are delivered to dnotify. * Find the dnotify mark on the relevant inode, run the list of dnotify structs * on that mark and determine which of them has expressed interest in receiving * events of this type. When found send the correct process and signal and * destroy the dnotify struct if it was not registered to receive multiple * events. */ static int dnotify_handle_event(struct fsnotify_mark *inode_mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *name, u32 cookie) { struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct fown_struct *fown; __u32 test_mask = mask & ~FS_EVENT_ON_CHILD; /* not a dir, dnotify doesn't care */ if (!dir && !(mask & FS_ISDIR)) return 0; dn_mark = container_of(inode_mark, struct dnotify_mark, fsn_mark); spin_lock(&inode_mark->lock); prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_mask & test_mask) == 0) { prev = &dn->dn_next; continue; } fown = &dn->dn_filp->f_owner; send_sigio(fown, dn->dn_fd, POLL_MSG); if (dn->dn_mask & FS_DN_MULTISHOT) prev = &dn->dn_next; else { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); dnotify_recalc_inode_mask(inode_mark); } } spin_unlock(&inode_mark->lock); return 0; } static void dnotify_free_mark(struct fsnotify_mark *fsn_mark) { struct dnotify_mark *dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); BUG_ON(dn_mark->dn); kmem_cache_free(dnotify_mark_cache, dn_mark); } static const struct fsnotify_ops dnotify_fsnotify_ops = { .handle_inode_event = dnotify_handle_event, .free_mark = dnotify_free_mark, }; /* * Called every time a file is closed. Looks first for a dnotify mark on the * inode. If one is found run all of the ->dn structures attached to that * mark for one relevant to this process closing the file and remove that * dnotify_struct. If that was the last dnotify_struct also remove the * fsnotify_mark. */ void dnotify_flush(struct file *filp, fl_owner_t id) { struct fsnotify_mark *fsn_mark; struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct inode *inode; bool free = false; inode = file_inode(filp); if (!S_ISDIR(inode->i_mode)) return; fsn_mark = fsnotify_find_inode_mark(inode, dnotify_group); if (!fsn_mark) return; dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); fsnotify_group_lock(dnotify_group); spin_lock(&fsn_mark->lock); prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_owner == id) && (dn->dn_filp == filp)) { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); dnotify_recalc_inode_mask(fsn_mark); break; } prev = &dn->dn_next; } spin_unlock(&fsn_mark->lock); /* nothing else could have found us thanks to the dnotify_groups mark_mutex */ if (dn_mark->dn == NULL) { fsnotify_detach_mark(fsn_mark); free = true; } fsnotify_group_unlock(dnotify_group); if (free) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); } /* this conversion is done only at watch creation */ static __u32 convert_arg(unsigned int arg) { __u32 new_mask = FS_EVENT_ON_CHILD; if (arg & DN_MULTISHOT) new_mask |= FS_DN_MULTISHOT; if (arg & DN_DELETE) new_mask |= (FS_DELETE | FS_MOVED_FROM); if (arg & DN_MODIFY) new_mask |= FS_MODIFY; if (arg & DN_ACCESS) new_mask |= FS_ACCESS; if (arg & DN_ATTRIB) new_mask |= FS_ATTRIB; if (arg & DN_RENAME) new_mask |= FS_RENAME; if (arg & DN_CREATE) new_mask |= (FS_CREATE | FS_MOVED_TO); return new_mask; } /* * If multiple processes watch the same inode with dnotify there is only one * dnotify mark in inode->i_fsnotify_marks but we chain a dnotify_struct * onto that mark. This function either attaches the new dnotify_struct onto * that list, or it |= the mask onto an existing dnofiy_struct. */ static int attach_dn(struct dnotify_struct *dn, struct dnotify_mark *dn_mark, fl_owner_t id, int fd, struct file *filp, __u32 mask) { struct dnotify_struct *odn; odn = dn_mark->dn; while (odn != NULL) { /* adding more events to existing dnofiy_struct? */ if ((odn->dn_owner == id) && (odn->dn_filp == filp)) { odn->dn_fd = fd; odn->dn_mask |= mask; return -EEXIST; } odn = odn->dn_next; } dn->dn_mask = mask; dn->dn_fd = fd; dn->dn_filp = filp; dn->dn_owner = id; dn->dn_next = dn_mark->dn; dn_mark->dn = dn; return 0; } /* * When a process calls fcntl to attach a dnotify watch to a directory it ends * up here. Allocate both a mark for fsnotify to add and a dnotify_struct to be * attached to the fsnotify_mark. */ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) { struct dnotify_mark *new_dn_mark, *dn_mark; struct fsnotify_mark *new_fsn_mark, *fsn_mark; struct dnotify_struct *dn; struct inode *inode; fl_owner_t id = current->files; struct file *f = NULL; int destroy = 0, error = 0; __u32 mask; /* we use these to tell if we need to kfree */ new_fsn_mark = NULL; dn = NULL; if (!dir_notify_enable) { error = -EINVAL; goto out_err; } /* a 0 mask means we are explicitly removing the watch */ if ((arg & ~DN_MULTISHOT) == 0) { dnotify_flush(filp, id); error = 0; goto out_err; } /* dnotify only works on directories */ inode = file_inode(filp); if (!S_ISDIR(inode->i_mode)) { error = -ENOTDIR; goto out_err; } /* * convert the userspace DN_* "arg" to the internal FS_* * defined in fsnotify */ mask = convert_arg(arg); error = security_path_notify(&filp->f_path, mask, FSNOTIFY_OBJ_TYPE_INODE); if (error) goto out_err; /* expect most fcntl to add new rather than augment old */ dn = kmem_cache_alloc(dnotify_struct_cache, GFP_KERNEL); if (!dn) { error = -ENOMEM; goto out_err; } /* new fsnotify mark, we expect most fcntl calls to add a new mark */ new_dn_mark = kmem_cache_alloc(dnotify_mark_cache, GFP_KERNEL); if (!new_dn_mark) { error = -ENOMEM; goto out_err; } /* set up the new_fsn_mark and new_dn_mark */ new_fsn_mark = &new_dn_mark->fsn_mark; fsnotify_init_mark(new_fsn_mark, dnotify_group); new_fsn_mark->mask = mask; new_dn_mark->dn = NULL; /* this is needed to prevent the fcntl/close race described below */ fsnotify_group_lock(dnotify_group); /* add the new_fsn_mark or find an old one. */ fsn_mark = fsnotify_find_inode_mark(inode, dnotify_group); if (fsn_mark) { dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); spin_lock(&fsn_mark->lock); } else { error = fsnotify_add_inode_mark_locked(new_fsn_mark, inode, 0); if (error) { fsnotify_group_unlock(dnotify_group); goto out_err; } spin_lock(&new_fsn_mark->lock); fsn_mark = new_fsn_mark; dn_mark = new_dn_mark; /* we used new_fsn_mark, so don't free it */ new_fsn_mark = NULL; } rcu_read_lock(); f = lookup_fdget_rcu(fd); rcu_read_unlock(); /* if (f != filp) means that we lost a race and another task/thread * actually closed the fd we are still playing with before we grabbed * the dnotify_groups mark_mutex and fsn_mark->lock. Since closing the * fd is the only time we clean up the marks we need to get our mark * off the list. */ if (f != filp) { /* if we added ourselves, shoot ourselves, it's possible that * the flush actually did shoot this fsn_mark. That's fine too * since multiple calls to destroy_mark is perfectly safe, if * we found a dn_mark already attached to the inode, just sod * off silently as the flush at close time dealt with it. */ if (dn_mark == new_dn_mark) destroy = 1; error = 0; goto out; } __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); error = attach_dn(dn, dn_mark, id, fd, filp, mask); /* !error means that we attached the dn to the dn_mark, so don't free it */ if (!error) dn = NULL; /* -EEXIST means that we didn't add this new dn and used an old one. * that isn't an error (and the unused dn should be freed) */ else if (error == -EEXIST) error = 0; dnotify_recalc_inode_mask(fsn_mark); out: spin_unlock(&fsn_mark->lock); if (destroy) fsnotify_detach_mark(fsn_mark); fsnotify_group_unlock(dnotify_group); if (destroy) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); out_err: if (new_fsn_mark) fsnotify_put_mark(new_fsn_mark); if (dn) kmem_cache_free(dnotify_struct_cache, dn); if (f) fput(f); return error; } static int __init dnotify_init(void) { dnotify_struct_cache = KMEM_CACHE(dnotify_struct, SLAB_PANIC|SLAB_ACCOUNT); dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT); dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops, FSNOTIFY_GROUP_NOFS); if (IS_ERR(dnotify_group)) panic("unable to allocate fsnotify group for dnotify\n"); dnotify_sysctl_init(); return 0; } module_init(dnotify_init) |
| 1 1772 1772 9 6 9 9 1 1 9 5 5 5 1 8 9 9 9 1 9 8 9 1774 1772 1768 1769 9 9 9 9 1773 1768 | 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 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/common.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include <linux/uaccess.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/string_helpers.h> #include "common.h" /* String table for operation mode. */ const char * const tomoyo_mode[TOMOYO_CONFIG_MAX_MODE] = { [TOMOYO_CONFIG_DISABLED] = "disabled", [TOMOYO_CONFIG_LEARNING] = "learning", [TOMOYO_CONFIG_PERMISSIVE] = "permissive", [TOMOYO_CONFIG_ENFORCING] = "enforcing" }; /* String table for /sys/kernel/security/tomoyo/profile */ const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX] = { /* CONFIG::file group */ [TOMOYO_MAC_FILE_EXECUTE] = "execute", [TOMOYO_MAC_FILE_OPEN] = "open", [TOMOYO_MAC_FILE_CREATE] = "create", [TOMOYO_MAC_FILE_UNLINK] = "unlink", [TOMOYO_MAC_FILE_GETATTR] = "getattr", [TOMOYO_MAC_FILE_MKDIR] = "mkdir", [TOMOYO_MAC_FILE_RMDIR] = "rmdir", [TOMOYO_MAC_FILE_MKFIFO] = "mkfifo", [TOMOYO_MAC_FILE_MKSOCK] = "mksock", [TOMOYO_MAC_FILE_TRUNCATE] = "truncate", [TOMOYO_MAC_FILE_SYMLINK] = "symlink", [TOMOYO_MAC_FILE_MKBLOCK] = "mkblock", [TOMOYO_MAC_FILE_MKCHAR] = "mkchar", [TOMOYO_MAC_FILE_LINK] = "link", [TOMOYO_MAC_FILE_RENAME] = "rename", [TOMOYO_MAC_FILE_CHMOD] = "chmod", [TOMOYO_MAC_FILE_CHOWN] = "chown", [TOMOYO_MAC_FILE_CHGRP] = "chgrp", [TOMOYO_MAC_FILE_IOCTL] = "ioctl", [TOMOYO_MAC_FILE_CHROOT] = "chroot", [TOMOYO_MAC_FILE_MOUNT] = "mount", [TOMOYO_MAC_FILE_UMOUNT] = "unmount", [TOMOYO_MAC_FILE_PIVOT_ROOT] = "pivot_root", /* CONFIG::network group */ [TOMOYO_MAC_NETWORK_INET_STREAM_BIND] = "inet_stream_bind", [TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN] = "inet_stream_listen", [TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT] = "inet_stream_connect", [TOMOYO_MAC_NETWORK_INET_DGRAM_BIND] = "inet_dgram_bind", [TOMOYO_MAC_NETWORK_INET_DGRAM_SEND] = "inet_dgram_send", [TOMOYO_MAC_NETWORK_INET_RAW_BIND] = "inet_raw_bind", [TOMOYO_MAC_NETWORK_INET_RAW_SEND] = "inet_raw_send", [TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND] = "unix_stream_bind", [TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN] = "unix_stream_listen", [TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT] = "unix_stream_connect", [TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND] = "unix_dgram_bind", [TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND] = "unix_dgram_send", [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND] = "unix_seqpacket_bind", [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN] = "unix_seqpacket_listen", [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT] = "unix_seqpacket_connect", /* CONFIG::misc group */ [TOMOYO_MAC_ENVIRON] = "env", /* CONFIG group */ [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_FILE] = "file", [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_NETWORK] = "network", [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_MISC] = "misc", }; /* String table for conditions. */ const char * const tomoyo_condition_keyword[TOMOYO_MAX_CONDITION_KEYWORD] = { [TOMOYO_TASK_UID] = "task.uid", [TOMOYO_TASK_EUID] = "task.euid", [TOMOYO_TASK_SUID] = "task.suid", [TOMOYO_TASK_FSUID] = "task.fsuid", [TOMOYO_TASK_GID] = "task.gid", [TOMOYO_TASK_EGID] = "task.egid", [TOMOYO_TASK_SGID] = "task.sgid", [TOMOYO_TASK_FSGID] = "task.fsgid", [TOMOYO_TASK_PID] = "task.pid", [TOMOYO_TASK_PPID] = "task.ppid", [TOMOYO_EXEC_ARGC] = "exec.argc", [TOMOYO_EXEC_ENVC] = "exec.envc", [TOMOYO_TYPE_IS_SOCKET] = "socket", [TOMOYO_TYPE_IS_SYMLINK] = "symlink", [TOMOYO_TYPE_IS_FILE] = "file", [TOMOYO_TYPE_IS_BLOCK_DEV] = "block", [TOMOYO_TYPE_IS_DIRECTORY] = "directory", [TOMOYO_TYPE_IS_CHAR_DEV] = "char", [TOMOYO_TYPE_IS_FIFO] = "fifo", [TOMOYO_MODE_SETUID] = "setuid", [TOMOYO_MODE_SETGID] = "setgid", [TOMOYO_MODE_STICKY] = "sticky", [TOMOYO_MODE_OWNER_READ] = "owner_read", [TOMOYO_MODE_OWNER_WRITE] = "owner_write", [TOMOYO_MODE_OWNER_EXECUTE] = "owner_execute", [TOMOYO_MODE_GROUP_READ] = "group_read", [TOMOYO_MODE_GROUP_WRITE] = "group_write", [TOMOYO_MODE_GROUP_EXECUTE] = "group_execute", [TOMOYO_MODE_OTHERS_READ] = "others_read", [TOMOYO_MODE_OTHERS_WRITE] = "others_write", [TOMOYO_MODE_OTHERS_EXECUTE] = "others_execute", [TOMOYO_EXEC_REALPATH] = "exec.realpath", [TOMOYO_SYMLINK_TARGET] = "symlink.target", [TOMOYO_PATH1_UID] = "path1.uid", [TOMOYO_PATH1_GID] = "path1.gid", [TOMOYO_PATH1_INO] = "path1.ino", [TOMOYO_PATH1_MAJOR] = "path1.major", [TOMOYO_PATH1_MINOR] = "path1.minor", [TOMOYO_PATH1_PERM] = "path1.perm", [TOMOYO_PATH1_TYPE] = "path1.type", [TOMOYO_PATH1_DEV_MAJOR] = "path1.dev_major", [TOMOYO_PATH1_DEV_MINOR] = "path1.dev_minor", [TOMOYO_PATH2_UID] = "path2.uid", [TOMOYO_PATH2_GID] = "path2.gid", [TOMOYO_PATH2_INO] = "path2.ino", [TOMOYO_PATH2_MAJOR] = "path2.major", [TOMOYO_PATH2_MINOR] = "path2.minor", [TOMOYO_PATH2_PERM] = "path2.perm", [TOMOYO_PATH2_TYPE] = "path2.type", [TOMOYO_PATH2_DEV_MAJOR] = "path2.dev_major", [TOMOYO_PATH2_DEV_MINOR] = "path2.dev_minor", [TOMOYO_PATH1_PARENT_UID] = "path1.parent.uid", [TOMOYO_PATH1_PARENT_GID] = "path1.parent.gid", [TOMOYO_PATH1_PARENT_INO] = "path1.parent.ino", [TOMOYO_PATH1_PARENT_PERM] = "path1.parent.perm", [TOMOYO_PATH2_PARENT_UID] = "path2.parent.uid", [TOMOYO_PATH2_PARENT_GID] = "path2.parent.gid", [TOMOYO_PATH2_PARENT_INO] = "path2.parent.ino", [TOMOYO_PATH2_PARENT_PERM] = "path2.parent.perm", }; /* String table for PREFERENCE keyword. */ static const char * const tomoyo_pref_keywords[TOMOYO_MAX_PREF] = { [TOMOYO_PREF_MAX_AUDIT_LOG] = "max_audit_log", [TOMOYO_PREF_MAX_LEARNING_ENTRY] = "max_learning_entry", }; /* String table for path operation. */ const char * const tomoyo_path_keyword[TOMOYO_MAX_PATH_OPERATION] = { [TOMOYO_TYPE_EXECUTE] = "execute", [TOMOYO_TYPE_READ] = "read", [TOMOYO_TYPE_WRITE] = "write", [TOMOYO_TYPE_APPEND] = "append", [TOMOYO_TYPE_UNLINK] = "unlink", [TOMOYO_TYPE_GETATTR] = "getattr", [TOMOYO_TYPE_RMDIR] = "rmdir", [TOMOYO_TYPE_TRUNCATE] = "truncate", [TOMOYO_TYPE_SYMLINK] = "symlink", [TOMOYO_TYPE_CHROOT] = "chroot", [TOMOYO_TYPE_UMOUNT] = "unmount", }; /* String table for socket's operation. */ const char * const tomoyo_socket_keyword[TOMOYO_MAX_NETWORK_OPERATION] = { [TOMOYO_NETWORK_BIND] = "bind", [TOMOYO_NETWORK_LISTEN] = "listen", [TOMOYO_NETWORK_CONNECT] = "connect", [TOMOYO_NETWORK_SEND] = "send", }; /* String table for categories. */ static const char * const tomoyo_category_keywords [TOMOYO_MAX_MAC_CATEGORY_INDEX] = { [TOMOYO_MAC_CATEGORY_FILE] = "file", [TOMOYO_MAC_CATEGORY_NETWORK] = "network", [TOMOYO_MAC_CATEGORY_MISC] = "misc", }; /* Permit policy management by non-root user? */ static bool tomoyo_manage_by_non_root; /* Utility functions. */ /** * tomoyo_addprintf - strncat()-like-snprintf(). * * @buffer: Buffer to write to. Must be '\0'-terminated. * @len: Size of @buffer. * @fmt: The printf()'s format string, followed by parameters. * * Returns nothing. */ __printf(3, 4) static void tomoyo_addprintf(char *buffer, int len, const char *fmt, ...) { va_list args; const int pos = strlen(buffer); va_start(args, fmt); vsnprintf(buffer + pos, len - pos - 1, fmt, args); va_end(args); } /** * tomoyo_flush - Flush queued string to userspace's buffer. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns true if all data was flushed, false otherwise. */ static bool tomoyo_flush(struct tomoyo_io_buffer *head) { while (head->r.w_pos) { const char *w = head->r.w[0]; size_t len = strlen(w); if (len) { if (len > head->read_user_buf_avail) len = head->read_user_buf_avail; if (!len) return false; if (copy_to_user(head->read_user_buf, w, len)) return false; head->read_user_buf_avail -= len; head->read_user_buf += len; w += len; } head->r.w[0] = w; if (*w) return false; /* Add '\0' for audit logs and query. */ if (head->poll) { if (!head->read_user_buf_avail || copy_to_user(head->read_user_buf, "", 1)) return false; head->read_user_buf_avail--; head->read_user_buf++; } head->r.w_pos--; for (len = 0; len < head->r.w_pos; len++) head->r.w[len] = head->r.w[len + 1]; } head->r.avail = 0; return true; } /** * tomoyo_set_string - Queue string to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * @string: String to print. * * Note that @string has to be kept valid until @head is kfree()d. * This means that char[] allocated on stack memory cannot be passed to * this function. Use tomoyo_io_printf() for char[] allocated on stack memory. */ static void tomoyo_set_string(struct tomoyo_io_buffer *head, const char *string) { if (head->r.w_pos < TOMOYO_MAX_IO_READ_QUEUE) { head->r.w[head->r.w_pos++] = string; tomoyo_flush(head); } else WARN_ON(1); } static void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt, ...) __printf(2, 3); /** * tomoyo_io_printf - printf() to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * @fmt: The printf()'s format string, followed by parameters. */ static void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt, ...) { va_list args; size_t len; size_t pos = head->r.avail; int size = head->readbuf_size - pos; if (size <= 0) return; va_start(args, fmt); len = vsnprintf(head->read_buf + pos, size, fmt, args) + 1; va_end(args); if (pos + len >= head->readbuf_size) { WARN_ON(1); return; } head->r.avail += len; tomoyo_set_string(head, head->read_buf + pos); } /** * tomoyo_set_space - Put a space to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_set_space(struct tomoyo_io_buffer *head) { tomoyo_set_string(head, " "); } /** * tomoyo_set_lf - Put a line feed to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static bool tomoyo_set_lf(struct tomoyo_io_buffer *head) { tomoyo_set_string(head, "\n"); return !head->r.w_pos; } /** * tomoyo_set_slash - Put a shash to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_set_slash(struct tomoyo_io_buffer *head) { tomoyo_set_string(head, "/"); } /* List of namespaces. */ LIST_HEAD(tomoyo_namespace_list); /* True if namespace other than tomoyo_kernel_namespace is defined. */ static bool tomoyo_namespace_enabled; /** * tomoyo_init_policy_namespace - Initialize namespace. * * @ns: Pointer to "struct tomoyo_policy_namespace". * * Returns nothing. */ void tomoyo_init_policy_namespace(struct tomoyo_policy_namespace *ns) { unsigned int idx; for (idx = 0; idx < TOMOYO_MAX_ACL_GROUPS; idx++) INIT_LIST_HEAD(&ns->acl_group[idx]); for (idx = 0; idx < TOMOYO_MAX_GROUP; idx++) INIT_LIST_HEAD(&ns->group_list[idx]); for (idx = 0; idx < TOMOYO_MAX_POLICY; idx++) INIT_LIST_HEAD(&ns->policy_list[idx]); ns->profile_version = 20150505; tomoyo_namespace_enabled = !list_empty(&tomoyo_namespace_list); list_add_tail_rcu(&ns->namespace_list, &tomoyo_namespace_list); } /** * tomoyo_print_namespace - Print namespace header. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_print_namespace(struct tomoyo_io_buffer *head) { if (!tomoyo_namespace_enabled) return; tomoyo_set_string(head, container_of(head->r.ns, struct tomoyo_policy_namespace, namespace_list)->name); tomoyo_set_space(head); } /** * tomoyo_print_name_union - Print a tomoyo_name_union. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_name_union". */ static void tomoyo_print_name_union(struct tomoyo_io_buffer *head, const struct tomoyo_name_union *ptr) { tomoyo_set_space(head); if (ptr->group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->group->group_name->name); } else { tomoyo_set_string(head, ptr->filename->name); } } /** * tomoyo_print_name_union_quoted - Print a tomoyo_name_union with a quote. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_name_union". * * Returns nothing. */ static void tomoyo_print_name_union_quoted(struct tomoyo_io_buffer *head, const struct tomoyo_name_union *ptr) { if (ptr->group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->group->group_name->name); } else { tomoyo_set_string(head, "\""); tomoyo_set_string(head, ptr->filename->name); tomoyo_set_string(head, "\""); } } /** * tomoyo_print_number_union_nospace - Print a tomoyo_number_union without a space. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_number_union". * * Returns nothing. */ static void tomoyo_print_number_union_nospace (struct tomoyo_io_buffer *head, const struct tomoyo_number_union *ptr) { if (ptr->group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->group->group_name->name); } else { int i; unsigned long min = ptr->values[0]; const unsigned long max = ptr->values[1]; u8 min_type = ptr->value_type[0]; const u8 max_type = ptr->value_type[1]; char buffer[128]; buffer[0] = '\0'; for (i = 0; i < 2; i++) { switch (min_type) { case TOMOYO_VALUE_TYPE_HEXADECIMAL: tomoyo_addprintf(buffer, sizeof(buffer), "0x%lX", min); break; case TOMOYO_VALUE_TYPE_OCTAL: tomoyo_addprintf(buffer, sizeof(buffer), "0%lo", min); break; default: tomoyo_addprintf(buffer, sizeof(buffer), "%lu", min); break; } if (min == max && min_type == max_type) break; tomoyo_addprintf(buffer, sizeof(buffer), "-"); min_type = max_type; min = max; } tomoyo_io_printf(head, "%s", buffer); } } /** * tomoyo_print_number_union - Print a tomoyo_number_union. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_number_union". * * Returns nothing. */ static void tomoyo_print_number_union(struct tomoyo_io_buffer *head, const struct tomoyo_number_union *ptr) { tomoyo_set_space(head); tomoyo_print_number_union_nospace(head, ptr); } /** * tomoyo_assign_profile - Create a new profile. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number to create. * * Returns pointer to "struct tomoyo_profile" on success, NULL otherwise. */ static struct tomoyo_profile *tomoyo_assign_profile (struct tomoyo_policy_namespace *ns, const unsigned int profile) { struct tomoyo_profile *ptr; struct tomoyo_profile *entry; if (profile >= TOMOYO_MAX_PROFILES) return NULL; ptr = ns->profile_ptr[profile]; if (ptr) return ptr; entry = kzalloc(sizeof(*entry), GFP_NOFS | __GFP_NOWARN); if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; ptr = ns->profile_ptr[profile]; if (!ptr && tomoyo_memory_ok(entry)) { ptr = entry; ptr->default_config = TOMOYO_CONFIG_DISABLED | TOMOYO_CONFIG_WANT_GRANT_LOG | TOMOYO_CONFIG_WANT_REJECT_LOG; memset(ptr->config, TOMOYO_CONFIG_USE_DEFAULT, sizeof(ptr->config)); ptr->pref[TOMOYO_PREF_MAX_AUDIT_LOG] = CONFIG_SECURITY_TOMOYO_MAX_AUDIT_LOG; ptr->pref[TOMOYO_PREF_MAX_LEARNING_ENTRY] = CONFIG_SECURITY_TOMOYO_MAX_ACCEPT_ENTRY; mb(); /* Avoid out-of-order execution. */ ns->profile_ptr[profile] = ptr; entry = NULL; } mutex_unlock(&tomoyo_policy_lock); out: kfree(entry); return ptr; } /** * tomoyo_profile - Find a profile. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number to find. * * Returns pointer to "struct tomoyo_profile". */ struct tomoyo_profile *tomoyo_profile(const struct tomoyo_policy_namespace *ns, const u8 profile) { static struct tomoyo_profile tomoyo_null_profile; struct tomoyo_profile *ptr = ns->profile_ptr[profile]; if (!ptr) ptr = &tomoyo_null_profile; return ptr; } /** * tomoyo_find_yesno - Find values for specified keyword. * * @string: String to check. * @find: Name of keyword. * * Returns 1 if "@find=yes" was found, 0 if "@find=no" was found, -1 otherwise. */ static s8 tomoyo_find_yesno(const char *string, const char *find) { const char *cp = strstr(string, find); if (cp) { cp += strlen(find); if (!strncmp(cp, "=yes", 4)) return 1; else if (!strncmp(cp, "=no", 3)) return 0; } return -1; } /** * tomoyo_set_uint - Set value for specified preference. * * @i: Pointer to "unsigned int". * @string: String to check. * @find: Name of keyword. * * Returns nothing. */ static void tomoyo_set_uint(unsigned int *i, const char *string, const char *find) { const char *cp = strstr(string, find); if (cp) sscanf(cp + strlen(find), "=%u", i); } /** * tomoyo_set_mode - Set mode for specified profile. * * @name: Name of functionality. * @value: Mode for @name. * @profile: Pointer to "struct tomoyo_profile". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_set_mode(char *name, const char *value, struct tomoyo_profile *profile) { u8 i; u8 config; if (!strcmp(name, "CONFIG")) { i = TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX; config = profile->default_config; } else if (tomoyo_str_starts(&name, "CONFIG::")) { config = 0; for (i = 0; i < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX; i++) { int len = 0; if (i < TOMOYO_MAX_MAC_INDEX) { const u8 c = tomoyo_index2category[i]; const char *category = tomoyo_category_keywords[c]; len = strlen(category); if (strncmp(name, category, len) || name[len++] != ':' || name[len++] != ':') continue; } if (strcmp(name + len, tomoyo_mac_keywords[i])) continue; config = profile->config[i]; break; } if (i == TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX) return -EINVAL; } else { return -EINVAL; } if (strstr(value, "use_default")) { config = TOMOYO_CONFIG_USE_DEFAULT; } else { u8 mode; for (mode = 0; mode < 4; mode++) if (strstr(value, tomoyo_mode[mode])) /* * Update lower 3 bits in order to distinguish * 'config' from 'TOMOYO_CONFIG_USE_DEFAULT'. */ config = (config & ~7) | mode; if (config != TOMOYO_CONFIG_USE_DEFAULT) { switch (tomoyo_find_yesno(value, "grant_log")) { case 1: config |= TOMOYO_CONFIG_WANT_GRANT_LOG; break; case 0: config &= ~TOMOYO_CONFIG_WANT_GRANT_LOG; break; } switch (tomoyo_find_yesno(value, "reject_log")) { case 1: config |= TOMOYO_CONFIG_WANT_REJECT_LOG; break; case 0: config &= ~TOMOYO_CONFIG_WANT_REJECT_LOG; break; } } } if (i < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX) profile->config[i] = config; else if (config != TOMOYO_CONFIG_USE_DEFAULT) profile->default_config = config; return 0; } /** * tomoyo_write_profile - Write profile table. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_write_profile(struct tomoyo_io_buffer *head) { char *data = head->write_buf; unsigned int i; char *cp; struct tomoyo_profile *profile; if (sscanf(data, "PROFILE_VERSION=%u", &head->w.ns->profile_version) == 1) return 0; i = simple_strtoul(data, &cp, 10); if (*cp != '-') return -EINVAL; data = cp + 1; profile = tomoyo_assign_profile(head->w.ns, i); if (!profile) return -EINVAL; cp = strchr(data, '='); if (!cp) return -EINVAL; *cp++ = '\0'; if (!strcmp(data, "COMMENT")) { static DEFINE_SPINLOCK(lock); const struct tomoyo_path_info *new_comment = tomoyo_get_name(cp); const struct tomoyo_path_info *old_comment; if (!new_comment) return -ENOMEM; spin_lock(&lock); old_comment = profile->comment; profile->comment = new_comment; spin_unlock(&lock); tomoyo_put_name(old_comment); return 0; } if (!strcmp(data, "PREFERENCE")) { for (i = 0; i < TOMOYO_MAX_PREF; i++) tomoyo_set_uint(&profile->pref[i], cp, tomoyo_pref_keywords[i]); return 0; } return tomoyo_set_mode(data, cp, profile); } /** * tomoyo_print_config - Print mode for specified functionality. * * @head: Pointer to "struct tomoyo_io_buffer". * @config: Mode for that functionality. * * Returns nothing. * * Caller prints functionality's name. */ static void tomoyo_print_config(struct tomoyo_io_buffer *head, const u8 config) { tomoyo_io_printf(head, "={ mode=%s grant_log=%s reject_log=%s }\n", tomoyo_mode[config & 3], str_yes_no(config & TOMOYO_CONFIG_WANT_GRANT_LOG), str_yes_no(config & TOMOYO_CONFIG_WANT_REJECT_LOG)); } /** * tomoyo_read_profile - Read profile table. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_read_profile(struct tomoyo_io_buffer *head) { u8 index; struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); const struct tomoyo_profile *profile; if (head->r.eof) return; next: index = head->r.index; profile = ns->profile_ptr[index]; switch (head->r.step) { case 0: tomoyo_print_namespace(head); tomoyo_io_printf(head, "PROFILE_VERSION=%u\n", ns->profile_version); head->r.step++; break; case 1: for ( ; head->r.index < TOMOYO_MAX_PROFILES; head->r.index++) if (ns->profile_ptr[head->r.index]) break; if (head->r.index == TOMOYO_MAX_PROFILES) { head->r.eof = true; return; } head->r.step++; break; case 2: { u8 i; const struct tomoyo_path_info *comment = profile->comment; tomoyo_print_namespace(head); tomoyo_io_printf(head, "%u-COMMENT=", index); tomoyo_set_string(head, comment ? comment->name : ""); tomoyo_set_lf(head); tomoyo_print_namespace(head); tomoyo_io_printf(head, "%u-PREFERENCE={ ", index); for (i = 0; i < TOMOYO_MAX_PREF; i++) tomoyo_io_printf(head, "%s=%u ", tomoyo_pref_keywords[i], profile->pref[i]); tomoyo_set_string(head, "}\n"); head->r.step++; } break; case 3: { tomoyo_print_namespace(head); tomoyo_io_printf(head, "%u-%s", index, "CONFIG"); tomoyo_print_config(head, profile->default_config); head->r.bit = 0; head->r.step++; } break; case 4: for ( ; head->r.bit < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX; head->r.bit++) { const u8 i = head->r.bit; const u8 config = profile->config[i]; if (config == TOMOYO_CONFIG_USE_DEFAULT) continue; tomoyo_print_namespace(head); if (i < TOMOYO_MAX_MAC_INDEX) tomoyo_io_printf(head, "%u-CONFIG::%s::%s", index, tomoyo_category_keywords [tomoyo_index2category[i]], tomoyo_mac_keywords[i]); else tomoyo_io_printf(head, "%u-CONFIG::%s", index, tomoyo_mac_keywords[i]); tomoyo_print_config(head, config); head->r.bit++; break; } if (head->r.bit == TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX) { head->r.index++; head->r.step = 1; } break; } if (tomoyo_flush(head)) goto next; } /** * tomoyo_same_manager - Check for duplicated "struct tomoyo_manager" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_manager(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { return container_of(a, struct tomoyo_manager, head)->manager == container_of(b, struct tomoyo_manager, head)->manager; } /** * tomoyo_update_manager_entry - Add a manager entry. * * @manager: The path to manager or the domainnamme. * @is_delete: True if it is a delete request. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_manager_entry(const char *manager, const bool is_delete) { struct tomoyo_manager e = { }; struct tomoyo_acl_param param = { /* .ns = &tomoyo_kernel_namespace, */ .is_delete = is_delete, .list = &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], }; int error = is_delete ? -ENOENT : -ENOMEM; if (!tomoyo_correct_domain(manager) && !tomoyo_correct_word(manager)) return -EINVAL; e.manager = tomoyo_get_name(manager); if (e.manager) { error = tomoyo_update_policy(&e.head, sizeof(e), ¶m, tomoyo_same_manager); tomoyo_put_name(e.manager); } return error; } /** * tomoyo_write_manager - Write manager policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_manager(struct tomoyo_io_buffer *head) { char *data = head->write_buf; if (!strcmp(data, "manage_by_non_root")) { tomoyo_manage_by_non_root = !head->w.is_delete; return 0; } return tomoyo_update_manager_entry(data, head->w.is_delete); } /** * tomoyo_read_manager - Read manager policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Caller holds tomoyo_read_lock(). */ static void tomoyo_read_manager(struct tomoyo_io_buffer *head) { if (head->r.eof) return; list_for_each_cookie(head->r.acl, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER]) { struct tomoyo_manager *ptr = list_entry(head->r.acl, typeof(*ptr), head.list); if (ptr->head.is_deleted) continue; if (!tomoyo_flush(head)) return; tomoyo_set_string(head, ptr->manager->name); tomoyo_set_lf(head); } head->r.eof = true; } /** * tomoyo_manager - Check whether the current process is a policy manager. * * Returns true if the current process is permitted to modify policy * via /sys/kernel/security/tomoyo/ interface. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_manager(void) { struct tomoyo_manager *ptr; const char *exe; const struct task_struct *task = current; const struct tomoyo_path_info *domainname = tomoyo_domain()->domainname; bool found = IS_ENABLED(CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING); if (!tomoyo_policy_loaded) return true; if (!tomoyo_manage_by_non_root && (!uid_eq(task->cred->uid, GLOBAL_ROOT_UID) || !uid_eq(task->cred->euid, GLOBAL_ROOT_UID))) return false; exe = tomoyo_get_exe(); if (!exe) return false; list_for_each_entry_rcu(ptr, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], head.list, srcu_read_lock_held(&tomoyo_ss)) { if (!ptr->head.is_deleted && (!tomoyo_pathcmp(domainname, ptr->manager) || !strcmp(exe, ptr->manager->name))) { found = true; break; } } if (!found) { /* Reduce error messages. */ static pid_t last_pid; const pid_t pid = current->pid; if (last_pid != pid) { pr_warn("%s ( %s ) is not permitted to update policies.\n", domainname->name, exe); last_pid = pid; } } kfree(exe); return found; } static struct tomoyo_domain_info *tomoyo_find_domain_by_qid (unsigned int serial); /** * tomoyo_select_domain - Parse select command. * * @head: Pointer to "struct tomoyo_io_buffer". * @data: String to parse. * * Returns true on success, false otherwise. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_select_domain(struct tomoyo_io_buffer *head, const char *data) { unsigned int pid; struct tomoyo_domain_info *domain = NULL; bool global_pid = false; if (strncmp(data, "select ", 7)) return false; data += 7; if (sscanf(data, "pid=%u", &pid) == 1 || (global_pid = true, sscanf(data, "global-pid=%u", &pid) == 1)) { struct task_struct *p; rcu_read_lock(); if (global_pid) p = find_task_by_pid_ns(pid, &init_pid_ns); else p = find_task_by_vpid(pid); if (p) domain = tomoyo_task(p)->domain_info; rcu_read_unlock(); } else if (!strncmp(data, "domain=", 7)) { if (tomoyo_domain_def(data + 7)) domain = tomoyo_find_domain(data + 7); } else if (sscanf(data, "Q=%u", &pid) == 1) { domain = tomoyo_find_domain_by_qid(pid); } else return false; head->w.domain = domain; /* Accessing read_buf is safe because head->io_sem is held. */ if (!head->read_buf) return true; /* Do nothing if open(O_WRONLY). */ memset(&head->r, 0, sizeof(head->r)); head->r.print_this_domain_only = true; if (domain) head->r.domain = &domain->list; else head->r.eof = true; tomoyo_io_printf(head, "# select %s\n", data); if (domain && domain->is_deleted) tomoyo_io_printf(head, "# This is a deleted domain.\n"); return true; } /** * tomoyo_same_task_acl - Check for duplicated "struct tomoyo_task_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_task_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_task_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_task_acl *p2 = container_of(b, typeof(*p2), head); return p1->domainname == p2->domainname; } /** * tomoyo_write_task - Update task related list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_task(struct tomoyo_acl_param *param) { int error = -EINVAL; if (tomoyo_str_starts(¶m->data, "manual_domain_transition ")) { struct tomoyo_task_acl e = { .head.type = TOMOYO_TYPE_MANUAL_TASK_ACL, .domainname = tomoyo_get_domainname(param), }; if (e.domainname) error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_task_acl, NULL); tomoyo_put_name(e.domainname); } return error; } /** * tomoyo_delete_domain - Delete a domain. * * @domainname: The name of domain. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_delete_domain(char *domainname) { struct tomoyo_domain_info *domain; struct tomoyo_path_info name; name.name = domainname; tomoyo_fill_path_info(&name); if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -EINTR; /* Is there an active domain? */ list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, srcu_read_lock_held(&tomoyo_ss)) { /* Never delete tomoyo_kernel_domain */ if (domain == &tomoyo_kernel_domain) continue; if (domain->is_deleted || tomoyo_pathcmp(domain->domainname, &name)) continue; domain->is_deleted = true; break; } mutex_unlock(&tomoyo_policy_lock); return 0; } /** * tomoyo_write_domain2 - Write domain policy. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @list: Pointer to "struct list_head". * @data: Policy to be interpreted. * @is_delete: True if it is a delete request. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_domain2(struct tomoyo_policy_namespace *ns, struct list_head *list, char *data, const bool is_delete) { struct tomoyo_acl_param param = { .ns = ns, .list = list, .data = data, .is_delete = is_delete, }; static const struct { const char *keyword; int (*write)(struct tomoyo_acl_param *param); } tomoyo_callback[5] = { { "file ", tomoyo_write_file }, { "network inet ", tomoyo_write_inet_network }, { "network unix ", tomoyo_write_unix_network }, { "misc ", tomoyo_write_misc }, { "task ", tomoyo_write_task }, }; u8 i; for (i = 0; i < ARRAY_SIZE(tomoyo_callback); i++) { if (!tomoyo_str_starts(¶m.data, tomoyo_callback[i].keyword)) continue; return tomoyo_callback[i].write(¶m); } return -EINVAL; } /* String table for domain flags. */ const char * const tomoyo_dif[TOMOYO_MAX_DOMAIN_INFO_FLAGS] = { [TOMOYO_DIF_QUOTA_WARNED] = "quota_exceeded\n", [TOMOYO_DIF_TRANSITION_FAILED] = "transition_failed\n", }; /** * tomoyo_write_domain - Write domain policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_domain(struct tomoyo_io_buffer *head) { char *data = head->write_buf; struct tomoyo_policy_namespace *ns; struct tomoyo_domain_info *domain = head->w.domain; const bool is_delete = head->w.is_delete; bool is_select = !is_delete && tomoyo_str_starts(&data, "select "); unsigned int idx; if (*data == '<') { int ret = 0; domain = NULL; if (is_delete) ret = tomoyo_delete_domain(data); else if (is_select) domain = tomoyo_find_domain(data); else domain = tomoyo_assign_domain(data, false); head->w.domain = domain; return ret; } if (!domain) return -EINVAL; ns = domain->ns; if (sscanf(data, "use_profile %u", &idx) == 1 && idx < TOMOYO_MAX_PROFILES) { if (!tomoyo_policy_loaded || ns->profile_ptr[idx]) if (!is_delete) domain->profile = (u8) idx; return 0; } if (sscanf(data, "use_group %u\n", &idx) == 1 && idx < TOMOYO_MAX_ACL_GROUPS) { if (!is_delete) set_bit(idx, domain->group); else clear_bit(idx, domain->group); return 0; } for (idx = 0; idx < TOMOYO_MAX_DOMAIN_INFO_FLAGS; idx++) { const char *cp = tomoyo_dif[idx]; if (strncmp(data, cp, strlen(cp) - 1)) continue; domain->flags[idx] = !is_delete; return 0; } return tomoyo_write_domain2(ns, &domain->acl_info_list, data, is_delete); } /** * tomoyo_print_condition - Print condition part. * * @head: Pointer to "struct tomoyo_io_buffer". * @cond: Pointer to "struct tomoyo_condition". * * Returns true on success, false otherwise. */ static bool tomoyo_print_condition(struct tomoyo_io_buffer *head, const struct tomoyo_condition *cond) { switch (head->r.cond_step) { case 0: head->r.cond_index = 0; head->r.cond_step++; if (cond->transit) { tomoyo_set_space(head); tomoyo_set_string(head, cond->transit->name); } fallthrough; case 1: { const u16 condc = cond->condc; const struct tomoyo_condition_element *condp = (typeof(condp)) (cond + 1); const struct tomoyo_number_union *numbers_p = (typeof(numbers_p)) (condp + condc); const struct tomoyo_name_union *names_p = (typeof(names_p)) (numbers_p + cond->numbers_count); const struct tomoyo_argv *argv = (typeof(argv)) (names_p + cond->names_count); const struct tomoyo_envp *envp = (typeof(envp)) (argv + cond->argc); u16 skip; for (skip = 0; skip < head->r.cond_index; skip++) { const u8 left = condp->left; const u8 right = condp->right; condp++; switch (left) { case TOMOYO_ARGV_ENTRY: argv++; continue; case TOMOYO_ENVP_ENTRY: envp++; continue; case TOMOYO_NUMBER_UNION: numbers_p++; break; } switch (right) { case TOMOYO_NAME_UNION: names_p++; break; case TOMOYO_NUMBER_UNION: numbers_p++; break; } } while (head->r.cond_index < condc) { const u8 match = condp->equals; const u8 left = condp->left; const u8 right = condp->right; if (!tomoyo_flush(head)) return false; condp++; head->r.cond_index++; tomoyo_set_space(head); switch (left) { case TOMOYO_ARGV_ENTRY: tomoyo_io_printf(head, "exec.argv[%lu]%s=\"", argv->index, argv->is_not ? "!" : ""); tomoyo_set_string(head, argv->value->name); tomoyo_set_string(head, "\""); argv++; continue; case TOMOYO_ENVP_ENTRY: tomoyo_set_string(head, "exec.envp[\""); tomoyo_set_string(head, envp->name->name); tomoyo_io_printf(head, "\"]%s=", envp->is_not ? "!" : ""); if (envp->value) { tomoyo_set_string(head, "\""); tomoyo_set_string(head, envp->value->name); tomoyo_set_string(head, "\""); } else { tomoyo_set_string(head, "NULL"); } envp++; continue; case TOMOYO_NUMBER_UNION: tomoyo_print_number_union_nospace (head, numbers_p++); break; default: tomoyo_set_string(head, tomoyo_condition_keyword[left]); break; } tomoyo_set_string(head, match ? "=" : "!="); switch (right) { case TOMOYO_NAME_UNION: tomoyo_print_name_union_quoted (head, names_p++); break; case TOMOYO_NUMBER_UNION: tomoyo_print_number_union_nospace (head, numbers_p++); break; default: tomoyo_set_string(head, tomoyo_condition_keyword[right]); break; } } } head->r.cond_step++; fallthrough; case 2: if (!tomoyo_flush(head)) break; head->r.cond_step++; fallthrough; case 3: if (cond->grant_log != TOMOYO_GRANTLOG_AUTO) tomoyo_io_printf(head, " grant_log=%s", str_yes_no(cond->grant_log == TOMOYO_GRANTLOG_YES)); tomoyo_set_lf(head); return true; } return false; } /** * tomoyo_set_group - Print "acl_group " header keyword and category name. * * @head: Pointer to "struct tomoyo_io_buffer". * @category: Category name. * * Returns nothing. */ static void tomoyo_set_group(struct tomoyo_io_buffer *head, const char *category) { if (head->type == TOMOYO_EXCEPTIONPOLICY) { tomoyo_print_namespace(head); tomoyo_io_printf(head, "acl_group %u ", head->r.acl_group_index); } tomoyo_set_string(head, category); } /** * tomoyo_print_entry - Print an ACL entry. * * @head: Pointer to "struct tomoyo_io_buffer". * @acl: Pointer to an ACL entry. * * Returns true on success, false otherwise. */ static bool tomoyo_print_entry(struct tomoyo_io_buffer *head, struct tomoyo_acl_info *acl) { const u8 acl_type = acl->type; bool first = true; u8 bit; if (head->r.print_cond_part) goto print_cond_part; if (acl->is_deleted) return true; if (!tomoyo_flush(head)) return false; else if (acl_type == TOMOYO_TYPE_PATH_ACL) { struct tomoyo_path_acl *ptr = container_of(acl, typeof(*ptr), head); const u16 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_PATH_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (head->r.print_transition_related_only && bit != TOMOYO_TYPE_EXECUTE) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_path_keyword[bit]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); } else if (acl_type == TOMOYO_TYPE_MANUAL_TASK_ACL) { struct tomoyo_task_acl *ptr = container_of(acl, typeof(*ptr), head); tomoyo_set_group(head, "task "); tomoyo_set_string(head, "manual_domain_transition "); tomoyo_set_string(head, ptr->domainname->name); } else if (head->r.print_transition_related_only) { return true; } else if (acl_type == TOMOYO_TYPE_PATH2_ACL) { struct tomoyo_path2_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_PATH2_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_mac_keywords [tomoyo_pp2mac[bit]]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name1); tomoyo_print_name_union(head, &ptr->name2); } else if (acl_type == TOMOYO_TYPE_PATH_NUMBER_ACL) { struct tomoyo_path_number_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_PATH_NUMBER_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_mac_keywords [tomoyo_pn2mac[bit]]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); tomoyo_print_number_union(head, &ptr->number); } else if (acl_type == TOMOYO_TYPE_MKDEV_ACL) { struct tomoyo_mkdev_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_MKDEV_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_mac_keywords [tomoyo_pnnn2mac[bit]]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); tomoyo_print_number_union(head, &ptr->mode); tomoyo_print_number_union(head, &ptr->major); tomoyo_print_number_union(head, &ptr->minor); } else if (acl_type == TOMOYO_TYPE_INET_ACL) { struct tomoyo_inet_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_NETWORK_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "network inet "); tomoyo_set_string(head, tomoyo_proto_keyword [ptr->protocol]); tomoyo_set_space(head); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_socket_keyword[bit]); } if (first) return true; tomoyo_set_space(head); if (ptr->address.group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->address.group->group_name ->name); } else { char buf[128]; tomoyo_print_ip(buf, sizeof(buf), &ptr->address); tomoyo_io_printf(head, "%s", buf); } tomoyo_print_number_union(head, &ptr->port); } else if (acl_type == TOMOYO_TYPE_UNIX_ACL) { struct tomoyo_unix_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_NETWORK_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "network unix "); tomoyo_set_string(head, tomoyo_proto_keyword [ptr->protocol]); tomoyo_set_space(head); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_socket_keyword[bit]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); } else if (acl_type == TOMOYO_TYPE_MOUNT_ACL) { struct tomoyo_mount_acl *ptr = container_of(acl, typeof(*ptr), head); tomoyo_set_group(head, "file mount"); tomoyo_print_name_union(head, &ptr->dev_name); tomoyo_print_name_union(head, &ptr->dir_name); tomoyo_print_name_union(head, &ptr->fs_type); tomoyo_print_number_union(head, &ptr->flags); } else if (acl_type == TOMOYO_TYPE_ENV_ACL) { struct tomoyo_env_acl *ptr = container_of(acl, typeof(*ptr), head); tomoyo_set_group(head, "misc env "); tomoyo_set_string(head, ptr->env->name); } if (acl->cond) { head->r.print_cond_part = true; head->r.cond_step = 0; if (!tomoyo_flush(head)) return false; print_cond_part: if (!tomoyo_print_condition(head, acl->cond)) return false; head->r.print_cond_part = false; } else { tomoyo_set_lf(head); } return true; } /** * tomoyo_read_domain2 - Read domain policy. * * @head: Pointer to "struct tomoyo_io_buffer". * @list: Pointer to "struct list_head". * * Caller holds tomoyo_read_lock(). * * Returns true on success, false otherwise. */ static bool tomoyo_read_domain2(struct tomoyo_io_buffer *head, struct list_head *list) { list_for_each_cookie(head->r.acl, list) { struct tomoyo_acl_info *ptr = list_entry(head->r.acl, typeof(*ptr), list); if (!tomoyo_print_entry(head, ptr)) return false; } head->r.acl = NULL; return true; } /** * tomoyo_read_domain - Read domain policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Caller holds tomoyo_read_lock(). */ static void tomoyo_read_domain(struct tomoyo_io_buffer *head) { if (head->r.eof) return; list_for_each_cookie(head->r.domain, &tomoyo_domain_list) { struct tomoyo_domain_info *domain = list_entry(head->r.domain, typeof(*domain), list); u8 i; switch (head->r.step) { case 0: if (domain->is_deleted && !head->r.print_this_domain_only) continue; /* Print domainname and flags. */ tomoyo_set_string(head, domain->domainname->name); tomoyo_set_lf(head); tomoyo_io_printf(head, "use_profile %u\n", domain->profile); for (i = 0; i < TOMOYO_MAX_DOMAIN_INFO_FLAGS; i++) if (domain->flags[i]) tomoyo_set_string(head, tomoyo_dif[i]); head->r.index = 0; head->r.step++; fallthrough; case 1: while (head->r.index < TOMOYO_MAX_ACL_GROUPS) { i = head->r.index++; if (!test_bit(i, domain->group)) continue; tomoyo_io_printf(head, "use_group %u\n", i); if (!tomoyo_flush(head)) return; } head->r.index = 0; head->r.step++; tomoyo_set_lf(head); fallthrough; case 2: if (!tomoyo_read_domain2(head, &domain->acl_info_list)) return; head->r.step++; if (!tomoyo_set_lf(head)) return; fallthrough; case 3: head->r.step = 0; if (head->r.print_this_domain_only) goto done; } } done: head->r.eof = true; } /** * tomoyo_write_pid: Specify PID to obtain domainname. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0. */ static int tomoyo_write_pid(struct tomoyo_io_buffer *head) { head->r.eof = false; return 0; } /** * tomoyo_read_pid - Get domainname of the specified PID. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns the domainname which the specified PID is in on success, * empty string otherwise. * The PID is specified by tomoyo_write_pid() so that the user can obtain * using read()/write() interface rather than sysctl() interface. */ static void tomoyo_read_pid(struct tomoyo_io_buffer *head) { char *buf = head->write_buf; bool global_pid = false; unsigned int pid; struct task_struct *p; struct tomoyo_domain_info *domain = NULL; /* Accessing write_buf is safe because head->io_sem is held. */ if (!buf) { head->r.eof = true; return; /* Do nothing if open(O_RDONLY). */ } if (head->r.w_pos || head->r.eof) return; head->r.eof = true; if (tomoyo_str_starts(&buf, "global-pid ")) global_pid = true; if (kstrtouint(buf, 10, &pid)) return; rcu_read_lock(); if (global_pid) p = find_task_by_pid_ns(pid, &init_pid_ns); else p = find_task_by_vpid(pid); if (p) domain = tomoyo_task(p)->domain_info; rcu_read_unlock(); if (!domain) return; tomoyo_io_printf(head, "%u %u ", pid, domain->profile); tomoyo_set_string(head, domain->domainname->name); } /* String table for domain transition control keywords. */ static const char *tomoyo_transition_type[TOMOYO_MAX_TRANSITION_TYPE] = { [TOMOYO_TRANSITION_CONTROL_NO_RESET] = "no_reset_domain ", [TOMOYO_TRANSITION_CONTROL_RESET] = "reset_domain ", [TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE] = "no_initialize_domain ", [TOMOYO_TRANSITION_CONTROL_INITIALIZE] = "initialize_domain ", [TOMOYO_TRANSITION_CONTROL_NO_KEEP] = "no_keep_domain ", [TOMOYO_TRANSITION_CONTROL_KEEP] = "keep_domain ", }; /* String table for grouping keywords. */ static const char *tomoyo_group_name[TOMOYO_MAX_GROUP] = { [TOMOYO_PATH_GROUP] = "path_group ", [TOMOYO_NUMBER_GROUP] = "number_group ", [TOMOYO_ADDRESS_GROUP] = "address_group ", }; /** * tomoyo_write_exception - Write exception policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_exception(struct tomoyo_io_buffer *head) { const bool is_delete = head->w.is_delete; struct tomoyo_acl_param param = { .ns = head->w.ns, .is_delete = is_delete, .data = head->write_buf, }; u8 i; if (tomoyo_str_starts(¶m.data, "aggregator ")) return tomoyo_write_aggregator(¶m); for (i = 0; i < TOMOYO_MAX_TRANSITION_TYPE; i++) if (tomoyo_str_starts(¶m.data, tomoyo_transition_type[i])) return tomoyo_write_transition_control(¶m, i); for (i = 0; i < TOMOYO_MAX_GROUP; i++) if (tomoyo_str_starts(¶m.data, tomoyo_group_name[i])) return tomoyo_write_group(¶m, i); if (tomoyo_str_starts(¶m.data, "acl_group ")) { unsigned int group; char *data; group = simple_strtoul(param.data, &data, 10); if (group < TOMOYO_MAX_ACL_GROUPS && *data++ == ' ') return tomoyo_write_domain2 (head->w.ns, &head->w.ns->acl_group[group], data, is_delete); } return -EINVAL; } /** * tomoyo_read_group - Read "struct tomoyo_path_group"/"struct tomoyo_number_group"/"struct tomoyo_address_group" list. * * @head: Pointer to "struct tomoyo_io_buffer". * @idx: Index number. * * Returns true on success, false otherwise. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_read_group(struct tomoyo_io_buffer *head, const int idx) { struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); struct list_head *list = &ns->group_list[idx]; list_for_each_cookie(head->r.group, list) { struct tomoyo_group *group = list_entry(head->r.group, typeof(*group), head.list); list_for_each_cookie(head->r.acl, &group->member_list) { struct tomoyo_acl_head *ptr = list_entry(head->r.acl, typeof(*ptr), list); if (ptr->is_deleted) continue; if (!tomoyo_flush(head)) return false; tomoyo_print_namespace(head); tomoyo_set_string(head, tomoyo_group_name[idx]); tomoyo_set_string(head, group->group_name->name); if (idx == TOMOYO_PATH_GROUP) { tomoyo_set_space(head); tomoyo_set_string(head, container_of (ptr, struct tomoyo_path_group, head)->member_name->name); } else if (idx == TOMOYO_NUMBER_GROUP) { tomoyo_print_number_union(head, &container_of (ptr, struct tomoyo_number_group, head)->number); } else if (idx == TOMOYO_ADDRESS_GROUP) { char buffer[128]; struct tomoyo_address_group *member = container_of(ptr, typeof(*member), head); tomoyo_print_ip(buffer, sizeof(buffer), &member->address); tomoyo_io_printf(head, " %s", buffer); } tomoyo_set_lf(head); } head->r.acl = NULL; } head->r.group = NULL; return true; } /** * tomoyo_read_policy - Read "struct tomoyo_..._entry" list. * * @head: Pointer to "struct tomoyo_io_buffer". * @idx: Index number. * * Returns true on success, false otherwise. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_read_policy(struct tomoyo_io_buffer *head, const int idx) { struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); struct list_head *list = &ns->policy_list[idx]; list_for_each_cookie(head->r.acl, list) { struct tomoyo_acl_head *acl = container_of(head->r.acl, typeof(*acl), list); if (acl->is_deleted) continue; if (!tomoyo_flush(head)) return false; switch (idx) { case TOMOYO_ID_TRANSITION_CONTROL: { struct tomoyo_transition_control *ptr = container_of(acl, typeof(*ptr), head); tomoyo_print_namespace(head); tomoyo_set_string(head, tomoyo_transition_type [ptr->type]); tomoyo_set_string(head, ptr->program ? ptr->program->name : "any"); tomoyo_set_string(head, " from "); tomoyo_set_string(head, ptr->domainname ? ptr->domainname->name : "any"); } break; case TOMOYO_ID_AGGREGATOR: { struct tomoyo_aggregator *ptr = container_of(acl, typeof(*ptr), head); tomoyo_print_namespace(head); tomoyo_set_string(head, "aggregator "); tomoyo_set_string(head, ptr->original_name->name); tomoyo_set_space(head); tomoyo_set_string(head, ptr->aggregated_name->name); } break; default: continue; } tomoyo_set_lf(head); } head->r.acl = NULL; return true; } /** * tomoyo_read_exception - Read exception policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Caller holds tomoyo_read_lock(). */ static void tomoyo_read_exception(struct tomoyo_io_buffer *head) { struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); if (head->r.eof) return; while (head->r.step < TOMOYO_MAX_POLICY && tomoyo_read_policy(head, head->r.step)) head->r.step++; if (head->r.step < TOMOYO_MAX_POLICY) return; while (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP && tomoyo_read_group(head, head->r.step - TOMOYO_MAX_POLICY)) head->r.step++; if (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP) return; while (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP + TOMOYO_MAX_ACL_GROUPS) { head->r.acl_group_index = head->r.step - TOMOYO_MAX_POLICY - TOMOYO_MAX_GROUP; if (!tomoyo_read_domain2(head, &ns->acl_group [head->r.acl_group_index])) return; head->r.step++; } head->r.eof = true; } /* Wait queue for kernel -> userspace notification. */ static DECLARE_WAIT_QUEUE_HEAD(tomoyo_query_wait); /* Wait queue for userspace -> kernel notification. */ static DECLARE_WAIT_QUEUE_HEAD(tomoyo_answer_wait); /* Structure for query. */ struct tomoyo_query { struct list_head list; struct tomoyo_domain_info *domain; char *query; size_t query_len; unsigned int serial; u8 timer; u8 answer; u8 retry; }; /* The list for "struct tomoyo_query". */ static LIST_HEAD(tomoyo_query_list); /* Lock for manipulating tomoyo_query_list. */ static DEFINE_SPINLOCK(tomoyo_query_list_lock); /* * Number of "struct file" referring /sys/kernel/security/tomoyo/query * interface. */ static atomic_t tomoyo_query_observers = ATOMIC_INIT(0); /** * tomoyo_truncate - Truncate a line. * * @str: String to truncate. * * Returns length of truncated @str. */ static int tomoyo_truncate(char *str) { char *start = str; while (*(unsigned char *) str > (unsigned char) ' ') str++; *str = '\0'; return strlen(start) + 1; } /** * tomoyo_add_entry - Add an ACL to current thread's domain. Used by learning mode. * * @domain: Pointer to "struct tomoyo_domain_info". * @header: Lines containing ACL. * * Returns nothing. */ static void tomoyo_add_entry(struct tomoyo_domain_info *domain, char *header) { char *buffer; char *realpath = NULL; char *argv0 = NULL; char *symlink = NULL; char *cp = strchr(header, '\n'); int len; if (!cp) return; cp = strchr(cp + 1, '\n'); if (!cp) return; *cp++ = '\0'; len = strlen(cp) + 1; /* strstr() will return NULL if ordering is wrong. */ if (*cp == 'f') { argv0 = strstr(header, " argv[]={ \""); if (argv0) { argv0 += 10; len += tomoyo_truncate(argv0) + 14; } realpath = strstr(header, " exec={ realpath=\""); if (realpath) { realpath += 8; len += tomoyo_truncate(realpath) + 6; } symlink = strstr(header, " symlink.target=\""); if (symlink) len += tomoyo_truncate(symlink + 1) + 1; } buffer = kmalloc(len, GFP_NOFS); if (!buffer) return; snprintf(buffer, len - 1, "%s", cp); if (realpath) tomoyo_addprintf(buffer, len, " exec.%s", realpath); if (argv0) tomoyo_addprintf(buffer, len, " exec.argv[0]=%s", argv0); if (symlink) tomoyo_addprintf(buffer, len, "%s", symlink); tomoyo_normalize_line(buffer); if (!tomoyo_write_domain2(domain->ns, &domain->acl_info_list, buffer, false)) tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); kfree(buffer); } /** * tomoyo_supervisor - Ask for the supervisor's decision. * * @r: Pointer to "struct tomoyo_request_info". * @fmt: The printf()'s format string, followed by parameters. * * Returns 0 if the supervisor decided to permit the access request which * violated the policy in enforcing mode, TOMOYO_RETRY_REQUEST if the * supervisor decided to retry the access request which violated the policy in * enforcing mode, 0 if it is not in enforcing mode, -EPERM otherwise. */ int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...) { va_list args; int error; int len; static unsigned int tomoyo_serial; struct tomoyo_query entry = { }; bool quota_exceeded = false; va_start(args, fmt); len = vsnprintf(NULL, 0, fmt, args) + 1; va_end(args); /* Write /sys/kernel/security/tomoyo/audit. */ va_start(args, fmt); tomoyo_write_log2(r, len, fmt, args); va_end(args); /* Nothing more to do if granted. */ if (r->granted) return 0; if (r->mode) tomoyo_update_stat(r->mode); switch (r->mode) { case TOMOYO_CONFIG_ENFORCING: error = -EPERM; if (atomic_read(&tomoyo_query_observers)) break; goto out; case TOMOYO_CONFIG_LEARNING: error = 0; /* Check max_learning_entry parameter. */ if (tomoyo_domain_quota_is_ok(r)) break; fallthrough; default: return 0; } /* Get message. */ va_start(args, fmt); entry.query = tomoyo_init_log(r, len, fmt, args); va_end(args); if (!entry.query) goto out; entry.query_len = strlen(entry.query) + 1; if (!error) { tomoyo_add_entry(r->domain, entry.query); goto out; } len = kmalloc_size_roundup(entry.query_len); entry.domain = r->domain; spin_lock(&tomoyo_query_list_lock); if (tomoyo_memory_quota[TOMOYO_MEMORY_QUERY] && tomoyo_memory_used[TOMOYO_MEMORY_QUERY] + len >= tomoyo_memory_quota[TOMOYO_MEMORY_QUERY]) { quota_exceeded = true; } else { entry.serial = tomoyo_serial++; entry.retry = r->retry; tomoyo_memory_used[TOMOYO_MEMORY_QUERY] += len; list_add_tail(&entry.list, &tomoyo_query_list); } spin_unlock(&tomoyo_query_list_lock); if (quota_exceeded) goto out; /* Give 10 seconds for supervisor's opinion. */ while (entry.timer < 10) { wake_up_all(&tomoyo_query_wait); if (wait_event_interruptible_timeout (tomoyo_answer_wait, entry.answer || !atomic_read(&tomoyo_query_observers), HZ)) break; entry.timer++; } spin_lock(&tomoyo_query_list_lock); list_del(&entry.list); tomoyo_memory_used[TOMOYO_MEMORY_QUERY] -= len; spin_unlock(&tomoyo_query_list_lock); switch (entry.answer) { case 3: /* Asked to retry by administrator. */ error = TOMOYO_RETRY_REQUEST; r->retry++; break; case 1: /* Granted by administrator. */ error = 0; break; default: /* Timed out or rejected by administrator. */ break; } out: kfree(entry.query); return error; } /** * tomoyo_find_domain_by_qid - Get domain by query id. * * @serial: Query ID assigned by tomoyo_supervisor(). * * Returns pointer to "struct tomoyo_domain_info" if found, NULL otherwise. */ static struct tomoyo_domain_info *tomoyo_find_domain_by_qid (unsigned int serial) { struct tomoyo_query *ptr; struct tomoyo_domain_info *domain = NULL; spin_lock(&tomoyo_query_list_lock); list_for_each_entry(ptr, &tomoyo_query_list, list) { if (ptr->serial != serial) continue; domain = ptr->domain; break; } spin_unlock(&tomoyo_query_list_lock); return domain; } /** * tomoyo_poll_query - poll() for /sys/kernel/security/tomoyo/query. * * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". * * Returns EPOLLIN | EPOLLRDNORM when ready to read, 0 otherwise. * * Waits for access requests which violated policy in enforcing mode. */ static __poll_t tomoyo_poll_query(struct file *file, poll_table *wait) { if (!list_empty(&tomoyo_query_list)) return EPOLLIN | EPOLLRDNORM; poll_wait(file, &tomoyo_query_wait, wait); if (!list_empty(&tomoyo_query_list)) return EPOLLIN | EPOLLRDNORM; return 0; } /** * tomoyo_read_query - Read access requests which violated policy in enforcing mode. * * @head: Pointer to "struct tomoyo_io_buffer". */ static void tomoyo_read_query(struct tomoyo_io_buffer *head) { struct list_head *tmp; unsigned int pos = 0; size_t len = 0; char *buf; if (head->r.w_pos) return; kfree(head->read_buf); head->read_buf = NULL; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); if (pos++ != head->r.query_index) continue; len = ptr->query_len; break; } spin_unlock(&tomoyo_query_list_lock); if (!len) { head->r.query_index = 0; return; } buf = kzalloc(len + 32, GFP_NOFS); if (!buf) return; pos = 0; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); if (pos++ != head->r.query_index) continue; /* * Some query can be skipped because tomoyo_query_list * can change, but I don't care. */ if (len == ptr->query_len) snprintf(buf, len + 31, "Q%u-%hu\n%s", ptr->serial, ptr->retry, ptr->query); break; } spin_unlock(&tomoyo_query_list_lock); if (buf[0]) { head->read_buf = buf; head->r.w[head->r.w_pos++] = buf; head->r.query_index++; } else { kfree(buf); } } /** * tomoyo_write_answer - Write the supervisor's decision. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, -EINVAL otherwise. */ static int tomoyo_write_answer(struct tomoyo_io_buffer *head) { char *data = head->write_buf; struct list_head *tmp; unsigned int serial; unsigned int answer; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); ptr->timer = 0; } spin_unlock(&tomoyo_query_list_lock); if (sscanf(data, "A%u=%u", &serial, &answer) != 2) return -EINVAL; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); if (ptr->serial != serial) continue; ptr->answer = answer; /* Remove from tomoyo_query_list. */ if (ptr->answer) list_del_init(&ptr->list); break; } spin_unlock(&tomoyo_query_list_lock); return 0; } /** * tomoyo_read_version: Get version. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns version information. */ static void tomoyo_read_version(struct tomoyo_io_buffer *head) { if (!head->r.eof) { tomoyo_io_printf(head, "2.6.0"); head->r.eof = true; } } /* String table for /sys/kernel/security/tomoyo/stat interface. */ static const char * const tomoyo_policy_headers[TOMOYO_MAX_POLICY_STAT] = { [TOMOYO_STAT_POLICY_UPDATES] = "update:", [TOMOYO_STAT_POLICY_LEARNING] = "violation in learning mode:", [TOMOYO_STAT_POLICY_PERMISSIVE] = "violation in permissive mode:", [TOMOYO_STAT_POLICY_ENFORCING] = "violation in enforcing mode:", }; /* String table for /sys/kernel/security/tomoyo/stat interface. */ static const char * const tomoyo_memory_headers[TOMOYO_MAX_MEMORY_STAT] = { [TOMOYO_MEMORY_POLICY] = "policy:", [TOMOYO_MEMORY_AUDIT] = "audit log:", [TOMOYO_MEMORY_QUERY] = "query message:", }; /* Counter for number of updates. */ static atomic_t tomoyo_stat_updated[TOMOYO_MAX_POLICY_STAT]; /* Timestamp counter for last updated. */ static time64_t tomoyo_stat_modified[TOMOYO_MAX_POLICY_STAT]; /** * tomoyo_update_stat - Update statistic counters. * * @index: Index for policy type. * * Returns nothing. */ void tomoyo_update_stat(const u8 index) { atomic_inc(&tomoyo_stat_updated[index]); tomoyo_stat_modified[index] = ktime_get_real_seconds(); } /** * tomoyo_read_stat - Read statistic data. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_read_stat(struct tomoyo_io_buffer *head) { u8 i; unsigned int total = 0; if (head->r.eof) return; for (i = 0; i < TOMOYO_MAX_POLICY_STAT; i++) { tomoyo_io_printf(head, "Policy %-30s %10u", tomoyo_policy_headers[i], atomic_read(&tomoyo_stat_updated[i])); if (tomoyo_stat_modified[i]) { struct tomoyo_time stamp; tomoyo_convert_time(tomoyo_stat_modified[i], &stamp); tomoyo_io_printf(head, " (Last: %04u/%02u/%02u %02u:%02u:%02u)", stamp.year, stamp.month, stamp.day, stamp.hour, stamp.min, stamp.sec); } tomoyo_set_lf(head); } for (i = 0; i < TOMOYO_MAX_MEMORY_STAT; i++) { unsigned int used = tomoyo_memory_used[i]; total += used; tomoyo_io_printf(head, "Memory used by %-22s %10u", tomoyo_memory_headers[i], used); used = tomoyo_memory_quota[i]; if (used) tomoyo_io_printf(head, " (Quota: %10u)", used); tomoyo_set_lf(head); } tomoyo_io_printf(head, "Total memory used: %10u\n", total); head->r.eof = true; } /** * tomoyo_write_stat - Set memory quota. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0. */ static int tomoyo_write_stat(struct tomoyo_io_buffer *head) { char *data = head->write_buf; u8 i; if (tomoyo_str_starts(&data, "Memory used by ")) for (i = 0; i < TOMOYO_MAX_MEMORY_STAT; i++) if (tomoyo_str_starts(&data, tomoyo_memory_headers[i])) sscanf(data, "%u", &tomoyo_memory_quota[i]); return 0; } /** * tomoyo_open_control - open() for /sys/kernel/security/tomoyo/ interface. * * @type: Type of interface. * @file: Pointer to "struct file". * * Returns 0 on success, negative value otherwise. */ int tomoyo_open_control(const u8 type, struct file *file) { struct tomoyo_io_buffer *head = kzalloc(sizeof(*head), GFP_NOFS); if (!head) return -ENOMEM; mutex_init(&head->io_sem); head->type = type; switch (type) { case TOMOYO_DOMAINPOLICY: /* /sys/kernel/security/tomoyo/domain_policy */ head->write = tomoyo_write_domain; head->read = tomoyo_read_domain; break; case TOMOYO_EXCEPTIONPOLICY: /* /sys/kernel/security/tomoyo/exception_policy */ head->write = tomoyo_write_exception; head->read = tomoyo_read_exception; break; case TOMOYO_AUDIT: /* /sys/kernel/security/tomoyo/audit */ head->poll = tomoyo_poll_log; head->read = tomoyo_read_log; break; case TOMOYO_PROCESS_STATUS: /* /sys/kernel/security/tomoyo/.process_status */ head->write = tomoyo_write_pid; head->read = tomoyo_read_pid; break; case TOMOYO_VERSION: /* /sys/kernel/security/tomoyo/version */ head->read = tomoyo_read_version; head->readbuf_size = 128; break; case TOMOYO_STAT: /* /sys/kernel/security/tomoyo/stat */ head->write = tomoyo_write_stat; head->read = tomoyo_read_stat; head->readbuf_size = 1024; break; case TOMOYO_PROFILE: /* /sys/kernel/security/tomoyo/profile */ head->write = tomoyo_write_profile; head->read = tomoyo_read_profile; break; case TOMOYO_QUERY: /* /sys/kernel/security/tomoyo/query */ head->poll = tomoyo_poll_query; head->write = tomoyo_write_answer; head->read = tomoyo_read_query; break; case TOMOYO_MANAGER: /* /sys/kernel/security/tomoyo/manager */ head->write = tomoyo_write_manager; head->read = tomoyo_read_manager; break; } if (!(file->f_mode & FMODE_READ)) { /* * No need to allocate read_buf since it is not opened * for reading. */ head->read = NULL; head->poll = NULL; } else if (!head->poll) { /* Don't allocate read_buf for poll() access. */ if (!head->readbuf_size) head->readbuf_size = 4096 * 2; head->read_buf = kzalloc(head->readbuf_size, GFP_NOFS); if (!head->read_buf) { kfree(head); return -ENOMEM; } } if (!(file->f_mode & FMODE_WRITE)) { /* * No need to allocate write_buf since it is not opened * for writing. */ head->write = NULL; } else if (head->write) { head->writebuf_size = 4096 * 2; head->write_buf = kzalloc(head->writebuf_size, GFP_NOFS); if (!head->write_buf) { kfree(head->read_buf); kfree(head); return -ENOMEM; } } /* * If the file is /sys/kernel/security/tomoyo/query , increment the * observer counter. * The obserber counter is used by tomoyo_supervisor() to see if * there is some process monitoring /sys/kernel/security/tomoyo/query. */ if (type == TOMOYO_QUERY) atomic_inc(&tomoyo_query_observers); file->private_data = head; tomoyo_notify_gc(head, true); return 0; } /** * tomoyo_poll_control - poll() for /sys/kernel/security/tomoyo/ interface. * * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". Maybe NULL. * * Returns EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM if ready to read/write, * EPOLLOUT | EPOLLWRNORM otherwise. */ __poll_t tomoyo_poll_control(struct file *file, poll_table *wait) { struct tomoyo_io_buffer *head = file->private_data; if (head->poll) return head->poll(file, wait) | EPOLLOUT | EPOLLWRNORM; return EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM; } /** * tomoyo_set_namespace_cursor - Set namespace to read. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static inline void tomoyo_set_namespace_cursor(struct tomoyo_io_buffer *head) { struct list_head *ns; if (head->type != TOMOYO_EXCEPTIONPOLICY && head->type != TOMOYO_PROFILE) return; /* * If this is the first read, or reading previous namespace finished * and has more namespaces to read, update the namespace cursor. */ ns = head->r.ns; if (!ns || (head->r.eof && ns->next != &tomoyo_namespace_list)) { /* Clearing is OK because tomoyo_flush() returned true. */ memset(&head->r, 0, sizeof(head->r)); head->r.ns = ns ? ns->next : tomoyo_namespace_list.next; } } /** * tomoyo_has_more_namespace - Check for unread namespaces. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns true if we have more entries to print, false otherwise. */ static inline bool tomoyo_has_more_namespace(struct tomoyo_io_buffer *head) { return (head->type == TOMOYO_EXCEPTIONPOLICY || head->type == TOMOYO_PROFILE) && head->r.eof && head->r.ns->next != &tomoyo_namespace_list; } /** * tomoyo_read_control - read() for /sys/kernel/security/tomoyo/ interface. * * @head: Pointer to "struct tomoyo_io_buffer". * @buffer: Pointer to buffer to write to. * @buffer_len: Size of @buffer. * * Returns bytes read on success, negative value otherwise. */ ssize_t tomoyo_read_control(struct tomoyo_io_buffer *head, char __user *buffer, const int buffer_len) { int len; int idx; if (!head->read) return -EINVAL; if (mutex_lock_interruptible(&head->io_sem)) return -EINTR; head->read_user_buf = buffer; head->read_user_buf_avail = buffer_len; idx = tomoyo_read_lock(); if (tomoyo_flush(head)) /* Call the policy handler. */ do { tomoyo_set_namespace_cursor(head); head->read(head); } while (tomoyo_flush(head) && tomoyo_has_more_namespace(head)); tomoyo_read_unlock(idx); len = head->read_user_buf - buffer; mutex_unlock(&head->io_sem); return len; } /** * tomoyo_parse_policy - Parse a policy line. * * @head: Pointer to "struct tomoyo_io_buffer". * @line: Line to parse. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_parse_policy(struct tomoyo_io_buffer *head, char *line) { /* Delete request? */ head->w.is_delete = !strncmp(line, "delete ", 7); if (head->w.is_delete) memmove(line, line + 7, strlen(line + 7) + 1); /* Selecting namespace to update. */ if (head->type == TOMOYO_EXCEPTIONPOLICY || head->type == TOMOYO_PROFILE) { if (*line == '<') { char *cp = strchr(line, ' '); if (cp) { *cp++ = '\0'; head->w.ns = tomoyo_assign_namespace(line); memmove(line, cp, strlen(cp) + 1); } else head->w.ns = NULL; } else head->w.ns = &tomoyo_kernel_namespace; /* Don't allow updating if namespace is invalid. */ if (!head->w.ns) return -ENOENT; } /* Do the update. */ return head->write(head); } /** * tomoyo_write_control - write() for /sys/kernel/security/tomoyo/ interface. * * @head: Pointer to "struct tomoyo_io_buffer". * @buffer: Pointer to buffer to read from. * @buffer_len: Size of @buffer. * * Returns @buffer_len on success, negative value otherwise. */ ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, const char __user *buffer, const int buffer_len) { int error = buffer_len; size_t avail_len = buffer_len; char *cp0; int idx; if (!head->write) return -EINVAL; if (mutex_lock_interruptible(&head->io_sem)) return -EINTR; cp0 = head->write_buf; head->read_user_buf_avail = 0; idx = tomoyo_read_lock(); /* Read a line and dispatch it to the policy handler. */ while (avail_len > 0) { char c; if (head->w.avail >= head->writebuf_size - 1) { const int len = head->writebuf_size * 2; char *cp = kzalloc(len, GFP_NOFS); if (!cp) { error = -ENOMEM; break; } memmove(cp, cp0, head->w.avail); kfree(cp0); head->write_buf = cp; cp0 = cp; head->writebuf_size = len; } if (get_user(c, buffer)) { error = -EFAULT; break; } buffer++; avail_len--; cp0[head->w.avail++] = c; if (c != '\n') continue; cp0[head->w.avail - 1] = '\0'; head->w.avail = 0; tomoyo_normalize_line(cp0); if (!strcmp(cp0, "reset")) { head->w.ns = &tomoyo_kernel_namespace; head->w.domain = NULL; memset(&head->r, 0, sizeof(head->r)); continue; } /* Don't allow updating policies by non manager programs. */ switch (head->type) { case TOMOYO_PROCESS_STATUS: /* This does not write anything. */ break; case TOMOYO_DOMAINPOLICY: if (tomoyo_select_domain(head, cp0)) continue; fallthrough; case TOMOYO_EXCEPTIONPOLICY: if (!strcmp(cp0, "select transition_only")) { head->r.print_transition_related_only = true; continue; } fallthrough; default: if (!tomoyo_manager()) { error = -EPERM; goto out; } } switch (tomoyo_parse_policy(head, cp0)) { case -EPERM: error = -EPERM; goto out; case 0: switch (head->type) { case TOMOYO_DOMAINPOLICY: case TOMOYO_EXCEPTIONPOLICY: case TOMOYO_STAT: case TOMOYO_PROFILE: case TOMOYO_MANAGER: tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); break; default: break; } break; } } out: tomoyo_read_unlock(idx); mutex_unlock(&head->io_sem); return error; } /** * tomoyo_close_control - close() for /sys/kernel/security/tomoyo/ interface. * * @head: Pointer to "struct tomoyo_io_buffer". */ void tomoyo_close_control(struct tomoyo_io_buffer *head) { /* * If the file is /sys/kernel/security/tomoyo/query , decrement the * observer counter. */ if (head->type == TOMOYO_QUERY && atomic_dec_and_test(&tomoyo_query_observers)) wake_up_all(&tomoyo_answer_wait); tomoyo_notify_gc(head, false); } /** * tomoyo_check_profile - Check all profiles currently assigned to domains are defined. */ void tomoyo_check_profile(void) { struct tomoyo_domain_info *domain; const int idx = tomoyo_read_lock(); tomoyo_policy_loaded = true; pr_info("TOMOYO: 2.6.0\n"); list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, srcu_read_lock_held(&tomoyo_ss)) { const u8 profile = domain->profile; struct tomoyo_policy_namespace *ns = domain->ns; if (ns->profile_version == 20110903) { pr_info_once("Converting profile version from %u to %u.\n", 20110903, 20150505); ns->profile_version = 20150505; } if (ns->profile_version != 20150505) pr_err("Profile version %u is not supported.\n", ns->profile_version); else if (!ns->profile_ptr[profile]) pr_err("Profile %u (used by '%s') is not defined.\n", profile, domain->domainname->name); else continue; pr_err("Userland tools for TOMOYO 2.6 must be installed and policy must be initialized.\n"); pr_err("Please see https://tomoyo.sourceforge.net/2.6/ for more information.\n"); panic("STOP!"); } tomoyo_read_unlock(idx); pr_info("Mandatory Access Control activated.\n"); } /** * tomoyo_load_builtin_policy - Load built-in policy. * * Returns nothing. */ void __init tomoyo_load_builtin_policy(void) { #ifdef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING static char tomoyo_builtin_profile[] __initdata = "PROFILE_VERSION=20150505\n" "0-CONFIG={ mode=learning grant_log=no reject_log=yes }\n"; static char tomoyo_builtin_exception_policy[] __initdata = "aggregator proc:/self/exe /proc/self/exe\n"; static char tomoyo_builtin_domain_policy[] __initdata = ""; static char tomoyo_builtin_manager[] __initdata = ""; static char tomoyo_builtin_stat[] __initdata = ""; #else /* * This include file is manually created and contains built-in policy * named "tomoyo_builtin_profile", "tomoyo_builtin_exception_policy", * "tomoyo_builtin_domain_policy", "tomoyo_builtin_manager", * "tomoyo_builtin_stat" in the form of "static char [] __initdata". */ #include "builtin-policy.h" #endif u8 i; const int idx = tomoyo_read_lock(); for (i = 0; i < 5; i++) { struct tomoyo_io_buffer head = { }; char *start = ""; switch (i) { case 0: start = tomoyo_builtin_profile; head.type = TOMOYO_PROFILE; head.write = tomoyo_write_profile; break; case 1: start = tomoyo_builtin_exception_policy; head.type = TOMOYO_EXCEPTIONPOLICY; head.write = tomoyo_write_exception; break; case 2: start = tomoyo_builtin_domain_policy; head.type = TOMOYO_DOMAINPOLICY; head.write = tomoyo_write_domain; break; case 3: start = tomoyo_builtin_manager; head.type = TOMOYO_MANAGER; head.write = tomoyo_write_manager; break; case 4: start = tomoyo_builtin_stat; head.type = TOMOYO_STAT; head.write = tomoyo_write_stat; break; } while (1) { char *end = strchr(start, '\n'); if (!end) break; *end = '\0'; tomoyo_normalize_line(start); head.write_buf = start; tomoyo_parse_policy(&head, start); start = end + 1; } } tomoyo_read_unlock(idx); #ifdef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER tomoyo_check_profile(); #endif } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 2 3 3 1 1 1 1 1 3 3 3 2 2 2 3 1 3 1 3 3 3 3 1 1 1 1 1 1 1 1 1 3 195 2 2 2 2 2 2 1 2 2 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * This file contains device methods for creating, using and destroying * virtual HSR or PRP devices. */ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> #include "hsr_device.h" #include "hsr_slave.h" #include "hsr_framereg.h" #include "hsr_main.h" #include "hsr_forward.h" static bool is_admin_up(struct net_device *dev) { return dev && (dev->flags & IFF_UP); } static bool is_slave_up(struct net_device *dev) { return dev && is_admin_up(dev) && netif_oper_up(dev); } static void hsr_set_operstate(struct hsr_port *master, bool has_carrier) { struct net_device *dev = master->dev; if (!is_admin_up(dev)) { netdev_set_operstate(dev, IF_OPER_DOWN); return; } if (has_carrier) netdev_set_operstate(dev, IF_OPER_UP); else netdev_set_operstate(dev, IF_OPER_LOWERLAYERDOWN); } static bool hsr_check_carrier(struct hsr_port *master) { struct hsr_port *port; ASSERT_RTNL(); hsr_for_each_port(master->hsr, port) { if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) { netif_carrier_on(master->dev); return true; } } netif_carrier_off(master->dev); return false; } static void hsr_check_announce(struct net_device *hsr_dev) { struct hsr_priv *hsr; hsr = netdev_priv(hsr_dev); if (netif_running(hsr_dev) && netif_oper_up(hsr_dev)) { /* Enable announce timer and start sending supervisory frames */ if (!timer_pending(&hsr->announce_timer)) { hsr->announce_count = 0; mod_timer(&hsr->announce_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); } } else { /* Deactivate the announce timer */ timer_delete(&hsr->announce_timer); } } void hsr_check_carrier_and_operstate(struct hsr_priv *hsr) { struct hsr_port *master; bool has_carrier; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); /* netif_stacked_transfer_operstate() cannot be used here since * it doesn't set IF_OPER_LOWERLAYERDOWN (?) */ has_carrier = hsr_check_carrier(master); hsr_set_operstate(master, has_carrier); hsr_check_announce(master->dev); } int hsr_get_max_mtu(struct hsr_priv *hsr) { unsigned int mtu_max; struct hsr_port *port; mtu_max = ETH_DATA_LEN; hsr_for_each_port(hsr, port) if (port->type != HSR_PT_MASTER) mtu_max = min(port->dev->mtu, mtu_max); if (mtu_max < HSR_HLEN) return 0; return mtu_max - HSR_HLEN; } static int hsr_dev_change_mtu(struct net_device *dev, int new_mtu) { struct hsr_priv *hsr; hsr = netdev_priv(dev); if (new_mtu > hsr_get_max_mtu(hsr)) { netdev_info(dev, "A HSR master's MTU cannot be greater than the smallest MTU of its slaves minus the HSR Tag length (%d octets).\n", HSR_HLEN); return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int hsr_dev_open(struct net_device *dev) { struct hsr_priv *hsr; struct hsr_port *port; const char *designation = NULL; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: designation = "Slave A"; break; case HSR_PT_SLAVE_B: designation = "Slave B"; break; case HSR_PT_INTERLINK: designation = "Interlink"; break; default: designation = "Unknown"; } if (!is_slave_up(port->dev)) netdev_warn(dev, "%s (%s) is not up; please bring it up to get a fully working HSR network\n", designation, port->dev->name); } if (!designation) netdev_warn(dev, "No slave devices configured\n"); return 0; } static int hsr_dev_close(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_uc_unsync(port->dev, dev); dev_mc_unsync(port->dev, dev); break; default: break; } } return 0; } static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr, netdev_features_t features) { netdev_features_t mask; struct hsr_port *port; mask = features; /* Mask out all features that, if supported by one device, should be * enabled for all devices (see NETIF_F_ONE_FOR_ALL). * * Anything that's off in mask will not be enabled - so only things * that were in features originally, and also is in NETIF_F_ONE_FOR_ALL, * may become enabled. */ features &= ~NETIF_F_ONE_FOR_ALL; hsr_for_each_port(hsr, port) features = netdev_increment_features(features, port->dev->features, mask); return features; } static netdev_features_t hsr_fix_features(struct net_device *dev, netdev_features_t features) { struct hsr_priv *hsr = netdev_priv(dev); return hsr_features_recompute(hsr, features); } static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct hsr_priv *hsr = netdev_priv(dev); struct hsr_port *master; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (master) { skb->dev = master->dev; skb_reset_mac_header(skb); skb_reset_mac_len(skb); spin_lock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } else { dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); } return NETDEV_TX_OK; } static const struct header_ops hsr_header_ops = { .create = eth_header, .parse = eth_header_parse, }; static struct sk_buff *hsr_init_skb(struct hsr_port *master) { struct hsr_priv *hsr = master->hsr; struct sk_buff *skb; int hlen, tlen; hlen = LL_RESERVED_SPACE(master->dev); tlen = master->dev->needed_tailroom; /* skb size is same for PRP/HSR frames, only difference * being, for PRP it is a trailer and for HSR it is a * header */ skb = dev_alloc_skb(sizeof(struct hsr_sup_tag) + sizeof(struct hsr_sup_payload) + hlen + tlen); if (!skb) return skb; skb_reserve(skb, hlen); skb->dev = master->dev; skb->priority = TC_PRIO_CONTROL; if (dev_hard_header(skb, skb->dev, ETH_P_PRP, hsr->sup_multicast_addr, skb->dev->dev_addr, skb->len) <= 0) goto out; skb_reset_mac_header(skb); skb_reset_mac_len(skb); skb_reset_network_header(skb); skb_reset_transport_header(skb); return skb; out: kfree_skb(skb); return NULL; } static void send_hsr_supervision_frame(struct hsr_port *master, unsigned long *interval) { struct hsr_priv *hsr = master->hsr; __u8 type = HSR_TLV_LIFE_CHECK; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tlv *hsr_stlv; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); if (hsr->announce_count < 3 && hsr->prot_version == 0) { type = HSR_TLV_ANNOUNCE; *interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); hsr->announce_count++; } skb = hsr_init_skb(master); if (!skb) { netdev_warn_once(master->dev, "HSR: Could not send supervision frame\n"); return; } hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); if (hsr->prot_version > 0) { hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; } else { hsr_stag->sequence_nr = htons(hsr->sequence_nr); hsr->sequence_nr++; } hsr_stag->tlv.HSR_TLV_type = type; /* TODO: Why 12 in HSRv0? */ hsr_stag->tlv.HSR_TLV_length = hsr->prot_version ? sizeof(struct hsr_sup_payload) : 12; /* Payload: MacAddressA */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); if (hsr->redbox) { hsr_stlv = skb_put(skb, sizeof(struct hsr_sup_tlv)); hsr_stlv->HSR_TLV_type = PRP_TLV_REDBOX_MAC; hsr_stlv->HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressRedBox */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, hsr->macaddress_redbox); } if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); return; } static void send_prp_supervision_frame(struct hsr_port *master, unsigned long *interval) { struct hsr_priv *hsr = master->hsr; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; skb = hsr_init_skb(master); if (!skb) { netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, (hsr->prot_version ? 1 : 0)); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; hsr_stag->tlv.HSR_TLV_type = PRP_TLV_LIFE_CHECK_DD; hsr_stag->tlv.HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressA */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } /* Announce (supervision frame) timer function */ static void hsr_announce(struct timer_list *t) { struct hsr_priv *hsr; struct hsr_port *master; unsigned long interval; hsr = from_timer(hsr, t, announce_timer); rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); hsr->proto_ops->send_sv_frame(master, &interval); if (is_admin_up(master->dev)) mod_timer(&hsr->announce_timer, jiffies + interval); rcu_read_unlock(); } void hsr_del_ports(struct hsr_priv *hsr) { struct hsr_port *port; port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (port) hsr_del_port(port); } static void hsr_set_rx_mode(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_mc_sync_multiple(port->dev, dev); dev_uc_sync_multiple(port->dev, dev); break; default: break; } } } static void hsr_change_rx_flags(struct net_device *dev, int change) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: if (change & IFF_ALLMULTI) dev_set_allmulti(port->dev, dev->flags & IFF_ALLMULTI ? 1 : -1); break; default: break; } } } static const struct net_device_ops hsr_device_ops = { .ndo_change_mtu = hsr_dev_change_mtu, .ndo_open = hsr_dev_open, .ndo_stop = hsr_dev_close, .ndo_start_xmit = hsr_dev_xmit, .ndo_change_rx_flags = hsr_change_rx_flags, .ndo_fix_features = hsr_fix_features, .ndo_set_rx_mode = hsr_set_rx_mode, }; static const struct device_type hsr_type = { .name = "hsr", }; static struct hsr_proto_ops hsr_ops = { .send_sv_frame = send_hsr_supervision_frame, .create_tagged_frame = hsr_create_tagged_frame, .get_untagged_frame = hsr_get_untagged_frame, .drop_frame = hsr_drop_frame, .fill_frame_info = hsr_fill_frame_info, .invalid_dan_ingress_frame = hsr_invalid_dan_ingress_frame, }; static struct hsr_proto_ops prp_ops = { .send_sv_frame = send_prp_supervision_frame, .create_tagged_frame = prp_create_tagged_frame, .get_untagged_frame = prp_get_untagged_frame, .drop_frame = prp_drop_frame, .fill_frame_info = prp_fill_frame_info, .handle_san_frame = prp_handle_san_frame, .update_san_info = prp_update_san_info, }; void hsr_dev_setup(struct net_device *dev) { eth_hw_addr_random(dev); ether_setup(dev); dev->min_mtu = 0; dev->header_ops = &hsr_header_ops; dev->netdev_ops = &hsr_device_ops; SET_NETDEV_DEVTYPE(dev, &hsr_type); dev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; dev->needs_free_netdev = true; dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX; dev->features = dev->hw_features; /* Prevent recursive tx locking */ dev->features |= NETIF_F_LLTX; /* VLAN on top of HSR needs testing and probably some work on * hsr_header_create() etc. */ dev->features |= NETIF_F_VLAN_CHALLENGED; /* Not sure about this. Taken from bridge code. netdev_features.h says * it means "Does not change network namespaces". */ dev->features |= NETIF_F_NETNS_LOCAL; } /* Return true if dev is a HSR master; return false otherwise. */ bool is_hsr_master(struct net_device *dev) { return (dev->netdev_ops->ndo_start_xmit == hsr_dev_xmit); } EXPORT_SYMBOL(is_hsr_master); /* Default multicast address for HSR Supervision frames */ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x15, 0x4e, 0x00, 0x01, 0x00 }; int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], struct net_device *interlink, unsigned char multicast_spec, u8 protocol_version, struct netlink_ext_ack *extack) { bool unregister = false; struct hsr_priv *hsr; int res; hsr = netdev_priv(hsr_dev); INIT_LIST_HEAD(&hsr->ports); INIT_LIST_HEAD(&hsr->node_db); INIT_LIST_HEAD(&hsr->proxy_node_db); spin_lock_init(&hsr->list_lock); eth_hw_addr_set(hsr_dev, slave[0]->dev_addr); /* initialize protocol specific functions */ if (protocol_version == PRP_V1) { /* For PRP, lan_id has most significant 3 bits holding * the net_id of PRP_LAN_ID */ hsr->net_id = PRP_LAN_ID << 1; hsr->proto_ops = &prp_ops; } else { hsr->proto_ops = &hsr_ops; } /* Make sure we recognize frames from ourselves in hsr_rcv() */ res = hsr_create_self_node(hsr, hsr_dev->dev_addr, slave[1]->dev_addr); if (res < 0) return res; spin_lock_init(&hsr->seqnr_lock); /* Overflow soon to find bugs easier: */ hsr->sequence_nr = HSR_SEQNR_START; hsr->sup_sequence_nr = HSR_SUP_SEQNR_START; hsr->interlink_sequence_nr = HSR_SEQNR_START; timer_setup(&hsr->announce_timer, hsr_announce, 0); timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0); timer_setup(&hsr->prune_proxy_timer, hsr_prune_proxy_nodes, 0); ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr); hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; hsr->prot_version = protocol_version; /* Make sure the 1st call to netif_carrier_on() gets through */ netif_carrier_off(hsr_dev); res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER, extack); if (res) goto err_add_master; /* HSR forwarding offload supported in lower device? */ if ((slave[0]->features & NETIF_F_HW_HSR_FWD) && (slave[1]->features & NETIF_F_HW_HSR_FWD)) hsr->fwd_offloaded = true; res = register_netdevice(hsr_dev); if (res) goto err_unregister; unregister = true; res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A, extack); if (res) goto err_unregister; res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B, extack); if (res) goto err_unregister; if (interlink) { res = hsr_add_port(hsr, interlink, HSR_PT_INTERLINK, extack); if (res) goto err_unregister; hsr->redbox = true; ether_addr_copy(hsr->macaddress_redbox, interlink->dev_addr); mod_timer(&hsr->prune_proxy_timer, jiffies + msecs_to_jiffies(PRUNE_PROXY_PERIOD)); } hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); return 0; err_unregister: hsr_del_ports(hsr); err_add_master: hsr_del_self_node(hsr); if (unregister) unregister_netdevice(hsr_dev); return res; } |
| 2 2 2 6 4 4 1 1 1 1 1 1 2 1 1 1 1 6 2 6 2 1 1 1 1 1 3 2 3 1 1 1 2 1 1 1 9 9 9 9 9 9 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 3 3 1 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Minimal file system backend for holding eBPF maps and programs, * used by bpf(2) object pinning. * * Authors: * * Daniel Borkmann <daniel@iogearbox.net> */ #include <linux/init.h> #include <linux/magic.h> #include <linux/major.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/kdev_t.h> #include <linux/filter.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <linux/kstrtox.h> #include "preload/bpf_preload.h" enum bpf_type { BPF_TYPE_UNSPEC = 0, BPF_TYPE_PROG, BPF_TYPE_MAP, BPF_TYPE_LINK, }; static void *bpf_any_get(void *raw, enum bpf_type type) { switch (type) { case BPF_TYPE_PROG: bpf_prog_inc(raw); break; case BPF_TYPE_MAP: bpf_map_inc_with_uref(raw); break; case BPF_TYPE_LINK: bpf_link_inc(raw); break; default: WARN_ON_ONCE(1); break; } return raw; } static void bpf_any_put(void *raw, enum bpf_type type) { switch (type) { case BPF_TYPE_PROG: bpf_prog_put(raw); break; case BPF_TYPE_MAP: bpf_map_put_with_uref(raw); break; case BPF_TYPE_LINK: bpf_link_put(raw); break; default: WARN_ON_ONCE(1); break; } } static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type) { void *raw; raw = bpf_map_get_with_uref(ufd); if (!IS_ERR(raw)) { *type = BPF_TYPE_MAP; return raw; } raw = bpf_prog_get(ufd); if (!IS_ERR(raw)) { *type = BPF_TYPE_PROG; return raw; } raw = bpf_link_get_from_fd(ufd); if (!IS_ERR(raw)) { *type = BPF_TYPE_LINK; return raw; } return ERR_PTR(-EINVAL); } static const struct inode_operations bpf_dir_iops; static const struct inode_operations bpf_prog_iops = { }; static const struct inode_operations bpf_map_iops = { }; static const struct inode_operations bpf_link_iops = { }; struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir, umode_t mode) { struct inode *inode; switch (mode & S_IFMT) { case S_IFDIR: case S_IFREG: case S_IFLNK: break; default: return ERR_PTR(-EINVAL); } inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOSPC); inode->i_ino = get_next_ino(); simple_inode_init_ts(inode); inode_init_owner(&nop_mnt_idmap, inode, dir, mode); return inode; } static int bpf_inode_type(const struct inode *inode, enum bpf_type *type) { *type = BPF_TYPE_UNSPEC; if (inode->i_op == &bpf_prog_iops) *type = BPF_TYPE_PROG; else if (inode->i_op == &bpf_map_iops) *type = BPF_TYPE_MAP; else if (inode->i_op == &bpf_link_iops) *type = BPF_TYPE_LINK; else return -EACCES; return 0; } static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode, struct inode *dir) { d_instantiate(dentry, inode); dget(dentry); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); } static int bpf_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; inode = bpf_get_inode(dir->i_sb, dir, mode | S_IFDIR); if (IS_ERR(inode)) return PTR_ERR(inode); inode->i_op = &bpf_dir_iops; inode->i_fop = &simple_dir_operations; inc_nlink(inode); inc_nlink(dir); bpf_dentry_finalize(dentry, inode, dir); return 0; } struct map_iter { void *key; bool done; }; static struct map_iter *map_iter(struct seq_file *m) { return m->private; } static struct bpf_map *seq_file_to_map(struct seq_file *m) { return file_inode(m->file)->i_private; } static void map_iter_free(struct map_iter *iter) { if (iter) { kfree(iter->key); kfree(iter); } } static struct map_iter *map_iter_alloc(struct bpf_map *map) { struct map_iter *iter; iter = kzalloc(sizeof(*iter), GFP_KERNEL | __GFP_NOWARN); if (!iter) goto error; iter->key = kzalloc(map->key_size, GFP_KERNEL | __GFP_NOWARN); if (!iter->key) goto error; return iter; error: map_iter_free(iter); return NULL; } static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) { struct bpf_map *map = seq_file_to_map(m); void *key = map_iter(m)->key; void *prev_key; (*pos)++; if (map_iter(m)->done) return NULL; if (unlikely(v == SEQ_START_TOKEN)) prev_key = NULL; else prev_key = key; rcu_read_lock(); if (map->ops->map_get_next_key(map, prev_key, key)) { map_iter(m)->done = true; key = NULL; } rcu_read_unlock(); return key; } static void *map_seq_start(struct seq_file *m, loff_t *pos) { if (map_iter(m)->done) return NULL; return *pos ? map_iter(m)->key : SEQ_START_TOKEN; } static void map_seq_stop(struct seq_file *m, void *v) { } static int map_seq_show(struct seq_file *m, void *v) { struct bpf_map *map = seq_file_to_map(m); void *key = map_iter(m)->key; if (unlikely(v == SEQ_START_TOKEN)) { seq_puts(m, "# WARNING!! The output is for debug purpose only\n"); seq_puts(m, "# WARNING!! The output format will change\n"); } else { map->ops->map_seq_show_elem(map, key, m); } return 0; } static const struct seq_operations bpffs_map_seq_ops = { .start = map_seq_start, .next = map_seq_next, .show = map_seq_show, .stop = map_seq_stop, }; static int bpffs_map_open(struct inode *inode, struct file *file) { struct bpf_map *map = inode->i_private; struct map_iter *iter; struct seq_file *m; int err; iter = map_iter_alloc(map); if (!iter) return -ENOMEM; err = seq_open(file, &bpffs_map_seq_ops); if (err) { map_iter_free(iter); return err; } m = file->private_data; m->private = iter; return 0; } static int bpffs_map_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; map_iter_free(map_iter(m)); return seq_release(inode, file); } /* bpffs_map_fops should only implement the basic * read operation for a BPF map. The purpose is to * provide a simple user intuitive way to do * "cat bpffs/pathto/a-pinned-map". * * Other operations (e.g. write, lookup...) should be realized by * the userspace tools (e.g. bpftool) through the * BPF_OBJ_GET_INFO_BY_FD and the map's lookup/update * interface. */ static const struct file_operations bpffs_map_fops = { .open = bpffs_map_open, .read = seq_read, .release = bpffs_map_release, }; static int bpffs_obj_open(struct inode *inode, struct file *file) { return -EIO; } static const struct file_operations bpffs_obj_fops = { .open = bpffs_obj_open, }; static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw, const struct inode_operations *iops, const struct file_operations *fops) { struct inode *dir = dentry->d_parent->d_inode; struct inode *inode = bpf_get_inode(dir->i_sb, dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); inode->i_op = iops; inode->i_fop = fops; inode->i_private = raw; bpf_dentry_finalize(dentry, inode, dir); return 0; } static int bpf_mkprog(struct dentry *dentry, umode_t mode, void *arg) { return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops, &bpffs_obj_fops); } static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg) { struct bpf_map *map = arg; return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops, bpf_map_support_seq_show(map) ? &bpffs_map_fops : &bpffs_obj_fops); } static int bpf_mklink(struct dentry *dentry, umode_t mode, void *arg) { struct bpf_link *link = arg; return bpf_mkobj_ops(dentry, mode, arg, &bpf_link_iops, bpf_link_is_iter(link) ? &bpf_iter_fops : &bpffs_obj_fops); } static struct dentry * bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags) { /* Dots in names (e.g. "/sys/fs/bpf/foo.bar") are reserved for future * extensions. That allows popoulate_bpffs() create special files. */ if ((dir->i_mode & S_IALLUGO) && strchr(dentry->d_name.name, '.')) return ERR_PTR(-EPERM); return simple_lookup(dir, dentry, flags); } static int bpf_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *target) { char *link = kstrdup(target, GFP_USER | __GFP_NOWARN); struct inode *inode; if (!link) return -ENOMEM; inode = bpf_get_inode(dir->i_sb, dir, S_IRWXUGO | S_IFLNK); if (IS_ERR(inode)) { kfree(link); return PTR_ERR(inode); } inode->i_op = &simple_symlink_inode_operations; inode->i_link = link; bpf_dentry_finalize(dentry, inode, dir); return 0; } static const struct inode_operations bpf_dir_iops = { .lookup = bpf_lookup, .mkdir = bpf_mkdir, .symlink = bpf_symlink, .rmdir = simple_rmdir, .rename = simple_rename, .link = simple_link, .unlink = simple_unlink, }; /* pin iterator link into bpffs */ static int bpf_iter_link_pin_kernel(struct dentry *parent, const char *name, struct bpf_link *link) { umode_t mode = S_IFREG | S_IRUSR; struct dentry *dentry; int ret; inode_lock(parent->d_inode); dentry = lookup_one_len(name, parent, strlen(name)); if (IS_ERR(dentry)) { inode_unlock(parent->d_inode); return PTR_ERR(dentry); } ret = bpf_mkobj_ops(dentry, mode, link, &bpf_link_iops, &bpf_iter_fops); dput(dentry); inode_unlock(parent->d_inode); return ret; } static int bpf_obj_do_pin(int path_fd, const char __user *pathname, void *raw, enum bpf_type type) { struct dentry *dentry; struct inode *dir; struct path path; umode_t mode; int ret; dentry = user_path_create(path_fd, pathname, &path, 0); if (IS_ERR(dentry)) return PTR_ERR(dentry); dir = d_inode(path.dentry); if (dir->i_op != &bpf_dir_iops) { ret = -EPERM; goto out; } mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); ret = security_path_mknod(&path, dentry, mode, 0); if (ret) goto out; switch (type) { case BPF_TYPE_PROG: ret = vfs_mkobj(dentry, mode, bpf_mkprog, raw); break; case BPF_TYPE_MAP: ret = vfs_mkobj(dentry, mode, bpf_mkmap, raw); break; case BPF_TYPE_LINK: ret = vfs_mkobj(dentry, mode, bpf_mklink, raw); break; default: ret = -EPERM; } out: done_path_create(&path, dentry); return ret; } int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname) { enum bpf_type type; void *raw; int ret; raw = bpf_fd_probe_obj(ufd, &type); if (IS_ERR(raw)) return PTR_ERR(raw); ret = bpf_obj_do_pin(path_fd, pathname, raw, type); if (ret != 0) bpf_any_put(raw, type); return ret; } static void *bpf_obj_do_get(int path_fd, const char __user *pathname, enum bpf_type *type, int flags) { struct inode *inode; struct path path; void *raw; int ret; ret = user_path_at(path_fd, pathname, LOOKUP_FOLLOW, &path); if (ret) return ERR_PTR(ret); inode = d_backing_inode(path.dentry); ret = path_permission(&path, ACC_MODE(flags)); if (ret) goto out; ret = bpf_inode_type(inode, type); if (ret) goto out; raw = bpf_any_get(inode->i_private, *type); if (!IS_ERR(raw)) touch_atime(&path); path_put(&path); return raw; out: path_put(&path); return ERR_PTR(ret); } int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags) { enum bpf_type type = BPF_TYPE_UNSPEC; int f_flags; void *raw; int ret; f_flags = bpf_get_file_flag(flags); if (f_flags < 0) return f_flags; raw = bpf_obj_do_get(path_fd, pathname, &type, f_flags); if (IS_ERR(raw)) return PTR_ERR(raw); if (type == BPF_TYPE_PROG) ret = bpf_prog_new_fd(raw); else if (type == BPF_TYPE_MAP) ret = bpf_map_new_fd(raw, f_flags); else if (type == BPF_TYPE_LINK) ret = (f_flags != O_RDWR) ? -EINVAL : bpf_link_new_fd(raw); else return -ENOENT; if (ret < 0) bpf_any_put(raw, type); return ret; } static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type) { struct bpf_prog *prog; int ret = inode_permission(&nop_mnt_idmap, inode, MAY_READ); if (ret) return ERR_PTR(ret); if (inode->i_op == &bpf_map_iops) return ERR_PTR(-EINVAL); if (inode->i_op == &bpf_link_iops) return ERR_PTR(-EINVAL); if (inode->i_op != &bpf_prog_iops) return ERR_PTR(-EACCES); prog = inode->i_private; ret = security_bpf_prog(prog); if (ret < 0) return ERR_PTR(ret); if (!bpf_prog_get_ok(prog, &type, false)) return ERR_PTR(-EINVAL); bpf_prog_inc(prog); return prog; } struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) { struct bpf_prog *prog; struct path path; int ret = kern_path(name, LOOKUP_FOLLOW, &path); if (ret) return ERR_PTR(ret); prog = __get_prog_inode(d_backing_inode(path.dentry), type); if (!IS_ERR(prog)) touch_atime(&path); path_put(&path); return prog; } EXPORT_SYMBOL(bpf_prog_get_type_path); struct bpffs_btf_enums { const struct btf *btf; const struct btf_type *cmd_t; const struct btf_type *map_t; const struct btf_type *prog_t; const struct btf_type *attach_t; }; static int find_bpffs_btf_enums(struct bpffs_btf_enums *info) { const struct btf *btf; const struct btf_type *t; const char *name; int i, n; memset(info, 0, sizeof(*info)); btf = bpf_get_btf_vmlinux(); if (IS_ERR(btf)) return PTR_ERR(btf); if (!btf) return -ENOENT; info->btf = btf; for (i = 1, n = btf_nr_types(btf); i < n; i++) { t = btf_type_by_id(btf, i); if (!btf_type_is_enum(t)) continue; name = btf_name_by_offset(btf, t->name_off); if (!name) continue; if (strcmp(name, "bpf_cmd") == 0) info->cmd_t = t; else if (strcmp(name, "bpf_map_type") == 0) info->map_t = t; else if (strcmp(name, "bpf_prog_type") == 0) info->prog_t = t; else if (strcmp(name, "bpf_attach_type") == 0) info->attach_t = t; else continue; if (info->cmd_t && info->map_t && info->prog_t && info->attach_t) return 0; } return -ESRCH; } static bool find_btf_enum_const(const struct btf *btf, const struct btf_type *enum_t, const char *prefix, const char *str, int *value) { const struct btf_enum *e; const char *name; int i, n, pfx_len = strlen(prefix); *value = 0; if (!btf || !enum_t) return false; for (i = 0, n = btf_vlen(enum_t); i < n; i++) { e = &btf_enum(enum_t)[i]; name = btf_name_by_offset(btf, e->name_off); if (!name || strncasecmp(name, prefix, pfx_len) != 0) continue; /* match symbolic name case insensitive and ignoring prefix */ if (strcasecmp(name + pfx_len, str) == 0) { *value = e->val; return true; } } return false; } static void seq_print_delegate_opts(struct seq_file *m, const char *opt_name, const struct btf *btf, const struct btf_type *enum_t, const char *prefix, u64 delegate_msk, u64 any_msk) { const struct btf_enum *e; bool first = true; const char *name; u64 msk; int i, n, pfx_len = strlen(prefix); delegate_msk &= any_msk; /* clear unknown bits */ if (delegate_msk == 0) return; seq_printf(m, ",%s", opt_name); if (delegate_msk == any_msk) { seq_printf(m, "=any"); return; } if (btf && enum_t) { for (i = 0, n = btf_vlen(enum_t); i < n; i++) { e = &btf_enum(enum_t)[i]; name = btf_name_by_offset(btf, e->name_off); if (!name || strncasecmp(name, prefix, pfx_len) != 0) continue; msk = 1ULL << e->val; if (delegate_msk & msk) { /* emit lower-case name without prefix */ seq_printf(m, "%c", first ? '=' : ':'); name += pfx_len; while (*name) { seq_printf(m, "%c", tolower(*name)); name++; } delegate_msk &= ~msk; first = false; } } } if (delegate_msk) seq_printf(m, "%c0x%llx", first ? '=' : ':', delegate_msk); } /* * Display the mount options in /proc/mounts. */ static int bpf_show_options(struct seq_file *m, struct dentry *root) { struct inode *inode = d_inode(root); umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX; struct bpf_mount_opts *opts = root->d_sb->s_fs_info; u64 mask; if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, inode->i_uid)); if (!gid_eq(inode->i_gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, inode->i_gid)); if (mode != S_IRWXUGO) seq_printf(m, ",mode=%o", mode); if (opts->delegate_cmds || opts->delegate_maps || opts->delegate_progs || opts->delegate_attachs) { struct bpffs_btf_enums info; /* ignore errors, fallback to hex */ (void)find_bpffs_btf_enums(&info); mask = (1ULL << __MAX_BPF_CMD) - 1; seq_print_delegate_opts(m, "delegate_cmds", info.btf, info.cmd_t, "BPF_", opts->delegate_cmds, mask); mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; seq_print_delegate_opts(m, "delegate_maps", info.btf, info.map_t, "BPF_MAP_TYPE_", opts->delegate_maps, mask); mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; seq_print_delegate_opts(m, "delegate_progs", info.btf, info.prog_t, "BPF_PROG_TYPE_", opts->delegate_progs, mask); mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; seq_print_delegate_opts(m, "delegate_attachs", info.btf, info.attach_t, "BPF_", opts->delegate_attachs, mask); } return 0; } static void bpf_free_inode(struct inode *inode) { enum bpf_type type; if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); if (!bpf_inode_type(inode, &type)) bpf_any_put(inode->i_private, type); free_inode_nonrcu(inode); } const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = bpf_show_options, .free_inode = bpf_free_inode, }; enum { OPT_UID, OPT_GID, OPT_MODE, OPT_DELEGATE_CMDS, OPT_DELEGATE_MAPS, OPT_DELEGATE_PROGS, OPT_DELEGATE_ATTACHS, }; static const struct fs_parameter_spec bpf_fs_parameters[] = { fsparam_u32 ("uid", OPT_UID), fsparam_u32 ("gid", OPT_GID), fsparam_u32oct ("mode", OPT_MODE), fsparam_string ("delegate_cmds", OPT_DELEGATE_CMDS), fsparam_string ("delegate_maps", OPT_DELEGATE_MAPS), fsparam_string ("delegate_progs", OPT_DELEGATE_PROGS), fsparam_string ("delegate_attachs", OPT_DELEGATE_ATTACHS), {} }; static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct bpf_mount_opts *opts = fc->s_fs_info; struct fs_parse_result result; kuid_t uid; kgid_t gid; int opt, err; opt = fs_parse(fc, bpf_fs_parameters, param, &result); if (opt < 0) { /* We might like to report bad mount options here, but * traditionally we've ignored all mount options, so we'd * better continue to ignore non-existing options for bpf. */ if (opt == -ENOPARAM) { opt = vfs_parse_fs_param_source(fc, param); if (opt != -ENOPARAM) return opt; return 0; } if (opt < 0) return opt; } switch (opt) { case OPT_UID: uid = make_kuid(current_user_ns(), result.uint_32); if (!uid_valid(uid)) goto bad_value; /* * The requested uid must be representable in the * filesystem's idmapping. */ if (!kuid_has_mapping(fc->user_ns, uid)) goto bad_value; opts->uid = uid; break; case OPT_GID: gid = make_kgid(current_user_ns(), result.uint_32); if (!gid_valid(gid)) goto bad_value; /* * The requested gid must be representable in the * filesystem's idmapping. */ if (!kgid_has_mapping(fc->user_ns, gid)) goto bad_value; opts->gid = gid; break; case OPT_MODE: opts->mode = result.uint_32 & S_IALLUGO; break; case OPT_DELEGATE_CMDS: case OPT_DELEGATE_MAPS: case OPT_DELEGATE_PROGS: case OPT_DELEGATE_ATTACHS: { struct bpffs_btf_enums info; const struct btf_type *enum_t; const char *enum_pfx; u64 *delegate_msk, msk = 0; char *p; int val; /* ignore errors, fallback to hex */ (void)find_bpffs_btf_enums(&info); switch (opt) { case OPT_DELEGATE_CMDS: delegate_msk = &opts->delegate_cmds; enum_t = info.cmd_t; enum_pfx = "BPF_"; break; case OPT_DELEGATE_MAPS: delegate_msk = &opts->delegate_maps; enum_t = info.map_t; enum_pfx = "BPF_MAP_TYPE_"; break; case OPT_DELEGATE_PROGS: delegate_msk = &opts->delegate_progs; enum_t = info.prog_t; enum_pfx = "BPF_PROG_TYPE_"; break; case OPT_DELEGATE_ATTACHS: delegate_msk = &opts->delegate_attachs; enum_t = info.attach_t; enum_pfx = "BPF_"; break; default: return -EINVAL; } while ((p = strsep(¶m->string, ":"))) { if (strcmp(p, "any") == 0) { msk |= ~0ULL; } else if (find_btf_enum_const(info.btf, enum_t, enum_pfx, p, &val)) { msk |= 1ULL << val; } else { err = kstrtou64(p, 0, &msk); if (err) return err; } } /* Setting delegation mount options requires privileges */ if (msk && !capable(CAP_SYS_ADMIN)) return -EPERM; *delegate_msk |= msk; break; } default: /* ignore unknown mount options */ break; } return 0; bad_value: return invalfc(fc, "Bad value for '%s'", param->key); } struct bpf_preload_ops *bpf_preload_ops; EXPORT_SYMBOL_GPL(bpf_preload_ops); static bool bpf_preload_mod_get(void) { /* If bpf_preload.ko wasn't loaded earlier then load it now. * When bpf_preload is built into vmlinux the module's __init * function will populate it. */ if (!bpf_preload_ops) { request_module("bpf_preload"); if (!bpf_preload_ops) return false; } /* And grab the reference, so the module doesn't disappear while the * kernel is interacting with the kernel module and its UMD. */ if (!try_module_get(bpf_preload_ops->owner)) { pr_err("bpf_preload module get failed.\n"); return false; } return true; } static void bpf_preload_mod_put(void) { if (bpf_preload_ops) /* now user can "rmmod bpf_preload" if necessary */ module_put(bpf_preload_ops->owner); } static DEFINE_MUTEX(bpf_preload_lock); static int populate_bpffs(struct dentry *parent) { struct bpf_preload_info objs[BPF_PRELOAD_LINKS] = {}; int err = 0, i; /* grab the mutex to make sure the kernel interactions with bpf_preload * are serialized */ mutex_lock(&bpf_preload_lock); /* if bpf_preload.ko wasn't built into vmlinux then load it */ if (!bpf_preload_mod_get()) goto out; err = bpf_preload_ops->preload(objs); if (err) goto out_put; for (i = 0; i < BPF_PRELOAD_LINKS; i++) { bpf_link_inc(objs[i].link); err = bpf_iter_link_pin_kernel(parent, objs[i].link_name, objs[i].link); if (err) { bpf_link_put(objs[i].link); goto out_put; } } out_put: bpf_preload_mod_put(); out: mutex_unlock(&bpf_preload_lock); return err; } static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr bpf_rfiles[] = { { "" } }; struct bpf_mount_opts *opts = sb->s_fs_info; struct inode *inode; int ret; /* Mounting an instance of BPF FS requires privileges */ if (fc->user_ns != &init_user_ns && !capable(CAP_SYS_ADMIN)) return -EPERM; ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles); if (ret) return ret; sb->s_op = &bpf_super_ops; inode = sb->s_root->d_inode; inode->i_uid = opts->uid; inode->i_gid = opts->gid; inode->i_op = &bpf_dir_iops; inode->i_mode &= ~S_IALLUGO; populate_bpffs(sb->s_root); inode->i_mode |= S_ISVTX | opts->mode; return 0; } static int bpf_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, bpf_fill_super); } static void bpf_free_fc(struct fs_context *fc) { kfree(fc->s_fs_info); } static const struct fs_context_operations bpf_context_ops = { .free = bpf_free_fc, .parse_param = bpf_parse_param, .get_tree = bpf_get_tree, }; /* * Set up the filesystem mount context. */ static int bpf_init_fs_context(struct fs_context *fc) { struct bpf_mount_opts *opts; opts = kzalloc(sizeof(struct bpf_mount_opts), GFP_KERNEL); if (!opts) return -ENOMEM; opts->mode = S_IRWXUGO; opts->uid = current_fsuid(); opts->gid = current_fsgid(); /* start out with no BPF token delegation enabled */ opts->delegate_cmds = 0; opts->delegate_maps = 0; opts->delegate_progs = 0; opts->delegate_attachs = 0; fc->s_fs_info = opts; fc->ops = &bpf_context_ops; return 0; } static void bpf_kill_super(struct super_block *sb) { struct bpf_mount_opts *opts = sb->s_fs_info; kill_litter_super(sb); kfree(opts); } static struct file_system_type bpf_fs_type = { .owner = THIS_MODULE, .name = "bpf", .init_fs_context = bpf_init_fs_context, .parameters = bpf_fs_parameters, .kill_sb = bpf_kill_super, .fs_flags = FS_USERNS_MOUNT, }; static int __init bpf_init(void) { int ret; ret = sysfs_create_mount_point(fs_kobj, "bpf"); if (ret) return ret; ret = register_filesystem(&bpf_fs_type); if (ret) sysfs_remove_mount_point(fs_kobj, "bpf"); return ret; } fs_initcall(bpf_init); |
| 18 18 18 18 17 18 18 17 1 431 436 437 435 8 434 359 109 433 436 276 279 277 33 34 280 280 280 278 278 24 274 279 24 24 24 71 197 71 45 130 155 130 128 153 42 42 29 29 7 30 327 327 14 3 14 14 20 233 234 279 55 56 25 64 5 1 5 12 13 13 277 279 278 276 278 277 278 279 278 279 277 58 230 279 3 275 280 275 13 13 13 13 13 25 7 7 6 7 7 25 34 16 15 15 15 14 33 333 3 330 331 330 410 408 228 208 208 208 15 110 25 25 84 37 38 38 4 5 5 3 2 3 3 5 4 1 1 1 1 1 1 1 20 20 20 20 20 20 20 20 20 20 20 20 20 20 21 21 4 3 4 18 18 17 1 18 18 21 2 2 1 2 2 2 2 2 2 2 7 7 7 25 25 25 7 7 4 13 13 11 11 13 36 280 278 36 251 38 276 278 328 336 331 326 331 278 335 2 1 2 225 164 136 52 134 225 72 59 70 71 71 48 182 227 182 125 182 226 228 227 226 48 228 227 225 239 237 229 228 227 224 223 223 225 193 212 212 183 183 179 183 27 26 69 67 1 58 59 59 48 46 46 2 2 47 49 83 74 62 74 63 71 85 73 72 72 71 75 75 10 10 10 8 10 20 5 15 4 11 3 8 20 77 38 1 76 77 43 43 2 2 42 1 1 4 4 4 240 502 502 505 17 503 502 467 332 5 5 1 50 50 1 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * (C) 1997 Linus Torvalds * (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation) */ #include <linux/export.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/mm.h> #include <linux/backing-dev.h> #include <linux/hash.h> #include <linux/swap.h> #include <linux/security.h> #include <linux/cdev.h> #include <linux/memblock.h> #include <linux/fsnotify.h> #include <linux/mount.h> #include <linux/posix_acl.h> #include <linux/buffer_head.h> /* for inode_has_buffers */ #include <linux/ratelimit.h> #include <linux/list_lru.h> #include <linux/iversion.h> #include <linux/rw_hint.h> #include <trace/events/writeback.h> #include "internal.h" /* * Inode locking rules: * * inode->i_lock protects: * inode->i_state, inode->i_hash, __iget(), inode->i_io_list * Inode LRU list locks protect: * inode->i_sb->s_inode_lru, inode->i_lru * inode->i_sb->s_inode_list_lock protects: * inode->i_sb->s_inodes, inode->i_sb_list * bdi->wb.list_lock protects: * bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_io_list * inode_hash_lock protects: * inode_hashtable, inode->i_hash * * Lock ordering: * * inode->i_sb->s_inode_list_lock * inode->i_lock * Inode LRU list locks * * bdi->wb.list_lock * inode->i_lock * * inode_hash_lock * inode->i_sb->s_inode_list_lock * inode->i_lock * * iunique_lock * inode_hash_lock */ static unsigned int i_hash_mask __ro_after_init; static unsigned int i_hash_shift __ro_after_init; static struct hlist_head *inode_hashtable __ro_after_init; static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock); /* * Empty aops. Can be used for the cases where the user does not * define any of the address_space operations. */ const struct address_space_operations empty_aops = { }; EXPORT_SYMBOL(empty_aops); static DEFINE_PER_CPU(unsigned long, nr_inodes); static DEFINE_PER_CPU(unsigned long, nr_unused); static struct kmem_cache *inode_cachep __ro_after_init; static long get_nr_inodes(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_inodes, i); return sum < 0 ? 0 : sum; } static inline long get_nr_inodes_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_unused, i); return sum < 0 ? 0 : sum; } long get_nr_dirty_inodes(void) { /* not actually dirty inodes, but a wild approximation */ long nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); return nr_dirty > 0 ? nr_dirty : 0; } /* * Handle nr_inode sysctl */ #ifdef CONFIG_SYSCTL /* * Statistics gathering.. */ static struct inodes_stat_t inodes_stat; static int proc_nr_inodes(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { inodes_stat.nr_inodes = get_nr_inodes(); inodes_stat.nr_unused = get_nr_inodes_unused(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static struct ctl_table inodes_sysctls[] = { { .procname = "inode-nr", .data = &inodes_stat, .maxlen = 2*sizeof(long), .mode = 0444, .proc_handler = proc_nr_inodes, }, { .procname = "inode-state", .data = &inodes_stat, .maxlen = 7*sizeof(long), .mode = 0444, .proc_handler = proc_nr_inodes, }, }; static int __init init_fs_inode_sysctls(void) { register_sysctl_init("fs", inodes_sysctls); return 0; } early_initcall(init_fs_inode_sysctls); #endif static int no_open(struct inode *inode, struct file *file) { return -ENXIO; } /** * inode_init_always - perform inode structure initialisation * @sb: superblock inode belongs to * @inode: inode to initialise * * These are initializations that need to be done on every inode * allocation as the fields are not initialised by slab allocation. */ int inode_init_always(struct super_block *sb, struct inode *inode) { static const struct inode_operations empty_iops; static const struct file_operations no_open_fops = {.open = no_open}; struct address_space *const mapping = &inode->i_data; inode->i_sb = sb; inode->i_blkbits = sb->s_blocksize_bits; inode->i_flags = 0; atomic64_set(&inode->i_sequence, 0); atomic_set(&inode->i_count, 1); inode->i_op = &empty_iops; inode->i_fop = &no_open_fops; inode->i_ino = 0; inode->__i_nlink = 1; inode->i_opflags = 0; if (sb->s_xattr) inode->i_opflags |= IOP_XATTR; i_uid_write(inode, 0); i_gid_write(inode, 0); atomic_set(&inode->i_writecount, 0); inode->i_size = 0; inode->i_write_hint = WRITE_LIFE_NOT_SET; inode->i_blocks = 0; inode->i_bytes = 0; inode->i_generation = 0; inode->i_pipe = NULL; inode->i_cdev = NULL; inode->i_link = NULL; inode->i_dir_seq = 0; inode->i_rdev = 0; inode->dirtied_when = 0; #ifdef CONFIG_CGROUP_WRITEBACK inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; #endif spin_lock_init(&inode->i_lock); lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key); init_rwsem(&inode->i_rwsem); lockdep_set_class(&inode->i_rwsem, &sb->s_type->i_mutex_key); atomic_set(&inode->i_dio_count, 0); mapping->a_ops = &empty_aops; mapping->host = inode; mapping->flags = 0; mapping->wb_err = 0; atomic_set(&mapping->i_mmap_writable, 0); #ifdef CONFIG_READ_ONLY_THP_FOR_FS atomic_set(&mapping->nr_thps, 0); #endif mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE); mapping->i_private_data = NULL; mapping->writeback_index = 0; init_rwsem(&mapping->invalidate_lock); lockdep_set_class_and_name(&mapping->invalidate_lock, &sb->s_type->invalidate_lock_key, "mapping.invalidate_lock"); if (sb->s_iflags & SB_I_STABLE_WRITES) mapping_set_stable_writes(mapping); inode->i_private = NULL; inode->i_mapping = mapping; INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ #ifdef CONFIG_FS_POSIX_ACL inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED; #endif #ifdef CONFIG_FSNOTIFY inode->i_fsnotify_mask = 0; #endif inode->i_flctx = NULL; if (unlikely(security_inode_alloc(inode))) return -ENOMEM; this_cpu_inc(nr_inodes); return 0; } EXPORT_SYMBOL(inode_init_always); void free_inode_nonrcu(struct inode *inode) { kmem_cache_free(inode_cachep, inode); } EXPORT_SYMBOL(free_inode_nonrcu); static void i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); if (inode->free_inode) inode->free_inode(inode); else free_inode_nonrcu(inode); } static struct inode *alloc_inode(struct super_block *sb) { const struct super_operations *ops = sb->s_op; struct inode *inode; if (ops->alloc_inode) inode = ops->alloc_inode(sb); else inode = alloc_inode_sb(sb, inode_cachep, GFP_KERNEL); if (!inode) return NULL; if (unlikely(inode_init_always(sb, inode))) { if (ops->destroy_inode) { ops->destroy_inode(inode); if (!ops->free_inode) return NULL; } inode->free_inode = ops->free_inode; i_callback(&inode->i_rcu); return NULL; } return inode; } void __destroy_inode(struct inode *inode) { BUG_ON(inode_has_buffers(inode)); inode_detach_wb(inode); security_inode_free(inode); fsnotify_inode_delete(inode); locks_free_lock_context(inode); if (!inode->i_nlink) { WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0); atomic_long_dec(&inode->i_sb->s_remove_count); } #ifdef CONFIG_FS_POSIX_ACL if (inode->i_acl && !is_uncached_acl(inode->i_acl)) posix_acl_release(inode->i_acl); if (inode->i_default_acl && !is_uncached_acl(inode->i_default_acl)) posix_acl_release(inode->i_default_acl); #endif this_cpu_dec(nr_inodes); } EXPORT_SYMBOL(__destroy_inode); static void destroy_inode(struct inode *inode) { const struct super_operations *ops = inode->i_sb->s_op; BUG_ON(!list_empty(&inode->i_lru)); __destroy_inode(inode); if (ops->destroy_inode) { ops->destroy_inode(inode); if (!ops->free_inode) return; } inode->free_inode = ops->free_inode; call_rcu(&inode->i_rcu, i_callback); } /** * drop_nlink - directly drop an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. In cases * where we are attempting to track writes to the * filesystem, a decrement to zero means an imminent * write when the file is truncated and actually unlinked * on the filesystem. */ void drop_nlink(struct inode *inode) { WARN_ON(inode->i_nlink == 0); inode->__i_nlink--; if (!inode->i_nlink) atomic_long_inc(&inode->i_sb->s_remove_count); } EXPORT_SYMBOL(drop_nlink); /** * clear_nlink - directly zero an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. See * drop_nlink() for why we care about i_nlink hitting zero. */ void clear_nlink(struct inode *inode) { if (inode->i_nlink) { inode->__i_nlink = 0; atomic_long_inc(&inode->i_sb->s_remove_count); } } EXPORT_SYMBOL(clear_nlink); /** * set_nlink - directly set an inode's link count * @inode: inode * @nlink: new nlink (should be non-zero) * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. */ void set_nlink(struct inode *inode, unsigned int nlink) { if (!nlink) { clear_nlink(inode); } else { /* Yes, some filesystems do change nlink from zero to one */ if (inode->i_nlink == 0) atomic_long_dec(&inode->i_sb->s_remove_count); inode->__i_nlink = nlink; } } EXPORT_SYMBOL(set_nlink); /** * inc_nlink - directly increment an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. Currently, * it is only here for parity with dec_nlink(). */ void inc_nlink(struct inode *inode) { if (unlikely(inode->i_nlink == 0)) { WARN_ON(!(inode->i_state & I_LINKABLE)); atomic_long_dec(&inode->i_sb->s_remove_count); } inode->__i_nlink++; } EXPORT_SYMBOL(inc_nlink); static void __address_space_init_once(struct address_space *mapping) { xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT); init_rwsem(&mapping->i_mmap_rwsem); INIT_LIST_HEAD(&mapping->i_private_list); spin_lock_init(&mapping->i_private_lock); mapping->i_mmap = RB_ROOT_CACHED; } void address_space_init_once(struct address_space *mapping) { memset(mapping, 0, sizeof(*mapping)); __address_space_init_once(mapping); } EXPORT_SYMBOL(address_space_init_once); /* * These are initializations that only need to be done * once, because the fields are idempotent across use * of the inode, so let the slab aware of that. */ void inode_init_once(struct inode *inode) { memset(inode, 0, sizeof(*inode)); INIT_HLIST_NODE(&inode->i_hash); INIT_LIST_HEAD(&inode->i_devices); INIT_LIST_HEAD(&inode->i_io_list); INIT_LIST_HEAD(&inode->i_wb_list); INIT_LIST_HEAD(&inode->i_lru); INIT_LIST_HEAD(&inode->i_sb_list); __address_space_init_once(&inode->i_data); i_size_ordered_init(inode); } EXPORT_SYMBOL(inode_init_once); static void init_once(void *foo) { struct inode *inode = (struct inode *) foo; inode_init_once(inode); } /* * inode->i_lock must be held */ void __iget(struct inode *inode) { atomic_inc(&inode->i_count); } /* * get additional reference to inode; caller must already hold one. */ void ihold(struct inode *inode) { WARN_ON(atomic_inc_return(&inode->i_count) < 2); } EXPORT_SYMBOL(ihold); static void __inode_add_lru(struct inode *inode, bool rotate) { if (inode->i_state & (I_DIRTY_ALL | I_SYNC | I_FREEING | I_WILL_FREE)) return; if (atomic_read(&inode->i_count)) return; if (!(inode->i_sb->s_flags & SB_ACTIVE)) return; if (!mapping_shrinkable(&inode->i_data)) return; if (list_lru_add_obj(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_inc(nr_unused); else if (rotate) inode->i_state |= I_REFERENCED; } /* * Add inode to LRU if needed (inode is unused and clean). * * Needs inode->i_lock held. */ void inode_add_lru(struct inode *inode) { __inode_add_lru(inode, false); } static void inode_lru_list_del(struct inode *inode) { if (list_lru_del_obj(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_dec(nr_unused); } /** * inode_sb_list_add - add inode to the superblock list of inodes * @inode: inode to add */ void inode_sb_list_add(struct inode *inode) { spin_lock(&inode->i_sb->s_inode_list_lock); list_add(&inode->i_sb_list, &inode->i_sb->s_inodes); spin_unlock(&inode->i_sb->s_inode_list_lock); } EXPORT_SYMBOL_GPL(inode_sb_list_add); static inline void inode_sb_list_del(struct inode *inode) { if (!list_empty(&inode->i_sb_list)) { spin_lock(&inode->i_sb->s_inode_list_lock); list_del_init(&inode->i_sb_list); spin_unlock(&inode->i_sb->s_inode_list_lock); } } static unsigned long hash(struct super_block *sb, unsigned long hashval) { unsigned long tmp; tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) / L1_CACHE_BYTES; tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> i_hash_shift); return tmp & i_hash_mask; } /** * __insert_inode_hash - hash an inode * @inode: unhashed inode * @hashval: unsigned long value used to locate this object in the * inode_hashtable. * * Add an inode to the inode hash for this superblock. */ void __insert_inode_hash(struct inode *inode, unsigned long hashval) { struct hlist_head *b = inode_hashtable + hash(inode->i_sb, hashval); spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); hlist_add_head_rcu(&inode->i_hash, b); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(__insert_inode_hash); /** * __remove_inode_hash - remove an inode from the hash * @inode: inode to unhash * * Remove an inode from the superblock. */ void __remove_inode_hash(struct inode *inode) { spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); hlist_del_init_rcu(&inode->i_hash); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(__remove_inode_hash); void dump_mapping(const struct address_space *mapping) { struct inode *host; const struct address_space_operations *a_ops; struct hlist_node *dentry_first; struct dentry *dentry_ptr; struct dentry dentry; unsigned long ino; /* * If mapping is an invalid pointer, we don't want to crash * accessing it, so probe everything depending on it carefully. */ if (get_kernel_nofault(host, &mapping->host) || get_kernel_nofault(a_ops, &mapping->a_ops)) { pr_warn("invalid mapping:%px\n", mapping); return; } if (!host) { pr_warn("aops:%ps\n", a_ops); return; } if (get_kernel_nofault(dentry_first, &host->i_dentry.first) || get_kernel_nofault(ino, &host->i_ino)) { pr_warn("aops:%ps invalid inode:%px\n", a_ops, host); return; } if (!dentry_first) { pr_warn("aops:%ps ino:%lx\n", a_ops, ino); return; } dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias); if (get_kernel_nofault(dentry, dentry_ptr) || !dentry.d_parent || !dentry.d_name.name) { pr_warn("aops:%ps ino:%lx invalid dentry:%px\n", a_ops, ino, dentry_ptr); return; } /* * if dentry is corrupted, the %pd handler may still crash, * but it's unlikely that we reach here with a corrupt mapping */ pr_warn("aops:%ps ino:%lx dentry name:\"%pd\"\n", a_ops, ino, &dentry); } void clear_inode(struct inode *inode) { /* * We have to cycle the i_pages lock here because reclaim can be in the * process of removing the last page (in __filemap_remove_folio()) * and we must not free the mapping under it. */ xa_lock_irq(&inode->i_data.i_pages); BUG_ON(inode->i_data.nrpages); /* * Almost always, mapping_empty(&inode->i_data) here; but there are * two known and long-standing ways in which nodes may get left behind * (when deep radix-tree node allocation failed partway; or when THP * collapse_file() failed). Until those two known cases are cleaned up, * or a cleanup function is called here, do not BUG_ON(!mapping_empty), * nor even WARN_ON(!mapping_empty). */ xa_unlock_irq(&inode->i_data.i_pages); BUG_ON(!list_empty(&inode->i_data.i_private_list)); BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(inode->i_state & I_CLEAR); BUG_ON(!list_empty(&inode->i_wb_list)); /* don't need i_lock here, no concurrent mods to i_state */ inode->i_state = I_FREEING | I_CLEAR; } EXPORT_SYMBOL(clear_inode); /* * Free the inode passed in, removing it from the lists it is still connected * to. We remove any pages still attached to the inode and wait for any IO that * is still in progress before finally destroying the inode. * * An inode must already be marked I_FREEING so that we avoid the inode being * moved back onto lists if we race with other code that manipulates the lists * (e.g. writeback_single_inode). The caller is responsible for setting this. * * An inode must already be removed from the LRU list before being evicted from * the cache. This should occur atomically with setting the I_FREEING state * flag, so no inodes here should ever be on the LRU when being evicted. */ static void evict(struct inode *inode) { const struct super_operations *op = inode->i_sb->s_op; BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(!list_empty(&inode->i_lru)); if (!list_empty(&inode->i_io_list)) inode_io_list_del(inode); inode_sb_list_del(inode); /* * Wait for flusher thread to be done with the inode so that filesystem * does not start destroying it while writeback is still running. Since * the inode has I_FREEING set, flusher thread won't start new work on * the inode. We just have to wait for running writeback to finish. */ inode_wait_for_writeback(inode); if (op->evict_inode) { op->evict_inode(inode); } else { truncate_inode_pages_final(&inode->i_data); clear_inode(inode); } if (S_ISCHR(inode->i_mode) && inode->i_cdev) cd_forget(inode); remove_inode_hash(inode); spin_lock(&inode->i_lock); wake_up_bit(&inode->i_state, __I_NEW); BUG_ON(inode->i_state != (I_FREEING | I_CLEAR)); spin_unlock(&inode->i_lock); destroy_inode(inode); } /* * dispose_list - dispose of the contents of a local list * @head: the head of the list to free * * Dispose-list gets a local list with local inodes in it, so it doesn't * need to worry about list corruption and SMP locks. */ static void dispose_list(struct list_head *head) { while (!list_empty(head)) { struct inode *inode; inode = list_first_entry(head, struct inode, i_lru); list_del_init(&inode->i_lru); evict(inode); cond_resched(); } } /** * evict_inodes - evict all evictable inodes for a superblock * @sb: superblock to operate on * * Make sure that no inodes with zero refcount are retained. This is * called by superblock shutdown after having SB_ACTIVE flag removed, * so any inode reaching zero refcount during or after that call will * be immediately evicted. */ void evict_inodes(struct super_block *sb) { struct inode *inode, *next; LIST_HEAD(dispose); again: spin_lock(&sb->s_inode_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { if (atomic_read(&inode->i_count)) continue; spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); continue; } inode->i_state |= I_FREEING; inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); /* * We can have a ton of inodes to evict at unmount time given * enough memory, check to see if we need to go to sleep for a * bit so we don't livelock. */ if (need_resched()) { spin_unlock(&sb->s_inode_list_lock); cond_resched(); dispose_list(&dispose); goto again; } } spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); } EXPORT_SYMBOL_GPL(evict_inodes); /** * invalidate_inodes - attempt to free all inodes on a superblock * @sb: superblock to operate on * * Attempts to free all inodes (including dirty inodes) for a given superblock. */ void invalidate_inodes(struct super_block *sb) { struct inode *inode, *next; LIST_HEAD(dispose); again: spin_lock(&sb->s_inode_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); continue; } if (atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); continue; } inode->i_state |= I_FREEING; inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); if (need_resched()) { spin_unlock(&sb->s_inode_list_lock); cond_resched(); dispose_list(&dispose); goto again; } } spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); } /* * Isolate the inode from the LRU in preparation for freeing it. * * If the inode has the I_REFERENCED flag set, then it means that it has been * used recently - the flag is set in iput_final(). When we encounter such an * inode, clear the flag and move it to the back of the LRU so it gets another * pass through the LRU before it gets reclaimed. This is necessary because of * the fact we are doing lazy LRU updates to minimise lock contention so the * LRU does not have strict ordering. Hence we don't want to reclaim inodes * with this flag set because they are the inodes that are out of order. */ static enum lru_status inode_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct inode *inode = container_of(item, struct inode, i_lru); /* * We are inverting the lru lock/inode->i_lock here, so use a * trylock. If we fail to get the lock, just skip it. */ if (!spin_trylock(&inode->i_lock)) return LRU_SKIP; /* * Inodes can get referenced, redirtied, or repopulated while * they're already on the LRU, and this can make them * unreclaimable for a while. Remove them lazily here; iput, * sync, or the last page cache deletion will requeue them. */ if (atomic_read(&inode->i_count) || (inode->i_state & ~I_REFERENCED) || !mapping_shrinkable(&inode->i_data)) { list_lru_isolate(lru, &inode->i_lru); spin_unlock(&inode->i_lock); this_cpu_dec(nr_unused); return LRU_REMOVED; } /* Recently referenced inodes get one more pass */ if (inode->i_state & I_REFERENCED) { inode->i_state &= ~I_REFERENCED; spin_unlock(&inode->i_lock); return LRU_ROTATE; } /* * On highmem systems, mapping_shrinkable() permits dropping * page cache in order to free up struct inodes: lowmem might * be under pressure before the cache inside the highmem zone. */ if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) { __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(lru_lock); if (remove_inode_buffers(inode)) { unsigned long reap; reap = invalidate_mapping_pages(&inode->i_data, 0, -1); if (current_is_kswapd()) __count_vm_events(KSWAPD_INODESTEAL, reap); else __count_vm_events(PGINODESTEAL, reap); mm_account_reclaimed_pages(reap); } iput(inode); spin_lock(lru_lock); return LRU_RETRY; } WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; list_lru_isolate_move(lru, &inode->i_lru, freeable); spin_unlock(&inode->i_lock); this_cpu_dec(nr_unused); return LRU_REMOVED; } /* * Walk the superblock inode LRU for freeable inodes and attempt to free them. * This is called from the superblock shrinker function with a number of inodes * to trim from the LRU. Inodes to be freed are moved to a temporary list and * then are freed outside inode_lock by dispose_list(). */ long prune_icache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(freeable); long freed; freed = list_lru_shrink_walk(&sb->s_inode_lru, sc, inode_lru_isolate, &freeable); dispose_list(&freeable); return freed; } static void __wait_on_freeing_inode(struct inode *inode); /* * Called with the inode lock held. */ static struct inode *find_inode(struct super_block *sb, struct hlist_head *head, int (*test)(struct inode *, void *), void *data) { struct inode *inode = NULL; repeat: hlist_for_each_entry(inode, head, i_hash) { if (inode->i_sb != sb) continue; if (!test(inode, data)) continue; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE)) { __wait_on_freeing_inode(inode); goto repeat; } if (unlikely(inode->i_state & I_CREATING)) { spin_unlock(&inode->i_lock); return ERR_PTR(-ESTALE); } __iget(inode); spin_unlock(&inode->i_lock); return inode; } return NULL; } /* * find_inode_fast is the fast path version of find_inode, see the comment at * iget_locked for details. */ static struct inode *find_inode_fast(struct super_block *sb, struct hlist_head *head, unsigned long ino) { struct inode *inode = NULL; repeat: hlist_for_each_entry(inode, head, i_hash) { if (inode->i_ino != ino) continue; if (inode->i_sb != sb) continue; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE)) { __wait_on_freeing_inode(inode); goto repeat; } if (unlikely(inode->i_state & I_CREATING)) { spin_unlock(&inode->i_lock); return ERR_PTR(-ESTALE); } __iget(inode); spin_unlock(&inode->i_lock); return inode; } return NULL; } /* * Each cpu owns a range of LAST_INO_BATCH numbers. * 'shared_last_ino' is dirtied only once out of LAST_INO_BATCH allocations, * to renew the exhausted range. * * This does not significantly increase overflow rate because every CPU can * consume at most LAST_INO_BATCH-1 unused inode numbers. So there is * NR_CPUS*(LAST_INO_BATCH-1) wastage. At 4096 and 1024, this is ~0.1% of the * 2^32 range, and is a worst-case. Even a 50% wastage would only increase * overflow rate by 2x, which does not seem too significant. * * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW * error if st_ino won't fit in target struct field. Use 32bit counter * here to attempt to avoid that. */ #define LAST_INO_BATCH 1024 static DEFINE_PER_CPU(unsigned int, last_ino); unsigned int get_next_ino(void) { unsigned int *p = &get_cpu_var(last_ino); unsigned int res = *p; #ifdef CONFIG_SMP if (unlikely((res & (LAST_INO_BATCH-1)) == 0)) { static atomic_t shared_last_ino; int next = atomic_add_return(LAST_INO_BATCH, &shared_last_ino); res = next - LAST_INO_BATCH; } #endif res++; /* get_next_ino should not provide a 0 inode number */ if (unlikely(!res)) res++; *p = res; put_cpu_var(last_ino); return res; } EXPORT_SYMBOL(get_next_ino); /** * new_inode_pseudo - obtain an inode * @sb: superblock * * Allocates a new inode for given superblock. * Inode wont be chained in superblock s_inodes list * This means : * - fs can't be unmount * - quotas, fsnotify, writeback can't work */ struct inode *new_inode_pseudo(struct super_block *sb) { struct inode *inode = alloc_inode(sb); if (inode) { spin_lock(&inode->i_lock); inode->i_state = 0; spin_unlock(&inode->i_lock); } return inode; } /** * new_inode - obtain an inode * @sb: superblock * * Allocates a new inode for given superblock. The default gfp_mask * for allocations related to inode->i_mapping is GFP_HIGHUSER_MOVABLE. * If HIGHMEM pages are unsuitable or it is known that pages allocated * for the page cache are not reclaimable or migratable, * mapping_set_gfp_mask() must be called with suitable flags on the * newly created inode's mapping * */ struct inode *new_inode(struct super_block *sb) { struct inode *inode; inode = new_inode_pseudo(sb); if (inode) inode_sb_list_add(inode); return inode; } EXPORT_SYMBOL(new_inode); #ifdef CONFIG_DEBUG_LOCK_ALLOC void lockdep_annotate_inode_mutex_key(struct inode *inode) { if (S_ISDIR(inode->i_mode)) { struct file_system_type *type = inode->i_sb->s_type; /* Set new key only if filesystem hasn't already changed it */ if (lockdep_match_class(&inode->i_rwsem, &type->i_mutex_key)) { /* * ensure nobody is actually holding i_mutex */ // mutex_destroy(&inode->i_mutex); init_rwsem(&inode->i_rwsem); lockdep_set_class(&inode->i_rwsem, &type->i_mutex_dir_key); } } } EXPORT_SYMBOL(lockdep_annotate_inode_mutex_key); #endif /** * unlock_new_inode - clear the I_NEW state and wake up any waiters * @inode: new inode to unlock * * Called when the inode is fully initialised to clear the new state of the * inode and wake up anyone waiting for the inode to finish initialisation. */ void unlock_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(unlock_new_inode); void discard_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); iput(inode); } EXPORT_SYMBOL(discard_new_inode); /** * lock_two_nondirectories - take two i_mutexes on non-directory objects * * Lock any non-NULL argument. Passed objects must not be directories. * Zero, one or two objects may be locked by this function. * * @inode1: first inode to lock * @inode2: second inode to lock */ void lock_two_nondirectories(struct inode *inode1, struct inode *inode2) { if (inode1) WARN_ON_ONCE(S_ISDIR(inode1->i_mode)); if (inode2) WARN_ON_ONCE(S_ISDIR(inode2->i_mode)); if (inode1 > inode2) swap(inode1, inode2); if (inode1) inode_lock(inode1); if (inode2 && inode2 != inode1) inode_lock_nested(inode2, I_MUTEX_NONDIR2); } EXPORT_SYMBOL(lock_two_nondirectories); /** * unlock_two_nondirectories - release locks from lock_two_nondirectories() * @inode1: first inode to unlock * @inode2: second inode to unlock */ void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2) { if (inode1) { WARN_ON_ONCE(S_ISDIR(inode1->i_mode)); inode_unlock(inode1); } if (inode2 && inode2 != inode1) { WARN_ON_ONCE(S_ISDIR(inode2->i_mode)); inode_unlock(inode2); } } EXPORT_SYMBOL(unlock_two_nondirectories); /** * inode_insert5 - obtain an inode from a mounted file system * @inode: pre-allocated inode to use for insert to cache * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * * Search for the inode specified by @hashval and @data in the inode cache, * and if present it is return it with an increased reference count. This is * a variant of iget5_locked() for callers that don't want to fail on memory * allocation of inode. * * If the inode is not in cache, insert the pre-allocated inode to cache and * return it locked, hashed, and with the I_NEW flag set. The file system gets * to fill it in before unlocking it via unlock_new_inode(). * * Note both @test and @set are called with the inode_hash_lock held, so can't * sleep. */ struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval); struct inode *old; again: spin_lock(&inode_hash_lock); old = find_inode(inode->i_sb, head, test, data); if (unlikely(old)) { /* * Uhhuh, somebody else created the same inode under us. * Use the old inode instead of the preallocated one. */ spin_unlock(&inode_hash_lock); if (IS_ERR(old)) return NULL; wait_on_inode(old); if (unlikely(inode_unhashed(old))) { iput(old); goto again; } return old; } if (set && unlikely(set(inode, data))) { inode = NULL; goto unlock; } /* * Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents */ spin_lock(&inode->i_lock); inode->i_state |= I_NEW; hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); /* * Add inode to the sb list if it's not already. It has I_NEW at this * point, so it should be safe to test i_sb_list locklessly. */ if (list_empty(&inode->i_sb_list)) inode_sb_list_add(inode); unlock: spin_unlock(&inode_hash_lock); return inode; } EXPORT_SYMBOL(inode_insert5); /** * iget5_locked - obtain an inode from a mounted file system * @sb: super block of file system * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * * Search for the inode specified by @hashval and @data in the inode cache, * and if present it is return it with an increased reference count. This is * a generalized version of iget_locked() for file systems where the inode * number is not sufficient for unique identification of an inode. * * If the inode is not in cache, allocate a new inode and return it locked, * hashed, and with the I_NEW flag set. The file system gets to fill it in * before unlocking it via unlock_new_inode(). * * Note both @test and @set are called with the inode_hash_lock held, so can't * sleep. */ struct inode *iget5_locked(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct inode *inode = ilookup5(sb, hashval, test, data); if (!inode) { struct inode *new = alloc_inode(sb); if (new) { new->i_state = 0; inode = inode_insert5(new, hashval, test, set, data); if (unlikely(inode != new)) destroy_inode(new); } } return inode; } EXPORT_SYMBOL(iget5_locked); /** * iget_locked - obtain an inode from a mounted file system * @sb: super block of file system * @ino: inode number to get * * Search for the inode specified by @ino in the inode cache and if present * return it with an increased reference count. This is for file systems * where the inode number is sufficient for unique identification of an inode. * * If the inode is not in cache, allocate a new inode and return it locked, * hashed, and with the I_NEW flag set. The file system gets to fill it in * before unlocking it via unlock_new_inode(). */ struct inode *iget_locked(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; again: spin_lock(&inode_hash_lock); inode = find_inode_fast(sb, head, ino); spin_unlock(&inode_hash_lock); if (inode) { if (IS_ERR(inode)) return NULL; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } return inode; } inode = alloc_inode(sb); if (inode) { struct inode *old; spin_lock(&inode_hash_lock); /* We released the lock, so.. */ old = find_inode_fast(sb, head, ino); if (!old) { inode->i_ino = ino; spin_lock(&inode->i_lock); inode->i_state = I_NEW; hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); inode_sb_list_add(inode); spin_unlock(&inode_hash_lock); /* Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents */ return inode; } /* * Uhhuh, somebody else created the same inode under * us. Use the old inode instead of the one we just * allocated. */ spin_unlock(&inode_hash_lock); destroy_inode(inode); if (IS_ERR(old)) return NULL; inode = old; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(iget_locked); /* * search the inode cache for a matching inode number. * If we find one, then the inode number we are trying to * allocate is not unique and so we should not use it. * * Returns 1 if the inode number is unique, 0 if it is not. */ static int test_inode_iunique(struct super_block *sb, unsigned long ino) { struct hlist_head *b = inode_hashtable + hash(sb, ino); struct inode *inode; hlist_for_each_entry_rcu(inode, b, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb) return 0; } return 1; } /** * iunique - get a unique inode number * @sb: superblock * @max_reserved: highest reserved inode number * * Obtain an inode number that is unique on the system for a given * superblock. This is used by file systems that have no natural * permanent inode numbering system. An inode number is returned that * is higher than the reserved limit but unique. * * BUGS: * With a large number of inodes live on the file system this function * currently becomes quite slow. */ ino_t iunique(struct super_block *sb, ino_t max_reserved) { /* * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW * error if st_ino won't fit in target struct field. Use 32bit counter * here to attempt to avoid that. */ static DEFINE_SPINLOCK(iunique_lock); static unsigned int counter; ino_t res; rcu_read_lock(); spin_lock(&iunique_lock); do { if (counter <= max_reserved) counter = max_reserved + 1; res = counter++; } while (!test_inode_iunique(sb, res)); spin_unlock(&iunique_lock); rcu_read_unlock(); return res; } EXPORT_SYMBOL(iunique); struct inode *igrab(struct inode *inode) { spin_lock(&inode->i_lock); if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) { __iget(inode); spin_unlock(&inode->i_lock); } else { spin_unlock(&inode->i_lock); /* * Handle the case where s_op->clear_inode is not been * called yet, and somebody is calling igrab * while the inode is getting freed. */ inode = NULL; } return inode; } EXPORT_SYMBOL(igrab); /** * ilookup5_nowait - search for an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test * * Search for the inode specified by @hashval and @data in the inode cache. * If the inode is in the cache, the inode is returned with an incremented * reference count. * * Note: I_NEW is not waited upon so you have to be very careful what you do * with the returned inode. You probably should be using ilookup5() instead. * * Note2: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode; spin_lock(&inode_hash_lock); inode = find_inode(sb, head, test, data); spin_unlock(&inode_hash_lock); return IS_ERR(inode) ? NULL : inode; } EXPORT_SYMBOL(ilookup5_nowait); /** * ilookup5 - search for an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test * * Search for the inode specified by @hashval and @data in the inode cache, * and if the inode is in the cache, return the inode with an incremented * reference count. Waits on I_NEW before returning the inode. * returned with an incremented reference count. * * This is a generalized version of ilookup() for file systems where the * inode number is not sufficient for unique identification of an inode. * * Note: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct inode *inode; again: inode = ilookup5_nowait(sb, hashval, test, data); if (inode) { wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(ilookup5); /** * ilookup - search for an inode in the inode cache * @sb: super block of file system to search * @ino: inode number to search for * * Search for the inode @ino in the inode cache, and if the inode is in the * cache, the inode is returned with an incremented reference count. */ struct inode *ilookup(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; again: spin_lock(&inode_hash_lock); inode = find_inode_fast(sb, head, ino); spin_unlock(&inode_hash_lock); if (inode) { if (IS_ERR(inode)) return NULL; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(ilookup); /** * find_inode_nowait - find an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @match: callback used for comparisons between inodes * @data: opaque data pointer to pass to @match * * Search for the inode specified by @hashval and @data in the inode * cache, where the helper function @match will return 0 if the inode * does not match, 1 if the inode does match, and -1 if the search * should be stopped. The @match function must be responsible for * taking the i_lock spin_lock and checking i_state for an inode being * freed or being initialized, and incrementing the reference count * before returning 1. It also must not sleep, since it is called with * the inode_hash_lock spinlock held. * * This is a even more generalized version of ilookup5() when the * function must never block --- find_inode() can block in * __wait_on_freeing_inode() --- or when the caller can not increment * the reference count because the resulting iput() might cause an * inode eviction. The tradeoff is that the @match funtion must be * very carefully implemented. */ struct inode *find_inode_nowait(struct super_block *sb, unsigned long hashval, int (*match)(struct inode *, unsigned long, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode, *ret_inode = NULL; int mval; spin_lock(&inode_hash_lock); hlist_for_each_entry(inode, head, i_hash) { if (inode->i_sb != sb) continue; mval = match(inode, hashval, data); if (mval == 0) continue; if (mval == 1) ret_inode = inode; goto out; } out: spin_unlock(&inode_hash_lock); return ret_inode; } EXPORT_SYMBOL(find_inode_nowait); /** * find_inode_rcu - find an inode in the inode cache * @sb: Super block of file system to search * @hashval: Key to hash * @test: Function to test match on an inode * @data: Data for test function * * Search for the inode specified by @hashval and @data in the inode cache, * where the helper function @test will return 0 if the inode does not match * and 1 if it does. The @test function must be responsible for taking the * i_lock spin_lock and checking i_state for an inode being freed or being * initialized. * * If successful, this will return the inode for which the @test function * returned 1 and NULL otherwise. * * The @test function is not permitted to take a ref on any inode presented. * It is also not permitted to sleep. * * The caller must hold the RCU read lock. */ struct inode *find_inode_rcu(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious find_inode_rcu() usage"); hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_sb == sb && !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE)) && test(inode, data)) return inode; } return NULL; } EXPORT_SYMBOL(find_inode_rcu); /** * find_inode_by_ino_rcu - Find an inode in the inode cache * @sb: Super block of file system to search * @ino: The inode number to match * * Search for the inode specified by @hashval and @data in the inode cache, * where the helper function @test will return 0 if the inode does not match * and 1 if it does. The @test function must be responsible for taking the * i_lock spin_lock and checking i_state for an inode being freed or being * initialized. * * If successful, this will return the inode for which the @test function * returned 1 and NULL otherwise. * * The @test function is not permitted to take a ref on any inode presented. * It is also not permitted to sleep. * * The caller must hold the RCU read lock. */ struct inode *find_inode_by_ino_rcu(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious find_inode_by_ino_rcu() usage"); hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb && !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE))) return inode; } return NULL; } EXPORT_SYMBOL(find_inode_by_ino_rcu); int insert_inode_locked(struct inode *inode) { struct super_block *sb = inode->i_sb; ino_t ino = inode->i_ino; struct hlist_head *head = inode_hashtable + hash(sb, ino); while (1) { struct inode *old = NULL; spin_lock(&inode_hash_lock); hlist_for_each_entry(old, head, i_hash) { if (old->i_ino != ino) continue; if (old->i_sb != sb) continue; spin_lock(&old->i_lock); if (old->i_state & (I_FREEING|I_WILL_FREE)) { spin_unlock(&old->i_lock); continue; } break; } if (likely(!old)) { spin_lock(&inode->i_lock); inode->i_state |= I_NEW | I_CREATING; hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); return 0; } if (unlikely(old->i_state & I_CREATING)) { spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); return -EBUSY; } __iget(old); spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); wait_on_inode(old); if (unlikely(!inode_unhashed(old))) { iput(old); return -EBUSY; } iput(old); } } EXPORT_SYMBOL(insert_inode_locked); int insert_inode_locked4(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct inode *old; inode->i_state |= I_CREATING; old = inode_insert5(inode, hashval, test, NULL, data); if (old != inode) { iput(old); return -EBUSY; } return 0; } EXPORT_SYMBOL(insert_inode_locked4); int generic_delete_inode(struct inode *inode) { return 1; } EXPORT_SYMBOL(generic_delete_inode); /* * Called when we're dropping the last reference * to an inode. * * Call the FS "drop_inode()" function, defaulting to * the legacy UNIX filesystem behaviour. If it tells * us to evict inode, do so. Otherwise, retain inode * in cache if fs is alive, sync and evict if fs is * shutting down. */ static void iput_final(struct inode *inode) { struct super_block *sb = inode->i_sb; const struct super_operations *op = inode->i_sb->s_op; unsigned long state; int drop; WARN_ON(inode->i_state & I_NEW); if (op->drop_inode) drop = op->drop_inode(inode); else drop = generic_drop_inode(inode); if (!drop && !(inode->i_state & I_DONTCACHE) && (sb->s_flags & SB_ACTIVE)) { __inode_add_lru(inode, true); spin_unlock(&inode->i_lock); return; } state = inode->i_state; if (!drop) { WRITE_ONCE(inode->i_state, state | I_WILL_FREE); spin_unlock(&inode->i_lock); write_inode_now(inode, 1); spin_lock(&inode->i_lock); state = inode->i_state; WARN_ON(state & I_NEW); state &= ~I_WILL_FREE; } WRITE_ONCE(inode->i_state, state | I_FREEING); if (!list_empty(&inode->i_lru)) inode_lru_list_del(inode); spin_unlock(&inode->i_lock); evict(inode); } /** * iput - put an inode * @inode: inode to put * * Puts an inode, dropping its usage count. If the inode use count hits * zero, the inode is then freed and may also be destroyed. * * Consequently, iput() can sleep. */ void iput(struct inode *inode) { if (!inode) return; BUG_ON(inode->i_state & I_CLEAR); retry: if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock)) { if (inode->i_nlink && (inode->i_state & I_DIRTY_TIME)) { atomic_inc(&inode->i_count); spin_unlock(&inode->i_lock); trace_writeback_lazytime_iput(inode); mark_inode_dirty_sync(inode); goto retry; } iput_final(inode); } } EXPORT_SYMBOL(iput); #ifdef CONFIG_BLOCK /** * bmap - find a block number in a file * @inode: inode owning the block number being requested * @block: pointer containing the block to find * * Replaces the value in ``*block`` with the block number on the device holding * corresponding to the requested block number in the file. * That is, asked for block 4 of inode 1 the function will replace the * 4 in ``*block``, with disk block relative to the disk start that holds that * block of the file. * * Returns -EINVAL in case of error, 0 otherwise. If mapping falls into a * hole, returns 0 and ``*block`` is also set to 0. */ int bmap(struct inode *inode, sector_t *block) { if (!inode->i_mapping->a_ops->bmap) return -EINVAL; *block = inode->i_mapping->a_ops->bmap(inode->i_mapping, *block); return 0; } EXPORT_SYMBOL(bmap); #endif /* * With relative atime, only update atime if the previous atime is * earlier than or equal to either the ctime or mtime, * or if at least a day has passed since the last atime update. */ static bool relatime_need_update(struct vfsmount *mnt, struct inode *inode, struct timespec64 now) { struct timespec64 atime, mtime, ctime; if (!(mnt->mnt_flags & MNT_RELATIME)) return true; /* * Is mtime younger than or equal to atime? If yes, update atime: */ atime = inode_get_atime(inode); mtime = inode_get_mtime(inode); if (timespec64_compare(&mtime, &atime) >= 0) return true; /* * Is ctime younger than or equal to atime? If yes, update atime: */ ctime = inode_get_ctime(inode); if (timespec64_compare(&ctime, &atime) >= 0) return true; /* * Is the previous atime value older than a day? If yes, * update atime: */ if ((long)(now.tv_sec - atime.tv_sec) >= 24*60*60) return true; /* * Good, we can skip the atime update: */ return false; } /** * inode_update_timestamps - update the timestamps on the inode * @inode: inode to be updated * @flags: S_* flags that needed to be updated * * The update_time function is called when an inode's timestamps need to be * updated for a read or write operation. This function handles updating the * actual timestamps. It's up to the caller to ensure that the inode is marked * dirty appropriately. * * In the case where any of S_MTIME, S_CTIME, or S_VERSION need to be updated, * attempt to update all three of them. S_ATIME updates can be handled * independently of the rest. * * Returns a set of S_* flags indicating which values changed. */ int inode_update_timestamps(struct inode *inode, int flags) { int updated = 0; struct timespec64 now; if (flags & (S_MTIME|S_CTIME|S_VERSION)) { struct timespec64 ctime = inode_get_ctime(inode); struct timespec64 mtime = inode_get_mtime(inode); now = inode_set_ctime_current(inode); if (!timespec64_equal(&now, &ctime)) updated |= S_CTIME; if (!timespec64_equal(&now, &mtime)) { inode_set_mtime_to_ts(inode, now); updated |= S_MTIME; } if (IS_I_VERSION(inode) && inode_maybe_inc_iversion(inode, updated)) updated |= S_VERSION; } else { now = current_time(inode); } if (flags & S_ATIME) { struct timespec64 atime = inode_get_atime(inode); if (!timespec64_equal(&now, &atime)) { inode_set_atime_to_ts(inode, now); updated |= S_ATIME; } } return updated; } EXPORT_SYMBOL(inode_update_timestamps); /** * generic_update_time - update the timestamps on the inode * @inode: inode to be updated * @flags: S_* flags that needed to be updated * * The update_time function is called when an inode's timestamps need to be * updated for a read or write operation. In the case where any of S_MTIME, S_CTIME, * or S_VERSION need to be updated we attempt to update all three of them. S_ATIME * updates can be handled done independently of the rest. * * Returns a S_* mask indicating which fields were updated. */ int generic_update_time(struct inode *inode, int flags) { int updated = inode_update_timestamps(inode, flags); int dirty_flags = 0; if (updated & (S_ATIME|S_MTIME|S_CTIME)) dirty_flags = inode->i_sb->s_flags & SB_LAZYTIME ? I_DIRTY_TIME : I_DIRTY_SYNC; if (updated & S_VERSION) dirty_flags |= I_DIRTY_SYNC; __mark_inode_dirty(inode, dirty_flags); return updated; } EXPORT_SYMBOL(generic_update_time); /* * This does the actual work of updating an inodes time or version. Must have * had called mnt_want_write() before calling this. */ int inode_update_time(struct inode *inode, int flags) { if (inode->i_op->update_time) return inode->i_op->update_time(inode, flags); generic_update_time(inode, flags); return 0; } EXPORT_SYMBOL(inode_update_time); /** * atime_needs_update - update the access time * @path: the &struct path to update * @inode: inode to update * * Update the accessed time on an inode and mark it for writeback. * This function automatically handles read only file systems and media, * as well as the "noatime" flag and inode specific "noatime" markers. */ bool atime_needs_update(const struct path *path, struct inode *inode) { struct vfsmount *mnt = path->mnt; struct timespec64 now, atime; if (inode->i_flags & S_NOATIME) return false; /* Atime updates will likely cause i_uid and i_gid to be written * back improprely if their true value is unknown to the vfs. */ if (HAS_UNMAPPED_ID(mnt_idmap(mnt), inode)) return false; if (IS_NOATIME(inode)) return false; if ((inode->i_sb->s_flags & SB_NODIRATIME) && S_ISDIR(inode->i_mode)) return false; if (mnt->mnt_flags & MNT_NOATIME) return false; if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)) return false; now = current_time(inode); if (!relatime_need_update(mnt, inode, now)) return false; atime = inode_get_atime(inode); if (timespec64_equal(&atime, &now)) return false; return true; } void touch_atime(const struct path *path) { struct vfsmount *mnt = path->mnt; struct inode *inode = d_inode(path->dentry); if (!atime_needs_update(path, inode)) return; if (!sb_start_write_trylock(inode->i_sb)) return; if (mnt_get_write_access(mnt) != 0) goto skip_update; /* * File systems can error out when updating inodes if they need to * allocate new space to modify an inode (such is the case for * Btrfs), but since we touch atime while walking down the path we * really don't care if we failed to update the atime of the file, * so just ignore the return value. * We may also fail on filesystems that have the ability to make parts * of the fs read only, e.g. subvolumes in Btrfs. */ inode_update_time(inode, S_ATIME); mnt_put_write_access(mnt); skip_update: sb_end_write(inode->i_sb); } EXPORT_SYMBOL(touch_atime); /* * Return mask of changes for notify_change() that need to be done as a * response to write or truncate. Return 0 if nothing has to be changed. * Negative value on error (change should be denied). */ int dentry_needs_remove_privs(struct mnt_idmap *idmap, struct dentry *dentry) { struct inode *inode = d_inode(dentry); int mask = 0; int ret; if (IS_NOSEC(inode)) return 0; mask = setattr_should_drop_suidgid(idmap, inode); ret = security_inode_need_killpriv(dentry); if (ret < 0) return ret; if (ret) mask |= ATTR_KILL_PRIV; return mask; } static int __remove_privs(struct mnt_idmap *idmap, struct dentry *dentry, int kill) { struct iattr newattrs; newattrs.ia_valid = ATTR_FORCE | kill; /* * Note we call this on write, so notify_change will not * encounter any conflicting delegations: */ return notify_change(idmap, dentry, &newattrs, NULL); } int file_remove_privs_flags(struct file *file, unsigned int flags) { struct dentry *dentry = file_dentry(file); struct inode *inode = file_inode(file); int error = 0; int kill; if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0; kill = dentry_needs_remove_privs(file_mnt_idmap(file), dentry); if (kill < 0) return kill; if (kill) { if (flags & IOCB_NOWAIT) return -EAGAIN; error = __remove_privs(file_mnt_idmap(file), dentry, kill); } if (!error) inode_has_no_xattr(inode); return error; } EXPORT_SYMBOL_GPL(file_remove_privs_flags); /** * file_remove_privs - remove special file privileges (suid, capabilities) * @file: file to remove privileges from * * When file is modified by a write or truncation ensure that special * file privileges are removed. * * Return: 0 on success, negative errno on failure. */ int file_remove_privs(struct file *file) { return file_remove_privs_flags(file, 0); } EXPORT_SYMBOL(file_remove_privs); static int inode_needs_update_time(struct inode *inode) { int sync_it = 0; struct timespec64 now = current_time(inode); struct timespec64 ts; /* First try to exhaust all avenues to not sync */ if (IS_NOCMTIME(inode)) return 0; ts = inode_get_mtime(inode); if (!timespec64_equal(&ts, &now)) sync_it = S_MTIME; ts = inode_get_ctime(inode); if (!timespec64_equal(&ts, &now)) sync_it |= S_CTIME; if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode)) sync_it |= S_VERSION; return sync_it; } static int __file_update_time(struct file *file, int sync_mode) { int ret = 0; struct inode *inode = file_inode(file); /* try to update time settings */ if (!mnt_get_write_access_file(file)) { ret = inode_update_time(inode, sync_mode); mnt_put_write_access_file(file); } return ret; } /** * file_update_time - update mtime and ctime time * @file: file accessed * * Update the mtime and ctime members of an inode and mark the inode for * writeback. Note that this function is meant exclusively for usage in * the file write path of filesystems, and filesystems may choose to * explicitly ignore updates via this function with the _NOCMTIME inode * flag, e.g. for network filesystem where these imestamps are handled * by the server. This can return an error for file systems who need to * allocate space in order to update an inode. * * Return: 0 on success, negative errno on failure. */ int file_update_time(struct file *file) { int ret; struct inode *inode = file_inode(file); ret = inode_needs_update_time(inode); if (ret <= 0) return ret; return __file_update_time(file, ret); } EXPORT_SYMBOL(file_update_time); /** * file_modified_flags - handle mandated vfs changes when modifying a file * @file: file that was modified * @flags: kiocb flags * * When file has been modified ensure that special * file privileges are removed and time settings are updated. * * If IOCB_NOWAIT is set, special file privileges will not be removed and * time settings will not be updated. It will return -EAGAIN. * * Context: Caller must hold the file's inode lock. * * Return: 0 on success, negative errno on failure. */ static int file_modified_flags(struct file *file, int flags) { int ret; struct inode *inode = file_inode(file); /* * Clear the security bits if the process is not being run by root. * This keeps people from modifying setuid and setgid binaries. */ ret = file_remove_privs_flags(file, flags); if (ret) return ret; if (unlikely(file->f_mode & FMODE_NOCMTIME)) return 0; ret = inode_needs_update_time(inode); if (ret <= 0) return ret; if (flags & IOCB_NOWAIT) return -EAGAIN; return __file_update_time(file, ret); } /** * file_modified - handle mandated vfs changes when modifying a file * @file: file that was modified * * When file has been modified ensure that special * file privileges are removed and time settings are updated. * * Context: Caller must hold the file's inode lock. * * Return: 0 on success, negative errno on failure. */ int file_modified(struct file *file) { return file_modified_flags(file, 0); } EXPORT_SYMBOL(file_modified); /** * kiocb_modified - handle mandated vfs changes when modifying a file * @iocb: iocb that was modified * * When file has been modified ensure that special * file privileges are removed and time settings are updated. * * Context: Caller must hold the file's inode lock. * * Return: 0 on success, negative errno on failure. */ int kiocb_modified(struct kiocb *iocb) { return file_modified_flags(iocb->ki_filp, iocb->ki_flags); } EXPORT_SYMBOL_GPL(kiocb_modified); int inode_needs_sync(struct inode *inode) { if (IS_SYNC(inode)) return 1; if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode)) return 1; return 0; } EXPORT_SYMBOL(inode_needs_sync); /* * If we try to find an inode in the inode hash while it is being * deleted, we have to wait until the filesystem completes its * deletion before reporting that it isn't found. This function waits * until the deletion _might_ have completed. Callers are responsible * to recheck inode state. * * It doesn't matter if I_NEW is not set initially, a call to * wake_up_bit(&inode->i_state, __I_NEW) after removing from the hash list * will DTRT. */ static void __wait_on_freeing_inode(struct inode *inode) { wait_queue_head_t *wq; DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW); wq = bit_waitqueue(&inode->i_state, __I_NEW); prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); schedule(); finish_wait(wq, &wait.wq_entry); spin_lock(&inode_hash_lock); } static __initdata unsigned long ihash_entries; static int __init set_ihash_entries(char *str) { if (!str) return 0; ihash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("ihash_entries=", set_ihash_entries); /* * Initialize the waitqueues and inode hash table. */ void __init inode_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; inode_hashtable = alloc_large_system_hash("Inode-cache", sizeof(struct hlist_head), ihash_entries, 14, HASH_EARLY | HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); } void __init inode_init(void) { /* inode slab cache */ inode_cachep = kmem_cache_create("inode_cache", sizeof(struct inode), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| SLAB_ACCOUNT), init_once); /* Hash may have been set up in inode_init_early */ if (!hashdist) return; inode_hashtable = alloc_large_system_hash("Inode-cache", sizeof(struct hlist_head), ihash_entries, 14, HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); } void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev) { inode->i_mode = mode; if (S_ISCHR(mode)) { inode->i_fop = &def_chr_fops; inode->i_rdev = rdev; } else if (S_ISBLK(mode)) { if (IS_ENABLED(CONFIG_BLOCK)) inode->i_fop = &def_blk_fops; inode->i_rdev = rdev; } else if (S_ISFIFO(mode)) inode->i_fop = &pipefifo_fops; else if (S_ISSOCK(mode)) ; /* leave it no_open_fops */ else printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o) for" " inode %s:%lu\n", mode, inode->i_sb->s_id, inode->i_ino); } EXPORT_SYMBOL(init_special_inode); /** * inode_init_owner - Init uid,gid,mode for new inode according to posix standards * @idmap: idmap of the mount the inode was created from * @inode: New inode * @dir: Directory inode * @mode: mode of the new inode * * If the inode has been created through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions * and initializing i_uid and i_gid. On non-idmapped mounts or if permission * checking is to be performed on the raw inode simply pass @nop_mnt_idmap. */ void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, const struct inode *dir, umode_t mode) { inode_fsuid_set(inode, idmap); if (dir && dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; /* Directories are special, and always inherit S_ISGID */ if (S_ISDIR(mode)) mode |= S_ISGID; } else inode_fsgid_set(inode, idmap); inode->i_mode = mode; } EXPORT_SYMBOL(inode_init_owner); /** * inode_owner_or_capable - check current task permissions to inode * @idmap: idmap of the mount the inode was found from * @inode: inode being checked * * Return true if current either has CAP_FOWNER in a namespace with the * inode owner uid mapped, or owns the file. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode) { vfsuid_t vfsuid; struct user_namespace *ns; vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) return true; ns = current_user_ns(); if (vfsuid_has_mapping(ns, vfsuid) && ns_capable(ns, CAP_FOWNER)) return true; return false; } EXPORT_SYMBOL(inode_owner_or_capable); /* * Direct i/o helper functions */ static void __inode_dio_wait(struct inode *inode) { wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP); DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP); do { prepare_to_wait(wq, &q.wq_entry, TASK_UNINTERRUPTIBLE); if (atomic_read(&inode->i_dio_count)) schedule(); } while (atomic_read(&inode->i_dio_count)); finish_wait(wq, &q.wq_entry); } /** * inode_dio_wait - wait for outstanding DIO requests to finish * @inode: inode to wait for * * Waits for all pending direct I/O requests to finish so that we can * proceed with a truncate or equivalent operation. * * Must be called under a lock that serializes taking new references * to i_dio_count, usually by inode->i_mutex. */ void inode_dio_wait(struct inode *inode) { if (atomic_read(&inode->i_dio_count)) __inode_dio_wait(inode); } EXPORT_SYMBOL(inode_dio_wait); /* * inode_set_flags - atomically set some inode flags * * Note: the caller should be holding i_mutex, or else be sure that * they have exclusive access to the inode structure (i.e., while the * inode is being instantiated). The reason for the cmpxchg() loop * --- which wouldn't be necessary if all code paths which modify * i_flags actually followed this rule, is that there is at least one * code path which doesn't today so we use cmpxchg() out of an abundance * of caution. * * In the long run, i_mutex is overkill, and we should probably look * at using the i_lock spinlock to protect i_flags, and then make sure * it is so documented in include/linux/fs.h and that all code follows * the locking convention!! */ void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask) { WARN_ON_ONCE(flags & ~mask); set_mask_bits(&inode->i_flags, mask, flags); } EXPORT_SYMBOL(inode_set_flags); void inode_nohighmem(struct inode *inode) { mapping_set_gfp_mask(inode->i_mapping, GFP_USER); } EXPORT_SYMBOL(inode_nohighmem); /** * timestamp_truncate - Truncate timespec to a granularity * @t: Timespec * @inode: inode being updated * * Truncate a timespec to the granularity supported by the fs * containing the inode. Always rounds down. gran must * not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns). */ struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned int gran = sb->s_time_gran; t.tv_sec = clamp(t.tv_sec, sb->s_time_min, sb->s_time_max); if (unlikely(t.tv_sec == sb->s_time_max || t.tv_sec == sb->s_time_min)) t.tv_nsec = 0; /* Avoid division in the common cases 1 ns and 1 s. */ if (gran == 1) ; /* nothing */ else if (gran == NSEC_PER_SEC) t.tv_nsec = 0; else if (gran > 1 && gran < NSEC_PER_SEC) t.tv_nsec -= t.tv_nsec % gran; else WARN(1, "invalid file time granularity: %u", gran); return t; } EXPORT_SYMBOL(timestamp_truncate); /** * current_time - Return FS time * @inode: inode. * * Return the current time truncated to the time granularity supported by * the fs. * * Note that inode and inode->sb cannot be NULL. * Otherwise, the function warns and returns time without truncation. */ struct timespec64 current_time(struct inode *inode) { struct timespec64 now; ktime_get_coarse_real_ts64(&now); return timestamp_truncate(now, inode); } EXPORT_SYMBOL(current_time); /** * inode_set_ctime_current - set the ctime to current_time * @inode: inode * * Set the inode->i_ctime to the current value for the inode. Returns * the current value that was assigned to i_ctime. */ struct timespec64 inode_set_ctime_current(struct inode *inode) { struct timespec64 now = current_time(inode); inode_set_ctime_to_ts(inode, now); return now; } EXPORT_SYMBOL(inode_set_ctime_current); /** * in_group_or_capable - check whether caller is CAP_FSETID privileged * @idmap: idmap of the mount @inode was found from * @inode: inode to check * @vfsgid: the new/current vfsgid of @inode * * Check wether @vfsgid is in the caller's group list or if the caller is * privileged with CAP_FSETID over @inode. This can be used to determine * whether the setgid bit can be kept or must be dropped. * * Return: true if the caller is sufficiently privileged, false if not. */ bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid) { if (vfsgid_in_group_p(vfsgid)) return true; if (capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID)) return true; return false; } /** * mode_strip_sgid - handle the sgid bit for non-directories * @idmap: idmap of the mount the inode was created from * @dir: parent directory inode * @mode: mode of the file to be created in @dir * * If the @mode of the new file has both the S_ISGID and S_IXGRP bit * raised and @dir has the S_ISGID bit raised ensure that the caller is * either in the group of the parent directory or they have CAP_FSETID * in their user namespace and are privileged over the parent directory. * In all other cases, strip the S_ISGID bit from @mode. * * Return: the new mode to use for the file */ umode_t mode_strip_sgid(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode) { if ((mode & (S_ISGID | S_IXGRP)) != (S_ISGID | S_IXGRP)) return mode; if (S_ISDIR(mode) || !dir || !(dir->i_mode & S_ISGID)) return mode; if (in_group_or_capable(idmap, dir, i_gid_into_vfsgid(idmap, dir))) return mode; return mode & ~S_ISGID; } EXPORT_SYMBOL(mode_strip_sgid); |
| 233 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TASK_WORK_H #define _LINUX_TASK_WORK_H #include <linux/list.h> #include <linux/sched.h> typedef void (*task_work_func_t)(struct callback_head *); static inline void init_task_work(struct callback_head *twork, task_work_func_t func) { twork->func = func; } enum task_work_notify_mode { TWA_NONE, TWA_RESUME, TWA_SIGNAL, TWA_SIGNAL_NO_IPI, }; static inline bool task_work_pending(struct task_struct *task) { return READ_ONCE(task->task_works); } int task_work_add(struct task_struct *task, struct callback_head *twork, enum task_work_notify_mode mode); struct callback_head *task_work_cancel_match(struct task_struct *task, bool (*match)(struct callback_head *, void *data), void *data); struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t); void task_work_run(void); static inline void exit_task_work(struct task_struct *task) { task_work_run(); } #endif /* _LINUX_TASK_WORK_H */ |
| 14 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * procfs namespace bits */ #ifndef _LINUX_PROC_NS_H #define _LINUX_PROC_NS_H #include <linux/ns_common.h> struct pid_namespace; struct nsset; struct path; struct task_struct; struct inode; struct proc_ns_operations { const char *name; const char *real_ns_name; int type; struct ns_common *(*get)(struct task_struct *task); void (*put)(struct ns_common *ns); int (*install)(struct nsset *nsset, struct ns_common *ns); struct user_namespace *(*owner)(struct ns_common *ns); struct ns_common *(*get_parent)(struct ns_common *ns); } __randomize_layout; extern const struct proc_ns_operations netns_operations; extern const struct proc_ns_operations utsns_operations; extern const struct proc_ns_operations ipcns_operations; extern const struct proc_ns_operations pidns_operations; extern const struct proc_ns_operations pidns_for_children_operations; extern const struct proc_ns_operations userns_operations; extern const struct proc_ns_operations mntns_operations; extern const struct proc_ns_operations cgroupns_operations; extern const struct proc_ns_operations timens_operations; extern const struct proc_ns_operations timens_for_children_operations; /* * We always define these enumerators */ enum { PROC_ROOT_INO = 1, PROC_IPC_INIT_INO = 0xEFFFFFFFU, PROC_UTS_INIT_INO = 0xEFFFFFFEU, PROC_USER_INIT_INO = 0xEFFFFFFDU, PROC_PID_INIT_INO = 0xEFFFFFFCU, PROC_CGROUP_INIT_INO = 0xEFFFFFFBU, PROC_TIME_INIT_INO = 0xEFFFFFFAU, }; #ifdef CONFIG_PROC_FS extern int proc_alloc_inum(unsigned int *pino); extern void proc_free_inum(unsigned int inum); #else /* CONFIG_PROC_FS */ static inline int proc_alloc_inum(unsigned int *inum) { *inum = 1; return 0; } static inline void proc_free_inum(unsigned int inum) {} #endif /* CONFIG_PROC_FS */ static inline int ns_alloc_inum(struct ns_common *ns) { WRITE_ONCE(ns->stashed, NULL); return proc_alloc_inum(&ns->inum); } #define ns_free_inum(ns) proc_free_inum((ns)->inum) #define get_proc_ns(inode) ((struct ns_common *)(inode)->i_private) extern int ns_get_path(struct path *path, struct task_struct *task, const struct proc_ns_operations *ns_ops); typedef struct ns_common *ns_get_path_helper_t(void *); extern int ns_get_path_cb(struct path *path, ns_get_path_helper_t ns_get_cb, void *private_data); extern bool ns_match(const struct ns_common *ns, dev_t dev, ino_t ino); extern int ns_get_name(char *buf, size_t size, struct task_struct *task, const struct proc_ns_operations *ns_ops); extern void nsfs_init(void); #endif /* _LINUX_PROC_NS_H */ |
| 28 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _TRACE_SYSCALL_H #define _TRACE_SYSCALL_H #include <linux/tracepoint.h> #include <linux/unistd.h> #include <linux/trace_events.h> #include <linux/thread_info.h> #include <asm/ptrace.h> /* * A syscall entry in the ftrace syscalls array. * * @name: name of the syscall * @syscall_nr: number of the syscall * @nb_args: number of parameters it takes * @types: list of types as strings * @args: list of args as strings (args[i] matches types[i]) * @enter_fields: list of fields for syscall_enter trace event * @enter_event: associated syscall_enter trace event * @exit_event: associated syscall_exit trace event */ struct syscall_metadata { const char *name; int syscall_nr; int nb_args; const char **types; const char **args; struct list_head enter_fields; struct trace_event_call *enter_event; struct trace_event_call *exit_event; }; #if defined(CONFIG_TRACEPOINTS) && defined(CONFIG_HAVE_SYSCALL_TRACEPOINTS) static inline void syscall_tracepoint_update(struct task_struct *p) { if (test_syscall_work(SYSCALL_TRACEPOINT)) set_task_syscall_work(p, SYSCALL_TRACEPOINT); else clear_task_syscall_work(p, SYSCALL_TRACEPOINT); } #else static inline void syscall_tracepoint_update(struct task_struct *p) { } #endif #endif /* _TRACE_SYSCALL_H */ |
| 13 13 3 3 3 3 12 5 1 2 1 1 12 11 3 2 6 7 5 3 2 3 2 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * Timer control routines * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include "seq_oss_timer.h" #include "seq_oss_event.h" #include <sound/seq_oss_legacy.h> #include <linux/slab.h> /* */ #define MIN_OSS_TEMPO 8 #define MAX_OSS_TEMPO 360 #define MIN_OSS_TIMEBASE 1 #define MAX_OSS_TIMEBASE 1000 /* */ static void calc_alsa_tempo(struct seq_oss_timer *timer); static int send_timer_event(struct seq_oss_devinfo *dp, int type, int value); /* * create and register a new timer. * if queue is not started yet, start it. */ struct seq_oss_timer * snd_seq_oss_timer_new(struct seq_oss_devinfo *dp) { struct seq_oss_timer *rec; rec = kzalloc(sizeof(*rec), GFP_KERNEL); if (rec == NULL) return NULL; rec->dp = dp; rec->cur_tick = 0; rec->realtime = 0; rec->running = 0; rec->oss_tempo = 60; rec->oss_timebase = 100; calc_alsa_tempo(rec); return rec; } /* * delete timer. * if no more timer exists, stop the queue. */ void snd_seq_oss_timer_delete(struct seq_oss_timer *rec) { if (rec) { snd_seq_oss_timer_stop(rec); kfree(rec); } } /* * process one timing event * return 1 : event proceseed -- skip this event * 0 : not a timer event -- enqueue this event */ int snd_seq_oss_process_timer_event(struct seq_oss_timer *rec, union evrec *ev) { abstime_t parm = ev->t.time; if (ev->t.code == EV_TIMING) { switch (ev->t.cmd) { case TMR_WAIT_REL: parm += rec->cur_tick; rec->realtime = 0; fallthrough; case TMR_WAIT_ABS: if (parm == 0) { rec->realtime = 1; } else if (parm >= rec->cur_tick) { rec->realtime = 0; rec->cur_tick = parm; } return 1; /* skip this event */ case TMR_START: snd_seq_oss_timer_start(rec); return 1; } } else if (ev->s.code == SEQ_WAIT) { /* time = from 1 to 3 bytes */ parm = (ev->echo >> 8) & 0xffffff; if (parm > rec->cur_tick) { /* set next event time */ rec->cur_tick = parm; rec->realtime = 0; } return 1; } return 0; } /* * convert tempo units */ static void calc_alsa_tempo(struct seq_oss_timer *timer) { timer->tempo = (60 * 1000000) / timer->oss_tempo; timer->ppq = timer->oss_timebase; } /* * dispatch a timer event */ static int send_timer_event(struct seq_oss_devinfo *dp, int type, int value) { struct snd_seq_event ev; memset(&ev, 0, sizeof(ev)); ev.type = type; ev.source.client = dp->cseq; ev.source.port = 0; ev.dest.client = SNDRV_SEQ_CLIENT_SYSTEM; ev.dest.port = SNDRV_SEQ_PORT_SYSTEM_TIMER; ev.queue = dp->queue; ev.data.queue.queue = dp->queue; ev.data.queue.param.value = value; return snd_seq_kernel_client_dispatch(dp->cseq, &ev, 1, 0); } /* * set queue tempo and start queue */ int snd_seq_oss_timer_start(struct seq_oss_timer *timer) { struct seq_oss_devinfo *dp = timer->dp; struct snd_seq_queue_tempo tmprec; if (timer->running) snd_seq_oss_timer_stop(timer); memset(&tmprec, 0, sizeof(tmprec)); tmprec.queue = dp->queue; tmprec.ppq = timer->ppq; tmprec.tempo = timer->tempo; snd_seq_set_queue_tempo(dp->cseq, &tmprec); send_timer_event(dp, SNDRV_SEQ_EVENT_START, 0); timer->running = 1; timer->cur_tick = 0; return 0; } /* * stop queue */ int snd_seq_oss_timer_stop(struct seq_oss_timer *timer) { if (! timer->running) return 0; send_timer_event(timer->dp, SNDRV_SEQ_EVENT_STOP, 0); timer->running = 0; return 0; } /* * continue queue */ int snd_seq_oss_timer_continue(struct seq_oss_timer *timer) { if (timer->running) return 0; send_timer_event(timer->dp, SNDRV_SEQ_EVENT_CONTINUE, 0); timer->running = 1; return 0; } /* * change queue tempo */ int snd_seq_oss_timer_tempo(struct seq_oss_timer *timer, int value) { if (value < MIN_OSS_TEMPO) value = MIN_OSS_TEMPO; else if (value > MAX_OSS_TEMPO) value = MAX_OSS_TEMPO; timer->oss_tempo = value; calc_alsa_tempo(timer); if (timer->running) send_timer_event(timer->dp, SNDRV_SEQ_EVENT_TEMPO, timer->tempo); return 0; } /* * ioctls */ int snd_seq_oss_timer_ioctl(struct seq_oss_timer *timer, unsigned int cmd, int __user *arg) { int value; if (cmd == SNDCTL_SEQ_CTRLRATE) { /* if *arg == 0, just return the current rate */ if (get_user(value, arg)) return -EFAULT; if (value) return -EINVAL; value = ((timer->oss_tempo * timer->oss_timebase) + 30) / 60; return put_user(value, arg) ? -EFAULT : 0; } if (timer->dp->seq_mode == SNDRV_SEQ_OSS_MODE_SYNTH) return 0; switch (cmd) { case SNDCTL_TMR_START: return snd_seq_oss_timer_start(timer); case SNDCTL_TMR_STOP: return snd_seq_oss_timer_stop(timer); case SNDCTL_TMR_CONTINUE: return snd_seq_oss_timer_continue(timer); case SNDCTL_TMR_TEMPO: if (get_user(value, arg)) return -EFAULT; return snd_seq_oss_timer_tempo(timer, value); case SNDCTL_TMR_TIMEBASE: if (get_user(value, arg)) return -EFAULT; if (value < MIN_OSS_TIMEBASE) value = MIN_OSS_TIMEBASE; else if (value > MAX_OSS_TIMEBASE) value = MAX_OSS_TIMEBASE; timer->oss_timebase = value; calc_alsa_tempo(timer); return 0; case SNDCTL_TMR_METRONOME: case SNDCTL_TMR_SELECT: case SNDCTL_TMR_SOURCE: /* not supported */ return 0; } return 0; } |
| 2 2 2 2 1 1 1 43 44 44 1 1 1 44 5 5 194 24 195 5 4 24 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/init.h> #include <linux/module.h> #include <linux/netfilter.h> #include <net/flow_offload.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_offload.h> #include <net/pkt_cls.h> static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions) { struct nft_flow_rule *flow; flow = kzalloc(sizeof(struct nft_flow_rule), GFP_KERNEL); if (!flow) return NULL; flow->rule = flow_rule_alloc(num_actions); if (!flow->rule) { kfree(flow); return NULL; } flow->rule->match.dissector = &flow->match.dissector; flow->rule->match.mask = &flow->match.mask; flow->rule->match.key = &flow->match.key; return flow; } void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, enum flow_dissector_key_id addr_type) { struct nft_flow_match *match = &flow->match; struct nft_flow_key *mask = &match->mask; struct nft_flow_key *key = &match->key; if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL)) return; key->control.addr_type = addr_type; mask->control.addr_type = 0xffff; match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL); match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL] = offsetof(struct nft_flow_key, control); } struct nft_offload_ethertype { __be16 value; __be16 mask; }; static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow) { struct nft_flow_match *match = &flow->match; struct nft_offload_ethertype ethertype = { .value = match->key.basic.n_proto, .mask = match->mask.basic.n_proto, }; if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) && (match->key.vlan.vlan_tpid == htons(ETH_P_8021Q) || match->key.vlan.vlan_tpid == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.cvlan.vlan_tpid; match->mask.basic.n_proto = match->mask.cvlan.vlan_tpid; match->key.cvlan.vlan_tpid = match->key.vlan.vlan_tpid; match->mask.cvlan.vlan_tpid = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; match->mask.vlan.vlan_tpid = ethertype.mask; match->dissector.offset[FLOW_DISSECTOR_KEY_CVLAN] = offsetof(struct nft_flow_key, cvlan); match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN); } else if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) && (match->key.basic.n_proto == htons(ETH_P_8021Q) || match->key.basic.n_proto == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.vlan.vlan_tpid; match->mask.basic.n_proto = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; match->mask.vlan.vlan_tpid = ethertype.mask; match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] = offsetof(struct nft_flow_key, vlan); match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_VLAN); } } struct nft_flow_rule *nft_flow_rule_create(struct net *net, const struct nft_rule *rule) { struct nft_offload_ctx *ctx; struct nft_flow_rule *flow; int num_actions = 0, err; struct nft_expr *expr; expr = nft_expr_first(rule); while (nft_expr_more(rule, expr)) { if (expr->ops->offload_action && expr->ops->offload_action(expr)) num_actions++; expr = nft_expr_next(expr); } if (num_actions == 0) return ERR_PTR(-EOPNOTSUPP); flow = nft_flow_rule_alloc(num_actions); if (!flow) return ERR_PTR(-ENOMEM); expr = nft_expr_first(rule); ctx = kzalloc(sizeof(struct nft_offload_ctx), GFP_KERNEL); if (!ctx) { err = -ENOMEM; goto err_out; } ctx->net = net; ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; while (nft_expr_more(rule, expr)) { if (!expr->ops->offload) { err = -EOPNOTSUPP; goto err_out; } err = expr->ops->offload(ctx, flow, expr); if (err < 0) goto err_out; expr = nft_expr_next(expr); } nft_flow_rule_transfer_vlan(ctx, flow); flow->proto = ctx->dep.l3num; kfree(ctx); return flow; err_out: kfree(ctx); nft_flow_rule_destroy(flow); return ERR_PTR(err); } void nft_flow_rule_destroy(struct nft_flow_rule *flow) { struct flow_action_entry *entry; int i; flow_action_for_each(i, entry, &flow->rule->action) { switch (entry->id) { case FLOW_ACTION_REDIRECT: case FLOW_ACTION_MIRRED: dev_put(entry->dev); break; default: break; } } kfree(flow->rule); kfree(flow); } void nft_offload_set_dependency(struct nft_offload_ctx *ctx, enum nft_offload_dep_type type) { ctx->dep.type = type; } void nft_offload_update_dependency(struct nft_offload_ctx *ctx, const void *data, u32 len) { switch (ctx->dep.type) { case NFT_OFFLOAD_DEP_NETWORK: WARN_ON(len != sizeof(__u16)); memcpy(&ctx->dep.l3num, data, sizeof(__u16)); break; case NFT_OFFLOAD_DEP_TRANSPORT: WARN_ON(len != sizeof(__u8)); memcpy(&ctx->dep.protonum, data, sizeof(__u8)); break; default: break; } ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; } static void nft_flow_offload_common_init(struct flow_cls_common_offload *common, __be16 proto, int priority, struct netlink_ext_ack *extack) { common->protocol = proto; common->prio = priority; common->extack = extack; } static int nft_setup_cb_call(enum tc_setup_type type, void *type_data, struct list_head *cb_list) { struct flow_block_cb *block_cb; int err; list_for_each_entry(block_cb, cb_list, list) { err = block_cb->cb(type, type_data, block_cb->cb_priv); if (err < 0) return err; } return 0; } static int nft_chain_offload_priority(const struct nft_base_chain *basechain) { if (basechain->ops.priority <= 0 || basechain->ops.priority > USHRT_MAX) return -1; return 0; } bool nft_chain_offload_support(const struct nft_base_chain *basechain) { struct net_device *dev; struct nft_hook *hook; if (nft_chain_offload_priority(basechain) < 0) return false; list_for_each_entry(hook, &basechain->hook_list, list) { if (hook->ops.pf != NFPROTO_NETDEV || hook->ops.hooknum != NF_NETDEV_INGRESS) return false; dev = hook->ops.dev; if (!dev->netdev_ops->ndo_setup_tc && !flow_indr_dev_exists()) return false; } return true; } static void nft_flow_cls_offload_setup(struct flow_cls_offload *cls_flow, const struct nft_base_chain *basechain, const struct nft_rule *rule, const struct nft_flow_rule *flow, struct netlink_ext_ack *extack, enum flow_cls_command command) { __be16 proto = ETH_P_ALL; memset(cls_flow, 0, sizeof(*cls_flow)); if (flow) proto = flow->proto; nft_flow_offload_common_init(&cls_flow->common, proto, basechain->ops.priority, extack); cls_flow->command = command; cls_flow->cookie = (unsigned long) rule; if (flow) cls_flow->rule = flow->rule; } static int nft_flow_offload_cmd(const struct nft_chain *chain, const struct nft_rule *rule, struct nft_flow_rule *flow, enum flow_cls_command command, struct flow_cls_offload *cls_flow) { struct netlink_ext_ack extack = {}; struct nft_base_chain *basechain; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); nft_flow_cls_offload_setup(cls_flow, basechain, rule, flow, &extack, command); return nft_setup_cb_call(TC_SETUP_CLSFLOWER, cls_flow, &basechain->flow_block.cb_list); } static int nft_flow_offload_rule(const struct nft_chain *chain, struct nft_rule *rule, struct nft_flow_rule *flow, enum flow_cls_command command) { struct flow_cls_offload cls_flow; return nft_flow_offload_cmd(chain, rule, flow, command, &cls_flow); } int nft_flow_rule_stats(const struct nft_chain *chain, const struct nft_rule *rule) { struct flow_cls_offload cls_flow = {}; struct nft_expr *expr, *next; int err; err = nft_flow_offload_cmd(chain, rule, NULL, FLOW_CLS_STATS, &cls_flow); if (err < 0) return err; nft_rule_for_each_expr(expr, next, rule) { if (expr->ops->offload_stats) expr->ops->offload_stats(expr, &cls_flow.stats); } return 0; } static int nft_flow_offload_bind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { list_splice(&bo->cb_list, &basechain->flow_block.cb_list); return 0; } static int nft_flow_offload_unbind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { struct flow_block_cb *block_cb, *next; struct flow_cls_offload cls_flow; struct netlink_ext_ack extack; struct nft_chain *chain; struct nft_rule *rule; chain = &basechain->chain; list_for_each_entry(rule, &chain->rules, list) { memset(&extack, 0, sizeof(extack)); nft_flow_cls_offload_setup(&cls_flow, basechain, rule, NULL, &extack, FLOW_CLS_DESTROY); nft_setup_cb_call(TC_SETUP_CLSFLOWER, &cls_flow, &bo->cb_list); } list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) { list_del(&block_cb->list); flow_block_cb_free(block_cb); } return 0; } static int nft_block_setup(struct nft_base_chain *basechain, struct flow_block_offload *bo, enum flow_block_command cmd) { int err; switch (cmd) { case FLOW_BLOCK_BIND: err = nft_flow_offload_bind(bo, basechain); break; case FLOW_BLOCK_UNBIND: err = nft_flow_offload_unbind(bo, basechain); break; default: WARN_ON_ONCE(1); err = -EOPNOTSUPP; } return err; } static void nft_flow_block_offload_init(struct flow_block_offload *bo, struct net *net, enum flow_block_command cmd, struct nft_base_chain *basechain, struct netlink_ext_ack *extack) { memset(bo, 0, sizeof(*bo)); bo->net = net; bo->block = &basechain->flow_block; bo->command = cmd; bo->binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; bo->extack = extack; bo->cb_list_head = &basechain->flow_block.cb_list; INIT_LIST_HEAD(&bo->cb_list); } static int nft_block_offload_cmd(struct nft_base_chain *chain, struct net_device *dev, enum flow_block_command cmd) { struct netlink_ext_ack extack = {}; struct flow_block_offload bo; int err; nft_flow_block_offload_init(&bo, dev_net(dev), cmd, chain, &extack); err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); if (err < 0) return err; return nft_block_setup(chain, &bo, cmd); } static void nft_indr_block_cleanup(struct flow_block_cb *block_cb) { struct nft_base_chain *basechain = block_cb->indr.data; struct net_device *dev = block_cb->indr.dev; struct netlink_ext_ack extack = {}; struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct flow_block_offload bo; nft_flow_block_offload_init(&bo, dev_net(dev), FLOW_BLOCK_UNBIND, basechain, &extack); nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); nft_flow_offload_unbind(&bo, basechain); mutex_unlock(&nft_net->commit_mutex); } static int nft_indr_block_offload_cmd(struct nft_base_chain *basechain, struct net_device *dev, enum flow_block_command cmd) { struct netlink_ext_ack extack = {}; struct flow_block_offload bo; int err; nft_flow_block_offload_init(&bo, dev_net(dev), cmd, basechain, &extack); err = flow_indr_dev_setup_offload(dev, NULL, TC_SETUP_BLOCK, basechain, &bo, nft_indr_block_cleanup); if (err < 0) return err; if (list_empty(&bo.cb_list)) return -EOPNOTSUPP; return nft_block_setup(basechain, &bo, cmd); } static int nft_chain_offload_cmd(struct nft_base_chain *basechain, struct net_device *dev, enum flow_block_command cmd) { int err; if (dev->netdev_ops->ndo_setup_tc) err = nft_block_offload_cmd(basechain, dev, cmd); else err = nft_indr_block_offload_cmd(basechain, dev, cmd); return err; } static int nft_flow_block_chain(struct nft_base_chain *basechain, const struct net_device *this_dev, enum flow_block_command cmd) { struct net_device *dev; struct nft_hook *hook; int err, i = 0; list_for_each_entry(hook, &basechain->hook_list, list) { dev = hook->ops.dev; if (this_dev && this_dev != dev) continue; err = nft_chain_offload_cmd(basechain, dev, cmd); if (err < 0 && cmd == FLOW_BLOCK_BIND) { if (!this_dev) goto err_flow_block; return err; } i++; } return 0; err_flow_block: list_for_each_entry(hook, &basechain->hook_list, list) { if (i-- <= 0) break; dev = hook->ops.dev; nft_chain_offload_cmd(basechain, dev, FLOW_BLOCK_UNBIND); } return err; } static int nft_flow_offload_chain(struct nft_chain *chain, u8 *ppolicy, enum flow_block_command cmd) { struct nft_base_chain *basechain; u8 policy; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); policy = ppolicy ? *ppolicy : basechain->policy; /* Only default policy to accept is supported for now. */ if (cmd == FLOW_BLOCK_BIND && policy == NF_DROP) return -EOPNOTSUPP; return nft_flow_block_chain(basechain, NULL, cmd); } static void nft_flow_rule_offload_abort(struct net *net, struct nft_trans *trans) { struct nftables_pernet *nft_net = nft_pernet(net); int err = 0; list_for_each_entry_continue_reverse(trans, &nft_net->commit_list, list) { if (trans->ctx.family != NFPROTO_NETDEV) continue; switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) || nft_trans_chain_update(trans)) continue; err = nft_flow_offload_chain(trans->ctx.chain, NULL, FLOW_BLOCK_UNBIND); break; case NFT_MSG_DELCHAIN: if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_chain(trans->ctx.chain, NULL, FLOW_BLOCK_BIND); break; case NFT_MSG_NEWRULE: if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(trans->ctx.chain, nft_trans_rule(trans), NULL, FLOW_CLS_DESTROY); break; case NFT_MSG_DELRULE: if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(trans->ctx.chain, nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); break; } if (WARN_ON_ONCE(err)) break; } } int nft_flow_rule_offload_commit(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans; int err = 0; u8 policy; list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->ctx.family != NFPROTO_NETDEV) continue; switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) || nft_trans_chain_update(trans)) continue; policy = nft_trans_chain_policy(trans); err = nft_flow_offload_chain(trans->ctx.chain, &policy, FLOW_BLOCK_BIND); break; case NFT_MSG_DELCHAIN: if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) continue; policy = nft_trans_chain_policy(trans); err = nft_flow_offload_chain(trans->ctx.chain, &policy, FLOW_BLOCK_UNBIND); break; case NFT_MSG_NEWRULE: if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) continue; if (trans->ctx.flags & NLM_F_REPLACE || !(trans->ctx.flags & NLM_F_APPEND)) { err = -EOPNOTSUPP; break; } err = nft_flow_offload_rule(trans->ctx.chain, nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); break; case NFT_MSG_DELRULE: if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(trans->ctx.chain, nft_trans_rule(trans), NULL, FLOW_CLS_DESTROY); break; } if (err) { nft_flow_rule_offload_abort(net, trans); break; } } return err; } static struct nft_chain *__nft_offload_get_chain(const struct nftables_pernet *nft_net, struct net_device *dev) { struct nft_base_chain *basechain; struct nft_hook *hook, *found; const struct nft_table *table; struct nft_chain *chain; list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV) continue; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_base_chain(chain) || !(chain->flags & NFT_CHAIN_HW_OFFLOAD)) continue; found = NULL; basechain = nft_base_chain(chain); list_for_each_entry(hook, &basechain->hook_list, list) { if (hook->ops.dev != dev) continue; found = hook; break; } if (!found) continue; return chain; } } return NULL; } static int nft_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct nft_chain *chain; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); chain = __nft_offload_get_chain(nft_net, dev); if (chain) nft_flow_block_chain(nft_base_chain(chain), dev, FLOW_BLOCK_UNBIND); mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } static struct notifier_block nft_offload_netdev_notifier = { .notifier_call = nft_offload_netdev_event, }; int nft_offload_init(void) { return register_netdevice_notifier(&nft_offload_netdev_notifier); } void nft_offload_exit(void) { unregister_netdevice_notifier(&nft_offload_netdev_notifier); } |
| 2 2 2 7 1 7 7 7 7 7 7 7 2 2 5 5 5 4 5 4 4 4 4 4 4 4 4 4 4 4 4 3 7 40 38 39 4 39 39 39 39 4 4 4 3 2 2 2 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 1 8 2 8 8 8 8 43 46 81 4 4 4 4 13 13 13 13 77 68 78 63 63 63 63 62 2 2 63 63 39 22 2 33 2 2 34 2 2 40 40 12 33 29 29 29 29 29 29 3 2 2 2 1 4 4 3 3 4 4 3 4 3 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001-2003 International Business Machines, Corp. * Copyright (c) 2001 Intel Corp. * Copyright (c) 2001 Nokia, Inc. * Copyright (c) 2001 La Monte H.P. Yarroll * * This file is part of the SCTP kernel implementation * * These functions handle all input from the IP layer into SCTP. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Xingang Guo <xingang.guo@intel.com> * Jon Grimm <jgrimm@us.ibm.com> * Hui Huang <hui.huang@nokia.com> * Daisy Chang <daisyc@us.ibm.com> * Sridhar Samudrala <sri@us.ibm.com> * Ardelle Fan <ardelle.fan@intel.com> */ #include <linux/types.h> #include <linux/list.h> /* For struct list_head */ #include <linux/socket.h> #include <linux/ip.h> #include <linux/time.h> /* For struct timeval */ #include <linux/slab.h> #include <net/ip.h> #include <net/icmp.h> #include <net/snmp.h> #include <net/sock.h> #include <net/xfrm.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/checksum.h> #include <net/net_namespace.h> #include <linux/rhashtable.h> #include <net/sock_reuseport.h> /* Forward declarations for internal helpers. */ static int sctp_rcv_ootb(struct sk_buff *); static struct sctp_association *__sctp_rcv_lookup(struct net *net, struct sk_buff *skb, const union sctp_addr *paddr, const union sctp_addr *laddr, struct sctp_transport **transportp, int dif, int sdif); static struct sctp_endpoint *__sctp_rcv_lookup_endpoint( struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, const union sctp_addr *daddr, int dif, int sdif); static struct sctp_association *__sctp_lookup_association( struct net *net, const union sctp_addr *local, const union sctp_addr *peer, struct sctp_transport **pt, int dif, int sdif); static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb); /* Calculate the SCTP checksum of an SCTP packet. */ static inline int sctp_rcv_checksum(struct net *net, struct sk_buff *skb) { struct sctphdr *sh = sctp_hdr(skb); __le32 cmp = sh->checksum; __le32 val = sctp_compute_cksum(skb, 0); if (val != cmp) { /* CRC failure, dump it. */ __SCTP_INC_STATS(net, SCTP_MIB_CHECKSUMERRORS); return -1; } return 0; } /* * This is the routine which IP calls when receiving an SCTP packet. */ int sctp_rcv(struct sk_buff *skb) { struct sock *sk; struct sctp_association *asoc; struct sctp_endpoint *ep = NULL; struct sctp_ep_common *rcvr; struct sctp_transport *transport = NULL; struct sctp_chunk *chunk; union sctp_addr src; union sctp_addr dest; int family; struct sctp_af *af; struct net *net = dev_net(skb->dev); bool is_gso = skb_is_gso(skb) && skb_is_gso_sctp(skb); int dif, sdif; if (skb->pkt_type != PACKET_HOST) goto discard_it; __SCTP_INC_STATS(net, SCTP_MIB_INSCTPPACKS); /* If packet is too small to contain a single chunk, let's not * waste time on it anymore. */ if (skb->len < sizeof(struct sctphdr) + sizeof(struct sctp_chunkhdr) + skb_transport_offset(skb)) goto discard_it; /* If the packet is fragmented and we need to do crc checking, * it's better to just linearize it otherwise crc computing * takes longer. */ if ((!is_gso && skb_linearize(skb)) || !pskb_may_pull(skb, sizeof(struct sctphdr))) goto discard_it; /* Pull up the IP header. */ __skb_pull(skb, skb_transport_offset(skb)); skb->csum_valid = 0; /* Previous value not applicable */ if (skb_csum_unnecessary(skb)) __skb_decr_checksum_unnecessary(skb); else if (!sctp_checksum_disable && !is_gso && sctp_rcv_checksum(net, skb) < 0) goto discard_it; skb->csum_valid = 1; __skb_pull(skb, sizeof(struct sctphdr)); family = ipver2af(ip_hdr(skb)->version); af = sctp_get_af_specific(family); if (unlikely(!af)) goto discard_it; SCTP_INPUT_CB(skb)->af = af; /* Initialize local addresses for lookups. */ af->from_skb(&src, skb, 1); af->from_skb(&dest, skb, 0); dif = af->skb_iif(skb); sdif = af->skb_sdif(skb); /* If the packet is to or from a non-unicast address, * silently discard the packet. * * This is not clearly defined in the RFC except in section * 8.4 - OOTB handling. However, based on the book "Stream Control * Transmission Protocol" 2.1, "It is important to note that the * IP address of an SCTP transport address must be a routable * unicast address. In other words, IP multicast addresses and * IP broadcast addresses cannot be used in an SCTP transport * address." */ if (!af->addr_valid(&src, NULL, skb) || !af->addr_valid(&dest, NULL, skb)) goto discard_it; asoc = __sctp_rcv_lookup(net, skb, &src, &dest, &transport, dif, sdif); if (!asoc) ep = __sctp_rcv_lookup_endpoint(net, skb, &dest, &src, dif, sdif); /* Retrieve the common input handling substructure. */ rcvr = asoc ? &asoc->base : &ep->base; sk = rcvr->sk; /* * RFC 2960, 8.4 - Handle "Out of the blue" Packets. * An SCTP packet is called an "out of the blue" (OOTB) * packet if it is correctly formed, i.e., passed the * receiver's checksum check, but the receiver is not * able to identify the association to which this * packet belongs. */ if (!asoc) { if (sctp_rcv_ootb(skb)) { __SCTP_INC_STATS(net, SCTP_MIB_OUTOFBLUES); goto discard_release; } } if (!xfrm_policy_check(sk, XFRM_POLICY_IN, skb, family)) goto discard_release; nf_reset_ct(skb); if (sk_filter(sk, skb)) goto discard_release; /* Create an SCTP packet structure. */ chunk = sctp_chunkify(skb, asoc, sk, GFP_ATOMIC); if (!chunk) goto discard_release; SCTP_INPUT_CB(skb)->chunk = chunk; /* Remember what endpoint is to handle this packet. */ chunk->rcvr = rcvr; /* Remember the SCTP header. */ chunk->sctp_hdr = sctp_hdr(skb); /* Set the source and destination addresses of the incoming chunk. */ sctp_init_addrs(chunk, &src, &dest); /* Remember where we came from. */ chunk->transport = transport; /* Acquire access to the sock lock. Note: We are safe from other * bottom halves on this lock, but a user may be in the lock too, * so check if it is busy. */ bh_lock_sock(sk); if (sk != rcvr->sk) { /* Our cached sk is different from the rcvr->sk. This is * because migrate()/accept() may have moved the association * to a new socket and released all the sockets. So now we * are holding a lock on the old socket while the user may * be doing something with the new socket. Switch our veiw * of the current sk. */ bh_unlock_sock(sk); sk = rcvr->sk; bh_lock_sock(sk); } if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) { if (sctp_add_backlog(sk, skb)) { bh_unlock_sock(sk); sctp_chunk_free(chunk); skb = NULL; /* sctp_chunk_free already freed the skb */ goto discard_release; } __SCTP_INC_STATS(net, SCTP_MIB_IN_PKT_BACKLOG); } else { __SCTP_INC_STATS(net, SCTP_MIB_IN_PKT_SOFTIRQ); sctp_inq_push(&chunk->rcvr->inqueue, chunk); } bh_unlock_sock(sk); /* Release the asoc/ep ref we took in the lookup calls. */ if (transport) sctp_transport_put(transport); else sctp_endpoint_put(ep); return 0; discard_it: __SCTP_INC_STATS(net, SCTP_MIB_IN_PKT_DISCARDS); kfree_skb(skb); return 0; discard_release: /* Release the asoc/ep ref we took in the lookup calls. */ if (transport) sctp_transport_put(transport); else sctp_endpoint_put(ep); goto discard_it; } /* Process the backlog queue of the socket. Every skb on * the backlog holds a ref on an association or endpoint. * We hold this ref throughout the state machine to make * sure that the structure we need is still around. */ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) { struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk; struct sctp_inq *inqueue = &chunk->rcvr->inqueue; struct sctp_transport *t = chunk->transport; struct sctp_ep_common *rcvr = NULL; int backloged = 0; rcvr = chunk->rcvr; /* If the rcvr is dead then the association or endpoint * has been deleted and we can safely drop the chunk * and refs that we are holding. */ if (rcvr->dead) { sctp_chunk_free(chunk); goto done; } if (unlikely(rcvr->sk != sk)) { /* In this case, the association moved from one socket to * another. We are currently sitting on the backlog of the * old socket, so we need to move. * However, since we are here in the process context we * need to take make sure that the user doesn't own * the new socket when we process the packet. * If the new socket is user-owned, queue the chunk to the * backlog of the new socket without dropping any refs. * Otherwise, we can safely push the chunk on the inqueue. */ sk = rcvr->sk; local_bh_disable(); bh_lock_sock(sk); if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) { if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) sctp_chunk_free(chunk); else backloged = 1; } else sctp_inq_push(inqueue, chunk); bh_unlock_sock(sk); local_bh_enable(); /* If the chunk was backloged again, don't drop refs */ if (backloged) return 0; } else { if (!sctp_newsk_ready(sk)) { if (!sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) return 0; sctp_chunk_free(chunk); } else { sctp_inq_push(inqueue, chunk); } } done: /* Release the refs we took in sctp_add_backlog */ if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type) sctp_transport_put(t); else if (SCTP_EP_TYPE_SOCKET == rcvr->type) sctp_endpoint_put(sctp_ep(rcvr)); else BUG(); return 0; } static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb) { struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk; struct sctp_transport *t = chunk->transport; struct sctp_ep_common *rcvr = chunk->rcvr; int ret; ret = sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)); if (!ret) { /* Hold the assoc/ep while hanging on the backlog queue. * This way, we know structures we need will not disappear * from us */ if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type) sctp_transport_hold(t); else if (SCTP_EP_TYPE_SOCKET == rcvr->type) sctp_endpoint_hold(sctp_ep(rcvr)); else BUG(); } return ret; } /* Handle icmp frag needed error. */ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc, struct sctp_transport *t, __u32 pmtu) { if (!t || (t->pathmtu <= pmtu && t->pl.probe_size + sctp_transport_pl_hlen(t) <= pmtu)) return; if (sock_owned_by_user(sk)) { atomic_set(&t->mtu_info, pmtu); asoc->pmtu_pending = 1; t->pmtu_pending = 1; return; } if (!(t->param_flags & SPP_PMTUD_ENABLE)) /* We can't allow retransmitting in such case, as the * retransmission would be sized just as before, and thus we * would get another icmp, and retransmit again. */ return; /* Update transports view of the MTU. Return if no update was needed. * If an update wasn't needed/possible, it also doesn't make sense to * try to retransmit now. */ if (!sctp_transport_update_pmtu(t, pmtu)) return; /* Update association pmtu. */ sctp_assoc_sync_pmtu(asoc); /* Retransmit with the new pmtu setting. */ sctp_retransmit(&asoc->outqueue, t, SCTP_RTXR_PMTUD); } void sctp_icmp_redirect(struct sock *sk, struct sctp_transport *t, struct sk_buff *skb) { struct dst_entry *dst; if (sock_owned_by_user(sk) || !t) return; dst = sctp_transport_dst_check(t); if (dst) dst->ops->redirect(dst, sk, skb); } /* * SCTP Implementer's Guide, 2.37 ICMP handling procedures * * ICMP8) If the ICMP code is a "Unrecognized next header type encountered" * or a "Protocol Unreachable" treat this message as an abort * with the T bit set. * * This function sends an event to the state machine, which will abort the * association. * */ void sctp_icmp_proto_unreachable(struct sock *sk, struct sctp_association *asoc, struct sctp_transport *t) { if (sock_owned_by_user(sk)) { if (timer_pending(&t->proto_unreach_timer)) return; else { if (!mod_timer(&t->proto_unreach_timer, jiffies + (HZ/20))) sctp_transport_hold(t); } } else { struct net *net = sock_net(sk); pr_debug("%s: unrecognized next header type " "encountered!\n", __func__); if (del_timer(&t->proto_unreach_timer)) sctp_transport_put(t); sctp_do_sm(net, SCTP_EVENT_T_OTHER, SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH), asoc->state, asoc->ep, asoc, t, GFP_ATOMIC); } } /* Common lookup code for icmp/icmpv6 error handler. */ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb, struct sctphdr *sctphdr, struct sctp_association **app, struct sctp_transport **tpp) { struct sctp_init_chunk *chunkhdr, _chunkhdr; union sctp_addr saddr; union sctp_addr daddr; struct sctp_af *af; struct sock *sk = NULL; struct sctp_association *asoc; struct sctp_transport *transport = NULL; __u32 vtag = ntohl(sctphdr->vtag); int sdif = inet_sdif(skb); int dif = inet_iif(skb); *app = NULL; *tpp = NULL; af = sctp_get_af_specific(family); if (unlikely(!af)) { return NULL; } /* Initialize local addresses for lookups. */ af->from_skb(&saddr, skb, 1); af->from_skb(&daddr, skb, 0); /* Look for an association that matches the incoming ICMP error * packet. */ asoc = __sctp_lookup_association(net, &saddr, &daddr, &transport, dif, sdif); if (!asoc) return NULL; sk = asoc->base.sk; /* RFC 4960, Appendix C. ICMP Handling * * ICMP6) An implementation MUST validate that the Verification Tag * contained in the ICMP message matches the Verification Tag of * the peer. If the Verification Tag is not 0 and does NOT * match, discard the ICMP message. If it is 0 and the ICMP * message contains enough bytes to verify that the chunk type is * an INIT chunk and that the Initiate Tag matches the tag of the * peer, continue with ICMP7. If the ICMP message is too short * or the chunk type or the Initiate Tag does not match, silently * discard the packet. */ if (vtag == 0) { /* chunk header + first 4 octects of init header */ chunkhdr = skb_header_pointer(skb, skb_transport_offset(skb) + sizeof(struct sctphdr), sizeof(struct sctp_chunkhdr) + sizeof(__be32), &_chunkhdr); if (!chunkhdr || chunkhdr->chunk_hdr.type != SCTP_CID_INIT || ntohl(chunkhdr->init_hdr.init_tag) != asoc->c.my_vtag) goto out; } else if (vtag != asoc->c.peer_vtag) { goto out; } bh_lock_sock(sk); /* If too many ICMPs get dropped on busy * servers this needs to be solved differently. */ if (sock_owned_by_user(sk)) __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS); *app = asoc; *tpp = transport; return sk; out: sctp_transport_put(transport); return NULL; } /* Common cleanup code for icmp/icmpv6 error handler. */ void sctp_err_finish(struct sock *sk, struct sctp_transport *t) __releases(&((__sk)->sk_lock.slock)) { bh_unlock_sock(sk); sctp_transport_put(t); } static void sctp_v4_err_handle(struct sctp_transport *t, struct sk_buff *skb, __u8 type, __u8 code, __u32 info) { struct sctp_association *asoc = t->asoc; struct sock *sk = asoc->base.sk; int err = 0; switch (type) { case ICMP_PARAMETERPROB: err = EPROTO; break; case ICMP_DEST_UNREACH: if (code > NR_ICMP_UNREACH) return; if (code == ICMP_FRAG_NEEDED) { sctp_icmp_frag_needed(sk, asoc, t, SCTP_TRUNC4(info)); return; } if (code == ICMP_PROT_UNREACH) { sctp_icmp_proto_unreachable(sk, asoc, t); return; } err = icmp_err_convert[code].errno; break; case ICMP_TIME_EXCEEDED: if (code == ICMP_EXC_FRAGTIME) return; err = EHOSTUNREACH; break; case ICMP_REDIRECT: sctp_icmp_redirect(sk, t, skb); return; default: return; } if (!sock_owned_by_user(sk) && inet_test_bit(RECVERR, sk)) { sk->sk_err = err; sk_error_report(sk); } else { /* Only an error on timeout */ WRITE_ONCE(sk->sk_err_soft, err); } } /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should * be closed and the error returned to the user. If err > 0 * it's just the icmp type << 8 | icmp code. After adjustment * header points to the first 8 bytes of the sctp header. We need * to find the appropriate port. * * The locking strategy used here is very "optimistic". When * someone else accesses the socket the ICMP is just dropped * and for some paths there is no check at all. * A more general error queue to queue errors for later handling * is probably better. * */ int sctp_v4_err(struct sk_buff *skb, __u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct net *net = dev_net(skb->dev); struct sctp_transport *transport; struct sctp_association *asoc; __u16 saveip, savesctp; struct sock *sk; /* Fix up skb to look at the embedded net header. */ saveip = skb->network_header; savesctp = skb->transport_header; skb_reset_network_header(skb); skb_set_transport_header(skb, iph->ihl * 4); sk = sctp_err_lookup(net, AF_INET, skb, sctp_hdr(skb), &asoc, &transport); /* Put back, the original values. */ skb->network_header = saveip; skb->transport_header = savesctp; if (!sk) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return -ENOENT; } sctp_v4_err_handle(transport, skb, type, code, info); sctp_err_finish(sk, transport); return 0; } int sctp_udp_v4_err(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb->dev); struct sctp_association *asoc; struct sctp_transport *t; struct icmphdr *hdr; __u32 info = 0; skb->transport_header += sizeof(struct udphdr); sk = sctp_err_lookup(net, AF_INET, skb, sctp_hdr(skb), &asoc, &t); if (!sk) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return -ENOENT; } skb->transport_header -= sizeof(struct udphdr); hdr = (struct icmphdr *)(skb_network_header(skb) - sizeof(struct icmphdr)); if (hdr->type == ICMP_REDIRECT) { /* can't be handled without outer iphdr known, leave it to udp_err */ sctp_err_finish(sk, t); return 0; } if (hdr->type == ICMP_DEST_UNREACH && hdr->code == ICMP_FRAG_NEEDED) info = ntohs(hdr->un.frag.mtu); sctp_v4_err_handle(t, skb, hdr->type, hdr->code, info); sctp_err_finish(sk, t); return 1; } /* * RFC 2960, 8.4 - Handle "Out of the blue" Packets. * * This function scans all the chunks in the OOTB packet to determine if * the packet should be discarded right away. If a response might be needed * for this packet, or, if further processing is possible, the packet will * be queued to a proper inqueue for the next phase of handling. * * Output: * Return 0 - If further processing is needed. * Return 1 - If the packet can be discarded right away. */ static int sctp_rcv_ootb(struct sk_buff *skb) { struct sctp_chunkhdr *ch, _ch; int ch_end, offset = 0; /* Scan through all the chunks in the packet. */ do { /* Make sure we have at least the header there */ if (offset + sizeof(_ch) > skb->len) break; ch = skb_header_pointer(skb, offset, sizeof(*ch), &_ch); /* Break out if chunk length is less then minimal. */ if (!ch || ntohs(ch->length) < sizeof(_ch)) break; ch_end = offset + SCTP_PAD4(ntohs(ch->length)); if (ch_end > skb->len) break; /* RFC 8.4, 2) If the OOTB packet contains an ABORT chunk, the * receiver MUST silently discard the OOTB packet and take no * further action. */ if (SCTP_CID_ABORT == ch->type) goto discard; /* RFC 8.4, 6) If the packet contains a SHUTDOWN COMPLETE * chunk, the receiver should silently discard the packet * and take no further action. */ if (SCTP_CID_SHUTDOWN_COMPLETE == ch->type) goto discard; /* RFC 4460, 2.11.2 * This will discard packets with INIT chunk bundled as * subsequent chunks in the packet. When INIT is first, * the normal INIT processing will discard the chunk. */ if (SCTP_CID_INIT == ch->type && (void *)ch != skb->data) goto discard; offset = ch_end; } while (ch_end < skb->len); return 0; discard: return 1; } /* Insert endpoint into the hash table. */ static int __sctp_hash_endpoint(struct sctp_endpoint *ep) { struct sock *sk = ep->base.sk; struct net *net = sock_net(sk); struct sctp_hashbucket *head; ep->hashent = sctp_ep_hashfn(net, ep->base.bind_addr.port); head = &sctp_ep_hashtable[ep->hashent]; if (sk->sk_reuseport) { bool any = sctp_is_ep_boundall(sk); struct sctp_endpoint *ep2; struct list_head *list; int cnt = 0, err = 1; list_for_each(list, &ep->base.bind_addr.address_list) cnt++; sctp_for_each_hentry(ep2, &head->chain) { struct sock *sk2 = ep2->base.sk; if (!net_eq(sock_net(sk2), net) || sk2 == sk || !uid_eq(sock_i_uid(sk2), sock_i_uid(sk)) || !sk2->sk_reuseport) continue; err = sctp_bind_addrs_check(sctp_sk(sk2), sctp_sk(sk), cnt); if (!err) { err = reuseport_add_sock(sk, sk2, any); if (err) return err; break; } else if (err < 0) { return err; } } if (err) { err = reuseport_alloc(sk, any); if (err) return err; } } write_lock(&head->lock); hlist_add_head(&ep->node, &head->chain); write_unlock(&head->lock); return 0; } /* Add an endpoint to the hash. Local BH-safe. */ int sctp_hash_endpoint(struct sctp_endpoint *ep) { int err; local_bh_disable(); err = __sctp_hash_endpoint(ep); local_bh_enable(); return err; } /* Remove endpoint from the hash table. */ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep) { struct sock *sk = ep->base.sk; struct sctp_hashbucket *head; ep->hashent = sctp_ep_hashfn(sock_net(sk), ep->base.bind_addr.port); head = &sctp_ep_hashtable[ep->hashent]; if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); write_lock(&head->lock); hlist_del_init(&ep->node); write_unlock(&head->lock); } /* Remove endpoint from the hash. Local BH-safe. */ void sctp_unhash_endpoint(struct sctp_endpoint *ep) { local_bh_disable(); __sctp_unhash_endpoint(ep); local_bh_enable(); } static inline __u32 sctp_hashfn(const struct net *net, __be16 lport, const union sctp_addr *paddr, __u32 seed) { __u32 addr; if (paddr->sa.sa_family == AF_INET6) addr = jhash(&paddr->v6.sin6_addr, 16, seed); else addr = (__force __u32)paddr->v4.sin_addr.s_addr; return jhash_3words(addr, ((__force __u32)paddr->v4.sin_port) << 16 | (__force __u32)lport, net_hash_mix(net), seed); } /* Look up an endpoint. */ static struct sctp_endpoint *__sctp_rcv_lookup_endpoint( struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, const union sctp_addr *paddr, int dif, int sdif) { struct sctp_hashbucket *head; struct sctp_endpoint *ep; struct sock *sk; __be16 lport; int hash; lport = laddr->v4.sin_port; hash = sctp_ep_hashfn(net, ntohs(lport)); head = &sctp_ep_hashtable[hash]; read_lock(&head->lock); sctp_for_each_hentry(ep, &head->chain) { if (sctp_endpoint_is_match(ep, net, laddr, dif, sdif)) goto hit; } ep = sctp_sk(net->sctp.ctl_sock)->ep; hit: sk = ep->base.sk; if (sk->sk_reuseport) { __u32 phash = sctp_hashfn(net, lport, paddr, 0); sk = reuseport_select_sock(sk, phash, skb, sizeof(struct sctphdr)); if (sk) ep = sctp_sk(sk)->ep; } sctp_endpoint_hold(ep); read_unlock(&head->lock); return ep; } /* rhashtable for transport */ struct sctp_hash_cmp_arg { const union sctp_addr *paddr; const struct net *net; __be16 lport; }; static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { struct sctp_transport *t = (struct sctp_transport *)ptr; const struct sctp_hash_cmp_arg *x = arg->key; int err = 1; if (!sctp_cmp_addr_exact(&t->ipaddr, x->paddr)) return err; if (!sctp_transport_hold(t)) return err; if (!net_eq(t->asoc->base.net, x->net)) goto out; if (x->lport != htons(t->asoc->base.bind_addr.port)) goto out; err = 0; out: sctp_transport_put(t); return err; } static inline __u32 sctp_hash_obj(const void *data, u32 len, u32 seed) { const struct sctp_transport *t = data; return sctp_hashfn(t->asoc->base.net, htons(t->asoc->base.bind_addr.port), &t->ipaddr, seed); } static inline __u32 sctp_hash_key(const void *data, u32 len, u32 seed) { const struct sctp_hash_cmp_arg *x = data; return sctp_hashfn(x->net, x->lport, x->paddr, seed); } static const struct rhashtable_params sctp_hash_params = { .head_offset = offsetof(struct sctp_transport, node), .hashfn = sctp_hash_key, .obj_hashfn = sctp_hash_obj, .obj_cmpfn = sctp_hash_cmp, .automatic_shrinking = true, }; int sctp_transport_hashtable_init(void) { return rhltable_init(&sctp_transport_hashtable, &sctp_hash_params); } void sctp_transport_hashtable_destroy(void) { rhltable_destroy(&sctp_transport_hashtable); } int sctp_hash_transport(struct sctp_transport *t) { struct sctp_transport *transport; struct rhlist_head *tmp, *list; struct sctp_hash_cmp_arg arg; int err; if (t->asoc->temp) return 0; arg.net = t->asoc->base.net; arg.paddr = &t->ipaddr; arg.lport = htons(t->asoc->base.bind_addr.port); rcu_read_lock(); list = rhltable_lookup(&sctp_transport_hashtable, &arg, sctp_hash_params); rhl_for_each_entry_rcu(transport, tmp, list, node) if (transport->asoc->ep == t->asoc->ep) { rcu_read_unlock(); return -EEXIST; } rcu_read_unlock(); err = rhltable_insert_key(&sctp_transport_hashtable, &arg, &t->node, sctp_hash_params); if (err) pr_err_once("insert transport fail, errno %d\n", err); return err; } void sctp_unhash_transport(struct sctp_transport *t) { if (t->asoc->temp) return; rhltable_remove(&sctp_transport_hashtable, &t->node, sctp_hash_params); } bool sctp_sk_bound_dev_eq(struct net *net, int bound_dev_if, int dif, int sdif) { bool l3mdev_accept = true; #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) l3mdev_accept = !!READ_ONCE(net->sctp.l3mdev_accept); #endif return inet_bound_dev_eq(l3mdev_accept, bound_dev_if, dif, sdif); } /* return a transport with holding it */ struct sctp_transport *sctp_addrs_lookup_transport( struct net *net, const union sctp_addr *laddr, const union sctp_addr *paddr, int dif, int sdif) { struct rhlist_head *tmp, *list; struct sctp_transport *t; int bound_dev_if; struct sctp_hash_cmp_arg arg = { .paddr = paddr, .net = net, .lport = laddr->v4.sin_port, }; list = rhltable_lookup(&sctp_transport_hashtable, &arg, sctp_hash_params); rhl_for_each_entry_rcu(t, tmp, list, node) { if (!sctp_transport_hold(t)) continue; bound_dev_if = READ_ONCE(t->asoc->base.sk->sk_bound_dev_if); if (sctp_sk_bound_dev_eq(net, bound_dev_if, dif, sdif) && sctp_bind_addr_match(&t->asoc->base.bind_addr, laddr, sctp_sk(t->asoc->base.sk))) return t; sctp_transport_put(t); } return NULL; } /* return a transport without holding it, as it's only used under sock lock */ struct sctp_transport *sctp_epaddr_lookup_transport( const struct sctp_endpoint *ep, const union sctp_addr *paddr) { struct rhlist_head *tmp, *list; struct sctp_transport *t; struct sctp_hash_cmp_arg arg = { .paddr = paddr, .net = ep->base.net, .lport = htons(ep->base.bind_addr.port), }; list = rhltable_lookup(&sctp_transport_hashtable, &arg, sctp_hash_params); rhl_for_each_entry_rcu(t, tmp, list, node) if (ep == t->asoc->ep) return t; return NULL; } /* Look up an association. */ static struct sctp_association *__sctp_lookup_association( struct net *net, const union sctp_addr *local, const union sctp_addr *peer, struct sctp_transport **pt, int dif, int sdif) { struct sctp_transport *t; struct sctp_association *asoc = NULL; t = sctp_addrs_lookup_transport(net, local, peer, dif, sdif); if (!t) goto out; asoc = t->asoc; *pt = t; out: return asoc; } /* Look up an association. protected by RCU read lock */ static struct sctp_association *sctp_lookup_association(struct net *net, const union sctp_addr *laddr, const union sctp_addr *paddr, struct sctp_transport **transportp, int dif, int sdif) { struct sctp_association *asoc; rcu_read_lock(); asoc = __sctp_lookup_association(net, laddr, paddr, transportp, dif, sdif); rcu_read_unlock(); return asoc; } /* Is there an association matching the given local and peer addresses? */ bool sctp_has_association(struct net *net, const union sctp_addr *laddr, const union sctp_addr *paddr, int dif, int sdif) { struct sctp_transport *transport; if (sctp_lookup_association(net, laddr, paddr, &transport, dif, sdif)) { sctp_transport_put(transport); return true; } return false; } /* * SCTP Implementors Guide, 2.18 Handling of address * parameters within the INIT or INIT-ACK. * * D) When searching for a matching TCB upon reception of an INIT * or INIT-ACK chunk the receiver SHOULD use not only the * source address of the packet (containing the INIT or * INIT-ACK) but the receiver SHOULD also use all valid * address parameters contained within the chunk. * * 2.18.3 Solution description * * This new text clearly specifies to an implementor the need * to look within the INIT or INIT-ACK. Any implementation that * does not do this, may not be able to establish associations * in certain circumstances. * */ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, struct sctp_transport **transportp, int dif, int sdif) { struct sctp_association *asoc; union sctp_addr addr; union sctp_addr *paddr = &addr; struct sctphdr *sh = sctp_hdr(skb); union sctp_params params; struct sctp_init_chunk *init; struct sctp_af *af; /* * This code will NOT touch anything inside the chunk--it is * strictly READ-ONLY. * * RFC 2960 3 SCTP packet Format * * Multiple chunks can be bundled into one SCTP packet up to * the MTU size, except for the INIT, INIT ACK, and SHUTDOWN * COMPLETE chunks. These chunks MUST NOT be bundled with any * other chunk in a packet. See Section 6.10 for more details * on chunk bundling. */ /* Find the start of the TLVs and the end of the chunk. This is * the region we search for address parameters. */ init = (struct sctp_init_chunk *)skb->data; /* Walk the parameters looking for embedded addresses. */ sctp_walk_params(params, init) { /* Note: Ignoring hostname addresses. */ af = sctp_get_af_specific(param_type2af(params.p->type)); if (!af) continue; if (!af->from_addr_param(paddr, params.addr, sh->source, 0)) continue; asoc = __sctp_lookup_association(net, laddr, paddr, transportp, dif, sdif); if (asoc) return asoc; } return NULL; } /* ADD-IP, Section 5.2 * When an endpoint receives an ASCONF Chunk from the remote peer * special procedures may be needed to identify the association the * ASCONF Chunk is associated with. To properly find the association * the following procedures SHOULD be followed: * * D2) If the association is not found, use the address found in the * Address Parameter TLV combined with the port number found in the * SCTP common header. If found proceed to rule D4. * * D2-ext) If more than one ASCONF Chunks are packed together, use the * address found in the ASCONF Address Parameter TLV of each of the * subsequent ASCONF Chunks. If found, proceed to rule D4. */ static struct sctp_association *__sctp_rcv_asconf_lookup( struct net *net, struct sctp_chunkhdr *ch, const union sctp_addr *laddr, __be16 peer_port, struct sctp_transport **transportp, int dif, int sdif) { struct sctp_addip_chunk *asconf = (struct sctp_addip_chunk *)ch; struct sctp_af *af; union sctp_addr_param *param; union sctp_addr paddr; if (ntohs(ch->length) < sizeof(*asconf) + sizeof(struct sctp_paramhdr)) return NULL; /* Skip over the ADDIP header and find the Address parameter */ param = (union sctp_addr_param *)(asconf + 1); af = sctp_get_af_specific(param_type2af(param->p.type)); if (unlikely(!af)) return NULL; if (!af->from_addr_param(&paddr, param, peer_port, 0)) return NULL; return __sctp_lookup_association(net, laddr, &paddr, transportp, dif, sdif); } /* SCTP-AUTH, Section 6.3: * If the receiver does not find a STCB for a packet containing an AUTH * chunk as the first chunk and not a COOKIE-ECHO chunk as the second * chunk, it MUST use the chunks after the AUTH chunk to look up an existing * association. * * This means that any chunks that can help us identify the association need * to be looked at to find this association. */ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, struct sctp_transport **transportp, int dif, int sdif) { struct sctp_association *asoc = NULL; struct sctp_chunkhdr *ch; int have_auth = 0; unsigned int chunk_num = 1; __u8 *ch_end; /* Walk through the chunks looking for AUTH or ASCONF chunks * to help us find the association. */ ch = (struct sctp_chunkhdr *)skb->data; do { /* Break out if chunk length is less then minimal. */ if (ntohs(ch->length) < sizeof(*ch)) break; ch_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length)); if (ch_end > skb_tail_pointer(skb)) break; switch (ch->type) { case SCTP_CID_AUTH: have_auth = chunk_num; break; case SCTP_CID_COOKIE_ECHO: /* If a packet arrives containing an AUTH chunk as * a first chunk, a COOKIE-ECHO chunk as the second * chunk, and possibly more chunks after them, and * the receiver does not have an STCB for that * packet, then authentication is based on * the contents of the COOKIE- ECHO chunk. */ if (have_auth == 1 && chunk_num == 2) return NULL; break; case SCTP_CID_ASCONF: if (have_auth || net->sctp.addip_noauth) asoc = __sctp_rcv_asconf_lookup( net, ch, laddr, sctp_hdr(skb)->source, transportp, dif, sdif); break; default: break; } if (asoc) break; ch = (struct sctp_chunkhdr *)ch_end; chunk_num++; } while (ch_end + sizeof(*ch) < skb_tail_pointer(skb)); return asoc; } /* * There are circumstances when we need to look inside the SCTP packet * for information to help us find the association. Examples * include looking inside of INIT/INIT-ACK chunks or after the AUTH * chunks. */ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, struct sctp_transport **transportp, int dif, int sdif) { struct sctp_chunkhdr *ch; /* We do not allow GSO frames here as we need to linearize and * then cannot guarantee frame boundaries. This shouldn't be an * issue as packets hitting this are mostly INIT or INIT-ACK and * those cannot be on GSO-style anyway. */ if (skb_is_gso(skb) && skb_is_gso_sctp(skb)) return NULL; ch = (struct sctp_chunkhdr *)skb->data; /* The code below will attempt to walk the chunk and extract * parameter information. Before we do that, we need to verify * that the chunk length doesn't cause overflow. Otherwise, we'll * walk off the end. */ if (SCTP_PAD4(ntohs(ch->length)) > skb->len) return NULL; /* If this is INIT/INIT-ACK look inside the chunk too. */ if (ch->type == SCTP_CID_INIT || ch->type == SCTP_CID_INIT_ACK) return __sctp_rcv_init_lookup(net, skb, laddr, transportp, dif, sdif); return __sctp_rcv_walk_lookup(net, skb, laddr, transportp, dif, sdif); } /* Lookup an association for an inbound skb. */ static struct sctp_association *__sctp_rcv_lookup(struct net *net, struct sk_buff *skb, const union sctp_addr *paddr, const union sctp_addr *laddr, struct sctp_transport **transportp, int dif, int sdif) { struct sctp_association *asoc; asoc = __sctp_lookup_association(net, laddr, paddr, transportp, dif, sdif); if (asoc) goto out; /* Further lookup for INIT/INIT-ACK packets. * SCTP Implementors Guide, 2.18 Handling of address * parameters within the INIT or INIT-ACK. */ asoc = __sctp_rcv_lookup_harder(net, skb, laddr, transportp, dif, sdif); if (asoc) goto out; if (paddr->sa.sa_family == AF_INET) pr_debug("sctp: asoc not found for src:%pI4:%d dst:%pI4:%d\n", &laddr->v4.sin_addr, ntohs(laddr->v4.sin_port), &paddr->v4.sin_addr, ntohs(paddr->v4.sin_port)); else pr_debug("sctp: asoc not found for src:%pI6:%d dst:%pI6:%d\n", &laddr->v6.sin6_addr, ntohs(laddr->v6.sin6_port), &paddr->v6.sin6_addr, ntohs(paddr->v6.sin6_port)); out: return asoc; } |
| 13 13 13 13 2 2 2 2 2 2 2 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * virtio transport for vsock * * Copyright (C) 2013-2015 Red Hat, Inc. * Author: Asias He <asias@redhat.com> * Stefan Hajnoczi <stefanha@redhat.com> * * Some of the code is take from Gerd Hoffmann <kraxel@redhat.com>'s * early virtio-vsock proof-of-concept bits. */ #include <linux/spinlock.h> #include <linux/module.h> #include <linux/list.h> #include <linux/atomic.h> #include <linux/virtio.h> #include <linux/virtio_ids.h> #include <linux/virtio_config.h> #include <linux/virtio_vsock.h> #include <net/sock.h> #include <linux/mutex.h> #include <net/af_vsock.h> static struct workqueue_struct *virtio_vsock_workqueue; static struct virtio_vsock __rcu *the_virtio_vsock; static DEFINE_MUTEX(the_virtio_vsock_mutex); /* protects the_virtio_vsock */ static struct virtio_transport virtio_transport; /* forward declaration */ struct virtio_vsock { struct virtio_device *vdev; struct virtqueue *vqs[VSOCK_VQ_MAX]; /* Virtqueue processing is deferred to a workqueue */ struct work_struct tx_work; struct work_struct rx_work; struct work_struct event_work; /* The following fields are protected by tx_lock. vqs[VSOCK_VQ_TX] * must be accessed with tx_lock held. */ struct mutex tx_lock; bool tx_run; struct work_struct send_pkt_work; struct sk_buff_head send_pkt_queue; atomic_t queued_replies; /* The following fields are protected by rx_lock. vqs[VSOCK_VQ_RX] * must be accessed with rx_lock held. */ struct mutex rx_lock; bool rx_run; int rx_buf_nr; int rx_buf_max_nr; /* The following fields are protected by event_lock. * vqs[VSOCK_VQ_EVENT] must be accessed with event_lock held. */ struct mutex event_lock; bool event_run; struct virtio_vsock_event event_list[8]; u32 guest_cid; bool seqpacket_allow; /* These fields are used only in tx path in function * 'virtio_transport_send_pkt_work()', so to save * stack space in it, place both of them here. Each * pointer from 'out_sgs' points to the corresponding * element in 'out_bufs' - this is initialized in * 'virtio_vsock_probe()'. Both fields are protected * by 'tx_lock'. +1 is needed for packet header. */ struct scatterlist *out_sgs[MAX_SKB_FRAGS + 1]; struct scatterlist out_bufs[MAX_SKB_FRAGS + 1]; }; static u32 virtio_transport_get_local_cid(void) { struct virtio_vsock *vsock; u32 ret; rcu_read_lock(); vsock = rcu_dereference(the_virtio_vsock); if (!vsock) { ret = VMADDR_CID_ANY; goto out_rcu; } ret = vsock->guest_cid; out_rcu: rcu_read_unlock(); return ret; } static void virtio_transport_send_pkt_work(struct work_struct *work) { struct virtio_vsock *vsock = container_of(work, struct virtio_vsock, send_pkt_work); struct virtqueue *vq; bool added = false; bool restart_rx = false; mutex_lock(&vsock->tx_lock); if (!vsock->tx_run) goto out; vq = vsock->vqs[VSOCK_VQ_TX]; for (;;) { int ret, in_sg = 0, out_sg = 0; struct scatterlist **sgs; struct sk_buff *skb; bool reply; skb = virtio_vsock_skb_dequeue(&vsock->send_pkt_queue); if (!skb) break; reply = virtio_vsock_skb_reply(skb); sgs = vsock->out_sgs; sg_init_one(sgs[out_sg], virtio_vsock_hdr(skb), sizeof(*virtio_vsock_hdr(skb))); out_sg++; if (!skb_is_nonlinear(skb)) { if (skb->len > 0) { sg_init_one(sgs[out_sg], skb->data, skb->len); out_sg++; } } else { struct skb_shared_info *si; int i; /* If skb is nonlinear, then its buffer must contain * only header and nothing more. Data is stored in * the fragged part. */ WARN_ON_ONCE(skb_headroom(skb) != sizeof(*virtio_vsock_hdr(skb))); si = skb_shinfo(skb); for (i = 0; i < si->nr_frags; i++) { skb_frag_t *skb_frag = &si->frags[i]; void *va; /* We will use 'page_to_virt()' for the userspace page * here, because virtio or dma-mapping layers will call * 'virt_to_phys()' later to fill the buffer descriptor. * We don't touch memory at "virtual" address of this page. */ va = page_to_virt(skb_frag_page(skb_frag)); sg_init_one(sgs[out_sg], va + skb_frag_off(skb_frag), skb_frag_size(skb_frag)); out_sg++; } } ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, skb, GFP_KERNEL); /* Usually this means that there is no more space available in * the vq */ if (ret < 0) { virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb); break; } virtio_transport_deliver_tap_pkt(skb); if (reply) { struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX]; int val; val = atomic_dec_return(&vsock->queued_replies); /* Do we now have resources to resume rx processing? */ if (val + 1 == virtqueue_get_vring_size(rx_vq)) restart_rx = true; } added = true; } if (added) virtqueue_kick(vq); out: mutex_unlock(&vsock->tx_lock); if (restart_rx) queue_work(virtio_vsock_workqueue, &vsock->rx_work); } static int virtio_transport_send_pkt(struct sk_buff *skb) { struct virtio_vsock_hdr *hdr; struct virtio_vsock *vsock; int len = skb->len; hdr = virtio_vsock_hdr(skb); rcu_read_lock(); vsock = rcu_dereference(the_virtio_vsock); if (!vsock) { kfree_skb(skb); len = -ENODEV; goto out_rcu; } if (le64_to_cpu(hdr->dst_cid) == vsock->guest_cid) { kfree_skb(skb); len = -ENODEV; goto out_rcu; } if (virtio_vsock_skb_reply(skb)) atomic_inc(&vsock->queued_replies); virtio_vsock_skb_queue_tail(&vsock->send_pkt_queue, skb); queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work); out_rcu: rcu_read_unlock(); return len; } static int virtio_transport_cancel_pkt(struct vsock_sock *vsk) { struct virtio_vsock *vsock; int cnt = 0, ret; rcu_read_lock(); vsock = rcu_dereference(the_virtio_vsock); if (!vsock) { ret = -ENODEV; goto out_rcu; } cnt = virtio_transport_purge_skbs(vsk, &vsock->send_pkt_queue); if (cnt) { struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX]; int new_cnt; new_cnt = atomic_sub_return(cnt, &vsock->queued_replies); if (new_cnt + cnt >= virtqueue_get_vring_size(rx_vq) && new_cnt < virtqueue_get_vring_size(rx_vq)) queue_work(virtio_vsock_workqueue, &vsock->rx_work); } ret = 0; out_rcu: rcu_read_unlock(); return ret; } static void virtio_vsock_rx_fill(struct virtio_vsock *vsock) { int total_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE + VIRTIO_VSOCK_SKB_HEADROOM; struct scatterlist pkt, *p; struct virtqueue *vq; struct sk_buff *skb; int ret; vq = vsock->vqs[VSOCK_VQ_RX]; do { skb = virtio_vsock_alloc_skb(total_len, GFP_KERNEL); if (!skb) break; memset(skb->head, 0, VIRTIO_VSOCK_SKB_HEADROOM); sg_init_one(&pkt, virtio_vsock_hdr(skb), total_len); p = &pkt; ret = virtqueue_add_sgs(vq, &p, 0, 1, skb, GFP_KERNEL); if (ret < 0) { kfree_skb(skb); break; } vsock->rx_buf_nr++; } while (vq->num_free); if (vsock->rx_buf_nr > vsock->rx_buf_max_nr) vsock->rx_buf_max_nr = vsock->rx_buf_nr; virtqueue_kick(vq); } static void virtio_transport_tx_work(struct work_struct *work) { struct virtio_vsock *vsock = container_of(work, struct virtio_vsock, tx_work); struct virtqueue *vq; bool added = false; vq = vsock->vqs[VSOCK_VQ_TX]; mutex_lock(&vsock->tx_lock); if (!vsock->tx_run) goto out; do { struct sk_buff *skb; unsigned int len; virtqueue_disable_cb(vq); while ((skb = virtqueue_get_buf(vq, &len)) != NULL) { consume_skb(skb); added = true; } } while (!virtqueue_enable_cb(vq)); out: mutex_unlock(&vsock->tx_lock); if (added) queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work); } /* Is there space left for replies to rx packets? */ static bool virtio_transport_more_replies(struct virtio_vsock *vsock) { struct virtqueue *vq = vsock->vqs[VSOCK_VQ_RX]; int val; smp_rmb(); /* paired with atomic_inc() and atomic_dec_return() */ val = atomic_read(&vsock->queued_replies); return val < virtqueue_get_vring_size(vq); } /* event_lock must be held */ static int virtio_vsock_event_fill_one(struct virtio_vsock *vsock, struct virtio_vsock_event *event) { struct scatterlist sg; struct virtqueue *vq; vq = vsock->vqs[VSOCK_VQ_EVENT]; sg_init_one(&sg, event, sizeof(*event)); return virtqueue_add_inbuf(vq, &sg, 1, event, GFP_KERNEL); } /* event_lock must be held */ static void virtio_vsock_event_fill(struct virtio_vsock *vsock) { size_t i; for (i = 0; i < ARRAY_SIZE(vsock->event_list); i++) { struct virtio_vsock_event *event = &vsock->event_list[i]; virtio_vsock_event_fill_one(vsock, event); } virtqueue_kick(vsock->vqs[VSOCK_VQ_EVENT]); } static void virtio_vsock_reset_sock(struct sock *sk) { /* vmci_transport.c doesn't take sk_lock here either. At least we're * under vsock_table_lock so the sock cannot disappear while we're * executing. */ sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; sk_error_report(sk); } static void virtio_vsock_update_guest_cid(struct virtio_vsock *vsock) { struct virtio_device *vdev = vsock->vdev; __le64 guest_cid; vdev->config->get(vdev, offsetof(struct virtio_vsock_config, guest_cid), &guest_cid, sizeof(guest_cid)); vsock->guest_cid = le64_to_cpu(guest_cid); } /* event_lock must be held */ static void virtio_vsock_event_handle(struct virtio_vsock *vsock, struct virtio_vsock_event *event) { switch (le32_to_cpu(event->id)) { case VIRTIO_VSOCK_EVENT_TRANSPORT_RESET: virtio_vsock_update_guest_cid(vsock); vsock_for_each_connected_socket(&virtio_transport.transport, virtio_vsock_reset_sock); break; } } static void virtio_transport_event_work(struct work_struct *work) { struct virtio_vsock *vsock = container_of(work, struct virtio_vsock, event_work); struct virtqueue *vq; vq = vsock->vqs[VSOCK_VQ_EVENT]; mutex_lock(&vsock->event_lock); if (!vsock->event_run) goto out; do { struct virtio_vsock_event *event; unsigned int len; virtqueue_disable_cb(vq); while ((event = virtqueue_get_buf(vq, &len)) != NULL) { if (len == sizeof(*event)) virtio_vsock_event_handle(vsock, event); virtio_vsock_event_fill_one(vsock, event); } } while (!virtqueue_enable_cb(vq)); virtqueue_kick(vsock->vqs[VSOCK_VQ_EVENT]); out: mutex_unlock(&vsock->event_lock); } static void virtio_vsock_event_done(struct virtqueue *vq) { struct virtio_vsock *vsock = vq->vdev->priv; if (!vsock) return; queue_work(virtio_vsock_workqueue, &vsock->event_work); } static void virtio_vsock_tx_done(struct virtqueue *vq) { struct virtio_vsock *vsock = vq->vdev->priv; if (!vsock) return; queue_work(virtio_vsock_workqueue, &vsock->tx_work); } static void virtio_vsock_rx_done(struct virtqueue *vq) { struct virtio_vsock *vsock = vq->vdev->priv; if (!vsock) return; queue_work(virtio_vsock_workqueue, &vsock->rx_work); } static bool virtio_transport_can_msgzerocopy(int bufs_num) { struct virtio_vsock *vsock; bool res = false; rcu_read_lock(); vsock = rcu_dereference(the_virtio_vsock); if (vsock) { struct virtqueue *vq = vsock->vqs[VSOCK_VQ_TX]; /* Check that tx queue is large enough to keep whole * data to send. This is needed, because when there is * not enough free space in the queue, current skb to * send will be reinserted to the head of tx list of * the socket to retry transmission later, so if skb * is bigger than whole queue, it will be reinserted * again and again, thus blocking other skbs to be sent. * Each page of the user provided buffer will be added * as a single buffer to the tx virtqueue, so compare * number of pages against maximum capacity of the queue. */ if (bufs_num <= vq->num_max) res = true; } rcu_read_unlock(); return res; } static bool virtio_transport_msgzerocopy_allow(void) { return true; } static bool virtio_transport_seqpacket_allow(u32 remote_cid); static struct virtio_transport virtio_transport = { .transport = { .module = THIS_MODULE, .get_local_cid = virtio_transport_get_local_cid, .init = virtio_transport_do_socket_init, .destruct = virtio_transport_destruct, .release = virtio_transport_release, .connect = virtio_transport_connect, .shutdown = virtio_transport_shutdown, .cancel_pkt = virtio_transport_cancel_pkt, .dgram_bind = virtio_transport_dgram_bind, .dgram_dequeue = virtio_transport_dgram_dequeue, .dgram_enqueue = virtio_transport_dgram_enqueue, .dgram_allow = virtio_transport_dgram_allow, .stream_dequeue = virtio_transport_stream_dequeue, .stream_enqueue = virtio_transport_stream_enqueue, .stream_has_data = virtio_transport_stream_has_data, .stream_has_space = virtio_transport_stream_has_space, .stream_rcvhiwat = virtio_transport_stream_rcvhiwat, .stream_is_active = virtio_transport_stream_is_active, .stream_allow = virtio_transport_stream_allow, .seqpacket_dequeue = virtio_transport_seqpacket_dequeue, .seqpacket_enqueue = virtio_transport_seqpacket_enqueue, .seqpacket_allow = virtio_transport_seqpacket_allow, .seqpacket_has_data = virtio_transport_seqpacket_has_data, .msgzerocopy_allow = virtio_transport_msgzerocopy_allow, .notify_poll_in = virtio_transport_notify_poll_in, .notify_poll_out = virtio_transport_notify_poll_out, .notify_recv_init = virtio_transport_notify_recv_init, .notify_recv_pre_block = virtio_transport_notify_recv_pre_block, .notify_recv_pre_dequeue = virtio_transport_notify_recv_pre_dequeue, .notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue, .notify_send_init = virtio_transport_notify_send_init, .notify_send_pre_block = virtio_transport_notify_send_pre_block, .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, .notify_buffer_size = virtio_transport_notify_buffer_size, .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, .read_skb = virtio_transport_read_skb, }, .send_pkt = virtio_transport_send_pkt, .can_msgzerocopy = virtio_transport_can_msgzerocopy, }; static bool virtio_transport_seqpacket_allow(u32 remote_cid) { struct virtio_vsock *vsock; bool seqpacket_allow; seqpacket_allow = false; rcu_read_lock(); vsock = rcu_dereference(the_virtio_vsock); if (vsock) seqpacket_allow = vsock->seqpacket_allow; rcu_read_unlock(); return seqpacket_allow; } static void virtio_transport_rx_work(struct work_struct *work) { struct virtio_vsock *vsock = container_of(work, struct virtio_vsock, rx_work); struct virtqueue *vq; vq = vsock->vqs[VSOCK_VQ_RX]; mutex_lock(&vsock->rx_lock); if (!vsock->rx_run) goto out; do { virtqueue_disable_cb(vq); for (;;) { struct sk_buff *skb; unsigned int len; if (!virtio_transport_more_replies(vsock)) { /* Stop rx until the device processes already * pending replies. Leave rx virtqueue * callbacks disabled. */ goto out; } skb = virtqueue_get_buf(vq, &len); if (!skb) break; vsock->rx_buf_nr--; /* Drop short/long packets */ if (unlikely(len < sizeof(struct virtio_vsock_hdr) || len > virtio_vsock_skb_len(skb))) { kfree_skb(skb); continue; } virtio_vsock_skb_rx_put(skb); virtio_transport_deliver_tap_pkt(skb); virtio_transport_recv_pkt(&virtio_transport, skb); } } while (!virtqueue_enable_cb(vq)); out: if (vsock->rx_buf_nr < vsock->rx_buf_max_nr / 2) virtio_vsock_rx_fill(vsock); mutex_unlock(&vsock->rx_lock); } static int virtio_vsock_vqs_init(struct virtio_vsock *vsock) { struct virtio_device *vdev = vsock->vdev; static const char * const names[] = { "rx", "tx", "event", }; vq_callback_t *callbacks[] = { virtio_vsock_rx_done, virtio_vsock_tx_done, virtio_vsock_event_done, }; int ret; ret = virtio_find_vqs(vdev, VSOCK_VQ_MAX, vsock->vqs, callbacks, names, NULL); if (ret < 0) return ret; virtio_vsock_update_guest_cid(vsock); virtio_device_ready(vdev); return 0; } static void virtio_vsock_vqs_start(struct virtio_vsock *vsock) { mutex_lock(&vsock->tx_lock); vsock->tx_run = true; mutex_unlock(&vsock->tx_lock); mutex_lock(&vsock->rx_lock); virtio_vsock_rx_fill(vsock); vsock->rx_run = true; mutex_unlock(&vsock->rx_lock); mutex_lock(&vsock->event_lock); virtio_vsock_event_fill(vsock); vsock->event_run = true; mutex_unlock(&vsock->event_lock); /* virtio_transport_send_pkt() can queue packets once * the_virtio_vsock is set, but they won't be processed until * vsock->tx_run is set to true. We queue vsock->send_pkt_work * when initialization finishes to send those packets queued * earlier. * We don't need to queue the other workers (rx, event) because * as long as we don't fill the queues with empty buffers, the * host can't send us any notification. */ queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work); } static void virtio_vsock_vqs_del(struct virtio_vsock *vsock) { struct virtio_device *vdev = vsock->vdev; struct sk_buff *skb; /* Reset all connected sockets when the VQs disappear */ vsock_for_each_connected_socket(&virtio_transport.transport, virtio_vsock_reset_sock); /* Stop all work handlers to make sure no one is accessing the device, * so we can safely call virtio_reset_device(). */ mutex_lock(&vsock->rx_lock); vsock->rx_run = false; mutex_unlock(&vsock->rx_lock); mutex_lock(&vsock->tx_lock); vsock->tx_run = false; mutex_unlock(&vsock->tx_lock); mutex_lock(&vsock->event_lock); vsock->event_run = false; mutex_unlock(&vsock->event_lock); /* Flush all device writes and interrupts, device will not use any * more buffers. */ virtio_reset_device(vdev); mutex_lock(&vsock->rx_lock); while ((skb = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_RX]))) kfree_skb(skb); mutex_unlock(&vsock->rx_lock); mutex_lock(&vsock->tx_lock); while ((skb = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_TX]))) kfree_skb(skb); mutex_unlock(&vsock->tx_lock); virtio_vsock_skb_queue_purge(&vsock->send_pkt_queue); /* Delete virtqueues and flush outstanding callbacks if any */ vdev->config->del_vqs(vdev); } static int virtio_vsock_probe(struct virtio_device *vdev) { struct virtio_vsock *vsock = NULL; int ret; int i; ret = mutex_lock_interruptible(&the_virtio_vsock_mutex); if (ret) return ret; /* Only one virtio-vsock device per guest is supported */ if (rcu_dereference_protected(the_virtio_vsock, lockdep_is_held(&the_virtio_vsock_mutex))) { ret = -EBUSY; goto out; } vsock = kzalloc(sizeof(*vsock), GFP_KERNEL); if (!vsock) { ret = -ENOMEM; goto out; } vsock->vdev = vdev; vsock->rx_buf_nr = 0; vsock->rx_buf_max_nr = 0; atomic_set(&vsock->queued_replies, 0); mutex_init(&vsock->tx_lock); mutex_init(&vsock->rx_lock); mutex_init(&vsock->event_lock); skb_queue_head_init(&vsock->send_pkt_queue); INIT_WORK(&vsock->rx_work, virtio_transport_rx_work); INIT_WORK(&vsock->tx_work, virtio_transport_tx_work); INIT_WORK(&vsock->event_work, virtio_transport_event_work); INIT_WORK(&vsock->send_pkt_work, virtio_transport_send_pkt_work); if (virtio_has_feature(vdev, VIRTIO_VSOCK_F_SEQPACKET)) vsock->seqpacket_allow = true; vdev->priv = vsock; ret = virtio_vsock_vqs_init(vsock); if (ret < 0) goto out; for (i = 0; i < ARRAY_SIZE(vsock->out_sgs); i++) vsock->out_sgs[i] = &vsock->out_bufs[i]; rcu_assign_pointer(the_virtio_vsock, vsock); virtio_vsock_vqs_start(vsock); mutex_unlock(&the_virtio_vsock_mutex); return 0; out: kfree(vsock); mutex_unlock(&the_virtio_vsock_mutex); return ret; } static void virtio_vsock_remove(struct virtio_device *vdev) { struct virtio_vsock *vsock = vdev->priv; mutex_lock(&the_virtio_vsock_mutex); vdev->priv = NULL; rcu_assign_pointer(the_virtio_vsock, NULL); synchronize_rcu(); virtio_vsock_vqs_del(vsock); /* Other works can be queued before 'config->del_vqs()', so we flush * all works before to free the vsock object to avoid use after free. */ flush_work(&vsock->rx_work); flush_work(&vsock->tx_work); flush_work(&vsock->event_work); flush_work(&vsock->send_pkt_work); mutex_unlock(&the_virtio_vsock_mutex); kfree(vsock); } #ifdef CONFIG_PM_SLEEP static int virtio_vsock_freeze(struct virtio_device *vdev) { struct virtio_vsock *vsock = vdev->priv; mutex_lock(&the_virtio_vsock_mutex); rcu_assign_pointer(the_virtio_vsock, NULL); synchronize_rcu(); virtio_vsock_vqs_del(vsock); mutex_unlock(&the_virtio_vsock_mutex); return 0; } static int virtio_vsock_restore(struct virtio_device *vdev) { struct virtio_vsock *vsock = vdev->priv; int ret; mutex_lock(&the_virtio_vsock_mutex); /* Only one virtio-vsock device per guest is supported */ if (rcu_dereference_protected(the_virtio_vsock, lockdep_is_held(&the_virtio_vsock_mutex))) { ret = -EBUSY; goto out; } ret = virtio_vsock_vqs_init(vsock); if (ret < 0) goto out; rcu_assign_pointer(the_virtio_vsock, vsock); virtio_vsock_vqs_start(vsock); out: mutex_unlock(&the_virtio_vsock_mutex); return ret; } #endif /* CONFIG_PM_SLEEP */ static struct virtio_device_id id_table[] = { { VIRTIO_ID_VSOCK, VIRTIO_DEV_ANY_ID }, { 0 }, }; static unsigned int features[] = { VIRTIO_VSOCK_F_SEQPACKET }; static struct virtio_driver virtio_vsock_driver = { .feature_table = features, .feature_table_size = ARRAY_SIZE(features), .driver.name = KBUILD_MODNAME, .id_table = id_table, .probe = virtio_vsock_probe, .remove = virtio_vsock_remove, #ifdef CONFIG_PM_SLEEP .freeze = virtio_vsock_freeze, .restore = virtio_vsock_restore, #endif }; static int __init virtio_vsock_init(void) { int ret; virtio_vsock_workqueue = alloc_workqueue("virtio_vsock", 0, 0); if (!virtio_vsock_workqueue) return -ENOMEM; ret = vsock_core_register(&virtio_transport.transport, VSOCK_TRANSPORT_F_G2H); if (ret) goto out_wq; ret = register_virtio_driver(&virtio_vsock_driver); if (ret) goto out_vci; return 0; out_vci: vsock_core_unregister(&virtio_transport.transport); out_wq: destroy_workqueue(virtio_vsock_workqueue); return ret; } static void __exit virtio_vsock_exit(void) { unregister_virtio_driver(&virtio_vsock_driver); vsock_core_unregister(&virtio_transport.transport); destroy_workqueue(virtio_vsock_workqueue); } module_init(virtio_vsock_init); module_exit(virtio_vsock_exit); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Asias He"); MODULE_DESCRIPTION("virtio transport for vsock"); MODULE_DEVICE_TABLE(virtio, id_table); |
| 188 187 186 188 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BACKING_DEV_DEFS_H #define __LINUX_BACKING_DEV_DEFS_H #include <linux/list.h> #include <linux/radix-tree.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/percpu_counter.h> #include <linux/percpu-refcount.h> #include <linux/flex_proportions.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/kref.h> #include <linux/refcount.h> struct page; struct device; struct dentry; /* * Bits in bdi_writeback.state */ enum wb_state { WB_registered, /* bdi_register() was done */ WB_writeback_running, /* Writeback is in progress */ WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */ WB_start_all, /* nr_pages == 0 (all) work pending */ }; enum wb_stat_item { WB_RECLAIMABLE, WB_WRITEBACK, WB_DIRTIED, WB_WRITTEN, NR_WB_STAT_ITEMS }; #define WB_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) /* * why some writeback work was initiated */ enum wb_reason { WB_REASON_BACKGROUND, WB_REASON_VMSCAN, WB_REASON_SYNC, WB_REASON_PERIODIC, WB_REASON_LAPTOP_TIMER, WB_REASON_FS_FREE_SPACE, /* * There is no bdi forker thread any more and works are done * by emergency worker, however, this is TPs userland visible * and we'll be exposing exactly the same information, * so it has a mismatch name. */ WB_REASON_FORKER_THREAD, WB_REASON_FOREIGN_FLUSH, WB_REASON_MAX, }; struct wb_completion { atomic_t cnt; wait_queue_head_t *waitq; }; #define __WB_COMPLETION_INIT(_waitq) \ (struct wb_completion){ .cnt = ATOMIC_INIT(1), .waitq = (_waitq) } /* * If one wants to wait for one or more wb_writeback_works, each work's * ->done should be set to a wb_completion defined using the following * macro. Once all work items are issued with wb_queue_work(), the caller * can wait for the completion of all using wb_wait_for_completion(). Work * items which are waited upon aren't freed automatically on completion. */ #define WB_COMPLETION_INIT(bdi) __WB_COMPLETION_INIT(&(bdi)->wb_waitq) #define DEFINE_WB_COMPLETION(cmpl, bdi) \ struct wb_completion cmpl = WB_COMPLETION_INIT(bdi) /* * Each wb (bdi_writeback) can perform writeback operations, is measured * and throttled, independently. Without cgroup writeback, each bdi * (bdi_writeback) is served by its embedded bdi->wb. * * On the default hierarchy, blkcg implicitly enables memcg. This allows * using memcg's page ownership for attributing writeback IOs, and every * memcg - blkcg combination can be served by its own wb by assigning a * dedicated wb to each memcg, which enables isolation across different * cgroups and propagation of IO back pressure down from the IO layer upto * the tasks which are generating the dirty pages to be written back. * * A cgroup wb is indexed on its bdi by the ID of the associated memcg, * refcounted with the number of inodes attached to it, and pins the memcg * and the corresponding blkcg. As the corresponding blkcg for a memcg may * change as blkcg is disabled and enabled higher up in the hierarchy, a wb * is tested for blkcg after lookup and removed from index on mismatch so * that a new wb for the combination can be created. * * Each bdi_writeback that is not embedded into the backing_dev_info must hold * a reference to the parent backing_dev_info. See cgwb_create() for details. */ struct bdi_writeback { struct backing_dev_info *bdi; /* our parent bdi */ unsigned long state; /* Always use atomic bitops on this */ unsigned long last_old_flush; /* last old data flush */ struct list_head b_dirty; /* dirty inodes */ struct list_head b_io; /* parked for writeback */ struct list_head b_more_io; /* parked for more writeback */ struct list_head b_dirty_time; /* time stamps are dirty */ spinlock_t list_lock; /* protects the b_* lists */ atomic_t writeback_inodes; /* number of inodes under writeback */ struct percpu_counter stat[NR_WB_STAT_ITEMS]; unsigned long bw_time_stamp; /* last time write bw is updated */ unsigned long dirtied_stamp; unsigned long written_stamp; /* pages written at bw_time_stamp */ unsigned long write_bandwidth; /* the estimated write bandwidth */ unsigned long avg_write_bandwidth; /* further smoothed write bw, > 0 */ /* * The base dirty throttle rate, re-calculated on every 200ms. * All the bdi tasks' dirty rate will be curbed under it. * @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit * in small steps and is much more smooth/stable than the latter. */ unsigned long dirty_ratelimit; unsigned long balanced_dirty_ratelimit; struct fprop_local_percpu completions; int dirty_exceeded; enum wb_reason start_all_reason; spinlock_t work_lock; /* protects work_list & dwork scheduling */ struct list_head work_list; struct delayed_work dwork; /* work item used for writeback */ struct delayed_work bw_dwork; /* work item used for bandwidth estimate */ struct list_head bdi_node; /* anchored at bdi->wb_list */ #ifdef CONFIG_CGROUP_WRITEBACK struct percpu_ref refcnt; /* used only for !root wb's */ struct fprop_local_percpu memcg_completions; struct cgroup_subsys_state *memcg_css; /* the associated memcg */ struct cgroup_subsys_state *blkcg_css; /* and blkcg */ struct list_head memcg_node; /* anchored at memcg->cgwb_list */ struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */ struct list_head b_attached; /* attached inodes, protected by list_lock */ struct list_head offline_node; /* anchored at offline_cgwbs */ union { struct work_struct release_work; struct rcu_head rcu; }; #endif }; struct backing_dev_info { u64 id; struct rb_node rb_node; /* keyed by ->id */ struct list_head bdi_list; unsigned long ra_pages; /* max readahead in PAGE_SIZE units */ unsigned long io_pages; /* max allowed IO size */ struct kref refcnt; /* Reference counter for the structure */ unsigned int capabilities; /* Device capabilities */ unsigned int min_ratio; unsigned int max_ratio, max_prop_frac; /* * Sum of avg_write_bw of wbs with dirty inodes. > 0 if there are * any dirty wbs, which is depended upon by bdi_has_dirty(). */ atomic_long_t tot_write_bandwidth; /* * Jiffies when last process was dirty throttled on this bdi. Used by * blk-wbt. */ unsigned long last_bdp_sleep; struct bdi_writeback wb; /* the root writeback info for this bdi */ struct list_head wb_list; /* list of all wbs */ #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */ #endif wait_queue_head_t wb_waitq; struct device *dev; char dev_name[64]; struct device *owner; struct timer_list laptop_mode_wb_timer; #ifdef CONFIG_DEBUG_FS struct dentry *debug_dir; #endif }; struct wb_lock_cookie { bool locked; unsigned long flags; }; #ifdef CONFIG_CGROUP_WRITEBACK /** * wb_tryget - try to increment a wb's refcount * @wb: bdi_writeback to get */ static inline bool wb_tryget(struct bdi_writeback *wb) { if (wb != &wb->bdi->wb) return percpu_ref_tryget(&wb->refcnt); return true; } /** * wb_get - increment a wb's refcount * @wb: bdi_writeback to get */ static inline void wb_get(struct bdi_writeback *wb) { if (wb != &wb->bdi->wb) percpu_ref_get(&wb->refcnt); } /** * wb_put - decrement a wb's refcount * @wb: bdi_writeback to put * @nr: number of references to put */ static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr) { if (WARN_ON_ONCE(!wb->bdi)) { /* * A driver bug might cause a file to be removed before bdi was * initialized. */ return; } if (wb != &wb->bdi->wb) percpu_ref_put_many(&wb->refcnt, nr); } /** * wb_put - decrement a wb's refcount * @wb: bdi_writeback to put */ static inline void wb_put(struct bdi_writeback *wb) { wb_put_many(wb, 1); } /** * wb_dying - is a wb dying? * @wb: bdi_writeback of interest * * Returns whether @wb is unlinked and being drained. */ static inline bool wb_dying(struct bdi_writeback *wb) { return percpu_ref_is_dying(&wb->refcnt); } #else /* CONFIG_CGROUP_WRITEBACK */ static inline bool wb_tryget(struct bdi_writeback *wb) { return true; } static inline void wb_get(struct bdi_writeback *wb) { } static inline void wb_put(struct bdi_writeback *wb) { } static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr) { } static inline bool wb_dying(struct bdi_writeback *wb) { return false; } #endif /* CONFIG_CGROUP_WRITEBACK */ #endif /* __LINUX_BACKING_DEV_DEFS_H */ |
| 2 1 1 1 4 4 1 4 4 9 2 8 10 5 4 8 5 4 4 1 4 4 4 3 3 3 3 3 3 3 4 4 4 1 1 1 2 1 1 1 2 9 9 9 9 7 7 7 1 6 1 5 3 4 4 7 3 3 3 3 1 3 3 4 4 4 4 4 4 4 4 1 1 1 3 3 3 4 3 2 1 1 2 2 2 2 3 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2023 Isovalent */ #include <linux/bpf.h> #include <linux/bpf_mprog.h> static int bpf_mprog_link(struct bpf_tuple *tuple, u32 id_or_fd, u32 flags, enum bpf_prog_type type) { struct bpf_link *link = ERR_PTR(-EINVAL); bool id = flags & BPF_F_ID; if (id) link = bpf_link_by_id(id_or_fd); else if (id_or_fd) link = bpf_link_get_from_fd(id_or_fd); if (IS_ERR(link)) return PTR_ERR(link); if (type && link->prog->type != type) { bpf_link_put(link); return -EINVAL; } tuple->link = link; tuple->prog = link->prog; return 0; } static int bpf_mprog_prog(struct bpf_tuple *tuple, u32 id_or_fd, u32 flags, enum bpf_prog_type type) { struct bpf_prog *prog = ERR_PTR(-EINVAL); bool id = flags & BPF_F_ID; if (id) prog = bpf_prog_by_id(id_or_fd); else if (id_or_fd) prog = bpf_prog_get(id_or_fd); if (IS_ERR(prog)) return PTR_ERR(prog); if (type && prog->type != type) { bpf_prog_put(prog); return -EINVAL; } tuple->link = NULL; tuple->prog = prog; return 0; } static int bpf_mprog_tuple_relative(struct bpf_tuple *tuple, u32 id_or_fd, u32 flags, enum bpf_prog_type type) { bool link = flags & BPF_F_LINK; bool id = flags & BPF_F_ID; memset(tuple, 0, sizeof(*tuple)); if (link) return bpf_mprog_link(tuple, id_or_fd, flags, type); /* If no relevant flag is set and no id_or_fd was passed, then * tuple link/prog is just NULLed. This is the case when before/ * after selects first/last position without passing fd. */ if (!id && !id_or_fd) return 0; return bpf_mprog_prog(tuple, id_or_fd, flags, type); } static void bpf_mprog_tuple_put(struct bpf_tuple *tuple) { if (tuple->link) bpf_link_put(tuple->link); else if (tuple->prog) bpf_prog_put(tuple->prog); } /* The bpf_mprog_{replace,delete}() operate on exact idx position with the * one exception that for deletion we support delete from front/back. In * case of front idx is -1, in case of back idx is bpf_mprog_total(entry). * Adjustment to first and last entry is trivial. The bpf_mprog_insert() * we have to deal with the following cases: * * idx + before: * * Insert P4 before P3: idx for old array is 1, idx for new array is 2, * hence we adjust target idx for the new array, so that memmove copies * P1 and P2 to the new entry, and we insert P4 into idx 2. Inserting * before P1 would have old idx -1 and new idx 0. * * +--+--+--+ +--+--+--+--+ +--+--+--+--+ * |P1|P2|P3| ==> |P1|P2| |P3| ==> |P1|P2|P4|P3| * +--+--+--+ +--+--+--+--+ +--+--+--+--+ * * idx + after: * * Insert P4 after P2: idx for old array is 2, idx for new array is 2. * Again, memmove copies P1 and P2 to the new entry, and we insert P4 * into idx 2. Inserting after P3 would have both old/new idx at 4 aka * bpf_mprog_total(entry). * * +--+--+--+ +--+--+--+--+ +--+--+--+--+ * |P1|P2|P3| ==> |P1|P2| |P3| ==> |P1|P2|P4|P3| * +--+--+--+ +--+--+--+--+ +--+--+--+--+ */ static int bpf_mprog_replace(struct bpf_mprog_entry *entry, struct bpf_mprog_entry **entry_new, struct bpf_tuple *ntuple, int idx) { struct bpf_mprog_fp *fp; struct bpf_mprog_cp *cp; struct bpf_prog *oprog; bpf_mprog_read(entry, idx, &fp, &cp); oprog = READ_ONCE(fp->prog); bpf_mprog_write(fp, cp, ntuple); if (!ntuple->link) { WARN_ON_ONCE(cp->link); bpf_prog_put(oprog); } *entry_new = entry; return 0; } static int bpf_mprog_insert(struct bpf_mprog_entry *entry, struct bpf_mprog_entry **entry_new, struct bpf_tuple *ntuple, int idx, u32 flags) { int total = bpf_mprog_total(entry); struct bpf_mprog_entry *peer; struct bpf_mprog_fp *fp; struct bpf_mprog_cp *cp; peer = bpf_mprog_peer(entry); bpf_mprog_entry_copy(peer, entry); if (idx == total) goto insert; else if (flags & BPF_F_BEFORE) idx += 1; bpf_mprog_entry_grow(peer, idx); insert: bpf_mprog_read(peer, idx, &fp, &cp); bpf_mprog_write(fp, cp, ntuple); bpf_mprog_inc(peer); *entry_new = peer; return 0; } static int bpf_mprog_delete(struct bpf_mprog_entry *entry, struct bpf_mprog_entry **entry_new, struct bpf_tuple *dtuple, int idx) { int total = bpf_mprog_total(entry); struct bpf_mprog_entry *peer; peer = bpf_mprog_peer(entry); bpf_mprog_entry_copy(peer, entry); if (idx == -1) idx = 0; else if (idx == total) idx = total - 1; bpf_mprog_entry_shrink(peer, idx); bpf_mprog_dec(peer); bpf_mprog_mark_for_release(peer, dtuple); *entry_new = peer; return 0; } /* In bpf_mprog_pos_*() we evaluate the target position for the BPF * program/link that needs to be replaced, inserted or deleted for * each "rule" independently. If all rules agree on that position * or existing element, then enact replacement, addition or deletion. * If this is not the case, then the request cannot be satisfied and * we bail out with an error. */ static int bpf_mprog_pos_exact(struct bpf_mprog_entry *entry, struct bpf_tuple *tuple) { struct bpf_mprog_fp *fp; struct bpf_mprog_cp *cp; int i; for (i = 0; i < bpf_mprog_total(entry); i++) { bpf_mprog_read(entry, i, &fp, &cp); if (tuple->prog == READ_ONCE(fp->prog)) return tuple->link == cp->link ? i : -EBUSY; } return -ENOENT; } static int bpf_mprog_pos_before(struct bpf_mprog_entry *entry, struct bpf_tuple *tuple) { struct bpf_mprog_fp *fp; struct bpf_mprog_cp *cp; int i; for (i = 0; i < bpf_mprog_total(entry); i++) { bpf_mprog_read(entry, i, &fp, &cp); if (tuple->prog == READ_ONCE(fp->prog) && (!tuple->link || tuple->link == cp->link)) return i - 1; } return tuple->prog ? -ENOENT : -1; } static int bpf_mprog_pos_after(struct bpf_mprog_entry *entry, struct bpf_tuple *tuple) { struct bpf_mprog_fp *fp; struct bpf_mprog_cp *cp; int i; for (i = 0; i < bpf_mprog_total(entry); i++) { bpf_mprog_read(entry, i, &fp, &cp); if (tuple->prog == READ_ONCE(fp->prog) && (!tuple->link || tuple->link == cp->link)) return i + 1; } return tuple->prog ? -ENOENT : bpf_mprog_total(entry); } int bpf_mprog_attach(struct bpf_mprog_entry *entry, struct bpf_mprog_entry **entry_new, struct bpf_prog *prog_new, struct bpf_link *link, struct bpf_prog *prog_old, u32 flags, u32 id_or_fd, u64 revision) { struct bpf_tuple rtuple, ntuple = { .prog = prog_new, .link = link, }, otuple = { .prog = prog_old, .link = link, }; int ret, idx = -ERANGE, tidx; if (revision && revision != bpf_mprog_revision(entry)) return -ESTALE; if (bpf_mprog_exists(entry, prog_new)) return -EEXIST; ret = bpf_mprog_tuple_relative(&rtuple, id_or_fd, flags & ~BPF_F_REPLACE, prog_new->type); if (ret) return ret; if (flags & BPF_F_REPLACE) { tidx = bpf_mprog_pos_exact(entry, &otuple); if (tidx < 0) { ret = tidx; goto out; } idx = tidx; } else if (bpf_mprog_total(entry) == bpf_mprog_max()) { ret = -ERANGE; goto out; } if (flags & BPF_F_BEFORE) { tidx = bpf_mprog_pos_before(entry, &rtuple); if (tidx < -1 || (idx >= -1 && tidx != idx)) { ret = tidx < -1 ? tidx : -ERANGE; goto out; } idx = tidx; } if (flags & BPF_F_AFTER) { tidx = bpf_mprog_pos_after(entry, &rtuple); if (tidx < -1 || (idx >= -1 && tidx != idx)) { ret = tidx < 0 ? tidx : -ERANGE; goto out; } idx = tidx; } if (idx < -1) { if (rtuple.prog || flags) { ret = -EINVAL; goto out; } idx = bpf_mprog_total(entry); flags = BPF_F_AFTER; } if (idx >= bpf_mprog_max()) { ret = -ERANGE; goto out; } if (flags & BPF_F_REPLACE) ret = bpf_mprog_replace(entry, entry_new, &ntuple, idx); else ret = bpf_mprog_insert(entry, entry_new, &ntuple, idx, flags); out: bpf_mprog_tuple_put(&rtuple); return ret; } static int bpf_mprog_fetch(struct bpf_mprog_entry *entry, struct bpf_tuple *tuple, int idx) { int total = bpf_mprog_total(entry); struct bpf_mprog_cp *cp; struct bpf_mprog_fp *fp; struct bpf_prog *prog; struct bpf_link *link; if (idx == -1) idx = 0; else if (idx == total) idx = total - 1; bpf_mprog_read(entry, idx, &fp, &cp); prog = READ_ONCE(fp->prog); link = cp->link; /* The deletion request can either be without filled tuple in which * case it gets populated here based on idx, or with filled tuple * where the only thing we end up doing is the WARN_ON_ONCE() assert. * If we hit a BPF link at the given index, it must not be removed * from opts path. */ if (link && !tuple->link) return -EBUSY; WARN_ON_ONCE(tuple->prog && tuple->prog != prog); WARN_ON_ONCE(tuple->link && tuple->link != link); tuple->prog = prog; tuple->link = link; return 0; } int bpf_mprog_detach(struct bpf_mprog_entry *entry, struct bpf_mprog_entry **entry_new, struct bpf_prog *prog, struct bpf_link *link, u32 flags, u32 id_or_fd, u64 revision) { struct bpf_tuple rtuple, dtuple = { .prog = prog, .link = link, }; int ret, idx = -ERANGE, tidx; if (flags & BPF_F_REPLACE) return -EINVAL; if (revision && revision != bpf_mprog_revision(entry)) return -ESTALE; if (!bpf_mprog_total(entry)) return -ENOENT; ret = bpf_mprog_tuple_relative(&rtuple, id_or_fd, flags, prog ? prog->type : BPF_PROG_TYPE_UNSPEC); if (ret) return ret; if (dtuple.prog) { tidx = bpf_mprog_pos_exact(entry, &dtuple); if (tidx < 0) { ret = tidx; goto out; } idx = tidx; } if (flags & BPF_F_BEFORE) { tidx = bpf_mprog_pos_before(entry, &rtuple); if (tidx < -1 || (idx >= -1 && tidx != idx)) { ret = tidx < -1 ? tidx : -ERANGE; goto out; } idx = tidx; } if (flags & BPF_F_AFTER) { tidx = bpf_mprog_pos_after(entry, &rtuple); if (tidx < -1 || (idx >= -1 && tidx != idx)) { ret = tidx < 0 ? tidx : -ERANGE; goto out; } idx = tidx; } if (idx < -1) { if (rtuple.prog || flags) { ret = -EINVAL; goto out; } idx = bpf_mprog_total(entry); flags = BPF_F_AFTER; } if (idx >= bpf_mprog_max()) { ret = -ERANGE; goto out; } ret = bpf_mprog_fetch(entry, &dtuple, idx); if (ret) goto out; ret = bpf_mprog_delete(entry, entry_new, &dtuple, idx); out: bpf_mprog_tuple_put(&rtuple); return ret; } int bpf_mprog_query(const union bpf_attr *attr, union bpf_attr __user *uattr, struct bpf_mprog_entry *entry) { u32 __user *uprog_flags, *ulink_flags; u32 __user *uprog_id, *ulink_id; struct bpf_mprog_fp *fp; struct bpf_mprog_cp *cp; struct bpf_prog *prog; const u32 flags = 0; u32 id, count = 0; u64 revision = 1; int i, ret = 0; if (attr->query.query_flags || attr->query.attach_flags) return -EINVAL; if (entry) { revision = bpf_mprog_revision(entry); count = bpf_mprog_total(entry); } if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) return -EFAULT; if (copy_to_user(&uattr->query.revision, &revision, sizeof(revision))) return -EFAULT; if (copy_to_user(&uattr->query.count, &count, sizeof(count))) return -EFAULT; uprog_id = u64_to_user_ptr(attr->query.prog_ids); uprog_flags = u64_to_user_ptr(attr->query.prog_attach_flags); ulink_id = u64_to_user_ptr(attr->query.link_ids); ulink_flags = u64_to_user_ptr(attr->query.link_attach_flags); if (attr->query.count == 0 || !uprog_id || !count) return 0; if (attr->query.count < count) { count = attr->query.count; ret = -ENOSPC; } for (i = 0; i < bpf_mprog_max(); i++) { bpf_mprog_read(entry, i, &fp, &cp); prog = READ_ONCE(fp->prog); if (!prog) break; id = prog->aux->id; if (copy_to_user(uprog_id + i, &id, sizeof(id))) return -EFAULT; if (uprog_flags && copy_to_user(uprog_flags + i, &flags, sizeof(flags))) return -EFAULT; id = cp->link ? cp->link->id : 0; if (ulink_id && copy_to_user(ulink_id + i, &id, sizeof(id))) return -EFAULT; if (ulink_flags && copy_to_user(ulink_flags + i, &flags, sizeof(flags))) return -EFAULT; if (i + 1 == count) break; } return ret; } |
| 9 10 9 9 24 25 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * bvec iterator * * Copyright (C) 2001 Ming Lei <ming.lei@canonical.com> */ #ifndef __LINUX_BVEC_H #define __LINUX_BVEC_H #include <linux/highmem.h> #include <linux/bug.h> #include <linux/errno.h> #include <linux/limits.h> #include <linux/minmax.h> #include <linux/types.h> struct page; /** * struct bio_vec - a contiguous range of physical memory addresses * @bv_page: First page associated with the address range. * @bv_len: Number of bytes in the address range. * @bv_offset: Start of the address range relative to the start of @bv_page. * * The following holds for a bvec if n * PAGE_SIZE < bv_offset + bv_len: * * nth_page(@bv_page, n) == @bv_page + n * * This holds because page_is_mergeable() checks the above property. */ struct bio_vec { struct page *bv_page; unsigned int bv_len; unsigned int bv_offset; }; /** * bvec_set_page - initialize a bvec based off a struct page * @bv: bvec to initialize * @page: page the bvec should point to * @len: length of the bvec * @offset: offset into the page */ static inline void bvec_set_page(struct bio_vec *bv, struct page *page, unsigned int len, unsigned int offset) { bv->bv_page = page; bv->bv_len = len; bv->bv_offset = offset; } /** * bvec_set_folio - initialize a bvec based off a struct folio * @bv: bvec to initialize * @folio: folio the bvec should point to * @len: length of the bvec * @offset: offset into the folio */ static inline void bvec_set_folio(struct bio_vec *bv, struct folio *folio, unsigned int len, unsigned int offset) { bvec_set_page(bv, &folio->page, len, offset); } /** * bvec_set_virt - initialize a bvec based on a virtual address * @bv: bvec to initialize * @vaddr: virtual address to set the bvec to * @len: length of the bvec */ static inline void bvec_set_virt(struct bio_vec *bv, void *vaddr, unsigned int len) { bvec_set_page(bv, virt_to_page(vaddr), len, offset_in_page(vaddr)); } struct bvec_iter { sector_t bi_sector; /* device address in 512 byte sectors */ unsigned int bi_size; /* residual I/O count */ unsigned int bi_idx; /* current index into bvl_vec */ unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ } __packed __aligned(4); struct bvec_iter_all { struct bio_vec bv; int idx; unsigned done; }; /* * various member access, note that bio_data should of course not be used * on highmem page vectors */ #define __bvec_iter_bvec(bvec, iter) (&(bvec)[(iter).bi_idx]) /* multi-page (mp_bvec) helpers */ #define mp_bvec_iter_page(bvec, iter) \ (__bvec_iter_bvec((bvec), (iter))->bv_page) #define mp_bvec_iter_len(bvec, iter) \ min((iter).bi_size, \ __bvec_iter_bvec((bvec), (iter))->bv_len - (iter).bi_bvec_done) #define mp_bvec_iter_offset(bvec, iter) \ (__bvec_iter_bvec((bvec), (iter))->bv_offset + (iter).bi_bvec_done) #define mp_bvec_iter_page_idx(bvec, iter) \ (mp_bvec_iter_offset((bvec), (iter)) / PAGE_SIZE) #define mp_bvec_iter_bvec(bvec, iter) \ ((struct bio_vec) { \ .bv_page = mp_bvec_iter_page((bvec), (iter)), \ .bv_len = mp_bvec_iter_len((bvec), (iter)), \ .bv_offset = mp_bvec_iter_offset((bvec), (iter)), \ }) /* For building single-page bvec in flight */ #define bvec_iter_offset(bvec, iter) \ (mp_bvec_iter_offset((bvec), (iter)) % PAGE_SIZE) #define bvec_iter_len(bvec, iter) \ min_t(unsigned, mp_bvec_iter_len((bvec), (iter)), \ PAGE_SIZE - bvec_iter_offset((bvec), (iter))) #define bvec_iter_page(bvec, iter) \ (mp_bvec_iter_page((bvec), (iter)) + \ mp_bvec_iter_page_idx((bvec), (iter))) #define bvec_iter_bvec(bvec, iter) \ ((struct bio_vec) { \ .bv_page = bvec_iter_page((bvec), (iter)), \ .bv_len = bvec_iter_len((bvec), (iter)), \ .bv_offset = bvec_iter_offset((bvec), (iter)), \ }) static inline bool bvec_iter_advance(const struct bio_vec *bv, struct bvec_iter *iter, unsigned bytes) { unsigned int idx = iter->bi_idx; if (WARN_ONCE(bytes > iter->bi_size, "Attempted to advance past end of bvec iter\n")) { iter->bi_size = 0; return false; } iter->bi_size -= bytes; bytes += iter->bi_bvec_done; while (bytes && bytes >= bv[idx].bv_len) { bytes -= bv[idx].bv_len; idx++; } iter->bi_idx = idx; iter->bi_bvec_done = bytes; return true; } /* * A simpler version of bvec_iter_advance(), @bytes should not span * across multiple bvec entries, i.e. bytes <= bv[i->bi_idx].bv_len */ static inline void bvec_iter_advance_single(const struct bio_vec *bv, struct bvec_iter *iter, unsigned int bytes) { unsigned int done = iter->bi_bvec_done + bytes; if (done == bv[iter->bi_idx].bv_len) { done = 0; iter->bi_idx++; } iter->bi_bvec_done = done; iter->bi_size -= bytes; } #define for_each_bvec(bvl, bio_vec, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = bvec_iter_bvec((bio_vec), (iter))), 1); \ bvec_iter_advance_single((bio_vec), &(iter), (bvl).bv_len)) /* for iterating one bio from start to end */ #define BVEC_ITER_ALL_INIT (struct bvec_iter) \ { \ .bi_sector = 0, \ .bi_size = UINT_MAX, \ .bi_idx = 0, \ .bi_bvec_done = 0, \ } static inline struct bio_vec *bvec_init_iter_all(struct bvec_iter_all *iter_all) { iter_all->done = 0; iter_all->idx = 0; return &iter_all->bv; } static inline void bvec_advance(const struct bio_vec *bvec, struct bvec_iter_all *iter_all) { struct bio_vec *bv = &iter_all->bv; if (iter_all->done) { bv->bv_page++; bv->bv_offset = 0; } else { bv->bv_page = bvec->bv_page + (bvec->bv_offset >> PAGE_SHIFT); bv->bv_offset = bvec->bv_offset & ~PAGE_MASK; } bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset, bvec->bv_len - iter_all->done); iter_all->done += bv->bv_len; if (iter_all->done == bvec->bv_len) { iter_all->idx++; iter_all->done = 0; } } /** * bvec_kmap_local - map a bvec into the kernel virtual address space * @bvec: bvec to map * * Must be called on single-page bvecs only. Call kunmap_local on the returned * address to unmap. */ static inline void *bvec_kmap_local(struct bio_vec *bvec) { return kmap_local_page(bvec->bv_page) + bvec->bv_offset; } /** * memcpy_from_bvec - copy data from a bvec * @bvec: bvec to copy from * * Must be called on single-page bvecs only. */ static inline void memcpy_from_bvec(char *to, struct bio_vec *bvec) { memcpy_from_page(to, bvec->bv_page, bvec->bv_offset, bvec->bv_len); } /** * memcpy_to_bvec - copy data to a bvec * @bvec: bvec to copy to * * Must be called on single-page bvecs only. */ static inline void memcpy_to_bvec(struct bio_vec *bvec, const char *from) { memcpy_to_page(bvec->bv_page, bvec->bv_offset, from, bvec->bv_len); } /** * memzero_bvec - zero all data in a bvec * @bvec: bvec to zero * * Must be called on single-page bvecs only. */ static inline void memzero_bvec(struct bio_vec *bvec) { memzero_page(bvec->bv_page, bvec->bv_offset, bvec->bv_len); } /** * bvec_virt - return the virtual address for a bvec * @bvec: bvec to return the virtual address for * * Note: the caller must ensure that @bvec->bv_page is not a highmem page. */ static inline void *bvec_virt(struct bio_vec *bvec) { WARN_ON_ONCE(PageHighMem(bvec->bv_page)); return page_address(bvec->bv_page) + bvec->bv_offset; } #endif /* __LINUX_BVEC_H */ |
| 17 14 17 1 17 18 18 17 18 18 2 6 4 6 8 6 5 6 1 5 4 6 8 17 17 17 17 15 2 2 15 14 2 13 3 3 3 3 13 12 1 11 13 3 1 14 1 1 13 14 14 14 12 1 12 1 11 1 11 10 12 6 6 6 6 6 6 6 5 5 5 5 5 4 3 4 1 1 18 19 19 5 5 5 5 5 17 10 9 2 4 4 4 4 4 4 4 1 4 1 2 2 2 1 1 1 2 2 9 9 9 2 9 9 9 2 3 2 1 6 3 5 2 6 5 5 5 5 6 6 12 12 12 2 5 4 3 2 1 1 1 5 5 5 5 5 2 2 2 5 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 3 2 1 1 3 3 3 1 3 3 3 3 3 3 5 4 4 1 4 1 10 7 5 2 7 2 7 7 7 7 7 4 2 1 8 3 3 8 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 12 8 7 1 7 5 5 5 5 5 2 1 3 2 10 10 9 9 9 10 8 2 10 10 10 10 10 2 2 10 10 10 1 7 1 7 5 7 4 2 2 7 7 2 5 1 1 1 9 4 9 2 2 2 2 2 1 1 1 1 1 5 5 3 5 15 15 11 13 3 3 3 3 3 3 3 3 3 4 4 2 2 4 2 2 11 11 4 4 11 4 4 4 1 1 1 4 4 1 1 1 1 1 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 3 3 3 2 4 4 4 3 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 5 6 6 6 3 3 1 6 6 6 6 6 6 6 3 6 6 6 6 6 6 6 1 1 1 1 1 1 1 2 1 1 2 2 2 2 2 2 2 2 1 1 2 2 2 2 2 2 2 2 2 2 1 1 3 3 9 2 9 9 6 7 7 2 6 6 9 7 2 8 5 5 5 8 8 6 8 3 1 1 1 1 1 1 1 1 1 6 | 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 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 | /* FUSE: Filesystem in Userspace Copyright (C) 2001-2008 Miklos Szeredi <miklos@szeredi.hu> This program can be distributed under the terms of the GNU GPL. See the file COPYING. */ #include "fuse_i.h" #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/signal.h> #include <linux/module.h> #include <linux/swap.h> #include <linux/falloc.h> #include <linux/uio.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/splice.h> #include <linux/task_io_accounting_ops.h> static int fuse_send_open(struct fuse_mount *fm, u64 nodeid, unsigned int open_flags, int opcode, struct fuse_open_out *outargp) { struct fuse_open_in inarg; FUSE_ARGS(args); memset(&inarg, 0, sizeof(inarg)); inarg.flags = open_flags & ~(O_CREAT | O_EXCL | O_NOCTTY); if (!fm->fc->atomic_o_trunc) inarg.flags &= ~O_TRUNC; if (fm->fc->handle_killpriv_v2 && (inarg.flags & O_TRUNC) && !capable(CAP_FSETID)) { inarg.open_flags |= FUSE_OPEN_KILL_SUIDGID; } args.opcode = opcode; args.nodeid = nodeid; args.in_numargs = 1; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; args.out_numargs = 1; args.out_args[0].size = sizeof(*outargp); args.out_args[0].value = outargp; return fuse_simple_request(fm, &args); } struct fuse_file *fuse_file_alloc(struct fuse_mount *fm, bool release) { struct fuse_file *ff; ff = kzalloc(sizeof(struct fuse_file), GFP_KERNEL_ACCOUNT); if (unlikely(!ff)) return NULL; ff->fm = fm; if (release) { ff->args = kzalloc(sizeof(*ff->args), GFP_KERNEL_ACCOUNT); if (!ff->args) { kfree(ff); return NULL; } } INIT_LIST_HEAD(&ff->write_entry); refcount_set(&ff->count, 1); RB_CLEAR_NODE(&ff->polled_node); init_waitqueue_head(&ff->poll_wait); ff->kh = atomic64_inc_return(&fm->fc->khctr); return ff; } void fuse_file_free(struct fuse_file *ff) { kfree(ff->args); kfree(ff); } static struct fuse_file *fuse_file_get(struct fuse_file *ff) { refcount_inc(&ff->count); return ff; } static void fuse_release_end(struct fuse_mount *fm, struct fuse_args *args, int error) { struct fuse_release_args *ra = container_of(args, typeof(*ra), args); iput(ra->inode); kfree(ra); } static void fuse_file_put(struct fuse_file *ff, bool sync) { if (refcount_dec_and_test(&ff->count)) { struct fuse_release_args *ra = &ff->args->release_args; struct fuse_args *args = (ra ? &ra->args : NULL); if (ra && ra->inode) fuse_file_io_release(ff, ra->inode); if (!args) { /* Do nothing when server does not implement 'open' */ } else if (sync) { fuse_simple_request(ff->fm, args); fuse_release_end(ff->fm, args, 0); } else { args->end = fuse_release_end; if (fuse_simple_background(ff->fm, args, GFP_KERNEL | __GFP_NOFAIL)) fuse_release_end(ff->fm, args, -ENOTCONN); } kfree(ff); } } struct fuse_file *fuse_file_open(struct fuse_mount *fm, u64 nodeid, unsigned int open_flags, bool isdir) { struct fuse_conn *fc = fm->fc; struct fuse_file *ff; int opcode = isdir ? FUSE_OPENDIR : FUSE_OPEN; bool open = isdir ? !fc->no_opendir : !fc->no_open; ff = fuse_file_alloc(fm, open); if (!ff) return ERR_PTR(-ENOMEM); ff->fh = 0; /* Default for no-open */ ff->open_flags = FOPEN_KEEP_CACHE | (isdir ? FOPEN_CACHE_DIR : 0); if (open) { /* Store outarg for fuse_finish_open() */ struct fuse_open_out *outargp = &ff->args->open_outarg; int err; err = fuse_send_open(fm, nodeid, open_flags, opcode, outargp); if (!err) { ff->fh = outargp->fh; ff->open_flags = outargp->open_flags; } else if (err != -ENOSYS) { fuse_file_free(ff); return ERR_PTR(err); } else { /* No release needed */ kfree(ff->args); ff->args = NULL; if (isdir) fc->no_opendir = 1; else fc->no_open = 1; } } if (isdir) ff->open_flags &= ~FOPEN_DIRECT_IO; ff->nodeid = nodeid; return ff; } int fuse_do_open(struct fuse_mount *fm, u64 nodeid, struct file *file, bool isdir) { struct fuse_file *ff = fuse_file_open(fm, nodeid, file->f_flags, isdir); if (!IS_ERR(ff)) file->private_data = ff; return PTR_ERR_OR_ZERO(ff); } EXPORT_SYMBOL_GPL(fuse_do_open); static void fuse_link_write_file(struct file *file) { struct inode *inode = file_inode(file); struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_file *ff = file->private_data; /* * file may be written through mmap, so chain it onto the * inodes's write_file list */ spin_lock(&fi->lock); if (list_empty(&ff->write_entry)) list_add(&ff->write_entry, &fi->write_files); spin_unlock(&fi->lock); } int fuse_finish_open(struct inode *inode, struct file *file) { struct fuse_file *ff = file->private_data; struct fuse_conn *fc = get_fuse_conn(inode); int err; err = fuse_file_io_open(file, inode); if (err) return err; if (ff->open_flags & FOPEN_STREAM) stream_open(inode, file); else if (ff->open_flags & FOPEN_NONSEEKABLE) nonseekable_open(inode, file); if ((file->f_mode & FMODE_WRITE) && fc->writeback_cache) fuse_link_write_file(file); return 0; } static void fuse_truncate_update_attr(struct inode *inode, struct file *file) { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); spin_lock(&fi->lock); fi->attr_version = atomic64_inc_return(&fc->attr_version); i_size_write(inode, 0); spin_unlock(&fi->lock); file_update_time(file); fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE); } static int fuse_open(struct inode *inode, struct file *file) { struct fuse_mount *fm = get_fuse_mount(inode); struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_conn *fc = fm->fc; struct fuse_file *ff; int err; bool is_truncate = (file->f_flags & O_TRUNC) && fc->atomic_o_trunc; bool is_wb_truncate = is_truncate && fc->writeback_cache; bool dax_truncate = is_truncate && FUSE_IS_DAX(inode); if (fuse_is_bad(inode)) return -EIO; err = generic_file_open(inode, file); if (err) return err; if (is_wb_truncate || dax_truncate) inode_lock(inode); if (dax_truncate) { filemap_invalidate_lock(inode->i_mapping); err = fuse_dax_break_layouts(inode, 0, 0); if (err) goto out_inode_unlock; } if (is_wb_truncate || dax_truncate) fuse_set_nowrite(inode); err = fuse_do_open(fm, get_node_id(inode), file, false); if (!err) { ff = file->private_data; err = fuse_finish_open(inode, file); if (err) fuse_sync_release(fi, ff, file->f_flags); else if (is_truncate) fuse_truncate_update_attr(inode, file); } if (is_wb_truncate || dax_truncate) fuse_release_nowrite(inode); if (!err) { if (is_truncate) truncate_pagecache(inode, 0); else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) invalidate_inode_pages2(inode->i_mapping); } if (dax_truncate) filemap_invalidate_unlock(inode->i_mapping); out_inode_unlock: if (is_wb_truncate || dax_truncate) inode_unlock(inode); return err; } static void fuse_prepare_release(struct fuse_inode *fi, struct fuse_file *ff, unsigned int flags, int opcode, bool sync) { struct fuse_conn *fc = ff->fm->fc; struct fuse_release_args *ra = &ff->args->release_args; if (fuse_file_passthrough(ff)) fuse_passthrough_release(ff, fuse_inode_backing(fi)); /* Inode is NULL on error path of fuse_create_open() */ if (likely(fi)) { spin_lock(&fi->lock); list_del(&ff->write_entry); spin_unlock(&fi->lock); } spin_lock(&fc->lock); if (!RB_EMPTY_NODE(&ff->polled_node)) rb_erase(&ff->polled_node, &fc->polled_files); spin_unlock(&fc->lock); wake_up_interruptible_all(&ff->poll_wait); if (!ra) return; /* ff->args was used for open outarg */ memset(ff->args, 0, sizeof(*ff->args)); ra->inarg.fh = ff->fh; ra->inarg.flags = flags; ra->args.in_numargs = 1; ra->args.in_args[0].size = sizeof(struct fuse_release_in); ra->args.in_args[0].value = &ra->inarg; ra->args.opcode = opcode; ra->args.nodeid = ff->nodeid; ra->args.force = true; ra->args.nocreds = true; /* * Hold inode until release is finished. * From fuse_sync_release() the refcount is 1 and everything's * synchronous, so we are fine with not doing igrab() here. */ ra->inode = sync ? NULL : igrab(&fi->inode); } void fuse_file_release(struct inode *inode, struct fuse_file *ff, unsigned int open_flags, fl_owner_t id, bool isdir) { struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_release_args *ra = &ff->args->release_args; int opcode = isdir ? FUSE_RELEASEDIR : FUSE_RELEASE; fuse_prepare_release(fi, ff, open_flags, opcode, false); if (ra && ff->flock) { ra->inarg.release_flags |= FUSE_RELEASE_FLOCK_UNLOCK; ra->inarg.lock_owner = fuse_lock_owner_id(ff->fm->fc, id); } /* * Normally this will send the RELEASE request, however if * some asynchronous READ or WRITE requests are outstanding, * the sending will be delayed. * * Make the release synchronous if this is a fuseblk mount, * synchronous RELEASE is allowed (and desirable) in this case * because the server can be trusted not to screw up. */ fuse_file_put(ff, ff->fm->fc->destroy); } void fuse_release_common(struct file *file, bool isdir) { fuse_file_release(file_inode(file), file->private_data, file->f_flags, (fl_owner_t) file, isdir); } static int fuse_release(struct inode *inode, struct file *file) { struct fuse_conn *fc = get_fuse_conn(inode); /* * Dirty pages might remain despite write_inode_now() call from * fuse_flush() due to writes racing with the close. */ if (fc->writeback_cache) write_inode_now(inode, 1); fuse_release_common(file, false); /* return value is ignored by VFS */ return 0; } void fuse_sync_release(struct fuse_inode *fi, struct fuse_file *ff, unsigned int flags) { WARN_ON(refcount_read(&ff->count) > 1); fuse_prepare_release(fi, ff, flags, FUSE_RELEASE, true); fuse_file_put(ff, true); } EXPORT_SYMBOL_GPL(fuse_sync_release); /* * Scramble the ID space with XTEA, so that the value of the files_struct * pointer is not exposed to userspace. */ u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id) { u32 *k = fc->scramble_key; u64 v = (unsigned long) id; u32 v0 = v; u32 v1 = v >> 32; u32 sum = 0; int i; for (i = 0; i < 32; i++) { v0 += ((v1 << 4 ^ v1 >> 5) + v1) ^ (sum + k[sum & 3]); sum += 0x9E3779B9; v1 += ((v0 << 4 ^ v0 >> 5) + v0) ^ (sum + k[sum>>11 & 3]); } return (u64) v0 + ((u64) v1 << 32); } struct fuse_writepage_args { struct fuse_io_args ia; struct rb_node writepages_entry; struct list_head queue_entry; struct fuse_writepage_args *next; struct inode *inode; struct fuse_sync_bucket *bucket; }; static struct fuse_writepage_args *fuse_find_writeback(struct fuse_inode *fi, pgoff_t idx_from, pgoff_t idx_to) { struct rb_node *n; n = fi->writepages.rb_node; while (n) { struct fuse_writepage_args *wpa; pgoff_t curr_index; wpa = rb_entry(n, struct fuse_writepage_args, writepages_entry); WARN_ON(get_fuse_inode(wpa->inode) != fi); curr_index = wpa->ia.write.in.offset >> PAGE_SHIFT; if (idx_from >= curr_index + wpa->ia.ap.num_pages) n = n->rb_right; else if (idx_to < curr_index) n = n->rb_left; else return wpa; } return NULL; } /* * Check if any page in a range is under writeback * * This is currently done by walking the list of writepage requests * for the inode, which can be pretty inefficient. */ static bool fuse_range_is_writeback(struct inode *inode, pgoff_t idx_from, pgoff_t idx_to) { struct fuse_inode *fi = get_fuse_inode(inode); bool found; spin_lock(&fi->lock); found = fuse_find_writeback(fi, idx_from, idx_to); spin_unlock(&fi->lock); return found; } static inline bool fuse_page_is_writeback(struct inode *inode, pgoff_t index) { return fuse_range_is_writeback(inode, index, index); } /* * Wait for page writeback to be completed. * * Since fuse doesn't rely on the VM writeback tracking, this has to * use some other means. */ static void fuse_wait_on_page_writeback(struct inode *inode, pgoff_t index) { struct fuse_inode *fi = get_fuse_inode(inode); wait_event(fi->page_waitq, !fuse_page_is_writeback(inode, index)); } /* * Wait for all pending writepages on the inode to finish. * * This is currently done by blocking further writes with FUSE_NOWRITE * and waiting for all sent writes to complete. * * This must be called under i_mutex, otherwise the FUSE_NOWRITE usage * could conflict with truncation. */ static void fuse_sync_writes(struct inode *inode) { fuse_set_nowrite(inode); fuse_release_nowrite(inode); } static int fuse_flush(struct file *file, fl_owner_t id) { struct inode *inode = file_inode(file); struct fuse_mount *fm = get_fuse_mount(inode); struct fuse_file *ff = file->private_data; struct fuse_flush_in inarg; FUSE_ARGS(args); int err; if (fuse_is_bad(inode)) return -EIO; if (ff->open_flags & FOPEN_NOFLUSH && !fm->fc->writeback_cache) return 0; err = write_inode_now(inode, 1); if (err) return err; inode_lock(inode); fuse_sync_writes(inode); inode_unlock(inode); err = filemap_check_errors(file->f_mapping); if (err) return err; err = 0; if (fm->fc->no_flush) goto inval_attr_out; memset(&inarg, 0, sizeof(inarg)); inarg.fh = ff->fh; inarg.lock_owner = fuse_lock_owner_id(fm->fc, id); args.opcode = FUSE_FLUSH; args.nodeid = get_node_id(inode); args.in_numargs = 1; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; args.force = true; err = fuse_simple_request(fm, &args); if (err == -ENOSYS) { fm->fc->no_flush = 1; err = 0; } inval_attr_out: /* * In memory i_blocks is not maintained by fuse, if writeback cache is * enabled, i_blocks from cached attr may not be accurate. */ if (!err && fm->fc->writeback_cache) fuse_invalidate_attr_mask(inode, STATX_BLOCKS); return err; } int fuse_fsync_common(struct file *file, loff_t start, loff_t end, int datasync, int opcode) { struct inode *inode = file->f_mapping->host; struct fuse_mount *fm = get_fuse_mount(inode); struct fuse_file *ff = file->private_data; FUSE_ARGS(args); struct fuse_fsync_in inarg; memset(&inarg, 0, sizeof(inarg)); inarg.fh = ff->fh; inarg.fsync_flags = datasync ? FUSE_FSYNC_FDATASYNC : 0; args.opcode = opcode; args.nodeid = get_node_id(inode); args.in_numargs = 1; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; return fuse_simple_request(fm, &args); } static int fuse_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file->f_mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); int err; if (fuse_is_bad(inode)) return -EIO; inode_lock(inode); /* * Start writeback against all dirty pages of the inode, then * wait for all outstanding writes, before sending the FSYNC * request. */ err = file_write_and_wait_range(file, start, end); if (err) goto out; fuse_sync_writes(inode); /* * Due to implementation of fuse writeback * file_write_and_wait_range() does not catch errors. * We have to do this directly after fuse_sync_writes() */ err = file_check_and_advance_wb_err(file); if (err) goto out; err = sync_inode_metadata(inode, 1); if (err) goto out; if (fc->no_fsync) goto out; err = fuse_fsync_common(file, start, end, datasync, FUSE_FSYNC); if (err == -ENOSYS) { fc->no_fsync = 1; err = 0; } out: inode_unlock(inode); return err; } void fuse_read_args_fill(struct fuse_io_args *ia, struct file *file, loff_t pos, size_t count, int opcode) { struct fuse_file *ff = file->private_data; struct fuse_args *args = &ia->ap.args; ia->read.in.fh = ff->fh; ia->read.in.offset = pos; ia->read.in.size = count; ia->read.in.flags = file->f_flags; args->opcode = opcode; args->nodeid = ff->nodeid; args->in_numargs = 1; args->in_args[0].size = sizeof(ia->read.in); args->in_args[0].value = &ia->read.in; args->out_argvar = true; args->out_numargs = 1; args->out_args[0].size = count; } static void fuse_release_user_pages(struct fuse_args_pages *ap, bool should_dirty) { unsigned int i; for (i = 0; i < ap->num_pages; i++) { if (should_dirty) set_page_dirty_lock(ap->pages[i]); if (ap->args.is_pinned) unpin_user_page(ap->pages[i]); } } static void fuse_io_release(struct kref *kref) { kfree(container_of(kref, struct fuse_io_priv, refcnt)); } static ssize_t fuse_get_res_by_io(struct fuse_io_priv *io) { if (io->err) return io->err; if (io->bytes >= 0 && io->write) return -EIO; return io->bytes < 0 ? io->size : io->bytes; } /* * In case of short read, the caller sets 'pos' to the position of * actual end of fuse request in IO request. Otherwise, if bytes_requested * == bytes_transferred or rw == WRITE, the caller sets 'pos' to -1. * * An example: * User requested DIO read of 64K. It was split into two 32K fuse requests, * both submitted asynchronously. The first of them was ACKed by userspace as * fully completed (req->out.args[0].size == 32K) resulting in pos == -1. The * second request was ACKed as short, e.g. only 1K was read, resulting in * pos == 33K. * * Thus, when all fuse requests are completed, the minimal non-negative 'pos' * will be equal to the length of the longest contiguous fragment of * transferred data starting from the beginning of IO request. */ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos) { int left; spin_lock(&io->lock); if (err) io->err = io->err ? : err; else if (pos >= 0 && (io->bytes < 0 || pos < io->bytes)) io->bytes = pos; left = --io->reqs; if (!left && io->blocking) complete(io->done); spin_unlock(&io->lock); if (!left && !io->blocking) { ssize_t res = fuse_get_res_by_io(io); if (res >= 0) { struct inode *inode = file_inode(io->iocb->ki_filp); struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); spin_lock(&fi->lock); fi->attr_version = atomic64_inc_return(&fc->attr_version); spin_unlock(&fi->lock); } io->iocb->ki_complete(io->iocb, res); } kref_put(&io->refcnt, fuse_io_release); } static struct fuse_io_args *fuse_io_alloc(struct fuse_io_priv *io, unsigned int npages) { struct fuse_io_args *ia; ia = kzalloc(sizeof(*ia), GFP_KERNEL); if (ia) { ia->io = io; ia->ap.pages = fuse_pages_alloc(npages, GFP_KERNEL, &ia->ap.descs); if (!ia->ap.pages) { kfree(ia); ia = NULL; } } return ia; } static void fuse_io_free(struct fuse_io_args *ia) { kfree(ia->ap.pages); kfree(ia); } static void fuse_aio_complete_req(struct fuse_mount *fm, struct fuse_args *args, int err) { struct fuse_io_args *ia = container_of(args, typeof(*ia), ap.args); struct fuse_io_priv *io = ia->io; ssize_t pos = -1; fuse_release_user_pages(&ia->ap, io->should_dirty); if (err) { /* Nothing */ } else if (io->write) { if (ia->write.out.size > ia->write.in.size) { err = -EIO; } else if (ia->write.in.size != ia->write.out.size) { pos = ia->write.in.offset - io->offset + ia->write.out.size; } } else { u32 outsize = args->out_args[0].size; if (ia->read.in.size != outsize) pos = ia->read.in.offset - io->offset + outsize; } fuse_aio_complete(io, err, pos); fuse_io_free(ia); } static ssize_t fuse_async_req_send(struct fuse_mount *fm, struct fuse_io_args *ia, size_t num_bytes) { ssize_t err; struct fuse_io_priv *io = ia->io; spin_lock(&io->lock); kref_get(&io->refcnt); io->size += num_bytes; io->reqs++; spin_unlock(&io->lock); ia->ap.args.end = fuse_aio_complete_req; ia->ap.args.may_block = io->should_dirty; err = fuse_simple_background(fm, &ia->ap.args, GFP_KERNEL); if (err) fuse_aio_complete_req(fm, &ia->ap.args, err); return num_bytes; } static ssize_t fuse_send_read(struct fuse_io_args *ia, loff_t pos, size_t count, fl_owner_t owner) { struct file *file = ia->io->iocb->ki_filp; struct fuse_file *ff = file->private_data; struct fuse_mount *fm = ff->fm; fuse_read_args_fill(ia, file, pos, count, FUSE_READ); if (owner != NULL) { ia->read.in.read_flags |= FUSE_READ_LOCKOWNER; ia->read.in.lock_owner = fuse_lock_owner_id(fm->fc, owner); } if (ia->io->async) return fuse_async_req_send(fm, ia, count); return fuse_simple_request(fm, &ia->ap.args); } static void fuse_read_update_size(struct inode *inode, loff_t size, u64 attr_ver) { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); spin_lock(&fi->lock); if (attr_ver >= fi->attr_version && size < inode->i_size && !test_bit(FUSE_I_SIZE_UNSTABLE, &fi->state)) { fi->attr_version = atomic64_inc_return(&fc->attr_version); i_size_write(inode, size); } spin_unlock(&fi->lock); } static void fuse_short_read(struct inode *inode, u64 attr_ver, size_t num_read, struct fuse_args_pages *ap) { struct fuse_conn *fc = get_fuse_conn(inode); /* * If writeback_cache is enabled, a short read means there's a hole in * the file. Some data after the hole is in page cache, but has not * reached the client fs yet. So the hole is not present there. */ if (!fc->writeback_cache) { loff_t pos = page_offset(ap->pages[0]) + num_read; fuse_read_update_size(inode, pos, attr_ver); } } static int fuse_do_readpage(struct file *file, struct page *page) { struct inode *inode = page->mapping->host; struct fuse_mount *fm = get_fuse_mount(inode); loff_t pos = page_offset(page); struct fuse_page_desc desc = { .length = PAGE_SIZE }; struct fuse_io_args ia = { .ap.args.page_zeroing = true, .ap.args.out_pages = true, .ap.num_pages = 1, .ap.pages = &page, .ap.descs = &desc, }; ssize_t res; u64 attr_ver; /* * Page writeback can extend beyond the lifetime of the * page-cache page, so make sure we read a properly synced * page. */ fuse_wait_on_page_writeback(inode, page->index); attr_ver = fuse_get_attr_version(fm->fc); /* Don't overflow end offset */ if (pos + (desc.length - 1) == LLONG_MAX) desc.length--; fuse_read_args_fill(&ia, file, pos, desc.length, FUSE_READ); res = fuse_simple_request(fm, &ia.ap.args); if (res < 0) return res; /* * Short read means EOF. If file size is larger, truncate it */ if (res < desc.length) fuse_short_read(inode, attr_ver, res, &ia.ap); SetPageUptodate(page); return 0; } static int fuse_read_folio(struct file *file, struct folio *folio) { struct page *page = &folio->page; struct inode *inode = page->mapping->host; int err; err = -EIO; if (fuse_is_bad(inode)) goto out; err = fuse_do_readpage(file, page); fuse_invalidate_atime(inode); out: unlock_page(page); return err; } static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args, int err) { int i; struct fuse_io_args *ia = container_of(args, typeof(*ia), ap.args); struct fuse_args_pages *ap = &ia->ap; size_t count = ia->read.in.size; size_t num_read = args->out_args[0].size; struct address_space *mapping = NULL; for (i = 0; mapping == NULL && i < ap->num_pages; i++) mapping = ap->pages[i]->mapping; if (mapping) { struct inode *inode = mapping->host; /* * Short read means EOF. If file size is larger, truncate it */ if (!err && num_read < count) fuse_short_read(inode, ia->read.attr_ver, num_read, ap); fuse_invalidate_atime(inode); } for (i = 0; i < ap->num_pages; i++) { struct folio *folio = page_folio(ap->pages[i]); folio_end_read(folio, !err); folio_put(folio); } if (ia->ff) fuse_file_put(ia->ff, false); fuse_io_free(ia); } static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file) { struct fuse_file *ff = file->private_data; struct fuse_mount *fm = ff->fm; struct fuse_args_pages *ap = &ia->ap; loff_t pos = page_offset(ap->pages[0]); size_t count = ap->num_pages << PAGE_SHIFT; ssize_t res; int err; ap->args.out_pages = true; ap->args.page_zeroing = true; ap->args.page_replace = true; /* Don't overflow end offset */ if (pos + (count - 1) == LLONG_MAX) { count--; ap->descs[ap->num_pages - 1].length--; } WARN_ON((loff_t) (pos + count) < 0); fuse_read_args_fill(ia, file, pos, count, FUSE_READ); ia->read.attr_ver = fuse_get_attr_version(fm->fc); if (fm->fc->async_read) { ia->ff = fuse_file_get(ff); ap->args.end = fuse_readpages_end; err = fuse_simple_background(fm, &ap->args, GFP_KERNEL); if (!err) return; } else { res = fuse_simple_request(fm, &ap->args); err = res < 0 ? res : 0; } fuse_readpages_end(fm, &ap->args, err); } static void fuse_readahead(struct readahead_control *rac) { struct inode *inode = rac->mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); unsigned int i, max_pages, nr_pages = 0; if (fuse_is_bad(inode)) return; max_pages = min_t(unsigned int, fc->max_pages, fc->max_read / PAGE_SIZE); for (;;) { struct fuse_io_args *ia; struct fuse_args_pages *ap; if (fc->num_background >= fc->congestion_threshold && rac->ra->async_size >= readahead_count(rac)) /* * Congested and only async pages left, so skip the * rest. */ break; nr_pages = readahead_count(rac) - nr_pages; if (nr_pages > max_pages) nr_pages = max_pages; if (nr_pages == 0) break; ia = fuse_io_alloc(NULL, nr_pages); if (!ia) return; ap = &ia->ap; nr_pages = __readahead_batch(rac, ap->pages, nr_pages); for (i = 0; i < nr_pages; i++) { fuse_wait_on_page_writeback(inode, readahead_index(rac) + i); ap->descs[i].length = PAGE_SIZE; } ap->num_pages = nr_pages; fuse_send_readpages(ia, rac->file); } } static ssize_t fuse_cache_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct inode *inode = iocb->ki_filp->f_mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); /* * In auto invalidate mode, always update attributes on read. * Otherwise, only update if we attempt to read past EOF (to ensure * i_size is up to date). */ if (fc->auto_inval_data || (iocb->ki_pos + iov_iter_count(to) > i_size_read(inode))) { int err; err = fuse_update_attributes(inode, iocb->ki_filp, STATX_SIZE); if (err) return err; } return generic_file_read_iter(iocb, to); } static void fuse_write_args_fill(struct fuse_io_args *ia, struct fuse_file *ff, loff_t pos, size_t count) { struct fuse_args *args = &ia->ap.args; ia->write.in.fh = ff->fh; ia->write.in.offset = pos; ia->write.in.size = count; args->opcode = FUSE_WRITE; args->nodeid = ff->nodeid; args->in_numargs = 2; if (ff->fm->fc->minor < 9) args->in_args[0].size = FUSE_COMPAT_WRITE_IN_SIZE; else args->in_args[0].size = sizeof(ia->write.in); args->in_args[0].value = &ia->write.in; args->in_args[1].size = count; args->out_numargs = 1; args->out_args[0].size = sizeof(ia->write.out); args->out_args[0].value = &ia->write.out; } static unsigned int fuse_write_flags(struct kiocb *iocb) { unsigned int flags = iocb->ki_filp->f_flags; if (iocb_is_dsync(iocb)) flags |= O_DSYNC; if (iocb->ki_flags & IOCB_SYNC) flags |= O_SYNC; return flags; } static ssize_t fuse_send_write(struct fuse_io_args *ia, loff_t pos, size_t count, fl_owner_t owner) { struct kiocb *iocb = ia->io->iocb; struct file *file = iocb->ki_filp; struct fuse_file *ff = file->private_data; struct fuse_mount *fm = ff->fm; struct fuse_write_in *inarg = &ia->write.in; ssize_t err; fuse_write_args_fill(ia, ff, pos, count); inarg->flags = fuse_write_flags(iocb); if (owner != NULL) { inarg->write_flags |= FUSE_WRITE_LOCKOWNER; inarg->lock_owner = fuse_lock_owner_id(fm->fc, owner); } if (ia->io->async) return fuse_async_req_send(fm, ia, count); err = fuse_simple_request(fm, &ia->ap.args); if (!err && ia->write.out.size > count) err = -EIO; return err ?: ia->write.out.size; } bool fuse_write_update_attr(struct inode *inode, loff_t pos, ssize_t written) { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); bool ret = false; spin_lock(&fi->lock); fi->attr_version = atomic64_inc_return(&fc->attr_version); if (written > 0 && pos > inode->i_size) { i_size_write(inode, pos); ret = true; } spin_unlock(&fi->lock); fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE); return ret; } static ssize_t fuse_send_write_pages(struct fuse_io_args *ia, struct kiocb *iocb, struct inode *inode, loff_t pos, size_t count) { struct fuse_args_pages *ap = &ia->ap; struct file *file = iocb->ki_filp; struct fuse_file *ff = file->private_data; struct fuse_mount *fm = ff->fm; unsigned int offset, i; bool short_write; int err; for (i = 0; i < ap->num_pages; i++) fuse_wait_on_page_writeback(inode, ap->pages[i]->index); fuse_write_args_fill(ia, ff, pos, count); ia->write.in.flags = fuse_write_flags(iocb); if (fm->fc->handle_killpriv_v2 && !capable(CAP_FSETID)) ia->write.in.write_flags |= FUSE_WRITE_KILL_SUIDGID; err = fuse_simple_request(fm, &ap->args); if (!err && ia->write.out.size > count) err = -EIO; short_write = ia->write.out.size < count; offset = ap->descs[0].offset; count = ia->write.out.size; for (i = 0; i < ap->num_pages; i++) { struct page *page = ap->pages[i]; if (err) { ClearPageUptodate(page); } else { if (count >= PAGE_SIZE - offset) count -= PAGE_SIZE - offset; else { if (short_write) ClearPageUptodate(page); count = 0; } offset = 0; } if (ia->write.page_locked && (i == ap->num_pages - 1)) unlock_page(page); put_page(page); } return err; } static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia, struct address_space *mapping, struct iov_iter *ii, loff_t pos, unsigned int max_pages) { struct fuse_args_pages *ap = &ia->ap; struct fuse_conn *fc = get_fuse_conn(mapping->host); unsigned offset = pos & (PAGE_SIZE - 1); size_t count = 0; int err; ap->args.in_pages = true; ap->descs[0].offset = offset; do { size_t tmp; struct page *page; pgoff_t index = pos >> PAGE_SHIFT; size_t bytes = min_t(size_t, PAGE_SIZE - offset, iov_iter_count(ii)); bytes = min_t(size_t, bytes, fc->max_write - count); again: err = -EFAULT; if (fault_in_iov_iter_readable(ii, bytes)) break; err = -ENOMEM; page = grab_cache_page_write_begin(mapping, index); if (!page) break; if (mapping_writably_mapped(mapping)) flush_dcache_page(page); tmp = copy_page_from_iter_atomic(page, offset, bytes, ii); flush_dcache_page(page); if (!tmp) { unlock_page(page); put_page(page); goto again; } err = 0; ap->pages[ap->num_pages] = page; ap->descs[ap->num_pages].length = tmp; ap->num_pages++; count += tmp; pos += tmp; offset += tmp; if (offset == PAGE_SIZE) offset = 0; /* If we copied full page, mark it uptodate */ if (tmp == PAGE_SIZE) SetPageUptodate(page); if (PageUptodate(page)) { unlock_page(page); } else { ia->write.page_locked = true; break; } if (!fc->big_writes) break; } while (iov_iter_count(ii) && count < fc->max_write && ap->num_pages < max_pages && offset == 0); return count > 0 ? count : err; } static inline unsigned int fuse_wr_pages(loff_t pos, size_t len, unsigned int max_pages) { return min_t(unsigned int, ((pos + len - 1) >> PAGE_SHIFT) - (pos >> PAGE_SHIFT) + 1, max_pages); } static ssize_t fuse_perform_write(struct kiocb *iocb, struct iov_iter *ii) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); loff_t pos = iocb->ki_pos; int err = 0; ssize_t res = 0; if (inode->i_size < pos + iov_iter_count(ii)) set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); do { ssize_t count; struct fuse_io_args ia = {}; struct fuse_args_pages *ap = &ia.ap; unsigned int nr_pages = fuse_wr_pages(pos, iov_iter_count(ii), fc->max_pages); ap->pages = fuse_pages_alloc(nr_pages, GFP_KERNEL, &ap->descs); if (!ap->pages) { err = -ENOMEM; break; } count = fuse_fill_write_pages(&ia, mapping, ii, pos, nr_pages); if (count <= 0) { err = count; } else { err = fuse_send_write_pages(&ia, iocb, inode, pos, count); if (!err) { size_t num_written = ia.write.out.size; res += num_written; pos += num_written; /* break out of the loop on short write */ if (num_written != count) err = -EIO; } } kfree(ap->pages); } while (!err && iov_iter_count(ii)); fuse_write_update_attr(inode, pos, res); clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); if (!res) return err; iocb->ki_pos += res; return res; } static bool fuse_io_past_eof(struct kiocb *iocb, struct iov_iter *iter) { struct inode *inode = file_inode(iocb->ki_filp); return iocb->ki_pos + iov_iter_count(iter) > i_size_read(inode); } /* * @return true if an exclusive lock for direct IO writes is needed */ static bool fuse_dio_wr_exclusive_lock(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct fuse_file *ff = file->private_data; struct inode *inode = file_inode(iocb->ki_filp); struct fuse_inode *fi = get_fuse_inode(inode); /* Server side has to advise that it supports parallel dio writes. */ if (!(ff->open_flags & FOPEN_PARALLEL_DIRECT_WRITES)) return true; /* * Append will need to know the eventual EOF - always needs an * exclusive lock. */ if (iocb->ki_flags & IOCB_APPEND) return true; /* shared locks are not allowed with parallel page cache IO */ if (test_bit(FUSE_I_CACHE_IO_MODE, &fi->state)) return false; /* Parallel dio beyond EOF is not supported, at least for now. */ if (fuse_io_past_eof(iocb, from)) return true; return false; } static void fuse_dio_lock(struct kiocb *iocb, struct iov_iter *from, bool *exclusive) { struct inode *inode = file_inode(iocb->ki_filp); struct fuse_inode *fi = get_fuse_inode(inode); *exclusive = fuse_dio_wr_exclusive_lock(iocb, from); if (*exclusive) { inode_lock(inode); } else { inode_lock_shared(inode); /* * New parallal dio allowed only if inode is not in caching * mode and denies new opens in caching mode. This check * should be performed only after taking shared inode lock. * Previous past eof check was without inode lock and might * have raced, so check it again. */ if (fuse_io_past_eof(iocb, from) || fuse_inode_uncached_io_start(fi, NULL) != 0) { inode_unlock_shared(inode); inode_lock(inode); *exclusive = true; } } } static void fuse_dio_unlock(struct kiocb *iocb, bool exclusive) { struct inode *inode = file_inode(iocb->ki_filp); struct fuse_inode *fi = get_fuse_inode(inode); if (exclusive) { inode_unlock(inode); } else { /* Allow opens in caching mode after last parallel dio end */ fuse_inode_uncached_io_end(fi); inode_unlock_shared(inode); } } static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; ssize_t written = 0; struct inode *inode = mapping->host; ssize_t err, count; struct fuse_conn *fc = get_fuse_conn(inode); if (fc->writeback_cache) { /* Update size (EOF optimization) and mode (SUID clearing) */ err = fuse_update_attributes(mapping->host, file, STATX_SIZE | STATX_MODE); if (err) return err; if (fc->handle_killpriv_v2 && setattr_should_drop_suidgid(&nop_mnt_idmap, file_inode(file))) { goto writethrough; } return generic_file_write_iter(iocb, from); } writethrough: inode_lock(inode); err = count = generic_write_checks(iocb, from); if (err <= 0) goto out; task_io_account_write(count); err = file_remove_privs(file); if (err) goto out; err = file_update_time(file); if (err) goto out; if (iocb->ki_flags & IOCB_DIRECT) { written = generic_file_direct_write(iocb, from); if (written < 0 || !iov_iter_count(from)) goto out; written = direct_write_fallback(iocb, from, written, fuse_perform_write(iocb, from)); } else { written = fuse_perform_write(iocb, from); } out: inode_unlock(inode); if (written > 0) written = generic_write_sync(iocb, written); return written ? written : err; } static inline unsigned long fuse_get_user_addr(const struct iov_iter *ii) { return (unsigned long)iter_iov(ii)->iov_base + ii->iov_offset; } static inline size_t fuse_get_frag_size(const struct iov_iter *ii, size_t max_size) { return min(iov_iter_single_seg_count(ii), max_size); } static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, size_t *nbytesp, int write, unsigned int max_pages) { size_t nbytes = 0; /* # bytes already packed in req */ ssize_t ret = 0; /* Special case for kernel I/O: can copy directly into the buffer */ if (iov_iter_is_kvec(ii)) { unsigned long user_addr = fuse_get_user_addr(ii); size_t frag_size = fuse_get_frag_size(ii, *nbytesp); if (write) ap->args.in_args[1].value = (void *) user_addr; else ap->args.out_args[0].value = (void *) user_addr; iov_iter_advance(ii, frag_size); *nbytesp = frag_size; return 0; } while (nbytes < *nbytesp && ap->num_pages < max_pages) { unsigned npages; size_t start; struct page **pt_pages; pt_pages = &ap->pages[ap->num_pages]; ret = iov_iter_extract_pages(ii, &pt_pages, *nbytesp - nbytes, max_pages - ap->num_pages, 0, &start); if (ret < 0) break; nbytes += ret; ret += start; npages = DIV_ROUND_UP(ret, PAGE_SIZE); ap->descs[ap->num_pages].offset = start; fuse_page_descs_length_init(ap->descs, ap->num_pages, npages); ap->num_pages += npages; ap->descs[ap->num_pages - 1].length -= (PAGE_SIZE - ret) & (PAGE_SIZE - 1); } ap->args.is_pinned = iov_iter_extract_will_pin(ii); ap->args.user_pages = true; if (write) ap->args.in_pages = true; else ap->args.out_pages = true; *nbytesp = nbytes; return ret < 0 ? ret : 0; } ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, loff_t *ppos, int flags) { int write = flags & FUSE_DIO_WRITE; int cuse = flags & FUSE_DIO_CUSE; struct file *file = io->iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; struct fuse_file *ff = file->private_data; struct fuse_conn *fc = ff->fm->fc; size_t nmax = write ? fc->max_write : fc->max_read; loff_t pos = *ppos; size_t count = iov_iter_count(iter); pgoff_t idx_from = pos >> PAGE_SHIFT; pgoff_t idx_to = (pos + count - 1) >> PAGE_SHIFT; ssize_t res = 0; int err = 0; struct fuse_io_args *ia; unsigned int max_pages; bool fopen_direct_io = ff->open_flags & FOPEN_DIRECT_IO; max_pages = iov_iter_npages(iter, fc->max_pages); ia = fuse_io_alloc(io, max_pages); if (!ia) return -ENOMEM; if (fopen_direct_io && fc->direct_io_allow_mmap) { res = filemap_write_and_wait_range(mapping, pos, pos + count - 1); if (res) { fuse_io_free(ia); return res; } } if (!cuse && fuse_range_is_writeback(inode, idx_from, idx_to)) { if (!write) inode_lock(inode); fuse_sync_writes(inode); if (!write) inode_unlock(inode); } if (fopen_direct_io && write) { res = invalidate_inode_pages2_range(mapping, idx_from, idx_to); if (res) { fuse_io_free(ia); return res; } } io->should_dirty = !write && user_backed_iter(iter); while (count) { ssize_t nres; fl_owner_t owner = current->files; size_t nbytes = min(count, nmax); err = fuse_get_user_pages(&ia->ap, iter, &nbytes, write, max_pages); if (err && !nbytes) break; if (write) { if (!capable(CAP_FSETID)) ia->write.in.write_flags |= FUSE_WRITE_KILL_SUIDGID; nres = fuse_send_write(ia, pos, nbytes, owner); } else { nres = fuse_send_read(ia, pos, nbytes, owner); } if (!io->async || nres < 0) { fuse_release_user_pages(&ia->ap, io->should_dirty); fuse_io_free(ia); } ia = NULL; if (nres < 0) { iov_iter_revert(iter, nbytes); err = nres; break; } WARN_ON(nres > nbytes); count -= nres; res += nres; pos += nres; if (nres != nbytes) { iov_iter_revert(iter, nbytes - nres); break; } if (count) { max_pages = iov_iter_npages(iter, fc->max_pages); ia = fuse_io_alloc(io, max_pages); if (!ia) break; } } if (ia) fuse_io_free(ia); if (res > 0) *ppos = pos; return res > 0 ? res : err; } EXPORT_SYMBOL_GPL(fuse_direct_io); static ssize_t __fuse_direct_read(struct fuse_io_priv *io, struct iov_iter *iter, loff_t *ppos) { ssize_t res; struct inode *inode = file_inode(io->iocb->ki_filp); res = fuse_direct_io(io, iter, ppos, 0); fuse_invalidate_atime(inode); return res; } static ssize_t fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter); static ssize_t fuse_direct_read_iter(struct kiocb *iocb, struct iov_iter *to) { ssize_t res; if (!is_sync_kiocb(iocb) && iocb->ki_flags & IOCB_DIRECT) { res = fuse_direct_IO(iocb, to); } else { struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb); res = __fuse_direct_read(&io, to, &iocb->ki_pos); } return res; } static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct inode *inode = file_inode(iocb->ki_filp); struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb); ssize_t res; bool exclusive; fuse_dio_lock(iocb, from, &exclusive); res = generic_write_checks(iocb, from); if (res > 0) { task_io_account_write(res); if (!is_sync_kiocb(iocb) && iocb->ki_flags & IOCB_DIRECT) { res = fuse_direct_IO(iocb, from); } else { res = fuse_direct_io(&io, from, &iocb->ki_pos, FUSE_DIO_WRITE); fuse_write_update_attr(inode, iocb->ki_pos, res); } } fuse_dio_unlock(iocb, exclusive); return res; } static ssize_t fuse_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct fuse_file *ff = file->private_data; struct inode *inode = file_inode(file); if (fuse_is_bad(inode)) return -EIO; if (FUSE_IS_DAX(inode)) return fuse_dax_read_iter(iocb, to); /* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */ if (ff->open_flags & FOPEN_DIRECT_IO) return fuse_direct_read_iter(iocb, to); else if (fuse_file_passthrough(ff)) return fuse_passthrough_read_iter(iocb, to); else return fuse_cache_read_iter(iocb, to); } static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct fuse_file *ff = file->private_data; struct inode *inode = file_inode(file); if (fuse_is_bad(inode)) return -EIO; if (FUSE_IS_DAX(inode)) return fuse_dax_write_iter(iocb, from); /* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */ if (ff->open_flags & FOPEN_DIRECT_IO) return fuse_direct_write_iter(iocb, from); else if (fuse_file_passthrough(ff)) return fuse_passthrough_write_iter(iocb, from); else return fuse_cache_write_iter(iocb, from); } static ssize_t fuse_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct fuse_file *ff = in->private_data; /* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */ if (fuse_file_passthrough(ff) && !(ff->open_flags & FOPEN_DIRECT_IO)) return fuse_passthrough_splice_read(in, ppos, pipe, len, flags); else return filemap_splice_read(in, ppos, pipe, len, flags); } static ssize_t fuse_splice_write(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { struct fuse_file *ff = out->private_data; /* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */ if (fuse_file_passthrough(ff) && !(ff->open_flags & FOPEN_DIRECT_IO)) return fuse_passthrough_splice_write(pipe, out, ppos, len, flags); else return iter_file_splice_write(pipe, out, ppos, len, flags); } static void fuse_writepage_free(struct fuse_writepage_args *wpa) { struct fuse_args_pages *ap = &wpa->ia.ap; int i; if (wpa->bucket) fuse_sync_bucket_dec(wpa->bucket); for (i = 0; i < ap->num_pages; i++) __free_page(ap->pages[i]); if (wpa->ia.ff) fuse_file_put(wpa->ia.ff, false); kfree(ap->pages); kfree(wpa); } static void fuse_writepage_finish(struct fuse_mount *fm, struct fuse_writepage_args *wpa) { struct fuse_args_pages *ap = &wpa->ia.ap; struct inode *inode = wpa->inode; struct fuse_inode *fi = get_fuse_inode(inode); struct backing_dev_info *bdi = inode_to_bdi(inode); int i; for (i = 0; i < ap->num_pages; i++) { dec_wb_stat(&bdi->wb, WB_WRITEBACK); dec_node_page_state(ap->pages[i], NR_WRITEBACK_TEMP); wb_writeout_inc(&bdi->wb); } wake_up(&fi->page_waitq); } /* Called under fi->lock, may release and reacquire it */ static void fuse_send_writepage(struct fuse_mount *fm, struct fuse_writepage_args *wpa, loff_t size) __releases(fi->lock) __acquires(fi->lock) { struct fuse_writepage_args *aux, *next; struct fuse_inode *fi = get_fuse_inode(wpa->inode); struct fuse_write_in *inarg = &wpa->ia.write.in; struct fuse_args *args = &wpa->ia.ap.args; __u64 data_size = wpa->ia.ap.num_pages * PAGE_SIZE; int err; fi->writectr++; if (inarg->offset + data_size <= size) { inarg->size = data_size; } else if (inarg->offset < size) { inarg->size = size - inarg->offset; } else { /* Got truncated off completely */ goto out_free; } args->in_args[1].size = inarg->size; args->force = true; args->nocreds = true; err = fuse_simple_background(fm, args, GFP_ATOMIC); if (err == -ENOMEM) { spin_unlock(&fi->lock); err = fuse_simple_background(fm, args, GFP_NOFS | __GFP_NOFAIL); spin_lock(&fi->lock); } /* Fails on broken connection only */ if (unlikely(err)) goto out_free; return; out_free: fi->writectr--; rb_erase(&wpa->writepages_entry, &fi->writepages); fuse_writepage_finish(fm, wpa); spin_unlock(&fi->lock); /* After fuse_writepage_finish() aux request list is private */ for (aux = wpa->next; aux; aux = next) { next = aux->next; aux->next = NULL; fuse_writepage_free(aux); } fuse_writepage_free(wpa); spin_lock(&fi->lock); } /* * If fi->writectr is positive (no truncate or fsync going on) send * all queued writepage requests. * * Called with fi->lock */ void fuse_flush_writepages(struct inode *inode) __releases(fi->lock) __acquires(fi->lock) { struct fuse_mount *fm = get_fuse_mount(inode); struct fuse_inode *fi = get_fuse_inode(inode); loff_t crop = i_size_read(inode); struct fuse_writepage_args *wpa; while (fi->writectr >= 0 && !list_empty(&fi->queued_writes)) { wpa = list_entry(fi->queued_writes.next, struct fuse_writepage_args, queue_entry); list_del_init(&wpa->queue_entry); fuse_send_writepage(fm, wpa, crop); } } static struct fuse_writepage_args *fuse_insert_writeback(struct rb_root *root, struct fuse_writepage_args *wpa) { pgoff_t idx_from = wpa->ia.write.in.offset >> PAGE_SHIFT; pgoff_t idx_to = idx_from + wpa->ia.ap.num_pages - 1; struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; WARN_ON(!wpa->ia.ap.num_pages); while (*p) { struct fuse_writepage_args *curr; pgoff_t curr_index; parent = *p; curr = rb_entry(parent, struct fuse_writepage_args, writepages_entry); WARN_ON(curr->inode != wpa->inode); curr_index = curr->ia.write.in.offset >> PAGE_SHIFT; if (idx_from >= curr_index + curr->ia.ap.num_pages) p = &(*p)->rb_right; else if (idx_to < curr_index) p = &(*p)->rb_left; else return curr; } rb_link_node(&wpa->writepages_entry, parent, p); rb_insert_color(&wpa->writepages_entry, root); return NULL; } static void tree_insert(struct rb_root *root, struct fuse_writepage_args *wpa) { WARN_ON(fuse_insert_writeback(root, wpa)); } static void fuse_writepage_end(struct fuse_mount *fm, struct fuse_args *args, int error) { struct fuse_writepage_args *wpa = container_of(args, typeof(*wpa), ia.ap.args); struct inode *inode = wpa->inode; struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_conn *fc = get_fuse_conn(inode); mapping_set_error(inode->i_mapping, error); /* * A writeback finished and this might have updated mtime/ctime on * server making local mtime/ctime stale. Hence invalidate attrs. * Do this only if writeback_cache is not enabled. If writeback_cache * is enabled, we trust local ctime/mtime. */ if (!fc->writeback_cache) fuse_invalidate_attr_mask(inode, FUSE_STATX_MODIFY); spin_lock(&fi->lock); rb_erase(&wpa->writepages_entry, &fi->writepages); while (wpa->next) { struct fuse_mount *fm = get_fuse_mount(inode); struct fuse_write_in *inarg = &wpa->ia.write.in; struct fuse_writepage_args *next = wpa->next; wpa->next = next->next; next->next = NULL; next->ia.ff = fuse_file_get(wpa->ia.ff); tree_insert(&fi->writepages, next); /* * Skip fuse_flush_writepages() to make it easy to crop requests * based on primary request size. * * 1st case (trivial): there are no concurrent activities using * fuse_set/release_nowrite. Then we're on safe side because * fuse_flush_writepages() would call fuse_send_writepage() * anyway. * * 2nd case: someone called fuse_set_nowrite and it is waiting * now for completion of all in-flight requests. This happens * rarely and no more than once per page, so this should be * okay. * * 3rd case: someone (e.g. fuse_do_setattr()) is in the middle * of fuse_set_nowrite..fuse_release_nowrite section. The fact * that fuse_set_nowrite returned implies that all in-flight * requests were completed along with all of their secondary * requests. Further primary requests are blocked by negative * writectr. Hence there cannot be any in-flight requests and * no invocations of fuse_writepage_end() while we're in * fuse_set_nowrite..fuse_release_nowrite section. */ fuse_send_writepage(fm, next, inarg->offset + inarg->size); } fi->writectr--; fuse_writepage_finish(fm, wpa); spin_unlock(&fi->lock); fuse_writepage_free(wpa); } static struct fuse_file *__fuse_write_file_get(struct fuse_inode *fi) { struct fuse_file *ff; spin_lock(&fi->lock); ff = list_first_entry_or_null(&fi->write_files, struct fuse_file, write_entry); if (ff) fuse_file_get(ff); spin_unlock(&fi->lock); return ff; } static struct fuse_file *fuse_write_file_get(struct fuse_inode *fi) { struct fuse_file *ff = __fuse_write_file_get(fi); WARN_ON(!ff); return ff; } int fuse_write_inode(struct inode *inode, struct writeback_control *wbc) { struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_file *ff; int err; /* * Inode is always written before the last reference is dropped and * hence this should not be reached from reclaim. * * Writing back the inode from reclaim can deadlock if the request * processing itself needs an allocation. Allocations triggering * reclaim while serving a request can't be prevented, because it can * involve any number of unrelated userspace processes. */ WARN_ON(wbc->for_reclaim); ff = __fuse_write_file_get(fi); err = fuse_flush_times(inode, ff); if (ff) fuse_file_put(ff, false); return err; } static struct fuse_writepage_args *fuse_writepage_args_alloc(void) { struct fuse_writepage_args *wpa; struct fuse_args_pages *ap; wpa = kzalloc(sizeof(*wpa), GFP_NOFS); if (wpa) { ap = &wpa->ia.ap; ap->num_pages = 0; ap->pages = fuse_pages_alloc(1, GFP_NOFS, &ap->descs); if (!ap->pages) { kfree(wpa); wpa = NULL; } } return wpa; } static void fuse_writepage_add_to_bucket(struct fuse_conn *fc, struct fuse_writepage_args *wpa) { if (!fc->sync_fs) return; rcu_read_lock(); /* Prevent resurrection of dead bucket in unlikely race with syncfs */ do { wpa->bucket = rcu_dereference(fc->curr_bucket); } while (unlikely(!atomic_inc_not_zero(&wpa->bucket->count))); rcu_read_unlock(); } static int fuse_writepage_locked(struct folio *folio) { struct address_space *mapping = folio->mapping; struct inode *inode = mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_writepage_args *wpa; struct fuse_args_pages *ap; struct folio *tmp_folio; int error = -ENOMEM; folio_start_writeback(folio); wpa = fuse_writepage_args_alloc(); if (!wpa) goto err; ap = &wpa->ia.ap; tmp_folio = folio_alloc(GFP_NOFS | __GFP_HIGHMEM, 0); if (!tmp_folio) goto err_free; error = -EIO; wpa->ia.ff = fuse_write_file_get(fi); if (!wpa->ia.ff) goto err_nofile; fuse_writepage_add_to_bucket(fc, wpa); fuse_write_args_fill(&wpa->ia, wpa->ia.ff, folio_pos(folio), 0); folio_copy(tmp_folio, folio); wpa->ia.write.in.write_flags |= FUSE_WRITE_CACHE; wpa->next = NULL; ap->args.in_pages = true; ap->num_pages = 1; ap->pages[0] = &tmp_folio->page; ap->descs[0].offset = 0; ap->descs[0].length = PAGE_SIZE; ap->args.end = fuse_writepage_end; wpa->inode = inode; inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK); node_stat_add_folio(tmp_folio, NR_WRITEBACK_TEMP); spin_lock(&fi->lock); tree_insert(&fi->writepages, wpa); list_add_tail(&wpa->queue_entry, &fi->queued_writes); fuse_flush_writepages(inode); spin_unlock(&fi->lock); folio_end_writeback(folio); return 0; err_nofile: folio_put(tmp_folio); err_free: kfree(wpa); err: mapping_set_error(folio->mapping, error); folio_end_writeback(folio); return error; } struct fuse_fill_wb_data { struct fuse_writepage_args *wpa; struct fuse_file *ff; struct inode *inode; struct page **orig_pages; unsigned int max_pages; }; static bool fuse_pages_realloc(struct fuse_fill_wb_data *data) { struct fuse_args_pages *ap = &data->wpa->ia.ap; struct fuse_conn *fc = get_fuse_conn(data->inode); struct page **pages; struct fuse_page_desc *descs; unsigned int npages = min_t(unsigned int, max_t(unsigned int, data->max_pages * 2, FUSE_DEFAULT_MAX_PAGES_PER_REQ), fc->max_pages); WARN_ON(npages <= data->max_pages); pages = fuse_pages_alloc(npages, GFP_NOFS, &descs); if (!pages) return false; memcpy(pages, ap->pages, sizeof(struct page *) * ap->num_pages); memcpy(descs, ap->descs, sizeof(struct fuse_page_desc) * ap->num_pages); kfree(ap->pages); ap->pages = pages; ap->descs = descs; data->max_pages = npages; return true; } static void fuse_writepages_send(struct fuse_fill_wb_data *data) { struct fuse_writepage_args *wpa = data->wpa; struct inode *inode = data->inode; struct fuse_inode *fi = get_fuse_inode(inode); int num_pages = wpa->ia.ap.num_pages; int i; wpa->ia.ff = fuse_file_get(data->ff); spin_lock(&fi->lock); list_add_tail(&wpa->queue_entry, &fi->queued_writes); fuse_flush_writepages(inode); spin_unlock(&fi->lock); for (i = 0; i < num_pages; i++) end_page_writeback(data->orig_pages[i]); } /* * Check under fi->lock if the page is under writeback, and insert it onto the * rb_tree if not. Otherwise iterate auxiliary write requests, to see if there's * one already added for a page at this offset. If there's none, then insert * this new request onto the auxiliary list, otherwise reuse the existing one by * swapping the new temp page with the old one. */ static bool fuse_writepage_add(struct fuse_writepage_args *new_wpa, struct page *page) { struct fuse_inode *fi = get_fuse_inode(new_wpa->inode); struct fuse_writepage_args *tmp; struct fuse_writepage_args *old_wpa; struct fuse_args_pages *new_ap = &new_wpa->ia.ap; WARN_ON(new_ap->num_pages != 0); new_ap->num_pages = 1; spin_lock(&fi->lock); old_wpa = fuse_insert_writeback(&fi->writepages, new_wpa); if (!old_wpa) { spin_unlock(&fi->lock); return true; } for (tmp = old_wpa->next; tmp; tmp = tmp->next) { pgoff_t curr_index; WARN_ON(tmp->inode != new_wpa->inode); curr_index = tmp->ia.write.in.offset >> PAGE_SHIFT; if (curr_index == page->index) { WARN_ON(tmp->ia.ap.num_pages != 1); swap(tmp->ia.ap.pages[0], new_ap->pages[0]); break; } } if (!tmp) { new_wpa->next = old_wpa->next; old_wpa->next = new_wpa; } spin_unlock(&fi->lock); if (tmp) { struct backing_dev_info *bdi = inode_to_bdi(new_wpa->inode); dec_wb_stat(&bdi->wb, WB_WRITEBACK); dec_node_page_state(new_ap->pages[0], NR_WRITEBACK_TEMP); wb_writeout_inc(&bdi->wb); fuse_writepage_free(new_wpa); } return false; } static bool fuse_writepage_need_send(struct fuse_conn *fc, struct page *page, struct fuse_args_pages *ap, struct fuse_fill_wb_data *data) { WARN_ON(!ap->num_pages); /* * Being under writeback is unlikely but possible. For example direct * read to an mmaped fuse file will set the page dirty twice; once when * the pages are faulted with get_user_pages(), and then after the read * completed. */ if (fuse_page_is_writeback(data->inode, page->index)) return true; /* Reached max pages */ if (ap->num_pages == fc->max_pages) return true; /* Reached max write bytes */ if ((ap->num_pages + 1) * PAGE_SIZE > fc->max_write) return true; /* Discontinuity */ if (data->orig_pages[ap->num_pages - 1]->index + 1 != page->index) return true; /* Need to grow the pages array? If so, did the expansion fail? */ if (ap->num_pages == data->max_pages && !fuse_pages_realloc(data)) return true; return false; } static int fuse_writepages_fill(struct folio *folio, struct writeback_control *wbc, void *_data) { struct fuse_fill_wb_data *data = _data; struct fuse_writepage_args *wpa = data->wpa; struct fuse_args_pages *ap = &wpa->ia.ap; struct inode *inode = data->inode; struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_conn *fc = get_fuse_conn(inode); struct page *tmp_page; int err; if (!data->ff) { err = -EIO; data->ff = fuse_write_file_get(fi); if (!data->ff) goto out_unlock; } if (wpa && fuse_writepage_need_send(fc, &folio->page, ap, data)) { fuse_writepages_send(data); data->wpa = NULL; } err = -ENOMEM; tmp_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM); if (!tmp_page) goto out_unlock; /* * The page must not be redirtied until the writeout is completed * (i.e. userspace has sent a reply to the write request). Otherwise * there could be more than one temporary page instance for each real * page. * * This is ensured by holding the page lock in page_mkwrite() while * checking fuse_page_is_writeback(). We already hold the page lock * since clear_page_dirty_for_io() and keep it held until we add the * request to the fi->writepages list and increment ap->num_pages. * After this fuse_page_is_writeback() will indicate that the page is * under writeback, so we can release the page lock. */ if (data->wpa == NULL) { err = -ENOMEM; wpa = fuse_writepage_args_alloc(); if (!wpa) { __free_page(tmp_page); goto out_unlock; } fuse_writepage_add_to_bucket(fc, wpa); data->max_pages = 1; ap = &wpa->ia.ap; fuse_write_args_fill(&wpa->ia, data->ff, folio_pos(folio), 0); wpa->ia.write.in.write_flags |= FUSE_WRITE_CACHE; wpa->next = NULL; ap->args.in_pages = true; ap->args.end = fuse_writepage_end; ap->num_pages = 0; wpa->inode = inode; } folio_start_writeback(folio); copy_highpage(tmp_page, &folio->page); ap->pages[ap->num_pages] = tmp_page; ap->descs[ap->num_pages].offset = 0; ap->descs[ap->num_pages].length = PAGE_SIZE; data->orig_pages[ap->num_pages] = &folio->page; inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK); inc_node_page_state(tmp_page, NR_WRITEBACK_TEMP); err = 0; if (data->wpa) { /* * Protected by fi->lock against concurrent access by * fuse_page_is_writeback(). */ spin_lock(&fi->lock); ap->num_pages++; spin_unlock(&fi->lock); } else if (fuse_writepage_add(wpa, &folio->page)) { data->wpa = wpa; } else { folio_end_writeback(folio); } out_unlock: folio_unlock(folio); return err; } static int fuse_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_fill_wb_data data; int err; err = -EIO; if (fuse_is_bad(inode)) goto out; if (wbc->sync_mode == WB_SYNC_NONE && fc->num_background >= fc->congestion_threshold) return 0; data.inode = inode; data.wpa = NULL; data.ff = NULL; err = -ENOMEM; data.orig_pages = kcalloc(fc->max_pages, sizeof(struct page *), GFP_NOFS); if (!data.orig_pages) goto out; err = write_cache_pages(mapping, wbc, fuse_writepages_fill, &data); if (data.wpa) { WARN_ON(!data.wpa->ia.ap.num_pages); fuse_writepages_send(&data); } if (data.ff) fuse_file_put(data.ff, false); kfree(data.orig_pages); out: return err; } /* * It's worthy to make sure that space is reserved on disk for the write, * but how to implement it without killing performance need more thinking. */ static int fuse_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, void **fsdata) { pgoff_t index = pos >> PAGE_SHIFT; struct fuse_conn *fc = get_fuse_conn(file_inode(file)); struct page *page; loff_t fsize; int err = -ENOMEM; WARN_ON(!fc->writeback_cache); page = grab_cache_page_write_begin(mapping, index); if (!page) goto error; fuse_wait_on_page_writeback(mapping->host, page->index); if (PageUptodate(page) || len == PAGE_SIZE) goto success; /* * Check if the start this page comes after the end of file, in which * case the readpage can be optimized away. */ fsize = i_size_read(mapping->host); if (fsize <= (pos & PAGE_MASK)) { size_t off = pos & ~PAGE_MASK; if (off) zero_user_segment(page, 0, off); goto success; } err = fuse_do_readpage(file, page); if (err) goto cleanup; success: *pagep = page; return 0; cleanup: unlock_page(page); put_page(page); error: return err; } static int fuse_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = page->mapping->host; /* Haven't copied anything? Skip zeroing, size extending, dirtying. */ if (!copied) goto unlock; pos += copied; if (!PageUptodate(page)) { /* Zero any unwritten bytes at the end of the page */ size_t endoff = pos & ~PAGE_MASK; if (endoff) zero_user_segment(page, endoff, PAGE_SIZE); SetPageUptodate(page); } if (pos > inode->i_size) i_size_write(inode, pos); set_page_dirty(page); unlock: unlock_page(page); put_page(page); return copied; } static int fuse_launder_folio(struct folio *folio) { int err = 0; if (folio_clear_dirty_for_io(folio)) { struct inode *inode = folio->mapping->host; /* Serialize with pending writeback for the same page */ fuse_wait_on_page_writeback(inode, folio->index); err = fuse_writepage_locked(folio); if (!err) fuse_wait_on_page_writeback(inode, folio->index); } return err; } /* * Write back dirty data/metadata now (there may not be any suitable * open files later for data) */ static void fuse_vma_close(struct vm_area_struct *vma) { int err; err = write_inode_now(vma->vm_file->f_mapping->host, 1); mapping_set_error(vma->vm_file->f_mapping, err); } /* * Wait for writeback against this page to complete before allowing it * to be marked dirty again, and hence written back again, possibly * before the previous writepage completed. * * Block here, instead of in ->writepage(), so that the userspace fs * can only block processes actually operating on the filesystem. * * Otherwise unprivileged userspace fs would be able to block * unrelated: * * - page migration * - sync(2) * - try_to_free_pages() with order > PAGE_ALLOC_COSTLY_ORDER */ static vm_fault_t fuse_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; struct inode *inode = file_inode(vmf->vma->vm_file); file_update_time(vmf->vma->vm_file); lock_page(page); if (page->mapping != inode->i_mapping) { unlock_page(page); return VM_FAULT_NOPAGE; } fuse_wait_on_page_writeback(inode, page->index); return VM_FAULT_LOCKED; } static const struct vm_operations_struct fuse_file_vm_ops = { .close = fuse_vma_close, .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = fuse_page_mkwrite, }; static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) { struct fuse_file *ff = file->private_data; struct fuse_conn *fc = ff->fm->fc; struct inode *inode = file_inode(file); int rc; /* DAX mmap is superior to direct_io mmap */ if (FUSE_IS_DAX(inode)) return fuse_dax_mmap(file, vma); /* * If inode is in passthrough io mode, because it has some file open * in passthrough mode, either mmap to backing file or fail mmap, * because mixing cached mmap and passthrough io mode is not allowed. */ if (fuse_file_passthrough(ff)) return fuse_passthrough_mmap(file, vma); else if (fuse_inode_backing(get_fuse_inode(inode))) return -ENODEV; /* * FOPEN_DIRECT_IO handling is special compared to O_DIRECT, * as does not allow MAP_SHARED mmap without FUSE_DIRECT_IO_ALLOW_MMAP. */ if (ff->open_flags & FOPEN_DIRECT_IO) { /* * Can't provide the coherency needed for MAP_SHARED * if FUSE_DIRECT_IO_ALLOW_MMAP isn't set. */ if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_allow_mmap) return -ENODEV; invalidate_inode_pages2(file->f_mapping); if (!(vma->vm_flags & VM_MAYSHARE)) { /* MAP_PRIVATE */ return generic_file_mmap(file, vma); } /* * First mmap of direct_io file enters caching inode io mode. * Also waits for parallel dio writers to go into serial mode * (exclusive instead of shared lock). * After first mmap, the inode stays in caching io mode until * the direct_io file release. */ rc = fuse_file_cached_io_open(inode, ff); if (rc) return rc; } if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) fuse_link_write_file(file); file_accessed(file); vma->vm_ops = &fuse_file_vm_ops; return 0; } static int convert_fuse_file_lock(struct fuse_conn *fc, const struct fuse_file_lock *ffl, struct file_lock *fl) { switch (ffl->type) { case F_UNLCK: break; case F_RDLCK: case F_WRLCK: if (ffl->start > OFFSET_MAX || ffl->end > OFFSET_MAX || ffl->end < ffl->start) return -EIO; fl->fl_start = ffl->start; fl->fl_end = ffl->end; /* * Convert pid into init's pid namespace. The locks API will * translate it into the caller's pid namespace. */ rcu_read_lock(); fl->c.flc_pid = pid_nr_ns(find_pid_ns(ffl->pid, fc->pid_ns), &init_pid_ns); rcu_read_unlock(); break; default: return -EIO; } fl->c.flc_type = ffl->type; return 0; } static void fuse_lk_fill(struct fuse_args *args, struct file *file, const struct file_lock *fl, int opcode, pid_t pid, int flock, struct fuse_lk_in *inarg) { struct inode *inode = file_inode(file); struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_file *ff = file->private_data; memset(inarg, 0, sizeof(*inarg)); inarg->fh = ff->fh; inarg->owner = fuse_lock_owner_id(fc, fl->c.flc_owner); inarg->lk.start = fl->fl_start; inarg->lk.end = fl->fl_end; inarg->lk.type = fl->c.flc_type; inarg->lk.pid = pid; if (flock) inarg->lk_flags |= FUSE_LK_FLOCK; args->opcode = opcode; args->nodeid = get_node_id(inode); args->in_numargs = 1; args->in_args[0].size = sizeof(*inarg); args->in_args[0].value = inarg; } static int fuse_getlk(struct file *file, struct file_lock *fl) { struct inode *inode = file_inode(file); struct fuse_mount *fm = get_fuse_mount(inode); FUSE_ARGS(args); struct fuse_lk_in inarg; struct fuse_lk_out outarg; int err; fuse_lk_fill(&args, file, fl, FUSE_GETLK, 0, 0, &inarg); args.out_numargs = 1; args.out_args[0].size = sizeof(outarg); args.out_args[0].value = &outarg; err = fuse_simple_request(fm, &args); if (!err) err = convert_fuse_file_lock(fm->fc, &outarg.lk, fl); return err; } static int fuse_setlk(struct file *file, struct file_lock *fl, int flock) { struct inode *inode = file_inode(file); struct fuse_mount *fm = get_fuse_mount(inode); FUSE_ARGS(args); struct fuse_lk_in inarg; int opcode = (fl->c.flc_flags & FL_SLEEP) ? FUSE_SETLKW : FUSE_SETLK; struct pid *pid = fl->c.flc_type != F_UNLCK ? task_tgid(current) : NULL; pid_t pid_nr = pid_nr_ns(pid, fm->fc->pid_ns); int err; if (fl->fl_lmops && fl->fl_lmops->lm_grant) { /* NLM needs asynchronous locks, which we don't support yet */ return -ENOLCK; } fuse_lk_fill(&args, file, fl, opcode, pid_nr, flock, &inarg); err = fuse_simple_request(fm, &args); /* locking is restartable */ if (err == -EINTR) err = -ERESTARTSYS; return err; } static int fuse_file_lock(struct file *file, int cmd, struct file_lock *fl) { struct inode *inode = file_inode(file); struct fuse_conn *fc = get_fuse_conn(inode); int err; if (cmd == F_CANCELLK) { err = 0; } else if (cmd == F_GETLK) { if (fc->no_lock) { posix_test_lock(file, fl); err = 0; } else err = fuse_getlk(file, fl); } else { if (fc->no_lock) err = posix_lock_file(file, fl, NULL); else err = fuse_setlk(file, fl, 0); } return err; } static int fuse_file_flock(struct file *file, int cmd, struct file_lock *fl) { struct inode *inode = file_inode(file); struct fuse_conn *fc = get_fuse_conn(inode); int err; if (fc->no_flock) { err = locks_lock_file_wait(file, fl); } else { struct fuse_file *ff = file->private_data; /* emulate flock with POSIX locks */ ff->flock = true; err = fuse_setlk(file, fl, 1); } return err; } static sector_t fuse_bmap(struct address_space *mapping, sector_t block) { struct inode *inode = mapping->host; struct fuse_mount *fm = get_fuse_mount(inode); FUSE_ARGS(args); struct fuse_bmap_in inarg; struct fuse_bmap_out outarg; int err; if (!inode->i_sb->s_bdev || fm->fc->no_bmap) return 0; memset(&inarg, 0, sizeof(inarg)); inarg.block = block; inarg.blocksize = inode->i_sb->s_blocksize; args.opcode = FUSE_BMAP; args.nodeid = get_node_id(inode); args.in_numargs = 1; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; args.out_numargs = 1; args.out_args[0].size = sizeof(outarg); args.out_args[0].value = &outarg; err = fuse_simple_request(fm, &args); if (err == -ENOSYS) fm->fc->no_bmap = 1; return err ? 0 : outarg.block; } static loff_t fuse_lseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; struct fuse_mount *fm = get_fuse_mount(inode); struct fuse_file *ff = file->private_data; FUSE_ARGS(args); struct fuse_lseek_in inarg = { .fh = ff->fh, .offset = offset, .whence = whence }; struct fuse_lseek_out outarg; int err; if (fm->fc->no_lseek) goto fallback; args.opcode = FUSE_LSEEK; args.nodeid = ff->nodeid; args.in_numargs = 1; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; args.out_numargs = 1; args.out_args[0].size = sizeof(outarg); args.out_args[0].value = &outarg; err = fuse_simple_request(fm, &args); if (err) { if (err == -ENOSYS) { fm->fc->no_lseek = 1; goto fallback; } return err; } return vfs_setpos(file, outarg.offset, inode->i_sb->s_maxbytes); fallback: err = fuse_update_attributes(inode, file, STATX_SIZE); if (!err) return generic_file_llseek(file, offset, whence); else return err; } static loff_t fuse_file_llseek(struct file *file, loff_t offset, int whence) { loff_t retval; struct inode *inode = file_inode(file); switch (whence) { case SEEK_SET: case SEEK_CUR: /* No i_mutex protection necessary for SEEK_CUR and SEEK_SET */ retval = generic_file_llseek(file, offset, whence); break; case SEEK_END: inode_lock(inode); retval = fuse_update_attributes(inode, file, STATX_SIZE); if (!retval) retval = generic_file_llseek(file, offset, whence); inode_unlock(inode); break; case SEEK_HOLE: case SEEK_DATA: inode_lock(inode); retval = fuse_lseek(file, offset, whence); inode_unlock(inode); break; default: retval = -EINVAL; } return retval; } /* * All files which have been polled are linked to RB tree * fuse_conn->polled_files which is indexed by kh. Walk the tree and * find the matching one. */ static struct rb_node **fuse_find_polled_node(struct fuse_conn *fc, u64 kh, struct rb_node **parent_out) { struct rb_node **link = &fc->polled_files.rb_node; struct rb_node *last = NULL; while (*link) { struct fuse_file *ff; last = *link; ff = rb_entry(last, struct fuse_file, polled_node); if (kh < ff->kh) link = &last->rb_left; else if (kh > ff->kh) link = &last->rb_right; else return link; } if (parent_out) *parent_out = last; return link; } /* * The file is about to be polled. Make sure it's on the polled_files * RB tree. Note that files once added to the polled_files tree are * not removed before the file is released. This is because a file * polled once is likely to be polled again. */ static void fuse_register_polled_file(struct fuse_conn *fc, struct fuse_file *ff) { spin_lock(&fc->lock); if (RB_EMPTY_NODE(&ff->polled_node)) { struct rb_node **link, *parent; link = fuse_find_polled_node(fc, ff->kh, &parent); BUG_ON(*link); rb_link_node(&ff->polled_node, parent, link); rb_insert_color(&ff->polled_node, &fc->polled_files); } spin_unlock(&fc->lock); } __poll_t fuse_file_poll(struct file *file, poll_table *wait) { struct fuse_file *ff = file->private_data; struct fuse_mount *fm = ff->fm; struct fuse_poll_in inarg = { .fh = ff->fh, .kh = ff->kh }; struct fuse_poll_out outarg; FUSE_ARGS(args); int err; if (fm->fc->no_poll) return DEFAULT_POLLMASK; poll_wait(file, &ff->poll_wait, wait); inarg.events = mangle_poll(poll_requested_events(wait)); /* * Ask for notification iff there's someone waiting for it. * The client may ignore the flag and always notify. */ if (waitqueue_active(&ff->poll_wait)) { inarg.flags |= FUSE_POLL_SCHEDULE_NOTIFY; fuse_register_polled_file(fm->fc, ff); } args.opcode = FUSE_POLL; args.nodeid = ff->nodeid; args.in_numargs = 1; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; args.out_numargs = 1; args.out_args[0].size = sizeof(outarg); args.out_args[0].value = &outarg; err = fuse_simple_request(fm, &args); if (!err) return demangle_poll(outarg.revents); if (err == -ENOSYS) { fm->fc->no_poll = 1; return DEFAULT_POLLMASK; } return EPOLLERR; } EXPORT_SYMBOL_GPL(fuse_file_poll); /* * This is called from fuse_handle_notify() on FUSE_NOTIFY_POLL and * wakes up the poll waiters. */ int fuse_notify_poll_wakeup(struct fuse_conn *fc, struct fuse_notify_poll_wakeup_out *outarg) { u64 kh = outarg->kh; struct rb_node **link; spin_lock(&fc->lock); link = fuse_find_polled_node(fc, kh, NULL); if (*link) { struct fuse_file *ff; ff = rb_entry(*link, struct fuse_file, polled_node); wake_up_interruptible_sync(&ff->poll_wait); } spin_unlock(&fc->lock); return 0; } static void fuse_do_truncate(struct file *file) { struct inode *inode = file->f_mapping->host; struct iattr attr; attr.ia_valid = ATTR_SIZE; attr.ia_size = i_size_read(inode); attr.ia_file = file; attr.ia_valid |= ATTR_FILE; fuse_do_setattr(file_dentry(file), &attr, file); } static inline loff_t fuse_round_up(struct fuse_conn *fc, loff_t off) { return round_up(off, fc->max_pages << PAGE_SHIFT); } static ssize_t fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { DECLARE_COMPLETION_ONSTACK(wait); ssize_t ret = 0; struct file *file = iocb->ki_filp; struct fuse_file *ff = file->private_data; loff_t pos = 0; struct inode *inode; loff_t i_size; size_t count = iov_iter_count(iter), shortened = 0; loff_t offset = iocb->ki_pos; struct fuse_io_priv *io; pos = offset; inode = file->f_mapping->host; i_size = i_size_read(inode); if ((iov_iter_rw(iter) == READ) && (offset >= i_size)) return 0; io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL); if (!io) return -ENOMEM; spin_lock_init(&io->lock); kref_init(&io->refcnt); io->reqs = 1; io->bytes = -1; io->size = 0; io->offset = offset; io->write = (iov_iter_rw(iter) == WRITE); io->err = 0; /* * By default, we want to optimize all I/Os with async request * submission to the client filesystem if supported. */ io->async = ff->fm->fc->async_dio; io->iocb = iocb; io->blocking = is_sync_kiocb(iocb); /* optimization for short read */ if (io->async && !io->write && offset + count > i_size) { iov_iter_truncate(iter, fuse_round_up(ff->fm->fc, i_size - offset)); shortened = count - iov_iter_count(iter); count -= shortened; } /* * We cannot asynchronously extend the size of a file. * In such case the aio will behave exactly like sync io. */ if ((offset + count > i_size) && io->write) io->blocking = true; if (io->async && io->blocking) { /* * Additional reference to keep io around after * calling fuse_aio_complete() */ kref_get(&io->refcnt); io->done = &wait; } if (iov_iter_rw(iter) == WRITE) { ret = fuse_direct_io(io, iter, &pos, FUSE_DIO_WRITE); fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE); } else { ret = __fuse_direct_read(io, iter, &pos); } iov_iter_reexpand(iter, iov_iter_count(iter) + shortened); if (io->async) { bool blocking = io->blocking; fuse_aio_complete(io, ret < 0 ? ret : 0, -1); /* we have a non-extending, async request, so return */ if (!blocking) return -EIOCBQUEUED; wait_for_completion(&wait); ret = fuse_get_res_by_io(io); } kref_put(&io->refcnt, fuse_io_release); if (iov_iter_rw(iter) == WRITE) { fuse_write_update_attr(inode, pos, ret); /* For extending writes we already hold exclusive lock */ if (ret < 0 && offset + count > i_size) fuse_do_truncate(file); } return ret; } static int fuse_writeback_range(struct inode *inode, loff_t start, loff_t end) { int err = filemap_write_and_wait_range(inode->i_mapping, start, LLONG_MAX); if (!err) fuse_sync_writes(inode); return err; } static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, loff_t length) { struct fuse_file *ff = file->private_data; struct inode *inode = file_inode(file); struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_mount *fm = ff->fm; FUSE_ARGS(args); struct fuse_fallocate_in inarg = { .fh = ff->fh, .offset = offset, .length = length, .mode = mode }; int err; bool block_faults = FUSE_IS_DAX(inode) && (!(mode & FALLOC_FL_KEEP_SIZE) || (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE))); if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) return -EOPNOTSUPP; if (fm->fc->no_fallocate) return -EOPNOTSUPP; inode_lock(inode); if (block_faults) { filemap_invalidate_lock(inode->i_mapping); err = fuse_dax_break_layouts(inode, 0, 0); if (err) goto out; } if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) { loff_t endbyte = offset + length - 1; err = fuse_writeback_range(inode, offset, endbyte); if (err) goto out; } if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + length > i_size_read(inode)) { err = inode_newsize_ok(inode, offset + length); if (err) goto out; } err = file_modified(file); if (err) goto out; if (!(mode & FALLOC_FL_KEEP_SIZE)) set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); args.opcode = FUSE_FALLOCATE; args.nodeid = ff->nodeid; args.in_numargs = 1; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; err = fuse_simple_request(fm, &args); if (err == -ENOSYS) { fm->fc->no_fallocate = 1; err = -EOPNOTSUPP; } if (err) goto out; /* we could have extended the file */ if (!(mode & FALLOC_FL_KEEP_SIZE)) { if (fuse_write_update_attr(inode, offset + length, length)) file_update_time(file); } if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) truncate_pagecache_range(inode, offset, offset + length - 1); fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE); out: if (!(mode & FALLOC_FL_KEEP_SIZE)) clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); if (block_faults) filemap_invalidate_unlock(inode->i_mapping); inode_unlock(inode); fuse_flush_time_update(inode); return err; } static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { struct fuse_file *ff_in = file_in->private_data; struct fuse_file *ff_out = file_out->private_data; struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); struct fuse_inode *fi_out = get_fuse_inode(inode_out); struct fuse_mount *fm = ff_in->fm; struct fuse_conn *fc = fm->fc; FUSE_ARGS(args); struct fuse_copy_file_range_in inarg = { .fh_in = ff_in->fh, .off_in = pos_in, .nodeid_out = ff_out->nodeid, .fh_out = ff_out->fh, .off_out = pos_out, .len = len, .flags = flags }; struct fuse_write_out outarg; ssize_t err; /* mark unstable when write-back is not used, and file_out gets * extended */ bool is_unstable = (!fc->writeback_cache) && ((pos_out + len) > inode_out->i_size); if (fc->no_copy_file_range) return -EOPNOTSUPP; if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) return -EXDEV; inode_lock(inode_in); err = fuse_writeback_range(inode_in, pos_in, pos_in + len - 1); inode_unlock(inode_in); if (err) return err; inode_lock(inode_out); err = file_modified(file_out); if (err) goto out; /* * Write out dirty pages in the destination file before sending the COPY * request to userspace. After the request is completed, truncate off * pages (including partial ones) from the cache that have been copied, * since these contain stale data at that point. * * This should be mostly correct, but if the COPY writes to partial * pages (at the start or end) and the parts not covered by the COPY are * written through a memory map after calling fuse_writeback_range(), * then these partial page modifications will be lost on truncation. * * It is unlikely that someone would rely on such mixed style * modifications. Yet this does give less guarantees than if the * copying was performed with write(2). * * To fix this a mapping->invalidate_lock could be used to prevent new * faults while the copy is ongoing. */ err = fuse_writeback_range(inode_out, pos_out, pos_out + len - 1); if (err) goto out; if (is_unstable) set_bit(FUSE_I_SIZE_UNSTABLE, &fi_out->state); args.opcode = FUSE_COPY_FILE_RANGE; args.nodeid = ff_in->nodeid; args.in_numargs = 1; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; args.out_numargs = 1; args.out_args[0].size = sizeof(outarg); args.out_args[0].value = &outarg; err = fuse_simple_request(fm, &args); if (err == -ENOSYS) { fc->no_copy_file_range = 1; err = -EOPNOTSUPP; } if (err) goto out; truncate_inode_pages_range(inode_out->i_mapping, ALIGN_DOWN(pos_out, PAGE_SIZE), ALIGN(pos_out + outarg.size, PAGE_SIZE) - 1); file_update_time(file_out); fuse_write_update_attr(inode_out, pos_out + outarg.size, outarg.size); err = outarg.size; out: if (is_unstable) clear_bit(FUSE_I_SIZE_UNSTABLE, &fi_out->state); inode_unlock(inode_out); file_accessed(file_in); fuse_flush_time_update(inode_out); return err; } static ssize_t fuse_copy_file_range(struct file *src_file, loff_t src_off, struct file *dst_file, loff_t dst_off, size_t len, unsigned int flags) { ssize_t ret; ret = __fuse_copy_file_range(src_file, src_off, dst_file, dst_off, len, flags); if (ret == -EOPNOTSUPP || ret == -EXDEV) ret = splice_copy_file_range(src_file, src_off, dst_file, dst_off, len); return ret; } static const struct file_operations fuse_file_operations = { .llseek = fuse_file_llseek, .read_iter = fuse_file_read_iter, .write_iter = fuse_file_write_iter, .mmap = fuse_file_mmap, .open = fuse_open, .flush = fuse_flush, .release = fuse_release, .fsync = fuse_fsync, .lock = fuse_file_lock, .get_unmapped_area = thp_get_unmapped_area, .flock = fuse_file_flock, .splice_read = fuse_splice_read, .splice_write = fuse_splice_write, .unlocked_ioctl = fuse_file_ioctl, .compat_ioctl = fuse_file_compat_ioctl, .poll = fuse_file_poll, .fallocate = fuse_file_fallocate, .copy_file_range = fuse_copy_file_range, }; static const struct address_space_operations fuse_file_aops = { .read_folio = fuse_read_folio, .readahead = fuse_readahead, .writepages = fuse_writepages, .launder_folio = fuse_launder_folio, .dirty_folio = filemap_dirty_folio, .migrate_folio = filemap_migrate_folio, .bmap = fuse_bmap, .direct_IO = fuse_direct_IO, .write_begin = fuse_write_begin, .write_end = fuse_write_end, }; void fuse_init_file_inode(struct inode *inode, unsigned int flags) { struct fuse_inode *fi = get_fuse_inode(inode); inode->i_fop = &fuse_file_operations; inode->i_data.a_ops = &fuse_file_aops; INIT_LIST_HEAD(&fi->write_files); INIT_LIST_HEAD(&fi->queued_writes); fi->writectr = 0; fi->iocachectr = 0; init_waitqueue_head(&fi->page_waitq); init_waitqueue_head(&fi->direct_io_waitq); fi->writepages = RB_ROOT; if (IS_ENABLED(CONFIG_FUSE_DAX)) fuse_dax_inode_init(inode, flags); } |
| 140 82 5 61 290 292 62 261 259 262 142 141 9 141 139 12 141 141 141 11 12 12 12 5 5 12 12 12 2 12 2 2 10 10 10 10 2 9 9 9 8 9 9 8 12 12 132 5 139 106 107 95 13 94 14 12 12 8 8 6 248 1 1 2 2 2 2 2 2 2 2 2 2 2 1 1 1 72 72 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Integrity Measurement Architecture * * Copyright (C) 2005,2006,2007,2008 IBM Corporation * * Authors: * Reiner Sailer <sailer@watson.ibm.com> * Serge Hallyn <serue@us.ibm.com> * Kylene Hall <kylene@us.ibm.com> * Mimi Zohar <zohar@us.ibm.com> * * File: ima_main.c * implements the IMA hooks: ima_bprm_check, ima_file_mmap, * and ima_file_check. */ #include <linux/module.h> #include <linux/file.h> #include <linux/binfmts.h> #include <linux/kernel_read_file.h> #include <linux/mount.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/xattr.h> #include <linux/ima.h> #include <linux/fs.h> #include <linux/iversion.h> #include <linux/evm.h> #include "ima.h" #ifdef CONFIG_IMA_APPRAISE int ima_appraise = IMA_APPRAISE_ENFORCE; #else int ima_appraise; #endif int __ro_after_init ima_hash_algo = HASH_ALGO_SHA1; static int hash_setup_done; static struct notifier_block ima_lsm_policy_notifier = { .notifier_call = ima_lsm_policy_change, }; static int __init hash_setup(char *str) { struct ima_template_desc *template_desc = ima_template_desc_current(); int i; if (hash_setup_done) return 1; if (strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0) { if (strncmp(str, "sha1", 4) == 0) { ima_hash_algo = HASH_ALGO_SHA1; } else if (strncmp(str, "md5", 3) == 0) { ima_hash_algo = HASH_ALGO_MD5; } else { pr_err("invalid hash algorithm \"%s\" for template \"%s\"", str, IMA_TEMPLATE_IMA_NAME); return 1; } goto out; } i = match_string(hash_algo_name, HASH_ALGO__LAST, str); if (i < 0) { pr_err("invalid hash algorithm \"%s\"", str); return 1; } ima_hash_algo = i; out: hash_setup_done = 1; return 1; } __setup("ima_hash=", hash_setup); enum hash_algo ima_get_current_hash_algo(void) { return ima_hash_algo; } /* Prevent mmap'ing a file execute that is already mmap'ed write */ static int mmap_violation_check(enum ima_hooks func, struct file *file, char **pathbuf, const char **pathname, char *filename) { struct inode *inode; int rc = 0; if ((func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) && mapping_writably_mapped(file->f_mapping)) { rc = -ETXTBSY; inode = file_inode(file); if (!*pathbuf) /* ima_rdwr_violation possibly pre-fetched */ *pathname = ima_d_path(&file->f_path, pathbuf, filename); integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, *pathname, "mmap_file", "mmapped_writers", rc, 0); } return rc; } /* * ima_rdwr_violation_check * * Only invalidate the PCR for measured files: * - Opening a file for write when already open for read, * results in a time of measure, time of use (ToMToU) error. * - Opening a file for read when already open for write, * could result in a file measurement error. * */ static void ima_rdwr_violation_check(struct file *file, struct ima_iint_cache *iint, int must_measure, char **pathbuf, const char **pathname, char *filename) { struct inode *inode = file_inode(file); fmode_t mode = file->f_mode; bool send_tomtou = false, send_writers = false; if (mode & FMODE_WRITE) { if (atomic_read(&inode->i_readcount) && IS_IMA(inode)) { if (!iint) iint = ima_iint_find(inode); /* IMA_MEASURE is set from reader side */ if (iint && test_bit(IMA_MUST_MEASURE, &iint->atomic_flags)) send_tomtou = true; } } else { if (must_measure) set_bit(IMA_MUST_MEASURE, &iint->atomic_flags); if (inode_is_open_for_write(inode) && must_measure) send_writers = true; } if (!send_tomtou && !send_writers) return; *pathname = ima_d_path(&file->f_path, pathbuf, filename); if (send_tomtou) ima_add_violation(file, *pathname, iint, "invalid_pcr", "ToMToU"); if (send_writers) ima_add_violation(file, *pathname, iint, "invalid_pcr", "open_writers"); } static void ima_check_last_writer(struct ima_iint_cache *iint, struct inode *inode, struct file *file) { fmode_t mode = file->f_mode; bool update; if (!(mode & FMODE_WRITE)) return; mutex_lock(&iint->mutex); if (atomic_read(&inode->i_writecount) == 1) { struct kstat stat; update = test_and_clear_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); if ((iint->flags & IMA_NEW_FILE) || vfs_getattr_nosec(&file->f_path, &stat, STATX_CHANGE_COOKIE, AT_STATX_SYNC_AS_STAT) || !(stat.result_mask & STATX_CHANGE_COOKIE) || stat.change_cookie != iint->real_inode.version) { iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE); iint->measured_pcrs = 0; if (update) ima_update_xattr(iint, file); } } mutex_unlock(&iint->mutex); } /** * ima_file_free - called on __fput() * @file: pointer to file structure being freed * * Flag files that changed, based on i_version */ static void ima_file_free(struct file *file) { struct inode *inode = file_inode(file); struct ima_iint_cache *iint; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; iint = ima_iint_find(inode); if (!iint) return; ima_check_last_writer(iint, inode, file); } static int process_measurement(struct file *file, const struct cred *cred, u32 secid, char *buf, loff_t size, int mask, enum ima_hooks func) { struct inode *real_inode, *inode = file_inode(file); struct ima_iint_cache *iint = NULL; struct ima_template_desc *template_desc = NULL; struct inode *metadata_inode; char *pathbuf = NULL; char filename[NAME_MAX]; const char *pathname = NULL; int rc = 0, action, must_appraise = 0; int pcr = CONFIG_IMA_MEASURE_PCR_IDX; struct evm_ima_xattr_data *xattr_value = NULL; struct modsig *modsig = NULL; int xattr_len = 0; bool violation_check; enum hash_algo hash_algo; unsigned int allowed_algos = 0; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return 0; /* Return an IMA_MEASURE, IMA_APPRAISE, IMA_AUDIT action * bitmask based on the appraise/audit/measurement policy. * Included is the appraise submask. */ action = ima_get_action(file_mnt_idmap(file), inode, cred, secid, mask, func, &pcr, &template_desc, NULL, &allowed_algos); violation_check = ((func == FILE_CHECK || func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) && (ima_policy_flag & IMA_MEASURE)); if (!action && !violation_check) return 0; must_appraise = action & IMA_APPRAISE; /* Is the appraise rule hook specific? */ if (action & IMA_FILE_APPRAISE) func = FILE_CHECK; inode_lock(inode); if (action) { iint = ima_inode_get(inode); if (!iint) rc = -ENOMEM; } if (!rc && violation_check) ima_rdwr_violation_check(file, iint, action & IMA_MEASURE, &pathbuf, &pathname, filename); inode_unlock(inode); if (rc) goto out; if (!action) goto out; mutex_lock(&iint->mutex); if (test_and_clear_bit(IMA_CHANGE_ATTR, &iint->atomic_flags)) /* reset appraisal flags if ima_inode_post_setattr was called */ iint->flags &= ~(IMA_APPRAISE | IMA_APPRAISED | IMA_APPRAISE_SUBMASK | IMA_APPRAISED_SUBMASK | IMA_NONACTION_FLAGS); /* * Re-evaulate the file if either the xattr has changed or the * kernel has no way of detecting file change on the filesystem. * (Limited to privileged mounted filesystems.) */ if (test_and_clear_bit(IMA_CHANGE_XATTR, &iint->atomic_flags) || ((inode->i_sb->s_iflags & SB_I_IMA_UNVERIFIABLE_SIGNATURE) && !(inode->i_sb->s_iflags & SB_I_UNTRUSTED_MOUNTER) && !(action & IMA_FAIL_UNVERIFIABLE_SIGS))) { iint->flags &= ~IMA_DONE_MASK; iint->measured_pcrs = 0; } /* * On stacked filesystems, detect and re-evaluate file data and * metadata changes. */ real_inode = d_real_inode(file_dentry(file)); if (real_inode != inode && (action & IMA_DO_MASK) && (iint->flags & IMA_DONE_MASK)) { if (!IS_I_VERSION(real_inode) || integrity_inode_attrs_changed(&iint->real_inode, real_inode)) { iint->flags &= ~IMA_DONE_MASK; iint->measured_pcrs = 0; } /* * Reset the EVM status when metadata changed. */ metadata_inode = d_inode(d_real(file_dentry(file), D_REAL_METADATA)); if (evm_metadata_changed(inode, metadata_inode)) iint->flags &= ~(IMA_APPRAISED | IMA_APPRAISED_SUBMASK); } /* Determine if already appraised/measured based on bitmask * (IMA_MEASURE, IMA_MEASURED, IMA_XXXX_APPRAISE, IMA_XXXX_APPRAISED, * IMA_AUDIT, IMA_AUDITED) */ iint->flags |= action; action &= IMA_DO_MASK; action &= ~((iint->flags & (IMA_DONE_MASK ^ IMA_MEASURED)) >> 1); /* If target pcr is already measured, unset IMA_MEASURE action */ if ((action & IMA_MEASURE) && (iint->measured_pcrs & (0x1 << pcr))) action ^= IMA_MEASURE; /* HASH sets the digital signature and update flags, nothing else */ if ((action & IMA_HASH) && !(test_bit(IMA_DIGSIG, &iint->atomic_flags))) { xattr_len = ima_read_xattr(file_dentry(file), &xattr_value, xattr_len); if ((xattr_value && xattr_len > 2) && (xattr_value->type == EVM_IMA_XATTR_DIGSIG)) set_bit(IMA_DIGSIG, &iint->atomic_flags); iint->flags |= IMA_HASHED; action ^= IMA_HASH; set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } /* Nothing to do, just return existing appraised status */ if (!action) { if (must_appraise) { rc = mmap_violation_check(func, file, &pathbuf, &pathname, filename); if (!rc) rc = ima_get_cache_status(iint, func); } goto out_locked; } if ((action & IMA_APPRAISE_SUBMASK) || strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0) { /* read 'security.ima' */ xattr_len = ima_read_xattr(file_dentry(file), &xattr_value, xattr_len); /* * Read the appended modsig if allowed by the policy, and allow * an additional measurement list entry, if needed, based on the * template format and whether the file was already measured. */ if (iint->flags & IMA_MODSIG_ALLOWED) { rc = ima_read_modsig(func, buf, size, &modsig); if (!rc && ima_template_has_modsig(template_desc) && iint->flags & IMA_MEASURED) action |= IMA_MEASURE; } } hash_algo = ima_get_hash_algo(xattr_value, xattr_len); rc = ima_collect_measurement(iint, file, buf, size, hash_algo, modsig); if (rc != 0 && rc != -EBADF && rc != -EINVAL) goto out_locked; if (!pathbuf) /* ima_rdwr_violation possibly pre-fetched */ pathname = ima_d_path(&file->f_path, &pathbuf, filename); if (action & IMA_MEASURE) ima_store_measurement(iint, file, pathname, xattr_value, xattr_len, modsig, pcr, template_desc); if (rc == 0 && (action & IMA_APPRAISE_SUBMASK)) { rc = ima_check_blacklist(iint, modsig, pcr); if (rc != -EPERM) { inode_lock(inode); rc = ima_appraise_measurement(func, iint, file, pathname, xattr_value, xattr_len, modsig); inode_unlock(inode); } if (!rc) rc = mmap_violation_check(func, file, &pathbuf, &pathname, filename); } if (action & IMA_AUDIT) ima_audit_measurement(iint, pathname); if ((file->f_flags & O_DIRECT) && (iint->flags & IMA_PERMIT_DIRECTIO)) rc = 0; /* Ensure the digest was generated using an allowed algorithm */ if (rc == 0 && must_appraise && allowed_algos != 0 && (allowed_algos & (1U << hash_algo)) == 0) { rc = -EACCES; integrity_audit_msg(AUDIT_INTEGRITY_DATA, file_inode(file), pathname, "collect_data", "denied-hash-algorithm", rc, 0); } out_locked: if ((mask & MAY_WRITE) && test_bit(IMA_DIGSIG, &iint->atomic_flags) && !(iint->flags & IMA_NEW_FILE)) rc = -EACCES; mutex_unlock(&iint->mutex); kfree(xattr_value); ima_free_modsig(modsig); out: if (pathbuf) __putname(pathbuf); if (must_appraise) { if (rc && (ima_appraise & IMA_APPRAISE_ENFORCE)) return -EACCES; if (file->f_mode & FMODE_WRITE) set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } return 0; } /** * ima_file_mmap - based on policy, collect/store measurement. * @file: pointer to the file to be measured (May be NULL) * @reqprot: protection requested by the application * @prot: protection that will be applied by the kernel * @flags: operational flags * * Measure files being mmapped executable based on the ima_must_measure() * policy decision. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_file_mmap(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { u32 secid; int ret; if (!file) return 0; security_current_getsecid_subj(&secid); if (reqprot & PROT_EXEC) { ret = process_measurement(file, current_cred(), secid, NULL, 0, MAY_EXEC, MMAP_CHECK_REQPROT); if (ret) return ret; } if (prot & PROT_EXEC) return process_measurement(file, current_cred(), secid, NULL, 0, MAY_EXEC, MMAP_CHECK); return 0; } /** * ima_file_mprotect - based on policy, limit mprotect change * @vma: vm_area_struct protection is set to * @reqprot: protection requested by the application * @prot: protection that will be applied by the kernel * * Files can be mmap'ed read/write and later changed to execute to circumvent * IMA's mmap appraisal policy rules. Due to locking issues (mmap semaphore * would be taken before i_mutex), files can not be measured or appraised at * this point. Eliminate this integrity gap by denying the mprotect * PROT_EXECUTE change, if an mmap appraise policy rule exists. * * On mprotect change success, return 0. On failure, return -EACESS. */ static int ima_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { struct ima_template_desc *template = NULL; struct file *file; char filename[NAME_MAX]; char *pathbuf = NULL; const char *pathname = NULL; struct inode *inode; int result = 0; int action; u32 secid; int pcr; /* Is mprotect making an mmap'ed file executable? */ if (!(ima_policy_flag & IMA_APPRAISE) || !vma->vm_file || !(prot & PROT_EXEC) || (vma->vm_flags & VM_EXEC)) return 0; security_current_getsecid_subj(&secid); inode = file_inode(vma->vm_file); action = ima_get_action(file_mnt_idmap(vma->vm_file), inode, current_cred(), secid, MAY_EXEC, MMAP_CHECK, &pcr, &template, NULL, NULL); action |= ima_get_action(file_mnt_idmap(vma->vm_file), inode, current_cred(), secid, MAY_EXEC, MMAP_CHECK_REQPROT, &pcr, &template, NULL, NULL); /* Is the mmap'ed file in policy? */ if (!(action & (IMA_MEASURE | IMA_APPRAISE_SUBMASK))) return 0; if (action & IMA_APPRAISE_SUBMASK) result = -EPERM; file = vma->vm_file; pathname = ima_d_path(&file->f_path, &pathbuf, filename); integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, pathname, "collect_data", "failed-mprotect", result, 0); if (pathbuf) __putname(pathbuf); return result; } /** * ima_bprm_check - based on policy, collect/store measurement. * @bprm: contains the linux_binprm structure * * The OS protects against an executable file, already open for write, * from being executed in deny_write_access() and an executable file, * already open for execute, from being modified in get_write_access(). * So we can be certain that what we verify and measure here is actually * what is being executed. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_bprm_check(struct linux_binprm *bprm) { int ret; u32 secid; security_current_getsecid_subj(&secid); ret = process_measurement(bprm->file, current_cred(), secid, NULL, 0, MAY_EXEC, BPRM_CHECK); if (ret) return ret; security_cred_getsecid(bprm->cred, &secid); return process_measurement(bprm->file, bprm->cred, secid, NULL, 0, MAY_EXEC, CREDS_CHECK); } /** * ima_file_check - based on policy, collect/store measurement. * @file: pointer to the file to be measured * @mask: contains MAY_READ, MAY_WRITE, MAY_EXEC or MAY_APPEND * * Measure files based on the ima_must_measure() policy decision. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_file_check(struct file *file, int mask) { u32 secid; security_current_getsecid_subj(&secid); return process_measurement(file, current_cred(), secid, NULL, 0, mask & (MAY_READ | MAY_WRITE | MAY_EXEC | MAY_APPEND), FILE_CHECK); } static int __ima_inode_hash(struct inode *inode, struct file *file, char *buf, size_t buf_size) { struct ima_iint_cache *iint = NULL, tmp_iint; int rc, hash_algo; if (ima_policy_flag) { iint = ima_iint_find(inode); if (iint) mutex_lock(&iint->mutex); } if ((!iint || !(iint->flags & IMA_COLLECTED)) && file) { if (iint) mutex_unlock(&iint->mutex); memset(&tmp_iint, 0, sizeof(tmp_iint)); mutex_init(&tmp_iint.mutex); rc = ima_collect_measurement(&tmp_iint, file, NULL, 0, ima_hash_algo, NULL); if (rc < 0) { /* ima_hash could be allocated in case of failure. */ if (rc != -ENOMEM) kfree(tmp_iint.ima_hash); return -EOPNOTSUPP; } iint = &tmp_iint; mutex_lock(&iint->mutex); } if (!iint) return -EOPNOTSUPP; /* * ima_file_hash can be called when ima_collect_measurement has still * not been called, we might not always have a hash. */ if (!iint->ima_hash || !(iint->flags & IMA_COLLECTED)) { mutex_unlock(&iint->mutex); return -EOPNOTSUPP; } if (buf) { size_t copied_size; copied_size = min_t(size_t, iint->ima_hash->length, buf_size); memcpy(buf, iint->ima_hash->digest, copied_size); } hash_algo = iint->ima_hash->algo; mutex_unlock(&iint->mutex); if (iint == &tmp_iint) kfree(iint->ima_hash); return hash_algo; } /** * ima_file_hash - return a measurement of the file * @file: pointer to the file * @buf: buffer in which to store the hash * @buf_size: length of the buffer * * On success, return the hash algorithm (as defined in the enum hash_algo). * If buf is not NULL, this function also outputs the hash into buf. * If the hash is larger than buf_size, then only buf_size bytes will be copied. * It generally just makes sense to pass a buffer capable of holding the largest * possible hash: IMA_MAX_DIGEST_SIZE. * The file hash returned is based on the entire file, including the appended * signature. * * If the measurement cannot be performed, return -EOPNOTSUPP. * If the parameters are incorrect, return -EINVAL. */ int ima_file_hash(struct file *file, char *buf, size_t buf_size) { if (!file) return -EINVAL; return __ima_inode_hash(file_inode(file), file, buf, buf_size); } EXPORT_SYMBOL_GPL(ima_file_hash); /** * ima_inode_hash - return the stored measurement if the inode has been hashed * and is in the iint cache. * @inode: pointer to the inode * @buf: buffer in which to store the hash * @buf_size: length of the buffer * * On success, return the hash algorithm (as defined in the enum hash_algo). * If buf is not NULL, this function also outputs the hash into buf. * If the hash is larger than buf_size, then only buf_size bytes will be copied. * It generally just makes sense to pass a buffer capable of holding the largest * possible hash: IMA_MAX_DIGEST_SIZE. * The hash returned is based on the entire contents, including the appended * signature. * * If IMA is disabled or if no measurement is available, return -EOPNOTSUPP. * If the parameters are incorrect, return -EINVAL. */ int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size) { if (!inode) return -EINVAL; return __ima_inode_hash(inode, NULL, buf, buf_size); } EXPORT_SYMBOL_GPL(ima_inode_hash); /** * ima_post_create_tmpfile - mark newly created tmpfile as new * @idmap: idmap of the mount the inode was found from * @inode: inode of the newly created tmpfile * * No measuring, appraising or auditing of newly created tmpfiles is needed. * Skip calling process_measurement(), but indicate which newly, created * tmpfiles are in policy. */ static void ima_post_create_tmpfile(struct mnt_idmap *idmap, struct inode *inode) { struct ima_iint_cache *iint; int must_appraise; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS, FILE_CHECK); if (!must_appraise) return; /* Nothing to do if we can't allocate memory */ iint = ima_inode_get(inode); if (!iint) return; /* needed for writing the security xattrs */ set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); iint->ima_file_status = INTEGRITY_PASS; } /** * ima_post_path_mknod - mark as a new inode * @idmap: idmap of the mount the inode was found from * @dentry: newly created dentry * * Mark files created via the mknodat syscall as new, so that the * file data can be written later. */ static void ima_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { struct ima_iint_cache *iint; struct inode *inode = dentry->d_inode; int must_appraise; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS, FILE_CHECK); if (!must_appraise) return; /* Nothing to do if we can't allocate memory */ iint = ima_inode_get(inode); if (!iint) return; /* needed for re-opening empty files */ iint->flags |= IMA_NEW_FILE; } /** * ima_read_file - pre-measure/appraise hook decision based on policy * @file: pointer to the file to be measured/appraised/audit * @read_id: caller identifier * @contents: whether a subsequent call will be made to ima_post_read_file() * * Permit reading a file based on policy. The policy rules are written * in terms of the policy identifier. Appraising the integrity of * a file requires a file descriptor. * * For permission return 0, otherwise return -EACCES. */ static int ima_read_file(struct file *file, enum kernel_read_file_id read_id, bool contents) { enum ima_hooks func; u32 secid; /* * Do devices using pre-allocated memory run the risk of the * firmware being accessible to the device prior to the completion * of IMA's signature verification any more than when using two * buffers? It may be desirable to include the buffer address * in this API and walk all the dma_map_single() mappings to check. */ /* * There will be a call made to ima_post_read_file() with * a filled buffer, so we don't need to perform an extra * read early here. */ if (contents) return 0; /* Read entire file for all partial reads. */ func = read_idmap[read_id] ?: FILE_CHECK; security_current_getsecid_subj(&secid); return process_measurement(file, current_cred(), secid, NULL, 0, MAY_READ, func); } const int read_idmap[READING_MAX_ID] = { [READING_FIRMWARE] = FIRMWARE_CHECK, [READING_MODULE] = MODULE_CHECK, [READING_KEXEC_IMAGE] = KEXEC_KERNEL_CHECK, [READING_KEXEC_INITRAMFS] = KEXEC_INITRAMFS_CHECK, [READING_POLICY] = POLICY_CHECK }; /** * ima_post_read_file - in memory collect/appraise/audit measurement * @file: pointer to the file to be measured/appraised/audit * @buf: pointer to in memory file contents * @size: size of in memory file contents * @read_id: caller identifier * * Measure/appraise/audit in memory file based on policy. Policy rules * are written in terms of a policy identifier. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id read_id) { enum ima_hooks func; u32 secid; /* permit signed certs */ if (!file && read_id == READING_X509_CERTIFICATE) return 0; if (!file || !buf || size == 0) { /* should never happen */ if (ima_appraise & IMA_APPRAISE_ENFORCE) return -EACCES; return 0; } func = read_idmap[read_id] ?: FILE_CHECK; security_current_getsecid_subj(&secid); return process_measurement(file, current_cred(), secid, buf, size, MAY_READ, func); } /** * ima_load_data - appraise decision based on policy * @id: kernel load data caller identifier * @contents: whether the full contents will be available in a later * call to ima_post_load_data(). * * Callers of this LSM hook can not measure, appraise, or audit the * data provided by userspace. Enforce policy rules requiring a file * signature (eg. kexec'ed kernel image). * * For permission return 0, otherwise return -EACCES. */ static int ima_load_data(enum kernel_load_data_id id, bool contents) { bool ima_enforce, sig_enforce; ima_enforce = (ima_appraise & IMA_APPRAISE_ENFORCE) == IMA_APPRAISE_ENFORCE; switch (id) { case LOADING_KEXEC_IMAGE: if (IS_ENABLED(CONFIG_KEXEC_SIG) && arch_ima_get_secureboot()) { pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); return -EACCES; } if (ima_enforce && (ima_appraise & IMA_APPRAISE_KEXEC)) { pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; case LOADING_FIRMWARE: if (ima_enforce && (ima_appraise & IMA_APPRAISE_FIRMWARE) && !contents) { pr_err("Prevent firmware sysfs fallback loading.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; case LOADING_MODULE: sig_enforce = is_module_sig_enforced(); if (ima_enforce && (!sig_enforce && (ima_appraise & IMA_APPRAISE_MODULES))) { pr_err("impossible to appraise a module without a file descriptor. sig_enforce kernel parameter might help\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; default: break; } return 0; } /** * ima_post_load_data - appraise decision based on policy * @buf: pointer to in memory file contents * @size: size of in memory file contents * @load_id: kernel load data caller identifier * @description: @load_id-specific description of contents * * Measure/appraise/audit in memory buffer based on policy. Policy rules * are written in terms of a policy identifier. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_post_load_data(char *buf, loff_t size, enum kernel_load_data_id load_id, char *description) { if (load_id == LOADING_FIRMWARE) { if ((ima_appraise & IMA_APPRAISE_FIRMWARE) && (ima_appraise & IMA_APPRAISE_ENFORCE)) { pr_err("Prevent firmware loading_store.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } return 0; } /* * Measure the init_module syscall buffer containing the ELF image. */ if (load_id == LOADING_MODULE) ima_measure_critical_data("modules", "init_module", buf, size, true, NULL, 0); return 0; } /** * process_buffer_measurement - Measure the buffer or the buffer data hash * @idmap: idmap of the mount the inode was found from * @inode: inode associated with the object being measured (NULL for KEY_CHECK) * @buf: pointer to the buffer that needs to be added to the log. * @size: size of buffer(in bytes). * @eventname: event name to be used for the buffer entry. * @func: IMA hook * @pcr: pcr to extend the measurement * @func_data: func specific data, may be NULL * @buf_hash: measure buffer data hash * @digest: buffer digest will be written to * @digest_len: buffer length * * Based on policy, either the buffer data or buffer data hash is measured * * Return: 0 if the buffer has been successfully measured, 1 if the digest * has been written to the passed location but not added to a measurement entry, * a negative value otherwise. */ int process_buffer_measurement(struct mnt_idmap *idmap, struct inode *inode, const void *buf, int size, const char *eventname, enum ima_hooks func, int pcr, const char *func_data, bool buf_hash, u8 *digest, size_t digest_len) { int ret = 0; const char *audit_cause = "ENOMEM"; struct ima_template_entry *entry = NULL; struct ima_iint_cache iint = {}; struct ima_event_data event_data = {.iint = &iint, .filename = eventname, .buf = buf, .buf_len = size}; struct ima_template_desc *template; struct ima_max_digest_data hash; struct ima_digest_data *hash_hdr = container_of(&hash.hdr, struct ima_digest_data, hdr); char digest_hash[IMA_MAX_DIGEST_SIZE]; int digest_hash_len = hash_digest_size[ima_hash_algo]; int violation = 0; int action = 0; u32 secid; if (digest && digest_len < digest_hash_len) return -EINVAL; if (!ima_policy_flag && !digest) return -ENOENT; template = ima_template_desc_buf(); if (!template) { ret = -EINVAL; audit_cause = "ima_template_desc_buf"; goto out; } /* * Both LSM hooks and auxilary based buffer measurements are * based on policy. To avoid code duplication, differentiate * between the LSM hooks and auxilary buffer measurements, * retrieving the policy rule information only for the LSM hook * buffer measurements. */ if (func) { security_current_getsecid_subj(&secid); action = ima_get_action(idmap, inode, current_cred(), secid, 0, func, &pcr, &template, func_data, NULL); if (!(action & IMA_MEASURE) && !digest) return -ENOENT; } if (!pcr) pcr = CONFIG_IMA_MEASURE_PCR_IDX; iint.ima_hash = hash_hdr; iint.ima_hash->algo = ima_hash_algo; iint.ima_hash->length = hash_digest_size[ima_hash_algo]; ret = ima_calc_buffer_hash(buf, size, iint.ima_hash); if (ret < 0) { audit_cause = "hashing_error"; goto out; } if (buf_hash) { memcpy(digest_hash, hash_hdr->digest, digest_hash_len); ret = ima_calc_buffer_hash(digest_hash, digest_hash_len, iint.ima_hash); if (ret < 0) { audit_cause = "hashing_error"; goto out; } event_data.buf = digest_hash; event_data.buf_len = digest_hash_len; } if (digest) memcpy(digest, iint.ima_hash->digest, digest_hash_len); if (!ima_policy_flag || (func && !(action & IMA_MEASURE))) return 1; ret = ima_alloc_init_template(&event_data, &entry, template); if (ret < 0) { audit_cause = "alloc_entry"; goto out; } ret = ima_store_template(entry, violation, NULL, event_data.buf, pcr); if (ret < 0) { audit_cause = "store_entry"; ima_free_template_entry(entry); } out: if (ret < 0) integrity_audit_message(AUDIT_INTEGRITY_PCR, NULL, eventname, func_measure_str(func), audit_cause, ret, 0, ret); return ret; } /** * ima_kexec_cmdline - measure kexec cmdline boot args * @kernel_fd: file descriptor of the kexec kernel being loaded * @buf: pointer to buffer * @size: size of buffer * * Buffers can only be measured, not appraised. */ void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) { struct fd f; if (!buf || !size) return; f = fdget(kernel_fd); if (!f.file) return; process_buffer_measurement(file_mnt_idmap(f.file), file_inode(f.file), buf, size, "kexec-cmdline", KEXEC_CMDLINE, 0, NULL, false, NULL, 0); fdput(f); } /** * ima_measure_critical_data - measure kernel integrity critical data * @event_label: unique event label for grouping and limiting critical data * @event_name: event name for the record in the IMA measurement list * @buf: pointer to buffer data * @buf_len: length of buffer data (in bytes) * @hash: measure buffer data hash * @digest: buffer digest will be written to * @digest_len: buffer length * * Measure data critical to the integrity of the kernel into the IMA log * and extend the pcr. Examples of critical data could be various data * structures, policies, and states stored in kernel memory that can * impact the integrity of the system. * * Return: 0 if the buffer has been successfully measured, 1 if the digest * has been written to the passed location but not added to a measurement entry, * a negative value otherwise. */ int ima_measure_critical_data(const char *event_label, const char *event_name, const void *buf, size_t buf_len, bool hash, u8 *digest, size_t digest_len) { if (!event_name || !event_label || !buf || !buf_len) return -ENOPARAM; return process_buffer_measurement(&nop_mnt_idmap, NULL, buf, buf_len, event_name, CRITICAL_DATA, 0, event_label, hash, digest, digest_len); } EXPORT_SYMBOL_GPL(ima_measure_critical_data); #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS /** * ima_kernel_module_request - Prevent crypto-pkcs1pad(rsa,*) requests * @kmod_name: kernel module name * * Avoid a verification loop where verifying the signature of the modprobe * binary requires executing modprobe itself. Since the modprobe iint->mutex * is already held when the signature verification is performed, a deadlock * occurs as soon as modprobe is executed within the critical region, since * the same lock cannot be taken again. * * This happens when public_key_verify_signature(), in case of RSA algorithm, * use alg_name to store internal information in order to construct an * algorithm on the fly, but crypto_larval_lookup() will try to use alg_name * in order to load a kernel module with same name. * * Since we don't have any real "crypto-pkcs1pad(rsa,*)" kernel modules, * we are safe to fail such module request from crypto_larval_lookup(), and * avoid the verification loop. * * Return: Zero if it is safe to load the kernel module, -EINVAL otherwise. */ static int ima_kernel_module_request(char *kmod_name) { if (strncmp(kmod_name, "crypto-pkcs1pad(rsa,", 20) == 0) return -EINVAL; return 0; } #endif /* CONFIG_INTEGRITY_ASYMMETRIC_KEYS */ static int __init init_ima(void) { int error; ima_appraise_parse_cmdline(); ima_init_template_list(); hash_setup(CONFIG_IMA_DEFAULT_HASH); error = ima_init(); if (error && strcmp(hash_algo_name[ima_hash_algo], CONFIG_IMA_DEFAULT_HASH) != 0) { pr_info("Allocating %s failed, going to use default hash algorithm %s\n", hash_algo_name[ima_hash_algo], CONFIG_IMA_DEFAULT_HASH); hash_setup_done = 0; hash_setup(CONFIG_IMA_DEFAULT_HASH); error = ima_init(); } if (error) return error; error = register_blocking_lsm_notifier(&ima_lsm_policy_notifier); if (error) pr_warn("Couldn't register LSM notifier, error %d\n", error); if (!error) ima_update_policy_flags(); return error; } static struct security_hook_list ima_hooks[] __ro_after_init = { LSM_HOOK_INIT(bprm_check_security, ima_bprm_check), LSM_HOOK_INIT(file_post_open, ima_file_check), LSM_HOOK_INIT(inode_post_create_tmpfile, ima_post_create_tmpfile), LSM_HOOK_INIT(file_release, ima_file_free), LSM_HOOK_INIT(mmap_file, ima_file_mmap), LSM_HOOK_INIT(file_mprotect, ima_file_mprotect), LSM_HOOK_INIT(kernel_load_data, ima_load_data), LSM_HOOK_INIT(kernel_post_load_data, ima_post_load_data), LSM_HOOK_INIT(kernel_read_file, ima_read_file), LSM_HOOK_INIT(kernel_post_read_file, ima_post_read_file), LSM_HOOK_INIT(path_post_mknod, ima_post_path_mknod), #ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS LSM_HOOK_INIT(key_post_create_or_update, ima_post_key_create_or_update), #endif #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS LSM_HOOK_INIT(kernel_module_request, ima_kernel_module_request), #endif LSM_HOOK_INIT(inode_free_security, ima_inode_free), }; static const struct lsm_id ima_lsmid = { .name = "ima", .id = LSM_ID_IMA, }; static int __init init_ima_lsm(void) { ima_iintcache_init(); security_add_hooks(ima_hooks, ARRAY_SIZE(ima_hooks), &ima_lsmid); init_ima_appraise_lsm(&ima_lsmid); return 0; } struct lsm_blob_sizes ima_blob_sizes __ro_after_init = { .lbs_inode = sizeof(struct ima_iint_cache *), }; DEFINE_LSM(ima) = { .name = "ima", .init = init_ima_lsm, .order = LSM_ORDER_LAST, .blobs = &ima_blob_sizes, }; late_initcall(init_ima); /* Start IMA after the TPM is available */ |
| 1 1 1 2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 1 2 2 2 3 2 2 3 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * vsock sock_diag(7) module * * Copyright (C) 2017 Red Hat, Inc. * Author: Stefan Hajnoczi <stefanha@redhat.com> */ #include <linux/module.h> #include <linux/sock_diag.h> #include <linux/vm_sockets_diag.h> #include <net/af_vsock.h> static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, u32 portid, u32 seq, u32 flags) { struct vsock_sock *vsk = vsock_sk(sk); struct vsock_diag_msg *rep; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep), flags); if (!nlh) return -EMSGSIZE; rep = nlmsg_data(nlh); rep->vdiag_family = AF_VSOCK; /* Lock order dictates that sk_lock is acquired before * vsock_table_lock, so we cannot lock here. Simply don't take * sk_lock; sk is guaranteed to stay alive since vsock_table_lock is * held. */ rep->vdiag_type = sk->sk_type; rep->vdiag_state = sk->sk_state; rep->vdiag_shutdown = sk->sk_shutdown; rep->vdiag_src_cid = vsk->local_addr.svm_cid; rep->vdiag_src_port = vsk->local_addr.svm_port; rep->vdiag_dst_cid = vsk->remote_addr.svm_cid; rep->vdiag_dst_port = vsk->remote_addr.svm_port; rep->vdiag_ino = sock_i_ino(sk); sock_diag_save_cookie(sk, rep->vdiag_cookie); return 0; } static int vsock_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct vsock_diag_req *req; struct vsock_sock *vsk; unsigned int bucket; unsigned int last_i; unsigned int table; struct net *net; unsigned int i; req = nlmsg_data(cb->nlh); net = sock_net(skb->sk); /* State saved between calls: */ table = cb->args[0]; bucket = cb->args[1]; i = last_i = cb->args[2]; /* TODO VMCI pending sockets? */ spin_lock_bh(&vsock_table_lock); /* Bind table (locally created sockets) */ if (table == 0) { while (bucket < ARRAY_SIZE(vsock_bind_table)) { struct list_head *head = &vsock_bind_table[bucket]; i = 0; list_for_each_entry(vsk, head, bound_table) { struct sock *sk = sk_vsock(vsk); if (!net_eq(sock_net(sk), net)) continue; if (i < last_i) goto next_bind; if (!(req->vdiag_states & (1 << sk->sk_state))) goto next_bind; if (sk_diag_fill(sk, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) goto done; next_bind: i++; } last_i = 0; bucket++; } table++; bucket = 0; } /* Connected table (accepted connections) */ while (bucket < ARRAY_SIZE(vsock_connected_table)) { struct list_head *head = &vsock_connected_table[bucket]; i = 0; list_for_each_entry(vsk, head, connected_table) { struct sock *sk = sk_vsock(vsk); /* Skip sockets we've already seen above */ if (__vsock_in_bound_table(vsk)) continue; if (!net_eq(sock_net(sk), net)) continue; if (i < last_i) goto next_connected; if (!(req->vdiag_states & (1 << sk->sk_state))) goto next_connected; if (sk_diag_fill(sk, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) goto done; next_connected: i++; } last_i = 0; bucket++; } done: spin_unlock_bh(&vsock_table_lock); cb->args[0] = table; cb->args[1] = bucket; cb->args[2] = i; return skb->len; } static int vsock_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) { int hdrlen = sizeof(struct vsock_diag_req); struct net *net = sock_net(skb->sk); if (nlmsg_len(h) < hdrlen) return -EINVAL; if (h->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = vsock_diag_dump, }; return netlink_dump_start(net->diag_nlsk, skb, h, &c); } return -EOPNOTSUPP; } static const struct sock_diag_handler vsock_diag_handler = { .owner = THIS_MODULE, .family = AF_VSOCK, .dump = vsock_diag_handler_dump, }; static int __init vsock_diag_init(void) { return sock_diag_register(&vsock_diag_handler); } static void __exit vsock_diag_exit(void) { sock_diag_unregister(&vsock_diag_handler); } module_init(vsock_diag_init); module_exit(vsock_diag_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("VMware Virtual Sockets monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 40 /* AF_VSOCK */); |
| 4 533 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VMALLOC_H #define _LINUX_VMALLOC_H #include <linux/alloc_tag.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <linux/init.h> #include <linux/list.h> #include <linux/llist.h> #include <asm/page.h> /* pgprot_t */ #include <linux/rbtree.h> #include <linux/overflow.h> #include <asm/vmalloc.h> struct vm_area_struct; /* vma defining user mapping in mm_types.h */ struct notifier_block; /* in notifier.h */ struct iov_iter; /* in uio.h */ /* bits in flags of vmalloc's vm_struct below */ #define VM_IOREMAP 0x00000001 /* ioremap() and friends */ #define VM_ALLOC 0x00000002 /* vmalloc() */ #define VM_MAP 0x00000004 /* vmap()ed pages */ #define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */ #define VM_DMA_COHERENT 0x00000010 /* dma_alloc_coherent */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ #define VM_NO_GUARD 0x00000040 /* ***DANGEROUS*** don't add guard page */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ #define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ #define VM_ALLOW_HUGE_VMAP 0x00000400 /* Allow for huge pages on archs with HAVE_ARCH_HUGE_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ !defined(CONFIG_KASAN_VMALLOC) #define VM_DEFER_KMEMLEAK 0x00000800 /* defer kmemleak object creation */ #else #define VM_DEFER_KMEMLEAK 0 #endif #define VM_SPARSE 0x00001000 /* sparse vm_area. not all pages are present. */ /* bits [20..32] reserved for arch specific ioremap internals */ /* * Maximum alignment for ioremap() regions. * Can be overridden by arch-specific value. */ #ifndef IOREMAP_MAX_ORDER #define IOREMAP_MAX_ORDER (7 + PAGE_SHIFT) /* 128 pages */ #endif struct vm_struct { struct vm_struct *next; void *addr; unsigned long size; unsigned long flags; struct page **pages; #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC unsigned int page_order; #endif unsigned int nr_pages; phys_addr_t phys_addr; const void *caller; }; struct vmap_area { unsigned long va_start; unsigned long va_end; struct rb_node rb_node; /* address sorted rbtree */ struct list_head list; /* address sorted list */ /* * The following two variables can be packed, because * a vmap_area object can be either: * 1) in "free" tree (root is free_vmap_area_root) * 2) or "busy" tree (root is vmap_area_root) */ union { unsigned long subtree_max_size; /* in "free" tree */ struct vm_struct *vm; /* in "busy" tree */ }; unsigned long flags; /* mark type of vm_map_ram area */ }; /* archs that select HAVE_ARCH_HUGE_VMAP should override one or more of these */ #ifndef arch_vmap_p4d_supported static inline bool arch_vmap_p4d_supported(pgprot_t prot) { return false; } #endif #ifndef arch_vmap_pud_supported static inline bool arch_vmap_pud_supported(pgprot_t prot) { return false; } #endif #ifndef arch_vmap_pmd_supported static inline bool arch_vmap_pmd_supported(pgprot_t prot) { return false; } #endif #ifndef arch_vmap_pte_range_map_size static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end, u64 pfn, unsigned int max_page_shift) { return PAGE_SIZE; } #endif #ifndef arch_vmap_pte_supported_shift static inline int arch_vmap_pte_supported_shift(unsigned long size) { return PAGE_SHIFT; } #endif #ifndef arch_vmap_pgprot_tagged static inline pgprot_t arch_vmap_pgprot_tagged(pgprot_t prot) { return prot; } #endif /* * Highlevel APIs for driver use */ extern void vm_unmap_ram(const void *mem, unsigned int count); extern void *vm_map_ram(struct page **pages, unsigned int count, int node); extern void vm_unmap_aliases(void); #ifdef CONFIG_MMU extern unsigned long vmalloc_nr_pages(void); #else static inline unsigned long vmalloc_nr_pages(void) { return 0; } #endif extern void *vmalloc_noprof(unsigned long size) __alloc_size(1); #define vmalloc(...) alloc_hooks(vmalloc_noprof(__VA_ARGS__)) extern void *vzalloc_noprof(unsigned long size) __alloc_size(1); #define vzalloc(...) alloc_hooks(vzalloc_noprof(__VA_ARGS__)) extern void *vmalloc_user_noprof(unsigned long size) __alloc_size(1); #define vmalloc_user(...) alloc_hooks(vmalloc_user_noprof(__VA_ARGS__)) extern void *vmalloc_node_noprof(unsigned long size, int node) __alloc_size(1); #define vmalloc_node(...) alloc_hooks(vmalloc_node_noprof(__VA_ARGS__)) extern void *vzalloc_node_noprof(unsigned long size, int node) __alloc_size(1); #define vzalloc_node(...) alloc_hooks(vzalloc_node_noprof(__VA_ARGS__)) extern void *vmalloc_32_noprof(unsigned long size) __alloc_size(1); #define vmalloc_32(...) alloc_hooks(vmalloc_32_noprof(__VA_ARGS__)) extern void *vmalloc_32_user_noprof(unsigned long size) __alloc_size(1); #define vmalloc_32_user(...) alloc_hooks(vmalloc_32_user_noprof(__VA_ARGS__)) extern void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask) __alloc_size(1); #define __vmalloc(...) alloc_hooks(__vmalloc_noprof(__VA_ARGS__)) extern void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller) __alloc_size(1); #define __vmalloc_node_range(...) alloc_hooks(__vmalloc_node_range_noprof(__VA_ARGS__)) void *__vmalloc_node_noprof(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) __alloc_size(1); #define __vmalloc_node(...) alloc_hooks(__vmalloc_node_noprof(__VA_ARGS__)) void *vmalloc_huge_noprof(unsigned long size, gfp_t gfp_mask) __alloc_size(1); #define vmalloc_huge(...) alloc_hooks(vmalloc_huge_noprof(__VA_ARGS__)) extern void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); #define __vmalloc_array(...) alloc_hooks(__vmalloc_array_noprof(__VA_ARGS__)) extern void *vmalloc_array_noprof(size_t n, size_t size) __alloc_size(1, 2); #define vmalloc_array(...) alloc_hooks(vmalloc_array_noprof(__VA_ARGS__)) extern void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); #define __vcalloc(...) alloc_hooks(__vcalloc_noprof(__VA_ARGS__)) extern void *vcalloc_noprof(size_t n, size_t size) __alloc_size(1, 2); #define vcalloc(...) alloc_hooks(vcalloc_noprof(__VA_ARGS__)) extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); extern void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot); void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot); extern void vunmap(const void *addr); extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, void *kaddr, unsigned long pgoff, unsigned long size); extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); /* * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings() * needs to be called. */ #ifndef ARCH_PAGE_TABLE_SYNC_MASK #define ARCH_PAGE_TABLE_SYNC_MASK 0 #endif /* * There is no default implementation for arch_sync_kernel_mappings(). It is * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK * is 0. */ void arch_sync_kernel_mappings(unsigned long start, unsigned long end); /* * Lowlevel-APIs (not for driver use!) */ static inline size_t get_vm_area_size(const struct vm_struct *area) { if (!(area->flags & VM_NO_GUARD)) /* return actual size without guard page */ return area->size - PAGE_SIZE; else return area->size; } extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags); extern struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller); extern struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, const void *caller); void free_vm_area(struct vm_struct *area); extern struct vm_struct *remove_vm_area(const void *addr); extern struct vm_struct *find_vm_area(const void *addr); struct vmap_area *find_vmap_area(unsigned long addr); static inline bool is_vm_area_hugepages(const void *addr) { /* * This may not 100% tell if the area is mapped with > PAGE_SIZE * page table entries, if for some reason the architecture indicates * larger sizes are available but decides not to use them, nothing * prevents that. This only indicates the size of the physical page * allocated in the vmalloc layer. */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC return find_vm_area(addr)->page_order > 0; #else return false; #endif } #ifdef CONFIG_MMU int vm_area_map_pages(struct vm_struct *area, unsigned long start, unsigned long end, struct page **pages); void vm_area_unmap_pages(struct vm_struct *area, unsigned long start, unsigned long end); void vunmap_range(unsigned long addr, unsigned long end); static inline void set_vm_flush_reset_perms(void *addr) { struct vm_struct *vm = find_vm_area(addr); if (vm) vm->flags |= VM_FLUSH_RESET_PERMS; } #else static inline void set_vm_flush_reset_perms(void *addr) { } #endif /* for /proc/kcore */ extern long vread_iter(struct iov_iter *iter, const char *addr, size_t count); /* * Internals. Don't use.. */ extern __init void vm_area_add_early(struct vm_struct *vm); extern __init void vm_area_register_early(struct vm_struct *vm, size_t align); #ifdef CONFIG_SMP # ifdef CONFIG_MMU struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align); void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms); # else static inline struct vm_struct ** pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align) { return NULL; } static inline void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) { } # endif #endif #ifdef CONFIG_MMU #define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) #else #define VMALLOC_TOTAL 0UL #endif int register_vmap_purge_notifier(struct notifier_block *nb); int unregister_vmap_purge_notifier(struct notifier_block *nb); #if defined(CONFIG_MMU) && defined(CONFIG_PRINTK) bool vmalloc_dump_obj(void *object); #else static inline bool vmalloc_dump_obj(void *object) { return false; } #endif #endif /* _LINUX_VMALLOC_H */ |
| 29 10 268 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * linux/cgroup-defs.h - basic definitions for cgroup * * This file provides basic type and interface. Include this file directly * only if necessary to avoid cyclic dependencies. */ #ifndef _LINUX_CGROUP_DEFS_H #define _LINUX_CGROUP_DEFS_H #include <linux/limits.h> #include <linux/list.h> #include <linux/idr.h> #include <linux/wait.h> #include <linux/mutex.h> #include <linux/rcupdate.h> #include <linux/refcount.h> #include <linux/percpu-refcount.h> #include <linux/percpu-rwsem.h> #include <linux/u64_stats_sync.h> #include <linux/workqueue.h> #include <linux/bpf-cgroup-defs.h> #include <linux/psi_types.h> #ifdef CONFIG_CGROUPS struct cgroup; struct cgroup_root; struct cgroup_subsys; struct cgroup_taskset; struct kernfs_node; struct kernfs_ops; struct kernfs_open_file; struct seq_file; struct poll_table_struct; #define MAX_CGROUP_TYPE_NAMELEN 32 #define MAX_CGROUP_ROOT_NAMELEN 64 #define MAX_CFTYPE_NAME 64 /* define the enumeration of all cgroup subsystems */ #define SUBSYS(_x) _x ## _cgrp_id, enum cgroup_subsys_id { #include <linux/cgroup_subsys.h> CGROUP_SUBSYS_COUNT, }; #undef SUBSYS /* bits in struct cgroup_subsys_state flags field */ enum { CSS_NO_REF = (1 << 0), /* no reference counting for this css */ CSS_ONLINE = (1 << 1), /* between ->css_online() and ->css_offline() */ CSS_RELEASED = (1 << 2), /* refcnt reached zero, released */ CSS_VISIBLE = (1 << 3), /* css is visible to userland */ CSS_DYING = (1 << 4), /* css is dying */ }; /* bits in struct cgroup flags field */ enum { /* Control Group requires release notifications to userspace */ CGRP_NOTIFY_ON_RELEASE, /* * Clone the parent's configuration when creating a new child * cpuset cgroup. For historical reasons, this option can be * specified at mount time and thus is implemented here. */ CGRP_CPUSET_CLONE_CHILDREN, /* Control group has to be frozen. */ CGRP_FREEZE, /* Cgroup is frozen. */ CGRP_FROZEN, /* Control group has to be killed. */ CGRP_KILL, }; /* cgroup_root->flags */ enum { CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ /* * Consider namespaces as delegation boundaries. If this flag is * set, controller specific interface files in a namespace root * aren't writeable from inside the namespace. */ CGRP_ROOT_NS_DELEGATE = (1 << 3), /* * Reduce latencies on dynamic cgroup modifications such as task * migrations and controller on/offs by disabling percpu operation on * cgroup_threadgroup_rwsem. This makes hot path operations such as * forks and exits into the slow path and more expensive. * * The static usage pattern of creating a cgroup, enabling controllers, * and then seeding it with CLONE_INTO_CGROUP doesn't require write * locking cgroup_threadgroup_rwsem and thus doesn't benefit from * favordynmod. */ CGRP_ROOT_FAVOR_DYNMODS = (1 << 4), /* * Enable cpuset controller in v1 cgroup to use v2 behavior. */ CGRP_ROOT_CPUSET_V2_MODE = (1 << 16), /* * Enable legacy local memory.events. */ CGRP_ROOT_MEMORY_LOCAL_EVENTS = (1 << 17), /* * Enable recursive subtree protection */ CGRP_ROOT_MEMORY_RECURSIVE_PROT = (1 << 18), /* * Enable hugetlb accounting for the memory controller. */ CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING = (1 << 19), }; /* cftype->flags */ enum { CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ CFTYPE_NS_DELEGATABLE = (1 << 2), /* writeable beyond delegation boundaries */ CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ CFTYPE_WORLD_WRITABLE = (1 << 4), /* (DON'T USE FOR NEW FILES) S_IWUGO */ CFTYPE_DEBUG = (1 << 5), /* create when cgroup_debug */ /* internal flags, do not use outside cgroup core proper */ __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ __CFTYPE_NOT_ON_DFL = (1 << 17), /* not on default hierarchy */ __CFTYPE_ADDED = (1 << 18), }; /* * cgroup_file is the handle for a file instance created in a cgroup which * is used, for example, to generate file changed notifications. This can * be obtained by setting cftype->file_offset. */ struct cgroup_file { /* do not access any fields from outside cgroup core */ struct kernfs_node *kn; unsigned long notified_at; struct timer_list notify_timer; }; /* * Per-subsystem/per-cgroup state maintained by the system. This is the * fundamental structural building block that controllers deal with. * * Fields marked with "PI:" are public and immutable and may be accessed * directly without synchronization. */ struct cgroup_subsys_state { /* PI: the cgroup that this css is attached to */ struct cgroup *cgroup; /* PI: the cgroup subsystem that this css is attached to */ struct cgroup_subsys *ss; /* reference count - access via css_[try]get() and css_put() */ struct percpu_ref refcnt; /* siblings list anchored at the parent's ->children */ struct list_head sibling; struct list_head children; /* flush target list anchored at cgrp->rstat_css_list */ struct list_head rstat_css_node; /* * PI: Subsys-unique ID. 0 is unused and root is always 1. The * matching css can be looked up using css_from_id(). */ int id; unsigned int flags; /* * Monotonically increasing unique serial number which defines a * uniform order among all csses. It's guaranteed that all * ->children lists are in the ascending order of ->serial_nr and * used to allow interrupting and resuming iterations. */ u64 serial_nr; /* * Incremented by online self and children. Used to guarantee that * parents are not offlined before their children. */ atomic_t online_cnt; /* percpu_ref killing and RCU release */ struct work_struct destroy_work; struct rcu_work destroy_rwork; /* * PI: the parent css. Placed here for cache proximity to following * fields of the containing structure. */ struct cgroup_subsys_state *parent; }; /* * A css_set is a structure holding pointers to a set of * cgroup_subsys_state objects. This saves space in the task struct * object and speeds up fork()/exit(), since a single inc/dec and a * list_add()/del() can bump the reference count on the entire cgroup * set for a task. */ struct css_set { /* * Set of subsystem states, one for each subsystem. This array is * immutable after creation apart from the init_css_set during * subsystem registration (at boot time). */ struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; /* reference count */ refcount_t refcount; /* * For a domain cgroup, the following points to self. If threaded, * to the matching cset of the nearest domain ancestor. The * dom_cset provides access to the domain cgroup and its csses to * which domain level resource consumptions should be charged. */ struct css_set *dom_cset; /* the default cgroup associated with this css_set */ struct cgroup *dfl_cgrp; /* internal task count, protected by css_set_lock */ int nr_tasks; /* * Lists running through all tasks using this cgroup group. * mg_tasks lists tasks which belong to this cset but are in the * process of being migrated out or in. Protected by * css_set_lock, but, during migration, once tasks are moved to * mg_tasks, it can be read safely while holding cgroup_mutex. */ struct list_head tasks; struct list_head mg_tasks; struct list_head dying_tasks; /* all css_task_iters currently walking this cset */ struct list_head task_iters; /* * On the default hierarchy, ->subsys[ssid] may point to a css * attached to an ancestor instead of the cgroup this css_set is * associated with. The following node is anchored at * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to * iterate through all css's attached to a given cgroup. */ struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; /* all threaded csets whose ->dom_cset points to this cset */ struct list_head threaded_csets; struct list_head threaded_csets_node; /* * List running through all cgroup groups in the same hash * slot. Protected by css_set_lock */ struct hlist_node hlist; /* * List of cgrp_cset_links pointing at cgroups referenced from this * css_set. Protected by css_set_lock. */ struct list_head cgrp_links; /* * List of csets participating in the on-going migration either as * source or destination. Protected by cgroup_mutex. */ struct list_head mg_src_preload_node; struct list_head mg_dst_preload_node; struct list_head mg_node; /* * If this cset is acting as the source of migration the following * two fields are set. mg_src_cgrp and mg_dst_cgrp are * respectively the source and destination cgroups of the on-going * migration. mg_dst_cset is the destination cset the target tasks * on this cset should be migrated to. Protected by cgroup_mutex. */ struct cgroup *mg_src_cgrp; struct cgroup *mg_dst_cgrp; struct css_set *mg_dst_cset; /* dead and being drained, ignore for migration */ bool dead; /* For RCU-protected deletion */ struct rcu_head rcu_head; }; struct cgroup_base_stat { struct task_cputime cputime; #ifdef CONFIG_SCHED_CORE u64 forceidle_sum; #endif }; /* * rstat - cgroup scalable recursive statistics. Accounting is done * per-cpu in cgroup_rstat_cpu which is then lazily propagated up the * hierarchy on reads. * * When a stat gets updated, the cgroup_rstat_cpu and its ancestors are * linked into the updated tree. On the following read, propagation only * considers and consumes the updated tree. This makes reading O(the * number of descendants which have been active since last read) instead of * O(the total number of descendants). * * This is important because there can be a lot of (draining) cgroups which * aren't active and stat may be read frequently. The combination can * become very expensive. By propagating selectively, increasing reading * frequency decreases the cost of each read. * * This struct hosts both the fields which implement the above - * updated_children and updated_next - and the fields which track basic * resource statistics on top of it - bsync, bstat and last_bstat. */ struct cgroup_rstat_cpu { /* * ->bsync protects ->bstat. These are the only fields which get * updated in the hot path. */ struct u64_stats_sync bsync; struct cgroup_base_stat bstat; /* * Snapshots at the last reading. These are used to calculate the * deltas to propagate to the global counters. */ struct cgroup_base_stat last_bstat; /* * This field is used to record the cumulative per-cpu time of * the cgroup and its descendants. Currently it can be read via * eBPF/drgn etc, and we are still trying to determine how to * expose it in the cgroupfs interface. */ struct cgroup_base_stat subtree_bstat; /* * Snapshots at the last reading. These are used to calculate the * deltas to propagate to the per-cpu subtree_bstat. */ struct cgroup_base_stat last_subtree_bstat; /* * Child cgroups with stat updates on this cpu since the last read * are linked on the parent's ->updated_children through * ->updated_next. * * In addition to being more compact, singly-linked list pointing * to the cgroup makes it unnecessary for each per-cpu struct to * point back to the associated cgroup. * * Protected by per-cpu cgroup_rstat_cpu_lock. */ struct cgroup *updated_children; /* terminated by self cgroup */ struct cgroup *updated_next; /* NULL iff not on the list */ }; struct cgroup_freezer_state { /* Should the cgroup and its descendants be frozen. */ bool freeze; /* Should the cgroup actually be frozen? */ int e_freeze; /* Fields below are protected by css_set_lock */ /* Number of frozen descendant cgroups */ int nr_frozen_descendants; /* * Number of tasks, which are counted as frozen: * frozen, SIGSTOPped, and PTRACEd. */ int nr_frozen_tasks; }; struct cgroup { /* self css with NULL ->ss, points back to this cgroup */ struct cgroup_subsys_state self; unsigned long flags; /* "unsigned long" so bitops work */ /* * The depth this cgroup is at. The root is at depth zero and each * step down the hierarchy increments the level. This along with * ancestors[] can determine whether a given cgroup is a * descendant of another without traversing the hierarchy. */ int level; /* Maximum allowed descent tree depth */ int max_depth; /* * Keep track of total numbers of visible and dying descent cgroups. * Dying cgroups are cgroups which were deleted by a user, * but are still existing because someone else is holding a reference. * max_descendants is a maximum allowed number of descent cgroups. * * nr_descendants and nr_dying_descendants are protected * by cgroup_mutex and css_set_lock. It's fine to read them holding * any of cgroup_mutex and css_set_lock; for writing both locks * should be held. */ int nr_descendants; int nr_dying_descendants; int max_descendants; /* * Each non-empty css_set associated with this cgroup contributes * one to nr_populated_csets. The counter is zero iff this cgroup * doesn't have any tasks. * * All children which have non-zero nr_populated_csets and/or * nr_populated_children of their own contribute one to either * nr_populated_domain_children or nr_populated_threaded_children * depending on their type. Each counter is zero iff all cgroups * of the type in the subtree proper don't have any tasks. */ int nr_populated_csets; int nr_populated_domain_children; int nr_populated_threaded_children; int nr_threaded_children; /* # of live threaded child cgroups */ struct kernfs_node *kn; /* cgroup kernfs entry */ struct cgroup_file procs_file; /* handle for "cgroup.procs" */ struct cgroup_file events_file; /* handle for "cgroup.events" */ /* handles for "{cpu,memory,io,irq}.pressure" */ struct cgroup_file psi_files[NR_PSI_RESOURCES]; /* * The bitmask of subsystems enabled on the child cgroups. * ->subtree_control is the one configured through * "cgroup.subtree_control" while ->subtree_ss_mask is the effective * one which may have more subsystems enabled. Controller knobs * are made available iff it's enabled in ->subtree_control. */ u16 subtree_control; u16 subtree_ss_mask; u16 old_subtree_control; u16 old_subtree_ss_mask; /* Private pointers for each registered subsystem */ struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; struct cgroup_root *root; /* * List of cgrp_cset_links pointing at css_sets with tasks in this * cgroup. Protected by css_set_lock. */ struct list_head cset_links; /* * On the default hierarchy, a css_set for a cgroup with some * susbsys disabled will point to css's which are associated with * the closest ancestor which has the subsys enabled. The * following lists all css_sets which point to this cgroup's css * for the given subsystem. */ struct list_head e_csets[CGROUP_SUBSYS_COUNT]; /* * If !threaded, self. If threaded, it points to the nearest * domain ancestor. Inside a threaded subtree, cgroups are exempt * from process granularity and no-internal-task constraint. * Domain level resource consumptions which aren't tied to a * specific task are charged to the dom_cgrp. */ struct cgroup *dom_cgrp; struct cgroup *old_dom_cgrp; /* used while enabling threaded */ /* per-cpu recursive resource statistics */ struct cgroup_rstat_cpu __percpu *rstat_cpu; struct list_head rstat_css_list; /* * Add padding to separate the read mostly rstat_cpu and * rstat_css_list into a different cacheline from the following * rstat_flush_next and *bstat fields which can have frequent updates. */ CACHELINE_PADDING(_pad_); /* * A singly-linked list of cgroup structures to be rstat flushed. * This is a scratch field to be used exclusively by * cgroup_rstat_flush_locked() and protected by cgroup_rstat_lock. */ struct cgroup *rstat_flush_next; /* cgroup basic resource statistics */ struct cgroup_base_stat last_bstat; struct cgroup_base_stat bstat; struct prev_cputime prev_cputime; /* for printing out cputime */ /* * list of pidlists, up to two for each namespace (one for procs, one * for tasks); created on demand. */ struct list_head pidlists; struct mutex pidlist_mutex; /* used to wait for offlining of csses */ wait_queue_head_t offline_waitq; /* used to schedule release agent */ struct work_struct release_agent_work; /* used to track pressure stalls */ struct psi_group *psi; /* used to store eBPF programs */ struct cgroup_bpf bpf; /* If there is block congestion on this cgroup. */ atomic_t congestion_count; /* Used to store internal freezer state */ struct cgroup_freezer_state freezer; #ifdef CONFIG_BPF_SYSCALL struct bpf_local_storage __rcu *bpf_cgrp_storage; #endif /* All ancestors including self */ struct cgroup *ancestors[]; }; /* * A cgroup_root represents the root of a cgroup hierarchy, and may be * associated with a kernfs_root to form an active hierarchy. This is * internal to cgroup core. Don't access directly from controllers. */ struct cgroup_root { struct kernfs_root *kf_root; /* The bitmask of subsystems attached to this hierarchy */ unsigned int subsys_mask; /* Unique id for this hierarchy. */ int hierarchy_id; /* A list running through the active hierarchies */ struct list_head root_list; struct rcu_head rcu; /* Must be near the top */ /* * The root cgroup. The containing cgroup_root will be destroyed on its * release. cgrp->ancestors[0] will be used overflowing into the * following field. cgrp_ancestor_storage must immediately follow. */ struct cgroup cgrp; /* must follow cgrp for cgrp->ancestors[0], see above */ struct cgroup *cgrp_ancestor_storage; /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ atomic_t nr_cgrps; /* Hierarchy-specific flags */ unsigned int flags; /* The path to use for release notifications. */ char release_agent_path[PATH_MAX]; /* The name for this hierarchy - may be empty */ char name[MAX_CGROUP_ROOT_NAMELEN]; }; /* * struct cftype: handler definitions for cgroup control files * * When reading/writing to a file: * - the cgroup to use is file->f_path.dentry->d_parent->d_fsdata * - the 'cftype' of the file is file->f_path.dentry->d_fsdata */ struct cftype { /* * By convention, the name should begin with the name of the * subsystem, followed by a period. Zero length string indicates * end of cftype array. */ char name[MAX_CFTYPE_NAME]; unsigned long private; /* * The maximum length of string, excluding trailing nul, that can * be passed to write. If < PAGE_SIZE-1, PAGE_SIZE-1 is assumed. */ size_t max_write_len; /* CFTYPE_* flags */ unsigned int flags; /* * If non-zero, should contain the offset from the start of css to * a struct cgroup_file field. cgroup will record the handle of * the created file into it. The recorded handle can be used as * long as the containing css remains accessible. */ unsigned int file_offset; /* * Fields used for internal bookkeeping. Initialized automatically * during registration. */ struct cgroup_subsys *ss; /* NULL for cgroup core files */ struct list_head node; /* anchored at ss->cfts */ struct kernfs_ops *kf_ops; int (*open)(struct kernfs_open_file *of); void (*release)(struct kernfs_open_file *of); /* * read_u64() is a shortcut for the common case of returning a * single integer. Use it in place of read() */ u64 (*read_u64)(struct cgroup_subsys_state *css, struct cftype *cft); /* * read_s64() is a signed version of read_u64() */ s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft); /* generic seq_file read interface */ int (*seq_show)(struct seq_file *sf, void *v); /* optional ops, implement all or none */ void *(*seq_start)(struct seq_file *sf, loff_t *ppos); void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos); void (*seq_stop)(struct seq_file *sf, void *v); /* * write_u64() is a shortcut for the common case of accepting * a single integer (as parsed by simple_strtoull) from * userspace. Use in place of write(); return 0 or error. */ int (*write_u64)(struct cgroup_subsys_state *css, struct cftype *cft, u64 val); /* * write_s64() is a signed version of write_u64() */ int (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft, s64 val); /* * write() is the generic write callback which maps directly to * kernfs write operation and overrides all other operations. * Maximum write size is determined by ->max_write_len. Use * of_css/cft() to access the associated css and cft. */ ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); __poll_t (*poll)(struct kernfs_open_file *of, struct poll_table_struct *pt); #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lock_class_key lockdep_key; #endif }; /* * Control Group subsystem type. * See Documentation/admin-guide/cgroup-v1/cgroups.rst for details */ struct cgroup_subsys { struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css); int (*css_online)(struct cgroup_subsys_state *css); void (*css_offline)(struct cgroup_subsys_state *css); void (*css_released)(struct cgroup_subsys_state *css); void (*css_free)(struct cgroup_subsys_state *css); void (*css_reset)(struct cgroup_subsys_state *css); void (*css_rstat_flush)(struct cgroup_subsys_state *css, int cpu); int (*css_extra_stat_show)(struct seq_file *seq, struct cgroup_subsys_state *css); int (*css_local_stat_show)(struct seq_file *seq, struct cgroup_subsys_state *css); int (*can_attach)(struct cgroup_taskset *tset); void (*cancel_attach)(struct cgroup_taskset *tset); void (*attach)(struct cgroup_taskset *tset); void (*post_attach)(void); int (*can_fork)(struct task_struct *task, struct css_set *cset); void (*cancel_fork)(struct task_struct *task, struct css_set *cset); void (*fork)(struct task_struct *task); void (*exit)(struct task_struct *task); void (*release)(struct task_struct *task); void (*bind)(struct cgroup_subsys_state *root_css); bool early_init:1; /* * If %true, the controller, on the default hierarchy, doesn't show * up in "cgroup.controllers" or "cgroup.subtree_control", is * implicitly enabled on all cgroups on the default hierarchy, and * bypasses the "no internal process" constraint. This is for * utility type controllers which is transparent to userland. * * An implicit controller can be stolen from the default hierarchy * anytime and thus must be okay with offline csses from previous * hierarchies coexisting with csses for the current one. */ bool implicit_on_dfl:1; /* * If %true, the controller, supports threaded mode on the default * hierarchy. In a threaded subtree, both process granularity and * no-internal-process constraint are ignored and a threaded * controllers should be able to handle that. * * Note that as an implicit controller is automatically enabled on * all cgroups on the default hierarchy, it should also be * threaded. implicit && !threaded is not supported. */ bool threaded:1; /* the following two fields are initialized automatically during boot */ int id; const char *name; /* optional, initialized automatically during boot if not set */ const char *legacy_name; /* link to parent, protected by cgroup_lock() */ struct cgroup_root *root; /* idr for css->id */ struct idr css_idr; /* * List of cftypes. Each entry is the first entry of an array * terminated by zero length name. */ struct list_head cfts; /* * Base cftypes which are automatically registered. The two can * point to the same array. */ struct cftype *dfl_cftypes; /* for the default hierarchy */ struct cftype *legacy_cftypes; /* for the legacy hierarchies */ /* * A subsystem may depend on other subsystems. When such subsystem * is enabled on a cgroup, the depended-upon subsystems are enabled * together if available. Subsystems enabled due to dependency are * not visible to userland until explicitly enabled. The following * specifies the mask of subsystems that this one depends on. */ unsigned int depends_on; }; extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem; /** * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups * @tsk: target task * * Allows cgroup operations to synchronize against threadgroup changes * using a percpu_rw_semaphore. */ static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) { percpu_down_read(&cgroup_threadgroup_rwsem); } /** * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups * @tsk: target task * * Counterpart of cgroup_threadcgroup_change_begin(). */ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) { percpu_up_read(&cgroup_threadgroup_rwsem); } #else /* CONFIG_CGROUPS */ #define CGROUP_SUBSYS_COUNT 0 static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) { might_sleep(); } static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} #endif /* CONFIG_CGROUPS */ #ifdef CONFIG_SOCK_CGROUP_DATA /* * sock_cgroup_data is embedded at sock->sk_cgrp_data and contains * per-socket cgroup information except for memcg association. * * On legacy hierarchies, net_prio and net_cls controllers directly * set attributes on each sock which can then be tested by the network * layer. On the default hierarchy, each sock is associated with the * cgroup it was created in and the networking layer can match the * cgroup directly. */ struct sock_cgroup_data { struct cgroup *cgroup; /* v2 */ #ifdef CONFIG_CGROUP_NET_CLASSID u32 classid; /* v1 */ #endif #ifdef CONFIG_CGROUP_NET_PRIO u16 prioidx; /* v1 */ #endif }; static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd) { #ifdef CONFIG_CGROUP_NET_PRIO return READ_ONCE(skcd->prioidx); #else return 1; #endif } static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd) { #ifdef CONFIG_CGROUP_NET_CLASSID return READ_ONCE(skcd->classid); #else return 0; #endif } static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd, u16 prioidx) { #ifdef CONFIG_CGROUP_NET_PRIO WRITE_ONCE(skcd->prioidx, prioidx); #endif } static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd, u32 classid) { #ifdef CONFIG_CGROUP_NET_CLASSID WRITE_ONCE(skcd->classid, classid); #endif } #else /* CONFIG_SOCK_CGROUP_DATA */ struct sock_cgroup_data { }; #endif /* CONFIG_SOCK_CGROUP_DATA */ #endif /* _LINUX_CGROUP_DEFS_H */ |
| 4 2 2 3 3 3 3 3 3 3 6 4 2 6 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Transparent proxy support for Linux/iptables * * Copyright (C) 2007-2008 BalaBit IT Ltd. * Author: Krisztian Kovacs */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <net/tcp.h> #include <net/udp.h> #include <net/icmp.h> #include <net/sock.h> #include <net/inet_sock.h> #include <net/netfilter/ipv4/nf_defrag_ipv4.h> #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/inet6_hashtables.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #endif #include <net/netfilter/nf_socket.h> #include <linux/netfilter/xt_socket.h> /* "socket" match based redirection (no specific rule) * =================================================== * * There are connections with dynamic endpoints (e.g. FTP data * connection) that the user is unable to add explicit rules * for. These are taken care of by a generic "socket" rule. It is * assumed that the proxy application is trusted to open such * connections without explicit iptables rule (except of course the * generic 'socket' rule). In this case the following sockets are * matched in preference order: * * - match: if there's a fully established connection matching the * _packet_ tuple * * - match: if there's a non-zero bound listener (possibly with a * non-local address) We don't accept zero-bound listeners, since * then local services could intercept traffic going through the * box. */ static bool socket_match(const struct sk_buff *skb, struct xt_action_param *par, const struct xt_socket_mtinfo1 *info) { struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; if (sk && !net_eq(xt_net(par), sock_net(sk))) sk = NULL; if (!sk) sk = nf_sk_lookup_slow_v4(xt_net(par), skb, xt_in(par)); if (sk) { bool wildcard; bool transparent = true; /* Ignore sockets listening on INADDR_ANY, * unless XT_SOCKET_NOWILDCARD is set */ wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) && sk_fullsock(sk) && inet_sk(sk)->inet_rcv_saddr == 0); /* Ignore non-transparent sockets, * if XT_SOCKET_TRANSPARENT is used */ if (info->flags & XT_SOCKET_TRANSPARENT) transparent = inet_sk_transparent(sk); if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) pskb->mark = READ_ONCE(sk->sk_mark); if (sk != skb->sk) sock_gen_put(sk); if (wildcard || !transparent) sk = NULL; } return sk != NULL; } static bool socket_mt4_v0(const struct sk_buff *skb, struct xt_action_param *par) { static struct xt_socket_mtinfo1 xt_info_v0 = { .flags = 0, }; return socket_match(skb, par, &xt_info_v0); } static bool socket_mt4_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) { return socket_match(skb, par, par->matchinfo); } #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) static bool socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; if (sk && !net_eq(xt_net(par), sock_net(sk))) sk = NULL; if (!sk) sk = nf_sk_lookup_slow_v6(xt_net(par), skb, xt_in(par)); if (sk) { bool wildcard; bool transparent = true; /* Ignore sockets listening on INADDR_ANY * unless XT_SOCKET_NOWILDCARD is set */ wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) && sk_fullsock(sk) && ipv6_addr_any(&sk->sk_v6_rcv_saddr)); /* Ignore non-transparent sockets, * if XT_SOCKET_TRANSPARENT is used */ if (info->flags & XT_SOCKET_TRANSPARENT) transparent = inet_sk_transparent(sk); if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) pskb->mark = READ_ONCE(sk->sk_mark); if (sk != skb->sk) sock_gen_put(sk); if (wildcard || !transparent) sk = NULL; } return sk != NULL; } #endif static int socket_mt_enable_defrag(struct net *net, int family) { switch (family) { case NFPROTO_IPV4: return nf_defrag_ipv4_enable(net); #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) case NFPROTO_IPV6: return nf_defrag_ipv6_enable(net); #endif } WARN_ONCE(1, "Unknown family %d\n", family); return 0; } static int socket_mt_v1_check(const struct xt_mtchk_param *par) { const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; int err; err = socket_mt_enable_defrag(par->net, par->family); if (err) return err; if (info->flags & ~XT_SOCKET_FLAGS_V1) { pr_info_ratelimited("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V1); return -EINVAL; } return 0; } static int socket_mt_v2_check(const struct xt_mtchk_param *par) { const struct xt_socket_mtinfo2 *info = (struct xt_socket_mtinfo2 *) par->matchinfo; int err; err = socket_mt_enable_defrag(par->net, par->family); if (err) return err; if (info->flags & ~XT_SOCKET_FLAGS_V2) { pr_info_ratelimited("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V2); return -EINVAL; } return 0; } static int socket_mt_v3_check(const struct xt_mtchk_param *par) { const struct xt_socket_mtinfo3 *info = (struct xt_socket_mtinfo3 *)par->matchinfo; int err; err = socket_mt_enable_defrag(par->net, par->family); if (err) return err; if (info->flags & ~XT_SOCKET_FLAGS_V3) { pr_info_ratelimited("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V3); return -EINVAL; } return 0; } static void socket_mt_destroy(const struct xt_mtdtor_param *par) { if (par->family == NFPROTO_IPV4) nf_defrag_ipv4_disable(par->net); #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) else if (par->family == NFPROTO_IPV6) nf_defrag_ipv6_disable(par->net); #endif } static struct xt_match socket_mt_reg[] __read_mostly = { { .name = "socket", .revision = 0, .family = NFPROTO_IPV4, .match = socket_mt4_v0, .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, { .name = "socket", .revision = 1, .family = NFPROTO_IPV4, .match = socket_mt4_v1_v2_v3, .destroy = socket_mt_destroy, .checkentry = socket_mt_v1_check, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "socket", .revision = 1, .family = NFPROTO_IPV6, .match = socket_mt6_v1_v2_v3, .checkentry = socket_mt_v1_check, .matchsize = sizeof(struct xt_socket_mtinfo1), .destroy = socket_mt_destroy, .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #endif { .name = "socket", .revision = 2, .family = NFPROTO_IPV4, .match = socket_mt4_v1_v2_v3, .checkentry = socket_mt_v2_check, .destroy = socket_mt_destroy, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "socket", .revision = 2, .family = NFPROTO_IPV6, .match = socket_mt6_v1_v2_v3, .checkentry = socket_mt_v2_check, .destroy = socket_mt_destroy, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #endif { .name = "socket", .revision = 3, .family = NFPROTO_IPV4, .match = socket_mt4_v1_v2_v3, .checkentry = socket_mt_v3_check, .destroy = socket_mt_destroy, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "socket", .revision = 3, .family = NFPROTO_IPV6, .match = socket_mt6_v1_v2_v3, .checkentry = socket_mt_v3_check, .destroy = socket_mt_destroy, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #endif }; static int __init socket_mt_init(void) { return xt_register_matches(socket_mt_reg, ARRAY_SIZE(socket_mt_reg)); } static void __exit socket_mt_exit(void) { xt_unregister_matches(socket_mt_reg, ARRAY_SIZE(socket_mt_reg)); } module_init(socket_mt_init); module_exit(socket_mt_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Krisztian Kovacs, Balazs Scheidler"); MODULE_DESCRIPTION("x_tables socket match module"); MODULE_ALIAS("ipt_socket"); MODULE_ALIAS("ip6t_socket"); |
| 63 64 64 64 64 2 2 2 63 64 63 5 5 5 5 70 44 43 43 42 44 78 78 46 77 78 78 2 2 2 2 2 2 60 60 60 43 43 43 60 18 4 4 4 4 4 4 18 55 55 5 5 55 1 1 1 1 1 1 1 4 1 4 4 4 4 4 46 46 46 46 46 3 63 41 23 24 18 24 24 43 5 5 45 99 64 64 64 3 3 3 3 67 67 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2003 * Copyright (c) Cisco 1999,2000 * Copyright (c) Motorola 1999,2000,2001 * Copyright (c) La Monte H.P. Yarroll 2001 * * This file is part of the SCTP kernel implementation. * * A collection class to handle the storage of transport addresses. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Jon Grimm <jgrimm@us.ibm.com> * Daisy Chang <daisyc@us.ibm.com> */ #include <linux/types.h> #include <linux/slab.h> #include <linux/in.h> #include <net/sock.h> #include <net/ipv6.h> #include <net/if_inet6.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> /* Forward declarations for internal helpers. */ static int sctp_copy_one_addr(struct net *net, struct sctp_bind_addr *dest, union sctp_addr *addr, enum sctp_scope scope, gfp_t gfp, int flags); static void sctp_bind_addr_clean(struct sctp_bind_addr *); /* First Level Abstractions. */ /* Copy 'src' to 'dest' taking 'scope' into account. Omit addresses * in 'src' which have a broader scope than 'scope'. */ int sctp_bind_addr_copy(struct net *net, struct sctp_bind_addr *dest, const struct sctp_bind_addr *src, enum sctp_scope scope, gfp_t gfp, int flags) { struct sctp_sockaddr_entry *addr; int error = 0; /* All addresses share the same port. */ dest->port = src->port; /* Extract the addresses which are relevant for this scope. */ list_for_each_entry(addr, &src->address_list, list) { error = sctp_copy_one_addr(net, dest, &addr->a, scope, gfp, flags); if (error < 0) goto out; } /* If there are no addresses matching the scope and * this is global scope, try to get a link scope address, with * the assumption that we must be sitting behind a NAT. */ if (list_empty(&dest->address_list) && (SCTP_SCOPE_GLOBAL == scope)) { list_for_each_entry(addr, &src->address_list, list) { error = sctp_copy_one_addr(net, dest, &addr->a, SCTP_SCOPE_LINK, gfp, flags); if (error < 0) goto out; } } /* If somehow no addresses were found that can be used with this * scope, it's an error. */ if (list_empty(&dest->address_list)) error = -ENETUNREACH; out: if (error) sctp_bind_addr_clean(dest); return error; } /* Exactly duplicate the address lists. This is necessary when doing * peer-offs and accepts. We don't want to put all the current system * addresses into the endpoint. That's useless. But we do want duplicat * the list of bound addresses that the older endpoint used. */ int sctp_bind_addr_dup(struct sctp_bind_addr *dest, const struct sctp_bind_addr *src, gfp_t gfp) { struct sctp_sockaddr_entry *addr; int error = 0; /* All addresses share the same port. */ dest->port = src->port; list_for_each_entry(addr, &src->address_list, list) { error = sctp_add_bind_addr(dest, &addr->a, sizeof(addr->a), 1, gfp); if (error < 0) break; } return error; } /* Initialize the SCTP_bind_addr structure for either an endpoint or * an association. */ void sctp_bind_addr_init(struct sctp_bind_addr *bp, __u16 port) { INIT_LIST_HEAD(&bp->address_list); bp->port = port; } /* Dispose of the address list. */ static void sctp_bind_addr_clean(struct sctp_bind_addr *bp) { struct sctp_sockaddr_entry *addr, *temp; /* Empty the bind address list. */ list_for_each_entry_safe(addr, temp, &bp->address_list, list) { list_del_rcu(&addr->list); kfree_rcu(addr, rcu); SCTP_DBG_OBJCNT_DEC(addr); } } /* Dispose of an SCTP_bind_addr structure */ void sctp_bind_addr_free(struct sctp_bind_addr *bp) { /* Empty the bind address list. */ sctp_bind_addr_clean(bp); } /* Add an address to the bind address list in the SCTP_bind_addr structure. */ int sctp_add_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *new, int new_size, __u8 addr_state, gfp_t gfp) { struct sctp_sockaddr_entry *addr; /* Add the address to the bind address list. */ addr = kzalloc(sizeof(*addr), gfp); if (!addr) return -ENOMEM; memcpy(&addr->a, new, min_t(size_t, sizeof(*new), new_size)); /* Fix up the port if it has not yet been set. * Both v4 and v6 have the port at the same offset. */ if (!addr->a.v4.sin_port) addr->a.v4.sin_port = htons(bp->port); addr->state = addr_state; addr->valid = 1; INIT_LIST_HEAD(&addr->list); /* We always hold a socket lock when calling this function, * and that acts as a writer synchronizing lock. */ list_add_tail_rcu(&addr->list, &bp->address_list); SCTP_DBG_OBJCNT_INC(addr); return 0; } /* Delete an address from the bind address list in the SCTP_bind_addr * structure. */ int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr) { struct sctp_sockaddr_entry *addr, *temp; int found = 0; /* We hold the socket lock when calling this function, * and that acts as a writer synchronizing lock. */ list_for_each_entry_safe(addr, temp, &bp->address_list, list) { if (sctp_cmp_addr_exact(&addr->a, del_addr)) { /* Found the exact match. */ found = 1; addr->valid = 0; list_del_rcu(&addr->list); break; } } if (found) { kfree_rcu(addr, rcu); SCTP_DBG_OBJCNT_DEC(addr); return 0; } return -EINVAL; } /* Create a network byte-order representation of all the addresses * formated as SCTP parameters. * * The second argument is the return value for the length. */ union sctp_params sctp_bind_addrs_to_raw(const struct sctp_bind_addr *bp, int *addrs_len, gfp_t gfp) { union sctp_params addrparms; union sctp_params retval; int addrparms_len; union sctp_addr_param rawaddr; int len; struct sctp_sockaddr_entry *addr; struct list_head *pos; struct sctp_af *af; addrparms_len = 0; len = 0; /* Allocate enough memory at once. */ list_for_each(pos, &bp->address_list) { len += sizeof(union sctp_addr_param); } /* Don't even bother embedding an address if there * is only one. */ if (len == sizeof(union sctp_addr_param)) { retval.v = NULL; goto end_raw; } retval.v = kmalloc(len, gfp); if (!retval.v) goto end_raw; addrparms = retval; list_for_each_entry(addr, &bp->address_list, list) { af = sctp_get_af_specific(addr->a.v4.sin_family); len = af->to_addr_param(&addr->a, &rawaddr); memcpy(addrparms.v, &rawaddr, len); addrparms.v += len; addrparms_len += len; } end_raw: *addrs_len = addrparms_len; return retval; } /* * Create an address list out of the raw address list format (IPv4 and IPv6 * address parameters). */ int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw_addr_list, int addrs_len, __u16 port, gfp_t gfp) { union sctp_addr_param *rawaddr; struct sctp_paramhdr *param; union sctp_addr addr; int retval = 0; int len; struct sctp_af *af; /* Convert the raw address to standard address format */ while (addrs_len) { param = (struct sctp_paramhdr *)raw_addr_list; rawaddr = (union sctp_addr_param *)raw_addr_list; af = sctp_get_af_specific(param_type2af(param->type)); if (unlikely(!af) || !af->from_addr_param(&addr, rawaddr, htons(port), 0)) { retval = -EINVAL; goto out_err; } if (sctp_bind_addr_state(bp, &addr) != -1) goto next; retval = sctp_add_bind_addr(bp, &addr, sizeof(addr), SCTP_ADDR_SRC, gfp); if (retval) /* Can't finish building the list, clean up. */ goto out_err; next: len = ntohs(param->length); addrs_len -= len; raw_addr_list += len; } return retval; out_err: if (retval) sctp_bind_addr_clean(bp); return retval; } /******************************************************************** * 2nd Level Abstractions ********************************************************************/ /* Does this contain a specified address? Allow wildcarding. */ int sctp_bind_addr_match(struct sctp_bind_addr *bp, const union sctp_addr *addr, struct sctp_sock *opt) { struct sctp_sockaddr_entry *laddr; int match = 0; rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { if (!laddr->valid) continue; if (opt->pf->cmp_addr(&laddr->a, addr, opt)) { match = 1; break; } } rcu_read_unlock(); return match; } int sctp_bind_addrs_check(struct sctp_sock *sp, struct sctp_sock *sp2, int cnt2) { struct sctp_bind_addr *bp2 = &sp2->ep->base.bind_addr; struct sctp_bind_addr *bp = &sp->ep->base.bind_addr; struct sctp_sockaddr_entry *laddr, *laddr2; bool exist = false; int cnt = 0; rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { list_for_each_entry_rcu(laddr2, &bp2->address_list, list) { if (sp->pf->af->cmp_addr(&laddr->a, &laddr2->a) && laddr->valid && laddr2->valid) { exist = true; goto next; } } cnt = 0; break; next: cnt++; } rcu_read_unlock(); return (cnt == cnt2) ? 0 : (exist ? -EEXIST : 1); } /* Does the address 'addr' conflict with any addresses in * the bp. */ int sctp_bind_addr_conflict(struct sctp_bind_addr *bp, const union sctp_addr *addr, struct sctp_sock *bp_sp, struct sctp_sock *addr_sp) { struct sctp_sockaddr_entry *laddr; int conflict = 0; struct sctp_sock *sp; /* Pick the IPv6 socket as the basis of comparison * since it's usually a superset of the IPv4. * If there is no IPv6 socket, then default to bind_addr. */ if (sctp_opt2sk(bp_sp)->sk_family == AF_INET6) sp = bp_sp; else if (sctp_opt2sk(addr_sp)->sk_family == AF_INET6) sp = addr_sp; else sp = bp_sp; rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { if (!laddr->valid) continue; conflict = sp->pf->cmp_addr(&laddr->a, addr, sp); if (conflict) break; } rcu_read_unlock(); return conflict; } /* Get the state of the entry in the bind_addr_list */ int sctp_bind_addr_state(const struct sctp_bind_addr *bp, const union sctp_addr *addr) { struct sctp_sockaddr_entry *laddr; struct sctp_af *af; af = sctp_get_af_specific(addr->sa.sa_family); if (unlikely(!af)) return -1; list_for_each_entry_rcu(laddr, &bp->address_list, list) { if (!laddr->valid) continue; if (af->cmp_addr(&laddr->a, addr)) return laddr->state; } return -1; } /* Find the first address in the bind address list that is not present in * the addrs packed array. */ union sctp_addr *sctp_find_unmatch_addr(struct sctp_bind_addr *bp, const union sctp_addr *addrs, int addrcnt, struct sctp_sock *opt) { struct sctp_sockaddr_entry *laddr; union sctp_addr *addr; void *addr_buf; struct sctp_af *af; int i; /* This is only called sctp_send_asconf_del_ip() and we hold * the socket lock in that code patch, so that address list * can't change. */ list_for_each_entry(laddr, &bp->address_list, list) { addr_buf = (union sctp_addr *)addrs; for (i = 0; i < addrcnt; i++) { addr = addr_buf; af = sctp_get_af_specific(addr->v4.sin_family); if (!af) break; if (opt->pf->cmp_addr(&laddr->a, addr, opt)) break; addr_buf += af->sockaddr_len; } if (i == addrcnt) return &laddr->a; } return NULL; } /* Copy out addresses from the global local address list. */ static int sctp_copy_one_addr(struct net *net, struct sctp_bind_addr *dest, union sctp_addr *addr, enum sctp_scope scope, gfp_t gfp, int flags) { int error = 0; if (sctp_is_any(NULL, addr)) { error = sctp_copy_local_addr_list(net, dest, scope, gfp, flags); } else if (sctp_in_scope(net, addr, scope)) { /* Now that the address is in scope, check to see if * the address type is supported by local sock as * well as the remote peer. */ if ((((AF_INET == addr->sa.sa_family) && (flags & SCTP_ADDR4_ALLOWED) && (flags & SCTP_ADDR4_PEERSUPP))) || (((AF_INET6 == addr->sa.sa_family) && (flags & SCTP_ADDR6_ALLOWED) && (flags & SCTP_ADDR6_PEERSUPP)))) error = sctp_add_bind_addr(dest, addr, sizeof(*addr), SCTP_ADDR_SRC, gfp); } return error; } /* Is this a wildcard address? */ int sctp_is_any(struct sock *sk, const union sctp_addr *addr) { unsigned short fam = 0; struct sctp_af *af; /* Try to get the right address family */ if (addr->sa.sa_family != AF_UNSPEC) fam = addr->sa.sa_family; else if (sk) fam = sk->sk_family; af = sctp_get_af_specific(fam); if (!af) return 0; return af->is_any(addr); } /* Is 'addr' valid for 'scope'? */ int sctp_in_scope(struct net *net, const union sctp_addr *addr, enum sctp_scope scope) { enum sctp_scope addr_scope = sctp_scope(addr); /* The unusable SCTP addresses will not be considered with * any defined scopes. */ if (SCTP_SCOPE_UNUSABLE == addr_scope) return 0; /* * For INIT and INIT-ACK address list, let L be the level of * requested destination address, sender and receiver * SHOULD include all of its addresses with level greater * than or equal to L. * * Address scoping can be selectively controlled via sysctl * option */ switch (net->sctp.scope_policy) { case SCTP_SCOPE_POLICY_DISABLE: return 1; case SCTP_SCOPE_POLICY_ENABLE: if (addr_scope <= scope) return 1; break; case SCTP_SCOPE_POLICY_PRIVATE: if (addr_scope <= scope || SCTP_SCOPE_PRIVATE == addr_scope) return 1; break; case SCTP_SCOPE_POLICY_LINK: if (addr_scope <= scope || SCTP_SCOPE_LINK == addr_scope) return 1; break; default: break; } return 0; } int sctp_is_ep_boundall(struct sock *sk) { struct sctp_bind_addr *bp; struct sctp_sockaddr_entry *addr; bp = &sctp_sk(sk)->ep->base.bind_addr; if (sctp_list_single_entry(&bp->address_list)) { addr = list_entry(bp->address_list.next, struct sctp_sockaddr_entry, list); if (sctp_is_any(sk, &addr->a)) return 1; } return 0; } /******************************************************************** * 3rd Level Abstractions ********************************************************************/ /* What is the scope of 'addr'? */ enum sctp_scope sctp_scope(const union sctp_addr *addr) { struct sctp_af *af; af = sctp_get_af_specific(addr->sa.sa_family); if (!af) return SCTP_SCOPE_UNUSABLE; return af->scope((union sctp_addr *)addr); } |
| 234 2943 3005 1 2 16 18 41 45 59 56 2999 2990 2997 3003 208 171 91 122 3 24 100 22 22 22 2 22 135 | 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 | #ifndef _LINUX_JHASH_H #define _LINUX_JHASH_H /* jhash.h: Jenkins hash support. * * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * * https://burtleburtle.net/bob/hash/ * * These are the credits from Bob's sources: * * lookup3.c, by Bob Jenkins, May 2006, Public Domain. * * These are functions for producing 32-bit hashes for hash table lookup. * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() * are externally useful functions. Routines to test the hash are included * if SELF_TEST is defined. You can use this free for any purpose. It's in * the public domain. It has no warranty. * * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@netfilter.org) * * I've modified Bob's hash to be useful in the Linux kernel, and * any bugs present are my fault. * Jozsef */ #include <linux/bitops.h> #include <linux/unaligned/packed_struct.h> /* Best hash sizes are of power of two */ #define jhash_size(n) ((u32)1<<(n)) /* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ #define jhash_mask(n) (jhash_size(n)-1) /* __jhash_mix -- mix 3 32-bit values reversibly. */ #define __jhash_mix(a, b, c) \ { \ a -= c; a ^= rol32(c, 4); c += b; \ b -= a; b ^= rol32(a, 6); a += c; \ c -= b; c ^= rol32(b, 8); b += a; \ a -= c; a ^= rol32(c, 16); c += b; \ b -= a; b ^= rol32(a, 19); a += c; \ c -= b; c ^= rol32(b, 4); b += a; \ } /* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ #define __jhash_final(a, b, c) \ { \ c ^= b; c -= rol32(b, 14); \ a ^= c; a -= rol32(c, 11); \ b ^= a; b -= rol32(a, 25); \ c ^= b; c -= rol32(b, 16); \ a ^= c; a -= rol32(c, 4); \ b ^= a; b -= rol32(a, 14); \ c ^= b; c -= rol32(b, 24); \ } /* An arbitrary initial parameter */ #define JHASH_INITVAL 0xdeadbeef /* jhash - hash an arbitrary key * @k: sequence of bytes as key * @length: the length of the key * @initval: the previous hash, or an arbitray value * * The generic version, hashes an arbitrary sequence of bytes. * No alignment or length assumptions are made about the input key. * * Returns the hash value of the key. The result depends on endianness. */ static inline u32 jhash(const void *key, u32 length, u32 initval) { u32 a, b, c; const u8 *k = key; /* Set up the internal state */ a = b = c = JHASH_INITVAL + length + initval; /* All but the last block: affect some 32 bits of (a,b,c) */ while (length > 12) { a += __get_unaligned_cpu32(k); b += __get_unaligned_cpu32(k + 4); c += __get_unaligned_cpu32(k + 8); __jhash_mix(a, b, c); length -= 12; k += 12; } /* Last block: affect all 32 bits of (c) */ switch (length) { case 12: c += (u32)k[11]<<24; fallthrough; case 11: c += (u32)k[10]<<16; fallthrough; case 10: c += (u32)k[9]<<8; fallthrough; case 9: c += k[8]; fallthrough; case 8: b += (u32)k[7]<<24; fallthrough; case 7: b += (u32)k[6]<<16; fallthrough; case 6: b += (u32)k[5]<<8; fallthrough; case 5: b += k[4]; fallthrough; case 4: a += (u32)k[3]<<24; fallthrough; case 3: a += (u32)k[2]<<16; fallthrough; case 2: a += (u32)k[1]<<8; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* jhash2 - hash an array of u32's * @k: the key which must be an array of u32's * @length: the number of u32's in the key * @initval: the previous hash, or an arbitray value * * Returns the hash value of the key. */ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) { u32 a, b, c; /* Set up the internal state */ a = b = c = JHASH_INITVAL + (length<<2) + initval; /* Handle most of the key */ while (length > 3) { a += k[0]; b += k[1]; c += k[2]; __jhash_mix(a, b, c); length -= 3; k += 3; } /* Handle the last 3 u32's */ switch (length) { case 3: c += k[2]; fallthrough; case 2: b += k[1]; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */ static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) { a += initval; b += initval; c += initval; __jhash_final(a, b, c); return c; } static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) { return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2)); } static inline u32 jhash_2words(u32 a, u32 b, u32 initval) { return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); } static inline u32 jhash_1word(u32 a, u32 initval) { return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2)); } #endif /* _LINUX_JHASH_H */ |
| 112 1 112 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HEX_H #define _LINUX_HEX_H #include <linux/types.h> extern const char hex_asc[]; #define hex_asc_lo(x) hex_asc[((x) & 0x0f)] #define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4] static inline char *hex_byte_pack(char *buf, u8 byte) { *buf++ = hex_asc_hi(byte); *buf++ = hex_asc_lo(byte); return buf; } extern const char hex_asc_upper[]; #define hex_asc_upper_lo(x) hex_asc_upper[((x) & 0x0f)] #define hex_asc_upper_hi(x) hex_asc_upper[((x) & 0xf0) >> 4] static inline char *hex_byte_pack_upper(char *buf, u8 byte) { *buf++ = hex_asc_upper_hi(byte); *buf++ = hex_asc_upper_lo(byte); return buf; } extern int hex_to_bin(unsigned char ch); extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); extern char *bin2hex(char *dst, const void *src, size_t count); bool mac_pton(const char *s, u8 *mac); #endif |
| 3 2 2 2 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 1 1 1 1 2 2 2 2 2 2 1 1 1 2 1 1 2 2 2 2 1 1 1 1 2 2 2 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 3 73 72 73 73 73 71 73 73 73 71 197 12 24 30 24 12 197 122 59 16 16 5 4 30 73 64 39 39 39 39 38 39 39 37 12 5 55 34 | 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 | /* * Copyright (c) 2015, Mellanox Technologies inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include "core_priv.h" #include <linux/in.h> #include <linux/in6.h> /* For in6_dev_get/in6_dev_put */ #include <net/addrconf.h> #include <net/bonding.h> #include <rdma/ib_cache.h> #include <rdma/ib_addr.h> static struct workqueue_struct *gid_cache_wq; enum gid_op_type { GID_DEL = 0, GID_ADD }; struct update_gid_event_work { struct work_struct work; union ib_gid gid; struct ib_gid_attr gid_attr; enum gid_op_type gid_op; }; #define ROCE_NETDEV_CALLBACK_SZ 3 struct netdev_event_work_cmd { roce_netdev_callback cb; roce_netdev_filter filter; struct net_device *ndev; struct net_device *filter_ndev; }; struct netdev_event_work { struct work_struct work; struct netdev_event_work_cmd cmds[ROCE_NETDEV_CALLBACK_SZ]; }; static const struct { bool (*is_supported)(const struct ib_device *device, u32 port_num); enum ib_gid_type gid_type; } PORT_CAP_TO_GID_TYPE[] = { {rdma_protocol_roce_eth_encap, IB_GID_TYPE_ROCE}, {rdma_protocol_roce_udp_encap, IB_GID_TYPE_ROCE_UDP_ENCAP}, }; #define CAP_TO_GID_TABLE_SIZE ARRAY_SIZE(PORT_CAP_TO_GID_TYPE) unsigned long roce_gid_type_mask_support(struct ib_device *ib_dev, u32 port) { int i; unsigned int ret_flags = 0; if (!rdma_protocol_roce(ib_dev, port)) return 1UL << IB_GID_TYPE_IB; for (i = 0; i < CAP_TO_GID_TABLE_SIZE; i++) if (PORT_CAP_TO_GID_TYPE[i].is_supported(ib_dev, port)) ret_flags |= 1UL << PORT_CAP_TO_GID_TYPE[i].gid_type; return ret_flags; } EXPORT_SYMBOL(roce_gid_type_mask_support); static void update_gid(enum gid_op_type gid_op, struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *gid_attr) { int i; unsigned long gid_type_mask = roce_gid_type_mask_support(ib_dev, port); for (i = 0; i < IB_GID_TYPE_SIZE; i++) { if ((1UL << i) & gid_type_mask) { gid_attr->gid_type = i; switch (gid_op) { case GID_ADD: ib_cache_gid_add(ib_dev, port, gid, gid_attr); break; case GID_DEL: ib_cache_gid_del(ib_dev, port, gid, gid_attr); break; } } } } enum bonding_slave_state { BONDING_SLAVE_STATE_ACTIVE = 1UL << 0, BONDING_SLAVE_STATE_INACTIVE = 1UL << 1, /* No primary slave or the device isn't a slave in bonding */ BONDING_SLAVE_STATE_NA = 1UL << 2, }; static enum bonding_slave_state is_eth_active_slave_of_bonding_rcu(struct net_device *dev, struct net_device *upper) { if (upper && netif_is_bond_master(upper)) { struct net_device *pdev = bond_option_active_slave_get_rcu(netdev_priv(upper)); if (pdev) return dev == pdev ? BONDING_SLAVE_STATE_ACTIVE : BONDING_SLAVE_STATE_INACTIVE; } return BONDING_SLAVE_STATE_NA; } #define REQUIRED_BOND_STATES (BONDING_SLAVE_STATE_ACTIVE | \ BONDING_SLAVE_STATE_NA) static bool is_eth_port_of_netdev_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *real_dev; bool res; if (!rdma_ndev) return false; rcu_read_lock(); real_dev = rdma_vlan_dev_real_dev(cookie); if (!real_dev) real_dev = cookie; res = ((rdma_is_upper_dev_rcu(rdma_ndev, cookie) && (is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev) & REQUIRED_BOND_STATES)) || real_dev == rdma_ndev); rcu_read_unlock(); return res; } static bool is_eth_port_inactive_slave_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *master_dev; bool res; if (!rdma_ndev) return false; rcu_read_lock(); master_dev = netdev_master_upper_dev_get_rcu(rdma_ndev); res = is_eth_active_slave_of_bonding_rcu(rdma_ndev, master_dev) == BONDING_SLAVE_STATE_INACTIVE; rcu_read_unlock(); return res; } /** * is_ndev_for_default_gid_filter - Check if a given netdevice * can be considered for default GIDs or not. * @ib_dev: IB device to check * @port: Port to consider for adding default GID * @rdma_ndev: rdma netdevice pointer * @cookie: Netdevice to consider to form a default GID * * is_ndev_for_default_gid_filter() returns true if a given netdevice can be * considered for deriving default RoCE GID, returns false otherwise. */ static bool is_ndev_for_default_gid_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *cookie_ndev = cookie; bool res; if (!rdma_ndev) return false; rcu_read_lock(); /* * When rdma netdevice is used in bonding, bonding master netdevice * should be considered for default GIDs. Therefore, ignore slave rdma * netdevices when bonding is considered. * Additionally when event(cookie) netdevice is bond master device, * make sure that it the upper netdevice of rdma netdevice. */ res = ((cookie_ndev == rdma_ndev && !netif_is_bond_slave(rdma_ndev)) || (netif_is_bond_master(cookie_ndev) && rdma_is_upper_dev_rcu(rdma_ndev, cookie_ndev))); rcu_read_unlock(); return res; } static bool pass_all_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { return true; } static bool upper_device_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { bool res; if (!rdma_ndev) return false; if (rdma_ndev == cookie) return true; rcu_read_lock(); res = rdma_is_upper_dev_rcu(rdma_ndev, cookie); rcu_read_unlock(); return res; } /** * is_upper_ndev_bond_master_filter - Check if a given netdevice * is bond master device of netdevice of the RDMA device of port. * @ib_dev: IB device to check * @port: Port to consider for adding default GID * @rdma_ndev: Pointer to rdma netdevice * @cookie: Netdevice to consider to form a default GID * * is_upper_ndev_bond_master_filter() returns true if a cookie_netdev * is bond master device and rdma_ndev is its lower netdevice. It might * not have been established as slave device yet. */ static bool is_upper_ndev_bond_master_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *cookie_ndev = cookie; bool match = false; if (!rdma_ndev) return false; rcu_read_lock(); if (netif_is_bond_master(cookie_ndev) && rdma_is_upper_dev_rcu(rdma_ndev, cookie_ndev)) match = true; rcu_read_unlock(); return match; } static void update_gid_ip(enum gid_op_type gid_op, struct ib_device *ib_dev, u32 port, struct net_device *ndev, struct sockaddr *addr) { union ib_gid gid; struct ib_gid_attr gid_attr; rdma_ip2gid(addr, &gid); memset(&gid_attr, 0, sizeof(gid_attr)); gid_attr.ndev = ndev; update_gid(gid_op, ib_dev, port, &gid, &gid_attr); } static void bond_delete_netdev_default_gids(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, struct net_device *event_ndev) { struct net_device *real_dev = rdma_vlan_dev_real_dev(event_ndev); unsigned long gid_type_mask; if (!rdma_ndev) return; if (!real_dev) real_dev = event_ndev; rcu_read_lock(); if (((rdma_ndev != event_ndev && !rdma_is_upper_dev_rcu(rdma_ndev, event_ndev)) || is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev) == BONDING_SLAVE_STATE_INACTIVE)) { rcu_read_unlock(); return; } rcu_read_unlock(); gid_type_mask = roce_gid_type_mask_support(ib_dev, port); ib_cache_gid_set_default_gid(ib_dev, port, rdma_ndev, gid_type_mask, IB_CACHE_GID_DEFAULT_MODE_DELETE); } static void enum_netdev_ipv4_ips(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { const struct in_ifaddr *ifa; struct in_device *in_dev; struct sin_list { struct list_head list; struct sockaddr_in ip; }; struct sin_list *sin_iter; struct sin_list *sin_temp; LIST_HEAD(sin_list); if (ndev->reg_state >= NETREG_UNREGISTERING) return; rcu_read_lock(); in_dev = __in_dev_get_rcu(ndev); if (!in_dev) { rcu_read_unlock(); return; } in_dev_for_each_ifa_rcu(ifa, in_dev) { struct sin_list *entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) continue; entry->ip.sin_family = AF_INET; entry->ip.sin_addr.s_addr = ifa->ifa_address; list_add_tail(&entry->list, &sin_list); } rcu_read_unlock(); list_for_each_entry_safe(sin_iter, sin_temp, &sin_list, list) { update_gid_ip(GID_ADD, ib_dev, port, ndev, (struct sockaddr *)&sin_iter->ip); list_del(&sin_iter->list); kfree(sin_iter); } } static void enum_netdev_ipv6_ips(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { struct inet6_ifaddr *ifp; struct inet6_dev *in6_dev; struct sin6_list { struct list_head list; struct sockaddr_in6 sin6; }; struct sin6_list *sin6_iter; struct sin6_list *sin6_temp; struct ib_gid_attr gid_attr = {.ndev = ndev}; LIST_HEAD(sin6_list); if (ndev->reg_state >= NETREG_UNREGISTERING) return; in6_dev = in6_dev_get(ndev); if (!in6_dev) return; read_lock_bh(&in6_dev->lock); list_for_each_entry(ifp, &in6_dev->addr_list, if_list) { struct sin6_list *entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) continue; entry->sin6.sin6_family = AF_INET6; entry->sin6.sin6_addr = ifp->addr; list_add_tail(&entry->list, &sin6_list); } read_unlock_bh(&in6_dev->lock); in6_dev_put(in6_dev); list_for_each_entry_safe(sin6_iter, sin6_temp, &sin6_list, list) { union ib_gid gid; rdma_ip2gid((struct sockaddr *)&sin6_iter->sin6, &gid); update_gid(GID_ADD, ib_dev, port, &gid, &gid_attr); list_del(&sin6_iter->list); kfree(sin6_iter); } } static void _add_netdev_ips(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { enum_netdev_ipv4_ips(ib_dev, port, ndev); if (IS_ENABLED(CONFIG_IPV6)) enum_netdev_ipv6_ips(ib_dev, port, ndev); } static void add_netdev_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { _add_netdev_ips(ib_dev, port, cookie); } static void del_netdev_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { ib_cache_gid_del_all_netdev_gids(ib_dev, port, cookie); } /** * del_default_gids - Delete default GIDs of the event/cookie netdevice * @ib_dev: RDMA device pointer * @port: Port of the RDMA device whose GID table to consider * @rdma_ndev: Unused rdma netdevice * @cookie: Pointer to event netdevice * * del_default_gids() deletes the default GIDs of the event/cookie netdevice. */ static void del_default_gids(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *cookie_ndev = cookie; unsigned long gid_type_mask; gid_type_mask = roce_gid_type_mask_support(ib_dev, port); ib_cache_gid_set_default_gid(ib_dev, port, cookie_ndev, gid_type_mask, IB_CACHE_GID_DEFAULT_MODE_DELETE); } static void add_default_gids(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *event_ndev = cookie; unsigned long gid_type_mask; gid_type_mask = roce_gid_type_mask_support(ib_dev, port); ib_cache_gid_set_default_gid(ib_dev, port, event_ndev, gid_type_mask, IB_CACHE_GID_DEFAULT_MODE_SET); } static void enum_all_gids_of_dev_cb(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net *net; struct net_device *ndev; /* Lock the rtnl to make sure the netdevs does not move under * our feet */ rtnl_lock(); down_read(&net_rwsem); for_each_net(net) for_each_netdev(net, ndev) { /* * Filter and add default GIDs of the primary netdevice * when not in bonding mode, or add default GIDs * of bond master device, when in bonding mode. */ if (is_ndev_for_default_gid_filter(ib_dev, port, rdma_ndev, ndev)) add_default_gids(ib_dev, port, rdma_ndev, ndev); if (is_eth_port_of_netdev_filter(ib_dev, port, rdma_ndev, ndev)) _add_netdev_ips(ib_dev, port, ndev); } up_read(&net_rwsem); rtnl_unlock(); } /** * rdma_roce_rescan_device - Rescan all of the network devices in the system * and add their gids, as needed, to the relevant RoCE devices. * * @ib_dev: the rdma device */ void rdma_roce_rescan_device(struct ib_device *ib_dev) { ib_enum_roce_netdev(ib_dev, pass_all_filter, NULL, enum_all_gids_of_dev_cb, NULL); } EXPORT_SYMBOL(rdma_roce_rescan_device); static void callback_for_addr_gid_device_scan(struct ib_device *device, u32 port, struct net_device *rdma_ndev, void *cookie) { struct update_gid_event_work *parsed = cookie; return update_gid(parsed->gid_op, device, port, &parsed->gid, &parsed->gid_attr); } struct upper_list { struct list_head list; struct net_device *upper; }; static int netdev_upper_walk(struct net_device *upper, struct netdev_nested_priv *priv) { struct upper_list *entry = kmalloc(sizeof(*entry), GFP_ATOMIC); struct list_head *upper_list = (struct list_head *)priv->data; if (!entry) return 0; list_add_tail(&entry->list, upper_list); dev_hold(upper); entry->upper = upper; return 0; } static void handle_netdev_upper(struct ib_device *ib_dev, u32 port, void *cookie, void (*handle_netdev)(struct ib_device *ib_dev, u32 port, struct net_device *ndev)) { struct net_device *ndev = cookie; struct netdev_nested_priv priv; struct upper_list *upper_iter; struct upper_list *upper_temp; LIST_HEAD(upper_list); priv.data = &upper_list; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(ndev, netdev_upper_walk, &priv); rcu_read_unlock(); handle_netdev(ib_dev, port, ndev); list_for_each_entry_safe(upper_iter, upper_temp, &upper_list, list) { handle_netdev(ib_dev, port, upper_iter->upper); dev_put(upper_iter->upper); list_del(&upper_iter->list); kfree(upper_iter); } } static void _roce_del_all_netdev_gids(struct ib_device *ib_dev, u32 port, struct net_device *event_ndev) { ib_cache_gid_del_all_netdev_gids(ib_dev, port, event_ndev); } static void del_netdev_upper_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { handle_netdev_upper(ib_dev, port, cookie, _roce_del_all_netdev_gids); } static void add_netdev_upper_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { handle_netdev_upper(ib_dev, port, cookie, _add_netdev_ips); } static void del_netdev_default_ips_join(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *master_ndev; rcu_read_lock(); master_ndev = netdev_master_upper_dev_get_rcu(rdma_ndev); dev_hold(master_ndev); rcu_read_unlock(); if (master_ndev) { bond_delete_netdev_default_gids(ib_dev, port, rdma_ndev, master_ndev); dev_put(master_ndev); } } /* The following functions operate on all IB devices. netdevice_event and * addr_event execute ib_enum_all_roce_netdevs through a work. * ib_enum_all_roce_netdevs iterates through all IB devices. */ static void netdevice_event_work_handler(struct work_struct *_work) { struct netdev_event_work *work = container_of(_work, struct netdev_event_work, work); unsigned int i; for (i = 0; i < ARRAY_SIZE(work->cmds) && work->cmds[i].cb; i++) { ib_enum_all_roce_netdevs(work->cmds[i].filter, work->cmds[i].filter_ndev, work->cmds[i].cb, work->cmds[i].ndev); dev_put(work->cmds[i].ndev); dev_put(work->cmds[i].filter_ndev); } kfree(work); } static int netdevice_queue_work(struct netdev_event_work_cmd *cmds, struct net_device *ndev) { unsigned int i; struct netdev_event_work *ndev_work = kmalloc(sizeof(*ndev_work), GFP_KERNEL); if (!ndev_work) return NOTIFY_DONE; memcpy(ndev_work->cmds, cmds, sizeof(ndev_work->cmds)); for (i = 0; i < ARRAY_SIZE(ndev_work->cmds) && ndev_work->cmds[i].cb; i++) { if (!ndev_work->cmds[i].ndev) ndev_work->cmds[i].ndev = ndev; if (!ndev_work->cmds[i].filter_ndev) ndev_work->cmds[i].filter_ndev = ndev; dev_hold(ndev_work->cmds[i].ndev); dev_hold(ndev_work->cmds[i].filter_ndev); } INIT_WORK(&ndev_work->work, netdevice_event_work_handler); queue_work(gid_cache_wq, &ndev_work->work); return NOTIFY_DONE; } static const struct netdev_event_work_cmd add_cmd = { .cb = add_netdev_ips, .filter = is_eth_port_of_netdev_filter }; static const struct netdev_event_work_cmd add_cmd_upper_ips = { .cb = add_netdev_upper_ips, .filter = is_eth_port_of_netdev_filter }; static void ndev_event_unlink(struct netdev_notifier_changeupper_info *changeupper_info, struct netdev_event_work_cmd *cmds) { static const struct netdev_event_work_cmd upper_ips_del_cmd = { .cb = del_netdev_upper_ips, .filter = upper_device_filter }; cmds[0] = upper_ips_del_cmd; cmds[0].ndev = changeupper_info->upper_dev; cmds[1] = add_cmd; } static const struct netdev_event_work_cmd bonding_default_add_cmd = { .cb = add_default_gids, .filter = is_upper_ndev_bond_master_filter }; static void ndev_event_link(struct net_device *event_ndev, struct netdev_notifier_changeupper_info *changeupper_info, struct netdev_event_work_cmd *cmds) { static const struct netdev_event_work_cmd bonding_default_del_cmd = { .cb = del_default_gids, .filter = is_upper_ndev_bond_master_filter }; /* * When a lower netdev is linked to its upper bonding * netdev, delete lower slave netdev's default GIDs. */ cmds[0] = bonding_default_del_cmd; cmds[0].ndev = event_ndev; cmds[0].filter_ndev = changeupper_info->upper_dev; /* Now add bonding upper device default GIDs */ cmds[1] = bonding_default_add_cmd; cmds[1].ndev = changeupper_info->upper_dev; cmds[1].filter_ndev = changeupper_info->upper_dev; /* Now add bonding upper device IP based GIDs */ cmds[2] = add_cmd_upper_ips; cmds[2].ndev = changeupper_info->upper_dev; cmds[2].filter_ndev = changeupper_info->upper_dev; } static void netdevice_event_changeupper(struct net_device *event_ndev, struct netdev_notifier_changeupper_info *changeupper_info, struct netdev_event_work_cmd *cmds) { if (changeupper_info->linking) ndev_event_link(event_ndev, changeupper_info, cmds); else ndev_event_unlink(changeupper_info, cmds); } static const struct netdev_event_work_cmd add_default_gid_cmd = { .cb = add_default_gids, .filter = is_ndev_for_default_gid_filter, }; static int netdevice_event(struct notifier_block *this, unsigned long event, void *ptr) { static const struct netdev_event_work_cmd del_cmd = { .cb = del_netdev_ips, .filter = pass_all_filter}; static const struct netdev_event_work_cmd bonding_default_del_cmd_join = { .cb = del_netdev_default_ips_join, .filter = is_eth_port_inactive_slave_filter }; static const struct netdev_event_work_cmd netdev_del_cmd = { .cb = del_netdev_ips, .filter = is_eth_port_of_netdev_filter }; static const struct netdev_event_work_cmd bonding_event_ips_del_cmd = { .cb = del_netdev_upper_ips, .filter = upper_device_filter}; struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct netdev_event_work_cmd cmds[ROCE_NETDEV_CALLBACK_SZ] = { {NULL} }; if (ndev->type != ARPHRD_ETHER) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: case NETDEV_UP: cmds[0] = bonding_default_del_cmd_join; cmds[1] = add_default_gid_cmd; cmds[2] = add_cmd; break; case NETDEV_UNREGISTER: if (ndev->reg_state < NETREG_UNREGISTERED) cmds[0] = del_cmd; else return NOTIFY_DONE; break; case NETDEV_CHANGEADDR: cmds[0] = netdev_del_cmd; if (ndev->reg_state == NETREG_REGISTERED) { cmds[1] = add_default_gid_cmd; cmds[2] = add_cmd; } break; case NETDEV_CHANGEUPPER: netdevice_event_changeupper(ndev, container_of(ptr, struct netdev_notifier_changeupper_info, info), cmds); break; case NETDEV_BONDING_FAILOVER: cmds[0] = bonding_event_ips_del_cmd; /* Add default GIDs of the bond device */ cmds[1] = bonding_default_add_cmd; /* Add IP based GIDs of the bond device */ cmds[2] = add_cmd_upper_ips; break; default: return NOTIFY_DONE; } return netdevice_queue_work(cmds, ndev); } static void update_gid_event_work_handler(struct work_struct *_work) { struct update_gid_event_work *work = container_of(_work, struct update_gid_event_work, work); ib_enum_all_roce_netdevs(is_eth_port_of_netdev_filter, work->gid_attr.ndev, callback_for_addr_gid_device_scan, work); dev_put(work->gid_attr.ndev); kfree(work); } static int addr_event(struct notifier_block *this, unsigned long event, struct sockaddr *sa, struct net_device *ndev) { struct update_gid_event_work *work; enum gid_op_type gid_op; if (ndev->type != ARPHRD_ETHER) return NOTIFY_DONE; switch (event) { case NETDEV_UP: gid_op = GID_ADD; break; case NETDEV_DOWN: gid_op = GID_DEL; break; default: return NOTIFY_DONE; } work = kmalloc(sizeof(*work), GFP_ATOMIC); if (!work) return NOTIFY_DONE; INIT_WORK(&work->work, update_gid_event_work_handler); rdma_ip2gid(sa, &work->gid); work->gid_op = gid_op; memset(&work->gid_attr, 0, sizeof(work->gid_attr)); dev_hold(ndev); work->gid_attr.ndev = ndev; queue_work(gid_cache_wq, &work->work); return NOTIFY_DONE; } static int inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct sockaddr_in in; struct net_device *ndev; struct in_ifaddr *ifa = ptr; in.sin_family = AF_INET; in.sin_addr.s_addr = ifa->ifa_address; ndev = ifa->ifa_dev->dev; return addr_event(this, event, (struct sockaddr *)&in, ndev); } static int inet6addr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct sockaddr_in6 in6; struct net_device *ndev; struct inet6_ifaddr *ifa6 = ptr; in6.sin6_family = AF_INET6; in6.sin6_addr = ifa6->addr; ndev = ifa6->idev->dev; return addr_event(this, event, (struct sockaddr *)&in6, ndev); } static struct notifier_block nb_netdevice = { .notifier_call = netdevice_event }; static struct notifier_block nb_inetaddr = { .notifier_call = inetaddr_event }; static struct notifier_block nb_inet6addr = { .notifier_call = inet6addr_event }; int __init roce_gid_mgmt_init(void) { gid_cache_wq = alloc_ordered_workqueue("gid-cache-wq", 0); if (!gid_cache_wq) return -ENOMEM; register_inetaddr_notifier(&nb_inetaddr); if (IS_ENABLED(CONFIG_IPV6)) register_inet6addr_notifier(&nb_inet6addr); /* We relay on the netdevice notifier to enumerate all * existing devices in the system. Register to this notifier * last to make sure we will not miss any IP add/del * callbacks. */ register_netdevice_notifier(&nb_netdevice); return 0; } void __exit roce_gid_mgmt_cleanup(void) { if (IS_ENABLED(CONFIG_IPV6)) unregister_inet6addr_notifier(&nb_inet6addr); unregister_inetaddr_notifier(&nb_inetaddr); unregister_netdevice_notifier(&nb_netdevice); /* Ensure all gid deletion tasks complete before we go down, * to avoid any reference to free'd memory. By the time * ib-core is removed, all physical devices have been removed, * so no issue with remaining hardware contexts. */ destroy_workqueue(gid_cache_wq); } |
| 70 70 69 1 1 1 259 257 240 261 258 256 261 259 260 260 259 74 72 3 69 70 256 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * umh - the kernel usermode helper */ #include <linux/module.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/binfmts.h> #include <linux/syscalls.h> #include <linux/unistd.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/completion.h> #include <linux/cred.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/fs_struct.h> #include <linux/workqueue.h> #include <linux/security.h> #include <linux/mount.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/resource.h> #include <linux/notifier.h> #include <linux/suspend.h> #include <linux/rwsem.h> #include <linux/ptrace.h> #include <linux/async.h> #include <linux/uaccess.h> #include <linux/initrd.h> #include <linux/freezer.h> #include <trace/events/module.h> static kernel_cap_t usermodehelper_bset = CAP_FULL_SET; static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET; static DEFINE_SPINLOCK(umh_sysctl_lock); static DECLARE_RWSEM(umhelper_sem); static void call_usermodehelper_freeinfo(struct subprocess_info *info) { if (info->cleanup) (*info->cleanup)(info); kfree(info); } static void umh_complete(struct subprocess_info *sub_info) { struct completion *comp = xchg(&sub_info->complete, NULL); /* * See call_usermodehelper_exec(). If xchg() returns NULL * we own sub_info, the UMH_KILLABLE caller has gone away * or the caller used UMH_NO_WAIT. */ if (comp) complete(comp); else call_usermodehelper_freeinfo(sub_info); } /* * This is the task which runs the usermode application */ static int call_usermodehelper_exec_async(void *data) { struct subprocess_info *sub_info = data; struct cred *new; int retval; spin_lock_irq(¤t->sighand->siglock); flush_signal_handlers(current, 1); spin_unlock_irq(¤t->sighand->siglock); /* * Initial kernel threads share ther FS with init, in order to * get the init root directory. But we've now created a new * thread that is going to execve a user process and has its own * 'struct fs_struct'. Reset umask to the default. */ current->fs->umask = 0022; /* * Our parent (unbound workqueue) runs with elevated scheduling * priority. Avoid propagating that into the userspace child. */ set_user_nice(current, 0); retval = -ENOMEM; new = prepare_kernel_cred(current); if (!new) goto out; spin_lock(&umh_sysctl_lock); new->cap_bset = cap_intersect(usermodehelper_bset, new->cap_bset); new->cap_inheritable = cap_intersect(usermodehelper_inheritable, new->cap_inheritable); spin_unlock(&umh_sysctl_lock); if (sub_info->init) { retval = sub_info->init(sub_info, new); if (retval) { abort_creds(new); goto out; } } commit_creds(new); wait_for_initramfs(); retval = kernel_execve(sub_info->path, (const char *const *)sub_info->argv, (const char *const *)sub_info->envp); out: sub_info->retval = retval; /* * call_usermodehelper_exec_sync() will call umh_complete * if UHM_WAIT_PROC. */ if (!(sub_info->wait & UMH_WAIT_PROC)) umh_complete(sub_info); if (!retval) return 0; do_exit(0); } /* Handles UMH_WAIT_PROC. */ static void call_usermodehelper_exec_sync(struct subprocess_info *sub_info) { pid_t pid; /* If SIGCLD is ignored do_wait won't populate the status. */ kernel_sigaction(SIGCHLD, SIG_DFL); pid = user_mode_thread(call_usermodehelper_exec_async, sub_info, SIGCHLD); if (pid < 0) sub_info->retval = pid; else kernel_wait(pid, &sub_info->retval); /* Restore default kernel sig handler */ kernel_sigaction(SIGCHLD, SIG_IGN); umh_complete(sub_info); } /* * We need to create the usermodehelper kernel thread from a task that is affine * to an optimized set of CPUs (or nohz housekeeping ones) such that they * inherit a widest affinity irrespective of call_usermodehelper() callers with * possibly reduced affinity (eg: per-cpu workqueues). We don't want * usermodehelper targets to contend a busy CPU. * * Unbound workqueues provide such wide affinity and allow to block on * UMH_WAIT_PROC requests without blocking pending request (up to some limit). * * Besides, workqueues provide the privilege level that caller might not have * to perform the usermodehelper request. * */ static void call_usermodehelper_exec_work(struct work_struct *work) { struct subprocess_info *sub_info = container_of(work, struct subprocess_info, work); if (sub_info->wait & UMH_WAIT_PROC) { call_usermodehelper_exec_sync(sub_info); } else { pid_t pid; /* * Use CLONE_PARENT to reparent it to kthreadd; we do not * want to pollute current->children, and we need a parent * that always ignores SIGCHLD to ensure auto-reaping. */ pid = user_mode_thread(call_usermodehelper_exec_async, sub_info, CLONE_PARENT | SIGCHLD); if (pid < 0) { sub_info->retval = pid; umh_complete(sub_info); } } } /* * If set, call_usermodehelper_exec() will exit immediately returning -EBUSY * (used for preventing user land processes from being created after the user * land has been frozen during a system-wide hibernation or suspend operation). * Should always be manipulated under umhelper_sem acquired for write. */ static enum umh_disable_depth usermodehelper_disabled = UMH_DISABLED; /* Number of helpers running */ static atomic_t running_helpers = ATOMIC_INIT(0); /* * Wait queue head used by usermodehelper_disable() to wait for all running * helpers to finish. */ static DECLARE_WAIT_QUEUE_HEAD(running_helpers_waitq); /* * Used by usermodehelper_read_lock_wait() to wait for usermodehelper_disabled * to become 'false'. */ static DECLARE_WAIT_QUEUE_HEAD(usermodehelper_disabled_waitq); /* * Time to wait for running_helpers to become zero before the setting of * usermodehelper_disabled in usermodehelper_disable() fails */ #define RUNNING_HELPERS_TIMEOUT (5 * HZ) int usermodehelper_read_trylock(void) { DEFINE_WAIT(wait); int ret = 0; down_read(&umhelper_sem); for (;;) { prepare_to_wait(&usermodehelper_disabled_waitq, &wait, TASK_INTERRUPTIBLE); if (!usermodehelper_disabled) break; if (usermodehelper_disabled == UMH_DISABLED) ret = -EAGAIN; up_read(&umhelper_sem); if (ret) break; schedule(); try_to_freeze(); down_read(&umhelper_sem); } finish_wait(&usermodehelper_disabled_waitq, &wait); return ret; } EXPORT_SYMBOL_GPL(usermodehelper_read_trylock); long usermodehelper_read_lock_wait(long timeout) { DEFINE_WAIT(wait); if (timeout < 0) return -EINVAL; down_read(&umhelper_sem); for (;;) { prepare_to_wait(&usermodehelper_disabled_waitq, &wait, TASK_UNINTERRUPTIBLE); if (!usermodehelper_disabled) break; up_read(&umhelper_sem); timeout = schedule_timeout(timeout); if (!timeout) break; down_read(&umhelper_sem); } finish_wait(&usermodehelper_disabled_waitq, &wait); return timeout; } EXPORT_SYMBOL_GPL(usermodehelper_read_lock_wait); void usermodehelper_read_unlock(void) { up_read(&umhelper_sem); } EXPORT_SYMBOL_GPL(usermodehelper_read_unlock); /** * __usermodehelper_set_disable_depth - Modify usermodehelper_disabled. * @depth: New value to assign to usermodehelper_disabled. * * Change the value of usermodehelper_disabled (under umhelper_sem locked for * writing) and wakeup tasks waiting for it to change. */ void __usermodehelper_set_disable_depth(enum umh_disable_depth depth) { down_write(&umhelper_sem); usermodehelper_disabled = depth; wake_up(&usermodehelper_disabled_waitq); up_write(&umhelper_sem); } /** * __usermodehelper_disable - Prevent new helpers from being started. * @depth: New value to assign to usermodehelper_disabled. * * Set usermodehelper_disabled to @depth and wait for running helpers to exit. */ int __usermodehelper_disable(enum umh_disable_depth depth) { long retval; if (!depth) return -EINVAL; down_write(&umhelper_sem); usermodehelper_disabled = depth; up_write(&umhelper_sem); /* * From now on call_usermodehelper_exec() won't start any new * helpers, so it is sufficient if running_helpers turns out to * be zero at one point (it may be increased later, but that * doesn't matter). */ retval = wait_event_timeout(running_helpers_waitq, atomic_read(&running_helpers) == 0, RUNNING_HELPERS_TIMEOUT); if (retval) return 0; __usermodehelper_set_disable_depth(UMH_ENABLED); return -EAGAIN; } static void helper_lock(void) { atomic_inc(&running_helpers); smp_mb__after_atomic(); } static void helper_unlock(void) { if (atomic_dec_and_test(&running_helpers)) wake_up(&running_helpers_waitq); } /** * call_usermodehelper_setup - prepare to call a usermode helper * @path: path to usermode executable * @argv: arg vector for process * @envp: environment for process * @gfp_mask: gfp mask for memory allocation * @init: an init function * @cleanup: a cleanup function * @data: arbitrary context sensitive data * * Returns either %NULL on allocation failure, or a subprocess_info * structure. This should be passed to call_usermodehelper_exec to * exec the process and free the structure. * * The init function is used to customize the helper process prior to * exec. A non-zero return code causes the process to error out, exit, * and return the failure to the calling process * * The cleanup function is just before the subprocess_info is about to * be freed. This can be used for freeing the argv and envp. The * Function must be runnable in either a process context or the * context in which call_usermodehelper_exec is called. */ struct subprocess_info *call_usermodehelper_setup(const char *path, char **argv, char **envp, gfp_t gfp_mask, int (*init)(struct subprocess_info *info, struct cred *new), void (*cleanup)(struct subprocess_info *info), void *data) { struct subprocess_info *sub_info; sub_info = kzalloc(sizeof(struct subprocess_info), gfp_mask); if (!sub_info) goto out; INIT_WORK(&sub_info->work, call_usermodehelper_exec_work); #ifdef CONFIG_STATIC_USERMODEHELPER sub_info->path = CONFIG_STATIC_USERMODEHELPER_PATH; #else sub_info->path = path; #endif sub_info->argv = argv; sub_info->envp = envp; sub_info->cleanup = cleanup; sub_info->init = init; sub_info->data = data; out: return sub_info; } EXPORT_SYMBOL(call_usermodehelper_setup); /** * call_usermodehelper_exec - start a usermode application * @sub_info: information about the subprocess * @wait: wait for the application to finish and return status. * when UMH_NO_WAIT don't wait at all, but you get no useful error back * when the program couldn't be exec'ed. This makes it safe to call * from interrupt context. * * Runs a user-space application. The application is started * asynchronously if wait is not set, and runs as a child of system workqueues. * (ie. it runs with full root capabilities and optimized affinity). * * Note: successful return value does not guarantee the helper was called at * all. You can't rely on sub_info->{init,cleanup} being called even for * UMH_WAIT_* wait modes as STATIC_USERMODEHELPER_PATH="" turns all helpers * into a successful no-op. */ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) { unsigned int state = TASK_UNINTERRUPTIBLE; DECLARE_COMPLETION_ONSTACK(done); int retval = 0; if (!sub_info->path) { call_usermodehelper_freeinfo(sub_info); return -EINVAL; } helper_lock(); if (usermodehelper_disabled) { retval = -EBUSY; goto out; } /* * If there is no binary for us to call, then just return and get out of * here. This allows us to set STATIC_USERMODEHELPER_PATH to "" and * disable all call_usermodehelper() calls. */ if (strlen(sub_info->path) == 0) goto out; /* * Set the completion pointer only if there is a waiter. * This makes it possible to use umh_complete to free * the data structure in case of UMH_NO_WAIT. */ sub_info->complete = (wait == UMH_NO_WAIT) ? NULL : &done; sub_info->wait = wait; queue_work(system_unbound_wq, &sub_info->work); if (wait == UMH_NO_WAIT) /* task has freed sub_info */ goto unlock; if (wait & UMH_FREEZABLE) state |= TASK_FREEZABLE; if (wait & UMH_KILLABLE) { retval = wait_for_completion_state(&done, state | TASK_KILLABLE); if (!retval) goto wait_done; /* umh_complete() will see NULL and free sub_info */ if (xchg(&sub_info->complete, NULL)) goto unlock; /* * fallthrough; in case of -ERESTARTSYS now do uninterruptible * wait_for_completion_state(). Since umh_complete() shall call * complete() in a moment if xchg() above returned NULL, this * uninterruptible wait_for_completion_state() will not block * SIGKILL'ed processes for long. */ } wait_for_completion_state(&done, state); wait_done: retval = sub_info->retval; out: call_usermodehelper_freeinfo(sub_info); unlock: helper_unlock(); return retval; } EXPORT_SYMBOL(call_usermodehelper_exec); /** * call_usermodehelper() - prepare and start a usermode application * @path: path to usermode executable * @argv: arg vector for process * @envp: environment for process * @wait: wait for the application to finish and return status. * when UMH_NO_WAIT don't wait at all, but you get no useful error back * when the program couldn't be exec'ed. This makes it safe to call * from interrupt context. * * This function is the equivalent to use call_usermodehelper_setup() and * call_usermodehelper_exec(). */ int call_usermodehelper(const char *path, char **argv, char **envp, int wait) { struct subprocess_info *info; gfp_t gfp_mask = (wait == UMH_NO_WAIT) ? GFP_ATOMIC : GFP_KERNEL; info = call_usermodehelper_setup(path, argv, envp, gfp_mask, NULL, NULL, NULL); if (info == NULL) return -ENOMEM; return call_usermodehelper_exec(info, wait); } EXPORT_SYMBOL(call_usermodehelper); #if defined(CONFIG_SYSCTL) static int proc_cap_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; unsigned long cap_array[2]; kernel_cap_t new_cap, *cap; int err; if (write && (!capable(CAP_SETPCAP) || !capable(CAP_SYS_MODULE))) return -EPERM; /* * convert from the global kernel_cap_t to the ulong array to print to * userspace if this is a read. * * Legacy format: capabilities are exposed as two 32-bit values */ cap = table->data; spin_lock(&umh_sysctl_lock); cap_array[0] = (u32) cap->val; cap_array[1] = cap->val >> 32; spin_unlock(&umh_sysctl_lock); t = *table; t.data = &cap_array; /* * actually read or write and array of ulongs from userspace. Remember * these are least significant 32 bits first */ err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos); if (err < 0) return err; new_cap.val = (u32)cap_array[0]; new_cap.val += (u64)cap_array[1] << 32; /* * Drop everything not in the new_cap (but don't add things) */ if (write) { spin_lock(&umh_sysctl_lock); *cap = cap_intersect(*cap, new_cap); spin_unlock(&umh_sysctl_lock); } return 0; } static struct ctl_table usermodehelper_table[] = { { .procname = "bset", .data = &usermodehelper_bset, .maxlen = 2 * sizeof(unsigned long), .mode = 0600, .proc_handler = proc_cap_handler, }, { .procname = "inheritable", .data = &usermodehelper_inheritable, .maxlen = 2 * sizeof(unsigned long), .mode = 0600, .proc_handler = proc_cap_handler, }, }; static int __init init_umh_sysctls(void) { register_sysctl_init("kernel/usermodehelper", usermodehelper_table); return 0; } early_initcall(init_umh_sysctls); #endif /* CONFIG_SYSCTL */ |
| 3 3 3 3 3 3 3 3 3 3 3 3 1 1 1 1 1 1 1 1 3 3 1 1 1 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/acct.c * * BSD Process Accounting for Linux * * Author: Marco van Wieringen <mvw@planets.elm.net> * * Some code based on ideas and code from: * Thomas K. Dyas <tdyas@eden.rutgers.edu> * * This file implements BSD-style process accounting. Whenever any * process exits, an accounting record of type "struct acct" is * written to the file specified with the acct() system call. It is * up to user-level programs to do useful things with the accounting * log. The kernel just provides the raw accounting information. * * (C) Copyright 1995 - 1997 Marco van Wieringen - ELM Consultancy B.V. * * Plugged two leaks. 1) It didn't return acct_file into the free_filps if * the file happened to be read-only. 2) If the accounting was suspended * due to the lack of space it happily allowed to reopen it and completely * lost the old acct_file. 3/10/98, Al Viro. * * Now we silently close acct_file on attempt to reopen. Cleaned sys_acct(). * XTerms and EMACS are manifestations of pure evil. 21/10/98, AV. * * Fixed a nasty interaction with sys_umount(). If the accounting * was suspeneded we failed to stop it on umount(). Messy. * Another one: remount to readonly didn't stop accounting. * Question: what should we do if we have CAP_SYS_ADMIN but not * CAP_SYS_PACCT? Current code does the following: umount returns -EBUSY * unless we are messing with the root. In that case we are getting a * real mess with do_remount_sb(). 9/11/98, AV. * * Fixed a bunch of races (and pair of leaks). Probably not the best way, * but this one obviously doesn't introduce deadlocks. Later. BTW, found * one race (and leak) in BSD implementation. * OK, that's better. ANOTHER race and leak in BSD variant. There always * is one more bug... 10/11/98, AV. * * Oh, fsck... Oopsable SMP race in do_process_acct() - we must hold * ->mmap_lock to walk the vma list of current->mm. Nasty, since it leaks * a struct file opened for write. Fixed. 2/6/2000, AV. */ #include <linux/mm.h> #include <linux/slab.h> #include <linux/acct.h> #include <linux/capability.h> #include <linux/file.h> #include <linux/tty.h> #include <linux/security.h> #include <linux/vfs.h> #include <linux/jiffies.h> #include <linux/times.h> #include <linux/syscalls.h> #include <linux/mount.h> #include <linux/uaccess.h> #include <linux/sched/cputime.h> #include <asm/div64.h> #include <linux/pid_namespace.h> #include <linux/fs_pin.h> /* * These constants control the amount of freespace that suspend and * resume the process accounting system, and the time delay between * each check. * Turned into sysctl-controllable parameters. AV, 12/11/98 */ static int acct_parm[3] = {4, 2, 30}; #define RESUME (acct_parm[0]) /* >foo% free space - resume */ #define SUSPEND (acct_parm[1]) /* <foo% free space - suspend */ #define ACCT_TIMEOUT (acct_parm[2]) /* foo second timeout between checks */ #ifdef CONFIG_SYSCTL static struct ctl_table kern_acct_table[] = { { .procname = "acct", .data = &acct_parm, .maxlen = 3*sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static __init int kernel_acct_sysctls_init(void) { register_sysctl_init("kernel", kern_acct_table); return 0; } late_initcall(kernel_acct_sysctls_init); #endif /* CONFIG_SYSCTL */ /* * External references and all of the globals. */ struct bsd_acct_struct { struct fs_pin pin; atomic_long_t count; struct rcu_head rcu; struct mutex lock; int active; unsigned long needcheck; struct file *file; struct pid_namespace *ns; struct work_struct work; struct completion done; }; static void do_acct_process(struct bsd_acct_struct *acct); /* * Check the amount of free space and suspend/resume accordingly. */ static int check_free_space(struct bsd_acct_struct *acct) { struct kstatfs sbuf; if (time_is_after_jiffies(acct->needcheck)) goto out; /* May block */ if (vfs_statfs(&acct->file->f_path, &sbuf)) goto out; if (acct->active) { u64 suspend = sbuf.f_blocks * SUSPEND; do_div(suspend, 100); if (sbuf.f_bavail <= suspend) { acct->active = 0; pr_info("Process accounting paused\n"); } } else { u64 resume = sbuf.f_blocks * RESUME; do_div(resume, 100); if (sbuf.f_bavail >= resume) { acct->active = 1; pr_info("Process accounting resumed\n"); } } acct->needcheck = jiffies + ACCT_TIMEOUT*HZ; out: return acct->active; } static void acct_put(struct bsd_acct_struct *p) { if (atomic_long_dec_and_test(&p->count)) kfree_rcu(p, rcu); } static inline struct bsd_acct_struct *to_acct(struct fs_pin *p) { return p ? container_of(p, struct bsd_acct_struct, pin) : NULL; } static struct bsd_acct_struct *acct_get(struct pid_namespace *ns) { struct bsd_acct_struct *res; again: smp_rmb(); rcu_read_lock(); res = to_acct(READ_ONCE(ns->bacct)); if (!res) { rcu_read_unlock(); return NULL; } if (!atomic_long_inc_not_zero(&res->count)) { rcu_read_unlock(); cpu_relax(); goto again; } rcu_read_unlock(); mutex_lock(&res->lock); if (res != to_acct(READ_ONCE(ns->bacct))) { mutex_unlock(&res->lock); acct_put(res); goto again; } return res; } static void acct_pin_kill(struct fs_pin *pin) { struct bsd_acct_struct *acct = to_acct(pin); mutex_lock(&acct->lock); do_acct_process(acct); schedule_work(&acct->work); wait_for_completion(&acct->done); cmpxchg(&acct->ns->bacct, pin, NULL); mutex_unlock(&acct->lock); pin_remove(pin); acct_put(acct); } static void close_work(struct work_struct *work) { struct bsd_acct_struct *acct = container_of(work, struct bsd_acct_struct, work); struct file *file = acct->file; if (file->f_op->flush) file->f_op->flush(file, NULL); __fput_sync(file); complete(&acct->done); } static int acct_on(struct filename *pathname) { struct file *file; struct vfsmount *mnt, *internal; struct pid_namespace *ns = task_active_pid_ns(current); struct bsd_acct_struct *acct; struct fs_pin *old; int err; acct = kzalloc(sizeof(struct bsd_acct_struct), GFP_KERNEL); if (!acct) return -ENOMEM; /* Difference from BSD - they don't do O_APPEND */ file = file_open_name(pathname, O_WRONLY|O_APPEND|O_LARGEFILE, 0); if (IS_ERR(file)) { kfree(acct); return PTR_ERR(file); } if (!S_ISREG(file_inode(file)->i_mode)) { kfree(acct); filp_close(file, NULL); return -EACCES; } if (!(file->f_mode & FMODE_CAN_WRITE)) { kfree(acct); filp_close(file, NULL); return -EIO; } internal = mnt_clone_internal(&file->f_path); if (IS_ERR(internal)) { kfree(acct); filp_close(file, NULL); return PTR_ERR(internal); } err = mnt_get_write_access(internal); if (err) { mntput(internal); kfree(acct); filp_close(file, NULL); return err; } mnt = file->f_path.mnt; file->f_path.mnt = internal; atomic_long_set(&acct->count, 1); init_fs_pin(&acct->pin, acct_pin_kill); acct->file = file; acct->needcheck = jiffies; acct->ns = ns; mutex_init(&acct->lock); INIT_WORK(&acct->work, close_work); init_completion(&acct->done); mutex_lock_nested(&acct->lock, 1); /* nobody has seen it yet */ pin_insert(&acct->pin, mnt); rcu_read_lock(); old = xchg(&ns->bacct, &acct->pin); mutex_unlock(&acct->lock); pin_kill(old); mnt_put_write_access(mnt); mntput(mnt); return 0; } static DEFINE_MUTEX(acct_on_mutex); /** * sys_acct - enable/disable process accounting * @name: file name for accounting records or NULL to shutdown accounting * * sys_acct() is the only system call needed to implement process * accounting. It takes the name of the file where accounting records * should be written. If the filename is NULL, accounting will be * shutdown. * * Returns: 0 for success or negative errno values for failure. */ SYSCALL_DEFINE1(acct, const char __user *, name) { int error = 0; if (!capable(CAP_SYS_PACCT)) return -EPERM; if (name) { struct filename *tmp = getname(name); if (IS_ERR(tmp)) return PTR_ERR(tmp); mutex_lock(&acct_on_mutex); error = acct_on(tmp); mutex_unlock(&acct_on_mutex); putname(tmp); } else { rcu_read_lock(); pin_kill(task_active_pid_ns(current)->bacct); } return error; } void acct_exit_ns(struct pid_namespace *ns) { rcu_read_lock(); pin_kill(ns->bacct); } /* * encode an u64 into a comp_t * * This routine has been adopted from the encode_comp_t() function in * the kern_acct.c file of the FreeBSD operating system. The encoding * is a 13-bit fraction with a 3-bit (base 8) exponent. */ #define MANTSIZE 13 /* 13 bit mantissa. */ #define EXPSIZE 3 /* Base 8 (3 bit) exponent. */ #define MAXFRACT ((1 << MANTSIZE) - 1) /* Maximum fractional value. */ static comp_t encode_comp_t(u64 value) { int exp, rnd; exp = rnd = 0; while (value > MAXFRACT) { rnd = value & (1 << (EXPSIZE - 1)); /* Round up? */ value >>= EXPSIZE; /* Base 8 exponent == 3 bit shift. */ exp++; } /* * If we need to round up, do it (and handle overflow correctly). */ if (rnd && (++value > MAXFRACT)) { value >>= EXPSIZE; exp++; } if (exp > (((comp_t) ~0U) >> MANTSIZE)) return (comp_t) ~0U; /* * Clean it up and polish it off. */ exp <<= MANTSIZE; /* Shift the exponent into place */ exp += value; /* and add on the mantissa. */ return exp; } #if ACCT_VERSION == 1 || ACCT_VERSION == 2 /* * encode an u64 into a comp2_t (24 bits) * * Format: 5 bit base 2 exponent, 20 bits mantissa. * The leading bit of the mantissa is not stored, but implied for * non-zero exponents. * Largest encodable value is 50 bits. */ #define MANTSIZE2 20 /* 20 bit mantissa. */ #define EXPSIZE2 5 /* 5 bit base 2 exponent. */ #define MAXFRACT2 ((1ul << MANTSIZE2) - 1) /* Maximum fractional value. */ #define MAXEXP2 ((1 << EXPSIZE2) - 1) /* Maximum exponent. */ static comp2_t encode_comp2_t(u64 value) { int exp, rnd; exp = (value > (MAXFRACT2>>1)); rnd = 0; while (value > MAXFRACT2) { rnd = value & 1; value >>= 1; exp++; } /* * If we need to round up, do it (and handle overflow correctly). */ if (rnd && (++value > MAXFRACT2)) { value >>= 1; exp++; } if (exp > MAXEXP2) { /* Overflow. Return largest representable number instead. */ return (1ul << (MANTSIZE2+EXPSIZE2-1)) - 1; } else { return (value & (MAXFRACT2>>1)) | (exp << (MANTSIZE2-1)); } } #elif ACCT_VERSION == 3 /* * encode an u64 into a 32 bit IEEE float */ static u32 encode_float(u64 value) { unsigned exp = 190; unsigned u; if (value == 0) return 0; while ((s64)value > 0) { value <<= 1; exp--; } u = (u32)(value >> 40) & 0x7fffffu; return u | (exp << 23); } #endif /* * Write an accounting entry for an exiting process * * The acct_process() call is the workhorse of the process * accounting system. The struct acct is built here and then written * into the accounting file. This function should only be called from * do_exit() or when switching to a different output file. */ static void fill_ac(acct_t *ac) { struct pacct_struct *pacct = ¤t->signal->pacct; u64 elapsed, run_time; time64_t btime; struct tty_struct *tty; /* * Fill the accounting struct with the needed info as recorded * by the different kernel functions. */ memset(ac, 0, sizeof(acct_t)); ac->ac_version = ACCT_VERSION | ACCT_BYTEORDER; strscpy(ac->ac_comm, current->comm, sizeof(ac->ac_comm)); /* calculate run_time in nsec*/ run_time = ktime_get_ns(); run_time -= current->group_leader->start_time; /* convert nsec -> AHZ */ elapsed = nsec_to_AHZ(run_time); #if ACCT_VERSION == 3 ac->ac_etime = encode_float(elapsed); #else ac->ac_etime = encode_comp_t(elapsed < (unsigned long) -1l ? (unsigned long) elapsed : (unsigned long) -1l); #endif #if ACCT_VERSION == 1 || ACCT_VERSION == 2 { /* new enlarged etime field */ comp2_t etime = encode_comp2_t(elapsed); ac->ac_etime_hi = etime >> 16; ac->ac_etime_lo = (u16) etime; } #endif do_div(elapsed, AHZ); btime = ktime_get_real_seconds() - elapsed; ac->ac_btime = clamp_t(time64_t, btime, 0, U32_MAX); #if ACCT_VERSION == 2 ac->ac_ahz = AHZ; #endif spin_lock_irq(¤t->sighand->siglock); tty = current->signal->tty; /* Safe as we hold the siglock */ ac->ac_tty = tty ? old_encode_dev(tty_devnum(tty)) : 0; ac->ac_utime = encode_comp_t(nsec_to_AHZ(pacct->ac_utime)); ac->ac_stime = encode_comp_t(nsec_to_AHZ(pacct->ac_stime)); ac->ac_flag = pacct->ac_flag; ac->ac_mem = encode_comp_t(pacct->ac_mem); ac->ac_minflt = encode_comp_t(pacct->ac_minflt); ac->ac_majflt = encode_comp_t(pacct->ac_majflt); ac->ac_exitcode = pacct->ac_exitcode; spin_unlock_irq(¤t->sighand->siglock); } /* * do_acct_process does all actual work. Caller holds the reference to file. */ static void do_acct_process(struct bsd_acct_struct *acct) { acct_t ac; unsigned long flim; const struct cred *orig_cred; struct file *file = acct->file; /* * Accounting records are not subject to resource limits. */ flim = rlimit(RLIMIT_FSIZE); current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; /* Perform file operations on behalf of whoever enabled accounting */ orig_cred = override_creds(file->f_cred); /* * First check to see if there is enough free_space to continue * the process accounting system. */ if (!check_free_space(acct)) goto out; fill_ac(&ac); /* we really need to bite the bullet and change layout */ ac.ac_uid = from_kuid_munged(file->f_cred->user_ns, orig_cred->uid); ac.ac_gid = from_kgid_munged(file->f_cred->user_ns, orig_cred->gid); #if ACCT_VERSION == 1 || ACCT_VERSION == 2 /* backward-compatible 16 bit fields */ ac.ac_uid16 = ac.ac_uid; ac.ac_gid16 = ac.ac_gid; #elif ACCT_VERSION == 3 { struct pid_namespace *ns = acct->ns; ac.ac_pid = task_tgid_nr_ns(current, ns); rcu_read_lock(); ac.ac_ppid = task_tgid_nr_ns(rcu_dereference(current->real_parent), ns); rcu_read_unlock(); } #endif /* * Get freeze protection. If the fs is frozen, just skip the write * as we could deadlock the system otherwise. */ if (file_start_write_trylock(file)) { /* it's been opened O_APPEND, so position is irrelevant */ loff_t pos = 0; __kernel_write(file, &ac, sizeof(acct_t), &pos); file_end_write(file); } out: current->signal->rlim[RLIMIT_FSIZE].rlim_cur = flim; revert_creds(orig_cred); } /** * acct_collect - collect accounting information into pacct_struct * @exitcode: task exit code * @group_dead: not 0, if this thread is the last one in the process. */ void acct_collect(long exitcode, int group_dead) { struct pacct_struct *pacct = ¤t->signal->pacct; u64 utime, stime; unsigned long vsize = 0; if (group_dead && current->mm) { struct mm_struct *mm = current->mm; VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *vma; mmap_read_lock(mm); for_each_vma(vmi, vma) vsize += vma->vm_end - vma->vm_start; mmap_read_unlock(mm); } spin_lock_irq(¤t->sighand->siglock); if (group_dead) pacct->ac_mem = vsize / 1024; if (thread_group_leader(current)) { pacct->ac_exitcode = exitcode; if (current->flags & PF_FORKNOEXEC) pacct->ac_flag |= AFORK; } if (current->flags & PF_SUPERPRIV) pacct->ac_flag |= ASU; if (current->flags & PF_DUMPCORE) pacct->ac_flag |= ACORE; if (current->flags & PF_SIGNALED) pacct->ac_flag |= AXSIG; task_cputime(current, &utime, &stime); pacct->ac_utime += utime; pacct->ac_stime += stime; pacct->ac_minflt += current->min_flt; pacct->ac_majflt += current->maj_flt; spin_unlock_irq(¤t->sighand->siglock); } static void slow_acct_process(struct pid_namespace *ns) { for ( ; ns; ns = ns->parent) { struct bsd_acct_struct *acct = acct_get(ns); if (acct) { do_acct_process(acct); mutex_unlock(&acct->lock); acct_put(acct); } } } /** * acct_process - handles process accounting for an exiting task */ void acct_process(void) { struct pid_namespace *ns; /* * This loop is safe lockless, since current is still * alive and holds its namespace, which in turn holds * its parent. */ for (ns = task_active_pid_ns(current); ns != NULL; ns = ns->parent) { if (ns->bacct) break; } if (unlikely(ns)) slow_acct_process(ns); } |
| 627 | 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Universal/legacy driver for 8250/16550-type serial ports * * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o. * * Copyright (C) 2001 Russell King. * * Supports: ISA-compatible 8250/16550 ports * PNP 8250/16550 ports * early_serial_setup() ports * userspace-configurable "phantom" ports * "serial8250" platform devices * serial8250_register_8250_port() ports */ #include <linux/acpi.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/ioport.h> #include <linux/init.h> #include <linux/console.h> #include <linux/sysrq.h> #include <linux/delay.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/tty.h> #include <linux/ratelimit.h> #include <linux/tty_flip.h> #include <linux/serial.h> #include <linux/serial_8250.h> #include <linux/nmi.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/string_helpers.h> #include <linux/uaccess.h> #include <linux/io.h> #ifdef CONFIG_SPARC #include <linux/sunserialcore.h> #endif #include <asm/irq.h> #include "8250.h" /* * Configuration: * share_irqs - whether we pass IRQF_SHARED to request_irq(). This option * is unsafe when used on edge-triggered interrupts. */ static unsigned int share_irqs = SERIAL8250_SHARE_IRQS; static unsigned int nr_uarts = CONFIG_SERIAL_8250_RUNTIME_UARTS; static struct uart_driver serial8250_reg; static unsigned int skip_txen_test; /* force skip of txen test at init time */ #define PASS_LIMIT 512 #include <asm/serial.h> /* * SERIAL_PORT_DFNS tells us about built-in ports that have no * standard enumeration mechanism. Platforms that can find all * serial ports via mechanisms like ACPI or PCI need not supply it. */ #ifndef SERIAL_PORT_DFNS #define SERIAL_PORT_DFNS #endif static const struct old_serial_port old_serial_port[] = { SERIAL_PORT_DFNS /* defined in asm/serial.h */ }; #define UART_NR CONFIG_SERIAL_8250_NR_UARTS #ifdef CONFIG_SERIAL_8250_RSA #define PORT_RSA_MAX 4 static unsigned long probe_rsa[PORT_RSA_MAX]; static unsigned int probe_rsa_count; #endif /* CONFIG_SERIAL_8250_RSA */ struct irq_info { struct hlist_node node; int irq; spinlock_t lock; /* Protects list not the hash */ struct list_head *head; }; #define NR_IRQ_HASH 32 /* Can be adjusted later */ static struct hlist_head irq_lists[NR_IRQ_HASH]; static DEFINE_MUTEX(hash_mutex); /* Used to walk the hash */ /* * This is the serial driver's interrupt routine. * * Arjan thinks the old way was overly complex, so it got simplified. * Alan disagrees, saying that need the complexity to handle the weird * nature of ISA shared interrupts. (This is a special exception.) * * In order to handle ISA shared interrupts properly, we need to check * that all ports have been serviced, and therefore the ISA interrupt * line has been de-asserted. * * This means we need to loop through all ports. checking that they * don't have an interrupt pending. */ static irqreturn_t serial8250_interrupt(int irq, void *dev_id) { struct irq_info *i = dev_id; struct list_head *l, *end = NULL; int pass_counter = 0, handled = 0; pr_debug("%s(%d): start\n", __func__, irq); spin_lock(&i->lock); l = i->head; do { struct uart_8250_port *up; struct uart_port *port; up = list_entry(l, struct uart_8250_port, list); port = &up->port; if (port->handle_irq(port)) { handled = 1; end = NULL; } else if (end == NULL) end = l; l = l->next; if (l == i->head && pass_counter++ > PASS_LIMIT) break; } while (l != end); spin_unlock(&i->lock); pr_debug("%s(%d): end\n", __func__, irq); return IRQ_RETVAL(handled); } /* * To support ISA shared interrupts, we need to have one interrupt * handler that ensures that the IRQ line has been deasserted * before returning. Failing to do this will result in the IRQ * line being stuck active, and, since ISA irqs are edge triggered, * no more IRQs will be seen. */ static void serial_do_unlink(struct irq_info *i, struct uart_8250_port *up) { spin_lock_irq(&i->lock); if (!list_empty(i->head)) { if (i->head == &up->list) i->head = i->head->next; list_del(&up->list); } else { BUG_ON(i->head != &up->list); i->head = NULL; } spin_unlock_irq(&i->lock); /* List empty so throw away the hash node */ if (i->head == NULL) { hlist_del(&i->node); kfree(i); } } static int serial_link_irq_chain(struct uart_8250_port *up) { struct hlist_head *h; struct irq_info *i; int ret; mutex_lock(&hash_mutex); h = &irq_lists[up->port.irq % NR_IRQ_HASH]; hlist_for_each_entry(i, h, node) if (i->irq == up->port.irq) break; if (i == NULL) { i = kzalloc(sizeof(struct irq_info), GFP_KERNEL); if (i == NULL) { mutex_unlock(&hash_mutex); return -ENOMEM; } spin_lock_init(&i->lock); i->irq = up->port.irq; hlist_add_head(&i->node, h); } mutex_unlock(&hash_mutex); spin_lock_irq(&i->lock); if (i->head) { list_add(&up->list, i->head); spin_unlock_irq(&i->lock); ret = 0; } else { INIT_LIST_HEAD(&up->list); i->head = &up->list; spin_unlock_irq(&i->lock); ret = request_irq(up->port.irq, serial8250_interrupt, up->port.irqflags, up->port.name, i); if (ret < 0) serial_do_unlink(i, up); } return ret; } static void serial_unlink_irq_chain(struct uart_8250_port *up) { struct irq_info *i; struct hlist_head *h; mutex_lock(&hash_mutex); h = &irq_lists[up->port.irq % NR_IRQ_HASH]; hlist_for_each_entry(i, h, node) if (i->irq == up->port.irq) break; BUG_ON(i == NULL); BUG_ON(i->head == NULL); if (list_empty(i->head)) free_irq(up->port.irq, i); serial_do_unlink(i, up); mutex_unlock(&hash_mutex); } /* * This function is used to handle ports that do not have an * interrupt. This doesn't work very well for 16450's, but gives * barely passable results for a 16550A. (Although at the expense * of much CPU overhead). */ static void serial8250_timeout(struct timer_list *t) { struct uart_8250_port *up = from_timer(up, t, timer); up->port.handle_irq(&up->port); mod_timer(&up->timer, jiffies + uart_poll_timeout(&up->port)); } static void serial8250_backup_timeout(struct timer_list *t) { struct uart_8250_port *up = from_timer(up, t, timer); unsigned int iir, ier = 0, lsr; unsigned long flags; uart_port_lock_irqsave(&up->port, &flags); /* * Must disable interrupts or else we risk racing with the interrupt * based handler. */ if (up->port.irq) { ier = serial_in(up, UART_IER); serial_out(up, UART_IER, 0); } iir = serial_in(up, UART_IIR); /* * This should be a safe test for anyone who doesn't trust the * IIR bits on their UART, but it's specifically designed for * the "Diva" UART used on the management processor on many HP * ia64 and parisc boxes. */ lsr = serial_lsr_in(up); if ((iir & UART_IIR_NO_INT) && (up->ier & UART_IER_THRI) && (!kfifo_is_empty(&up->port.state->port.xmit_fifo) || up->port.x_char) && (lsr & UART_LSR_THRE)) { iir &= ~(UART_IIR_ID | UART_IIR_NO_INT); iir |= UART_IIR_THRI; } if (!(iir & UART_IIR_NO_INT)) serial8250_tx_chars(up); if (up->port.irq) serial_out(up, UART_IER, ier); uart_port_unlock_irqrestore(&up->port, flags); /* Standard timer interval plus 0.2s to keep the port running */ mod_timer(&up->timer, jiffies + uart_poll_timeout(&up->port) + HZ / 5); } static void univ8250_setup_timer(struct uart_8250_port *up) { struct uart_port *port = &up->port; /* * The above check will only give an accurate result the first time * the port is opened so this value needs to be preserved. */ if (up->bugs & UART_BUG_THRE) { pr_debug("%s - using backup timer\n", port->name); up->timer.function = serial8250_backup_timeout; mod_timer(&up->timer, jiffies + uart_poll_timeout(port) + HZ / 5); } /* * If the "interrupt" for this port doesn't correspond with any * hardware interrupt, we use a timer-based system. The original * driver used to do this with IRQ0. */ if (!port->irq) mod_timer(&up->timer, jiffies + uart_poll_timeout(port)); } static int univ8250_setup_irq(struct uart_8250_port *up) { struct uart_port *port = &up->port; if (port->irq) return serial_link_irq_chain(up); return 0; } static void univ8250_release_irq(struct uart_8250_port *up) { struct uart_port *port = &up->port; del_timer_sync(&up->timer); up->timer.function = serial8250_timeout; if (port->irq) serial_unlink_irq_chain(up); } #ifdef CONFIG_SERIAL_8250_RSA static int serial8250_request_rsa_resource(struct uart_8250_port *up) { unsigned long start = UART_RSA_BASE << up->port.regshift; unsigned int size = 8 << up->port.regshift; struct uart_port *port = &up->port; int ret = -EINVAL; switch (port->iotype) { case UPIO_HUB6: case UPIO_PORT: start += port->iobase; if (request_region(start, size, "serial-rsa")) ret = 0; else ret = -EBUSY; break; } return ret; } static void serial8250_release_rsa_resource(struct uart_8250_port *up) { unsigned long offset = UART_RSA_BASE << up->port.regshift; unsigned int size = 8 << up->port.regshift; struct uart_port *port = &up->port; switch (port->iotype) { case UPIO_HUB6: case UPIO_PORT: release_region(port->iobase + offset, size); break; } } #endif static const struct uart_ops *base_ops; static struct uart_ops univ8250_port_ops; static const struct uart_8250_ops univ8250_driver_ops = { .setup_irq = univ8250_setup_irq, .release_irq = univ8250_release_irq, .setup_timer = univ8250_setup_timer, }; static struct uart_8250_port serial8250_ports[UART_NR]; /** * serial8250_get_port - retrieve struct uart_8250_port * @line: serial line number * * This function retrieves struct uart_8250_port for the specific line. * This struct *must* *not* be used to perform a 8250 or serial core operation * which is not accessible otherwise. Its only purpose is to make the struct * accessible to the runtime-pm callbacks for context suspend/restore. * The lock assumption made here is none because runtime-pm suspend/resume * callbacks should not be invoked if there is any operation performed on the * port. */ struct uart_8250_port *serial8250_get_port(int line) { return &serial8250_ports[line]; } EXPORT_SYMBOL_GPL(serial8250_get_port); static void (*serial8250_isa_config)(int port, struct uart_port *up, u32 *capabilities); void serial8250_set_isa_configurator( void (*v)(int port, struct uart_port *up, u32 *capabilities)) { serial8250_isa_config = v; } EXPORT_SYMBOL(serial8250_set_isa_configurator); #ifdef CONFIG_SERIAL_8250_RSA static void univ8250_config_port(struct uart_port *port, int flags) { struct uart_8250_port *up = up_to_u8250p(port); up->probe &= ~UART_PROBE_RSA; if (port->type == PORT_RSA) { if (serial8250_request_rsa_resource(up) == 0) up->probe |= UART_PROBE_RSA; } else if (flags & UART_CONFIG_TYPE) { int i; for (i = 0; i < probe_rsa_count; i++) { if (probe_rsa[i] == up->port.iobase) { if (serial8250_request_rsa_resource(up) == 0) up->probe |= UART_PROBE_RSA; break; } } } base_ops->config_port(port, flags); if (port->type != PORT_RSA && up->probe & UART_PROBE_RSA) serial8250_release_rsa_resource(up); } static int univ8250_request_port(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); int ret; ret = base_ops->request_port(port); if (ret == 0 && port->type == PORT_RSA) { ret = serial8250_request_rsa_resource(up); if (ret < 0) base_ops->release_port(port); } return ret; } static void univ8250_release_port(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); if (port->type == PORT_RSA) serial8250_release_rsa_resource(up); base_ops->release_port(port); } static void univ8250_rsa_support(struct uart_ops *ops) { ops->config_port = univ8250_config_port; ops->request_port = univ8250_request_port; ops->release_port = univ8250_release_port; } #else #define univ8250_rsa_support(x) do { } while (0) #endif /* CONFIG_SERIAL_8250_RSA */ static inline void serial8250_apply_quirks(struct uart_8250_port *up) { up->port.quirks |= skip_txen_test ? UPQ_NO_TXEN_TEST : 0; } static struct uart_8250_port *serial8250_setup_port(int index) { struct uart_8250_port *up; if (index >= UART_NR) return NULL; up = &serial8250_ports[index]; up->port.line = index; up->port.port_id = index; serial8250_init_port(up); if (!base_ops) base_ops = up->port.ops; up->port.ops = &univ8250_port_ops; timer_setup(&up->timer, serial8250_timeout, 0); up->ops = &univ8250_driver_ops; serial8250_set_defaults(up); return up; } static void __init serial8250_isa_init_ports(void) { struct uart_8250_port *up; static int first = 1; int i, irqflag = 0; if (!first) return; first = 0; if (nr_uarts > UART_NR) nr_uarts = UART_NR; /* * Set up initial isa ports based on nr_uart module param, or else * default to CONFIG_SERIAL_8250_RUNTIME_UARTS. Note that we do not * need to increase nr_uarts when setting up the initial isa ports. */ for (i = 0; i < nr_uarts; i++) serial8250_setup_port(i); /* chain base port ops to support Remote Supervisor Adapter */ univ8250_port_ops = *base_ops; univ8250_rsa_support(&univ8250_port_ops); if (share_irqs) irqflag = IRQF_SHARED; for (i = 0, up = serial8250_ports; i < ARRAY_SIZE(old_serial_port) && i < nr_uarts; i++, up++) { struct uart_port *port = &up->port; port->iobase = old_serial_port[i].port; port->irq = irq_canonicalize(old_serial_port[i].irq); port->irqflags = 0; port->uartclk = old_serial_port[i].baud_base * 16; port->flags = old_serial_port[i].flags; port->hub6 = 0; port->membase = old_serial_port[i].iomem_base; port->iotype = old_serial_port[i].io_type; port->regshift = old_serial_port[i].iomem_reg_shift; port->irqflags |= irqflag; if (serial8250_isa_config != NULL) serial8250_isa_config(i, &up->port, &up->capabilities); } } static void __init serial8250_register_ports(struct uart_driver *drv, struct device *dev) { int i; for (i = 0; i < nr_uarts; i++) { struct uart_8250_port *up = &serial8250_ports[i]; if (up->port.type == PORT_8250_CIR) continue; if (up->port.dev) continue; up->port.dev = dev; if (uart_console_registered(&up->port)) pm_runtime_get_sync(up->port.dev); serial8250_apply_quirks(up); uart_add_one_port(drv, &up->port); } } #ifdef CONFIG_SERIAL_8250_CONSOLE static void univ8250_console_write(struct console *co, const char *s, unsigned int count) { struct uart_8250_port *up = &serial8250_ports[co->index]; serial8250_console_write(up, s, count); } static int univ8250_console_setup(struct console *co, char *options) { struct uart_8250_port *up; struct uart_port *port; int retval, i; /* * Check whether an invalid uart number has been specified, and * if so, search for the first available port that does have * console support. */ if (co->index < 0 || co->index >= UART_NR) co->index = 0; /* * If the console is past the initial isa ports, init more ports up to * co->index as needed and increment nr_uarts accordingly. */ for (i = nr_uarts; i <= co->index; i++) { up = serial8250_setup_port(i); if (!up) return -ENODEV; nr_uarts++; } port = &serial8250_ports[co->index].port; /* link port to console */ port->cons = co; retval = serial8250_console_setup(port, options, false); if (retval != 0) port->cons = NULL; return retval; } static int univ8250_console_exit(struct console *co) { struct uart_port *port; port = &serial8250_ports[co->index].port; return serial8250_console_exit(port); } /** * univ8250_console_match - non-standard console matching * @co: registering console * @name: name from console command line * @idx: index from console command line * @options: ptr to option string from console command line * * Only attempts to match console command lines of the form: * console=uart[8250],io|mmio|mmio16|mmio32,<addr>[,<options>] * console=uart[8250],0x<addr>[,<options>] * This form is used to register an initial earlycon boot console and * replace it with the serial8250_console at 8250 driver init. * * Performs console setup for a match (as required by interface) * If no <options> are specified, then assume the h/w is already setup. * * Returns 0 if console matches; otherwise non-zero to use default matching */ static int univ8250_console_match(struct console *co, char *name, int idx, char *options) { char match[] = "uart"; /* 8250-specific earlycon name */ unsigned char iotype; resource_size_t addr; int i; if (strncmp(name, match, 4) != 0) return -ENODEV; if (uart_parse_earlycon(options, &iotype, &addr, &options)) return -ENODEV; /* try to match the port specified on the command line */ for (i = 0; i < nr_uarts; i++) { struct uart_port *port = &serial8250_ports[i].port; if (port->iotype != iotype) continue; if ((iotype == UPIO_MEM || iotype == UPIO_MEM16 || iotype == UPIO_MEM32 || iotype == UPIO_MEM32BE) && (port->mapbase != addr)) continue; if (iotype == UPIO_PORT && port->iobase != addr) continue; co->index = i; port->cons = co; return serial8250_console_setup(port, options, true); } return -ENODEV; } static struct console univ8250_console = { .name = "ttyS", .write = univ8250_console_write, .device = uart_console_device, .setup = univ8250_console_setup, .exit = univ8250_console_exit, .match = univ8250_console_match, .flags = CON_PRINTBUFFER | CON_ANYTIME, .index = -1, .data = &serial8250_reg, }; static int __init univ8250_console_init(void) { if (nr_uarts == 0) return -ENODEV; serial8250_isa_init_ports(); register_console(&univ8250_console); return 0; } console_initcall(univ8250_console_init); #define SERIAL8250_CONSOLE (&univ8250_console) #else #define SERIAL8250_CONSOLE NULL #endif static struct uart_driver serial8250_reg = { .owner = THIS_MODULE, .driver_name = "serial", .dev_name = "ttyS", .major = TTY_MAJOR, .minor = 64, .cons = SERIAL8250_CONSOLE, }; /* * early_serial_setup - early registration for 8250 ports * * Setup an 8250 port structure prior to console initialisation. Use * after console initialisation will cause undefined behaviour. */ int __init early_serial_setup(struct uart_port *port) { struct uart_port *p; if (port->line >= ARRAY_SIZE(serial8250_ports) || nr_uarts == 0) return -ENODEV; serial8250_isa_init_ports(); p = &serial8250_ports[port->line].port; p->iobase = port->iobase; p->membase = port->membase; p->irq = port->irq; p->irqflags = port->irqflags; p->uartclk = port->uartclk; p->fifosize = port->fifosize; p->regshift = port->regshift; p->iotype = port->iotype; p->flags = port->flags; p->mapbase = port->mapbase; p->mapsize = port->mapsize; p->private_data = port->private_data; p->type = port->type; p->line = port->line; serial8250_set_defaults(up_to_u8250p(p)); if (port->serial_in) p->serial_in = port->serial_in; if (port->serial_out) p->serial_out = port->serial_out; if (port->handle_irq) p->handle_irq = port->handle_irq; return 0; } /** * serial8250_suspend_port - suspend one serial port * @line: serial line number * * Suspend one serial port. */ void serial8250_suspend_port(int line) { struct uart_8250_port *up = &serial8250_ports[line]; struct uart_port *port = &up->port; if (!console_suspend_enabled && uart_console(port) && port->type != PORT_8250) { unsigned char canary = 0xa5; serial_out(up, UART_SCR, canary); if (serial_in(up, UART_SCR) == canary) up->canary = canary; } uart_suspend_port(&serial8250_reg, port); } EXPORT_SYMBOL(serial8250_suspend_port); /** * serial8250_resume_port - resume one serial port * @line: serial line number * * Resume one serial port. */ void serial8250_resume_port(int line) { struct uart_8250_port *up = &serial8250_ports[line]; struct uart_port *port = &up->port; up->canary = 0; if (up->capabilities & UART_NATSEMI) { /* Ensure it's still in high speed mode */ serial_port_out(port, UART_LCR, 0xE0); ns16550a_goto_highspeed(up); serial_port_out(port, UART_LCR, 0); port->uartclk = 921600*16; } uart_resume_port(&serial8250_reg, port); } EXPORT_SYMBOL(serial8250_resume_port); /* * Register a set of serial devices attached to a platform device. The * list is terminated with a zero flags entry, which means we expect * all entries to have at least UPF_BOOT_AUTOCONF set. */ static int serial8250_probe(struct platform_device *dev) { struct plat_serial8250_port *p = dev_get_platdata(&dev->dev); struct uart_8250_port uart; int ret, i, irqflag = 0; memset(&uart, 0, sizeof(uart)); if (share_irqs) irqflag = IRQF_SHARED; for (i = 0; p && p->flags != 0; p++, i++) { uart.port.iobase = p->iobase; uart.port.membase = p->membase; uart.port.irq = p->irq; uart.port.irqflags = p->irqflags; uart.port.uartclk = p->uartclk; uart.port.regshift = p->regshift; uart.port.iotype = p->iotype; uart.port.flags = p->flags; uart.port.mapbase = p->mapbase; uart.port.mapsize = p->mapsize; uart.port.hub6 = p->hub6; uart.port.has_sysrq = p->has_sysrq; uart.port.private_data = p->private_data; uart.port.type = p->type; uart.bugs = p->bugs; uart.port.serial_in = p->serial_in; uart.port.serial_out = p->serial_out; uart.dl_read = p->dl_read; uart.dl_write = p->dl_write; uart.port.handle_irq = p->handle_irq; uart.port.handle_break = p->handle_break; uart.port.set_termios = p->set_termios; uart.port.set_ldisc = p->set_ldisc; uart.port.get_mctrl = p->get_mctrl; uart.port.pm = p->pm; uart.port.dev = &dev->dev; uart.port.irqflags |= irqflag; ret = serial8250_register_8250_port(&uart); if (ret < 0) { dev_err(&dev->dev, "unable to register port at index %d " "(IO%lx MEM%llx IRQ%d): %d\n", i, p->iobase, (unsigned long long)p->mapbase, p->irq, ret); } } return 0; } /* * Remove serial ports registered against a platform device. */ static void serial8250_remove(struct platform_device *dev) { int i; for (i = 0; i < nr_uarts; i++) { struct uart_8250_port *up = &serial8250_ports[i]; if (up->port.dev == &dev->dev) serial8250_unregister_port(i); } } static int serial8250_suspend(struct platform_device *dev, pm_message_t state) { int i; for (i = 0; i < UART_NR; i++) { struct uart_8250_port *up = &serial8250_ports[i]; if (up->port.type != PORT_UNKNOWN && up->port.dev == &dev->dev) uart_suspend_port(&serial8250_reg, &up->port); } return 0; } static int serial8250_resume(struct platform_device *dev) { int i; for (i = 0; i < UART_NR; i++) { struct uart_8250_port *up = &serial8250_ports[i]; if (up->port.type != PORT_UNKNOWN && up->port.dev == &dev->dev) serial8250_resume_port(i); } return 0; } static struct platform_driver serial8250_isa_driver = { .probe = serial8250_probe, .remove_new = serial8250_remove, .suspend = serial8250_suspend, .resume = serial8250_resume, .driver = { .name = "serial8250", }, }; /* * This "device" covers _all_ ISA 8250-compatible serial devices listed * in the table in include/asm/serial.h */ static struct platform_device *serial8250_isa_devs; /* * serial8250_register_8250_port and serial8250_unregister_port allows for * 16x50 serial ports to be configured at run-time, to support PCMCIA * modems and PCI multiport cards. */ static DEFINE_MUTEX(serial_mutex); static struct uart_8250_port *serial8250_find_match_or_unused(const struct uart_port *port) { int i; /* * First, find a port entry which matches. */ for (i = 0; i < nr_uarts; i++) if (uart_match_port(&serial8250_ports[i].port, port)) return &serial8250_ports[i]; /* try line number first if still available */ i = port->line; if (i < nr_uarts && serial8250_ports[i].port.type == PORT_UNKNOWN && serial8250_ports[i].port.iobase == 0) return &serial8250_ports[i]; /* * We didn't find a matching entry, so look for the first * free entry. We look for one which hasn't been previously * used (indicated by zero iobase). */ for (i = 0; i < nr_uarts; i++) if (serial8250_ports[i].port.type == PORT_UNKNOWN && serial8250_ports[i].port.iobase == 0) return &serial8250_ports[i]; /* * That also failed. Last resort is to find any entry which * doesn't have a real port associated with it. */ for (i = 0; i < nr_uarts; i++) if (serial8250_ports[i].port.type == PORT_UNKNOWN) return &serial8250_ports[i]; return NULL; } static void serial_8250_overrun_backoff_work(struct work_struct *work) { struct uart_8250_port *up = container_of(to_delayed_work(work), struct uart_8250_port, overrun_backoff); struct uart_port *port = &up->port; unsigned long flags; uart_port_lock_irqsave(port, &flags); up->ier |= UART_IER_RLSI | UART_IER_RDI; up->port.read_status_mask |= UART_LSR_DR; serial_out(up, UART_IER, up->ier); uart_port_unlock_irqrestore(port, flags); } /** * serial8250_register_8250_port - register a serial port * @up: serial port template * * Configure the serial port specified by the request. If the * port exists and is in use, it is hung up and unregistered * first. * * The port is then probed and if necessary the IRQ is autodetected * If this fails an error is returned. * * On success the port is ready to use and the line number is returned. */ int serial8250_register_8250_port(const struct uart_8250_port *up) { struct uart_8250_port *uart; int ret = -ENOSPC; if (up->port.uartclk == 0) return -EINVAL; mutex_lock(&serial_mutex); uart = serial8250_find_match_or_unused(&up->port); if (!uart) { /* * If the port is past the initial isa ports, initialize a new * port and increment nr_uarts accordingly. */ uart = serial8250_setup_port(nr_uarts); if (!uart) goto unlock; nr_uarts++; } if (uart->port.type != PORT_8250_CIR) { struct mctrl_gpios *gpios; if (uart->port.dev) uart_remove_one_port(&serial8250_reg, &uart->port); uart->port.ctrl_id = up->port.ctrl_id; uart->port.port_id = up->port.port_id; uart->port.iobase = up->port.iobase; uart->port.membase = up->port.membase; uart->port.irq = up->port.irq; uart->port.irqflags = up->port.irqflags; uart->port.uartclk = up->port.uartclk; uart->port.fifosize = up->port.fifosize; uart->port.regshift = up->port.regshift; uart->port.iotype = up->port.iotype; uart->port.flags = up->port.flags | UPF_BOOT_AUTOCONF; uart->bugs = up->bugs; uart->port.mapbase = up->port.mapbase; uart->port.mapsize = up->port.mapsize; uart->port.private_data = up->port.private_data; uart->tx_loadsz = up->tx_loadsz; uart->capabilities = up->capabilities; uart->port.throttle = up->port.throttle; uart->port.unthrottle = up->port.unthrottle; uart->port.rs485_config = up->port.rs485_config; uart->port.rs485_supported = up->port.rs485_supported; uart->port.rs485 = up->port.rs485; uart->rs485_start_tx = up->rs485_start_tx; uart->rs485_stop_tx = up->rs485_stop_tx; uart->lsr_save_mask = up->lsr_save_mask; uart->dma = up->dma; /* Take tx_loadsz from fifosize if it wasn't set separately */ if (uart->port.fifosize && !uart->tx_loadsz) uart->tx_loadsz = uart->port.fifosize; if (up->port.dev) { uart->port.dev = up->port.dev; ret = uart_get_rs485_mode(&uart->port); if (ret) goto err; } if (up->port.flags & UPF_FIXED_TYPE) uart->port.type = up->port.type; /* * Only call mctrl_gpio_init(), if the device has no ACPI * companion device */ if (!has_acpi_companion(uart->port.dev)) { gpios = mctrl_gpio_init(&uart->port, 0); if (IS_ERR(gpios)) { ret = PTR_ERR(gpios); goto err; } else { uart->gpios = gpios; } } serial8250_set_defaults(uart); /* Possibly override default I/O functions. */ if (up->port.serial_in) uart->port.serial_in = up->port.serial_in; if (up->port.serial_out) uart->port.serial_out = up->port.serial_out; if (up->port.handle_irq) uart->port.handle_irq = up->port.handle_irq; /* Possibly override set_termios call */ if (up->port.set_termios) uart->port.set_termios = up->port.set_termios; if (up->port.set_ldisc) uart->port.set_ldisc = up->port.set_ldisc; if (up->port.get_mctrl) uart->port.get_mctrl = up->port.get_mctrl; if (up->port.set_mctrl) uart->port.set_mctrl = up->port.set_mctrl; if (up->port.get_divisor) uart->port.get_divisor = up->port.get_divisor; if (up->port.set_divisor) uart->port.set_divisor = up->port.set_divisor; if (up->port.startup) uart->port.startup = up->port.startup; if (up->port.shutdown) uart->port.shutdown = up->port.shutdown; if (up->port.pm) uart->port.pm = up->port.pm; if (up->port.handle_break) uart->port.handle_break = up->port.handle_break; if (up->dl_read) uart->dl_read = up->dl_read; if (up->dl_write) uart->dl_write = up->dl_write; if (uart->port.type != PORT_8250_CIR) { if (serial8250_isa_config != NULL) serial8250_isa_config(0, &uart->port, &uart->capabilities); serial8250_apply_quirks(uart); ret = uart_add_one_port(&serial8250_reg, &uart->port); if (ret) goto err; ret = uart->port.line; } else { dev_info(uart->port.dev, "skipping CIR port at 0x%lx / 0x%llx, IRQ %d\n", uart->port.iobase, (unsigned long long)uart->port.mapbase, uart->port.irq); ret = 0; } if (!uart->lsr_save_mask) uart->lsr_save_mask = LSR_SAVE_FLAGS; /* Use default LSR mask */ /* Initialise interrupt backoff work if required */ if (up->overrun_backoff_time_ms > 0) { uart->overrun_backoff_time_ms = up->overrun_backoff_time_ms; INIT_DELAYED_WORK(&uart->overrun_backoff, serial_8250_overrun_backoff_work); } else { uart->overrun_backoff_time_ms = 0; } } unlock: mutex_unlock(&serial_mutex); return ret; err: uart->port.dev = NULL; mutex_unlock(&serial_mutex); return ret; } EXPORT_SYMBOL(serial8250_register_8250_port); /** * serial8250_unregister_port - remove a 16x50 serial port at runtime * @line: serial line number * * Remove one serial port. This may not be called from interrupt * context. We hand the port back to the our control. */ void serial8250_unregister_port(int line) { struct uart_8250_port *uart = &serial8250_ports[line]; mutex_lock(&serial_mutex); if (uart->em485) { unsigned long flags; uart_port_lock_irqsave(&uart->port, &flags); serial8250_em485_destroy(uart); uart_port_unlock_irqrestore(&uart->port, flags); } uart_remove_one_port(&serial8250_reg, &uart->port); if (serial8250_isa_devs) { uart->port.flags &= ~UPF_BOOT_AUTOCONF; uart->port.type = PORT_UNKNOWN; uart->port.dev = &serial8250_isa_devs->dev; uart->port.port_id = line; uart->capabilities = 0; serial8250_init_port(uart); serial8250_apply_quirks(uart); uart_add_one_port(&serial8250_reg, &uart->port); } else { uart->port.dev = NULL; } mutex_unlock(&serial_mutex); } EXPORT_SYMBOL(serial8250_unregister_port); static int __init serial8250_init(void) { int ret; if (nr_uarts == 0) return -ENODEV; serial8250_isa_init_ports(); pr_info("Serial: 8250/16550 driver, %d ports, IRQ sharing %s\n", nr_uarts, str_enabled_disabled(share_irqs)); #ifdef CONFIG_SPARC ret = sunserial_register_minors(&serial8250_reg, UART_NR); #else serial8250_reg.nr = UART_NR; ret = uart_register_driver(&serial8250_reg); #endif if (ret) goto out; ret = serial8250_pnp_init(); if (ret) goto unreg_uart_drv; serial8250_isa_devs = platform_device_alloc("serial8250", PLAT8250_DEV_LEGACY); if (!serial8250_isa_devs) { ret = -ENOMEM; goto unreg_pnp; } ret = platform_device_add(serial8250_isa_devs); if (ret) goto put_dev; serial8250_register_ports(&serial8250_reg, &serial8250_isa_devs->dev); ret = platform_driver_register(&serial8250_isa_driver); if (ret == 0) goto out; platform_device_del(serial8250_isa_devs); put_dev: platform_device_put(serial8250_isa_devs); unreg_pnp: serial8250_pnp_exit(); unreg_uart_drv: #ifdef CONFIG_SPARC sunserial_unregister_minors(&serial8250_reg, UART_NR); #else uart_unregister_driver(&serial8250_reg); #endif out: return ret; } static void __exit serial8250_exit(void) { struct platform_device *isa_dev = serial8250_isa_devs; /* * This tells serial8250_unregister_port() not to re-register * the ports (thereby making serial8250_isa_driver permanently * in use.) */ serial8250_isa_devs = NULL; platform_driver_unregister(&serial8250_isa_driver); platform_device_unregister(isa_dev); serial8250_pnp_exit(); #ifdef CONFIG_SPARC sunserial_unregister_minors(&serial8250_reg, UART_NR); #else uart_unregister_driver(&serial8250_reg); #endif } module_init(serial8250_init); module_exit(serial8250_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Generic 8250/16x50 serial driver"); module_param_hw(share_irqs, uint, other, 0644); MODULE_PARM_DESC(share_irqs, "Share IRQs with other non-8250/16x50 devices (unsafe)"); module_param(nr_uarts, uint, 0644); MODULE_PARM_DESC(nr_uarts, "Maximum number of UARTs supported. (1-" __MODULE_STRING(CONFIG_SERIAL_8250_NR_UARTS) ")"); module_param(skip_txen_test, uint, 0644); MODULE_PARM_DESC(skip_txen_test, "Skip checking for the TXEN bug at init time"); #ifdef CONFIG_SERIAL_8250_RSA module_param_hw_array(probe_rsa, ulong, ioport, &probe_rsa_count, 0444); MODULE_PARM_DESC(probe_rsa, "Probe I/O ports for RSA"); #endif MODULE_ALIAS_CHARDEV_MAJOR(TTY_MAJOR); #ifdef CONFIG_SERIAL_8250_DEPRECATED_OPTIONS #ifndef MODULE /* This module was renamed to 8250_core in 3.7. Keep the old "8250" name * working as well for the module options so we don't break people. We * need to keep the names identical and the convenient macros will happily * refuse to let us do that by failing the build with redefinition errors * of global variables. So we stick them inside a dummy function to avoid * those conflicts. The options still get parsed, and the redefined * MODULE_PARAM_PREFIX lets us keep the "8250." syntax alive. * * This is hacky. I'm sorry. */ static void __used s8250_options(void) { #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "8250_core." module_param_cb(share_irqs, ¶m_ops_uint, &share_irqs, 0644); module_param_cb(nr_uarts, ¶m_ops_uint, &nr_uarts, 0644); module_param_cb(skip_txen_test, ¶m_ops_uint, &skip_txen_test, 0644); #ifdef CONFIG_SERIAL_8250_RSA __module_param_call(MODULE_PARAM_PREFIX, probe_rsa, ¶m_array_ops, .arr = &__param_arr_probe_rsa, 0444, -1, 0); #endif } #else MODULE_ALIAS("8250_core"); #endif #endif |
| 3 33 33 33 32 33 33 32 32 32 762 756 749 348 435 738 2 299 34 34 34 34 34 34 34 33 34 34 33 33 33 32 33 33 34 32 34 33 33 34 34 3 3 3 3 3 3 3 6 3 3 3 3 6 3 2 2 3 753 752 754 765 763 761 762 738 742 739 737 738 741 347 416 741 760 3 754 303 299 294 300 115 655 661 657 654 653 656 655 661 196 196 195 195 193 194 3 3 112 113 113 113 110 111 112 107 59 113 112 113 112 2 2 2 2 2 2 2 113 114 113 2 114 78 58 59 59 59 59 59 6359 6373 6313 6326 6330 6302 3 6417 6417 6416 440 432 8 14 13 13 3 21 21 21 6150 92 92 6162 6081 6040 6077 154 216 933 923 216 214 928 205 4 4 4 2 2 4 4 4 4 23 23 23 23 22 23 23 22 23 8 8 7 8 5 5 5 5 5 3 5 8 8 8 18 18 17 17 17 16 18 1 18 1 1 1 4 3 4 3 3 1 1 1 1 1 1 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/file.c * * Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes * * Manage the dynamic fd arrays in the process files_struct. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/close_range.h> #include <net/sock.h> #include "internal.h" unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ #define __const_min(x, y) ((x) < (y) ? (x) : (y)) unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void __free_fdtable(struct fdtable *fdt) { kvfree(fdt->fd); kvfree(fdt->open_fds); kfree(fdt); } static void free_fdtable_rcu(struct rcu_head *rcu) { __free_fdtable(container_of(rcu, struct fdtable, rcu)); } #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int count) { unsigned int cpy, set; cpy = count / BITS_PER_BYTE; set = (nfdt->max_fds - count) / BITS_PER_BYTE; memcpy(nfdt->open_fds, ofdt->open_fds, cpy); memset((char *)nfdt->open_fds + cpy, 0, set); memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy); memset((char *)nfdt->close_on_exec + cpy, 0, set); cpy = BITBIT_SIZE(count); set = BITBIT_SIZE(nfdt->max_fds) - cpy; memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy); memset((char *)nfdt->full_fds_bits + cpy, 0, set); } /* * Copy all file descriptors from the old table to the new, expanded table and * clear the extra space. Called with the files spinlock held for write. */ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) { size_t cpy, set; BUG_ON(nfdt->max_fds < ofdt->max_fds); cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds); } /* * Note how the fdtable bitmap allocations very much have to be a multiple of * BITS_PER_LONG. This is not only because we walk those things in chunks of * 'unsigned long' in some places, but simply because that is how the Linux * kernel bitmaps are defined to work: they are not "bits in an array of bytes", * they are very much "bits in an array of unsigned long". * * The ALIGN(nr, BITS_PER_LONG) here is for clarity: since we just multiplied * by that "1024/sizeof(ptr)" before, we already know there are sufficient * clear low bits. Clang seems to realize that, gcc ends up being confused. * * On a 128-bit machine, the ALIGN() would actually matter. In the meantime, * let's consider it documentation (and maybe a test-case for gcc to improve * its code generation ;) */ static struct fdtable * alloc_fdtable(unsigned int nr) { struct fdtable *fdt; void *data; /* * Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. */ nr /= (1024 / sizeof(struct file *)); nr = roundup_pow_of_two(nr + 1); nr *= (1024 / sizeof(struct file *)); nr = ALIGN(nr, BITS_PER_LONG); /* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. Deal * with that in caller, it's cheaper that way. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly... */ if (unlikely(nr > sysctl_nr_open)) nr = ((sysctl_nr_open - 1) | (BITS_PER_LONG - 1)) + 1; fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; data = kvmalloc(max_t(size_t, 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; data += nr / BITS_PER_BYTE; fdt->full_fds_bits = data; return fdt; out_arr: kvfree(fdt->fd); out_fdt: kfree(fdt); out: return NULL; } /* * Expand the file descriptor table. * This function will allocate a new fdtable and both fd array and fdset, of * the given size. * Return <0 error code on error; 1 on successful completion. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_fdtable(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *new_fdt, *cur_fdt; spin_unlock(&files->file_lock); new_fdt = alloc_fdtable(nr); /* make sure all fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section. */ if (atomic_read(&files->count) > 1) synchronize_rcu(); spin_lock(&files->file_lock); if (!new_fdt) return -ENOMEM; /* * extremely unlikely race - sysctl_nr_open decreased between the check in * caller and alloc_fdtable(). Cheaper to catch it here... */ if (unlikely(new_fdt->max_fds <= nr)) { __free_fdtable(new_fdt); return -EMFILE; } cur_fdt = files_fdtable(files); BUG_ON(nr < cur_fdt->max_fds); copy_fdtable(new_fdt, cur_fdt); rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab) call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in fd_install() */ smp_wmb(); return 1; } /* * Expand files. * This function will expand the file structures, if the requested size exceeds * the current capacity and there is room for expansion. * Return <0 error code on error; 0 when nothing done; 1 when files were * expanded and execution may have blocked. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_files(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *fdt; int expanded = 0; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return expanded; /* Can we expand? */ if (nr >= sysctl_nr_open) return -EMFILE; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); expanded = 1; wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } /* All good, so we try */ files->resize_in_progress = true; expanded = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return expanded; } static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->close_on_exec); } static inline void __clear_close_on_exec(unsigned int fd, struct fdtable *fdt) { if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec); } static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->open_fds); fd /= BITS_PER_LONG; if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits); } static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) { __clear_bit(fd, fdt->open_fds); __clear_bit(fd / BITS_PER_LONG, fdt->full_fds_bits); } static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->open_fds); } static unsigned int count_open_files(struct fdtable *fdt) { unsigned int size = fdt->max_fds; unsigned int i; /* Find the last open fd */ for (i = size / BITS_PER_LONG; i > 0; ) { if (fdt->open_fds[--i]) break; } i = (i + 1) * BITS_PER_LONG; return i; } /* * Note that a sane fdtable size always has to be a multiple of * BITS_PER_LONG, since we have bitmaps that are sized by this. * * 'max_fds' will normally already be properly aligned, but it * turns out that in the close_range() -> __close_range() -> * unshare_fd() -> dup_fd() -> sane_fdtable_size() we can end * up having a 'max_fds' value that isn't already aligned. * * Rather than make close_range() have to worry about this, * just make that BITS_PER_LONG alignment be part of a sane * fdtable size. Becuase that's really what it is. */ static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds) { unsigned int count; count = count_open_files(fdt); if (max_fds < NR_OPEN_DEFAULT) max_fds = NR_OPEN_DEFAULT; return ALIGN(min(count, max_fds), BITS_PER_LONG); } /* * Allocate a new files structure and copy contents from the * passed in files structure. * errorp will be valid only when the returned files_struct is NULL. */ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int *errorp) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; *errorp = -ENOMEM; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) goto out; atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); newf->resize_in_progress = false; init_waitqueue_head(&newf->resize_wait); newf->next_fd = 0; new_fdt = &newf->fdtab; new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, max_fds); /* * Check whether we need to allocate a larger fd array and fd set. */ while (unlikely(open_files > new_fdt->max_fds)) { spin_unlock(&oldf->file_lock); if (new_fdt != &newf->fdtab) __free_fdtable(new_fdt); new_fdt = alloc_fdtable(open_files - 1); if (!new_fdt) { *errorp = -ENOMEM; goto out_release; } /* beyond sysctl_nr_open; nothing to do */ if (unlikely(new_fdt->max_fds < open_files)) { __free_fdtable(new_fdt); *errorp = -EMFILE; goto out_release; } /* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer. */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, max_fds); } copy_fd_bitmaps(new_fdt, old_fdt, open_files); old_fds = old_fdt->fd; new_fds = new_fdt->fd; for (i = open_files; i != 0; i--) { struct file *f = *old_fds++; if (f) { get_file(f); } else { /* * The fd may be claimed in the fd bitmap but not yet * instantiated in the files array if a sibling thread * is partway through open(). So make sure that this * fd is available to the new process. */ __clear_open_fd(open_files - i, new_fdt); } rcu_assign_pointer(*new_fds++, f); } spin_unlock(&oldf->file_lock); /* clear the remainder */ memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); rcu_assign_pointer(newf->fdt, new_fdt); return newf; out_release: kmem_cache_free(files_cachep, newf); out: return NULL; } static struct fdtable *close_files(struct files_struct * files) { /* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the * files structure. */ struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned int i, j = 0; for (;;) { unsigned long set; i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file * file = xchg(&fdt->fd[i], NULL); if (file) { filp_close(file, files); cond_resched(); } } i++; set >>= 1; } } return fdt; } void put_files_struct(struct files_struct *files) { if (atomic_dec_and_test(&files->count)) { struct fdtable *fdt = close_files(files); /* free the arrays if they are not embedded */ if (fdt != &files->fdtab) __free_fdtable(fdt); kmem_cache_free(files_cachep, files); } } void exit_files(struct task_struct *tsk) { struct files_struct * files = tsk->files; if (files) { task_lock(tsk); tsk->files = NULL; task_unlock(tsk); put_files_struct(files); } } struct files_struct init_files = { .count = ATOMIC_INIT(1), .fdt = &init_files.fdtab, .fdtab = { .max_fds = NR_OPEN_DEFAULT, .fd = &init_files.fd_array[0], .close_on_exec = init_files.close_on_exec_init, .open_fds = init_files.open_fds_init, .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), .resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait), }; static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) { unsigned int maxfd = fdt->max_fds; /* always multiple of BITS_PER_LONG */ unsigned int maxbit = maxfd / BITS_PER_LONG; unsigned int bitbit = start / BITS_PER_LONG; bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG; if (bitbit >= maxfd) return maxfd; if (bitbit > start) start = bitbit; return find_next_zero_bit(fdt->open_fds, maxfd, start); } /* * allocate a file descriptor, mark it busy. */ static int alloc_fd(unsigned start, unsigned end, unsigned flags) { struct files_struct *files = current->files; unsigned int fd; int error; struct fdtable *fdt; spin_lock(&files->file_lock); repeat: fdt = files_fdtable(files); fd = start; if (fd < files->next_fd) fd = files->next_fd; if (fd < fdt->max_fds) fd = find_next_fd(fdt, fd); /* * N.B. For clone tasks sharing a files structure, this test * will limit the total number of files that can be opened. */ error = -EMFILE; if (fd >= end) goto out; error = expand_files(files, fd); if (error < 0) goto out; /* * If we needed to expand the fs array we * might have blocked - try again. */ if (error) goto repeat; if (start <= files->next_fd) files->next_fd = fd + 1; __set_open_fd(fd, fdt); if (flags & O_CLOEXEC) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); error = fd; #if 1 /* Sanity check */ if (rcu_access_pointer(fdt->fd[fd]) != NULL) { printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd); rcu_assign_pointer(fdt->fd[fd], NULL); } #endif out: spin_unlock(&files->file_lock); return error; } int __get_unused_fd_flags(unsigned flags, unsigned long nofile) { return alloc_fd(0, nofile, flags); } int get_unused_fd_flags(unsigned flags) { return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE)); } EXPORT_SYMBOL(get_unused_fd_flags); static void __put_unused_fd(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = files_fdtable(files); __clear_open_fd(fd, fdt); if (fd < files->next_fd) files->next_fd = fd; } void put_unused_fd(unsigned int fd) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); } EXPORT_SYMBOL(put_unused_fd); /* * Install a file pointer in the fd array. * * The VFS is full of places where we drop the files lock between * setting the open_fds bitmap and installing the file in the file * array. At any such point, we are vulnerable to a dup2() race * installing a file in the array before us. We need to detect this and * fput() the struct file we are about to overwrite in this case. * * It should never happen - if we allow dup2() do it, _really_ bad things * will follow. * * This consumes the "file" refcount, so callers should treat it * as if they had called fput(file). */ void fd_install(unsigned int fd, struct file *file) { struct files_struct *files = current->files; struct fdtable *fdt; if (WARN_ON_ONCE(unlikely(file->f_mode & FMODE_BACKING))) return; rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); spin_unlock(&files->file_lock); return; } /* coupled with smp_wmb() in expand_fdtable() */ smp_rmb(); fdt = rcu_dereference_sched(files->fdt); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); rcu_read_unlock_sched(); } EXPORT_SYMBOL(fd_install); /** * file_close_fd_locked - return file associated with fd * @files: file struct to retrieve file from * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Context: files_lock must be held. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd_locked(struct files_struct *files, unsigned fd) { struct fdtable *fdt = files_fdtable(files); struct file *file; lockdep_assert_held(&files->file_lock); if (fd >= fdt->max_fds) return NULL; fd = array_index_nospec(fd, fdt->max_fds); file = fdt->fd[fd]; if (file) { rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); } return file; } int close_fd(unsigned fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); if (!file) return -EBADF; return filp_close(file, files); } EXPORT_SYMBOL(close_fd); /* for ksys_close() */ /** * last_fd - return last valid index into fd table * @fdt: File descriptor table. * * Context: Either rcu read lock or files_lock must be held. * * Returns: Last valid index into fdtable. */ static inline unsigned last_fd(struct fdtable *fdt) { return fdt->max_fds - 1; } static inline void __range_cloexec(struct files_struct *cur_fds, unsigned int fd, unsigned int max_fd) { struct fdtable *fdt; /* make sure we're using the correct maximum value */ spin_lock(&cur_fds->file_lock); fdt = files_fdtable(cur_fds); max_fd = min(last_fd(fdt), max_fd); if (fd <= max_fd) bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1); spin_unlock(&cur_fds->file_lock); } static inline void __range_close(struct files_struct *files, unsigned int fd, unsigned int max_fd) { struct file *file; unsigned n; spin_lock(&files->file_lock); n = last_fd(files_fdtable(files)); max_fd = min(max_fd, n); for (; fd <= max_fd; fd++) { file = file_close_fd_locked(files, fd); if (file) { spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } else if (need_resched()) { spin_unlock(&files->file_lock); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } /** * __close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * @flags: CLOSE_RANGE flags. * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. */ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags) { struct task_struct *me = current; struct files_struct *cur_fds = me->files, *fds = NULL; if (flags & ~(CLOSE_RANGE_UNSHARE | CLOSE_RANGE_CLOEXEC)) return -EINVAL; if (fd > max_fd) return -EINVAL; if (flags & CLOSE_RANGE_UNSHARE) { int ret; unsigned int max_unshare_fds = NR_OPEN_MAX; /* * If the caller requested all fds to be made cloexec we always * copy all of the file descriptors since they still want to * use them. */ if (!(flags & CLOSE_RANGE_CLOEXEC)) { /* * If the requested range is greater than the current * maximum, we're closing everything so only copy all * file descriptors beneath the lowest file descriptor. */ rcu_read_lock(); if (max_fd >= last_fd(files_fdtable(cur_fds))) max_unshare_fds = fd; rcu_read_unlock(); } ret = unshare_fd(CLONE_FILES, max_unshare_fds, &fds); if (ret) return ret; /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below. */ if (fds) swap(cur_fds, fds); } if (flags & CLOSE_RANGE_CLOEXEC) __range_cloexec(cur_fds, fd, max_fd); else __range_close(cur_fds, fd, max_fd); if (fds) { /* * We're done closing the files we were supposed to. Time to install * the new file descriptor table and drop the old one. */ task_lock(me); me->files = cur_fds; task_unlock(me); put_files_struct(fds); } return 0; } /** * file_close_fd - return file associated with fd * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd(unsigned int fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); return file; } void do_close_on_exec(struct files_struct *files) { unsigned i; struct fdtable *fdt; /* exec unshares first */ spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; unsigned fd = i * BITS_PER_LONG; fdt = files_fdtable(files); if (fd >= fdt->max_fds) break; set = fdt->close_on_exec[i]; if (!set) continue; fdt->close_on_exec[i] = 0; for ( ; set ; fd++, set >>= 1) { struct file *file; if (!(set & 1)) continue; file = fdt->fd[fd]; if (!file) continue; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } static struct file *__get_file_rcu(struct file __rcu **f) { struct file __rcu *file; struct file __rcu *file_reloaded; struct file __rcu *file_reloaded_cmp; file = rcu_dereference_raw(*f); if (!file) return NULL; if (unlikely(!atomic_long_inc_not_zero(&file->f_count))) return ERR_PTR(-EAGAIN); file_reloaded = rcu_dereference_raw(*f); /* * Ensure that all accesses have a dependency on the load from * rcu_dereference_raw() above so we get correct ordering * between reuse/allocation and the pointer check below. */ file_reloaded_cmp = file_reloaded; OPTIMIZER_HIDE_VAR(file_reloaded_cmp); /* * atomic_long_inc_not_zero() above provided a full memory * barrier when we acquired a reference. * * This is paired with the write barrier from assigning to the * __rcu protected file pointer so that if that pointer still * matches the current file, we know we have successfully * acquired a reference to the right file. * * If the pointers don't match the file has been reallocated by * SLAB_TYPESAFE_BY_RCU. */ if (file == file_reloaded_cmp) return file_reloaded; fput(file); return ERR_PTR(-EAGAIN); } /** * get_file_rcu - try go get a reference to a file under rcu * @f: the file to get a reference on * * This function tries to get a reference on @f carefully verifying that * @f hasn't been reused. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_rcu(struct file __rcu **f) { for (;;) { struct file __rcu *file; file = __get_file_rcu(f); if (!IS_ERR(file)) return file; } } EXPORT_SYMBOL_GPL(get_file_rcu); /** * get_file_active - try go get a reference to a file * @f: the file to get a reference on * * In contast to get_file_rcu() the pointer itself isn't part of the * reference counting. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_active(struct file **f) { struct file __rcu *file; rcu_read_lock(); file = __get_file_rcu(f); rcu_read_unlock(); if (IS_ERR(file)) file = NULL; return file; } EXPORT_SYMBOL_GPL(get_file_active); static inline struct file *__fget_files_rcu(struct files_struct *files, unsigned int fd, fmode_t mask) { for (;;) { struct file *file; struct fdtable *fdt = rcu_dereference_raw(files->fdt); struct file __rcu **fdentry; unsigned long nospec_mask; /* Mask is a 0 for invalid fd's, ~0 for valid ones */ nospec_mask = array_index_mask_nospec(fd, fdt->max_fds); /* * fdentry points to the 'fd' offset, or fdt->fd[0]. * Loading from fdt->fd[0] is always safe, because the * array always exists. */ fdentry = fdt->fd + (fd & nospec_mask); /* Do the load, then mask any invalid result */ file = rcu_dereference_raw(*fdentry); file = (void *)(nospec_mask & (unsigned long)file); if (unlikely(!file)) return NULL; /* * Ok, we have a file pointer that was valid at * some point, but it might have become stale since. * * We need to confirm it by incrementing the refcount * and then check the lookup again. * * atomic_long_inc_not_zero() gives us a full memory * barrier. We only really need an 'acquire' one to * protect the loads below, but we don't have that. */ if (unlikely(!atomic_long_inc_not_zero(&file->f_count))) continue; /* * Such a race can take two forms: * * (a) the file ref already went down to zero and the * file hasn't been reused yet or the file count * isn't zero but the file has already been reused. * * (b) the file table entry has changed under us. * Note that we don't need to re-check the 'fdt->fd' * pointer having changed, because it always goes * hand-in-hand with 'fdt'. * * If so, we need to put our ref and try again. */ if (unlikely(file != rcu_dereference_raw(*fdentry)) || unlikely(rcu_dereference_raw(files->fdt) != fdt)) { fput(file); continue; } /* * This isn't the file we're looking for or we're not * allowed to get a reference to it. */ if (unlikely(file->f_mode & mask)) { fput(file); return NULL; } /* * Ok, we have a ref to the file, and checked that it * still exists. */ return file; } } static struct file *__fget_files(struct files_struct *files, unsigned int fd, fmode_t mask) { struct file *file; rcu_read_lock(); file = __fget_files_rcu(files, fd, mask); rcu_read_unlock(); return file; } static inline struct file *__fget(unsigned int fd, fmode_t mask) { return __fget_files(current->files, fd, mask); } struct file *fget(unsigned int fd) { return __fget(fd, FMODE_PATH); } EXPORT_SYMBOL(fget); struct file *fget_raw(unsigned int fd) { return __fget(fd, 0); } EXPORT_SYMBOL(fget_raw); struct file *fget_task(struct task_struct *task, unsigned int fd) { struct file *file = NULL; task_lock(task); if (task->files) file = __fget_files(task->files, fd, 0); task_unlock(task); return file; } struct file *lookup_fdget_rcu(unsigned int fd) { return __fget_files_rcu(current->files, fd, 0); } EXPORT_SYMBOL_GPL(lookup_fdget_rcu); struct file *task_lookup_fdget_rcu(struct task_struct *task, unsigned int fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; struct file *file = NULL; task_lock(task); files = task->files; if (files) file = __fget_files_rcu(files, fd, 0); task_unlock(task); return file; } struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *ret_fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; unsigned int fd = *ret_fd; struct file *file = NULL; task_lock(task); files = task->files; if (files) { for (; fd < files_fdtable(files)->max_fds; fd++) { file = __fget_files_rcu(files, fd, 0); if (file) break; } } task_unlock(task); *ret_fd = fd; return file; } EXPORT_SYMBOL(task_lookup_next_fdget_rcu); /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. * * You can use this instead of fget if you satisfy all of the following * conditions: * 1) You must call fput_light before exiting the syscall and returning control * to userspace (i.e. you cannot remember the returned struct file * after * returning to userspace). * 2) You must not call filp_close on the returned struct file * in between * calls to fget_light and fput_light. * 3) You must not clone the current task in between the calls to fget_light * and fput_light. * * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. */ static unsigned long __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; /* * If another thread is concurrently calling close_fd() followed * by put_files_struct(), we must not observe the old table * entry combined with the new refcount - otherwise we could * return a file that is concurrently being freed. * * atomic_read_acquire() pairs with atomic_dec_and_test() in * put_files_struct(). */ if (likely(atomic_read_acquire(&files->count) == 1)) { file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) return 0; return (unsigned long)file; } else { file = __fget_files(files, fd, mask); if (!file) return 0; return FDPUT_FPUT | (unsigned long)file; } } unsigned long __fdget(unsigned int fd) { return __fget_light(fd, FMODE_PATH); } EXPORT_SYMBOL(__fdget); unsigned long __fdget_raw(unsigned int fd) { return __fget_light(fd, 0); } /* * Try to avoid f_pos locking. We only need it if the * file is marked for FMODE_ATOMIC_POS, and it can be * accessed multiple ways. * * Always do it for directories, because pidfd_getfd() * can make a file accessible even if it otherwise would * not be, and for directories this is a correctness * issue, not a "POSIX requirement". */ static inline bool file_needs_f_pos_lock(struct file *file) { return (file->f_mode & FMODE_ATOMIC_POS) && (file_count(file) > 1 || file->f_op->iterate_shared); } unsigned long __fdget_pos(unsigned int fd) { unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); if (file && file_needs_f_pos_lock(file)) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } return v; } void __f_unlock_pos(struct file *f) { mutex_unlock(&f->f_pos_lock); } /* * We only lock f_pos if we have threads or if the file might be * shared with another process. In both cases we'll have an elevated * file count (done either by fdget() or by fork()). */ void set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); if (flag) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); spin_unlock(&files->file_lock); } bool get_close_on_exec(unsigned int fd) { bool res; rcu_read_lock(); res = close_on_exec(fd, current->files); rcu_read_unlock(); return res; } static int do_dup2(struct files_struct *files, struct file *file, unsigned fd, unsigned flags) __releases(&files->file_lock) { struct file *tofree; struct fdtable *fdt; /* * We need to detect attempts to do dup2() over allocated but still * not finished descriptor. NB: OpenBSD avoids that at the price of * extra work in their equivalent of fget() - they insert struct * file immediately after grabbing descriptor, mark it larval if * more work (e.g. actual opening) is needed and make sure that * fget() treats larval files as absent. Potentially interesting, * but while extra work in fget() is trivial, locking implications * and amount of surgery on open()-related paths in VFS are not. * FreeBSD fails with -EBADF in the same situation, NetBSD "solution" * deadlocks in rather amusing ways, AFAICS. All of that is out of * scope of POSIX or SUS, since neither considers shared descriptor * tables and this condition does not arise without those. */ fdt = files_fdtable(files); tofree = fdt->fd[fd]; if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; get_file(file); rcu_assign_pointer(fdt->fd[fd], file); __set_open_fd(fd, fdt); if (flags & O_CLOEXEC) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); spin_unlock(&files->file_lock); if (tofree) filp_close(tofree, files); return fd; Ebusy: spin_unlock(&files->file_lock); return -EBUSY; } int replace_fd(unsigned fd, struct file *file, unsigned flags) { int err; struct files_struct *files = current->files; if (!file) return close_fd(fd); if (fd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, fd); if (unlikely(err < 0)) goto out_unlock; return do_dup2(files, file, fd, flags); out_unlock: spin_unlock(&files->file_lock); return err; } /** * receive_fd() - Install received file into file descriptor table * @file: struct file that was received from another process * @ufd: __user pointer to write new fd number to * @o_flags: the O_* flags to apply to the new fd entry * * Installs a received file into the file descriptor table, with appropriate * checks and count updates. Optionally writes the fd number to userspace, if * @ufd is non-NULL. * * This helper handles its own reference counting of the incoming * struct file. * * Returns newly install fd or -ve on error. */ int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags) { int new_fd; int error; error = security_file_receive(file); if (error) return error; new_fd = get_unused_fd_flags(o_flags); if (new_fd < 0) return new_fd; if (ufd) { error = put_user(new_fd, ufd); if (error) { put_unused_fd(new_fd); return error; } } fd_install(new_fd, get_file(file)); __receive_sock(file); return new_fd; } EXPORT_SYMBOL_GPL(receive_fd); int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags) { int error; error = security_file_receive(file); if (error) return error; error = replace_fd(new_fd, file, o_flags); if (error) return error; __receive_sock(file); return new_fd; } static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; struct file *file; struct files_struct *files = current->files; if ((flags & ~O_CLOEXEC) != 0) return -EINVAL; if (unlikely(oldfd == newfd)) return -EINVAL; if (newfd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, newfd); file = files_lookup_fd_locked(files, oldfd); if (unlikely(!file)) goto Ebadf; if (unlikely(err < 0)) { if (err == -EMFILE) goto Ebadf; goto out_unlock; } return do_dup2(files, file, newfd, flags); Ebadf: err = -EBADF; out_unlock: spin_unlock(&files->file_lock); return err; } SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) { return ksys_dup3(oldfd, newfd, flags); } SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; struct file *f; int retval = oldfd; rcu_read_lock(); f = __fget_files_rcu(files, oldfd, 0); if (!f) retval = -EBADF; rcu_read_unlock(); if (f) fput(f); return retval; } return ksys_dup3(oldfd, newfd, 0); } SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); if (file) { ret = get_unused_fd_flags(0); if (ret >= 0) fd_install(ret, file); else fput(file); } return ret; } int f_dupfd(unsigned int from, struct file *file, unsigned flags) { unsigned long nofile = rlimit(RLIMIT_NOFILE); int err; if (from >= nofile) return -EINVAL; err = alloc_fd(from, nofile, flags); if (err >= 0) { get_file(file); fd_install(err, file); } return err; } int iterate_fd(struct files_struct *files, unsigned n, int (*f)(const void *, struct file *, unsigned), const void *p) { struct fdtable *fdt; int res = 0; if (!files) return 0; spin_lock(&files->file_lock); for (fdt = files_fdtable(files); n < fdt->max_fds; n++) { struct file *file; file = rcu_dereference_check_fdtable(files, fdt->fd[n]); if (!file) continue; res = f(p, file, n); if (res) break; } spin_unlock(&files->file_lock); return res; } EXPORT_SYMBOL(iterate_fd); |
| 1 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/cpumask.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> #include <linux/proc_fs.h> #include <linux/sched.h> #include <linux/sched/stat.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/time_namespace.h> #include <linux/irqnr.h> #include <linux/sched/cputime.h> #include <linux/tick.h> #ifndef arch_irq_stat_cpu #define arch_irq_stat_cpu(cpu) 0 #endif #ifndef arch_irq_stat #define arch_irq_stat() 0 #endif u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) { u64 idle, idle_usecs = -1ULL; if (cpu_online(cpu)) idle_usecs = get_cpu_idle_time_us(cpu, NULL); if (idle_usecs == -1ULL) /* !NO_HZ or cpu offline so we can rely on cpustat.idle */ idle = kcs->cpustat[CPUTIME_IDLE]; else idle = idle_usecs * NSEC_PER_USEC; return idle; } static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu) { u64 iowait, iowait_usecs = -1ULL; if (cpu_online(cpu)) iowait_usecs = get_cpu_iowait_time_us(cpu, NULL); if (iowait_usecs == -1ULL) /* !NO_HZ or cpu offline so we can rely on cpustat.iowait */ iowait = kcs->cpustat[CPUTIME_IOWAIT]; else iowait = iowait_usecs * NSEC_PER_USEC; return iowait; } static void show_irq_gap(struct seq_file *p, unsigned int gap) { static const char zeros[] = " 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0"; while (gap > 0) { unsigned int inc; inc = min_t(unsigned int, gap, ARRAY_SIZE(zeros) / 2); seq_write(p, zeros, 2 * inc); gap -= inc; } } static void show_all_irqs(struct seq_file *p) { unsigned int i, next = 0; for_each_active_irq(i) { show_irq_gap(p, i - next); seq_put_decimal_ull(p, " ", kstat_irqs_usr(i)); next = i + 1; } show_irq_gap(p, nr_irqs - next); } static int show_stat(struct seq_file *p, void *v) { int i, j; u64 user, nice, system, idle, iowait, irq, softirq, steal; u64 guest, guest_nice; u64 sum = 0; u64 sum_softirq = 0; unsigned int per_softirq_sums[NR_SOFTIRQS] = {0}; struct timespec64 boottime; user = nice = system = idle = iowait = irq = softirq = steal = 0; guest = guest_nice = 0; getboottime64(&boottime); /* shift boot timestamp according to the timens offset */ timens_sub_boottime(&boottime); for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; kcpustat_cpu_fetch(&kcpustat, i); user += cpustat[CPUTIME_USER]; nice += cpustat[CPUTIME_NICE]; system += cpustat[CPUTIME_SYSTEM]; idle += get_idle_time(&kcpustat, i); iowait += get_iowait_time(&kcpustat, i); irq += cpustat[CPUTIME_IRQ]; softirq += cpustat[CPUTIME_SOFTIRQ]; steal += cpustat[CPUTIME_STEAL]; guest += cpustat[CPUTIME_GUEST]; guest_nice += cpustat[CPUTIME_GUEST_NICE]; sum += kstat_cpu_irqs_sum(i); sum += arch_irq_stat_cpu(i); for (j = 0; j < NR_SOFTIRQS; j++) { unsigned int softirq_stat = kstat_softirqs_cpu(j, i); per_softirq_sums[j] += softirq_stat; sum_softirq += softirq_stat; } } sum += arch_irq_stat(); seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(user)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(system)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice)); seq_putc(p, '\n'); for_each_online_cpu(i) { struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; kcpustat_cpu_fetch(&kcpustat, i); /* Copy values here to work around gcc-2.95.3, gcc-2.96 */ user = cpustat[CPUTIME_USER]; nice = cpustat[CPUTIME_NICE]; system = cpustat[CPUTIME_SYSTEM]; idle = get_idle_time(&kcpustat, i); iowait = get_iowait_time(&kcpustat, i); irq = cpustat[CPUTIME_IRQ]; softirq = cpustat[CPUTIME_SOFTIRQ]; steal = cpustat[CPUTIME_STEAL]; guest = cpustat[CPUTIME_GUEST]; guest_nice = cpustat[CPUTIME_GUEST_NICE]; seq_printf(p, "cpu%d", i); seq_put_decimal_ull(p, " ", nsec_to_clock_t(user)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(system)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice)); seq_putc(p, '\n'); } seq_put_decimal_ull(p, "intr ", (unsigned long long)sum); show_all_irqs(p); seq_printf(p, "\nctxt %llu\n" "btime %llu\n" "processes %lu\n" "procs_running %u\n" "procs_blocked %u\n", nr_context_switches(), (unsigned long long)boottime.tv_sec, total_forks, nr_running(), nr_iowait()); seq_put_decimal_ull(p, "softirq ", (unsigned long long)sum_softirq); for (i = 0; i < NR_SOFTIRQS; i++) seq_put_decimal_ull(p, " ", per_softirq_sums[i]); seq_putc(p, '\n'); return 0; } static int stat_open(struct inode *inode, struct file *file) { unsigned int size = 1024 + 128 * num_online_cpus(); /* minimum size to display an interrupt count : 2 bytes */ size += 2 * nr_irqs; return single_open_size(file, show_stat, NULL, size); } static const struct proc_ops stat_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = stat_open, .proc_read_iter = seq_read_iter, .proc_lseek = seq_lseek, .proc_release = single_release, }; static int __init proc_stat_init(void) { proc_create("stat", 0, NULL, &stat_proc_ops); return 0; } fs_initcall(proc_stat_init); |
| 1 1 1 1 1 1 5 3 1 1 2 1 3 5 5 5 5 5 3 3 3 5 5 3 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 2 7 7 7 6 7 5 5 5 5 5 2 1 5 5 5 5 1 4 2 1 1 7 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * The NFC Controller Interface is the communication protocol between an * NFC Controller (NFCC) and a Device Host (DH). * * Copyright (C) 2011 Texas Instruments, Inc. * Copyright (C) 2014 Marvell International Ltd. * * Written by Ilan Elias <ilane@ti.com> * * Acknowledgements: * This file is based on hci_core.c, which was written * by Maxim Krasnyansky. */ #define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__ #include <linux/module.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/workqueue.h> #include <linux/completion.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/bitops.h> #include <linux/skbuff.h> #include <linux/kcov.h> #include "../nfc.h" #include <net/nfc/nci.h> #include <net/nfc/nci_core.h> #include <linux/nfc.h> struct core_conn_create_data { int length; struct nci_core_conn_create_cmd *cmd; }; static void nci_cmd_work(struct work_struct *work); static void nci_rx_work(struct work_struct *work); static void nci_tx_work(struct work_struct *work); struct nci_conn_info *nci_get_conn_info_by_conn_id(struct nci_dev *ndev, int conn_id) { struct nci_conn_info *conn_info; list_for_each_entry(conn_info, &ndev->conn_info_list, list) { if (conn_info->conn_id == conn_id) return conn_info; } return NULL; } int nci_get_conn_info_by_dest_type_params(struct nci_dev *ndev, u8 dest_type, const struct dest_spec_params *params) { const struct nci_conn_info *conn_info; list_for_each_entry(conn_info, &ndev->conn_info_list, list) { if (conn_info->dest_type == dest_type) { if (!params) return conn_info->conn_id; if (params->id == conn_info->dest_params->id && params->protocol == conn_info->dest_params->protocol) return conn_info->conn_id; } } return -EINVAL; } EXPORT_SYMBOL(nci_get_conn_info_by_dest_type_params); /* ---- NCI requests ---- */ void nci_req_complete(struct nci_dev *ndev, int result) { if (ndev->req_status == NCI_REQ_PEND) { ndev->req_result = result; ndev->req_status = NCI_REQ_DONE; complete(&ndev->req_completion); } } EXPORT_SYMBOL(nci_req_complete); static void nci_req_cancel(struct nci_dev *ndev, int err) { if (ndev->req_status == NCI_REQ_PEND) { ndev->req_result = err; ndev->req_status = NCI_REQ_CANCELED; complete(&ndev->req_completion); } } /* Execute request and wait for completion. */ static int __nci_request(struct nci_dev *ndev, void (*req)(struct nci_dev *ndev, const void *opt), const void *opt, __u32 timeout) { int rc = 0; long completion_rc; ndev->req_status = NCI_REQ_PEND; reinit_completion(&ndev->req_completion); req(ndev, opt); completion_rc = wait_for_completion_interruptible_timeout(&ndev->req_completion, timeout); pr_debug("wait_for_completion return %ld\n", completion_rc); if (completion_rc > 0) { switch (ndev->req_status) { case NCI_REQ_DONE: rc = nci_to_errno(ndev->req_result); break; case NCI_REQ_CANCELED: rc = -ndev->req_result; break; default: rc = -ETIMEDOUT; break; } } else { pr_err("wait_for_completion_interruptible_timeout failed %ld\n", completion_rc); rc = ((completion_rc == 0) ? (-ETIMEDOUT) : (completion_rc)); } ndev->req_status = ndev->req_result = 0; return rc; } inline int nci_request(struct nci_dev *ndev, void (*req)(struct nci_dev *ndev, const void *opt), const void *opt, __u32 timeout) { int rc; /* Serialize all requests */ mutex_lock(&ndev->req_lock); /* check the state after obtaing the lock against any races * from nci_close_device when the device gets removed. */ if (test_bit(NCI_UP, &ndev->flags)) rc = __nci_request(ndev, req, opt, timeout); else rc = -ENETDOWN; mutex_unlock(&ndev->req_lock); return rc; } static void nci_reset_req(struct nci_dev *ndev, const void *opt) { struct nci_core_reset_cmd cmd; cmd.reset_type = NCI_RESET_TYPE_RESET_CONFIG; nci_send_cmd(ndev, NCI_OP_CORE_RESET_CMD, 1, &cmd); } static void nci_init_req(struct nci_dev *ndev, const void *opt) { u8 plen = 0; if (opt) plen = sizeof(struct nci_core_init_v2_cmd); nci_send_cmd(ndev, NCI_OP_CORE_INIT_CMD, plen, opt); } static void nci_init_complete_req(struct nci_dev *ndev, const void *opt) { struct nci_rf_disc_map_cmd cmd; struct disc_map_config *cfg = cmd.mapping_configs; __u8 *num = &cmd.num_mapping_configs; int i; /* set rf mapping configurations */ *num = 0; /* by default mapping is set to NCI_RF_INTERFACE_FRAME */ for (i = 0; i < ndev->num_supported_rf_interfaces; i++) { if (ndev->supported_rf_interfaces[i] == NCI_RF_INTERFACE_ISO_DEP) { cfg[*num].rf_protocol = NCI_RF_PROTOCOL_ISO_DEP; cfg[*num].mode = NCI_DISC_MAP_MODE_POLL | NCI_DISC_MAP_MODE_LISTEN; cfg[*num].rf_interface = NCI_RF_INTERFACE_ISO_DEP; (*num)++; } else if (ndev->supported_rf_interfaces[i] == NCI_RF_INTERFACE_NFC_DEP) { cfg[*num].rf_protocol = NCI_RF_PROTOCOL_NFC_DEP; cfg[*num].mode = NCI_DISC_MAP_MODE_POLL | NCI_DISC_MAP_MODE_LISTEN; cfg[*num].rf_interface = NCI_RF_INTERFACE_NFC_DEP; (*num)++; } if (*num == NCI_MAX_NUM_MAPPING_CONFIGS) break; } nci_send_cmd(ndev, NCI_OP_RF_DISCOVER_MAP_CMD, (1 + ((*num) * sizeof(struct disc_map_config))), &cmd); } struct nci_set_config_param { __u8 id; size_t len; const __u8 *val; }; static void nci_set_config_req(struct nci_dev *ndev, const void *opt) { const struct nci_set_config_param *param = opt; struct nci_core_set_config_cmd cmd; BUG_ON(param->len > NCI_MAX_PARAM_LEN); cmd.num_params = 1; cmd.param.id = param->id; cmd.param.len = param->len; memcpy(cmd.param.val, param->val, param->len); nci_send_cmd(ndev, NCI_OP_CORE_SET_CONFIG_CMD, (3 + param->len), &cmd); } struct nci_rf_discover_param { __u32 im_protocols; __u32 tm_protocols; }; static void nci_rf_discover_req(struct nci_dev *ndev, const void *opt) { const struct nci_rf_discover_param *param = opt; struct nci_rf_disc_cmd cmd; cmd.num_disc_configs = 0; if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS) && (param->im_protocols & NFC_PROTO_JEWEL_MASK || param->im_protocols & NFC_PROTO_MIFARE_MASK || param->im_protocols & NFC_PROTO_ISO14443_MASK || param->im_protocols & NFC_PROTO_NFC_DEP_MASK)) { cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode = NCI_NFC_A_PASSIVE_POLL_MODE; cmd.disc_configs[cmd.num_disc_configs].frequency = 1; cmd.num_disc_configs++; } if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS) && (param->im_protocols & NFC_PROTO_ISO14443_B_MASK)) { cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode = NCI_NFC_B_PASSIVE_POLL_MODE; cmd.disc_configs[cmd.num_disc_configs].frequency = 1; cmd.num_disc_configs++; } if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS) && (param->im_protocols & NFC_PROTO_FELICA_MASK || param->im_protocols & NFC_PROTO_NFC_DEP_MASK)) { cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode = NCI_NFC_F_PASSIVE_POLL_MODE; cmd.disc_configs[cmd.num_disc_configs].frequency = 1; cmd.num_disc_configs++; } if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS) && (param->im_protocols & NFC_PROTO_ISO15693_MASK)) { cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode = NCI_NFC_V_PASSIVE_POLL_MODE; cmd.disc_configs[cmd.num_disc_configs].frequency = 1; cmd.num_disc_configs++; } if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS - 1) && (param->tm_protocols & NFC_PROTO_NFC_DEP_MASK)) { cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode = NCI_NFC_A_PASSIVE_LISTEN_MODE; cmd.disc_configs[cmd.num_disc_configs].frequency = 1; cmd.num_disc_configs++; cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode = NCI_NFC_F_PASSIVE_LISTEN_MODE; cmd.disc_configs[cmd.num_disc_configs].frequency = 1; cmd.num_disc_configs++; } nci_send_cmd(ndev, NCI_OP_RF_DISCOVER_CMD, (1 + (cmd.num_disc_configs * sizeof(struct disc_config))), &cmd); } struct nci_rf_discover_select_param { __u8 rf_discovery_id; __u8 rf_protocol; }; static void nci_rf_discover_select_req(struct nci_dev *ndev, const void *opt) { const struct nci_rf_discover_select_param *param = opt; struct nci_rf_discover_select_cmd cmd; cmd.rf_discovery_id = param->rf_discovery_id; cmd.rf_protocol = param->rf_protocol; switch (cmd.rf_protocol) { case NCI_RF_PROTOCOL_ISO_DEP: cmd.rf_interface = NCI_RF_INTERFACE_ISO_DEP; break; case NCI_RF_PROTOCOL_NFC_DEP: cmd.rf_interface = NCI_RF_INTERFACE_NFC_DEP; break; default: cmd.rf_interface = NCI_RF_INTERFACE_FRAME; break; } nci_send_cmd(ndev, NCI_OP_RF_DISCOVER_SELECT_CMD, sizeof(struct nci_rf_discover_select_cmd), &cmd); } static void nci_rf_deactivate_req(struct nci_dev *ndev, const void *opt) { struct nci_rf_deactivate_cmd cmd; cmd.type = (unsigned long)opt; nci_send_cmd(ndev, NCI_OP_RF_DEACTIVATE_CMD, sizeof(struct nci_rf_deactivate_cmd), &cmd); } struct nci_cmd_param { __u16 opcode; size_t len; const __u8 *payload; }; static void nci_generic_req(struct nci_dev *ndev, const void *opt) { const struct nci_cmd_param *param = opt; nci_send_cmd(ndev, param->opcode, param->len, param->payload); } int nci_prop_cmd(struct nci_dev *ndev, __u8 oid, size_t len, const __u8 *payload) { struct nci_cmd_param param; param.opcode = nci_opcode_pack(NCI_GID_PROPRIETARY, oid); param.len = len; param.payload = payload; return __nci_request(ndev, nci_generic_req, ¶m, msecs_to_jiffies(NCI_CMD_TIMEOUT)); } EXPORT_SYMBOL(nci_prop_cmd); int nci_core_cmd(struct nci_dev *ndev, __u16 opcode, size_t len, const __u8 *payload) { struct nci_cmd_param param; param.opcode = opcode; param.len = len; param.payload = payload; return __nci_request(ndev, nci_generic_req, ¶m, msecs_to_jiffies(NCI_CMD_TIMEOUT)); } EXPORT_SYMBOL(nci_core_cmd); int nci_core_reset(struct nci_dev *ndev) { return __nci_request(ndev, nci_reset_req, (void *)0, msecs_to_jiffies(NCI_RESET_TIMEOUT)); } EXPORT_SYMBOL(nci_core_reset); int nci_core_init(struct nci_dev *ndev) { return __nci_request(ndev, nci_init_req, (void *)0, msecs_to_jiffies(NCI_INIT_TIMEOUT)); } EXPORT_SYMBOL(nci_core_init); struct nci_loopback_data { u8 conn_id; struct sk_buff *data; }; static void nci_send_data_req(struct nci_dev *ndev, const void *opt) { const struct nci_loopback_data *data = opt; nci_send_data(ndev, data->conn_id, data->data); } static void nci_nfcc_loopback_cb(void *context, struct sk_buff *skb, int err) { struct nci_dev *ndev = (struct nci_dev *)context; struct nci_conn_info *conn_info; conn_info = nci_get_conn_info_by_conn_id(ndev, ndev->cur_conn_id); if (!conn_info) { nci_req_complete(ndev, NCI_STATUS_REJECTED); return; } conn_info->rx_skb = skb; nci_req_complete(ndev, NCI_STATUS_OK); } int nci_nfcc_loopback(struct nci_dev *ndev, const void *data, size_t data_len, struct sk_buff **resp) { int r; struct nci_loopback_data loopback_data; struct nci_conn_info *conn_info; struct sk_buff *skb; int conn_id = nci_get_conn_info_by_dest_type_params(ndev, NCI_DESTINATION_NFCC_LOOPBACK, NULL); if (conn_id < 0) { r = nci_core_conn_create(ndev, NCI_DESTINATION_NFCC_LOOPBACK, 0, 0, NULL); if (r != NCI_STATUS_OK) return r; conn_id = nci_get_conn_info_by_dest_type_params(ndev, NCI_DESTINATION_NFCC_LOOPBACK, NULL); } conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id); if (!conn_info) return -EPROTO; /* store cb and context to be used on receiving data */ conn_info->data_exchange_cb = nci_nfcc_loopback_cb; conn_info->data_exchange_cb_context = ndev; skb = nci_skb_alloc(ndev, NCI_DATA_HDR_SIZE + data_len, GFP_KERNEL); if (!skb) return -ENOMEM; skb_reserve(skb, NCI_DATA_HDR_SIZE); skb_put_data(skb, data, data_len); loopback_data.conn_id = conn_id; loopback_data.data = skb; ndev->cur_conn_id = conn_id; r = nci_request(ndev, nci_send_data_req, &loopback_data, msecs_to_jiffies(NCI_DATA_TIMEOUT)); if (r == NCI_STATUS_OK && resp) *resp = conn_info->rx_skb; return r; } EXPORT_SYMBOL(nci_nfcc_loopback); static int nci_open_device(struct nci_dev *ndev) { int rc = 0; mutex_lock(&ndev->req_lock); if (test_bit(NCI_UNREG, &ndev->flags)) { rc = -ENODEV; goto done; } if (test_bit(NCI_UP, &ndev->flags)) { rc = -EALREADY; goto done; } if (ndev->ops->open(ndev)) { rc = -EIO; goto done; } atomic_set(&ndev->cmd_cnt, 1); set_bit(NCI_INIT, &ndev->flags); if (ndev->ops->init) rc = ndev->ops->init(ndev); if (!rc) { rc = __nci_request(ndev, nci_reset_req, (void *)0, msecs_to_jiffies(NCI_RESET_TIMEOUT)); } if (!rc && ndev->ops->setup) { rc = ndev->ops->setup(ndev); } if (!rc) { struct nci_core_init_v2_cmd nci_init_v2_cmd = { .feature1 = NCI_FEATURE_DISABLE, .feature2 = NCI_FEATURE_DISABLE }; const void *opt = NULL; if (ndev->nci_ver & NCI_VER_2_MASK) opt = &nci_init_v2_cmd; rc = __nci_request(ndev, nci_init_req, opt, msecs_to_jiffies(NCI_INIT_TIMEOUT)); } if (!rc && ndev->ops->post_setup) rc = ndev->ops->post_setup(ndev); if (!rc) { rc = __nci_request(ndev, nci_init_complete_req, (void *)0, msecs_to_jiffies(NCI_INIT_TIMEOUT)); } clear_bit(NCI_INIT, &ndev->flags); if (!rc) { set_bit(NCI_UP, &ndev->flags); nci_clear_target_list(ndev); atomic_set(&ndev->state, NCI_IDLE); } else { /* Init failed, cleanup */ skb_queue_purge(&ndev->cmd_q); skb_queue_purge(&ndev->rx_q); skb_queue_purge(&ndev->tx_q); ndev->ops->close(ndev); ndev->flags &= BIT(NCI_UNREG); } done: mutex_unlock(&ndev->req_lock); return rc; } static int nci_close_device(struct nci_dev *ndev) { nci_req_cancel(ndev, ENODEV); /* This mutex needs to be held as a barrier for * caller nci_unregister_device */ mutex_lock(&ndev->req_lock); if (!test_and_clear_bit(NCI_UP, &ndev->flags)) { /* Need to flush the cmd wq in case * there is a queued/running cmd_work */ flush_workqueue(ndev->cmd_wq); del_timer_sync(&ndev->cmd_timer); del_timer_sync(&ndev->data_timer); mutex_unlock(&ndev->req_lock); return 0; } /* Drop RX and TX queues */ skb_queue_purge(&ndev->rx_q); skb_queue_purge(&ndev->tx_q); /* Flush RX and TX wq */ flush_workqueue(ndev->rx_wq); flush_workqueue(ndev->tx_wq); /* Reset device */ skb_queue_purge(&ndev->cmd_q); atomic_set(&ndev->cmd_cnt, 1); set_bit(NCI_INIT, &ndev->flags); __nci_request(ndev, nci_reset_req, (void *)0, msecs_to_jiffies(NCI_RESET_TIMEOUT)); /* After this point our queues are empty * and no works are scheduled. */ ndev->ops->close(ndev); clear_bit(NCI_INIT, &ndev->flags); /* Flush cmd wq */ flush_workqueue(ndev->cmd_wq); del_timer_sync(&ndev->cmd_timer); /* Clear flags except NCI_UNREG */ ndev->flags &= BIT(NCI_UNREG); mutex_unlock(&ndev->req_lock); return 0; } /* NCI command timer function */ static void nci_cmd_timer(struct timer_list *t) { struct nci_dev *ndev = from_timer(ndev, t, cmd_timer); atomic_set(&ndev->cmd_cnt, 1); queue_work(ndev->cmd_wq, &ndev->cmd_work); } /* NCI data exchange timer function */ static void nci_data_timer(struct timer_list *t) { struct nci_dev *ndev = from_timer(ndev, t, data_timer); set_bit(NCI_DATA_EXCHANGE_TO, &ndev->flags); queue_work(ndev->rx_wq, &ndev->rx_work); } static int nci_dev_up(struct nfc_dev *nfc_dev) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); return nci_open_device(ndev); } static int nci_dev_down(struct nfc_dev *nfc_dev) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); return nci_close_device(ndev); } int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, const __u8 *val) { struct nci_set_config_param param; if (!val || !len) return 0; param.id = id; param.len = len; param.val = val; return __nci_request(ndev, nci_set_config_req, ¶m, msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT)); } EXPORT_SYMBOL(nci_set_config); static void nci_nfcee_discover_req(struct nci_dev *ndev, const void *opt) { struct nci_nfcee_discover_cmd cmd; __u8 action = (unsigned long)opt; cmd.discovery_action = action; nci_send_cmd(ndev, NCI_OP_NFCEE_DISCOVER_CMD, 1, &cmd); } int nci_nfcee_discover(struct nci_dev *ndev, u8 action) { unsigned long opt = action; return __nci_request(ndev, nci_nfcee_discover_req, (void *)opt, msecs_to_jiffies(NCI_CMD_TIMEOUT)); } EXPORT_SYMBOL(nci_nfcee_discover); static void nci_nfcee_mode_set_req(struct nci_dev *ndev, const void *opt) { const struct nci_nfcee_mode_set_cmd *cmd = opt; nci_send_cmd(ndev, NCI_OP_NFCEE_MODE_SET_CMD, sizeof(struct nci_nfcee_mode_set_cmd), cmd); } int nci_nfcee_mode_set(struct nci_dev *ndev, u8 nfcee_id, u8 nfcee_mode) { struct nci_nfcee_mode_set_cmd cmd; cmd.nfcee_id = nfcee_id; cmd.nfcee_mode = nfcee_mode; return __nci_request(ndev, nci_nfcee_mode_set_req, &cmd, msecs_to_jiffies(NCI_CMD_TIMEOUT)); } EXPORT_SYMBOL(nci_nfcee_mode_set); static void nci_core_conn_create_req(struct nci_dev *ndev, const void *opt) { const struct core_conn_create_data *data = opt; nci_send_cmd(ndev, NCI_OP_CORE_CONN_CREATE_CMD, data->length, data->cmd); } int nci_core_conn_create(struct nci_dev *ndev, u8 destination_type, u8 number_destination_params, size_t params_len, const struct core_conn_create_dest_spec_params *params) { int r; struct nci_core_conn_create_cmd *cmd; struct core_conn_create_data data; data.length = params_len + sizeof(struct nci_core_conn_create_cmd); cmd = kzalloc(data.length, GFP_KERNEL); if (!cmd) return -ENOMEM; cmd->destination_type = destination_type; cmd->number_destination_params = number_destination_params; data.cmd = cmd; if (params) { memcpy(cmd->params, params, params_len); if (params->length > 0) memcpy(&ndev->cur_params, ¶ms->value[DEST_SPEC_PARAMS_ID_INDEX], sizeof(struct dest_spec_params)); else ndev->cur_params.id = 0; } else { ndev->cur_params.id = 0; } ndev->cur_dest_type = destination_type; r = __nci_request(ndev, nci_core_conn_create_req, &data, msecs_to_jiffies(NCI_CMD_TIMEOUT)); kfree(cmd); return r; } EXPORT_SYMBOL(nci_core_conn_create); static void nci_core_conn_close_req(struct nci_dev *ndev, const void *opt) { __u8 conn_id = (unsigned long)opt; nci_send_cmd(ndev, NCI_OP_CORE_CONN_CLOSE_CMD, 1, &conn_id); } int nci_core_conn_close(struct nci_dev *ndev, u8 conn_id) { unsigned long opt = conn_id; ndev->cur_conn_id = conn_id; return __nci_request(ndev, nci_core_conn_close_req, (void *)opt, msecs_to_jiffies(NCI_CMD_TIMEOUT)); } EXPORT_SYMBOL(nci_core_conn_close); static int nci_set_local_general_bytes(struct nfc_dev *nfc_dev) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); struct nci_set_config_param param; int rc; param.val = nfc_get_local_general_bytes(nfc_dev, ¶m.len); if ((param.val == NULL) || (param.len == 0)) return 0; if (param.len > NFC_MAX_GT_LEN) return -EINVAL; param.id = NCI_PN_ATR_REQ_GEN_BYTES; rc = nci_request(ndev, nci_set_config_req, ¶m, msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT)); if (rc) return rc; param.id = NCI_LN_ATR_RES_GEN_BYTES; return nci_request(ndev, nci_set_config_req, ¶m, msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT)); } static int nci_set_listen_parameters(struct nfc_dev *nfc_dev) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); int rc; __u8 val; val = NCI_LA_SEL_INFO_NFC_DEP_MASK; rc = nci_set_config(ndev, NCI_LA_SEL_INFO, 1, &val); if (rc) return rc; val = NCI_LF_PROTOCOL_TYPE_NFC_DEP_MASK; rc = nci_set_config(ndev, NCI_LF_PROTOCOL_TYPE, 1, &val); if (rc) return rc; val = NCI_LF_CON_BITR_F_212 | NCI_LF_CON_BITR_F_424; return nci_set_config(ndev, NCI_LF_CON_BITR_F, 1, &val); } static int nci_start_poll(struct nfc_dev *nfc_dev, __u32 im_protocols, __u32 tm_protocols) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); struct nci_rf_discover_param param; int rc; if ((atomic_read(&ndev->state) == NCI_DISCOVERY) || (atomic_read(&ndev->state) == NCI_W4_ALL_DISCOVERIES)) { pr_err("unable to start poll, since poll is already active\n"); return -EBUSY; } if (ndev->target_active_prot) { pr_err("there is an active target\n"); return -EBUSY; } if ((atomic_read(&ndev->state) == NCI_W4_HOST_SELECT) || (atomic_read(&ndev->state) == NCI_POLL_ACTIVE)) { pr_debug("target active or w4 select, implicitly deactivate\n"); rc = nci_request(ndev, nci_rf_deactivate_req, (void *)NCI_DEACTIVATE_TYPE_IDLE_MODE, msecs_to_jiffies(NCI_RF_DEACTIVATE_TIMEOUT)); if (rc) return -EBUSY; } if ((im_protocols | tm_protocols) & NFC_PROTO_NFC_DEP_MASK) { rc = nci_set_local_general_bytes(nfc_dev); if (rc) { pr_err("failed to set local general bytes\n"); return rc; } } if (tm_protocols & NFC_PROTO_NFC_DEP_MASK) { rc = nci_set_listen_parameters(nfc_dev); if (rc) pr_err("failed to set listen parameters\n"); } param.im_protocols = im_protocols; param.tm_protocols = tm_protocols; rc = nci_request(ndev, nci_rf_discover_req, ¶m, msecs_to_jiffies(NCI_RF_DISC_TIMEOUT)); if (!rc) ndev->poll_prots = im_protocols; return rc; } static void nci_stop_poll(struct nfc_dev *nfc_dev) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); if ((atomic_read(&ndev->state) != NCI_DISCOVERY) && (atomic_read(&ndev->state) != NCI_W4_ALL_DISCOVERIES)) { pr_err("unable to stop poll, since poll is not active\n"); return; } nci_request(ndev, nci_rf_deactivate_req, (void *)NCI_DEACTIVATE_TYPE_IDLE_MODE, msecs_to_jiffies(NCI_RF_DEACTIVATE_TIMEOUT)); } static int nci_activate_target(struct nfc_dev *nfc_dev, struct nfc_target *target, __u32 protocol) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); struct nci_rf_discover_select_param param; const struct nfc_target *nci_target = NULL; int i; int rc = 0; pr_debug("target_idx %d, protocol 0x%x\n", target->idx, protocol); if ((atomic_read(&ndev->state) != NCI_W4_HOST_SELECT) && (atomic_read(&ndev->state) != NCI_POLL_ACTIVE)) { pr_err("there is no available target to activate\n"); return -EINVAL; } if (ndev->target_active_prot) { pr_err("there is already an active target\n"); return -EBUSY; } for (i = 0; i < ndev->n_targets; i++) { if (ndev->targets[i].idx == target->idx) { nci_target = &ndev->targets[i]; break; } } if (!nci_target) { pr_err("unable to find the selected target\n"); return -EINVAL; } if (protocol >= NFC_PROTO_MAX) { pr_err("the requested nfc protocol is invalid\n"); return -EINVAL; } if (!(nci_target->supported_protocols & (1 << protocol))) { pr_err("target does not support the requested protocol 0x%x\n", protocol); return -EINVAL; } if (atomic_read(&ndev->state) == NCI_W4_HOST_SELECT) { param.rf_discovery_id = nci_target->logical_idx; if (protocol == NFC_PROTO_JEWEL) param.rf_protocol = NCI_RF_PROTOCOL_T1T; else if (protocol == NFC_PROTO_MIFARE) param.rf_protocol = NCI_RF_PROTOCOL_T2T; else if (protocol == NFC_PROTO_FELICA) param.rf_protocol = NCI_RF_PROTOCOL_T3T; else if (protocol == NFC_PROTO_ISO14443 || protocol == NFC_PROTO_ISO14443_B) param.rf_protocol = NCI_RF_PROTOCOL_ISO_DEP; else param.rf_protocol = NCI_RF_PROTOCOL_NFC_DEP; rc = nci_request(ndev, nci_rf_discover_select_req, ¶m, msecs_to_jiffies(NCI_RF_DISC_SELECT_TIMEOUT)); } if (!rc) ndev->target_active_prot = protocol; return rc; } static void nci_deactivate_target(struct nfc_dev *nfc_dev, struct nfc_target *target, __u8 mode) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); unsigned long nci_mode = NCI_DEACTIVATE_TYPE_IDLE_MODE; if (!ndev->target_active_prot) { pr_err("unable to deactivate target, no active target\n"); return; } ndev->target_active_prot = 0; switch (mode) { case NFC_TARGET_MODE_SLEEP: nci_mode = NCI_DEACTIVATE_TYPE_SLEEP_MODE; break; } if (atomic_read(&ndev->state) == NCI_POLL_ACTIVE) { nci_request(ndev, nci_rf_deactivate_req, (void *)nci_mode, msecs_to_jiffies(NCI_RF_DEACTIVATE_TIMEOUT)); } } static int nci_dep_link_up(struct nfc_dev *nfc_dev, struct nfc_target *target, __u8 comm_mode, __u8 *gb, size_t gb_len) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); int rc; pr_debug("target_idx %d, comm_mode %d\n", target->idx, comm_mode); rc = nci_activate_target(nfc_dev, target, NFC_PROTO_NFC_DEP); if (rc) return rc; rc = nfc_set_remote_general_bytes(nfc_dev, ndev->remote_gb, ndev->remote_gb_len); if (!rc) rc = nfc_dep_link_is_up(nfc_dev, target->idx, NFC_COMM_PASSIVE, NFC_RF_INITIATOR); return rc; } static int nci_dep_link_down(struct nfc_dev *nfc_dev) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); int rc; if (nfc_dev->rf_mode == NFC_RF_INITIATOR) { nci_deactivate_target(nfc_dev, NULL, NCI_DEACTIVATE_TYPE_IDLE_MODE); } else { if (atomic_read(&ndev->state) == NCI_LISTEN_ACTIVE || atomic_read(&ndev->state) == NCI_DISCOVERY) { nci_request(ndev, nci_rf_deactivate_req, (void *)0, msecs_to_jiffies(NCI_RF_DEACTIVATE_TIMEOUT)); } rc = nfc_tm_deactivated(nfc_dev); if (rc) pr_err("error when signaling tm deactivation\n"); } return 0; } static int nci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target, struct sk_buff *skb, data_exchange_cb_t cb, void *cb_context) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); int rc; struct nci_conn_info *conn_info; conn_info = ndev->rf_conn_info; if (!conn_info) return -EPROTO; pr_debug("target_idx %d, len %d\n", target->idx, skb->len); if (!ndev->target_active_prot) { pr_err("unable to exchange data, no active target\n"); return -EINVAL; } if (test_and_set_bit(NCI_DATA_EXCHANGE, &ndev->flags)) return -EBUSY; /* store cb and context to be used on receiving data */ conn_info->data_exchange_cb = cb; conn_info->data_exchange_cb_context = cb_context; rc = nci_send_data(ndev, NCI_STATIC_RF_CONN_ID, skb); if (rc) clear_bit(NCI_DATA_EXCHANGE, &ndev->flags); return rc; } static int nci_tm_send(struct nfc_dev *nfc_dev, struct sk_buff *skb) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); int rc; rc = nci_send_data(ndev, NCI_STATIC_RF_CONN_ID, skb); if (rc) pr_err("unable to send data\n"); return rc; } static int nci_enable_se(struct nfc_dev *nfc_dev, u32 se_idx) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); if (ndev->ops->enable_se) return ndev->ops->enable_se(ndev, se_idx); return 0; } static int nci_disable_se(struct nfc_dev *nfc_dev, u32 se_idx) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); if (ndev->ops->disable_se) return ndev->ops->disable_se(ndev, se_idx); return 0; } static int nci_discover_se(struct nfc_dev *nfc_dev) { int r; struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); if (ndev->ops->discover_se) { r = nci_nfcee_discover(ndev, NCI_NFCEE_DISCOVERY_ACTION_ENABLE); if (r != NCI_STATUS_OK) return -EPROTO; return ndev->ops->discover_se(ndev); } return 0; } static int nci_se_io(struct nfc_dev *nfc_dev, u32 se_idx, u8 *apdu, size_t apdu_length, se_io_cb_t cb, void *cb_context) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); if (ndev->ops->se_io) return ndev->ops->se_io(ndev, se_idx, apdu, apdu_length, cb, cb_context); return 0; } static int nci_fw_download(struct nfc_dev *nfc_dev, const char *firmware_name) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); if (!ndev->ops->fw_download) return -ENOTSUPP; return ndev->ops->fw_download(ndev, firmware_name); } static const struct nfc_ops nci_nfc_ops = { .dev_up = nci_dev_up, .dev_down = nci_dev_down, .start_poll = nci_start_poll, .stop_poll = nci_stop_poll, .dep_link_up = nci_dep_link_up, .dep_link_down = nci_dep_link_down, .activate_target = nci_activate_target, .deactivate_target = nci_deactivate_target, .im_transceive = nci_transceive, .tm_send = nci_tm_send, .enable_se = nci_enable_se, .disable_se = nci_disable_se, .discover_se = nci_discover_se, .se_io = nci_se_io, .fw_download = nci_fw_download, }; /* ---- Interface to NCI drivers ---- */ /** * nci_allocate_device - allocate a new nci device * * @ops: device operations * @supported_protocols: NFC protocols supported by the device * @tx_headroom: Reserved space at beginning of skb * @tx_tailroom: Reserved space at end of skb */ struct nci_dev *nci_allocate_device(const struct nci_ops *ops, __u32 supported_protocols, int tx_headroom, int tx_tailroom) { struct nci_dev *ndev; pr_debug("supported_protocols 0x%x\n", supported_protocols); if (!ops->open || !ops->close || !ops->send) return NULL; if (!supported_protocols) return NULL; ndev = kzalloc(sizeof(struct nci_dev), GFP_KERNEL); if (!ndev) return NULL; ndev->ops = ops; if (ops->n_prop_ops > NCI_MAX_PROPRIETARY_CMD) { pr_err("Too many proprietary commands: %zd\n", ops->n_prop_ops); goto free_nci; } ndev->tx_headroom = tx_headroom; ndev->tx_tailroom = tx_tailroom; init_completion(&ndev->req_completion); ndev->nfc_dev = nfc_allocate_device(&nci_nfc_ops, supported_protocols, tx_headroom + NCI_DATA_HDR_SIZE, tx_tailroom); if (!ndev->nfc_dev) goto free_nci; ndev->hci_dev = nci_hci_allocate(ndev); if (!ndev->hci_dev) goto free_nfc; nfc_set_drvdata(ndev->nfc_dev, ndev); return ndev; free_nfc: nfc_free_device(ndev->nfc_dev); free_nci: kfree(ndev); return NULL; } EXPORT_SYMBOL(nci_allocate_device); /** * nci_free_device - deallocate nci device * * @ndev: The nci device to deallocate */ void nci_free_device(struct nci_dev *ndev) { nfc_free_device(ndev->nfc_dev); nci_hci_deallocate(ndev); /* drop partial rx data packet if present */ if (ndev->rx_data_reassembly) kfree_skb(ndev->rx_data_reassembly); kfree(ndev); } EXPORT_SYMBOL(nci_free_device); /** * nci_register_device - register a nci device in the nfc subsystem * * @ndev: The nci device to register */ int nci_register_device(struct nci_dev *ndev) { int rc; struct device *dev = &ndev->nfc_dev->dev; char name[32]; ndev->flags = 0; INIT_WORK(&ndev->cmd_work, nci_cmd_work); snprintf(name, sizeof(name), "%s_nci_cmd_wq", dev_name(dev)); ndev->cmd_wq = create_singlethread_workqueue(name); if (!ndev->cmd_wq) { rc = -ENOMEM; goto exit; } INIT_WORK(&ndev->rx_work, nci_rx_work); snprintf(name, sizeof(name), "%s_nci_rx_wq", dev_name(dev)); ndev->rx_wq = create_singlethread_workqueue(name); if (!ndev->rx_wq) { rc = -ENOMEM; goto destroy_cmd_wq_exit; } INIT_WORK(&ndev->tx_work, nci_tx_work); snprintf(name, sizeof(name), "%s_nci_tx_wq", dev_name(dev)); ndev->tx_wq = create_singlethread_workqueue(name); if (!ndev->tx_wq) { rc = -ENOMEM; goto destroy_rx_wq_exit; } skb_queue_head_init(&ndev->cmd_q); skb_queue_head_init(&ndev->rx_q); skb_queue_head_init(&ndev->tx_q); timer_setup(&ndev->cmd_timer, nci_cmd_timer, 0); timer_setup(&ndev->data_timer, nci_data_timer, 0); mutex_init(&ndev->req_lock); INIT_LIST_HEAD(&ndev->conn_info_list); rc = nfc_register_device(ndev->nfc_dev); if (rc) goto destroy_tx_wq_exit; goto exit; destroy_tx_wq_exit: destroy_workqueue(ndev->tx_wq); destroy_rx_wq_exit: destroy_workqueue(ndev->rx_wq); destroy_cmd_wq_exit: destroy_workqueue(ndev->cmd_wq); exit: return rc; } EXPORT_SYMBOL(nci_register_device); /** * nci_unregister_device - unregister a nci device in the nfc subsystem * * @ndev: The nci device to unregister */ void nci_unregister_device(struct nci_dev *ndev) { struct nci_conn_info *conn_info, *n; /* This set_bit is not protected with specialized barrier, * However, it is fine because the mutex_lock(&ndev->req_lock); * in nci_close_device() will help to emit one. */ set_bit(NCI_UNREG, &ndev->flags); nci_close_device(ndev); destroy_workqueue(ndev->cmd_wq); destroy_workqueue(ndev->rx_wq); destroy_workqueue(ndev->tx_wq); list_for_each_entry_safe(conn_info, n, &ndev->conn_info_list, list) { list_del(&conn_info->list); /* conn_info is allocated with devm_kzalloc */ } nfc_unregister_device(ndev->nfc_dev); } EXPORT_SYMBOL(nci_unregister_device); /** * nci_recv_frame - receive frame from NCI drivers * * @ndev: The nci device * @skb: The sk_buff to receive */ int nci_recv_frame(struct nci_dev *ndev, struct sk_buff *skb) { pr_debug("len %d\n", skb->len); if (!ndev || (!test_bit(NCI_UP, &ndev->flags) && !test_bit(NCI_INIT, &ndev->flags))) { kfree_skb(skb); return -ENXIO; } /* Queue frame for rx worker thread */ skb_queue_tail(&ndev->rx_q, skb); queue_work(ndev->rx_wq, &ndev->rx_work); return 0; } EXPORT_SYMBOL(nci_recv_frame); int nci_send_frame(struct nci_dev *ndev, struct sk_buff *skb) { pr_debug("len %d\n", skb->len); if (!ndev) { kfree_skb(skb); return -ENODEV; } /* Get rid of skb owner, prior to sending to the driver. */ skb_orphan(skb); /* Send copy to sniffer */ nfc_send_to_raw_sock(ndev->nfc_dev, skb, RAW_PAYLOAD_NCI, NFC_DIRECTION_TX); return ndev->ops->send(ndev, skb); } EXPORT_SYMBOL(nci_send_frame); /* Send NCI command */ int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, const void *payload) { struct nci_ctrl_hdr *hdr; struct sk_buff *skb; pr_debug("opcode 0x%x, plen %d\n", opcode, plen); skb = nci_skb_alloc(ndev, (NCI_CTRL_HDR_SIZE + plen), GFP_KERNEL); if (!skb) { pr_err("no memory for command\n"); return -ENOMEM; } hdr = skb_put(skb, NCI_CTRL_HDR_SIZE); hdr->gid = nci_opcode_gid(opcode); hdr->oid = nci_opcode_oid(opcode); hdr->plen = plen; nci_mt_set((__u8 *)hdr, NCI_MT_CMD_PKT); nci_pbf_set((__u8 *)hdr, NCI_PBF_LAST); if (plen) skb_put_data(skb, payload, plen); skb_queue_tail(&ndev->cmd_q, skb); queue_work(ndev->cmd_wq, &ndev->cmd_work); return 0; } EXPORT_SYMBOL(nci_send_cmd); /* Proprietary commands API */ static const struct nci_driver_ops *ops_cmd_lookup(const struct nci_driver_ops *ops, size_t n_ops, __u16 opcode) { size_t i; const struct nci_driver_ops *op; if (!ops || !n_ops) return NULL; for (i = 0; i < n_ops; i++) { op = &ops[i]; if (op->opcode == opcode) return op; } return NULL; } static int nci_op_rsp_packet(struct nci_dev *ndev, __u16 rsp_opcode, struct sk_buff *skb, const struct nci_driver_ops *ops, size_t n_ops) { const struct nci_driver_ops *op; op = ops_cmd_lookup(ops, n_ops, rsp_opcode); if (!op || !op->rsp) return -ENOTSUPP; return op->rsp(ndev, skb); } static int nci_op_ntf_packet(struct nci_dev *ndev, __u16 ntf_opcode, struct sk_buff *skb, const struct nci_driver_ops *ops, size_t n_ops) { const struct nci_driver_ops *op; op = ops_cmd_lookup(ops, n_ops, ntf_opcode); if (!op || !op->ntf) return -ENOTSUPP; return op->ntf(ndev, skb); } int nci_prop_rsp_packet(struct nci_dev *ndev, __u16 opcode, struct sk_buff *skb) { return nci_op_rsp_packet(ndev, opcode, skb, ndev->ops->prop_ops, ndev->ops->n_prop_ops); } int nci_prop_ntf_packet(struct nci_dev *ndev, __u16 opcode, struct sk_buff *skb) { return nci_op_ntf_packet(ndev, opcode, skb, ndev->ops->prop_ops, ndev->ops->n_prop_ops); } int nci_core_rsp_packet(struct nci_dev *ndev, __u16 opcode, struct sk_buff *skb) { return nci_op_rsp_packet(ndev, opcode, skb, ndev->ops->core_ops, ndev->ops->n_core_ops); } int nci_core_ntf_packet(struct nci_dev *ndev, __u16 opcode, struct sk_buff *skb) { return nci_op_ntf_packet(ndev, opcode, skb, ndev->ops->core_ops, ndev->ops->n_core_ops); } static bool nci_valid_size(struct sk_buff *skb) { BUILD_BUG_ON(NCI_CTRL_HDR_SIZE != NCI_DATA_HDR_SIZE); unsigned int hdr_size = NCI_CTRL_HDR_SIZE; if (skb->len < hdr_size || !nci_plen(skb->data) || skb->len < hdr_size + nci_plen(skb->data)) { return false; } return true; } /* ---- NCI TX Data worker thread ---- */ static void nci_tx_work(struct work_struct *work) { struct nci_dev *ndev = container_of(work, struct nci_dev, tx_work); struct nci_conn_info *conn_info; struct sk_buff *skb; conn_info = nci_get_conn_info_by_conn_id(ndev, ndev->cur_conn_id); if (!conn_info) return; pr_debug("credits_cnt %d\n", atomic_read(&conn_info->credits_cnt)); /* Send queued tx data */ while (atomic_read(&conn_info->credits_cnt)) { skb = skb_dequeue(&ndev->tx_q); if (!skb) return; kcov_remote_start_common(skb_get_kcov_handle(skb)); /* Check if data flow control is used */ if (atomic_read(&conn_info->credits_cnt) != NCI_DATA_FLOW_CONTROL_NOT_USED) atomic_dec(&conn_info->credits_cnt); pr_debug("NCI TX: MT=data, PBF=%d, conn_id=%d, plen=%d\n", nci_pbf(skb->data), nci_conn_id(skb->data), nci_plen(skb->data)); nci_send_frame(ndev, skb); mod_timer(&ndev->data_timer, jiffies + msecs_to_jiffies(NCI_DATA_TIMEOUT)); kcov_remote_stop(); } } /* ----- NCI RX worker thread (data & control) ----- */ static void nci_rx_work(struct work_struct *work) { struct nci_dev *ndev = container_of(work, struct nci_dev, rx_work); struct sk_buff *skb; for (; (skb = skb_dequeue(&ndev->rx_q)); kcov_remote_stop()) { kcov_remote_start_common(skb_get_kcov_handle(skb)); /* Send copy to sniffer */ nfc_send_to_raw_sock(ndev->nfc_dev, skb, RAW_PAYLOAD_NCI, NFC_DIRECTION_RX); if (!nci_valid_size(skb)) { kfree_skb(skb); continue; } /* Process frame */ switch (nci_mt(skb->data)) { case NCI_MT_RSP_PKT: nci_rsp_packet(ndev, skb); break; case NCI_MT_NTF_PKT: nci_ntf_packet(ndev, skb); break; case NCI_MT_DATA_PKT: nci_rx_data_packet(ndev, skb); break; default: pr_err("unknown MT 0x%x\n", nci_mt(skb->data)); kfree_skb(skb); break; } } /* check if a data exchange timeout has occurred */ if (test_bit(NCI_DATA_EXCHANGE_TO, &ndev->flags)) { /* complete the data exchange transaction, if exists */ if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags)) nci_data_exchange_complete(ndev, NULL, ndev->cur_conn_id, -ETIMEDOUT); clear_bit(NCI_DATA_EXCHANGE_TO, &ndev->flags); } } /* ----- NCI TX CMD worker thread ----- */ static void nci_cmd_work(struct work_struct *work) { struct nci_dev *ndev = container_of(work, struct nci_dev, cmd_work); struct sk_buff *skb; pr_debug("cmd_cnt %d\n", atomic_read(&ndev->cmd_cnt)); /* Send queued command */ if (atomic_read(&ndev->cmd_cnt)) { skb = skb_dequeue(&ndev->cmd_q); if (!skb) return; kcov_remote_start_common(skb_get_kcov_handle(skb)); atomic_dec(&ndev->cmd_cnt); pr_debug("NCI TX: MT=cmd, PBF=%d, GID=0x%x, OID=0x%x, plen=%d\n", nci_pbf(skb->data), nci_opcode_gid(nci_opcode(skb->data)), nci_opcode_oid(nci_opcode(skb->data)), nci_plen(skb->data)); nci_send_frame(ndev, skb); mod_timer(&ndev->cmd_timer, jiffies + msecs_to_jiffies(NCI_CMD_TIMEOUT)); kcov_remote_stop(); } } MODULE_DESCRIPTION("NFC Controller Interface"); MODULE_LICENSE("GPL"); |
| 16 14 16 21 18 15 15 17 16 7 7 12 3 | 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 | /* * Copyright (C) 2014 Red Hat * Copyright (C) 2014 Intel Corp. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), * to deal in the Software without restriction, including without limitation * the rights to use, copy, modify, merge, publish, distribute, sublicense, * and/or sell copies of the Software, and to permit persons to whom the * Software is furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice shall be included in * all copies or substantial portions of the Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR * OTHER DEALINGS IN THE SOFTWARE. * * Authors: * Rob Clark <robdclark@gmail.com> * Daniel Vetter <daniel.vetter@ffwll.ch> */ #ifndef DRM_ATOMIC_H_ #define DRM_ATOMIC_H_ #include <drm/drm_crtc.h> #include <drm/drm_util.h> /** * struct drm_crtc_commit - track modeset commits on a CRTC * * This structure is used to track pending modeset changes and atomic commit on * a per-CRTC basis. Since updating the list should never block, this structure * is reference counted to allow waiters to safely wait on an event to complete, * without holding any locks. * * It has 3 different events in total to allow a fine-grained synchronization * between outstanding updates:: * * atomic commit thread hardware * * write new state into hardware ----> ... * signal hw_done * switch to new state on next * ... v/hblank * * wait for buffers to show up ... * * ... send completion irq * irq handler signals flip_done * cleanup old buffers * * signal cleanup_done * * wait for flip_done <---- * clean up atomic state * * The important bit to know is that &cleanup_done is the terminal event, but the * ordering between &flip_done and &hw_done is entirely up to the specific driver * and modeset state change. * * For an implementation of how to use this look at * drm_atomic_helper_setup_commit() from the atomic helper library. * * See also drm_crtc_commit_wait(). */ struct drm_crtc_commit { /** * @crtc: * * DRM CRTC for this commit. */ struct drm_crtc *crtc; /** * @ref: * * Reference count for this structure. Needed to allow blocking on * completions without the risk of the completion disappearing * meanwhile. */ struct kref ref; /** * @flip_done: * * Will be signaled when the hardware has flipped to the new set of * buffers. Signals at the same time as when the drm event for this * commit is sent to userspace, or when an out-fence is singalled. Note * that for most hardware, in most cases this happens after @hw_done is * signalled. * * Completion of this stage is signalled implicitly by calling * drm_crtc_send_vblank_event() on &drm_crtc_state.event. */ struct completion flip_done; /** * @hw_done: * * Will be signalled when all hw register changes for this commit have * been written out. Especially when disabling a pipe this can be much * later than @flip_done, since that can signal already when the * screen goes black, whereas to fully shut down a pipe more register * I/O is required. * * Note that this does not need to include separately reference-counted * resources like backing storage buffer pinning, or runtime pm * management. * * Drivers should call drm_atomic_helper_commit_hw_done() to signal * completion of this stage. */ struct completion hw_done; /** * @cleanup_done: * * Will be signalled after old buffers have been cleaned up by calling * drm_atomic_helper_cleanup_planes(). Since this can only happen after * a vblank wait completed it might be a bit later. This completion is * useful to throttle updates and avoid hardware updates getting ahead * of the buffer cleanup too much. * * Drivers should call drm_atomic_helper_commit_cleanup_done() to signal * completion of this stage. */ struct completion cleanup_done; /** * @commit_entry: * * Entry on the per-CRTC &drm_crtc.commit_list. Protected by * $drm_crtc.commit_lock. */ struct list_head commit_entry; /** * @event: * * &drm_pending_vblank_event pointer to clean up private events. */ struct drm_pending_vblank_event *event; /** * @abort_completion: * * A flag that's set after drm_atomic_helper_setup_commit() takes a * second reference for the completion of $drm_crtc_state.event. It's * used by the free code to remove the second reference if commit fails. */ bool abort_completion; }; struct __drm_planes_state { struct drm_plane *ptr; struct drm_plane_state *state, *old_state, *new_state; }; struct __drm_crtcs_state { struct drm_crtc *ptr; struct drm_crtc_state *state, *old_state, *new_state; /** * @commit: * * A reference to the CRTC commit object that is kept for use by * drm_atomic_helper_wait_for_flip_done() after * drm_atomic_helper_commit_hw_done() is called. This ensures that a * concurrent commit won't free a commit object that is still in use. */ struct drm_crtc_commit *commit; s32 __user *out_fence_ptr; u64 last_vblank_count; }; struct __drm_connnectors_state { struct drm_connector *ptr; struct drm_connector_state *state, *old_state, *new_state; /** * @out_fence_ptr: * * User-provided pointer which the kernel uses to return a sync_file * file descriptor. Used by writeback connectors to signal completion of * the writeback. */ s32 __user *out_fence_ptr; }; struct drm_private_obj; struct drm_private_state; /** * struct drm_private_state_funcs - atomic state functions for private objects * * These hooks are used by atomic helpers to create, swap and destroy states of * private objects. The structure itself is used as a vtable to identify the * associated private object type. Each private object type that needs to be * added to the atomic states is expected to have an implementation of these * hooks and pass a pointer to its drm_private_state_funcs struct to * drm_atomic_get_private_obj_state(). */ struct drm_private_state_funcs { /** * @atomic_duplicate_state: * * Duplicate the current state of the private object and return it. It * is an error to call this before obj->state has been initialized. * * RETURNS: * * Duplicated atomic state or NULL when obj->state is not * initialized or allocation failed. */ struct drm_private_state *(*atomic_duplicate_state)(struct drm_private_obj *obj); /** * @atomic_destroy_state: * * Frees the private object state created with @atomic_duplicate_state. */ void (*atomic_destroy_state)(struct drm_private_obj *obj, struct drm_private_state *state); /** * @atomic_print_state: * * If driver subclasses &struct drm_private_state, it should implement * this optional hook for printing additional driver specific state. * * Do not call this directly, use drm_atomic_private_obj_print_state() * instead. */ void (*atomic_print_state)(struct drm_printer *p, const struct drm_private_state *state); }; /** * struct drm_private_obj - base struct for driver private atomic object * * A driver private object is initialized by calling * drm_atomic_private_obj_init() and cleaned up by calling * drm_atomic_private_obj_fini(). * * Currently only tracks the state update functions and the opaque driver * private state itself, but in the future might also track which * &drm_modeset_lock is required to duplicate and update this object's state. * * All private objects must be initialized before the DRM device they are * attached to is registered to the DRM subsystem (call to drm_dev_register()) * and should stay around until this DRM device is unregistered (call to * drm_dev_unregister()). In other words, private objects lifetime is tied * to the DRM device lifetime. This implies that: * * 1/ all calls to drm_atomic_private_obj_init() must be done before calling * drm_dev_register() * 2/ all calls to drm_atomic_private_obj_fini() must be done after calling * drm_dev_unregister() * * If that private object is used to store a state shared by multiple * CRTCs, proper care must be taken to ensure that non-blocking commits are * properly ordered to avoid a use-after-free issue. * * Indeed, assuming a sequence of two non-blocking &drm_atomic_commit on two * different &drm_crtc using different &drm_plane and &drm_connector, so with no * resources shared, there's no guarantee on which commit is going to happen * first. However, the second &drm_atomic_commit will consider the first * &drm_private_obj its old state, and will be in charge of freeing it whenever * the second &drm_atomic_commit is done. * * If the first &drm_atomic_commit happens after it, it will consider its * &drm_private_obj the new state and will be likely to access it, resulting in * an access to a freed memory region. Drivers should store (and get a reference * to) the &drm_crtc_commit structure in our private state in * &drm_mode_config_helper_funcs.atomic_commit_setup, and then wait for that * commit to complete as the first step of * &drm_mode_config_helper_funcs.atomic_commit_tail, similar to * drm_atomic_helper_wait_for_dependencies(). */ struct drm_private_obj { /** * @head: List entry used to attach a private object to a &drm_device * (queued to &drm_mode_config.privobj_list). */ struct list_head head; /** * @lock: Modeset lock to protect the state object. */ struct drm_modeset_lock lock; /** * @state: Current atomic state for this driver private object. */ struct drm_private_state *state; /** * @funcs: * * Functions to manipulate the state of this driver private object, see * &drm_private_state_funcs. */ const struct drm_private_state_funcs *funcs; }; /** * drm_for_each_privobj() - private object iterator * * @privobj: pointer to the current private object. Updated after each * iteration * @dev: the DRM device we want get private objects from * * Allows one to iterate over all private objects attached to @dev */ #define drm_for_each_privobj(privobj, dev) \ list_for_each_entry(privobj, &(dev)->mode_config.privobj_list, head) /** * struct drm_private_state - base struct for driver private object state * * Currently only contains a backpointer to the overall atomic update, * and the relevant private object but in the future also might hold * synchronization information similar to e.g. &drm_crtc.commit. */ struct drm_private_state { /** * @state: backpointer to global drm_atomic_state */ struct drm_atomic_state *state; /** * @obj: backpointer to the private object */ struct drm_private_obj *obj; }; struct __drm_private_objs_state { struct drm_private_obj *ptr; struct drm_private_state *state, *old_state, *new_state; }; /** * struct drm_atomic_state - Atomic commit structure * * This structure is the kernel counterpart of @drm_mode_atomic and represents * an atomic commit that transitions from an old to a new display state. It * contains all the objects affected by the atomic commit and both the new * state structures and pointers to the old state structures for * these. * * States are added to an atomic update by calling drm_atomic_get_crtc_state(), * drm_atomic_get_plane_state(), drm_atomic_get_connector_state(), or for * private state structures, drm_atomic_get_private_obj_state(). */ struct drm_atomic_state { /** * @ref: * * Count of all references to this update (will not be freed until zero). */ struct kref ref; /** * @dev: Parent DRM Device. */ struct drm_device *dev; /** * @allow_modeset: * * Allow full modeset. This is used by the ATOMIC IOCTL handler to * implement the DRM_MODE_ATOMIC_ALLOW_MODESET flag. Drivers should * never consult this flag, instead looking at the output of * drm_atomic_crtc_needs_modeset(). */ bool allow_modeset : 1; /** * @legacy_cursor_update: * * Hint to enforce legacy cursor IOCTL semantics. * * WARNING: This is thoroughly broken and pretty much impossible to * implement correctly. Drivers must ignore this and should instead * implement &drm_plane_helper_funcs.atomic_async_check and * &drm_plane_helper_funcs.atomic_async_commit hooks. New users of this * flag are not allowed. */ bool legacy_cursor_update : 1; /** * @async_update: hint for asynchronous plane update */ bool async_update : 1; /** * @duplicated: * * Indicates whether or not this atomic state was duplicated using * drm_atomic_helper_duplicate_state(). Drivers and atomic helpers * should use this to fixup normal inconsistencies in duplicated * states. */ bool duplicated : 1; /** * @planes: * * Pointer to array of @drm_plane and @drm_plane_state part of this * update. */ struct __drm_planes_state *planes; /** * @crtcs: * * Pointer to array of @drm_crtc and @drm_crtc_state part of this * update. */ struct __drm_crtcs_state *crtcs; /** * @num_connector: size of the @connectors array */ int num_connector; /** * @connectors: * * Pointer to array of @drm_connector and @drm_connector_state part of * this update. */ struct __drm_connnectors_state *connectors; /** * @num_private_objs: size of the @private_objs array */ int num_private_objs; /** * @private_objs: * * Pointer to array of @drm_private_obj and @drm_private_obj_state part * of this update. */ struct __drm_private_objs_state *private_objs; /** * @acquire_ctx: acquire context for this atomic modeset state update */ struct drm_modeset_acquire_ctx *acquire_ctx; /** * @fake_commit: * * Used for signaling unbound planes/connectors. * When a connector or plane is not bound to any CRTC, it's still important * to preserve linearity to prevent the atomic states from being freed to early. * * This commit (if set) is not bound to any CRTC, but will be completed when * drm_atomic_helper_commit_hw_done() is called. */ struct drm_crtc_commit *fake_commit; /** * @commit_work: * * Work item which can be used by the driver or helpers to execute the * commit without blocking. */ struct work_struct commit_work; }; void __drm_crtc_commit_free(struct kref *kref); /** * drm_crtc_commit_get - acquire a reference to the CRTC commit * @commit: CRTC commit * * Increases the reference of @commit. * * Returns: * The pointer to @commit, with reference increased. */ static inline struct drm_crtc_commit *drm_crtc_commit_get(struct drm_crtc_commit *commit) { kref_get(&commit->ref); return commit; } /** * drm_crtc_commit_put - release a reference to the CRTC commmit * @commit: CRTC commit * * This releases a reference to @commit which is freed after removing the * final reference. No locking required and callable from any context. */ static inline void drm_crtc_commit_put(struct drm_crtc_commit *commit) { kref_put(&commit->ref, __drm_crtc_commit_free); } int drm_crtc_commit_wait(struct drm_crtc_commit *commit); struct drm_atomic_state * __must_check drm_atomic_state_alloc(struct drm_device *dev); void drm_atomic_state_clear(struct drm_atomic_state *state); /** * drm_atomic_state_get - acquire a reference to the atomic state * @state: The atomic state * * Returns a new reference to the @state */ static inline struct drm_atomic_state * drm_atomic_state_get(struct drm_atomic_state *state) { kref_get(&state->ref); return state; } void __drm_atomic_state_free(struct kref *ref); /** * drm_atomic_state_put - release a reference to the atomic state * @state: The atomic state * * This releases a reference to @state which is freed after removing the * final reference. No locking required and callable from any context. */ static inline void drm_atomic_state_put(struct drm_atomic_state *state) { kref_put(&state->ref, __drm_atomic_state_free); } int __must_check drm_atomic_state_init(struct drm_device *dev, struct drm_atomic_state *state); void drm_atomic_state_default_clear(struct drm_atomic_state *state); void drm_atomic_state_default_release(struct drm_atomic_state *state); struct drm_crtc_state * __must_check drm_atomic_get_crtc_state(struct drm_atomic_state *state, struct drm_crtc *crtc); struct drm_plane_state * __must_check drm_atomic_get_plane_state(struct drm_atomic_state *state, struct drm_plane *plane); struct drm_connector_state * __must_check drm_atomic_get_connector_state(struct drm_atomic_state *state, struct drm_connector *connector); void drm_atomic_private_obj_init(struct drm_device *dev, struct drm_private_obj *obj, struct drm_private_state *state, const struct drm_private_state_funcs *funcs); void drm_atomic_private_obj_fini(struct drm_private_obj *obj); struct drm_private_state * __must_check drm_atomic_get_private_obj_state(struct drm_atomic_state *state, struct drm_private_obj *obj); struct drm_private_state * drm_atomic_get_old_private_obj_state(const struct drm_atomic_state *state, struct drm_private_obj *obj); struct drm_private_state * drm_atomic_get_new_private_obj_state(const struct drm_atomic_state *state, struct drm_private_obj *obj); struct drm_connector * drm_atomic_get_old_connector_for_encoder(const struct drm_atomic_state *state, struct drm_encoder *encoder); struct drm_connector * drm_atomic_get_new_connector_for_encoder(const struct drm_atomic_state *state, struct drm_encoder *encoder); struct drm_crtc * drm_atomic_get_old_crtc_for_encoder(struct drm_atomic_state *state, struct drm_encoder *encoder); struct drm_crtc * drm_atomic_get_new_crtc_for_encoder(struct drm_atomic_state *state, struct drm_encoder *encoder); /** * drm_atomic_get_existing_crtc_state - get CRTC state, if it exists * @state: global atomic state object * @crtc: CRTC to grab * * This function returns the CRTC state for the given CRTC, or NULL * if the CRTC is not part of the global atomic state. * * This function is deprecated, @drm_atomic_get_old_crtc_state or * @drm_atomic_get_new_crtc_state should be used instead. */ static inline struct drm_crtc_state * drm_atomic_get_existing_crtc_state(const struct drm_atomic_state *state, struct drm_crtc *crtc) { return state->crtcs[drm_crtc_index(crtc)].state; } /** * drm_atomic_get_old_crtc_state - get old CRTC state, if it exists * @state: global atomic state object * @crtc: CRTC to grab * * This function returns the old CRTC state for the given CRTC, or * NULL if the CRTC is not part of the global atomic state. */ static inline struct drm_crtc_state * drm_atomic_get_old_crtc_state(const struct drm_atomic_state *state, struct drm_crtc *crtc) { return state->crtcs[drm_crtc_index(crtc)].old_state; } /** * drm_atomic_get_new_crtc_state - get new CRTC state, if it exists * @state: global atomic state object * @crtc: CRTC to grab * * This function returns the new CRTC state for the given CRTC, or * NULL if the CRTC is not part of the global atomic state. */ static inline struct drm_crtc_state * drm_atomic_get_new_crtc_state(const struct drm_atomic_state *state, struct drm_crtc *crtc) { return state->crtcs[drm_crtc_index(crtc)].new_state; } /** * drm_atomic_get_existing_plane_state - get plane state, if it exists * @state: global atomic state object * @plane: plane to grab * * This function returns the plane state for the given plane, or NULL * if the plane is not part of the global atomic state. * * This function is deprecated, @drm_atomic_get_old_plane_state or * @drm_atomic_get_new_plane_state should be used instead. */ static inline struct drm_plane_state * drm_atomic_get_existing_plane_state(const struct drm_atomic_state *state, struct drm_plane *plane) { return state->planes[drm_plane_index(plane)].state; } /** * drm_atomic_get_old_plane_state - get plane state, if it exists * @state: global atomic state object * @plane: plane to grab * * This function returns the old plane state for the given plane, or * NULL if the plane is not part of the global atomic state. */ static inline struct drm_plane_state * drm_atomic_get_old_plane_state(const struct drm_atomic_state *state, struct drm_plane *plane) { return state->planes[drm_plane_index(plane)].old_state; } /** * drm_atomic_get_new_plane_state - get plane state, if it exists * @state: global atomic state object * @plane: plane to grab * * This function returns the new plane state for the given plane, or * NULL if the plane is not part of the global atomic state. */ static inline struct drm_plane_state * drm_atomic_get_new_plane_state(const struct drm_atomic_state *state, struct drm_plane *plane) { return state->planes[drm_plane_index(plane)].new_state; } /** * drm_atomic_get_existing_connector_state - get connector state, if it exists * @state: global atomic state object * @connector: connector to grab * * This function returns the connector state for the given connector, * or NULL if the connector is not part of the global atomic state. * * This function is deprecated, @drm_atomic_get_old_connector_state or * @drm_atomic_get_new_connector_state should be used instead. */ static inline struct drm_connector_state * drm_atomic_get_existing_connector_state(const struct drm_atomic_state *state, struct drm_connector *connector) { int index = drm_connector_index(connector); if (index >= state->num_connector) return NULL; return state->connectors[index].state; } /** * drm_atomic_get_old_connector_state - get connector state, if it exists * @state: global atomic state object * @connector: connector to grab * * This function returns the old connector state for the given connector, * or NULL if the connector is not part of the global atomic state. */ static inline struct drm_connector_state * drm_atomic_get_old_connector_state(const struct drm_atomic_state *state, struct drm_connector *connector) { int index = drm_connector_index(connector); if (index >= state->num_connector) return NULL; return state->connectors[index].old_state; } /** * drm_atomic_get_new_connector_state - get connector state, if it exists * @state: global atomic state object * @connector: connector to grab * * This function returns the new connector state for the given connector, * or NULL if the connector is not part of the global atomic state. */ static inline struct drm_connector_state * drm_atomic_get_new_connector_state(const struct drm_atomic_state *state, struct drm_connector *connector) { int index = drm_connector_index(connector); if (index >= state->num_connector) return NULL; return state->connectors[index].new_state; } /** * __drm_atomic_get_current_plane_state - get current plane state * @state: global atomic state object * @plane: plane to grab * * This function returns the plane state for the given plane, either from * @state, or if the plane isn't part of the atomic state update, from @plane. * This is useful in atomic check callbacks, when drivers need to peek at, but * not change, state of other planes, since it avoids threading an error code * back up the call chain. * * WARNING: * * Note that this function is in general unsafe since it doesn't check for the * required locking for access state structures. Drivers must ensure that it is * safe to access the returned state structure through other means. One common * example is when planes are fixed to a single CRTC, and the driver knows that * the CRTC lock is held already. In that case holding the CRTC lock gives a * read-lock on all planes connected to that CRTC. But if planes can be * reassigned things get more tricky. In that case it's better to use * drm_atomic_get_plane_state and wire up full error handling. * * Returns: * * Read-only pointer to the current plane state. */ static inline const struct drm_plane_state * __drm_atomic_get_current_plane_state(const struct drm_atomic_state *state, struct drm_plane *plane) { if (state->planes[drm_plane_index(plane)].state) return state->planes[drm_plane_index(plane)].state; return plane->state; } int __must_check drm_atomic_add_encoder_bridges(struct drm_atomic_state *state, struct drm_encoder *encoder); int __must_check drm_atomic_add_affected_connectors(struct drm_atomic_state *state, struct drm_crtc *crtc); int __must_check drm_atomic_add_affected_planes(struct drm_atomic_state *state, struct drm_crtc *crtc); int __must_check drm_atomic_check_only(struct drm_atomic_state *state); int __must_check drm_atomic_commit(struct drm_atomic_state *state); int __must_check drm_atomic_nonblocking_commit(struct drm_atomic_state *state); void drm_state_dump(struct drm_device *dev, struct drm_printer *p); /** * for_each_oldnew_connector_in_state - iterate over all connectors in an atomic update * @__state: &struct drm_atomic_state pointer * @connector: &struct drm_connector iteration cursor * @old_connector_state: &struct drm_connector_state iteration cursor for the * old state * @new_connector_state: &struct drm_connector_state iteration cursor for the * new state * @__i: int iteration cursor, for macro-internal use * * This iterates over all connectors in an atomic update, tracking both old and * new state. This is useful in places where the state delta needs to be * considered, for example in atomic check functions. */ #define for_each_oldnew_connector_in_state(__state, connector, old_connector_state, new_connector_state, __i) \ for ((__i) = 0; \ (__i) < (__state)->num_connector; \ (__i)++) \ for_each_if ((__state)->connectors[__i].ptr && \ ((connector) = (__state)->connectors[__i].ptr, \ (void)(connector) /* Only to avoid unused-but-set-variable warning */, \ (old_connector_state) = (__state)->connectors[__i].old_state, \ (new_connector_state) = (__state)->connectors[__i].new_state, 1)) /** * for_each_old_connector_in_state - iterate over all connectors in an atomic update * @__state: &struct drm_atomic_state pointer * @connector: &struct drm_connector iteration cursor * @old_connector_state: &struct drm_connector_state iteration cursor for the * old state * @__i: int iteration cursor, for macro-internal use * * This iterates over all connectors in an atomic update, tracking only the old * state. This is useful in disable functions, where we need the old state the * hardware is still in. */ #define for_each_old_connector_in_state(__state, connector, old_connector_state, __i) \ for ((__i) = 0; \ (__i) < (__state)->num_connector; \ (__i)++) \ for_each_if ((__state)->connectors[__i].ptr && \ ((connector) = (__state)->connectors[__i].ptr, \ (void)(connector) /* Only to avoid unused-but-set-variable warning */, \ (old_connector_state) = (__state)->connectors[__i].old_state, 1)) /** * for_each_new_connector_in_state - iterate over all connectors in an atomic update * @__state: &struct drm_atomic_state pointer * @connector: &struct drm_connector iteration cursor * @new_connector_state: &struct drm_connector_state iteration cursor for the * new state * @__i: int iteration cursor, for macro-internal use * * This iterates over all connectors in an atomic update, tracking only the new * state. This is useful in enable functions, where we need the new state the * hardware should be in when the atomic commit operation has completed. */ #define for_each_new_connector_in_state(__state, connector, new_connector_state, __i) \ for ((__i) = 0; \ (__i) < (__state)->num_connector; \ (__i)++) \ for_each_if ((__state)->connectors[__i].ptr && \ ((connector) = (__state)->connectors[__i].ptr, \ (void)(connector) /* Only to avoid unused-but-set-variable warning */, \ (new_connector_state) = (__state)->connectors[__i].new_state, \ (void)(new_connector_state) /* Only to avoid unused-but-set-variable warning */, 1)) /** * for_each_oldnew_crtc_in_state - iterate over all CRTCs in an atomic update * @__state: &struct drm_atomic_state pointer * @crtc: &struct drm_crtc iteration cursor * @old_crtc_state: &struct drm_crtc_state iteration cursor for the old state * @new_crtc_state: &struct drm_crtc_state iteration cursor for the new state * @__i: int iteration cursor, for macro-internal use * * This iterates over all CRTCs in an atomic update, tracking both old and * new state. This is useful in places where the state delta needs to be * considered, for example in atomic check functions. */ #define for_each_oldnew_crtc_in_state(__state, crtc, old_crtc_state, new_crtc_state, __i) \ for ((__i) = 0; \ (__i) < (__state)->dev->mode_config.num_crtc; \ (__i)++) \ for_each_if ((__state)->crtcs[__i].ptr && \ ((crtc) = (__state)->crtcs[__i].ptr, \ (void)(crtc) /* Only to avoid unused-but-set-variable warning */, \ (old_crtc_state) = (__state)->crtcs[__i].old_state, \ (void)(old_crtc_state) /* Only to avoid unused-but-set-variable warning */, \ (new_crtc_state) = (__state)->crtcs[__i].new_state, \ (void)(new_crtc_state) /* Only to avoid unused-but-set-variable warning */, 1)) /** * for_each_old_crtc_in_state - iterate over all CRTCs in an atomic update * @__state: &struct drm_atomic_state pointer * @crtc: &struct drm_crtc iteration cursor * @old_crtc_state: &struct drm_crtc_state iteration cursor for the old state * @__i: int iteration cursor, for macro-internal use * * This iterates over all CRTCs in an atomic update, tracking only the old * state. This is useful in disable functions, where we need the old state the * hardware is still in. */ #define for_each_old_crtc_in_state(__state, crtc, old_crtc_state, __i) \ for ((__i) = 0; \ (__i) < (__state)->dev->mode_config.num_crtc; \ (__i)++) \ for_each_if ((__state)->crtcs[__i].ptr && \ ((crtc) = (__state)->crtcs[__i].ptr, \ (void)(crtc) /* Only to avoid unused-but-set-variable warning */, \ (old_crtc_state) = (__state)->crtcs[__i].old_state, 1)) /** * for_each_new_crtc_in_state - iterate over all CRTCs in an atomic update * @__state: &struct drm_atomic_state pointer * @crtc: &struct drm_crtc iteration cursor * @new_crtc_state: &struct drm_crtc_state iteration cursor for the new state * @__i: int iteration cursor, for macro-internal use * * This iterates over all CRTCs in an atomic update, tracking only the new * state. This is useful in enable functions, where we need the new state the * hardware should be in when the atomic commit operation has completed. */ #define for_each_new_crtc_in_state(__state, crtc, new_crtc_state, __i) \ for ((__i) = 0; \ (__i) < (__state)->dev->mode_config.num_crtc; \ (__i)++) \ for_each_if ((__state)->crtcs[__i].ptr && \ ((crtc) = (__state)->crtcs[__i].ptr, \ (void)(crtc) /* Only to avoid unused-but-set-variable warning */, \ (new_crtc_state) = (__state)->crtcs[__i].new_state, \ (void)(new_crtc_state) /* Only to avoid unused-but-set-variable warning */, 1)) /** * for_each_oldnew_plane_in_state - iterate over all planes in an atomic update * @__state: &struct drm_atomic_state pointer * @plane: &struct drm_plane iteration cursor * @old_plane_state: &struct drm_plane_state iteration cursor for the old state * @new_plane_state: &struct drm_plane_state iteration cursor for the new state * @__i: int iteration cursor, for macro-internal use * * This iterates over all planes in an atomic update, tracking both old and * new state. This is useful in places where the state delta needs to be * considered, for example in atomic check functions. */ #define for_each_oldnew_plane_in_state(__state, plane, old_plane_state, new_plane_state, __i) \ for ((__i) = 0; \ (__i) < (__state)->dev->mode_config.num_total_plane; \ (__i)++) \ for_each_if ((__state)->planes[__i].ptr && \ ((plane) = (__state)->planes[__i].ptr, \ (void)(plane) /* Only to avoid unused-but-set-variable warning */, \ (old_plane_state) = (__state)->planes[__i].old_state,\ (new_plane_state) = (__state)->planes[__i].new_state, 1)) /** * for_each_oldnew_plane_in_state_reverse - iterate over all planes in an atomic * update in reverse order * @__state: &struct drm_atomic_state pointer * @plane: &struct drm_plane iteration cursor * @old_plane_state: &struct drm_plane_state iteration cursor for the old state * @new_plane_state: &struct drm_plane_state iteration cursor for the new state * @__i: int iteration cursor, for macro-internal use * * This iterates over all planes in an atomic update in reverse order, * tracking both old and new state. This is useful in places where the * state delta needs to be considered, for example in atomic check functions. */ #define for_each_oldnew_plane_in_state_reverse(__state, plane, old_plane_state, new_plane_state, __i) \ for ((__i) = ((__state)->dev->mode_config.num_total_plane - 1); \ (__i) >= 0; \ (__i)--) \ for_each_if ((__state)->planes[__i].ptr && \ ((plane) = (__state)->planes[__i].ptr, \ (old_plane_state) = (__state)->planes[__i].old_state,\ (new_plane_state) = (__state)->planes[__i].new_state, 1)) /** * for_each_new_plane_in_state_reverse - other than only tracking new state, * it's the same as for_each_oldnew_plane_in_state_reverse * @__state: &struct drm_atomic_state pointer * @plane: &struct drm_plane iteration cursor * @new_plane_state: &struct drm_plane_state iteration cursor for the new state * @__i: int iteration cursor, for macro-internal use */ #define for_each_new_plane_in_state_reverse(__state, plane, new_plane_state, __i) \ for ((__i) = ((__state)->dev->mode_config.num_total_plane - 1); \ (__i) >= 0; \ (__i)--) \ for_each_if ((__state)->planes[__i].ptr && \ ((plane) = (__state)->planes[__i].ptr, \ (new_plane_state) = (__state)->planes[__i].new_state, 1)) /** * for_each_old_plane_in_state - iterate over all planes in an atomic update * @__state: &struct drm_atomic_state pointer * @plane: &struct drm_plane iteration cursor * @old_plane_state: &struct drm_plane_state iteration cursor for the old state * @__i: int iteration cursor, for macro-internal use * * This iterates over all planes in an atomic update, tracking only the old * state. This is useful in disable functions, where we need the old state the * hardware is still in. */ #define for_each_old_plane_in_state(__state, plane, old_plane_state, __i) \ for ((__i) = 0; \ (__i) < (__state)->dev->mode_config.num_total_plane; \ (__i)++) \ for_each_if ((__state)->planes[__i].ptr && \ ((plane) = (__state)->planes[__i].ptr, \ (old_plane_state) = (__state)->planes[__i].old_state, 1)) /** * for_each_new_plane_in_state - iterate over all planes in an atomic update * @__state: &struct drm_atomic_state pointer * @plane: &struct drm_plane iteration cursor * @new_plane_state: &struct drm_plane_state iteration cursor for the new state * @__i: int iteration cursor, for macro-internal use * * This iterates over all planes in an atomic update, tracking only the new * state. This is useful in enable functions, where we need the new state the * hardware should be in when the atomic commit operation has completed. */ #define for_each_new_plane_in_state(__state, plane, new_plane_state, __i) \ for ((__i) = 0; \ (__i) < (__state)->dev->mode_config.num_total_plane; \ (__i)++) \ for_each_if ((__state)->planes[__i].ptr && \ ((plane) = (__state)->planes[__i].ptr, \ (void)(plane) /* Only to avoid unused-but-set-variable warning */, \ (new_plane_state) = (__state)->planes[__i].new_state, \ (void)(new_plane_state) /* Only to avoid unused-but-set-variable warning */, 1)) /** * for_each_oldnew_private_obj_in_state - iterate over all private objects in an atomic update * @__state: &struct drm_atomic_state pointer * @obj: &struct drm_private_obj iteration cursor * @old_obj_state: &struct drm_private_state iteration cursor for the old state * @new_obj_state: &struct drm_private_state iteration cursor for the new state * @__i: int iteration cursor, for macro-internal use * * This iterates over all private objects in an atomic update, tracking both * old and new state. This is useful in places where the state delta needs * to be considered, for example in atomic check functions. */ #define for_each_oldnew_private_obj_in_state(__state, obj, old_obj_state, new_obj_state, __i) \ for ((__i) = 0; \ (__i) < (__state)->num_private_objs && \ ((obj) = (__state)->private_objs[__i].ptr, \ (old_obj_state) = (__state)->private_objs[__i].old_state, \ (new_obj_state) = (__state)->private_objs[__i].new_state, 1); \ (__i)++) /** * for_each_old_private_obj_in_state - iterate over all private objects in an atomic update * @__state: &struct drm_atomic_state pointer * @obj: &struct drm_private_obj iteration cursor * @old_obj_state: &struct drm_private_state iteration cursor for the old state * @__i: int iteration cursor, for macro-internal use * * This iterates over all private objects in an atomic update, tracking only * the old state. This is useful in disable functions, where we need the old * state the hardware is still in. */ #define for_each_old_private_obj_in_state(__state, obj, old_obj_state, __i) \ for ((__i) = 0; \ (__i) < (__state)->num_private_objs && \ ((obj) = (__state)->private_objs[__i].ptr, \ (old_obj_state) = (__state)->private_objs[__i].old_state, 1); \ (__i)++) /** * for_each_new_private_obj_in_state - iterate over all private objects in an atomic update * @__state: &struct drm_atomic_state pointer * @obj: &struct drm_private_obj iteration cursor * @new_obj_state: &struct drm_private_state iteration cursor for the new state * @__i: int iteration cursor, for macro-internal use * * This iterates over all private objects in an atomic update, tracking only * the new state. This is useful in enable functions, where we need the new state the * hardware should be in when the atomic commit operation has completed. */ #define for_each_new_private_obj_in_state(__state, obj, new_obj_state, __i) \ for ((__i) = 0; \ (__i) < (__state)->num_private_objs && \ ((obj) = (__state)->private_objs[__i].ptr, \ (void)(obj) /* Only to avoid unused-but-set-variable warning */, \ (new_obj_state) = (__state)->private_objs[__i].new_state, 1); \ (__i)++) /** * drm_atomic_crtc_needs_modeset - compute combined modeset need * @state: &drm_crtc_state for the CRTC * * To give drivers flexibility &struct drm_crtc_state has 3 booleans to track * whether the state CRTC changed enough to need a full modeset cycle: * mode_changed, active_changed and connectors_changed. This helper simply * combines these three to compute the overall need for a modeset for @state. * * The atomic helper code sets these booleans, but drivers can and should * change them appropriately to accurately represent whether a modeset is * really needed. In general, drivers should avoid full modesets whenever * possible. * * For example if the CRTC mode has changed, and the hardware is able to enact * the requested mode change without going through a full modeset, the driver * should clear mode_changed in its &drm_mode_config_funcs.atomic_check * implementation. */ static inline bool drm_atomic_crtc_needs_modeset(const struct drm_crtc_state *state) { return state->mode_changed || state->active_changed || state->connectors_changed; } /** * drm_atomic_crtc_effectively_active - compute whether CRTC is actually active * @state: &drm_crtc_state for the CRTC * * When in self refresh mode, the crtc_state->active value will be false, since * the CRTC is off. However in some cases we're interested in whether the CRTC * is active, or effectively active (ie: it's connected to an active display). * In these cases, use this function instead of just checking active. */ static inline bool drm_atomic_crtc_effectively_active(const struct drm_crtc_state *state) { return state->active || state->self_refresh_active; } /** * struct drm_bus_cfg - bus configuration * * This structure stores the configuration of a physical bus between two * components in an output pipeline, usually between two bridges, an encoder * and a bridge, or a bridge and a connector. * * The bus configuration is stored in &drm_bridge_state separately for the * input and output buses, as seen from the point of view of each bridge. The * bus configuration of a bridge output is usually identical to the * configuration of the next bridge's input, but may differ if the signals are * modified between the two bridges, for instance by an inverter on the board. * The input and output configurations of a bridge may differ if the bridge * modifies the signals internally, for instance by performing format * conversion, or modifying signals polarities. */ struct drm_bus_cfg { /** * @format: format used on this bus (one of the MEDIA_BUS_FMT_* format) * * This field should not be directly modified by drivers * (drm_atomic_bridge_chain_select_bus_fmts() takes care of the bus * format negotiation). */ u32 format; /** * @flags: DRM_BUS_* flags used on this bus */ u32 flags; }; /** * struct drm_bridge_state - Atomic bridge state object */ struct drm_bridge_state { /** * @base: inherit from &drm_private_state */ struct drm_private_state base; /** * @bridge: the bridge this state refers to */ struct drm_bridge *bridge; /** * @input_bus_cfg: input bus configuration */ struct drm_bus_cfg input_bus_cfg; /** * @output_bus_cfg: output bus configuration */ struct drm_bus_cfg output_bus_cfg; }; static inline struct drm_bridge_state * drm_priv_to_bridge_state(struct drm_private_state *priv) { return container_of(priv, struct drm_bridge_state, base); } struct drm_bridge_state * drm_atomic_get_bridge_state(struct drm_atomic_state *state, struct drm_bridge *bridge); struct drm_bridge_state * drm_atomic_get_old_bridge_state(const struct drm_atomic_state *state, struct drm_bridge *bridge); struct drm_bridge_state * drm_atomic_get_new_bridge_state(const struct drm_atomic_state *state, struct drm_bridge *bridge); #endif /* DRM_ATOMIC_H_ */ |
| 14 11 20 11 11 12 12 47 47 11 4 4 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __BEN_VLAN_802_1Q_INC__ #define __BEN_VLAN_802_1Q_INC__ #include <linux/if_vlan.h> #include <linux/u64_stats_sync.h> #include <linux/list.h> /* if this changes, algorithm will have to be reworked because this * depends on completely exhausting the VLAN identifier space. Thus * it gives constant time look-up, but in many cases it wastes memory. */ #define VLAN_GROUP_ARRAY_SPLIT_PARTS 8 #define VLAN_GROUP_ARRAY_PART_LEN (VLAN_N_VID/VLAN_GROUP_ARRAY_SPLIT_PARTS) enum vlan_protos { VLAN_PROTO_8021Q = 0, VLAN_PROTO_8021AD, VLAN_PROTO_NUM, }; struct vlan_group { unsigned int nr_vlan_devs; struct hlist_node hlist; /* linked list */ struct net_device **vlan_devices_arrays[VLAN_PROTO_NUM] [VLAN_GROUP_ARRAY_SPLIT_PARTS]; }; struct vlan_info { struct net_device *real_dev; /* The ethernet(like) device * the vlan is attached to. */ struct vlan_group grp; struct list_head vid_list; unsigned int nr_vids; struct rcu_head rcu; }; static inline int vlan_proto_idx(__be16 proto) { switch (proto) { case htons(ETH_P_8021Q): return VLAN_PROTO_8021Q; case htons(ETH_P_8021AD): return VLAN_PROTO_8021AD; default: WARN(1, "invalid VLAN protocol: 0x%04x\n", ntohs(proto)); return -EINVAL; } } static inline struct net_device *__vlan_group_get_device(struct vlan_group *vg, unsigned int pidx, u16 vlan_id) { struct net_device **array; array = vg->vlan_devices_arrays[pidx] [vlan_id / VLAN_GROUP_ARRAY_PART_LEN]; /* paired with smp_wmb() in vlan_group_prealloc_vid() */ smp_rmb(); return array ? array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] : NULL; } static inline struct net_device *vlan_group_get_device(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id) { int pidx = vlan_proto_idx(vlan_proto); if (pidx < 0) return NULL; return __vlan_group_get_device(vg, pidx, vlan_id); } static inline void vlan_group_set_device(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id, struct net_device *dev) { int pidx = vlan_proto_idx(vlan_proto); struct net_device **array; if (!vg || pidx < 0) return; array = vg->vlan_devices_arrays[pidx] [vlan_id / VLAN_GROUP_ARRAY_PART_LEN]; array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] = dev; } /* Must be invoked with rcu_read_lock or with RTNL. */ static inline struct net_device *vlan_find_dev(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id) { struct vlan_info *vlan_info = rcu_dereference_rtnl(real_dev->vlan_info); if (vlan_info) return vlan_group_get_device(&vlan_info->grp, vlan_proto, vlan_id); return NULL; } static inline netdev_features_t vlan_tnl_features(struct net_device *real_dev) { netdev_features_t ret; ret = real_dev->hw_enc_features & (NETIF_F_CSUM_MASK | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL); if ((ret & NETIF_F_GSO_ENCAP_ALL) && (ret & NETIF_F_CSUM_MASK)) return (ret & ~NETIF_F_CSUM_MASK) | NETIF_F_HW_CSUM; return 0; } #define vlan_group_for_each_dev(grp, i, dev) \ for ((i) = 0; i < VLAN_PROTO_NUM * VLAN_N_VID; i++) \ if (((dev) = __vlan_group_get_device((grp), (i) / VLAN_N_VID, \ (i) % VLAN_N_VID))) int vlan_filter_push_vids(struct vlan_info *vlan_info, __be16 proto); void vlan_filter_drop_vids(struct vlan_info *vlan_info, __be16 proto); /* found in vlan_dev.c */ void vlan_dev_set_ingress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio); int vlan_dev_set_egress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio); void vlan_dev_free_egress_priority(const struct net_device *dev); int vlan_dev_change_flags(const struct net_device *dev, u32 flag, u32 mask); void vlan_dev_get_realdev_name(const struct net_device *dev, char *result, size_t size); int vlan_check_real_dev(struct net_device *real_dev, __be16 protocol, u16 vlan_id, struct netlink_ext_ack *extack); void vlan_setup(struct net_device *dev); int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack); void unregister_vlan_dev(struct net_device *dev, struct list_head *head); bool vlan_dev_inherit_address(struct net_device *dev, struct net_device *real_dev); static inline u32 vlan_get_ingress_priority(struct net_device *dev, u16 vlan_tci) { struct vlan_dev_priv *vip = vlan_dev_priv(dev); return vip->ingress_priority_map[(vlan_tci >> VLAN_PRIO_SHIFT) & 0x7]; } #ifdef CONFIG_VLAN_8021Q_GVRP int vlan_gvrp_request_join(const struct net_device *dev); void vlan_gvrp_request_leave(const struct net_device *dev); int vlan_gvrp_init_applicant(struct net_device *dev); void vlan_gvrp_uninit_applicant(struct net_device *dev); int vlan_gvrp_init(void); void vlan_gvrp_uninit(void); #else static inline int vlan_gvrp_request_join(const struct net_device *dev) { return 0; } static inline void vlan_gvrp_request_leave(const struct net_device *dev) {} static inline int vlan_gvrp_init_applicant(struct net_device *dev) { return 0; } static inline void vlan_gvrp_uninit_applicant(struct net_device *dev) {} static inline int vlan_gvrp_init(void) { return 0; } static inline void vlan_gvrp_uninit(void) {} #endif #ifdef CONFIG_VLAN_8021Q_MVRP int vlan_mvrp_request_join(const struct net_device *dev); void vlan_mvrp_request_leave(const struct net_device *dev); int vlan_mvrp_init_applicant(struct net_device *dev); void vlan_mvrp_uninit_applicant(struct net_device *dev); int vlan_mvrp_init(void); void vlan_mvrp_uninit(void); #else static inline int vlan_mvrp_request_join(const struct net_device *dev) { return 0; } static inline void vlan_mvrp_request_leave(const struct net_device *dev) {} static inline int vlan_mvrp_init_applicant(struct net_device *dev) { return 0; } static inline void vlan_mvrp_uninit_applicant(struct net_device *dev) {} static inline int vlan_mvrp_init(void) { return 0; } static inline void vlan_mvrp_uninit(void) {} #endif extern const char vlan_fullname[]; extern const char vlan_version[]; int vlan_netlink_init(void); void vlan_netlink_fini(void); extern struct rtnl_link_ops vlan_link_ops; extern unsigned int vlan_net_id; struct proc_dir_entry; struct vlan_net { /* /proc/net/vlan */ struct proc_dir_entry *proc_vlan_dir; /* /proc/net/vlan/config */ struct proc_dir_entry *proc_vlan_conf; /* Determines interface naming scheme. */ unsigned short name_type; }; #endif /* !(__BEN_VLAN_802_1Q_INC__) */ |
| 1 1 22 133 18 1 1 1 1 1 | 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 | #ifndef INTERNAL_IO_SLIST_H #define INTERNAL_IO_SLIST_H #include <linux/io_uring_types.h> #define __wq_list_for_each(pos, head) \ for (pos = (head)->first; pos; pos = (pos)->next) #define wq_list_for_each(pos, prv, head) \ for (pos = (head)->first, prv = NULL; pos; prv = pos, pos = (pos)->next) #define wq_list_for_each_resume(pos, prv) \ for (; pos; prv = pos, pos = (pos)->next) #define wq_list_empty(list) (READ_ONCE((list)->first) == NULL) #define INIT_WQ_LIST(list) do { \ (list)->first = NULL; \ } while (0) static inline void wq_list_add_after(struct io_wq_work_node *node, struct io_wq_work_node *pos, struct io_wq_work_list *list) { struct io_wq_work_node *next = pos->next; pos->next = node; node->next = next; if (!next) list->last = node; } static inline void wq_list_add_tail(struct io_wq_work_node *node, struct io_wq_work_list *list) { node->next = NULL; if (!list->first) { list->last = node; WRITE_ONCE(list->first, node); } else { list->last->next = node; list->last = node; } } static inline void wq_list_add_head(struct io_wq_work_node *node, struct io_wq_work_list *list) { node->next = list->first; if (!node->next) list->last = node; WRITE_ONCE(list->first, node); } static inline void wq_list_cut(struct io_wq_work_list *list, struct io_wq_work_node *last, struct io_wq_work_node *prev) { /* first in the list, if prev==NULL */ if (!prev) WRITE_ONCE(list->first, last->next); else prev->next = last->next; if (last == list->last) list->last = prev; last->next = NULL; } static inline void __wq_list_splice(struct io_wq_work_list *list, struct io_wq_work_node *to) { list->last->next = to->next; to->next = list->first; INIT_WQ_LIST(list); } static inline bool wq_list_splice(struct io_wq_work_list *list, struct io_wq_work_node *to) { if (!wq_list_empty(list)) { __wq_list_splice(list, to); return true; } return false; } static inline void wq_stack_add_head(struct io_wq_work_node *node, struct io_wq_work_node *stack) { node->next = stack->next; stack->next = node; } static inline void wq_list_del(struct io_wq_work_list *list, struct io_wq_work_node *node, struct io_wq_work_node *prev) { wq_list_cut(list, node, prev); } static inline struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack) { struct io_wq_work_node *node = stack->next; stack->next = node->next; return node; } static inline struct io_wq_work *wq_next_work(struct io_wq_work *work) { if (!work->list.next) return NULL; return container_of(work->list.next, struct io_wq_work, list); } #endif // INTERNAL_IO_SLIST_H |
| 214 177 180 179 180 181 178 215 3 3 3 177 136 26 32 33 33 5 32 5 33 5 33 33 5 28 28 28 28 28 23 28 28 28 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * class.c - basic device class management * * Copyright (c) 2002-3 Patrick Mochel * Copyright (c) 2002-3 Open Source Development Labs * Copyright (c) 2003-2004 Greg Kroah-Hartman * Copyright (c) 2003-2004 IBM Corp. */ #include <linux/device/class.h> #include <linux/device.h> #include <linux/module.h> #include <linux/init.h> #include <linux/string.h> #include <linux/kdev_t.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/mutex.h> #include "base.h" /* /sys/class */ static struct kset *class_kset; #define to_class_attr(_attr) container_of(_attr, struct class_attribute, attr) /** * class_to_subsys - Turn a struct class into a struct subsys_private * * @class: pointer to the struct bus_type to look up * * The driver core internals need to work on the subsys_private structure, not * the external struct class pointer. This function walks the list of * registered classes in the system and finds the matching one and returns the * internal struct subsys_private that relates to that class. * * Note, the reference count of the return value is INCREMENTED if it is not * NULL. A call to subsys_put() must be done when finished with the pointer in * order for it to be properly freed. */ struct subsys_private *class_to_subsys(const struct class *class) { struct subsys_private *sp = NULL; struct kobject *kobj; if (!class || !class_kset) return NULL; spin_lock(&class_kset->list_lock); if (list_empty(&class_kset->list)) goto done; list_for_each_entry(kobj, &class_kset->list, entry) { struct kset *kset = container_of(kobj, struct kset, kobj); sp = container_of_const(kset, struct subsys_private, subsys); if (sp->class == class) goto done; } sp = NULL; done: sp = subsys_get(sp); spin_unlock(&class_kset->list_lock); return sp; } static ssize_t class_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct class_attribute *class_attr = to_class_attr(attr); struct subsys_private *cp = to_subsys_private(kobj); ssize_t ret = -EIO; if (class_attr->show) ret = class_attr->show(cp->class, class_attr, buf); return ret; } static ssize_t class_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct class_attribute *class_attr = to_class_attr(attr); struct subsys_private *cp = to_subsys_private(kobj); ssize_t ret = -EIO; if (class_attr->store) ret = class_attr->store(cp->class, class_attr, buf, count); return ret; } static void class_release(struct kobject *kobj) { struct subsys_private *cp = to_subsys_private(kobj); const struct class *class = cp->class; pr_debug("class '%s': release.\n", class->name); if (class->class_release) class->class_release(class); else pr_debug("class '%s' does not have a release() function, " "be careful\n", class->name); lockdep_unregister_key(&cp->lock_key); kfree(cp); } static const struct kobj_ns_type_operations *class_child_ns_type(const struct kobject *kobj) { const struct subsys_private *cp = to_subsys_private(kobj); const struct class *class = cp->class; return class->ns_type; } static const struct sysfs_ops class_sysfs_ops = { .show = class_attr_show, .store = class_attr_store, }; static const struct kobj_type class_ktype = { .sysfs_ops = &class_sysfs_ops, .release = class_release, .child_ns_type = class_child_ns_type, }; int class_create_file_ns(const struct class *cls, const struct class_attribute *attr, const void *ns) { struct subsys_private *sp = class_to_subsys(cls); int error; if (!sp) return -EINVAL; error = sysfs_create_file_ns(&sp->subsys.kobj, &attr->attr, ns); subsys_put(sp); return error; } EXPORT_SYMBOL_GPL(class_create_file_ns); void class_remove_file_ns(const struct class *cls, const struct class_attribute *attr, const void *ns) { struct subsys_private *sp = class_to_subsys(cls); if (!sp) return; sysfs_remove_file_ns(&sp->subsys.kobj, &attr->attr, ns); subsys_put(sp); } EXPORT_SYMBOL_GPL(class_remove_file_ns); static struct device *klist_class_to_dev(struct klist_node *n) { struct device_private *p = to_device_private_class(n); return p->device; } static void klist_class_dev_get(struct klist_node *n) { struct device *dev = klist_class_to_dev(n); get_device(dev); } static void klist_class_dev_put(struct klist_node *n) { struct device *dev = klist_class_to_dev(n); put_device(dev); } int class_register(const struct class *cls) { struct subsys_private *cp; struct lock_class_key *key; int error; pr_debug("device class '%s': registering\n", cls->name); cp = kzalloc(sizeof(*cp), GFP_KERNEL); if (!cp) return -ENOMEM; klist_init(&cp->klist_devices, klist_class_dev_get, klist_class_dev_put); INIT_LIST_HEAD(&cp->interfaces); kset_init(&cp->glue_dirs); key = &cp->lock_key; lockdep_register_key(key); __mutex_init(&cp->mutex, "subsys mutex", key); error = kobject_set_name(&cp->subsys.kobj, "%s", cls->name); if (error) goto err_out; cp->subsys.kobj.kset = class_kset; cp->subsys.kobj.ktype = &class_ktype; cp->class = cls; error = kset_register(&cp->subsys); if (error) goto err_out; error = sysfs_create_groups(&cp->subsys.kobj, cls->class_groups); if (error) { kobject_del(&cp->subsys.kobj); kfree_const(cp->subsys.kobj.name); goto err_out; } return 0; err_out: lockdep_unregister_key(key); kfree(cp); return error; } EXPORT_SYMBOL_GPL(class_register); void class_unregister(const struct class *cls) { struct subsys_private *sp = class_to_subsys(cls); if (!sp) return; pr_debug("device class '%s': unregistering\n", cls->name); sysfs_remove_groups(&sp->subsys.kobj, cls->class_groups); kset_unregister(&sp->subsys); subsys_put(sp); } EXPORT_SYMBOL_GPL(class_unregister); static void class_create_release(const struct class *cls) { pr_debug("%s called for %s\n", __func__, cls->name); kfree(cls); } /** * class_create - create a struct class structure * @name: pointer to a string for the name of this class. * * This is used to create a struct class pointer that can then be used * in calls to device_create(). * * Returns &struct class pointer on success, or ERR_PTR() on error. * * Note, the pointer created here is to be destroyed when finished by * making a call to class_destroy(). */ struct class *class_create(const char *name) { struct class *cls; int retval; cls = kzalloc(sizeof(*cls), GFP_KERNEL); if (!cls) { retval = -ENOMEM; goto error; } cls->name = name; cls->class_release = class_create_release; retval = class_register(cls); if (retval) goto error; return cls; error: kfree(cls); return ERR_PTR(retval); } EXPORT_SYMBOL_GPL(class_create); /** * class_destroy - destroys a struct class structure * @cls: pointer to the struct class that is to be destroyed * * Note, the pointer to be destroyed must have been created with a call * to class_create(). */ void class_destroy(const struct class *cls) { if (IS_ERR_OR_NULL(cls)) return; class_unregister(cls); } EXPORT_SYMBOL_GPL(class_destroy); /** * class_dev_iter_init - initialize class device iterator * @iter: class iterator to initialize * @class: the class we wanna iterate over * @start: the device to start iterating from, if any * @type: device_type of the devices to iterate over, NULL for all * * Initialize class iterator @iter such that it iterates over devices * of @class. If @start is set, the list iteration will start there, * otherwise if it is NULL, the iteration starts at the beginning of * the list. */ void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, const struct device *start, const struct device_type *type) { struct subsys_private *sp = class_to_subsys(class); struct klist_node *start_knode = NULL; if (!sp) return; if (start) start_knode = &start->p->knode_class; klist_iter_init_node(&sp->klist_devices, &iter->ki, start_knode); iter->type = type; iter->sp = sp; } EXPORT_SYMBOL_GPL(class_dev_iter_init); /** * class_dev_iter_next - iterate to the next device * @iter: class iterator to proceed * * Proceed @iter to the next device and return it. Returns NULL if * iteration is complete. * * The returned device is referenced and won't be released till * iterator is proceed to the next device or exited. The caller is * free to do whatever it wants to do with the device including * calling back into class code. */ struct device *class_dev_iter_next(struct class_dev_iter *iter) { struct klist_node *knode; struct device *dev; while (1) { knode = klist_next(&iter->ki); if (!knode) return NULL; dev = klist_class_to_dev(knode); if (!iter->type || iter->type == dev->type) return dev; } } EXPORT_SYMBOL_GPL(class_dev_iter_next); /** * class_dev_iter_exit - finish iteration * @iter: class iterator to finish * * Finish an iteration. Always call this function after iteration is * complete whether the iteration ran till the end or not. */ void class_dev_iter_exit(struct class_dev_iter *iter) { klist_iter_exit(&iter->ki); subsys_put(iter->sp); } EXPORT_SYMBOL_GPL(class_dev_iter_exit); /** * class_for_each_device - device iterator * @class: the class we're iterating * @start: the device to start with in the list, if any. * @data: data for the callback * @fn: function to be called for each device * * Iterate over @class's list of devices, and call @fn for each, * passing it @data. If @start is set, the list iteration will start * there, otherwise if it is NULL, the iteration starts at the * beginning of the list. * * We check the return of @fn each time. If it returns anything * other than 0, we break out and return that value. * * @fn is allowed to do anything including calling back into class * code. There's no locking restriction. */ int class_for_each_device(const struct class *class, const struct device *start, void *data, int (*fn)(struct device *, void *)) { struct subsys_private *sp = class_to_subsys(class); struct class_dev_iter iter; struct device *dev; int error = 0; if (!class) return -EINVAL; if (!sp) { WARN(1, "%s called for class '%s' before it was initialized", __func__, class->name); return -EINVAL; } class_dev_iter_init(&iter, class, start, NULL); while ((dev = class_dev_iter_next(&iter))) { error = fn(dev, data); if (error) break; } class_dev_iter_exit(&iter); subsys_put(sp); return error; } EXPORT_SYMBOL_GPL(class_for_each_device); /** * class_find_device - device iterator for locating a particular device * @class: the class we're iterating * @start: Device to begin with * @data: data for the match function * @match: function to check device * * This is similar to the class_for_each_dev() function above, but it * returns a reference to a device that is 'found' for later use, as * determined by the @match callback. * * The callback should return 0 if the device doesn't match and non-zero * if it does. If the callback returns non-zero, this function will * return to the caller and not iterate over any more devices. * * Note, you will need to drop the reference with put_device() after use. * * @match is allowed to do anything including calling back into class * code. There's no locking restriction. */ struct device *class_find_device(const struct class *class, const struct device *start, const void *data, int (*match)(struct device *, const void *)) { struct subsys_private *sp = class_to_subsys(class); struct class_dev_iter iter; struct device *dev; if (!class) return NULL; if (!sp) { WARN(1, "%s called for class '%s' before it was initialized", __func__, class->name); return NULL; } class_dev_iter_init(&iter, class, start, NULL); while ((dev = class_dev_iter_next(&iter))) { if (match(dev, data)) { get_device(dev); break; } } class_dev_iter_exit(&iter); subsys_put(sp); return dev; } EXPORT_SYMBOL_GPL(class_find_device); int class_interface_register(struct class_interface *class_intf) { struct subsys_private *sp; const struct class *parent; struct class_dev_iter iter; struct device *dev; if (!class_intf || !class_intf->class) return -ENODEV; parent = class_intf->class; sp = class_to_subsys(parent); if (!sp) return -EINVAL; /* * Reference in sp is now incremented and will be dropped when * the interface is removed in the call to class_interface_unregister() */ mutex_lock(&sp->mutex); list_add_tail(&class_intf->node, &sp->interfaces); if (class_intf->add_dev) { class_dev_iter_init(&iter, parent, NULL, NULL); while ((dev = class_dev_iter_next(&iter))) class_intf->add_dev(dev); class_dev_iter_exit(&iter); } mutex_unlock(&sp->mutex); return 0; } EXPORT_SYMBOL_GPL(class_interface_register); void class_interface_unregister(struct class_interface *class_intf) { struct subsys_private *sp; const struct class *parent = class_intf->class; struct class_dev_iter iter; struct device *dev; if (!parent) return; sp = class_to_subsys(parent); if (!sp) return; mutex_lock(&sp->mutex); list_del_init(&class_intf->node); if (class_intf->remove_dev) { class_dev_iter_init(&iter, parent, NULL, NULL); while ((dev = class_dev_iter_next(&iter))) class_intf->remove_dev(dev); class_dev_iter_exit(&iter); } mutex_unlock(&sp->mutex); /* * Decrement the reference count twice, once for the class_to_subsys() * call in the start of this function, and the second one from the * reference increment in class_interface_register() */ subsys_put(sp); subsys_put(sp); } EXPORT_SYMBOL_GPL(class_interface_unregister); ssize_t show_class_attr_string(const struct class *class, const struct class_attribute *attr, char *buf) { struct class_attribute_string *cs; cs = container_of(attr, struct class_attribute_string, attr); return sysfs_emit(buf, "%s\n", cs->str); } EXPORT_SYMBOL_GPL(show_class_attr_string); struct class_compat { struct kobject *kobj; }; /** * class_compat_register - register a compatibility class * @name: the name of the class * * Compatibility class are meant as a temporary user-space compatibility * workaround when converting a family of class devices to a bus devices. */ struct class_compat *class_compat_register(const char *name) { struct class_compat *cls; cls = kmalloc(sizeof(struct class_compat), GFP_KERNEL); if (!cls) return NULL; cls->kobj = kobject_create_and_add(name, &class_kset->kobj); if (!cls->kobj) { kfree(cls); return NULL; } return cls; } EXPORT_SYMBOL_GPL(class_compat_register); /** * class_compat_unregister - unregister a compatibility class * @cls: the class to unregister */ void class_compat_unregister(struct class_compat *cls) { kobject_put(cls->kobj); kfree(cls); } EXPORT_SYMBOL_GPL(class_compat_unregister); /** * class_compat_create_link - create a compatibility class device link to * a bus device * @cls: the compatibility class * @dev: the target bus device * @device_link: an optional device to which a "device" link should be created */ int class_compat_create_link(struct class_compat *cls, struct device *dev, struct device *device_link) { int error; error = sysfs_create_link(cls->kobj, &dev->kobj, dev_name(dev)); if (error) return error; /* * Optionally add a "device" link (typically to the parent), as a * class device would have one and we want to provide as much * backwards compatibility as possible. */ if (device_link) { error = sysfs_create_link(&dev->kobj, &device_link->kobj, "device"); if (error) sysfs_remove_link(cls->kobj, dev_name(dev)); } return error; } EXPORT_SYMBOL_GPL(class_compat_create_link); /** * class_compat_remove_link - remove a compatibility class device link to * a bus device * @cls: the compatibility class * @dev: the target bus device * @device_link: an optional device to which a "device" link was previously * created */ void class_compat_remove_link(struct class_compat *cls, struct device *dev, struct device *device_link) { if (device_link) sysfs_remove_link(&dev->kobj, "device"); sysfs_remove_link(cls->kobj, dev_name(dev)); } EXPORT_SYMBOL_GPL(class_compat_remove_link); /** * class_is_registered - determine if at this moment in time, a class is * registered in the driver core or not. * @class: the class to check * * Returns a boolean to state if the class is registered in the driver core * or not. Note that the value could switch right after this call is made, * so only use this in places where you "know" it is safe to do so (usually * to determine if the specific class has been registered yet or not). * * Be careful in using this. */ bool class_is_registered(const struct class *class) { struct subsys_private *sp = class_to_subsys(class); bool is_initialized = false; if (sp) { is_initialized = true; subsys_put(sp); } return is_initialized; } EXPORT_SYMBOL_GPL(class_is_registered); int __init classes_init(void) { class_kset = kset_create_and_add("class", NULL, NULL); if (!class_kset) return -ENOMEM; return 0; } |
| 11 11 9 9 6 9 11 47 47 46 47 44 11 47 47 47 48 11 11 11 3 3 1 105 104 12 106 1 106 94 92 49 13 13 13 11 11 92 35 35 6 6 6 6 6 6 6 6 6 6 6 6 92 92 9 9 91 9 9 9 90 9 13 13 11 10 11 11 11 11 3 3 3 11 11 11 11 11 11 11 11 13 2 2 2 92 91 92 55 47 45 47 46 46 44 44 44 6 2 2 4 4 4 4 4 4 4 4 44 4 87 4 92 63 64 59 63 16 62 64 63 6 6 6 1 5 5 6 92 91 91 92 36 1 36 36 36 36 35 36 36 36 1 35 34 34 35 35 35 36 1 1 1 1 1 36 38 38 38 38 38 37 37 15 14 1 1 1 1 16 37 37 37 2 2 36 35 35 35 3 3 36 35 36 36 36 36 35 189 6 17 1 16 5 16 16 16 15 14 10 10 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/runtime.c - Helper functions for device runtime PM * * Copyright (c) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc. * Copyright (C) 2010 Alan Stern <stern@rowland.harvard.edu> */ #include <linux/sched/mm.h> #include <linux/ktime.h> #include <linux/hrtimer.h> #include <linux/export.h> #include <linux/pm_runtime.h> #include <linux/pm_wakeirq.h> #include <linux/rculist.h> #include <trace/events/rpm.h> #include "../base.h" #include "power.h" typedef int (*pm_callback_t)(struct device *); static pm_callback_t __rpm_get_callback(struct device *dev, size_t cb_offset) { pm_callback_t cb; const struct dev_pm_ops *ops; if (dev->pm_domain) ops = &dev->pm_domain->ops; else if (dev->type && dev->type->pm) ops = dev->type->pm; else if (dev->class && dev->class->pm) ops = dev->class->pm; else if (dev->bus && dev->bus->pm) ops = dev->bus->pm; else ops = NULL; if (ops) cb = *(pm_callback_t *)((void *)ops + cb_offset); else cb = NULL; if (!cb && dev->driver && dev->driver->pm) cb = *(pm_callback_t *)((void *)dev->driver->pm + cb_offset); return cb; } #define RPM_GET_CALLBACK(dev, callback) \ __rpm_get_callback(dev, offsetof(struct dev_pm_ops, callback)) static int rpm_resume(struct device *dev, int rpmflags); static int rpm_suspend(struct device *dev, int rpmflags); /** * update_pm_runtime_accounting - Update the time accounting of power states * @dev: Device to update the accounting for * * In order to be able to have time accounting of the various power states * (as used by programs such as PowerTOP to show the effectiveness of runtime * PM), we need to track the time spent in each state. * update_pm_runtime_accounting must be called each time before the * runtime_status field is updated, to account the time in the old state * correctly. */ static void update_pm_runtime_accounting(struct device *dev) { u64 now, last, delta; if (dev->power.disable_depth > 0) return; last = dev->power.accounting_timestamp; now = ktime_get_mono_fast_ns(); dev->power.accounting_timestamp = now; /* * Because ktime_get_mono_fast_ns() is not monotonic during * timekeeping updates, ensure that 'now' is after the last saved * timesptamp. */ if (now < last) return; delta = now - last; if (dev->power.runtime_status == RPM_SUSPENDED) dev->power.suspended_time += delta; else dev->power.active_time += delta; } static void __update_runtime_status(struct device *dev, enum rpm_status status) { update_pm_runtime_accounting(dev); trace_rpm_status(dev, status); dev->power.runtime_status = status; } static u64 rpm_get_accounted_time(struct device *dev, bool suspended) { u64 time; unsigned long flags; spin_lock_irqsave(&dev->power.lock, flags); update_pm_runtime_accounting(dev); time = suspended ? dev->power.suspended_time : dev->power.active_time; spin_unlock_irqrestore(&dev->power.lock, flags); return time; } u64 pm_runtime_active_time(struct device *dev) { return rpm_get_accounted_time(dev, false); } u64 pm_runtime_suspended_time(struct device *dev) { return rpm_get_accounted_time(dev, true); } EXPORT_SYMBOL_GPL(pm_runtime_suspended_time); /** * pm_runtime_deactivate_timer - Deactivate given device's suspend timer. * @dev: Device to handle. */ static void pm_runtime_deactivate_timer(struct device *dev) { if (dev->power.timer_expires > 0) { hrtimer_try_to_cancel(&dev->power.suspend_timer); dev->power.timer_expires = 0; } } /** * pm_runtime_cancel_pending - Deactivate suspend timer and cancel requests. * @dev: Device to handle. */ static void pm_runtime_cancel_pending(struct device *dev) { pm_runtime_deactivate_timer(dev); /* * In case there's a request pending, make sure its work function will * return without doing anything. */ dev->power.request = RPM_REQ_NONE; } /* * pm_runtime_autosuspend_expiration - Get a device's autosuspend-delay expiration time. * @dev: Device to handle. * * Compute the autosuspend-delay expiration time based on the device's * power.last_busy time. If the delay has already expired or is disabled * (negative) or the power.use_autosuspend flag isn't set, return 0. * Otherwise return the expiration time in nanoseconds (adjusted to be nonzero). * * This function may be called either with or without dev->power.lock held. * Either way it can be racy, since power.last_busy may be updated at any time. */ u64 pm_runtime_autosuspend_expiration(struct device *dev) { int autosuspend_delay; u64 expires; if (!dev->power.use_autosuspend) return 0; autosuspend_delay = READ_ONCE(dev->power.autosuspend_delay); if (autosuspend_delay < 0) return 0; expires = READ_ONCE(dev->power.last_busy); expires += (u64)autosuspend_delay * NSEC_PER_MSEC; if (expires > ktime_get_mono_fast_ns()) return expires; /* Expires in the future */ return 0; } EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration); static int dev_memalloc_noio(struct device *dev, void *data) { return dev->power.memalloc_noio; } /* * pm_runtime_set_memalloc_noio - Set a device's memalloc_noio flag. * @dev: Device to handle. * @enable: True for setting the flag and False for clearing the flag. * * Set the flag for all devices in the path from the device to the * root device in the device tree if @enable is true, otherwise clear * the flag for devices in the path whose siblings don't set the flag. * * The function should only be called by block device, or network * device driver for solving the deadlock problem during runtime * resume/suspend: * * If memory allocation with GFP_KERNEL is called inside runtime * resume/suspend callback of any one of its ancestors(or the * block device itself), the deadlock may be triggered inside the * memory allocation since it might not complete until the block * device becomes active and the involed page I/O finishes. The * situation is pointed out first by Alan Stern. Network device * are involved in iSCSI kind of situation. * * The lock of dev_hotplug_mutex is held in the function for handling * hotplug race because pm_runtime_set_memalloc_noio() may be called * in async probe(). * * The function should be called between device_add() and device_del() * on the affected device(block/network device). */ void pm_runtime_set_memalloc_noio(struct device *dev, bool enable) { static DEFINE_MUTEX(dev_hotplug_mutex); mutex_lock(&dev_hotplug_mutex); for (;;) { bool enabled; /* hold power lock since bitfield is not SMP-safe. */ spin_lock_irq(&dev->power.lock); enabled = dev->power.memalloc_noio; dev->power.memalloc_noio = enable; spin_unlock_irq(&dev->power.lock); /* * not need to enable ancestors any more if the device * has been enabled. */ if (enabled && enable) break; dev = dev->parent; /* * clear flag of the parent device only if all the * children don't set the flag because ancestor's * flag was set by any one of the descendants. */ if (!dev || (!enable && device_for_each_child(dev, NULL, dev_memalloc_noio))) break; } mutex_unlock(&dev_hotplug_mutex); } EXPORT_SYMBOL_GPL(pm_runtime_set_memalloc_noio); /** * rpm_check_suspend_allowed - Test whether a device may be suspended. * @dev: Device to test. */ static int rpm_check_suspend_allowed(struct device *dev) { int retval = 0; if (dev->power.runtime_error) retval = -EINVAL; else if (dev->power.disable_depth > 0) retval = -EACCES; else if (atomic_read(&dev->power.usage_count)) retval = -EAGAIN; else if (!dev->power.ignore_children && atomic_read(&dev->power.child_count)) retval = -EBUSY; /* Pending resume requests take precedence over suspends. */ else if ((dev->power.deferred_resume && dev->power.runtime_status == RPM_SUSPENDING) || (dev->power.request_pending && dev->power.request == RPM_REQ_RESUME)) retval = -EAGAIN; else if (__dev_pm_qos_resume_latency(dev) == 0) retval = -EPERM; else if (dev->power.runtime_status == RPM_SUSPENDED) retval = 1; return retval; } static int rpm_get_suppliers(struct device *dev) { struct device_link *link; list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) { int retval; if (!(link->flags & DL_FLAG_PM_RUNTIME)) continue; retval = pm_runtime_get_sync(link->supplier); /* Ignore suppliers with disabled runtime PM. */ if (retval < 0 && retval != -EACCES) { pm_runtime_put_noidle(link->supplier); return retval; } refcount_inc(&link->rpm_active); } return 0; } /** * pm_runtime_release_supplier - Drop references to device link's supplier. * @link: Target device link. * * Drop all runtime PM references associated with @link to its supplier device. */ void pm_runtime_release_supplier(struct device_link *link) { struct device *supplier = link->supplier; /* * The additional power.usage_count check is a safety net in case * the rpm_active refcount becomes saturated, in which case * refcount_dec_not_one() would return true forever, but it is not * strictly necessary. */ while (refcount_dec_not_one(&link->rpm_active) && atomic_read(&supplier->power.usage_count) > 0) pm_runtime_put_noidle(supplier); } static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend) { struct device_link *link; list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) { pm_runtime_release_supplier(link); if (try_to_suspend) pm_request_idle(link->supplier); } } static void rpm_put_suppliers(struct device *dev) { __rpm_put_suppliers(dev, true); } static void rpm_suspend_suppliers(struct device *dev) { struct device_link *link; int idx = device_links_read_lock(); list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) pm_request_idle(link->supplier); device_links_read_unlock(idx); } /** * __rpm_callback - Run a given runtime PM callback for a given device. * @cb: Runtime PM callback to run. * @dev: Device to run the callback for. */ static int __rpm_callback(int (*cb)(struct device *), struct device *dev) __releases(&dev->power.lock) __acquires(&dev->power.lock) { int retval = 0, idx; bool use_links = dev->power.links_count > 0; if (dev->power.irq_safe) { spin_unlock(&dev->power.lock); } else { spin_unlock_irq(&dev->power.lock); /* * Resume suppliers if necessary. * * The device's runtime PM status cannot change until this * routine returns, so it is safe to read the status outside of * the lock. */ if (use_links && dev->power.runtime_status == RPM_RESUMING) { idx = device_links_read_lock(); retval = rpm_get_suppliers(dev); if (retval) { rpm_put_suppliers(dev); goto fail; } device_links_read_unlock(idx); } } if (cb) retval = cb(dev); if (dev->power.irq_safe) { spin_lock(&dev->power.lock); } else { /* * If the device is suspending and the callback has returned * success, drop the usage counters of the suppliers that have * been reference counted on its resume. * * Do that if resume fails too. */ if (use_links && ((dev->power.runtime_status == RPM_SUSPENDING && !retval) || (dev->power.runtime_status == RPM_RESUMING && retval))) { idx = device_links_read_lock(); __rpm_put_suppliers(dev, false); fail: device_links_read_unlock(idx); } spin_lock_irq(&dev->power.lock); } return retval; } /** * rpm_callback - Run a given runtime PM callback for a given device. * @cb: Runtime PM callback to run. * @dev: Device to run the callback for. */ static int rpm_callback(int (*cb)(struct device *), struct device *dev) { int retval; if (dev->power.memalloc_noio) { unsigned int noio_flag; /* * Deadlock might be caused if memory allocation with * GFP_KERNEL happens inside runtime_suspend and * runtime_resume callbacks of one block device's * ancestor or the block device itself. Network * device might be thought as part of iSCSI block * device, so network device and its ancestor should * be marked as memalloc_noio too. */ noio_flag = memalloc_noio_save(); retval = __rpm_callback(cb, dev); memalloc_noio_restore(noio_flag); } else { retval = __rpm_callback(cb, dev); } dev->power.runtime_error = retval; return retval != -EACCES ? retval : -EIO; } /** * rpm_idle - Notify device bus type if the device can be suspended. * @dev: Device to notify the bus type about. * @rpmflags: Flag bits. * * Check if the device's runtime PM status allows it to be suspended. If * another idle notification has been started earlier, return immediately. If * the RPM_ASYNC flag is set then queue an idle-notification request; otherwise * run the ->runtime_idle() callback directly. If the ->runtime_idle callback * doesn't exist or if it returns 0, call rpm_suspend with the RPM_AUTO flag. * * This function must be called under dev->power.lock with interrupts disabled. */ static int rpm_idle(struct device *dev, int rpmflags) { int (*callback)(struct device *); int retval; trace_rpm_idle(dev, rpmflags); retval = rpm_check_suspend_allowed(dev); if (retval < 0) ; /* Conditions are wrong. */ /* Idle notifications are allowed only in the RPM_ACTIVE state. */ else if (dev->power.runtime_status != RPM_ACTIVE) retval = -EAGAIN; /* * Any pending request other than an idle notification takes * precedence over us, except that the timer may be running. */ else if (dev->power.request_pending && dev->power.request > RPM_REQ_IDLE) retval = -EAGAIN; /* Act as though RPM_NOWAIT is always set. */ else if (dev->power.idle_notification) retval = -EINPROGRESS; if (retval) goto out; /* Pending requests need to be canceled. */ dev->power.request = RPM_REQ_NONE; callback = RPM_GET_CALLBACK(dev, runtime_idle); /* If no callback assume success. */ if (!callback || dev->power.no_callbacks) goto out; /* Carry out an asynchronous or a synchronous idle notification. */ if (rpmflags & RPM_ASYNC) { dev->power.request = RPM_REQ_IDLE; if (!dev->power.request_pending) { dev->power.request_pending = true; queue_work(pm_wq, &dev->power.work); } trace_rpm_return_int(dev, _THIS_IP_, 0); return 0; } dev->power.idle_notification = true; if (dev->power.irq_safe) spin_unlock(&dev->power.lock); else spin_unlock_irq(&dev->power.lock); retval = callback(dev); if (dev->power.irq_safe) spin_lock(&dev->power.lock); else spin_lock_irq(&dev->power.lock); dev->power.idle_notification = false; wake_up_all(&dev->power.wait_queue); out: trace_rpm_return_int(dev, _THIS_IP_, retval); return retval ? retval : rpm_suspend(dev, rpmflags | RPM_AUTO); } /** * rpm_suspend - Carry out runtime suspend of given device. * @dev: Device to suspend. * @rpmflags: Flag bits. * * Check if the device's runtime PM status allows it to be suspended. * Cancel a pending idle notification, autosuspend or suspend. If * another suspend has been started earlier, either return immediately * or wait for it to finish, depending on the RPM_NOWAIT and RPM_ASYNC * flags. If the RPM_ASYNC flag is set then queue a suspend request; * otherwise run the ->runtime_suspend() callback directly. When * ->runtime_suspend succeeded, if a deferred resume was requested while * the callback was running then carry it out, otherwise send an idle * notification for its parent (if the suspend succeeded and both * ignore_children of parent->power and irq_safe of dev->power are not set). * If ->runtime_suspend failed with -EAGAIN or -EBUSY, and if the RPM_AUTO * flag is set and the next autosuspend-delay expiration time is in the * future, schedule another autosuspend attempt. * * This function must be called under dev->power.lock with interrupts disabled. */ static int rpm_suspend(struct device *dev, int rpmflags) __releases(&dev->power.lock) __acquires(&dev->power.lock) { int (*callback)(struct device *); struct device *parent = NULL; int retval; trace_rpm_suspend(dev, rpmflags); repeat: retval = rpm_check_suspend_allowed(dev); if (retval < 0) goto out; /* Conditions are wrong. */ /* Synchronous suspends are not allowed in the RPM_RESUMING state. */ if (dev->power.runtime_status == RPM_RESUMING && !(rpmflags & RPM_ASYNC)) retval = -EAGAIN; if (retval) goto out; /* If the autosuspend_delay time hasn't expired yet, reschedule. */ if ((rpmflags & RPM_AUTO) && dev->power.runtime_status != RPM_SUSPENDING) { u64 expires = pm_runtime_autosuspend_expiration(dev); if (expires != 0) { /* Pending requests need to be canceled. */ dev->power.request = RPM_REQ_NONE; /* * Optimization: If the timer is already running and is * set to expire at or before the autosuspend delay, * avoid the overhead of resetting it. Just let it * expire; pm_suspend_timer_fn() will take care of the * rest. */ if (!(dev->power.timer_expires && dev->power.timer_expires <= expires)) { /* * We add a slack of 25% to gather wakeups * without sacrificing the granularity. */ u64 slack = (u64)READ_ONCE(dev->power.autosuspend_delay) * (NSEC_PER_MSEC >> 2); dev->power.timer_expires = expires; hrtimer_start_range_ns(&dev->power.suspend_timer, ns_to_ktime(expires), slack, HRTIMER_MODE_ABS); } dev->power.timer_autosuspends = 1; goto out; } } /* Other scheduled or pending requests need to be canceled. */ pm_runtime_cancel_pending(dev); if (dev->power.runtime_status == RPM_SUSPENDING) { DEFINE_WAIT(wait); if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) { retval = -EINPROGRESS; goto out; } if (dev->power.irq_safe) { spin_unlock(&dev->power.lock); cpu_relax(); spin_lock(&dev->power.lock); goto repeat; } /* Wait for the other suspend running in parallel with us. */ for (;;) { prepare_to_wait(&dev->power.wait_queue, &wait, TASK_UNINTERRUPTIBLE); if (dev->power.runtime_status != RPM_SUSPENDING) break; spin_unlock_irq(&dev->power.lock); schedule(); spin_lock_irq(&dev->power.lock); } finish_wait(&dev->power.wait_queue, &wait); goto repeat; } if (dev->power.no_callbacks) goto no_callback; /* Assume success. */ /* Carry out an asynchronous or a synchronous suspend. */ if (rpmflags & RPM_ASYNC) { dev->power.request = (rpmflags & RPM_AUTO) ? RPM_REQ_AUTOSUSPEND : RPM_REQ_SUSPEND; if (!dev->power.request_pending) { dev->power.request_pending = true; queue_work(pm_wq, &dev->power.work); } goto out; } __update_runtime_status(dev, RPM_SUSPENDING); callback = RPM_GET_CALLBACK(dev, runtime_suspend); dev_pm_enable_wake_irq_check(dev, true); retval = rpm_callback(callback, dev); if (retval) goto fail; dev_pm_enable_wake_irq_complete(dev); no_callback: __update_runtime_status(dev, RPM_SUSPENDED); pm_runtime_deactivate_timer(dev); if (dev->parent) { parent = dev->parent; atomic_add_unless(&parent->power.child_count, -1, 0); } wake_up_all(&dev->power.wait_queue); if (dev->power.deferred_resume) { dev->power.deferred_resume = false; rpm_resume(dev, 0); retval = -EAGAIN; goto out; } if (dev->power.irq_safe) goto out; /* Maybe the parent is now able to suspend. */ if (parent && !parent->power.ignore_children) { spin_unlock(&dev->power.lock); spin_lock(&parent->power.lock); rpm_idle(parent, RPM_ASYNC); spin_unlock(&parent->power.lock); spin_lock(&dev->power.lock); } /* Maybe the suppliers are now able to suspend. */ if (dev->power.links_count > 0) { spin_unlock_irq(&dev->power.lock); rpm_suspend_suppliers(dev); spin_lock_irq(&dev->power.lock); } out: trace_rpm_return_int(dev, _THIS_IP_, retval); return retval; fail: dev_pm_disable_wake_irq_check(dev, true); __update_runtime_status(dev, RPM_ACTIVE); dev->power.deferred_resume = false; wake_up_all(&dev->power.wait_queue); if (retval == -EAGAIN || retval == -EBUSY) { dev->power.runtime_error = 0; /* * If the callback routine failed an autosuspend, and * if the last_busy time has been updated so that there * is a new autosuspend expiration time, automatically * reschedule another autosuspend. */ if ((rpmflags & RPM_AUTO) && pm_runtime_autosuspend_expiration(dev) != 0) goto repeat; } else { pm_runtime_cancel_pending(dev); } goto out; } /** * rpm_resume - Carry out runtime resume of given device. * @dev: Device to resume. * @rpmflags: Flag bits. * * Check if the device's runtime PM status allows it to be resumed. Cancel * any scheduled or pending requests. If another resume has been started * earlier, either return immediately or wait for it to finish, depending on the * RPM_NOWAIT and RPM_ASYNC flags. Similarly, if there's a suspend running in * parallel with this function, either tell the other process to resume after * suspending (deferred_resume) or wait for it to finish. If the RPM_ASYNC * flag is set then queue a resume request; otherwise run the * ->runtime_resume() callback directly. Queue an idle notification for the * device if the resume succeeded. * * This function must be called under dev->power.lock with interrupts disabled. */ static int rpm_resume(struct device *dev, int rpmflags) __releases(&dev->power.lock) __acquires(&dev->power.lock) { int (*callback)(struct device *); struct device *parent = NULL; int retval = 0; trace_rpm_resume(dev, rpmflags); repeat: if (dev->power.runtime_error) { retval = -EINVAL; } else if (dev->power.disable_depth > 0) { if (dev->power.runtime_status == RPM_ACTIVE && dev->power.last_status == RPM_ACTIVE) retval = 1; else retval = -EACCES; } if (retval) goto out; /* * Other scheduled or pending requests need to be canceled. Small * optimization: If an autosuspend timer is running, leave it running * rather than cancelling it now only to restart it again in the near * future. */ dev->power.request = RPM_REQ_NONE; if (!dev->power.timer_autosuspends) pm_runtime_deactivate_timer(dev); if (dev->power.runtime_status == RPM_ACTIVE) { retval = 1; goto out; } if (dev->power.runtime_status == RPM_RESUMING || dev->power.runtime_status == RPM_SUSPENDING) { DEFINE_WAIT(wait); if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) { if (dev->power.runtime_status == RPM_SUSPENDING) { dev->power.deferred_resume = true; if (rpmflags & RPM_NOWAIT) retval = -EINPROGRESS; } else { retval = -EINPROGRESS; } goto out; } if (dev->power.irq_safe) { spin_unlock(&dev->power.lock); cpu_relax(); spin_lock(&dev->power.lock); goto repeat; } /* Wait for the operation carried out in parallel with us. */ for (;;) { prepare_to_wait(&dev->power.wait_queue, &wait, TASK_UNINTERRUPTIBLE); if (dev->power.runtime_status != RPM_RESUMING && dev->power.runtime_status != RPM_SUSPENDING) break; spin_unlock_irq(&dev->power.lock); schedule(); spin_lock_irq(&dev->power.lock); } finish_wait(&dev->power.wait_queue, &wait); goto repeat; } /* * See if we can skip waking up the parent. This is safe only if * power.no_callbacks is set, because otherwise we don't know whether * the resume will actually succeed. */ if (dev->power.no_callbacks && !parent && dev->parent) { spin_lock_nested(&dev->parent->power.lock, SINGLE_DEPTH_NESTING); if (dev->parent->power.disable_depth > 0 || dev->parent->power.ignore_children || dev->parent->power.runtime_status == RPM_ACTIVE) { atomic_inc(&dev->parent->power.child_count); spin_unlock(&dev->parent->power.lock); retval = 1; goto no_callback; /* Assume success. */ } spin_unlock(&dev->parent->power.lock); } /* Carry out an asynchronous or a synchronous resume. */ if (rpmflags & RPM_ASYNC) { dev->power.request = RPM_REQ_RESUME; if (!dev->power.request_pending) { dev->power.request_pending = true; queue_work(pm_wq, &dev->power.work); } retval = 0; goto out; } if (!parent && dev->parent) { /* * Increment the parent's usage counter and resume it if * necessary. Not needed if dev is irq-safe; then the * parent is permanently resumed. */ parent = dev->parent; if (dev->power.irq_safe) goto skip_parent; spin_unlock(&dev->power.lock); pm_runtime_get_noresume(parent); spin_lock(&parent->power.lock); /* * Resume the parent if it has runtime PM enabled and not been * set to ignore its children. */ if (!parent->power.disable_depth && !parent->power.ignore_children) { rpm_resume(parent, 0); if (parent->power.runtime_status != RPM_ACTIVE) retval = -EBUSY; } spin_unlock(&parent->power.lock); spin_lock(&dev->power.lock); if (retval) goto out; goto repeat; } skip_parent: if (dev->power.no_callbacks) goto no_callback; /* Assume success. */ __update_runtime_status(dev, RPM_RESUMING); callback = RPM_GET_CALLBACK(dev, runtime_resume); dev_pm_disable_wake_irq_check(dev, false); retval = rpm_callback(callback, dev); if (retval) { __update_runtime_status(dev, RPM_SUSPENDED); pm_runtime_cancel_pending(dev); dev_pm_enable_wake_irq_check(dev, false); } else { no_callback: __update_runtime_status(dev, RPM_ACTIVE); pm_runtime_mark_last_busy(dev); if (parent) atomic_inc(&parent->power.child_count); } wake_up_all(&dev->power.wait_queue); if (retval >= 0) rpm_idle(dev, RPM_ASYNC); out: if (parent && !dev->power.irq_safe) { spin_unlock_irq(&dev->power.lock); pm_runtime_put(parent); spin_lock_irq(&dev->power.lock); } trace_rpm_return_int(dev, _THIS_IP_, retval); return retval; } /** * pm_runtime_work - Universal runtime PM work function. * @work: Work structure used for scheduling the execution of this function. * * Use @work to get the device object the work is to be done for, determine what * is to be done and execute the appropriate runtime PM function. */ static void pm_runtime_work(struct work_struct *work) { struct device *dev = container_of(work, struct device, power.work); enum rpm_request req; spin_lock_irq(&dev->power.lock); if (!dev->power.request_pending) goto out; req = dev->power.request; dev->power.request = RPM_REQ_NONE; dev->power.request_pending = false; switch (req) { case RPM_REQ_NONE: break; case RPM_REQ_IDLE: rpm_idle(dev, RPM_NOWAIT); break; case RPM_REQ_SUSPEND: rpm_suspend(dev, RPM_NOWAIT); break; case RPM_REQ_AUTOSUSPEND: rpm_suspend(dev, RPM_NOWAIT | RPM_AUTO); break; case RPM_REQ_RESUME: rpm_resume(dev, RPM_NOWAIT); break; } out: spin_unlock_irq(&dev->power.lock); } /** * pm_suspend_timer_fn - Timer function for pm_schedule_suspend(). * @timer: hrtimer used by pm_schedule_suspend(). * * Check if the time is right and queue a suspend request. */ static enum hrtimer_restart pm_suspend_timer_fn(struct hrtimer *timer) { struct device *dev = container_of(timer, struct device, power.suspend_timer); unsigned long flags; u64 expires; spin_lock_irqsave(&dev->power.lock, flags); expires = dev->power.timer_expires; /* * If 'expires' is after the current time, we've been called * too early. */ if (expires > 0 && expires < ktime_get_mono_fast_ns()) { dev->power.timer_expires = 0; rpm_suspend(dev, dev->power.timer_autosuspends ? (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC); } spin_unlock_irqrestore(&dev->power.lock, flags); return HRTIMER_NORESTART; } /** * pm_schedule_suspend - Set up a timer to submit a suspend request in future. * @dev: Device to suspend. * @delay: Time to wait before submitting a suspend request, in milliseconds. */ int pm_schedule_suspend(struct device *dev, unsigned int delay) { unsigned long flags; u64 expires; int retval; spin_lock_irqsave(&dev->power.lock, flags); if (!delay) { retval = rpm_suspend(dev, RPM_ASYNC); goto out; } retval = rpm_check_suspend_allowed(dev); if (retval) goto out; /* Other scheduled or pending requests need to be canceled. */ pm_runtime_cancel_pending(dev); expires = ktime_get_mono_fast_ns() + (u64)delay * NSEC_PER_MSEC; dev->power.timer_expires = expires; dev->power.timer_autosuspends = 0; hrtimer_start(&dev->power.suspend_timer, expires, HRTIMER_MODE_ABS); out: spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(pm_schedule_suspend); static int rpm_drop_usage_count(struct device *dev) { int ret; ret = atomic_sub_return(1, &dev->power.usage_count); if (ret >= 0) return ret; /* * Because rpm_resume() does not check the usage counter, it will resume * the device even if the usage counter is 0 or negative, so it is * sufficient to increment the usage counter here to reverse the change * made above. */ atomic_inc(&dev->power.usage_count); dev_warn(dev, "Runtime PM usage count underflow!\n"); return -EINVAL; } /** * __pm_runtime_idle - Entry point for runtime idle operations. * @dev: Device to send idle notification for. * @rpmflags: Flag bits. * * If the RPM_GET_PUT flag is set, decrement the device's usage count and * return immediately if it is larger than zero (if it becomes negative, log a * warning, increment it, and return an error). Then carry out an idle * notification, either synchronous or asynchronous. * * This routine may be called in atomic context if the RPM_ASYNC flag is set, * or if pm_runtime_irq_safe() has been called. */ int __pm_runtime_idle(struct device *dev, int rpmflags) { unsigned long flags; int retval; if (rpmflags & RPM_GET_PUT) { retval = rpm_drop_usage_count(dev); if (retval < 0) { return retval; } else if (retval > 0) { trace_rpm_usage(dev, rpmflags); return 0; } } might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_idle(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(__pm_runtime_idle); /** * __pm_runtime_suspend - Entry point for runtime put/suspend operations. * @dev: Device to suspend. * @rpmflags: Flag bits. * * If the RPM_GET_PUT flag is set, decrement the device's usage count and * return immediately if it is larger than zero (if it becomes negative, log a * warning, increment it, and return an error). Then carry out a suspend, * either synchronous or asynchronous. * * This routine may be called in atomic context if the RPM_ASYNC flag is set, * or if pm_runtime_irq_safe() has been called. */ int __pm_runtime_suspend(struct device *dev, int rpmflags) { unsigned long flags; int retval; if (rpmflags & RPM_GET_PUT) { retval = rpm_drop_usage_count(dev); if (retval < 0) { return retval; } else if (retval > 0) { trace_rpm_usage(dev, rpmflags); return 0; } } might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_suspend(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(__pm_runtime_suspend); /** * __pm_runtime_resume - Entry point for runtime resume operations. * @dev: Device to resume. * @rpmflags: Flag bits. * * If the RPM_GET_PUT flag is set, increment the device's usage count. Then * carry out a resume, either synchronous or asynchronous. * * This routine may be called in atomic context if the RPM_ASYNC flag is set, * or if pm_runtime_irq_safe() has been called. */ int __pm_runtime_resume(struct device *dev, int rpmflags) { unsigned long flags; int retval; might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe && dev->power.runtime_status != RPM_ACTIVE); if (rpmflags & RPM_GET_PUT) atomic_inc(&dev->power.usage_count); spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_resume(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(__pm_runtime_resume); /** * pm_runtime_get_conditional - Conditionally bump up device usage counter. * @dev: Device to handle. * @ign_usage_count: Whether or not to look at the current usage counter value. * * Return -EINVAL if runtime PM is disabled for @dev. * * Otherwise, if the runtime PM status of @dev is %RPM_ACTIVE and either * @ign_usage_count is %true or the runtime PM usage counter of @dev is not * zero, increment the usage counter of @dev and return 1. Otherwise, return 0 * without changing the usage counter. * * If @ign_usage_count is %true, this function can be used to prevent suspending * the device when its runtime PM status is %RPM_ACTIVE. * * If @ign_usage_count is %false, this function can be used to prevent * suspending the device when both its runtime PM status is %RPM_ACTIVE and its * runtime PM usage counter is not zero. * * The caller is responsible for decrementing the runtime PM usage counter of * @dev after this function has returned a positive value for it. */ static int pm_runtime_get_conditional(struct device *dev, bool ign_usage_count) { unsigned long flags; int retval; spin_lock_irqsave(&dev->power.lock, flags); if (dev->power.disable_depth > 0) { retval = -EINVAL; } else if (dev->power.runtime_status != RPM_ACTIVE) { retval = 0; } else if (ign_usage_count) { retval = 1; atomic_inc(&dev->power.usage_count); } else { retval = atomic_inc_not_zero(&dev->power.usage_count); } trace_rpm_usage(dev, 0); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } /** * pm_runtime_get_if_active - Bump up runtime PM usage counter if the device is * in active state * @dev: Target device. * * Increment the runtime PM usage counter of @dev if its runtime PM status is * %RPM_ACTIVE, in which case it returns 1. If the device is in a different * state, 0 is returned. -EINVAL is returned if runtime PM is disabled for the * device, in which case also the usage_count will remain unmodified. */ int pm_runtime_get_if_active(struct device *dev) { return pm_runtime_get_conditional(dev, true); } EXPORT_SYMBOL_GPL(pm_runtime_get_if_active); /** * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter. * @dev: Target device. * * Increment the runtime PM usage counter of @dev if its runtime PM status is * %RPM_ACTIVE and its runtime PM usage counter is greater than 0, in which case * it returns 1. If the device is in a different state or its usage_count is 0, * 0 is returned. -EINVAL is returned if runtime PM is disabled for the device, * in which case also the usage_count will remain unmodified. */ int pm_runtime_get_if_in_use(struct device *dev) { return pm_runtime_get_conditional(dev, false); } EXPORT_SYMBOL_GPL(pm_runtime_get_if_in_use); /** * __pm_runtime_set_status - Set runtime PM status of a device. * @dev: Device to handle. * @status: New runtime PM status of the device. * * If runtime PM of the device is disabled or its power.runtime_error field is * different from zero, the status may be changed either to RPM_ACTIVE, or to * RPM_SUSPENDED, as long as that reflects the actual state of the device. * However, if the device has a parent and the parent is not active, and the * parent's power.ignore_children flag is unset, the device's status cannot be * set to RPM_ACTIVE, so -EBUSY is returned in that case. * * If successful, __pm_runtime_set_status() clears the power.runtime_error field * and the device parent's counter of unsuspended children is modified to * reflect the new status. If the new status is RPM_SUSPENDED, an idle * notification request for the parent is submitted. * * If @dev has any suppliers (as reflected by device links to them), and @status * is RPM_ACTIVE, they will be activated upfront and if the activation of one * of them fails, the status of @dev will be changed to RPM_SUSPENDED (instead * of the @status value) and the suppliers will be deacticated on exit. The * error returned by the failing supplier activation will be returned in that * case. */ int __pm_runtime_set_status(struct device *dev, unsigned int status) { struct device *parent = dev->parent; bool notify_parent = false; unsigned long flags; int error = 0; if (status != RPM_ACTIVE && status != RPM_SUSPENDED) return -EINVAL; spin_lock_irqsave(&dev->power.lock, flags); /* * Prevent PM-runtime from being enabled for the device or return an * error if it is enabled already and working. */ if (dev->power.runtime_error || dev->power.disable_depth) dev->power.disable_depth++; else error = -EAGAIN; spin_unlock_irqrestore(&dev->power.lock, flags); if (error) return error; /* * If the new status is RPM_ACTIVE, the suppliers can be activated * upfront regardless of the current status, because next time * rpm_put_suppliers() runs, the rpm_active refcounts of the links * involved will be dropped down to one anyway. */ if (status == RPM_ACTIVE) { int idx = device_links_read_lock(); error = rpm_get_suppliers(dev); if (error) status = RPM_SUSPENDED; device_links_read_unlock(idx); } spin_lock_irqsave(&dev->power.lock, flags); if (dev->power.runtime_status == status || !parent) goto out_set; if (status == RPM_SUSPENDED) { atomic_add_unless(&parent->power.child_count, -1, 0); notify_parent = !parent->power.ignore_children; } else { spin_lock_nested(&parent->power.lock, SINGLE_DEPTH_NESTING); /* * It is invalid to put an active child under a parent that is * not active, has runtime PM enabled and the * 'power.ignore_children' flag unset. */ if (!parent->power.disable_depth && !parent->power.ignore_children && parent->power.runtime_status != RPM_ACTIVE) { dev_err(dev, "runtime PM trying to activate child device %s but parent (%s) is not active\n", dev_name(dev), dev_name(parent)); error = -EBUSY; } else if (dev->power.runtime_status == RPM_SUSPENDED) { atomic_inc(&parent->power.child_count); } spin_unlock(&parent->power.lock); if (error) { status = RPM_SUSPENDED; goto out; } } out_set: __update_runtime_status(dev, status); if (!error) dev->power.runtime_error = 0; out: spin_unlock_irqrestore(&dev->power.lock, flags); if (notify_parent) pm_request_idle(parent); if (status == RPM_SUSPENDED) { int idx = device_links_read_lock(); rpm_put_suppliers(dev); device_links_read_unlock(idx); } pm_runtime_enable(dev); return error; } EXPORT_SYMBOL_GPL(__pm_runtime_set_status); /** * __pm_runtime_barrier - Cancel pending requests and wait for completions. * @dev: Device to handle. * * Flush all pending requests for the device from pm_wq and wait for all * runtime PM operations involving the device in progress to complete. * * Should be called under dev->power.lock with interrupts disabled. */ static void __pm_runtime_barrier(struct device *dev) { pm_runtime_deactivate_timer(dev); if (dev->power.request_pending) { dev->power.request = RPM_REQ_NONE; spin_unlock_irq(&dev->power.lock); cancel_work_sync(&dev->power.work); spin_lock_irq(&dev->power.lock); dev->power.request_pending = false; } if (dev->power.runtime_status == RPM_SUSPENDING || dev->power.runtime_status == RPM_RESUMING || dev->power.idle_notification) { DEFINE_WAIT(wait); /* Suspend, wake-up or idle notification in progress. */ for (;;) { prepare_to_wait(&dev->power.wait_queue, &wait, TASK_UNINTERRUPTIBLE); if (dev->power.runtime_status != RPM_SUSPENDING && dev->power.runtime_status != RPM_RESUMING && !dev->power.idle_notification) break; spin_unlock_irq(&dev->power.lock); schedule(); spin_lock_irq(&dev->power.lock); } finish_wait(&dev->power.wait_queue, &wait); } } /** * pm_runtime_barrier - Flush pending requests and wait for completions. * @dev: Device to handle. * * Prevent the device from being suspended by incrementing its usage counter and * if there's a pending resume request for the device, wake the device up. * Next, make sure that all pending requests for the device have been flushed * from pm_wq and wait for all runtime PM operations involving the device in * progress to complete. * * Return value: * 1, if there was a resume request pending and the device had to be woken up, * 0, otherwise */ int pm_runtime_barrier(struct device *dev) { int retval = 0; pm_runtime_get_noresume(dev); spin_lock_irq(&dev->power.lock); if (dev->power.request_pending && dev->power.request == RPM_REQ_RESUME) { rpm_resume(dev, 0); retval = 1; } __pm_runtime_barrier(dev); spin_unlock_irq(&dev->power.lock); pm_runtime_put_noidle(dev); return retval; } EXPORT_SYMBOL_GPL(pm_runtime_barrier); /** * __pm_runtime_disable - Disable runtime PM of a device. * @dev: Device to handle. * @check_resume: If set, check if there's a resume request for the device. * * Increment power.disable_depth for the device and if it was zero previously, * cancel all pending runtime PM requests for the device and wait for all * operations in progress to complete. The device can be either active or * suspended after its runtime PM has been disabled. * * If @check_resume is set and there's a resume request pending when * __pm_runtime_disable() is called and power.disable_depth is zero, the * function will wake up the device before disabling its runtime PM. */ void __pm_runtime_disable(struct device *dev, bool check_resume) { spin_lock_irq(&dev->power.lock); if (dev->power.disable_depth > 0) { dev->power.disable_depth++; goto out; } /* * Wake up the device if there's a resume request pending, because that * means there probably is some I/O to process and disabling runtime PM * shouldn't prevent the device from processing the I/O. */ if (check_resume && dev->power.request_pending && dev->power.request == RPM_REQ_RESUME) { /* * Prevent suspends and idle notifications from being carried * out after we have woken up the device. */ pm_runtime_get_noresume(dev); rpm_resume(dev, 0); pm_runtime_put_noidle(dev); } /* Update time accounting before disabling PM-runtime. */ update_pm_runtime_accounting(dev); if (!dev->power.disable_depth++) { __pm_runtime_barrier(dev); dev->power.last_status = dev->power.runtime_status; } out: spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(__pm_runtime_disable); /** * pm_runtime_enable - Enable runtime PM of a device. * @dev: Device to handle. */ void pm_runtime_enable(struct device *dev) { unsigned long flags; spin_lock_irqsave(&dev->power.lock, flags); if (!dev->power.disable_depth) { dev_warn(dev, "Unbalanced %s!\n", __func__); goto out; } if (--dev->power.disable_depth > 0) goto out; dev->power.last_status = RPM_INVALID; dev->power.accounting_timestamp = ktime_get_mono_fast_ns(); if (dev->power.runtime_status == RPM_SUSPENDED && !dev->power.ignore_children && atomic_read(&dev->power.child_count) > 0) dev_warn(dev, "Enabling runtime PM for inactive device with active children\n"); out: spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_runtime_enable); static void pm_runtime_disable_action(void *data) { pm_runtime_dont_use_autosuspend(data); pm_runtime_disable(data); } /** * devm_pm_runtime_enable - devres-enabled version of pm_runtime_enable. * * NOTE: this will also handle calling pm_runtime_dont_use_autosuspend() for * you at driver exit time if needed. * * @dev: Device to handle. */ int devm_pm_runtime_enable(struct device *dev) { pm_runtime_enable(dev); return devm_add_action_or_reset(dev, pm_runtime_disable_action, dev); } EXPORT_SYMBOL_GPL(devm_pm_runtime_enable); /** * pm_runtime_forbid - Block runtime PM of a device. * @dev: Device to handle. * * Increase the device's usage count and clear its power.runtime_auto flag, * so that it cannot be suspended at run time until pm_runtime_allow() is called * for it. */ void pm_runtime_forbid(struct device *dev) { spin_lock_irq(&dev->power.lock); if (!dev->power.runtime_auto) goto out; dev->power.runtime_auto = false; atomic_inc(&dev->power.usage_count); rpm_resume(dev, 0); out: spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(pm_runtime_forbid); /** * pm_runtime_allow - Unblock runtime PM of a device. * @dev: Device to handle. * * Decrease the device's usage count and set its power.runtime_auto flag. */ void pm_runtime_allow(struct device *dev) { int ret; spin_lock_irq(&dev->power.lock); if (dev->power.runtime_auto) goto out; dev->power.runtime_auto = true; ret = rpm_drop_usage_count(dev); if (ret == 0) rpm_idle(dev, RPM_AUTO | RPM_ASYNC); else if (ret > 0) trace_rpm_usage(dev, RPM_AUTO | RPM_ASYNC); out: spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(pm_runtime_allow); /** * pm_runtime_no_callbacks - Ignore runtime PM callbacks for a device. * @dev: Device to handle. * * Set the power.no_callbacks flag, which tells the PM core that this * device is power-managed through its parent and has no runtime PM * callbacks of its own. The runtime sysfs attributes will be removed. */ void pm_runtime_no_callbacks(struct device *dev) { spin_lock_irq(&dev->power.lock); dev->power.no_callbacks = 1; spin_unlock_irq(&dev->power.lock); if (device_is_registered(dev)) rpm_sysfs_remove(dev); } EXPORT_SYMBOL_GPL(pm_runtime_no_callbacks); /** * pm_runtime_irq_safe - Leave interrupts disabled during callbacks. * @dev: Device to handle * * Set the power.irq_safe flag, which tells the PM core that the * ->runtime_suspend() and ->runtime_resume() callbacks for this device should * always be invoked with the spinlock held and interrupts disabled. It also * causes the parent's usage counter to be permanently incremented, preventing * the parent from runtime suspending -- otherwise an irq-safe child might have * to wait for a non-irq-safe parent. */ void pm_runtime_irq_safe(struct device *dev) { if (dev->parent) pm_runtime_get_sync(dev->parent); spin_lock_irq(&dev->power.lock); dev->power.irq_safe = 1; spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(pm_runtime_irq_safe); /** * update_autosuspend - Handle a change to a device's autosuspend settings. * @dev: Device to handle. * @old_delay: The former autosuspend_delay value. * @old_use: The former use_autosuspend value. * * Prevent runtime suspend if the new delay is negative and use_autosuspend is * set; otherwise allow it. Send an idle notification if suspends are allowed. * * This function must be called under dev->power.lock with interrupts disabled. */ static void update_autosuspend(struct device *dev, int old_delay, int old_use) { int delay = dev->power.autosuspend_delay; /* Should runtime suspend be prevented now? */ if (dev->power.use_autosuspend && delay < 0) { /* If it used to be allowed then prevent it. */ if (!old_use || old_delay >= 0) { atomic_inc(&dev->power.usage_count); rpm_resume(dev, 0); } else { trace_rpm_usage(dev, 0); } } /* Runtime suspend should be allowed now. */ else { /* If it used to be prevented then allow it. */ if (old_use && old_delay < 0) atomic_dec(&dev->power.usage_count); /* Maybe we can autosuspend now. */ rpm_idle(dev, RPM_AUTO); } } /** * pm_runtime_set_autosuspend_delay - Set a device's autosuspend_delay value. * @dev: Device to handle. * @delay: Value of the new delay in milliseconds. * * Set the device's power.autosuspend_delay value. If it changes to negative * and the power.use_autosuspend flag is set, prevent runtime suspends. If it * changes the other way, allow runtime suspends. */ void pm_runtime_set_autosuspend_delay(struct device *dev, int delay) { int old_delay, old_use; spin_lock_irq(&dev->power.lock); old_delay = dev->power.autosuspend_delay; old_use = dev->power.use_autosuspend; dev->power.autosuspend_delay = delay; update_autosuspend(dev, old_delay, old_use); spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(pm_runtime_set_autosuspend_delay); /** * __pm_runtime_use_autosuspend - Set a device's use_autosuspend flag. * @dev: Device to handle. * @use: New value for use_autosuspend. * * Set the device's power.use_autosuspend flag, and allow or prevent runtime * suspends as needed. */ void __pm_runtime_use_autosuspend(struct device *dev, bool use) { int old_delay, old_use; spin_lock_irq(&dev->power.lock); old_delay = dev->power.autosuspend_delay; old_use = dev->power.use_autosuspend; dev->power.use_autosuspend = use; update_autosuspend(dev, old_delay, old_use); spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(__pm_runtime_use_autosuspend); /** * pm_runtime_init - Initialize runtime PM fields in given device object. * @dev: Device object to initialize. */ void pm_runtime_init(struct device *dev) { dev->power.runtime_status = RPM_SUSPENDED; dev->power.last_status = RPM_INVALID; dev->power.idle_notification = false; dev->power.disable_depth = 1; atomic_set(&dev->power.usage_count, 0); dev->power.runtime_error = 0; atomic_set(&dev->power.child_count, 0); pm_suspend_ignore_children(dev, false); dev->power.runtime_auto = true; dev->power.request_pending = false; dev->power.request = RPM_REQ_NONE; dev->power.deferred_resume = false; dev->power.needs_force_resume = 0; INIT_WORK(&dev->power.work, pm_runtime_work); dev->power.timer_expires = 0; hrtimer_init(&dev->power.suspend_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); dev->power.suspend_timer.function = pm_suspend_timer_fn; init_waitqueue_head(&dev->power.wait_queue); } /** * pm_runtime_reinit - Re-initialize runtime PM fields in given device object. * @dev: Device object to re-initialize. */ void pm_runtime_reinit(struct device *dev) { if (!pm_runtime_enabled(dev)) { if (dev->power.runtime_status == RPM_ACTIVE) pm_runtime_set_suspended(dev); if (dev->power.irq_safe) { spin_lock_irq(&dev->power.lock); dev->power.irq_safe = 0; spin_unlock_irq(&dev->power.lock); if (dev->parent) pm_runtime_put(dev->parent); } } } /** * pm_runtime_remove - Prepare for removing a device from device hierarchy. * @dev: Device object being removed from device hierarchy. */ void pm_runtime_remove(struct device *dev) { __pm_runtime_disable(dev, false); pm_runtime_reinit(dev); } /** * pm_runtime_get_suppliers - Resume and reference-count supplier devices. * @dev: Consumer device. */ void pm_runtime_get_suppliers(struct device *dev) { struct device_link *link; int idx; idx = device_links_read_lock(); list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) if (link->flags & DL_FLAG_PM_RUNTIME) { link->supplier_preactivated = true; pm_runtime_get_sync(link->supplier); } device_links_read_unlock(idx); } /** * pm_runtime_put_suppliers - Drop references to supplier devices. * @dev: Consumer device. */ void pm_runtime_put_suppliers(struct device *dev) { struct device_link *link; int idx; idx = device_links_read_lock(); list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) if (link->supplier_preactivated) { link->supplier_preactivated = false; pm_runtime_put(link->supplier); } device_links_read_unlock(idx); } void pm_runtime_new_link(struct device *dev) { spin_lock_irq(&dev->power.lock); dev->power.links_count++; spin_unlock_irq(&dev->power.lock); } static void pm_runtime_drop_link_count(struct device *dev) { spin_lock_irq(&dev->power.lock); WARN_ON(dev->power.links_count == 0); dev->power.links_count--; spin_unlock_irq(&dev->power.lock); } /** * pm_runtime_drop_link - Prepare for device link removal. * @link: Device link going away. * * Drop the link count of the consumer end of @link and decrement the supplier * device's runtime PM usage counter as many times as needed to drop all of the * PM runtime reference to it from the consumer. */ void pm_runtime_drop_link(struct device_link *link) { if (!(link->flags & DL_FLAG_PM_RUNTIME)) return; pm_runtime_drop_link_count(link->consumer); pm_runtime_release_supplier(link); pm_request_idle(link->supplier); } static bool pm_runtime_need_not_resume(struct device *dev) { return atomic_read(&dev->power.usage_count) <= 1 && (atomic_read(&dev->power.child_count) == 0 || dev->power.ignore_children); } /** * pm_runtime_force_suspend - Force a device into suspend state if needed. * @dev: Device to suspend. * * Disable runtime PM so we safely can check the device's runtime PM status and * if it is active, invoke its ->runtime_suspend callback to suspend it and * change its runtime PM status field to RPM_SUSPENDED. Also, if the device's * usage and children counters don't indicate that the device was in use before * the system-wide transition under way, decrement its parent's children counter * (if there is a parent). Keep runtime PM disabled to preserve the state * unless we encounter errors. * * Typically this function may be invoked from a system suspend callback to make * sure the device is put into low power state and it should only be used during * system-wide PM transitions to sleep states. It assumes that the analogous * pm_runtime_force_resume() will be used to resume the device. * * Do not use with DPM_FLAG_SMART_SUSPEND as this can lead to an inconsistent * state where this function has called the ->runtime_suspend callback but the * PM core marks the driver as runtime active. */ int pm_runtime_force_suspend(struct device *dev) { int (*callback)(struct device *); int ret; pm_runtime_disable(dev); if (pm_runtime_status_suspended(dev)) return 0; callback = RPM_GET_CALLBACK(dev, runtime_suspend); dev_pm_enable_wake_irq_check(dev, true); ret = callback ? callback(dev) : 0; if (ret) goto err; dev_pm_enable_wake_irq_complete(dev); /* * If the device can stay in suspend after the system-wide transition * to the working state that will follow, drop the children counter of * its parent, but set its status to RPM_SUSPENDED anyway in case this * function will be called again for it in the meantime. */ if (pm_runtime_need_not_resume(dev)) { pm_runtime_set_suspended(dev); } else { __update_runtime_status(dev, RPM_SUSPENDED); dev->power.needs_force_resume = 1; } return 0; err: dev_pm_disable_wake_irq_check(dev, true); pm_runtime_enable(dev); return ret; } EXPORT_SYMBOL_GPL(pm_runtime_force_suspend); /** * pm_runtime_force_resume - Force a device into resume state if needed. * @dev: Device to resume. * * Prior invoking this function we expect the user to have brought the device * into low power state by a call to pm_runtime_force_suspend(). Here we reverse * those actions and bring the device into full power, if it is expected to be * used on system resume. In the other case, we defer the resume to be managed * via runtime PM. * * Typically this function may be invoked from a system resume callback. */ int pm_runtime_force_resume(struct device *dev) { int (*callback)(struct device *); int ret = 0; if (!pm_runtime_status_suspended(dev) || !dev->power.needs_force_resume) goto out; /* * The value of the parent's children counter is correct already, so * just update the status of the device. */ __update_runtime_status(dev, RPM_ACTIVE); callback = RPM_GET_CALLBACK(dev, runtime_resume); dev_pm_disable_wake_irq_check(dev, false); ret = callback ? callback(dev) : 0; if (ret) { pm_runtime_set_suspended(dev); dev_pm_enable_wake_irq_check(dev, false); goto out; } pm_runtime_mark_last_busy(dev); out: dev->power.needs_force_resume = 0; pm_runtime_enable(dev); return ret; } EXPORT_SYMBOL_GPL(pm_runtime_force_resume); |
| 452 1 12 1 12 1007 1004 1 1003 1002 501 1467 714 719 713 68 719 140 152 168 165 5 5 5 168 182 167 140 168 2 168 182 6 6 6 182 182 180 181 182 24 24 24 173 9 9 9 9 9 9 171 172 173 2 172 147 147 147 147 7 173 170 173 173 173 7 44 13 212 243 68 107 8 8 8 8 1 1 8 1 8 7 107 87 8 8 86 7 7 86 4 2 4 3 1 1 3 15 38 15 187 9 1 1 1 1 181 182 181 1 182 181 9 181 180 9 181 182 182 181 186 186 187 187 187 12 187 12 187 186 187 185 186 184 185 2 187 187 186 187 187 185 187 186 185 187 187 185 186 187 186 75 187 187 9 187 186 187 128 185 1 187 127 187 184 187 187 187 187 186 30 179 186 186 187 1 1 187 187 1 1 187 187 187 185 186 186 12 185 7 185 185 186 187 185 186 187 187 184 187 187 187 187 186 186 186 184 186 186 186 187 186 187 185 186 185 187 187 187 185 185 186 187 186 8 186 152 152 187 187 187 187 186 187 24 173 187 184 185 31 187 187 187 187 187 185 187 187 12 12 12 187 187 7 8 8 8 8 8 3 3 1 1 1 9 9 10 10 9 2 8 8 2 1 1 10 2 7 8 8 8 8 8 1 1 1 1 2 4 2 2 2 4 115 2 113 112 1 115 114 115 212 16 212 212 209 1 1 1 184 6 185 1 182 2 1 184 1 1 183 1 182 2 183 2 183 7 6 6 6 6 184 11 1 1 1 10 1 1 9 2 2 2 1 1 7 1 1 1 6 2 1 4 1 1 3 1 2 1 1 1 1 1 1 1 12 1 12 1 1 12 7 5 1 5 4 1 1 1 1 62 6 57 61 2 3 2 1 1 1 1 1 61 61 4 4 2 58 6 4 55 3 56 1 1 56 1 56 56 18 55 6 4 54 1 52 2 2 53 53 1 1 53 1 1 1 53 2 1 53 2 1 53 3 53 53 12 12 11 11 11 11 1 41 1 12 39 2 1 1 38 5 4 4 38 5 32 5 8 5 5 4 3 3 2 2 2 2 38 37 20 7 14 62 23 15 23 19 19 18 16 18 14 4 4 18 17 19 9 9 9 1 10 10 10 10 9 10 8 7 2 5 10 3 9 9 63 61 24 59 2 60 48 111 5 107 14 112 111 15 19 1 14 110 109 110 111 1 109 3 1 2 109 2 109 1 109 1 108 108 1 106 109 1 109 108 106 109 111 1 3 3 3 111 112 112 9 101 111 112 111 3 109 109 96 66 61 44 44 6 69 88 7 7 195 196 194 192 67 126 1 126 15 82 62 1 192 154 39 193 152 154 39 153 151 151 139 152 146 172 175 2 2 2 177 60 60 60 28 24 24 44 1 44 122 8 3 3 3 115 113 3 1 1 3 112 195 195 174 4 4 3 1 1 1 1 1 1 4 4 4 3 3 1 1 2 2 1 1 1 2 1 1 1 2 3 3 1 3 1 2 1 4 4 4 4 4 3 1 1 4 3 3 3 3 1 1 2 2 14 14 13 1 1 1 1 1 1 11 11 11 11 11 11 11 11 11 11 11 11 11 11 180 179 13 178 178 179 176 176 160 175 176 160 155 2 2 2 1 2 1 1 1 1 1 1 1 1 1 1 1 8 8 3 7 1 6 1 5 1 4 1 3 3 2 3 2 1 1 2 1 8 8 1 8 3 8 7 1 6 1 5 4 1 3 1 3 1 2 1 1 1 1 1 8 1 1 1 1 1 2 1 1 1 2 5 5 5 4 2 3 3 3 3 3 1 1 1 1 1 1 1 6 5 1 6 3 1 2 2 2 2 2 2 2 2 2 1 2 2 2 2 2 2 6 4 4 1 3 2 2 2 2 1 2 2 4 4 2 2 2 4 2 1 1 1 1 2 1 1 1 1 2 1 1 1 1 1 3 3 2 2 2 2 2 2 2 2 3 3 3 3 1 2 2 2 2 1 1 1 1 1 3 3 3 3 1 2 1 1 2 1 3 6 1 4 4 4 4 1 1 4 1 2 5 5 5 4 5 5 1 5 3 5 1 5 5 4 1 5 5 5 4 1 1 1 4 3 5 2 1 2 1 2 1 1 2 6 6 6 6 4 4 4 6 3 3 2 2 2 2 5 2 1 1 1 1 1 1 6 5 5 5 5 1 4 4 4 4 4 4 6 3 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 6 5 5 6 9 10 10 1 1 2 2 2 2 1 1 2 1 1 1 6 5 5 6 4 4 4 3 4 4 4 1 1 1 1 1 2 2 1 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 2 2 2 4 4 4 1 1 3 1 2 2 3 1 4 3 3 1 1 3 2 2 1 1 1 2 1 4 2 3 3 1 1 4 14 14 14 2 1 10 9 75 719 713 567 719 713 74 71 3 3 74 14 75 74 75 75 646 608 47 46 647 651 90 6 646 59 59 59 58 596 590 591 567 693 1 716 3 2 3 75 194 75 197 3 3 3 | 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 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Routing netlink socket interface: protocol independent part. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Fixes: * Vitaly E. Lavrov RTA_OK arithmetic was wrong. */ #include <linux/bitops.h> #include <linux/errno.h> #include <linux/module.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/kernel.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/fcntl.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/capability.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/security.h> #include <linux/mutex.h> #include <linux/if_addr.h> #include <linux/if_bridge.h> #include <linux/if_vlan.h> #include <linux/pci.h> #include <linux/etherdevice.h> #include <linux/bpf.h> #include <linux/uaccess.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <net/ip.h> #include <net/protocol.h> #include <net/arp.h> #include <net/route.h> #include <net/udp.h> #include <net/tcp.h> #include <net/sock.h> #include <net/pkt_sched.h> #include <net/fib_rules.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/devlink.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/addrconf.h> #endif #include <linux/dpll.h> #include "dev.h" #define RTNL_MAX_TYPE 50 #define RTNL_SLAVE_MAX_TYPE 44 struct rtnl_link { rtnl_doit_func doit; rtnl_dumpit_func dumpit; struct module *owner; unsigned int flags; struct rcu_head rcu; }; static DEFINE_MUTEX(rtnl_mutex); void rtnl_lock(void) { mutex_lock(&rtnl_mutex); } EXPORT_SYMBOL(rtnl_lock); int rtnl_lock_killable(void) { return mutex_lock_killable(&rtnl_mutex); } EXPORT_SYMBOL(rtnl_lock_killable); static struct sk_buff *defer_kfree_skb_list; void rtnl_kfree_skbs(struct sk_buff *head, struct sk_buff *tail) { if (head && tail) { tail->next = defer_kfree_skb_list; defer_kfree_skb_list = head; } } EXPORT_SYMBOL(rtnl_kfree_skbs); void __rtnl_unlock(void) { struct sk_buff *head = defer_kfree_skb_list; defer_kfree_skb_list = NULL; /* Ensure that we didn't actually add any TODO item when __rtnl_unlock() * is used. In some places, e.g. in cfg80211, we have code that will do * something like * rtnl_lock() * wiphy_lock() * ... * rtnl_unlock() * * and because netdev_run_todo() acquires the RTNL for items on the list * we could cause a situation such as this: * Thread 1 Thread 2 * rtnl_lock() * unregister_netdevice() * __rtnl_unlock() * rtnl_lock() * wiphy_lock() * rtnl_unlock() * netdev_run_todo() * __rtnl_unlock() * * // list not empty now * // because of thread 2 * rtnl_lock() * while (!list_empty(...)) * rtnl_lock() * wiphy_lock() * **** DEADLOCK **** * * However, usage of __rtnl_unlock() is rare, and so we can ensure that * it's not used in cases where something is added to do the list. */ WARN_ON(!list_empty(&net_todo_list)); mutex_unlock(&rtnl_mutex); while (head) { struct sk_buff *next = head->next; kfree_skb(head); cond_resched(); head = next; } } void rtnl_unlock(void) { /* This fellow will unlock it for us. */ netdev_run_todo(); } EXPORT_SYMBOL(rtnl_unlock); int rtnl_trylock(void) { return mutex_trylock(&rtnl_mutex); } EXPORT_SYMBOL(rtnl_trylock); int rtnl_is_locked(void) { return mutex_is_locked(&rtnl_mutex); } EXPORT_SYMBOL(rtnl_is_locked); bool refcount_dec_and_rtnl_lock(refcount_t *r) { return refcount_dec_and_mutex_lock(r, &rtnl_mutex); } EXPORT_SYMBOL(refcount_dec_and_rtnl_lock); #ifdef CONFIG_PROVE_LOCKING bool lockdep_rtnl_is_held(void) { return lockdep_is_held(&rtnl_mutex); } EXPORT_SYMBOL(lockdep_rtnl_is_held); #endif /* #ifdef CONFIG_PROVE_LOCKING */ static struct rtnl_link __rcu *__rcu *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1]; static inline int rtm_msgindex(int msgtype) { int msgindex = msgtype - RTM_BASE; /* * msgindex < 0 implies someone tried to register a netlink * control code. msgindex >= RTM_NR_MSGTYPES may indicate that * the message type has not been added to linux/rtnetlink.h */ BUG_ON(msgindex < 0 || msgindex >= RTM_NR_MSGTYPES); return msgindex; } static struct rtnl_link *rtnl_get_link(int protocol, int msgtype) { struct rtnl_link __rcu **tab; if (protocol >= ARRAY_SIZE(rtnl_msg_handlers)) protocol = PF_UNSPEC; tab = rcu_dereference_rtnl(rtnl_msg_handlers[protocol]); if (!tab) tab = rcu_dereference_rtnl(rtnl_msg_handlers[PF_UNSPEC]); return rcu_dereference_rtnl(tab[msgtype]); } static int rtnl_register_internal(struct module *owner, int protocol, int msgtype, rtnl_doit_func doit, rtnl_dumpit_func dumpit, unsigned int flags) { struct rtnl_link *link, *old; struct rtnl_link __rcu **tab; int msgindex; int ret = -ENOBUFS; BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); msgindex = rtm_msgindex(msgtype); rtnl_lock(); tab = rtnl_dereference(rtnl_msg_handlers[protocol]); if (tab == NULL) { tab = kcalloc(RTM_NR_MSGTYPES, sizeof(void *), GFP_KERNEL); if (!tab) goto unlock; /* ensures we see the 0 stores */ rcu_assign_pointer(rtnl_msg_handlers[protocol], tab); } old = rtnl_dereference(tab[msgindex]); if (old) { link = kmemdup(old, sizeof(*old), GFP_KERNEL); if (!link) goto unlock; } else { link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) goto unlock; } WARN_ON(link->owner && link->owner != owner); link->owner = owner; WARN_ON(doit && link->doit && link->doit != doit); if (doit) link->doit = doit; WARN_ON(dumpit && link->dumpit && link->dumpit != dumpit); if (dumpit) link->dumpit = dumpit; WARN_ON(rtnl_msgtype_kind(msgtype) != RTNL_KIND_DEL && (flags & RTNL_FLAG_BULK_DEL_SUPPORTED)); link->flags |= flags; /* publish protocol:msgtype */ rcu_assign_pointer(tab[msgindex], link); ret = 0; if (old) kfree_rcu(old, rcu); unlock: rtnl_unlock(); return ret; } /** * rtnl_register_module - Register a rtnetlink message type * * @owner: module registering the hook (THIS_MODULE) * @protocol: Protocol family or PF_UNSPEC * @msgtype: rtnetlink message type * @doit: Function pointer called for each request message * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message * @flags: rtnl_link_flags to modify behaviour of doit/dumpit functions * * Like rtnl_register, but for use by removable modules. */ int rtnl_register_module(struct module *owner, int protocol, int msgtype, rtnl_doit_func doit, rtnl_dumpit_func dumpit, unsigned int flags) { return rtnl_register_internal(owner, protocol, msgtype, doit, dumpit, flags); } EXPORT_SYMBOL_GPL(rtnl_register_module); /** * rtnl_register - Register a rtnetlink message type * @protocol: Protocol family or PF_UNSPEC * @msgtype: rtnetlink message type * @doit: Function pointer called for each request message * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message * @flags: rtnl_link_flags to modify behaviour of doit/dumpit functions * * Registers the specified function pointers (at least one of them has * to be non-NULL) to be called whenever a request message for the * specified protocol family and message type is received. * * The special protocol family PF_UNSPEC may be used to define fallback * function pointers for the case when no entry for the specific protocol * family exists. */ void rtnl_register(int protocol, int msgtype, rtnl_doit_func doit, rtnl_dumpit_func dumpit, unsigned int flags) { int err; err = rtnl_register_internal(NULL, protocol, msgtype, doit, dumpit, flags); if (err) pr_err("Unable to register rtnetlink message handler, " "protocol = %d, message type = %d\n", protocol, msgtype); } /** * rtnl_unregister - Unregister a rtnetlink message type * @protocol: Protocol family or PF_UNSPEC * @msgtype: rtnetlink message type * * Returns 0 on success or a negative error code. */ int rtnl_unregister(int protocol, int msgtype) { struct rtnl_link __rcu **tab; struct rtnl_link *link; int msgindex; BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); msgindex = rtm_msgindex(msgtype); rtnl_lock(); tab = rtnl_dereference(rtnl_msg_handlers[protocol]); if (!tab) { rtnl_unlock(); return -ENOENT; } link = rcu_replace_pointer_rtnl(tab[msgindex], NULL); rtnl_unlock(); kfree_rcu(link, rcu); return 0; } EXPORT_SYMBOL_GPL(rtnl_unregister); /** * rtnl_unregister_all - Unregister all rtnetlink message type of a protocol * @protocol : Protocol family or PF_UNSPEC * * Identical to calling rtnl_unregster() for all registered message types * of a certain protocol family. */ void rtnl_unregister_all(int protocol) { struct rtnl_link __rcu **tab; struct rtnl_link *link; int msgindex; BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); rtnl_lock(); tab = rcu_replace_pointer_rtnl(rtnl_msg_handlers[protocol], NULL); if (!tab) { rtnl_unlock(); return; } for (msgindex = 0; msgindex < RTM_NR_MSGTYPES; msgindex++) { link = rcu_replace_pointer_rtnl(tab[msgindex], NULL); kfree_rcu(link, rcu); } rtnl_unlock(); synchronize_net(); kfree(tab); } EXPORT_SYMBOL_GPL(rtnl_unregister_all); static LIST_HEAD(link_ops); static const struct rtnl_link_ops *rtnl_link_ops_get(const char *kind) { const struct rtnl_link_ops *ops; list_for_each_entry(ops, &link_ops, list) { if (!strcmp(ops->kind, kind)) return ops; } return NULL; } /** * __rtnl_link_register - Register rtnl_link_ops with rtnetlink. * @ops: struct rtnl_link_ops * to register * * The caller must hold the rtnl_mutex. This function should be used * by drivers that create devices during module initialization. It * must be called before registering the devices. * * Returns 0 on success or a negative error code. */ int __rtnl_link_register(struct rtnl_link_ops *ops) { if (rtnl_link_ops_get(ops->kind)) return -EEXIST; /* The check for alloc/setup is here because if ops * does not have that filled up, it is not possible * to use the ops for creating device. So do not * fill up dellink as well. That disables rtnl_dellink. */ if ((ops->alloc || ops->setup) && !ops->dellink) ops->dellink = unregister_netdevice_queue; list_add_tail(&ops->list, &link_ops); return 0; } EXPORT_SYMBOL_GPL(__rtnl_link_register); /** * rtnl_link_register - Register rtnl_link_ops with rtnetlink. * @ops: struct rtnl_link_ops * to register * * Returns 0 on success or a negative error code. */ int rtnl_link_register(struct rtnl_link_ops *ops) { int err; /* Sanity-check max sizes to avoid stack buffer overflow. */ if (WARN_ON(ops->maxtype > RTNL_MAX_TYPE || ops->slave_maxtype > RTNL_SLAVE_MAX_TYPE)) return -EINVAL; rtnl_lock(); err = __rtnl_link_register(ops); rtnl_unlock(); return err; } EXPORT_SYMBOL_GPL(rtnl_link_register); static void __rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops) { struct net_device *dev; LIST_HEAD(list_kill); for_each_netdev(net, dev) { if (dev->rtnl_link_ops == ops) ops->dellink(dev, &list_kill); } unregister_netdevice_many(&list_kill); } /** * __rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink. * @ops: struct rtnl_link_ops * to unregister * * The caller must hold the rtnl_mutex and guarantee net_namespace_list * integrity (hold pernet_ops_rwsem for writing to close the race * with setup_net() and cleanup_net()). */ void __rtnl_link_unregister(struct rtnl_link_ops *ops) { struct net *net; for_each_net(net) { __rtnl_kill_links(net, ops); } list_del(&ops->list); } EXPORT_SYMBOL_GPL(__rtnl_link_unregister); /* Return with the rtnl_lock held when there are no network * devices unregistering in any network namespace. */ static void rtnl_lock_unregistering_all(void) { DEFINE_WAIT_FUNC(wait, woken_wake_function); add_wait_queue(&netdev_unregistering_wq, &wait); for (;;) { rtnl_lock(); /* We held write locked pernet_ops_rwsem, and parallel * setup_net() and cleanup_net() are not possible. */ if (!atomic_read(&dev_unreg_count)) break; __rtnl_unlock(); wait_woken(&wait, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); } remove_wait_queue(&netdev_unregistering_wq, &wait); } /** * rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink. * @ops: struct rtnl_link_ops * to unregister */ void rtnl_link_unregister(struct rtnl_link_ops *ops) { /* Close the race with setup_net() and cleanup_net() */ down_write(&pernet_ops_rwsem); rtnl_lock_unregistering_all(); __rtnl_link_unregister(ops); rtnl_unlock(); up_write(&pernet_ops_rwsem); } EXPORT_SYMBOL_GPL(rtnl_link_unregister); static size_t rtnl_link_get_slave_info_data_size(const struct net_device *dev) { struct net_device *master_dev; const struct rtnl_link_ops *ops; size_t size = 0; rcu_read_lock(); master_dev = netdev_master_upper_dev_get_rcu((struct net_device *)dev); if (!master_dev) goto out; ops = master_dev->rtnl_link_ops; if (!ops || !ops->get_slave_size) goto out; /* IFLA_INFO_SLAVE_DATA + nested data */ size = nla_total_size(sizeof(struct nlattr)) + ops->get_slave_size(master_dev, dev); out: rcu_read_unlock(); return size; } static size_t rtnl_link_get_size(const struct net_device *dev) { const struct rtnl_link_ops *ops = dev->rtnl_link_ops; size_t size; if (!ops) return 0; size = nla_total_size(sizeof(struct nlattr)) + /* IFLA_LINKINFO */ nla_total_size(strlen(ops->kind) + 1); /* IFLA_INFO_KIND */ if (ops->get_size) /* IFLA_INFO_DATA + nested data */ size += nla_total_size(sizeof(struct nlattr)) + ops->get_size(dev); if (ops->get_xstats_size) /* IFLA_INFO_XSTATS */ size += nla_total_size(ops->get_xstats_size(dev)); size += rtnl_link_get_slave_info_data_size(dev); return size; } static LIST_HEAD(rtnl_af_ops); static const struct rtnl_af_ops *rtnl_af_lookup(const int family) { const struct rtnl_af_ops *ops; ASSERT_RTNL(); list_for_each_entry(ops, &rtnl_af_ops, list) { if (ops->family == family) return ops; } return NULL; } /** * rtnl_af_register - Register rtnl_af_ops with rtnetlink. * @ops: struct rtnl_af_ops * to register * * Returns 0 on success or a negative error code. */ void rtnl_af_register(struct rtnl_af_ops *ops) { rtnl_lock(); list_add_tail_rcu(&ops->list, &rtnl_af_ops); rtnl_unlock(); } EXPORT_SYMBOL_GPL(rtnl_af_register); /** * rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink. * @ops: struct rtnl_af_ops * to unregister */ void rtnl_af_unregister(struct rtnl_af_ops *ops) { rtnl_lock(); list_del_rcu(&ops->list); rtnl_unlock(); synchronize_rcu(); } EXPORT_SYMBOL_GPL(rtnl_af_unregister); static size_t rtnl_link_get_af_size(const struct net_device *dev, u32 ext_filter_mask) { struct rtnl_af_ops *af_ops; size_t size; /* IFLA_AF_SPEC */ size = nla_total_size(sizeof(struct nlattr)); rcu_read_lock(); list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) { if (af_ops->get_link_af_size) { /* AF_* + nested data */ size += nla_total_size(sizeof(struct nlattr)) + af_ops->get_link_af_size(dev, ext_filter_mask); } } rcu_read_unlock(); return size; } static bool rtnl_have_link_slave_info(const struct net_device *dev) { struct net_device *master_dev; bool ret = false; rcu_read_lock(); master_dev = netdev_master_upper_dev_get_rcu((struct net_device *)dev); if (master_dev && master_dev->rtnl_link_ops) ret = true; rcu_read_unlock(); return ret; } static int rtnl_link_slave_info_fill(struct sk_buff *skb, const struct net_device *dev) { struct net_device *master_dev; const struct rtnl_link_ops *ops; struct nlattr *slave_data; int err; master_dev = netdev_master_upper_dev_get((struct net_device *) dev); if (!master_dev) return 0; ops = master_dev->rtnl_link_ops; if (!ops) return 0; if (nla_put_string(skb, IFLA_INFO_SLAVE_KIND, ops->kind) < 0) return -EMSGSIZE; if (ops->fill_slave_info) { slave_data = nla_nest_start_noflag(skb, IFLA_INFO_SLAVE_DATA); if (!slave_data) return -EMSGSIZE; err = ops->fill_slave_info(skb, master_dev, dev); if (err < 0) goto err_cancel_slave_data; nla_nest_end(skb, slave_data); } return 0; err_cancel_slave_data: nla_nest_cancel(skb, slave_data); return err; } static int rtnl_link_info_fill(struct sk_buff *skb, const struct net_device *dev) { const struct rtnl_link_ops *ops = dev->rtnl_link_ops; struct nlattr *data; int err; if (!ops) return 0; if (nla_put_string(skb, IFLA_INFO_KIND, ops->kind) < 0) return -EMSGSIZE; if (ops->fill_xstats) { err = ops->fill_xstats(skb, dev); if (err < 0) return err; } if (ops->fill_info) { data = nla_nest_start_noflag(skb, IFLA_INFO_DATA); if (data == NULL) return -EMSGSIZE; err = ops->fill_info(skb, dev); if (err < 0) goto err_cancel_data; nla_nest_end(skb, data); } return 0; err_cancel_data: nla_nest_cancel(skb, data); return err; } static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev) { struct nlattr *linkinfo; int err = -EMSGSIZE; linkinfo = nla_nest_start_noflag(skb, IFLA_LINKINFO); if (linkinfo == NULL) goto out; err = rtnl_link_info_fill(skb, dev); if (err < 0) goto err_cancel_link; err = rtnl_link_slave_info_fill(skb, dev); if (err < 0) goto err_cancel_link; nla_nest_end(skb, linkinfo); return 0; err_cancel_link: nla_nest_cancel(skb, linkinfo); out: return err; } int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, int echo) { struct sock *rtnl = net->rtnl; return nlmsg_notify(rtnl, skb, pid, group, echo, GFP_KERNEL); } int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid) { struct sock *rtnl = net->rtnl; return nlmsg_unicast(rtnl, skb, pid); } EXPORT_SYMBOL(rtnl_unicast); void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, const struct nlmsghdr *nlh, gfp_t flags) { struct sock *rtnl = net->rtnl; nlmsg_notify(rtnl, skb, pid, group, nlmsg_report(nlh), flags); } EXPORT_SYMBOL(rtnl_notify); void rtnl_set_sk_err(struct net *net, u32 group, int error) { struct sock *rtnl = net->rtnl; netlink_set_err(rtnl, 0, group, error); } EXPORT_SYMBOL(rtnl_set_sk_err); int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) { struct nlattr *mx; int i, valid = 0; /* nothing is dumped for dst_default_metrics, so just skip the loop */ if (metrics == dst_default_metrics.metrics) return 0; mx = nla_nest_start_noflag(skb, RTA_METRICS); if (mx == NULL) return -ENOBUFS; for (i = 0; i < RTAX_MAX; i++) { if (metrics[i]) { if (i == RTAX_CC_ALGO - 1) { char tmp[TCP_CA_NAME_MAX], *name; name = tcp_ca_get_name_by_key(metrics[i], tmp); if (!name) continue; if (nla_put_string(skb, i + 1, name)) goto nla_put_failure; } else if (i == RTAX_FEATURES - 1) { u32 user_features = metrics[i] & RTAX_FEATURE_MASK; if (!user_features) continue; BUILD_BUG_ON(RTAX_FEATURE_MASK & DST_FEATURE_MASK); if (nla_put_u32(skb, i + 1, user_features)) goto nla_put_failure; } else { if (nla_put_u32(skb, i + 1, metrics[i])) goto nla_put_failure; } valid++; } } if (!valid) { nla_nest_cancel(skb, mx); return 0; } return nla_nest_end(skb, mx); nla_put_failure: nla_nest_cancel(skb, mx); return -EMSGSIZE; } EXPORT_SYMBOL(rtnetlink_put_metrics); int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, long expires, u32 error) { struct rta_cacheinfo ci = { .rta_error = error, .rta_id = id, }; if (dst) { ci.rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse); ci.rta_used = dst->__use; ci.rta_clntref = rcuref_read(&dst->__rcuref); } if (expires) { unsigned long clock; clock = jiffies_to_clock_t(abs(expires)); clock = min_t(unsigned long, clock, INT_MAX); ci.rta_expires = (expires > 0) ? clock : -clock; } return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci); } EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo); void netdev_set_operstate(struct net_device *dev, int newstate) { unsigned int old = READ_ONCE(dev->operstate); do { if (old == newstate) return; } while (!try_cmpxchg(&dev->operstate, &old, newstate)); netdev_state_change(dev); } EXPORT_SYMBOL(netdev_set_operstate); static void set_operstate(struct net_device *dev, unsigned char transition) { unsigned char operstate = READ_ONCE(dev->operstate); switch (transition) { case IF_OPER_UP: if ((operstate == IF_OPER_DORMANT || operstate == IF_OPER_TESTING || operstate == IF_OPER_UNKNOWN) && !netif_dormant(dev) && !netif_testing(dev)) operstate = IF_OPER_UP; break; case IF_OPER_TESTING: if (netif_oper_up(dev)) operstate = IF_OPER_TESTING; break; case IF_OPER_DORMANT: if (netif_oper_up(dev)) operstate = IF_OPER_DORMANT; break; } netdev_set_operstate(dev, operstate); } static unsigned int rtnl_dev_get_flags(const struct net_device *dev) { return (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI)) | (dev->gflags & (IFF_PROMISC | IFF_ALLMULTI)); } static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, const struct ifinfomsg *ifm) { unsigned int flags = ifm->ifi_flags; /* bugwards compatibility: ifi_change == 0 is treated as ~0 */ if (ifm->ifi_change) flags = (flags & ifm->ifi_change) | (rtnl_dev_get_flags(dev) & ~if |